kernel_optimize_test/net/sched/act_connmark.c
Davide Caratti c53075ea5d net/sched: act_connmark: validate the control action inside init()
the following script:

 # tc qdisc add dev crash0 clsact
 # tc filter add dev crash0 egress matchall \
 > action connmark pass index 90
 # tc actions replace action connmark \
 > goto chain 42 index 90 cookie c1a0c1a0
 # tc actions show action connmark

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: connmark zone 0 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 0 P4D 0
 Oops: 0000 [#1] SMP PTI
 CPU: 0 PID: 302 Comm: kworker/0:2 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:ffff9bea406c3ad0 EFLAGS: 00010246
 RAX: 000000002000002a RBX: ffff8c5dfc009f00 RCX: 0000000000000000
 RDX: 0000000000000000 RSI: ffff9bea406c3a80 RDI: ffff8c5dfb9d6ec0
 RBP: ffff9bea406c3b70 R08: ffff8c5dfda222a0 R09: ffffffff90933c3c
 R10: 0000000000000000 R11: 0000000092793f7d R12: ffff8c5df48b3c00
 R13: ffff8c5df48b3c08 R14: 0000000000000001 R15: ffff8c5dfb9d6e40
 FS:  0000000000000000(0000) GS:ffff8c5dfda00000(0000) knlGS:0000000000000000
 CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 CR2: 0000000000000000 CR3: 0000000062e0e006 CR4: 00000000001606f0
 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_connmark nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 veth ip6table_filter ip6_tables iptable_filter binfmt_misc ext4 crct10dif_pclmul mbcache crc32_pclmul jbd2 snd_hda_codec_generic ghash_clmulni_intel snd_hda_intel snd_hda_codec snd_hwdep snd_hda_core snd_seq snd_seq_device snd_pcm aesni_intel snd_timer crypto_simd cryptd snd glue_helper joydev virtio_balloon pcspkr soundcore i2c_piix4 nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs ata_generic pata_acpi qxl drm_kms_helper virtio_net net_failover syscopyarea virtio_blk failover virtio_console sysfillrect sysimgblt fb_sys_fops ttm drm ata_piix crc32c_intel serio_raw libata virtio_pci virtio_ring virtio floppy dm_mirror dm_region_hash dm_log dm_mod
 CR2: 0000000000000000

Validating the control action within tcf_connmark_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>
2019-03-21 13:26:41 -07:00

267 lines
6.7 KiB
C

/*
* net/sched/act_connmark.c netfilter connmark retriever action
* skb mark is over-written
*
* Copyright (c) 2011 Felix Fietkau <nbd@openwrt.org>
*
* 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/module.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/skbuff.h>
#include <linux/rtnetlink.h>
#include <linux/pkt_cls.h>
#include <linux/ip.h>
#include <linux/ipv6.h>
#include <net/netlink.h>
#include <net/pkt_sched.h>
#include <net/act_api.h>
#include <net/pkt_cls.h>
#include <uapi/linux/tc_act/tc_connmark.h>
#include <net/tc_act/tc_connmark.h>
#include <net/netfilter/nf_conntrack.h>
#include <net/netfilter/nf_conntrack_core.h>
#include <net/netfilter/nf_conntrack_zones.h>
static unsigned int connmark_net_id;
static struct tc_action_ops act_connmark_ops;
static int tcf_connmark_act(struct sk_buff *skb, const struct tc_action *a,
struct tcf_result *res)
{
const struct nf_conntrack_tuple_hash *thash;
struct nf_conntrack_tuple tuple;
enum ip_conntrack_info ctinfo;
struct tcf_connmark_info *ca = to_connmark(a);
struct nf_conntrack_zone zone;
struct nf_conn *c;
int proto;
spin_lock(&ca->tcf_lock);
tcf_lastuse_update(&ca->tcf_tm);
bstats_update(&ca->tcf_bstats, skb);
if (skb->protocol == htons(ETH_P_IP)) {
if (skb->len < sizeof(struct iphdr))
goto out;
proto = NFPROTO_IPV4;
} else if (skb->protocol == htons(ETH_P_IPV6)) {
if (skb->len < sizeof(struct ipv6hdr))
goto out;
proto = NFPROTO_IPV6;
} else {
goto out;
}
c = nf_ct_get(skb, &ctinfo);
if (c) {
skb->mark = c->mark;
/* using overlimits stats to count how many packets marked */
ca->tcf_qstats.overlimits++;
goto out;
}
if (!nf_ct_get_tuplepr(skb, skb_network_offset(skb),
proto, ca->net, &tuple))
goto out;
zone.id = ca->zone;
zone.dir = NF_CT_DEFAULT_ZONE_DIR;
thash = nf_conntrack_find_get(ca->net, &zone, &tuple);
if (!thash)
goto out;
c = nf_ct_tuplehash_to_ctrack(thash);
/* using overlimits stats to count how many packets marked */
ca->tcf_qstats.overlimits++;
skb->mark = c->mark;
nf_ct_put(c);
out:
spin_unlock(&ca->tcf_lock);
return ca->tcf_action;
}
static const struct nla_policy connmark_policy[TCA_CONNMARK_MAX + 1] = {
[TCA_CONNMARK_PARMS] = { .len = sizeof(struct tc_connmark) },
};
static int tcf_connmark_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, connmark_net_id);
struct nlattr *tb[TCA_CONNMARK_MAX + 1];
struct tcf_chain *goto_ch = NULL;
struct tcf_connmark_info *ci;
struct tc_connmark *parm;
int ret = 0, err;
if (!nla)
return -EINVAL;
ret = nla_parse_nested(tb, TCA_CONNMARK_MAX, nla, connmark_policy,
NULL);
if (ret < 0)
return ret;
if (!tb[TCA_CONNMARK_PARMS])
return -EINVAL;
parm = nla_data(tb[TCA_CONNMARK_PARMS]);
ret = tcf_idr_check_alloc(tn, &parm->index, a, bind);
if (!ret) {
ret = tcf_idr_create(tn, parm->index, est, a,
&act_connmark_ops, bind, false);
if (ret) {
tcf_idr_cleanup(tn, parm->index);
return ret;
}
ci = to_connmark(*a);
err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch,
extack);
if (err < 0)
goto release_idr;
tcf_action_set_ctrlact(*a, parm->action, goto_ch);
ci->net = net;
ci->zone = parm->zone;
tcf_idr_insert(tn, *a);
ret = ACT_P_CREATED;
} else if (ret > 0) {
ci = to_connmark(*a);
if (bind)
return 0;
if (!ovr) {
tcf_idr_release(*a, bind);
return -EEXIST;
}
err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch,
extack);
if (err < 0)
goto release_idr;
/* replacing action and zone */
spin_lock_bh(&ci->tcf_lock);
goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch);
ci->zone = parm->zone;
spin_unlock_bh(&ci->tcf_lock);
if (goto_ch)
tcf_chain_put_by_act(goto_ch);
ret = 0;
}
return ret;
release_idr:
tcf_idr_release(*a, bind);
return err;
}
static inline int tcf_connmark_dump(struct sk_buff *skb, struct tc_action *a,
int bind, int ref)
{
unsigned char *b = skb_tail_pointer(skb);
struct tcf_connmark_info *ci = to_connmark(a);
struct tc_connmark opt = {
.index = ci->tcf_index,
.refcnt = refcount_read(&ci->tcf_refcnt) - ref,
.bindcnt = atomic_read(&ci->tcf_bindcnt) - bind,
};
struct tcf_t t;
spin_lock_bh(&ci->tcf_lock);
opt.action = ci->tcf_action;
opt.zone = ci->zone;
if (nla_put(skb, TCA_CONNMARK_PARMS, sizeof(opt), &opt))
goto nla_put_failure;
tcf_tm_dump(&t, &ci->tcf_tm);
if (nla_put_64bit(skb, TCA_CONNMARK_TM, sizeof(t), &t,
TCA_CONNMARK_PAD))
goto nla_put_failure;
spin_unlock_bh(&ci->tcf_lock);
return skb->len;
nla_put_failure:
spin_unlock_bh(&ci->tcf_lock);
nlmsg_trim(skb, b);
return -1;
}
static int tcf_connmark_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, connmark_net_id);
return tcf_generic_walker(tn, skb, cb, type, ops, extack);
}
static int tcf_connmark_search(struct net *net, struct tc_action **a, u32 index)
{
struct tc_action_net *tn = net_generic(net, connmark_net_id);
return tcf_idr_search(tn, a, index);
}
static struct tc_action_ops act_connmark_ops = {
.kind = "connmark",
.id = TCA_ID_CONNMARK,
.owner = THIS_MODULE,
.act = tcf_connmark_act,
.dump = tcf_connmark_dump,
.init = tcf_connmark_init,
.walk = tcf_connmark_walker,
.lookup = tcf_connmark_search,
.size = sizeof(struct tcf_connmark_info),
};
static __net_init int connmark_init_net(struct net *net)
{
struct tc_action_net *tn = net_generic(net, connmark_net_id);
return tc_action_net_init(tn, &act_connmark_ops);
}
static void __net_exit connmark_exit_net(struct list_head *net_list)
{
tc_action_net_exit(net_list, connmark_net_id);
}
static struct pernet_operations connmark_net_ops = {
.init = connmark_init_net,
.exit_batch = connmark_exit_net,
.id = &connmark_net_id,
.size = sizeof(struct tc_action_net),
};
static int __init connmark_init_module(void)
{
return tcf_register_action(&act_connmark_ops, &connmark_net_ops);
}
static void __exit connmark_cleanup_module(void)
{
tcf_unregister_action(&act_connmark_ops, &connmark_net_ops);
}
module_init(connmark_init_module);
module_exit(connmark_cleanup_module);
MODULE_AUTHOR("Felix Fietkau <nbd@openwrt.org>");
MODULE_DESCRIPTION("Connection tracking mark restoring");
MODULE_LICENSE("GPL");