Re: [PATCH 1/2] f2fs: fix sbi->extent_list corruption issue

[Jaegeuk Kim]

On 11/22, Chao Yu wrote:
> On 2018/11/22 18:59, Sahitya Tummala wrote:
> > When there is a failure in f2fs_fill_super() after/during
> > the recovery of fsync'd nodes, it frees the current sbi and
> > retries again. This time the mount is successful, but the files
> > that got recovered before retry, still holds the extent tree,
> > whose extent nodes list is corrupted since sbi and sbi->extent_list
> > is freed up. The list_del corruption issue is observed when the
> > file system is getting unmounted and when those recoverd files extent
> > node is being freed up in the below context.
> > 
> > list_del corruption. prev->next should be fffffff1e1ef5480, but was (null)
> > <...>
> > kernel BUG at kernel/msm-4.14/lib/list_debug.c:53!
> > task: fffffff1f46f2280 task.stack: ffffff8008068000
> > lr : __list_del_entry_valid+0x94/0xb4
> > pc : __list_del_entry_valid+0x94/0xb4
> > <...>
> > Call trace:
> > __list_del_entry_valid+0x94/0xb4
> > __release_extent_node+0xb0/0x114
> > __free_extent_tree+0x58/0x7c
> > f2fs_shrink_extent_tree+0xdc/0x3b0
> > f2fs_leave_shrinker+0x28/0x7c
> > f2fs_put_super+0xfc/0x1e0
> > generic_shutdown_super+0x70/0xf4
> > kill_block_super+0x2c/0x5c
> > kill_f2fs_super+0x44/0x50
> > deactivate_locked_super+0x60/0x8c
> > deactivate_super+0x68/0x74
> > cleanup_mnt+0x40/0x78
> > __cleanup_mnt+0x1c/0x28
> > task_work_run+0x48/0xd0
> > do_notify_resume+0x678/0xe98
> > work_pending+0x8/0x14
> > 
> > Fix this by cleaning up the extent tree of those recovered files
> > before freeing up sbi and before next retry.
> 
> Would it be more clear to call shrink_dcache_sb earlier to invalid all
> inodes and call f2fs_shrink_extent_tree release cached entries and trees in
> error path?

Agreed.

> 
> BTW, I don't see any benefit of retry flow in fill_super, I guess we can
> avoid it to simply fill_super flow?

I expect it can avoid another mount failure.

> 
> To Jaegeuk, how do you think?
> 
> Thanks,
> 
> > 
> > Signed-off-by: Sahitya Tummala <stummala@xxxxxxxxxxxxxx>
> > ---
> >  fs/f2fs/extent_cache.c |  6 +++++-
> >  fs/f2fs/f2fs.h         |  2 +-
> >  fs/f2fs/inode.c        |  2 +-
> >  fs/f2fs/super.c        | 10 ++++++++++
> >  4 files changed, 17 insertions(+), 3 deletions(-)
> > 
> > diff --git a/fs/f2fs/extent_cache.c b/fs/f2fs/extent_cache.c
> > index 1cb0fcc..763ba83 100644
> > --- a/fs/f2fs/extent_cache.c
> > +++ b/fs/f2fs/extent_cache.c
> > @@ -743,7 +743,7 @@ void f2fs_drop_extent_tree(struct inode *inode)
> >  		f2fs_mark_inode_dirty_sync(inode, true);
> >  }
> >  
> > -void f2fs_destroy_extent_tree(struct inode *inode)
> > +void f2fs_destroy_extent_tree(struct inode *inode, bool force)
> >  {
> >  	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
> >  	struct extent_tree *et = F2FS_I(inode)->extent_tree;
> > @@ -752,6 +752,9 @@ void f2fs_destroy_extent_tree(struct inode *inode)
> >  	if (!et)
> >  		return;
> >  
> > +	if (force)
> > +		goto destroy_et;
> > +
> >  	if (inode->i_nlink && !is_bad_inode(inode) &&
> >  					atomic_read(&et->node_cnt)) {
> >  		mutex_lock(&sbi->extent_tree_lock);
> > @@ -761,6 +764,7 @@ void f2fs_destroy_extent_tree(struct inode *inode)
> >  		return;
> >  	}
> >  
> > +destroy_et:
> >  	/* free all extent info belong to this extent tree */
> >  	node_cnt = f2fs_destroy_extent_node(inode);
> >  
> > diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
> > index 1e03197..db8a919 100644
> > --- a/fs/f2fs/f2fs.h
> > +++ b/fs/f2fs/f2fs.h
> > @@ -3410,7 +3410,7 @@ bool f2fs_check_rb_tree_consistence(struct f2fs_sb_info *sbi,
> >  bool f2fs_init_extent_tree(struct inode *inode, struct f2fs_extent *i_ext);
> >  void f2fs_drop_extent_tree(struct inode *inode);
> >  unsigned int f2fs_destroy_extent_node(struct inode *inode);
> > -void f2fs_destroy_extent_tree(struct inode *inode);
> > +void f2fs_destroy_extent_tree(struct inode *inode, bool force);
> >  bool f2fs_lookup_extent_cache(struct inode *inode, pgoff_t pgofs,
> >  			struct extent_info *ei);
> >  void f2fs_update_extent_cache(struct dnode_of_data *dn);
> > diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c
> > index 91ceee0..39e3ade3 100644
> > --- a/fs/f2fs/inode.c
> > +++ b/fs/f2fs/inode.c
> > @@ -649,7 +649,7 @@ void f2fs_evict_inode(struct inode *inode)
> >  	f2fs_bug_on(sbi, get_dirty_pages(inode));
> >  	f2fs_remove_dirty_inode(inode);
> >  
> > -	f2fs_destroy_extent_tree(inode);
> > +	f2fs_destroy_extent_tree(inode, false);
> >  
> >  	if (inode->i_nlink || is_bad_inode(inode))
> >  		goto no_delete;
> > diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
> > index af58b2c..f41ac43 100644
> > --- a/fs/f2fs/super.c
> > +++ b/fs/f2fs/super.c
> > @@ -3016,6 +3016,15 @@ static void f2fs_tuning_parameters(struct f2fs_sb_info *sbi)
> >  	sbi->readdir_ra = 1;
> >  }
> >  
> > +void f2fs_cleanup_extent_cache(struct f2fs_sb_info *sbi)
> > +{
> > +	struct super_block *sb = sbi->sb;
> > +	struct inode *inode, *next;
> > +
> > +	list_for_each_entry_safe(inode, next, &sb->s_inodes, i_sb_list)
> > +		f2fs_destroy_extent_tree(inode, true);
> > +}
> > +
> >  static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
> >  {
> >  	struct f2fs_sb_info *sbi;
> > @@ -3402,6 +3411,7 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
> >  	 * falls into an infinite loop in f2fs_sync_meta_pages().
> >  	 */
> >  	truncate_inode_pages_final(META_MAPPING(sbi));
> > +	f2fs_cleanup_extent_cache(sbi);
> >  	f2fs_unregister_sysfs(sbi);
> >  free_root_inode:
> >  	dput(sb->s_root);
> >