Re: [PATCH 7/9] atomic.h : powerpc

[Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>]

* Benjamin Herrenschmidt (benh@kernel.crashing.org) wrote:
> 
> > +
> > +/**
> > + * atomic64_add_unless - add unless the number is a given value
> > + * @v: pointer of type atomic64_t
> > + * @a: the amount to add to v...
> > + * @u: ...unless v is equal to u.
> > + *
> > + * Atomically adds @a to @v, so long as it was not @u.
> > + * Returns non-zero if @v was not @u, and zero otherwise.
> > + */
> > +static __inline__ int atomic64_add_unless(atomic64_t *v, long a, long u)
> > +{
> > +	long t;
> > +
> > +	__asm__ __volatile__ (
> > +	LWSYNC_ON_SMP
> > +"1:	ldarx	%0,0,%1		# atomic_add_unless\n\
> > +	cmpd	0,%0,%3 \n\
> > +	beq-	2f \n\
> > +	add	%0,%2,%0 \n"
> > +	PPC405_ERR77(0,%2)
> > +"	stdcx.	%0,0,%1 \n\
> > +	bne-	1b \n"
> > +	ISYNC_ON_SMP
> > +"	subf	%0,%2,%0 \n\
> > +2:"
> > +	: "=&r" (t)
> > +	: "r" (&v->counter), "r" (a), "r" (u)
> > +	: "cc", "memory");
> > +
> > +	return t != u;
> > +}
> > +
> 
> You shouldn't try to define those when building 32 bits code... Also,
> the PPC405 errata, as it's name implies, is specific to 405 cores which
> are all 32 bits.
> 
> Ben.
> 
> 

Hi Ben,

It is within a 
#ifdef __powerpc64__
...
#endif /* __powerpc64__ */

so it should only build on 64 bits.

You are right about the PPC405 errata, it seems unnecessary.

The same is true for my asm-powerpc/local.h modification.

Thanks,

Mathieu

-- 
OpenPGP public key:              http://krystal.dyndns.org:8080/key/compudj.gpg
Key fingerprint:     8CD5 52C3 8E3C 4140 715F  BA06 3F25 A8FE 3BAE 9A68