kernel_optimize_test/net/sched/act_skbmod.c
Davide Caratti 7c3d825d12 net/sched: act_skbmod: validate the control action inside init()
the following script:

 # tc qdisc add dev crash0 clsact
 # tc filter add dev crash0 egress matchall \
 > action skbmod set smac 00:c1:a0:c1:a0:00 pass index 90
 # tc actions replace action skbmod \
 > set smac 00:c1:a0:c1:a0:00 goto chain 42 index 90 cookie c1a0c1a0
 # tc actions show action skbmod

had the following output:

 src MAC address <00:c1:a0:c1:a0:00>
 src MAC address <00:c1:a0:c1:a0:00>
 Error: Failed to init TC action chain.
 We have an error talking to the kernel
 total acts 1

         action order 0: skbmod goto chain 42 set smac 00:c1:a0:c1:a0:00
          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 800000002d5c7067 P4D 800000002d5c7067 PUD 77e16067 PMD 0
 Oops: 0000 [#1] SMP PTI
 CPU: 3 PID: 0 Comm: swapper/3 Not tainted 5.0.0-rc4.gotochain_crash+ #536
 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011
 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:ffff8987ffd83be0 EFLAGS: 00010246
 RAX: 000000002000002a RBX: ffff8987aeb68800 RCX: ffff8987fa263640
 RDX: 0000000000000000 RSI: ffff8987f51c8802 RDI: 00000000000000a0
 RBP: ffff8987ffd83c80 R08: ffff8987f939bac8 R09: 0000000000000000
 R10: 0000000000000000 R11: 0000000000000000 R12: ffff8987f5c77d00
 R13: ffff8987f5c77d08 R14: 0000000000000001 R15: ffff8987f0c29f00
 FS:  0000000000000000(0000) GS:ffff8987ffd80000(0000) knlGS:0000000000000000
 CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 CR2: 0000000000000000 CR3: 000000007832c004 CR4: 00000000001606e0
 Call Trace:
  <IRQ>
  tcf_classify+0x58/0x120
  __dev_queue_xmit+0x40a/0x890
  ? ip6_finish_output2+0x369/0x590
  ip6_finish_output2+0x369/0x590
  ? ip6_output+0x68/0x110
  ip6_output+0x68/0x110
  ? nf_hook.constprop.35+0x79/0xc0
  mld_sendpack+0x16f/0x220
  mld_ifc_timer_expire+0x195/0x2c0
  ? igmp6_timer_handler+0x70/0x70
  call_timer_fn+0x2b/0x130
  run_timer_softirq+0x3e8/0x440
  ? tick_sched_timer+0x37/0x70
  __do_softirq+0xe3/0x2f5
  irq_exit+0xf0/0x100
  smp_apic_timer_interrupt+0x6c/0x130
  apic_timer_interrupt+0xf/0x20
  </IRQ>
 RIP: 0010:native_safe_halt+0x2/0x10
 Code: 56 ff ff ff 7f f3 c3 65 48 8b 04 25 00 5c 01 00 f0 80 48 02 20 48 8b 00 a8 08 74 8b eb c1 90 90 90 90 90 90 90 90 90 90 fb f4 <c3> 0f 1f 00 66 2e 0f 1f 84 00 00 00 00 00 f4 c3 90 90 90 90 90 90
 RSP: 0018:ffffa2a1c038feb8 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff13
 RAX: ffffffffa94184f0 RBX: 0000000000000003 RCX: 0000000000000001
 RDX: 0000000000000001 RSI: 0000000000000087 RDI: 0000000000000003
 RBP: 0000000000000003 R08: 001123cfc2ba71ac R09: 0000000000000000
 R10: 0000000000000000 R11: 00000000000f4240 R12: 0000000000000000
 R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000
  ? __sched_text_end+0x1/0x1
  default_idle+0x1c/0x140
  do_idle+0x1c4/0x280
  cpu_startup_entry+0x19/0x20
  start_secondary+0x1a7/0x200
  secondary_startup_64+0xa4/0xb0
 Modules linked in: act_skbmod 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 aesni_intel crypto_simd cryptd glue_helper snd_pcm joydev pcspkr virtio_balloon snd_timer snd i2c_piix4 soundcore nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs ata_generic pata_acpi qxl drm_kms_helper syscopyarea sysfillrect virtio_net sysimgblt fb_sys_fops net_failover virtio_console ttm virtio_blk failover drm crc32c_intel serio_raw ata_piix virtio_pci libata virtio_ring virtio floppy dm_mirror dm_region_hash dm_log dm_mod
 CR2: 0000000000000000

Validating the control action within tcf_skbmod_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 13:26:42 -07:00

323 lines
8.1 KiB
C

/*
* net/sched/act_skbmod.c skb data modifier
*
* Copyright (c) 2016 Jamal Hadi Salim <jhs@mojatatu.com>
*
* 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 <net/netlink.h>
#include <net/pkt_sched.h>
#include <net/pkt_cls.h>
#include <linux/tc_act/tc_skbmod.h>
#include <net/tc_act/tc_skbmod.h>
static unsigned int skbmod_net_id;
static struct tc_action_ops act_skbmod_ops;
#define MAX_EDIT_LEN ETH_HLEN
static int tcf_skbmod_act(struct sk_buff *skb, const struct tc_action *a,
struct tcf_result *res)
{
struct tcf_skbmod *d = to_skbmod(a);
int action;
struct tcf_skbmod_params *p;
u64 flags;
int err;
tcf_lastuse_update(&d->tcf_tm);
bstats_cpu_update(this_cpu_ptr(d->common.cpu_bstats), skb);
/* XXX: if you are going to edit more fields beyond ethernet header
* (example when you add IP header replacement or vlan swap)
* then MAX_EDIT_LEN needs to change appropriately
*/
err = skb_ensure_writable(skb, MAX_EDIT_LEN);
if (unlikely(err)) /* best policy is to drop on the floor */
goto drop;
action = READ_ONCE(d->tcf_action);
if (unlikely(action == TC_ACT_SHOT))
goto drop;
p = rcu_dereference_bh(d->skbmod_p);
flags = p->flags;
if (flags & SKBMOD_F_DMAC)
ether_addr_copy(eth_hdr(skb)->h_dest, p->eth_dst);
if (flags & SKBMOD_F_SMAC)
ether_addr_copy(eth_hdr(skb)->h_source, p->eth_src);
if (flags & SKBMOD_F_ETYPE)
eth_hdr(skb)->h_proto = p->eth_type;
if (flags & SKBMOD_F_SWAPMAC) {
u16 tmpaddr[ETH_ALEN / 2]; /* ether_addr_copy() requirement */
/*XXX: I am sure we can come up with more efficient swapping*/
ether_addr_copy((u8 *)tmpaddr, eth_hdr(skb)->h_dest);
ether_addr_copy(eth_hdr(skb)->h_dest, eth_hdr(skb)->h_source);
ether_addr_copy(eth_hdr(skb)->h_source, (u8 *)tmpaddr);
}
return action;
drop:
qstats_overlimit_inc(this_cpu_ptr(d->common.cpu_qstats));
return TC_ACT_SHOT;
}
static const struct nla_policy skbmod_policy[TCA_SKBMOD_MAX + 1] = {
[TCA_SKBMOD_PARMS] = { .len = sizeof(struct tc_skbmod) },
[TCA_SKBMOD_DMAC] = { .len = ETH_ALEN },
[TCA_SKBMOD_SMAC] = { .len = ETH_ALEN },
[TCA_SKBMOD_ETYPE] = { .type = NLA_U16 },
};
static int tcf_skbmod_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, skbmod_net_id);
struct nlattr *tb[TCA_SKBMOD_MAX + 1];
struct tcf_skbmod_params *p, *p_old;
struct tcf_chain *goto_ch = NULL;
struct tc_skbmod *parm;
struct tcf_skbmod *d;
bool exists = false;
u8 *daddr = NULL;
u8 *saddr = NULL;
u16 eth_type = 0;
u32 lflags = 0;
int ret = 0, err;
if (!nla)
return -EINVAL;
err = nla_parse_nested(tb, TCA_SKBMOD_MAX, nla, skbmod_policy, NULL);
if (err < 0)
return err;
if (!tb[TCA_SKBMOD_PARMS])
return -EINVAL;
if (tb[TCA_SKBMOD_DMAC]) {
daddr = nla_data(tb[TCA_SKBMOD_DMAC]);
lflags |= SKBMOD_F_DMAC;
}
if (tb[TCA_SKBMOD_SMAC]) {
saddr = nla_data(tb[TCA_SKBMOD_SMAC]);
lflags |= SKBMOD_F_SMAC;
}
if (tb[TCA_SKBMOD_ETYPE]) {
eth_type = nla_get_u16(tb[TCA_SKBMOD_ETYPE]);
lflags |= SKBMOD_F_ETYPE;
}
parm = nla_data(tb[TCA_SKBMOD_PARMS]);
if (parm->flags & SKBMOD_F_SWAPMAC)
lflags = SKBMOD_F_SWAPMAC;
err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
if (err < 0)
return err;
exists = err;
if (exists && bind)
return 0;
if (!lflags) {
if (exists)
tcf_idr_release(*a, bind);
else
tcf_idr_cleanup(tn, parm->index);
return -EINVAL;
}
if (!exists) {
ret = tcf_idr_create(tn, parm->index, est, a,
&act_skbmod_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;
d = to_skbmod(*a);
p = kzalloc(sizeof(struct tcf_skbmod_params), GFP_KERNEL);
if (unlikely(!p)) {
err = -ENOMEM;
goto put_chain;
}
p->flags = lflags;
if (ovr)
spin_lock_bh(&d->tcf_lock);
/* Protected by tcf_lock if overwriting existing action. */
goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch);
p_old = rcu_dereference_protected(d->skbmod_p, 1);
if (lflags & SKBMOD_F_DMAC)
ether_addr_copy(p->eth_dst, daddr);
if (lflags & SKBMOD_F_SMAC)
ether_addr_copy(p->eth_src, saddr);
if (lflags & SKBMOD_F_ETYPE)
p->eth_type = htons(eth_type);
rcu_assign_pointer(d->skbmod_p, p);
if (ovr)
spin_unlock_bh(&d->tcf_lock);
if (p_old)
kfree_rcu(p_old, rcu);
if (goto_ch)
tcf_chain_put_by_act(goto_ch);
if (ret == ACT_P_CREATED)
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 void tcf_skbmod_cleanup(struct tc_action *a)
{
struct tcf_skbmod *d = to_skbmod(a);
struct tcf_skbmod_params *p;
p = rcu_dereference_protected(d->skbmod_p, 1);
if (p)
kfree_rcu(p, rcu);
}
static int tcf_skbmod_dump(struct sk_buff *skb, struct tc_action *a,
int bind, int ref)
{
struct tcf_skbmod *d = to_skbmod(a);
unsigned char *b = skb_tail_pointer(skb);
struct tcf_skbmod_params *p;
struct tc_skbmod opt = {
.index = d->tcf_index,
.refcnt = refcount_read(&d->tcf_refcnt) - ref,
.bindcnt = atomic_read(&d->tcf_bindcnt) - bind,
};
struct tcf_t t;
spin_lock_bh(&d->tcf_lock);
opt.action = d->tcf_action;
p = rcu_dereference_protected(d->skbmod_p,
lockdep_is_held(&d->tcf_lock));
opt.flags = p->flags;
if (nla_put(skb, TCA_SKBMOD_PARMS, sizeof(opt), &opt))
goto nla_put_failure;
if ((p->flags & SKBMOD_F_DMAC) &&
nla_put(skb, TCA_SKBMOD_DMAC, ETH_ALEN, p->eth_dst))
goto nla_put_failure;
if ((p->flags & SKBMOD_F_SMAC) &&
nla_put(skb, TCA_SKBMOD_SMAC, ETH_ALEN, p->eth_src))
goto nla_put_failure;
if ((p->flags & SKBMOD_F_ETYPE) &&
nla_put_u16(skb, TCA_SKBMOD_ETYPE, ntohs(p->eth_type)))
goto nla_put_failure;
tcf_tm_dump(&t, &d->tcf_tm);
if (nla_put_64bit(skb, TCA_SKBMOD_TM, sizeof(t), &t, TCA_SKBMOD_PAD))
goto nla_put_failure;
spin_unlock_bh(&d->tcf_lock);
return skb->len;
nla_put_failure:
spin_unlock_bh(&d->tcf_lock);
nlmsg_trim(skb, b);
return -1;
}
static int tcf_skbmod_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, skbmod_net_id);
return tcf_generic_walker(tn, skb, cb, type, ops, extack);
}
static int tcf_skbmod_search(struct net *net, struct tc_action **a, u32 index)
{
struct tc_action_net *tn = net_generic(net, skbmod_net_id);
return tcf_idr_search(tn, a, index);
}
static struct tc_action_ops act_skbmod_ops = {
.kind = "skbmod",
.id = TCA_ACT_SKBMOD,
.owner = THIS_MODULE,
.act = tcf_skbmod_act,
.dump = tcf_skbmod_dump,
.init = tcf_skbmod_init,
.cleanup = tcf_skbmod_cleanup,
.walk = tcf_skbmod_walker,
.lookup = tcf_skbmod_search,
.size = sizeof(struct tcf_skbmod),
};
static __net_init int skbmod_init_net(struct net *net)
{
struct tc_action_net *tn = net_generic(net, skbmod_net_id);
return tc_action_net_init(tn, &act_skbmod_ops);
}
static void __net_exit skbmod_exit_net(struct list_head *net_list)
{
tc_action_net_exit(net_list, skbmod_net_id);
}
static struct pernet_operations skbmod_net_ops = {
.init = skbmod_init_net,
.exit_batch = skbmod_exit_net,
.id = &skbmod_net_id,
.size = sizeof(struct tc_action_net),
};
MODULE_AUTHOR("Jamal Hadi Salim, <jhs@mojatatu.com>");
MODULE_DESCRIPTION("SKB data mod-ing");
MODULE_LICENSE("GPL");
static int __init skbmod_init_module(void)
{
return tcf_register_action(&act_skbmod_ops, &skbmod_net_ops);
}
static void __exit skbmod_cleanup_module(void)
{
tcf_unregister_action(&act_skbmod_ops, &skbmod_net_ops);
}
module_init(skbmod_init_module);
module_exit(skbmod_cleanup_module);