Re: [PATCH v3 2/2] powerpc/64s: Make POWER10 and later use pause_short in cpu_relax loops

[Michael Ellerman <mpe@ellerman.id.au>]

Nicholas Piggin <npiggin@gmail.com> writes:
> We want to move away from using SMT prioroty updates for cpu_relax, and
> use a 'wait' instruction which is similar to x86. As well as being a
> much better fit for what everybody else uses and tests with, priority
> nops are stateful which is nasty (interrupts have to consider they might
> be taken at a different priority), and they're expensive to execute,
> similar to a mtSPR which can effect other threads in the pipe.
>
> Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
> ---
> Unfortunately qemu TCG does not emulate pause_short properly and will
> cause hangs.

That _really_ sucks for testing, being able to use qemu is a huge
benefit. I can boot test multiple kernels per minute using qemu, vs
multiple minutes per kernel using real hardware.

> I have a patch for it but not merged yet. But if we tune
> qspinlock code it would be best to do it with this patch.

What's the urgency on this patch? Can we wait for the qemu change to
land? I guess Qemu 8 is not due until next year? :/

cheers