Re: [PATCH -tip 2/2] x86/hweight: Use POPCNT when available with X86_NATIVE_CPU option

[Ingo Molnar]

* Borislav Petkov <bp@xxxxxxxxx> wrote:

> On Sun, Mar 30, 2025 at 05:15:16PM +0200, Uros Bizjak wrote:
> > You missed this part:
> > 
> > --q--
> > ... where there is no need for an entry in the .altinstr_replacement
> 
> Not really - .altinstr* memory gets jettisoned after boot.
> 
> > section, shrinking all text sections by 9476 bytes:
> 
> So if anything, this saves a whopping ~9K disk space and makes 
> hweight* an unreadable mess.

What unreadable mess?

The proposed patch is:

 +#ifdef __POPCNT__
 +     asm_inline (ASM_FORCE_CLR "popcntl %[val], %[cnt]"
 +                 : [cnt] "=&r" (res)
 +                 : [val] ASM_INPUT_RM (w));
 +#else
       asm_inline (ALTERNATIVE(ANNOTATE_IGNORE_ALTERNATIVE
                               "call __sw_hweight32",
                               ASM_CLR "popcntl %[val], %[cnt]",
                               X86_FEATURE_POPCNT)
                        : [cnt] "=a" (res), ASM_CALL_CONSTRAINT
                        : [val] REG_IN (w));
 -
 +#endif

Which is 3 straightforward lines of assembly code and a straightforward #ifdef.

My main objection is different: if __POPCNT__ isn't defined during the 
kernel build of major Linux distros, then this optimization almost 
doesn't exist to our users. And I don't think it's defined.

Thanks,

	Ingo