[PATCH V3] powerpc: Implement {cmp}xchg for u8 and u16

[Peter Zijlstra]

On Wed, Apr 20, 2016 at 09:24:00PM +0800, Pan Xinhui wrote:

> +#define __XCHG_GEN(cmp, type, sfx, skip, v)				\
> +static __always_inline unsigned long					\
> +__cmpxchg_u32##sfx(v unsigned int *p, unsigned long old,		\
> +			 unsigned long new);				\
> +static __always_inline u32						\
> +__##cmp##xchg_##type##sfx(v void *ptr, u32 old, u32 new)		\
> +{									\
> +	int size = sizeof (type);					\
> +	int off = (unsigned long)ptr % sizeof(u32);			\
> +	volatile u32 *p = ptr - off;					\
> +	int bitoff = BITOFF_CAL(size, off);				\
> +	u32 bitmask = ((0x1 << size * BITS_PER_BYTE) - 1) << bitoff;	\
> +	u32 oldv, newv, tmp;						\
> +	u32 ret;							\
> +	oldv = READ_ONCE(*p);						\
> +	do {								\
> +		ret = (oldv & bitmask) >> bitoff;			\
> +		if (skip && ret != old)					\
> +			break;						\
> +		newv = (oldv & ~bitmask) | (new << bitoff);		\
> +		tmp = oldv;						\
> +		oldv = __cmpxchg_u32##sfx((v u32*)p, oldv, newv);	\
> +	} while (tmp != oldv);						\
> +	return ret;							\
> +}

So for an LL/SC based arch using cmpxchg() like that is sub-optimal.

Why did you choose to write it entirely in C?