Hi Zoltan, The architecture defines that only mandatory (=demand) RSE accesses can fault, background RSE activity never raises faults - see SDM II.6.6. (In any case, current processors don't implement eager mode, so RSE accesses are only done on demand anyway...) Matt On Mon, Feb 18, 2008 at 02:32:10PM +0100, Zoltan Menyhart wrote: > Let's assume a user program just has been interrupted. > The RSE can continue spilling/filling registers on behalf of the > interrupted user. > Let's assume the RSE engine touches a swapped out page. > As PSR.ic is 0, the page fault cannot be captured correctly. > > Can this scenario happen to the current Linux kernel implementation? > > Thanks, > > Zoltan Menyhart > > - > To unsubscribe from this list: send the line "unsubscribe linux-ia64" in > the body of a message to majordomo@xxxxxxxxxxxxxxx > More majordomo info at http://vger.kernel.org/majordomo-info.html - To unsubscribe from this list: send the line "unsubscribe linux-ia64" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
![]() |