powercap: add suspend and resume mechanism for SOC power limit

PL1 and PL2 could be throlled or de-throttled by
Thermal management to control SOC temperature.

However, currently, their value will be reset to default value
after once system suspend and resume.

Add pm_notifier to save PL1, PL2 before system suspect and restore
PL1, PL2 after system resume.

Signed-off-by: Zhen Han <zhen.han@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>

drivers/powercap/intel_rapl.c

@@ -29,6 +29,7 @@
 #include <linux/sysfs.h>
 #include <linux/cpu.h>
 #include <linux/powercap.h>
+#include <linux/suspend.h>
 #include <asm/iosf_mbi.h>
 
 #include <asm/processor.h>
@@ -155,6 +156,7 @@ struct rapl_power_limit {
 	int prim_id; /* primitive ID used to enable */
 	struct rapl_domain *domain;
 	const char *name;
+	u64 last_power_limit;
 };
 
 static const char pl1_name[] = "long_term";
@@ -1533,6 +1535,92 @@ static int rapl_cpu_down_prep(unsigned int cpu)
 
 static enum cpuhp_state pcap_rapl_online;
 
+static void power_limit_state_save(void)
+{
+	struct rapl_package *rp;
+	struct rapl_domain *rd;
+	int nr_pl, ret, i;
+
+	get_online_cpus();
+	list_for_each_entry(rp, &rapl_packages, plist) {
+		if (!rp->power_zone)
+			continue;
+		rd = power_zone_to_rapl_domain(rp->power_zone);
+		nr_pl = find_nr_power_limit(rd);
+		for (i = 0; i < nr_pl; i++) {
+			switch (rd->rpl[i].prim_id) {
+			case PL1_ENABLE:
+				ret = rapl_read_data_raw(rd,
+						POWER_LIMIT1,
+						true,
+						&rd->rpl[i].last_power_limit);
+				if (ret)
+					rd->rpl[i].last_power_limit = 0;
+				break;
+			case PL2_ENABLE:
+				ret = rapl_read_data_raw(rd,
+						POWER_LIMIT2,
+						true,
+						&rd->rpl[i].last_power_limit);
+				if (ret)
+					rd->rpl[i].last_power_limit = 0;
+				break;
+			}
+		}
+	}
+	put_online_cpus();
+}
+
+static void power_limit_state_restore(void)
+{
+	struct rapl_package *rp;
+	struct rapl_domain *rd;
+	int nr_pl, i;
+
+	get_online_cpus();
+	list_for_each_entry(rp, &rapl_packages, plist) {
+		if (!rp->power_zone)
+			continue;
+		rd = power_zone_to_rapl_domain(rp->power_zone);
+		nr_pl = find_nr_power_limit(rd);
+		for (i = 0; i < nr_pl; i++) {
+			switch (rd->rpl[i].prim_id) {
+			case PL1_ENABLE:
+				if (rd->rpl[i].last_power_limit)
+					rapl_write_data_raw(rd,
+						POWER_LIMIT1,
+						rd->rpl[i].last_power_limit);
+				break;
+			case PL2_ENABLE:
+				if (rd->rpl[i].last_power_limit)
+					rapl_write_data_raw(rd,
+						POWER_LIMIT2,
+						rd->rpl[i].last_power_limit);
+				break;
+			}
+		}
+	}
+	put_online_cpus();
+}
+
+static int rapl_pm_callback(struct notifier_block *nb,
+	unsigned long mode, void *_unused)
+{
+	switch (mode) {
+	case PM_SUSPEND_PREPARE:
+		power_limit_state_save();
+		break;
+	case PM_POST_SUSPEND:
+		power_limit_state_restore();
+		break;
+	}
+	return NOTIFY_OK;
+}
+
+static struct notifier_block rapl_pm_notifier = {
+	.notifier_call = rapl_pm_callback,
+};
+
 static int __init rapl_init(void)
 {
 	const struct x86_cpu_id *id;
@@ -1560,8 +1648,16 @@ static int __init rapl_init(void)
 
 	/* Don't bail out if PSys is not supported */
 	rapl_register_psys();
+
+	ret = register_pm_notifier(&rapl_pm_notifier);
+	if (ret)
+		goto err_unreg_all;
+
 	return 0;
 
+err_unreg_all:
+	cpuhp_remove_state(pcap_rapl_online);
+
 err_unreg:
 	rapl_unregister_powercap();
 	return ret;
@@ -1569,6 +1665,7 @@ err_unreg:
 
 static void __exit rapl_exit(void)
 {
+	unregister_pm_notifier(&rapl_pm_notifier);
 	cpuhp_remove_state(pcap_rapl_online);
 	rapl_unregister_powercap();
 }