alistair23-linux/net/netfilter/nft_set_rbtree.c
Taehee Yoo c293ac959f netfilter: nft_set_rbtree: fix panic when destroying set by GC
This patch fixes below.
1. check null pointer of rb_next.
 rb_next can return null. so null check routine should be added.
2. add rcu_barrier in destroy routine.
 GC uses call_rcu to remove elements. but all elements should be
 removed before destroying set and chains. so that rcu_barrier is added.

test script:
   %cat test.nft
   table inet aa {
	   map map1 {
		   type ipv4_addr : verdict; flags interval, timeout;
		   elements = {
			   0-1 : jump a0,
			   3-4 : jump a0,
			   6-7 : jump a0,
			   9-10 : jump a0,
			   12-13 : jump a0,
			   15-16 : jump a0,
			   18-19 : jump a0,
			   21-22 : jump a0,
			   24-25 : jump a0,
			   27-28 : jump a0,
		   }
		   timeout 1s;
	   }
	   chain a0 {
	   }
   }
   flush ruleset
   table inet aa {
	   map map1 {
		   type ipv4_addr : verdict; flags interval, timeout;
		   elements = {
			   0-1 : jump a0,
			   3-4 : jump a0,
			   6-7 : jump a0,
			   9-10 : jump a0,
			   12-13 : jump a0,
			   15-16 : jump a0,
			   18-19 : jump a0,
			   21-22 : jump a0,
			   24-25 : jump a0,
			   27-28 : jump a0,
		   }
		   timeout 1s;
	   }
	   chain a0 {
	   }
   }
   flush ruleset

splat looks like:
[ 2402.419838] kasan: GPF could be caused by NULL-ptr deref or user memory access
[ 2402.428433] general protection fault: 0000 [#1] SMP DEBUG_PAGEALLOC KASAN PTI
[ 2402.429343] CPU: 1 PID: 1350 Comm: kworker/1:1 Not tainted 4.18.0-rc2+ #1
[ 2402.429343] Hardware name: To be filled by O.E.M. To be filled by O.E.M./Aptio CRB, BIOS 5.6.5 03/23/2017
[ 2402.429343] Workqueue: events_power_efficient nft_rbtree_gc [nft_set_rbtree]
[ 2402.429343] RIP: 0010:rb_next+0x1e/0x130
[ 2402.429343] Code: e9 de f2 ff ff 0f 1f 80 00 00 00 00 41 55 48 89 fa 41 54 55 53 48 c1 ea 03 48 b8 00 00 00 0
[ 2402.429343] RSP: 0018:ffff880105f77678 EFLAGS: 00010296
[ 2402.429343] RAX: dffffc0000000000 RBX: ffff8801143e3428 RCX: 1ffff1002287c69c
[ 2402.429343] RDX: 0000000000000000 RSI: 0000000000000004 RDI: 0000000000000000
[ 2402.429343] RBP: 0000000000000000 R08: ffffed0016aabc24 R09: ffffed0016aabc24
[ 2402.429343] R10: 0000000000000001 R11: ffffed0016aabc23 R12: 0000000000000000
[ 2402.429343] R13: ffff8800b6933388 R14: dffffc0000000000 R15: ffff8801143e3440
[ 2402.534486] kasan: CONFIG_KASAN_INLINE enabled
[ 2402.534212] FS:  0000000000000000(0000) GS:ffff88011b600000(0000) knlGS:0000000000000000
[ 2402.534212] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 2402.534212] CR2: 0000000000863008 CR3: 00000000a3c16000 CR4: 00000000001006e0
[ 2402.534212] Call Trace:
[ 2402.534212]  nft_rbtree_gc+0x2b5/0x5f0 [nft_set_rbtree]
[ 2402.534212]  process_one_work+0xc1b/0x1ee0
[ 2402.540329] kasan: GPF could be caused by NULL-ptr deref or user memory access
[ 2402.534212]  ? _raw_spin_unlock_irq+0x29/0x40
[ 2402.534212]  ? pwq_dec_nr_in_flight+0x3e0/0x3e0
[ 2402.534212]  ? set_load_weight+0x270/0x270
[ 2402.534212]  ? __schedule+0x6ea/0x1fb0
[ 2402.534212]  ? __sched_text_start+0x8/0x8
[ 2402.534212]  ? save_trace+0x320/0x320
[ 2402.534212]  ? sched_clock_local+0xe2/0x150
[ 2402.534212]  ? find_held_lock+0x39/0x1c0
[ 2402.534212]  ? worker_thread+0x35f/0x1150
[ 2402.534212]  ? lock_contended+0xe90/0xe90
[ 2402.534212]  ? __lock_acquire+0x4520/0x4520
[ 2402.534212]  ? do_raw_spin_unlock+0xb1/0x350
[ 2402.534212]  ? do_raw_spin_trylock+0x111/0x1b0
[ 2402.534212]  ? do_raw_spin_lock+0x1f0/0x1f0
[ 2402.534212]  worker_thread+0x169/0x1150

Fixes: 8d8540c4f5e0("netfilter: nft_set_rbtree: add timeout support")
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
2018-07-18 17:12:05 +02:00

487 lines
12 KiB
C

/*
* Copyright (c) 2008-2009 Patrick McHardy <kaber@trash.net>
*
* 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.
*
* Development of this code funded by Astaro AG (http://www.astaro.com/)
*/
#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/module.h>
#include <linux/list.h>
#include <linux/rbtree.h>
#include <linux/netlink.h>
#include <linux/netfilter.h>
#include <linux/netfilter/nf_tables.h>
#include <net/netfilter/nf_tables.h>
struct nft_rbtree {
struct rb_root root;
rwlock_t lock;
seqcount_t count;
struct delayed_work gc_work;
};
struct nft_rbtree_elem {
struct rb_node node;
struct nft_set_ext ext;
};
static bool nft_rbtree_interval_end(const struct nft_rbtree_elem *rbe)
{
return nft_set_ext_exists(&rbe->ext, NFT_SET_EXT_FLAGS) &&
(*nft_set_ext_flags(&rbe->ext) & NFT_SET_ELEM_INTERVAL_END);
}
static bool nft_rbtree_equal(const struct nft_set *set, const void *this,
const struct nft_rbtree_elem *interval)
{
return memcmp(this, nft_set_ext_key(&interval->ext), set->klen) == 0;
}
static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set,
const u32 *key, const struct nft_set_ext **ext,
unsigned int seq)
{
struct nft_rbtree *priv = nft_set_priv(set);
const struct nft_rbtree_elem *rbe, *interval = NULL;
u8 genmask = nft_genmask_cur(net);
const struct rb_node *parent;
const void *this;
int d;
parent = rcu_dereference_raw(priv->root.rb_node);
while (parent != NULL) {
if (read_seqcount_retry(&priv->count, seq))
return false;
rbe = rb_entry(parent, struct nft_rbtree_elem, node);
this = nft_set_ext_key(&rbe->ext);
d = memcmp(this, key, set->klen);
if (d < 0) {
parent = rcu_dereference_raw(parent->rb_left);
if (interval &&
nft_rbtree_equal(set, this, interval) &&
nft_rbtree_interval_end(rbe) &&
!nft_rbtree_interval_end(interval))
continue;
interval = rbe;
} else if (d > 0)
parent = rcu_dereference_raw(parent->rb_right);
else {
if (!nft_set_elem_active(&rbe->ext, genmask)) {
parent = rcu_dereference_raw(parent->rb_left);
continue;
}
if (nft_rbtree_interval_end(rbe))
goto out;
*ext = &rbe->ext;
return true;
}
}
if (set->flags & NFT_SET_INTERVAL && interval != NULL &&
nft_set_elem_active(&interval->ext, genmask) &&
!nft_rbtree_interval_end(interval)) {
*ext = &interval->ext;
return true;
}
out:
return false;
}
static bool nft_rbtree_lookup(const struct net *net, const struct nft_set *set,
const u32 *key, const struct nft_set_ext **ext)
{
struct nft_rbtree *priv = nft_set_priv(set);
unsigned int seq = read_seqcount_begin(&priv->count);
bool ret;
ret = __nft_rbtree_lookup(net, set, key, ext, seq);
if (ret || !read_seqcount_retry(&priv->count, seq))
return ret;
read_lock_bh(&priv->lock);
seq = read_seqcount_begin(&priv->count);
ret = __nft_rbtree_lookup(net, set, key, ext, seq);
read_unlock_bh(&priv->lock);
return ret;
}
static bool __nft_rbtree_get(const struct net *net, const struct nft_set *set,
const u32 *key, struct nft_rbtree_elem **elem,
unsigned int seq, unsigned int flags, u8 genmask)
{
struct nft_rbtree_elem *rbe, *interval = NULL;
struct nft_rbtree *priv = nft_set_priv(set);
const struct rb_node *parent;
const void *this;
int d;
parent = rcu_dereference_raw(priv->root.rb_node);
while (parent != NULL) {
if (read_seqcount_retry(&priv->count, seq))
return false;
rbe = rb_entry(parent, struct nft_rbtree_elem, node);
this = nft_set_ext_key(&rbe->ext);
d = memcmp(this, key, set->klen);
if (d < 0) {
parent = rcu_dereference_raw(parent->rb_left);
interval = rbe;
} else if (d > 0) {
parent = rcu_dereference_raw(parent->rb_right);
} else {
if (!nft_set_elem_active(&rbe->ext, genmask))
parent = rcu_dereference_raw(parent->rb_left);
if (!nft_set_ext_exists(&rbe->ext, NFT_SET_EXT_FLAGS) ||
(*nft_set_ext_flags(&rbe->ext) & NFT_SET_ELEM_INTERVAL_END) ==
(flags & NFT_SET_ELEM_INTERVAL_END)) {
*elem = rbe;
return true;
}
return false;
}
}
if (set->flags & NFT_SET_INTERVAL && interval != NULL &&
nft_set_elem_active(&interval->ext, genmask) &&
!nft_rbtree_interval_end(interval)) {
*elem = interval;
return true;
}
return false;
}
static void *nft_rbtree_get(const struct net *net, const struct nft_set *set,
const struct nft_set_elem *elem, unsigned int flags)
{
struct nft_rbtree *priv = nft_set_priv(set);
unsigned int seq = read_seqcount_begin(&priv->count);
struct nft_rbtree_elem *rbe = ERR_PTR(-ENOENT);
const u32 *key = (const u32 *)&elem->key.val;
u8 genmask = nft_genmask_cur(net);
bool ret;
ret = __nft_rbtree_get(net, set, key, &rbe, seq, flags, genmask);
if (ret || !read_seqcount_retry(&priv->count, seq))
return rbe;
read_lock_bh(&priv->lock);
seq = read_seqcount_begin(&priv->count);
ret = __nft_rbtree_get(net, set, key, &rbe, seq, flags, genmask);
if (!ret)
rbe = ERR_PTR(-ENOENT);
read_unlock_bh(&priv->lock);
return rbe;
}
static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set,
struct nft_rbtree_elem *new,
struct nft_set_ext **ext)
{
struct nft_rbtree *priv = nft_set_priv(set);
u8 genmask = nft_genmask_next(net);
struct nft_rbtree_elem *rbe;
struct rb_node *parent, **p;
int d;
parent = NULL;
p = &priv->root.rb_node;
while (*p != NULL) {
parent = *p;
rbe = rb_entry(parent, struct nft_rbtree_elem, node);
d = memcmp(nft_set_ext_key(&rbe->ext),
nft_set_ext_key(&new->ext),
set->klen);
if (d < 0)
p = &parent->rb_left;
else if (d > 0)
p = &parent->rb_right;
else {
if (nft_rbtree_interval_end(rbe) &&
!nft_rbtree_interval_end(new)) {
p = &parent->rb_left;
} else if (!nft_rbtree_interval_end(rbe) &&
nft_rbtree_interval_end(new)) {
p = &parent->rb_right;
} else if (nft_set_elem_active(&rbe->ext, genmask)) {
*ext = &rbe->ext;
return -EEXIST;
} else {
p = &parent->rb_left;
}
}
}
rb_link_node_rcu(&new->node, parent, p);
rb_insert_color(&new->node, &priv->root);
return 0;
}
static int nft_rbtree_insert(const struct net *net, const struct nft_set *set,
const struct nft_set_elem *elem,
struct nft_set_ext **ext)
{
struct nft_rbtree *priv = nft_set_priv(set);
struct nft_rbtree_elem *rbe = elem->priv;
int err;
write_lock_bh(&priv->lock);
write_seqcount_begin(&priv->count);
err = __nft_rbtree_insert(net, set, rbe, ext);
write_seqcount_end(&priv->count);
write_unlock_bh(&priv->lock);
return err;
}
static void nft_rbtree_remove(const struct net *net,
const struct nft_set *set,
const struct nft_set_elem *elem)
{
struct nft_rbtree *priv = nft_set_priv(set);
struct nft_rbtree_elem *rbe = elem->priv;
write_lock_bh(&priv->lock);
write_seqcount_begin(&priv->count);
rb_erase(&rbe->node, &priv->root);
write_seqcount_end(&priv->count);
write_unlock_bh(&priv->lock);
}
static void nft_rbtree_activate(const struct net *net,
const struct nft_set *set,
const struct nft_set_elem *elem)
{
struct nft_rbtree_elem *rbe = elem->priv;
nft_set_elem_change_active(net, set, &rbe->ext);
nft_set_elem_clear_busy(&rbe->ext);
}
static bool nft_rbtree_flush(const struct net *net,
const struct nft_set *set, void *priv)
{
struct nft_rbtree_elem *rbe = priv;
if (!nft_set_elem_mark_busy(&rbe->ext) ||
!nft_is_active(net, &rbe->ext)) {
nft_set_elem_change_active(net, set, &rbe->ext);
return true;
}
return false;
}
static void *nft_rbtree_deactivate(const struct net *net,
const struct nft_set *set,
const struct nft_set_elem *elem)
{
const struct nft_rbtree *priv = nft_set_priv(set);
const struct rb_node *parent = priv->root.rb_node;
struct nft_rbtree_elem *rbe, *this = elem->priv;
u8 genmask = nft_genmask_next(net);
int d;
while (parent != NULL) {
rbe = rb_entry(parent, struct nft_rbtree_elem, node);
d = memcmp(nft_set_ext_key(&rbe->ext), &elem->key.val,
set->klen);
if (d < 0)
parent = parent->rb_left;
else if (d > 0)
parent = parent->rb_right;
else {
if (!nft_set_elem_active(&rbe->ext, genmask)) {
parent = parent->rb_left;
continue;
}
if (nft_rbtree_interval_end(rbe) &&
!nft_rbtree_interval_end(this)) {
parent = parent->rb_left;
continue;
} else if (!nft_rbtree_interval_end(rbe) &&
nft_rbtree_interval_end(this)) {
parent = parent->rb_right;
continue;
}
nft_rbtree_flush(net, set, rbe);
return rbe;
}
}
return NULL;
}
static void nft_rbtree_walk(const struct nft_ctx *ctx,
struct nft_set *set,
struct nft_set_iter *iter)
{
struct nft_rbtree *priv = nft_set_priv(set);
struct nft_rbtree_elem *rbe;
struct nft_set_elem elem;
struct rb_node *node;
read_lock_bh(&priv->lock);
for (node = rb_first(&priv->root); node != NULL; node = rb_next(node)) {
rbe = rb_entry(node, struct nft_rbtree_elem, node);
if (iter->count < iter->skip)
goto cont;
if (!nft_set_elem_active(&rbe->ext, iter->genmask))
goto cont;
elem.priv = rbe;
iter->err = iter->fn(ctx, set, iter, &elem);
if (iter->err < 0) {
read_unlock_bh(&priv->lock);
return;
}
cont:
iter->count++;
}
read_unlock_bh(&priv->lock);
}
static void nft_rbtree_gc(struct work_struct *work)
{
struct nft_set_gc_batch *gcb = NULL;
struct rb_node *node, *prev = NULL;
struct nft_rbtree_elem *rbe;
struct nft_rbtree *priv;
struct nft_set *set;
int i;
priv = container_of(work, struct nft_rbtree, gc_work.work);
set = nft_set_container_of(priv);
write_lock_bh(&priv->lock);
write_seqcount_begin(&priv->count);
for (node = rb_first(&priv->root); node != NULL; node = rb_next(node)) {
rbe = rb_entry(node, struct nft_rbtree_elem, node);
if (nft_rbtree_interval_end(rbe)) {
prev = node;
continue;
}
if (!nft_set_elem_expired(&rbe->ext))
continue;
if (nft_set_elem_mark_busy(&rbe->ext))
continue;
gcb = nft_set_gc_batch_check(set, gcb, GFP_ATOMIC);
if (!gcb)
break;
atomic_dec(&set->nelems);
nft_set_gc_batch_add(gcb, rbe);
if (prev) {
rbe = rb_entry(prev, struct nft_rbtree_elem, node);
atomic_dec(&set->nelems);
nft_set_gc_batch_add(gcb, rbe);
prev = NULL;
}
node = rb_next(node);
if (!node)
break;
}
if (gcb) {
for (i = 0; i < gcb->head.cnt; i++) {
rbe = gcb->elems[i];
rb_erase(&rbe->node, &priv->root);
}
}
write_seqcount_end(&priv->count);
write_unlock_bh(&priv->lock);
nft_set_gc_batch_complete(gcb);
queue_delayed_work(system_power_efficient_wq, &priv->gc_work,
nft_set_gc_interval(set));
}
static unsigned int nft_rbtree_privsize(const struct nlattr * const nla[],
const struct nft_set_desc *desc)
{
return sizeof(struct nft_rbtree);
}
static int nft_rbtree_init(const struct nft_set *set,
const struct nft_set_desc *desc,
const struct nlattr * const nla[])
{
struct nft_rbtree *priv = nft_set_priv(set);
rwlock_init(&priv->lock);
seqcount_init(&priv->count);
priv->root = RB_ROOT;
INIT_DEFERRABLE_WORK(&priv->gc_work, nft_rbtree_gc);
if (set->flags & NFT_SET_TIMEOUT)
queue_delayed_work(system_power_efficient_wq, &priv->gc_work,
nft_set_gc_interval(set));
return 0;
}
static void nft_rbtree_destroy(const struct nft_set *set)
{
struct nft_rbtree *priv = nft_set_priv(set);
struct nft_rbtree_elem *rbe;
struct rb_node *node;
cancel_delayed_work_sync(&priv->gc_work);
rcu_barrier();
while ((node = priv->root.rb_node) != NULL) {
rb_erase(node, &priv->root);
rbe = rb_entry(node, struct nft_rbtree_elem, node);
nft_set_elem_destroy(set, rbe, true);
}
}
static bool nft_rbtree_estimate(const struct nft_set_desc *desc, u32 features,
struct nft_set_estimate *est)
{
if (desc->size)
est->size = sizeof(struct nft_rbtree) +
desc->size * sizeof(struct nft_rbtree_elem);
else
est->size = ~0;
est->lookup = NFT_SET_CLASS_O_LOG_N;
est->space = NFT_SET_CLASS_O_N;
return true;
}
struct nft_set_type nft_set_rbtree_type __read_mostly = {
.owner = THIS_MODULE,
.features = NFT_SET_INTERVAL | NFT_SET_MAP | NFT_SET_OBJECT | NFT_SET_TIMEOUT,
.ops = {
.privsize = nft_rbtree_privsize,
.elemsize = offsetof(struct nft_rbtree_elem, ext),
.estimate = nft_rbtree_estimate,
.init = nft_rbtree_init,
.destroy = nft_rbtree_destroy,
.insert = nft_rbtree_insert,
.remove = nft_rbtree_remove,
.deactivate = nft_rbtree_deactivate,
.flush = nft_rbtree_flush,
.activate = nft_rbtree_activate,
.lookup = nft_rbtree_lookup,
.walk = nft_rbtree_walk,
.get = nft_rbtree_get,
},
};