linux_dsm_epyc7002/include/net/inet_frag.h
Eric Dumazet dc93f46bc4 inet: frags: fix use-after-free read in inet_frag_destroy_rcu
As caught by syzbot [1], the rcu grace period that is respected
before fqdir_rwork_fn() proceeds and frees fqdir is not enough
to prevent inet_frag_destroy_rcu() being run after the freeing.

We need a proper rcu_barrier() synchronization to replace
the one we had in inet_frags_fini()

We also have to fix a potential problem at module removal :
inet_frags_fini() needs to make sure that all queued work queues
(fqdir_rwork_fn) have completed, otherwise we might
call kmem_cache_destroy() too soon and get another use-after-free.

[1]
BUG: KASAN: use-after-free in inet_frag_destroy_rcu+0xd9/0xe0 net/ipv4/inet_fragment.c:201
Read of size 8 at addr ffff88806ed47a18 by task swapper/1/0

CPU: 1 PID: 0 Comm: swapper/1 Not tainted 5.2.0-rc1+ #2
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 <IRQ>
 __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
 inet_frag_destroy_rcu+0xd9/0xe0 net/ipv4/inet_fragment.c:201
 __rcu_reclaim kernel/rcu/rcu.h:222 [inline]
 rcu_do_batch kernel/rcu/tree.c:2092 [inline]
 invoke_rcu_callbacks kernel/rcu/tree.c:2310 [inline]
 rcu_core+0xba5/0x1500 kernel/rcu/tree.c:2291
 __do_softirq+0x25c/0x94c kernel/softirq.c:293
 invoke_softirq kernel/softirq.c:374 [inline]
 irq_exit+0x180/0x1d0 kernel/softirq.c:414
 exiting_irq arch/x86/include/asm/apic.h:536 [inline]
 smp_apic_timer_interrupt+0x13b/0x550 arch/x86/kernel/apic/apic.c:1068
 apic_timer_interrupt+0xf/0x20 arch/x86/entry/entry_64.S:806
 </IRQ>
RIP: 0010:native_safe_halt+0xe/0x10 arch/x86/include/asm/irqflags.h:61
Code: ff ff 48 89 df e8 f2 95 8c fa eb 82 e9 07 00 00 00 0f 00 2d e4 45 4b 00 f4 c3 66 90 e9 07 00 00 00 0f 00 2d d4 45 4b 00 fb f4 <c3> 90 55 48 89 e5 41 57 41 56 41 55 41 54 53 e8 8e 18 42 fa e8 99
RSP: 0018:ffff8880a98e7d78 EFLAGS: 00000282 ORIG_RAX: ffffffffffffff13
RAX: 1ffffffff1164e11 RBX: ffff8880a98d4340 RCX: 0000000000000000
RDX: dffffc0000000000 RSI: 0000000000000006 RDI: ffff8880a98d4bbc
RBP: ffff8880a98e7da8 R08: ffff8880a98d4340 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000001
R13: ffffffff88b27078 R14: 0000000000000001 R15: 0000000000000000
 arch_cpu_idle+0xa/0x10 arch/x86/kernel/process.c:571
 default_idle_call+0x36/0x90 kernel/sched/idle.c:94
 cpuidle_idle_call kernel/sched/idle.c:154 [inline]
 do_idle+0x377/0x560 kernel/sched/idle.c:263
 cpu_startup_entry+0x1b/0x20 kernel/sched/idle.c:354
 start_secondary+0x34e/0x4c0 arch/x86/kernel/smpboot.c:267
 secondary_startup_64+0xa4/0xb0 arch/x86/kernel/head_64.S:243

Allocated by task 8877:
 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
 kmem_cache_alloc_trace+0x151/0x750 mm/slab.c:3555
 kmalloc include/linux/slab.h:547 [inline]
 kzalloc include/linux/slab.h:742 [inline]
 fqdir_init include/net/inet_frag.h:115 [inline]
 ipv6_frags_init_net+0x48/0x460 net/ipv6/reassembly.c:513
 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 17:
 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
 fqdir_rwork_fn+0x33/0x40 net/ipv4/inet_fragment.c:154
 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 ffff88806ed47a00
 which belongs to the cache kmalloc-512 of size 512
The buggy address is located 24 bytes inside of
 512-byte region [ffff88806ed47a00, ffff88806ed47c00)
The buggy address belongs to the page:
page:ffffea0001bb51c0 refcount:1 mapcount:0 mapping:ffff8880aa400940 index:0x0
flags: 0x1fffc0000000200(slab)
raw: 01fffc0000000200 ffffea000282a788 ffffea0001bb53c8 ffff8880aa400940
raw: 0000000000000000 ffff88806ed47000 0000000100000006 0000000000000000
page dumped because: kasan: bad access detected

Memory state around the buggy address:
 ffff88806ed47900: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
 ffff88806ed47980: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
>ffff88806ed47a00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
                            ^
 ffff88806ed47a80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
 ffff88806ed47b00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb

Fixes: 3c8fc87820 ("inet: frags: rework rhashtable dismantle")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2019-05-28 17:22:15 -07:00

172 lines
4.6 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef __NET_FRAG_H__
#define __NET_FRAG_H__
#include <linux/rhashtable-types.h>
#include <linux/completion.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;
refcount_t refcnt;
struct completion completion;
};
int inet_frags_init(struct inet_frags *);
void inet_frags_fini(struct inet_frags *);
int fqdir_init(struct fqdir **fqdirp, struct inet_frags *f, struct net *net);
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