On Tue, Jul 21, 2015 at 11:41:45PM +0800, Leo Yan wrote:
> Hi Morten,
>
> On Tue, Jul 07, 2015 at 07:23:44PM +0100, Morten Rasmussen wrote:
> > From: Morten Rasmussen <morten.rasmus...@arm.com>
> >
> > Implements arch-specific function to provide the scheduler with a
> > frequency scaling correction factor for more accurate load-tracking.
> > The factor is:
> >
> > current_freq(cpu) << SCHED_CAPACITY_SHIFT / max_freq(cpu)
> >
> > This implementation only provides frequency invariance. No cpu
> > invariance yet.
> >
> > Cc: Russell King <li...@arm.linux.org.uk>
> >
> > Signed-off-by: Morten Rasmussen <morten.rasmus...@arm.com>
> >
> > ---
> > arch/arm/include/asm/topology.h | 7 +++++
> > arch/arm/kernel/smp.c | 57
> > +++++++++++++++++++++++++++++++++++++++--
> > arch/arm/kernel/topology.c | 17 ++++++++++++
> > 3 files changed, 79 insertions(+), 2 deletions(-)
> >
> > diff --git a/arch/arm/include/asm/topology.h
> > b/arch/arm/include/asm/topology.h
> > index 370f7a7..c31096f 100644
> > --- a/arch/arm/include/asm/topology.h
> > +++ b/arch/arm/include/asm/topology.h
> > @@ -24,6 +24,13 @@ void init_cpu_topology(void);
> > void store_cpu_topology(unsigned int cpuid);
> > const struct cpumask *cpu_coregroup_mask(int cpu);
> >
> > +#define arch_scale_freq_capacity arm_arch_scale_freq_capacity
> > +struct sched_domain;
> > +extern
> > +unsigned long arm_arch_scale_freq_capacity(struct sched_domain *sd, int
> > cpu);
> > +
> > +DECLARE_PER_CPU(atomic_long_t, cpu_freq_capacity);
> > +
> > #else
> >
> > static inline void init_cpu_topology(void) { }
> > diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
> > index cca5b87..a32539c 100644
> > --- a/arch/arm/kernel/smp.c
> > +++ b/arch/arm/kernel/smp.c
> > @@ -677,12 +677,34 @@ static DEFINE_PER_CPU(unsigned long, l_p_j_ref);
> > static DEFINE_PER_CPU(unsigned long, l_p_j_ref_freq);
> > static unsigned long global_l_p_j_ref;
> > static unsigned long global_l_p_j_ref_freq;
> > +static DEFINE_PER_CPU(atomic_long_t, cpu_max_freq);
> > +DEFINE_PER_CPU(atomic_long_t, cpu_freq_capacity);
> > +
> > +/*
> > + * Scheduler load-tracking scale-invariance
> > + *
> > + * Provides the scheduler with a scale-invariance correction factor that
> > + * compensates for frequency scaling through arch_scale_freq_capacity()
> > + * (implemented in topology.c).
> > + */
> > +static inline
> > +void scale_freq_capacity(int cpu, unsigned long curr, unsigned long max)
> > +{
> > + unsigned long capacity;
> > +
> > + if (!max)
> > + return;
> > +
> > + capacity = (curr << SCHED_CAPACITY_SHIFT) / max;
> > + atomic_long_set(&per_cpu(cpu_freq_capacity, cpu), capacity);
> > +}
> >
> > static int cpufreq_callback(struct notifier_block *nb,
> > unsigned long val, void *data)
> > {
> > struct cpufreq_freqs *freq = data;
> > int cpu = freq->cpu;
> > + unsigned long max = atomic_long_read(&per_cpu(cpu_max_freq, cpu));
> >
> > if (freq->flags & CPUFREQ_CONST_LOOPS)
> > return NOTIFY_OK;
> > @@ -707,6 +729,10 @@ static int cpufreq_callback(struct notifier_block *nb,
> > per_cpu(l_p_j_ref_freq, cpu),
> > freq->new);
> > }
> > +
> > + if (val == CPUFREQ_PRECHANGE)
> > + scale_freq_capacity(cpu, freq->new, max);
> > +
> > return NOTIFY_OK;
> > }
> >
> > @@ -714,11 +740,38 @@ static struct notifier_block cpufreq_notifier = {
> > .notifier_call = cpufreq_callback,
> > };
> >
> > +static int cpufreq_policy_callback(struct notifier_block *nb,
> > + unsigned long val, void *data)
> > +{
> > + struct cpufreq_policy *policy = data;
> > + int i;
> > +
> > + if (val != CPUFREQ_NOTIFY)
> > + return NOTIFY_OK;
> > +
> > + for_each_cpu(i, policy->cpus) {
> > + scale_freq_capacity(i, policy->cur, policy->max);
> > + atomic_long_set(&per_cpu(cpu_max_freq, i), policy->max);
> > + }
> > +
> > + return NOTIFY_OK;
> > +}
> > +
> > +static struct notifier_block cpufreq_policy_notifier = {
> > + .notifier_call = cpufreq_policy_callback,
> > +};
> > +
> > static int __init register_cpufreq_notifier(void)
> > {
> > - return cpufreq_register_notifier(&cpufreq_notifier,
> > + int ret;
> > +
> > + ret = cpufreq_register_notifier(&cpufreq_notifier,
> > CPUFREQ_TRANSITION_NOTIFIER);
> > + if (ret)
> > + return ret;
> > +
> > + return cpufreq_register_notifier(&cpufreq_policy_notifier,
> > + CPUFREQ_POLICY_NOTIFIER);
> > }
> > core_initcall(register_cpufreq_notifier);
>
> For "cpu_freq_capacity" structure, could move it into driver/cpufreq
> so that it can be shared by all architectures? Otherwise, every
> architecture's smp.c need register notifier for themselves.
We could, but I put it in arch/arm/* as not all architectures might want
this notifier. The frequency scaling factor could be provided based on
architecture specific performance counters instead. AFAIK, the Intel
p-state driver does not even fire the notifiers so the notifier
solution would be redundant code for those platforms.
That said, the above solution is not handling changes to policy->max
very well. Basically, we don't inform the scheduler if it has changed
which means that the OPP represented by "100%" might change. We need
cpufreq to keep track of the true max frequency when policy->max is
changed to work out the correct scaling factor instead of having it
relative to policy->max.
Morten
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
