lkml.org 
[lkml]   [2020]   [Dec]   [1]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
SubjectRe: [PATCH 2/8] x86: use exit_lazy_tlb rather than membarrier_mm_sync_core_before_usermode
Excerpts from Andy Lutomirski's message of November 29, 2020 3:55 am:
> On Sat, Nov 28, 2020 at 8:02 AM Nicholas Piggin <npiggin@gmail.com> wrote:
>>
>> And get rid of the generic sync_core_before_usermode facility. This is
>> functionally a no-op in the core scheduler code, but it also catches
>>
>> This helper is the wrong way around I think. The idea that membarrier
>> state requires a core sync before returning to user is the easy one
>> that does not need hiding behind membarrier calls. The gap in core
>> synchronization due to x86's sysret/sysexit and lazy tlb mode, is the
>> tricky detail that is better put in x86 lazy tlb code.
>>
>> Consider if an arch did not synchronize core in switch_mm either, then
>> membarrier_mm_sync_core_before_usermode would be in the wrong place
>> but arch specific mmu context functions would still be the right place.
>> There is also a exit_lazy_tlb case that is not covered by this call, which
>> could be a bugs (kthread use mm the membarrier process's mm then context
>> switch back to the process without switching mm or lazy mm switch).
>>
>> This makes lazy tlb code a bit more modular.
>
> I have a couple of membarrier fixes that I want to send out today or
> tomorrow, and they might eliminate the need for this patch. Let me
> think about this a little bit. I'll cc you. The existing code is way
> to subtle and the comments are far too confusing for me to be quickly
> confident about any of my conclusions :)
>

Thanks for the head's up. I'll have to have a better look through them
but I don't know that it eliminates the need for this entirely although
it might close some gaps and make this not a bug fix. The problem here
is x86 code wanted something to be called when a lazy mm is unlazied,
but it missed some spots and also the core scheduler doesn't need to
know about those x86 details if it has this generic call that annotates
the lazy handling better.

I'll go through the wording again and look at your patches a bit better
but I think they are somewhat orthogonal.

Thanks,
Nick

\
 
 \ /
  Last update: 2020-12-02 03:51    [W:0.282 / U:9.968 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site