2
0
mirror of https://github.com/edk2-porting/linux-next.git synced 2024-12-25 13:43:55 +08:00
linux-next/net/sched/act_mirred.c
Davide Caratti ff9721d32b net/sched: act_mirred: validate the control action inside init()
the following script:

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

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: mirred (Ingress Mirror to device lo) goto chain 42
         index 90 ref 2 bind 1
         cookie c1a0c1a0

Then, the first packet transmitted by crash0 made the kernel crash:

 Mirror/redirect action on
 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: 3 PID: 47 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:ffffa772404b7ad0 EFLAGS: 00010246
 RAX: 000000002000002a RBX: ffff9c5afc3f4300 RCX: 0000000000000000
 RDX: 0000000000000000 RSI: ffff9c5afdba9380 RDI: 0000000000029380
 RBP: ffffa772404b7b70 R08: ffff9c5af7010028 R09: ffff9c5af7010029
 R10: 0000000000000000 R11: ffff9c5af94c6a38 R12: ffff9c5af7953000
 R13: ffff9c5af7953008 R14: 0000000000000001 R15: ffff9c5af7953d00
 FS:  0000000000000000(0000) GS:ffff9c5afdb80000(0000) knlGS:0000000000000000
 CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 CR2: 0000000000000000 CR3: 000000007c514004 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_mirred veth ip6table_filter ip6_tables iptable_filter binfmt_misc ext4 crct10dif_pclmul snd_hda_codec_generic crc32_pclmul snd_hda_intel snd_hda_codec mbcache ghash_clmulni_intel jbd2 snd_hwdep snd_hda_core snd_seq snd_seq_device snd_pcm aesni_intel snd_timer snd crypto_simd cryptd glue_helper soundcore virtio_balloon joydev pcspkr i2c_piix4 nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs ata_generic pata_acpi qxl drm_kms_helper syscopyarea sysfillrect sysimgblt fb_sys_fops virtio_net ttm virtio_blk net_failover virtio_console failover drm ata_piix crc32c_intel virtio_pci serio_raw libata virtio_ring virtio floppy dm_mirror dm_region_hash dm_log dm_mod
 CR2: 0000000000000000

Validating the control action within tcf_mirred_init() proved to fix the
above issue. For the same reason, postpone the assignment of tcfa_action
and tcfm_eaction to avoid partial reconfiguration of a mirred rule when
it's replaced by another one that mirrors to a device that does not
exist. 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

472 lines
12 KiB
C

/*
* net/sched/act_mirred.c packet mirroring and redirect actions
*
* 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.
*
* Authors: Jamal Hadi Salim (2002-4)
*
* TODO: Add ingress support (and socket redirect support)
*
*/
#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/gfp.h>
#include <linux/if_arp.h>
#include <net/net_namespace.h>
#include <net/netlink.h>
#include <net/pkt_sched.h>
#include <net/pkt_cls.h>
#include <linux/tc_act/tc_mirred.h>
#include <net/tc_act/tc_mirred.h>
static LIST_HEAD(mirred_list);
static DEFINE_SPINLOCK(mirred_list_lock);
static bool tcf_mirred_is_act_redirect(int action)
{
return action == TCA_EGRESS_REDIR || action == TCA_INGRESS_REDIR;
}
static bool tcf_mirred_act_wants_ingress(int action)
{
switch (action) {
case TCA_EGRESS_REDIR:
case TCA_EGRESS_MIRROR:
return false;
case TCA_INGRESS_REDIR:
case TCA_INGRESS_MIRROR:
return true;
default:
BUG();
}
}
static bool tcf_mirred_can_reinsert(int action)
{
switch (action) {
case TC_ACT_SHOT:
case TC_ACT_STOLEN:
case TC_ACT_QUEUED:
case TC_ACT_TRAP:
return true;
}
return false;
}
static struct net_device *tcf_mirred_dev_dereference(struct tcf_mirred *m)
{
return rcu_dereference_protected(m->tcfm_dev,
lockdep_is_held(&m->tcf_lock));
}
static void tcf_mirred_release(struct tc_action *a)
{
struct tcf_mirred *m = to_mirred(a);
struct net_device *dev;
spin_lock(&mirred_list_lock);
list_del(&m->tcfm_list);
spin_unlock(&mirred_list_lock);
/* last reference to action, no need to lock */
dev = rcu_dereference_protected(m->tcfm_dev, 1);
if (dev)
dev_put(dev);
}
static const struct nla_policy mirred_policy[TCA_MIRRED_MAX + 1] = {
[TCA_MIRRED_PARMS] = { .len = sizeof(struct tc_mirred) },
};
static unsigned int mirred_net_id;
static struct tc_action_ops act_mirred_ops;
static int tcf_mirred_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, mirred_net_id);
struct nlattr *tb[TCA_MIRRED_MAX + 1];
struct tcf_chain *goto_ch = NULL;
bool mac_header_xmit = false;
struct tc_mirred *parm;
struct tcf_mirred *m;
struct net_device *dev;
bool exists = false;
int ret, err;
if (!nla) {
NL_SET_ERR_MSG_MOD(extack, "Mirred requires attributes to be passed");
return -EINVAL;
}
ret = nla_parse_nested(tb, TCA_MIRRED_MAX, nla, mirred_policy, extack);
if (ret < 0)
return ret;
if (!tb[TCA_MIRRED_PARMS]) {
NL_SET_ERR_MSG_MOD(extack, "Missing required mirred parameters");
return -EINVAL;
}
parm = nla_data(tb[TCA_MIRRED_PARMS]);
err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
if (err < 0)
return err;
exists = err;
if (exists && bind)
return 0;
switch (parm->eaction) {
case TCA_EGRESS_MIRROR:
case TCA_EGRESS_REDIR:
case TCA_INGRESS_REDIR:
case TCA_INGRESS_MIRROR:
break;
default:
if (exists)
tcf_idr_release(*a, bind);
else
tcf_idr_cleanup(tn, parm->index);
NL_SET_ERR_MSG_MOD(extack, "Unknown mirred option");
return -EINVAL;
}
if (!exists) {
if (!parm->ifindex) {
tcf_idr_cleanup(tn, parm->index);
NL_SET_ERR_MSG_MOD(extack, "Specified device does not exist");
return -EINVAL;
}
ret = tcf_idr_create(tn, parm->index, est, a,
&act_mirred_ops, bind, true);
if (ret) {
tcf_idr_cleanup(tn, parm->index);
return ret;
}
ret = ACT_P_CREATED;
} else 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;
m = to_mirred(*a);
spin_lock_bh(&m->tcf_lock);
if (parm->ifindex) {
dev = dev_get_by_index(net, parm->ifindex);
if (!dev) {
spin_unlock_bh(&m->tcf_lock);
err = -ENODEV;
goto put_chain;
}
mac_header_xmit = dev_is_mac_header_xmit(dev);
rcu_swap_protected(m->tcfm_dev, dev,
lockdep_is_held(&m->tcf_lock));
if (dev)
dev_put(dev);
m->tcfm_mac_header_xmit = mac_header_xmit;
}
goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch);
m->tcfm_eaction = parm->eaction;
spin_unlock_bh(&m->tcf_lock);
if (goto_ch)
tcf_chain_put_by_act(goto_ch);
if (ret == ACT_P_CREATED) {
spin_lock(&mirred_list_lock);
list_add(&m->tcfm_list, &mirred_list);
spin_unlock(&mirred_list_lock);
tcf_idr_insert(tn, *a);
}
return ret;
put_chain:
if (goto_ch)
tcf_chain_put_by_act(goto_ch);
release_idr:
tcf_idr_release(*a, bind);
return err;
}
static int tcf_mirred_act(struct sk_buff *skb, const struct tc_action *a,
struct tcf_result *res)
{
struct tcf_mirred *m = to_mirred(a);
struct sk_buff *skb2 = skb;
bool m_mac_header_xmit;
struct net_device *dev;
int retval, err = 0;
bool use_reinsert;
bool want_ingress;
bool is_redirect;
int m_eaction;
int mac_len;
tcf_lastuse_update(&m->tcf_tm);
bstats_cpu_update(this_cpu_ptr(m->common.cpu_bstats), skb);
m_mac_header_xmit = READ_ONCE(m->tcfm_mac_header_xmit);
m_eaction = READ_ONCE(m->tcfm_eaction);
retval = READ_ONCE(m->tcf_action);
dev = rcu_dereference_bh(m->tcfm_dev);
if (unlikely(!dev)) {
pr_notice_once("tc mirred: target device is gone\n");
goto out;
}
if (unlikely(!(dev->flags & IFF_UP))) {
net_notice_ratelimited("tc mirred to Houston: device %s is down\n",
dev->name);
goto out;
}
/* we could easily avoid the clone only if called by ingress and clsact;
* since we can't easily detect the clsact caller, skip clone only for
* ingress - that covers the TC S/W datapath.
*/
is_redirect = tcf_mirred_is_act_redirect(m_eaction);
use_reinsert = skb_at_tc_ingress(skb) && is_redirect &&
tcf_mirred_can_reinsert(retval);
if (!use_reinsert) {
skb2 = skb_clone(skb, GFP_ATOMIC);
if (!skb2)
goto out;
}
/* If action's target direction differs than filter's direction,
* and devices expect a mac header on xmit, then mac push/pull is
* needed.
*/
want_ingress = tcf_mirred_act_wants_ingress(m_eaction);
if (skb_at_tc_ingress(skb) != want_ingress && m_mac_header_xmit) {
if (!skb_at_tc_ingress(skb)) {
/* caught at egress, act ingress: pull mac */
mac_len = skb_network_header(skb) - skb_mac_header(skb);
skb_pull_rcsum(skb2, mac_len);
} else {
/* caught at ingress, act egress: push mac */
skb_push_rcsum(skb2, skb->mac_len);
}
}
skb2->skb_iif = skb->dev->ifindex;
skb2->dev = dev;
/* mirror is always swallowed */
if (is_redirect) {
skb2->tc_redirected = 1;
skb2->tc_from_ingress = skb2->tc_at_ingress;
if (skb2->tc_from_ingress)
skb2->tstamp = 0;
/* let's the caller reinsert the packet, if possible */
if (use_reinsert) {
res->ingress = want_ingress;
res->qstats = this_cpu_ptr(m->common.cpu_qstats);
return TC_ACT_REINSERT;
}
}
if (!want_ingress)
err = dev_queue_xmit(skb2);
else
err = netif_receive_skb(skb2);
if (err) {
out:
qstats_overlimit_inc(this_cpu_ptr(m->common.cpu_qstats));
if (tcf_mirred_is_act_redirect(m_eaction))
retval = TC_ACT_SHOT;
}
return retval;
}
static void tcf_stats_update(struct tc_action *a, u64 bytes, u32 packets,
u64 lastuse, bool hw)
{
struct tcf_mirred *m = to_mirred(a);
struct tcf_t *tm = &m->tcf_tm;
_bstats_cpu_update(this_cpu_ptr(a->cpu_bstats), bytes, packets);
if (hw)
_bstats_cpu_update(this_cpu_ptr(a->cpu_bstats_hw),
bytes, packets);
tm->lastuse = max_t(u64, tm->lastuse, lastuse);
}
static int tcf_mirred_dump(struct sk_buff *skb, struct tc_action *a, int bind,
int ref)
{
unsigned char *b = skb_tail_pointer(skb);
struct tcf_mirred *m = to_mirred(a);
struct tc_mirred opt = {
.index = m->tcf_index,
.refcnt = refcount_read(&m->tcf_refcnt) - ref,
.bindcnt = atomic_read(&m->tcf_bindcnt) - bind,
};
struct net_device *dev;
struct tcf_t t;
spin_lock_bh(&m->tcf_lock);
opt.action = m->tcf_action;
opt.eaction = m->tcfm_eaction;
dev = tcf_mirred_dev_dereference(m);
if (dev)
opt.ifindex = dev->ifindex;
if (nla_put(skb, TCA_MIRRED_PARMS, sizeof(opt), &opt))
goto nla_put_failure;
tcf_tm_dump(&t, &m->tcf_tm);
if (nla_put_64bit(skb, TCA_MIRRED_TM, sizeof(t), &t, TCA_MIRRED_PAD))
goto nla_put_failure;
spin_unlock_bh(&m->tcf_lock);
return skb->len;
nla_put_failure:
spin_unlock_bh(&m->tcf_lock);
nlmsg_trim(skb, b);
return -1;
}
static int tcf_mirred_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, mirred_net_id);
return tcf_generic_walker(tn, skb, cb, type, ops, extack);
}
static int tcf_mirred_search(struct net *net, struct tc_action **a, u32 index)
{
struct tc_action_net *tn = net_generic(net, mirred_net_id);
return tcf_idr_search(tn, a, index);
}
static int mirred_device_event(struct notifier_block *unused,
unsigned long event, void *ptr)
{
struct net_device *dev = netdev_notifier_info_to_dev(ptr);
struct tcf_mirred *m;
ASSERT_RTNL();
if (event == NETDEV_UNREGISTER) {
spin_lock(&mirred_list_lock);
list_for_each_entry(m, &mirred_list, tcfm_list) {
spin_lock_bh(&m->tcf_lock);
if (tcf_mirred_dev_dereference(m) == dev) {
dev_put(dev);
/* Note : no rcu grace period necessary, as
* net_device are already rcu protected.
*/
RCU_INIT_POINTER(m->tcfm_dev, NULL);
}
spin_unlock_bh(&m->tcf_lock);
}
spin_unlock(&mirred_list_lock);
}
return NOTIFY_DONE;
}
static struct notifier_block mirred_device_notifier = {
.notifier_call = mirred_device_event,
};
static struct net_device *tcf_mirred_get_dev(const struct tc_action *a)
{
struct tcf_mirred *m = to_mirred(a);
struct net_device *dev;
rcu_read_lock();
dev = rcu_dereference(m->tcfm_dev);
if (dev)
dev_hold(dev);
rcu_read_unlock();
return dev;
}
static void tcf_mirred_put_dev(struct net_device *dev)
{
dev_put(dev);
}
static struct tc_action_ops act_mirred_ops = {
.kind = "mirred",
.id = TCA_ID_MIRRED,
.owner = THIS_MODULE,
.act = tcf_mirred_act,
.stats_update = tcf_stats_update,
.dump = tcf_mirred_dump,
.cleanup = tcf_mirred_release,
.init = tcf_mirred_init,
.walk = tcf_mirred_walker,
.lookup = tcf_mirred_search,
.size = sizeof(struct tcf_mirred),
.get_dev = tcf_mirred_get_dev,
.put_dev = tcf_mirred_put_dev,
};
static __net_init int mirred_init_net(struct net *net)
{
struct tc_action_net *tn = net_generic(net, mirred_net_id);
return tc_action_net_init(tn, &act_mirred_ops);
}
static void __net_exit mirred_exit_net(struct list_head *net_list)
{
tc_action_net_exit(net_list, mirred_net_id);
}
static struct pernet_operations mirred_net_ops = {
.init = mirred_init_net,
.exit_batch = mirred_exit_net,
.id = &mirred_net_id,
.size = sizeof(struct tc_action_net),
};
MODULE_AUTHOR("Jamal Hadi Salim(2002)");
MODULE_DESCRIPTION("Device Mirror/redirect actions");
MODULE_LICENSE("GPL");
static int __init mirred_init_module(void)
{
int err = register_netdevice_notifier(&mirred_device_notifier);
if (err)
return err;
pr_info("Mirror/redirect action on\n");
return tcf_register_action(&act_mirred_ops, &mirred_net_ops);
}
static void __exit mirred_cleanup_module(void)
{
tcf_unregister_action(&act_mirred_ops, &mirred_net_ops);
unregister_netdevice_notifier(&mirred_device_notifier);
}
module_init(mirred_init_module);
module_exit(mirred_cleanup_module);