Re: [f2fs-dev] [PATCH v2] f2fs: fix to avoid deadlock of atomic file operations

[Gao Xiang]

Sorry, please ignore my reply... (If there no
truncate and commit race...)

On 2019/2/25 17:25, Gao Xiang wrote:
> Hi Chao,
> 
> On 2019/2/25 17:11, Chao Yu wrote:
>> Thread A				Thread B
>> - __fput
>>  - f2fs_release_file
>>   - drop_inmem_pages
>>    - mutex_lock(&fi->inmem_lock)
>>    - __revoke_inmem_pages
>>     - lock_page(page)
>> 					- open
>> 					- f2fs_setattr
>> 					- truncate_setsize
>> 					 - truncate_inode_pages_range
>> 					  - lock_page(page)
>> 					  - truncate_cleanup_page
>> 					   - f2fs_invalidate_page
>> 					    - drop_inmem_page
>> 					    - mutex_lock(&fi->inmem_lock);
>>
>> We may encounter above ABBA deadlock as reported by Kyungtae Kim:
>>
>> I'm reporting a bug in linux-4.17.19: "INFO: task hung in
>> drop_inmem_page" (no reproducer)
>>
>> I think this might be somehow related to the following:
>> https://groups.google.com/forum/#!searchin/syzkaller-bugs/INFO$3A$20task$20hung$20in$20%7Csort:date/syzkaller-bugs/c6soBTrdaIo/AjAzPeIzCgAJ
>>
>> =========================================
>> INFO: task syz-executor7:10822 blocked for more than 120 seconds.
>>       Not tainted 4.17.19 #1
>> "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
>> syz-executor7   D27024 10822   6346 0x00000004
>> Call Trace:
>>  context_switch kernel/sched/core.c:2867 [inline]
>>  __schedule+0x721/0x1e60 kernel/sched/core.c:3515
>>  schedule+0x88/0x1c0 kernel/sched/core.c:3559
>>  schedule_preempt_disabled+0x18/0x30 kernel/sched/core.c:3617
>>  __mutex_lock_common kernel/locking/mutex.c:833 [inline]
>>  __mutex_lock+0x5bd/0x1410 kernel/locking/mutex.c:893
>>  mutex_lock_nested+0x1b/0x20 kernel/locking/mutex.c:908
>>  drop_inmem_page+0xcb/0x810 fs/f2fs/segment.c:327
>>  f2fs_invalidate_page+0x337/0x5e0 fs/f2fs/data.c:2401
>>  do_invalidatepage mm/truncate.c:165 [inline]
>>  truncate_cleanup_page+0x261/0x330 mm/truncate.c:187
>>  truncate_inode_pages_range+0x552/0x1610 mm/truncate.c:367
>>  truncate_inode_pages mm/truncate.c:478 [inline]
>>  truncate_pagecache+0x6d/0x90 mm/truncate.c:801
>>  truncate_setsize+0x81/0xa0 mm/truncate.c:826
>>  f2fs_setattr+0x44f/0x1270 fs/f2fs/file.c:781
>>  notify_change+0xa62/0xe80 fs/attr.c:313
>>  do_truncate+0x12e/0x1e0 fs/open.c:63
>>  do_last fs/namei.c:2955 [inline]
>>  path_openat+0x2042/0x29f0 fs/namei.c:3505
>>  do_filp_open+0x1bd/0x2c0 fs/namei.c:3540
>>  do_sys_open+0x35e/0x4e0 fs/open.c:1101
>>  __do_sys_open fs/open.c:1119 [inline]
>>  __se_sys_open fs/open.c:1114 [inline]
>>  __x64_sys_open+0x89/0xc0 fs/open.c:1114
>>  do_syscall_64+0xc4/0x4e0 arch/x86/entry/common.c:287
>>  entry_SYSCALL_64_after_hwframe+0x49/0xbe
>> RIP: 0033:0x4497b9
>> RSP: 002b:00007f734e459c68 EFLAGS: 00000246 ORIG_RAX: 0000000000000002
>> RAX: ffffffffffffffda RBX: 00007f734e45a6cc RCX: 00000000004497b9
>> RDX: 0000000000000104 RSI: 00000000000a8280 RDI: 0000000020000080
>> RBP: 000000000071bea0 R08: 0000000000000000 R09: 0000000000000000
>> R10: 0000000000000000 R11: 0000000000000246 R12: 00000000ffffffff
>> R13: 0000000000007230 R14: 00000000006f02d0 R15: 00007f734e45a700
>> INFO: task syz-executor7:10858 blocked for more than 120 seconds.
>>       Not tainted 4.17.19 #1
>> "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
>> syz-executor7   D28880 10858   6346 0x00000004
>> Call Trace:
>>  context_switch kernel/sched/core.c:2867 [inline]
>>  __schedule+0x721/0x1e60 kernel/sched/core.c:3515
>>  schedule+0x88/0x1c0 kernel/sched/core.c:3559
>>  __rwsem_down_write_failed_common kernel/locking/rwsem-xadd.c:565 [inline]
>>  rwsem_down_write_failed+0x5e6/0xc90 kernel/locking/rwsem-xadd.c:594
>>  call_rwsem_down_write_failed+0x17/0x30 arch/x86/lib/rwsem.S:117
>>  __down_write arch/x86/include/asm/rwsem.h:142 [inline]
>>  down_write+0x58/0xa0 kernel/locking/rwsem.c:72
>>  inode_lock include/linux/fs.h:713 [inline]
>>  do_truncate+0x120/0x1e0 fs/open.c:61
>>  do_last fs/namei.c:2955 [inline]
>>  path_openat+0x2042/0x29f0 fs/namei.c:3505
>>  do_filp_open+0x1bd/0x2c0 fs/namei.c:3540
>>  do_sys_open+0x35e/0x4e0 fs/open.c:1101
>>  __do_sys_open fs/open.c:1119 [inline]
>>  __se_sys_open fs/open.c:1114 [inline]
>>  __x64_sys_open+0x89/0xc0 fs/open.c:1114
>>  do_syscall_64+0xc4/0x4e0 arch/x86/entry/common.c:287
>>  entry_SYSCALL_64_after_hwframe+0x49/0xbe
>> RIP: 0033:0x4497b9
>> RSP: 002b:00007f734e3b4c68 EFLAGS: 00000246 ORIG_RAX: 0000000000000002
>> RAX: ffffffffffffffda RBX: 00007f734e3b56cc RCX: 00000000004497b9
>> RDX: 0000000000000104 RSI: 00000000000a8280 RDI: 0000000020000080
>> RBP: 000000000071c238 R08: 0000000000000000 R09: 0000000000000000
>> R10: 0000000000000000 R11: 0000000000000246 R12: 00000000ffffffff
>> R13: 0000000000007230 R14: 00000000006f02d0 R15: 00007f734e3b5700
>> INFO: task syz-executor5:10829 blocked for more than 120 seconds.
>>       Not tainted 4.17.19 #1
>> "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
>> syz-executor5   D28760 10829   6308 0x80000002
>> Call Trace:
>>  context_switch kernel/sched/core.c:2867 [inline]
>>  __schedule+0x721/0x1e60 kernel/sched/core.c:3515
>>  schedule+0x88/0x1c0 kernel/sched/core.c:3559
>>  io_schedule+0x21/0x80 kernel/sched/core.c:5179
>>  wait_on_page_bit_common mm/filemap.c:1100 [inline]
>>  __lock_page+0x2b5/0x390 mm/filemap.c:1273
>>  lock_page include/linux/pagemap.h:483 [inline]
>>  __revoke_inmem_pages+0xb35/0x11c0 fs/f2fs/segment.c:231
>>  drop_inmem_pages+0xa3/0x3e0 fs/f2fs/segment.c:306
>>  f2fs_release_file+0x2c7/0x330 fs/f2fs/file.c:1556
>>  __fput+0x2c7/0x780 fs/file_table.c:209
>>  ____fput+0x1a/0x20 fs/file_table.c:243
>>  task_work_run+0x151/0x1d0 kernel/task_work.c:113
>>  exit_task_work include/linux/task_work.h:22 [inline]
>>  do_exit+0x8ba/0x30a0 kernel/exit.c:865
>>  do_group_exit+0x13b/0x3a0 kernel/exit.c:968
>>  get_signal+0x6bb/0x1650 kernel/signal.c:2482
>>  do_signal+0x84/0x1b70 arch/x86/kernel/signal.c:810
>>  exit_to_usermode_loop+0x155/0x190 arch/x86/entry/common.c:162
>>  prepare_exit_to_usermode arch/x86/entry/common.c:196 [inline]
>>  syscall_return_slowpath arch/x86/entry/common.c:265 [inline]
>>  do_syscall_64+0x445/0x4e0 arch/x86/entry/common.c:290
>>  entry_SYSCALL_64_after_hwframe+0x49/0xbe
>> RIP: 0033:0x4497b9
>> RSP: 002b:00007f1c68e74ce8 EFLAGS: 00000246 ORIG_RAX: 00000000000000ca
>> RAX: fffffffffffffe00 RBX: 000000000071bf80 RCX: 00000000004497b9
>> RDX: 0000000000000000 RSI: 0000000000000000 RDI: 000000000071bf80
>> RBP: 000000000071bf80 R08: 0000000000000000 R09: 000000000071bf58
>> R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000
>> R13: 0000000000000000 R14: 00007f1c68e759c0 R15: 00007f1c68e75700
>>
>> This patch tries to use trylock_page to mitigate such deadlock condition
>> for fix.
>>
>> Signed-off-by: Chao Yu <yuchao0@xxxxxxxxxx>
>> ---
>> v2:
>> - fix wrong mutex_unlock position.
>>  fs/f2fs/segment.c | 43 +++++++++++++++++++++++++++++++------------
>>  1 file changed, 31 insertions(+), 12 deletions(-)
>>
>> diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
>> index fdd8cd21522f..ca786913b2c6 100644
>> --- a/fs/f2fs/segment.c
>> +++ b/fs/f2fs/segment.c
>> @@ -215,7 +215,8 @@ void f2fs_register_inmem_page(struct inode *inode, struct page *page)
>>  }
>>  
>>  static int __revoke_inmem_pages(struct inode *inode,
>> -				struct list_head *head, bool drop, bool recover)
>> +				struct list_head *head, bool drop, bool recover,
>> +				bool trylock)
>>  {
>>  	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
>>  	struct inmem_pages *cur, *tmp;
>> @@ -227,7 +228,16 @@ static int __revoke_inmem_pages(struct inode *inode,
>>  		if (drop)
>>  			trace_f2fs_commit_inmem_page(page, INMEM_DROP);
>>  
>> -		lock_page(page);
>> +		if (trylock) {
>> +			/*
>> +			 * to avoid deadlock in between page lock and
>> +			 * inmem_lock.
>> +			 */
>> +			if (!trylock_page(page))
>> +				continue;
> 
> Will it cause memleak? since revoke_list is a temporary local linked list...
> Is there a better way than just simplily skip it?
> 
> Thanks,
> Gao Xiang
> 
>> +		} else {
>> +			lock_page(page);
>> +		}
>>  
>>  		f2fs_wait_on_page_writeback(page, DATA, true, true);
>>  
>> @@ -318,13 +328,19 @@ void f2fs_drop_inmem_pages(struct inode *inode)
>>  	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
>>  	struct f2fs_inode_info *fi = F2FS_I(inode);
>>  
>> -	mutex_lock(&fi->inmem_lock);
>> -	__revoke_inmem_pages(inode, &fi->inmem_pages, true, false);
>> -	spin_lock(&sbi->inode_lock[ATOMIC_FILE]);
>> -	if (!list_empty(&fi->inmem_ilist))
>> -		list_del_init(&fi->inmem_ilist);
>> -	spin_unlock(&sbi->inode_lock[ATOMIC_FILE]);
>> -	mutex_unlock(&fi->inmem_lock);
>> +	while (!list_empty(&fi->inmem_pages)) {
>> +		mutex_lock(&fi->inmem_lock);
>> +		__revoke_inmem_pages(inode, &fi->inmem_pages,
>> +						true, false, true);
>> +
>> +		if (list_empty(&fi->inmem_pages)) {
>> +			spin_lock(&sbi->inode_lock[ATOMIC_FILE]);
>> +			if (!list_empty(&fi->inmem_ilist))
>> +				list_del_init(&fi->inmem_ilist);
>> +			spin_unlock(&sbi->inode_lock[ATOMIC_FILE]);
>> +		}
>> +		mutex_unlock(&fi->inmem_lock);
>> +	}
>>  
>>  	clear_inode_flag(inode, FI_ATOMIC_FILE);
>>  	fi->i_gc_failures[GC_FAILURE_ATOMIC] = 0;
>> @@ -429,12 +445,15 @@ static int __f2fs_commit_inmem_pages(struct inode *inode)
>>  		 * recovery or rewrite & commit last transaction. For other
>>  		 * error number, revoking was done by filesystem itself.
>>  		 */
>> -		err = __revoke_inmem_pages(inode, &revoke_list, false, true);
>> +		err = __revoke_inmem_pages(inode, &revoke_list,
>> +						false, true, false);
>>  
>>  		/* drop all uncommitted pages */
>> -		__revoke_inmem_pages(inode, &fi->inmem_pages, true, false);
>> +		__revoke_inmem_pages(inode, &fi->inmem_pages,
>> +						true, false, false);
>>  	} else {
>> -		__revoke_inmem_pages(inode, &revoke_list, false, false);
>> +		__revoke_inmem_pages(inode, &revoke_list,
>> +						false, false, false);
>>  	}
>>  
>>  	return err;
>>
> 
> 
> _______________________________________________
> Linux-f2fs-devel mailing list
> Linux-f2fs-devel@xxxxxxxxxxxxxxxxxxxxx
> https://lists.sourceforge.net/lists/listinfo/linux-f2fs-devel
>