lkml.org 
[lkml]   [2020]   [May]   [8]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
From
SubjectRe: [RFC][PATCH 3/3] x86/entry, ORC: Teach objtool/unwind_orc about stack irq swizzles
Date
Thomas Gleixner <tglx@linutronix.de> writes:
> Peter Zijlstra <peterz@infradead.org> writes:
>> Are we sure the rat-poison crap is noise for all the other system
>> vectors? I suppose it is for most since they'll do indirect calls
>> themselves anyway, right?
>
> 3) Quick
>
> RESCHEDULE_VECTOR
>
> POSTED_INTR_VECTOR
> POSTED_INTR_NESTED_VECTOR
>
> These two postit ones are weird because they are both empty and
> just increment different irq counts.

For those 3 it's also pointless to run them on IST stack at all.

> HYPERV_REENLIGHTENMENT_VECTOR
>
> schedules delayed work, i,e. arms a timer which should be
> straight forward, but does it matter?

This one shouldn't have an issue when running on task stack either, but
we can run it through the regular indirect path for now and switch it
over when it matters performance wise.

Thanks,

tglx

\
 
 \ /
  Last update: 2020-05-08 14:45    [W:0.045 / U:0.036 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site