Re: [RFC 2/3] sched/topology: fix sched groups on NUMA machines with mesh topology

[Peter Zijlstra <peterz@infradead.org>]

On Fri, Apr 14, 2017 at 01:38:13PM +0200, Peter Zijlstra wrote:

> An equivalent patch would be (if for_each_cpu_wrap() were exposed):

---
Subject: sched,cpumask: Export for_each_cpu_wrap()

More users for for_each_cpu_wrap() have appeared. Promote the construct
to generic cpumask interface.

The implementation is slightly modified to reduce arguments.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
 include/linux/cpumask.h | 16 ++++++++++++++++
 kernel/sched/fair.c     | 45 ++++-----------------------------------------
 lib/cpumask.c           | 32 ++++++++++++++++++++++++++++++++
 3 files changed, 52 insertions(+), 41 deletions(-)

diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index 96f1e88..4b87b7b 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -236,6 +236,22 @@ unsigned int cpumask_local_spread(unsigned int i, int node);
 		(cpu) = cpumask_next_zero((cpu), (mask)),	\
 		(cpu) < nr_cpu_ids;)
 
+
+/**
+ * for_each_cpu_wrap - iterate over every cpu in a mask, starting at a specified location
+ * @cpu: the (optionally unsigned) integer iterator
+ * @mask: the cpumask poiter
+ * @start: the start location
+ *
+ * The implementation does not assume any bit in @mask is set (including @start).
+ *
+ * After the loop, cpu is >= nr_cpu_ids.
+ */
+#define for_each_cpu_wrap(cpu, mask, start)					\
+	for ((cpu) = cpumask_next_wrap((start)-1, (mask), (start), false);	\
+	     (cpu) < nr_cpumask_bits;						\
+	     (cpu) = cpumask_next_wrap((cpu), (mask), (start), true))
+
 /**
  * for_each_cpu_and - iterate over every cpu in both masks
  * @cpu: the (optionally unsigned) integer iterator
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index a903276..d89d700 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -5640,43 +5640,6 @@ find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu)
 	return shallowest_idle_cpu != -1 ? shallowest_idle_cpu : least_loaded_cpu;
 }
 
-/*
- * Implement a for_each_cpu() variant that starts the scan at a given cpu
- * (@start), and wraps around.
- *
- * This is used to scan for idle CPUs; such that not all CPUs looking for an
- * idle CPU find the same CPU. The down-side is that tasks tend to cycle
- * through the LLC domain.
- *
- * Especially tbench is found sensitive to this.
- */
-
-static int cpumask_next_wrap(int n, const struct cpumask *mask, int start, int *wrapped)
-{
-	int next;
-
-again:
-	next = find_next_bit(cpumask_bits(mask), nr_cpumask_bits, n+1);
-
-	if (*wrapped) {
-		if (next >= start)
-			return nr_cpumask_bits;
-	} else {
-		if (next >= nr_cpumask_bits) {
-			*wrapped = 1;
-			n = -1;
-			goto again;
-		}
-	}
-
-	return next;
-}
-
-#define for_each_cpu_wrap(cpu, mask, start, wrap)				\
-	for ((wrap) = 0, (cpu) = (start)-1;					\
-		(cpu) = cpumask_next_wrap((cpu), (mask), (start), &(wrap)),	\
-		(cpu) < nr_cpumask_bits; )
-
 #ifdef CONFIG_SCHED_SMT
 
 static inline void set_idle_cores(int cpu, int val)
@@ -5736,7 +5699,7 @@ void __update_idle_core(struct rq *rq)
 static int select_idle_core(struct task_struct *p, struct sched_domain *sd, int target)
 {
 	struct cpumask *cpus = this_cpu_cpumask_var_ptr(select_idle_mask);
-	int core, cpu, wrap;
+	int core, cpu;
 
 	if (!static_branch_likely(&sched_smt_present))
 		return -1;
@@ -5746,7 +5709,7 @@ static int select_idle_core(struct task_struct *p, struct sched_domain *sd, int
 
 	cpumask_and(cpus, sched_domain_span(sd), &p->cpus_allowed);
 
-	for_each_cpu_wrap(core, cpus, target, wrap) {
+	for_each_cpu_wrap(core, cpus, target) {
 		bool idle = true;
 
 		for_each_cpu(cpu, cpu_smt_mask(core)) {
@@ -5812,7 +5775,7 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int t
 	u64 avg_cost, avg_idle = this_rq()->avg_idle;
 	u64 time, cost;
 	s64 delta;
-	int cpu, wrap;
+	int cpu;
 
 	this_sd = rcu_dereference(*this_cpu_ptr(&sd_llc));
 	if (!this_sd)
@@ -5829,7 +5792,7 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int t
 
 	time = local_clock();
 
-	for_each_cpu_wrap(cpu, sched_domain_span(sd), target, wrap) {
+	for_each_cpu_wrap(cpu, sched_domain_span(sd), target) {
 		if (!cpumask_test_cpu(cpu, &p->cpus_allowed))
 			continue;
 		if (idle_cpu(cpu))
diff --git a/lib/cpumask.c b/lib/cpumask.c
index 81dedaa..4731a08 100644
--- a/lib/cpumask.c
+++ b/lib/cpumask.c
@@ -43,6 +43,38 @@ int cpumask_any_but(const struct cpumask *mask, unsigned int cpu)
 }
 EXPORT_SYMBOL(cpumask_any_but);
 
+/**
+ * cpumask_next_wrap - helper to implement for_each_cpu_wrap
+ * @n: the cpu prior to the place to search
+ * @mask: the cpumask pointer
+ * @start: the start point of the iteration
+ * @wrap: assume @n crossing @start terminates the iteration
+ *
+ * Returns >= nr_cpu_ids on completion
+ *
+ * Note: the @wrap argument is required for the start condition when
+ * we cannot assume @start is set in @mask.
+ */
+int cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool wrap)
+{
+	int next;
+
+again:
+	next = cpumask_next(n, mask);
+
+	if (wrap && n < start && next >= start) {
+		return nr_cpumask_bits;
+
+	} else if (next >= nr_cpumask_bits) {
+		wrap = true;
+		n = -1;
+		goto again;
+	}
+
+	return next;
+}
+EXPORT_SYMBOL(cpumask_next_wrap);
+
 /* These are not inline because of header tangles. */
 #ifdef CONFIG_CPUMASK_OFFSTACK
 /**