diff options
Diffstat (limited to 'net/netfilter')
52 files changed, 1382 insertions, 622 deletions
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index fefa514b991..56d22cae590 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -124,9 +124,14 @@ config NF_CONNTRACK_TIMESTAMP If unsure, say `N'. +config NF_CONNTRACK_LABELS + bool + help + This option enables support for assigning user-defined flag bits + to connection tracking entries. It selected by the connlabel match. + config NF_CT_PROTO_DCCP - tristate 'DCCP protocol connection tracking support (EXPERIMENTAL)' - depends on EXPERIMENTAL + tristate 'DCCP protocol connection tracking support' depends on NETFILTER_ADVANCED default IP_DCCP help @@ -139,8 +144,7 @@ config NF_CT_PROTO_GRE tristate config NF_CT_PROTO_SCTP - tristate 'SCTP protocol connection tracking support (EXPERIMENTAL)' - depends on EXPERIMENTAL + tristate 'SCTP protocol connection tracking support' depends on NETFILTER_ADVANCED default IP_SCTP help @@ -281,8 +285,7 @@ config NF_CONNTRACK_PPTP To compile it as a module, choose M here. If unsure, say N. config NF_CONNTRACK_SANE - tristate "SANE protocol support (EXPERIMENTAL)" - depends on EXPERIMENTAL + tristate "SANE protocol support" depends on NETFILTER_ADVANCED help SANE is a protocol for remote access to scanners as implemented @@ -409,8 +412,7 @@ endif # NF_CONNTRACK # transparent proxy support config NETFILTER_TPROXY - tristate "Transparent proxying support (EXPERIMENTAL)" - depends on EXPERIMENTAL + tristate "Transparent proxying support" depends on IP_NF_MANGLE depends on NETFILTER_ADVANCED help @@ -680,6 +682,13 @@ config NETFILTER_XT_TARGET_NFQUEUE To compile it as a module, choose M here. If unsure, say N. +config NETFILTER_XT_TARGET_NOTRACK + tristate '"NOTRACK" target support (DEPRECATED)' + depends on NF_CONNTRACK + depends on IP_NF_RAW || IP6_NF_RAW + depends on NETFILTER_ADVANCED + select NETFILTER_XT_TARGET_CT + config NETFILTER_XT_TARGET_RATEEST tristate '"RATEEST" target support' depends on NETFILTER_ADVANCED @@ -711,8 +720,7 @@ config NETFILTER_XT_TARGET_TEE this clone be rerouted to another nexthop. config NETFILTER_XT_TARGET_TPROXY - tristate '"TPROXY" target support (EXPERIMENTAL)' - depends on EXPERIMENTAL + tristate '"TPROXY" target support' depends on NETFILTER_TPROXY depends on NETFILTER_XTABLES depends on NETFILTER_ADVANCED @@ -776,8 +784,7 @@ config NETFILTER_XT_TARGET_TCPMSS To compile it as a module, choose M here. If unsure, say N. config NETFILTER_XT_TARGET_TCPOPTSTRIP - tristate '"TCPOPTSTRIP" target support (EXPERIMENTAL)' - depends on EXPERIMENTAL + tristate '"TCPOPTSTRIP" target support' depends on IP_NF_MANGLE || IP6_NF_MANGLE depends on NETFILTER_ADVANCED help @@ -798,6 +805,15 @@ config NETFILTER_XT_MATCH_ADDRTYPE If you want to compile it as a module, say M here and read <file:Documentation/kbuild/modules.txt>. If unsure, say `N'. +config NETFILTER_XT_MATCH_BPF + tristate '"bpf" match support' + depends on NETFILTER_ADVANCED + help + BPF matching applies a linux socket filter to each packet and + accepts those for which the filter returns non-zero. + + To compile it as a module, choose M here. If unsure, say N. + config NETFILTER_XT_MATCH_CLUSTER tristate '"cluster" match support' depends on NF_CONNTRACK @@ -835,6 +851,19 @@ config NETFILTER_XT_MATCH_CONNBYTES If you want to compile it as a module, say M here and read <file:Documentation/kbuild/modules.txt>. If unsure, say `N'. +config NETFILTER_XT_MATCH_CONNLABEL + tristate '"connlabel" match support' + select NF_CONNTRACK_LABELS + depends on NF_CONNTRACK + depends on NETFILTER_ADVANCED + ---help--- + This match allows you to test and assign userspace-defined labels names + to a connection. The kernel only stores bit values - mapping + names to bits is done by userspace. + + Unlike connmark, more than 32 flag bits may be assigned to a + connection simultaneously. + config NETFILTER_XT_MATCH_CONNLIMIT tristate '"connlimit" match support"' depends on NF_CONNTRACK @@ -1138,8 +1167,7 @@ config NETFILTER_XT_MATCH_RECENT Official Website: <http://snowman.net/projects/ipt_recent/> config NETFILTER_XT_MATCH_SCTP - tristate '"sctp" protocol match support (EXPERIMENTAL)' - depends on EXPERIMENTAL + tristate '"sctp" protocol match support' depends on NETFILTER_ADVANCED default IP_SCTP help @@ -1151,8 +1179,7 @@ config NETFILTER_XT_MATCH_SCTP <file:Documentation/kbuild/modules.txt>. If unsure, say `N'. config NETFILTER_XT_MATCH_SOCKET - tristate '"socket" match support (EXPERIMENTAL)' - depends on EXPERIMENTAL + tristate '"socket" match support' depends on NETFILTER_TPROXY depends on NETFILTER_XTABLES depends on NETFILTER_ADVANCED diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index 32596978df1..a1abf87d43b 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -4,6 +4,7 @@ nf_conntrack-y := nf_conntrack_core.o nf_conntrack_standalone.o nf_conntrack_exp nf_conntrack-$(CONFIG_NF_CONNTRACK_TIMEOUT) += nf_conntrack_timeout.o nf_conntrack-$(CONFIG_NF_CONNTRACK_TIMESTAMP) += nf_conntrack_timestamp.o nf_conntrack-$(CONFIG_NF_CONNTRACK_EVENTS) += nf_conntrack_ecache.o +nf_conntrack-$(CONFIG_NF_CONNTRACK_LABELS) += nf_conntrack_labels.o obj-$(CONFIG_NETFILTER) = netfilter.o @@ -98,9 +99,11 @@ obj-$(CONFIG_NETFILTER_XT_TARGET_IDLETIMER) += xt_IDLETIMER.o # matches obj-$(CONFIG_NETFILTER_XT_MATCH_ADDRTYPE) += xt_addrtype.o +obj-$(CONFIG_NETFILTER_XT_MATCH_BPF) += xt_bpf.o obj-$(CONFIG_NETFILTER_XT_MATCH_CLUSTER) += xt_cluster.o obj-$(CONFIG_NETFILTER_XT_MATCH_COMMENT) += xt_comment.o obj-$(CONFIG_NETFILTER_XT_MATCH_CONNBYTES) += xt_connbytes.o +obj-$(CONFIG_NETFILTER_XT_MATCH_CONNLABEL) += xt_connlabel.o obj-$(CONFIG_NETFILTER_XT_MATCH_CONNLIMIT) += xt_connlimit.o obj-$(CONFIG_NETFILTER_XT_MATCH_CONNTRACK) += xt_conntrack.o obj-$(CONFIG_NETFILTER_XT_MATCH_CPU) += xt_cpu.o diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index 6d6d8f2b033..f82b2e606cf 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -88,14 +88,14 @@ find_set_type(const char *name, u8 family, u8 revision) static bool load_settype(const char *name) { - nfnl_unlock(); + nfnl_unlock(NFNL_SUBSYS_IPSET); pr_debug("try to load ip_set_%s\n", name); if (request_module("ip_set_%s", name) < 0) { pr_warning("Can't find ip_set type %s\n", name); - nfnl_lock(); + nfnl_lock(NFNL_SUBSYS_IPSET); return false; } - nfnl_lock(); + nfnl_lock(NFNL_SUBSYS_IPSET); return true; } @@ -532,7 +532,7 @@ ip_set_nfnl_get(const char *name) ip_set_id_t i, index = IPSET_INVALID_ID; struct ip_set *s; - nfnl_lock(); + nfnl_lock(NFNL_SUBSYS_IPSET); for (i = 0; i < ip_set_max; i++) { s = nfnl_set(i); if (s != NULL && STREQ(s->name, name)) { @@ -541,7 +541,7 @@ ip_set_nfnl_get(const char *name) break; } } - nfnl_unlock(); + nfnl_unlock(NFNL_SUBSYS_IPSET); return index; } @@ -561,13 +561,13 @@ ip_set_nfnl_get_byindex(ip_set_id_t index) if (index > ip_set_max) return IPSET_INVALID_ID; - nfnl_lock(); + nfnl_lock(NFNL_SUBSYS_IPSET); set = nfnl_set(index); if (set) __ip_set_get(set); else index = IPSET_INVALID_ID; - nfnl_unlock(); + nfnl_unlock(NFNL_SUBSYS_IPSET); return index; } @@ -584,11 +584,11 @@ void ip_set_nfnl_put(ip_set_id_t index) { struct ip_set *set; - nfnl_lock(); + nfnl_lock(NFNL_SUBSYS_IPSET); set = nfnl_set(index); if (set != NULL) __ip_set_put(set); - nfnl_unlock(); + nfnl_unlock(NFNL_SUBSYS_IPSET); } EXPORT_SYMBOL_GPL(ip_set_nfnl_put); @@ -1763,10 +1763,10 @@ ip_set_sockfn_get(struct sock *sk, int optval, void __user *user, int *len) goto done; } req_get->set.name[IPSET_MAXNAMELEN - 1] = '\0'; - nfnl_lock(); + nfnl_lock(NFNL_SUBSYS_IPSET); find_set_and_id(req_get->set.name, &id); req_get->set.index = id; - nfnl_unlock(); + nfnl_unlock(NFNL_SUBSYS_IPSET); goto copy; } case IP_SET_OP_GET_BYINDEX: { @@ -1778,11 +1778,11 @@ ip_set_sockfn_get(struct sock *sk, int optval, void __user *user, int *len) ret = -EINVAL; goto done; } - nfnl_lock(); + nfnl_lock(NFNL_SUBSYS_IPSET); set = nfnl_set(req_get->set.index); strncpy(req_get->set.name, set ? set->name : "", IPSET_MAXNAMELEN); - nfnl_unlock(); + nfnl_unlock(NFNL_SUBSYS_IPSET); goto copy; } default: diff --git a/net/netfilter/ipset/ip_set_hash_ip.c b/net/netfilter/ipset/ip_set_hash_ip.c index 5c0b78528e5..b7d4cb475ae 100644 --- a/net/netfilter/ipset/ip_set_hash_ip.c +++ b/net/netfilter/ipset/ip_set_hash_ip.c @@ -234,7 +234,7 @@ hash_ip6_data_equal(const struct hash_ip6_elem *ip1, const struct hash_ip6_elem *ip2, u32 *multi) { - return ipv6_addr_cmp(&ip1->ip.in6, &ip2->ip.in6) == 0; + return ipv6_addr_equal(&ip1->ip.in6, &ip2->ip.in6); } static inline bool diff --git a/net/netfilter/ipset/ip_set_hash_ipport.c b/net/netfilter/ipset/ip_set_hash_ipport.c index 6283351f4ee..d8f77bacae8 100644 --- a/net/netfilter/ipset/ip_set_hash_ipport.c +++ b/net/netfilter/ipset/ip_set_hash_ipport.c @@ -284,7 +284,7 @@ hash_ipport6_data_equal(const struct hash_ipport6_elem *ip1, const struct hash_ipport6_elem *ip2, u32 *multi) { - return ipv6_addr_cmp(&ip1->ip.in6, &ip2->ip.in6) == 0 && + return ipv6_addr_equal(&ip1->ip.in6, &ip2->ip.in6) && ip1->port == ip2->port && ip1->proto == ip2->proto; } diff --git a/net/netfilter/ipset/ip_set_hash_ipportip.c b/net/netfilter/ipset/ip_set_hash_ipportip.c index 6a21271c8d5..1da1e955f38 100644 --- a/net/netfilter/ipset/ip_set_hash_ipportip.c +++ b/net/netfilter/ipset/ip_set_hash_ipportip.c @@ -294,8 +294,8 @@ hash_ipportip6_data_equal(const struct hash_ipportip6_elem *ip1, const struct hash_ipportip6_elem *ip2, u32 *multi) { - return ipv6_addr_cmp(&ip1->ip.in6, &ip2->ip.in6) == 0 && - ipv6_addr_cmp(&ip1->ip2.in6, &ip2->ip2.in6) == 0 && + return ipv6_addr_equal(&ip1->ip.in6, &ip2->ip.in6) && + ipv6_addr_equal(&ip1->ip2.in6, &ip2->ip2.in6) && ip1->port == ip2->port && ip1->proto == ip2->proto; } diff --git a/net/netfilter/ipset/ip_set_hash_ipportnet.c b/net/netfilter/ipset/ip_set_hash_ipportnet.c index 2d5cd4ee30e..f2627226a08 100644 --- a/net/netfilter/ipset/ip_set_hash_ipportnet.c +++ b/net/netfilter/ipset/ip_set_hash_ipportnet.c @@ -388,8 +388,8 @@ hash_ipportnet6_data_equal(const struct hash_ipportnet6_elem *ip1, const struct hash_ipportnet6_elem *ip2, u32 *multi) { - return ipv6_addr_cmp(&ip1->ip.in6, &ip2->ip.in6) == 0 && - ipv6_addr_cmp(&ip1->ip2.in6, &ip2->ip2.in6) == 0 && + return ipv6_addr_equal(&ip1->ip.in6, &ip2->ip.in6) && + ipv6_addr_equal(&ip1->ip2.in6, &ip2->ip2.in6) && ip1->cidr == ip2->cidr && ip1->port == ip2->port && ip1->proto == ip2->proto; diff --git a/net/netfilter/ipset/ip_set_hash_net.c b/net/netfilter/ipset/ip_set_hash_net.c index 29e94b981f3..4b677cf6bf7 100644 --- a/net/netfilter/ipset/ip_set_hash_net.c +++ b/net/netfilter/ipset/ip_set_hash_net.c @@ -286,7 +286,7 @@ hash_net6_data_equal(const struct hash_net6_elem *ip1, const struct hash_net6_elem *ip2, u32 *multi) { - return ipv6_addr_cmp(&ip1->ip.in6, &ip2->ip.in6) == 0 && + return ipv6_addr_equal(&ip1->ip.in6, &ip2->ip.in6) && ip1->cidr == ip2->cidr; } diff --git a/net/netfilter/ipset/ip_set_hash_netiface.c b/net/netfilter/ipset/ip_set_hash_netiface.c index 45a101439bc..6ba985f1c96 100644 --- a/net/netfilter/ipset/ip_set_hash_netiface.c +++ b/net/netfilter/ipset/ip_set_hash_netiface.c @@ -471,7 +471,7 @@ hash_netiface6_data_equal(const struct hash_netiface6_elem *ip1, const struct hash_netiface6_elem *ip2, u32 *multi) { - return ipv6_addr_cmp(&ip1->ip.in6, &ip2->ip.in6) == 0 && + return ipv6_addr_equal(&ip1->ip.in6, &ip2->ip.in6) && ip1->cidr == ip2->cidr && (++*multi) && ip1->physdev == ip2->physdev && diff --git a/net/netfilter/ipset/ip_set_hash_netport.c b/net/netfilter/ipset/ip_set_hash_netport.c index 7ef700de596..af20c0c5ced 100644 --- a/net/netfilter/ipset/ip_set_hash_netport.c +++ b/net/netfilter/ipset/ip_set_hash_netport.c @@ -350,7 +350,7 @@ hash_netport6_data_equal(const struct hash_netport6_elem *ip1, const struct hash_netport6_elem *ip2, u32 *multi) { - return ipv6_addr_cmp(&ip1->ip.in6, &ip2->ip.in6) == 0 && + return ipv6_addr_equal(&ip1->ip.in6, &ip2->ip.in6) && ip1->port == ip2->port && ip1->proto == ip2->proto && ip1->cidr == ip2->cidr; diff --git a/net/netfilter/ipvs/ip_vs_app.c b/net/netfilter/ipvs/ip_vs_app.c index 9713e6e86d4..0b779d7df88 100644 --- a/net/netfilter/ipvs/ip_vs_app.c +++ b/net/netfilter/ipvs/ip_vs_app.c @@ -605,12 +605,12 @@ int __net_init ip_vs_app_net_init(struct net *net) struct netns_ipvs *ipvs = net_ipvs(net); INIT_LIST_HEAD(&ipvs->app_list); - proc_net_fops_create(net, "ip_vs_app", 0, &ip_vs_app_fops); + proc_create("ip_vs_app", 0, net->proc_net, &ip_vs_app_fops); return 0; } void __net_exit ip_vs_app_net_cleanup(struct net *net) { unregister_ip_vs_app(net, NULL /* all */); - proc_net_remove(net, "ip_vs_app"); + remove_proc_entry("ip_vs_app", net->proc_net); } diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index 30e764ad021..9f00db7e03f 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -796,8 +796,7 @@ static void ip_vs_conn_expire(unsigned long data) */ if (likely(atomic_read(&cp->refcnt) == 1)) { /* delete the timer if it is activated by other users */ - if (timer_pending(&cp->timer)) - del_timer(&cp->timer); + del_timer(&cp->timer); /* does anybody control me? */ if (cp->control) @@ -1292,8 +1291,8 @@ int __net_init ip_vs_conn_net_init(struct net *net) atomic_set(&ipvs->conn_count, 0); - proc_net_fops_create(net, "ip_vs_conn", 0, &ip_vs_conn_fops); - proc_net_fops_create(net, "ip_vs_conn_sync", 0, &ip_vs_conn_sync_fops); + proc_create("ip_vs_conn", 0, net->proc_net, &ip_vs_conn_fops); + proc_create("ip_vs_conn_sync", 0, net->proc_net, &ip_vs_conn_sync_fops); return 0; } @@ -1301,8 +1300,8 @@ void __net_exit ip_vs_conn_net_cleanup(struct net *net) { /* flush all the connection entries first */ ip_vs_conn_flush(net); - proc_net_remove(net, "ip_vs_conn"); - proc_net_remove(net, "ip_vs_conn_sync"); + remove_proc_entry("ip_vs_conn", net->proc_net); + remove_proc_entry("ip_vs_conn_sync", net->proc_net); } int __init ip_vs_conn_init(void) diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index ec664cbb119..c68198bf912 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -3800,10 +3800,10 @@ int __net_init ip_vs_control_net_init(struct net *net) spin_lock_init(&ipvs->tot_stats.lock); - proc_net_fops_create(net, "ip_vs", 0, &ip_vs_info_fops); - proc_net_fops_create(net, "ip_vs_stats", 0, &ip_vs_stats_fops); - proc_net_fops_create(net, "ip_vs_stats_percpu", 0, - &ip_vs_stats_percpu_fops); + proc_create("ip_vs", 0, net->proc_net, &ip_vs_info_fops); + proc_create("ip_vs_stats", 0, net->proc_net, &ip_vs_stats_fops); + proc_create("ip_vs_stats_percpu", 0, net->proc_net, + &ip_vs_stats_percpu_fops); if (ip_vs_control_net_init_sysctl(net)) goto err; @@ -3822,9 +3822,9 @@ void __net_exit ip_vs_control_net_cleanup(struct net *net) ip_vs_trash_cleanup(net); ip_vs_stop_estimator(net, &ipvs->tot_stats); ip_vs_control_net_cleanup_sysctl(net); - proc_net_remove(net, "ip_vs_stats_percpu"); - proc_net_remove(net, "ip_vs_stats"); - proc_net_remove(net, "ip_vs"); + remove_proc_entry("ip_vs_stats_percpu", net->proc_net); + remove_proc_entry("ip_vs_stats", net->proc_net); + remove_proc_entry("ip_vs", net->proc_net); free_percpu(ipvs->tot_stats.cpustats); } diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c index 746048b13ef..ae8ec6f2768 100644 --- a/net/netfilter/ipvs/ip_vs_proto_sctp.c +++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c @@ -61,14 +61,27 @@ sctp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, return 1; } +static void sctp_nat_csum(struct sk_buff *skb, sctp_sctphdr_t *sctph, + unsigned int sctphoff) +{ + __u32 crc32; + struct sk_buff *iter; + + crc32 = sctp_start_cksum((__u8 *)sctph, skb_headlen(skb) - sctphoff); + skb_walk_frags(skb, iter) + crc32 = sctp_update_cksum((u8 *) iter->data, + skb_headlen(iter), crc32); + sctph->checksum = sctp_end_cksum(crc32); + + skb->ip_summed = CHECKSUM_UNNECESSARY; +} + static int sctp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, struct ip_vs_conn *cp, struct ip_vs_iphdr *iph) { sctp_sctphdr_t *sctph; unsigned int sctphoff = iph->len; - struct sk_buff *iter; - __be32 crc32; #ifdef CONFIG_IP_VS_IPV6 if (cp->af == AF_INET6 && iph->fragoffs) @@ -92,13 +105,7 @@ sctp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, sctph = (void *) skb_network_header(skb) + sctphoff; sctph->source = cp->vport; - /* Calculate the checksum */ - crc32 = sctp_start_cksum((u8 *) sctph, skb_headlen(skb) - sctphoff); - skb_walk_frags(skb, iter) - crc32 = sctp_update_cksum((u8 *) iter->data, skb_headlen(iter), - crc32); - crc32 = sctp_end_cksum(crc32); - sctph->checksum = crc32; + sctp_nat_csum(skb, sctph, sctphoff); return 1; } @@ -109,8 +116,6 @@ sctp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, { sctp_sctphdr_t *sctph; unsigned int sctphoff = iph->len; - struct sk_buff *iter; - __be32 crc32; #ifdef CONFIG_IP_VS_IPV6 if (cp->af == AF_INET6 && iph->fragoffs) @@ -134,13 +139,7 @@ sctp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, sctph = (void *) skb_network_header(skb) + sctphoff; sctph->dest = cp->dport; - /* Calculate the checksum */ - crc32 = sctp_start_cksum((u8 *) sctph, skb_headlen(skb) - sctphoff); - skb_walk_frags(skb, iter) - crc32 = sctp_update_cksum((u8 *) iter->data, skb_headlen(iter), - crc32); - crc32 = sctp_end_cksum(crc32); - sctph->checksum = crc32; + sctp_nat_csum(skb, sctph, sctphoff); return 1; } diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index effa10c9e4e..44fd10c539a 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -1795,6 +1795,8 @@ int start_sync_thread(struct net *net, int state, char *mcast_ifn, __u8 syncid) GFP_KERNEL); if (!tinfo->buf) goto outtinfo; + } else { + tinfo->buf = NULL; } tinfo->id = id; diff --git a/net/netfilter/nf_conntrack_acct.c b/net/netfilter/nf_conntrack_acct.c index 7df424e2d10..2d3030ab5b6 100644 --- a/net/netfilter/nf_conntrack_acct.c +++ b/net/netfilter/nf_conntrack_acct.c @@ -106,36 +106,26 @@ static void nf_conntrack_acct_fini_sysctl(struct net *net) } #endif -int nf_conntrack_acct_init(struct net *net) +int nf_conntrack_acct_pernet_init(struct net *net) { - int ret; - net->ct.sysctl_acct = nf_ct_acct; + return nf_conntrack_acct_init_sysctl(net); +} - if (net_eq(net, &init_net)) { - ret = nf_ct_extend_register(&acct_extend); - if (ret < 0) { - printk(KERN_ERR "nf_conntrack_acct: Unable to register extension\n"); - goto out_extend_register; - } - } +void nf_conntrack_acct_pernet_fini(struct net *net) +{ + nf_conntrack_acct_fini_sysctl(net); +} - ret = nf_conntrack_acct_init_sysctl(net); +int nf_conntrack_acct_init(void) +{ + int ret = nf_ct_extend_register(&acct_extend); if (ret < 0) - goto out_sysctl; - - return 0; - -out_sysctl: - if (net_eq(net, &init_net)) - nf_ct_extend_unregister(&acct_extend); -out_extend_register: + pr_err("nf_conntrack_acct: Unable to register extension\n"); return ret; } -void nf_conntrack_acct_fini(struct net *net) +void nf_conntrack_acct_fini(void) { - nf_conntrack_acct_fini_sysctl(net); - if (net_eq(net, &init_net)) - nf_ct_extend_unregister(&acct_extend); + nf_ct_extend_unregister(&acct_extend); } diff --git a/net/netfilter/nf_conntrack_amanda.c b/net/netfilter/nf_conntrack_amanda.c index c514fe6033d..dbdaa114926 100644 --- a/net/netfilter/nf_conntrack_amanda.c +++ b/net/netfilter/nf_conntrack_amanda.c @@ -145,6 +145,7 @@ static int amanda_help(struct sk_buff *skb, exp = nf_ct_expect_alloc(ct); if (exp == NULL) { + nf_ct_helper_log(skb, ct, "cannot alloc expectation"); ret = NF_DROP; goto out; } @@ -158,8 +159,10 @@ static int amanda_help(struct sk_buff *skb, if (nf_nat_amanda && ct->status & IPS_NAT_MASK) ret = nf_nat_amanda(skb, ctinfo, protoff, off - dataoff, len, exp); - else if (nf_ct_expect_related(exp) != 0) + else if (nf_ct_expect_related(exp) != 0) { + nf_ct_helper_log(skb, ct, "cannot add expectation"); ret = NF_DROP; + } nf_ct_expect_put(exp); } diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 08cdc71d8e8..c8e001a9c45 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -45,6 +45,7 @@ #include <net/netfilter/nf_conntrack_zones.h> #include <net/netfilter/nf_conntrack_timestamp.h> #include <net/netfilter/nf_conntrack_timeout.h> +#include <net/netfilter/nf_conntrack_labels.h> #include <net/netfilter/nf_nat.h> #include <net/netfilter/nf_nat_core.h> @@ -763,6 +764,7 @@ void nf_conntrack_free(struct nf_conn *ct) } EXPORT_SYMBOL_GPL(nf_conntrack_free); + /* Allocate a new conntrack: we return -ENOMEM if classification failed due to stress. Otherwise it really is unclassifiable. */ static struct nf_conntrack_tuple_hash * @@ -809,6 +811,7 @@ init_conntrack(struct net *net, struct nf_conn *tmpl, nf_ct_acct_ext_add(ct, GFP_ATOMIC); nf_ct_tstamp_ext_add(ct, GFP_ATOMIC); + nf_ct_labels_ext_add(ct); ecache = tmpl ? nf_ct_ecache_find(tmpl) : NULL; nf_ct_ecache_ext_add(ct, ecache ? ecache->ctmask : 0, @@ -1331,18 +1334,42 @@ static int untrack_refs(void) return cnt; } -static void nf_conntrack_cleanup_init_net(void) +void nf_conntrack_cleanup_start(void) { + RCU_INIT_POINTER(ip_ct_attach, NULL); +} + +void nf_conntrack_cleanup_end(void) +{ + RCU_INIT_POINTER(nf_ct_destroy, NULL); while (untrack_refs() > 0) schedule(); #ifdef CONFIG_NF_CONNTRACK_ZONES nf_ct_extend_unregister(&nf_ct_zone_extend); #endif + nf_conntrack_proto_fini(); + nf_conntrack_labels_fini(); + nf_conntrack_helper_fini(); + nf_conntrack_timeout_fini(); + nf_conntrack_ecache_fini(); + nf_conntrack_tstamp_fini(); + nf_conntrack_acct_fini(); + nf_conntrack_expect_fini(); } -static void nf_conntrack_cleanup_net(struct net *net) +/* + * Mishearing the voices in his head, our hero wonders how he's + * supposed to kill the mall. + */ +void nf_conntrack_cleanup_net(struct net *net) { + /* + * This makes sure all current packets have passed through + * netfilter framework. Roll on, two-stage module + * delete... + */ + synchronize_net(); i_see_dead_people: nf_ct_iterate_cleanup(net, kill_all, NULL); nf_ct_release_dying_list(net); @@ -1352,37 +1379,17 @@ static void nf_conntrack_cleanup_net(struct net *net) } nf_ct_free_hashtable(net->ct.hash, net->ct.htable_size); - nf_conntrack_helper_fini(net); - nf_conntrack_timeout_fini(net); - nf_conntrack_ecache_fini(net); - nf_conntrack_tstamp_fini(net); - nf_conntrack_acct_fini(net); - nf_conntrack_expect_fini(net); + nf_conntrack_proto_pernet_fini(net); + nf_conntrack_helper_pernet_fini(net); + nf_conntrack_ecache_pernet_fini(net); + nf_conntrack_tstamp_pernet_fini(net); + nf_conntrack_acct_pernet_fini(net); + nf_conntrack_expect_pernet_fini(net); kmem_cache_destroy(net->ct.nf_conntrack_cachep); kfree(net->ct.slabname); free_percpu(net->ct.stat); } -/* Mishearing the voices in his head, our hero wonders how he's - supposed to kill the mall. */ -void nf_conntrack_cleanup(struct net *net) -{ - if (net_eq(net, &init_net)) - RCU_INIT_POINTER(ip_ct_attach, NULL); - - /* This makes sure all current packets have passed through - netfilter framework. Roll on, two-stage module - delete... */ - synchronize_net(); - nf_conntrack_proto_fini(net); - nf_conntrack_cleanup_net(net); - - if (net_eq(net, &init_net)) { - RCU_INIT_POINTER(nf_ct_destroy, NULL); - nf_conntrack_cleanup_init_net(); - } -} - void *nf_ct_alloc_hashtable(unsigned int *sizep, int nulls) { struct hlist_nulls_head *hash; @@ -1473,7 +1480,7 @@ void nf_ct_untracked_status_or(unsigned long bits) } EXPORT_SYMBOL_GPL(nf_ct_untracked_status_or); -static int nf_conntrack_init_init_net(void) +int nf_conntrack_init_start(void) { int max_factor = 8; int ret, cpu; @@ -1500,11 +1507,44 @@ static int nf_conntrack_init_init_net(void) printk(KERN_INFO "nf_conntrack version %s (%u buckets, %d max)\n", NF_CONNTRACK_VERSION, nf_conntrack_htable_size, nf_conntrack_max); + + ret = nf_conntrack_expect_init(); + if (ret < 0) + goto err_expect; + + ret = nf_conntrack_acct_init(); + if (ret < 0) + goto err_acct; + + ret = nf_conntrack_tstamp_init(); + if (ret < 0) + goto err_tstamp; + + ret = nf_conntrack_ecache_init(); + if (ret < 0) + goto err_ecache; + + ret = nf_conntrack_timeout_init(); + if (ret < 0) + goto err_timeout; + + ret = nf_conntrack_helper_init(); + if (ret < 0) + goto err_helper; + + ret = nf_conntrack_labels_init(); + if (ret < 0) + goto err_labels; + #ifdef CONFIG_NF_CONNTRACK_ZONES ret = nf_ct_extend_register(&nf_ct_zone_extend); if (ret < 0) goto err_extend; #endif + ret = nf_conntrack_proto_init(); + if (ret < 0) + goto err_proto; + /* Set up fake conntrack: to never be deleted, not in any hashes */ for_each_possible_cpu(cpu) { struct nf_conn *ct = &per_cpu(nf_conntrack_untracked, cpu); @@ -1515,25 +1555,53 @@ static int nf_conntrack_init_init_net(void) nf_ct_untracked_status_or(IPS_CONFIRMED | IPS_UNTRACKED); return 0; +err_proto: #ifdef CONFIG_NF_CONNTRACK_ZONES + nf_ct_extend_unregister(&nf_ct_zone_extend); err_extend: #endif + nf_conntrack_labels_fini(); +err_labels: + nf_conntrack_helper_fini(); +err_helper: + nf_conntrack_timeout_fini(); +err_timeout: + nf_conntrack_ecache_fini(); +err_ecache: + nf_conntrack_tstamp_fini(); +err_tstamp: + nf_conntrack_acct_fini(); +err_acct: + nf_conntrack_expect_fini(); +err_expect: return ret; } +void nf_conntrack_init_end(void) +{ + /* For use by REJECT target */ + RCU_INIT_POINTER(ip_ct_attach, nf_conntrack_attach); + RCU_INIT_POINTER(nf_ct_destroy, destroy_conntrack); + + /* Howto get NAT offsets */ + RCU_INIT_POINTER(nf_ct_nat_offset, NULL); +} + /* * We need to use special "null" values, not used in hash table */ #define UNCONFIRMED_NULLS_VAL ((1<<30)+0) #define DYING_NULLS_VAL ((1<<30)+1) +#define TEMPLATE_NULLS_VAL ((1<<30)+2) -static int nf_conntrack_init_net(struct net *net) +int nf_conntrack_init_net(struct net *net) { int ret; atomic_set(&net->ct.count, 0); INIT_HLIST_NULLS_HEAD(&net->ct.unconfirmed, UNCONFIRMED_NULLS_VAL); INIT_HLIST_NULLS_HEAD(&net->ct.dying, DYING_NULLS_VAL); + INIT_HLIST_NULLS_HEAD(&net->ct.tmpl, TEMPLATE_NULLS_VAL); net->ct.stat = alloc_percpu(struct ip_conntrack_stat); if (!net->ct.stat) { ret = -ENOMEM; @@ -1562,35 +1630,36 @@ static int nf_conntrack_init_net(struct net *net) printk(KERN_ERR "Unable to create nf_conntrack_hash\n"); goto err_hash; } - ret = nf_conntrack_expect_init(net); + ret = nf_conntrack_expect_pernet_init(net); if (ret < 0) goto err_expect; - ret = nf_conntrack_acct_init(net); + ret = nf_conntrack_acct_pernet_init(net); if (ret < 0) goto err_acct; - ret = nf_conntrack_tstamp_init(net); + ret = nf_conntrack_tstamp_pernet_init(net); if (ret < 0) goto err_tstamp; - ret = nf_conntrack_ecache_init(net); + ret = nf_conntrack_ecache_pernet_init(net); if (ret < 0) goto err_ecache; - ret = nf_conntrack_timeout_init(net); - if (ret < 0) - goto err_timeout; - ret = nf_conntrack_helper_init(net); + ret = nf_conntrack_helper_pernet_init(net); if (ret < 0) goto err_helper; + ret = nf_conntrack_proto_pernet_init(net); + if (ret < 0) + goto err_proto; return 0; + +err_proto: + nf_conntrack_helper_pernet_fini(net); err_helper: - nf_conntrack_timeout_fini(net); -err_timeout: - nf_conntrack_ecache_fini(net); + nf_conntrack_ecache_pernet_fini(net); err_ecache: - nf_conntrack_tstamp_fini(net); + nf_conntrack_tstamp_pernet_fini(net); err_tstamp: - nf_conntrack_acct_fini(net); + nf_conntrack_acct_pernet_fini(net); err_acct: - nf_conntrack_expect_fini(net); + nf_conntrack_expect_pernet_fini(net); err_expect: nf_ct_free_hashtable(net->ct.hash, net->ct.htable_size); err_hash: @@ -1607,38 +1676,3 @@ s16 (*nf_ct_nat_offset)(const struct nf_conn *ct, enum ip_conntrack_dir dir, u32 seq); EXPORT_SYMBOL_GPL(nf_ct_nat_offset); - -int nf_conntrack_init(struct net *net) -{ - int ret; - - if (net_eq(net, &init_net)) { - ret = nf_conntrack_init_init_net(); - if (ret < 0) - goto out_init_net; - } - ret = nf_conntrack_proto_init(net); - if (ret < 0) - goto out_proto; - ret = nf_conntrack_init_net(net); - if (ret < 0) - goto out_net; - - if (net_eq(net, &init_net)) { - /* For use by REJECT target */ - RCU_INIT_POINTER(ip_ct_attach, nf_conntrack_attach); - RCU_INIT_POINTER(nf_ct_destroy, destroy_conntrack); - - /* Howto get NAT offsets */ - RCU_INIT_POINTER(nf_ct_nat_offset, NULL); - } - return 0; - -out_net: - nf_conntrack_proto_fini(net); -out_proto: - if (net_eq(net, &init_net)) - nf_conntrack_cleanup_init_net(); -out_init_net: - return ret; -} diff --git a/net/netfilter/nf_conntrack_ecache.c b/net/netfilter/nf_conntrack_ecache.c index faa978f1714..b5d2eb8bf0d 100644 --- a/net/netfilter/nf_conntrack_ecache.c +++ b/net/netfilter/nf_conntrack_ecache.c @@ -233,38 +233,27 @@ static void nf_conntrack_event_fini_sysctl(struct net *net) } #endif /* CONFIG_SYSCTL */ -int nf_conntrack_ecache_init(struct net *net) +int nf_conntrack_ecache_pernet_init(struct net *net) { - int ret; - net->ct.sysctl_events = nf_ct_events; net->ct.sysctl_events_retry_timeout = nf_ct_events_retry_timeout; + return nf_conntrack_event_init_sysctl(net); +} - if (net_eq(net, &init_net)) { - ret = nf_ct_extend_register(&event_extend); - if (ret < 0) { - printk(KERN_ERR "nf_ct_event: Unable to register " - "event extension.\n"); - goto out_extend_register; - } - } +void nf_conntrack_ecache_pernet_fini(struct net *net) +{ + nf_conntrack_event_fini_sysctl(net); +} - ret = nf_conntrack_event_init_sysctl(net); +int nf_conntrack_ecache_init(void) +{ + int ret = nf_ct_extend_register(&event_extend); if (ret < 0) - goto out_sysctl; - - return 0; - -out_sysctl: - if (net_eq(net, &init_net)) - nf_ct_extend_unregister(&event_extend); -out_extend_register: + pr_err("nf_ct_event: Unable to register event extension.\n"); return ret; } -void nf_conntrack_ecache_fini(struct net *net) +void nf_conntrack_ecache_fini(void) { - nf_conntrack_event_fini_sysctl(net); - if (net_eq(net, &init_net)) - nf_ct_extend_unregister(&event_extend); + nf_ct_extend_unregister(&event_extend); } diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c index 527651a53a4..3921e5bc123 100644 --- a/net/netfilter/nf_conntrack_expect.c +++ b/net/netfilter/nf_conntrack_expect.c @@ -571,7 +571,8 @@ static int exp_proc_init(struct net *net) #ifdef CONFIG_NF_CONNTRACK_PROCFS struct proc_dir_entry *proc; - proc = proc_net_fops_create(net, "nf_conntrack_expect", 0440, &exp_file_ops); + proc = proc_create("nf_conntrack_expect", 0440, net->proc_net, + &exp_file_ops); if (!proc) return -ENOMEM; #endif /* CONFIG_NF_CONNTRACK_PROCFS */ @@ -581,59 +582,56 @@ static int exp_proc_init(struct net *net) static void exp_proc_remove(struct net *net) { #ifdef CONFIG_NF_CONNTRACK_PROCFS - proc_net_remove(net, "nf_conntrack_expect"); + remove_proc_entry("nf_conntrack_expect", net->proc_net); #endif /* CONFIG_NF_CONNTRACK_PROCFS */ } module_param_named(expect_hashsize, nf_ct_expect_hsize, uint, 0400); -int nf_conntrack_expect_init(struct net *net) +int nf_conntrack_expect_pernet_init(struct net *net) { int err = -ENOMEM; - if (net_eq(net, &init_net)) { - if (!nf_ct_expect_hsize) { - nf_ct_expect_hsize = net->ct.htable_size / 256; - if (!nf_ct_expect_hsize) - nf_ct_expect_hsize = 1; - } - nf_ct_expect_max = nf_ct_expect_hsize * 4; - } - net->ct.expect_count = 0; net->ct.expect_hash = nf_ct_alloc_hashtable(&nf_ct_expect_hsize, 0); if (net->ct.expect_hash == NULL) goto err1; - if (net_eq(net, &init_net)) { - nf_ct_expect_cachep = kmem_cache_create("nf_conntrack_expect", - sizeof(struct nf_conntrack_expect), - 0, 0, NULL); - if (!nf_ct_expect_cachep) - goto err2; - } - err = exp_proc_init(net); if (err < 0) - goto err3; + goto err2; return 0; - -err3: - if (net_eq(net, &init_net)) - kmem_cache_destroy(nf_ct_expect_cachep); err2: nf_ct_free_hashtable(net->ct.expect_hash, nf_ct_expect_hsize); err1: return err; } -void nf_conntrack_expect_fini(struct net *net) +void nf_conntrack_expect_pernet_fini(struct net *net) { exp_proc_remove(net); - if (net_eq(net, &init_net)) { - rcu_barrier(); /* Wait for call_rcu() before destroy */ - kmem_cache_destroy(nf_ct_expect_cachep); - } nf_ct_free_hashtable(net->ct.expect_hash, nf_ct_expect_hsize); } + +int nf_conntrack_expect_init(void) +{ + if (!nf_ct_expect_hsize) { + nf_ct_expect_hsize = nf_conntrack_htable_size / 256; + if (!nf_ct_expect_hsize) + nf_ct_expect_hsize = 1; + } + nf_ct_expect_max = nf_ct_expect_hsize * 4; + nf_ct_expect_cachep = kmem_cache_create("nf_conntrack_expect", + sizeof(struct nf_conntrack_expect), + 0, 0, NULL); + if (!nf_ct_expect_cachep) + return -ENOMEM; + return 0; +} + +void nf_conntrack_expect_fini(void) +{ + rcu_barrier(); /* Wait for call_rcu() before destroy */ + kmem_cache_destroy(nf_ct_expect_cachep); +} diff --git a/net/netfilter/nf_conntrack_ftp.c b/net/netfilter/nf_conntrack_ftp.c index 1ce3befb7c8..62fb8faedb8 100644 --- a/net/netfilter/nf_conntrack_ftp.c +++ b/net/netfilter/nf_conntrack_ftp.c @@ -435,8 +435,8 @@ skip_nl_seq: connection tracking, not packet filtering. However, it is necessary for accurate tracking in this case. */ - pr_debug("conntrack_ftp: partial %s %u+%u\n", - search[dir][i].pattern, ntohl(th->seq), datalen); + nf_ct_helper_log(skb, ct, "partial matching of `%s'", + search[dir][i].pattern); ret = NF_DROP; goto out; } else if (found == 0) { /* No match */ @@ -450,6 +450,7 @@ skip_nl_seq: exp = nf_ct_expect_alloc(ct); if (exp == NULL) { + nf_ct_helper_log(skb, ct, "cannot alloc expectation"); ret = NF_DROP; goto out; } @@ -500,9 +501,10 @@ skip_nl_seq: protoff, matchoff, matchlen, exp); else { /* Can't expect this? Best to drop packet now. */ - if (nf_ct_expect_related(exp) != 0) + if (nf_ct_expect_related(exp) != 0) { + nf_ct_helper_log(skb, ct, "cannot add expectation"); ret = NF_DROP; - else + } else ret = NF_ACCEPT; } diff --git a/net/netfilter/nf_conntrack_h323_main.c b/net/netfilter/nf_conntrack_h323_main.c index 962795e839a..7df7b36d2e2 100644 --- a/net/netfilter/nf_conntrack_h323_main.c +++ b/net/netfilter/nf_conntrack_h323_main.c @@ -623,7 +623,7 @@ static int h245_help(struct sk_buff *skb, unsigned int protoff, drop: spin_unlock_bh(&nf_h323_lock); - net_info_ratelimited("nf_ct_h245: packet dropped\n"); + nf_ct_helper_log(skb, ct, "cannot process H.245 message"); return NF_DROP; } @@ -1197,7 +1197,7 @@ static int q931_help(struct sk_buff *skb, unsigned int protoff, drop: spin_unlock_bh(&nf_h323_lock); - net_info_ratelimited("nf_ct_q931: packet dropped\n"); + nf_ct_helper_log(skb, ct, "cannot process Q.931 message"); return NF_DROP; } @@ -1795,7 +1795,7 @@ static int ras_help(struct sk_buff *skb, unsigned int protoff, drop: spin_unlock_bh(&nf_h323_lock); - net_info_ratelimited("nf_ct_ras: packet dropped\n"); + nf_ct_helper_log(skb, ct, "cannot process RAS message"); return NF_DROP; } diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c index 884f2b39319..013cdf69fe2 100644 --- a/net/netfilter/nf_conntrack_helper.c +++ b/net/netfilter/nf_conntrack_helper.c @@ -28,6 +28,7 @@ #include <net/netfilter/nf_conntrack_helper.h> #include <net/netfilter/nf_conntrack_core.h> #include <net/netfilter/nf_conntrack_extend.h> +#include <net/netfilter/nf_log.h> static DEFINE_MUTEX(nf_ct_helper_mutex); struct hlist_head *nf_ct_helper_hash __read_mostly; @@ -236,7 +237,9 @@ int __nf_ct_try_assign_helper(struct nf_conn *ct, struct nf_conn *tmpl, /* We only allow helper re-assignment of the same sort since * we cannot reallocate the helper extension area. */ - if (help->helper != helper) { + struct nf_conntrack_helper *tmp = rcu_dereference(help->helper); + + if (tmp && tmp->help != helper->help) { RCU_INIT_POINTER(help->helper, NULL); goto out; } @@ -332,6 +335,24 @@ nf_ct_helper_expectfn_find_by_symbol(const void *symbol) } EXPORT_SYMBOL_GPL(nf_ct_helper_expectfn_find_by_symbol); +__printf(3, 4) +void nf_ct_helper_log(struct sk_buff *skb, const struct nf_conn *ct, + const char *fmt, ...) +{ + const struct nf_conn_help *help; + const struct nf_conntrack_helper *helper; + + /* Called from the helper function, this call never fails */ + help = nfct_help(ct); + + /* rcu_read_lock()ed by nf_hook_slow */ + helper = rcu_dereference(help->helper); + + nf_log_packet(nf_ct_l3num(ct), 0, skb, NULL, NULL, NULL, + "nf_ct_%s: dropping packet: %s ", helper->name, fmt); +} +EXPORT_SYMBOL_GPL(nf_ct_helper_log); + int nf_conntrack_helper_register(struct nf_conntrack_helper *me) { int ret = 0; @@ -423,44 +444,41 @@ static struct nf_ct_ext_type helper_extend __read_mostly = { .id = NF_CT_EXT_HELPER, }; -int nf_conntrack_helper_init(struct net *net) +int nf_conntrack_helper_pernet_init(struct net *net) { - int err; - net->ct.auto_assign_helper_warned = false; net->ct.sysctl_auto_assign_helper = nf_ct_auto_assign_helper; + return nf_conntrack_helper_init_sysctl(net); +} - if (net_eq(net, &init_net)) { - nf_ct_helper_hsize = 1; /* gets rounded up to use one page */ - nf_ct_helper_hash = - nf_ct_alloc_hashtable(&nf_ct_helper_hsize, 0); - if (!nf_ct_helper_hash) - return -ENOMEM; +void nf_conntrack_helper_pernet_fini(struct net *net) +{ + nf_conntrack_helper_fini_sysctl(net); +} - err = nf_ct_extend_register(&helper_extend); - if (err < 0) - goto err1; +int nf_conntrack_helper_init(void) +{ + int ret; + nf_ct_helper_hsize = 1; /* gets rounded up to use one page */ + nf_ct_helper_hash = + nf_ct_alloc_hashtable(&nf_ct_helper_hsize, 0); + if (!nf_ct_helper_hash) + return -ENOMEM; + + ret = nf_ct_extend_register(&helper_extend); + if (ret < 0) { + pr_err("nf_ct_helper: Unable to register helper extension.\n"); + goto out_extend; } - err = nf_conntrack_helper_init_sysctl(net); - if (err < 0) - goto out_sysctl; - return 0; - -out_sysctl: - if (net_eq(net, &init_net)) - nf_ct_extend_unregister(&helper_extend); -err1: +out_extend: nf_ct_free_hashtable(nf_ct_helper_hash, nf_ct_helper_hsize); - return err; + return ret; } -void nf_conntrack_helper_fini(struct net *net) +void nf_conntrack_helper_fini(void) { - nf_conntrack_helper_fini_sysctl(net); - if (net_eq(net, &init_net)) { - nf_ct_extend_unregister(&helper_extend); - nf_ct_free_hashtable(nf_ct_helper_hash, nf_ct_helper_hsize); - } + nf_ct_extend_unregister(&helper_extend); + nf_ct_free_hashtable(nf_ct_helper_hash, nf_ct_helper_hsize); } diff --git a/net/netfilter/nf_conntrack_irc.c b/net/netfilter/nf_conntrack_irc.c index 3b20aa77cfc..70985c5d0ff 100644 --- a/net/netfilter/nf_conntrack_irc.c +++ b/net/netfilter/nf_conntrack_irc.c @@ -194,6 +194,8 @@ static int help(struct sk_buff *skb, unsigned int protoff, exp = nf_ct_expect_alloc(ct); if (exp == NULL) { + nf_ct_helper_log(skb, ct, + "cannot alloc expectation"); ret = NF_DROP; goto out; } @@ -210,8 +212,11 @@ static int help(struct sk_buff *skb, unsigned int protoff, addr_beg_p - ib_ptr, addr_end_p - addr_beg_p, exp); - else if (nf_ct_expect_related(exp) != 0) + else if (nf_ct_expect_related(exp) != 0) { + nf_ct_helper_log(skb, ct, + "cannot add expectation"); ret = NF_DROP; + } nf_ct_expect_put(exp); goto out; } diff --git a/net/netfilter/nf_conntrack_labels.c b/net/netfilter/nf_conntrack_labels.c new file mode 100644 index 00000000000..8fe2e99428b --- /dev/null +++ b/net/netfilter/nf_conntrack_labels.c @@ -0,0 +1,112 @@ +/* + * test/set flag bits stored in conntrack extension area. + * + * (C) 2013 Astaro GmbH & Co KG + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/ctype.h> +#include <linux/export.h> +#include <linux/jhash.h> +#include <linux/spinlock.h> +#include <linux/types.h> +#include <linux/slab.h> + +#include <net/netfilter/nf_conntrack_ecache.h> +#include <net/netfilter/nf_conntrack_labels.h> + +static unsigned int label_bits(const struct nf_conn_labels *l) +{ + unsigned int longs = l->words; + return longs * BITS_PER_LONG; +} + +bool nf_connlabel_match(const struct nf_conn *ct, u16 bit) +{ + struct nf_conn_labels *labels = nf_ct_labels_find(ct); + + if (!labels) + return false; + + return bit < label_bits(labels) && test_bit(bit, labels->bits); +} +EXPORT_SYMBOL_GPL(nf_connlabel_match); + +int nf_connlabel_set(struct nf_conn *ct, u16 bit) +{ + struct nf_conn_labels *labels = nf_ct_labels_find(ct); + + if (!labels || bit >= label_bits(labels)) + return -ENOSPC; + + if (test_bit(bit, labels->bits)) + return 0; + + if (test_and_set_bit(bit, labels->bits)) + nf_conntrack_event_cache(IPCT_LABEL, ct); + + return 0; +} +EXPORT_SYMBOL_GPL(nf_connlabel_set); + +#if IS_ENABLED(CONFIG_NF_CT_NETLINK) +static void replace_u32(u32 *address, u32 mask, u32 new) +{ + u32 old, tmp; + + do { + old = *address; + tmp = (old & mask) ^ new; + } while (cmpxchg(address, old, tmp) != old); +} + +int nf_connlabels_replace(struct nf_conn *ct, + const u32 *data, + const u32 *mask, unsigned int words32) +{ + struct nf_conn_labels *labels; + unsigned int size, i; + u32 *dst; + + labels = nf_ct_labels_find(ct); + if (!labels) + return -ENOSPC; + + size = labels->words * sizeof(long); + if (size < (words32 * sizeof(u32))) + words32 = size / sizeof(u32); + + dst = (u32 *) labels->bits; + if (words32) { + for (i = 0; i < words32; i++) + replace_u32(&dst[i], mask ? ~mask[i] : 0, data[i]); + } + + size /= sizeof(u32); + for (i = words32; i < size; i++) /* pad */ + replace_u32(&dst[i], 0, 0); + + nf_conntrack_event_cache(IPCT_LABEL, ct); + return 0; +} +EXPORT_SYMBOL_GPL(nf_connlabels_replace); +#endif + +static struct nf_ct_ext_type labels_extend __read_mostly = { + .len = sizeof(struct nf_conn_labels), + .align = __alignof__(struct nf_conn_labels), + .id = NF_CT_EXT_LABELS, +}; + +int nf_conntrack_labels_init(void) +{ + return nf_ct_extend_register(&labels_extend); +} + +void nf_conntrack_labels_fini(void) +{ + nf_ct_extend_unregister(&labels_extend); +} diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 4e078cd84d8..5d60e04f967 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -43,6 +43,7 @@ #include <net/netfilter/nf_conntrack_acct.h> #include <net/netfilter/nf_conntrack_zones.h> #include <net/netfilter/nf_conntrack_timestamp.h> +#include <net/netfilter/nf_conntrack_labels.h> #ifdef CONFIG_NF_NAT_NEEDED #include <net/netfilter/nf_nat_core.h> #include <net/netfilter/nf_nat_l4proto.h> @@ -323,6 +324,40 @@ nla_put_failure: #define ctnetlink_dump_secctx(a, b) (0) #endif +#ifdef CONFIG_NF_CONNTRACK_LABELS +static int ctnetlink_label_size(const struct nf_conn *ct) +{ + struct nf_conn_labels *labels = nf_ct_labels_find(ct); + + if (!labels) + return 0; + return nla_total_size(labels->words * sizeof(long)); +} + +static int +ctnetlink_dump_labels(struct sk_buff *skb, const struct nf_conn *ct) +{ + struct nf_conn_labels *labels = nf_ct_labels_find(ct); + unsigned int len, i; + + if (!labels) + return 0; + + len = labels->words * sizeof(long); + i = 0; + do { + if (labels->bits[i] != 0) + return nla_put(skb, CTA_LABELS, len, labels->bits); + i++; + } while (i < labels->words); + + return 0; +} +#else +#define ctnetlink_dump_labels(a, b) (0) +#define ctnetlink_label_size(a) (0) +#endif + #define master_tuple(ct) &(ct->master->tuplehash[IP_CT_DIR_ORIGINAL].tuple) static inline int @@ -463,6 +498,7 @@ ctnetlink_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type, ctnetlink_dump_helpinfo(skb, ct) < 0 || ctnetlink_dump_mark(skb, ct) < 0 || ctnetlink_dump_secctx(skb, ct) < 0 || + ctnetlink_dump_labels(skb, ct) < 0 || ctnetlink_dump_id(skb, ct) < 0 || ctnetlink_dump_use(skb, ct) < 0 || ctnetlink_dump_master(skb, ct) < 0 || @@ -561,6 +597,7 @@ ctnetlink_nlmsg_size(const struct nf_conn *ct) + nla_total_size(sizeof(u_int32_t)) /* CTA_MARK */ #endif + ctnetlink_proto_size(ct) + + ctnetlink_label_size(ct) ; } @@ -662,6 +699,9 @@ ctnetlink_conntrack_event(unsigned int events, struct nf_ct_event *item) && ctnetlink_dump_secctx(skb, ct) < 0) goto nla_put_failure; #endif + if (events & (1 << IPCT_LABEL) && + ctnetlink_dump_labels(skb, ct) < 0) + goto nla_put_failure; if (events & (1 << IPCT_RELATED) && ctnetlink_dump_master(skb, ct) < 0) @@ -921,6 +961,7 @@ ctnetlink_parse_help(const struct nlattr *attr, char **helper_name, return 0; } +#define __CTA_LABELS_MAX_LENGTH ((XT_CONNLABEL_MAXBIT + 1) / BITS_PER_BYTE) static const struct nla_policy ct_nla_policy[CTA_MAX+1] = { [CTA_TUPLE_ORIG] = { .type = NLA_NESTED }, [CTA_TUPLE_REPLY] = { .type = NLA_NESTED }, @@ -937,6 +978,10 @@ static const struct nla_policy ct_nla_policy[CTA_MAX+1] = { [CTA_NAT_SEQ_ADJ_REPLY] = { .type = NLA_NESTED }, [CTA_ZONE] = { .type = NLA_U16 }, [CTA_MARK_MASK] = { .type = NLA_U32 }, + [CTA_LABELS] = { .type = NLA_BINARY, + .len = __CTA_LABELS_MAX_LENGTH }, + [CTA_LABELS_MASK] = { .type = NLA_BINARY, + .len = __CTA_LABELS_MAX_LENGTH }, }; static int @@ -1211,13 +1256,13 @@ ctnetlink_parse_nat_setup(struct nf_conn *ct, if (!parse_nat_setup) { #ifdef CONFIG_MODULES rcu_read_unlock(); - nfnl_unlock(); + nfnl_unlock(NFNL_SUBSYS_CTNETLINK); if (request_module("nf-nat") < 0) { - nfnl_lock(); + nfnl_lock(NFNL_SUBSYS_CTNETLINK); rcu_read_lock(); return -EOPNOTSUPP; } - nfnl_lock(); + nfnl_lock(NFNL_SUBSYS_CTNETLINK); rcu_read_lock(); if (nfnetlink_parse_nat_setup_hook) return -EAGAIN; @@ -1229,13 +1274,13 @@ ctnetlink_parse_nat_setup(struct nf_conn *ct, if (err == -EAGAIN) { #ifdef CONFIG_MODULES rcu_read_unlock(); - nfnl_unlock(); + nfnl_unlock(NFNL_SUBSYS_CTNETLINK); if (request_module("nf-nat-%u", nf_ct_l3num(ct)) < 0) { - nfnl_lock(); + nfnl_lock(NFNL_SUBSYS_CTNETLINK); rcu_read_lock(); return -EOPNOTSUPP; } - nfnl_lock(); + nfnl_lock(NFNL_SUBSYS_CTNETLINK); rcu_read_lock(); #else err = -EOPNOTSUPP; @@ -1465,6 +1510,31 @@ ctnetlink_change_nat_seq_adj(struct nf_conn *ct, #endif static int +ctnetlink_attach_labels(struct nf_conn *ct, const struct nlattr * const cda[]) +{ +#ifdef CONFIG_NF_CONNTRACK_LABELS + size_t len = nla_len(cda[CTA_LABELS]); + const void *mask = cda[CTA_LABELS_MASK]; + + if (len & (sizeof(u32)-1)) /* must be multiple of u32 */ + return -EINVAL; + + if (mask) { + if (nla_len(cda[CTA_LABELS_MASK]) == 0 || + nla_len(cda[CTA_LABELS_MASK]) != len) + return -EINVAL; + mask = nla_data(cda[CTA_LABELS_MASK]); + } + + len /= sizeof(u32); + + return nf_connlabels_replace(ct, nla_data(cda[CTA_LABELS]), mask, len); +#else + return -EOPNOTSUPP; +#endif +} + +static int ctnetlink_change_conntrack(struct nf_conn *ct, const struct nlattr * const cda[]) { @@ -1510,6 +1580,11 @@ ctnetlink_change_conntrack(struct nf_conn *ct, return err; } #endif + if (cda[CTA_LABELS]) { + err = ctnetlink_attach_labels(ct, cda); + if (err < 0) + return err; + } return 0; } @@ -1598,6 +1673,8 @@ ctnetlink_create_conntrack(struct net *net, u16 zone, nf_ct_acct_ext_add(ct, GFP_ATOMIC); nf_ct_tstamp_ext_add(ct, GFP_ATOMIC); nf_ct_ecache_ext_add(ct, 0, 0, GFP_ATOMIC); + nf_ct_labels_ext_add(ct); + /* we must add conntrack extensions before confirmation. */ ct->status |= IPS_CONFIRMED; @@ -1705,6 +1782,9 @@ ctnetlink_new_conntrack(struct sock *ctnl, struct sk_buff *skb, if (nlh->nlmsg_flags & NLM_F_CREATE) { enum ip_conntrack_events events; + if (!cda[CTA_TUPLE_ORIG] || !cda[CTA_TUPLE_REPLY]) + return -EINVAL; + ct = ctnetlink_create_conntrack(net, zone, cda, &otuple, &rtuple, u3); if (IS_ERR(ct)) @@ -1716,6 +1796,10 @@ ctnetlink_new_conntrack(struct sock *ctnl, struct sk_buff *skb, else events = IPCT_NEW; + if (cda[CTA_LABELS] && + ctnetlink_attach_labels(ct, cda) == 0) + events |= (1 << IPCT_LABEL); + nf_conntrack_eventmask_report((1 << IPCT_REPLY) | (1 << IPCT_ASSURED) | (1 << IPCT_HELPER) | @@ -1983,6 +2067,8 @@ ctnetlink_nfqueue_build(struct sk_buff *skb, struct nf_conn *ct) if (ct->mark && ctnetlink_dump_mark(skb, ct) < 0) goto nla_put_failure; #endif + if (ctnetlink_dump_labels(skb, ct) < 0) + goto nla_put_failure; rcu_read_unlock(); return 0; @@ -2011,6 +2097,11 @@ ctnetlink_nfqueue_parse_ct(const struct nlattr *cda[], struct nf_conn *ct) if (err < 0) return err; } + if (cda[CTA_LABELS]) { + err = ctnetlink_attach_labels(ct, cda); + if (err < 0) + return err; + } #if defined(CONFIG_NF_CONNTRACK_MARK) if (cda[CTA_MARK]) ct->mark = ntohl(nla_get_be32(cda[CTA_MARK])); @@ -2624,7 +2715,7 @@ ctnetlink_create_expect(struct net *net, u16 zone, if (!help) { if (!cda[CTA_EXPECT_TIMEOUT]) { err = -EINVAL; - goto out; + goto err_out; } exp->timeout.expires = jiffies + ntohl(nla_get_be32(cda[CTA_EXPECT_TIMEOUT])) * HZ; diff --git a/net/netfilter/nf_conntrack_pptp.c b/net/netfilter/nf_conntrack_pptp.c index cc7669ef0b9..e6678d2b624 100644 --- a/net/netfilter/nf_conntrack_pptp.c +++ b/net/netfilter/nf_conntrack_pptp.c @@ -14,7 +14,7 @@ * Limitations: * - We blindly assume that control connections are always * established in PNS->PAC direction. This is a violation - * of RFFC2673 + * of RFC 2637 * - We can only support one single call within each session * TODO: * - testing of incoming PPTP calls diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c index 51e928db48c..58ab4050830 100644 --- a/net/netfilter/nf_conntrack_proto.c +++ b/net/netfilter/nf_conntrack_proto.c @@ -212,8 +212,7 @@ static void nf_ct_l3proto_unregister_sysctl(struct net *net, #endif } -static int -nf_conntrack_l3proto_register_net(struct nf_conntrack_l3proto *proto) +int nf_ct_l3proto_register(struct nf_conntrack_l3proto *proto) { int ret = 0; struct nf_conntrack_l3proto *old; @@ -242,8 +241,9 @@ out_unlock: return ret; } +EXPORT_SYMBOL_GPL(nf_ct_l3proto_register); -int nf_conntrack_l3proto_register(struct net *net, +int nf_ct_l3proto_pernet_register(struct net *net, struct nf_conntrack_l3proto *proto) { int ret = 0; @@ -254,22 +254,11 @@ int nf_conntrack_l3proto_register(struct net *net, return ret; } - ret = nf_ct_l3proto_register_sysctl(net, proto); - if (ret < 0) - return ret; - - if (net == &init_net) { - ret = nf_conntrack_l3proto_register_net(proto); - if (ret < 0) - nf_ct_l3proto_unregister_sysctl(net, proto); - } - - return ret; + return nf_ct_l3proto_register_sysctl(net, proto); } -EXPORT_SYMBOL_GPL(nf_conntrack_l3proto_register); +EXPORT_SYMBOL_GPL(nf_ct_l3proto_pernet_register); -static void -nf_conntrack_l3proto_unregister_net(struct nf_conntrack_l3proto *proto) +void nf_ct_l3proto_unregister(struct nf_conntrack_l3proto *proto) { BUG_ON(proto->l3proto >= AF_MAX); @@ -283,19 +272,17 @@ nf_conntrack_l3proto_unregister_net(struct nf_conntrack_l3proto *proto) synchronize_rcu(); } +EXPORT_SYMBOL_GPL(nf_ct_l3proto_unregister); -void nf_conntrack_l3proto_unregister(struct net *net, +void nf_ct_l3proto_pernet_unregister(struct net *net, struct nf_conntrack_l3proto *proto) { - if (net == &init_net) - nf_conntrack_l3proto_unregister_net(proto); - nf_ct_l3proto_unregister_sysctl(net, proto); /* Remove all contrack entries for this protocol */ nf_ct_iterate_cleanup(net, kill_l3proto, proto); } -EXPORT_SYMBOL_GPL(nf_conntrack_l3proto_unregister); +EXPORT_SYMBOL_GPL(nf_ct_l3proto_pernet_unregister); static struct nf_proto_net *nf_ct_l4proto_net(struct net *net, struct nf_conntrack_l4proto *l4proto) @@ -376,8 +363,7 @@ void nf_ct_l4proto_unregister_sysctl(struct net *net, /* FIXME: Allow NULL functions and sub in pointers to generic for them. --RR */ -static int -nf_conntrack_l4proto_register_net(struct nf_conntrack_l4proto *l4proto) +int nf_ct_l4proto_register(struct nf_conntrack_l4proto *l4proto) { int ret = 0; @@ -431,8 +417,9 @@ out_unlock: mutex_unlock(&nf_ct_proto_mutex); return ret; } +EXPORT_SYMBOL_GPL(nf_ct_l4proto_register); -int nf_conntrack_l4proto_register(struct net *net, +int nf_ct_l4proto_pernet_register(struct net *net, struct nf_conntrack_l4proto *l4proto) { int ret = 0; @@ -452,22 +439,13 @@ int nf_conntrack_l4proto_register(struct net *net, if (ret < 0) goto out; - if (net == &init_net) { - ret = nf_conntrack_l4proto_register_net(l4proto); - if (ret < 0) { - nf_ct_l4proto_unregister_sysctl(net, pn, l4proto); - goto out; - } - } - pn->users++; out: return ret; } -EXPORT_SYMBOL_GPL(nf_conntrack_l4proto_register); +EXPORT_SYMBOL_GPL(nf_ct_l4proto_pernet_register); -static void -nf_conntrack_l4proto_unregister_net(struct nf_conntrack_l4proto *l4proto) +void nf_ct_l4proto_unregister(struct nf_conntrack_l4proto *l4proto) { BUG_ON(l4proto->l3proto >= PF_MAX); @@ -482,15 +460,13 @@ nf_conntrack_l4proto_unregister_net(struct nf_conntrack_l4proto *l4proto) synchronize_rcu(); } +EXPORT_SYMBOL_GPL(nf_ct_l4proto_unregister); -void nf_conntrack_l4proto_unregister(struct net *net, +void nf_ct_l4proto_pernet_unregister(struct net *net, struct nf_conntrack_l4proto *l4proto) { struct nf_proto_net *pn = NULL; - if (net == &init_net) - nf_conntrack_l4proto_unregister_net(l4proto); - pn = nf_ct_l4proto_net(net, l4proto); if (pn == NULL) return; @@ -501,11 +477,10 @@ void nf_conntrack_l4proto_unregister(struct net *net, /* Remove all contrack entries for this protocol */ nf_ct_iterate_cleanup(net, kill_l4proto, l4proto); } -EXPORT_SYMBOL_GPL(nf_conntrack_l4proto_unregister); +EXPORT_SYMBOL_GPL(nf_ct_l4proto_pernet_unregister); -int nf_conntrack_proto_init(struct net *net) +int nf_conntrack_proto_pernet_init(struct net *net) { - unsigned int i; int err; struct nf_proto_net *pn = nf_ct_l4proto_net(net, &nf_conntrack_l4proto_generic); @@ -520,19 +495,12 @@ int nf_conntrack_proto_init(struct net *net) if (err < 0) return err; - if (net == &init_net) { - for (i = 0; i < AF_MAX; i++) - rcu_assign_pointer(nf_ct_l3protos[i], - &nf_conntrack_l3proto_generic); - } - pn->users++; return 0; } -void nf_conntrack_proto_fini(struct net *net) +void nf_conntrack_proto_pernet_fini(struct net *net) { - unsigned int i; struct nf_proto_net *pn = nf_ct_l4proto_net(net, &nf_conntrack_l4proto_generic); @@ -540,9 +508,21 @@ void nf_conntrack_proto_fini(struct net *net) nf_ct_l4proto_unregister_sysctl(net, pn, &nf_conntrack_l4proto_generic); - if (net == &init_net) { - /* free l3proto protocol tables */ - for (i = 0; i < PF_MAX; i++) - kfree(nf_ct_protos[i]); - } +} + +int nf_conntrack_proto_init(void) +{ + unsigned int i; + for (i = 0; i < AF_MAX; i++) + rcu_assign_pointer(nf_ct_l3protos[i], + &nf_conntrack_l3proto_generic); + return 0; +} + +void nf_conntrack_proto_fini(void) +{ + unsigned int i; + /* free l3proto protocol tables */ + for (i = 0; i < PF_MAX; i++) + kfree(nf_ct_protos[i]); } diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c index a8ae287bc7a..432f9578000 100644 --- a/net/netfilter/nf_conntrack_proto_dccp.c +++ b/net/netfilter/nf_conntrack_proto_dccp.c @@ -935,32 +935,27 @@ static struct nf_conntrack_l4proto dccp_proto6 __read_mostly = { static __net_init int dccp_net_init(struct net *net) { int ret = 0; - ret = nf_conntrack_l4proto_register(net, - &dccp_proto4); + ret = nf_ct_l4proto_pernet_register(net, &dccp_proto4); if (ret < 0) { - pr_err("nf_conntrack_l4proto_dccp4 :protocol register failed.\n"); + pr_err("nf_conntrack_dccp4: pernet registration failed.\n"); goto out; } - ret = nf_conntrack_l4proto_register(net, - &dccp_proto6); + ret = nf_ct_l4proto_pernet_register(net, &dccp_proto6); if (ret < 0) { - pr_err("nf_conntrack_l4proto_dccp6 :protocol register failed.\n"); + pr_err("nf_conntrack_dccp6: pernet registration failed.\n"); goto cleanup_dccp4; } return 0; cleanup_dccp4: - nf_conntrack_l4proto_unregister(net, - &dccp_proto4); + nf_ct_l4proto_pernet_unregister(net, &dccp_proto4); out: return ret; } static __net_exit void dccp_net_exit(struct net *net) { - nf_conntrack_l4proto_unregister(net, - &dccp_proto6); - nf_conntrack_l4proto_unregister(net, - &dccp_proto4); + nf_ct_l4proto_pernet_unregister(net, &dccp_proto6); + nf_ct_l4proto_pernet_unregister(net, &dccp_proto4); } static struct pernet_operations dccp_net_ops = { @@ -972,11 +967,33 @@ static struct pernet_operations dccp_net_ops = { static int __init nf_conntrack_proto_dccp_init(void) { - return register_pernet_subsys(&dccp_net_ops); + int ret; + + ret = nf_ct_l4proto_register(&dccp_proto4); + if (ret < 0) + goto out_dccp4; + + ret = nf_ct_l4proto_register(&dccp_proto6); + if (ret < 0) + goto out_dccp6; + + ret = register_pernet_subsys(&dccp_net_ops); + if (ret < 0) + goto out_pernet; + + return 0; +out_pernet: + nf_ct_l4proto_unregister(&dccp_proto6); +out_dccp6: + nf_ct_l4proto_unregister(&dccp_proto4); +out_dccp4: + return ret; } static void __exit nf_conntrack_proto_dccp_fini(void) { + nf_ct_l4proto_unregister(&dccp_proto6); + nf_ct_l4proto_unregister(&dccp_proto4); unregister_pernet_subsys(&dccp_net_ops); } diff --git a/net/netfilter/nf_conntrack_proto_gre.c b/net/netfilter/nf_conntrack_proto_gre.c index b09b7af7f6f..bd7d01d9c7e 100644 --- a/net/netfilter/nf_conntrack_proto_gre.c +++ b/net/netfilter/nf_conntrack_proto_gre.c @@ -397,15 +397,15 @@ static struct nf_conntrack_l4proto nf_conntrack_l4proto_gre4 __read_mostly = { static int proto_gre_net_init(struct net *net) { int ret = 0; - ret = nf_conntrack_l4proto_register(net, &nf_conntrack_l4proto_gre4); + ret = nf_ct_l4proto_pernet_register(net, &nf_conntrack_l4proto_gre4); if (ret < 0) - pr_err("nf_conntrack_l4proto_gre4 :protocol register failed.\n"); + pr_err("nf_conntrack_gre4: pernet registration failed.\n"); return ret; } static void proto_gre_net_exit(struct net *net) { - nf_conntrack_l4proto_unregister(net, &nf_conntrack_l4proto_gre4); + nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_gre4); nf_ct_gre_keymap_flush(net); } @@ -418,11 +418,26 @@ static struct pernet_operations proto_gre_net_ops = { static int __init nf_ct_proto_gre_init(void) { - return register_pernet_subsys(&proto_gre_net_ops); + int ret; + + ret = nf_ct_l4proto_register(&nf_conntrack_l4proto_gre4); + if (ret < 0) + goto out_gre4; + + ret = register_pernet_subsys(&proto_gre_net_ops); + if (ret < 0) + goto out_pernet; + + return 0; +out_pernet: + nf_ct_l4proto_unregister(&nf_conntrack_l4proto_gre4); +out_gre4: + return ret; } static void __exit nf_ct_proto_gre_fini(void) { + nf_ct_l4proto_unregister(&nf_conntrack_l4proto_gre4); unregister_pernet_subsys(&proto_gre_net_ops); } diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index c746d61f83e..480f616d593 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -853,33 +853,28 @@ static int sctp_net_init(struct net *net) { int ret = 0; - ret = nf_conntrack_l4proto_register(net, - &nf_conntrack_l4proto_sctp4); + ret = nf_ct_l4proto_pernet_register(net, &nf_conntrack_l4proto_sctp4); if (ret < 0) { - pr_err("nf_conntrack_l4proto_sctp4 :protocol register failed.\n"); + pr_err("nf_conntrack_sctp4: pernet registration failed.\n"); goto out; } - ret = nf_conntrack_l4proto_register(net, - &nf_conntrack_l4proto_sctp6); + ret = nf_ct_l4proto_pernet_register(net, &nf_conntrack_l4proto_sctp6); if (ret < 0) { - pr_err("nf_conntrack_l4proto_sctp6 :protocol register failed.\n"); + pr_err("nf_conntrack_sctp6: pernet registration failed.\n"); goto cleanup_sctp4; } return 0; cleanup_sctp4: - nf_conntrack_l4proto_unregister(net, - &nf_conntrack_l4proto_sctp4); + nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_sctp4); out: return ret; } static void sctp_net_exit(struct net *net) { - nf_conntrack_l4proto_unregister(net, - &nf_conntrack_l4proto_sctp6); - nf_conntrack_l4proto_unregister(net, - &nf_conntrack_l4proto_sctp4); + nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_sctp6); + nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_sctp4); } static struct pernet_operations sctp_net_ops = { @@ -891,11 +886,33 @@ static struct pernet_operations sctp_net_ops = { static int __init nf_conntrack_proto_sctp_init(void) { - return register_pernet_subsys(&sctp_net_ops); + int ret; + + ret = nf_ct_l4proto_register(&nf_conntrack_l4proto_sctp4); + if (ret < 0) + goto out_sctp4; + + ret = nf_ct_l4proto_register(&nf_conntrack_l4proto_sctp6); + if (ret < 0) + goto out_sctp6; + + ret = register_pernet_subsys(&sctp_net_ops); + if (ret < 0) + goto out_pernet; + + return 0; +out_pernet: + nf_ct_l4proto_unregister(&nf_conntrack_l4proto_sctp6); +out_sctp6: + nf_ct_l4proto_unregister(&nf_conntrack_l4proto_sctp4); +out_sctp4: + return ret; } static void __exit nf_conntrack_proto_sctp_fini(void) { + nf_ct_l4proto_unregister(&nf_conntrack_l4proto_sctp6); + nf_ct_l4proto_unregister(&nf_conntrack_l4proto_sctp4); unregister_pernet_subsys(&sctp_net_ops); } diff --git a/net/netfilter/nf_conntrack_proto_udplite.c b/net/netfilter/nf_conntrack_proto_udplite.c index 4b66df20928..157489581c3 100644 --- a/net/netfilter/nf_conntrack_proto_udplite.c +++ b/net/netfilter/nf_conntrack_proto_udplite.c @@ -336,30 +336,28 @@ static int udplite_net_init(struct net *net) { int ret = 0; - ret = nf_conntrack_l4proto_register(net, - &nf_conntrack_l4proto_udplite4); + ret = nf_ct_l4proto_pernet_register(net, &nf_conntrack_l4proto_udplite4); if (ret < 0) { - pr_err("nf_conntrack_l4proto_udplite4 :protocol register failed.\n"); + pr_err("nf_conntrack_udplite4: pernet registration failed.\n"); goto out; } - ret = nf_conntrack_l4proto_register(net, - &nf_conntrack_l4proto_udplite6); + ret = nf_ct_l4proto_pernet_register(net, &nf_conntrack_l4proto_udplite6); if (ret < 0) { - pr_err("nf_conntrack_l4proto_udplite4 :protocol register failed.\n"); + pr_err("nf_conntrack_udplite6: pernet registration failed.\n"); goto cleanup_udplite4; } return 0; cleanup_udplite4: - nf_conntrack_l4proto_unregister(net, &nf_conntrack_l4proto_udplite4); + nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_udplite4); out: return ret; } static void udplite_net_exit(struct net *net) { - nf_conntrack_l4proto_unregister(net, &nf_conntrack_l4proto_udplite6); - nf_conntrack_l4proto_unregister(net, &nf_conntrack_l4proto_udplite4); + nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_udplite6); + nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_udplite4); } static struct pernet_operations udplite_net_ops = { @@ -371,11 +369,33 @@ static struct pernet_operations udplite_net_ops = { static int __init nf_conntrack_proto_udplite_init(void) { - return register_pernet_subsys(&udplite_net_ops); + int ret; + + ret = nf_ct_l4proto_register(&nf_conntrack_l4proto_udplite4); + if (ret < 0) + goto out_udplite4; + + ret = nf_ct_l4proto_register(&nf_conntrack_l4proto_udplite6); + if (ret < 0) + goto out_udplite6; + + ret = register_pernet_subsys(&udplite_net_ops); + if (ret < 0) + goto out_pernet; + + return 0; +out_pernet: + nf_ct_l4proto_unregister(&nf_conntrack_l4proto_udplite6); +out_udplite6: + nf_ct_l4proto_unregister(&nf_conntrack_l4proto_udplite4); +out_udplite4: + return ret; } static void __exit nf_conntrack_proto_udplite_exit(void) { + nf_ct_l4proto_unregister(&nf_conntrack_l4proto_udplite6); + nf_ct_l4proto_unregister(&nf_conntrack_l4proto_udplite4); unregister_pernet_subsys(&udplite_net_ops); } diff --git a/net/netfilter/nf_conntrack_sane.c b/net/netfilter/nf_conntrack_sane.c index 295429f3908..4a2134fd3fc 100644 --- a/net/netfilter/nf_conntrack_sane.c +++ b/net/netfilter/nf_conntrack_sane.c @@ -138,6 +138,7 @@ static int help(struct sk_buff *skb, exp = nf_ct_expect_alloc(ct); if (exp == NULL) { + nf_ct_helper_log(skb, ct, "cannot alloc expectation"); ret = NF_DROP; goto out; } @@ -151,8 +152,10 @@ static int help(struct sk_buff *skb, nf_ct_dump_tuple(&exp->tuple); /* Can't expect this? Best to drop packet now. */ - if (nf_ct_expect_related(exp) != 0) + if (nf_ct_expect_related(exp) != 0) { + nf_ct_helper_log(skb, ct, "cannot add expectation"); ret = NF_DROP; + } nf_ct_expect_put(exp); diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c index df8f4f28448..069229d919b 100644 --- a/net/netfilter/nf_conntrack_sip.c +++ b/net/netfilter/nf_conntrack_sip.c @@ -1095,8 +1095,10 @@ static int process_sdp(struct sk_buff *skb, unsigned int protoff, port = simple_strtoul(*dptr + mediaoff, NULL, 10); if (port == 0) continue; - if (port < 1024 || port > 65535) + if (port < 1024 || port > 65535) { + nf_ct_helper_log(skb, ct, "wrong port %u", port); return NF_DROP; + } /* The media description overrides the session description. */ maddr_len = 0; @@ -1107,15 +1109,20 @@ static int process_sdp(struct sk_buff *skb, unsigned int protoff, memcpy(&rtp_addr, &maddr, sizeof(rtp_addr)); } else if (caddr_len) memcpy(&rtp_addr, &caddr, sizeof(rtp_addr)); - else + else { + nf_ct_helper_log(skb, ct, "cannot parse SDP message"); return NF_DROP; + } ret = set_expected_rtp_rtcp(skb, protoff, dataoff, dptr, datalen, &rtp_addr, htons(port), t->class, mediaoff, medialen); - if (ret != NF_ACCEPT) + if (ret != NF_ACCEPT) { + nf_ct_helper_log(skb, ct, + "cannot add expectation for voice"); return ret; + } /* Update media connection address if present */ if (maddr_len && nf_nat_sdp_addr && ct->status & IPS_NAT_MASK) { @@ -1123,8 +1130,10 @@ static int process_sdp(struct sk_buff *skb, unsigned int protoff, dptr, datalen, mediaoff, SDP_HDR_CONNECTION, SDP_HDR_MEDIA, &rtp_addr); - if (ret != NF_ACCEPT) + if (ret != NF_ACCEPT) { + nf_ct_helper_log(skb, ct, "cannot mangle SDP"); return ret; + } } i++; } @@ -1258,9 +1267,10 @@ static int process_register_request(struct sk_buff *skb, unsigned int protoff, ret = ct_sip_parse_header_uri(ct, *dptr, NULL, *datalen, SIP_HDR_CONTACT, NULL, &matchoff, &matchlen, &daddr, &port); - if (ret < 0) + if (ret < 0) { + nf_ct_helper_log(skb, ct, "cannot parse contact"); return NF_DROP; - else if (ret == 0) + } else if (ret == 0) return NF_ACCEPT; /* We don't support third-party registrations */ @@ -1273,8 +1283,10 @@ static int process_register_request(struct sk_buff *skb, unsigned int protoff, if (ct_sip_parse_numerical_param(ct, *dptr, matchoff + matchlen, *datalen, - "expires=", NULL, NULL, &expires) < 0) + "expires=", NULL, NULL, &expires) < 0) { + nf_ct_helper_log(skb, ct, "cannot parse expires"); return NF_DROP; + } if (expires == 0) { ret = NF_ACCEPT; @@ -1282,8 +1294,10 @@ static int process_register_request(struct sk_buff *skb, unsigned int protoff, } exp = nf_ct_expect_alloc(ct); - if (!exp) + if (!exp) { + nf_ct_helper_log(skb, ct, "cannot alloc expectation"); return NF_DROP; + } saddr = NULL; if (sip_direct_signalling) @@ -1300,9 +1314,10 @@ static int process_register_request(struct sk_buff *skb, unsigned int protoff, ret = nf_nat_sip_expect(skb, protoff, dataoff, dptr, datalen, exp, matchoff, matchlen); else { - if (nf_ct_expect_related(exp) != 0) + if (nf_ct_expect_related(exp) != 0) { + nf_ct_helper_log(skb, ct, "cannot add expectation"); ret = NF_DROP; - else + } else ret = NF_ACCEPT; } nf_ct_expect_put(exp); @@ -1356,9 +1371,10 @@ static int process_register_response(struct sk_buff *skb, unsigned int protoff, SIP_HDR_CONTACT, &in_contact, &matchoff, &matchlen, &addr, &port); - if (ret < 0) + if (ret < 0) { + nf_ct_helper_log(skb, ct, "cannot parse contact"); return NF_DROP; - else if (ret == 0) + } else if (ret == 0) break; /* We don't support third-party registrations */ @@ -1373,8 +1389,10 @@ static int process_register_response(struct sk_buff *skb, unsigned int protoff, matchoff + matchlen, *datalen, "expires=", NULL, NULL, &c_expires); - if (ret < 0) + if (ret < 0) { + nf_ct_helper_log(skb, ct, "cannot parse expires"); return NF_DROP; + } if (c_expires == 0) break; if (refresh_signalling_expectation(ct, &addr, proto, port, @@ -1408,15 +1426,21 @@ static int process_sip_response(struct sk_buff *skb, unsigned int protoff, if (*datalen < strlen("SIP/2.0 200")) return NF_ACCEPT; code = simple_strtoul(*dptr + strlen("SIP/2.0 "), NULL, 10); - if (!code) + if (!code) { + nf_ct_helper_log(skb, ct, "cannot get code"); return NF_DROP; + } if (ct_sip_get_header(ct, *dptr, 0, *datalen, SIP_HDR_CSEQ, - &matchoff, &matchlen) <= 0) + &matchoff, &matchlen) <= 0) { + nf_ct_helper_log(skb, ct, "cannot parse cseq"); return NF_DROP; + } cseq = simple_strtoul(*dptr + matchoff, NULL, 10); - if (!cseq) + if (!cseq) { + nf_ct_helper_log(skb, ct, "cannot get cseq"); return NF_DROP; + } matchend = matchoff + matchlen + 1; for (i = 0; i < ARRAY_SIZE(sip_handlers); i++) { @@ -1440,8 +1464,25 @@ static int process_sip_request(struct sk_buff *skb, unsigned int protoff, { enum ip_conntrack_info ctinfo; struct nf_conn *ct = nf_ct_get(skb, &ctinfo); + struct nf_ct_sip_master *ct_sip_info = nfct_help_data(ct); + enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); unsigned int matchoff, matchlen; unsigned int cseq, i; + union nf_inet_addr addr; + __be16 port; + + /* Many Cisco IP phones use a high source port for SIP requests, but + * listen for the response on port 5060. If we are the local + * router for one of these phones, save the port number from the + * Via: header so that nf_nat_sip can redirect the responses to + * the correct port. + */ + if (ct_sip_parse_header_uri(ct, *dptr, NULL, *datalen, + SIP_HDR_VIA_UDP, NULL, &matchoff, + &matchlen, &addr, &port) > 0 && + port != ct->tuplehash[dir].tuple.src.u.udp.port && + nf_inet_addr_cmp(&addr, &ct->tuplehash[dir].tuple.src.u3)) + ct_sip_info->forced_dport = port; for (i = 0; i < ARRAY_SIZE(sip_handlers); i++) { const struct sip_handler *handler; @@ -1454,11 +1495,15 @@ static int process_sip_request(struct sk_buff *skb, unsigned int protoff, continue; if (ct_sip_get_header(ct, *dptr, 0, *datalen, SIP_HDR_CSEQ, - &matchoff, &matchlen) <= 0) + &matchoff, &matchlen) <= 0) { + nf_ct_helper_log(skb, ct, "cannot parse cseq"); return NF_DROP; + } cseq = simple_strtoul(*dptr + matchoff, NULL, 10); - if (!cseq) + if (!cseq) { + nf_ct_helper_log(skb, ct, "cannot get cseq"); return NF_DROP; + } return handler->request(skb, protoff, dataoff, dptr, datalen, cseq); @@ -1481,8 +1526,10 @@ static int process_sip_msg(struct sk_buff *skb, struct nf_conn *ct, if (ret == NF_ACCEPT && ct->status & IPS_NAT_MASK) { nf_nat_sip = rcu_dereference(nf_nat_sip_hook); if (nf_nat_sip && !nf_nat_sip(skb, protoff, dataoff, - dptr, datalen)) + dptr, datalen)) { + nf_ct_helper_log(skb, ct, "cannot NAT SIP message"); ret = NF_DROP; + } } return ret; @@ -1546,11 +1593,14 @@ static int sip_help_tcp(struct sk_buff *skb, unsigned int protoff, end += strlen("\r\n\r\n") + clen; msglen = origlen = end - dptr; - if (msglen > datalen) + if (msglen > datalen) { + nf_ct_helper_log(skb, ct, "incomplete/bad SIP message"); return NF_DROP; + } ret = process_sip_msg(skb, ct, protoff, dataoff, &dptr, &msglen); + /* process_sip_* functions report why this packet is dropped */ if (ret != NF_ACCEPT) break; diff = msglen - origlen; diff --git a/net/netfilter/nf_conntrack_snmp.c b/net/netfilter/nf_conntrack_snmp.c index 6e545e26289..87b95a2c270 100644 --- a/net/netfilter/nf_conntrack_snmp.c +++ b/net/netfilter/nf_conntrack_snmp.c @@ -16,6 +16,7 @@ #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_conntrack_helper.h> #include <net/netfilter/nf_conntrack_expect.h> +#include <linux/netfilter/nf_conntrack_snmp.h> #define SNMP_PORT 161 diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index 363285d544a..6bcce401fd1 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -366,7 +366,7 @@ static int nf_conntrack_standalone_init_proc(struct net *net) { struct proc_dir_entry *pde; - pde = proc_net_fops_create(net, "nf_conntrack", 0440, &ct_file_ops); + pde = proc_create("nf_conntrack", 0440, net->proc_net, &ct_file_ops); if (!pde) goto out_nf_conntrack; @@ -377,7 +377,7 @@ static int nf_conntrack_standalone_init_proc(struct net *net) return 0; out_stat_nf_conntrack: - proc_net_remove(net, "nf_conntrack"); + remove_proc_entry("nf_conntrack", net->proc_net); out_nf_conntrack: return -ENOMEM; } @@ -385,7 +385,7 @@ out_nf_conntrack: static void nf_conntrack_standalone_fini_proc(struct net *net) { remove_proc_entry("nf_conntrack", net->proc_net_stat); - proc_net_remove(net, "nf_conntrack"); + remove_proc_entry("nf_conntrack", net->proc_net); } #else static int nf_conntrack_standalone_init_proc(struct net *net) @@ -472,13 +472,6 @@ static int nf_conntrack_standalone_init_sysctl(struct net *net) { struct ctl_table *table; - if (net_eq(net, &init_net)) { - nf_ct_netfilter_header = - register_net_sysctl(&init_net, "net", nf_ct_netfilter_table); - if (!nf_ct_netfilter_header) - goto out; - } - table = kmemdup(nf_ct_sysctl_table, sizeof(nf_ct_sysctl_table), GFP_KERNEL); if (!table) @@ -502,10 +495,6 @@ static int nf_conntrack_standalone_init_sysctl(struct net *net) out_unregister_netfilter: kfree(table); out_kmemdup: - if (net_eq(net, &init_net)) - unregister_net_sysctl_table(nf_ct_netfilter_header); -out: - printk(KERN_ERR "nf_conntrack: can't register to sysctl.\n"); return -ENOMEM; } @@ -513,8 +502,6 @@ static void nf_conntrack_standalone_fini_sysctl(struct net *net) { struct ctl_table *table; - if (net_eq(net, &init_net)) - unregister_net_sysctl_table(nf_ct_netfilter_header); table = net->ct.sysctl_header->ctl_table_arg; unregister_net_sysctl_table(net->ct.sysctl_header); kfree(table); @@ -530,51 +517,86 @@ static void nf_conntrack_standalone_fini_sysctl(struct net *net) } #endif /* CONFIG_SYSCTL */ -static int nf_conntrack_net_init(struct net *net) +static int nf_conntrack_pernet_init(struct net *net) { int ret; - ret = nf_conntrack_init(net); + ret = nf_conntrack_init_net(net); if (ret < 0) goto out_init; + ret = nf_conntrack_standalone_init_proc(net); if (ret < 0) goto out_proc; + net->ct.sysctl_checksum = 1; net->ct.sysctl_log_invalid = 0; ret = nf_conntrack_standalone_init_sysctl(net); if (ret < 0) goto out_sysctl; + return 0; out_sysctl: nf_conntrack_standalone_fini_proc(net); out_proc: - nf_conntrack_cleanup(net); + nf_conntrack_cleanup_net(net); out_init: return ret; } -static void nf_conntrack_net_exit(struct net *net) +static void nf_conntrack_pernet_exit(struct net *net) { nf_conntrack_standalone_fini_sysctl(net); nf_conntrack_standalone_fini_proc(net); - nf_conntrack_cleanup(net); + nf_conntrack_cleanup_net(net); } static struct pernet_operations nf_conntrack_net_ops = { - .init = nf_conntrack_net_init, - .exit = nf_conntrack_net_exit, + .init = nf_conntrack_pernet_init, + .exit = nf_conntrack_pernet_exit, }; static int __init nf_conntrack_standalone_init(void) { - return register_pernet_subsys(&nf_conntrack_net_ops); + int ret = nf_conntrack_init_start(); + if (ret < 0) + goto out_start; + +#ifdef CONFIG_SYSCTL + nf_ct_netfilter_header = + register_net_sysctl(&init_net, "net", nf_ct_netfilter_table); + if (!nf_ct_netfilter_header) { + pr_err("nf_conntrack: can't register to sysctl.\n"); + goto out_sysctl; + } +#endif + + ret = register_pernet_subsys(&nf_conntrack_net_ops); + if (ret < 0) + goto out_pernet; + + nf_conntrack_init_end(); + return 0; + +out_pernet: +#ifdef CONFIG_SYSCTL + unregister_net_sysctl_table(nf_ct_netfilter_header); +out_sysctl: +#endif + nf_conntrack_cleanup_end(); +out_start: + return ret; } static void __exit nf_conntrack_standalone_fini(void) { + nf_conntrack_cleanup_start(); unregister_pernet_subsys(&nf_conntrack_net_ops); +#ifdef CONFIG_SYSCTL + unregister_net_sysctl_table(nf_ct_netfilter_header); +#endif + nf_conntrack_cleanup_end(); } module_init(nf_conntrack_standalone_init); diff --git a/net/netfilter/nf_conntrack_tftp.c b/net/netfilter/nf_conntrack_tftp.c index 81fc61c0526..e9936c83020 100644 --- a/net/netfilter/nf_conntrack_tftp.c +++ b/net/netfilter/nf_conntrack_tftp.c @@ -60,8 +60,10 @@ static int tftp_help(struct sk_buff *skb, nf_ct_dump_tuple(&ct->tuplehash[IP_CT_DIR_REPLY].tuple); exp = nf_ct_expect_alloc(ct); - if (exp == NULL) + if (exp == NULL) { + nf_ct_helper_log(skb, ct, "cannot alloc expectation"); return NF_DROP; + } tuple = &ct->tuplehash[IP_CT_DIR_REPLY].tuple; nf_ct_expect_init(exp, NF_CT_EXPECT_CLASS_DEFAULT, nf_ct_l3num(ct), @@ -74,8 +76,10 @@ static int tftp_help(struct sk_buff *skb, nf_nat_tftp = rcu_dereference(nf_nat_tftp_hook); if (nf_nat_tftp && ct->status & IPS_NAT_MASK) ret = nf_nat_tftp(skb, ctinfo, exp); - else if (nf_ct_expect_related(exp) != 0) + else if (nf_ct_expect_related(exp) != 0) { + nf_ct_helper_log(skb, ct, "cannot add expectation"); ret = NF_DROP; + } nf_ct_expect_put(exp); break; case TFTP_OPCODE_DATA: diff --git a/net/netfilter/nf_conntrack_timeout.c b/net/netfilter/nf_conntrack_timeout.c index a878ce5b252..93da609d9d2 100644 --- a/net/netfilter/nf_conntrack_timeout.c +++ b/net/netfilter/nf_conntrack_timeout.c @@ -37,24 +37,15 @@ static struct nf_ct_ext_type timeout_extend __read_mostly = { .id = NF_CT_EXT_TIMEOUT, }; -int nf_conntrack_timeout_init(struct net *net) +int nf_conntrack_timeout_init(void) { - int ret = 0; - - if (net_eq(net, &init_net)) { - ret = nf_ct_extend_register(&timeout_extend); - if (ret < 0) { - printk(KERN_ERR "nf_ct_timeout: Unable to register " - "timeout extension.\n"); - return ret; - } - } - - return 0; + int ret = nf_ct_extend_register(&timeout_extend); + if (ret < 0) + pr_err("nf_ct_timeout: Unable to register timeout extension.\n"); + return ret; } -void nf_conntrack_timeout_fini(struct net *net) +void nf_conntrack_timeout_fini(void) { - if (net_eq(net, &init_net)) - nf_ct_extend_unregister(&timeout_extend); + nf_ct_extend_unregister(&timeout_extend); } diff --git a/net/netfilter/nf_conntrack_timestamp.c b/net/netfilter/nf_conntrack_timestamp.c index 7ea8026f07c..902fb0a6b38 100644 --- a/net/netfilter/nf_conntrack_timestamp.c +++ b/net/netfilter/nf_conntrack_timestamp.c @@ -88,37 +88,28 @@ static void nf_conntrack_tstamp_fini_sysctl(struct net *net) } #endif -int nf_conntrack_tstamp_init(struct net *net) +int nf_conntrack_tstamp_pernet_init(struct net *net) { - int ret; - net->ct.sysctl_tstamp = nf_ct_tstamp; + return nf_conntrack_tstamp_init_sysctl(net); +} - if (net_eq(net, &init_net)) { - ret = nf_ct_extend_register(&tstamp_extend); - if (ret < 0) { - printk(KERN_ERR "nf_ct_tstamp: Unable to register " - "extension\n"); - goto out_extend_register; - } - } +void nf_conntrack_tstamp_pernet_fini(struct net *net) +{ + nf_conntrack_tstamp_fini_sysctl(net); + nf_ct_extend_unregister(&tstamp_extend); +} - ret = nf_conntrack_tstamp_init_sysctl(net); +int nf_conntrack_tstamp_init(void) +{ + int ret; + ret = nf_ct_extend_register(&tstamp_extend); if (ret < 0) - goto out_sysctl; - - return 0; - -out_sysctl: - if (net_eq(net, &init_net)) - nf_ct_extend_unregister(&tstamp_extend); -out_extend_register: + pr_err("nf_ct_tstamp: Unable to register extension\n"); return ret; } -void nf_conntrack_tstamp_fini(struct net *net) +void nf_conntrack_tstamp_fini(void) { - nf_conntrack_tstamp_fini_sysctl(net); - if (net_eq(net, &init_net)) - nf_ct_extend_unregister(&tstamp_extend); + nf_ct_extend_unregister(&tstamp_extend); } diff --git a/net/netfilter/nf_nat_amanda.c b/net/netfilter/nf_nat_amanda.c index 42d33788117..3b67c9d1127 100644 --- a/net/netfilter/nf_nat_amanda.c +++ b/net/netfilter/nf_nat_amanda.c @@ -56,15 +56,19 @@ static unsigned int help(struct sk_buff *skb, } } - if (port == 0) + if (port == 0) { + nf_ct_helper_log(skb, exp->master, "all ports in use"); return NF_DROP; + } sprintf(buffer, "%u", port); ret = nf_nat_mangle_udp_packet(skb, exp->master, ctinfo, protoff, matchoff, matchlen, buffer, strlen(buffer)); - if (ret != NF_ACCEPT) + if (ret != NF_ACCEPT) { + nf_ct_helper_log(skb, exp->master, "cannot mangle packet"); nf_ct_unexpect_related(exp); + } return ret; } diff --git a/net/netfilter/nf_nat_ftp.c b/net/netfilter/nf_nat_ftp.c index e839b97b286..e84a578dbe3 100644 --- a/net/netfilter/nf_nat_ftp.c +++ b/net/netfilter/nf_nat_ftp.c @@ -96,8 +96,10 @@ static unsigned int nf_nat_ftp(struct sk_buff *skb, } } - if (port == 0) + if (port == 0) { + nf_ct_helper_log(skb, ct, "all ports in use"); return NF_DROP; + } buflen = nf_nat_ftp_fmt_cmd(ct, type, buffer, sizeof(buffer), &newaddr, port); @@ -113,6 +115,7 @@ static unsigned int nf_nat_ftp(struct sk_buff *skb, return NF_ACCEPT; out: + nf_ct_helper_log(skb, ct, "cannot mangle packet"); nf_ct_unexpect_related(exp); return NF_DROP; } diff --git a/net/netfilter/nf_nat_irc.c b/net/netfilter/nf_nat_irc.c index 1fedee6e7fb..f02b3605823 100644 --- a/net/netfilter/nf_nat_irc.c +++ b/net/netfilter/nf_nat_irc.c @@ -56,14 +56,18 @@ static unsigned int help(struct sk_buff *skb, } } - if (port == 0) + if (port == 0) { + nf_ct_helper_log(skb, exp->master, "all ports in use"); return NF_DROP; + } ret = nf_nat_mangle_tcp_packet(skb, exp->master, ctinfo, protoff, matchoff, matchlen, buffer, strlen(buffer)); - if (ret != NF_ACCEPT) + if (ret != NF_ACCEPT) { + nf_ct_helper_log(skb, exp->master, "cannot mangle packet"); nf_ct_unexpect_related(exp); + } return ret; } diff --git a/net/netfilter/nf_nat_sip.c b/net/netfilter/nf_nat_sip.c index 16303c75221..96ccdf78a29 100644 --- a/net/netfilter/nf_nat_sip.c +++ b/net/netfilter/nf_nat_sip.c @@ -95,6 +95,7 @@ static int map_addr(struct sk_buff *skb, unsigned int protoff, enum ip_conntrack_info ctinfo; struct nf_conn *ct = nf_ct_get(skb, &ctinfo); enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); + struct nf_ct_sip_master *ct_sip_info = nfct_help_data(ct); char buffer[INET6_ADDRSTRLEN + sizeof("[]:nnnnn")]; unsigned int buflen; union nf_inet_addr newaddr; @@ -107,7 +108,8 @@ static int map_addr(struct sk_buff *skb, unsigned int protoff, } else if (nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.dst.u3, addr) && ct->tuplehash[dir].tuple.dst.u.udp.port == port) { newaddr = ct->tuplehash[!dir].tuple.src.u3; - newport = ct->tuplehash[!dir].tuple.src.u.udp.port; + newport = ct_sip_info->forced_dport ? : + ct->tuplehash[!dir].tuple.src.u.udp.port; } else return 1; @@ -144,6 +146,7 @@ static unsigned int nf_nat_sip(struct sk_buff *skb, unsigned int protoff, enum ip_conntrack_info ctinfo; struct nf_conn *ct = nf_ct_get(skb, &ctinfo); enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); + struct nf_ct_sip_master *ct_sip_info = nfct_help_data(ct); unsigned int coff, matchoff, matchlen; enum sip_header_types hdr; union nf_inet_addr addr; @@ -156,8 +159,10 @@ static unsigned int nf_nat_sip(struct sk_buff *skb, unsigned int protoff, &matchoff, &matchlen, &addr, &port) > 0 && !map_addr(skb, protoff, dataoff, dptr, datalen, - matchoff, matchlen, &addr, port)) + matchoff, matchlen, &addr, port)) { + nf_ct_helper_log(skb, ct, "cannot mangle SIP message"); return NF_DROP; + } request = 1; } else request = 0; @@ -190,8 +195,10 @@ static unsigned int nf_nat_sip(struct sk_buff *skb, unsigned int protoff, olen = *datalen; if (!map_addr(skb, protoff, dataoff, dptr, datalen, - matchoff, matchlen, &addr, port)) + matchoff, matchlen, &addr, port)) { + nf_ct_helper_log(skb, ct, "cannot mangle Via header"); return NF_DROP; + } matchend = matchoff + matchlen + *datalen - olen; @@ -206,8 +213,10 @@ static unsigned int nf_nat_sip(struct sk_buff *skb, unsigned int protoff, &ct->tuplehash[!dir].tuple.dst.u3, true); if (!mangle_packet(skb, protoff, dataoff, dptr, datalen, - poff, plen, buffer, buflen)) + poff, plen, buffer, buflen)) { + nf_ct_helper_log(skb, ct, "cannot mangle maddr"); return NF_DROP; + } } /* The received= parameter (RFC 2361) contains the address @@ -222,6 +231,7 @@ static unsigned int nf_nat_sip(struct sk_buff *skb, unsigned int protoff, false); if (!mangle_packet(skb, protoff, dataoff, dptr, datalen, poff, plen, buffer, buflen)) + nf_ct_helper_log(skb, ct, "cannot mangle received"); return NF_DROP; } @@ -235,8 +245,10 @@ static unsigned int nf_nat_sip(struct sk_buff *skb, unsigned int protoff, __be16 p = ct->tuplehash[!dir].tuple.src.u.udp.port; buflen = sprintf(buffer, "%u", ntohs(p)); if (!mangle_packet(skb, protoff, dataoff, dptr, datalen, - poff, plen, buffer, buflen)) + poff, plen, buffer, buflen)) { + nf_ct_helper_log(skb, ct, "cannot mangle rport"); return NF_DROP; + } } } @@ -250,13 +262,36 @@ next: &addr, &port) > 0) { if (!map_addr(skb, protoff, dataoff, dptr, datalen, matchoff, matchlen, - &addr, port)) + &addr, port)) { + nf_ct_helper_log(skb, ct, "cannot mangle contact"); return NF_DROP; + } } if (!map_sip_addr(skb, protoff, dataoff, dptr, datalen, SIP_HDR_FROM) || - !map_sip_addr(skb, protoff, dataoff, dptr, datalen, SIP_HDR_TO)) + !map_sip_addr(skb, protoff, dataoff, dptr, datalen, SIP_HDR_TO)) { + nf_ct_helper_log(skb, ct, "cannot mangle SIP from/to"); return NF_DROP; + } + + /* Mangle destination port for Cisco phones, then fix up checksums */ + if (dir == IP_CT_DIR_REPLY && ct_sip_info->forced_dport) { + struct udphdr *uh; + + if (!skb_make_writable(skb, skb->len)) { + nf_ct_helper_log(skb, ct, "cannot mangle packet"); + return NF_DROP; + } + + uh = (void *)skb->data + protoff; + uh->dest = ct_sip_info->forced_dport; + + if (!nf_nat_mangle_udp_packet(skb, ct, ctinfo, protoff, + 0, 0, NULL, 0)) { + nf_ct_helper_log(skb, ct, "cannot mangle packet"); + return NF_DROP; + } + } return NF_ACCEPT; } @@ -311,8 +346,10 @@ static unsigned int nf_nat_sip_expect(struct sk_buff *skb, unsigned int protoff, enum ip_conntrack_info ctinfo; struct nf_conn *ct = nf_ct_get(skb, &ctinfo); enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); + struct nf_ct_sip_master *ct_sip_info = nfct_help_data(ct); union nf_inet_addr newaddr; u_int16_t port; + __be16 srcport; char buffer[INET6_ADDRSTRLEN + sizeof("[]:nnnnn")]; unsigned int buflen; @@ -326,8 +363,9 @@ static unsigned int nf_nat_sip_expect(struct sk_buff *skb, unsigned int protoff, /* If the signalling port matches the connection's source port in the * original direction, try to use the destination port in the opposite * direction. */ - if (exp->tuple.dst.u.udp.port == - ct->tuplehash[dir].tuple.src.u.udp.port) + srcport = ct_sip_info->forced_dport ? : + ct->tuplehash[dir].tuple.src.u.udp.port; + if (exp->tuple.dst.u.udp.port == srcport) port = ntohs(ct->tuplehash[!dir].tuple.dst.u.udp.port); else port = ntohs(exp->tuple.dst.u.udp.port); @@ -351,15 +389,19 @@ static unsigned int nf_nat_sip_expect(struct sk_buff *skb, unsigned int protoff, } } - if (port == 0) + if (port == 0) { + nf_ct_helper_log(skb, ct, "all ports in use for SIP"); return NF_DROP; + } if (!nf_inet_addr_cmp(&exp->tuple.dst.u3, &exp->saved_addr) || exp->tuple.dst.u.udp.port != exp->saved_proto.udp.port) { buflen = sip_sprintf_addr_port(ct, buffer, &newaddr, port); if (!mangle_packet(skb, protoff, dataoff, dptr, datalen, - matchoff, matchlen, buffer, buflen)) + matchoff, matchlen, buffer, buflen)) { + nf_ct_helper_log(skb, ct, "cannot mangle packet"); goto err; + } } return NF_ACCEPT; @@ -552,14 +594,18 @@ static unsigned int nf_nat_sdp_media(struct sk_buff *skb, unsigned int protoff, } } - if (port == 0) + if (port == 0) { + nf_ct_helper_log(skb, ct, "all ports in use for SDP media"); goto err1; + } /* Update media port. */ if (rtp_exp->tuple.dst.u.udp.port != rtp_exp->saved_proto.udp.port && !nf_nat_sdp_port(skb, protoff, dataoff, dptr, datalen, - mediaoff, medialen, port)) + mediaoff, medialen, port)) { + nf_ct_helper_log(skb, ct, "cannot mangle SDP message"); goto err2; + } return NF_ACCEPT; diff --git a/net/netfilter/nf_nat_tftp.c b/net/netfilter/nf_nat_tftp.c index ccabbda71a3..7f67e1d5310 100644 --- a/net/netfilter/nf_nat_tftp.c +++ b/net/netfilter/nf_nat_tftp.c @@ -28,8 +28,10 @@ static unsigned int help(struct sk_buff *skb, = 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_ct_expect_related(exp) != 0) + if (nf_ct_expect_related(exp) != 0) { + nf_ct_helper_log(skb, exp->master, "cannot add expectation"); return NF_DROP; + } return NF_ACCEPT; } diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index 58a09b7c3f6..d578ec25171 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -36,8 +36,10 @@ MODULE_ALIAS_NET_PF_PROTO(PF_NETLINK, NETLINK_NETFILTER); static char __initdata nfversion[] = "0.30"; -static const struct nfnetlink_subsystem __rcu *subsys_table[NFNL_SUBSYS_COUNT]; -static DEFINE_MUTEX(nfnl_mutex); +static struct { + struct mutex mutex; + const struct nfnetlink_subsystem __rcu *subsys; +} table[NFNL_SUBSYS_COUNT]; static const int nfnl_group2type[NFNLGRP_MAX+1] = { [NFNLGRP_CONNTRACK_NEW] = NFNL_SUBSYS_CTNETLINK, @@ -48,27 +50,32 @@ static const int nfnl_group2type[NFNLGRP_MAX+1] = { [NFNLGRP_CONNTRACK_EXP_DESTROY] = NFNL_SUBSYS_CTNETLINK_EXP, }; -void nfnl_lock(void) +void nfnl_lock(__u8 subsys_id) { - mutex_lock(&nfnl_mutex); + mutex_lock(&table[subsys_id].mutex); } EXPORT_SYMBOL_GPL(nfnl_lock); -void nfnl_unlock(void) +void nfnl_unlock(__u8 subsys_id) { - mutex_unlock(&nfnl_mutex); + mutex_unlock(&table[subsys_id].mutex); } EXPORT_SYMBOL_GPL(nfnl_unlock); +static struct mutex *nfnl_get_lock(__u8 subsys_id) +{ + return &table[subsys_id].mutex; +} + int nfnetlink_subsys_register(const struct nfnetlink_subsystem *n) { - nfnl_lock(); - if (subsys_table[n->subsys_id]) { - nfnl_unlock(); + nfnl_lock(n->subsys_id); + if (table[n->subsys_id].subsys) { + nfnl_unlock(n->subsys_id); return -EBUSY; } - rcu_assign_pointer(subsys_table[n->subsys_id], n); - nfnl_unlock(); + rcu_assign_pointer(table[n->subsys_id].subsys, n); + nfnl_unlock(n->subsys_id); return 0; } @@ -76,9 +83,9 @@ EXPORT_SYMBOL_GPL(nfnetlink_subsys_register); int nfnetlink_subsys_unregister(const struct nfnetlink_subsystem *n) { - nfnl_lock(); - subsys_table[n->subsys_id] = NULL; - nfnl_unlock(); + nfnl_lock(n->subsys_id); + table[n->subsys_id].subsys = NULL; + nfnl_unlock(n->subsys_id); synchronize_rcu(); return 0; } @@ -91,7 +98,7 @@ static inline const struct nfnetlink_subsystem *nfnetlink_get_subsys(u_int16_t t if (subsys_id >= NFNL_SUBSYS_COUNT) return NULL; - return rcu_dereference(subsys_table[subsys_id]); + return rcu_dereference(table[subsys_id].subsys); } static inline const struct nfnl_callback * @@ -175,6 +182,7 @@ replay: struct nlattr *cda[ss->cb[cb_id].attr_count + 1]; struct nlattr *attr = (void *)nlh + min_len; int attrlen = nlh->nlmsg_len - min_len; + __u8 subsys_id = NFNL_SUBSYS_ID(type); err = nla_parse(cda, ss->cb[cb_id].attr_count, attr, attrlen, ss->cb[cb_id].policy); @@ -189,10 +197,9 @@ replay: rcu_read_unlock(); } else { rcu_read_unlock(); - nfnl_lock(); - if (rcu_dereference_protected( - subsys_table[NFNL_SUBSYS_ID(type)], - lockdep_is_held(&nfnl_mutex)) != ss || + nfnl_lock(subsys_id); + if (rcu_dereference_protected(table[subsys_id].subsys, + lockdep_is_held(nfnl_get_lock(subsys_id))) != ss || nfnetlink_find_client(type, ss) != nc) err = -EAGAIN; else if (nc->call) @@ -200,7 +207,7 @@ replay: (const struct nlattr **)cda); else err = -EINVAL; - nfnl_unlock(); + nfnl_unlock(subsys_id); } if (err == -EAGAIN) goto replay; @@ -267,6 +274,11 @@ static struct pernet_operations nfnetlink_net_ops = { static int __init nfnetlink_init(void) { + int i; + + for (i=0; i<NFNL_SUBSYS_COUNT; i++) + mutex_init(&table[i].mutex); + pr_info("Netfilter messages via NETLINK v%s.\n", nfversion); return register_pernet_subsys(&nfnetlink_net_ops); } diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index 9f199f2e31f..92fd8eca0d3 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -13,6 +13,7 @@ */ #include <linux/module.h> #include <linux/skbuff.h> +#include <linux/if_arp.h> #include <linux/init.h> #include <linux/ip.h> #include <linux/ipv6.h> @@ -384,6 +385,7 @@ __build_packet_message(struct nfulnl_instance *inst, struct nfgenmsg *nfmsg; sk_buff_data_t old_tail = inst->skb->tail; struct sock *sk; + const unsigned char *hwhdrp; nlh = nlmsg_put(inst->skb, 0, 0, NFNL_SUBSYS_ULOG << 8 | NFULNL_MSG_PACKET, @@ -485,9 +487,17 @@ __build_packet_message(struct nfulnl_instance *inst, if (indev && skb_mac_header_was_set(skb)) { if (nla_put_be16(inst->skb, NFULA_HWTYPE, htons(skb->dev->type)) || nla_put_be16(inst->skb, NFULA_HWLEN, - htons(skb->dev->hard_header_len)) || - nla_put(inst->skb, NFULA_HWHEADER, skb->dev->hard_header_len, - skb_mac_header(skb))) + htons(skb->dev->hard_header_len))) + goto nla_put_failure; + + hwhdrp = skb_mac_header(skb); + + if (skb->dev->type == ARPHRD_SIT) + hwhdrp -= ETH_HLEN; + + if (hwhdrp >= skb->head && + nla_put(inst->skb, NFULA_HWHEADER, + skb->dev->hard_header_len, hwhdrp)) goto nla_put_failure; } diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index 8d987c3573f..686c7715d77 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -345,19 +345,27 @@ int xt_find_revision(u8 af, const char *name, u8 revision, int target, } EXPORT_SYMBOL_GPL(xt_find_revision); -static char *textify_hooks(char *buf, size_t size, unsigned int mask) +static char * +textify_hooks(char *buf, size_t size, unsigned int mask, uint8_t nfproto) { - static const char *const names[] = { + static const char *const inetbr_names[] = { "PREROUTING", "INPUT", "FORWARD", "OUTPUT", "POSTROUTING", "BROUTING", }; - unsigned int i; + static const char *const arp_names[] = { + "INPUT", "FORWARD", "OUTPUT", + }; + const char *const *names; + unsigned int i, max; char *p = buf; bool np = false; int res; + names = (nfproto == NFPROTO_ARP) ? arp_names : inetbr_names; + max = (nfproto == NFPROTO_ARP) ? ARRAY_SIZE(arp_names) : + ARRAY_SIZE(inetbr_names); *p = '\0'; - for (i = 0; i < ARRAY_SIZE(names); ++i) { + for (i = 0; i < max; ++i) { if (!(mask & (1 << i))) continue; res = snprintf(p, size, "%s%s", np ? "/" : "", names[i]); @@ -402,8 +410,10 @@ int xt_check_match(struct xt_mtchk_param *par, pr_err("%s_tables: %s match: used from hooks %s, but only " "valid from %s\n", xt_prefix[par->family], par->match->name, - textify_hooks(used, sizeof(used), par->hook_mask), - textify_hooks(allow, sizeof(allow), par->match->hooks)); + textify_hooks(used, sizeof(used), par->hook_mask, + par->family), + textify_hooks(allow, sizeof(allow), par->match->hooks, + par->family)); return -EINVAL; } if (par->match->proto && (par->match->proto != proto || inv_proto)) { @@ -575,8 +585,10 @@ int xt_check_target(struct xt_tgchk_param *par, pr_err("%s_tables: %s target: used from hooks %s, but only " "usable from %s\n", xt_prefix[par->family], par->target->name, - textify_hooks(used, sizeof(used), par->hook_mask), - textify_hooks(allow, sizeof(allow), par->target->hooks)); + textify_hooks(used, sizeof(used), par->hook_mask, + par->family), + textify_hooks(allow, sizeof(allow), par->target->hooks, + par->family)); return -EINVAL; } if (par->target->proto && (par->target->proto != proto || inv_proto)) { @@ -1311,12 +1323,12 @@ int xt_proto_init(struct net *net, u_int8_t af) out_remove_matches: strlcpy(buf, xt_prefix[af], sizeof(buf)); strlcat(buf, FORMAT_MATCHES, sizeof(buf)); - proc_net_remove(net, buf); + remove_proc_entry(buf, net->proc_net); out_remove_tables: strlcpy(buf, xt_prefix[af], sizeof(buf)); strlcat(buf, FORMAT_TABLES, sizeof(buf)); - proc_net_remove(net, buf); + remove_proc_entry(buf, net->proc_net); out: return -1; #endif @@ -1330,15 +1342,15 @@ void xt_proto_fini(struct net *net, u_int8_t af) strlcpy(buf, xt_prefix[af], sizeof(buf)); strlcat(buf, FORMAT_TABLES, sizeof(buf)); - proc_net_remove(net, buf); + remove_proc_entry(buf, net->proc_net); strlcpy(buf, xt_prefix[af], sizeof(buf)); strlcat(buf, FORMAT_TARGETS, sizeof(buf)); - proc_net_remove(net, buf); + remove_proc_entry(buf, net->proc_net); strlcpy(buf, xt_prefix[af], sizeof(buf)); strlcat(buf, FORMAT_MATCHES, sizeof(buf)); - proc_net_remove(net, buf); + remove_proc_entry(buf, net->proc_net); #endif /*CONFIG_PROC_FS*/ } EXPORT_SYMBOL_GPL(xt_proto_fini); diff --git a/net/netfilter/xt_CT.c b/net/netfilter/xt_CT.c index ae7f5daeee4..a60261cb0e8 100644 --- a/net/netfilter/xt_CT.c +++ b/net/netfilter/xt_CT.c @@ -20,12 +20,8 @@ #include <net/netfilter/nf_conntrack_timeout.h> #include <net/netfilter/nf_conntrack_zones.h> -static unsigned int xt_ct_target_v0(struct sk_buff *skb, - const struct xt_action_param *par) +static inline int xt_ct_target(struct sk_buff *skb, struct nf_conn *ct) { - const struct xt_ct_target_info *info = par->targinfo; - struct nf_conn *ct = info->ct; - /* Previously seen (loopback)? Ignore. */ if (skb->nfct != NULL) return XT_CONTINUE; @@ -37,21 +33,22 @@ static unsigned int xt_ct_target_v0(struct sk_buff *skb, return XT_CONTINUE; } -static unsigned int xt_ct_target_v1(struct sk_buff *skb, +static unsigned int xt_ct_target_v0(struct sk_buff *skb, const struct xt_action_param *par) { - const struct xt_ct_target_info_v1 *info = par->targinfo; + const struct xt_ct_target_info *info = par->targinfo; struct nf_conn *ct = info->ct; - /* Previously seen (loopback)? Ignore. */ - if (skb->nfct != NULL) - return XT_CONTINUE; + return xt_ct_target(skb, ct); +} - atomic_inc(&ct->ct_general.use); - skb->nfct = &ct->ct_general; - skb->nfctinfo = IP_CT_NEW; +static unsigned int xt_ct_target_v1(struct sk_buff *skb, + const struct xt_action_param *par) +{ + const struct xt_ct_target_info_v1 *info = par->targinfo; + struct nf_conn *ct = info->ct; - return XT_CONTINUE; + return xt_ct_target(skb, ct); } static u8 xt_ct_find_proto(const struct xt_tgchk_param *par) @@ -104,63 +101,6 @@ xt_ct_set_helper(struct nf_conn *ct, const char *helper_name, return 0; } -static int xt_ct_tg_check_v0(const struct xt_tgchk_param *par) -{ - struct xt_ct_target_info *info = par->targinfo; - struct nf_conntrack_tuple t; - struct nf_conn *ct; - int ret; - - if (info->flags & ~XT_CT_NOTRACK) - return -EINVAL; - - if (info->flags & XT_CT_NOTRACK) { - ct = nf_ct_untracked_get(); - atomic_inc(&ct->ct_general.use); - goto out; - } - -#ifndef CONFIG_NF_CONNTRACK_ZONES - if (info->zone) - goto err1; -#endif - - ret = nf_ct_l3proto_try_module_get(par->family); - if (ret < 0) - goto err1; - - memset(&t, 0, sizeof(t)); - ct = nf_conntrack_alloc(par->net, info->zone, &t, &t, GFP_KERNEL); - ret = PTR_ERR(ct); - if (IS_ERR(ct)) - goto err2; - - ret = 0; - if ((info->ct_events || info->exp_events) && - !nf_ct_ecache_ext_add(ct, info->ct_events, info->exp_events, - GFP_KERNEL)) - goto err3; - - if (info->helper[0]) { - ret = xt_ct_set_helper(ct, info->helper, par); - if (ret < 0) - goto err3; - } - - __set_bit(IPS_TEMPLATE_BIT, &ct->status); - __set_bit(IPS_CONFIRMED_BIT, &ct->status); -out: - info->ct = ct; - return 0; - -err3: - nf_conntrack_free(ct); -err2: - nf_ct_l3proto_module_put(par->family); -err1: - return ret; -} - #ifdef CONFIG_NF_CONNTRACK_TIMEOUT static void __xt_ct_tg_timeout_put(struct ctnl_timeout *timeout) { @@ -238,15 +178,12 @@ out: #endif } -static int xt_ct_tg_check_v1(const struct xt_tgchk_param *par) +static int xt_ct_tg_check(const struct xt_tgchk_param *par, + struct xt_ct_target_info_v1 *info) { - struct xt_ct_target_info_v1 *info = par->targinfo; struct nf_conntrack_tuple t; struct nf_conn *ct; - int ret; - - if (info->flags & ~XT_CT_NOTRACK) - return -EINVAL; + int ret = -EOPNOTSUPP; if (info->flags & XT_CT_NOTRACK) { ct = nf_ct_untracked_get(); @@ -289,6 +226,10 @@ static int xt_ct_tg_check_v1(const struct xt_tgchk_param *par) __set_bit(IPS_TEMPLATE_BIT, &ct->status); __set_bit(IPS_CONFIRMED_BIT, &ct->status); + + /* Overload tuple linked list to put us in template list. */ + hlist_nulls_add_head_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode, + &par->net->ct.tmpl); out: info->ct = ct; return 0; @@ -301,20 +242,49 @@ err1: return ret; } -static void xt_ct_tg_destroy_v0(const struct xt_tgdtor_param *par) +static int xt_ct_tg_check_v0(const struct xt_tgchk_param *par) { struct xt_ct_target_info *info = par->targinfo; - struct nf_conn *ct = info->ct; - struct nf_conn_help *help; + struct xt_ct_target_info_v1 info_v1 = { + .flags = info->flags, + .zone = info->zone, + .ct_events = info->ct_events, + .exp_events = info->exp_events, + }; + int ret; - if (!nf_ct_is_untracked(ct)) { - help = nfct_help(ct); - if (help) - module_put(help->helper->me); + if (info->flags & ~XT_CT_NOTRACK) + return -EINVAL; - nf_ct_l3proto_module_put(par->family); - } - nf_ct_put(info->ct); + memcpy(info_v1.helper, info->helper, sizeof(info->helper)); + + ret = xt_ct_tg_check(par, &info_v1); + if (ret < 0) + return ret; + + info->ct = info_v1.ct; + + return ret; +} + +static int xt_ct_tg_check_v1(const struct xt_tgchk_param *par) +{ + struct xt_ct_target_info_v1 *info = par->targinfo; + + if (info->flags & ~XT_CT_NOTRACK) + return -EINVAL; + + return xt_ct_tg_check(par, par->targinfo); +} + +static int xt_ct_tg_check_v2(const struct xt_tgchk_param *par) +{ + struct xt_ct_target_info_v1 *info = par->targinfo; + + if (info->flags & ~XT_CT_MASK) + return -EINVAL; + + return xt_ct_tg_check(par, par->targinfo); } static void xt_ct_destroy_timeout(struct nf_conn *ct) @@ -335,9 +305,9 @@ static void xt_ct_destroy_timeout(struct nf_conn *ct) #endif } -static void xt_ct_tg_destroy_v1(const struct xt_tgdtor_param *par) +static void xt_ct_tg_destroy(const struct xt_tgdtor_param *par, + struct xt_ct_target_info_v1 *info) { - struct xt_ct_target_info_v1 *info = par->targinfo; struct nf_conn *ct = info->ct; struct nf_conn_help *help; @@ -353,6 +323,26 @@ static void xt_ct_tg_destroy_v1(const struct xt_tgdtor_param *par) nf_ct_put(info->ct); } +static void xt_ct_tg_destroy_v0(const struct xt_tgdtor_param *par) +{ + struct xt_ct_target_info *info = par->targinfo; + struct xt_ct_target_info_v1 info_v1 = { + .flags = info->flags, + .zone = info->zone, + .ct_events = info->ct_events, + .exp_events = info->exp_events, + .ct = info->ct, + }; + memcpy(info_v1.helper, info->helper, sizeof(info->helper)); + + xt_ct_tg_destroy(par, &info_v1); +} + +static void xt_ct_tg_destroy_v1(const struct xt_tgdtor_param *par) +{ + xt_ct_tg_destroy(par, par->targinfo); +} + static struct xt_target xt_ct_tg_reg[] __read_mostly = { { .name = "CT", @@ -375,16 +365,73 @@ static struct xt_target xt_ct_tg_reg[] __read_mostly = { .table = "raw", .me = THIS_MODULE, }, + { + .name = "CT", + .family = NFPROTO_UNSPEC, + .revision = 2, + .targetsize = sizeof(struct xt_ct_target_info_v1), + .checkentry = xt_ct_tg_check_v2, + .destroy = xt_ct_tg_destroy_v1, + .target = xt_ct_target_v1, + .table = "raw", + .me = THIS_MODULE, + }, +}; + +static unsigned int +notrack_tg(struct sk_buff *skb, const struct xt_action_param *par) +{ + /* Previously seen (loopback)? Ignore. */ + if (skb->nfct != NULL) + return XT_CONTINUE; + + skb->nfct = &nf_ct_untracked_get()->ct_general; + skb->nfctinfo = IP_CT_NEW; + nf_conntrack_get(skb->nfct); + + return XT_CONTINUE; +} + +static int notrack_chk(const struct xt_tgchk_param *par) +{ + if (!par->net->xt.notrack_deprecated_warning) { + pr_info("netfilter: NOTRACK target is deprecated, " + "use CT instead or upgrade iptables\n"); + par->net->xt.notrack_deprecated_warning = true; + } + return 0; +} + +static struct xt_target notrack_tg_reg __read_mostly = { + .name = "NOTRACK", + .revision = 0, + .family = NFPROTO_UNSPEC, + .checkentry = notrack_chk, + .target = notrack_tg, + .table = "raw", + .me = THIS_MODULE, }; static int __init xt_ct_tg_init(void) { - return xt_register_targets(xt_ct_tg_reg, ARRAY_SIZE(xt_ct_tg_reg)); + int ret; + + ret = xt_register_target(¬rack_tg_reg); + if (ret < 0) + return ret; + + ret = xt_register_targets(xt_ct_tg_reg, ARRAY_SIZE(xt_ct_tg_reg)); + if (ret < 0) { + xt_unregister_target(¬rack_tg_reg); + return ret; + } + return 0; } static void __exit xt_ct_tg_exit(void) { xt_unregister_targets(xt_ct_tg_reg, ARRAY_SIZE(xt_ct_tg_reg)); + xt_unregister_target(¬rack_tg_reg); } module_init(xt_ct_tg_init); @@ -394,3 +441,5 @@ MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Xtables: connection tracking target"); MODULE_ALIAS("ipt_CT"); MODULE_ALIAS("ip6t_CT"); +MODULE_ALIAS("ipt_NOTRACK"); +MODULE_ALIAS("ip6t_NOTRACK"); diff --git a/net/netfilter/xt_bpf.c b/net/netfilter/xt_bpf.c new file mode 100644 index 00000000000..12d4da8e6c7 --- /dev/null +++ b/net/netfilter/xt_bpf.c @@ -0,0 +1,73 @@ +/* Xtables module to match packets using a BPF filter. + * Copyright 2013 Google Inc. + * Written by Willem de Bruijn <willemb@google.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/module.h> +#include <linux/skbuff.h> +#include <linux/filter.h> + +#include <linux/netfilter/xt_bpf.h> +#include <linux/netfilter/x_tables.h> + +MODULE_AUTHOR("Willem de Bruijn <willemb@google.com>"); +MODULE_DESCRIPTION("Xtables: BPF filter match"); +MODULE_LICENSE("GPL"); +MODULE_ALIAS("ipt_bpf"); +MODULE_ALIAS("ip6t_bpf"); + +static int bpf_mt_check(const struct xt_mtchk_param *par) +{ + struct xt_bpf_info *info = par->matchinfo; + struct sock_fprog program; + + program.len = info->bpf_program_num_elem; + program.filter = (struct sock_filter __user *) info->bpf_program; + if (sk_unattached_filter_create(&info->filter, &program)) { + pr_info("bpf: check failed: parse error\n"); + return -EINVAL; + } + + return 0; +} + +static bool bpf_mt(const struct sk_buff *skb, struct xt_action_param *par) +{ + const struct xt_bpf_info *info = par->matchinfo; + + return SK_RUN_FILTER(info->filter, skb); +} + +static void bpf_mt_destroy(const struct xt_mtdtor_param *par) +{ + const struct xt_bpf_info *info = par->matchinfo; + sk_unattached_filter_destroy(info->filter); +} + +static struct xt_match bpf_mt_reg __read_mostly = { + .name = "bpf", + .revision = 0, + .family = NFPROTO_UNSPEC, + .checkentry = bpf_mt_check, + .match = bpf_mt, + .destroy = bpf_mt_destroy, + .matchsize = sizeof(struct xt_bpf_info), + .me = THIS_MODULE, +}; + +static int __init bpf_mt_init(void) +{ + return xt_register_match(&bpf_mt_reg); +} + +static void __exit bpf_mt_exit(void) +{ + xt_unregister_match(&bpf_mt_reg); +} + +module_init(bpf_mt_init); +module_exit(bpf_mt_exit); diff --git a/net/netfilter/xt_connlabel.c b/net/netfilter/xt_connlabel.c new file mode 100644 index 00000000000..9f8719df200 --- /dev/null +++ b/net/netfilter/xt_connlabel.c @@ -0,0 +1,99 @@ +/* + * (C) 2013 Astaro GmbH & Co KG + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/module.h> +#include <linux/skbuff.h> +#include <net/netfilter/nf_conntrack.h> +#include <net/netfilter/nf_conntrack_labels.h> +#include <linux/netfilter/x_tables.h> + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Florian Westphal <fw@strlen.de>"); +MODULE_DESCRIPTION("Xtables: add/match connection trackling labels"); +MODULE_ALIAS("ipt_connlabel"); +MODULE_ALIAS("ip6t_connlabel"); + +static bool +connlabel_mt(const struct sk_buff *skb, struct xt_action_param *par) +{ + const struct xt_connlabel_mtinfo *info = par->matchinfo; + enum ip_conntrack_info ctinfo; + struct nf_conn *ct; + bool invert = info->options & XT_CONNLABEL_OP_INVERT; + + ct = nf_ct_get(skb, &ctinfo); + if (ct == NULL || nf_ct_is_untracked(ct)) + return invert; + + if (info->options & XT_CONNLABEL_OP_SET) + return (nf_connlabel_set(ct, info->bit) == 0) ^ invert; + + return nf_connlabel_match(ct, info->bit) ^ invert; +} + +static int connlabel_mt_check(const struct xt_mtchk_param *par) +{ + const int options = XT_CONNLABEL_OP_INVERT | + XT_CONNLABEL_OP_SET; + struct xt_connlabel_mtinfo *info = par->matchinfo; + int ret; + size_t words; + + if (info->bit > XT_CONNLABEL_MAXBIT) + return -ERANGE; + + if (info->options & ~options) { + pr_err("Unknown options in mask %x\n", info->options); + return -EINVAL; + } + + ret = nf_ct_l3proto_try_module_get(par->family); + if (ret < 0) { + pr_info("cannot load conntrack support for proto=%u\n", + par->family); + return ret; + } + + par->net->ct.labels_used++; + words = BITS_TO_LONGS(info->bit+1); + if (words > par->net->ct.label_words) + par->net->ct.label_words = words; + + return ret; +} + +static void connlabel_mt_destroy(const struct xt_mtdtor_param *par) +{ + par->net->ct.labels_used--; + if (par->net->ct.labels_used == 0) + par->net->ct.label_words = 0; + nf_ct_l3proto_module_put(par->family); +} + +static struct xt_match connlabels_mt_reg __read_mostly = { + .name = "connlabel", + .family = NFPROTO_UNSPEC, + .checkentry = connlabel_mt_check, + .match = connlabel_mt, + .matchsize = sizeof(struct xt_connlabel_mtinfo), + .destroy = connlabel_mt_destroy, + .me = THIS_MODULE, +}; + +static int __init connlabel_mt_init(void) +{ + return xt_register_match(&connlabels_mt_reg); +} + +static void __exit connlabel_mt_exit(void) +{ + xt_unregister_match(&connlabels_mt_reg); +} + +module_init(connlabel_mt_init); +module_exit(connlabel_mt_exit); diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c index 26a668a84aa..98218c896d2 100644 --- a/net/netfilter/xt_hashlimit.c +++ b/net/netfilter/xt_hashlimit.c @@ -157,11 +157,22 @@ dsthash_find(const struct xt_hashlimit_htable *ht, /* allocate dsthash_ent, initialize dst, put in htable and lock it */ static struct dsthash_ent * dsthash_alloc_init(struct xt_hashlimit_htable *ht, - const struct dsthash_dst *dst) + const struct dsthash_dst *dst, bool *race) { struct dsthash_ent *ent; spin_lock(&ht->lock); + + /* Two or more packets may race to create the same entry in the + * hashtable, double check if this packet lost race. + */ + ent = dsthash_find(ht, dst); + if (ent != NULL) { + spin_unlock(&ht->lock); + *race = true; + return ent; + } + /* initialize hash with random val at the time we allocate * the first hashtable entry */ if (unlikely(!ht->rnd_initialized)) { @@ -318,7 +329,10 @@ static void htable_destroy(struct xt_hashlimit_htable *hinfo) parent = hashlimit_net->ipt_hashlimit; else parent = hashlimit_net->ip6t_hashlimit; - remove_proc_entry(hinfo->pde->name, parent); + + if(parent != NULL) + remove_proc_entry(hinfo->pde->name, parent); + htable_selective_cleanup(hinfo, select_all); vfree(hinfo); } @@ -585,6 +599,7 @@ hashlimit_mt(const struct sk_buff *skb, struct xt_action_param *par) unsigned long now = jiffies; struct dsthash_ent *dh; struct dsthash_dst dst; + bool race = false; u32 cost; if (hashlimit_init_dst(hinfo, &dst, skb, par->thoff) < 0) @@ -593,13 +608,18 @@ hashlimit_mt(const struct sk_buff *skb, struct xt_action_param *par) rcu_read_lock_bh(); dh = dsthash_find(hinfo, &dst); if (dh == NULL) { - dh = dsthash_alloc_init(hinfo, &dst); + dh = dsthash_alloc_init(hinfo, &dst, &race); if (dh == NULL) { rcu_read_unlock_bh(); goto hotdrop; + } else if (race) { + /* Already got an entry, update expiration timeout */ + dh->expires = now + msecs_to_jiffies(hinfo->cfg.expire); + rateinfo_recalc(dh, now, hinfo->cfg.mode); + } else { + dh->expires = jiffies + msecs_to_jiffies(hinfo->cfg.expire); + rateinfo_init(dh, hinfo); } - dh->expires = jiffies + msecs_to_jiffies(hinfo->cfg.expire); - rateinfo_init(dh, hinfo); } else { /* update expiration timeout */ dh->expires = now + msecs_to_jiffies(hinfo->cfg.expire); @@ -847,7 +867,7 @@ static int __net_init hashlimit_proc_net_init(struct net *net) #if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) hashlimit_net->ip6t_hashlimit = proc_mkdir("ip6t_hashlimit", net->proc_net); if (!hashlimit_net->ip6t_hashlimit) { - proc_net_remove(net, "ipt_hashlimit"); + remove_proc_entry("ipt_hashlimit", net->proc_net); return -ENOMEM; } #endif @@ -856,9 +876,30 @@ static int __net_init hashlimit_proc_net_init(struct net *net) static void __net_exit hashlimit_proc_net_exit(struct net *net) { - proc_net_remove(net, "ipt_hashlimit"); + struct xt_hashlimit_htable *hinfo; + struct hlist_node *pos; + struct proc_dir_entry *pde; + struct hashlimit_net *hashlimit_net = hashlimit_pernet(net); + + /* recent_net_exit() is called before recent_mt_destroy(). Make sure + * that the parent xt_recent proc entry is is empty before trying to + * remove it. + */ + mutex_lock(&hashlimit_mutex); + pde = hashlimit_net->ipt_hashlimit; + if (pde == NULL) + pde = hashlimit_net->ip6t_hashlimit; + + hlist_for_each_entry(hinfo, pos, &hashlimit_net->htables, node) + remove_proc_entry(hinfo->pde->name, pde); + + hashlimit_net->ipt_hashlimit = NULL; + hashlimit_net->ip6t_hashlimit = NULL; + mutex_unlock(&hashlimit_mutex); + + remove_proc_entry("ipt_hashlimit", net->proc_net); #if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) - proc_net_remove(net, "ip6t_hashlimit"); + remove_proc_entry("ip6t_hashlimit", net->proc_net); #endif } @@ -872,9 +913,6 @@ static int __net_init hashlimit_net_init(struct net *net) static void __net_exit hashlimit_net_exit(struct net *net) { - struct hashlimit_net *hashlimit_net = hashlimit_pernet(net); - - BUG_ON(!hlist_empty(&hashlimit_net->htables)); hashlimit_proc_net_exit(net); } diff --git a/net/netfilter/xt_recent.c b/net/netfilter/xt_recent.c index 4635c9b0045..31bf233dae9 100644 --- a/net/netfilter/xt_recent.c +++ b/net/netfilter/xt_recent.c @@ -29,6 +29,7 @@ #include <linux/skbuff.h> #include <linux/inet.h> #include <linux/slab.h> +#include <linux/vmalloc.h> #include <net/net_namespace.h> #include <net/netns/generic.h> @@ -310,6 +311,14 @@ out: return ret; } +static void recent_table_free(void *addr) +{ + if (is_vmalloc_addr(addr)) + vfree(addr); + else + kfree(addr); +} + static int recent_mt_check(const struct xt_mtchk_param *par, const struct xt_recent_mtinfo_v1 *info) { @@ -322,6 +331,7 @@ static int recent_mt_check(const struct xt_mtchk_param *par, #endif unsigned int i; int ret = -EINVAL; + size_t sz; if (unlikely(!hash_rnd_inited)) { get_random_bytes(&hash_rnd, sizeof(hash_rnd)); @@ -360,8 +370,11 @@ static int recent_mt_check(const struct xt_mtchk_param *par, goto out; } - t = kzalloc(sizeof(*t) + sizeof(t->iphash[0]) * ip_list_hash_size, - GFP_KERNEL); + sz = sizeof(*t) + sizeof(t->iphash[0]) * ip_list_hash_size; + if (sz <= PAGE_SIZE) + t = kzalloc(sz, GFP_KERNEL); + else + t = vzalloc(sz); if (t == NULL) { ret = -ENOMEM; goto out; @@ -377,14 +390,14 @@ static int recent_mt_check(const struct xt_mtchk_param *par, uid = make_kuid(&init_user_ns, ip_list_uid); gid = make_kgid(&init_user_ns, ip_list_gid); if (!uid_valid(uid) || !gid_valid(gid)) { - kfree(t); + recent_table_free(t); ret = -EINVAL; goto out; } pde = proc_create_data(t->name, ip_list_perms, recent_net->xt_recent, &recent_mt_fops, t); if (pde == NULL) { - kfree(t); + recent_table_free(t); ret = -ENOMEM; goto out; } @@ -431,10 +444,11 @@ static void recent_mt_destroy(const struct xt_mtdtor_param *par) list_del(&t->list); spin_unlock_bh(&recent_lock); #ifdef CONFIG_PROC_FS - remove_proc_entry(t->name, recent_net->xt_recent); + if (recent_net->xt_recent != NULL) + remove_proc_entry(t->name, recent_net->xt_recent); #endif recent_table_flush(t); - kfree(t); + recent_table_free(t); } mutex_unlock(&recent_mutex); } @@ -615,7 +629,21 @@ static int __net_init recent_proc_net_init(struct net *net) static void __net_exit recent_proc_net_exit(struct net *net) { - proc_net_remove(net, "xt_recent"); + struct recent_net *recent_net = recent_pernet(net); + struct recent_table *t; + + /* recent_net_exit() is called before recent_mt_destroy(). Make sure + * that the parent xt_recent proc entry is is empty before trying to + * remove it. + */ + spin_lock_bh(&recent_lock); + list_for_each_entry(t, &recent_net->tables, list) + remove_proc_entry(t->name, recent_net->xt_recent); + + recent_net->xt_recent = NULL; + spin_unlock_bh(&recent_lock); + + remove_proc_entry("xt_recent", net->proc_net); } #else static inline int recent_proc_net_init(struct net *net) @@ -638,9 +666,6 @@ static int __net_init recent_net_init(struct net *net) static void __net_exit recent_net_exit(struct net *net) { - struct recent_net *recent_net = recent_pernet(net); - - BUG_ON(!list_empty(&recent_net->tables)); recent_proc_net_exit(net); } |