diff options
author | David S. Miller <davem@davemloft.net> | 2019-03-02 14:01:04 -0800 |
---|---|---|
committer | David S. Miller <davem@davemloft.net> | 2019-03-02 14:01:04 -0800 |
commit | 4e7df119d9a621262f22cacf8ae5ca5060183bea (patch) | |
tree | e771bb702e3eda858f2e588dbcefff8913c8d4f3 /net | |
parent | 2369afb6696c5a53772bfbc8b57b75dd40e46bfc (diff) | |
parent | db8ab38880e06dedbfc879e75f5b0ddc495f4eb6 (diff) | |
download | linux-4e7df119d9a621262f22cacf8ae5ca5060183bea.tar.gz linux-4e7df119d9a621262f22cacf8ae5ca5060183bea.tar.bz2 linux-4e7df119d9a621262f22cacf8ae5ca5060183bea.zip |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/pablo/nf-next
Pablo Neira Ayuso says:
====================
Netfilter/IPVS updates for net-next
The following patchset contains Netfilter/IPVS updates for net-next:
1) Add .release_ops to properly unroll .select_ops, use it from nft_compat.
After this change, we can remove list of extensions too to simplify this
codebase.
2) Update amanda conntrack helper to support v3.4, from Florian Tham.
3) Get rid of the obsolete BUGPRINT macro in ebtables, from
Florian Westphal.
4) Merge IPv4 and IPv6 masquerading infrastructure into one single module.
From Florian Westphal.
5) Patchset to remove nf_nat_l3proto structure to get rid of
indirections, from Florian Westphal.
6) Skip unnecessary conntrack timeout updates in case the value is
still the same, also from Florian Westphal.
7) Remove unnecessary 'fall through' comments in empty switch cases,
from Li RongQing.
8) Fix lookup to fixed size hashtable sets on big endian with 32-bit keys.
9) Incorrect logic to deactivate path of fixed size hashtable sets,
element was being tested to self.
10) Remove nft_hash_key(), the bitmap set is always selected for 16-bit
keys.
11) Use boolean whenever possible in IPVS codebase, from Andrea Claudi.
12) Enter close state in conntrack if RST matches exact sequence number,
from Florian Westphal.
13) Initialize dst_cache in tunnel extension, from wenxu.
14) Pass protocol as u16 to xt_check_match and xt_check_target, from
Li RongQing.
15) SCTP header is granted to be in a linear area from IPVS NAT handler,
from Xin Long.
16) Don't steal packets coming from slave VRF device from the
ip_sabotage_in() path, from David Ahern.
17) Fix unsafe update of basechain stats, from Li RongQing.
18) Make sure CONNTRACK_LOCKS is power of 2 to let compiler optimize
modulo operation as bitwise AND, from Li RongQing.
19) Use device_attribute instead of internal definition in the IDLETIMER
target, from Sami Tolvanen.
20) Merge redir, masq and IPv4/IPv6 NAT chain types, from Florian Westphal.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net')
47 files changed, 1695 insertions, 2267 deletions
diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index 40d058378b52..9d34de68571b 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -831,7 +831,8 @@ static unsigned int ip_sabotage_in(void *priv, struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb); if (nf_bridge && !nf_bridge->in_prerouting && - !netif_is_l3_master(skb->dev)) { + !netif_is_l3_master(skb->dev) && + !netif_is_l3_slave(skb->dev)) { state->okfn(state->net, state->sk, skb); return NF_STOLEN; } diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 6693e209efe8..eb15891f8b9f 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -31,10 +31,6 @@ /* needed for logical [in,out]-dev filtering */ #include "../br_private.h" -#define BUGPRINT(format, args...) printk("kernel msg: ebtables bug: please "\ - "report to author: "format, ## args) -/* #define BUGPRINT(format, args...) */ - /* Each cpu has its own set of counters, so there is no need for write_lock in * the softirq * For reading or updating the counters, the user context needs to @@ -385,7 +381,7 @@ ebt_check_match(struct ebt_entry_match *m, struct xt_mtchk_param *par, par->match = match; par->matchinfo = m->data; ret = xt_check_match(par, m->match_size, - e->ethproto, e->invflags & EBT_IPROTO); + ntohs(e->ethproto), e->invflags & EBT_IPROTO); if (ret < 0) { module_put(match->me); return ret; @@ -422,7 +418,7 @@ ebt_check_watcher(struct ebt_entry_watcher *w, struct xt_tgchk_param *par, par->target = watcher; par->targinfo = w->data; ret = xt_check_target(par, w->watcher_size, - e->ethproto, e->invflags & EBT_IPROTO); + ntohs(e->ethproto), e->invflags & EBT_IPROTO); if (ret < 0) { module_put(watcher->me); return ret; @@ -466,8 +462,6 @@ static int ebt_verify_pointers(const struct ebt_replace *repl, /* we make userspace set this right, * so there is no misunderstanding */ - BUGPRINT("EBT_ENTRY_OR_ENTRIES shouldn't be set " - "in distinguisher\n"); return -EINVAL; } if (i != NF_BR_NUMHOOKS) @@ -485,18 +479,14 @@ static int ebt_verify_pointers(const struct ebt_replace *repl, offset += e->next_offset; } } - if (offset != limit) { - BUGPRINT("entries_size too small\n"); + if (offset != limit) return -EINVAL; - } /* check if all valid hooks have a chain */ for (i = 0; i < NF_BR_NUMHOOKS; i++) { if (!newinfo->hook_entry[i] && - (valid_hooks & (1 << i))) { - BUGPRINT("Valid hook without chain\n"); + (valid_hooks & (1 << i))) return -EINVAL; - } } return 0; } @@ -523,26 +513,20 @@ ebt_check_entry_size_and_hooks(const struct ebt_entry *e, /* this checks if the previous chain has as many entries * as it said it has */ - if (*n != *cnt) { - BUGPRINT("nentries does not equal the nr of entries " - "in the chain\n"); + if (*n != *cnt) return -EINVAL; - } + if (((struct ebt_entries *)e)->policy != EBT_DROP && ((struct ebt_entries *)e)->policy != EBT_ACCEPT) { /* only RETURN from udc */ if (i != NF_BR_NUMHOOKS || - ((struct ebt_entries *)e)->policy != EBT_RETURN) { - BUGPRINT("bad policy\n"); + ((struct ebt_entries *)e)->policy != EBT_RETURN) return -EINVAL; - } } if (i == NF_BR_NUMHOOKS) /* it's a user defined chain */ (*udc_cnt)++; - if (((struct ebt_entries *)e)->counter_offset != *totalcnt) { - BUGPRINT("counter_offset != totalcnt"); + if (((struct ebt_entries *)e)->counter_offset != *totalcnt) return -EINVAL; - } *n = ((struct ebt_entries *)e)->nentries; *cnt = 0; return 0; @@ -550,15 +534,13 @@ ebt_check_entry_size_and_hooks(const struct ebt_entry *e, /* a plain old entry, heh */ if (sizeof(struct ebt_entry) > e->watchers_offset || e->watchers_offset > e->target_offset || - e->target_offset >= e->next_offset) { - BUGPRINT("entry offsets not in right order\n"); + e->target_offset >= e->next_offset) return -EINVAL; - } + /* this is not checked anywhere else */ - if (e->next_offset - e->target_offset < sizeof(struct ebt_entry_target)) { - BUGPRINT("target size too small\n"); + if (e->next_offset - e->target_offset < sizeof(struct ebt_entry_target)) return -EINVAL; - } + (*cnt)++; (*totalcnt)++; return 0; @@ -678,18 +660,15 @@ ebt_check_entry(struct ebt_entry *e, struct net *net, if (e->bitmask == 0) return 0; - if (e->bitmask & ~EBT_F_MASK) { - BUGPRINT("Unknown flag for bitmask\n"); + if (e->bitmask & ~EBT_F_MASK) return -EINVAL; - } - if (e->invflags & ~EBT_INV_MASK) { - BUGPRINT("Unknown flag for inv bitmask\n"); + + if (e->invflags & ~EBT_INV_MASK) return -EINVAL; - } - if ((e->bitmask & EBT_NOPROTO) && (e->bitmask & EBT_802_3)) { - BUGPRINT("NOPROTO & 802_3 not allowed\n"); + + if ((e->bitmask & EBT_NOPROTO) && (e->bitmask & EBT_802_3)) return -EINVAL; - } + /* what hook do we belong to? */ for (i = 0; i < NF_BR_NUMHOOKS; i++) { if (!newinfo->hook_entry[i]) @@ -748,13 +727,11 @@ ebt_check_entry(struct ebt_entry *e, struct net *net, t->u.target = target; if (t->u.target == &ebt_standard_target) { if (gap < sizeof(struct ebt_standard_target)) { - BUGPRINT("Standard target size too big\n"); ret = -EFAULT; goto cleanup_watchers; } if (((struct ebt_standard_target *)t)->verdict < -NUM_STANDARD_TARGETS) { - BUGPRINT("Invalid standard target\n"); ret = -EFAULT; goto cleanup_watchers; } @@ -767,7 +744,7 @@ ebt_check_entry(struct ebt_entry *e, struct net *net, tgpar.target = target; tgpar.targinfo = t->data; ret = xt_check_target(&tgpar, t->target_size, - e->ethproto, e->invflags & EBT_IPROTO); + ntohs(e->ethproto), e->invflags & EBT_IPROTO); if (ret < 0) { module_put(target->me); goto cleanup_watchers; @@ -813,10 +790,9 @@ static int check_chainloops(const struct ebt_entries *chain, struct ebt_cl_stack if (strcmp(t->u.name, EBT_STANDARD_TARGET)) goto letscontinue; if (e->target_offset + sizeof(struct ebt_standard_target) > - e->next_offset) { - BUGPRINT("Standard target size too big\n"); + e->next_offset) return -1; - } + verdict = ((struct ebt_standard_target *)t)->verdict; if (verdict >= 0) { /* jump to another chain */ struct ebt_entries *hlp2 = @@ -825,14 +801,12 @@ static int check_chainloops(const struct ebt_entries *chain, struct ebt_cl_stack if (hlp2 == cl_s[i].cs.chaininfo) break; /* bad destination or loop */ - if (i == udc_cnt) { - BUGPRINT("bad destination\n"); + if (i == udc_cnt) return -1; - } - if (cl_s[i].cs.n) { - BUGPRINT("loop\n"); + + if (cl_s[i].cs.n) return -1; - } + if (cl_s[i].hookmask & (1 << hooknr)) goto letscontinue; /* this can't be 0, so the loop test is correct */ @@ -865,24 +839,21 @@ static int translate_table(struct net *net, const char *name, i = 0; while (i < NF_BR_NUMHOOKS && !newinfo->hook_entry[i]) i++; - if (i == NF_BR_NUMHOOKS) { - BUGPRINT("No valid hooks specified\n"); + if (i == NF_BR_NUMHOOKS) return -EINVAL; - } - if (newinfo->hook_entry[i] != (struct ebt_entries *)newinfo->entries) { - BUGPRINT("Chains don't start at beginning\n"); + + if (newinfo->hook_entry[i] != (struct ebt_entries *)newinfo->entries) return -EINVAL; - } + /* make sure chains are ordered after each other in same order * as their corresponding hooks */ for (j = i + 1; j < NF_BR_NUMHOOKS; j++) { if (!newinfo->hook_entry[j]) continue; - if (newinfo->hook_entry[j] <= newinfo->hook_entry[i]) { - BUGPRINT("Hook order must be followed\n"); + if (newinfo->hook_entry[j] <= newinfo->hook_entry[i]) return -EINVAL; - } + i = j; } @@ -900,15 +871,11 @@ static int translate_table(struct net *net, const char *name, if (ret != 0) return ret; - if (i != j) { - BUGPRINT("nentries does not equal the nr of entries in the " - "(last) chain\n"); + if (i != j) return -EINVAL; - } - if (k != newinfo->nentries) { - BUGPRINT("Total nentries is wrong\n"); + + if (k != newinfo->nentries) return -EINVAL; - } /* get the location of the udc, put them in an array * while we're at it, allocate the chainstack @@ -942,7 +909,6 @@ static int translate_table(struct net *net, const char *name, ebt_get_udc_positions, newinfo, &i, cl_s); /* sanity check */ if (i != udc_cnt) { - BUGPRINT("i != udc_cnt\n"); vfree(cl_s); return -EFAULT; } @@ -1042,7 +1008,6 @@ static int do_replace_finish(struct net *net, struct ebt_replace *repl, goto free_unlock; if (repl->num_counters && repl->num_counters != t->private->nentries) { - BUGPRINT("Wrong nr. of counters requested\n"); ret = -EINVAL; goto free_unlock; } @@ -1118,15 +1083,12 @@ static int do_replace(struct net *net, const void __user *user, if (copy_from_user(&tmp, user, sizeof(tmp)) != 0) return -EFAULT; - if (len != sizeof(tmp) + tmp.entries_size) { - BUGPRINT("Wrong len argument\n"); + if (len != sizeof(tmp) + tmp.entries_size) return -EINVAL; - } - if (tmp.entries_size == 0) { - BUGPRINT("Entries_size never zero\n"); + if (tmp.entries_size == 0) return -EINVAL; - } + /* overflow check */ if (tmp.nentries >= ((INT_MAX - sizeof(struct ebt_table_info)) / NR_CPUS - SMP_CACHE_BYTES) / sizeof(struct ebt_counter)) @@ -1153,7 +1115,6 @@ static int do_replace(struct net *net, const void __user *user, } if (copy_from_user( newinfo->entries, tmp.entries, tmp.entries_size) != 0) { - BUGPRINT("Couldn't copy entries from userspace\n"); ret = -EFAULT; goto free_entries; } @@ -1194,10 +1155,8 @@ int ebt_register_table(struct net *net, const struct ebt_table *input_table, if (input_table == NULL || (repl = input_table->table) == NULL || repl->entries == NULL || repl->entries_size == 0 || - repl->counters != NULL || input_table->private != NULL) { - BUGPRINT("Bad table data for ebt_register_table!!!\n"); + repl->counters != NULL || input_table->private != NULL) return -EINVAL; - } /* Don't add one table to multiple lists. */ table = kmemdup(input_table, sizeof(struct ebt_table), GFP_KERNEL); @@ -1235,13 +1194,10 @@ int ebt_register_table(struct net *net, const struct ebt_table *input_table, ((char *)repl->hook_entry[i] - repl->entries); } ret = translate_table(net, repl->name, newinfo); - if (ret != 0) { - BUGPRINT("Translate_table failed\n"); + if (ret != 0) goto free_chainstack; - } if (table->check && table->check(newinfo, table->valid_hooks)) { - BUGPRINT("The table doesn't like its own initial data, lol\n"); ret = -EINVAL; goto free_chainstack; } @@ -1252,7 +1208,6 @@ int ebt_register_table(struct net *net, const struct ebt_table *input_table, list_for_each_entry(t, &net->xt.tables[NFPROTO_BRIDGE], list) { if (strcmp(t->name, table->name) == 0) { ret = -EEXIST; - BUGPRINT("Table name already exists\n"); goto free_unlock; } } @@ -1320,7 +1275,6 @@ static int do_update_counters(struct net *net, const char *name, goto free_tmp; if (num_counters != t->private->nentries) { - BUGPRINT("Wrong nr of counters\n"); ret = -EINVAL; goto unlock_mutex; } @@ -1447,10 +1401,8 @@ static int copy_counters_to_user(struct ebt_table *t, if (num_counters == 0) return 0; - if (num_counters != nentries) { - BUGPRINT("Num_counters wrong\n"); + if (num_counters != nentries) return -EINVAL; - } counterstmp = vmalloc(array_size(nentries, sizeof(*counterstmp))); if (!counterstmp) @@ -1496,15 +1448,11 @@ static int copy_everything_to_user(struct ebt_table *t, void __user *user, (tmp.num_counters ? nentries * sizeof(struct ebt_counter) : 0)) return -EINVAL; - if (tmp.nentries != nentries) { - BUGPRINT("Nentries wrong\n"); + if (tmp.nentries != nentries) return -EINVAL; - } - if (tmp.entries_size != entries_size) { - BUGPRINT("Wrong size\n"); + if (tmp.entries_size != entries_size) return -EINVAL; - } ret = copy_counters_to_user(t, oldcounters, tmp.counters, tmp.num_counters, nentries); @@ -1576,7 +1524,6 @@ static int do_ebt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) } mutex_unlock(&ebt_mutex); if (copy_to_user(user, &tmp, *len) != 0) { - BUGPRINT("c2u Didn't work\n"); ret = -EFAULT; break; } diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig index 80f72cc5ca8d..c98391d49200 100644 --- a/net/ipv4/netfilter/Kconfig +++ b/net/ipv4/netfilter/Kconfig @@ -94,50 +94,7 @@ config NF_REJECT_IPV4 tristate "IPv4 packet rejection" default m if NETFILTER_ADVANCED=n -config NF_NAT_IPV4 - tristate "IPv4 NAT" - depends on NF_CONNTRACK - default m if NETFILTER_ADVANCED=n - select NF_NAT - help - The IPv4 NAT option allows masquerading, port forwarding and other - forms of full Network Address Port Translation. This can be - controlled by iptables or nft. - -if NF_NAT_IPV4 - -config NF_NAT_MASQUERADE_IPV4 - bool - -if NF_TABLES -config NFT_CHAIN_NAT_IPV4 - depends on NF_TABLES_IPV4 - tristate "IPv4 nf_tables nat chain support" - help - This option enables the "nat" chain for IPv4 in nf_tables. This - chain type is used to perform Network Address Translation (NAT) - packet transformations such as the source, destination address and - source and destination ports. - -config NFT_MASQ_IPV4 - tristate "IPv4 masquerading support for nf_tables" - depends on NF_TABLES_IPV4 - depends on NFT_MASQ - select NF_NAT_MASQUERADE_IPV4 - help - This is the expression that provides IPv4 masquerading support for - nf_tables. - -config NFT_REDIR_IPV4 - tristate "IPv4 redirect support for nf_tables" - depends on NF_TABLES_IPV4 - depends on NFT_REDIR - select NF_NAT_REDIRECT - help - This is the expression that provides IPv4 redirect support for - nf_tables. -endif # NF_TABLES - +if NF_NAT config NF_NAT_SNMP_BASIC tristate "Basic SNMP-ALG support" depends on NF_CONNTRACK_SNMP @@ -166,7 +123,7 @@ config NF_NAT_H323 depends on NF_CONNTRACK default NF_CONNTRACK_H323 -endif # NF_NAT_IPV4 +endif # NF_NAT config IP_NF_IPTABLES tristate "IP tables support (required for filtering/masq/NAT)" @@ -263,7 +220,6 @@ config IP_NF_NAT depends on NF_CONNTRACK default m if NETFILTER_ADVANCED=n select NF_NAT - select NF_NAT_IPV4 select NETFILTER_XT_NAT help This enables the `nat' table in iptables. This allows masquerading, @@ -276,7 +232,7 @@ if IP_NF_NAT config IP_NF_TARGET_MASQUERADE tristate "MASQUERADE target support" - select NF_NAT_MASQUERADE_IPV4 + select NF_NAT_MASQUERADE default m if NETFILTER_ADVANCED=n help Masquerading is a special case of NAT: all outgoing connections are diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile index fd7122e0e2c9..e241f5188ebe 100644 --- a/net/ipv4/netfilter/Makefile +++ b/net/ipv4/netfilter/Makefile @@ -3,10 +3,6 @@ # Makefile for the netfilter modules on top of IPv4. # -nf_nat_ipv4-y := nf_nat_l3proto_ipv4.o -nf_nat_ipv4-$(CONFIG_NF_NAT_MASQUERADE_IPV4) += nf_nat_masquerade_ipv4.o -obj-$(CONFIG_NF_NAT_IPV4) += nf_nat_ipv4.o - # defrag obj-$(CONFIG_NF_DEFRAG_IPV4) += nf_defrag_ipv4.o @@ -29,11 +25,8 @@ $(obj)/nf_nat_snmp_basic_main.o: $(obj)/nf_nat_snmp_basic.asn1.h obj-$(CONFIG_NF_NAT_SNMP_BASIC) += nf_nat_snmp_basic.o obj-$(CONFIG_NFT_CHAIN_ROUTE_IPV4) += nft_chain_route_ipv4.o -obj-$(CONFIG_NFT_CHAIN_NAT_IPV4) += nft_chain_nat_ipv4.o obj-$(CONFIG_NFT_REJECT_IPV4) += nft_reject_ipv4.o obj-$(CONFIG_NFT_FIB_IPV4) += nft_fib_ipv4.o -obj-$(CONFIG_NFT_MASQ_IPV4) += nft_masq_ipv4.o -obj-$(CONFIG_NFT_REDIR_IPV4) += nft_redir_ipv4.o obj-$(CONFIG_NFT_DUP_IPV4) += nft_dup_ipv4.o # flow table support diff --git a/net/ipv4/netfilter/iptable_nat.c b/net/ipv4/netfilter/iptable_nat.c index a317445448bf..007da0882412 100644 --- a/net/ipv4/netfilter/iptable_nat.c +++ b/net/ipv4/netfilter/iptable_nat.c @@ -15,8 +15,6 @@ #include <net/ip.h> #include <net/netfilter/nf_nat.h> -#include <net/netfilter/nf_nat_core.h> -#include <net/netfilter/nf_nat_l3proto.h> static int __net_init iptable_nat_table_init(struct net *net); @@ -70,10 +68,10 @@ static int ipt_nat_register_lookups(struct net *net) int i, ret; for (i = 0; i < ARRAY_SIZE(nf_nat_ipv4_ops); i++) { - ret = nf_nat_l3proto_ipv4_register_fn(net, &nf_nat_ipv4_ops[i]); + ret = nf_nat_ipv4_register_fn(net, &nf_nat_ipv4_ops[i]); if (ret) { while (i) - nf_nat_l3proto_ipv4_unregister_fn(net, &nf_nat_ipv4_ops[--i]); + nf_nat_ipv4_unregister_fn(net, &nf_nat_ipv4_ops[--i]); return ret; } @@ -87,7 +85,7 @@ static void ipt_nat_unregister_lookups(struct net *net) int i; for (i = 0; i < ARRAY_SIZE(nf_nat_ipv4_ops); i++) - nf_nat_l3proto_ipv4_unregister_fn(net, &nf_nat_ipv4_ops[i]); + nf_nat_ipv4_unregister_fn(net, &nf_nat_ipv4_ops[i]); } static int __net_init iptable_nat_table_init(struct net *net) diff --git a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c deleted file mode 100644 index 4b07eb8a9b18..000000000000 --- a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c +++ /dev/null @@ -1,388 +0,0 @@ -/* - * (C) 1999-2001 Paul `Rusty' Russell - * (C) 2002-2006 Netfilter Core Team <coreteam@netfilter.org> - * (C) 2011 Patrick McHardy <kaber@trash.net> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#include <linux/types.h> -#include <linux/module.h> -#include <linux/skbuff.h> -#include <linux/ip.h> -#include <linux/icmp.h> -#include <linux/netfilter.h> -#include <linux/netfilter_ipv4.h> -#include <net/secure_seq.h> -#include <net/checksum.h> -#include <net/route.h> -#include <net/ip.h> - -#include <net/netfilter/nf_conntrack_core.h> -#include <net/netfilter/nf_conntrack.h> -#include <net/netfilter/nf_nat_core.h> -#include <net/netfilter/nf_nat_l3proto.h> -#include <net/netfilter/nf_nat_l4proto.h> - -static const struct nf_nat_l3proto nf_nat_l3proto_ipv4; - -#ifdef CONFIG_XFRM -static void nf_nat_ipv4_decode_session(struct sk_buff *skb, - const struct nf_conn *ct, - enum ip_conntrack_dir dir, - unsigned long statusbit, - struct flowi *fl) -{ - const struct nf_conntrack_tuple *t = &ct->tuplehash[dir].tuple; - struct flowi4 *fl4 = &fl->u.ip4; - - if (ct->status & statusbit) { - fl4->daddr = t->dst.u3.ip; - if (t->dst.protonum == IPPROTO_TCP || - t->dst.protonum == IPPROTO_UDP || - t->dst.protonum == IPPROTO_UDPLITE || - t->dst.protonum == IPPROTO_DCCP || - t->dst.protonum == IPPROTO_SCTP) - fl4->fl4_dport = t->dst.u.all; - } - - statusbit ^= IPS_NAT_MASK; - - if (ct->status & statusbit) { - fl4->saddr = t->src.u3.ip; - if (t->dst.protonum == IPPROTO_TCP || - t->dst.protonum == IPPROTO_UDP || - t->dst.protonum == IPPROTO_UDPLITE || - t->dst.protonum == IPPROTO_DCCP || - t->dst.protonum == IPPROTO_SCTP) - fl4->fl4_sport = t->src.u.all; - } -} -#endif /* CONFIG_XFRM */ - -static bool nf_nat_ipv4_manip_pkt(struct sk_buff *skb, - unsigned int iphdroff, - const struct nf_conntrack_tuple *target, - enum nf_nat_manip_type maniptype) -{ - struct iphdr *iph; - unsigned int hdroff; - - if (!skb_make_writable(skb, iphdroff + sizeof(*iph))) - return false; - - iph = (void *)skb->data + iphdroff; - hdroff = iphdroff + iph->ihl * 4; - - if (!nf_nat_l4proto_manip_pkt(skb, &nf_nat_l3proto_ipv4, iphdroff, - hdroff, target, maniptype)) - return false; - iph = (void *)skb->data + iphdroff; - - if (maniptype == NF_NAT_MANIP_SRC) { - csum_replace4(&iph->check, iph->saddr, target->src.u3.ip); - iph->saddr = target->src.u3.ip; - } else { - csum_replace4(&iph->check, iph->daddr, target->dst.u3.ip); - iph->daddr = target->dst.u3.ip; - } - return true; -} - -static void nf_nat_ipv4_csum_update(struct sk_buff *skb, - unsigned int iphdroff, __sum16 *check, - const struct nf_conntrack_tuple *t, - enum nf_nat_manip_type maniptype) -{ - struct iphdr *iph = (struct iphdr *)(skb->data + iphdroff); - __be32 oldip, newip; - - if (maniptype == NF_NAT_MANIP_SRC) { - oldip = iph->saddr; - newip = t->src.u3.ip; - } else { - oldip = iph->daddr; - newip = t->dst.u3.ip; - } - inet_proto_csum_replace4(check, skb, oldip, newip, true); -} - -static void nf_nat_ipv4_csum_recalc(struct sk_buff *skb, - u8 proto, void *data, __sum16 *check, - int datalen, int oldlen) -{ - if (skb->ip_summed != CHECKSUM_PARTIAL) { - const struct iphdr *iph = ip_hdr(skb); - - skb->ip_summed = CHECKSUM_PARTIAL; - skb->csum_start = skb_headroom(skb) + skb_network_offset(skb) + - ip_hdrlen(skb); - skb->csum_offset = (void *)check - data; - *check = ~csum_tcpudp_magic(iph->saddr, iph->daddr, datalen, - proto, 0); - } else - inet_proto_csum_replace2(check, skb, - htons(oldlen), htons(datalen), true); -} - -#if IS_ENABLED(CONFIG_NF_CT_NETLINK) -static int nf_nat_ipv4_nlattr_to_range(struct nlattr *tb[], - struct nf_nat_range2 *range) -{ - if (tb[CTA_NAT_V4_MINIP]) { - range->min_addr.ip = nla_get_be32(tb[CTA_NAT_V4_MINIP]); - range->flags |= NF_NAT_RANGE_MAP_IPS; - } - - if (tb[CTA_NAT_V4_MAXIP]) - range->max_addr.ip = nla_get_be32(tb[CTA_NAT_V4_MAXIP]); - else - range->max_addr.ip = range->min_addr.ip; - - return 0; -} -#endif - -static const struct nf_nat_l3proto nf_nat_l3proto_ipv4 = { - .l3proto = NFPROTO_IPV4, - .manip_pkt = nf_nat_ipv4_manip_pkt, - .csum_update = nf_nat_ipv4_csum_update, - .csum_recalc = nf_nat_ipv4_csum_recalc, -#if IS_ENABLED(CONFIG_NF_CT_NETLINK) - .nlattr_to_range = nf_nat_ipv4_nlattr_to_range, -#endif -#ifdef CONFIG_XFRM - .decode_session = nf_nat_ipv4_decode_session, -#endif -}; - -int nf_nat_icmp_reply_translation(struct sk_buff *skb, - struct nf_conn *ct, - enum ip_conntrack_info ctinfo, - unsigned int hooknum) -{ - struct { - struct icmphdr icmp; - struct iphdr ip; - } *inside; - enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); - enum nf_nat_manip_type manip = HOOK2MANIP(hooknum); - unsigned int hdrlen = ip_hdrlen(skb); - struct nf_conntrack_tuple target; - unsigned long statusbit; - - WARN_ON(ctinfo != IP_CT_RELATED && ctinfo != IP_CT_RELATED_REPLY); - - if (!skb_make_writable(skb, hdrlen + sizeof(*inside))) - return 0; - if (nf_ip_checksum(skb, hooknum, hdrlen, 0)) - return 0; - - inside = (void *)skb->data + hdrlen; - if (inside->icmp.type == ICMP_REDIRECT) { - if ((ct->status & IPS_NAT_DONE_MASK) != IPS_NAT_DONE_MASK) - return 0; - if (ct->status & IPS_NAT_MASK) - return 0; - } - - if (manip == NF_NAT_MANIP_SRC) - statusbit = IPS_SRC_NAT; - else - statusbit = IPS_DST_NAT; - - /* Invert if this is reply direction */ - if (dir == IP_CT_DIR_REPLY) - statusbit ^= IPS_NAT_MASK; - - if (!(ct->status & statusbit)) - return 1; - - if (!nf_nat_ipv4_manip_pkt(skb, hdrlen + sizeof(inside->icmp), - &ct->tuplehash[!dir].tuple, !manip)) - return 0; - - if (skb->ip_summed != CHECKSUM_PARTIAL) { - /* Reloading "inside" here since manip_pkt may reallocate */ - inside = (void *)skb->data + hdrlen; - inside->icmp.checksum = 0; - inside->icmp.checksum = - csum_fold(skb_checksum(skb, hdrlen, - skb->len - hdrlen, 0)); - } - - /* Change outer to look like the reply to an incoming packet */ - nf_ct_invert_tuple(&target, &ct->tuplehash[!dir].tuple); - target.dst.protonum = IPPROTO_ICMP; - if (!nf_nat_ipv4_manip_pkt(skb, 0, &target, manip)) - return 0; - - return 1; -} -EXPORT_SYMBOL_GPL(nf_nat_icmp_reply_translation); - -static unsigned int -nf_nat_ipv4_fn(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state) -{ - struct nf_conn *ct; - enum ip_conntrack_info ctinfo; - - ct = nf_ct_get(skb, &ctinfo); - if (!ct) - return NF_ACCEPT; - - if (ctinfo == IP_CT_RELATED || ctinfo == IP_CT_RELATED_REPLY) { - if (ip_hdr(skb)->protocol == IPPROTO_ICMP) { - if (!nf_nat_icmp_reply_translation(skb, ct, ctinfo, - state->hook)) - return NF_DROP; - else - return NF_ACCEPT; - } - } - - return nf_nat_inet_fn(priv, skb, state); -} - -static unsigned int -nf_nat_ipv4_in(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state) -{ - unsigned int ret; - __be32 daddr = ip_hdr(skb)->daddr; - - ret = nf_nat_ipv4_fn(priv, skb, state); - if (ret != NF_DROP && ret != NF_STOLEN && - daddr != ip_hdr(skb)->daddr) - skb_dst_drop(skb); - - return ret; -} - -static unsigned int -nf_nat_ipv4_out(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state) -{ -#ifdef CONFIG_XFRM - const struct nf_conn *ct; - enum ip_conntrack_info ctinfo; - int err; -#endif - unsigned int ret; - - ret = nf_nat_ipv4_fn(priv, skb, state); -#ifdef CONFIG_XFRM - if (ret != NF_DROP && ret != NF_STOLEN && - !(IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED) && - (ct = nf_ct_get(skb, &ctinfo)) != NULL) { - enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); - - if ((ct->tuplehash[dir].tuple.src.u3.ip != - ct->tuplehash[!dir].tuple.dst.u3.ip) || - (ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMP && - ct->tuplehash[dir].tuple.src.u.all != - ct->tuplehash[!dir].tuple.dst.u.all)) { - err = nf_xfrm_me_harder(state->net, skb, AF_INET); - if (err < 0) - ret = NF_DROP_ERR(err); - } - } -#endif - return ret; -} - -static unsigned int -nf_nat_ipv4_local_fn(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state) -{ - const struct nf_conn *ct; - enum ip_conntrack_info ctinfo; - unsigned int ret; - int err; - - ret = nf_nat_ipv4_fn(priv, skb, state); - if (ret != NF_DROP && ret != NF_STOLEN && - (ct = nf_ct_get(skb, &ctinfo)) != NULL) { - enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); - - if (ct->tuplehash[dir].tuple.dst.u3.ip != - ct->tuplehash[!dir].tuple.src.u3.ip) { - err = ip_route_me_harder(state->net, skb, RTN_UNSPEC); - if (err < 0) - ret = NF_DROP_ERR(err); - } -#ifdef CONFIG_XFRM - else if (!(IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED) && - ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMP && - ct->tuplehash[dir].tuple.dst.u.all != - ct->tuplehash[!dir].tuple.src.u.all) { - err = nf_xfrm_me_harder(state->net, skb, AF_INET); - if (err < 0) - ret = NF_DROP_ERR(err); - } -#endif - } - return ret; -} - -static const struct nf_hook_ops nf_nat_ipv4_ops[] = { - /* Before packet filtering, change destination */ - { - .hook = nf_nat_ipv4_in, - .pf = NFPROTO_IPV4, - .hooknum = NF_INET_PRE_ROUTING, - .priority = NF_IP_PRI_NAT_DST, - }, - /* After packet filtering, change source */ - { - .hook = nf_nat_ipv4_out, - .pf = NFPROTO_IPV4, - .hooknum = NF_INET_POST_ROUTING, - .priority = NF_IP_PRI_NAT_SRC, - }, - /* Before packet filtering, change destination */ - { - .hook = nf_nat_ipv4_local_fn, - .pf = NFPROTO_IPV4, - .hooknum = NF_INET_LOCAL_OUT, - .priority = NF_IP_PRI_NAT_DST, - }, - /* After packet filtering, change source */ - { - .hook = nf_nat_ipv4_fn, - .pf = NFPROTO_IPV4, - .hooknum = NF_INET_LOCAL_IN, - .priority = NF_IP_PRI_NAT_SRC, - }, -}; - -int nf_nat_l3proto_ipv4_register_fn(struct net *net, const struct nf_hook_ops *ops) -{ - return nf_nat_register_fn(net, ops, nf_nat_ipv4_ops, ARRAY_SIZE(nf_nat_ipv4_ops)); -} -EXPORT_SYMBOL_GPL(nf_nat_l3proto_ipv4_register_fn); - -void nf_nat_l3proto_ipv4_unregister_fn(struct net *net, const struct nf_hook_ops *ops) -{ - nf_nat_unregister_fn(net, ops, ARRAY_SIZE(nf_nat_ipv4_ops)); -} -EXPORT_SYMBOL_GPL(nf_nat_l3proto_ipv4_unregister_fn); - -static int __init nf_nat_l3proto_ipv4_init(void) -{ - return nf_nat_l3proto_register(&nf_nat_l3proto_ipv4); -} - -static void __exit nf_nat_l3proto_ipv4_exit(void) -{ - nf_nat_l3proto_unregister(&nf_nat_l3proto_ipv4); -} - -MODULE_LICENSE("GPL"); -MODULE_ALIAS("nf-nat-" __stringify(AF_INET)); - -module_init(nf_nat_l3proto_ipv4_init); -module_exit(nf_nat_l3proto_ipv4_exit); diff --git a/net/ipv4/netfilter/nft_chain_nat_ipv4.c b/net/ipv4/netfilter/nft_chain_nat_ipv4.c deleted file mode 100644 index a3c4ea303e3e..000000000000 --- a/net/ipv4/netfilter/nft_chain_nat_ipv4.c +++ /dev/null @@ -1,87 +0,0 @@ -/* - * Copyright (c) 2008-2009 Patrick McHardy <kaber@trash.net> - * Copyright (c) 2012 Pablo Neira Ayuso <pablo@netfilter.org> - * Copyright (c) 2012 Intel Corporation - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * Development of this code funded by Astaro AG (http://www.astaro.com/) - */ - -#include <linux/module.h> -#include <linux/init.h> -#include <linux/list.h> -#include <linux/skbuff.h> -#include <linux/ip.h> -#include <linux/netfilter.h> -#include <linux/netfilter_ipv4.h> -#include <linux/netfilter/nf_tables.h> -#include <net/netfilter/nf_conntrack.h> -#include <net/netfilter/nf_nat.h> -#include <net/netfilter/nf_nat_core.h> -#include <net/netfilter/nf_tables.h> -#include <net/netfilter/nf_tables_ipv4.h> -#include <net/netfilter/nf_nat_l3proto.h> -#include <net/ip.h> - -static unsigned int nft_nat_do_chain(void *priv, - struct sk_buff *skb, - const struct nf_hook_state *state) -{ - struct nft_pktinfo pkt; - - nft_set_pktinfo(&pkt, skb, state); - nft_set_pktinfo_ipv4(&pkt, skb); - - return nft_do_chain(&pkt, priv); -} - -static int nft_nat_ipv4_reg(struct net *net, const struct nf_hook_ops *ops) -{ - return nf_nat_l3proto_ipv4_register_fn(net, ops); -} - -static void nft_nat_ipv4_unreg(struct net *net, const struct nf_hook_ops *ops) -{ - nf_nat_l3proto_ipv4_unregister_fn(net, ops); -} - -static const struct nft_chain_type nft_chain_nat_ipv4 = { - .name = "nat", - .type = NFT_CHAIN_T_NAT, - .family = NFPROTO_IPV4, - .owner = THIS_MODULE, - .hook_mask = (1 << NF_INET_PRE_ROUTING) | - (1 << NF_INET_POST_ROUTING) | - (1 << NF_INET_LOCAL_OUT) | - (1 << NF_INET_LOCAL_IN), - .hooks = { - [NF_INET_PRE_ROUTING] = nft_nat_do_chain, - [NF_INET_POST_ROUTING] = nft_nat_do_chain, - [NF_INET_LOCAL_OUT] = nft_nat_do_chain, - [NF_INET_LOCAL_IN] = nft_nat_do_chain, - }, - .ops_register = nft_nat_ipv4_reg, - .ops_unregister = nft_nat_ipv4_unreg, -}; - -static int __init nft_chain_nat_init(void) -{ - nft_register_chain_type(&nft_chain_nat_ipv4); - - return 0; -} - -static void __exit nft_chain_nat_exit(void) -{ - nft_unregister_chain_type(&nft_chain_nat_ipv4); -} - -module_init(nft_chain_nat_init); -module_exit(nft_chain_nat_exit); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); -MODULE_ALIAS_NFT_CHAIN(AF_INET, "nat"); diff --git a/net/ipv4/netfilter/nft_masq_ipv4.c b/net/ipv4/netfilter/nft_masq_ipv4.c deleted file mode 100644 index 6847de1d1db8..000000000000 --- a/net/ipv4/netfilter/nft_masq_ipv4.c +++ /dev/null @@ -1,90 +0,0 @@ -/* - * Copyright (c) 2014 Arturo Borrero Gonzalez <arturo@debian.org> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#include <linux/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_masq.h> -#include <net/netfilter/ipv4/nf_nat_masquerade.h> - -static void nft_masq_ipv4_eval(const struct nft_expr *expr, - struct nft_regs *regs, - const struct nft_pktinfo *pkt) -{ - struct nft_masq *priv = nft_expr_priv(expr); - struct nf_nat_range2 range; - - memset(&range, 0, sizeof(range)); - range.flags = priv->flags; - if (priv->sreg_proto_min) { - range.min_proto.all = (__force __be16)nft_reg_load16( - ®s->data[priv->sreg_proto_min]); - range.max_proto.all = (__force __be16)nft_reg_load16( - ®s->data[priv->sreg_proto_max]); - } - regs->verdict.code = nf_nat_masquerade_ipv4(pkt->skb, nft_hook(pkt), - &range, nft_out(pkt)); -} - -static void -nft_masq_ipv4_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr) -{ - nf_ct_netns_put(ctx->net, NFPROTO_IPV4); -} - -static struct nft_expr_type nft_masq_ipv4_type; -static const struct nft_expr_ops nft_masq_ipv4_ops = { - .type = &nft_masq_ipv4_type, - .size = NFT_EXPR_SIZE(sizeof(struct nft_masq)), - .eval = nft_masq_ipv4_eval, - .init = nft_masq_init, - .destroy = nft_masq_ipv4_destroy, - .dump = nft_masq_dump, - .validate = nft_masq_validate, -}; - -static struct nft_expr_type nft_masq_ipv4_type __read_mostly = { - .family = NFPROTO_IPV4, - .name = "masq", - .ops = &nft_masq_ipv4_ops, - .policy = nft_masq_policy, - .maxattr = NFTA_MASQ_MAX, - .owner = THIS_MODULE, -}; - -static int __init nft_masq_ipv4_module_init(void) -{ - int ret; - - ret = nft_register_expr(&nft_masq_ipv4_type); - if (ret < 0) - return ret; - - ret = nf_nat_masquerade_ipv4_register_notifier(); - if (ret) - nft_unregister_expr(&nft_masq_ipv4_type); - - return ret; -} - -static void __exit nft_masq_ipv4_module_exit(void) -{ - nft_unregister_expr(&nft_masq_ipv4_type); - nf_nat_masquerade_ipv4_unregister_notifier(); -} - -module_init(nft_masq_ipv4_module_init); -module_exit(nft_masq_ipv4_module_exit); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Arturo Borrero Gonzalez <arturo@debian.org"); -MODULE_ALIAS_NFT_AF_EXPR(AF_INET, "masq"); diff --git a/net/ipv4/netfilter/nft_redir_ipv4.c b/net/ipv4/netfilter/nft_redir_ipv4.c deleted file mode 100644 index 5120be1d3118..000000000000 --- a/net/ipv4/netfilter/nft_redir_ipv4.c +++ /dev/null @@ -1,82 +0,0 @@ -/* - * Copyright (c) 2014 Arturo Borrero Gonzalez <arturo@debian.org> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#include <linux/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/nf_nat.h> -#include <net/netfilter/nf_nat_redirect.h> -#include <net/netfilter/nft_redir.h> - -static void nft_redir_ipv4_eval(const struct nft_expr *expr, - struct nft_regs *regs, - const struct nft_pktinfo *pkt) -{ - struct nft_redir *priv = nft_expr_priv(expr); - struct nf_nat_ipv4_multi_range_compat mr; - - memset(&mr, 0, sizeof(mr)); - if (priv->sreg_proto_min) { - mr.range[0].min.all = (__force __be16)nft_reg_load16( - ®s->data[priv->sreg_proto_min]); - mr.range[0].max.all = (__force __be16)nft_reg_load16( - ®s->data[priv->sreg_proto_max]); - mr.range[0].flags |= NF_NAT_RANGE_PROTO_SPECIFIED; - } - - mr.range[0].flags |= priv->flags; - - regs->verdict.code = nf_nat_redirect_ipv4(pkt->skb, &mr, nft_hook(pkt)); -} - -static void -nft_redir_ipv4_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr) -{ - nf_ct_netns_put(ctx->net, NFPROTO_IPV4); -} - -static struct nft_expr_type nft_redir_ipv4_type; -static const struct nft_expr_ops nft_redir_ipv4_ops = { - .type = &nft_redir_ipv4_type, - .size = NFT_EXPR_SIZE(sizeof(struct nft_redir)), - .eval = nft_redir_ipv4_eval, - .init = nft_redir_init, - .destroy = nft_redir_ipv4_destroy, - .dump = nft_redir_dump, - .validate = nft_redir_validate, -}; - -static struct nft_expr_type nft_redir_ipv4_type __read_mostly = { - .family = NFPROTO_IPV4, - .name = "redir", - .ops = &nft_redir_ipv4_ops, - .policy = nft_redir_policy, - .maxattr = NFTA_REDIR_MAX, - .owner = THIS_MODULE, -}; - -static int __init nft_redir_ipv4_module_init(void) -{ - return nft_register_expr(&nft_redir_ipv4_type); -} - -static void __exit nft_redir_ipv4_module_exit(void) -{ - nft_unregister_expr(&nft_redir_ipv4_type); -} - -module_init(nft_redir_ipv4_module_init); -module_exit(nft_redir_ipv4_module_exit); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Arturo Borrero Gonzalez <arturo@debian.org>"); -MODULE_ALIAS_NFT_AF_EXPR(AF_INET, "redir"); diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig index 339d0762b027..ddc99a1653aa 100644 --- a/net/ipv6/netfilter/Kconfig +++ b/net/ipv6/netfilter/Kconfig @@ -31,34 +31,6 @@ config NFT_CHAIN_ROUTE_IPV6 fields such as the source, destination, flowlabel, hop-limit and the packet mark. -if NF_NAT_IPV6 - -config NFT_CHAIN_NAT_IPV6 - tristate "IPv6 nf_tables nat chain support" - help - This option enables the "nat" chain for IPv6 in nf_tables. This - chain type is used to perform Network Address Translation (NAT) - packet transformations such as the source, destination address and - source and destination ports. - -config NFT_MASQ_IPV6 - tristate "IPv6 masquerade support for nf_tables" - depends on NFT_MASQ - select NF_NAT_MASQUERADE_IPV6 - help - This is the expression that provides IPv4 masquerading support for - nf_tables. - -config NFT_REDIR_IPV6 - tristate "IPv6 redirect support for nf_tables" - depends on NFT_REDIR - select NF_NAT_REDIRECT - help - This is the expression that provides IPv4 redirect support for - nf_tables. - -endif # NF_NAT_IPV6 - config NFT_REJECT_IPV6 select NF_REJECT_IPV6 default NFT_REJECT @@ -106,23 +78,6 @@ config NF_LOG_IPV6 default m if NETFILTER_ADVANCED=n select NF_LOG_COMMON -config NF_NAT_IPV6 - tristate "IPv6 NAT" - depends on NF_CONNTRACK - depends on NETFILTER_ADVANCED - select NF_NAT - help - The IPv6 NAT option allows masquerading, port forwarding and other - forms of full Network Address Port Translation. This can be - controlled by iptables or nft. - -if NF_NAT_IPV6 - -config NF_NAT_MASQUERADE_IPV6 - bool - -endif # NF_NAT_IPV6 - config IP6_NF_IPTABLES tristate "IP6 tables support (required for filtering)" depends on INET && IPV6 @@ -311,7 +266,6 @@ config IP6_NF_NAT depends on NF_CONNTRACK depends on NETFILTER_ADVANCED select NF_NAT - select NF_NAT_IPV6 select NETFILTER_XT_NAT help This enables the `nat' table in ip6tables. This allows masquerading, @@ -324,7 +278,7 @@ if IP6_NF_NAT config IP6_NF_TARGET_MASQUERADE tristate "MASQUERADE target support" - select NF_NAT_MASQUERADE_IPV6 + select NF_NAT_MASQUERADE help Masquerading is a special case of NAT: all outgoing connections are changed to seem to come from a particular interface's address, and diff --git a/net/ipv6/netfilter/Makefile b/net/ipv6/netfilter/Makefile index 9ea43d5256e0..3853c648ebaa 100644 --- a/net/ipv6/netfilter/Makefile +++ b/net/ipv6/netfilter/Makefile @@ -11,10 +11,6 @@ obj-$(CONFIG_IP6_NF_RAW) += ip6table_raw.o obj-$(CONFIG_IP6_NF_SECURITY) += ip6table_security.o obj-$(CONFIG_IP6_NF_NAT) += ip6table_nat.o -nf_nat_ipv6-y := nf_nat_l3proto_ipv6.o -nf_nat_ipv6-$(CONFIG_NF_NAT_MASQUERADE_IPV6) += nf_nat_masquerade_ipv6.o -obj-$(CONFIG_NF_NAT_IPV6) += nf_nat_ipv6.o - # defrag nf_defrag_ipv6-y := nf_defrag_ipv6_hooks.o nf_conntrack_reasm.o obj-$(CONFIG_NF_DEFRAG_IPV6) += nf_defrag_ipv6.o @@ -32,10 +28,7 @@ obj-$(CONFIG_NF_DUP_IPV6) += nf_dup_ipv6.o # nf_tables obj-$(CONFIG_NFT_CHAIN_ROUTE_IPV6) += nft_chain_route_ipv6.o -obj-$(CONFIG_NFT_CHAIN_NAT_IPV6) += nft_chain_nat_ipv6.o obj-$(CONFIG_NFT_REJECT_IPV6) += nft_reject_ipv6.o -obj-$(CONFIG_NFT_MASQ_IPV6) += nft_masq_ipv6.o -obj-$(CONFIG_NFT_REDIR_IPV6) += nft_redir_ipv6.o obj-$(CONFIG_NFT_DUP_IPV6) += nft_dup_ipv6.o obj-$(CONFIG_NFT_FIB_IPV6) += nft_fib_ipv6.o diff --git a/net/ipv6/netfilter/ip6table_nat.c b/net/ipv6/netfilter/ip6table_nat.c index 67ba70ab9f5c..3e1fab9d7503 100644 --- a/net/ipv6/netfilter/ip6table_nat.c +++ b/net/ipv6/netfilter/ip6table_nat.c @@ -17,8 +17,6 @@ #include <net/ipv6.h> #include <net/netfilter/nf_nat.h> -#include <net/netfilter/nf_nat_core.h> -#include <net/netfilter/nf_nat_l3proto.h> static int __net_init ip6table_nat_table_init(struct net *net); @@ -72,10 +70,10 @@ static int ip6t_nat_register_lookups(struct net *net) int i, ret; for (i = 0; i < ARRAY_SIZE(nf_nat_ipv6_ops); i++) { - ret = nf_nat_l3proto_ipv6_register_fn(net, &nf_nat_ipv6_ops[i]); + ret = nf_nat_ipv6_register_fn(net, &nf_nat_ipv6_ops[i]); if (ret) { while (i) - nf_nat_l3proto_ipv6_unregister_fn(net, &nf_nat_ipv6_ops[--i]); + nf_nat_ipv6_unregister_fn(net, &nf_nat_ipv6_ops[--i]); return ret; } @@ -89,7 +87,7 @@ static void ip6t_nat_unregister_lookups(struct net *net) int i; for (i = 0; i < ARRAY_SIZE(nf_nat_ipv6_ops); i++) - nf_nat_l3proto_ipv6_unregister_fn(net, &nf_nat_ipv6_ops[i]); + nf_nat_ipv6_unregister_fn(net, &nf_nat_ipv6_ops[i]); } static int __net_init ip6table_nat_table_init(struct net *net) diff --git a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c deleted file mode 100644 index 490bfd3c9162..000000000000 --- a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c +++ /dev/null @@ -1,427 +0,0 @@ -/* - * Copyright (c) 2011 Patrick McHardy <kaber@trash.net> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * Development of IPv6 NAT funded by Astaro. - */ -#include <linux/types.h> -#include <linux/module.h> -#include <linux/skbuff.h> -#include <linux/ipv6.h> -#include <linux/netfilter.h> -#include <linux/netfilter_ipv6.h> -#include <net/secure_seq.h> -#include <net/checksum.h> -#include <net/ip6_checksum.h> -#include <net/ip6_route.h> -#include <net/xfrm.h> -#include <net/ipv6.h> - -#include <net/netfilter/nf_conntrack_core.h> -#include <net/netfilter/nf_conntrack.h> -#include <net/netfilter/nf_nat_core.h> -#include <net/netfilter/nf_nat_l3proto.h> -#include <net/netfilter/nf_nat_l4proto.h> - -static const struct nf_nat_l3proto nf_nat_l3proto_ipv6; - -#ifdef CONFIG_XFRM -static void nf_nat_ipv6_decode_session(struct sk_buff *skb, - const struct nf_conn *ct, - enum ip_conntrack_dir dir, - unsigned long statusbit, - struct flowi *fl) -{ - const struct nf_conntrack_tuple *t = &ct->tuplehash[dir].tuple; - struct flowi6 *fl6 = &fl->u.ip6; - - if (ct->status & statusbit) { - fl6->daddr = t->dst.u3.in6; - if (t->dst.protonum == IPPROTO_TCP || - t->dst.protonum == IPPROTO_UDP || - t->dst.protonum == IPPROTO_UDPLITE || - t->dst.protonum == IPPROTO_DCCP || - t->dst.protonum == IPPROTO_SCTP) - fl6->fl6_dport = t->dst.u.all; - } - - statusbit ^= IPS_NAT_MASK; - - if (ct->status & statusbit) { - fl6->saddr = t->src.u3.in6; - if (t->dst.protonum == IPPROTO_TCP || - t->dst.protonum == IPPROTO_UDP || - t->dst.protonum == IPPROTO_UDPLITE || - t->dst.protonum == IPPROTO_DCCP || - t->dst.protonum == IPPROTO_SCTP) - fl6->fl6_sport = t->src.u.all; - } -} -#endif - -static bool nf_nat_ipv6_manip_pkt(struct sk_buff *skb, - unsigned int iphdroff, - const struct nf_conntrack_tuple *target, - enum nf_nat_manip_type maniptype) -{ - struct ipv6hdr *ipv6h; - __be16 frag_off; - int hdroff; - u8 nexthdr; - - if (!skb_make_writable(skb, iphdroff + sizeof(*ipv6h))) - return false; - - ipv6h = (void *)skb->data + iphdroff; - nexthdr = ipv6h->nexthdr; - hdroff = ipv6_skip_exthdr(skb, iphdroff + sizeof(*ipv6h), - &nexthdr, &frag_off); - if (hdroff < 0) - goto manip_addr; - - if ((frag_off & htons(~0x7)) == 0 && - !nf_nat_l4proto_manip_pkt(skb, &nf_nat_l3proto_ipv6, iphdroff, hdroff, - target, maniptype)) - return false; - - /* must reload, offset might have changed */ - ipv6h = (void *)skb->data + iphdroff; - -manip_addr: - if (maniptype == NF_NAT_MANIP_SRC) - ipv6h->saddr = target->src.u3.in6; - else - ipv6h->daddr = target->dst.u3.in6; - - return true; -} - -static void nf_nat_ipv6_csum_update(struct sk_buff *skb, - unsigned int iphdroff, __sum16 *check, - const struct nf_conntrack_tuple *t, - enum nf_nat_manip_type maniptype) -{ - const struct ipv6hdr *ipv6h = (struct ipv6hdr *)(skb->data + iphdroff); - const struct in6_addr *oldip, *newip; - - if (maniptype == NF_NAT_MANIP_SRC) { - oldip = &ipv6h->saddr; - newip = &t->src.u3.in6; - } else { - oldip = &ipv6h->daddr; - newip = &t->dst.u3.in6; - } - inet_proto_csum_replace16(check, skb, oldip->s6_addr32, - newip->s6_addr32, true); -} - -static void nf_nat_ipv6_csum_recalc(struct sk_buff *skb, - u8 proto, void *data, __sum16 *check, - int datalen, int oldlen) -{ - if (skb->ip_summed != CHECKSUM_PARTIAL) { - const struct ipv6hdr *ipv6h = ipv6_hdr(skb); - - skb->ip_summed = CHECKSUM_PARTIAL; - skb->csum_start = skb_headroom(skb) + skb_network_offset(skb) + - (data - (void *)skb->data); - skb->csum_offset = (void *)check - data; - *check = ~csum_ipv6_magic(&ipv6h->saddr, &ipv6h->daddr, - datalen, proto, 0); - } else - inet_proto_csum_replace2(check, skb, - htons(oldlen), htons(datalen), true); -} - -#if IS_ENABLED(CONFIG_NF_CT_NETLINK) -static int nf_nat_ipv6_nlattr_to_range(struct nlattr *tb[], - struct nf_nat_range2 *range) -{ - if (tb[CTA_NAT_V6_MINIP]) { - nla_memcpy(&range->min_addr.ip6, tb[CTA_NAT_V6_MINIP], - sizeof(struct in6_addr)); - range->flags |= NF_NAT_RANGE_MAP_IPS; - } - - if (tb[CTA_NAT_V6_MAXIP]) - nla_memcpy(&range->max_addr.ip6, tb[CTA_NAT_V6_MAXIP], - sizeof(struct in6_addr)); - else - range->max_addr = range->min_addr; - - return 0; -} -#endif - -static const struct nf_nat_l3proto nf_nat_l3proto_ipv6 = { - .l3proto = NFPROTO_IPV6, - .manip_pkt = nf_nat_ipv6_manip_pkt, - .csum_update = nf_nat_ipv6_csum_update, - .csum_recalc = nf_nat_ipv6_csum_recalc, -#if IS_ENABLED(CONFIG_NF_CT_NETLINK) - .nlattr_to_range = nf_nat_ipv6_nlattr_to_range, -#endif -#ifdef CONFIG_XFRM - .decode_session = nf_nat_ipv6_decode_session, -#endif -}; - -int nf_nat_icmpv6_reply_translation(struct sk_buff *skb, - struct nf_conn *ct, - enum ip_conntrack_info ctinfo, - unsigned int hooknum, - unsigned int hdrlen) -{ - struct { - struct icmp6hdr icmp6; - struct ipv6hdr ip6; - } *inside; - enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); - enum nf_nat_manip_type manip = HOOK2MANIP(hooknum); - struct nf_conntrack_tuple target; - unsigned long statusbit; - - WARN_ON(ctinfo != IP_CT_RELATED && ctinfo != IP_CT_RELATED_REPLY); - - if (!skb_make_writable(skb, hdrlen + sizeof(*inside))) - return 0; - if (nf_ip6_checksum(skb, hooknum, hdrlen, IPPROTO_ICMPV6)) - return 0; - - inside = (void *)skb->data + hdrlen; - if (inside->icmp6.icmp6_type == NDISC_REDIRECT) { - if ((ct->status & IPS_NAT_DONE_MASK) != IPS_NAT_DONE_MASK) - return 0; - if (ct->status & IPS_NAT_MASK) - return 0; - } - - if (manip == NF_NAT_MANIP_SRC) - statusbit = IPS_SRC_NAT; - else - statusbit = IPS_DST_NAT; - - /* Invert if this is reply direction */ - if (dir == IP_CT_DIR_REPLY) - statusbit ^= IPS_NAT_MASK; - - if (!(ct->status & statusbit)) - return 1; - - if (!nf_nat_ipv6_manip_pkt(skb, hdrlen + sizeof(inside->icmp6), - &ct->tuplehash[!dir].tuple, !manip)) - return 0; - - if (skb->ip_summed != CHECKSUM_PARTIAL) { - struct ipv6hdr *ipv6h = ipv6_hdr(skb); - inside = (void *)skb->data + hdrlen; - inside->icmp6.icmp6_cksum = 0; - inside->icmp6.icmp6_cksum = - csum_ipv6_magic(&ipv6h->saddr, &ipv6h->daddr, - skb->len - hdrlen, IPPROTO_ICMPV6, - skb_checksum(skb, hdrlen, - skb->len - hdrlen, 0)); - } - - nf_ct_invert_tuple(&target, &ct->tuplehash[!dir].tuple); - target.dst.protonum = IPPROTO_ICMPV6; - if (!nf_nat_ipv6_manip_pkt(skb, 0, &target, manip)) - return 0; - - return 1; -} -EXPORT_SYMBOL_GPL(nf_nat_icmpv6_reply_translation); - -static unsigned int -nf_nat_ipv6_fn(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state) -{ - struct nf_conn *ct; - enum ip_conntrack_info ctinfo; - __be16 frag_off; - int hdrlen; - u8 nexthdr; - - ct = nf_ct_get(skb, &ctinfo); - /* Can't track? It's not due to stress, or conntrack would - * have dropped it. Hence it's the user's responsibilty to - * packet filter it out, or implement conntrack/NAT for that - * protocol. 8) --RR - */ - if (!ct) - return NF_ACCEPT; - - if (ctinfo == IP_CT_RELATED || ctinfo == IP_CT_RELATED_REPLY) { - nexthdr = ipv6_hdr(skb)->nexthdr; - hdrlen = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), - &nexthdr, &frag_off); - - if (hdrlen >= 0 && nexthdr == IPPROTO_ICMPV6) { - if (!nf_nat_icmpv6_reply_translation(skb, ct, ctinfo, - state->hook, - hdrlen)) - return NF_DROP; - else - return NF_ACCEPT; - } - } - - return nf_nat_inet_fn(priv, skb, state); -} - -static unsigned int -nf_nat_ipv6_in(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state) -{ - unsigned int ret; - struct in6_addr daddr = ipv6_hdr(skb)->daddr; - - ret = nf_nat_ipv6_fn(priv, skb, state); - if (ret != NF_DROP && ret != NF_STOLEN && - ipv6_addr_cmp(&daddr, &ipv6_hdr(skb)->daddr)) - skb_dst_drop(skb); - - return ret; -} - -static unsigned int -nf_nat_ipv6_out(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state) -{ -#ifdef CONFIG_XFRM - const struct nf_conn *ct; - enum ip_conntrack_info ctinfo; - int err; -#endif - unsigned int ret; - - ret = nf_nat_ipv6_fn(priv, skb, state); -#ifdef CONFIG_XFRM - if (ret != NF_DROP && ret != NF_STOLEN && - !(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) && - (ct = nf_ct_get(skb, &ctinfo)) != NULL) { - enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); - - if (!nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.src.u3, - &ct->tuplehash[!dir].tuple.dst.u3) || - (ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMPV6 && - ct->tuplehash[dir].tuple.src.u.all != - ct->tuplehash[!dir].tuple.dst.u.all)) { - err = nf_xfrm_me_harder(state->net, skb, AF_INET6); - if (err < 0) - ret = NF_DROP_ERR(err); - } - } -#endif - return ret; -} - -static int nat_route_me_harder(struct net *net, struct sk_buff *skb) -{ -#ifdef CONFIG_IPV6_MODULE - const struct nf_ipv6_ops *v6_ops = nf_get_ipv6_ops(); - - if (!v6_ops) - return -EHOSTUNREACH; - - return v6_ops->route_me_harder(net, skb); -#else - return ip6_route_me_harder(net, skb); -#endif -} - -static unsigned int -nf_nat_ipv6_local_fn(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state) -{ - const struct nf_conn *ct; - enum ip_conntrack_info ctinfo; - unsigned int ret; - int err; - - ret = nf_nat_ipv6_fn(priv, skb, state); - if (ret != NF_DROP && ret != NF_STOLEN && - (ct = nf_ct_get(skb, &ctinfo)) != NULL) { - enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); - - if (!nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.dst.u3, - &ct->tuplehash[!dir].tuple.src.u3)) { - err = nat_route_me_harder(state->net, skb); - if (err < 0) - ret = NF_DROP_ERR(err); - } -#ifdef CONFIG_XFRM - else if (!(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) && - ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMPV6 && - ct->tuplehash[dir].tuple.dst.u.all != - ct->tuplehash[!dir].tuple.src.u.all) { - err = nf_xfrm_me_harder(state->net, skb, AF_INET6); - if (err < 0) - ret = NF_DROP_ERR(err); - } -#endif - } - return ret; -} - -static const struct nf_hook_ops nf_nat_ipv6_ops[] = { - /* Before packet filtering, change destination */ - { - .hook = nf_nat_ipv6_in, - .pf = NFPROTO_IPV6, - .hooknum = NF_INET_PRE_ROUTING, - .priority = NF_IP6_PRI_NAT_DST, - }, - /* After packet filtering, change source */ - { - .hook = nf_nat_ipv6_out, - .pf = NFPROTO_IPV6, - .hooknum = NF_INET_POST_ROUTING, - .priority = NF_IP6_PRI_NAT_SRC, - }, - /* Before packet filtering, change destination */ - { - .hook = nf_nat_ipv6_local_fn, - .pf = NFPROTO_IPV6, - .hooknum = NF_INET_LOCAL_OUT, - .priority = NF_IP6_PRI_NAT_DST, - }, - /* After packet filtering, change source */ - { - .hook = nf_nat_ipv6_fn, - .pf = NFPROTO_IPV6, - .hooknum = NF_INET_LOCAL_IN, - .priority = NF_IP6_PRI_NAT_SRC, - }, -}; - -int nf_nat_l3proto_ipv6_register_fn(struct net *net, const struct nf_hook_ops *ops) -{ - return nf_nat_register_fn(net, ops, nf_nat_ipv6_ops, ARRAY_SIZE(nf_nat_ipv6_ops)); -} -EXPORT_SYMBOL_GPL(nf_nat_l3proto_ipv6_register_fn); - -void nf_nat_l3proto_ipv6_unregister_fn(struct net *net, const struct nf_hook_ops *ops) -{ - nf_nat_unregister_fn(net, ops, ARRAY_SIZE(nf_nat_ipv6_ops)); -} -EXPORT_SYMBOL_GPL(nf_nat_l3proto_ipv6_unregister_fn); - -static int __init nf_nat_l3proto_ipv6_init(void) -{ - return nf_nat_l3proto_register(&nf_nat_l3proto_ipv6); -} - -static void __exit nf_nat_l3proto_ipv6_exit(void) -{ - nf_nat_l3proto_unregister(&nf_nat_l3proto_ipv6); -} - -MODULE_LICENSE("GPL"); -MODULE_ALIAS("nf-nat-" __stringify(AF_INET6)); - -module_init(nf_nat_l3proto_ipv6_init); -module_exit(nf_nat_l3proto_ipv6_exit); diff --git a/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c b/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c deleted file mode 100644 index fd313b726263..000000000000 --- a/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c +++ /dev/null @@ -1,240 +0,0 @@ -/* - * Copyright (c) 2011 Patrick McHardy <kaber@trash.net> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * Based on Rusty Russell's IPv6 MASQUERADE target. Development of IPv6 - * NAT funded by Astaro. - */ - -#include <linux/kernel.h> -#include <linux/atomic.h> -#include <linux/netdevice.h> -#include <linux/ipv6.h> -#include <linux/netfilter.h> -#include <linux/netfilter_ipv6.h> -#include <net/netfilter/nf_nat.h> -#include <net/addrconf.h> -#include <net/ipv6.h> -#include <net/netfilter/ipv6/nf_nat_masquerade.h> - -#define MAX_WORK_COUNT 16 - -static atomic_t v6_worker_count; - -static int -nat_ipv6_dev_get_saddr(struct net *net, const struct net_device *dev, - const struct in6_addr *daddr, unsigned int srcprefs, - struct in6_addr *saddr) -{ -#ifdef CONFIG_IPV6_MODULE - const struct nf_ipv6_ops *v6_ops = nf_get_ipv6_ops(); - - if (!v6_ops) - return -EHOSTUNREACH; - - return v6_ops->dev_get_saddr(net, dev, daddr, srcprefs, saddr); -#else - return ipv6_dev_get_saddr(net, dev, daddr, srcprefs, saddr); -#endif -} - -unsigned int -nf_nat_masquerade_ipv6(struct sk_buff *skb, const struct nf_nat_range2 *range, - const struct net_device *out) -{ - enum ip_conntrack_info ctinfo; - struct nf_conn_nat *nat; - struct in6_addr src; - struct nf_conn *ct; - struct nf_nat_range2 newrange; - - ct = nf_ct_get(skb, &ctinfo); - WARN_ON(!(ct && (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED || - ctinfo == IP_CT_RELATED_REPLY))); - - if (nat_ipv6_dev_get_saddr(nf_ct_net(ct), out, - &ipv6_hdr(skb)->daddr, 0, &src) < 0) - return NF_DROP; - - nat = nf_ct_nat_ext_add(ct); - if (nat) - nat->masq_index = out->ifindex; - - newrange.flags = range->flags | NF_NAT_RANGE_MAP_IPS; - newrange.min_addr.in6 = src; - newrange.max_addr.in6 = src; - newrange.min_proto = range->min_proto; - newrange.max_proto = range->max_proto; - - return nf_nat_setup_info(ct, &newrange, NF_NAT_MANIP_SRC); -} -EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv6); - -static int device_cmp(struct nf_conn *ct, void *ifindex) -{ - const struct nf_conn_nat *nat = nfct_nat(ct); - - if (!nat) - return 0; - if (nf_ct_l3num(ct) != NFPROTO_IPV6) - return 0; - return nat->masq_index == (int)(long)ifindex; -} - -static int masq_device_event(struct notifier_block *this, - unsigned long event, void *ptr) -{ - const struct net_device *dev = netdev_notifier_info_to_dev(ptr); - struct net *net = dev_net(dev); - - if (event == NETDEV_DOWN) - nf_ct_iterate_cleanup_net(net, device_cmp, - (void *)(long)dev->ifindex, 0, 0); - - return NOTIFY_DONE; -} - -static struct notifier_block masq_dev_notifier = { - .notifier_call = masq_device_event, -}; - -struct masq_dev_work { - struct work_struct work; - struct net *net; - struct in6_addr addr; - int ifindex; -}; - -static int inet_cmp(struct nf_conn *ct, void *work) -{ - struct masq_dev_work *w = (struct masq_dev_work *)work; - struct nf_conntrack_tuple *tuple; - - if (!device_cmp(ct, (void *)(long)w->ifindex)) - return 0; - - tuple = &ct->tuplehash[IP_CT_DIR_REPLY].tuple; - - return ipv6_addr_equal(&w->addr, &tuple->dst.u3.in6); -} - -static void iterate_cleanup_work(struct work_struct *work) -{ - struct masq_dev_work *w; - - w = container_of(work, struct masq_dev_work, work); - - nf_ct_iterate_cleanup_net(w->net, inet_cmp, (void *)w, 0, 0); - - put_net(w->net); - kfree(w); - atomic_dec(&v6_worker_count); - module_put(THIS_MODULE); -} - -/* ipv6 inet notifier is an atomic notifier, i.e. we cannot - * schedule. - * - * Unfortunately, nf_ct_iterate_cleanup_net can run for a long - * time if there are lots of conntracks and the system - * handles high softirq load, so it frequently calls cond_resched - * while iterating the conntrack table. - * - * So we defer nf_ct_iterate_cleanup_net walk to the system workqueue. - * - * As we can have 'a lot' of inet_events (depending on amount - * of ipv6 addresses being deleted), we also need to add an upper - * limit to the number of queued work items. - */ -static int masq_inet6_event(struct notifier_block *this, - unsigned long event, void *ptr) -{ - struct inet6_ifaddr *ifa = ptr; - const struct net_device *dev; - struct masq_dev_work *w; - struct net *net; - - if (event != NETDEV_DOWN || - atomic_read(&v6_worker_count) >= MAX_WORK_COUNT) - return NOTIFY_DONE; - - dev = ifa->idev->dev; - net = maybe_get_net(dev_net(dev)); - if (!net) - return NOTIFY_DONE; - - if (!try_module_get(THIS_MODULE)) - goto err_module; - - w = kmalloc(sizeof(*w), GFP_ATOMIC); - if (w) { - atomic_inc(&v6_worker_count); - - INIT_WORK(&w->work, iterate_cleanup_work); - w->ifindex = dev->ifindex; - w->net = net; - w->addr = ifa->addr; - schedule_work(&w->work); - - return NOTIFY_DONE; - } - - module_put(THIS_MODULE); - err_module: - put_net(net); - return NOTIFY_DONE; -} - -static struct notifier_block masq_inet6_notifier = { - .notifier_call = masq_inet6_event, -}; - -static int masq_refcnt; -static DEFINE_MUTEX(masq_mutex); - -int nf_nat_masquerade_ipv6_register_notifier(void) -{ - int ret = 0; - - mutex_lock(&masq_mutex); - /* check if the notifier is already set */ - if (++masq_refcnt > 1) - goto out_unlock; - - ret = register_netdevice_notifier(&masq_dev_notifier); - if (ret) - goto err_dec; - - ret = register_inet6addr_notifier(&masq_inet6_notifier); - if (ret) - goto err_unregister; - - mutex_unlock(&masq_mutex); - return ret; - -err_unregister: - unregister_netdevice_notifier(&masq_dev_notifier); -err_dec: - masq_refcnt--; -out_unlock: - mutex_unlock(&masq_mutex); - return ret; -} -EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv6_register_notifier); - -void nf_nat_masquerade_ipv6_unregister_notifier(void) -{ - mutex_lock(&masq_mutex); - /* check if the notifier still has clients */ - if (--masq_refcnt > 0) - goto out_unlock; - - unregister_inet6addr_notifier(&masq_inet6_notifier); - unregister_netdevice_notifier(&masq_dev_notifier); -out_unlock: - mutex_unlock(&masq_mutex); -} -EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv6_unregister_notifier); diff --git a/net/ipv6/netfilter/nft_chain_nat_ipv6.c b/net/ipv6/netfilter/nft_chain_nat_ipv6.c deleted file mode 100644 index 8a081ad7d5db..000000000000 --- a/net/ipv6/netfilter/nft_chain_nat_ipv6.c +++ /dev/null @@ -1,85 +0,0 @@ -/* - * Copyright (c) 2011 Patrick McHardy <kaber@trash.net> - * Copyright (c) 2012 Intel Corporation - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - */ - -#include <linux/module.h> -#include <linux/init.h> -#include <linux/list.h> -#include <linux/skbuff.h> -#include <linux/ip.h> -#include <linux/netfilter.h> -#include <linux/netfilter_ipv6.h> -#include <linux/netfilter/nf_tables.h> -#include <net/netfilter/nf_conntrack.h> -#include <net/netfilter/nf_nat.h> -#include <net/netfilter/nf_nat_core.h> -#include <net/netfilter/nf_tables.h> -#include <net/netfilter/nf_tables_ipv6.h> -#include <net/netfilter/nf_nat_l3proto.h> -#include <net/ipv6.h> - -static unsigned int nft_nat_do_chain(void *priv, - struct sk_buff *skb, - const struct nf_hook_state *state) -{ - struct nft_pktinfo pkt; - - nft_set_pktinfo(&pkt, skb, state); - nft_set_pktinfo_ipv6(&pkt, skb); - - return nft_do_chain(&pkt, priv); -} - -static int nft_nat_ipv6_reg(struct net *net, const struct nf_hook_ops *ops) -{ - return nf_nat_l3proto_ipv6_register_fn(net, ops); -} - -static void nft_nat_ipv6_unreg(struct net *net, const struct nf_hook_ops *ops) -{ - nf_nat_l3proto_ipv6_unregister_fn(net, ops); -} - -static const struct nft_chain_type nft_chain_nat_ipv6 = { - .name = "nat", - .type = NFT_CHAIN_T_NAT, - .family = NFPROTO_IPV6, - .owner = THIS_MODULE, - .hook_mask = (1 << NF_INET_PRE_ROUTING) | - (1 << NF_INET_POST_ROUTING) | - (1 << NF_INET_LOCAL_OUT) | - (1 << NF_INET_LOCAL_IN), - .hooks = { - [NF_INET_PRE_ROUTING] = nft_nat_do_chain, - [NF_INET_POST_ROUTING] = nft_nat_do_chain, - [NF_INET_LOCAL_OUT] = nft_nat_do_chain, - [NF_INET_LOCAL_IN] = nft_nat_do_chain, - }, - .ops_register = nft_nat_ipv6_reg, - .ops_unregister = nft_nat_ipv6_unreg, -}; - -static int __init nft_chain_nat_ipv6_init(void) -{ - nft_register_chain_type(&nft_chain_nat_ipv6); - - return 0; -} - -static void __exit nft_chain_nat_ipv6_exit(void) -{ - nft_unregister_chain_type(&nft_chain_nat_ipv6); -} - -module_init(nft_chain_nat_ipv6_init); -module_exit(nft_chain_nat_ipv6_exit); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Tomasz Bursztyka <tomasz.bursztyka@linux.intel.com>"); -MODULE_ALIAS_NFT_CHAIN(AF_INET6, "nat"); diff --git a/net/ipv6/netfilter/nft_masq_ipv6.c b/net/ipv6/netfilter/nft_masq_ipv6.c deleted file mode 100644 index e06c82e9dfcd..000000000000 --- a/net/ipv6/netfilter/nft_masq_ipv6.c +++ /dev/null @@ -1,91 +0,0 @@ -/* - * Copyright (c) 2014 Arturo Borrero Gonzalez <arturo@debian.org> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#include <linux/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/nf_nat.h> -#include <net/netfilter/nft_masq.h> -#include <net/netfilter/ipv6/nf_nat_masquerade.h> - -static void nft_masq_ipv6_eval(const struct nft_expr *expr, - struct nft_regs *regs, - const struct nft_pktinfo *pkt) -{ - struct nft_masq *priv = nft_expr_priv(expr); - struct nf_nat_range2 range; - - memset(&range, 0, sizeof(range)); - range.flags = priv->flags; - if (priv->sreg_proto_min) { - range.min_proto.all = (__force __be16)nft_reg_load16( - ®s->data[priv->sreg_proto_min]); - range.max_proto.all = (__force __be16)nft_reg_load16( - ®s->data[priv->sreg_proto_max]); - } - regs->verdict.code = nf_nat_masquerade_ipv6(pkt->skb, &range, - nft_out(pkt)); -} - -static void -nft_masq_ipv6_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr) -{ - nf_ct_netns_put(ctx->net, NFPROTO_IPV6); -} - -static struct nft_expr_type nft_masq_ipv6_type; -static const struct nft_expr_ops nft_masq_ipv6_ops = { - .type = &nft_masq_ipv6_type, - .size = NFT_EXPR_SIZE(sizeof(struct nft_masq)), - .eval = nft_masq_ipv6_eval, - .init = nft_masq_init, - .destroy = nft_masq_ipv6_destroy, - .dump = nft_masq_dump, - .validate = nft_masq_validate, -}; - -static struct nft_expr_type nft_masq_ipv6_type __read_mostly = { - .family = NFPROTO_IPV6, - .name = "masq", - .ops = &nft_masq_ipv6_ops, - .policy = nft_masq_policy, - .maxattr = NFTA_MASQ_MAX, - .owner = THIS_MODULE, -}; - -static int __init nft_masq_ipv6_module_init(void) -{ - int ret; - - ret = nft_register_expr(&nft_masq_ipv6_type); - if (ret < 0) - return ret; - - ret = nf_nat_masquerade_ipv6_register_notifier(); - if (ret) - nft_unregister_expr(&nft_masq_ipv6_type); - - return ret; -} - -static void __exit nft_masq_ipv6_module_exit(void) -{ - nft_unregister_expr(&nft_masq_ipv6_type); - nf_nat_masquerade_ipv6_unregister_notifier(); -} - -module_init(nft_masq_ipv6_module_init); -module_exit(nft_masq_ipv6_module_exit); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Arturo Borrero Gonzalez <arturo@debian.org>"); -MODULE_ALIAS_NFT_AF_EXPR(AF_INET6, "masq"); diff --git a/net/ipv6/netfilter/nft_redir_ipv6.c b/net/ipv6/netfilter/nft_redir_ipv6.c deleted file mode 100644 index 74269865acc8..000000000000 --- a/net/ipv6/netfilter/nft_redir_ipv6.c +++ /dev/null @@ -1,83 +0,0 @@ -/* - * Copyright (c) 2014 Arturo Borrero Gonzalez <arturo@debian.org> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#include <linux/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/nf_nat.h> -#include <net/netfilter/nft_redir.h> -#include <net/netfilter/nf_nat_redirect.h> - -static void nft_redir_ipv6_eval(const struct nft_expr *expr, - struct nft_regs *regs, - const struct nft_pktinfo *pkt) -{ - struct nft_redir *priv = nft_expr_priv(expr); - struct nf_nat_range2 range; - - memset(&range, 0, sizeof(range)); - if (priv->sreg_proto_min) { - range.min_proto.all = (__force __be16)nft_reg_load16( - ®s->data[priv->sreg_proto_min]); - range.max_proto.all = (__force __be16)nft_reg_load16( - ®s->data[priv->sreg_proto_max]); - range.flags |= NF_NAT_RANGE_PROTO_SPECIFIED; - } - - range.flags |= priv->flags; - - regs->verdict.code = - nf_nat_redirect_ipv6(pkt->skb, &range, nft_hook(pkt)); -} - -static void -nft_redir_ipv6_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr) -{ - nf_ct_netns_put(ctx->net, NFPROTO_IPV6); -} - -static struct nft_expr_type nft_redir_ipv6_type; -static const struct nft_expr_ops nft_redir_ipv6_ops = { - .type = &nft_redir_ipv6_type, - .size = NFT_EXPR_SIZE(sizeof(struct nft_redir)), - .eval = nft_redir_ipv6_eval, - .init = nft_redir_init, - .destroy = nft_redir_ipv6_destroy, - .dump = nft_redir_dump, - .validate = nft_redir_validate, -}; - -static struct nft_expr_type nft_redir_ipv6_type __read_mostly = { - .family = NFPROTO_IPV6, - .name = "redir", - .ops = &nft_redir_ipv6_ops, - .policy = nft_redir_policy, - .maxattr = NFTA_REDIR_MAX, - .owner = THIS_MODULE, -}; - -static int __init nft_redir_ipv6_module_init(void) -{ - return nft_register_expr(&nft_redir_ipv6_type); -} - -static void __exit nft_redir_ipv6_module_exit(void) -{ - nft_unregister_expr(&nft_redir_ipv6_type); -} - -module_init(nft_redir_ipv6_module_init); -module_exit(nft_redir_ipv6_module_exit); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Arturo Borrero Gonzalez <arturo@debian.org>"); -MODULE_ALIAS_NFT_AF_EXPR(AF_INET6, "redir"); diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index fefd63a243f2..d43ffb09939b 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -396,7 +396,13 @@ config NETFILTER_NETLINK_GLUE_CT the enqueued via NFNETLINK. config NF_NAT - tristate + tristate "Network Address Translation support" + depends on NF_CONNTRACK + default m if NETFILTER_ADVANCED=n + help + The NAT option allows masquerading, port forwarding and other + forms of full Network Address Port Translation. This can be + controlled by iptables, ip6tables or nft. config NF_NAT_NEEDED bool @@ -431,6 +437,9 @@ config NF_NAT_TFTP config NF_NAT_REDIRECT bool +config NF_NAT_MASQUERADE + bool + config NETFILTER_SYNPROXY tristate @@ -523,6 +532,7 @@ config NFT_LIMIT config NFT_MASQ depends on NF_CONNTRACK depends on NF_NAT + select NF_NAT_MASQUERADE tristate "Netfilter nf_tables masquerade support" help This option adds the "masquerade" expression that you can use @@ -532,6 +542,7 @@ config NFT_REDIR depends on NF_CONNTRACK depends on NF_NAT tristate "Netfilter nf_tables redirect support" + select NF_NAT_REDIRECT help This options adds the "redirect" expression that you can use to perform NAT in the redirect flavour. @@ -539,6 +550,7 @@ config NFT_REDIR config NFT_NAT depends on NF_CONNTRACK select NF_NAT + depends on NF_TABLES_IPV4 || NF_TABLES_IPV6 tristate "Netfilter nf_tables nat module" help This option adds the "nat" expression that you can use to perform diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index e66067befa42..4894a85cdd0b 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -56,6 +56,7 @@ obj-$(CONFIG_NF_LOG_NETDEV) += nf_log_netdev.o obj-$(CONFIG_NF_NAT) += nf_nat.o nf_nat-$(CONFIG_NF_NAT_REDIRECT) += nf_nat_redirect.o +nf_nat-$(CONFIG_NF_NAT_MASQUERADE) += nf_nat_masquerade.o # NAT helpers obj-$(CONFIG_NF_NAT_AMANDA) += nf_nat_amanda.o @@ -109,6 +110,8 @@ obj-$(CONFIG_NFT_OSF) += nft_osf.o obj-$(CONFIG_NFT_TPROXY) += nft_tproxy.o obj-$(CONFIG_NFT_XFRM) += nft_xfrm.o +obj-$(CONFIG_NFT_NAT) += nft_chain_nat.o + # nf_tables netdev obj-$(CONFIG_NFT_DUP_NETDEV) += nft_dup_netdev.o obj-$(CONFIG_NFT_FWD_NETDEV) += nft_fwd_netdev.o diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 2a3d4e27cf3b..053cd96b9c76 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -3086,7 +3086,7 @@ static bool ip_vs_is_af_valid(int af) static int ip_vs_genl_parse_service(struct netns_ipvs *ipvs, struct ip_vs_service_user_kern *usvc, - struct nlattr *nla, int full_entry, + struct nlattr *nla, bool full_entry, struct ip_vs_service **ret_svc) { struct nlattr *attrs[IPVS_SVC_ATTR_MAX + 1]; @@ -3173,7 +3173,7 @@ static struct ip_vs_service *ip_vs_genl_find_service(struct netns_ipvs *ipvs, struct ip_vs_service *svc; int ret; - ret = ip_vs_genl_parse_service(ipvs, &usvc, nla, 0, &svc); + ret = ip_vs_genl_parse_service(ipvs, &usvc, nla, false, &svc); return ret ? ERR_PTR(ret) : svc; } @@ -3283,7 +3283,7 @@ out_err: } static int ip_vs_genl_parse_dest(struct ip_vs_dest_user_kern *udest, - struct nlattr *nla, int full_entry) + struct nlattr *nla, bool full_entry) { struct nlattr *attrs[IPVS_DEST_ATTR_MAX + 1]; struct nlattr *nla_addr, *nla_port; @@ -3545,11 +3545,11 @@ out: static int ip_vs_genl_set_cmd(struct sk_buff *skb, struct genl_info *info) { + bool need_full_svc = false, need_full_dest = false; struct ip_vs_service *svc = NULL; struct ip_vs_service_user_kern usvc; struct ip_vs_dest_user_kern udest; int ret = 0, cmd; - int need_full_svc = 0, need_full_dest = 0; struct net *net = sock_net(skb->sk); struct netns_ipvs *ipvs = net_ipvs(net); @@ -3573,7 +3573,7 @@ static int ip_vs_genl_set_cmd(struct sk_buff *skb, struct genl_info *info) * received a valid one. We need a full service specification when * adding / editing a service. Only identifying members otherwise. */ if (cmd == IPVS_CMD_NEW_SERVICE || cmd == IPVS_CMD_SET_SERVICE) - need_full_svc = 1; + need_full_svc = true; ret = ip_vs_genl_parse_service(ipvs, &usvc, info->attrs[IPVS_CMD_ATTR_SERVICE], @@ -3593,7 +3593,7 @@ static int ip_vs_genl_set_cmd(struct sk_buff *skb, struct genl_info *info) if (cmd == IPVS_CMD_NEW_DEST || cmd == IPVS_CMD_SET_DEST || cmd == IPVS_CMD_DEL_DEST) { if (cmd != IPVS_CMD_DEL_DEST) - need_full_dest = 1; + need_full_dest = true; ret = ip_vs_genl_parse_dest(&udest, info->attrs[IPVS_CMD_ATTR_DEST], diff --git a/net/netfilter/ipvs/ip_vs_ftp.c b/net/netfilter/ipvs/ip_vs_ftp.c index 4398a72edec5..fe69d46ff779 100644 --- a/net/netfilter/ipvs/ip_vs_ftp.c +++ b/net/netfilter/ipvs/ip_vs_ftp.c @@ -124,7 +124,7 @@ static int ip_vs_ftp_get_addrport(char *data, char *data_limit, } s = data + plen; if (skip) { - int found = 0; + bool found = false; for (;; s++) { if (s == data_limit) @@ -136,7 +136,7 @@ static int ip_vs_ftp_get_addrport(char *data, char *data_limit, if (!ext && isdigit(*s)) break; if (*s == skip) - found = 1; + found = true; } else if (*s != skip) { break; } diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c index bc3d1625ecc8..b58ddb7dffd1 100644 --- a/net/netfilter/ipvs/ip_vs_proto_sctp.c +++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c @@ -186,7 +186,7 @@ static int sctp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp) { unsigned int sctphoff; - struct sctphdr *sh, _sctph; + struct sctphdr *sh; __le32 cmp, val; #ifdef CONFIG_IP_VS_IPV6 @@ -196,10 +196,7 @@ sctp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp) #endif sctphoff = ip_hdrlen(skb); - sh = skb_header_pointer(skb, sctphoff, sizeof(_sctph), &_sctph); - if (sh == NULL) - return 0; - + sh = (struct sctphdr *)(skb->data + sctphoff); cmp = sh->checksum; val = sctp_compute_cksum(skb, sctphoff); diff --git a/net/netfilter/ipvs/ip_vs_proto_tcp.c b/net/netfilter/ipvs/ip_vs_proto_tcp.c index 479419759983..00ce07dda980 100644 --- a/net/netfilter/ipvs/ip_vs_proto_tcp.c +++ b/net/netfilter/ipvs/ip_vs_proto_tcp.c @@ -153,8 +153,8 @@ tcp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, { struct tcphdr *tcph; unsigned int tcphoff = iph->len; + bool payload_csum = false; int oldlen; - int payload_csum = 0; #ifdef CONFIG_IP_VS_IPV6 if (cp->af == AF_INET6 && iph->fragoffs) @@ -180,7 +180,7 @@ tcp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, if (ret == 1) oldlen = skb->len - tcphoff; else - payload_csum = 1; + payload_csum = true; } tcph = (void *)skb_network_header(skb) + tcphoff; @@ -231,8 +231,8 @@ tcp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, { struct tcphdr *tcph; unsigned int tcphoff = iph->len; + bool payload_csum = false; int oldlen; - int payload_csum = 0; #ifdef CONFIG_IP_VS_IPV6 if (cp->af == AF_INET6 && iph->fragoffs) @@ -261,7 +261,7 @@ tcp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, if (ret == 1) oldlen = skb->len - tcphoff; else - payload_csum = 1; + payload_csum = true; } tcph = (void *)skb_network_header(skb) + tcphoff; diff --git a/net/netfilter/ipvs/ip_vs_proto_udp.c b/net/netfilter/ipvs/ip_vs_proto_udp.c index 646c384910fb..92c078abcb3e 100644 --- a/net/netfilter/ipvs/ip_vs_proto_udp.c +++ b/net/netfilter/ipvs/ip_vs_proto_udp.c @@ -143,8 +143,8 @@ udp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, { struct udphdr *udph; unsigned int udphoff = iph->len; + bool payload_csum = false; int oldlen; - int payload_csum = 0; #ifdef CONFIG_IP_VS_IPV6 if (cp->af == AF_INET6 && iph->fragoffs) @@ -172,7 +172,7 @@ udp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, if (ret == 1) oldlen = skb->len - udphoff; else - payload_csum = 1; + payload_csum = true; } udph = (void *)skb_network_header(skb) + udphoff; @@ -226,8 +226,8 @@ udp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, { struct udphdr *udph; unsigned int udphoff = iph->len; + bool payload_csum = false; int oldlen; - int payload_csum = 0; #ifdef CONFIG_IP_VS_IPV6 if (cp->af == AF_INET6 && iph->fragoffs) @@ -256,7 +256,7 @@ udp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, if (ret == 1) oldlen = skb->len - udphoff; else - payload_csum = 1; + payload_csum = true; } udph = (void *)skb_network_header(skb) + udphoff; diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index 473cce2a5231..175349fcf91f 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -126,7 +126,7 @@ static struct rtable *do_output_route4(struct net *net, __be32 daddr, { struct flowi4 fl4; struct rtable *rt; - int loop = 0; + bool loop = false; memset(&fl4, 0, sizeof(fl4)); fl4.daddr = daddr; @@ -149,7 +149,7 @@ retry: ip_rt_put(rt); *saddr = fl4.saddr; flowi4_update_output(&fl4, 0, 0, daddr, fl4.saddr); - loop++; + loop = true; goto retry; } *saddr = fl4.saddr; diff --git a/net/netfilter/nf_conntrack_amanda.c b/net/netfilter/nf_conntrack_amanda.c index 20edd589fe06..f2681ec5b5f6 100644 --- a/net/netfilter/nf_conntrack_amanda.c +++ b/net/netfilter/nf_conntrack_amanda.c @@ -54,6 +54,7 @@ enum amanda_strings { SEARCH_DATA, SEARCH_MESG, SEARCH_INDEX, + SEARCH_STATE, }; static struct { @@ -81,6 +82,10 @@ static struct { .string = "INDEX ", .len = 6, }, + [SEARCH_STATE] = { + .string = "STATE ", + .len = 6, + }, }; static int amanda_help(struct sk_buff *skb, @@ -124,7 +129,7 @@ static int amanda_help(struct sk_buff *skb, goto out; stop += start; - for (i = SEARCH_DATA; i <= SEARCH_INDEX; i++) { + for (i = SEARCH_DATA; i <= SEARCH_STATE; i++) { off = skb_find_text(skb, start, stop, search[i].ts); if (off == UINT_MAX) continue; @@ -168,7 +173,7 @@ out: } static const struct nf_conntrack_expect_policy amanda_exp_policy = { - .max_expected = 3, + .max_expected = 4, .timeout = 180, }; diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index e139c256e269..82bfbeef46af 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -51,7 +51,6 @@ #include <net/netfilter/nf_conntrack_labels.h> #include <net/netfilter/nf_conntrack_synproxy.h> #include <net/netfilter/nf_nat.h> -#include <net/netfilter/nf_nat_core.h> #include <net/netfilter/nf_nat_helper.h> #include <net/netns/hash.h> #include <net/ip.h> @@ -1752,11 +1751,9 @@ EXPORT_SYMBOL_GPL(nf_conntrack_alter_reply); void __nf_ct_refresh_acct(struct nf_conn *ct, enum ip_conntrack_info ctinfo, const struct sk_buff *skb, - unsigned long extra_jiffies, - int do_acct) + u32 extra_jiffies, + bool do_acct) { - WARN_ON(!skb); - /* Only update if this is not a fixed timeout */ if (test_bit(IPS_FIXED_TIMEOUT_BIT, &ct->status)) goto acct; @@ -1765,7 +1762,8 @@ void __nf_ct_refresh_acct(struct nf_conn *ct, if (nf_ct_is_confirmed(ct)) extra_jiffies += nfct_time_stamp; - ct->timeout = extra_jiffies; + if (ct->timeout != extra_jiffies) + ct->timeout = extra_jiffies; acct: if (do_acct) nf_ct_acct_update(ct, ctinfo, skb->len); @@ -2482,6 +2480,7 @@ int nf_conntrack_init_net(struct net *net) int cpu; BUILD_BUG_ON(IP_CT_UNTRACKED == IP_CT_NUMBER); + BUILD_BUG_ON_NOT_POWER_OF_2(CONNTRACK_LOCKS); atomic_set(&net->ct.count, 0); net->ct.pcpu_lists = alloc_percpu(struct ct_pcpu); diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 349b42a65c8a..66c596d287a5 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -46,7 +46,7 @@ #include <net/netfilter/nf_conntrack_labels.h> #include <net/netfilter/nf_conntrack_synproxy.h> #ifdef CONFIG_NF_NAT_NEEDED -#include <net/netfilter/nf_nat_core.h> +#include <net/netfilter/nf_nat.h> #include <net/netfilter/nf_nat_helper.h> #endif diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index 01c748fa8913..a06875a466a4 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -828,6 +828,12 @@ static noinline bool tcp_new(struct nf_conn *ct, const struct sk_buff *skb, return true; } +static bool nf_conntrack_tcp_established(const struct nf_conn *ct) +{ + return ct->proto.tcp.state == TCP_CONNTRACK_ESTABLISHED && + test_bit(IPS_ASSURED_BIT, &ct->status); +} + /* Returns verdict for packet, or -1 for invalid. */ int nf_conntrack_tcp_packet(struct nf_conn *ct, struct sk_buff *skb, @@ -1030,16 +1036,38 @@ int nf_conntrack_tcp_packet(struct nf_conn *ct, new_state = TCP_CONNTRACK_ESTABLISHED; break; case TCP_CONNTRACK_CLOSE: - if (index == TCP_RST_SET - && (ct->proto.tcp.seen[!dir].flags & IP_CT_TCP_FLAG_MAXACK_SET) - && before(ntohl(th->seq), ct->proto.tcp.seen[!dir].td_maxack)) { - /* Invalid RST */ - spin_unlock_bh(&ct->lock); - nf_ct_l4proto_log_invalid(skb, ct, "invalid rst"); - return -NF_ACCEPT; + if (index != TCP_RST_SET) + break; + + if (ct->proto.tcp.seen[!dir].flags & IP_CT_TCP_FLAG_MAXACK_SET) { + u32 seq = ntohl(th->seq); + + if (before(seq, ct->proto.tcp.seen[!dir].td_maxack)) { + /* Invalid RST */ + spin_unlock_bh(&ct->lock); + nf_ct_l4proto_log_invalid(skb, ct, "invalid rst"); + return -NF_ACCEPT; + } + + if (!nf_conntrack_tcp_established(ct) || + seq == ct->proto.tcp.seen[!dir].td_maxack) + break; + + /* Check if rst is part of train, such as + * foo:80 > bar:4379: P, 235946583:235946602(19) ack 42 + * foo:80 > bar:4379: R, 235946602:235946602(0) ack 42 + */ + if (ct->proto.tcp.last_index == TCP_ACK_SET && + ct->proto.tcp.last_dir == dir && + seq == ct->proto.tcp.last_end) + break; + + /* ... RST sequence number doesn't match exactly, keep + * established state to allow a possible challenge ACK. + */ + new_state = old_state; } - if (index == TCP_RST_SET - && ((test_bit(IPS_SEEN_REPLY_BIT, &ct->status) + if (((test_bit(IPS_SEEN_REPLY_BIT, &ct->status) && ct->proto.tcp.last_index == TCP_SYN_SET) || (!test_bit(IPS_ASSURED_BIT, &ct->status) && ct->proto.tcp.last_index == TCP_ACK_SET)) @@ -1055,7 +1083,7 @@ int nf_conntrack_tcp_packet(struct nf_conn *ct, * segments we ignored. */ goto in_window; } - /* Just fall through */ + break; default: /* Keep compilers happy. */ break; @@ -1090,6 +1118,8 @@ int nf_conntrack_tcp_packet(struct nf_conn *ct, if (ct->proto.tcp.retrans >= tn->tcp_max_retrans && timeouts[new_state] > timeouts[TCP_CONNTRACK_RETRANS]) timeout = timeouts[TCP_CONNTRACK_RETRANS]; + else if (unlikely(index == TCP_RST_SET)) + timeout = timeouts[TCP_CONNTRACK_CLOSE]; else if ((ct->proto.tcp.seen[0].flags | ct->proto.tcp.seen[1].flags) & IP_CT_TCP_FLAG_DATA_UNACKNOWLEDGED && timeouts[new_state] > timeouts[TCP_CONNTRACK_UNACK]) diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index 35e61038ae96..af7dc6537758 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -22,8 +22,6 @@ #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_conntrack_core.h> #include <net/netfilter/nf_nat.h> -#include <net/netfilter/nf_nat_l3proto.h> -#include <net/netfilter/nf_nat_core.h> #include <net/netfilter/nf_nat_helper.h> #include <net/netfilter/nf_conntrack_helper.h> #include <net/netfilter/nf_conntrack_seqadj.h> @@ -35,8 +33,6 @@ static spinlock_t nf_nat_locks[CONNTRACK_LOCKS]; static DEFINE_MUTEX(nf_nat_proto_mutex); -static const struct nf_nat_l3proto __rcu *nf_nat_l3protos[NFPROTO_NUMPROTO] - __read_mostly; static unsigned int nat_net_id __read_mostly; static struct hlist_head *nf_nat_bysource __read_mostly; @@ -58,16 +54,75 @@ struct nat_net { struct nf_nat_hooks_net nat_proto_net[NFPROTO_NUMPROTO]; }; -inline const struct nf_nat_l3proto * -__nf_nat_l3proto_find(u8 family) +#ifdef CONFIG_XFRM +static void nf_nat_ipv4_decode_session(struct sk_buff *skb, + const struct nf_conn *ct, + enum ip_conntrack_dir dir, + unsigned long statusbit, + struct flowi *fl) { - return rcu_dereference(nf_nat_l3protos[family]); + const struct nf_conntrack_tuple *t = &ct->tuplehash[dir].tuple; + struct flowi4 *fl4 = &fl->u.ip4; + + if (ct->status & statusbit) { + fl4->daddr = t->dst.u3.ip; + if (t->dst.protonum == IPPROTO_TCP || + t->dst.protonum == IPPROTO_UDP || + t->dst.protonum == IPPROTO_UDPLITE || + t->dst.protonum == IPPROTO_DCCP || + t->dst.protonum == IPPROTO_SCTP) + fl4->fl4_dport = t->dst.u.all; + } + + statusbit ^= IPS_NAT_MASK; + + if (ct->status & statusbit) { + fl4->saddr = t->src.u3.ip; + if (t->dst.protonum == IPPROTO_TCP || + t->dst.protonum == IPPROTO_UDP || + t->dst.protonum == IPPROTO_UDPLITE || + t->dst.protonum == IPPROTO_DCCP || + t->dst.protonum == IPPROTO_SCTP) + fl4->fl4_sport = t->src.u.all; + } +} + +static void nf_nat_ipv6_decode_session(struct sk_buff *skb, + const struct nf_conn *ct, + enum ip_conntrack_dir dir, + unsigned long statusbit, + struct flowi *fl) +{ +#if IS_ENABLED(CONFIG_IPV6) + const struct nf_conntrack_tuple *t = &ct->tuplehash[dir].tuple; + struct flowi6 *fl6 = &fl->u.ip6; + + if (ct->status & statusbit) { + fl6->daddr = t->dst.u3.in6; + if (t->dst.protonum == IPPROTO_TCP || + t->dst.protonum == IPPROTO_UDP || + t->dst.protonum == IPPROTO_UDPLITE || + t->dst.protonum == IPPROTO_DCCP || + t->dst.protonum == IPPROTO_SCTP) + fl6->fl6_dport = t->dst.u.all; + } + + statusbit ^= IPS_NAT_MASK; + + if (ct->status & statusbit) { + fl6->saddr = t->src.u3.in6; + if (t->dst.protonum == IPPROTO_TCP || + t->dst.protonum == IPPROTO_UDP || + t->dst.protonum == IPPROTO_UDPLITE || + t->dst.protonum == IPPROTO_DCCP || + t->dst.protonum == IPPROTO_SCTP) + fl6->fl6_sport = t->src.u.all; + } +#endif } -#ifdef CONFIG_XFRM static void __nf_nat_decode_session(struct sk_buff *skb, struct flowi *fl) { - const struct nf_nat_l3proto *l3proto; const struct nf_conn *ct; enum ip_conntrack_info ctinfo; enum ip_conntrack_dir dir; @@ -79,17 +134,20 @@ static void __nf_nat_decode_session(struct sk_buff *skb, struct flowi *fl) return; family = nf_ct_l3num(ct); - l3proto = __nf_nat_l3proto_find(family); - if (l3proto == NULL) - return; - dir = CTINFO2DIR(ctinfo); if (dir == IP_CT_DIR_ORIGINAL) statusbit = IPS_DST_NAT; else statusbit = IPS_SRC_NAT; - l3proto->decode_session(skb, ct, dir, statusbit, fl); + switch (family) { + case NFPROTO_IPV4: + nf_nat_ipv4_decode_session(skb, ct, dir, statusbit, fl); + return; + case NFPROTO_IPV6: + nf_nat_ipv6_decode_session(skb, ct, dir, statusbit, fl); + return; + } } int nf_xfrm_me_harder(struct net *net, struct sk_buff *skb, unsigned int family) @@ -182,7 +240,7 @@ static bool l4proto_in_range(const struct nf_conntrack_tuple *tuple, __be16 port; switch (tuple->dst.protonum) { - case IPPROTO_ICMP: /* fallthrough */ + case IPPROTO_ICMP: case IPPROTO_ICMPV6: return ntohs(tuple->src.u.icmp.id) >= ntohs(min->icmp.id) && ntohs(tuple->src.u.icmp.id) <= ntohs(max->icmp.id); @@ -631,23 +689,6 @@ nf_nat_alloc_null_binding(struct nf_conn *ct, unsigned int hooknum) } EXPORT_SYMBOL_GPL(nf_nat_alloc_null_binding); -static unsigned int nf_nat_manip_pkt(struct sk_buff *skb, struct nf_conn *ct, - enum nf_nat_manip_type mtype, - enum ip_conntrack_dir dir) -{ - const struct nf_nat_l3proto *l3proto; - struct nf_conntrack_tuple target; - - /* We are aiming to look like inverse of other direction. */ - nf_ct_invert_tuple(&target, &ct->tuplehash[!dir].tuple); - - l3proto = __nf_nat_l3proto_find(target.src.l3num); - if (!l3proto->manip_pkt(skb, 0, &target, mtype)) - return NF_DROP; - - return NF_ACCEPT; -} - /* Do packet manipulations according to nf_nat_setup_info. */ unsigned int nf_nat_packet(struct nf_conn *ct, enum ip_conntrack_info ctinfo, @@ -798,33 +839,6 @@ static int nf_nat_proto_clean(struct nf_conn *ct, void *data) return 0; } -static void nf_nat_l3proto_clean(u8 l3proto) -{ - struct nf_nat_proto_clean clean = { - .l3proto = l3proto, - }; - - nf_ct_iterate_destroy(nf_nat_proto_remove, &clean); -} - -int nf_nat_l3proto_register(const struct nf_nat_l3proto *l3proto) -{ - RCU_INIT_POINTER(nf_nat_l3protos[l3proto->l3proto], l3proto); - return 0; -} -EXPORT_SYMBOL_GPL(nf_nat_l3proto_register); - -void nf_nat_l3proto_unregister(const struct nf_nat_l3proto *l3proto) -{ - mutex_lock(&nf_nat_proto_mutex); - RCU_INIT_POINTER(nf_nat_l3protos[l3proto->l3proto], NULL); - mutex_unlock(&nf_nat_proto_mutex); - synchronize_rcu(); - - nf_nat_l3proto_clean(l3proto->l3proto); -} -EXPORT_SYMBOL_GPL(nf_nat_l3proto_unregister); - /* No one using conntrack by the time this called. */ static void nf_nat_cleanup_conntrack(struct nf_conn *ct) { @@ -887,10 +901,43 @@ static const struct nla_policy nat_nla_policy[CTA_NAT_MAX+1] = { [CTA_NAT_PROTO] = { .type = NLA_NESTED }, }; +static int nf_nat_ipv4_nlattr_to_range(struct nlattr *tb[], + struct nf_nat_range2 *range) +{ + if (tb[CTA_NAT_V4_MINIP]) { + range->min_addr.ip = nla_get_be32(tb[CTA_NAT_V4_MINIP]); + range->flags |= NF_NAT_RANGE_MAP_IPS; + } + + if (tb[CTA_NAT_V4_MAXIP]) + range->max_addr.ip = nla_get_be32(tb[CTA_NAT_V4_MAXIP]); + else + range->max_addr.ip = range->min_addr.ip; + + return 0; +} + +static int nf_nat_ipv6_nlattr_to_range(struct nlattr *tb[], + struct nf_nat_range2 *range) +{ + if (tb[CTA_NAT_V6_MINIP]) { + nla_memcpy(&range->min_addr.ip6, tb[CTA_NAT_V6_MINIP], + sizeof(struct in6_addr)); + range->flags |= NF_NAT_RANGE_MAP_IPS; + } + + if (tb[CTA_NAT_V6_MAXIP]) + nla_memcpy(&range->max_addr.ip6, tb[CTA_NAT_V6_MAXIP], + sizeof(struct in6_addr)); + else + range->max_addr = range->min_addr; + + return 0; +} + static int nfnetlink_parse_nat(const struct nlattr *nat, - const struct nf_conn *ct, struct nf_nat_range2 *range, - const struct nf_nat_l3proto *l3proto) + const struct nf_conn *ct, struct nf_nat_range2 *range) { struct nlattr *tb[CTA_NAT_MAX+1]; int err; @@ -901,8 +948,19 @@ nfnetlink_parse_nat(const struct nlattr *nat, if (err < 0) return err; - err = l3proto->nlattr_to_range(tb, range); - if (err < 0) + switch (nf_ct_l3num(ct)) { + case NFPROTO_IPV4: + err = nf_nat_ipv4_nlattr_to_range(tb, range); + break; + case NFPROTO_IPV6: + err = nf_nat_ipv6_nlattr_to_range(tb, range); + break; + default: + err = -EPROTONOSUPPORT; + break; + } + + if (err) return err; if (!tb[CTA_NAT_PROTO]) @@ -918,7 +976,6 @@ nfnetlink_parse_nat_setup(struct nf_conn *ct, const struct nlattr *attr) { struct nf_nat_range2 range; - const struct nf_nat_l3proto *l3proto; int err; /* Should not happen, restricted to creating new conntracks @@ -927,18 +984,11 @@ nfnetlink_parse_nat_setup(struct nf_conn *ct, if (WARN_ON_ONCE(nf_nat_initialized(ct, manip))) return -EEXIST; - /* Make sure that L3 NAT is there by when we call nf_nat_setup_info to - * attach the null binding, otherwise this may oops. - */ - l3proto = __nf_nat_l3proto_find(nf_ct_l3num(ct)); - if (l3proto == NULL) - return -EAGAIN; - /* No NAT information has been passed, allocate the null-binding */ if (attr == NULL) return __nf_nat_alloc_null_binding(ct, manip) == NF_DROP ? -ENOMEM : 0; - err = nfnetlink_parse_nat(attr, ct, &range, l3proto); + err = nfnetlink_parse_nat(attr, ct, &range); if (err < 0) return err; @@ -1035,7 +1085,6 @@ int nf_nat_register_fn(struct net *net, const struct nf_hook_ops *ops, mutex_unlock(&nf_nat_proto_mutex); return ret; } -EXPORT_SYMBOL_GPL(nf_nat_register_fn); void nf_nat_unregister_fn(struct net *net, const struct nf_hook_ops *ops, unsigned int ops_count) @@ -1084,7 +1133,6 @@ void nf_nat_unregister_fn(struct net *net, const struct nf_hook_ops *ops, unlock: mutex_unlock(&nf_nat_proto_mutex); } -EXPORT_SYMBOL_GPL(nf_nat_unregister_fn); static struct pernet_operations nat_net_ops = { .id = &nat_net_id, diff --git a/net/netfilter/nf_nat_helper.c b/net/netfilter/nf_nat_helper.c index 38793b95d9bc..ccc06f7539d7 100644 --- a/net/netfilter/nf_nat_helper.c +++ b/net/netfilter/nf_nat_helper.c @@ -22,9 +22,6 @@ #include <net/netfilter/nf_conntrack_expect.h> #include <net/netfilter/nf_conntrack_seqadj.h> #include <net/netfilter/nf_nat.h> -#include <net/netfilter/nf_nat_l3proto.h> -#include <net/netfilter/nf_nat_l4proto.h> -#include <net/netfilter/nf_nat_core.h> #include <net/netfilter/nf_nat_helper.h> /* Frobs data inside this packet, which is linear. */ @@ -98,7 +95,6 @@ bool __nf_nat_mangle_tcp_packet(struct sk_buff *skb, const char *rep_buffer, unsigned int rep_len, bool adjust) { - const struct nf_nat_l3proto *l3proto; struct tcphdr *tcph; int oldlen, datalen; @@ -118,9 +114,8 @@ bool __nf_nat_mangle_tcp_packet(struct sk_buff *skb, datalen = skb->len - protoff; - l3proto = __nf_nat_l3proto_find(nf_ct_l3num(ct)); - l3proto->csum_recalc(skb, IPPROTO_TCP, tcph, &tcph->check, - datalen, oldlen); + nf_nat_csum_recalc(skb, nf_ct_l3num(ct), IPPROTO_TCP, + tcph, &tcph->check, datalen, oldlen); if (adjust && rep_len != match_len) nf_ct_seqadj_set(ct, ctinfo, tcph->seq, @@ -150,7 +145,6 @@ nf_nat_mangle_udp_packet(struct sk_buff *skb, const char *rep_buffer, unsigned int rep_len) { - const struct nf_nat_l3proto *l3proto; struct udphdr *udph; int datalen, oldlen; @@ -176,9 +170,8 @@ nf_nat_mangle_udp_packet(struct sk_buff *skb, if (!udph->check && skb->ip_summed != CHECKSUM_PARTIAL) return true; - l3proto = __nf_nat_l3proto_find(nf_ct_l3num(ct)); - l3proto->csum_recalc(skb, IPPROTO_UDP, udph, &udph->check, - datalen, oldlen); + nf_nat_csum_recalc(skb, nf_ct_l3num(ct), IPPROTO_TCP, + udph, &udph->check, datalen, oldlen); return true; } diff --git a/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c b/net/netfilter/nf_nat_masquerade.c index 41327bb99093..86fa4dcc63c5 100644 --- a/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c +++ b/net/netfilter/nf_nat_masquerade.c @@ -1,25 +1,17 @@ -/* (C) 1999-2001 Paul `Rusty' Russell - * (C) 2002-2006 Netfilter Core Team <coreteam@netfilter.org> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ +// SPDX-License-Identifier: GPL-2.0 #include <linux/types.h> #include <linux/atomic.h> #include <linux/inetdevice.h> -#include <linux/ip.h> -#include <linux/timer.h> #include <linux/netfilter.h> -#include <net/protocol.h> -#include <net/ip.h> -#include <net/checksum.h> -#include <net/route.h> #include <linux/netfilter_ipv4.h> -#include <linux/netfilter/x_tables.h> -#include <net/netfilter/nf_nat.h> +#include <linux/netfilter_ipv6.h> + #include <net/netfilter/ipv4/nf_nat_masquerade.h> +#include <net/netfilter/ipv6/nf_nat_masquerade.h> + +static DEFINE_MUTEX(masq_mutex); +static unsigned int masq_refcnt __read_mostly; unsigned int nf_nat_masquerade_ipv4(struct sk_buff *skb, unsigned int hooknum, @@ -78,8 +70,6 @@ static int device_cmp(struct nf_conn *i, void *ifindex) if (!nat) return 0; - if (nf_ct_l3num(i) != NFPROTO_IPV4) - return 0; return nat->masq_index == (int)(long)ifindex; } @@ -95,7 +85,6 @@ static int masq_device_event(struct notifier_block *this, * conntracks which were associated with that device, * and forget them. */ - WARN_ON(dev->ifindex == 0); nf_ct_iterate_cleanup_net(net, device_cmp, (void *)(long)dev->ifindex, 0, 0); @@ -147,9 +136,6 @@ static struct notifier_block masq_inet_notifier = { .notifier_call = masq_inet_event, }; -static int masq_refcnt; -static DEFINE_MUTEX(masq_mutex); - int nf_nat_masquerade_ipv4_register_notifier(void) { int ret = 0; @@ -194,3 +180,183 @@ out_unlock: mutex_unlock(&masq_mutex); } EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv4_unregister_notifier); + +#if IS_ENABLED(CONFIG_IPV6) +static atomic_t v6_worker_count __read_mostly; + +static int +nat_ipv6_dev_get_saddr(struct net *net, const struct net_device *dev, + const struct in6_addr *daddr, unsigned int srcprefs, + struct in6_addr *saddr) +{ +#ifdef CONFIG_IPV6_MODULE + const struct nf_ipv6_ops *v6_ops = nf_get_ipv6_ops(); + + if (!v6_ops) + return -EHOSTUNREACH; + + return v6_ops->dev_get_saddr(net, dev, daddr, srcprefs, saddr); +#else + return ipv6_dev_get_saddr(net, dev, daddr, srcprefs, saddr); +#endif +} + +unsigned int +nf_nat_masquerade_ipv6(struct sk_buff *skb, const struct nf_nat_range2 *range, + const struct net_device *out) +{ + enum ip_conntrack_info ctinfo; + struct nf_conn_nat *nat; + struct in6_addr src; + struct nf_conn *ct; + struct nf_nat_range2 newrange; + + ct = nf_ct_get(skb, &ctinfo); + WARN_ON(!(ct && (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED || + ctinfo == IP_CT_RELATED_REPLY))); + + if (nat_ipv6_dev_get_saddr(nf_ct_net(ct), out, + &ipv6_hdr(skb)->daddr, 0, &src) < 0) + return NF_DROP; + + nat = nf_ct_nat_ext_add(ct); + if (nat) + nat->masq_index = out->ifindex; + + newrange.flags = range->flags | NF_NAT_RANGE_MAP_IPS; + newrange.min_addr.in6 = src; + newrange.max_addr.in6 = src; + newrange.min_proto = range->min_proto; + newrange.max_proto = range->max_proto; + + return nf_nat_setup_info(ct, &newrange, NF_NAT_MANIP_SRC); +} +EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv6); + +struct masq_dev_work { + struct work_struct work; + struct net *net; + struct in6_addr addr; + int ifindex; +}; + +static int inet6_cmp(struct nf_conn *ct, void *work) +{ + struct masq_dev_work *w = (struct masq_dev_work *)work; + struct nf_conntrack_tuple *tuple; + + if (!device_cmp(ct, (void *)(long)w->ifindex)) + return 0; + + tuple = &ct->tuplehash[IP_CT_DIR_REPLY].tuple; + + return ipv6_addr_equal(&w->addr, &tuple->dst.u3.in6); +} + +static void iterate_cleanup_work(struct work_struct *work) +{ + struct masq_dev_work *w; + + w = container_of(work, struct masq_dev_work, work); + + nf_ct_iterate_cleanup_net(w->net, inet6_cmp, (void *)w, 0, 0); + + put_net(w->net); + kfree(w); + atomic_dec(&v6_worker_count); + module_put(THIS_MODULE); +} + +/* atomic notifier; can't call nf_ct_iterate_cleanup_net (it can sleep). + * + * Defer it to the system workqueue. + * + * As we can have 'a lot' of inet_events (depending on amount of ipv6 + * addresses being deleted), we also need to limit work item queue. + */ +static int masq_inet6_event(struct notifier_block *this, + unsigned long event, void *ptr) +{ + struct inet6_ifaddr *ifa = ptr; + const struct net_device *dev; + struct masq_dev_work *w; + struct net *net; + + if (event != NETDEV_DOWN || atomic_read(&v6_worker_count) >= 16) + return NOTIFY_DONE; + + dev = ifa->idev->dev; + net = maybe_get_net(dev_net(dev)); + if (!net) + return NOTIFY_DONE; + + if (!try_module_get(THIS_MODULE)) + goto err_module; + + w = kmalloc(sizeof(*w), GFP_ATOMIC); + if (w) { + atomic_inc(&v6_worker_count); + + INIT_WORK(&w->work, iterate_cleanup_work); + w->ifindex = dev->ifindex; + w->net = net; + w->addr = ifa->addr; + schedule_work(&w->work); + + return NOTIFY_DONE; + } + + module_put(THIS_MODULE); + err_module: + put_net(net); + return NOTIFY_DONE; +} + +static struct notifier_block masq_inet6_notifier = { + .notifier_call = masq_inet6_event, +}; + +int nf_nat_masquerade_ipv6_register_notifier(void) +{ + int ret = 0; + + mutex_lock(&masq_mutex); + /* check if the notifier is already set */ + if (++masq_refcnt > 1) + goto out_unlock; + + ret = register_netdevice_notifier(&masq_dev_notifier); + if (ret) + goto err_dec; + + ret = register_inet6addr_notifier(&masq_inet6_notifier); + if (ret) + goto err_unregister; + + mutex_unlock(&masq_mutex); + return ret; + +err_unregister: + unregister_netdevice_notifier(&masq_dev_notifier); +err_dec: + masq_refcnt--; +out_unlock: + mutex_unlock(&masq_mutex); + return ret; +} +EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv6_register_notifier); + +void nf_nat_masquerade_ipv6_unregister_notifier(void) +{ + mutex_lock(&masq_mutex); + /* check if the notifier still has clients */ + if (--masq_refcnt > 0) + goto out_unlock; + + unregister_inet6addr_notifier(&masq_inet6_notifier); + unregister_netdevice_notifier(&masq_dev_notifier); +out_unlock: + mutex_unlock(&masq_mutex); +} +EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv6_unregister_notifier); +#endif diff --git a/net/netfilter/nf_nat_proto.c b/net/netfilter/nf_nat_proto.c index f83bf9d8c9f5..62743da3004f 100644 --- a/net/netfilter/nf_nat_proto.c +++ b/net/netfilter/nf_nat_proto.c @@ -20,13 +20,26 @@ #include <linux/netfilter.h> #include <net/netfilter/nf_nat.h> -#include <net/netfilter/nf_nat_core.h> -#include <net/netfilter/nf_nat_l3proto.h> -#include <net/netfilter/nf_nat_l4proto.h> + +#include <linux/ipv6.h> +#include <linux/netfilter_ipv6.h> +#include <net/checksum.h> +#include <net/ip6_checksum.h> +#include <net/ip6_route.h> +#include <net/xfrm.h> +#include <net/ipv6.h> + +#include <net/netfilter/nf_conntrack_core.h> +#include <net/netfilter/nf_conntrack.h> +#include <linux/netfilter/nfnetlink_conntrack.h> + +static void nf_csum_update(struct sk_buff *skb, + unsigned int iphdroff, __sum16 *check, + const struct nf_conntrack_tuple *t, + enum nf_nat_manip_type maniptype); static void __udp_manip_pkt(struct sk_buff *skb, - const struct nf_nat_l3proto *l3proto, unsigned int iphdroff, struct udphdr *hdr, const struct nf_conntrack_tuple *tuple, enum nf_nat_manip_type maniptype, bool do_csum) @@ -43,8 +56,7 @@ __udp_manip_pkt(struct sk_buff *skb, portptr = &hdr->dest; } if (do_csum) { - l3proto->csum_update(skb, iphdroff, &hdr->check, - tuple, maniptype); + nf_csum_update(skb, iphdroff, &hdr->check, tuple, maniptype); inet_proto_csum_replace2(&hdr->check, skb, *portptr, newport, false); if (!hdr->check) @@ -54,7 +66,6 @@ __udp_manip_pkt(struct sk_buff *skb, } static bool udp_manip_pkt(struct sk_buff *skb, - const struct nf_nat_l3proto *l3proto, unsigned int iphdroff, unsigned int hdroff, const struct nf_conntrack_tuple *tuple, enum nf_nat_manip_type maniptype) @@ -68,12 +79,11 @@ static bool udp_manip_pkt(struct sk_buff *skb, hdr = (struct udphdr *)(skb->data + hdroff); do_csum = hdr->check || skb->ip_summed == CHECKSUM_PARTIAL; - __udp_manip_pkt(skb, l3proto, iphdroff, hdr, tuple, maniptype, do_csum); + __udp_manip_pkt(skb, iphdroff, hdr, tuple, maniptype, do_csum); return true; } static bool udplite_manip_pkt(struct sk_buff *skb, - const struct nf_nat_l3proto *l3proto, unsigned int iphdroff, unsigned int hdroff, const struct nf_conntrack_tuple *tuple, enum nf_nat_manip_type maniptype) @@ -85,14 +95,13 @@ static bool udplite_manip_pkt(struct sk_buff *skb, return false; hdr = (struct udphdr *)(skb->data + hdroff); - __udp_manip_pkt(skb, l3proto, iphdroff, hdr, tuple, maniptype, true); + __udp_manip_pkt(skb, iphdroff, hdr, tuple, maniptype, true); #endif return true; } static bool sctp_manip_pkt(struct sk_buff *skb, - const struct nf_nat_l3proto *l3proto, unsigned int iphdroff, unsigned int hdroff, const struct nf_conntrack_tuple *tuple, enum nf_nat_manip_type maniptype) @@ -135,7 +144,6 @@ sctp_manip_pkt(struct sk_buff *skb, static bool tcp_manip_pkt(struct sk_buff *skb, - const struct nf_nat_l3proto *l3proto, unsigned int iphdroff, unsigned int hdroff, const struct nf_conntrack_tuple *tuple, enum nf_nat_manip_type maniptype) @@ -171,14 +179,13 @@ tcp_manip_pkt(struct sk_buff *skb, if (hdrsize < sizeof(*hdr)) return true; - l3proto->csum_update(skb, iphdroff, &hdr->check, tuple, maniptype); + nf_csum_update(skb, iphdroff, &hdr->check, tuple, maniptype); inet_proto_csum_replace2(&hdr->check, skb, oldport, newport, false); return true; } static bool dccp_manip_pkt(struct sk_buff *skb, - const struct nf_nat_l3proto *l3proto, unsigned int iphdroff, unsigned int hdroff, const struct nf_conntrack_tuple *tuple, enum nf_nat_manip_type maniptype) @@ -210,8 +217,7 @@ dccp_manip_pkt(struct sk_buff *skb, if (hdrsize < sizeof(*hdr)) return true; - l3proto->csum_update(skb, iphdroff, &hdr->dccph_checksum, - tuple, maniptype); + nf_csum_update(skb, iphdroff, &hdr->dccph_checksum, tuple, maniptype); inet_proto_csum_replace2(&hdr->dccph_checksum, skb, oldport, newport, false); #endif @@ -220,7 +226,6 @@ dccp_manip_pkt(struct sk_buff *skb, static bool icmp_manip_pkt(struct sk_buff *skb, - const struct nf_nat_l3proto *l3proto, unsigned int iphdroff, unsigned int hdroff, const struct nf_conntrack_tuple *tuple, enum nf_nat_manip_type maniptype) @@ -239,7 +244,6 @@ icmp_manip_pkt(struct sk_buff *skb, static bool icmpv6_manip_pkt(struct sk_buff *skb, - const struct nf_nat_l3proto *l3proto, unsigned int iphdroff, unsigned int hdroff, const struct nf_conntrack_tuple *tuple, enum nf_nat_manip_type maniptype) @@ -250,8 +254,7 @@ icmpv6_manip_pkt(struct sk_buff *skb, return false; hdr = (struct icmp6hdr *)(skb->data + hdroff); - l3proto->csum_update(skb, iphdroff, &hdr->icmp6_cksum, - tuple, maniptype); + nf_csum_update(skb, iphdroff, &hdr->icmp6_cksum, tuple, maniptype); if (hdr->icmp6_type == ICMPV6_ECHO_REQUEST || hdr->icmp6_type == ICMPV6_ECHO_REPLY) { inet_proto_csum_replace2(&hdr->icmp6_cksum, skb, @@ -265,7 +268,6 @@ icmpv6_manip_pkt(struct sk_buff *skb, /* manipulate a GRE packet according to maniptype */ static bool gre_manip_pkt(struct sk_buff *skb, - const struct nf_nat_l3proto *l3proto, unsigned int iphdroff, unsigned int hdroff, const struct nf_conntrack_tuple *tuple, enum nf_nat_manip_type maniptype) @@ -304,40 +306,718 @@ gre_manip_pkt(struct sk_buff *skb, return true; } -bool nf_nat_l4proto_manip_pkt(struct sk_buff *skb, - const struct nf_nat_l3proto *l3proto, +static bool l4proto_manip_pkt(struct sk_buff *skb, unsigned int iphdroff, unsigned int hdroff, const struct nf_conntrack_tuple *tuple, enum nf_nat_manip_type maniptype) { switch (tuple->dst.protonum) { case IPPROTO_TCP: - return tcp_manip_pkt(skb, l3proto, iphdroff, hdroff, + return tcp_manip_pkt(skb, iphdroff, hdroff, tuple, maniptype); case IPPROTO_UDP: - return udp_manip_pkt(skb, l3proto, iphdroff, hdroff, + return udp_manip_pkt(skb, iphdroff, hdroff, tuple, maniptype); case IPPROTO_UDPLITE: - return udplite_manip_pkt(skb, l3proto, iphdroff, hdroff, + return udplite_manip_pkt(skb, iphdroff, hdroff, tuple, maniptype); case IPPROTO_SCTP: - return sctp_manip_pkt(skb, l3proto, iphdroff, hdroff, + return sctp_manip_pkt(skb, iphdroff, hdroff, tuple, maniptype); case IPPROTO_ICMP: - return icmp_manip_pkt(skb, l3proto, iphdroff, hdroff, + return icmp_manip_pkt(skb, iphdroff, hdroff, tuple, maniptype); case IPPROTO_ICMPV6: - return icmpv6_manip_pkt(skb, l3proto, iphdroff, hdroff, + return icmpv6_manip_pkt(skb, iphdroff, hdroff, tuple, maniptype); case IPPROTO_DCCP: - return dccp_manip_pkt(skb, l3proto, iphdroff, hdroff, + return dccp_manip_pkt(skb, iphdroff, hdroff, tuple, maniptype); case IPPROTO_GRE: - return gre_manip_pkt(skb, l3proto, iphdroff, hdroff, + return gre_manip_pkt(skb, iphdroff, hdroff, tuple, maniptype); } /* If we don't know protocol -- no error, pass it unmodified. */ return true; } -EXPORT_SYMBOL_GPL(nf_nat_l4proto_manip_pkt); + +static bool nf_nat_ipv4_manip_pkt(struct sk_buff *skb, + unsigned int iphdroff, + const struct nf_conntrack_tuple *target, + enum nf_nat_manip_type maniptype) +{ + struct iphdr *iph; + unsigned int hdroff; + + if (!skb_make_writable(skb, iphdroff + sizeof(*iph))) + return false; + + iph = (void *)skb->data + iphdroff; + hdroff = iphdroff + iph->ihl * 4; + + if (!l4proto_manip_pkt(skb, iphdroff, hdroff, target, maniptype)) + return false; + iph = (void *)skb->data + iphdroff; + + if (maniptype == NF_NAT_MANIP_SRC) { + csum_replace4(&iph->check, iph->saddr, target->src.u3.ip); + iph->saddr = target->src.u3.ip; + } else { + csum_replace4(&iph->check, iph->daddr, target->dst.u3.ip); + iph->daddr = target->dst.u3.ip; + } + return true; +} + +static bool nf_nat_ipv6_manip_pkt(struct sk_buff *skb, + unsigned int iphdroff, + const struct nf_conntrack_tuple *target, + enum nf_nat_manip_type maniptype) +{ +#if IS_ENABLED(CONFIG_IPV6) + struct ipv6hdr *ipv6h; + __be16 frag_off; + int hdroff; + u8 nexthdr; + + if (!skb_make_writable(skb, iphdroff + sizeof(*ipv6h))) + return false; + + ipv6h = (void *)skb->data + iphdroff; + nexthdr = ipv6h->nexthdr; + hdroff = ipv6_skip_exthdr(skb, iphdroff + sizeof(*ipv6h), + &nexthdr, &frag_off); + if (hdroff < 0) + goto manip_addr; + + if ((frag_off & htons(~0x7)) == 0 && + !l4proto_manip_pkt(skb, iphdroff, hdroff, target, maniptype)) + return false; + + /* must reload, offset might have changed */ + ipv6h = (void *)skb->data + iphdroff; + +manip_addr: + if (maniptype == NF_NAT_MANIP_SRC) + ipv6h->saddr = target->src.u3.in6; + else + ipv6h->daddr = target->dst.u3.in6; + +#endif + return true; +} + +unsigned int nf_nat_manip_pkt(struct sk_buff *skb, struct nf_conn *ct, + enum nf_nat_manip_type mtype, + enum ip_conntrack_dir dir) +{ + struct nf_conntrack_tuple target; + + /* We are aiming to look like inverse of other direction. */ + nf_ct_invert_tuple(&target, &ct->tuplehash[!dir].tuple); + + switch (target.src.l3num) { + case NFPROTO_IPV6: + if (nf_nat_ipv6_manip_pkt(skb, 0, &target, mtype)) + return NF_ACCEPT; + break; + case NFPROTO_IPV4: + if (nf_nat_ipv4_manip_pkt(skb, 0, &target, mtype)) + return NF_ACCEPT; + break; + default: + WARN_ON_ONCE(1); + break; + } + + return NF_DROP; +} + +static void nf_nat_ipv4_csum_update(struct sk_buff *skb, + unsigned int iphdroff, __sum16 *check, + const struct nf_conntrack_tuple *t, + enum nf_nat_manip_type maniptype) +{ + struct iphdr *iph = (struct iphdr *)(skb->data + iphdroff); + __be32 oldip, newip; + + if (maniptype == NF_NAT_MANIP_SRC) { + oldip = iph->saddr; + newip = t->src.u3.ip; + } else { + oldip = iph->daddr; + newip = t->dst.u3.ip; + } + inet_proto_csum_replace4(check, skb, oldip, newip, true); +} + +static void nf_nat_ipv6_csum_update(struct sk_buff *skb, + unsigned int iphdroff, __sum16 *check, + const struct nf_conntrack_tuple *t, + enum nf_nat_manip_type maniptype) +{ +#if IS_ENABLED(CONFIG_IPV6) + const struct ipv6hdr *ipv6h = (struct ipv6hdr *)(skb->data + iphdroff); + const struct in6_addr *oldip, *newip; + + if (maniptype == NF_NAT_MANIP_SRC) { + oldip = &ipv6h->saddr; + newip = &t->src.u3.in6; + } else { + oldip = &ipv6h->daddr; + newip = &t->dst.u3.in6; + } + inet_proto_csum_replace16(check, skb, oldip->s6_addr32, + newip->s6_addr32, true); +#endif +} + +static void nf_csum_update(struct sk_buff *skb, + unsigned int iphdroff, __sum16 *check, + const struct nf_conntrack_tuple *t, + enum nf_nat_manip_type maniptype) +{ + switch (t->src.l3num) { + case NFPROTO_IPV4: + nf_nat_ipv4_csum_update(skb, iphdroff, check, t, maniptype); + return; + case NFPROTO_IPV6: + nf_nat_ipv6_csum_update(skb, iphdroff, check, t, maniptype); + return; + } +} + +static void nf_nat_ipv4_csum_recalc(struct sk_buff *skb, + u8 proto, void *data, __sum16 *check, + int datalen, int oldlen) +{ + if (skb->ip_summed != CHECKSUM_PARTIAL) { + const struct iphdr *iph = ip_hdr(skb); + + skb->ip_summed = CHECKSUM_PARTIAL; + skb->csum_start = skb_headroom(skb) + skb_network_offset(skb) + + ip_hdrlen(skb); + skb->csum_offset = (void *)check - data; + *check = ~csum_tcpudp_magic(iph->saddr, iph->daddr, datalen, + proto, 0); + } else { + inet_proto_csum_replace2(check, skb, + htons(oldlen), htons(datalen), true); + } +} + +#if IS_ENABLED(CONFIG_IPV6) +static void nf_nat_ipv6_csum_recalc(struct sk_buff *skb, + u8 proto, void *data, __sum16 *check, + int datalen, int oldlen) +{ + if (skb->ip_summed != CHECKSUM_PARTIAL) { + const struct ipv6hdr *ipv6h = ipv6_hdr(skb); + + skb->ip_summed = CHECKSUM_PARTIAL; + skb->csum_start = skb_headroom(skb) + skb_network_offset(skb) + + (data - (void *)skb->data); + skb->csum_offset = (void *)check - data; + *check = ~csum_ipv6_magic(&ipv6h->saddr, &ipv6h->daddr, + datalen, proto, 0); + } else { + inet_proto_csum_replace2(check, skb, + htons(oldlen), htons(datalen), true); + } +} +#endif + +void nf_nat_csum_recalc(struct sk_buff *skb, + u8 nfproto, u8 proto, void *data, __sum16 *check, + int datalen, int oldlen) +{ + switch (nfproto) { + case NFPROTO_IPV4: + nf_nat_ipv4_csum_recalc(skb, proto, data, check, + datalen, oldlen); + return; +#if IS_ENABLED(CONFIG_IPV6) + case NFPROTO_IPV6: + nf_nat_ipv6_csum_recalc(skb, proto, data, check, + datalen, oldlen); + return; +#endif + } + + WARN_ON_ONCE(1); +} + +int nf_nat_icmp_reply_translation(struct sk_buff *skb, + struct nf_conn *ct, + enum ip_conntrack_info ctinfo, + unsigned int hooknum) +{ + struct { + struct icmphdr icmp; + struct iphdr ip; + } *inside; + enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); + enum nf_nat_manip_type manip = HOOK2MANIP(hooknum); + unsigned int hdrlen = ip_hdrlen(skb); + struct nf_conntrack_tuple target; + unsigned long statusbit; + + WARN_ON(ctinfo != IP_CT_RELATED && ctinfo != IP_CT_RELATED_REPLY); + + if (!skb_make_writable(skb, hdrlen + sizeof(*inside))) + return 0; + if (nf_ip_checksum(skb, hooknum, hdrlen, 0)) + return 0; + + inside = (void *)skb->data + hdrlen; + if (inside->icmp.type == ICMP_REDIRECT) { + if ((ct->status & IPS_NAT_DONE_MASK) != IPS_NAT_DONE_MASK) + return 0; + if (ct->status & IPS_NAT_MASK) + return 0; + } + + if (manip == NF_NAT_MANIP_SRC) + statusbit = IPS_SRC_NAT; + else + statusbit = IPS_DST_NAT; + + /* Invert if this is reply direction */ + if (dir == IP_CT_DIR_REPLY) + statusbit ^= IPS_NAT_MASK; + + if (!(ct->status & statusbit)) + return 1; + + if (!nf_nat_ipv4_manip_pkt(skb, hdrlen + sizeof(inside->icmp), + &ct->tuplehash[!dir].tuple, !manip)) + return 0; + + if (skb->ip_summed != CHECKSUM_PARTIAL) { + /* Reloading "inside" here since manip_pkt may reallocate */ + inside = (void *)skb->data + hdrlen; + inside->icmp.checksum = 0; + inside->icmp.checksum = + csum_fold(skb_checksum(skb, hdrlen, + skb->len - hdrlen, 0)); + } + + /* Change outer to look like the reply to an incoming packet */ + nf_ct_invert_tuple(&target, &ct->tuplehash[!dir].tuple); + target.dst.protonum = IPPROTO_ICMP; + if (!nf_nat_ipv4_manip_pkt(skb, 0, &target, manip)) + return 0; + + return 1; +} +EXPORT_SYMBOL_GPL(nf_nat_icmp_reply_translation); + +static unsigned int +nf_nat_ipv4_fn(void *priv, struct sk_buff *skb, + const struct nf_hook_state *state) +{ + struct nf_conn *ct; + enum ip_conntrack_info ctinfo; + + ct = nf_ct_get(skb, &ctinfo); + if (!ct) + return NF_ACCEPT; + + if (ctinfo == IP_CT_RELATED || ctinfo == IP_CT_RELATED_REPLY) { + if (ip_hdr(skb)->protocol == IPPROTO_ICMP) { + if (!nf_nat_icmp_reply_translation(skb, ct, ctinfo, + state->hook)) + return NF_DROP; + else + return NF_ACCEPT; + } + } + + return nf_nat_inet_fn(priv, skb, state); +} + +static unsigned int +nf_nat_ipv4_in(void *priv, struct sk_buff *skb, + const struct nf_hook_state *state) +{ + unsigned int ret; + __be32 daddr = ip_hdr(skb)->daddr; + + ret = nf_nat_ipv4_fn(priv, skb, state); + if (ret == NF_ACCEPT && daddr != ip_hdr(skb)->daddr) + skb_dst_drop(skb); + + return ret; +} + +static unsigned int +nf_nat_ipv4_out(void *priv, struct sk_buff *skb, + const struct nf_hook_state *state) +{ +#ifdef CONFIG_XFRM + const struct nf_conn *ct; + enum ip_conntrack_info ctinfo; + int err; +#endif + unsigned int ret; + + ret = nf_nat_ipv4_fn(priv, skb, state); +#ifdef CONFIG_XFRM + if (ret != NF_ACCEPT) + return ret; + + if (IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED) + return ret; + + ct = nf_ct_get(skb, &ctinfo); + if (ct) { + enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); + + if (ct->tuplehash[dir].tuple.src.u3.ip != + ct->tuplehash[!dir].tuple.dst.u3.ip || + (ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMP && + ct->tuplehash[dir].tuple.src.u.all != + ct->tuplehash[!dir].tuple.dst.u.all)) { + err = nf_xfrm_me_harder(state->net, skb, AF_INET); + if (err < 0) + ret = NF_DROP_ERR(err); + } + } +#endif + return ret; +} + +static unsigned int +nf_nat_ipv4_local_fn(void *priv, struct sk_buff *skb, + const struct nf_hook_state *state) +{ + const struct nf_conn *ct; + enum ip_conntrack_info ctinfo; + unsigned int ret; + int err; + + ret = nf_nat_ipv4_fn(priv, skb, state); + if (ret != NF_ACCEPT) + return ret; + + ct = nf_ct_get(skb, &ctinfo); + if (ct) { + enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); + + if (ct->tuplehash[dir].tuple.dst.u3.ip != + ct->tuplehash[!dir].tuple.src.u3.ip) { + err = ip_route_me_harder(state->net, skb, RTN_UNSPEC); + if (err < 0) + ret = NF_DROP_ERR(err); + } +#ifdef CONFIG_XFRM + else if (!(IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED) && + ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMP && + ct->tuplehash[dir].tuple.dst.u.all != + ct->tuplehash[!dir].tuple.src.u.all) { + err = nf_xfrm_me_harder(state->net, skb, AF_INET); + if (err < 0) + ret = NF_DROP_ERR(err); + } +#endif + } + return ret; +} + +static const struct nf_hook_ops nf_nat_ipv4_ops[] = { + /* Before packet filtering, change destination */ + { + .hook = nf_nat_ipv4_in, + .pf = NFPROTO_IPV4, + .hooknum = NF_INET_PRE_ROUTING, + .priority = NF_IP_PRI_NAT_DST, + }, + /* After packet filtering, change source */ + { + .hook = nf_nat_ipv4_out, + .pf = NFPROTO_IPV4, + .hooknum = NF_INET_POST_ROUTING, + .priority = NF_IP_PRI_NAT_SRC, + }, + /* Before packet filtering, change destination */ + { + .hook = nf_nat_ipv4_local_fn, + .pf = NFPROTO_IPV4, + .hooknum = NF_INET_LOCAL_OUT, + .priority = NF_IP_PRI_NAT_DST, + }, + /* After packet filtering, change source */ + { + .hook = nf_nat_ipv4_fn, + .pf = NFPROTO_IPV4, + .hooknum = NF_INET_LOCAL_IN, + .priority = NF_IP_PRI_NAT_SRC, + }, +}; + +int nf_nat_ipv4_register_fn(struct net *net, const struct nf_hook_ops *ops) +{ + return nf_nat_register_fn(net, ops, nf_nat_ipv4_ops, ARRAY_SIZE(nf_nat_ipv4_ops)); +} +EXPORT_SYMBOL_GPL(nf_nat_ipv4_register_fn); + +void nf_nat_ipv4_unregister_fn(struct net *net, const struct nf_hook_ops *ops) +{ + nf_nat_unregister_fn(net, ops, ARRAY_SIZE(nf_nat_ipv4_ops)); +} +EXPORT_SYMBOL_GPL(nf_nat_ipv4_unregister_fn); + +#if IS_ENABLED(CONFIG_IPV6) +int nf_nat_icmpv6_reply_translation(struct sk_buff *skb, + struct nf_conn *ct, + enum ip_conntrack_info ctinfo, + unsigned int hooknum, + unsigned int hdrlen) +{ + struct { + struct icmp6hdr icmp6; + struct ipv6hdr ip6; + } *inside; + enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); + enum nf_nat_manip_type manip = HOOK2MANIP(hooknum); + struct nf_conntrack_tuple target; + unsigned long statusbit; + + WARN_ON(ctinfo != IP_CT_RELATED && ctinfo != IP_CT_RELATED_REPLY); + + if (!skb_make_writable(skb, hdrlen + sizeof(*inside))) + return 0; + if (nf_ip6_checksum(skb, hooknum, hdrlen, IPPROTO_ICMPV6)) + return 0; + + inside = (void *)skb->data + hdrlen; + if (inside->icmp6.icmp6_type == NDISC_REDIRECT) { + if ((ct->status & IPS_NAT_DONE_MASK) != IPS_NAT_DONE_MASK) + return 0; + if (ct->status & IPS_NAT_MASK) + return 0; + } + + if (manip == NF_NAT_MANIP_SRC) + statusbit = IPS_SRC_NAT; + else + statusbit = IPS_DST_NAT; + + /* Invert if this is reply direction */ + if (dir == IP_CT_DIR_REPLY) + statusbit ^= IPS_NAT_MASK; + + if (!(ct->status & statusbit)) + return 1; + + if (!nf_nat_ipv6_manip_pkt(skb, hdrlen + sizeof(inside->icmp6), + &ct->tuplehash[!dir].tuple, !manip)) + return 0; + + if (skb->ip_summed != CHECKSUM_PARTIAL) { + struct ipv6hdr *ipv6h = ipv6_hdr(skb); + + inside = (void *)skb->data + hdrlen; + inside->icmp6.icmp6_cksum = 0; + inside->icmp6.icmp6_cksum = + csum_ipv6_magic(&ipv6h->saddr, &ipv6h->daddr, + skb->len - hdrlen, IPPROTO_ICMPV6, + skb_checksum(skb, hdrlen, + skb->len - hdrlen, 0)); + } + + nf_ct_invert_tuple(&target, &ct->tuplehash[!dir].tuple); + target.dst.protonum = IPPROTO_ICMPV6; + if (!nf_nat_ipv6_manip_pkt(skb, 0, &target, manip)) + return 0; + + return 1; +} +EXPORT_SYMBOL_GPL(nf_nat_icmpv6_reply_translation); + +static unsigned int +nf_nat_ipv6_fn(void *priv, struct sk_buff *skb, + const struct nf_hook_state *state) +{ + struct nf_conn *ct; + enum ip_conntrack_info ctinfo; + __be16 frag_off; + int hdrlen; + u8 nexthdr; + + ct = nf_ct_get(skb, &ctinfo); + /* Can't track? It's not due to stress, or conntrack would + * have dropped it. Hence it's the user's responsibilty to + * packet filter it out, or implement conntrack/NAT for that + * protocol. 8) --RR + */ + if (!ct) + return NF_ACCEPT; + + if (ctinfo == IP_CT_RELATED || ctinfo == IP_CT_RELATED_REPLY) { + nexthdr = ipv6_hdr(skb)->nexthdr; + hdrlen = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), + &nexthdr, &frag_off); + + if (hdrlen >= 0 && nexthdr == IPPROTO_ICMPV6) { + if (!nf_nat_icmpv6_reply_translation(skb, ct, ctinfo, + state->hook, + hdrlen)) + return NF_DROP; + else + return NF_ACCEPT; + } + } + + return nf_nat_inet_fn(priv, skb, state); +} + +static unsigned int +nf_nat_ipv6_in(void *priv, struct sk_buff *skb, + const struct nf_hook_state *state) +{ + unsigned int ret; + struct in6_addr daddr = ipv6_hdr(skb)->daddr; + + ret = nf_nat_ipv6_fn(priv, skb, state); + if (ret != NF_DROP && ret != NF_STOLEN && + ipv6_addr_cmp(&daddr, &ipv6_hdr(skb)->daddr)) + skb_dst_drop(skb); + + return ret; +} + +static unsigned int +nf_nat_ipv6_out(void *priv, struct sk_buff *skb, + const struct nf_hook_state *state) +{ +#ifdef CONFIG_XFRM + const struct nf_conn *ct; + enum ip_conntrack_info ctinfo; + int err; +#endif + unsigned int ret; + + ret = nf_nat_ipv6_fn(priv, skb, state); +#ifdef CONFIG_XFRM + if (ret != NF_ACCEPT) + return ret; + + if (IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) + return ret; + ct = nf_ct_get(skb, &ctinfo); + if (ct) { + enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); + + if (!nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.src.u3, + &ct->tuplehash[!dir].tuple.dst.u3) || + (ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMPV6 && + ct->tuplehash[dir].tuple.src.u.all != + ct->tuplehash[!dir].tuple.dst.u.all)) { + err = nf_xfrm_me_harder(state->net, skb, AF_INET6); + if (err < 0) + ret = NF_DROP_ERR(err); + } + } +#endif + + return ret; +} + +static int nat_route_me_harder(struct net *net, struct sk_buff *skb) +{ +#ifdef CONFIG_IPV6_MODULE + const struct nf_ipv6_ops *v6_ops = nf_get_ipv6_ops(); + + if (!v6_ops) + return -EHOSTUNREACH; + + return v6_ops->route_me_harder(net, skb); +#else + return ip6_route_me_harder(net, skb); +#endif +} + +static unsigned int +nf_nat_ipv6_local_fn(void *priv, struct sk_buff *skb, + const struct nf_hook_state *state) +{ + const struct nf_conn *ct; + enum ip_conntrack_info ctinfo; + unsigned int ret; + int err; + + ret = nf_nat_ipv6_fn(priv, skb, state); + if (ret != NF_ACCEPT) + return ret; + + ct = nf_ct_get(skb, &ctinfo); + if (ct) { + enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); + + if (!nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.dst.u3, + &ct->tuplehash[!dir].tuple.src.u3)) { + err = nat_route_me_harder(state->net, skb); + if (err < 0) + ret = NF_DROP_ERR(err); + } +#ifdef CONFIG_XFRM + else if (!(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) && + ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMPV6 && + ct->tuplehash[dir].tuple.dst.u.all != + ct->tuplehash[!dir].tuple.src.u.all) { + err = nf_xfrm_me_harder(state->net, skb, AF_INET6); + if (err < 0) + ret = NF_DROP_ERR(err); + } +#endif + } + + return ret; +} + +static const struct nf_hook_ops nf_nat_ipv6_ops[] = { + /* Before packet filtering, change destination */ + { + .hook = nf_nat_ipv6_in, + .pf = NFPROTO_IPV6, + .hooknum = NF_INET_PRE_ROUTING, + .priority = NF_IP6_PRI_NAT_DST, + }, + /* After packet filtering, change source */ + { + .hook = nf_nat_ipv6_out, + .pf = NFPROTO_IPV6, + .hooknum = NF_INET_POST_ROUTING, + .priority = NF_IP6_PRI_NAT_SRC, + }, + /* Before packet filtering, change destination */ + { + .hook = nf_nat_ipv6_local_fn, + .pf = NFPROTO_IPV6, + .hooknum = NF_INET_LOCAL_OUT, + .priority = NF_IP6_PRI_NAT_DST, + }, + /* After packet filtering, change source */ + { + .hook = nf_nat_ipv6_fn, + .pf = NFPROTO_IPV6, + .hooknum = NF_INET_LOCAL_IN, + .priority = NF_IP6_PRI_NAT_SRC, + }, +}; + +int nf_nat_ipv6_register_fn(struct net *net, const struct nf_hook_ops *ops) +{ + return nf_nat_register_fn(net, ops, nf_nat_ipv6_ops, + ARRAY_SIZE(nf_nat_ipv6_ops)); +} +EXPORT_SYMBOL_GPL(nf_nat_ipv6_register_fn); + +void nf_nat_ipv6_unregister_fn(struct net *net, const struct nf_hook_ops *ops) +{ + nf_nat_unregister_fn(net, ops, ARRAY_SIZE(nf_nat_ipv6_ops)); +} +EXPORT_SYMBOL_GPL(nf_nat_ipv6_unregister_fn); +#endif /* CONFIG_IPV6 */ diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index e1a88ba2249e..faf6bd10a19f 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -2172,6 +2172,7 @@ struct nft_expr *nft_expr_init(const struct nft_ctx *ctx, { struct nft_expr_info info; struct nft_expr *expr; + struct module *owner; int err; err = nf_tables_expr_parse(ctx, nla, &info); @@ -2191,7 +2192,11 @@ struct nft_expr *nft_expr_init(const struct nft_ctx *ctx, err3: kfree(expr); err2: - module_put(info.ops->type->owner); + owner = info.ops->type->owner; + if (info.ops->type->release_ops) + info.ops->type->release_ops(info.ops); + + module_put(owner); err1: return ERR_PTR(err); } diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c index 2a00aef7b6d4..d0f168c2670f 100644 --- a/net/netfilter/nf_tables_core.c +++ b/net/netfilter/nf_tables_core.c @@ -98,21 +98,23 @@ static noinline void nft_update_chain_stats(const struct nft_chain *chain, const struct nft_pktinfo *pkt) { struct nft_base_chain *base_chain; + struct nft_stats __percpu *pstats; struct nft_stats *stats; base_chain = nft_base_chain(chain); - if (!rcu_access_pointer(base_chain->stats)) - return; - local_bh_disable(); - stats = this_cpu_ptr(rcu_dereference(base_chain->stats)); - if (stats) { + rcu_read_lock(); + pstats = READ_ONCE(base_chain->stats); + if (pstats) { + local_bh_disable(); + stats = this_cpu_ptr(pstats); u64_stats_update_begin(&stats->syncp); stats->pkts++; stats->bytes += pkt->skb->len; u64_stats_update_end(&stats->syncp); + local_bh_enable(); } - local_bh_enable(); + rcu_read_unlock(); } struct nft_jumpstack { @@ -221,7 +223,6 @@ next_rule: chain = regs.verdict.chain; goto do_chain; case NFT_CONTINUE: - /* fall through */ case NFT_RETURN: nft_trace_packet(&info, chain, rule, NFT_TRACETYPE_RETURN); diff --git a/net/netfilter/nft_chain_nat.c b/net/netfilter/nft_chain_nat.c new file mode 100644 index 000000000000..ee4852088d50 --- /dev/null +++ b/net/netfilter/nft_chain_nat.c @@ -0,0 +1,108 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/module.h> +#include <linux/netfilter/nf_tables.h> +#include <net/netfilter/nf_nat.h> +#include <net/netfilter/nf_tables.h> +#include <net/netfilter/nf_tables_ipv4.h> +#include <net/netfilter/nf_tables_ipv6.h> + +static unsigned int nft_nat_do_chain(void *priv, struct sk_buff *skb, + const struct nf_hook_state *state) +{ + struct nft_pktinfo pkt; + + nft_set_pktinfo(&pkt, skb, state); + + switch (state->pf) { +#ifdef CONFIG_NF_TABLES_IPV4 + case NFPROTO_IPV4: + nft_set_pktinfo_ipv4(&pkt, skb); + break; +#endif +#ifdef CONFIG_NF_TABLES_IPV6 + case NFPROTO_IPV6: + nft_set_pktinfo_ipv6(&pkt, skb); + break; +#endif + default: + break; + } + + return nft_do_chain(&pkt, priv); +} + +#ifdef CONFIG_NF_TABLES_IPV4 +static const struct nft_chain_type nft_chain_nat_ipv4 = { + .name = "nat", + .type = NFT_CHAIN_T_NAT, + .family = NFPROTO_IPV4, + .owner = THIS_MODULE, + .hook_mask = (1 << NF_INET_PRE_ROUTING) | + (1 << NF_INET_POST_ROUTING) | + (1 << NF_INET_LOCAL_OUT) | + (1 << NF_INET_LOCAL_IN), + .hooks = { + [NF_INET_PRE_ROUTING] = nft_nat_do_chain, + [NF_INET_POST_ROUTING] = nft_nat_do_chain, + [NF_INET_LOCAL_OUT] = nft_nat_do_chain, + [NF_INET_LOCAL_IN] = nft_nat_do_chain, + }, + .ops_register = nf_nat_ipv4_register_fn, + .ops_unregister = nf_nat_ipv4_unregister_fn, +}; +#endif + +#ifdef CONFIG_NF_TABLES_IPV6 +static const struct nft_chain_type nft_chain_nat_ipv6 = { + .name = "nat", + .type = NFT_CHAIN_T_NAT, + .family = NFPROTO_IPV6, + .owner = THIS_MODULE, + .hook_mask = (1 << NF_INET_PRE_ROUTING) | + (1 << NF_INET_POST_ROUTING) | + (1 << NF_INET_LOCAL_OUT) | + (1 << NF_INET_LOCAL_IN), + .hooks = { + [NF_INET_PRE_ROUTING] = nft_nat_do_chain, + [NF_INET_POST_ROUTING] = nft_nat_do_chain, + [NF_INET_LOCAL_OUT] = nft_nat_do_chain, + [NF_INET_LOCAL_IN] = nft_nat_do_chain, + }, + .ops_register = nf_nat_ipv6_register_fn, + .ops_unregister = nf_nat_ipv6_unregister_fn, +}; +#endif + +static int __init nft_chain_nat_init(void) +{ +#ifdef CONFIG_NF_TABLES_IPV6 + nft_register_chain_type(&nft_chain_nat_ipv6); +#endif +#ifdef CONFIG_NF_TABLES_IPV4 + nft_register_chain_type(&nft_chain_nat_ipv4); +#endif + + return 0; +} + +static void __exit nft_chain_nat_exit(void) +{ +#ifdef CONFIG_NF_TABLES_IPV4 + nft_unregister_chain_type(&nft_chain_nat_ipv4); +#endif +#ifdef CONFIG_NF_TABLES_IPV6 + nft_unregister_chain_type(&nft_chain_nat_ipv6); +#endif +} + +module_init(nft_chain_nat_init); +module_exit(nft_chain_nat_exit); + +MODULE_LICENSE("GPL"); +#ifdef CONFIG_NF_TABLES_IPV4 +MODULE_ALIAS_NFT_CHAIN(AF_INET, "nat"); +#endif +#ifdef CONFIG_NF_TABLES_IPV6 +MODULE_ALIAS_NFT_CHAIN(AF_INET6, "nat"); +#endif diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c index 0a4bad55a8aa..469f9da5073b 100644 --- a/net/netfilter/nft_compat.c +++ b/net/netfilter/nft_compat.c @@ -22,23 +22,6 @@ #include <linux/netfilter_bridge/ebtables.h> #include <linux/netfilter_arp/arp_tables.h> #include <net/netfilter/nf_tables.h> -#include <net/netns/generic.h> - -struct nft_xt { - struct list_head head; - struct nft_expr_ops ops; - refcount_t refcnt; - - /* used only when transaction mutex is locked */ - unsigned int listcnt; - - /* Unlike other expressions, ops doesn't have static storage duration. - * nft core assumes they do. We use kfree_rcu so that nft core can - * can check expr->ops->size even after nft_compat->destroy() frees - * the nft_xt struct that holds the ops structure. - */ - struct rcu_head rcu_head; -}; /* Used for matches where *info is larger than X byte */ #define NFT_MATCH_LARGE_THRESH 192 @@ -47,46 +30,6 @@ struct nft_xt_match_priv { void *info; }; -struct nft_compat_net { - struct list_head nft_target_list; - struct list_head nft_match_list; -}; - -static unsigned int nft_compat_net_id __read_mostly; -static struct nft_expr_type nft_match_type; -static struct nft_expr_type nft_target_type; - -static struct nft_compat_net *nft_compat_pernet(struct net *net) -{ - return net_generic(net, nft_compat_net_id); -} - -static void nft_xt_get(struct nft_xt *xt) -{ - /* refcount_inc() warns on 0 -> 1 transition, but we can't - * init the reference count to 1 in .select_ops -- we can't - * undo such an increase when another expression inside the same - * rule fails afterwards. - */ - if (xt->listcnt == 0) - refcount_set(&xt->refcnt, 1); - else - refcount_inc(&xt->refcnt); - - xt->listcnt++; -} - -static bool nft_xt_put(struct nft_xt *xt) -{ - if (refcount_dec_and_test(&xt->refcnt)) { - WARN_ON_ONCE(!list_empty(&xt->head)); - kfree_rcu(xt, rcu_head); - return true; - } - - return false; -} - static int nft_compat_chain_validate_dependency(const struct nft_ctx *ctx, const char *tablename) { @@ -281,7 +224,6 @@ nft_target_init(const struct nft_ctx *ctx, const struct nft_expr *expr, struct xt_target *target = expr->ops->data; struct xt_tgchk_param par; size_t size = XT_ALIGN(nla_len(tb[NFTA_TARGET_INFO])); - struct nft_xt *nft_xt; u16 proto = 0; bool inv = false; union nft_entry e = {}; @@ -305,8 +247,6 @@ nft_target_init(const struct nft_ctx *ctx, const struct nft_expr *expr, if (!target->target) return -EINVAL; - nft_xt = container_of(expr->ops, struct nft_xt, ops); - nft_xt_get(nft_xt); return 0; } @@ -325,8 +265,8 @@ nft_target_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr) if (par.target->destroy != NULL) par.target->destroy(&par); - if (nft_xt_put(container_of(expr->ops, struct nft_xt, ops))) - module_put(me); + module_put(me); + kfree(expr->ops); } static int nft_extension_dump_info(struct sk_buff *skb, int attr, @@ -499,7 +439,6 @@ __nft_match_init(const struct nft_ctx *ctx, const struct nft_expr *expr, struct xt_match *match = expr->ops->data; struct xt_mtchk_param par; size_t size = XT_ALIGN(nla_len(tb[NFTA_MATCH_INFO])); - struct nft_xt *nft_xt; u16 proto = 0; bool inv = false; union nft_entry e = {}; @@ -515,13 +454,7 @@ __nft_match_init(const struct nft_ctx *ctx, const struct nft_expr *expr, nft_match_set_mtchk_param(&par, ctx, match, info, &e, proto, inv); - ret = xt_check_match(&par, size, proto, inv); - if (ret < 0) - return ret; - - nft_xt = container_of(expr->ops, struct nft_xt, ops); - nft_xt_get(nft_xt); - return 0; + return xt_check_match(&par, size, proto, inv); } static int @@ -564,8 +497,8 @@ __nft_match_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr, if (par.match->destroy != NULL) par.match->destroy(&par); - if (nft_xt_put(container_of(expr->ops, struct nft_xt, ops))) - module_put(me); + module_put(me); + kfree(expr->ops); } static void @@ -574,18 +507,6 @@ nft_match_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr) __nft_match_destroy(ctx, expr, nft_expr_priv(expr)); } -static void nft_compat_deactivate(const struct nft_ctx *ctx, - const struct nft_expr *expr, - enum nft_trans_phase phase) -{ - struct nft_xt *xt = container_of(expr->ops, struct nft_xt, ops); - - if (phase == NFT_TRANS_ABORT || phase == NFT_TRANS_COMMIT) { - if (--xt->listcnt == 0) - list_del_init(&xt->head); - } -} - static void nft_match_large_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr) { @@ -780,19 +701,13 @@ static const struct nfnetlink_subsystem nfnl_compat_subsys = { .cb = nfnl_nft_compat_cb, }; -static bool nft_match_cmp(const struct xt_match *match, - const char *name, u32 rev, u32 family) -{ - return strcmp(match->name, name) == 0 && match->revision == rev && - (match->family == NFPROTO_UNSPEC || match->family == family); -} +static struct nft_expr_type nft_match_type; static const struct nft_expr_ops * nft_match_select_ops(const struct nft_ctx *ctx, const struct nlattr * const tb[]) { - struct nft_compat_net *cn; - struct nft_xt *nft_match; + struct nft_expr_ops *ops; struct xt_match *match; unsigned int matchsize; char *mt_name; @@ -808,16 +723,6 @@ nft_match_select_ops(const struct nft_ctx *ctx, rev = ntohl(nla_get_be32(tb[NFTA_MATCH_REV])); family = ctx->family; - cn = nft_compat_pernet(ctx->net); - - /* Re-use the existing match if it's already loaded. */ - list_for_each_entry(nft_match, &cn->nft_match_list, head) { - struct xt_match *match = nft_match->ops.data; - - if (nft_match_cmp(match, mt_name, rev, family)) - return &nft_match->ops; - } - match = xt_request_find_match(family, mt_name, rev); if (IS_ERR(match)) return ERR_PTR(-ENOENT); @@ -827,65 +732,62 @@ nft_match_select_ops(const struct nft_ctx *ctx, goto err; } - /* This is the first time we use this match, allocate operations */ - nft_match = kzalloc(sizeof(struct nft_xt), GFP_KERNEL); - if (nft_match == NULL) { + ops = kzalloc(sizeof(struct nft_expr_ops), GFP_KERNEL); + if (!ops) { err = -ENOMEM; goto err; } - refcount_set(&nft_match->refcnt, 0); - nft_match->ops.type = &nft_match_type; - nft_match->ops.eval = nft_match_eval; - nft_match->ops.init = nft_match_init; - nft_match->ops.destroy = nft_match_destroy; - nft_match->ops.deactivate = nft_compat_deactivate; - nft_match->ops.dump = nft_match_dump; - nft_match->ops.validate = nft_match_validate; - nft_match->ops.data = match; + ops->type = &nft_match_type; + ops->eval = nft_match_eval; + ops->init = nft_match_init; + ops->destroy = nft_match_destroy; + ops->dump = nft_match_dump; + ops->validate = nft_match_validate; + ops->data = match; matchsize = NFT_EXPR_SIZE(XT_ALIGN(match->matchsize)); if (matchsize > NFT_MATCH_LARGE_THRESH) { matchsize = NFT_EXPR_SIZE(sizeof(struct nft_xt_match_priv)); - nft_match->ops.eval = nft_match_large_eval; - nft_match->ops.init = nft_match_large_init; - nft_match->ops.destroy = nft_match_large_destroy; - nft_match->ops.dump = nft_match_large_dump; + ops->eval = nft_match_large_eval; + ops->init = nft_match_large_init; + ops->destroy = nft_match_large_destroy; + ops->dump = nft_match_large_dump; } - nft_match->ops.size = matchsize; + ops->size = matchsize; - nft_match->listcnt = 0; - list_add(&nft_match->head, &cn->nft_match_list); - - return &nft_match->ops; + return ops; err: module_put(match->me); return ERR_PTR(err); } +static void nft_match_release_ops(const struct nft_expr_ops *ops) +{ + struct xt_match *match = ops->data; + + module_put(match->me); + kfree(ops); +} + static struct nft_expr_type nft_match_type __read_mostly = { .name = "match", .select_ops = nft_match_select_ops, + .release_ops = nft_match_release_ops, .policy = nft_match_policy, .maxattr = NFTA_MATCH_MAX, .owner = THIS_MODULE, }; -static bool nft_target_cmp(const struct xt_target *tg, - const char *name, u32 rev, u32 family) -{ - return strcmp(tg->name, name) == 0 && tg->revision == rev && - (tg->family == NFPROTO_UNSPEC || tg->family == family); -} +static struct nft_expr_type nft_target_type; static const struct nft_expr_ops * nft_target_select_ops(const struct nft_ctx *ctx, const struct nlattr * const tb[]) { - struct nft_compat_net *cn; - struct nft_xt *nft_target; + struct nft_expr_ops *ops; struct xt_target *target; char *tg_name; u32 rev, family; @@ -905,18 +807,6 @@ nft_target_select_ops(const struct nft_ctx *ctx, strcmp(tg_name, "standard") == 0) return ERR_PTR(-EINVAL); - cn = nft_compat_pernet(ctx->net); - /* Re-use the existing target if it's already loaded. */ - list_for_each_entry(nft_target, &cn->nft_target_list, head) { - struct xt_target *target = nft_target->ops.data; - - if (!target->target) - continue; - - if (nft_target_cmp(target, tg_name, rev, family)) - return &nft_target->ops; - } - target = xt_request_find_target(family, tg_name, rev); if (IS_ERR(target)) return ERR_PTR(-ENOENT); @@ -931,113 +821,55 @@ nft_target_select_ops(const struct nft_ctx *ctx, goto err; } - /* This is the first time we use this target, allocate operations */ - nft_target = kzalloc(sizeof(struct nft_xt), GFP_KERNEL); - if (nft_target == NULL) { + ops = kzalloc(sizeof(struct nft_expr_ops), GFP_KERNEL); + if (!ops) { err = -ENOMEM; goto err; } - refcount_set(&nft_target->refcnt, 0); - nft_target->ops.type = &nft_target_type; - nft_target->ops.size = NFT_EXPR_SIZE(XT_ALIGN(target->targetsize)); - nft_target->ops.init = nft_target_init; - nft_target->ops.destroy = nft_target_destroy; - nft_target->ops.deactivate = nft_compat_deactivate; - nft_target->ops.dump = nft_target_dump; - nft_target->ops.validate = nft_target_validate; - nft_target->ops.data = target; + ops->type = &nft_target_type; + ops->size = NFT_EXPR_SIZE(XT_ALIGN(target->targetsize)); + ops->init = nft_target_init; + ops->destroy = nft_target_destroy; + ops->dump = nft_target_dump; + ops->validate = nft_target_validate; + ops->data = target; if (family == NFPROTO_BRIDGE) - nft_target->ops.eval = nft_target_eval_bridge; + ops->eval = nft_target_eval_bridge; else - nft_target->ops.eval = nft_target_eval_xt; - - nft_target->listcnt = 0; - list_add(&nft_target->head, &cn->nft_target_list); + ops->eval = nft_target_eval_xt; - return &nft_target->ops; + return ops; err: module_put(target->me); return ERR_PTR(err); } +static void nft_target_release_ops(const struct nft_expr_ops *ops) +{ + struct xt_target *target = ops->data; + + module_put(target->me); + kfree(ops); +} + static struct nft_expr_type nft_target_type __read_mostly = { .name = "target", .select_ops = nft_target_select_ops, + .release_ops = nft_target_release_ops, .policy = nft_target_policy, .maxattr = NFTA_TARGET_MAX, .owner = THIS_MODULE, }; -static int __net_init nft_compat_init_net(struct net *net) -{ - struct nft_compat_net *cn = nft_compat_pernet(net); - - INIT_LIST_HEAD(&cn->nft_target_list); - INIT_LIST_HEAD(&cn->nft_match_list); - - return 0; -} - -static void __net_exit nft_compat_exit_net(struct net *net) -{ - struct nft_compat_net *cn = nft_compat_pernet(net); - struct nft_xt *xt, *next; - - if (list_empty(&cn->nft_match_list) && - list_empty(&cn->nft_target_list)) - return; - - /* If there was an error that caused nft_xt expr to not be initialized - * fully and noone else requested the same expression later, the lists - * contain 0-refcount entries that still hold module reference. - * - * Clean them here. - */ - mutex_lock(&net->nft.commit_mutex); - list_for_each_entry_safe(xt, next, &cn->nft_target_list, head) { - struct xt_target *target = xt->ops.data; - - list_del_init(&xt->head); - - if (refcount_read(&xt->refcnt)) - continue; - module_put(target->me); - kfree(xt); - } - - list_for_each_entry_safe(xt, next, &cn->nft_match_list, head) { - struct xt_match *match = xt->ops.data; - - list_del_init(&xt->head); - - if (refcount_read(&xt->refcnt)) - continue; - module_put(match->me); - kfree(xt); - } - mutex_unlock(&net->nft.commit_mutex); -} - -static struct pernet_operations nft_compat_net_ops = { - .init = nft_compat_init_net, - .exit = nft_compat_exit_net, - .id = &nft_compat_net_id, - .size = sizeof(struct nft_compat_net), -}; - static int __init nft_compat_module_init(void) { int ret; - ret = register_pernet_subsys(&nft_compat_net_ops); - if (ret < 0) - goto err_target; - ret = nft_register_expr(&nft_match_type); if (ret < 0) - goto err_pernet; + return ret; ret = nft_register_expr(&nft_target_type); if (ret < 0) @@ -1054,8 +886,6 @@ err_target: nft_unregister_expr(&nft_target_type); err_match: nft_unregister_expr(&nft_match_type); -err_pernet: - unregister_pernet_subsys(&nft_compat_net_ops); return ret; } @@ -1064,7 +894,6 @@ static void __exit nft_compat_module_exit(void) nfnetlink_subsys_unregister(&nfnl_compat_subsys); nft_unregister_expr(&nft_target_type); nft_unregister_expr(&nft_match_type); - unregister_pernet_subsys(&nft_compat_net_ops); } MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_NFT_COMPAT); diff --git a/net/netfilter/nft_masq.c b/net/netfilter/nft_masq.c index 9d8655bc1bea..bee156eaa400 100644 --- a/net/netfilter/nft_masq.c +++ b/net/netfilter/nft_masq.c @@ -14,18 +14,24 @@ #include <linux/netfilter/nf_tables.h> #include <net/netfilter/nf_tables.h> #include <net/netfilter/nf_nat.h> -#include <net/netfilter/nft_masq.h> +#include <net/netfilter/ipv4/nf_nat_masquerade.h> +#include <net/netfilter/ipv6/nf_nat_masquerade.h> -const struct nla_policy nft_masq_policy[NFTA_MASQ_MAX + 1] = { +struct nft_masq { + u32 flags; + enum nft_registers sreg_proto_min:8; + enum nft_registers sreg_proto_max:8; +}; + +static const struct nla_policy nft_masq_policy[NFTA_MASQ_MAX + 1] = { [NFTA_MASQ_FLAGS] = { .type = NLA_U32 }, [NFTA_MASQ_REG_PROTO_MIN] = { .type = NLA_U32 }, [NFTA_MASQ_REG_PROTO_MAX] = { .type = NLA_U32 }, }; -EXPORT_SYMBOL_GPL(nft_masq_policy); -int nft_masq_validate(const struct nft_ctx *ctx, - const struct nft_expr *expr, - const struct nft_data **data) +static int nft_masq_validate(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nft_data **data) { int err; @@ -36,11 +42,10 @@ int nft_masq_validate(const struct nft_ctx *ctx, return nft_chain_validate_hooks(ctx->chain, (1 << NF_INET_POST_ROUTING)); } -EXPORT_SYMBOL_GPL(nft_masq_validate); -int nft_masq_init(const struct nft_ctx *ctx, - const struct nft_expr *expr, - const struct nlattr * const tb[]) +static int nft_masq_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]) { u32 plen = FIELD_SIZEOF(struct nf_nat_range, min_addr.all); struct nft_masq *priv = nft_expr_priv(expr); @@ -75,9 +80,8 @@ int nft_masq_init(const struct nft_ctx *ctx, return nf_ct_netns_get(ctx->net, ctx->family); } -EXPORT_SYMBOL_GPL(nft_masq_init); -int nft_masq_dump(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_masq_dump(struct sk_buff *skb, const struct nft_expr *expr) { const struct nft_masq *priv = nft_expr_priv(expr); @@ -98,7 +102,157 @@ int nft_masq_dump(struct sk_buff *skb, const struct nft_expr *expr) nla_put_failure: return -1; } -EXPORT_SYMBOL_GPL(nft_masq_dump); + +static void nft_masq_ipv4_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + struct nft_masq *priv = nft_expr_priv(expr); + struct nf_nat_range2 range; + + memset(&range, 0, sizeof(range)); + range.flags = priv->flags; + if (priv->sreg_proto_min) { + range.min_proto.all = (__force __be16)nft_reg_load16( + ®s->data[priv->sreg_proto_min]); + range.max_proto.all = (__force __be16)nft_reg_load16( + ®s->data[priv->sreg_proto_max]); + } + regs->verdict.code = nf_nat_masquerade_ipv4(pkt->skb, nft_hook(pkt), + &range, nft_out(pkt)); +} + +static void +nft_masq_ipv4_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr) +{ + nf_ct_netns_put(ctx->net, NFPROTO_IPV4); +} + +static struct nft_expr_type nft_masq_ipv4_type; +static const struct nft_expr_ops nft_masq_ipv4_ops = { + .type = &nft_masq_ipv4_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_masq)), + .eval = nft_masq_ipv4_eval, + .init = nft_masq_init, + .destroy = nft_masq_ipv4_destroy, + .dump = nft_masq_dump, + .validate = nft_masq_validate, +}; + +static struct nft_expr_type nft_masq_ipv4_type __read_mostly = { + .family = NFPROTO_IPV4, + .name = "masq", + .ops = &nft_masq_ipv4_ops, + .policy = nft_masq_policy, + .maxattr = NFTA_MASQ_MAX, + .owner = THIS_MODULE, +}; + +#ifdef CONFIG_NF_TABLES_IPV6 +static void nft_masq_ipv6_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + struct nft_masq *priv = nft_expr_priv(expr); + struct nf_nat_range2 range; + + memset(&range, 0, sizeof(range)); + range.flags = priv->flags; + if (priv->sreg_proto_min) { + range.min_proto.all = (__force __be16)nft_reg_load16( + ®s->data[priv->sreg_proto_min]); + range.max_proto.all = (__force __be16)nft_reg_load16( + ®s->data[priv->sreg_proto_max]); + } + regs->verdict.code = nf_nat_masquerade_ipv6(pkt->skb, &range, + nft_out(pkt)); +} + +static void +nft_masq_ipv6_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr) +{ + nf_ct_netns_put(ctx->net, NFPROTO_IPV6); +} + +static struct nft_expr_type nft_masq_ipv6_type; +static const struct nft_expr_ops nft_masq_ipv6_ops = { + .type = &nft_masq_ipv6_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_masq)), + .eval = nft_masq_ipv6_eval, + .init = nft_masq_init, + .destroy = nft_masq_ipv6_destroy, + .dump = nft_masq_dump, + .validate = nft_masq_validate, +}; + +static struct nft_expr_type nft_masq_ipv6_type __read_mostly = { + .family = NFPROTO_IPV6, + .name = "masq", + .ops = &nft_masq_ipv6_ops, + .policy = nft_masq_policy, + .maxattr = NFTA_MASQ_MAX, + .owner = THIS_MODULE, +}; + +static int __init nft_masq_module_init_ipv6(void) +{ + int ret = nft_register_expr(&nft_masq_ipv6_type); + + if (ret) + return ret; + + ret = nf_nat_masquerade_ipv6_register_notifier(); + if (ret < 0) + nft_unregister_expr(&nft_masq_ipv6_type); + + return ret; +} + +static void nft_masq_module_exit_ipv6(void) +{ + nft_unregister_expr(&nft_masq_ipv6_type); + nf_nat_masquerade_ipv6_unregister_notifier(); +} +#else +static inline int nft_masq_module_init_ipv6(void) { return 0; } +static inline void nft_masq_module_exit_ipv6(void) {} +#endif + +static int __init nft_masq_module_init(void) +{ + int ret; + + ret = nft_masq_module_init_ipv6(); + if (ret < 0) + return ret; + + ret = nft_register_expr(&nft_masq_ipv4_type); + if (ret < 0) { + nft_masq_module_exit_ipv6(); + return ret; + } + + ret = nf_nat_masquerade_ipv4_register_notifier(); + if (ret < 0) { + nft_masq_module_exit_ipv6(); + nft_unregister_expr(&nft_masq_ipv4_type); + return ret; + } + + return ret; +} + +static void __exit nft_masq_module_exit(void) +{ + nft_masq_module_exit_ipv6(); + nft_unregister_expr(&nft_masq_ipv4_type); + nf_nat_masquerade_ipv4_unregister_notifier(); +} + +module_init(nft_masq_module_init); +module_exit(nft_masq_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Arturo Borrero Gonzalez <arturo@debian.org>"); +MODULE_ALIAS_NFT_AF_EXPR(AF_INET6, "masq"); +MODULE_ALIAS_NFT_AF_EXPR(AF_INET, "masq"); diff --git a/net/netfilter/nft_nat.c b/net/netfilter/nft_nat.c index c15807d10b91..e93aed9bda88 100644 --- a/net/netfilter/nft_nat.c +++ b/net/netfilter/nft_nat.c @@ -21,9 +21,7 @@ #include <linux/netfilter/nf_tables.h> #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_nat.h> -#include <net/netfilter/nf_nat_core.h> #include <net/netfilter/nf_tables.h> -#include <net/netfilter/nf_nat_l3proto.h> #include <net/ip.h> struct nft_nat { diff --git a/net/netfilter/nft_redir.c b/net/netfilter/nft_redir.c index c64cbe78dee7..f8092926f704 100644 --- a/net/netfilter/nft_redir.c +++ b/net/netfilter/nft_redir.c @@ -13,19 +13,24 @@ #include <linux/netfilter.h> #include <linux/netfilter/nf_tables.h> #include <net/netfilter/nf_nat.h> +#include <net/netfilter/nf_nat_redirect.h> #include <net/netfilter/nf_tables.h> -#include <net/netfilter/nft_redir.h> -const struct nla_policy nft_redir_policy[NFTA_REDIR_MAX + 1] = { +struct nft_redir { + enum nft_registers sreg_proto_min:8; + enum nft_registers sreg_proto_max:8; + u16 flags; +}; + +static const struct nla_policy nft_redir_policy[NFTA_REDIR_MAX + 1] = { [NFTA_REDIR_REG_PROTO_MIN] = { .type = NLA_U32 }, [NFTA_REDIR_REG_PROTO_MAX] = { .type = NLA_U32 }, [NFTA_REDIR_FLAGS] = { .type = NLA_U32 }, }; -EXPORT_SYMBOL_GPL(nft_redir_policy); -int nft_redir_validate(const struct nft_ctx *ctx, - const struct nft_expr *expr, - const struct nft_data **data) +static int nft_redir_validate(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nft_data **data) { int err; @@ -37,11 +42,10 @@ int nft_redir_validate(const struct nft_ctx *ctx, (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_OUT)); } -EXPORT_SYMBOL_GPL(nft_redir_validate); -int nft_redir_init(const struct nft_ctx *ctx, - const struct nft_expr *expr, - const struct nlattr * const tb[]) +static int nft_redir_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]) { struct nft_redir *priv = nft_expr_priv(expr); unsigned int plen; @@ -77,7 +81,6 @@ int nft_redir_init(const struct nft_ctx *ctx, return nf_ct_netns_get(ctx->net, ctx->family); } -EXPORT_SYMBOL_GPL(nft_redir_init); int nft_redir_dump(struct sk_buff *skb, const struct nft_expr *expr) { @@ -101,7 +104,134 @@ int nft_redir_dump(struct sk_buff *skb, const struct nft_expr *expr) nla_put_failure: return -1; } -EXPORT_SYMBOL_GPL(nft_redir_dump); + +static void nft_redir_ipv4_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + struct nft_redir *priv = nft_expr_priv(expr); + struct nf_nat_ipv4_multi_range_compat mr; + + memset(&mr, 0, sizeof(mr)); + if (priv->sreg_proto_min) { + mr.range[0].min.all = (__force __be16)nft_reg_load16( + ®s->data[priv->sreg_proto_min]); + mr.range[0].max.all = (__force __be16)nft_reg_load16( + ®s->data[priv->sreg_proto_max]); + mr.range[0].flags |= NF_NAT_RANGE_PROTO_SPECIFIED; + } + + mr.range[0].flags |= priv->flags; + + regs->verdict.code = nf_nat_redirect_ipv4(pkt->skb, &mr, nft_hook(pkt)); +} + +static void +nft_redir_ipv4_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr) +{ + nf_ct_netns_put(ctx->net, NFPROTO_IPV4); +} + +static struct nft_expr_type nft_redir_ipv4_type; +static const struct nft_expr_ops nft_redir_ipv4_ops = { + .type = &nft_redir_ipv4_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_redir)), + .eval = nft_redir_ipv4_eval, + .init = nft_redir_init, + .destroy = nft_redir_ipv4_destroy, + .dump = nft_redir_dump, + .validate = nft_redir_validate, +}; + +static struct nft_expr_type nft_redir_ipv4_type __read_mostly = { + .family = NFPROTO_IPV4, + .name = "redir", + .ops = &nft_redir_ipv4_ops, + .policy = nft_redir_policy, + .maxattr = NFTA_REDIR_MAX, + .owner = THIS_MODULE, +}; + +#ifdef CONFIG_NF_TABLES_IPV6 +static void nft_redir_ipv6_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + struct nft_redir *priv = nft_expr_priv(expr); + struct nf_nat_range2 range; + + memset(&range, 0, sizeof(range)); + if (priv->sreg_proto_min) { + range.min_proto.all = (__force __be16)nft_reg_load16( + ®s->data[priv->sreg_proto_min]); + range.max_proto.all = (__force __be16)nft_reg_load16( + ®s->data[priv->sreg_proto_max]); + range.flags |= NF_NAT_RANGE_PROTO_SPECIFIED; + } + + range.flags |= priv->flags; + + regs->verdict.code = + nf_nat_redirect_ipv6(pkt->skb, &range, nft_hook(pkt)); +} + +static void +nft_redir_ipv6_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr) +{ + nf_ct_netns_put(ctx->net, NFPROTO_IPV6); +} + +static struct nft_expr_type nft_redir_ipv6_type; +static const struct nft_expr_ops nft_redir_ipv6_ops = { + .type = &nft_redir_ipv6_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_redir)), + .eval = nft_redir_ipv6_eval, + .init = nft_redir_init, + .destroy = nft_redir_ipv6_destroy, + .dump = nft_redir_dump, + .validate = nft_redir_validate, +}; + +static struct nft_expr_type nft_redir_ipv6_type __read_mostly = { + .family = NFPROTO_IPV6, + .name = "redir", + .ops = &nft_redir_ipv6_ops, + .policy = nft_redir_policy, + .maxattr = NFTA_REDIR_MAX, + .owner = THIS_MODULE, +}; +#endif + +static int __init nft_redir_module_init(void) +{ + int ret = nft_register_expr(&nft_redir_ipv4_type); + + if (ret) + return ret; + +#ifdef CONFIG_NF_TABLES_IPV6 + ret = nft_register_expr(&nft_redir_ipv6_type); + if (ret) { + nft_unregister_expr(&nft_redir_ipv4_type); + return ret; + } +#endif + + return ret; +} + +static void __exit nft_redir_module_exit(void) +{ + nft_unregister_expr(&nft_redir_ipv4_type); +#ifdef CONFIG_NF_TABLES_IPV6 + nft_unregister_expr(&nft_redir_ipv6_type); +#endif +} + +module_init(nft_redir_module_init); +module_exit(nft_redir_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Arturo Borrero Gonzalez <arturo@debian.org>"); +MODULE_ALIAS_NFT_AF_EXPR(AF_INET4, "redir"); +MODULE_ALIAS_NFT_AF_EXPR(AF_INET6, "redir"); diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c index 339a9dd1c832..03df08801e28 100644 --- a/net/netfilter/nft_set_hash.c +++ b/net/netfilter/nft_set_hash.c @@ -442,15 +442,6 @@ static void *nft_hash_get(const struct net *net, const struct nft_set *set, return ERR_PTR(-ENOENT); } -/* nft_hash_select_ops() makes sure key size can be either 2 or 4 bytes . */ -static inline u32 nft_hash_key(const u32 *key, u32 klen) -{ - if (klen == 4) - return *key; - - return *(u16 *)key; -} - static bool nft_hash_lookup_fast(const struct net *net, const struct nft_set *set, const u32 *key, const struct nft_set_ext **ext) @@ -460,11 +451,11 @@ static bool nft_hash_lookup_fast(const struct net *net, const struct nft_hash_elem *he; u32 hash, k1, k2; - k1 = nft_hash_key(key, set->klen); + k1 = *key; hash = jhash_1word(k1, priv->seed); hash = reciprocal_scale(hash, priv->buckets); hlist_for_each_entry_rcu(he, &priv->table[hash], node) { - k2 = nft_hash_key(nft_set_ext_key(&he->ext)->data, set->klen); + k2 = *(u32 *)nft_set_ext_key(&he->ext)->data; if (k1 == k2 && nft_set_elem_active(&he->ext, genmask)) { *ext = &he->ext; @@ -474,6 +465,23 @@ static bool nft_hash_lookup_fast(const struct net *net, return false; } +static u32 nft_jhash(const struct nft_set *set, const struct nft_hash *priv, + const struct nft_set_ext *ext) +{ + const struct nft_data *key = nft_set_ext_key(ext); + u32 hash, k1; + + if (set->klen == 4) { + k1 = *(u32 *)key; + hash = jhash_1word(k1, priv->seed); + } else { + hash = jhash(key, set->klen, priv->seed); + } + hash = reciprocal_scale(hash, priv->buckets); + + return hash; +} + static int nft_hash_insert(const struct net *net, const struct nft_set *set, const struct nft_set_elem *elem, struct nft_set_ext **ext) @@ -483,8 +491,7 @@ static int nft_hash_insert(const struct net *net, const struct nft_set *set, u8 genmask = nft_genmask_next(net); u32 hash; - hash = jhash(nft_set_ext_key(&this->ext), set->klen, priv->seed); - hash = reciprocal_scale(hash, priv->buckets); + hash = nft_jhash(set, priv, &this->ext); hlist_for_each_entry(he, &priv->table[hash], node) { if (!memcmp(nft_set_ext_key(&this->ext), nft_set_ext_key(&he->ext), set->klen) && @@ -523,10 +530,9 @@ static void *nft_hash_deactivate(const struct net *net, u8 genmask = nft_genmask_next(net); u32 hash; - hash = jhash(nft_set_ext_key(&this->ext), set->klen, priv->seed); - hash = reciprocal_scale(hash, priv->buckets); + hash = nft_jhash(set, priv, &this->ext); hlist_for_each_entry(he, &priv->table[hash], node) { - if (!memcmp(nft_set_ext_key(&this->ext), &elem->key.val, + if (!memcmp(nft_set_ext_key(&he->ext), &elem->key.val, set->klen) && nft_set_elem_active(&he->ext, genmask)) { nft_set_elem_change_active(net, set, &he->ext); diff --git a/net/netfilter/nft_tunnel.c b/net/netfilter/nft_tunnel.c index ea28588c5eed..b113fcac94e1 100644 --- a/net/netfilter/nft_tunnel.c +++ b/net/netfilter/nft_tunnel.c @@ -406,6 +406,13 @@ static int nft_tunnel_obj_init(const struct nft_ctx *ctx, return -ENOMEM; memcpy(&md->u.tun_info, &info, sizeof(info)); +#ifdef CONFIG_DST_CACHE + err = dst_cache_init(&md->u.tun_info.dst_cache, GFP_KERNEL); + if (err < 0) { + metadata_dst_free(md); + return err; + } +#endif ip_tunnel_info_opts_set(&md->u.tun_info, &priv->opts.u, priv->opts.len, priv->opts.flags); priv->md = md; diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index 13e1ac333fa4..e5e5c64df8d1 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -461,7 +461,7 @@ int xt_check_proc_name(const char *name, unsigned int size) EXPORT_SYMBOL(xt_check_proc_name); int xt_check_match(struct xt_mtchk_param *par, - unsigned int size, u_int8_t proto, bool inv_proto) + unsigned int size, u16 proto, bool inv_proto) { int ret; @@ -984,7 +984,7 @@ bool xt_find_jump_offset(const unsigned int *offsets, EXPORT_SYMBOL(xt_find_jump_offset); int xt_check_target(struct xt_tgchk_param *par, - unsigned int size, u_int8_t proto, bool inv_proto) + unsigned int size, u16 proto, bool inv_proto) { int ret; diff --git a/net/netfilter/xt_IDLETIMER.c b/net/netfilter/xt_IDLETIMER.c index eb4cbd244c3d..5f9b37e12801 100644 --- a/net/netfilter/xt_IDLETIMER.c +++ b/net/netfilter/xt_IDLETIMER.c @@ -41,19 +41,13 @@ #include <linux/workqueue.h> #include <linux/sysfs.h> -struct idletimer_tg_attr { - struct attribute attr; - ssize_t (*show)(struct kobject *kobj, - struct attribute *attr, char *buf); -}; - struct idletimer_tg { struct list_head entry; struct timer_list timer; struct work_struct work; struct kobject *kobj; - struct idletimer_tg_attr attr; + struct device_attribute attr; unsigned int refcnt; }; @@ -76,15 +70,15 @@ struct idletimer_tg *__idletimer_tg_find_by_label(const char *label) return NULL; } -static ssize_t idletimer_tg_show(struct kobject *kobj, struct attribute *attr, - char *buf) +static ssize_t idletimer_tg_show(struct device *dev, + struct device_attribute *attr, char *buf) { struct idletimer_tg *timer; unsigned long expires = 0; mutex_lock(&list_mutex); - timer = __idletimer_tg_find_by_label(attr->name); + timer = __idletimer_tg_find_by_label(attr->attr.name); if (timer) expires = timer->timer.expires; diff --git a/net/netfilter/xt_nat.c b/net/netfilter/xt_nat.c index ac91170fc8c8..61eabd171186 100644 --- a/net/netfilter/xt_nat.c +++ b/net/netfilter/xt_nat.c @@ -14,7 +14,7 @@ #include <linux/skbuff.h> #include <linux/netfilter.h> #include <linux/netfilter/x_tables.h> -#include <net/netfilter/nf_nat_core.h> +#include <net/netfilter/nf_nat.h> static int xt_nat_checkentry_v0(const struct xt_tgchk_param *par) { diff --git a/net/openvswitch/Kconfig b/net/openvswitch/Kconfig index 89da9512ec1e..ac1cc6e38170 100644 --- a/net/openvswitch/Kconfig +++ b/net/openvswitch/Kconfig @@ -8,8 +8,6 @@ config OPENVSWITCH depends on !NF_CONNTRACK || \ (NF_CONNTRACK && ((!NF_DEFRAG_IPV6 || NF_DEFRAG_IPV6) && \ (!NF_NAT || NF_NAT) && \ - (!NF_NAT_IPV4 || NF_NAT_IPV4) && \ - (!NF_NAT_IPV6 || NF_NAT_IPV6) && \ (!NETFILTER_CONNCOUNT || NETFILTER_CONNCOUNT))) select LIBCRC32C select MPLS diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index 35884f836260..1b6896896fff 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -29,9 +29,7 @@ #include <net/ipv6_frag.h> #ifdef CONFIG_NF_NAT_NEEDED -#include <linux/netfilter/nf_nat.h> -#include <net/netfilter/nf_nat_core.h> -#include <net/netfilter/nf_nat_l3proto.h> +#include <net/netfilter/nf_nat.h> #endif #include "datapath.h" @@ -745,14 +743,14 @@ static int ovs_ct_nat_execute(struct sk_buff *skb, struct nf_conn *ct, switch (ctinfo) { case IP_CT_RELATED: case IP_CT_RELATED_REPLY: - if (IS_ENABLED(CONFIG_NF_NAT_IPV4) && + if (IS_ENABLED(CONFIG_NF_NAT) && skb->protocol == htons(ETH_P_IP) && ip_hdr(skb)->protocol == IPPROTO_ICMP) { if (!nf_nat_icmp_reply_translation(skb, ct, ctinfo, hooknum)) err = NF_DROP; goto push; - } else if (IS_ENABLED(CONFIG_NF_NAT_IPV6) && + } else if (IS_ENABLED(CONFIG_IPV6) && skb->protocol == htons(ETH_P_IPV6)) { __be16 frag_off; u8 nexthdr = ipv6_hdr(skb)->nexthdr; @@ -1673,7 +1671,7 @@ static bool ovs_ct_nat_to_attr(const struct ovs_conntrack_info *info, } if (info->range.flags & NF_NAT_RANGE_MAP_IPS) { - if (IS_ENABLED(CONFIG_NF_NAT_IPV4) && + if (IS_ENABLED(CONFIG_NF_NAT) && info->family == NFPROTO_IPV4) { if (nla_put_in_addr(skb, OVS_NAT_ATTR_IP_MIN, info->range.min_addr.ip) || @@ -1682,7 +1680,7 @@ static bool ovs_ct_nat_to_attr(const struct ovs_conntrack_info *info, (nla_put_in_addr(skb, OVS_NAT_ATTR_IP_MAX, info->range.max_addr.ip)))) return false; - } else if (IS_ENABLED(CONFIG_NF_NAT_IPV6) && + } else if (IS_ENABLED(CONFIG_IPV6) && info->family == NFPROTO_IPV6) { if (nla_put_in6_addr(skb, OVS_NAT_ATTR_IP_MIN, &info->range.min_addr.in6) || |