Re: [PATCH v5 10/10] fs: add support for copy file range in zonefs

[Nitesh Shetty]

On Wed, Nov 23, 2022 at 08:53:14AM +0200, Amir Goldstein wrote:
> On Wed, Nov 23, 2022 at 8:26 AM Nitesh Shetty <nj.shetty@xxxxxxxxxxx> wrote:
> >
> > copy_file_range is implemented using copy offload,
> > copy offloading to device is always enabled.
> > To disable copy offloading mount with "no_copy_offload" mount option.
> > At present copy offload is only used, if the source and destination files
> > are on same block device, otherwise copy file range is completed by
> > generic copy file range.
> >
> > copy file range implemented as following:
> >         - write pending writes on the src and dest files
> >         - drop page cache for dest file if its conv zone
> >         - copy the range using offload
> >         - update dest file info
> >
> > For all failure cases we fallback to generic file copy range
> > At present this implementation does not support conv aggregation
> >
> > Signed-off-by: Nitesh Shetty <nj.shetty@xxxxxxxxxxx>
> > Signed-off-by: Anuj Gupta <anuj20.g@xxxxxxxxxxx>
> > ---
> >  fs/zonefs/super.c | 179 ++++++++++++++++++++++++++++++++++++++++++++++
> >  1 file changed, 179 insertions(+)
> >
> > diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c
> > index abc9a85106f2..15613433d4ae 100644
> > --- a/fs/zonefs/super.c
> > +++ b/fs/zonefs/super.c
> > @@ -1223,6 +1223,183 @@ static int zonefs_file_release(struct inode *inode, struct file *file)
> >         return 0;
> >  }
> >
> > +static int zonefs_is_file_copy_offset_ok(struct inode *src_inode,
> > +               struct inode *dst_inode, loff_t src_off, loff_t dst_off,
> > +               size_t *len)
> > +{
> > +       loff_t size, endoff;
> > +       struct zonefs_inode_info *dst_zi = ZONEFS_I(dst_inode);
> > +
> > +       inode_lock(src_inode);
> > +       size = i_size_read(src_inode);
> > +       inode_unlock(src_inode);
> > +       /* Don't copy beyond source file EOF. */
> > +       if (src_off < size) {
> > +               if (src_off + *len > size)
> > +                       *len = (size - (src_off + *len));
> > +       } else
> > +               *len = 0;
> > +
> > +       mutex_lock(&dst_zi->i_truncate_mutex);
> > +       if (dst_zi->i_ztype == ZONEFS_ZTYPE_SEQ) {
> > +               if (*len > dst_zi->i_max_size - dst_zi->i_wpoffset)
> > +                       *len -= dst_zi->i_max_size - dst_zi->i_wpoffset;
> > +
> > +               if (dst_off != dst_zi->i_wpoffset)
> > +                       goto err;
> > +       }
> > +       mutex_unlock(&dst_zi->i_truncate_mutex);
> > +
> > +       endoff = dst_off + *len;
> > +       inode_lock(dst_inode);
> > +       if (endoff > dst_zi->i_max_size ||
> > +                       inode_newsize_ok(dst_inode, endoff)) {
> > +               inode_unlock(dst_inode);
> > +               goto err;
> > +       }
> > +       inode_unlock(dst_inode);
> > +
> > +       return 0;
> > +err:
> > +       mutex_unlock(&dst_zi->i_truncate_mutex);
> > +       return -EINVAL;
> > +}
> > +
> > +static ssize_t zonefs_issue_copy(struct zonefs_inode_info *src_zi,
> > +               loff_t src_off, struct zonefs_inode_info *dst_zi,
> > +               loff_t dst_off, size_t len)
> > +{
> > +       struct block_device *src_bdev = src_zi->i_vnode.i_sb->s_bdev;
> > +       struct block_device *dst_bdev = dst_zi->i_vnode.i_sb->s_bdev;
> > +       struct range_entry *rlist = NULL;
> > +       int ret = len;
> > +
> > +       rlist = kmalloc(sizeof(*rlist), GFP_KERNEL);
> > +       if (!rlist)
> > +               return -ENOMEM;
> > +
> > +       rlist[0].dst = (dst_zi->i_zsector << SECTOR_SHIFT) + dst_off;
> > +       rlist[0].src = (src_zi->i_zsector << SECTOR_SHIFT) + src_off;
> > +       rlist[0].len = len;
> > +       rlist[0].comp_len = 0;
> > +       ret = blkdev_issue_copy(src_bdev, dst_bdev, rlist, 1, NULL, NULL,
> > +                       GFP_KERNEL);
> > +       if (rlist[0].comp_len > 0)
> > +               ret = rlist[0].comp_len;
> > +       kfree(rlist);
> > +
> > +       return ret;
> > +}
> > +
> > +/* Returns length of possible copy, else returns error */
> > +static ssize_t zonefs_copy_file_checks(struct file *src_file, loff_t src_off,
> > +                                       struct file *dst_file, loff_t dst_off,
> > +                                       size_t *len, unsigned int flags)
> > +{
> > +       struct inode *src_inode = file_inode(src_file);
> > +       struct inode *dst_inode = file_inode(dst_file);
> > +       struct zonefs_inode_info *src_zi = ZONEFS_I(src_inode);
> > +       struct zonefs_inode_info *dst_zi = ZONEFS_I(dst_inode);
> > +       ssize_t ret;
> > +
> > +       if (src_inode->i_sb != dst_inode->i_sb)
> > +               return -EXDEV;
> > +
> > +       /* Start by sync'ing the source and destination files for conv zones */
> > +       if (src_zi->i_ztype == ZONEFS_ZTYPE_CNV) {
> > +               ret = file_write_and_wait_range(src_file, src_off,
> > +                               (src_off + *len));
> > +               if (ret < 0)
> > +                       goto io_error;
> > +       }
> > +       inode_dio_wait(src_inode);
> > +
> > +       /* Start by sync'ing the source and destination files ifor conv zones */
> > +       if (dst_zi->i_ztype == ZONEFS_ZTYPE_CNV) {
> > +               ret = file_write_and_wait_range(dst_file, dst_off,
> > +                               (dst_off + *len));
> > +               if (ret < 0)
> > +                       goto io_error;
> > +       }
> > +       inode_dio_wait(dst_inode);
> > +
> > +       /* Drop dst file cached pages for a conv zone*/
> > +       if (dst_zi->i_ztype == ZONEFS_ZTYPE_CNV) {
> > +               ret = invalidate_inode_pages2_range(dst_inode->i_mapping,
> > +                               dst_off >> PAGE_SHIFT,
> > +                               (dst_off + *len) >> PAGE_SHIFT);
> > +               if (ret < 0)
> > +                       goto io_error;
> > +       }
> > +
> > +       ret = zonefs_is_file_copy_offset_ok(src_inode, dst_inode, src_off,
> > +                       dst_off, len);
> > +       if (ret < 0)
> > +               return ret;
> > +
> > +       return *len;
> > +
> > +io_error:
> > +       zonefs_io_error(dst_inode, true);
> > +       return ret;
> > +}
> > +
> > +static ssize_t zonefs_copy_file(struct file *src_file, loff_t src_off,
> > +               struct file *dst_file, loff_t dst_off,
> > +               size_t len, unsigned int flags)
> > +{
> > +       struct inode *src_inode = file_inode(src_file);
> > +       struct inode *dst_inode = file_inode(dst_file);
> > +       struct zonefs_inode_info *src_zi = ZONEFS_I(src_inode);
> > +       struct zonefs_inode_info *dst_zi = ZONEFS_I(dst_inode);
> > +       ssize_t ret = 0, bytes;
> > +
> > +       inode_lock(src_inode);
> > +       inode_lock(dst_inode);
> > +       bytes = zonefs_issue_copy(src_zi, src_off, dst_zi, dst_off, len);
> > +       if (bytes < 0)
> > +               goto unlock_exit;
> > +
> > +       ret += bytes;
> > +
> > +       file_update_time(dst_file);
> > +       mutex_lock(&dst_zi->i_truncate_mutex);
> > +       zonefs_update_stats(dst_inode, dst_off + bytes);
> > +       zonefs_i_size_write(dst_inode, dst_off + bytes);
> > +       dst_zi->i_wpoffset += bytes;
> > +       mutex_unlock(&dst_zi->i_truncate_mutex);
> > +       /* if we still have some bytes left, do splice copy */
> > +       if (bytes && (bytes < len)) {
> > +               bytes = do_splice_direct(src_file, &src_off, dst_file,
> > +                                        &dst_off, len, flags);
> > +               if (bytes > 0)
> > +                       ret += bytes;
> > +       }
> > +unlock_exit:
> > +       if (ret < 0)
> > +               zonefs_io_error(dst_inode, true);
> > +       inode_unlock(src_inode);
> > +       inode_unlock(dst_inode);
> > +       return ret;
> > +}
> > +
> > +static ssize_t zonefs_copy_file_range(struct file *src_file, loff_t src_off,
> > +                                     struct file *dst_file, loff_t dst_off,
> > +                                     size_t len, unsigned int flags)
> > +{
> > +       ssize_t ret = -EIO;
> > +
> > +       ret = zonefs_copy_file_checks(src_file, src_off, dst_file, dst_off,
> > +                                    &len, flags);
> > +       if (ret > 0)
> > +               ret = zonefs_copy_file(src_file, src_off, dst_file, dst_off,
> > +                                    len, flags);
> > +       else if (ret < 0 && ret == -EXDEV)
> 
> First of all, ret < 0 is redundant.
> 

acked

> > +               ret = generic_copy_file_range(src_file, src_off, dst_file,
> > +                                             dst_off, len, flags);
> 
> But more importantly, why do you want to fall back to
> do_splice_direct() in zonefs copy_file_range?
> How does it serve your patch set or the prospect consumers
> of zonefs copy_file_range?
> 
> The reason I am asking is because commit 5dae222a5ff0
> ("vfs: allow copy_file_range to copy across devices")
> turned out to be an API mistake that was later reverted by
> 868f9f2f8e00 ("vfs: fix copy_file_range() regression in cross-fs copies")
> 
> It is always better to return EXDEV to userspace which can
> always fallback to splice itself, but maybe it has something
> smarter to do.
> 
> The places where it made sense for kernel to fallback to
> direct splice was for network servers server-side-copy, but that
> is independent of any specific filesystem copy_file_range()
> implementation.
> 
> Thanks,
> Amir.
> 

At present we don't handle few case's such as IO getting split incase of
copy offload, so we wanted to fallback to existing mechanism. So went with
default operation, do_splice_direct.

Regards,
Nitesh Shetty