HMP: Force new non-kernel tasks onto big CPUs until load stabilises

Initialise the load stats for new tasks so that they do not
see the instability in early task life which makes it so hard to
decide which CPU is appropriate.

Also, change the fork balance algorithm so that the least loaded of
the CPUs in the big cluster is chosen regardless of the bigness of
the parent task.

This is intended to help performance for applications which use
many short-lived tasks. Although best practise is usually to use
a thread pool, apps which do not do this should not be subject to
the randomness of the early stats.

We should ignore real-time threads for forking on big CPUs, but
it is not possible to figure out if a new thread is real-time or
not at the fork stage. Instead, we prevent kernel threads from
getting the initial boost - when they later become real-time they
will only be on big if their compute requirements demand it.

Signed-off-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Signed-off-by: Chris Redpath <chris.redpath@arm.com>

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index e45295dc33adb7ed82c893d08b0b6cba4c3f6cd4..4c53da3781e08f67258328268cea97ee8f15e79b 100644 (file)
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1618,8 +1618,18 @@ static void __sched_fork(struct task_struct *p)
        p->se.avg.runnable_avg_period = 0;
        p->se.avg.runnable_avg_sum = 0;
 #ifdef CONFIG_SCHED_HMP
-       p->se.avg.hmp_last_up_migration = 0;
-       p->se.avg.hmp_last_down_migration = 0;
+       /* keep LOAD_AVG_MAX in sync with fair.c if load avg series is changed */
+#define LOAD_AVG_MAX 47742
+       if (p->mm) {
+               p->se.avg.hmp_last_up_migration = 0;
+               p->se.avg.hmp_last_down_migration = 0;
+               p->se.avg.load_avg_ratio = 1023;
+               p->se.avg.load_avg_contrib =
+                               (1023 * scale_load_down(p->se.load.weight));
+               p->se.avg.runnable_avg_period = LOAD_AVG_MAX;
+               p->se.avg.runnable_avg_sum = LOAD_AVG_MAX;
+               p->se.avg.usage_avg_sum = LOAD_AVG_MAX;
+       }
 #endif
 #endif
 #ifdef CONFIG_SCHEDSTATS

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index a38a3edb07de93fa20f9e458afb7ed5a8b4ee55d..1b784eea661da758771ab742b693e2830adb8e8b 100644 (file)
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -3957,6 +3957,28 @@ select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flags)
        if (p->nr_cpus_allowed == 1)
                return prev_cpu;
 
+#ifdef CONFIG_SCHED_HMP
+       /* always put non-kernel forking tasks on a big domain */
+       if (p->mm && (sd_flag & SD_BALANCE_FORK)) {
+               if(hmp_cpu_is_fastest(prev_cpu)) {
+                       struct hmp_domain *hmpdom = list_entry(&hmp_cpu_domain(prev_cpu)->hmp_domains, struct hmp_domain, hmp_domains);
+                       __always_unused int lowest_ratio = hmp_domain_min_load(hmpdom, &new_cpu);
+                       if(new_cpu != NR_CPUS && cpumask_test_cpu(new_cpu,tsk_cpus_allowed(p)))
+                               return new_cpu;
+                       else {
+                               new_cpu = cpumask_any_and(&hmp_faster_domain(cpu)->cpus,
+                                               tsk_cpus_allowed(p));
+                               if(new_cpu < nr_cpu_ids)
+                                       return new_cpu;
+                       }
+               } else {
+                       new_cpu = hmp_select_faster_cpu(p, prev_cpu);
+                       if (new_cpu != NR_CPUS)
+                               return new_cpu;
+               }
+       }
+#endif
+
        if (sd_flag & SD_BALANCE_WAKE) {
                if (cpumask_test_cpu(cpu, tsk_cpus_allowed(p)))
                        want_affine = 1;