Re: [patch V6 01/37] tracing/hwlat: Use ktime_get_mono_fast_ns()

[Peter Zijlstra]

On Sat, May 16, 2020 at 01:45:48AM +0200, Thomas Gleixner wrote:
> Timestamping in the hardware latency detector uses sched_clock() underneath
> and depends on CONFIG_GENERIC_SCHED_CLOCK=n because sched clocks from that
> subsystem are not NMI safe.

AFAICT that's not actually true, see commit:

  1809bfa44e10 ("timers, sched/clock: Avoid deadlock during read from NMI")

that said, no objection to switching to ktime, people that run HPET
clocks deserve all the pain and suffering available with those setups.