pmdomain: governor: Consider CPU latency tolerance from pm_domain_cpu_gov

commit 500ba33284416255b9a5b50ace24470b6fe77ea5 upstream.

pm_domain_cpu_gov is selecting a cluster idle state but does not consider
latency tolerance of child CPUs. This results in deeper cluster idle state
whose latency does not meet latency tolerance requirement.

Select deeper idle state only if global and device latency tolerance of all
child CPUs meet.

Test results on SM8750 with 300 usec PM-QoS on CPU0 which is less than
domain idle state entry (2150) + exit (1983) usec latency mentioned in
devicetree, demonstrate the issue.

	# echo 300 > /sys/devices/system/cpu/cpu0/power/pm_qos_resume_latency_us

Before: (Usage is incrementing)
======
	# cat /sys/kernel/debug/pm_genpd/power-domain-cluster0/idle_states
	State          Time Spent(ms) Usage      Rejected   Above      Below
	S0             29817          537        8          270        0

	# cat /sys/kernel/debug/pm_genpd/power-domain-cluster0/idle_states
	State          Time Spent(ms) Usage      Rejected   Above      Below
	S0             30348          542        8          271        0

After: (Usage is not incrementing due to latency tolerance)
======
	# cat /sys/kernel/debug/pm_genpd/power-domain-cluster0/idle_states
	State          Time Spent(ms) Usage      Rejected   Above      Below
	S0             39319          626        14         307        0

	# cat /sys/kernel/debug/pm_genpd/power-domain-cluster0/idle_states
	State          Time Spent(ms) Usage      Rejected   Above      Below
	S0             39319          626        14         307        0

Signed-off-by: Maulik Shah <maulik.shah@oss.qualcomm.com>
Fixes: e94999688e ("PM / Domains: Add genpd governor for CPUs")
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20250709-pmdomain_qos-v2-1-976b12257899@oss.qualcomm.com
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

drivers/base/power/domain_governor.c

@@ -8,6 +8,7 @@
 #include <linux/pm_domain.h>
 #include <linux/pm_qos.h>
 #include <linux/hrtimer.h>
+#include <linux/cpu.h>
 #include <linux/cpuidle.h>
 #include <linux/cpumask.h>
 #include <linux/ktime.h>
@@ -345,6 +346,8 @@ static bool cpu_power_down_ok(struct dev_pm_domain *pd)
 	struct cpuidle_device *dev;
 	ktime_t domain_wakeup, next_hrtimer;
 	ktime_t now = ktime_get();
+	struct device *cpu_dev;
+	s64 cpu_constraint, global_constraint;
 	s64 idle_duration_ns;
 	int cpu, i;
 
@@ -355,6 +358,7 @@ static bool cpu_power_down_ok(struct dev_pm_domain *pd)
 	if (!(genpd->flags & GENPD_FLAG_CPU_DOMAIN))
 		return true;
 
+	global_constraint = cpu_latency_qos_limit();
 	/*
 	 * Find the next wakeup for any of the online CPUs within the PM domain
 	 * and its subdomains. Note, we only need the genpd->cpus, as it already
@@ -368,8 +372,16 @@ static bool cpu_power_down_ok(struct dev_pm_domain *pd)
 			if (ktime_before(next_hrtimer, domain_wakeup))
 				domain_wakeup = next_hrtimer;
 		}
+
+		cpu_dev = get_cpu_device(cpu);
+		if (cpu_dev) {
+			cpu_constraint = dev_pm_qos_raw_resume_latency(cpu_dev);
+			if (cpu_constraint < global_constraint)
+				global_constraint = cpu_constraint;
+		}
 	}
 
+	global_constraint *= NSEC_PER_USEC;
 	/* The minimum idle duration is from now - until the next wakeup. */
 	idle_duration_ns = ktime_to_ns(ktime_sub(domain_wakeup, now));
 	if (idle_duration_ns <= 0)
@@ -385,8 +397,10 @@ static bool cpu_power_down_ok(struct dev_pm_domain *pd)
 	 */
 	i = genpd->state_idx;
 	do {
-		if (idle_duration_ns >= (genpd->states[i].residency_ns +
+		if ((idle_duration_ns >= (genpd->states[i].residency_ns +
-		    genpd->states[i].power_off_latency_ns)) {
+		    genpd->states[i].power_off_latency_ns)) &&
+		    (global_constraint >= (genpd->states[i].power_on_latency_ns +
+		    genpd->states[i].power_off_latency_ns))) {
 			genpd->state_idx = i;
 			return true;
 		}