diff options
author | Patrick McHardy <kaber@trash.net> | 2013-10-14 09:00:02 (GMT) |
---|---|---|
committer | Pablo Neira Ayuso <pablo@netfilter.org> | 2013-10-14 15:15:48 (GMT) |
commit | 96518518cc417bb0a8c80b9fb736202e28acdf96 (patch) | |
tree | 2ac4f939a88f0a8047403d0e07b5167369236f82 /net/ipv4/netfilter | |
parent | f59cb0453cd885736daa11ae2445982c5ab2fc83 (diff) | |
download | linux-fsl-qoriq-96518518cc417bb0a8c80b9fb736202e28acdf96.tar.xz |
netfilter: add nftables
This patch adds nftables which is the intended successor of iptables.
This packet filtering framework reuses the existing netfilter hooks,
the connection tracking system, the NAT subsystem, the transparent
proxying engine, the logging infrastructure and the userspace packet
queueing facilities.
In a nutshell, nftables provides a pseudo-state machine with 4 general
purpose registers of 128 bits and 1 specific purpose register to store
verdicts. This pseudo-machine comes with an extensible instruction set,
a.k.a. "expressions" in the nftables jargon. The expressions included
in this patch provide the basic functionality, they are:
* bitwise: to perform bitwise operations.
* byteorder: to change from host/network endianess.
* cmp: to compare data with the content of the registers.
* counter: to enable counters on rules.
* ct: to store conntrack keys into register.
* exthdr: to match IPv6 extension headers.
* immediate: to load data into registers.
* limit: to limit matching based on packet rate.
* log: to log packets.
* meta: to match metainformation that usually comes with the skbuff.
* nat: to perform Network Address Translation.
* payload: to fetch data from the packet payload and store it into
registers.
* reject (IPv4 only): to explicitly close connection, eg. TCP RST.
Using this instruction-set, the userspace utility 'nft' can transform
the rules expressed in human-readable text representation (using a
new syntax, inspired by tcpdump) to nftables bytecode.
nftables also inherits the table, chain and rule objects from
iptables, but in a more configurable way, and it also includes the
original datatype-agnostic set infrastructure with mapping support.
This set infrastructure is enhanced in the follow up patch (netfilter:
nf_tables: add netlink set API).
This patch includes the following components:
* the netlink API: net/netfilter/nf_tables_api.c and
include/uapi/netfilter/nf_tables.h
* the packet filter core: net/netfilter/nf_tables_core.c
* the expressions (described above): net/netfilter/nft_*.c
* the filter tables: arp, IPv4, IPv6 and bridge:
net/ipv4/netfilter/nf_tables_ipv4.c
net/ipv6/netfilter/nf_tables_ipv6.c
net/ipv4/netfilter/nf_tables_arp.c
net/bridge/netfilter/nf_tables_bridge.c
* the NAT table (IPv4 only):
net/ipv4/netfilter/nf_table_nat_ipv4.c
* the route table (similar to mangle):
net/ipv4/netfilter/nf_table_route_ipv4.c
net/ipv6/netfilter/nf_table_route_ipv6.c
* internal definitions under:
include/net/netfilter/nf_tables.h
include/net/netfilter/nf_tables_core.h
* It also includes an skeleton expression:
net/netfilter/nft_expr_template.c
and the preliminary implementation of the meta target
net/netfilter/nft_meta_target.c
It also includes a change in struct nf_hook_ops to add a new
pointer to store private data to the hook, that is used to store
the rule list per chain.
This patch is based on the patch from Patrick McHardy, plus merged
accumulated cleanups, fixes and small enhancements to the nftables
code that has been done since 2009, which are:
From Patrick McHardy:
* nf_tables: adjust netlink handler function signatures
* nf_tables: only retry table lookup after successful table module load
* nf_tables: fix event notification echo and avoid unnecessary messages
* nft_ct: add l3proto support
* nf_tables: pass expression context to nft_validate_data_load()
* nf_tables: remove redundant definition
* nft_ct: fix maxattr initialization
* nf_tables: fix invalid event type in nf_tables_getrule()
* nf_tables: simplify nft_data_init() usage
* nf_tables: build in more core modules
* nf_tables: fix double lookup expression unregistation
* nf_tables: move expression initialization to nf_tables_core.c
* nf_tables: build in payload module
* nf_tables: use NFPROTO constants
* nf_tables: rename pid variables to portid
* nf_tables: save 48 bits per rule
* nf_tables: introduce chain rename
* nf_tables: check for duplicate names on chain rename
* nf_tables: remove ability to specify handles for new rules
* nf_tables: return error for rule change request
* nf_tables: return error for NLM_F_REPLACE without rule handle
* nf_tables: include NLM_F_APPEND/NLM_F_REPLACE flags in rule notification
* nf_tables: fix NLM_F_MULTI usage in netlink notifications
* nf_tables: include NLM_F_APPEND in rule dumps
From Pablo Neira Ayuso:
* nf_tables: fix stack overflow in nf_tables_newrule
* nf_tables: nft_ct: fix compilation warning
* nf_tables: nft_ct: fix crash with invalid packets
* nft_log: group and qthreshold are 2^16
* nf_tables: nft_meta: fix socket uid,gid handling
* nft_counter: allow to restore counters
* nf_tables: fix module autoload
* nf_tables: allow to remove all rules placed in one chain
* nf_tables: use 64-bits rule handle instead of 16-bits
* nf_tables: fix chain after rule deletion
* nf_tables: improve deletion performance
* nf_tables: add missing code in route chain type
* nf_tables: rise maximum number of expressions from 12 to 128
* nf_tables: don't delete table if in use
* nf_tables: fix basechain release
From Tomasz Bursztyka:
* nf_tables: Add support for changing users chain's name
* nf_tables: Change chain's name to be fixed sized
* nf_tables: Add support for replacing a rule by another one
* nf_tables: Update uapi nftables netlink header documentation
From Florian Westphal:
* nft_log: group is u16, snaplen u32
From Phil Oester:
* nf_tables: operational limit match
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Diffstat (limited to 'net/ipv4/netfilter')
-rw-r--r-- | net/ipv4/netfilter/Kconfig | 16 | ||||
-rw-r--r-- | net/ipv4/netfilter/Makefile | 5 | ||||
-rw-r--r-- | net/ipv4/netfilter/nf_table_nat_ipv4.c | 409 | ||||
-rw-r--r-- | net/ipv4/netfilter/nf_table_route_ipv4.c | 97 | ||||
-rw-r--r-- | net/ipv4/netfilter/nf_tables_ipv4.c | 59 | ||||
-rw-r--r-- | net/ipv4/netfilter/nft_reject_ipv4.c | 117 |
6 files changed, 703 insertions, 0 deletions
diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig index 1657e39b..eb1d56e 100644 --- a/net/ipv4/netfilter/Kconfig +++ b/net/ipv4/netfilter/Kconfig @@ -36,6 +36,22 @@ config NF_CONNTRACK_PROC_COMPAT If unsure, say Y. +config NF_TABLES_IPV4 + depends on NF_TABLES + tristate "IPv4 nf_tables support" + +config NFT_REJECT_IPV4 + depends on NF_TABLES_IPV4 + tristate "nf_tables IPv4 reject support" + +config NF_TABLE_ROUTE_IPV4 + depends on NF_TABLES_IPV4 + tristate "IPv4 nf_tables route table support" + +config NF_TABLE_NAT_IPV4 + depends on NF_TABLES_IPV4 + tristate "IPv4 nf_tables nat table support" + config IP_NF_IPTABLES tristate "IP tables support (required for filtering/masq/NAT)" default m if NETFILTER_ADVANCED=n diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile index 3622b24..b2f01cd 100644 --- a/net/ipv4/netfilter/Makefile +++ b/net/ipv4/netfilter/Makefile @@ -27,6 +27,11 @@ obj-$(CONFIG_NF_NAT_SNMP_BASIC) += nf_nat_snmp_basic.o # NAT protocols (nf_nat) obj-$(CONFIG_NF_NAT_PROTO_GRE) += nf_nat_proto_gre.o +obj-$(CONFIG_NF_TABLES_IPV4) += nf_tables_ipv4.o +obj-$(CONFIG_NFT_REJECT_IPV4) += nft_reject_ipv4.o +obj-$(CONFIG_NF_TABLE_ROUTE_IPV4) += nf_table_route_ipv4.o +obj-$(CONFIG_NF_TABLE_NAT_IPV4) += nf_table_nat_ipv4.o + # generic IP tables obj-$(CONFIG_IP_NF_IPTABLES) += ip_tables.o diff --git a/net/ipv4/netfilter/nf_table_nat_ipv4.c b/net/ipv4/netfilter/nf_table_nat_ipv4.c new file mode 100644 index 0000000..2a6f184 --- /dev/null +++ b/net/ipv4/netfilter/nf_table_nat_ipv4.c @@ -0,0 +1,409 @@ +/* + * Copyright (c) 2008 Patrick McHardy <kaber@trash.net> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * Development of this code funded by Astaro AG (http://www.astaro.com/) + */ + +#include <linux/module.h> +#include <linux/init.h> +#include <linux/list.h> +#include <linux/skbuff.h> +#include <linux/ip.h> +#include <linux/netlink.h> +#include <linux/netfilter.h> +#include <linux/netfilter_ipv4.h> +#include <linux/netfilter/nfnetlink.h> +#include <linux/netfilter/nf_tables.h> +#include <net/netfilter/nf_conntrack.h> +#include <net/netfilter/nf_nat.h> +#include <net/netfilter/nf_nat_core.h> +#include <net/netfilter/nf_tables.h> +#include <net/netfilter/nf_nat_l3proto.h> +#include <net/ip.h> + +struct nft_nat { + enum nft_registers sreg_addr_min:8; + enum nft_registers sreg_addr_max:8; + enum nft_registers sreg_proto_min:8; + enum nft_registers sreg_proto_max:8; + enum nf_nat_manip_type type; +}; + +static void nft_nat_eval(const struct nft_expr *expr, + struct nft_data data[NFT_REG_MAX + 1], + const struct nft_pktinfo *pkt) +{ + const struct nft_nat *priv = nft_expr_priv(expr); + enum ip_conntrack_info ctinfo; + struct nf_conn *ct = nf_ct_get(pkt->skb, &ctinfo); + struct nf_nat_range range; + + memset(&range, 0, sizeof(range)); + if (priv->sreg_addr_min) { + range.min_addr.ip = data[priv->sreg_addr_min].data[0]; + range.max_addr.ip = data[priv->sreg_addr_max].data[0]; + range.flags |= NF_NAT_RANGE_MAP_IPS; + } + + if (priv->sreg_proto_min) { + range.min_proto.all = data[priv->sreg_proto_min].data[0]; + range.max_proto.all = data[priv->sreg_proto_max].data[0]; + range.flags |= NF_NAT_RANGE_PROTO_SPECIFIED; + } + + data[NFT_REG_VERDICT].verdict = + nf_nat_setup_info(ct, &range, priv->type); +} + +static const struct nla_policy nft_nat_policy[NFTA_NAT_MAX + 1] = { + [NFTA_NAT_ADDR_MIN] = { .type = NLA_U32 }, + [NFTA_NAT_ADDR_MAX] = { .type = NLA_U32 }, + [NFTA_NAT_PROTO_MIN] = { .type = NLA_U32 }, + [NFTA_NAT_PROTO_MAX] = { .type = NLA_U32 }, + [NFTA_NAT_TYPE] = { .type = NLA_U32 }, +}; + +static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr, + const struct nlattr * const tb[]) +{ + struct nft_nat *priv = nft_expr_priv(expr); + int err; + + if (tb[NFTA_NAT_TYPE] == NULL) + return -EINVAL; + + switch (ntohl(nla_get_be32(tb[NFTA_NAT_TYPE]))) { + case NFT_NAT_SNAT: + priv->type = NF_NAT_MANIP_SRC; + break; + case NFT_NAT_DNAT: + priv->type = NF_NAT_MANIP_DST; + break; + default: + return -EINVAL; + } + + if (tb[NFTA_NAT_ADDR_MIN]) { + priv->sreg_addr_min = ntohl(nla_get_be32(tb[NFTA_NAT_ADDR_MIN])); + err = nft_validate_input_register(priv->sreg_addr_min); + if (err < 0) + return err; + } + + if (tb[NFTA_NAT_ADDR_MAX]) { + priv->sreg_addr_max = ntohl(nla_get_be32(tb[NFTA_NAT_ADDR_MAX])); + err = nft_validate_input_register(priv->sreg_addr_max); + if (err < 0) + return err; + } else + priv->sreg_addr_max = priv->sreg_addr_min; + + if (tb[NFTA_NAT_PROTO_MIN]) { + priv->sreg_proto_min = ntohl(nla_get_be32(tb[NFTA_NAT_PROTO_MIN])); + err = nft_validate_input_register(priv->sreg_proto_min); + if (err < 0) + return err; + } + + if (tb[NFTA_NAT_PROTO_MAX]) { + priv->sreg_proto_max = ntohl(nla_get_be32(tb[NFTA_NAT_PROTO_MAX])); + err = nft_validate_input_register(priv->sreg_proto_max); + if (err < 0) + return err; + } else + priv->sreg_proto_max = priv->sreg_proto_min; + + return 0; +} + +static int nft_nat_dump(struct sk_buff *skb, const struct nft_expr *expr) +{ + const struct nft_nat *priv = nft_expr_priv(expr); + + switch (priv->type) { + case NF_NAT_MANIP_SRC: + if (nla_put_be32(skb, NFTA_NAT_TYPE, htonl(NFT_NAT_SNAT))) + goto nla_put_failure; + break; + case NF_NAT_MANIP_DST: + if (nla_put_be32(skb, NFTA_NAT_TYPE, htonl(NFT_NAT_DNAT))) + goto nla_put_failure; + break; + } + + if (nla_put_be32(skb, NFTA_NAT_ADDR_MIN, htonl(priv->sreg_addr_min))) + goto nla_put_failure; + if (nla_put_be32(skb, NFTA_NAT_ADDR_MAX, htonl(priv->sreg_addr_max))) + goto nla_put_failure; + if (nla_put_be32(skb, NFTA_NAT_PROTO_MIN, htonl(priv->sreg_proto_min))) + goto nla_put_failure; + if (nla_put_be32(skb, NFTA_NAT_PROTO_MAX, htonl(priv->sreg_proto_max))) + goto nla_put_failure; + return 0; + +nla_put_failure: + return -1; +} + +static struct nft_expr_ops nft_nat_ops __read_mostly = { + .name = "nat", + .size = NFT_EXPR_SIZE(sizeof(struct nft_nat)), + .owner = THIS_MODULE, + .eval = nft_nat_eval, + .init = nft_nat_init, + .dump = nft_nat_dump, + .policy = nft_nat_policy, + .maxattr = NFTA_NAT_MAX, +}; + +/* + * NAT table + */ + +static unsigned int nf_nat_fn(const struct nf_hook_ops *ops, + struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) +{ + enum ip_conntrack_info ctinfo; + struct nf_conn *ct = nf_ct_get(skb, &ctinfo); + struct nf_conn_nat *nat; + enum nf_nat_manip_type maniptype = HOOK2MANIP(ops->hooknum); + unsigned int ret; + + if (ct == NULL || nf_ct_is_untracked(ct)) + return NF_ACCEPT; + + NF_CT_ASSERT(!(ip_hdr(skb)->frag_off & htons(IP_MF | IP_OFFSET))); + + nat = nfct_nat(ct); + if (nat == NULL) { + /* Conntrack module was loaded late, can't add extension. */ + if (nf_ct_is_confirmed(ct)) + return NF_ACCEPT; + nat = nf_ct_ext_add(ct, NF_CT_EXT_NAT, GFP_ATOMIC); + if (nat == NULL) + return NF_ACCEPT; + } + + switch (ctinfo) { + case IP_CT_RELATED: + case IP_CT_RELATED + IP_CT_IS_REPLY: + if (ip_hdr(skb)->protocol == IPPROTO_ICMP) { + if (!nf_nat_icmp_reply_translation(skb, ct, ctinfo, + ops->hooknum)) + return NF_DROP; + else + return NF_ACCEPT; + } + /* Fall through */ + case IP_CT_NEW: + if (nf_nat_initialized(ct, maniptype)) + break; + + ret = nft_do_chain(ops, skb, in, out, okfn); + if (ret != NF_ACCEPT) + return ret; + if (!nf_nat_initialized(ct, maniptype)) { + ret = nf_nat_alloc_null_binding(ct, ops->hooknum); + if (ret != NF_ACCEPT) + return ret; + } + default: + break; + } + + return nf_nat_packet(ct, ctinfo, ops->hooknum, skb); +} + +static unsigned int nf_nat_prerouting(const struct nf_hook_ops *ops, + struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) +{ + __be32 daddr = ip_hdr(skb)->daddr; + unsigned int ret; + + ret = nf_nat_fn(ops, skb, in, out, okfn); + if (ret != NF_DROP && ret != NF_STOLEN && + ip_hdr(skb)->daddr != daddr) { + skb_dst_drop(skb); + } + return ret; +} + +static unsigned int nf_nat_postrouting(const struct nf_hook_ops *ops, + struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) +{ + enum ip_conntrack_info ctinfo __maybe_unused; + const struct nf_conn *ct __maybe_unused; + unsigned int ret; + + ret = nf_nat_fn(ops, skb, in, out, okfn); +#ifdef CONFIG_XFRM + if (ret != NF_DROP && ret != NF_STOLEN && + (ct = nf_ct_get(skb, &ctinfo)) != NULL) { + enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); + + if (ct->tuplehash[dir].tuple.src.u3.ip != + ct->tuplehash[!dir].tuple.dst.u3.ip || + ct->tuplehash[dir].tuple.src.u.all != + ct->tuplehash[!dir].tuple.dst.u.all) + return nf_xfrm_me_harder(skb, AF_INET) == 0 ? + ret : NF_DROP; + } +#endif + return ret; +} + +static unsigned int nf_nat_output(const struct nf_hook_ops *ops, + struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) +{ + enum ip_conntrack_info ctinfo; + const struct nf_conn *ct; + unsigned int ret; + + ret = nf_nat_fn(ops, skb, in, out, okfn); + if (ret != NF_DROP && ret != NF_STOLEN && + (ct = nf_ct_get(skb, &ctinfo)) != NULL) { + enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); + + if (ct->tuplehash[dir].tuple.dst.u3.ip != + ct->tuplehash[!dir].tuple.src.u3.ip) { + if (ip_route_me_harder(skb, RTN_UNSPEC)) + ret = NF_DROP; + } +#ifdef CONFIG_XFRM + else if (ct->tuplehash[dir].tuple.dst.u.all != + ct->tuplehash[!dir].tuple.src.u.all) + if (nf_xfrm_me_harder(skb, AF_INET)) + ret = NF_DROP; +#endif + } + return ret; +} + +static struct nft_base_chain nf_chain_nat_prerouting __read_mostly = { + .chain = { + .name = "PREROUTING", + .rules = LIST_HEAD_INIT(nf_chain_nat_prerouting.chain.rules), + .flags = NFT_BASE_CHAIN | NFT_CHAIN_BUILTIN, + }, + .ops = { + .hook = nf_nat_prerouting, + .owner = THIS_MODULE, + .pf = NFPROTO_IPV4, + .hooknum = NF_INET_PRE_ROUTING, + .priority = NF_IP_PRI_NAT_DST, + .priv = &nf_chain_nat_prerouting.chain, + }, +}; + +static struct nft_base_chain nf_chain_nat_postrouting __read_mostly = { + .chain = { + .name = "POSTROUTING", + .rules = LIST_HEAD_INIT(nf_chain_nat_postrouting.chain.rules), + .flags = NFT_BASE_CHAIN | NFT_CHAIN_BUILTIN, + }, + .ops = { + .hook = nf_nat_postrouting, + .owner = THIS_MODULE, + .pf = NFPROTO_IPV4, + .hooknum = NF_INET_POST_ROUTING, + .priority = NF_IP_PRI_NAT_SRC, + .priv = &nf_chain_nat_postrouting.chain, + }, +}; + +static struct nft_base_chain nf_chain_nat_output __read_mostly = { + .chain = { + .name = "OUTPUT", + .rules = LIST_HEAD_INIT(nf_chain_nat_output.chain.rules), + .flags = NFT_BASE_CHAIN | NFT_CHAIN_BUILTIN, + }, + .ops = { + .hook = nf_nat_output, + .owner = THIS_MODULE, + .pf = NFPROTO_IPV4, + .hooknum = NF_INET_LOCAL_OUT, + .priority = NF_IP_PRI_NAT_DST, + .priv = &nf_chain_nat_output.chain, + }, +}; + +static struct nft_base_chain nf_chain_nat_input __read_mostly = { + .chain = { + .name = "INPUT", + .rules = LIST_HEAD_INIT(nf_chain_nat_input.chain.rules), + .flags = NFT_BASE_CHAIN | NFT_CHAIN_BUILTIN, + }, + .ops = { + .hook = nf_nat_fn, + .owner = THIS_MODULE, + .pf = NFPROTO_IPV4, + .hooknum = NF_INET_LOCAL_IN, + .priority = NF_IP_PRI_NAT_SRC, + .priv = &nf_chain_nat_input.chain, + }, +}; + + +static struct nft_table nf_table_nat_ipv4 __read_mostly = { + .name = "nat", + .chains = LIST_HEAD_INIT(nf_table_nat_ipv4.chains), +}; + +static int __init nf_table_nat_init(void) +{ + int err; + + list_add_tail(&nf_chain_nat_prerouting.chain.list, + &nf_table_nat_ipv4.chains); + list_add_tail(&nf_chain_nat_postrouting.chain.list, + &nf_table_nat_ipv4.chains); + list_add_tail(&nf_chain_nat_output.chain.list, + &nf_table_nat_ipv4.chains); + list_add_tail(&nf_chain_nat_input.chain.list, + &nf_table_nat_ipv4.chains); + + err = nft_register_table(&nf_table_nat_ipv4, NFPROTO_IPV4); + if (err < 0) + goto err1; + + err = nft_register_expr(&nft_nat_ops); + if (err < 0) + goto err2; + + return 0; + +err2: + nft_unregister_table(&nf_table_nat_ipv4, NFPROTO_IPV4); +err1: + return err; +} + +static void __exit nf_table_nat_exit(void) +{ + nft_unregister_expr(&nft_nat_ops); + nft_unregister_table(&nf_table_nat_ipv4, AF_INET); +} + +module_init(nf_table_nat_init); +module_exit(nf_table_nat_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); +MODULE_ALIAS_NFT_TABLE(AF_INET, "nat"); +MODULE_ALIAS_NFT_EXPR("nat"); diff --git a/net/ipv4/netfilter/nf_table_route_ipv4.c b/net/ipv4/netfilter/nf_table_route_ipv4.c new file mode 100644 index 0000000..4f257a1 --- /dev/null +++ b/net/ipv4/netfilter/nf_table_route_ipv4.c @@ -0,0 +1,97 @@ +/* + * Copyright (c) 2008 Patrick McHardy <kaber@trash.net> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/module.h> +#include <linux/init.h> +#include <linux/list.h> +#include <linux/skbuff.h> +#include <linux/netlink.h> +#include <linux/netfilter.h> +#include <linux/netfilter_ipv4.h> +#include <linux/netfilter/nfnetlink.h> +#include <linux/netfilter/nf_tables.h> +#include <net/netfilter/nf_tables.h> +#include <net/route.h> +#include <net/ip.h> + +static unsigned int nf_route_table_hook(const struct nf_hook_ops *ops, + struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) +{ + unsigned int ret; + u32 mark; + __be32 saddr, daddr; + u_int8_t tos; + const struct iphdr *iph; + + /* root is playing with raw sockets. */ + if (skb->len < sizeof(struct iphdr) || + ip_hdrlen(skb) < sizeof(struct iphdr)) + return NF_ACCEPT; + + mark = skb->mark; + iph = ip_hdr(skb); + saddr = iph->saddr; + daddr = iph->daddr; + tos = iph->tos; + + ret = nft_do_chain(ops, skb, in, out, okfn); + if (ret != NF_DROP && ret != NF_QUEUE) { + iph = ip_hdr(skb); + + if (iph->saddr != saddr || + iph->daddr != daddr || + skb->mark != mark || + iph->tos != tos) + if (ip_route_me_harder(skb, RTN_UNSPEC)) + ret = NF_DROP; + } + return ret; +} + +static struct nft_base_chain nf_chain_route_output __read_mostly = { + .chain = { + .name = "OUTPUT", + .rules = LIST_HEAD_INIT(nf_chain_route_output.chain.rules), + .flags = NFT_BASE_CHAIN | NFT_CHAIN_BUILTIN, + }, + .ops = { + .hook = nf_route_table_hook, + .owner = THIS_MODULE, + .pf = NFPROTO_IPV4, + .hooknum = NF_INET_LOCAL_OUT, + .priority = NF_IP_PRI_MANGLE, + .priv = &nf_chain_route_output.chain, + }, +}; + +static struct nft_table nf_table_route_ipv4 __read_mostly = { + .name = "route", + .chains = LIST_HEAD_INIT(nf_table_route_ipv4.chains), +}; + +static int __init nf_table_route_init(void) +{ + list_add_tail(&nf_chain_route_output.chain.list, + &nf_table_route_ipv4.chains); + return nft_register_table(&nf_table_route_ipv4, NFPROTO_IPV4); +} + +static void __exit nf_table_route_exit(void) +{ + nft_unregister_table(&nf_table_route_ipv4, NFPROTO_IPV4); +} + +module_init(nf_table_route_init); +module_exit(nf_table_route_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); +MODULE_ALIAS_NFT_TABLE(AF_INET, "route"); diff --git a/net/ipv4/netfilter/nf_tables_ipv4.c b/net/ipv4/netfilter/nf_tables_ipv4.c new file mode 100644 index 0000000..63d0a3b --- /dev/null +++ b/net/ipv4/netfilter/nf_tables_ipv4.c @@ -0,0 +1,59 @@ +/* + * Copyright (c) 2008 Patrick McHardy <kaber@trash.net> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * Development of this code funded by Astaro AG (http://www.astaro.com/) + */ + +#include <linux/init.h> +#include <linux/module.h> +#include <linux/ip.h> +#include <linux/netfilter_ipv4.h> +#include <net/netfilter/nf_tables.h> +#include <net/ip.h> + +static unsigned int nft_ipv4_output(const struct nf_hook_ops *ops, + struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) +{ + if (unlikely(skb->len < sizeof(struct iphdr) || + ip_hdr(skb)->ihl < sizeof(struct iphdr) / 4)) { + if (net_ratelimit()) + pr_info("nf_tables_ipv4: ignoring short SOCK_RAW " + "packet\n"); + return NF_ACCEPT; + } + + return nft_do_chain(ops, skb, in, out, okfn); +} + +static struct nft_af_info nft_af_ipv4 __read_mostly = { + .family = NFPROTO_IPV4, + .nhooks = NF_INET_NUMHOOKS, + .owner = THIS_MODULE, + .hooks = { + [NF_INET_LOCAL_OUT] = nft_ipv4_output, + }, +}; + +static int __init nf_tables_ipv4_init(void) +{ + return nft_register_afinfo(&nft_af_ipv4); +} + +static void __exit nf_tables_ipv4_exit(void) +{ + nft_unregister_afinfo(&nft_af_ipv4); +} + +module_init(nf_tables_ipv4_init); +module_exit(nf_tables_ipv4_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); +MODULE_ALIAS_NFT_FAMILY(AF_INET); diff --git a/net/ipv4/netfilter/nft_reject_ipv4.c b/net/ipv4/netfilter/nft_reject_ipv4.c new file mode 100644 index 0000000..b4ee8d3 --- /dev/null +++ b/net/ipv4/netfilter/nft_reject_ipv4.c @@ -0,0 +1,117 @@ +/* + * Copyright (c) 2008 Patrick McHardy <kaber@trash.net> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * Development of this code funded by Astaro AG (http://www.astaro.com/) + */ + +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/module.h> +#include <linux/netlink.h> +#include <linux/netfilter.h> +#include <linux/netfilter/nf_tables.h> +#include <net/netfilter/nf_tables.h> +#include <net/icmp.h> + +struct nft_reject { + enum nft_reject_types type:8; + u8 icmp_code; +}; + +static void nft_reject_eval(const struct nft_expr *expr, + struct nft_data data[NFT_REG_MAX + 1], + const struct nft_pktinfo *pkt) +{ + struct nft_reject *priv = nft_expr_priv(expr); + + switch (priv->type) { + case NFT_REJECT_ICMP_UNREACH: + icmp_send(pkt->skb, ICMP_DEST_UNREACH, priv->icmp_code, 0); + break; + case NFT_REJECT_TCP_RST: + break; + } + + data[NFT_REG_VERDICT].verdict = NF_DROP; +} + +static const struct nla_policy nft_reject_policy[NFTA_REJECT_MAX + 1] = { + [NFTA_REJECT_TYPE] = { .type = NLA_U32 }, + [NFTA_REJECT_ICMP_CODE] = { .type = NLA_U8 }, +}; + +static int nft_reject_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]) +{ + struct nft_reject *priv = nft_expr_priv(expr); + + if (tb[NFTA_REJECT_TYPE] == NULL) + return -EINVAL; + + priv->type = ntohl(nla_get_be32(tb[NFTA_REJECT_TYPE])); + switch (priv->type) { + case NFT_REJECT_ICMP_UNREACH: + if (tb[NFTA_REJECT_ICMP_CODE] == NULL) + return -EINVAL; + priv->icmp_code = nla_get_u8(tb[NFTA_REJECT_ICMP_CODE]); + case NFT_REJECT_TCP_RST: + break; + default: + return -EINVAL; + } + + return 0; +} + +static int nft_reject_dump(struct sk_buff *skb, const struct nft_expr *expr) +{ + const struct nft_reject *priv = nft_expr_priv(expr); + + if (nla_put_be32(skb, NFTA_REJECT_TYPE, priv->type)) + goto nla_put_failure; + + switch (priv->type) { + case NFT_REJECT_ICMP_UNREACH: + if (nla_put_u8(skb, NFTA_REJECT_ICMP_CODE, priv->icmp_code)) + goto nla_put_failure; + break; + } + + return 0; + +nla_put_failure: + return -1; +} + +static struct nft_expr_ops reject_ops __read_mostly = { + .name = "reject", + .size = NFT_EXPR_SIZE(sizeof(struct nft_reject)), + .owner = THIS_MODULE, + .eval = nft_reject_eval, + .init = nft_reject_init, + .dump = nft_reject_dump, + .policy = nft_reject_policy, + .maxattr = NFTA_REJECT_MAX, +}; + +static int __init nft_reject_module_init(void) +{ + return nft_register_expr(&reject_ops); +} + +static void __exit nft_reject_module_exit(void) +{ + nft_unregister_expr(&reject_ops); +} + +module_init(nft_reject_module_init); +module_exit(nft_reject_module_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); +MODULE_ALIAS_NFT_EXPR("reject"); |