From 8776980b5d0c6021839ffd1bfe9b93aee578e92b Mon Sep 17 00:00:00 2001
From: Yuan ZhaoXiong <yuanzhaoxiong@baidu.com>
Date: Sun, 6 Jun 2021 21:11:55 +0800
Subject: [PATCH] sched: Optimize housekeeping_cpumask() in for_each_cpu_and()

Patch-mainline: v5.15-rc1
References: bsc#1189999 (Scheduler functional and performance backports)
Git-commit: 031e3bd8986fffe31e1ddbf5264cccfe30c9abd7

On a 128 cores AMD machine, there are 8 cores in nohz_full mode, and
the others are used for housekeeping. When many housekeeping cpus are
in idle state, we can observe huge time burn in the loop for searching
nearest busy housekeeper cpu by ftrace.

   9)               |              get_nohz_timer_target() {
   9)               |                housekeeping_test_cpu() {
   9)   0.390 us    |                  housekeeping_get_mask.part.1();
   9)   0.561 us    |                }
   9)   0.090 us    |                __rcu_read_lock();
   9)   0.090 us    |                housekeeping_cpumask();
   9)   0.521 us    |                housekeeping_cpumask();
   9)   0.140 us    |                housekeeping_cpumask();

   ...

   9)   0.500 us    |                housekeeping_cpumask();
   9)               |                housekeeping_any_cpu() {
   9)   0.090 us    |                  housekeeping_get_mask.part.1();
   9)   0.100 us    |                  sched_numa_find_closest();
   9)   0.491 us    |                }
   9)   0.100 us    |                __rcu_read_unlock();
   9) + 76.163 us   |              }

for_each_cpu_and() is a micro function, so in get_nohz_timer_target()
function the
        for_each_cpu_and(i, sched_domain_span(sd),
                housekeeping_cpumask(HK_FLAG_TIMER))
equals to below:
        for (i = -1; i = cpumask_next_and(i, sched_domain_span(sd),
                housekeeping_cpumask(HK_FLAG_TIMER)), i < nr_cpu_ids;)
That will cause that housekeeping_cpumask() will be invoked many times.
The housekeeping_cpumask() function returns a const value, so it is
unnecessary to invoke it every time. This patch can minimize the worst
searching time from ~76us to ~16us in my testing.

Similarly, the find_new_ilb() function has the same problem.

Co-developed-by: Li RongQing <lirongqing@baidu.com>
Signed-off-by: Li RongQing <lirongqing@baidu.com>
Signed-off-by: Yuan ZhaoXiong <yuanzhaoxiong@baidu.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/1622985115-51007-1-git-send-email-yuanzhaoxiong@baidu.com
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 kernel/sched/core.c | 6 ++++--
 kernel/sched/fair.c | 6 ++++--
 2 files changed, 8 insertions(+), 4 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index d5dc6d4a604e..61bad0835148 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1007,6 +1007,7 @@ int get_nohz_timer_target(void)
 {
 	int i, cpu = smp_processor_id(), default_cpu = -1;
 	struct sched_domain *sd;
+	const struct cpumask *hk_mask;
 
 	if (housekeeping_cpu(cpu, HK_FLAG_TIMER)) {
 		if (!idle_cpu(cpu))
@@ -1014,10 +1015,11 @@ int get_nohz_timer_target(void)
 		default_cpu = cpu;
 	}
 
+	hk_mask = housekeeping_cpumask(HK_FLAG_TIMER);
+
 	rcu_read_lock();
 	for_each_domain(cpu, sd) {
-		for_each_cpu_and(i, sched_domain_span(sd),
-			housekeeping_cpumask(HK_FLAG_TIMER)) {
+		for_each_cpu_and(i, sched_domain_span(sd), hk_mask) {
 			if (cpu == i)
 				continue;
 
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 0ca9a2097607..3e1158574dc6 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -10219,9 +10219,11 @@ static inline int on_null_domain(struct rq *rq)
 static inline int find_new_ilb(void)
 {
 	int ilb;
+	const struct cpumask *hk_mask;
 
-	for_each_cpu_and(ilb, nohz.idle_cpus_mask,
-			      housekeeping_cpumask(HK_FLAG_MISC)) {
+	hk_mask = housekeeping_cpumask(HK_FLAG_MISC);
+
+	for_each_cpu_and(ilb, nohz.idle_cpus_mask, hk_mask) {
 
 		if (ilb == smp_processor_id())
 			continue;