Re: [RFC][PATCH 5/5] powerpc: Remove SYNC from _switch

From	Michael Ellerman <mpe@ellerman.id.au>
Newsgroups	linux.kernel
Subject	Re: [RFC][PATCH 5/5] powerpc: Remove SYNC from _switch
Date	2017-06-08 12:00 +0200
Message-ID	<tQ2oq-2Ex-13@gated-at.bofh.it> (permalink)
References	(1 earlier) <tPM0j-zo-53@gated-at.bofh.it> <tPTEu-5rT-13@gated-at.bofh.it> <tPZAf-Nh-25@gated-at.bofh.it> <tQ0cV-1hd-15@gated-at.bofh.it> <tQ0wh-1oo-15@gated-at.bofh.it>
Organization	linux.* mail to news gateway

Show all headers | View raw

Peter Zijlstra <peterz@infradead.org> writes:
> On Thu, Jun 08, 2017 at 05:29:38PM +1000, Nicholas Piggin wrote:
>> On Thu, 8 Jun 2017 08:54:00 +0200
>> Peter Zijlstra <peterz@infradead.org> wrote:
>> > 
>> > Right, so this patch relies on the smp_mb__before_spinlock ->
>> > smp_mb__after_spinlock conversion that makes the rq->lock RCsc and
>> > should thus provide the required SYNC for migrations.
>> 
>> AFAIKS either one will do, so long as there is a hwsync there. The
>> point is just that I have added some commentary in the generic and
>> powerpc parts to make it clear we're relying on that behavior of
>> the primitive. smp_mb* is not guaranteed to order MMIO, it's just
>> that it does on powerpc.
>
> I'm not particularly happy with the generic comment; I don't feel we
> should care that PPC is special here.

I think it'd be nice if there was *some* comment on the two uses of
smp_mb__after_spinlock(), it's fairly subtle, but I don't think it needs
to mention PPC specifically.


If we have:

arch/powerpc/include/asm/barrier.h:
+/*
+ * This must resolve to hwsync on SMP for the context switch path. See
+ * _switch.
+ */
 #define smp_mb__after_spinlock()   smp_mb()


And then something in _switch() that says "we rely on the
smp_mb__after_spinlock() in the scheduler core being a hwsync", that
should probably be sufficient.

cheers

Thread

[RFC][PATCH 5/5] powerpc: Remove SYNC from _switch Peter Zijlstra <peterz@infradead.org> - 2017-06-07 18:30 +0200
  Re: [RFC][PATCH 5/5] powerpc: Remove SYNC from _switch Nicholas Piggin <npiggin@gmail.com> - 2017-06-08 02:40 +0200
    Re: [RFC][PATCH 5/5] powerpc: Remove SYNC from _switch Peter Zijlstra <peterz@infradead.org> - 2017-06-08 09:00 +0200
      Re: [RFC][PATCH 5/5] powerpc: Remove SYNC from _switch Nicholas Piggin <npiggin@gmail.com> - 2017-06-08 09:40 +0200
        Re: [RFC][PATCH 5/5] powerpc: Remove SYNC from _switch Peter Zijlstra <peterz@infradead.org> - 2017-06-08 10:00 +0200
          Re: [RFC][PATCH 5/5] powerpc: Remove SYNC from _switch Nicholas Piggin <npiggin@gmail.com> - 2017-06-08 10:30 +0200
          Re: [RFC][PATCH 5/5] powerpc: Remove SYNC from _switch Michael Ellerman <mpe@ellerman.id.au> - 2017-06-08 12:00 +0200
            Re: [RFC][PATCH 5/5] powerpc: Remove SYNC from _switch Nicholas Piggin <npiggin@gmail.com> - 2017-06-08 12:10 +0200
              Re: [RFC][PATCH 5/5] powerpc: Remove SYNC from _switch Peter Zijlstra <peterz@infradead.org> - 2017-06-08 14:50 +0200
                Re: [RFC][PATCH 5/5] powerpc: Remove SYNC from _switch Nicholas Piggin <npiggin@gmail.com> - 2017-06-08 15:20 +0200
                Re: [RFC][PATCH 5/5] powerpc: Remove SYNC from _switch Peter Zijlstra <peterz@infradead.org> - 2017-06-08 15:50 +0200

csiph-web