Re: [f2fs-dev] [PATCH v3] f2fs: don't use GFP_ZERO for page caches

[Chao Yu <yuchao0@huawei.com>]

On 2018/4/10 11:29, Jaegeuk Kim wrote:
> Change log from v2:
>  - consider IO error case when dealing with metapage
>  - memset by fill_node_footer
> 
> Change log from v1:
>  - don't memset for recovered page
>  
> Related to https://lkml.org/lkml/2018/4/8/661
> 
> Sometimes, we need to write meta data to new allocated block address,
> then we will allocate a zeroed page in inner inode's address space, and
> fill partial data in it, and leave other place with zero value which means
> some fields are initial status.
> 
> There are two inner inodes (meta inode and node inode) setting __GFP_ZERO,
> I have just checked them, for both of them, we can avoid using __GFP_ZERO,
> and do initialization by ourselves to avoid unneeded/redundant zeroing
> from mm.
> 
> Cc: <stable@vger.kernel.org>
> Signed-off-by: Chao Yu <yuchao0@huawei.com>
> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
> ---
>  fs/f2fs/checkpoint.c | 4 +++-
>  fs/f2fs/inode.c      | 4 ++--
>  fs/f2fs/segment.c    | 3 +++
>  fs/f2fs/segment.h    | 1 +
>  4 files changed, 9 insertions(+), 3 deletions(-)
> 
> diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
> index bf779461df13..2e23b953d304 100644
> --- a/fs/f2fs/checkpoint.c
> +++ b/fs/f2fs/checkpoint.c
> @@ -100,8 +100,10 @@ static struct page *__get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index,
>  	 * readonly and make sure do not write checkpoint with non-uptodate
>  	 * meta page.
>  	 */
> -	if (unlikely(!PageUptodate(page)))
> +	if (unlikely(!PageUptodate(page))) {
> +		memset(page_address(page), 0, PAGE_SIZE);
>  		f2fs_stop_checkpoint(sbi, false);
> +	}
>  out:
>  	return page;
>  }
> diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c
> index 417c9dcd0269..87535bf63421 100644
> --- a/fs/f2fs/inode.c
> +++ b/fs/f2fs/inode.c
> @@ -320,10 +320,10 @@ struct inode *f2fs_iget(struct super_block *sb, unsigned long ino)
>  make_now:
>  	if (ino == F2FS_NODE_INO(sbi)) {
>  		inode->i_mapping->a_ops = &f2fs_node_aops;
> -		mapping_set_gfp_mask(inode->i_mapping, GFP_F2FS_ZERO);
> +		mapping_set_gfp_mask(inode->i_mapping, GFP_NOFS);
>  	} else if (ino == F2FS_META_INO(sbi)) {
>  		inode->i_mapping->a_ops = &f2fs_meta_aops;
> -		mapping_set_gfp_mask(inode->i_mapping, GFP_F2FS_ZERO);
> +		mapping_set_gfp_mask(inode->i_mapping, GFP_NOFS);
>  	} else if (S_ISREG(inode->i_mode)) {
>  		inode->i_op = &f2fs_file_inode_operations;
>  		inode->i_fop = &f2fs_file_operations;
> diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
> index a4b8e3e24ccb..1f5db557ab96 100644
> --- a/fs/f2fs/segment.c
> +++ b/fs/f2fs/segment.c
> @@ -2021,6 +2021,7 @@ static void write_current_sum_page(struct f2fs_sb_info *sbi,
>  	struct f2fs_summary_block *dst;
>  
>  	dst = (struct f2fs_summary_block *)page_address(page);
> +	memset(dst, 0, PAGE_SIZE);

We will fill all summary page later, so we don't need initialize it?

>  
>  	mutex_lock(&curseg->curseg_mutex);
>  
> @@ -3117,6 +3118,7 @@ static void write_compacted_summaries(struct f2fs_sb_info *sbi, block_t blkaddr)
>  
>  	page = grab_meta_page(sbi, blkaddr++);
>  	kaddr = (unsigned char *)page_address(page);
> +	memset(kaddr, 0, PAGE_SIZE);

I checked here, we will not use uninitialized space due to:

read_compacted_summaries()
{
...
	if (offset + SUMMARY_SIZE <= PAGE_SIZE - SUM_FOOTER_SIZE)
		continue;
...
}

Are we safe here?

>  
>  	/* Step 1: write nat cache */
>  	seg_i = CURSEG_I(sbi, CURSEG_HOT_DATA);
> @@ -3141,6 +3143,7 @@ static void write_compacted_summaries(struct f2fs_sb_info *sbi, block_t blkaddr)
>  			if (!page) {
>  				page = grab_meta_page(sbi, blkaddr++);
>  				kaddr = (unsigned char *)page_address(page);
> +				memset(kaddr, 0, PAGE_SIZE);

Ditto.

>  				written_size = 0;
>  			}
>  			summary = (struct f2fs_summary *)(kaddr + written_size);
> diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h
> index 3325d0769723..492ad0c86fa9 100644
> --- a/fs/f2fs/segment.h
> +++ b/fs/f2fs/segment.h
> @@ -375,6 +375,7 @@ static inline void seg_info_to_sit_page(struct f2fs_sb_info *sbi,
>  	int i;
>  
>  	raw_sit = (struct f2fs_sit_block *)page_address(page);
> +	memset(raw_sit, 0, PAGE_SIZE);

I suspect that root cause of panic is that we don't memset here?

Thanks,

>  	for (i = 0; i < end - start; i++) {
>  		rs = &raw_sit->entries[i];
>  		se = get_seg_entry(sbi, start + i);
>