blob: 64e1ee09122582bce81a4ee996064763083bcfa0 [file] [log] [blame]
/*
* Copyright (c) 2007-2009 Patrick McHardy <kaber@trash.net>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*
* Development of this code funded by Astaro AG (http://www.astaro.com/)
*/
#include <linux/module.h>
#include <linux/init.h>
#include <linux/list.h>
#include <linux/skbuff.h>
#include <linux/netlink.h>
#include <linux/vmalloc.h>
#include <linux/netfilter.h>
#include <linux/netfilter/nfnetlink.h>
#include <linux/netfilter/nf_tables.h>
#include <net/netfilter/nf_tables_core.h>
#include <net/netfilter/nf_tables.h>
#include <net/net_namespace.h>
#include <net/sock.h>
static LIST_HEAD(nf_tables_expressions);
static LIST_HEAD(nf_tables_objects);
/**
* nft_register_afinfo - register nf_tables address family info
*
* @afi: address family info to register
*
* Register the address family for use with nf_tables. Returns zero on
* success or a negative errno code otherwise.
*/
int nft_register_afinfo(struct net *net, struct nft_af_info *afi)
{
INIT_LIST_HEAD(&afi->tables);
nfnl_lock(NFNL_SUBSYS_NFTABLES);
list_add_tail_rcu(&afi->list, &net->nft.af_info);
nfnl_unlock(NFNL_SUBSYS_NFTABLES);
return 0;
}
EXPORT_SYMBOL_GPL(nft_register_afinfo);
static void __nft_release_afinfo(struct net *net, struct nft_af_info *afi);
/**
* nft_unregister_afinfo - unregister nf_tables address family info
*
* @afi: address family info to unregister
*
* Unregister the address family for use with nf_tables.
*/
void nft_unregister_afinfo(struct net *net, struct nft_af_info *afi)
{
nfnl_lock(NFNL_SUBSYS_NFTABLES);
__nft_release_afinfo(net, afi);
list_del_rcu(&afi->list);
nfnl_unlock(NFNL_SUBSYS_NFTABLES);
}
EXPORT_SYMBOL_GPL(nft_unregister_afinfo);
static struct nft_af_info *nft_afinfo_lookup(struct net *net, int family)
{
struct nft_af_info *afi;
list_for_each_entry(afi, &net->nft.af_info, list) {
if (afi->family == family)
return afi;
}
return NULL;
}
static struct nft_af_info *
nf_tables_afinfo_lookup(struct net *net, int family, bool autoload)
{
struct nft_af_info *afi;
afi = nft_afinfo_lookup(net, family);
if (afi != NULL)
return afi;
#ifdef CONFIG_MODULES
if (autoload) {
nfnl_unlock(NFNL_SUBSYS_NFTABLES);
request_module("nft-afinfo-%u", family);
nfnl_lock(NFNL_SUBSYS_NFTABLES);
afi = nft_afinfo_lookup(net, family);
if (afi != NULL)
return ERR_PTR(-EAGAIN);
}
#endif
return ERR_PTR(-EAFNOSUPPORT);
}
static void nft_ctx_init(struct nft_ctx *ctx,
struct net *net,
const struct sk_buff *skb,
const struct nlmsghdr *nlh,
struct nft_af_info *afi,
struct nft_table *table,
struct nft_chain *chain,
const struct nlattr * const *nla)
{
ctx->net = net;
ctx->afi = afi;
ctx->table = table;
ctx->chain = chain;
ctx->nla = nla;
ctx->portid = NETLINK_CB(skb).portid;
ctx->report = nlmsg_report(nlh);
ctx->seq = nlh->nlmsg_seq;
}
static struct nft_trans *nft_trans_alloc_gfp(const struct nft_ctx *ctx,
int msg_type, u32 size, gfp_t gfp)
{
struct nft_trans *trans;
trans = kzalloc(sizeof(struct nft_trans) + size, gfp);
if (trans == NULL)
return NULL;
trans->msg_type = msg_type;
trans->ctx = *ctx;
return trans;
}
static struct nft_trans *nft_trans_alloc(const struct nft_ctx *ctx,
int msg_type, u32 size)
{
return nft_trans_alloc_gfp(ctx, msg_type, size, GFP_KERNEL);
}
static void nft_trans_destroy(struct nft_trans *trans)
{
list_del(&trans->list);
kfree(trans);
}
static int nf_tables_register_hooks(struct net *net,
const struct nft_table *table,
struct nft_chain *chain,
unsigned int hook_nops)
{
if (table->flags & NFT_TABLE_F_DORMANT ||
!nft_is_base_chain(chain))
return 0;
return nf_register_net_hooks(net, nft_base_chain(chain)->ops,
hook_nops);
}
static void nf_tables_unregister_hooks(struct net *net,
const struct nft_table *table,
struct nft_chain *chain,
unsigned int hook_nops)
{
if (table->flags & NFT_TABLE_F_DORMANT ||
!nft_is_base_chain(chain))
return;
nf_unregister_net_hooks(net, nft_base_chain(chain)->ops, hook_nops);
}
static int nft_trans_table_add(struct nft_ctx *ctx, int msg_type)
{
struct nft_trans *trans;
trans = nft_trans_alloc(ctx, msg_type, sizeof(struct nft_trans_table));
if (trans == NULL)
return -ENOMEM;
if (msg_type == NFT_MSG_NEWTABLE)
nft_activate_next(ctx->net, ctx->table);
list_add_tail(&trans->list, &ctx->net->nft.commit_list);
return 0;
}
static int nft_deltable(struct nft_ctx *ctx)
{
int err;
err = nft_trans_table_add(ctx, NFT_MSG_DELTABLE);
if (err < 0)
return err;
nft_deactivate_next(ctx->net, ctx->table);
return err;
}
static int nft_trans_chain_add(struct nft_ctx *ctx, int msg_type)
{
struct nft_trans *trans;
trans = nft_trans_alloc(ctx, msg_type, sizeof(struct nft_trans_chain));
if (trans == NULL)
return -ENOMEM;
if (msg_type == NFT_MSG_NEWCHAIN)
nft_activate_next(ctx->net, ctx->chain);
list_add_tail(&trans->list, &ctx->net->nft.commit_list);
return 0;
}
static int nft_delchain(struct nft_ctx *ctx)
{
int err;
err = nft_trans_chain_add(ctx, NFT_MSG_DELCHAIN);
if (err < 0)
return err;
ctx->table->use--;
nft_deactivate_next(ctx->net, ctx->chain);
return err;
}
static int
nf_tables_delrule_deactivate(struct nft_ctx *ctx, struct nft_rule *rule)
{
/* You cannot delete the same rule twice */
if (nft_is_active_next(ctx->net, rule)) {
nft_deactivate_next(ctx->net, rule);
ctx->chain->use--;
return 0;
}
return -ENOENT;
}
static struct nft_trans *nft_trans_rule_add(struct nft_ctx *ctx, int msg_type,
struct nft_rule *rule)
{
struct nft_trans *trans;
trans = nft_trans_alloc(ctx, msg_type, sizeof(struct nft_trans_rule));
if (trans == NULL)
return NULL;
if (msg_type == NFT_MSG_NEWRULE && ctx->nla[NFTA_RULE_ID] != NULL) {
nft_trans_rule_id(trans) =
ntohl(nla_get_be32(ctx->nla[NFTA_RULE_ID]));
}
nft_trans_rule(trans) = rule;
list_add_tail(&trans->list, &ctx->net->nft.commit_list);
return trans;
}
static int nft_delrule(struct nft_ctx *ctx, struct nft_rule *rule)
{
struct nft_trans *trans;
int err;
trans = nft_trans_rule_add(ctx, NFT_MSG_DELRULE, rule);
if (trans == NULL)
return -ENOMEM;
err = nf_tables_delrule_deactivate(ctx, rule);
if (err < 0) {
nft_trans_destroy(trans);
return err;
}
return 0;
}
static int nft_delrule_by_chain(struct nft_ctx *ctx)
{
struct nft_rule *rule;
int err;
list_for_each_entry(rule, &ctx->chain->rules, list) {
err = nft_delrule(ctx, rule);
if (err < 0)
return err;
}
return 0;
}
static int nft_trans_set_add(struct nft_ctx *ctx, int msg_type,
struct nft_set *set)
{
struct nft_trans *trans;
trans = nft_trans_alloc(ctx, msg_type, sizeof(struct nft_trans_set));
if (trans == NULL)
return -ENOMEM;
if (msg_type == NFT_MSG_NEWSET && ctx->nla[NFTA_SET_ID] != NULL) {
nft_trans_set_id(trans) =
ntohl(nla_get_be32(ctx->nla[NFTA_SET_ID]));
nft_activate_next(ctx->net, set);
}
nft_trans_set(trans) = set;
list_add_tail(&trans->list, &ctx->net->nft.commit_list);
return 0;
}
static int nft_delset(struct nft_ctx *ctx, struct nft_set *set)
{
int err;
err = nft_trans_set_add(ctx, NFT_MSG_DELSET, set);
if (err < 0)
return err;
nft_deactivate_next(ctx->net, set);
ctx->table->use--;
return err;
}
static int nft_trans_obj_add(struct nft_ctx *ctx, int msg_type,
struct nft_object *obj)
{
struct nft_trans *trans;
trans = nft_trans_alloc(ctx, msg_type, sizeof(struct nft_trans_obj));
if (trans == NULL)
return -ENOMEM;
if (msg_type == NFT_MSG_NEWOBJ)
nft_activate_next(ctx->net, obj);
nft_trans_obj(trans) = obj;
list_add_tail(&trans->list, &ctx->net->nft.commit_list);
return 0;
}
static int nft_delobj(struct nft_ctx *ctx, struct nft_object *obj)
{
int err;
err = nft_trans_obj_add(ctx, NFT_MSG_DELOBJ, obj);
if (err < 0)
return err;
nft_deactivate_next(ctx->net, obj);
ctx->table->use--;
return err;
}
/*
* Tables
*/
static struct nft_table *nft_table_lookup(const struct nft_af_info *afi,
const struct nlattr *nla,
u8 genmask)
{
struct nft_table *table;
list_for_each_entry(table, &afi->tables, list) {
if (!nla_strcmp(nla, table->name) &&
nft_active_genmask(table, genmask))
return table;
}
return NULL;
}
static struct nft_table *nf_tables_table_lookup(const struct nft_af_info *afi,
const struct nlattr *nla,
u8 genmask)
{
struct nft_table *table;
if (nla == NULL)
return ERR_PTR(-EINVAL);
table = nft_table_lookup(afi, nla, genmask);
if (table != NULL)
return table;
return ERR_PTR(-ENOENT);
}
static inline u64 nf_tables_alloc_handle(struct nft_table *table)
{
return ++table->hgenerator;
}
static const struct nf_chain_type *chain_type[NFPROTO_NUMPROTO][NFT_CHAIN_T_MAX];
static const struct nf_chain_type *
__nf_tables_chain_type_lookup(int family, const struct nlattr *nla)
{
int i;
for (i = 0; i < NFT_CHAIN_T_MAX; i++) {
if (chain_type[family][i] != NULL &&
!nla_strcmp(nla, chain_type[family][i]->name))
return chain_type[family][i];
}
return NULL;
}
static const struct nf_chain_type *
nf_tables_chain_type_lookup(const struct nft_af_info *afi,
const struct nlattr *nla,
bool autoload)
{
const struct nf_chain_type *type;
type = __nf_tables_chain_type_lookup(afi->family, nla);
if (type != NULL)
return type;
#ifdef CONFIG_MODULES
if (autoload) {
nfnl_unlock(NFNL_SUBSYS_NFTABLES);
request_module("nft-chain-%u-%.*s", afi->family,
nla_len(nla), (const char *)nla_data(nla));
nfnl_lock(NFNL_SUBSYS_NFTABLES);
type = __nf_tables_chain_type_lookup(afi->family, nla);
if (type != NULL)
return ERR_PTR(-EAGAIN);
}
#endif
return ERR_PTR(-ENOENT);
}
static const struct nla_policy nft_table_policy[NFTA_TABLE_MAX + 1] = {
[NFTA_TABLE_NAME] = { .type = NLA_STRING,
.len = NFT_TABLE_MAXNAMELEN - 1 },
[NFTA_TABLE_FLAGS] = { .type = NLA_U32 },
};
static int nf_tables_fill_table_info(struct sk_buff *skb, struct net *net,
u32 portid, u32 seq, int event, u32 flags,
int family, const struct nft_table *table)
{
struct nlmsghdr *nlh;
struct nfgenmsg *nfmsg;
event = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event);
nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct nfgenmsg), flags);
if (nlh == NULL)
goto nla_put_failure;
nfmsg = nlmsg_data(nlh);
nfmsg->nfgen_family = family;
nfmsg->version = NFNETLINK_V0;
nfmsg->res_id = htons(net->nft.base_seq & 0xffff);
if (nla_put_string(skb, NFTA_TABLE_NAME, table->name) ||
nla_put_be32(skb, NFTA_TABLE_FLAGS, htonl(table->flags)) ||
nla_put_be32(skb, NFTA_TABLE_USE, htonl(table->use)))
goto nla_put_failure;
nlmsg_end(skb, nlh);
return 0;
nla_put_failure:
nlmsg_trim(skb, nlh);
return -1;
}
static void nf_tables_table_notify(const struct nft_ctx *ctx, int event)
{
struct sk_buff *skb;
int err;
if (!ctx->report &&
!nfnetlink_has_listeners(ctx->net, NFNLGRP_NFTABLES))
return;
skb = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL);
if (skb == NULL)
goto err;
err = nf_tables_fill_table_info(skb, ctx->net, ctx->portid, ctx->seq,
event, 0, ctx->afi->family, ctx->table);
if (err < 0) {
kfree_skb(skb);
goto err;
}
nfnetlink_send(skb, ctx->net, ctx->portid, NFNLGRP_NFTABLES,
ctx->report, GFP_KERNEL);
return;
err:
nfnetlink_set_err(ctx->net, ctx->portid, NFNLGRP_NFTABLES, -ENOBUFS);
}
static int nf_tables_dump_tables(struct sk_buff *skb,
struct netlink_callback *cb)
{
const struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh);
const struct nft_af_info *afi;
const struct nft_table *table;
unsigned int idx = 0, s_idx = cb->args[0];
struct net *net = sock_net(skb->sk);
int family = nfmsg->nfgen_family;
rcu_read_lock();
cb->seq = net->nft.base_seq;
list_for_each_entry_rcu(afi, &net->nft.af_info, list) {
if (family != NFPROTO_UNSPEC && family != afi->family)
continue;
list_for_each_entry_rcu(table, &afi->tables, list) {
if (idx < s_idx)
goto cont;
if (idx > s_idx)
memset(&cb->args[1], 0,
sizeof(cb->args) - sizeof(cb->args[0]));
if (!nft_is_active(net, table))
continue;
if (nf_tables_fill_table_info(skb, net,
NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq,
NFT_MSG_NEWTABLE,
NLM_F_MULTI,
afi->family, table) < 0)
goto done;
nl_dump_check_consistent(cb, nlmsg_hdr(skb));
cont:
idx++;
}
}
done:
rcu_read_unlock();
cb->args[0] = idx;
return skb->len;
}
static int nf_tables_gettable(struct net *net, struct sock *nlsk,
struct sk_buff *skb, const struct nlmsghdr *nlh,
const struct nlattr * const nla[],
struct netlink_ext_ack *extack)
{
const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
u8 genmask = nft_genmask_cur(net);
const struct nft_af_info *afi;
const struct nft_table *table;
struct sk_buff *skb2;
int family = nfmsg->nfgen_family;
int err;
if (nlh->nlmsg_flags & NLM_F_DUMP) {
struct netlink_dump_control c = {
.dump = nf_tables_dump_tables,
};
return netlink_dump_start(nlsk, skb, nlh, &c);
}
afi = nf_tables_afinfo_lookup(net, family, false);
if (IS_ERR(afi))
return PTR_ERR(afi);
table = nf_tables_table_lookup(afi, nla[NFTA_TABLE_NAME], genmask);
if (IS_ERR(table))
return PTR_ERR(table);
skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
if (!skb2)
return -ENOMEM;
err = nf_tables_fill_table_info(skb2, net, NETLINK_CB(skb).portid,
nlh->nlmsg_seq, NFT_MSG_NEWTABLE, 0,
family, table);
if (err < 0)
goto err;
return nlmsg_unicast(nlsk, skb2, NETLINK_CB(skb).portid);
err:
kfree_skb(skb2);
return err;
}
static void _nf_tables_table_disable(struct net *net,
const struct nft_af_info *afi,
struct nft_table *table,
u32 cnt)
{
struct nft_chain *chain;
u32 i = 0;
list_for_each_entry(chain, &table->chains, list) {
if (!nft_is_active_next(net, chain))
continue;
if (!nft_is_base_chain(chain))
continue;
if (cnt && i++ == cnt)
break;
nf_unregister_net_hooks(net, nft_base_chain(chain)->ops,
afi->nops);
}
}
static int nf_tables_table_enable(struct net *net,
const struct nft_af_info *afi,
struct nft_table *table)
{
struct nft_chain *chain;
int err, i = 0;
list_for_each_entry(chain, &table->chains, list) {
if (!nft_is_active_next(net, chain))
continue;
if (!nft_is_base_chain(chain))
continue;
err = nf_register_net_hooks(net, nft_base_chain(chain)->ops,
afi->nops);
if (err < 0)
goto err;
i++;
}
return 0;
err:
if (i)
_nf_tables_table_disable(net, afi, table, i);
return err;
}
static void nf_tables_table_disable(struct net *net,
const struct nft_af_info *afi,
struct nft_table *table)
{
_nf_tables_table_disable(net, afi, table, 0);
}
static int nf_tables_updtable(struct nft_ctx *ctx)
{
struct nft_trans *trans;
u32 flags;
int ret = 0;
if (!ctx->nla[NFTA_TABLE_FLAGS])
return 0;
flags = ntohl(nla_get_be32(ctx->nla[NFTA_TABLE_FLAGS]));
if (flags & ~NFT_TABLE_F_DORMANT)
return -EINVAL;
if (flags == ctx->table->flags)
return 0;
trans = nft_trans_alloc(ctx, NFT_MSG_NEWTABLE,
sizeof(struct nft_trans_table));
if (trans == NULL)
return -ENOMEM;
if ((flags & NFT_TABLE_F_DORMANT) &&
!(ctx->table->flags & NFT_TABLE_F_DORMANT)) {
nft_trans_table_enable(trans) = false;
} else if (!(flags & NFT_TABLE_F_DORMANT) &&
ctx->table->flags & NFT_TABLE_F_DORMANT) {
ret = nf_tables_table_enable(ctx->net, ctx->afi, ctx->table);
if (ret >= 0) {
ctx->table->flags &= ~NFT_TABLE_F_DORMANT;
nft_trans_table_enable(trans) = true;
}
}
if (ret < 0)
goto err;
nft_trans_table_update(trans) = true;
list_add_tail(&trans->list, &ctx->net->nft.commit_list);
return 0;
err:
nft_trans_destroy(trans);
return ret;
}
static int nf_tables_newtable(struct net *net, struct sock *nlsk,
struct sk_buff *skb, const struct nlmsghdr *nlh,
const struct nlattr * const nla[],
struct netlink_ext_ack *extack)
{
const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
u8 genmask = nft_genmask_next(net);
const struct nlattr *name;
struct nft_af_info *afi;
struct nft_table *table;
int family = nfmsg->nfgen_family;
u32 flags = 0;
struct nft_ctx ctx;
int err;
afi = nf_tables_afinfo_lookup(net, family, true);
if (IS_ERR(afi))
return PTR_ERR(afi);
name = nla[NFTA_TABLE_NAME];
table = nf_tables_table_lookup(afi, name, genmask);
if (IS_ERR(table)) {
if (PTR_ERR(table) != -ENOENT)
return PTR_ERR(table);
} else {
if (nlh->nlmsg_flags & NLM_F_EXCL)
return -EEXIST;
if (nlh->nlmsg_flags & NLM_F_REPLACE)
return -EOPNOTSUPP;
nft_ctx_init(&ctx, net, skb, nlh, afi, table, NULL, nla);
return nf_tables_updtable(&ctx);
}
if (nla[NFTA_TABLE_FLAGS]) {
flags = ntohl(nla_get_be32(nla[NFTA_TABLE_FLAGS]));
if (flags & ~NFT_TABLE_F_DORMANT)
return -EINVAL;
}
err = -EAFNOSUPPORT;
if (!try_module_get(afi->owner))
goto err1;
err = -ENOMEM;
table = kzalloc(sizeof(*table), GFP_KERNEL);
if (table == NULL)
goto err2;
table->name = nla_strdup(name, GFP_KERNEL);
if (table->name == NULL)
goto err3;
INIT_LIST_HEAD(&table->chains);
INIT_LIST_HEAD(&table->sets);
INIT_LIST_HEAD(&table->objects);
table->flags = flags;
nft_ctx_init(&ctx, net, skb, nlh, afi, table, NULL, nla);
err = nft_trans_table_add(&ctx, NFT_MSG_NEWTABLE);
if (err < 0)
goto err4;
list_add_tail_rcu(&table->list, &afi->tables);
return 0;
err4:
kfree(table->name);
err3:
kfree(table);
err2:
module_put(afi->owner);
err1:
return err;
}
static int nft_flush_table(struct nft_ctx *ctx)
{
int err;
struct nft_chain *chain, *nc;
struct nft_object *obj, *ne;
struct nft_set *set, *ns;
list_for_each_entry(chain, &ctx->table->chains, list) {
if (!nft_is_active_next(ctx->net, chain))
continue;
ctx->chain = chain;
err = nft_delrule_by_chain(ctx);
if (err < 0)
goto out;
}
list_for_each_entry_safe(set, ns, &ctx->table->sets, list) {
if (!nft_is_active_next(ctx->net, set))
continue;
if (set->flags & NFT_SET_ANONYMOUS &&
!list_empty(&set->bindings))
continue;
err = nft_delset(ctx, set);
if (err < 0)
goto out;
}
list_for_each_entry_safe(obj, ne, &ctx->table->objects, list) {
err = nft_delobj(ctx, obj);
if (err < 0)
goto out;
}
list_for_each_entry_safe(chain, nc, &ctx->table->chains, list) {
if (!nft_is_active_next(ctx->net, chain))
continue;
ctx->chain = chain;
err = nft_delchain(ctx);
if (err < 0)
goto out;
}
err = nft_deltable(ctx);
out:
return err;
}
static int nft_flush(struct nft_ctx *ctx, int family)
{
struct nft_af_info *afi;
struct nft_table *table, *nt;
const struct nlattr * const *nla = ctx->nla;
int err = 0;
list_for_each_entry(afi, &ctx->net->nft.af_info, list) {
if (family != AF_UNSPEC && afi->family != family)
continue;
ctx->afi = afi;
list_for_each_entry_safe(table, nt, &afi->tables, list) {
if (!nft_is_active_next(ctx->net, table))
continue;
if (nla[NFTA_TABLE_NAME] &&
nla_strcmp(nla[NFTA_TABLE_NAME], table->name) != 0)
continue;
ctx->table = table;
err = nft_flush_table(ctx);
if (err < 0)
goto out;
}
}
out:
return err;
}
static int nf_tables_deltable(struct net *net, struct sock *nlsk,
struct sk_buff *skb, const struct nlmsghdr *nlh,
const struct nlattr * const nla[],
struct netlink_ext_ack *extack)
{
const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
u8 genmask = nft_genmask_next(net);
struct nft_af_info *afi;
struct nft_table *table;
int family = nfmsg->nfgen_family;
struct nft_ctx ctx;
nft_ctx_init(&ctx, net, skb, nlh, NULL, NULL, NULL, nla);
if (family == AF_UNSPEC || nla[NFTA_TABLE_NAME] == NULL)
return nft_flush(&ctx, family);
afi = nf_tables_afinfo_lookup(net, family, false);
if (IS_ERR(afi))
return PTR_ERR(afi);
table = nf_tables_table_lookup(afi, nla[NFTA_TABLE_NAME], genmask);
if (IS_ERR(table))
return PTR_ERR(table);
if (nlh->nlmsg_flags & NLM_F_NONREC &&
table->use > 0)
return -EBUSY;
ctx.afi = afi;
ctx.table = table;
return nft_flush_table(&ctx);
}
static void nf_tables_table_destroy(struct nft_ctx *ctx)
{
BUG_ON(ctx->table->use > 0);
kfree(ctx->table->name);
kfree(ctx->table);
module_put(ctx->afi->owner);
}
int nft_register_chain_type(const struct nf_chain_type *ctype)
{
int err = 0;
if (WARN_ON(ctype->family >= NFPROTO_NUMPROTO))
return -EINVAL;
nfnl_lock(NFNL_SUBSYS_NFTABLES);
if (chain_type[ctype->family][ctype->type] != NULL) {
err = -EBUSY;
goto out;
}
chain_type[ctype->family][ctype->type] = ctype;
out:
nfnl_unlock(NFNL_SUBSYS_NFTABLES);
return err;
}
EXPORT_SYMBOL_GPL(nft_register_chain_type);
void nft_unregister_chain_type(const struct nf_chain_type *ctype)
{
nfnl_lock(NFNL_SUBSYS_NFTABLES);
chain_type[ctype->family][ctype->type] = NULL;
nfnl_unlock(NFNL_SUBSYS_NFTABLES);
}
EXPORT_SYMBOL_GPL(nft_unregister_chain_type);
/*
* Chains
*/
static struct nft_chain *
nf_tables_chain_lookup_byhandle(const struct nft_table *table, u64 handle,
u8 genmask)
{
struct nft_chain *chain;
list_for_each_entry(chain, &table->chains, list) {
if (chain->handle == handle &&
nft_active_genmask(chain, genmask))
return chain;
}
return ERR_PTR(-ENOENT);
}
static struct nft_chain *nf_tables_chain_lookup(const struct nft_table *table,
const struct nlattr *nla,
u8 genmask)
{
struct nft_chain *chain;
if (nla == NULL)
return ERR_PTR(-EINVAL);
list_for_each_entry(chain, &table->chains, list) {
if (!nla_strcmp(nla, chain->name) &&
nft_active_genmask(chain, genmask))
return chain;
}
return ERR_PTR(-ENOENT);
}
static const struct nla_policy nft_chain_policy[NFTA_CHAIN_MAX + 1] = {
[NFTA_CHAIN_TABLE] = { .type = NLA_STRING,
.len = NFT_TABLE_MAXNAMELEN - 1 },
[NFTA_CHAIN_HANDLE] = { .type = NLA_U64 },
[NFTA_CHAIN_NAME] = { .type = NLA_STRING,
.len = NFT_CHAIN_MAXNAMELEN - 1 },
[NFTA_CHAIN_HOOK] = { .type = NLA_NESTED },
[NFTA_CHAIN_POLICY] = { .type = NLA_U32 },
[NFTA_CHAIN_TYPE] = { .type = NLA_STRING },
[NFTA_CHAIN_COUNTERS] = { .type = NLA_NESTED },
};
static const struct nla_policy nft_hook_policy[NFTA_HOOK_MAX + 1] = {
[NFTA_HOOK_HOOKNUM] = { .type = NLA_U32 },
[NFTA_HOOK_PRIORITY] = { .type = NLA_U32 },
[NFTA_HOOK_DEV] = { .type = NLA_STRING,
.len = IFNAMSIZ - 1 },
};
static int nft_dump_stats(struct sk_buff *skb, struct nft_stats __percpu *stats)
{
struct nft_stats *cpu_stats, total;
struct nlattr *nest;
unsigned int seq;
u64 pkts, bytes;
int cpu;
memset(&total, 0, sizeof(total));
for_each_possible_cpu(cpu) {
cpu_stats = per_cpu_ptr(stats, cpu);
do {
seq = u64_stats_fetch_begin_irq(&cpu_stats->syncp);
pkts = cpu_stats->pkts;
bytes = cpu_stats->bytes;
} while (u64_stats_fetch_retry_irq(&cpu_stats->syncp, seq));
total.pkts += pkts;
total.bytes += bytes;
}
nest = nla_nest_start(skb, NFTA_CHAIN_COUNTERS);
if (nest == NULL)
goto nla_put_failure;
if (nla_put_be64(skb, NFTA_COUNTER_PACKETS, cpu_to_be64(total.pkts),
NFTA_COUNTER_PAD) ||
nla_put_be64(skb, NFTA_COUNTER_BYTES, cpu_to_be64(total.bytes),
NFTA_COUNTER_PAD))
goto nla_put_failure;
nla_nest_end(skb, nest);
return 0;
nla_put_failure:
return -ENOSPC;
}
static int nf_tables_fill_chain_info(struct sk_buff *skb, struct net *net,
u32 portid, u32 seq, int event, u32 flags,
int family, const struct nft_table *table,
const struct nft_chain *chain)
{
struct nlmsghdr *nlh;
struct nfgenmsg *nfmsg;
event = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event);
nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct nfgenmsg), flags);
if (nlh == NULL)
goto nla_put_failure;
nfmsg = nlmsg_data(nlh);
nfmsg->nfgen_family = family;
nfmsg->version = NFNETLINK_V0;
nfmsg->res_id = htons(net->nft.base_seq & 0xffff);
if (nla_put_string(skb, NFTA_CHAIN_TABLE, table->name))
goto nla_put_failure;
if (nla_put_be64(skb, NFTA_CHAIN_HANDLE, cpu_to_be64(chain->handle),
NFTA_CHAIN_PAD))
goto nla_put_failure;
if (nla_put_string(skb, NFTA_CHAIN_NAME, chain->name))
goto nla_put_failure;
if (nft_is_base_chain(chain)) {
const struct nft_base_chain *basechain = nft_base_chain(chain);
const struct nf_hook_ops *ops = &basechain->ops[0];
struct nlattr *nest;
nest = nla_nest_start(skb, NFTA_CHAIN_HOOK);
if (nest == NULL)
goto nla_put_failure;
if (nla_put_be32(skb, NFTA_HOOK_HOOKNUM, htonl(ops->hooknum)))
goto nla_put_failure;
if (nla_put_be32(skb, NFTA_HOOK_PRIORITY, htonl(ops->priority)))
goto nla_put_failure;
if (basechain->dev_name[0] &&
nla_put_string(skb, NFTA_HOOK_DEV, basechain->dev_name))
goto nla_put_failure;
nla_nest_end(skb, nest);
if (nla_put_be32(skb, NFTA_CHAIN_POLICY,
htonl(basechain->policy)))
goto nla_put_failure;
if (nla_put_string(skb, NFTA_CHAIN_TYPE, basechain->type->name))
goto nla_put_failure;
if (basechain->stats && nft_dump_stats(skb, basechain->stats))
goto nla_put_failure;
}
if (nla_put_be32(skb, NFTA_CHAIN_USE, htonl(chain->use)))
goto nla_put_failure;
nlmsg_end(skb, nlh);
return 0;
nla_put_failure:
nlmsg_trim(skb, nlh);
return -1;
}
static void nf_tables_chain_notify(const struct nft_ctx *ctx, int event)
{
struct sk_buff *skb;
int err;
if (!ctx->report &&
!nfnetlink_has_listeners(ctx->net, NFNLGRP_NFTABLES))
return;
skb = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL);
if (skb == NULL)
goto err;
err = nf_tables_fill_chain_info(skb, ctx->net, ctx->portid, ctx->seq,
event, 0, ctx->afi->family, ctx->table,
ctx->chain);
if (err < 0) {
kfree_skb(skb);
goto err;
}
nfnetlink_send(skb, ctx->net, ctx->portid, NFNLGRP_NFTABLES,
ctx->report, GFP_KERNEL);
return;
err:
nfnetlink_set_err(ctx->net, ctx->portid, NFNLGRP_NFTABLES, -ENOBUFS);
}
static int nf_tables_dump_chains(struct sk_buff *skb,
struct netlink_callback *cb)
{
const struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh);
const struct nft_af_info *afi;
const struct nft_table *table;
const struct nft_chain *chain;
unsigned int idx = 0, s_idx = cb->args[0];
struct net *net = sock_net(skb->sk);
int family = nfmsg->nfgen_family;
rcu_read_lock();
cb->seq = net->nft.base_seq;
list_for_each_entry_rcu(afi, &net->nft.af_info, list) {
if (family != NFPROTO_UNSPEC && family != afi->family)
continue;
list_for_each_entry_rcu(table, &afi->tables, list) {
list_for_each_entry_rcu(chain, &table->chains, list) {
if (idx < s_idx)
goto cont;
if (idx > s_idx)
memset(&cb->args[1], 0,
sizeof(cb->args) - sizeof(cb->args[0]));
if (!nft_is_active(net, chain))
continue;
if (nf_tables_fill_chain_info(skb, net,
NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq,
NFT_MSG_NEWCHAIN,
NLM_F_MULTI,
afi->family, table, chain) < 0)
goto done;
nl_dump_check_consistent(cb, nlmsg_hdr(skb));
cont:
idx++;
}
}
}
done:
rcu_read_unlock();
cb->args[0] = idx;
return skb->len;
}
static int nf_tables_getchain(struct net *net, struct sock *nlsk,
struct sk_buff *skb, const struct nlmsghdr *nlh,
const struct nlattr * const nla[],
struct netlink_ext_ack *extack)
{
const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
u8 genmask = nft_genmask_cur(net);
const struct nft_af_info *afi;
const struct nft_table *table;
const struct nft_chain *chain;
struct sk_buff *skb2;
int family = nfmsg->nfgen_family;
int err;
if (nlh->nlmsg_flags & NLM_F_DUMP) {
struct netlink_dump_control c = {
.dump = nf_tables_dump_chains,
};
return netlink_dump_start(nlsk, skb, nlh, &c);
}
afi = nf_tables_afinfo_lookup(net, family, false);
if (IS_ERR(afi))
return PTR_ERR(afi);
table = nf_tables_table_lookup(afi, nla[NFTA_CHAIN_TABLE], genmask);
if (IS_ERR(table))
return PTR_ERR(table);
chain = nf_tables_chain_lookup(table, nla[NFTA_CHAIN_NAME], genmask);
if (IS_ERR(chain))
return PTR_ERR(chain);
skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
if (!skb2)
return -ENOMEM;
err = nf_tables_fill_chain_info(skb2, net, NETLINK_CB(skb).portid,
nlh->nlmsg_seq, NFT_MSG_NEWCHAIN, 0,
family, table, chain);
if (err < 0)
goto err;
return nlmsg_unicast(nlsk, skb2, NETLINK_CB(skb).portid);
err:
kfree_skb(skb2);
return err;
}
static const struct nla_policy nft_counter_policy[NFTA_COUNTER_MAX + 1] = {
[NFTA_COUNTER_PACKETS] = { .type = NLA_U64 },
[NFTA_COUNTER_BYTES] = { .type = NLA_U64 },
};
static struct nft_stats __percpu *nft_stats_alloc(const struct nlattr *attr)
{
struct nlattr *tb[NFTA_COUNTER_MAX+1];
struct nft_stats __percpu *newstats;
struct nft_stats *stats;
int err;
err = nla_parse_nested(tb, NFTA_COUNTER_MAX, attr, nft_counter_policy,
NULL);
if (err < 0)
return ERR_PTR(err);
if (!tb[NFTA_COUNTER_BYTES] || !tb[NFTA_COUNTER_PACKETS])
return ERR_PTR(-EINVAL);
newstats = netdev_alloc_pcpu_stats(struct nft_stats);
if (newstats == NULL)
return ERR_PTR(-ENOMEM);
/* Restore old counters on this cpu, no problem. Per-cpu statistics
* are not exposed to userspace.
*/
preempt_disable();
stats = this_cpu_ptr(newstats);
stats->bytes = be64_to_cpu(nla_get_be64(tb[NFTA_COUNTER_BYTES]));
stats->pkts = be64_to_cpu(nla_get_be64(tb[NFTA_COUNTER_PACKETS]));
preempt_enable();
return newstats;
}
static void nft_chain_stats_replace(struct nft_base_chain *chain,
struct nft_stats __percpu *newstats)
{
if (newstats == NULL)
return;
if (chain->stats) {
struct nft_stats __percpu *oldstats =
nft_dereference(chain->stats);
rcu_assign_pointer(chain->stats, newstats);
synchronize_rcu();
free_percpu(oldstats);
} else
rcu_assign_pointer(chain->stats, newstats);
}
static void nf_tables_chain_destroy(struct nft_chain *chain)
{
BUG_ON(chain->use > 0);
if (nft_is_base_chain(chain)) {
struct nft_base_chain *basechain = nft_base_chain(chain);
module_put(basechain->type->owner);
free_percpu(basechain->stats);
if (basechain->stats)
static_branch_dec(&nft_counters_enabled);
if (basechain->ops[0].dev != NULL)
dev_put(basechain->ops[0].dev);
kfree(chain->name);
kfree(basechain);
} else {
kfree(chain->name);
kfree(chain);
}
}
struct nft_chain_hook {
u32 num;
u32 priority;
const struct nf_chain_type *type;
struct net_device *dev;
};
static int nft_chain_parse_hook(struct net *net,
const struct nlattr * const nla[],
struct nft_af_info *afi,
struct nft_chain_hook *hook, bool create)
{
struct nlattr *ha[NFTA_HOOK_MAX + 1];
const struct nf_chain_type *type;
struct net_device *dev;
int err;
err = nla_parse_nested(ha, NFTA_HOOK_MAX, nla[NFTA_CHAIN_HOOK],
nft_hook_policy, NULL);
if (err < 0)
return err;
if (ha[NFTA_HOOK_HOOKNUM] == NULL ||
ha[NFTA_HOOK_PRIORITY] == NULL)
return -EINVAL;
hook->num = ntohl(nla_get_be32(ha[NFTA_HOOK_HOOKNUM]));
if (hook->num >= afi->nhooks)
return -EINVAL;
hook->priority = ntohl(nla_get_be32(ha[NFTA_HOOK_PRIORITY]));
type = chain_type[afi->family][NFT_CHAIN_T_DEFAULT];
if (nla[NFTA_CHAIN_TYPE]) {
type = nf_tables_chain_type_lookup(afi, nla[NFTA_CHAIN_TYPE],
create);
if (IS_ERR(type))
return PTR_ERR(type);
}
if (!(type->hook_mask & (1 << hook->num)))
return -EOPNOTSUPP;
if (!try_module_get(type->owner))
return -ENOENT;
hook->type = type;
hook->dev = NULL;
if (afi->flags & NFT_AF_NEEDS_DEV) {
char ifname[IFNAMSIZ];
if (!ha[NFTA_HOOK_DEV]) {
module_put(type->owner);
return -EOPNOTSUPP;
}
nla_strlcpy(ifname, ha[NFTA_HOOK_DEV], IFNAMSIZ);
dev = dev_get_by_name(net, ifname);
if (!dev) {
module_put(type->owner);
return -ENOENT;
}
hook->dev = dev;
} else if (ha[NFTA_HOOK_DEV]) {
module_put(type->owner);
return -EOPNOTSUPP;
}
return 0;
}
static void nft_chain_release_hook(struct nft_chain_hook *hook)
{
module_put(hook->type->owner);
if (hook->dev != NULL)
dev_put(hook->dev);
}
static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask,
u8 policy, bool create)
{
const struct nlattr * const *nla = ctx->nla;
struct nft_table *table = ctx->table;
struct nft_af_info *afi = ctx->afi;
struct nft_base_chain *basechain;
struct nft_stats __percpu *stats;
struct net *net = ctx->net;
struct nft_chain *chain;
unsigned int i;
int err;
if (table->use == UINT_MAX)
return -EOVERFLOW;
if (nla[NFTA_CHAIN_HOOK]) {
struct nft_chain_hook hook;
struct nf_hook_ops *ops;
nf_hookfn *hookfn;
err = nft_chain_parse_hook(net, nla, afi, &hook, create);
if (err < 0)
return err;
basechain = kzalloc(sizeof(*basechain), GFP_KERNEL);
if (basechain == NULL) {
nft_chain_release_hook(&hook);
return -ENOMEM;
}
if (hook.dev != NULL)
strncpy(basechain->dev_name, hook.dev->name, IFNAMSIZ);
if (nla[NFTA_CHAIN_COUNTERS]) {
stats = nft_stats_alloc(nla[NFTA_CHAIN_COUNTERS]);
if (IS_ERR(stats)) {
nft_chain_release_hook(&hook);
kfree(basechain);
return PTR_ERR(stats);
}
basechain->stats = stats;
static_branch_inc(&nft_counters_enabled);
}
hookfn = hook.type->hooks[hook.num];
basechain->type = hook.type;
chain = &basechain->chain;
for (i = 0; i < afi->nops; i++) {
ops = &basechain->ops[i];
ops->pf = family;
ops->hooknum = hook.num;
ops->priority = hook.priority;
ops->priv = chain;
ops->hook = afi->hooks[ops->hooknum];
ops->dev = hook.dev;
if (hookfn)
ops->hook = hookfn;
if (afi->hook_ops_init)
afi->hook_ops_init(ops, i);
}
chain->flags |= NFT_BASE_CHAIN;
basechain->policy = policy;
} else {
chain = kzalloc(sizeof(*chain), GFP_KERNEL);
if (chain == NULL)
return -ENOMEM;
}
INIT_LIST_HEAD(&chain->rules);
chain->handle = nf_tables_alloc_handle(table);
chain->table = table;
chain->name = nla_strdup(nla[NFTA_CHAIN_NAME], GFP_KERNEL);
if (!chain->name) {
err = -ENOMEM;
goto err1;
}
err = nf_tables_register_hooks(net, table, chain, afi->nops);
if (err < 0)
goto err1;
ctx->chain = chain;
err = nft_trans_chain_add(ctx, NFT_MSG_NEWCHAIN);
if (err < 0)
goto err2;
table->use++;
list_add_tail_rcu(&chain->list, &table->chains);
return 0;
err2:
nf_tables_unregister_hooks(net, table, chain, afi->nops);
err1:
nf_tables_chain_destroy(chain);
return err;
}
static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy,
bool create)
{
const struct nlattr * const *nla = ctx->nla;
struct nft_table *table = ctx->table;
struct nft_chain *chain = ctx->chain;
struct nft_af_info *afi = ctx->afi;
struct nft_base_chain *basechain;
struct nft_stats *stats = NULL;
struct nft_chain_hook hook;
const struct nlattr *name;
struct nf_hook_ops *ops;
struct nft_trans *trans;
int err, i;
if (nla[NFTA_CHAIN_HOOK]) {
if (!nft_is_base_chain(chain))
return -EBUSY;
err = nft_chain_parse_hook(ctx->net, nla, ctx->afi, &hook,
create);
if (err < 0)
return err;
basechain = nft_base_chain(chain);
if (basechain->type != hook.type) {
nft_chain_release_hook(&hook);
return -EBUSY;
}
for (i = 0; i < afi->nops; i++) {
ops = &basechain->ops[i];
if (ops->hooknum != hook.num ||
ops->priority != hook.priority ||
ops->dev != hook.dev) {
nft_chain_release_hook(&hook);
return -EBUSY;
}
}
nft_chain_release_hook(&hook);
}
if (nla[NFTA_CHAIN_HANDLE] &&
nla[NFTA_CHAIN_NAME]) {
struct nft_chain *chain2;
chain2 = nf_tables_chain_lookup(table, nla[NFTA_CHAIN_NAME],
genmask);
if (!IS_ERR(chain2))
return -EEXIST;
}
if (nla[NFTA_CHAIN_COUNTERS]) {
if (!nft_is_base_chain(chain))
return -EOPNOTSUPP;
stats = nft_stats_alloc(nla[NFTA_CHAIN_COUNTERS]);
if (IS_ERR(stats))
return PTR_ERR(stats);
}
trans = nft_trans_alloc(ctx, NFT_MSG_NEWCHAIN,
sizeof(struct nft_trans_chain));
if (trans == NULL) {
free_percpu(stats);
return -ENOMEM;
}
nft_trans_chain_stats(trans) = stats;
nft_trans_chain_update(trans) = true;
if (nla[NFTA_CHAIN_POLICY])
nft_trans_chain_policy(trans) = policy;
else
nft_trans_chain_policy(trans) = -1;
name = nla[NFTA_CHAIN_NAME];
if (nla[NFTA_CHAIN_HANDLE] && name) {
nft_trans_chain_name(trans) =
nla_strdup(name, GFP_KERNEL);
if (!nft_trans_chain_name(trans)) {
kfree(trans);
free_percpu(stats);
return -ENOMEM;
}
}
list_add_tail(&trans->list, &ctx->net->nft.commit_list);
return 0;
}
static int nf_tables_newchain(struct net *net, struct sock *nlsk,
struct sk_buff *skb, const struct nlmsghdr *nlh,
const struct nlattr * const nla[],
struct netlink_ext_ack *extack)
{
const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
const struct nlattr * uninitialized_var(name);
u8 genmask = nft_genmask_next(net);
int family = nfmsg->nfgen_family;
struct nft_af_info *afi;
struct nft_table *table;
struct nft_chain *chain;
u8 policy = NF_ACCEPT;
struct nft_ctx ctx;
u64 handle = 0;
bool create;
create = nlh->nlmsg_flags & NLM_F_CREATE ? true : false;
afi = nf_tables_afinfo_lookup(net, family, true);
if (IS_ERR(afi))
return PTR_ERR(afi);
table = nf_tables_table_lookup(afi, nla[NFTA_CHAIN_TABLE], genmask);
if (IS_ERR(table))
return PTR_ERR(table);
chain = NULL;
name = nla[NFTA_CHAIN_NAME];
if (nla[NFTA_CHAIN_HANDLE]) {
handle = be64_to_cpu(nla_get_be64(nla[NFTA_CHAIN_HANDLE]));
chain = nf_tables_chain_lookup_byhandle(table, handle, genmask);
if (IS_ERR(chain))
return PTR_ERR(chain);
} else {
chain = nf_tables_chain_lookup(table, name, genmask);
if (IS_ERR(chain)) {
if (PTR_ERR(chain) != -ENOENT)
return PTR_ERR(chain);
chain = NULL;
}
}
if (nla[NFTA_CHAIN_POLICY]) {
if (chain != NULL &&
!nft_is_base_chain(chain))
return -EOPNOTSUPP;
if (chain == NULL &&
nla[NFTA_CHAIN_HOOK] == NULL)
return -EOPNOTSUPP;
policy = ntohl(nla_get_be32(nla[NFTA_CHAIN_POLICY]));
switch (policy) {
case NF_DROP:
case NF_ACCEPT:
break;
default:
return -EINVAL;
}
}
nft_ctx_init(&ctx, net, skb, nlh, afi, table, chain, nla);
if (chain != NULL) {
if (nlh->nlmsg_flags & NLM_F_EXCL)
return -EEXIST;
if (nlh->nlmsg_flags & NLM_F_REPLACE)
return -EOPNOTSUPP;
return nf_tables_updchain(&ctx, genmask, policy, create);
}
return nf_tables_addchain(&ctx, family, genmask, policy, create);
}
static int nf_tables_delchain(struct net *net, struct sock *nlsk,
struct sk_buff *skb, const struct nlmsghdr *nlh,
const struct nlattr * const nla[],
struct netlink_ext_ack *extack)
{
const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
u8 genmask = nft_genmask_next(net);
struct nft_af_info *afi;
struct nft_table *table;
struct nft_chain *chain;
struct nft_rule *rule;
int family = nfmsg->nfgen_family;
struct nft_ctx ctx;
u32 use;
int err;
afi = nf_tables_afinfo_lookup(net, family, false);
if (IS_ERR(afi))
return PTR_ERR(afi);
table = nf_tables_table_lookup(afi, nla[NFTA_CHAIN_TABLE], genmask);
if (IS_ERR(table))
return PTR_ERR(table);
chain = nf_tables_chain_lookup(table, nla[NFTA_CHAIN_NAME], genmask);
if (IS_ERR(chain))
return PTR_ERR(chain);
if (nlh->nlmsg_flags & NLM_F_NONREC &&
chain->use > 0)
return -EBUSY;
nft_ctx_init(&ctx, net, skb, nlh, afi, table, chain, nla);
use = chain->use;
list_for_each_entry(rule, &chain->rules, list) {
if (!nft_is_active_next(net, rule))
continue;
use--;
err = nft_delrule(&ctx, rule);
if (err < 0)
return err;
}
/* There are rules and elements that are still holding references to us,
* we cannot do a recursive removal in this case.
*/
if (use > 0)
return -EBUSY;
return nft_delchain(&ctx);
}
/*
* Expressions
*/
/**
* nft_register_expr - register nf_tables expr type
* @ops: expr type
*
* Registers the expr type for use with nf_tables. Returns zero on
* success or a negative errno code otherwise.
*/
int nft_register_expr(struct nft_expr_type *type)
{
nfnl_lock(NFNL_SUBSYS_NFTABLES);
if (type->family == NFPROTO_UNSPEC)
list_add_tail_rcu(&type->list, &nf_tables_expressions);
else
list_add_rcu(&type->list, &nf_tables_expressions);
nfnl_unlock(NFNL_SUBSYS_NFTABLES);
return 0;
}
EXPORT_SYMBOL_GPL(nft_register_expr);
/**
* nft_unregister_expr - unregister nf_tables expr type
* @ops: expr type
*
* Unregisters the expr typefor use with nf_tables.
*/
void nft_unregister_expr(struct nft_expr_type *type)
{
nfnl_lock(NFNL_SUBSYS_NFTABLES);
list_del_rcu(&type->list);
nfnl_unlock(NFNL_SUBSYS_NFTABLES);
}
EXPORT_SYMBOL_GPL(nft_unregister_expr);
static const struct nft_expr_type *__nft_expr_type_get(u8 family,
struct nlattr *nla)
{
const struct nft_expr_type *type;
list_for_each_entry(type, &nf_tables_expressions, list) {
if (!nla_strcmp(nla, type->name) &&
(!type->family || type->family == family))
return type;
}
return NULL;
}
static const struct nft_expr_type *nft_expr_type_get(u8 family,
struct nlattr *nla)
{
const struct nft_expr_type *type;
if (nla == NULL)
return ERR_PTR(-EINVAL);
type = __nft_expr_type_get(family, nla);
if (type != NULL && try_module_get(type->owner))
return type;
#ifdef CONFIG_MODULES
if (type == NULL) {
nfnl_unlock(NFNL_SUBSYS_NFTABLES);
request_module("nft-expr-%u-%.*s", family,
nla_len(nla), (char *)nla_data(nla));
nfnl_lock(NFNL_SUBSYS_NFTABLES);
if (__nft_expr_type_get(family, nla))
return ERR_PTR(-EAGAIN);
nfnl_unlock(NFNL_SUBSYS_NFTABLES);
request_module("nft-expr-%.*s",
nla_len(nla), (char *)nla_data(nla));
nfnl_lock(NFNL_SUBSYS_NFTABLES);
if (__nft_expr_type_get(family, nla))
return ERR_PTR(-EAGAIN);
}
#endif
return ERR_PTR(-ENOENT);
}
static const struct nla_policy nft_expr_policy[NFTA_EXPR_MAX + 1] = {
[NFTA_EXPR_NAME] = { .type = NLA_STRING },
[NFTA_EXPR_DATA] = { .type = NLA_NESTED },
};
static int nf_tables_fill_expr_info(struct sk_buff *skb,
const struct nft_expr *expr)
{
if (nla_put_string(skb, NFTA_EXPR_NAME, expr->ops->type->name))
goto nla_put_failure;
if (expr->ops->dump) {
struct nlattr *data = nla_nest_start(skb, NFTA_EXPR_DATA);
if (data == NULL)
goto nla_put_failure;
if (expr->ops->dump(skb, expr) < 0)
goto nla_put_failure;
nla_nest_end(skb, data);
}
return skb->len;
nla_put_failure:
return -1;
};
int nft_expr_dump(struct sk_buff *skb, unsigned int attr,
const struct nft_expr *expr)
{
struct nlattr *nest;
nest = nla_nest_start(skb, attr);
if (!nest)
goto nla_put_failure;
if (nf_tables_fill_expr_info(skb, expr) < 0)
goto nla_put_failure;
nla_nest_end(skb, nest);
return 0;
nla_put_failure:
return -1;
}
struct nft_expr_info {
const struct nft_expr_ops *ops;
struct nlattr *tb[NFT_EXPR_MAXATTR + 1];
};
static int nf_tables_expr_parse(const struct nft_ctx *ctx,
const struct nlattr *nla,
struct nft_expr_info *info)
{
const struct nft_expr_type *type;
const struct nft_expr_ops *ops;
struct nlattr *tb[NFTA_EXPR_MAX + 1];
int err;
err = nla_parse_nested(tb, NFTA_EXPR_MAX, nla, nft_expr_policy, NULL);
if (err < 0)
return err;
type = nft_expr_type_get(ctx->afi->family, tb[NFTA_EXPR_NAME]);
if (IS_ERR(type))
return PTR_ERR(type);
if (tb[NFTA_EXPR_DATA]) {
err = nla_parse_nested(info->tb, type->maxattr,
tb[NFTA_EXPR_DATA], type->policy, NULL);
if (err < 0)
goto err1;
} else
memset(info->tb, 0, sizeof(info->tb[0]) * (type->maxattr + 1));
if (type->select_ops != NULL) {
ops = type->select_ops(ctx,
(const struct nlattr * const *)info->tb);
if (IS_ERR(ops)) {
err = PTR_ERR(ops);
goto err1;
}
} else
ops = type->ops;
info->ops = ops;
return 0;
err1:
module_put(type->owner);
return err;
}
static int nf_tables_newexpr(const struct nft_ctx *ctx,
const struct nft_expr_info *info,
struct nft_expr *expr)
{
const struct nft_expr_ops *ops = info->ops;
int err;
expr->ops = ops;
if (ops->init) {
err = ops->init(ctx, expr, (const struct nlattr **)info->tb);
if (err < 0)
goto err1;
}
if (ops->validate) {
const struct nft_data *data = NULL;
err = ops->validate(ctx, expr, &data);
if (err < 0)
goto err2;
}
return 0;
err2:
if (ops->destroy)
ops->destroy(ctx, expr);
err1:
expr->ops = NULL;
return err;
}
static void nf_tables_expr_destroy(const struct nft_ctx *ctx,
struct nft_expr *expr)
{
if (expr->ops->destroy)
expr->ops->destroy(ctx, expr);
module_put(expr->ops->type->owner);
}
struct nft_expr *nft_expr_init(const struct nft_ctx *ctx,
const struct nlattr *nla)
{
struct nft_expr_info info;
struct nft_expr *expr;
int err;
err = nf_tables_expr_parse(ctx, nla, &info);
if (err < 0)
goto err1;
err = -ENOMEM;
expr = kzalloc(info.ops->size, GFP_KERNEL);
if (expr == NULL)
goto err2;
err = nf_tables_newexpr(ctx, &info, expr);
if (err < 0)
goto err3;
return expr;
err3:
kfree(expr);
err2:
module_put(info.ops->type->owner);
err1:
return ERR_PTR(err);
}
void nft_expr_destroy(const struct nft_ctx *ctx, struct nft_expr *expr)
{
nf_tables_expr_destroy(ctx, expr);
kfree(expr);
}
/*
* Rules
*/
static struct nft_rule *__nf_tables_rule_lookup(const struct nft_chain *chain,
u64 handle)
{
struct nft_rule *rule;
// FIXME: this sucks
list_for_each_entry(rule, &chain->rules, list) {
if (handle == rule->handle)
return rule;
}
return ERR_PTR(-ENOENT);
}
static struct nft_rule *nf_tables_rule_lookup(const struct nft_chain *chain,
const struct nlattr *nla)
{
if (nla == NULL)
return ERR_PTR(-EINVAL);
return __nf_tables_rule_lookup(chain, be64_to_cpu(nla_get_be64(nla)));
}
static const struct nla_policy nft_rule_policy[NFTA_RULE_MAX + 1] = {
[NFTA_RULE_TABLE] = { .type = NLA_STRING,
.len = NFT_TABLE_MAXNAMELEN - 1 },
[NFTA_RULE_CHAIN] = { .type = NLA_STRING,
.len = NFT_CHAIN_MAXNAMELEN - 1 },
[NFTA_RULE_HANDLE] = { .type = NLA_U64 },
[NFTA_RULE_EXPRESSIONS] = { .type = NLA_NESTED },
[NFTA_RULE_COMPAT] = { .type = NLA_NESTED },
[NFTA_RULE_POSITION] = { .type = NLA_U64 },
[NFTA_RULE_USERDATA] = { .type = NLA_BINARY,
.len = NFT_USERDATA_MAXLEN },
};
static int nf_tables_fill_rule_info(struct sk_buff *skb, struct net *net,
u32 portid, u32 seq, int event,
u32 flags, int family,
const struct nft_table *table,
const struct nft_chain *chain,
const struct nft_rule *rule)
{
struct nlmsghdr *nlh;
struct nfgenmsg *nfmsg;
const struct nft_expr *expr, *next;
struct nlattr *list;
const struct nft_rule *prule;
u16 type = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event);
nlh = nlmsg_put(skb, portid, seq, type, sizeof(struct nfgenmsg), flags);
if (nlh == NULL)
goto nla_put_failure;
nfmsg = nlmsg_data(nlh);
nfmsg->nfgen_family = family;
nfmsg->version = NFNETLINK_V0;
nfmsg->res_id = htons(net->nft.base_seq & 0xffff);
if (nla_put_string(skb, NFTA_RULE_TABLE, table->name))
goto nla_put_failure;
if (nla_put_string(skb, NFTA_RULE_CHAIN, chain->name))
goto nla_put_failure;
if (nla_put_be64(skb, NFTA_RULE_HANDLE, cpu_to_be64(rule->handle),
NFTA_RULE_PAD))
goto nla_put_failure;
if ((event != NFT_MSG_DELRULE) && (rule->list.prev != &chain->rules)) {
prule = list_prev_entry(rule, list);
if (nla_put_be64(skb, NFTA_RULE_POSITION,
cpu_to_be64(prule->handle),
NFTA_RULE_PAD))
goto nla_put_failure;
}
list = nla_nest_start(skb, NFTA_RULE_EXPRESSIONS);
if (list == NULL)
goto nla_put_failure;
nft_rule_for_each_expr(expr, next, rule) {
if (nft_expr_dump(skb, NFTA_LIST_ELEM, expr) < 0)
goto nla_put_failure;
}
nla_nest_end(skb, list);
if (rule->udata) {
struct nft_userdata *udata = nft_userdata(rule);
if (nla_put(skb, NFTA_RULE_USERDATA, udata->len + 1,
udata->data) < 0)
goto nla_put_failure;
}
nlmsg_end(skb, nlh);
return 0;
nla_put_failure:
nlmsg_trim(skb, nlh);
return -1;
}
static void nf_tables_rule_notify(const struct nft_ctx *ctx,
const struct nft_rule *rule, int event)
{
struct sk_buff *skb;
int err;
if (!ctx->report &&
!nfnetlink_has_listeners(ctx->net, NFNLGRP_NFTABLES))
return;
skb = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL);
if (skb == NULL)
goto err;
err = nf_tables_fill_rule_info(skb, ctx->net, ctx->portid, ctx->seq,
event, 0, ctx->afi->family, ctx->table,
ctx->chain, rule);
if (err < 0) {
kfree_skb(skb);
goto err;
}
nfnetlink_send(skb, ctx->net, ctx->portid, NFNLGRP_NFTABLES,
ctx->report, GFP_KERNEL);
return;
err:
nfnetlink_set_err(ctx->net, ctx->portid, NFNLGRP_NFTABLES, -ENOBUFS);
}
struct nft_rule_dump_ctx {
char *table;
char *chain;
};
static int nf_tables_dump_rules(struct sk_buff *skb,
struct netlink_callback *cb)
{
const struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh);
const struct nft_rule_dump_ctx *ctx = cb->data;
const struct nft_af_info *afi;
const struct nft_table *table;
const struct nft_chain *chain;
const struct nft_rule *rule;
unsigned int idx = 0, s_idx = cb->args[0];
struct net *net = sock_net(skb->sk);
int family = nfmsg->nfgen_family;
rcu_read_lock();
cb->seq = net->nft.base_seq;
list_for_each_entry_rcu(afi, &net->nft.af_info, list) {
if (family != NFPROTO_UNSPEC && family != afi->family)
continue;
list_for_each_entry_rcu(table, &afi->tables, list) {
if (ctx && ctx->table &&
strcmp(ctx->table, table->name) != 0)
continue;
list_for_each_entry_rcu(chain, &table->chains, list) {
if (ctx && ctx->chain[0] &&
strcmp(ctx->chain, chain->name) != 0)
continue;
list_for_each_entry_rcu(rule, &chain->rules, list) {
if (!nft_is_active(net, rule))
goto cont;
if (idx < s_idx)
goto cont;
if (idx > s_idx)
memset(&cb->args[1], 0,
sizeof(cb->args) - sizeof(cb->args[0]));
if (nf_tables_fill_rule_info(skb, net, NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq,
NFT_MSG_NEWRULE,
NLM_F_MULTI | NLM_F_APPEND,
afi->family, table, chain, rule) < 0)
goto done;
nl_dump_check_consistent(cb, nlmsg_hdr(skb));
cont:
idx++;
}
}
}
}
done:
rcu_read_unlock();
cb->args[0] = idx;
return skb->len;
}
static int nf_tables_dump_rules_done(struct netlink_callback *cb)
{
struct nft_rule_dump_ctx *ctx = cb->data;
if (ctx) {
kfree(ctx->table);
kfree(ctx->chain);
kfree(ctx);
}
return 0;
}
static int nf_tables_getrule(struct net *net, struct sock *nlsk,
struct sk_buff *skb, const struct nlmsghdr *nlh,
const struct nlattr * const nla[],
struct netlink_ext_ack *extack)
{
const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
u8 genmask = nft_genmask_cur(net);
const struct nft_af_info *afi;
const struct nft_table *table;
const struct nft_chain *chain;
const struct nft_rule *rule;
struct sk_buff *skb2;
int family = nfmsg->nfgen_family;
int err;
if (nlh->nlmsg_flags & NLM_F_DUMP) {
struct netlink_dump_control c = {
.dump = nf_tables_dump_rules,
.done = nf_tables_dump_rules_done,
};
if (nla[NFTA_RULE_TABLE] || nla[NFTA_RULE_CHAIN]) {
struct nft_rule_dump_ctx *ctx;
ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
if (!ctx)
return -ENOMEM;
if (nla[NFTA_RULE_TABLE]) {
ctx->table = nla_strdup(nla[NFTA_RULE_TABLE],
GFP_KERNEL);
if (!ctx->table) {
kfree(ctx);
return -ENOMEM;
}
}
if (nla[NFTA_RULE_CHAIN]) {
ctx->chain = nla_strdup(nla[NFTA_RULE_CHAIN],
GFP_KERNEL);
if (!ctx->chain) {
kfree(ctx->table);
kfree(ctx);
return -ENOMEM;
}
}
c.data = ctx;
}
return netlink_dump_start(nlsk, skb, nlh, &c);
}
afi = nf_tables_afinfo_lookup(net, family, false);
if (IS_ERR(afi))
return PTR_ERR(afi);
table = nf_tables_table_lookup(afi, nla[NFTA_RULE_TABLE], genmask);
if (IS_ERR(table))
return PTR_ERR(table);
chain = nf_tables_chain_lookup(table, nla[NFTA_RULE_CHAIN], genmask);
if (IS_ERR(chain))
return PTR_ERR(chain);
rule = nf_tables_rule_lookup(chain, nla[NFTA_RULE_HANDLE]);
if (IS_ERR(rule))
return PTR_ERR(rule);
skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
if (!skb2)
return -ENOMEM;
err = nf_tables_fill_rule_info(skb2, net, NETLINK_CB(skb).portid,
nlh->nlmsg_seq, NFT_MSG_NEWRULE, 0,
family, table, chain, rule);
if (err < 0)
goto err;
return nlmsg_unicast(nlsk, skb2, NETLINK_CB(skb).portid);
err:
kfree_skb(skb2);
return err;
}
static void nf_tables_rule_destroy(const struct nft_ctx *ctx,
struct nft_rule *rule)
{
struct nft_expr *expr;
/*
* Careful: some expressions might not be initialized in case this
* is called on error from nf_tables_newrule().
*/
expr = nft_expr_first(rule);
while (expr != nft_expr_last(rule) && expr->ops) {
nf_tables_expr_destroy(ctx, expr);
expr = nft_expr_next(expr);
}
kfree(rule);
}
#define NFT_RULE_MAXEXPRS 128
static struct nft_expr_info *info;
static int nf_tables_newrule(struct net *net, struct sock *nlsk,
struct sk_buff *skb, const struct nlmsghdr *nlh,
const struct nlattr * const nla[],
struct netlink_ext_ack *extack)
{
const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
u8 genmask = nft_genmask_next(net);
struct nft_af_info *afi;
struct nft_table *table;
struct nft_chain *chain;
struct nft_rule *rule, *old_rule = NULL;
struct nft_userdata *udata;
struct nft_trans *trans = NULL;
struct nft_expr *expr;
struct nft_ctx ctx;
struct nlattr *tmp;
unsigned int size, i, n, ulen = 0, usize = 0;
int err, rem;
bool create;
u64 handle, pos_handle;
create = nlh->nlmsg_flags & NLM_F_CREATE ? true : false;
afi = nf_tables_afinfo_lookup(net, nfmsg->nfgen_family, create);
if (IS_ERR(afi))
return PTR_ERR(afi);
table = nf_tables_table_lookup(afi, nla[NFTA_RULE_TABLE], genmask);
if (IS_ERR(table))
return PTR_ERR(table);
chain = nf_tables_chain_lookup(table, nla[NFTA_RULE_CHAIN], genmask);
if (IS_ERR(chain))
return PTR_ERR(chain);
if (nla[NFTA_RULE_HANDLE]) {
handle = be64_to_cpu(nla_get_be64(nla[NFTA_RULE_HANDLE]));
rule = __nf_tables_rule_lookup(chain, handle);
if (IS_ERR(rule))
return PTR_ERR(rule);
if (nlh->nlmsg_flags & NLM_F_EXCL)
return -EEXIST;
if (nlh->nlmsg_flags & NLM_F_REPLACE)
old_rule = rule;
else
return -EOPNOTSUPP;
} else {
if (!create || nlh->nlmsg_flags & NLM_F_REPLACE)
return -EINVAL;
handle = nf_tables_alloc_handle(table);
if (chain->use == UINT_MAX)
return -EOVERFLOW;
}
if (nla[NFTA_RULE_POSITION]) {
if (!(nlh->nlmsg_flags & NLM_F_CREATE))
return -EOPNOTSUPP;
pos_handle = be64_to_cpu(nla_get_be64(nla[NFTA_RULE_POSITION]));
old_rule = __nf_tables_rule_lookup(chain, pos_handle);
if (IS_ERR(old_rule))
return PTR_ERR(old_rule);
}
nft_ctx_init(&ctx, net, skb, nlh, afi, table, chain, nla);
n = 0;
size = 0;
if (nla[NFTA_RULE_EXPRESSIONS]) {
nla_for_each_nested(tmp, nla[NFTA_RULE_EXPRESSIONS], rem) {
err = -EINVAL;
if (nla_type(tmp) != NFTA_LIST_ELEM)
goto err1;
if (n == NFT_RULE_MAXEXPRS)
goto err1;
err = nf_tables_expr_parse(&ctx, tmp, &info[n]);
if (err < 0)
goto err1;
size += info[n].ops->size;
n++;
}
}
/* Check for overflow of dlen field */
err = -EFBIG;
if (size >= 1 << 12)
goto err1;
if (nla[NFTA_RULE_USERDATA]) {
ulen = nla_len(nla[NFTA_RULE_USERDATA]);
if (ulen > 0)
usize = sizeof(struct nft_userdata) + ulen;
}
err = -ENOMEM;
rule = kzalloc(sizeof(*rule) + size + usize, GFP_KERNEL);
if (rule == NULL)
goto err1;
nft_activate_next(net, rule);
rule->handle = handle;
rule->dlen = size;
rule->udata = ulen ? 1 : 0;
if (ulen) {
udata = nft_userdata(rule);
udata->len = ulen - 1;
nla_memcpy(udata->data, nla[NFTA_RULE_USERDATA], ulen);
}
expr = nft_expr_first(rule);
for (i = 0; i < n; i++) {
err = nf_tables_newexpr(&ctx, &info[i], expr);
if (err < 0)
goto err2;
info[i].ops = NULL;
expr = nft_expr_next(expr);
}
if (nlh->nlmsg_flags & NLM_F_REPLACE) {
if (nft_is_active_next(net, old_rule)) {
trans = nft_trans_rule_add(&ctx, NFT_MSG_DELRULE,
old_rule);
if (trans == NULL) {
err = -ENOMEM;
goto err2;
}
nft_deactivate_next(net, old_rule);
chain->use--;
list_add_tail_rcu(&rule->list, &old_rule->list);
} else {
err = -ENOENT;
goto err2;
}
} else if (nlh->nlmsg_flags & NLM_F_APPEND)
if (old_rule)
list_add_rcu(&rule->list, &old_rule->list);
else
list_add_tail_rcu(&rule->list, &chain->rules);
else {
if (old_rule)
list_add_tail_rcu(&rule->list, &old_rule->list);
else
list_add_rcu(&rule->list, &chain->rules);
}
if (nft_trans_rule_add(&ctx, NFT_MSG_NEWRULE, rule) == NULL) {
err = -ENOMEM;
goto err3;
}
chain->use++;
return 0;
err3:
list_del_rcu(&rule->list);
err2:
nf_tables_rule_destroy(&ctx, rule);
err1:
for (i = 0; i < n; i++) {
if (info[i].ops != NULL)
module_put(info[i].ops->type->owner);
}
return err;
}
static struct nft_rule *nft_rule_lookup_byid(const struct net *net,
const struct nlattr *nla)
{
u32 id = ntohl(nla_get_be32(nla));
struct nft_trans *trans;
list_for_each_entry(trans, &net->nft.commit_list, list) {
struct nft_rule *rule = nft_trans_rule(trans);
if (trans->msg_type == NFT_MSG_NEWRULE &&
id == nft_trans_rule_id(trans))
return rule;
}
return ERR_PTR(-ENOENT);
}
static int nf_tables_delrule(struct net *net, struct sock *nlsk,
struct sk_buff *skb, const struct nlmsghdr *nlh,
const struct nlattr * const nla[],
struct netlink_ext_ack *extack)
{
const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
u8 genmask = nft_genmask_next(net);
struct nft_af_info *afi;
struct nft_table *table;
struct nft_chain *chain = NULL;
struct nft_rule *rule;
int family = nfmsg->nfgen_family, err = 0;
struct nft_ctx ctx;
afi = nf_tables_afinfo_lookup(net, family, false);
if (IS_ERR(afi))
return PTR_ERR(afi);
table = nf_tables_table_lookup(afi, nla[NFTA_RULE_TABLE], genmask);
if (IS_ERR(table))
return PTR_ERR(table);
if (nla[NFTA_RULE_CHAIN]) {
chain = nf_tables_chain_lookup(table, nla[NFTA_RULE_CHAIN],
genmask);
if (IS_ERR(chain))
return PTR_ERR(chain);
}
nft_ctx_init(&ctx, net, skb, nlh, afi, table, chain, nla);
if (chain) {
if (nla[NFTA_RULE_HANDLE]) {
rule = nf_tables_rule_lookup(chain,
nla[NFTA_RULE_HANDLE]);
if (IS_ERR(rule))
return PTR_ERR(rule);
err = nft_delrule(&ctx, rule);
} else if (nla[NFTA_RULE_ID]) {
rule = nft_rule_lookup_byid(net, nla[NFTA_RULE_ID]);
if (IS_ERR(rule))
return PTR_ERR(rule);
err = nft_delrule(&ctx, rule);
} else {
err = nft_delrule_by_chain(&ctx);
}
} else {
list_for_each_entry(chain, &table->chains, list) {
if (!nft_is_active_next(net, chain))
continue;
ctx.chain = chain;
err = nft_delrule_by_chain(&ctx);
if (err < 0)
break;
}
}
return err;
}
/*
* Sets
*/
static LIST_HEAD(nf_tables_set_types);
int nft_register_set(struct nft_set_type *type)
{
nfnl_lock(NFNL_SUBSYS_NFTABLES);
list_add_tail_rcu(&type->list, &nf_tables_set_types);
nfnl_unlock(NFNL_SUBSYS_NFTABLES);
return 0;
}
EXPORT_SYMBOL_GPL(nft_register_set);
void nft_unregister_set(struct nft_set_type *type)
{
nfnl_lock(NFNL_SUBSYS_NFTABLES);
list_del_rcu(&type->list);
nfnl_unlock(NFNL_SUBSYS_NFTABLES);
}
EXPORT_SYMBOL_GPL(nft_unregister_set);
#define NFT_SET_FEATURES (NFT_SET_INTERVAL | NFT_SET_MAP | \
NFT_SET_TIMEOUT | NFT_SET_OBJECT)
static bool nft_set_ops_candidate(const struct nft_set_ops *ops, u32 flags)
{
return (flags & ops->features) == (flags & NFT_SET_FEATURES);
}
/*
* Select a set implementation based on the data characteristics and the
* given policy. The total memory use might not be known if no size is
* given, in that case the amount of memory per element is used.
*/
static const struct nft_set_ops *
nft_select_set_ops(const struct nft_ctx *ctx,
const struct nlattr * const nla[],
const struct nft_set_desc *desc,
enum nft_set_policies policy)
{
const struct nft_set_ops *ops, *bops;
struct nft_set_estimate est, best;
const struct nft_set_type *type;
u32 flags = 0;
#ifdef CONFIG_MODULES
if (list_empty(&nf_tables_set_types)) {
nfnl_unlock(NFNL_SUBSYS_NFTABLES);
request_module("nft-set");
nfnl_lock(NFNL_SUBSYS_NFTABLES);
if (!list_empty(&nf_tables_set_types))
return ERR_PTR(-EAGAIN);
}
#endif
if (nla[NFTA_SET_FLAGS] != NULL)
flags = ntohl(nla_get_be32(nla[NFTA_SET_FLAGS]));
bops = NULL;
best.size = ~0;
best.lookup = ~0;
best.space = ~0;
list_for_each_entry(type, &nf_tables_set_types, list) {
if (!type->select_ops)
ops = type->ops;
else
ops = type->select_ops(ctx, desc, flags);
if (!ops)
continue;
if (!nft_set_ops_candidate(ops, flags))
continue;
if (!ops->estimate(desc, flags, &est))
continue;
switch (policy) {
case NFT_SET_POL_PERFORMANCE:
if (est.lookup < best.lookup)
break;
if (est.lookup == best.lookup) {
if (!desc->size) {
if (est.space < best.space)
break;
} else if (est.size < best.size) {
break;
}
}
continue;
case NFT_SET_POL_MEMORY:
if (!desc->size) {
if (est.space < best.space)
break;
if (est.space == best.space &&
est.lookup < best.lookup)
break;
} else if (est.size < best.size) {
break;
}
continue;
default:
break;
}
if (!try_module_get(type->owner))
continue;
if (bops != NULL)
module_put(bops->type->owner);
bops = ops;
best = est;
}
if (bops != NULL)
return bops;
return ERR_PTR(-EOPNOTSUPP);
}
static const struct nla_policy nft_set_policy[NFTA_SET_MAX + 1] = {
[NFTA_SET_TABLE] = { .type = NLA_STRING,
.len = NFT_TABLE_MAXNAMELEN - 1 },
[NFTA_SET_NAME] = { .type = NLA_STRING,
.len = NFT_SET_MAXNAMELEN - 1 },
[NFTA_SET_FLAGS] = { .type = NLA_U32 },
[NFTA_SET_KEY_TYPE] = { .type = NLA_U32 },
[NFTA_SET_KEY_LEN] = { .type = NLA_U32 },
[NFTA_SET_DATA_TYPE] = { .type = NLA_U32 },
[NFTA_SET_DATA_LEN] = { .type = NLA_U32 },
[NFTA_SET_POLICY] = { .type = NLA_U32 },
[NFTA_SET_DESC] = { .type = NLA_NESTED },
[NFTA_SET_ID] = { .type = NLA_U32 },
[NFTA_SET_TIMEOUT] = { .type = NLA_U64 },
[NFTA_SET_GC_INTERVAL] = { .type = NLA_U32 },
[NFTA_SET_USERDATA] = { .type = NLA_BINARY,
.len = NFT_USERDATA_MAXLEN },
[NFTA_SET_OBJ_TYPE] = { .type = NLA_U32 },
};
static const struct nla_policy nft_set_desc_policy[NFTA_SET_DESC_MAX + 1] = {
[NFTA_SET_DESC_SIZE] = { .type = NLA_U32 },
};
static int nft_ctx_init_from_setattr(struct nft_ctx *ctx, struct net *net,
const struct sk_buff *skb,
const struct nlmsghdr *nlh,
const struct nlattr * const nla[],
u8 genmask)
{
const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
struct nft_af_info *afi = NULL;
struct nft_table *table = NULL;
if (nfmsg->nfgen_family != NFPROTO_UNSPEC) {
afi = nf_tables_afinfo_lookup(net, nfmsg->nfgen_family, false);
if (IS_ERR(afi))
return PTR_ERR(afi);
}
if (nla[NFTA_SET_TABLE] != NULL) {
if (afi == NULL)
return -EAFNOSUPPORT;
table = nf_tables_table_lookup(afi, nla[NFTA_SET_TABLE],
genmask);
if (IS_ERR(table))
return PTR_ERR(table);
}
nft_ctx_init(ctx, net, skb, nlh, afi, table, NULL, nla);
return 0;
}
static struct nft_set *nf_tables_set_lookup(const struct nft_table *table,
const struct nlattr *nla, u8 genmask)
{
struct nft_set *set;
if (nla == NULL)
return ERR_PTR(-EINVAL);
list_for_each_entry(set, &table->sets, list) {
if (!nla_strcmp(nla, set->name) &&
nft_active_genmask(set, genmask))
return set;
}
return ERR_PTR(-ENOENT);
}
static struct nft_set *nf_tables_set_lookup_byid(const struct net *net,
const struct nlattr *nla,
u8 genmask)
{
struct nft_trans *trans;
u32 id = ntohl(nla_get_be32(nla));
list_for_each_entry(trans, &net->nft.commit_list, list) {
struct nft_set *set = nft_trans_set(trans);
if (trans->msg_type == NFT_MSG_NEWSET &&
id == nft_trans_set_id(trans) &&
nft_active_genmask(set, genmask))
return set;
}
return ERR_PTR(-ENOENT);
}
struct nft_set *nft_set_lookup(const struct net *net,
const struct nft_table *table,
const struct nlattr *nla_set_name,
const struct nlattr *nla_set_id,
u8 genmask)
{
struct nft_set *set;
set = nf_tables_set_lookup(table, nla_set_name, genmask);
if (IS_ERR(set)) {
if (!nla_set_id)
return set;
set = nf_tables_set_lookup_byid(net, nla_set_id, genmask);
}
return set;
}
EXPORT_SYMBOL_GPL(nft_set_lookup);
static int nf_tables_set_alloc_name(struct nft_ctx *ctx, struct nft_set *set,
const char *name)
{
const struct nft_set *i;
const char *p;
unsigned long *inuse;
unsigned int n = 0, min = 0;
p = strchr(name, '%');
if (p != NULL) {
if (p[1] != 'd' || strchr(p + 2, '%'))
return -EINVAL;
inuse = (unsigned long *)get_zeroed_page(GFP_KERNEL);
if (inuse == NULL)
return -ENOMEM;
cont:
list_for_each_entry(i, &ctx->table->sets, list) {
int tmp;
if (!nft_is_active_next(ctx->net, set))
continue;
if (!sscanf(i->name, name, &tmp))
continue;
if (tmp < min || tmp >= min + BITS_PER_BYTE * PAGE_SIZE)
continue;
set_bit(tmp - min, inuse);
}
n = find_first_zero_bit(inuse, BITS_PER_BYTE * PAGE_SIZE);
if (n >= BITS_PER_BYTE * PAGE_SIZE) {
min += BITS_PER_BYTE * PAGE_SIZE;
memset(inuse, 0, PAGE_SIZE);
goto cont;
}
free_page((unsigned long)inuse);
}
set->name = kasprintf(GFP_KERNEL, name, min + n);
if (!set->name)
return -ENOMEM;
list_for_each_entry(i, &ctx->table->sets, list) {
if (!nft_is_active_next(ctx->net, i))
continue;
if (!strcmp(set->name, i->name)) {
kfree(set->name);
return -ENFILE;
}
}
return 0;
}
static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx,
const struct nft_set *set, u16 event, u16 flags)
{
struct nfgenmsg *nfmsg;
struct nlmsghdr *nlh;
struct nlattr *desc;
u32 portid = ctx->portid;
u32 seq = ctx->seq;
event = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event);
nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct nfgenmsg),
flags);
if (nlh == NULL)
goto nla_put_failure;
nfmsg = nlmsg_data(nlh);
nfmsg->nfgen_family = ctx->afi->family;
nfmsg->version = NFNETLINK_V0;
nfmsg->res_id = htons(ctx->net->nft.base_seq & 0xffff);
if (nla_put_string(skb, NFTA_SET_TABLE, ctx->table->name))
goto nla_put_failure;
if (nla_put_string(skb, NFTA_SET_NAME, set->name))
goto nla_put_failure;
if (set->flags != 0)
if (nla_put_be32(skb, NFTA_SET_FLAGS, htonl(set->flags)))
goto nla_put_failure;
if (nla_put_be32(skb, NFTA_SET_KEY_TYPE, htonl(set->ktype)))
goto nla_put_failure;
if (nla_put_be32(skb, NFTA_SET_KEY_LEN, htonl(set->klen)))
goto nla_put_failure;
if (set->flags & NFT_SET_MAP) {
if (nla_put_be32(skb, NFTA_SET_DATA_TYPE, htonl(set->dtype)))
goto nla_put_failure;
if (nla_put_be32(skb, NFTA_SET_DATA_LEN, htonl(set->dlen)))
goto nla_put_failure;
}
if (set->flags & NFT_SET_OBJECT &&
nla_put_be32(skb, NFTA_SET_OBJ_TYPE, htonl(set->objtype)))
goto nla_put_failure;
if (set->timeout &&
nla_put_be64(skb, NFTA_SET_TIMEOUT,
cpu_to_be64(jiffies_to_msecs(set->timeout)),
NFTA_SET_PAD))
goto nla_put_failure;
if (set->gc_int &&
nla_put_be32(skb, NFTA_SET_GC_INTERVAL, htonl(set->gc_int)))
goto nla_put_failure;
if (set->policy != NFT_SET_POL_PERFORMANCE) {
if (nla_put_be32(skb, NFTA_SET_POLICY, htonl(set->policy)))
goto nla_put_failure;
}
if (nla_put(skb, NFTA_SET_USERDATA, set->udlen, set->udata))
goto nla_put_failure;
desc = nla_nest_start(skb, NFTA_SET_DESC);
if (desc == NULL)
goto nla_put_failure;
if (set->size &&
nla_put_be32(skb, NFTA_SET_DESC_SIZE, htonl(set->size)))
goto nla_put_failure;
nla_nest_end(skb, desc);
nlmsg_end(skb, nlh);
return 0;
nla_put_failure:
nlmsg_trim(skb, nlh);
return -1;
}
static void nf_tables_set_notify(const struct nft_ctx *ctx,
const struct nft_set *set, int event,
gfp_t gfp_flags)
{
struct sk_buff *skb;
u32 portid = ctx->portid;
int err;
if (!ctx->report &&
!nfnetlink_has_listeners(ctx->net, NFNLGRP_NFTABLES))
return;
skb = nlmsg_new(NLMSG_GOODSIZE, gfp_flags);
if (skb == NULL)
goto err;
err = nf_tables_fill_set(skb, ctx, set, event, 0);
if (err < 0) {
kfree_skb(skb);
goto err;
}
nfnetlink_send(skb, ctx->net, portid, NFNLGRP_NFTABLES, ctx->report,
gfp_flags);
return;
err:
nfnetlink_set_err(ctx->net, portid, NFNLGRP_NFTABLES, -ENOBUFS);
}
static int nf_tables_dump_sets(struct sk_buff *skb, struct netlink_callback *cb)
{
const struct nft_set *set;
unsigned int idx, s_idx = cb->args[0];
struct nft_af_info *afi;
struct nft_table *table, *cur_table = (struct nft_table *)cb->args[2];
struct net *net = sock_net(skb->sk);
int cur_family = cb->args[3];
struct nft_ctx *ctx = cb->data, ctx_set;
if (cb->args[1])
return skb->len;
rcu_read_lock();
cb->seq = net->nft.base_seq;
list_for_each_entry_rcu(afi, &net->nft.af_info, list) {
if (ctx->afi && ctx->afi != afi)
continue;
if (cur_family) {
if (afi->family != cur_family)
continue;
cur_family = 0;
}
list_for_each_entry_rcu(table, &afi->tables, list) {
if (ctx->table && ctx->table != table)
continue;
if (cur_table) {
if (cur_table != table)
continue;
cur_table = NULL;
}
idx = 0;
list_for_each_entry_rcu(set, &table->sets, list) {
if (idx < s_idx)
goto cont;
if (!nft_is_active(net, set))
goto cont;
ctx_set = *ctx;
ctx_set.table = table;
ctx_set.afi = afi;
if (nf_tables_fill_set(skb, &ctx_set, set,
NFT_MSG_NEWSET,
NLM_F_MULTI) < 0) {
cb->