mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-25 20:15:13 +07:00
34043d250f
Matteo reported the following splat, testing the datapath of TC 'sample': BUG: KASAN: null-ptr-deref in tcf_sample_act+0xc4/0x310 Read of size 8 at addr 0000000000000000 by task nc/433 CPU: 0 PID: 433 Comm: nc Not tainted 4.19.0-rc3-kvm #17 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS ?-20180531_142017-buildhw-08.phx2.fedoraproject.org-1.fc28 04/01/2014 Call Trace: kasan_report.cold.6+0x6c/0x2fa tcf_sample_act+0xc4/0x310 ? dev_hard_start_xmit+0x117/0x180 tcf_action_exec+0xa3/0x160 tcf_classify+0xdd/0x1d0 htb_enqueue+0x18e/0x6b0 ? deref_stack_reg+0x7a/0xb0 ? htb_delete+0x4b0/0x4b0 ? unwind_next_frame+0x819/0x8f0 ? entry_SYSCALL_64_after_hwframe+0x44/0xa9 __dev_queue_xmit+0x722/0xca0 ? unwind_get_return_address_ptr+0x50/0x50 ? netdev_pick_tx+0xe0/0xe0 ? save_stack+0x8c/0xb0 ? kasan_kmalloc+0xbe/0xd0 ? __kmalloc_track_caller+0xe4/0x1c0 ? __kmalloc_reserve.isra.45+0x24/0x70 ? __alloc_skb+0xdd/0x2e0 ? sk_stream_alloc_skb+0x91/0x3b0 ? tcp_sendmsg_locked+0x71b/0x15a0 ? tcp_sendmsg+0x22/0x40 ? __sys_sendto+0x1b0/0x250 ? __x64_sys_sendto+0x6f/0x80 ? do_syscall_64+0x5d/0x150 ? entry_SYSCALL_64_after_hwframe+0x44/0xa9 ? __sys_sendto+0x1b0/0x250 ? __x64_sys_sendto+0x6f/0x80 ? do_syscall_64+0x5d/0x150 ? entry_SYSCALL_64_after_hwframe+0x44/0xa9 ip_finish_output2+0x495/0x590 ? ip_copy_metadata+0x2e0/0x2e0 ? skb_gso_validate_network_len+0x6f/0x110 ? ip_finish_output+0x174/0x280 __tcp_transmit_skb+0xb17/0x12b0 ? __tcp_select_window+0x380/0x380 tcp_write_xmit+0x913/0x1de0 ? __sk_mem_schedule+0x50/0x80 tcp_sendmsg_locked+0x49d/0x15a0 ? tcp_rcv_established+0x8da/0xa30 ? tcp_set_state+0x220/0x220 ? clear_user+0x1f/0x50 ? iov_iter_zero+0x1ae/0x590 ? __fget_light+0xa0/0xe0 tcp_sendmsg+0x22/0x40 __sys_sendto+0x1b0/0x250 ? __ia32_sys_getpeername+0x40/0x40 ? _copy_to_user+0x58/0x70 ? poll_select_copy_remaining+0x176/0x200 ? __pollwait+0x1c0/0x1c0 ? ktime_get_ts64+0x11f/0x140 ? kern_select+0x108/0x150 ? core_sys_select+0x360/0x360 ? vfs_read+0x127/0x150 ? kernel_write+0x90/0x90 __x64_sys_sendto+0x6f/0x80 do_syscall_64+0x5d/0x150 entry_SYSCALL_64_after_hwframe+0x44/0xa9 RIP: 0033:0x7fefef2b129d Code: ff ff ff ff eb b6 0f 1f 80 00 00 00 00 48 8d 05 51 37 0c 00 41 89 ca 8b 00 85 c0 75 20 45 31 c9 45 31 c0 b8 2c 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 6b f3 c3 66 0f 1f 84 00 00 00 00 00 41 56 41 RSP: 002b:00007fff2f5350c8 EFLAGS: 00000246 ORIG_RAX: 000000000000002c RAX: ffffffffffffffda RBX: 000056118d60c120 RCX: 00007fefef2b129d RDX: 0000000000002000 RSI: 000056118d629320 RDI: 0000000000000003 RBP: 000056118d530370 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000002000 R13: 000056118d5c2a10 R14: 000056118d5c2a10 R15: 000056118d5303b8 tcf_sample_act() tried to update its per-cpu stats, but tcf_sample_init() forgot to allocate them, because tcf_idr_create() was called with a wrong value of 'cpustats'. Setting it to true proved to fix the reported crash. Reported-by: Matteo Croce <mcroce@redhat.com> Fixes:65a206c01e
("net/sched: Change act_api and act_xxx modules to use IDR") Fixes:5c5670fae4
("net/sched: Introduce sample tc action") Tested-by: Matteo Croce <mcroce@redhat.com> Signed-off-by: Davide Caratti <dcaratti@redhat.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
283 lines
7.2 KiB
C
283 lines
7.2 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 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 netlink_ext_ack *extack)
|
|
{
|
|
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",
|
|
.type = TCA_ACT_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");
|