Received-SPF: pass (google.com: domain of linux-ext4+bounces-1260-linux.lists.archive=gmail.com@vger.kernel.org designates 139.178.88.99 as permitted sender) client-ip=139.178.88.99;
Subject: Re: [RFC PATCH v3 07/26] iomap: don't increase i_size if it's not a
 write operation
To: Christoph Hellwig <hch@infradead.org>
Cc: linux-ext4@vger.kernel.org, linux-fsdevel@vger.kernel.org,
 linux-mm@kvack.org, linux-kernel@vger.kernel.org, tytso@mit.edu,
 adilger.kernel@dilger.ca, jack@suse.cz, ritesh.list@gmail.com,
 djwong@kernel.org, willy@infradead.org, zokeefe@google.com,
 yi.zhang@huawei.com, chengzhihao1@huawei.com, yukuai3@huawei.com,
 wangkefeng.wang@huawei.com
References: <20240127015825.1608160-1-yi.zhang@huaweicloud.com>
 <20240127015825.1608160-8-yi.zhang@huaweicloud.com>
 <ZcsCP4h-ExNOcdD6@infradead.org>
From: Zhang Yi <yi.zhang@huaweicloud.com>
Message-ID: <74ab3c3e-3daf-5374-75e5-bcb25ffdb527@huaweicloud.com>
Date: Sat, 17 Feb 2024 16:55:51 +0800
User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:78.0) Gecko/20100101
 Thunderbird/78.12.0
Precedence: bulk
MIME-Version: 1.0
In-Reply-To: <ZcsCP4h-ExNOcdD6@infradead.org>
Content-Type: text/plain; charset=utf-8
Content-Language: en-US
Content-Transfer-Encoding: 7bit

On 2024/2/13 13:46, Christoph Hellwig wrote:
> Wouldn't it make more sense to just move the size manipulation to the
> write-only code?  An untested version of that is below.  With this

Sorry for the late reply and thanks for your suggestion, The reason why
I introduced this new helper iomap_write_end_simple() is I don't want to
open code __iomap_put_folio() in each caller since corresponding to
iomap_write_begin(), it's the responsibility for iomap_write_end_*() to
put and unlock folio, so I'd like to keep it in iomap_write_end_*().
But I don't feel strongly about it, it's also fine by me to just move
the size manipulation to the write-only code if you think it's better.

> the naming of the status variable becomes even more confusing than
> it already is, maybe we need to do a cleanup of the *_write_end
> calling conventions as it always returns the passed in copied value
> or 0.

Indeed, it becomes more confused and deserve a cleanup.

Thanks,
Yi.

> 
> diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
> index 3dab060aed6d7b..8401a9ca702fc0 100644
> --- a/fs/iomap/buffered-io.c
> +++ b/fs/iomap/buffered-io.c
> @@ -876,34 +876,13 @@ static size_t iomap_write_end(struct iomap_iter *iter, loff_t pos, size_t len,
>  		size_t copied, struct folio *folio)
>  {
>  	const struct iomap *srcmap = iomap_iter_srcmap(iter);
> -	loff_t old_size = iter->inode->i_size;
> -	size_t ret;
> -
> -	if (srcmap->type == IOMAP_INLINE) {
> -		ret = iomap_write_end_inline(iter, folio, pos, copied);
> -	} else if (srcmap->flags & IOMAP_F_BUFFER_HEAD) {
> -		ret = block_write_end(NULL, iter->inode->i_mapping, pos, len,
> -				copied, &folio->page, NULL);
> -	} else {
> -		ret = __iomap_write_end(iter->inode, pos, len, copied, folio);
> -	}
> -
> -	/*
> -	 * Update the in-memory inode size after copying the data into the page
> -	 * cache.  It's up to the file system to write the updated size to disk,
> -	 * preferably after I/O completion so that no stale data is exposed.
> -	 */
> -	if (pos + ret > old_size) {
> -		i_size_write(iter->inode, pos + ret);
> -		iter->iomap.flags |= IOMAP_F_SIZE_CHANGED;
> -	}
> -	__iomap_put_folio(iter, pos, ret, folio);
>  
> -	if (old_size < pos)
> -		pagecache_isize_extended(iter->inode, old_size, pos);
> -	if (ret < len)
> -		iomap_write_failed(iter->inode, pos + ret, len - ret);
> -	return ret;
> +	if (srcmap->type == IOMAP_INLINE)
> +		return iomap_write_end_inline(iter, folio, pos, copied);
> +	if (srcmap->flags & IOMAP_F_BUFFER_HEAD)
> +		return block_write_end(NULL, iter->inode->i_mapping, pos, len,
> +					copied, &folio->page, NULL);
> +	return __iomap_write_end(iter->inode, pos, len, copied, folio);
>  }
>  
>  static loff_t iomap_write_iter(struct iomap_iter *iter, struct iov_iter *i)
> @@ -918,6 +897,7 @@ static loff_t iomap_write_iter(struct iomap_iter *iter, struct iov_iter *i)
>  
>  	do {
>  		struct folio *folio;
> +		loff_t old_size;
>  		size_t offset;		/* Offset into folio */
>  		size_t bytes;		/* Bytes to write to folio */
>  		size_t copied;		/* Bytes copied from user */
> @@ -964,7 +944,24 @@ static loff_t iomap_write_iter(struct iomap_iter *iter, struct iov_iter *i)
>  
>  		copied = copy_folio_from_iter_atomic(folio, offset, bytes, i);
>  		status = iomap_write_end(iter, pos, bytes, copied, folio);
> +		/*
> +		 * Update the in-memory inode size after copying the data into
> +		 * the page cache.  It's up to the file system to write the
> +		 * updated size to disk, preferably after I/O completion so that
> +		 * no stale data is exposed.
> +		 */
> +		old_size = iter->inode->i_size;
> +		if (pos + status > old_size) {
> +			i_size_write(iter->inode, pos + status);
> +			iter->iomap.flags |= IOMAP_F_SIZE_CHANGED;
> +		}
> +		__iomap_put_folio(iter, pos, status, folio);
>  
> +		if (old_size < pos)
> +			pagecache_isize_extended(iter->inode, old_size, pos);
> +		if (status < bytes)
> +			iomap_write_failed(iter->inode, pos + status,
> +						bytes - status);
>  		if (unlikely(copied != status))
>  			iov_iter_revert(i, copied - status);
>  
> @@ -1334,6 +1331,7 @@ static loff_t iomap_unshare_iter(struct iomap_iter *iter)
>  			bytes = folio_size(folio) - offset;
>  
>  		bytes = iomap_write_end(iter, pos, bytes, bytes, folio);
> +		__iomap_put_folio(iter, pos, bytes, folio);
>  		if (WARN_ON_ONCE(bytes == 0))
>  			return -EIO;
>  
> @@ -1398,6 +1396,7 @@ static loff_t iomap_zero_iter(struct iomap_iter *iter, bool *did_zero)
>  		folio_mark_accessed(folio);
>  
>  		bytes = iomap_write_end(iter, pos, bytes, bytes, folio);
> +		__iomap_put_folio(iter, pos, bytes, folio);
>  		if (WARN_ON_ONCE(bytes == 0))
>  			return -EIO;
>  
>