diff options
| -rw-r--r-- | drivers/cpufreq/cpufreq_governor.c | 3 | ||||
| -rw-r--r-- | drivers/cpufreq/intel_pstate.c | 8 | ||||
| -rw-r--r-- | include/linux/cpufreq.h | 9 | ||||
| -rw-r--r-- | kernel/sched/cpufreq_schedutil.c | 31 | ||||
| -rw-r--r-- | kernel/sched/deadline.c | 2 | ||||
| -rw-r--r-- | kernel/sched/fair.c | 8 | ||||
| -rw-r--r-- | kernel/sched/rt.c | 2 | ||||
| -rw-r--r-- | kernel/sched/sched.h | 10 |
8 files changed, 55 insertions, 18 deletions
diff --git a/drivers/cpufreq/cpufreq_governor.c b/drivers/cpufreq/cpufreq_governor.c index 47e24b5384b3..ce5f3ec7ce71 100644 --- a/drivers/cpufreq/cpufreq_governor.c +++ b/drivers/cpufreq/cpufreq_governor.c @@ -275,6 +275,9 @@ static void dbs_update_util_handler(struct update_util_data *data, u64 time, struct policy_dbs_info *policy_dbs = cdbs->policy_dbs; u64 delta_ns, lst; + if (!cpufreq_can_do_remote_dvfs(policy_dbs->policy)) + return; + /* * The work may not be allowed to be queued up right now. * Possible reasons: diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 6cd503525638..d299b86a5a00 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -1747,6 +1747,10 @@ static void intel_pstate_update_util_pid(struct update_util_data *data, struct cpudata *cpu = container_of(data, struct cpudata, update_util); u64 delta_ns = time - cpu->sample.time; + /* Don't allow remote callbacks */ + if (smp_processor_id() != cpu->cpu) + return; + if ((s64)delta_ns < pid_params.sample_rate_ns) return; @@ -1764,6 +1768,10 @@ static void intel_pstate_update_util(struct update_util_data *data, u64 time, struct cpudata *cpu = container_of(data, struct cpudata, update_util); u64 delta_ns; + /* Don't allow remote callbacks */ + if (smp_processor_id() != cpu->cpu) + return; + if (flags & SCHED_CPUFREQ_IOWAIT) { cpu->iowait_boost = int_tofp(1); } else if (cpu->iowait_boost) { diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index f10a9b3761cd..c4035964e6b3 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -562,6 +562,15 @@ struct governor_attr { size_t count); }; +static inline bool cpufreq_can_do_remote_dvfs(struct cpufreq_policy *policy) +{ + /* Allow remote callbacks only on the CPUs sharing cpufreq policy */ + if (cpumask_test_cpu(smp_processor_id(), policy->cpus)) + return true; + + return false; +} + /********************************************************************* * FREQUENCY TABLE HELPERS * *********************************************************************/ diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c index ddd385f2a985..7dbc76801f86 100644 --- a/kernel/sched/cpufreq_schedutil.c +++ b/kernel/sched/cpufreq_schedutil.c @@ -52,6 +52,7 @@ struct sugov_policy { struct sugov_cpu { struct update_util_data update_util; struct sugov_policy *sg_policy; + unsigned int cpu; bool iowait_boost_pending; unsigned int iowait_boost; @@ -77,6 +78,21 @@ static bool sugov_should_update_freq(struct sugov_policy *sg_policy, u64 time) { s64 delta_ns; + /* + * Since cpufreq_update_util() is called with rq->lock held for + * the @target_cpu, our per-cpu data is fully serialized. + * + * However, drivers cannot in general deal with cross-cpu + * requests, so while get_next_freq() will work, our + * sugov_update_commit() call may not. + * + * Hence stop here for remote requests if they aren't supported + * by the hardware, as calculating the frequency is pointless if + * we cannot in fact act on it. + */ + if (!cpufreq_can_do_remote_dvfs(sg_policy->policy)) + return false; + if (sg_policy->work_in_progress) return false; @@ -155,12 +171,12 @@ static unsigned int get_next_freq(struct sugov_policy *sg_policy, return cpufreq_driver_resolve_freq(policy, freq); } -static void sugov_get_util(unsigned long *util, unsigned long *max) +static void sugov_get_util(unsigned long *util, unsigned long *max, int cpu) { - struct rq *rq = this_rq(); + struct rq *rq = cpu_rq(cpu); unsigned long cfs_max; - cfs_max = arch_scale_cpu_capacity(NULL, smp_processor_id()); + cfs_max = arch_scale_cpu_capacity(NULL, cpu); *util = min(rq->cfs.avg.util_avg, cfs_max); *max = cfs_max; @@ -254,7 +270,7 @@ static void sugov_update_single(struct update_util_data *hook, u64 time, if (flags & SCHED_CPUFREQ_RT_DL) { next_f = policy->cpuinfo.max_freq; } else { - sugov_get_util(&util, &max); + sugov_get_util(&util, &max, sg_cpu->cpu); sugov_iowait_boost(sg_cpu, &util, &max); next_f = get_next_freq(sg_policy, util, max); /* @@ -316,7 +332,7 @@ static void sugov_update_shared(struct update_util_data *hook, u64 time, unsigned long util, max; unsigned int next_f; - sugov_get_util(&util, &max); + sugov_get_util(&util, &max, sg_cpu->cpu); raw_spin_lock(&sg_policy->update_lock); @@ -697,6 +713,11 @@ struct cpufreq_governor *cpufreq_default_governor(void) static int __init sugov_register(void) { + int cpu; + + for_each_possible_cpu(cpu) + per_cpu(sugov_cpu, cpu).cpu = cpu; + return cpufreq_register_governor(&schedutil_gov); } fs_initcall(sugov_register); diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 755bd3f1a1a9..5c3bf4bd0327 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -1136,7 +1136,7 @@ static void update_curr_dl(struct rq *rq) } /* kick cpufreq (see the comment in kernel/sched/sched.h). */ - cpufreq_update_this_cpu(rq, SCHED_CPUFREQ_DL); + cpufreq_update_util(rq, SCHED_CPUFREQ_DL); schedstat_set(curr->se.statistics.exec_max, max(curr->se.statistics.exec_max, delta_exec)); diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index c95880e216f6..d378d02fdfcb 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -3278,7 +3278,9 @@ static inline void set_tg_cfs_propagate(struct cfs_rq *cfs_rq) {} static inline void cfs_rq_util_change(struct cfs_rq *cfs_rq) { - if (&this_rq()->cfs == cfs_rq) { + struct rq *rq = rq_of(cfs_rq); + + if (&rq->cfs == cfs_rq) { /* * There are a few boundary cases this might miss but it should * get called often enough that that should (hopefully) not be @@ -3295,7 +3297,7 @@ static inline void cfs_rq_util_change(struct cfs_rq *cfs_rq) * * See cpu_util(). */ - cpufreq_update_util(rq_of(cfs_rq), 0); + cpufreq_update_util(rq, 0); } } @@ -4875,7 +4877,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags) * passed. */ if (p->in_iowait) - cpufreq_update_this_cpu(rq, SCHED_CPUFREQ_IOWAIT); + cpufreq_update_util(rq, SCHED_CPUFREQ_IOWAIT); for_each_sched_entity(se) { if (se->on_rq) diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index 45caf937ef90..0af5ca9e3e3f 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -970,7 +970,7 @@ static void update_curr_rt(struct rq *rq) return; /* Kick cpufreq (see the comment in kernel/sched/sched.h). */ - cpufreq_update_this_cpu(rq, SCHED_CPUFREQ_RT); + cpufreq_update_util(rq, SCHED_CPUFREQ_RT); schedstat_set(curr->se.statistics.exec_max, max(curr->se.statistics.exec_max, delta_exec)); diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index eeef1a3086d1..aa9d5b87b4f8 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -2070,19 +2070,13 @@ static inline void cpufreq_update_util(struct rq *rq, unsigned int flags) { struct update_util_data *data; - data = rcu_dereference_sched(*this_cpu_ptr(&cpufreq_update_util_data)); + data = rcu_dereference_sched(*per_cpu_ptr(&cpufreq_update_util_data, + cpu_of(rq))); if (data) data->func(data, rq_clock(rq), flags); } - -static inline void cpufreq_update_this_cpu(struct rq *rq, unsigned int flags) -{ - if (cpu_of(rq) == smp_processor_id()) - cpufreq_update_util(rq, flags); -} #else static inline void cpufreq_update_util(struct rq *rq, unsigned int flags) {} -static inline void cpufreq_update_this_cpu(struct rq *rq, unsigned int flags) {} #endif /* CONFIG_CPU_FREQ */ #ifdef arch_scale_freq_capacity |