On 04/08/2014 12:14 PM, David Woodhouse wrote: > On Mon, 2014-04-07 at 16:43 -0400, Don Dutile wrote: >> >> Additionally, a tidbit of information like "some servers force NMI's >> on DMAR faults, >> and cause a system reset, thereby, preventing a kdump to occur" >> should have been included as one reason to stop DMAR faults from >> occurring on kexec-boot, >> in addition to the fact that a flood of them can lock up a system. > > How about allocating a physical scratch page, and setting up a mapping > for each device such that *every* virtual address (apart from those > listed in RMRRs, perhaps) is mapped to that same scratch page? > > That way you avoid the faults, but you also avoid stray DMA to parts of > the system that you don't want to get corrupted. > +1... more isolation as second kernel booting sounds good.
