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_sample.c
Davide Caratti 85d0966fa5 net/sched: prepare TC actions to properly validate the control action
- pass a pointer to struct tcf_proto in each actions's init() handler,
  to allow validating the control action, checking whether the chain
  exists and (eventually) refcounting it.
- remove code that validates the control action after a successful call
  to the action's init() handler, and replace it with a test that forbids
  addition of actions having 'goto_chain' and NULL goto_chain pointer at
  the same time.
- add tcf_action_check_ctrlact(), that will validate the control action
  and eventually allocate the action 'goto_chain' within the init()
  handler.
- add tcf_action_set_ctrlact(), that will assign the control action and
  swap the current 'goto_chain' pointer with the new given one.

This disallows 'goto_chain' on actions that don't initialize it properly
in their init() handler, i.e. calling tcf_action_check_ctrlact() after
successful IDR reservation and then calling tcf_action_set_ctrlact()
to assign 'goto_chain' and 'tcf_action' consistently.

By doing this, the kernel does not leak anymore refcounts when a valid
'goto chain' handle is replaced in TC actions, causing kmemleak splats
like the following one:

 # tc chain add dev dd0 chain 42 ingress protocol ip flower \
 > ip_proto tcp action drop
 # tc chain add dev dd0 chain 43 ingress protocol ip flower \
 > ip_proto udp action drop
 # tc filter add dev dd0 ingress matchall \
 > action gact goto chain 42 index 66
 # tc filter replace dev dd0 ingress matchall \
 > action gact goto chain 43 index 66
 # echo scan >/sys/kernel/debug/kmemleak
 <...>
 unreferenced object 0xffff93c0ee09f000 (size 1024):
 comm "tc", pid 2565, jiffies 4295339808 (age 65.426s)
 hex dump (first 32 bytes):
   00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
   00 00 00 00 08 00 06 00 00 00 00 00 00 00 00 00  ................
 backtrace:
   [<000000009b63f92d>] tc_ctl_chain+0x3d2/0x4c0
   [<00000000683a8d72>] rtnetlink_rcv_msg+0x263/0x2d0
   [<00000000ddd88f8e>] netlink_rcv_skb+0x4a/0x110
   [<000000006126a348>] netlink_unicast+0x1a0/0x250
   [<00000000b3340877>] netlink_sendmsg+0x2c1/0x3c0
   [<00000000a25a2171>] sock_sendmsg+0x36/0x40
   [<00000000f19ee1ec>] ___sys_sendmsg+0x280/0x2f0
   [<00000000d0422042>] __sys_sendmsg+0x5e/0xa0
   [<000000007a6c61f9>] do_syscall_64+0x5b/0x180
   [<00000000ccd07542>] entry_SYSCALL_64_after_hwframe+0x44/0xa9
   [<0000000013eaa334>] 0xffffffffffffffff

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

282 lines
7.1 KiB
C

/*
* net/sched/act_sample.c - Packet sampling tc action
* Copyright (c) 2017 Yotam Gigi <yotamg@mellanox.com>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*/
#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 <net/net_namespace.h>
#include <net/netlink.h>
#include <net/pkt_sched.h>
#include <linux/tc_act/tc_sample.h>
#include <net/tc_act/tc_sample.h>
#include <net/psample.h>
#include <linux/if_arp.h>
static unsigned int sample_net_id;
static struct tc_action_ops act_sample_ops;
static const struct nla_policy sample_policy[TCA_SAMPLE_MAX + 1] = {
[TCA_SAMPLE_PARMS] = { .len = sizeof(struct tc_sample) },
[TCA_SAMPLE_RATE] = { .type = NLA_U32 },
[TCA_SAMPLE_TRUNC_SIZE] = { .type = NLA_U32 },
[TCA_SAMPLE_PSAMPLE_GROUP] = { .type = NLA_U32 },
};
static int tcf_sample_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, sample_net_id);
struct nlattr *tb[TCA_SAMPLE_MAX + 1];
struct psample_group *psample_group;
struct tc_sample *parm;
u32 psample_group_num;
struct tcf_sample *s;
bool exists = false;
int ret, err;
if (!nla)
return -EINVAL;
ret = nla_parse_nested(tb, TCA_SAMPLE_MAX, nla, sample_policy, NULL);
if (ret < 0)
return ret;
if (!tb[TCA_SAMPLE_PARMS] || !tb[TCA_SAMPLE_RATE] ||
!tb[TCA_SAMPLE_PSAMPLE_GROUP])
return -EINVAL;
parm = nla_data(tb[TCA_SAMPLE_PARMS]);
err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
if (err < 0)
return err;
exists = err;
if (exists && bind)
return 0;
if (!exists) {
ret = tcf_idr_create(tn, parm->index, est, a,
&act_sample_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;
}
psample_group_num = nla_get_u32(tb[TCA_SAMPLE_PSAMPLE_GROUP]);
psample_group = psample_group_get(net, psample_group_num);
if (!psample_group) {
tcf_idr_release(*a, bind);
return -ENOMEM;
}
s = to_sample(*a);
spin_lock_bh(&s->tcf_lock);
s->tcf_action = parm->action;
s->rate = nla_get_u32(tb[TCA_SAMPLE_RATE]);
s->psample_group_num = psample_group_num;
RCU_INIT_POINTER(s->psample_group, psample_group);
if (tb[TCA_SAMPLE_TRUNC_SIZE]) {
s->truncate = true;
s->trunc_size = nla_get_u32(tb[TCA_SAMPLE_TRUNC_SIZE]);
}
spin_unlock_bh(&s->tcf_lock);
if (ret == ACT_P_CREATED)
tcf_idr_insert(tn, *a);
return ret;
}
static void tcf_sample_cleanup(struct tc_action *a)
{
struct tcf_sample *s = to_sample(a);
struct psample_group *psample_group;
/* last reference to action, no need to lock */
psample_group = rcu_dereference_protected(s->psample_group, 1);
RCU_INIT_POINTER(s->psample_group, NULL);
if (psample_group)
psample_group_put(psample_group);
}
static bool tcf_sample_dev_ok_push(struct net_device *dev)
{
switch (dev->type) {
case ARPHRD_TUNNEL:
case ARPHRD_TUNNEL6:
case ARPHRD_SIT:
case ARPHRD_IPGRE:
case ARPHRD_VOID:
case ARPHRD_NONE:
return false;
default:
return true;
}
}
static int tcf_sample_act(struct sk_buff *skb, const struct tc_action *a,
struct tcf_result *res)
{
struct tcf_sample *s = to_sample(a);
struct psample_group *psample_group;
int retval;
int size;
int iif;
int oif;
tcf_lastuse_update(&s->tcf_tm);
bstats_cpu_update(this_cpu_ptr(s->common.cpu_bstats), skb);
retval = READ_ONCE(s->tcf_action);
psample_group = rcu_dereference_bh(s->psample_group);
/* randomly sample packets according to rate */
if (psample_group && (prandom_u32() % s->rate == 0)) {
if (!skb_at_tc_ingress(skb)) {
iif = skb->skb_iif;
oif = skb->dev->ifindex;
} else {
iif = skb->dev->ifindex;
oif = 0;
}
/* on ingress, the mac header gets popped, so push it back */
if (skb_at_tc_ingress(skb) && tcf_sample_dev_ok_push(skb->dev))
skb_push(skb, skb->mac_len);
size = s->truncate ? s->trunc_size : skb->len;
psample_sample_packet(psample_group, skb, size, iif, oif,
s->rate);
if (skb_at_tc_ingress(skb) && tcf_sample_dev_ok_push(skb->dev))
skb_pull(skb, skb->mac_len);
}
return retval;
}
static int tcf_sample_dump(struct sk_buff *skb, struct tc_action *a,
int bind, int ref)
{
unsigned char *b = skb_tail_pointer(skb);
struct tcf_sample *s = to_sample(a);
struct tc_sample opt = {
.index = s->tcf_index,
.refcnt = refcount_read(&s->tcf_refcnt) - ref,
.bindcnt = atomic_read(&s->tcf_bindcnt) - bind,
};
struct tcf_t t;
spin_lock_bh(&s->tcf_lock);
opt.action = s->tcf_action;
if (nla_put(skb, TCA_SAMPLE_PARMS, sizeof(opt), &opt))
goto nla_put_failure;
tcf_tm_dump(&t, &s->tcf_tm);
if (nla_put_64bit(skb, TCA_SAMPLE_TM, sizeof(t), &t, TCA_SAMPLE_PAD))
goto nla_put_failure;
if (nla_put_u32(skb, TCA_SAMPLE_RATE, s->rate))
goto nla_put_failure;
if (s->truncate)
if (nla_put_u32(skb, TCA_SAMPLE_TRUNC_SIZE, s->trunc_size))
goto nla_put_failure;
if (nla_put_u32(skb, TCA_SAMPLE_PSAMPLE_GROUP, s->psample_group_num))
goto nla_put_failure;
spin_unlock_bh(&s->tcf_lock);
return skb->len;
nla_put_failure:
spin_unlock_bh(&s->tcf_lock);
nlmsg_trim(skb, b);
return -1;
}
static int tcf_sample_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, sample_net_id);
return tcf_generic_walker(tn, skb, cb, type, ops, extack);
}
static int tcf_sample_search(struct net *net, struct tc_action **a, u32 index)
{
struct tc_action_net *tn = net_generic(net, sample_net_id);
return tcf_idr_search(tn, a, index);
}
static struct tc_action_ops act_sample_ops = {
.kind = "sample",
.id = TCA_ID_SAMPLE,
.owner = THIS_MODULE,
.act = tcf_sample_act,
.dump = tcf_sample_dump,
.init = tcf_sample_init,
.cleanup = tcf_sample_cleanup,
.walk = tcf_sample_walker,
.lookup = tcf_sample_search,
.size = sizeof(struct tcf_sample),
};
static __net_init int sample_init_net(struct net *net)
{
struct tc_action_net *tn = net_generic(net, sample_net_id);
return tc_action_net_init(tn, &act_sample_ops);
}
static void __net_exit sample_exit_net(struct list_head *net_list)
{
tc_action_net_exit(net_list, sample_net_id);
}
static struct pernet_operations sample_net_ops = {
.init = sample_init_net,
.exit_batch = sample_exit_net,
.id = &sample_net_id,
.size = sizeof(struct tc_action_net),
};
static int __init sample_init_module(void)
{
return tcf_register_action(&act_sample_ops, &sample_net_ops);
}
static void __exit sample_cleanup_module(void)
{
tcf_unregister_action(&act_sample_ops, &sample_net_ops);
}
module_init(sample_init_module);
module_exit(sample_cleanup_module);
MODULE_AUTHOR("Yotam Gigi <yotam.gi@gmail.com>");
MODULE_DESCRIPTION("Packet sampling action");
MODULE_LICENSE("GPL v2");