sched/deadline: Implement fallback mechanism for !fit case

When a task has a runtime that cannot be served within the scheduling
deadline by any of the idle CPU (later_mask) the task is doomed to miss
its deadline.

This can happen since the SCHED_DEADLINE admission control guarantees
only bounded tardiness and not the hard respect of all deadlines.
In this case try to select the idle CPU with the largest CPU capacity
to minimize tardiness.

Favor task_cpu(p) if it has max capacity of !fitting CPUs so that
find_later_rq() can potentially still return it (most likely cache-hot)
early.
Signed-off-by: Luca Abeni <luca.abeni@santannapisa.it>
Signed-off-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Juri Lelli <juri.lelli@redhat.com>
Link: https://lkml.kernel.org/r/20200520134243.19352-6-dietmar.eggemann@arm.com

kernel/sched/cpudeadline.c

@@ -121,19 +121,31 @@ int cpudl_find(struct cpudl *cp, struct task_struct *p,
 
 	if (later_mask &&
 	    cpumask_and(later_mask, cp->free_cpus, p->cpus_ptr)) {
-		int cpu;
+		unsigned long cap, max_cap = 0;
+		int cpu, max_cpu = -1;
 
 		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))
+			if (!dl_task_fits_capacity(p, cpu)) {
 				cpumask_clear_cpu(cpu, later_mask);
+
+				cap = capacity_orig_of(cpu);
+
+				if (cap > max_cap ||
+				    (cpu == task_cpu(p) && cap == max_cap)) {
+					max_cap = cap;
+					max_cpu = cpu;
+				}
+			}
 		}
 
-		if (!cpumask_empty(later_mask))
-			return 1;
+		if (cpumask_empty(later_mask))
+			cpumask_set_cpu(max_cpu, later_mask);
+
+		return 1;
 	} else {
 		int best_cpu = cpudl_maximum(cp);