linux-kernel - [PATCH v5 3/4] scmi-cpufreq: get opp_shared

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <20201208174229.24323-4-nicola.mazzucato@arm.com>
Date:   Tue,  8 Dec 2020 17:42:28 +0000
From:   Nicola Mazzucato <nicola.mazzucato@....com>
To:     linux-kernel@...r.kernel.org, linux-arm-kernel@...ts.infradead.org,
        linux-pm@...r.kernel.org, devicetree@...r.kernel.org,
        sudeep.holla@....com, rjw@...ysocki.net, vireshk@...nel.org,
        robh+dt@...nel.org, sboyd@...nel.org, nm@...com
Cc:     daniel.lezcano@...aro.org, morten.rasmussen@....com,
        chris.redpath@....com, nicola.mazzucato@....com
Subject: [PATCH v5 3/4] scmi-cpufreq: get opp_shared_cpus from opp-v2 for EM

By design, SCMI performance domains define the granularity of
performance controls, they do not describe any underlying hardware
dependencies (although they may match in many cases).

It is therefore possible to have some platforms where hardware may have
the ability to control CPU performance at different granularity and choose
to describe fine-grained performance control through SCMI.

In such situations, the energy model would be provided with inaccurate
information based on controls, while it still needs to know the
performance boundaries.

To restore correct functionality, retrieve information of CPUs under the
same performance domain from operating-points-v2 in DT, and pass it on to
EM.

As part of the rework, the deferred probe is also removed as this
condition should never occur.

Signed-off-by: Nicola Mazzucato <nicola.mazzucato@....com>
---
 drivers/cpufreq/scmi-cpufreq.c | 69 ++++++++++++++++++++++++----------
 1 file changed, 50 insertions(+), 19 deletions(-)

diff --git a/drivers/cpufreq/scmi-cpufreq.c b/drivers/cpufreq/scmi-cpufreq.c
index 491a0a24fb1e..88ebfd47c5de 100644
--- a/drivers/cpufreq/scmi-cpufreq.c
+++ b/drivers/cpufreq/scmi-cpufreq.c
@@ -127,6 +127,7 @@ static int scmi_cpufreq_init(struct cpufreq_policy *policy)
 	struct cpufreq_frequency_table *freq_table;
 	struct em_data_callback em_cb = EM_DATA_CB(scmi_get_cpu_power);
 	bool power_scale_mw;
+	cpumask_var_t opp_shared_cpus;
 
 	cpu_dev = get_cpu_device(policy->cpu);
 	if (!cpu_dev) {
@@ -134,30 +135,62 @@ static int scmi_cpufreq_init(struct cpufreq_policy *policy)
 		return -ENODEV;
 	}
 
-	ret = handle->perf_ops->device_opps_add(handle, cpu_dev);
-	if (ret) {
-		dev_warn(cpu_dev, "failed to add opps to the device\n");
-		return ret;
-	}
+	if (!zalloc_cpumask_var(&opp_shared_cpus, GFP_KERNEL))
+		return -ENOMEM;
 
 	ret = scmi_get_sharing_cpus(cpu_dev, policy->cpus);
 	if (ret) {
 		dev_warn(cpu_dev, "failed to get sharing cpumask\n");
-		return ret;
+		goto out_free_cpumask;
 	}
 
-	ret = dev_pm_opp_set_sharing_cpus(cpu_dev, policy->cpus);
-	if (ret) {
-		dev_err(cpu_dev, "%s: failed to mark OPPs as shared: %d\n",
-			__func__, ret);
-		return ret;
+	/*
+	 * The OPP 'sharing cpus' info may come from dt through an empty opp
+	 * table and opp-shared. If found, it takes precedence over the SCMI
+	 * domain IDs info.
+	 */
+	ret = dev_pm_opp_of_get_sharing_cpus(cpu_dev, opp_shared_cpus);
+	if (ret || !cpumask_weight(opp_shared_cpus)) {
+		/*
+		 * Either opp-table is not set or no opp-shared was found,
+		 * use the information from SCMI domain IDs.
+		 */
+		cpumask_copy(opp_shared_cpus, policy->cpus);
 	}
 
+	/*
+	 * For a given opp_shared_cpus, add OPPs only for the 'first' CPU and
+	 * mark the other ones as shared.
+	 */
 	nr_opp = dev_pm_opp_get_opp_count(cpu_dev);
 	if (nr_opp <= 0) {
-		dev_dbg(cpu_dev, "OPP table is not ready, deferring probe\n");
-		ret = -EPROBE_DEFER;
-		goto out_free_opp;
+		ret = handle->perf_ops->device_opps_add(handle, cpu_dev);
+		if (ret) {
+			dev_warn(cpu_dev, "failed to add OPPs to the device\n");
+			goto out_free_cpumask;
+		}
+
+		ret = dev_pm_opp_set_sharing_cpus(cpu_dev, opp_shared_cpus);
+		if (ret) {
+			dev_err(cpu_dev, "%s: failed to mark OPPs as shared: %d\n",
+				__func__, ret);
+			goto out_free_cpumask;
+		}
+
+		/*
+		 * To correctly register EM, get the number of OPPs just added
+		 * for this CPU.
+		 */
+		nr_opp = dev_pm_opp_get_opp_count(cpu_dev);
+		if (nr_opp <= 0) {
+			dev_err(cpu_dev, "%s: No OPPs for this device: %d\n",
+				__func__, ret);
+			goto out_free_cpumask;
+		}
+
+		power_scale_mw = handle->perf_ops->power_scale_mw_get(handle);
+		em_dev_register_perf_domain(cpu_dev, nr_opp, &em_cb,
+					    opp_shared_cpus, power_scale_mw);
 	}
 
 	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
@@ -190,16 +223,14 @@ static int scmi_cpufreq_init(struct cpufreq_policy *policy)
 	policy->fast_switch_possible =
 		handle->perf_ops->fast_switch_possible(handle, cpu_dev);
 
-	power_scale_mw = handle->perf_ops->power_scale_mw_get(handle);
-	em_dev_register_perf_domain(cpu_dev, nr_opp, &em_cb, policy->cpus,
-				    power_scale_mw);
-
-	return 0;
+	goto out_free_cpumask;
 
 out_free_priv:
 	kfree(priv);
 out_free_opp:
 	dev_pm_opp_remove_all_dynamic(cpu_dev);
+out_free_cpumask:
+	free_cpumask_var(opp_shared_cpus);
 
 	return ret;
 }
-- 
2.27.0