linux-kernel - Re: [PATCH] mm: migrate: fix data-race in migrate_folio

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <B1FCFC88-1242-4472-BCED-71BA9530B639@gmail.com>
Date: Tue, 24 Sep 2024 09:28:44 +0900
From: Jeongjun Park <aha310510@...il.com>
To: Matthew Wilcox <willy@...radead.org>
Cc: David Hildenbrand <david@...hat.com>, akpm@...ux-foundation.org,
 wangkefeng.wang@...wei.com, ziy@...dia.com, linux-mm@...ck.org,
 linux-kernel@...r.kernel.org, stable@...r.kernel.org,
 syzbot <syzkaller@...glegroups.com>
Subject: Re: [PATCH] mm: migrate: fix data-race in migrate_folio_unmap()



> Matthew Wilcox <willy@...radead.org> wrote:
> 
> On Mon, Sep 23, 2024 at 05:56:40PM +0200, David Hildenbrand wrote:
>>> On 22.09.24 17:17, Jeongjun Park wrote:
>>> I found a report from syzbot [1]
>>> 
>>> When __folio_test_movable() is called in migrate_folio_unmap() to read
>>> folio->mapping, a data race occurs because the folio is read without
>>> protecting it with folio_lock.
>>> 
>>> This can cause unintended behavior because folio->mapping is initialized
>>> to a NULL value. Therefore, I think it is appropriate to call
>>> __folio_test_movable() under the protection of folio_lock to prevent
>>> data-race.
>> 
>> We hold a folio reference, would we really see PAGE_MAPPING_MOVABLE flip?
>> Hmm
> 
> No; this shows a page cache folio getting truncated.  It's fine; really
> a false alarm from the tool.  I don't think the proposed patch
> introduces any problems, but it's all a bit meh.
> 

Well, I still don't understand why it's okay to read folio->mapping 
without folio_lock . Since migrate_folio_unmap() is already protected 
by folio_lock , I think it's definitely necessary to fix it to read 
folio->mapping under folio_lock protection. If it were still okay to 
call __folio_test_movable() without folio_lock , then we could 
annotate data-race, but I'm still not sure if this is a good way 
to do it.

Regards,
Jeongjun Park

>> Even a racing __ClearPageMovable() would still leave PAGE_MAPPING_MOVABLE
>> set.
>> 
>>> [1]
>>> 
>>> ==================================================================
>>> BUG: KCSAN: data-race in __filemap_remove_folio / migrate_pages_batch
>>> 
>>> write to 0xffffea0004b81dd8 of 8 bytes by task 6348 on cpu 0:
>>>  page_cache_delete mm/filemap.c:153 [inline]
>>>  __filemap_remove_folio+0x1ac/0x2c0 mm/filemap.c:233
>>>  filemap_remove_folio+0x6b/0x1f0 mm/filemap.c:265
>>>  truncate_inode_folio+0x42/0x50 mm/truncate.c:178
>>>  shmem_undo_range+0x25b/0xa70 mm/shmem.c:1028
>>>  shmem_truncate_range mm/shmem.c:1144 [inline]
>>>  shmem_evict_inode+0x14d/0x530 mm/shmem.c:1272
>>>  evict+0x2f0/0x580 fs/inode.c:731
>>>  iput_final fs/inode.c:1883 [inline]
>>>  iput+0x42a/0x5b0 fs/inode.c:1909
>>>  dentry_unlink_inode+0x24f/0x260 fs/dcache.c:412
>>>  __dentry_kill+0x18b/0x4c0 fs/dcache.c:615
>>>  dput+0x5c/0xd0 fs/dcache.c:857
>>>  __fput+0x3fb/0x6d0 fs/file_table.c:439
>>>  ____fput+0x1c/0x30 fs/file_table.c:459
>>>  task_work_run+0x13a/0x1a0 kernel/task_work.c:228
>>>  resume_user_mode_work include/linux/resume_user_mode.h:50 [inline]
>>>  exit_to_user_mode_loop kernel/entry/common.c:114 [inline]
>>>  exit_to_user_mode_prepare include/linux/entry-common.h:328 [inline]
>>>  __syscall_exit_to_user_mode_work kernel/entry/common.c:207 [inline]
>>>  syscall_exit_to_user_mode+0xbe/0x130 kernel/entry/common.c:218
>>>  do_syscall_64+0xd6/0x1c0 arch/x86/entry/common.c:89
>>>  entry_SYSCALL_64_after_hwframe+0x77/0x7f
>>> 
>>> read to 0xffffea0004b81dd8 of 8 bytes by task 6342 on cpu 1:
>>>  __folio_test_movable include/linux/page-flags.h:699 [inline]
>>>  migrate_folio_unmap mm/migrate.c:1199 [inline]
>>>  migrate_pages_batch+0x24c/0x1940 mm/migrate.c:1797
>>>  migrate_pages_sync mm/migrate.c:1963 [inline]
>>>  migrate_pages+0xff1/0x1820 mm/migrate.c:2072
>>>  do_mbind mm/mempolicy.c:1390 [inline]
>>>  kernel_mbind mm/mempolicy.c:1533 [inline]
>>>  __do_sys_mbind mm/mempolicy.c:1607 [inline]
>>>  __se_sys_mbind+0xf76/0x1160 mm/mempolicy.c:1603
>>>  __x64_sys_mbind+0x78/0x90 mm/mempolicy.c:1603
>>>  x64_sys_call+0x2b4d/0x2d60 arch/x86/include/generated/asm/syscalls_64.h:238
>>>  do_syscall_x64 arch/x86/entry/common.c:52 [inline]
>>>  do_syscall_64+0xc9/0x1c0 arch/x86/entry/common.c:83
>>>  entry_SYSCALL_64_after_hwframe+0x77/0x7f
>>> 
>>> value changed: 0xffff888127601078 -> 0x0000000000000000
>> 
>> Note that this doesn't flip PAGE_MAPPING_MOVABLE, just some unrelated bits.
>> 
>>> 
>>> Reported-by: syzbot <syzkaller@...glegroups.com>
>>> Cc: stable@...r.kernel.org
>>> Fixes: 7e2a5e5ab217 ("mm: migrate: use __folio_test_movable()")
>>> Signed-off-by: Jeongjun Park <aha310510@...il.com>
>>> ---
>>>  mm/migrate.c | 3 ++-
>>>  1 file changed, 2 insertions(+), 1 deletion(-)
>>> 
>>> diff --git a/mm/migrate.c b/mm/migrate.c
>>> index 923ea80ba744..e62dac12406b 100644
>>> --- a/mm/migrate.c
>>> +++ b/mm/migrate.c
>>> @@ -1118,7 +1118,7 @@ static int migrate_folio_unmap(new_folio_t get_new_folio,
>>>      int rc = -EAGAIN;
>>>      int old_page_state = 0;
>>>      struct anon_vma *anon_vma = NULL;
>>> -    bool is_lru = !__folio_test_movable(src);
>>> +    bool is_lru;
>>>      bool locked = false;
>>>      bool dst_locked = false;
>>> @@ -1172,6 +1172,7 @@ static int migrate_folio_unmap(new_folio_t get_new_folio,
>>>      locked = true;
>>>      if (folio_test_mlocked(src))
>>>          old_page_state |= PAGE_WAS_MLOCKED;
>>> +    is_lru = !__folio_test_movable(src);
>> 
>> 
>> Looks straight forward, though
>> 
>> Acked-by: David Hildenbrand <david@...hat.com>
>> 
>> 
>> --
>> Cheers,
>> 
>> David / dhildenb
>>