From: Chen Yu <yu.c.chen@intel.com>
Date: Sat, 5 May 2018 19:53:22 +0800
Subject: ACPI: acpi_pad: Do not launch acpi_pad threads on idle cpus
Patch-mainline: never, mainline wants to replace acpi_pad with the idle-inject framework
References: bsc#1113399

According to current implementation of acpi_pad driver,
it does not make sense to spawn any power saving threads
on the cpus which are already idle - it might bring
unnecessary overhead on these idle cpus and causes power
waste. So verify the condition that if the number of 'busy'
cpus exceeds the amount of the 'forced idle' cpus is met.
This is applicable due to round-robin attribute of the
power saving threads, otherwise ignore the setting/ACPI
notification.

Suggested-by: Lenny Szubowicz <lszubowi@redhat.com>
Suggested-by: Len Brown <lenb@kernel.org>
Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
Cc: Lenny Szubowicz <lszubowi@redhat.com>
Cc: Len Brown <lenb@kernel.org>
Cc: Jacob Pan <jacob.jun.pan@linux.intel.com>
Cc: Rui Zhang <rui.zhang@intel.com>
Cc: linux-acpi@vger.kernel.org
Signed-off-by: Chen Yu <yu.c.chen@intel.com>
Acked-by: Giovanni Gherdovich <ggherdovich@suse.cz>
---
 drivers/acpi/acpi_pad.c |   54 +++++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 53 insertions(+), 1 deletion(-)

--- a/drivers/acpi/acpi_pad.c
+++ b/drivers/acpi/acpi_pad.c
@@ -26,6 +26,8 @@
 #include <linux/tick.h>
 #include <linux/slab.h>
 #include <linux/acpi.h>
+#include <linux/kernel_stat.h>
+#include <linux/jiffies.h>
 #include <asm/mwait.h>
 #include <xen/xen.h>
 
@@ -254,12 +256,62 @@ static void set_power_saving_task_num(un
 	}
 }
 
+/*
+ * Extra acpi_pad threads should not be created until
+ * the requested idle count is less than/equals to the
+ * number of the busy cpus - it does not make sense to
+ * throttle the idle cpus.
+ */
+#define SAMPLE_INTERVAL_JIF	20
+
+static u64 get_idle_time(int cpu)
+{
+	u64 idle, idle_usecs = -1ULL;
+
+	idle_usecs = get_cpu_idle_time_us(cpu, NULL);
+
+	if (idle_usecs == -1ULL)
+		idle = kcpustat_cpu(cpu).cpustat[CPUTIME_IDLE];
+	else
+		idle = idle_usecs * NSEC_PER_USEC;
+
+	return idle;
+}
+
+static bool idle_nr_valid(unsigned int num_cpus)
+{
+	int busy_nr = 0, i = 0, load_thresh = 100 - idle_pct;
+
+	if (!num_cpus)
+		return true;
+
+	for_each_online_cpu(i) {
+		u64 wall_time, idle_time;
+		unsigned int elapsed_delta, idle_delta, load;
+
+		wall_time = jiffies64_to_nsecs(get_jiffies_64());
+		idle_time = get_idle_time(i);
+		/* Wait and see... */
+		schedule_timeout_uninterruptible(SAMPLE_INTERVAL_JIF);
+
+		idle_delta = get_idle_time(i) - idle_time;
+		elapsed_delta = jiffies64_to_nsecs(get_jiffies_64()) - wall_time;
+		idle_delta = (idle_delta > elapsed_delta) ? elapsed_delta : idle_delta;
+		load = 100 * (elapsed_delta - idle_delta) / elapsed_delta;
+		if (load >= load_thresh)
+			busy_nr++;
+	}
+
+	return (busy_nr >= num_cpus) ? true : false;
+}
+
 static void acpi_pad_idle_cpus(unsigned int num_cpus)
 {
 	get_online_cpus();
 
 	num_cpus = min_t(unsigned int, num_cpus, num_online_cpus());
-	set_power_saving_task_num(num_cpus);
+	if (idle_nr_valid(num_cpus))
+		set_power_saving_task_num(num_cpus);
 
 	put_online_cpus();
 }