linuxdebug/net/sched/act_ipt.c

453 lines
10 KiB
C

// SPDX-License-Identifier: GPL-2.0-or-later
/*
* net/sched/act_ipt.c iptables target interface
*
*TODO: Add other tables. For now we only support the ipv4 table targets
*
* Copyright: Jamal Hadi Salim (2002-13)
*/
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/string.h>
#include <linux/errno.h>
#include <linux/skbuff.h>
#include <linux/rtnetlink.h>
#include <linux/module.h>
#include <linux/init.h>
#include <linux/slab.h>
#include <net/netlink.h>
#include <net/pkt_sched.h>
#include <linux/tc_act/tc_ipt.h>
#include <net/tc_act/tc_ipt.h>
#include <linux/netfilter_ipv4/ip_tables.h>
static struct tc_action_ops act_ipt_ops;
static struct tc_action_ops act_xt_ops;
static int ipt_init_target(struct net *net, struct xt_entry_target *t,
char *table, unsigned int hook)
{
struct xt_tgchk_param par;
struct xt_target *target;
struct ipt_entry e = {};
int ret = 0;
target = xt_request_find_target(AF_INET, t->u.user.name,
t->u.user.revision);
if (IS_ERR(target))
return PTR_ERR(target);
t->u.kernel.target = target;
memset(&par, 0, sizeof(par));
par.net = net;
par.table = table;
par.entryinfo = &e;
par.target = target;
par.targinfo = t->data;
par.hook_mask = 1 << hook;
par.family = NFPROTO_IPV4;
ret = xt_check_target(&par, t->u.target_size - sizeof(*t), 0, false);
if (ret < 0) {
module_put(t->u.kernel.target->me);
return ret;
}
return 0;
}
static void ipt_destroy_target(struct xt_entry_target *t, struct net *net)
{
struct xt_tgdtor_param par = {
.target = t->u.kernel.target,
.targinfo = t->data,
.family = NFPROTO_IPV4,
.net = net,
};
if (par.target->destroy != NULL)
par.target->destroy(&par);
module_put(par.target->me);
}
static void tcf_ipt_release(struct tc_action *a)
{
struct tcf_ipt *ipt = to_ipt(a);
if (ipt->tcfi_t) {
ipt_destroy_target(ipt->tcfi_t, a->idrinfo->net);
kfree(ipt->tcfi_t);
}
kfree(ipt->tcfi_tname);
}
static const struct nla_policy ipt_policy[TCA_IPT_MAX + 1] = {
[TCA_IPT_TABLE] = { .type = NLA_STRING, .len = IFNAMSIZ },
[TCA_IPT_HOOK] = NLA_POLICY_RANGE(NLA_U32, NF_INET_PRE_ROUTING,
NF_INET_NUMHOOKS),
[TCA_IPT_INDEX] = { .type = NLA_U32 },
[TCA_IPT_TARG] = { .len = sizeof(struct xt_entry_target) },
};
static int __tcf_ipt_init(struct net *net, unsigned int id, struct nlattr *nla,
struct nlattr *est, struct tc_action **a,
const struct tc_action_ops *ops,
struct tcf_proto *tp, u32 flags)
{
struct tc_action_net *tn = net_generic(net, id);
bool bind = flags & TCA_ACT_FLAGS_BIND;
struct nlattr *tb[TCA_IPT_MAX + 1];
struct tcf_ipt *ipt;
struct xt_entry_target *td, *t;
char *tname;
bool exists = false;
int ret = 0, err;
u32 hook = 0;
u32 index = 0;
if (nla == NULL)
return -EINVAL;
err = nla_parse_nested_deprecated(tb, TCA_IPT_MAX, nla, ipt_policy,
NULL);
if (err < 0)
return err;
if (tb[TCA_IPT_INDEX] != NULL)
index = nla_get_u32(tb[TCA_IPT_INDEX]);
err = tcf_idr_check_alloc(tn, &index, a, bind);
if (err < 0)
return err;
exists = err;
if (exists && bind)
return 0;
if (tb[TCA_IPT_HOOK] == NULL || tb[TCA_IPT_TARG] == NULL) {
if (exists)
tcf_idr_release(*a, bind);
else
tcf_idr_cleanup(tn, index);
return -EINVAL;
}
td = (struct xt_entry_target *)nla_data(tb[TCA_IPT_TARG]);
if (nla_len(tb[TCA_IPT_TARG]) != td->u.target_size) {
if (exists)
tcf_idr_release(*a, bind);
else
tcf_idr_cleanup(tn, index);
return -EINVAL;
}
if (!exists) {
ret = tcf_idr_create(tn, index, est, a, ops, bind,
false, flags);
if (ret) {
tcf_idr_cleanup(tn, index);
return ret;
}
ret = ACT_P_CREATED;
} else {
if (bind)/* dont override defaults */
return 0;
if (!(flags & TCA_ACT_FLAGS_REPLACE)) {
tcf_idr_release(*a, bind);
return -EEXIST;
}
}
err = -EINVAL;
hook = nla_get_u32(tb[TCA_IPT_HOOK]);
switch (hook) {
case NF_INET_PRE_ROUTING:
break;
case NF_INET_POST_ROUTING:
break;
default:
goto err1;
}
if (tb[TCA_IPT_TABLE]) {
/* mangle only for now */
if (nla_strcmp(tb[TCA_IPT_TABLE], "mangle"))
goto err1;
}
tname = kstrdup("mangle", GFP_KERNEL);
if (unlikely(!tname))
goto err1;
t = kmemdup(td, td->u.target_size, GFP_KERNEL);
if (unlikely(!t))
goto err2;
err = ipt_init_target(net, t, tname, hook);
if (err < 0)
goto err3;
ipt = to_ipt(*a);
spin_lock_bh(&ipt->tcf_lock);
if (ret != ACT_P_CREATED) {
ipt_destroy_target(ipt->tcfi_t, net);
kfree(ipt->tcfi_tname);
kfree(ipt->tcfi_t);
}
ipt->tcfi_tname = tname;
ipt->tcfi_t = t;
ipt->tcfi_hook = hook;
spin_unlock_bh(&ipt->tcf_lock);
return ret;
err3:
kfree(t);
err2:
kfree(tname);
err1:
tcf_idr_release(*a, bind);
return err;
}
static int tcf_ipt_init(struct net *net, struct nlattr *nla,
struct nlattr *est, struct tc_action **a,
struct tcf_proto *tp,
u32 flags, struct netlink_ext_ack *extack)
{
return __tcf_ipt_init(net, act_ipt_ops.net_id, nla, est,
a, &act_ipt_ops, tp, flags);
}
static int tcf_xt_init(struct net *net, struct nlattr *nla,
struct nlattr *est, struct tc_action **a,
struct tcf_proto *tp,
u32 flags, struct netlink_ext_ack *extack)
{
return __tcf_ipt_init(net, act_xt_ops.net_id, nla, est,
a, &act_xt_ops, tp, flags);
}
static bool tcf_ipt_act_check(struct sk_buff *skb)
{
const struct iphdr *iph;
unsigned int nhoff, len;
if (!pskb_may_pull(skb, sizeof(struct iphdr)))
return false;
nhoff = skb_network_offset(skb);
iph = ip_hdr(skb);
if (iph->ihl < 5 || iph->version != 4)
return false;
len = skb_ip_totlen(skb);
if (skb->len < nhoff + len || len < (iph->ihl * 4u))
return false;
return pskb_may_pull(skb, iph->ihl * 4u);
}
static int tcf_ipt_act(struct sk_buff *skb, const struct tc_action *a,
struct tcf_result *res)
{
int ret = 0, result = 0;
struct tcf_ipt *ipt = to_ipt(a);
struct xt_action_param par;
struct nf_hook_state state = {
.net = dev_net(skb->dev),
.in = skb->dev,
.hook = ipt->tcfi_hook,
.pf = NFPROTO_IPV4,
};
if (skb_protocol(skb, false) != htons(ETH_P_IP))
return TC_ACT_UNSPEC;
if (skb_unclone(skb, GFP_ATOMIC))
return TC_ACT_UNSPEC;
if (!tcf_ipt_act_check(skb))
return TC_ACT_UNSPEC;
if (state.hook == NF_INET_POST_ROUTING) {
if (!skb_dst(skb))
return TC_ACT_UNSPEC;
state.out = skb->dev;
}
spin_lock(&ipt->tcf_lock);
tcf_lastuse_update(&ipt->tcf_tm);
bstats_update(&ipt->tcf_bstats, skb);
/* yes, we have to worry about both in and out dev
* worry later - danger - this API seems to have changed
* from earlier kernels
*/
par.state = &state;
par.target = ipt->tcfi_t->u.kernel.target;
par.targinfo = ipt->tcfi_t->data;
ret = par.target->target(skb, &par);
switch (ret) {
case NF_ACCEPT:
result = TC_ACT_OK;
break;
case NF_DROP:
result = TC_ACT_SHOT;
ipt->tcf_qstats.drops++;
break;
case XT_CONTINUE:
result = TC_ACT_PIPE;
break;
default:
net_notice_ratelimited("tc filter: Bogus netfilter code %d assume ACCEPT\n",
ret);
result = TC_ACT_OK;
break;
}
spin_unlock(&ipt->tcf_lock);
return result;
}
static int tcf_ipt_dump(struct sk_buff *skb, struct tc_action *a, int bind,
int ref)
{
unsigned char *b = skb_tail_pointer(skb);
struct tcf_ipt *ipt = to_ipt(a);
struct xt_entry_target *t;
struct tcf_t tm;
struct tc_cnt c;
/* for simple targets kernel size == user size
* user name = target name
* for foolproof you need to not assume this
*/
spin_lock_bh(&ipt->tcf_lock);
t = kmemdup(ipt->tcfi_t, ipt->tcfi_t->u.user.target_size, GFP_ATOMIC);
if (unlikely(!t))
goto nla_put_failure;
c.bindcnt = atomic_read(&ipt->tcf_bindcnt) - bind;
c.refcnt = refcount_read(&ipt->tcf_refcnt) - ref;
strcpy(t->u.user.name, ipt->tcfi_t->u.kernel.target->name);
if (nla_put(skb, TCA_IPT_TARG, ipt->tcfi_t->u.user.target_size, t) ||
nla_put_u32(skb, TCA_IPT_INDEX, ipt->tcf_index) ||
nla_put_u32(skb, TCA_IPT_HOOK, ipt->tcfi_hook) ||
nla_put(skb, TCA_IPT_CNT, sizeof(struct tc_cnt), &c) ||
nla_put_string(skb, TCA_IPT_TABLE, ipt->tcfi_tname))
goto nla_put_failure;
tcf_tm_dump(&tm, &ipt->tcf_tm);
if (nla_put_64bit(skb, TCA_IPT_TM, sizeof(tm), &tm, TCA_IPT_PAD))
goto nla_put_failure;
spin_unlock_bh(&ipt->tcf_lock);
kfree(t);
return skb->len;
nla_put_failure:
spin_unlock_bh(&ipt->tcf_lock);
nlmsg_trim(skb, b);
kfree(t);
return -1;
}
static struct tc_action_ops act_ipt_ops = {
.kind = "ipt",
.id = TCA_ID_IPT,
.owner = THIS_MODULE,
.act = tcf_ipt_act,
.dump = tcf_ipt_dump,
.cleanup = tcf_ipt_release,
.init = tcf_ipt_init,
.size = sizeof(struct tcf_ipt),
};
static __net_init int ipt_init_net(struct net *net)
{
struct tc_action_net *tn = net_generic(net, act_ipt_ops.net_id);
return tc_action_net_init(net, tn, &act_ipt_ops);
}
static void __net_exit ipt_exit_net(struct list_head *net_list)
{
tc_action_net_exit(net_list, act_ipt_ops.net_id);
}
static struct pernet_operations ipt_net_ops = {
.init = ipt_init_net,
.exit_batch = ipt_exit_net,
.id = &act_ipt_ops.net_id,
.size = sizeof(struct tc_action_net),
};
static struct tc_action_ops act_xt_ops = {
.kind = "xt",
.id = TCA_ID_XT,
.owner = THIS_MODULE,
.act = tcf_ipt_act,
.dump = tcf_ipt_dump,
.cleanup = tcf_ipt_release,
.init = tcf_xt_init,
.size = sizeof(struct tcf_ipt),
};
static __net_init int xt_init_net(struct net *net)
{
struct tc_action_net *tn = net_generic(net, act_xt_ops.net_id);
return tc_action_net_init(net, tn, &act_xt_ops);
}
static void __net_exit xt_exit_net(struct list_head *net_list)
{
tc_action_net_exit(net_list, act_xt_ops.net_id);
}
static struct pernet_operations xt_net_ops = {
.init = xt_init_net,
.exit_batch = xt_exit_net,
.id = &act_xt_ops.net_id,
.size = sizeof(struct tc_action_net),
};
MODULE_AUTHOR("Jamal Hadi Salim(2002-13)");
MODULE_DESCRIPTION("Iptables target actions");
MODULE_LICENSE("GPL");
MODULE_ALIAS("act_xt");
static int __init ipt_init_module(void)
{
int ret1, ret2;
ret1 = tcf_register_action(&act_xt_ops, &xt_net_ops);
if (ret1 < 0)
pr_err("Failed to load xt action\n");
ret2 = tcf_register_action(&act_ipt_ops, &ipt_net_ops);
if (ret2 < 0)
pr_err("Failed to load ipt action\n");
if (ret1 < 0 && ret2 < 0) {
return ret1;
} else
return 0;
}
static void __exit ipt_cleanup_module(void)
{
tcf_unregister_action(&act_ipt_ops, &ipt_net_ops);
tcf_unregister_action(&act_xt_ops, &xt_net_ops);
}
module_init(ipt_init_module);
module_exit(ipt_cleanup_module);