diff options
Diffstat (limited to 'kernel/sched/sched.h')
| -rw-r--r-- | kernel/sched/sched.h | 154 |
1 files changed, 152 insertions, 2 deletions
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 55d92a1ca070..e137445987d8 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -506,10 +506,18 @@ struct dl_rq { #else struct dl_bw dl_bw; #endif + /* This is the "average utilization" for this runqueue */ + s64 avg_bw; }; #ifdef CONFIG_SMP +struct max_cpu_capacity { + raw_spinlock_t lock; + unsigned long val; + int cpu; +}; + /* * 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 @@ -528,6 +536,9 @@ struct root_domain { /* Indicate more than one runnable task for any CPU */ bool overload; + /* Indicate one or more cpus over-utilized (tipping point) */ + bool overutilized; + /* * The bit corresponding to a CPU gets set here if such CPU has more * than one runnable -deadline task (as it is below for RT tasks). @@ -543,6 +554,9 @@ struct root_domain { */ cpumask_var_t rto_mask; struct cpupri cpupri; + + /* Maximum cpu capacity in the system. */ + struct max_cpu_capacity max_cpu_capacity; }; extern struct root_domain def_root_domain; @@ -572,6 +586,7 @@ struct rq { #define CPU_LOAD_IDX_MAX 5 unsigned long cpu_load[CPU_LOAD_IDX_MAX]; unsigned long last_load_update_tick; + unsigned int misfit_task; #ifdef CONFIG_NO_HZ_COMMON u64 nohz_stamp; unsigned long nohz_flags; @@ -687,6 +702,7 @@ struct rq { #ifdef CONFIG_CPU_IDLE /* Must be inspected within a rcu lock section */ struct cpuidle_state *idle_state; + int idle_state_idx; #endif }; @@ -836,6 +852,8 @@ DECLARE_PER_CPU(int, sd_llc_id); DECLARE_PER_CPU(struct sched_domain *, sd_numa); DECLARE_PER_CPU(struct sched_domain *, sd_busy); DECLARE_PER_CPU(struct sched_domain *, sd_asym); +DECLARE_PER_CPU(struct sched_domain *, sd_ea); +DECLARE_PER_CPU(struct sched_domain *, sd_scs); struct sched_group_capacity { atomic_t ref; @@ -843,7 +861,8 @@ struct sched_group_capacity { * CPU capacity of this group, SCHED_LOAD_SCALE being max capacity * for a single CPU. */ - unsigned int capacity; + unsigned long capacity; + unsigned long max_capacity; /* Max per-cpu capacity in group */ unsigned long next_update; int imbalance; /* XXX unrelated to capacity but shared group state */ /* @@ -860,6 +879,7 @@ struct sched_group { unsigned int group_weight; struct sched_group_capacity *sgc; + const struct sched_group_energy const *sge; /* * The CPUs this group covers. @@ -1163,6 +1183,7 @@ static const u32 prio_to_wmult[40] = { #endif #define ENQUEUE_REPLENISH 0x08 #define ENQUEUE_RESTORE 0x10 +#define ENQUEUE_WAKEUP_NEW 0x20 #define DEQUEUE_SLEEP 0x01 #define DEQUEUE_SAVE 0x02 @@ -1276,6 +1297,17 @@ static inline struct cpuidle_state *idle_get_state(struct rq *rq) WARN_ON(!rcu_read_lock_held()); return rq->idle_state; } + +static inline void idle_set_state_idx(struct rq *rq, int idle_state_idx) +{ + rq->idle_state_idx = idle_state_idx; +} + +static inline int idle_get_state_idx(struct rq *rq) +{ + WARN_ON(!rcu_read_lock_held()); + return rq->idle_state_idx; +} #else static inline void idle_set_state(struct rq *rq, struct cpuidle_state *idle_state) @@ -1286,6 +1318,15 @@ static inline struct cpuidle_state *idle_get_state(struct rq *rq) { return NULL; } + +static inline void idle_set_state_idx(struct rq *rq, int idle_state_idx) +{ +} + +static inline int idle_get_state_idx(struct rq *rq) +{ + return -1; +} #endif extern void sysrq_sched_debug_show(void); @@ -1310,6 +1351,8 @@ unsigned long to_ratio(u64 period, u64 runtime); extern void init_entity_runnable_average(struct sched_entity *se); +extern void init_max_cpu_capacity(struct max_cpu_capacity *mcc); + static inline void add_nr_running(struct rq *rq, unsigned count) { unsigned prev_nr = rq->nr_running; @@ -1415,10 +1458,117 @@ unsigned long arch_scale_cpu_capacity(struct sched_domain *sd, int cpu) } #endif +#ifdef CONFIG_SMP +static inline unsigned long capacity_of(int cpu) +{ + return cpu_rq(cpu)->cpu_capacity; +} + +static inline unsigned long capacity_orig_of(int cpu) +{ + return cpu_rq(cpu)->cpu_capacity_orig; +} + +/* + * cpu_util returns the amount of capacity of a CPU that is used by CFS + * tasks. The unit of the return value must be the one of capacity so we can + * compare the utilization with the capacity of the CPU that is available for + * CFS task (ie cpu_capacity). + * + * cfs_rq.avg.util_avg is the sum of running time of runnable tasks plus the + * recent utilization of currently non-runnable tasks on a CPU. It represents + * the amount of utilization of a CPU in the range [0..capacity_orig] where + * capacity_orig is the cpu_capacity available at the highest frequency + * (arch_scale_freq_capacity()). + * The utilization of a CPU converges towards a sum equal to or less than the + * current capacity (capacity_curr <= capacity_orig) of the CPU because it is + * the running time on this CPU scaled by capacity_curr. + * + * Nevertheless, cfs_rq.avg.util_avg can be higher than capacity_curr or even + * higher than capacity_orig because of unfortunate rounding in + * cfs.avg.util_avg or just after migrating tasks and new task wakeups until + * the average stabilizes with the new running time. We need to check that the + * utilization stays within the range of [0..capacity_orig] and cap it if + * necessary. Without utilization capping, a group could be seen as overloaded + * (CPU0 utilization at 121% + CPU1 utilization at 80%) whereas CPU1 has 20% of + * available capacity. We allow utilization to overshoot capacity_curr (but not + * capacity_orig) as it useful for predicting the capacity required after task + * migrations (scheduler-driven DVFS). + */ +static inline unsigned long __cpu_util(int cpu, int delta) +{ + unsigned long util = cpu_rq(cpu)->cfs.avg.util_avg; + unsigned long capacity = capacity_orig_of(cpu); + + delta += util; + if (delta < 0) + return 0; + + return (delta >= capacity) ? capacity : delta; +} + +static inline unsigned long cpu_util(int cpu) +{ + return __cpu_util(cpu, 0); +} + +#endif + +#ifdef CONFIG_CPU_FREQ_GOV_SCHED +#define capacity_max SCHED_CAPACITY_SCALE +extern unsigned int capacity_margin; +extern struct static_key __sched_freq; + +static inline bool sched_freq(void) +{ + return static_key_false(&__sched_freq); +} + +DECLARE_PER_CPU(struct sched_capacity_reqs, cpu_sched_capacity_reqs); +void update_cpu_capacity_request(int cpu, bool request); + +static inline void set_cfs_cpu_capacity(int cpu, bool request, + unsigned long capacity) +{ + if (per_cpu(cpu_sched_capacity_reqs, cpu).cfs != capacity) { + per_cpu(cpu_sched_capacity_reqs, cpu).cfs = capacity; + update_cpu_capacity_request(cpu, request); + } +} + +static inline void set_rt_cpu_capacity(int cpu, bool request, + unsigned long capacity) +{ + if (per_cpu(cpu_sched_capacity_reqs, cpu).rt != capacity) { + per_cpu(cpu_sched_capacity_reqs, cpu).rt = capacity; + update_cpu_capacity_request(cpu, request); + } +} + +static inline void set_dl_cpu_capacity(int cpu, bool request, + unsigned long capacity) +{ + if (per_cpu(cpu_sched_capacity_reqs, cpu).dl != capacity) { + per_cpu(cpu_sched_capacity_reqs, cpu).dl = capacity; + update_cpu_capacity_request(cpu, request); + } +} +#else +static inline bool sched_freq(void) { return false; } +static inline void set_cfs_cpu_capacity(int cpu, bool request, + unsigned long capacity) +{ } +static inline void set_rt_cpu_capacity(int cpu, bool request, + unsigned long capacity) +{ } +static inline void set_dl_cpu_capacity(int cpu, bool request, + unsigned long capacity) +{ } +#endif + static inline void sched_rt_avg_update(struct rq *rq, u64 rt_delta) { rq->rt_avg += rt_delta * arch_scale_freq_capacity(NULL, cpu_of(rq)); - sched_avg_update(rq); } #else static inline void sched_rt_avg_update(struct rq *rq, u64 rt_delta) { } |