Linux page table isolation is not needed on AMD processors

Re:Linux page table isolation is not needed on AMD processors by czeidler on Wednesday January 03, 2018 @02:28AM (#16059224)

Would it be possible to slow down segfault notifications to mitigate the attack? For example, if the segfault was not on kernel space, halt the application for the time offset of a kernel read. In this way all segfaults would be reported at more or less the same time and the attack could be avoided.

Are there any sane apps that depends on timely segfault handling and thus might be affected by such a workaround?

[ Parent | on HN ]

Re:Linux page table isolation is not needed on AMD processors by caf on Wednesday January 03, 2018 @08:44AM (#16060862)

It's not timing the segfault delivery itself, the idea is to time another read of your own address space after the fault to see if it's been prefetched or not.

Maybe you could CLFLUSH on segfault delivery though.

[ Parent | on HN ]

Re:Linux page table isolation is not needed on AMD processors by caf on Wednesday January 03, 2018 @07:08PM (#16066749)

Turns out "maybe" is "not" - if you put the faulting read at a mispredicted branch target, you don't take the fault.

[ Parent | on HN ]