![Davide Caratti](/assets/img/avatar_default.png)
the following script: # tc qdisc add dev crash0 clsact # tc filter add dev crash0 egress matchall \ > action nat ingress 1.18.1.1 1.18.2.2 pass index 90 # tc actions replace action nat \ > ingress 1.18.1.1 1.18.2.2 goto chain 42 index 90 cookie c1a0c1a0 # tc actions show action nat had the following output: Error: Failed to init TC action chain. We have an error talking to the kernel total acts 1 action order 0: nat ingress 1.18.1.1/32 1.18.2.2 goto chain 42 index 90 ref 2 bind 1 cookie c1a0c1a0 Then, the first packet transmitted by crash0 made the kernel crash: BUG: unable to handle kernel NULL pointer dereference at 0000000000000000 #PF error: [normal kernel read fault] PGD 800000002d180067 P4D 800000002d180067 PUD 7cb8b067 PMD 0 Oops: 0000 [#1] SMP PTI CPU: 3 PID: 164 Comm: kworker/3:1 Not tainted 5.0.0-rc4.gotochain_crash+ #533 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 Workqueue: ipv6_addrconf addrconf_dad_work RIP: 0010:tcf_action_exec+0xb8/0x100 Code: 00 00 00 20 74 1d 83 f8 03 75 09 49 83 c4 08 4d 39 ec 75 bc 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 49 8b 97 a8 00 00 00 <48> 8b 12 48 89 55 00 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 RSP: 0018:ffffae4500e2fad0 EFLAGS: 00010246 RAX: 000000002000002a RBX: ffff9fa52e28c800 RCX: 0000000001011201 RDX: 0000000000000000 RSI: 0000000000000056 RDI: ffff9fa52ca12800 RBP: ffffae4500e2fb70 R08: 0000000000000022 R09: 000000000000000e R10: 00000000ffffffff R11: 0000000001011201 R12: ffff9fa52cbc9c00 R13: ffff9fa52cbc9c08 R14: 0000000000000001 R15: ffff9fa52ca12780 FS: 0000000000000000(0000) GS:ffff9fa57db80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 0000000073f8c004 CR4: 00000000001606e0 Call Trace: tcf_classify+0x58/0x120 __dev_queue_xmit+0x40a/0x890 ? ndisc_next_option+0x50/0x50 ? ___neigh_create+0x4d5/0x680 ? ip6_finish_output2+0x1b5/0x590 ip6_finish_output2+0x1b5/0x590 ? ip6_output+0x68/0x110 ip6_output+0x68/0x110 ? nf_hook.constprop.28+0x79/0xc0 ndisc_send_skb+0x248/0x2e0 ndisc_send_ns+0xf8/0x200 ? addrconf_dad_work+0x389/0x4b0 addrconf_dad_work+0x389/0x4b0 ? __switch_to_asm+0x34/0x70 ? process_one_work+0x195/0x380 ? addrconf_dad_completed+0x370/0x370 process_one_work+0x195/0x380 worker_thread+0x30/0x390 ? process_one_work+0x380/0x380 kthread+0x113/0x130 ? kthread_park+0x90/0x90 ret_from_fork+0x35/0x40 Modules linked in: act_nat veth ip6table_filter ip6_tables iptable_filter binfmt_misc ext4 crct10dif_pclmul crc32_pclmul ghash_clmulni_intel mbcache jbd2 snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hwdep snd_hda_core snd_seq snd_seq_device snd_pcm aesni_intel crypto_simd cryptd glue_helper snd_timer snd joydev virtio_balloon pcspkr soundcore i2c_piix4 nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs qxl ata_generic pata_acpi drm_kms_helper syscopyarea sysfillrect sysimgblt fb_sys_fops ttm virtio_net virtio_blk net_failover failover virtio_console drm crc32c_intel floppy ata_piix libata virtio_pci virtio_ring virtio serio_raw dm_mirror dm_region_hash dm_log dm_mod CR2: 0000000000000000 Validating the control action within tcf_nat_init() proved to fix the above issue. A TDC selftest is added to verify the correct behavior. Fixes:db50514f9a
("net: sched: add termination action to allow goto chain") Fixes:97763dc0f4
("net_sched: reject unknown tcfa_action values") Signed-off-by: Davide Caratti <dcaratti@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
362 lines
8 KiB
C
362 lines
8 KiB
C
/*
|
|
* Stateless NAT actions
|
|
*
|
|
* Copyright (c) 2007 Herbert Xu <herbert@gondor.apana.org.au>
|
|
*
|
|
* This program is free software; you can redistribute it and/or modify it
|
|
* under the terms of the GNU General Public License as published by the Free
|
|
* Software Foundation; either version 2 of the License, or (at your option)
|
|
* any later version.
|
|
*/
|
|
|
|
#include <linux/errno.h>
|
|
#include <linux/init.h>
|
|
#include <linux/kernel.h>
|
|
#include <linux/module.h>
|
|
#include <linux/netfilter.h>
|
|
#include <linux/rtnetlink.h>
|
|
#include <linux/skbuff.h>
|
|
#include <linux/slab.h>
|
|
#include <linux/spinlock.h>
|
|
#include <linux/string.h>
|
|
#include <linux/tc_act/tc_nat.h>
|
|
#include <net/act_api.h>
|
|
#include <net/pkt_cls.h>
|
|
#include <net/icmp.h>
|
|
#include <net/ip.h>
|
|
#include <net/netlink.h>
|
|
#include <net/tc_act/tc_nat.h>
|
|
#include <net/tcp.h>
|
|
#include <net/udp.h>
|
|
|
|
|
|
static unsigned int nat_net_id;
|
|
static struct tc_action_ops act_nat_ops;
|
|
|
|
static const struct nla_policy nat_policy[TCA_NAT_MAX + 1] = {
|
|
[TCA_NAT_PARMS] = { .len = sizeof(struct tc_nat) },
|
|
};
|
|
|
|
static int tcf_nat_init(struct net *net, struct nlattr *nla, struct nlattr *est,
|
|
struct tc_action **a, int ovr, int bind,
|
|
bool rtnl_held, struct tcf_proto *tp,
|
|
struct netlink_ext_ack *extack)
|
|
{
|
|
struct tc_action_net *tn = net_generic(net, nat_net_id);
|
|
struct nlattr *tb[TCA_NAT_MAX + 1];
|
|
struct tcf_chain *goto_ch = NULL;
|
|
struct tc_nat *parm;
|
|
int ret = 0, err;
|
|
struct tcf_nat *p;
|
|
|
|
if (nla == NULL)
|
|
return -EINVAL;
|
|
|
|
err = nla_parse_nested(tb, TCA_NAT_MAX, nla, nat_policy, NULL);
|
|
if (err < 0)
|
|
return err;
|
|
|
|
if (tb[TCA_NAT_PARMS] == NULL)
|
|
return -EINVAL;
|
|
parm = nla_data(tb[TCA_NAT_PARMS]);
|
|
|
|
err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
|
|
if (!err) {
|
|
ret = tcf_idr_create(tn, parm->index, est, a,
|
|
&act_nat_ops, bind, false);
|
|
if (ret) {
|
|
tcf_idr_cleanup(tn, parm->index);
|
|
return ret;
|
|
}
|
|
ret = ACT_P_CREATED;
|
|
} else if (err > 0) {
|
|
if (bind)
|
|
return 0;
|
|
if (!ovr) {
|
|
tcf_idr_release(*a, bind);
|
|
return -EEXIST;
|
|
}
|
|
} else {
|
|
return err;
|
|
}
|
|
err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack);
|
|
if (err < 0)
|
|
goto release_idr;
|
|
p = to_tcf_nat(*a);
|
|
|
|
spin_lock_bh(&p->tcf_lock);
|
|
p->old_addr = parm->old_addr;
|
|
p->new_addr = parm->new_addr;
|
|
p->mask = parm->mask;
|
|
p->flags = parm->flags;
|
|
|
|
goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch);
|
|
spin_unlock_bh(&p->tcf_lock);
|
|
if (goto_ch)
|
|
tcf_chain_put_by_act(goto_ch);
|
|
|
|
if (ret == ACT_P_CREATED)
|
|
tcf_idr_insert(tn, *a);
|
|
|
|
return ret;
|
|
release_idr:
|
|
tcf_idr_release(*a, bind);
|
|
return err;
|
|
}
|
|
|
|
static int tcf_nat_act(struct sk_buff *skb, const struct tc_action *a,
|
|
struct tcf_result *res)
|
|
{
|
|
struct tcf_nat *p = to_tcf_nat(a);
|
|
struct iphdr *iph;
|
|
__be32 old_addr;
|
|
__be32 new_addr;
|
|
__be32 mask;
|
|
__be32 addr;
|
|
int egress;
|
|
int action;
|
|
int ihl;
|
|
int noff;
|
|
|
|
spin_lock(&p->tcf_lock);
|
|
|
|
tcf_lastuse_update(&p->tcf_tm);
|
|
old_addr = p->old_addr;
|
|
new_addr = p->new_addr;
|
|
mask = p->mask;
|
|
egress = p->flags & TCA_NAT_FLAG_EGRESS;
|
|
action = p->tcf_action;
|
|
|
|
bstats_update(&p->tcf_bstats, skb);
|
|
|
|
spin_unlock(&p->tcf_lock);
|
|
|
|
if (unlikely(action == TC_ACT_SHOT))
|
|
goto drop;
|
|
|
|
noff = skb_network_offset(skb);
|
|
if (!pskb_may_pull(skb, sizeof(*iph) + noff))
|
|
goto drop;
|
|
|
|
iph = ip_hdr(skb);
|
|
|
|
if (egress)
|
|
addr = iph->saddr;
|
|
else
|
|
addr = iph->daddr;
|
|
|
|
if (!((old_addr ^ addr) & mask)) {
|
|
if (skb_try_make_writable(skb, sizeof(*iph) + noff))
|
|
goto drop;
|
|
|
|
new_addr &= mask;
|
|
new_addr |= addr & ~mask;
|
|
|
|
/* Rewrite IP header */
|
|
iph = ip_hdr(skb);
|
|
if (egress)
|
|
iph->saddr = new_addr;
|
|
else
|
|
iph->daddr = new_addr;
|
|
|
|
csum_replace4(&iph->check, addr, new_addr);
|
|
} else if ((iph->frag_off & htons(IP_OFFSET)) ||
|
|
iph->protocol != IPPROTO_ICMP) {
|
|
goto out;
|
|
}
|
|
|
|
ihl = iph->ihl * 4;
|
|
|
|
/* It would be nice to share code with stateful NAT. */
|
|
switch (iph->frag_off & htons(IP_OFFSET) ? 0 : iph->protocol) {
|
|
case IPPROTO_TCP:
|
|
{
|
|
struct tcphdr *tcph;
|
|
|
|
if (!pskb_may_pull(skb, ihl + sizeof(*tcph) + noff) ||
|
|
skb_try_make_writable(skb, ihl + sizeof(*tcph) + noff))
|
|
goto drop;
|
|
|
|
tcph = (void *)(skb_network_header(skb) + ihl);
|
|
inet_proto_csum_replace4(&tcph->check, skb, addr, new_addr,
|
|
true);
|
|
break;
|
|
}
|
|
case IPPROTO_UDP:
|
|
{
|
|
struct udphdr *udph;
|
|
|
|
if (!pskb_may_pull(skb, ihl + sizeof(*udph) + noff) ||
|
|
skb_try_make_writable(skb, ihl + sizeof(*udph) + noff))
|
|
goto drop;
|
|
|
|
udph = (void *)(skb_network_header(skb) + ihl);
|
|
if (udph->check || skb->ip_summed == CHECKSUM_PARTIAL) {
|
|
inet_proto_csum_replace4(&udph->check, skb, addr,
|
|
new_addr, true);
|
|
if (!udph->check)
|
|
udph->check = CSUM_MANGLED_0;
|
|
}
|
|
break;
|
|
}
|
|
case IPPROTO_ICMP:
|
|
{
|
|
struct icmphdr *icmph;
|
|
|
|
if (!pskb_may_pull(skb, ihl + sizeof(*icmph) + noff))
|
|
goto drop;
|
|
|
|
icmph = (void *)(skb_network_header(skb) + ihl);
|
|
|
|
if ((icmph->type != ICMP_DEST_UNREACH) &&
|
|
(icmph->type != ICMP_TIME_EXCEEDED) &&
|
|
(icmph->type != ICMP_PARAMETERPROB))
|
|
break;
|
|
|
|
if (!pskb_may_pull(skb, ihl + sizeof(*icmph) + sizeof(*iph) +
|
|
noff))
|
|
goto drop;
|
|
|
|
icmph = (void *)(skb_network_header(skb) + ihl);
|
|
iph = (void *)(icmph + 1);
|
|
if (egress)
|
|
addr = iph->daddr;
|
|
else
|
|
addr = iph->saddr;
|
|
|
|
if ((old_addr ^ addr) & mask)
|
|
break;
|
|
|
|
if (skb_try_make_writable(skb, ihl + sizeof(*icmph) +
|
|
sizeof(*iph) + noff))
|
|
goto drop;
|
|
|
|
icmph = (void *)(skb_network_header(skb) + ihl);
|
|
iph = (void *)(icmph + 1);
|
|
|
|
new_addr &= mask;
|
|
new_addr |= addr & ~mask;
|
|
|
|
/* XXX Fix up the inner checksums. */
|
|
if (egress)
|
|
iph->daddr = new_addr;
|
|
else
|
|
iph->saddr = new_addr;
|
|
|
|
inet_proto_csum_replace4(&icmph->checksum, skb, addr, new_addr,
|
|
false);
|
|
break;
|
|
}
|
|
default:
|
|
break;
|
|
}
|
|
|
|
out:
|
|
return action;
|
|
|
|
drop:
|
|
spin_lock(&p->tcf_lock);
|
|
p->tcf_qstats.drops++;
|
|
spin_unlock(&p->tcf_lock);
|
|
return TC_ACT_SHOT;
|
|
}
|
|
|
|
static int tcf_nat_dump(struct sk_buff *skb, struct tc_action *a,
|
|
int bind, int ref)
|
|
{
|
|
unsigned char *b = skb_tail_pointer(skb);
|
|
struct tcf_nat *p = to_tcf_nat(a);
|
|
struct tc_nat opt = {
|
|
.index = p->tcf_index,
|
|
.refcnt = refcount_read(&p->tcf_refcnt) - ref,
|
|
.bindcnt = atomic_read(&p->tcf_bindcnt) - bind,
|
|
};
|
|
struct tcf_t t;
|
|
|
|
spin_lock_bh(&p->tcf_lock);
|
|
opt.old_addr = p->old_addr;
|
|
opt.new_addr = p->new_addr;
|
|
opt.mask = p->mask;
|
|
opt.flags = p->flags;
|
|
opt.action = p->tcf_action;
|
|
|
|
if (nla_put(skb, TCA_NAT_PARMS, sizeof(opt), &opt))
|
|
goto nla_put_failure;
|
|
|
|
tcf_tm_dump(&t, &p->tcf_tm);
|
|
if (nla_put_64bit(skb, TCA_NAT_TM, sizeof(t), &t, TCA_NAT_PAD))
|
|
goto nla_put_failure;
|
|
spin_unlock_bh(&p->tcf_lock);
|
|
|
|
return skb->len;
|
|
|
|
nla_put_failure:
|
|
spin_unlock_bh(&p->tcf_lock);
|
|
nlmsg_trim(skb, b);
|
|
return -1;
|
|
}
|
|
|
|
static int tcf_nat_walker(struct net *net, struct sk_buff *skb,
|
|
struct netlink_callback *cb, int type,
|
|
const struct tc_action_ops *ops,
|
|
struct netlink_ext_ack *extack)
|
|
{
|
|
struct tc_action_net *tn = net_generic(net, nat_net_id);
|
|
|
|
return tcf_generic_walker(tn, skb, cb, type, ops, extack);
|
|
}
|
|
|
|
static int tcf_nat_search(struct net *net, struct tc_action **a, u32 index)
|
|
{
|
|
struct tc_action_net *tn = net_generic(net, nat_net_id);
|
|
|
|
return tcf_idr_search(tn, a, index);
|
|
}
|
|
|
|
static struct tc_action_ops act_nat_ops = {
|
|
.kind = "nat",
|
|
.id = TCA_ID_NAT,
|
|
.owner = THIS_MODULE,
|
|
.act = tcf_nat_act,
|
|
.dump = tcf_nat_dump,
|
|
.init = tcf_nat_init,
|
|
.walk = tcf_nat_walker,
|
|
.lookup = tcf_nat_search,
|
|
.size = sizeof(struct tcf_nat),
|
|
};
|
|
|
|
static __net_init int nat_init_net(struct net *net)
|
|
{
|
|
struct tc_action_net *tn = net_generic(net, nat_net_id);
|
|
|
|
return tc_action_net_init(tn, &act_nat_ops);
|
|
}
|
|
|
|
static void __net_exit nat_exit_net(struct list_head *net_list)
|
|
{
|
|
tc_action_net_exit(net_list, nat_net_id);
|
|
}
|
|
|
|
static struct pernet_operations nat_net_ops = {
|
|
.init = nat_init_net,
|
|
.exit_batch = nat_exit_net,
|
|
.id = &nat_net_id,
|
|
.size = sizeof(struct tc_action_net),
|
|
};
|
|
|
|
MODULE_DESCRIPTION("Stateless NAT actions");
|
|
MODULE_LICENSE("GPL");
|
|
|
|
static int __init nat_init_module(void)
|
|
{
|
|
return tcf_register_action(&act_nat_ops, &nat_net_ops);
|
|
}
|
|
|
|
static void __exit nat_cleanup_module(void)
|
|
{
|
|
tcf_unregister_action(&act_nat_ops, &nat_net_ops);
|
|
}
|
|
|
|
module_init(nat_init_module);
|
|
module_exit(nat_cleanup_module);
|