Re: [PATCH v3 03/11] riscv: Implement cmpxchg8/16() using Zabha

[Conor Dooley]

On Wed, Jul 17, 2024 at 10:26:34AM -0500, Andrew Jones wrote:
> On Wed, Jul 17, 2024 at 08:19:49AM GMT, Alexandre Ghiti wrote:
> > -#define __arch_cmpxchg_masked(sc_sfx, prepend, append, r, p, o, n)	\
> > +#define __arch_cmpxchg_masked(sc_sfx, cas_sfx, prepend, append, r, p, o, n)	\
> >  ({									\
> > +	__label__ no_zabha_zacas, end;					\
> > +									\
> > +	if (IS_ENABLED(CONFIG_RISCV_ISA_ZABHA) &&			\
> > +	    IS_ENABLED(CONFIG_RISCV_ISA_ZACAS)) {			\
> > +		asm goto(ALTERNATIVE("j %[no_zabha_zacas]", "nop", 0,	\
> > +				     RISCV_ISA_EXT_ZABHA, 1)		\
> > +			 : : : : no_zabha_zacas);			\
> > +		asm goto(ALTERNATIVE("j %[no_zabha_zacas]", "nop", 0,	\
> > +				     RISCV_ISA_EXT_ZACAS, 1)		\
> > +			 : : : : no_zabha_zacas);			\
> 
> I came late to the call, but I guess trying to get rid of these asm gotos
> was the topic of the discussion. The proposal was to try and use static
> branches, but keep in mind that we've had trouble with static branches
> inside macros in the past when those macros are used in many places[1]
> 
> [1] commit 0b1d60d6dd9e ("riscv: Fix build with CONFIG_CC_OPTIMIZE_FOR_SIZE=y")

The other half of the suggestion was not using an asm goto, but instead
trying to patch the whole thing in the alternative, for the problematic
section with llvm < 17.

> 
> > +									\
> > +		__asm__ __volatile__ (					\
> > +			prepend						\
> > +			"	amocas" cas_sfx " %0, %z2, %1\n"	\
> > +			append						\
> > +			: "+&r" (r), "+A" (*(p))			\
> > +			: "rJ" (n)					\
> > +			: "memory");					\
> > +		goto end;						\
> > +	}								\
> > +									\
> > +no_zabha_zacas:;							\
> 
> unnecessary ;
> 
> >  	u32 *__ptr32b = (u32 *)((ulong)(p) & ~0x3);			\
> >  	ulong __s = ((ulong)(p) & (0x4 - sizeof(*p))) * BITS_PER_BYTE;	\
> >  	ulong __mask = GENMASK(((sizeof(*p)) * BITS_PER_BYTE) - 1, 0)	\
> > @@ -133,6 +155,8 @@
> >  		: "memory");						\
> >  									\
> >  	r = (__typeof__(*(p)))((__retx & __mask) >> __s);		\
> > +									\
> > +end:;									\
> >  })
> >  
> >  #define __arch_cmpxchg(lr_sfx, sc_cas_sfx, prepend, append, r, p, co, o, n)	\

Attachment: signature.asc
Description: PGP signature