diff options
Diffstat (limited to 'net/ipv6/netfilter')
29 files changed, 6792 insertions, 0 deletions
diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig new file mode 100644 index 000000000..0ba62f486 --- /dev/null +++ b/net/ipv6/netfilter/Kconfig @@ -0,0 +1,288 @@ +# SPDX-License-Identifier: GPL-2.0-only +# +# IP netfilter configuration +# + +menu "IPv6: Netfilter Configuration" + depends on INET && IPV6 && NETFILTER + +config NF_SOCKET_IPV6 + tristate "IPv6 socket lookup support" + help + This option enables the IPv6 socket lookup infrastructure. This + is used by the {ip6,nf}tables socket match. + +config NF_TPROXY_IPV6 + tristate "IPv6 tproxy support" + +if NF_TABLES + +config NF_TABLES_IPV6 + bool "IPv6 nf_tables support" + help + This option enables the IPv6 support for nf_tables. + +if NF_TABLES_IPV6 + +config NFT_REJECT_IPV6 + select NF_REJECT_IPV6 + default NFT_REJECT + tristate + +config NFT_DUP_IPV6 + tristate "IPv6 nf_tables packet duplication support" + depends on !NF_CONNTRACK || NF_CONNTRACK + select NF_DUP_IPV6 + help + This module enables IPv6 packet duplication support for nf_tables. + +config NFT_FIB_IPV6 + tristate "nf_tables fib / ipv6 route lookup support" + select NFT_FIB + help + This module enables IPv6 FIB lookups, e.g. for reverse path filtering. + It also allows query of the FIB for the route type, e.g. local, unicast, + multicast or blackhole. + +endif # NF_TABLES_IPV6 +endif # NF_TABLES + +config NF_DUP_IPV6 + tristate "Netfilter IPv6 packet duplication to alternate destination" + depends on !NF_CONNTRACK || NF_CONNTRACK + help + This option enables the nf_dup_ipv6 core, which duplicates an IPv6 + packet to be rerouted to another destination. + +config NF_REJECT_IPV6 + tristate "IPv6 packet rejection" + default m if NETFILTER_ADVANCED=n + +config NF_LOG_IPV6 + tristate "IPv6 packet logging" + default m if NETFILTER_ADVANCED=n + select NF_LOG_SYSLOG + help + This is a backwards-compat option for the user's convenience + (e.g. when running oldconfig). It selects CONFIG_NF_LOG_SYSLOG. + +config IP6_NF_IPTABLES + tristate "IP6 tables support (required for filtering)" + depends on INET && IPV6 + select NETFILTER_XTABLES + default m if NETFILTER_ADVANCED=n + help + ip6tables is a general, extensible packet identification framework. + Currently only the packet filtering and packet mangling subsystem + for IPv6 use this, but connection tracking is going to follow. + Say 'Y' or 'M' here if you want to use either of those. + + To compile it as a module, choose M here. If unsure, say N. + +if IP6_NF_IPTABLES + +# The simple matches. +config IP6_NF_MATCH_AH + tristate '"ah" match support' + depends on NETFILTER_ADVANCED + help + This module allows one to match AH packets. + + To compile it as a module, choose M here. If unsure, say N. + +config IP6_NF_MATCH_EUI64 + tristate '"eui64" address check' + depends on NETFILTER_ADVANCED + help + This module performs checking on the IPv6 source address + Compares the last 64 bits with the EUI64 (delivered + from the MAC address) address + + To compile it as a module, choose M here. If unsure, say N. + +config IP6_NF_MATCH_FRAG + tristate '"frag" Fragmentation header match support' + depends on NETFILTER_ADVANCED + help + frag matching allows you to match packets based on the fragmentation + header of the packet. + + To compile it as a module, choose M here. If unsure, say N. + +config IP6_NF_MATCH_OPTS + tristate '"hbh" hop-by-hop and "dst" opts header match support' + depends on NETFILTER_ADVANCED + help + This allows one to match packets based on the hop-by-hop + and destination options headers of a packet. + + To compile it as a module, choose M here. If unsure, say N. + +config IP6_NF_MATCH_HL + tristate '"hl" hoplimit match support' + depends on NETFILTER_ADVANCED + select NETFILTER_XT_MATCH_HL + help + This is a backwards-compat option for the user's convenience + (e.g. when running oldconfig). It selects + CONFIG_NETFILTER_XT_MATCH_HL. + +config IP6_NF_MATCH_IPV6HEADER + tristate '"ipv6header" IPv6 Extension Headers Match' + default m if NETFILTER_ADVANCED=n + help + This module allows one to match packets based upon + the ipv6 extension headers. + + To compile it as a module, choose M here. If unsure, say N. + +config IP6_NF_MATCH_MH + tristate '"mh" match support' + depends on NETFILTER_ADVANCED + help + This module allows one to match MH packets. + + To compile it as a module, choose M here. If unsure, say N. + +config IP6_NF_MATCH_RPFILTER + tristate '"rpfilter" reverse path filter match support' + depends on NETFILTER_ADVANCED + depends on IP6_NF_MANGLE || IP6_NF_RAW + help + This option allows you to match packets whose replies would + go out via the interface the packet came in. + + To compile it as a module, choose M here. If unsure, say N. + The module will be called ip6t_rpfilter. + +config IP6_NF_MATCH_RT + tristate '"rt" Routing header match support' + depends on NETFILTER_ADVANCED + help + rt matching allows you to match packets based on the routing + header of the packet. + + To compile it as a module, choose M here. If unsure, say N. + +config IP6_NF_MATCH_SRH + tristate '"srh" Segment Routing header match support' + depends on NETFILTER_ADVANCED + help + srh matching allows you to match packets based on the segment + routing header of the packet. + + To compile it as a module, choose M here. If unsure, say N. + +# The targets +config IP6_NF_TARGET_HL + tristate '"HL" hoplimit target support' + depends on NETFILTER_ADVANCED && IP6_NF_MANGLE + select NETFILTER_XT_TARGET_HL + help + This is a backwards-compatible option for the user's convenience + (e.g. when running oldconfig). It selects + CONFIG_NETFILTER_XT_TARGET_HL. + +config IP6_NF_FILTER + tristate "Packet filtering" + default m if NETFILTER_ADVANCED=n + help + Packet filtering defines a table `filter', which has a series of + rules for simple packet filtering at local input, forwarding and + local output. See the man page for iptables(8). + + To compile it as a module, choose M here. If unsure, say N. + +config IP6_NF_TARGET_REJECT + tristate "REJECT target support" + depends on IP6_NF_FILTER + select NF_REJECT_IPV6 + default m if NETFILTER_ADVANCED=n + help + The REJECT target allows a filtering rule to specify that an ICMPv6 + error should be issued in response to an incoming packet, rather + than silently being dropped. + + To compile it as a module, choose M here. If unsure, say N. + +config IP6_NF_TARGET_SYNPROXY + tristate "SYNPROXY target support" + depends on NF_CONNTRACK && NETFILTER_ADVANCED + select NETFILTER_SYNPROXY + select SYN_COOKIES + help + The SYNPROXY target allows you to intercept TCP connections and + establish them using syncookies before they are passed on to the + server. This allows to avoid conntrack and server resource usage + during SYN-flood attacks. + + To compile it as a module, choose M here. If unsure, say N. + +config IP6_NF_MANGLE + tristate "Packet mangling" + default m if NETFILTER_ADVANCED=n + help + This option adds a `mangle' table to iptables: see the man page for + iptables(8). This table is used for various packet alterations + which can effect how the packet is routed. + + To compile it as a module, choose M here. If unsure, say N. + +config IP6_NF_RAW + tristate 'raw table support (required for TRACE)' + help + This option adds a `raw' table to ip6tables. This table is the very + first in the netfilter framework and hooks in at the PREROUTING + and OUTPUT chains. + + If you want to compile it as a module, say M here and read + <file:Documentation/kbuild/modules.rst>. If unsure, say `N'. + +# security table for MAC policy +config IP6_NF_SECURITY + tristate "Security table" + depends on SECURITY + depends on NETFILTER_ADVANCED + help + This option adds a `security' table to iptables, for use + with Mandatory Access Control (MAC) policy. + + If unsure, say N. + +config IP6_NF_NAT + tristate "ip6tables NAT support" + depends on NF_CONNTRACK + depends on NETFILTER_ADVANCED + select NF_NAT + select NETFILTER_XT_NAT + help + This enables the `nat' table in ip6tables. This allows masquerading, + port forwarding and other forms of full Network Address Port + Translation. + + To compile it as a module, choose M here. If unsure, say N. + +if IP6_NF_NAT + +config IP6_NF_TARGET_MASQUERADE + tristate "MASQUERADE target support" + select NETFILTER_XT_TARGET_MASQUERADE + help + This is a backwards-compat option for the user's convenience + (e.g. when running oldconfig). It selects NETFILTER_XT_TARGET_MASQUERADE. + +config IP6_NF_TARGET_NPT + tristate "NPT (Network Prefix translation) target support" + help + This option adds the `SNPT' and `DNPT' target, which perform + stateless IPv6-to-IPv6 Network Prefix Translation per RFC 6296. + + To compile it as a module, choose M here. If unsure, say N. + +endif # IP6_NF_NAT + +endif # IP6_NF_IPTABLES +endmenu + +config NF_DEFRAG_IPV6 + tristate diff --git a/net/ipv6/netfilter/Makefile b/net/ipv6/netfilter/Makefile new file mode 100644 index 000000000..b8d6dc9ae --- /dev/null +++ b/net/ipv6/netfilter/Makefile @@ -0,0 +1,45 @@ +# SPDX-License-Identifier: GPL-2.0 +# +# Makefile for the netfilter modules on top of IPv6. +# + +# Link order matters here. +obj-$(CONFIG_IP6_NF_IPTABLES) += ip6_tables.o +obj-$(CONFIG_IP6_NF_FILTER) += ip6table_filter.o +obj-$(CONFIG_IP6_NF_MANGLE) += ip6table_mangle.o +obj-$(CONFIG_IP6_NF_RAW) += ip6table_raw.o +obj-$(CONFIG_IP6_NF_SECURITY) += ip6table_security.o +obj-$(CONFIG_IP6_NF_NAT) += ip6table_nat.o + +# defrag +nf_defrag_ipv6-y := nf_defrag_ipv6_hooks.o nf_conntrack_reasm.o +obj-$(CONFIG_NF_DEFRAG_IPV6) += nf_defrag_ipv6.o + +obj-$(CONFIG_NF_SOCKET_IPV6) += nf_socket_ipv6.o +obj-$(CONFIG_NF_TPROXY_IPV6) += nf_tproxy_ipv6.o + +# reject +obj-$(CONFIG_NF_REJECT_IPV6) += nf_reject_ipv6.o + +obj-$(CONFIG_NF_DUP_IPV6) += nf_dup_ipv6.o + +# nf_tables +obj-$(CONFIG_NFT_REJECT_IPV6) += nft_reject_ipv6.o +obj-$(CONFIG_NFT_DUP_IPV6) += nft_dup_ipv6.o +obj-$(CONFIG_NFT_FIB_IPV6) += nft_fib_ipv6.o + +# matches +obj-$(CONFIG_IP6_NF_MATCH_AH) += ip6t_ah.o +obj-$(CONFIG_IP6_NF_MATCH_EUI64) += ip6t_eui64.o +obj-$(CONFIG_IP6_NF_MATCH_FRAG) += ip6t_frag.o +obj-$(CONFIG_IP6_NF_MATCH_IPV6HEADER) += ip6t_ipv6header.o +obj-$(CONFIG_IP6_NF_MATCH_MH) += ip6t_mh.o +obj-$(CONFIG_IP6_NF_MATCH_OPTS) += ip6t_hbh.o +obj-$(CONFIG_IP6_NF_MATCH_RPFILTER) += ip6t_rpfilter.o +obj-$(CONFIG_IP6_NF_MATCH_RT) += ip6t_rt.o +obj-$(CONFIG_IP6_NF_MATCH_SRH) += ip6t_srh.o + +# targets +obj-$(CONFIG_IP6_NF_TARGET_NPT) += ip6t_NPT.o +obj-$(CONFIG_IP6_NF_TARGET_REJECT) += ip6t_REJECT.o +obj-$(CONFIG_IP6_NF_TARGET_SYNPROXY) += ip6t_SYNPROXY.o diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c new file mode 100644 index 000000000..0ce0ed17c --- /dev/null +++ b/net/ipv6/netfilter/ip6_tables.c @@ -0,0 +1,1960 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Packet matching code. + * + * Copyright (C) 1999 Paul `Rusty' Russell & Michael J. Neuling + * Copyright (C) 2000-2005 Netfilter Core Team <coreteam@netfilter.org> + * Copyright (c) 2006-2010 Patrick McHardy <kaber@trash.net> + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/kernel.h> +#include <linux/capability.h> +#include <linux/in.h> +#include <linux/skbuff.h> +#include <linux/kmod.h> +#include <linux/vmalloc.h> +#include <linux/netdevice.h> +#include <linux/module.h> +#include <linux/poison.h> +#include <linux/icmpv6.h> +#include <net/ipv6.h> +#include <net/compat.h> +#include <linux/uaccess.h> +#include <linux/mutex.h> +#include <linux/proc_fs.h> +#include <linux/err.h> +#include <linux/cpumask.h> + +#include <linux/netfilter_ipv6/ip6_tables.h> +#include <linux/netfilter/x_tables.h> +#include <net/netfilter/nf_log.h> +#include "../../netfilter/xt_repldata.h" + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>"); +MODULE_DESCRIPTION("IPv6 packet filter"); +MODULE_ALIAS("ip6t_icmp6"); + +void *ip6t_alloc_initial_table(const struct xt_table *info) +{ + return xt_alloc_initial_table(ip6t, IP6T); +} +EXPORT_SYMBOL_GPL(ip6t_alloc_initial_table); + +/* Returns whether matches rule or not. */ +/* Performance critical - called for every packet */ +static inline bool +ip6_packet_match(const struct sk_buff *skb, + const char *indev, + const char *outdev, + const struct ip6t_ip6 *ip6info, + unsigned int *protoff, + u16 *fragoff, bool *hotdrop) +{ + unsigned long ret; + const struct ipv6hdr *ipv6 = ipv6_hdr(skb); + + if (NF_INVF(ip6info, IP6T_INV_SRCIP, + ipv6_masked_addr_cmp(&ipv6->saddr, &ip6info->smsk, + &ip6info->src)) || + NF_INVF(ip6info, IP6T_INV_DSTIP, + ipv6_masked_addr_cmp(&ipv6->daddr, &ip6info->dmsk, + &ip6info->dst))) + return false; + + ret = ifname_compare_aligned(indev, ip6info->iniface, ip6info->iniface_mask); + + if (NF_INVF(ip6info, IP6T_INV_VIA_IN, ret != 0)) + return false; + + ret = ifname_compare_aligned(outdev, ip6info->outiface, ip6info->outiface_mask); + + if (NF_INVF(ip6info, IP6T_INV_VIA_OUT, ret != 0)) + return false; + +/* ... might want to do something with class and flowlabel here ... */ + + /* look for the desired protocol header */ + if (ip6info->flags & IP6T_F_PROTO) { + int protohdr; + unsigned short _frag_off; + + protohdr = ipv6_find_hdr(skb, protoff, -1, &_frag_off, NULL); + if (protohdr < 0) { + if (_frag_off == 0) + *hotdrop = true; + return false; + } + *fragoff = _frag_off; + + if (ip6info->proto == protohdr) { + if (ip6info->invflags & IP6T_INV_PROTO) + return false; + + return true; + } + + /* We need match for the '-p all', too! */ + if ((ip6info->proto != 0) && + !(ip6info->invflags & IP6T_INV_PROTO)) + return false; + } + return true; +} + +/* should be ip6 safe */ +static bool +ip6_checkentry(const struct ip6t_ip6 *ipv6) +{ + if (ipv6->flags & ~IP6T_F_MASK) + return false; + if (ipv6->invflags & ~IP6T_INV_MASK) + return false; + + return true; +} + +static unsigned int +ip6t_error(struct sk_buff *skb, const struct xt_action_param *par) +{ + net_info_ratelimited("error: `%s'\n", (const char *)par->targinfo); + + return NF_DROP; +} + +static inline struct ip6t_entry * +get_entry(const void *base, unsigned int offset) +{ + return (struct ip6t_entry *)(base + offset); +} + +/* All zeroes == unconditional rule. */ +/* Mildly perf critical (only if packet tracing is on) */ +static inline bool unconditional(const struct ip6t_entry *e) +{ + static const struct ip6t_ip6 uncond; + + return e->target_offset == sizeof(struct ip6t_entry) && + memcmp(&e->ipv6, &uncond, sizeof(uncond)) == 0; +} + +static inline const struct xt_entry_target * +ip6t_get_target_c(const struct ip6t_entry *e) +{ + return ip6t_get_target((struct ip6t_entry *)e); +} + +#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) +/* This cries for unification! */ +static const char *const hooknames[] = { + [NF_INET_PRE_ROUTING] = "PREROUTING", + [NF_INET_LOCAL_IN] = "INPUT", + [NF_INET_FORWARD] = "FORWARD", + [NF_INET_LOCAL_OUT] = "OUTPUT", + [NF_INET_POST_ROUTING] = "POSTROUTING", +}; + +enum nf_ip_trace_comments { + NF_IP6_TRACE_COMMENT_RULE, + NF_IP6_TRACE_COMMENT_RETURN, + NF_IP6_TRACE_COMMENT_POLICY, +}; + +static const char *const comments[] = { + [NF_IP6_TRACE_COMMENT_RULE] = "rule", + [NF_IP6_TRACE_COMMENT_RETURN] = "return", + [NF_IP6_TRACE_COMMENT_POLICY] = "policy", +}; + +static const struct nf_loginfo trace_loginfo = { + .type = NF_LOG_TYPE_LOG, + .u = { + .log = { + .level = LOGLEVEL_WARNING, + .logflags = NF_LOG_DEFAULT_MASK, + }, + }, +}; + +/* Mildly perf critical (only if packet tracing is on) */ +static inline int +get_chainname_rulenum(const struct ip6t_entry *s, const struct ip6t_entry *e, + const char *hookname, const char **chainname, + const char **comment, unsigned int *rulenum) +{ + const struct xt_standard_target *t = (void *)ip6t_get_target_c(s); + + if (strcmp(t->target.u.kernel.target->name, XT_ERROR_TARGET) == 0) { + /* Head of user chain: ERROR target with chainname */ + *chainname = t->target.data; + (*rulenum) = 0; + } else if (s == e) { + (*rulenum)++; + + if (unconditional(s) && + strcmp(t->target.u.kernel.target->name, + XT_STANDARD_TARGET) == 0 && + t->verdict < 0) { + /* Tail of chains: STANDARD target (return/policy) */ + *comment = *chainname == hookname + ? comments[NF_IP6_TRACE_COMMENT_POLICY] + : comments[NF_IP6_TRACE_COMMENT_RETURN]; + } + return 1; + } else + (*rulenum)++; + + return 0; +} + +static void trace_packet(struct net *net, + const struct sk_buff *skb, + unsigned int hook, + const struct net_device *in, + const struct net_device *out, + const char *tablename, + const struct xt_table_info *private, + const struct ip6t_entry *e) +{ + const struct ip6t_entry *root; + const char *hookname, *chainname, *comment; + const struct ip6t_entry *iter; + unsigned int rulenum = 0; + + root = get_entry(private->entries, private->hook_entry[hook]); + + hookname = chainname = hooknames[hook]; + comment = comments[NF_IP6_TRACE_COMMENT_RULE]; + + xt_entry_foreach(iter, root, private->size - private->hook_entry[hook]) + if (get_chainname_rulenum(iter, e, hookname, + &chainname, &comment, &rulenum) != 0) + break; + + nf_log_trace(net, AF_INET6, hook, skb, in, out, &trace_loginfo, + "TRACE: %s:%s:%s:%u ", + tablename, chainname, comment, rulenum); +} +#endif + +static inline struct ip6t_entry * +ip6t_next_entry(const struct ip6t_entry *entry) +{ + return (void *)entry + entry->next_offset; +} + +/* Returns one of the generic firewall policies, like NF_ACCEPT. */ +unsigned int +ip6t_do_table(void *priv, struct sk_buff *skb, + const struct nf_hook_state *state) +{ + const struct xt_table *table = priv; + unsigned int hook = state->hook; + static const char nulldevname[IFNAMSIZ] __attribute__((aligned(sizeof(long)))); + /* Initializing verdict to NF_DROP keeps gcc happy. */ + unsigned int verdict = NF_DROP; + const char *indev, *outdev; + const void *table_base; + struct ip6t_entry *e, **jumpstack; + unsigned int stackidx, cpu; + const struct xt_table_info *private; + struct xt_action_param acpar; + unsigned int addend; + + /* Initialization */ + stackidx = 0; + indev = state->in ? state->in->name : nulldevname; + outdev = state->out ? state->out->name : nulldevname; + /* We handle fragments by dealing with the first fragment as + * if it was a normal packet. All other fragments are treated + * normally, except that they will NEVER match rules that ask + * things we don't know, ie. tcp syn flag or ports). If the + * rule is also a fragment-specific rule, non-fragments won't + * match it. */ + acpar.fragoff = 0; + acpar.hotdrop = false; + acpar.state = state; + + WARN_ON(!(table->valid_hooks & (1 << hook))); + + local_bh_disable(); + addend = xt_write_recseq_begin(); + private = READ_ONCE(table->private); /* Address dependency. */ + cpu = smp_processor_id(); + table_base = private->entries; + jumpstack = (struct ip6t_entry **)private->jumpstack[cpu]; + + /* Switch to alternate jumpstack if we're being invoked via TEE. + * TEE issues XT_CONTINUE verdict on original skb so we must not + * clobber the jumpstack. + * + * For recursion via REJECT or SYNPROXY the stack will be clobbered + * but it is no problem since absolute verdict is issued by these. + */ + if (static_key_false(&xt_tee_enabled)) + jumpstack += private->stacksize * __this_cpu_read(nf_skb_duplicated); + + e = get_entry(table_base, private->hook_entry[hook]); + + do { + const struct xt_entry_target *t; + const struct xt_entry_match *ematch; + struct xt_counters *counter; + + WARN_ON(!e); + acpar.thoff = 0; + if (!ip6_packet_match(skb, indev, outdev, &e->ipv6, + &acpar.thoff, &acpar.fragoff, &acpar.hotdrop)) { + no_match: + e = ip6t_next_entry(e); + continue; + } + + xt_ematch_foreach(ematch, e) { + acpar.match = ematch->u.kernel.match; + acpar.matchinfo = ematch->data; + if (!acpar.match->match(skb, &acpar)) + goto no_match; + } + + counter = xt_get_this_cpu_counter(&e->counters); + ADD_COUNTER(*counter, skb->len, 1); + + t = ip6t_get_target_c(e); + WARN_ON(!t->u.kernel.target); + +#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) + /* The packet is traced: log it */ + if (unlikely(skb->nf_trace)) + trace_packet(state->net, skb, hook, state->in, + state->out, table->name, private, e); +#endif + /* Standard target? */ + if (!t->u.kernel.target->target) { + int v; + + v = ((struct xt_standard_target *)t)->verdict; + if (v < 0) { + /* Pop from stack? */ + if (v != XT_RETURN) { + verdict = (unsigned int)(-v) - 1; + break; + } + if (stackidx == 0) + e = get_entry(table_base, + private->underflow[hook]); + else + e = ip6t_next_entry(jumpstack[--stackidx]); + continue; + } + if (table_base + v != ip6t_next_entry(e) && + !(e->ipv6.flags & IP6T_F_GOTO)) { + if (unlikely(stackidx >= private->stacksize)) { + verdict = NF_DROP; + break; + } + jumpstack[stackidx++] = e; + } + + e = get_entry(table_base, v); + continue; + } + + acpar.target = t->u.kernel.target; + acpar.targinfo = t->data; + + verdict = t->u.kernel.target->target(skb, &acpar); + if (verdict == XT_CONTINUE) + e = ip6t_next_entry(e); + else + /* Verdict */ + break; + } while (!acpar.hotdrop); + + xt_write_recseq_end(addend); + local_bh_enable(); + + if (acpar.hotdrop) + return NF_DROP; + else return verdict; +} + +/* Figures out from what hook each rule can be called: returns 0 if + there are loops. Puts hook bitmask in comefrom. */ +static int +mark_source_chains(const struct xt_table_info *newinfo, + unsigned int valid_hooks, void *entry0, + unsigned int *offsets) +{ + unsigned int hook; + + /* No recursion; use packet counter to save back ptrs (reset + to 0 as we leave), and comefrom to save source hook bitmask */ + for (hook = 0; hook < NF_INET_NUMHOOKS; hook++) { + unsigned int pos = newinfo->hook_entry[hook]; + struct ip6t_entry *e = entry0 + pos; + + if (!(valid_hooks & (1 << hook))) + continue; + + /* Set initial back pointer. */ + e->counters.pcnt = pos; + + for (;;) { + const struct xt_standard_target *t + = (void *)ip6t_get_target_c(e); + int visited = e->comefrom & (1 << hook); + + if (e->comefrom & (1 << NF_INET_NUMHOOKS)) + return 0; + + e->comefrom |= ((1 << hook) | (1 << NF_INET_NUMHOOKS)); + + /* Unconditional return/END. */ + if ((unconditional(e) && + (strcmp(t->target.u.user.name, + XT_STANDARD_TARGET) == 0) && + t->verdict < 0) || visited) { + unsigned int oldpos, size; + + /* Return: backtrack through the last + big jump. */ + do { + e->comefrom ^= (1<<NF_INET_NUMHOOKS); + oldpos = pos; + pos = e->counters.pcnt; + e->counters.pcnt = 0; + + /* We're at the start. */ + if (pos == oldpos) + goto next; + + e = entry0 + pos; + } while (oldpos == pos + e->next_offset); + + /* Move along one */ + size = e->next_offset; + e = entry0 + pos + size; + if (pos + size >= newinfo->size) + return 0; + e->counters.pcnt = pos; + pos += size; + } else { + int newpos = t->verdict; + + if (strcmp(t->target.u.user.name, + XT_STANDARD_TARGET) == 0 && + newpos >= 0) { + /* This a jump; chase it. */ + if (!xt_find_jump_offset(offsets, newpos, + newinfo->number)) + return 0; + } else { + /* ... this is a fallthru */ + newpos = pos + e->next_offset; + if (newpos >= newinfo->size) + return 0; + } + e = entry0 + newpos; + e->counters.pcnt = pos; + pos = newpos; + } + } +next: ; + } + return 1; +} + +static void cleanup_match(struct xt_entry_match *m, struct net *net) +{ + struct xt_mtdtor_param par; + + par.net = net; + par.match = m->u.kernel.match; + par.matchinfo = m->data; + par.family = NFPROTO_IPV6; + if (par.match->destroy != NULL) + par.match->destroy(&par); + module_put(par.match->me); +} + +static int check_match(struct xt_entry_match *m, struct xt_mtchk_param *par) +{ + const struct ip6t_ip6 *ipv6 = par->entryinfo; + + par->match = m->u.kernel.match; + par->matchinfo = m->data; + + return xt_check_match(par, m->u.match_size - sizeof(*m), + ipv6->proto, ipv6->invflags & IP6T_INV_PROTO); +} + +static int +find_check_match(struct xt_entry_match *m, struct xt_mtchk_param *par) +{ + struct xt_match *match; + int ret; + + match = xt_request_find_match(NFPROTO_IPV6, m->u.user.name, + m->u.user.revision); + if (IS_ERR(match)) + return PTR_ERR(match); + + m->u.kernel.match = match; + + ret = check_match(m, par); + if (ret) + goto err; + + return 0; +err: + module_put(m->u.kernel.match->me); + return ret; +} + +static int check_target(struct ip6t_entry *e, struct net *net, const char *name) +{ + struct xt_entry_target *t = ip6t_get_target(e); + struct xt_tgchk_param par = { + .net = net, + .table = name, + .entryinfo = e, + .target = t->u.kernel.target, + .targinfo = t->data, + .hook_mask = e->comefrom, + .family = NFPROTO_IPV6, + }; + + return xt_check_target(&par, t->u.target_size - sizeof(*t), + e->ipv6.proto, + e->ipv6.invflags & IP6T_INV_PROTO); +} + +static int +find_check_entry(struct ip6t_entry *e, struct net *net, const char *name, + unsigned int size, + struct xt_percpu_counter_alloc_state *alloc_state) +{ + struct xt_entry_target *t; + struct xt_target *target; + int ret; + unsigned int j; + struct xt_mtchk_param mtpar; + struct xt_entry_match *ematch; + + if (!xt_percpu_counter_alloc(alloc_state, &e->counters)) + return -ENOMEM; + + j = 0; + memset(&mtpar, 0, sizeof(mtpar)); + mtpar.net = net; + mtpar.table = name; + mtpar.entryinfo = &e->ipv6; + mtpar.hook_mask = e->comefrom; + mtpar.family = NFPROTO_IPV6; + xt_ematch_foreach(ematch, e) { + ret = find_check_match(ematch, &mtpar); + if (ret != 0) + goto cleanup_matches; + ++j; + } + + t = ip6t_get_target(e); + target = xt_request_find_target(NFPROTO_IPV6, t->u.user.name, + t->u.user.revision); + if (IS_ERR(target)) { + ret = PTR_ERR(target); + goto cleanup_matches; + } + t->u.kernel.target = target; + + ret = check_target(e, net, name); + if (ret) + goto err; + return 0; + err: + module_put(t->u.kernel.target->me); + cleanup_matches: + xt_ematch_foreach(ematch, e) { + if (j-- == 0) + break; + cleanup_match(ematch, net); + } + + xt_percpu_counter_free(&e->counters); + + return ret; +} + +static bool check_underflow(const struct ip6t_entry *e) +{ + const struct xt_entry_target *t; + unsigned int verdict; + + if (!unconditional(e)) + return false; + t = ip6t_get_target_c(e); + if (strcmp(t->u.user.name, XT_STANDARD_TARGET) != 0) + return false; + verdict = ((struct xt_standard_target *)t)->verdict; + verdict = -verdict - 1; + return verdict == NF_DROP || verdict == NF_ACCEPT; +} + +static int +check_entry_size_and_hooks(struct ip6t_entry *e, + struct xt_table_info *newinfo, + const unsigned char *base, + const unsigned char *limit, + const unsigned int *hook_entries, + const unsigned int *underflows, + unsigned int valid_hooks) +{ + unsigned int h; + int err; + + if ((unsigned long)e % __alignof__(struct ip6t_entry) != 0 || + (unsigned char *)e + sizeof(struct ip6t_entry) >= limit || + (unsigned char *)e + e->next_offset > limit) + return -EINVAL; + + if (e->next_offset + < sizeof(struct ip6t_entry) + sizeof(struct xt_entry_target)) + return -EINVAL; + + if (!ip6_checkentry(&e->ipv6)) + return -EINVAL; + + err = xt_check_entry_offsets(e, e->elems, e->target_offset, + e->next_offset); + if (err) + return err; + + /* Check hooks & underflows */ + for (h = 0; h < NF_INET_NUMHOOKS; h++) { + if (!(valid_hooks & (1 << h))) + continue; + if ((unsigned char *)e - base == hook_entries[h]) + newinfo->hook_entry[h] = hook_entries[h]; + if ((unsigned char *)e - base == underflows[h]) { + if (!check_underflow(e)) + return -EINVAL; + + newinfo->underflow[h] = underflows[h]; + } + } + + /* Clear counters and comefrom */ + e->counters = ((struct xt_counters) { 0, 0 }); + e->comefrom = 0; + return 0; +} + +static void cleanup_entry(struct ip6t_entry *e, struct net *net) +{ + struct xt_tgdtor_param par; + struct xt_entry_target *t; + struct xt_entry_match *ematch; + + /* Cleanup all matches */ + xt_ematch_foreach(ematch, e) + cleanup_match(ematch, net); + t = ip6t_get_target(e); + + par.net = net; + par.target = t->u.kernel.target; + par.targinfo = t->data; + par.family = NFPROTO_IPV6; + if (par.target->destroy != NULL) + par.target->destroy(&par); + module_put(par.target->me); + xt_percpu_counter_free(&e->counters); +} + +/* Checks and translates the user-supplied table segment (held in + newinfo) */ +static int +translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0, + const struct ip6t_replace *repl) +{ + struct xt_percpu_counter_alloc_state alloc_state = { 0 }; + struct ip6t_entry *iter; + unsigned int *offsets; + unsigned int i; + int ret = 0; + + newinfo->size = repl->size; + newinfo->number = repl->num_entries; + + /* Init all hooks to impossible value. */ + for (i = 0; i < NF_INET_NUMHOOKS; i++) { + newinfo->hook_entry[i] = 0xFFFFFFFF; + newinfo->underflow[i] = 0xFFFFFFFF; + } + + offsets = xt_alloc_entry_offsets(newinfo->number); + if (!offsets) + return -ENOMEM; + i = 0; + /* Walk through entries, checking offsets. */ + xt_entry_foreach(iter, entry0, newinfo->size) { + ret = check_entry_size_and_hooks(iter, newinfo, entry0, + entry0 + repl->size, + repl->hook_entry, + repl->underflow, + repl->valid_hooks); + if (ret != 0) + goto out_free; + if (i < repl->num_entries) + offsets[i] = (void *)iter - entry0; + ++i; + if (strcmp(ip6t_get_target(iter)->u.user.name, + XT_ERROR_TARGET) == 0) + ++newinfo->stacksize; + } + + ret = -EINVAL; + if (i != repl->num_entries) + goto out_free; + + ret = xt_check_table_hooks(newinfo, repl->valid_hooks); + if (ret) + goto out_free; + + if (!mark_source_chains(newinfo, repl->valid_hooks, entry0, offsets)) { + ret = -ELOOP; + goto out_free; + } + kvfree(offsets); + + /* Finally, each sanity check must pass */ + i = 0; + xt_entry_foreach(iter, entry0, newinfo->size) { + ret = find_check_entry(iter, net, repl->name, repl->size, + &alloc_state); + if (ret != 0) + break; + ++i; + } + + if (ret != 0) { + xt_entry_foreach(iter, entry0, newinfo->size) { + if (i-- == 0) + break; + cleanup_entry(iter, net); + } + return ret; + } + + return ret; + out_free: + kvfree(offsets); + return ret; +} + +static void +get_counters(const struct xt_table_info *t, + struct xt_counters counters[]) +{ + struct ip6t_entry *iter; + unsigned int cpu; + unsigned int i; + + for_each_possible_cpu(cpu) { + seqcount_t *s = &per_cpu(xt_recseq, cpu); + + i = 0; + xt_entry_foreach(iter, t->entries, t->size) { + struct xt_counters *tmp; + u64 bcnt, pcnt; + unsigned int start; + + tmp = xt_get_per_cpu_counter(&iter->counters, cpu); + do { + start = read_seqcount_begin(s); + bcnt = tmp->bcnt; + pcnt = tmp->pcnt; + } while (read_seqcount_retry(s, start)); + + ADD_COUNTER(counters[i], bcnt, pcnt); + ++i; + cond_resched(); + } + } +} + +static void get_old_counters(const struct xt_table_info *t, + struct xt_counters counters[]) +{ + struct ip6t_entry *iter; + unsigned int cpu, i; + + for_each_possible_cpu(cpu) { + i = 0; + xt_entry_foreach(iter, t->entries, t->size) { + const struct xt_counters *tmp; + + tmp = xt_get_per_cpu_counter(&iter->counters, cpu); + ADD_COUNTER(counters[i], tmp->bcnt, tmp->pcnt); + ++i; + } + cond_resched(); + } +} + +static struct xt_counters *alloc_counters(const struct xt_table *table) +{ + unsigned int countersize; + struct xt_counters *counters; + const struct xt_table_info *private = table->private; + + /* We need atomic snapshot of counters: rest doesn't change + (other than comefrom, which userspace doesn't care + about). */ + countersize = sizeof(struct xt_counters) * private->number; + counters = vzalloc(countersize); + + if (counters == NULL) + return ERR_PTR(-ENOMEM); + + get_counters(private, counters); + + return counters; +} + +static int +copy_entries_to_user(unsigned int total_size, + const struct xt_table *table, + void __user *userptr) +{ + unsigned int off, num; + const struct ip6t_entry *e; + struct xt_counters *counters; + const struct xt_table_info *private = table->private; + int ret = 0; + const void *loc_cpu_entry; + + counters = alloc_counters(table); + if (IS_ERR(counters)) + return PTR_ERR(counters); + + loc_cpu_entry = private->entries; + + /* FIXME: use iterator macros --RR */ + /* ... then go back and fix counters and names */ + for (off = 0, num = 0; off < total_size; off += e->next_offset, num++){ + unsigned int i; + const struct xt_entry_match *m; + const struct xt_entry_target *t; + + e = loc_cpu_entry + off; + if (copy_to_user(userptr + off, e, sizeof(*e))) { + ret = -EFAULT; + goto free_counters; + } + if (copy_to_user(userptr + off + + offsetof(struct ip6t_entry, counters), + &counters[num], + sizeof(counters[num])) != 0) { + ret = -EFAULT; + goto free_counters; + } + + for (i = sizeof(struct ip6t_entry); + i < e->target_offset; + i += m->u.match_size) { + m = (void *)e + i; + + if (xt_match_to_user(m, userptr + off + i)) { + ret = -EFAULT; + goto free_counters; + } + } + + t = ip6t_get_target_c(e); + if (xt_target_to_user(t, userptr + off + e->target_offset)) { + ret = -EFAULT; + goto free_counters; + } + } + + free_counters: + vfree(counters); + return ret; +} + +#ifdef CONFIG_NETFILTER_XTABLES_COMPAT +static void compat_standard_from_user(void *dst, const void *src) +{ + int v = *(compat_int_t *)src; + + if (v > 0) + v += xt_compat_calc_jump(AF_INET6, v); + memcpy(dst, &v, sizeof(v)); +} + +static int compat_standard_to_user(void __user *dst, const void *src) +{ + compat_int_t cv = *(int *)src; + + if (cv > 0) + cv -= xt_compat_calc_jump(AF_INET6, cv); + return copy_to_user(dst, &cv, sizeof(cv)) ? -EFAULT : 0; +} + +static int compat_calc_entry(const struct ip6t_entry *e, + const struct xt_table_info *info, + const void *base, struct xt_table_info *newinfo) +{ + const struct xt_entry_match *ematch; + const struct xt_entry_target *t; + unsigned int entry_offset; + int off, i, ret; + + off = sizeof(struct ip6t_entry) - sizeof(struct compat_ip6t_entry); + entry_offset = (void *)e - base; + xt_ematch_foreach(ematch, e) + off += xt_compat_match_offset(ematch->u.kernel.match); + t = ip6t_get_target_c(e); + off += xt_compat_target_offset(t->u.kernel.target); + newinfo->size -= off; + ret = xt_compat_add_offset(AF_INET6, entry_offset, off); + if (ret) + return ret; + + for (i = 0; i < NF_INET_NUMHOOKS; i++) { + if (info->hook_entry[i] && + (e < (struct ip6t_entry *)(base + info->hook_entry[i]))) + newinfo->hook_entry[i] -= off; + if (info->underflow[i] && + (e < (struct ip6t_entry *)(base + info->underflow[i]))) + newinfo->underflow[i] -= off; + } + return 0; +} + +static int compat_table_info(const struct xt_table_info *info, + struct xt_table_info *newinfo) +{ + struct ip6t_entry *iter; + const void *loc_cpu_entry; + int ret; + + if (!newinfo || !info) + return -EINVAL; + + /* we dont care about newinfo->entries */ + memcpy(newinfo, info, offsetof(struct xt_table_info, entries)); + newinfo->initial_entries = 0; + loc_cpu_entry = info->entries; + ret = xt_compat_init_offsets(AF_INET6, info->number); + if (ret) + return ret; + xt_entry_foreach(iter, loc_cpu_entry, info->size) { + ret = compat_calc_entry(iter, info, loc_cpu_entry, newinfo); + if (ret != 0) + return ret; + } + return 0; +} +#endif + +static int get_info(struct net *net, void __user *user, const int *len) +{ + char name[XT_TABLE_MAXNAMELEN]; + struct xt_table *t; + int ret; + + if (*len != sizeof(struct ip6t_getinfo)) + return -EINVAL; + + if (copy_from_user(name, user, sizeof(name)) != 0) + return -EFAULT; + + name[XT_TABLE_MAXNAMELEN-1] = '\0'; +#ifdef CONFIG_NETFILTER_XTABLES_COMPAT + if (in_compat_syscall()) + xt_compat_lock(AF_INET6); +#endif + t = xt_request_find_table_lock(net, AF_INET6, name); + if (!IS_ERR(t)) { + struct ip6t_getinfo info; + const struct xt_table_info *private = t->private; +#ifdef CONFIG_NETFILTER_XTABLES_COMPAT + struct xt_table_info tmp; + + if (in_compat_syscall()) { + ret = compat_table_info(private, &tmp); + xt_compat_flush_offsets(AF_INET6); + private = &tmp; + } +#endif + memset(&info, 0, sizeof(info)); + info.valid_hooks = t->valid_hooks; + memcpy(info.hook_entry, private->hook_entry, + sizeof(info.hook_entry)); + memcpy(info.underflow, private->underflow, + sizeof(info.underflow)); + info.num_entries = private->number; + info.size = private->size; + strcpy(info.name, name); + + if (copy_to_user(user, &info, *len) != 0) + ret = -EFAULT; + else + ret = 0; + + xt_table_unlock(t); + module_put(t->me); + } else + ret = PTR_ERR(t); +#ifdef CONFIG_NETFILTER_XTABLES_COMPAT + if (in_compat_syscall()) + xt_compat_unlock(AF_INET6); +#endif + return ret; +} + +static int +get_entries(struct net *net, struct ip6t_get_entries __user *uptr, + const int *len) +{ + int ret; + struct ip6t_get_entries get; + struct xt_table *t; + + if (*len < sizeof(get)) + return -EINVAL; + if (copy_from_user(&get, uptr, sizeof(get)) != 0) + return -EFAULT; + if (*len != sizeof(struct ip6t_get_entries) + get.size) + return -EINVAL; + + get.name[sizeof(get.name) - 1] = '\0'; + + t = xt_find_table_lock(net, AF_INET6, get.name); + if (!IS_ERR(t)) { + struct xt_table_info *private = t->private; + if (get.size == private->size) + ret = copy_entries_to_user(private->size, + t, uptr->entrytable); + else + ret = -EAGAIN; + + module_put(t->me); + xt_table_unlock(t); + } else + ret = PTR_ERR(t); + + return ret; +} + +static int +__do_replace(struct net *net, const char *name, unsigned int valid_hooks, + struct xt_table_info *newinfo, unsigned int num_counters, + void __user *counters_ptr) +{ + int ret; + struct xt_table *t; + struct xt_table_info *oldinfo; + struct xt_counters *counters; + struct ip6t_entry *iter; + + counters = xt_counters_alloc(num_counters); + if (!counters) { + ret = -ENOMEM; + goto out; + } + + t = xt_request_find_table_lock(net, AF_INET6, name); + if (IS_ERR(t)) { + ret = PTR_ERR(t); + goto free_newinfo_counters_untrans; + } + + /* You lied! */ + if (valid_hooks != t->valid_hooks) { + ret = -EINVAL; + goto put_module; + } + + oldinfo = xt_replace_table(t, num_counters, newinfo, &ret); + if (!oldinfo) + goto put_module; + + /* Update module usage count based on number of rules */ + if ((oldinfo->number > oldinfo->initial_entries) || + (newinfo->number <= oldinfo->initial_entries)) + module_put(t->me); + if ((oldinfo->number > oldinfo->initial_entries) && + (newinfo->number <= oldinfo->initial_entries)) + module_put(t->me); + + xt_table_unlock(t); + + get_old_counters(oldinfo, counters); + + /* Decrease module usage counts and free resource */ + xt_entry_foreach(iter, oldinfo->entries, oldinfo->size) + cleanup_entry(iter, net); + + xt_free_table_info(oldinfo); + if (copy_to_user(counters_ptr, counters, + sizeof(struct xt_counters) * num_counters) != 0) { + /* Silent error, can't fail, new table is already in place */ + net_warn_ratelimited("ip6tables: counters copy to user failed while replacing table\n"); + } + vfree(counters); + return 0; + + put_module: + module_put(t->me); + xt_table_unlock(t); + free_newinfo_counters_untrans: + vfree(counters); + out: + return ret; +} + +static int +do_replace(struct net *net, sockptr_t arg, unsigned int len) +{ + int ret; + struct ip6t_replace tmp; + struct xt_table_info *newinfo; + void *loc_cpu_entry; + struct ip6t_entry *iter; + + if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0) + return -EFAULT; + + /* overflow check */ + if (tmp.num_counters >= INT_MAX / sizeof(struct xt_counters)) + return -ENOMEM; + if (tmp.num_counters == 0) + return -EINVAL; + + tmp.name[sizeof(tmp.name)-1] = 0; + + newinfo = xt_alloc_table_info(tmp.size); + if (!newinfo) + return -ENOMEM; + + loc_cpu_entry = newinfo->entries; + if (copy_from_sockptr_offset(loc_cpu_entry, arg, sizeof(tmp), + tmp.size) != 0) { + ret = -EFAULT; + goto free_newinfo; + } + + ret = translate_table(net, newinfo, loc_cpu_entry, &tmp); + if (ret != 0) + goto free_newinfo; + + ret = __do_replace(net, tmp.name, tmp.valid_hooks, newinfo, + tmp.num_counters, tmp.counters); + if (ret) + goto free_newinfo_untrans; + return 0; + + free_newinfo_untrans: + xt_entry_foreach(iter, loc_cpu_entry, newinfo->size) + cleanup_entry(iter, net); + free_newinfo: + xt_free_table_info(newinfo); + return ret; +} + +static int +do_add_counters(struct net *net, sockptr_t arg, unsigned int len) +{ + unsigned int i; + struct xt_counters_info tmp; + struct xt_counters *paddc; + struct xt_table *t; + const struct xt_table_info *private; + int ret = 0; + struct ip6t_entry *iter; + unsigned int addend; + + paddc = xt_copy_counters(arg, len, &tmp); + if (IS_ERR(paddc)) + return PTR_ERR(paddc); + t = xt_find_table_lock(net, AF_INET6, tmp.name); + if (IS_ERR(t)) { + ret = PTR_ERR(t); + goto free; + } + + local_bh_disable(); + private = t->private; + if (private->number != tmp.num_counters) { + ret = -EINVAL; + goto unlock_up_free; + } + + i = 0; + addend = xt_write_recseq_begin(); + xt_entry_foreach(iter, private->entries, private->size) { + struct xt_counters *tmp; + + tmp = xt_get_this_cpu_counter(&iter->counters); + ADD_COUNTER(*tmp, paddc[i].bcnt, paddc[i].pcnt); + ++i; + } + xt_write_recseq_end(addend); + unlock_up_free: + local_bh_enable(); + xt_table_unlock(t); + module_put(t->me); + free: + vfree(paddc); + + return ret; +} + +#ifdef CONFIG_NETFILTER_XTABLES_COMPAT +struct compat_ip6t_replace { + char name[XT_TABLE_MAXNAMELEN]; + u32 valid_hooks; + u32 num_entries; + u32 size; + u32 hook_entry[NF_INET_NUMHOOKS]; + u32 underflow[NF_INET_NUMHOOKS]; + u32 num_counters; + compat_uptr_t counters; /* struct xt_counters * */ + struct compat_ip6t_entry entries[]; +}; + +static int +compat_copy_entry_to_user(struct ip6t_entry *e, void __user **dstptr, + unsigned int *size, struct xt_counters *counters, + unsigned int i) +{ + struct xt_entry_target *t; + struct compat_ip6t_entry __user *ce; + u_int16_t target_offset, next_offset; + compat_uint_t origsize; + const struct xt_entry_match *ematch; + int ret = 0; + + origsize = *size; + ce = *dstptr; + if (copy_to_user(ce, e, sizeof(struct ip6t_entry)) != 0 || + copy_to_user(&ce->counters, &counters[i], + sizeof(counters[i])) != 0) + return -EFAULT; + + *dstptr += sizeof(struct compat_ip6t_entry); + *size -= sizeof(struct ip6t_entry) - sizeof(struct compat_ip6t_entry); + + xt_ematch_foreach(ematch, e) { + ret = xt_compat_match_to_user(ematch, dstptr, size); + if (ret != 0) + return ret; + } + target_offset = e->target_offset - (origsize - *size); + t = ip6t_get_target(e); + ret = xt_compat_target_to_user(t, dstptr, size); + if (ret) + return ret; + next_offset = e->next_offset - (origsize - *size); + if (put_user(target_offset, &ce->target_offset) != 0 || + put_user(next_offset, &ce->next_offset) != 0) + return -EFAULT; + return 0; +} + +static int +compat_find_calc_match(struct xt_entry_match *m, + const struct ip6t_ip6 *ipv6, + int *size) +{ + struct xt_match *match; + + match = xt_request_find_match(NFPROTO_IPV6, m->u.user.name, + m->u.user.revision); + if (IS_ERR(match)) + return PTR_ERR(match); + + m->u.kernel.match = match; + *size += xt_compat_match_offset(match); + return 0; +} + +static void compat_release_entry(struct compat_ip6t_entry *e) +{ + struct xt_entry_target *t; + struct xt_entry_match *ematch; + + /* Cleanup all matches */ + xt_ematch_foreach(ematch, e) + module_put(ematch->u.kernel.match->me); + t = compat_ip6t_get_target(e); + module_put(t->u.kernel.target->me); +} + +static int +check_compat_entry_size_and_hooks(struct compat_ip6t_entry *e, + struct xt_table_info *newinfo, + unsigned int *size, + const unsigned char *base, + const unsigned char *limit) +{ + struct xt_entry_match *ematch; + struct xt_entry_target *t; + struct xt_target *target; + unsigned int entry_offset; + unsigned int j; + int ret, off; + + if ((unsigned long)e % __alignof__(struct compat_ip6t_entry) != 0 || + (unsigned char *)e + sizeof(struct compat_ip6t_entry) >= limit || + (unsigned char *)e + e->next_offset > limit) + return -EINVAL; + + if (e->next_offset < sizeof(struct compat_ip6t_entry) + + sizeof(struct compat_xt_entry_target)) + return -EINVAL; + + if (!ip6_checkentry(&e->ipv6)) + return -EINVAL; + + ret = xt_compat_check_entry_offsets(e, e->elems, + e->target_offset, e->next_offset); + if (ret) + return ret; + + off = sizeof(struct ip6t_entry) - sizeof(struct compat_ip6t_entry); + entry_offset = (void *)e - (void *)base; + j = 0; + xt_ematch_foreach(ematch, e) { + ret = compat_find_calc_match(ematch, &e->ipv6, &off); + if (ret != 0) + goto release_matches; + ++j; + } + + t = compat_ip6t_get_target(e); + target = xt_request_find_target(NFPROTO_IPV6, t->u.user.name, + t->u.user.revision); + if (IS_ERR(target)) { + ret = PTR_ERR(target); + goto release_matches; + } + t->u.kernel.target = target; + + off += xt_compat_target_offset(target); + *size += off; + ret = xt_compat_add_offset(AF_INET6, entry_offset, off); + if (ret) + goto out; + + return 0; + +out: + module_put(t->u.kernel.target->me); +release_matches: + xt_ematch_foreach(ematch, e) { + if (j-- == 0) + break; + module_put(ematch->u.kernel.match->me); + } + return ret; +} + +static void +compat_copy_entry_from_user(struct compat_ip6t_entry *e, void **dstptr, + unsigned int *size, + struct xt_table_info *newinfo, unsigned char *base) +{ + struct xt_entry_target *t; + struct ip6t_entry *de; + unsigned int origsize; + int h; + struct xt_entry_match *ematch; + + origsize = *size; + de = *dstptr; + memcpy(de, e, sizeof(struct ip6t_entry)); + memcpy(&de->counters, &e->counters, sizeof(e->counters)); + + *dstptr += sizeof(struct ip6t_entry); + *size += sizeof(struct ip6t_entry) - sizeof(struct compat_ip6t_entry); + + xt_ematch_foreach(ematch, e) + xt_compat_match_from_user(ematch, dstptr, size); + + de->target_offset = e->target_offset - (origsize - *size); + t = compat_ip6t_get_target(e); + xt_compat_target_from_user(t, dstptr, size); + + de->next_offset = e->next_offset - (origsize - *size); + for (h = 0; h < NF_INET_NUMHOOKS; h++) { + if ((unsigned char *)de - base < newinfo->hook_entry[h]) + newinfo->hook_entry[h] -= origsize - *size; + if ((unsigned char *)de - base < newinfo->underflow[h]) + newinfo->underflow[h] -= origsize - *size; + } +} + +static int +translate_compat_table(struct net *net, + struct xt_table_info **pinfo, + void **pentry0, + const struct compat_ip6t_replace *compatr) +{ + unsigned int i, j; + struct xt_table_info *newinfo, *info; + void *pos, *entry0, *entry1; + struct compat_ip6t_entry *iter0; + struct ip6t_replace repl; + unsigned int size; + int ret; + + info = *pinfo; + entry0 = *pentry0; + size = compatr->size; + info->number = compatr->num_entries; + + j = 0; + xt_compat_lock(AF_INET6); + ret = xt_compat_init_offsets(AF_INET6, compatr->num_entries); + if (ret) + goto out_unlock; + /* Walk through entries, checking offsets. */ + xt_entry_foreach(iter0, entry0, compatr->size) { + ret = check_compat_entry_size_and_hooks(iter0, info, &size, + entry0, + entry0 + compatr->size); + if (ret != 0) + goto out_unlock; + ++j; + } + + ret = -EINVAL; + if (j != compatr->num_entries) + goto out_unlock; + + ret = -ENOMEM; + newinfo = xt_alloc_table_info(size); + if (!newinfo) + goto out_unlock; + + memset(newinfo->entries, 0, size); + + newinfo->number = compatr->num_entries; + for (i = 0; i < NF_INET_NUMHOOKS; i++) { + newinfo->hook_entry[i] = compatr->hook_entry[i]; + newinfo->underflow[i] = compatr->underflow[i]; + } + entry1 = newinfo->entries; + pos = entry1; + size = compatr->size; + xt_entry_foreach(iter0, entry0, compatr->size) + compat_copy_entry_from_user(iter0, &pos, &size, + newinfo, entry1); + + /* all module references in entry0 are now gone. */ + xt_compat_flush_offsets(AF_INET6); + xt_compat_unlock(AF_INET6); + + memcpy(&repl, compatr, sizeof(*compatr)); + + for (i = 0; i < NF_INET_NUMHOOKS; i++) { + repl.hook_entry[i] = newinfo->hook_entry[i]; + repl.underflow[i] = newinfo->underflow[i]; + } + + repl.num_counters = 0; + repl.counters = NULL; + repl.size = newinfo->size; + ret = translate_table(net, newinfo, entry1, &repl); + if (ret) + goto free_newinfo; + + *pinfo = newinfo; + *pentry0 = entry1; + xt_free_table_info(info); + return 0; + +free_newinfo: + xt_free_table_info(newinfo); + return ret; +out_unlock: + xt_compat_flush_offsets(AF_INET6); + xt_compat_unlock(AF_INET6); + xt_entry_foreach(iter0, entry0, compatr->size) { + if (j-- == 0) + break; + compat_release_entry(iter0); + } + return ret; +} + +static int +compat_do_replace(struct net *net, sockptr_t arg, unsigned int len) +{ + int ret; + struct compat_ip6t_replace tmp; + struct xt_table_info *newinfo; + void *loc_cpu_entry; + struct ip6t_entry *iter; + + if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0) + return -EFAULT; + + /* overflow check */ + if (tmp.num_counters >= INT_MAX / sizeof(struct xt_counters)) + return -ENOMEM; + if (tmp.num_counters == 0) + return -EINVAL; + + tmp.name[sizeof(tmp.name)-1] = 0; + + newinfo = xt_alloc_table_info(tmp.size); + if (!newinfo) + return -ENOMEM; + + loc_cpu_entry = newinfo->entries; + if (copy_from_sockptr_offset(loc_cpu_entry, arg, sizeof(tmp), + tmp.size) != 0) { + ret = -EFAULT; + goto free_newinfo; + } + + ret = translate_compat_table(net, &newinfo, &loc_cpu_entry, &tmp); + if (ret != 0) + goto free_newinfo; + + ret = __do_replace(net, tmp.name, tmp.valid_hooks, newinfo, + tmp.num_counters, compat_ptr(tmp.counters)); + if (ret) + goto free_newinfo_untrans; + return 0; + + free_newinfo_untrans: + xt_entry_foreach(iter, loc_cpu_entry, newinfo->size) + cleanup_entry(iter, net); + free_newinfo: + xt_free_table_info(newinfo); + return ret; +} + +struct compat_ip6t_get_entries { + char name[XT_TABLE_MAXNAMELEN]; + compat_uint_t size; + struct compat_ip6t_entry entrytable[]; +}; + +static int +compat_copy_entries_to_user(unsigned int total_size, struct xt_table *table, + void __user *userptr) +{ + struct xt_counters *counters; + const struct xt_table_info *private = table->private; + void __user *pos; + unsigned int size; + int ret = 0; + unsigned int i = 0; + struct ip6t_entry *iter; + + counters = alloc_counters(table); + if (IS_ERR(counters)) + return PTR_ERR(counters); + + pos = userptr; + size = total_size; + xt_entry_foreach(iter, private->entries, total_size) { + ret = compat_copy_entry_to_user(iter, &pos, + &size, counters, i++); + if (ret != 0) + break; + } + + vfree(counters); + return ret; +} + +static int +compat_get_entries(struct net *net, struct compat_ip6t_get_entries __user *uptr, + int *len) +{ + int ret; + struct compat_ip6t_get_entries get; + struct xt_table *t; + + if (*len < sizeof(get)) + return -EINVAL; + + if (copy_from_user(&get, uptr, sizeof(get)) != 0) + return -EFAULT; + + if (*len != sizeof(struct compat_ip6t_get_entries) + get.size) + return -EINVAL; + + get.name[sizeof(get.name) - 1] = '\0'; + + xt_compat_lock(AF_INET6); + t = xt_find_table_lock(net, AF_INET6, get.name); + if (!IS_ERR(t)) { + const struct xt_table_info *private = t->private; + struct xt_table_info info; + ret = compat_table_info(private, &info); + if (!ret && get.size == info.size) + ret = compat_copy_entries_to_user(private->size, + t, uptr->entrytable); + else if (!ret) + ret = -EAGAIN; + + xt_compat_flush_offsets(AF_INET6); + module_put(t->me); + xt_table_unlock(t); + } else + ret = PTR_ERR(t); + + xt_compat_unlock(AF_INET6); + return ret; +} +#endif + +static int +do_ip6t_set_ctl(struct sock *sk, int cmd, sockptr_t arg, unsigned int len) +{ + int ret; + + if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) + return -EPERM; + + switch (cmd) { + case IP6T_SO_SET_REPLACE: +#ifdef CONFIG_NETFILTER_XTABLES_COMPAT + if (in_compat_syscall()) + ret = compat_do_replace(sock_net(sk), arg, len); + else +#endif + ret = do_replace(sock_net(sk), arg, len); + break; + + case IP6T_SO_SET_ADD_COUNTERS: + ret = do_add_counters(sock_net(sk), arg, len); + break; + + default: + ret = -EINVAL; + } + + return ret; +} + +static int +do_ip6t_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) +{ + int ret; + + if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) + return -EPERM; + + switch (cmd) { + case IP6T_SO_GET_INFO: + ret = get_info(sock_net(sk), user, len); + break; + + case IP6T_SO_GET_ENTRIES: +#ifdef CONFIG_NETFILTER_XTABLES_COMPAT + if (in_compat_syscall()) + ret = compat_get_entries(sock_net(sk), user, len); + else +#endif + ret = get_entries(sock_net(sk), user, len); + break; + + case IP6T_SO_GET_REVISION_MATCH: + case IP6T_SO_GET_REVISION_TARGET: { + struct xt_get_revision rev; + int target; + + if (*len != sizeof(rev)) { + ret = -EINVAL; + break; + } + if (copy_from_user(&rev, user, sizeof(rev)) != 0) { + ret = -EFAULT; + break; + } + rev.name[sizeof(rev.name)-1] = 0; + + if (cmd == IP6T_SO_GET_REVISION_TARGET) + target = 1; + else + target = 0; + + try_then_request_module(xt_find_revision(AF_INET6, rev.name, + rev.revision, + target, &ret), + "ip6t_%s", rev.name); + break; + } + + default: + ret = -EINVAL; + } + + return ret; +} + +static void __ip6t_unregister_table(struct net *net, struct xt_table *table) +{ + struct xt_table_info *private; + void *loc_cpu_entry; + struct module *table_owner = table->me; + struct ip6t_entry *iter; + + private = xt_unregister_table(table); + + /* Decrease module usage counts and free resources */ + loc_cpu_entry = private->entries; + xt_entry_foreach(iter, loc_cpu_entry, private->size) + cleanup_entry(iter, net); + if (private->number > private->initial_entries) + module_put(table_owner); + xt_free_table_info(private); +} + +int ip6t_register_table(struct net *net, const struct xt_table *table, + const struct ip6t_replace *repl, + const struct nf_hook_ops *template_ops) +{ + struct nf_hook_ops *ops; + unsigned int num_ops; + int ret, i; + struct xt_table_info *newinfo; + struct xt_table_info bootstrap = {0}; + void *loc_cpu_entry; + struct xt_table *new_table; + + newinfo = xt_alloc_table_info(repl->size); + if (!newinfo) + return -ENOMEM; + + loc_cpu_entry = newinfo->entries; + memcpy(loc_cpu_entry, repl->entries, repl->size); + + ret = translate_table(net, newinfo, loc_cpu_entry, repl); + if (ret != 0) { + xt_free_table_info(newinfo); + return ret; + } + + new_table = xt_register_table(net, table, &bootstrap, newinfo); + if (IS_ERR(new_table)) { + struct ip6t_entry *iter; + + xt_entry_foreach(iter, loc_cpu_entry, newinfo->size) + cleanup_entry(iter, net); + xt_free_table_info(newinfo); + return PTR_ERR(new_table); + } + + if (!template_ops) + return 0; + + num_ops = hweight32(table->valid_hooks); + if (num_ops == 0) { + ret = -EINVAL; + goto out_free; + } + + ops = kmemdup(template_ops, sizeof(*ops) * num_ops, GFP_KERNEL); + if (!ops) { + ret = -ENOMEM; + goto out_free; + } + + for (i = 0; i < num_ops; i++) + ops[i].priv = new_table; + + new_table->ops = ops; + + ret = nf_register_net_hooks(net, ops, num_ops); + if (ret != 0) + goto out_free; + + return ret; + +out_free: + __ip6t_unregister_table(net, new_table); + return ret; +} + +void ip6t_unregister_table_pre_exit(struct net *net, const char *name) +{ + struct xt_table *table = xt_find_table(net, NFPROTO_IPV6, name); + + if (table) + nf_unregister_net_hooks(net, table->ops, hweight32(table->valid_hooks)); +} + +void ip6t_unregister_table_exit(struct net *net, const char *name) +{ + struct xt_table *table = xt_find_table(net, NFPROTO_IPV6, name); + + if (table) + __ip6t_unregister_table(net, table); +} + +/* Returns 1 if the type and code is matched by the range, 0 otherwise */ +static inline bool +icmp6_type_code_match(u_int8_t test_type, u_int8_t min_code, u_int8_t max_code, + u_int8_t type, u_int8_t code, + bool invert) +{ + return (type == test_type && code >= min_code && code <= max_code) + ^ invert; +} + +static bool +icmp6_match(const struct sk_buff *skb, struct xt_action_param *par) +{ + const struct icmp6hdr *ic; + struct icmp6hdr _icmph; + const struct ip6t_icmp *icmpinfo = par->matchinfo; + + /* Must not be a fragment. */ + if (par->fragoff != 0) + return false; + + ic = skb_header_pointer(skb, par->thoff, sizeof(_icmph), &_icmph); + if (ic == NULL) { + /* We've been asked to examine this packet, and we + * can't. Hence, no choice but to drop. + */ + par->hotdrop = true; + return false; + } + + return icmp6_type_code_match(icmpinfo->type, + icmpinfo->code[0], + icmpinfo->code[1], + ic->icmp6_type, ic->icmp6_code, + !!(icmpinfo->invflags&IP6T_ICMP_INV)); +} + +/* Called when user tries to insert an entry of this type. */ +static int icmp6_checkentry(const struct xt_mtchk_param *par) +{ + const struct ip6t_icmp *icmpinfo = par->matchinfo; + + /* Must specify no unknown invflags */ + return (icmpinfo->invflags & ~IP6T_ICMP_INV) ? -EINVAL : 0; +} + +/* The built-in targets: standard (NULL) and error. */ +static struct xt_target ip6t_builtin_tg[] __read_mostly = { + { + .name = XT_STANDARD_TARGET, + .targetsize = sizeof(int), + .family = NFPROTO_IPV6, +#ifdef CONFIG_NETFILTER_XTABLES_COMPAT + .compatsize = sizeof(compat_int_t), + .compat_from_user = compat_standard_from_user, + .compat_to_user = compat_standard_to_user, +#endif + }, + { + .name = XT_ERROR_TARGET, + .target = ip6t_error, + .targetsize = XT_FUNCTION_MAXNAMELEN, + .family = NFPROTO_IPV6, + }, +}; + +static struct nf_sockopt_ops ip6t_sockopts = { + .pf = PF_INET6, + .set_optmin = IP6T_BASE_CTL, + .set_optmax = IP6T_SO_SET_MAX+1, + .set = do_ip6t_set_ctl, + .get_optmin = IP6T_BASE_CTL, + .get_optmax = IP6T_SO_GET_MAX+1, + .get = do_ip6t_get_ctl, + .owner = THIS_MODULE, +}; + +static struct xt_match ip6t_builtin_mt[] __read_mostly = { + { + .name = "icmp6", + .match = icmp6_match, + .matchsize = sizeof(struct ip6t_icmp), + .checkentry = icmp6_checkentry, + .proto = IPPROTO_ICMPV6, + .family = NFPROTO_IPV6, + .me = THIS_MODULE, + }, +}; + +static int __net_init ip6_tables_net_init(struct net *net) +{ + return xt_proto_init(net, NFPROTO_IPV6); +} + +static void __net_exit ip6_tables_net_exit(struct net *net) +{ + xt_proto_fini(net, NFPROTO_IPV6); +} + +static struct pernet_operations ip6_tables_net_ops = { + .init = ip6_tables_net_init, + .exit = ip6_tables_net_exit, +}; + +static int __init ip6_tables_init(void) +{ + int ret; + + ret = register_pernet_subsys(&ip6_tables_net_ops); + if (ret < 0) + goto err1; + + /* No one else will be downing sem now, so we won't sleep */ + ret = xt_register_targets(ip6t_builtin_tg, ARRAY_SIZE(ip6t_builtin_tg)); + if (ret < 0) + goto err2; + ret = xt_register_matches(ip6t_builtin_mt, ARRAY_SIZE(ip6t_builtin_mt)); + if (ret < 0) + goto err4; + + /* Register setsockopt */ + ret = nf_register_sockopt(&ip6t_sockopts); + if (ret < 0) + goto err5; + + return 0; + +err5: + xt_unregister_matches(ip6t_builtin_mt, ARRAY_SIZE(ip6t_builtin_mt)); +err4: + xt_unregister_targets(ip6t_builtin_tg, ARRAY_SIZE(ip6t_builtin_tg)); +err2: + unregister_pernet_subsys(&ip6_tables_net_ops); +err1: + return ret; +} + +static void __exit ip6_tables_fini(void) +{ + nf_unregister_sockopt(&ip6t_sockopts); + + xt_unregister_matches(ip6t_builtin_mt, ARRAY_SIZE(ip6t_builtin_mt)); + xt_unregister_targets(ip6t_builtin_tg, ARRAY_SIZE(ip6t_builtin_tg)); + unregister_pernet_subsys(&ip6_tables_net_ops); +} + +EXPORT_SYMBOL(ip6t_register_table); +EXPORT_SYMBOL(ip6t_unregister_table_pre_exit); +EXPORT_SYMBOL(ip6t_unregister_table_exit); +EXPORT_SYMBOL(ip6t_do_table); + +module_init(ip6_tables_init); +module_exit(ip6_tables_fini); diff --git a/net/ipv6/netfilter/ip6t_NPT.c b/net/ipv6/netfilter/ip6t_NPT.c new file mode 100644 index 000000000..787c74aa8 --- /dev/null +++ b/net/ipv6/netfilter/ip6t_NPT.c @@ -0,0 +1,191 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2011, 2012 Patrick McHardy <kaber@trash.net> + */ + +#include <linux/module.h> +#include <linux/skbuff.h> +#include <linux/ipv6.h> +#include <net/ipv6.h> +#include <linux/netfilter.h> +#include <linux/netfilter_ipv6.h> +#include <linux/netfilter_ipv6/ip6t_NPT.h> +#include <linux/netfilter/x_tables.h> + +static int ip6t_npt_checkentry(const struct xt_tgchk_param *par) +{ + struct ip6t_npt_tginfo *npt = par->targinfo; + struct in6_addr pfx; + __wsum src_sum, dst_sum; + + if (npt->src_pfx_len > 64 || npt->dst_pfx_len > 64) + return -EINVAL; + + /* Ensure that LSB of prefix is zero */ + ipv6_addr_prefix(&pfx, &npt->src_pfx.in6, npt->src_pfx_len); + if (!ipv6_addr_equal(&pfx, &npt->src_pfx.in6)) + return -EINVAL; + ipv6_addr_prefix(&pfx, &npt->dst_pfx.in6, npt->dst_pfx_len); + if (!ipv6_addr_equal(&pfx, &npt->dst_pfx.in6)) + return -EINVAL; + + src_sum = csum_partial(&npt->src_pfx.in6, sizeof(npt->src_pfx.in6), 0); + dst_sum = csum_partial(&npt->dst_pfx.in6, sizeof(npt->dst_pfx.in6), 0); + + npt->adjustment = ~csum_fold(csum_sub(src_sum, dst_sum)); + return 0; +} + +static bool ip6t_npt_map_pfx(const struct ip6t_npt_tginfo *npt, + struct in6_addr *addr) +{ + unsigned int pfx_len; + unsigned int i, idx; + __be32 mask; + __sum16 sum; + + pfx_len = max(npt->src_pfx_len, npt->dst_pfx_len); + for (i = 0; i < pfx_len; i += 32) { + if (pfx_len - i >= 32) + mask = 0; + else + mask = htonl((1 << (i - pfx_len + 32)) - 1); + + idx = i / 32; + addr->s6_addr32[idx] &= mask; + addr->s6_addr32[idx] |= ~mask & npt->dst_pfx.in6.s6_addr32[idx]; + } + + if (pfx_len <= 48) + idx = 3; + else { + for (idx = 4; idx < ARRAY_SIZE(addr->s6_addr16); idx++) { + if ((__force __sum16)addr->s6_addr16[idx] != + CSUM_MANGLED_0) + break; + } + if (idx == ARRAY_SIZE(addr->s6_addr16)) + return false; + } + + sum = ~csum_fold(csum_add(csum_unfold((__force __sum16)addr->s6_addr16[idx]), + csum_unfold(npt->adjustment))); + if (sum == CSUM_MANGLED_0) + sum = 0; + *(__force __sum16 *)&addr->s6_addr16[idx] = sum; + + return true; +} + +static struct ipv6hdr *icmpv6_bounced_ipv6hdr(struct sk_buff *skb, + struct ipv6hdr *_bounced_hdr) +{ + if (ipv6_hdr(skb)->nexthdr != IPPROTO_ICMPV6) + return NULL; + + if (!icmpv6_is_err(icmp6_hdr(skb)->icmp6_type)) + return NULL; + + return skb_header_pointer(skb, + skb_transport_offset(skb) + sizeof(struct icmp6hdr), + sizeof(struct ipv6hdr), + _bounced_hdr); +} + +static unsigned int +ip6t_snpt_tg(struct sk_buff *skb, const struct xt_action_param *par) +{ + const struct ip6t_npt_tginfo *npt = par->targinfo; + struct ipv6hdr _bounced_hdr; + struct ipv6hdr *bounced_hdr; + struct in6_addr bounced_pfx; + + if (!ip6t_npt_map_pfx(npt, &ipv6_hdr(skb)->saddr)) { + icmpv6_send(skb, ICMPV6_PARAMPROB, ICMPV6_HDR_FIELD, + offsetof(struct ipv6hdr, saddr)); + return NF_DROP; + } + + /* rewrite dst addr of bounced packet which was sent to dst range */ + bounced_hdr = icmpv6_bounced_ipv6hdr(skb, &_bounced_hdr); + if (bounced_hdr) { + ipv6_addr_prefix(&bounced_pfx, &bounced_hdr->daddr, npt->src_pfx_len); + if (ipv6_addr_cmp(&bounced_pfx, &npt->src_pfx.in6) == 0) + ip6t_npt_map_pfx(npt, &bounced_hdr->daddr); + } + + return XT_CONTINUE; +} + +static unsigned int +ip6t_dnpt_tg(struct sk_buff *skb, const struct xt_action_param *par) +{ + const struct ip6t_npt_tginfo *npt = par->targinfo; + struct ipv6hdr _bounced_hdr; + struct ipv6hdr *bounced_hdr; + struct in6_addr bounced_pfx; + + if (!ip6t_npt_map_pfx(npt, &ipv6_hdr(skb)->daddr)) { + icmpv6_send(skb, ICMPV6_PARAMPROB, ICMPV6_HDR_FIELD, + offsetof(struct ipv6hdr, daddr)); + return NF_DROP; + } + + /* rewrite src addr of bounced packet which was sent from dst range */ + bounced_hdr = icmpv6_bounced_ipv6hdr(skb, &_bounced_hdr); + if (bounced_hdr) { + ipv6_addr_prefix(&bounced_pfx, &bounced_hdr->saddr, npt->src_pfx_len); + if (ipv6_addr_cmp(&bounced_pfx, &npt->src_pfx.in6) == 0) + ip6t_npt_map_pfx(npt, &bounced_hdr->saddr); + } + + return XT_CONTINUE; +} + +static struct xt_target ip6t_npt_target_reg[] __read_mostly = { + { + .name = "SNPT", + .table = "mangle", + .target = ip6t_snpt_tg, + .targetsize = sizeof(struct ip6t_npt_tginfo), + .usersize = offsetof(struct ip6t_npt_tginfo, adjustment), + .checkentry = ip6t_npt_checkentry, + .family = NFPROTO_IPV6, + .hooks = (1 << NF_INET_LOCAL_IN) | + (1 << NF_INET_POST_ROUTING), + .me = THIS_MODULE, + }, + { + .name = "DNPT", + .table = "mangle", + .target = ip6t_dnpt_tg, + .targetsize = sizeof(struct ip6t_npt_tginfo), + .usersize = offsetof(struct ip6t_npt_tginfo, adjustment), + .checkentry = ip6t_npt_checkentry, + .family = NFPROTO_IPV6, + .hooks = (1 << NF_INET_PRE_ROUTING) | + (1 << NF_INET_LOCAL_OUT), + .me = THIS_MODULE, + }, +}; + +static int __init ip6t_npt_init(void) +{ + return xt_register_targets(ip6t_npt_target_reg, + ARRAY_SIZE(ip6t_npt_target_reg)); +} + +static void __exit ip6t_npt_exit(void) +{ + xt_unregister_targets(ip6t_npt_target_reg, + ARRAY_SIZE(ip6t_npt_target_reg)); +} + +module_init(ip6t_npt_init); +module_exit(ip6t_npt_exit); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("IPv6-to-IPv6 Network Prefix Translation (RFC 6296)"); +MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); +MODULE_ALIAS("ip6t_SNPT"); +MODULE_ALIAS("ip6t_DNPT"); diff --git a/net/ipv6/netfilter/ip6t_REJECT.c b/net/ipv6/netfilter/ip6t_REJECT.c new file mode 100644 index 000000000..a35019d2e --- /dev/null +++ b/net/ipv6/netfilter/ip6t_REJECT.c @@ -0,0 +1,121 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * IP6 tables REJECT target module + * Linux INET6 implementation + * + * Copyright (C)2003 USAGI/WIDE Project + * + * Authors: + * Yasuyuki Kozakai <yasuyuki.kozakai@toshiba.co.jp> + * + * Copyright (c) 2005-2007 Patrick McHardy <kaber@trash.net> + * + * Based on net/ipv4/netfilter/ipt_REJECT.c + */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/gfp.h> +#include <linux/module.h> +#include <linux/skbuff.h> +#include <linux/icmpv6.h> +#include <linux/netdevice.h> +#include <net/icmp.h> +#include <net/flow.h> +#include <linux/netfilter/x_tables.h> +#include <linux/netfilter_ipv6/ip6_tables.h> +#include <linux/netfilter_ipv6/ip6t_REJECT.h> + +#include <net/netfilter/ipv6/nf_reject.h> + +MODULE_AUTHOR("Yasuyuki KOZAKAI <yasuyuki.kozakai@toshiba.co.jp>"); +MODULE_DESCRIPTION("Xtables: packet \"rejection\" target for IPv6"); +MODULE_LICENSE("GPL"); + +static unsigned int +reject_tg6(struct sk_buff *skb, const struct xt_action_param *par) +{ + const struct ip6t_reject_info *reject = par->targinfo; + struct net *net = xt_net(par); + + switch (reject->with) { + case IP6T_ICMP6_NO_ROUTE: + nf_send_unreach6(net, skb, ICMPV6_NOROUTE, xt_hooknum(par)); + break; + case IP6T_ICMP6_ADM_PROHIBITED: + nf_send_unreach6(net, skb, ICMPV6_ADM_PROHIBITED, + xt_hooknum(par)); + break; + case IP6T_ICMP6_NOT_NEIGHBOUR: + nf_send_unreach6(net, skb, ICMPV6_NOT_NEIGHBOUR, + xt_hooknum(par)); + break; + case IP6T_ICMP6_ADDR_UNREACH: + nf_send_unreach6(net, skb, ICMPV6_ADDR_UNREACH, + xt_hooknum(par)); + break; + case IP6T_ICMP6_PORT_UNREACH: + nf_send_unreach6(net, skb, ICMPV6_PORT_UNREACH, + xt_hooknum(par)); + break; + case IP6T_ICMP6_ECHOREPLY: + /* Do nothing */ + break; + case IP6T_TCP_RESET: + nf_send_reset6(net, par->state->sk, skb, xt_hooknum(par)); + break; + case IP6T_ICMP6_POLICY_FAIL: + nf_send_unreach6(net, skb, ICMPV6_POLICY_FAIL, xt_hooknum(par)); + break; + case IP6T_ICMP6_REJECT_ROUTE: + nf_send_unreach6(net, skb, ICMPV6_REJECT_ROUTE, + xt_hooknum(par)); + break; + } + + return NF_DROP; +} + +static int reject_tg6_check(const struct xt_tgchk_param *par) +{ + const struct ip6t_reject_info *rejinfo = par->targinfo; + const struct ip6t_entry *e = par->entryinfo; + + if (rejinfo->with == IP6T_ICMP6_ECHOREPLY) { + pr_info_ratelimited("ECHOREPLY is not supported\n"); + return -EINVAL; + } else if (rejinfo->with == IP6T_TCP_RESET) { + /* Must specify that it's a TCP packet */ + if (!(e->ipv6.flags & IP6T_F_PROTO) || + e->ipv6.proto != IPPROTO_TCP || + (e->ipv6.invflags & XT_INV_PROTO)) { + pr_info_ratelimited("TCP_RESET illegal for non-tcp\n"); + return -EINVAL; + } + } + return 0; +} + +static struct xt_target reject_tg6_reg __read_mostly = { + .name = "REJECT", + .family = NFPROTO_IPV6, + .target = reject_tg6, + .targetsize = sizeof(struct ip6t_reject_info), + .table = "filter", + .hooks = (1 << NF_INET_LOCAL_IN) | (1 << NF_INET_FORWARD) | + (1 << NF_INET_LOCAL_OUT), + .checkentry = reject_tg6_check, + .me = THIS_MODULE +}; + +static int __init reject_tg6_init(void) +{ + return xt_register_target(&reject_tg6_reg); +} + +static void __exit reject_tg6_exit(void) +{ + xt_unregister_target(&reject_tg6_reg); +} + +module_init(reject_tg6_init); +module_exit(reject_tg6_exit); diff --git a/net/ipv6/netfilter/ip6t_SYNPROXY.c b/net/ipv6/netfilter/ip6t_SYNPROXY.c new file mode 100644 index 000000000..d51d0c3e5 --- /dev/null +++ b/net/ipv6/netfilter/ip6t_SYNPROXY.c @@ -0,0 +1,124 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2013 Patrick McHardy <kaber@trash.net> + */ + +#include <linux/netfilter_ipv6/ip6_tables.h> +#include <linux/netfilter/x_tables.h> +#include <linux/netfilter/xt_SYNPROXY.h> + +#include <net/netfilter/nf_synproxy.h> + +static unsigned int +synproxy_tg6(struct sk_buff *skb, const struct xt_action_param *par) +{ + const struct xt_synproxy_info *info = par->targinfo; + struct net *net = xt_net(par); + struct synproxy_net *snet = synproxy_pernet(net); + struct synproxy_options opts = {}; + struct tcphdr *th, _th; + + if (nf_ip6_checksum(skb, xt_hooknum(par), par->thoff, IPPROTO_TCP)) + return NF_DROP; + + th = skb_header_pointer(skb, par->thoff, sizeof(_th), &_th); + if (th == NULL) + return NF_DROP; + + if (!synproxy_parse_options(skb, par->thoff, th, &opts)) + return NF_DROP; + + if (th->syn && !(th->ack || th->fin || th->rst)) { + /* Initial SYN from client */ + this_cpu_inc(snet->stats->syn_received); + + if (th->ece && th->cwr) + opts.options |= XT_SYNPROXY_OPT_ECN; + + opts.options &= info->options; + opts.mss_encode = opts.mss_option; + opts.mss_option = info->mss; + if (opts.options & XT_SYNPROXY_OPT_TIMESTAMP) + synproxy_init_timestamp_cookie(info, &opts); + else + opts.options &= ~(XT_SYNPROXY_OPT_WSCALE | + XT_SYNPROXY_OPT_SACK_PERM | + XT_SYNPROXY_OPT_ECN); + + synproxy_send_client_synack_ipv6(net, skb, th, &opts); + consume_skb(skb); + return NF_STOLEN; + + } else if (th->ack && !(th->fin || th->rst || th->syn)) { + /* ACK from client */ + if (synproxy_recv_client_ack_ipv6(net, skb, th, &opts, + ntohl(th->seq))) { + consume_skb(skb); + return NF_STOLEN; + } else { + return NF_DROP; + } + } + + return XT_CONTINUE; +} + +static int synproxy_tg6_check(const struct xt_tgchk_param *par) +{ + struct synproxy_net *snet = synproxy_pernet(par->net); + const struct ip6t_entry *e = par->entryinfo; + int err; + + if (!(e->ipv6.flags & IP6T_F_PROTO) || + e->ipv6.proto != IPPROTO_TCP || + e->ipv6.invflags & XT_INV_PROTO) + return -EINVAL; + + err = nf_ct_netns_get(par->net, par->family); + if (err) + return err; + + err = nf_synproxy_ipv6_init(snet, par->net); + if (err) { + nf_ct_netns_put(par->net, par->family); + return err; + } + + return err; +} + +static void synproxy_tg6_destroy(const struct xt_tgdtor_param *par) +{ + struct synproxy_net *snet = synproxy_pernet(par->net); + + nf_synproxy_ipv6_fini(snet, par->net); + nf_ct_netns_put(par->net, par->family); +} + +static struct xt_target synproxy_tg6_reg __read_mostly = { + .name = "SYNPROXY", + .family = NFPROTO_IPV6, + .hooks = (1 << NF_INET_LOCAL_IN) | (1 << NF_INET_FORWARD), + .target = synproxy_tg6, + .targetsize = sizeof(struct xt_synproxy_info), + .checkentry = synproxy_tg6_check, + .destroy = synproxy_tg6_destroy, + .me = THIS_MODULE, +}; + +static int __init synproxy_tg6_init(void) +{ + return xt_register_target(&synproxy_tg6_reg); +} + +static void __exit synproxy_tg6_exit(void) +{ + xt_unregister_target(&synproxy_tg6_reg); +} + +module_init(synproxy_tg6_init); +module_exit(synproxy_tg6_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); +MODULE_DESCRIPTION("Intercept IPv6 TCP connections and establish them using syncookies"); diff --git a/net/ipv6/netfilter/ip6t_ah.c b/net/ipv6/netfilter/ip6t_ah.c new file mode 100644 index 000000000..70da2f2ce --- /dev/null +++ b/net/ipv6/netfilter/ip6t_ah.c @@ -0,0 +1,117 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Kernel module to match AH parameters. */ + +/* (C) 2001-2002 Andras Kis-Szabo <kisza@sch.bme.hu> + */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include <linux/module.h> +#include <linux/skbuff.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/types.h> +#include <net/checksum.h> +#include <net/ipv6.h> + +#include <linux/netfilter/x_tables.h> +#include <linux/netfilter_ipv6/ip6_tables.h> +#include <linux/netfilter_ipv6/ip6t_ah.h> + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Xtables: IPv6 IPsec-AH match"); +MODULE_AUTHOR("Andras Kis-Szabo <kisza@sch.bme.hu>"); + +/* Returns 1 if the spi is matched by the range, 0 otherwise */ +static inline bool +spi_match(u_int32_t min, u_int32_t max, u_int32_t spi, bool invert) +{ + bool r; + + pr_debug("spi_match:%c 0x%x <= 0x%x <= 0x%x\n", + invert ? '!' : ' ', min, spi, max); + r = (spi >= min && spi <= max) ^ invert; + pr_debug(" result %s\n", r ? "PASS" : "FAILED"); + return r; +} + +static bool ah_mt6(const struct sk_buff *skb, struct xt_action_param *par) +{ + struct ip_auth_hdr _ah; + const struct ip_auth_hdr *ah; + const struct ip6t_ah *ahinfo = par->matchinfo; + unsigned int ptr = 0; + unsigned int hdrlen = 0; + int err; + + err = ipv6_find_hdr(skb, &ptr, NEXTHDR_AUTH, NULL, NULL); + if (err < 0) { + if (err != -ENOENT) + par->hotdrop = true; + return false; + } + + ah = skb_header_pointer(skb, ptr, sizeof(_ah), &_ah); + if (ah == NULL) { + par->hotdrop = true; + return false; + } + + hdrlen = ipv6_authlen(ah); + + pr_debug("IPv6 AH LEN %u %u ", hdrlen, ah->hdrlen); + pr_debug("RES %04X ", ah->reserved); + pr_debug("SPI %u %08X\n", ntohl(ah->spi), ntohl(ah->spi)); + + pr_debug("IPv6 AH spi %02X ", + spi_match(ahinfo->spis[0], ahinfo->spis[1], + ntohl(ah->spi), + !!(ahinfo->invflags & IP6T_AH_INV_SPI))); + pr_debug("len %02X %04X %02X ", + ahinfo->hdrlen, hdrlen, + (!ahinfo->hdrlen || + (ahinfo->hdrlen == hdrlen) ^ + !!(ahinfo->invflags & IP6T_AH_INV_LEN))); + pr_debug("res %02X %04X %02X\n", + ahinfo->hdrres, ah->reserved, + !(ahinfo->hdrres && ah->reserved)); + + return spi_match(ahinfo->spis[0], ahinfo->spis[1], + ntohl(ah->spi), + !!(ahinfo->invflags & IP6T_AH_INV_SPI)) && + (!ahinfo->hdrlen || + (ahinfo->hdrlen == hdrlen) ^ + !!(ahinfo->invflags & IP6T_AH_INV_LEN)) && + !(ahinfo->hdrres && ah->reserved); +} + +static int ah_mt6_check(const struct xt_mtchk_param *par) +{ + const struct ip6t_ah *ahinfo = par->matchinfo; + + if (ahinfo->invflags & ~IP6T_AH_INV_MASK) { + pr_debug("unknown flags %X\n", ahinfo->invflags); + return -EINVAL; + } + return 0; +} + +static struct xt_match ah_mt6_reg __read_mostly = { + .name = "ah", + .family = NFPROTO_IPV6, + .match = ah_mt6, + .matchsize = sizeof(struct ip6t_ah), + .checkentry = ah_mt6_check, + .me = THIS_MODULE, +}; + +static int __init ah_mt6_init(void) +{ + return xt_register_match(&ah_mt6_reg); +} + +static void __exit ah_mt6_exit(void) +{ + xt_unregister_match(&ah_mt6_reg); +} + +module_init(ah_mt6_init); +module_exit(ah_mt6_exit); diff --git a/net/ipv6/netfilter/ip6t_eui64.c b/net/ipv6/netfilter/ip6t_eui64.c new file mode 100644 index 000000000..d704f7ed3 --- /dev/null +++ b/net/ipv6/netfilter/ip6t_eui64.c @@ -0,0 +1,71 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Kernel module to match EUI64 address parameters. */ + +/* (C) 2001-2002 Andras Kis-Szabo <kisza@sch.bme.hu> + */ + +#include <linux/module.h> +#include <linux/skbuff.h> +#include <linux/ipv6.h> +#include <linux/if_ether.h> + +#include <linux/netfilter/x_tables.h> +#include <linux/netfilter_ipv6/ip6_tables.h> + +MODULE_DESCRIPTION("Xtables: IPv6 EUI64 address match"); +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Andras Kis-Szabo <kisza@sch.bme.hu>"); + +static bool +eui64_mt6(const struct sk_buff *skb, struct xt_action_param *par) +{ + unsigned char eui64[8]; + + if (!(skb_mac_header(skb) >= skb->head && + skb_mac_header(skb) + ETH_HLEN <= skb->data) && + par->fragoff != 0) { + par->hotdrop = true; + return false; + } + + memset(eui64, 0, sizeof(eui64)); + + if (eth_hdr(skb)->h_proto == htons(ETH_P_IPV6)) { + if (ipv6_hdr(skb)->version == 0x6) { + memcpy(eui64, eth_hdr(skb)->h_source, 3); + memcpy(eui64 + 5, eth_hdr(skb)->h_source + 3, 3); + eui64[3] = 0xff; + eui64[4] = 0xfe; + eui64[0] ^= 0x02; + + if (!memcmp(ipv6_hdr(skb)->saddr.s6_addr + 8, eui64, + sizeof(eui64))) + return true; + } + } + + return false; +} + +static struct xt_match eui64_mt6_reg __read_mostly = { + .name = "eui64", + .family = NFPROTO_IPV6, + .match = eui64_mt6, + .matchsize = sizeof(int), + .hooks = (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_IN) | + (1 << NF_INET_FORWARD), + .me = THIS_MODULE, +}; + +static int __init eui64_mt6_init(void) +{ + return xt_register_match(&eui64_mt6_reg); +} + +static void __exit eui64_mt6_exit(void) +{ + xt_unregister_match(&eui64_mt6_reg); +} + +module_init(eui64_mt6_init); +module_exit(eui64_mt6_exit); diff --git a/net/ipv6/netfilter/ip6t_frag.c b/net/ipv6/netfilter/ip6t_frag.c new file mode 100644 index 000000000..3aad64393 --- /dev/null +++ b/net/ipv6/netfilter/ip6t_frag.c @@ -0,0 +1,132 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Kernel module to match FRAG parameters. */ + +/* (C) 2001-2002 Andras Kis-Szabo <kisza@sch.bme.hu> + */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include <linux/module.h> +#include <linux/skbuff.h> +#include <linux/ipv6.h> +#include <linux/types.h> +#include <net/checksum.h> +#include <net/ipv6.h> + +#include <linux/netfilter/x_tables.h> +#include <linux/netfilter_ipv6/ip6_tables.h> +#include <linux/netfilter_ipv6/ip6t_frag.h> + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Xtables: IPv6 fragment match"); +MODULE_AUTHOR("Andras Kis-Szabo <kisza@sch.bme.hu>"); + +/* Returns 1 if the id is matched by the range, 0 otherwise */ +static inline bool +id_match(u_int32_t min, u_int32_t max, u_int32_t id, bool invert) +{ + bool r; + pr_debug("id_match:%c 0x%x <= 0x%x <= 0x%x\n", invert ? '!' : ' ', + min, id, max); + r = (id >= min && id <= max) ^ invert; + pr_debug(" result %s\n", r ? "PASS" : "FAILED"); + return r; +} + +static bool +frag_mt6(const struct sk_buff *skb, struct xt_action_param *par) +{ + struct frag_hdr _frag; + const struct frag_hdr *fh; + const struct ip6t_frag *fraginfo = par->matchinfo; + unsigned int ptr = 0; + int err; + + err = ipv6_find_hdr(skb, &ptr, NEXTHDR_FRAGMENT, NULL, NULL); + if (err < 0) { + if (err != -ENOENT) + par->hotdrop = true; + return false; + } + + fh = skb_header_pointer(skb, ptr, sizeof(_frag), &_frag); + if (fh == NULL) { + par->hotdrop = true; + return false; + } + + pr_debug("INFO %04X ", fh->frag_off); + pr_debug("OFFSET %04X ", ntohs(fh->frag_off) & ~0x7); + pr_debug("RES %02X %04X", fh->reserved, ntohs(fh->frag_off) & 0x6); + pr_debug("MF %04X ", fh->frag_off & htons(IP6_MF)); + pr_debug("ID %u %08X\n", ntohl(fh->identification), + ntohl(fh->identification)); + + pr_debug("IPv6 FRAG id %02X ", + id_match(fraginfo->ids[0], fraginfo->ids[1], + ntohl(fh->identification), + !!(fraginfo->invflags & IP6T_FRAG_INV_IDS))); + pr_debug("res %02X %02X%04X %02X ", + fraginfo->flags & IP6T_FRAG_RES, fh->reserved, + ntohs(fh->frag_off) & 0x6, + !((fraginfo->flags & IP6T_FRAG_RES) && + (fh->reserved || (ntohs(fh->frag_off) & 0x06)))); + pr_debug("first %02X %02X %02X ", + fraginfo->flags & IP6T_FRAG_FST, + ntohs(fh->frag_off) & ~0x7, + !((fraginfo->flags & IP6T_FRAG_FST) && + (ntohs(fh->frag_off) & ~0x7))); + pr_debug("mf %02X %02X %02X ", + fraginfo->flags & IP6T_FRAG_MF, + ntohs(fh->frag_off) & IP6_MF, + !((fraginfo->flags & IP6T_FRAG_MF) && + !((ntohs(fh->frag_off) & IP6_MF)))); + pr_debug("last %02X %02X %02X\n", + fraginfo->flags & IP6T_FRAG_NMF, + ntohs(fh->frag_off) & IP6_MF, + !((fraginfo->flags & IP6T_FRAG_NMF) && + (ntohs(fh->frag_off) & IP6_MF))); + + return id_match(fraginfo->ids[0], fraginfo->ids[1], + ntohl(fh->identification), + !!(fraginfo->invflags & IP6T_FRAG_INV_IDS)) && + !((fraginfo->flags & IP6T_FRAG_RES) && + (fh->reserved || (ntohs(fh->frag_off) & 0x6))) && + !((fraginfo->flags & IP6T_FRAG_FST) && + (ntohs(fh->frag_off) & ~0x7)) && + !((fraginfo->flags & IP6T_FRAG_MF) && + !(ntohs(fh->frag_off) & IP6_MF)) && + !((fraginfo->flags & IP6T_FRAG_NMF) && + (ntohs(fh->frag_off) & IP6_MF)); +} + +static int frag_mt6_check(const struct xt_mtchk_param *par) +{ + const struct ip6t_frag *fraginfo = par->matchinfo; + + if (fraginfo->invflags & ~IP6T_FRAG_INV_MASK) { + pr_debug("unknown flags %X\n", fraginfo->invflags); + return -EINVAL; + } + return 0; +} + +static struct xt_match frag_mt6_reg __read_mostly = { + .name = "frag", + .family = NFPROTO_IPV6, + .match = frag_mt6, + .matchsize = sizeof(struct ip6t_frag), + .checkentry = frag_mt6_check, + .me = THIS_MODULE, +}; + +static int __init frag_mt6_init(void) +{ + return xt_register_match(&frag_mt6_reg); +} + +static void __exit frag_mt6_exit(void) +{ + xt_unregister_match(&frag_mt6_reg); +} + +module_init(frag_mt6_init); +module_exit(frag_mt6_exit); diff --git a/net/ipv6/netfilter/ip6t_hbh.c b/net/ipv6/netfilter/ip6t_hbh.c new file mode 100644 index 000000000..e7a3fb935 --- /dev/null +++ b/net/ipv6/netfilter/ip6t_hbh.c @@ -0,0 +1,211 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Kernel module to match Hop-by-Hop and Destination parameters. */ + +/* (C) 2001-2002 Andras Kis-Szabo <kisza@sch.bme.hu> + */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include <linux/module.h> +#include <linux/skbuff.h> +#include <linux/ipv6.h> +#include <linux/types.h> +#include <net/checksum.h> +#include <net/ipv6.h> + +#include <asm/byteorder.h> + +#include <linux/netfilter/x_tables.h> +#include <linux/netfilter_ipv6/ip6_tables.h> +#include <linux/netfilter_ipv6/ip6t_opts.h> + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Xtables: IPv6 Hop-By-Hop and Destination Header match"); +MODULE_AUTHOR("Andras Kis-Szabo <kisza@sch.bme.hu>"); +MODULE_ALIAS("ip6t_dst"); + +/* + * (Type & 0xC0) >> 6 + * 0 -> ignorable + * 1 -> must drop the packet + * 2 -> send ICMP PARM PROB regardless and drop packet + * 3 -> Send ICMP if not a multicast address and drop packet + * (Type & 0x20) >> 5 + * 0 -> invariant + * 1 -> can change the routing + * (Type & 0x1F) Type + * 0 -> Pad1 (only 1 byte!) + * 1 -> PadN LENGTH info (total length = length + 2) + * C0 | 2 -> JUMBO 4 x x x x ( xxxx > 64k ) + * 5 -> RTALERT 2 x x + */ + +static struct xt_match hbh_mt6_reg[] __read_mostly; + +static bool +hbh_mt6(const struct sk_buff *skb, struct xt_action_param *par) +{ + struct ipv6_opt_hdr _optsh; + const struct ipv6_opt_hdr *oh; + const struct ip6t_opts *optinfo = par->matchinfo; + unsigned int temp; + unsigned int ptr = 0; + unsigned int hdrlen = 0; + bool ret = false; + u8 _opttype; + u8 _optlen; + const u_int8_t *tp = NULL; + const u_int8_t *lp = NULL; + unsigned int optlen; + int err; + + err = ipv6_find_hdr(skb, &ptr, + (par->match == &hbh_mt6_reg[0]) ? + NEXTHDR_HOP : NEXTHDR_DEST, NULL, NULL); + if (err < 0) { + if (err != -ENOENT) + par->hotdrop = true; + return false; + } + + oh = skb_header_pointer(skb, ptr, sizeof(_optsh), &_optsh); + if (oh == NULL) { + par->hotdrop = true; + return false; + } + + hdrlen = ipv6_optlen(oh); + if (skb->len - ptr < hdrlen) { + /* Packet smaller than it's length field */ + return false; + } + + pr_debug("IPv6 OPTS LEN %u %u ", hdrlen, oh->hdrlen); + + pr_debug("len %02X %04X %02X ", + optinfo->hdrlen, hdrlen, + (!(optinfo->flags & IP6T_OPTS_LEN) || + ((optinfo->hdrlen == hdrlen) ^ + !!(optinfo->invflags & IP6T_OPTS_INV_LEN)))); + + ret = (!(optinfo->flags & IP6T_OPTS_LEN) || + ((optinfo->hdrlen == hdrlen) ^ + !!(optinfo->invflags & IP6T_OPTS_INV_LEN))); + + ptr += 2; + hdrlen -= 2; + if (!(optinfo->flags & IP6T_OPTS_OPTS)) { + return ret; + } else { + pr_debug("Strict "); + pr_debug("#%d ", optinfo->optsnr); + for (temp = 0; temp < optinfo->optsnr; temp++) { + /* type field exists ? */ + if (hdrlen < 1) + break; + tp = skb_header_pointer(skb, ptr, sizeof(_opttype), + &_opttype); + if (tp == NULL) + break; + + /* Type check */ + if (*tp != (optinfo->opts[temp] & 0xFF00) >> 8) { + pr_debug("Tbad %02X %02X\n", *tp, + (optinfo->opts[temp] & 0xFF00) >> 8); + return false; + } else { + pr_debug("Tok "); + } + /* Length check */ + if (*tp) { + u16 spec_len; + + /* length field exists ? */ + if (hdrlen < 2) + break; + lp = skb_header_pointer(skb, ptr + 1, + sizeof(_optlen), + &_optlen); + if (lp == NULL) + break; + spec_len = optinfo->opts[temp] & 0x00FF; + + if (spec_len != 0x00FF && spec_len != *lp) { + pr_debug("Lbad %02X %04X\n", *lp, + spec_len); + return false; + } + pr_debug("Lok "); + optlen = *lp + 2; + } else { + pr_debug("Pad1\n"); + optlen = 1; + } + + /* Step to the next */ + pr_debug("len%04X\n", optlen); + + if ((ptr > skb->len - optlen || hdrlen < optlen) && + temp < optinfo->optsnr - 1) { + pr_debug("new pointer is too large!\n"); + break; + } + ptr += optlen; + hdrlen -= optlen; + } + if (temp == optinfo->optsnr) + return ret; + else + return false; + } + + return false; +} + +static int hbh_mt6_check(const struct xt_mtchk_param *par) +{ + const struct ip6t_opts *optsinfo = par->matchinfo; + + if (optsinfo->invflags & ~IP6T_OPTS_INV_MASK) { + pr_debug("unknown flags %X\n", optsinfo->invflags); + return -EINVAL; + } + + if (optsinfo->flags & IP6T_OPTS_NSTRICT) { + pr_debug("Not strict - not implemented"); + return -EINVAL; + } + + return 0; +} + +static struct xt_match hbh_mt6_reg[] __read_mostly = { + { + /* Note, hbh_mt6 relies on the order of hbh_mt6_reg */ + .name = "hbh", + .family = NFPROTO_IPV6, + .match = hbh_mt6, + .matchsize = sizeof(struct ip6t_opts), + .checkentry = hbh_mt6_check, + .me = THIS_MODULE, + }, + { + .name = "dst", + .family = NFPROTO_IPV6, + .match = hbh_mt6, + .matchsize = sizeof(struct ip6t_opts), + .checkentry = hbh_mt6_check, + .me = THIS_MODULE, + }, +}; + +static int __init hbh_mt6_init(void) +{ + return xt_register_matches(hbh_mt6_reg, ARRAY_SIZE(hbh_mt6_reg)); +} + +static void __exit hbh_mt6_exit(void) +{ + xt_unregister_matches(hbh_mt6_reg, ARRAY_SIZE(hbh_mt6_reg)); +} + +module_init(hbh_mt6_init); +module_exit(hbh_mt6_exit); diff --git a/net/ipv6/netfilter/ip6t_ipv6header.c b/net/ipv6/netfilter/ip6t_ipv6header.c new file mode 100644 index 000000000..c52ff929c --- /dev/null +++ b/net/ipv6/netfilter/ip6t_ipv6header.c @@ -0,0 +1,153 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* ipv6header match - matches IPv6 packets based + on whether they contain certain headers */ + +/* Original idea: Brad Chapman + * Rewritten by: Andras Kis-Szabo <kisza@sch.bme.hu> */ + +/* (C) 2001-2002 Andras Kis-Szabo <kisza@sch.bme.hu> + */ + +#include <linux/module.h> +#include <linux/skbuff.h> +#include <linux/ipv6.h> +#include <linux/types.h> +#include <net/checksum.h> +#include <net/ipv6.h> + +#include <linux/netfilter/x_tables.h> +#include <linux/netfilter_ipv6.h> +#include <linux/netfilter_ipv6/ip6t_ipv6header.h> + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Xtables: IPv6 header types match"); +MODULE_AUTHOR("Andras Kis-Szabo <kisza@sch.bme.hu>"); + +static bool +ipv6header_mt6(const struct sk_buff *skb, struct xt_action_param *par) +{ + const struct ip6t_ipv6header_info *info = par->matchinfo; + unsigned int temp; + int len; + u8 nexthdr; + unsigned int ptr; + + /* Make sure this isn't an evil packet */ + + /* type of the 1st exthdr */ + nexthdr = ipv6_hdr(skb)->nexthdr; + /* pointer to the 1st exthdr */ + ptr = sizeof(struct ipv6hdr); + /* available length */ + len = skb->len - ptr; + temp = 0; + + while (nf_ip6_ext_hdr(nexthdr)) { + const struct ipv6_opt_hdr *hp; + struct ipv6_opt_hdr _hdr; + int hdrlen; + + /* No more exthdr -> evaluate */ + if (nexthdr == NEXTHDR_NONE) { + temp |= MASK_NONE; + break; + } + /* Is there enough space for the next ext header? */ + if (len < (int)sizeof(struct ipv6_opt_hdr)) + return false; + /* ESP -> evaluate */ + if (nexthdr == NEXTHDR_ESP) { + temp |= MASK_ESP; + break; + } + + hp = skb_header_pointer(skb, ptr, sizeof(_hdr), &_hdr); + if (!hp) { + par->hotdrop = true; + return false; + } + + /* Calculate the header length */ + if (nexthdr == NEXTHDR_FRAGMENT) + hdrlen = 8; + else if (nexthdr == NEXTHDR_AUTH) + hdrlen = ipv6_authlen(hp); + else + hdrlen = ipv6_optlen(hp); + + /* set the flag */ + switch (nexthdr) { + case NEXTHDR_HOP: + temp |= MASK_HOPOPTS; + break; + case NEXTHDR_ROUTING: + temp |= MASK_ROUTING; + break; + case NEXTHDR_FRAGMENT: + temp |= MASK_FRAGMENT; + break; + case NEXTHDR_AUTH: + temp |= MASK_AH; + break; + case NEXTHDR_DEST: + temp |= MASK_DSTOPTS; + break; + default: + return false; + } + + nexthdr = hp->nexthdr; + len -= hdrlen; + ptr += hdrlen; + if (ptr > skb->len) + break; + } + + if (nexthdr != NEXTHDR_NONE && nexthdr != NEXTHDR_ESP) + temp |= MASK_PROTO; + + if (info->modeflag) + return !((temp ^ info->matchflags ^ info->invflags) + & info->matchflags); + else { + if (info->invflags) + return temp != info->matchflags; + else + return temp == info->matchflags; + } +} + +static int ipv6header_mt6_check(const struct xt_mtchk_param *par) +{ + const struct ip6t_ipv6header_info *info = par->matchinfo; + + /* invflags is 0 or 0xff in hard mode */ + if ((!info->modeflag) && info->invflags != 0x00 && + info->invflags != 0xFF) + return -EINVAL; + + return 0; +} + +static struct xt_match ipv6header_mt6_reg __read_mostly = { + .name = "ipv6header", + .family = NFPROTO_IPV6, + .match = ipv6header_mt6, + .matchsize = sizeof(struct ip6t_ipv6header_info), + .checkentry = ipv6header_mt6_check, + .destroy = NULL, + .me = THIS_MODULE, +}; + +static int __init ipv6header_mt6_init(void) +{ + return xt_register_match(&ipv6header_mt6_reg); +} + +static void __exit ipv6header_mt6_exit(void) +{ + xt_unregister_match(&ipv6header_mt6_reg); +} + +module_init(ipv6header_mt6_init); +module_exit(ipv6header_mt6_exit); diff --git a/net/ipv6/netfilter/ip6t_mh.c b/net/ipv6/netfilter/ip6t_mh.c new file mode 100644 index 000000000..fd492b69a --- /dev/null +++ b/net/ipv6/netfilter/ip6t_mh.c @@ -0,0 +1,90 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C)2006 USAGI/WIDE Project + * + * Author: + * Masahide NAKAMURA @USAGI <masahide.nakamura.cz@hitachi.com> + * + * Based on net/netfilter/xt_tcpudp.c + */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include <linux/types.h> +#include <linux/module.h> +#include <net/ip.h> +#include <linux/ipv6.h> +#include <net/ipv6.h> +#include <net/mip6.h> + +#include <linux/netfilter/x_tables.h> +#include <linux/netfilter_ipv6/ip6t_mh.h> + +MODULE_DESCRIPTION("Xtables: IPv6 Mobility Header match"); +MODULE_LICENSE("GPL"); + +/* Returns 1 if the type is matched by the range, 0 otherwise */ +static inline bool +type_match(u_int8_t min, u_int8_t max, u_int8_t type, bool invert) +{ + return (type >= min && type <= max) ^ invert; +} + +static bool mh_mt6(const struct sk_buff *skb, struct xt_action_param *par) +{ + struct ip6_mh _mh; + const struct ip6_mh *mh; + const struct ip6t_mh *mhinfo = par->matchinfo; + + /* Must not be a fragment. */ + if (par->fragoff != 0) + return false; + + mh = skb_header_pointer(skb, par->thoff, sizeof(_mh), &_mh); + if (mh == NULL) { + /* We've been asked to examine this packet, and we + can't. Hence, no choice but to drop. */ + pr_debug("Dropping evil MH tinygram.\n"); + par->hotdrop = true; + return false; + } + + if (mh->ip6mh_proto != IPPROTO_NONE) { + pr_debug("Dropping invalid MH Payload Proto: %u\n", + mh->ip6mh_proto); + par->hotdrop = true; + return false; + } + + return type_match(mhinfo->types[0], mhinfo->types[1], mh->ip6mh_type, + !!(mhinfo->invflags & IP6T_MH_INV_TYPE)); +} + +static int mh_mt6_check(const struct xt_mtchk_param *par) +{ + const struct ip6t_mh *mhinfo = par->matchinfo; + + /* Must specify no unknown invflags */ + return (mhinfo->invflags & ~IP6T_MH_INV_MASK) ? -EINVAL : 0; +} + +static struct xt_match mh_mt6_reg __read_mostly = { + .name = "mh", + .family = NFPROTO_IPV6, + .checkentry = mh_mt6_check, + .match = mh_mt6, + .matchsize = sizeof(struct ip6t_mh), + .proto = IPPROTO_MH, + .me = THIS_MODULE, +}; + +static int __init mh_mt6_init(void) +{ + return xt_register_match(&mh_mt6_reg); +} + +static void __exit mh_mt6_exit(void) +{ + xt_unregister_match(&mh_mt6_reg); +} + +module_init(mh_mt6_init); +module_exit(mh_mt6_exit); diff --git a/net/ipv6/netfilter/ip6t_rpfilter.c b/net/ipv6/netfilter/ip6t_rpfilter.c new file mode 100644 index 000000000..67c87a88c --- /dev/null +++ b/net/ipv6/netfilter/ip6t_rpfilter.c @@ -0,0 +1,150 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2011 Florian Westphal <fw@strlen.de> + */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include <linux/module.h> +#include <linux/skbuff.h> +#include <linux/netdevice.h> +#include <linux/route.h> +#include <net/ip6_fib.h> +#include <net/ip6_route.h> + +#include <linux/netfilter/xt_rpfilter.h> +#include <linux/netfilter/x_tables.h> + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Florian Westphal <fw@strlen.de>"); +MODULE_DESCRIPTION("Xtables: IPv6 reverse path filter match"); + +static bool rpfilter_addr_unicast(const struct in6_addr *addr) +{ + int addr_type = ipv6_addr_type(addr); + return addr_type & IPV6_ADDR_UNICAST; +} + +static bool rpfilter_addr_linklocal(const struct in6_addr *addr) +{ + int addr_type = ipv6_addr_type(addr); + return addr_type & IPV6_ADDR_LINKLOCAL; +} + +static bool rpfilter_lookup_reverse6(struct net *net, const struct sk_buff *skb, + const struct net_device *dev, u8 flags) +{ + struct rt6_info *rt; + struct ipv6hdr *iph = ipv6_hdr(skb); + bool ret = false; + struct flowi6 fl6 = { + .flowi6_iif = LOOPBACK_IFINDEX, + .flowi6_l3mdev = l3mdev_master_ifindex_rcu(dev), + .flowlabel = (* (__be32 *) iph) & IPV6_FLOWINFO_MASK, + .flowi6_proto = iph->nexthdr, + .flowi6_uid = sock_net_uid(net, NULL), + .daddr = iph->saddr, + }; + int lookup_flags; + + if (rpfilter_addr_unicast(&iph->daddr)) { + memcpy(&fl6.saddr, &iph->daddr, sizeof(struct in6_addr)); + lookup_flags = RT6_LOOKUP_F_HAS_SADDR; + } else { + lookup_flags = 0; + } + + fl6.flowi6_mark = flags & XT_RPFILTER_VALID_MARK ? skb->mark : 0; + + if (rpfilter_addr_linklocal(&iph->saddr)) { + lookup_flags |= RT6_LOOKUP_F_IFACE; + fl6.flowi6_oif = dev->ifindex; + } else if ((flags & XT_RPFILTER_LOOSE) == 0) + fl6.flowi6_oif = dev->ifindex; + + rt = (void *)ip6_route_lookup(net, &fl6, skb, lookup_flags); + if (rt->dst.error) + goto out; + + if (rt->rt6i_flags & (RTF_REJECT|RTF_ANYCAST)) + goto out; + + if (rt->rt6i_flags & RTF_LOCAL) { + ret = flags & XT_RPFILTER_ACCEPT_LOCAL; + goto out; + } + + if (rt->rt6i_idev->dev == dev || + l3mdev_master_ifindex_rcu(rt->rt6i_idev->dev) == dev->ifindex || + (flags & XT_RPFILTER_LOOSE)) + ret = true; + out: + ip6_rt_put(rt); + return ret; +} + +static bool +rpfilter_is_loopback(const struct sk_buff *skb, const struct net_device *in) +{ + return skb->pkt_type == PACKET_LOOPBACK || in->flags & IFF_LOOPBACK; +} + +static bool rpfilter_mt(const struct sk_buff *skb, struct xt_action_param *par) +{ + const struct xt_rpfilter_info *info = par->matchinfo; + int saddrtype; + struct ipv6hdr *iph; + bool invert = info->flags & XT_RPFILTER_INVERT; + + if (rpfilter_is_loopback(skb, xt_in(par))) + return true ^ invert; + + iph = ipv6_hdr(skb); + saddrtype = ipv6_addr_type(&iph->saddr); + if (unlikely(saddrtype == IPV6_ADDR_ANY)) + return true ^ invert; /* not routable: forward path will drop it */ + + return rpfilter_lookup_reverse6(xt_net(par), skb, xt_in(par), + info->flags) ^ invert; +} + +static int rpfilter_check(const struct xt_mtchk_param *par) +{ + const struct xt_rpfilter_info *info = par->matchinfo; + unsigned int options = ~XT_RPFILTER_OPTION_MASK; + + if (info->flags & options) { + pr_info_ratelimited("unknown options\n"); + return -EINVAL; + } + + if (strcmp(par->table, "mangle") != 0 && + strcmp(par->table, "raw") != 0) { + pr_info_ratelimited("only valid in \'raw\' or \'mangle\' table, not \'%s\'\n", + par->table); + return -EINVAL; + } + + return 0; +} + +static struct xt_match rpfilter_mt_reg __read_mostly = { + .name = "rpfilter", + .family = NFPROTO_IPV6, + .checkentry = rpfilter_check, + .match = rpfilter_mt, + .matchsize = sizeof(struct xt_rpfilter_info), + .hooks = (1 << NF_INET_PRE_ROUTING), + .me = THIS_MODULE +}; + +static int __init rpfilter_mt_init(void) +{ + return xt_register_match(&rpfilter_mt_reg); +} + +static void __exit rpfilter_mt_exit(void) +{ + xt_unregister_match(&rpfilter_mt_reg); +} + +module_init(rpfilter_mt_init); +module_exit(rpfilter_mt_exit); diff --git a/net/ipv6/netfilter/ip6t_rt.c b/net/ipv6/netfilter/ip6t_rt.c new file mode 100644 index 000000000..4ad8b2032 --- /dev/null +++ b/net/ipv6/netfilter/ip6t_rt.c @@ -0,0 +1,191 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Kernel module to match ROUTING parameters. */ + +/* (C) 2001-2002 Andras Kis-Szabo <kisza@sch.bme.hu> + */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include <linux/module.h> +#include <linux/skbuff.h> +#include <linux/ipv6.h> +#include <linux/types.h> +#include <net/checksum.h> +#include <net/ipv6.h> + +#include <asm/byteorder.h> + +#include <linux/netfilter/x_tables.h> +#include <linux/netfilter_ipv6/ip6_tables.h> +#include <linux/netfilter_ipv6/ip6t_rt.h> + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Xtables: IPv6 Routing Header match"); +MODULE_AUTHOR("Andras Kis-Szabo <kisza@sch.bme.hu>"); + +/* Returns 1 if the id is matched by the range, 0 otherwise */ +static inline bool +segsleft_match(u_int32_t min, u_int32_t max, u_int32_t id, bool invert) +{ + return (id >= min && id <= max) ^ invert; +} + +static bool rt_mt6(const struct sk_buff *skb, struct xt_action_param *par) +{ + struct ipv6_rt_hdr _route; + const struct ipv6_rt_hdr *rh; + const struct ip6t_rt *rtinfo = par->matchinfo; + unsigned int temp; + unsigned int ptr = 0; + unsigned int hdrlen = 0; + bool ret = false; + struct in6_addr _addr; + const struct in6_addr *ap; + int err; + + err = ipv6_find_hdr(skb, &ptr, NEXTHDR_ROUTING, NULL, NULL); + if (err < 0) { + if (err != -ENOENT) + par->hotdrop = true; + return false; + } + + rh = skb_header_pointer(skb, ptr, sizeof(_route), &_route); + if (rh == NULL) { + par->hotdrop = true; + return false; + } + + hdrlen = ipv6_optlen(rh); + if (skb->len - ptr < hdrlen) { + /* Pcket smaller than its length field */ + return false; + } + + ret = (segsleft_match(rtinfo->segsleft[0], rtinfo->segsleft[1], + rh->segments_left, + !!(rtinfo->invflags & IP6T_RT_INV_SGS))) && + (!(rtinfo->flags & IP6T_RT_LEN) || + ((rtinfo->hdrlen == hdrlen) ^ + !!(rtinfo->invflags & IP6T_RT_INV_LEN))) && + (!(rtinfo->flags & IP6T_RT_TYP) || + ((rtinfo->rt_type == rh->type) ^ + !!(rtinfo->invflags & IP6T_RT_INV_TYP))); + + if (ret && (rtinfo->flags & IP6T_RT_RES)) { + const u_int32_t *rp; + u_int32_t _reserved; + rp = skb_header_pointer(skb, + ptr + offsetof(struct rt0_hdr, + reserved), + sizeof(_reserved), + &_reserved); + if (!rp) { + par->hotdrop = true; + return false; + } + + ret = (*rp == 0); + } + + if (!(rtinfo->flags & IP6T_RT_FST)) { + return ret; + } else if (rtinfo->flags & IP6T_RT_FST_NSTRICT) { + if (rtinfo->addrnr > (unsigned int)((hdrlen - 8) / 16)) { + return false; + } else { + unsigned int i = 0; + + for (temp = 0; + temp < (unsigned int)((hdrlen - 8) / 16); + temp++) { + ap = skb_header_pointer(skb, + ptr + + sizeof(struct rt0_hdr) + + temp * sizeof(_addr), + sizeof(_addr), + &_addr); + + if (ap == NULL) { + par->hotdrop = true; + return false; + } + + if (ipv6_addr_equal(ap, &rtinfo->addrs[i])) + i++; + if (i == rtinfo->addrnr) + break; + } + if (i == rtinfo->addrnr) + return ret; + else + return false; + } + } else { + if (rtinfo->addrnr > (unsigned int)((hdrlen - 8) / 16)) { + return false; + } else { + for (temp = 0; temp < rtinfo->addrnr; temp++) { + ap = skb_header_pointer(skb, + ptr + + sizeof(struct rt0_hdr) + + temp * sizeof(_addr), + sizeof(_addr), + &_addr); + if (ap == NULL) { + par->hotdrop = true; + return false; + } + + if (!ipv6_addr_equal(ap, &rtinfo->addrs[temp])) + break; + } + if (temp == rtinfo->addrnr && + temp == (unsigned int)((hdrlen - 8) / 16)) + return ret; + else + return false; + } + } + + return false; +} + +static int rt_mt6_check(const struct xt_mtchk_param *par) +{ + const struct ip6t_rt *rtinfo = par->matchinfo; + + if (rtinfo->invflags & ~IP6T_RT_INV_MASK) { + pr_debug("unknown flags %X\n", rtinfo->invflags); + return -EINVAL; + } + if ((rtinfo->flags & (IP6T_RT_RES | IP6T_RT_FST_MASK)) && + (!(rtinfo->flags & IP6T_RT_TYP) || + (rtinfo->rt_type != 0) || + (rtinfo->invflags & IP6T_RT_INV_TYP))) { + pr_debug("`--rt-type 0' required before `--rt-0-*'"); + return -EINVAL; + } + + return 0; +} + +static struct xt_match rt_mt6_reg __read_mostly = { + .name = "rt", + .family = NFPROTO_IPV6, + .match = rt_mt6, + .matchsize = sizeof(struct ip6t_rt), + .checkentry = rt_mt6_check, + .me = THIS_MODULE, +}; + +static int __init rt_mt6_init(void) +{ + return xt_register_match(&rt_mt6_reg); +} + +static void __exit rt_mt6_exit(void) +{ + xt_unregister_match(&rt_mt6_reg); +} + +module_init(rt_mt6_init); +module_exit(rt_mt6_exit); diff --git a/net/ipv6/netfilter/ip6t_srh.c b/net/ipv6/netfilter/ip6t_srh.c new file mode 100644 index 000000000..db0fd64d8 --- /dev/null +++ b/net/ipv6/netfilter/ip6t_srh.c @@ -0,0 +1,320 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* Kernel module to match Segment Routing Header (SRH) parameters. */ + +/* Author: + * Ahmed Abdelsalam <amsalam20@gmail.com> + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include <linux/module.h> +#include <linux/skbuff.h> +#include <linux/ipv6.h> +#include <linux/types.h> +#include <net/ipv6.h> +#include <net/seg6.h> + +#include <linux/netfilter/x_tables.h> +#include <linux/netfilter_ipv6/ip6t_srh.h> +#include <linux/netfilter_ipv6/ip6_tables.h> + +/* Test a struct->mt_invflags and a boolean for inequality */ +#define NF_SRH_INVF(ptr, flag, boolean) \ + ((boolean) ^ !!((ptr)->mt_invflags & (flag))) + +static bool srh_mt6(const struct sk_buff *skb, struct xt_action_param *par) +{ + const struct ip6t_srh *srhinfo = par->matchinfo; + struct ipv6_sr_hdr *srh; + struct ipv6_sr_hdr _srh; + int hdrlen, srhoff = 0; + + if (ipv6_find_hdr(skb, &srhoff, IPPROTO_ROUTING, NULL, NULL) < 0) + return false; + srh = skb_header_pointer(skb, srhoff, sizeof(_srh), &_srh); + if (!srh) + return false; + + hdrlen = ipv6_optlen(srh); + if (skb->len - srhoff < hdrlen) + return false; + + if (srh->type != IPV6_SRCRT_TYPE_4) + return false; + + if (srh->segments_left > srh->first_segment) + return false; + + /* Next Header matching */ + if (srhinfo->mt_flags & IP6T_SRH_NEXTHDR) + if (NF_SRH_INVF(srhinfo, IP6T_SRH_INV_NEXTHDR, + !(srh->nexthdr == srhinfo->next_hdr))) + return false; + + /* Header Extension Length matching */ + if (srhinfo->mt_flags & IP6T_SRH_LEN_EQ) + if (NF_SRH_INVF(srhinfo, IP6T_SRH_INV_LEN_EQ, + !(srh->hdrlen == srhinfo->hdr_len))) + return false; + + if (srhinfo->mt_flags & IP6T_SRH_LEN_GT) + if (NF_SRH_INVF(srhinfo, IP6T_SRH_INV_LEN_GT, + !(srh->hdrlen > srhinfo->hdr_len))) + return false; + + if (srhinfo->mt_flags & IP6T_SRH_LEN_LT) + if (NF_SRH_INVF(srhinfo, IP6T_SRH_INV_LEN_LT, + !(srh->hdrlen < srhinfo->hdr_len))) + return false; + + /* Segments Left matching */ + if (srhinfo->mt_flags & IP6T_SRH_SEGS_EQ) + if (NF_SRH_INVF(srhinfo, IP6T_SRH_INV_SEGS_EQ, + !(srh->segments_left == srhinfo->segs_left))) + return false; + + if (srhinfo->mt_flags & IP6T_SRH_SEGS_GT) + if (NF_SRH_INVF(srhinfo, IP6T_SRH_INV_SEGS_GT, + !(srh->segments_left > srhinfo->segs_left))) + return false; + + if (srhinfo->mt_flags & IP6T_SRH_SEGS_LT) + if (NF_SRH_INVF(srhinfo, IP6T_SRH_INV_SEGS_LT, + !(srh->segments_left < srhinfo->segs_left))) + return false; + + /** + * Last Entry matching + * Last_Entry field was introduced in revision 6 of the SRH draft. + * It was called First_Segment in the previous revision + */ + if (srhinfo->mt_flags & IP6T_SRH_LAST_EQ) + if (NF_SRH_INVF(srhinfo, IP6T_SRH_INV_LAST_EQ, + !(srh->first_segment == srhinfo->last_entry))) + return false; + + if (srhinfo->mt_flags & IP6T_SRH_LAST_GT) + if (NF_SRH_INVF(srhinfo, IP6T_SRH_INV_LAST_GT, + !(srh->first_segment > srhinfo->last_entry))) + return false; + + if (srhinfo->mt_flags & IP6T_SRH_LAST_LT) + if (NF_SRH_INVF(srhinfo, IP6T_SRH_INV_LAST_LT, + !(srh->first_segment < srhinfo->last_entry))) + return false; + + /** + * Tag matchig + * Tag field was introduced in revision 6 of the SRH draft. + */ + if (srhinfo->mt_flags & IP6T_SRH_TAG) + if (NF_SRH_INVF(srhinfo, IP6T_SRH_INV_TAG, + !(srh->tag == srhinfo->tag))) + return false; + return true; +} + +static bool srh1_mt6(const struct sk_buff *skb, struct xt_action_param *par) +{ + int hdrlen, psidoff, nsidoff, lsidoff, srhoff = 0; + const struct ip6t_srh1 *srhinfo = par->matchinfo; + struct in6_addr *psid, *nsid, *lsid; + struct in6_addr _psid, _nsid, _lsid; + struct ipv6_sr_hdr *srh; + struct ipv6_sr_hdr _srh; + + if (ipv6_find_hdr(skb, &srhoff, IPPROTO_ROUTING, NULL, NULL) < 0) + return false; + srh = skb_header_pointer(skb, srhoff, sizeof(_srh), &_srh); + if (!srh) + return false; + + hdrlen = ipv6_optlen(srh); + if (skb->len - srhoff < hdrlen) + return false; + + if (srh->type != IPV6_SRCRT_TYPE_4) + return false; + + if (srh->segments_left > srh->first_segment) + return false; + + /* Next Header matching */ + if (srhinfo->mt_flags & IP6T_SRH_NEXTHDR) + if (NF_SRH_INVF(srhinfo, IP6T_SRH_INV_NEXTHDR, + !(srh->nexthdr == srhinfo->next_hdr))) + return false; + + /* Header Extension Length matching */ + if (srhinfo->mt_flags & IP6T_SRH_LEN_EQ) + if (NF_SRH_INVF(srhinfo, IP6T_SRH_INV_LEN_EQ, + !(srh->hdrlen == srhinfo->hdr_len))) + return false; + if (srhinfo->mt_flags & IP6T_SRH_LEN_GT) + if (NF_SRH_INVF(srhinfo, IP6T_SRH_INV_LEN_GT, + !(srh->hdrlen > srhinfo->hdr_len))) + return false; + if (srhinfo->mt_flags & IP6T_SRH_LEN_LT) + if (NF_SRH_INVF(srhinfo, IP6T_SRH_INV_LEN_LT, + !(srh->hdrlen < srhinfo->hdr_len))) + return false; + + /* Segments Left matching */ + if (srhinfo->mt_flags & IP6T_SRH_SEGS_EQ) + if (NF_SRH_INVF(srhinfo, IP6T_SRH_INV_SEGS_EQ, + !(srh->segments_left == srhinfo->segs_left))) + return false; + if (srhinfo->mt_flags & IP6T_SRH_SEGS_GT) + if (NF_SRH_INVF(srhinfo, IP6T_SRH_INV_SEGS_GT, + !(srh->segments_left > srhinfo->segs_left))) + return false; + if (srhinfo->mt_flags & IP6T_SRH_SEGS_LT) + if (NF_SRH_INVF(srhinfo, IP6T_SRH_INV_SEGS_LT, + !(srh->segments_left < srhinfo->segs_left))) + return false; + + /** + * Last Entry matching + * Last_Entry field was introduced in revision 6 of the SRH draft. + * It was called First_Segment in the previous revision + */ + if (srhinfo->mt_flags & IP6T_SRH_LAST_EQ) + if (NF_SRH_INVF(srhinfo, IP6T_SRH_INV_LAST_EQ, + !(srh->first_segment == srhinfo->last_entry))) + return false; + if (srhinfo->mt_flags & IP6T_SRH_LAST_GT) + if (NF_SRH_INVF(srhinfo, IP6T_SRH_INV_LAST_GT, + !(srh->first_segment > srhinfo->last_entry))) + return false; + if (srhinfo->mt_flags & IP6T_SRH_LAST_LT) + if (NF_SRH_INVF(srhinfo, IP6T_SRH_INV_LAST_LT, + !(srh->first_segment < srhinfo->last_entry))) + return false; + + /** + * Tag matchig + * Tag field was introduced in revision 6 of the SRH draft + */ + if (srhinfo->mt_flags & IP6T_SRH_TAG) + if (NF_SRH_INVF(srhinfo, IP6T_SRH_INV_TAG, + !(srh->tag == srhinfo->tag))) + return false; + + /* Previous SID matching */ + if (srhinfo->mt_flags & IP6T_SRH_PSID) { + if (srh->segments_left == srh->first_segment) + return false; + psidoff = srhoff + sizeof(struct ipv6_sr_hdr) + + ((srh->segments_left + 1) * sizeof(struct in6_addr)); + psid = skb_header_pointer(skb, psidoff, sizeof(_psid), &_psid); + if (!psid) + return false; + if (NF_SRH_INVF(srhinfo, IP6T_SRH_INV_PSID, + ipv6_masked_addr_cmp(psid, &srhinfo->psid_msk, + &srhinfo->psid_addr))) + return false; + } + + /* Next SID matching */ + if (srhinfo->mt_flags & IP6T_SRH_NSID) { + if (srh->segments_left == 0) + return false; + nsidoff = srhoff + sizeof(struct ipv6_sr_hdr) + + ((srh->segments_left - 1) * sizeof(struct in6_addr)); + nsid = skb_header_pointer(skb, nsidoff, sizeof(_nsid), &_nsid); + if (!nsid) + return false; + if (NF_SRH_INVF(srhinfo, IP6T_SRH_INV_NSID, + ipv6_masked_addr_cmp(nsid, &srhinfo->nsid_msk, + &srhinfo->nsid_addr))) + return false; + } + + /* Last SID matching */ + if (srhinfo->mt_flags & IP6T_SRH_LSID) { + lsidoff = srhoff + sizeof(struct ipv6_sr_hdr); + lsid = skb_header_pointer(skb, lsidoff, sizeof(_lsid), &_lsid); + if (!lsid) + return false; + if (NF_SRH_INVF(srhinfo, IP6T_SRH_INV_LSID, + ipv6_masked_addr_cmp(lsid, &srhinfo->lsid_msk, + &srhinfo->lsid_addr))) + return false; + } + return true; +} + +static int srh_mt6_check(const struct xt_mtchk_param *par) +{ + const struct ip6t_srh *srhinfo = par->matchinfo; + + if (srhinfo->mt_flags & ~IP6T_SRH_MASK) { + pr_info_ratelimited("unknown srh match flags %X\n", + srhinfo->mt_flags); + return -EINVAL; + } + + if (srhinfo->mt_invflags & ~IP6T_SRH_INV_MASK) { + pr_info_ratelimited("unknown srh invflags %X\n", + srhinfo->mt_invflags); + return -EINVAL; + } + + return 0; +} + +static int srh1_mt6_check(const struct xt_mtchk_param *par) +{ + const struct ip6t_srh1 *srhinfo = par->matchinfo; + + if (srhinfo->mt_flags & ~IP6T_SRH_MASK) { + pr_info_ratelimited("unknown srh match flags %X\n", + srhinfo->mt_flags); + return -EINVAL; + } + + if (srhinfo->mt_invflags & ~IP6T_SRH_INV_MASK) { + pr_info_ratelimited("unknown srh invflags %X\n", + srhinfo->mt_invflags); + return -EINVAL; + } + + return 0; +} + +static struct xt_match srh_mt6_reg[] __read_mostly = { + { + .name = "srh", + .revision = 0, + .family = NFPROTO_IPV6, + .match = srh_mt6, + .matchsize = sizeof(struct ip6t_srh), + .checkentry = srh_mt6_check, + .me = THIS_MODULE, + }, + { + .name = "srh", + .revision = 1, + .family = NFPROTO_IPV6, + .match = srh1_mt6, + .matchsize = sizeof(struct ip6t_srh1), + .checkentry = srh1_mt6_check, + .me = THIS_MODULE, + } +}; + +static int __init srh_mt6_init(void) +{ + return xt_register_matches(srh_mt6_reg, ARRAY_SIZE(srh_mt6_reg)); +} + +static void __exit srh_mt6_exit(void) +{ + xt_unregister_matches(srh_mt6_reg, ARRAY_SIZE(srh_mt6_reg)); +} + +module_init(srh_mt6_init); +module_exit(srh_mt6_exit); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Xtables: IPv6 Segment Routing Header match"); +MODULE_AUTHOR("Ahmed Abdelsalam <amsalam20@gmail.com>"); diff --git a/net/ipv6/netfilter/ip6table_filter.c b/net/ipv6/netfilter/ip6table_filter.c new file mode 100644 index 000000000..df785ebda --- /dev/null +++ b/net/ipv6/netfilter/ip6table_filter.c @@ -0,0 +1,109 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * This is the 1999 rewrite of IP Firewalling, aiming for kernel 2.3.x. + * + * Copyright (C) 1999 Paul `Rusty' Russell & Michael J. Neuling + * Copyright (C) 2000-2004 Netfilter Core Team <coreteam@netfilter.org> + */ + +#include <linux/module.h> +#include <linux/moduleparam.h> +#include <linux/netfilter_ipv6/ip6_tables.h> +#include <linux/slab.h> + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>"); +MODULE_DESCRIPTION("ip6tables filter table"); + +#define FILTER_VALID_HOOKS ((1 << NF_INET_LOCAL_IN) | \ + (1 << NF_INET_FORWARD) | \ + (1 << NF_INET_LOCAL_OUT)) + +static const struct xt_table packet_filter = { + .name = "filter", + .valid_hooks = FILTER_VALID_HOOKS, + .me = THIS_MODULE, + .af = NFPROTO_IPV6, + .priority = NF_IP6_PRI_FILTER, +}; + +static struct nf_hook_ops *filter_ops __read_mostly; + +/* Default to forward because I got too much mail already. */ +static bool forward = true; +module_param(forward, bool, 0000); + +static int ip6table_filter_table_init(struct net *net) +{ + struct ip6t_replace *repl; + int err; + + repl = ip6t_alloc_initial_table(&packet_filter); + if (repl == NULL) + return -ENOMEM; + /* Entry 1 is the FORWARD hook */ + ((struct ip6t_standard *)repl->entries)[1].target.verdict = + forward ? -NF_ACCEPT - 1 : -NF_DROP - 1; + + err = ip6t_register_table(net, &packet_filter, repl, filter_ops); + kfree(repl); + return err; +} + +static int __net_init ip6table_filter_net_init(struct net *net) +{ + if (!forward) + return ip6table_filter_table_init(net); + + return 0; +} + +static void __net_exit ip6table_filter_net_pre_exit(struct net *net) +{ + ip6t_unregister_table_pre_exit(net, "filter"); +} + +static void __net_exit ip6table_filter_net_exit(struct net *net) +{ + ip6t_unregister_table_exit(net, "filter"); +} + +static struct pernet_operations ip6table_filter_net_ops = { + .init = ip6table_filter_net_init, + .pre_exit = ip6table_filter_net_pre_exit, + .exit = ip6table_filter_net_exit, +}; + +static int __init ip6table_filter_init(void) +{ + int ret = xt_register_template(&packet_filter, + ip6table_filter_table_init); + + if (ret < 0) + return ret; + + filter_ops = xt_hook_ops_alloc(&packet_filter, ip6t_do_table); + if (IS_ERR(filter_ops)) { + xt_unregister_template(&packet_filter); + return PTR_ERR(filter_ops); + } + + ret = register_pernet_subsys(&ip6table_filter_net_ops); + if (ret < 0) { + xt_unregister_template(&packet_filter); + kfree(filter_ops); + return ret; + } + + return ret; +} + +static void __exit ip6table_filter_fini(void) +{ + unregister_pernet_subsys(&ip6table_filter_net_ops); + xt_unregister_template(&packet_filter); + kfree(filter_ops); +} + +module_init(ip6table_filter_init); +module_exit(ip6table_filter_fini); diff --git a/net/ipv6/netfilter/ip6table_mangle.c b/net/ipv6/netfilter/ip6table_mangle.c new file mode 100644 index 000000000..a88b2ce4a --- /dev/null +++ b/net/ipv6/netfilter/ip6table_mangle.c @@ -0,0 +1,136 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * IPv6 packet mangling table, a port of the IPv4 mangle table to IPv6 + * + * Copyright (C) 2000-2001 by Harald Welte <laforge@gnumonks.org> + * Copyright (C) 2000-2004 Netfilter Core Team <coreteam@netfilter.org> + */ +#include <linux/module.h> +#include <linux/netfilter_ipv6/ip6_tables.h> +#include <linux/slab.h> +#include <net/ipv6.h> + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>"); +MODULE_DESCRIPTION("ip6tables mangle table"); + +#define MANGLE_VALID_HOOKS ((1 << NF_INET_PRE_ROUTING) | \ + (1 << NF_INET_LOCAL_IN) | \ + (1 << NF_INET_FORWARD) | \ + (1 << NF_INET_LOCAL_OUT) | \ + (1 << NF_INET_POST_ROUTING)) + +static const struct xt_table packet_mangler = { + .name = "mangle", + .valid_hooks = MANGLE_VALID_HOOKS, + .me = THIS_MODULE, + .af = NFPROTO_IPV6, + .priority = NF_IP6_PRI_MANGLE, +}; + +static unsigned int +ip6t_mangle_out(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) +{ + unsigned int ret; + struct in6_addr saddr, daddr; + u_int8_t hop_limit; + u_int32_t flowlabel, mark; + int err; + + /* save source/dest address, mark, hoplimit, flowlabel, priority, */ + memcpy(&saddr, &ipv6_hdr(skb)->saddr, sizeof(saddr)); + memcpy(&daddr, &ipv6_hdr(skb)->daddr, sizeof(daddr)); + mark = skb->mark; + hop_limit = ipv6_hdr(skb)->hop_limit; + + /* flowlabel and prio (includes version, which shouldn't change either */ + flowlabel = *((u_int32_t *)ipv6_hdr(skb)); + + ret = ip6t_do_table(priv, skb, state); + + if (ret != NF_DROP && ret != NF_STOLEN && + (!ipv6_addr_equal(&ipv6_hdr(skb)->saddr, &saddr) || + !ipv6_addr_equal(&ipv6_hdr(skb)->daddr, &daddr) || + skb->mark != mark || + ipv6_hdr(skb)->hop_limit != hop_limit || + flowlabel != *((u_int32_t *)ipv6_hdr(skb)))) { + err = ip6_route_me_harder(state->net, state->sk, skb); + if (err < 0) + ret = NF_DROP_ERR(err); + } + + return ret; +} + +/* The work comes in here from netfilter.c. */ +static unsigned int +ip6table_mangle_hook(void *priv, struct sk_buff *skb, + const struct nf_hook_state *state) +{ + if (state->hook == NF_INET_LOCAL_OUT) + return ip6t_mangle_out(priv, skb, state); + return ip6t_do_table(priv, skb, state); +} + +static struct nf_hook_ops *mangle_ops __read_mostly; +static int ip6table_mangle_table_init(struct net *net) +{ + struct ip6t_replace *repl; + int ret; + + repl = ip6t_alloc_initial_table(&packet_mangler); + if (repl == NULL) + return -ENOMEM; + ret = ip6t_register_table(net, &packet_mangler, repl, mangle_ops); + kfree(repl); + return ret; +} + +static void __net_exit ip6table_mangle_net_pre_exit(struct net *net) +{ + ip6t_unregister_table_pre_exit(net, "mangle"); +} + +static void __net_exit ip6table_mangle_net_exit(struct net *net) +{ + ip6t_unregister_table_exit(net, "mangle"); +} + +static struct pernet_operations ip6table_mangle_net_ops = { + .pre_exit = ip6table_mangle_net_pre_exit, + .exit = ip6table_mangle_net_exit, +}; + +static int __init ip6table_mangle_init(void) +{ + int ret = xt_register_template(&packet_mangler, + ip6table_mangle_table_init); + + if (ret < 0) + return ret; + + mangle_ops = xt_hook_ops_alloc(&packet_mangler, ip6table_mangle_hook); + if (IS_ERR(mangle_ops)) { + xt_unregister_template(&packet_mangler); + return PTR_ERR(mangle_ops); + } + + ret = register_pernet_subsys(&ip6table_mangle_net_ops); + if (ret < 0) { + xt_unregister_template(&packet_mangler); + kfree(mangle_ops); + return ret; + } + + return ret; +} + +static void __exit ip6table_mangle_fini(void) +{ + unregister_pernet_subsys(&ip6table_mangle_net_ops); + xt_unregister_template(&packet_mangler); + kfree(mangle_ops); +} + +module_init(ip6table_mangle_init); +module_exit(ip6table_mangle_fini); diff --git a/net/ipv6/netfilter/ip6table_nat.c b/net/ipv6/netfilter/ip6table_nat.c new file mode 100644 index 000000000..bf3cb3a13 --- /dev/null +++ b/net/ipv6/netfilter/ip6table_nat.c @@ -0,0 +1,172 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2011 Patrick McHardy <kaber@trash.net> + * + * Based on Rusty Russell's IPv4 NAT code. Development of IPv6 NAT + * funded by Astaro. + */ + +#include <linux/module.h> +#include <linux/netfilter.h> +#include <linux/netfilter_ipv6.h> +#include <linux/netfilter_ipv6/ip6_tables.h> +#include <linux/ipv6.h> +#include <net/ipv6.h> + +#include <net/netfilter/nf_nat.h> + +struct ip6table_nat_pernet { + struct nf_hook_ops *nf_nat_ops; +}; + +static unsigned int ip6table_nat_net_id __read_mostly; + +static const struct xt_table nf_nat_ipv6_table = { + .name = "nat", + .valid_hooks = (1 << NF_INET_PRE_ROUTING) | + (1 << NF_INET_POST_ROUTING) | + (1 << NF_INET_LOCAL_OUT) | + (1 << NF_INET_LOCAL_IN), + .me = THIS_MODULE, + .af = NFPROTO_IPV6, +}; + +static const struct nf_hook_ops nf_nat_ipv6_ops[] = { + { + .hook = ip6t_do_table, + .pf = NFPROTO_IPV6, + .hooknum = NF_INET_PRE_ROUTING, + .priority = NF_IP6_PRI_NAT_DST, + }, + { + .hook = ip6t_do_table, + .pf = NFPROTO_IPV6, + .hooknum = NF_INET_POST_ROUTING, + .priority = NF_IP6_PRI_NAT_SRC, + }, + { + .hook = ip6t_do_table, + .pf = NFPROTO_IPV6, + .hooknum = NF_INET_LOCAL_OUT, + .priority = NF_IP6_PRI_NAT_DST, + }, + { + .hook = ip6t_do_table, + .pf = NFPROTO_IPV6, + .hooknum = NF_INET_LOCAL_IN, + .priority = NF_IP6_PRI_NAT_SRC, + }, +}; + +static int ip6t_nat_register_lookups(struct net *net) +{ + struct ip6table_nat_pernet *xt_nat_net; + struct nf_hook_ops *ops; + struct xt_table *table; + int i, ret; + + table = xt_find_table(net, NFPROTO_IPV6, "nat"); + if (WARN_ON_ONCE(!table)) + return -ENOENT; + + xt_nat_net = net_generic(net, ip6table_nat_net_id); + ops = kmemdup(nf_nat_ipv6_ops, sizeof(nf_nat_ipv6_ops), GFP_KERNEL); + if (!ops) + return -ENOMEM; + + for (i = 0; i < ARRAY_SIZE(nf_nat_ipv6_ops); i++) { + ops[i].priv = table; + ret = nf_nat_ipv6_register_fn(net, &ops[i]); + if (ret) { + while (i) + nf_nat_ipv6_unregister_fn(net, &ops[--i]); + + kfree(ops); + return ret; + } + } + + xt_nat_net->nf_nat_ops = ops; + return 0; +} + +static void ip6t_nat_unregister_lookups(struct net *net) +{ + struct ip6table_nat_pernet *xt_nat_net = net_generic(net, ip6table_nat_net_id); + struct nf_hook_ops *ops = xt_nat_net->nf_nat_ops; + int i; + + if (!ops) + return; + + for (i = 0; i < ARRAY_SIZE(nf_nat_ipv6_ops); i++) + nf_nat_ipv6_unregister_fn(net, &ops[i]); + + kfree(ops); +} + +static int ip6table_nat_table_init(struct net *net) +{ + struct ip6t_replace *repl; + int ret; + + repl = ip6t_alloc_initial_table(&nf_nat_ipv6_table); + if (repl == NULL) + return -ENOMEM; + ret = ip6t_register_table(net, &nf_nat_ipv6_table, repl, + NULL); + if (ret < 0) { + kfree(repl); + return ret; + } + + ret = ip6t_nat_register_lookups(net); + if (ret < 0) + ip6t_unregister_table_exit(net, "nat"); + + kfree(repl); + return ret; +} + +static void __net_exit ip6table_nat_net_pre_exit(struct net *net) +{ + ip6t_nat_unregister_lookups(net); +} + +static void __net_exit ip6table_nat_net_exit(struct net *net) +{ + ip6t_unregister_table_exit(net, "nat"); +} + +static struct pernet_operations ip6table_nat_net_ops = { + .pre_exit = ip6table_nat_net_pre_exit, + .exit = ip6table_nat_net_exit, + .id = &ip6table_nat_net_id, + .size = sizeof(struct ip6table_nat_pernet), +}; + +static int __init ip6table_nat_init(void) +{ + int ret = xt_register_template(&nf_nat_ipv6_table, + ip6table_nat_table_init); + + if (ret < 0) + return ret; + + ret = register_pernet_subsys(&ip6table_nat_net_ops); + if (ret) + xt_unregister_template(&nf_nat_ipv6_table); + + return ret; +} + +static void __exit ip6table_nat_exit(void) +{ + unregister_pernet_subsys(&ip6table_nat_net_ops); + xt_unregister_template(&nf_nat_ipv6_table); +} + +module_init(ip6table_nat_init); +module_exit(ip6table_nat_exit); + +MODULE_LICENSE("GPL"); diff --git a/net/ipv6/netfilter/ip6table_raw.c b/net/ipv6/netfilter/ip6table_raw.c new file mode 100644 index 000000000..08861d5d1 --- /dev/null +++ b/net/ipv6/netfilter/ip6table_raw.c @@ -0,0 +1,108 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * IPv6 raw table, a port of the IPv4 raw table to IPv6 + * + * Copyright (C) 2003 Jozsef Kadlecsik <kadlec@netfilter.org> + */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include <linux/module.h> +#include <linux/netfilter_ipv6/ip6_tables.h> +#include <linux/slab.h> + +#define RAW_VALID_HOOKS ((1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_OUT)) + +static bool raw_before_defrag __read_mostly; +MODULE_PARM_DESC(raw_before_defrag, "Enable raw table before defrag"); +module_param(raw_before_defrag, bool, 0000); + +static const struct xt_table packet_raw = { + .name = "raw", + .valid_hooks = RAW_VALID_HOOKS, + .me = THIS_MODULE, + .af = NFPROTO_IPV6, + .priority = NF_IP6_PRI_RAW, +}; + +static const struct xt_table packet_raw_before_defrag = { + .name = "raw", + .valid_hooks = RAW_VALID_HOOKS, + .me = THIS_MODULE, + .af = NFPROTO_IPV6, + .priority = NF_IP6_PRI_RAW_BEFORE_DEFRAG, +}; + +static struct nf_hook_ops *rawtable_ops __read_mostly; + +static int ip6table_raw_table_init(struct net *net) +{ + struct ip6t_replace *repl; + const struct xt_table *table = &packet_raw; + int ret; + + if (raw_before_defrag) + table = &packet_raw_before_defrag; + + repl = ip6t_alloc_initial_table(table); + if (repl == NULL) + return -ENOMEM; + ret = ip6t_register_table(net, table, repl, rawtable_ops); + kfree(repl); + return ret; +} + +static void __net_exit ip6table_raw_net_pre_exit(struct net *net) +{ + ip6t_unregister_table_pre_exit(net, "raw"); +} + +static void __net_exit ip6table_raw_net_exit(struct net *net) +{ + ip6t_unregister_table_exit(net, "raw"); +} + +static struct pernet_operations ip6table_raw_net_ops = { + .pre_exit = ip6table_raw_net_pre_exit, + .exit = ip6table_raw_net_exit, +}; + +static int __init ip6table_raw_init(void) +{ + const struct xt_table *table = &packet_raw; + int ret; + + if (raw_before_defrag) { + table = &packet_raw_before_defrag; + pr_info("Enabling raw table before defrag\n"); + } + + ret = xt_register_template(table, ip6table_raw_table_init); + if (ret < 0) + return ret; + + /* Register hooks */ + rawtable_ops = xt_hook_ops_alloc(table, ip6t_do_table); + if (IS_ERR(rawtable_ops)) { + xt_unregister_template(table); + return PTR_ERR(rawtable_ops); + } + + ret = register_pernet_subsys(&ip6table_raw_net_ops); + if (ret < 0) { + kfree(rawtable_ops); + xt_unregister_template(table); + return ret; + } + + return ret; +} + +static void __exit ip6table_raw_fini(void) +{ + unregister_pernet_subsys(&ip6table_raw_net_ops); + xt_unregister_template(&packet_raw); + kfree(rawtable_ops); +} + +module_init(ip6table_raw_init); +module_exit(ip6table_raw_fini); +MODULE_LICENSE("GPL"); diff --git a/net/ipv6/netfilter/ip6table_security.c b/net/ipv6/netfilter/ip6table_security.c new file mode 100644 index 000000000..4df14a9ba --- /dev/null +++ b/net/ipv6/netfilter/ip6table_security.c @@ -0,0 +1,97 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * "security" table for IPv6 + * + * This is for use by Mandatory Access Control (MAC) security models, + * which need to be able to manage security policy in separate context + * to DAC. + * + * Based on iptable_mangle.c + * + * Copyright (C) 1999 Paul `Rusty' Russell & Michael J. Neuling + * Copyright (C) 2000-2004 Netfilter Core Team <coreteam <at> netfilter.org> + * Copyright (C) 2008 Red Hat, Inc., James Morris <jmorris <at> redhat.com> + */ +#include <linux/module.h> +#include <linux/netfilter_ipv6/ip6_tables.h> +#include <linux/slab.h> + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("James Morris <jmorris <at> redhat.com>"); +MODULE_DESCRIPTION("ip6tables security table, for MAC rules"); + +#define SECURITY_VALID_HOOKS (1 << NF_INET_LOCAL_IN) | \ + (1 << NF_INET_FORWARD) | \ + (1 << NF_INET_LOCAL_OUT) + +static const struct xt_table security_table = { + .name = "security", + .valid_hooks = SECURITY_VALID_HOOKS, + .me = THIS_MODULE, + .af = NFPROTO_IPV6, + .priority = NF_IP6_PRI_SECURITY, +}; + +static struct nf_hook_ops *sectbl_ops __read_mostly; + +static int ip6table_security_table_init(struct net *net) +{ + struct ip6t_replace *repl; + int ret; + + repl = ip6t_alloc_initial_table(&security_table); + if (repl == NULL) + return -ENOMEM; + ret = ip6t_register_table(net, &security_table, repl, sectbl_ops); + kfree(repl); + return ret; +} + +static void __net_exit ip6table_security_net_pre_exit(struct net *net) +{ + ip6t_unregister_table_pre_exit(net, "security"); +} + +static void __net_exit ip6table_security_net_exit(struct net *net) +{ + ip6t_unregister_table_exit(net, "security"); +} + +static struct pernet_operations ip6table_security_net_ops = { + .pre_exit = ip6table_security_net_pre_exit, + .exit = ip6table_security_net_exit, +}; + +static int __init ip6table_security_init(void) +{ + int ret = xt_register_template(&security_table, + ip6table_security_table_init); + + if (ret < 0) + return ret; + + sectbl_ops = xt_hook_ops_alloc(&security_table, ip6t_do_table); + if (IS_ERR(sectbl_ops)) { + xt_unregister_template(&security_table); + return PTR_ERR(sectbl_ops); + } + + ret = register_pernet_subsys(&ip6table_security_net_ops); + if (ret < 0) { + kfree(sectbl_ops); + xt_unregister_template(&security_table); + return ret; + } + + return ret; +} + +static void __exit ip6table_security_fini(void) +{ + unregister_pernet_subsys(&ip6table_security_net_ops); + xt_unregister_template(&security_table); + kfree(sectbl_ops); +} + +module_init(ip6table_security_init); +module_exit(ip6table_security_fini); diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c new file mode 100644 index 000000000..38db0064d --- /dev/null +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -0,0 +1,568 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * IPv6 fragment reassembly for connection tracking + * + * Copyright (C)2004 USAGI/WIDE Project + * + * Author: + * Yasuyuki Kozakai @USAGI <yasuyuki.kozakai@toshiba.co.jp> + * + * Based on: net/ipv6/reassembly.c + */ + +#define pr_fmt(fmt) "IPv6-nf: " fmt + +#include <linux/errno.h> +#include <linux/types.h> +#include <linux/string.h> +#include <linux/net.h> +#include <linux/netdevice.h> +#include <linux/ipv6.h> +#include <linux/slab.h> + +#include <net/ipv6_frag.h> + +#include <net/netfilter/ipv6/nf_conntrack_ipv6.h> +#include <linux/sysctl.h> +#include <linux/netfilter.h> +#include <linux/netfilter_ipv6.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <net/netfilter/ipv6/nf_defrag_ipv6.h> +#include <net/netns/generic.h> + +static const char nf_frags_cache_name[] = "nf-frags"; + +static unsigned int nf_frag_pernet_id __read_mostly; +static struct inet_frags nf_frags; + +static struct nft_ct_frag6_pernet *nf_frag_pernet(struct net *net) +{ + return net_generic(net, nf_frag_pernet_id); +} + +#ifdef CONFIG_SYSCTL + +static struct ctl_table nf_ct_frag6_sysctl_table[] = { + { + .procname = "nf_conntrack_frag6_timeout", + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, + { + .procname = "nf_conntrack_frag6_low_thresh", + .maxlen = sizeof(unsigned long), + .mode = 0644, + .proc_handler = proc_doulongvec_minmax, + }, + { + .procname = "nf_conntrack_frag6_high_thresh", + .maxlen = sizeof(unsigned long), + .mode = 0644, + .proc_handler = proc_doulongvec_minmax, + }, + { } +}; + +static int nf_ct_frag6_sysctl_register(struct net *net) +{ + struct nft_ct_frag6_pernet *nf_frag; + struct ctl_table *table; + struct ctl_table_header *hdr; + + table = nf_ct_frag6_sysctl_table; + if (!net_eq(net, &init_net)) { + table = kmemdup(table, sizeof(nf_ct_frag6_sysctl_table), + GFP_KERNEL); + if (table == NULL) + goto err_alloc; + } + + nf_frag = nf_frag_pernet(net); + + table[0].data = &nf_frag->fqdir->timeout; + table[1].data = &nf_frag->fqdir->low_thresh; + table[1].extra2 = &nf_frag->fqdir->high_thresh; + table[2].data = &nf_frag->fqdir->high_thresh; + table[2].extra1 = &nf_frag->fqdir->low_thresh; + + hdr = register_net_sysctl(net, "net/netfilter", table); + if (hdr == NULL) + goto err_reg; + + nf_frag->nf_frag_frags_hdr = hdr; + return 0; + +err_reg: + if (!net_eq(net, &init_net)) + kfree(table); +err_alloc: + return -ENOMEM; +} + +static void __net_exit nf_ct_frags6_sysctl_unregister(struct net *net) +{ + struct nft_ct_frag6_pernet *nf_frag = nf_frag_pernet(net); + struct ctl_table *table; + + table = nf_frag->nf_frag_frags_hdr->ctl_table_arg; + unregister_net_sysctl_table(nf_frag->nf_frag_frags_hdr); + if (!net_eq(net, &init_net)) + kfree(table); +} + +#else +static int nf_ct_frag6_sysctl_register(struct net *net) +{ + return 0; +} +static void __net_exit nf_ct_frags6_sysctl_unregister(struct net *net) +{ +} +#endif + +static int nf_ct_frag6_reasm(struct frag_queue *fq, struct sk_buff *skb, + struct sk_buff *prev_tail, struct net_device *dev); + +static inline u8 ip6_frag_ecn(const struct ipv6hdr *ipv6h) +{ + return 1 << (ipv6_get_dsfield(ipv6h) & INET_ECN_MASK); +} + +static void nf_ct_frag6_expire(struct timer_list *t) +{ + struct inet_frag_queue *frag = from_timer(frag, t, timer); + struct frag_queue *fq; + + fq = container_of(frag, struct frag_queue, q); + + ip6frag_expire_frag_queue(fq->q.fqdir->net, fq); +} + +/* Creation primitives. */ +static struct frag_queue *fq_find(struct net *net, __be32 id, u32 user, + const struct ipv6hdr *hdr, int iif) +{ + struct nft_ct_frag6_pernet *nf_frag = nf_frag_pernet(net); + struct frag_v6_compare_key key = { + .id = id, + .saddr = hdr->saddr, + .daddr = hdr->daddr, + .user = user, + .iif = iif, + }; + struct inet_frag_queue *q; + + q = inet_frag_find(nf_frag->fqdir, &key); + if (!q) + return NULL; + + return container_of(q, struct frag_queue, q); +} + + +static int nf_ct_frag6_queue(struct frag_queue *fq, struct sk_buff *skb, + const struct frag_hdr *fhdr, int nhoff) +{ + unsigned int payload_len; + struct net_device *dev; + struct sk_buff *prev; + int offset, end, err; + u8 ecn; + + if (fq->q.flags & INET_FRAG_COMPLETE) { + pr_debug("Already completed\n"); + goto err; + } + + payload_len = ntohs(ipv6_hdr(skb)->payload_len); + + offset = ntohs(fhdr->frag_off) & ~0x7; + end = offset + (payload_len - + ((u8 *)(fhdr + 1) - (u8 *)(ipv6_hdr(skb) + 1))); + + if ((unsigned int)end > IPV6_MAXPLEN) { + pr_debug("offset is too large.\n"); + return -EINVAL; + } + + ecn = ip6_frag_ecn(ipv6_hdr(skb)); + + if (skb->ip_summed == CHECKSUM_COMPLETE) { + const unsigned char *nh = skb_network_header(skb); + skb->csum = csum_sub(skb->csum, + csum_partial(nh, (u8 *)(fhdr + 1) - nh, + 0)); + } + + /* Is this the final fragment? */ + if (!(fhdr->frag_off & htons(IP6_MF))) { + /* If we already have some bits beyond end + * or have different end, the segment is corrupted. + */ + if (end < fq->q.len || + ((fq->q.flags & INET_FRAG_LAST_IN) && end != fq->q.len)) { + pr_debug("already received last fragment\n"); + goto err; + } + fq->q.flags |= INET_FRAG_LAST_IN; + fq->q.len = end; + } else { + /* Check if the fragment is rounded to 8 bytes. + * Required by the RFC. + */ + if (end & 0x7) { + /* RFC2460 says always send parameter problem in + * this case. -DaveM + */ + pr_debug("end of fragment not rounded to 8 bytes.\n"); + inet_frag_kill(&fq->q); + return -EPROTO; + } + if (end > fq->q.len) { + /* Some bits beyond end -> corruption. */ + if (fq->q.flags & INET_FRAG_LAST_IN) { + pr_debug("last packet already reached.\n"); + goto err; + } + fq->q.len = end; + } + } + + if (end == offset) + goto err; + + /* Point into the IP datagram 'data' part. */ + if (!pskb_pull(skb, (u8 *) (fhdr + 1) - skb->data)) { + pr_debug("queue: message is too short.\n"); + goto err; + } + if (pskb_trim_rcsum(skb, end - offset)) { + pr_debug("Can't trim\n"); + goto err; + } + + /* Note : skb->rbnode and skb->dev share the same location. */ + dev = skb->dev; + /* Makes sure compiler wont do silly aliasing games */ + barrier(); + + prev = fq->q.fragments_tail; + err = inet_frag_queue_insert(&fq->q, skb, offset, end); + if (err) { + if (err == IPFRAG_DUP) { + /* No error for duplicates, pretend they got queued. */ + kfree_skb(skb); + return -EINPROGRESS; + } + goto insert_error; + } + + if (dev) + fq->iif = dev->ifindex; + + fq->q.stamp = skb->tstamp; + fq->q.mono_delivery_time = skb->mono_delivery_time; + fq->q.meat += skb->len; + fq->ecn |= ecn; + if (payload_len > fq->q.max_size) + fq->q.max_size = payload_len; + add_frag_mem_limit(fq->q.fqdir, skb->truesize); + + /* The first fragment. + * nhoffset is obtained from the first fragment, of course. + */ + if (offset == 0) { + fq->nhoffset = nhoff; + fq->q.flags |= INET_FRAG_FIRST_IN; + } + + if (fq->q.flags == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) && + fq->q.meat == fq->q.len) { + unsigned long orefdst = skb->_skb_refdst; + + skb->_skb_refdst = 0UL; + err = nf_ct_frag6_reasm(fq, skb, prev, dev); + skb->_skb_refdst = orefdst; + + /* After queue has assumed skb ownership, only 0 or + * -EINPROGRESS must be returned. + */ + return err ? -EINPROGRESS : 0; + } + + skb_dst_drop(skb); + return -EINPROGRESS; + +insert_error: + inet_frag_kill(&fq->q); +err: + skb_dst_drop(skb); + return -EINVAL; +} + +/* + * Check if this packet is complete. + * + * It is called with locked fq, and caller must check that + * queue is eligible for reassembly i.e. it is not COMPLETE, + * the last and the first frames arrived and all the bits are here. + */ +static int nf_ct_frag6_reasm(struct frag_queue *fq, struct sk_buff *skb, + struct sk_buff *prev_tail, struct net_device *dev) +{ + void *reasm_data; + int payload_len; + u8 ecn; + + inet_frag_kill(&fq->q); + + ecn = ip_frag_ecn_table[fq->ecn]; + if (unlikely(ecn == 0xff)) + goto err; + + reasm_data = inet_frag_reasm_prepare(&fq->q, skb, prev_tail); + if (!reasm_data) + goto err; + + payload_len = ((skb->data - skb_network_header(skb)) - + sizeof(struct ipv6hdr) + fq->q.len - + sizeof(struct frag_hdr)); + if (payload_len > IPV6_MAXPLEN) { + net_dbg_ratelimited("nf_ct_frag6_reasm: payload len = %d\n", + payload_len); + goto err; + } + + /* We have to remove fragment header from datagram and to relocate + * header in order to calculate ICV correctly. */ + skb_network_header(skb)[fq->nhoffset] = skb_transport_header(skb)[0]; + memmove(skb->head + sizeof(struct frag_hdr), skb->head, + (skb->data - skb->head) - sizeof(struct frag_hdr)); + skb->mac_header += sizeof(struct frag_hdr); + skb->network_header += sizeof(struct frag_hdr); + + skb_reset_transport_header(skb); + + inet_frag_reasm_finish(&fq->q, skb, reasm_data, false); + + skb->ignore_df = 1; + skb->dev = dev; + ipv6_hdr(skb)->payload_len = htons(payload_len); + ipv6_change_dsfield(ipv6_hdr(skb), 0xff, ecn); + IP6CB(skb)->frag_max_size = sizeof(struct ipv6hdr) + fq->q.max_size; + IP6CB(skb)->flags |= IP6SKB_FRAGMENTED; + + /* Yes, and fold redundant checksum back. 8) */ + if (skb->ip_summed == CHECKSUM_COMPLETE) + skb->csum = csum_partial(skb_network_header(skb), + skb_network_header_len(skb), + skb->csum); + + fq->q.rb_fragments = RB_ROOT; + fq->q.fragments_tail = NULL; + fq->q.last_run_head = NULL; + + return 0; + +err: + inet_frag_kill(&fq->q); + return -EINVAL; +} + +/* + * find the header just before Fragment Header. + * + * if success return 0 and set ... + * (*prevhdrp): the value of "Next Header Field" in the header + * just before Fragment Header. + * (*prevhoff): the offset of "Next Header Field" in the header + * just before Fragment Header. + * (*fhoff) : the offset of Fragment Header. + * + * Based on ipv6_skip_hdr() in net/ipv6/exthdr.c + * + */ +static int +find_prev_fhdr(struct sk_buff *skb, u8 *prevhdrp, int *prevhoff, int *fhoff) +{ + u8 nexthdr = ipv6_hdr(skb)->nexthdr; + const int netoff = skb_network_offset(skb); + u8 prev_nhoff = netoff + offsetof(struct ipv6hdr, nexthdr); + int start = netoff + sizeof(struct ipv6hdr); + int len = skb->len - start; + u8 prevhdr = NEXTHDR_IPV6; + + while (nexthdr != NEXTHDR_FRAGMENT) { + struct ipv6_opt_hdr hdr; + int hdrlen; + + if (!ipv6_ext_hdr(nexthdr)) { + return -1; + } + if (nexthdr == NEXTHDR_NONE) { + pr_debug("next header is none\n"); + return -1; + } + if (len < (int)sizeof(struct ipv6_opt_hdr)) { + pr_debug("too short\n"); + return -1; + } + if (skb_copy_bits(skb, start, &hdr, sizeof(hdr))) + BUG(); + if (nexthdr == NEXTHDR_AUTH) + hdrlen = ipv6_authlen(&hdr); + else + hdrlen = ipv6_optlen(&hdr); + + prevhdr = nexthdr; + prev_nhoff = start; + + nexthdr = hdr.nexthdr; + len -= hdrlen; + start += hdrlen; + } + + if (len < 0) + return -1; + + *prevhdrp = prevhdr; + *prevhoff = prev_nhoff; + *fhoff = start; + + return 0; +} + +int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user) +{ + u16 savethdr = skb->transport_header; + u8 nexthdr = NEXTHDR_FRAGMENT; + int fhoff, nhoff, ret; + struct frag_hdr *fhdr; + struct frag_queue *fq; + struct ipv6hdr *hdr; + u8 prevhdr; + + /* Jumbo payload inhibits frag. header */ + if (ipv6_hdr(skb)->payload_len == 0) { + pr_debug("payload len = 0\n"); + return 0; + } + + if (find_prev_fhdr(skb, &prevhdr, &nhoff, &fhoff) < 0) + return 0; + + /* Discard the first fragment if it does not include all headers + * RFC 8200, Section 4.5 + */ + if (ipv6frag_thdr_truncated(skb, fhoff, &nexthdr)) { + pr_debug("Drop incomplete fragment\n"); + return 0; + } + + if (!pskb_may_pull(skb, fhoff + sizeof(*fhdr))) + return -ENOMEM; + + skb_set_transport_header(skb, fhoff); + hdr = ipv6_hdr(skb); + fhdr = (struct frag_hdr *)skb_transport_header(skb); + + skb_orphan(skb); + fq = fq_find(net, fhdr->identification, user, hdr, + skb->dev ? skb->dev->ifindex : 0); + if (fq == NULL) { + pr_debug("Can't find and can't create new queue\n"); + return -ENOMEM; + } + + spin_lock_bh(&fq->q.lock); + + ret = nf_ct_frag6_queue(fq, skb, fhdr, nhoff); + if (ret == -EPROTO) { + skb->transport_header = savethdr; + ret = 0; + } + + spin_unlock_bh(&fq->q.lock); + inet_frag_put(&fq->q); + return ret; +} +EXPORT_SYMBOL_GPL(nf_ct_frag6_gather); + +static int nf_ct_net_init(struct net *net) +{ + struct nft_ct_frag6_pernet *nf_frag = nf_frag_pernet(net); + int res; + + res = fqdir_init(&nf_frag->fqdir, &nf_frags, net); + if (res < 0) + return res; + + nf_frag->fqdir->high_thresh = IPV6_FRAG_HIGH_THRESH; + nf_frag->fqdir->low_thresh = IPV6_FRAG_LOW_THRESH; + nf_frag->fqdir->timeout = IPV6_FRAG_TIMEOUT; + + res = nf_ct_frag6_sysctl_register(net); + if (res < 0) + fqdir_exit(nf_frag->fqdir); + return res; +} + +static void nf_ct_net_pre_exit(struct net *net) +{ + struct nft_ct_frag6_pernet *nf_frag = nf_frag_pernet(net); + + fqdir_pre_exit(nf_frag->fqdir); +} + +static void nf_ct_net_exit(struct net *net) +{ + struct nft_ct_frag6_pernet *nf_frag = nf_frag_pernet(net); + + nf_ct_frags6_sysctl_unregister(net); + fqdir_exit(nf_frag->fqdir); +} + +static struct pernet_operations nf_ct_net_ops = { + .init = nf_ct_net_init, + .pre_exit = nf_ct_net_pre_exit, + .exit = nf_ct_net_exit, + .id = &nf_frag_pernet_id, + .size = sizeof(struct nft_ct_frag6_pernet), +}; + +static const struct rhashtable_params nfct_rhash_params = { + .head_offset = offsetof(struct inet_frag_queue, node), + .hashfn = ip6frag_key_hashfn, + .obj_hashfn = ip6frag_obj_hashfn, + .obj_cmpfn = ip6frag_obj_cmpfn, + .automatic_shrinking = true, +}; + +int nf_ct_frag6_init(void) +{ + int ret = 0; + + nf_frags.constructor = ip6frag_init; + nf_frags.destructor = NULL; + nf_frags.qsize = sizeof(struct frag_queue); + nf_frags.frag_expire = nf_ct_frag6_expire; + nf_frags.frags_cache_name = nf_frags_cache_name; + nf_frags.rhash_params = nfct_rhash_params; + ret = inet_frags_init(&nf_frags); + if (ret) + goto out; + ret = register_pernet_subsys(&nf_ct_net_ops); + if (ret) + inet_frags_fini(&nf_frags); + +out: + return ret; +} + +void nf_ct_frag6_cleanup(void) +{ + unregister_pernet_subsys(&nf_ct_net_ops); + inet_frags_fini(&nf_frags); +} diff --git a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c new file mode 100644 index 000000000..cb4eb1d2c --- /dev/null +++ b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c @@ -0,0 +1,173 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* (C) 1999-2001 Paul `Rusty' Russell + * (C) 2002-2004 Netfilter Core Team <coreteam@netfilter.org> + */ + +#include <linux/types.h> +#include <linux/ipv6.h> +#include <linux/in6.h> +#include <linux/netfilter.h> +#include <linux/module.h> +#include <linux/skbuff.h> +#include <linux/icmp.h> +#include <linux/sysctl.h> +#include <net/ipv6_frag.h> + +#include <linux/netfilter_ipv6.h> +#include <linux/netfilter_bridge.h> +#if IS_ENABLED(CONFIG_NF_CONNTRACK) +#include <net/netfilter/nf_conntrack.h> +#include <net/netfilter/nf_conntrack_helper.h> +#include <net/netfilter/nf_conntrack_l4proto.h> +#include <net/netfilter/nf_conntrack_core.h> +#include <net/netfilter/ipv6/nf_conntrack_ipv6.h> +#endif +#include <net/netfilter/nf_conntrack_zones.h> +#include <net/netfilter/ipv6/nf_defrag_ipv6.h> + +static DEFINE_MUTEX(defrag6_mutex); + +static enum ip6_defrag_users nf_ct6_defrag_user(unsigned int hooknum, + struct sk_buff *skb) +{ + u16 zone_id = NF_CT_DEFAULT_ZONE_ID; +#if IS_ENABLED(CONFIG_NF_CONNTRACK) + if (skb_nfct(skb)) { + enum ip_conntrack_info ctinfo; + const struct nf_conn *ct = nf_ct_get(skb, &ctinfo); + + zone_id = nf_ct_zone_id(nf_ct_zone(ct), CTINFO2DIR(ctinfo)); + } +#endif + if (nf_bridge_in_prerouting(skb)) + return IP6_DEFRAG_CONNTRACK_BRIDGE_IN + zone_id; + + if (hooknum == NF_INET_PRE_ROUTING) + return IP6_DEFRAG_CONNTRACK_IN + zone_id; + else + return IP6_DEFRAG_CONNTRACK_OUT + zone_id; +} + +static unsigned int ipv6_defrag(void *priv, + struct sk_buff *skb, + const struct nf_hook_state *state) +{ + int err; + +#if IS_ENABLED(CONFIG_NF_CONNTRACK) + /* Previously seen (loopback)? */ + if (skb_nfct(skb) && !nf_ct_is_template((struct nf_conn *)skb_nfct(skb))) + return NF_ACCEPT; + + if (skb->_nfct == IP_CT_UNTRACKED) + return NF_ACCEPT; +#endif + + err = nf_ct_frag6_gather(state->net, skb, + nf_ct6_defrag_user(state->hook, skb)); + /* queued */ + if (err == -EINPROGRESS) + return NF_STOLEN; + + return err == 0 ? NF_ACCEPT : NF_DROP; +} + +static const struct nf_hook_ops ipv6_defrag_ops[] = { + { + .hook = ipv6_defrag, + .pf = NFPROTO_IPV6, + .hooknum = NF_INET_PRE_ROUTING, + .priority = NF_IP6_PRI_CONNTRACK_DEFRAG, + }, + { + .hook = ipv6_defrag, + .pf = NFPROTO_IPV6, + .hooknum = NF_INET_LOCAL_OUT, + .priority = NF_IP6_PRI_CONNTRACK_DEFRAG, + }, +}; + +static void __net_exit defrag6_net_exit(struct net *net) +{ + if (net->nf.defrag_ipv6_users) { + nf_unregister_net_hooks(net, ipv6_defrag_ops, + ARRAY_SIZE(ipv6_defrag_ops)); + net->nf.defrag_ipv6_users = 0; + } +} + +static struct pernet_operations defrag6_net_ops = { + .exit = defrag6_net_exit, +}; + +static int __init nf_defrag_init(void) +{ + int ret = 0; + + ret = nf_ct_frag6_init(); + if (ret < 0) { + pr_err("nf_defrag_ipv6: can't initialize frag6.\n"); + return ret; + } + ret = register_pernet_subsys(&defrag6_net_ops); + if (ret < 0) { + pr_err("nf_defrag_ipv6: can't register pernet ops\n"); + goto cleanup_frag6; + } + return ret; + +cleanup_frag6: + nf_ct_frag6_cleanup(); + return ret; + +} + +static void __exit nf_defrag_fini(void) +{ + unregister_pernet_subsys(&defrag6_net_ops); + nf_ct_frag6_cleanup(); +} + +int nf_defrag_ipv6_enable(struct net *net) +{ + int err = 0; + + mutex_lock(&defrag6_mutex); + if (net->nf.defrag_ipv6_users == UINT_MAX) { + err = -EOVERFLOW; + goto out_unlock; + } + + if (net->nf.defrag_ipv6_users) { + net->nf.defrag_ipv6_users++; + goto out_unlock; + } + + err = nf_register_net_hooks(net, ipv6_defrag_ops, + ARRAY_SIZE(ipv6_defrag_ops)); + if (err == 0) + net->nf.defrag_ipv6_users = 1; + + out_unlock: + mutex_unlock(&defrag6_mutex); + return err; +} +EXPORT_SYMBOL_GPL(nf_defrag_ipv6_enable); + +void nf_defrag_ipv6_disable(struct net *net) +{ + mutex_lock(&defrag6_mutex); + if (net->nf.defrag_ipv6_users) { + net->nf.defrag_ipv6_users--; + if (net->nf.defrag_ipv6_users == 0) + nf_unregister_net_hooks(net, ipv6_defrag_ops, + ARRAY_SIZE(ipv6_defrag_ops)); + } + mutex_unlock(&defrag6_mutex); +} +EXPORT_SYMBOL_GPL(nf_defrag_ipv6_disable); + +module_init(nf_defrag_init); +module_exit(nf_defrag_fini); + +MODULE_LICENSE("GPL"); diff --git a/net/ipv6/netfilter/nf_dup_ipv6.c b/net/ipv6/netfilter/nf_dup_ipv6.c new file mode 100644 index 000000000..a0a2de30b --- /dev/null +++ b/net/ipv6/netfilter/nf_dup_ipv6.c @@ -0,0 +1,78 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * (C) 2007 by Sebastian Claßen <sebastian.classen@freenet.ag> + * (C) 2007-2010 by Jan Engelhardt <jengelh@medozas.de> + * + * Extracted from xt_TEE.c + */ +#include <linux/module.h> +#include <linux/percpu.h> +#include <linux/skbuff.h> +#include <linux/netfilter.h> +#include <net/ipv6.h> +#include <net/ip6_route.h> +#include <net/netfilter/ipv6/nf_dup_ipv6.h> +#if IS_ENABLED(CONFIG_NF_CONNTRACK) +#include <net/netfilter/nf_conntrack.h> +#endif + +static bool nf_dup_ipv6_route(struct net *net, struct sk_buff *skb, + const struct in6_addr *gw, int oif) +{ + const struct ipv6hdr *iph = ipv6_hdr(skb); + struct dst_entry *dst; + struct flowi6 fl6; + + memset(&fl6, 0, sizeof(fl6)); + if (oif != -1) + fl6.flowi6_oif = oif; + + fl6.daddr = *gw; + fl6.flowlabel = (__force __be32)(((iph->flow_lbl[0] & 0xF) << 16) | + (iph->flow_lbl[1] << 8) | iph->flow_lbl[2]); + fl6.flowi6_flags = FLOWI_FLAG_KNOWN_NH; + dst = ip6_route_output(net, NULL, &fl6); + if (dst->error) { + dst_release(dst); + return false; + } + skb_dst_drop(skb); + skb_dst_set(skb, dst); + skb->dev = dst->dev; + skb->protocol = htons(ETH_P_IPV6); + + return true; +} + +void nf_dup_ipv6(struct net *net, struct sk_buff *skb, unsigned int hooknum, + const struct in6_addr *gw, int oif) +{ + if (this_cpu_read(nf_skb_duplicated)) + return; + skb = pskb_copy(skb, GFP_ATOMIC); + if (skb == NULL) + return; + +#if IS_ENABLED(CONFIG_NF_CONNTRACK) + nf_reset_ct(skb); + nf_ct_set(skb, NULL, IP_CT_UNTRACKED); +#endif + if (hooknum == NF_INET_PRE_ROUTING || + hooknum == NF_INET_LOCAL_IN) { + struct ipv6hdr *iph = ipv6_hdr(skb); + --iph->hop_limit; + } + if (nf_dup_ipv6_route(net, skb, gw, oif)) { + __this_cpu_write(nf_skb_duplicated, true); + ip6_local_out(net, skb->sk, skb); + __this_cpu_write(nf_skb_duplicated, false); + } else { + kfree_skb(skb); + } +} +EXPORT_SYMBOL_GPL(nf_dup_ipv6); + +MODULE_AUTHOR("Sebastian Claßen <sebastian.classen@freenet.ag>"); +MODULE_AUTHOR("Jan Engelhardt <jengelh@medozas.de>"); +MODULE_DESCRIPTION("nf_dup_ipv6: IPv6 packet duplication"); +MODULE_LICENSE("GPL"); diff --git a/net/ipv6/netfilter/nf_reject_ipv6.c b/net/ipv6/netfilter/nf_reject_ipv6.c new file mode 100644 index 000000000..433d98bbe --- /dev/null +++ b/net/ipv6/netfilter/nf_reject_ipv6.c @@ -0,0 +1,419 @@ +// 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 <net/ipv6.h> +#include <net/ip6_route.h> +#include <net/ip6_fib.h> +#include <net/ip6_checksum.h> +#include <net/netfilter/ipv6/nf_reject.h> +#include <linux/netfilter_ipv6.h> +#include <linux/netfilter_bridge.h> + +static bool nf_reject_v6_csum_ok(struct sk_buff *skb, int hook) +{ + const struct ipv6hdr *ip6h = ipv6_hdr(skb); + int thoff; + __be16 fo; + u8 proto = ip6h->nexthdr; + + if (skb_csum_unnecessary(skb)) + return true; + + if (ip6h->payload_len && + pskb_trim_rcsum(skb, ntohs(ip6h->payload_len) + sizeof(*ip6h))) + return false; + + ip6h = ipv6_hdr(skb); + thoff = ipv6_skip_exthdr(skb, ((u8*)(ip6h+1) - skb->data), &proto, &fo); + if (thoff < 0 || thoff >= skb->len || (fo & htons(~0x7)) != 0) + return false; + + if (!nf_reject_verify_csum(skb, thoff, proto)) + return true; + + return nf_ip6_checksum(skb, hook, thoff, proto) == 0; +} + +static int nf_reject_ip6hdr_validate(struct sk_buff *skb) +{ + struct ipv6hdr *hdr; + u32 pkt_len; + + if (!pskb_may_pull(skb, sizeof(struct ipv6hdr))) + return 0; + + hdr = ipv6_hdr(skb); + if (hdr->version != 6) + return 0; + + pkt_len = ntohs(hdr->payload_len); + if (pkt_len + sizeof(struct ipv6hdr) > skb->len) + return 0; + + return 1; +} + +struct sk_buff *nf_reject_skb_v6_tcp_reset(struct net *net, + struct sk_buff *oldskb, + const struct net_device *dev, + int hook) +{ + struct sk_buff *nskb; + const struct tcphdr *oth; + struct tcphdr _oth; + unsigned int otcplen; + struct ipv6hdr *nip6h; + + if (!nf_reject_ip6hdr_validate(oldskb)) + return NULL; + + oth = nf_reject_ip6_tcphdr_get(oldskb, &_oth, &otcplen, hook); + if (!oth) + return NULL; + + nskb = alloc_skb(sizeof(struct ipv6hdr) + sizeof(struct tcphdr) + + LL_MAX_HEADER, GFP_ATOMIC); + if (!nskb) + return NULL; + + nskb->dev = (struct net_device *)dev; + + skb_reserve(nskb, LL_MAX_HEADER); + nip6h = nf_reject_ip6hdr_put(nskb, oldskb, IPPROTO_TCP, + net->ipv6.devconf_all->hop_limit); + nf_reject_ip6_tcphdr_put(nskb, oldskb, oth, otcplen); + nip6h->payload_len = htons(nskb->len - sizeof(struct ipv6hdr)); + + return nskb; +} +EXPORT_SYMBOL_GPL(nf_reject_skb_v6_tcp_reset); + +struct sk_buff *nf_reject_skb_v6_unreach(struct net *net, + struct sk_buff *oldskb, + const struct net_device *dev, + int hook, u8 code) +{ + struct sk_buff *nskb; + struct ipv6hdr *nip6h; + struct icmp6hdr *icmp6h; + unsigned int len; + + if (!nf_reject_ip6hdr_validate(oldskb)) + return NULL; + + /* Include "As much of invoking packet as possible without the ICMPv6 + * packet exceeding the minimum IPv6 MTU" in the ICMP payload. + */ + len = min_t(unsigned int, 1220, oldskb->len); + + if (!pskb_may_pull(oldskb, len)) + return NULL; + + if (!nf_reject_v6_csum_ok(oldskb, hook)) + return NULL; + + nskb = alloc_skb(sizeof(struct ipv6hdr) + sizeof(struct icmp6hdr) + + LL_MAX_HEADER + len, GFP_ATOMIC); + if (!nskb) + return NULL; + + nskb->dev = (struct net_device *)dev; + + skb_reserve(nskb, LL_MAX_HEADER); + nip6h = nf_reject_ip6hdr_put(nskb, oldskb, IPPROTO_ICMPV6, + net->ipv6.devconf_all->hop_limit); + + skb_reset_transport_header(nskb); + icmp6h = skb_put_zero(nskb, sizeof(struct icmp6hdr)); + icmp6h->icmp6_type = ICMPV6_DEST_UNREACH; + icmp6h->icmp6_code = code; + + skb_put_data(nskb, skb_network_header(oldskb), len); + nip6h->payload_len = htons(nskb->len - sizeof(struct ipv6hdr)); + + icmp6h->icmp6_cksum = + csum_ipv6_magic(&nip6h->saddr, &nip6h->daddr, + nskb->len - sizeof(struct ipv6hdr), + IPPROTO_ICMPV6, + csum_partial(icmp6h, + nskb->len - sizeof(struct ipv6hdr), + 0)); + + return nskb; +} +EXPORT_SYMBOL_GPL(nf_reject_skb_v6_unreach); + +const struct tcphdr *nf_reject_ip6_tcphdr_get(struct sk_buff *oldskb, + struct tcphdr *otcph, + unsigned int *otcplen, int hook) +{ + const struct ipv6hdr *oip6h = ipv6_hdr(oldskb); + u8 proto; + __be16 frag_off; + int tcphoff; + + proto = oip6h->nexthdr; + tcphoff = ipv6_skip_exthdr(oldskb, ((u8 *)(oip6h + 1) - oldskb->data), + &proto, &frag_off); + + if ((tcphoff < 0) || (tcphoff > oldskb->len)) { + pr_debug("Cannot get TCP header.\n"); + return NULL; + } + + *otcplen = oldskb->len - tcphoff; + + /* IP header checks: fragment, too short. */ + if (proto != IPPROTO_TCP || *otcplen < sizeof(struct tcphdr)) { + pr_debug("proto(%d) != IPPROTO_TCP or too short (len = %d)\n", + proto, *otcplen); + return NULL; + } + + otcph = skb_header_pointer(oldskb, tcphoff, sizeof(struct tcphdr), + otcph); + if (otcph == NULL) + return NULL; + + /* No RST for RST. */ + if (otcph->rst) { + pr_debug("RST is set\n"); + return NULL; + } + + /* Check checksum. */ + if (nf_ip6_checksum(oldskb, hook, tcphoff, IPPROTO_TCP)) { + pr_debug("TCP checksum is invalid\n"); + return NULL; + } + + return otcph; +} +EXPORT_SYMBOL_GPL(nf_reject_ip6_tcphdr_get); + +struct ipv6hdr *nf_reject_ip6hdr_put(struct sk_buff *nskb, + const struct sk_buff *oldskb, + __u8 protocol, int hoplimit) +{ + struct ipv6hdr *ip6h; + const struct ipv6hdr *oip6h = ipv6_hdr(oldskb); +#define DEFAULT_TOS_VALUE 0x0U + const __u8 tclass = DEFAULT_TOS_VALUE; + + skb_put(nskb, sizeof(struct ipv6hdr)); + skb_reset_network_header(nskb); + ip6h = ipv6_hdr(nskb); + ip6_flow_hdr(ip6h, tclass, 0); + ip6h->hop_limit = hoplimit; + ip6h->nexthdr = protocol; + ip6h->saddr = oip6h->daddr; + ip6h->daddr = oip6h->saddr; + + nskb->protocol = htons(ETH_P_IPV6); + + return ip6h; +} +EXPORT_SYMBOL_GPL(nf_reject_ip6hdr_put); + +void nf_reject_ip6_tcphdr_put(struct sk_buff *nskb, + const struct sk_buff *oldskb, + const struct tcphdr *oth, unsigned int otcplen) +{ + struct tcphdr *tcph; + int needs_ack; + + skb_reset_transport_header(nskb); + tcph = skb_put(nskb, sizeof(struct tcphdr)); + /* Truncate to length (no data) */ + tcph->doff = sizeof(struct tcphdr)/4; + tcph->source = oth->dest; + tcph->dest = oth->source; + + if (oth->ack) { + needs_ack = 0; + tcph->seq = oth->ack_seq; + tcph->ack_seq = 0; + } else { + needs_ack = 1; + tcph->ack_seq = htonl(ntohl(oth->seq) + oth->syn + oth->fin + + otcplen - (oth->doff<<2)); + tcph->seq = 0; + } + + /* Reset flags */ + ((u_int8_t *)tcph)[13] = 0; + tcph->rst = 1; + tcph->ack = needs_ack; + tcph->window = 0; + tcph->urg_ptr = 0; + tcph->check = 0; + + /* Adjust TCP checksum */ + tcph->check = csum_ipv6_magic(&ipv6_hdr(nskb)->saddr, + &ipv6_hdr(nskb)->daddr, + sizeof(struct tcphdr), IPPROTO_TCP, + csum_partial(tcph, + sizeof(struct tcphdr), 0)); +} +EXPORT_SYMBOL_GPL(nf_reject_ip6_tcphdr_put); + +static int nf_reject6_fill_skb_dst(struct sk_buff *skb_in) +{ + struct dst_entry *dst = NULL; + struct flowi fl; + + memset(&fl, 0, sizeof(struct flowi)); + fl.u.ip6.daddr = ipv6_hdr(skb_in)->saddr; + nf_ip6_route(dev_net(skb_in->dev), &dst, &fl, false); + if (!dst) + return -1; + + skb_dst_set(skb_in, dst); + return 0; +} + +void nf_send_reset6(struct net *net, struct sock *sk, struct sk_buff *oldskb, + int hook) +{ + struct sk_buff *nskb; + struct tcphdr _otcph; + const struct tcphdr *otcph; + unsigned int otcplen, hh_len; + const struct ipv6hdr *oip6h = ipv6_hdr(oldskb); + struct ipv6hdr *ip6h; + struct dst_entry *dst = NULL; + struct flowi6 fl6; + + if ((!(ipv6_addr_type(&oip6h->saddr) & IPV6_ADDR_UNICAST)) || + (!(ipv6_addr_type(&oip6h->daddr) & IPV6_ADDR_UNICAST))) { + pr_debug("addr is not unicast.\n"); + return; + } + + otcph = nf_reject_ip6_tcphdr_get(oldskb, &_otcph, &otcplen, hook); + if (!otcph) + return; + + memset(&fl6, 0, sizeof(fl6)); + fl6.flowi6_proto = IPPROTO_TCP; + fl6.saddr = oip6h->daddr; + fl6.daddr = oip6h->saddr; + fl6.fl6_sport = otcph->dest; + fl6.fl6_dport = otcph->source; + + if (hook == NF_INET_PRE_ROUTING || hook == NF_INET_INGRESS) { + nf_ip6_route(net, &dst, flowi6_to_flowi(&fl6), false); + if (!dst) + return; + skb_dst_set(oldskb, dst); + } + + fl6.flowi6_oif = l3mdev_master_ifindex(skb_dst(oldskb)->dev); + fl6.flowi6_mark = IP6_REPLY_MARK(net, oldskb->mark); + security_skb_classify_flow(oldskb, flowi6_to_flowi_common(&fl6)); + dst = ip6_route_output(net, NULL, &fl6); + if (dst->error) { + dst_release(dst); + return; + } + dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), NULL, 0); + if (IS_ERR(dst)) + return; + + hh_len = (dst->dev->hard_header_len + 15)&~15; + nskb = alloc_skb(hh_len + 15 + dst->header_len + sizeof(struct ipv6hdr) + + sizeof(struct tcphdr) + dst->trailer_len, + GFP_ATOMIC); + + if (!nskb) { + net_dbg_ratelimited("cannot alloc skb\n"); + dst_release(dst); + return; + } + + skb_dst_set(nskb, dst); + + nskb->mark = fl6.flowi6_mark; + + skb_reserve(nskb, hh_len + dst->header_len); + ip6h = nf_reject_ip6hdr_put(nskb, oldskb, IPPROTO_TCP, + ip6_dst_hoplimit(dst)); + nf_reject_ip6_tcphdr_put(nskb, oldskb, otcph, otcplen); + + nf_ct_attach(nskb, oldskb); + +#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) + /* If we use ip6_local_out for bridged traffic, the MAC source on + * the RST will be ours, instead of the destination's. This confuses + * some routers/firewalls, and they drop the packet. So we need to + * build the eth header using the original destination's MAC as the + * source, and send the RST packet directly. + */ + if (nf_bridge_info_exists(oldskb)) { + struct ethhdr *oeth = eth_hdr(oldskb); + struct net_device *br_indev; + + br_indev = nf_bridge_get_physindev(oldskb, net); + if (!br_indev) { + kfree_skb(nskb); + return; + } + + nskb->dev = br_indev; + nskb->protocol = htons(ETH_P_IPV6); + ip6h->payload_len = htons(sizeof(struct tcphdr)); + if (dev_hard_header(nskb, nskb->dev, ntohs(nskb->protocol), + oeth->h_source, oeth->h_dest, nskb->len) < 0) { + kfree_skb(nskb); + return; + } + dev_queue_xmit(nskb); + } else +#endif + ip6_local_out(net, sk, nskb); +} +EXPORT_SYMBOL_GPL(nf_send_reset6); + +static bool reject6_csum_ok(struct sk_buff *skb, int hook) +{ + const struct ipv6hdr *ip6h = ipv6_hdr(skb); + int thoff; + __be16 fo; + u8 proto; + + if (skb_csum_unnecessary(skb)) + return true; + + proto = ip6h->nexthdr; + thoff = ipv6_skip_exthdr(skb, ((u8 *)(ip6h + 1) - skb->data), &proto, &fo); + + if (thoff < 0 || thoff >= skb->len || (fo & htons(~0x7)) != 0) + return false; + + if (!nf_reject_verify_csum(skb, thoff, proto)) + return true; + + return nf_ip6_checksum(skb, hook, thoff, proto) == 0; +} + +void nf_send_unreach6(struct net *net, struct sk_buff *skb_in, + unsigned char code, unsigned int hooknum) +{ + if (!reject6_csum_ok(skb_in, hooknum)) + return; + + if (hooknum == NF_INET_LOCAL_OUT && skb_in->dev == NULL) + skb_in->dev = net->loopback_dev; + + if ((hooknum == NF_INET_PRE_ROUTING || hooknum == NF_INET_INGRESS) && + nf_reject6_fill_skb_dst(skb_in) < 0) + return; + + icmpv6_send(skb_in, ICMPV6_DEST_UNREACH, code, 0); +} +EXPORT_SYMBOL_GPL(nf_send_unreach6); + +MODULE_LICENSE("GPL"); diff --git a/net/ipv6/netfilter/nf_socket_ipv6.c b/net/ipv6/netfilter/nf_socket_ipv6.c new file mode 100644 index 000000000..a7690ec62 --- /dev/null +++ b/net/ipv6/netfilter/nf_socket_ipv6.c @@ -0,0 +1,146 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2007-2008 BalaBit IT Ltd. + * Author: Krisztian Kovacs + */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include <linux/module.h> +#include <linux/skbuff.h> +#include <net/tcp.h> +#include <net/udp.h> +#include <net/icmp.h> +#include <net/sock.h> +#include <net/inet_sock.h> +#include <net/inet6_hashtables.h> +#include <net/netfilter/nf_socket.h> +#if IS_ENABLED(CONFIG_NF_CONNTRACK) +#include <net/netfilter/nf_conntrack.h> +#endif + +static int +extract_icmp6_fields(const struct sk_buff *skb, + unsigned int outside_hdrlen, + int *protocol, + const struct in6_addr **raddr, + const struct in6_addr **laddr, + __be16 *rport, + __be16 *lport, + struct ipv6hdr *ipv6_var) +{ + const struct ipv6hdr *inside_iph; + struct icmp6hdr *icmph, _icmph; + __be16 *ports, _ports[2]; + u8 inside_nexthdr; + __be16 inside_fragoff; + int inside_hdrlen; + + icmph = skb_header_pointer(skb, outside_hdrlen, + sizeof(_icmph), &_icmph); + if (icmph == NULL) + return 1; + + if (icmph->icmp6_type & ICMPV6_INFOMSG_MASK) + return 1; + + inside_iph = skb_header_pointer(skb, outside_hdrlen + sizeof(_icmph), + sizeof(*ipv6_var), ipv6_var); + if (inside_iph == NULL) + return 1; + inside_nexthdr = inside_iph->nexthdr; + + inside_hdrlen = ipv6_skip_exthdr(skb, outside_hdrlen + sizeof(_icmph) + + sizeof(*ipv6_var), + &inside_nexthdr, &inside_fragoff); + if (inside_hdrlen < 0) + return 1; /* hjm: Packet has no/incomplete transport layer headers. */ + + if (inside_nexthdr != IPPROTO_TCP && + inside_nexthdr != IPPROTO_UDP) + return 1; + + ports = skb_header_pointer(skb, inside_hdrlen, + sizeof(_ports), &_ports); + if (ports == NULL) + return 1; + + /* the inside IP packet is the one quoted from our side, thus + * its saddr is the local address */ + *protocol = inside_nexthdr; + *laddr = &inside_iph->saddr; + *lport = ports[0]; + *raddr = &inside_iph->daddr; + *rport = ports[1]; + + return 0; +} + +static struct sock * +nf_socket_get_sock_v6(struct net *net, struct sk_buff *skb, int doff, + const u8 protocol, + const struct in6_addr *saddr, const struct in6_addr *daddr, + const __be16 sport, const __be16 dport, + const struct net_device *in) +{ + switch (protocol) { + case IPPROTO_TCP: + return inet6_lookup(net, net->ipv4.tcp_death_row.hashinfo, + skb, doff, saddr, sport, daddr, dport, + in->ifindex); + case IPPROTO_UDP: + return udp6_lib_lookup(net, saddr, sport, daddr, dport, + in->ifindex); + } + + return NULL; +} + +struct sock *nf_sk_lookup_slow_v6(struct net *net, const struct sk_buff *skb, + const struct net_device *indev) +{ + __be16 dport, sport; + const struct in6_addr *daddr = NULL, *saddr = NULL; + struct ipv6hdr *iph = ipv6_hdr(skb), ipv6_var; + struct sk_buff *data_skb = NULL; + int doff = 0; + int thoff = 0, tproto; + + tproto = ipv6_find_hdr(skb, &thoff, -1, NULL, NULL); + if (tproto < 0) { + pr_debug("unable to find transport header in IPv6 packet, dropping\n"); + return NULL; + } + + if (tproto == IPPROTO_UDP || tproto == IPPROTO_TCP) { + struct tcphdr _hdr; + struct udphdr *hp; + + hp = skb_header_pointer(skb, thoff, tproto == IPPROTO_UDP ? + sizeof(*hp) : sizeof(_hdr), &_hdr); + if (hp == NULL) + return NULL; + + saddr = &iph->saddr; + sport = hp->source; + daddr = &iph->daddr; + dport = hp->dest; + data_skb = (struct sk_buff *)skb; + doff = tproto == IPPROTO_TCP ? + thoff + __tcp_hdrlen((struct tcphdr *)hp) : + thoff + sizeof(*hp); + + } else if (tproto == IPPROTO_ICMPV6) { + if (extract_icmp6_fields(skb, thoff, &tproto, &saddr, &daddr, + &sport, &dport, &ipv6_var)) + return NULL; + } else { + return NULL; + } + + return nf_socket_get_sock_v6(net, data_skb, doff, tproto, saddr, daddr, + sport, dport, indev); +} +EXPORT_SYMBOL_GPL(nf_sk_lookup_slow_v6); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Krisztian Kovacs, Balazs Scheidler"); +MODULE_DESCRIPTION("Netfilter IPv6 socket lookup infrastructure"); diff --git a/net/ipv6/netfilter/nf_tproxy_ipv6.c b/net/ipv6/netfilter/nf_tproxy_ipv6.c new file mode 100644 index 000000000..52f828bb5 --- /dev/null +++ b/net/ipv6/netfilter/nf_tproxy_ipv6.c @@ -0,0 +1,153 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include <net/netfilter/nf_tproxy.h> +#include <linux/module.h> +#include <net/inet6_hashtables.h> +#include <net/addrconf.h> +#include <net/udp.h> +#include <net/tcp.h> + +const struct in6_addr * +nf_tproxy_laddr6(struct sk_buff *skb, const struct in6_addr *user_laddr, + const struct in6_addr *daddr) +{ + struct inet6_dev *indev; + struct inet6_ifaddr *ifa; + struct in6_addr *laddr; + + if (!ipv6_addr_any(user_laddr)) + return user_laddr; + laddr = NULL; + + indev = __in6_dev_get(skb->dev); + if (indev) { + read_lock_bh(&indev->lock); + list_for_each_entry(ifa, &indev->addr_list, if_list) { + if (ifa->flags & (IFA_F_TENTATIVE | IFA_F_DEPRECATED)) + continue; + + laddr = &ifa->addr; + break; + } + read_unlock_bh(&indev->lock); + } + + return laddr ? laddr : daddr; +} +EXPORT_SYMBOL_GPL(nf_tproxy_laddr6); + +struct sock * +nf_tproxy_handle_time_wait6(struct sk_buff *skb, int tproto, int thoff, + struct net *net, + const struct in6_addr *laddr, + const __be16 lport, + struct sock *sk) +{ + const struct ipv6hdr *iph = ipv6_hdr(skb); + struct tcphdr _hdr, *hp; + + hp = skb_header_pointer(skb, thoff, sizeof(_hdr), &_hdr); + if (hp == NULL) { + inet_twsk_put(inet_twsk(sk)); + return NULL; + } + + if (hp->syn && !hp->rst && !hp->ack && !hp->fin) { + /* SYN to a TIME_WAIT socket, we'd rather redirect it + * to a listener socket if there's one */ + struct sock *sk2; + + sk2 = nf_tproxy_get_sock_v6(net, skb, thoff, tproto, + &iph->saddr, + nf_tproxy_laddr6(skb, laddr, &iph->daddr), + hp->source, + lport ? lport : hp->dest, + skb->dev, NF_TPROXY_LOOKUP_LISTENER); + if (sk2) { + nf_tproxy_twsk_deschedule_put(inet_twsk(sk)); + sk = sk2; + } + } + + return sk; +} +EXPORT_SYMBOL_GPL(nf_tproxy_handle_time_wait6); + +struct sock * +nf_tproxy_get_sock_v6(struct net *net, struct sk_buff *skb, int thoff, + const u8 protocol, + const struct in6_addr *saddr, const struct in6_addr *daddr, + const __be16 sport, const __be16 dport, + const struct net_device *in, + const enum nf_tproxy_lookup_t lookup_type) +{ + struct inet_hashinfo *hinfo = net->ipv4.tcp_death_row.hashinfo; + struct sock *sk; + + switch (protocol) { + case IPPROTO_TCP: { + struct tcphdr _hdr, *hp; + + hp = skb_header_pointer(skb, thoff, + sizeof(struct tcphdr), &_hdr); + if (hp == NULL) + return NULL; + + switch (lookup_type) { + case NF_TPROXY_LOOKUP_LISTENER: + sk = inet6_lookup_listener(net, hinfo, skb, + thoff + __tcp_hdrlen(hp), + saddr, sport, + daddr, ntohs(dport), + in->ifindex, 0); + + if (sk && !refcount_inc_not_zero(&sk->sk_refcnt)) + sk = NULL; + /* NOTE: we return listeners even if bound to + * 0.0.0.0, those are filtered out in + * xt_socket, since xt_TPROXY needs 0 bound + * listeners too + */ + break; + case NF_TPROXY_LOOKUP_ESTABLISHED: + sk = __inet6_lookup_established(net, hinfo, saddr, sport, daddr, + ntohs(dport), in->ifindex, 0); + break; + default: + BUG(); + } + break; + } + case IPPROTO_UDP: + sk = udp6_lib_lookup(net, saddr, sport, daddr, dport, + in->ifindex); + if (sk) { + int connected = (sk->sk_state == TCP_ESTABLISHED); + int wildcard = ipv6_addr_any(&sk->sk_v6_rcv_saddr); + + /* NOTE: we return listeners even if bound to + * 0.0.0.0, those are filtered out in + * xt_socket, since xt_TPROXY needs 0 bound + * listeners too + */ + if ((lookup_type == NF_TPROXY_LOOKUP_ESTABLISHED && (!connected || wildcard)) || + (lookup_type == NF_TPROXY_LOOKUP_LISTENER && connected)) { + sock_put(sk); + sk = NULL; + } + } + break; + default: + WARN_ON(1); + sk = NULL; + } + + pr_debug("tproxy socket lookup: proto %u %pI6:%u -> %pI6:%u, lookup type: %d, sock %p\n", + protocol, saddr, ntohs(sport), daddr, ntohs(dport), lookup_type, sk); + + return sk; +} +EXPORT_SYMBOL_GPL(nf_tproxy_get_sock_v6); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Balazs Scheidler, Krisztian Kovacs"); +MODULE_DESCRIPTION("Netfilter IPv6 transparent proxy support"); diff --git a/net/ipv6/netfilter/nft_dup_ipv6.c b/net/ipv6/netfilter/nft_dup_ipv6.c new file mode 100644 index 000000000..70a405b40 --- /dev/null +++ b/net/ipv6/netfilter/nft_dup_ipv6.c @@ -0,0 +1,109 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2015 Pablo Neira Ayuso <pablo@netfilter.org> + */ + +#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/netfilter/ipv6/nf_dup_ipv6.h> + +struct nft_dup_ipv6 { + u8 sreg_addr; + u8 sreg_dev; +}; + +static void nft_dup_ipv6_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + struct nft_dup_ipv6 *priv = nft_expr_priv(expr); + struct in6_addr *gw = (struct in6_addr *)®s->data[priv->sreg_addr]; + int oif = priv->sreg_dev ? regs->data[priv->sreg_dev] : -1; + + nf_dup_ipv6(nft_net(pkt), pkt->skb, nft_hook(pkt), gw, oif); +} + +static int nft_dup_ipv6_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]) +{ + struct nft_dup_ipv6 *priv = nft_expr_priv(expr); + int err; + + if (tb[NFTA_DUP_SREG_ADDR] == NULL) + return -EINVAL; + + err = nft_parse_register_load(tb[NFTA_DUP_SREG_ADDR], &priv->sreg_addr, + sizeof(struct in6_addr)); + if (err < 0) + return err; + + if (tb[NFTA_DUP_SREG_DEV]) + err = nft_parse_register_load(tb[NFTA_DUP_SREG_DEV], + &priv->sreg_dev, sizeof(int)); + + return err; +} + +static int nft_dup_ipv6_dump(struct sk_buff *skb, const struct nft_expr *expr) +{ + struct nft_dup_ipv6 *priv = nft_expr_priv(expr); + + if (nft_dump_register(skb, NFTA_DUP_SREG_ADDR, priv->sreg_addr)) + goto nla_put_failure; + if (priv->sreg_dev && + nft_dump_register(skb, NFTA_DUP_SREG_DEV, priv->sreg_dev)) + goto nla_put_failure; + + return 0; + +nla_put_failure: + return -1; +} + +static struct nft_expr_type nft_dup_ipv6_type; +static const struct nft_expr_ops nft_dup_ipv6_ops = { + .type = &nft_dup_ipv6_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_dup_ipv6)), + .eval = nft_dup_ipv6_eval, + .init = nft_dup_ipv6_init, + .dump = nft_dup_ipv6_dump, + .reduce = NFT_REDUCE_READONLY, +}; + +static const struct nla_policy nft_dup_ipv6_policy[NFTA_DUP_MAX + 1] = { + [NFTA_DUP_SREG_ADDR] = { .type = NLA_U32 }, + [NFTA_DUP_SREG_DEV] = { .type = NLA_U32 }, +}; + +static struct nft_expr_type nft_dup_ipv6_type __read_mostly = { + .family = NFPROTO_IPV6, + .name = "dup", + .ops = &nft_dup_ipv6_ops, + .policy = nft_dup_ipv6_policy, + .maxattr = NFTA_DUP_MAX, + .owner = THIS_MODULE, +}; + +static int __init nft_dup_ipv6_module_init(void) +{ + return nft_register_expr(&nft_dup_ipv6_type); +} + +static void __exit nft_dup_ipv6_module_exit(void) +{ + nft_unregister_expr(&nft_dup_ipv6_type); +} + +module_init(nft_dup_ipv6_module_init); +module_exit(nft_dup_ipv6_module_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>"); +MODULE_ALIAS_NFT_AF_EXPR(AF_INET6, "dup"); +MODULE_DESCRIPTION("IPv6 nftables packet duplication support"); diff --git a/net/ipv6/netfilter/nft_fib_ipv6.c b/net/ipv6/netfilter/nft_fib_ipv6.c new file mode 100644 index 000000000..36dc14b34 --- /dev/null +++ b/net/ipv6/netfilter/nft_fib_ipv6.c @@ -0,0 +1,283 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#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 <linux/netfilter_ipv6.h> +#include <net/netfilter/nf_tables_core.h> +#include <net/netfilter/nf_tables.h> +#include <net/netfilter/nft_fib.h> + +#include <net/ip6_fib.h> +#include <net/ip6_route.h> + +static int get_ifindex(const struct net_device *dev) +{ + return dev ? dev->ifindex : 0; +} + +static int nft_fib6_flowi_init(struct flowi6 *fl6, const struct nft_fib *priv, + const struct nft_pktinfo *pkt, + const struct net_device *dev, + struct ipv6hdr *iph) +{ + int lookup_flags = 0; + + if (priv->flags & NFTA_FIB_F_DADDR) { + fl6->daddr = iph->daddr; + fl6->saddr = iph->saddr; + } else { + if (nft_hook(pkt) == NF_INET_FORWARD && + priv->flags & NFTA_FIB_F_IIF) + fl6->flowi6_iif = nft_out(pkt)->ifindex; + + fl6->daddr = iph->saddr; + fl6->saddr = iph->daddr; + } + + if (ipv6_addr_type(&fl6->daddr) & IPV6_ADDR_LINKLOCAL) { + lookup_flags |= RT6_LOOKUP_F_IFACE; + fl6->flowi6_oif = get_ifindex(dev ? dev : pkt->skb->dev); + } else if (priv->flags & NFTA_FIB_F_IIF) { + fl6->flowi6_l3mdev = l3mdev_master_ifindex_rcu(dev); + } + + if (ipv6_addr_type(&fl6->saddr) & IPV6_ADDR_UNICAST) + lookup_flags |= RT6_LOOKUP_F_HAS_SADDR; + + if (priv->flags & NFTA_FIB_F_MARK) + fl6->flowi6_mark = pkt->skb->mark; + + fl6->flowlabel = (*(__be32 *)iph) & IPV6_FLOWINFO_MASK; + + return lookup_flags; +} + +static u32 __nft_fib6_eval_type(const struct nft_fib *priv, + const struct nft_pktinfo *pkt, + struct ipv6hdr *iph) +{ + const struct net_device *dev = NULL; + int route_err, addrtype; + struct rt6_info *rt; + struct flowi6 fl6 = { + .flowi6_iif = LOOPBACK_IFINDEX, + .flowi6_proto = pkt->tprot, + .flowi6_uid = sock_net_uid(nft_net(pkt), NULL), + }; + u32 ret = 0; + + if (priv->flags & NFTA_FIB_F_IIF) + dev = nft_in(pkt); + else if (priv->flags & NFTA_FIB_F_OIF) + dev = nft_out(pkt); + + nft_fib6_flowi_init(&fl6, priv, pkt, dev, iph); + + if (dev && nf_ipv6_chk_addr(nft_net(pkt), &fl6.daddr, dev, true)) + ret = RTN_LOCAL; + + route_err = nf_ip6_route(nft_net(pkt), (struct dst_entry **)&rt, + flowi6_to_flowi(&fl6), false); + if (route_err) + goto err; + + if (rt->rt6i_flags & RTF_REJECT) { + route_err = rt->dst.error; + dst_release(&rt->dst); + goto err; + } + + if (ipv6_anycast_destination((struct dst_entry *)rt, &fl6.daddr)) + ret = RTN_ANYCAST; + else if (!dev && rt->rt6i_flags & RTF_LOCAL) + ret = RTN_LOCAL; + + dst_release(&rt->dst); + + if (ret) + return ret; + + addrtype = ipv6_addr_type(&fl6.daddr); + + if (addrtype & IPV6_ADDR_MULTICAST) + return RTN_MULTICAST; + if (addrtype & IPV6_ADDR_UNICAST) + return RTN_UNICAST; + + return RTN_UNSPEC; + err: + switch (route_err) { + case -EINVAL: + return RTN_BLACKHOLE; + case -EACCES: + return RTN_PROHIBIT; + case -EAGAIN: + return RTN_THROW; + default: + break; + } + + return RTN_UNREACHABLE; +} + +void nft_fib6_eval_type(const struct nft_expr *expr, struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + const struct nft_fib *priv = nft_expr_priv(expr); + int noff = skb_network_offset(pkt->skb); + u32 *dest = ®s->data[priv->dreg]; + struct ipv6hdr *iph, _iph; + + iph = skb_header_pointer(pkt->skb, noff, sizeof(_iph), &_iph); + if (!iph) { + regs->verdict.code = NFT_BREAK; + return; + } + + *dest = __nft_fib6_eval_type(priv, pkt, iph); +} +EXPORT_SYMBOL_GPL(nft_fib6_eval_type); + +static bool nft_fib_v6_skip_icmpv6(const struct sk_buff *skb, u8 next, const struct ipv6hdr *iph) +{ + if (likely(next != IPPROTO_ICMPV6)) + return false; + + if (ipv6_addr_type(&iph->saddr) != IPV6_ADDR_ANY) + return false; + + return ipv6_addr_type(&iph->daddr) & IPV6_ADDR_LINKLOCAL; +} + +void nft_fib6_eval(const struct nft_expr *expr, struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + const struct nft_fib *priv = nft_expr_priv(expr); + int noff = skb_network_offset(pkt->skb); + const struct net_device *oif = NULL; + u32 *dest = ®s->data[priv->dreg]; + struct ipv6hdr *iph, _iph; + struct flowi6 fl6 = { + .flowi6_iif = LOOPBACK_IFINDEX, + .flowi6_proto = pkt->tprot, + .flowi6_uid = sock_net_uid(nft_net(pkt), NULL), + }; + struct rt6_info *rt; + int lookup_flags; + + if (priv->flags & NFTA_FIB_F_IIF) + oif = nft_in(pkt); + else if (priv->flags & NFTA_FIB_F_OIF) + oif = nft_out(pkt); + + iph = skb_header_pointer(pkt->skb, noff, sizeof(_iph), &_iph); + if (!iph) { + regs->verdict.code = NFT_BREAK; + return; + } + + lookup_flags = nft_fib6_flowi_init(&fl6, priv, pkt, oif, iph); + + if (nft_hook(pkt) == NF_INET_PRE_ROUTING || + nft_hook(pkt) == NF_INET_INGRESS) { + if (nft_fib_is_loopback(pkt->skb, nft_in(pkt)) || + nft_fib_v6_skip_icmpv6(pkt->skb, pkt->tprot, iph)) { + nft_fib_store_result(dest, priv, nft_in(pkt)); + return; + } + } + + *dest = 0; + rt = (void *)ip6_route_lookup(nft_net(pkt), &fl6, pkt->skb, + lookup_flags); + if (rt->dst.error) + goto put_rt_err; + + /* Should not see RTF_LOCAL here */ + if (rt->rt6i_flags & (RTF_REJECT | RTF_ANYCAST | RTF_LOCAL)) + goto put_rt_err; + + if (oif && oif != rt->rt6i_idev->dev && + l3mdev_master_ifindex_rcu(rt->rt6i_idev->dev) != oif->ifindex) + goto put_rt_err; + + nft_fib_store_result(dest, priv, rt->rt6i_idev->dev); + put_rt_err: + ip6_rt_put(rt); +} +EXPORT_SYMBOL_GPL(nft_fib6_eval); + +static struct nft_expr_type nft_fib6_type; + +static const struct nft_expr_ops nft_fib6_type_ops = { + .type = &nft_fib6_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_fib)), + .eval = nft_fib6_eval_type, + .init = nft_fib_init, + .dump = nft_fib_dump, + .validate = nft_fib_validate, + .reduce = nft_fib_reduce, +}; + +static const struct nft_expr_ops nft_fib6_ops = { + .type = &nft_fib6_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_fib)), + .eval = nft_fib6_eval, + .init = nft_fib_init, + .dump = nft_fib_dump, + .validate = nft_fib_validate, + .reduce = nft_fib_reduce, +}; + +static const struct nft_expr_ops * +nft_fib6_select_ops(const struct nft_ctx *ctx, + const struct nlattr * const tb[]) +{ + enum nft_fib_result result; + + if (!tb[NFTA_FIB_RESULT]) + return ERR_PTR(-EINVAL); + + result = ntohl(nla_get_be32(tb[NFTA_FIB_RESULT])); + + switch (result) { + case NFT_FIB_RESULT_OIF: + return &nft_fib6_ops; + case NFT_FIB_RESULT_OIFNAME: + return &nft_fib6_ops; + case NFT_FIB_RESULT_ADDRTYPE: + return &nft_fib6_type_ops; + default: + return ERR_PTR(-EOPNOTSUPP); + } +} + +static struct nft_expr_type nft_fib6_type __read_mostly = { + .name = "fib", + .select_ops = nft_fib6_select_ops, + .policy = nft_fib_policy, + .maxattr = NFTA_FIB_MAX, + .family = NFPROTO_IPV6, + .owner = THIS_MODULE, +}; + +static int __init nft_fib6_module_init(void) +{ + return nft_register_expr(&nft_fib6_type); +} + +static void __exit nft_fib6_module_exit(void) +{ + nft_unregister_expr(&nft_fib6_type); +} +module_init(nft_fib6_module_init); +module_exit(nft_fib6_module_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Florian Westphal <fw@strlen.de>"); +MODULE_ALIAS_NFT_AF_EXPR(10, "fib"); +MODULE_DESCRIPTION("nftables fib / ipv6 route lookup support"); diff --git a/net/ipv6/netfilter/nft_reject_ipv6.c b/net/ipv6/netfilter/nft_reject_ipv6.c new file mode 100644 index 000000000..5c61294f4 --- /dev/null +++ b/net/ipv6/netfilter/nft_reject_ipv6.c @@ -0,0 +1,77 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2008-2009 Patrick McHardy <kaber@trash.net> + * Copyright (c) 2013 Eric Leblond <eric@regit.org> + * + * 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/netfilter/nft_reject.h> +#include <net/netfilter/ipv6/nf_reject.h> + +static void nft_reject_ipv6_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + struct nft_reject *priv = nft_expr_priv(expr); + + switch (priv->type) { + case NFT_REJECT_ICMP_UNREACH: + nf_send_unreach6(nft_net(pkt), pkt->skb, priv->icmp_code, + nft_hook(pkt)); + break; + case NFT_REJECT_TCP_RST: + nf_send_reset6(nft_net(pkt), nft_sk(pkt), pkt->skb, + nft_hook(pkt)); + break; + default: + break; + } + + regs->verdict.code = NF_DROP; +} + +static struct nft_expr_type nft_reject_ipv6_type; +static const struct nft_expr_ops nft_reject_ipv6_ops = { + .type = &nft_reject_ipv6_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_reject)), + .eval = nft_reject_ipv6_eval, + .init = nft_reject_init, + .dump = nft_reject_dump, + .validate = nft_reject_validate, + .reduce = NFT_REDUCE_READONLY, +}; + +static struct nft_expr_type nft_reject_ipv6_type __read_mostly = { + .family = NFPROTO_IPV6, + .name = "reject", + .ops = &nft_reject_ipv6_ops, + .policy = nft_reject_policy, + .maxattr = NFTA_REJECT_MAX, + .owner = THIS_MODULE, +}; + +static int __init nft_reject_ipv6_module_init(void) +{ + return nft_register_expr(&nft_reject_ipv6_type); +} + +static void __exit nft_reject_ipv6_module_exit(void) +{ + nft_unregister_expr(&nft_reject_ipv6_type); +} + +module_init(nft_reject_ipv6_module_init); +module_exit(nft_reject_ipv6_module_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); +MODULE_ALIAS_NFT_AF_EXPR(AF_INET6, "reject"); +MODULE_DESCRIPTION("IPv6 packet rejection for nftables"); |