diff options
Diffstat (limited to 'net/ipv4')
58 files changed, 1308 insertions, 1017 deletions
diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index 0c94a1ac2946..8e3a1fd938ab 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 @@ -587,9 +601,15 @@ choice config DEFAULT_HTCP bool "Htcp" if TCP_CONG_HTCP=y + config DEFAULT_HYBLA + bool "Hybla" if TCP_CONG_HYBLA=y + config DEFAULT_VEGAS bool "Vegas" if TCP_CONG_VEGAS=y + config DEFAULT_VENO + bool "Veno" if TCP_CONG_VENO=y + config DEFAULT_WESTWOOD bool "Westwood" if TCP_CONG_WESTWOOD=y @@ -610,8 +630,10 @@ config DEFAULT_TCP_CONG default "bic" if DEFAULT_BIC default "cubic" if DEFAULT_CUBIC default "htcp" if DEFAULT_HTCP + default "hybla" if DEFAULT_HYBLA default "vegas" if DEFAULT_VEGAS default "westwood" if DEFAULT_WESTWOOD + default "veno" if DEFAULT_VENO default "reno" if DEFAULT_RENO default "cubic" diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index f71357422380..551ce564b035 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -154,7 +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); @@ -419,6 +419,8 @@ int inet_release(struct socket *sock) if (sk) { long timeout; + sock_rps_reset_flow(sk); + /* Applications forget to leave groups before exiting */ ip_mc_drop_socket(sk); @@ -546,7 +548,7 @@ static long inet_wait_for_connect(struct sock *sk, long timeo) { DEFINE_WAIT(wait); - prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE); + prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); /* Basic assumption: if someone sets sk->sk_err, he _must_ * change state of the socket from TCP_SYN_*. @@ -559,9 +561,9 @@ static long inet_wait_for_connect(struct sock *sk, long timeo) lock_sock(sk); if (signal_pending(current) || !timeo) break; - prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE); + prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); } - finish_wait(sk->sk_sleep, &wait); + finish_wait(sk_sleep(sk), &wait); return timeo; } @@ -720,6 +722,8 @@ int inet_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, { struct sock *sk = sock->sk; + sock_rps_record_flow(sk); + /* We may need to bind the socket. */ if (!inet_sk(sk)->inet_num && inet_autobind(sk)) return -EAGAIN; @@ -728,12 +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; + sock_rps_record_flow(sk); + /* We may need to bind the socket. */ if (!inet_sk(sk)->inet_num && inet_autobind(sk)) return -EAGAIN; @@ -743,6 +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; + + sock_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) { @@ -872,7 +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, @@ -899,7 +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 @@ -929,7 +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 @@ -1302,8 +1323,8 @@ static struct sk_buff **inet_gro_receive(struct sk_buff **head, if (unlikely(ip_fast_csum((u8 *)iph, iph->ihl))) goto out_unlock; - id = ntohl(*(u32 *)&iph->id); - flush = (u16)((ntohl(*(u32 *)iph) ^ skb_gro_len(skb)) | (id ^ IP_DF)); + id = ntohl(*(__be32 *)&iph->id); + flush = (u16)((ntohl(*(__be32 *)iph) ^ skb_gro_len(skb)) | (id ^ IP_DF)); id >>= 16; for (p = *head; p; p = p->next) { @@ -1316,8 +1337,8 @@ static struct sk_buff **inet_gro_receive(struct sk_buff **head, if ((iph->protocol ^ iph2->protocol) | (iph->tos ^ iph2->tos) | - (iph->saddr ^ iph2->saddr) | - (iph->daddr ^ iph2->daddr)) { + ((__force u32)iph->saddr ^ (__force u32)iph2->saddr) | + ((__force u32)iph->daddr ^ (__force u32)iph2->daddr)) { NAPI_GRO_CB(p)->same_flow = 0; continue; } @@ -1407,10 +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; @@ -1552,9 +1573,13 @@ static int __init inet_init(void) BUILD_BUG_ON(sizeof(struct inet_skb_parm) > sizeof(dummy_skb->cb)); + sysctl_local_reserved_ports = kzalloc(65536 / 8, GFP_KERNEL); + if (!sysctl_local_reserved_ports) + goto out; + rc = proto_register(&tcp_prot, 1); if (rc) - goto out; + goto out_free_reserved_ports; rc = proto_register(&udp_prot, 1); if (rc) @@ -1653,6 +1678,8 @@ out_unregister_udp_proto: proto_unregister(&udp_prot); out_unregister_tcp_proto: proto_unregister(&tcp_prot); +out_free_reserved_ports: + kfree(sysctl_local_reserved_ports); goto out; } diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 6e747065c202..f094b75810db 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -661,13 +661,13 @@ struct sk_buff *arp_create(int type, int ptype, __be32 dest_ip, #endif #endif -#ifdef CONFIG_FDDI +#if defined(CONFIG_FDDI) || defined(CONFIG_FDDI_MODULE) case ARPHRD_FDDI: arp->ar_hrd = htons(ARPHRD_ETHER); arp->ar_pro = htons(ETH_P_IP); break; #endif -#ifdef CONFIG_TR +#if defined(CONFIG_TR) || defined(CONFIG_TR_MODULE) case ARPHRD_IEEE802_TR: arp->ar_hrd = htons(ARPHRD_IEEE802); arp->ar_pro = htons(ETH_P_IP); @@ -854,7 +854,7 @@ static int arp_process(struct sk_buff *skb) } if (arp->ar_op == htons(ARPOP_REQUEST) && - ip_route_input(skb, tip, sip, 0, dev) == 0) { + ip_route_input_noref(skb, tip, sip, 0, dev) == 0) { rt = skb_rtable(skb); addr_type = rt->rt_type; @@ -1051,7 +1051,7 @@ static int arp_req_set(struct net *net, struct arpreq *r, return -EINVAL; } switch (dev->type) { -#ifdef CONFIG_FDDI +#if defined(CONFIG_FDDI) || defined(CONFIG_FDDI_MODULE) case ARPHRD_FDDI: /* * According to RFC 1390, FDDI devices should accept ARP diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index c97cd9ff697e..3a92a76ae41d 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -290,8 +290,6 @@ void cipso_v4_cache_invalidate(void) cipso_v4_cache[iter].size = 0; spin_unlock_bh(&cipso_v4_cache[iter].lock); } - - return; } /** diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 90e3d6379a42..382bc768ed56 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1096,10 +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: diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index ca2d07b1c706..76daeb5ff564 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 */ @@ -263,7 +245,7 @@ static void fib4_rule_flush_cache(struct fib_rules_ops *ops) rt_cache_flush(ops->fro_net, -1); } -static struct fib_rules_ops fib4_rules_ops_template = { +static const struct fib_rules_ops __net_initdata fib4_rules_ops_template = { .family = AF_INET, .rule_size = sizeof(struct fib4_rule), .addr_size = sizeof(u32), @@ -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_trie.c b/net/ipv4/fib_trie.c index c98f115fb0fd..79d057a939ba 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1022,8 +1022,6 @@ static void trie_rebalance(struct trie *t, struct tnode *tn) rcu_assign_pointer(t->trie, (struct node *)tn); tnode_free_flush(); - - return; } /* only used from updater-side */ diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index ac4dec132735..d65e9215bcd7 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -331,9 +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; @@ -586,20 +587,20 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info) err = __ip_route_output_key(net, &rt2, &fl); else { struct flowi fl2 = {}; - struct dst_entry *odst; + unsigned long orefdst; fl2.fl4_dst = fl.fl4_src; if (ip_route_output_key(net, &rt2, &fl2)) goto relookup_failed; /* Ugh! */ - odst = skb_dst(skb_in); + orefdst = skb_in->_skb_refdst; /* save old refdst */ err = ip_route_input(skb_in, fl.fl4_dst, fl.fl4_src, RT_TOS(tos), rt2->u.dst.dev); dst_release(&rt2->u.dst); rt2 = skb_rtable(skb_in); - skb_dst_set(skb_in, odst); + skb_in->_skb_refdst = orefdst; /* restore old refdst */ } if (err) diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 15d3eeda92f5..5fff865a4fa7 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -998,7 +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); } /* @@ -1011,7 +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_connection_sock.c b/net/ipv4/inet_connection_sock.c index 8da6429269dd..70eb3507c406 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -37,6 +37,9 @@ struct local_ports sysctl_local_ports __read_mostly = { .range = { 32768, 61000 }, }; +unsigned long *sysctl_local_reserved_ports; +EXPORT_SYMBOL(sysctl_local_reserved_ports); + void inet_get_local_port_range(int *low, int *high) { unsigned seq; @@ -108,6 +111,8 @@ again: smallest_size = -1; do { + if (inet_is_reserved_local_port(rover)) + goto next_nolock; head = &hashinfo->bhash[inet_bhashfn(net, rover, hashinfo->bhash_size)]; spin_lock(&head->lock); @@ -130,6 +135,7 @@ again: break; next: spin_unlock(&head->lock); + next_nolock: if (++rover > high) rover = low; } while (--remaining > 0); @@ -234,7 +240,7 @@ static int inet_csk_wait_for_connect(struct sock *sk, long timeo) * having to remove and re-insert us on the wait queue. */ for (;;) { - prepare_to_wait_exclusive(sk->sk_sleep, &wait, + prepare_to_wait_exclusive(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); release_sock(sk); if (reqsk_queue_empty(&icsk->icsk_accept_queue)) @@ -253,7 +259,7 @@ static int inet_csk_wait_for_connect(struct sock *sk, long timeo) if (!timeo) break; } - finish_wait(sk->sk_sleep, &wait); + finish_wait(sk_sleep(sk), &wait); return err; } diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 2b79377b468d..d3e160a88219 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -456,6 +456,8 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row, local_bh_disable(); for (i = 1; i <= remaining; i++) { port = low + (i + offset) % remaining; + if (inet_is_reserved_local_port(port)) + continue; head = &hinfo->bhash[inet_bhashfn(net, port, hinfo->bhash_size)]; spin_lock(&head->lock); diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c index af10942b326c..56cdf68a074c 100644 --- a/net/ipv4/ip_forward.c +++ b/net/ipv4/ip_forward.c @@ -112,8 +112,8 @@ int ip_forward(struct sk_buff *skb) skb->priority = rt_tos2priority(iph->tos); - return NF_HOOK(PF_INET, NF_INET_FORWARD, skb, skb->dev, rt->u.dst.dev, - ip_forward_finish); + return NF_HOOK(NFPROTO_IPV4, NF_INET_FORWARD, skb, skb->dev, + rt->u.dst.dev, ip_forward_finish); sr_failed: /* diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index fe381d12ecdd..32618e11076d 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -502,7 +502,6 @@ static void ipgre_err(struct sk_buff *skb, u32 info) t->err_time = jiffies; out: rcu_read_unlock(); - return; } static inline void ipgre_ecn_decapsulate(struct iphdr *iph, struct sk_buff *skb) @@ -538,7 +537,6 @@ static int ipgre_rcv(struct sk_buff *skb) struct ip_tunnel *tunnel; int offset = 4; __be16 gre_proto; - unsigned int len; if (!pskb_may_pull(skb, 16)) goto drop_nolock; @@ -629,8 +627,6 @@ static int ipgre_rcv(struct sk_buff *skb) tunnel->i_seqno = seqno + 1; } - len = skb->len; - /* Warning: All skb pointers will be invalidated! */ if (tunnel->dev->type == ARPHRD_ETHER) { if (!pskb_may_pull(skb, ETH_HLEN)) { @@ -644,11 +640,7 @@ static int ipgre_rcv(struct sk_buff *skb) skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN); } - stats->rx_packets++; - stats->rx_bytes += len; - skb->dev = tunnel->dev; - skb_dst_drop(skb); - nf_reset(skb); + skb_tunnel_rx(skb, tunnel->dev); skb_reset_network_header(skb); ipgre_ecn_decapsulate(iph, skb); diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index f8ab7a380d4a..d930dc5e4d85 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -266,7 +266,7 @@ int ip_local_deliver(struct sk_buff *skb) return 0; } - return NF_HOOK(PF_INET, NF_INET_LOCAL_IN, skb, skb->dev, NULL, + return NF_HOOK(NFPROTO_IPV4, NF_INET_LOCAL_IN, skb, skb->dev, NULL, ip_local_deliver_finish); } @@ -331,8 +331,8 @@ static int ip_rcv_finish(struct sk_buff *skb) * how the packet travels inside Linux networking. */ if (skb_dst(skb) == NULL) { - int err = ip_route_input(skb, iph->daddr, iph->saddr, iph->tos, - skb->dev); + int err = ip_route_input_noref(skb, iph->daddr, iph->saddr, + iph->tos, skb->dev); if (unlikely(err)) { if (err == -EHOSTUNREACH) IP_INC_STATS_BH(dev_net(skb->dev), @@ -444,7 +444,7 @@ int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, /* Must drop socket now because of tproxy. */ skb_orphan(skb); - return NF_HOOK(PF_INET, NF_INET_PRE_ROUTING, skb, dev, NULL, + return NF_HOOK(NFPROTO_IPV4, NF_INET_PRE_ROUTING, skb, dev, NULL, ip_rcv_finish); inhdr_error: diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c index 4c09a31fd140..ba9836c488ed 100644 --- a/net/ipv4/ip_options.c +++ b/net/ipv4/ip_options.c @@ -238,7 +238,6 @@ void ip_options_fragment(struct sk_buff * skb) opt->rr_needaddr = 0; opt->ts_needaddr = 0; opt->ts_needtime = 0; - return; } /* @@ -601,6 +600,7 @@ int ip_options_rcv_srr(struct sk_buff *skb) unsigned char *optptr = skb_network_header(skb) + opt->srr; struct rtable *rt = skb_rtable(skb); struct rtable *rt2; + unsigned long orefdst; int err; if (!opt->srr) @@ -624,16 +624,16 @@ int ip_options_rcv_srr(struct sk_buff *skb) } memcpy(&nexthop, &optptr[srrptr-1], 4); - rt = skb_rtable(skb); + orefdst = skb->_skb_refdst; skb_dst_set(skb, NULL); err = ip_route_input(skb, nexthop, iph->saddr, iph->tos, skb->dev); rt2 = skb_rtable(skb); if (err || (rt2->rt_type != RTN_UNICAST && rt2->rt_type != RTN_LOCAL)) { - ip_rt_put(rt2); - skb_dst_set(skb, &rt->u.dst); + skb_dst_drop(skb); + skb->_skb_refdst = orefdst; return -EINVAL; } - ip_rt_put(rt); + refdst_drop(orefdst); if (rt2->rt_type != RTN_LOCAL) break; /* Superfast 8) loopback forward */ diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index d1bcc9f21d4f..9a4a6c96cb0d 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -96,8 +96,8 @@ int __ip_local_out(struct sk_buff *skb) iph->tot_len = htons(skb->len); ip_send_check(iph); - return nf_hook(PF_INET, NF_INET_LOCAL_OUT, skb, NULL, skb_dst(skb)->dev, - dst_output); + return nf_hook(NFPROTO_IPV4, NF_INET_LOCAL_OUT, skb, NULL, + skb_dst(skb)->dev, dst_output); } int ip_local_out(struct sk_buff *skb) @@ -272,8 +272,8 @@ int ip_mc_output(struct sk_buff *skb) ) { struct sk_buff *newskb = skb_clone(skb, GFP_ATOMIC); if (newskb) - NF_HOOK(PF_INET, NF_INET_POST_ROUTING, newskb, - NULL, newskb->dev, + NF_HOOK(NFPROTO_IPV4, NF_INET_POST_ROUTING, + newskb, NULL, newskb->dev, ip_dev_loopback_xmit); } @@ -288,12 +288,12 @@ int ip_mc_output(struct sk_buff *skb) if (rt->rt_flags&RTCF_BROADCAST) { struct sk_buff *newskb = skb_clone(skb, GFP_ATOMIC); if (newskb) - NF_HOOK(PF_INET, NF_INET_POST_ROUTING, newskb, NULL, - newskb->dev, ip_dev_loopback_xmit); + NF_HOOK(NFPROTO_IPV4, NF_INET_POST_ROUTING, newskb, + NULL, newskb->dev, ip_dev_loopback_xmit); } - return NF_HOOK_COND(PF_INET, NF_INET_POST_ROUTING, skb, NULL, skb->dev, - ip_finish_output, + return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING, skb, NULL, + skb->dev, ip_finish_output, !(IPCB(skb)->flags & IPSKB_REROUTED)); } @@ -306,22 +306,24 @@ int ip_output(struct sk_buff *skb) skb->dev = dev; skb->protocol = htons(ETH_P_IP); - return NF_HOOK_COND(PF_INET, NF_INET_POST_ROUTING, skb, NULL, dev, + return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING, skb, NULL, dev, ip_finish_output, !(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); struct ip_options *opt = inet->opt; struct rtable *rt; struct iphdr *iph; + int res; /* Skip all of this if the packet is already routed, * f.e. by something like SCTP. */ + rcu_read_lock(); rt = skb_rtable(skb); if (rt != NULL) goto packet_routed; @@ -359,7 +361,7 @@ int ip_queue_xmit(struct sk_buff *skb, int ipfragok) } sk_setup_caps(sk, &rt->u.dst); } - skb_dst_set(skb, dst_clone(&rt->u.dst)); + skb_dst_set_noref(skb, &rt->u.dst); packet_routed: if (opt && opt->is_strictroute && rt->rt_dst != rt->rt_gateway) @@ -370,7 +372,7 @@ 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; @@ -391,9 +393,12 @@ packet_routed: skb->priority = sk->sk_priority; skb->mark = sk->sk_mark; - return ip_local_out(skb); + res = ip_local_out(skb); + rcu_read_unlock(); + return res; no_route: + rcu_read_unlock(); IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTNOROUTES); kfree_skb(skb); return -EHOSTUNREACH; @@ -469,6 +474,10 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) hlen = iph->ihl * 4; mtu = dst_mtu(&rt->u.dst) - hlen; /* Size of data space */ +#ifdef CONFIG_BRIDGE_NETFILTER + if (skb->nf_bridge) + mtu -= nf_bridge_mtu_reduction(skb); +#endif IPCB(skb)->flags |= IPSKB_FRAG_COMPLETE; /* When frag_list is given, use it. First, check its validity: diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 1e64dabbd232..ce231780a2b1 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -287,12 +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; @@ -958,6 +954,22 @@ e_inval: return -EINVAL; } +/** + * ip_queue_rcv_skb - Queue an skb into sock receive queue + * @sk: socket + * @skb: buffer + * + * Queues an skb into socket receive queue. If IP_CMSG_PKTINFO option + * is not set, we drop skb dst entry now, while dst cache line is hot. + */ +int ip_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) +{ + if (!(inet_sk(sk)->cmsg_flags & IP_CMSG_PKTINFO)) + skb_dst_drop(skb); + return sock_queue_rcv_skb(sk, skb); +} +EXPORT_SYMBOL(ip_queue_rcv_skb); + int ip_setsockopt(struct sock *sk, int level, int optname, char __user *optval, unsigned int optlen) { diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index 067ce9e043dc..b9d84e800cf4 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -976,7 +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 0b27b14dcc9d..7fd636711037 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -374,11 +374,8 @@ static int ipip_rcv(struct sk_buff *skb) skb->protocol = htons(ETH_P_IP); skb->pkt_type = PACKET_HOST; - tunnel->dev->stats.rx_packets++; - tunnel->dev->stats.rx_bytes += skb->len; - skb->dev = tunnel->dev; - skb_dst_drop(skb); - nf_reset(skb); + skb_tunnel_rx(skb, tunnel->dev); + ipip_ecn_decapsulate(iph, skb); netif_rx(skb); rcu_read_unlock(); diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 9d4f6d1340a4..45889103b3e2 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -22,7 +22,7 @@ * overflow. * Carlos Picoto : PIMv1 Support * Pavlin Ivanov Radoslavov: PIMv2 Registers must checksum only PIM header - * Relax this requrement to work with older peers. + * Relax this requirement to work with older peers. * */ @@ -63,11 +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. */ @@ -78,9 +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); @@ -95,12 +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; -static struct timer_list ipmr_expire_timer; + 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 const struct fib_rules_ops __net_initdata ipmr_rules_ops_template = { + .family = RTNL_FAMILY_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; + + 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 */ @@ -201,12 +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; @@ -226,12 +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]; + + if (mrt->id == RT_TABLE_DEFAULT) + sprintf(name, "pimreg"); + else + sprintf(name, "pimreg%u", mrt->id); - dev = alloc_netdev(0, "pimreg", reg_vif_setup); + dev = alloc_netdev(0, name, reg_vif_setup); if (dev == NULL) return NULL; @@ -276,17 +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; @@ -298,17 +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); @@ -329,7 +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); } @@ -337,13 +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) { @@ -364,42 +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); @@ -407,17 +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) @@ -428,16 +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) { @@ -447,9 +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); @@ -525,49 +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; } @@ -575,7 +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; @@ -588,7 +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 { @@ -600,9 +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); } } @@ -613,7 +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; @@ -646,7 +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)); @@ -678,7 +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; } @@ -686,7 +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"); @@ -701,27 +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); @@ -738,7 +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 @@ -750,11 +995,11 @@ 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); + if (atomic_read(&mrt->cache_resolve_queue_len) == 1) + mod_timer(&mrt->ipmr_expire_timer, c->mfc_un.unres.expires); } /* @@ -776,19 +1021,18 @@ 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); @@ -798,27 +1042,30 @@ 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); @@ -828,43 +1075,42 @@ 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; @@ -874,53 +1120,41 @@ 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); } @@ -929,16 +1163,19 @@ 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(); } @@ -956,9 +1193,14 @@ 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; } @@ -971,7 +1213,7 @@ 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; } @@ -979,7 +1221,7 @@ 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)++; @@ -987,7 +1229,7 @@ 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: @@ -1000,9 +1242,9 @@ 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; @@ -1019,9 +1261,9 @@ 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; /* @@ -1032,7 +1274,7 @@ 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 @@ -1046,14 +1288,35 @@ 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. @@ -1072,6 +1335,11 @@ 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 @@ -1093,10 +1361,10 @@ 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; @@ -1113,16 +1381,21 @@ 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; @@ -1140,7 +1413,7 @@ 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; @@ -1163,16 +1436,20 @@ 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; @@ -1231,11 +1508,11 @@ 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; @@ -1249,7 +1526,7 @@ 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 @@ -1323,21 +1600,20 @@ static void ipmr_queue_xmit(struct sk_buff *skb, struct mfc_cache *c, int vifi) * not mrouter) cannot join to more than one interface - it will * result in receiving multiple packets. */ - NF_HOOK(PF_INET, NF_INET_FORWARD, skb, skb->dev, dev, + NF_HOOK(NFPROTO_IPV4, NF_INET_FORWARD, skb, skb->dev, dev, ipmr_forward_finish); return; out_free: kfree_skb(skb); - 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; @@ -1345,11 +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++; @@ -1358,7 +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) { @@ -1377,26 +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 @@ -1406,7 +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; } @@ -1415,9 +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; } } @@ -1438,6 +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. @@ -1445,6 +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)) @@ -1457,9 +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; } @@ -1468,7 +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 @@ -1486,19 +1770,19 @@ 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 err2 = ipmr_cache_unresolved(mrt, vif, skb); read_unlock(&mrt_lock); - return err; + return err2; } read_unlock(&mrt_lock); kfree_skb(skb); return -ENODEV; } - ip_mr_forward(skb, cache, local); + ip_mr_forward(net, mrt, skb, cache, local); read_unlock(&mrt_lock); @@ -1515,11 +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); /* @@ -1534,8 +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); @@ -1546,14 +1830,12 @@ static int __pim_rcv(struct sk_buff *skb, unsigned int pimlen) skb->mac_header = skb->network_header; skb_pull(skb, (u8*)encap - skb->data); skb_reset_network_header(skb); - skb->dev = reg_dev; skb->protocol = htons(ETH_P_IP); skb->ip_summed = 0; skb->pkt_type = PACKET_HOST; - skb_dst_drop(skb); - reg_dev->stats.rx_bytes += skb->len; - reg_dev->stats.rx_packets++; - nf_reset(skb); + + skb_tunnel_rx(skb, reg_dev); + netif_rx(skb); dev_put(reg_dev); @@ -1570,17 +1852,21 @@ 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); } @@ -1592,6 +1878,8 @@ 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; @@ -1603,7 +1891,10 @@ 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); } @@ -1611,12 +1902,11 @@ drop: } #endif -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) { int ct; struct rtnexthop *nhp; - struct net *net = mfc_net(c); u8 *b = skb_tail_pointer(skb); struct rtattr *mp_head; @@ -1624,19 +1914,19 @@ ipmr_fill_mroute(struct sk_buff *skb, struct mfc_cache *c, struct rtmsg *rtm) if (c->mfc_parent > MAXVIFS) return -ENOENT; - if (VIF_EXISTS(net, c->mfc_parent)) - RTA_PUT(skb, RTA_IIF, 4, &net->ipv4.vif_table[c->mfc_parent].dev->ifindex); + 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 (VIF_EXISTS(net, ct) && 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); } } @@ -1654,11 +1944,16 @@ 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; @@ -1672,7 +1967,7 @@ 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; } @@ -1689,24 +1984,107 @@ 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; } +static int ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, + u32 pid, u32 seq, struct mfc_cache *c) +{ + struct nlmsghdr *nlh; + struct rtmsg *rtm; + + nlh = nlmsg_put(skb, pid, seq, RTM_NEWROUTE, sizeof(*rtm), NLM_F_MULTI); + if (nlh == NULL) + return -EMSGSIZE; + + rtm = nlmsg_data(nlh); + rtm->rtm_family = RTNL_FAMILY_IPMR; + rtm->rtm_dst_len = 32; + rtm->rtm_src_len = 32; + rtm->rtm_tos = 0; + rtm->rtm_table = mrt->id; + NLA_PUT_U32(skb, RTA_TABLE, mrt->id); + rtm->rtm_type = RTN_MULTICAST; + rtm->rtm_scope = RT_SCOPE_UNIVERSE; + rtm->rtm_protocol = RTPROT_UNSPEC; + rtm->rtm_flags = 0; + + NLA_PUT_BE32(skb, RTA_SRC, c->mfc_origin); + NLA_PUT_BE32(skb, RTA_DST, c->mfc_mcastgrp); + + if (__ipmr_fill_mroute(mrt, skb, c, rtm) < 0) + goto nla_put_failure; + + return nlmsg_end(skb, nlh); + +nla_put_failure: + nlmsg_cancel(skb, nlh); + return -EMSGSIZE; +} + +static int ipmr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct net *net = sock_net(skb->sk); + struct mr_table *mrt; + struct mfc_cache *mfc; + unsigned int t = 0, s_t; + unsigned int h = 0, s_h; + unsigned int e = 0, s_e; + + s_t = cb->args[0]; + s_h = cb->args[1]; + s_e = cb->args[2]; + + read_lock(&mrt_lock); + ipmr_for_each_table(mrt, net) { + if (t < s_t) + goto next_table; + if (t > s_t) + s_h = 0; + for (h = s_h; h < MFC_LINES; h++) { + list_for_each_entry(mfc, &mrt->mfc_cache_array[h], list) { + if (e < s_e) + goto next_entry; + if (ipmr_fill_mroute(mrt, skb, + NETLINK_CB(cb->skb).pid, + cb->nlh->nlmsg_seq, + mfc) < 0) + goto done; +next_entry: + e++; + } + e = s_e = 0; + } + s_h = 0; +next_table: + t++; + } +done: + read_unlock(&mrt_lock); + + cb->args[2] = e; + cb->args[1] = h; + cb->args[0] = t; + + return skb->len; +} + #ifdef CONFIG_PROC_FS /* * The /proc interfaces to multicast routing /proc/ip_mr_cache /proc/ip_mr_vif */ struct ipmr_vif_iter { struct seq_net_private p; + struct mr_table *mrt; int ct; }; @@ -1714,11 +2092,13 @@ 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; } @@ -1726,7 +2106,15 @@ 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) @@ -1737,15 +2125,16 @@ 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; } @@ -1758,7 +2147,8 @@ 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, @@ -1769,7 +2159,7 @@ 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); @@ -1800,7 +2190,8 @@ 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; }; @@ -1808,22 +2199,22 @@ 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); @@ -1836,7 +2227,13 @@ 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) @@ -1848,37 +2245,36 @@ 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); @@ -1890,18 +2286,17 @@ 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, @@ -1909,20 +2304,21 @@ 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, + seq_printf(seq, "%08X %08X %-3hd", + (__force u32) mfc->mfc_mcastgrp, + (__force u32) 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", @@ -1974,27 +2370,11 @@ 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; @@ -2009,10 +2389,8 @@ 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; } @@ -2023,8 +2401,7 @@ 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 = { @@ -2047,7 +2424,6 @@ 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; @@ -2058,6 +2434,7 @@ int __init ip_mr_init(void) goto add_proto_fail; } #endif + rtnl_register(RTNL_FAMILY_IPMR, RTM_GETROUTE, NULL, ipmr_rtm_dumproute); return 0; #ifdef CONFIG_IP_PIMSM_V2 @@ -2065,7 +2442,6 @@ 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 82fb43c5c59e..07de855e2175 100644 --- a/net/ipv4/netfilter.c +++ b/net/ipv4/netfilter.c @@ -17,7 +17,7 @@ int ip_route_me_harder(struct sk_buff *skb, unsigned addr_type) const struct iphdr *iph = ip_hdr(skb); struct rtable *rt; struct flowi fl = {}; - struct dst_entry *odst; + unsigned long orefdst; unsigned int hh_len; unsigned int type; @@ -51,14 +51,14 @@ int ip_route_me_harder(struct sk_buff *skb, unsigned addr_type) if (ip_route_output_key(net, &rt, &fl) != 0) return -1; - odst = skb_dst(skb); + orefdst = skb->_skb_refdst; if (ip_route_input(skb, iph->daddr, iph->saddr, RT_TOS(iph->tos), rt->u.dst.dev) != 0) { dst_release(&rt->u.dst); return -1; } dst_release(&rt->u.dst); - dst_release(odst); + refdst_drop(orefdst); } if (skb_dst(skb)->error) diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index f07d77f65751..1ac01b128621 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -49,12 +49,7 @@ MODULE_DESCRIPTION("arptables core"); #endif #ifdef CONFIG_NETFILTER_DEBUG -#define ARP_NF_ASSERT(x) \ -do { \ - if (!(x)) \ - printk("ARP_NF_ASSERT: %s:%s:%u\n", \ - __func__, __FILE__, __LINE__); \ -} while(0) +#define ARP_NF_ASSERT(x) WARN_ON(!(x)) #else #define ARP_NF_ASSERT(x) #endif @@ -224,10 +219,10 @@ static inline int arp_checkentry(const struct arpt_arp *arp) } static unsigned int -arpt_error(struct sk_buff *skb, const struct xt_target_param *par) +arpt_error(struct sk_buff *skb, const struct xt_action_param *par) { if (net_ratelimit()) - printk("arp_tables: error: '%s'\n", + pr_err("arp_tables: error: '%s'\n", (const char *)par->targinfo); return NF_DROP; @@ -260,12 +255,11 @@ unsigned int arpt_do_table(struct sk_buff *skb, static const char nulldevname[IFNAMSIZ] __attribute__((aligned(sizeof(long)))); unsigned int verdict = NF_DROP; const struct arphdr *arp; - bool hotdrop = false; struct arpt_entry *e, *back; const char *indev, *outdev; void *table_base; const struct xt_table_info *private; - struct xt_target_param tgpar; + struct xt_action_param acpar; if (!pskb_may_pull(skb, arp_hdr_len(skb->dev))) return NF_DROP; @@ -280,10 +274,11 @@ unsigned int arpt_do_table(struct sk_buff *skb, e = get_entry(table_base, private->hook_entry[hook]); back = get_entry(table_base, private->underflow[hook]); - tgpar.in = in; - tgpar.out = out; - tgpar.hooknum = hook; - tgpar.family = NFPROTO_ARP; + acpar.in = in; + acpar.out = out; + acpar.hooknum = hook; + acpar.family = NFPROTO_ARP; + acpar.hotdrop = false; arp = arp_hdr(skb); do { @@ -333,9 +328,9 @@ unsigned int arpt_do_table(struct sk_buff *skb, /* Targets which reenter must return * abs. verdicts */ - tgpar.target = t->u.kernel.target; - tgpar.targinfo = t->data; - verdict = t->u.kernel.target->target(skb, &tgpar); + acpar.target = t->u.kernel.target; + acpar.targinfo = t->data; + verdict = t->u.kernel.target->target(skb, &acpar); /* Target might have changed stuff. */ arp = arp_hdr(skb); @@ -345,10 +340,10 @@ unsigned int arpt_do_table(struct sk_buff *skb, else /* Verdict */ break; - } while (!hotdrop); + } while (!acpar.hotdrop); xt_info_rdunlock_bh(); - if (hotdrop) + if (acpar.hotdrop) return NF_DROP; else return verdict; @@ -390,7 +385,7 @@ static int mark_source_chains(const struct xt_table_info *newinfo, int visited = e->comefrom & (1 << hook); if (e->comefrom & (1 << NF_ARP_NUMHOOKS)) { - printk("arptables: loop hook %u pos %u %08X.\n", + pr_notice("arptables: loop hook %u pos %u %08X.\n", hook, pos, e->comefrom); return 0; } @@ -523,13 +518,11 @@ find_check_entry(struct arpt_entry *e, const char *name, unsigned int size) return ret; t = arpt_get_target(e); - target = try_then_request_module(xt_find_target(NFPROTO_ARP, - t->u.user.name, - t->u.user.revision), - "arpt_%s", t->u.user.name); - if (IS_ERR(target) || !target) { + target = xt_request_find_target(NFPROTO_ARP, t->u.user.name, + t->u.user.revision); + if (IS_ERR(target)) { duprintf("find_check_entry: `%s' not found\n", t->u.user.name); - ret = target ? PTR_ERR(target) : -ENOENT; + ret = PTR_ERR(target); goto out; } t->u.kernel.target = target; @@ -651,6 +644,9 @@ static int translate_table(struct xt_table_info *newinfo, void *entry0, if (ret != 0) break; ++i; + if (strcmp(arpt_get_target(iter)->u.user.name, + XT_ERROR_TARGET) == 0) + ++newinfo->stacksize; } duprintf("translate_table: ARPT_ENTRY_ITERATE gives %d\n", ret); if (ret != 0) @@ -1252,14 +1248,12 @@ check_compat_entry_size_and_hooks(struct compat_arpt_entry *e, entry_offset = (void *)e - (void *)base; t = compat_arpt_get_target(e); - target = try_then_request_module(xt_find_target(NFPROTO_ARP, - t->u.user.name, - t->u.user.revision), - "arpt_%s", t->u.user.name); - if (IS_ERR(target) || !target) { + target = xt_request_find_target(NFPROTO_ARP, t->u.user.name, + t->u.user.revision); + if (IS_ERR(target)) { duprintf("check_compat_entry_size_and_hooks: `%s' not found\n", t->u.user.name); - ret = target ? PTR_ERR(target) : -ENOENT; + ret = PTR_ERR(target); goto out; } t->u.kernel.target = target; @@ -1778,8 +1772,7 @@ struct xt_table *arpt_register_table(struct net *net, { int ret; struct xt_table_info *newinfo; - struct xt_table_info bootstrap - = { 0, 0, 0, { 0 }, { 0 }, { } }; + struct xt_table_info bootstrap = {0}; void *loc_cpu_entry; struct xt_table *new_table; @@ -1830,22 +1823,23 @@ void arpt_unregister_table(struct xt_table *table) } /* The built-in targets: standard (NULL) and error. */ -static struct xt_target arpt_standard_target __read_mostly = { - .name = ARPT_STANDARD_TARGET, - .targetsize = sizeof(int), - .family = NFPROTO_ARP, +static struct xt_target arpt_builtin_tg[] __read_mostly = { + { + .name = ARPT_STANDARD_TARGET, + .targetsize = sizeof(int), + .family = NFPROTO_ARP, #ifdef CONFIG_COMPAT - .compatsize = sizeof(compat_int_t), - .compat_from_user = compat_standard_from_user, - .compat_to_user = compat_standard_to_user, + .compatsize = sizeof(compat_int_t), + .compat_from_user = compat_standard_from_user, + .compat_to_user = compat_standard_to_user, #endif -}; - -static struct xt_target arpt_error_target __read_mostly = { - .name = ARPT_ERROR_TARGET, - .target = arpt_error, - .targetsize = ARPT_FUNCTION_MAXNAMELEN, - .family = NFPROTO_ARP, + }, + { + .name = ARPT_ERROR_TARGET, + .target = arpt_error, + .targetsize = ARPT_FUNCTION_MAXNAMELEN, + .family = NFPROTO_ARP, + }, }; static struct nf_sockopt_ops arpt_sockopts = { @@ -1889,12 +1883,9 @@ static int __init arp_tables_init(void) goto err1; /* Noone else will be downing sem now, so we won't sleep */ - ret = xt_register_target(&arpt_standard_target); + ret = xt_register_targets(arpt_builtin_tg, ARRAY_SIZE(arpt_builtin_tg)); if (ret < 0) goto err2; - ret = xt_register_target(&arpt_error_target); - if (ret < 0) - goto err3; /* Register setsockopt */ ret = nf_register_sockopt(&arpt_sockopts); @@ -1905,9 +1896,7 @@ static int __init arp_tables_init(void) return 0; err4: - xt_unregister_target(&arpt_error_target); -err3: - xt_unregister_target(&arpt_standard_target); + xt_unregister_targets(arpt_builtin_tg, ARRAY_SIZE(arpt_builtin_tg)); err2: unregister_pernet_subsys(&arp_tables_net_ops); err1: @@ -1917,8 +1906,7 @@ err1: static void __exit arp_tables_fini(void) { nf_unregister_sockopt(&arpt_sockopts); - xt_unregister_target(&arpt_error_target); - xt_unregister_target(&arpt_standard_target); + xt_unregister_targets(arpt_builtin_tg, ARRAY_SIZE(arpt_builtin_tg)); unregister_pernet_subsys(&arp_tables_net_ops); } diff --git a/net/ipv4/netfilter/arpt_mangle.c b/net/ipv4/netfilter/arpt_mangle.c index b0d5b1d0a769..e1be7dd1171b 100644 --- a/net/ipv4/netfilter/arpt_mangle.c +++ b/net/ipv4/netfilter/arpt_mangle.c @@ -9,7 +9,7 @@ MODULE_AUTHOR("Bart De Schuymer <bdschuym@pandora.be>"); MODULE_DESCRIPTION("arptables arp payload mangle target"); static unsigned int -target(struct sk_buff *skb, const struct xt_target_param *par) +target(struct sk_buff *skb, const struct xt_action_param *par) { const struct arpt_mangle *mangle = par->targinfo; const struct arphdr *arp; @@ -54,7 +54,7 @@ target(struct sk_buff *skb, const struct xt_target_param *par) return mangle->target; } -static bool checkentry(const struct xt_tgchk_param *par) +static int checkentry(const struct xt_tgchk_param *par) { const struct arpt_mangle *mangle = par->targinfo; diff --git a/net/ipv4/netfilter/ip_queue.c b/net/ipv4/netfilter/ip_queue.c index e2787048aa0a..a4e5fc5df4bf 100644 --- a/net/ipv4/netfilter/ip_queue.c +++ b/net/ipv4/netfilter/ip_queue.c @@ -161,8 +161,7 @@ ipq_build_packet_message(struct nf_queue_entry *entry, int *errp) break; case IPQ_COPY_PACKET: - if ((entry->skb->ip_summed == CHECKSUM_PARTIAL || - entry->skb->ip_summed == CHECKSUM_COMPLETE) && + if (entry->skb->ip_summed == CHECKSUM_PARTIAL && (*errp = skb_checksum_help(entry->skb))) { read_unlock_bh(&queue_lock); return NULL; @@ -462,7 +461,6 @@ __ipq_rcv_skb(struct sk_buff *skb) if (flags & NLM_F_ACK) netlink_ack(skb, nlh, 0); - return; } static void diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index b29c66df8d1f..63958f3394a5 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -39,24 +39,19 @@ MODULE_DESCRIPTION("IPv4 packet filter"); /*#define DEBUG_IP_FIREWALL_USER*/ #ifdef DEBUG_IP_FIREWALL -#define dprintf(format, args...) printk(format , ## args) +#define dprintf(format, args...) pr_info(format , ## args) #else #define dprintf(format, args...) #endif #ifdef DEBUG_IP_FIREWALL_USER -#define duprintf(format, args...) printk(format , ## args) +#define duprintf(format, args...) pr_info(format , ## args) #else #define duprintf(format, args...) #endif #ifdef CONFIG_NETFILTER_DEBUG -#define IP_NF_ASSERT(x) \ -do { \ - if (!(x)) \ - printk("IP_NF_ASSERT: %s:%s:%u\n", \ - __func__, __FILE__, __LINE__); \ -} while(0) +#define IP_NF_ASSERT(x) WARN_ON(!(x)) #else #define IP_NF_ASSERT(x) #endif @@ -165,30 +160,14 @@ ip_checkentry(const struct ipt_ip *ip) } static unsigned int -ipt_error(struct sk_buff *skb, const struct xt_target_param *par) +ipt_error(struct sk_buff *skb, const struct xt_action_param *par) { if (net_ratelimit()) - printk("ip_tables: error: `%s'\n", - (const char *)par->targinfo); + pr_info("error: `%s'\n", (const char *)par->targinfo); return NF_DROP; } -/* Performance critical - called for every packet */ -static inline bool -do_match(const struct ipt_entry_match *m, const struct sk_buff *skb, - struct xt_match_param *par) -{ - par->match = m->u.kernel.match; - par->matchinfo = m->data; - - /* Stop iteration if it doesn't match */ - if (!m->u.kernel.match->match(skb, par)) - return true; - else - return false; -} - /* Performance critical */ static inline struct ipt_entry * get_entry(const void *base, unsigned int offset) @@ -322,19 +301,16 @@ ipt_do_table(struct sk_buff *skb, const struct net_device *out, struct xt_table *table) { -#define tb_comefrom ((struct ipt_entry *)table_base)->comefrom - static const char nulldevname[IFNAMSIZ] __attribute__((aligned(sizeof(long)))); const struct iphdr *ip; - bool hotdrop = false; /* Initializing verdict to NF_DROP keeps gcc happy. */ unsigned int verdict = NF_DROP; const char *indev, *outdev; const void *table_base; - struct ipt_entry *e, *back; + struct ipt_entry *e, **jumpstack; + unsigned int *stackptr, origptr, cpu; const struct xt_table_info *private; - struct xt_match_param mtpar; - struct xt_target_param tgpar; + struct xt_action_param acpar; /* Initialization */ ip = ip_hdr(skb); @@ -346,40 +322,47 @@ ipt_do_table(struct sk_buff *skb, * things we don't know, ie. tcp syn flag or ports). If the * rule is also a fragment-specific rule, non-fragments won't * match it. */ - mtpar.fragoff = ntohs(ip->frag_off) & IP_OFFSET; - mtpar.thoff = ip_hdrlen(skb); - mtpar.hotdrop = &hotdrop; - mtpar.in = tgpar.in = in; - mtpar.out = tgpar.out = out; - mtpar.family = tgpar.family = NFPROTO_IPV4; - mtpar.hooknum = tgpar.hooknum = hook; + acpar.fragoff = ntohs(ip->frag_off) & IP_OFFSET; + acpar.thoff = ip_hdrlen(skb); + acpar.hotdrop = false; + acpar.in = in; + acpar.out = out; + acpar.family = NFPROTO_IPV4; + acpar.hooknum = hook; IP_NF_ASSERT(table->valid_hooks & (1 << hook)); xt_info_rdlock_bh(); private = table->private; - table_base = private->entries[smp_processor_id()]; + cpu = smp_processor_id(); + table_base = private->entries[cpu]; + jumpstack = (struct ipt_entry **)private->jumpstack[cpu]; + stackptr = &private->stackptr[cpu]; + origptr = *stackptr; e = get_entry(table_base, private->hook_entry[hook]); - /* For return from builtin chain */ - back = get_entry(table_base, private->underflow[hook]); + pr_debug("Entering %s(hook %u); sp at %u (UF %p)\n", + table->name, hook, origptr, + get_entry(table_base, private->underflow[hook])); do { const struct ipt_entry_target *t; const struct xt_entry_match *ematch; IP_NF_ASSERT(e); - IP_NF_ASSERT(back); if (!ip_packet_match(ip, indev, outdev, - &e->ip, mtpar.fragoff)) { + &e->ip, acpar.fragoff)) { no_match: e = ipt_next_entry(e); continue; } - xt_ematch_foreach(ematch, e) - if (do_match(ematch, skb, &mtpar) != 0) + xt_ematch_foreach(ematch, e) { + acpar.match = ematch->u.kernel.match; + acpar.matchinfo = ematch->data; + if (!acpar.match->match(skb, &acpar)) goto no_match; + } ADD_COUNTER(e->counters, ntohs(ip->tot_len), 1); @@ -404,41 +387,38 @@ ipt_do_table(struct sk_buff *skb, verdict = (unsigned)(-v) - 1; break; } - e = back; - back = get_entry(table_base, back->comefrom); + if (*stackptr == 0) { + e = get_entry(table_base, + private->underflow[hook]); + pr_debug("Underflow (this is normal) " + "to %p\n", e); + } else { + e = jumpstack[--*stackptr]; + pr_debug("Pulled %p out from pos %u\n", + e, *stackptr); + e = ipt_next_entry(e); + } continue; } if (table_base + v != ipt_next_entry(e) && !(e->ip.flags & IPT_F_GOTO)) { - /* Save old back ptr in next entry */ - struct ipt_entry *next = ipt_next_entry(e); - next->comefrom = (void *)back - table_base; - /* set back pointer to next entry */ - back = next; + if (*stackptr >= private->stacksize) { + verdict = NF_DROP; + break; + } + jumpstack[(*stackptr)++] = e; + pr_debug("Pushed %p into pos %u\n", + e, *stackptr - 1); } e = get_entry(table_base, v); continue; } - /* Targets which reenter must return - abs. verdicts */ - tgpar.target = t->u.kernel.target; - tgpar.targinfo = t->data; - + acpar.target = t->u.kernel.target; + acpar.targinfo = t->data; -#ifdef CONFIG_NETFILTER_DEBUG - tb_comefrom = 0xeeeeeeec; -#endif - verdict = t->u.kernel.target->target(skb, &tgpar); -#ifdef CONFIG_NETFILTER_DEBUG - if (tb_comefrom != 0xeeeeeeec && verdict == IPT_CONTINUE) { - printk("Target %s reentered!\n", - t->u.kernel.target->name); - verdict = NF_DROP; - } - tb_comefrom = 0x57acc001; -#endif + verdict = t->u.kernel.target->target(skb, &acpar); /* Target might have changed stuff. */ ip = ip_hdr(skb); if (verdict == IPT_CONTINUE) @@ -446,18 +426,18 @@ ipt_do_table(struct sk_buff *skb, else /* Verdict */ break; - } while (!hotdrop); + } while (!acpar.hotdrop); xt_info_rdunlock_bh(); - + pr_debug("Exiting %s; resetting sp from %u to %u\n", + __func__, *stackptr, origptr); + *stackptr = origptr; #ifdef DEBUG_ALLOW_ALL return NF_ACCEPT; #else - if (hotdrop) + if (acpar.hotdrop) return NF_DROP; else return verdict; #endif - -#undef tb_comefrom } /* Figures out from what hook each rule can be called: returns 0 if @@ -486,7 +466,7 @@ mark_source_chains(const struct xt_table_info *newinfo, int visited = e->comefrom & (1 << hook); if (e->comefrom & (1 << NF_INET_NUMHOOKS)) { - printk("iptables: loop hook %u pos %u %08X.\n", + pr_err("iptables: loop hook %u pos %u %08X.\n", hook, pos, e->comefrom); return 0; } @@ -591,7 +571,7 @@ check_entry(const struct ipt_entry *e, const char *name) const struct ipt_entry_target *t; if (!ip_checkentry(&e->ip)) { - duprintf("ip_tables: ip check failed %p %s.\n", e, name); + duprintf("ip check failed %p %s.\n", e, par->match->name); return -EINVAL; } @@ -618,8 +598,7 @@ check_match(struct ipt_entry_match *m, struct xt_mtchk_param *par) ret = xt_check_match(par, m->u.match_size - sizeof(*m), ip->proto, ip->invflags & IPT_INV_PROTO); if (ret < 0) { - duprintf("ip_tables: check failed for `%s'.\n", - par.match->name); + duprintf("check failed for `%s'.\n", par->match->name); return ret; } return 0; @@ -631,12 +610,11 @@ find_check_match(struct ipt_entry_match *m, struct xt_mtchk_param *par) struct xt_match *match; int ret; - match = try_then_request_module(xt_find_match(AF_INET, m->u.user.name, - m->u.user.revision), - "ipt_%s", m->u.user.name); - if (IS_ERR(match) || !match) { + match = xt_request_find_match(NFPROTO_IPV4, m->u.user.name, + m->u.user.revision); + if (IS_ERR(match)) { duprintf("find_check_match: `%s' not found\n", m->u.user.name); - return match ? PTR_ERR(match) : -ENOENT; + return PTR_ERR(match); } m->u.kernel.match = match; @@ -667,7 +645,7 @@ static int check_target(struct ipt_entry *e, struct net *net, const char *name) ret = xt_check_target(&par, t->u.target_size - sizeof(*t), e->ip.proto, e->ip.invflags & IPT_INV_PROTO); if (ret < 0) { - duprintf("ip_tables: check failed for `%s'.\n", + duprintf("check failed for `%s'.\n", t->u.kernel.target->name); return ret; } @@ -703,13 +681,11 @@ find_check_entry(struct ipt_entry *e, struct net *net, const char *name, } t = ipt_get_target(e); - target = try_then_request_module(xt_find_target(AF_INET, - t->u.user.name, - t->u.user.revision), - "ipt_%s", t->u.user.name); - if (IS_ERR(target) || !target) { + target = xt_request_find_target(NFPROTO_IPV4, t->u.user.name, + t->u.user.revision); + if (IS_ERR(target)) { duprintf("find_check_entry: `%s' not found\n", t->u.user.name); - ret = target ? PTR_ERR(target) : -ENOENT; + ret = PTR_ERR(target); goto cleanup_matches; } t->u.kernel.target = target; @@ -843,6 +819,9 @@ translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0, if (ret != 0) return ret; ++i; + if (strcmp(ipt_get_target(iter)->u.user.name, + XT_ERROR_TARGET) == 0) + ++newinfo->stacksize; } if (i != repl->num_entries) { @@ -1311,7 +1290,7 @@ do_replace(struct net *net, const void __user *user, unsigned int len) if (ret != 0) goto free_newinfo; - duprintf("ip_tables: Translated table\n"); + duprintf("Translated table\n"); ret = __do_replace(net, tmp.name, tmp.valid_hooks, newinfo, tmp.num_counters, tmp.counters); @@ -1476,13 +1455,12 @@ compat_find_calc_match(struct ipt_entry_match *m, { struct xt_match *match; - match = try_then_request_module(xt_find_match(AF_INET, m->u.user.name, - m->u.user.revision), - "ipt_%s", m->u.user.name); - if (IS_ERR(match) || !match) { + match = xt_request_find_match(NFPROTO_IPV4, m->u.user.name, + m->u.user.revision); + if (IS_ERR(match)) { duprintf("compat_check_calc_match: `%s' not found\n", m->u.user.name); - return match ? PTR_ERR(match) : -ENOENT; + return PTR_ERR(match); } m->u.kernel.match = match; *size += xt_compat_match_offset(match); @@ -1549,14 +1527,12 @@ check_compat_entry_size_and_hooks(struct compat_ipt_entry *e, } t = compat_ipt_get_target(e); - target = try_then_request_module(xt_find_target(AF_INET, - t->u.user.name, - t->u.user.revision), - "ipt_%s", t->u.user.name); - if (IS_ERR(target) || !target) { + target = xt_request_find_target(NFPROTO_IPV4, t->u.user.name, + t->u.user.revision); + if (IS_ERR(target)) { duprintf("check_compat_entry_size_and_hooks: `%s' not found\n", t->u.user.name); - ret = target ? PTR_ERR(target) : -ENOENT; + ret = PTR_ERR(target); goto release_matches; } t->u.kernel.target = target; @@ -2094,8 +2070,7 @@ struct xt_table *ipt_register_table(struct net *net, { int ret; struct xt_table_info *newinfo; - struct xt_table_info bootstrap - = { 0, 0, 0, { 0 }, { 0 }, { } }; + struct xt_table_info bootstrap = {0}; void *loc_cpu_entry; struct xt_table *new_table; @@ -2157,7 +2132,7 @@ icmp_type_code_match(u_int8_t test_type, u_int8_t min_code, u_int8_t max_code, } static bool -icmp_match(const struct sk_buff *skb, const struct xt_match_param *par) +icmp_match(const struct sk_buff *skb, struct xt_action_param *par) { const struct icmphdr *ic; struct icmphdr _icmph; @@ -2173,7 +2148,7 @@ icmp_match(const struct sk_buff *skb, const struct xt_match_param *par) * can't. Hence, no choice but to drop. */ duprintf("Dropping evil ICMP tinygram.\n"); - *par->hotdrop = true; + par->hotdrop = true; return false; } @@ -2184,31 +2159,31 @@ icmp_match(const struct sk_buff *skb, const struct xt_match_param *par) !!(icmpinfo->invflags&IPT_ICMP_INV)); } -static bool icmp_checkentry(const struct xt_mtchk_param *par) +static int icmp_checkentry(const struct xt_mtchk_param *par) { const struct ipt_icmp *icmpinfo = par->matchinfo; /* Must specify no unknown invflags */ - return !(icmpinfo->invflags & ~IPT_ICMP_INV); + return (icmpinfo->invflags & ~IPT_ICMP_INV) ? -EINVAL : 0; } -/* The built-in targets: standard (NULL) and error. */ -static struct xt_target ipt_standard_target __read_mostly = { - .name = IPT_STANDARD_TARGET, - .targetsize = sizeof(int), - .family = NFPROTO_IPV4, +static struct xt_target ipt_builtin_tg[] __read_mostly = { + { + .name = IPT_STANDARD_TARGET, + .targetsize = sizeof(int), + .family = NFPROTO_IPV4, #ifdef CONFIG_COMPAT - .compatsize = sizeof(compat_int_t), - .compat_from_user = compat_standard_from_user, - .compat_to_user = compat_standard_to_user, + .compatsize = sizeof(compat_int_t), + .compat_from_user = compat_standard_from_user, + .compat_to_user = compat_standard_to_user, #endif -}; - -static struct xt_target ipt_error_target __read_mostly = { - .name = IPT_ERROR_TARGET, - .target = ipt_error, - .targetsize = IPT_FUNCTION_MAXNAMELEN, - .family = NFPROTO_IPV4, + }, + { + .name = IPT_ERROR_TARGET, + .target = ipt_error, + .targetsize = IPT_FUNCTION_MAXNAMELEN, + .family = NFPROTO_IPV4, + }, }; static struct nf_sockopt_ops ipt_sockopts = { @@ -2228,13 +2203,15 @@ static struct nf_sockopt_ops ipt_sockopts = { .owner = THIS_MODULE, }; -static struct xt_match icmp_matchstruct __read_mostly = { - .name = "icmp", - .match = icmp_match, - .matchsize = sizeof(struct ipt_icmp), - .checkentry = icmp_checkentry, - .proto = IPPROTO_ICMP, - .family = NFPROTO_IPV4, +static struct xt_match ipt_builtin_mt[] __read_mostly = { + { + .name = "icmp", + .match = icmp_match, + .matchsize = sizeof(struct ipt_icmp), + .checkentry = icmp_checkentry, + .proto = IPPROTO_ICMP, + .family = NFPROTO_IPV4, + }, }; static int __net_init ip_tables_net_init(struct net *net) @@ -2261,13 +2238,10 @@ static int __init ip_tables_init(void) goto err1; /* Noone else will be downing sem now, so we won't sleep */ - ret = xt_register_target(&ipt_standard_target); + ret = xt_register_targets(ipt_builtin_tg, ARRAY_SIZE(ipt_builtin_tg)); if (ret < 0) goto err2; - ret = xt_register_target(&ipt_error_target); - if (ret < 0) - goto err3; - ret = xt_register_match(&icmp_matchstruct); + ret = xt_register_matches(ipt_builtin_mt, ARRAY_SIZE(ipt_builtin_mt)); if (ret < 0) goto err4; @@ -2276,15 +2250,13 @@ static int __init ip_tables_init(void) if (ret < 0) goto err5; - printk(KERN_INFO "ip_tables: (C) 2000-2006 Netfilter Core Team\n"); + pr_info("(C) 2000-2006 Netfilter Core Team\n"); return 0; err5: - xt_unregister_match(&icmp_matchstruct); + xt_unregister_matches(ipt_builtin_mt, ARRAY_SIZE(ipt_builtin_mt)); err4: - xt_unregister_target(&ipt_error_target); -err3: - xt_unregister_target(&ipt_standard_target); + xt_unregister_targets(ipt_builtin_tg, ARRAY_SIZE(ipt_builtin_tg)); err2: unregister_pernet_subsys(&ip_tables_net_ops); err1: @@ -2295,10 +2267,8 @@ static void __exit ip_tables_fini(void) { nf_unregister_sockopt(&ipt_sockopts); - xt_unregister_match(&icmp_matchstruct); - xt_unregister_target(&ipt_error_target); - xt_unregister_target(&ipt_standard_target); - + xt_unregister_matches(ipt_builtin_mt, ARRAY_SIZE(ipt_builtin_mt)); + xt_unregister_targets(ipt_builtin_tg, ARRAY_SIZE(ipt_builtin_tg)); unregister_pernet_subsys(&ip_tables_net_ops); } diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c index ab828400ed71..f91c94b9a790 100644 --- a/net/ipv4/netfilter/ipt_CLUSTERIP.c +++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c @@ -9,6 +9,7 @@ * published by the Free Software Foundation. * */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/proc_fs.h> #include <linux/jhash.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 @@ -239,8 +240,7 @@ clusterip_hashfn(const struct sk_buff *skb, break; default: if (net_ratelimit()) - printk(KERN_NOTICE "CLUSTERIP: unknown protocol `%u'\n", - iph->protocol); + pr_info("unknown protocol %u\n", iph->protocol); sport = dport = 0; } @@ -262,7 +262,7 @@ clusterip_hashfn(const struct sk_buff *skb, hashval = 0; /* This cannot happen, unless the check function wasn't called * at rule load time */ - printk("CLUSTERIP: unknown mode `%u'\n", config->hash_mode); + pr_info("unknown mode %u\n", config->hash_mode); BUG(); break; } @@ -282,7 +282,7 @@ clusterip_responsible(const struct clusterip_config *config, u_int32_t hash) ***********************************************************************/ static unsigned int -clusterip_tg(struct sk_buff *skb, const struct xt_target_param *par) +clusterip_tg(struct sk_buff *skb, const struct xt_action_param *par) { const struct ipt_clusterip_tgt_info *cipinfo = par->targinfo; struct nf_conn *ct; @@ -295,7 +295,7 @@ clusterip_tg(struct sk_buff *skb, const struct xt_target_param *par) ct = nf_ct_get(skb, &ctinfo); if (ct == NULL) { - printk(KERN_ERR "CLUSTERIP: no conntrack!\n"); + pr_info("no conntrack!\n"); /* FIXME: need to drop invalid ones, since replies * to outgoing connections of other nodes will be * marked as INVALID */ @@ -348,25 +348,24 @@ clusterip_tg(struct sk_buff *skb, const struct xt_target_param *par) return XT_CONTINUE; } -static bool clusterip_tg_check(const struct xt_tgchk_param *par) +static int clusterip_tg_check(const struct xt_tgchk_param *par) { struct ipt_clusterip_tgt_info *cipinfo = par->targinfo; const struct ipt_entry *e = par->entryinfo; - struct clusterip_config *config; + int ret; if (cipinfo->hash_mode != CLUSTERIP_HASHMODE_SIP && cipinfo->hash_mode != CLUSTERIP_HASHMODE_SIP_SPT && cipinfo->hash_mode != CLUSTERIP_HASHMODE_SIP_SPT_DPT) { - printk(KERN_WARNING "CLUSTERIP: unknown mode `%u'\n", - cipinfo->hash_mode); - return false; + pr_info("unknown mode %u\n", cipinfo->hash_mode); + return -EINVAL; } if (e->ip.dmsk.s_addr != htonl(0xffffffff) || e->ip.dst.s_addr == 0) { - printk(KERN_ERR "CLUSTERIP: Please specify destination IP\n"); - return false; + pr_info("Please specify destination IP\n"); + return -EINVAL; } /* FIXME: further sanity checks */ @@ -374,41 +373,41 @@ static bool clusterip_tg_check(const struct xt_tgchk_param *par) config = clusterip_config_find_get(e->ip.dst.s_addr, 1); if (!config) { if (!(cipinfo->flags & CLUSTERIP_FLAG_NEW)) { - printk(KERN_WARNING "CLUSTERIP: no config found for %pI4, need 'new'\n", &e->ip.dst.s_addr); - return false; + pr_info("no config found for %pI4, need 'new'\n", + &e->ip.dst.s_addr); + return -EINVAL; } else { struct net_device *dev; if (e->ip.iniface[0] == '\0') { - printk(KERN_WARNING "CLUSTERIP: Please specify an interface name\n"); - return false; + pr_info("Please specify an interface name\n"); + return -EINVAL; } dev = dev_get_by_name(&init_net, e->ip.iniface); if (!dev) { - printk(KERN_WARNING "CLUSTERIP: no such interface %s\n", e->ip.iniface); - return false; + pr_info("no such interface %s\n", + e->ip.iniface); + return -ENOENT; } config = clusterip_config_init(cipinfo, e->ip.dst.s_addr, dev); if (!config) { - printk(KERN_WARNING "CLUSTERIP: cannot allocate config\n"); + pr_info("cannot allocate config\n"); dev_put(dev); - return false; + return -ENOMEM; } - dev_mc_add(config->dev,config->clustermac, ETH_ALEN, 0); + dev_mc_add(config->dev, config->clustermac); } } cipinfo->config = config; - if (nf_ct_l3proto_try_module_get(par->target->family) < 0) { - printk(KERN_WARNING "can't load conntrack support for " - "proto=%u\n", par->target->family); - return false; - } - - return true; + ret = nf_ct_l3proto_try_module_get(par->family); + if (ret < 0) + pr_info("cannot load conntrack support for proto=%u\n", + par->family); + return ret; } /* drop reference count of cluster config when rule is deleted */ @@ -422,7 +421,7 @@ static void clusterip_tg_destroy(const struct xt_tgdtor_param *par) clusterip_config_put(cipinfo->config); - nf_ct_l3proto_module_put(par->target->family); + nf_ct_l3proto_module_put(par->family); } #ifdef CONFIG_COMPAT @@ -479,8 +478,8 @@ static void arp_print(struct arp_payload *payload) } hbuffer[--k]='\0'; - printk("src %pI4@%s, dst %pI4\n", - &payload->src_ip, hbuffer, &payload->dst_ip); + pr_debug("src %pI4@%s, dst %pI4\n", + &payload->src_ip, hbuffer, &payload->dst_ip); } #endif @@ -519,7 +518,7 @@ arp_mangle(unsigned int hook, * this wouldn't work, since we didn't subscribe the mcast group on * other interfaces */ if (c->dev != out) { - pr_debug("CLUSTERIP: not mangling arp reply on different " + pr_debug("not mangling arp reply on different " "interface: cip'%s'-skb'%s'\n", c->dev->name, out->name); clusterip_config_put(c); @@ -530,7 +529,7 @@ arp_mangle(unsigned int hook, memcpy(payload->src_hw, c->clustermac, arp->ar_hln); #ifdef DEBUG - pr_debug(KERN_DEBUG "CLUSTERIP mangled arp reply: "); + pr_debug("mangled arp reply: "); arp_print(payload); #endif @@ -601,7 +600,8 @@ static void *clusterip_seq_next(struct seq_file *s, void *v, loff_t *pos) static void clusterip_seq_stop(struct seq_file *s, void *v) { - kfree(v); + if (!IS_ERR(v)) + kfree(v); } static int clusterip_seq_show(struct seq_file *s, void *v) @@ -706,13 +706,13 @@ static int __init clusterip_tg_init(void) #ifdef CONFIG_PROC_FS clusterip_procdir = proc_mkdir("ipt_CLUSTERIP", init_net.proc_net); if (!clusterip_procdir) { - printk(KERN_ERR "CLUSTERIP: Unable to proc dir entry\n"); + pr_err("Unable to proc dir entry\n"); ret = -ENOMEM; goto cleanup_hook; } #endif /* CONFIG_PROC_FS */ - printk(KERN_NOTICE "ClusterIP Version %s loaded successfully\n", + pr_info("ClusterIP Version %s loaded successfully\n", CLUSTERIP_VERSION); return 0; @@ -727,8 +727,7 @@ cleanup_target: static void __exit clusterip_tg_exit(void) { - printk(KERN_NOTICE "ClusterIP Version %s unloading\n", - CLUSTERIP_VERSION); + pr_info("ClusterIP Version %s unloading\n", CLUSTERIP_VERSION); #ifdef CONFIG_PROC_FS remove_proc_entry(clusterip_procdir->name, clusterip_procdir->parent); #endif diff --git a/net/ipv4/netfilter/ipt_ECN.c b/net/ipv4/netfilter/ipt_ECN.c index ea5cea2415c1..4bf3dc49ad1e 100644 --- a/net/ipv4/netfilter/ipt_ECN.c +++ b/net/ipv4/netfilter/ipt_ECN.c @@ -6,7 +6,7 @@ * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. */ - +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/in.h> #include <linux/module.h> #include <linux/skbuff.h> @@ -77,7 +77,7 @@ set_ect_tcp(struct sk_buff *skb, const struct ipt_ECN_info *einfo) } static unsigned int -ecn_tg(struct sk_buff *skb, const struct xt_target_param *par) +ecn_tg(struct sk_buff *skb, const struct xt_action_param *par) { const struct ipt_ECN_info *einfo = par->targinfo; @@ -93,28 +93,25 @@ ecn_tg(struct sk_buff *skb, const struct xt_target_param *par) return XT_CONTINUE; } -static bool ecn_tg_check(const struct xt_tgchk_param *par) +static int ecn_tg_check(const struct xt_tgchk_param *par) { const struct ipt_ECN_info *einfo = par->targinfo; const struct ipt_entry *e = par->entryinfo; if (einfo->operation & IPT_ECN_OP_MASK) { - printk(KERN_WARNING "ECN: unsupported ECN operation %x\n", - einfo->operation); - return false; + pr_info("unsupported ECN operation %x\n", einfo->operation); + return -EINVAL; } if (einfo->ip_ect & ~IPT_ECN_IP_MASK) { - printk(KERN_WARNING "ECN: new ECT codepoint %x out of mask\n", - einfo->ip_ect); - return false; + pr_info("new ECT codepoint %x out of mask\n", einfo->ip_ect); + return -EINVAL; } if ((einfo->operation & (IPT_ECN_OP_SET_ECE|IPT_ECN_OP_SET_CWR)) && (e->ip.proto != IPPROTO_TCP || (e->ip.invflags & XT_INV_PROTO))) { - printk(KERN_WARNING "ECN: cannot use TCP operations on a " - "non-tcp rule\n"); - return false; + pr_info("cannot use TCP operations on a non-tcp rule\n"); + return -EINVAL; } - return true; + return 0; } static struct xt_target ecn_tg_reg __read_mostly = { diff --git a/net/ipv4/netfilter/ipt_LOG.c b/net/ipv4/netfilter/ipt_LOG.c index ee128efa1c8d..5234f4f3499a 100644 --- a/net/ipv4/netfilter/ipt_LOG.c +++ b/net/ipv4/netfilter/ipt_LOG.c @@ -9,7 +9,7 @@ * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. */ - +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/spinlock.h> #include <linux/skbuff.h> @@ -367,7 +367,7 @@ static struct nf_loginfo default_loginfo = { .type = NF_LOG_TYPE_LOG, .u = { .log = { - .level = 0, + .level = 5, .logflags = NF_LOG_MASK, }, }, @@ -425,7 +425,7 @@ ipt_log_packet(u_int8_t pf, } static unsigned int -log_tg(struct sk_buff *skb, const struct xt_target_param *par) +log_tg(struct sk_buff *skb, const struct xt_action_param *par) { const struct ipt_log_info *loginfo = par->targinfo; struct nf_loginfo li; @@ -439,20 +439,19 @@ log_tg(struct sk_buff *skb, const struct xt_target_param *par) return XT_CONTINUE; } -static bool log_tg_check(const struct xt_tgchk_param *par) +static int log_tg_check(const struct xt_tgchk_param *par) { const struct ipt_log_info *loginfo = par->targinfo; if (loginfo->level >= 8) { - pr_debug("LOG: level %u >= 8\n", loginfo->level); - return false; + pr_debug("level %u >= 8\n", loginfo->level); + return -EINVAL; } if (loginfo->prefix[sizeof(loginfo->prefix)-1] != '\0') { - pr_debug("LOG: prefix term %i\n", - loginfo->prefix[sizeof(loginfo->prefix)-1]); - return false; + pr_debug("prefix is not null-terminated\n"); + return -EINVAL; } - return true; + return 0; } static struct xt_target log_tg_reg __read_mostly = { diff --git a/net/ipv4/netfilter/ipt_MASQUERADE.c b/net/ipv4/netfilter/ipt_MASQUERADE.c index 650b54042b01..d2ed9dc74ebc 100644 --- a/net/ipv4/netfilter/ipt_MASQUERADE.c +++ b/net/ipv4/netfilter/ipt_MASQUERADE.c @@ -8,7 +8,7 @@ * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. */ - +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/types.h> #include <linux/inetdevice.h> #include <linux/ip.h> @@ -28,23 +28,23 @@ MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>"); MODULE_DESCRIPTION("Xtables: automatic-address SNAT"); /* FIXME: Multiple targets. --RR */ -static bool masquerade_tg_check(const struct xt_tgchk_param *par) +static int masquerade_tg_check(const struct xt_tgchk_param *par) { const struct nf_nat_multi_range_compat *mr = par->targinfo; if (mr->range[0].flags & IP_NAT_RANGE_MAP_IPS) { - pr_debug("masquerade_check: bad MAP_IPS.\n"); - return false; + pr_debug("bad MAP_IPS.\n"); + return -EINVAL; } if (mr->rangesize != 1) { - pr_debug("masquerade_check: bad rangesize %u\n", mr->rangesize); - return false; + pr_debug("bad rangesize %u\n", mr->rangesize); + return -EINVAL; } - return true; + return 0; } static unsigned int -masquerade_tg(struct sk_buff *skb, const struct xt_target_param *par) +masquerade_tg(struct sk_buff *skb, const struct xt_action_param *par) { struct nf_conn *ct; struct nf_conn_nat *nat; @@ -72,7 +72,7 @@ masquerade_tg(struct sk_buff *skb, const struct xt_target_param *par) rt = skb_rtable(skb); newsrc = inet_select_addr(par->out, rt->rt_gateway, RT_SCOPE_UNIVERSE); if (!newsrc) { - printk("MASQUERADE: %s ate my IP address\n", par->out->name); + pr_info("%s ate my IP address\n", par->out->name); return NF_DROP; } diff --git a/net/ipv4/netfilter/ipt_NETMAP.c b/net/ipv4/netfilter/ipt_NETMAP.c index 7c29582d4ec8..f43867d1697f 100644 --- a/net/ipv4/netfilter/ipt_NETMAP.c +++ b/net/ipv4/netfilter/ipt_NETMAP.c @@ -9,7 +9,7 @@ * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. */ - +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/ip.h> #include <linux/module.h> #include <linux/netdevice.h> @@ -22,23 +22,23 @@ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Svenning Soerensen <svenning@post5.tele.dk>"); MODULE_DESCRIPTION("Xtables: 1:1 NAT mapping of IPv4 subnets"); -static bool netmap_tg_check(const struct xt_tgchk_param *par) +static int netmap_tg_check(const struct xt_tgchk_param *par) { const struct nf_nat_multi_range_compat *mr = par->targinfo; if (!(mr->range[0].flags & IP_NAT_RANGE_MAP_IPS)) { - pr_debug("NETMAP:check: bad MAP_IPS.\n"); - return false; + pr_debug("bad MAP_IPS.\n"); + return -EINVAL; } if (mr->rangesize != 1) { - pr_debug("NETMAP:check: bad rangesize %u.\n", mr->rangesize); - return false; + pr_debug("bad rangesize %u.\n", mr->rangesize); + return -EINVAL; } - return true; + return 0; } static unsigned int -netmap_tg(struct sk_buff *skb, const struct xt_target_param *par) +netmap_tg(struct sk_buff *skb, const struct xt_action_param *par) { struct nf_conn *ct; enum ip_conntrack_info ctinfo; diff --git a/net/ipv4/netfilter/ipt_REDIRECT.c b/net/ipv4/netfilter/ipt_REDIRECT.c index 698e5e78685b..18a0656505a0 100644 --- a/net/ipv4/netfilter/ipt_REDIRECT.c +++ b/net/ipv4/netfilter/ipt_REDIRECT.c @@ -6,7 +6,7 @@ * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. */ - +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/types.h> #include <linux/ip.h> #include <linux/timer.h> @@ -26,23 +26,23 @@ MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>"); MODULE_DESCRIPTION("Xtables: Connection redirection to localhost"); /* FIXME: Take multiple ranges --RR */ -static bool redirect_tg_check(const struct xt_tgchk_param *par) +static int redirect_tg_check(const struct xt_tgchk_param *par) { const struct nf_nat_multi_range_compat *mr = par->targinfo; if (mr->range[0].flags & IP_NAT_RANGE_MAP_IPS) { - pr_debug("redirect_check: bad MAP_IPS.\n"); - return false; + pr_debug("bad MAP_IPS.\n"); + return -EINVAL; } if (mr->rangesize != 1) { - pr_debug("redirect_check: bad rangesize %u.\n", mr->rangesize); - return false; + pr_debug("bad rangesize %u.\n", mr->rangesize); + return -EINVAL; } - return true; + return 0; } static unsigned int -redirect_tg(struct sk_buff *skb, const struct xt_target_param *par) +redirect_tg(struct sk_buff *skb, const struct xt_action_param *par) { struct nf_conn *ct; enum ip_conntrack_info ctinfo; diff --git a/net/ipv4/netfilter/ipt_REJECT.c b/net/ipv4/netfilter/ipt_REJECT.c index a0e8bcf04159..f5f4a888e4ec 100644 --- a/net/ipv4/netfilter/ipt_REJECT.c +++ b/net/ipv4/netfilter/ipt_REJECT.c @@ -9,7 +9,7 @@ * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. */ - +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/skbuff.h> #include <linux/slab.h> @@ -136,13 +136,10 @@ static inline void send_unreach(struct sk_buff *skb_in, int code) } static unsigned int -reject_tg(struct sk_buff *skb, const struct xt_target_param *par) +reject_tg(struct sk_buff *skb, const struct xt_action_param *par) { const struct ipt_reject_info *reject = par->targinfo; - /* WARNING: This code causes reentry within iptables. - This means that the iptables jump stack is now crap. We - must return an absolute verdict. --RR */ switch (reject->with) { case IPT_ICMP_NET_UNREACHABLE: send_unreach(skb, ICMP_NET_UNREACH); @@ -175,23 +172,23 @@ reject_tg(struct sk_buff *skb, const struct xt_target_param *par) return NF_DROP; } -static bool reject_tg_check(const struct xt_tgchk_param *par) +static int reject_tg_check(const struct xt_tgchk_param *par) { const struct ipt_reject_info *rejinfo = par->targinfo; const struct ipt_entry *e = par->entryinfo; if (rejinfo->with == IPT_ICMP_ECHOREPLY) { - printk("ipt_REJECT: ECHOREPLY no longer supported.\n"); - return false; + pr_info("ECHOREPLY no longer supported.\n"); + return -EINVAL; } else if (rejinfo->with == IPT_TCP_RESET) { /* Must specify that it's a TCP packet */ if (e->ip.proto != IPPROTO_TCP || (e->ip.invflags & XT_INV_PROTO)) { - printk("ipt_REJECT: TCP_RESET invalid for non-tcp\n"); - return false; + pr_info("TCP_RESET invalid for non-tcp\n"); + return -EINVAL; } } - return true; + return 0; } static struct xt_target reject_tg_reg __read_mostly = { diff --git a/net/ipv4/netfilter/ipt_ULOG.c b/net/ipv4/netfilter/ipt_ULOG.c index 0dbe697f164f..446e0f467a17 100644 --- a/net/ipv4/netfilter/ipt_ULOG.c +++ b/net/ipv4/netfilter/ipt_ULOG.c @@ -29,7 +29,7 @@ * Specify, after how many hundredths of a second the queue should be * flushed even if it is not full yet. */ - +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/spinlock.h> #include <linux/socket.h> @@ -57,8 +57,6 @@ MODULE_ALIAS_NET_PF_PROTO(PF_NETLINK, NETLINK_NFLOG); #define ULOG_NL_EVENT 111 /* Harald's favorite number */ #define ULOG_MAXNLGROUPS 32 /* numer of nlgroups */ -#define PRINTR(format, args...) do { if (net_ratelimit()) printk(format , ## args); } while (0) - static unsigned int nlbufsiz = NLMSG_GOODSIZE; module_param(nlbufsiz, uint, 0400); MODULE_PARM_DESC(nlbufsiz, "netlink buffer size"); @@ -91,12 +89,12 @@ static void ulog_send(unsigned int nlgroupnum) ulog_buff_t *ub = &ulog_buffers[nlgroupnum]; if (timer_pending(&ub->timer)) { - pr_debug("ipt_ULOG: ulog_send: timer was pending, deleting\n"); + pr_debug("ulog_send: timer was pending, deleting\n"); del_timer(&ub->timer); } if (!ub->skb) { - pr_debug("ipt_ULOG: ulog_send: nothing to send\n"); + pr_debug("ulog_send: nothing to send\n"); return; } @@ -105,7 +103,7 @@ static void ulog_send(unsigned int nlgroupnum) ub->lastnlh->nlmsg_type = NLMSG_DONE; NETLINK_CB(ub->skb).dst_group = nlgroupnum + 1; - pr_debug("ipt_ULOG: throwing %d packets to netlink group %u\n", + pr_debug("throwing %d packets to netlink group %u\n", ub->qlen, nlgroupnum + 1); netlink_broadcast(nflognl, ub->skb, 0, nlgroupnum + 1, GFP_ATOMIC); @@ -118,7 +116,7 @@ static void ulog_send(unsigned int nlgroupnum) /* timer function to flush queue in flushtimeout time */ static void ulog_timer(unsigned long data) { - pr_debug("ipt_ULOG: timer function called, calling ulog_send\n"); + pr_debug("timer function called, calling ulog_send\n"); /* lock to protect against somebody modifying our structure * from ipt_ulog_target at the same time */ @@ -139,7 +137,7 @@ static struct sk_buff *ulog_alloc_skb(unsigned int size) n = max(size, nlbufsiz); skb = alloc_skb(n, GFP_ATOMIC); if (!skb) { - PRINTR("ipt_ULOG: can't alloc whole buffer %ub!\n", n); + pr_debug("cannot alloc whole buffer %ub!\n", n); if (n > size) { /* try to allocate only as much as we need for @@ -147,8 +145,7 @@ static struct sk_buff *ulog_alloc_skb(unsigned int size) skb = alloc_skb(size, GFP_ATOMIC); if (!skb) - PRINTR("ipt_ULOG: can't even allocate %ub\n", - size); + pr_debug("cannot even allocate %ub\n", size); } } @@ -199,8 +196,7 @@ static void ipt_ulog_packet(unsigned int hooknum, goto alloc_failure; } - pr_debug("ipt_ULOG: qlen %d, qthreshold %Zu\n", ub->qlen, - loginfo->qthreshold); + pr_debug("qlen %d, qthreshold %Zu\n", ub->qlen, loginfo->qthreshold); /* NLMSG_PUT contains a hidden goto nlmsg_failure !!! */ nlh = NLMSG_PUT(ub->skb, 0, ub->qlen, ULOG_NL_EVENT, @@ -273,16 +269,14 @@ static void ipt_ulog_packet(unsigned int hooknum, return; nlmsg_failure: - PRINTR("ipt_ULOG: error during NLMSG_PUT\n"); - + pr_debug("error during NLMSG_PUT\n"); alloc_failure: - PRINTR("ipt_ULOG: Error building netlink message\n"); - + pr_debug("Error building netlink message\n"); spin_unlock_bh(&ulog_lock); } static unsigned int -ulog_tg(struct sk_buff *skb, const struct xt_target_param *par) +ulog_tg(struct sk_buff *skb, const struct xt_action_param *par) { ipt_ulog_packet(par->hooknum, skb, par->in, par->out, par->targinfo, NULL); @@ -314,21 +308,20 @@ static void ipt_logfn(u_int8_t pf, ipt_ulog_packet(hooknum, skb, in, out, &loginfo, prefix); } -static bool ulog_tg_check(const struct xt_tgchk_param *par) +static int ulog_tg_check(const struct xt_tgchk_param *par) { const struct ipt_ulog_info *loginfo = par->targinfo; if (loginfo->prefix[sizeof(loginfo->prefix) - 1] != '\0') { - pr_debug("ipt_ULOG: prefix term %i\n", - loginfo->prefix[sizeof(loginfo->prefix) - 1]); - return false; + pr_debug("prefix not null-terminated\n"); + return -EINVAL; } if (loginfo->qthreshold > ULOG_MAX_QLEN) { - pr_debug("ipt_ULOG: queue threshold %Zu > MAX_QLEN\n", + pr_debug("queue threshold %Zu > MAX_QLEN\n", loginfo->qthreshold); - return false; + return -EINVAL; } - return true; + return 0; } #ifdef CONFIG_COMPAT @@ -390,10 +383,10 @@ static int __init ulog_tg_init(void) { int ret, i; - pr_debug("ipt_ULOG: init module\n"); + pr_debug("init module\n"); if (nlbufsiz > 128*1024) { - printk("Netlink buffer has to be <= 128kB\n"); + pr_warning("Netlink buffer has to be <= 128kB\n"); return -EINVAL; } @@ -423,7 +416,7 @@ static void __exit ulog_tg_exit(void) ulog_buff_t *ub; int i; - pr_debug("ipt_ULOG: cleanup_module\n"); + pr_debug("cleanup_module\n"); if (nflog) nf_log_unregister(&ipt_ulog_logger); diff --git a/net/ipv4/netfilter/ipt_addrtype.c b/net/ipv4/netfilter/ipt_addrtype.c index 3b216be3bc9f..db8bff0fb86d 100644 --- a/net/ipv4/netfilter/ipt_addrtype.c +++ b/net/ipv4/netfilter/ipt_addrtype.c @@ -8,7 +8,7 @@ * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. */ - +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kernel.h> #include <linux/module.h> #include <linux/skbuff.h> @@ -30,7 +30,7 @@ static inline bool match_type(struct net *net, const struct net_device *dev, } static bool -addrtype_mt_v0(const struct sk_buff *skb, const struct xt_match_param *par) +addrtype_mt_v0(const struct sk_buff *skb, struct xt_action_param *par) { struct net *net = dev_net(par->in ? par->in : par->out); const struct ipt_addrtype_info *info = par->matchinfo; @@ -48,7 +48,7 @@ addrtype_mt_v0(const struct sk_buff *skb, const struct xt_match_param *par) } static bool -addrtype_mt_v1(const struct sk_buff *skb, const struct xt_match_param *par) +addrtype_mt_v1(const struct sk_buff *skb, struct xt_action_param *par) { struct net *net = dev_net(par->in ? par->in : par->out); const struct ipt_addrtype_info_v1 *info = par->matchinfo; @@ -70,34 +70,34 @@ addrtype_mt_v1(const struct sk_buff *skb, const struct xt_match_param *par) return ret; } -static bool addrtype_mt_checkentry_v1(const struct xt_mtchk_param *par) +static int addrtype_mt_checkentry_v1(const struct xt_mtchk_param *par) { struct ipt_addrtype_info_v1 *info = par->matchinfo; if (info->flags & IPT_ADDRTYPE_LIMIT_IFACE_IN && info->flags & IPT_ADDRTYPE_LIMIT_IFACE_OUT) { - printk(KERN_ERR "ipt_addrtype: both incoming and outgoing " - "interface limitation cannot be selected\n"); - return false; + pr_info("both incoming and outgoing " + "interface limitation cannot be selected\n"); + return -EINVAL; } if (par->hook_mask & ((1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_IN)) && info->flags & IPT_ADDRTYPE_LIMIT_IFACE_OUT) { - printk(KERN_ERR "ipt_addrtype: output interface limitation " - "not valid in PRE_ROUTING and INPUT\n"); - return false; + pr_info("output interface limitation " + "not valid in PREROUTING and INPUT\n"); + return -EINVAL; } if (par->hook_mask & ((1 << NF_INET_POST_ROUTING) | (1 << NF_INET_LOCAL_OUT)) && info->flags & IPT_ADDRTYPE_LIMIT_IFACE_IN) { - printk(KERN_ERR "ipt_addrtype: input interface limitation " - "not valid in POST_ROUTING and OUTPUT\n"); - return false; + pr_info("input interface limitation " + "not valid in POSTROUTING and OUTPUT\n"); + return -EINVAL; } - return true; + return 0; } static struct xt_match addrtype_mt_reg[] __read_mostly = { diff --git a/net/ipv4/netfilter/ipt_ah.c b/net/ipv4/netfilter/ipt_ah.c index 0104c0b399de..14a2aa8b8a14 100644 --- a/net/ipv4/netfilter/ipt_ah.c +++ b/net/ipv4/netfilter/ipt_ah.c @@ -5,7 +5,7 @@ * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. */ - +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/in.h> #include <linux/module.h> #include <linux/skbuff.h> @@ -18,25 +18,19 @@ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Yon Uriarte <yon@astaro.de>"); MODULE_DESCRIPTION("Xtables: IPv4 IPsec-AH SPI match"); -#ifdef DEBUG_CONNTRACK -#define duprintf(format, args...) printk(format , ## args) -#else -#define duprintf(format, args...) -#endif - /* Returns 1 if the spi is matched by the range, 0 otherwise */ static inline bool spi_match(u_int32_t min, u_int32_t max, u_int32_t spi, bool invert) { bool r; - duprintf("ah spi_match:%c 0x%x <= 0x%x <= 0x%x",invert? '!':' ', - min,spi,max); + pr_debug("spi_match:%c 0x%x <= 0x%x <= 0x%x\n", + invert ? '!' : ' ', min, spi, max); r=(spi >= min && spi <= max) ^ invert; - duprintf(" result %s\n",r? "PASS" : "FAILED"); + pr_debug(" result %s\n", r ? "PASS" : "FAILED"); return r; } -static bool ah_mt(const struct sk_buff *skb, const struct xt_match_param *par) +static bool ah_mt(const struct sk_buff *skb, struct xt_action_param *par) { struct ip_auth_hdr _ahdr; const struct ip_auth_hdr *ah; @@ -51,8 +45,8 @@ static bool ah_mt(const struct sk_buff *skb, const struct xt_match_param *par) /* We've been asked to examine this packet, and we * can't. Hence, no choice but to drop. */ - duprintf("Dropping evil AH tinygram.\n"); - *par->hotdrop = true; + pr_debug("Dropping evil AH tinygram.\n"); + par->hotdrop = true; return 0; } @@ -61,16 +55,16 @@ static bool ah_mt(const struct sk_buff *skb, const struct xt_match_param *par) !!(ahinfo->invflags & IPT_AH_INV_SPI)); } -static bool ah_mt_check(const struct xt_mtchk_param *par) +static int ah_mt_check(const struct xt_mtchk_param *par) { const struct ipt_ah *ahinfo = par->matchinfo; /* Must specify no unknown invflags */ if (ahinfo->invflags & ~IPT_AH_INV_MASK) { - duprintf("ipt_ah: unknown flags %X\n", ahinfo->invflags); - return false; + pr_debug("unknown flags %X\n", ahinfo->invflags); + return -EINVAL; } - return true; + return 0; } static struct xt_match ah_mt_reg __read_mostly = { diff --git a/net/ipv4/netfilter/ipt_ecn.c b/net/ipv4/netfilter/ipt_ecn.c index 2a1e56b71908..af6e9c778345 100644 --- a/net/ipv4/netfilter/ipt_ecn.c +++ b/net/ipv4/netfilter/ipt_ecn.c @@ -6,7 +6,7 @@ * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. */ - +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/in.h> #include <linux/ip.h> #include <net/ip.h> @@ -67,7 +67,7 @@ static inline bool match_tcp(const struct sk_buff *skb, return true; } -static bool ecn_mt(const struct sk_buff *skb, const struct xt_match_param *par) +static bool ecn_mt(const struct sk_buff *skb, struct xt_action_param *par) { const struct ipt_ecn_info *info = par->matchinfo; @@ -78,32 +78,31 @@ static bool ecn_mt(const struct sk_buff *skb, const struct xt_match_param *par) if (info->operation & (IPT_ECN_OP_MATCH_ECE|IPT_ECN_OP_MATCH_CWR)) { if (ip_hdr(skb)->protocol != IPPROTO_TCP) return false; - if (!match_tcp(skb, info, par->hotdrop)) + if (!match_tcp(skb, info, &par->hotdrop)) return false; } return true; } -static bool ecn_mt_check(const struct xt_mtchk_param *par) +static int ecn_mt_check(const struct xt_mtchk_param *par) { const struct ipt_ecn_info *info = par->matchinfo; const struct ipt_ip *ip = par->entryinfo; if (info->operation & IPT_ECN_OP_MATCH_MASK) - return false; + return -EINVAL; if (info->invert & IPT_ECN_OP_MATCH_MASK) - return false; + return -EINVAL; if (info->operation & (IPT_ECN_OP_MATCH_ECE|IPT_ECN_OP_MATCH_CWR) && ip->proto != IPPROTO_TCP) { - printk(KERN_WARNING "ipt_ecn: can't match TCP bits in rule for" - " non-tcp packets\n"); - return false; + pr_info("cannot match TCP bits in rule for non-tcp packets\n"); + return -EINVAL; } - return true; + return 0; } static struct xt_match ecn_mt_reg __read_mostly = { diff --git a/net/ipv4/netfilter/iptable_filter.c b/net/ipv4/netfilter/iptable_filter.c index 55392466daa4..c37641e819f2 100644 --- a/net/ipv4/netfilter/iptable_filter.c +++ b/net/ipv4/netfilter/iptable_filter.c @@ -89,7 +89,7 @@ static int __init iptable_filter_init(void) int ret; if (forward < 0 || forward > NF_MAX_VERDICT) { - printk("iptables forward must be 0 or 1\n"); + pr_err("iptables forward must be 0 or 1\n"); return -EINVAL; } diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c index 2bb1f87051c4..5a03c02af999 100644 --- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c +++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c @@ -382,32 +382,32 @@ static int __init nf_conntrack_l3proto_ipv4_init(void) ret = nf_conntrack_l4proto_register(&nf_conntrack_l4proto_tcp4); if (ret < 0) { - printk("nf_conntrack_ipv4: can't register tcp.\n"); + pr_err("nf_conntrack_ipv4: can't register tcp.\n"); goto cleanup_sockopt; } ret = nf_conntrack_l4proto_register(&nf_conntrack_l4proto_udp4); if (ret < 0) { - printk("nf_conntrack_ipv4: can't register udp.\n"); + pr_err("nf_conntrack_ipv4: can't register udp.\n"); goto cleanup_tcp; } ret = nf_conntrack_l4proto_register(&nf_conntrack_l4proto_icmp); if (ret < 0) { - printk("nf_conntrack_ipv4: can't register icmp.\n"); + pr_err("nf_conntrack_ipv4: can't register icmp.\n"); goto cleanup_udp; } ret = nf_conntrack_l3proto_register(&nf_conntrack_l3proto_ipv4); if (ret < 0) { - printk("nf_conntrack_ipv4: can't register ipv4\n"); + pr_err("nf_conntrack_ipv4: can't register ipv4\n"); goto cleanup_icmp; } ret = nf_register_hooks(ipv4_conntrack_ops, ARRAY_SIZE(ipv4_conntrack_ops)); if (ret < 0) { - printk("nf_conntrack_ipv4: can't register hooks.\n"); + pr_err("nf_conntrack_ipv4: can't register hooks.\n"); goto cleanup_ipv4; } #if defined(CONFIG_PROC_FS) && defined(CONFIG_NF_CONNTRACK_PROC_COMPAT) diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c index 2fb7b76da94f..244f7cb08d68 100644 --- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c +++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c @@ -336,12 +336,12 @@ static int ct_cpu_seq_show(struct seq_file *seq, void *v) const struct ip_conntrack_stat *st = v; if (v == SEQ_START_TOKEN) { - seq_printf(seq, "entries searched found new invalid ignore delete delete_list insert insert_failed drop early_drop icmp_error expect_new expect_create expect_delete\n"); + seq_printf(seq, "entries searched found new invalid ignore delete delete_list insert insert_failed drop early_drop icmp_error expect_new expect_create expect_delete search_restart\n"); return 0; } seq_printf(seq, "%08x %08x %08x %08x %08x %08x %08x %08x " - "%08x %08x %08x %08x %08x %08x %08x %08x \n", + "%08x %08x %08x %08x %08x %08x %08x %08x %08x\n", nr_conntracks, st->searched, st->found, @@ -358,7 +358,8 @@ static int ct_cpu_seq_show(struct seq_file *seq, void *v) st->expect_new, st->expect_create, - st->expect_delete + st->expect_delete, + st->search_restart ); return 0; } diff --git a/net/ipv4/netfilter/nf_nat_h323.c b/net/ipv4/netfilter/nf_nat_h323.c index 7e8e6fc75413..5045196d853c 100644 --- a/net/ipv4/netfilter/nf_nat_h323.c +++ b/net/ipv4/netfilter/nf_nat_h323.c @@ -10,7 +10,6 @@ */ #include <linux/module.h> -#include <linux/moduleparam.h> #include <linux/tcp.h> #include <net/tcp.h> @@ -44,7 +43,7 @@ static int set_addr(struct sk_buff *skb, addroff, sizeof(buf), (char *) &buf, sizeof(buf))) { if (net_ratelimit()) - printk("nf_nat_h323: nf_nat_mangle_tcp_packet" + pr_notice("nf_nat_h323: nf_nat_mangle_tcp_packet" " error\n"); return -1; } @@ -60,7 +59,7 @@ static int set_addr(struct sk_buff *skb, addroff, sizeof(buf), (char *) &buf, sizeof(buf))) { if (net_ratelimit()) - printk("nf_nat_h323: nf_nat_mangle_udp_packet" + pr_notice("nf_nat_h323: nf_nat_mangle_udp_packet" " error\n"); return -1; } @@ -216,7 +215,7 @@ static int nat_rtp_rtcp(struct sk_buff *skb, struct nf_conn *ct, /* Run out of expectations */ if (i >= H323_RTP_CHANNEL_MAX) { if (net_ratelimit()) - printk("nf_nat_h323: out of expectations\n"); + pr_notice("nf_nat_h323: out of expectations\n"); return 0; } @@ -235,7 +234,7 @@ static int nat_rtp_rtcp(struct sk_buff *skb, struct nf_conn *ct, if (nated_port == 0) { /* No port available */ if (net_ratelimit()) - printk("nf_nat_h323: out of RTP ports\n"); + pr_notice("nf_nat_h323: out of RTP ports\n"); return 0; } @@ -292,7 +291,7 @@ static int nat_t120(struct sk_buff *skb, struct nf_conn *ct, if (nated_port == 0) { /* No port available */ if (net_ratelimit()) - printk("nf_nat_h323: out of TCP ports\n"); + pr_notice("nf_nat_h323: out of TCP ports\n"); return 0; } @@ -342,7 +341,7 @@ static int nat_h245(struct sk_buff *skb, struct nf_conn *ct, if (nated_port == 0) { /* No port available */ if (net_ratelimit()) - printk("nf_nat_q931: out of TCP ports\n"); + pr_notice("nf_nat_q931: out of TCP ports\n"); return 0; } @@ -426,7 +425,7 @@ static int nat_q931(struct sk_buff *skb, struct nf_conn *ct, if (nated_port == 0) { /* No port available */ if (net_ratelimit()) - printk("nf_nat_ras: out of TCP ports\n"); + pr_notice("nf_nat_ras: out of TCP ports\n"); return 0; } @@ -508,7 +507,7 @@ static int nat_callforwarding(struct sk_buff *skb, struct nf_conn *ct, if (nated_port == 0) { /* No port available */ if (net_ratelimit()) - printk("nf_nat_q931: out of TCP ports\n"); + pr_notice("nf_nat_q931: out of TCP ports\n"); return 0; } diff --git a/net/ipv4/netfilter/nf_nat_rule.c b/net/ipv4/netfilter/nf_nat_rule.c index 26de2c1f7fab..98ed78281aee 100644 --- a/net/ipv4/netfilter/nf_nat_rule.c +++ b/net/ipv4/netfilter/nf_nat_rule.c @@ -7,6 +7,7 @@ */ /* Everything about the rules for NAT. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/types.h> #include <linux/ip.h> #include <linux/netfilter.h> @@ -38,7 +39,7 @@ static const struct xt_table nat_table = { /* Source NAT */ static unsigned int -ipt_snat_target(struct sk_buff *skb, const struct xt_target_param *par) +ipt_snat_target(struct sk_buff *skb, const struct xt_action_param *par) { struct nf_conn *ct; enum ip_conntrack_info ctinfo; @@ -57,7 +58,7 @@ ipt_snat_target(struct sk_buff *skb, const struct xt_target_param *par) } static unsigned int -ipt_dnat_target(struct sk_buff *skb, const struct xt_target_param *par) +ipt_dnat_target(struct sk_buff *skb, const struct xt_action_param *par) { struct nf_conn *ct; enum ip_conntrack_info ctinfo; @@ -74,28 +75,28 @@ ipt_dnat_target(struct sk_buff *skb, const struct xt_target_param *par) return nf_nat_setup_info(ct, &mr->range[0], IP_NAT_MANIP_DST); } -static bool ipt_snat_checkentry(const struct xt_tgchk_param *par) +static int ipt_snat_checkentry(const struct xt_tgchk_param *par) { const struct nf_nat_multi_range_compat *mr = par->targinfo; /* Must be a valid range */ if (mr->rangesize != 1) { - printk("SNAT: multiple ranges no longer supported\n"); - return false; + pr_info("SNAT: multiple ranges no longer supported\n"); + return -EINVAL; } - return true; + return 0; } -static bool ipt_dnat_checkentry(const struct xt_tgchk_param *par) +static int ipt_dnat_checkentry(const struct xt_tgchk_param *par) { const struct nf_nat_multi_range_compat *mr = par->targinfo; /* Must be a valid range */ if (mr->rangesize != 1) { - printk("DNAT: multiple ranges no longer supported\n"); - return false; + pr_info("DNAT: multiple ranges no longer supported\n"); + return -EINVAL; } - return true; + return 0; } unsigned int diff --git a/net/ipv4/netfilter/nf_nat_snmp_basic.c b/net/ipv4/netfilter/nf_nat_snmp_basic.c index 4d85b6e55f29..1679e2c0963d 100644 --- a/net/ipv4/netfilter/nf_nat_snmp_basic.c +++ b/net/ipv4/netfilter/nf_nat_snmp_basic.c @@ -401,7 +401,7 @@ static unsigned char asn1_octets_decode(struct asn1_ctx *ctx, *octets = kmalloc(eoc - ctx->pointer, GFP_ATOMIC); if (*octets == NULL) { if (net_ratelimit()) - printk("OOM in bsalg (%d)\n", __LINE__); + pr_notice("OOM in bsalg (%d)\n", __LINE__); return 0; } @@ -452,7 +452,7 @@ static unsigned char asn1_oid_decode(struct asn1_ctx *ctx, *oid = kmalloc(size * sizeof(unsigned long), GFP_ATOMIC); if (*oid == NULL) { if (net_ratelimit()) - printk("OOM in bsalg (%d)\n", __LINE__); + pr_notice("OOM in bsalg (%d)\n", __LINE__); return 0; } @@ -729,7 +729,7 @@ static unsigned char snmp_object_decode(struct asn1_ctx *ctx, if (*obj == NULL) { kfree(id); if (net_ratelimit()) - printk("OOM in bsalg (%d)\n", __LINE__); + pr_notice("OOM in bsalg (%d)\n", __LINE__); return 0; } (*obj)->syntax.l[0] = l; @@ -746,7 +746,7 @@ static unsigned char snmp_object_decode(struct asn1_ctx *ctx, kfree(p); kfree(id); if (net_ratelimit()) - printk("OOM in bsalg (%d)\n", __LINE__); + pr_notice("OOM in bsalg (%d)\n", __LINE__); return 0; } memcpy((*obj)->syntax.c, p, len); @@ -761,7 +761,7 @@ static unsigned char snmp_object_decode(struct asn1_ctx *ctx, if (*obj == NULL) { kfree(id); if (net_ratelimit()) - printk("OOM in bsalg (%d)\n", __LINE__); + pr_notice("OOM in bsalg (%d)\n", __LINE__); return 0; } if (!asn1_null_decode(ctx, end)) { @@ -782,7 +782,7 @@ static unsigned char snmp_object_decode(struct asn1_ctx *ctx, kfree(lp); kfree(id); if (net_ratelimit()) - printk("OOM in bsalg (%d)\n", __LINE__); + pr_notice("OOM in bsalg (%d)\n", __LINE__); return 0; } memcpy((*obj)->syntax.ul, lp, len); @@ -803,7 +803,7 @@ static unsigned char snmp_object_decode(struct asn1_ctx *ctx, kfree(p); kfree(id); if (net_ratelimit()) - printk("OOM in bsalg (%d)\n", __LINE__); + pr_notice("OOM in bsalg (%d)\n", __LINE__); return 0; } memcpy((*obj)->syntax.uc, p, len); @@ -821,7 +821,7 @@ static unsigned char snmp_object_decode(struct asn1_ctx *ctx, if (*obj == NULL) { kfree(id); if (net_ratelimit()) - printk("OOM in bsalg (%d)\n", __LINE__); + pr_notice("OOM in bsalg (%d)\n", __LINE__); return 0; } (*obj)->syntax.ul[0] = ul; diff --git a/net/ipv4/netfilter/nf_nat_standalone.c b/net/ipv4/netfilter/nf_nat_standalone.c index c39c9cf6bee6..beb25819c9c9 100644 --- a/net/ipv4/netfilter/nf_nat_standalone.c +++ b/net/ipv4/netfilter/nf_nat_standalone.c @@ -138,9 +138,8 @@ nf_nat_fn(unsigned int hooknum, ret = nf_nat_rule_find(skb, hooknum, in, out, ct); - if (ret != NF_ACCEPT) { + if (ret != NF_ACCEPT) return ret; - } } else pr_debug("Already setup manip %s for ct %p\n", maniptype == IP_NAT_MANIP_SRC ? "SRC" : "DST", @@ -294,12 +293,12 @@ static int __init nf_nat_standalone_init(void) #endif ret = nf_nat_rule_init(); if (ret < 0) { - printk("nf_nat_init: can't setup rules.\n"); + pr_err("nf_nat_init: can't setup rules.\n"); goto cleanup_decode_session; } ret = nf_register_hooks(nf_nat_ops, ARRAY_SIZE(nf_nat_ops)); if (ret < 0) { - printk("nf_nat_init: can't register hooks.\n"); + pr_err("nf_nat_init: can't register hooks.\n"); goto cleanup_rule_init; } return ret; diff --git a/net/ipv4/netfilter/nf_nat_tftp.c b/net/ipv4/netfilter/nf_nat_tftp.c index b096e81500ae..7274a43c7a12 100644 --- a/net/ipv4/netfilter/nf_nat_tftp.c +++ b/net/ipv4/netfilter/nf_nat_tftp.c @@ -6,7 +6,6 @@ */ #include <linux/module.h> -#include <linux/moduleparam.h> #include <linux/udp.h> #include <net/netfilter/nf_nat_helper.h> diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index 4f1f337f4337..3dc9914c1dce 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 cc6f097fbd5f..2c7a1639388a 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -290,7 +290,7 @@ static int raw_rcv_skb(struct sock * sk, struct sk_buff * skb) { /* Charge it to the socket. */ - if (sock_queue_rcv_skb(sk, skb) < 0) { + if (ip_queue_rcv_skb(sk, skb) < 0) { kfree_skb(skb); return NET_RX_DROP; } @@ -381,8 +381,8 @@ static int raw_send_hdrinc(struct sock *sk, void *from, size_t length, icmp_out_count(net, ((struct icmphdr *) skb_transport_header(skb))->type); - err = NF_HOOK(PF_INET, NF_INET_LOCAL_OUT, skb, NULL, rt->u.dst.dev, - dst_output); + err = NF_HOOK(NFPROTO_IPV4, NF_INET_LOCAL_OUT, skb, NULL, + rt->u.dst.dev, dst_output); if (err > 0) err = net_xmit_errno(err); if (err) diff --git a/net/ipv4/route.c b/net/ipv4/route.c index cb562fdd9b9a..560acc677ce4 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -129,7 +129,6 @@ static int ip_rt_gc_elasticity __read_mostly = 8; static int ip_rt_mtu_expires __read_mostly = 10 * 60 * HZ; static int ip_rt_min_pmtu __read_mostly = 512 + 20 + 20; static int ip_rt_min_advmss __read_mostly = 256; -static int ip_rt_secret_interval __read_mostly = 10 * 60 * HZ; static int rt_chain_length_max __read_mostly = 20; static struct delayed_work expires_work; @@ -258,10 +257,9 @@ static DEFINE_PER_CPU(struct rt_cache_stat, rt_cache_stat); (__raw_get_cpu_var(rt_cache_stat).field++) static inline unsigned int rt_hash(__be32 daddr, __be32 saddr, int idx, - int genid) + int genid) { - return jhash_3words((__force u32)(__be32)(daddr), - (__force u32)(__be32)(saddr), + return jhash_3words((__force u32)daddr, (__force u32)saddr, idx, genid) & rt_hash_mask; } @@ -378,12 +376,13 @@ static int rt_cache_seq_show(struct seq_file *seq, void *v) struct rtable *r = v; int len; - seq_printf(seq, "%s\t%08lX\t%08lX\t%8X\t%d\t%u\t%d\t" - "%08lX\t%d\t%u\t%u\t%02X\t%d\t%1d\t%08X%n", + seq_printf(seq, "%s\t%08X\t%08X\t%8X\t%d\t%u\t%d\t" + "%08X\t%d\t%u\t%u\t%02X\t%d\t%1d\t%08X%n", r->u.dst.dev ? r->u.dst.dev->name : "*", - (unsigned long)r->rt_dst, (unsigned long)r->rt_gateway, + (__force u32)r->rt_dst, + (__force u32)r->rt_gateway, r->rt_flags, atomic_read(&r->u.dst.__refcnt), - r->u.dst.__use, 0, (unsigned long)r->rt_src, + r->u.dst.__use, 0, (__force u32)r->rt_src, (dst_metric(&r->u.dst, RTAX_ADVMSS) ? (int)dst_metric(&r->u.dst, RTAX_ADVMSS) + 40 : 0), dst_metric(&r->u.dst, RTAX_WINDOW), @@ -685,18 +684,17 @@ static inline bool rt_caching(const struct net *net) static inline bool compare_hash_inputs(const struct flowi *fl1, const struct flowi *fl2) { - return (__force u32)(((fl1->nl_u.ip4_u.daddr ^ fl2->nl_u.ip4_u.daddr) | - (fl1->nl_u.ip4_u.saddr ^ fl2->nl_u.ip4_u.saddr) | + return ((((__force u32)fl1->nl_u.ip4_u.daddr ^ (__force u32)fl2->nl_u.ip4_u.daddr) | + ((__force u32)fl1->nl_u.ip4_u.saddr ^ (__force u32)fl2->nl_u.ip4_u.saddr) | (fl1->iif ^ fl2->iif)) == 0); } static inline int compare_keys(struct flowi *fl1, struct flowi *fl2) { - return ((__force u32)((fl1->nl_u.ip4_u.daddr ^ fl2->nl_u.ip4_u.daddr) | - (fl1->nl_u.ip4_u.saddr ^ fl2->nl_u.ip4_u.saddr)) | + return (((__force u32)fl1->nl_u.ip4_u.daddr ^ (__force u32)fl2->nl_u.ip4_u.daddr) | + ((__force u32)fl1->nl_u.ip4_u.saddr ^ (__force u32)fl2->nl_u.ip4_u.saddr) | (fl1->mark ^ fl2->mark) | - (*(u16 *)&fl1->nl_u.ip4_u.tos ^ - *(u16 *)&fl2->nl_u.ip4_u.tos) | + (*(u16 *)&fl1->nl_u.ip4_u.tos ^ *(u16 *)&fl2->nl_u.ip4_u.tos) | (fl1->oif ^ fl2->oif) | (fl1->iif ^ fl2->iif)) == 0; } @@ -919,32 +917,11 @@ void rt_cache_flush_batch(void) rt_do_flush(!in_softirq()); } -/* - * We change rt_genid and let gc do the cleanup - */ -static void rt_secret_rebuild(unsigned long __net) -{ - struct net *net = (struct net *)__net; - rt_cache_invalidate(net); - mod_timer(&net->ipv4.rt_secret_timer, jiffies + ip_rt_secret_interval); -} - -static void rt_secret_rebuild_oneshot(struct net *net) -{ - del_timer_sync(&net->ipv4.rt_secret_timer); - rt_cache_invalidate(net); - if (ip_rt_secret_interval) - mod_timer(&net->ipv4.rt_secret_timer, jiffies + ip_rt_secret_interval); -} - static void rt_emergency_hash_rebuild(struct net *net) { - if (net_ratelimit()) { + if (net_ratelimit()) printk(KERN_WARNING "Route hash chain too long!\n"); - printk(KERN_WARNING "Adjust your secret_interval!\n"); - } - - rt_secret_rebuild_oneshot(net); + rt_cache_invalidate(net); } /* @@ -2300,8 +2277,8 @@ martian_source: goto e_inval; } -int ip_route_input(struct sk_buff *skb, __be32 daddr, __be32 saddr, - u8 tos, struct net_device *dev) +int ip_route_input_common(struct sk_buff *skb, __be32 daddr, __be32 saddr, + u8 tos, struct net_device *dev, bool noref) { struct rtable * rth; unsigned hash; @@ -2319,18 +2296,23 @@ int ip_route_input(struct sk_buff *skb, __be32 daddr, __be32 saddr, rcu_read_lock(); for (rth = rcu_dereference(rt_hash_table[hash].chain); rth; rth = rcu_dereference(rth->u.dst.rt_next)) { - if (((rth->fl.fl4_dst ^ daddr) | - (rth->fl.fl4_src ^ saddr) | + if ((((__force u32)rth->fl.fl4_dst ^ (__force u32)daddr) | + ((__force u32)rth->fl.fl4_src ^ (__force u32)saddr) | (rth->fl.iif ^ iif) | rth->fl.oif | (rth->fl.fl4_tos ^ tos)) == 0 && rth->fl.mark == skb->mark && net_eq(dev_net(rth->u.dst.dev), net) && !rt_is_expired(rth)) { - dst_use(&rth->u.dst, jiffies); + if (noref) { + dst_use_noref(&rth->u.dst, jiffies); + skb_dst_set_noref(skb, &rth->u.dst); + } else { + dst_use(&rth->u.dst, jiffies); + skb_dst_set(skb, &rth->u.dst); + } RT_CACHE_STAT_INC(in_hit); rcu_read_unlock(); - skb_dst_set(skb, &rth->u.dst); return 0; } RT_CACHE_STAT_INC(in_hlist_search); @@ -2373,6 +2355,7 @@ skip_cache: } return ip_route_input_slow(skb, daddr, saddr, tos, dev); } +EXPORT_SYMBOL(ip_route_input_common); static int __mkroute_output(struct rtable **result, struct fib_result *res, @@ -3056,7 +3039,7 @@ int ip_rt_dump(struct sk_buff *skb, struct netlink_callback *cb) continue; if (rt_is_expired(rt)) continue; - skb_dst_set(skb, dst_clone(&rt->u.dst)); + skb_dst_set_noref(skb, &rt->u.dst); if (rt_fill_info(net, skb, NETLINK_CB(cb->skb).pid, cb->nlh->nlmsg_seq, RTM_NEWROUTE, 1, NLM_F_MULTI) <= 0) { @@ -3102,48 +3085,6 @@ static int ipv4_sysctl_rtcache_flush(ctl_table *__ctl, int write, return -EINVAL; } -static void rt_secret_reschedule(int old) -{ - struct net *net; - int new = ip_rt_secret_interval; - int diff = new - old; - - if (!diff) - return; - - rtnl_lock(); - for_each_net(net) { - int deleted = del_timer_sync(&net->ipv4.rt_secret_timer); - long time; - - if (!new) - continue; - - if (deleted) { - time = net->ipv4.rt_secret_timer.expires - jiffies; - - if (time <= 0 || (time += diff) <= 0) - time = 0; - } else - time = new; - - mod_timer(&net->ipv4.rt_secret_timer, jiffies + time); - } - rtnl_unlock(); -} - -static int ipv4_sysctl_rt_secret_interval(ctl_table *ctl, int write, - void __user *buffer, size_t *lenp, - loff_t *ppos) -{ - int old = ip_rt_secret_interval; - int ret = proc_dointvec_jiffies(ctl, write, buffer, lenp, ppos); - - rt_secret_reschedule(old); - - return ret; -} - static ctl_table ipv4_route_table[] = { { .procname = "gc_thresh", @@ -3252,13 +3193,6 @@ static ctl_table ipv4_route_table[] = { .mode = 0644, .proc_handler = proc_dointvec, }, - { - .procname = "secret_interval", - .data = &ip_rt_secret_interval, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = ipv4_sysctl_rt_secret_interval, - }, { } }; @@ -3337,34 +3271,15 @@ static __net_initdata struct pernet_operations sysctl_route_ops = { }; #endif - -static __net_init int rt_secret_timer_init(struct net *net) +static __net_init int rt_genid_init(struct net *net) { - atomic_set(&net->ipv4.rt_genid, - (int) ((num_physpages ^ (num_physpages>>8)) ^ - (jiffies ^ (jiffies >> 7)))); - - net->ipv4.rt_secret_timer.function = rt_secret_rebuild; - net->ipv4.rt_secret_timer.data = (unsigned long)net; - init_timer_deferrable(&net->ipv4.rt_secret_timer); - - if (ip_rt_secret_interval) { - net->ipv4.rt_secret_timer.expires = - jiffies + net_random() % ip_rt_secret_interval + - ip_rt_secret_interval; - add_timer(&net->ipv4.rt_secret_timer); - } + get_random_bytes(&net->ipv4.rt_genid, + sizeof(net->ipv4.rt_genid)); return 0; } -static __net_exit void rt_secret_timer_exit(struct net *net) -{ - del_timer_sync(&net->ipv4.rt_secret_timer); -} - -static __net_initdata struct pernet_operations rt_secret_timer_ops = { - .init = rt_secret_timer_init, - .exit = rt_secret_timer_exit, +static __net_initdata struct pernet_operations rt_genid_ops = { + .init = rt_genid_init, }; @@ -3425,9 +3340,6 @@ int __init ip_rt_init(void) schedule_delayed_work(&expires_work, net_random() % ip_rt_gc_interval + ip_rt_gc_interval); - if (register_pernet_subsys(&rt_secret_timer_ops)) - printk(KERN_ERR "Unable to setup rt_secret_timer\n"); - if (ip_rt_proc_init()) printk(KERN_ERR "Unable to create route proc files\n"); #ifdef CONFIG_XFRM @@ -3439,6 +3351,7 @@ int __init ip_rt_init(void) #ifdef CONFIG_SYSCTL register_pernet_subsys(&sysctl_route_ops); #endif + register_pernet_subsys(&rt_genid_ops); return rc; } @@ -3454,5 +3367,4 @@ void __init ip_static_sysctl_init(void) #endif EXPORT_SYMBOL(__ip_select_ident); -EXPORT_SYMBOL(ip_route_input); EXPORT_SYMBOL(ip_route_output_key); diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 1cd5c15174b8..d96c1da4b17c 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -299,6 +299,13 @@ static struct ctl_table ipv4_table[] = { .mode = 0644, .proc_handler = ipv4_local_port_range, }, + { + .procname = "ip_local_reserved_ports", + .data = NULL, /* initialized in sysctl_ipv4_init */ + .maxlen = 65536, + .mode = 0644, + .proc_handler = proc_do_large_bitmap, + }, #ifdef CONFIG_IP_MULTICAST { .procname = "igmp_max_memberships", @@ -736,6 +743,16 @@ static __net_initdata struct pernet_operations ipv4_sysctl_ops = { static __init int sysctl_ipv4_init(void) { struct ctl_table_header *hdr; + struct ctl_table *i; + + for (i = ipv4_table; i->procname; i++) { + if (strcmp(i->procname, "ip_local_reserved_ports") == 0) { + i->data = sysctl_local_reserved_ports; + break; + } + } + if (!i->procname) + return -EINVAL; hdr = register_sysctl_paths(net_ipv4_ctl_path, ipv4_table); if (hdr == NULL) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 0f8caf64caa3..6596b4feeddc 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -378,7 +378,7 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait) struct sock *sk = sock->sk; struct tcp_sock *tp = tcp_sk(sk); - sock_poll_wait(file, sk->sk_sleep, wait); + sock_poll_wait(file, sk_sleep(sk), wait); if (sk->sk_state == TCP_LISTEN) return inet_csk_listen_poll(sk); @@ -2215,7 +2215,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level, default: /* fallthru */ break; - }; + } if (optlen < sizeof(int)) return -EINVAL; @@ -2298,7 +2298,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level, if (sock_flag(sk, SOCK_KEEPOPEN) && !((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) { - __u32 elapsed = tcp_time_stamp - tp->rcv_tstamp; + u32 elapsed = keepalive_time_elapsed(tp); if (tp->keepalive_time > elapsed) elapsed = tp->keepalive_time - elapsed; else @@ -2721,7 +2721,7 @@ struct sk_buff **tcp_gro_receive(struct sk_buff **head, struct sk_buff *skb) struct tcphdr *th2; unsigned int len; unsigned int thlen; - unsigned int flags; + __be32 flags; unsigned int mss = 1; unsigned int hlen; unsigned int off; @@ -2771,10 +2771,10 @@ struct sk_buff **tcp_gro_receive(struct sk_buff **head, struct sk_buff *skb) found: flush = NAPI_GRO_CB(p)->flush; - flush |= flags & TCP_FLAG_CWR; - flush |= (flags ^ tcp_flag_word(th2)) & - ~(TCP_FLAG_CWR | TCP_FLAG_FIN | TCP_FLAG_PSH); - flush |= th->ack_seq ^ th2->ack_seq; + flush |= (__force int)(flags & TCP_FLAG_CWR); + flush |= (__force int)((flags ^ tcp_flag_word(th2)) & + ~(TCP_FLAG_CWR | TCP_FLAG_FIN | TCP_FLAG_PSH)); + flush |= (__force int)(th->ack_seq ^ th2->ack_seq); for (i = sizeof(*th); i < thlen; i += 4) flush |= *(u32 *)((u8 *)th + i) ^ *(u32 *)((u8 *)th2 + i); @@ -2795,8 +2795,9 @@ found: out_check_final: flush = len < mss; - flush |= flags & (TCP_FLAG_URG | TCP_FLAG_PSH | TCP_FLAG_RST | - TCP_FLAG_SYN | TCP_FLAG_FIN); + flush |= (__force int)(flags & (TCP_FLAG_URG | TCP_FLAG_PSH | + TCP_FLAG_RST | TCP_FLAG_SYN | + TCP_FLAG_FIN)); if (p && (!NAPI_GRO_CB(skb)->same_flow || flush)) pp = head; @@ -2839,7 +2840,6 @@ static void __tcp_free_md5sig_pool(struct tcp_md5sig_pool * __percpu *pool) if (p->md5_desc.tfm) crypto_free_hash(p->md5_desc.tfm); kfree(p); - p = NULL; } } free_percpu(pool); @@ -2937,25 +2937,40 @@ retry: EXPORT_SYMBOL(tcp_alloc_md5sig_pool); -struct tcp_md5sig_pool *__tcp_get_md5sig_pool(int cpu) + +/** + * tcp_get_md5sig_pool - get md5sig_pool for this user + * + * We use percpu structure, so if we succeed, we exit with preemption + * and BH disabled, to make sure another thread or softirq handling + * wont try to get same context. + */ +struct tcp_md5sig_pool *tcp_get_md5sig_pool(void) { struct tcp_md5sig_pool * __percpu *p; - spin_lock_bh(&tcp_md5sig_pool_lock); + + local_bh_disable(); + + spin_lock(&tcp_md5sig_pool_lock); p = tcp_md5sig_pool; if (p) tcp_md5sig_users++; - spin_unlock_bh(&tcp_md5sig_pool_lock); - return (p ? *per_cpu_ptr(p, cpu) : NULL); -} + spin_unlock(&tcp_md5sig_pool_lock); + + if (p) + return *per_cpu_ptr(p, smp_processor_id()); -EXPORT_SYMBOL(__tcp_get_md5sig_pool); + local_bh_enable(); + return NULL; +} +EXPORT_SYMBOL(tcp_get_md5sig_pool); -void __tcp_put_md5sig_pool(void) +void tcp_put_md5sig_pool(void) { + local_bh_enable(); tcp_free_md5sig_pool(); } - -EXPORT_SYMBOL(__tcp_put_md5sig_pool); +EXPORT_SYMBOL(tcp_put_md5sig_pool); int tcp_md5_hash_header(struct tcp_md5sig_pool *hp, struct tcphdr *th) diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index f240f57b2199..3e6dafcb1071 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3710,7 +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; @@ -3845,12 +3845,13 @@ void tcp_parse_options(struct sk_buff *skb, struct tcp_options_received *opt_rx, /* 16-bit multiple */ opt_rx->cookie_plus = opsize; *hvpp = ptr; + break; default: /* ignore option */ break; - }; + } break; - }; + } ptr += opsize-2; length -= opsize; @@ -4319,7 +4320,7 @@ 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; @@ -4367,6 +4368,7 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb) if (TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq) goto drop; + skb_dst_drop(skb); __skb_pull(skb, th->doff * 4); TCP_ECN_accept_cwr(tp, skb); @@ -5833,7 +5835,7 @@ 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 3c23e70885f4..202cf09c4cd4 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -519,26 +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; @@ -551,10 +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; } @@ -763,13 +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, @@ -894,7 +891,7 @@ int tcp_v4_md5_do_add(struct sock *sk, __be32 addr, kfree(newkey); return -ENOMEM; } - sk->sk_route_caps &= ~NETIF_F_GSO_MASK; + sk_nocaps_add(sk, NETIF_F_GSO_MASK); } if (tcp_alloc_md5sig_pool(sk) == NULL) { kfree(newkey); @@ -1024,7 +1021,7 @@ static int tcp_v4_parse_md5_keys(struct sock *sk, char __user *optval, return -EINVAL; tp->md5sig_info = p; - sk->sk_route_caps &= ~NETIF_F_GSO_MASK; + sk_nocaps_add(sk, NETIF_F_GSO_MASK); } newkey = kmemdup(cmd.tcpm_key, cmd.tcpm_keylen, sk->sk_allocation); @@ -1289,8 +1286,8 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) goto drop_and_release; /* Secret recipe starts with IP addresses */ - *mess++ ^= daddr; - *mess++ ^= saddr; + *mess++ ^= (__force u32)daddr; + *mess++ ^= (__force u32)saddr; /* plus variable length Initiator Cookie */ c = (u8 *)mess; @@ -1465,7 +1462,7 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb, if (newkey != NULL) tcp_v4_md5_do_add(newsk, newinet->inet_daddr, newkey, key->keylen); - newsk->sk_route_caps &= ~NETIF_F_GSO_MASK; + sk_nocaps_add(newsk, NETIF_F_GSO_MASK); } #endif @@ -1675,6 +1672,8 @@ process: skb->dev = NULL; + sock_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 5fabff9ac6d6..794c2e122a41 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -672,6 +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 0dda86e72ad8..b4ed957f201a 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -350,6 +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; @@ -667,7 +668,6 @@ static unsigned tcp_synack_options(struct sock *sk, u8 cookie_plus = (xvp != NULL && !xvp->cookie_out_never) ? xvp->cookie_plus : 0; - bool doing_ts = ireq->tstamp_ok; #ifdef CONFIG_TCP_MD5SIG *md5 = tcp_rsk(req)->af_specific->md5_lookup(sk, req); @@ -680,7 +680,7 @@ static unsigned tcp_synack_options(struct sock *sk, * rather than TS in order to fit in better with old, * buggy kernels, but that was deemed to be unnecessary. */ - doing_ts &= !ireq->sack_ok; + ireq->tstamp_ok &= !ireq->sack_ok; } #else *md5 = NULL; @@ -695,7 +695,7 @@ static unsigned tcp_synack_options(struct sock *sk, opts->options |= OPTION_WSCALE; remaining -= TCPOLEN_WSCALE_ALIGNED; } - if (likely(doing_ts)) { + if (likely(ireq->tstamp_ok)) { opts->options |= OPTION_TS; opts->tsval = TCP_SKB_CB(skb)->when; opts->tsecr = req->ts_recent; @@ -703,7 +703,7 @@ static unsigned tcp_synack_options(struct sock *sk, } if (likely(ireq->sack_ok)) { opts->options |= OPTION_SACK_ADVERTISE; - if (unlikely(!doing_ts)) + if (unlikely(!ireq->tstamp_ok)) remaining -= TCPOLEN_SACKPERM_ALIGNED; } @@ -711,7 +711,7 @@ static unsigned tcp_synack_options(struct sock *sk, * If the <SYN> options fit, the same options should fit now! */ if (*md5 == NULL && - doing_ts && + ireq->tstamp_ok && cookie_plus > TCPOLEN_COOKIE_BASE) { int need = cookie_plus; /* has TCPOLEN_COOKIE_BASE */ @@ -860,7 +860,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, th->urg_ptr = htons(tp->snd_up - tcb->seq); th->urg = 1; } else if (after(tcb->seq + 0xFFFF, tp->snd_nxt)) { - th->urg_ptr = 0xFFFF; + th->urg_ptr = htons(0xFFFF); th->urg = 1; } } @@ -872,13 +872,13 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, #ifdef CONFIG_TCP_MD5SIG /* Calculate the MD5 hash, as we have all we need now */ if (md5) { - sk->sk_route_caps &= ~NETIF_F_GSO_MASK; + sk_nocaps_add(sk, NETIF_F_GSO_MASK); tp->af_specific->calc_md5_hash(opts.hash_location, md5, sk, NULL, skb); } #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)); @@ -887,9 +887,10 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, tcp_event_data_sent(tp, skb, sk); if (after(tcb->end_seq, tp->snd_nxt) || tcb->seq == tcb->end_seq) - TCP_INC_STATS(sock_net(sk), TCP_MIB_OUTSEGS); + TCP_ADD_STATS(sock_net(sk), TCP_MIB_OUTSEGS, + tcp_skb_pcount(skb)); - err = icsk->icsk_af_ops->queue_xmit(skb, 0); + err = icsk->icsk_af_ops->queue_xmit(skb); if (likely(err <= 0)) return err; @@ -2484,7 +2485,7 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst, *tail-- ^= TCP_SKB_CB(skb)->seq + 1; /* recommended */ - *tail-- ^= ((th->dest << 16) | th->source); + *tail-- ^= (((__force u32)th->dest << 16) | (__force u32)th->source); *tail-- ^= (u32)(unsigned long)cvp; /* per sockopt */ sha_transform((__u32 *)&xvp->cookie_bakery[0], @@ -2502,7 +2503,7 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst, th->window = htons(min(req->rcv_wnd, 65535U)); tcp_options_write((__be32 *)(th + 1), tp, &opts); th->doff = (tcp_header_size >> 2); - TCP_INC_STATS(sock_net(sk), TCP_MIB_OUTSEGS); + TCP_ADD_STATS(sock_net(sk), TCP_MIB_OUTSEGS, tcp_skb_pcount(skb)); #ifdef CONFIG_TCP_MD5SIG /* Okay, we have all we need - do the md5 hash if needed */ diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 8a0ab2977f1f..440a5c6004f6 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -172,14 +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; @@ -517,7 +517,7 @@ static void tcp_keepalive_timer (unsigned long data) struct sock *sk = (struct sock *) data; struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); - __u32 elapsed; + u32 elapsed; /* Only process if socket is not in use. */ bh_lock_sock(sk); @@ -554,7 +554,7 @@ static void tcp_keepalive_timer (unsigned long data) if (tp->packets_out || tcp_send_head(sk)) goto resched; - elapsed = tcp_time_stamp - tp->rcv_tstamp; + elapsed = keepalive_time_elapsed(tp); if (elapsed >= keepalive_time_when(tp)) { if (icsk->icsk_probes_out >= keepalive_probes(tp)) { diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 8fef859db35d..9de6a698f91d 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -233,7 +233,8 @@ int udp_lib_get_port(struct sock *sk, unsigned short snum, */ do { if (low <= snum && snum <= high && - !test_bit(snum >> udptable->log, bitmap)) + !test_bit(snum >> udptable->log, bitmap) && + !inet_is_reserved_local_port(snum)) goto found; snum += rand; } while (snum != first); @@ -307,13 +308,13 @@ static int ipv4_rcv_saddr_equal(const struct sock *sk1, const struct sock *sk2) static unsigned int udp4_portaddr_hash(struct net *net, __be32 saddr, unsigned int port) { - return jhash_1word(saddr, net_hash_mix(net)) ^ port; + return jhash_1word((__force u32)saddr, net_hash_mix(net)) ^ port; } int udp_v4_get_port(struct sock *sk, unsigned short snum) { unsigned int hash2_nulladdr = - udp4_portaddr_hash(sock_net(sk), INADDR_ANY, snum); + udp4_portaddr_hash(sock_net(sk), htonl(INADDR_ANY), snum); unsigned int hash2_partial = udp4_portaddr_hash(sock_net(sk), inet_sk(sk)->inet_rcv_saddr, 0); @@ -466,14 +467,14 @@ static struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr, daddr, hnum, dif, hslot2, slot2); if (!result) { - hash2 = udp4_portaddr_hash(net, INADDR_ANY, hnum); + hash2 = udp4_portaddr_hash(net, htonl(INADDR_ANY), hnum); slot2 = hash2 & udptable->mask; hslot2 = &udptable->hash2[slot2]; if (hslot->count < hslot2->count) goto begin; result = udp4_lib_lookup2(net, saddr, sport, - INADDR_ANY, hnum, dif, + htonl(INADDR_ANY), hnum, dif, hslot2, slot2); } rcu_read_unlock(); @@ -1062,10 +1063,10 @@ static unsigned int first_packet_length(struct sock *sk) spin_unlock_bh(&rcvq->lock); if (!skb_queue_empty(&list_kill)) { - lock_sock(sk); + lock_sock_bh(sk); __skb_queue_purge(&list_kill); sk_mem_reclaim_partial(sk); - release_sock(sk); + unlock_sock_bh(sk); } return res; } @@ -1196,10 +1197,10 @@ out: return err; csum_copy_err: - lock_sock(sk); + lock_sock_bh(sk); if (!skb_kill_datagram(sk, skb, flags)) UDP_INC_STATS_USER(sock_net(sk), UDP_MIB_INERRORS, is_udplite); - release_sock(sk); + unlock_sock_bh(sk); if (noblock) return -EAGAIN; @@ -1217,6 +1218,7 @@ int udp_disconnect(struct sock *sk, int flags) sk->sk_state = TCP_CLOSE; inet->inet_daddr = 0; inet->inet_dport = 0; + sock_rps_save_rxhash(sk, 0); sk->sk_bound_dev_if = 0; if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) inet_reset_saddr(sk); @@ -1258,8 +1260,12 @@ 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) + sock_rps_save_rxhash(sk, skb->rxhash); + + rc = ip_queue_rcv_skb(sk, skb); if (rc < 0) { int is_udplite = IS_UDPLITE(sk); @@ -1367,6 +1373,10 @@ int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) goto drop; } + + if (sk_rcvqueues_full(sk, skb)) + goto drop; + rc = 0; bh_lock_sock(sk); @@ -1527,6 +1537,9 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, uh = udp_hdr(skb); ulen = ntohs(uh->len); + saddr = ip_hdr(skb)->saddr; + daddr = ip_hdr(skb)->daddr; + if (ulen > skb->len) goto short_packet; @@ -1540,9 +1553,6 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, if (udp4_csum_init(skb, uh, proto)) goto csum_error; - saddr = ip_hdr(skb)->saddr; - daddr = ip_hdr(skb)->daddr; - if (rt->rt_flags & (RTCF_BROADCAST|RTCF_MULTICAST)) return __udp4_lib_mcast_deliver(net, skb, uh, saddr, daddr, udptable); @@ -1615,9 +1625,9 @@ int udp_rcv(struct sk_buff *skb) void udp_destroy_sock(struct sock *sk) { - lock_sock(sk); + lock_sock_bh(sk); udp_flush_pending_frames(sk); - release_sock(sk); + unlock_sock_bh(sk); } /* diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c index c791bb63203f..ad8fbb871aa0 100644 --- a/net/ipv4/xfrm4_input.c +++ b/net/ipv4/xfrm4_input.c @@ -27,8 +27,8 @@ static inline int xfrm4_rcv_encap_finish(struct sk_buff *skb) if (skb_dst(skb) == NULL) { const struct iphdr *iph = ip_hdr(skb); - if (ip_route_input(skb, iph->daddr, iph->saddr, iph->tos, - skb->dev)) + if (ip_route_input_noref(skb, iph->daddr, iph->saddr, + iph->tos, skb->dev)) goto drop; } return dst_input(skb); @@ -61,7 +61,7 @@ int xfrm4_transport_finish(struct sk_buff *skb, int async) iph->tot_len = htons(skb->len); ip_send_check(iph); - NF_HOOK(PF_INET, NF_INET_PRE_ROUTING, skb, skb->dev, NULL, + NF_HOOK(NFPROTO_IPV4, NF_INET_PRE_ROUTING, skb, skb->dev, NULL, xfrm4_rcv_encap_finish); return 0; } diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c index c908bd99bcba..571aa96a175c 100644 --- a/net/ipv4/xfrm4_output.c +++ b/net/ipv4/xfrm4_output.c @@ -86,7 +86,7 @@ static int xfrm4_output_finish(struct sk_buff *skb) int xfrm4_output(struct sk_buff *skb) { - return NF_HOOK_COND(PF_INET, NF_INET_POST_ROUTING, skb, + return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING, skb, NULL, skb_dst(skb)->dev, xfrm4_output_finish, !(IPCB(skb)->flags & IPSKB_REROUTED)); } diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index e4a1483fba77..1705476670ef 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, |