[PATCH v3 12/19] sched,rt: Use cpumask_any*_distribute()

[Peter Zijlstra]

Replace a bunch of cpumask_any*() instances with
cpumask_any*_distribute(), by injecting this little bit of random in
cpu selection, we reduce the chance two competing balance operations
working off the same lowest_mask pick the same CPU.

Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
---
 include/linux/cpumask.h |    6 ++++++
 kernel/sched/deadline.c |    6 +++---
 kernel/sched/rt.c       |    6 +++---
 lib/cpumask.c           |   18 ++++++++++++++++++
 4 files changed, 30 insertions(+), 6 deletions(-)

--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -199,6 +199,11 @@ static inline int cpumask_any_and_distri
 	return cpumask_next_and(-1, src1p, src2p);
 }
 
+static inline int cpumask_any_distribute(const struct cpumask *srcp)
+{
+	return cpumask_first(srcp);
+}
+
 #define for_each_cpu(cpu, mask)			\
 	for ((cpu) = 0; (cpu) < 1; (cpu)++, (void)mask)
 #define for_each_cpu_not(cpu, mask)		\
@@ -252,6 +257,7 @@ int cpumask_any_but(const struct cpumask
 unsigned int cpumask_local_spread(unsigned int i, int node);
 int cpumask_any_and_distribute(const struct cpumask *src1p,
 			       const struct cpumask *src2p);
+int cpumask_any_distribute(const struct cpumask *srcp);
 
 /**
  * for_each_cpu - iterate over every cpu in a mask
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1981,8 +1981,8 @@ static int find_later_rq(struct task_str
 				return this_cpu;
 			}
 
-			best_cpu = cpumask_first_and(later_mask,
-							sched_domain_span(sd));
+			best_cpu = cpumask_any_and_distribute(later_mask,
+							      sched_domain_span(sd));
 			/*
 			 * Last chance: if a CPU being in both later_mask
 			 * and current sd span is valid, that becomes our
@@ -2004,7 +2004,7 @@ static int find_later_rq(struct task_str
 	if (this_cpu != -1)
 		return this_cpu;
 
-	cpu = cpumask_any(later_mask);
+	cpu = cpumask_any_distribute(later_mask);
 	if (cpu < nr_cpu_ids)
 		return cpu;
 
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -1752,8 +1752,8 @@ static int find_lowest_rq(struct task_st
 				return this_cpu;
 			}
 
-			best_cpu = cpumask_first_and(lowest_mask,
-						     sched_domain_span(sd));
+			best_cpu = cpumask_any_and_distribute(lowest_mask,
+							      sched_domain_span(sd));
 			if (best_cpu < nr_cpu_ids) {
 				rcu_read_unlock();
 				return best_cpu;
@@ -1770,7 +1770,7 @@ static int find_lowest_rq(struct task_st
 	if (this_cpu != -1)
 		return this_cpu;
 
-	cpu = cpumask_any(lowest_mask);
+	cpu = cpumask_any_distribute(lowest_mask);
 	if (cpu < nr_cpu_ids)
 		return cpu;
 
--- a/lib/cpumask.c
+++ b/lib/cpumask.c
@@ -267,3 +267,21 @@ int cpumask_any_and_distribute(const str
 	return next;
 }
 EXPORT_SYMBOL(cpumask_any_and_distribute);
+
+int cpumask_any_distribute(const struct cpumask *srcp)
+{
+	int next, prev;
+
+	/* NOTE: our first selection will skip 0. */
+	prev = __this_cpu_read(distribute_cpu_mask_prev);
+
+	next = cpumask_next(prev, srcp);
+	if (next >= nr_cpu_ids)
+		next = cpumask_first(srcp);
+
+	if (next < nr_cpu_ids)
+		__this_cpu_write(distribute_cpu_mask_prev, next);
+
+	return next;
+}
+EXPORT_SYMBOL(cpumask_any_distribute);