[PATCH 4.9 62/72] sched/fair, cpumask: Export for_each_cpu_wrap()

From: Greg Kroah-Hartman
Date: Wed Jul 19 2017 - 06:27:56 EST


4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Peter Zijlstra <peterz@xxxxxxxxxxxxx>

commit c6508a39640b9a27fc2bc10cb708152672c82045 upstream.

commit c743f0a5c50f2fcbc628526279cfa24f3dabe182 upstream.

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@xxxxxxxxxxxxx>
Cc: Lauro Ramos Venancio <lvenanci@xxxxxxxxxx>
Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Cc: Mike Galbraith <efault@xxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Rik van Riel <riel@xxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: lwang@xxxxxxxxxx
Link: http://lkml.kernel.org/r/20170414122005.o35me2h5nowqkxbv@xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
Signed-off-by: Mel Gorman <mgorman@xxxxxxxxxxxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>

---
include/linux/cpumask.h | 17 +++++++++++++++++
kernel/sched/fair.c | 45 ++++-----------------------------------------
lib/cpumask.c | 32 ++++++++++++++++++++++++++++++++
3 files changed, 53 insertions(+), 41 deletions(-)

--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -236,6 +236,23 @@ unsigned int cpumask_local_spread(unsign
(cpu) = cpumask_next_zero((cpu), (mask)), \
(cpu) < nr_cpu_ids;)

+extern int cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool wrap);
+
+/**
+ * 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
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -5310,43 +5310,6 @@ find_idlest_cpu(struct sched_group *grou
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)
@@ -5406,14 +5369,14 @@ unlock:
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 (!test_idle_cores(target, false))
return -1;

cpumask_and(cpus, sched_domain_span(sd), tsk_cpus_allowed(p));

- 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)) {
@@ -5476,7 +5439,7 @@ static int select_idle_cpu(struct task_s
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)
@@ -5493,7 +5456,7 @@ static int select_idle_cpu(struct task_s

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, tsk_cpus_allowed(p)))
continue;
if (idle_cpu(cpu))
--- a/lib/cpumask.c
+++ b/lib/cpumask.c
@@ -43,6 +43,38 @@ int cpumask_any_but(const struct cpumask
}
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
/**