sched/topology: Reference the Energy Model of CPUs when available

[linux.git] / kernel / sched / sched.h

diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 618577fc9aa873d20425c3c4ac590bb91a8af003..808a565187b1de47dff2357f5478de09c08796db 100644 (file)
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -23,6 +23,7 @@
 #include <linux/sched/prio.h>
 #include <linux/sched/rt.h>
 #include <linux/sched/signal.h>
+#include <linux/sched/smt.h>
 #include <linux/sched/stat.h>
 #include <linux/sched/sysctl.h>
 #include <linux/sched/task.h>
@@ -44,6 +45,7 @@
 #include <linux/ctype.h>
 #include <linux/debugfs.h>
 #include <linux/delayacct.h>
+#include <linux/energy_model.h>
 #include <linux/init_task.h>
 #include <linux/kprobes.h>
 #include <linux/kthread.h>
@@ -176,6 +178,11 @@ static inline bool valid_policy(int policy)
                rt_policy(policy) || dl_policy(policy);
 }
 
+static inline int task_has_idle_policy(struct task_struct *p)
+{
+       return idle_policy(p->policy);
+}
+
 static inline int task_has_rt_policy(struct task_struct *p)
 {
        return rt_policy(p->policy);
@@ -631,7 +638,7 @@ struct dl_rq {
        /*
         * Deadline values of the currently executing and the
         * earliest ready task on this rq. Caching these facilitates
-        * the decision wether or not a ready but not running task
+        * the decision whether or not a ready but not running task
         * should migrate somewhere else.
         */
        struct {
@@ -703,6 +710,12 @@ static inline bool sched_asym_prefer(int a, int b)
        return arch_asym_cpu_priority(a) > arch_asym_cpu_priority(b);
 }
 
+struct perf_domain {
+       struct em_perf_domain *em_pd;
+       struct perf_domain *next;
+       struct rcu_head rcu;
+};
+
 /*
  * We add the notion of a root-domain which will be used to define per-domain
  * variables. Each exclusive cpuset essentially defines an island domain by
@@ -755,6 +768,12 @@ struct root_domain {
        struct cpupri           cpupri;
 
        unsigned long           max_cpu_capacity;
+
+       /*
+        * NULL-terminated list of performance domains intersecting with the
+        * CPUs of the rd. Protected by RCU.
+        */
+       struct perf_domain      *pd;
 };
 
 extern struct root_domain def_root_domain;
@@ -936,9 +955,6 @@ static inline int cpu_of(struct rq *rq)
 
 
 #ifdef CONFIG_SCHED_SMT
-
-extern struct static_key_false sched_smt_present;
-
 extern void __update_idle_core(struct rq *rq);
 
 static inline void update_idle_core(struct rq *rq)
@@ -1431,7 +1447,7 @@ static inline void __set_task_cpu(struct task_struct *p, unsigned int cpu)
 #ifdef CONFIG_SMP
        /*
         * After ->cpu is set up to a new value, task_rq_lock(p, ...) can be
-        * successfuly executed on another CPU. We must ensure that updates of
+        * successfully executed on another CPU. We must ensure that updates of
         * per-task data have been completed by this moment.
         */
        smp_wmb();
@@ -1796,12 +1812,12 @@ static inline void add_nr_running(struct rq *rq, unsigned count)
 
        rq->nr_running = prev_nr + count;
 
-       if (prev_nr < 2 && rq->nr_running >= 2) {
 #ifdef CONFIG_SMP
+       if (prev_nr < 2 && rq->nr_running >= 2) {
                if (!READ_ONCE(rq->rd->overload))
                        WRITE_ONCE(rq->rd->overload, 1);
-#endif
        }
+#endif
 
        sched_update_tick_dependency(rq);
 }
@@ -1856,27 +1872,6 @@ unsigned long arch_scale_freq_capacity(int cpu)
 }
 #endif
 
-#ifdef CONFIG_SMP
-#ifndef arch_scale_cpu_capacity
-static __always_inline
-unsigned long arch_scale_cpu_capacity(struct sched_domain *sd, int cpu)
-{
-       if (sd && (sd->flags & SD_SHARE_CPUCAPACITY) && (sd->span_weight > 1))
-               return sd->smt_gain / sd->span_weight;
-
-       return SCHED_CAPACITY_SCALE;
-}
-#endif
-#else
-#ifndef arch_scale_cpu_capacity
-static __always_inline
-unsigned long arch_scale_cpu_capacity(void __always_unused *sd, int cpu)
-{
-       return SCHED_CAPACITY_SCALE;
-}
-#endif
-#endif
-
 #ifdef CONFIG_SMP
 #ifdef CONFIG_PREEMPT
 
@@ -2209,6 +2204,31 @@ static inline void cpufreq_update_util(struct rq *rq, unsigned int flags) {}
 #endif
 
 #ifdef CONFIG_CPU_FREQ_GOV_SCHEDUTIL
+/**
+ * enum schedutil_type - CPU utilization type
+ * @FREQUENCY_UTIL:    Utilization used to select frequency
+ * @ENERGY_UTIL:       Utilization used during energy calculation
+ *
+ * The utilization signals of all scheduling classes (CFS/RT/DL) and IRQ time
+ * need to be aggregated differently depending on the usage made of them. This
+ * enum is used within schedutil_freq_util() to differentiate the types of
+ * utilization expected by the callers, and adjust the aggregation accordingly.
+ */
+enum schedutil_type {
+       FREQUENCY_UTIL,
+       ENERGY_UTIL,
+};
+
+unsigned long schedutil_freq_util(int cpu, unsigned long util_cfs,
+                                 unsigned long max, enum schedutil_type type);
+
+static inline unsigned long schedutil_energy_util(int cpu, unsigned long cfs)
+{
+       unsigned long max = arch_scale_cpu_capacity(NULL, cpu);
+
+       return schedutil_freq_util(cpu, cfs, max, ENERGY_UTIL);
+}
+
 static inline unsigned long cpu_bw_dl(struct rq *rq)
 {
        return (rq->dl.running_bw * SCHED_CAPACITY_SCALE) >> BW_SHIFT;
@@ -2235,6 +2255,11 @@ static inline unsigned long cpu_util_rt(struct rq *rq)
 {
        return READ_ONCE(rq->avg_rt.util_avg);
 }
+#else /* CONFIG_CPU_FREQ_GOV_SCHEDUTIL */
+static inline unsigned long schedutil_energy_util(int cpu, unsigned long cfs)
+{
+       return cfs;
+}
 #endif
 
 #ifdef CONFIG_HAVE_SCHED_AVG_IRQ
@@ -2264,3 +2289,11 @@ unsigned long scale_irq_capacity(unsigned long util, unsigned long irq, unsigned
        return util;
 }
 #endif
+
+#ifdef CONFIG_SMP
+#ifdef CONFIG_ENERGY_MODEL
+#define perf_domain_span(pd) (to_cpumask(((pd)->em_pd->cpus)))
+#else
+#define perf_domain_span(pd) NULL
+#endif
+#endif