Loading include/linux/psi_types.h +7 −7 Original line number Diff line number Diff line Loading @@ -69,17 +69,17 @@ struct psi_group_cpu { }; struct psi_group { /* Protects data updated during an aggregation */ struct mutex stat_lock; /* Protects data used by the aggregator */ struct mutex avgs_lock; /* Per-cpu task state & time tracking */ struct psi_group_cpu __percpu *pcpu; /* Periodic aggregation state */ u64 total_prev[NR_PSI_STATES - 1]; u64 last_update; u64 next_update; struct delayed_work clock_work; /* Running pressure averages */ u64 avg_total[NR_PSI_STATES - 1]; u64 avg_last_update; u64 avg_next_update; struct delayed_work avgs_work; /* Total stall times and sampled pressure averages */ u64 total[NR_PSI_STATES - 1]; Loading kernel/sched/psi.c +23 −22 Original line number Diff line number Diff line Loading @@ -140,9 +140,9 @@ static int psi_bug __read_mostly; DEFINE_STATIC_KEY_FALSE(psi_disabled); #ifdef CONFIG_PSI_DEFAULT_DISABLED bool psi_enable; static bool psi_enable; #else bool psi_enable = true; static bool psi_enable = true; #endif static int __init setup_psi(char *str) { Loading @@ -165,7 +165,7 @@ static struct psi_group psi_system = { .pcpu = &system_group_pcpu, }; static void psi_update_work(struct work_struct *work); static void psi_avgs_work(struct work_struct *work); static void group_init(struct psi_group *group) { Loading @@ -173,9 +173,9 @@ static void group_init(struct psi_group *group) for_each_possible_cpu(cpu) seqcount_init(&per_cpu_ptr(group->pcpu, cpu)->seq); group->next_update = sched_clock() + psi_period; INIT_DELAYED_WORK(&group->clock_work, psi_update_work); mutex_init(&group->stat_lock); group->avg_next_update = sched_clock() + psi_period; INIT_DELAYED_WORK(&group->avgs_work, psi_avgs_work); mutex_init(&group->avgs_lock); } void __init psi_init(void) Loading Loading @@ -278,7 +278,7 @@ static bool update_stats(struct psi_group *group) int cpu; int s; mutex_lock(&group->stat_lock); mutex_lock(&group->avgs_lock); /* * Collect the per-cpu time buckets and average them into a Loading Loading @@ -319,7 +319,7 @@ static bool update_stats(struct psi_group *group) /* avgX= */ now = sched_clock(); expires = group->next_update; expires = group->avg_next_update; if (now < expires) goto out; if (now - expires >= psi_period) Loading @@ -332,14 +332,14 @@ static bool update_stats(struct psi_group *group) * But the deltas we sample out of the per-cpu buckets above * are based on the actual time elapsing between clock ticks. */ group->next_update = expires + ((1 + missed_periods) * psi_period); period = now - (group->last_update + (missed_periods * psi_period)); group->last_update = now; group->avg_next_update = expires + ((1 + missed_periods) * psi_period); period = now - (group->avg_last_update + (missed_periods * psi_period)); group->avg_last_update = now; for (s = 0; s < NR_PSI_STATES - 1; s++) { u32 sample; sample = group->total[s] - group->total_prev[s]; sample = group->total[s] - group->avg_total[s]; /* * Due to the lockless sampling of the time buckets, * recorded time deltas can slip into the next period, Loading @@ -359,22 +359,22 @@ static bool update_stats(struct psi_group *group) */ if (sample > period) sample = period; group->total_prev[s] += sample; group->avg_total[s] += sample; calc_avgs(group->avg[s], missed_periods, sample, period); } out: mutex_unlock(&group->stat_lock); mutex_unlock(&group->avgs_lock); return nonidle_total; } static void psi_update_work(struct work_struct *work) static void psi_avgs_work(struct work_struct *work) { struct delayed_work *dwork; struct psi_group *group; bool nonidle; dwork = to_delayed_work(work); group = container_of(dwork, struct psi_group, clock_work); group = container_of(dwork, struct psi_group, avgs_work); /* * If there is task activity, periodically fold the per-cpu Loading @@ -391,8 +391,9 @@ static void psi_update_work(struct work_struct *work) u64 now; now = sched_clock(); if (group->next_update > now) delay = nsecs_to_jiffies(group->next_update - now) + 1; if (group->avg_next_update > now) delay = nsecs_to_jiffies( group->avg_next_update - now) + 1; schedule_delayed_work(dwork, delay); } } Loading Loading @@ -546,13 +547,13 @@ void psi_task_change(struct task_struct *task, int clear, int set) */ if (unlikely((clear & TSK_RUNNING) && (task->flags & PF_WQ_WORKER) && wq_worker_last_func(task) == psi_update_work)) wq_worker_last_func(task) == psi_avgs_work)) wake_clock = false; while ((group = iterate_groups(task, &iter))) { psi_group_change(group, cpu, clear, set); if (wake_clock && !delayed_work_pending(&group->clock_work)) schedule_delayed_work(&group->clock_work, PSI_FREQ); if (wake_clock && !delayed_work_pending(&group->avgs_work)) schedule_delayed_work(&group->avgs_work, PSI_FREQ); } } Loading Loading @@ -649,7 +650,7 @@ void psi_cgroup_free(struct cgroup *cgroup) if (static_branch_likely(&psi_disabled)) return; cancel_delayed_work_sync(&cgroup->psi.clock_work); cancel_delayed_work_sync(&cgroup->psi.avgs_work); free_percpu(cgroup->psi.pcpu); } Loading Loading
include/linux/psi_types.h +7 −7 Original line number Diff line number Diff line Loading @@ -69,17 +69,17 @@ struct psi_group_cpu { }; struct psi_group { /* Protects data updated during an aggregation */ struct mutex stat_lock; /* Protects data used by the aggregator */ struct mutex avgs_lock; /* Per-cpu task state & time tracking */ struct psi_group_cpu __percpu *pcpu; /* Periodic aggregation state */ u64 total_prev[NR_PSI_STATES - 1]; u64 last_update; u64 next_update; struct delayed_work clock_work; /* Running pressure averages */ u64 avg_total[NR_PSI_STATES - 1]; u64 avg_last_update; u64 avg_next_update; struct delayed_work avgs_work; /* Total stall times and sampled pressure averages */ u64 total[NR_PSI_STATES - 1]; Loading
kernel/sched/psi.c +23 −22 Original line number Diff line number Diff line Loading @@ -140,9 +140,9 @@ static int psi_bug __read_mostly; DEFINE_STATIC_KEY_FALSE(psi_disabled); #ifdef CONFIG_PSI_DEFAULT_DISABLED bool psi_enable; static bool psi_enable; #else bool psi_enable = true; static bool psi_enable = true; #endif static int __init setup_psi(char *str) { Loading @@ -165,7 +165,7 @@ static struct psi_group psi_system = { .pcpu = &system_group_pcpu, }; static void psi_update_work(struct work_struct *work); static void psi_avgs_work(struct work_struct *work); static void group_init(struct psi_group *group) { Loading @@ -173,9 +173,9 @@ static void group_init(struct psi_group *group) for_each_possible_cpu(cpu) seqcount_init(&per_cpu_ptr(group->pcpu, cpu)->seq); group->next_update = sched_clock() + psi_period; INIT_DELAYED_WORK(&group->clock_work, psi_update_work); mutex_init(&group->stat_lock); group->avg_next_update = sched_clock() + psi_period; INIT_DELAYED_WORK(&group->avgs_work, psi_avgs_work); mutex_init(&group->avgs_lock); } void __init psi_init(void) Loading Loading @@ -278,7 +278,7 @@ static bool update_stats(struct psi_group *group) int cpu; int s; mutex_lock(&group->stat_lock); mutex_lock(&group->avgs_lock); /* * Collect the per-cpu time buckets and average them into a Loading Loading @@ -319,7 +319,7 @@ static bool update_stats(struct psi_group *group) /* avgX= */ now = sched_clock(); expires = group->next_update; expires = group->avg_next_update; if (now < expires) goto out; if (now - expires >= psi_period) Loading @@ -332,14 +332,14 @@ static bool update_stats(struct psi_group *group) * But the deltas we sample out of the per-cpu buckets above * are based on the actual time elapsing between clock ticks. */ group->next_update = expires + ((1 + missed_periods) * psi_period); period = now - (group->last_update + (missed_periods * psi_period)); group->last_update = now; group->avg_next_update = expires + ((1 + missed_periods) * psi_period); period = now - (group->avg_last_update + (missed_periods * psi_period)); group->avg_last_update = now; for (s = 0; s < NR_PSI_STATES - 1; s++) { u32 sample; sample = group->total[s] - group->total_prev[s]; sample = group->total[s] - group->avg_total[s]; /* * Due to the lockless sampling of the time buckets, * recorded time deltas can slip into the next period, Loading @@ -359,22 +359,22 @@ static bool update_stats(struct psi_group *group) */ if (sample > period) sample = period; group->total_prev[s] += sample; group->avg_total[s] += sample; calc_avgs(group->avg[s], missed_periods, sample, period); } out: mutex_unlock(&group->stat_lock); mutex_unlock(&group->avgs_lock); return nonidle_total; } static void psi_update_work(struct work_struct *work) static void psi_avgs_work(struct work_struct *work) { struct delayed_work *dwork; struct psi_group *group; bool nonidle; dwork = to_delayed_work(work); group = container_of(dwork, struct psi_group, clock_work); group = container_of(dwork, struct psi_group, avgs_work); /* * If there is task activity, periodically fold the per-cpu Loading @@ -391,8 +391,9 @@ static void psi_update_work(struct work_struct *work) u64 now; now = sched_clock(); if (group->next_update > now) delay = nsecs_to_jiffies(group->next_update - now) + 1; if (group->avg_next_update > now) delay = nsecs_to_jiffies( group->avg_next_update - now) + 1; schedule_delayed_work(dwork, delay); } } Loading Loading @@ -546,13 +547,13 @@ void psi_task_change(struct task_struct *task, int clear, int set) */ if (unlikely((clear & TSK_RUNNING) && (task->flags & PF_WQ_WORKER) && wq_worker_last_func(task) == psi_update_work)) wq_worker_last_func(task) == psi_avgs_work)) wake_clock = false; while ((group = iterate_groups(task, &iter))) { psi_group_change(group, cpu, clear, set); if (wake_clock && !delayed_work_pending(&group->clock_work)) schedule_delayed_work(&group->clock_work, PSI_FREQ); if (wake_clock && !delayed_work_pending(&group->avgs_work)) schedule_delayed_work(&group->avgs_work, PSI_FREQ); } } Loading Loading @@ -649,7 +650,7 @@ void psi_cgroup_free(struct cgroup *cgroup) if (static_branch_likely(&psi_disabled)) return; cancel_delayed_work_sync(&cgroup->psi.clock_work); cancel_delayed_work_sync(&cgroup->psi.avgs_work); free_percpu(cgroup->psi.pcpu); } Loading