On 15/01/15 16:18, Jan Beulich wrote:
>
> Wouldn't most of the changes up to here make a nice preparatory
> cleanup patch, easing review?
Yes, so...
> Leaving aside those mostly mechanical comments, content wise the
> patch looks good to me, but I'd hope for at least one other review.
,.. it mi
>>> On 13.01.15 at 11:46, wrote:
> --- a/xen/common/grant_table.c
> +++ b/xen/common/grant_table.c
> @@ -2077,152 +2077,293 @@ __acquire_grant_for_copy(
> return rc;
> }
>
> -static void
> -__gnttab_copy(
> -struct gnttab_copy *op)
> +struct gnttab_copy_buf {
> +/* guest provided.
Acquiring a page for the source or destination of a grant copy is an
expensive operation. A common use case is for two adjacent grant copy
ops to operate on either the same source or the same destination page.
Instead of always acquiring and releasing destination and source pages
for each operati