Re: [PATCH v4 01/10] ext4: remove writable userspace mappings before truncating page cache

[Jan Kara]

On Mon 16-12-24 09:39:06, Zhang Yi wrote:
> From: Zhang Yi <yi.zhang@xxxxxxxxxx>
> 
> When zeroing a range of folios on the filesystem which block size is
> less than the page size, the file's mapped blocks within one page will
> be marked as unwritten, we should remove writable userspace mappings to
> ensure that ext4_page_mkwrite() can be called during subsequent write
> access to these partial folios. Otherwise, data written by subsequent
> mmap writes may not be saved to disk.
> 
>  $mkfs.ext4 -b 1024 /dev/vdb
>  $mount /dev/vdb /mnt
>  $xfs_io -t -f -c "pwrite -S 0x58 0 4096" -c "mmap -rw 0 4096" \
>                -c "mwrite -S 0x5a 2048 2048" -c "fzero 2048 2048" \
>                -c "mwrite -S 0x59 2048 2048" -c "close" /mnt/foo
> 
>  $od -Ax -t x1z /mnt/foo
>  000000 58 58 58 58 58 58 58 58 58 58 58 58 58 58 58 58
>  *
>  000800 59 59 59 59 59 59 59 59 59 59 59 59 59 59 59 59
>  *
>  001000
> 
>  $umount /mnt && mount /dev/vdb /mnt
>  $od -Ax -t x1z /mnt/foo
>  000000 58 58 58 58 58 58 58 58 58 58 58 58 58 58 58 58
>  *
>  000800 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
>  *
>  001000
> 
> Fix this by introducing ext4_truncate_page_cache_block_range() to remove
> writable userspace mappings when truncating a partial folio range.
> Additionally, move the journal data mode-specific handlers and
> truncate_pagecache_range() into this function, allowing it to serve as a
> common helper that correctly manages the page cache in preparation for
> block range manipulations.
> 
> Signed-off-by: Zhang Yi <yi.zhang@xxxxxxxxxx>

I like the patch. Feel free to add:

Reviewed-by: Jan Kara <jack@xxxxxxx>

Just one thing occured to me when thinking about this: It seems like a
nasty catch that truncate_inode_pages_range() does not writeprotect these
partial pages because practically any filesystem supporting blocksize <
pagesize and doing anything non-trivial in ->page_mkwrite handler will need
this. So ultimately I think we might want to fix this in generic code but
ext4 solution is fine for now.

								Honza
> ---
>  fs/ext4/ext4.h    |  2 ++
>  fs/ext4/extents.c | 19 ++++-----------
>  fs/ext4/inode.c   | 62 +++++++++++++++++++++++++++++++++++++++++++++++
>  3 files changed, 69 insertions(+), 14 deletions(-)
> 
> diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
> index 74f2071189b2..8843929b46ce 100644
> --- a/fs/ext4/ext4.h
> +++ b/fs/ext4/ext4.h
> @@ -3016,6 +3016,8 @@ extern int ext4_inode_attach_jinode(struct inode *inode);
>  extern int ext4_can_truncate(struct inode *inode);
>  extern int ext4_truncate(struct inode *);
>  extern int ext4_break_layouts(struct inode *);
> +extern int ext4_truncate_page_cache_block_range(struct inode *inode,
> +						loff_t start, loff_t end);
>  extern int ext4_punch_hole(struct file *file, loff_t offset, loff_t length);
>  extern void ext4_set_inode_flags(struct inode *, bool init);
>  extern int ext4_alloc_da_blocks(struct inode *inode);
> diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
> index a07a98a4b97a..8dc6b4271b15 100644
> --- a/fs/ext4/extents.c
> +++ b/fs/ext4/extents.c
> @@ -4667,22 +4667,13 @@ static long ext4_zero_range(struct file *file, loff_t offset,
>  			goto out_mutex;
>  		}
>  
> -		/*
> -		 * For journalled data we need to write (and checkpoint) pages
> -		 * before discarding page cache to avoid inconsitent data on
> -		 * disk in case of crash before zeroing trans is committed.
> -		 */
> -		if (ext4_should_journal_data(inode)) {
> -			ret = filemap_write_and_wait_range(mapping, start,
> -							   end - 1);
> -			if (ret) {
> -				filemap_invalidate_unlock(mapping);
> -				goto out_mutex;
> -			}
> +		/* Now release the pages and zero block aligned part of pages */
> +		ret = ext4_truncate_page_cache_block_range(inode, start, end);
> +		if (ret) {
> +			filemap_invalidate_unlock(mapping);
> +			goto out_mutex;
>  		}
>  
> -		/* Now release the pages and zero block aligned part of pages */
> -		truncate_pagecache_range(inode, start, end - 1);
>  		inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode));
>  
>  		ret = ext4_alloc_file_blocks(file, lblk, max_blocks, new_size,
> diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
> index 89aade6f45f6..c68a8b841148 100644
> --- a/fs/ext4/inode.c
> +++ b/fs/ext4/inode.c
> @@ -31,6 +31,7 @@
>  #include <linux/writeback.h>
>  #include <linux/pagevec.h>
>  #include <linux/mpage.h>
> +#include <linux/rmap.h>
>  #include <linux/namei.h>
>  #include <linux/uio.h>
>  #include <linux/bio.h>
> @@ -3902,6 +3903,67 @@ int ext4_update_disksize_before_punch(struct inode *inode, loff_t offset,
>  	return ret;
>  }
>  
> +static inline void ext4_truncate_folio(struct inode *inode,
> +				       loff_t start, loff_t end)
> +{
> +	unsigned long blocksize = i_blocksize(inode);
> +	struct folio *folio;
> +
> +	/* Nothing to be done if no complete block needs to be truncated. */
> +	if (round_up(start, blocksize) >= round_down(end, blocksize))
> +		return;
> +
> +	folio = filemap_lock_folio(inode->i_mapping, start >> PAGE_SHIFT);
> +	if (IS_ERR(folio))
> +		return;
> +
> +	if (folio_mkclean(folio))
> +		folio_mark_dirty(folio);
> +	folio_unlock(folio);
> +	folio_put(folio);
> +}
> +
> +int ext4_truncate_page_cache_block_range(struct inode *inode,
> +					 loff_t start, loff_t end)
> +{
> +	unsigned long blocksize = i_blocksize(inode);
> +	int ret;
> +
> +	/*
> +	 * For journalled data we need to write (and checkpoint) pages
> +	 * before discarding page cache to avoid inconsitent data on disk
> +	 * in case of crash before freeing or unwritten converting trans
> +	 * is committed.
> +	 */
> +	if (ext4_should_journal_data(inode)) {
> +		ret = filemap_write_and_wait_range(inode->i_mapping, start,
> +						   end - 1);
> +		if (ret)
> +			return ret;
> +		goto truncate_pagecache;
> +	}
> +
> +	/*
> +	 * If the block size is less than the page size, the file's mapped
> +	 * blocks within one page could be freed or converted to unwritten.
> +	 * So it's necessary to remove writable userspace mappings, and then
> +	 * ext4_page_mkwrite() can be called during subsequent write access
> +	 * to these partial folios.
> +	 */
> +	if (blocksize < PAGE_SIZE && start < inode->i_size) {
> +		loff_t start_boundary = round_up(start, PAGE_SIZE);
> +
> +		ext4_truncate_folio(inode, start, min(start_boundary, end));
> +		if (end > start_boundary)
> +			ext4_truncate_folio(inode,
> +					    round_down(end, PAGE_SIZE), end);
> +	}
> +
> +truncate_pagecache:
> +	truncate_pagecache_range(inode, start, end - 1);
> +	return 0;
> +}
> +
>  static void ext4_wait_dax_page(struct inode *inode)
>  {
>  	filemap_invalidate_unlock(inode->i_mapping);
> -- 
> 2.46.1
> 
-- 
Jan Kara <jack@xxxxxxxx>
SUSE Labs, CR