sched/deadline: Make DL capacity-aware

The current SCHED_DEADLINE (DL) scheduler uses a global EDF scheduling
algorithm w/o considering CPU capacity or task utilization.
This works well on homogeneous systems where DL tasks are guaranteed
to have a bounded tardiness but presents issues on heterogeneous
systems.

A DL task can migrate to a CPU which does not have enough CPU capacity
to correctly serve the task (e.g. a task w/ 70ms runtime and 100ms
period on a CPU w/ 512 capacity).

Add the DL fitness function dl_task_fits_capacity() for DL admission
control on heterogeneous systems. A task fits onto a CPU if:

    CPU original capacity / 1024 >= task runtime / task deadline

Use this function on heterogeneous systems to try to find a CPU which
meets this criterion during task wakeup, push and offline migration.

On homogeneous systems the original behavior of the DL admission
control should be retained.

Signed-off-by: Luca Abeni <[email protected]>
Signed-off-by: Dietmar Eggemann <[email protected]>
Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Acked-by: Juri Lelli <[email protected]>
Link: https://lkml.kernel.org/r/[email protected]

Author: Luca Abeni

kernel/sched/cpudeadline.c

@@ -121,7 +121,19 @@ int cpudl_find(struct cpudl *cp, struct task_struct *p,
 
 	if (later_mask &&
 	    cpumask_and(later_mask, cp->free_cpus, p->cpus_ptr)) {
-		return 1;
+		int cpu;
+
+		if (!static_branch_unlikely(&sched_asym_cpucapacity))
+			return 1;
+
+		/* Ensure the capacity of the CPUs fits the task. */
+		for_each_cpu(cpu, later_mask) {
+			if (!dl_task_fits_capacity(p, cpu))
+				cpumask_clear_cpu(cpu, later_mask);
+		}
+
+		if (!cpumask_empty(later_mask))
+			return 1;
 	} else {
 		int best_cpu = cpudl_maximum(cp);
 

kernel/sched/deadline.c

@@ -1643,6 +1643,7 @@ static int
 select_task_rq_dl(struct task_struct *p, int cpu, int sd_flag, int flags)
 {
 	struct task_struct *curr;
+	bool select_rq;
 	struct rq *rq;
 
 	if (sd_flag != SD_BALANCE_WAKE)
@@ -1662,10 +1663,19 @@ select_task_rq_dl(struct task_struct *p, int cpu, int sd_flag, int flags)
 	 * other hand, if it has a shorter deadline, we
 	 * try to make it stay here, it might be important.
 	 */
-	if (unlikely(dl_task(curr)) &&
-	    (curr->nr_cpus_allowed < 2 ||
-	     !dl_entity_preempt(&p->dl, &curr->dl)) &&
-	    (p->nr_cpus_allowed > 1)) {
+	select_rq = unlikely(dl_task(curr)) &&
+		    (curr->nr_cpus_allowed < 2 ||
+		     !dl_entity_preempt(&p->dl, &curr->dl)) &&
+		    p->nr_cpus_allowed > 1;
+
+	/*
+	 * Take the capacity of the CPU into account to
+	 * ensure it fits the requirement of the task.
+	 */
+	if (static_branch_unlikely(&sched_asym_cpucapacity))
+		select_rq |= !dl_task_fits_capacity(p, cpu);
+
+	if (select_rq) {
 		int target = find_later_rq(p);
 
 		if (target != -1 &&

kernel/sched/sched.h

@@ -317,6 +317,21 @@ static inline bool __dl_overflow(struct dl_bw *dl_b, unsigned long cap,
 	       cap_scale(dl_b->bw, cap) < dl_b->total_bw - old_bw + new_bw;
 }
 
+/*
+ * Verify the fitness of task @p to run on @cpu taking into account the
+ * CPU original capacity and the runtime/deadline ratio of the task.
+ *
+ * The function will return true if the CPU original capacity of the
+ * @cpu scaled by SCHED_CAPACITY_SCALE >= runtime/deadline ratio of the
+ * task and false otherwise.
+ */
+static inline bool dl_task_fits_capacity(struct task_struct *p, int cpu)
+{
+	unsigned long cap = arch_scale_cpu_capacity(cpu);
+
+	return cap_scale(p->dl.dl_deadline, cap) >= p->dl.dl_runtime;
+}
+
 extern void init_dl_bw(struct dl_bw *dl_b);
 extern int  sched_dl_global_validate(void);
 extern void sched_dl_do_global(void);