[PATCH v3] vfs: fix copy_file_range regression in cross-fs copies

[Amir Goldstein]

On Wed, Feb 17, 2021 at 7:25 PM Luis Henriques <lhenriques at suse.de> wrote:
>
> A regression has been reported by Nicolas Boichat, found while using the
> copy_file_range syscall to copy a tracefs file.  Before commit
> 5dae222a5ff0 ("vfs: allow copy_file_range to copy across devices") the
> kernel would return -EXDEV to userspace when trying to copy a file across
> different filesystems.  After this commit, the syscall doesn't fail anymore
> and instead returns zero (zero bytes copied), as this file's content is
> generated on-the-fly and thus reports a size of zero.
>
> This patch restores some cross-filesystems copy restrictions that existed
> prior to commit 5dae222a5ff0 ("vfs: allow copy_file_range to copy across
> devices").  It also introduces a flag (COPY_FILE_SPLICE) that can be used
> by filesystems calling directly into the vfs copy_file_range to override
> these restrictions.  Right now, only NFS needs to set this flag.
>
> Fixes: 5dae222a5ff0 ("vfs: allow copy_file_range to copy across devices")
> Link: https://lore.kernel.org/linux-fsdevel/20210212044405.4120619-1-drinkcat@chromium.org/
> Link: https://lore.kernel.org/linux-fsdevel/CANMq1KDZuxir2LM5jOTm0xx+BnvW=ZmpsG47CyHFJwnw7zSX6Q@mail.gmail.com/
> Link: https://lore.kernel.org/linux-fsdevel/20210126135012.1.If45b7cdc3ff707bc1efa17f5366057d60603c45f@changeid/
> Reported-by: Nicolas Boichat <drinkcat at chromium.org>
> Signed-off-by: Luis Henriques <lhenriques at suse.de>
> ---
> Ok, I've tried to address all the issues and comments.  Hopefully this v3
> is a bit closer to the final fix.
>
> Changes since v2
> - do all the required checks earlier, in generic_copy_file_checks(),
>   adding new checks for ->remap_file_range
> - new COPY_FILE_SPLICE flag
> - don't remove filesystem's fallback to generic_copy_file_range()
> - updated commit changelog (and subject)
> Changes since v1 (after Amir review)
> - restored do_copy_file_range() helper
> - return -EOPNOTSUPP if fs doesn't implement CFR
> - updated commit description
>
>  fs/nfsd/vfs.c      |  3 ++-
>  fs/read_write.c    | 44 +++++++++++++++++++++++++++++++++++++++++---
>  include/linux/fs.h |  7 +++++++
>  3 files changed, 50 insertions(+), 4 deletions(-)
>
> diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
> index 04937e51de56..14e55822c223 100644
> --- a/fs/nfsd/vfs.c
> +++ b/fs/nfsd/vfs.c
> @@ -578,7 +578,8 @@ ssize_t nfsd_copy_file_range(struct file *src, u64 src_pos, struct file *dst,
>          * limit like this and pipeline multiple COPY requests.
>          */
>         count = min_t(u64, count, 1 << 22);
> -       return vfs_copy_file_range(src, src_pos, dst, dst_pos, count, 0);
> +       return vfs_copy_file_range(src, src_pos, dst, dst_pos, count,
> +                                  COPY_FILE_SPLICE);
>  }
>
>  __be32 nfsd4_vfs_fallocate(struct svc_rqst *rqstp, struct svc_fh *fhp,
> diff --git a/fs/read_write.c b/fs/read_write.c
> index 75f764b43418..40a16003fb05 100644
> --- a/fs/read_write.c
> +++ b/fs/read_write.c
> @@ -1410,6 +1410,33 @@ static ssize_t do_copy_file_range(struct file *file_in, loff_t pos_in,
>                                        flags);
>  }
>
> +/*
> + * This helper function checks whether copy_file_range can actually be used,
> + * depending on the source and destination filesystems being the same.
> + *
> + * In-kernel callers may set COPY_FILE_SPLICE to override these checks.
> + */
> +static int fops_copy_file_checks(struct file *file_in, struct file *file_out,
> +                                unsigned int flags)
> +{
> +       if (WARN_ON_ONCE(flags & ~COPY_FILE_SPLICE))
> +               return -EINVAL;
> +
> +       if (flags & COPY_FILE_SPLICE)
> +               return 0;
> +       /*
> +        * We got here from userspace, so forbid copies if copy_file_range isn't
> +        * implemented or if we're doing a cross-fs copy.
> +        */

Suggest:

       if (!file_in->f_op->copy_file_range) {
               if (file_in->f_op->copy_file_range !=
                   file_out->f_op->copy_file_range)
                   return -EXDEV;
       } else if (file_in->f_op->remap_file_range) {
               if (file_inode(file_in)->i_sb != file_inode(file_out)->i_sb)
                    return -EXDEV;
       } else {
                return -EOPNOTSUPP;
       }

       return 0;
}

> +
>  /*
>   * Performs necessary checks before doing a file copy
>   *
> @@ -1427,6 +1454,14 @@ static int generic_copy_file_checks(struct file *file_in, loff_t pos_in,
>         loff_t size_in;
>         int ret;
>
> +       /* Only check f_ops if we're not trying to clone */
> +       if (!file_in->f_op->remap_file_range ||
> +           (file_inode(file_in)->i_sb == file_inode(file_out)->i_sb)) {
> +               ret = fops_copy_file_checks(file_in, file_out, flags);
> +               if (ret)
> +                       return ret;
> +       }
> +

and then you don't need this special casing of clone here.

>         ret = generic_file_rw_checks(file_in, file_out);
>         if (ret)
>                 return ret;
> @@ -1474,9 +1509,6 @@ ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in,
>  {
>         ssize_t ret;
>
> -       if (flags != 0)
> -               return -EINVAL;
> -
>         ret = generic_copy_file_checks(file_in, pos_in, file_out, pos_out, &len,
>                                        flags);
>         if (unlikely(ret))
> @@ -1511,6 +1543,9 @@ ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in,
>                         ret = cloned;
>                         goto done;
>                 }
> +               ret = fops_copy_file_checks(file_in, file_out, flags);
> +               if (ret)
> +                       return ret;

and you don't need this here (right?)

and you can remove the checks for same i_sb and same copy_file_range
op that were already tested from vfs_copy_file_range().

Hope I am not missing anything.

Thanks,
Amir.