Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > linux.kernel > #1535391 > unrolled thread

net: use-after-free in worker_thread

Started byAndrey Konovalov <andreyknvl@google.com>
First post2016-12-03 14:00 +0100
Last post2016-12-05 08:30 +0100
Articles 13 — 5 participants

Back to article view | Back to linux.kernel

Contents

  net: use-after-free in worker_thread Andrey Konovalov <andreyknvl@google.com> - 2016-12-03 14:00 +0100
    Re: net: use-after-free in worker_thread Andrey Konovalov <andreyknvl@google.com> - 2016-12-03 14:10 +0100
      Re: net: use-after-free in worker_thread Eric Dumazet <eric.dumazet@gmail.com> - 2016-12-03 15:00 +0100
        Re: net: use-after-free in worker_thread Andrey Konovalov <andreyknvl@google.com> - 2016-12-03 16:40 +0100
        Re: net: use-after-free in worker_thread Herbert Xu <herbert@gondor.apana.org.au> - 2016-12-05 08:30 +0100
    Re: net: use-after-free in worker_thread Andrey Konovalov <andreyknvl@google.com> - 2016-12-03 14:10 +0100
    Re: net: use-after-free in worker_thread Cong Wang <xiyou.wangcong@gmail.com> - 2016-12-03 18:50 +0100
      Re: net: use-after-free in worker_thread Cong Wang <xiyou.wangcong@gmail.com> - 2016-12-03 19:20 +0100
        [v2 PATCH] netlink: Do not schedule work from sk_destruct Herbert Xu <herbert@gondor.apana.org.au> - 2016-12-05 08:30 +0100
          [v3 PATCH] netlink: Do not schedule work from sk_destruct Herbert Xu <herbert@gondor.apana.org.au> - 2016-12-05 09:10 +0100
            Re: [v3 PATCH] netlink: Do not schedule work from sk_destruct Andrey Konovalov <andreyknvl@google.com> - 2016-12-05 13:00 +0100
            Re: [v3 PATCH] netlink: Do not schedule work from sk_destruct David Miller <davem@davemloft.net> - 2016-12-06 01:50 +0100
        Re: net: use-after-free in worker_thread Herbert Xu <herbert@gondor.apana.org.au> - 2016-12-05 08:30 +0100

#1535391 — net: use-after-free in worker_thread

FromAndrey Konovalov <andreyknvl@google.com>
Date2016-12-03 14:00 +0100
Subjectnet: use-after-free in worker_thread
Message-ID<sKi54-1eT-9@gated-at.bofh.it>
Hi!

I'm seeing lots of the following error reports while running the
syzkaller fuzzer.

Reports appeared when I updated to 3c49de52 (Dec 2) from 2caceb32 (Dec 1).

==================================================================
BUG: KASAN: use-after-free in worker_thread+0x17d8/0x18a0
Read of size 8 at addr ffff880067f3ecd8 by task kworker/3:1/774

page:ffffea00019fce00 count:1 mapcount:0 mapping:          (null)
index:0xffff880067f39c10 compound_mapcount: 0
flags: 0x500000000004080(slab|head)
page dumped because: kasan: bad access detected

CPU: 3 PID: 774 Comm: kworker/3:1 Not tainted 4.9.0-rc7+ #66
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011
 ffff88006c267838 ffffffff81f882da ffffffff6c25e338 1ffff1000d84ce9a
 ffffed000d84ce92 ffff88006c25e340 0000000041b58ab3 ffffffff8541e198
 ffffffff81f88048 0000000100000000 0000000041b58ab3 ffffffff853d3ee8
Call Trace:
 [<     inline     >] __dump_stack lib/dump_stack.c:15
 [<ffffffff81f882da>] dump_stack+0x292/0x398 lib/dump_stack.c:51
 [<     inline     >] describe_address mm/kasan/report.c:262
 [<ffffffff817e50d1>] kasan_report_error+0x121/0x560 mm/kasan/report.c:368
 [<     inline     >] kasan_report mm/kasan/report.c:390
 [<ffffffff817e560e>] __asan_report_load8_noabort+0x3e/0x40
mm/kasan/report.c:411
 [<ffffffff81329b88>] worker_thread+0x17d8/0x18a0 kernel/workqueue.c:2228
 [<ffffffff8133ebf3>] kthread+0x323/0x3e0 kernel/kthread.c:209
 [<ffffffff84a2a22a>] ret_from_fork+0x2a/0x40 arch/x86/entry/entry_64.S:433

The buggy address belongs to the object at ffff880067f3e6d0
 which belongs to the cache kmalloc-2048 of size 2048
The buggy address ffff880067f3ecd8 is located 1544 bytes inside
 of 2048-byte region [ffff880067f3e6d0, ffff880067f3eed0)

Freed by task 0:
 [<ffffffff81203526>] save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:57
 [<ffffffff817e4173>] save_stack+0x43/0xd0 mm/kasan/kasan.c:495
 [<     inline     >] set_track mm/kasan/kasan.c:507
 [<ffffffff817e4a53>] kasan_slab_free+0x73/0xc0 mm/kasan/kasan.c:571
 [<     inline     >] slab_free_hook mm/slub.c:1352
 [<     inline     >] slab_free_freelist_hook mm/slub.c:1374
 [<     inline     >] slab_free mm/slub.c:2951
 [<ffffffff817e0eb7>] kfree+0xe7/0x2b0 mm/slub.c:3871
 [<     inline     >] sk_prot_free net/core/sock.c:1372
 [<ffffffff831ea1c7>] __sk_destruct+0x5c7/0x6e0 net/core/sock.c:1445
 [<ffffffff831f3517>] sk_destruct+0x47/0x80 net/core/sock.c:1453
 [<ffffffff831f35a7>] __sk_free+0x57/0x230 net/core/sock.c:1461
 [<ffffffff831f37a3>] sk_free+0x23/0x30 net/core/sock.c:1472
 [<     inline     >] sock_put include/net/sock.h:1591
 [<ffffffff8348ca9c>] deferred_put_nlk_sk+0x2c/0x40 net/netlink/af_netlink.c:671
 [<     inline     >] __rcu_reclaim kernel/rcu/rcu.h:118
 [<ffffffff8146d42f>] rcu_do_batch.isra.67+0x8ff/0xc50 kernel/rcu/tree.c:2776
 [<     inline     >] invoke_rcu_callbacks kernel/rcu/tree.c:3040
 [<     inline     >] __rcu_process_callbacks kernel/rcu/tree.c:3007
 [<ffffffff8146e097>] rcu_process_callbacks+0x2b7/0xba0 kernel/rcu/tree.c:3024
 [<ffffffff84a2d08b>] __do_softirq+0x2fb/0xb63 kernel/softirq.c:284

Allocated by task 10748:
 [<ffffffff81203526>] save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:57
 [<ffffffff817e4173>] save_stack+0x43/0xd0 mm/kasan/kasan.c:495
 [<     inline     >] set_track mm/kasan/kasan.c:507
 [<ffffffff817e43fd>] kasan_kmalloc+0xad/0xe0 mm/kasan/kasan.c:598
 [<ffffffff817e0050>] __kmalloc+0xa0/0x2d0 mm/slub.c:3734
 [<     inline     >] kmalloc include/linux/slab.h:495
 [<ffffffff831e4c01>] sk_prot_alloc+0x101/0x2a0 net/core/sock.c:1333
 [<ffffffff831efd15>] sk_alloc+0x105/0x1000 net/core/sock.c:1389
 [<ffffffff8348ad46>] __netlink_create+0x66/0x1d0 net/netlink/af_netlink.c:588
 [<ffffffff8348cdab>] netlink_create+0x2fb/0x500 net/netlink/af_netlink.c:647
 [<ffffffff831dd1d6>] __sock_create+0x4f6/0x880 net/socket.c:1168
 [<     inline     >] sock_create net/socket.c:1208
 [<     inline     >] SYSC_socket net/socket.c:1238
 [<ffffffff831dd799>] SyS_socket+0xf9/0x230 net/socket.c:1218
 [<ffffffff84a29fc1>] entry_SYSCALL_64_fastpath+0x1f/0xc2

Memory state around the buggy address:
 ffff880067f3eb80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
 ffff880067f3ec00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
>ffff880067f3ec80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
                                                    ^
 ffff880067f3ed00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
 ffff880067f3ed80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
==================================================================

[toc] | [next] | [standalone]

#1535394

FromAndrey Konovalov <andreyknvl@google.com>
Date2016-12-03 14:10 +0100
Message-ID<sKieK-1BX-23@gated-at.bofh.it>
In reply to#1535391
On Sat, Dec 3, 2016 at 1:58 PM, Andrey Konovalov <andreyknvl@google.com> wrote:
> +syzkaller@googlegroups.com
>
> On Sat, Dec 3, 2016 at 1:56 PM, Andrey Konovalov <andreyknvl@google.com> wrote:
>> Hi!
>>
>> I'm seeing lots of the following error reports while running the
>> syzkaller fuzzer.
>>
>> Reports appeared when I updated to 3c49de52 (Dec 2) from 2caceb32 (Dec 1).
>>
>> ==================================================================
>> BUG: KASAN: use-after-free in worker_thread+0x17d8/0x18a0
>> Read of size 8 at addr ffff880067f3ecd8 by task kworker/3:1/774
>>
>> page:ffffea00019fce00 count:1 mapcount:0 mapping:          (null)
>> index:0xffff880067f39c10 compound_mapcount: 0
>> flags: 0x500000000004080(slab|head)
>> page dumped because: kasan: bad access detected
>>
>> CPU: 3 PID: 774 Comm: kworker/3:1 Not tainted 4.9.0-rc7+ #66
>> Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011
>>  ffff88006c267838 ffffffff81f882da ffffffff6c25e338 1ffff1000d84ce9a
>>  ffffed000d84ce92 ffff88006c25e340 0000000041b58ab3 ffffffff8541e198
>>  ffffffff81f88048 0000000100000000 0000000041b58ab3 ffffffff853d3ee8
>> Call Trace:
>>  [<     inline     >] __dump_stack lib/dump_stack.c:15
>>  [<ffffffff81f882da>] dump_stack+0x292/0x398 lib/dump_stack.c:51
>>  [<     inline     >] describe_address mm/kasan/report.c:262
>>  [<ffffffff817e50d1>] kasan_report_error+0x121/0x560 mm/kasan/report.c:368
>>  [<     inline     >] kasan_report mm/kasan/report.c:390
>>  [<ffffffff817e560e>] __asan_report_load8_noabort+0x3e/0x40
>> mm/kasan/report.c:411
>>  [<ffffffff81329b88>] worker_thread+0x17d8/0x18a0 kernel/workqueue.c:2228
>>  [<ffffffff8133ebf3>] kthread+0x323/0x3e0 kernel/kthread.c:209
>>  [<ffffffff84a2a22a>] ret_from_fork+0x2a/0x40 arch/x86/entry/entry_64.S:433
>>
>> The buggy address belongs to the object at ffff880067f3e6d0
>>  which belongs to the cache kmalloc-2048 of size 2048
>> The buggy address ffff880067f3ecd8 is located 1544 bytes inside
>>  of 2048-byte region [ffff880067f3e6d0, ffff880067f3eed0)
>>
>> Freed by task 0:
>>  [<ffffffff81203526>] save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:57
>>  [<ffffffff817e4173>] save_stack+0x43/0xd0 mm/kasan/kasan.c:495
>>  [<     inline     >] set_track mm/kasan/kasan.c:507
>>  [<ffffffff817e4a53>] kasan_slab_free+0x73/0xc0 mm/kasan/kasan.c:571
>>  [<     inline     >] slab_free_hook mm/slub.c:1352
>>  [<     inline     >] slab_free_freelist_hook mm/slub.c:1374
>>  [<     inline     >] slab_free mm/slub.c:2951
>>  [<ffffffff817e0eb7>] kfree+0xe7/0x2b0 mm/slub.c:3871
>>  [<     inline     >] sk_prot_free net/core/sock.c:1372
>>  [<ffffffff831ea1c7>] __sk_destruct+0x5c7/0x6e0 net/core/sock.c:1445
>>  [<ffffffff831f3517>] sk_destruct+0x47/0x80 net/core/sock.c:1453
>>  [<ffffffff831f35a7>] __sk_free+0x57/0x230 net/core/sock.c:1461
>>  [<ffffffff831f37a3>] sk_free+0x23/0x30 net/core/sock.c:1472
>>  [<     inline     >] sock_put include/net/sock.h:1591
>>  [<ffffffff8348ca9c>] deferred_put_nlk_sk+0x2c/0x40 net/netlink/af_netlink.c:671
>>  [<     inline     >] __rcu_reclaim kernel/rcu/rcu.h:118
>>  [<ffffffff8146d42f>] rcu_do_batch.isra.67+0x8ff/0xc50 kernel/rcu/tree.c:2776
>>  [<     inline     >] invoke_rcu_callbacks kernel/rcu/tree.c:3040
>>  [<     inline     >] __rcu_process_callbacks kernel/rcu/tree.c:3007
>>  [<ffffffff8146e097>] rcu_process_callbacks+0x2b7/0xba0 kernel/rcu/tree.c:3024
>>  [<ffffffff84a2d08b>] __do_softirq+0x2fb/0xb63 kernel/softirq.c:284
>>
>> Allocated by task 10748:
>>  [<ffffffff81203526>] save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:57
>>  [<ffffffff817e4173>] save_stack+0x43/0xd0 mm/kasan/kasan.c:495
>>  [<     inline     >] set_track mm/kasan/kasan.c:507
>>  [<ffffffff817e43fd>] kasan_kmalloc+0xad/0xe0 mm/kasan/kasan.c:598
>>  [<ffffffff817e0050>] __kmalloc+0xa0/0x2d0 mm/slub.c:3734
>>  [<     inline     >] kmalloc include/linux/slab.h:495
>>  [<ffffffff831e4c01>] sk_prot_alloc+0x101/0x2a0 net/core/sock.c:1333
>>  [<ffffffff831efd15>] sk_alloc+0x105/0x1000 net/core/sock.c:1389
>>  [<ffffffff8348ad46>] __netlink_create+0x66/0x1d0 net/netlink/af_netlink.c:588
>>  [<ffffffff8348cdab>] netlink_create+0x2fb/0x500 net/netlink/af_netlink.c:647
>>  [<ffffffff831dd1d6>] __sock_create+0x4f6/0x880 net/socket.c:1168
>>  [<     inline     >] sock_create net/socket.c:1208
>>  [<     inline     >] SYSC_socket net/socket.c:1238
>>  [<ffffffff831dd799>] SyS_socket+0xf9/0x230 net/socket.c:1218
>>  [<ffffffff84a29fc1>] entry_SYSCALL_64_fastpath+0x1f/0xc2
>>
>> Memory state around the buggy address:
>>  ffff880067f3eb80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
>>  ffff880067f3ec00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
>>>ffff880067f3ec80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
>>                                                     ^
>>  ffff880067f3ed00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
>>  ffff880067f3ed80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
>> ==================================================================

Here is another report that looks related:

==================================================================
BUG: KASAN: use-after-free in __list_add+0x236/0x2c0
Read of size 8 at addr ffff880068854780 by task ksoftirqd/2/20

page:ffffea0001a21400 count:1 mapcount:0 mapping:          (null)
index:0x0 compound_mapcount: 0
flags: 0x500000000004080(slab|head)
page dumped because: kasan: bad access detected

CPU: 2 PID: 20 Comm: ksoftirqd/2 Not tainted 4.9.0-rc7+ #66
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011
 ffff88006daf6578 ffffffff81f882da ffffffff6daf62a0 1ffff1000db5ec42
 ffffed000db5ec3a dffffc0000000000 0000000041b58ab3 ffffffff8541e198
 ffffffff81f88048 ffff88006dac3610 ffff88006daf6300 0000000000000802
Call Trace:
 [<     inline     >] __dump_stack lib/dump_stack.c:15
 [<ffffffff81f882da>] dump_stack+0x292/0x398 lib/dump_stack.c:51
 [<     inline     >] describe_address mm/kasan/report.c:262
 [<ffffffff817e50d1>] kasan_report_error+0x121/0x560 mm/kasan/report.c:368
 [<     inline     >] kasan_report mm/kasan/report.c:390
 [<ffffffff817e560e>] __asan_report_load8_noabort+0x3e/0x40
mm/kasan/report.c:411
 [<ffffffff8200c166>] __list_add+0x236/0x2c0 lib/list_debug.c:30
 [<     inline     >] list_add_tail include/linux/list.h:77
 [<ffffffff8131e295>] insert_work+0x175/0x4b0 kernel/workqueue.c:1298
 [<ffffffff8131eb52>] __queue_work+0x582/0x11e0 kernel/workqueue.c:1459
 [<ffffffff81320c21>] queue_work_on+0x231/0x240 kernel/workqueue.c:1484
 [<     inline     >] queue_work include/linux/workqueue.h:474
 [<     inline     >] schedule_work include/linux/workqueue.h:532
 [<ffffffff8348c8cc>] netlink_sock_destruct+0x23c/0x2d0
net/netlink/af_netlink.c:361
 [<ffffffff831e9ce1>] __sk_destruct+0xe1/0x6e0 net/core/sock.c:1423
 [<ffffffff831f3517>] sk_destruct+0x47/0x80 net/core/sock.c:1453
 [<ffffffff831f35a7>] __sk_free+0x57/0x230 net/core/sock.c:1461
 [<ffffffff831f37a3>] sk_free+0x23/0x30 net/core/sock.c:1472
 [<     inline     >] sock_put include/net/sock.h:1591
 [<ffffffff8348ca9c>] deferred_put_nlk_sk+0x2c/0x40 net/netlink/af_netlink.c:671
 [<     inline     >] __rcu_reclaim kernel/rcu/rcu.h:118
 [<ffffffff8146d42f>] rcu_do_batch.isra.67+0x8ff/0xc50 kernel/rcu/tree.c:2776
 [<     inline     >] invoke_rcu_callbacks kernel/rcu/tree.c:3040
 [<     inline     >] __rcu_process_callbacks kernel/rcu/tree.c:3007
 [<ffffffff8146e097>] rcu_process_callbacks+0x2b7/0xba0 kernel/rcu/tree.c:3024
 [<ffffffff84a2d08b>] __do_softirq+0x2fb/0xb63 kernel/softirq.c:284
 [<ffffffff812d38c0>] run_ksoftirqd+0x20/0x60 kernel/softirq.c:676
 [<ffffffff81350132>] smpboot_thread_fn+0x562/0x860 kernel/smpboot.c:163
 [<ffffffff8133ebf3>] kthread+0x323/0x3e0 kernel/kthread.c:209
 [<ffffffff84a2a22a>] ret_from_fork+0x2a/0x40 arch/x86/entry/entry_64.S:433

The buggy address belongs to the object at ffff880068854170
 which belongs to the cache kmalloc-2048 of size 2048
The buggy address ffff880068854780 is located 1552 bytes inside
 of 2048-byte region [ffff880068854170, ffff880068854970)

Freed by task 20:
 [<ffffffff81203526>] save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:57
 [<ffffffff817e4173>] save_stack+0x43/0xd0 mm/kasan/kasan.c:495
 [<     inline     >] set_track mm/kasan/kasan.c:507
 [<ffffffff817e4a53>] kasan_slab_free+0x73/0xc0 mm/kasan/kasan.c:571
 [<     inline     >] slab_free_hook mm/slub.c:1352
 [<     inline     >] slab_free_freelist_hook mm/slub.c:1374
 [<     inline     >] slab_free mm/slub.c:2951
 [<ffffffff817e0eb7>] kfree+0xe7/0x2b0 mm/slub.c:3871
 [<     inline     >] sk_prot_free net/core/sock.c:1372
 [<ffffffff831ea1c7>] __sk_destruct+0x5c7/0x6e0 net/core/sock.c:1445
 [<ffffffff831f3517>] sk_destruct+0x47/0x80 net/core/sock.c:1453
 [<ffffffff831f35a7>] __sk_free+0x57/0x230 net/core/sock.c:1461
 [<ffffffff831f37a3>] sk_free+0x23/0x30 net/core/sock.c:1472
 [<     inline     >] sock_put include/net/sock.h:1591
 [<ffffffff8348ca9c>] deferred_put_nlk_sk+0x2c/0x40 net/netlink/af_netlink.c:671
 [<     inline     >] __rcu_reclaim kernel/rcu/rcu.h:118
 [<ffffffff8146d42f>] rcu_do_batch.isra.67+0x8ff/0xc50 kernel/rcu/tree.c:2776
 [<     inline     >] invoke_rcu_callbacks kernel/rcu/tree.c:3040
 [<     inline     >] __rcu_process_callbacks kernel/rcu/tree.c:3007
 [<ffffffff8146e097>] rcu_process_callbacks+0x2b7/0xba0 kernel/rcu/tree.c:3024
 [<ffffffff84a2d08b>] __do_softirq+0x2fb/0xb63 kernel/softirq.c:284

Allocated by task 9480:
 [<ffffffff81203526>] save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:57
 [<ffffffff817e4173>] save_stack+0x43/0xd0 mm/kasan/kasan.c:495
 [<     inline     >] set_track mm/kasan/kasan.c:507
 [<ffffffff817e43fd>] kasan_kmalloc+0xad/0xe0 mm/kasan/kasan.c:598
 [<ffffffff817e0050>] __kmalloc+0xa0/0x2d0 mm/slub.c:3734
 [<     inline     >] kmalloc include/linux/slab.h:495
 [<ffffffff831e4c01>] sk_prot_alloc+0x101/0x2a0 net/core/sock.c:1333
 [<ffffffff831efd15>] sk_alloc+0x105/0x1000 net/core/sock.c:1389
 [<ffffffff8348ad46>] __netlink_create+0x66/0x1d0 net/netlink/af_netlink.c:588
 [<ffffffff8348cdab>] netlink_create+0x2fb/0x500 net/netlink/af_netlink.c:647
 [<ffffffff831dd1d6>] __sock_create+0x4f6/0x880 net/socket.c:1168
 [<     inline     >] sock_create net/socket.c:1208
 [<     inline     >] SYSC_socket net/socket.c:1238
 [<ffffffff831dd799>] SyS_socket+0xf9/0x230 net/socket.c:1218
 [<ffffffff84a29fc1>] entry_SYSCALL_64_fastpath+0x1f/0xc2

Memory state around the buggy address:
 ffff880068854680: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
 ffff880068854700: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
>ffff880068854780: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
                   ^
 ffff880068854800: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
 ffff880068854880: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
==================================================================

[toc] | [prev] | [next] | [standalone]

#1535402

FromEric Dumazet <eric.dumazet@gmail.com>
Date2016-12-03 15:00 +0100
Message-ID<sKj17-24l-1@gated-at.bofh.it>
In reply to#1535394
On Sat, 2016-12-03 at 14:05 +0100, Andrey Konovalov wrote:
> On Sat, Dec 3, 2016 at 1:58 PM, Andrey Konovalov <andreyknvl@google.com> wrote:
> > +syzkaller@googlegroups.com
> >
> > On Sat, Dec 3, 2016 at 1:56 PM, Andrey Konovalov <andreyknvl@google.com> wrote:
> >> Hi!
> >>
> >> I'm seeing lots of the following error reports while running the
> >> syzkaller fuzzer.
> >>
> >> Reports appeared when I updated to 3c49de52 (Dec 2) from 2caceb32 (Dec 1).
> >>
> >> ==================================================================
> >> BUG: KASAN: use-after-free in worker_thread+0x17d8/0x18a0
> >> Read of size 8 at addr ffff880067f3ecd8 by task kworker/3:1/774
> >>
> >> page:ffffea00019fce00 count:1 mapcount:0 mapping:          (null)
> >> index:0xffff880067f39c10 compound_mapcount: 0
> >> flags: 0x500000000004080(slab|head)
> >> page dumped because: kasan: bad access detected
> >>
> >> CPU: 3 PID: 774 Comm: kworker/3:1 Not tainted 4.9.0-rc7+ #66
> >> Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011
> >>  ffff88006c267838 ffffffff81f882da ffffffff6c25e338 1ffff1000d84ce9a
> >>  ffffed000d84ce92 ffff88006c25e340 0000000041b58ab3 ffffffff8541e198
> >>  ffffffff81f88048 0000000100000000 0000000041b58ab3 ffffffff853d3ee8
> >> Call Trace:
> >>  [<     inline     >] __dump_stack lib/dump_stack.c:15
> >>  [<ffffffff81f882da>] dump_stack+0x292/0x398 lib/dump_stack.c:51
> >>  [<     inline     >] describe_address mm/kasan/report.c:262
> >>  [<ffffffff817e50d1>] kasan_report_error+0x121/0x560 mm/kasan/report.c:368
> >>  [<     inline     >] kasan_report mm/kasan/report.c:390
> >>  [<ffffffff817e560e>] __asan_report_load8_noabort+0x3e/0x40
> >> mm/kasan/report.c:411
> >>  [<ffffffff81329b88>] worker_thread+0x17d8/0x18a0 kernel/workqueue.c:2228
> >>  [<ffffffff8133ebf3>] kthread+0x323/0x3e0 kernel/kthread.c:209
> >>  [<ffffffff84a2a22a>] ret_from_fork+0x2a/0x40 arch/x86/entry/entry_64.S:433
> >>
> >> The buggy address belongs to the object at ffff880067f3e6d0
> >>  which belongs to the cache kmalloc-2048 of size 2048
> >> The buggy address ffff880067f3ecd8 is located 1544 bytes inside
> >>  of 2048-byte region [ffff880067f3e6d0, ffff880067f3eed0)
> >>
> >> Freed by task 0:
> >>  [<ffffffff81203526>] save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:57
> >>  [<ffffffff817e4173>] save_stack+0x43/0xd0 mm/kasan/kasan.c:495
> >>  [<     inline     >] set_track mm/kasan/kasan.c:507
> >>  [<ffffffff817e4a53>] kasan_slab_free+0x73/0xc0 mm/kasan/kasan.c:571
> >>  [<     inline     >] slab_free_hook mm/slub.c:1352
> >>  [<     inline     >] slab_free_freelist_hook mm/slub.c:1374
> >>  [<     inline     >] slab_free mm/slub.c:2951
> >>  [<ffffffff817e0eb7>] kfree+0xe7/0x2b0 mm/slub.c:3871
> >>  [<     inline     >] sk_prot_free net/core/sock.c:1372
> >>  [<ffffffff831ea1c7>] __sk_destruct+0x5c7/0x6e0 net/core/sock.c:1445
> >>  [<ffffffff831f3517>] sk_destruct+0x47/0x80 net/core/sock.c:1453
> >>  [<ffffffff831f35a7>] __sk_free+0x57/0x230 net/core/sock.c:1461
> >>  [<ffffffff831f37a3>] sk_free+0x23/0x30 net/core/sock.c:1472
> >>  [<     inline     >] sock_put include/net/sock.h:1591
> >>  [<ffffffff8348ca9c>] deferred_put_nlk_sk+0x2c/0x40 net/netlink/af_netlink.c:671
> >>  [<     inline     >] __rcu_reclaim kernel/rcu/rcu.h:118
> >>  [<ffffffff8146d42f>] rcu_do_batch.isra.67+0x8ff/0xc50 kernel/rcu/tree.c:2776
> >>  [<     inline     >] invoke_rcu_callbacks kernel/rcu/tree.c:3040
> >>  [<     inline     >] __rcu_process_callbacks kernel/rcu/tree.c:3007
> >>  [<ffffffff8146e097>] rcu_process_callbacks+0x2b7/0xba0 kernel/rcu/tree.c:3024
> >>  [<ffffffff84a2d08b>] __do_softirq+0x2fb/0xb63 kernel/softirq.c:284
> >>
> >> Allocated by task 10748:
> >>  [<ffffffff81203526>] save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:57
> >>  [<ffffffff817e4173>] save_stack+0x43/0xd0 mm/kasan/kasan.c:495
> >>  [<     inline     >] set_track mm/kasan/kasan.c:507
> >>  [<ffffffff817e43fd>] kasan_kmalloc+0xad/0xe0 mm/kasan/kasan.c:598
> >>  [<ffffffff817e0050>] __kmalloc+0xa0/0x2d0 mm/slub.c:3734
> >>  [<     inline     >] kmalloc include/linux/slab.h:495
> >>  [<ffffffff831e4c01>] sk_prot_alloc+0x101/0x2a0 net/core/sock.c:1333
> >>  [<ffffffff831efd15>] sk_alloc+0x105/0x1000 net/core/sock.c:1389
> >>  [<ffffffff8348ad46>] __netlink_create+0x66/0x1d0 net/netlink/af_netlink.c:588
> >>  [<ffffffff8348cdab>] netlink_create+0x2fb/0x500 net/netlink/af_netlink.c:647
> >>  [<ffffffff831dd1d6>] __sock_create+0x4f6/0x880 net/socket.c:1168
> >>  [<     inline     >] sock_create net/socket.c:1208
> >>  [<     inline     >] SYSC_socket net/socket.c:1238
> >>  [<ffffffff831dd799>] SyS_socket+0xf9/0x230 net/socket.c:1218
> >>  [<ffffffff84a29fc1>] entry_SYSCALL_64_fastpath+0x1f/0xc2
> >>
> >> Memory state around the buggy address:
> >>  ffff880067f3eb80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
> >>  ffff880067f3ec00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
> >>>ffff880067f3ec80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
> >>                                                     ^
> >>  ffff880067f3ed00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
> >>  ffff880067f3ed80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
> >> ==================================================================
> 
> Here is another report that looks related:
> 
> ==================================================================
> BUG: KASAN: use-after-free in __list_add+0x236/0x2c0
> Read of size 8 at addr ffff880068854780 by task ksoftirqd/2/20
> 
> page:ffffea0001a21400 count:1 mapcount:0 mapping:          (null)
> index:0x0 compound_mapcount: 0
> flags: 0x500000000004080(slab|head)
> page dumped because: kasan: bad access detected
> 
> CPU: 2 PID: 20 Comm: ksoftirqd/2 Not tainted 4.9.0-rc7+ #66
> Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011
>  ffff88006daf6578 ffffffff81f882da ffffffff6daf62a0 1ffff1000db5ec42
>  ffffed000db5ec3a dffffc0000000000 0000000041b58ab3 ffffffff8541e198
>  ffffffff81f88048 ffff88006dac3610 ffff88006daf6300 0000000000000802
> Call Trace:
>  [<     inline     >] __dump_stack lib/dump_stack.c:15
>  [<ffffffff81f882da>] dump_stack+0x292/0x398 lib/dump_stack.c:51
>  [<     inline     >] describe_address mm/kasan/report.c:262
>  [<ffffffff817e50d1>] kasan_report_error+0x121/0x560 mm/kasan/report.c:368
>  [<     inline     >] kasan_report mm/kasan/report.c:390
>  [<ffffffff817e560e>] __asan_report_load8_noabort+0x3e/0x40
> mm/kasan/report.c:411
>  [<ffffffff8200c166>] __list_add+0x236/0x2c0 lib/list_debug.c:30
>  [<     inline     >] list_add_tail include/linux/list.h:77
>  [<ffffffff8131e295>] insert_work+0x175/0x4b0 kernel/workqueue.c:1298
>  [<ffffffff8131eb52>] __queue_work+0x582/0x11e0 kernel/workqueue.c:1459
>  [<ffffffff81320c21>] queue_work_on+0x231/0x240 kernel/workqueue.c:1484
>  [<     inline     >] queue_work include/linux/workqueue.h:474
>  [<     inline     >] schedule_work include/linux/workqueue.h:532
>  [<ffffffff8348c8cc>] netlink_sock_destruct+0x23c/0x2d0
> net/netlink/af_netlink.c:361
>  [<ffffffff831e9ce1>] __sk_destruct+0xe1/0x6e0 net/core/sock.c:1423
>  [<ffffffff831f3517>] sk_destruct+0x47/0x80 net/core/sock.c:1453
>  [<ffffffff831f35a7>] __sk_free+0x57/0x230 net/core/sock.c:1461
>  [<ffffffff831f37a3>] sk_free+0x23/0x30 net/core/sock.c:1472
>  [<     inline     >] sock_put include/net/sock.h:1591
>  [<ffffffff8348ca9c>] deferred_put_nlk_sk+0x2c/0x40 net/netlink/af_netlink.c:671
>  [<     inline     >] __rcu_reclaim kernel/rcu/rcu.h:118
>  [<ffffffff8146d42f>] rcu_do_batch.isra.67+0x8ff/0xc50 kernel/rcu/tree.c:2776
>  [<     inline     >] invoke_rcu_callbacks kernel/rcu/tree.c:3040
>  [<     inline     >] __rcu_process_callbacks kernel/rcu/tree.c:3007
>  [<ffffffff8146e097>] rcu_process_callbacks+0x2b7/0xba0 kernel/rcu/tree.c:3024
>  [<ffffffff84a2d08b>] __do_softirq+0x2fb/0xb63 kernel/softirq.c:284
>  [<ffffffff812d38c0>] run_ksoftirqd+0x20/0x60 kernel/softirq.c:676
>  [<ffffffff81350132>] smpboot_thread_fn+0x562/0x860 kernel/smpboot.c:163
>  [<ffffffff8133ebf3>] kthread+0x323/0x3e0 kernel/kthread.c:209
>  [<ffffffff84a2a22a>] ret_from_fork+0x2a/0x40 arch/x86/entry/entry_64.S:433
> 
> The buggy address belongs to the object at ffff880068854170
>  which belongs to the cache kmalloc-2048 of size 2048
> The buggy address ffff880068854780 is located 1552 bytes inside
>  of 2048-byte region [ffff880068854170, ffff880068854970)
> 
> Freed by task 20:
>  [<ffffffff81203526>] save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:57
>  [<ffffffff817e4173>] save_stack+0x43/0xd0 mm/kasan/kasan.c:495
>  [<     inline     >] set_track mm/kasan/kasan.c:507
>  [<ffffffff817e4a53>] kasan_slab_free+0x73/0xc0 mm/kasan/kasan.c:571
>  [<     inline     >] slab_free_hook mm/slub.c:1352
>  [<     inline     >] slab_free_freelist_hook mm/slub.c:1374
>  [<     inline     >] slab_free mm/slub.c:2951
>  [<ffffffff817e0eb7>] kfree+0xe7/0x2b0 mm/slub.c:3871
>  [<     inline     >] sk_prot_free net/core/sock.c:1372
>  [<ffffffff831ea1c7>] __sk_destruct+0x5c7/0x6e0 net/core/sock.c:1445
>  [<ffffffff831f3517>] sk_destruct+0x47/0x80 net/core/sock.c:1453
>  [<ffffffff831f35a7>] __sk_free+0x57/0x230 net/core/sock.c:1461
>  [<ffffffff831f37a3>] sk_free+0x23/0x30 net/core/sock.c:1472
>  [<     inline     >] sock_put include/net/sock.h:1591
>  [<ffffffff8348ca9c>] deferred_put_nlk_sk+0x2c/0x40 net/netlink/af_netlink.c:671
>  [<     inline     >] __rcu_reclaim kernel/rcu/rcu.h:118
>  [<ffffffff8146d42f>] rcu_do_batch.isra.67+0x8ff/0xc50 kernel/rcu/tree.c:2776
>  [<     inline     >] invoke_rcu_callbacks kernel/rcu/tree.c:3040
>  [<     inline     >] __rcu_process_callbacks kernel/rcu/tree.c:3007
>  [<ffffffff8146e097>] rcu_process_callbacks+0x2b7/0xba0 kernel/rcu/tree.c:3024
>  [<ffffffff84a2d08b>] __do_softirq+0x2fb/0xb63 kernel/softirq.c:284
> 
> Allocated by task 9480:
>  [<ffffffff81203526>] save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:57
>  [<ffffffff817e4173>] save_stack+0x43/0xd0 mm/kasan/kasan.c:495
>  [<     inline     >] set_track mm/kasan/kasan.c:507
>  [<ffffffff817e43fd>] kasan_kmalloc+0xad/0xe0 mm/kasan/kasan.c:598
>  [<ffffffff817e0050>] __kmalloc+0xa0/0x2d0 mm/slub.c:3734
>  [<     inline     >] kmalloc include/linux/slab.h:495
>  [<ffffffff831e4c01>] sk_prot_alloc+0x101/0x2a0 net/core/sock.c:1333
>  [<ffffffff831efd15>] sk_alloc+0x105/0x1000 net/core/sock.c:1389
>  [<ffffffff8348ad46>] __netlink_create+0x66/0x1d0 net/netlink/af_netlink.c:588
>  [<ffffffff8348cdab>] netlink_create+0x2fb/0x500 net/netlink/af_netlink.c:647
>  [<ffffffff831dd1d6>] __sock_create+0x4f6/0x880 net/socket.c:1168
>  [<     inline     >] sock_create net/socket.c:1208
>  [<     inline     >] SYSC_socket net/socket.c:1238
>  [<ffffffff831dd799>] SyS_socket+0xf9/0x230 net/socket.c:1218
>  [<ffffffff84a29fc1>] entry_SYSCALL_64_fastpath+0x1f/0xc2
> 
> Memory state around the buggy address:
>  ffff880068854680: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
>  ffff880068854700: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
> >ffff880068854780: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
>                    ^
>  ffff880068854800: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
>  ffff880068854880: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
> ==================================================================


Hi Andrey. Please give us some rest during the week end ;)

This looks like the bug I mentioned earlier for which I have a pending
patch ? Can you try it ?

The RCU conversion done by Thomas was quite buggy.

Thanks.


diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 602e5ebe9db39ec6c72708628bc48efad9f0e680..c348c4a5ea4ecc05dcc9e2afbc069ab65a1a57fe 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -475,8 +475,8 @@ static struct sock *netlink_lookup(struct net *net, int protocol, u32 portid)
 
 	rcu_read_lock();
 	sk = __netlink_lookup(table, portid, net);
-	if (sk)
-		sock_hold(sk);
+	if (sk && !atomic_inc_not_zero(&sk->sk_refcnt))
+		sk = NULL;
 	rcu_read_unlock();
 
 	return sk;
@@ -600,6 +600,7 @@ static int __netlink_create(struct net *net, struct socket *sock,
 	}
 	init_waitqueue_head(&nlk->wait);
 
+	sock_set_flag(sk, SOCK_RCU_FREE);
 	sk->sk_destruct = netlink_sock_destruct;
 	sk->sk_protocol = protocol;
 	return 0;
@@ -664,13 +665,6 @@ static int netlink_create(struct net *net, struct socket *sock, int protocol,
 	goto out;
 }
 
-static void deferred_put_nlk_sk(struct rcu_head *head)
-{
-	struct netlink_sock *nlk = container_of(head, struct netlink_sock, rcu);
-
-	sock_put(&nlk->sk);
-}
-
 static int netlink_release(struct socket *sock)
 {
 	struct sock *sk = sock->sk;
@@ -743,7 +737,7 @@ static int netlink_release(struct socket *sock)
 	local_bh_disable();
 	sock_prot_inuse_add(sock_net(sk), &netlink_proto, -1);
 	local_bh_enable();
-	call_rcu(&nlk->rcu, deferred_put_nlk_sk);
+	sock_put(sk);
 	return 0;
 }
 
diff --git a/net/netlink/af_netlink.h b/net/netlink/af_netlink.h
index 4fdb3831897775547f77c069a8018c0d2a253c8c..988d1a02487e37b7efd4872dd0ab6d230e5a2021 100644
--- a/net/netlink/af_netlink.h
+++ b/net/netlink/af_netlink.h
@@ -33,7 +33,6 @@ struct netlink_sock {
 	struct module		*module;
 
 	struct rhash_head	node;
-	struct rcu_head		rcu;
 	struct work_struct	work;
 };

[toc] | [prev] | [next] | [standalone]

#1535440

FromAndrey Konovalov <andreyknvl@google.com>
Date2016-12-03 16:40 +0100
Message-ID<sKkzT-36C-7@gated-at.bofh.it>
In reply to#1535402

[Multipart message — attachments visible in raw view] — view raw

On Sat, Dec 3, 2016 at 2:49 PM, Eric Dumazet <eric.dumazet@gmail.com> wrote:
> On Sat, 2016-12-03 at 14:05 +0100, Andrey Konovalov wrote:
>> On Sat, Dec 3, 2016 at 1:58 PM, Andrey Konovalov <andreyknvl@google.com> wrote:
>> > +syzkaller@googlegroups.com
>> >
>> > On Sat, Dec 3, 2016 at 1:56 PM, Andrey Konovalov <andreyknvl@google.com> wrote:
>> >> Hi!
>> >>
>> >> I'm seeing lots of the following error reports while running the
>> >> syzkaller fuzzer.
>> >>
>> >> Reports appeared when I updated to 3c49de52 (Dec 2) from 2caceb32 (Dec 1).
>> >>
>> >> ==================================================================
>> >> BUG: KASAN: use-after-free in worker_thread+0x17d8/0x18a0
>> >> Read of size 8 at addr ffff880067f3ecd8 by task kworker/3:1/774
>> >>
>> >> page:ffffea00019fce00 count:1 mapcount:0 mapping:          (null)
>> >> index:0xffff880067f39c10 compound_mapcount: 0
>> >> flags: 0x500000000004080(slab|head)
>> >> page dumped because: kasan: bad access detected
>> >>
>> >> CPU: 3 PID: 774 Comm: kworker/3:1 Not tainted 4.9.0-rc7+ #66
>> >> Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011
>> >>  ffff88006c267838 ffffffff81f882da ffffffff6c25e338 1ffff1000d84ce9a
>> >>  ffffed000d84ce92 ffff88006c25e340 0000000041b58ab3 ffffffff8541e198
>> >>  ffffffff81f88048 0000000100000000 0000000041b58ab3 ffffffff853d3ee8
>> >> Call Trace:
>> >>  [<     inline     >] __dump_stack lib/dump_stack.c:15
>> >>  [<ffffffff81f882da>] dump_stack+0x292/0x398 lib/dump_stack.c:51
>> >>  [<     inline     >] describe_address mm/kasan/report.c:262
>> >>  [<ffffffff817e50d1>] kasan_report_error+0x121/0x560 mm/kasan/report.c:368
>> >>  [<     inline     >] kasan_report mm/kasan/report.c:390
>> >>  [<ffffffff817e560e>] __asan_report_load8_noabort+0x3e/0x40
>> >> mm/kasan/report.c:411
>> >>  [<ffffffff81329b88>] worker_thread+0x17d8/0x18a0 kernel/workqueue.c:2228
>> >>  [<ffffffff8133ebf3>] kthread+0x323/0x3e0 kernel/kthread.c:209
>> >>  [<ffffffff84a2a22a>] ret_from_fork+0x2a/0x40 arch/x86/entry/entry_64.S:433
>> >>
>> >> The buggy address belongs to the object at ffff880067f3e6d0
>> >>  which belongs to the cache kmalloc-2048 of size 2048
>> >> The buggy address ffff880067f3ecd8 is located 1544 bytes inside
>> >>  of 2048-byte region [ffff880067f3e6d0, ffff880067f3eed0)
>> >>
>> >> Freed by task 0:
>> >>  [<ffffffff81203526>] save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:57
>> >>  [<ffffffff817e4173>] save_stack+0x43/0xd0 mm/kasan/kasan.c:495
>> >>  [<     inline     >] set_track mm/kasan/kasan.c:507
>> >>  [<ffffffff817e4a53>] kasan_slab_free+0x73/0xc0 mm/kasan/kasan.c:571
>> >>  [<     inline     >] slab_free_hook mm/slub.c:1352
>> >>  [<     inline     >] slab_free_freelist_hook mm/slub.c:1374
>> >>  [<     inline     >] slab_free mm/slub.c:2951
>> >>  [<ffffffff817e0eb7>] kfree+0xe7/0x2b0 mm/slub.c:3871
>> >>  [<     inline     >] sk_prot_free net/core/sock.c:1372
>> >>  [<ffffffff831ea1c7>] __sk_destruct+0x5c7/0x6e0 net/core/sock.c:1445
>> >>  [<ffffffff831f3517>] sk_destruct+0x47/0x80 net/core/sock.c:1453
>> >>  [<ffffffff831f35a7>] __sk_free+0x57/0x230 net/core/sock.c:1461
>> >>  [<ffffffff831f37a3>] sk_free+0x23/0x30 net/core/sock.c:1472
>> >>  [<     inline     >] sock_put include/net/sock.h:1591
>> >>  [<ffffffff8348ca9c>] deferred_put_nlk_sk+0x2c/0x40 net/netlink/af_netlink.c:671
>> >>  [<     inline     >] __rcu_reclaim kernel/rcu/rcu.h:118
>> >>  [<ffffffff8146d42f>] rcu_do_batch.isra.67+0x8ff/0xc50 kernel/rcu/tree.c:2776
>> >>  [<     inline     >] invoke_rcu_callbacks kernel/rcu/tree.c:3040
>> >>  [<     inline     >] __rcu_process_callbacks kernel/rcu/tree.c:3007
>> >>  [<ffffffff8146e097>] rcu_process_callbacks+0x2b7/0xba0 kernel/rcu/tree.c:3024
>> >>  [<ffffffff84a2d08b>] __do_softirq+0x2fb/0xb63 kernel/softirq.c:284
>> >>
>> >> Allocated by task 10748:
>> >>  [<ffffffff81203526>] save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:57
>> >>  [<ffffffff817e4173>] save_stack+0x43/0xd0 mm/kasan/kasan.c:495
>> >>  [<     inline     >] set_track mm/kasan/kasan.c:507
>> >>  [<ffffffff817e43fd>] kasan_kmalloc+0xad/0xe0 mm/kasan/kasan.c:598
>> >>  [<ffffffff817e0050>] __kmalloc+0xa0/0x2d0 mm/slub.c:3734
>> >>  [<     inline     >] kmalloc include/linux/slab.h:495
>> >>  [<ffffffff831e4c01>] sk_prot_alloc+0x101/0x2a0 net/core/sock.c:1333
>> >>  [<ffffffff831efd15>] sk_alloc+0x105/0x1000 net/core/sock.c:1389
>> >>  [<ffffffff8348ad46>] __netlink_create+0x66/0x1d0 net/netlink/af_netlink.c:588
>> >>  [<ffffffff8348cdab>] netlink_create+0x2fb/0x500 net/netlink/af_netlink.c:647
>> >>  [<ffffffff831dd1d6>] __sock_create+0x4f6/0x880 net/socket.c:1168
>> >>  [<     inline     >] sock_create net/socket.c:1208
>> >>  [<     inline     >] SYSC_socket net/socket.c:1238
>> >>  [<ffffffff831dd799>] SyS_socket+0xf9/0x230 net/socket.c:1218
>> >>  [<ffffffff84a29fc1>] entry_SYSCALL_64_fastpath+0x1f/0xc2
>> >>
>> >> Memory state around the buggy address:
>> >>  ffff880067f3eb80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
>> >>  ffff880067f3ec00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
>> >>>ffff880067f3ec80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
>> >>                                                     ^
>> >>  ffff880067f3ed00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
>> >>  ffff880067f3ed80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
>> >> ==================================================================
>>
>> Here is another report that looks related:
>>
>> ==================================================================
>> BUG: KASAN: use-after-free in __list_add+0x236/0x2c0
>> Read of size 8 at addr ffff880068854780 by task ksoftirqd/2/20
>>
>> page:ffffea0001a21400 count:1 mapcount:0 mapping:          (null)
>> index:0x0 compound_mapcount: 0
>> flags: 0x500000000004080(slab|head)
>> page dumped because: kasan: bad access detected
>>
>> CPU: 2 PID: 20 Comm: ksoftirqd/2 Not tainted 4.9.0-rc7+ #66
>> Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011
>>  ffff88006daf6578 ffffffff81f882da ffffffff6daf62a0 1ffff1000db5ec42
>>  ffffed000db5ec3a dffffc0000000000 0000000041b58ab3 ffffffff8541e198
>>  ffffffff81f88048 ffff88006dac3610 ffff88006daf6300 0000000000000802
>> Call Trace:
>>  [<     inline     >] __dump_stack lib/dump_stack.c:15
>>  [<ffffffff81f882da>] dump_stack+0x292/0x398 lib/dump_stack.c:51
>>  [<     inline     >] describe_address mm/kasan/report.c:262
>>  [<ffffffff817e50d1>] kasan_report_error+0x121/0x560 mm/kasan/report.c:368
>>  [<     inline     >] kasan_report mm/kasan/report.c:390
>>  [<ffffffff817e560e>] __asan_report_load8_noabort+0x3e/0x40
>> mm/kasan/report.c:411
>>  [<ffffffff8200c166>] __list_add+0x236/0x2c0 lib/list_debug.c:30
>>  [<     inline     >] list_add_tail include/linux/list.h:77
>>  [<ffffffff8131e295>] insert_work+0x175/0x4b0 kernel/workqueue.c:1298
>>  [<ffffffff8131eb52>] __queue_work+0x582/0x11e0 kernel/workqueue.c:1459
>>  [<ffffffff81320c21>] queue_work_on+0x231/0x240 kernel/workqueue.c:1484
>>  [<     inline     >] queue_work include/linux/workqueue.h:474
>>  [<     inline     >] schedule_work include/linux/workqueue.h:532
>>  [<ffffffff8348c8cc>] netlink_sock_destruct+0x23c/0x2d0
>> net/netlink/af_netlink.c:361
>>  [<ffffffff831e9ce1>] __sk_destruct+0xe1/0x6e0 net/core/sock.c:1423
>>  [<ffffffff831f3517>] sk_destruct+0x47/0x80 net/core/sock.c:1453
>>  [<ffffffff831f35a7>] __sk_free+0x57/0x230 net/core/sock.c:1461
>>  [<ffffffff831f37a3>] sk_free+0x23/0x30 net/core/sock.c:1472
>>  [<     inline     >] sock_put include/net/sock.h:1591
>>  [<ffffffff8348ca9c>] deferred_put_nlk_sk+0x2c/0x40 net/netlink/af_netlink.c:671
>>  [<     inline     >] __rcu_reclaim kernel/rcu/rcu.h:118
>>  [<ffffffff8146d42f>] rcu_do_batch.isra.67+0x8ff/0xc50 kernel/rcu/tree.c:2776
>>  [<     inline     >] invoke_rcu_callbacks kernel/rcu/tree.c:3040
>>  [<     inline     >] __rcu_process_callbacks kernel/rcu/tree.c:3007
>>  [<ffffffff8146e097>] rcu_process_callbacks+0x2b7/0xba0 kernel/rcu/tree.c:3024
>>  [<ffffffff84a2d08b>] __do_softirq+0x2fb/0xb63 kernel/softirq.c:284
>>  [<ffffffff812d38c0>] run_ksoftirqd+0x20/0x60 kernel/softirq.c:676
>>  [<ffffffff81350132>] smpboot_thread_fn+0x562/0x860 kernel/smpboot.c:163
>>  [<ffffffff8133ebf3>] kthread+0x323/0x3e0 kernel/kthread.c:209
>>  [<ffffffff84a2a22a>] ret_from_fork+0x2a/0x40 arch/x86/entry/entry_64.S:433
>>
>> The buggy address belongs to the object at ffff880068854170
>>  which belongs to the cache kmalloc-2048 of size 2048
>> The buggy address ffff880068854780 is located 1552 bytes inside
>>  of 2048-byte region [ffff880068854170, ffff880068854970)
>>
>> Freed by task 20:
>>  [<ffffffff81203526>] save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:57
>>  [<ffffffff817e4173>] save_stack+0x43/0xd0 mm/kasan/kasan.c:495
>>  [<     inline     >] set_track mm/kasan/kasan.c:507
>>  [<ffffffff817e4a53>] kasan_slab_free+0x73/0xc0 mm/kasan/kasan.c:571
>>  [<     inline     >] slab_free_hook mm/slub.c:1352
>>  [<     inline     >] slab_free_freelist_hook mm/slub.c:1374
>>  [<     inline     >] slab_free mm/slub.c:2951
>>  [<ffffffff817e0eb7>] kfree+0xe7/0x2b0 mm/slub.c:3871
>>  [<     inline     >] sk_prot_free net/core/sock.c:1372
>>  [<ffffffff831ea1c7>] __sk_destruct+0x5c7/0x6e0 net/core/sock.c:1445
>>  [<ffffffff831f3517>] sk_destruct+0x47/0x80 net/core/sock.c:1453
>>  [<ffffffff831f35a7>] __sk_free+0x57/0x230 net/core/sock.c:1461
>>  [<ffffffff831f37a3>] sk_free+0x23/0x30 net/core/sock.c:1472
>>  [<     inline     >] sock_put include/net/sock.h:1591
>>  [<ffffffff8348ca9c>] deferred_put_nlk_sk+0x2c/0x40 net/netlink/af_netlink.c:671
>>  [<     inline     >] __rcu_reclaim kernel/rcu/rcu.h:118
>>  [<ffffffff8146d42f>] rcu_do_batch.isra.67+0x8ff/0xc50 kernel/rcu/tree.c:2776
>>  [<     inline     >] invoke_rcu_callbacks kernel/rcu/tree.c:3040
>>  [<     inline     >] __rcu_process_callbacks kernel/rcu/tree.c:3007
>>  [<ffffffff8146e097>] rcu_process_callbacks+0x2b7/0xba0 kernel/rcu/tree.c:3024
>>  [<ffffffff84a2d08b>] __do_softirq+0x2fb/0xb63 kernel/softirq.c:284
>>
>> Allocated by task 9480:
>>  [<ffffffff81203526>] save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:57
>>  [<ffffffff817e4173>] save_stack+0x43/0xd0 mm/kasan/kasan.c:495
>>  [<     inline     >] set_track mm/kasan/kasan.c:507
>>  [<ffffffff817e43fd>] kasan_kmalloc+0xad/0xe0 mm/kasan/kasan.c:598
>>  [<ffffffff817e0050>] __kmalloc+0xa0/0x2d0 mm/slub.c:3734
>>  [<     inline     >] kmalloc include/linux/slab.h:495
>>  [<ffffffff831e4c01>] sk_prot_alloc+0x101/0x2a0 net/core/sock.c:1333
>>  [<ffffffff831efd15>] sk_alloc+0x105/0x1000 net/core/sock.c:1389
>>  [<ffffffff8348ad46>] __netlink_create+0x66/0x1d0 net/netlink/af_netlink.c:588
>>  [<ffffffff8348cdab>] netlink_create+0x2fb/0x500 net/netlink/af_netlink.c:647
>>  [<ffffffff831dd1d6>] __sock_create+0x4f6/0x880 net/socket.c:1168
>>  [<     inline     >] sock_create net/socket.c:1208
>>  [<     inline     >] SYSC_socket net/socket.c:1238
>>  [<ffffffff831dd799>] SyS_socket+0xf9/0x230 net/socket.c:1218
>>  [<ffffffff84a29fc1>] entry_SYSCALL_64_fastpath+0x1f/0xc2
>>
>> Memory state around the buggy address:
>>  ffff880068854680: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
>>  ffff880068854700: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
>> >ffff880068854780: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
>>                    ^
>>  ffff880068854800: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
>>  ffff880068854880: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
>> ==================================================================
>
>
> Hi Andrey. Please give us some rest during the week end ;)

Hi Eric,

Sorry, wanted to restart fuzzer on newer kernel and immediately
started getting enormous amount of crashes :)

>
> This looks like the bug I mentioned earlier for which I have a pending
> patch ? Can you try it ?

No, it seems that your patch doesn't help, this is apparently something else.

I've attached a reproducer.

Thanks!

>
> The RCU conversion done by Thomas was quite buggy.
>
> Thanks.
>
>
> diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
> index 602e5ebe9db39ec6c72708628bc48efad9f0e680..c348c4a5ea4ecc05dcc9e2afbc069ab65a1a57fe 100644
> --- a/net/netlink/af_netlink.c
> +++ b/net/netlink/af_netlink.c
> @@ -475,8 +475,8 @@ static struct sock *netlink_lookup(struct net *net, int protocol, u32 portid)
>
>         rcu_read_lock();
>         sk = __netlink_lookup(table, portid, net);
> -       if (sk)
> -               sock_hold(sk);
> +       if (sk && !atomic_inc_not_zero(&sk->sk_refcnt))
> +               sk = NULL;
>         rcu_read_unlock();
>
>         return sk;
> @@ -600,6 +600,7 @@ static int __netlink_create(struct net *net, struct socket *sock,
>         }
>         init_waitqueue_head(&nlk->wait);
>
> +       sock_set_flag(sk, SOCK_RCU_FREE);
>         sk->sk_destruct = netlink_sock_destruct;
>         sk->sk_protocol = protocol;
>         return 0;
> @@ -664,13 +665,6 @@ static int netlink_create(struct net *net, struct socket *sock, int protocol,
>         goto out;
>  }
>
> -static void deferred_put_nlk_sk(struct rcu_head *head)
> -{
> -       struct netlink_sock *nlk = container_of(head, struct netlink_sock, rcu);
> -
> -       sock_put(&nlk->sk);
> -}
> -
>  static int netlink_release(struct socket *sock)
>  {
>         struct sock *sk = sock->sk;
> @@ -743,7 +737,7 @@ static int netlink_release(struct socket *sock)
>         local_bh_disable();
>         sock_prot_inuse_add(sock_net(sk), &netlink_proto, -1);
>         local_bh_enable();
> -       call_rcu(&nlk->rcu, deferred_put_nlk_sk);
> +       sock_put(sk);
>         return 0;
>  }
>
> diff --git a/net/netlink/af_netlink.h b/net/netlink/af_netlink.h
> index 4fdb3831897775547f77c069a8018c0d2a253c8c..988d1a02487e37b7efd4872dd0ab6d230e5a2021 100644
> --- a/net/netlink/af_netlink.h
> +++ b/net/netlink/af_netlink.h
> @@ -33,7 +33,6 @@ struct netlink_sock {
>         struct module           *module;
>
>         struct rhash_head       node;
> -       struct rcu_head         rcu;
>         struct work_struct      work;
>  };
>
>
>
>
> --
> You received this message because you are subscribed to the Google Groups "syzkaller" group.
> To unsubscribe from this group and stop receiving emails from it, send an email to syzkaller+unsubscribe@googlegroups.com.
> For more options, visit https://groups.google.com/d/optout.

[toc] | [prev] | [next] | [standalone]

#1535865

FromHerbert Xu <herbert@gondor.apana.org.au>
Date2016-12-05 08:30 +0100
Message-ID<sKVSN-1tp-13@gated-at.bofh.it>
In reply to#1535402
On Sat, Dec 03, 2016 at 05:49:07AM -0800, Eric Dumazet wrote:
>
> @@ -600,6 +600,7 @@ static int __netlink_create(struct net *net, struct socket *sock,
>  	}
>  	init_waitqueue_head(&nlk->wait);
>  
> +	sock_set_flag(sk, SOCK_RCU_FREE);
>  	sk->sk_destruct = netlink_sock_destruct;
>  	sk->sk_protocol = protocol;
>  	return 0;

It's not necessarily a big deal but I just wanted to point out
that SOCK_RCU_FREE is not equivalent to the call_rcu thing that
netlink does.  The latter only does the RCU deferral for the socket
release call which is the only place where it's needed while
SOCK_RCU_FREE will force every path to do an RCU deferral.

Cheers,
-- 
Email: Herbert Xu <herbert@gondor.apana.org.au>
Home Page: http://gondor.apana.org.au/~herbert/
PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txt

[toc] | [prev] | [next] | [standalone]

#1535396

FromAndrey Konovalov <andreyknvl@google.com>
Date2016-12-03 14:10 +0100
Message-ID<sKieK-1BX-19@gated-at.bofh.it>
In reply to#1535391
+syzkaller@googlegroups.com

On Sat, Dec 3, 2016 at 1:56 PM, Andrey Konovalov <andreyknvl@google.com> wrote:
> Hi!
>
> I'm seeing lots of the following error reports while running the
> syzkaller fuzzer.
>
> Reports appeared when I updated to 3c49de52 (Dec 2) from 2caceb32 (Dec 1).
>
> ==================================================================
> BUG: KASAN: use-after-free in worker_thread+0x17d8/0x18a0
> Read of size 8 at addr ffff880067f3ecd8 by task kworker/3:1/774
>
> page:ffffea00019fce00 count:1 mapcount:0 mapping:          (null)
> index:0xffff880067f39c10 compound_mapcount: 0
> flags: 0x500000000004080(slab|head)
> page dumped because: kasan: bad access detected
>
> CPU: 3 PID: 774 Comm: kworker/3:1 Not tainted 4.9.0-rc7+ #66
> Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011
>  ffff88006c267838 ffffffff81f882da ffffffff6c25e338 1ffff1000d84ce9a
>  ffffed000d84ce92 ffff88006c25e340 0000000041b58ab3 ffffffff8541e198
>  ffffffff81f88048 0000000100000000 0000000041b58ab3 ffffffff853d3ee8
> Call Trace:
>  [<     inline     >] __dump_stack lib/dump_stack.c:15
>  [<ffffffff81f882da>] dump_stack+0x292/0x398 lib/dump_stack.c:51
>  [<     inline     >] describe_address mm/kasan/report.c:262
>  [<ffffffff817e50d1>] kasan_report_error+0x121/0x560 mm/kasan/report.c:368
>  [<     inline     >] kasan_report mm/kasan/report.c:390
>  [<ffffffff817e560e>] __asan_report_load8_noabort+0x3e/0x40
> mm/kasan/report.c:411
>  [<ffffffff81329b88>] worker_thread+0x17d8/0x18a0 kernel/workqueue.c:2228
>  [<ffffffff8133ebf3>] kthread+0x323/0x3e0 kernel/kthread.c:209
>  [<ffffffff84a2a22a>] ret_from_fork+0x2a/0x40 arch/x86/entry/entry_64.S:433
>
> The buggy address belongs to the object at ffff880067f3e6d0
>  which belongs to the cache kmalloc-2048 of size 2048
> The buggy address ffff880067f3ecd8 is located 1544 bytes inside
>  of 2048-byte region [ffff880067f3e6d0, ffff880067f3eed0)
>
> Freed by task 0:
>  [<ffffffff81203526>] save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:57
>  [<ffffffff817e4173>] save_stack+0x43/0xd0 mm/kasan/kasan.c:495
>  [<     inline     >] set_track mm/kasan/kasan.c:507
>  [<ffffffff817e4a53>] kasan_slab_free+0x73/0xc0 mm/kasan/kasan.c:571
>  [<     inline     >] slab_free_hook mm/slub.c:1352
>  [<     inline     >] slab_free_freelist_hook mm/slub.c:1374
>  [<     inline     >] slab_free mm/slub.c:2951
>  [<ffffffff817e0eb7>] kfree+0xe7/0x2b0 mm/slub.c:3871
>  [<     inline     >] sk_prot_free net/core/sock.c:1372
>  [<ffffffff831ea1c7>] __sk_destruct+0x5c7/0x6e0 net/core/sock.c:1445
>  [<ffffffff831f3517>] sk_destruct+0x47/0x80 net/core/sock.c:1453
>  [<ffffffff831f35a7>] __sk_free+0x57/0x230 net/core/sock.c:1461
>  [<ffffffff831f37a3>] sk_free+0x23/0x30 net/core/sock.c:1472
>  [<     inline     >] sock_put include/net/sock.h:1591
>  [<ffffffff8348ca9c>] deferred_put_nlk_sk+0x2c/0x40 net/netlink/af_netlink.c:671
>  [<     inline     >] __rcu_reclaim kernel/rcu/rcu.h:118
>  [<ffffffff8146d42f>] rcu_do_batch.isra.67+0x8ff/0xc50 kernel/rcu/tree.c:2776
>  [<     inline     >] invoke_rcu_callbacks kernel/rcu/tree.c:3040
>  [<     inline     >] __rcu_process_callbacks kernel/rcu/tree.c:3007
>  [<ffffffff8146e097>] rcu_process_callbacks+0x2b7/0xba0 kernel/rcu/tree.c:3024
>  [<ffffffff84a2d08b>] __do_softirq+0x2fb/0xb63 kernel/softirq.c:284
>
> Allocated by task 10748:
>  [<ffffffff81203526>] save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:57
>  [<ffffffff817e4173>] save_stack+0x43/0xd0 mm/kasan/kasan.c:495
>  [<     inline     >] set_track mm/kasan/kasan.c:507
>  [<ffffffff817e43fd>] kasan_kmalloc+0xad/0xe0 mm/kasan/kasan.c:598
>  [<ffffffff817e0050>] __kmalloc+0xa0/0x2d0 mm/slub.c:3734
>  [<     inline     >] kmalloc include/linux/slab.h:495
>  [<ffffffff831e4c01>] sk_prot_alloc+0x101/0x2a0 net/core/sock.c:1333
>  [<ffffffff831efd15>] sk_alloc+0x105/0x1000 net/core/sock.c:1389
>  [<ffffffff8348ad46>] __netlink_create+0x66/0x1d0 net/netlink/af_netlink.c:588
>  [<ffffffff8348cdab>] netlink_create+0x2fb/0x500 net/netlink/af_netlink.c:647
>  [<ffffffff831dd1d6>] __sock_create+0x4f6/0x880 net/socket.c:1168
>  [<     inline     >] sock_create net/socket.c:1208
>  [<     inline     >] SYSC_socket net/socket.c:1238
>  [<ffffffff831dd799>] SyS_socket+0xf9/0x230 net/socket.c:1218
>  [<ffffffff84a29fc1>] entry_SYSCALL_64_fastpath+0x1f/0xc2
>
> Memory state around the buggy address:
>  ffff880067f3eb80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
>  ffff880067f3ec00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
>>ffff880067f3ec80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
>                                                     ^
>  ffff880067f3ed00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
>  ffff880067f3ed80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
> ==================================================================

[toc] | [prev] | [next] | [standalone]

#1535468

FromCong Wang <xiyou.wangcong@gmail.com>
Date2016-12-03 18:50 +0100
Message-ID<sKmBH-4kL-1@gated-at.bofh.it>
In reply to#1535391
On Sat, Dec 3, 2016 at 4:56 AM, Andrey Konovalov <andreyknvl@google.com> wrote:
> Hi!
>
> I'm seeing lots of the following error reports while running the
> syzkaller fuzzer.
>
> Reports appeared when I updated to 3c49de52 (Dec 2) from 2caceb32 (Dec 1).
>
> ==================================================================
> BUG: KASAN: use-after-free in worker_thread+0x17d8/0x18a0
> Read of size 8 at addr ffff880067f3ecd8 by task kworker/3:1/774
>
> page:ffffea00019fce00 count:1 mapcount:0 mapping:          (null)
> index:0xffff880067f39c10 compound_mapcount: 0
> flags: 0x500000000004080(slab|head)
> page dumped because: kasan: bad access detected
>
> CPU: 3 PID: 774 Comm: kworker/3:1 Not tainted 4.9.0-rc7+ #66
> Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011
>  ffff88006c267838 ffffffff81f882da ffffffff6c25e338 1ffff1000d84ce9a
>  ffffed000d84ce92 ffff88006c25e340 0000000041b58ab3 ffffffff8541e198
>  ffffffff81f88048 0000000100000000 0000000041b58ab3 ffffffff853d3ee8
> Call Trace:
>  [<     inline     >] __dump_stack lib/dump_stack.c:15
>  [<ffffffff81f882da>] dump_stack+0x292/0x398 lib/dump_stack.c:51
>  [<     inline     >] describe_address mm/kasan/report.c:262
>  [<ffffffff817e50d1>] kasan_report_error+0x121/0x560 mm/kasan/report.c:368
>  [<     inline     >] kasan_report mm/kasan/report.c:390
>  [<ffffffff817e560e>] __asan_report_load8_noabort+0x3e/0x40
> mm/kasan/report.c:411
>  [<ffffffff81329b88>] worker_thread+0x17d8/0x18a0 kernel/workqueue.c:2228
>  [<ffffffff8133ebf3>] kthread+0x323/0x3e0 kernel/kthread.c:209
>  [<ffffffff84a2a22a>] ret_from_fork+0x2a/0x40 arch/x86/entry/entry_64.S:433

Heck... this is the pending work vs. sk_destruct() race. :-/
We can't wait for the work in RCU callback, let me think about it...

[toc] | [prev] | [next] | [standalone]

#1535475

FromCong Wang <xiyou.wangcong@gmail.com>
Date2016-12-03 19:20 +0100
Message-ID<sKn4J-4LH-5@gated-at.bofh.it>
In reply to#1535468

[Multipart message — attachments visible in raw view] — view raw

On Sat, Dec 3, 2016 at 9:41 AM, Cong Wang <xiyou.wangcong@gmail.com> wrote:
> On Sat, Dec 3, 2016 at 4:56 AM, Andrey Konovalov <andreyknvl@google.com> wrote:
>> Hi!
>>
>> I'm seeing lots of the following error reports while running the
>> syzkaller fuzzer.
>>
>> Reports appeared when I updated to 3c49de52 (Dec 2) from 2caceb32 (Dec 1).
>>
>> ==================================================================
>> BUG: KASAN: use-after-free in worker_thread+0x17d8/0x18a0
>> Read of size 8 at addr ffff880067f3ecd8 by task kworker/3:1/774
>>
>> page:ffffea00019fce00 count:1 mapcount:0 mapping:          (null)
>> index:0xffff880067f39c10 compound_mapcount: 0
>> flags: 0x500000000004080(slab|head)
>> page dumped because: kasan: bad access detected
>>
>> CPU: 3 PID: 774 Comm: kworker/3:1 Not tainted 4.9.0-rc7+ #66
>> Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011
>>  ffff88006c267838 ffffffff81f882da ffffffff6c25e338 1ffff1000d84ce9a
>>  ffffed000d84ce92 ffff88006c25e340 0000000041b58ab3 ffffffff8541e198
>>  ffffffff81f88048 0000000100000000 0000000041b58ab3 ffffffff853d3ee8
>> Call Trace:
>>  [<     inline     >] __dump_stack lib/dump_stack.c:15
>>  [<ffffffff81f882da>] dump_stack+0x292/0x398 lib/dump_stack.c:51
>>  [<     inline     >] describe_address mm/kasan/report.c:262
>>  [<ffffffff817e50d1>] kasan_report_error+0x121/0x560 mm/kasan/report.c:368
>>  [<     inline     >] kasan_report mm/kasan/report.c:390
>>  [<ffffffff817e560e>] __asan_report_load8_noabort+0x3e/0x40
>> mm/kasan/report.c:411
>>  [<ffffffff81329b88>] worker_thread+0x17d8/0x18a0 kernel/workqueue.c:2228
>>  [<ffffffff8133ebf3>] kthread+0x323/0x3e0 kernel/kthread.c:209
>>  [<ffffffff84a2a22a>] ret_from_fork+0x2a/0x40 arch/x86/entry/entry_64.S:433
>
> Heck... this is the pending work vs. sk_destruct() race. :-/
> We can't wait for the work in RCU callback, let me think about it...

Please try the attached patch, I only did compile test, I can't access
my desktop now, so can't do further tests.

Thanks!

[toc] | [prev] | [next] | [standalone]

#1535863 — [v2 PATCH] netlink: Do not schedule work from sk_destruct

FromHerbert Xu <herbert@gondor.apana.org.au>
Date2016-12-05 08:30 +0100
Subject[v2 PATCH] netlink: Do not schedule work from sk_destruct
Message-ID<sKVSN-1tp-9@gated-at.bofh.it>
In reply to#1535475
On Mon, Dec 05, 2016 at 03:19:46PM +0800, Herbert Xu wrote:
>
> Thanks for the patch.  It'll obviously work but I wanted avoid that
> because it penalises the common path for the rare case.
> 
> Andrey, please try this patch and let me know if it's any better.
> 
> ---8<---
> Subject: netlink: Do not schedule work from sk_destruct

Crap, I screwed it up again.  Here is a v2 which moves the atomic
call into the RCU callback as otherwise the socket can be freed from
another path while we await the RCU callback.

---8<---
It is wrong to schedule a work from sk_destruct using the socket
as the memory reserve because the socket will be freed immediately
after the return from sk_destruct.

Instead we should do the deferral prior to sk_free.

This patch does just that.

Fixes: 707693c8a498 ("netlink: Call cb->done from a worker thread")
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 602e5eb..463f5cf 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -322,11 +322,13 @@ static void netlink_skb_set_owner_r(struct sk_buff *skb, struct sock *sk)
 	sk_mem_charge(sk, skb->truesize);
 }
 
-static void __netlink_sock_destruct(struct sock *sk)
+static void netlink_sock_destruct(struct sock *sk)
 {
 	struct netlink_sock *nlk = nlk_sk(sk);
 
 	if (nlk->cb_running) {
+		if (nlk->cb.done)
+			nlk->cb.done(&nlk->cb);
 		module_put(nlk->cb.module);
 		kfree_skb(nlk->cb.skb);
 	}
@@ -348,21 +350,7 @@ static void netlink_sock_destruct_work(struct work_struct *work)
 	struct netlink_sock *nlk = container_of(work, struct netlink_sock,
 						work);
 
-	nlk->cb.done(&nlk->cb);
-	__netlink_sock_destruct(&nlk->sk);
-}
-
-static void netlink_sock_destruct(struct sock *sk)
-{
-	struct netlink_sock *nlk = nlk_sk(sk);
-
-	if (nlk->cb_running && nlk->cb.done) {
-		INIT_WORK(&nlk->work, netlink_sock_destruct_work);
-		schedule_work(&nlk->work);
-		return;
-	}
-
-	__netlink_sock_destruct(sk);
+	sk_free(&nlk->sk);
 }
 
 /* This lock without WQ_FLAG_EXCLUSIVE is good on UP and it is _very_ bad on
@@ -664,11 +652,21 @@ static int netlink_create(struct net *net, struct socket *sock, int protocol,
 	goto out;
 }
 
-static void deferred_put_nlk_sk(struct rcu_head *head)
+static void deferred_free_nlk_sk(struct rcu_head *head)
 {
 	struct netlink_sock *nlk = container_of(head, struct netlink_sock, rcu);
+	struct sock *sk = &nlk->sk;
+
+	if (!atomic_dec_and_test(&sk->sk_refcnt))
+		return;
+
+	if (nlk->cb_running && nlk->cb.done) {
+		INIT_WORK(&nlk->work, netlink_sock_destruct_work);
+		schedule_work(&nlk->work);
+		return;
+	}
 
-	sock_put(&nlk->sk);
+	sk_free(sk);
 }
 
 static int netlink_release(struct socket *sock)
@@ -743,7 +741,7 @@ static int netlink_release(struct socket *sock)
 	local_bh_disable();
 	sock_prot_inuse_add(sock_net(sk), &netlink_proto, -1);
 	local_bh_enable();
-	call_rcu(&nlk->rcu, deferred_put_nlk_sk);
+	call_rcu(&nlk->rcu, deferred_free_nlk_sk);
 	return 0;
 }
 
-- 
Email: Herbert Xu <herbert@gondor.apana.org.au>
Home Page: http://gondor.apana.org.au/~herbert/
PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txt

[toc] | [prev] | [next] | [standalone]

#1535880 — [v3 PATCH] netlink: Do not schedule work from sk_destruct

FromHerbert Xu <herbert@gondor.apana.org.au>
Date2016-12-05 09:10 +0100
Subject[v3 PATCH] netlink: Do not schedule work from sk_destruct
Message-ID<sKWvw-1WP-9@gated-at.bofh.it>
In reply to#1535863
On Mon, Dec 05, 2016 at 03:26:00PM +0800, Herbert Xu wrote:
> On Mon, Dec 05, 2016 at 03:19:46PM +0800, Herbert Xu wrote:
> >
> > Thanks for the patch.  It'll obviously work but I wanted avoid that
> > because it penalises the common path for the rare case.
> > 
> > Andrey, please try this patch and let me know if it's any better.
> > 
> > ---8<---
> > Subject: netlink: Do not schedule work from sk_destruct
> 
> Crap, I screwed it up again.  Here is a v2 which moves the atomic
> call into the RCU callback as otherwise the socket can be freed from
> another path while we await the RCU callback.

With the move it no longer makes sense to rename deferred_put_nlk_sk
so here is v3 which restores the original name.

---8<---
It is wrong to schedule a work from sk_destruct using the socket
as the memory reserve because the socket will be freed immediately
after the return from sk_destruct.

Instead we should do the deferral prior to sk_free.

This patch does just that.

Fixes: 707693c8a498 ("netlink: Call cb->done from a worker thread")
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 602e5eb..246f29d 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -322,11 +322,13 @@ static void netlink_skb_set_owner_r(struct sk_buff *skb, struct sock *sk)
 	sk_mem_charge(sk, skb->truesize);
 }
 
-static void __netlink_sock_destruct(struct sock *sk)
+static void netlink_sock_destruct(struct sock *sk)
 {
 	struct netlink_sock *nlk = nlk_sk(sk);
 
 	if (nlk->cb_running) {
+		if (nlk->cb.done)
+			nlk->cb.done(&nlk->cb);
 		module_put(nlk->cb.module);
 		kfree_skb(nlk->cb.skb);
 	}
@@ -348,21 +350,7 @@ static void netlink_sock_destruct_work(struct work_struct *work)
 	struct netlink_sock *nlk = container_of(work, struct netlink_sock,
 						work);
 
-	nlk->cb.done(&nlk->cb);
-	__netlink_sock_destruct(&nlk->sk);
-}
-
-static void netlink_sock_destruct(struct sock *sk)
-{
-	struct netlink_sock *nlk = nlk_sk(sk);
-
-	if (nlk->cb_running && nlk->cb.done) {
-		INIT_WORK(&nlk->work, netlink_sock_destruct_work);
-		schedule_work(&nlk->work);
-		return;
-	}
-
-	__netlink_sock_destruct(sk);
+	sk_free(&nlk->sk);
 }
 
 /* This lock without WQ_FLAG_EXCLUSIVE is good on UP and it is _very_ bad on
@@ -667,8 +655,18 @@ static int netlink_create(struct net *net, struct socket *sock, int protocol,
 static void deferred_put_nlk_sk(struct rcu_head *head)
 {
 	struct netlink_sock *nlk = container_of(head, struct netlink_sock, rcu);
+	struct sock *sk = &nlk->sk;
+
+	if (!atomic_dec_and_test(&sk->sk_refcnt))
+		return;
+
+	if (nlk->cb_running && nlk->cb.done) {
+		INIT_WORK(&nlk->work, netlink_sock_destruct_work);
+		schedule_work(&nlk->work);
+		return;
+	}
 
-	sock_put(&nlk->sk);
+	sk_free(sk);
 }
 
 static int netlink_release(struct socket *sock)
-- 
Email: Herbert Xu <herbert@gondor.apana.org.au>
Home Page: http://gondor.apana.org.au/~herbert/
PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txt

[toc] | [prev] | [next] | [standalone]

#1536027 — Re: [v3 PATCH] netlink: Do not schedule work from sk_destruct

FromAndrey Konovalov <andreyknvl@google.com>
Date2016-12-05 13:00 +0100
SubjectRe: [v3 PATCH] netlink: Do not schedule work from sk_destruct
Message-ID<sL06d-437-89@gated-at.bofh.it>
In reply to#1535880
On Mon, Dec 5, 2016 at 8:28 AM, Herbert Xu <herbert@gondor.apana.org.au> wrote:
> On Mon, Dec 05, 2016 at 03:26:00PM +0800, Herbert Xu wrote:
>> On Mon, Dec 05, 2016 at 03:19:46PM +0800, Herbert Xu wrote:
>> >
>> > Thanks for the patch.  It'll obviously work but I wanted avoid that
>> > because it penalises the common path for the rare case.
>> >
>> > Andrey, please try this patch and let me know if it's any better.
>> >
>> > ---8<---
>> > Subject: netlink: Do not schedule work from sk_destruct
>>
>> Crap, I screwed it up again.  Here is a v2 which moves the atomic
>> call into the RCU callback as otherwise the socket can be freed from
>> another path while we await the RCU callback.
>
> With the move it no longer makes sense to rename deferred_put_nlk_sk
> so here is v3 which restores the original name.
>
> ---8<---
> It is wrong to schedule a work from sk_destruct using the socket
> as the memory reserve because the socket will be freed immediately
> after the return from sk_destruct.
>
> Instead we should do the deferral prior to sk_free.
>
> This patch does just that.
>
> Fixes: 707693c8a498 ("netlink: Call cb->done from a worker thread")
> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
>
> diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
> index 602e5eb..246f29d 100644
> --- a/net/netlink/af_netlink.c
> +++ b/net/netlink/af_netlink.c
> @@ -322,11 +322,13 @@ static void netlink_skb_set_owner_r(struct sk_buff *skb, struct sock *sk)
>         sk_mem_charge(sk, skb->truesize);
>  }
>
> -static void __netlink_sock_destruct(struct sock *sk)
> +static void netlink_sock_destruct(struct sock *sk)
>  {
>         struct netlink_sock *nlk = nlk_sk(sk);
>
>         if (nlk->cb_running) {
> +               if (nlk->cb.done)
> +                       nlk->cb.done(&nlk->cb);
>                 module_put(nlk->cb.module);
>                 kfree_skb(nlk->cb.skb);
>         }
> @@ -348,21 +350,7 @@ static void netlink_sock_destruct_work(struct work_struct *work)
>         struct netlink_sock *nlk = container_of(work, struct netlink_sock,
>                                                 work);
>
> -       nlk->cb.done(&nlk->cb);
> -       __netlink_sock_destruct(&nlk->sk);
> -}
> -
> -static void netlink_sock_destruct(struct sock *sk)
> -{
> -       struct netlink_sock *nlk = nlk_sk(sk);
> -
> -       if (nlk->cb_running && nlk->cb.done) {
> -               INIT_WORK(&nlk->work, netlink_sock_destruct_work);
> -               schedule_work(&nlk->work);
> -               return;
> -       }
> -
> -       __netlink_sock_destruct(sk);
> +       sk_free(&nlk->sk);
>  }
>
>  /* This lock without WQ_FLAG_EXCLUSIVE is good on UP and it is _very_ bad on
> @@ -667,8 +655,18 @@ static int netlink_create(struct net *net, struct socket *sock, int protocol,
>  static void deferred_put_nlk_sk(struct rcu_head *head)
>  {
>         struct netlink_sock *nlk = container_of(head, struct netlink_sock, rcu);
> +       struct sock *sk = &nlk->sk;
> +
> +       if (!atomic_dec_and_test(&sk->sk_refcnt))
> +               return;
> +
> +       if (nlk->cb_running && nlk->cb.done) {
> +               INIT_WORK(&nlk->work, netlink_sock_destruct_work);
> +               schedule_work(&nlk->work);
> +               return;
> +       }
>
> -       sock_put(&nlk->sk);
> +       sk_free(sk);
>  }
>
>  static int netlink_release(struct socket *sock)
> --
> Email: Herbert Xu <herbert@gondor.apana.org.au>
> Home Page: http://gondor.apana.org.au/~herbert/
> PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txt

Hi Herbert,

Tested the last version of your patch, the reports go away.

Thanks for the fix!

Tested-by: Andrey Konovalov <andreyknvl@google.com>

[toc] | [prev] | [next] | [standalone]

#1536565 — Re: [v3 PATCH] netlink: Do not schedule work from sk_destruct

FromDavid Miller <davem@davemloft.net>
Date2016-12-06 01:50 +0100
SubjectRe: [v3 PATCH] netlink: Do not schedule work from sk_destruct
Message-ID<sLc7f-3hn-1@gated-at.bofh.it>
In reply to#1535880
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Mon, 5 Dec 2016 15:28:21 +0800

> It is wrong to schedule a work from sk_destruct using the socket
> as the memory reserve because the socket will be freed immediately
> after the return from sk_destruct.
> 
> Instead we should do the deferral prior to sk_free.
> 
> This patch does just that.
> 
> Fixes: 707693c8a498 ("netlink: Call cb->done from a worker thread")
> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>

Applied, thanks Herbert.

[toc] | [prev] | [next] | [standalone]

#1535866

FromHerbert Xu <herbert@gondor.apana.org.au>
Date2016-12-05 08:30 +0100
Message-ID<sKVSN-1tp-11@gated-at.bofh.it>
In reply to#1535475
On Sat, Dec 03, 2016 at 10:14:48AM -0800, Cong Wang wrote:
> On Sat, Dec 3, 2016 at 9:41 AM, Cong Wang <xiyou.wangcong@gmail.com> wrote:
> > On Sat, Dec 3, 2016 at 4:56 AM, Andrey Konovalov <andreyknvl@google.com> wrote:
> >> Hi!
> >>
> >> I'm seeing lots of the following error reports while running the
> >> syzkaller fuzzer.
> >>
> >> Reports appeared when I updated to 3c49de52 (Dec 2) from 2caceb32 (Dec 1).
> >>
> >> ==================================================================
> >> BUG: KASAN: use-after-free in worker_thread+0x17d8/0x18a0
> >> Read of size 8 at addr ffff880067f3ecd8 by task kworker/3:1/774
> >>
> >> page:ffffea00019fce00 count:1 mapcount:0 mapping:          (null)
> >> index:0xffff880067f39c10 compound_mapcount: 0
> >> flags: 0x500000000004080(slab|head)
> >> page dumped because: kasan: bad access detected
> >>
> >> CPU: 3 PID: 774 Comm: kworker/3:1 Not tainted 4.9.0-rc7+ #66
> >> Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011
> >>  ffff88006c267838 ffffffff81f882da ffffffff6c25e338 1ffff1000d84ce9a
> >>  ffffed000d84ce92 ffff88006c25e340 0000000041b58ab3 ffffffff8541e198
> >>  ffffffff81f88048 0000000100000000 0000000041b58ab3 ffffffff853d3ee8
> >> Call Trace:
> >>  [<     inline     >] __dump_stack lib/dump_stack.c:15
> >>  [<ffffffff81f882da>] dump_stack+0x292/0x398 lib/dump_stack.c:51
> >>  [<     inline     >] describe_address mm/kasan/report.c:262
> >>  [<ffffffff817e50d1>] kasan_report_error+0x121/0x560 mm/kasan/report.c:368
> >>  [<     inline     >] kasan_report mm/kasan/report.c:390
> >>  [<ffffffff817e560e>] __asan_report_load8_noabort+0x3e/0x40
> >> mm/kasan/report.c:411
> >>  [<ffffffff81329b88>] worker_thread+0x17d8/0x18a0 kernel/workqueue.c:2228
> >>  [<ffffffff8133ebf3>] kthread+0x323/0x3e0 kernel/kthread.c:209
> >>  [<ffffffff84a2a22a>] ret_from_fork+0x2a/0x40 arch/x86/entry/entry_64.S:433
> >
> > Heck... this is the pending work vs. sk_destruct() race. :-/
> > We can't wait for the work in RCU callback, let me think about it...

Sorry, my patch was obviously crap as it was trying to delay the
freeing of a socket from sk_destruct which can't be done.

> Please try the attached patch, I only did compile test, I can't access
> my desktop now, so can't do further tests.

Thanks for the patch.  It'll obviously work but I wanted avoid that
because it penalises the common path for the rare case.

Andrey, please try this patch and let me know if it's any better.

---8<---
Subject: netlink: Do not schedule work from sk_destruct

It is wrong to schedule a work from sk_destruct using the socket
as the memory reserve because the socket will be freed immediately
after the return from sk_destruct.

Instead we should do the deferral prior to sk_free.

This patch does just that.

Fixes: 707693c8a498 ("netlink: Call cb->done from a worker thread")
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 602e5eb..8a642c5 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -322,11 +322,13 @@ static void netlink_skb_set_owner_r(struct sk_buff *skb, struct sock *sk)
 	sk_mem_charge(sk, skb->truesize);
 }
 
-static void __netlink_sock_destruct(struct sock *sk)
+static void netlink_sock_destruct(struct sock *sk)
 {
 	struct netlink_sock *nlk = nlk_sk(sk);
 
 	if (nlk->cb_running) {
+		if (nlk->cb.done)
+			nlk->cb.done(&nlk->cb);
 		module_put(nlk->cb.module);
 		kfree_skb(nlk->cb.skb);
 	}
@@ -348,21 +350,7 @@ static void netlink_sock_destruct_work(struct work_struct *work)
 	struct netlink_sock *nlk = container_of(work, struct netlink_sock,
 						work);
 
-	nlk->cb.done(&nlk->cb);
-	__netlink_sock_destruct(&nlk->sk);
-}
-
-static void netlink_sock_destruct(struct sock *sk)
-{
-	struct netlink_sock *nlk = nlk_sk(sk);
-
-	if (nlk->cb_running && nlk->cb.done) {
-		INIT_WORK(&nlk->work, netlink_sock_destruct_work);
-		schedule_work(&nlk->work);
-		return;
-	}
-
-	__netlink_sock_destruct(sk);
+	sk_free(&nlk->sk);
 }
 
 /* This lock without WQ_FLAG_EXCLUSIVE is good on UP and it is _very_ bad on
@@ -664,11 +652,17 @@ static int netlink_create(struct net *net, struct socket *sock, int protocol,
 	goto out;
 }
 
-static void deferred_put_nlk_sk(struct rcu_head *head)
+static void deferred_free_nlk_sk(struct rcu_head *head)
 {
 	struct netlink_sock *nlk = container_of(head, struct netlink_sock, rcu);
 
-	sock_put(&nlk->sk);
+	if (nlk->cb_running && nlk->cb.done) {
+		INIT_WORK(&nlk->work, netlink_sock_destruct_work);
+		schedule_work(&nlk->work);
+		return;
+	}
+
+	sk_free(&nlk->sk);
 }
 
 static int netlink_release(struct socket *sock)
@@ -743,7 +737,9 @@ static int netlink_release(struct socket *sock)
 	local_bh_disable();
 	sock_prot_inuse_add(sock_net(sk), &netlink_proto, -1);
 	local_bh_enable();
-	call_rcu(&nlk->rcu, deferred_put_nlk_sk);
+
+	if (atomic_dec_and_test(&sk->sk_refcnt))
+		call_rcu(&nlk->rcu, deferred_free_nlk_sk);
 	return 0;
 }
 
-- 
Email: Herbert Xu <herbert@gondor.apana.org.au>
Home Page: http://gondor.apana.org.au/~herbert/
PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txt

[toc] | [prev] | [standalone]

Back to top | Article view | linux.kernel

csiph-web