sched: Fully integrate cpus_active_map and root-domain code

Reflect "active" cpus in the rq->rd->online field, instead of
the online_map.

The motivation is that things that use the root-domain code
(such as cpupri) only care about cpus classified as "active"
anyway. By synchronizing the root-domain state with the active
map, we allow several optimizations.

For instance, we can remove an extra cpumask_and from the
scheduler hotpath by utilizing rq->rd->online (since it is now
a cached version of cpu_active_map & rq->rd->span).

Signed-off-by: Gregory Haskins <ghaskins@novell.com>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Acked-by: Max Krasnyansky <maxk@qualcomm.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <20090730145723.25226.24493.stgit@dev.haskins.net>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

3 files changed, 8 insertions, 11 deletions

diff --git a/kernel/sched.c b/kernel/sched.c
index 613fee54fc89..475138c42548 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -7927,7 +7927,7 @@ static void rq_attach_root(struct rq *rq, struct root_domain *rd)
         rq->rd = rd;
 
         cpumask_set_cpu(rq->cpu, rd->span);
-        if (cpumask_test_cpu(rq->cpu, cpu_online_mask))
+        if (cpumask_test_cpu(rq->cpu, cpu_active_mask))
                 set_rq_online(rq);
 
         spin_unlock_irqrestore(&rq->lock, flags);
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 652e8bdef9aa..493472984879 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -1046,17 +1046,21 @@ static void yield_task_fair(struct rq *rq)
  * search starts with cpus closest then further out as needed,
  * so we always favor a closer, idle cpu.
  * Domains may include CPUs that are not usable for migration,
- * hence we need to mask them out (cpu_active_mask)
+ * hence we need to mask them out (rq->rd->online)
  *
  * Returns the CPU we should wake onto.
  */
 #if defined(ARCH_HAS_SCHED_WAKE_IDLE)
+
+#define cpu_rd_active(cpu, rq) cpumask_test_cpu(cpu, rq->rd->online)
+
 static int wake_idle(int cpu, struct task_struct *p)
 {
         struct sched_domain *sd;
         int i;
         unsigned int chosen_wakeup_cpu;
         int this_cpu;
+        struct rq *task_rq = task_rq(p);
 
         /*
          * At POWERSAVINGS_BALANCE_WAKEUP level, if both this_cpu and prev_cpu
@@ -1089,10 +1093,10 @@ static int wake_idle(int cpu, struct task_struct *p)
         for_each_domain(cpu, sd) {
                 if ((sd->flags & SD_WAKE_IDLE)
                     || ((sd->flags & SD_WAKE_IDLE_FAR)
-                        && !task_hot(p, task_rq(p)->clock, sd))) {
+                        && !task_hot(p, task_rq->clock, sd))) {
                         for_each_cpu_and(i, sched_domain_span(sd),
                                          &p->cpus_allowed) {
-                                if (cpu_active(i) && idle_cpu(i)) {
+                                if (cpu_rd_active(i, task_rq) && idle_cpu(i)) {
                                         if (i != task_cpu(p)) {
                                                 schedstat_inc(p,
                                                        se.nr_wakeups_idle);
diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index a8f89bc3e5eb..13f728ef5b38 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -1173,13 +1173,6 @@ static int find_lowest_rq(struct task_struct *task)
                 return -1; /* No targets found */
 
         /*
-         * Only consider CPUs that are usable for migration.
-         * I guess we might want to change cpupri_find() to ignore those
-         * in the first place.
-         */
-        cpumask_and(lowest_mask, lowest_mask, cpu_active_mask);
-
-        /*
          * At this point we have built a mask of cpus representing the
          * lowest priority tasks in the system.  Now we want to elect
          * the best one based on our affinity and topology.