From: Rafael J. Wysocki Date: Fri, 4 Mar 2016 02:58:22 +0000 (+0100) Subject: cpufreq: Reduce cpufreq_update_util() overhead a bit X-Git-Url: https://git.stricted.de/?a=commitdiff_plain;h=08f511fd41c3afe303eb9b41bff0570f7c1b6937;p=GitHub%2Fmoto-9609%2Fandroid_kernel_motorola_exynos9610.git cpufreq: Reduce cpufreq_update_util() overhead a bit Use the observation that cpufreq_update_util() is only called by the scheduler with rq->lock held, so the callers of cpufreq_set_update_util_data() can use synchronize_sched() instead of synchronize_rcu() to wait for cpufreq_update_util() to complete. Moreover, if they are updated to do that, rcu_read_(un)lock() calls in cpufreq_update_util() might be replaced with rcu_read_(un)lock_sched(), respectively, but those aren't really necessary, because the scheduler calls that function from RCU-sched read-side critical sections already. In addition to that, if cpufreq_set_update_util_data() checks the func field in the struct update_util_data before setting the per-CPU pointer to it, the data->func check may be dropped from cpufreq_update_util() as well. Make the above changes to reduce the overhead from cpufreq_update_util() in the scheduler paths invoking it and to make the cleanup after removing its callbacks less heavy-weight somewhat. Signed-off-by: Rafael J. Wysocki Acked-by: Viresh Kumar Acked-by: Peter Zijlstra (Intel) --- diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index dd568aaf2728..6eca12ab71d7 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -115,12 +115,15 @@ static DEFINE_PER_CPU(struct update_util_data *, cpufreq_update_util_data); * to call from cpufreq_update_util(). That function will be called from an RCU * read-side critical section, so it must not sleep. * - * Callers must use RCU callbacks to free any memory that might be accessed - * via the old update_util_data pointer or invoke synchronize_rcu() right after - * this function to avoid use-after-free. + * Callers must use RCU-sched callbacks to free any memory that might be + * accessed via the old update_util_data pointer or invoke synchronize_sched() + * right after this function to avoid use-after-free. */ void cpufreq_set_update_util_data(int cpu, struct update_util_data *data) { + if (WARN_ON(data && !data->func)) + return; + rcu_assign_pointer(per_cpu(cpufreq_update_util_data, cpu), data); } EXPORT_SYMBOL_GPL(cpufreq_set_update_util_data); @@ -133,18 +136,24 @@ EXPORT_SYMBOL_GPL(cpufreq_set_update_util_data); * * This function is called by the scheduler on every invocation of * update_load_avg() on the CPU whose utilization is being updated. + * + * It can only be called from RCU-sched read-side critical sections. */ void cpufreq_update_util(u64 time, unsigned long util, unsigned long max) { struct update_util_data *data; - rcu_read_lock(); +#ifdef CONFIG_LOCKDEP + WARN_ON(debug_locks && !rcu_read_lock_sched_held()); +#endif - data = rcu_dereference(*this_cpu_ptr(&cpufreq_update_util_data)); - if (data && data->func) + data = rcu_dereference_sched(*this_cpu_ptr(&cpufreq_update_util_data)); + /* + * If this isn't inside of an RCU-sched read-side critical section, data + * may become NULL after the check below. + */ + if (data) data->func(data, time, util, max); - - rcu_read_unlock(); } /* Flag to suspend/resume CPUFreq governors */ diff --git a/drivers/cpufreq/cpufreq_governor.c b/drivers/cpufreq/cpufreq_governor.c index 70079e21fa2d..db46190bb246 100644 --- a/drivers/cpufreq/cpufreq_governor.c +++ b/drivers/cpufreq/cpufreq_governor.c @@ -280,7 +280,7 @@ static inline void gov_clear_update_util(struct cpufreq_policy *policy) for_each_cpu(i, policy->cpus) cpufreq_set_update_util_data(i, NULL); - synchronize_rcu(); + synchronize_sched(); } static void gov_cancel_work(struct cpufreq_policy *policy) diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index f4d85c2ae7b1..2165d2b2fc35 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -1168,7 +1168,7 @@ static void intel_pstate_stop_cpu(struct cpufreq_policy *policy) pr_debug("intel_pstate: CPU %d exiting\n", cpu_num); cpufreq_set_update_util_data(cpu_num, NULL); - synchronize_rcu(); + synchronize_sched(); if (hwp_active) return; @@ -1426,7 +1426,7 @@ out: for_each_online_cpu(cpu) { if (all_cpu_data[cpu]) { cpufreq_set_update_util_data(cpu, NULL); - synchronize_rcu(); + synchronize_sched(); kfree(all_cpu_data[cpu]); } }