On 7/8/20 4:32 AM, Peter Zijlstra wrote:
On Tue, Jul 07, 2020 at 11:33:45PM -0400, Waiman Long wrote:
From 5d7941a498935fb225b2c7a3108cbf590114c3db Mon Sep 17 00:00:00 2001
From: Waiman Long <longman@xxxxxxxxxx>
Date: Tue, 7 Jul 2020 22:29:16 -0400
Subject: [PATCH 2/9] locking/pvqspinlock: Introduce
CONFIG_PARAVIRT_QSPINLOCKS_LITE
Add a new PARAVIRT_QSPINLOCKS_LITE config option that allows
architectures to use the PV qspinlock code without the need to use or
implement a pv_kick() function, thus eliminating the atomic unlock
overhead. The non-atomic queued_spin_unlock() can be used instead.
The pv_wait() function will still be needed, but it can be a dummy
function.
With that option set, the hybrid PV queued/unfair locking code should
still be able to make it performant enough in a paravirtualized
How is this supposed to work? If there is no kick, you have no control
over who wakes up and fairness goes out the window entirely.
You don't even begin to explain...
I don't have a full understanding of how the PPC hypervisor work myself.
Apparently, a cpu kick may not be needed.
This is just a test patch to see if it yields better result. It is
subjected to further modifcation.
Cheers,
Longman
