linux-kernel - Re: [PATCH v2] f2fs: fix to avoid racing in between read and OPU dio write

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: <ZkOMwKAcKmEPQ4Xz@google.com>
Date: Tue, 14 May 2024 16:09:36 +0000
From: Jaegeuk Kim <jaegeuk@...nel.org>
To: Chao Yu <chao@...nel.org>
Cc: linux-f2fs-devel@...ts.sourceforge.net, linux-kernel@...r.kernel.org
Subject: Re: [PATCH v2] f2fs: fix to avoid racing in between read and OPU dio
 write

On 05/10, Chao Yu wrote:
> If lfs mode is on, buffered read may race w/ OPU dio write as below,
> it may cause buffered read hits unwritten data unexpectly, and for
> dio read, the race condition exists as well.
> 
> Thread A			Thread B
> - f2fs_file_write_iter
>  - f2fs_dio_write_iter
>   - __iomap_dio_rw
>    - f2fs_iomap_begin
>     - f2fs_map_blocks
>      - __allocate_data_block
>       - allocated blkaddr #x
>        - iomap_dio_submit_bio
> 				- f2fs_file_read_iter
> 				 - filemap_read
> 				  - f2fs_read_data_folio
> 				   - f2fs_mpage_readpages
> 				    - f2fs_map_blocks
> 				     : get blkaddr #x
> 				    - f2fs_submit_read_bio
> 				IRQ
> 				- f2fs_read_end_io
> 				 : read IO on blkaddr #x complete
> IRQ
> - iomap_dio_bio_end_io
>  : direct write IO on blkaddr #x complete
> 
> This patch introduces a new per-inode i_opu_rwsem lock to avoid
> such race condition.

Wasn't this supposed to be managed by user-land?

> 
> Fixes: f847c699cff3 ("f2fs: allow out-place-update for direct IO in LFS mode")
> Signed-off-by: Chao Yu <chao@...nel.org>
> ---
> v2:
> - fix to cover dio read path w/ i_opu_rwsem as well.
>  fs/f2fs/f2fs.h  |  1 +
>  fs/f2fs/file.c  | 28 ++++++++++++++++++++++++++--
>  fs/f2fs/super.c |  1 +
>  3 files changed, 28 insertions(+), 2 deletions(-)
> 
> diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
> index 30058e16a5d0..91cf4b3d6bc6 100644
> --- a/fs/f2fs/f2fs.h
> +++ b/fs/f2fs/f2fs.h
> @@ -847,6 +847,7 @@ struct f2fs_inode_info {
>  	/* avoid racing between foreground op and gc */
>  	struct f2fs_rwsem i_gc_rwsem[2];
>  	struct f2fs_rwsem i_xattr_sem; /* avoid racing between reading and changing EAs */
> +	struct f2fs_rwsem i_opu_rwsem;	/* avoid racing between buf read and opu dio write */
>  
>  	int i_extra_isize;		/* size of extra space located in i_addr */
>  	kprojid_t i_projid;		/* id for project quota */
> diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
> index 72ce1a522fb2..4ec260af321f 100644
> --- a/fs/f2fs/file.c
> +++ b/fs/f2fs/file.c
> @@ -4445,6 +4445,7 @@ static ssize_t f2fs_dio_read_iter(struct kiocb *iocb, struct iov_iter *to)
>  	const loff_t pos = iocb->ki_pos;
>  	const size_t count = iov_iter_count(to);
>  	struct iomap_dio *dio;
> +	bool do_opu = f2fs_lfs_mode(sbi);
>  	ssize_t ret;
>  
>  	if (count == 0)
> @@ -4457,8 +4458,14 @@ static ssize_t f2fs_dio_read_iter(struct kiocb *iocb, struct iov_iter *to)
>  			ret = -EAGAIN;
>  			goto out;
>  		}
> +		if (do_opu && !f2fs_down_read_trylock(&fi->i_opu_rwsem)) {
> +			f2fs_up_read(&fi->i_gc_rwsem[READ]);
> +			ret = -EAGAIN;
> +			goto out;
> +		}
>  	} else {
>  		f2fs_down_read(&fi->i_gc_rwsem[READ]);
> +		f2fs_down_read(&fi->i_opu_rwsem);
>  	}
>  
>  	/*
> @@ -4477,6 +4484,7 @@ static ssize_t f2fs_dio_read_iter(struct kiocb *iocb, struct iov_iter *to)
>  		ret = iomap_dio_complete(dio);
>  	}
>  
> +	f2fs_up_read(&fi->i_opu_rwsem);
>  	f2fs_up_read(&fi->i_gc_rwsem[READ]);
>  
>  	file_accessed(file);
> @@ -4523,7 +4531,13 @@ static ssize_t f2fs_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
>  	if (f2fs_should_use_dio(inode, iocb, to)) {
>  		ret = f2fs_dio_read_iter(iocb, to);
>  	} else {
> +		bool do_opu = f2fs_lfs_mode(F2FS_I_SB(inode));
> +
> +		if (do_opu)
> +			f2fs_down_read(&F2FS_I(inode)->i_opu_rwsem);
>  		ret = filemap_read(iocb, to, 0);
> +		if (do_opu)
> +			f2fs_up_read(&F2FS_I(inode)->i_opu_rwsem);
>  		if (ret > 0)
>  			f2fs_update_iostat(F2FS_I_SB(inode), inode,
>  						APP_BUFFERED_READ_IO, ret);
> @@ -4748,14 +4762,22 @@ static ssize_t f2fs_dio_write_iter(struct kiocb *iocb, struct iov_iter *from,
>  			ret = -EAGAIN;
>  			goto out;
>  		}
> +		if (do_opu && !f2fs_down_write_trylock(&fi->i_opu_rwsem)) {
> +			f2fs_up_read(&fi->i_gc_rwsem[READ]);
> +			f2fs_up_read(&fi->i_gc_rwsem[WRITE]);
> +			ret = -EAGAIN;
> +			goto out;
> +		}
>  	} else {
>  		ret = f2fs_convert_inline_inode(inode);
>  		if (ret)
>  			goto out;
>  
>  		f2fs_down_read(&fi->i_gc_rwsem[WRITE]);
> -		if (do_opu)
> +		if (do_opu) {
>  			f2fs_down_read(&fi->i_gc_rwsem[READ]);
> +			f2fs_down_write(&fi->i_opu_rwsem);
> +		}
>  	}
>  
>  	/*
> @@ -4779,8 +4801,10 @@ static ssize_t f2fs_dio_write_iter(struct kiocb *iocb, struct iov_iter *from,
>  		ret = iomap_dio_complete(dio);
>  	}
>  
> -	if (do_opu)
> +	if (do_opu) {
> +		f2fs_up_write(&fi->i_opu_rwsem);
>  		f2fs_up_read(&fi->i_gc_rwsem[READ]);
> +	}
>  	f2fs_up_read(&fi->i_gc_rwsem[WRITE]);
>  
>  	if (ret < 0)
> diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
> index daf2c4dbe150..b4ed3b094366 100644
> --- a/fs/f2fs/super.c
> +++ b/fs/f2fs/super.c
> @@ -1428,6 +1428,7 @@ static struct inode *f2fs_alloc_inode(struct super_block *sb)
>  	init_f2fs_rwsem(&fi->i_gc_rwsem[READ]);
>  	init_f2fs_rwsem(&fi->i_gc_rwsem[WRITE]);
>  	init_f2fs_rwsem(&fi->i_xattr_sem);
> +	init_f2fs_rwsem(&fi->i_opu_rwsem);
>  
>  	/* Will be used by directory only */
>  	fi->i_dir_level = F2FS_SB(sb)->dir_level;
> -- 
> 2.40.1