Re: [PATCH 7/7] x86,idle: do not leave mm in idle state

[Rik van Riel <riel@surriel.com>]

[-- Attachment #1: Type: text/plain, Size: 1242 bytes --]

On Fri, 2018-06-22 at 08:36 -0700, Andy Lutomirski wrote:
> On Wed, Jun 20, 2018 at 12:57 PM Rik van Riel <riel@surriel.com>
> wrote:
> > 
> > Do not call leave_mm when going into a cstate. Now that mprotect
> > and
> > madvise no longer send IPIs for TLB shootdowns to idle CPUs, there
> > is
> > no real reason to disable lazy TLB mode in idle states.
> > 
> > This seems to help performance on Broadwell systems. Haswell
> > performance
> > numbers are inconclusive.
> 
> I'm skeptical.  The code you're removing is more about power
> consumption than about performance.  If a task migrates from one cpu
> to another, runs for awhile, and exits, we don't want to IPI the old
> CPU if the old CPU is deeply asleep.  The logic you're removing is a
> bit awkwardly written, but the intent is to only do the leave_mm() in
> deep sleep.  We should arguably change the condition to check the
> expected sleep duration instead of the microarchitectural properties
> of the target state, though.

That is fair.

A quick hack could be to just remove the tlb flush
from C3 state (which gets called a lot), but keep
it for C6 state and deeper (which get called more
when a CPU is really idle).

-- 
All Rights Reversed.

[-- Attachment #2: This is a digitally signed message part --]
[-- Type: application/pgp-signature, Size: 488 bytes --]