linux/include/net/inet_frag.h
Eric Dumazet 3c8fc87820 inet: frags: rework rhashtable dismantle
syszbot found an interesting use-after-free [1] happening
while IPv4 fragment rhashtable was destroyed at netns dismantle.

While no insertions can possibly happen at the time a dismantling
netns is destroying this rhashtable, timers can still fire and
attempt to remove elements from this rhashtable.

This is forbidden, since rhashtable_free_and_destroy() has
no synchronization against concurrent inserts and deletes.

Add a new fqdir->dead flag so that timers do not attempt
a rhashtable_remove_fast() operation.

We also have to respect an RCU grace period before starting
the rhashtable_free_and_destroy() from process context,
thus we use rcu_work infrastructure.

This is a refinement of a prior rough attempt to fix this bug :
https://marc.info/?l=linux-netdev&m=153845936820900&w=2

Since the rhashtable cleanup is now deferred to a work queue,
netns dismantles should be slightly faster.

[1]
BUG: KASAN: use-after-free in __read_once_size include/linux/compiler.h:194 [inline]
BUG: KASAN: use-after-free in rhashtable_last_table+0x162/0x180 lib/rhashtable.c:212
Read of size 8 at addr ffff8880a6497b70 by task kworker/0:0/5

CPU: 0 PID: 5 Comm: kworker/0:0 Not tainted 5.2.0-rc1+ #2
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Workqueue: events rht_deferred_worker
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x172/0x1f0 lib/dump_stack.c:113
 print_address_description.cold+0x7c/0x20d mm/kasan/report.c:188
 __kasan_report.cold+0x1b/0x40 mm/kasan/report.c:317
 kasan_report+0x12/0x20 mm/kasan/common.c:614
 __asan_report_load8_noabort+0x14/0x20 mm/kasan/generic_report.c:132
 __read_once_size include/linux/compiler.h:194 [inline]
 rhashtable_last_table+0x162/0x180 lib/rhashtable.c:212
 rht_deferred_worker+0x111/0x2030 lib/rhashtable.c:411
 process_one_work+0x989/0x1790 kernel/workqueue.c:2269
 worker_thread+0x98/0xe40 kernel/workqueue.c:2415
 kthread+0x354/0x420 kernel/kthread.c:255
 ret_from_fork+0x24/0x30 arch/x86/entry/entry_64.S:352

Allocated by task 32687:
 save_stack+0x23/0x90 mm/kasan/common.c:71
 set_track mm/kasan/common.c:79 [inline]
 __kasan_kmalloc mm/kasan/common.c:489 [inline]
 __kasan_kmalloc.constprop.0+0xcf/0xe0 mm/kasan/common.c:462
 kasan_kmalloc+0x9/0x10 mm/kasan/common.c:503
 __do_kmalloc_node mm/slab.c:3620 [inline]
 __kmalloc_node+0x4e/0x70 mm/slab.c:3627
 kmalloc_node include/linux/slab.h:590 [inline]
 kvmalloc_node+0x68/0x100 mm/util.c:431
 kvmalloc include/linux/mm.h:637 [inline]
 kvzalloc include/linux/mm.h:645 [inline]
 bucket_table_alloc+0x90/0x480 lib/rhashtable.c:178
 rhashtable_init+0x3f4/0x7b0 lib/rhashtable.c:1057
 inet_frags_init_net include/net/inet_frag.h:109 [inline]
 ipv4_frags_init_net+0x182/0x410 net/ipv4/ip_fragment.c:683
 ops_init+0xb3/0x410 net/core/net_namespace.c:130
 setup_net+0x2d3/0x740 net/core/net_namespace.c:316
 copy_net_ns+0x1df/0x340 net/core/net_namespace.c:439
 create_new_namespaces+0x400/0x7b0 kernel/nsproxy.c:107
 unshare_nsproxy_namespaces+0xc2/0x200 kernel/nsproxy.c:206
 ksys_unshare+0x440/0x980 kernel/fork.c:2692
 __do_sys_unshare kernel/fork.c:2760 [inline]
 __se_sys_unshare kernel/fork.c:2758 [inline]
 __x64_sys_unshare+0x31/0x40 kernel/fork.c:2758
 do_syscall_64+0xfd/0x680 arch/x86/entry/common.c:301
 entry_SYSCALL_64_after_hwframe+0x49/0xbe

Freed by task 7:
 save_stack+0x23/0x90 mm/kasan/common.c:71
 set_track mm/kasan/common.c:79 [inline]
 __kasan_slab_free+0x102/0x150 mm/kasan/common.c:451
 kasan_slab_free+0xe/0x10 mm/kasan/common.c:459
 __cache_free mm/slab.c:3432 [inline]
 kfree+0xcf/0x220 mm/slab.c:3755
 kvfree+0x61/0x70 mm/util.c:460
 bucket_table_free+0x69/0x150 lib/rhashtable.c:108
 rhashtable_free_and_destroy+0x165/0x8b0 lib/rhashtable.c:1155
 inet_frags_exit_net+0x3d/0x50 net/ipv4/inet_fragment.c:152
 ipv4_frags_exit_net+0x73/0x90 net/ipv4/ip_fragment.c:695
 ops_exit_list.isra.0+0xaa/0x150 net/core/net_namespace.c:154
 cleanup_net+0x3fb/0x960 net/core/net_namespace.c:553
 process_one_work+0x989/0x1790 kernel/workqueue.c:2269
 worker_thread+0x98/0xe40 kernel/workqueue.c:2415
 kthread+0x354/0x420 kernel/kthread.c:255
 ret_from_fork+0x24/0x30 arch/x86/entry/entry_64.S:352

The buggy address belongs to the object at ffff8880a6497b40
 which belongs to the cache kmalloc-1k of size 1024
The buggy address is located 48 bytes inside of
 1024-byte region [ffff8880a6497b40, ffff8880a6497f40)
The buggy address belongs to the page:
page:ffffea0002992580 refcount:1 mapcount:0 mapping:ffff8880aa400ac0 index:0xffff8880a64964c0 compound_mapcount: 0
flags: 0x1fffc0000010200(slab|head)
raw: 01fffc0000010200 ffffea0002916e88 ffffea000218fe08 ffff8880aa400ac0
raw: ffff8880a64964c0 ffff8880a6496040 0000000100000005 0000000000000000
page dumped because: kasan: bad access detected

Memory state around the buggy address:
 ffff8880a6497a00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
 ffff8880a6497a80: fb fb fb fb fb fb fb fb fc fc fc fc fc fc fc fc
>ffff8880a6497b00: fc fc fc fc fc fc fc fc fb fb fb fb fb fb fb fb
                                                             ^
 ffff8880a6497b80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
 ffff8880a6497c00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb

Fixes: 648700f76b03 ("inet: frags: use rhashtables for reassembly units")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2019-05-26 14:08:05 -07:00

187 lines
4.8 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef __NET_FRAG_H__
#define __NET_FRAG_H__
#include <linux/rhashtable-types.h>
/* Per netns frag queues directory */
struct fqdir {
/* sysctls */
long high_thresh;
long low_thresh;
int timeout;
int max_dist;
struct inet_frags *f;
struct net *net;
bool dead;
struct rhashtable rhashtable ____cacheline_aligned_in_smp;
/* Keep atomic mem on separate cachelines in structs that include it */
atomic_long_t mem ____cacheline_aligned_in_smp;
struct rcu_work destroy_rwork;
};
/**
* fragment queue flags
*
* @INET_FRAG_FIRST_IN: first fragment has arrived
* @INET_FRAG_LAST_IN: final fragment has arrived
* @INET_FRAG_COMPLETE: frag queue has been processed and is due for destruction
* @INET_FRAG_HASH_DEAD: inet_frag_kill() has not removed fq from rhashtable
*/
enum {
INET_FRAG_FIRST_IN = BIT(0),
INET_FRAG_LAST_IN = BIT(1),
INET_FRAG_COMPLETE = BIT(2),
INET_FRAG_HASH_DEAD = BIT(3),
};
struct frag_v4_compare_key {
__be32 saddr;
__be32 daddr;
u32 user;
u32 vif;
__be16 id;
u16 protocol;
};
struct frag_v6_compare_key {
struct in6_addr saddr;
struct in6_addr daddr;
u32 user;
__be32 id;
u32 iif;
};
/**
* struct inet_frag_queue - fragment queue
*
* @node: rhash node
* @key: keys identifying this frag.
* @timer: queue expiration timer
* @lock: spinlock protecting this frag
* @refcnt: reference count of the queue
* @rb_fragments: received fragments rb-tree root
* @fragments_tail: received fragments tail
* @last_run_head: the head of the last "run". see ip_fragment.c
* @stamp: timestamp of the last received fragment
* @len: total length of the original datagram
* @meat: length of received fragments so far
* @flags: fragment queue flags
* @max_size: maximum received fragment size
* @fqdir: pointer to struct fqdir
* @rcu: rcu head for freeing deferall
*/
struct inet_frag_queue {
struct rhash_head node;
union {
struct frag_v4_compare_key v4;
struct frag_v6_compare_key v6;
} key;
struct timer_list timer;
spinlock_t lock;
refcount_t refcnt;
struct rb_root rb_fragments;
struct sk_buff *fragments_tail;
struct sk_buff *last_run_head;
ktime_t stamp;
int len;
int meat;
__u8 flags;
u16 max_size;
struct fqdir *fqdir;
struct rcu_head rcu;
};
struct inet_frags {
unsigned int qsize;
void (*constructor)(struct inet_frag_queue *q,
const void *arg);
void (*destructor)(struct inet_frag_queue *);
void (*frag_expire)(struct timer_list *t);
struct kmem_cache *frags_cachep;
const char *frags_cache_name;
struct rhashtable_params rhash_params;
};
int inet_frags_init(struct inet_frags *);
void inet_frags_fini(struct inet_frags *);
static inline int fqdir_init(struct fqdir **fqdirp, struct inet_frags *f,
struct net *net)
{
struct fqdir *fqdir = kzalloc(sizeof(*fqdir), GFP_KERNEL);
int res;
if (!fqdir)
return -ENOMEM;
fqdir->f = f;
fqdir->net = net;
res = rhashtable_init(&fqdir->rhashtable, &fqdir->f->rhash_params);
if (res < 0) {
kfree(fqdir);
return res;
}
*fqdirp = fqdir;
return 0;
}
void fqdir_exit(struct fqdir *fqdir);
void inet_frag_kill(struct inet_frag_queue *q);
void inet_frag_destroy(struct inet_frag_queue *q);
struct inet_frag_queue *inet_frag_find(struct fqdir *fqdir, void *key);
/* Free all skbs in the queue; return the sum of their truesizes. */
unsigned int inet_frag_rbtree_purge(struct rb_root *root);
static inline void inet_frag_put(struct inet_frag_queue *q)
{
if (refcount_dec_and_test(&q->refcnt))
inet_frag_destroy(q);
}
/* Memory Tracking Functions. */
static inline long frag_mem_limit(const struct fqdir *fqdir)
{
return atomic_long_read(&fqdir->mem);
}
static inline void sub_frag_mem_limit(struct fqdir *fqdir, long val)
{
atomic_long_sub(val, &fqdir->mem);
}
static inline void add_frag_mem_limit(struct fqdir *fqdir, long val)
{
atomic_long_add(val, &fqdir->mem);
}
/* RFC 3168 support :
* We want to check ECN values of all fragments, do detect invalid combinations.
* In ipq->ecn, we store the OR value of each ip4_frag_ecn() fragment value.
*/
#define IPFRAG_ECN_NOT_ECT 0x01 /* one frag had ECN_NOT_ECT */
#define IPFRAG_ECN_ECT_1 0x02 /* one frag had ECN_ECT_1 */
#define IPFRAG_ECN_ECT_0 0x04 /* one frag had ECN_ECT_0 */
#define IPFRAG_ECN_CE 0x08 /* one frag had ECN_CE */
extern const u8 ip_frag_ecn_table[16];
/* Return values of inet_frag_queue_insert() */
#define IPFRAG_OK 0
#define IPFRAG_DUP 1
#define IPFRAG_OVERLAP 2
int inet_frag_queue_insert(struct inet_frag_queue *q, struct sk_buff *skb,
int offset, int end);
void *inet_frag_reasm_prepare(struct inet_frag_queue *q, struct sk_buff *skb,
struct sk_buff *parent);
void inet_frag_reasm_finish(struct inet_frag_queue *q, struct sk_buff *head,
void *reasm_data);
struct sk_buff *inet_frag_pull_head(struct inet_frag_queue *q);
#endif