>>> On 14.05.15 at 17:06, <roger....@citrix.com> wrote:
> @@ -3584,12 +3591,8 @@ int shadow_track_dirty_vram(struct domain *d,
> rc = -ENODATA;
> }
> else if (dirty_vram->last_dirty == -1)
> - {
> /* still completely clean, just copy our empty bitmap */
> - rc = -EFAULT;
> - if ( copy_to_guest(dirty_bitmap, dirty_vram->dirty_bitmap,
> dirty_size) == 0 )
> - rc = 0;
> - }
> + memcpy(dirty_bitmap, dirty_vram->dirty_bitmap, dirty_size);
Btw, having looked at this again in the context of the coverity issue
it causes - wouldn't this (according to the retained comment) be a
memset()? And if so, in turn a loop over clear_page()?
Which gets me to a second thing: With the large amounts of data
being pushed through copy_to_guest() here and in its HAP
counterpart, wouldn't it make sense to have a specialized function
avoiding cache thrashing along the lines of clear_page() and
copy_page()?
Jan
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
http://lists.xen.org/xen-devel
