Re: [PATCH 2/2] Use fiemap internal infra-structure to handle FIBMAP

[Eric Sandeen <sandeen@redhat.com>]

On 9/5/18 8:57 AM, Carlos Maiolino wrote:
> This patch modifies ioctl_fibmap to use FIEMAP interface internally. The
> FIBMAP API is not changed, but now ->bmap can go.

Not really, because you still call it if ->fiemap isn't there ;)

> 
> Signed-off-by: Carlos Maiolino <cmaiolino@redhat.com>
> ---
>  fs/inode.c                  | 38 +++++++++++++++++++++++++++++++++++++-
>  fs/ioctl.c                  | 11 +++++++++--
>  include/uapi/linux/fiemap.h |  1 +
>  3 files changed, 47 insertions(+), 3 deletions(-)
> 
> diff --git a/fs/inode.c b/fs/inode.c
> index 41812a3e829e..07befc5f253b 100644
> --- a/fs/inode.c
> +++ b/fs/inode.c
> @@ -1588,9 +1588,45 @@ EXPORT_SYMBOL(iput);
>   */
>  sector_t bmap(struct inode *inode, sector_t block)
>  {
> +
> +	struct fiemap_extent_info fieinfo = { 0, };
> +	struct fiemap_extent fextent;
> +	u64 start = block << inode->i_blkbits;
> +	int error;
>  	sector_t res = 0;
> -	if (inode->i_mapping->a_ops->bmap)
> +
> +	if (inode->i_op->fiemap) {
> +		fextent.fe_logical = 0;
> +		fextent.fe_physical = 0;
> +		fieinfo.fi_flags = FIEMAP_KERNEL_FIBMAP;

| FIEMAP_FLAG_SYNC?

> +		fieinfo.fi_extents_max = 1;
> +		fieinfo.fi_extents_start = (__force struct fiemap_extent __user *) &fextent;
> +
> +		error = inode->i_op->fiemap(inode, &fieinfo, start, 1);
> +
> +		/* FIBMAP expect a zero return for error */
> +		if (error)
> +			goto out;

do you need to test fieinfo.fi_extents_mapped > 0?  I don't know if it's
possible to return error == 0 && fi_extents_mapped == 0, TBH.

> +
> +		/*
> +		 * Fiemap implementation of some filesystems will return the
> +		 * extent map beginning at the requested offset
> +		 * (fextent.fi_logical == start), while other FSes will return
> +		 * the beginning of the extent at fextent.fe_logical, even if
> +		 * the requested offset is somehwere in the middle of the
> +		 * extent. We must be sure to return the correct block block
> +		 * here in both cases.
> +		 */
> +		if (fextent.fe_logical != start)
> +			res = (fextent.fe_physical + start) >> inode->i_blkbits;

I don't think this is correct, is it?  You can't add the entire requested
logical file offset (start) to the resulting physical extent start (fe_physical).

You'd need to add the delta, (start - fextent.fe_logical) to the physical extent
start to get the offset into the mapping, right?

		res = (fextent.fe_physical +
		       (start - fextent.fe_logical)) >> inode->i_blkbits;

You'll also need to test the resulting fm_flags to be sure that
this is something that's valid to return via FIBMAP.

For example, you might get a shared block, which we have recently learned
Must Not Be Provided Under Any Circumstances to userspace via FIBMAP.

(I'm still thinking about how this change is structured in general, but I think
the above are a few logical issues w/ the code.)

-Eric

> +		else
> +			res = fextent.fe_physical >> inode->i_blkbits;
> +
> +	} else if (inode->i_mapping->a_ops->bmap) {
>  		res = inode->i_mapping->a_ops->bmap(inode->i_mapping, block);
> +	}
> +
> +out:
>  	return res;
>  }
>  EXPORT_SYMBOL(bmap);
> diff --git a/fs/ioctl.c b/fs/ioctl.c
> index 413585d58415..58de1dd507b1 100644
> --- a/fs/ioctl.c
> +++ b/fs/ioctl.c
> @@ -117,8 +117,14 @@ int fiemap_fill_next_extent(struct fiemap_extent_info *fieinfo, u64 logical,
>  	extent.fe_flags = flags;
>  
>  	dest += fieinfo->fi_extents_mapped;
> -	if (copy_to_user(dest, &extent, sizeof(extent)))
> -		return -EFAULT;
> +
> +	if (fieinfo->fi_flags & FIEMAP_KERNEL_FIBMAP) {
> +		memcpy((__force struct fiemap_extent *)dest, &extent,
> +		       sizeof(extent));
> +	} else {
> +		if (copy_to_user(dest, &extent, sizeof(extent)))
> +			return -EFAULT;
> +	}
>  
>  	fieinfo->fi_extents_mapped++;
>  	if (fieinfo->fi_extents_mapped == fieinfo->fi_extents_max)
> @@ -146,6 +152,7 @@ int fiemap_check_flags(struct fiemap_extent_info *fieinfo, u32 fs_flags)
>  	u32 incompat_flags;
>  
>  	incompat_flags = fieinfo->fi_flags & ~(FIEMAP_FLAGS_COMPAT & fs_flags);
> +	incompat_flags &= ~(FIEMAP_KERNEL_FIBMAP);
>  	if (incompat_flags) {
>  		fieinfo->fi_flags = incompat_flags;
>  		return -EBADR;
> diff --git a/include/uapi/linux/fiemap.h b/include/uapi/linux/fiemap.h
> index 8c0bc24d5d95..7064a3fa5421 100644
> --- a/include/uapi/linux/fiemap.h
> +++ b/include/uapi/linux/fiemap.h
> @@ -42,6 +42,7 @@ struct fiemap {
>  #define FIEMAP_FLAG_SYNC	0x00000001 /* sync file data before map */
>  #define FIEMAP_FLAG_XATTR	0x00000002 /* map extended attribute tree */
>  #define FIEMAP_FLAG_CACHE	0x00000004 /* request caching of the extents */
> +#define FIEMAP_KERNEL_FIBMAP	0x00000008 /* Use FIEMAP for FIBMAP */
>  
>  #define FIEMAP_FLAGS_COMPAT	(FIEMAP_FLAG_SYNC | FIEMAP_FLAG_XATTR)
>  
>