public inbox for linuxppc-dev@ozlabs.org 
 help / color / mirror / Atom feed
From: Michael Ellerman <mpe@ellerman•id.au>
To: Nicholas Piggin <npiggin@gmail•com>, linuxppc-dev@lists•ozlabs.org
Cc: Anton Blanchard <anton@samba•org>, Nicholas Piggin <npiggin@gmail•com>
Subject: Re: [PATCH] powerpc: Fix smp_wmb barrier definition use use lwsync consistently
Date: Wed, 28 Mar 2018 23:40:05 +1100	[thread overview]
Message-ID: <874ll02x22.fsf@concordia.ellerman.id.au> (raw)
In-Reply-To: <20180322104146.5350-1-npiggin@gmail.com>

Nicholas Piggin <npiggin@gmail•com> writes:

> asm/barrier.h is not always included after asm/synch.h, which meant
> it was missing __SUBARCH_HAS_LWSYNC, so in some files smp_wmb() would
> be eieio when it should be lwsync. kernel/time/hrtimer.c is one case.

Wow nice catch. Only broken since 2008 presumably.

Some days I think maybe we aren't very good at this writing software
thing, good to have some certainty :)

> __SUBARCH_HAS_LWSYNC is only used in one place, so just fold it in
> to where it's used. Previously with my small simulator config, 377
> instances of eieio in the tree. After this patch there are 55.

At least for Book3S this isn't actually a terrible bug AFAICS:

 - smp_wmb() is only defined to order accesses to cacheable memory.
 - smp_wmb() only orders prior stores vs later stores.
 - eieio orders all prior stores vs all later stores for cacheable
   memory.
 - lwsync orders everything except prior stores vs later loads for
   cacheable memory.

So eieio and lwsync are both valid to use as smp_wmb(), but it's still
terrible fishy that we were using both in different places depending on
include ordering.

I'm inclined to tag this for stable unless anyone can think of a reason
not to?

cheers

> diff --git a/arch/powerpc/include/asm/barrier.h b/arch/powerpc/include/asm/barrier.h
> index 10daa1d56e0a..c7c63959ba91 100644
> --- a/arch/powerpc/include/asm/barrier.h
> +++ b/arch/powerpc/include/asm/barrier.h
> @@ -35,7 +35,8 @@
>  #define rmb()  __asm__ __volatile__ ("sync" : : : "memory")
>  #define wmb()  __asm__ __volatile__ ("sync" : : : "memory")
>  
> -#ifdef __SUBARCH_HAS_LWSYNC
> +/* The sub-arch has lwsync */
> +#if defined(__powerpc64__) || defined(CONFIG_PPC_E500MC)
>  #    define SMPWMB      LWSYNC
>  #else
>  #    define SMPWMB      eieio
> diff --git a/arch/powerpc/include/asm/synch.h b/arch/powerpc/include/asm/synch.h
> index 63e7f5a1f105..6ec546090ba1 100644
> --- a/arch/powerpc/include/asm/synch.h
> +++ b/arch/powerpc/include/asm/synch.h
> @@ -6,10 +6,6 @@
>  #include <linux/stringify.h>
>  #include <asm/feature-fixups.h>
>  
> -#if defined(__powerpc64__) || defined(CONFIG_PPC_E500MC)
> -#define __SUBARCH_HAS_LWSYNC
> -#endif
> -
>  #ifndef __ASSEMBLY__
>  extern unsigned int __start___lwsync_fixup, __stop___lwsync_fixup;
>  extern void do_lwsync_fixups(unsigned long value, void *fixup_start,
> -- 
> 2.16.1

  reply	other threads:[~2018-03-28 12:40 UTC|newest]

Thread overview: 4+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-03-22 10:41 [PATCH] powerpc: Fix smp_wmb barrier definition use use lwsync consistently Nicholas Piggin
2018-03-28 12:40 ` Michael Ellerman [this message]
2018-03-28 13:43   ` Nicholas Piggin
2018-03-31 14:04 ` Michael Ellerman

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=874ll02x22.fsf@concordia.ellerman.id.au \
    --to=mpe@ellerman$(echo .)id.au \
    --cc=anton@samba$(echo .)org \
    --cc=linuxppc-dev@lists$(echo .)ozlabs.org \
    --cc=npiggin@gmail$(echo .)com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox