sched: Clean up domain traversal in select_idle_sibling()

Instead of going through the scheduler domain hierarchy multiple times
(for giving priority to an idle core over an idle SMT sibling in a busy
core), start with the highest scheduler domain with the SD_SHARE_PKG_RESOURCES
flag and traverse the domain hierarchy down till we find an idle group.

This cleanup also addresses an issue reported by Mike where the recent
changes returned the busy thread even in the presence of an idle SMT
sibling in single socket platforms.

Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>
Tested-by: Mike Galbraith <efault@gmx.de>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1321556904.15339.25.camel@sbsiddha-desk.sc.intel.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>

2 files changed, 27 insertions, 13 deletions

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 7c62e2bf234f..96a9ecec699b 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2644,6 +2644,28 @@ find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu)
         return idlest;
 }
 
+/**
+ * highest_flag_domain - Return highest sched_domain containing flag.
+ * @cpu:        The cpu whose highest level of sched domain is to
+ *              be returned.
+ * @flag:       The flag to check for the highest sched_domain
+ *              for the given cpu.
+ *
+ * Returns the highest sched_domain of a cpu which contains the given flag.
+ */
+static inline struct sched_domain *highest_flag_domain(int cpu, int flag)
+{
+        struct sched_domain *sd, *hsd = NULL;
+
+        for_each_domain(cpu, sd) {
+                if (!(sd->flags & flag))
+                        break;
+                hsd = sd;
+        }
+
+        return hsd;
+}
+
 /*
  * Try and locate an idle CPU in the sched_domain.
  */
@@ -2653,7 +2675,7 @@ static int select_idle_sibling(struct task_struct *p, int target)
         int prev_cpu = task_cpu(p);
         struct sched_domain *sd;
         struct sched_group *sg;
-        int i, smt = 0;
+        int i;
 
         /*
          * If the task is going to be woken-up on this cpu and if it is
@@ -2673,19 +2695,9 @@ static int select_idle_sibling(struct task_struct *p, int target)
          * Otherwise, iterate the domains and find an elegible idle cpu.
          */
         rcu_read_lock();
-again:
-        for_each_domain(target, sd) {
-                if (!smt && (sd->flags & SD_SHARE_CPUPOWER))
-                        continue;
-
-                if (!(sd->flags & SD_SHARE_PKG_RESOURCES)) {
-                        if (!smt) {
-                                smt = 1;
-                                goto again;
-                        }
-                        break;
-                }
 
+        sd = highest_flag_domain(target, SD_SHARE_PKG_RESOURCES);
+        for_each_lower_domain(sd) {
                 sg = sd->groups;
                 do {
                         if (!cpumask_intersects(sched_group_cpus(sg),
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index c2e780234c31..8715055979d1 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -501,6 +501,8 @@ DECLARE_PER_CPU(struct rq, runqueues);
 #define for_each_domain(cpu, __sd) \
         for (__sd = rcu_dereference_check_sched_domain(cpu_rq(cpu)->sd); __sd; __sd = __sd->parent)
 
+#define for_each_lower_domain(sd) for (; sd; sd = sd->child)
+
 #define cpu_rq(cpu)             (&per_cpu(runqueues, (cpu)))
 #define this_rq()               (&__get_cpu_var(runqueues))
 #define task_rq(p)              cpu_rq(task_cpu(p))