Re: [PATCH] x86: Add an explicit barrier() to clflushopt()

[Borislav Petkov]

On Mon, Oct 19, 2015 at 12:05:29PM +0100, Chris Wilson wrote:
> In order to add the clobbers, I had to adjust the macro slightly:
> 
> +#define alternative_output(oldinstr, newinstr, feature, output)        \
> +       asm volatile (ALTERNATIVE(oldinstr, newinstr, feature)          \
> +               : output : "i" (0) : "memory")
> 
> and that also works. The concern I have here is that the asm does use
> "+m" as its output already, and the clflush() asm doesn't require the
> manual clobber.

Yeah, you could make the above

#define alternative_output(oldinstr, newinstr, feature, output, clobber...)

and use it to define clflushopt(). hpa might have a better idea, though...

-- 
Regards/Gruss,
    Boris.

ECO tip #101: Trim your mails when you reply.
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/