On Thu, Jun 02, 2011 at 12:28:53PM -0700, Richard Henderson wrote:
> On 06/02/2011 10:35 AM, Eduard - Gabriel Munteanu wrote:
> > My latest patches seem to have fixed that:
> >
> > + if (plen < *len) {
> > + *len = plen;
> > + }
> > +
> > + buf = cpu_physical_memory_map(paddr, len, is_write);
>
> No, len is (or was in previous patches) dma_addr_t which
> is not the same as target_phys_addr_t.
>
> Which is why plen was used before, because it was the
> right type.
Ah, indeed, this is a bug. It probably slipped through because the
pointers are compatible on x86-64. Thanks for pointing it out.
Eduard
> r~
