Re: [RFC][PATCH 7/9] x86/tsc: Provide sched_clock_noinstr()

[Peter Zijlstra]

On Mon, May 08, 2023 at 11:19:58PM +0200, Peter Zijlstra wrote:

> --- a/drivers/clocksource/hyperv_timer.c
> +++ b/drivers/clocksource/hyperv_timer.c
> @@ -408,9 +408,9 @@ static u64 notrace read_hv_clock_tsc_cs(
>  	return read_hv_clock_tsc();
>  }
>  
> -static u64 notrace read_hv_sched_clock_tsc(void)
> +static u64 noinstr read_hv_sched_clock_tsc(void)
>  {
> -	return (read_hv_clock_tsc() - hv_sched_clock_offset) *
> +	return (hv_read_tsc_page(hv_get_tsc_page()) - hv_sched_clock_offset) *
>  		(NSEC_PER_SEC / HV_CLOCK_HZ);
>  }
>  
> --- a/include/clocksource/hyperv_timer.h
> +++ b/include/clocksource/hyperv_timer.h
> @@ -38,7 +38,7 @@ extern void hv_remap_tsc_clocksource(voi
>  extern unsigned long hv_get_tsc_pfn(void);
>  extern struct ms_hyperv_tsc_page *hv_get_tsc_page(void);
>  
> -static inline notrace u64
> +static __always_inline notrace u64
>  hv_read_tsc_page_tsc(const struct ms_hyperv_tsc_page *tsc_pg, u64 *cur_tsc)
>  {
>  	u64 scale, offset;
> @@ -85,7 +85,7 @@ hv_read_tsc_page_tsc(const struct ms_hyp
>  	return mul_u64_u64_shr(*cur_tsc, scale, 64) + offset;
>  }
>  
> -static inline notrace u64
> +static __always_inline notrace u64
>  hv_read_tsc_page(const struct ms_hyperv_tsc_page *tsc_pg)
>  {
>  	u64 cur_tsc;

Hyper-V folks!

While reviewing all this I found the following 'gem':

hv_init_clocksource()
  hv_setup_sched_clock()
    paravirt_set_sched_clock(read_hv_sched_clock_msr)

read_hv_sched_clock_msr() [notrace]
  read_hv_clock_msr()     [notrace]
    hv_get_register()      *traced*
      hv_get_non_nested_register() ...
        hv_ghcb_msr_read()
	  WARN_ON(in_nmi())
	  ...
	  local_irq_save()


Note that:

 a) sched_clock() is used in NMI context a *LOT*
 b) sched_clock() is notrace (or even noinstr with these patches)
    and local_irq_save() implies tracing


Can you pretty please:

 1) delete all this; or,
 2) fix it in a hurry?

Thanks!