psi: split update_stats into parts

Split update_stats into collect_percpu_times and update_averages for
collect_percpu_times to be reused later inside psi monitor.

Link: http://lkml.kernel.org/r/20190319235619.260832-5-surenb@google.com
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Dennis Zhou <dennis@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Li Zefan <lizefan@huawei.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Tejun Heo <tj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c
index 4fb4d99..ace5ed9 100644 (file)
--- a/kernel/sched/psi.c
+++ b/kernel/sched/psi.c
@@ -269,17 +269,13 @@ static void calc_avgs(unsigned long avg[3], int missed_periods,
        avg[2] = calc_load(avg[2], EXP_300s, pct);
 }
 
-static bool update_stats(struct psi_group *group)
+static bool collect_percpu_times(struct psi_group *group)
 {
        u64 deltas[NR_PSI_STATES - 1] = { 0, };
-       unsigned long missed_periods = 0;
        unsigned long nonidle_total = 0;
-       u64 now, expires, period;
        int cpu;
        int s;
 
-       mutex_lock(&group->avgs_lock);
-
        /*
         * Collect the per-cpu time buckets and average them into a
         * single time sample that is normalized to wallclock time.
@@ -317,11 +313,18 @@ static bool update_stats(struct psi_group *group)
        for (s = 0; s < NR_PSI_STATES - 1; s++)
                group->total[s] += div_u64(deltas[s], max(nonidle_total, 1UL));
 
+       return nonidle_total;
+}
+
+static u64 update_averages(struct psi_group *group, u64 now)
+{
+       unsigned long missed_periods = 0;
+       u64 expires, period;
+       u64 avg_next_update;
+       int s;
+
        /* avgX= */
-       now = sched_clock();
        expires = group->avg_next_update;
-       if (now < expires)
-               goto out;
        if (now - expires >= psi_period)
                missed_periods = div_u64(now - expires, psi_period);
 
@@ -332,7 +335,7 @@ 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->avg_next_update = expires + ((1 + missed_periods) * psi_period);
+       avg_next_update = expires + ((1 + missed_periods) * psi_period);
        period = now - (group->avg_last_update + (missed_periods * psi_period));
        group->avg_last_update = now;
 
@@ -362,9 +365,8 @@ static bool update_stats(struct psi_group *group)
                group->avg_total[s] += sample;
                calc_avgs(group->avg[s], missed_periods, sample, period);
        }
-out:
-       mutex_unlock(&group->avgs_lock);
-       return nonidle_total;
+
+       return avg_next_update;
 }
 
 static void psi_avgs_work(struct work_struct *work)
@@ -372,10 +374,16 @@ static void psi_avgs_work(struct work_struct *work)
        struct delayed_work *dwork;
        struct psi_group *group;
        bool nonidle;
+       u64 now;
 
        dwork = to_delayed_work(work);
        group = container_of(dwork, struct psi_group, avgs_work);
 
+       mutex_lock(&group->avgs_lock);
+
+       now = sched_clock();
+
+       nonidle = collect_percpu_times(group);
        /*
         * If there is task activity, periodically fold the per-cpu
         * times and feed samples into the running averages. If things
@@ -383,19 +391,15 @@ static void psi_avgs_work(struct work_struct *work)
         * Once restarted, we'll catch up the running averages in one
         * go - see calc_avgs() and missed_periods.
         */
-
-       nonidle = update_stats(group);
+       if (now >= group->avg_next_update)
+               group->avg_next_update = update_averages(group, now);
 
        if (nonidle) {
-               unsigned long delay = 0;
-               u64 now;
-
-               now = sched_clock();
-               if (group->avg_next_update > now)
-                       delay = nsecs_to_jiffies(
-                                       group->avg_next_update - now) + 1;
-               schedule_delayed_work(dwork, delay);
+               schedule_delayed_work(dwork, nsecs_to_jiffies(
+                               group->avg_next_update - now) + 1);
        }
+
+       mutex_unlock(&group->avgs_lock);
 }
 
 static void record_times(struct psi_group_cpu *groupc, int cpu,
@@ -707,11 +711,18 @@ void cgroup_move_task(struct task_struct *task, struct css_set *to)
 int psi_show(struct seq_file *m, struct psi_group *group, enum psi_res res)
 {
        int full;
+       u64 now;
 
        if (static_branch_likely(&psi_disabled))
                return -EOPNOTSUPP;
 
-       update_stats(group);
+       /* Update averages before reporting them */
+       mutex_lock(&group->avgs_lock);
+       now = sched_clock();
+       collect_percpu_times(group);
+       if (now >= group->avg_next_update)
+               group->avg_next_update = update_averages(group, now);
+       mutex_unlock(&group->avgs_lock);
 
        for (full = 0; full < 2 - (res == PSI_CPU); full++) {
                unsigned long avg[3];