Re: [PATCH] x86: add hintable NOPs emulation

[Marcos Del Sol Vives <marcos@orca.pet>]

Hi Ahmed,

El 20/08/2025 a las 11:14, Ahmed S. Darwish escribió:
> Can we please remove all this 'hnop_warn' trickery?  Removing it will
> simplifiy the code and avoid complicating 'thread_struct' further.
> 
> It's just the kernel doing its normal job.
> 
> And if the system is full of binaries with hintable NOPs, ratelimiting
> will not save you much.  I got hit recently by a 'ratelimited'
> correctible error PCI subsystem warning, and it still overflows the log
> buffers of my Thinkpad laptop, in just 4 to 5 days :(

But I think the kernel should let the user know the binaries they're
running are having some performance penalty due to this emulation, in case
they want to recompile without the offending flags.

Without the logging, they'd be in the dark and might get confused on why
their programs are running slower than on other machines.

>>
>> static inline void handle_invalid_op(struct pt_regs *regs)
>> {
>> +#ifdef CONFIG_X86_HNOP_EMU
>> +	if (user_mode(regs) && handle_hnop(regs))
>> +		return;
>> +#endif
>> +
>>
> 
> CPP conditionals within C function code are ugly.  Please do instead:
> 
>     static bool handle_hnop(struct pt_regs *regs)
>     {
> 	if (!IS_ENABLED(CONFIG_X86_HNOP_EMU))
> 		return false;
> 	...
>     }
> 
> Thanks for your contribution!

I originally did that, but then realized it was not possible due to
"handle_hnop" depending on the conditionally-available "hnop_warn" flag.

Greetings,
Marcos