diff -drupN a/include/linux/sched.h b/include/linux/sched.h --- a/include/linux/sched.h 2018-08-06 17:23:04.000000000 +0300 +++ b/include/linux/sched.h 2022-06-12 05:28:14.000000000 +0300 @@ -173,6 +173,9 @@ extern bool single_task_running(void); extern unsigned long nr_iowait(void); extern unsigned long nr_iowait_cpu(int cpu); extern void get_iowait_load(unsigned long *nr_waiters, unsigned long *load); +#ifdef CONFIG_CPU_QUIET +extern u64 nr_running_integral(unsigned int cpu); +#endif extern void calc_global_load(unsigned long ticks); @@ -315,6 +318,15 @@ extern char ___assert_task_state[1 - 2*! /* Task command name length */ #define TASK_COMM_LEN 16 +enum task_event { + PUT_PREV_TASK = 0, + PICK_NEXT_TASK = 1, + TASK_WAKE = 2, + TASK_MIGRATE = 3, + TASK_UPDATE = 4, + IRQ_UPDATE = 5, +}; + #include /* @@ -982,6 +994,14 @@ enum cpu_idle_type { #define SCHED_CAPACITY_SHIFT SCHED_FIXEDPOINT_SHIFT #define SCHED_CAPACITY_SCALE (1L << SCHED_CAPACITY_SHIFT) +struct sched_capacity_reqs { + unsigned long cfs; + unsigned long rt; + unsigned long dl; + + unsigned long total; +}; + /* * Wake-queues are lists of tasks with a pending wakeup, whose * callers have already marked the task as woken internally, @@ -1045,6 +1065,7 @@ extern void wake_up_q(struct wake_q_head #define SD_PREFER_SIBLING 0x1000 /* Prefer to place tasks in a sibling domain */ #define SD_OVERLAP 0x2000 /* sched_domains of this level overlap */ #define SD_NUMA 0x4000 /* cross-node balancing */ +#define SD_SHARE_CAP_STATES 0x8000 /* Domain members share capacity state */ #ifdef CONFIG_SCHED_SMT static inline int cpu_smt_flags(void) @@ -1077,8 +1098,57 @@ struct sched_domain_attr { extern int sched_domain_level_max; +struct capacity_state { + unsigned long cap; /* compute capacity */ + unsigned long power; /* power consumption at this compute capacity */ +}; + +struct idle_state { + unsigned long power; /* power consumption in this idle state */ +}; + +struct sched_group_energy { + unsigned int nr_idle_states; /* number of idle states */ + struct idle_state *idle_states; /* ptr to idle state array */ + unsigned int nr_cap_states; /* number of capacity states */ + struct capacity_state *cap_states; /* ptr to capacity state array */ +}; + +unsigned long capacity_curr_of(int cpu); + struct sched_group; +struct eas_stats { + /* select_idle_sibling() stats */ + u64 sis_attempts; + u64 sis_idle; + u64 sis_cache_affine; + u64 sis_suff_cap; + u64 sis_idle_cpu; + u64 sis_count; + + /* select_energy_cpu_brute() stats */ + u64 secb_attempts; + u64 secb_sync; + u64 secb_idle_bt; + u64 secb_insuff_cap; + u64 secb_no_nrg_sav; + u64 secb_nrg_sav; + u64 secb_count; + + /* find_best_target() stats */ + u64 fbt_attempts; + u64 fbt_no_cpu; + u64 fbt_no_sd; + u64 fbt_pref_idle; + u64 fbt_count; + + /* cas */ + /* select_task_rq_fair() stats */ + u64 cas_attempts; + u64 cas_count; +}; + struct sched_domain_shared { atomic_t ref; atomic_t nr_busy_cpus; @@ -1147,6 +1217,8 @@ struct sched_domain { unsigned int ttwu_wake_remote; unsigned int ttwu_move_affine; unsigned int ttwu_move_balance; + + struct eas_stats eas_stats; #endif #ifdef CONFIG_SCHED_DEBUG char *name; @@ -1184,6 +1256,8 @@ bool cpus_share_cache(int this_cpu, int typedef const struct cpumask *(*sched_domain_mask_f)(int cpu); typedef int (*sched_domain_flags_f)(void); +typedef +const struct sched_group_energy * const(*sched_domain_energy_f)(int cpu); #define SDTL_OVERLAP 0x01 @@ -1197,6 +1271,7 @@ struct sd_data { struct sched_domain_topology_level { sched_domain_mask_f mask; sched_domain_flags_f sd_flags; + sched_domain_energy_f energy; int flags; int numa_level; struct sd_data data; @@ -1342,6 +1417,70 @@ struct sched_statistics { u64 nr_wakeups_affine_attempts; u64 nr_wakeups_passive; u64 nr_wakeups_idle; + + /* select_idle_sibling() */ + u64 nr_wakeups_sis_attempts; + u64 nr_wakeups_sis_idle; + u64 nr_wakeups_sis_cache_affine; + u64 nr_wakeups_sis_suff_cap; + u64 nr_wakeups_sis_idle_cpu; + u64 nr_wakeups_sis_count; + + /* energy_aware_wake_cpu() */ + u64 nr_wakeups_secb_attempts; + u64 nr_wakeups_secb_sync; + u64 nr_wakeups_secb_idle_bt; + u64 nr_wakeups_secb_insuff_cap; + u64 nr_wakeups_secb_no_nrg_sav; + u64 nr_wakeups_secb_nrg_sav; + u64 nr_wakeups_secb_count; + + /* find_best_target() */ + u64 nr_wakeups_fbt_attempts; + u64 nr_wakeups_fbt_no_cpu; + u64 nr_wakeups_fbt_no_sd; + u64 nr_wakeups_fbt_pref_idle; + u64 nr_wakeups_fbt_count; + + /* cas */ + /* select_task_rq_fair() */ + u64 nr_wakeups_cas_attempts; + u64 nr_wakeups_cas_count; +}; +#endif + +#ifdef CONFIG_SCHED_WALT +#define RAVG_HIST_SIZE_MAX 5 + +/* ravg represents frequency scaled cpu-demand of tasks */ +struct ravg { + /* + * 'mark_start' marks the beginning of an event (task waking up, task + * starting to execute, task being preempted) within a window + * + * 'sum' represents how runnable a task has been within current + * window. It incorporates both running time and wait time and is + * frequency scaled. + * + * 'sum_history' keeps track of history of 'sum' seen over previous + * RAVG_HIST_SIZE windows. Windows where task was entirely sleeping are + * ignored. + * + * 'demand' represents maximum sum seen over previous + * sysctl_sched_ravg_hist_size windows. 'demand' could drive frequency + * demand for tasks. + * + * 'curr_window' represents task's contribution to cpu busy time + * statistics (rq->curr_runnable_sum) in current window + * + * 'prev_window' represents task's contribution to cpu busy time + * statistics (rq->prev_runnable_sum) in previous window + */ + u64 mark_start; + u32 sum, demand; + u32 sum_history[RAVG_HIST_SIZE_MAX]; + u32 curr_window, prev_window; + u16 active_windows; }; #endif @@ -1516,6 +1655,16 @@ struct task_struct { const struct sched_class *sched_class; struct sched_entity se; struct sched_rt_entity rt; +#ifdef CONFIG_SCHED_WALT + struct ravg ravg; + /* + * 'init_load_pct' represents the initial task load assigned to children + * of this task + */ + u32 init_load_pct; + u64 last_sleep_ts; +#endif + #ifdef CONFIG_CGROUP_SCHED struct task_group *sched_task_group; #endif @@ -1644,6 +1793,10 @@ struct task_struct { cputime_t utime, stime, utimescaled, stimescaled; cputime_t gtime; +#ifdef CONFIG_CPU_FREQ_TIMES + u64 *time_in_state; + unsigned int max_state; +#endif struct prev_cputime prev_cputime; #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN seqcount_t vtime_seqcount; @@ -3571,6 +3724,11 @@ static inline void inc_syscw(struct task { tsk->ioac.syscw++; } + +static inline void inc_syscfs(struct task_struct *tsk) +{ + tsk->ioac.syscfs++; +} #else static inline void add_rchar(struct task_struct *tsk, ssize_t amt) { @@ -3587,6 +3745,9 @@ static inline void inc_syscr(struct task static inline void inc_syscw(struct task_struct *tsk) { } +static inline void inc_syscfs(struct task_struct *tsk) +{ +} #endif #ifndef TASK_SIZE_OF