Merge branch 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (35 commits)
  sched, cputime: Introduce thread_group_times()
  sched, cputime: Cleanups related to task_times()
  Revert "sched, x86: Optimize branch hint in __switch_to()"
  sched: Fix isolcpus boot option
  sched: Revert 498657a478c60be092208422fefa9c7b248729c2
  sched, time: Define nsecs_to_jiffies()
  sched: Remove task_{u,s,g}time()
  sched: Introduce task_times() to replace task_{u,s}time() pair
  sched: Limit the number of scheduler debug messages
  sched.c: Call debug_show_all_locks() when dumping all tasks
  sched, x86: Optimize branch hint in __switch_to()
  sched: Optimize branch hint in context_switch()
  sched: Optimize branch hint in pick_next_task_fair()
  sched_feat_write(): Update ppos instead of file->f_pos
  sched: Sched_rt_periodic_timer vs cpu hotplug
  sched, kvm: Fix race condition involving sched_in_preempt_notifers
  sched: More generic WAKE_AFFINE vs select_idle_sibling()
  sched: Cleanup select_task_rq_fair()
  sched: Fix granularity of task_u/stime()
  sched: Fix/add missing update_rq_clock() calls
  ...

1 files changed, 60 insertions, 5 deletions

diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 37087a7..f61837a 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -1345,6 +1345,37 @@ find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu)
 }
 
 /*
+ * Try and locate an idle CPU in the sched_domain.
+ */
+static int
+select_idle_sibling(struct task_struct *p, struct sched_domain *sd, int target)
+{
+	int cpu = smp_processor_id();
+	int prev_cpu = task_cpu(p);
+	int i;
+
+	/*
+	 * If this domain spans both cpu and prev_cpu (see the SD_WAKE_AFFINE
+	 * test in select_task_rq_fair) and the prev_cpu is idle then that's
+	 * always a better target than the current cpu.
+	 */
+	if (target == cpu && !cpu_rq(prev_cpu)->cfs.nr_running)
+		return prev_cpu;
+
+	/*
+	 * Otherwise, iterate the domain and find an elegible idle cpu.
+	 */
+	for_each_cpu_and(i, sched_domain_span(sd), &p->cpus_allowed) {
+		if (!cpu_rq(i)->cfs.nr_running) {
+			target = i;
+			break;
+		}
+	}
+
+	return target;
+}
+
+/*
  * sched_balance_self: balance the current task (running on cpu) in domains
  * that have the 'flag' flag set. In practice, this is SD_BALANCE_FORK and
  * SD_BALANCE_EXEC.
@@ -1398,11 +1429,35 @@ static int select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flag
 				want_sd = 0;
 		}
 
-		if (want_affine && (tmp->flags & SD_WAKE_AFFINE) &&
-		    cpumask_test_cpu(prev_cpu, sched_domain_span(tmp))) {
+		/*
+		 * While iterating the domains looking for a spanning
+		 * WAKE_AFFINE domain, adjust the affine target to any idle cpu
+		 * in cache sharing domains along the way.
+		 */
+		if (want_affine) {
+			int target = -1;
 
-			affine_sd = tmp;
-			want_affine = 0;
+			/*
+			 * If both cpu and prev_cpu are part of this domain,
+			 * cpu is a valid SD_WAKE_AFFINE target.
+			 */
+			if (cpumask_test_cpu(prev_cpu, sched_domain_span(tmp)))
+				target = cpu;
+
+			/*
+			 * If there's an idle sibling in this domain, make that
+			 * the wake_affine target instead of the current cpu.
+			 */
+			if (tmp->flags & SD_PREFER_SIBLING)
+				target = select_idle_sibling(p, tmp, target);
+
+			if (target >= 0) {
+				if (tmp->flags & SD_WAKE_AFFINE) {
+					affine_sd = tmp;
+					want_affine = 0;
+				}
+				cpu = target;
+			}
 		}
 
 		if (!want_sd && !want_affine)
@@ -1679,7 +1734,7 @@ static struct task_struct *pick_next_task_fair(struct rq *rq)
 	struct cfs_rq *cfs_rq = &rq->cfs;
 	struct sched_entity *se;
 
-	if (unlikely(!cfs_rq->nr_running))
+	if (!cfs_rq->nr_running)
 		return NULL;
 
 	do {