[ofa-general] Re: mapping kernel memory to userspace in <= 2.6.14

[Steve Wise]

On Wed, 2007-03-14 at 07:19 +0200, Michael S. Tsirkin wrote:
> > I figured out why I was hitting the BUG_ON() in page_remove_rmap().  Its
> > because my library was destroying the QP or CQ object _before_ unmaping
> > the objects.  I changed it to unmap first, and things work as expected.
> 
> I guess kernel side also needs to be fixed, otherwise buggy userspace
> can trigger BUG_ON's?
> 

a buggy provider library.