diff options
Diffstat (limited to 'net/ipv4')
86 files changed, 1198 insertions, 2272 deletions
diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index 010fbb2d45e9..fb7909774254 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -116,48 +116,6 @@ config IP_ROUTE_MULTIPATH equal "cost" and chooses one of them in a non-deterministic fashion if a matching packet arrives. -config IP_ROUTE_MULTIPATH_CACHED - bool "IP: equal cost multipath with caching support (EXPERIMENTAL)" - depends on IP_ROUTE_MULTIPATH - help - Normally, equal cost multipath routing is not supported by the - routing cache. If you say Y here, alternative routes are cached - and on cache lookup a route is chosen in a configurable fashion. - - If unsure, say N. - -config IP_ROUTE_MULTIPATH_RR - tristate "MULTIPATH: round robin algorithm" - depends on IP_ROUTE_MULTIPATH_CACHED - help - Multipath routes are chosen according to Round Robin - -config IP_ROUTE_MULTIPATH_RANDOM - tristate "MULTIPATH: random algorithm" - depends on IP_ROUTE_MULTIPATH_CACHED - help - Multipath routes are chosen in a random fashion. Actually, - there is no weight for a route. The advantage of this policy - is that it is implemented stateless and therefore introduces only - a very small delay. - -config IP_ROUTE_MULTIPATH_WRANDOM - tristate "MULTIPATH: weighted random algorithm" - depends on IP_ROUTE_MULTIPATH_CACHED - help - Multipath routes are chosen in a weighted random fashion. - The per route weights are the weights visible via ip route 2. As the - corresponding state management introduces some overhead routing delay - is increased. - -config IP_ROUTE_MULTIPATH_DRR - tristate "MULTIPATH: interface round robin algorithm" - depends on IP_ROUTE_MULTIPATH_CACHED - help - Connections are distributed in a round robin fashion over the - available interfaces. This policy makes sense if the connections - should be primarily distributed on interfaces and not on routes. - config IP_ROUTE_VERBOSE bool "IP: verbose route monitoring" depends on IP_ADVANCED_ROUTER diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile index 4ff6c151d7f3..fbf1674e0c2a 100644 --- a/net/ipv4/Makefile +++ b/net/ipv4/Makefile @@ -29,14 +29,9 @@ obj-$(CONFIG_INET_TUNNEL) += tunnel4.o obj-$(CONFIG_INET_XFRM_MODE_TRANSPORT) += xfrm4_mode_transport.o obj-$(CONFIG_INET_XFRM_MODE_TUNNEL) += xfrm4_mode_tunnel.o obj-$(CONFIG_IP_PNP) += ipconfig.o -obj-$(CONFIG_IP_ROUTE_MULTIPATH_RR) += multipath_rr.o -obj-$(CONFIG_IP_ROUTE_MULTIPATH_RANDOM) += multipath_random.o -obj-$(CONFIG_IP_ROUTE_MULTIPATH_WRANDOM) += multipath_wrandom.o -obj-$(CONFIG_IP_ROUTE_MULTIPATH_DRR) += multipath_drr.o obj-$(CONFIG_NETFILTER) += netfilter.o netfilter/ obj-$(CONFIG_IP_VS) += ipvs/ obj-$(CONFIG_INET_DIAG) += inet_diag.o -obj-$(CONFIG_IP_ROUTE_MULTIPATH_CACHED) += multipath.o obj-$(CONFIG_INET_TCP_DIAG) += tcp_diag.o obj-$(CONFIG_NET_TCPPROBE) += tcp_probe.o obj-$(CONFIG_TCP_CONG_BIC) += tcp_bic.o diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 041fba3fa0aa..06c08e5740fb 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1170,6 +1170,9 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb, int features) int ihl; int id; + if (!(features & NETIF_F_V4_CSUM)) + features &= ~NETIF_F_SG; + if (unlikely(skb_shinfo(skb)->gso_type & ~(SKB_GSO_TCPV4 | SKB_GSO_UDP | diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c index 6da8ff597ad3..7a23e59c374a 100644 --- a/net/ipv4/ah4.c +++ b/net/ipv4/ah4.c @@ -339,3 +339,4 @@ static void __exit ah4_fini(void) module_init(ah4_init); module_exit(ah4_fini); MODULE_LICENSE("GPL"); +MODULE_ALIAS_XFRM_TYPE(AF_INET, XFRM_PROTO_AH); diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index e00767e8ebd9..9ab9d534fbac 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -885,7 +885,7 @@ static int arp_process(struct sk_buff *skb) if (n == NULL && arp->ar_op == htons(ARPOP_REPLY) && inet_addr_type(sip) == RTN_UNICAST) - n = __neigh_lookup(&arp_tbl, &sip, dev, -1); + n = __neigh_lookup(&arp_tbl, &sip, dev, 1); } if (n) { diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index 47c95e8ef045..98767a4f1185 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -481,3 +481,4 @@ static void __exit esp4_fini(void) module_init(esp4_init); module_exit(esp4_fini); MODULE_LICENSE("GPL"); +MODULE_ALIAS_XFRM_TYPE(AF_INET, XFRM_PROTO_ESP); diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 311d633f7f39..eff6bce453ee 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -453,7 +453,6 @@ const struct nla_policy rtm_ipv4_policy[RTA_MAX+1] = { [RTA_MULTIPATH] = { .len = sizeof(struct rtnexthop) }, [RTA_PROTOINFO] = { .type = NLA_U32 }, [RTA_FLOW] = { .type = NLA_U32 }, - [RTA_MP_ALGO] = { .type = NLA_U32 }, }; static int rtm_to_fib_config(struct sk_buff *skb, struct nlmsghdr *nlh, @@ -515,9 +514,6 @@ static int rtm_to_fib_config(struct sk_buff *skb, struct nlmsghdr *nlh, case RTA_FLOW: cfg->fc_flow = nla_get_u32(attr); break; - case RTA_MP_ALGO: - cfg->fc_mp_alg = nla_get_u32(attr); - break; case RTA_TABLE: cfg->fc_table = nla_get_u32(attr); break; @@ -821,7 +817,7 @@ static void nl_fib_input(struct sock *sk, int len) static void nl_fib_lookup_init(void) { netlink_kernel_create(NETLINK_FIB_LOOKUP, 0, nl_fib_input, NULL, - THIS_MODULE); + THIS_MODULE); } static void fib_disable_ip(struct net_device *dev, int force) diff --git a/net/ipv4/fib_hash.c b/net/ipv4/fib_hash.c index 07e843a47dde..9ad1d9ff9ce7 100644 --- a/net/ipv4/fib_hash.c +++ b/net/ipv4/fib_hash.c @@ -771,13 +771,13 @@ struct fib_table * __init fib_hash_init(u32 id) fn_hash_kmem = kmem_cache_create("ip_fib_hash", sizeof(struct fib_node), 0, SLAB_HWCACHE_ALIGN, - NULL, NULL); + NULL); if (fn_alias_kmem == NULL) fn_alias_kmem = kmem_cache_create("ip_fib_alias", sizeof(struct fib_alias), 0, SLAB_HWCACHE_ALIGN, - NULL, NULL); + NULL); tb = kmalloc(sizeof(struct fib_table) + sizeof(struct fn_hash), GFP_KERNEL); diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index bb94550d95c3..c434119deb52 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -42,7 +42,6 @@ #include <net/tcp.h> #include <net/sock.h> #include <net/ip_fib.h> -#include <net/ip_mp_alg.h> #include <net/netlink.h> #include <net/nexthop.h> @@ -697,13 +696,6 @@ struct fib_info *fib_create_info(struct fib_config *cfg) goto err_inval; } #endif -#ifdef CONFIG_IP_ROUTE_MULTIPATH_CACHED - if (cfg->fc_mp_alg) { - if (cfg->fc_mp_alg < IP_MP_ALG_NONE || - cfg->fc_mp_alg > IP_MP_ALG_MAX) - goto err_inval; - } -#endif err = -ENOBUFS; if (fib_info_cnt >= fib_hash_size) { @@ -791,10 +783,6 @@ struct fib_info *fib_create_info(struct fib_config *cfg) #endif } -#ifdef CONFIG_IP_ROUTE_MULTIPATH_CACHED - fi->fib_mp_alg = cfg->fc_mp_alg; -#endif - if (fib_props[cfg->fc_type].error) { if (cfg->fc_gw || cfg->fc_oif || cfg->fc_mp) goto err_inval; @@ -940,10 +928,6 @@ out_fill_res: res->type = fa->fa_type; res->scope = fa->fa_scope; res->fi = fa->fa_info; -#ifdef CONFIG_IP_ROUTE_MULTIPATH_CACHED - res->netmask = mask; - res->network = zone & inet_make_mask(prefixlen); -#endif atomic_inc(&res->fi->fib_clntref); return 0; } diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 30e332ade61b..9ca786a6fd3c 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1970,7 +1970,7 @@ struct fib_table * __init fib_hash_init(u32 id) fn_alias_kmem = kmem_cache_create("ip_fib_alias", sizeof(struct fib_alias), 0, SLAB_HWCACHE_ALIGN, - NULL, NULL); + NULL); tb = kmalloc(sizeof(struct fib_table) + sizeof(struct trie), GFP_KERNEL); diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index a73cf93cee36..2586df09b9b6 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -14,7 +14,8 @@ #include <net/ip.h> /* Must be called with locally disabled BHs. */ -void __inet_twsk_kill(struct inet_timewait_sock *tw, struct inet_hashinfo *hashinfo) +static void __inet_twsk_kill(struct inet_timewait_sock *tw, + struct inet_hashinfo *hashinfo) { struct inet_bind_hashbucket *bhead; struct inet_bind_bucket *tb; @@ -47,8 +48,6 @@ void __inet_twsk_kill(struct inet_timewait_sock *tw, struct inet_hashinfo *hashi inet_twsk_put(tw); } -EXPORT_SYMBOL_GPL(__inet_twsk_kill); - /* * Enter the time wait state. This is called with locally disabled BH. * Essentially we whip up a timewait bucket, copy the relevant info into it diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c index 2f44e6128068..771031dfbd0f 100644 --- a/net/ipv4/inetpeer.c +++ b/net/ipv4/inetpeer.c @@ -123,7 +123,7 @@ void __init inet_initpeers(void) peer_cachep = kmem_cache_create("inet_peer_cache", sizeof(struct inet_peer), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, - NULL, NULL); + NULL); /* All the timers, started at system startup tend to synchronize. Perturb it a bit. @@ -158,7 +158,7 @@ static void unlink_from_unused(struct inet_peer *p) #define lookup(_daddr,_stack) \ ({ \ struct inet_peer *u, **v; \ - if (_stack) { \ + if (_stack != NULL) { \ stackptr = _stack; \ *stackptr++ = &peer_root; \ } \ @@ -169,7 +169,7 @@ static void unlink_from_unused(struct inet_peer *p) v = &u->avl_left; \ else \ v = &u->avl_right; \ - if (_stack) \ + if (_stack != NULL) \ *stackptr++ = v; \ u = *v; \ } \ diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c index 9cb04df0054b..8c95cf09f87a 100644 --- a/net/ipv4/ip_forward.c +++ b/net/ipv4/ip_forward.c @@ -86,7 +86,7 @@ int ip_forward(struct sk_buff *skb) goto sr_failed; if (unlikely(skb->len > dst_mtu(&rt->u.dst) && - (ip_hdr(skb)->frag_off & htons(IP_DF))) && !skb->local_df) { + (ip_hdr(skb)->frag_off & htons(IP_DF))) && !skb->local_df) { IP_INC_STATS(IPSTATS_MIB_FRAGFAILS); icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(dst_mtu(&rt->u.dst))); diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 63282934725e..5c14ed63e56c 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -809,7 +809,8 @@ static int ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) max_headroom = LL_RESERVED_SPACE(tdev) + gre_hlen; - if (skb_headroom(skb) < max_headroom || skb_cloned(skb) || skb_shared(skb)) { + if (skb_headroom(skb) < max_headroom || skb_shared(skb)|| + (skb_cloned(skb) && !skb_clone_writable(skb, 0))) { struct sk_buff *new_skb = skb_realloc_headroom(skb, max_headroom); if (!new_skb) { ip_rt_put(rt); diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 34ea4547ebbe..c9e2b5e6305e 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -399,6 +399,10 @@ static void ip_copy_metadata(struct sk_buff *to, struct sk_buff *from) to->tc_index = from->tc_index; #endif nf_copy(to, from); +#if defined(CONFIG_NETFILTER_XT_TARGET_TRACE) || \ + defined(CONFIG_NETFILTER_XT_TARGET_TRACE_MODULE) + to->nf_trace = from->nf_trace; +#endif #if defined(CONFIG_IP_VS) || defined(CONFIG_IP_VS_MODULE) to->ipvs_property = from->ipvs_property; #endif @@ -837,7 +841,7 @@ int ip_append_data(struct sock *sk, */ if (transhdrlen && length + fragheaderlen <= mtu && - rt->u.dst.dev->features & NETIF_F_ALL_CSUM && + rt->u.dst.dev->features & NETIF_F_V4_CSUM && !exthdrlen) csummode = CHECKSUM_PARTIAL; diff --git a/net/ipv4/ipcomp.c b/net/ipv4/ipcomp.c index ab86137c71d2..e787044a8514 100644 --- a/net/ipv4/ipcomp.c +++ b/net/ipv4/ipcomp.c @@ -485,3 +485,4 @@ MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("IP Payload Compression Protocol (IPComp) - RFC3173"); MODULE_AUTHOR("James Morris <jmorris@intercode.com.au>"); +MODULE_ALIAS_XFRM_TYPE(AF_INET, XFRM_PROTO_COMP); diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index ebd2f2d532f6..396437242a1b 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -595,7 +595,8 @@ static int ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) */ max_headroom = (LL_RESERVED_SPACE(tdev)+sizeof(struct iphdr)); - if (skb_headroom(skb) < max_headroom || skb_cloned(skb) || skb_shared(skb)) { + if (skb_headroom(skb) < max_headroom || skb_shared(skb) || + (skb_cloned(skb) && !skb_clone_writable(skb, 0))) { struct sk_buff *new_skb = skb_realloc_headroom(skb, max_headroom); if (!new_skb) { ip_rt_put(rt); diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index d96582acdf69..7003cc1b7fe2 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -1917,7 +1917,7 @@ void __init ip_mr_init(void) mrt_cachep = kmem_cache_create("ip_mrt_cache", sizeof(struct mfc_cache), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, - NULL, NULL); + NULL); init_timer(&ipmr_expire_timer); ipmr_expire_timer.function=ipmr_expire_process; register_netdevice_notifier(&ip_mr_notifier); diff --git a/net/ipv4/ipvs/ip_vs_app.c b/net/ipv4/ipvs/ip_vs_app.c index 15ad5dd2d984..8d6901d4e94f 100644 --- a/net/ipv4/ipvs/ip_vs_app.c +++ b/net/ipv4/ipvs/ip_vs_app.c @@ -549,7 +549,7 @@ static int ip_vs_app_seq_show(struct seq_file *seq, void *v) return 0; } -static struct seq_operations ip_vs_app_seq_ops = { +static const struct seq_operations ip_vs_app_seq_ops = { .start = ip_vs_app_seq_start, .next = ip_vs_app_seq_next, .stop = ip_vs_app_seq_stop, diff --git a/net/ipv4/ipvs/ip_vs_conn.c b/net/ipv4/ipvs/ip_vs_conn.c index 7018f97c75dc..d612a6a5d957 100644 --- a/net/ipv4/ipvs/ip_vs_conn.c +++ b/net/ipv4/ipvs/ip_vs_conn.c @@ -745,7 +745,7 @@ static int ip_vs_conn_seq_show(struct seq_file *seq, void *v) return 0; } -static struct seq_operations ip_vs_conn_seq_ops = { +static const struct seq_operations ip_vs_conn_seq_ops = { .start = ip_vs_conn_seq_start, .next = ip_vs_conn_seq_next, .stop = ip_vs_conn_seq_stop, @@ -901,7 +901,7 @@ int ip_vs_conn_init(void) /* Allocate ip_vs_conn slab cache */ ip_vs_conn_cachep = kmem_cache_create("ip_vs_conn", sizeof(struct ip_vs_conn), 0, - SLAB_HWCACHE_ALIGN, NULL, NULL); + SLAB_HWCACHE_ALIGN, NULL); if (!ip_vs_conn_cachep) { vfree(ip_vs_conn_tab); return -ENOMEM; diff --git a/net/ipv4/ipvs/ip_vs_ctl.c b/net/ipv4/ipvs/ip_vs_ctl.c index 68fe1d4d0210..e1052bcf4ed1 100644 --- a/net/ipv4/ipvs/ip_vs_ctl.c +++ b/net/ipv4/ipvs/ip_vs_ctl.c @@ -1783,7 +1783,7 @@ static int ip_vs_info_seq_show(struct seq_file *seq, void *v) return 0; } -static struct seq_operations ip_vs_info_seq_ops = { +static const struct seq_operations ip_vs_info_seq_ops = { .start = ip_vs_info_seq_start, .next = ip_vs_info_seq_next, .stop = ip_vs_info_seq_stop, diff --git a/net/ipv4/multipath.c b/net/ipv4/multipath.c deleted file mode 100644 index 4e9ca7c76407..000000000000 --- a/net/ipv4/multipath.c +++ /dev/null @@ -1,55 +0,0 @@ -/* multipath.c: IPV4 multipath algorithm support. - * - * Copyright (C) 2004, 2005 Einar Lueck <elueck@de.ibm.com> - * Copyright (C) 2005 David S. Miller <davem@davemloft.net> - */ - -#include <linux/module.h> -#include <linux/errno.h> -#include <linux/netdevice.h> -#include <linux/spinlock.h> - -#include <net/ip_mp_alg.h> - -static DEFINE_SPINLOCK(alg_table_lock); -struct ip_mp_alg_ops *ip_mp_alg_table[IP_MP_ALG_MAX + 1]; - -int multipath_alg_register(struct ip_mp_alg_ops *ops, enum ip_mp_alg n) -{ - struct ip_mp_alg_ops **slot; - int err; - - if (n < IP_MP_ALG_NONE || n > IP_MP_ALG_MAX || - !ops->mp_alg_select_route) - return -EINVAL; - - spin_lock(&alg_table_lock); - slot = &ip_mp_alg_table[n]; - if (*slot != NULL) { - err = -EBUSY; - } else { - *slot = ops; - err = 0; - } - spin_unlock(&alg_table_lock); - - return err; -} -EXPORT_SYMBOL(multipath_alg_register); - -void multipath_alg_unregister(struct ip_mp_alg_ops *ops, enum ip_mp_alg n) -{ - struct ip_mp_alg_ops **slot; - - if (n < IP_MP_ALG_NONE || n > IP_MP_ALG_MAX) - return; - - spin_lock(&alg_table_lock); - slot = &ip_mp_alg_table[n]; - if (*slot == ops) - *slot = NULL; - spin_unlock(&alg_table_lock); - - synchronize_net(); -} -EXPORT_SYMBOL(multipath_alg_unregister); diff --git a/net/ipv4/multipath_drr.c b/net/ipv4/multipath_drr.c deleted file mode 100644 index b03c5ca2c823..000000000000 --- a/net/ipv4/multipath_drr.c +++ /dev/null @@ -1,249 +0,0 @@ -/* - * Device round robin policy for multipath. - * - * - * Version: $Id: multipath_drr.c,v 1.1.2.1 2004/09/16 07:42:34 elueck Exp $ - * - * Authors: Einar Lueck <elueck@de.ibm.com><lkml@einar-lueck.de> - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ - -#include <asm/system.h> -#include <asm/uaccess.h> -#include <linux/types.h> -#include <linux/errno.h> -#include <linux/timer.h> -#include <linux/mm.h> -#include <linux/kernel.h> -#include <linux/fcntl.h> -#include <linux/stat.h> -#include <linux/socket.h> -#include <linux/in.h> -#include <linux/inet.h> -#include <linux/netdevice.h> -#include <linux/inetdevice.h> -#include <linux/igmp.h> -#include <linux/proc_fs.h> -#include <linux/seq_file.h> -#include <linux/module.h> -#include <linux/mroute.h> -#include <linux/init.h> -#include <net/ip.h> -#include <net/protocol.h> -#include <linux/skbuff.h> -#include <net/sock.h> -#include <net/icmp.h> -#include <net/udp.h> -#include <net/raw.h> -#include <linux/notifier.h> -#include <linux/if_arp.h> -#include <linux/netfilter_ipv4.h> -#include <net/ipip.h> -#include <net/checksum.h> -#include <net/ip_mp_alg.h> - -struct multipath_device { - int ifi; /* interface index of device */ - atomic_t usecount; - int allocated; -}; - -#define MULTIPATH_MAX_DEVICECANDIDATES 10 - -static struct multipath_device state[MULTIPATH_MAX_DEVICECANDIDATES]; -static DEFINE_SPINLOCK(state_lock); - -static int inline __multipath_findslot(void) -{ - int i; - - for (i = 0; i < MULTIPATH_MAX_DEVICECANDIDATES; i++) { - if (state[i].allocated == 0) - return i; - } - return -1; -} - -static int inline __multipath_finddev(int ifindex) -{ - int i; - - for (i = 0; i < MULTIPATH_MAX_DEVICECANDIDATES; i++) { - if (state[i].allocated != 0 && - state[i].ifi == ifindex) - return i; - } - return -1; -} - -static int drr_dev_event(struct notifier_block *this, - unsigned long event, void *ptr) -{ - struct net_device *dev = ptr; - int devidx; - - switch (event) { - case NETDEV_UNREGISTER: - case NETDEV_DOWN: - spin_lock_bh(&state_lock); - - devidx = __multipath_finddev(dev->ifindex); - if (devidx != -1) { - state[devidx].allocated = 0; - state[devidx].ifi = 0; - atomic_set(&state[devidx].usecount, 0); - } - - spin_unlock_bh(&state_lock); - break; - } - - return NOTIFY_DONE; -} - -static struct notifier_block drr_dev_notifier = { - .notifier_call = drr_dev_event, -}; - - -static void drr_safe_inc(atomic_t *usecount) -{ - int n; - - atomic_inc(usecount); - - n = atomic_read(usecount); - if (n <= 0) { - int i; - - spin_lock_bh(&state_lock); - - for (i = 0; i < MULTIPATH_MAX_DEVICECANDIDATES; i++) - atomic_set(&state[i].usecount, 0); - - spin_unlock_bh(&state_lock); - } -} - -static void drr_select_route(const struct flowi *flp, - struct rtable *first, struct rtable **rp) -{ - struct rtable *nh, *result, *cur_min; - int min_usecount = -1; - int devidx = -1; - int cur_min_devidx = -1; - - /* 1. make sure all alt. nexthops have the same GC related data */ - /* 2. determine the new candidate to be returned */ - result = NULL; - cur_min = NULL; - for (nh = rcu_dereference(first); nh; - nh = rcu_dereference(nh->u.dst.rt_next)) { - if ((nh->u.dst.flags & DST_BALANCED) != 0 && - multipath_comparekeys(&nh->fl, flp)) { - int nh_ifidx = nh->u.dst.dev->ifindex; - - nh->u.dst.lastuse = jiffies; - nh->u.dst.__use++; - if (result != NULL) - continue; - - /* search for the output interface */ - - /* this is not SMP safe, only add/remove are - * SMP safe as wrong usecount updates have no big - * impact - */ - devidx = __multipath_finddev(nh_ifidx); - if (devidx == -1) { - /* add the interface to the array - * SMP safe - */ - spin_lock_bh(&state_lock); - - /* due to SMP: search again */ - devidx = __multipath_finddev(nh_ifidx); - if (devidx == -1) { - /* add entry for device */ - devidx = __multipath_findslot(); - if (devidx == -1) { - /* unlikely but possible */ - continue; - } - - state[devidx].allocated = 1; - state[devidx].ifi = nh_ifidx; - atomic_set(&state[devidx].usecount, 0); - min_usecount = 0; - } - - spin_unlock_bh(&state_lock); - } - - if (min_usecount == 0) { - /* if the device has not been used it is - * the primary target - */ - drr_safe_inc(&state[devidx].usecount); - result = nh; - } else { - int count = - atomic_read(&state[devidx].usecount); - - if (min_usecount == -1 || - count < min_usecount) { - cur_min = nh; - cur_min_devidx = devidx; - min_usecount = count; - } - } - } - } - - if (!result) { - if (cur_min) { - drr_safe_inc(&state[cur_min_devidx].usecount); - result = cur_min; - } else { - result = first; - } - } - - *rp = result; -} - -static struct ip_mp_alg_ops drr_ops = { - .mp_alg_select_route = drr_select_route, -}; - -static int __init drr_init(void) -{ - int err = register_netdevice_notifier(&drr_dev_notifier); - - if (err) - return err; - - err = multipath_alg_register(&drr_ops, IP_MP_ALG_DRR); - if (err) - goto fail; - - return 0; - -fail: - unregister_netdevice_notifier(&drr_dev_notifier); - return err; -} - -static void __exit drr_exit(void) -{ - unregister_netdevice_notifier(&drr_dev_notifier); - multipath_alg_unregister(&drr_ops, IP_MP_ALG_DRR); -} - -module_init(drr_init); -module_exit(drr_exit); -MODULE_LICENSE("GPL"); diff --git a/net/ipv4/multipath_random.c b/net/ipv4/multipath_random.c deleted file mode 100644 index c312785d14d0..000000000000 --- a/net/ipv4/multipath_random.c +++ /dev/null @@ -1,114 +0,0 @@ -/* - * Random policy for multipath. - * - * - * Version: $Id: multipath_random.c,v 1.1.2.3 2004/09/21 08:42:11 elueck Exp $ - * - * Authors: Einar Lueck <elueck@de.ibm.com><lkml@einar-lueck.de> - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ - -#include <asm/system.h> -#include <asm/uaccess.h> -#include <linux/types.h> -#include <linux/errno.h> -#include <linux/timer.h> -#include <linux/mm.h> -#include <linux/kernel.h> -#include <linux/fcntl.h> -#include <linux/stat.h> -#include <linux/socket.h> -#include <linux/in.h> -#include <linux/inet.h> -#include <linux/netdevice.h> -#include <linux/inetdevice.h> -#include <linux/igmp.h> -#include <linux/proc_fs.h> -#include <linux/seq_file.h> -#include <linux/module.h> -#include <linux/mroute.h> -#include <linux/init.h> -#include <linux/random.h> -#include <net/ip.h> -#include <net/protocol.h> -#include <linux/skbuff.h> -#include <net/sock.h> -#include <net/icmp.h> -#include <net/udp.h> -#include <net/raw.h> -#include <linux/notifier.h> -#include <linux/if_arp.h> -#include <linux/netfilter_ipv4.h> -#include <net/ipip.h> -#include <net/checksum.h> -#include <net/ip_mp_alg.h> - -#define MULTIPATH_MAX_CANDIDATES 40 - -static void random_select_route(const struct flowi *flp, - struct rtable *first, - struct rtable **rp) -{ - struct rtable *rt; - struct rtable *decision; - unsigned char candidate_count = 0; - - /* count all candidate */ - for (rt = rcu_dereference(first); rt; - rt = rcu_dereference(rt->u.dst.rt_next)) { - if ((rt->u.dst.flags & DST_BALANCED) != 0 && - multipath_comparekeys(&rt->fl, flp)) - ++candidate_count; - } - - /* choose a random candidate */ - decision = first; - if (candidate_count > 1) { - unsigned char i = 0; - unsigned char candidate_no = (unsigned char) - (random32() % candidate_count); - - /* find chosen candidate and adjust GC data for all candidates - * to ensure they stay in cache - */ - for (rt = first; rt; rt = rt->u.dst.rt_next) { - if ((rt->u.dst.flags & DST_BALANCED) != 0 && - multipath_comparekeys(&rt->fl, flp)) { - rt->u.dst.lastuse = jiffies; - - if (i == candidate_no) - decision = rt; - - if (i >= candidate_count) - break; - - i++; - } - } - } - - decision->u.dst.__use++; - *rp = decision; -} - -static struct ip_mp_alg_ops random_ops = { - .mp_alg_select_route = random_select_route, -}; - -static int __init random_init(void) -{ - return multipath_alg_register(&random_ops, IP_MP_ALG_RANDOM); -} - -static void __exit random_exit(void) -{ - multipath_alg_unregister(&random_ops, IP_MP_ALG_RANDOM); -} - -module_init(random_init); -module_exit(random_exit); -MODULE_LICENSE("GPL"); diff --git a/net/ipv4/multipath_rr.c b/net/ipv4/multipath_rr.c deleted file mode 100644 index 0ad22524f450..000000000000 --- a/net/ipv4/multipath_rr.c +++ /dev/null @@ -1,95 +0,0 @@ -/* - * Round robin policy for multipath. - * - * - * Version: $Id: multipath_rr.c,v 1.1.2.2 2004/09/16 07:42:34 elueck Exp $ - * - * Authors: Einar Lueck <elueck@de.ibm.com><lkml@einar-lueck.de> - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ - -#include <asm/system.h> -#include <asm/uaccess.h> -#include <linux/types.h> -#include <linux/errno.h> -#include <linux/timer.h> -#include <linux/mm.h> -#include <linux/kernel.h> -#include <linux/fcntl.h> -#include <linux/stat.h> -#include <linux/socket.h> -#include <linux/in.h> -#include <linux/inet.h> -#include <linux/netdevice.h> -#include <linux/inetdevice.h> -#include <linux/igmp.h> -#include <linux/proc_fs.h> -#include <linux/seq_file.h> -#include <linux/module.h> -#include <linux/mroute.h> -#include <linux/init.h> -#include <net/ip.h> -#include <net/protocol.h> -#include <linux/skbuff.h> -#include <net/sock.h> -#include <net/icmp.h> -#include <net/udp.h> -#include <net/raw.h> -#include <linux/notifier.h> -#include <linux/if_arp.h> -#include <linux/netfilter_ipv4.h> -#include <net/ipip.h> -#include <net/checksum.h> -#include <net/ip_mp_alg.h> - -static void rr_select_route(const struct flowi *flp, - struct rtable *first, struct rtable **rp) -{ - struct rtable *nh, *result, *min_use_cand = NULL; - int min_use = -1; - - /* 1. make sure all alt. nexthops have the same GC related data - * 2. determine the new candidate to be returned - */ - result = NULL; - for (nh = rcu_dereference(first); nh; - nh = rcu_dereference(nh->u.dst.rt_next)) { - if ((nh->u.dst.flags & DST_BALANCED) != 0 && - multipath_comparekeys(&nh->fl, flp)) { - nh->u.dst.lastuse = jiffies; - - if (min_use == -1 || nh->u.dst.__use < min_use) { - min_use = nh->u.dst.__use; - min_use_cand = nh; - } - } - } - result = min_use_cand; - if (!result) - result = first; - - result->u.dst.__use++; - *rp = result; -} - -static struct ip_mp_alg_ops rr_ops = { - .mp_alg_select_route = rr_select_route, -}; - -static int __init rr_init(void) -{ - return multipath_alg_register(&rr_ops, IP_MP_ALG_RR); -} - -static void __exit rr_exit(void) -{ - multipath_alg_unregister(&rr_ops, IP_MP_ALG_RR); -} - -module_init(rr_init); -module_exit(rr_exit); -MODULE_LICENSE("GPL"); diff --git a/net/ipv4/multipath_wrandom.c b/net/ipv4/multipath_wrandom.c deleted file mode 100644 index 57c503694539..000000000000 --- a/net/ipv4/multipath_wrandom.c +++ /dev/null @@ -1,329 +0,0 @@ -/* - * Weighted random policy for multipath. - * - * - * Version: $Id: multipath_wrandom.c,v 1.1.2.3 2004/09/22 07:51:40 elueck Exp $ - * - * Authors: Einar Lueck <elueck@de.ibm.com><lkml@einar-lueck.de> - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ - -#include <asm/system.h> -#include <asm/uaccess.h> -#include <linux/types.h> -#include <linux/errno.h> -#include <linux/timer.h> -#include <linux/mm.h> -#include <linux/kernel.h> -#include <linux/fcntl.h> -#include <linux/stat.h> -#include <linux/socket.h> -#include <linux/in.h> -#include <linux/inet.h> -#include <linux/netdevice.h> -#include <linux/inetdevice.h> -#include <linux/igmp.h> -#include <linux/proc_fs.h> -#include <linux/seq_file.h> -#include <linux/module.h> -#include <linux/mroute.h> -#include <linux/init.h> -#include <linux/random.h> -#include <net/ip.h> -#include <net/protocol.h> -#include <linux/skbuff.h> -#include <net/sock.h> -#include <net/icmp.h> -#include <net/udp.h> -#include <net/raw.h> -#include <linux/notifier.h> -#include <linux/if_arp.h> -#include <linux/netfilter_ipv4.h> -#include <net/ipip.h> -#include <net/checksum.h> -#include <net/ip_fib.h> -#include <net/ip_mp_alg.h> - -#define MULTIPATH_STATE_SIZE 15 - -struct multipath_candidate { - struct multipath_candidate *next; - int power; - struct rtable *rt; -}; - -struct multipath_dest { - struct list_head list; - - const struct fib_nh *nh_info; - __be32 netmask; - __be32 network; - unsigned char prefixlen; - - struct rcu_head rcu; -}; - -struct multipath_bucket { - struct list_head head; - spinlock_t lock; -}; - -struct multipath_route { - struct list_head list; - - int oif; - __be32 gw; - struct list_head dests; - - struct rcu_head rcu; -}; - -/* state: primarily weight per route information */ -static struct multipath_bucket state[MULTIPATH_STATE_SIZE]; - -static unsigned char __multipath_lookup_weight(const struct flowi *fl, - const struct rtable *rt) -{ - const int state_idx = rt->idev->dev->ifindex % MULTIPATH_STATE_SIZE; - struct multipath_route *r; - struct multipath_route *target_route = NULL; - struct multipath_dest *d; - int weight = 1; - - /* lookup the weight information for a certain route */ - rcu_read_lock(); - - /* find state entry for gateway or add one if necessary */ - list_for_each_entry_rcu(r, &state[state_idx].head, list) { - if (r->gw == rt->rt_gateway && - r->oif == rt->idev->dev->ifindex) { - target_route = r; - break; - } - } - - if (!target_route) { - /* this should not happen... but we are prepared */ - printk( KERN_CRIT"%s: missing state for gateway: %u and " \ - "device %d\n", __FUNCTION__, rt->rt_gateway, - rt->idev->dev->ifindex); - goto out; - } - - /* find state entry for destination */ - list_for_each_entry_rcu(d, &target_route->dests, list) { - __be32 targetnetwork = fl->fl4_dst & - inet_make_mask(d->prefixlen); - - if ((targetnetwork & d->netmask) == d->network) { - weight = d->nh_info->nh_weight; - goto out; - } - } - -out: - rcu_read_unlock(); - return weight; -} - -static void wrandom_init_state(void) -{ - int i; - - for (i = 0; i < MULTIPATH_STATE_SIZE; ++i) { - INIT_LIST_HEAD(&state[i].head); - spin_lock_init(&state[i].lock); - } -} - -static void wrandom_select_route(const struct flowi *flp, - struct rtable *first, - struct rtable **rp) -{ - struct rtable *rt; - struct rtable *decision; - struct multipath_candidate *first_mpc = NULL; - struct multipath_candidate *mpc, *last_mpc = NULL; - int power = 0; - int last_power; - int selector; - const size_t size_mpc = sizeof(struct multipath_candidate); - - /* collect all candidates and identify their weights */ - for (rt = rcu_dereference(first); rt; - rt = rcu_dereference(rt->u.dst.rt_next)) { - if ((rt->u.dst.flags & DST_BALANCED) != 0 && - multipath_comparekeys(&rt->fl, flp)) { - struct multipath_candidate* mpc = - (struct multipath_candidate*) - kmalloc(size_mpc, GFP_ATOMIC); - - if (!mpc) - return; - - power += __multipath_lookup_weight(flp, rt) * 10000; - - mpc->power = power; - mpc->rt = rt; - mpc->next = NULL; - - if (!first_mpc) - first_mpc = mpc; - else - last_mpc->next = mpc; - - last_mpc = mpc; - } - } - - /* choose a weighted random candidate */ - decision = first; - selector = random32() % power; - last_power = 0; - - /* select candidate, adjust GC data and cleanup local state */ - decision = first; - last_mpc = NULL; - for (mpc = first_mpc; mpc; mpc = mpc->next) { - mpc->rt->u.dst.lastuse = jiffies; - if (last_power <= selector && selector < mpc->power) - decision = mpc->rt; - - last_power = mpc->power; - kfree(last_mpc); - last_mpc = mpc; - } - - /* concurrent __multipath_flush may lead to !last_mpc */ - kfree(last_mpc); - - decision->u.dst.__use++; - *rp = decision; -} - -static void wrandom_set_nhinfo(__be32 network, - __be32 netmask, - unsigned char prefixlen, - const struct fib_nh *nh) -{ - const int state_idx = nh->nh_oif % MULTIPATH_STATE_SIZE; - struct multipath_route *r, *target_route = NULL; - struct multipath_dest *d, *target_dest = NULL; - - /* store the weight information for a certain route */ - spin_lock_bh(&state[state_idx].lock); - - /* find state entry for gateway or add one if necessary */ - list_for_each_entry_rcu(r, &state[state_idx].head, list) { - if (r->gw == nh->nh_gw && r->oif == nh->nh_oif) { - target_route = r; - break; - } - } - - if (!target_route) { - const size_t size_rt = sizeof(struct multipath_route); - target_route = (struct multipath_route *) - kmalloc(size_rt, GFP_ATOMIC); - - target_route->gw = nh->nh_gw; - target_route->oif = nh->nh_oif; - memset(&target_route->rcu, 0, sizeof(struct rcu_head)); - INIT_LIST_HEAD(&target_route->dests); - - list_add_rcu(&target_route->list, &state[state_idx].head); - } - - /* find state entry for destination or add one if necessary */ - list_for_each_entry_rcu(d, &target_route->dests, list) { - if (d->nh_info == nh) { - target_dest = d; - break; - } - } - - if (!target_dest) { - const size_t size_dst = sizeof(struct multipath_dest); - target_dest = (struct multipath_dest*) - kmalloc(size_dst, GFP_ATOMIC); - - target_dest->nh_info = nh; - target_dest->network = network; - target_dest->netmask = netmask; - target_dest->prefixlen = prefixlen; - memset(&target_dest->rcu, 0, sizeof(struct rcu_head)); - - list_add_rcu(&target_dest->list, &target_route->dests); - } - /* else: we already stored this info for another destination => - * we are finished - */ - - spin_unlock_bh(&state[state_idx].lock); -} - -static void __multipath_free(struct rcu_head *head) -{ - struct multipath_route *rt = container_of(head, struct multipath_route, - rcu); - kfree(rt); -} - -static void __multipath_free_dst(struct rcu_head *head) -{ - struct multipath_dest *dst = container_of(head, - struct multipath_dest, - rcu); - kfree(dst); -} - -static void wrandom_flush(void) -{ - int i; - - /* defere delete to all entries */ - for (i = 0; i < MULTIPATH_STATE_SIZE; ++i) { - struct multipath_route *r; - - spin_lock_bh(&state[i].lock); - list_for_each_entry_rcu(r, &state[i].head, list) { - struct multipath_dest *d; - list_for_each_entry_rcu(d, &r->dests, list) { - list_del_rcu(&d->list); - call_rcu(&d->rcu, - __multipath_free_dst); - } - list_del_rcu(&r->list); - call_rcu(&r->rcu, - __multipath_free); - } - - spin_unlock_bh(&state[i].lock); - } -} - -static struct ip_mp_alg_ops wrandom_ops = { - .mp_alg_select_route = wrandom_select_route, - .mp_alg_flush = wrandom_flush, - .mp_alg_set_nhinfo = wrandom_set_nhinfo, -}; - -static int __init wrandom_init(void) -{ - wrandom_init_state(); - - return multipath_alg_register(&wrandom_ops, IP_MP_ALG_WRANDOM); -} - -static void __exit wrandom_exit(void) -{ - multipath_alg_unregister(&wrandom_ops, IP_MP_ALG_WRANDOM); -} - -module_init(wrandom_init); -module_exit(wrandom_exit); -MODULE_LICENSE("GPL"); diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig index 46509fae9fd8..fa97947c6ae1 100644 --- a/net/ipv4/netfilter/Kconfig +++ b/net/ipv4/netfilter/Kconfig @@ -230,7 +230,7 @@ config IP_NF_TARGET_NETMAP To compile it as a module, choose M here. If unsure, say N. config IP_NF_TARGET_SAME - tristate "SAME target support" + tristate "SAME target support (OBSOLETE)" depends on NF_NAT help This option adds a `SAME' target, which works like the standard SNAT diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index cae41215e3c7..d1149aba9351 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -224,7 +224,7 @@ unsigned int arpt_do_table(struct sk_buff **pskb, static const char nulldevname[IFNAMSIZ]; unsigned int verdict = NF_DROP; struct arphdr *arp; - int hotdrop = 0; + bool hotdrop = false; struct arpt_entry *e, *back; const char *indev, *outdev; void *table_base; @@ -1140,13 +1140,13 @@ void arpt_unregister_table(struct arpt_table *table) } /* The built-in targets: standard (NULL) and error. */ -static struct arpt_target arpt_standard_target = { +static struct arpt_target arpt_standard_target __read_mostly = { .name = ARPT_STANDARD_TARGET, .targetsize = sizeof(int), .family = NF_ARP, }; -static struct arpt_target arpt_error_target = { +static struct arpt_target arpt_error_target __read_mostly = { .name = ARPT_ERROR_TARGET, .target = arpt_error, .targetsize = ARPT_FUNCTION_MAXNAMELEN, @@ -1184,7 +1184,7 @@ static int __init arp_tables_init(void) if (ret < 0) goto err4; - printk("arp_tables: (C) 2002 David S. Miller\n"); + printk(KERN_INFO "arp_tables: (C) 2002 David S. Miller\n"); return 0; err4: diff --git a/net/ipv4/netfilter/arpt_mangle.c b/net/ipv4/netfilter/arpt_mangle.c index 6298d404e7c7..c4bdab47597f 100644 --- a/net/ipv4/netfilter/arpt_mangle.c +++ b/net/ipv4/netfilter/arpt_mangle.c @@ -65,7 +65,7 @@ target(struct sk_buff **pskb, return mangle->target; } -static int +static bool checkentry(const char *tablename, const void *e, const struct xt_target *target, void *targinfo, unsigned int hook_mask) { @@ -73,15 +73,15 @@ checkentry(const char *tablename, const void *e, const struct xt_target *target, if (mangle->flags & ~ARPT_MANGLE_MASK || !(mangle->flags & ARPT_MANGLE_MASK)) - return 0; + return false; if (mangle->target != NF_DROP && mangle->target != NF_ACCEPT && mangle->target != ARPT_CONTINUE) - return 0; - return 1; + return false; + return true; } -static struct arpt_target arpt_mangle_reg = { +static struct arpt_target arpt_mangle_reg __read_mostly = { .name = "mangle", .target = target, .targetsize = sizeof(struct arpt_mangle), diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index 9bacf1a03630..e1b402c6b855 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -152,20 +152,20 @@ ip_packet_match(const struct iphdr *ip, return 1; } -static inline int +static inline bool ip_checkentry(const struct ipt_ip *ip) { if (ip->flags & ~IPT_F_MASK) { duprintf("Unknown flag bits set: %08X\n", ip->flags & ~IPT_F_MASK); - return 0; + return false; } if (ip->invflags & ~IPT_INV_MASK) { duprintf("Unknown invflag bits set: %08X\n", ip->invflags & ~IPT_INV_MASK); - return 0; + return false; } - return 1; + return true; } static unsigned int @@ -183,19 +183,19 @@ ipt_error(struct sk_buff **pskb, } static inline -int do_match(struct ipt_entry_match *m, - const struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int offset, - int *hotdrop) +bool do_match(struct ipt_entry_match *m, + const struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + int offset, + bool *hotdrop) { /* Stop iteration if it doesn't match */ if (!m->u.kernel.match->match(skb, in, out, m->u.kernel.match, m->data, offset, ip_hdrlen(skb), hotdrop)) - return 1; + return true; else - return 0; + return false; } static inline struct ipt_entry * @@ -204,6 +204,112 @@ get_entry(void *base, unsigned int offset) return (struct ipt_entry *)(base + offset); } +/* All zeroes == unconditional rule. */ +static inline int +unconditional(const struct ipt_ip *ip) +{ + unsigned int i; + + for (i = 0; i < sizeof(*ip)/sizeof(__u32); i++) + if (((__u32 *)ip)[i]) + return 0; + + return 1; +} + +#if defined(CONFIG_NETFILTER_XT_TARGET_TRACE) || \ + defined(CONFIG_NETFILTER_XT_TARGET_TRACE_MODULE) +static const char *hooknames[] = { + [NF_IP_PRE_ROUTING] = "PREROUTING", + [NF_IP_LOCAL_IN] = "INPUT", + [NF_IP_FORWARD] = "FORWARD", + [NF_IP_LOCAL_OUT] = "OUTPUT", + [NF_IP_POST_ROUTING] = "POSTROUTING", +}; + +enum nf_ip_trace_comments { + NF_IP_TRACE_COMMENT_RULE, + NF_IP_TRACE_COMMENT_RETURN, + NF_IP_TRACE_COMMENT_POLICY, +}; + +static const char *comments[] = { + [NF_IP_TRACE_COMMENT_RULE] = "rule", + [NF_IP_TRACE_COMMENT_RETURN] = "return", + [NF_IP_TRACE_COMMENT_POLICY] = "policy", +}; + +static struct nf_loginfo trace_loginfo = { + .type = NF_LOG_TYPE_LOG, + .u = { + .log = { + .level = 4, + .logflags = NF_LOG_MASK, + }, + }, +}; + +static inline int +get_chainname_rulenum(struct ipt_entry *s, struct ipt_entry *e, + char *hookname, char **chainname, + char **comment, unsigned int *rulenum) +{ + struct ipt_standard_target *t = (void *)ipt_get_target(s); + + if (strcmp(t->target.u.kernel.target->name, IPT_ERROR_TARGET) == 0) { + /* Head of user chain: ERROR target with chainname */ + *chainname = t->target.data; + (*rulenum) = 0; + } else if (s == e) { + (*rulenum)++; + + if (s->target_offset == sizeof(struct ipt_entry) + && strcmp(t->target.u.kernel.target->name, + IPT_STANDARD_TARGET) == 0 + && t->verdict < 0 + && unconditional(&s->ip)) { + /* Tail of chains: STANDARD target (return/policy) */ + *comment = *chainname == hookname + ? (char *)comments[NF_IP_TRACE_COMMENT_POLICY] + : (char *)comments[NF_IP_TRACE_COMMENT_RETURN]; + } + return 1; + } else + (*rulenum)++; + + return 0; +} + +static void trace_packet(struct sk_buff *skb, + unsigned int hook, + const struct net_device *in, + const struct net_device *out, + char *tablename, + struct xt_table_info *private, + struct ipt_entry *e) +{ + void *table_base; + struct ipt_entry *root; + char *hookname, *chainname, *comment; + unsigned int rulenum = 0; + + table_base = (void *)private->entries[smp_processor_id()]; + root = get_entry(table_base, private->hook_entry[hook]); + + hookname = chainname = (char *)hooknames[hook]; + comment = (char *)comments[NF_IP_TRACE_COMMENT_RULE]; + + IPT_ENTRY_ITERATE(root, + private->size - private->hook_entry[hook], + get_chainname_rulenum, + e, hookname, &chainname, &comment, &rulenum); + + nf_log_packet(AF_INET, hook, skb, in, out, &trace_loginfo, + "TRACE: %s:%s:%s:%u ", + tablename, chainname, comment, rulenum); +} +#endif + /* Returns one of the generic firewall policies, like NF_ACCEPT. */ unsigned int ipt_do_table(struct sk_buff **pskb, @@ -216,7 +322,7 @@ ipt_do_table(struct sk_buff **pskb, u_int16_t offset; struct iphdr *ip; u_int16_t datalen; - int hotdrop = 0; + bool hotdrop = false; /* Initializing verdict to NF_DROP keeps gcc happy. */ unsigned int verdict = NF_DROP; const char *indev, *outdev; @@ -261,6 +367,14 @@ ipt_do_table(struct sk_buff **pskb, t = ipt_get_target(e); IP_NF_ASSERT(t->u.kernel.target); + +#if defined(CONFIG_NETFILTER_XT_TARGET_TRACE) || \ + defined(CONFIG_NETFILTER_XT_TARGET_TRACE_MODULE) + /* The packet is traced: log it */ + if (unlikely((*pskb)->nf_trace)) + trace_packet(*pskb, hook, in, out, + table->name, private, e); +#endif /* Standard target? */ if (!t->u.kernel.target->target) { int v; @@ -341,19 +455,6 @@ ipt_do_table(struct sk_buff **pskb, #endif } -/* All zeroes == unconditional rule. */ -static inline int -unconditional(const struct ipt_ip *ip) -{ - unsigned int i; - - for (i = 0; i < sizeof(*ip)/sizeof(__u32); i++) - if (((__u32 *)ip)[i]) - return 0; - - return 1; -} - /* Figures out from what hook each rule can be called: returns 0 if there are loops. Puts hook bitmask in comefrom. */ static int @@ -2105,16 +2206,16 @@ void ipt_unregister_table(struct xt_table *table) } /* Returns 1 if the type and code is matched by the range, 0 otherwise */ -static inline int +static inline bool icmp_type_code_match(u_int8_t test_type, u_int8_t min_code, u_int8_t max_code, u_int8_t type, u_int8_t code, - int invert) + bool invert) { return ((test_type == 0xFF) || (type == test_type && code >= min_code && code <= max_code)) ^ invert; } -static int +static bool icmp_match(const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, @@ -2122,14 +2223,14 @@ icmp_match(const struct sk_buff *skb, const void *matchinfo, int offset, unsigned int protoff, - int *hotdrop) + bool *hotdrop) { struct icmphdr _icmph, *ic; const struct ipt_icmp *icmpinfo = matchinfo; /* Must not be a fragment. */ if (offset) - return 0; + return false; ic = skb_header_pointer(skb, protoff, sizeof(_icmph), &_icmph); if (ic == NULL) { @@ -2137,8 +2238,8 @@ icmp_match(const struct sk_buff *skb, * can't. Hence, no choice but to drop. */ duprintf("Dropping evil ICMP tinygram.\n"); - *hotdrop = 1; - return 0; + *hotdrop = true; + return false; } return icmp_type_code_match(icmpinfo->type, @@ -2149,7 +2250,7 @@ icmp_match(const struct sk_buff *skb, } /* Called when user tries to insert an entry of this type. */ -static int +static bool icmp_checkentry(const char *tablename, const void *info, const struct xt_match *match, @@ -2163,7 +2264,7 @@ icmp_checkentry(const char *tablename, } /* The built-in targets: standard (NULL) and error. */ -static struct xt_target ipt_standard_target = { +static struct xt_target ipt_standard_target __read_mostly = { .name = IPT_STANDARD_TARGET, .targetsize = sizeof(int), .family = AF_INET, @@ -2174,7 +2275,7 @@ static struct xt_target ipt_standard_target = { #endif }; -static struct xt_target ipt_error_target = { +static struct xt_target ipt_error_target __read_mostly = { .name = IPT_ERROR_TARGET, .target = ipt_error, .targetsize = IPT_FUNCTION_MAXNAMELEN, @@ -2197,7 +2298,7 @@ static struct nf_sockopt_ops ipt_sockopts = { #endif }; -static struct xt_match icmp_matchstruct = { +static struct xt_match icmp_matchstruct __read_mostly = { .name = "icmp", .match = icmp_match, .matchsize = sizeof(struct ipt_icmp), @@ -2230,7 +2331,7 @@ static int __init ip_tables_init(void) if (ret < 0) goto err5; - printk("ip_tables: (C) 2000-2006 Netfilter Core Team\n"); + printk(KERN_INFO "ip_tables: (C) 2000-2006 Netfilter Core Team\n"); return 0; err5: diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c index 40e273421398..dcc12b183474 100644 --- a/net/ipv4/netfilter/ipt_CLUSTERIP.c +++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c @@ -30,14 +30,6 @@ #define CLUSTERIP_VERSION "0.8" -#define DEBUG_CLUSTERIP - -#ifdef DEBUG_CLUSTERIP -#define DEBUGP printk -#else -#define DEBUGP -#endif - MODULE_LICENSE("GPL"); MODULE_AUTHOR("Harald Welte <laforge@netfilter.org>"); MODULE_DESCRIPTION("iptables target for CLUSTERIP"); @@ -122,9 +114,8 @@ __clusterip_config_find(__be32 clusterip) list_for_each(pos, &clusterip_configs) { struct clusterip_config *c = list_entry(pos, struct clusterip_config, list); - if (c->clusterip == clusterip) { + if (c->clusterip == clusterip) return c; - } } return NULL; @@ -155,9 +146,8 @@ clusterip_config_init_nodelist(struct clusterip_config *c, { int n; - for (n = 0; n < i->num_local_nodes; n++) { + for (n = 0; n < i->num_local_nodes; n++) set_bit(i->local_nodes[n] - 1, &c->local_nodes); - } } static struct clusterip_config * @@ -220,27 +210,28 @@ clusterip_add_node(struct clusterip_config *c, u_int16_t nodenum) return 0; } -static int +static bool clusterip_del_node(struct clusterip_config *c, u_int16_t nodenum) { if (nodenum == 0 || nodenum > c->num_total_nodes) - return 1; + return true; if (test_and_clear_bit(nodenum - 1, &c->local_nodes)) - return 0; + return false; - return 1; + return true; } #endif static inline u_int32_t -clusterip_hashfn(struct sk_buff *skb, struct clusterip_config *config) +clusterip_hashfn(const struct sk_buff *skb, + const struct clusterip_config *config) { - struct iphdr *iph = ip_hdr(skb); + const struct iphdr *iph = ip_hdr(skb); unsigned long hashval; u_int16_t sport, dport; - u_int16_t *ports; + const u_int16_t *ports; switch (iph->protocol) { case IPPROTO_TCP: @@ -249,15 +240,14 @@ clusterip_hashfn(struct sk_buff *skb, struct clusterip_config *config) case IPPROTO_SCTP: case IPPROTO_DCCP: case IPPROTO_ICMP: - ports = (void *)iph+iph->ihl*4; + ports = (const void *)iph+iph->ihl*4; sport = ports[0]; dport = ports[1]; break; default: - if (net_ratelimit()) { + if (net_ratelimit()) printk(KERN_NOTICE "CLUSTERIP: unknown protocol `%u'\n", iph->protocol); - } sport = dport = 0; } @@ -285,11 +275,11 @@ clusterip_hashfn(struct sk_buff *skb, struct clusterip_config *config) } /* node numbers are 1..n, not 0..n */ - return ((hashval % config->num_total_nodes)+1); + return (hashval % config->num_total_nodes) + 1; } static inline int -clusterip_responsible(struct clusterip_config *config, u_int32_t hash) +clusterip_responsible(const struct clusterip_config *config, u_int32_t hash) { return test_bit(hash - 1, &config->local_nodes); } @@ -353,15 +343,15 @@ target(struct sk_buff **pskb, break; } -#ifdef DEBUG_CLUSTERP +#ifdef DEBUG DUMP_TUPLE(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); #endif - DEBUGP("hash=%u ct_hash=%u ", hash, ct->mark); + pr_debug("hash=%u ct_hash=%u ", hash, ct->mark); if (!clusterip_responsible(cipinfo->config, hash)) { - DEBUGP("not responsible\n"); + pr_debug("not responsible\n"); return NF_DROP; } - DEBUGP("responsible\n"); + pr_debug("responsible\n"); /* despite being received via linklayer multicast, this is * actually a unicast IP packet. TCP doesn't like PACKET_MULTICAST */ @@ -370,7 +360,7 @@ target(struct sk_buff **pskb, return XT_CONTINUE; } -static int +static bool checkentry(const char *tablename, const void *e_void, const struct xt_target *target, @@ -387,50 +377,34 @@ checkentry(const char *tablename, cipinfo->hash_mode != CLUSTERIP_HASHMODE_SIP_SPT_DPT) { printk(KERN_WARNING "CLUSTERIP: unknown mode `%u'\n", cipinfo->hash_mode); - return 0; + return false; } if (e->ip.dmsk.s_addr != htonl(0xffffffff) || e->ip.dst.s_addr == 0) { printk(KERN_ERR "CLUSTERIP: Please specify destination IP\n"); - return 0; + return false; } /* FIXME: further sanity checks */ config = clusterip_config_find_get(e->ip.dst.s_addr, 1); - if (config) { - if (cipinfo->config != NULL) { - /* Case A: This is an entry that gets reloaded, since - * it still has a cipinfo->config pointer. Simply - * increase the entry refcount and return */ - if (cipinfo->config != config) { - printk(KERN_ERR "CLUSTERIP: Reloaded entry " - "has invalid config pointer!\n"); - return 0; - } - } else { - /* Case B: This is a new rule referring to an existing - * clusterip config. */ - cipinfo->config = config; - } - } else { - /* Case C: This is a completely new clusterip config */ + if (!config) { if (!(cipinfo->flags & CLUSTERIP_FLAG_NEW)) { printk(KERN_WARNING "CLUSTERIP: no config found for %u.%u.%u.%u, need 'new'\n", NIPQUAD(e->ip.dst.s_addr)); - return 0; + return false; } else { struct net_device *dev; if (e->ip.iniface[0] == '\0') { printk(KERN_WARNING "CLUSTERIP: Please specify an interface name\n"); - return 0; + return false; } dev = dev_get_by_name(e->ip.iniface); if (!dev) { printk(KERN_WARNING "CLUSTERIP: no such interface %s\n", e->ip.iniface); - return 0; + return false; } config = clusterip_config_init(cipinfo, @@ -438,20 +412,20 @@ checkentry(const char *tablename, if (!config) { printk(KERN_WARNING "CLUSTERIP: cannot allocate config\n"); dev_put(dev); - return 0; + return false; } dev_mc_add(config->dev,config->clustermac, ETH_ALEN, 0); } - cipinfo->config = config; } + cipinfo->config = config; if (nf_ct_l3proto_try_module_get(target->family) < 0) { printk(KERN_WARNING "can't load conntrack support for " "proto=%d\n", target->family); - return 0; + return false; } - return 1; + return true; } /* drop reference count of cluster config when rule is deleted */ @@ -468,13 +442,30 @@ static void destroy(const struct xt_target *target, void *targinfo) nf_ct_l3proto_module_put(target->family); } -static struct xt_target clusterip_tgt = { +#ifdef CONFIG_COMPAT +struct compat_ipt_clusterip_tgt_info +{ + u_int32_t flags; + u_int8_t clustermac[6]; + u_int16_t num_total_nodes; + u_int16_t num_local_nodes; + u_int16_t local_nodes[CLUSTERIP_MAX_NODES]; + u_int32_t hash_mode; + u_int32_t hash_initval; + compat_uptr_t config; +}; +#endif /* CONFIG_COMPAT */ + +static struct xt_target clusterip_tgt __read_mostly = { .name = "CLUSTERIP", .family = AF_INET, .target = target, - .targetsize = sizeof(struct ipt_clusterip_tgt_info), .checkentry = checkentry, .destroy = destroy, + .targetsize = sizeof(struct ipt_clusterip_tgt_info), +#ifdef CONFIG_COMPAT + .compatsize = sizeof(struct compat_ipt_clusterip_tgt_info), +#endif /* CONFIG_COMPAT */ .me = THIS_MODULE }; @@ -491,7 +482,7 @@ struct arp_payload { __be32 dst_ip; } __attribute__ ((packed)); -#ifdef CLUSTERIP_DEBUG +#ifdef DEBUG static void arp_print(struct arp_payload *payload) { #define HBUFFERLEN 30 @@ -547,8 +538,9 @@ arp_mangle(unsigned int hook, * this wouldn't work, since we didn't subscribe the mcast group on * other interfaces */ if (c->dev != out) { - DEBUGP("CLUSTERIP: not mangling arp reply on different " - "interface: cip'%s'-skb'%s'\n", c->dev->name, out->name); + pr_debug("CLUSTERIP: not mangling arp reply on different " + "interface: cip'%s'-skb'%s'\n", + c->dev->name, out->name); clusterip_config_put(c); return NF_ACCEPT; } @@ -556,8 +548,8 @@ arp_mangle(unsigned int hook, /* mangle reply hardware address */ memcpy(payload->src_hw, c->clustermac, arp->ar_hln); -#ifdef CLUSTERIP_DEBUG - DEBUGP(KERN_DEBUG "CLUSTERIP mangled arp reply: "); +#ifdef DEBUG + pr_debug(KERN_DEBUG "CLUSTERIP mangled arp reply: "); arp_print(payload); #endif @@ -647,7 +639,7 @@ static int clusterip_seq_show(struct seq_file *s, void *v) return 0; } -static struct seq_operations clusterip_seq_ops = { +static const struct seq_operations clusterip_seq_ops = { .start = clusterip_seq_start, .next = clusterip_seq_next, .stop = clusterip_seq_stop, diff --git a/net/ipv4/netfilter/ipt_ECN.c b/net/ipv4/netfilter/ipt_ECN.c index 918ca92e534a..f1253bd3837f 100644 --- a/net/ipv4/netfilter/ipt_ECN.c +++ b/net/ipv4/netfilter/ipt_ECN.c @@ -24,8 +24,8 @@ MODULE_AUTHOR("Harald Welte <laforge@netfilter.org>"); MODULE_DESCRIPTION("iptables ECN modification module"); /* set ECT codepoint from IP header. - * return 0 if there was an error. */ -static inline int + * return false if there was an error. */ +static inline bool set_ect_ip(struct sk_buff **pskb, const struct ipt_ECN_info *einfo) { struct iphdr *iph = ip_hdr(*pskb); @@ -33,18 +33,18 @@ set_ect_ip(struct sk_buff **pskb, const struct ipt_ECN_info *einfo) if ((iph->tos & IPT_ECN_IP_MASK) != (einfo->ip_ect & IPT_ECN_IP_MASK)) { __u8 oldtos; if (!skb_make_writable(pskb, sizeof(struct iphdr))) - return 0; + return false; iph = ip_hdr(*pskb); oldtos = iph->tos; iph->tos &= ~IPT_ECN_IP_MASK; iph->tos |= (einfo->ip_ect & IPT_ECN_IP_MASK); nf_csum_replace2(&iph->check, htons(oldtos), htons(iph->tos)); } - return 1; + return true; } -/* Return 0 if there was an error. */ -static inline int +/* Return false if there was an error. */ +static inline bool set_ect_tcp(struct sk_buff **pskb, const struct ipt_ECN_info *einfo) { struct tcphdr _tcph, *tcph; @@ -54,16 +54,16 @@ set_ect_tcp(struct sk_buff **pskb, const struct ipt_ECN_info *einfo) tcph = skb_header_pointer(*pskb, ip_hdrlen(*pskb), sizeof(_tcph), &_tcph); if (!tcph) - return 0; + return false; if ((!(einfo->operation & IPT_ECN_OP_SET_ECE) || tcph->ece == einfo->proto.tcp.ece) && - ((!(einfo->operation & IPT_ECN_OP_SET_CWR) || - tcph->cwr == einfo->proto.tcp.cwr))) - return 1; + (!(einfo->operation & IPT_ECN_OP_SET_CWR) || + tcph->cwr == einfo->proto.tcp.cwr)) + return true; if (!skb_make_writable(pskb, ip_hdrlen(*pskb) + sizeof(*tcph))) - return 0; + return false; tcph = (void *)ip_hdr(*pskb) + ip_hdrlen(*pskb); oldval = ((__be16 *)tcph)[6]; @@ -74,7 +74,7 @@ set_ect_tcp(struct sk_buff **pskb, const struct ipt_ECN_info *einfo) nf_proto_csum_replace2(&tcph->check, *pskb, oldval, ((__be16 *)tcph)[6], 0); - return 1; + return true; } static unsigned int @@ -99,7 +99,7 @@ target(struct sk_buff **pskb, return XT_CONTINUE; } -static int +static bool checkentry(const char *tablename, const void *e_void, const struct xt_target *target, @@ -112,23 +112,23 @@ checkentry(const char *tablename, if (einfo->operation & IPT_ECN_OP_MASK) { printk(KERN_WARNING "ECN: unsupported ECN operation %x\n", einfo->operation); - return 0; + return false; } if (einfo->ip_ect & ~IPT_ECN_IP_MASK) { printk(KERN_WARNING "ECN: new ECT codepoint %x out of mask\n", einfo->ip_ect); - return 0; + return false; } 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 0; + return false; } - return 1; + return true; } -static struct xt_target ipt_ecn_reg = { +static struct xt_target ipt_ecn_reg __read_mostly = { .name = "ECN", .family = AF_INET, .target = target, diff --git a/net/ipv4/netfilter/ipt_LOG.c b/net/ipv4/netfilter/ipt_LOG.c index a42c5cd968b1..5937ad150b9f 100644 --- a/net/ipv4/netfilter/ipt_LOG.c +++ b/net/ipv4/netfilter/ipt_LOG.c @@ -27,12 +27,6 @@ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>"); MODULE_DESCRIPTION("iptables syslog logging module"); -#if 0 -#define DEBUGP printk -#else -#define DEBUGP(format, args...) -#endif - /* Use lock to serialize, so printks don't overlap */ static DEFINE_SPINLOCK(log_lock); @@ -41,7 +35,8 @@ static void dump_packet(const struct nf_loginfo *info, const struct sk_buff *skb, unsigned int iphoff) { - struct iphdr _iph, *ih; + struct iphdr _iph; + const struct iphdr *ih; unsigned int logflags; if (info->type == NF_LOG_TYPE_LOG) @@ -100,7 +95,8 @@ static void dump_packet(const struct nf_loginfo *info, switch (ih->protocol) { case IPPROTO_TCP: { - struct tcphdr _tcph, *th; + struct tcphdr _tcph; + const struct tcphdr *th; /* Max length: 10 "PROTO=TCP " */ printk("PROTO=TCP "); @@ -151,7 +147,7 @@ static void dump_packet(const struct nf_loginfo *info, if ((logflags & IPT_LOG_TCPOPT) && th->doff * 4 > sizeof(struct tcphdr)) { unsigned char _opt[4 * 15 - sizeof(struct tcphdr)]; - unsigned char *op; + const unsigned char *op; unsigned int i, optsize; optsize = th->doff * 4 - sizeof(struct tcphdr); @@ -173,7 +169,8 @@ static void dump_packet(const struct nf_loginfo *info, } case IPPROTO_UDP: case IPPROTO_UDPLITE: { - struct udphdr _udph, *uh; + struct udphdr _udph; + const struct udphdr *uh; if (ih->protocol == IPPROTO_UDP) /* Max length: 10 "PROTO=UDP " */ @@ -200,7 +197,8 @@ static void dump_packet(const struct nf_loginfo *info, break; } case IPPROTO_ICMP: { - struct icmphdr _icmph, *ich; + struct icmphdr _icmph; + const struct icmphdr *ich; static const size_t required_len[NR_ICMP_TYPES+1] = { [ICMP_ECHOREPLY] = 4, [ICMP_DEST_UNREACH] @@ -285,7 +283,8 @@ static void dump_packet(const struct nf_loginfo *info, } /* Max Length */ case IPPROTO_AH: { - struct ip_auth_hdr _ahdr, *ah; + struct ip_auth_hdr _ahdr; + const struct ip_auth_hdr *ah; if (ntohs(ih->frag_off) & IP_OFFSET) break; @@ -307,7 +306,8 @@ static void dump_packet(const struct nf_loginfo *info, break; } case IPPROTO_ESP: { - struct ip_esp_hdr _esph, *eh; + struct ip_esp_hdr _esph; + const struct ip_esp_hdr *eh; /* Max length: 10 "PROTO=ESP " */ printk("PROTO=ESP "); @@ -385,11 +385,13 @@ ipt_log_packet(unsigned int pf, out ? out->name : ""); #ifdef CONFIG_BRIDGE_NETFILTER if (skb->nf_bridge) { - struct net_device *physindev = skb->nf_bridge->physindev; - struct net_device *physoutdev = skb->nf_bridge->physoutdev; + const struct net_device *physindev; + const struct net_device *physoutdev; + physindev = skb->nf_bridge->physindev; if (physindev && in != physindev) printk("PHYSIN=%s ", physindev->name); + physoutdev = skb->nf_bridge->physoutdev; if (physoutdev && out != physoutdev) printk("PHYSOUT=%s ", physoutdev->name); } @@ -435,27 +437,27 @@ ipt_log_target(struct sk_buff **pskb, return XT_CONTINUE; } -static int ipt_log_checkentry(const char *tablename, - const void *e, - const struct xt_target *target, - void *targinfo, - unsigned int hook_mask) +static bool ipt_log_checkentry(const char *tablename, + const void *e, + const struct xt_target *target, + void *targinfo, + unsigned int hook_mask) { const struct ipt_log_info *loginfo = targinfo; if (loginfo->level >= 8) { - DEBUGP("LOG: level %u >= 8\n", loginfo->level); - return 0; + pr_debug("LOG: level %u >= 8\n", loginfo->level); + return false; } if (loginfo->prefix[sizeof(loginfo->prefix)-1] != '\0') { - DEBUGP("LOG: prefix term %i\n", - loginfo->prefix[sizeof(loginfo->prefix)-1]); - return 0; + pr_debug("LOG: prefix term %i\n", + loginfo->prefix[sizeof(loginfo->prefix)-1]); + return false; } - return 1; + return true; } -static struct xt_target ipt_log_reg = { +static struct xt_target ipt_log_reg __read_mostly = { .name = "LOG", .family = AF_INET, .target = ipt_log_target, diff --git a/net/ipv4/netfilter/ipt_MASQUERADE.c b/net/ipv4/netfilter/ipt_MASQUERADE.c index d4f2d7775330..7c4e4be7c8b3 100644 --- a/net/ipv4/netfilter/ipt_MASQUERADE.c +++ b/net/ipv4/netfilter/ipt_MASQUERADE.c @@ -27,17 +27,11 @@ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>"); MODULE_DESCRIPTION("iptables MASQUERADE target module"); -#if 0 -#define DEBUGP printk -#else -#define DEBUGP(format, args...) -#endif - /* Lock protects masq region inside conntrack */ static DEFINE_RWLOCK(masq_lock); /* FIXME: Multiple targets. --RR */ -static int +static bool masquerade_check(const char *tablename, const void *e, const struct xt_target *target, @@ -47,14 +41,14 @@ masquerade_check(const char *tablename, const struct nf_nat_multi_range_compat *mr = targinfo; if (mr->range[0].flags & IP_NAT_RANGE_MAP_IPS) { - DEBUGP("masquerade_check: bad MAP_IPS.\n"); - return 0; + pr_debug("masquerade_check: bad MAP_IPS.\n"); + return false; } if (mr->rangesize != 1) { - DEBUGP("masquerade_check: bad rangesize %u.\n", mr->rangesize); - return 0; + pr_debug("masquerade_check: bad rangesize %u\n", mr->rangesize); + return false; } - return 1; + return true; } static unsigned int @@ -70,7 +64,7 @@ masquerade_target(struct sk_buff **pskb, enum ip_conntrack_info ctinfo; struct nf_nat_range newrange; const struct nf_nat_multi_range_compat *mr; - struct rtable *rt; + const struct rtable *rt; __be32 newsrc; NF_CT_ASSERT(hooknum == NF_IP_POST_ROUTING); @@ -109,10 +103,10 @@ masquerade_target(struct sk_buff **pskb, return nf_nat_setup_info(ct, &newrange, hooknum); } -static inline int +static int device_cmp(struct nf_conn *i, void *ifindex) { - struct nf_conn_nat *nat = nfct_nat(i); + const struct nf_conn_nat *nat = nfct_nat(i); int ret; if (!nat) @@ -129,7 +123,7 @@ static int masq_device_event(struct notifier_block *this, unsigned long event, void *ptr) { - struct net_device *dev = ptr; + const struct net_device *dev = ptr; if (event == NETDEV_DOWN) { /* Device was downed. Search entire table for @@ -147,7 +141,7 @@ static int masq_inet_event(struct notifier_block *this, unsigned long event, void *ptr) { - struct net_device *dev = ((struct in_ifaddr *)ptr)->ifa_dev->dev; + const struct net_device *dev = ((struct in_ifaddr *)ptr)->ifa_dev->dev; if (event == NETDEV_DOWN) { /* IP address was deleted. Search entire table for @@ -169,7 +163,7 @@ static struct notifier_block masq_inet_notifier = { .notifier_call = masq_inet_event, }; -static struct xt_target masquerade = { +static struct xt_target masquerade __read_mostly = { .name = "MASQUERADE", .family = AF_INET, .target = masquerade_target, diff --git a/net/ipv4/netfilter/ipt_NETMAP.c b/net/ipv4/netfilter/ipt_NETMAP.c index 068c69bce30e..41a011d5a065 100644 --- a/net/ipv4/netfilter/ipt_NETMAP.c +++ b/net/ipv4/netfilter/ipt_NETMAP.c @@ -18,18 +18,11 @@ #include <linux/netfilter/x_tables.h> #include <net/netfilter/nf_nat_rule.h> -#define MODULENAME "NETMAP" MODULE_LICENSE("GPL"); MODULE_AUTHOR("Svenning Soerensen <svenning@post5.tele.dk>"); MODULE_DESCRIPTION("iptables 1:1 NAT mapping of IP networks target"); -#if 0 -#define DEBUGP printk -#else -#define DEBUGP(format, args...) -#endif - -static int +static bool check(const char *tablename, const void *e, const struct xt_target *target, @@ -39,14 +32,14 @@ check(const char *tablename, const struct nf_nat_multi_range_compat *mr = targinfo; if (!(mr->range[0].flags & IP_NAT_RANGE_MAP_IPS)) { - DEBUGP(MODULENAME":check: bad MAP_IPS.\n"); - return 0; + pr_debug("NETMAP:check: bad MAP_IPS.\n"); + return false; } if (mr->rangesize != 1) { - DEBUGP(MODULENAME":check: bad rangesize %u.\n", mr->rangesize); - return 0; + pr_debug("NETMAP:check: bad rangesize %u.\n", mr->rangesize); + return false; } - return 1; + return true; } static unsigned int @@ -85,8 +78,8 @@ target(struct sk_buff **pskb, return nf_nat_setup_info(ct, &newrange, hooknum); } -static struct xt_target target_module = { - .name = MODULENAME, +static struct xt_target target_module __read_mostly = { + .name = "NETMAP", .family = AF_INET, .target = target, .targetsize = sizeof(struct nf_nat_multi_range_compat), diff --git a/net/ipv4/netfilter/ipt_REDIRECT.c b/net/ipv4/netfilter/ipt_REDIRECT.c index 68cc76a198eb..6ac7a2373316 100644 --- a/net/ipv4/netfilter/ipt_REDIRECT.c +++ b/net/ipv4/netfilter/ipt_REDIRECT.c @@ -25,14 +25,8 @@ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>"); MODULE_DESCRIPTION("iptables REDIRECT target module"); -#if 0 -#define DEBUGP printk -#else -#define DEBUGP(format, args...) -#endif - /* FIXME: Take multiple ranges --RR */ -static int +static bool redirect_check(const char *tablename, const void *e, const struct xt_target *target, @@ -42,14 +36,14 @@ redirect_check(const char *tablename, const struct nf_nat_multi_range_compat *mr = targinfo; if (mr->range[0].flags & IP_NAT_RANGE_MAP_IPS) { - DEBUGP("redirect_check: bad MAP_IPS.\n"); - return 0; + pr_debug("redirect_check: bad MAP_IPS.\n"); + return false; } if (mr->rangesize != 1) { - DEBUGP("redirect_check: bad rangesize %u.\n", mr->rangesize); - return 0; + pr_debug("redirect_check: bad rangesize %u.\n", mr->rangesize); + return false; } - return 1; + return true; } static unsigned int @@ -101,7 +95,7 @@ redirect_target(struct sk_buff **pskb, return nf_nat_setup_info(ct, &newrange, hooknum); } -static struct xt_target redirect_reg = { +static struct xt_target redirect_reg __read_mostly = { .name = "REDIRECT", .family = AF_INET, .target = redirect_target, diff --git a/net/ipv4/netfilter/ipt_REJECT.c b/net/ipv4/netfilter/ipt_REJECT.c index 9041e0741f6f..cb038c8fbc9d 100644 --- a/net/ipv4/netfilter/ipt_REJECT.c +++ b/net/ipv4/netfilter/ipt_REJECT.c @@ -31,12 +31,6 @@ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>"); MODULE_DESCRIPTION("iptables REJECT target module"); -#if 0 -#define DEBUGP printk -#else -#define DEBUGP(format, args...) -#endif - /* Send RST reply */ static void send_reset(struct sk_buff *oldskb, int hook) { @@ -122,7 +116,7 @@ static void send_reset(struct sk_buff *oldskb, int hook) tcph->check = 0; tcph->check = tcp_v4_check(sizeof(struct tcphdr), niph->saddr, niph->daddr, - csum_partial((char *)tcph, + csum_partial(tcph, sizeof(struct tcphdr), 0)); /* Set DF, id = 0 */ @@ -217,30 +211,30 @@ static unsigned int reject(struct sk_buff **pskb, return NF_DROP; } -static int check(const char *tablename, - const void *e_void, - const struct xt_target *target, - void *targinfo, - unsigned int hook_mask) +static bool check(const char *tablename, + const void *e_void, + const struct xt_target *target, + void *targinfo, + unsigned int hook_mask) { const struct ipt_reject_info *rejinfo = targinfo; const struct ipt_entry *e = e_void; if (rejinfo->with == IPT_ICMP_ECHOREPLY) { - printk("REJECT: ECHOREPLY no longer supported.\n"); - return 0; + printk("ipt_REJECT: ECHOREPLY no longer supported.\n"); + return false; } 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)) { - DEBUGP("REJECT: TCP_RESET invalid for non-tcp\n"); - return 0; + printk("ipt_REJECT: TCP_RESET invalid for non-tcp\n"); + return false; } } - return 1; + return true; } -static struct xt_target ipt_reject_reg = { +static struct xt_target ipt_reject_reg __read_mostly = { .name = "REJECT", .family = AF_INET, .target = reject, diff --git a/net/ipv4/netfilter/ipt_SAME.c b/net/ipv4/netfilter/ipt_SAME.c index 511e5ff84938..97641f1a97f6 100644 --- a/net/ipv4/netfilter/ipt_SAME.c +++ b/net/ipv4/netfilter/ipt_SAME.c @@ -27,13 +27,7 @@ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Martin Josefsson <gandalf@wlug.westbo.se>"); MODULE_DESCRIPTION("iptables special SNAT module for consistent sourceip"); -#if 0 -#define DEBUGP printk -#else -#define DEBUGP(format, args...) -#endif - -static int +static bool same_check(const char *tablename, const void *e, const struct xt_target *target, @@ -46,58 +40,56 @@ same_check(const char *tablename, mr->ipnum = 0; if (mr->rangesize < 1) { - DEBUGP("same_check: need at least one dest range.\n"); - return 0; + pr_debug("same_check: need at least one dest range.\n"); + return false; } if (mr->rangesize > IPT_SAME_MAX_RANGE) { - DEBUGP("same_check: too many ranges specified, maximum " - "is %u ranges\n", - IPT_SAME_MAX_RANGE); - return 0; + pr_debug("same_check: too many ranges specified, maximum " + "is %u ranges\n", IPT_SAME_MAX_RANGE); + return false; } for (count = 0; count < mr->rangesize; count++) { if (ntohl(mr->range[count].min_ip) > ntohl(mr->range[count].max_ip)) { - DEBUGP("same_check: min_ip is larger than max_ip in " - "range `%u.%u.%u.%u-%u.%u.%u.%u'.\n", - NIPQUAD(mr->range[count].min_ip), - NIPQUAD(mr->range[count].max_ip)); - return 0; + pr_debug("same_check: min_ip is larger than max_ip in " + "range `%u.%u.%u.%u-%u.%u.%u.%u'.\n", + NIPQUAD(mr->range[count].min_ip), + NIPQUAD(mr->range[count].max_ip)); + return false; } if (!(mr->range[count].flags & IP_NAT_RANGE_MAP_IPS)) { - DEBUGP("same_check: bad MAP_IPS.\n"); - return 0; + pr_debug("same_check: bad MAP_IPS.\n"); + return false; } rangeip = (ntohl(mr->range[count].max_ip) - ntohl(mr->range[count].min_ip) + 1); mr->ipnum += rangeip; - DEBUGP("same_check: range %u, ipnum = %u\n", count, rangeip); + pr_debug("same_check: range %u, ipnum = %u\n", count, rangeip); } - DEBUGP("same_check: total ipaddresses = %u\n", mr->ipnum); + pr_debug("same_check: total ipaddresses = %u\n", mr->ipnum); mr->iparray = kmalloc((sizeof(u_int32_t) * mr->ipnum), GFP_KERNEL); if (!mr->iparray) { - DEBUGP("same_check: Couldn't allocate %u bytes " - "for %u ipaddresses!\n", - (sizeof(u_int32_t) * mr->ipnum), mr->ipnum); - return 0; + pr_debug("same_check: Couldn't allocate %Zu bytes " + "for %u ipaddresses!\n", + (sizeof(u_int32_t) * mr->ipnum), mr->ipnum); + return false; } - DEBUGP("same_check: Allocated %u bytes for %u ipaddresses.\n", - (sizeof(u_int32_t) * mr->ipnum), mr->ipnum); + pr_debug("same_check: Allocated %Zu bytes for %u ipaddresses.\n", + (sizeof(u_int32_t) * mr->ipnum), mr->ipnum); for (count = 0; count < mr->rangesize; count++) { for (countess = ntohl(mr->range[count].min_ip); countess <= ntohl(mr->range[count].max_ip); countess++) { mr->iparray[index] = countess; - DEBUGP("same_check: Added ipaddress `%u.%u.%u.%u' " - "in index %u.\n", - HIPQUAD(countess), index); + pr_debug("same_check: Added ipaddress `%u.%u.%u.%u' " + "in index %u.\n", HIPQUAD(countess), index); index++; } } - return 1; + return true; } static void @@ -107,8 +99,8 @@ same_destroy(const struct xt_target *target, void *targinfo) kfree(mr->iparray); - DEBUGP("same_destroy: Deallocated %u bytes for %u ipaddresses.\n", - (sizeof(u_int32_t) * mr->ipnum), mr->ipnum); + pr_debug("same_destroy: Deallocated %Zu bytes for %u ipaddresses.\n", + (sizeof(u_int32_t) * mr->ipnum), mr->ipnum); } static unsigned int @@ -146,10 +138,9 @@ same_target(struct sk_buff **pskb, new_ip = htonl(same->iparray[aindex]); - DEBUGP("ipt_SAME: src=%u.%u.%u.%u dst=%u.%u.%u.%u, " - "new src=%u.%u.%u.%u\n", - NIPQUAD(t->src.ip), NIPQUAD(t->dst.ip), - NIPQUAD(new_ip)); + pr_debug("ipt_SAME: src=%u.%u.%u.%u dst=%u.%u.%u.%u, " + "new src=%u.%u.%u.%u\n", + NIPQUAD(t->src.u3.ip), NIPQUAD(t->dst.u3.ip), NIPQUAD(new_ip)); /* Transfer from original range. */ newrange = ((struct nf_nat_range) @@ -161,7 +152,7 @@ same_target(struct sk_buff **pskb, return nf_nat_setup_info(ct, &newrange, hooknum); } -static struct xt_target same_reg = { +static struct xt_target same_reg __read_mostly = { .name = "SAME", .family = AF_INET, .target = same_target, diff --git a/net/ipv4/netfilter/ipt_TOS.c b/net/ipv4/netfilter/ipt_TOS.c index 0ad02f249837..25f5d0b39065 100644 --- a/net/ipv4/netfilter/ipt_TOS.c +++ b/net/ipv4/netfilter/ipt_TOS.c @@ -43,7 +43,7 @@ target(struct sk_buff **pskb, return XT_CONTINUE; } -static int +static bool checkentry(const char *tablename, const void *e_void, const struct xt_target *target, @@ -58,12 +58,12 @@ checkentry(const char *tablename, && tos != IPTOS_MINCOST && tos != IPTOS_NORMALSVC) { printk(KERN_WARNING "TOS: bad tos value %#x\n", tos); - return 0; + return false; } - return 1; + return true; } -static struct xt_target ipt_tos_reg = { +static struct xt_target ipt_tos_reg __read_mostly = { .name = "TOS", .family = AF_INET, .target = target, diff --git a/net/ipv4/netfilter/ipt_TTL.c b/net/ipv4/netfilter/ipt_TTL.c index a991ec7bd4e7..2b54e7b0cfe8 100644 --- a/net/ipv4/netfilter/ipt_TTL.c +++ b/net/ipv4/netfilter/ipt_TTL.c @@ -62,25 +62,25 @@ ipt_ttl_target(struct sk_buff **pskb, return XT_CONTINUE; } -static int ipt_ttl_checkentry(const char *tablename, +static bool ipt_ttl_checkentry(const char *tablename, const void *e, const struct xt_target *target, void *targinfo, unsigned int hook_mask) { - struct ipt_TTL_info *info = targinfo; + const struct ipt_TTL_info *info = targinfo; if (info->mode > IPT_TTL_MAXMODE) { printk(KERN_WARNING "ipt_TTL: invalid or unknown Mode %u\n", info->mode); - return 0; + return false; } - if ((info->mode != IPT_TTL_SET) && (info->ttl == 0)) - return 0; - return 1; + if (info->mode != IPT_TTL_SET && info->ttl == 0) + return false; + return true; } -static struct xt_target ipt_TTL = { +static struct xt_target ipt_TTL __read_mostly = { .name = "TTL", .family = AF_INET, .target = ipt_ttl_target, diff --git a/net/ipv4/netfilter/ipt_ULOG.c b/net/ipv4/netfilter/ipt_ULOG.c index 23b607b33b32..6ca43e4ca7e3 100644 --- a/net/ipv4/netfilter/ipt_ULOG.c +++ b/net/ipv4/netfilter/ipt_ULOG.c @@ -55,13 +55,6 @@ 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 */ -#if 0 -#define DEBUGP(format, args...) printk("%s:%s:" format, \ - __FILE__, __FUNCTION__ , ## args) -#else -#define DEBUGP(format, args...) -#endif - #define PRINTR(format, args...) do { if (net_ratelimit()) printk(format , ## args); } while (0) static unsigned int nlbufsiz = NLMSG_GOODSIZE; @@ -96,12 +89,12 @@ static void ulog_send(unsigned int nlgroupnum) ulog_buff_t *ub = &ulog_buffers[nlgroupnum]; if (timer_pending(&ub->timer)) { - DEBUGP("ipt_ULOG: ulog_send: timer was pending, deleting\n"); + pr_debug("ipt_ULOG: ulog_send: timer was pending, deleting\n"); del_timer(&ub->timer); } if (!ub->skb) { - DEBUGP("ipt_ULOG: ulog_send: nothing to send\n"); + pr_debug("ipt_ULOG: ulog_send: nothing to send\n"); return; } @@ -110,8 +103,8 @@ static void ulog_send(unsigned int nlgroupnum) ub->lastnlh->nlmsg_type = NLMSG_DONE; NETLINK_CB(ub->skb).dst_group = nlgroupnum + 1; - DEBUGP("ipt_ULOG: throwing %d packets to netlink group %u\n", - ub->qlen, nlgroupnum + 1); + pr_debug("ipt_ULOG: throwing %d packets to netlink group %u\n", + ub->qlen, nlgroupnum + 1); netlink_broadcast(nflognl, ub->skb, 0, nlgroupnum + 1, GFP_ATOMIC); ub->qlen = 0; @@ -123,7 +116,7 @@ static void ulog_send(unsigned int nlgroupnum) /* timer function to flush queue in flushtimeout time */ static void ulog_timer(unsigned long data) { - DEBUGP("ipt_ULOG: timer function called, calling ulog_send\n"); + pr_debug("ipt_ULOG: timer function called, calling ulog_send\n"); /* lock to protect against somebody modifying our structure * from ipt_ulog_target at the same time */ @@ -179,12 +172,10 @@ static void ipt_ulog_packet(unsigned int hooknum, unsigned int groupnum = ffs(loginfo->nl_group) - 1; /* calculate the size of the skb needed */ - if ((loginfo->copy_range == 0) || - (loginfo->copy_range > skb->len)) { + if (loginfo->copy_range == 0 || loginfo->copy_range > skb->len) copy_len = skb->len; - } else { + else copy_len = loginfo->copy_range; - } size = NLMSG_SPACE(sizeof(*pm) + copy_len); @@ -206,8 +197,8 @@ static void ipt_ulog_packet(unsigned int hooknum, goto alloc_failure; } - DEBUGP("ipt_ULOG: qlen %d, qthreshold %d\n", ub->qlen, - loginfo->qthreshold); + pr_debug("ipt_ULOG: 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, @@ -257,9 +248,8 @@ static void ipt_ulog_packet(unsigned int hooknum, BUG(); /* check if we are building multi-part messages */ - if (ub->qlen > 1) { + if (ub->qlen > 1) ub->lastnlh->nlmsg_flags |= NLM_F_MULTI; - } ub->lastnlh = nlh; @@ -328,25 +318,25 @@ static void ipt_logfn(unsigned int pf, ipt_ulog_packet(hooknum, skb, in, out, &loginfo, prefix); } -static int ipt_ulog_checkentry(const char *tablename, - const void *e, - const struct xt_target *target, - void *targinfo, - unsigned int hookmask) +static bool ipt_ulog_checkentry(const char *tablename, + const void *e, + const struct xt_target *target, + void *targinfo, + unsigned int hookmask) { - struct ipt_ulog_info *loginfo = (struct ipt_ulog_info *) targinfo; + const struct ipt_ulog_info *loginfo = targinfo; if (loginfo->prefix[sizeof(loginfo->prefix) - 1] != '\0') { - DEBUGP("ipt_ULOG: prefix term %i\n", - loginfo->prefix[sizeof(loginfo->prefix) - 1]); - return 0; + pr_debug("ipt_ULOG: prefix term %i\n", + loginfo->prefix[sizeof(loginfo->prefix) - 1]); + return false; } if (loginfo->qthreshold > ULOG_MAX_QLEN) { - DEBUGP("ipt_ULOG: queue threshold %i > MAX_QLEN\n", - loginfo->qthreshold); - return 0; + pr_debug("ipt_ULOG: queue threshold %Zu > MAX_QLEN\n", + loginfo->qthreshold); + return false; } - return 1; + return true; } #ifdef CONFIG_COMPAT @@ -359,7 +349,7 @@ struct compat_ipt_ulog_info { static void compat_from_user(void *dst, void *src) { - struct compat_ipt_ulog_info *cl = src; + const struct compat_ipt_ulog_info *cl = src; struct ipt_ulog_info l = { .nl_group = cl->nl_group, .copy_range = cl->copy_range, @@ -372,7 +362,7 @@ static void compat_from_user(void *dst, void *src) static int compat_to_user(void __user *dst, void *src) { - struct ipt_ulog_info *l = src; + const struct ipt_ulog_info *l = src; struct compat_ipt_ulog_info cl = { .nl_group = l->nl_group, .copy_range = l->copy_range, @@ -384,7 +374,7 @@ static int compat_to_user(void __user *dst, void *src) } #endif /* CONFIG_COMPAT */ -static struct xt_target ipt_ulog_reg = { +static struct xt_target ipt_ulog_reg __read_mostly = { .name = "ULOG", .family = AF_INET, .target = ipt_ulog_target, @@ -408,7 +398,7 @@ static int __init ipt_ulog_init(void) { int ret, i; - DEBUGP("ipt_ULOG: init module\n"); + pr_debug("ipt_ULOG: init module\n"); if (nlbufsiz > 128*1024) { printk("Netlink buffer has to be <= 128kB\n"); @@ -440,7 +430,7 @@ static void __exit ipt_ulog_fini(void) ulog_buff_t *ub; int i; - DEBUGP("ipt_ULOG: cleanup_module\n"); + pr_debug("ipt_ULOG: cleanup_module\n"); if (nflog) nf_log_unregister(&ipt_ulog_logger); @@ -451,7 +441,7 @@ static void __exit ipt_ulog_fini(void) for (i = 0; i < ULOG_MAXNLGROUPS; i++) { ub = &ulog_buffers[i]; if (timer_pending(&ub->timer)) { - DEBUGP("timer was pending, deleting\n"); + pr_debug("timer was pending, deleting\n"); del_timer(&ub->timer); } diff --git a/net/ipv4/netfilter/ipt_addrtype.c b/net/ipv4/netfilter/ipt_addrtype.c index a652a1451552..59f01f7ba6b4 100644 --- a/net/ipv4/netfilter/ipt_addrtype.c +++ b/net/ipv4/netfilter/ipt_addrtype.c @@ -22,19 +22,19 @@ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); MODULE_DESCRIPTION("iptables addrtype match"); -static inline int match_type(__be32 addr, u_int16_t mask) +static inline bool match_type(__be32 addr, u_int16_t mask) { return !!(mask & (1 << inet_addr_type(addr))); } -static int match(const struct sk_buff *skb, - const struct net_device *in, const struct net_device *out, - const struct xt_match *match, const void *matchinfo, - int offset, unsigned int protoff, int *hotdrop) +static bool match(const struct sk_buff *skb, + const struct net_device *in, const struct net_device *out, + const struct xt_match *match, const void *matchinfo, + int offset, unsigned int protoff, bool *hotdrop) { const struct ipt_addrtype_info *info = matchinfo; const struct iphdr *iph = ip_hdr(skb); - int ret = 1; + bool ret = true; if (info->source) ret &= match_type(iph->saddr, info->source)^info->invert_source; @@ -44,7 +44,7 @@ static int match(const struct sk_buff *skb, return ret; } -static struct xt_match addrtype_match = { +static struct xt_match addrtype_match __read_mostly = { .name = "addrtype", .family = AF_INET, .match = match, diff --git a/net/ipv4/netfilter/ipt_ah.c b/net/ipv4/netfilter/ipt_ah.c index 18a16782cf40..61b017fd743c 100644 --- a/net/ipv4/netfilter/ipt_ah.c +++ b/net/ipv4/netfilter/ipt_ah.c @@ -25,10 +25,10 @@ MODULE_DESCRIPTION("iptables AH SPI match module"); #endif /* Returns 1 if the spi is matched by the range, 0 otherwise */ -static inline int -spi_match(u_int32_t min, u_int32_t max, u_int32_t spi, int invert) +static inline bool +spi_match(u_int32_t min, u_int32_t max, u_int32_t spi, bool invert) { - int r=0; + bool r; duprintf("ah spi_match:%c 0x%x <= 0x%x <= 0x%x",invert? '!':' ', min,spi,max); r=(spi >= min && spi <= max) ^ invert; @@ -36,7 +36,7 @@ spi_match(u_int32_t min, u_int32_t max, u_int32_t spi, int invert) return r; } -static int +static bool match(const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, @@ -44,14 +44,15 @@ match(const struct sk_buff *skb, const void *matchinfo, int offset, unsigned int protoff, - int *hotdrop) + bool *hotdrop) { - struct ip_auth_hdr _ahdr, *ah; + struct ip_auth_hdr _ahdr; + const struct ip_auth_hdr *ah; const struct ipt_ah *ahinfo = matchinfo; /* Must not be a fragment. */ if (offset) - return 0; + return false; ah = skb_header_pointer(skb, protoff, sizeof(_ahdr), &_ahdr); @@ -60,7 +61,7 @@ match(const struct sk_buff *skb, * can't. Hence, no choice but to drop. */ duprintf("Dropping evil AH tinygram.\n"); - *hotdrop = 1; + *hotdrop = true; return 0; } @@ -70,7 +71,7 @@ match(const struct sk_buff *skb, } /* Called when user tries to insert an entry of this type. */ -static int +static bool checkentry(const char *tablename, const void *ip_void, const struct xt_match *match, @@ -82,12 +83,12 @@ checkentry(const char *tablename, /* Must specify no unknown invflags */ if (ahinfo->invflags & ~IPT_AH_INV_MASK) { duprintf("ipt_ah: unknown flags %X\n", ahinfo->invflags); - return 0; + return false; } - return 1; + return true; } -static struct xt_match ah_match = { +static struct xt_match ah_match __read_mostly = { .name = "ah", .family = AF_INET, .match = match, diff --git a/net/ipv4/netfilter/ipt_ecn.c b/net/ipv4/netfilter/ipt_ecn.c index 26218122f865..d6925c674069 100644 --- a/net/ipv4/netfilter/ipt_ecn.c +++ b/net/ipv4/netfilter/ipt_ecn.c @@ -22,95 +22,96 @@ MODULE_AUTHOR("Harald Welte <laforge@netfilter.org>"); MODULE_DESCRIPTION("iptables ECN matching module"); MODULE_LICENSE("GPL"); -static inline int match_ip(const struct sk_buff *skb, - const struct ipt_ecn_info *einfo) +static inline bool match_ip(const struct sk_buff *skb, + const struct ipt_ecn_info *einfo) { return (ip_hdr(skb)->tos & IPT_ECN_IP_MASK) == einfo->ip_ect; } -static inline int match_tcp(const struct sk_buff *skb, - const struct ipt_ecn_info *einfo, - int *hotdrop) +static inline bool match_tcp(const struct sk_buff *skb, + const struct ipt_ecn_info *einfo, + bool *hotdrop) { - struct tcphdr _tcph, *th; + struct tcphdr _tcph; + const struct tcphdr *th; /* In practice, TCP match does this, so can't fail. But let's * be good citizens. */ th = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(_tcph), &_tcph); if (th == NULL) { - *hotdrop = 0; - return 0; + *hotdrop = false; + return false; } if (einfo->operation & IPT_ECN_OP_MATCH_ECE) { if (einfo->invert & IPT_ECN_OP_MATCH_ECE) { if (th->ece == 1) - return 0; + return false; } else { if (th->ece == 0) - return 0; + return false; } } if (einfo->operation & IPT_ECN_OP_MATCH_CWR) { if (einfo->invert & IPT_ECN_OP_MATCH_CWR) { if (th->cwr == 1) - return 0; + return false; } else { if (th->cwr == 0) - return 0; + return false; } } - return 1; + return true; } -static int match(const struct sk_buff *skb, - const struct net_device *in, const struct net_device *out, - const struct xt_match *match, const void *matchinfo, - int offset, unsigned int protoff, int *hotdrop) +static bool match(const struct sk_buff *skb, + const struct net_device *in, const struct net_device *out, + const struct xt_match *match, const void *matchinfo, + int offset, unsigned int protoff, bool *hotdrop) { const struct ipt_ecn_info *info = matchinfo; if (info->operation & IPT_ECN_OP_MATCH_IP) if (!match_ip(skb, info)) - return 0; + return false; if (info->operation & (IPT_ECN_OP_MATCH_ECE|IPT_ECN_OP_MATCH_CWR)) { if (ip_hdr(skb)->protocol != IPPROTO_TCP) - return 0; + return false; if (!match_tcp(skb, info, hotdrop)) - return 0; + return false; } - return 1; + return true; } -static int checkentry(const char *tablename, const void *ip_void, - const struct xt_match *match, - void *matchinfo, unsigned int hook_mask) +static bool checkentry(const char *tablename, const void *ip_void, + const struct xt_match *match, + void *matchinfo, unsigned int hook_mask) { const struct ipt_ecn_info *info = matchinfo; const struct ipt_ip *ip = ip_void; if (info->operation & IPT_ECN_OP_MATCH_MASK) - return 0; + return false; if (info->invert & IPT_ECN_OP_MATCH_MASK) - return 0; + return false; 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 0; + return false; } - return 1; + return true; } -static struct xt_match ecn_match = { +static struct xt_match ecn_match __read_mostly = { .name = "ecn", .family = AF_INET, .match = match, diff --git a/net/ipv4/netfilter/ipt_iprange.c b/net/ipv4/netfilter/ipt_iprange.c index 33af9e940887..0106dc955a69 100644 --- a/net/ipv4/netfilter/ipt_iprange.c +++ b/net/ipv4/netfilter/ipt_iprange.c @@ -17,53 +17,47 @@ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>"); MODULE_DESCRIPTION("iptables arbitrary IP range match module"); -#if 0 -#define DEBUGP printk -#else -#define DEBUGP(format, args...) -#endif - -static int +static bool match(const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, const struct xt_match *match, const void *matchinfo, - int offset, unsigned int protoff, int *hotdrop) + int offset, unsigned int protoff, bool *hotdrop) { const struct ipt_iprange_info *info = matchinfo; const struct iphdr *iph = ip_hdr(skb); if (info->flags & IPRANGE_SRC) { - if (((ntohl(iph->saddr) < ntohl(info->src.min_ip)) - || (ntohl(iph->saddr) > ntohl(info->src.max_ip))) + if ((ntohl(iph->saddr) < ntohl(info->src.min_ip) + || ntohl(iph->saddr) > ntohl(info->src.max_ip)) ^ !!(info->flags & IPRANGE_SRC_INV)) { - DEBUGP("src IP %u.%u.%u.%u NOT in range %s" - "%u.%u.%u.%u-%u.%u.%u.%u\n", - NIPQUAD(iph->saddr), - info->flags & IPRANGE_SRC_INV ? "(INV) " : "", - NIPQUAD(info->src.min_ip), - NIPQUAD(info->src.max_ip)); - return 0; + pr_debug("src IP %u.%u.%u.%u NOT in range %s" + "%u.%u.%u.%u-%u.%u.%u.%u\n", + NIPQUAD(iph->saddr), + info->flags & IPRANGE_SRC_INV ? "(INV) " : "", + NIPQUAD(info->src.min_ip), + NIPQUAD(info->src.max_ip)); + return false; } } if (info->flags & IPRANGE_DST) { - if (((ntohl(iph->daddr) < ntohl(info->dst.min_ip)) - || (ntohl(iph->daddr) > ntohl(info->dst.max_ip))) + if ((ntohl(iph->daddr) < ntohl(info->dst.min_ip) + || ntohl(iph->daddr) > ntohl(info->dst.max_ip)) ^ !!(info->flags & IPRANGE_DST_INV)) { - DEBUGP("dst IP %u.%u.%u.%u NOT in range %s" - "%u.%u.%u.%u-%u.%u.%u.%u\n", - NIPQUAD(iph->daddr), - info->flags & IPRANGE_DST_INV ? "(INV) " : "", - NIPQUAD(info->dst.min_ip), - NIPQUAD(info->dst.max_ip)); - return 0; + pr_debug("dst IP %u.%u.%u.%u NOT in range %s" + "%u.%u.%u.%u-%u.%u.%u.%u\n", + NIPQUAD(iph->daddr), + info->flags & IPRANGE_DST_INV ? "(INV) " : "", + NIPQUAD(info->dst.min_ip), + NIPQUAD(info->dst.max_ip)); + return false; } } - return 1; + return true; } -static struct xt_match iprange_match = { +static struct xt_match iprange_match __read_mostly = { .name = "iprange", .family = AF_INET, .match = match, diff --git a/net/ipv4/netfilter/ipt_owner.c b/net/ipv4/netfilter/ipt_owner.c index 7fae9aa8944c..b14e77da7a33 100644 --- a/net/ipv4/netfilter/ipt_owner.c +++ b/net/ipv4/netfilter/ipt_owner.c @@ -21,7 +21,7 @@ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Marc Boucher <marc@mbsi.ca>"); MODULE_DESCRIPTION("iptables owner match"); -static int +static bool match(const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, @@ -29,29 +29,29 @@ match(const struct sk_buff *skb, const void *matchinfo, int offset, unsigned int protoff, - int *hotdrop) + bool *hotdrop) { const struct ipt_owner_info *info = matchinfo; if (!skb->sk || !skb->sk->sk_socket || !skb->sk->sk_socket->file) - return 0; + return false; if(info->match & IPT_OWNER_UID) { if ((skb->sk->sk_socket->file->f_uid != info->uid) ^ !!(info->invert & IPT_OWNER_UID)) - return 0; + return false; } if(info->match & IPT_OWNER_GID) { if ((skb->sk->sk_socket->file->f_gid != info->gid) ^ !!(info->invert & IPT_OWNER_GID)) - return 0; + return false; } - return 1; + return true; } -static int +static bool checkentry(const char *tablename, const void *ip, const struct xt_match *match, @@ -63,12 +63,12 @@ checkentry(const char *tablename, if (info->match & (IPT_OWNER_PID|IPT_OWNER_SID|IPT_OWNER_COMM)) { printk("ipt_owner: pid, sid and command matching " "not supported anymore\n"); - return 0; + return false; } - return 1; + return true; } -static struct xt_match owner_match = { +static struct xt_match owner_match __read_mostly = { .name = "owner", .family = AF_INET, .match = match, diff --git a/net/ipv4/netfilter/ipt_recent.c b/net/ipv4/netfilter/ipt_recent.c index 15a9e8bbb7cc..321804315659 100644 --- a/net/ipv4/netfilter/ipt_recent.c +++ b/net/ipv4/netfilter/ipt_recent.c @@ -163,24 +163,23 @@ static void recent_table_flush(struct recent_table *t) struct recent_entry *e, *next; unsigned int i; - for (i = 0; i < ip_list_hash_size; i++) { + for (i = 0; i < ip_list_hash_size; i++) list_for_each_entry_safe(e, next, &t->iphash[i], list) recent_entry_remove(t, e); - } } -static int +static bool ipt_recent_match(const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, const struct xt_match *match, const void *matchinfo, - int offset, unsigned int protoff, int *hotdrop) + int offset, unsigned int protoff, bool *hotdrop) { const struct ipt_recent_info *info = matchinfo; struct recent_table *t; struct recent_entry *e; __be32 addr; u_int8_t ttl; - int ret = info->invert; + bool ret = info->invert; if (info->side == IPT_RECENT_DEST) addr = ip_hdr(skb)->daddr; @@ -201,16 +200,16 @@ ipt_recent_match(const struct sk_buff *skb, goto out; e = recent_entry_init(t, addr, ttl); if (e == NULL) - *hotdrop = 1; - ret ^= 1; + *hotdrop = true; + ret = !ret; goto out; } if (info->check_set & IPT_RECENT_SET) - ret ^= 1; + ret = !ret; else if (info->check_set & IPT_RECENT_REMOVE) { recent_entry_remove(t, e); - ret ^= 1; + ret = !ret; } else if (info->check_set & (IPT_RECENT_CHECK | IPT_RECENT_UPDATE)) { unsigned long t = jiffies - info->seconds * HZ; unsigned int i, hits = 0; @@ -219,7 +218,7 @@ ipt_recent_match(const struct sk_buff *skb, if (info->seconds && time_after(t, e->stamps[i])) continue; if (++hits >= info->hit_count) { - ret ^= 1; + ret = !ret; break; } } @@ -235,7 +234,7 @@ out: return ret; } -static int +static bool ipt_recent_checkentry(const char *tablename, const void *ip, const struct xt_match *match, void *matchinfo, unsigned int hook_mask) @@ -243,24 +242,24 @@ ipt_recent_checkentry(const char *tablename, const void *ip, const struct ipt_recent_info *info = matchinfo; struct recent_table *t; unsigned i; - int ret = 0; + bool ret = false; if (hweight8(info->check_set & (IPT_RECENT_SET | IPT_RECENT_REMOVE | IPT_RECENT_CHECK | IPT_RECENT_UPDATE)) != 1) - return 0; + return false; if ((info->check_set & (IPT_RECENT_SET | IPT_RECENT_REMOVE)) && (info->seconds || info->hit_count)) - return 0; + return false; if (info->name[0] == '\0' || strnlen(info->name, IPT_RECENT_NAME_LEN) == IPT_RECENT_NAME_LEN) - return 0; + return false; mutex_lock(&recent_mutex); t = recent_table_lookup(info->name); if (t != NULL) { t->refcnt++; - ret = 1; + ret = true; goto out; } @@ -287,7 +286,7 @@ ipt_recent_checkentry(const char *tablename, const void *ip, spin_lock_bh(&recent_lock); list_add_tail(&t->list, &tables); spin_unlock_bh(&recent_lock); - ret = 1; + ret = true; out: mutex_unlock(&recent_mutex); return ret; @@ -323,18 +322,16 @@ struct recent_iter_state { static void *recent_seq_start(struct seq_file *seq, loff_t *pos) { struct recent_iter_state *st = seq->private; - struct recent_table *t = st->table; + const struct recent_table *t = st->table; struct recent_entry *e; loff_t p = *pos; spin_lock_bh(&recent_lock); - for (st->bucket = 0; st->bucket < ip_list_hash_size; st->bucket++) { - list_for_each_entry(e, &t->iphash[st->bucket], list) { + for (st->bucket = 0; st->bucket < ip_list_hash_size; st->bucket++) + list_for_each_entry(e, &t->iphash[st->bucket], list) if (p-- == 0) return e; - } - } return NULL; } @@ -373,7 +370,7 @@ static int recent_seq_show(struct seq_file *seq, void *v) return 0; } -static struct seq_operations recent_seq_ops = { +static const struct seq_operations recent_seq_ops = { .start = recent_seq_start, .next = recent_seq_next, .stop = recent_seq_stop, @@ -463,7 +460,7 @@ static const struct file_operations recent_fops = { }; #endif /* CONFIG_PROC_FS */ -static struct xt_match recent_match = { +static struct xt_match recent_match __read_mostly = { .name = "recent", .family = AF_INET, .match = ipt_recent_match, diff --git a/net/ipv4/netfilter/ipt_tos.c b/net/ipv4/netfilter/ipt_tos.c index d314844af12b..e740441c973d 100644 --- a/net/ipv4/netfilter/ipt_tos.c +++ b/net/ipv4/netfilter/ipt_tos.c @@ -18,7 +18,7 @@ MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("iptables TOS match module"); -static int +static bool match(const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, @@ -26,14 +26,14 @@ match(const struct sk_buff *skb, const void *matchinfo, int offset, unsigned int protoff, - int *hotdrop) + bool *hotdrop) { const struct ipt_tos_info *info = matchinfo; return (ip_hdr(skb)->tos == info->tos) ^ info->invert; } -static struct xt_match tos_match = { +static struct xt_match tos_match __read_mostly = { .name = "tos", .family = AF_INET, .match = match, diff --git a/net/ipv4/netfilter/ipt_ttl.c b/net/ipv4/netfilter/ipt_ttl.c index ab02d9e3139c..a439900a4ba5 100644 --- a/net/ipv4/netfilter/ipt_ttl.c +++ b/net/ipv4/netfilter/ipt_ttl.c @@ -18,37 +18,33 @@ MODULE_AUTHOR("Harald Welte <laforge@netfilter.org>"); MODULE_DESCRIPTION("IP tables TTL matching module"); MODULE_LICENSE("GPL"); -static int match(const struct sk_buff *skb, - const struct net_device *in, const struct net_device *out, - const struct xt_match *match, const void *matchinfo, - int offset, unsigned int protoff, int *hotdrop) +static bool match(const struct sk_buff *skb, + const struct net_device *in, const struct net_device *out, + const struct xt_match *match, const void *matchinfo, + int offset, unsigned int protoff, bool *hotdrop) { const struct ipt_ttl_info *info = matchinfo; const u8 ttl = ip_hdr(skb)->ttl; switch (info->mode) { case IPT_TTL_EQ: - return (ttl == info->ttl); - break; + return ttl == info->ttl; case IPT_TTL_NE: - return (!(ttl == info->ttl)); - break; + return ttl != info->ttl; case IPT_TTL_LT: - return (ttl < info->ttl); - break; + return ttl < info->ttl; case IPT_TTL_GT: - return (ttl > info->ttl); - break; + return ttl > info->ttl; default: printk(KERN_WARNING "ipt_ttl: unknown mode %d\n", info->mode); - return 0; + return false; } - return 0; + return false; } -static struct xt_match ttl_match = { +static struct xt_match ttl_match __read_mostly = { .name = "ttl", .family = AF_INET, .match = match, diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c index 6dc72a815f77..64552afd01cb 100644 --- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c +++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c @@ -24,12 +24,6 @@ #include <net/netfilter/nf_conntrack_core.h> #include <net/netfilter/ipv4/nf_conntrack_ipv4.h> -#if 0 -#define DEBUGP printk -#else -#define DEBUGP(format, args...) -#endif - static int ipv4_pkt_to_tuple(const struct sk_buff *skb, unsigned int nhoff, struct nf_conntrack_tuple *tuple) { @@ -84,36 +78,30 @@ nf_ct_ipv4_gather_frags(struct sk_buff *skb, u_int32_t user) return skb; } -static int -ipv4_prepare(struct sk_buff **pskb, unsigned int hooknum, unsigned int *dataoff, - u_int8_t *protonum) +static int ipv4_get_l4proto(const struct sk_buff *skb, unsigned int nhoff, + unsigned int *dataoff, u_int8_t *protonum) { + struct iphdr _iph, *iph; + + iph = skb_header_pointer(skb, nhoff, sizeof(_iph), &_iph); + if (iph == NULL) + return -NF_DROP; + /* Never happen */ - if (ip_hdr(*pskb)->frag_off & htons(IP_OFFSET)) { + if (iph->frag_off & htons(IP_OFFSET)) { if (net_ratelimit()) { - printk(KERN_ERR "ipv4_prepare: Frag of proto %u (hook=%u)\n", - ip_hdr(*pskb)->protocol, hooknum); + printk(KERN_ERR "ipv4_get_l4proto: Frag of proto %u\n", + iph->protocol); } return -NF_DROP; } - *dataoff = skb_network_offset(*pskb) + ip_hdrlen(*pskb); - *protonum = ip_hdr(*pskb)->protocol; + *dataoff = nhoff + (iph->ihl << 2); + *protonum = iph->protocol; return NF_ACCEPT; } -int nf_nat_module_is_loaded = 0; -EXPORT_SYMBOL_GPL(nf_nat_module_is_loaded); - -static u_int32_t ipv4_get_features(const struct nf_conntrack_tuple *tuple) -{ - if (nf_nat_module_is_loaded) - return NF_CT_F_NAT; - - return NF_CT_F_BASIC; -} - static unsigned int ipv4_confirm(unsigned int hooknum, struct sk_buff **pskb, const struct net_device *in, @@ -335,17 +323,17 @@ getorigdst(struct sock *sk, int optval, void __user *user, int *len) /* We only do TCP at the moment: is there a better way? */ if (strcmp(sk->sk_prot->name, "TCP")) { - DEBUGP("SO_ORIGINAL_DST: Not a TCP socket\n"); + pr_debug("SO_ORIGINAL_DST: Not a TCP socket\n"); return -ENOPROTOOPT; } if ((unsigned int) *len < sizeof(struct sockaddr_in)) { - DEBUGP("SO_ORIGINAL_DST: len %u not %u\n", - *len, sizeof(struct sockaddr_in)); + pr_debug("SO_ORIGINAL_DST: len %d not %Zu\n", + *len, sizeof(struct sockaddr_in)); return -EINVAL; } - h = nf_conntrack_find_get(&tuple, NULL); + h = nf_conntrack_find_get(&tuple); if (h) { struct sockaddr_in sin; struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(h); @@ -357,17 +345,17 @@ getorigdst(struct sock *sk, int optval, void __user *user, int *len) .tuple.dst.u3.ip; memset(sin.sin_zero, 0, sizeof(sin.sin_zero)); - DEBUGP("SO_ORIGINAL_DST: %u.%u.%u.%u %u\n", - NIPQUAD(sin.sin_addr.s_addr), ntohs(sin.sin_port)); + pr_debug("SO_ORIGINAL_DST: %u.%u.%u.%u %u\n", + NIPQUAD(sin.sin_addr.s_addr), ntohs(sin.sin_port)); nf_ct_put(ct); if (copy_to_user(user, &sin, sizeof(sin)) != 0) return -EFAULT; else return 0; } - DEBUGP("SO_ORIGINAL_DST: Can't find %u.%u.%u.%u/%u-%u.%u.%u.%u/%u.\n", - NIPQUAD(tuple.src.u3.ip), ntohs(tuple.src.u.tcp.port), - NIPQUAD(tuple.dst.u3.ip), ntohs(tuple.dst.u.tcp.port)); + pr_debug("SO_ORIGINAL_DST: Can't find %u.%u.%u.%u/%u-%u.%u.%u.%u/%u.\n", + NIPQUAD(tuple.src.u3.ip), ntohs(tuple.src.u.tcp.port), + NIPQUAD(tuple.dst.u3.ip), ntohs(tuple.dst.u.tcp.port)); return -ENOENT; } @@ -417,15 +405,14 @@ static struct nf_sockopt_ops so_getorigdst = { .get = &getorigdst, }; -struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv4 = { +struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv4 __read_mostly = { .l3proto = PF_INET, .name = "ipv4", .pkt_to_tuple = ipv4_pkt_to_tuple, .invert_tuple = ipv4_invert_tuple, .print_tuple = ipv4_print_tuple, .print_conntrack = ipv4_print_conntrack, - .prepare = ipv4_prepare, - .get_features = ipv4_get_features, + .get_l4proto = ipv4_get_l4proto, #if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) .tuple_to_nfattr = ipv4_tuple_to_nfattr, .nfattr_to_tuple = ipv4_nfattr_to_tuple, diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c index 89f933e81035..27c7918e442a 100644 --- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c +++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c @@ -18,12 +18,6 @@ #include <net/netfilter/nf_conntrack_l4proto.h> #include <net/netfilter/nf_conntrack_expect.h> -#if 0 -#define DEBUGP printk -#else -#define DEBUGP(format, args...) -#endif - #ifdef CONFIG_NF_CT_ACCT static unsigned int seq_print_counters(struct seq_file *s, @@ -41,35 +35,36 @@ struct ct_iter_state { unsigned int bucket; }; -static struct list_head *ct_get_first(struct seq_file *seq) +static struct hlist_node *ct_get_first(struct seq_file *seq) { struct ct_iter_state *st = seq->private; for (st->bucket = 0; st->bucket < nf_conntrack_htable_size; st->bucket++) { - if (!list_empty(&nf_conntrack_hash[st->bucket])) - return nf_conntrack_hash[st->bucket].next; + if (!hlist_empty(&nf_conntrack_hash[st->bucket])) + return nf_conntrack_hash[st->bucket].first; } return NULL; } -static struct list_head *ct_get_next(struct seq_file *seq, struct list_head *head) +static struct hlist_node *ct_get_next(struct seq_file *seq, + struct hlist_node *head) { struct ct_iter_state *st = seq->private; head = head->next; - while (head == &nf_conntrack_hash[st->bucket]) { + while (head == NULL) { if (++st->bucket >= nf_conntrack_htable_size) return NULL; - head = nf_conntrack_hash[st->bucket].next; + head = nf_conntrack_hash[st->bucket].first; } return head; } -static struct list_head *ct_get_idx(struct seq_file *seq, loff_t pos) +static struct hlist_node *ct_get_idx(struct seq_file *seq, loff_t pos) { - struct list_head *head = ct_get_first(seq); + struct hlist_node *head = ct_get_first(seq); if (head) while (pos && (head = ct_get_next(seq, head))) @@ -169,7 +164,7 @@ static int ct_seq_show(struct seq_file *s, void *v) return 0; } -static struct seq_operations ct_seq_ops = { +static const struct seq_operations ct_seq_ops = { .start = ct_seq_start, .next = ct_seq_next, .stop = ct_seq_stop, @@ -182,7 +177,7 @@ static int ct_open(struct inode *inode, struct file *file) struct ct_iter_state *st; int ret; - st = kmalloc(sizeof(struct ct_iter_state), GFP_KERNEL); + st = kzalloc(sizeof(struct ct_iter_state), GFP_KERNEL); if (st == NULL) return -ENOMEM; ret = seq_open(file, &ct_seq_ops); @@ -190,7 +185,6 @@ static int ct_open(struct inode *inode, struct file *file) goto out_free; seq = file->private_data; seq->private = st; - memset(st, 0, sizeof(struct ct_iter_state)); return ret; out_free: kfree(st); @@ -206,47 +200,68 @@ static const struct file_operations ct_file_ops = { }; /* expects */ -static void *exp_seq_start(struct seq_file *s, loff_t *pos) +struct ct_expect_iter_state { + unsigned int bucket; +}; + +static struct hlist_node *ct_expect_get_first(struct seq_file *seq) { - struct list_head *e = &nf_conntrack_expect_list; - loff_t i; + struct ct_expect_iter_state *st = seq->private; - /* strange seq_file api calls stop even if we fail, - * thus we need to grab lock since stop unlocks */ - read_lock_bh(&nf_conntrack_lock); + for (st->bucket = 0; st->bucket < nf_ct_expect_hsize; st->bucket++) { + if (!hlist_empty(&nf_ct_expect_hash[st->bucket])) + return nf_ct_expect_hash[st->bucket].first; + } + return NULL; +} - if (list_empty(e)) - return NULL; +static struct hlist_node *ct_expect_get_next(struct seq_file *seq, + struct hlist_node *head) +{ + struct ct_expect_iter_state *st = seq->private; - for (i = 0; i <= *pos; i++) { - e = e->next; - if (e == &nf_conntrack_expect_list) + head = head->next; + while (head == NULL) { + if (++st->bucket >= nf_ct_expect_hsize) return NULL; + head = nf_ct_expect_hash[st->bucket].first; } - return e; + return head; } -static void *exp_seq_next(struct seq_file *s, void *v, loff_t *pos) +static struct hlist_node *ct_expect_get_idx(struct seq_file *seq, loff_t pos) { - struct list_head *e = v; + struct hlist_node *head = ct_expect_get_first(seq); - ++*pos; - e = e->next; + if (head) + while (pos && (head = ct_expect_get_next(seq, head))) + pos--; + return pos ? NULL : head; +} - if (e == &nf_conntrack_expect_list) - return NULL; +static void *exp_seq_start(struct seq_file *seq, loff_t *pos) +{ + read_lock_bh(&nf_conntrack_lock); + return ct_expect_get_idx(seq, *pos); +} - return e; +static void *exp_seq_next(struct seq_file *seq, void *v, loff_t *pos) +{ + (*pos)++; + return ct_expect_get_next(seq, v); } -static void exp_seq_stop(struct seq_file *s, void *v) +static void exp_seq_stop(struct seq_file *seq, void *v) { read_unlock_bh(&nf_conntrack_lock); } static int exp_seq_show(struct seq_file *s, void *v) { - struct nf_conntrack_expect *exp = v; + struct nf_conntrack_expect *exp; + struct hlist_node *n = v; + + exp = hlist_entry(n, struct nf_conntrack_expect, hnode); if (exp->tuple.src.l3num != AF_INET) return 0; @@ -266,7 +281,7 @@ static int exp_seq_show(struct seq_file *s, void *v) return seq_putc(s, '\n'); } -static struct seq_operations exp_seq_ops = { +static const struct seq_operations exp_seq_ops = { .start = exp_seq_start, .next = exp_seq_next, .stop = exp_seq_stop, @@ -275,7 +290,23 @@ static struct seq_operations exp_seq_ops = { static int exp_open(struct inode *inode, struct file *file) { - return seq_open(file, &exp_seq_ops); + struct seq_file *seq; + struct ct_expect_iter_state *st; + int ret; + + st = kmalloc(sizeof(struct ct_expect_iter_state), GFP_KERNEL); + if (st == NULL) + return -ENOMEM; + ret = seq_open(file, &exp_seq_ops); + if (ret) + goto out_free; + seq = file->private_data; + seq->private = st; + memset(st, 0, sizeof(struct ct_expect_iter_state)); + return ret; +out_free: + kfree(st); + return ret; } static const struct file_operations ip_exp_file_ops = { @@ -283,7 +314,7 @@ static const struct file_operations ip_exp_file_ops = { .open = exp_open, .read = seq_read, .llseek = seq_lseek, - .release = seq_release + .release = seq_release_private, }; static void *ct_cpu_seq_start(struct seq_file *seq, loff_t *pos) @@ -354,7 +385,7 @@ static int ct_cpu_seq_show(struct seq_file *seq, void *v) return 0; } -static struct seq_operations ct_cpu_seq_ops = { +static const struct seq_operations ct_cpu_seq_ops = { .start = ct_cpu_seq_start, .next = ct_cpu_seq_next, .stop = ct_cpu_seq_stop, diff --git a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c index f4fc657c1983..6593fd2c5b10 100644 --- a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c +++ b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c @@ -21,12 +21,6 @@ static unsigned long nf_ct_icmp_timeout __read_mostly = 30*HZ; -#if 0 -#define DEBUGP printk -#else -#define DEBUGP(format, args...) -#endif - static int icmp_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, struct nf_conntrack_tuple *tuple) @@ -125,8 +119,8 @@ static int icmp_new(struct nf_conn *conntrack, if (conntrack->tuplehash[0].tuple.dst.u.icmp.type >= sizeof(valid_new) || !valid_new[conntrack->tuplehash[0].tuple.dst.u.icmp.type]) { /* Can't create a new ICMP `conn' with this. */ - DEBUGP("icmp: can't create new conn with type %u\n", - conntrack->tuplehash[0].tuple.dst.u.icmp.type); + pr_debug("icmp: can't create new conn with type %u\n", + conntrack->tuplehash[0].tuple.dst.u.icmp.type); NF_CT_DUMP_TUPLE(&conntrack->tuplehash[0].tuple); return 0; } @@ -142,72 +136,42 @@ icmp_error_message(struct sk_buff *skb, unsigned int hooknum) { struct nf_conntrack_tuple innertuple, origtuple; - struct { - struct icmphdr icmp; - struct iphdr ip; - } _in, *inside; struct nf_conntrack_l4proto *innerproto; struct nf_conntrack_tuple_hash *h; - int dataoff; NF_CT_ASSERT(skb->nfct == NULL); - /* Not enough header? */ - inside = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(_in), &_in); - if (inside == NULL) - return -NF_ACCEPT; - - /* Ignore ICMP's containing fragments (shouldn't happen) */ - if (inside->ip.frag_off & htons(IP_OFFSET)) { - DEBUGP("icmp_error_message: fragment of proto %u\n", - inside->ip.protocol); + /* Are they talking about one of our connections? */ + if (!nf_ct_get_tuplepr(skb, + skb_network_offset(skb) + ip_hdrlen(skb) + + sizeof(struct icmphdr), + PF_INET, &origtuple)) { + pr_debug("icmp_error_message: failed to get tuple\n"); return -NF_ACCEPT; } /* rcu_read_lock()ed by nf_hook_slow */ - innerproto = __nf_ct_l4proto_find(PF_INET, inside->ip.protocol); - - dataoff = ip_hdrlen(skb) + sizeof(inside->icmp); - /* Are they talking about one of our connections? */ - if (!nf_ct_get_tuple(skb, dataoff, dataoff + inside->ip.ihl*4, PF_INET, - inside->ip.protocol, &origtuple, - &nf_conntrack_l3proto_ipv4, innerproto)) { - DEBUGP("icmp_error_message: ! get_tuple p=%u", - inside->ip.protocol); - return -NF_ACCEPT; - } + innerproto = __nf_ct_l4proto_find(PF_INET, origtuple.dst.protonum); /* Ordinarily, we'd expect the inverted tupleproto, but it's been preserved inside the ICMP. */ if (!nf_ct_invert_tuple(&innertuple, &origtuple, &nf_conntrack_l3proto_ipv4, innerproto)) { - DEBUGP("icmp_error_message: no match\n"); + pr_debug("icmp_error_message: no match\n"); return -NF_ACCEPT; } *ctinfo = IP_CT_RELATED; - h = nf_conntrack_find_get(&innertuple, NULL); + h = nf_conntrack_find_get(&innertuple); if (!h) { - /* Locally generated ICMPs will match inverted if they - haven't been SNAT'ed yet */ - /* FIXME: NAT code has to handle half-done double NAT --RR */ - if (hooknum == NF_IP_LOCAL_OUT) - h = nf_conntrack_find_get(&origtuple, NULL); - - if (!h) { - DEBUGP("icmp_error_message: no match\n"); - return -NF_ACCEPT; - } - - /* Reverse direction from that found */ - if (NF_CT_DIRECTION(h) == IP_CT_DIR_REPLY) - *ctinfo += IP_CT_IS_REPLY; - } else { - if (NF_CT_DIRECTION(h) == IP_CT_DIR_REPLY) - *ctinfo += IP_CT_IS_REPLY; + pr_debug("icmp_error_message: no match\n"); + return -NF_ACCEPT; } + if (NF_CT_DIRECTION(h) == IP_CT_DIR_REPLY) + *ctinfo += IP_CT_IS_REPLY; + /* Update skb to refer to this connection */ skb->nfct = &nf_ct_tuplehash_to_ctrack(h)->ct_general; skb->nfctinfo = *ctinfo; @@ -348,7 +312,7 @@ static struct ctl_table icmp_compat_sysctl_table[] = { #endif /* CONFIG_NF_CONNTRACK_PROC_COMPAT */ #endif /* CONFIG_SYSCTL */ -struct nf_conntrack_l4proto nf_conntrack_l4proto_icmp = +struct nf_conntrack_l4proto nf_conntrack_l4proto_icmp __read_mostly = { .l3proto = PF_INET, .l4proto = IPPROTO_ICMP, @@ -374,4 +338,3 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_icmp = #endif #endif }; -EXPORT_SYMBOL_GPL(nf_conntrack_l4proto_icmp); diff --git a/net/ipv4/netfilter/nf_nat_amanda.c b/net/ipv4/netfilter/nf_nat_amanda.c index 0f17098917bc..bd93a1d71052 100644 --- a/net/ipv4/netfilter/nf_nat_amanda.c +++ b/net/ipv4/netfilter/nf_nat_amanda.c @@ -45,7 +45,7 @@ static unsigned int help(struct sk_buff **pskb, /* Try to get same port: if not, try to change it. */ for (port = ntohs(exp->saved_proto.tcp.port); port != 0; port++) { exp->tuple.dst.u.tcp.port = htons(port); - if (nf_conntrack_expect_related(exp) == 0) + if (nf_ct_expect_related(exp) == 0) break; } @@ -57,7 +57,7 @@ static unsigned int help(struct sk_buff **pskb, matchoff, matchlen, buffer, strlen(buffer)); if (ret != NF_ACCEPT) - nf_conntrack_unexpect_related(exp); + nf_ct_unexpect_related(exp); return ret; } diff --git a/net/ipv4/netfilter/nf_nat_core.c b/net/ipv4/netfilter/nf_nat_core.c index ea02f00d2dac..e848d8d6292f 100644 --- a/net/ipv4/netfilter/nf_nat_core.c +++ b/net/ipv4/netfilter/nf_nat_core.c @@ -12,7 +12,6 @@ #include <linux/types.h> #include <linux/timer.h> #include <linux/skbuff.h> -#include <linux/vmalloc.h> #include <net/checksum.h> #include <net/icmp.h> #include <net/ip.h> @@ -32,20 +31,15 @@ #include <net/netfilter/nf_conntrack_l3proto.h> #include <net/netfilter/nf_conntrack_l4proto.h> -#if 0 -#define DEBUGP printk -#else -#define DEBUGP(format, args...) -#endif - static DEFINE_RWLOCK(nf_nat_lock); static struct nf_conntrack_l3proto *l3proto = NULL; /* Calculated at init based on memory size */ static unsigned int nf_nat_htable_size; +static int nf_nat_vmalloced; -static struct list_head *bysource; +static struct hlist_head *bysource; #define MAX_IP_NAT_PROTO 256 static struct nf_nat_protocol *nf_nat_protos[MAX_IP_NAT_PROTO]; @@ -87,19 +81,6 @@ hash_by_src(const struct nf_conntrack_tuple *tuple) tuple->dst.protonum, 0) % nf_nat_htable_size; } -/* Noone using conntrack by the time this called. */ -static void nf_nat_cleanup_conntrack(struct nf_conn *conn) -{ - struct nf_conn_nat *nat; - if (!(conn->status & IPS_NAT_DONE_MASK)) - return; - - nat = nfct_nat(conn); - write_lock_bh(&nf_nat_lock); - list_del(&nat->info.bysource); - write_unlock_bh(&nf_nat_lock); -} - /* Is this tuple already taken? (not by us) */ int nf_nat_used_tuple(const struct nf_conntrack_tuple *tuple, @@ -166,10 +147,11 @@ find_appropriate_src(const struct nf_conntrack_tuple *tuple, unsigned int h = hash_by_src(tuple); struct nf_conn_nat *nat; struct nf_conn *ct; + struct hlist_node *n; read_lock_bh(&nf_nat_lock); - list_for_each_entry(nat, &bysource[h], info.bysource) { - ct = (struct nf_conn *)((char *)nat - offsetof(struct nf_conn, data)); + hlist_for_each_entry(nat, n, &bysource[h], bysource) { + ct = nat->ct; if (same_src(ct, tuple)) { /* Copy source part from reply tuple. */ nf_ct_invert_tuplepr(result, @@ -254,7 +236,7 @@ get_unique_tuple(struct nf_conntrack_tuple *tuple, manips not an issue. */ if (maniptype == IP_NAT_MANIP_SRC) { if (find_appropriate_src(orig_tuple, tuple, range)) { - DEBUGP("get_unique_tuple: Found current src map\n"); + pr_debug("get_unique_tuple: Found current src map\n"); if (!(range->flags & IP_NAT_RANGE_PROTO_RANDOM)) if (!nf_nat_used_tuple(tuple, ct)) return; @@ -296,11 +278,20 @@ nf_nat_setup_info(struct nf_conn *ct, unsigned int hooknum) { struct nf_conntrack_tuple curr_tuple, new_tuple; - struct nf_conn_nat *nat = nfct_nat(ct); - struct nf_nat_info *info = &nat->info; + struct nf_conn_nat *nat; int have_to_hash = !(ct->status & IPS_NAT_DONE_MASK); enum nf_nat_manip_type maniptype = HOOK2MANIP(hooknum); + /* nat helper or nfctnetlink also setup binding */ + nat = nfct_nat(ct); + if (!nat) { + nat = nf_ct_ext_add(ct, NF_CT_EXT_NAT, GFP_ATOMIC); + if (nat == NULL) { + pr_debug("failed to add NAT extension\n"); + return NF_ACCEPT; + } + } + NF_CT_ASSERT(hooknum == NF_IP_PRE_ROUTING || hooknum == NF_IP_POST_ROUTING || hooknum == NF_IP_LOCAL_IN || @@ -337,7 +328,10 @@ nf_nat_setup_info(struct nf_conn *ct, srchash = hash_by_src(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); write_lock_bh(&nf_nat_lock); - list_add(&info->bysource, &bysource[srchash]); + /* nf_conntrack_alter_reply might re-allocate exntension aera */ + nat = nfct_nat(ct); + nat->ct = ct; + hlist_add_head(&nat->bysource, &bysource[srchash]); write_unlock_bh(&nf_nat_lock); } @@ -462,8 +456,9 @@ int nf_nat_icmp_reply_translation(struct nf_conn *ct, return 0; } - DEBUGP("icmp_reply_translation: translating error %p manp %u dir %s\n", - *pskb, manip, dir == IP_CT_DIR_ORIGINAL ? "ORIG" : "REPLY"); + pr_debug("icmp_reply_translation: translating error %p manip %u " + "dir %s\n", *pskb, manip, + dir == IP_CT_DIR_ORIGINAL ? "ORIG" : "REPLY"); /* rcu_read_lock()ed by nf_hook_slow */ l4proto = __nf_ct_l4proto_find(PF_INET, inside->ip.protocol); @@ -590,17 +585,69 @@ nf_nat_port_nfattr_to_range(struct nfattr *tb[], struct nf_nat_range *range) EXPORT_SYMBOL_GPL(nf_nat_port_range_to_nfattr); #endif +/* Noone using conntrack by the time this called. */ +static void nf_nat_cleanup_conntrack(struct nf_conn *ct) +{ + struct nf_conn_nat *nat = nf_ct_ext_find(ct, NF_CT_EXT_NAT); + + if (nat == NULL || nat->ct == NULL) + return; + + NF_CT_ASSERT(nat->ct->status & IPS_NAT_DONE_MASK); + + write_lock_bh(&nf_nat_lock); + hlist_del(&nat->bysource); + nat->ct = NULL; + write_unlock_bh(&nf_nat_lock); +} + +static void nf_nat_move_storage(struct nf_conn *conntrack, void *old) +{ + struct nf_conn_nat *new_nat = nf_ct_ext_find(conntrack, NF_CT_EXT_NAT); + struct nf_conn_nat *old_nat = (struct nf_conn_nat *)old; + struct nf_conn *ct = old_nat->ct; + unsigned int srchash; + + if (!(ct->status & IPS_NAT_DONE_MASK)) + return; + + srchash = hash_by_src(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); + + write_lock_bh(&nf_nat_lock); + hlist_replace_rcu(&old_nat->bysource, &new_nat->bysource); + new_nat->ct = ct; + write_unlock_bh(&nf_nat_lock); +} + +static struct nf_ct_ext_type nat_extend __read_mostly = { + .len = sizeof(struct nf_conn_nat), + .align = __alignof__(struct nf_conn_nat), + .destroy = nf_nat_cleanup_conntrack, + .move = nf_nat_move_storage, + .id = NF_CT_EXT_NAT, + .flags = NF_CT_EXT_F_PREALLOC, +}; + static int __init nf_nat_init(void) { size_t i; + int ret; + + ret = nf_ct_extend_register(&nat_extend); + if (ret < 0) { + printk(KERN_ERR "nf_nat_core: Unable to register extension\n"); + return ret; + } /* Leave them the same for the moment. */ nf_nat_htable_size = nf_conntrack_htable_size; - /* One vmalloc for both hash tables */ - bysource = vmalloc(sizeof(struct list_head) * nf_nat_htable_size); - if (!bysource) - return -ENOMEM; + bysource = nf_ct_alloc_hashtable(&nf_nat_htable_size, + &nf_nat_vmalloced); + if (!bysource) { + ret = -ENOMEM; + goto cleanup_extend; + } /* Sew in builtin protocols. */ write_lock_bh(&nf_nat_lock); @@ -612,18 +659,18 @@ static int __init nf_nat_init(void) write_unlock_bh(&nf_nat_lock); for (i = 0; i < nf_nat_htable_size; i++) { - INIT_LIST_HEAD(&bysource[i]); + INIT_HLIST_HEAD(&bysource[i]); } - /* FIXME: Man, this is a hack. <SIGH> */ - NF_CT_ASSERT(rcu_dereference(nf_conntrack_destroyed) == NULL); - rcu_assign_pointer(nf_conntrack_destroyed, nf_nat_cleanup_conntrack); - /* Initialize fake conntrack so that NAT will skip it */ nf_conntrack_untracked.status |= IPS_NAT_DONE_MASK; l3proto = nf_ct_l3proto_find_get((u_int16_t)AF_INET); return 0; + + cleanup_extend: + nf_ct_extend_unregister(&nat_extend); + return ret; } /* Clear NAT section of all conntracks, in case we're loaded again. */ @@ -641,10 +688,10 @@ static int clean_nat(struct nf_conn *i, void *data) static void __exit nf_nat_cleanup(void) { nf_ct_iterate_cleanup(&clean_nat, NULL); - rcu_assign_pointer(nf_conntrack_destroyed, NULL); synchronize_rcu(); - vfree(bysource); + nf_ct_free_hashtable(bysource, nf_nat_vmalloced, nf_nat_htable_size); nf_ct_l3proto_put(l3proto); + nf_ct_extend_unregister(&nat_extend); } MODULE_LICENSE("GPL"); diff --git a/net/ipv4/netfilter/nf_nat_ftp.c b/net/ipv4/netfilter/nf_nat_ftp.c index e6bc8e5a72f1..3663bd879c39 100644 --- a/net/ipv4/netfilter/nf_nat_ftp.c +++ b/net/ipv4/netfilter/nf_nat_ftp.c @@ -25,12 +25,6 @@ MODULE_AUTHOR("Rusty Russell <rusty@rustcorp.com.au>"); MODULE_DESCRIPTION("ftp NAT helper"); MODULE_ALIAS("ip_nat_ftp"); -#if 0 -#define DEBUGP printk -#else -#define DEBUGP(format, args...) -#endif - /* FIXME: Time out? --RR */ static int @@ -47,7 +41,7 @@ mangle_rfc959_packet(struct sk_buff **pskb, sprintf(buffer, "%u,%u,%u,%u,%u,%u", NIPQUAD(newip), port>>8, port&0xFF); - DEBUGP("calling nf_nat_mangle_tcp_packet\n"); + pr_debug("calling nf_nat_mangle_tcp_packet\n"); return nf_nat_mangle_tcp_packet(pskb, ct, ctinfo, matchoff, matchlen, buffer, strlen(buffer)); @@ -67,7 +61,7 @@ mangle_eprt_packet(struct sk_buff **pskb, sprintf(buffer, "|1|%u.%u.%u.%u|%u|", NIPQUAD(newip), port); - DEBUGP("calling nf_nat_mangle_tcp_packet\n"); + pr_debug("calling nf_nat_mangle_tcp_packet\n"); return nf_nat_mangle_tcp_packet(pskb, ct, ctinfo, matchoff, matchlen, buffer, strlen(buffer)); @@ -87,7 +81,7 @@ mangle_epsv_packet(struct sk_buff **pskb, sprintf(buffer, "|||%u|", port); - DEBUGP("calling nf_nat_mangle_tcp_packet\n"); + pr_debug("calling nf_nat_mangle_tcp_packet\n"); return nf_nat_mangle_tcp_packet(pskb, ct, ctinfo, matchoff, matchlen, buffer, strlen(buffer)); @@ -117,7 +111,7 @@ static unsigned int nf_nat_ftp(struct sk_buff **pskb, int dir = CTINFO2DIR(ctinfo); struct nf_conn *ct = exp->master; - DEBUGP("FTP_NAT: type %i, off %u len %u\n", type, matchoff, matchlen); + pr_debug("FTP_NAT: type %i, off %u len %u\n", type, matchoff, matchlen); /* Connection will come from wherever this packet goes, hence !dir */ newip = ct->tuplehash[!dir].tuple.dst.u3.ip; @@ -131,7 +125,7 @@ static unsigned int nf_nat_ftp(struct sk_buff **pskb, /* Try to get same port: if not, try to change it. */ for (port = ntohs(exp->saved_proto.tcp.port); port != 0; port++) { exp->tuple.dst.u.tcp.port = htons(port); - if (nf_conntrack_expect_related(exp) == 0) + if (nf_ct_expect_related(exp) == 0) break; } @@ -139,7 +133,7 @@ static unsigned int nf_nat_ftp(struct sk_buff **pskb, return NF_DROP; if (!mangle[type](pskb, newip, port, matchoff, matchlen, ct, ctinfo)) { - nf_conntrack_unexpect_related(exp); + nf_ct_unexpect_related(exp); return NF_DROP; } return NF_ACCEPT; diff --git a/net/ipv4/netfilter/nf_nat_h323.c b/net/ipv4/netfilter/nf_nat_h323.c index c5d2a2d690b8..c1b059a73708 100644 --- a/net/ipv4/netfilter/nf_nat_h323.c +++ b/net/ipv4/netfilter/nf_nat_h323.c @@ -21,12 +21,6 @@ #include <net/netfilter/nf_conntrack_expect.h> #include <linux/netfilter/nf_conntrack_h323.h> -#if 0 -#define DEBUGP printk -#else -#define DEBUGP(format, args...) -#endif - /****************************************************************************/ static int set_addr(struct sk_buff **pskb, unsigned char **data, int dataoff, @@ -126,12 +120,11 @@ static int set_sig_addr(struct sk_buff **pskb, struct nf_conn *ct, (ntohl(addr.ip) & 0xff000000) == 0x7f000000) i = 0; - DEBUGP - ("nf_nat_ras: set signal address " - "%u.%u.%u.%u:%hu->%u.%u.%u.%u:%hu\n", - NIPQUAD(ip), port, - NIPQUAD(ct->tuplehash[!dir].tuple.dst. - ip), info->sig_port[!dir]); + pr_debug("nf_nat_ras: set signal address " + "%u.%u.%u.%u:%hu->%u.%u.%u.%u:%hu\n", + NIPQUAD(addr.ip), port, + NIPQUAD(ct->tuplehash[!dir].tuple.dst.u3.ip), + info->sig_port[!dir]); return set_h225_addr(pskb, data, 0, &taddr[i], &ct->tuplehash[!dir]. tuple.dst.u3, @@ -139,12 +132,11 @@ static int set_sig_addr(struct sk_buff **pskb, struct nf_conn *ct, } else if (addr.ip == ct->tuplehash[dir].tuple.dst.u3.ip && port == info->sig_port[dir]) { /* GK->GW */ - DEBUGP - ("nf_nat_ras: set signal address " - "%u.%u.%u.%u:%hu->%u.%u.%u.%u:%hu\n", - NIPQUAD(ip), port, - NIPQUAD(ct->tuplehash[!dir].tuple.src. - ip), info->sig_port[!dir]); + pr_debug("nf_nat_ras: set signal address " + "%u.%u.%u.%u:%hu->%u.%u.%u.%u:%hu\n", + NIPQUAD(addr.ip), port, + NIPQUAD(ct->tuplehash[!dir].tuple.src.u3.ip), + info->sig_port[!dir]); return set_h225_addr(pskb, data, 0, &taddr[i], &ct->tuplehash[!dir]. tuple.src.u3, @@ -171,12 +163,11 @@ static int set_ras_addr(struct sk_buff **pskb, struct nf_conn *ct, if (get_h225_addr(ct, *data, &taddr[i], &addr, &port) && addr.ip == ct->tuplehash[dir].tuple.src.u3.ip && port == ct->tuplehash[dir].tuple.src.u.udp.port) { - DEBUGP("nf_nat_ras: set rasAddress " - "%u.%u.%u.%u:%hu->%u.%u.%u.%u:%hu\n", - NIPQUAD(ip), ntohs(port), - NIPQUAD(ct->tuplehash[!dir].tuple.dst.u3.ip), - ntohs(ct->tuplehash[!dir].tuple.dst.u.udp. - port)); + pr_debug("nf_nat_ras: set rasAddress " + "%u.%u.%u.%u:%hu->%u.%u.%u.%u:%hu\n", + NIPQUAD(addr.ip), ntohs(port), + NIPQUAD(ct->tuplehash[!dir].tuple.dst.u3.ip), + ntohs(ct->tuplehash[!dir].tuple.dst.u.udp.port)); return set_h225_addr(pskb, data, 0, &taddr[i], &ct->tuplehash[!dir].tuple.dst.u3, ct->tuplehash[!dir].tuple. @@ -237,12 +228,12 @@ static int nat_rtp_rtcp(struct sk_buff **pskb, struct nf_conn *ct, for (nated_port = ntohs(rtp_exp->tuple.dst.u.udp.port); nated_port != 0; nated_port += 2) { rtp_exp->tuple.dst.u.udp.port = htons(nated_port); - if (nf_conntrack_expect_related(rtp_exp) == 0) { + if (nf_ct_expect_related(rtp_exp) == 0) { rtcp_exp->tuple.dst.u.udp.port = htons(nated_port + 1); - if (nf_conntrack_expect_related(rtcp_exp) == 0) + if (nf_ct_expect_related(rtcp_exp) == 0) break; - nf_conntrack_unexpect_related(rtp_exp); + nf_ct_unexpect_related(rtp_exp); } } @@ -261,22 +252,22 @@ static int nat_rtp_rtcp(struct sk_buff **pskb, struct nf_conn *ct, info->rtp_port[i][dir] = rtp_port; info->rtp_port[i][!dir] = htons(nated_port); } else { - nf_conntrack_unexpect_related(rtp_exp); - nf_conntrack_unexpect_related(rtcp_exp); + nf_ct_unexpect_related(rtp_exp); + nf_ct_unexpect_related(rtcp_exp); return -1; } /* Success */ - DEBUGP("nf_nat_h323: expect RTP %u.%u.%u.%u:%hu->%u.%u.%u.%u:%hu\n", - NIPQUAD(rtp_exp->tuple.src.ip), - ntohs(rtp_exp->tuple.src.u.udp.port), - NIPQUAD(rtp_exp->tuple.dst.ip), - ntohs(rtp_exp->tuple.dst.u.udp.port)); - DEBUGP("nf_nat_h323: expect RTCP %u.%u.%u.%u:%hu->%u.%u.%u.%u:%hu\n", - NIPQUAD(rtcp_exp->tuple.src.ip), - ntohs(rtcp_exp->tuple.src.u.udp.port), - NIPQUAD(rtcp_exp->tuple.dst.ip), - ntohs(rtcp_exp->tuple.dst.u.udp.port)); + pr_debug("nf_nat_h323: expect RTP %u.%u.%u.%u:%hu->%u.%u.%u.%u:%hu\n", + NIPQUAD(rtp_exp->tuple.src.u3.ip), + ntohs(rtp_exp->tuple.src.u.udp.port), + NIPQUAD(rtp_exp->tuple.dst.u3.ip), + ntohs(rtp_exp->tuple.dst.u.udp.port)); + pr_debug("nf_nat_h323: expect RTCP %u.%u.%u.%u:%hu->%u.%u.%u.%u:%hu\n", + NIPQUAD(rtcp_exp->tuple.src.u3.ip), + ntohs(rtcp_exp->tuple.src.u.udp.port), + NIPQUAD(rtcp_exp->tuple.dst.u3.ip), + ntohs(rtcp_exp->tuple.dst.u.udp.port)); return 0; } @@ -299,7 +290,7 @@ static int nat_t120(struct sk_buff **pskb, struct nf_conn *ct, /* Try to get same port: if not, try to change it. */ for (; nated_port != 0; nated_port++) { exp->tuple.dst.u.tcp.port = htons(nated_port); - if (nf_conntrack_expect_related(exp) == 0) + if (nf_ct_expect_related(exp) == 0) break; } @@ -313,13 +304,15 @@ static int nat_t120(struct sk_buff **pskb, struct nf_conn *ct, if (set_h245_addr(pskb, data, dataoff, taddr, &ct->tuplehash[!dir].tuple.dst.u3, htons(nated_port)) < 0) { - nf_conntrack_unexpect_related(exp); + nf_ct_unexpect_related(exp); return -1; } - DEBUGP("nf_nat_h323: expect T.120 %u.%u.%u.%u:%hu->%u.%u.%u.%u:%hu\n", - NIPQUAD(exp->tuple.src.ip), ntohs(exp->tuple.src.u.tcp.port), - NIPQUAD(exp->tuple.dst.ip), ntohs(exp->tuple.dst.u.tcp.port)); + pr_debug("nf_nat_h323: expect T.120 %u.%u.%u.%u:%hu->%u.%u.%u.%u:%hu\n", + NIPQUAD(exp->tuple.src.u3.ip), + ntohs(exp->tuple.src.u.tcp.port), + NIPQUAD(exp->tuple.dst.u3.ip), + ntohs(exp->tuple.dst.u.tcp.port)); return 0; } @@ -347,7 +340,7 @@ static int nat_h245(struct sk_buff **pskb, struct nf_conn *ct, /* Try to get same port: if not, try to change it. */ for (; nated_port != 0; nated_port++) { exp->tuple.dst.u.tcp.port = htons(nated_port); - if (nf_conntrack_expect_related(exp) == 0) + if (nf_ct_expect_related(exp) == 0) break; } @@ -365,13 +358,15 @@ static int nat_h245(struct sk_buff **pskb, struct nf_conn *ct, info->sig_port[dir] = port; info->sig_port[!dir] = htons(nated_port); } else { - nf_conntrack_unexpect_related(exp); + nf_ct_unexpect_related(exp); return -1; } - DEBUGP("nf_nat_q931: expect H.245 %u.%u.%u.%u:%hu->%u.%u.%u.%u:%hu\n", - NIPQUAD(exp->tuple.src.ip), ntohs(exp->tuple.src.u.tcp.port), - NIPQUAD(exp->tuple.dst.ip), ntohs(exp->tuple.dst.u.tcp.port)); + pr_debug("nf_nat_q931: expect H.245 %u.%u.%u.%u:%hu->%u.%u.%u.%u:%hu\n", + NIPQUAD(exp->tuple.src.u3.ip), + ntohs(exp->tuple.src.u.tcp.port), + NIPQUAD(exp->tuple.dst.u3.ip), + ntohs(exp->tuple.dst.u.tcp.port)); return 0; } @@ -433,7 +428,7 @@ static int nat_q931(struct sk_buff **pskb, struct nf_conn *ct, /* Try to get same port: if not, try to change it. */ for (; nated_port != 0; nated_port++) { exp->tuple.dst.u.tcp.port = htons(nated_port); - if (nf_conntrack_expect_related(exp) == 0) + if (nf_ct_expect_related(exp) == 0) break; } @@ -460,14 +455,16 @@ static int nat_q931(struct sk_buff **pskb, struct nf_conn *ct, info->sig_port[!dir]); } } else { - nf_conntrack_unexpect_related(exp); + nf_ct_unexpect_related(exp); return -1; } /* Success */ - DEBUGP("nf_nat_ras: expect Q.931 %u.%u.%u.%u:%hu->%u.%u.%u.%u:%hu\n", - NIPQUAD(exp->tuple.src.ip), ntohs(exp->tuple.src.u.tcp.port), - NIPQUAD(exp->tuple.dst.ip), ntohs(exp->tuple.dst.u.tcp.port)); + pr_debug("nf_nat_ras: expect Q.931 %u.%u.%u.%u:%hu->%u.%u.%u.%u:%hu\n", + NIPQUAD(exp->tuple.src.u3.ip), + ntohs(exp->tuple.src.u.tcp.port), + NIPQUAD(exp->tuple.dst.u3.ip), + ntohs(exp->tuple.dst.u.tcp.port)); return 0; } @@ -517,7 +514,7 @@ static int nat_callforwarding(struct sk_buff **pskb, struct nf_conn *ct, /* Try to get same port: if not, try to change it. */ for (nated_port = ntohs(port); nated_port != 0; nated_port++) { exp->tuple.dst.u.tcp.port = htons(nated_port); - if (nf_conntrack_expect_related(exp) == 0) + if (nf_ct_expect_related(exp) == 0) break; } @@ -531,15 +528,17 @@ static int nat_callforwarding(struct sk_buff **pskb, struct nf_conn *ct, if (!set_h225_addr(pskb, data, dataoff, taddr, &ct->tuplehash[!dir].tuple.dst.u3, htons(nated_port)) == 0) { - nf_conntrack_unexpect_related(exp); + nf_ct_unexpect_related(exp); return -1; } /* Success */ - DEBUGP("nf_nat_q931: expect Call Forwarding " - "%u.%u.%u.%u:%hu->%u.%u.%u.%u:%hu\n", - NIPQUAD(exp->tuple.src.ip), ntohs(exp->tuple.src.u.tcp.port), - NIPQUAD(exp->tuple.dst.ip), ntohs(exp->tuple.dst.u.tcp.port)); + pr_debug("nf_nat_q931: expect Call Forwarding " + "%u.%u.%u.%u:%hu->%u.%u.%u.%u:%hu\n", + NIPQUAD(exp->tuple.src.u3.ip), + ntohs(exp->tuple.src.u.tcp.port), + NIPQUAD(exp->tuple.dst.u3.ip), + ntohs(exp->tuple.dst.u.tcp.port)); return 0; } @@ -566,8 +565,6 @@ static int __init init(void) rcu_assign_pointer(nat_h245_hook, nat_h245); rcu_assign_pointer(nat_callforwarding_hook, nat_callforwarding); rcu_assign_pointer(nat_q931_hook, nat_q931); - - DEBUGP("nf_nat_h323: init success\n"); return 0; } diff --git a/net/ipv4/netfilter/nf_nat_helper.c b/net/ipv4/netfilter/nf_nat_helper.c index 15b6e5ce3a04..93d8a0a8f035 100644 --- a/net/ipv4/netfilter/nf_nat_helper.c +++ b/net/ipv4/netfilter/nf_nat_helper.c @@ -26,13 +26,9 @@ #include <net/netfilter/nf_nat_core.h> #include <net/netfilter/nf_nat_helper.h> -#if 0 -#define DEBUGP printk -#define DUMP_OFFSET(x) printk("offset_before=%d, offset_after=%d, correction_pos=%u\n", x->offset_before, x->offset_after, x->correction_pos); -#else -#define DEBUGP(format, args...) -#define DUMP_OFFSET(x) -#endif +#define DUMP_OFFSET(x) \ + pr_debug("offset_before=%d, offset_after=%d, correction_pos=%u\n", \ + x->offset_before, x->offset_after, x->correction_pos); static DEFINE_SPINLOCK(nf_nat_seqofs_lock); @@ -47,15 +43,15 @@ adjust_tcp_sequence(u32 seq, struct nf_nat_seq *this_way, *other_way; struct nf_conn_nat *nat = nfct_nat(ct); - DEBUGP("nf_nat_resize_packet: old_size = %u, new_size = %u\n", - (*skb)->len, new_size); + pr_debug("adjust_tcp_sequence: seq = %u, sizediff = %d\n", + ntohl(seq), seq); dir = CTINFO2DIR(ctinfo); - this_way = &nat->info.seq[dir]; - other_way = &nat->info.seq[!dir]; + this_way = &nat->seq[dir]; + other_way = &nat->seq[!dir]; - DEBUGP("nf_nat_resize_packet: Seq_offset before: "); + pr_debug("nf_nat_resize_packet: Seq_offset before: "); DUMP_OFFSET(this_way); spin_lock_bh(&nf_nat_seqofs_lock); @@ -72,7 +68,7 @@ adjust_tcp_sequence(u32 seq, } spin_unlock_bh(&nf_nat_seqofs_lock); - DEBUGP("nf_nat_resize_packet: Seq_offset after: "); + pr_debug("nf_nat_resize_packet: Seq_offset after: "); DUMP_OFFSET(this_way); } @@ -100,14 +96,12 @@ static void mangle_contents(struct sk_buff *skb, /* update skb info */ if (rep_len > match_len) { - DEBUGP("nf_nat_mangle_packet: Extending packet by " - "%u from %u bytes\n", rep_len - match_len, - skb->len); + pr_debug("nf_nat_mangle_packet: Extending packet by " + "%u from %u bytes\n", rep_len - match_len, skb->len); skb_put(skb, rep_len - match_len); } else { - DEBUGP("nf_nat_mangle_packet: Shrinking packet from " - "%u from %u bytes\n", match_len - rep_len, - skb->len); + pr_debug("nf_nat_mangle_packet: Shrinking packet from " + "%u from %u bytes\n", match_len - rep_len, skb->len); __skb_trim(skb, skb->len + rep_len - match_len); } @@ -178,7 +172,7 @@ nf_nat_mangle_tcp_packet(struct sk_buff **pskb, datalen = (*pskb)->len - iph->ihl*4; if ((*pskb)->ip_summed != CHECKSUM_PARTIAL) { if (!(rt->rt_flags & RTCF_LOCAL) && - (*pskb)->dev->features & NETIF_F_ALL_CSUM) { + (*pskb)->dev->features & NETIF_F_V4_CSUM) { (*pskb)->ip_summed = CHECKSUM_PARTIAL; (*pskb)->csum_start = skb_headroom(*pskb) + skb_network_offset(*pskb) + @@ -190,7 +184,7 @@ nf_nat_mangle_tcp_packet(struct sk_buff **pskb, tcph->check = 0; tcph->check = tcp_v4_check(datalen, iph->saddr, iph->daddr, - csum_partial((char *)tcph, + csum_partial(tcph, datalen, 0)); } } else @@ -265,7 +259,7 @@ nf_nat_mangle_udp_packet(struct sk_buff **pskb, if ((*pskb)->ip_summed != CHECKSUM_PARTIAL) { if (!(rt->rt_flags & RTCF_LOCAL) && - (*pskb)->dev->features & NETIF_F_ALL_CSUM) { + (*pskb)->dev->features & NETIF_F_V4_CSUM) { (*pskb)->ip_summed = CHECKSUM_PARTIAL; (*pskb)->csum_start = skb_headroom(*pskb) + skb_network_offset(*pskb) + @@ -278,7 +272,7 @@ nf_nat_mangle_udp_packet(struct sk_buff **pskb, udph->check = 0; udph->check = csum_tcpudp_magic(iph->saddr, iph->daddr, datalen, IPPROTO_UDP, - csum_partial((char *)udph, + csum_partial(udph, datalen, 0)); if (!udph->check) udph->check = CSUM_MANGLED_0; @@ -320,9 +314,9 @@ sack_adjust(struct sk_buff *skb, new_end_seq = htonl(ntohl(sack->end_seq) - natseq->offset_before); - DEBUGP("sack_adjust: start_seq: %d->%d, end_seq: %d->%d\n", - ntohl(sack->start_seq), new_start_seq, - ntohl(sack->end_seq), new_end_seq); + pr_debug("sack_adjust: start_seq: %d->%d, end_seq: %d->%d\n", + ntohl(sack->start_seq), new_start_seq, + ntohl(sack->end_seq), new_end_seq); nf_proto_csum_replace4(&tcph->check, skb, sack->start_seq, new_start_seq, 0); @@ -372,8 +366,7 @@ nf_nat_sack_adjust(struct sk_buff **pskb, op[1] >= 2+TCPOLEN_SACK_PERBLOCK && ((op[1] - 2) % TCPOLEN_SACK_PERBLOCK) == 0) sack_adjust(*pskb, tcph, optoff+2, - optoff+op[1], - &nat->info.seq[!dir]); + optoff+op[1], &nat->seq[!dir]); optoff += op[1]; } } @@ -394,8 +387,8 @@ nf_nat_seq_adjust(struct sk_buff **pskb, dir = CTINFO2DIR(ctinfo); - this_way = &nat->info.seq[dir]; - other_way = &nat->info.seq[!dir]; + this_way = &nat->seq[dir]; + other_way = &nat->seq[!dir]; if (!skb_make_writable(pskb, ip_hdrlen(*pskb) + sizeof(*tcph))) return 0; @@ -415,9 +408,9 @@ nf_nat_seq_adjust(struct sk_buff **pskb, nf_proto_csum_replace4(&tcph->check, *pskb, tcph->seq, newseq, 0); nf_proto_csum_replace4(&tcph->check, *pskb, tcph->ack_seq, newack, 0); - DEBUGP("Adjusting sequence number from %u->%u, ack from %u->%u\n", - ntohl(tcph->seq), ntohl(newseq), ntohl(tcph->ack_seq), - ntohl(newack)); + pr_debug("Adjusting sequence number from %u->%u, ack from %u->%u\n", + ntohl(tcph->seq), ntohl(newseq), ntohl(tcph->ack_seq), + ntohl(newack)); tcph->seq = newseq; tcph->ack_seq = newack; diff --git a/net/ipv4/netfilter/nf_nat_irc.c b/net/ipv4/netfilter/nf_nat_irc.c index 9b8c0daea744..bcf274bba602 100644 --- a/net/ipv4/netfilter/nf_nat_irc.c +++ b/net/ipv4/netfilter/nf_nat_irc.c @@ -22,12 +22,6 @@ #include <net/netfilter/nf_conntrack_expect.h> #include <linux/netfilter/nf_conntrack_irc.h> -#if 0 -#define DEBUGP printk -#else -#define DEBUGP(format, args...) -#endif - MODULE_AUTHOR("Harald Welte <laforge@gnumonks.org>"); MODULE_DESCRIPTION("IRC (DCC) NAT helper"); MODULE_LICENSE("GPL"); @@ -44,9 +38,6 @@ static unsigned int help(struct sk_buff **pskb, u_int16_t port; unsigned int ret; - DEBUGP("IRC_NAT: info (seq %u + %u) in %u\n", - expect->seq, exp_irc_info->len, ntohl(tcph->seq)); - /* Reply comes from server. */ exp->saved_proto.tcp.port = exp->tuple.dst.u.tcp.port; exp->dir = IP_CT_DIR_REPLY; @@ -55,7 +46,7 @@ static unsigned int help(struct sk_buff **pskb, /* Try to get same port: if not, try to change it. */ for (port = ntohs(exp->saved_proto.tcp.port); port != 0; port++) { exp->tuple.dst.u.tcp.port = htons(port); - if (nf_conntrack_expect_related(exp) == 0) + if (nf_ct_expect_related(exp) == 0) break; } @@ -64,14 +55,14 @@ static unsigned int help(struct sk_buff **pskb, ip = ntohl(exp->master->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3.ip); sprintf(buffer, "%u %u", ip, port); - DEBUGP("nf_nat_irc: inserting '%s' == %u.%u.%u.%u, port %u\n", - buffer, NIPQUAD(ip), port); + pr_debug("nf_nat_irc: inserting '%s' == %u.%u.%u.%u, port %u\n", + buffer, NIPQUAD(ip), port); ret = nf_nat_mangle_tcp_packet(pskb, exp->master, ctinfo, matchoff, matchlen, buffer, strlen(buffer)); if (ret != NF_ACCEPT) - nf_conntrack_unexpect_related(exp); + nf_ct_unexpect_related(exp); return ret; } diff --git a/net/ipv4/netfilter/nf_nat_pptp.c b/net/ipv4/netfilter/nf_nat_pptp.c index a66888749ceb..984ec8308b2e 100644 --- a/net/ipv4/netfilter/nf_nat_pptp.c +++ b/net/ipv4/netfilter/nf_nat_pptp.c @@ -37,14 +37,6 @@ MODULE_AUTHOR("Harald Welte <laforge@gnumonks.org>"); MODULE_DESCRIPTION("Netfilter NAT helper module for PPTP"); MODULE_ALIAS("ip_nat_pptp"); -#if 0 -extern const char *pptp_msg_name[]; -#define DEBUGP(format, args...) printk(KERN_DEBUG "%s:%s: " format, __FILE__, \ - __FUNCTION__, ## args) -#else -#define DEBUGP(format, args...) -#endif - static void pptp_nat_expected(struct nf_conn *ct, struct nf_conntrack_expect *exp) { @@ -60,7 +52,7 @@ static void pptp_nat_expected(struct nf_conn *ct, /* And here goes the grand finale of corrosion... */ if (exp->dir == IP_CT_DIR_ORIGINAL) { - DEBUGP("we are PNS->PAC\n"); + pr_debug("we are PNS->PAC\n"); /* therefore, build tuple for PAC->PNS */ t.src.l3num = AF_INET; t.src.u3.ip = master->tuplehash[!exp->dir].tuple.src.u3.ip; @@ -69,7 +61,7 @@ static void pptp_nat_expected(struct nf_conn *ct, t.dst.u.gre.key = ct_pptp_info->pns_call_id; t.dst.protonum = IPPROTO_GRE; } else { - DEBUGP("we are PAC->PNS\n"); + pr_debug("we are PAC->PNS\n"); /* build tuple for PNS->PAC */ t.src.l3num = AF_INET; t.src.u3.ip = master->tuplehash[!exp->dir].tuple.src.u3.ip; @@ -79,15 +71,15 @@ static void pptp_nat_expected(struct nf_conn *ct, t.dst.protonum = IPPROTO_GRE; } - DEBUGP("trying to unexpect other dir: "); + pr_debug("trying to unexpect other dir: "); NF_CT_DUMP_TUPLE(&t); - other_exp = nf_conntrack_expect_find_get(&t); + other_exp = nf_ct_expect_find_get(&t); if (other_exp) { - nf_conntrack_unexpect_related(other_exp); - nf_conntrack_expect_put(other_exp); - DEBUGP("success\n"); + nf_ct_unexpect_related(other_exp); + nf_ct_expect_put(other_exp); + pr_debug("success\n"); } else { - DEBUGP("not found!\n"); + pr_debug("not found!\n"); } /* This must be a fresh one. */ @@ -161,9 +153,9 @@ pptp_outbound_pkt(struct sk_buff **pskb, cid_off = offsetof(union pptp_ctrl_union, clrreq.callID); break; default: - DEBUGP("unknown outbound packet 0x%04x:%s\n", msg, - (msg <= PPTP_MSG_MAX)? - pptp_msg_name[msg]:pptp_msg_name[0]); + pr_debug("unknown outbound packet 0x%04x:%s\n", msg, + msg <= PPTP_MSG_MAX ? pptp_msg_name[msg] : + pptp_msg_name[0]); /* fall through */ case PPTP_SET_LINK_INFO: /* only need to NAT in case PAC is behind NAT box */ @@ -179,8 +171,8 @@ pptp_outbound_pkt(struct sk_buff **pskb, /* only OUT_CALL_REQUEST, IN_CALL_REPLY, CALL_CLEAR_REQUEST pass * down to here */ - DEBUGP("altering call id from 0x%04x to 0x%04x\n", - ntohs(REQ_CID(pptpReq, cid_off)), ntohs(new_callid)); + pr_debug("altering call id from 0x%04x to 0x%04x\n", + ntohs(REQ_CID(pptpReq, cid_off)), ntohs(new_callid)); /* mangle packet */ if (nf_nat_mangle_tcp_packet(pskb, ct, ctinfo, @@ -255,8 +247,9 @@ pptp_inbound_pkt(struct sk_buff **pskb, pcid_off = offsetof(union pptp_ctrl_union, setlink.peersCallID); break; default: - DEBUGP("unknown inbound packet %s\n", (msg <= PPTP_MSG_MAX)? - pptp_msg_name[msg]:pptp_msg_name[0]); + pr_debug("unknown inbound packet %s\n", + msg <= PPTP_MSG_MAX ? pptp_msg_name[msg] : + pptp_msg_name[0]); /* fall through */ case PPTP_START_SESSION_REQUEST: case PPTP_START_SESSION_REPLY: @@ -272,8 +265,8 @@ pptp_inbound_pkt(struct sk_buff **pskb, * WAN_ERROR_NOTIFY, CALL_DISCONNECT_NOTIFY pass down here */ /* mangle packet */ - DEBUGP("altering peer call id from 0x%04x to 0x%04x\n", - ntohs(REQ_CID(pptpReq, pcid_off)), ntohs(new_pcid)); + pr_debug("altering peer call id from 0x%04x to 0x%04x\n", + ntohs(REQ_CID(pptpReq, pcid_off)), ntohs(new_pcid)); if (nf_nat_mangle_tcp_packet(pskb, ct, ctinfo, pcid_off + sizeof(struct pptp_pkt_hdr) + diff --git a/net/ipv4/netfilter/nf_nat_proto_gre.c b/net/ipv4/netfilter/nf_nat_proto_gre.c index c3908bc5a709..2e40cc83526a 100644 --- a/net/ipv4/netfilter/nf_nat_proto_gre.c +++ b/net/ipv4/netfilter/nf_nat_proto_gre.c @@ -36,13 +36,6 @@ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Harald Welte <laforge@gnumonks.org>"); MODULE_DESCRIPTION("Netfilter NAT protocol helper module for GRE"); -#if 0 -#define DEBUGP(format, args...) printk(KERN_DEBUG "%s:%s: " format, __FILE__, \ - __FUNCTION__, ## args) -#else -#define DEBUGP(x, args...) -#endif - /* is key in given range between min and max */ static int gre_in_range(const struct nf_conntrack_tuple *tuple, @@ -83,7 +76,7 @@ gre_unique_tuple(struct nf_conntrack_tuple *tuple, keyptr = &tuple->dst.u.gre.key; if (!(range->flags & IP_NAT_RANGE_PROTO_SPECIFIED)) { - DEBUGP("%p: NATing GRE PPTP\n", conntrack); + pr_debug("%p: NATing GRE PPTP\n", conntrack); min = 1; range_size = 0xffff; } else { @@ -91,7 +84,7 @@ gre_unique_tuple(struct nf_conntrack_tuple *tuple, range_size = ntohs(range->max.gre.key) - min + 1; } - DEBUGP("min = %u, range_size = %u\n", min, range_size); + pr_debug("min = %u, range_size = %u\n", min, range_size); for (i = 0; i < range_size; i++, key++) { *keyptr = htons(min + key % range_size); @@ -99,7 +92,7 @@ gre_unique_tuple(struct nf_conntrack_tuple *tuple, return 1; } - DEBUGP("%p: no NAT mapping\n", conntrack); + pr_debug("%p: no NAT mapping\n", conntrack); return 0; } @@ -132,11 +125,11 @@ gre_manip_pkt(struct sk_buff **pskb, unsigned int iphdroff, * Try to behave like "nf_nat_proto_unknown" */ break; case GRE_VERSION_PPTP: - DEBUGP("call_id -> 0x%04x\n", ntohs(tuple->dst.u.gre.key)); + pr_debug("call_id -> 0x%04x\n", ntohs(tuple->dst.u.gre.key)); pgreh->call_id = tuple->dst.u.gre.key; break; default: - DEBUGP("can't nat unknown GRE version\n"); + pr_debug("can't nat unknown GRE version\n"); return 0; } return 1; diff --git a/net/ipv4/netfilter/nf_nat_rule.c b/net/ipv4/netfilter/nf_nat_rule.c index 6740736c5e79..0f45427e5fdc 100644 --- a/net/ipv4/netfilter/nf_nat_rule.c +++ b/net/ipv4/netfilter/nf_nat_rule.c @@ -24,12 +24,6 @@ #include <net/netfilter/nf_nat_core.h> #include <net/netfilter/nf_nat_rule.h> -#if 0 -#define DEBUGP printk -#else -#define DEBUGP(format, args...) -#endif - #define NAT_VALID_HOOKS ((1<<NF_IP_PRE_ROUTING) | (1<<NF_IP_POST_ROUTING) | (1<<NF_IP_LOCAL_OUT)) static struct @@ -140,39 +134,39 @@ static unsigned int ipt_dnat_target(struct sk_buff **pskb, return nf_nat_setup_info(ct, &mr->range[0], hooknum); } -static int ipt_snat_checkentry(const char *tablename, - const void *entry, - const struct xt_target *target, - void *targinfo, - unsigned int hook_mask) +static bool ipt_snat_checkentry(const char *tablename, + const void *entry, + const struct xt_target *target, + void *targinfo, + unsigned int hook_mask) { struct nf_nat_multi_range_compat *mr = targinfo; /* Must be a valid range */ if (mr->rangesize != 1) { printk("SNAT: multiple ranges no longer supported\n"); - return 0; + return false; } - return 1; + return true; } -static int ipt_dnat_checkentry(const char *tablename, - const void *entry, - const struct xt_target *target, - void *targinfo, - unsigned int hook_mask) +static bool ipt_dnat_checkentry(const char *tablename, + const void *entry, + const struct xt_target *target, + void *targinfo, + unsigned int hook_mask) { struct nf_nat_multi_range_compat *mr = targinfo; /* Must be a valid range */ if (mr->rangesize != 1) { printk("DNAT: multiple ranges no longer supported\n"); - return 0; + return false; } - return 1; + return true; } -inline unsigned int +unsigned int alloc_null_binding(struct nf_conn *ct, unsigned int hooknum) { /* Force range to this IP; let proto decide mapping for @@ -186,8 +180,8 @@ alloc_null_binding(struct nf_conn *ct, unsigned int hooknum) struct nf_nat_range range = { IP_NAT_RANGE_MAP_IPS, ip, ip, { 0 }, { 0 } }; - DEBUGP("Allocating NULL binding for %p (%u.%u.%u.%u)\n", - ct, NIPQUAD(ip)); + pr_debug("Allocating NULL binding for %p (%u.%u.%u.%u)\n", + ct, NIPQUAD(ip)); return nf_nat_setup_info(ct, &range, hooknum); } @@ -205,8 +199,8 @@ alloc_null_binding_confirmed(struct nf_conn *ct, unsigned int hooknum) struct nf_nat_range range = { IP_NAT_RANGE_MAP_IPS, ip, ip, { all }, { all } }; - DEBUGP("Allocating NULL binding for confirmed %p (%u.%u.%u.%u)\n", - ct, NIPQUAD(ip)); + pr_debug("Allocating NULL binding for confirmed %p (%u.%u.%u.%u)\n", + ct, NIPQUAD(ip)); return nf_nat_setup_info(ct, &range, hooknum); } @@ -228,7 +222,7 @@ int nf_nat_rule_find(struct sk_buff **pskb, return ret; } -static struct xt_target ipt_snat_reg = { +static struct xt_target ipt_snat_reg __read_mostly = { .name = "SNAT", .target = ipt_snat_target, .targetsize = sizeof(struct nf_nat_multi_range_compat), @@ -238,7 +232,7 @@ static struct xt_target ipt_snat_reg = { .family = AF_INET, }; -static struct xt_target ipt_dnat_reg = { +static struct xt_target ipt_dnat_reg __read_mostly = { .name = "DNAT", .target = ipt_dnat_target, .targetsize = sizeof(struct nf_nat_multi_range_compat), diff --git a/net/ipv4/netfilter/nf_nat_sip.c b/net/ipv4/netfilter/nf_nat_sip.c index fac97cf51ae5..a889ec3ec83a 100644 --- a/net/ipv4/netfilter/nf_nat_sip.c +++ b/net/ipv4/netfilter/nf_nat_sip.c @@ -26,12 +26,6 @@ MODULE_AUTHOR("Christian Hentschel <chentschel@arnet.com.ar>"); MODULE_DESCRIPTION("SIP NAT helper"); MODULE_ALIAS("ip_nat_sip"); -#if 0 -#define DEBUGP printk -#else -#define DEBUGP(format, args...) -#endif - struct addr_map { struct { char src[sizeof("nnn.nnn.nnn.nnn:nnnnn")]; @@ -257,10 +251,12 @@ static unsigned int ip_nat_sdp(struct sk_buff **pskb, __be32 newip; u_int16_t port; - DEBUGP("ip_nat_sdp():\n"); - /* Connection will come from reply */ - newip = ct->tuplehash[!dir].tuple.dst.u3.ip; + if (ct->tuplehash[dir].tuple.src.u3.ip == + ct->tuplehash[!dir].tuple.dst.u3.ip) + newip = exp->tuple.dst.u3.ip; + else + newip = ct->tuplehash[!dir].tuple.dst.u3.ip; exp->saved_ip = exp->tuple.dst.u3.ip; exp->tuple.dst.u3.ip = newip; @@ -274,7 +270,7 @@ static unsigned int ip_nat_sdp(struct sk_buff **pskb, /* Try to get same port: if not, try to change it. */ for (port = ntohs(exp->saved_proto.udp.port); port != 0; port++) { exp->tuple.dst.u.udp.port = htons(port); - if (nf_conntrack_expect_related(exp) == 0) + if (nf_ct_expect_related(exp) == 0) break; } @@ -282,7 +278,7 @@ static unsigned int ip_nat_sdp(struct sk_buff **pskb, return NF_DROP; if (!mangle_sdp(pskb, ctinfo, ct, newip, port, dptr)) { - nf_conntrack_unexpect_related(exp); + nf_ct_unexpect_related(exp); return NF_DROP; } return NF_ACCEPT; diff --git a/net/ipv4/netfilter/nf_nat_snmp_basic.c b/net/ipv4/netfilter/nf_nat_snmp_basic.c index 6e88505d6162..6bfcd3a90f08 100644 --- a/net/ipv4/netfilter/nf_nat_snmp_basic.c +++ b/net/ipv4/netfilter/nf_nat_snmp_basic.c @@ -1276,9 +1276,6 @@ static struct nf_conntrack_helper snmp_helper __read_mostly = { .tuple.src.l3num = AF_INET, .tuple.src.u.udp.port = __constant_htons(SNMP_PORT), .tuple.dst.protonum = IPPROTO_UDP, - .mask.src.l3num = 0xFFFF, - .mask.src.u.udp.port = __constant_htons(0xFFFF), - .mask.dst.protonum = 0xFF, }; static struct nf_conntrack_helper snmp_trap_helper __read_mostly = { @@ -1290,9 +1287,6 @@ static struct nf_conntrack_helper snmp_trap_helper __read_mostly = { .tuple.src.l3num = AF_INET, .tuple.src.u.udp.port = __constant_htons(SNMP_TRAP_PORT), .tuple.dst.protonum = IPPROTO_UDP, - .mask.src.l3num = 0xFFFF, - .mask.src.u.udp.port = __constant_htons(0xFFFF), - .mask.dst.protonum = 0xFF, }; /***************************************************************************** diff --git a/net/ipv4/netfilter/nf_nat_standalone.c b/net/ipv4/netfilter/nf_nat_standalone.c index 55dac36dbc85..332814dac503 100644 --- a/net/ipv4/netfilter/nf_nat_standalone.c +++ b/net/ipv4/netfilter/nf_nat_standalone.c @@ -19,6 +19,7 @@ #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_conntrack_core.h> +#include <net/netfilter/nf_conntrack_extend.h> #include <net/netfilter/nf_nat.h> #include <net/netfilter/nf_nat_rule.h> #include <net/netfilter/nf_nat_protocol.h> @@ -26,12 +27,6 @@ #include <net/netfilter/nf_nat_helper.h> #include <linux/netfilter_ipv4/ip_tables.h> -#if 0 -#define DEBUGP printk -#else -#define DEBUGP(format, args...) -#endif - #ifdef CONFIG_XFRM static void nat_decode_session(struct sk_buff *skb, struct flowi *fl) { @@ -113,8 +108,13 @@ nf_nat_fn(unsigned int hooknum, return NF_ACCEPT; nat = nfct_nat(ct); - if (!nat) - return NF_ACCEPT; + if (!nat) { + nat = nf_ct_ext_add(ct, NF_CT_EXT_NAT, GFP_ATOMIC); + if (nat == NULL) { + pr_debug("failed to add NAT extension\n"); + return NF_ACCEPT; + } + } switch (ctinfo) { case IP_CT_RELATED: @@ -148,9 +148,9 @@ nf_nat_fn(unsigned int hooknum, return ret; } } else - DEBUGP("Already setup manip %s for ct %p\n", - maniptype == IP_NAT_MANIP_SRC ? "SRC" : "DST", - ct); + pr_debug("Already setup manip %s for ct %p\n", + maniptype == IP_NAT_MANIP_SRC ? "SRC" : "DST", + ct); break; default: @@ -264,7 +264,7 @@ nf_nat_adjust(unsigned int hooknum, ct = nf_ct_get(*pskb, &ctinfo); if (ct && test_bit(IPS_SEQ_ADJUST_BIT, &ct->status)) { - DEBUGP("nf_nat_standalone: adjusting sequence number\n"); + pr_debug("nf_nat_standalone: adjusting sequence number\n"); if (!nf_nat_seq_adjust(pskb, ct, ctinfo)) return NF_DROP; } @@ -326,26 +326,10 @@ static struct nf_hook_ops nf_nat_ops[] = { static int __init nf_nat_standalone_init(void) { - int size, ret = 0; + int ret = 0; need_conntrack(); - size = ALIGN(sizeof(struct nf_conn), __alignof__(struct nf_conn_nat)) + - sizeof(struct nf_conn_nat); - ret = nf_conntrack_register_cache(NF_CT_F_NAT, "nf_nat:base", size); - if (ret < 0) { - printk(KERN_ERR "nf_nat_init: Unable to create slab cache\n"); - return ret; - } - - size = ALIGN(size, __alignof__(struct nf_conn_help)) + - sizeof(struct nf_conn_help); - ret = nf_conntrack_register_cache(NF_CT_F_NAT|NF_CT_F_HELP, - "nf_nat:help", size); - if (ret < 0) { - printk(KERN_ERR "nf_nat_init: Unable to create slab cache\n"); - goto cleanup_register_cache; - } #ifdef CONFIG_XFRM BUG_ON(ip_nat_decode_session != NULL); ip_nat_decode_session = nat_decode_session; @@ -360,7 +344,6 @@ static int __init nf_nat_standalone_init(void) printk("nf_nat_init: can't register hooks.\n"); goto cleanup_rule_init; } - nf_nat_module_is_loaded = 1; return ret; cleanup_rule_init: @@ -370,9 +353,6 @@ static int __init nf_nat_standalone_init(void) ip_nat_decode_session = NULL; synchronize_net(); #endif - nf_conntrack_unregister_cache(NF_CT_F_NAT|NF_CT_F_HELP); - cleanup_register_cache: - nf_conntrack_unregister_cache(NF_CT_F_NAT); return ret; } @@ -380,7 +360,6 @@ static void __exit nf_nat_standalone_fini(void) { nf_unregister_hooks(nf_nat_ops, ARRAY_SIZE(nf_nat_ops)); nf_nat_rule_cleanup(); - nf_nat_module_is_loaded = 0; #ifdef CONFIG_XFRM ip_nat_decode_session = NULL; synchronize_net(); diff --git a/net/ipv4/netfilter/nf_nat_tftp.c b/net/ipv4/netfilter/nf_nat_tftp.c index 2566b79de224..04dfeaefec02 100644 --- a/net/ipv4/netfilter/nf_nat_tftp.c +++ b/net/ipv4/netfilter/nf_nat_tftp.c @@ -30,7 +30,7 @@ static unsigned int help(struct sk_buff **pskb, = ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u.udp.port; exp->dir = IP_CT_DIR_REPLY; exp->expectfn = nf_nat_follow_master; - if (nf_conntrack_expect_related(exp) != 0) + if (nf_ct_expect_related(exp) != 0) return NF_DROP; return NF_ACCEPT; } diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 29ca63e81ced..df42b7fb3268 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -101,7 +101,6 @@ #include <net/tcp.h> #include <net/icmp.h> #include <net/xfrm.h> -#include <net/ip_mp_alg.h> #include <net/netevent.h> #include <net/rtnetlink.h> #ifdef CONFIG_SYSCTL @@ -168,7 +167,7 @@ static struct dst_ops ipv4_dst_ops = { #define ECN_OR_COST(class) TC_PRIO_##class -__u8 ip_tos2prio[16] = { +const __u8 ip_tos2prio[16] = { TC_PRIO_BESTEFFORT, ECN_OR_COST(FILLER), TC_PRIO_BESTEFFORT, @@ -495,13 +494,11 @@ static const struct file_operations rt_cpu_seq_fops = { static __inline__ void rt_free(struct rtable *rt) { - multipath_remove(rt); call_rcu_bh(&rt->u.dst.rcu_head, dst_rcu_free); } static __inline__ void rt_drop(struct rtable *rt) { - multipath_remove(rt); ip_rt_put(rt); call_rcu_bh(&rt->u.dst.rcu_head, dst_rcu_free); } @@ -574,52 +571,6 @@ static inline int compare_keys(struct flowi *fl1, struct flowi *fl2) (fl1->iif ^ fl2->iif)) == 0; } -#ifdef CONFIG_IP_ROUTE_MULTIPATH_CACHED -static struct rtable **rt_remove_balanced_route(struct rtable **chain_head, - struct rtable *expentry, - int *removed_count) -{ - int passedexpired = 0; - struct rtable **nextstep = NULL; - struct rtable **rthp = chain_head; - struct rtable *rth; - - if (removed_count) - *removed_count = 0; - - while ((rth = *rthp) != NULL) { - if (rth == expentry) - passedexpired = 1; - - if (((*rthp)->u.dst.flags & DST_BALANCED) != 0 && - compare_keys(&(*rthp)->fl, &expentry->fl)) { - if (*rthp == expentry) { - *rthp = rth->u.dst.rt_next; - continue; - } else { - *rthp = rth->u.dst.rt_next; - rt_free(rth); - if (removed_count) - ++(*removed_count); - } - } else { - if (!((*rthp)->u.dst.flags & DST_BALANCED) && - passedexpired && !nextstep) - nextstep = &rth->u.dst.rt_next; - - rthp = &rth->u.dst.rt_next; - } - } - - rt_free(expentry); - if (removed_count) - ++(*removed_count); - - return nextstep; -} -#endif /* CONFIG_IP_ROUTE_MULTIPATH_CACHED */ - - /* This runs via a timer and thus is always in BH context. */ static void rt_check_expire(unsigned long dummy) { @@ -658,22 +609,8 @@ static void rt_check_expire(unsigned long dummy) } /* Cleanup aged off entries. */ -#ifdef CONFIG_IP_ROUTE_MULTIPATH_CACHED - /* remove all related balanced entries if necessary */ - if (rth->u.dst.flags & DST_BALANCED) { - rthp = rt_remove_balanced_route( - &rt_hash_table[i].chain, - rth, NULL); - if (!rthp) - break; - } else { - *rthp = rth->u.dst.rt_next; - rt_free(rth); - } -#else /* CONFIG_IP_ROUTE_MULTIPATH_CACHED */ *rthp = rth->u.dst.rt_next; rt_free(rth); -#endif /* CONFIG_IP_ROUTE_MULTIPATH_CACHED */ } spin_unlock(rt_hash_lock_addr(i)); @@ -721,9 +658,6 @@ void rt_cache_flush(int delay) if (delay < 0) delay = ip_rt_min_delay; - /* flush existing multipath state*/ - multipath_flush(); - spin_lock_bh(&rt_flush_lock); if (del_timer(&rt_flush_timer) && delay > 0 && rt_deadline) { @@ -842,30 +776,9 @@ static int rt_garbage_collect(void) rthp = &rth->u.dst.rt_next; continue; } -#ifdef CONFIG_IP_ROUTE_MULTIPATH_CACHED - /* remove all related balanced entries - * if necessary - */ - if (rth->u.dst.flags & DST_BALANCED) { - int r; - - rthp = rt_remove_balanced_route( - &rt_hash_table[k].chain, - rth, - &r); - goal -= r; - if (!rthp) - break; - } else { - *rthp = rth->u.dst.rt_next; - rt_free(rth); - goal--; - } -#else /* CONFIG_IP_ROUTE_MULTIPATH_CACHED */ *rthp = rth->u.dst.rt_next; rt_free(rth); goal--; -#endif /* CONFIG_IP_ROUTE_MULTIPATH_CACHED */ } spin_unlock_bh(rt_hash_lock_addr(k)); if (goal <= 0) @@ -939,12 +852,7 @@ restart: spin_lock_bh(rt_hash_lock_addr(hash)); while ((rth = *rthp) != NULL) { -#ifdef CONFIG_IP_ROUTE_MULTIPATH_CACHED - if (!(rth->u.dst.flags & DST_BALANCED) && - compare_keys(&rth->fl, &rt->fl)) { -#else if (compare_keys(&rth->fl, &rt->fl)) { -#endif /* Put it first */ *rthp = rth->u.dst.rt_next; /* @@ -1774,10 +1682,6 @@ static inline int __mkroute_input(struct sk_buff *skb, atomic_set(&rth->u.dst.__refcnt, 1); rth->u.dst.flags= DST_HOST; -#ifdef CONFIG_IP_ROUTE_MULTIPATH_CACHED - if (res->fi->fib_nhs > 1) - rth->u.dst.flags |= DST_BALANCED; -#endif if (IN_DEV_CONF_GET(in_dev, NOPOLICY)) rth->u.dst.flags |= DST_NOPOLICY; if (IN_DEV_CONF_GET(out_dev, NOXFRM)) @@ -1812,11 +1716,11 @@ static inline int __mkroute_input(struct sk_buff *skb, return err; } -static inline int ip_mkroute_input_def(struct sk_buff *skb, - struct fib_result* res, - const struct flowi *fl, - struct in_device *in_dev, - __be32 daddr, __be32 saddr, u32 tos) +static inline int ip_mkroute_input(struct sk_buff *skb, + struct fib_result* res, + const struct flowi *fl, + struct in_device *in_dev, + __be32 daddr, __be32 saddr, u32 tos) { struct rtable* rth = NULL; int err; @@ -1837,63 +1741,6 @@ static inline int ip_mkroute_input_def(struct sk_buff *skb, return rt_intern_hash(hash, rth, (struct rtable**)&skb->dst); } -static inline int ip_mkroute_input(struct sk_buff *skb, - struct fib_result* res, - const struct flowi *fl, - struct in_device *in_dev, - __be32 daddr, __be32 saddr, u32 tos) -{ -#ifdef CONFIG_IP_ROUTE_MULTIPATH_CACHED - struct rtable* rth = NULL, *rtres; - unsigned char hop, hopcount; - int err = -EINVAL; - unsigned int hash; - - if (res->fi) - hopcount = res->fi->fib_nhs; - else - hopcount = 1; - - /* distinguish between multipath and singlepath */ - if (hopcount < 2) - return ip_mkroute_input_def(skb, res, fl, in_dev, daddr, - saddr, tos); - - /* add all alternatives to the routing cache */ - for (hop = 0; hop < hopcount; hop++) { - res->nh_sel = hop; - - /* put reference to previous result */ - if (hop) - ip_rt_put(rtres); - - /* create a routing cache entry */ - err = __mkroute_input(skb, res, in_dev, daddr, saddr, tos, - &rth); - if (err) - return err; - - /* put it into the cache */ - hash = rt_hash(daddr, saddr, fl->iif); - err = rt_intern_hash(hash, rth, &rtres); - if (err) - return err; - - /* forward hop information to multipath impl. */ - multipath_set_nhinfo(rth, - FIB_RES_NETWORK(*res), - FIB_RES_NETMASK(*res), - res->prefixlen, - &FIB_RES_NH(*res)); - } - skb->dst = &rtres->u.dst; - return err; -#else /* CONFIG_IP_ROUTE_MULTIPATH_CACHED */ - return ip_mkroute_input_def(skb, res, fl, in_dev, daddr, saddr, tos); -#endif /* CONFIG_IP_ROUTE_MULTIPATH_CACHED */ -} - - /* * NOTE. We drop all the packets that has local source * addresses, because every properly looped back packet @@ -2211,13 +2058,6 @@ static inline int __mkroute_output(struct rtable **result, atomic_set(&rth->u.dst.__refcnt, 1); rth->u.dst.flags= DST_HOST; -#ifdef CONFIG_IP_ROUTE_MULTIPATH_CACHED - if (res->fi) { - rth->rt_multipath_alg = res->fi->fib_mp_alg; - if (res->fi->fib_nhs > 1) - rth->u.dst.flags |= DST_BALANCED; - } -#endif if (IN_DEV_CONF_GET(in_dev, NOXFRM)) rth->u.dst.flags |= DST_NOXFRM; if (IN_DEV_CONF_GET(in_dev, NOPOLICY)) @@ -2277,12 +2117,12 @@ static inline int __mkroute_output(struct rtable **result, return err; } -static inline int ip_mkroute_output_def(struct rtable **rp, - struct fib_result* res, - const struct flowi *fl, - const struct flowi *oldflp, - struct net_device *dev_out, - unsigned flags) +static inline int ip_mkroute_output(struct rtable **rp, + struct fib_result* res, + const struct flowi *fl, + const struct flowi *oldflp, + struct net_device *dev_out, + unsigned flags) { struct rtable *rth = NULL; int err = __mkroute_output(&rth, res, fl, oldflp, dev_out, flags); @@ -2295,68 +2135,6 @@ static inline int ip_mkroute_output_def(struct rtable **rp, return err; } -static inline int ip_mkroute_output(struct rtable** rp, - struct fib_result* res, - const struct flowi *fl, - const struct flowi *oldflp, - struct net_device *dev_out, - unsigned flags) -{ -#ifdef CONFIG_IP_ROUTE_MULTIPATH_CACHED - unsigned char hop; - unsigned hash; - int err = -EINVAL; - struct rtable *rth = NULL; - - if (res->fi && res->fi->fib_nhs > 1) { - unsigned char hopcount = res->fi->fib_nhs; - - for (hop = 0; hop < hopcount; hop++) { - struct net_device *dev2nexthop; - - res->nh_sel = hop; - - /* hold a work reference to the output device */ - dev2nexthop = FIB_RES_DEV(*res); - dev_hold(dev2nexthop); - - /* put reference to previous result */ - if (hop) - ip_rt_put(*rp); - - err = __mkroute_output(&rth, res, fl, oldflp, - dev2nexthop, flags); - - if (err != 0) - goto cleanup; - - hash = rt_hash(oldflp->fl4_dst, oldflp->fl4_src, - oldflp->oif); - err = rt_intern_hash(hash, rth, rp); - - /* forward hop information to multipath impl. */ - multipath_set_nhinfo(rth, - FIB_RES_NETWORK(*res), - FIB_RES_NETMASK(*res), - res->prefixlen, - &FIB_RES_NH(*res)); - cleanup: - /* release work reference to output device */ - dev_put(dev2nexthop); - - if (err != 0) - return err; - } - return err; - } else { - return ip_mkroute_output_def(rp, res, fl, oldflp, dev_out, - flags); - } -#else /* CONFIG_IP_ROUTE_MULTIPATH_CACHED */ - return ip_mkroute_output_def(rp, res, fl, oldflp, dev_out, flags); -#endif -} - /* * Major route resolver routine. */ @@ -2570,17 +2348,6 @@ int __ip_route_output_key(struct rtable **rp, const struct flowi *flp) rth->fl.mark == flp->mark && !((rth->fl.fl4_tos ^ flp->fl4_tos) & (IPTOS_RT_MASK | RTO_ONLINK))) { - - /* check for multipath routes and choose one if - * necessary - */ - if (multipath_select_route(flp, rth, rp)) { - dst_hold(&(*rp)->u.dst); - RT_CACHE_STAT_INC(out_hit); - rcu_read_unlock_bh(); - return 0; - } - rth->u.dst.lastuse = jiffies; dst_hold(&rth->u.dst); rth->u.dst.__use++; @@ -2729,10 +2496,6 @@ static int rt_fill_info(struct sk_buff *skb, u32 pid, u32 seq, int event, if (rt->u.dst.tclassid) NLA_PUT_U32(skb, RTA_FLOW, rt->u.dst.tclassid); #endif -#ifdef CONFIG_IP_ROUTE_MULTIPATH_CACHED - if (rt->rt_multipath_alg != IP_MP_ALG_NONE) - NLA_PUT_U32(skb, RTA_MP_ALGO, rt->rt_multipath_alg); -#endif if (rt->fl.iif) NLA_PUT_BE32(skb, RTA_PREFSRC, rt->rt_spec_dst); else if (rt->rt_src != rt->fl.fl4_src) @@ -3204,7 +2967,7 @@ int __init ip_rt_init(void) ipv4_dst_ops.kmem_cachep = kmem_cache_create("ip_dst_cache", sizeof(struct rtable), 0, - SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL, NULL); + SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL); ipv4_dst_blackhole_ops.kmem_cachep = ipv4_dst_ops.kmem_cachep; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 450f44bb2c8e..da4c0b6ab79a 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1116,6 +1116,7 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, long timeo; struct task_struct *user_recv = NULL; int copied_early = 0; + struct sk_buff *skb; lock_sock(sk); @@ -1142,16 +1143,26 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, #ifdef CONFIG_NET_DMA tp->ucopy.dma_chan = NULL; preempt_disable(); - if ((len > sysctl_tcp_dma_copybreak) && !(flags & MSG_PEEK) && - !sysctl_tcp_low_latency && __get_cpu_var(softnet_data).net_dma) { - preempt_enable_no_resched(); - tp->ucopy.pinned_list = dma_pin_iovec_pages(msg->msg_iov, len); - } else - preempt_enable_no_resched(); + skb = skb_peek_tail(&sk->sk_receive_queue); + { + int available = 0; + + if (skb) + available = TCP_SKB_CB(skb)->seq + skb->len - (*seq); + if ((available < target) && + (len > sysctl_tcp_dma_copybreak) && !(flags & MSG_PEEK) && + !sysctl_tcp_low_latency && + __get_cpu_var(softnet_data).net_dma) { + preempt_enable_no_resched(); + tp->ucopy.pinned_list = + dma_pin_iovec_pages(msg->msg_iov, len); + } else { + preempt_enable_no_resched(); + } + } #endif do { - struct sk_buff *skb; u32 offset; /* Are we at urgent data? Stop if we have read anything or have SIGURG pending. */ @@ -1439,7 +1450,6 @@ skip_copy: #ifdef CONFIG_NET_DMA if (tp->ucopy.dma_chan) { - struct sk_buff *skb; dma_cookie_t done, used; dma_async_memcpy_issue_pending(tp->ucopy.dma_chan); @@ -2420,7 +2430,7 @@ void __init tcp_init(void) tcp_hashinfo.bind_bucket_cachep = kmem_cache_create("tcp_bind_bucket", sizeof(struct inet_bind_bucket), 0, - SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL, NULL); + SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL); /* Size and allocate the main established and bind bucket * hash tables. diff --git a/net/ipv4/tcp_bic.c b/net/ipv4/tcp_bic.c index dd9ef65ad3ff..519de091a94d 100644 --- a/net/ipv4/tcp_bic.c +++ b/net/ipv4/tcp_bic.c @@ -137,7 +137,7 @@ static inline void bictcp_update(struct bictcp *ca, u32 cwnd) } static void bictcp_cong_avoid(struct sock *sk, u32 ack, - u32 seq_rtt, u32 in_flight, int data_acked) + u32 in_flight, int data_acked) { struct tcp_sock *tp = tcp_sk(sk); struct bictcp *ca = inet_csk_ca(sk); diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c index 1260e52ad772..55fca1820c34 100644 --- a/net/ipv4/tcp_cong.c +++ b/net/ipv4/tcp_cong.c @@ -324,8 +324,7 @@ EXPORT_SYMBOL_GPL(tcp_slow_start); /* This is Jacobson's slow start and congestion avoidance. * SIGCOMM '88, p. 328. */ -void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 rtt, u32 in_flight, - int flag) +void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 in_flight, int flag) { struct tcp_sock *tp = tcp_sk(sk); diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c index ebfaac2f9f46..d17da30d82d6 100644 --- a/net/ipv4/tcp_cubic.c +++ b/net/ipv4/tcp_cubic.c @@ -270,7 +270,7 @@ static inline void measure_delay(struct sock *sk) } static void bictcp_cong_avoid(struct sock *sk, u32 ack, - u32 seq_rtt, u32 in_flight, int data_acked) + u32 in_flight, int data_acked) { struct tcp_sock *tp = tcp_sk(sk); struct bictcp *ca = inet_csk_ca(sk); diff --git a/net/ipv4/tcp_highspeed.c b/net/ipv4/tcp_highspeed.c index 43d624e5043c..14a073d8b60f 100644 --- a/net/ipv4/tcp_highspeed.c +++ b/net/ipv4/tcp_highspeed.c @@ -109,7 +109,7 @@ static void hstcp_init(struct sock *sk) tp->snd_cwnd_clamp = min_t(u32, tp->snd_cwnd_clamp, 0xffffffff/128); } -static void hstcp_cong_avoid(struct sock *sk, u32 adk, u32 rtt, +static void hstcp_cong_avoid(struct sock *sk, u32 adk, u32 in_flight, int data_acked) { struct tcp_sock *tp = tcp_sk(sk); diff --git a/net/ipv4/tcp_htcp.c b/net/ipv4/tcp_htcp.c index 4ba4a7ae0a85..08a02e6045c9 100644 --- a/net/ipv4/tcp_htcp.c +++ b/net/ipv4/tcp_htcp.c @@ -225,7 +225,7 @@ static u32 htcp_recalc_ssthresh(struct sock *sk) return max((tp->snd_cwnd * ca->beta) >> 7, 2U); } -static void htcp_cong_avoid(struct sock *sk, u32 ack, u32 rtt, +static void htcp_cong_avoid(struct sock *sk, u32 ack, u32 in_flight, int data_acked) { struct tcp_sock *tp = tcp_sk(sk); diff --git a/net/ipv4/tcp_hybla.c b/net/ipv4/tcp_hybla.c index e5be35117223..b3e55cf56171 100644 --- a/net/ipv4/tcp_hybla.c +++ b/net/ipv4/tcp_hybla.c @@ -85,7 +85,7 @@ static inline u32 hybla_fraction(u32 odds) * o Give cwnd a new value based on the model proposed * o remember increments <1 */ -static void hybla_cong_avoid(struct sock *sk, u32 ack, u32 rtt, +static void hybla_cong_avoid(struct sock *sk, u32 ack, u32 in_flight, int flag) { struct tcp_sock *tp = tcp_sk(sk); @@ -103,7 +103,7 @@ static void hybla_cong_avoid(struct sock *sk, u32 ack, u32 rtt, return; if (!ca->hybla_en) - return tcp_reno_cong_avoid(sk, ack, rtt, in_flight, flag); + return tcp_reno_cong_avoid(sk, ack, in_flight, flag); if (ca->rho == 0) hybla_recalc_param(sk); diff --git a/net/ipv4/tcp_illinois.c b/net/ipv4/tcp_illinois.c index b2b2256d3b84..cc5de6f69d46 100644 --- a/net/ipv4/tcp_illinois.c +++ b/net/ipv4/tcp_illinois.c @@ -258,7 +258,7 @@ static void tcp_illinois_state(struct sock *sk, u8 new_state) /* * Increase window in response to successful acknowledgment. */ -static void tcp_illinois_cong_avoid(struct sock *sk, u32 ack, u32 rtt, +static void tcp_illinois_cong_avoid(struct sock *sk, u32 ack, u32 in_flight, int flag) { struct tcp_sock *tp = tcp_sk(sk); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 69f9f1ef3ef6..fec8a7a4dbaf 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -1398,7 +1398,9 @@ static void tcp_enter_frto_loss(struct sock *sk, int allowed_segments, int flag) * waiting for the first ACK and did not get it)... */ if ((tp->frto_counter == 1) && !(flag&FLAG_DATA_ACKED)) { - tp->retrans_out += tcp_skb_pcount(skb); + /* For some reason this R-bit might get cleared? */ + if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS) + tp->retrans_out += tcp_skb_pcount(skb); /* ...enter this if branch just for the first segment */ flag |= FLAG_DATA_ACKED; } else { @@ -2321,11 +2323,11 @@ static inline void tcp_ack_update_rtt(struct sock *sk, const int flag, tcp_ack_no_tstamp(sk, seq_rtt, flag); } -static void tcp_cong_avoid(struct sock *sk, u32 ack, u32 rtt, +static void tcp_cong_avoid(struct sock *sk, u32 ack, u32 in_flight, int good) { const struct inet_connection_sock *icsk = inet_csk(sk); - icsk->icsk_ca_ops->cong_avoid(sk, ack, rtt, in_flight, good); + icsk->icsk_ca_ops->cong_avoid(sk, ack, in_flight, good); tcp_sk(sk)->snd_cwnd_stamp = tcp_time_stamp; } @@ -2824,11 +2826,11 @@ static int tcp_ack(struct sock *sk, struct sk_buff *skb, int flag) /* Advance CWND, if state allows this. */ if ((flag & FLAG_DATA_ACKED) && !frto_cwnd && tcp_may_raise_cwnd(sk, flag)) - tcp_cong_avoid(sk, ack, seq_rtt, prior_in_flight, 0); + tcp_cong_avoid(sk, ack, prior_in_flight, 0); tcp_fastretrans_alert(sk, prior_snd_una, prior_packets, flag); } else { if ((flag & FLAG_DATA_ACKED) && !frto_cwnd) - tcp_cong_avoid(sk, ack, seq_rtt, prior_in_flight, 1); + tcp_cong_avoid(sk, ack, prior_in_flight, 1); } if ((flag & FLAG_FORWARD_PROGRESS) || !(flag&FLAG_NOT_DUP)) diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 354721d67f69..3f5f7423b95c 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2045,10 +2045,7 @@ static void *established_get_first(struct seq_file *seq) struct hlist_node *node; struct inet_timewait_sock *tw; - /* We can reschedule _before_ having picked the target: */ - cond_resched_softirq(); - - read_lock(&tcp_hashinfo.ehash[st->bucket].lock); + read_lock_bh(&tcp_hashinfo.ehash[st->bucket].lock); sk_for_each(sk, node, &tcp_hashinfo.ehash[st->bucket].chain) { if (sk->sk_family != st->family) { continue; @@ -2065,7 +2062,7 @@ static void *established_get_first(struct seq_file *seq) rc = tw; goto out; } - read_unlock(&tcp_hashinfo.ehash[st->bucket].lock); + read_unlock_bh(&tcp_hashinfo.ehash[st->bucket].lock); st->state = TCP_SEQ_STATE_ESTABLISHED; } out: @@ -2092,14 +2089,11 @@ get_tw: cur = tw; goto out; } - read_unlock(&tcp_hashinfo.ehash[st->bucket].lock); + read_unlock_bh(&tcp_hashinfo.ehash[st->bucket].lock); st->state = TCP_SEQ_STATE_ESTABLISHED; - /* We can reschedule between buckets: */ - cond_resched_softirq(); - if (++st->bucket < tcp_hashinfo.ehash_size) { - read_lock(&tcp_hashinfo.ehash[st->bucket].lock); + read_lock_bh(&tcp_hashinfo.ehash[st->bucket].lock); sk = sk_head(&tcp_hashinfo.ehash[st->bucket].chain); } else { cur = NULL; @@ -2144,7 +2138,6 @@ static void *tcp_get_idx(struct seq_file *seq, loff_t pos) if (!rc) { inet_listen_unlock(&tcp_hashinfo); - local_bh_disable(); st->state = TCP_SEQ_STATE_ESTABLISHED; rc = established_get_idx(seq, pos); } @@ -2177,7 +2170,6 @@ static void *tcp_seq_next(struct seq_file *seq, void *v, loff_t *pos) rc = listening_get_next(seq, v); if (!rc) { inet_listen_unlock(&tcp_hashinfo); - local_bh_disable(); st->state = TCP_SEQ_STATE_ESTABLISHED; rc = established_get_first(seq); } @@ -2209,8 +2201,7 @@ static void tcp_seq_stop(struct seq_file *seq, void *v) case TCP_SEQ_STATE_TIME_WAIT: case TCP_SEQ_STATE_ESTABLISHED: if (v) - read_unlock(&tcp_hashinfo.ehash[st->bucket].lock); - local_bh_enable(); + read_unlock_bh(&tcp_hashinfo.ehash[st->bucket].lock); break; } } diff --git a/net/ipv4/tcp_lp.c b/net/ipv4/tcp_lp.c index e49836ce012e..80e140e3ec2d 100644 --- a/net/ipv4/tcp_lp.c +++ b/net/ipv4/tcp_lp.c @@ -115,13 +115,12 @@ static void tcp_lp_init(struct sock *sk) * Will only call newReno CA when away from inference. * From TCP-LP's paper, this will be handled in additive increasement. */ -static void tcp_lp_cong_avoid(struct sock *sk, u32 ack, u32 rtt, u32 in_flight, - int flag) +static void tcp_lp_cong_avoid(struct sock *sk, u32 ack, u32 in_flight, int flag) { struct lp *lp = inet_csk_ca(sk); if (!(lp->flag & LP_WITHIN_INF)) - tcp_reno_cong_avoid(sk, ack, rtt, in_flight, flag); + tcp_reno_cong_avoid(sk, ack, in_flight, flag); } /** diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 53232dd6fb48..666d8a58d14a 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -699,6 +699,14 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len, unsigned int mss tp->fackets_out -= diff; if ((int)tp->fackets_out < 0) tp->fackets_out = 0; + /* SACK fastpath might overwrite it unless dealt with */ + if (tp->fastpath_skb_hint != NULL && + after(TCP_SKB_CB(tp->fastpath_skb_hint)->seq, + TCP_SKB_CB(skb)->seq)) { + tp->fastpath_cnt_hint -= diff; + if ((int)tp->fastpath_cnt_hint < 0) + tp->fastpath_cnt_hint = 0; + } } } @@ -1607,7 +1615,7 @@ u32 __tcp_select_window(struct sock *sk) if (window <= free_space - mss || window > free_space) window = (free_space/mss)*mss; else if (mss == full_space && - free_space > window + full_space/2) + free_space > window + full_space/2) window = free_space; } diff --git a/net/ipv4/tcp_probe.c b/net/ipv4/tcp_probe.c index d9323dfff826..b76398d1b454 100644 --- a/net/ipv4/tcp_probe.c +++ b/net/ipv4/tcp_probe.c @@ -6,8 +6,7 @@ * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. + * the Free Software Foundation; either version 2 of the License. * * This program is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of @@ -25,23 +24,22 @@ #include <linux/tcp.h> #include <linux/proc_fs.h> #include <linux/module.h> -#include <linux/kfifo.h> #include <linux/ktime.h> #include <linux/time.h> -#include <linux/vmalloc.h> #include <net/tcp.h> MODULE_AUTHOR("Stephen Hemminger <shemminger@linux-foundation.org>"); MODULE_DESCRIPTION("TCP cwnd snooper"); MODULE_LICENSE("GPL"); +MODULE_VERSION("1.1"); static int port __read_mostly = 0; MODULE_PARM_DESC(port, "Port to match (0=all)"); module_param(port, int, 0); -static int bufsize __read_mostly = 64*1024; -MODULE_PARM_DESC(bufsize, "Log buffer size (default 64k)"); +static int bufsize __read_mostly = 4096; +MODULE_PARM_DESC(bufsize, "Log buffer size in packets (4096)"); module_param(bufsize, int, 0); static int full __read_mostly; @@ -50,39 +48,38 @@ module_param(full, int, 0); static const char procname[] = "tcpprobe"; -struct { - struct kfifo *fifo; +struct tcp_log { + ktime_t tstamp; + __be32 saddr, daddr; + __be16 sport, dport; + u16 length; + u32 snd_nxt; + u32 snd_una; + u32 snd_wnd; + u32 snd_cwnd; + u32 ssthresh; + u32 srtt; +}; + +static struct { spinlock_t lock; wait_queue_head_t wait; ktime_t start; u32 lastcwnd; -} tcpw; -/* - * Print to log with timestamps. - * FIXME: causes an extra copy - */ -static void printl(const char *fmt, ...) - __attribute__ ((format (printf, 1, 2))); + unsigned long head, tail; + struct tcp_log *log; +} tcp_probe; + -static void printl(const char *fmt, ...) +static inline int tcp_probe_used(void) { - va_list args; - int len; - struct timespec tv; - char tbuf[256]; - - va_start(args, fmt); - /* want monotonic time since start of tcp_probe */ - tv = ktime_to_timespec(ktime_sub(ktime_get(), tcpw.start)); - - len = sprintf(tbuf, "%lu.%09lu ", - (unsigned long) tv.tv_sec, (unsigned long) tv.tv_nsec); - len += vscnprintf(tbuf+len, sizeof(tbuf)-len, fmt, args); - va_end(args); - - kfifo_put(tcpw.fifo, tbuf, len); - wake_up(&tcpw.wait); + return (tcp_probe.head - tcp_probe.tail) % bufsize; +} + +static inline int tcp_probe_avail(void) +{ + return bufsize - tcp_probe_used(); } /* @@ -97,63 +94,118 @@ static int jtcp_rcv_established(struct sock *sk, struct sk_buff *skb, /* Only update if port matches */ if ((port == 0 || ntohs(inet->dport) == port || ntohs(inet->sport) == port) - && (full || tp->snd_cwnd != tcpw.lastcwnd)) { - printl("%d.%d.%d.%d:%u %d.%d.%d.%d:%u %d %#x %#x %u %u %u %u\n", - NIPQUAD(inet->saddr), ntohs(inet->sport), - NIPQUAD(inet->daddr), ntohs(inet->dport), - skb->len, tp->snd_nxt, tp->snd_una, - tp->snd_cwnd, tcp_current_ssthresh(sk), - tp->snd_wnd, tp->srtt >> 3); - tcpw.lastcwnd = tp->snd_cwnd; + && (full || tp->snd_cwnd != tcp_probe.lastcwnd)) { + + spin_lock(&tcp_probe.lock); + /* If log fills, just silently drop */ + if (tcp_probe_avail() > 1) { + struct tcp_log *p = tcp_probe.log + tcp_probe.head; + + p->tstamp = ktime_get(); + p->saddr = inet->saddr; + p->sport = inet->sport; + p->daddr = inet->daddr; + p->dport = inet->dport; + p->length = skb->len; + p->snd_nxt = tp->snd_nxt; + p->snd_una = tp->snd_una; + p->snd_cwnd = tp->snd_cwnd; + p->snd_wnd = tp->snd_wnd; + p->ssthresh = tcp_current_ssthresh(sk); + p->srtt = tp->srtt >> 3; + + tcp_probe.head = (tcp_probe.head + 1) % bufsize; + } + tcp_probe.lastcwnd = tp->snd_cwnd; + spin_unlock(&tcp_probe.lock); + + wake_up(&tcp_probe.wait); } jprobe_return(); return 0; } -static struct jprobe tcp_probe = { +static struct jprobe tcp_jprobe = { .kp = { .symbol_name = "tcp_rcv_established", }, - .entry = JPROBE_ENTRY(jtcp_rcv_established), + .entry = jtcp_rcv_established, }; - static int tcpprobe_open(struct inode * inode, struct file * file) { - kfifo_reset(tcpw.fifo); - tcpw.start = ktime_get(); + /* Reset (empty) log */ + spin_lock_bh(&tcp_probe.lock); + tcp_probe.head = tcp_probe.tail = 0; + tcp_probe.start = ktime_get(); + spin_unlock_bh(&tcp_probe.lock); + return 0; } +static int tcpprobe_sprint(char *tbuf, int n) +{ + const struct tcp_log *p + = tcp_probe.log + tcp_probe.tail % bufsize; + struct timespec tv + = ktime_to_timespec(ktime_sub(p->tstamp, tcp_probe.start)); + + return snprintf(tbuf, n, + "%lu.%09lu %d.%d.%d.%d:%u %d.%d.%d.%d:%u" + " %d %#x %#x %u %u %u %u\n", + (unsigned long) tv.tv_sec, + (unsigned long) tv.tv_nsec, + NIPQUAD(p->saddr), ntohs(p->sport), + NIPQUAD(p->daddr), ntohs(p->dport), + p->length, p->snd_nxt, p->snd_una, + p->snd_cwnd, p->ssthresh, p->snd_wnd, p->srtt); +} + static ssize_t tcpprobe_read(struct file *file, char __user *buf, size_t len, loff_t *ppos) { int error = 0, cnt = 0; - unsigned char *tbuf; if (!buf || len < 0) return -EINVAL; - if (len == 0) - return 0; + while (cnt < len) { + char tbuf[128]; + int width; + + /* Wait for data in buffer */ + error = wait_event_interruptible(tcp_probe.wait, + tcp_probe_used() > 0); + if (error) + break; - tbuf = vmalloc(len); - if (!tbuf) - return -ENOMEM; + spin_lock_bh(&tcp_probe.lock); + if (tcp_probe.head == tcp_probe.tail) { + /* multiple readers race? */ + spin_unlock_bh(&tcp_probe.lock); + continue; + } - error = wait_event_interruptible(tcpw.wait, - __kfifo_len(tcpw.fifo) != 0); - if (error) - goto out_free; + width = tcpprobe_sprint(tbuf, sizeof(tbuf)); - cnt = kfifo_get(tcpw.fifo, tbuf, len); - error = copy_to_user(buf, tbuf, cnt); + if (width < len) + tcp_probe.tail = (tcp_probe.tail + 1) % bufsize; -out_free: - vfree(tbuf); + spin_unlock_bh(&tcp_probe.lock); + + /* if record greater than space available + return partial buffer (so far) */ + if (width >= len) + break; + + error = copy_to_user(buf + cnt, tbuf, width); + if (error) + break; + cnt += width; + } - return error ? error : cnt; + return cnt == 0 ? error : cnt; } static const struct file_operations tcpprobe_fops = { @@ -166,34 +218,37 @@ static __init int tcpprobe_init(void) { int ret = -ENOMEM; - init_waitqueue_head(&tcpw.wait); - spin_lock_init(&tcpw.lock); - tcpw.fifo = kfifo_alloc(bufsize, GFP_KERNEL, &tcpw.lock); - if (IS_ERR(tcpw.fifo)) - return PTR_ERR(tcpw.fifo); + init_waitqueue_head(&tcp_probe.wait); + spin_lock_init(&tcp_probe.lock); + + if (bufsize < 0) + return -EINVAL; + + tcp_probe.log = kcalloc(sizeof(struct tcp_log), bufsize, GFP_KERNEL); + if (!tcp_probe.log) + goto err0; if (!proc_net_fops_create(procname, S_IRUSR, &tcpprobe_fops)) goto err0; - ret = register_jprobe(&tcp_probe); + ret = register_jprobe(&tcp_jprobe); if (ret) goto err1; - pr_info("TCP watch registered (port=%d)\n", port); + pr_info("TCP probe registered (port=%d)\n", port); return 0; err1: proc_net_remove(procname); err0: - kfifo_free(tcpw.fifo); + kfree(tcp_probe.log); return ret; } module_init(tcpprobe_init); static __exit void tcpprobe_exit(void) { - kfifo_free(tcpw.fifo); proc_net_remove(procname); - unregister_jprobe(&tcp_probe); - + unregister_jprobe(&tcp_jprobe); + kfree(tcp_probe.log); } module_exit(tcpprobe_exit); diff --git a/net/ipv4/tcp_scalable.c b/net/ipv4/tcp_scalable.c index 4624501e9680..be27a33a1c68 100644 --- a/net/ipv4/tcp_scalable.c +++ b/net/ipv4/tcp_scalable.c @@ -15,7 +15,7 @@ #define TCP_SCALABLE_AI_CNT 50U #define TCP_SCALABLE_MD_SCALE 3 -static void tcp_scalable_cong_avoid(struct sock *sk, u32 ack, u32 rtt, +static void tcp_scalable_cong_avoid(struct sock *sk, u32 ack, u32 in_flight, int flag) { struct tcp_sock *tp = tcp_sk(sk); diff --git a/net/ipv4/tcp_vegas.c b/net/ipv4/tcp_vegas.c index e218a51ceced..914e0307f7af 100644 --- a/net/ipv4/tcp_vegas.c +++ b/net/ipv4/tcp_vegas.c @@ -163,13 +163,13 @@ void tcp_vegas_cwnd_event(struct sock *sk, enum tcp_ca_event event) EXPORT_SYMBOL_GPL(tcp_vegas_cwnd_event); static void tcp_vegas_cong_avoid(struct sock *sk, u32 ack, - u32 seq_rtt, u32 in_flight, int flag) + u32 in_flight, int flag) { struct tcp_sock *tp = tcp_sk(sk); struct vegas *vegas = inet_csk_ca(sk); if (!vegas->doing_vegas_now) - return tcp_reno_cong_avoid(sk, ack, seq_rtt, in_flight, flag); + return tcp_reno_cong_avoid(sk, ack, in_flight, flag); /* The key players are v_beg_snd_una and v_beg_snd_nxt. * @@ -228,7 +228,7 @@ static void tcp_vegas_cong_avoid(struct sock *sk, u32 ack, /* We don't have enough RTT samples to do the Vegas * calculation, so we'll behave like Reno. */ - tcp_reno_cong_avoid(sk, ack, seq_rtt, in_flight, flag); + tcp_reno_cong_avoid(sk, ack, in_flight, flag); } else { u32 rtt, target_cwnd, diff; diff --git a/net/ipv4/tcp_veno.c b/net/ipv4/tcp_veno.c index ec854cc5fad5..7a55ddf86032 100644 --- a/net/ipv4/tcp_veno.c +++ b/net/ipv4/tcp_veno.c @@ -115,13 +115,13 @@ static void tcp_veno_cwnd_event(struct sock *sk, enum tcp_ca_event event) } static void tcp_veno_cong_avoid(struct sock *sk, u32 ack, - u32 seq_rtt, u32 in_flight, int flag) + u32 in_flight, int flag) { struct tcp_sock *tp = tcp_sk(sk); struct veno *veno = inet_csk_ca(sk); if (!veno->doing_veno_now) - return tcp_reno_cong_avoid(sk, ack, seq_rtt, in_flight, flag); + return tcp_reno_cong_avoid(sk, ack, in_flight, flag); /* limited by applications */ if (!tcp_is_cwnd_limited(sk, in_flight)) @@ -132,7 +132,7 @@ static void tcp_veno_cong_avoid(struct sock *sk, u32 ack, /* We don't have enough rtt samples to do the Veno * calculation, so we'll behave like Reno. */ - tcp_reno_cong_avoid(sk, ack, seq_rtt, in_flight, flag); + tcp_reno_cong_avoid(sk, ack, in_flight, flag); } else { u32 rtt, target_cwnd; diff --git a/net/ipv4/tcp_yeah.c b/net/ipv4/tcp_yeah.c index 545ed237ab53..c04b7c6ec702 100644 --- a/net/ipv4/tcp_yeah.c +++ b/net/ipv4/tcp_yeah.c @@ -70,7 +70,7 @@ static void tcp_yeah_pkts_acked(struct sock *sk, u32 pkts_acked, ktime_t last) } static void tcp_yeah_cong_avoid(struct sock *sk, u32 ack, - u32 seq_rtt, u32 in_flight, int flag) + u32 in_flight, int flag) { struct tcp_sock *tp = tcp_sk(sk); struct yeah *yeah = inet_csk_ca(sk); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index facb7e29304e..28355350fb62 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -70,6 +70,7 @@ * Alexey Kuznetsov: allow both IPv4 and IPv6 sockets to bind * a single port at the same time. * Derek Atkins <derek@ihtfp.com>: Add Encapulation Support + * James Chapman : Add L2TP encapsulation type. * * * This program is free software; you can redistribute it and/or @@ -919,104 +920,6 @@ int udp_disconnect(struct sock *sk, int flags) return 0; } -/* return: - * 1 if the UDP system should process it - * 0 if we should drop this packet - * -1 if it should get processed by xfrm4_rcv_encap - */ -static int udp_encap_rcv(struct sock * sk, struct sk_buff *skb) -{ -#ifndef CONFIG_XFRM - return 1; -#else - struct udp_sock *up = udp_sk(sk); - struct udphdr *uh; - struct iphdr *iph; - int iphlen, len; - - __u8 *udpdata; - __be32 *udpdata32; - __u16 encap_type = up->encap_type; - - /* if we're overly short, let UDP handle it */ - len = skb->len - sizeof(struct udphdr); - if (len <= 0) - return 1; - - /* if this is not encapsulated socket, then just return now */ - if (!encap_type) - return 1; - - /* If this is a paged skb, make sure we pull up - * whatever data we need to look at. */ - if (!pskb_may_pull(skb, sizeof(struct udphdr) + min(len, 8))) - return 1; - - /* Now we can get the pointers */ - uh = udp_hdr(skb); - udpdata = (__u8 *)uh + sizeof(struct udphdr); - udpdata32 = (__be32 *)udpdata; - - switch (encap_type) { - default: - case UDP_ENCAP_ESPINUDP: - /* Check if this is a keepalive packet. If so, eat it. */ - if (len == 1 && udpdata[0] == 0xff) { - return 0; - } else if (len > sizeof(struct ip_esp_hdr) && udpdata32[0] != 0) { - /* ESP Packet without Non-ESP header */ - len = sizeof(struct udphdr); - } else - /* Must be an IKE packet.. pass it through */ - return 1; - break; - case UDP_ENCAP_ESPINUDP_NON_IKE: - /* Check if this is a keepalive packet. If so, eat it. */ - if (len == 1 && udpdata[0] == 0xff) { - return 0; - } else if (len > 2 * sizeof(u32) + sizeof(struct ip_esp_hdr) && - udpdata32[0] == 0 && udpdata32[1] == 0) { - - /* ESP Packet with Non-IKE marker */ - len = sizeof(struct udphdr) + 2 * sizeof(u32); - } else - /* Must be an IKE packet.. pass it through */ - return 1; - break; - } - - /* At this point we are sure that this is an ESPinUDP packet, - * so we need to remove 'len' bytes from the packet (the UDP - * header and optional ESP marker bytes) and then modify the - * protocol to ESP, and then call into the transform receiver. - */ - if (skb_cloned(skb) && pskb_expand_head(skb, 0, 0, GFP_ATOMIC)) - return 0; - - /* Now we can update and verify the packet length... */ - iph = ip_hdr(skb); - iphlen = iph->ihl << 2; - iph->tot_len = htons(ntohs(iph->tot_len) - len); - if (skb->len < iphlen + len) { - /* packet is too small!?! */ - return 0; - } - - /* pull the data buffer up to the ESP header and set the - * transport header to point to ESP. Keep UDP on the stack - * for later. - */ - __skb_pull(skb, len); - skb_reset_transport_header(skb); - - /* modify the protocol (it's ESP!) */ - iph->protocol = IPPROTO_ESP; - - /* and let the caller know to send this into the ESP processor... */ - return -1; -#endif -} - /* returns: * -1: error * 0: success @@ -1039,28 +942,28 @@ int udp_queue_rcv_skb(struct sock * sk, struct sk_buff *skb) if (up->encap_type) { /* - * This is an encapsulation socket, so let's see if this is - * an encapsulated packet. - * If it's a keepalive packet, then just eat it. - * If it's an encapsulateed packet, then pass it to the - * IPsec xfrm input and return the response - * appropriately. Otherwise, just fall through and - * pass this up the UDP socket. + * This is an encapsulation socket so pass the skb to + * the socket's udp_encap_rcv() hook. Otherwise, just + * fall through and pass this up the UDP socket. + * up->encap_rcv() returns the following value: + * =0 if skb was successfully passed to the encap + * handler or was discarded by it. + * >0 if skb should be passed on to UDP. + * <0 if skb should be resubmitted as proto -N */ - int ret; - ret = udp_encap_rcv(sk, skb); - if (ret == 0) { - /* Eat the packet .. */ - kfree_skb(skb); - return 0; - } - if (ret < 0) { - /* process the ESP packet */ - ret = xfrm4_rcv_encap(skb, up->encap_type); - UDP_INC_STATS_BH(UDP_MIB_INDATAGRAMS, up->pcflag); - return -ret; + /* if we're overly short, let UDP handle it */ + if (skb->len > sizeof(struct udphdr) && + up->encap_rcv != NULL) { + int ret; + + ret = (*up->encap_rcv)(sk, skb); + if (ret <= 0) { + UDP_INC_STATS_BH(UDP_MIB_INDATAGRAMS, up->pcflag); + return -ret; + } } + /* FALLTHROUGH -- it's a UDP Packet */ } @@ -1349,6 +1252,9 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname, case 0: case UDP_ENCAP_ESPINUDP: case UDP_ENCAP_ESPINUDP_NON_IKE: + up->encap_rcv = xfrm4_udp_encap_rcv; + /* FALLTHROUGH */ + case UDP_ENCAP_L2TPINUDP: up->encap_type = val; break; default: diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c index fa1902dc81b8..2fa108245413 100644 --- a/net/ipv4/xfrm4_input.c +++ b/net/ipv4/xfrm4_input.c @@ -16,13 +16,6 @@ #include <net/ip.h> #include <net/xfrm.h> -int xfrm4_rcv(struct sk_buff *skb) -{ - return xfrm4_rcv_encap(skb, 0); -} - -EXPORT_SYMBOL(xfrm4_rcv); - static int xfrm4_parse_spi(struct sk_buff *skb, u8 nexthdr, __be32 *spi, __be32 *seq) { switch (nexthdr) { @@ -53,7 +46,7 @@ drop: } #endif -int xfrm4_rcv_encap(struct sk_buff *skb, __u16 encap_type) +static int xfrm4_rcv_encap(struct sk_buff *skb, __u16 encap_type) { __be32 spi, seq; struct xfrm_state *xfrm_vec[XFRM_MAX_DEPTH]; @@ -167,3 +160,108 @@ drop: kfree_skb(skb); return 0; } + +/* If it's a keepalive packet, then just eat it. + * If it's an encapsulated packet, then pass it to the + * IPsec xfrm input. + * Returns 0 if skb passed to xfrm or was dropped. + * Returns >0 if skb should be passed to UDP. + * Returns <0 if skb should be resubmitted (-ret is protocol) + */ +int xfrm4_udp_encap_rcv(struct sock *sk, struct sk_buff *skb) +{ + struct udp_sock *up = udp_sk(sk); + struct udphdr *uh; + struct iphdr *iph; + int iphlen, len; + int ret; + + __u8 *udpdata; + __be32 *udpdata32; + __u16 encap_type = up->encap_type; + + /* if this is not encapsulated socket, then just return now */ + if (!encap_type) + return 1; + + /* If this is a paged skb, make sure we pull up + * whatever data we need to look at. */ + len = skb->len - sizeof(struct udphdr); + if (!pskb_may_pull(skb, sizeof(struct udphdr) + min(len, 8))) + return 1; + + /* Now we can get the pointers */ + uh = udp_hdr(skb); + udpdata = (__u8 *)uh + sizeof(struct udphdr); + udpdata32 = (__be32 *)udpdata; + + switch (encap_type) { + default: + case UDP_ENCAP_ESPINUDP: + /* Check if this is a keepalive packet. If so, eat it. */ + if (len == 1 && udpdata[0] == 0xff) { + goto drop; + } else if (len > sizeof(struct ip_esp_hdr) && udpdata32[0] != 0) { + /* ESP Packet without Non-ESP header */ + len = sizeof(struct udphdr); + } else + /* Must be an IKE packet.. pass it through */ + return 1; + break; + case UDP_ENCAP_ESPINUDP_NON_IKE: + /* Check if this is a keepalive packet. If so, eat it. */ + if (len == 1 && udpdata[0] == 0xff) { + goto drop; + } else if (len > 2 * sizeof(u32) + sizeof(struct ip_esp_hdr) && + udpdata32[0] == 0 && udpdata32[1] == 0) { + + /* ESP Packet with Non-IKE marker */ + len = sizeof(struct udphdr) + 2 * sizeof(u32); + } else + /* Must be an IKE packet.. pass it through */ + return 1; + break; + } + + /* At this point we are sure that this is an ESPinUDP packet, + * so we need to remove 'len' bytes from the packet (the UDP + * header and optional ESP marker bytes) and then modify the + * protocol to ESP, and then call into the transform receiver. + */ + if (skb_cloned(skb) && pskb_expand_head(skb, 0, 0, GFP_ATOMIC)) + goto drop; + + /* Now we can update and verify the packet length... */ + iph = ip_hdr(skb); + iphlen = iph->ihl << 2; + iph->tot_len = htons(ntohs(iph->tot_len) - len); + if (skb->len < iphlen + len) { + /* packet is too small!?! */ + goto drop; + } + + /* pull the data buffer up to the ESP header and set the + * transport header to point to ESP. Keep UDP on the stack + * for later. + */ + __skb_pull(skb, len); + skb_reset_transport_header(skb); + + /* modify the protocol (it's ESP!) */ + iph->protocol = IPPROTO_ESP; + + /* process ESP */ + ret = xfrm4_rcv_encap(skb, encap_type); + return ret; + +drop: + kfree_skb(skb); + return 0; +} + +int xfrm4_rcv(struct sk_buff *skb) +{ + return xfrm4_rcv_encap(skb, 0); +} + +EXPORT_SYMBOL(xfrm4_rcv); diff --git a/net/ipv4/xfrm4_tunnel.c b/net/ipv4/xfrm4_tunnel.c index 568510304553..9275c79119b6 100644 --- a/net/ipv4/xfrm4_tunnel.c +++ b/net/ipv4/xfrm4_tunnel.c @@ -109,3 +109,4 @@ static void __exit ipip_fini(void) module_init(ipip_init); module_exit(ipip_fini); MODULE_LICENSE("GPL"); +MODULE_ALIAS_XFRM_TYPE(AF_INET, XFRM_PROTO_IPIP); |