Re: [f2fs-dev] [PATCH 2/2] f2fs: sync filesystem after roll-forward recovery

[Chao Yu]

On 2019/1/25 8:52, Jaegeuk Kim wrote:
> On 01/24, Chao Yu wrote:
>> On 2019/1/23 8:02, Jaegeuk Kim wrote:
>>> Some works after roll-forward recovery can get an error which will release
>>> all the data structures. Let's flush them in order to make it clean.
>>>
>>> One possible corruption came from:
>>>
>>> [   90.400500] list_del corruption. prev->next should be ffffffed1f566208, but was (null)
>>> [   90.675349] Call trace:
>>> [   90.677869]  __list_del_entry_valid+0x94/0xb4
>>> [   90.682351]  remove_dirty_inode+0xac/0x114
>>> [   90.686563]  __f2fs_write_data_pages+0x6a8/0x6c8
>>> [   90.691302]  f2fs_write_data_pages+0x40/0x4c
>>> [   90.695695]  do_writepages+0x80/0xf0
>>> [   90.699372]  __writeback_single_inode+0xdc/0x4ac
>>> [   90.704113]  writeback_sb_inodes+0x280/0x440
>>> [   90.708501]  wb_writeback+0x1b8/0x3d0
>>> [   90.712267]  wb_workfn+0x1a8/0x4d4
>>> [   90.715765]  process_one_work+0x1c0/0x3d4
>>> [   90.719883]  worker_thread+0x224/0x344
>>> [   90.723739]  kthread+0x120/0x130
>>> [   90.727055]  ret_from_fork+0x10/0x18
>>>
>>> Reported-by: Sahitya Tummala <stummala@xxxxxxxxxxxxxx>
>>> Signed-off-by: Jaegeuk Kim <jaegeuk@xxxxxxxxxx>
>>> ---
>>>  fs/f2fs/checkpoint.c |  5 +++--
>>>  fs/f2fs/node.c       |  4 +++-
>>>  fs/f2fs/super.c      | 42 +++++++++++++++++++++++++++++++-----------
>>>  3 files changed, 37 insertions(+), 14 deletions(-)
>>>
>>> diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
>>> index f955cd3e0677..ccccf0ce2f06 100644
>>> --- a/fs/f2fs/checkpoint.c
>>> +++ b/fs/f2fs/checkpoint.c
>>> @@ -306,8 +306,9 @@ static int f2fs_write_meta_pages(struct address_space *mapping,
>>>  		goto skip_write;
>>>  
>>>  	/* collect a number of dirty meta pages and write together */
>>> -	if (wbc->for_kupdate ||
>>> -		get_pages(sbi, F2FS_DIRTY_META) < nr_pages_to_skip(sbi, META))
>>> +	if (wbc->sync_mode != WB_SYNC_ALL &&
>>> +			get_pages(sbi, F2FS_DIRTY_META) <
>>> +					nr_pages_to_skip(sbi, META))
>>>  		goto skip_write;
>>>  
>>>  	/* if locked failed, cp will flush dirty pages instead */
>>> diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
>>> index 4f450e573312..f6ff84e29749 100644
>>> --- a/fs/f2fs/node.c
>>> +++ b/fs/f2fs/node.c
>>> @@ -1920,7 +1920,9 @@ static int f2fs_write_node_pages(struct address_space *mapping,
>>>  	f2fs_balance_fs_bg(sbi);
>>>  
>>>  	/* collect a number of dirty node pages and write together */
>>> -	if (get_pages(sbi, F2FS_DIRTY_NODES) < nr_pages_to_skip(sbi, NODE))
>>> +	if (wbc->sync_mode != WB_SYNC_ALL &&
>>> +			get_pages(sbi, F2FS_DIRTY_NODES) <
>>> +					nr_pages_to_skip(sbi, NODE))
>>>  		goto skip_write;
>>>  
>>>  	if (wbc->sync_mode == WB_SYNC_ALL)
>>> diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
>>> index 7998ff5418f2..2af0db2b738e 100644
>>> --- a/fs/f2fs/super.c
>>> +++ b/fs/f2fs/super.c
>>> @@ -1456,9 +1456,16 @@ static int f2fs_enable_quotas(struct super_block *sb);
>>>  
>>>  static int f2fs_disable_checkpoint(struct f2fs_sb_info *sbi)
>>>  {
>>> +	unsigned int s_flags = sbi->sb->s_flags;
>>>  	struct cp_control cpc;
>>> -	int err;
>>> +	int err = 0;
>>> +	int ret;
>>>  
>>> +	if (s_flags & SB_RDONLY) {
>>> +		f2fs_msg(sbi->sb, KERN_ERR,
>>> +				"checkpoint=disable on readonly fs");
>>> +		return -EINVAL;
>>> +	}
>>>  	sbi->sb->s_flags |= SB_ACTIVE;
>>>  
>>>  	f2fs_update_time(sbi, DISABLE_TIME);
>>> @@ -1466,18 +1473,24 @@ static int f2fs_disable_checkpoint(struct f2fs_sb_info *sbi)
>>>  	while (!f2fs_time_over(sbi, DISABLE_TIME)) {
>>>  		mutex_lock(&sbi->gc_mutex);
>>>  		err = f2fs_gc(sbi, true, false, NULL_SEGNO);
>>> -		if (err == -ENODATA)
>>> +		if (err == -ENODATA) {
>>> +			err = 0;
>>>  			break;
>>> +		}
>>>  		if (err && err != -EAGAIN)
>>> -			return err;
>>> +			break;
>>
>> Should be?
>>
>> if (err) {
>> 	if (err == -EAGAIN)
>> 		err = 0;
> 
> Have to report EAGAIN, but not for ENODATA.

Oh, right. :)

Reviewed-by: Chao Yu <yuchao0@xxxxxxxxxx>

Thanks,

> 
>> 	else
>> 		break;
>> }
>>
>> Thanks,
>>
>>>  	}
>>>  
>>> -	err = sync_filesystem(sbi->sb);
>>> -	if (err)
>>> -		return err;
>>> +	ret = sync_filesystem(sbi->sb);
>>> +	if (ret || err) {
>>> +		err = ret ? ret: err;
>>> +		goto restore_flag;
>>> +	}
>>>  
>>> -	if (f2fs_disable_cp_again(sbi))
>>> -		return -EAGAIN;
>>> +	if (f2fs_disable_cp_again(sbi)) {
>>> +		err = -EAGAIN;
>>> +		goto restore_flag;
>>> +	}
>>>  
>>>  	mutex_lock(&sbi->gc_mutex);
>>>  	cpc.reason = CP_PAUSE;
>>> @@ -1486,7 +1499,9 @@ static int f2fs_disable_checkpoint(struct f2fs_sb_info *sbi)
>>>  
>>>  	sbi->unusable_block_count = 0;
>>>  	mutex_unlock(&sbi->gc_mutex);
>>> -	return 0;
>>> +restore_flag:
>>> +	sbi->sb->s_flags = s_flags;	/* Restore MS_RDONLY status */
>>> +	return err;
>>>  }
>>>  
>>>  static void f2fs_enable_checkpoint(struct f2fs_sb_info *sbi)
>>> @@ -3356,7 +3371,7 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
>>>  	if (test_opt(sbi, DISABLE_CHECKPOINT)) {
>>>  		err = f2fs_disable_checkpoint(sbi);
>>>  		if (err)
>>> -			goto free_meta;
>>> +			goto sync_free_meta;
>>>  	} else if (is_set_ckpt_flags(sbi, CP_DISABLED_FLAG)) {
>>>  		f2fs_enable_checkpoint(sbi);
>>>  	}
>>> @@ -3369,7 +3384,7 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
>>>  		/* After POR, we can run background GC thread.*/
>>>  		err = f2fs_start_gc_thread(sbi);
>>>  		if (err)
>>> -			goto free_meta;
>>> +			goto sync_free_meta;
>>>  	}
>>>  	kvfree(options);
>>>  
>>> @@ -3391,6 +3406,11 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
>>>  	f2fs_update_time(sbi, REQ_TIME);
>>>  	return 0;
>>>  
>>> +sync_free_meta:
>>> +	/* safe to flush all the data */
>>> +	sync_filesystem(sbi->sb);
>>> +	retry = false;
>>> +
>>>  free_meta:
>>>  #ifdef CONFIG_QUOTA
>>>  	f2fs_truncate_quota_inode_pages(sb);
>>>
> 
> .
>