HMP: Select least-loaded CPU when performing HMP Migrations

The reference patch set always selects the first CPU in an HMP
domain as a migration target. In busy situations, this means that
the migrated thread cannot make immediate use of an idle CPU but
must share a busy one until the load balancer runs across the big
domain.

This patch uses the hmp_domain_min_load function introduced in
global balancing to figure out which of the CPUs is the least busy
and selects that as a migration target - in both directions.

This essentially implements a task-spread strategy and is intended
to maximise performance of migrated threads but is likely
to use more power than the packing strategy previously employed.

Signed-off-by: Chris Redpath <chris.redpath@arm.com>

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index a90a63807cf9639dc4c28f25608355296be9330f..d7303c5fd1edd9c15c575fd7fcd0bcf12009ffca 100644 (file)
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -3598,6 +3598,8 @@ unsigned int hmp_next_down_threshold = 4096;
 
 static unsigned int hmp_up_migration(int cpu, struct sched_entity *se);
 static unsigned int hmp_down_migration(int cpu, struct sched_entity *se);
+static inline unsigned int hmp_domain_min_load(struct hmp_domain *hmpd,
+                                               int *min_cpu);
 
 /* Check if cpu is in fastest hmp_domain */
 static inline unsigned int hmp_cpu_is_fastest(int cpu)
@@ -3642,7 +3644,16 @@ static inline struct hmp_domain *hmp_faster_domain(int cpu)
 static inline unsigned int hmp_select_faster_cpu(struct task_struct *tsk,
                                                        int cpu)
 {
-       return cpumask_any_and(&hmp_faster_domain(cpu)->cpus,
+       int lowest_cpu=NR_CPUS;
+       __always_unused int lowest_ratio = hmp_domain_min_load(hmp_faster_domain(cpu), &lowest_cpu);
+       /*
+        * If the lowest-loaded CPU in the domain is allowed by the task affinity
+        * select that one, otherwise select one which is allowed
+        */
+       if(lowest_cpu != NR_CPUS && cpumask_test_cpu(lowest_cpu,tsk_cpus_allowed(tsk)))
+               return lowest_cpu;
+       else
+               return cpumask_any_and(&hmp_faster_domain(cpu)->cpus,
                                tsk_cpus_allowed(tsk));
 }
 
@@ -3653,7 +3664,16 @@ static inline unsigned int hmp_select_faster_cpu(struct task_struct *tsk,
 static inline unsigned int hmp_select_slower_cpu(struct task_struct *tsk,
                                                        int cpu)
 {
-       return cpumask_any_and(&hmp_slower_domain(cpu)->cpus,
+       int lowest_cpu=NR_CPUS;
+       __always_unused int lowest_ratio = hmp_domain_min_load(hmp_slower_domain(cpu), &lowest_cpu);
+       /*
+        * If the lowest-loaded CPU in the domain is allowed by the task affinity
+        * select that one, otherwise select one which is allowed
+        */
+       if(lowest_cpu != NR_CPUS && cpumask_test_cpu(lowest_cpu,tsk_cpus_allowed(tsk)))
+               return lowest_cpu;
+       else
+               return cpumask_any_and(&hmp_slower_domain(cpu)->cpus,
                                tsk_cpus_allowed(tsk));
 }