On Fri, Mar 15, 2019 at 02:43:07PM +0530, Viresh Kumar wrote:
> diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
> index 3fae23834069..cff8779fc0d2 100644
> --- a/arch/x86/kernel/tsc.c
> +++ b/arch/x86/kernel/tsc.c
> @@ -956,28 +956,38 @@ static int time_cpufreq_notifier(struct notifier_block
> *nb, unsigned long val,
> void *data)
> {
> struct cpufreq_freqs *freq = data;
> - unsigned long *lpj;
> -
> - lpj = &boot_cpu_data.loops_per_jiffy;
> -#ifdef CONFIG_SMP
> - if (!(freq->flags & CPUFREQ_CONST_LOOPS))
> - lpj = &cpu_data(freq->cpu).loops_per_jiffy;
> -#endif
> + struct cpumask *cpus = freq->policy->cpus;
> + bool boot_cpu = !IS_ENABLED(CONFIG_SMP) || freq->flags &
> CPUFREQ_CONST_LOOPS;
> + unsigned long lpj;
> + int cpu;
>
> if (!ref_freq) {
> ref_freq = freq->old;
> - loops_per_jiffy_ref = *lpj;
> tsc_khz_ref = tsc_khz;
> +
> + if (boot_cpu)
> + loops_per_jiffy_ref = boot_cpu_data.loops_per_jiffy;
> + else
> + loops_per_jiffy_ref =
> cpu_data(cpumask_first(cpus)).loops_per_jiffy;
> }
> +
> if ((val == CPUFREQ_PRECHANGE && freq->old < freq->new) ||
> (val == CPUFREQ_POSTCHANGE && freq->old > freq->new)) {
> - *lpj = cpufreq_scale(loops_per_jiffy_ref, ref_freq, freq->new);
> -
> + lpj = cpufreq_scale(loops_per_jiffy_ref, ref_freq, freq->new);
> tsc_khz = cpufreq_scale(tsc_khz_ref, ref_freq, freq->new);
> +
> if (!(freq->flags & CPUFREQ_CONST_LOOPS))
> mark_tsc_unstable("cpufreq changes");
>
> - set_cyc2ns_scale(tsc_khz, freq->cpu, rdtsc());
> + if (boot_cpu) {
> + boot_cpu_data.loops_per_jiffy = lpj;
> + } else {
> + for_each_cpu(cpu, cpus)
> + cpu_data(cpu).loops_per_jiffy = lpj;
> + }
> +
> + for_each_cpu(cpu, cpus)
> + set_cyc2ns_scale(tsc_khz, cpu, rdtsc());
This code doesn't make sense, the rdtsc() _must_ be called on the CPU in
question. That's part of the whole problem here, TSC isn't sync'ed when
it's subject to CPUFREQ.
> }
>
> return 0;
