Hi,

On Thu, Nov 16, 2017 at 06:27:28AM +0000, Jia He wrote:
> Sometimes userspace need a high resolution cycle counter by reading
> pmccntr_el0.
> 
> In commit da4e4f18afe0 ("drivers/perf: arm_pmu: implement CPU_PM
> notifier"), it resets all the counters even when the pmcr_el0.E and
> pmcntenset_el0.C are both 1 . That is incorrect.

I appreciate that you may wish to make use of the cycle counter from
userspace, but this is the intended behaviour kernel-side. Direct
userspace counter acceess is not supported.

In power states where context is lost, any perf events are
saved/restored by cpu_pm_pmu_setup(). So we certainly shouldn't be
modifying the counter registers in any other PM code.

We *could* expose counters to userspace on homogeneous systems, so long
as users stuck to the usual perf data page interface. However, this
comes with a number of subtle problems, and no-one's done the work to
enable this.

Even then, perf may modify counters at any point in time, and
monotonicity (and/or presence) of counters is not guaranteed.

> We need to save the registers and counter before CPU_PM_ENTER and
> restore them after CPU_PM_EXIT.
> 
> Fixes: da4e4f18afe0 ("drivers/perf: arm_pmu: implement CPU_PM notifier")

As above, this patch is not a  fix, and is not currently necessary.

Thanks,
Mark.

> Signed-off-by: Jia He <jia...@hxt-semitech.com>
> ---
>  drivers/perf/arm_pmu.c | 72 
> +++++++++++++++++++++++++++++++++++++++++++++-----
>  1 file changed, 66 insertions(+), 6 deletions(-)
> 
> diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c
> index 7bc5eee..cf55c91 100644
> --- a/drivers/perf/arm_pmu.c
> +++ b/drivers/perf/arm_pmu.c
> @@ -26,6 +26,12 @@
>  
>  #include <asm/irq_regs.h>
>  
> +#ifdef CONFIG_CPU_PM
> +DEFINE_PER_CPU(u32, saved_pmcr_el0);
> +DEFINE_PER_CPU(u32, saved_pmcntenset_el0);
> +DEFINE_PER_CPU(u64, saved_cycle_cnter);
> +#endif
> +
>  static int
>  armpmu_map_cache_event(const unsigned (*cache_map)
>                                     [PERF_COUNT_HW_CACHE_MAX]
> @@ -719,6 +725,15 @@ static void cpu_pm_pmu_setup(struct arm_pmu *armpmu, 
> unsigned long cmd)
>       }
>  }
>  
> +static int pmc_cycle_counter_enabled(void)
> +{
> +     if ((read_sysreg(pmcr_el0) & ARMV8_PMU_PMCR_E) &&
> +                             read_sysreg(pmcntenset_el0) & 1<<31)
> +             return 1;
> +
> +     return 0;
> +}
> +
>  static int cpu_pm_pmu_notify(struct notifier_block *b, unsigned long cmd,
>                            void *v)
>  {
> @@ -729,16 +744,53 @@ static int cpu_pm_pmu_notify(struct notifier_block *b, 
> unsigned long cmd,
>       if (!cpumask_test_cpu(smp_processor_id(), &armpmu->supported_cpus))
>               return NOTIFY_DONE;
>  
> -     /*
> -      * Always reset the PMU registers on power-up even if
> -      * there are no events running.
> -      */
> -     if (cmd == CPU_PM_EXIT && armpmu->reset)
> -             armpmu->reset(armpmu);
> +     if (cmd == CPU_PM_EXIT) {
> +             /*
> +              * Always reset the PMU registers on power-up even if
> +              * there are no events running.
> +              */
> +             if (armpmu->reset)
> +                     armpmu->reset(armpmu);
> +
> +             /*
> +              * Restore the saved pmcr_el0 and pmcntenset_el0
> +              * if pmc cycle counter is enabled, restore the counter
> +              */
> +             write_sysreg(get_cpu_var(saved_pmcr_el0), pmcr_el0);
> +             write_sysreg(get_cpu_var(saved_pmcntenset_el0),
> +                             pmcntenset_el0);
> +
> +             if (pmc_cycle_counter_enabled()) {
> +                     write_sysreg(get_cpu_var(saved_cycle_cnter),
> +                                     pmccntr_el0);
> +                     put_cpu_var(saved_cycle_cnter);
> +             }
> +             put_cpu_var(saved_pmcntenset_el0);
> +             put_cpu_var(saved_pmcr_el0);
> +     }
> +
> +     if (cmd == CPU_PM_ENTER) {
> +             /* If currently pmc cycle counter is enabled,
> +              * save the counter to percpu section
> +              */
> +             if (pmc_cycle_counter_enabled()) {
> +                     get_cpu_var(saved_cycle_cnter) = read_sysreg(
> +                                                     pmccntr_el0);
> +                     put_cpu_var(saved_cycle_cnter);
> +             }
> +
> +             get_cpu_var(saved_pmcr_el0) = read_sysreg(pmcr_el0);
> +
> +             get_cpu_var(saved_pmcntenset_el0) = read_sysreg(
> +                                                     pmcntenset_el0);
> +             put_cpu_var(saved_pmcntenset_el0);
> +             put_cpu_var(saved_pmcr_el0);
> +     }
>  
>       if (!enabled)
>               return NOTIFY_OK;
>  
> +     /* if any hw_events is used */
>       switch (cmd) {
>       case CPU_PM_ENTER:
>               armpmu->stop(armpmu);
> @@ -758,7 +810,15 @@ static int cpu_pm_pmu_notify(struct notifier_block *b, 
> unsigned long cmd,
>  
>  static int cpu_pm_pmu_register(struct arm_pmu *cpu_pmu)
>  {
> +     int i;
>       cpu_pmu->cpu_pm_nb.notifier_call = cpu_pm_pmu_notify;
> +
> +     for_each_possible_cpu(i) {
> +             per_cpu(saved_pmcr_el0, i) = 0;
> +             per_cpu(saved_pmcntenset_el0, i) = 0;
> +             per_cpu(saved_cycle_cnter, i) = 0;
> +     }
> +
>       return cpu_pm_register_notifier(&cpu_pmu->cpu_pm_nb);
>  }
>  
> -- 
> 2.7.4
> 

Reply via email to