Re: [PATCH -tip] x86/locking/atomic: Use asm_inline for atomic locking insns

[H. Peter Anvin]

On 3/5/25 09:04, Linus Torvalds wrote:
> That said, I do want to bring up another issue: maybe it's time to
> just retire the LOCK_PREFIX thing entirely?
>
> It harkens back to Ye Olde Days when UP was the norm, and we didn't
> want to pay the cost of lock prefixes when the kernel was built for
> SMP but was run on an UP machine.
>
> And honestly, none of that makes sense any more. You can't buy a UP
> machine any more, and the only UP case would be some silly minimal
> virtual environment, and if people really care about that minimal
> case, they should just compile the kernel without SMP support.
> Becxause UP has gone from being the default to being irrelevant. At
> least for x86-64.

I think the key there is that "they should just compile the kernel 
without SMP support" (which may very well make sense for some oddball 
embedded uses) *does* still mean that remaining cases of locks 
can/should be elided so demacroizing it is still not an option.

But yes... would get rid of a lot of crap machinery which is basically 
dead code, and that would be a Very Good Thing[TM].

	-hpa