Messages in this thread | | | From | Linus Torvalds <> | Date | Sat, 21 Jul 2018 14:06:52 -0700 | Subject | Re: [PATCH 1/3] perf/core: Make sure the ring-buffer is mapped in all page-tables |
| |
On Fri, Jul 20, 2018 at 3:20 PM Andy Lutomirski <luto@amacapital.net> wrote: > Thanks for digging! The problem was presumably that vmalloc_fault() will IRET and re-enable NMIs on the way out. > But we’ve supported page faults on user memory in NMI handlers on 32-bit and 64-bit for quite a while, and it’s fine now. > > I would remove the warning, re-test, and revert the other patch.
Agreed. I don't think we have any issues with page faults during NMI any more. Afaik the kprobe people depend on it.
That said, 64-bit mode has that scary PV-op case (arch_flush_lazy_mmu_mode). Being PV mode, I can't find it in myself to worry about it, I'm assuming it's ok.
Linus
| |