diff options
Diffstat (limited to 'net/netfilter')
57 files changed, 4284 insertions, 2102 deletions
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 1a92063c73a4..56a2531a3402 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -71,12 +71,17 @@ config NF_CONNTRACK To compile it as a module, choose M here. If unsure, say N. -config NF_LOG_COMMON - tristate - -config NF_LOG_NETDEV - tristate "Netdev packet logging" - select NF_LOG_COMMON +config NF_LOG_SYSLOG + tristate "Syslog packet logging" + default m if NETFILTER_ADVANCED=n + help + This option enable support for packet logging via syslog. + It supports IPv4, IPV6, ARP and common transport protocols such + as TCP and UDP. + This is a simpler but less flexible logging method compared to + CONFIG_NETFILTER_NETLINK_LOG. + If both are enabled the backend to use can be configured at run-time + by means of per-address-family sysctl tunables. if NF_CONNTRACK config NETFILTER_CONNCOUNT @@ -723,6 +728,16 @@ config NETFILTER_XTABLES if NETFILTER_XTABLES +config NETFILTER_XTABLES_COMPAT + bool "Netfilter Xtables 32bit support" + depends on COMPAT + default y + help + This option provides a translation layer to run 32bit arp,ip(6),ebtables + binaries on 64bit kernels. + + If unsure, say N. + comment "Xtables combined modules" config NETFILTER_XT_MARK @@ -922,8 +937,7 @@ config NETFILTER_XT_TARGET_LED config NETFILTER_XT_TARGET_LOG tristate "LOG target support" - select NF_LOG_COMMON - select NF_LOG_IPV4 + select NF_LOG_SYSLOG select NF_LOG_IPV6 if IP6_NF_IPTABLES default m if NETFILTER_ADVANCED=n help diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index 33da7bf1b68e..e80e010354b1 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -48,11 +48,7 @@ obj-$(CONFIG_NF_CONNTRACK_TFTP) += nf_conntrack_tftp.o nf_nat-y := nf_nat_core.o nf_nat_proto.o nf_nat_helper.o -# generic transport layer logging -obj-$(CONFIG_NF_LOG_COMMON) += nf_log_common.o - -# packet logging for netdev family -obj-$(CONFIG_NF_LOG_NETDEV) += nf_log_netdev.o +obj-$(CONFIG_NF_LOG_SYSLOG) += nf_log_syslog.o obj-$(CONFIG_NF_NAT) += nf_nat.o nf_nat-$(CONFIG_NF_NAT_REDIRECT) += nf_nat_redirect.o diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index 89009c82a6b2..de2d20c37cda 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -963,20 +963,9 @@ static struct nlmsghdr * start_msg(struct sk_buff *skb, u32 portid, u32 seq, unsigned int flags, enum ipset_cmd cmd) { - struct nlmsghdr *nlh; - struct nfgenmsg *nfmsg; - - nlh = nlmsg_put(skb, portid, seq, nfnl_msg_type(NFNL_SUBSYS_IPSET, cmd), - sizeof(*nfmsg), flags); - if (!nlh) - return NULL; - - nfmsg = nlmsg_data(nlh); - nfmsg->nfgen_family = NFPROTO_IPV4; - nfmsg->version = NFNETLINK_V0; - nfmsg->res_id = 0; - - return nlh; + return nfnl_msg_put(skb, portid, seq, + nfnl_msg_type(NFNL_SUBSYS_IPSET, cmd), flags, + NFPROTO_IPV4, NFNETLINK_V0, 0); } /* Create a set */ @@ -1042,26 +1031,22 @@ find_free_id(struct ip_set_net *inst, const char *name, ip_set_id_t *index, return 0; } -static int ip_set_none(struct net *net, struct sock *ctnl, struct sk_buff *skb, - const struct nlmsghdr *nlh, - const struct nlattr * const attr[], - struct netlink_ext_ack *extack) +static int ip_set_none(struct sk_buff *skb, const struct nfnl_info *info, + const struct nlattr * const attr[]) { return -EOPNOTSUPP; } -static int ip_set_create(struct net *net, struct sock *ctnl, - struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const attr[], - struct netlink_ext_ack *extack) +static int ip_set_create(struct sk_buff *skb, const struct nfnl_info *info, + const struct nlattr * const attr[]) { - struct ip_set_net *inst = ip_set_pernet(net); + struct ip_set_net *inst = ip_set_pernet(info->net); struct ip_set *set, *clash = NULL; ip_set_id_t index = IPSET_INVALID_ID; struct nlattr *tb[IPSET_ATTR_CREATE_MAX + 1] = {}; const char *name, *typename; u8 family, revision; - u32 flags = flag_exist(nlh); + u32 flags = flag_exist(info->nlh); int ret = 0; if (unlikely(protocol_min_failed(attr) || @@ -1112,7 +1097,7 @@ static int ip_set_create(struct net *net, struct sock *ctnl, /* Set create flags depending on the type revision */ set->flags |= set->type->create_flags[revision]; - ret = set->type->create(net, set, tb, flags); + ret = set->type->create(info->net, set, tb, flags); if (ret != 0) goto put_out; @@ -1194,12 +1179,10 @@ ip_set_destroy_set(struct ip_set *set) kfree(set); } -static int ip_set_destroy(struct net *net, struct sock *ctnl, - struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const attr[], - struct netlink_ext_ack *extack) +static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info, + const struct nlattr * const attr[]) { - struct ip_set_net *inst = ip_set_pernet(net); + struct ip_set_net *inst = ip_set_pernet(info->net); struct ip_set *s; ip_set_id_t i; int ret = 0; @@ -1241,7 +1224,7 @@ static int ip_set_destroy(struct net *net, struct sock *ctnl, /* Modified by ip_set_destroy() only, which is serialized */ inst->is_destroyed = false; } else { - u32 flags = flag_exist(nlh); + u32 flags = flag_exist(info->nlh); s = find_set_and_id(inst, nla_data(attr[IPSET_ATTR_SETNAME]), &i); if (!s) { @@ -1275,12 +1258,10 @@ ip_set_flush_set(struct ip_set *set) ip_set_unlock(set); } -static int ip_set_flush(struct net *net, struct sock *ctnl, struct sk_buff *skb, - const struct nlmsghdr *nlh, - const struct nlattr * const attr[], - struct netlink_ext_ack *extack) +static int ip_set_flush(struct sk_buff *skb, const struct nfnl_info *info, + const struct nlattr * const attr[]) { - struct ip_set_net *inst = ip_set_pernet(net); + struct ip_set_net *inst = ip_set_pernet(info->net); struct ip_set *s; ip_set_id_t i; @@ -1315,12 +1296,10 @@ ip_set_setname2_policy[IPSET_ATTR_CMD_MAX + 1] = { .len = IPSET_MAXNAMELEN - 1 }, }; -static int ip_set_rename(struct net *net, struct sock *ctnl, - struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const attr[], - struct netlink_ext_ack *extack) +static int ip_set_rename(struct sk_buff *skb, const struct nfnl_info *info, + const struct nlattr * const attr[]) { - struct ip_set_net *inst = ip_set_pernet(net); + struct ip_set_net *inst = ip_set_pernet(info->net); struct ip_set *set, *s; const char *name2; ip_set_id_t i; @@ -1365,12 +1344,10 @@ out: * so the ip_set_list always contains valid pointers to the sets. */ -static int ip_set_swap(struct net *net, struct sock *ctnl, struct sk_buff *skb, - const struct nlmsghdr *nlh, - const struct nlattr * const attr[], - struct netlink_ext_ack *extack) +static int ip_set_swap(struct sk_buff *skb, const struct nfnl_info *info, + const struct nlattr * const attr[]) { - struct ip_set_net *inst = ip_set_pernet(net); + struct ip_set_net *inst = ip_set_pernet(info->net); struct ip_set *from, *to; ip_set_id_t from_id, to_id; char from_name[IPSET_MAXNAMELEN]; @@ -1680,10 +1657,8 @@ out: return ret < 0 ? ret : skb->len; } -static int ip_set_dump(struct net *net, struct sock *ctnl, struct sk_buff *skb, - const struct nlmsghdr *nlh, - const struct nlattr * const attr[], - struct netlink_ext_ack *extack) +static int ip_set_dump(struct sk_buff *skb, const struct nfnl_info *info, + const struct nlattr * const attr[]) { if (unlikely(protocol_min_failed(attr))) return -IPSET_ERR_PROTOCOL; @@ -1694,7 +1669,7 @@ static int ip_set_dump(struct net *net, struct sock *ctnl, struct sk_buff *skb, .dump = ip_set_dump_do, .done = ip_set_dump_done, }; - return netlink_dump_start(ctnl, skb, nlh, &c); + return netlink_dump_start(info->sk, skb, info->nlh, &c); } } @@ -1828,30 +1803,24 @@ static int ip_set_ad(struct net *net, struct sock *ctnl, return ret; } -static int ip_set_uadd(struct net *net, struct sock *ctnl, - struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const attr[], - struct netlink_ext_ack *extack) +static int ip_set_uadd(struct sk_buff *skb, const struct nfnl_info *info, + const struct nlattr * const attr[]) { - return ip_set_ad(net, ctnl, skb, - IPSET_ADD, nlh, attr, extack); + return ip_set_ad(info->net, info->sk, skb, + IPSET_ADD, info->nlh, attr, info->extack); } -static int ip_set_udel(struct net *net, struct sock *ctnl, - struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const attr[], - struct netlink_ext_ack *extack) +static int ip_set_udel(struct sk_buff *skb, const struct nfnl_info *info, + const struct nlattr * const attr[]) { - return ip_set_ad(net, ctnl, skb, - IPSET_DEL, nlh, attr, extack); + return ip_set_ad(info->net, info->sk, skb, + IPSET_DEL, info->nlh, attr, info->extack); } -static int ip_set_utest(struct net *net, struct sock *ctnl, struct sk_buff *skb, - const struct nlmsghdr *nlh, - const struct nlattr * const attr[], - struct netlink_ext_ack *extack) +static int ip_set_utest(struct sk_buff *skb, const struct nfnl_info *info, + const struct nlattr * const attr[]) { - struct ip_set_net *inst = ip_set_pernet(net); + struct ip_set_net *inst = ip_set_pernet(info->net); struct ip_set *set; struct nlattr *tb[IPSET_ATTR_ADT_MAX + 1] = {}; int ret = 0; @@ -1883,12 +1852,10 @@ static int ip_set_utest(struct net *net, struct sock *ctnl, struct sk_buff *skb, /* Get headed data of a set */ -static int ip_set_header(struct net *net, struct sock *ctnl, - struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const attr[], - struct netlink_ext_ack *extack) +static int ip_set_header(struct sk_buff *skb, const struct nfnl_info *info, + const struct nlattr * const attr[]) { - struct ip_set_net *inst = ip_set_pernet(net); + struct ip_set_net *inst = ip_set_pernet(info->net); const struct ip_set *set; struct sk_buff *skb2; struct nlmsghdr *nlh2; @@ -1906,7 +1873,7 @@ static int ip_set_header(struct net *net, struct sock *ctnl, if (!skb2) return -ENOMEM; - nlh2 = start_msg(skb2, NETLINK_CB(skb).portid, nlh->nlmsg_seq, 0, + nlh2 = start_msg(skb2, NETLINK_CB(skb).portid, info->nlh->nlmsg_seq, 0, IPSET_CMD_HEADER); if (!nlh2) goto nlmsg_failure; @@ -1918,7 +1885,8 @@ static int ip_set_header(struct net *net, struct sock *ctnl, goto nla_put_failure; nlmsg_end(skb2, nlh2); - ret = netlink_unicast(ctnl, skb2, NETLINK_CB(skb).portid, MSG_DONTWAIT); + ret = netlink_unicast(info->sk, skb2, NETLINK_CB(skb).portid, + MSG_DONTWAIT); if (ret < 0) return ret; @@ -1940,10 +1908,8 @@ static const struct nla_policy ip_set_type_policy[IPSET_ATTR_CMD_MAX + 1] = { [IPSET_ATTR_FAMILY] = { .type = NLA_U8 }, }; -static int ip_set_type(struct net *net, struct sock *ctnl, struct sk_buff *skb, - const struct nlmsghdr *nlh, - const struct nlattr * const attr[], - struct netlink_ext_ack *extack) +static int ip_set_type(struct sk_buff *skb, const struct nfnl_info *info, + const struct nlattr * const attr[]) { struct sk_buff *skb2; struct nlmsghdr *nlh2; @@ -1966,7 +1932,7 @@ static int ip_set_type(struct net *net, struct sock *ctnl, struct sk_buff *skb, if (!skb2) return -ENOMEM; - nlh2 = start_msg(skb2, NETLINK_CB(skb).portid, nlh->nlmsg_seq, 0, + nlh2 = start_msg(skb2, NETLINK_CB(skb).portid, info->nlh->nlmsg_seq, 0, IPSET_CMD_TYPE); if (!nlh2) goto nlmsg_failure; @@ -1979,7 +1945,8 @@ static int ip_set_type(struct net *net, struct sock *ctnl, struct sk_buff *skb, nlmsg_end(skb2, nlh2); pr_debug("Send TYPE, nlmsg_len: %u\n", nlh2->nlmsg_len); - ret = netlink_unicast(ctnl, skb2, NETLINK_CB(skb).portid, MSG_DONTWAIT); + ret = netlink_unicast(info->sk, skb2, NETLINK_CB(skb).portid, + MSG_DONTWAIT); if (ret < 0) return ret; @@ -1999,10 +1966,8 @@ ip_set_protocol_policy[IPSET_ATTR_CMD_MAX + 1] = { [IPSET_ATTR_PROTOCOL] = { .type = NLA_U8 }, }; -static int ip_set_protocol(struct net *net, struct sock *ctnl, - struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const attr[], - struct netlink_ext_ack *extack) +static int ip_set_protocol(struct sk_buff *skb, const struct nfnl_info *info, + const struct nlattr * const attr[]) { struct sk_buff *skb2; struct nlmsghdr *nlh2; @@ -2015,7 +1980,7 @@ static int ip_set_protocol(struct net *net, struct sock *ctnl, if (!skb2) return -ENOMEM; - nlh2 = start_msg(skb2, NETLINK_CB(skb).portid, nlh->nlmsg_seq, 0, + nlh2 = start_msg(skb2, NETLINK_CB(skb).portid, info->nlh->nlmsg_seq, 0, IPSET_CMD_PROTOCOL); if (!nlh2) goto nlmsg_failure; @@ -2025,7 +1990,8 @@ static int ip_set_protocol(struct net *net, struct sock *ctnl, goto nla_put_failure; nlmsg_end(skb2, nlh2); - ret = netlink_unicast(ctnl, skb2, NETLINK_CB(skb).portid, MSG_DONTWAIT); + ret = netlink_unicast(info->sk, skb2, NETLINK_CB(skb).portid, + MSG_DONTWAIT); if (ret < 0) return ret; @@ -2040,12 +2006,10 @@ nlmsg_failure: /* Get set by name or index, from userspace */ -static int ip_set_byname(struct net *net, struct sock *ctnl, - struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const attr[], - struct netlink_ext_ack *extack) +static int ip_set_byname(struct sk_buff *skb, const struct nfnl_info *info, + const struct nlattr * const attr[]) { - struct ip_set_net *inst = ip_set_pernet(net); + struct ip_set_net *inst = ip_set_pernet(info->net); struct sk_buff *skb2; struct nlmsghdr *nlh2; ip_set_id_t id = IPSET_INVALID_ID; @@ -2064,7 +2028,7 @@ static int ip_set_byname(struct net *net, struct sock *ctnl, if (!skb2) return -ENOMEM; - nlh2 = start_msg(skb2, NETLINK_CB(skb).portid, nlh->nlmsg_seq, 0, + nlh2 = start_msg(skb2, NETLINK_CB(skb).portid, info->nlh->nlmsg_seq, 0, IPSET_CMD_GET_BYNAME); if (!nlh2) goto nlmsg_failure; @@ -2074,7 +2038,8 @@ static int ip_set_byname(struct net *net, struct sock *ctnl, goto nla_put_failure; nlmsg_end(skb2, nlh2); - ret = netlink_unicast(ctnl, skb2, NETLINK_CB(skb).portid, MSG_DONTWAIT); + ret = netlink_unicast(info->sk, skb2, NETLINK_CB(skb).portid, + MSG_DONTWAIT); if (ret < 0) return ret; @@ -2092,12 +2057,10 @@ static const struct nla_policy ip_set_index_policy[IPSET_ATTR_CMD_MAX + 1] = { [IPSET_ATTR_INDEX] = { .type = NLA_U16 }, }; -static int ip_set_byindex(struct net *net, struct sock *ctnl, - struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const attr[], - struct netlink_ext_ack *extack) +static int ip_set_byindex(struct sk_buff *skb, const struct nfnl_info *info, + const struct nlattr * const attr[]) { - struct ip_set_net *inst = ip_set_pernet(net); + struct ip_set_net *inst = ip_set_pernet(info->net); struct sk_buff *skb2; struct nlmsghdr *nlh2; ip_set_id_t id = IPSET_INVALID_ID; @@ -2119,7 +2082,7 @@ static int ip_set_byindex(struct net *net, struct sock *ctnl, if (!skb2) return -ENOMEM; - nlh2 = start_msg(skb2, NETLINK_CB(skb).portid, nlh->nlmsg_seq, 0, + nlh2 = start_msg(skb2, NETLINK_CB(skb).portid, info->nlh->nlmsg_seq, 0, IPSET_CMD_GET_BYINDEX); if (!nlh2) goto nlmsg_failure; @@ -2128,7 +2091,8 @@ static int ip_set_byindex(struct net *net, struct sock *ctnl, goto nla_put_failure; nlmsg_end(skb2, nlh2); - ret = netlink_unicast(ctnl, skb2, NETLINK_CB(skb).portid, MSG_DONTWAIT); + ret = netlink_unicast(info->sk, skb2, NETLINK_CB(skb).portid, + MSG_DONTWAIT); if (ret < 0) return ret; @@ -2144,80 +2108,96 @@ nlmsg_failure: static const struct nfnl_callback ip_set_netlink_subsys_cb[IPSET_MSG_MAX] = { [IPSET_CMD_NONE] = { .call = ip_set_none, + .type = NFNL_CB_MUTEX, .attr_count = IPSET_ATTR_CMD_MAX, }, [IPSET_CMD_CREATE] = { .call = ip_set_create, + .type = NFNL_CB_MUTEX, .attr_count = IPSET_ATTR_CMD_MAX, .policy = ip_set_create_policy, }, [IPSET_CMD_DESTROY] = { .call = ip_set_destroy, + .type = NFNL_CB_MUTEX, .attr_count = IPSET_ATTR_CMD_MAX, .policy = ip_set_setname_policy, }, [IPSET_CMD_FLUSH] = { .call = ip_set_flush, + .type = NFNL_CB_MUTEX, .attr_count = IPSET_ATTR_CMD_MAX, .policy = ip_set_setname_policy, }, [IPSET_CMD_RENAME] = { .call = ip_set_rename, + .type = NFNL_CB_MUTEX, .attr_count = IPSET_ATTR_CMD_MAX, .policy = ip_set_setname2_policy, }, [IPSET_CMD_SWAP] = { .call = ip_set_swap, + .type = NFNL_CB_MUTEX, .attr_count = IPSET_ATTR_CMD_MAX, .policy = ip_set_setname2_policy, }, [IPSET_CMD_LIST] = { .call = ip_set_dump, + .type = NFNL_CB_MUTEX, .attr_count = IPSET_ATTR_CMD_MAX, .policy = ip_set_dump_policy, }, [IPSET_CMD_SAVE] = { .call = ip_set_dump, + .type = NFNL_CB_MUTEX, .attr_count = IPSET_ATTR_CMD_MAX, .policy = ip_set_setname_policy, }, [IPSET_CMD_ADD] = { .call = ip_set_uadd, + .type = NFNL_CB_MUTEX, .attr_count = IPSET_ATTR_CMD_MAX, .policy = ip_set_adt_policy, }, [IPSET_CMD_DEL] = { .call = ip_set_udel, + .type = NFNL_CB_MUTEX, .attr_count = IPSET_ATTR_CMD_MAX, .policy = ip_set_adt_policy, }, [IPSET_CMD_TEST] = { .call = ip_set_utest, + .type = NFNL_CB_MUTEX, .attr_count = IPSET_ATTR_CMD_MAX, .policy = ip_set_adt_policy, }, [IPSET_CMD_HEADER] = { .call = ip_set_header, + .type = NFNL_CB_MUTEX, .attr_count = IPSET_ATTR_CMD_MAX, .policy = ip_set_setname_policy, }, [IPSET_CMD_TYPE] = { .call = ip_set_type, + .type = NFNL_CB_MUTEX, .attr_count = IPSET_ATTR_CMD_MAX, .policy = ip_set_type_policy, }, [IPSET_CMD_PROTOCOL] = { .call = ip_set_protocol, + .type = NFNL_CB_MUTEX, .attr_count = IPSET_ATTR_CMD_MAX, .policy = ip_set_protocol_policy, }, [IPSET_CMD_GET_BYNAME] = { .call = ip_set_byname, + .type = NFNL_CB_MUTEX, .attr_count = IPSET_ATTR_CMD_MAX, .policy = ip_set_setname_policy, }, [IPSET_CMD_GET_BYINDEX] = { .call = ip_set_byindex, + .type = NFNL_CB_MUTEX, .attr_count = IPSET_ATTR_CMD_MAX, .policy = ip_set_index_policy, }, diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 0c132ff9b446..128690c512df 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -2398,7 +2398,7 @@ static int __net_init __ip_vs_init(struct net *net) if (ipvs == NULL) return -ENOMEM; - /* Hold the beast until a service is registerd */ + /* Hold the beast until a service is registered */ ipvs->enable = 0; ipvs->net = net; /* Counters used for creating unique names */ diff --git a/net/netfilter/ipvs/ip_vs_ftp.c b/net/netfilter/ipvs/ip_vs_ftp.c index cf925906f59b..ef1f45e43b63 100644 --- a/net/netfilter/ipvs/ip_vs_ftp.c +++ b/net/netfilter/ipvs/ip_vs_ftp.c @@ -591,8 +591,6 @@ static int __net_init __ip_vs_ftp_init(struct net *net) ret = register_ip_vs_app_inc(ipvs, app, app->protocol, ports[i]); if (ret) goto err_unreg; - pr_info("%s: loaded support on port[%d] = %u\n", - app->name, i, ports[i]); } return 0; diff --git a/net/netfilter/nf_conntrack_acct.c b/net/netfilter/nf_conntrack_acct.c index 2ccda8ace796..91bc8df3e4b0 100644 --- a/net/netfilter/nf_conntrack_acct.c +++ b/net/netfilter/nf_conntrack_acct.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-only -/* Accouting handling for netfilter. */ +/* Accounting handling for netfilter. */ /* * (C) 2008 Krzysztof Piotr Oledzki <ole@ans.pl> diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index ff0168736f6e..e0befcf8113a 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -55,6 +55,8 @@ #include "nf_internals.h" +extern unsigned int nf_conntrack_net_id; + __cacheline_aligned_in_smp spinlock_t nf_conntrack_locks[CONNTRACK_LOCKS]; EXPORT_SYMBOL_GPL(nf_conntrack_locks); @@ -85,6 +87,8 @@ static __read_mostly bool nf_conntrack_locks_all; static struct conntrack_gc_work conntrack_gc_work; +extern unsigned int nf_conntrack_net_id; + void nf_conntrack_lock(spinlock_t *lock) __acquires(lock) { /* 1) Acquire the lock */ @@ -656,6 +660,7 @@ static void nf_ct_delete_from_lists(struct nf_conn *ct) bool nf_ct_delete(struct nf_conn *ct, u32 portid, int report) { struct nf_conn_tstamp *tstamp; + struct net *net; if (test_and_set_bit(IPS_DYING_BIT, &ct->status)) return false; @@ -670,11 +675,13 @@ bool nf_ct_delete(struct nf_conn *ct, u32 portid, int report) * be done by event cache worker on redelivery. */ nf_ct_delete_from_lists(ct); - nf_conntrack_ecache_delayed_work(nf_ct_net(ct)); + nf_conntrack_ecache_work(nf_ct_net(ct), NFCT_ECACHE_DESTROY_FAIL); return false; } - nf_conntrack_ecache_work(nf_ct_net(ct)); + net = nf_ct_net(ct); + if (nf_conntrack_ecache_dwork_pending(net)) + nf_conntrack_ecache_work(net, NFCT_ECACHE_DESTROY_SENT); nf_ct_delete_from_lists(ct); nf_ct_put(ct); return true; @@ -1376,6 +1383,7 @@ static void gc_worker(struct work_struct *work) i = 0; hlist_nulls_for_each_entry_rcu(h, n, &ct_hash[i], hnnode) { + struct nf_conntrack_net *cnet; struct net *net; tmp = nf_ct_tuplehash_to_ctrack(h); @@ -1396,7 +1404,8 @@ static void gc_worker(struct work_struct *work) continue; net = nf_ct_net(tmp); - if (atomic_read(&net->ct.count) < nf_conntrack_max95) + cnet = net_generic(net, nf_conntrack_net_id); + if (atomic_read(&cnet->count) < nf_conntrack_max95) continue; /* need to take reference to avoid possible races */ @@ -1475,17 +1484,18 @@ __nf_conntrack_alloc(struct net *net, const struct nf_conntrack_tuple *repl, gfp_t gfp, u32 hash) { + struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id); + unsigned int ct_count; struct nf_conn *ct; /* We don't want any race condition at early drop stage */ - atomic_inc(&net->ct.count); + ct_count = atomic_inc_return(&cnet->count); - if (nf_conntrack_max && - unlikely(atomic_read(&net->ct.count) > nf_conntrack_max)) { + if (nf_conntrack_max && unlikely(ct_count > nf_conntrack_max)) { if (!early_drop(net, hash)) { if (!conntrack_gc_work.early_drop) conntrack_gc_work.early_drop = true; - atomic_dec(&net->ct.count); + atomic_dec(&cnet->count); net_warn_ratelimited("nf_conntrack: table full, dropping packet\n"); return ERR_PTR(-ENOMEM); } @@ -1520,7 +1530,7 @@ __nf_conntrack_alloc(struct net *net, atomic_set(&ct->ct_general.use, 0); return ct; out: - atomic_dec(&net->ct.count); + atomic_dec(&cnet->count); return ERR_PTR(-ENOMEM); } @@ -1537,6 +1547,7 @@ EXPORT_SYMBOL_GPL(nf_conntrack_alloc); void nf_conntrack_free(struct nf_conn *ct) { struct net *net = nf_ct_net(ct); + struct nf_conntrack_net *cnet; /* A freed object has refcnt == 0, that's * the golden rule for SLAB_TYPESAFE_BY_RCU @@ -1545,8 +1556,10 @@ void nf_conntrack_free(struct nf_conn *ct) nf_ct_ext_destroy(ct); kmem_cache_free(nf_conntrack_cachep, ct); + cnet = net_generic(net, nf_conntrack_net_id); + smp_mb__before_atomic(); - atomic_dec(&net->ct.count); + atomic_dec(&cnet->count); } EXPORT_SYMBOL_GPL(nf_conntrack_free); @@ -1567,6 +1580,7 @@ init_conntrack(struct net *net, struct nf_conn *tmpl, const struct nf_conntrack_zone *zone; struct nf_conn_timeout *timeout_ext; struct nf_conntrack_zone tmp; + struct nf_conntrack_net *cnet; if (!nf_ct_invert_tuple(&repl_tuple, tuple)) { pr_debug("Can't invert tuple.\n"); @@ -1600,7 +1614,8 @@ init_conntrack(struct net *net, struct nf_conn *tmpl, GFP_ATOMIC); local_bh_disable(); - if (net->ct.expect_count) { + cnet = net_generic(net, nf_conntrack_net_id); + if (cnet->expect_count) { spin_lock(&nf_conntrack_expect_lock); exp = nf_ct_find_expectation(net, zone, tuple); if (exp) { @@ -2302,9 +2317,11 @@ __nf_ct_unconfirmed_destroy(struct net *net) void nf_ct_unconfirmed_destroy(struct net *net) { + struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id); + might_sleep(); - if (atomic_read(&net->ct.count) > 0) { + if (atomic_read(&cnet->count) > 0) { __nf_ct_unconfirmed_destroy(net); nf_queue_nf_hook_drop(net); synchronize_net(); @@ -2316,11 +2333,12 @@ void nf_ct_iterate_cleanup_net(struct net *net, int (*iter)(struct nf_conn *i, void *data), void *data, u32 portid, int report) { + struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id); struct iter_data d; might_sleep(); - if (atomic_read(&net->ct.count) == 0) + if (atomic_read(&cnet->count) == 0) return; d.iter = iter; @@ -2349,7 +2367,9 @@ nf_ct_iterate_destroy(int (*iter)(struct nf_conn *i, void *data), void *data) down_read(&net_rwsem); for_each_net(net) { - if (atomic_read(&net->ct.count) == 0) + struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id); + + if (atomic_read(&cnet->count) == 0) continue; __nf_ct_unconfirmed_destroy(net); nf_queue_nf_hook_drop(net); @@ -2429,8 +2449,10 @@ void nf_conntrack_cleanup_net_list(struct list_head *net_exit_list) i_see_dead_people: busy = 0; list_for_each_entry(net, net_exit_list, exit_list) { + struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id); + nf_ct_iterate_cleanup(kill_all, net, 0, 0); - if (atomic_read(&net->ct.count) != 0) + if (atomic_read(&cnet->count) != 0) busy = 1; } if (busy) { @@ -2711,12 +2733,13 @@ void nf_conntrack_init_end(void) int nf_conntrack_init_net(struct net *net) { + struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id); int ret = -ENOMEM; int cpu; BUILD_BUG_ON(IP_CT_UNTRACKED == IP_CT_NUMBER); BUILD_BUG_ON_NOT_POWER_OF_2(CONNTRACK_LOCKS); - atomic_set(&net->ct.count, 0); + atomic_set(&cnet->count, 0); net->ct.pcpu_lists = alloc_percpu(struct ct_pcpu); if (!net->ct.pcpu_lists) diff --git a/net/netfilter/nf_conntrack_ecache.c b/net/netfilter/nf_conntrack_ecache.c index 7956c9f19899..759d87aef95f 100644 --- a/net/netfilter/nf_conntrack_ecache.c +++ b/net/netfilter/nf_conntrack_ecache.c @@ -27,6 +27,8 @@ #include <net/netfilter/nf_conntrack_ecache.h> #include <net/netfilter/nf_conntrack_extend.h> +extern unsigned int nf_conntrack_net_id; + static DEFINE_MUTEX(nf_ct_ecache_mutex); #define ECACHE_RETRY_WAIT (HZ/10) @@ -96,8 +98,8 @@ static enum retry_state ecache_work_evict_list(struct ct_pcpu *pcpu) static void ecache_work(struct work_struct *work) { - struct netns_ct *ctnet = - container_of(work, struct netns_ct, ecache_dwork.work); + struct nf_conntrack_net *cnet = container_of(work, struct nf_conntrack_net, ecache_dwork.work); + struct netns_ct *ctnet = cnet->ct_net; int cpu, delay = -1; struct ct_pcpu *pcpu; @@ -127,7 +129,7 @@ static void ecache_work(struct work_struct *work) ctnet->ecache_dwork_pending = delay > 0; if (delay >= 0) - schedule_delayed_work(&ctnet->ecache_dwork, delay); + schedule_delayed_work(&cnet->ecache_dwork, delay); } int nf_conntrack_eventmask_report(unsigned int eventmask, struct nf_conn *ct, @@ -344,6 +346,20 @@ void nf_ct_expect_unregister_notifier(struct net *net, } EXPORT_SYMBOL_GPL(nf_ct_expect_unregister_notifier); +void nf_conntrack_ecache_work(struct net *net, enum nf_ct_ecache_state state) +{ + struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id); + + if (state == NFCT_ECACHE_DESTROY_FAIL && + !delayed_work_pending(&cnet->ecache_dwork)) { + schedule_delayed_work(&cnet->ecache_dwork, HZ); + net->ct.ecache_dwork_pending = true; + } else if (state == NFCT_ECACHE_DESTROY_SENT) { + net->ct.ecache_dwork_pending = false; + mod_delayed_work(system_wq, &cnet->ecache_dwork, 0); + } +} + #define NF_CT_EVENTS_DEFAULT 1 static int nf_ct_events __read_mostly = NF_CT_EVENTS_DEFAULT; @@ -355,13 +371,18 @@ static const struct nf_ct_ext_type event_extend = { void nf_conntrack_ecache_pernet_init(struct net *net) { + struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id); + net->ct.sysctl_events = nf_ct_events; - INIT_DELAYED_WORK(&net->ct.ecache_dwork, ecache_work); + cnet->ct_net = &net->ct; + INIT_DELAYED_WORK(&cnet->ecache_dwork, ecache_work); } void nf_conntrack_ecache_pernet_fini(struct net *net) { - cancel_delayed_work_sync(&net->ct.ecache_dwork); + struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id); + + cancel_delayed_work_sync(&cnet->ecache_dwork); } int nf_conntrack_ecache_init(void) diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c index 42557d2b6a90..efdd391b3f72 100644 --- a/net/netfilter/nf_conntrack_expect.c +++ b/net/netfilter/nf_conntrack_expect.c @@ -43,18 +43,23 @@ unsigned int nf_ct_expect_max __read_mostly; static struct kmem_cache *nf_ct_expect_cachep __read_mostly; static unsigned int nf_ct_expect_hashrnd __read_mostly; +extern unsigned int nf_conntrack_net_id; + /* nf_conntrack_expect helper functions */ void nf_ct_unlink_expect_report(struct nf_conntrack_expect *exp, u32 portid, int report) { struct nf_conn_help *master_help = nfct_help(exp->master); struct net *net = nf_ct_exp_net(exp); + struct nf_conntrack_net *cnet; WARN_ON(!master_help); WARN_ON(timer_pending(&exp->timeout)); hlist_del_rcu(&exp->hnode); - net->ct.expect_count--; + + cnet = net_generic(net, nf_conntrack_net_id); + cnet->expect_count--; hlist_del_rcu(&exp->lnode); master_help->expecting[exp->class]--; @@ -118,10 +123,11 @@ __nf_ct_expect_find(struct net *net, const struct nf_conntrack_zone *zone, const struct nf_conntrack_tuple *tuple) { + struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id); struct nf_conntrack_expect *i; unsigned int h; - if (!net->ct.expect_count) + if (!cnet->expect_count) return NULL; h = nf_ct_expect_dst_hash(net, tuple); @@ -158,10 +164,11 @@ nf_ct_find_expectation(struct net *net, const struct nf_conntrack_zone *zone, const struct nf_conntrack_tuple *tuple) { + struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id); struct nf_conntrack_expect *i, *exp = NULL; unsigned int h; - if (!net->ct.expect_count) + if (!cnet->expect_count) return NULL; h = nf_ct_expect_dst_hash(net, tuple); @@ -368,6 +375,7 @@ EXPORT_SYMBOL_GPL(nf_ct_expect_put); static void nf_ct_expect_insert(struct nf_conntrack_expect *exp) { + struct nf_conntrack_net *cnet; struct nf_conn_help *master_help = nfct_help(exp->master); struct nf_conntrack_helper *helper; struct net *net = nf_ct_exp_net(exp); @@ -389,7 +397,8 @@ static void nf_ct_expect_insert(struct nf_conntrack_expect *exp) master_help->expecting[exp->class]++; hlist_add_head_rcu(&exp->hnode, &nf_ct_expect_hash[h]); - net->ct.expect_count++; + cnet = net_generic(net, nf_conntrack_net_id); + cnet->expect_count++; NF_CT_STAT_INC(net, expect_create); } @@ -415,6 +424,7 @@ static inline int __nf_ct_expect_check(struct nf_conntrack_expect *expect, { const struct nf_conntrack_expect_policy *p; struct nf_conntrack_expect *i; + struct nf_conntrack_net *cnet; struct nf_conn *master = expect->master; struct nf_conn_help *master_help = nfct_help(master); struct nf_conntrack_helper *helper; @@ -458,7 +468,8 @@ static inline int __nf_ct_expect_check(struct nf_conntrack_expect *expect, } } - if (net->ct.expect_count >= nf_ct_expect_max) { + cnet = net_generic(net, nf_conntrack_net_id); + if (cnet->expect_count >= nf_ct_expect_max) { net_warn_ratelimited("nf_conntrack: expectation table full\n"); ret = -EMFILE; } @@ -686,7 +697,6 @@ module_param_named(expect_hashsize, nf_ct_expect_hsize, uint, 0400); int nf_conntrack_expect_pernet_init(struct net *net) { - net->ct.expect_count = 0; return exp_proc_init(net); } diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c index b055187235f8..ac396cc8bfae 100644 --- a/net/netfilter/nf_conntrack_helper.c +++ b/net/netfilter/nf_conntrack_helper.c @@ -43,6 +43,8 @@ MODULE_PARM_DESC(nf_conntrack_helper, static DEFINE_MUTEX(nf_ct_nat_helpers_mutex); static struct list_head nf_ct_nat_helpers __read_mostly; +extern unsigned int nf_conntrack_net_id; + /* Stupid hash, but collision free for the default registrations of the * helpers currently in the kernel. */ static unsigned int helper_hash(const struct nf_conntrack_tuple *tuple) @@ -212,8 +214,10 @@ EXPORT_SYMBOL_GPL(nf_ct_helper_ext_add); static struct nf_conntrack_helper * nf_ct_lookup_helper(struct nf_conn *ct, struct net *net) { - if (!net->ct.sysctl_auto_assign_helper) { - if (net->ct.auto_assign_helper_warned) + struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id); + + if (!cnet->sysctl_auto_assign_helper) { + if (cnet->auto_assign_helper_warned) return NULL; if (!__nf_ct_helper_find(&ct->tuplehash[IP_CT_DIR_REPLY].tuple)) return NULL; @@ -221,7 +225,7 @@ nf_ct_lookup_helper(struct nf_conn *ct, struct net *net) "has been turned off for security reasons and CT-based " "firewall rule not found. Use the iptables CT target " "to attach helpers instead.\n"); - net->ct.auto_assign_helper_warned = 1; + cnet->auto_assign_helper_warned = true; return NULL; } @@ -556,8 +560,9 @@ static const struct nf_ct_ext_type helper_extend = { void nf_conntrack_helper_pernet_init(struct net *net) { - net->ct.auto_assign_helper_warned = false; - net->ct.sysctl_auto_assign_helper = nf_ct_auto_assign_helper; + struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id); + + cnet->sysctl_auto_assign_helper = nf_ct_auto_assign_helper; } int nf_conntrack_helper_init(void) diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 1d519b0e51a5..8690fc07030f 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -555,22 +555,17 @@ ctnetlink_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type, { const struct nf_conntrack_zone *zone; struct nlmsghdr *nlh; - struct nfgenmsg *nfmsg; struct nlattr *nest_parms; unsigned int event; if (portid) flags |= NLM_F_MULTI; event = nfnl_msg_type(NFNL_SUBSYS_CTNETLINK, IPCTNL_MSG_CT_NEW); - nlh = nlmsg_put(skb, portid, seq, event, sizeof(*nfmsg), flags); - if (nlh == NULL) + nlh = nfnl_msg_put(skb, portid, seq, event, flags, nf_ct_l3num(ct), + NFNETLINK_V0, 0); + if (!nlh) goto nlmsg_failure; - nfmsg = nlmsg_data(nlh); - nfmsg->nfgen_family = nf_ct_l3num(ct); - nfmsg->version = NFNETLINK_V0; - nfmsg->res_id = 0; - zone = nf_ct_zone(ct); nest_parms = nla_nest_start(skb, CTA_TUPLE_ORIG); @@ -713,7 +708,6 @@ ctnetlink_conntrack_event(unsigned int events, struct nf_ct_event *item) const struct nf_conntrack_zone *zone; struct net *net; struct nlmsghdr *nlh; - struct nfgenmsg *nfmsg; struct nlattr *nest_parms; struct nf_conn *ct = item->ct; struct sk_buff *skb; @@ -743,15 +737,11 @@ ctnetlink_conntrack_event(unsigned int events, struct nf_ct_event *item) goto errout; type = nfnl_msg_type(NFNL_SUBSYS_CTNETLINK, type); - nlh = nlmsg_put(skb, item->portid, 0, type, sizeof(*nfmsg), flags); - if (nlh == NULL) + nlh = nfnl_msg_put(skb, item->portid, 0, type, flags, nf_ct_l3num(ct), + NFNETLINK_V0, 0); + if (!nlh) goto nlmsg_failure; - nfmsg = nlmsg_data(nlh); - nfmsg->nfgen_family = nf_ct_l3num(ct); - nfmsg->version = NFNETLINK_V0; - nfmsg->res_id = 0; - zone = nf_ct_zone(ct); nest_parms = nla_nest_start(skb, CTA_TUPLE_ORIG); @@ -1534,17 +1524,15 @@ static int ctnetlink_flush_conntrack(struct net *net, return 0; } -static int ctnetlink_del_conntrack(struct net *net, struct sock *ctnl, - struct sk_buff *skb, - const struct nlmsghdr *nlh, - const struct nlattr * const cda[], - struct netlink_ext_ack *extack) +static int ctnetlink_del_conntrack(struct sk_buff *skb, + const struct nfnl_info *info, + const struct nlattr * const cda[]) { + struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); struct nf_conntrack_tuple_hash *h; struct nf_conntrack_tuple tuple; - struct nf_conn *ct; - struct nfgenmsg *nfmsg = nlmsg_data(nlh); struct nf_conntrack_zone zone; + struct nf_conn *ct; int err; err = ctnetlink_parse_zone(cda[CTA_ZONE], &zone); @@ -1560,15 +1548,15 @@ static int ctnetlink_del_conntrack(struct net *net, struct sock *ctnl, else { u_int8_t u3 = nfmsg->version ? nfmsg->nfgen_family : AF_UNSPEC; - return ctnetlink_flush_conntrack(net, cda, + return ctnetlink_flush_conntrack(info->net, cda, NETLINK_CB(skb).portid, - nlmsg_report(nlh), u3); + nlmsg_report(info->nlh), u3); } if (err < 0) return err; - h = nf_conntrack_find_get(net, &zone, &tuple); + h = nf_conntrack_find_get(info->net, &zone, &tuple); if (!h) return -ENOENT; @@ -1588,28 +1576,26 @@ static int ctnetlink_del_conntrack(struct net *net, struct sock *ctnl, } } - nf_ct_delete(ct, NETLINK_CB(skb).portid, nlmsg_report(nlh)); + nf_ct_delete(ct, NETLINK_CB(skb).portid, nlmsg_report(info->nlh)); nf_ct_put(ct); return 0; } -static int ctnetlink_get_conntrack(struct net *net, struct sock *ctnl, - struct sk_buff *skb, - const struct nlmsghdr *nlh, - const struct nlattr * const cda[], - struct netlink_ext_ack *extack) +static int ctnetlink_get_conntrack(struct sk_buff *skb, + const struct nfnl_info *info, + const struct nlattr * const cda[]) { + struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); + u_int8_t u3 = nfmsg->nfgen_family; struct nf_conntrack_tuple_hash *h; struct nf_conntrack_tuple tuple; - struct nf_conn *ct; - struct sk_buff *skb2 = NULL; - struct nfgenmsg *nfmsg = nlmsg_data(nlh); - u_int8_t u3 = nfmsg->nfgen_family; struct nf_conntrack_zone zone; + struct sk_buff *skb2; + struct nf_conn *ct; int err; - if (nlh->nlmsg_flags & NLM_F_DUMP) { + if (info->nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { .start = ctnetlink_start, .dump = ctnetlink_dump_table, @@ -1617,7 +1603,7 @@ static int ctnetlink_get_conntrack(struct net *net, struct sock *ctnl, .data = (void *)cda, }; - return netlink_dump_start(ctnl, skb, nlh, &c); + return netlink_dump_start(info->sk, skb, info->nlh, &c); } err = ctnetlink_parse_zone(cda[CTA_ZONE], &zone); @@ -1636,7 +1622,7 @@ static int ctnetlink_get_conntrack(struct net *net, struct sock *ctnl, if (err < 0) return err; - h = nf_conntrack_find_get(net, &zone, &tuple); + h = nf_conntrack_find_get(info->net, &zone, &tuple); if (!h) return -ENOENT; @@ -1649,13 +1635,16 @@ static int ctnetlink_get_conntrack(struct net *net, struct sock *ctnl, return -ENOMEM; } - err = ctnetlink_fill_info(skb2, NETLINK_CB(skb).portid, nlh->nlmsg_seq, - NFNL_MSG_TYPE(nlh->nlmsg_type), ct, true, 0); + err = ctnetlink_fill_info(skb2, NETLINK_CB(skb).portid, + info->nlh->nlmsg_seq, + NFNL_MSG_TYPE(info->nlh->nlmsg_type), ct, + true, 0); nf_ct_put(ct); if (err <= 0) goto free; - err = netlink_unicast(ctnl, skb2, NETLINK_CB(skb).portid, MSG_DONTWAIT); + err = netlink_unicast(info->sk, skb2, NETLINK_CB(skb).portid, + MSG_DONTWAIT); if (err < 0) goto out; @@ -1753,18 +1742,16 @@ ctnetlink_dump_dying(struct sk_buff *skb, struct netlink_callback *cb) return ctnetlink_dump_list(skb, cb, true); } -static int ctnetlink_get_ct_dying(struct net *net, struct sock *ctnl, - struct sk_buff *skb, - const struct nlmsghdr *nlh, - const struct nlattr * const cda[], - struct netlink_ext_ack *extack) +static int ctnetlink_get_ct_dying(struct sk_buff *skb, + const struct nfnl_info *info, + const struct nlattr * const cda[]) { - if (nlh->nlmsg_flags & NLM_F_DUMP) { + if (info->nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { .dump = ctnetlink_dump_dying, .done = ctnetlink_done_list, }; - return netlink_dump_start(ctnl, skb, nlh, &c); + return netlink_dump_start(info->sk, skb, info->nlh, &c); } return -EOPNOTSUPP; @@ -1776,18 +1763,16 @@ ctnetlink_dump_unconfirmed(struct sk_buff *skb, struct netlink_callback *cb) return ctnetlink_dump_list(skb, cb, false); } -static int ctnetlink_get_ct_unconfirmed(struct net *net, struct sock *ctnl, - struct sk_buff *skb, - const struct nlmsghdr *nlh, - const struct nlattr * const cda[], - struct netlink_ext_ack *extack) +static int ctnetlink_get_ct_unconfirmed(struct sk_buff *skb, + const struct nfnl_info *info, + const struct nlattr * const cda[]) { - if (nlh->nlmsg_flags & NLM_F_DUMP) { + if (info->nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { .dump = ctnetlink_dump_unconfirmed, .done = ctnetlink_done_list, }; - return netlink_dump_start(ctnl, skb, nlh, &c); + return netlink_dump_start(info->sk, skb, info->nlh, &c); } return -EOPNOTSUPP; @@ -2384,18 +2369,16 @@ err1: return ERR_PTR(err); } -static int ctnetlink_new_conntrack(struct net *net, struct sock *ctnl, - struct sk_buff *skb, - const struct nlmsghdr *nlh, - const struct nlattr * const cda[], - struct netlink_ext_ack *extack) +static int ctnetlink_new_conntrack(struct sk_buff *skb, + const struct nfnl_info *info, + const struct nlattr * const cda[]) { + struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); struct nf_conntrack_tuple otuple, rtuple; struct nf_conntrack_tuple_hash *h = NULL; - struct nfgenmsg *nfmsg = nlmsg_data(nlh); - struct nf_conn *ct; u_int8_t u3 = nfmsg->nfgen_family; struct nf_conntrack_zone zone; + struct nf_conn *ct; int err; err = ctnetlink_parse_zone(cda[CTA_ZONE], &zone); @@ -2417,13 +2400,13 @@ static int ctnetlink_new_conntrack(struct net *net, struct sock *ctnl, } if (cda[CTA_TUPLE_ORIG]) - h = nf_conntrack_find_get(net, &zone, &otuple); + h = nf_conntrack_find_get(info->net, &zone, &otuple); else if (cda[CTA_TUPLE_REPLY]) - h = nf_conntrack_find_get(net, &zone, &rtuple); + h = nf_conntrack_find_get(info->net, &zone, &rtuple); if (h == NULL) { err = -ENOENT; - if (nlh->nlmsg_flags & NLM_F_CREATE) { + if (info->nlh->nlmsg_flags & NLM_F_CREATE) { enum ip_conntrack_events events; if (!cda[CTA_TUPLE_ORIG] || !cda[CTA_TUPLE_REPLY]) @@ -2431,8 +2414,8 @@ static int ctnetlink_new_conntrack(struct net *net, struct sock *ctnl, if (otuple.dst.protonum != rtuple.dst.protonum) return -EINVAL; - ct = ctnetlink_create_conntrack(net, &zone, cda, &otuple, - &rtuple, u3); + ct = ctnetlink_create_conntrack(info->net, &zone, cda, + &otuple, &rtuple, u3); if (IS_ERR(ct)) return PTR_ERR(ct); @@ -2455,7 +2438,7 @@ static int ctnetlink_new_conntrack(struct net *net, struct sock *ctnl, (1 << IPCT_SYNPROXY) | events, ct, NETLINK_CB(skb).portid, - nlmsg_report(nlh)); + nlmsg_report(info->nlh)); nf_ct_put(ct); } @@ -2465,7 +2448,7 @@ static int ctnetlink_new_conntrack(struct net *net, struct sock *ctnl, err = -EEXIST; ct = nf_ct_tuplehash_to_ctrack(h); - if (!(nlh->nlmsg_flags & NLM_F_EXCL)) { + if (!(info->nlh->nlmsg_flags & NLM_F_EXCL)) { err = ctnetlink_change_conntrack(ct, cda); if (err == 0) { nf_conntrack_eventmask_report((1 << IPCT_REPLY) | @@ -2477,7 +2460,7 @@ static int ctnetlink_new_conntrack(struct net *net, struct sock *ctnl, (1 << IPCT_MARK) | (1 << IPCT_SYNPROXY), ct, NETLINK_CB(skb).portid, - nlmsg_report(nlh)); + nlmsg_report(info->nlh)); } } @@ -2490,20 +2473,15 @@ ctnetlink_ct_stat_cpu_fill_info(struct sk_buff *skb, u32 portid, u32 seq, __u16 cpu, const struct ip_conntrack_stat *st) { struct nlmsghdr *nlh; - struct nfgenmsg *nfmsg; unsigned int flags = portid ? NLM_F_MULTI : 0, event; event = nfnl_msg_type(NFNL_SUBSYS_CTNETLINK, IPCTNL_MSG_CT_GET_STATS_CPU); - nlh = nlmsg_put(skb, portid, seq, event, sizeof(*nfmsg), flags); - if (nlh == NULL) + nlh = nfnl_msg_put(skb, portid, seq, event, flags, AF_UNSPEC, + NFNETLINK_V0, htons(cpu)); + if (!nlh) goto nlmsg_failure; - nfmsg = nlmsg_data(nlh); - nfmsg->nfgen_family = AF_UNSPEC; - nfmsg->version = NFNETLINK_V0; - nfmsg->res_id = htons(cpu); - if (nla_put_be32(skb, CTA_STATS_FOUND, htonl(st->found)) || nla_put_be32(skb, CTA_STATS_INVALID, htonl(st->invalid)) || nla_put_be32(skb, CTA_STATS_INSERT, htonl(st->insert)) || @@ -2554,17 +2532,15 @@ ctnetlink_ct_stat_cpu_dump(struct sk_buff *skb, struct netlink_callback *cb) return skb->len; } -static int ctnetlink_stat_ct_cpu(struct net *net, struct sock *ctnl, - struct sk_buff *skb, - const struct nlmsghdr *nlh, - const struct nlattr * const cda[], - struct netlink_ext_ack *extack) +static int ctnetlink_stat_ct_cpu(struct sk_buff *skb, + const struct nfnl_info *info, + const struct nlattr * const cda[]) { - if (nlh->nlmsg_flags & NLM_F_DUMP) { + if (info->nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { .dump = ctnetlink_ct_stat_cpu_dump, }; - return netlink_dump_start(ctnl, skb, nlh, &c); + return netlink_dump_start(info->sk, skb, info->nlh, &c); } return 0; @@ -2574,21 +2550,17 @@ static int ctnetlink_stat_ct_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type, struct net *net) { - struct nlmsghdr *nlh; - struct nfgenmsg *nfmsg; unsigned int flags = portid ? NLM_F_MULTI : 0, event; - unsigned int nr_conntracks = atomic_read(&net->ct.count); + unsigned int nr_conntracks; + struct nlmsghdr *nlh; event = nfnl_msg_type(NFNL_SUBSYS_CTNETLINK, IPCTNL_MSG_CT_GET_STATS); - nlh = nlmsg_put(skb, portid, seq, event, sizeof(*nfmsg), flags); - if (nlh == NULL) + nlh = nfnl_msg_put(skb, portid, seq, event, flags, AF_UNSPEC, + NFNETLINK_V0, 0); + if (!nlh) goto nlmsg_failure; - nfmsg = nlmsg_data(nlh); - nfmsg->nfgen_family = AF_UNSPEC; - nfmsg->version = NFNETLINK_V0; - nfmsg->res_id = 0; - + nr_conntracks = nf_conntrack_count(net); if (nla_put_be32(skb, CTA_STATS_GLOBAL_ENTRIES, htonl(nr_conntracks))) goto nla_put_failure; @@ -2604,10 +2576,8 @@ nlmsg_failure: return -1; } -static int ctnetlink_stat_ct(struct net *net, struct sock *ctnl, - struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const cda[], - struct netlink_ext_ack *extack) +static int ctnetlink_stat_ct(struct sk_buff *skb, const struct nfnl_info *info, + const struct nlattr * const cda[]) { struct sk_buff *skb2; int err; @@ -2617,13 +2587,14 @@ static int ctnetlink_stat_ct(struct net *net, struct sock *ctnl, return -ENOMEM; err = ctnetlink_stat_ct_fill_info(skb2, NETLINK_CB(skb).portid, - nlh->nlmsg_seq, - NFNL_MSG_TYPE(nlh->nlmsg_type), + info->nlh->nlmsg_seq, + NFNL_MSG_TYPE(info->nlh->nlmsg_type), sock_net(skb->sk)); if (err <= 0) goto free; - err = netlink_unicast(ctnl, skb2, NETLINK_CB(skb).portid, MSG_DONTWAIT); + err = netlink_unicast(info->sk, skb2, NETLINK_CB(skb).portid, + MSG_DONTWAIT); if (err < 0) goto out; @@ -3085,19 +3056,14 @@ ctnetlink_exp_fill_info(struct sk_buff *skb, u32 portid, u32 seq, int event, const struct nf_conntrack_expect *exp) { struct nlmsghdr *nlh; - struct nfgenmsg *nfmsg; unsigned int flags = portid ? NLM_F_MULTI : 0; event = nfnl_msg_type(NFNL_SUBSYS_CTNETLINK_EXP, event); - nlh = nlmsg_put(skb, portid, seq, event, sizeof(*nfmsg), flags); - if (nlh == NULL) + nlh = nfnl_msg_put(skb, portid, seq, event, flags, + exp->tuple.src.l3num, NFNETLINK_V0, 0); + if (!nlh) goto nlmsg_failure; - nfmsg = nlmsg_data(nlh); - nfmsg->nfgen_family = exp->tuple.src.l3num; - nfmsg->version = NFNETLINK_V0; - nfmsg->res_id = 0; - if (ctnetlink_exp_dump_expect(skb, exp) < 0) goto nla_put_failure; @@ -3117,7 +3083,6 @@ ctnetlink_expect_event(unsigned int events, struct nf_exp_event *item) struct nf_conntrack_expect *exp = item->exp; struct net *net = nf_ct_exp_net(exp); struct nlmsghdr *nlh; - struct nfgenmsg *nfmsg; struct sk_buff *skb; unsigned int type, group; int flags = 0; @@ -3140,15 +3105,11 @@ ctnetlink_expect_event(unsigned int events, struct nf_exp_event *item) goto errout; type = nfnl_msg_type(NFNL_SUBSYS_CTNETLINK_EXP, type); - nlh = nlmsg_put(skb, item->portid, 0, type, sizeof(*nfmsg), flags); - if (nlh == NULL) + nlh = nfnl_msg_put(skb, item->portid, 0, type, flags, + exp->tuple.src.l3num, NFNETLINK_V0, 0); + if (!nlh) goto nlmsg_failure; - nfmsg = nlmsg_data(nlh); - nfmsg->nfgen_family = exp->tuple.src.l3num; - nfmsg->version = NFNETLINK_V0; - nfmsg->res_id = 0; - if (ctnetlink_exp_dump_expect(skb, exp) < 0) goto nla_put_failure; @@ -3313,29 +3274,29 @@ static int ctnetlink_dump_exp_ct(struct net *net, struct sock *ctnl, return err; } -static int ctnetlink_get_expect(struct net *net, struct sock *ctnl, - struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const cda[], - struct netlink_ext_ack *extack) +static int ctnetlink_get_expect(struct sk_buff *skb, + const struct nfnl_info *info, + const struct nlattr * const cda[]) { + struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); + u_int8_t u3 = nfmsg->nfgen_family; struct nf_conntrack_tuple tuple; struct nf_conntrack_expect *exp; - struct sk_buff *skb2; - struct nfgenmsg *nfmsg = nlmsg_data(nlh); - u_int8_t u3 = nfmsg->nfgen_family; struct nf_conntrack_zone zone; + struct sk_buff *skb2; int err; - if (nlh->nlmsg_flags & NLM_F_DUMP) { + if (info->nlh->nlmsg_flags & NLM_F_DUMP) { if (cda[CTA_EXPECT_MASTER]) - return ctnetlink_dump_exp_ct(net, ctnl, skb, nlh, cda, - extack); + return ctnetlink_dump_exp_ct(info->net, info->sk, skb, + info->nlh, cda, + info->extack); else { struct netlink_dump_control c = { .dump = ctnetlink_exp_dump_table, .done = ctnetlink_exp_done, }; - return netlink_dump_start(ctnl, skb, nlh, &c); + return netlink_dump_start(info->sk, skb, info->nlh, &c); } } @@ -3355,7 +3316,7 @@ static int ctnetlink_get_expect(struct net *net, struct sock *ctnl, if (err < 0) return err; - exp = nf_ct_expect_find_get(net, &zone, &tuple); + exp = nf_ct_expect_find_get(info->net, &zone, &tuple); if (!exp) return -ENOENT; @@ -3377,13 +3338,15 @@ static int ctnetlink_get_expect(struct net *net, struct sock *ctnl, rcu_read_lock(); err = ctnetlink_exp_fill_info(skb2, NETLINK_CB(skb).portid, - nlh->nlmsg_seq, IPCTNL_MSG_EXP_NEW, exp); + info->nlh->nlmsg_seq, IPCTNL_MSG_EXP_NEW, + exp); rcu_read_unlock(); nf_ct_expect_put(exp); if (err <= 0) goto free; - err = netlink_unicast(ctnl, skb2, NETLINK_CB(skb).portid, MSG_DONTWAIT); + err = netlink_unicast(info->sk, skb2, NETLINK_CB(skb).portid, + MSG_DONTWAIT); if (err < 0) goto out; @@ -3411,15 +3374,14 @@ static bool expect_iter_all(struct nf_conntrack_expect *exp, void *data) return true; } -static int ctnetlink_del_expect(struct net *net, struct sock *ctnl, - struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const cda[], - struct netlink_ext_ack *extack) +static int ctnetlink_del_expect(struct sk_buff *skb, + const struct nfnl_info *info, + const struct nlattr * const cda[]) { + struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); + u_int8_t u3 = nfmsg->nfgen_family; struct nf_conntrack_expect *exp; struct nf_conntrack_tuple tuple; - struct nfgenmsg *nfmsg = nlmsg_data(nlh); - u_int8_t u3 = nfmsg->nfgen_family; struct nf_conntrack_zone zone; int err; @@ -3435,7 +3397,7 @@ static int ctnetlink_del_expect(struct net *net, struct sock *ctnl, return err; /* bump usage count to 2 */ - exp = nf_ct_expect_find_get(net, &zone, &tuple); + exp = nf_ct_expect_find_get(info->net, &zone, &tuple); if (!exp) return -ENOENT; @@ -3451,7 +3413,7 @@ static int ctnetlink_del_expect(struct net *net, struct sock *ctnl, spin_lock_bh(&nf_conntrack_expect_lock); if (del_timer(&exp->timeout)) { nf_ct_unlink_expect_report(exp, NETLINK_CB(skb).portid, - nlmsg_report(nlh)); + nlmsg_report(info->nlh)); nf_ct_expect_put(exp); } spin_unlock_bh(&nf_conntrack_expect_lock); @@ -3461,14 +3423,14 @@ static int ctnetlink_del_expect(struct net *net, struct sock *ctnl, } else if (cda[CTA_EXPECT_HELP_NAME]) { char *name = nla_data(cda[CTA_EXPECT_HELP_NAME]); - nf_ct_expect_iterate_net(net, expect_iter_name, name, + nf_ct_expect_iterate_net(info->net, expect_iter_name, name, NETLINK_CB(skb).portid, - nlmsg_report(nlh)); + nlmsg_report(info->nlh)); } else { /* This basically means we have to flush everything*/ - nf_ct_expect_iterate_net(net, expect_iter_all, NULL, + nf_ct_expect_iterate_net(info->net, expect_iter_all, NULL, NETLINK_CB(skb).portid, - nlmsg_report(nlh)); + nlmsg_report(info->nlh)); } return 0; @@ -3664,15 +3626,14 @@ err_ct: return err; } -static int ctnetlink_new_expect(struct net *net, struct sock *ctnl, - struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const cda[], - struct netlink_ext_ack *extack) +static int ctnetlink_new_expect(struct sk_buff *skb, + const struct nfnl_info *info, + const struct nlattr * const cda[]) { + struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); + u_int8_t u3 = nfmsg->nfgen_family; struct nf_conntrack_tuple tuple; struct nf_conntrack_expect *exp; - struct nfgenmsg *nfmsg = nlmsg_data(nlh); - u_int8_t u3 = nfmsg->nfgen_family; struct nf_conntrack_zone zone; int err; @@ -3691,20 +3652,20 @@ static int ctnetlink_new_expect(struct net *net, struct sock *ctnl, return err; spin_lock_bh(&nf_conntrack_expect_lock); - exp = __nf_ct_expect_find(net, &zone, &tuple); + exp = __nf_ct_expect_find(info->net, &zone, &tuple); if (!exp) { spin_unlock_bh(&nf_conntrack_expect_lock); err = -ENOENT; - if (nlh->nlmsg_flags & NLM_F_CREATE) { - err = ctnetlink_create_expect(net, &zone, cda, u3, + if (info->nlh->nlmsg_flags & NLM_F_CREATE) { + err = ctnetlink_create_expect(info->net, &zone, cda, u3, NETLINK_CB(skb).portid, - nlmsg_report(nlh)); + nlmsg_report(info->nlh)); } return err; } err = -EEXIST; - if (!(nlh->nlmsg_flags & NLM_F_EXCL)) + if (!(info->nlh->nlmsg_flags & NLM_F_EXCL)) err = ctnetlink_change_expect(exp, cda); spin_unlock_bh(&nf_conntrack_expect_lock); @@ -3716,20 +3677,15 @@ ctnetlink_exp_stat_fill_info(struct sk_buff *skb, u32 portid, u32 seq, int cpu, const struct ip_conntrack_stat *st) { struct nlmsghdr *nlh; - struct nfgenmsg *nfmsg; unsigned int flags = portid ? NLM_F_MULTI : 0, event; event = nfnl_msg_type(NFNL_SUBSYS_CTNETLINK, IPCTNL_MSG_EXP_GET_STATS_CPU); - nlh = nlmsg_put(skb, portid, seq, event, sizeof(*nfmsg), flags); - if (nlh == NULL) + nlh = nfnl_msg_put(skb, portid, seq, event, flags, AF_UNSPEC, + NFNETLINK_V0, htons(cpu)); + if (!nlh) goto nlmsg_failure; - nfmsg = nlmsg_data(nlh); - nfmsg->nfgen_family = AF_UNSPEC; - nfmsg->version = NFNETLINK_V0; - nfmsg->res_id = htons(cpu); - if (nla_put_be32(skb, CTA_STATS_EXP_NEW, htonl(st->expect_new)) || nla_put_be32(skb, CTA_STATS_EXP_CREATE, htonl(st->expect_create)) || nla_put_be32(skb, CTA_STATS_EXP_DELETE, htonl(st->expect_delete))) @@ -3770,17 +3726,15 @@ ctnetlink_exp_stat_cpu_dump(struct sk_buff *skb, struct netlink_callback *cb) return skb->len; } -static int ctnetlink_stat_exp_cpu(struct net *net, struct sock *ctnl, - struct sk_buff *skb, - const struct nlmsghdr *nlh, - const struct nlattr * const cda[], - struct netlink_ext_ack *extack) +static int ctnetlink_stat_exp_cpu(struct sk_buff *skb, + const struct nfnl_info *info, + const struct nlattr * const cda[]) { - if (nlh->nlmsg_flags & NLM_F_DUMP) { + if (info->nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { .dump = ctnetlink_exp_stat_cpu_dump, }; - return netlink_dump_start(ctnl, skb, nlh, &c); + return netlink_dump_start(info->sk, skb, info->nlh, &c); } return 0; @@ -3797,35 +3751,71 @@ static struct nf_exp_event_notifier ctnl_notifier_exp = { #endif static const struct nfnl_callback ctnl_cb[IPCTNL_MSG_MAX] = { - [IPCTNL_MSG_CT_NEW] = { .call = ctnetlink_new_conntrack, - .attr_count = CTA_MAX, - .policy = ct_nla_policy }, - [IPCTNL_MSG_CT_GET] = { .call = ctnetlink_get_conntrack, - .attr_count = CTA_MAX, - .policy = ct_nla_policy }, - [IPCTNL_MSG_CT_DELETE] = { .call = ctnetlink_del_conntrack, - .attr_count = CTA_MAX, - .policy = ct_nla_policy }, - [IPCTNL_MSG_CT_GET_CTRZERO] = { .call = ctnetlink_get_conntrack, - .attr_count = CTA_MAX, - .policy = ct_nla_policy }, - [IPCTNL_MSG_CT_GET_STATS_CPU] = { .call = ctnetlink_stat_ct_cpu }, - [IPCTNL_MSG_CT_GET_STATS] = { .call = ctnetlink_stat_ct }, - [IPCTNL_MSG_CT_GET_DYING] = { .call = ctnetlink_get_ct_dying }, - [IPCTNL_MSG_CT_GET_UNCONFIRMED] = { .call = ctnetlink_get_ct_unconfirmed }, + [IPCTNL_MSG_CT_NEW] = { + .call = ctnetlink_new_conntrack, + .type = NFNL_CB_MUTEX, + .attr_count = CTA_MAX, + .policy = ct_nla_policy + }, + [IPCTNL_MSG_CT_GET] = { + .call = ctnetlink_get_conntrack, + .type = NFNL_CB_MUTEX, + .attr_count = CTA_MAX, + .policy = ct_nla_policy + }, + [IPCTNL_MSG_CT_DELETE] = { + .call = ctnetlink_del_conntrack, + .type = NFNL_CB_MUTEX, + .attr_count = CTA_MAX, + .policy = ct_nla_policy + }, + [IPCTNL_MSG_CT_GET_CTRZERO] = { + .call = ctnetlink_get_conntrack, + .type = NFNL_CB_MUTEX, + .attr_count = CTA_MAX, + .policy = ct_nla_policy + }, + [IPCTNL_MSG_CT_GET_STATS_CPU] = { + .call = ctnetlink_stat_ct_cpu, + .type = NFNL_CB_MUTEX, + }, + [IPCTNL_MSG_CT_GET_STATS] = { + .call = ctnetlink_stat_ct, + .type = NFNL_CB_MUTEX, + }, + [IPCTNL_MSG_CT_GET_DYING] = { + .call = ctnetlink_get_ct_dying, + .type = NFNL_CB_MUTEX, + }, + [IPCTNL_MSG_CT_GET_UNCONFIRMED] = { + .call = ctnetlink_get_ct_unconfirmed, + .type = NFNL_CB_MUTEX, + }, }; static const struct nfnl_callback ctnl_exp_cb[IPCTNL_MSG_EXP_MAX] = { - [IPCTNL_MSG_EXP_GET] = { .call = ctnetlink_get_expect, - .attr_count = CTA_EXPECT_MAX, - .policy = exp_nla_policy }, - [IPCTNL_MSG_EXP_NEW] = { .call = ctnetlink_new_expect, - .attr_count = CTA_EXPECT_MAX, - .policy = exp_nla_policy }, - [IPCTNL_MSG_EXP_DELETE] = { .call = ctnetlink_del_expect, - .attr_count = CTA_EXPECT_MAX, - .policy = exp_nla_policy }, - [IPCTNL_MSG_EXP_GET_STATS_CPU] = { .call = ctnetlink_stat_exp_cpu }, + [IPCTNL_MSG_EXP_GET] = { + .call = ctnetlink_get_expect, + .type = NFNL_CB_MUTEX, + .attr_count = CTA_EXPECT_MAX, + .policy = exp_nla_policy + }, + [IPCTNL_MSG_EXP_NEW] = { + .call = ctnetlink_new_expect, + .type = NFNL_CB_MUTEX, + .attr_count = CTA_EXPECT_MAX, + .policy = exp_nla_policy + }, + [IPCTNL_MSG_EXP_DELETE] = { + .call = ctnetlink_del_expect, + .type = NFNL_CB_MUTEX, + .attr_count = CTA_EXPECT_MAX, + .policy = exp_nla_policy + }, + [IPCTNL_MSG_EXP_GET_STATS_CPU] = { + .call = ctnetlink_stat_exp_cpu, + .type = NFNL_CB_MUTEX, + }, }; static const struct nfnetlink_subsystem ctnl_subsys = { diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c index 47e9319d2cf3..89e5bac384d7 100644 --- a/net/netfilter/nf_conntrack_proto.c +++ b/net/netfilter/nf_conntrack_proto.c @@ -536,15 +536,19 @@ static void nf_ct_netns_do_put(struct net *net, u8 nfproto) mutex_lock(&nf_ct_proto_mutex); switch (nfproto) { case NFPROTO_IPV4: - if (cnet->users4 && (--cnet->users4 == 0)) + if (cnet->users4 && (--cnet->users4 == 0)) { nf_unregister_net_hooks(net, ipv4_conntrack_ops, ARRAY_SIZE(ipv4_conntrack_ops)); + nf_defrag_ipv4_disable(net); + } break; #if IS_ENABLED(CONFIG_IPV6) case NFPROTO_IPV6: - if (cnet->users6 && (--cnet->users6 == 0)) + if (cnet->users6 && (--cnet->users6 == 0)) { nf_unregister_net_hooks(net, ipv6_conntrack_ops, ARRAY_SIZE(ipv6_conntrack_ops)); + nf_defrag_ipv6_disable(net); + } break; #endif case NFPROTO_BRIDGE: diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c index db7479db8512..4f33307fa3cf 100644 --- a/net/netfilter/nf_conntrack_proto_dccp.c +++ b/net/netfilter/nf_conntrack_proto_dccp.c @@ -397,6 +397,7 @@ dccp_new(struct nf_conn *ct, const struct sk_buff *skb, msg = "not picking up existing connection "; goto out_invalid; } + break; case CT_DCCP_REQUEST: break; case CT_DCCP_INVALID: diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index ec23330687a5..318b8f723349 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -31,20 +31,6 @@ #include <net/netfilter/ipv4/nf_conntrack_ipv4.h> #include <net/netfilter/ipv6/nf_conntrack_ipv6.h> -/* "Be conservative in what you do, - be liberal in what you accept from others." - If it's non-zero, we mark only out of window RST segments as INVALID. */ -static int nf_ct_tcp_be_liberal __read_mostly = 0; - -/* If it is set to zero, we disable picking up already established - connections. */ -static int nf_ct_tcp_loose __read_mostly = 1; - -/* Max number of the retransmitted packets without receiving an (acceptable) - ACK from the destination. If this number is reached, a shorter timer - will be started. */ -static int nf_ct_tcp_max_retrans __read_mostly = 3; - /* FIXME: Examine ipfilter's timeouts and conntrack transitions more closely. They're more complex. --RR */ @@ -1436,9 +1422,23 @@ void nf_conntrack_tcp_init_net(struct net *net) * ->timeouts[0] contains 'new' timeout, like udp or icmp. */ tn->timeouts[0] = tcp_timeouts[TCP_CONNTRACK_SYN_SENT]; - tn->tcp_loose = nf_ct_tcp_loose; - tn->tcp_be_liberal = nf_ct_tcp_be_liberal; - tn->tcp_max_retrans = nf_ct_tcp_max_retrans; + + /* If it is set to zero, we disable picking up already established + * connections. + */ + tn->tcp_loose = 1; + + /* "Be conservative in what you do, + * be liberal in what you accept from others." + * If it's non-zero, we mark only out of window RST segments as INVALID. + */ + tn->tcp_be_liberal = 0; + + /* Max number of the retransmitted packets without receiving an (acceptable) + * ACK from the destination. If this number is reached, a shorter timer + * will be started. + */ + tn->tcp_max_retrans = 3; } const struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp = diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index c6c0cb465664..aaa55246d0ca 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -425,14 +425,16 @@ static void ct_cpu_seq_stop(struct seq_file *seq, void *v) static int ct_cpu_seq_show(struct seq_file *seq, void *v) { struct net *net = seq_file_net(seq); - unsigned int nr_conntracks = atomic_read(&net->ct.count); const struct ip_conntrack_stat *st = v; + unsigned int nr_conntracks; if (v == SEQ_START_TOKEN) { seq_puts(seq, "entries clashres found new invalid ignore delete delete_list insert insert_failed drop early_drop icmp_error expect_new expect_create expect_delete search_restart\n"); return 0; } + nr_conntracks = nf_conntrack_count(net); + seq_printf(seq, "%08x %08x %08x %08x %08x %08x %08x %08x " "%08x %08x %08x %08x %08x %08x %08x %08x %08x\n", nr_conntracks, @@ -508,13 +510,19 @@ static void nf_conntrack_standalone_fini_proc(struct net *net) } #endif /* CONFIG_NF_CONNTRACK_PROCFS */ +u32 nf_conntrack_count(const struct net *net) +{ + const struct nf_conntrack_net *cnet; + + cnet = net_generic(net, nf_conntrack_net_id); + + return atomic_read(&cnet->count); +} +EXPORT_SYMBOL_GPL(nf_conntrack_count); + /* Sysctl support */ #ifdef CONFIG_SYSCTL -/* Log invalid packets of a given protocol */ -static int log_invalid_proto_min __read_mostly; -static int log_invalid_proto_max __read_mostly = 255; - /* size the user *wants to set */ static unsigned int nf_conntrack_htable_size_user __read_mostly; @@ -615,7 +623,6 @@ static struct ctl_table nf_ct_sysctl_table[] = { }, [NF_SYSCTL_CT_COUNT] = { .procname = "nf_conntrack_count", - .data = &init_net.ct.count, .maxlen = sizeof(int), .mode = 0444, .proc_handler = proc_dointvec, @@ -630,20 +637,18 @@ static struct ctl_table nf_ct_sysctl_table[] = { [NF_SYSCTL_CT_CHECKSUM] = { .procname = "nf_conntrack_checksum", .data = &init_net.ct.sysctl_checksum, - .maxlen = sizeof(int), + .maxlen = sizeof(u8), .mode = 0644, - .proc_handler = proc_dointvec_minmax, + .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, [NF_SYSCTL_CT_LOG_INVALID] = { .procname = "nf_conntrack_log_invalid", .data = &init_net.ct.sysctl_log_invalid, - .maxlen = sizeof(unsigned int), + .maxlen = sizeof(u8), .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = &log_invalid_proto_min, - .extra2 = &log_invalid_proto_max, + .proc_handler = proc_dou8vec_minmax, }, [NF_SYSCTL_CT_EXPECT_MAX] = { .procname = "nf_conntrack_expect_max", @@ -655,18 +660,17 @@ static struct ctl_table nf_ct_sysctl_table[] = { [NF_SYSCTL_CT_ACCT] = { .procname = "nf_conntrack_acct", .data = &init_net.ct.sysctl_acct, - .maxlen = sizeof(int), + .maxlen = sizeof(u8), .mode = 0644, - .proc_handler = proc_dointvec_minmax, + .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, [NF_SYSCTL_CT_HELPER] = { .procname = "nf_conntrack_helper", - .data = &init_net.ct.sysctl_auto_assign_helper, - .maxlen = sizeof(int), + .maxlen = sizeof(u8), .mode = 0644, - .proc_handler = proc_dointvec_minmax, + .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, @@ -674,9 +678,9 @@ static struct ctl_table nf_ct_sysctl_table[] = { [NF_SYSCTL_CT_EVENTS] = { .procname = "nf_conntrack_events", .data = &init_net.ct.sysctl_events, - .maxlen = sizeof(int), + .maxlen = sizeof(u8), .mode = 0644, - .proc_handler = proc_dointvec_minmax, + .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, @@ -685,9 +689,9 @@ static struct ctl_table nf_ct_sysctl_table[] = { [NF_SYSCTL_CT_TIMESTAMP] = { .procname = "nf_conntrack_timestamp", .data = &init_net.ct.sysctl_tstamp, - .maxlen = sizeof(int), + .maxlen = sizeof(u8), .mode = 0644, - .proc_handler = proc_dointvec_minmax, + .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, @@ -760,25 +764,25 @@ static struct ctl_table nf_ct_sysctl_table[] = { }, [NF_SYSCTL_CT_PROTO_TCP_LOOSE] = { .procname = "nf_conntrack_tcp_loose", - .maxlen = sizeof(int), + .maxlen = sizeof(u8), .mode = 0644, - .proc_handler = proc_dointvec_minmax, + .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, [NF_SYSCTL_CT_PROTO_TCP_LIBERAL] = { .procname = "nf_conntrack_tcp_be_liberal", - .maxlen = sizeof(int), + .maxlen = sizeof(u8), .mode = 0644, - .proc_handler = proc_dointvec_minmax, + .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, [NF_SYSCTL_CT_PROTO_TCP_MAX_RETRANS] = { .procname = "nf_conntrack_tcp_max_retrans", - .maxlen = sizeof(unsigned int), + .maxlen = sizeof(u8), .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = proc_dou8vec_minmax, }, [NF_SYSCTL_CT_PROTO_TIMEOUT_UDP] = { .procname = "nf_conntrack_udp_timeout", @@ -905,9 +909,9 @@ static struct ctl_table nf_ct_sysctl_table[] = { }, [NF_SYSCTL_CT_PROTO_DCCP_LOOSE] = { .procname = "nf_conntrack_dccp_loose", - .maxlen = sizeof(int), + .maxlen = sizeof(u8), .mode = 0644, - .proc_handler = proc_dointvec_minmax, + .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, @@ -1028,6 +1032,7 @@ static void nf_conntrack_standalone_init_gre_sysctl(struct net *net, static int nf_conntrack_standalone_init_sysctl(struct net *net) { + struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id); struct nf_udp_net *un = nf_udp_pernet(net); struct ctl_table *table; @@ -1038,11 +1043,11 @@ static int nf_conntrack_standalone_init_sysctl(struct net *net) if (!table) return -ENOMEM; - table[NF_SYSCTL_CT_COUNT].data = &net->ct.count; + table[NF_SYSCTL_CT_COUNT].data = &cnet->count; table[NF_SYSCTL_CT_CHECKSUM].data = &net->ct.sysctl_checksum; table[NF_SYSCTL_CT_LOG_INVALID].data = &net->ct.sysctl_log_invalid; table[NF_SYSCTL_CT_ACCT].data = &net->ct.sysctl_acct; - table[NF_SYSCTL_CT_HELPER].data = &net->ct.sysctl_auto_assign_helper; + table[NF_SYSCTL_CT_HELPER].data = &cnet->sysctl_auto_assign_helper; #ifdef CONFIG_NF_CONNTRACK_EVENTS table[NF_SYSCTL_CT_EVENTS].data = &net->ct.sysctl_events; #endif @@ -1060,21 +1065,15 @@ static int nf_conntrack_standalone_init_sysctl(struct net *net) nf_conntrack_standalone_init_dccp_sysctl(net, table); nf_conntrack_standalone_init_gre_sysctl(net, table); - /* Don't allow unprivileged users to alter certain sysctls */ - if (net->user_ns != &init_user_ns) { + /* Don't allow non-init_net ns to alter global sysctls */ + if (!net_eq(&init_net, net)) { table[NF_SYSCTL_CT_MAX].mode = 0444; table[NF_SYSCTL_CT_EXPECT_MAX].mode = 0444; - table[NF_SYSCTL_CT_HELPER].mode = 0444; -#ifdef CONFIG_NF_CONNTRACK_EVENTS - table[NF_SYSCTL_CT_EVENTS].mode = 0444; -#endif - table[NF_SYSCTL_CT_BUCKETS].mode = 0444; - } else if (!net_eq(&init_net, net)) { table[NF_SYSCTL_CT_BUCKETS].mode = 0444; } - net->ct.sysctl_header = register_net_sysctl(net, "net/netfilter", table); - if (!net->ct.sysctl_header) + cnet->sysctl_header = register_net_sysctl(net, "net/netfilter", table); + if (!cnet->sysctl_header) goto out_unregister_netfilter; return 0; @@ -1086,10 +1085,11 @@ out_unregister_netfilter: static void nf_conntrack_standalone_fini_sysctl(struct net *net) { + struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id); struct ctl_table *table; - table = net->ct.sysctl_header->ctl_table_arg; - unregister_net_sysctl_table(net->ct.sysctl_header); + table = cnet->sysctl_header->ctl_table_arg; + unregister_net_sysctl_table(cnet->sysctl_header); kfree(table); } #else diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c index c77ba8690ed8..39c02d1aeedf 100644 --- a/net/netfilter/nf_flow_table_core.c +++ b/net/netfilter/nf_flow_table_core.c @@ -74,16 +74,25 @@ err_ct_refcnt: } EXPORT_SYMBOL_GPL(flow_offload_alloc); +static u32 flow_offload_dst_cookie(struct flow_offload_tuple *flow_tuple) +{ + const struct rt6_info *rt; + + if (flow_tuple->l3proto == NFPROTO_IPV6) { + rt = (const struct rt6_info *)flow_tuple->dst_cache; + return rt6_get_cookie(rt); + } + + return 0; +} + static int flow_offload_fill_route(struct flow_offload *flow, const struct nf_flow_route *route, enum flow_offload_tuple_dir dir) { struct flow_offload_tuple *flow_tuple = &flow->tuplehash[dir].tuple; - struct dst_entry *other_dst = route->tuple[!dir].dst; struct dst_entry *dst = route->tuple[dir].dst; - - if (!dst_hold_safe(route->tuple[dir].dst)) - return -1; + int i, j = 0; switch (flow_tuple->l3proto) { case NFPROTO_IPV4: @@ -94,12 +103,50 @@ static int flow_offload_fill_route(struct flow_offload *flow, break; } - flow_tuple->iifidx = other_dst->dev->ifindex; - flow_tuple->dst_cache = dst; + flow_tuple->iifidx = route->tuple[dir].in.ifindex; + for (i = route->tuple[dir].in.num_encaps - 1; i >= 0; i--) { + flow_tuple->encap[j].id = route->tuple[dir].in.encap[i].id; + flow_tuple->encap[j].proto = route->tuple[dir].in.encap[i].proto; + if (route->tuple[dir].in.ingress_vlans & BIT(i)) + flow_tuple->in_vlan_ingress |= BIT(j); + j++; + } + flow_tuple->encap_num = route->tuple[dir].in.num_encaps; + + switch (route->tuple[dir].xmit_type) { + case FLOW_OFFLOAD_XMIT_DIRECT: + memcpy(flow_tuple->out.h_dest, route->tuple[dir].out.h_dest, + ETH_ALEN); + memcpy(flow_tuple->out.h_source, route->tuple[dir].out.h_source, + ETH_ALEN); + flow_tuple->out.ifidx = route->tuple[dir].out.ifindex; + flow_tuple->out.hw_ifidx = route->tuple[dir].out.hw_ifindex; + break; + case FLOW_OFFLOAD_XMIT_XFRM: + case FLOW_OFFLOAD_XMIT_NEIGH: + if (!dst_hold_safe(route->tuple[dir].dst)) + return -1; + + flow_tuple->dst_cache = dst; + flow_tuple->dst_cookie = flow_offload_dst_cookie(flow_tuple); + break; + default: + WARN_ON_ONCE(1); + break; + } + flow_tuple->xmit_type = route->tuple[dir].xmit_type; return 0; } +static void nft_flow_dst_release(struct flow_offload *flow, + enum flow_offload_tuple_dir dir) +{ + if (flow->tuplehash[dir].tuple.xmit_type == FLOW_OFFLOAD_XMIT_NEIGH || + flow->tuplehash[dir].tuple.xmit_type == FLOW_OFFLOAD_XMIT_XFRM) + dst_release(flow->tuplehash[dir].tuple.dst_cache); +} + int flow_offload_route_init(struct flow_offload *flow, const struct nf_flow_route *route) { @@ -118,7 +165,7 @@ int flow_offload_route_init(struct flow_offload *flow, return 0; err_route_reply: - dst_release(route->tuple[FLOW_OFFLOAD_DIR_ORIGINAL].dst); + nft_flow_dst_release(flow, FLOW_OFFLOAD_DIR_ORIGINAL); return err; } @@ -169,8 +216,8 @@ static void flow_offload_fixup_ct(struct nf_conn *ct) static void flow_offload_route_release(struct flow_offload *flow) { - dst_release(flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_cache); - dst_release(flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_cache); + nft_flow_dst_release(flow, FLOW_OFFLOAD_DIR_ORIGINAL); + nft_flow_dst_release(flow, FLOW_OFFLOAD_DIR_REPLY); } void flow_offload_free(struct flow_offload *flow) @@ -359,11 +406,33 @@ nf_flow_table_iterate(struct nf_flowtable *flow_table, return err; } +static bool flow_offload_stale_dst(struct flow_offload_tuple *tuple) +{ + struct dst_entry *dst; + + if (tuple->xmit_type == FLOW_OFFLOAD_XMIT_NEIGH || + tuple->xmit_type == FLOW_OFFLOAD_XMIT_XFRM) { + dst = tuple->dst_cache; + if (!dst_check(dst, tuple->dst_cookie)) + return true; + } + + return false; +} + +static bool nf_flow_has_stale_dst(struct flow_offload *flow) +{ + return flow_offload_stale_dst(&flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple) || + flow_offload_stale_dst(&flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple); +} + static void nf_flow_offload_gc_step(struct flow_offload *flow, void *data) { struct nf_flowtable *flow_table = data; - if (nf_flow_has_expired(flow) || nf_ct_is_dying(flow->ct)) + if (nf_flow_has_expired(flow) || + nf_ct_is_dying(flow->ct) || + nf_flow_has_stale_dst(flow)) set_bit(NF_FLOW_TEARDOWN, &flow->flags); if (test_bit(NF_FLOW_TEARDOWN, &flow->flags)) { @@ -389,29 +458,20 @@ static void nf_flow_offload_work_gc(struct work_struct *work) queue_delayed_work(system_power_efficient_wq, &flow_table->gc_work, HZ); } - -static int nf_flow_nat_port_tcp(struct sk_buff *skb, unsigned int thoff, - __be16 port, __be16 new_port) +static void nf_flow_nat_port_tcp(struct sk_buff *skb, unsigned int thoff, + __be16 port, __be16 new_port) { struct tcphdr *tcph; - if (skb_try_make_writable(skb, thoff + sizeof(*tcph))) - return -1; - tcph = (void *)(skb_network_header(skb) + thoff); inet_proto_csum_replace2(&tcph->check, skb, port, new_port, false); - - return 0; } -static int nf_flow_nat_port_udp(struct sk_buff *skb, unsigned int thoff, - __be16 port, __be16 new_port) +static void nf_flow_nat_port_udp(struct sk_buff *skb, unsigned int thoff, + __be16 port, __be16 new_port) { struct udphdr *udph; - if (skb_try_make_writable(skb, thoff + sizeof(*udph))) - return -1; - udph = (void *)(skb_network_header(skb) + thoff); if (udph->check || skb->ip_summed == CHECKSUM_PARTIAL) { inet_proto_csum_replace2(&udph->check, skb, port, @@ -419,37 +479,28 @@ static int nf_flow_nat_port_udp(struct sk_buff *skb, unsigned int thoff, if (!udph->check) udph->check = CSUM_MANGLED_0; } - - return 0; } -static int nf_flow_nat_port(struct sk_buff *skb, unsigned int thoff, - u8 protocol, __be16 port, __be16 new_port) +static void nf_flow_nat_port(struct sk_buff *skb, unsigned int thoff, + u8 protocol, __be16 port, __be16 new_port) { switch (protocol) { case IPPROTO_TCP: - if (nf_flow_nat_port_tcp(skb, thoff, port, new_port) < 0) - return NF_DROP; + nf_flow_nat_port_tcp(skb, thoff, port, new_port); break; case IPPROTO_UDP: - if (nf_flow_nat_port_udp(skb, thoff, port, new_port) < 0) - return NF_DROP; + nf_flow_nat_port_udp(skb, thoff, port, new_port); break; } - - return 0; } -int nf_flow_snat_port(const struct flow_offload *flow, - struct sk_buff *skb, unsigned int thoff, - u8 protocol, enum flow_offload_tuple_dir dir) +void nf_flow_snat_port(const struct flow_offload *flow, + struct sk_buff *skb, unsigned int thoff, + u8 protocol, enum flow_offload_tuple_dir dir) { struct flow_ports *hdr; __be16 port, new_port; - if (skb_try_make_writable(skb, thoff + sizeof(*hdr))) - return -1; - hdr = (void *)(skb_network_header(skb) + thoff); switch (dir) { @@ -463,24 +514,19 @@ int nf_flow_snat_port(const struct flow_offload *flow, new_port = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_port; hdr->dest = new_port; break; - default: - return -1; } - return nf_flow_nat_port(skb, thoff, protocol, port, new_port); + nf_flow_nat_port(skb, thoff, protocol, port, new_port); } EXPORT_SYMBOL_GPL(nf_flow_snat_port); -int nf_flow_dnat_port(const struct flow_offload *flow, - struct sk_buff *skb, unsigned int thoff, - u8 protocol, enum flow_offload_tuple_dir dir) +void nf_flow_dnat_port(const struct flow_offload *flow, struct sk_buff *skb, + unsigned int thoff, u8 protocol, + enum flow_offload_tuple_dir dir) { struct flow_ports *hdr; __be16 port, new_port; - if (skb_try_make_writable(skb, thoff + sizeof(*hdr))) - return -1; - hdr = (void *)(skb_network_header(skb) + thoff); switch (dir) { @@ -494,11 +540,9 @@ int nf_flow_dnat_port(const struct flow_offload *flow, new_port = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_port; hdr->source = new_port; break; - default: - return -1; } - return nf_flow_nat_port(skb, thoff, protocol, port, new_port); + nf_flow_nat_port(skb, thoff, protocol, port, new_port); } EXPORT_SYMBOL_GPL(nf_flow_dnat_port); diff --git a/net/netfilter/nf_flow_table_ip.c b/net/netfilter/nf_flow_table_ip.c index a698dbe28ef5..889cf88d3dba 100644 --- a/net/netfilter/nf_flow_table_ip.c +++ b/net/netfilter/nf_flow_table_ip.c @@ -7,6 +7,9 @@ #include <linux/ip.h> #include <linux/ipv6.h> #include <linux/netdevice.h> +#include <linux/if_ether.h> +#include <linux/if_pppox.h> +#include <linux/ppp_defs.h> #include <net/ip.h> #include <net/ipv6.h> #include <net/ip6_route.h> @@ -34,28 +37,20 @@ static int nf_flow_state_check(struct flow_offload *flow, int proto, return 0; } -static int nf_flow_nat_ip_tcp(struct sk_buff *skb, unsigned int thoff, - __be32 addr, __be32 new_addr) +static void nf_flow_nat_ip_tcp(struct sk_buff *skb, unsigned int thoff, + __be32 addr, __be32 new_addr) { struct tcphdr *tcph; - if (skb_try_make_writable(skb, thoff + sizeof(*tcph))) - return -1; - tcph = (void *)(skb_network_header(skb) + thoff); inet_proto_csum_replace4(&tcph->check, skb, addr, new_addr, true); - - return 0; } -static int nf_flow_nat_ip_udp(struct sk_buff *skb, unsigned int thoff, - __be32 addr, __be32 new_addr) +static void nf_flow_nat_ip_udp(struct sk_buff *skb, unsigned int thoff, + __be32 addr, __be32 new_addr) { struct udphdr *udph; - if (skb_try_make_writable(skb, thoff + sizeof(*udph))) - return -1; - udph = (void *)(skb_network_header(skb) + thoff); if (udph->check || skb->ip_summed == CHECKSUM_PARTIAL) { inet_proto_csum_replace4(&udph->check, skb, addr, @@ -63,31 +58,25 @@ static int nf_flow_nat_ip_udp(struct sk_buff *skb, unsigned int thoff, if (!udph->check) udph->check = CSUM_MANGLED_0; } - - return 0; } -static int nf_flow_nat_ip_l4proto(struct sk_buff *skb, struct iphdr *iph, - unsigned int thoff, __be32 addr, - __be32 new_addr) +static void nf_flow_nat_ip_l4proto(struct sk_buff *skb, struct iphdr *iph, + unsigned int thoff, __be32 addr, + __be32 new_addr) { switch (iph->protocol) { case IPPROTO_TCP: - if (nf_flow_nat_ip_tcp(skb, thoff, addr, new_addr) < 0) - return NF_DROP; + nf_flow_nat_ip_tcp(skb, thoff, addr, new_addr); break; case IPPROTO_UDP: - if (nf_flow_nat_ip_udp(skb, thoff, addr, new_addr) < 0) - return NF_DROP; + nf_flow_nat_ip_udp(skb, thoff, addr, new_addr); break; } - - return 0; } -static int nf_flow_snat_ip(const struct flow_offload *flow, struct sk_buff *skb, - struct iphdr *iph, unsigned int thoff, - enum flow_offload_tuple_dir dir) +static void nf_flow_snat_ip(const struct flow_offload *flow, + struct sk_buff *skb, struct iphdr *iph, + unsigned int thoff, enum flow_offload_tuple_dir dir) { __be32 addr, new_addr; @@ -102,17 +91,15 @@ static int nf_flow_snat_ip(const struct flow_offload *flow, struct sk_buff *skb, new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_v4.s_addr; iph->daddr = new_addr; break; - default: - return -1; } csum_replace4(&iph->check, addr, new_addr); - return nf_flow_nat_ip_l4proto(skb, iph, thoff, addr, new_addr); + nf_flow_nat_ip_l4proto(skb, iph, thoff, addr, new_addr); } -static int nf_flow_dnat_ip(const struct flow_offload *flow, struct sk_buff *skb, - struct iphdr *iph, unsigned int thoff, - enum flow_offload_tuple_dir dir) +static void nf_flow_dnat_ip(const struct flow_offload *flow, + struct sk_buff *skb, struct iphdr *iph, + unsigned int thoff, enum flow_offload_tuple_dir dir) { __be32 addr, new_addr; @@ -127,31 +114,24 @@ static int nf_flow_dnat_ip(const struct flow_offload *flow, struct sk_buff *skb, new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_v4.s_addr; iph->saddr = new_addr; break; - default: - return -1; } csum_replace4(&iph->check, addr, new_addr); - return nf_flow_nat_ip_l4proto(skb, iph, thoff, addr, new_addr); + nf_flow_nat_ip_l4proto(skb, iph, thoff, addr, new_addr); } -static int nf_flow_nat_ip(const struct flow_offload *flow, struct sk_buff *skb, - unsigned int thoff, enum flow_offload_tuple_dir dir) +static void nf_flow_nat_ip(const struct flow_offload *flow, struct sk_buff *skb, + unsigned int thoff, enum flow_offload_tuple_dir dir, + struct iphdr *iph) { - struct iphdr *iph = ip_hdr(skb); - - if (test_bit(NF_FLOW_SNAT, &flow->flags) && - (nf_flow_snat_port(flow, skb, thoff, iph->protocol, dir) < 0 || - nf_flow_snat_ip(flow, skb, ip_hdr(skb), thoff, dir) < 0)) - return -1; - - iph = ip_hdr(skb); - if (test_bit(NF_FLOW_DNAT, &flow->flags) && - (nf_flow_dnat_port(flow, skb, thoff, iph->protocol, dir) < 0 || - nf_flow_dnat_ip(flow, skb, ip_hdr(skb), thoff, dir) < 0)) - return -1; - - return 0; + if (test_bit(NF_FLOW_SNAT, &flow->flags)) { + nf_flow_snat_port(flow, skb, thoff, iph->protocol, dir); + nf_flow_snat_ip(flow, skb, iph, thoff, dir); + } + if (test_bit(NF_FLOW_DNAT, &flow->flags)) { + nf_flow_dnat_port(flow, skb, thoff, iph->protocol, dir); + nf_flow_dnat_ip(flow, skb, iph, thoff, dir); + } } static bool ip_has_options(unsigned int thoff) @@ -159,29 +139,58 @@ static bool ip_has_options(unsigned int thoff) return thoff != sizeof(struct iphdr); } +static void nf_flow_tuple_encap(struct sk_buff *skb, + struct flow_offload_tuple *tuple) +{ + struct vlan_ethhdr *veth; + struct pppoe_hdr *phdr; + int i = 0; + + if (skb_vlan_tag_present(skb)) { + tuple->encap[i].id = skb_vlan_tag_get(skb); + tuple->encap[i].proto = skb->vlan_proto; + i++; + } + switch (skb->protocol) { + case htons(ETH_P_8021Q): + veth = (struct vlan_ethhdr *)skb_mac_header(skb); + tuple->encap[i].id = ntohs(veth->h_vlan_TCI); + tuple->encap[i].proto = skb->protocol; + break; + case htons(ETH_P_PPP_SES): + phdr = (struct pppoe_hdr *)skb_mac_header(skb); + tuple->encap[i].id = ntohs(phdr->sid); + tuple->encap[i].proto = skb->protocol; + break; + } +} + static int nf_flow_tuple_ip(struct sk_buff *skb, const struct net_device *dev, - struct flow_offload_tuple *tuple) + struct flow_offload_tuple *tuple, u32 *hdrsize, + u32 offset) { - unsigned int thoff, hdrsize; struct flow_ports *ports; + unsigned int thoff; struct iphdr *iph; - if (!pskb_may_pull(skb, sizeof(*iph))) + if (!pskb_may_pull(skb, sizeof(*iph) + offset)) return -1; - iph = ip_hdr(skb); - thoff = iph->ihl * 4; + iph = (struct iphdr *)(skb_network_header(skb) + offset); + thoff = (iph->ihl * 4); if (ip_is_fragment(iph) || unlikely(ip_has_options(thoff))) return -1; + thoff += offset; + switch (iph->protocol) { case IPPROTO_TCP: - hdrsize = sizeof(struct tcphdr); + *hdrsize = sizeof(struct tcphdr); break; case IPPROTO_UDP: - hdrsize = sizeof(struct udphdr); + *hdrsize = sizeof(struct udphdr); break; default: return -1; @@ -190,11 +199,10 @@ static int nf_flow_tuple_ip(struct sk_buff *skb, const struct net_device *dev, if (iph->ttl <= 1) return -1; - thoff = iph->ihl * 4; - if (!pskb_may_pull(skb, thoff + hdrsize)) + if (!pskb_may_pull(skb, thoff + *hdrsize)) return -1; - iph = ip_hdr(skb); + iph = (struct iphdr *)(skb_network_header(skb) + offset); ports = (struct flow_ports *)(skb_network_header(skb) + thoff); tuple->src_v4.s_addr = iph->saddr; @@ -204,6 +212,7 @@ static int nf_flow_tuple_ip(struct sk_buff *skb, const struct net_device *dev, tuple->l3proto = AF_INET; tuple->l4proto = iph->protocol; tuple->iifidx = dev->ifindex; + nf_flow_tuple_encap(skb, tuple); return 0; } @@ -220,14 +229,6 @@ static bool nf_flow_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu) return true; } -static int nf_flow_offload_dst_check(struct dst_entry *dst) -{ - if (unlikely(dst_xfrm(dst))) - return dst_check(dst, 0) ? 0 : -1; - - return 0; -} - static unsigned int nf_flow_xmit_xfrm(struct sk_buff *skb, const struct nf_hook_state *state, struct dst_entry *dst) @@ -238,6 +239,91 @@ static unsigned int nf_flow_xmit_xfrm(struct sk_buff *skb, return NF_STOLEN; } +static inline __be16 nf_flow_pppoe_proto(const struct sk_buff *skb) +{ + __be16 proto; + + proto = *((__be16 *)(skb_mac_header(skb) + ETH_HLEN + + sizeof(struct pppoe_hdr))); + switch (proto) { + case htons(PPP_IP): + return htons(ETH_P_IP); + case htons(PPP_IPV6): + return htons(ETH_P_IPV6); + } + + return 0; +} + +static bool nf_flow_skb_encap_protocol(const struct sk_buff *skb, __be16 proto, + u32 *offset) +{ + struct vlan_ethhdr *veth; + + switch (skb->protocol) { + case htons(ETH_P_8021Q): + veth = (struct vlan_ethhdr *)skb_mac_header(skb); + if (veth->h_vlan_encapsulated_proto == proto) { + *offset += VLAN_HLEN; + return true; + } + break; + case htons(ETH_P_PPP_SES): + if (nf_flow_pppoe_proto(skb) == proto) { + *offset += PPPOE_SES_HLEN; + return true; + } + break; + } + + return false; +} + +static void nf_flow_encap_pop(struct sk_buff *skb, + struct flow_offload_tuple_rhash *tuplehash) +{ + struct vlan_hdr *vlan_hdr; + int i; + + for (i = 0; i < tuplehash->tuple.encap_num; i++) { + if (skb_vlan_tag_present(skb)) { + __vlan_hwaccel_clear_tag(skb); + continue; + } + switch (skb->protocol) { + case htons(ETH_P_8021Q): + vlan_hdr = (struct vlan_hdr *)skb->data; + __skb_pull(skb, VLAN_HLEN); + vlan_set_encap_proto(skb, vlan_hdr); + skb_reset_network_header(skb); + break; + case htons(ETH_P_PPP_SES): + skb->protocol = nf_flow_pppoe_proto(skb); + skb_pull(skb, PPPOE_SES_HLEN); + skb_reset_network_header(skb); + break; + } + } +} + +static unsigned int nf_flow_queue_xmit(struct net *net, struct sk_buff *skb, + const struct flow_offload_tuple_rhash *tuplehash, + unsigned short type) +{ + struct net_device *outdev; + + outdev = dev_get_by_index_rcu(net, tuplehash->tuple.out.ifidx); + if (!outdev) + return NF_DROP; + + skb->dev = outdev; + dev_hard_header(skb, skb->dev, type, tuplehash->tuple.out.h_dest, + tuplehash->tuple.out.h_source, skb->len); + dev_queue_xmit(skb); + + return NF_STOLEN; +} + unsigned int nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) @@ -248,15 +334,18 @@ nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb, enum flow_offload_tuple_dir dir; struct flow_offload *flow; struct net_device *outdev; + u32 hdrsize, offset = 0; + unsigned int thoff, mtu; struct rtable *rt; - unsigned int thoff; struct iphdr *iph; __be32 nexthop; + int ret; - if (skb->protocol != htons(ETH_P_IP)) + if (skb->protocol != htons(ETH_P_IP) && + !nf_flow_skb_encap_protocol(skb, htons(ETH_P_IP), &offset)) return NF_ACCEPT; - if (nf_flow_tuple_ip(skb, state->in, &tuple) < 0) + if (nf_flow_tuple_ip(skb, state->in, &tuple, &hdrsize, offset) < 0) return NF_ACCEPT; tuplehash = flow_offload_lookup(flow_table, &tuple); @@ -265,77 +354,80 @@ nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb, dir = tuplehash->tuple.dir; flow = container_of(tuplehash, struct flow_offload, tuplehash[dir]); - rt = (struct rtable *)flow->tuplehash[dir].tuple.dst_cache; - outdev = rt->dst.dev; - if (unlikely(nf_flow_exceeds_mtu(skb, flow->tuplehash[dir].tuple.mtu))) + mtu = flow->tuplehash[dir].tuple.mtu + offset; + if (unlikely(nf_flow_exceeds_mtu(skb, mtu))) return NF_ACCEPT; - if (skb_try_make_writable(skb, sizeof(*iph))) - return NF_DROP; - - thoff = ip_hdr(skb)->ihl * 4; - if (nf_flow_state_check(flow, ip_hdr(skb)->protocol, skb, thoff)) + iph = (struct iphdr *)(skb_network_header(skb) + offset); + thoff = (iph->ihl * 4) + offset; + if (nf_flow_state_check(flow, iph->protocol, skb, thoff)) return NF_ACCEPT; - flow_offload_refresh(flow_table, flow); + if (skb_try_make_writable(skb, thoff + hdrsize)) + return NF_DROP; - if (nf_flow_offload_dst_check(&rt->dst)) { - flow_offload_teardown(flow); - return NF_ACCEPT; - } + flow_offload_refresh(flow_table, flow); - if (nf_flow_nat_ip(flow, skb, thoff, dir) < 0) - return NF_DROP; + nf_flow_encap_pop(skb, tuplehash); + thoff -= offset; iph = ip_hdr(skb); + nf_flow_nat_ip(flow, skb, thoff, dir, iph); + ip_decrease_ttl(iph); skb->tstamp = 0; if (flow_table->flags & NF_FLOWTABLE_COUNTER) nf_ct_acct_update(flow->ct, tuplehash->tuple.dir, skb->len); - if (unlikely(dst_xfrm(&rt->dst))) { + if (unlikely(tuplehash->tuple.xmit_type == FLOW_OFFLOAD_XMIT_XFRM)) { + rt = (struct rtable *)tuplehash->tuple.dst_cache; memset(skb->cb, 0, sizeof(struct inet_skb_parm)); IPCB(skb)->iif = skb->dev->ifindex; IPCB(skb)->flags = IPSKB_FORWARDED; return nf_flow_xmit_xfrm(skb, state, &rt->dst); } - skb->dev = outdev; - nexthop = rt_nexthop(rt, flow->tuplehash[!dir].tuple.src_v4.s_addr); - skb_dst_set_noref(skb, &rt->dst); - neigh_xmit(NEIGH_ARP_TABLE, outdev, &nexthop, skb); + switch (tuplehash->tuple.xmit_type) { + case FLOW_OFFLOAD_XMIT_NEIGH: + rt = (struct rtable *)tuplehash->tuple.dst_cache; + outdev = rt->dst.dev; + skb->dev = outdev; + nexthop = rt_nexthop(rt, flow->tuplehash[!dir].tuple.src_v4.s_addr); + skb_dst_set_noref(skb, &rt->dst); + neigh_xmit(NEIGH_ARP_TABLE, outdev, &nexthop, skb); + ret = NF_STOLEN; + break; + case FLOW_OFFLOAD_XMIT_DIRECT: + ret = nf_flow_queue_xmit(state->net, skb, tuplehash, ETH_P_IP); + if (ret == NF_DROP) + flow_offload_teardown(flow); + break; + } - return NF_STOLEN; + return ret; } EXPORT_SYMBOL_GPL(nf_flow_offload_ip_hook); -static int nf_flow_nat_ipv6_tcp(struct sk_buff *skb, unsigned int thoff, - struct in6_addr *addr, - struct in6_addr *new_addr) +static void nf_flow_nat_ipv6_tcp(struct sk_buff *skb, unsigned int thoff, + struct in6_addr *addr, + struct in6_addr *new_addr, + struct ipv6hdr *ip6h) { struct tcphdr *tcph; - if (skb_try_make_writable(skb, thoff + sizeof(*tcph))) - return -1; - tcph = (void *)(skb_network_header(skb) + thoff); inet_proto_csum_replace16(&tcph->check, skb, addr->s6_addr32, new_addr->s6_addr32, true); - - return 0; } -static int nf_flow_nat_ipv6_udp(struct sk_buff *skb, unsigned int thoff, - struct in6_addr *addr, - struct in6_addr *new_addr) +static void nf_flow_nat_ipv6_udp(struct sk_buff *skb, unsigned int thoff, + struct in6_addr *addr, + struct in6_addr *new_addr) { struct udphdr *udph; - if (skb_try_make_writable(skb, thoff + sizeof(*udph))) - return -1; - udph = (void *)(skb_network_header(skb) + thoff); if (udph->check || skb->ip_summed == CHECKSUM_PARTIAL) { inet_proto_csum_replace16(&udph->check, skb, addr->s6_addr32, @@ -343,32 +435,26 @@ static int nf_flow_nat_ipv6_udp(struct sk_buff *skb, unsigned int thoff, if (!udph->check) udph->check = CSUM_MANGLED_0; } - - return 0; } -static int nf_flow_nat_ipv6_l4proto(struct sk_buff *skb, struct ipv6hdr *ip6h, - unsigned int thoff, struct in6_addr *addr, - struct in6_addr *new_addr) +static void nf_flow_nat_ipv6_l4proto(struct sk_buff *skb, struct ipv6hdr *ip6h, + unsigned int thoff, struct in6_addr *addr, + struct in6_addr *new_addr) { switch (ip6h->nexthdr) { case IPPROTO_TCP: - if (nf_flow_nat_ipv6_tcp(skb, thoff, addr, new_addr) < 0) - return NF_DROP; + nf_flow_nat_ipv6_tcp(skb, thoff, addr, new_addr, ip6h); break; case IPPROTO_UDP: - if (nf_flow_nat_ipv6_udp(skb, thoff, addr, new_addr) < 0) - return NF_DROP; + nf_flow_nat_ipv6_udp(skb, thoff, addr, new_addr); break; } - - return 0; } -static int nf_flow_snat_ipv6(const struct flow_offload *flow, - struct sk_buff *skb, struct ipv6hdr *ip6h, - unsigned int thoff, - enum flow_offload_tuple_dir dir) +static void nf_flow_snat_ipv6(const struct flow_offload *flow, + struct sk_buff *skb, struct ipv6hdr *ip6h, + unsigned int thoff, + enum flow_offload_tuple_dir dir) { struct in6_addr addr, new_addr; @@ -383,17 +469,15 @@ static int nf_flow_snat_ipv6(const struct flow_offload *flow, new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_v6; ip6h->daddr = new_addr; break; - default: - return -1; } - return nf_flow_nat_ipv6_l4proto(skb, ip6h, thoff, &addr, &new_addr); + nf_flow_nat_ipv6_l4proto(skb, ip6h, thoff, &addr, &new_addr); } -static int nf_flow_dnat_ipv6(const struct flow_offload *flow, - struct sk_buff *skb, struct ipv6hdr *ip6h, - unsigned int thoff, - enum flow_offload_tuple_dir dir) +static void nf_flow_dnat_ipv6(const struct flow_offload *flow, + struct sk_buff *skb, struct ipv6hdr *ip6h, + unsigned int thoff, + enum flow_offload_tuple_dir dir) { struct in6_addr addr, new_addr; @@ -408,52 +492,48 @@ static int nf_flow_dnat_ipv6(const struct flow_offload *flow, new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_v6; ip6h->saddr = new_addr; break; - default: - return -1; } - return nf_flow_nat_ipv6_l4proto(skb, ip6h, thoff, &addr, &new_addr); + nf_flow_nat_ipv6_l4proto(skb, ip6h, thoff, &addr, &new_addr); } -static int nf_flow_nat_ipv6(const struct flow_offload *flow, - struct sk_buff *skb, - enum flow_offload_tuple_dir dir) +static void nf_flow_nat_ipv6(const struct flow_offload *flow, + struct sk_buff *skb, + enum flow_offload_tuple_dir dir, + struct ipv6hdr *ip6h) { - struct ipv6hdr *ip6h = ipv6_hdr(skb); unsigned int thoff = sizeof(*ip6h); - if (test_bit(NF_FLOW_SNAT, &flow->flags) && - (nf_flow_snat_port(flow, skb, thoff, ip6h->nexthdr, dir) < 0 || - nf_flow_snat_ipv6(flow, skb, ipv6_hdr(skb), thoff, dir) < 0)) - return -1; - - ip6h = ipv6_hdr(skb); - if (test_bit(NF_FLOW_DNAT, &flow->flags) && - (nf_flow_dnat_port(flow, skb, thoff, ip6h->nexthdr, dir) < 0 || - nf_flow_dnat_ipv6(flow, skb, ipv6_hdr(skb), thoff, dir) < 0)) - return -1; - - return 0; + if (test_bit(NF_FLOW_SNAT, &flow->flags)) { + nf_flow_snat_port(flow, skb, thoff, ip6h->nexthdr, dir); + nf_flow_snat_ipv6(flow, skb, ip6h, thoff, dir); + } + if (test_bit(NF_FLOW_DNAT, &flow->flags)) { + nf_flow_dnat_port(flow, skb, thoff, ip6h->nexthdr, dir); + nf_flow_dnat_ipv6(flow, skb, ip6h, thoff, dir); + } } static int nf_flow_tuple_ipv6(struct sk_buff *skb, const struct net_device *dev, - struct flow_offload_tuple *tuple) + struct flow_offload_tuple *tuple, u32 *hdrsize, + u32 offset) { - unsigned int thoff, hdrsize; struct flow_ports *ports; struct ipv6hdr *ip6h; + unsigned int thoff; - if (!pskb_may_pull(skb, sizeof(*ip6h))) + thoff = sizeof(*ip6h) + offset; + if (!pskb_may_pull(skb, thoff)) return -1; - ip6h = ipv6_hdr(skb); + ip6h = (struct ipv6hdr *)(skb_network_header(skb) + offset); switch (ip6h->nexthdr) { case IPPROTO_TCP: - hdrsize = sizeof(struct tcphdr); + *hdrsize = sizeof(struct tcphdr); break; case IPPROTO_UDP: - hdrsize = sizeof(struct udphdr); + *hdrsize = sizeof(struct udphdr); break; default: return -1; @@ -462,11 +542,10 @@ static int nf_flow_tuple_ipv6(struct sk_buff *skb, const struct net_device *dev, if (ip6h->hop_limit <= 1) return -1; - thoff = sizeof(*ip6h); - if (!pskb_may_pull(skb, thoff + hdrsize)) + if (!pskb_may_pull(skb, thoff + *hdrsize)) return -1; - ip6h = ipv6_hdr(skb); + ip6h = (struct ipv6hdr *)(skb_network_header(skb) + offset); ports = (struct flow_ports *)(skb_network_header(skb) + thoff); tuple->src_v6 = ip6h->saddr; @@ -476,6 +555,7 @@ static int nf_flow_tuple_ipv6(struct sk_buff *skb, const struct net_device *dev, tuple->l3proto = AF_INET6; tuple->l4proto = ip6h->nexthdr; tuple->iifidx = dev->ifindex; + nf_flow_tuple_encap(skb, tuple); return 0; } @@ -491,13 +571,17 @@ nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb, const struct in6_addr *nexthop; struct flow_offload *flow; struct net_device *outdev; + unsigned int thoff, mtu; + u32 hdrsize, offset = 0; struct ipv6hdr *ip6h; struct rt6_info *rt; + int ret; - if (skb->protocol != htons(ETH_P_IPV6)) + if (skb->protocol != htons(ETH_P_IPV6) && + !nf_flow_skb_encap_protocol(skb, htons(ETH_P_IPV6), &offset)) return NF_ACCEPT; - if (nf_flow_tuple_ipv6(skb, state->in, &tuple) < 0) + if (nf_flow_tuple_ipv6(skb, state->in, &tuple, &hdrsize, offset) < 0) return NF_ACCEPT; tuplehash = flow_offload_lookup(flow_table, &tuple); @@ -506,48 +590,57 @@ nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb, dir = tuplehash->tuple.dir; flow = container_of(tuplehash, struct flow_offload, tuplehash[dir]); - rt = (struct rt6_info *)flow->tuplehash[dir].tuple.dst_cache; - outdev = rt->dst.dev; - if (unlikely(nf_flow_exceeds_mtu(skb, flow->tuplehash[dir].tuple.mtu))) + mtu = flow->tuplehash[dir].tuple.mtu + offset; + if (unlikely(nf_flow_exceeds_mtu(skb, mtu))) return NF_ACCEPT; - if (nf_flow_state_check(flow, ipv6_hdr(skb)->nexthdr, skb, - sizeof(*ip6h))) + ip6h = (struct ipv6hdr *)(skb_network_header(skb) + offset); + thoff = sizeof(*ip6h) + offset; + if (nf_flow_state_check(flow, ip6h->nexthdr, skb, thoff)) return NF_ACCEPT; - flow_offload_refresh(flow_table, flow); - - if (nf_flow_offload_dst_check(&rt->dst)) { - flow_offload_teardown(flow); - return NF_ACCEPT; - } - - if (skb_try_make_writable(skb, sizeof(*ip6h))) + if (skb_try_make_writable(skb, thoff + hdrsize)) return NF_DROP; - if (nf_flow_nat_ipv6(flow, skb, dir) < 0) - return NF_DROP; + flow_offload_refresh(flow_table, flow); + + nf_flow_encap_pop(skb, tuplehash); ip6h = ipv6_hdr(skb); + nf_flow_nat_ipv6(flow, skb, dir, ip6h); + ip6h->hop_limit--; skb->tstamp = 0; if (flow_table->flags & NF_FLOWTABLE_COUNTER) nf_ct_acct_update(flow->ct, tuplehash->tuple.dir, skb->len); - if (unlikely(dst_xfrm(&rt->dst))) { + if (unlikely(tuplehash->tuple.xmit_type == FLOW_OFFLOAD_XMIT_XFRM)) { + rt = (struct rt6_info *)tuplehash->tuple.dst_cache; memset(skb->cb, 0, sizeof(struct inet6_skb_parm)); IP6CB(skb)->iif = skb->dev->ifindex; IP6CB(skb)->flags = IP6SKB_FORWARDED; return nf_flow_xmit_xfrm(skb, state, &rt->dst); } - skb->dev = outdev; - nexthop = rt6_nexthop(rt, &flow->tuplehash[!dir].tuple.src_v6); - skb_dst_set_noref(skb, &rt->dst); - neigh_xmit(NEIGH_ND_TABLE, outdev, nexthop, skb); + switch (tuplehash->tuple.xmit_type) { + case FLOW_OFFLOAD_XMIT_NEIGH: + rt = (struct rt6_info *)tuplehash->tuple.dst_cache; + outdev = rt->dst.dev; + skb->dev = outdev; + nexthop = rt6_nexthop(rt, &flow->tuplehash[!dir].tuple.src_v6); + skb_dst_set_noref(skb, &rt->dst); + neigh_xmit(NEIGH_ND_TABLE, outdev, nexthop, skb); + ret = NF_STOLEN; + break; + case FLOW_OFFLOAD_XMIT_DIRECT: + ret = nf_flow_queue_xmit(state->net, skb, tuplehash, ETH_P_IPV6); + if (ret == NF_DROP) + flow_offload_teardown(flow); + break; + } - return NF_STOLEN; + return ret; } EXPORT_SYMBOL_GPL(nf_flow_offload_ipv6_hook); diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c index 1c5460e7bce8..2af7bdb38407 100644 --- a/net/netfilter/nf_flow_table_offload.c +++ b/net/netfilter/nf_flow_table_offload.c @@ -13,7 +13,9 @@ #include <net/netfilter/nf_conntrack_core.h> #include <net/netfilter/nf_conntrack_tuple.h> -static struct workqueue_struct *nf_flow_offload_wq; +static struct workqueue_struct *nf_flow_offload_add_wq; +static struct workqueue_struct *nf_flow_offload_del_wq; +static struct workqueue_struct *nf_flow_offload_stats_wq; struct flow_offload_work { struct list_head list; @@ -76,6 +78,16 @@ static void nf_flow_rule_lwt_match(struct nf_flow_match *match, match->dissector.used_keys |= enc_keys; } +static void nf_flow_rule_vlan_match(struct flow_dissector_key_vlan *key, + struct flow_dissector_key_vlan *mask, + u16 vlan_id, __be16 proto) +{ + key->vlan_id = vlan_id; + mask->vlan_id = VLAN_VID_MASK; + key->vlan_tpid = proto; + mask->vlan_tpid = 0xffff; +} + static int nf_flow_rule_match(struct nf_flow_match *match, const struct flow_offload_tuple *tuple, struct dst_entry *other_dst) @@ -83,6 +95,7 @@ static int nf_flow_rule_match(struct nf_flow_match *match, struct nf_flow_key *mask = &match->mask; struct nf_flow_key *key = &match->key; struct ip_tunnel_info *tun_info; + bool vlan_encap = false; NF_FLOW_DISSECTOR(match, FLOW_DISSECTOR_KEY_META, meta); NF_FLOW_DISSECTOR(match, FLOW_DISSECTOR_KEY_CONTROL, control); @@ -100,6 +113,32 @@ static int nf_flow_rule_match(struct nf_flow_match *match, key->meta.ingress_ifindex = tuple->iifidx; mask->meta.ingress_ifindex = 0xffffffff; + if (tuple->encap_num > 0 && !(tuple->in_vlan_ingress & BIT(0)) && + tuple->encap[0].proto == htons(ETH_P_8021Q)) { + NF_FLOW_DISSECTOR(match, FLOW_DISSECTOR_KEY_VLAN, vlan); + nf_flow_rule_vlan_match(&key->vlan, &mask->vlan, + tuple->encap[0].id, + tuple->encap[0].proto); + vlan_encap = true; + } + + if (tuple->encap_num > 1 && !(tuple->in_vlan_ingress & BIT(1)) && + tuple->encap[1].proto == htons(ETH_P_8021Q)) { + if (vlan_encap) { + NF_FLOW_DISSECTOR(match, FLOW_DISSECTOR_KEY_CVLAN, + cvlan); + nf_flow_rule_vlan_match(&key->cvlan, &mask->cvlan, + tuple->encap[1].id, + tuple->encap[1].proto); + } else { + NF_FLOW_DISSECTOR(match, FLOW_DISSECTOR_KEY_VLAN, + vlan); + nf_flow_rule_vlan_match(&key->vlan, &mask->vlan, + tuple->encap[1].id, + tuple->encap[1].proto); + } + } + switch (tuple->l3proto) { case AF_INET: key->control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; @@ -175,28 +214,45 @@ static int flow_offload_eth_src(struct net *net, enum flow_offload_tuple_dir dir, struct nf_flow_rule *flow_rule) { - const struct flow_offload_tuple *tuple = &flow->tuplehash[!dir].tuple; struct flow_action_entry *entry0 = flow_action_entry_next(flow_rule); struct flow_action_entry *entry1 = flow_action_entry_next(flow_rule); - struct net_device *dev; + const struct flow_offload_tuple *other_tuple, *this_tuple; + struct net_device *dev = NULL; + const unsigned char *addr; u32 mask, val; u16 val16; - dev = dev_get_by_index(net, tuple->iifidx); - if (!dev) - return -ENOENT; + this_tuple = &flow->tuplehash[dir].tuple; + + switch (this_tuple->xmit_type) { + case FLOW_OFFLOAD_XMIT_DIRECT: + addr = this_tuple->out.h_source; + break; + case FLOW_OFFLOAD_XMIT_NEIGH: + other_tuple = &flow->tuplehash[!dir].tuple; + dev = dev_get_by_index(net, other_tuple->iifidx); + if (!dev) + return -ENOENT; + + addr = dev->dev_addr; + break; + default: + return -EOPNOTSUPP; + } mask = ~0xffff0000; - memcpy(&val16, dev->dev_addr, 2); + memcpy(&val16, addr, 2); val = val16 << 16; flow_offload_mangle(entry0, FLOW_ACT_MANGLE_HDR_TYPE_ETH, 4, &val, &mask); mask = ~0xffffffff; - memcpy(&val, dev->dev_addr + 2, 4); + memcpy(&val, addr + 2, 4); flow_offload_mangle(entry1, FLOW_ACT_MANGLE_HDR_TYPE_ETH, 8, &val, &mask); - dev_put(dev); + + if (dev) + dev_put(dev); return 0; } @@ -208,27 +264,40 @@ static int flow_offload_eth_dst(struct net *net, { struct flow_action_entry *entry0 = flow_action_entry_next(flow_rule); struct flow_action_entry *entry1 = flow_action_entry_next(flow_rule); - const void *daddr = &flow->tuplehash[!dir].tuple.src_v4; + const struct flow_offload_tuple *other_tuple, *this_tuple; const struct dst_entry *dst_cache; unsigned char ha[ETH_ALEN]; struct neighbour *n; + const void *daddr; u32 mask, val; u8 nud_state; u16 val16; - dst_cache = flow->tuplehash[dir].tuple.dst_cache; - n = dst_neigh_lookup(dst_cache, daddr); - if (!n) - return -ENOENT; - - read_lock_bh(&n->lock); - nud_state = n->nud_state; - ether_addr_copy(ha, n->ha); - read_unlock_bh(&n->lock); + this_tuple = &flow->tuplehash[dir].tuple; - if (!(nud_state & NUD_VALID)) { + switch (this_tuple->xmit_type) { + case FLOW_OFFLOAD_XMIT_DIRECT: + ether_addr_copy(ha, this_tuple->out.h_dest); + break; + case FLOW_OFFLOAD_XMIT_NEIGH: + other_tuple = &flow->tuplehash[!dir].tuple; + daddr = &other_tuple->src_v4; + dst_cache = this_tuple->dst_cache; + n = dst_neigh_lookup(dst_cache, daddr); + if (!n) + return -ENOENT; + + read_lock_bh(&n->lock); + nud_state = n->nud_state; + ether_addr_copy(ha, n->ha); + read_unlock_bh(&n->lock); neigh_release(n); - return -ENOENT; + + if (!(nud_state & NUD_VALID)) + return -ENOENT; + break; + default: + return -EOPNOTSUPP; } mask = ~0xffffffff; @@ -241,7 +310,6 @@ static int flow_offload_eth_dst(struct net *net, val = val16; flow_offload_mangle(entry1, FLOW_ACT_MANGLE_HDR_TYPE_ETH, 4, &val, &mask); - neigh_release(n); return 0; } @@ -463,27 +531,52 @@ static void flow_offload_ipv4_checksum(struct net *net, } } -static void flow_offload_redirect(const struct flow_offload *flow, +static void flow_offload_redirect(struct net *net, + const struct flow_offload *flow, enum flow_offload_tuple_dir dir, struct nf_flow_rule *flow_rule) { - struct flow_action_entry *entry = flow_action_entry_next(flow_rule); - struct rtable *rt; + const struct flow_offload_tuple *this_tuple, *other_tuple; + struct flow_action_entry *entry; + struct net_device *dev; + int ifindex; + + this_tuple = &flow->tuplehash[dir].tuple; + switch (this_tuple->xmit_type) { + case FLOW_OFFLOAD_XMIT_DIRECT: + this_tuple = &flow->tuplehash[dir].tuple; + ifindex = this_tuple->out.hw_ifidx; + break; + case FLOW_OFFLOAD_XMIT_NEIGH: + other_tuple = &flow->tuplehash[!dir].tuple; + ifindex = other_tuple->iifidx; + break; + default: + return; + } + + dev = dev_get_by_index(net, ifindex); + if (!dev) + return; - rt = (struct rtable *)flow->tuplehash[dir].tuple.dst_cache; + entry = flow_action_entry_next(flow_rule); entry->id = FLOW_ACTION_REDIRECT; - entry->dev = rt->dst.dev; - dev_hold(rt->dst.dev); + entry->dev = dev; } static void flow_offload_encap_tunnel(const struct flow_offload *flow, enum flow_offload_tuple_dir dir, struct nf_flow_rule *flow_rule) { + const struct flow_offload_tuple *this_tuple; struct flow_action_entry *entry; struct dst_entry *dst; - dst = flow->tuplehash[dir].tuple.dst_cache; + this_tuple = &flow->tuplehash[dir].tuple; + if (this_tuple->xmit_type == FLOW_OFFLOAD_XMIT_DIRECT) + return; + + dst = this_tuple->dst_cache; if (dst && dst->lwtstate) { struct ip_tunnel_info *tun_info; @@ -500,10 +593,15 @@ static void flow_offload_decap_tunnel(const struct flow_offload *flow, enum flow_offload_tuple_dir dir, struct nf_flow_rule *flow_rule) { + const struct flow_offload_tuple *other_tuple; struct flow_action_entry *entry; struct dst_entry *dst; - dst = flow->tuplehash[!dir].tuple.dst_cache; + other_tuple = &flow->tuplehash[!dir].tuple; + if (other_tuple->xmit_type == FLOW_OFFLOAD_XMIT_DIRECT) + return; + + dst = other_tuple->dst_cache; if (dst && dst->lwtstate) { struct ip_tunnel_info *tun_info; @@ -515,10 +613,15 @@ static void flow_offload_decap_tunnel(const struct flow_offload *flow, } } -int nf_flow_rule_route_ipv4(struct net *net, const struct flow_offload *flow, - enum flow_offload_tuple_dir dir, - struct nf_flow_rule *flow_rule) +static int +nf_flow_rule_route_common(struct net *net, const struct flow_offload *flow, + enum flow_offload_tuple_dir dir, + struct nf_flow_rule *flow_rule) { + const struct flow_offload_tuple *other_tuple; + const struct flow_offload_tuple *tuple; + int i; + flow_offload_decap_tunnel(flow, dir, flow_rule); flow_offload_encap_tunnel(flow, dir, flow_rule); @@ -526,6 +629,53 @@ int nf_flow_rule_route_ipv4(struct net *net, const struct flow_offload *flow, flow_offload_eth_dst(net, flow, dir, flow_rule) < 0) return -1; + tuple = &flow->tuplehash[dir].tuple; + + for (i = 0; i < tuple->encap_num; i++) { + struct flow_action_entry *entry; + + if (tuple->in_vlan_ingress & BIT(i)) + continue; + + if (tuple->encap[i].proto == htons(ETH_P_8021Q)) { + entry = flow_action_entry_next(flow_rule); + entry->id = FLOW_ACTION_VLAN_POP; + } + } + + other_tuple = &flow->tuplehash[!dir].tuple; + + for (i = 0; i < other_tuple->encap_num; i++) { + struct flow_action_entry *entry; + + if (other_tuple->in_vlan_ingress & BIT(i)) + continue; + + entry = flow_action_entry_next(flow_rule); + + switch (other_tuple->encap[i].proto) { + case htons(ETH_P_PPP_SES): + entry->id = FLOW_ACTION_PPPOE_PUSH; + entry->pppoe.sid = other_tuple->encap[i].id; + break; + case htons(ETH_P_8021Q): + entry->id = FLOW_ACTION_VLAN_PUSH; + entry->vlan.vid = other_tuple->encap[i].id; + entry->vlan.proto = other_tuple->encap[i].proto; + break; + } + } + + return 0; +} + +int nf_flow_rule_route_ipv4(struct net *net, const struct flow_offload *flow, + enum flow_offload_tuple_dir dir, + struct nf_flow_rule *flow_rule) +{ + if (nf_flow_rule_route_common(net, flow, dir, flow_rule) < 0) + return -1; + if (test_bit(NF_FLOW_SNAT, &flow->flags)) { flow_offload_ipv4_snat(net, flow, dir, flow_rule); flow_offload_port_snat(net, flow, dir, flow_rule); @@ -538,7 +688,7 @@ int nf_flow_rule_route_ipv4(struct net *net, const struct flow_offload *flow, test_bit(NF_FLOW_DNAT, &flow->flags)) flow_offload_ipv4_checksum(net, flow, flow_rule); - flow_offload_redirect(flow, dir, flow_rule); + flow_offload_redirect(net, flow, dir, flow_rule); return 0; } @@ -548,11 +698,7 @@ int nf_flow_rule_route_ipv6(struct net *net, const struct flow_offload *flow, enum flow_offload_tuple_dir dir, struct nf_flow_rule *flow_rule) { - flow_offload_decap_tunnel(flow, dir, flow_rule); - flow_offload_encap_tunnel(flow, dir, flow_rule); - - if (flow_offload_eth_src(net, flow, dir, flow_rule) < 0 || - flow_offload_eth_dst(net, flow, dir, flow_rule) < 0) + if (nf_flow_rule_route_common(net, flow, dir, flow_rule) < 0) return -1; if (test_bit(NF_FLOW_SNAT, &flow->flags)) { @@ -564,7 +710,7 @@ int nf_flow_rule_route_ipv6(struct net *net, const struct flow_offload *flow, flow_offload_port_dnat(net, flow, dir, flow_rule); } - flow_offload_redirect(flow, dir, flow_rule); + flow_offload_redirect(net, flow, dir, flow_rule); return 0; } @@ -578,10 +724,10 @@ nf_flow_offload_rule_alloc(struct net *net, enum flow_offload_tuple_dir dir) { const struct nf_flowtable *flowtable = offload->flowtable; + const struct flow_offload_tuple *tuple, *other_tuple; const struct flow_offload *flow = offload->flow; - const struct flow_offload_tuple *tuple; + struct dst_entry *other_dst = NULL; struct nf_flow_rule *flow_rule; - struct dst_entry *other_dst; int err = -ENOMEM; flow_rule = kzalloc(sizeof(*flow_rule), GFP_KERNEL); @@ -597,7 +743,10 @@ nf_flow_offload_rule_alloc(struct net *net, flow_rule->rule->match.key = &flow_rule->match.key; tuple = &flow->tuplehash[dir].tuple; - other_dst = flow->tuplehash[!dir].tuple.dst_cache; + other_tuple = &flow->tuplehash[!dir].tuple; + if (other_tuple->xmit_type == FLOW_OFFLOAD_XMIT_NEIGH) + other_dst = other_tuple->dst_cache; + err = nf_flow_rule_match(&flow_rule->match, tuple, other_dst); if (err < 0) goto err_flow_match; @@ -826,7 +975,12 @@ static void flow_offload_work_handler(struct work_struct *work) static void flow_offload_queue_work(struct flow_offload_work *offload) { - queue_work(nf_flow_offload_wq, &offload->work); + if (offload->cmd == FLOW_CLS_REPLACE) + queue_work(nf_flow_offload_add_wq, &offload->work); + else if (offload->cmd == FLOW_CLS_DESTROY) + queue_work(nf_flow_offload_del_wq, &offload->work); + else + queue_work(nf_flow_offload_stats_wq, &offload->work); } static struct flow_offload_work * @@ -898,8 +1052,11 @@ void nf_flow_offload_stats(struct nf_flowtable *flowtable, void nf_flow_table_offload_flush(struct nf_flowtable *flowtable) { - if (nf_flowtable_hw_offload(flowtable)) - flush_workqueue(nf_flow_offload_wq); + if (nf_flowtable_hw_offload(flowtable)) { + flush_workqueue(nf_flow_offload_add_wq); + flush_workqueue(nf_flow_offload_del_wq); + flush_workqueue(nf_flow_offload_stats_wq); + } } static int nf_flow_table_block_setup(struct nf_flowtable *flowtable, @@ -1011,15 +1168,33 @@ EXPORT_SYMBOL_GPL(nf_flow_table_offload_setup); int nf_flow_table_offload_init(void) { - nf_flow_offload_wq = alloc_workqueue("nf_flow_table_offload", - WQ_UNBOUND, 0); - if (!nf_flow_offload_wq) + nf_flow_offload_add_wq = alloc_workqueue("nf_ft_offload_add", + WQ_UNBOUND | WQ_SYSFS, 0); + if (!nf_flow_offload_add_wq) return -ENOMEM; + nf_flow_offload_del_wq = alloc_workqueue("nf_ft_offload_del", + WQ_UNBOUND | WQ_SYSFS, 0); + if (!nf_flow_offload_del_wq) + goto err_del_wq; + + nf_flow_offload_stats_wq = alloc_workqueue("nf_ft_offload_stats", + WQ_UNBOUND | WQ_SYSFS, 0); + if (!nf_flow_offload_stats_wq) + goto err_stats_wq; + return 0; + +err_stats_wq: + destroy_workqueue(nf_flow_offload_del_wq); +err_del_wq: + destroy_workqueue(nf_flow_offload_add_wq); + return -ENOMEM; } void nf_flow_table_offload_exit(void) { - destroy_workqueue(nf_flow_offload_wq); + destroy_workqueue(nf_flow_offload_add_wq); + destroy_workqueue(nf_flow_offload_del_wq); + destroy_workqueue(nf_flow_offload_stats_wq); } diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c index 6cb9f9474b05..edee7fa944c1 100644 --- a/net/netfilter/nf_log.c +++ b/net/netfilter/nf_log.c @@ -151,13 +151,6 @@ void nf_log_unbind_pf(struct net *net, u_int8_t pf) } EXPORT_SYMBOL(nf_log_unbind_pf); -void nf_logger_request_module(int pf, enum nf_log_type type) -{ - if (loggers[pf][type] == NULL) - request_module("nf-logger-%u-%u", pf, type); -} -EXPORT_SYMBOL_GPL(nf_logger_request_module); - int nf_logger_find_get(int pf, enum nf_log_type type) { struct nf_logger *logger; @@ -177,9 +170,6 @@ int nf_logger_find_get(int pf, enum nf_log_type type) return 0; } - if (rcu_access_pointer(loggers[pf][type]) == NULL) - request_module("nf-logger-%u-%u", pf, type); - rcu_read_lock(); logger = rcu_dereference(loggers[pf][type]); if (logger == NULL) diff --git a/net/netfilter/nf_log_common.c b/net/netfilter/nf_log_common.c deleted file mode 100644 index fd7c5f0f5c25..000000000000 --- a/net/netfilter/nf_log_common.c +++ /dev/null @@ -1,224 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* (C) 1999-2001 Paul `Rusty' Russell - * (C) 2002-2004 Netfilter Core Team <coreteam@netfilter.org> - */ - -#include <linux/module.h> -#include <linux/spinlock.h> -#include <linux/skbuff.h> -#include <linux/if_arp.h> -#include <linux/ip.h> -#include <net/icmp.h> -#include <net/udp.h> -#include <net/tcp.h> -#include <net/route.h> - -#include <linux/netfilter.h> -#include <linux/netfilter_bridge.h> -#include <linux/netfilter/xt_LOG.h> -#include <net/netfilter/nf_log.h> - -int nf_log_dump_udp_header(struct nf_log_buf *m, const struct sk_buff *skb, - u8 proto, int fragment, unsigned int offset) -{ - struct udphdr _udph; - const struct udphdr *uh; - - if (proto == IPPROTO_UDP) - /* Max length: 10 "PROTO=UDP " */ - nf_log_buf_add(m, "PROTO=UDP "); - else /* Max length: 14 "PROTO=UDPLITE " */ - nf_log_buf_add(m, "PROTO=UDPLITE "); - - if (fragment) - goto out; - - /* Max length: 25 "INCOMPLETE [65535 bytes] " */ - uh = skb_header_pointer(skb, offset, sizeof(_udph), &_udph); - if (uh == NULL) { - nf_log_buf_add(m, "INCOMPLETE [%u bytes] ", skb->len - offset); - - return 1; - } - - /* Max length: 20 "SPT=65535 DPT=65535 " */ - nf_log_buf_add(m, "SPT=%u DPT=%u LEN=%u ", - ntohs(uh->source), ntohs(uh->dest), ntohs(uh->len)); - -out: - return 0; -} -EXPORT_SYMBOL_GPL(nf_log_dump_udp_header); - -int nf_log_dump_tcp_header(struct nf_log_buf *m, const struct sk_buff *skb, - u8 proto, int fragment, unsigned int offset, - unsigned int logflags) -{ - struct tcphdr _tcph; - const struct tcphdr *th; - - /* Max length: 10 "PROTO=TCP " */ - nf_log_buf_add(m, "PROTO=TCP "); - - if (fragment) - return 0; - - /* Max length: 25 "INCOMPLETE [65535 bytes] " */ - th = skb_header_pointer(skb, offset, sizeof(_tcph), &_tcph); - if (th == NULL) { - nf_log_buf_add(m, "INCOMPLETE [%u bytes] ", skb->len - offset); - return 1; - } - - /* Max length: 20 "SPT=65535 DPT=65535 " */ - nf_log_buf_add(m, "SPT=%u DPT=%u ", - ntohs(th->source), ntohs(th->dest)); - /* Max length: 30 "SEQ=4294967295 ACK=4294967295 " */ - if (logflags & NF_LOG_TCPSEQ) { - nf_log_buf_add(m, "SEQ=%u ACK=%u ", - ntohl(th->seq), ntohl(th->ack_seq)); - } - - /* Max length: 13 "WINDOW=65535 " */ - nf_log_buf_add(m, "WINDOW=%u ", ntohs(th->window)); - /* Max length: 9 "RES=0x3C " */ - nf_log_buf_add(m, "RES=0x%02x ", (u_int8_t)(ntohl(tcp_flag_word(th) & - TCP_RESERVED_BITS) >> 22)); - /* Max length: 32 "CWR ECE URG ACK PSH RST SYN FIN " */ - if (th->cwr) - nf_log_buf_add(m, "CWR "); - if (th->ece) - nf_log_buf_add(m, "ECE "); - if (th->urg) - nf_log_buf_add(m, "URG "); - if (th->ack) - nf_log_buf_add(m, "ACK "); - if (th->psh) - nf_log_buf_add(m, "PSH "); - if (th->rst) - nf_log_buf_add(m, "RST "); - if (th->syn) - nf_log_buf_add(m, "SYN "); - if (th->fin) - nf_log_buf_add(m, "FIN "); - /* Max length: 11 "URGP=65535 " */ - nf_log_buf_add(m, "URGP=%u ", ntohs(th->urg_ptr)); - - if ((logflags & NF_LOG_TCPOPT) && th->doff*4 > sizeof(struct tcphdr)) { - u_int8_t _opt[60 - sizeof(struct tcphdr)]; - const u_int8_t *op; - unsigned int i; - unsigned int optsize = th->doff*4 - sizeof(struct tcphdr); - - op = skb_header_pointer(skb, offset + sizeof(struct tcphdr), - optsize, _opt); - if (op == NULL) { - nf_log_buf_add(m, "OPT (TRUNCATED)"); - return 1; - } - - /* Max length: 127 "OPT (" 15*4*2chars ") " */ - nf_log_buf_add(m, "OPT ("); - for (i = 0; i < optsize; i++) - nf_log_buf_add(m, "%02X", op[i]); - - nf_log_buf_add(m, ") "); - } - - return 0; -} -EXPORT_SYMBOL_GPL(nf_log_dump_tcp_header); - -void nf_log_dump_sk_uid_gid(struct net *net, struct nf_log_buf *m, - struct sock *sk) -{ - if (!sk || !sk_fullsock(sk) || !net_eq(net, sock_net(sk))) - return; - - read_lock_bh(&sk->sk_callback_lock); - if (sk->sk_socket && sk->sk_socket->file) { - const struct cred *cred = sk->sk_socket->file->f_cred; - nf_log_buf_add(m, "UID=%u GID=%u ", - from_kuid_munged(&init_user_ns, cred->fsuid), - from_kgid_munged(&init_user_ns, cred->fsgid)); - } - read_unlock_bh(&sk->sk_callback_lock); -} -EXPORT_SYMBOL_GPL(nf_log_dump_sk_uid_gid); - -void -nf_log_dump_packet_common(struct nf_log_buf *m, u_int8_t pf, - unsigned int hooknum, const struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - const struct nf_loginfo *loginfo, const char *prefix) -{ - const struct net_device *physoutdev __maybe_unused; - const struct net_device *physindev __maybe_unused; - - nf_log_buf_add(m, KERN_SOH "%c%sIN=%s OUT=%s ", - '0' + loginfo->u.log.level, prefix, - in ? in->name : "", - out ? out->name : ""); -#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) - physindev = nf_bridge_get_physindev(skb); - if (physindev && in != physindev) - nf_log_buf_add(m, "PHYSIN=%s ", physindev->name); - physoutdev = nf_bridge_get_physoutdev(skb); - if (physoutdev && out != physoutdev) - nf_log_buf_add(m, "PHYSOUT=%s ", physoutdev->name); -#endif -} -EXPORT_SYMBOL_GPL(nf_log_dump_packet_common); - -void nf_log_dump_vlan(struct nf_log_buf *m, const struct sk_buff *skb) -{ - u16 vid; - - if (!skb_vlan_tag_present(skb)) - return; - - vid = skb_vlan_tag_get(skb); - nf_log_buf_add(m, "VPROTO=%04x VID=%u ", ntohs(skb->vlan_proto), vid); -} -EXPORT_SYMBOL_GPL(nf_log_dump_vlan); - -/* bridge and netdev logging families share this code. */ -void nf_log_l2packet(struct net *net, u_int8_t pf, - __be16 protocol, - unsigned int hooknum, - const struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - const struct nf_loginfo *loginfo, - const char *prefix) -{ - switch (protocol) { - case htons(ETH_P_IP): - nf_log_packet(net, NFPROTO_IPV4, hooknum, skb, in, out, - loginfo, "%s", prefix); - break; - case htons(ETH_P_IPV6): - nf_log_packet(net, NFPROTO_IPV6, hooknum, skb, in, out, - loginfo, "%s", prefix); - break; - case htons(ETH_P_ARP): - case htons(ETH_P_RARP): - nf_log_packet(net, NFPROTO_ARP, hooknum, skb, in, out, - loginfo, "%s", prefix); - break; - } -} -EXPORT_SYMBOL_GPL(nf_log_l2packet); - -static int __init nf_log_common_init(void) -{ - return 0; -} - -static void __exit nf_log_common_exit(void) {} - -module_init(nf_log_common_init); -module_exit(nf_log_common_exit); - -MODULE_LICENSE("GPL"); diff --git a/net/netfilter/nf_log_netdev.c b/net/netfilter/nf_log_netdev.c deleted file mode 100644 index 968dafa684c9..000000000000 --- a/net/netfilter/nf_log_netdev.c +++ /dev/null @@ -1,78 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * (C) 2016 by Pablo Neira Ayuso <pablo@netfilter.org> - */ - -#include <linux/module.h> -#include <linux/spinlock.h> -#include <linux/skbuff.h> -#include <linux/ip.h> -#include <net/route.h> - -#include <linux/netfilter.h> -#include <net/netfilter/nf_log.h> - -static void nf_log_netdev_packet(struct net *net, u_int8_t pf, - unsigned int hooknum, - const struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - const struct nf_loginfo *loginfo, - const char *prefix) -{ - nf_log_l2packet(net, pf, skb->protocol, hooknum, skb, in, out, - loginfo, prefix); -} - -static struct nf_logger nf_netdev_logger __read_mostly = { - .name = "nf_log_netdev", - .type = NF_LOG_TYPE_LOG, - .logfn = nf_log_netdev_packet, - .me = THIS_MODULE, -}; - -static int __net_init nf_log_netdev_net_init(struct net *net) -{ - return nf_log_set(net, NFPROTO_NETDEV, &nf_netdev_logger); -} - -static void __net_exit nf_log_netdev_net_exit(struct net *net) -{ - nf_log_unset(net, &nf_netdev_logger); -} - -static struct pernet_operations nf_log_netdev_net_ops = { - .init = nf_log_netdev_net_init, - .exit = nf_log_netdev_net_exit, -}; - -static int __init nf_log_netdev_init(void) -{ - int ret; - - /* Request to load the real packet loggers. */ - nf_logger_request_module(NFPROTO_IPV4, NF_LOG_TYPE_LOG); - nf_logger_request_module(NFPROTO_IPV6, NF_LOG_TYPE_LOG); - nf_logger_request_module(NFPROTO_ARP, NF_LOG_TYPE_LOG); - - ret = register_pernet_subsys(&nf_log_netdev_net_ops); - if (ret < 0) - return ret; - - nf_log_register(NFPROTO_NETDEV, &nf_netdev_logger); - return 0; -} - -static void __exit nf_log_netdev_exit(void) -{ - unregister_pernet_subsys(&nf_log_netdev_net_ops); - nf_log_unregister(&nf_netdev_logger); -} - -module_init(nf_log_netdev_init); -module_exit(nf_log_netdev_exit); - -MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>"); -MODULE_DESCRIPTION("Netfilter netdev packet logging"); -MODULE_LICENSE("GPL"); -MODULE_ALIAS_NF_LOGGER(5, 0); /* NFPROTO_NETDEV */ diff --git a/net/netfilter/nf_log_syslog.c b/net/netfilter/nf_log_syslog.c new file mode 100644 index 000000000000..13234641cdb3 --- /dev/null +++ b/net/netfilter/nf_log_syslog.c @@ -0,0 +1,1090 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* (C) 1999-2001 Paul `Rusty' Russell + * (C) 2002-2004 Netfilter Core Team <coreteam@netfilter.org> + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/spinlock.h> +#include <linux/skbuff.h> +#include <linux/if_arp.h> +#include <linux/ip.h> +#include <net/ipv6.h> +#include <net/icmp.h> +#include <net/udp.h> +#include <net/tcp.h> +#include <net/route.h> + +#include <linux/netfilter.h> +#include <linux/netfilter_bridge.h> +#include <linux/netfilter_ipv6.h> +#include <linux/netfilter/xt_LOG.h> +#include <net/netfilter/nf_log.h> + +static const struct nf_loginfo default_loginfo = { + .type = NF_LOG_TYPE_LOG, + .u = { + .log = { + .level = LOGLEVEL_NOTICE, + .logflags = NF_LOG_DEFAULT_MASK, + }, + }, +}; + +struct arppayload { + unsigned char mac_src[ETH_ALEN]; + unsigned char ip_src[4]; + unsigned char mac_dst[ETH_ALEN]; + unsigned char ip_dst[4]; +}; + +static void nf_log_dump_vlan(struct nf_log_buf *m, const struct sk_buff *skb) +{ + u16 vid; + + if (!skb_vlan_tag_present(skb)) + return; + + vid = skb_vlan_tag_get(skb); + nf_log_buf_add(m, "VPROTO=%04x VID=%u ", ntohs(skb->vlan_proto), vid); +} +static void noinline_for_stack +dump_arp_packet(struct nf_log_buf *m, + const struct nf_loginfo *info, + const struct sk_buff *skb, unsigned int nhoff) +{ + const struct arppayload *ap; + struct arppayload _arpp; + const struct arphdr *ah; + unsigned int logflags; + struct arphdr _arph; + + ah = skb_header_pointer(skb, 0, sizeof(_arph), &_arph); + if (!ah) { + nf_log_buf_add(m, "TRUNCATED"); + return; + } + + if (info->type == NF_LOG_TYPE_LOG) + logflags = info->u.log.logflags; + else + logflags = NF_LOG_DEFAULT_MASK; + + if (logflags & NF_LOG_MACDECODE) { + nf_log_buf_add(m, "MACSRC=%pM MACDST=%pM ", + eth_hdr(skb)->h_source, eth_hdr(skb)->h_dest); + nf_log_dump_vlan(m, skb); + nf_log_buf_add(m, "MACPROTO=%04x ", + ntohs(eth_hdr(skb)->h_proto)); + } + + nf_log_buf_add(m, "ARP HTYPE=%d PTYPE=0x%04x OPCODE=%d", + ntohs(ah->ar_hrd), ntohs(ah->ar_pro), ntohs(ah->ar_op)); + /* If it's for Ethernet and the lengths are OK, then log the ARP + * payload. + */ + if (ah->ar_hrd != htons(ARPHRD_ETHER) || + ah->ar_hln != ETH_ALEN || + ah->ar_pln != sizeof(__be32)) + return; + + ap = skb_header_pointer(skb, sizeof(_arph), sizeof(_arpp), &_arpp); + if (!ap) { + nf_log_buf_add(m, " INCOMPLETE [%zu bytes]", + skb->len - sizeof(_arph)); + return; + } + nf_log_buf_add(m, " MACSRC=%pM IPSRC=%pI4 MACDST=%pM IPDST=%pI4", + ap->mac_src, ap->ip_src, ap->mac_dst, ap->ip_dst); +} + +static void +nf_log_dump_packet_common(struct nf_log_buf *m, u8 pf, + unsigned int hooknum, const struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + const struct nf_loginfo *loginfo, const char *prefix) +{ + const struct net_device *physoutdev __maybe_unused; + const struct net_device *physindev __maybe_unused; + + nf_log_buf_add(m, KERN_SOH "%c%sIN=%s OUT=%s ", + '0' + loginfo->u.log.level, prefix, + in ? in->name : "", + out ? out->name : ""); +#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) + physindev = nf_bridge_get_physindev(skb); + if (physindev && in != physindev) + nf_log_buf_add(m, "PHYSIN=%s ", physindev->name); + physoutdev = nf_bridge_get_physoutdev(skb); + if (physoutdev && out != physoutdev) + nf_log_buf_add(m, "PHYSOUT=%s ", physoutdev->name); +#endif +} + +static void nf_log_arp_packet(struct net *net, u_int8_t pf, + unsigned int hooknum, const struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + const struct nf_loginfo *loginfo, + const char *prefix) +{ + struct nf_log_buf *m; + + /* FIXME: Disabled from containers until syslog ns is supported */ + if (!net_eq(net, &init_net) && !sysctl_nf_log_all_netns) + return; + + m = nf_log_buf_open(); + + if (!loginfo) + loginfo = &default_loginfo; + + nf_log_dump_packet_common(m, pf, hooknum, skb, in, out, loginfo, + prefix); + dump_arp_packet(m, loginfo, skb, 0); + + nf_log_buf_close(m); +} + +static struct nf_logger nf_arp_logger __read_mostly = { + .name = "nf_log_arp", + .type = NF_LOG_TYPE_LOG, + .logfn = nf_log_arp_packet, + .me = THIS_MODULE, +}; + +static void nf_log_dump_sk_uid_gid(struct net *net, struct nf_log_buf *m, + struct sock *sk) +{ + if (!sk || !sk_fullsock(sk) || !net_eq(net, sock_net(sk))) + return; + + read_lock_bh(&sk->sk_callback_lock); + if (sk->sk_socket && sk->sk_socket->file) { + const struct cred *cred = sk->sk_socket->file->f_cred; + + nf_log_buf_add(m, "UID=%u GID=%u ", + from_kuid_munged(&init_user_ns, cred->fsuid), + from_kgid_munged(&init_user_ns, cred->fsgid)); + } + read_unlock_bh(&sk->sk_callback_lock); +} + +static noinline_for_stack int +nf_log_dump_tcp_header(struct nf_log_buf *m, + const struct sk_buff *skb, + u8 proto, int fragment, + unsigned int offset, + unsigned int logflags) +{ + struct tcphdr _tcph; + const struct tcphdr *th; + + /* Max length: 10 "PROTO=TCP " */ + nf_log_buf_add(m, "PROTO=TCP "); + + if (fragment) + return 0; + + /* Max length: 25 "INCOMPLETE [65535 bytes] " */ + th = skb_header_pointer(skb, offset, sizeof(_tcph), &_tcph); + if (!th) { + nf_log_buf_add(m, "INCOMPLETE [%u bytes] ", skb->len - offset); + return 1; + } + + /* Max length: 20 "SPT=65535 DPT=65535 " */ + nf_log_buf_add(m, "SPT=%u DPT=%u ", + ntohs(th->source), ntohs(th->dest)); + /* Max length: 30 "SEQ=4294967295 ACK=4294967295 " */ + if (logflags & NF_LOG_TCPSEQ) { + nf_log_buf_add(m, "SEQ=%u ACK=%u ", + ntohl(th->seq), ntohl(th->ack_seq)); + } + + /* Max length: 13 "WINDOW=65535 " */ + nf_log_buf_add(m, "WINDOW=%u ", ntohs(th->window)); + /* Max length: 9 "RES=0x3C " */ + nf_log_buf_add(m, "RES=0x%02x ", (u_int8_t)(ntohl(tcp_flag_word(th) & + TCP_RESERVED_BITS) >> 22)); + /* Max length: 32 "CWR ECE URG ACK PSH RST SYN FIN " */ + if (th->cwr) + nf_log_buf_add(m, "CWR "); + if (th->ece) + nf_log_buf_add(m, "ECE "); + if (th->urg) + nf_log_buf_add(m, "URG "); + if (th->ack) + nf_log_buf_add(m, "ACK "); + if (th->psh) + nf_log_buf_add(m, "PSH "); + if (th->rst) + nf_log_buf_add(m, "RST "); + if (th->syn) + nf_log_buf_add(m, "SYN "); + if (th->fin) + nf_log_buf_add(m, "FIN "); + /* Max length: 11 "URGP=65535 " */ + nf_log_buf_add(m, "URGP=%u ", ntohs(th->urg_ptr)); + + if ((logflags & NF_LOG_TCPOPT) && th->doff * 4 > sizeof(struct tcphdr)) { + unsigned int optsize = th->doff * 4 - sizeof(struct tcphdr); + u8 _opt[60 - sizeof(struct tcphdr)]; + unsigned int i; + const u8 *op; + + op = skb_header_pointer(skb, offset + sizeof(struct tcphdr), + optsize, _opt); + if (!op) { + nf_log_buf_add(m, "OPT (TRUNCATED)"); + return 1; + } + + /* Max length: 127 "OPT (" 15*4*2chars ") " */ + nf_log_buf_add(m, "OPT ("); + for (i = 0; i < optsize; i++) + nf_log_buf_add(m, "%02X", op[i]); + + nf_log_buf_add(m, ") "); + } + + return 0; +} + +static noinline_for_stack int +nf_log_dump_udp_header(struct nf_log_buf *m, + const struct sk_buff *skb, + u8 proto, int fragment, + unsigned int offset) +{ + struct udphdr _udph; + const struct udphdr *uh; + + if (proto == IPPROTO_UDP) + /* Max length: 10 "PROTO=UDP " */ + nf_log_buf_add(m, "PROTO=UDP "); + else /* Max length: 14 "PROTO=UDPLITE " */ + nf_log_buf_add(m, "PROTO=UDPLITE "); + + if (fragment) + goto out; + + /* Max length: 25 "INCOMPLETE [65535 bytes] " */ + uh = skb_header_pointer(skb, offset, sizeof(_udph), &_udph); + if (!uh) { + nf_log_buf_add(m, "INCOMPLETE [%u bytes] ", skb->len - offset); + + return 1; + } + + /* Max length: 20 "SPT=65535 DPT=65535 " */ + nf_log_buf_add(m, "SPT=%u DPT=%u LEN=%u ", + ntohs(uh->source), ntohs(uh->dest), ntohs(uh->len)); + +out: + return 0; +} + +/* One level of recursion won't kill us */ +static noinline_for_stack void +dump_ipv4_packet(struct net *net, struct nf_log_buf *m, + const struct nf_loginfo *info, + const struct sk_buff *skb, unsigned int iphoff) +{ + const struct iphdr *ih; + unsigned int logflags; + struct iphdr _iph; + + if (info->type == NF_LOG_TYPE_LOG) + logflags = info->u.log.logflags; + else + logflags = NF_LOG_DEFAULT_MASK; + + ih = skb_header_pointer(skb, iphoff, sizeof(_iph), &_iph); + if (!ih) { + nf_log_buf_add(m, "TRUNCATED"); + return; + } + + /* Important fields: + * TOS, len, DF/MF, fragment offset, TTL, src, dst, options. + * Max length: 40 "SRC=255.255.255.255 DST=255.255.255.255 " + */ + nf_log_buf_add(m, "SRC=%pI4 DST=%pI4 ", &ih->saddr, &ih->daddr); + + /* Max length: 46 "LEN=65535 TOS=0xFF PREC=0xFF TTL=255 ID=65535 " */ + nf_log_buf_add(m, "LEN=%u TOS=0x%02X PREC=0x%02X TTL=%u ID=%u ", + ntohs(ih->tot_len), ih->tos & IPTOS_TOS_MASK, + ih->tos & IPTOS_PREC_MASK, ih->ttl, ntohs(ih->id)); + + /* Max length: 6 "CE DF MF " */ + if (ntohs(ih->frag_off) & IP_CE) + nf_log_buf_add(m, "CE "); + if (ntohs(ih->frag_off) & IP_DF) + nf_log_buf_add(m, "DF "); + if (ntohs(ih->frag_off) & IP_MF) + nf_log_buf_add(m, "MF "); + + /* Max length: 11 "FRAG:65535 " */ + if (ntohs(ih->frag_off) & IP_OFFSET) + nf_log_buf_add(m, "FRAG:%u ", ntohs(ih->frag_off) & IP_OFFSET); + + if ((logflags & NF_LOG_IPOPT) && + ih->ihl * 4 > sizeof(struct iphdr)) { + unsigned char _opt[4 * 15 - sizeof(struct iphdr)]; + const unsigned char *op; + unsigned int i, optsize; + + optsize = ih->ihl * 4 - sizeof(struct iphdr); + op = skb_header_pointer(skb, iphoff + sizeof(_iph), + optsize, _opt); + if (!op) { + nf_log_buf_add(m, "TRUNCATED"); + return; + } + + /* Max length: 127 "OPT (" 15*4*2chars ") " */ + nf_log_buf_add(m, "OPT ("); + for (i = 0; i < optsize; i++) + nf_log_buf_add(m, "%02X", op[i]); + nf_log_buf_add(m, ") "); + } + + switch (ih->protocol) { + case IPPROTO_TCP: + if (nf_log_dump_tcp_header(m, skb, ih->protocol, + ntohs(ih->frag_off) & IP_OFFSET, + iphoff + ih->ihl * 4, logflags)) + return; + break; + case IPPROTO_UDP: + case IPPROTO_UDPLITE: + if (nf_log_dump_udp_header(m, skb, ih->protocol, + ntohs(ih->frag_off) & IP_OFFSET, + iphoff + ih->ihl * 4)) + return; + break; + case IPPROTO_ICMP: { + static const size_t required_len[NR_ICMP_TYPES + 1] = { + [ICMP_ECHOREPLY] = 4, + [ICMP_DEST_UNREACH] = 8 + sizeof(struct iphdr), + [ICMP_SOURCE_QUENCH] = 8 + sizeof(struct iphdr), + [ICMP_REDIRECT] = 8 + sizeof(struct iphdr), + [ICMP_ECHO] = 4, + [ICMP_TIME_EXCEEDED] = 8 + sizeof(struct iphdr), + [ICMP_PARAMETERPROB] = 8 + sizeof(struct iphdr), + [ICMP_TIMESTAMP] = 20, + [ICMP_TIMESTAMPREPLY] = 20, + [ICMP_ADDRESS] = 12, + [ICMP_ADDRESSREPLY] = 12 }; + const struct icmphdr *ich; + struct icmphdr _icmph; + + /* Max length: 11 "PROTO=ICMP " */ + nf_log_buf_add(m, "PROTO=ICMP "); + + if (ntohs(ih->frag_off) & IP_OFFSET) + break; + + /* Max length: 25 "INCOMPLETE [65535 bytes] " */ + ich = skb_header_pointer(skb, iphoff + ih->ihl * 4, + sizeof(_icmph), &_icmph); + if (!ich) { + nf_log_buf_add(m, "INCOMPLETE [%u bytes] ", + skb->len - iphoff - ih->ihl * 4); + break; + } + + /* Max length: 18 "TYPE=255 CODE=255 " */ + nf_log_buf_add(m, "TYPE=%u CODE=%u ", ich->type, ich->code); + + /* Max length: 25 "INCOMPLETE [65535 bytes] " */ + if (ich->type <= NR_ICMP_TYPES && + required_len[ich->type] && + skb->len - iphoff - ih->ihl * 4 < required_len[ich->type]) { + nf_log_buf_add(m, "INCOMPLETE [%u bytes] ", + skb->len - iphoff - ih->ihl * 4); + break; + } + + switch (ich->type) { + case ICMP_ECHOREPLY: + case ICMP_ECHO: + /* Max length: 19 "ID=65535 SEQ=65535 " */ + nf_log_buf_add(m, "ID=%u SEQ=%u ", + ntohs(ich->un.echo.id), + ntohs(ich->un.echo.sequence)); + break; + + case ICMP_PARAMETERPROB: + /* Max length: 14 "PARAMETER=255 " */ + nf_log_buf_add(m, "PARAMETER=%u ", + ntohl(ich->un.gateway) >> 24); + break; + case ICMP_REDIRECT: + /* Max length: 24 "GATEWAY=255.255.255.255 " */ + nf_log_buf_add(m, "GATEWAY=%pI4 ", &ich->un.gateway); + fallthrough; + case ICMP_DEST_UNREACH: + case ICMP_SOURCE_QUENCH: + case ICMP_TIME_EXCEEDED: + /* Max length: 3+maxlen */ + if (!iphoff) { /* Only recurse once. */ + nf_log_buf_add(m, "["); + dump_ipv4_packet(net, m, info, skb, + iphoff + ih->ihl * 4 + sizeof(_icmph)); + nf_log_buf_add(m, "] "); + } + + /* Max length: 10 "MTU=65535 " */ + if (ich->type == ICMP_DEST_UNREACH && + ich->code == ICMP_FRAG_NEEDED) { + nf_log_buf_add(m, "MTU=%u ", + ntohs(ich->un.frag.mtu)); + } + } + break; + } + /* Max Length */ + case IPPROTO_AH: { + const struct ip_auth_hdr *ah; + struct ip_auth_hdr _ahdr; + + if (ntohs(ih->frag_off) & IP_OFFSET) + break; + + /* Max length: 9 "PROTO=AH " */ + nf_log_buf_add(m, "PROTO=AH "); + + /* Max length: 25 "INCOMPLETE [65535 bytes] " */ + ah = skb_header_pointer(skb, iphoff + ih->ihl * 4, + sizeof(_ahdr), &_ahdr); + if (!ah) { + nf_log_buf_add(m, "INCOMPLETE [%u bytes] ", + skb->len - iphoff - ih->ihl * 4); + break; + } + + /* Length: 15 "SPI=0xF1234567 " */ + nf_log_buf_add(m, "SPI=0x%x ", ntohl(ah->spi)); + break; + } + case IPPROTO_ESP: { + const struct ip_esp_hdr *eh; + struct ip_esp_hdr _esph; + + /* Max length: 10 "PROTO=ESP " */ + nf_log_buf_add(m, "PROTO=ESP "); + + if (ntohs(ih->frag_off) & IP_OFFSET) + break; + + /* Max length: 25 "INCOMPLETE [65535 bytes] " */ + eh = skb_header_pointer(skb, iphoff + ih->ihl * 4, + sizeof(_esph), &_esph); + if (!eh) { + nf_log_buf_add(m, "INCOMPLETE [%u bytes] ", + skb->len - iphoff - ih->ihl * 4); + break; + } + + /* Length: 15 "SPI=0xF1234567 " */ + nf_log_buf_add(m, "SPI=0x%x ", ntohl(eh->spi)); + break; + } + /* Max length: 10 "PROTO 255 " */ + default: + nf_log_buf_add(m, "PROTO=%u ", ih->protocol); + } + + /* Max length: 15 "UID=4294967295 " */ + if ((logflags & NF_LOG_UID) && !iphoff) + nf_log_dump_sk_uid_gid(net, m, skb->sk); + + /* Max length: 16 "MARK=0xFFFFFFFF " */ + if (!iphoff && skb->mark) + nf_log_buf_add(m, "MARK=0x%x ", skb->mark); + + /* Proto Max log string length */ + /* IP: 40+46+6+11+127 = 230 */ + /* TCP: 10+max(25,20+30+13+9+32+11+127) = 252 */ + /* UDP: 10+max(25,20) = 35 */ + /* UDPLITE: 14+max(25,20) = 39 */ + /* ICMP: 11+max(25, 18+25+max(19,14,24+3+n+10,3+n+10)) = 91+n */ + /* ESP: 10+max(25)+15 = 50 */ + /* AH: 9+max(25)+15 = 49 */ + /* unknown: 10 */ + + /* (ICMP allows recursion one level deep) */ + /* maxlen = IP + ICMP + IP + max(TCP,UDP,ICMP,unknown) */ + /* maxlen = 230+ 91 + 230 + 252 = 803 */ +} + +static noinline_for_stack void +dump_ipv6_packet(struct net *net, struct nf_log_buf *m, + const struct nf_loginfo *info, + const struct sk_buff *skb, unsigned int ip6hoff, + int recurse) +{ + const struct ipv6hdr *ih; + unsigned int hdrlen = 0; + unsigned int logflags; + struct ipv6hdr _ip6h; + unsigned int ptr; + u8 currenthdr; + int fragment; + + if (info->type == NF_LOG_TYPE_LOG) + logflags = info->u.log.logflags; + else + logflags = NF_LOG_DEFAULT_MASK; + + ih = skb_header_pointer(skb, ip6hoff, sizeof(_ip6h), &_ip6h); + if (!ih) { + nf_log_buf_add(m, "TRUNCATED"); + return; + } + + /* Max length: 88 "SRC=0000.0000.0000.0000.0000.0000.0000.0000 DST=0000.0000.0000.0000.0000.0000.0000.0000 " */ + nf_log_buf_add(m, "SRC=%pI6 DST=%pI6 ", &ih->saddr, &ih->daddr); + + /* Max length: 44 "LEN=65535 TC=255 HOPLIMIT=255 FLOWLBL=FFFFF " */ + nf_log_buf_add(m, "LEN=%zu TC=%u HOPLIMIT=%u FLOWLBL=%u ", + ntohs(ih->payload_len) + sizeof(struct ipv6hdr), + (ntohl(*(__be32 *)ih) & 0x0ff00000) >> 20, + ih->hop_limit, + (ntohl(*(__be32 *)ih) & 0x000fffff)); + + fragment = 0; + ptr = ip6hoff + sizeof(struct ipv6hdr); + currenthdr = ih->nexthdr; + while (currenthdr != NEXTHDR_NONE && nf_ip6_ext_hdr(currenthdr)) { + struct ipv6_opt_hdr _hdr; + const struct ipv6_opt_hdr *hp; + + hp = skb_header_pointer(skb, ptr, sizeof(_hdr), &_hdr); + if (!hp) { + nf_log_buf_add(m, "TRUNCATED"); + return; + } + + /* Max length: 48 "OPT (...) " */ + if (logflags & NF_LOG_IPOPT) + nf_log_buf_add(m, "OPT ( "); + + switch (currenthdr) { + case IPPROTO_FRAGMENT: { + struct frag_hdr _fhdr; + const struct frag_hdr *fh; + + nf_log_buf_add(m, "FRAG:"); + fh = skb_header_pointer(skb, ptr, sizeof(_fhdr), + &_fhdr); + if (!fh) { + nf_log_buf_add(m, "TRUNCATED "); + return; + } + + /* Max length: 6 "65535 " */ + nf_log_buf_add(m, "%u ", ntohs(fh->frag_off) & 0xFFF8); + + /* Max length: 11 "INCOMPLETE " */ + if (fh->frag_off & htons(0x0001)) + nf_log_buf_add(m, "INCOMPLETE "); + + nf_log_buf_add(m, "ID:%08x ", + ntohl(fh->identification)); + + if (ntohs(fh->frag_off) & 0xFFF8) + fragment = 1; + + hdrlen = 8; + break; + } + case IPPROTO_DSTOPTS: + case IPPROTO_ROUTING: + case IPPROTO_HOPOPTS: + if (fragment) { + if (logflags & NF_LOG_IPOPT) + nf_log_buf_add(m, ")"); + return; + } + hdrlen = ipv6_optlen(hp); + break; + /* Max Length */ + case IPPROTO_AH: + if (logflags & NF_LOG_IPOPT) { + struct ip_auth_hdr _ahdr; + const struct ip_auth_hdr *ah; + + /* Max length: 3 "AH " */ + nf_log_buf_add(m, "AH "); + + if (fragment) { + nf_log_buf_add(m, ")"); + return; + } + + ah = skb_header_pointer(skb, ptr, sizeof(_ahdr), + &_ahdr); + if (!ah) { + /* Max length: 26 "INCOMPLETE [65535 bytes] )" */ + nf_log_buf_add(m, "INCOMPLETE [%u bytes] )", + skb->len - ptr); + return; + } + + /* Length: 15 "SPI=0xF1234567 */ + nf_log_buf_add(m, "SPI=0x%x ", ntohl(ah->spi)); + } + + hdrlen = ipv6_authlen(hp); + break; + case IPPROTO_ESP: + if (logflags & NF_LOG_IPOPT) { + struct ip_esp_hdr _esph; + const struct ip_esp_hdr *eh; + + /* Max length: 4 "ESP " */ + nf_log_buf_add(m, "ESP "); + + if (fragment) { + nf_log_buf_add(m, ")"); + return; + } + + /* Max length: 26 "INCOMPLETE [65535 bytes] )" */ + eh = skb_header_pointer(skb, ptr, sizeof(_esph), + &_esph); + if (!eh) { + nf_log_buf_add(m, "INCOMPLETE [%u bytes] )", + skb->len - ptr); + return; + } + + /* Length: 16 "SPI=0xF1234567 )" */ + nf_log_buf_add(m, "SPI=0x%x )", + ntohl(eh->spi)); + } + return; + default: + /* Max length: 20 "Unknown Ext Hdr 255" */ + nf_log_buf_add(m, "Unknown Ext Hdr %u", currenthdr); + return; + } + if (logflags & NF_LOG_IPOPT) + nf_log_buf_add(m, ") "); + + currenthdr = hp->nexthdr; + ptr += hdrlen; + } + + switch (currenthdr) { + case IPPROTO_TCP: + if (nf_log_dump_tcp_header(m, skb, currenthdr, fragment, + ptr, logflags)) + return; + break; + case IPPROTO_UDP: + case IPPROTO_UDPLITE: + if (nf_log_dump_udp_header(m, skb, currenthdr, fragment, ptr)) + return; + break; + case IPPROTO_ICMPV6: { + struct icmp6hdr _icmp6h; + const struct icmp6hdr *ic; + + /* Max length: 13 "PROTO=ICMPv6 " */ + nf_log_buf_add(m, "PROTO=ICMPv6 "); + + if (fragment) + break; + + /* Max length: 25 "INCOMPLETE [65535 bytes] " */ + ic = skb_header_pointer(skb, ptr, sizeof(_icmp6h), &_icmp6h); + if (!ic) { + nf_log_buf_add(m, "INCOMPLETE [%u bytes] ", + skb->len - ptr); + return; + } + + /* Max length: 18 "TYPE=255 CODE=255 " */ + nf_log_buf_add(m, "TYPE=%u CODE=%u ", + ic->icmp6_type, ic->icmp6_code); + + switch (ic->icmp6_type) { + case ICMPV6_ECHO_REQUEST: + case ICMPV6_ECHO_REPLY: + /* Max length: 19 "ID=65535 SEQ=65535 " */ + nf_log_buf_add(m, "ID=%u SEQ=%u ", + ntohs(ic->icmp6_identifier), + ntohs(ic->icmp6_sequence)); + break; + case ICMPV6_MGM_QUERY: + case ICMPV6_MGM_REPORT: + case ICMPV6_MGM_REDUCTION: + break; + + case ICMPV6_PARAMPROB: + /* Max length: 17 "POINTER=ffffffff " */ + nf_log_buf_add(m, "POINTER=%08x ", + ntohl(ic->icmp6_pointer)); + fallthrough; + case ICMPV6_DEST_UNREACH: + case ICMPV6_PKT_TOOBIG: + case ICMPV6_TIME_EXCEED: + /* Max length: 3+maxlen */ + if (recurse) { + nf_log_buf_add(m, "["); + dump_ipv6_packet(net, m, info, skb, + ptr + sizeof(_icmp6h), 0); + nf_log_buf_add(m, "] "); + } + + /* Max length: 10 "MTU=65535 " */ + if (ic->icmp6_type == ICMPV6_PKT_TOOBIG) { + nf_log_buf_add(m, "MTU=%u ", + ntohl(ic->icmp6_mtu)); + } + } + break; + } + /* Max length: 10 "PROTO=255 " */ + default: + nf_log_buf_add(m, "PROTO=%u ", currenthdr); + } + + /* Max length: 15 "UID=4294967295 " */ + if ((logflags & NF_LOG_UID) && recurse) + nf_log_dump_sk_uid_gid(net, m, skb->sk); + + /* Max length: 16 "MARK=0xFFFFFFFF " */ + if (recurse && skb->mark) + nf_log_buf_add(m, "MARK=0x%x ", skb->mark); +} + +static void dump_ipv4_mac_header(struct nf_log_buf *m, + const struct nf_loginfo *info, + const struct sk_buff *skb) +{ + struct net_device *dev = skb->dev; + unsigned int logflags = 0; + + if (info->type == NF_LOG_TYPE_LOG) + logflags = info->u.log.logflags; + + if (!(logflags & NF_LOG_MACDECODE)) + goto fallback; + + switch (dev->type) { + case ARPHRD_ETHER: + nf_log_buf_add(m, "MACSRC=%pM MACDST=%pM ", + eth_hdr(skb)->h_source, eth_hdr(skb)->h_dest); + nf_log_dump_vlan(m, skb); + nf_log_buf_add(m, "MACPROTO=%04x ", + ntohs(eth_hdr(skb)->h_proto)); + return; + default: + break; + } + +fallback: + nf_log_buf_add(m, "MAC="); + if (dev->hard_header_len && + skb->mac_header != skb->network_header) { + const unsigned char *p = skb_mac_header(skb); + unsigned int i; + + nf_log_buf_add(m, "%02x", *p++); + for (i = 1; i < dev->hard_header_len; i++, p++) + nf_log_buf_add(m, ":%02x", *p); + } + nf_log_buf_add(m, " "); +} + +static void nf_log_ip_packet(struct net *net, u_int8_t pf, + unsigned int hooknum, const struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + const struct nf_loginfo *loginfo, + const char *prefix) +{ + struct nf_log_buf *m; + + /* FIXME: Disabled from containers until syslog ns is supported */ + if (!net_eq(net, &init_net) && !sysctl_nf_log_all_netns) + return; + + m = nf_log_buf_open(); + + if (!loginfo) + loginfo = &default_loginfo; + + nf_log_dump_packet_common(m, pf, hooknum, skb, in, + out, loginfo, prefix); + + if (in) + dump_ipv4_mac_header(m, loginfo, skb); + + dump_ipv4_packet(net, m, loginfo, skb, 0); + + nf_log_buf_close(m); +} + +static struct nf_logger nf_ip_logger __read_mostly = { + .name = "nf_log_ipv4", + .type = NF_LOG_TYPE_LOG, + .logfn = nf_log_ip_packet, + .me = THIS_MODULE, +}; + +static void dump_ipv6_mac_header(struct nf_log_buf *m, + const struct nf_loginfo *info, + const struct sk_buff *skb) +{ + struct net_device *dev = skb->dev; + unsigned int logflags = 0; + + if (info->type == NF_LOG_TYPE_LOG) + logflags = info->u.log.logflags; + + if (!(logflags & NF_LOG_MACDECODE)) + goto fallback; + + switch (dev->type) { + case ARPHRD_ETHER: + nf_log_buf_add(m, "MACSRC=%pM MACDST=%pM ", + eth_hdr(skb)->h_source, eth_hdr(skb)->h_dest); + nf_log_dump_vlan(m, skb); + nf_log_buf_add(m, "MACPROTO=%04x ", + ntohs(eth_hdr(skb)->h_proto)); + return; + default: + break; + } + +fallback: + nf_log_buf_add(m, "MAC="); + if (dev->hard_header_len && + skb->mac_header != skb->network_header) { + const unsigned char *p = skb_mac_header(skb); + unsigned int len = dev->hard_header_len; + unsigned int i; + + if (dev->type == ARPHRD_SIT) { + p -= ETH_HLEN; + + if (p < skb->head) + p = NULL; + } + + if (p) { + nf_log_buf_add(m, "%02x", *p++); + for (i = 1; i < len; i++) + nf_log_buf_add(m, ":%02x", *p++); + } + nf_log_buf_add(m, " "); + + if (dev->type == ARPHRD_SIT) { + const struct iphdr *iph = + (struct iphdr *)skb_mac_header(skb); + nf_log_buf_add(m, "TUNNEL=%pI4->%pI4 ", &iph->saddr, + &iph->daddr); + } + } else { + nf_log_buf_add(m, " "); + } +} + +static void nf_log_ip6_packet(struct net *net, u_int8_t pf, + unsigned int hooknum, const struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + const struct nf_loginfo *loginfo, + const char *prefix) +{ + struct nf_log_buf *m; + + /* FIXME: Disabled from containers until syslog ns is supported */ + if (!net_eq(net, &init_net) && !sysctl_nf_log_all_netns) + return; + + m = nf_log_buf_open(); + + if (!loginfo) + loginfo = &default_loginfo; + + nf_log_dump_packet_common(m, pf, hooknum, skb, in, out, + loginfo, prefix); + + if (in) + dump_ipv6_mac_header(m, loginfo, skb); + + dump_ipv6_packet(net, m, loginfo, skb, skb_network_offset(skb), 1); + + nf_log_buf_close(m); +} + +static struct nf_logger nf_ip6_logger __read_mostly = { + .name = "nf_log_ipv6", + .type = NF_LOG_TYPE_LOG, + .logfn = nf_log_ip6_packet, + .me = THIS_MODULE, +}; + +static void nf_log_netdev_packet(struct net *net, u_int8_t pf, + unsigned int hooknum, + const struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + const struct nf_loginfo *loginfo, + const char *prefix) +{ + switch (skb->protocol) { + case htons(ETH_P_IP): + nf_log_ip_packet(net, pf, hooknum, skb, in, out, loginfo, prefix); + break; + case htons(ETH_P_IPV6): + nf_log_ip6_packet(net, pf, hooknum, skb, in, out, loginfo, prefix); + break; + case htons(ETH_P_ARP): + case htons(ETH_P_RARP): + nf_log_arp_packet(net, pf, hooknum, skb, in, out, loginfo, prefix); + break; + } +} + +static struct nf_logger nf_netdev_logger __read_mostly = { + .name = "nf_log_netdev", + .type = NF_LOG_TYPE_LOG, + .logfn = nf_log_netdev_packet, + .me = THIS_MODULE, +}; + +static struct nf_logger nf_bridge_logger __read_mostly = { + .name = "nf_log_bridge", + .type = NF_LOG_TYPE_LOG, + .logfn = nf_log_netdev_packet, + .me = THIS_MODULE, +}; + +static int __net_init nf_log_syslog_net_init(struct net *net) +{ + int ret = nf_log_set(net, NFPROTO_IPV4, &nf_ip_logger); + + if (ret) + return ret; + + ret = nf_log_set(net, NFPROTO_ARP, &nf_arp_logger); + if (ret) + goto err1; + + ret = nf_log_set(net, NFPROTO_IPV6, &nf_ip6_logger); + if (ret) + goto err2; + + ret = nf_log_set(net, NFPROTO_NETDEV, &nf_netdev_logger); + if (ret) + goto err3; + + ret = nf_log_set(net, NFPROTO_BRIDGE, &nf_bridge_logger); + if (ret) + goto err4; + return 0; +err4: + nf_log_unset(net, &nf_netdev_logger); +err3: + nf_log_unset(net, &nf_ip6_logger); +err2: + nf_log_unset(net, &nf_arp_logger); +err1: + nf_log_unset(net, &nf_ip_logger); + return ret; +} + +static void __net_exit nf_log_syslog_net_exit(struct net *net) +{ + nf_log_unset(net, &nf_ip_logger); + nf_log_unset(net, &nf_arp_logger); + nf_log_unset(net, &nf_ip6_logger); + nf_log_unset(net, &nf_netdev_logger); + nf_log_unset(net, &nf_bridge_logger); +} + +static struct pernet_operations nf_log_syslog_net_ops = { + .init = nf_log_syslog_net_init, + .exit = nf_log_syslog_net_exit, +}; + +static int __init nf_log_syslog_init(void) +{ + int ret; + + ret = register_pernet_subsys(&nf_log_syslog_net_ops); + if (ret < 0) + return ret; + + ret = nf_log_register(NFPROTO_IPV4, &nf_ip_logger); + if (ret < 0) + goto err1; + + ret = nf_log_register(NFPROTO_ARP, &nf_arp_logger); + if (ret < 0) + goto err2; + + ret = nf_log_register(NFPROTO_IPV6, &nf_ip6_logger); + if (ret < 0) + goto err3; + + ret = nf_log_register(NFPROTO_NETDEV, &nf_netdev_logger); + if (ret < 0) + goto err4; + + ret = nf_log_register(NFPROTO_BRIDGE, &nf_bridge_logger); + if (ret < 0) + goto err5; + + return 0; +err5: + nf_log_unregister(&nf_netdev_logger); +err4: + nf_log_unregister(&nf_ip6_logger); +err3: + nf_log_unregister(&nf_arp_logger); +err2: + nf_log_unregister(&nf_ip_logger); +err1: + pr_err("failed to register logger\n"); + unregister_pernet_subsys(&nf_log_syslog_net_ops); + return ret; +} + +static void __exit nf_log_syslog_exit(void) +{ + unregister_pernet_subsys(&nf_log_syslog_net_ops); + nf_log_unregister(&nf_ip_logger); + nf_log_unregister(&nf_arp_logger); + nf_log_unregister(&nf_ip6_logger); + nf_log_unregister(&nf_netdev_logger); + nf_log_unregister(&nf_bridge_logger); +} + +module_init(nf_log_syslog_init); +module_exit(nf_log_syslog_exit); + +MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>"); +MODULE_DESCRIPTION("Netfilter syslog packet logging"); +MODULE_LICENSE("GPL"); +MODULE_ALIAS("nf_log_arp"); +MODULE_ALIAS("nf_log_bridge"); +MODULE_ALIAS("nf_log_ipv4"); +MODULE_ALIAS("nf_log_ipv6"); +MODULE_ALIAS("nf_log_netdev"); +MODULE_ALIAS_NF_LOGGER(AF_BRIDGE, 0); +MODULE_ALIAS_NF_LOGGER(AF_INET, 0); +MODULE_ALIAS_NF_LOGGER(3, 0); +MODULE_ALIAS_NF_LOGGER(5, 0); /* NFPROTO_NETDEV */ +MODULE_ALIAS_NF_LOGGER(AF_INET6, 0); diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index b7c3c902290f..7de595ead06a 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -146,43 +146,6 @@ static void __nf_nat_decode_session(struct sk_buff *skb, struct flowi *fl) return; } } - -int nf_xfrm_me_harder(struct net *net, struct sk_buff *skb, unsigned int family) -{ - struct flowi fl; - unsigned int hh_len; - struct dst_entry *dst; - struct sock *sk = skb->sk; - int err; - - err = xfrm_decode_session(skb, &fl, family); - if (err < 0) - return err; - - dst = skb_dst(skb); - if (dst->xfrm) - dst = ((struct xfrm_dst *)dst)->route; - if (!dst_hold_safe(dst)) - return -EHOSTUNREACH; - - if (sk && !net_eq(net, sock_net(sk))) - sk = NULL; - - dst = xfrm_lookup(net, dst, &fl, sk, 0); - if (IS_ERR(dst)) - return PTR_ERR(dst); - - skb_dst_drop(skb); - skb_dst_set(skb, dst); - - /* Change in oif may mean change in hh_len. */ - hh_len = skb_dst(skb)->dev->hard_header_len; - if (skb_headroom(skb) < hh_len && - pskb_expand_head(skb, hh_len - skb_headroom(skb), 0, GFP_ATOMIC)) - return -ENOMEM; - return 0; -} -EXPORT_SYMBOL(nf_xfrm_me_harder); #endif /* CONFIG_XFRM */ /* We keep an extra hash for each conntrack, for fast searching. */ diff --git a/net/netfilter/nf_nat_proto.c b/net/netfilter/nf_nat_proto.c index 4731d21fc3ad..48cc60084d28 100644 --- a/net/netfilter/nf_nat_proto.c +++ b/net/netfilter/nf_nat_proto.c @@ -659,6 +659,44 @@ nf_nat_ipv4_pre_routing(void *priv, struct sk_buff *skb, return ret; } +#ifdef CONFIG_XFRM +static int nf_xfrm_me_harder(struct net *net, struct sk_buff *skb, unsigned int family) +{ + struct sock *sk = skb->sk; + struct dst_entry *dst; + unsigned int hh_len; + struct flowi fl; + int err; + + err = xfrm_decode_session(skb, &fl, family); + if (err < 0) + return err; + + dst = skb_dst(skb); + if (dst->xfrm) + dst = ((struct xfrm_dst *)dst)->route; + if (!dst_hold_safe(dst)) + return -EHOSTUNREACH; + + if (sk && !net_eq(net, sock_net(sk))) + sk = NULL; + + dst = xfrm_lookup(net, dst, &fl, sk, 0); + if (IS_ERR(dst)) + return PTR_ERR(dst); + + skb_dst_drop(skb); + skb_dst_set(skb, dst); + + /* Change in oif may mean change in hh_len. */ + hh_len = skb_dst(skb)->dev->hard_header_len; + if (skb_headroom(skb) < hh_len && + pskb_expand_head(skb, hh_len - skb_headroom(skb), 0, GFP_ATOMIC)) + return -ENOMEM; + return 0; +} +#endif + static unsigned int nf_nat_ipv4_local_in(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 589d2f6978d3..0b7fe0a902ff 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -25,6 +25,8 @@ #define NFT_MODULE_AUTOLOAD_LIMIT (MODULE_NAME_LEN - sizeof("nft-expr-255-")) +unsigned int nf_tables_net_id __read_mostly; + static LIST_HEAD(nf_tables_expressions); static LIST_HEAD(nf_tables_objects); static LIST_HEAD(nf_tables_flowtables); @@ -66,9 +68,46 @@ static const struct rhashtable_params nft_objname_ht_params = { .automatic_shrinking = true, }; +struct nft_audit_data { + struct nft_table *table; + int entries; + int op; + struct list_head list; +}; + +static const u8 nft2audit_op[NFT_MSG_MAX] = { // enum nf_tables_msg_types + [NFT_MSG_NEWTABLE] = AUDIT_NFT_OP_TABLE_REGISTER, + [NFT_MSG_GETTABLE] = AUDIT_NFT_OP_INVALID, + [NFT_MSG_DELTABLE] = AUDIT_NFT_OP_TABLE_UNREGISTER, + [NFT_MSG_NEWCHAIN] = AUDIT_NFT_OP_CHAIN_REGISTER, + [NFT_MSG_GETCHAIN] = AUDIT_NFT_OP_INVALID, + [NFT_MSG_DELCHAIN] = AUDIT_NFT_OP_CHAIN_UNREGISTER, + [NFT_MSG_NEWRULE] = AUDIT_NFT_OP_RULE_REGISTER, + [NFT_MSG_GETRULE] = AUDIT_NFT_OP_INVALID, + [NFT_MSG_DELRULE] = AUDIT_NFT_OP_RULE_UNREGISTER, + [NFT_MSG_NEWSET] = AUDIT_NFT_OP_SET_REGISTER, + [NFT_MSG_GETSET] = AUDIT_NFT_OP_INVALID, + [NFT_MSG_DELSET] = AUDIT_NFT_OP_SET_UNREGISTER, + [NFT_MSG_NEWSETELEM] = AUDIT_NFT_OP_SETELEM_REGISTER, + [NFT_MSG_GETSETELEM] = AUDIT_NFT_OP_INVALID, + [NFT_MSG_DELSETELEM] = AUDIT_NFT_OP_SETELEM_UNREGISTER, + [NFT_MSG_NEWGEN] = AUDIT_NFT_OP_GEN_REGISTER, + [NFT_MSG_GETGEN] = AUDIT_NFT_OP_INVALID, + [NFT_MSG_TRACE] = AUDIT_NFT_OP_INVALID, + [NFT_MSG_NEWOBJ] = AUDIT_NFT_OP_OBJ_REGISTER, + [NFT_MSG_GETOBJ] = AUDIT_NFT_OP_INVALID, + [NFT_MSG_DELOBJ] = AUDIT_NFT_OP_OBJ_UNREGISTER, + [NFT_MSG_GETOBJ_RESET] = AUDIT_NFT_OP_OBJ_RESET, + [NFT_MSG_NEWFLOWTABLE] = AUDIT_NFT_OP_FLOWTABLE_REGISTER, + [NFT_MSG_GETFLOWTABLE] = AUDIT_NFT_OP_INVALID, + [NFT_MSG_DELFLOWTABLE] = AUDIT_NFT_OP_FLOWTABLE_UNREGISTER, +}; + static void nft_validate_state_update(struct net *net, u8 new_validate_state) { - switch (net->nft.validate_state) { + struct nftables_pernet *nft_net = nft_pernet(net); + + switch (nft_net->validate_state) { case NFT_VALIDATE_SKIP: WARN_ON_ONCE(new_validate_state == NFT_VALIDATE_DO); break; @@ -79,7 +118,7 @@ static void nft_validate_state_update(struct net *net, u8 new_validate_state) return; } - net->nft.validate_state = new_validate_state; + nft_net->validate_state = new_validate_state; } static void nf_tables_trans_destroy_work(struct work_struct *w); static DECLARE_WORK(trans_destroy_work, nf_tables_trans_destroy_work); @@ -134,13 +173,15 @@ static void nft_trans_destroy(struct nft_trans *trans) static void nft_set_trans_bind(const struct nft_ctx *ctx, struct nft_set *set) { + struct nftables_pernet *nft_net; struct net *net = ctx->net; struct nft_trans *trans; if (!nft_set_is_anonymous(set)) return; - list_for_each_entry_reverse(trans, &net->nft.commit_list, list) { + nft_net = nft_pernet(net); + list_for_each_entry_reverse(trans, &nft_net->commit_list, list) { switch (trans->msg_type) { case NFT_MSG_NEWSET: if (nft_trans_set(trans) == set) @@ -234,6 +275,13 @@ static void nf_tables_unregister_hook(struct net *net, nf_unregister_net_hook(net, &basechain->ops); } +static void nft_trans_commit_list_add_tail(struct net *net, struct nft_trans *trans) +{ + struct nftables_pernet *nft_net = nft_pernet(net); + + list_add_tail(&trans->list, &nft_net->commit_list); +} + static int nft_trans_table_add(struct nft_ctx *ctx, int msg_type) { struct nft_trans *trans; @@ -245,7 +293,7 @@ static int nft_trans_table_add(struct nft_ctx *ctx, int msg_type) if (msg_type == NFT_MSG_NEWTABLE) nft_activate_next(ctx->net, ctx->table); - list_add_tail(&trans->list, &ctx->net->nft.commit_list); + nft_trans_commit_list_add_tail(ctx->net, trans); return 0; } @@ -278,7 +326,7 @@ static struct nft_trans *nft_trans_chain_add(struct nft_ctx *ctx, int msg_type) } } - list_add_tail(&trans->list, &ctx->net->nft.commit_list); + nft_trans_commit_list_add_tail(ctx->net, trans); return trans; } @@ -351,7 +399,7 @@ static struct nft_trans *nft_trans_rule_add(struct nft_ctx *ctx, int msg_type, ntohl(nla_get_be32(ctx->nla[NFTA_RULE_ID])); } nft_trans_rule(trans) = rule; - list_add_tail(&trans->list, &ctx->net->nft.commit_list); + nft_trans_commit_list_add_tail(ctx->net, trans); return trans; } @@ -417,7 +465,7 @@ static int nft_trans_set_add(const struct nft_ctx *ctx, int msg_type, nft_activate_next(ctx->net, set); } nft_trans_set(trans) = set; - list_add_tail(&trans->list, &ctx->net->nft.commit_list); + nft_trans_commit_list_add_tail(ctx->net, trans); return 0; } @@ -449,7 +497,7 @@ static int nft_trans_obj_add(struct nft_ctx *ctx, int msg_type, nft_activate_next(ctx->net, obj); nft_trans_obj(trans) = obj; - list_add_tail(&trans->list, &ctx->net->nft.commit_list); + nft_trans_commit_list_add_tail(ctx->net, trans); return 0; } @@ -482,7 +530,7 @@ static int nft_trans_flowtable_add(struct nft_ctx *ctx, int msg_type, nft_activate_next(ctx->net, flowtable); nft_trans_flowtable(trans) = flowtable; - list_add_tail(&trans->list, &ctx->net->nft.commit_list); + nft_trans_commit_list_add_tail(ctx->net, trans); return 0; } @@ -510,13 +558,15 @@ static struct nft_table *nft_table_lookup(const struct net *net, const struct nlattr *nla, u8 family, u8 genmask, u32 nlpid) { + struct nftables_pernet *nft_net; struct nft_table *table; if (nla == NULL) return ERR_PTR(-EINVAL); - list_for_each_entry_rcu(table, &net->nft.tables, list, - lockdep_is_held(&net->nft.commit_mutex)) { + nft_net = nft_pernet(net); + list_for_each_entry_rcu(table, &nft_net->tables, list, + lockdep_is_held(&nft_net->commit_mutex)) { if (!nla_strcmp(nla, table->name) && table->family == family && nft_active_genmask(table, genmask)) { @@ -535,9 +585,11 @@ static struct nft_table *nft_table_lookup_byhandle(const struct net *net, const struct nlattr *nla, u8 genmask) { + struct nftables_pernet *nft_net; struct nft_table *table; - list_for_each_entry(table, &net->nft.tables, list) { + nft_net = nft_pernet(net); + list_for_each_entry(table, &nft_net->tables, list) { if (be64_to_cpu(nla_get_be64(nla)) == table->handle && nft_active_genmask(table, genmask)) return table; @@ -586,10 +638,11 @@ struct nft_module_request { }; #ifdef CONFIG_MODULES -static __printf(2, 3) int nft_request_module(struct net *net, const char *fmt, - ...) +__printf(2, 3) int nft_request_module(struct net *net, const char *fmt, + ...) { char module_name[MODULE_NAME_LEN]; + struct nftables_pernet *nft_net; struct nft_module_request *req; va_list args; int ret; @@ -600,7 +653,8 @@ static __printf(2, 3) int nft_request_module(struct net *net, const char *fmt, if (ret >= MODULE_NAME_LEN) return 0; - list_for_each_entry(req, &net->nft.module_list, list) { + nft_net = nft_pernet(net); + list_for_each_entry(req, &nft_net->module_list, list) { if (!strcmp(req->module, module_name)) { if (req->done) return 0; @@ -616,10 +670,11 @@ static __printf(2, 3) int nft_request_module(struct net *net, const char *fmt, req->done = false; strlcpy(req->module, module_name, MODULE_NAME_LEN); - list_add_tail(&req->list, &net->nft.module_list); + list_add_tail(&req->list, &nft_net->module_list); return -EAGAIN; } +EXPORT_SYMBOL_GPL(nft_request_module); #endif static void lockdep_nfnl_nft_mutex_not_held(void) @@ -652,6 +707,13 @@ nf_tables_chain_type_lookup(struct net *net, const struct nlattr *nla, return ERR_PTR(-ENOENT); } +static __be16 nft_base_seq(const struct net *net) +{ + struct nftables_pernet *nft_net = nft_pernet(net); + + return htons(nft_net->base_seq & 0xffff); +} + static const struct nla_policy nft_table_policy[NFTA_TABLE_MAX + 1] = { [NFTA_TABLE_NAME] = { .type = NLA_STRING, .len = NFT_TABLE_MAXNAMELEN - 1 }, @@ -666,18 +728,13 @@ static int nf_tables_fill_table_info(struct sk_buff *skb, struct net *net, int family, const struct nft_table *table) { struct nlmsghdr *nlh; - struct nfgenmsg *nfmsg; event = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event); - nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct nfgenmsg), flags); - if (nlh == NULL) + nlh = nfnl_msg_put(skb, portid, seq, event, flags, family, + NFNETLINK_V0, nft_base_seq(net)); + if (!nlh) goto nla_put_failure; - nfmsg = nlmsg_data(nlh); - nfmsg->nfgen_family = family; - nfmsg->version = NFNETLINK_V0; - nfmsg->res_id = htons(net->nft.base_seq & 0xffff); - if (nla_put_string(skb, NFTA_TABLE_NAME, table->name) || nla_put_be32(skb, NFTA_TABLE_FLAGS, htonl(table->flags)) || nla_put_be32(skb, NFTA_TABLE_USE, htonl(table->use)) || @@ -715,19 +772,9 @@ static void nft_notify_enqueue(struct sk_buff *skb, bool report, static void nf_tables_table_notify(const struct nft_ctx *ctx, int event) { + struct nftables_pernet *nft_net; struct sk_buff *skb; int err; - char *buf = kasprintf(GFP_KERNEL, "%s:%llu;?:0", - ctx->table->name, ctx->table->handle); - - audit_log_nfcfg(buf, - ctx->family, - ctx->table->use, - event == NFT_MSG_NEWTABLE ? - AUDIT_NFT_OP_TABLE_REGISTER : - AUDIT_NFT_OP_TABLE_UNREGISTER, - GFP_KERNEL); - kfree(buf); if (!ctx->report && !nfnetlink_has_listeners(ctx->net, NFNLGRP_NFTABLES)) @@ -744,7 +791,8 @@ static void nf_tables_table_notify(const struct nft_ctx *ctx, int event) goto err; } - nft_notify_enqueue(skb, ctx->report, &ctx->net->nft.notify_list); + nft_net = nft_pernet(ctx->net); + nft_notify_enqueue(skb, ctx->report, &nft_net->notify_list); return; err: nfnetlink_set_err(ctx->net, ctx->portid, NFNLGRP_NFTABLES, -ENOBUFS); @@ -754,15 +802,17 @@ static int nf_tables_dump_tables(struct sk_buff *skb, struct netlink_callback *cb) { const struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh); + struct nftables_pernet *nft_net; const struct nft_table *table; unsigned int idx = 0, s_idx = cb->args[0]; struct net *net = sock_net(skb->sk); int family = nfmsg->nfgen_family; rcu_read_lock(); - cb->seq = net->nft.base_seq; + nft_net = nft_pernet(net); + cb->seq = nft_net->base_seq; - list_for_each_entry_rcu(table, &net->nft.tables, list) { + list_for_each_entry_rcu(table, &nft_net->tables, list) { if (family != NFPROTO_UNSPEC && family != table->family) continue; @@ -808,25 +858,25 @@ static int nft_netlink_dump_start_rcu(struct sock *nlsk, struct sk_buff *skb, } /* called with rcu_read_lock held */ -static int nf_tables_gettable(struct net *net, struct sock *nlsk, - struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nla[], - struct netlink_ext_ack *extack) +static int nf_tables_gettable(struct sk_buff *skb, const struct nfnl_info *info, + const struct nlattr * const nla[]) { - const struct nfgenmsg *nfmsg = nlmsg_data(nlh); - u8 genmask = nft_genmask_cur(net); + const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); + struct netlink_ext_ack *extack = info->extack; + u8 genmask = nft_genmask_cur(info->net); + int family = nfmsg->nfgen_family; const struct nft_table *table; + struct net *net = info->net; struct sk_buff *skb2; - int family = nfmsg->nfgen_family; int err; - if (nlh->nlmsg_flags & NLM_F_DUMP) { + if (info->nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { .dump = nf_tables_dump_tables, .module = THIS_MODULE, }; - return nft_netlink_dump_start_rcu(nlsk, skb, nlh, &c); + return nft_netlink_dump_start_rcu(info->sk, skb, info->nlh, &c); } table = nft_table_lookup(net, nla[NFTA_TABLE_NAME], family, genmask, 0); @@ -840,8 +890,8 @@ static int nf_tables_gettable(struct net *net, struct sock *nlsk, return -ENOMEM; err = nf_tables_fill_table_info(skb2, net, NETLINK_CB(skb).portid, - nlh->nlmsg_seq, NFT_MSG_NEWTABLE, 0, - family, table); + info->nlh->nlmsg_seq, NFT_MSG_NEWTABLE, + 0, family, table); if (err < 0) goto err_fill_table_info; @@ -900,6 +950,12 @@ static void nf_tables_table_disable(struct net *net, struct nft_table *table) nft_table_disable(net, table, 0); } +enum { + NFT_TABLE_STATE_UNCHANGED = 0, + NFT_TABLE_STATE_DORMANT, + NFT_TABLE_STATE_WAKEUP +}; + static int nf_tables_updtable(struct nft_ctx *ctx) { struct nft_trans *trans; @@ -929,21 +985,19 @@ static int nf_tables_updtable(struct nft_ctx *ctx) if ((flags & NFT_TABLE_F_DORMANT) && !(ctx->table->flags & NFT_TABLE_F_DORMANT)) { - nft_trans_table_enable(trans) = false; + nft_trans_table_state(trans) = NFT_TABLE_STATE_DORMANT; } else if (!(flags & NFT_TABLE_F_DORMANT) && ctx->table->flags & NFT_TABLE_F_DORMANT) { - ctx->table->flags &= ~NFT_TABLE_F_DORMANT; ret = nf_tables_table_enable(ctx->net, ctx->table); if (ret >= 0) - nft_trans_table_enable(trans) = true; - else - ctx->table->flags |= NFT_TABLE_F_DORMANT; + nft_trans_table_state(trans) = NFT_TABLE_STATE_WAKEUP; } if (ret < 0) goto err; + nft_trans_table_flags(trans) = flags; nft_trans_table_update(trans) = true; - list_add_tail(&trans->list, &ctx->net->nft.commit_list); + nft_trans_commit_list_add_tail(ctx->net, trans); return 0; err: nft_trans_destroy(trans); @@ -1001,21 +1055,22 @@ static int nft_objname_hash_cmp(struct rhashtable_compare_arg *arg, return strcmp(obj->key.name, k->name); } -static int nf_tables_newtable(struct net *net, struct sock *nlsk, - struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nla[], - struct netlink_ext_ack *extack) +static int nf_tables_newtable(struct sk_buff *skb, const struct nfnl_info *info, + const struct nlattr * const nla[]) { - const struct nfgenmsg *nfmsg = nlmsg_data(nlh); - u8 genmask = nft_genmask_next(net); + struct nftables_pernet *nft_net = nft_pernet(info->net); + const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); + struct netlink_ext_ack *extack = info->extack; + u8 genmask = nft_genmask_next(info->net); int family = nfmsg->nfgen_family; + struct net *net = info->net; const struct nlattr *attr; struct nft_table *table; struct nft_ctx ctx; u32 flags = 0; int err; - lockdep_assert_held(&net->nft.commit_mutex); + lockdep_assert_held(&nft_net->commit_mutex); attr = nla[NFTA_TABLE_NAME]; table = nft_table_lookup(net, attr, family, genmask, NETLINK_CB(skb).portid); @@ -1023,14 +1078,15 @@ static int nf_tables_newtable(struct net *net, struct sock *nlsk, if (PTR_ERR(table) != -ENOENT) return PTR_ERR(table); } else { - if (nlh->nlmsg_flags & NLM_F_EXCL) { + if (info->nlh->nlmsg_flags & NLM_F_EXCL) { NL_SET_BAD_ATTR(extack, attr); return -EEXIST; } - if (nlh->nlmsg_flags & NLM_F_REPLACE) + if (info->nlh->nlmsg_flags & NLM_F_REPLACE) return -EOPNOTSUPP; - nft_ctx_init(&ctx, net, skb, nlh, family, table, NULL, nla); + nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla); + return nf_tables_updtable(&ctx); } @@ -1071,12 +1127,12 @@ static int nf_tables_newtable(struct net *net, struct sock *nlsk, if (table->flags & NFT_TABLE_F_OWNER) table->nlpid = NETLINK_CB(skb).portid; - nft_ctx_init(&ctx, net, skb, nlh, family, table, NULL, nla); + nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla); err = nft_trans_table_add(&ctx, NFT_MSG_NEWTABLE); if (err < 0) goto err_trans; - list_add_tail_rcu(&table->list, &net->nft.tables); + list_add_tail_rcu(&table->list, &nft_net->tables); return 0; err_trans: rhltable_destroy(&table->chains_ht); @@ -1164,11 +1220,12 @@ out: static int nft_flush(struct nft_ctx *ctx, int family) { - struct nft_table *table, *nt; + struct nftables_pernet *nft_net = nft_pernet(ctx->net); const struct nlattr * const *nla = ctx->nla; + struct nft_table *table, *nt; int err = 0; - list_for_each_entry_safe(table, nt, &ctx->net->nft.tables, list) { + list_for_each_entry_safe(table, nt, &nft_net->tables, list) { if (family != AF_UNSPEC && table->family != family) continue; @@ -1194,19 +1251,19 @@ out: return err; } -static int nf_tables_deltable(struct net *net, struct sock *nlsk, - struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nla[], - struct netlink_ext_ack *extack) +static int nf_tables_deltable(struct sk_buff *skb, const struct nfnl_info *info, + const struct nlattr * const nla[]) { - const struct nfgenmsg *nfmsg = nlmsg_data(nlh); - u8 genmask = nft_genmask_next(net); + const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); + struct netlink_ext_ack *extack = info->extack; + u8 genmask = nft_genmask_next(info->net); int family = nfmsg->nfgen_family; + struct net *net = info->net; const struct nlattr *attr; struct nft_table *table; struct nft_ctx ctx; - nft_ctx_init(&ctx, net, skb, nlh, 0, NULL, NULL, nla); + nft_ctx_init(&ctx, net, skb, info->nlh, 0, NULL, NULL, nla); if (family == AF_UNSPEC || (!nla[NFTA_TABLE_NAME] && !nla[NFTA_TABLE_HANDLE])) return nft_flush(&ctx, family); @@ -1225,7 +1282,7 @@ static int nf_tables_deltable(struct net *net, struct sock *nlsk, return PTR_ERR(table); } - if (nlh->nlmsg_flags & NLM_F_NONREC && + if (info->nlh->nlmsg_flags & NLM_F_NONREC && table->use > 0) return -EBUSY; @@ -1287,7 +1344,9 @@ nft_chain_lookup_byhandle(const struct nft_table *table, u64 handle, u8 genmask) static bool lockdep_commit_lock_is_held(const struct net *net) { #ifdef CONFIG_PROVE_LOCKING - return lockdep_is_held(&net->nft.commit_mutex); + struct nftables_pernet *nft_net = nft_pernet(net); + + return lockdep_is_held(&nft_net->commit_mutex); #else return true; #endif @@ -1434,18 +1493,13 @@ static int nf_tables_fill_chain_info(struct sk_buff *skb, struct net *net, const struct nft_chain *chain) { struct nlmsghdr *nlh; - struct nfgenmsg *nfmsg; event = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event); - nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct nfgenmsg), flags); - if (nlh == NULL) + nlh = nfnl_msg_put(skb, portid, seq, event, flags, family, + NFNETLINK_V0, nft_base_seq(net)); + if (!nlh) goto nla_put_failure; - nfmsg = nlmsg_data(nlh); - nfmsg->nfgen_family = family; - nfmsg->version = NFNETLINK_V0; - nfmsg->res_id = htons(net->nft.base_seq & 0xffff); - if (nla_put_string(skb, NFTA_CHAIN_TABLE, table->name)) goto nla_put_failure; if (nla_put_be64(skb, NFTA_CHAIN_HANDLE, cpu_to_be64(chain->handle), @@ -1495,20 +1549,9 @@ nla_put_failure: static void nf_tables_chain_notify(const struct nft_ctx *ctx, int event) { + struct nftables_pernet *nft_net; struct sk_buff *skb; int err; - char *buf = kasprintf(GFP_KERNEL, "%s:%llu;%s:%llu", - ctx->table->name, ctx->table->handle, - ctx->chain->name, ctx->chain->handle); - - audit_log_nfcfg(buf, - ctx->family, - ctx->chain->use, - event == NFT_MSG_NEWCHAIN ? - AUDIT_NFT_OP_CHAIN_REGISTER : - AUDIT_NFT_OP_CHAIN_UNREGISTER, - GFP_KERNEL); - kfree(buf); if (!ctx->report && !nfnetlink_has_listeners(ctx->net, NFNLGRP_NFTABLES)) @@ -1526,7 +1569,8 @@ static void nf_tables_chain_notify(const struct nft_ctx *ctx, int event) goto err; } - nft_notify_enqueue(skb, ctx->report, &ctx->net->nft.notify_list); + nft_net = nft_pernet(ctx->net); + nft_notify_enqueue(skb, ctx->report, &nft_net->notify_list); return; err: nfnetlink_set_err(ctx->net, ctx->portid, NFNLGRP_NFTABLES, -ENOBUFS); @@ -1536,16 +1580,18 @@ static int nf_tables_dump_chains(struct sk_buff *skb, struct netlink_callback *cb) { const struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh); - const struct nft_table *table; - const struct nft_chain *chain; unsigned int idx = 0, s_idx = cb->args[0]; struct net *net = sock_net(skb->sk); int family = nfmsg->nfgen_family; + struct nftables_pernet *nft_net; + const struct nft_table *table; + const struct nft_chain *chain; rcu_read_lock(); - cb->seq = net->nft.base_seq; + nft_net = nft_pernet(net); + cb->seq = nft_net->base_seq; - list_for_each_entry_rcu(table, &net->nft.tables, list) { + list_for_each_entry_rcu(table, &nft_net->tables, list) { if (family != NFPROTO_UNSPEC && family != table->family) continue; @@ -1578,26 +1624,26 @@ done: } /* called with rcu_read_lock held */ -static int nf_tables_getchain(struct net *net, struct sock *nlsk, - struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nla[], - struct netlink_ext_ack *extack) +static int nf_tables_getchain(struct sk_buff *skb, const struct nfnl_info *info, + const struct nlattr * const nla[]) { - const struct nfgenmsg *nfmsg = nlmsg_data(nlh); - u8 genmask = nft_genmask_cur(net); + const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); + struct netlink_ext_ack *extack = info->extack; + u8 genmask = nft_genmask_cur(info->net); + int family = nfmsg->nfgen_family; const struct nft_chain *chain; + struct net *net = info->net; struct nft_table *table; struct sk_buff *skb2; - int family = nfmsg->nfgen_family; int err; - if (nlh->nlmsg_flags & NLM_F_DUMP) { + if (info->nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { .dump = nf_tables_dump_chains, .module = THIS_MODULE, }; - return nft_netlink_dump_start_rcu(nlsk, skb, nlh, &c); + return nft_netlink_dump_start_rcu(info->sk, skb, info->nlh, &c); } table = nft_table_lookup(net, nla[NFTA_CHAIN_TABLE], family, genmask, 0); @@ -1617,8 +1663,8 @@ static int nf_tables_getchain(struct net *net, struct sock *nlsk, return -ENOMEM; err = nf_tables_fill_chain_info(skb2, net, NETLINK_CB(skb).portid, - nlh->nlmsg_seq, NFT_MSG_NEWCHAIN, 0, - family, table, chain); + info->nlh->nlmsg_seq, NFT_MSG_NEWCHAIN, + 0, family, table, chain); if (err < 0) goto err_fill_chain_info; @@ -1861,11 +1907,12 @@ static int nft_chain_parse_hook(struct net *net, struct nft_chain_hook *hook, u8 family, bool autoload) { + struct nftables_pernet *nft_net = nft_pernet(net); struct nlattr *ha[NFTA_HOOK_MAX + 1]; const struct nft_chain_type *type; int err; - lockdep_assert_held(&net->nft.commit_mutex); + lockdep_assert_held(&nft_net->commit_mutex); lockdep_nfnl_nft_mutex_not_held(); err = nla_parse_nested_deprecated(ha, NFTA_HOOK_MAX, @@ -2254,6 +2301,7 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy, if (nla[NFTA_CHAIN_HANDLE] && nla[NFTA_CHAIN_NAME]) { + struct nftables_pernet *nft_net = nft_pernet(ctx->net); struct nft_trans *tmp; char *name; @@ -2263,7 +2311,7 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy, goto err; err = -EEXIST; - list_for_each_entry(tmp, &ctx->net->nft.commit_list, list) { + list_for_each_entry(tmp, &nft_net->commit_list, list) { if (tmp->msg_type == NFT_MSG_NEWCHAIN && tmp->ctx.table == table && nft_trans_chain_update(tmp) && @@ -2277,7 +2325,7 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy, nft_trans_chain_name(trans) = name; } - list_add_tail(&trans->list, &ctx->net->nft.commit_list); + nft_trans_commit_list_add_tail(ctx->net, trans); return 0; err: @@ -2289,10 +2337,11 @@ err: static struct nft_chain *nft_chain_lookup_byid(const struct net *net, const struct nlattr *nla) { + struct nftables_pernet *nft_net = nft_pernet(net); u32 id = ntohl(nla_get_be32(nla)); struct nft_trans *trans; - list_for_each_entry(trans, &net->nft.commit_list, list) { + list_for_each_entry(trans, &nft_net->commit_list, list) { struct nft_chain *chain = trans->ctx.chain; if (trans->msg_type == NFT_MSG_NEWCHAIN && @@ -2302,15 +2351,16 @@ static struct nft_chain *nft_chain_lookup_byid(const struct net *net, return ERR_PTR(-ENOENT); } -static int nf_tables_newchain(struct net *net, struct sock *nlsk, - struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nla[], - struct netlink_ext_ack *extack) +static int nf_tables_newchain(struct sk_buff *skb, const struct nfnl_info *info, + const struct nlattr * const nla[]) { - const struct nfgenmsg *nfmsg = nlmsg_data(nlh); - u8 genmask = nft_genmask_next(net); + struct nftables_pernet *nft_net = nft_pernet(info->net); + const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); + struct netlink_ext_ack *extack = info->extack; + u8 genmask = nft_genmask_next(info->net); int family = nfmsg->nfgen_family; struct nft_chain *chain = NULL; + struct net *net = info->net; const struct nlattr *attr; struct nft_table *table; u8 policy = NF_ACCEPT; @@ -2318,7 +2368,7 @@ static int nf_tables_newchain(struct net *net, struct sock *nlsk, u64 handle = 0; u32 flags = 0; - lockdep_assert_held(&net->nft.commit_mutex); + lockdep_assert_held(&nft_net->commit_mutex); table = nft_table_lookup(net, nla[NFTA_CHAIN_TABLE], family, genmask, NETLINK_CB(skb).portid); @@ -2382,14 +2432,14 @@ static int nf_tables_newchain(struct net *net, struct sock *nlsk, if (flags & ~NFT_CHAIN_FLAGS) return -EOPNOTSUPP; - nft_ctx_init(&ctx, net, skb, nlh, family, table, chain, nla); + nft_ctx_init(&ctx, net, skb, info->nlh, family, table, chain, nla); if (chain != NULL) { - if (nlh->nlmsg_flags & NLM_F_EXCL) { + if (info->nlh->nlmsg_flags & NLM_F_EXCL) { NL_SET_BAD_ATTR(extack, attr); return -EEXIST; } - if (nlh->nlmsg_flags & NLM_F_REPLACE) + if (info->nlh->nlmsg_flags & NLM_F_REPLACE) return -EOPNOTSUPP; flags |= chain->flags & NFT_CHAIN_BASE; @@ -2400,14 +2450,14 @@ static int nf_tables_newchain(struct net *net, struct sock *nlsk, return nf_tables_addchain(&ctx, family, genmask, policy, flags); } -static int nf_tables_delchain(struct net *net, struct sock *nlsk, - struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nla[], - struct netlink_ext_ack *extack) +static int nf_tables_delchain(struct sk_buff *skb, const struct nfnl_info *info, + const struct nlattr * const nla[]) { - const struct nfgenmsg *nfmsg = nlmsg_data(nlh); - u8 genmask = nft_genmask_next(net); + const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); + struct netlink_ext_ack *extack = info->extack; + u8 genmask = nft_genmask_next(info->net); int family = nfmsg->nfgen_family; + struct net *net = info->net; const struct nlattr *attr; struct nft_table *table; struct nft_chain *chain; @@ -2437,11 +2487,11 @@ static int nf_tables_delchain(struct net *net, struct sock *nlsk, return PTR_ERR(chain); } - if (nlh->nlmsg_flags & NLM_F_NONREC && + if (info->nlh->nlmsg_flags & NLM_F_NONREC && chain->use > 0) return -EBUSY; - nft_ctx_init(&ctx, net, skb, nlh, family, table, chain, nla); + nft_ctx_init(&ctx, net, skb, info->nlh, family, table, chain, nla); use = chain->use; list_for_each_entry(rule, &chain->rules, list) { @@ -2664,15 +2714,15 @@ err1: } static int nf_tables_newexpr(const struct nft_ctx *ctx, - const struct nft_expr_info *info, + const struct nft_expr_info *expr_info, struct nft_expr *expr) { - const struct nft_expr_ops *ops = info->ops; + const struct nft_expr_ops *ops = expr_info->ops; int err; expr->ops = ops; if (ops->init) { - err = ops->init(ctx, expr, (const struct nlattr **)info->tb); + err = ops->init(ctx, expr, (const struct nlattr **)expr_info->tb); if (err < 0) goto err1; } @@ -2696,21 +2746,21 @@ static void nf_tables_expr_destroy(const struct nft_ctx *ctx, static struct nft_expr *nft_expr_init(const struct nft_ctx *ctx, const struct nlattr *nla) { - struct nft_expr_info info; + struct nft_expr_info expr_info; struct nft_expr *expr; struct module *owner; int err; - err = nf_tables_expr_parse(ctx, nla, &info); + err = nf_tables_expr_parse(ctx, nla, &expr_info); if (err < 0) goto err1; err = -ENOMEM; - expr = kzalloc(info.ops->size, GFP_KERNEL); + expr = kzalloc(expr_info.ops->size, GFP_KERNEL); if (expr == NULL) goto err2; - err = nf_tables_newexpr(ctx, &info, expr); + err = nf_tables_newexpr(ctx, &expr_info, expr); if (err < 0) goto err3; @@ -2718,9 +2768,9 @@ static struct nft_expr *nft_expr_init(const struct nft_ctx *ctx, err3: kfree(expr); err2: - owner = info.ops->type->owner; - if (info.ops->type->release_ops) - info.ops->type->release_ops(info.ops); + owner = expr_info.ops->type->owner; + if (expr_info.ops->type->release_ops) + expr_info.ops->type->release_ops(expr_info.ops); module_put(owner); err1: @@ -2803,20 +2853,15 @@ static int nf_tables_fill_rule_info(struct sk_buff *skb, struct net *net, const struct nft_rule *prule) { struct nlmsghdr *nlh; - struct nfgenmsg *nfmsg; const struct nft_expr *expr, *next; struct nlattr *list; u16 type = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event); - nlh = nlmsg_put(skb, portid, seq, type, sizeof(struct nfgenmsg), flags); - if (nlh == NULL) + nlh = nfnl_msg_put(skb, portid, seq, type, flags, family, NFNETLINK_V0, + nft_base_seq(net)); + if (!nlh) goto nla_put_failure; - nfmsg = nlmsg_data(nlh); - nfmsg->nfgen_family = family; - nfmsg->version = NFNETLINK_V0; - nfmsg->res_id = htons(net->nft.base_seq & 0xffff); - if (nla_put_string(skb, NFTA_RULE_TABLE, table->name)) goto nla_put_failure; if (nla_put_string(skb, NFTA_RULE_CHAIN, chain->name)) @@ -2832,6 +2877,9 @@ static int nf_tables_fill_rule_info(struct sk_buff *skb, struct net *net, goto nla_put_failure; } + if (chain->flags & NFT_CHAIN_HW_OFFLOAD) + nft_flow_rule_stats(chain, rule); + list = nla_nest_start_noflag(skb, NFTA_RULE_EXPRESSIONS); if (list == NULL) goto nla_put_failure; @@ -2859,20 +2907,9 @@ nla_put_failure: static void nf_tables_rule_notify(const struct nft_ctx *ctx, const struct nft_rule *rule, int event) { + struct nftables_pernet *nft_net = nft_pernet(ctx->net); struct sk_buff *skb; int err; - char *buf = kasprintf(GFP_KERNEL, "%s:%llu;%s:%llu", - ctx->table->name, ctx->table->handle, - ctx->chain->name, ctx->chain->handle); - - audit_log_nfcfg(buf, - ctx->family, - rule->handle, - event == NFT_MSG_NEWRULE ? - AUDIT_NFT_OP_RULE_REGISTER : - AUDIT_NFT_OP_RULE_UNREGISTER, - GFP_KERNEL); - kfree(buf); if (!ctx->report && !nfnetlink_has_listeners(ctx->net, NFNLGRP_NFTABLES)) @@ -2890,7 +2927,7 @@ static void nf_tables_rule_notify(const struct nft_ctx *ctx, goto err; } - nft_notify_enqueue(skb, ctx->report, &ctx->net->nft.notify_list); + nft_notify_enqueue(skb, ctx->report, &nft_net->notify_list); return; err: nfnetlink_set_err(ctx->net, ctx->portid, NFNLGRP_NFTABLES, -ENOBUFS); @@ -2948,11 +2985,13 @@ static int nf_tables_dump_rules(struct sk_buff *skb, unsigned int idx = 0; struct net *net = sock_net(skb->sk); int family = nfmsg->nfgen_family; + struct nftables_pernet *nft_net; rcu_read_lock(); - cb->seq = net->nft.base_seq; + nft_net = nft_pernet(net); + cb->seq = nft_net->base_seq; - list_for_each_entry_rcu(table, &net->nft.tables, list) { + list_for_each_entry_rcu(table, &nft_net->tables, list) { if (family != NFPROTO_UNSPEC && family != table->family) continue; @@ -3038,21 +3077,21 @@ static int nf_tables_dump_rules_done(struct netlink_callback *cb) } /* called with rcu_read_lock held */ -static int nf_tables_getrule(struct net *net, struct sock *nlsk, - struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nla[], - struct netlink_ext_ack *extack) +static int nf_tables_getrule(struct sk_buff *skb, const struct nfnl_info *info, + const struct nlattr * const nla[]) { - const struct nfgenmsg *nfmsg = nlmsg_data(nlh); - u8 genmask = nft_genmask_cur(net); + const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); + struct netlink_ext_ack *extack = info->extack; + u8 genmask = nft_genmask_cur(info->net); + int family = nfmsg->nfgen_family; const struct nft_chain *chain; const struct nft_rule *rule; + struct net *net = info->net; struct nft_table *table; struct sk_buff *skb2; - int family = nfmsg->nfgen_family; int err; - if (nlh->nlmsg_flags & NLM_F_DUMP) { + if (info->nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { .start= nf_tables_dump_rules_start, .dump = nf_tables_dump_rules, @@ -3061,7 +3100,7 @@ static int nf_tables_getrule(struct net *net, struct sock *nlsk, .data = (void *)nla, }; - return nft_netlink_dump_start_rcu(nlsk, skb, nlh, &c); + return nft_netlink_dump_start_rcu(info->sk, skb, info->nlh, &c); } table = nft_table_lookup(net, nla[NFTA_RULE_TABLE], family, genmask, 0); @@ -3087,7 +3126,7 @@ static int nf_tables_getrule(struct net *net, struct sock *nlsk, return -ENOMEM; err = nf_tables_fill_rule_info(skb2, net, NETLINK_CB(skb).portid, - nlh->nlmsg_seq, NFT_MSG_NEWRULE, 0, + info->nlh->nlmsg_seq, NFT_MSG_NEWRULE, 0, family, table, chain, rule, NULL); if (err < 0) goto err_fill_rule_info; @@ -3178,29 +3217,30 @@ static struct nft_rule *nft_rule_lookup_byid(const struct net *net, #define NFT_RULE_MAXEXPRS 128 -static int nf_tables_newrule(struct net *net, struct sock *nlsk, - struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nla[], - struct netlink_ext_ack *extack) +static int nf_tables_newrule(struct sk_buff *skb, const struct nfnl_info *info, + const struct nlattr * const nla[]) { - const struct nfgenmsg *nfmsg = nlmsg_data(nlh); - u8 genmask = nft_genmask_next(net); - struct nft_expr_info *info = NULL; + struct nftables_pernet *nft_net = nft_pernet(info->net); + const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); + struct netlink_ext_ack *extack = info->extack; + unsigned int size, i, n, ulen = 0, usize = 0; + u8 genmask = nft_genmask_next(info->net); + struct nft_rule *rule, *old_rule = NULL; + struct nft_expr_info *expr_info = NULL; int family = nfmsg->nfgen_family; + struct net *net = info->net; struct nft_flow_rule *flow; + struct nft_userdata *udata; struct nft_table *table; struct nft_chain *chain; - struct nft_rule *rule, *old_rule = NULL; - struct nft_userdata *udata; - struct nft_trans *trans = NULL; + struct nft_trans *trans; + u64 handle, pos_handle; struct nft_expr *expr; struct nft_ctx ctx; struct nlattr *tmp; - unsigned int size, i, n, ulen = 0, usize = 0; int err, rem; - u64 handle, pos_handle; - lockdep_assert_held(&net->nft.commit_mutex); + lockdep_assert_held(&nft_net->commit_mutex); table = nft_table_lookup(net, nla[NFTA_RULE_TABLE], family, genmask, NETLINK_CB(skb).portid); @@ -3237,17 +3277,17 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk, return PTR_ERR(rule); } - if (nlh->nlmsg_flags & NLM_F_EXCL) { + if (info->nlh->nlmsg_flags & NLM_F_EXCL) { NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_HANDLE]); return -EEXIST; } - if (nlh->nlmsg_flags & NLM_F_REPLACE) + if (info->nlh->nlmsg_flags & NLM_F_REPLACE) old_rule = rule; else return -EOPNOTSUPP; } else { - if (!(nlh->nlmsg_flags & NLM_F_CREATE) || - nlh->nlmsg_flags & NLM_F_REPLACE) + if (!(info->nlh->nlmsg_flags & NLM_F_CREATE) || + info->nlh->nlmsg_flags & NLM_F_REPLACE) return -EINVAL; handle = nf_tables_alloc_handle(table); @@ -3270,15 +3310,15 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk, } } - nft_ctx_init(&ctx, net, skb, nlh, family, table, chain, nla); + nft_ctx_init(&ctx, net, skb, info->nlh, family, table, chain, nla); n = 0; size = 0; if (nla[NFTA_RULE_EXPRESSIONS]) { - info = kvmalloc_array(NFT_RULE_MAXEXPRS, - sizeof(struct nft_expr_info), - GFP_KERNEL); - if (!info) + expr_info = kvmalloc_array(NFT_RULE_MAXEXPRS, + sizeof(struct nft_expr_info), + GFP_KERNEL); + if (!expr_info) return -ENOMEM; nla_for_each_nested(tmp, nla[NFTA_RULE_EXPRESSIONS], rem) { @@ -3287,10 +3327,10 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk, goto err1; if (n == NFT_RULE_MAXEXPRS) goto err1; - err = nf_tables_expr_parse(&ctx, tmp, &info[n]); + err = nf_tables_expr_parse(&ctx, tmp, &expr_info[n]); if (err < 0) goto err1; - size += info[n].ops->size; + size += expr_info[n].ops->size; n++; } } @@ -3324,20 +3364,20 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk, expr = nft_expr_first(rule); for (i = 0; i < n; i++) { - err = nf_tables_newexpr(&ctx, &info[i], expr); + err = nf_tables_newexpr(&ctx, &expr_info[i], expr); if (err < 0) { - NL_SET_BAD_ATTR(extack, info[i].attr); + NL_SET_BAD_ATTR(extack, expr_info[i].attr); goto err2; } - if (info[i].ops->validate) + if (expr_info[i].ops->validate) nft_validate_state_update(net, NFT_VALIDATE_NEED); - info[i].ops = NULL; + expr_info[i].ops = NULL; expr = nft_expr_next(expr); } - if (nlh->nlmsg_flags & NLM_F_REPLACE) { + if (info->nlh->nlmsg_flags & NLM_F_REPLACE) { trans = nft_trans_rule_add(&ctx, NFT_MSG_NEWRULE, rule); if (trans == NULL) { err = -ENOMEM; @@ -3357,7 +3397,7 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk, goto err2; } - if (nlh->nlmsg_flags & NLM_F_APPEND) { + if (info->nlh->nlmsg_flags & NLM_F_APPEND) { if (old_rule) list_add_rcu(&rule->list, &old_rule->list); else @@ -3369,10 +3409,10 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk, list_add_rcu(&rule->list, &chain->rules); } } - kvfree(info); + kvfree(expr_info); chain->use++; - if (net->nft.validate_state == NFT_VALIDATE_DO) + if (nft_net->validate_state == NFT_VALIDATE_DO) return nft_table_validate(net, table); if (chain->flags & NFT_CHAIN_HW_OFFLOAD) { @@ -3388,23 +3428,25 @@ err2: nf_tables_rule_release(&ctx, rule); err1: for (i = 0; i < n; i++) { - if (info[i].ops) { - module_put(info[i].ops->type->owner); - if (info[i].ops->type->release_ops) - info[i].ops->type->release_ops(info[i].ops); + if (expr_info[i].ops) { + module_put(expr_info[i].ops->type->owner); + if (expr_info[i].ops->type->release_ops) + expr_info[i].ops->type->release_ops(expr_info[i].ops); } } - kvfree(info); + kvfree(expr_info); + return err; } static struct nft_rule *nft_rule_lookup_byid(const struct net *net, const struct nlattr *nla) { + struct nftables_pernet *nft_net = nft_pernet(net); u32 id = ntohl(nla_get_be32(nla)); struct nft_trans *trans; - list_for_each_entry(trans, &net->nft.commit_list, list) { + list_for_each_entry(trans, &nft_net->commit_list, list) { struct nft_rule *rule = nft_trans_rule(trans); if (trans->msg_type == NFT_MSG_NEWRULE && @@ -3414,17 +3456,17 @@ static struct nft_rule *nft_rule_lookup_byid(const struct net *net, return ERR_PTR(-ENOENT); } -static int nf_tables_delrule(struct net *net, struct sock *nlsk, - struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nla[], - struct netlink_ext_ack *extack) +static int nf_tables_delrule(struct sk_buff *skb, const struct nfnl_info *info, + const struct nlattr * const nla[]) { - const struct nfgenmsg *nfmsg = nlmsg_data(nlh); - u8 genmask = nft_genmask_next(net); - struct nft_table *table; + const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); + struct netlink_ext_ack *extack = info->extack; + int family = nfmsg->nfgen_family, err = 0; + u8 genmask = nft_genmask_next(info->net); struct nft_chain *chain = NULL; + struct net *net = info->net; + struct nft_table *table; struct nft_rule *rule; - int family = nfmsg->nfgen_family, err = 0; struct nft_ctx ctx; table = nft_table_lookup(net, nla[NFTA_RULE_TABLE], family, genmask, @@ -3445,7 +3487,7 @@ static int nf_tables_delrule(struct net *net, struct sock *nlsk, return -EOPNOTSUPP; } - nft_ctx_init(&ctx, net, skb, nlh, family, table, chain, nla); + nft_ctx_init(&ctx, net, skb, info->nlh, family, table, chain, nla); if (chain) { if (nla[NFTA_RULE_HANDLE]) { @@ -3517,13 +3559,14 @@ nft_select_set_ops(const struct nft_ctx *ctx, const struct nft_set_desc *desc, enum nft_set_policies policy) { + struct nftables_pernet *nft_net = nft_pernet(ctx->net); const struct nft_set_ops *ops, *bops; struct nft_set_estimate est, best; const struct nft_set_type *type; u32 flags = 0; int i; - lockdep_assert_held(&ctx->net->nft.commit_mutex); + lockdep_assert_held(&nft_net->commit_mutex); lockdep_nfnl_nft_mutex_not_held(); if (nla[NFTA_SET_FLAGS] != NULL) @@ -3661,10 +3704,11 @@ static struct nft_set *nft_set_lookup_byhandle(const struct nft_table *table, static struct nft_set *nft_set_lookup_byid(const struct net *net, const struct nlattr *nla, u8 genmask) { - struct nft_trans *trans; + struct nftables_pernet *nft_net = nft_pernet(net); u32 id = ntohl(nla_get_be32(nla)); + struct nft_trans *trans; - list_for_each_entry(trans, &net->nft.commit_list, list) { + list_for_each_entry(trans, &nft_net->commit_list, list) { if (trans->msg_type == NFT_MSG_NEWSET) { struct nft_set *set = nft_trans_set(trans); @@ -3799,7 +3843,6 @@ static int nf_tables_fill_set_concat(struct sk_buff *skb, static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx, const struct nft_set *set, u16 event, u16 flags) { - struct nfgenmsg *nfmsg; struct nlmsghdr *nlh; u32 portid = ctx->portid; struct nlattr *nest; @@ -3807,16 +3850,11 @@ static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx, int i; event = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event); - nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct nfgenmsg), - flags); - if (nlh == NULL) + nlh = nfnl_msg_put(skb, portid, seq, event, flags, ctx->family, + NFNETLINK_V0, nft_base_seq(ctx->net)); + if (!nlh) goto nla_put_failure; - nfmsg = nlmsg_data(nlh); - nfmsg->nfgen_family = ctx->family; - nfmsg->version = NFNETLINK_V0; - nfmsg->res_id = htons(ctx->net->nft.base_seq & 0xffff); - if (nla_put_string(skb, NFTA_SET_TABLE, ctx->table->name)) goto nla_put_failure; if (nla_put_string(skb, NFTA_SET_NAME, set->name)) @@ -3904,21 +3942,10 @@ static void nf_tables_set_notify(const struct nft_ctx *ctx, const struct nft_set *set, int event, gfp_t gfp_flags) { + struct nftables_pernet *nft_net = nft_pernet(ctx->net); struct sk_buff *skb; u32 portid = ctx->portid; int err; - char *buf = kasprintf(gfp_flags, "%s:%llu;%s:%llu", - ctx->table->name, ctx->table->handle, - set->name, set->handle); - - audit_log_nfcfg(buf, - ctx->family, - set->field_count, - event == NFT_MSG_NEWSET ? - AUDIT_NFT_OP_SET_REGISTER : - AUDIT_NFT_OP_SET_UNREGISTER, - gfp_flags); - kfree(buf); if (!ctx->report && !nfnetlink_has_listeners(ctx->net, NFNLGRP_NFTABLES)) @@ -3934,7 +3961,7 @@ static void nf_tables_set_notify(const struct nft_ctx *ctx, goto err; } - nft_notify_enqueue(skb, ctx->report, &ctx->net->nft.notify_list); + nft_notify_enqueue(skb, ctx->report, &nft_net->notify_list); return; err: nfnetlink_set_err(ctx->net, portid, NFNLGRP_NFTABLES, -ENOBUFS); @@ -3947,14 +3974,16 @@ static int nf_tables_dump_sets(struct sk_buff *skb, struct netlink_callback *cb) struct nft_table *table, *cur_table = (struct nft_table *)cb->args[2]; struct net *net = sock_net(skb->sk); struct nft_ctx *ctx = cb->data, ctx_set; + struct nftables_pernet *nft_net; if (cb->args[1]) return skb->len; rcu_read_lock(); - cb->seq = net->nft.base_seq; + nft_net = nft_pernet(net); + cb->seq = nft_net->base_seq; - list_for_each_entry_rcu(table, &net->nft.tables, list) { + list_for_each_entry_rcu(table, &nft_net->tables, list) { if (ctx->family != NFPROTO_UNSPEC && ctx->family != table->family) continue; @@ -4018,25 +4047,25 @@ static int nf_tables_dump_sets_done(struct netlink_callback *cb) } /* called with rcu_read_lock held */ -static int nf_tables_getset(struct net *net, struct sock *nlsk, - struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nla[], - struct netlink_ext_ack *extack) +static int nf_tables_getset(struct sk_buff *skb, const struct nfnl_info *info, + const struct nlattr * const nla[]) { - u8 genmask = nft_genmask_cur(net); + const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); + struct netlink_ext_ack *extack = info->extack; + u8 genmask = nft_genmask_cur(info->net); + struct net *net = info->net; const struct nft_set *set; - struct nft_ctx ctx; struct sk_buff *skb2; - const struct nfgenmsg *nfmsg = nlmsg_data(nlh); + struct nft_ctx ctx; int err; /* Verify existence before starting dump */ - err = nft_ctx_init_from_setattr(&ctx, net, skb, nlh, nla, extack, + err = nft_ctx_init_from_setattr(&ctx, net, skb, info->nlh, nla, extack, genmask, 0); if (err < 0) return err; - if (nlh->nlmsg_flags & NLM_F_DUMP) { + if (info->nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { .start = nf_tables_dump_sets_start, .dump = nf_tables_dump_sets, @@ -4045,7 +4074,7 @@ static int nf_tables_getset(struct net *net, struct sock *nlsk, .module = THIS_MODULE, }; - return nft_netlink_dump_start_rcu(nlsk, skb, nlh, &c); + return nft_netlink_dump_start_rcu(info->sk, skb, info->nlh, &c); } /* Only accept unspec with dump */ @@ -4139,28 +4168,27 @@ static int nf_tables_set_desc_parse(struct nft_set_desc *desc, return err; } -static int nf_tables_newset(struct net *net, struct sock *nlsk, - struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nla[], - struct netlink_ext_ack *extack) +static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info, + const struct nlattr * const nla[]) { - const struct nfgenmsg *nfmsg = nlmsg_data(nlh); - u8 genmask = nft_genmask_next(net); + const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); + u32 ktype, dtype, flags, policy, gc_int, objtype; + struct netlink_ext_ack *extack = info->extack; + u8 genmask = nft_genmask_next(info->net); int family = nfmsg->nfgen_family; const struct nft_set_ops *ops; struct nft_expr *expr = NULL; + struct net *net = info->net; + struct nft_set_desc desc; struct nft_table *table; + unsigned char *udata; struct nft_set *set; struct nft_ctx ctx; - char *name; - u64 size; u64 timeout; - u32 ktype, dtype, flags, policy, gc_int, objtype; - struct nft_set_desc desc; - unsigned char *udata; + char *name; + int err, i; u16 udlen; - int err; - int i; + u64 size; if (nla[NFTA_SET_TABLE] == NULL || nla[NFTA_SET_NAME] == NULL || @@ -4268,7 +4296,7 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk, return PTR_ERR(table); } - nft_ctx_init(&ctx, net, skb, nlh, family, table, NULL, nla); + nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla); set = nft_set_lookup(table, nla[NFTA_SET_NAME], genmask); if (IS_ERR(set)) { @@ -4277,17 +4305,17 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk, return PTR_ERR(set); } } else { - if (nlh->nlmsg_flags & NLM_F_EXCL) { + if (info->nlh->nlmsg_flags & NLM_F_EXCL) { NL_SET_BAD_ATTR(extack, nla[NFTA_SET_NAME]); return -EEXIST; } - if (nlh->nlmsg_flags & NLM_F_REPLACE) + if (info->nlh->nlmsg_flags & NLM_F_REPLACE) return -EOPNOTSUPP; return 0; } - if (!(nlh->nlmsg_flags & NLM_F_CREATE)) + if (!(info->nlh->nlmsg_flags & NLM_F_CREATE)) return -ENOENT; ops = nft_select_set_ops(&ctx, nla, &desc, policy); @@ -4361,6 +4389,7 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk, } INIT_LIST_HEAD(&set->bindings); + INIT_LIST_HEAD(&set->catchall_list); set->table = table; write_pnet(&set->net, net); set->ops = ops; @@ -4406,6 +4435,24 @@ err_set_name: return err; } +struct nft_set_elem_catchall { + struct list_head list; + struct rcu_head rcu; + void *elem; +}; + +static void nft_set_catchall_destroy(const struct nft_ctx *ctx, + struct nft_set *set) +{ + struct nft_set_elem_catchall *catchall; + + list_for_each_entry_rcu(catchall, &set->catchall_list, list) { + list_del_rcu(&catchall->list); + nft_set_elem_destroy(set, catchall->elem, true); + kfree_rcu(catchall); + } +} + static void nft_set_destroy(const struct nft_ctx *ctx, struct nft_set *set) { int i; @@ -4417,17 +4464,18 @@ static void nft_set_destroy(const struct nft_ctx *ctx, struct nft_set *set) nft_expr_destroy(ctx, set->exprs[i]); set->ops->destroy(set); + nft_set_catchall_destroy(ctx, set); kfree(set->name); kvfree(set); } -static int nf_tables_delset(struct net *net, struct sock *nlsk, - struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nla[], - struct netlink_ext_ack *extack) +static int nf_tables_delset(struct sk_buff *skb, const struct nfnl_info *info, + const struct nlattr * const nla[]) { - const struct nfgenmsg *nfmsg = nlmsg_data(nlh); - u8 genmask = nft_genmask_next(net); + const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); + struct netlink_ext_ack *extack = info->extack; + u8 genmask = nft_genmask_next(info->net); + struct net *net = info->net; const struct nlattr *attr; struct nft_set *set; struct nft_ctx ctx; @@ -4438,7 +4486,7 @@ static int nf_tables_delset(struct net *net, struct sock *nlsk, if (nla[NFTA_SET_TABLE] == NULL) return -EINVAL; - err = nft_ctx_init_from_setattr(&ctx, net, skb, nlh, nla, extack, + err = nft_ctx_init_from_setattr(&ctx, net, skb, info->nlh, nla, extack, genmask, NETLINK_CB(skb).portid); if (err < 0) return err; @@ -4456,7 +4504,8 @@ static int nf_tables_delset(struct net *net, struct sock *nlsk, return PTR_ERR(set); } if (set->use || - (nlh->nlmsg_flags & NLM_F_NONREC && atomic_read(&set->nelems) > 0)) { + (info->nlh->nlmsg_flags & NLM_F_NONREC && + atomic_read(&set->nelems) > 0)) { NL_SET_BAD_ATTR(extack, attr); return -EBUSY; } @@ -4470,10 +4519,9 @@ static int nft_validate_register_store(const struct nft_ctx *ctx, enum nft_data_types type, unsigned int len); -static int nf_tables_bind_check_setelem(const struct nft_ctx *ctx, - struct nft_set *set, - const struct nft_set_iter *iter, - struct nft_set_elem *elem) +static int nft_setelem_data_validate(const struct nft_ctx *ctx, + struct nft_set *set, + struct nft_set_elem *elem) { const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); enum nft_registers dreg; @@ -4485,6 +4533,37 @@ static int nf_tables_bind_check_setelem(const struct nft_ctx *ctx, set->dlen); } +static int nf_tables_bind_check_setelem(const struct nft_ctx *ctx, + struct nft_set *set, + const struct nft_set_iter *iter, + struct nft_set_elem *elem) +{ + return nft_setelem_data_validate(ctx, set, elem); +} + +static int nft_set_catchall_bind_check(const struct nft_ctx *ctx, + struct nft_set *set) +{ + u8 genmask = nft_genmask_next(ctx->net); + struct nft_set_elem_catchall *catchall; + struct nft_set_elem elem; + struct nft_set_ext *ext; + int ret = 0; + + list_for_each_entry_rcu(catchall, &set->catchall_list, list) { + ext = nft_set_elem_ext(set, catchall->elem); + if (!nft_set_elem_active(ext, genmask)) + continue; + + elem.priv = catchall->elem; + ret = nft_setelem_data_validate(ctx, set, &elem); + if (ret < 0) + break; + } + + return ret; +} + int nf_tables_bind_set(const struct nft_ctx *ctx, struct nft_set *set, struct nft_set_binding *binding) { @@ -4514,6 +4593,9 @@ int nf_tables_bind_set(const struct nft_ctx *ctx, struct nft_set *set, iter.fn = nf_tables_bind_check_setelem; set->ops->walk(ctx, set, &iter); + if (!iter.err) + iter.err = nft_set_catchall_bind_check(ctx, set); + if (iter.err < 0) return iter.err; } @@ -4700,7 +4782,8 @@ static int nf_tables_fill_setelem(struct sk_buff *skb, if (nest == NULL) goto nla_put_failure; - if (nft_data_dump(skb, NFTA_SET_ELEM_KEY, nft_set_ext_key(ext), + if (nft_set_ext_exists(ext, NFT_SET_EXT_KEY) && + nft_data_dump(skb, NFTA_SET_ELEM_KEY, nft_set_ext_key(ext), NFT_DATA_VALUE, set->klen) < 0) goto nla_put_failure; @@ -4789,22 +4872,46 @@ struct nft_set_dump_ctx { struct nft_ctx ctx; }; +static int nft_set_catchall_dump(struct net *net, struct sk_buff *skb, + const struct nft_set *set) +{ + struct nft_set_elem_catchall *catchall; + u8 genmask = nft_genmask_cur(net); + struct nft_set_elem elem; + struct nft_set_ext *ext; + int ret = 0; + + list_for_each_entry_rcu(catchall, &set->catchall_list, list) { + ext = nft_set_elem_ext(set, catchall->elem); + if (!nft_set_elem_active(ext, genmask) || + nft_set_elem_expired(ext)) + continue; + + elem.priv = catchall->elem; + ret = nf_tables_fill_setelem(skb, set, &elem); + break; + } + + return ret; +} + static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb) { struct nft_set_dump_ctx *dump_ctx = cb->data; struct net *net = sock_net(skb->sk); + struct nftables_pernet *nft_net; struct nft_table *table; struct nft_set *set; struct nft_set_dump_args args; bool set_found = false; - struct nfgenmsg *nfmsg; struct nlmsghdr *nlh; struct nlattr *nest; u32 portid, seq; int event; rcu_read_lock(); - list_for_each_entry_rcu(table, &net->nft.tables, list) { + nft_net = nft_pernet(net); + list_for_each_entry_rcu(table, &nft_net->tables, list) { if (dump_ctx->ctx.family != NFPROTO_UNSPEC && dump_ctx->ctx.family != table->family) continue; @@ -4830,16 +4937,11 @@ static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb) portid = NETLINK_CB(cb->skb).portid; seq = cb->nlh->nlmsg_seq; - nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct nfgenmsg), - NLM_F_MULTI); - if (nlh == NULL) + nlh = nfnl_msg_put(skb, portid, seq, event, NLM_F_MULTI, + table->family, NFNETLINK_V0, nft_base_seq(net)); + if (!nlh) goto nla_put_failure; - nfmsg = nlmsg_data(nlh); - nfmsg->nfgen_family = table->family; - nfmsg->version = NFNETLINK_V0; - nfmsg->res_id = htons(net->nft.base_seq & 0xffff); - if (nla_put_string(skb, NFTA_SET_ELEM_LIST_TABLE, table->name)) goto nla_put_failure; if (nla_put_string(skb, NFTA_SET_ELEM_LIST_SET, set->name)) @@ -4857,6 +4959,9 @@ static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb) args.iter.err = 0; args.iter.fn = nf_tables_dump_setelem; set->ops->walk(&dump_ctx->ctx, set, &args.iter); + + if (!args.iter.err && args.iter.count == cb->args[0]) + args.iter.err = nft_set_catchall_dump(net, skb, set); rcu_read_unlock(); nla_nest_end(skb, nest); @@ -4896,22 +5001,16 @@ static int nf_tables_fill_setelem_info(struct sk_buff *skb, const struct nft_set *set, const struct nft_set_elem *elem) { - struct nfgenmsg *nfmsg; struct nlmsghdr *nlh; struct nlattr *nest; int err; event = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event); - nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct nfgenmsg), - flags); - if (nlh == NULL) + nlh = nfnl_msg_put(skb, portid, seq, event, flags, ctx->family, + NFNETLINK_V0, nft_base_seq(ctx->net)); + if (!nlh) goto nla_put_failure; - nfmsg = nlmsg_data(nlh); - nfmsg->nfgen_family = ctx->family; - nfmsg->version = NFNETLINK_V0; - nfmsg->res_id = htons(ctx->net->nft.base_seq & 0xffff); - if (nla_put_string(skb, NFTA_SET_TABLE, ctx->table->name)) goto nla_put_failure; if (nla_put_string(skb, NFTA_SET_NAME, set->name)) @@ -4942,8 +5041,8 @@ static int nft_setelem_parse_flags(const struct nft_set *set, return 0; *flags = ntohl(nla_get_be32(attr)); - if (*flags & ~NFT_SET_ELEM_INTERVAL_END) - return -EINVAL; + if (*flags & ~(NFT_SET_ELEM_INTERVAL_END | NFT_SET_ELEM_CATCHALL)) + return -EOPNOTSUPP; if (!(set->flags & NFT_SET_INTERVAL) && *flags & NFT_SET_ELEM_INTERVAL_END) return -EINVAL; @@ -4988,6 +5087,46 @@ static int nft_setelem_parse_data(struct nft_ctx *ctx, struct nft_set *set, return 0; } +static void *nft_setelem_catchall_get(const struct net *net, + const struct nft_set *set) +{ + struct nft_set_elem_catchall *catchall; + u8 genmask = nft_genmask_cur(net); + struct nft_set_ext *ext; + void *priv = NULL; + + list_for_each_entry_rcu(catchall, &set->catchall_list, list) { + ext = nft_set_elem_ext(set, catchall->elem); + if (!nft_set_elem_active(ext, genmask) || + nft_set_elem_expired(ext)) + continue; + + priv = catchall->elem; + break; + } + + return priv; +} + +static int nft_setelem_get(struct nft_ctx *ctx, struct nft_set *set, + struct nft_set_elem *elem, u32 flags) +{ + void *priv; + + if (!(flags & NFT_SET_ELEM_CATCHALL)) { + priv = set->ops->get(ctx->net, set, elem, flags); + if (IS_ERR(priv)) + return PTR_ERR(priv); + } else { + priv = nft_setelem_catchall_get(ctx->net, set); + if (!priv) + return -ENOENT; + } + elem->priv = priv; + + return 0; +} + static int nft_get_set_elem(struct nft_ctx *ctx, struct nft_set *set, const struct nlattr *attr) { @@ -4995,7 +5134,6 @@ static int nft_get_set_elem(struct nft_ctx *ctx, struct nft_set *set, struct nft_set_elem elem; struct sk_buff *skb; uint32_t flags = 0; - void *priv; int err; err = nla_parse_nested_deprecated(nla, NFTA_SET_ELEM_MAX, attr, @@ -5003,17 +5141,19 @@ static int nft_get_set_elem(struct nft_ctx *ctx, struct nft_set *set, if (err < 0) return err; - if (!nla[NFTA_SET_ELEM_KEY]) - return -EINVAL; - err = nft_setelem_parse_flags(set, nla[NFTA_SET_ELEM_FLAGS], &flags); if (err < 0) return err; - err = nft_setelem_parse_key(ctx, set, &elem.key.val, - nla[NFTA_SET_ELEM_KEY]); - if (err < 0) - return err; + if (!nla[NFTA_SET_ELEM_KEY] && !(flags & NFT_SET_ELEM_CATCHALL)) + return -EINVAL; + + if (nla[NFTA_SET_ELEM_KEY]) { + err = nft_setelem_parse_key(ctx, set, &elem.key.val, + nla[NFTA_SET_ELEM_KEY]); + if (err < 0) + return err; + } if (nla[NFTA_SET_ELEM_KEY_END]) { err = nft_setelem_parse_key(ctx, set, &elem.key_end.val, @@ -5022,11 +5162,9 @@ static int nft_get_set_elem(struct nft_ctx *ctx, struct nft_set *set, return err; } - priv = set->ops->get(ctx->net, set, &elem, flags); - if (IS_ERR(priv)) - return PTR_ERR(priv); - - elem.priv = priv; + err = nft_setelem_get(ctx, set, &elem, flags); + if (err < 0) + return err; err = -ENOMEM; skb = nlmsg_new(NLMSG_GOODSIZE, GFP_ATOMIC); @@ -5046,18 +5184,19 @@ err_fill_setelem: } /* called with rcu_read_lock held */ -static int nf_tables_getsetelem(struct net *net, struct sock *nlsk, - struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nla[], - struct netlink_ext_ack *extack) +static int nf_tables_getsetelem(struct sk_buff *skb, + const struct nfnl_info *info, + const struct nlattr * const nla[]) { - u8 genmask = nft_genmask_cur(net); + struct netlink_ext_ack *extack = info->extack; + u8 genmask = nft_genmask_cur(info->net); + struct net *net = info->net; struct nft_set *set; struct nlattr *attr; struct nft_ctx ctx; int rem, err = 0; - err = nft_ctx_init_from_elemattr(&ctx, net, skb, nlh, nla, extack, + err = nft_ctx_init_from_elemattr(&ctx, net, skb, info->nlh, nla, extack, genmask, NETLINK_CB(skb).portid); if (err < 0) return err; @@ -5066,7 +5205,7 @@ static int nf_tables_getsetelem(struct net *net, struct sock *nlsk, if (IS_ERR(set)) return PTR_ERR(set); - if (nlh->nlmsg_flags & NLM_F_DUMP) { + if (info->nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { .start = nf_tables_dump_set_start, .dump = nf_tables_dump_set, @@ -5079,7 +5218,7 @@ static int nf_tables_getsetelem(struct net *net, struct sock *nlsk, }; c.data = &dump_ctx; - return nft_netlink_dump_start_rcu(nlsk, skb, nlh, &c); + return nft_netlink_dump_start_rcu(info->sk, skb, info->nlh, &c); } if (!nla[NFTA_SET_ELEM_LIST_ELEMENTS]) @@ -5099,22 +5238,11 @@ static void nf_tables_setelem_notify(const struct nft_ctx *ctx, const struct nft_set_elem *elem, int event, u16 flags) { + struct nftables_pernet *nft_net; struct net *net = ctx->net; u32 portid = ctx->portid; struct sk_buff *skb; int err; - char *buf = kasprintf(GFP_KERNEL, "%s:%llu;%s:%llu", - ctx->table->name, ctx->table->handle, - set->name, set->handle); - - audit_log_nfcfg(buf, - ctx->family, - set->handle, - event == NFT_MSG_NEWSETELEM ? - AUDIT_NFT_OP_SETELEM_REGISTER : - AUDIT_NFT_OP_SETELEM_UNREGISTER, - GFP_KERNEL); - kfree(buf); if (!ctx->report && !nfnetlink_has_listeners(net, NFNLGRP_NFTABLES)) return; @@ -5130,7 +5258,8 @@ static void nf_tables_setelem_notify(const struct nft_ctx *ctx, goto err; } - nft_notify_enqueue(skb, ctx->report, &ctx->net->nft.notify_list); + nft_net = nft_pernet(net); + nft_notify_enqueue(skb, ctx->report, &nft_net->notify_list); return; err: nfnetlink_set_err(net, portid, NFNLGRP_NFTABLES, -ENOBUFS); @@ -5195,7 +5324,8 @@ void *nft_set_elem_init(const struct nft_set *set, ext = nft_set_elem_ext(set, elem); nft_set_ext_init(ext, tmpl); - memcpy(nft_set_ext_key(ext), key, set->klen); + if (nft_set_ext_exists(ext, NFT_SET_EXT_KEY)) + memcpy(nft_set_ext_key(ext), key, set->klen); if (nft_set_ext_exists(ext, NFT_SET_EXT_KEY_END)) memcpy(nft_set_ext_key_end(ext), key_end, set->klen); if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA)) @@ -5253,8 +5383,8 @@ void nft_set_elem_destroy(const struct nft_set *set, void *elem, } EXPORT_SYMBOL_GPL(nft_set_elem_destroy); -/* Only called from commit path, nft_set_elem_deactivate() already deals with - * the refcounting from the preparation phase. +/* Only called from commit path, nft_setelem_data_deactivate() already deals + * with the refcounting from the preparation phase. */ static void nf_tables_set_elem_destroy(const struct nft_ctx *ctx, const struct nft_set *set, void *elem) @@ -5326,6 +5456,192 @@ err_elem_expr_setup: return -ENOMEM; } +struct nft_set_ext *nft_set_catchall_lookup(const struct net *net, + const struct nft_set *set) +{ + struct nft_set_elem_catchall *catchall; + u8 genmask = nft_genmask_cur(net); + struct nft_set_ext *ext; + + list_for_each_entry_rcu(catchall, &set->catchall_list, list) { + ext = nft_set_elem_ext(set, catchall->elem); + if (nft_set_elem_active(ext, genmask) && + !nft_set_elem_expired(ext)) + return ext; + } + + return NULL; +} +EXPORT_SYMBOL_GPL(nft_set_catchall_lookup); + +void *nft_set_catchall_gc(const struct nft_set *set) +{ + struct nft_set_elem_catchall *catchall, *next; + struct nft_set_ext *ext; + void *elem = NULL; + + list_for_each_entry_safe(catchall, next, &set->catchall_list, list) { + ext = nft_set_elem_ext(set, catchall->elem); + + if (!nft_set_elem_expired(ext) || + nft_set_elem_mark_busy(ext)) + continue; + + elem = catchall->elem; + list_del_rcu(&catchall->list); + kfree_rcu(catchall, rcu); + break; + } + + return elem; +} +EXPORT_SYMBOL_GPL(nft_set_catchall_gc); + +static int nft_setelem_catchall_insert(const struct net *net, + struct nft_set *set, + const struct nft_set_elem *elem, + struct nft_set_ext **pext) +{ + struct nft_set_elem_catchall *catchall; + u8 genmask = nft_genmask_next(net); + struct nft_set_ext *ext; + + list_for_each_entry(catchall, &set->catchall_list, list) { + ext = nft_set_elem_ext(set, catchall->elem); + if (nft_set_elem_active(ext, genmask)) { + *pext = ext; + return -EEXIST; + } + } + + catchall = kmalloc(sizeof(*catchall), GFP_KERNEL); + if (!catchall) + return -ENOMEM; + + catchall->elem = elem->priv; + list_add_tail_rcu(&catchall->list, &set->catchall_list); + + return 0; +} + +static int nft_setelem_insert(const struct net *net, + struct nft_set *set, + const struct nft_set_elem *elem, + struct nft_set_ext **ext, unsigned int flags) +{ + int ret; + + if (flags & NFT_SET_ELEM_CATCHALL) + ret = nft_setelem_catchall_insert(net, set, elem, ext); + else + ret = set->ops->insert(net, set, elem, ext); + + return ret; +} + +static bool nft_setelem_is_catchall(const struct nft_set *set, + const struct nft_set_elem *elem) +{ + struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); + + if (nft_set_ext_exists(ext, NFT_SET_EXT_FLAGS) && + *nft_set_ext_flags(ext) & NFT_SET_ELEM_CATCHALL) + return true; + + return false; +} + +static void nft_setelem_activate(struct net *net, struct nft_set *set, + struct nft_set_elem *elem) +{ + struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); + + if (nft_setelem_is_catchall(set, elem)) { + nft_set_elem_change_active(net, set, ext); + nft_set_elem_clear_busy(ext); + } else { + set->ops->activate(net, set, elem); + } +} + +static int nft_setelem_catchall_deactivate(const struct net *net, + struct nft_set *set, + struct nft_set_elem *elem) +{ + struct nft_set_elem_catchall *catchall; + struct nft_set_ext *ext; + + list_for_each_entry(catchall, &set->catchall_list, list) { + ext = nft_set_elem_ext(set, catchall->elem); + if (!nft_is_active(net, ext) || + nft_set_elem_mark_busy(ext)) + continue; + + kfree(elem->priv); + elem->priv = catchall->elem; + nft_set_elem_change_active(net, set, ext); + return 0; + } + + return -ENOENT; +} + +static int __nft_setelem_deactivate(const struct net *net, + struct nft_set *set, + struct nft_set_elem *elem) +{ + void *priv; + + priv = set->ops->deactivate(net, set, elem); + if (!priv) + return -ENOENT; + + kfree(elem->priv); + elem->priv = priv; + set->ndeact++; + + return 0; +} + +static int nft_setelem_deactivate(const struct net *net, + struct nft_set *set, + struct nft_set_elem *elem, u32 flags) +{ + int ret; + + if (flags & NFT_SET_ELEM_CATCHALL) + ret = nft_setelem_catchall_deactivate(net, set, elem); + else + ret = __nft_setelem_deactivate(net, set, elem); + + return ret; +} + +static void nft_setelem_catchall_remove(const struct net *net, + const struct nft_set *set, + const struct nft_set_elem *elem) +{ + struct nft_set_elem_catchall *catchall, *next; + + list_for_each_entry_safe(catchall, next, &set->catchall_list, list) { + if (catchall->elem == elem->priv) { + list_del_rcu(&catchall->list); + kfree_rcu(catchall); + break; + } + } +} + +static void nft_setelem_remove(const struct net *net, + const struct nft_set *set, + const struct nft_set_elem *elem) +{ + if (nft_setelem_is_catchall(set, elem)) + nft_setelem_catchall_remove(net, set, elem); + else + set->ops->remove(net, set, elem); +} + static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, const struct nlattr *attr, u32 nlmsg_flags) { @@ -5352,14 +5668,15 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, if (err < 0) return err; - if (nla[NFTA_SET_ELEM_KEY] == NULL) - return -EINVAL; - nft_set_ext_prepare(&tmpl); err = nft_setelem_parse_flags(set, nla[NFTA_SET_ELEM_FLAGS], &flags); if (err < 0) return err; + + if (!nla[NFTA_SET_ELEM_KEY] && !(flags & NFT_SET_ELEM_CATCHALL)) + return -EINVAL; + if (flags != 0) nft_set_ext_add(&tmpl, NFT_SET_EXT_FLAGS); @@ -5464,12 +5781,14 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, num_exprs = set->num_exprs; } - err = nft_setelem_parse_key(ctx, set, &elem.key.val, - nla[NFTA_SET_ELEM_KEY]); - if (err < 0) - goto err_set_elem_expr; + if (nla[NFTA_SET_ELEM_KEY]) { + err = nft_setelem_parse_key(ctx, set, &elem.key.val, + nla[NFTA_SET_ELEM_KEY]); + if (err < 0) + goto err_set_elem_expr; - nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY, set->klen); + nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY, set->klen); + } if (nla[NFTA_SET_ELEM_KEY_END]) { err = nft_setelem_parse_key(ctx, set, &elem.key_end.val, @@ -5586,7 +5905,8 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, } ext->genmask = nft_genmask_cur(ctx->net) | NFT_SET_ELEM_BUSY_MASK; - err = set->ops->insert(ctx->net, set, &elem, &ext2); + + err = nft_setelem_insert(ctx->net, set, &elem, &ext2, flags); if (err) { if (err == -EEXIST) { if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA) ^ @@ -5613,18 +5933,18 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, goto err_element_clash; } - if (set->size && + if (!(flags & NFT_SET_ELEM_CATCHALL) && set->size && !atomic_add_unless(&set->nelems, 1, set->size + set->ndeact)) { err = -ENFILE; goto err_set_full; } nft_trans_elem(trans) = elem; - list_add_tail(&trans->list, &ctx->net->nft.commit_list); + nft_trans_commit_list_add_tail(ctx->net, trans); return 0; err_set_full: - set->ops->remove(ctx->net, set, &elem); + nft_setelem_remove(ctx->net, set, &elem); err_element_clash: kfree(trans); err_elem_expr: @@ -5646,12 +5966,14 @@ err_set_elem_expr_clone: return err; } -static int nf_tables_newsetelem(struct net *net, struct sock *nlsk, - struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nla[], - struct netlink_ext_ack *extack) +static int nf_tables_newsetelem(struct sk_buff *skb, + const struct nfnl_info *info, + const struct nlattr * const nla[]) { - u8 genmask = nft_genmask_next(net); + struct nftables_pernet *nft_net = nft_pernet(info->net); + struct netlink_ext_ack *extack = info->extack; + u8 genmask = nft_genmask_next(info->net); + struct net *net = info->net; const struct nlattr *attr; struct nft_set *set; struct nft_ctx ctx; @@ -5660,7 +5982,7 @@ static int nf_tables_newsetelem(struct net *net, struct sock *nlsk, if (nla[NFTA_SET_ELEM_LIST_ELEMENTS] == NULL) return -EINVAL; - err = nft_ctx_init_from_elemattr(&ctx, net, skb, nlh, nla, extack, + err = nft_ctx_init_from_elemattr(&ctx, net, skb, info->nlh, nla, extack, genmask, NETLINK_CB(skb).portid); if (err < 0) return err; @@ -5674,12 +5996,12 @@ static int nf_tables_newsetelem(struct net *net, struct sock *nlsk, return -EBUSY; nla_for_each_nested(attr, nla[NFTA_SET_ELEM_LIST_ELEMENTS], rem) { - err = nft_add_set_elem(&ctx, set, attr, nlh->nlmsg_flags); + err = nft_add_set_elem(&ctx, set, attr, info->nlh->nlmsg_flags); if (err < 0) return err; } - if (net->nft.validate_state == NFT_VALIDATE_DO) + if (nft_net->validate_state == NFT_VALIDATE_DO) return nft_table_validate(net, ctx.table); return 0; @@ -5721,9 +6043,9 @@ void nft_data_hold(const struct nft_data *data, enum nft_data_types type) } } -static void nft_set_elem_activate(const struct net *net, - const struct nft_set *set, - struct nft_set_elem *elem) +static void nft_setelem_data_activate(const struct net *net, + const struct nft_set *set, + struct nft_set_elem *elem) { const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); @@ -5733,9 +6055,9 @@ static void nft_set_elem_activate(const struct net *net, (*nft_set_ext_obj(ext))->use++; } -static void nft_set_elem_deactivate(const struct net *net, - const struct nft_set *set, - struct nft_set_elem *elem) +static void nft_setelem_data_deactivate(const struct net *net, + const struct nft_set *set, + struct nft_set_elem *elem) { const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); @@ -5754,7 +6076,6 @@ static int nft_del_setelem(struct nft_ctx *ctx, struct nft_set *set, struct nft_set_ext *ext; struct nft_trans *trans; u32 flags = 0; - void *priv; int err; err = nla_parse_nested_deprecated(nla, NFTA_SET_ELEM_MAX, attr, @@ -5762,23 +6083,26 @@ static int nft_del_setelem(struct nft_ctx *ctx, struct nft_set *set, if (err < 0) return err; - if (nla[NFTA_SET_ELEM_KEY] == NULL) + err = nft_setelem_parse_flags(set, nla[NFTA_SET_ELEM_FLAGS], &flags); + if (err < 0) + return err; + + if (!nla[NFTA_SET_ELEM_KEY] && !(flags & NFT_SET_ELEM_CATCHALL)) return -EINVAL; nft_set_ext_prepare(&tmpl); - err = nft_setelem_parse_flags(set, nla[NFTA_SET_ELEM_FLAGS], &flags); - if (err < 0) - return err; if (flags != 0) nft_set_ext_add(&tmpl, NFT_SET_EXT_FLAGS); - err = nft_setelem_parse_key(ctx, set, &elem.key.val, - nla[NFTA_SET_ELEM_KEY]); - if (err < 0) - return err; + if (nla[NFTA_SET_ELEM_KEY]) { + err = nft_setelem_parse_key(ctx, set, &elem.key.val, + nla[NFTA_SET_ELEM_KEY]); + if (err < 0) + return err; - nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY, set->klen); + nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY, set->klen); + } if (nla[NFTA_SET_ELEM_KEY_END]) { err = nft_setelem_parse_key(ctx, set, &elem.key_end.val, @@ -5804,18 +6128,14 @@ static int nft_del_setelem(struct nft_ctx *ctx, struct nft_set *set, if (trans == NULL) goto fail_trans; - priv = set->ops->deactivate(ctx->net, set, &elem); - if (priv == NULL) { - err = -ENOENT; + err = nft_setelem_deactivate(ctx->net, set, &elem, flags); + if (err < 0) goto fail_ops; - } - kfree(elem.priv); - elem.priv = priv; - nft_set_elem_deactivate(ctx->net, set, &elem); + nft_setelem_data_deactivate(ctx->net, set, &elem); nft_trans_elem(trans) = elem; - list_add_tail(&trans->list, &ctx->net->nft.commit_list); + nft_trans_commit_list_add_tail(ctx->net, trans); return 0; fail_ops: @@ -5827,10 +6147,10 @@ fail_elem: return err; } -static int nft_flush_set(const struct nft_ctx *ctx, - struct nft_set *set, - const struct nft_set_iter *iter, - struct nft_set_elem *elem) +static int nft_setelem_flush(const struct nft_ctx *ctx, + struct nft_set *set, + const struct nft_set_iter *iter, + struct nft_set_elem *elem) { struct nft_trans *trans; int err; @@ -5846,10 +6166,10 @@ static int nft_flush_set(const struct nft_ctx *ctx, } set->ndeact++; - nft_set_elem_deactivate(ctx->net, set, elem); + nft_setelem_data_deactivate(ctx->net, set, elem); nft_trans_elem_set(trans) = set; nft_trans_elem(trans) = *elem; - list_add_tail(&trans->list, &ctx->net->nft.commit_list); + nft_trans_commit_list_add_tail(ctx->net, trans); return 0; err1: @@ -5857,18 +6177,76 @@ err1: return err; } -static int nf_tables_delsetelem(struct net *net, struct sock *nlsk, - struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nla[], - struct netlink_ext_ack *extack) +static int __nft_set_catchall_flush(const struct nft_ctx *ctx, + struct nft_set *set, + struct nft_set_elem *elem) { - u8 genmask = nft_genmask_next(net); + struct nft_trans *trans; + + trans = nft_trans_alloc_gfp(ctx, NFT_MSG_DELSETELEM, + sizeof(struct nft_trans_elem), GFP_KERNEL); + if (!trans) + return -ENOMEM; + + nft_setelem_data_deactivate(ctx->net, set, elem); + nft_trans_elem_set(trans) = set; + nft_trans_elem(trans) = *elem; + nft_trans_commit_list_add_tail(ctx->net, trans); + + return 0; +} + +static int nft_set_catchall_flush(const struct nft_ctx *ctx, + struct nft_set *set) +{ + u8 genmask = nft_genmask_next(ctx->net); + struct nft_set_elem_catchall *catchall; + struct nft_set_elem elem; + struct nft_set_ext *ext; + int ret = 0; + + list_for_each_entry_rcu(catchall, &set->catchall_list, list) { + ext = nft_set_elem_ext(set, catchall->elem); + if (!nft_set_elem_active(ext, genmask) || + nft_set_elem_mark_busy(ext)) + continue; + + elem.priv = catchall->elem; + ret = __nft_set_catchall_flush(ctx, set, &elem); + if (ret < 0) + break; + } + + return ret; +} + +static int nft_set_flush(struct nft_ctx *ctx, struct nft_set *set, u8 genmask) +{ + struct nft_set_iter iter = { + .genmask = genmask, + .fn = nft_setelem_flush, + }; + + set->ops->walk(ctx, set, &iter); + if (!iter.err) + iter.err = nft_set_catchall_flush(ctx, set); + + return iter.err; +} + +static int nf_tables_delsetelem(struct sk_buff *skb, + const struct nfnl_info *info, + const struct nlattr * const nla[]) +{ + struct netlink_ext_ack *extack = info->extack; + u8 genmask = nft_genmask_next(info->net); + struct net *net = info->net; const struct nlattr *attr; struct nft_set *set; struct nft_ctx ctx; int rem, err = 0; - err = nft_ctx_init_from_elemattr(&ctx, net, skb, nlh, nla, extack, + err = nft_ctx_init_from_elemattr(&ctx, net, skb, info->nlh, nla, extack, genmask, NETLINK_CB(skb).portid); if (err < 0) return err; @@ -5879,22 +6257,13 @@ static int nf_tables_delsetelem(struct net *net, struct sock *nlsk, if (!list_empty(&set->bindings) && set->flags & NFT_SET_CONSTANT) return -EBUSY; - if (nla[NFTA_SET_ELEM_LIST_ELEMENTS] == NULL) { - struct nft_set_iter iter = { - .genmask = genmask, - .fn = nft_flush_set, - }; - set->ops->walk(&ctx, set, &iter); - - return iter.err; - } + if (!nla[NFTA_SET_ELEM_LIST_ELEMENTS]) + return nft_set_flush(&ctx, set, genmask); nla_for_each_nested(attr, nla[NFTA_SET_ELEM_LIST_ELEMENTS], rem) { err = nft_del_setelem(&ctx, set, attr); if (err < 0) break; - - set->ndeact++; } return err; } @@ -6143,7 +6512,7 @@ static int nf_tables_updobj(const struct nft_ctx *ctx, nft_trans_obj(trans) = obj; nft_trans_obj_update(trans) = true; nft_trans_obj_newobj(trans) = newobj; - list_add_tail(&trans->list, &ctx->net->nft.commit_list); + nft_trans_commit_list_add_tail(ctx->net, trans); return 0; @@ -6152,15 +6521,15 @@ err_free_trans: return err; } -static int nf_tables_newobj(struct net *net, struct sock *nlsk, - struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nla[], - struct netlink_ext_ack *extack) +static int nf_tables_newobj(struct sk_buff *skb, const struct nfnl_info *info, + const struct nlattr * const nla[]) { - const struct nfgenmsg *nfmsg = nlmsg_data(nlh); + const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); + struct netlink_ext_ack *extack = info->extack; + u8 genmask = nft_genmask_next(info->net); const struct nft_object_type *type; - u8 genmask = nft_genmask_next(net); int family = nfmsg->nfgen_family; + struct net *net = info->net; struct nft_table *table; struct nft_object *obj; struct nft_ctx ctx; @@ -6188,20 +6557,20 @@ static int nf_tables_newobj(struct net *net, struct sock *nlsk, return err; } } else { - if (nlh->nlmsg_flags & NLM_F_EXCL) { + if (info->nlh->nlmsg_flags & NLM_F_EXCL) { NL_SET_BAD_ATTR(extack, nla[NFTA_OBJ_NAME]); return -EEXIST; } - if (nlh->nlmsg_flags & NLM_F_REPLACE) + if (info->nlh->nlmsg_flags & NLM_F_REPLACE) return -EOPNOTSUPP; type = __nft_obj_type_get(objtype); - nft_ctx_init(&ctx, net, skb, nlh, family, table, NULL, nla); + nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla); return nf_tables_updobj(&ctx, type, nla[NFTA_OBJ_DATA], obj); } - nft_ctx_init(&ctx, net, skb, nlh, family, table, NULL, nla); + nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla); type = nft_obj_type_get(net, objtype); if (IS_ERR(type)) @@ -6263,19 +6632,14 @@ static int nf_tables_fill_obj_info(struct sk_buff *skb, struct net *net, int family, const struct nft_table *table, struct nft_object *obj, bool reset) { - struct nfgenmsg *nfmsg; struct nlmsghdr *nlh; event = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event); - nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct nfgenmsg), flags); - if (nlh == NULL) + nlh = nfnl_msg_put(skb, portid, seq, event, flags, family, + NFNETLINK_V0, nft_base_seq(net)); + if (!nlh) goto nla_put_failure; - nfmsg = nlmsg_data(nlh); - nfmsg->nfgen_family = family; - nfmsg->version = NFNETLINK_V0; - nfmsg->res_id = htons(net->nft.base_seq & 0xffff); - if (nla_put_string(skb, NFTA_OBJ_TABLE, table->name) || nla_put_string(skb, NFTA_OBJ_NAME, obj->key.name) || nla_put_be32(skb, NFTA_OBJ_TYPE, htonl(obj->ops->type->type)) || @@ -6310,6 +6674,7 @@ static int nf_tables_dump_obj(struct sk_buff *skb, struct netlink_callback *cb) struct nft_obj_filter *filter = cb->data; struct net *net = sock_net(skb->sk); int family = nfmsg->nfgen_family; + struct nftables_pernet *nft_net; struct nft_object *obj; bool reset = false; @@ -6317,9 +6682,10 @@ static int nf_tables_dump_obj(struct sk_buff *skb, struct netlink_callback *cb) reset = true; rcu_read_lock(); - cb->seq = net->nft.base_seq; + nft_net = nft_pernet(net); + cb->seq = nft_net->base_seq; - list_for_each_entry_rcu(table, &net->nft.tables, list) { + list_for_each_entry_rcu(table, &nft_net->tables, list) { if (family != NFPROTO_UNSPEC && family != table->family) continue; @@ -6338,12 +6704,11 @@ static int nf_tables_dump_obj(struct sk_buff *skb, struct netlink_callback *cb) filter->type != NFT_OBJECT_UNSPEC && obj->ops->type->type != filter->type) goto cont; - if (reset) { char *buf = kasprintf(GFP_ATOMIC, - "%s:%llu;?:0", + "%s:%u", table->name, - table->handle); + nft_net->base_seq); audit_log_nfcfg(buf, family, @@ -6412,22 +6777,22 @@ static int nf_tables_dump_obj_done(struct netlink_callback *cb) } /* called with rcu_read_lock held */ -static int nf_tables_getobj(struct net *net, struct sock *nlsk, - struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nla[], - struct netlink_ext_ack *extack) +static int nf_tables_getobj(struct sk_buff *skb, const struct nfnl_info *info, + const struct nlattr * const nla[]) { - const struct nfgenmsg *nfmsg = nlmsg_data(nlh); - u8 genmask = nft_genmask_cur(net); + const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); + struct netlink_ext_ack *extack = info->extack; + u8 genmask = nft_genmask_cur(info->net); int family = nfmsg->nfgen_family; const struct nft_table *table; + struct net *net = info->net; struct nft_object *obj; struct sk_buff *skb2; bool reset = false; u32 objtype; int err; - if (nlh->nlmsg_flags & NLM_F_DUMP) { + if (info->nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { .start = nf_tables_dump_obj_start, .dump = nf_tables_dump_obj, @@ -6436,7 +6801,7 @@ static int nf_tables_getobj(struct net *net, struct sock *nlsk, .data = (void *)nla, }; - return nft_netlink_dump_start_rcu(nlsk, skb, nlh, &c); + return nft_netlink_dump_start_rcu(info->sk, skb, info->nlh, &c); } if (!nla[NFTA_OBJ_NAME] || @@ -6460,12 +6825,15 @@ static int nf_tables_getobj(struct net *net, struct sock *nlsk, if (!skb2) return -ENOMEM; - if (NFNL_MSG_TYPE(nlh->nlmsg_type) == NFT_MSG_GETOBJ_RESET) + if (NFNL_MSG_TYPE(info->nlh->nlmsg_type) == NFT_MSG_GETOBJ_RESET) reset = true; if (reset) { - char *buf = kasprintf(GFP_ATOMIC, "%s:%llu;?:0", - table->name, table->handle); + const struct nftables_pernet *nft_net; + char *buf; + + nft_net = nft_pernet(net); + buf = kasprintf(GFP_ATOMIC, "%s:%u", table->name, nft_net->base_seq); audit_log_nfcfg(buf, family, @@ -6476,7 +6844,7 @@ static int nf_tables_getobj(struct net *net, struct sock *nlsk, } err = nf_tables_fill_obj_info(skb2, net, NETLINK_CB(skb).portid, - nlh->nlmsg_seq, NFT_MSG_NEWOBJ, 0, + info->nlh->nlmsg_seq, NFT_MSG_NEWOBJ, 0, family, table, obj, reset); if (err < 0) goto err_fill_obj_info; @@ -6499,14 +6867,14 @@ static void nft_obj_destroy(const struct nft_ctx *ctx, struct nft_object *obj) kfree(obj); } -static int nf_tables_delobj(struct net *net, struct sock *nlsk, - struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nla[], - struct netlink_ext_ack *extack) +static int nf_tables_delobj(struct sk_buff *skb, const struct nfnl_info *info, + const struct nlattr * const nla[]) { - const struct nfgenmsg *nfmsg = nlmsg_data(nlh); - u8 genmask = nft_genmask_next(net); + const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); + struct netlink_ext_ack *extack = info->extack; + u8 genmask = nft_genmask_next(info->net); int family = nfmsg->nfgen_family; + struct net *net = info->net; const struct nlattr *attr; struct nft_table *table; struct nft_object *obj; @@ -6542,7 +6910,7 @@ static int nf_tables_delobj(struct net *net, struct sock *nlsk, return -EBUSY; } - nft_ctx_init(&ctx, net, skb, nlh, family, table, NULL, nla); + nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla); return nft_delobj(&ctx, obj); } @@ -6551,17 +6919,18 @@ void nft_obj_notify(struct net *net, const struct nft_table *table, struct nft_object *obj, u32 portid, u32 seq, int event, int family, int report, gfp_t gfp) { + struct nftables_pernet *nft_net = nft_pernet(net); struct sk_buff *skb; int err; - char *buf = kasprintf(gfp, "%s:%llu;?:0", - table->name, table->handle); + char *buf = kasprintf(gfp, "%s:%u", + table->name, nft_net->base_seq); audit_log_nfcfg(buf, family, obj->handle, event == NFT_MSG_NEWOBJ ? - AUDIT_NFT_OP_OBJ_REGISTER : - AUDIT_NFT_OP_OBJ_UNREGISTER, + AUDIT_NFT_OP_OBJ_REGISTER : + AUDIT_NFT_OP_OBJ_UNREGISTER, gfp); kfree(buf); @@ -6580,7 +6949,7 @@ void nft_obj_notify(struct net *net, const struct nft_table *table, goto err; } - nft_notify_enqueue(skb, report, &net->nft.notify_list); + nft_notify_enqueue(skb, report, &nft_net->notify_list); return; err: nfnetlink_set_err(net, portid, NFNLGRP_NFTABLES, -ENOBUFS); @@ -6912,7 +7281,7 @@ static int nft_flowtable_update(struct nft_ctx *ctx, const struct nlmsghdr *nlh, INIT_LIST_HEAD(&nft_trans_flowtable_hooks(trans)); list_splice(&flowtable_hook.list, &nft_trans_flowtable_hooks(trans)); - list_add_tail(&trans->list, &ctx->net->nft.commit_list); + nft_trans_commit_list_add_tail(ctx->net, trans); return 0; @@ -6928,19 +7297,19 @@ err_flowtable_update_hook: } -static int nf_tables_newflowtable(struct net *net, struct sock *nlsk, - struct sk_buff *skb, - const struct nlmsghdr *nlh, - const struct nlattr * const nla[], - struct netlink_ext_ack *extack) +static int nf_tables_newflowtable(struct sk_buff *skb, + const struct nfnl_info *info, + const struct nlattr * const nla[]) { - const struct nfgenmsg *nfmsg = nlmsg_data(nlh); + const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); + struct netlink_ext_ack *extack = info->extack; struct nft_flowtable_hook flowtable_hook; + u8 genmask = nft_genmask_next(info->net); const struct nf_flowtable_type *type; - u8 genmask = nft_genmask_next(net); int family = nfmsg->nfgen_family; struct nft_flowtable *flowtable; struct nft_hook *hook, *next; + struct net *net = info->net; struct nft_table *table; struct nft_ctx ctx; int err; @@ -6966,17 +7335,17 @@ static int nf_tables_newflowtable(struct net *net, struct sock *nlsk, return err; } } else { - if (nlh->nlmsg_flags & NLM_F_EXCL) { + if (info->nlh->nlmsg_flags & NLM_F_EXCL) { NL_SET_BAD_ATTR(extack, nla[NFTA_FLOWTABLE_NAME]); return -EEXIST; } - nft_ctx_init(&ctx, net, skb, nlh, family, table, NULL, nla); + nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla); - return nft_flowtable_update(&ctx, nlh, flowtable); + return nft_flowtable_update(&ctx, info->nlh, flowtable); } - nft_ctx_init(&ctx, net, skb, nlh, family, table, NULL, nla); + nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla); flowtable = kzalloc(sizeof(*flowtable), GFP_KERNEL); if (!flowtable) @@ -7100,7 +7469,7 @@ static int nft_delflowtable_hook(struct nft_ctx *ctx, INIT_LIST_HEAD(&nft_trans_flowtable_hooks(trans)); nft_flowtable_hook_release(&flowtable_hook); - list_add_tail(&trans->list, &ctx->net->nft.commit_list); + nft_trans_commit_list_add_tail(ctx->net, trans); return 0; @@ -7117,16 +7486,16 @@ err_flowtable_del_hook: return err; } -static int nf_tables_delflowtable(struct net *net, struct sock *nlsk, - struct sk_buff *skb, - const struct nlmsghdr *nlh, - const struct nlattr * const nla[], - struct netlink_ext_ack *extack) +static int nf_tables_delflowtable(struct sk_buff *skb, + const struct nfnl_info *info, + const struct nlattr * const nla[]) { - const struct nfgenmsg *nfmsg = nlmsg_data(nlh); - u8 genmask = nft_genmask_next(net); + const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); + struct netlink_ext_ack *extack = info->extack; + u8 genmask = nft_genmask_next(info->net); int family = nfmsg->nfgen_family; struct nft_flowtable *flowtable; + struct net *net = info->net; const struct nlattr *attr; struct nft_table *table; struct nft_ctx ctx; @@ -7156,7 +7525,7 @@ static int nf_tables_delflowtable(struct net *net, struct sock *nlsk, return PTR_ERR(flowtable); } - nft_ctx_init(&ctx, net, skb, nlh, family, table, NULL, nla); + nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla); if (nla[NFTA_FLOWTABLE_HOOK]) return nft_delflowtable_hook(&ctx, flowtable); @@ -7176,20 +7545,15 @@ static int nf_tables_fill_flowtable_info(struct sk_buff *skb, struct net *net, struct list_head *hook_list) { struct nlattr *nest, *nest_devs; - struct nfgenmsg *nfmsg; struct nft_hook *hook; struct nlmsghdr *nlh; event = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event); - nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct nfgenmsg), flags); - if (nlh == NULL) + nlh = nfnl_msg_put(skb, portid, seq, event, flags, family, + NFNETLINK_V0, nft_base_seq(net)); + if (!nlh) goto nla_put_failure; - nfmsg = nlmsg_data(nlh); - nfmsg->nfgen_family = family; - nfmsg->version = NFNETLINK_V0; - nfmsg->res_id = htons(net->nft.base_seq & 0xffff); - if (nla_put_string(skb, NFTA_FLOWTABLE_TABLE, flowtable->table->name) || nla_put_string(skb, NFTA_FLOWTABLE_NAME, flowtable->name) || nla_put_be32(skb, NFTA_FLOWTABLE_USE, htonl(flowtable->use)) || @@ -7237,12 +7601,14 @@ static int nf_tables_dump_flowtable(struct sk_buff *skb, struct net *net = sock_net(skb->sk); int family = nfmsg->nfgen_family; struct nft_flowtable *flowtable; + struct nftables_pernet *nft_net; const struct nft_table *table; rcu_read_lock(); - cb->seq = net->nft.base_seq; + nft_net = nft_pernet(net); + cb->seq = nft_net->base_seq; - list_for_each_entry_rcu(table, &net->nft.tables, list) { + list_for_each_entry_rcu(table, &nft_net->tables, list) { if (family != NFPROTO_UNSPEC && family != table->family) continue; @@ -7315,21 +7681,20 @@ static int nf_tables_dump_flowtable_done(struct netlink_callback *cb) } /* called with rcu_read_lock held */ -static int nf_tables_getflowtable(struct net *net, struct sock *nlsk, - struct sk_buff *skb, - const struct nlmsghdr *nlh, - const struct nlattr * const nla[], - struct netlink_ext_ack *extack) +static int nf_tables_getflowtable(struct sk_buff *skb, + const struct nfnl_info *info, + const struct nlattr * const nla[]) { - const struct nfgenmsg *nfmsg = nlmsg_data(nlh); - u8 genmask = nft_genmask_cur(net); + const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); + u8 genmask = nft_genmask_cur(info->net); int family = nfmsg->nfgen_family; struct nft_flowtable *flowtable; const struct nft_table *table; + struct net *net = info->net; struct sk_buff *skb2; int err; - if (nlh->nlmsg_flags & NLM_F_DUMP) { + if (info->nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { .start = nf_tables_dump_flowtable_start, .dump = nf_tables_dump_flowtable, @@ -7338,7 +7703,7 @@ static int nf_tables_getflowtable(struct net *net, struct sock *nlsk, .data = (void *)nla, }; - return nft_netlink_dump_start_rcu(nlsk, skb, nlh, &c); + return nft_netlink_dump_start_rcu(info->sk, skb, info->nlh, &c); } if (!nla[NFTA_FLOWTABLE_NAME]) @@ -7359,7 +7724,7 @@ static int nf_tables_getflowtable(struct net *net, struct sock *nlsk, return -ENOMEM; err = nf_tables_fill_flowtable_info(skb2, net, NETLINK_CB(skb).portid, - nlh->nlmsg_seq, + info->nlh->nlmsg_seq, NFT_MSG_NEWFLOWTABLE, 0, family, flowtable, &flowtable->hook_list); if (err < 0) @@ -7377,20 +7742,9 @@ static void nf_tables_flowtable_notify(struct nft_ctx *ctx, struct list_head *hook_list, int event) { + struct nftables_pernet *nft_net = nft_pernet(ctx->net); struct sk_buff *skb; int err; - char *buf = kasprintf(GFP_KERNEL, "%s:%llu;%s:%llu", - flowtable->table->name, flowtable->table->handle, - flowtable->name, flowtable->handle); - - audit_log_nfcfg(buf, - ctx->family, - flowtable->hooknum, - event == NFT_MSG_NEWFLOWTABLE ? - AUDIT_NFT_OP_FLOWTABLE_REGISTER : - AUDIT_NFT_OP_FLOWTABLE_UNREGISTER, - GFP_KERNEL); - kfree(buf); if (!ctx->report && !nfnetlink_has_listeners(ctx->net, NFNLGRP_NFTABLES)) @@ -7408,7 +7762,7 @@ static void nf_tables_flowtable_notify(struct nft_ctx *ctx, goto err; } - nft_notify_enqueue(skb, ctx->report, &ctx->net->nft.notify_list); + nft_notify_enqueue(skb, ctx->report, &nft_net->notify_list); return; err: nfnetlink_set_err(ctx->net, ctx->portid, NFNLGRP_NFTABLES, -ENOBUFS); @@ -7433,21 +7787,17 @@ static void nf_tables_flowtable_destroy(struct nft_flowtable *flowtable) static int nf_tables_fill_gen_info(struct sk_buff *skb, struct net *net, u32 portid, u32 seq) { + struct nftables_pernet *nft_net = nft_pernet(net); struct nlmsghdr *nlh; - struct nfgenmsg *nfmsg; char buf[TASK_COMM_LEN]; int event = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, NFT_MSG_NEWGEN); - nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct nfgenmsg), 0); - if (nlh == NULL) + nlh = nfnl_msg_put(skb, portid, seq, event, 0, AF_UNSPEC, + NFNETLINK_V0, nft_base_seq(net)); + if (!nlh) goto nla_put_failure; - nfmsg = nlmsg_data(nlh); - nfmsg->nfgen_family = AF_UNSPEC; - nfmsg->version = NFNETLINK_V0; - nfmsg->res_id = htons(net->nft.base_seq & 0xffff); - - if (nla_put_be32(skb, NFTA_GEN_ID, htonl(net->nft.base_seq)) || + if (nla_put_be32(skb, NFTA_GEN_ID, htonl(nft_net->base_seq)) || nla_put_be32(skb, NFTA_GEN_PROC_PID, htonl(task_pid_nr(current))) || nla_put_string(skb, NFTA_GEN_PROC_NAME, get_task_comm(buf, current))) goto nla_put_failure; @@ -7482,6 +7832,7 @@ static int nf_tables_flowtable_event(struct notifier_block *this, { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct nft_flowtable *flowtable; + struct nftables_pernet *nft_net; struct nft_table *table; struct net *net; @@ -7489,13 +7840,14 @@ static int nf_tables_flowtable_event(struct notifier_block *this, return 0; net = dev_net(dev); - mutex_lock(&net->nft.commit_mutex); - list_for_each_entry(table, &net->nft.tables, list) { + nft_net = nft_pernet(net); + mutex_lock(&nft_net->commit_mutex); + list_for_each_entry(table, &nft_net->tables, list) { list_for_each_entry(flowtable, &table->flowtables, list) { nft_flowtable_event(event, dev, flowtable); } } - mutex_unlock(&net->nft.commit_mutex); + mutex_unlock(&nft_net->commit_mutex); return NOTIFY_DONE; } @@ -7511,9 +7863,6 @@ static void nf_tables_gen_notify(struct net *net, struct sk_buff *skb, struct sk_buff *skb2; int err; - audit_log_nfcfg("?:0;?:0", 0, net->nft.base_seq, - AUDIT_NFT_OP_GEN_REGISTER, GFP_KERNEL); - if (!nlmsg_report(nlh) && !nfnetlink_has_listeners(net, NFNLGRP_NFTABLES)) return; @@ -7537,10 +7886,8 @@ err: -ENOBUFS); } -static int nf_tables_getgen(struct net *net, struct sock *nlsk, - struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nla[], - struct netlink_ext_ack *extack) +static int nf_tables_getgen(struct sk_buff *skb, const struct nfnl_info *info, + const struct nlattr * const nla[]) { struct sk_buff *skb2; int err; @@ -7549,12 +7896,12 @@ static int nf_tables_getgen(struct net *net, struct sock *nlsk, if (skb2 == NULL) return -ENOMEM; - err = nf_tables_fill_gen_info(skb2, net, NETLINK_CB(skb).portid, - nlh->nlmsg_seq); + err = nf_tables_fill_gen_info(skb2, info->net, NETLINK_CB(skb).portid, + info->nlh->nlmsg_seq); if (err < 0) goto err_fill_gen_info; - return nfnetlink_unicast(skb2, net, NETLINK_CB(skb).portid); + return nfnetlink_unicast(skb2, info->net, NETLINK_CB(skb).portid); err_fill_gen_info: kfree_skb(skb2); @@ -7563,115 +7910,138 @@ err_fill_gen_info: static const struct nfnl_callback nf_tables_cb[NFT_MSG_MAX] = { [NFT_MSG_NEWTABLE] = { - .call_batch = nf_tables_newtable, + .call = nf_tables_newtable, + .type = NFNL_CB_BATCH, .attr_count = NFTA_TABLE_MAX, .policy = nft_table_policy, }, [NFT_MSG_GETTABLE] = { - .call_rcu = nf_tables_gettable, + .call = nf_tables_gettable, + .type = NFNL_CB_RCU, .attr_count = NFTA_TABLE_MAX, .policy = nft_table_policy, }, [NFT_MSG_DELTABLE] = { - .call_batch = nf_tables_deltable, + .call = nf_tables_deltable, + .type = NFNL_CB_BATCH, .attr_count = NFTA_TABLE_MAX, .policy = nft_table_policy, }, [NFT_MSG_NEWCHAIN] = { - .call_batch = nf_tables_newchain, + .call = nf_tables_newchain, + .type = NFNL_CB_BATCH, .attr_count = NFTA_CHAIN_MAX, .policy = nft_chain_policy, }, [NFT_MSG_GETCHAIN] = { - .call_rcu = nf_tables_getchain, + .call = nf_tables_getchain, + .type = NFNL_CB_RCU, .attr_count = NFTA_CHAIN_MAX, .policy = nft_chain_policy, }, [NFT_MSG_DELCHAIN] = { - .call_batch = nf_tables_delchain, + .call = nf_tables_delchain, + .type = NFNL_CB_BATCH, .attr_count = NFTA_CHAIN_MAX, .policy = nft_chain_policy, }, [NFT_MSG_NEWRULE] = { - .call_batch = nf_tables_newrule, + .call = nf_tables_newrule, + .type = NFNL_CB_BATCH, .attr_count = NFTA_RULE_MAX, .policy = nft_rule_policy, }, [NFT_MSG_GETRULE] = { - .call_rcu = nf_tables_getrule, + .call = nf_tables_getrule, + .type = NFNL_CB_RCU, .attr_count = NFTA_RULE_MAX, .policy = nft_rule_policy, }, [NFT_MSG_DELRULE] = { - .call_batch = nf_tables_delrule, + .call = nf_tables_delrule, + .type = NFNL_CB_BATCH, .attr_count = NFTA_RULE_MAX, .policy = nft_rule_policy, }, [NFT_MSG_NEWSET] = { - .call_batch = nf_tables_newset, + .call = nf_tables_newset, + .type = NFNL_CB_BATCH, .attr_count = NFTA_SET_MAX, .policy = nft_set_policy, }, [NFT_MSG_GETSET] = { - .call_rcu = nf_tables_getset, + .call = nf_tables_getset, + .type = NFNL_CB_RCU, .attr_count = NFTA_SET_MAX, .policy = nft_set_policy, }, [NFT_MSG_DELSET] = { - .call_batch = nf_tables_delset, + .call = nf_tables_delset, + .type = NFNL_CB_BATCH, .attr_count = NFTA_SET_MAX, .policy = nft_set_policy, }, [NFT_MSG_NEWSETELEM] = { - .call_batch = nf_tables_newsetelem, + .call = nf_tables_newsetelem, + .type = NFNL_CB_BATCH, .attr_count = NFTA_SET_ELEM_LIST_MAX, .policy = nft_set_elem_list_policy, }, [NFT_MSG_GETSETELEM] = { - .call_rcu = nf_tables_getsetelem, + .call = nf_tables_getsetelem, + .type = NFNL_CB_RCU, .attr_count = NFTA_SET_ELEM_LIST_MAX, .policy = nft_set_elem_list_policy, }, [NFT_MSG_DELSETELEM] = { - .call_batch = nf_tables_delsetelem, + .call = nf_tables_delsetelem, + .type = NFNL_CB_BATCH, .attr_count = NFTA_SET_ELEM_LIST_MAX, .policy = nft_set_elem_list_policy, }, [NFT_MSG_GETGEN] = { - .call_rcu = nf_tables_getgen, + .call = nf_tables_getgen, + .type = NFNL_CB_RCU, }, [NFT_MSG_NEWOBJ] = { - .call_batch = nf_tables_newobj, + .call = nf_tables_newobj, + .type = NFNL_CB_BATCH, .attr_count = NFTA_OBJ_MAX, .policy = nft_obj_policy, }, [NFT_MSG_GETOBJ] = { - .call_rcu = nf_tables_getobj, + .call = nf_tables_getobj, + .type = NFNL_CB_RCU, .attr_count = NFTA_OBJ_MAX, .policy = nft_obj_policy, }, [NFT_MSG_DELOBJ] = { - .call_batch = nf_tables_delobj, + .call = nf_tables_delobj, + .type = NFNL_CB_BATCH, .attr_count = NFTA_OBJ_MAX, .policy = nft_obj_policy, }, [NFT_MSG_GETOBJ_RESET] = { - .call_rcu = nf_tables_getobj, + .call = nf_tables_getobj, + .type = NFNL_CB_RCU, .attr_count = NFTA_OBJ_MAX, .policy = nft_obj_policy, }, [NFT_MSG_NEWFLOWTABLE] = { - .call_batch = nf_tables_newflowtable, + .call = nf_tables_newflowtable, + .type = NFNL_CB_BATCH, .attr_count = NFTA_FLOWTABLE_MAX, .policy = nft_flowtable_policy, }, [NFT_MSG_GETFLOWTABLE] = { - .call_rcu = nf_tables_getflowtable, + .call = nf_tables_getflowtable, + .type = NFNL_CB_RCU, .attr_count = NFTA_FLOWTABLE_MAX, .policy = nft_flowtable_policy, }, [NFT_MSG_DELFLOWTABLE] = { - .call_batch = nf_tables_delflowtable, + .call = nf_tables_delflowtable, + .type = NFNL_CB_BATCH, .attr_count = NFTA_FLOWTABLE_MAX, .policy = nft_flowtable_policy, }, @@ -7679,16 +8049,17 @@ static const struct nfnl_callback nf_tables_cb[NFT_MSG_MAX] = { static int nf_tables_validate(struct net *net) { + struct nftables_pernet *nft_net = nft_pernet(net); struct nft_table *table; - switch (net->nft.validate_state) { + switch (nft_net->validate_state) { case NFT_VALIDATE_SKIP: break; case NFT_VALIDATE_NEED: nft_validate_state_update(net, NFT_VALIDATE_DO); fallthrough; case NFT_VALIDATE_DO: - list_for_each_entry(table, &net->nft.tables, list) { + list_for_each_entry(table, &nft_net->tables, list) { if (nft_table_validate(net, table) < 0) return -EAGAIN; } @@ -7863,9 +8234,10 @@ static int nf_tables_commit_chain_prepare(struct net *net, struct nft_chain *cha static void nf_tables_commit_chain_prepare_cancel(struct net *net) { + struct nftables_pernet *nft_net = nft_pernet(net); struct nft_trans *trans, *next; - list_for_each_entry_safe(trans, next, &net->nft.commit_list, list) { + list_for_each_entry_safe(trans, next, &nft_net->commit_list, list) { struct nft_chain *chain = trans->ctx.chain; if (trans->msg_type == NFT_MSG_NEWRULE || @@ -7974,10 +8346,11 @@ static void nft_flowtable_hooks_del(struct nft_flowtable *flowtable, static void nf_tables_module_autoload_cleanup(struct net *net) { + struct nftables_pernet *nft_net = nft_pernet(net); struct nft_module_request *req, *next; - WARN_ON_ONCE(!list_empty(&net->nft.commit_list)); - list_for_each_entry_safe(req, next, &net->nft.module_list, list) { + WARN_ON_ONCE(!list_empty(&nft_net->commit_list)); + list_for_each_entry_safe(req, next, &nft_net->module_list, list) { WARN_ON_ONCE(!req->done); list_del(&req->list); kfree(req); @@ -7986,6 +8359,7 @@ static void nf_tables_module_autoload_cleanup(struct net *net) static void nf_tables_commit_release(struct net *net) { + struct nftables_pernet *nft_net = nft_pernet(net); struct nft_trans *trans; /* all side effects have to be made visible. @@ -7995,35 +8369,36 @@ static void nf_tables_commit_release(struct net *net) * Memory reclaim happens asynchronously from work queue * to prevent expensive synchronize_rcu() in commit phase. */ - if (list_empty(&net->nft.commit_list)) { + if (list_empty(&nft_net->commit_list)) { nf_tables_module_autoload_cleanup(net); - mutex_unlock(&net->nft.commit_mutex); + mutex_unlock(&nft_net->commit_mutex); return; } - trans = list_last_entry(&net->nft.commit_list, + trans = list_last_entry(&nft_net->commit_list, struct nft_trans, list); get_net(trans->ctx.net); WARN_ON_ONCE(trans->put_net); trans->put_net = true; spin_lock(&nf_tables_destroy_list_lock); - list_splice_tail_init(&net->nft.commit_list, &nf_tables_destroy_list); + list_splice_tail_init(&nft_net->commit_list, &nf_tables_destroy_list); spin_unlock(&nf_tables_destroy_list_lock); nf_tables_module_autoload_cleanup(net); schedule_work(&trans_destroy_work); - mutex_unlock(&net->nft.commit_mutex); + mutex_unlock(&nft_net->commit_mutex); } static void nft_commit_notify(struct net *net, u32 portid) { + struct nftables_pernet *nft_net = nft_pernet(net); struct sk_buff *batch_skb = NULL, *nskb, *skb; unsigned char *data; int len; - list_for_each_entry_safe(skb, nskb, &net->nft.notify_list, list) { + list_for_each_entry_safe(skb, nskb, &nft_net->notify_list, list) { if (!batch_skb) { new_batch: batch_skb = skb; @@ -8049,19 +8424,72 @@ new_batch: NFT_CB(batch_skb).report, GFP_KERNEL); } - WARN_ON_ONCE(!list_empty(&net->nft.notify_list)); + WARN_ON_ONCE(!list_empty(&nft_net->notify_list)); +} + +static int nf_tables_commit_audit_alloc(struct list_head *adl, + struct nft_table *table) +{ + struct nft_audit_data *adp; + + list_for_each_entry(adp, adl, list) { + if (adp->table == table) + return 0; + } + adp = kzalloc(sizeof(*adp), GFP_KERNEL); + if (!adp) + return -ENOMEM; + adp->table = table; + list_add(&adp->list, adl); + return 0; +} + +static void nf_tables_commit_audit_collect(struct list_head *adl, + struct nft_table *table, u32 op) +{ + struct nft_audit_data *adp; + + list_for_each_entry(adp, adl, list) { + if (adp->table == table) + goto found; + } + WARN_ONCE(1, "table=%s not expected in commit list", table->name); + return; +found: + adp->entries++; + if (!adp->op || adp->op > op) + adp->op = op; +} + +#define AUNFTABLENAMELEN (NFT_TABLE_MAXNAMELEN + 22) + +static void nf_tables_commit_audit_log(struct list_head *adl, u32 generation) +{ + struct nft_audit_data *adp, *adn; + char aubuf[AUNFTABLENAMELEN]; + + list_for_each_entry_safe(adp, adn, adl, list) { + snprintf(aubuf, AUNFTABLENAMELEN, "%s:%u", adp->table->name, + generation); + audit_log_nfcfg(aubuf, adp->table->family, adp->entries, + nft2audit_op[adp->op], GFP_KERNEL); + list_del(&adp->list); + kfree(adp); + } } static int nf_tables_commit(struct net *net, struct sk_buff *skb) { + struct nftables_pernet *nft_net = nft_pernet(net); struct nft_trans *trans, *next; struct nft_trans_elem *te; struct nft_chain *chain; struct nft_table *table; + LIST_HEAD(adl); int err; - if (list_empty(&net->nft.commit_list)) { - mutex_unlock(&net->nft.commit_mutex); + if (list_empty(&nft_net->commit_list)) { + mutex_unlock(&nft_net->commit_mutex); return 0; } @@ -8074,9 +8502,14 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) return err; /* 1. Allocate space for next generation rules_gen_X[] */ - list_for_each_entry_safe(trans, next, &net->nft.commit_list, list) { + list_for_each_entry_safe(trans, next, &nft_net->commit_list, list) { int ret; + ret = nf_tables_commit_audit_alloc(&adl, trans->ctx.table); + if (ret) { + nf_tables_commit_chain_prepare_cancel(net); + return ret; + } if (trans->msg_type == NFT_MSG_NEWRULE || trans->msg_type == NFT_MSG_DELRULE) { chain = trans->ctx.chain; @@ -8090,7 +8523,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) } /* step 2. Make rules_gen_X visible to packet path */ - list_for_each_entry(table, &net->nft.tables, list) { + list_for_each_entry(table, &nft_net->tables, list) { list_for_each_entry(chain, &table->chains, list) nf_tables_commit_chain(net, chain); } @@ -8099,20 +8532,22 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) * Bump generation counter, invalidate any dump in progress. * Cannot fail after this point. */ - while (++net->nft.base_seq == 0); + while (++nft_net->base_seq == 0) + ; /* step 3. Start new generation, rules_gen_X now in use. */ net->nft.gencursor = nft_gencursor_next(net); - list_for_each_entry_safe(trans, next, &net->nft.commit_list, list) { + list_for_each_entry_safe(trans, next, &nft_net->commit_list, list) { + nf_tables_commit_audit_collect(&adl, trans->ctx.table, + trans->msg_type); switch (trans->msg_type) { case NFT_MSG_NEWTABLE: if (nft_trans_table_update(trans)) { - if (!nft_trans_table_enable(trans)) { - nf_tables_table_disable(net, - trans->ctx.table); - trans->ctx.table->flags |= NFT_TABLE_F_DORMANT; - } + if (nft_trans_table_state(trans) == NFT_TABLE_STATE_DORMANT) + nf_tables_table_disable(net, trans->ctx.table); + + trans->ctx.table->flags = nft_trans_table_flags(trans); } else { nft_clear(net, trans->ctx.table); } @@ -8179,7 +8614,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) case NFT_MSG_NEWSETELEM: te = (struct nft_trans_elem *)trans->data; - te->set->ops->activate(net, te->set, &te->elem); + nft_setelem_activate(net, te->set, &te->elem); nf_tables_setelem_notify(&trans->ctx, te->set, &te->elem, NFT_MSG_NEWSETELEM, 0); @@ -8191,9 +8626,11 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) nf_tables_setelem_notify(&trans->ctx, te->set, &te->elem, NFT_MSG_DELSETELEM, 0); - te->set->ops->remove(net, te->set, &te->elem); - atomic_dec(&te->set->nelems); - te->set->ndeact--; + nft_setelem_remove(net, te->set, &te->elem); + if (!nft_setelem_is_catchall(te->set, &te->elem)) { + atomic_dec(&te->set->nelems); + te->set->ndeact--; + } break; case NFT_MSG_NEWOBJ: if (nft_trans_obj_update(trans)) { @@ -8258,6 +8695,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) nft_commit_notify(net, NETLINK_CB(skb).portid); nf_tables_gen_notify(net, skb, NFT_MSG_NEWGEN); + nf_tables_commit_audit_log(&adl, nft_net->base_seq); nf_tables_commit_release(net); return 0; @@ -8265,17 +8703,18 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) static void nf_tables_module_autoload(struct net *net) { + struct nftables_pernet *nft_net = nft_pernet(net); struct nft_module_request *req, *next; LIST_HEAD(module_list); - list_splice_init(&net->nft.module_list, &module_list); - mutex_unlock(&net->nft.commit_mutex); + list_splice_init(&nft_net->module_list, &module_list); + mutex_unlock(&nft_net->commit_mutex); list_for_each_entry_safe(req, next, &module_list, list) { request_module("%s", req->module); req->done = true; } - mutex_lock(&net->nft.commit_mutex); - list_splice(&module_list, &net->nft.module_list); + mutex_lock(&nft_net->commit_mutex); + list_splice(&module_list, &nft_net->module_list); } static void nf_tables_abort_release(struct nft_trans *trans) @@ -8312,6 +8751,7 @@ static void nf_tables_abort_release(struct nft_trans *trans) static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) { + struct nftables_pernet *nft_net = nft_pernet(net); struct nft_trans *trans, *next; struct nft_trans_elem *te; struct nft_hook *hook; @@ -8320,16 +8760,14 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) nf_tables_validate(net) < 0) return -EAGAIN; - list_for_each_entry_safe_reverse(trans, next, &net->nft.commit_list, + list_for_each_entry_safe_reverse(trans, next, &nft_net->commit_list, list) { switch (trans->msg_type) { case NFT_MSG_NEWTABLE: if (nft_trans_table_update(trans)) { - if (nft_trans_table_enable(trans)) { - nf_tables_table_disable(net, - trans->ctx.table); - trans->ctx.table->flags |= NFT_TABLE_F_DORMANT; - } + if (nft_trans_table_state(trans) == NFT_TABLE_STATE_WAKEUP) + nf_tables_table_disable(net, trans->ctx.table); + nft_trans_destroy(trans); } else { list_del_rcu(&trans->ctx.table->list); @@ -8393,15 +8831,17 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) break; } te = (struct nft_trans_elem *)trans->data; - te->set->ops->remove(net, te->set, &te->elem); - atomic_dec(&te->set->nelems); + nft_setelem_remove(net, te->set, &te->elem); + if (!nft_setelem_is_catchall(te->set, &te->elem)) + atomic_dec(&te->set->nelems); break; case NFT_MSG_DELSETELEM: te = (struct nft_trans_elem *)trans->data; - nft_set_elem_activate(net, te->set, &te->elem); - te->set->ops->activate(net, te->set, &te->elem); - te->set->ndeact--; + nft_setelem_data_activate(net, te->set, &te->elem); + nft_setelem_activate(net, te->set, &te->elem); + if (!nft_setelem_is_catchall(te->set, &te->elem)) + te->set->ndeact--; nft_trans_destroy(trans); break; @@ -8446,7 +8886,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) synchronize_rcu(); list_for_each_entry_safe_reverse(trans, next, - &net->nft.commit_list, list) { + &nft_net->commit_list, list) { list_del(&trans->list); nf_tables_abort_release(trans); } @@ -8467,22 +8907,24 @@ static void nf_tables_cleanup(struct net *net) static int nf_tables_abort(struct net *net, struct sk_buff *skb, enum nfnl_abort_action action) { + struct nftables_pernet *nft_net = nft_pernet(net); int ret = __nf_tables_abort(net, action); - mutex_unlock(&net->nft.commit_mutex); + mutex_unlock(&nft_net->commit_mutex); return ret; } static bool nf_tables_valid_genid(struct net *net, u32 genid) { + struct nftables_pernet *nft_net = nft_pernet(net); bool genid_ok; - mutex_lock(&net->nft.commit_mutex); + mutex_lock(&nft_net->commit_mutex); - genid_ok = genid == 0 || net->nft.base_seq == genid; + genid_ok = genid == 0 || nft_net->base_seq == genid; if (!genid_ok) - mutex_unlock(&net->nft.commit_mutex); + mutex_unlock(&nft_net->commit_mutex); /* else, commit mutex has to be released by commit or abort function */ return genid_ok; @@ -8544,26 +8986,59 @@ EXPORT_SYMBOL_GPL(nft_chain_validate_hooks); static int nf_tables_check_loops(const struct nft_ctx *ctx, const struct nft_chain *chain); +static int nft_check_loops(const struct nft_ctx *ctx, + const struct nft_set_ext *ext) +{ + const struct nft_data *data; + int ret; + + data = nft_set_ext_data(ext); + switch (data->verdict.code) { + case NFT_JUMP: + case NFT_GOTO: + ret = nf_tables_check_loops(ctx, data->verdict.chain); + break; + default: + ret = 0; + break; + } + + return ret; +} + static int nf_tables_loop_check_setelem(const struct nft_ctx *ctx, struct nft_set *set, const struct nft_set_iter *iter, struct nft_set_elem *elem) { const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); - const struct nft_data *data; if (nft_set_ext_exists(ext, NFT_SET_EXT_FLAGS) && *nft_set_ext_flags(ext) & NFT_SET_ELEM_INTERVAL_END) return 0; - data = nft_set_ext_data(ext); - switch (data->verdict.code) { - case NFT_JUMP: - case NFT_GOTO: - return nf_tables_check_loops(ctx, data->verdict.chain); - default: - return 0; + return nft_check_loops(ctx, ext); +} + +static int nft_set_catchall_loops(const struct nft_ctx *ctx, + struct nft_set *set) +{ + u8 genmask = nft_genmask_next(ctx->net); + struct nft_set_elem_catchall *catchall; + struct nft_set_ext *ext; + int ret = 0; + + list_for_each_entry_rcu(catchall, &set->catchall_list, list) { + ext = nft_set_elem_ext(set, catchall->elem); + if (!nft_set_elem_active(ext, genmask)) + continue; + + ret = nft_check_loops(ctx, ext); + if (ret < 0) + return ret; } + + return ret; } static int nf_tables_check_loops(const struct nft_ctx *ctx, @@ -8599,6 +9074,7 @@ static int nf_tables_check_loops(const struct nft_ctx *ctx, data->verdict.chain); if (err < 0) return err; + break; default: break; } @@ -8624,6 +9100,9 @@ static int nf_tables_check_loops(const struct nft_ctx *ctx, iter.fn = nf_tables_loop_check_setelem; set->ops->walk(ctx, set, &iter); + if (!iter.err) + iter.err = nft_set_catchall_loops(ctx, set); + if (iter.err < 0) return iter.err; } @@ -8657,15 +9136,6 @@ int nft_parse_u32_check(const struct nlattr *attr, int max, u32 *dest) } EXPORT_SYMBOL_GPL(nft_parse_u32_check); -/** - * nft_parse_register - parse a register value from a netlink attribute - * - * @attr: netlink attribute - * - * Parse and translate a register value from a netlink attribute. - * Registers used to be 128 bit wide, these register numbers will be - * mapped to the corresponding 32 bit register numbers. - */ static unsigned int nft_parse_register(const struct nlattr *attr) { unsigned int reg; @@ -8701,15 +9171,6 @@ int nft_dump_register(struct sk_buff *skb, unsigned int attr, unsigned int reg) } EXPORT_SYMBOL_GPL(nft_dump_register); -/** - * nft_validate_register_load - validate a load from a register - * - * @reg: the register number - * @len: the length of the data - * - * Validate that the input register is one of the general purpose - * registers and that the length of the load is within the bounds. - */ static int nft_validate_register_load(enum nft_registers reg, unsigned int len) { if (reg < NFT_REG_1 * NFT_REG_SIZE / NFT_REG32_SIZE) @@ -8737,20 +9198,6 @@ int nft_parse_register_load(const struct nlattr *attr, u8 *sreg, u32 len) } EXPORT_SYMBOL_GPL(nft_parse_register_load); -/** - * nft_validate_register_store - validate an expressions' register store - * - * @ctx: context of the expression performing the load - * @reg: the destination register number - * @data: the data to load - * @type: the data type - * @len: the length of the data - * - * Validate that a data load uses the appropriate data type for - * the destination register and the length is within the bounds. - * A value of NULL for the data means that its runtime gathered - * data. - */ static int nft_validate_register_store(const struct nft_ctx *ctx, enum nft_registers reg, const struct nft_data *data, @@ -9068,9 +9515,10 @@ static void __nft_release_hook(struct net *net, struct nft_table *table) static void __nft_release_hooks(struct net *net) { + struct nftables_pernet *nft_net = nft_pernet(net); struct nft_table *table; - list_for_each_entry(table, &net->nft.tables, list) { + list_for_each_entry(table, &nft_net->tables, list) { if (nft_table_has_owner(table)) continue; @@ -9127,9 +9575,10 @@ static void __nft_release_table(struct net *net, struct nft_table *table) static void __nft_release_tables(struct net *net) { + struct nftables_pernet *nft_net = nft_pernet(net); struct nft_table *table, *nt; - list_for_each_entry_safe(table, nt, &net->nft.tables, list) { + list_for_each_entry_safe(table, nt, &nft_net->tables, list) { if (nft_table_has_owner(table)) continue; @@ -9140,6 +9589,7 @@ static void __nft_release_tables(struct net *net) static int nft_rcv_nl_event(struct notifier_block *this, unsigned long event, void *ptr) { + struct nftables_pernet *nft_net; struct netlink_notify *n = ptr; struct nft_table *table, *nt; struct net *net = n->net; @@ -9148,8 +9598,9 @@ static int nft_rcv_nl_event(struct notifier_block *this, unsigned long event, if (event != NETLINK_URELEASE || n->protocol != NETLINK_NETFILTER) return NOTIFY_DONE; - mutex_lock(&net->nft.commit_mutex); - list_for_each_entry(table, &net->nft.tables, list) { + nft_net = nft_pernet(net); + mutex_lock(&nft_net->commit_mutex); + list_for_each_entry(table, &nft_net->tables, list) { if (nft_table_has_owner(table) && n->portid == table->nlpid) { __nft_release_hook(net, table); @@ -9158,13 +9609,13 @@ static int nft_rcv_nl_event(struct notifier_block *this, unsigned long event, } if (release) { synchronize_rcu(); - list_for_each_entry_safe(table, nt, &net->nft.tables, list) { + list_for_each_entry_safe(table, nt, &nft_net->tables, list) { if (nft_table_has_owner(table) && n->portid == table->nlpid) __nft_release_table(net, table); } } - mutex_unlock(&net->nft.commit_mutex); + mutex_unlock(&nft_net->commit_mutex); return NOTIFY_DONE; } @@ -9175,13 +9626,15 @@ static struct notifier_block nft_nl_notifier = { static int __net_init nf_tables_init_net(struct net *net) { - INIT_LIST_HEAD(&net->nft.tables); - INIT_LIST_HEAD(&net->nft.commit_list); - INIT_LIST_HEAD(&net->nft.module_list); - INIT_LIST_HEAD(&net->nft.notify_list); - mutex_init(&net->nft.commit_mutex); - net->nft.base_seq = 1; - net->nft.validate_state = NFT_VALIDATE_SKIP; + struct nftables_pernet *nft_net = nft_pernet(net); + + INIT_LIST_HEAD(&nft_net->tables); + INIT_LIST_HEAD(&nft_net->commit_list); + INIT_LIST_HEAD(&nft_net->module_list); + INIT_LIST_HEAD(&nft_net->notify_list); + mutex_init(&nft_net->commit_mutex); + nft_net->base_seq = 1; + nft_net->validate_state = NFT_VALIDATE_SKIP; return 0; } @@ -9193,27 +9646,30 @@ static void __net_exit nf_tables_pre_exit_net(struct net *net) static void __net_exit nf_tables_exit_net(struct net *net) { - mutex_lock(&net->nft.commit_mutex); - if (!list_empty(&net->nft.commit_list)) + struct nftables_pernet *nft_net = nft_pernet(net); + + mutex_lock(&nft_net->commit_mutex); + if (!list_empty(&nft_net->commit_list)) __nf_tables_abort(net, NFNL_ABORT_NONE); __nft_release_tables(net); - mutex_unlock(&net->nft.commit_mutex); - WARN_ON_ONCE(!list_empty(&net->nft.tables)); - WARN_ON_ONCE(!list_empty(&net->nft.module_list)); - WARN_ON_ONCE(!list_empty(&net->nft.notify_list)); + mutex_unlock(&nft_net->commit_mutex); + WARN_ON_ONCE(!list_empty(&nft_net->tables)); + WARN_ON_ONCE(!list_empty(&nft_net->module_list)); + WARN_ON_ONCE(!list_empty(&nft_net->notify_list)); } static struct pernet_operations nf_tables_net_ops = { .init = nf_tables_init_net, .pre_exit = nf_tables_pre_exit_net, .exit = nf_tables_exit_net, + .id = &nf_tables_net_id, + .size = sizeof(struct nftables_pernet), }; static int __init nf_tables_module_init(void) { int err; - spin_lock_init(&nf_tables_destroy_list_lock); err = register_pernet_subsys(&nf_tables_net_ops); if (err < 0) return err; diff --git a/net/netfilter/nf_tables_offload.c b/net/netfilter/nf_tables_offload.c index 9ae14270c543..a48c5fd53a80 100644 --- a/net/netfilter/nf_tables_offload.c +++ b/net/netfilter/nf_tables_offload.c @@ -45,6 +45,48 @@ void nft_flow_rule_set_addr_type(struct nft_flow_rule *flow, offsetof(struct nft_flow_key, control); } +struct nft_offload_ethertype { + __be16 value; + __be16 mask; +}; + +static void nft_flow_rule_transfer_vlan(struct nft_offload_ctx *ctx, + struct nft_flow_rule *flow) +{ + struct nft_flow_match *match = &flow->match; + struct nft_offload_ethertype ethertype; + + if (match->dissector.used_keys & BIT(FLOW_DISSECTOR_KEY_CONTROL) && + match->key.basic.n_proto != htons(ETH_P_8021Q) && + match->key.basic.n_proto != htons(ETH_P_8021AD)) + return; + + ethertype.value = match->key.basic.n_proto; + ethertype.mask = match->mask.basic.n_proto; + + if (match->dissector.used_keys & BIT(FLOW_DISSECTOR_KEY_VLAN) && + (match->key.vlan.vlan_tpid == htons(ETH_P_8021Q) || + match->key.vlan.vlan_tpid == htons(ETH_P_8021AD))) { + match->key.basic.n_proto = match->key.cvlan.vlan_tpid; + match->mask.basic.n_proto = match->mask.cvlan.vlan_tpid; + match->key.cvlan.vlan_tpid = match->key.vlan.vlan_tpid; + match->mask.cvlan.vlan_tpid = match->mask.vlan.vlan_tpid; + match->key.vlan.vlan_tpid = ethertype.value; + match->mask.vlan.vlan_tpid = ethertype.mask; + match->dissector.offset[FLOW_DISSECTOR_KEY_CVLAN] = + offsetof(struct nft_flow_key, cvlan); + match->dissector.used_keys |= BIT(FLOW_DISSECTOR_KEY_CVLAN); + } else { + match->key.basic.n_proto = match->key.vlan.vlan_tpid; + match->mask.basic.n_proto = match->mask.vlan.vlan_tpid; + match->key.vlan.vlan_tpid = ethertype.value; + match->mask.vlan.vlan_tpid = ethertype.mask; + match->dissector.offset[FLOW_DISSECTOR_KEY_VLAN] = + offsetof(struct nft_flow_key, vlan); + match->dissector.used_keys |= BIT(FLOW_DISSECTOR_KEY_VLAN); + } +} + struct nft_flow_rule *nft_flow_rule_create(struct net *net, const struct nft_rule *rule) { @@ -89,6 +131,8 @@ struct nft_flow_rule *nft_flow_rule_create(struct net *net, expr = nft_expr_next(expr); } + nft_flow_rule_transfer_vlan(ctx, flow); + flow->proto = ctx->dep.l3num; kfree(ctx); @@ -197,26 +241,56 @@ static void nft_flow_cls_offload_setup(struct flow_cls_offload *cls_flow, cls_flow->rule = flow->rule; } -static int nft_flow_offload_rule(struct nft_chain *chain, - struct nft_rule *rule, - struct nft_flow_rule *flow, - enum flow_cls_command command) +static int nft_flow_offload_cmd(const struct nft_chain *chain, + const struct nft_rule *rule, + struct nft_flow_rule *flow, + enum flow_cls_command command, + struct flow_cls_offload *cls_flow) { struct netlink_ext_ack extack = {}; - struct flow_cls_offload cls_flow; struct nft_base_chain *basechain; if (!nft_is_base_chain(chain)) return -EOPNOTSUPP; basechain = nft_base_chain(chain); - nft_flow_cls_offload_setup(&cls_flow, basechain, rule, flow, &extack, + nft_flow_cls_offload_setup(cls_flow, basechain, rule, flow, &extack, command); - return nft_setup_cb_call(TC_SETUP_CLSFLOWER, &cls_flow, + return nft_setup_cb_call(TC_SETUP_CLSFLOWER, cls_flow, &basechain->flow_block.cb_list); } +static int nft_flow_offload_rule(const struct nft_chain *chain, + struct nft_rule *rule, + struct nft_flow_rule *flow, + enum flow_cls_command command) +{ + struct flow_cls_offload cls_flow; + + return nft_flow_offload_cmd(chain, rule, flow, command, &cls_flow); +} + +int nft_flow_rule_stats(const struct nft_chain *chain, + const struct nft_rule *rule) +{ + struct flow_cls_offload cls_flow = {}; + struct nft_expr *expr, *next; + int err; + + err = nft_flow_offload_cmd(chain, rule, NULL, FLOW_CLS_STATS, + &cls_flow); + if (err < 0) + return err; + + nft_rule_for_each_expr(expr, next, rule) { + if (expr->ops->offload_stats) + expr->ops->offload_stats(expr, &cls_flow.stats); + } + + return 0; +} + static int nft_flow_offload_bind(struct flow_block_offload *bo, struct nft_base_chain *basechain) { @@ -307,16 +381,18 @@ static void nft_indr_block_cleanup(struct flow_block_cb *block_cb) struct nft_base_chain *basechain = block_cb->indr.data; struct net_device *dev = block_cb->indr.dev; struct netlink_ext_ack extack = {}; + struct nftables_pernet *nft_net; struct net *net = dev_net(dev); struct flow_block_offload bo; nft_flow_block_offload_init(&bo, dev_net(dev), FLOW_BLOCK_UNBIND, basechain, &extack); - mutex_lock(&net->nft.commit_mutex); + nft_net = nft_pernet(net); + mutex_lock(&nft_net->commit_mutex); list_del(&block_cb->driver_list); list_move(&block_cb->list, &bo.cb_list); nft_flow_offload_unbind(&bo, basechain); - mutex_unlock(&net->nft.commit_mutex); + mutex_unlock(&nft_net->commit_mutex); } static int nft_indr_block_offload_cmd(struct nft_base_chain *basechain, @@ -412,9 +488,10 @@ static int nft_flow_offload_chain(struct nft_chain *chain, u8 *ppolicy, static void nft_flow_rule_offload_abort(struct net *net, struct nft_trans *trans) { + struct nftables_pernet *nft_net = nft_pernet(net); int err = 0; - list_for_each_entry_continue_reverse(trans, &net->nft.commit_list, list) { + list_for_each_entry_continue_reverse(trans, &nft_net->commit_list, list) { if (trans->ctx.family != NFPROTO_NETDEV) continue; @@ -460,11 +537,12 @@ static void nft_flow_rule_offload_abort(struct net *net, int nft_flow_rule_offload_commit(struct net *net) { + struct nftables_pernet *nft_net = nft_pernet(net); struct nft_trans *trans; int err = 0; u8 policy; - list_for_each_entry(trans, &net->nft.commit_list, list) { + list_for_each_entry(trans, &nft_net->commit_list, list) { if (trans->ctx.family != NFPROTO_NETDEV) continue; @@ -516,7 +594,7 @@ int nft_flow_rule_offload_commit(struct net *net) } } - list_for_each_entry(trans, &net->nft.commit_list, list) { + list_for_each_entry(trans, &nft_net->commit_list, list) { if (trans->ctx.family != NFPROTO_NETDEV) continue; @@ -536,15 +614,15 @@ int nft_flow_rule_offload_commit(struct net *net) return err; } -static struct nft_chain *__nft_offload_get_chain(struct net_device *dev) +static struct nft_chain *__nft_offload_get_chain(const struct nftables_pernet *nft_net, + struct net_device *dev) { struct nft_base_chain *basechain; - struct net *net = dev_net(dev); struct nft_hook *hook, *found; const struct nft_table *table; struct nft_chain *chain; - list_for_each_entry(table, &net->nft.tables, list) { + list_for_each_entry(table, &nft_net->tables, list) { if (table->family != NFPROTO_NETDEV) continue; @@ -576,19 +654,21 @@ static int nft_offload_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); + struct nftables_pernet *nft_net; struct net *net = dev_net(dev); struct nft_chain *chain; if (event != NETDEV_UNREGISTER) return NOTIFY_DONE; - mutex_lock(&net->nft.commit_mutex); - chain = __nft_offload_get_chain(dev); + nft_net = nft_pernet(net); + mutex_lock(&nft_net->commit_mutex); + chain = __nft_offload_get_chain(nft_net, dev); if (chain) nft_flow_block_chain(nft_base_chain(chain), dev, FLOW_BLOCK_UNBIND); - mutex_unlock(&net->nft.commit_mutex); + mutex_unlock(&nft_net->commit_mutex); return NOTIFY_DONE; } diff --git a/net/netfilter/nf_tables_trace.c b/net/netfilter/nf_tables_trace.c index 87b36da5cd98..0cf3278007ba 100644 --- a/net/netfilter/nf_tables_trace.c +++ b/net/netfilter/nf_tables_trace.c @@ -183,7 +183,6 @@ static bool nft_trace_have_verdict_chain(struct nft_traceinfo *info) void nft_trace_notify(struct nft_traceinfo *info) { const struct nft_pktinfo *pkt = info->pkt; - struct nfgenmsg *nfmsg; struct nlmsghdr *nlh; struct sk_buff *skb; unsigned int size; @@ -219,15 +218,11 @@ void nft_trace_notify(struct nft_traceinfo *info) return; event = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, NFT_MSG_TRACE); - nlh = nlmsg_put(skb, 0, 0, event, sizeof(struct nfgenmsg), 0); + nlh = nfnl_msg_put(skb, 0, 0, event, 0, info->basechain->type->family, + NFNETLINK_V0, 0); if (!nlh) goto nla_put_failure; - nfmsg = nlmsg_data(nlh); - nfmsg->nfgen_family = info->basechain->type->family; - nfmsg->version = NFNETLINK_V0; - nfmsg->res_id = 0; - if (nla_put_be32(skb, NFTA_TRACE_NFPROTO, htonl(nft_pf(pkt)))) goto nla_put_failure; diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index d3df66a39b5e..d7a9628b6cee 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -28,6 +28,7 @@ #include <linux/sched/signal.h> #include <net/netlink.h> +#include <net/netns/generic.h> #include <linux/netfilter/nfnetlink.h> MODULE_LICENSE("GPL"); @@ -41,6 +42,12 @@ MODULE_DESCRIPTION("Netfilter messages via netlink socket"); #define NFNL_MAX_ATTR_COUNT 32 +static unsigned int nfnetlink_pernet_id __read_mostly; + +struct nfnl_net { + struct sock *nfnl; +}; + static struct { struct mutex mutex; const struct nfnetlink_subsystem __rcu *subsys; @@ -75,6 +82,11 @@ static const int nfnl_group2type[NFNLGRP_MAX+1] = { [NFNLGRP_NFTRACE] = NFNL_SUBSYS_NFTABLES, }; +static struct nfnl_net *nfnl_pernet(struct net *net) +{ + return net_generic(net, nfnetlink_pernet_id); +} + void nfnl_lock(__u8 subsys_id) { mutex_lock(&table[subsys_id].mutex); @@ -149,28 +161,35 @@ nfnetlink_find_client(u16 type, const struct nfnetlink_subsystem *ss) int nfnetlink_has_listeners(struct net *net, unsigned int group) { - return netlink_has_listeners(net->nfnl, group); + struct nfnl_net *nfnlnet = nfnl_pernet(net); + + return netlink_has_listeners(nfnlnet->nfnl, group); } EXPORT_SYMBOL_GPL(nfnetlink_has_listeners); int nfnetlink_send(struct sk_buff *skb, struct net *net, u32 portid, unsigned int group, int echo, gfp_t flags) { - return nlmsg_notify(net->nfnl, skb, portid, group, echo, flags); + struct nfnl_net *nfnlnet = nfnl_pernet(net); + + return nlmsg_notify(nfnlnet->nfnl, skb, portid, group, echo, flags); } EXPORT_SYMBOL_GPL(nfnetlink_send); int nfnetlink_set_err(struct net *net, u32 portid, u32 group, int error) { - return netlink_set_err(net->nfnl, portid, group, error); + struct nfnl_net *nfnlnet = nfnl_pernet(net); + + return netlink_set_err(nfnlnet->nfnl, portid, group, error); } EXPORT_SYMBOL_GPL(nfnetlink_set_err); int nfnetlink_unicast(struct sk_buff *skb, struct net *net, u32 portid) { + struct nfnl_net *nfnlnet = nfnl_pernet(net); int err; - err = nlmsg_unicast(net->nfnl, skb, portid); + err = nlmsg_unicast(nfnlnet->nfnl, skb, portid); if (err == -EAGAIN) err = -ENOBUFS; @@ -178,6 +197,15 @@ int nfnetlink_unicast(struct sk_buff *skb, struct net *net, u32 portid) } EXPORT_SYMBOL_GPL(nfnetlink_unicast); +void nfnetlink_broadcast(struct net *net, struct sk_buff *skb, __u32 portid, + __u32 group, gfp_t allocation) +{ + struct nfnl_net *nfnlnet = nfnl_pernet(net); + + netlink_broadcast(nfnlnet->nfnl, skb, portid, group, allocation); +} +EXPORT_SYMBOL_GPL(nfnetlink_broadcast); + /* Process one complete nfnetlink message. */ static int nfnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) @@ -194,6 +222,7 @@ static int nfnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, type = nlh->nlmsg_type; replay: rcu_read_lock(); + ss = nfnetlink_get_subsys(type); if (!ss) { #ifdef CONFIG_MODULES @@ -217,11 +246,18 @@ replay: { int min_len = nlmsg_total_size(sizeof(struct nfgenmsg)); + struct nfnl_net *nfnlnet = nfnl_pernet(net); u8 cb_id = NFNL_MSG_TYPE(nlh->nlmsg_type); struct nlattr *cda[NFNL_MAX_ATTR_COUNT + 1]; struct nlattr *attr = (void *)nlh + min_len; int attrlen = nlh->nlmsg_len - min_len; __u8 subsys_id = NFNL_SUBSYS_ID(type); + struct nfnl_info info = { + .net = net, + .sk = nfnlnet->nfnl, + .nlh = nlh, + .extack = extack, + }; /* Sanity-check NFNL_MAX_ATTR_COUNT */ if (ss->cb[cb_id].attr_count > NFNL_MAX_ATTR_COUNT) { @@ -237,24 +273,30 @@ replay: return err; } - if (nc->call_rcu) { - err = nc->call_rcu(net, net->nfnl, skb, nlh, - (const struct nlattr **)cda, - extack); + if (!nc->call) { rcu_read_unlock(); - } else { + return -EINVAL; + } + + switch (nc->type) { + case NFNL_CB_RCU: + err = nc->call(skb, &info, (const struct nlattr **)cda); + rcu_read_unlock(); + break; + case NFNL_CB_MUTEX: rcu_read_unlock(); nfnl_lock(subsys_id); if (nfnl_dereference_protected(subsys_id) != ss || - nfnetlink_find_client(type, ss) != nc) + nfnetlink_find_client(type, ss) != nc) { err = -EAGAIN; - else if (nc->call) - err = nc->call(net, net->nfnl, skb, nlh, - (const struct nlattr **)cda, - extack); - else - err = -EINVAL; + break; + } + err = nc->call(skb, &info, (const struct nlattr **)cda); nfnl_unlock(subsys_id); + break; + default: + err = -EINVAL; + break; } if (err == -EAGAIN) goto replay; @@ -432,12 +474,24 @@ replay_abort: goto ack; } + if (nc->type != NFNL_CB_BATCH) { + err = -EINVAL; + goto ack; + } + { int min_len = nlmsg_total_size(sizeof(struct nfgenmsg)); - u8 cb_id = NFNL_MSG_TYPE(nlh->nlmsg_type); + struct nfnl_net *nfnlnet = nfnl_pernet(net); struct nlattr *cda[NFNL_MAX_ATTR_COUNT + 1]; struct nlattr *attr = (void *)nlh + min_len; + u8 cb_id = NFNL_MSG_TYPE(nlh->nlmsg_type); int attrlen = nlh->nlmsg_len - min_len; + struct nfnl_info info = { + .net = net, + .sk = nfnlnet->nfnl, + .nlh = nlh, + .extack = &extack, + }; /* Sanity-check NFTA_MAX_ATTR */ if (ss->cb[cb_id].attr_count > NFNL_MAX_ATTR_COUNT) { @@ -452,11 +506,7 @@ replay_abort: if (err < 0) goto ack; - if (nc->call_batch) { - err = nc->call_batch(net, net->nfnl, skb, nlh, - (const struct nlattr **)cda, - &extack); - } + err = nc->call(skb, &info, (const struct nlattr **)cda); /* The lock was released to autoload some module, we * have to abort and start from scratch using the @@ -622,7 +672,7 @@ static int nfnetlink_bind(struct net *net, int group) static int __net_init nfnetlink_net_init(struct net *net) { - struct sock *nfnl; + struct nfnl_net *nfnlnet = nfnl_pernet(net); struct netlink_kernel_cfg cfg = { .groups = NFNLGRP_MAX, .input = nfnetlink_rcv, @@ -631,28 +681,29 @@ static int __net_init nfnetlink_net_init(struct net *net) #endif }; - nfnl = netlink_kernel_create(net, NETLINK_NETFILTER, &cfg); - if (!nfnl) + nfnlnet->nfnl = netlink_kernel_create(net, NETLINK_NETFILTER, &cfg); + if (!nfnlnet->nfnl) return -ENOMEM; - net->nfnl_stash = nfnl; - rcu_assign_pointer(net->nfnl, nfnl); return 0; } static void __net_exit nfnetlink_net_exit_batch(struct list_head *net_exit_list) { + struct nfnl_net *nfnlnet; struct net *net; - list_for_each_entry(net, net_exit_list, exit_list) - RCU_INIT_POINTER(net->nfnl, NULL); - synchronize_net(); - list_for_each_entry(net, net_exit_list, exit_list) - netlink_kernel_release(net->nfnl_stash); + list_for_each_entry(net, net_exit_list, exit_list) { + nfnlnet = nfnl_pernet(net); + + netlink_kernel_release(nfnlnet->nfnl); + } } static struct pernet_operations nfnetlink_net_ops = { .init = nfnetlink_net_init, .exit_batch = nfnetlink_net_exit_batch, + .id = &nfnetlink_pernet_id, + .size = sizeof(struct nfnl_net), }; static int __init nfnetlink_init(void) diff --git a/net/netfilter/nfnetlink_acct.c b/net/netfilter/nfnetlink_acct.c index 0fa1653b5f19..3c8cf8748cfb 100644 --- a/net/netfilter/nfnetlink_acct.c +++ b/net/netfilter/nfnetlink_acct.c @@ -56,15 +56,13 @@ static inline struct nfnl_acct_net *nfnl_acct_pernet(struct net *net) #define NFACCT_F_QUOTA (NFACCT_F_QUOTA_PKTS | NFACCT_F_QUOTA_BYTES) #define NFACCT_OVERQUOTA_BIT 2 /* NFACCT_F_OVERQUOTA */ -static int nfnl_acct_new(struct net *net, struct sock *nfnl, - struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const tb[], - struct netlink_ext_ack *extack) +static int nfnl_acct_new(struct sk_buff *skb, const struct nfnl_info *info, + const struct nlattr * const tb[]) { - struct nfnl_acct_net *nfnl_acct_net = nfnl_acct_pernet(net); + struct nfnl_acct_net *nfnl_acct_net = nfnl_acct_pernet(info->net); struct nf_acct *nfacct, *matching = NULL; - char *acct_name; unsigned int size = 0; + char *acct_name; u32 flags = 0; if (!tb[NFACCT_NAME]) @@ -78,7 +76,7 @@ static int nfnl_acct_new(struct net *net, struct sock *nfnl, if (strncmp(nfacct->name, acct_name, NFACCT_NAME_MAX) != 0) continue; - if (nlh->nlmsg_flags & NLM_F_EXCL) + if (info->nlh->nlmsg_flags & NLM_F_EXCL) return -EEXIST; matching = nfacct; @@ -86,7 +84,7 @@ static int nfnl_acct_new(struct net *net, struct sock *nfnl, } if (matching) { - if (nlh->nlmsg_flags & NLM_F_REPLACE) { + if (info->nlh->nlmsg_flags & NLM_F_REPLACE) { /* reset counters if you request a replacement. */ atomic64_set(&matching->pkts, 0); atomic64_set(&matching->bytes, 0); @@ -145,21 +143,16 @@ nfnl_acct_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type, int event, struct nf_acct *acct) { struct nlmsghdr *nlh; - struct nfgenmsg *nfmsg; unsigned int flags = portid ? NLM_F_MULTI : 0; u64 pkts, bytes; u32 old_flags; event = nfnl_msg_type(NFNL_SUBSYS_ACCT, event); - nlh = nlmsg_put(skb, portid, seq, event, sizeof(*nfmsg), flags); - if (nlh == NULL) + nlh = nfnl_msg_put(skb, portid, seq, event, flags, AF_UNSPEC, + NFNETLINK_V0, 0); + if (!nlh) goto nlmsg_failure; - nfmsg = nlmsg_data(nlh); - nfmsg->nfgen_family = AF_UNSPEC; - nfmsg->version = NFNETLINK_V0; - nfmsg->res_id = 0; - if (nla_put_string(skb, NFACCT_NAME, acct->name)) goto nla_put_failure; @@ -278,17 +271,15 @@ static int nfnl_acct_start(struct netlink_callback *cb) return 0; } -static int nfnl_acct_get(struct net *net, struct sock *nfnl, - struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const tb[], - struct netlink_ext_ack *extack) +static int nfnl_acct_get(struct sk_buff *skb, const struct nfnl_info *info, + const struct nlattr * const tb[]) { - struct nfnl_acct_net *nfnl_acct_net = nfnl_acct_pernet(net); + struct nfnl_acct_net *nfnl_acct_net = nfnl_acct_pernet(info->net); int ret = -ENOENT; struct nf_acct *cur; char *acct_name; - if (nlh->nlmsg_flags & NLM_F_DUMP) { + if (info->nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { .dump = nfnl_acct_dump, .start = nfnl_acct_start, @@ -296,7 +287,7 @@ static int nfnl_acct_get(struct net *net, struct sock *nfnl, .data = (void *)tb[NFACCT_FILTER], }; - return netlink_dump_start(nfnl, skb, nlh, &c); + return netlink_dump_start(info->sk, skb, info->nlh, &c); } if (!tb[NFACCT_NAME]) @@ -316,15 +307,15 @@ static int nfnl_acct_get(struct net *net, struct sock *nfnl, } ret = nfnl_acct_fill_info(skb2, NETLINK_CB(skb).portid, - nlh->nlmsg_seq, - NFNL_MSG_TYPE(nlh->nlmsg_type), - NFNL_MSG_ACCT_NEW, cur); + info->nlh->nlmsg_seq, + NFNL_MSG_TYPE(info->nlh->nlmsg_type), + NFNL_MSG_ACCT_NEW, cur); if (ret <= 0) { kfree_skb(skb2); break; } - ret = netlink_unicast(nfnl, skb2, NETLINK_CB(skb).portid, - MSG_DONTWAIT); + ret = netlink_unicast(info->sk, skb2, NETLINK_CB(skb).portid, + MSG_DONTWAIT); if (ret > 0) ret = 0; @@ -352,12 +343,10 @@ static int nfnl_acct_try_del(struct nf_acct *cur) return ret; } -static int nfnl_acct_del(struct net *net, struct sock *nfnl, - struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const tb[], - struct netlink_ext_ack *extack) +static int nfnl_acct_del(struct sk_buff *skb, const struct nfnl_info *info, + const struct nlattr * const tb[]) { - struct nfnl_acct_net *nfnl_acct_net = nfnl_acct_pernet(net); + struct nfnl_acct_net *nfnl_acct_net = nfnl_acct_pernet(info->net); struct nf_acct *cur, *tmp; int ret = -ENOENT; char *acct_name; @@ -393,18 +382,30 @@ static const struct nla_policy nfnl_acct_policy[NFACCT_MAX+1] = { }; static const struct nfnl_callback nfnl_acct_cb[NFNL_MSG_ACCT_MAX] = { - [NFNL_MSG_ACCT_NEW] = { .call = nfnl_acct_new, - .attr_count = NFACCT_MAX, - .policy = nfnl_acct_policy }, - [NFNL_MSG_ACCT_GET] = { .call = nfnl_acct_get, - .attr_count = NFACCT_MAX, - .policy = nfnl_acct_policy }, - [NFNL_MSG_ACCT_GET_CTRZERO] = { .call = nfnl_acct_get, - .attr_count = NFACCT_MAX, - .policy = nfnl_acct_policy }, - [NFNL_MSG_ACCT_DEL] = { .call = nfnl_acct_del, - .attr_count = NFACCT_MAX, - .policy = nfnl_acct_policy }, + [NFNL_MSG_ACCT_NEW] = { + .call = nfnl_acct_new, + .type = NFNL_CB_MUTEX, + .attr_count = NFACCT_MAX, + .policy = nfnl_acct_policy + }, + [NFNL_MSG_ACCT_GET] = { + .call = nfnl_acct_get, + .type = NFNL_CB_MUTEX, + .attr_count = NFACCT_MAX, + .policy = nfnl_acct_policy + }, + [NFNL_MSG_ACCT_GET_CTRZERO] = { + .call = nfnl_acct_get, + .type = NFNL_CB_MUTEX, + .attr_count = NFACCT_MAX, + .policy = nfnl_acct_policy + }, + [NFNL_MSG_ACCT_DEL] = { + .call = nfnl_acct_del, + .type = NFNL_CB_MUTEX, + .attr_count = NFACCT_MAX, + .policy = nfnl_acct_policy + }, }; static const struct nfnetlink_subsystem nfnl_acct_subsys = { @@ -474,8 +475,7 @@ static void nfnl_overquota_report(struct net *net, struct nf_acct *nfacct) kfree_skb(skb); return; } - netlink_broadcast(net->nfnl, skb, 0, NFNLGRP_ACCT_QUOTA, - GFP_ATOMIC); + nfnetlink_broadcast(net, skb, 0, NFNLGRP_ACCT_QUOTA, GFP_ATOMIC); } int nfnl_acct_overquota(struct net *net, struct nf_acct *nfacct) diff --git a/net/netfilter/nfnetlink_cthelper.c b/net/netfilter/nfnetlink_cthelper.c index 0f94fce1d3ed..322ac5dd5402 100644 --- a/net/netfilter/nfnetlink_cthelper.c +++ b/net/netfilter/nfnetlink_cthelper.c @@ -408,10 +408,8 @@ nfnl_cthelper_update(const struct nlattr * const tb[], return 0; } -static int nfnl_cthelper_new(struct net *net, struct sock *nfnl, - struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const tb[], - struct netlink_ext_ack *extack) +static int nfnl_cthelper_new(struct sk_buff *skb, const struct nfnl_info *info, + const struct nlattr * const tb[]) { const char *helper_name; struct nf_conntrack_helper *cur, *helper = NULL; @@ -441,7 +439,7 @@ static int nfnl_cthelper_new(struct net *net, struct sock *nfnl, tuple.dst.protonum != cur->tuple.dst.protonum)) continue; - if (nlh->nlmsg_flags & NLM_F_EXCL) + if (info->nlh->nlmsg_flags & NLM_F_EXCL) return -EEXIST; helper = cur; @@ -526,20 +524,15 @@ nfnl_cthelper_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type, int event, struct nf_conntrack_helper *helper) { struct nlmsghdr *nlh; - struct nfgenmsg *nfmsg; unsigned int flags = portid ? NLM_F_MULTI : 0; int status; event = nfnl_msg_type(NFNL_SUBSYS_CTHELPER, event); - nlh = nlmsg_put(skb, portid, seq, event, sizeof(*nfmsg), flags); - if (nlh == NULL) + nlh = nfnl_msg_put(skb, portid, seq, event, flags, AF_UNSPEC, + NFNETLINK_V0, 0); + if (!nlh) goto nlmsg_failure; - nfmsg = nlmsg_data(nlh); - nfmsg->nfgen_family = AF_UNSPEC; - nfmsg->version = NFNETLINK_V0; - nfmsg->res_id = 0; - if (nla_put_string(skb, NFCTH_NAME, helper->name)) goto nla_put_failure; @@ -612,10 +605,8 @@ out: return skb->len; } -static int nfnl_cthelper_get(struct net *net, struct sock *nfnl, - struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const tb[], - struct netlink_ext_ack *extack) +static int nfnl_cthelper_get(struct sk_buff *skb, const struct nfnl_info *info, + const struct nlattr * const tb[]) { int ret = -ENOENT; struct nf_conntrack_helper *cur; @@ -628,11 +619,11 @@ static int nfnl_cthelper_get(struct net *net, struct sock *nfnl, if (!capable(CAP_NET_ADMIN)) return -EPERM; - if (nlh->nlmsg_flags & NLM_F_DUMP) { + if (info->nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { .dump = nfnl_cthelper_dump_table, }; - return netlink_dump_start(nfnl, skb, nlh, &c); + return netlink_dump_start(info->sk, skb, info->nlh, &c); } if (tb[NFCTH_NAME]) @@ -664,15 +655,15 @@ static int nfnl_cthelper_get(struct net *net, struct sock *nfnl, } ret = nfnl_cthelper_fill_info(skb2, NETLINK_CB(skb).portid, - nlh->nlmsg_seq, - NFNL_MSG_TYPE(nlh->nlmsg_type), + info->nlh->nlmsg_seq, + NFNL_MSG_TYPE(info->nlh->nlmsg_type), NFNL_MSG_CTHELPER_NEW, cur); if (ret <= 0) { kfree_skb(skb2); break; } - ret = netlink_unicast(nfnl, skb2, NETLINK_CB(skb).portid, + ret = netlink_unicast(info->sk, skb2, NETLINK_CB(skb).portid, MSG_DONTWAIT); if (ret > 0) ret = 0; @@ -683,10 +674,8 @@ static int nfnl_cthelper_get(struct net *net, struct sock *nfnl, return ret; } -static int nfnl_cthelper_del(struct net *net, struct sock *nfnl, - struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const tb[], - struct netlink_ext_ack *extack) +static int nfnl_cthelper_del(struct sk_buff *skb, const struct nfnl_info *info, + const struct nlattr * const tb[]) { char *helper_name = NULL; struct nf_conntrack_helper *cur; @@ -748,15 +737,24 @@ static const struct nla_policy nfnl_cthelper_policy[NFCTH_MAX+1] = { }; static const struct nfnl_callback nfnl_cthelper_cb[NFNL_MSG_CTHELPER_MAX] = { - [NFNL_MSG_CTHELPER_NEW] = { .call = nfnl_cthelper_new, - .attr_count = NFCTH_MAX, - .policy = nfnl_cthelper_policy }, - [NFNL_MSG_CTHELPER_GET] = { .call = nfnl_cthelper_get, - .attr_count = NFCTH_MAX, - .policy = nfnl_cthelper_policy }, - [NFNL_MSG_CTHELPER_DEL] = { .call = nfnl_cthelper_del, - .attr_count = NFCTH_MAX, - .policy = nfnl_cthelper_policy }, + [NFNL_MSG_CTHELPER_NEW] = { + .call = nfnl_cthelper_new, + .type = NFNL_CB_MUTEX, + .attr_count = NFCTH_MAX, + .policy = nfnl_cthelper_policy + }, + [NFNL_MSG_CTHELPER_GET] = { + .call = nfnl_cthelper_get, + .type = NFNL_CB_MUTEX, + .attr_count = NFCTH_MAX, + .policy = nfnl_cthelper_policy + }, + [NFNL_MSG_CTHELPER_DEL] = { + .call = nfnl_cthelper_del, + .type = NFNL_CB_MUTEX, + .attr_count = NFCTH_MAX, + .policy = nfnl_cthelper_policy + }, }; static const struct nfnetlink_subsystem nfnl_cthelper_subsys = { diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c index 89a381f7f945..38848ad68899 100644 --- a/net/netfilter/nfnetlink_cttimeout.c +++ b/net/netfilter/nfnetlink_cttimeout.c @@ -20,6 +20,7 @@ #include <linux/netfilter.h> #include <net/netlink.h> +#include <net/netns/generic.h> #include <net/sock.h> #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_conntrack_core.h> @@ -30,6 +31,12 @@ #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_cttimeout.h> +static unsigned int nfct_timeout_id __read_mostly; + +struct nfct_timeout_pernet { + struct list_head nfct_timeout_list; +}; + MODULE_LICENSE("GPL"); MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>"); MODULE_DESCRIPTION("cttimeout: Extended Netfilter Connection Tracking timeout tuning"); @@ -42,6 +49,11 @@ static const struct nla_policy cttimeout_nla_policy[CTA_TIMEOUT_MAX+1] = { [CTA_TIMEOUT_DATA] = { .type = NLA_NESTED }, }; +static struct nfct_timeout_pernet *nfct_timeout_pernet(struct net *net) +{ + return net_generic(net, nfct_timeout_id); +} + static int ctnl_timeout_parse_policy(void *timeout, const struct nf_conntrack_l4proto *l4proto, @@ -71,12 +83,11 @@ err: return ret; } -static int cttimeout_new_timeout(struct net *net, struct sock *ctnl, - struct sk_buff *skb, - const struct nlmsghdr *nlh, - const struct nlattr * const cda[], - struct netlink_ext_ack *extack) +static int cttimeout_new_timeout(struct sk_buff *skb, + const struct nfnl_info *info, + const struct nlattr * const cda[]) { + struct nfct_timeout_pernet *pernet = nfct_timeout_pernet(info->net); __u16 l3num; __u8 l4num; const struct nf_conntrack_l4proto *l4proto; @@ -94,11 +105,11 @@ static int cttimeout_new_timeout(struct net *net, struct sock *ctnl, l3num = ntohs(nla_get_be16(cda[CTA_TIMEOUT_L3PROTO])); l4num = nla_get_u8(cda[CTA_TIMEOUT_L4PROTO]); - list_for_each_entry(timeout, &net->nfct_timeout_list, head) { + list_for_each_entry(timeout, &pernet->nfct_timeout_list, head) { if (strncmp(timeout->name, name, CTNL_TIMEOUT_NAME_MAX) != 0) continue; - if (nlh->nlmsg_flags & NLM_F_EXCL) + if (info->nlh->nlmsg_flags & NLM_F_EXCL) return -EEXIST; matching = timeout; @@ -106,7 +117,7 @@ static int cttimeout_new_timeout(struct net *net, struct sock *ctnl, } if (matching) { - if (nlh->nlmsg_flags & NLM_F_REPLACE) { + if (info->nlh->nlmsg_flags & NLM_F_REPLACE) { /* You cannot replace one timeout policy by another of * different kind, sorry. */ @@ -116,7 +127,8 @@ static int cttimeout_new_timeout(struct net *net, struct sock *ctnl, return ctnl_timeout_parse_policy(&matching->timeout.data, matching->timeout.l4proto, - net, cda[CTA_TIMEOUT_DATA]); + info->net, + cda[CTA_TIMEOUT_DATA]); } return -EBUSY; @@ -137,8 +149,8 @@ static int cttimeout_new_timeout(struct net *net, struct sock *ctnl, goto err_proto_put; } - ret = ctnl_timeout_parse_policy(&timeout->timeout.data, l4proto, net, - cda[CTA_TIMEOUT_DATA]); + ret = ctnl_timeout_parse_policy(&timeout->timeout.data, l4proto, + info->net, cda[CTA_TIMEOUT_DATA]); if (ret < 0) goto err; @@ -146,7 +158,7 @@ static int cttimeout_new_timeout(struct net *net, struct sock *ctnl, timeout->timeout.l3num = l3num; timeout->timeout.l4proto = l4proto; refcount_set(&timeout->refcnt, 1); - list_add_tail_rcu(&timeout->head, &net->nfct_timeout_list); + list_add_tail_rcu(&timeout->head, &pernet->nfct_timeout_list); return 0; err: @@ -160,22 +172,17 @@ ctnl_timeout_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type, int event, struct ctnl_timeout *timeout) { struct nlmsghdr *nlh; - struct nfgenmsg *nfmsg; unsigned int flags = portid ? NLM_F_MULTI : 0; const struct nf_conntrack_l4proto *l4proto = timeout->timeout.l4proto; struct nlattr *nest_parms; int ret; event = nfnl_msg_type(NFNL_SUBSYS_CTNETLINK_TIMEOUT, event); - nlh = nlmsg_put(skb, portid, seq, event, sizeof(*nfmsg), flags); - if (nlh == NULL) + nlh = nfnl_msg_put(skb, portid, seq, event, flags, AF_UNSPEC, + NFNETLINK_V0, 0); + if (!nlh) goto nlmsg_failure; - nfmsg = nlmsg_data(nlh); - nfmsg->nfgen_family = AF_UNSPEC; - nfmsg->version = NFNETLINK_V0; - nfmsg->res_id = 0; - if (nla_put_string(skb, CTA_TIMEOUT_NAME, timeout->name) || nla_put_be16(skb, CTA_TIMEOUT_L3PROTO, htons(timeout->timeout.l3num)) || @@ -206,6 +213,7 @@ nla_put_failure: static int ctnl_timeout_dump(struct sk_buff *skb, struct netlink_callback *cb) { + struct nfct_timeout_pernet *pernet; struct net *net = sock_net(skb->sk); struct ctnl_timeout *cur, *last; @@ -217,7 +225,8 @@ ctnl_timeout_dump(struct sk_buff *skb, struct netlink_callback *cb) cb->args[1] = 0; rcu_read_lock(); - list_for_each_entry_rcu(cur, &net->nfct_timeout_list, head) { + pernet = nfct_timeout_pernet(net); + list_for_each_entry_rcu(cur, &pernet->nfct_timeout_list, head) { if (last) { if (cur != last) continue; @@ -238,28 +247,27 @@ ctnl_timeout_dump(struct sk_buff *skb, struct netlink_callback *cb) return skb->len; } -static int cttimeout_get_timeout(struct net *net, struct sock *ctnl, - struct sk_buff *skb, - const struct nlmsghdr *nlh, - const struct nlattr * const cda[], - struct netlink_ext_ack *extack) +static int cttimeout_get_timeout(struct sk_buff *skb, + const struct nfnl_info *info, + const struct nlattr * const cda[]) { + struct nfct_timeout_pernet *pernet = nfct_timeout_pernet(info->net); int ret = -ENOENT; char *name; struct ctnl_timeout *cur; - if (nlh->nlmsg_flags & NLM_F_DUMP) { + if (info->nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { .dump = ctnl_timeout_dump, }; - return netlink_dump_start(ctnl, skb, nlh, &c); + return netlink_dump_start(info->sk, skb, info->nlh, &c); } if (!cda[CTA_TIMEOUT_NAME]) return -EINVAL; name = nla_data(cda[CTA_TIMEOUT_NAME]); - list_for_each_entry(cur, &net->nfct_timeout_list, head) { + list_for_each_entry(cur, &pernet->nfct_timeout_list, head) { struct sk_buff *skb2; if (strncmp(cur->name, name, CTNL_TIMEOUT_NAME_MAX) != 0) @@ -272,15 +280,15 @@ static int cttimeout_get_timeout(struct net *net, struct sock *ctnl, } ret = ctnl_timeout_fill_info(skb2, NETLINK_CB(skb).portid, - nlh->nlmsg_seq, - NFNL_MSG_TYPE(nlh->nlmsg_type), + info->nlh->nlmsg_seq, + NFNL_MSG_TYPE(info->nlh->nlmsg_type), IPCTNL_MSG_TIMEOUT_NEW, cur); if (ret <= 0) { kfree_skb(skb2); break; } - ret = netlink_unicast(ctnl, skb2, NETLINK_CB(skb).portid, - MSG_DONTWAIT); + ret = netlink_unicast(info->sk, skb2, NETLINK_CB(skb).portid, + MSG_DONTWAIT); if (ret > 0) ret = 0; @@ -309,30 +317,29 @@ static int ctnl_timeout_try_del(struct net *net, struct ctnl_timeout *timeout) return ret; } -static int cttimeout_del_timeout(struct net *net, struct sock *ctnl, - struct sk_buff *skb, - const struct nlmsghdr *nlh, - const struct nlattr * const cda[], - struct netlink_ext_ack *extack) +static int cttimeout_del_timeout(struct sk_buff *skb, + const struct nfnl_info *info, + const struct nlattr * const cda[]) { + struct nfct_timeout_pernet *pernet = nfct_timeout_pernet(info->net); struct ctnl_timeout *cur, *tmp; int ret = -ENOENT; char *name; if (!cda[CTA_TIMEOUT_NAME]) { - list_for_each_entry_safe(cur, tmp, &net->nfct_timeout_list, + list_for_each_entry_safe(cur, tmp, &pernet->nfct_timeout_list, head) - ctnl_timeout_try_del(net, cur); + ctnl_timeout_try_del(info->net, cur); return 0; } name = nla_data(cda[CTA_TIMEOUT_NAME]); - list_for_each_entry(cur, &net->nfct_timeout_list, head) { + list_for_each_entry(cur, &pernet->nfct_timeout_list, head) { if (strncmp(cur->name, name, CTNL_TIMEOUT_NAME_MAX) != 0) continue; - ret = ctnl_timeout_try_del(net, cur); + ret = ctnl_timeout_try_del(info->net, cur); if (ret < 0) return ret; @@ -341,11 +348,9 @@ static int cttimeout_del_timeout(struct net *net, struct sock *ctnl, return ret; } -static int cttimeout_default_set(struct net *net, struct sock *ctnl, - struct sk_buff *skb, - const struct nlmsghdr *nlh, - const struct nlattr * const cda[], - struct netlink_ext_ack *extack) +static int cttimeout_default_set(struct sk_buff *skb, + const struct nfnl_info *info, + const struct nlattr * const cda[]) { const struct nf_conntrack_l4proto *l4proto; __u8 l4num; @@ -365,7 +370,7 @@ static int cttimeout_default_set(struct net *net, struct sock *ctnl, goto err; } - ret = ctnl_timeout_parse_policy(NULL, l4proto, net, + ret = ctnl_timeout_parse_policy(NULL, l4proto, info->net, cda[CTA_TIMEOUT_DATA]); if (ret < 0) goto err; @@ -382,21 +387,16 @@ cttimeout_default_fill_info(struct net *net, struct sk_buff *skb, u32 portid, const unsigned int *timeouts) { struct nlmsghdr *nlh; - struct nfgenmsg *nfmsg; unsigned int flags = portid ? NLM_F_MULTI : 0; struct nlattr *nest_parms; int ret; event = nfnl_msg_type(NFNL_SUBSYS_CTNETLINK_TIMEOUT, event); - nlh = nlmsg_put(skb, portid, seq, event, sizeof(*nfmsg), flags); - if (nlh == NULL) + nlh = nfnl_msg_put(skb, portid, seq, event, flags, AF_UNSPEC, + NFNETLINK_V0, 0); + if (!nlh) goto nlmsg_failure; - nfmsg = nlmsg_data(nlh); - nfmsg->nfgen_family = AF_UNSPEC; - nfmsg->version = NFNETLINK_V0; - nfmsg->res_id = 0; - if (nla_put_be16(skb, CTA_TIMEOUT_L3PROTO, htons(l3num)) || nla_put_u8(skb, CTA_TIMEOUT_L4PROTO, l4proto->l4proto)) goto nla_put_failure; @@ -420,11 +420,9 @@ nla_put_failure: return -1; } -static int cttimeout_default_get(struct net *net, struct sock *ctnl, - struct sk_buff *skb, - const struct nlmsghdr *nlh, - const struct nlattr * const cda[], - struct netlink_ext_ack *extack) +static int cttimeout_default_get(struct sk_buff *skb, + const struct nfnl_info *info, + const struct nlattr * const cda[]) { const struct nf_conntrack_l4proto *l4proto; unsigned int *timeouts = NULL; @@ -446,35 +444,35 @@ static int cttimeout_default_get(struct net *net, struct sock *ctnl, switch (l4proto->l4proto) { case IPPROTO_ICMP: - timeouts = &nf_icmp_pernet(net)->timeout; + timeouts = &nf_icmp_pernet(info->net)->timeout; break; case IPPROTO_TCP: - timeouts = nf_tcp_pernet(net)->timeouts; + timeouts = nf_tcp_pernet(info->net)->timeouts; break; case IPPROTO_UDP: case IPPROTO_UDPLITE: - timeouts = nf_udp_pernet(net)->timeouts; + timeouts = nf_udp_pernet(info->net)->timeouts; break; case IPPROTO_DCCP: #ifdef CONFIG_NF_CT_PROTO_DCCP - timeouts = nf_dccp_pernet(net)->dccp_timeout; + timeouts = nf_dccp_pernet(info->net)->dccp_timeout; #endif break; case IPPROTO_ICMPV6: - timeouts = &nf_icmpv6_pernet(net)->timeout; + timeouts = &nf_icmpv6_pernet(info->net)->timeout; break; case IPPROTO_SCTP: #ifdef CONFIG_NF_CT_PROTO_SCTP - timeouts = nf_sctp_pernet(net)->timeouts; + timeouts = nf_sctp_pernet(info->net)->timeouts; #endif break; case IPPROTO_GRE: #ifdef CONFIG_NF_CT_PROTO_GRE - timeouts = nf_gre_pernet(net)->timeouts; + timeouts = nf_gre_pernet(info->net)->timeouts; #endif break; case 255: - timeouts = &nf_generic_pernet(net)->timeout; + timeouts = &nf_generic_pernet(info->net)->timeout; break; default: WARN_ONCE(1, "Missing timeouts for proto %d", l4proto->l4proto); @@ -490,9 +488,10 @@ static int cttimeout_default_get(struct net *net, struct sock *ctnl, goto err; } - ret = cttimeout_default_fill_info(net, skb2, NETLINK_CB(skb).portid, - nlh->nlmsg_seq, - NFNL_MSG_TYPE(nlh->nlmsg_type), + ret = cttimeout_default_fill_info(info->net, skb2, + NETLINK_CB(skb).portid, + info->nlh->nlmsg_seq, + NFNL_MSG_TYPE(info->nlh->nlmsg_type), IPCTNL_MSG_TIMEOUT_DEFAULT_SET, l3num, l4proto, timeouts); if (ret <= 0) { @@ -500,7 +499,8 @@ static int cttimeout_default_get(struct net *net, struct sock *ctnl, err = -ENOMEM; goto err; } - ret = netlink_unicast(ctnl, skb2, NETLINK_CB(skb).portid, MSG_DONTWAIT); + ret = netlink_unicast(info->sk, skb2, NETLINK_CB(skb).portid, + MSG_DONTWAIT); if (ret > 0) ret = 0; @@ -513,9 +513,10 @@ err: static struct nf_ct_timeout *ctnl_timeout_find_get(struct net *net, const char *name) { + struct nfct_timeout_pernet *pernet = nfct_timeout_pernet(net); struct ctnl_timeout *timeout, *matching = NULL; - list_for_each_entry_rcu(timeout, &net->nfct_timeout_list, head) { + list_for_each_entry_rcu(timeout, &pernet->nfct_timeout_list, head) { if (strncmp(timeout->name, name, CTNL_TIMEOUT_NAME_MAX) != 0) continue; @@ -545,21 +546,36 @@ static void ctnl_timeout_put(struct nf_ct_timeout *t) } static const struct nfnl_callback cttimeout_cb[IPCTNL_MSG_TIMEOUT_MAX] = { - [IPCTNL_MSG_TIMEOUT_NEW] = { .call = cttimeout_new_timeout, - .attr_count = CTA_TIMEOUT_MAX, - .policy = cttimeout_nla_policy }, - [IPCTNL_MSG_TIMEOUT_GET] = { .call = cttimeout_get_timeout, - .attr_count = CTA_TIMEOUT_MAX, - .policy = cttimeout_nla_policy }, - [IPCTNL_MSG_TIMEOUT_DELETE] = { .call = cttimeout_del_timeout, - .attr_count = CTA_TIMEOUT_MAX, - .policy = cttimeout_nla_policy }, - [IPCTNL_MSG_TIMEOUT_DEFAULT_SET]= { .call = cttimeout_default_set, - .attr_count = CTA_TIMEOUT_MAX, - .policy = cttimeout_nla_policy }, - [IPCTNL_MSG_TIMEOUT_DEFAULT_GET]= { .call = cttimeout_default_get, - .attr_count = CTA_TIMEOUT_MAX, - .policy = cttimeout_nla_policy }, + [IPCTNL_MSG_TIMEOUT_NEW] = { + .call = cttimeout_new_timeout, + .type = NFNL_CB_MUTEX, + .attr_count = CTA_TIMEOUT_MAX, + .policy = cttimeout_nla_policy + }, + [IPCTNL_MSG_TIMEOUT_GET] = { + .call = cttimeout_get_timeout, + .type = NFNL_CB_MUTEX, + .attr_count = CTA_TIMEOUT_MAX, + .policy = cttimeout_nla_policy + }, + [IPCTNL_MSG_TIMEOUT_DELETE] = { + .call = cttimeout_del_timeout, + .type = NFNL_CB_MUTEX, + .attr_count = CTA_TIMEOUT_MAX, + .policy = cttimeout_nla_policy + }, + [IPCTNL_MSG_TIMEOUT_DEFAULT_SET] = { + .call = cttimeout_default_set, + .type = NFNL_CB_MUTEX, + .attr_count = CTA_TIMEOUT_MAX, + .policy = cttimeout_nla_policy + }, + [IPCTNL_MSG_TIMEOUT_DEFAULT_GET] = { + .call = cttimeout_default_get, + .type = NFNL_CB_MUTEX, + .attr_count = CTA_TIMEOUT_MAX, + .policy = cttimeout_nla_policy + }, }; static const struct nfnetlink_subsystem cttimeout_subsys = { @@ -573,19 +589,22 @@ MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_CTNETLINK_TIMEOUT); static int __net_init cttimeout_net_init(struct net *net) { - INIT_LIST_HEAD(&net->nfct_timeout_list); + struct nfct_timeout_pernet *pernet = nfct_timeout_pernet(net); + + INIT_LIST_HEAD(&pernet->nfct_timeout_list); return 0; } static void __net_exit cttimeout_net_exit(struct net *net) { + struct nfct_timeout_pernet *pernet = nfct_timeout_pernet(net); struct ctnl_timeout *cur, *tmp; nf_ct_unconfirmed_destroy(net); nf_ct_untimeout(net, NULL); - list_for_each_entry_safe(cur, tmp, &net->nfct_timeout_list, head) { + list_for_each_entry_safe(cur, tmp, &pernet->nfct_timeout_list, head) { list_del_rcu(&cur->head); if (refcount_dec_and_test(&cur->refcnt)) @@ -596,6 +615,8 @@ static void __net_exit cttimeout_net_exit(struct net *net) static struct pernet_operations cttimeout_ops = { .init = cttimeout_net_init, .exit = cttimeout_net_exit, + .id = &nfct_timeout_id, + .size = sizeof(struct nfct_timeout_pernet), }; static int __init cttimeout_init(void) diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index 26776b88a539..587086b18c36 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -456,20 +456,15 @@ __build_packet_message(struct nfnl_log_net *log, { struct nfulnl_msg_packet_hdr pmsg; struct nlmsghdr *nlh; - 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_msg_type(NFNL_SUBSYS_ULOG, NFULNL_MSG_PACKET), - sizeof(struct nfgenmsg), 0); + nlh = nfnl_msg_put(inst->skb, 0, 0, + nfnl_msg_type(NFNL_SUBSYS_ULOG, NFULNL_MSG_PACKET), + 0, pf, NFNETLINK_V0, htons(inst->group_num)); if (!nlh) return -1; - nfmsg = nlmsg_data(nlh); - nfmsg->nfgen_family = pf; - nfmsg->version = NFNETLINK_V0; - nfmsg->res_id = htons(inst->group_num); memset(&pmsg, 0, sizeof(pmsg)); pmsg.hw_protocol = skb->protocol; @@ -850,10 +845,8 @@ static struct notifier_block nfulnl_rtnl_notifier = { .notifier_call = nfulnl_rcv_nl_event, }; -static int nfulnl_recv_unsupp(struct net *net, struct sock *ctnl, - struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nfqa[], - struct netlink_ext_ack *extack) +static int nfulnl_recv_unsupp(struct sk_buff *skb, const struct nfnl_info *info, + const struct nlattr * const nfula[]) { return -ENOTSUPP; } @@ -874,18 +867,16 @@ static const struct nla_policy nfula_cfg_policy[NFULA_CFG_MAX+1] = { [NFULA_CFG_FLAGS] = { .type = NLA_U16 }, }; -static int nfulnl_recv_config(struct net *net, struct sock *ctnl, - struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nfula[], - struct netlink_ext_ack *extack) +static int nfulnl_recv_config(struct sk_buff *skb, const struct nfnl_info *info, + const struct nlattr * const nfula[]) { - struct nfgenmsg *nfmsg = nlmsg_data(nlh); + struct nfnl_log_net *log = nfnl_log_pernet(info->net); + struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); u_int16_t group_num = ntohs(nfmsg->res_id); - struct nfulnl_instance *inst; struct nfulnl_msg_config_cmd *cmd = NULL; - struct nfnl_log_net *log = nfnl_log_pernet(net); - int ret = 0; + struct nfulnl_instance *inst; u16 flags = 0; + int ret = 0; if (nfula[NFULA_CFG_CMD]) { u_int8_t pf = nfmsg->nfgen_family; @@ -894,9 +885,9 @@ static int nfulnl_recv_config(struct net *net, struct sock *ctnl, /* Commands without queue context */ switch (cmd->command) { case NFULNL_CFG_CMD_PF_BIND: - return nf_log_bind_pf(net, pf, &nfulnl_logger); + return nf_log_bind_pf(info->net, pf, &nfulnl_logger); case NFULNL_CFG_CMD_PF_UNBIND: - nf_log_unbind_pf(net, pf); + nf_log_unbind_pf(info->net, pf); return 0; } } @@ -937,7 +928,7 @@ static int nfulnl_recv_config(struct net *net, struct sock *ctnl, goto out_put; } - inst = instance_create(net, group_num, + inst = instance_create(info->net, group_num, NETLINK_CB(skb).portid, sk_user_ns(NETLINK_CB(skb).sk)); if (IS_ERR(inst)) { @@ -998,11 +989,17 @@ out: } static const struct nfnl_callback nfulnl_cb[NFULNL_MSG_MAX] = { - [NFULNL_MSG_PACKET] = { .call = nfulnl_recv_unsupp, - .attr_count = NFULA_MAX, }, - [NFULNL_MSG_CONFIG] = { .call = nfulnl_recv_config, - .attr_count = NFULA_CFG_MAX, - .policy = nfula_cfg_policy }, + [NFULNL_MSG_PACKET] = { + .call = nfulnl_recv_unsupp, + .type = NFNL_CB_MUTEX, + .attr_count = NFULA_MAX, + }, + [NFULNL_MSG_CONFIG] = { + .call = nfulnl_recv_config, + .type = NFNL_CB_MUTEX, + .attr_count = NFULA_CFG_MAX, + .policy = nfula_cfg_policy + }, }; static const struct nfnetlink_subsystem nfulnl_subsys = { diff --git a/net/netfilter/nfnetlink_osf.c b/net/netfilter/nfnetlink_osf.c index 916a3c7f9eaf..e8f8875c6884 100644 --- a/net/netfilter/nfnetlink_osf.c +++ b/net/netfilter/nfnetlink_osf.c @@ -292,10 +292,9 @@ static const struct nla_policy nfnl_osf_policy[OSF_ATTR_MAX + 1] = { [OSF_ATTR_FINGER] = { .len = sizeof(struct nf_osf_user_finger) }, }; -static int nfnl_osf_add_callback(struct net *net, struct sock *ctnl, - struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const osf_attrs[], - struct netlink_ext_ack *extack) +static int nfnl_osf_add_callback(struct sk_buff *skb, + const struct nfnl_info *info, + const struct nlattr * const osf_attrs[]) { struct nf_osf_user_finger *f; struct nf_osf_finger *kf = NULL, *sf; @@ -307,7 +306,7 @@ static int nfnl_osf_add_callback(struct net *net, struct sock *ctnl, if (!osf_attrs[OSF_ATTR_FINGER]) return -EINVAL; - if (!(nlh->nlmsg_flags & NLM_F_CREATE)) + if (!(info->nlh->nlmsg_flags & NLM_F_CREATE)) return -EINVAL; f = nla_data(osf_attrs[OSF_ATTR_FINGER]); @@ -325,7 +324,7 @@ static int nfnl_osf_add_callback(struct net *net, struct sock *ctnl, kfree(kf); kf = NULL; - if (nlh->nlmsg_flags & NLM_F_EXCL) + if (info->nlh->nlmsg_flags & NLM_F_EXCL) err = -EEXIST; break; } @@ -339,11 +338,9 @@ static int nfnl_osf_add_callback(struct net *net, struct sock *ctnl, return err; } -static int nfnl_osf_remove_callback(struct net *net, struct sock *ctnl, - struct sk_buff *skb, - const struct nlmsghdr *nlh, - const struct nlattr * const osf_attrs[], - struct netlink_ext_ack *extack) +static int nfnl_osf_remove_callback(struct sk_buff *skb, + const struct nfnl_info *info, + const struct nlattr * const osf_attrs[]) { struct nf_osf_user_finger *f; struct nf_osf_finger *sf; @@ -377,11 +374,13 @@ static int nfnl_osf_remove_callback(struct net *net, struct sock *ctnl, static const struct nfnl_callback nfnl_osf_callbacks[OSF_MSG_MAX] = { [OSF_MSG_ADD] = { .call = nfnl_osf_add_callback, + .type = NFNL_CB_MUTEX, .attr_count = OSF_ATTR_MAX, .policy = nfnl_osf_policy, }, [OSF_MSG_REMOVE] = { .call = nfnl_osf_remove_callback, + .type = NFNL_CB_MUTEX, .attr_count = OSF_ATTR_MAX, .policy = nfnl_osf_policy, }, diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index 48a07914fd94..f37a575ebd7f 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -383,7 +383,6 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, struct nlattr *nla; struct nfqnl_msg_packet_hdr *pmsg; struct nlmsghdr *nlh; - struct nfgenmsg *nfmsg; struct sk_buff *entskb = entry->skb; struct net_device *indev; struct net_device *outdev; @@ -471,18 +470,15 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, goto nlmsg_failure; } - nlh = nlmsg_put(skb, 0, 0, - nfnl_msg_type(NFNL_SUBSYS_QUEUE, NFQNL_MSG_PACKET), - sizeof(struct nfgenmsg), 0); + nlh = nfnl_msg_put(skb, 0, 0, + nfnl_msg_type(NFNL_SUBSYS_QUEUE, NFQNL_MSG_PACKET), + 0, entry->state.pf, NFNETLINK_V0, + htons(queue->queue_num)); if (!nlh) { skb_tx_error(entskb); kfree_skb(skb); goto nlmsg_failure; } - nfmsg = nlmsg_data(nlh); - nfmsg->nfgen_family = entry->state.pf; - nfmsg->version = NFNETLINK_V0; - nfmsg->res_id = htons(queue->queue_num); nla = __nla_reserve(skb, NFQA_PACKET_HDR, sizeof(*pmsg)); pmsg = nla_data(nla); @@ -1050,20 +1046,18 @@ static int nfq_id_after(unsigned int id, unsigned int max) return (int)(id - max) > 0; } -static int nfqnl_recv_verdict_batch(struct net *net, struct sock *ctnl, - struct sk_buff *skb, - const struct nlmsghdr *nlh, - const struct nlattr * const nfqa[], - struct netlink_ext_ack *extack) +static int nfqnl_recv_verdict_batch(struct sk_buff *skb, + const struct nfnl_info *info, + const struct nlattr * const nfqa[]) { - struct nfgenmsg *nfmsg = nlmsg_data(nlh); + struct nfnl_queue_net *q = nfnl_queue_pernet(info->net); + struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); + u16 queue_num = ntohs(nfmsg->res_id); struct nf_queue_entry *entry, *tmp; - unsigned int verdict, maxid; struct nfqnl_msg_verdict_hdr *vhdr; struct nfqnl_instance *queue; + unsigned int verdict, maxid; LIST_HEAD(batch_list); - u16 queue_num = ntohs(nfmsg->res_id); - struct nfnl_queue_net *q = nfnl_queue_pernet(net); queue = verdict_instance_lookup(q, queue_num, NETLINK_CB(skb).portid); @@ -1162,22 +1156,19 @@ static int nfqa_parse_bridge(struct nf_queue_entry *entry, return 0; } -static int nfqnl_recv_verdict(struct net *net, struct sock *ctnl, - struct sk_buff *skb, - const struct nlmsghdr *nlh, - const struct nlattr * const nfqa[], - struct netlink_ext_ack *extack) +static int nfqnl_recv_verdict(struct sk_buff *skb, const struct nfnl_info *info, + const struct nlattr * const nfqa[]) { - struct nfgenmsg *nfmsg = nlmsg_data(nlh); + struct nfnl_queue_net *q = nfnl_queue_pernet(info->net); + struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); u_int16_t queue_num = ntohs(nfmsg->res_id); struct nfqnl_msg_verdict_hdr *vhdr; + enum ip_conntrack_info ctinfo; struct nfqnl_instance *queue; - unsigned int verdict; struct nf_queue_entry *entry; - enum ip_conntrack_info ctinfo; struct nfnl_ct_hook *nfnl_ct; struct nf_conn *ct = NULL; - struct nfnl_queue_net *q = nfnl_queue_pernet(net); + unsigned int verdict; int err; queue = verdict_instance_lookup(q, queue_num, @@ -1200,7 +1191,8 @@ static int nfqnl_recv_verdict(struct net *net, struct sock *ctnl, if (nfqa[NFQA_CT]) { if (nfnl_ct != NULL) - ct = nfqnl_ct_parse(nfnl_ct, nlh, nfqa, entry, &ctinfo); + ct = nfqnl_ct_parse(nfnl_ct, info->nlh, nfqa, entry, + &ctinfo); } if (entry->state.pf == PF_BRIDGE) { @@ -1228,10 +1220,8 @@ static int nfqnl_recv_verdict(struct net *net, struct sock *ctnl, return 0; } -static int nfqnl_recv_unsupp(struct net *net, struct sock *ctnl, - struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nfqa[], - struct netlink_ext_ack *extack) +static int nfqnl_recv_unsupp(struct sk_buff *skb, const struct nfnl_info *info, + const struct nlattr * const cda[]) { return -ENOTSUPP; } @@ -1249,16 +1239,14 @@ static const struct nf_queue_handler nfqh = { .nf_hook_drop = nfqnl_nf_hook_drop, }; -static int nfqnl_recv_config(struct net *net, struct sock *ctnl, - struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nfqa[], - struct netlink_ext_ack *extack) +static int nfqnl_recv_config(struct sk_buff *skb, const struct nfnl_info *info, + const struct nlattr * const nfqa[]) { - struct nfgenmsg *nfmsg = nlmsg_data(nlh); + struct nfnl_queue_net *q = nfnl_queue_pernet(info->net); + struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); u_int16_t queue_num = ntohs(nfmsg->res_id); - struct nfqnl_instance *queue; struct nfqnl_msg_config_cmd *cmd = NULL; - struct nfnl_queue_net *q = nfnl_queue_pernet(net); + struct nfqnl_instance *queue; __u32 flags = 0, mask = 0; int ret = 0; @@ -1377,17 +1365,29 @@ err_out_unlock: } static const struct nfnl_callback nfqnl_cb[NFQNL_MSG_MAX] = { - [NFQNL_MSG_PACKET] = { .call_rcu = nfqnl_recv_unsupp, - .attr_count = NFQA_MAX, }, - [NFQNL_MSG_VERDICT] = { .call_rcu = nfqnl_recv_verdict, - .attr_count = NFQA_MAX, - .policy = nfqa_verdict_policy }, - [NFQNL_MSG_CONFIG] = { .call = nfqnl_recv_config, - .attr_count = NFQA_CFG_MAX, - .policy = nfqa_cfg_policy }, - [NFQNL_MSG_VERDICT_BATCH]={ .call_rcu = nfqnl_recv_verdict_batch, - .attr_count = NFQA_MAX, - .policy = nfqa_verdict_batch_policy }, + [NFQNL_MSG_PACKET] = { + .call = nfqnl_recv_unsupp, + .type = NFNL_CB_RCU, + .attr_count = NFQA_MAX, + }, + [NFQNL_MSG_VERDICT] = { + .call = nfqnl_recv_verdict, + .type = NFNL_CB_RCU, + .attr_count = NFQA_MAX, + .policy = nfqa_verdict_policy + }, + [NFQNL_MSG_CONFIG] = { + .call = nfqnl_recv_config, + .type = NFNL_CB_MUTEX, + .attr_count = NFQA_CFG_MAX, + .policy = nfqa_cfg_policy + }, + [NFQNL_MSG_VERDICT_BATCH] = { + .call = nfqnl_recv_verdict_batch, + .type = NFNL_CB_RCU, + .attr_count = NFQA_MAX, + .policy = nfqa_verdict_batch_policy + }, }; static const struct nfnetlink_subsystem nfqnl_subsys = { diff --git a/net/netfilter/nft_chain_filter.c b/net/netfilter/nft_chain_filter.c index ff8528ad3dc6..363bdd7044ec 100644 --- a/net/netfilter/nft_chain_filter.c +++ b/net/netfilter/nft_chain_filter.c @@ -355,6 +355,7 @@ static int nf_tables_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); + struct nftables_pernet *nft_net; struct nft_table *table; struct nft_chain *chain, *nr; struct nft_ctx ctx = { @@ -365,8 +366,9 @@ static int nf_tables_netdev_event(struct notifier_block *this, event != NETDEV_CHANGENAME) return NOTIFY_DONE; - mutex_lock(&ctx.net->nft.commit_mutex); - list_for_each_entry(table, &ctx.net->nft.tables, list) { + nft_net = nft_pernet(ctx.net); + mutex_lock(&nft_net->commit_mutex); + list_for_each_entry(table, &nft_net->tables, list) { if (table->family != NFPROTO_NETDEV) continue; @@ -380,7 +382,7 @@ static int nf_tables_netdev_event(struct notifier_block *this, nft_netdev_event(event, dev, &ctx); } } - mutex_unlock(&ctx.net->nft.commit_mutex); + mutex_unlock(&nft_net->commit_mutex); return NOTIFY_DONE; } diff --git a/net/netfilter/nft_cmp.c b/net/netfilter/nft_cmp.c index eb6a43a180bb..47b6d05f1ae6 100644 --- a/net/netfilter/nft_cmp.c +++ b/net/netfilter/nft_cmp.c @@ -114,19 +114,56 @@ nla_put_failure: return -1; } +union nft_cmp_offload_data { + u16 val16; + u32 val32; + u64 val64; +}; + +static void nft_payload_n2h(union nft_cmp_offload_data *data, + const u8 *val, u32 len) +{ + switch (len) { + case 2: + data->val16 = ntohs(*((u16 *)val)); + break; + case 4: + data->val32 = ntohl(*((u32 *)val)); + break; + case 8: + data->val64 = be64_to_cpu(*((u64 *)val)); + break; + default: + WARN_ON_ONCE(1); + break; + } +} + static int __nft_cmp_offload(struct nft_offload_ctx *ctx, struct nft_flow_rule *flow, const struct nft_cmp_expr *priv) { struct nft_offload_reg *reg = &ctx->regs[priv->sreg]; + union nft_cmp_offload_data _data, _datamask; u8 *mask = (u8 *)&flow->match.mask; u8 *key = (u8 *)&flow->match.key; + u8 *data, *datamask; if (priv->op != NFT_CMP_EQ || priv->len > reg->len) return -EOPNOTSUPP; - memcpy(key + reg->offset, &priv->data, reg->len); - memcpy(mask + reg->offset, ®->mask, reg->len); + if (reg->flags & NFT_OFFLOAD_F_NETWORK2HOST) { + nft_payload_n2h(&_data, (u8 *)&priv->data, reg->len); + nft_payload_n2h(&_datamask, (u8 *)®->mask, reg->len); + data = (u8 *)&_data; + datamask = (u8 *)&_datamask; + } else { + data = (u8 *)&priv->data; + datamask = (u8 *)®->mask; + } + + memcpy(key + reg->offset, data, reg->len); + memcpy(mask + reg->offset, datamask, reg->len); flow->match.dissector.used_keys |= BIT(reg->key); flow->match.dissector.offset[reg->key] = reg->base_offset; diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c index 8e56f353ff35..5415ab14400d 100644 --- a/net/netfilter/nft_compat.c +++ b/net/netfilter/nft_compat.c @@ -591,19 +591,14 @@ nfnl_compat_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type, int rev, int target) { struct nlmsghdr *nlh; - struct nfgenmsg *nfmsg; unsigned int flags = portid ? NLM_F_MULTI : 0; event = nfnl_msg_type(NFNL_SUBSYS_NFT_COMPAT, event); - nlh = nlmsg_put(skb, portid, seq, event, sizeof(*nfmsg), flags); - if (nlh == NULL) + nlh = nfnl_msg_put(skb, portid, seq, event, flags, family, + NFNETLINK_V0, 0); + if (!nlh) goto nlmsg_failure; - nfmsg = nlmsg_data(nlh); - nfmsg->nfgen_family = family; - nfmsg->version = NFNETLINK_V0; - nfmsg->res_id = 0; - if (nla_put_string(skb, NFTA_COMPAT_NAME, name) || nla_put_be32(skb, NFTA_COMPAT_REV, htonl(rev)) || nla_put_be32(skb, NFTA_COMPAT_TYPE, htonl(target))) @@ -618,17 +613,15 @@ nla_put_failure: return -1; } -static int nfnl_compat_get_rcu(struct net *net, struct sock *nfnl, - struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const tb[], - struct netlink_ext_ack *extack) +static int nfnl_compat_get_rcu(struct sk_buff *skb, + const struct nfnl_info *info, + const struct nlattr * const tb[]) { - int ret = 0, target; struct nfgenmsg *nfmsg; - const char *fmt; - const char *name; - u32 rev; + const char *name, *fmt; struct sk_buff *skb2; + int ret = 0, target; + u32 rev; if (tb[NFTA_COMPAT_NAME] == NULL || tb[NFTA_COMPAT_REV] == NULL || @@ -639,7 +632,7 @@ static int nfnl_compat_get_rcu(struct net *net, struct sock *nfnl, rev = ntohl(nla_get_be32(tb[NFTA_COMPAT_REV])); target = ntohl(nla_get_be32(tb[NFTA_COMPAT_TYPE])); - nfmsg = nlmsg_data(nlh); + nfmsg = nlmsg_data(info->nlh); switch(nfmsg->nfgen_family) { case AF_INET: @@ -678,8 +671,8 @@ static int nfnl_compat_get_rcu(struct net *net, struct sock *nfnl, /* include the best revision for this extension in the message */ if (nfnl_compat_fill_info(skb2, NETLINK_CB(skb).portid, - nlh->nlmsg_seq, - NFNL_MSG_TYPE(nlh->nlmsg_type), + info->nlh->nlmsg_seq, + NFNL_MSG_TYPE(info->nlh->nlmsg_type), NFNL_MSG_COMPAT_GET, nfmsg->nfgen_family, name, ret, target) <= 0) { @@ -687,8 +680,8 @@ static int nfnl_compat_get_rcu(struct net *net, struct sock *nfnl, goto out_put; } - ret = netlink_unicast(nfnl, skb2, NETLINK_CB(skb).portid, - MSG_DONTWAIT); + ret = netlink_unicast(info->sk, skb2, NETLINK_CB(skb).portid, + MSG_DONTWAIT); if (ret > 0) ret = 0; out_put: @@ -705,9 +698,12 @@ static const struct nla_policy nfnl_compat_policy_get[NFTA_COMPAT_MAX+1] = { }; static const struct nfnl_callback nfnl_nft_compat_cb[NFNL_MSG_COMPAT_MAX] = { - [NFNL_MSG_COMPAT_GET] = { .call_rcu = nfnl_compat_get_rcu, - .attr_count = NFTA_COMPAT_MAX, - .policy = nfnl_compat_policy_get }, + [NFNL_MSG_COMPAT_GET] = { + .call = nfnl_compat_get_rcu, + .type = NFNL_CB_RCU, + .attr_count = NFTA_COMPAT_MAX, + .policy = nfnl_compat_policy_get + }, }; static const struct nfnetlink_subsystem nfnl_compat_subsys = { diff --git a/net/netfilter/nft_counter.c b/net/netfilter/nft_counter.c index 85ed461ec24e..8edd3b3c173d 100644 --- a/net/netfilter/nft_counter.c +++ b/net/netfilter/nft_counter.c @@ -13,6 +13,7 @@ #include <linux/netfilter.h> #include <linux/netfilter/nf_tables.h> #include <net/netfilter/nf_tables.h> +#include <net/netfilter/nf_tables_offload.h> struct nft_counter { s64 bytes; @@ -248,6 +249,32 @@ static int nft_counter_clone(struct nft_expr *dst, const struct nft_expr *src) return 0; } +static int nft_counter_offload(struct nft_offload_ctx *ctx, + struct nft_flow_rule *flow, + const struct nft_expr *expr) +{ + /* No specific offload action is needed, but report success. */ + return 0; +} + +static void nft_counter_offload_stats(struct nft_expr *expr, + const struct flow_stats *stats) +{ + struct nft_counter_percpu_priv *priv = nft_expr_priv(expr); + struct nft_counter *this_cpu; + seqcount_t *myseq; + + preempt_disable(); + this_cpu = this_cpu_ptr(priv->counter); + myseq = this_cpu_ptr(&nft_counter_seq); + + write_seqcount_begin(myseq); + this_cpu->packets += stats->pkts; + this_cpu->bytes += stats->bytes; + write_seqcount_end(myseq); + preempt_enable(); +} + static struct nft_expr_type nft_counter_type; static const struct nft_expr_ops nft_counter_ops = { .type = &nft_counter_type, @@ -258,6 +285,8 @@ static const struct nft_expr_ops nft_counter_ops = { .destroy_clone = nft_counter_destroy, .dump = nft_counter_dump, .clone = nft_counter_clone, + .offload = nft_counter_offload, + .offload_stats = nft_counter_offload_stats, }; static struct nft_expr_type nft_counter_type __read_mostly = { diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index 882fe8648653..0592a9456084 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -527,6 +527,7 @@ static void __nft_ct_set_destroy(const struct nft_ctx *ctx, struct nft_ct *priv) case NFT_CT_ZONE: if (--nft_ct_pcpu_template_refcnt == 0) nft_ct_tmpl_put_pcpu(); + break; #endif default: break; diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c index d44a70c11b3f..6ba3256fa844 100644 --- a/net/netfilter/nft_dynset.c +++ b/net/netfilter/nft_dynset.c @@ -161,13 +161,14 @@ static int nft_dynset_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]) { + struct nftables_pernet *nft_net = nft_pernet(ctx->net); struct nft_dynset *priv = nft_expr_priv(expr); u8 genmask = nft_genmask_next(ctx->net); struct nft_set *set; u64 timeout; int err, i; - lockdep_assert_held(&ctx->net->nft.commit_mutex); + lockdep_assert_held(&nft_net->commit_mutex); if (tb[NFTA_DYNSET_SET_NAME] == NULL || tb[NFTA_DYNSET_OP] == NULL || diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c index 3a6c84fb2c90..4843dd2b410c 100644 --- a/net/netfilter/nft_flow_offload.c +++ b/net/netfilter/nft_flow_offload.c @@ -19,10 +19,205 @@ struct nft_flow_offload { struct nft_flowtable *flowtable; }; +static enum flow_offload_xmit_type nft_xmit_type(struct dst_entry *dst) +{ + if (dst_xfrm(dst)) + return FLOW_OFFLOAD_XMIT_XFRM; + + return FLOW_OFFLOAD_XMIT_NEIGH; +} + +static void nft_default_forward_path(struct nf_flow_route *route, + struct dst_entry *dst_cache, + enum ip_conntrack_dir dir) +{ + route->tuple[!dir].in.ifindex = dst_cache->dev->ifindex; + route->tuple[dir].dst = dst_cache; + route->tuple[dir].xmit_type = nft_xmit_type(dst_cache); +} + +static int nft_dev_fill_forward_path(const struct nf_flow_route *route, + const struct dst_entry *dst_cache, + const struct nf_conn *ct, + enum ip_conntrack_dir dir, u8 *ha, + struct net_device_path_stack *stack) +{ + const void *daddr = &ct->tuplehash[!dir].tuple.src.u3; + struct net_device *dev = dst_cache->dev; + struct neighbour *n; + u8 nud_state; + + n = dst_neigh_lookup(dst_cache, daddr); + if (!n) + return -1; + + read_lock_bh(&n->lock); + nud_state = n->nud_state; + ether_addr_copy(ha, n->ha); + read_unlock_bh(&n->lock); + neigh_release(n); + + if (!(nud_state & NUD_VALID)) + return -1; + + return dev_fill_forward_path(dev, ha, stack); +} + +struct nft_forward_info { + const struct net_device *indev; + const struct net_device *outdev; + const struct net_device *hw_outdev; + struct id { + __u16 id; + __be16 proto; + } encap[NF_FLOW_TABLE_ENCAP_MAX]; + u8 num_encaps; + u8 ingress_vlans; + u8 h_source[ETH_ALEN]; + u8 h_dest[ETH_ALEN]; + enum flow_offload_xmit_type xmit_type; +}; + +static bool nft_is_valid_ether_device(const struct net_device *dev) +{ + if (!dev || (dev->flags & IFF_LOOPBACK) || dev->type != ARPHRD_ETHER || + dev->addr_len != ETH_ALEN || !is_valid_ether_addr(dev->dev_addr)) + return false; + + return true; +} + +static void nft_dev_path_info(const struct net_device_path_stack *stack, + struct nft_forward_info *info, + unsigned char *ha, struct nf_flowtable *flowtable) +{ + const struct net_device_path *path; + int i; + + memcpy(info->h_dest, ha, ETH_ALEN); + + for (i = 0; i < stack->num_paths; i++) { + path = &stack->path[i]; + switch (path->type) { + case DEV_PATH_ETHERNET: + case DEV_PATH_DSA: + case DEV_PATH_VLAN: + case DEV_PATH_PPPOE: + info->indev = path->dev; + if (is_zero_ether_addr(info->h_source)) + memcpy(info->h_source, path->dev->dev_addr, ETH_ALEN); + + if (path->type == DEV_PATH_ETHERNET) + break; + if (path->type == DEV_PATH_DSA) { + i = stack->num_paths; + break; + } + + /* DEV_PATH_VLAN and DEV_PATH_PPPOE */ + if (info->num_encaps >= NF_FLOW_TABLE_ENCAP_MAX) { + info->indev = NULL; + break; + } + info->outdev = path->dev; + info->encap[info->num_encaps].id = path->encap.id; + info->encap[info->num_encaps].proto = path->encap.proto; + info->num_encaps++; + if (path->type == DEV_PATH_PPPOE) + memcpy(info->h_dest, path->encap.h_dest, ETH_ALEN); + break; + case DEV_PATH_BRIDGE: + if (is_zero_ether_addr(info->h_source)) + memcpy(info->h_source, path->dev->dev_addr, ETH_ALEN); + + switch (path->bridge.vlan_mode) { + case DEV_PATH_BR_VLAN_UNTAG_HW: + info->ingress_vlans |= BIT(info->num_encaps - 1); + break; + case DEV_PATH_BR_VLAN_TAG: + info->encap[info->num_encaps].id = path->bridge.vlan_id; + info->encap[info->num_encaps].proto = path->bridge.vlan_proto; + info->num_encaps++; + break; + case DEV_PATH_BR_VLAN_UNTAG: + info->num_encaps--; + break; + case DEV_PATH_BR_VLAN_KEEP: + break; + } + info->xmit_type = FLOW_OFFLOAD_XMIT_DIRECT; + break; + default: + info->indev = NULL; + break; + } + } + if (!info->outdev) + info->outdev = info->indev; + + info->hw_outdev = info->indev; + + if (nf_flowtable_hw_offload(flowtable) && + nft_is_valid_ether_device(info->indev)) + info->xmit_type = FLOW_OFFLOAD_XMIT_DIRECT; +} + +static bool nft_flowtable_find_dev(const struct net_device *dev, + struct nft_flowtable *ft) +{ + struct nft_hook *hook; + bool found = false; + + list_for_each_entry_rcu(hook, &ft->hook_list, list) { + if (hook->ops.dev != dev) + continue; + + found = true; + break; + } + + return found; +} + +static void nft_dev_forward_path(struct nf_flow_route *route, + const struct nf_conn *ct, + enum ip_conntrack_dir dir, + struct nft_flowtable *ft) +{ + const struct dst_entry *dst = route->tuple[dir].dst; + struct net_device_path_stack stack; + struct nft_forward_info info = {}; + unsigned char ha[ETH_ALEN]; + int i; + + if (nft_dev_fill_forward_path(route, dst, ct, dir, ha, &stack) >= 0) + nft_dev_path_info(&stack, &info, ha, &ft->data); + + if (!info.indev || !nft_flowtable_find_dev(info.indev, ft)) + return; + + route->tuple[!dir].in.ifindex = info.indev->ifindex; + for (i = 0; i < info.num_encaps; i++) { + route->tuple[!dir].in.encap[i].id = info.encap[i].id; + route->tuple[!dir].in.encap[i].proto = info.encap[i].proto; + } + route->tuple[!dir].in.num_encaps = info.num_encaps; + route->tuple[!dir].in.ingress_vlans = info.ingress_vlans; + + if (info.xmit_type == FLOW_OFFLOAD_XMIT_DIRECT) { + memcpy(route->tuple[dir].out.h_source, info.h_source, ETH_ALEN); + memcpy(route->tuple[dir].out.h_dest, info.h_dest, ETH_ALEN); + route->tuple[dir].out.ifindex = info.outdev->ifindex; + route->tuple[dir].out.hw_ifindex = info.hw_outdev->ifindex; + route->tuple[dir].xmit_type = info.xmit_type; + } +} + static int nft_flow_route(const struct nft_pktinfo *pkt, const struct nf_conn *ct, struct nf_flow_route *route, - enum ip_conntrack_dir dir) + enum ip_conntrack_dir dir, + struct nft_flowtable *ft) { struct dst_entry *this_dst = skb_dst(pkt->skb); struct dst_entry *other_dst = NULL; @@ -44,8 +239,14 @@ static int nft_flow_route(const struct nft_pktinfo *pkt, if (!other_dst) return -ENOENT; - route->tuple[dir].dst = this_dst; - route->tuple[!dir].dst = other_dst; + nft_default_forward_path(route, this_dst, dir); + nft_default_forward_path(route, other_dst, !dir); + + if (route->tuple[dir].xmit_type == FLOW_OFFLOAD_XMIT_NEIGH && + route->tuple[!dir].xmit_type == FLOW_OFFLOAD_XMIT_NEIGH) { + nft_dev_forward_path(route, ct, dir, ft); + nft_dev_forward_path(route, ct, !dir, ft); + } return 0; } @@ -74,8 +275,8 @@ static void nft_flow_offload_eval(const struct nft_expr *expr, struct nft_flow_offload *priv = nft_expr_priv(expr); struct nf_flowtable *flowtable = &priv->flowtable->data; struct tcphdr _tcph, *tcph = NULL; + struct nf_flow_route route = {}; enum ip_conntrack_info ctinfo; - struct nf_flow_route route; struct flow_offload *flow; enum ip_conntrack_dir dir; struct nf_conn *ct; @@ -112,7 +313,7 @@ static void nft_flow_offload_eval(const struct nft_expr *expr, goto out; dir = CTINFO2DIR(ctinfo); - if (nft_flow_route(pkt, ct, &route, dir) < 0) + if (nft_flow_route(pkt, ct, &route, dir, priv->flowtable) < 0) goto err_flow_route; flow = flow_offload_alloc(ct); diff --git a/net/netfilter/nft_log.c b/net/netfilter/nft_log.c index a06a46b039c5..54f6c2035e84 100644 --- a/net/netfilter/nft_log.c +++ b/net/netfilter/nft_log.c @@ -128,6 +128,20 @@ static const struct nla_policy nft_log_policy[NFTA_LOG_MAX + 1] = { [NFTA_LOG_FLAGS] = { .type = NLA_U32 }, }; +static int nft_log_modprobe(struct net *net, enum nf_log_type t) +{ + switch (t) { + case NF_LOG_TYPE_LOG: + return nft_request_module(net, "%s", "nf_log_syslog"); + case NF_LOG_TYPE_ULOG: + return nft_request_module(net, "%s", "nfnetlink_log"); + case NF_LOG_TYPE_MAX: + break; + } + + return -ENOENT; +} + static int nft_log_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]) @@ -197,8 +211,12 @@ static int nft_log_init(const struct nft_ctx *ctx, return 0; err = nf_logger_find_get(ctx->family, li->type); - if (err < 0) + if (err < 0) { + if (nft_log_modprobe(ctx->net, li->type) == -EAGAIN) + err = -EAGAIN; + goto err1; + } return 0; diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c index b0f558b4fea5..a479f8a1270c 100644 --- a/net/netfilter/nft_lookup.c +++ b/net/netfilter/nft_lookup.c @@ -30,13 +30,17 @@ void nft_lookup_eval(const struct nft_expr *expr, const struct nft_lookup *priv = nft_expr_priv(expr); const struct nft_set *set = priv->set; const struct nft_set_ext *ext = NULL; + const struct net *net = nft_net(pkt); bool found; - found = set->ops->lookup(nft_net(pkt), set, ®s->data[priv->sreg], - &ext) ^ priv->invert; + found = set->ops->lookup(net, set, ®s->data[priv->sreg], &ext) ^ + priv->invert; if (!found) { - regs->verdict.code = NFT_BREAK; - return; + ext = nft_set_catchall_lookup(net, set); + if (!ext) { + regs->verdict.code = NFT_BREAK; + return; + } } if (ext) { diff --git a/net/netfilter/nft_objref.c b/net/netfilter/nft_objref.c index bc104d36d3bb..7e47edee88ee 100644 --- a/net/netfilter/nft_objref.c +++ b/net/netfilter/nft_objref.c @@ -105,15 +105,18 @@ static void nft_objref_map_eval(const struct nft_expr *expr, { struct nft_objref_map *priv = nft_expr_priv(expr); const struct nft_set *set = priv->set; + struct net *net = nft_net(pkt); const struct nft_set_ext *ext; struct nft_object *obj; bool found; - found = set->ops->lookup(nft_net(pkt), set, ®s->data[priv->sreg], - &ext); + found = set->ops->lookup(net, set, ®s->data[priv->sreg], &ext); if (!found) { - regs->verdict.code = NFT_BREAK; - return; + ext = nft_set_catchall_lookup(net, set); + if (!ext) { + regs->verdict.code = NFT_BREAK; + return; + } } obj = *nft_set_ext_obj(ext); obj->ops->eval(obj, regs, pkt); diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c index cb1c8c231880..501c5b24cc39 100644 --- a/net/netfilter/nft_payload.c +++ b/net/netfilter/nft_payload.c @@ -226,8 +226,9 @@ static int nft_payload_offload_ll(struct nft_offload_ctx *ctx, if (!nft_payload_offload_mask(reg, priv->len, sizeof(__be16))) return -EOPNOTSUPP; - NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_VLAN, vlan, - vlan_tci, sizeof(__be16), reg); + NFT_OFFLOAD_MATCH_FLAGS(FLOW_DISSECTOR_KEY_VLAN, vlan, + vlan_tci, sizeof(__be16), reg, + NFT_OFFLOAD_F_NETWORK2HOST); break; case offsetof(struct vlan_ethhdr, h_vlan_encapsulated_proto): if (!nft_payload_offload_mask(reg, priv->len, sizeof(__be16))) @@ -241,16 +242,18 @@ static int nft_payload_offload_ll(struct nft_offload_ctx *ctx, if (!nft_payload_offload_mask(reg, priv->len, sizeof(__be16))) return -EOPNOTSUPP; - NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_CVLAN, vlan, - vlan_tci, sizeof(__be16), reg); + NFT_OFFLOAD_MATCH_FLAGS(FLOW_DISSECTOR_KEY_CVLAN, cvlan, + vlan_tci, sizeof(__be16), reg, + NFT_OFFLOAD_F_NETWORK2HOST); break; case offsetof(struct vlan_ethhdr, h_vlan_encapsulated_proto) + sizeof(struct vlan_hdr): if (!nft_payload_offload_mask(reg, priv->len, sizeof(__be16))) return -EOPNOTSUPP; - NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_CVLAN, vlan, + NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_CVLAN, cvlan, vlan_tpid, sizeof(__be16), reg); + nft_offload_set_dependency(ctx, NFT_OFFLOAD_DEP_NETWORK); break; default: return -EOPNOTSUPP; diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c index bf618b7ec1ae..58f576abcd4a 100644 --- a/net/netfilter/nft_set_hash.c +++ b/net/netfilter/nft_set_hash.c @@ -350,6 +350,12 @@ needs_gc_run: rhashtable_walk_stop(&hti); rhashtable_walk_exit(&hti); + he = nft_set_catchall_gc(set); + if (he) { + gcb = nft_set_gc_batch_check(set, gcb, GFP_ATOMIC); + if (gcb) + nft_set_gc_batch_add(gcb, he); + } nft_set_gc_batch_complete(gcb); queue_delayed_work(system_power_efficient_wq, &priv->gc_work, nft_set_gc_interval(set)); diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index 9944523f5c2c..528a2d7ca991 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -1529,11 +1529,11 @@ static void pipapo_gc(const struct nft_set *set, struct nft_pipapo_match *m) { struct nft_pipapo *priv = nft_set_priv(set); int rules_f0, first_rule = 0; + struct nft_pipapo_elem *e; while ((rules_f0 = pipapo_rules_same_key(m->f, first_rule))) { union nft_pipapo_map_bucket rulemap[NFT_PIPAPO_MAX_FIELDS]; struct nft_pipapo_field *f; - struct nft_pipapo_elem *e; int i, start, rules_fx; start = first_rule; @@ -1569,6 +1569,10 @@ static void pipapo_gc(const struct nft_set *set, struct nft_pipapo_match *m) } } + e = nft_set_catchall_gc(set); + if (e) + nft_set_elem_destroy(set, e, true); + priv->last_gc = jiffies; } diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 217ab3644c25..9e36eb4a7429 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -541,6 +541,12 @@ static void nft_rbtree_gc(struct work_struct *work) write_seqcount_end(&priv->count); write_unlock_bh(&priv->lock); + rbe = nft_set_catchall_gc(set); + if (rbe) { + gcb = nft_set_gc_batch_check(set, gcb, GFP_ATOMIC); + if (gcb) + nft_set_gc_batch_add(gcb, rbe); + } nft_set_gc_batch_complete(gcb); queue_delayed_work(system_power_efficient_wq, &priv->gc_work, diff --git a/net/netfilter/nft_socket.c b/net/netfilter/nft_socket.c index c9b8a2b03b71..d601974c9d2e 100644 --- a/net/netfilter/nft_socket.c +++ b/net/netfilter/nft_socket.c @@ -9,6 +9,7 @@ struct nft_socket { enum nft_socket_keys key:8; + u8 level; union { u8 dreg; }; @@ -33,6 +34,26 @@ static void nft_socket_wildcard(const struct nft_pktinfo *pkt, } } +#ifdef CONFIG_SOCK_CGROUP_DATA +static noinline bool +nft_sock_get_eval_cgroupv2(u32 *dest, const struct nft_pktinfo *pkt, u32 level) +{ + struct sock *sk = skb_to_full_sk(pkt->skb); + struct cgroup *cgrp; + + if (!sk || !sk_fullsock(sk) || !net_eq(nft_net(pkt), sock_net(sk))) + return false; + + cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); + if (level > cgrp->level) + return false; + + memcpy(dest, &cgrp->ancestor_ids[level], sizeof(u64)); + + return true; +} +#endif + static void nft_socket_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) @@ -85,6 +106,14 @@ static void nft_socket_eval(const struct nft_expr *expr, } nft_socket_wildcard(pkt, regs, sk, dest); break; +#ifdef CONFIG_SOCK_CGROUP_DATA + case NFT_SOCKET_CGROUPV2: + if (!nft_sock_get_eval_cgroupv2(dest, pkt, priv->level)) { + regs->verdict.code = NFT_BREAK; + return; + } + break; +#endif default: WARN_ON(1); regs->verdict.code = NFT_BREAK; @@ -97,6 +126,7 @@ static void nft_socket_eval(const struct nft_expr *expr, static const struct nla_policy nft_socket_policy[NFTA_SOCKET_MAX + 1] = { [NFTA_SOCKET_KEY] = { .type = NLA_U32 }, [NFTA_SOCKET_DREG] = { .type = NLA_U32 }, + [NFTA_SOCKET_LEVEL] = { .type = NLA_U32 }, }; static int nft_socket_init(const struct nft_ctx *ctx, @@ -129,6 +159,22 @@ static int nft_socket_init(const struct nft_ctx *ctx, case NFT_SOCKET_MARK: len = sizeof(u32); break; +#ifdef CONFIG_CGROUPS + case NFT_SOCKET_CGROUPV2: { + unsigned int level; + + if (!tb[NFTA_SOCKET_LEVEL]) + return -EINVAL; + + level = ntohl(nla_get_u32(tb[NFTA_SOCKET_LEVEL])); + if (level > 255) + return -EOPNOTSUPP; + + priv->level = level; + len = sizeof(u64); + break; + } +#endif default: return -EOPNOTSUPP; } @@ -146,6 +192,9 @@ static int nft_socket_dump(struct sk_buff *skb, return -1; if (nft_dump_register(skb, NFTA_SOCKET_DREG, priv->dreg)) return -1; + if (priv->key == NFT_SOCKET_CGROUPV2 && + nla_put_u32(skb, NFTA_SOCKET_LEVEL, htonl(priv->level))) + return -1; return 0; } diff --git a/net/netfilter/nft_tproxy.c b/net/netfilter/nft_tproxy.c index 43a5a780a6d3..accef672088c 100644 --- a/net/netfilter/nft_tproxy.c +++ b/net/netfilter/nft_tproxy.c @@ -263,6 +263,29 @@ static int nft_tproxy_init(const struct nft_ctx *ctx, return 0; } +static void nft_tproxy_destroy(const struct nft_ctx *ctx, + const struct nft_expr *expr) +{ + const struct nft_tproxy *priv = nft_expr_priv(expr); + + switch (priv->family) { + case NFPROTO_IPV4: + nf_defrag_ipv4_disable(ctx->net); + break; +#if IS_ENABLED(CONFIG_NF_TABLES_IPV6) + case NFPROTO_IPV6: + nf_defrag_ipv6_disable(ctx->net); + break; +#endif + case NFPROTO_UNSPEC: + nf_defrag_ipv4_disable(ctx->net); +#if IS_ENABLED(CONFIG_NF_TABLES_IPV6) + nf_defrag_ipv6_disable(ctx->net); +#endif + break; + } +} + static int nft_tproxy_dump(struct sk_buff *skb, const struct nft_expr *expr) { @@ -288,6 +311,7 @@ static const struct nft_expr_ops nft_tproxy_ops = { .size = NFT_EXPR_SIZE(sizeof(struct nft_tproxy)), .eval = nft_tproxy_eval, .init = nft_tproxy_init, + .destroy = nft_tproxy_destroy, .dump = nft_tproxy_dump, }; diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index 92e9d4ebc5e8..84e58ee501a4 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -24,6 +24,7 @@ #include <linux/audit.h> #include <linux/user_namespace.h> #include <net/net_namespace.h> +#include <net/netns/generic.h> #include <linux/netfilter/x_tables.h> #include <linux/netfilter_arp.h> @@ -38,6 +39,10 @@ MODULE_DESCRIPTION("{ip,ip6,arp,eb}_tables backend module"); #define XT_PCPU_BLOCK_SIZE 4096 #define XT_MAX_TABLE_SIZE (512 * 1024 * 1024) +struct xt_pernet { + struct list_head tables[NFPROTO_NUMPROTO]; +}; + struct compat_delta { unsigned int offset; /* offset in kernel */ int delta; /* delta in 32bit user land */ @@ -47,7 +52,7 @@ struct xt_af { struct mutex mutex; struct list_head match; struct list_head target; -#ifdef CONFIG_COMPAT +#ifdef CONFIG_NETFILTER_XTABLES_COMPAT struct mutex compat_mutex; struct compat_delta *compat_tab; unsigned int number; /* number of slots in compat_tab[] */ @@ -55,7 +60,8 @@ struct xt_af { #endif }; -static struct xt_af *xt; +static unsigned int xt_pernet_id __read_mostly; +static struct xt_af *xt __read_mostly; static const char *const xt_prefix[NFPROTO_NUMPROTO] = { [NFPROTO_UNSPEC] = "x", @@ -641,7 +647,7 @@ static bool error_tg_ok(unsigned int usersize, unsigned int kernsize, return usersize == kernsize && strnlen(msg, msglen) < msglen; } -#ifdef CONFIG_COMPAT +#ifdef CONFIG_NETFILTER_XTABLES_COMPAT int xt_compat_add_offset(u_int8_t af, unsigned int offset, int delta) { struct xt_af *xp = &xt[af]; @@ -844,7 +850,7 @@ int xt_compat_check_entry_offsets(const void *base, const char *elems, __alignof__(struct compat_xt_entry_match)); } EXPORT_SYMBOL(xt_compat_check_entry_offsets); -#endif /* CONFIG_COMPAT */ +#endif /* CONFIG_NETFILTER_XTABLES_COMPAT */ /** * xt_check_entry_offsets - validate arp/ip/ip6t_entry @@ -862,7 +868,7 @@ EXPORT_SYMBOL(xt_compat_check_entry_offsets); * match structures are aligned, and that the last structure ends where * the target structure begins. * - * Also see xt_compat_check_entry_offsets for CONFIG_COMPAT version. + * Also see xt_compat_check_entry_offsets for CONFIG_NETFILTER_XTABLES_COMPAT version. * * The arp/ip/ip6t_entry structure @base must have passed following tests: * - it must point to a valid memory location @@ -1053,7 +1059,7 @@ void *xt_copy_counters(sockptr_t arg, unsigned int len, void *mem; u64 size; -#ifdef CONFIG_COMPAT +#ifdef CONFIG_NETFILTER_XTABLES_COMPAT if (in_compat_syscall()) { /* structures only differ in size due to alignment */ struct compat_xt_counters_info compat_tmp; @@ -1100,7 +1106,7 @@ void *xt_copy_counters(sockptr_t arg, unsigned int len, } EXPORT_SYMBOL_GPL(xt_copy_counters); -#ifdef CONFIG_COMPAT +#ifdef CONFIG_NETFILTER_XTABLES_COMPAT int xt_compat_target_offset(const struct xt_target *target) { u_int16_t csize = target->compatsize ? : target->targetsize; @@ -1193,14 +1199,32 @@ void xt_free_table_info(struct xt_table_info *info) } EXPORT_SYMBOL(xt_free_table_info); +struct xt_table *xt_find_table(struct net *net, u8 af, const char *name) +{ + struct xt_pernet *xt_net = net_generic(net, xt_pernet_id); + struct xt_table *t; + + mutex_lock(&xt[af].mutex); + list_for_each_entry(t, &xt_net->tables[af], list) { + if (strcmp(t->name, name) == 0) { + mutex_unlock(&xt[af].mutex); + return t; + } + } + mutex_unlock(&xt[af].mutex); + return NULL; +} +EXPORT_SYMBOL(xt_find_table); + /* Find table by name, grabs mutex & ref. Returns ERR_PTR on error. */ struct xt_table *xt_find_table_lock(struct net *net, u_int8_t af, const char *name) { + struct xt_pernet *xt_net = net_generic(net, xt_pernet_id); struct xt_table *t, *found = NULL; mutex_lock(&xt[af].mutex); - list_for_each_entry(t, &net->xt.tables[af], list) + list_for_each_entry(t, &xt_net->tables[af], list) if (strcmp(t->name, name) == 0 && try_module_get(t->me)) return t; @@ -1208,7 +1232,8 @@ struct xt_table *xt_find_table_lock(struct net *net, u_int8_t af, goto out; /* Table doesn't exist in this netns, re-try init */ - list_for_each_entry(t, &init_net.xt.tables[af], list) { + xt_net = net_generic(&init_net, xt_pernet_id); + list_for_each_entry(t, &xt_net->tables[af], list) { int err; if (strcmp(t->name, name)) @@ -1231,8 +1256,9 @@ struct xt_table *xt_find_table_lock(struct net *net, u_int8_t af, if (!found) goto out; + xt_net = net_generic(net, xt_pernet_id); /* and once again: */ - list_for_each_entry(t, &net->xt.tables[af], list) + list_for_each_entry(t, &xt_net->tables[af], list) if (strcmp(t->name, name) == 0) return t; @@ -1267,7 +1293,7 @@ void xt_table_unlock(struct xt_table *table) } EXPORT_SYMBOL_GPL(xt_table_unlock); -#ifdef CONFIG_COMPAT +#ifdef CONFIG_NETFILTER_XTABLES_COMPAT void xt_compat_lock(u_int8_t af) { mutex_lock(&xt[af].compat_mutex); @@ -1417,9 +1443,10 @@ struct xt_table *xt_register_table(struct net *net, struct xt_table_info *bootstrap, struct xt_table_info *newinfo) { - int ret; + struct xt_pernet *xt_net = net_generic(net, xt_pernet_id); struct xt_table_info *private; struct xt_table *t, *table; + int ret; /* Don't add one object to multiple lists. */ table = kmemdup(input_table, sizeof(struct xt_table), GFP_KERNEL); @@ -1430,7 +1457,7 @@ struct xt_table *xt_register_table(struct net *net, mutex_lock(&xt[table->af].mutex); /* Don't autoload: we'd eat our tail... */ - list_for_each_entry(t, &net->xt.tables[table->af], list) { + list_for_each_entry(t, &xt_net->tables[table->af], list) { if (strcmp(t->name, table->name) == 0) { ret = -EEXIST; goto unlock; @@ -1449,7 +1476,7 @@ struct xt_table *xt_register_table(struct net *net, /* save number of initial entries */ private->initial_entries = private->number; - list_add(&table->list, &net->xt.tables[table->af]); + list_add(&table->list, &xt_net->tables[table->af]); mutex_unlock(&xt[table->af].mutex); return table; @@ -1471,6 +1498,7 @@ void *xt_unregister_table(struct xt_table *table) mutex_unlock(&xt[table->af].mutex); audit_log_nfcfg(table->name, table->af, private->number, AUDIT_XT_OP_UNREGISTER, GFP_KERNEL); + kfree(table->ops); kfree(table); return private; @@ -1480,19 +1508,25 @@ EXPORT_SYMBOL_GPL(xt_unregister_table); #ifdef CONFIG_PROC_FS static void *xt_table_seq_start(struct seq_file *seq, loff_t *pos) { + u8 af = (unsigned long)PDE_DATA(file_inode(seq->file)); struct net *net = seq_file_net(seq); - u_int8_t af = (unsigned long)PDE_DATA(file_inode(seq->file)); + struct xt_pernet *xt_net; + + xt_net = net_generic(net, xt_pernet_id); mutex_lock(&xt[af].mutex); - return seq_list_start(&net->xt.tables[af], *pos); + return seq_list_start(&xt_net->tables[af], *pos); } static void *xt_table_seq_next(struct seq_file *seq, void *v, loff_t *pos) { + u8 af = (unsigned long)PDE_DATA(file_inode(seq->file)); struct net *net = seq_file_net(seq); - u_int8_t af = (unsigned long)PDE_DATA(file_inode(seq->file)); + struct xt_pernet *xt_net; + + xt_net = net_generic(net, xt_pernet_id); - return seq_list_next(v, &net->xt.tables[af], pos); + return seq_list_next(v, &xt_net->tables[af], pos); } static void xt_table_seq_stop(struct seq_file *seq, void *v) @@ -1858,24 +1892,28 @@ EXPORT_SYMBOL_GPL(xt_percpu_counter_free); static int __net_init xt_net_init(struct net *net) { + struct xt_pernet *xt_net = net_generic(net, xt_pernet_id); int i; for (i = 0; i < NFPROTO_NUMPROTO; i++) - INIT_LIST_HEAD(&net->xt.tables[i]); + INIT_LIST_HEAD(&xt_net->tables[i]); return 0; } static void __net_exit xt_net_exit(struct net *net) { + struct xt_pernet *xt_net = net_generic(net, xt_pernet_id); int i; for (i = 0; i < NFPROTO_NUMPROTO; i++) - WARN_ON_ONCE(!list_empty(&net->xt.tables[i])); + WARN_ON_ONCE(!list_empty(&xt_net->tables[i])); } static struct pernet_operations xt_net_ops = { .init = xt_net_init, .exit = xt_net_exit, + .id = &xt_pernet_id, + .size = sizeof(struct xt_pernet), }; static int __init xt_init(void) @@ -1893,7 +1931,7 @@ static int __init xt_init(void) for (i = 0; i < NFPROTO_NUMPROTO; i++) { mutex_init(&xt[i].mutex); -#ifdef CONFIG_COMPAT +#ifdef CONFIG_NETFILTER_XTABLES_COMPAT mutex_init(&xt[i].compat_mutex); xt[i].compat_tab = NULL; #endif diff --git a/net/netfilter/xt_LOG.c b/net/netfilter/xt_LOG.c index a1e79b517c01..2ff75f7637b0 100644 --- a/net/netfilter/xt_LOG.c +++ b/net/netfilter/xt_LOG.c @@ -108,3 +108,4 @@ MODULE_AUTHOR("Jan Rekorajski <baggins@pld.org.pl>"); MODULE_DESCRIPTION("Xtables: IPv4/IPv6 packet logging"); MODULE_ALIAS("ipt_LOG"); MODULE_ALIAS("ip6t_LOG"); +MODULE_SOFTDEP("pre: nf_log_syslog"); diff --git a/net/netfilter/xt_NFLOG.c b/net/netfilter/xt_NFLOG.c index 6e83ce3000db..fb5793208059 100644 --- a/net/netfilter/xt_NFLOG.c +++ b/net/netfilter/xt_NFLOG.c @@ -79,3 +79,4 @@ static void __exit nflog_tg_exit(void) module_init(nflog_tg_init); module_exit(nflog_tg_exit); +MODULE_SOFTDEP("pre: nfnetlink_log"); diff --git a/net/netfilter/xt_TPROXY.c b/net/netfilter/xt_TPROXY.c index 194dc03341f3..459d0696c91a 100644 --- a/net/netfilter/xt_TPROXY.c +++ b/net/netfilter/xt_TPROXY.c @@ -200,6 +200,11 @@ static int tproxy_tg6_check(const struct xt_tgchk_param *par) pr_info_ratelimited("Can be used only with -p tcp or -p udp\n"); return -EINVAL; } + +static void tproxy_tg6_destroy(const struct xt_tgdtor_param *par) +{ + nf_defrag_ipv6_disable(par->net); +} #endif static int tproxy_tg4_check(const struct xt_tgchk_param *par) @@ -219,6 +224,11 @@ static int tproxy_tg4_check(const struct xt_tgchk_param *par) return -EINVAL; } +static void tproxy_tg4_destroy(const struct xt_tgdtor_param *par) +{ + nf_defrag_ipv4_disable(par->net); +} + static struct xt_target tproxy_tg_reg[] __read_mostly = { { .name = "TPROXY", @@ -228,6 +238,7 @@ static struct xt_target tproxy_tg_reg[] __read_mostly = { .revision = 0, .targetsize = sizeof(struct xt_tproxy_target_info), .checkentry = tproxy_tg4_check, + .destroy = tproxy_tg4_destroy, .hooks = 1 << NF_INET_PRE_ROUTING, .me = THIS_MODULE, }, @@ -239,6 +250,7 @@ static struct xt_target tproxy_tg_reg[] __read_mostly = { .revision = 1, .targetsize = sizeof(struct xt_tproxy_target_info_v1), .checkentry = tproxy_tg4_check, + .destroy = tproxy_tg4_destroy, .hooks = 1 << NF_INET_PRE_ROUTING, .me = THIS_MODULE, }, @@ -251,6 +263,7 @@ static struct xt_target tproxy_tg_reg[] __read_mostly = { .revision = 1, .targetsize = sizeof(struct xt_tproxy_target_info_v1), .checkentry = tproxy_tg6_check, + .destroy = tproxy_tg6_destroy, .hooks = 1 << NF_INET_PRE_ROUTING, .me = THIS_MODULE, }, diff --git a/net/netfilter/xt_TRACE.c b/net/netfilter/xt_TRACE.c index 349ab5609b1b..5582dce98cae 100644 --- a/net/netfilter/xt_TRACE.c +++ b/net/netfilter/xt_TRACE.c @@ -52,3 +52,4 @@ static void __exit trace_tg_exit(void) module_init(trace_tg_init); module_exit(trace_tg_exit); +MODULE_SOFTDEP("pre: nf_log_syslog"); diff --git a/net/netfilter/xt_limit.c b/net/netfilter/xt_limit.c index bd1dea9c7b88..24d4afb9988d 100644 --- a/net/netfilter/xt_limit.c +++ b/net/netfilter/xt_limit.c @@ -134,7 +134,7 @@ static void limit_mt_destroy(const struct xt_mtdtor_param *par) kfree(info->master); } -#ifdef CONFIG_COMPAT +#ifdef CONFIG_NETFILTER_XTABLES_COMPAT struct compat_xt_rateinfo { u_int32_t avg; u_int32_t burst; @@ -176,7 +176,7 @@ static int limit_mt_compat_to_user(void __user *dst, const void *src) }; return copy_to_user(dst, &cm, sizeof(cm)) ? -EFAULT : 0; } -#endif /* CONFIG_COMPAT */ +#endif /* CONFIG_NETFILTER_XTABLES_COMPAT */ static struct xt_match limit_mt_reg __read_mostly = { .name = "limit", @@ -186,7 +186,7 @@ static struct xt_match limit_mt_reg __read_mostly = { .checkentry = limit_mt_check, .destroy = limit_mt_destroy, .matchsize = sizeof(struct xt_rateinfo), -#ifdef CONFIG_COMPAT +#ifdef CONFIG_NETFILTER_XTABLES_COMPAT .compatsize = sizeof(struct compat_xt_rateinfo), .compat_from_user = limit_mt_compat_from_user, .compat_to_user = limit_mt_compat_to_user, diff --git a/net/netfilter/xt_socket.c b/net/netfilter/xt_socket.c index 5f973987265d..5e6459e11605 100644 --- a/net/netfilter/xt_socket.c +++ b/net/netfilter/xt_socket.c @@ -216,6 +216,14 @@ static int socket_mt_v3_check(const struct xt_mtchk_param *par) return 0; } +static void socket_mt_destroy(const struct xt_mtdtor_param *par) +{ + if (par->family == NFPROTO_IPV4) + nf_defrag_ipv4_disable(par->net); + else if (par->family == NFPROTO_IPV6) + nf_defrag_ipv4_disable(par->net); +} + static struct xt_match socket_mt_reg[] __read_mostly = { { .name = "socket", @@ -231,6 +239,7 @@ static struct xt_match socket_mt_reg[] __read_mostly = { .revision = 1, .family = NFPROTO_IPV4, .match = socket_mt4_v1_v2_v3, + .destroy = socket_mt_destroy, .checkentry = socket_mt_v1_check, .matchsize = sizeof(struct xt_socket_mtinfo1), .hooks = (1 << NF_INET_PRE_ROUTING) | @@ -245,6 +254,7 @@ static struct xt_match socket_mt_reg[] __read_mostly = { .match = socket_mt6_v1_v2_v3, .checkentry = socket_mt_v1_check, .matchsize = sizeof(struct xt_socket_mtinfo1), + .destroy = socket_mt_destroy, .hooks = (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_IN), .me = THIS_MODULE, @@ -256,6 +266,7 @@ static struct xt_match socket_mt_reg[] __read_mostly = { .family = NFPROTO_IPV4, .match = socket_mt4_v1_v2_v3, .checkentry = socket_mt_v2_check, + .destroy = socket_mt_destroy, .matchsize = sizeof(struct xt_socket_mtinfo1), .hooks = (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_IN), @@ -268,6 +279,7 @@ static struct xt_match socket_mt_reg[] __read_mostly = { .family = NFPROTO_IPV6, .match = socket_mt6_v1_v2_v3, .checkentry = socket_mt_v2_check, + .destroy = socket_mt_destroy, .matchsize = sizeof(struct xt_socket_mtinfo1), .hooks = (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_IN), @@ -280,6 +292,7 @@ static struct xt_match socket_mt_reg[] __read_mostly = { .family = NFPROTO_IPV4, .match = socket_mt4_v1_v2_v3, .checkentry = socket_mt_v3_check, + .destroy = socket_mt_destroy, .matchsize = sizeof(struct xt_socket_mtinfo1), .hooks = (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_IN), @@ -292,6 +305,7 @@ static struct xt_match socket_mt_reg[] __read_mostly = { .family = NFPROTO_IPV6, .match = socket_mt6_v1_v2_v3, .checkentry = socket_mt_v3_check, + .destroy = socket_mt_destroy, .matchsize = sizeof(struct xt_socket_mtinfo1), .hooks = (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_IN), |