On Fri, Jul 29, 2022 at 04:07:36PM -0700, Tony Luck wrote: > On Fri, Jul 29, 2022 at 03:54:58PM -0700, Dave Hansen wrote: > > On 7/29/22 14:46, Pawan Gupta wrote: > > > Let me see if there is a way to distinguish between 4. and 5. below: > > > > > > CPU category X86_BUG_MMIO_STALE_DATA X86_BUG_MMIO_UNKNOWN > > > ----------------------------------------------------------------------------------------------- > > > 1. Known affected (in cpu list) 1 0 > > > 2. CPUs with HW immunity (MMIO_NO=1) 0 0 > > > 3. Other vendors 0 0 > > > 4. Older Intel CPUs 0 1 > > > 5. Not affected current CPUs (but MMIO_NO=0) 0 ? > > > > This seems like something we would need to go back to our colleagues to > > figure out. Basically, at the time of publishing the > > X86_BUG_MMIO_STALE_DATA papers, what was considered "older"? > > > > In other words, we need the folks at Intel that did this good work to > > _show_ their work (at least part of it). > > https://www.intel.com/content/www/us/en/developer/topic-technology/software-security-guidance/processors-affected-consolidated-product-cpu-model.html > > Click to the 2022 tab. The MMIO affected/not-affected status is there > (you'll need to use the horizontal scroll to shift over to see those > columns). > > This table lists all the CPUs that were not "older". > > Any CPU not on that list is out of servicing period. I thought about this option, this will require CPUs to be added to whitelist too. If the maintainers wont hate it, I will go this route.
