Re: [PATCH] f2fs: reserve space to be shrunk during resize_fs

[Chao Yu <chao@kernel.org>]

On 10/14/26 11:06, Daeho Jeong wrote:
> From: Daeho Jeong <daehojeong@google.com>
> 
> f2fs_resize_fs() checks whether there is enough free space for the
> shrink, runs a dry-run GC to migrate blocks out of the target range,
> and then drops gc_lock and the cp lock before freeze_super(). During
> that window, other processes, including root ones that are allowed to
> use root reserved blocks, can still allocate the free space, so the
> second check after freeze_super() fails with -ENOSPC even though the
> first check passed. This is easy to hit when the shrink is triggered
> on a live, busy filesystem, e.g. by an updater at OTA install time.
> 
> Fix this by reserving the space to be shrunk once the first check
> passes. Add resize_reserved_blocks and deduct it in
> __get_available_block_count() for all callers, like
> alias_reserved_blocks, so that no one can allocate the reserved space
> until the shrink is done. The reservation is released together with
> the user_block_count update on success, or on any error.
> 
> Also factor out __get_available_block_count() and use it in
> f2fs_resize_fs() to share the available block calculation, which takes
> alias_reserved_blocks into account as well.
> 
> Suggested-by: Chao Yu <chao@kernel.org>
> Signed-off-by: Daeho Jeong <daehojeong@google.com>
> ---
>  fs/f2fs/f2fs.h  | 18 ++++++++++++++----
>  fs/f2fs/gc.c    | 41 +++++++++++++++++++++++++++++------------
>  fs/f2fs/super.c |  1 +
>  3 files changed, 44 insertions(+), 16 deletions(-)
> 
> diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
> index 089a62c054e..6b9e1d0e71c 100644
> --- a/fs/f2fs/f2fs.h
> +++ b/fs/f2fs/f2fs.h
> @@ -1897,6 +1897,7 @@ struct f2fs_sb_info {
>  	block_t reserved_blocks;		/* configurable reserved blocks */
>  	block_t current_reserved_blocks;	/* current reserved blocks */
>  	block_t alias_reserved_blocks;		/* reserved blocks for device alias */
> +	block_t resize_reserved_blocks;		/* reserved blocks for resize_fs */
>  
>  	/* Additional tracking for no checkpoint mode */
>  	block_t unusable_block_count;		/* # of blocks saved by last cp */
> @@ -2666,16 +2667,18 @@ static inline bool __allow_reserved_root(struct f2fs_sb_info *sbi,
>  	return false;
>  }
>  
> -static inline unsigned int get_available_block_count(struct f2fs_sb_info *sbi,
> -						struct inode *inode, bool cap)
> +static inline unsigned int __get_available_block_count(
> +					struct f2fs_sb_info *sbi,
> +					bool allow_root)
>  {
>  	block_t avail_user_block_count;
>  
>  	avail_user_block_count = sbi->user_block_count -
>  					sbi->current_reserved_blocks -
> -					sbi->alias_reserved_blocks;
> +					sbi->alias_reserved_blocks -
> +					sbi->resize_reserved_blocks;
>  
> -	if (test_opt(sbi, RESERVE_ROOT) && !__allow_reserved_root(sbi, inode, cap))
> +	if (test_opt(sbi, RESERVE_ROOT) && !allow_root)
>  		avail_user_block_count -= F2FS_OPTION(sbi).root_reserved_blocks;
>  
>  	if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) {
> @@ -2688,6 +2691,13 @@ static inline unsigned int get_available_block_count(struct f2fs_sb_info *sbi,
>  	return avail_user_block_count;
>  }
>  
> +static inline unsigned int get_available_block_count(struct f2fs_sb_info *sbi,
> +						struct inode *inode, bool cap)
> +{
> +	return __get_available_block_count(sbi,
> +				__allow_reserved_root(sbi, inode, cap));
> +}

Do we need to use this to cover current_reserved_blocks update? because
reserved_blocks sysfs bypasses the reservation.

	if (a->struct_type == RESERVED_BLOCKS) {
		spin_lock(&sbi->stat_lock);
		if (t > (unsigned long)(sbi->user_block_count -
				F2FS_OPTION(sbi).root_reserved_blocks)) {
			spin_unlock(&sbi->stat_lock);
			return -EINVAL;
		}
		*ui = t;
		sbi->current_reserved_blocks = min(sbi->reserved_blocks,
				sbi->user_block_count - valid_user_blocks(sbi));
		spin_unlock(&sbi->stat_lock);
		return count;
	}

> +
>  static inline void f2fs_i_blocks_write(struct inode *, block_t, bool, bool);
>  static inline int inc_valid_block_count(struct f2fs_sb_info *sbi,
>  				 struct inode *inode, blkcnt_t *count,
> diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c
> index 926e6976bc2..5bfdaeae794 100644
> --- a/fs/f2fs/gc.c
> +++ b/fs/f2fs/gc.c
> @@ -2374,6 +2374,7 @@ int f2fs_resize_fs(struct file *filp, __u64 block_count)
>  	struct f2fs_lock_context glc;
>  	struct f2fs_lock_context clc;
>  	unsigned int secs;
> +	bool reserved = false;
>  	int err = 0;
>  	__u32 rem;
>  
> @@ -2425,10 +2426,17 @@ int f2fs_resize_fs(struct file *filp, __u64 block_count)
>  	f2fs_lock_op(sbi, &lc);
>  
>  	spin_lock(&sbi->stat_lock);
> -	if (shrunk_blocks + valid_user_blocks(sbi) +
> -		sbi->current_reserved_blocks + sbi->unusable_block_count +
> -		F2FS_OPTION(sbi).root_reserved_blocks > sbi->user_block_count)
> +	if (shrunk_blocks + valid_user_blocks(sbi) >
> +			__get_available_block_count(sbi, false)) {
>  		err = -ENOSPC;
> +	} else {
> +		/*
> +		 * Reserve the space to be shrunk so that no one, including
> +		 * root, can allocate it until the shrink is done.
> +		 */
> +		sbi->resize_reserved_blocks += shrunk_blocks;
> +		reserved = true;
> +	}
>  	spin_unlock(&sbi->stat_lock);
>  
>  	if (err)
> @@ -2442,29 +2450,32 @@ int f2fs_resize_fs(struct file *filp, __u64 block_count)
>  out_drop_write:
>  	mnt_drop_write_file(filp);
>  	if (err)
> -		return err;
> +		goto out_release;
>  
>  	err = freeze_super(sbi->sb, FREEZE_HOLDER_KERNEL, NULL);
>  	if (err)
> -		return err;
> +		goto out_release;
>  
>  	if (f2fs_readonly(sbi->sb)) {
>  		err = thaw_super(sbi->sb, FREEZE_HOLDER_KERNEL, NULL);
> -		if (err)
> -			return err;
> -		return -EROFS;
> +		if (!err)
> +			err = -EROFS;
> +		goto out_release;
>  	}
>  
>  	f2fs_down_write_trace(&sbi->gc_lock, &glc);
>  	f2fs_down_write_trace(&sbi->cp_global_sem, &clc);
>  
>  	spin_lock(&sbi->stat_lock);
> -	if (shrunk_blocks + valid_user_blocks(sbi) +
> -		sbi->current_reserved_blocks + sbi->unusable_block_count +
> -		F2FS_OPTION(sbi).root_reserved_blocks > sbi->user_block_count)
> +	/* shrunk_blocks is already accounted in resize_reserved_blocks */
> +	if (valid_user_blocks(sbi) >
> +			__get_available_block_count(sbi, false)) {
>  		err = -ENOSPC;

Since we already have reserved blocks in resize_reserved_blocks, we should
not expect there will be ENOSPC case here, right?

Thanks,

> -	else
> +	} else {
>  		sbi->user_block_count -= shrunk_blocks;
> +		sbi->resize_reserved_blocks -= shrunk_blocks;
> +		reserved = false;
> +	}
>  	spin_unlock(&sbi->stat_lock);
>  	if (err)
>  		goto out_err;
> @@ -2510,5 +2521,11 @@ int f2fs_resize_fs(struct file *filp, __u64 block_count)>  	f2fs_up_write_trace(&sbi->cp_global_sem, &clc);
>  	f2fs_up_write_trace(&sbi->gc_lock, &glc);
>  	thaw_super(sbi->sb, FREEZE_HOLDER_KERNEL, NULL);
> +out_release:
> +	if (reserved) {
> +		spin_lock(&sbi->stat_lock);
> +		sbi->resize_reserved_blocks -= shrunk_blocks;
> +		spin_unlock(&sbi->stat_lock);
> +	}
>  	return err;
>  }
> diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
> index d683240040f..28e49e8d71e 100644
> --- a/fs/f2fs/super.c
> +++ b/fs/f2fs/super.c
> @@ -5345,6 +5345,7 @@ static int f2fs_fill_super(struct super_block *sb, struct fs_context *fc)
>  	sbi->reserved_blocks = 0;
>  	sbi->current_reserved_blocks = 0;
>  	sbi->alias_reserved_blocks = 0;
> +	sbi->resize_reserved_blocks = 0;
>  	limit_reserve_root(sbi);
>  	adjust_unusable_cap_perc(sbi);
>