More power management updates for 6.9-rc1

- Modify the Energy Model code to bail out and complain if the unit of
    power is not uW to prevent errors due to unit mismatches (Lukasz Luba).
 
  - Make the intel_rapl platform driver use a remove callback returning
    void (Uwe Kleine-König).
 
  - Fix typo in the suspend and interrupts document (Saravana Kannan).
 
  - Make per-policy boost flags actually take effect on platforms using
    cpufreq_boost_set_sw() (Sibi Sankar).
 
  - Enable boost support in the SCMI cpufreq driver (Sibi Sankar).
 
  - Make the DT cpufreq driver use zalloc_cpumask_var() for allocating
    cpumasks to avoid using unitinialized memory (Marek Szyprowski).
 -----BEGIN PGP SIGNATURE-----
 
 iQJGBAABCAAwFiEE4fcc61cGeeHD/fCwgsRv/nhiVHEFAmX5iRASHHJqd0Byand5
 c29ja2kubmV0AAoJEILEb/54YlRxof8P/R+MrENvw2bIe5VGwqX99Nd47spbAe2J
 QchuY8R9RIhd4laJ74C+Nc7E1rawLukLHctVql1QzkygldyriAjhHnVeL98Tmh8C
 H+2928BEztPzbIzLMQ7uAVKY+iUD9BfTipPwqV6D118nswtRUbubQkLtrKAmssHQ
 Sm5BqYmEb91CiSIe9wjqCyfc7kq7ina7nqmGa7DgZNMUgCzjmAEDRz1vXV1oRjNl
 aIXpx9X1wtG699HRCXBkxt7SbgXN3bFim6ZFoTvxT4U2Rhcj9JJ/PxKufFL2vuGF
 1M99eu1aMqL0iS3vhj4k88uPG5kDv37qIFYD6Z2vqRVTy040fL+6Sny5IKMlQb+Z
 PUB/TT1rulhH4kCjhkJXuErLqMBG2Ujf8D4drosQK2avp20pF0TCm2h+0LX3HVXM
 dcv+WirjOyljygWm4D0XyvY6U88gcKiGGY/Qf7YQ/GC8Jyrj0h6qMvDw38725XU+
 VQ0JlYCoM1R24dT4iYWWrMbvK6pEQ5R9lwJNSgdtQWOFNmyQy8j8s7D4qyRrCdG/
 JERwNIi+NF3oezg3ahF8s9cemnkndqxlqX1atMmjL9WCbqUPl2LCxJ7TWM5H/mfg
 /h3jNk9ai6d2cHStvoxFzbAYqZX/72IVEteOomKKiHdW7lxWUW+J2xZRy0Pv0163
 iNNyshJAsuaf
 =dlQ/
 -----END PGP SIGNATURE-----

Merge tag 'pm-6.9-rc1-2' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull more power management updates from Rafael Wysocki:
 "These update the Energy Model to make it prevent errors due to power
  unit mismatches, fix a typo in power management documentation, convert
  one driver to using a platform remove callback returning void, address
  two cpufreq issues (one in the core and one in the DT driver), and
  enable boost support in the SCMI cpufreq driver.

  Specifics:

   - Modify the Energy Model code to bail out and complain if the unit
     of power is not uW to prevent errors due to unit mismatches (Lukasz
     Luba)

   - Make the intel_rapl platform driver use a remove callback returning
     void (Uwe Kleine-König)

   - Fix typo in the suspend and interrupts document (Saravana Kannan)

   - Make per-policy boost flags actually take effect on platforms using
     cpufreq_boost_set_sw() (Sibi Sankar)

   - Enable boost support in the SCMI cpufreq driver (Sibi Sankar)

   - Make the DT cpufreq driver use zalloc_cpumask_var() for allocating
     cpumasks to avoid using unitinialized memory (Marek Szyprowski)"

* tag 'pm-6.9-rc1-2' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm:
  cpufreq: scmi: Enable boost support
  firmware: arm_scmi: Add support for marking certain frequencies as turbo
  cpufreq: dt: always allocate zeroed cpumask
  cpufreq: Fix per-policy boost behavior on SoCs using cpufreq_boost_set_sw()
  Documentation: power: Fix typo in suspend and interrupts doc
  PM: EM: Force device drivers to provide power in uW
  powercap: intel_rapl: Convert to platform remove callback returning void

Documentation/power/suspend-and-interrupts.rst

@@ -78,7 +78,7 @@ handling the given IRQ as a system wakeup interrupt line and disable_irq_wake()
 turns that logic off.
 
 Calling enable_irq_wake() causes suspend_device_irqs() to treat the given IRQ
-in a special way.  Namely, the IRQ remains enabled, by on the first interrupt
+in a special way.  Namely, the IRQ remains enabled, but on the first interrupt
 it will be disabled, marked as pending and "suspended" so that it will be
 re-enabled by resume_device_irqs() during the subsequent system resume.  Also
 the PM core is notified about the event which causes the system suspend in

drivers/cpufreq/cpufreq-dt.c

@@ -208,7 +208,7 @@ static int dt_cpufreq_early_init(struct device *dev, int cpu)
 	if (!priv)
 		return -ENOMEM;
 
-	if (!alloc_cpumask_var(&priv->cpus, GFP_KERNEL))
+	if (!zalloc_cpumask_var(&priv->cpus, GFP_KERNEL))
 		return -ENOMEM;
 
 	cpumask_set_cpu(cpu, priv->cpus);

drivers/cpufreq/cpufreq.c

@@ -653,14 +653,16 @@ static ssize_t store_local_boost(struct cpufreq_policy *policy,
 	if (policy->boost_enabled == enable)
 		return count;
 
+	policy->boost_enabled = enable;
+
 	cpus_read_lock();
 	ret = cpufreq_driver->set_boost(policy, enable);
 	cpus_read_unlock();
 
-	if (ret)
+	if (ret) {
+		policy->boost_enabled = !policy->boost_enabled;
 		return ret;
-
-	policy->boost_enabled = enable;
+	}
 
 	return count;
 }
@@ -1428,6 +1430,9 @@ static int cpufreq_online(unsigned int cpu)
 			goto out_free_policy;
 		}
 
+		/* Let the per-policy boost flag mirror the cpufreq_driver boost during init */
+		policy->boost_enabled = cpufreq_boost_enabled() && policy_has_boost_freq(policy);
+
 		/*
 		 * The initialization has succeeded and the policy is online.
 		 * If there is a problem with its frequency table, take it
@@ -2769,11 +2774,12 @@ int cpufreq_boost_trigger_state(int state)
 
 	cpus_read_lock();
 	for_each_active_policy(policy) {
-		ret = cpufreq_driver->set_boost(policy, state);
-		if (ret)
-			goto err_reset_state;
-
 		policy->boost_enabled = state;
+		ret = cpufreq_driver->set_boost(policy, state);
+		if (ret) {
+			policy->boost_enabled = !policy->boost_enabled;
+			goto err_reset_state;
+		}
 	}
 	cpus_read_unlock();
 

drivers/cpufreq/freq_table.c

@@ -40,7 +40,7 @@ int cpufreq_frequency_table_cpuinfo(struct cpufreq_policy *policy,
 	cpufreq_for_each_valid_entry(pos, table) {
 		freq = pos->frequency;
 
-		if (!cpufreq_boost_enabled()
+		if ((!cpufreq_boost_enabled() || !policy->boost_enabled)
 		    && (pos->flags & CPUFREQ_BOOST_FREQ))
 			continue;
 

drivers/cpufreq/scmi-cpufreq.c

@@ -30,6 +30,7 @@ struct scmi_data {
 
 static struct scmi_protocol_handle *ph;
 static const struct scmi_perf_proto_ops *perf_ops;
+static struct cpufreq_driver scmi_cpufreq_driver;
 
 static unsigned int scmi_cpufreq_get_rate(unsigned int cpu)
 {
@@ -167,6 +168,12 @@ scmi_get_rate_limit(u32 domain, bool has_fast_switch)
 	return rate_limit;
 }
 
+static struct freq_attr *scmi_cpufreq_hw_attr[] = {
+	&cpufreq_freq_attr_scaling_available_freqs,
+	NULL,
+	NULL,
+};
+
 static int scmi_cpufreq_init(struct cpufreq_policy *policy)
 {
 	int ret, nr_opp, domain;
@@ -276,6 +283,17 @@ static int scmi_cpufreq_init(struct cpufreq_policy *policy)
 	policy->transition_delay_us =
 		scmi_get_rate_limit(domain, policy->fast_switch_possible);
 
+	if (policy_has_boost_freq(policy)) {
+		ret = cpufreq_enable_boost_support();
+		if (ret) {
+			dev_warn(cpu_dev, "failed to enable boost: %d\n", ret);
+			goto out_free_opp;
+		} else {
+			scmi_cpufreq_hw_attr[1] = &cpufreq_freq_attr_scaling_boost_freqs;
+			scmi_cpufreq_driver.boost_enabled = true;
+		}
+	}
+
 	return 0;
 
 out_free_opp:
@@ -334,7 +352,7 @@ static struct cpufreq_driver scmi_cpufreq_driver = {
 		  CPUFREQ_NEED_INITIAL_FREQ_CHECK |
 		  CPUFREQ_IS_COOLING_DEV,
 	.verify	= cpufreq_generic_frequency_table_verify,
-	.attr	= cpufreq_generic_attr,
+	.attr	= scmi_cpufreq_hw_attr,
 	.target_index	= scmi_cpufreq_set_target,
 	.fast_switch	= scmi_cpufreq_fast_switch,
 	.get	= scmi_cpufreq_get_rate,

drivers/firmware/arm_scmi/perf.c

@@ -871,6 +871,9 @@ static int scmi_dvfs_device_opps_add(const struct scmi_protocol_handle *ph,
 		else
 			freq = dom->opp[idx].indicative_freq * dom->mult_factor;
 
+		/* All OPPs above the sustained frequency are treated as turbo */
+		data.turbo = freq > dom->sustained_freq_khz * 1000;
+
 		data.level = dom->opp[idx].perf;
 		data.freq = freq;
 

drivers/powercap/intel_rapl_msr.c

@@ -197,11 +197,10 @@ out:
 	return ret;
 }
 
-static int rapl_msr_remove(struct platform_device *pdev)
+static void rapl_msr_remove(struct platform_device *pdev)
 {
 	cpuhp_remove_state(rapl_msr_priv->pcap_rapl_online);
 	powercap_unregister_control_type(rapl_msr_priv->control_type);
-	return 0;
 }
 
 static const struct platform_device_id rapl_msr_ids[] = {
@@ -212,7 +211,7 @@ MODULE_DEVICE_TABLE(platform, rapl_msr_ids);
 
 static struct platform_driver intel_rapl_msr_driver = {
 	.probe = rapl_msr_probe,
-	.remove = rapl_msr_remove,
+	.remove_new = rapl_msr_remove,
 	.id_table = rapl_msr_ids,
 	.driver = {
 		.name = "intel_rapl_msr",

kernel/power/energy_model.c

@@ -612,6 +612,17 @@ int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states,
 	else if (cb->get_cost)
 		flags |= EM_PERF_DOMAIN_ARTIFICIAL;
 
+	/*
+	 * EM only supports uW (exception is artificial EM).
+	 * Therefore, check and force the drivers to provide
+	 * power in uW.
+	 */
+	if (!microwatts && !(flags & EM_PERF_DOMAIN_ARTIFICIAL)) {
+		dev_err(dev, "EM: only supports uW power values\n");
+		ret = -EINVAL;
+		goto unlock;
+	}
+
 	ret = em_create_pd(dev, nr_states, cb, cpus, flags);
 	if (ret)
 		goto unlock;