On Thu, Jun 02, 2016 at 01:52:02PM +0200, Peter Zijlstra wrote:
[snip]
> --- a/arch/powerpc/include/asm/spinlock.h
> +++ b/arch/powerpc/include/asm/spinlock.h
> @@ -27,6 +27,8 @@
>  #include <asm/asm-compat.h>
>  #include <asm/synch.h>
>  #include <asm/ppc-opcode.h>
> +#include <asm/barrier.h>
> +#include <asm/processor.h>
>  
>  #ifdef CONFIG_PPC64
>  /* use 0x800000yy when locked, where yy == CPU number */
> @@ -165,8 +167,10 @@ static inline void arch_spin_unlock(arch
>  #ifdef CONFIG_PPC64
>  extern void arch_spin_unlock_wait(arch_spinlock_t *lock);
>  #else
> -#define arch_spin_unlock_wait(lock) \
> -	do { while (arch_spin_is_locked(lock)) cpu_relax(); } while (0)
> +static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
> +{
> +	smp_cond_load_acquire(&lock->slock, !VAL);
> +}
>  #endif
>  

About spin_unlock_wait() on ppc, I actually have a fix pending review:

http://lkml.kernel.org/r/1461130033-70898-1-git-send-email-boqun.feng@gmail.com

that patch fixed a different problem when people want to pair a
spin_unlock_wait() with a spin_lock().

I think we still need that fix, and there are two conflicts with this
series:

1.	arch_spin_unlock_wait() code for PPC32 was deleted, and
	consolidated into one.

2.	I actually downgraded spin_unlock_wait() to !ACQUIRE ;-)


I can think of two ways to solve thoes conflicts:

1.	Modify my patch to make spin_unlock_wait() an ACQUIRE, and it
	can be merged in powerpc tree, and possible go into to mainline
	before 4.7. Then there is no need for this series to have code
	for ppc, therefore no conflict.

or

2.	I can rebase my patch on this series, and it can be added in
	this series, and will go into mainline at 4.8.


Michael and Peter, any thought?

Regards,
Boqun

>  /*