cpufreq: Set policy->min and max as real QoS constraints

cpufreq_set_policy() will ultimately override the policy min/max
values written in the .init() callback through:
cpufreq_policy_online()
\-cpufreq_init_policy()
  \-cpufreq_set_policy()
    \-/* Set policy->min/max */
Thus the policy min/max values provided are only temporary.

There is an exception if CPUFREQ_NEED_INITIAL_FREQ_CHECK is set and:
cpufreq_policy_online()
\-cpufreq_init_policy()
  \-__cpufreq_driver_target()
    \-cpufreq_driver->target()
is called. To avoid any regression, set policy->min/max in cpufreq.c
if the values were not initialized.

In this patch:
- Setting policy->min or max value in driver .init() cb is
  interpreted as setting a QoS constraint.
- Remove policy->min/max initialization in drivers if the values
  are similar to policy->cpuinfo.min_freq/max_freq.
  The only drivers where these values are different are:
  - gx-suspmod.c
  - cppc-cpufreq.c
  - longrun.c
- For the cppc-cpufreq driver, the lowest non-linear freq. is
  used as a min QoS constraint as suggested at:
  https://lore.kernel.org/lkml/20260213100633.15413-1-zhangpengjie2@huawei.com/

Signed-off-by: Pierre Gondois <pierre.gondois@arm.com>

Author: pierregondois

drivers/cpufreq/amd-pstate.c

@@ -1003,12 +1003,12 @@ static int amd_pstate_cpu_init(struct cpufreq_policy *policy)
 
 	perf = READ_ONCE(cpudata->perf);
 
-	policy->cpuinfo.min_freq = policy->min = perf_to_freq(perf,
-							      cpudata->nominal_freq,
-							      perf.lowest_perf);
-	policy->cpuinfo.max_freq = policy->max = perf_to_freq(perf,
-							      cpudata->nominal_freq,
-							      perf.highest_perf);
+	policy->cpuinfo.min_freq = perf_to_freq(perf,
+						cpudata->nominal_freq,
+						perf.lowest_perf);
+	policy->cpuinfo.max_freq = perf_to_freq(perf,
+						cpudata->nominal_freq,
+						perf.highest_perf);
 
 	ret = amd_pstate_cppc_enable(policy);
 	if (ret)
@@ -1492,12 +1492,12 @@ static int amd_pstate_epp_cpu_init(struct cpufreq_policy *policy)
 
 	perf = READ_ONCE(cpudata->perf);
 
-	policy->cpuinfo.min_freq = policy->min = perf_to_freq(perf,
-							      cpudata->nominal_freq,
-							      perf.lowest_perf);
-	policy->cpuinfo.max_freq = policy->max = perf_to_freq(perf,
-							      cpudata->nominal_freq,
-							      perf.highest_perf);
+	policy->cpuinfo.min_freq = perf_to_freq(perf,
+						cpudata->nominal_freq,
+						perf.lowest_perf);
+	policy->cpuinfo.max_freq = perf_to_freq(perf,
+						cpudata->nominal_freq,
+						perf.highest_perf);
 	policy->driver_data = cpudata;
 
 	ret = amd_pstate_cppc_enable(policy);

drivers/cpufreq/cppc_cpufreq.c

@@ -613,6 +613,7 @@ static int cppc_cpufreq_cpu_init(struct cpufreq_policy *policy)
 	unsigned int cpu = policy->cpu;
 	struct cppc_cpudata *cpu_data;
 	struct cppc_perf_caps *caps;
+	unsigned int min, max;
 	int ret;
 
 	cpu_data = cppc_cpufreq_get_cpu_data(cpu);
@@ -623,21 +624,23 @@ static int cppc_cpufreq_cpu_init(struct cpufreq_policy *policy)
 	caps = &cpu_data->perf_caps;
 	policy->driver_data = cpu_data;
 
+	min = cppc_perf_to_khz(caps, caps->lowest_nonlinear_perf);
+	max = cppc_perf_to_khz(caps, policy->boost_enabled ?
+			       caps->highest_perf : caps->nominal_perf);
+
 	/*
 	 * Set min to lowest nonlinear perf to avoid any efficiency penalty (see
 	 * Section 8.4.7.1.1.5 of ACPI 6.1 spec)
 	 */
-	policy->min = cppc_perf_to_khz(caps, caps->lowest_nonlinear_perf);
-	policy->max = cppc_perf_to_khz(caps, policy->boost_enabled ?
-						caps->highest_perf : caps->nominal_perf);
+	policy->min = min;
 
 	/*
 	 * Set cpuinfo.min_freq to Lowest to make the full range of performance
 	 * available if userspace wants to use any perf between lowest & lowest
 	 * nonlinear perf
 	 */
 	policy->cpuinfo.min_freq = cppc_perf_to_khz(caps, caps->lowest_perf);
-	policy->cpuinfo.max_freq = policy->max;
+	policy->cpuinfo.max_freq = max;
 
 	policy->transition_delay_us = cppc_cpufreq_get_transition_delay_us(cpu);
 	policy->shared_type = cpu_data->shared_type;

drivers/cpufreq/cpufreq-nforce2.c

@@ -355,8 +355,8 @@ static int nforce2_cpu_init(struct cpufreq_policy *policy)
 		min_fsb = NFORCE2_MIN_FSB;
 
 	/* cpuinfo and default policy values */
-	policy->min = policy->cpuinfo.min_freq = min_fsb * fid * 100;
-	policy->max = policy->cpuinfo.max_freq = max_fsb * fid * 100;
+	policy->cpuinfo.min_freq = min_fsb * fid * 100;
+	policy->cpuinfo.max_freq = max_fsb * fid * 100;
 
 	return 0;
 }

drivers/cpufreq/cpufreq.c

@@ -1435,6 +1435,14 @@ static int cpufreq_policy_online(struct cpufreq_policy *policy,
 	cpumask_and(policy->cpus, policy->cpus, cpu_online_mask);
 
 	if (new_policy) {
+		unsigned int min, max;
+
+		/* Use policy->min/max set by the driver as QoS requests. */
+		min = max(FREQ_QOS_MIN_DEFAULT_VALUE, policy->min);
+		if (policy->max)
+			max = min(FREQ_QOS_MAX_DEFAULT_VALUE, policy->max);
+		else
+			max = FREQ_QOS_MAX_DEFAULT_VALUE;
 		for_each_cpu(j, policy->related_cpus) {
 			per_cpu(cpufreq_cpu_data, j) = policy;
 			add_cpu_dev_symlink(policy, j, get_cpu_device(j));
@@ -1449,7 +1457,7 @@ static int cpufreq_policy_online(struct cpufreq_policy *policy,
 
 		ret = freq_qos_add_request(&policy->constraints,
 					   policy->min_freq_req, FREQ_QOS_MIN,
-					   FREQ_QOS_MIN_DEFAULT_VALUE);
+					   min);
 		if (ret < 0) {
 			/*
 			 * So we don't call freq_qos_remove_request() for an
@@ -1469,14 +1477,21 @@ static int cpufreq_policy_online(struct cpufreq_policy *policy,
 
 		ret = freq_qos_add_request(&policy->constraints,
 					   policy->max_freq_req, FREQ_QOS_MAX,
-					   FREQ_QOS_MAX_DEFAULT_VALUE);
+					   max);
 		if (ret < 0) {
 			policy->max_freq_req = NULL;
 			goto out_destroy_policy;
 		}
 
 		blocking_notifier_call_chain(&cpufreq_policy_notifier_list,
 				CPUFREQ_CREATE_POLICY, policy);
+
+		/*
+		 * If the driver didn't set QoS constraints, policy->min/max still
+		 * need to be set as they are used to clamp frequency requests.
+		 */
+		policy->min = policy->min ? policy->min : policy->cpuinfo.min_freq;
+		policy->max = policy->max ? policy->max : policy->cpuinfo.max_freq;
 	}
 
 	if (cpufreq_driver->get && has_target()) {

drivers/cpufreq/freq_table.c

@@ -50,16 +50,15 @@ int cpufreq_frequency_table_cpuinfo(struct cpufreq_policy *policy,
 			max_freq = freq;
 	}
 
-	policy->min = policy->cpuinfo.min_freq = min_freq;
-	policy->max = max_freq;
+	policy->cpuinfo.min_freq = min_freq;
 	/*
 	 * If the driver has set its own cpuinfo.max_freq above max_freq, leave
 	 * it as is.
 	 */
 	if (policy->cpuinfo.max_freq < max_freq)
-		policy->max = policy->cpuinfo.max_freq = max_freq;
+		policy->cpuinfo.max_freq = max_freq;
 
-	if (policy->min == ~0)
+	if (min_freq == ~0)
 		return -EINVAL;
 	else
 		return 0;

drivers/cpufreq/gx-suspmod.c

@@ -397,7 +397,7 @@ static int cpufreq_gx_target(struct cpufreq_policy *policy,
 
 static int cpufreq_gx_cpu_init(struct cpufreq_policy *policy)
 {
-	unsigned int maxfreq;
+	unsigned int minfreq, maxfreq;
 
 	if (!policy || policy->cpu != 0)
 		return -ENODEV;
@@ -418,10 +418,11 @@ static int cpufreq_gx_cpu_init(struct cpufreq_policy *policy)
 	policy->cpu = 0;
 
 	if (max_duration < POLICY_MIN_DIV)
-		policy->min = maxfreq / max_duration;
+		minfreq = maxfreq / max_duration;
 	else
-		policy->min = maxfreq / POLICY_MIN_DIV;
-	policy->max = maxfreq;
+		minfreq = maxfreq / POLICY_MIN_DIV;
+
+	policy->min = minfreq;
 	policy->cpuinfo.min_freq = maxfreq / max_duration;
 	policy->cpuinfo.max_freq = maxfreq;
 

drivers/cpufreq/intel_pstate.c

@@ -3113,9 +3113,6 @@ static int __intel_pstate_cpu_init(struct cpufreq_policy *policy)
 	policy->cpuinfo.max_freq = READ_ONCE(global.no_turbo) ?
 			cpu->pstate.max_freq : cpu->pstate.turbo_freq;
 
-	policy->min = policy->cpuinfo.min_freq;
-	policy->max = policy->cpuinfo.max_freq;
-
 	intel_pstate_init_acpi_perf_limits(policy);
 
 	policy->fast_switch_possible = true;

drivers/cpufreq/pcc-cpufreq.c

@@ -551,13 +551,13 @@ static int pcc_cpufreq_cpu_init(struct cpufreq_policy *policy)
 		goto out;
 	}
 
-	policy->max = policy->cpuinfo.max_freq =
+	policy->cpuinfo.max_freq =
 		ioread32(&pcch_hdr->nominal) * 1000;
-	policy->min = policy->cpuinfo.min_freq =
+	policy->cpuinfo.min_freq =
 		ioread32(&pcch_hdr->minimum_frequency) * 1000;
 
-	pr_debug("init: policy->max is %d, policy->min is %d\n",
-		policy->max, policy->min);
+	pr_debug("init: max_freq is %d, min_freq is %d\n",
+		 policy->cpuinfo.max_freq, policy->cpuinfo.min_freq);
 out:
 	return result;
 }

drivers/cpufreq/pxa3xx-cpufreq.c

@@ -185,8 +185,8 @@ static int pxa3xx_cpufreq_init(struct cpufreq_policy *policy)
 	int ret = -EINVAL;
 
 	/* set default policy and cpuinfo */
-	policy->min = policy->cpuinfo.min_freq = 104000;
-	policy->max = policy->cpuinfo.max_freq =
+	policy->cpuinfo.min_freq = 104000;
+	policy->cpuinfo.max_freq =
 		(cpu_is_pxa320()) ? 806000 : 624000;
 	policy->cpuinfo.transition_latency = 1000; /* FIXME: 1 ms, assumed */
 

drivers/cpufreq/sh-cpufreq.c

@@ -126,9 +126,9 @@ static int sh_cpufreq_cpu_init(struct cpufreq_policy *policy)
 		dev_notice(dev, "no frequency table found, falling back "
 			   "to rate rounding.\n");
 
-		policy->min = policy->cpuinfo.min_freq =
+		policy->cpuinfo.min_freq =
 			(clk_round_rate(cpuclk, 1) + 500) / 1000;
-		policy->max = policy->cpuinfo.max_freq =
+		policy->cpuinfo.max_freq =
 			(clk_round_rate(cpuclk, ~0UL) + 500) / 1000;
 	}