From bb8c26d9387fe428068dcab35b1873ea3b881de1 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Wed, 11 Aug 2021 10:22:55 +0530 Subject: cpufreq: vexpress: Set CPUFREQ_IS_COOLING_DEV flag Reuse the cpufreq core's registration of cooling device by setting the CPUFREQ_IS_COOLING_DEV flag. Set this only if bL switcher isn't enabled. Signed-off-by: Viresh Kumar --- drivers/cpufreq/vexpress-spc-cpufreq.c | 22 +++------------------- 1 file changed, 3 insertions(+), 19 deletions(-) (limited to 'drivers/cpufreq') diff --git a/drivers/cpufreq/vexpress-spc-cpufreq.c b/drivers/cpufreq/vexpress-spc-cpufreq.c index 51dfa9ae6cf5..ab56813b7256 100644 --- a/drivers/cpufreq/vexpress-spc-cpufreq.c +++ b/drivers/cpufreq/vexpress-spc-cpufreq.c @@ -15,7 +15,6 @@ #include #include #include -#include #include #include #include @@ -47,7 +46,6 @@ static bool bL_switching_enabled; #define ACTUAL_FREQ(cluster, freq) ((cluster == A7_CLUSTER) ? freq << 1 : freq) #define VIRT_FREQ(cluster, freq) ((cluster == A7_CLUSTER) ? freq >> 1 : freq) -static struct thermal_cooling_device *cdev[MAX_CLUSTERS]; static struct clk *clk[MAX_CLUSTERS]; static struct cpufreq_frequency_table *freq_table[MAX_CLUSTERS + 1]; static atomic_t cluster_usage[MAX_CLUSTERS + 1]; @@ -457,11 +455,6 @@ static int ve_spc_cpufreq_exit(struct cpufreq_policy *policy) struct device *cpu_dev; int cur_cluster = cpu_to_cluster(policy->cpu); - if (cur_cluster < MAX_CLUSTERS) { - cpufreq_cooling_unregister(cdev[cur_cluster]); - cdev[cur_cluster] = NULL; - } - cpu_dev = get_cpu_device(policy->cpu); if (!cpu_dev) { pr_err("%s: failed to get cpu%d device\n", __func__, @@ -473,17 +466,6 @@ static int ve_spc_cpufreq_exit(struct cpufreq_policy *policy) return 0; } -static void ve_spc_cpufreq_ready(struct cpufreq_policy *policy) -{ - int cur_cluster = cpu_to_cluster(policy->cpu); - - /* Do not register a cpu_cooling device if we are in IKS mode */ - if (cur_cluster >= MAX_CLUSTERS) - return; - - cdev[cur_cluster] = of_cpufreq_cooling_register(policy); -} - static struct cpufreq_driver ve_spc_cpufreq_driver = { .name = "vexpress-spc", .flags = CPUFREQ_HAVE_GOVERNOR_PER_POLICY | @@ -493,7 +475,6 @@ static struct cpufreq_driver ve_spc_cpufreq_driver = { .get = ve_spc_cpufreq_get_rate, .init = ve_spc_cpufreq_init, .exit = ve_spc_cpufreq_exit, - .ready = ve_spc_cpufreq_ready, .attr = cpufreq_generic_attr, }; @@ -553,6 +534,9 @@ static int ve_spc_cpufreq_probe(struct platform_device *pdev) for (i = 0; i < MAX_CLUSTERS; i++) mutex_init(&cluster_lock[i]); + if (!is_bL_switching_enabled()) + ve_spc_cpufreq_driver.flags |= CPUFREQ_IS_COOLING_DEV; + ret = cpufreq_register_driver(&ve_spc_cpufreq_driver); if (ret) { pr_info("%s: Failed registering platform driver: %s, err: %d\n", -- cgit v1.2.3 From c17495b01b72b53bd290f442d39b060e015c7aea Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Tue, 10 Aug 2021 12:04:33 +0530 Subject: cpufreq: Add callback to register with energy model Many cpufreq drivers register with the energy model for each policy and do exactly the same thing. Follow the footsteps of thermal-cooling, to get it done from the cpufreq core itself. Provide a new callback, which will be called, if present, by the cpufreq core at the right moment (more on that in the code's comment). Also provide a generic implementation that uses dev_pm_opp_of_register_em(). This also allows us to register with the EM at a later point of time, compared to ->init(), from where the EM core can access cpufreq policy directly using cpufreq_cpu_get() type of helpers and perform other work, like marking few frequencies inefficient, this will be done separately. Reviewed-by: Quentin Perret Reviewed-by: Lukasz Luba Signed-off-by: Viresh Kumar --- drivers/cpufreq/cpufreq.c | 13 +++++++++++++ include/linux/cpufreq.h | 14 ++++++++++++++ 2 files changed, 27 insertions(+) (limited to 'drivers/cpufreq') diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 45f3416988f1..d301f39248a0 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -1491,6 +1491,19 @@ static int cpufreq_online(unsigned int cpu) write_lock_irqsave(&cpufreq_driver_lock, flags); list_add(&policy->policy_list, &cpufreq_policy_list); write_unlock_irqrestore(&cpufreq_driver_lock, flags); + + /* + * Register with the energy model before + * sched_cpufreq_governor_change() is called, which will result + * in rebuilding of the sched domains, which should only be done + * once the energy model is properly initialized for the policy + * first. + * + * Also, this should be called before the policy is registered + * with cooling framework. + */ + if (cpufreq_driver->register_em) + cpufreq_driver->register_em(policy); } ret = cpufreq_init_policy(policy); diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 9fd719475fcd..c65a1d7385f8 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -9,10 +9,12 @@ #define _LINUX_CPUFREQ_H #include +#include #include #include #include #include +#include #include #include #include @@ -373,6 +375,12 @@ struct cpufreq_driver { /* platform specific boost support code */ bool boost_enabled; int (*set_boost)(struct cpufreq_policy *policy, int state); + + /* + * Set by drivers that want to register with the energy model after the + * policy is properly initialized, but before the governor is started. + */ + void (*register_em)(struct cpufreq_policy *policy); }; /* flags */ @@ -1046,4 +1054,10 @@ unsigned int cpufreq_generic_get(unsigned int cpu); void cpufreq_generic_init(struct cpufreq_policy *policy, struct cpufreq_frequency_table *table, unsigned int transition_latency); + +static inline void cpufreq_register_em_with_opp(struct cpufreq_policy *policy) +{ + dev_pm_opp_of_register_em(get_cpu_device(policy->cpu), + policy->related_cpus); +} #endif /* _LINUX_CPUFREQ_H */ -- cgit v1.2.3 From 94ab4c3c259c7d00746e5cafb55b5f5125f34b71 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Tue, 10 Aug 2021 12:24:36 +0530 Subject: cpufreq: dt: Use .register_em() to register with energy model Set the newly added .register_em() callback with cpufreq_register_em_with_opp() to register with the EM core. Signed-off-by: Viresh Kumar --- drivers/cpufreq/cpufreq-dt.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'drivers/cpufreq') diff --git a/drivers/cpufreq/cpufreq-dt.c b/drivers/cpufreq/cpufreq-dt.c index ece52863ba62..8fcaba541539 100644 --- a/drivers/cpufreq/cpufreq-dt.c +++ b/drivers/cpufreq/cpufreq-dt.c @@ -143,8 +143,6 @@ static int cpufreq_init(struct cpufreq_policy *policy) cpufreq_dt_attr[1] = &cpufreq_freq_attr_scaling_boost_freqs; } - dev_pm_opp_of_register_em(cpu_dev, policy->cpus); - return 0; out_clk_put: @@ -184,6 +182,7 @@ static struct cpufreq_driver dt_cpufreq_driver = { .exit = cpufreq_exit, .online = cpufreq_online, .offline = cpufreq_offline, + .register_em = cpufreq_register_em_with_opp, .name = "cpufreq-dt", .attr = cpufreq_dt_attr, .suspend = cpufreq_generic_suspend, -- cgit v1.2.3 From fcd300c685d5152e76a811c492b0e6eccde29717 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Tue, 10 Aug 2021 12:24:36 +0530 Subject: cpufreq: imx6q: Use .register_em() to register with energy model Set the newly added .register_em() callback with cpufreq_register_em_with_opp() to register with the EM core. Signed-off-by: Viresh Kumar --- drivers/cpufreq/imx6q-cpufreq.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/cpufreq') diff --git a/drivers/cpufreq/imx6q-cpufreq.c b/drivers/cpufreq/imx6q-cpufreq.c index 5bf5fc759881..90beb26ed34e 100644 --- a/drivers/cpufreq/imx6q-cpufreq.c +++ b/drivers/cpufreq/imx6q-cpufreq.c @@ -192,7 +192,6 @@ static int imx6q_cpufreq_init(struct cpufreq_policy *policy) policy->clk = clks[ARM].clk; cpufreq_generic_init(policy, freq_table, transition_latency); policy->suspend_freq = max_freq; - dev_pm_opp_of_register_em(cpu_dev, policy->cpus); return 0; } @@ -204,6 +203,7 @@ static struct cpufreq_driver imx6q_cpufreq_driver = { .target_index = imx6q_set_target, .get = cpufreq_generic_get, .init = imx6q_cpufreq_init, + .register_em = cpufreq_register_em_with_opp, .name = "imx6q-cpufreq", .attr = cpufreq_generic_attr, .suspend = cpufreq_generic_suspend, -- cgit v1.2.3 From 3701fd64a3fb947fc805ca0d108ab87562a9659b Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Tue, 10 Aug 2021 12:24:36 +0530 Subject: cpufreq: mediatek: Use .register_em() to register with energy model Set the newly added .register_em() callback with cpufreq_register_em_with_opp() to register with the EM core. Signed-off-by: Viresh Kumar --- drivers/cpufreq/mediatek-cpufreq.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'drivers/cpufreq') diff --git a/drivers/cpufreq/mediatek-cpufreq.c b/drivers/cpufreq/mediatek-cpufreq.c index 87019d5a9547..866163883b48 100644 --- a/drivers/cpufreq/mediatek-cpufreq.c +++ b/drivers/cpufreq/mediatek-cpufreq.c @@ -448,8 +448,6 @@ static int mtk_cpufreq_init(struct cpufreq_policy *policy) policy->driver_data = info; policy->clk = info->cpu_clk; - dev_pm_opp_of_register_em(info->cpu_dev, policy->cpus); - return 0; } @@ -471,6 +469,7 @@ static struct cpufreq_driver mtk_cpufreq_driver = { .get = cpufreq_generic_get, .init = mtk_cpufreq_init, .exit = mtk_cpufreq_exit, + .register_em = cpufreq_register_em_with_opp, .name = "mtk-cpufreq", .attr = cpufreq_generic_attr, }; -- cgit v1.2.3 From 361a172d230964807c0b479738749c50d95d7b50 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Tue, 10 Aug 2021 12:24:36 +0530 Subject: cpufreq: omap: Use .register_em() to register with energy model Set the newly added .register_em() callback with cpufreq_register_em_with_opp() to register with the EM core. Signed-off-by: Viresh Kumar --- drivers/cpufreq/omap-cpufreq.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/cpufreq') diff --git a/drivers/cpufreq/omap-cpufreq.c b/drivers/cpufreq/omap-cpufreq.c index e035ee216b0f..1b50df06c6bc 100644 --- a/drivers/cpufreq/omap-cpufreq.c +++ b/drivers/cpufreq/omap-cpufreq.c @@ -131,7 +131,6 @@ static int omap_cpu_init(struct cpufreq_policy *policy) /* FIXME: what's the actual transition time? */ cpufreq_generic_init(policy, freq_table, 300 * 1000); - dev_pm_opp_of_register_em(mpu_dev, policy->cpus); return 0; } @@ -150,6 +149,7 @@ static struct cpufreq_driver omap_driver = { .get = cpufreq_generic_get, .init = omap_cpu_init, .exit = omap_cpu_exit, + .register_em = cpufreq_register_em_with_opp, .name = "omap", .attr = cpufreq_generic_attr, }; -- cgit v1.2.3 From e96c2153d0fc0a1c218bf5ba149ccdf75d19a275 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Tue, 10 Aug 2021 12:24:36 +0530 Subject: cpufreq: qcom-cpufreq-hw: Use .register_em() to register with energy model Set the newly added .register_em() callback with cpufreq_register_em_with_opp() to register with the EM core. Signed-off-by: Viresh Kumar --- drivers/cpufreq/qcom-cpufreq-hw.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'drivers/cpufreq') diff --git a/drivers/cpufreq/qcom-cpufreq-hw.c b/drivers/cpufreq/qcom-cpufreq-hw.c index f86859bf76f1..c2e71c430fbf 100644 --- a/drivers/cpufreq/qcom-cpufreq-hw.c +++ b/drivers/cpufreq/qcom-cpufreq-hw.c @@ -362,8 +362,6 @@ static int qcom_cpufreq_hw_cpu_init(struct cpufreq_policy *policy) goto error; } - dev_pm_opp_of_register_em(cpu_dev, policy->cpus); - if (policy_has_boost_freq(policy)) { ret = cpufreq_enable_boost_support(); if (ret) @@ -412,6 +410,7 @@ static struct cpufreq_driver cpufreq_qcom_hw_driver = { .get = qcom_cpufreq_hw_get, .init = qcom_cpufreq_hw_cpu_init, .exit = qcom_cpufreq_hw_cpu_exit, + .register_em = cpufreq_register_em_with_opp, .fast_switch = qcom_cpufreq_hw_fast_switch, .name = "qcom-cpufreq-hw", .attr = qcom_cpufreq_hw_attr, -- cgit v1.2.3 From 4d584efae0b28928011dd5b3b9b3a3ac4324bcac Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Tue, 10 Aug 2021 12:24:36 +0530 Subject: cpufreq: scpi: Use .register_em() to register with energy model Set the newly added .register_em() callback with cpufreq_register_em_with_opp() to register with the EM core. Acked-by: Sudeep Holla Signed-off-by: Viresh Kumar --- drivers/cpufreq/scpi-cpufreq.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'drivers/cpufreq') diff --git a/drivers/cpufreq/scpi-cpufreq.c b/drivers/cpufreq/scpi-cpufreq.c index d6a698a1b5d1..bda3e7d42964 100644 --- a/drivers/cpufreq/scpi-cpufreq.c +++ b/drivers/cpufreq/scpi-cpufreq.c @@ -163,8 +163,6 @@ static int scpi_cpufreq_init(struct cpufreq_policy *policy) policy->fast_switch_possible = false; - dev_pm_opp_of_register_em(cpu_dev, policy->cpus); - return 0; out_free_cpufreq_table: @@ -200,6 +198,7 @@ static struct cpufreq_driver scpi_cpufreq_driver = { .init = scpi_cpufreq_init, .exit = scpi_cpufreq_exit, .target_index = scpi_cpufreq_set_target, + .register_em = cpufreq_register_em_with_opp, }; static int scpi_cpufreq_probe(struct platform_device *pdev) -- cgit v1.2.3 From 3fd23111185d2167696547d59235bda8d307425c Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Tue, 10 Aug 2021 12:24:36 +0530 Subject: cpufreq: vexpress: Use .register_em() to register with energy model Set the newly added .register_em() callback with cpufreq_register_em_with_opp() to register with the EM core. Acked-by: Sudeep Holla Signed-off-by: Viresh Kumar --- drivers/cpufreq/vexpress-spc-cpufreq.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'drivers/cpufreq') diff --git a/drivers/cpufreq/vexpress-spc-cpufreq.c b/drivers/cpufreq/vexpress-spc-cpufreq.c index ab56813b7256..284b6bd040b1 100644 --- a/drivers/cpufreq/vexpress-spc-cpufreq.c +++ b/drivers/cpufreq/vexpress-spc-cpufreq.c @@ -440,8 +440,6 @@ static int ve_spc_cpufreq_init(struct cpufreq_policy *policy) policy->freq_table = freq_table[cur_cluster]; policy->cpuinfo.transition_latency = 1000000; /* 1 ms */ - dev_pm_opp_of_register_em(cpu_dev, policy->cpus); - if (is_bL_switching_enabled()) per_cpu(cpu_last_req_freq, policy->cpu) = clk_get_cpu_rate(policy->cpu); @@ -475,6 +473,7 @@ static struct cpufreq_driver ve_spc_cpufreq_driver = { .get = ve_spc_cpufreq_get_rate, .init = ve_spc_cpufreq_init, .exit = ve_spc_cpufreq_exit, + .register_em = cpufreq_register_em_with_opp, .attr = cpufreq_generic_attr, }; -- cgit v1.2.3 From 37f188318ea3f1da75b32df3b1a19f45d9840652 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Tue, 10 Aug 2021 12:24:36 +0530 Subject: cpufreq: scmi: Use .register_em() to register with energy model Set the newly added .register_em() callback to register with the EM after the cpufreq policy is properly initialized. Acked-by: Sudeep Holla Signed-off-by: Viresh Kumar --- drivers/cpufreq/scmi-cpufreq.c | 65 +++++++++++++++++++++++++++--------------- 1 file changed, 42 insertions(+), 23 deletions(-) (limited to 'drivers/cpufreq') diff --git a/drivers/cpufreq/scmi-cpufreq.c b/drivers/cpufreq/scmi-cpufreq.c index 75f818d04b48..1e0cd4d165f0 100644 --- a/drivers/cpufreq/scmi-cpufreq.c +++ b/drivers/cpufreq/scmi-cpufreq.c @@ -22,7 +22,9 @@ struct scmi_data { int domain_id; + int nr_opp; struct device *cpu_dev; + cpumask_var_t opp_shared_cpus; }; static struct scmi_protocol_handle *ph; @@ -123,9 +125,6 @@ static int scmi_cpufreq_init(struct cpufreq_policy *policy) struct device *cpu_dev; struct scmi_data *priv; struct cpufreq_frequency_table *freq_table; - struct em_data_callback em_cb = EM_DATA_CB(scmi_get_cpu_power); - cpumask_var_t opp_shared_cpus; - bool power_scale_mw; cpu_dev = get_cpu_device(policy->cpu); if (!cpu_dev) { @@ -133,9 +132,15 @@ static int scmi_cpufreq_init(struct cpufreq_policy *policy) return -ENODEV; } - if (!zalloc_cpumask_var(&opp_shared_cpus, GFP_KERNEL)) + priv = kzalloc(sizeof(*priv), GFP_KERNEL); + if (!priv) return -ENOMEM; + if (!zalloc_cpumask_var(&priv->opp_shared_cpus, GFP_KERNEL)) { + ret = -ENOMEM; + goto out_free_priv; + } + /* Obtain CPUs that share SCMI performance controls */ ret = scmi_get_sharing_cpus(cpu_dev, policy->cpus); if (ret) { @@ -148,14 +153,14 @@ static int scmi_cpufreq_init(struct cpufreq_policy *policy) * The OPP 'sharing cpus' info may come from DT through an empty opp * table and opp-shared. */ - ret = dev_pm_opp_of_get_sharing_cpus(cpu_dev, opp_shared_cpus); - if (ret || !cpumask_weight(opp_shared_cpus)) { + ret = dev_pm_opp_of_get_sharing_cpus(cpu_dev, priv->opp_shared_cpus); + if (ret || !cpumask_weight(priv->opp_shared_cpus)) { /* * Either opp-table is not set or no opp-shared was found. * Use the CPU mask from SCMI to designate CPUs sharing an OPP * table. */ - cpumask_copy(opp_shared_cpus, policy->cpus); + cpumask_copy(priv->opp_shared_cpus, policy->cpus); } /* @@ -180,7 +185,7 @@ static int scmi_cpufreq_init(struct cpufreq_policy *policy) goto out_free_opp; } - ret = dev_pm_opp_set_sharing_cpus(cpu_dev, opp_shared_cpus); + ret = dev_pm_opp_set_sharing_cpus(cpu_dev, priv->opp_shared_cpus); if (ret) { dev_err(cpu_dev, "%s: failed to mark OPPs as shared: %d\n", __func__, ret); @@ -188,21 +193,13 @@ static int scmi_cpufreq_init(struct cpufreq_policy *policy) goto out_free_opp; } - power_scale_mw = perf_ops->power_scale_mw_get(ph); - em_dev_register_perf_domain(cpu_dev, nr_opp, &em_cb, - opp_shared_cpus, power_scale_mw); - } - - priv = kzalloc(sizeof(*priv), GFP_KERNEL); - if (!priv) { - ret = -ENOMEM; - goto out_free_opp; + priv->nr_opp = nr_opp; } ret = dev_pm_opp_init_cpufreq_table(cpu_dev, &freq_table); if (ret) { dev_err(cpu_dev, "failed to init cpufreq table: %d\n", ret); - goto out_free_priv; + goto out_free_opp; } priv->cpu_dev = cpu_dev; @@ -223,17 +220,16 @@ static int scmi_cpufreq_init(struct cpufreq_policy *policy) policy->fast_switch_possible = perf_ops->fast_switch_possible(ph, cpu_dev); - free_cpumask_var(opp_shared_cpus); return 0; -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); + free_cpumask_var(priv->opp_shared_cpus); + +out_free_priv: + kfree(priv); return ret; } @@ -244,11 +240,33 @@ static int scmi_cpufreq_exit(struct cpufreq_policy *policy) dev_pm_opp_free_cpufreq_table(priv->cpu_dev, &policy->freq_table); dev_pm_opp_remove_all_dynamic(priv->cpu_dev); + free_cpumask_var(priv->opp_shared_cpus); kfree(priv); return 0; } +static void scmi_cpufreq_register_em(struct cpufreq_policy *policy) +{ + struct em_data_callback em_cb = EM_DATA_CB(scmi_get_cpu_power); + bool power_scale_mw = perf_ops->power_scale_mw_get(ph); + struct scmi_data *priv = policy->driver_data; + + /* + * This callback will be called for each policy, but we don't need to + * register with EM every time. Despite not being part of the same + * policy, some CPUs may still share their perf-domains, and a CPU from + * another policy may already have registered with EM on behalf of CPUs + * of this policy. + */ + if (!priv->nr_opp) + return; + + em_dev_register_perf_domain(get_cpu_device(policy->cpu), priv->nr_opp, + &em_cb, priv->opp_shared_cpus, + power_scale_mw); +} + static struct cpufreq_driver scmi_cpufreq_driver = { .name = "scmi", .flags = CPUFREQ_HAVE_GOVERNOR_PER_POLICY | @@ -261,6 +279,7 @@ static struct cpufreq_driver scmi_cpufreq_driver = { .get = scmi_cpufreq_get_rate, .init = scmi_cpufreq_init, .exit = scmi_cpufreq_exit, + .register_em = scmi_cpufreq_register_em, }; static int scmi_cpufreq_probe(struct scmi_device *sdev) -- cgit v1.2.3 From 275157b367f479334f3e2df7be93a3dd772f359c Mon Sep 17 00:00:00 2001 From: Thara Gopinath Date: Mon, 9 Aug 2021 15:16:01 -0400 Subject: cpufreq: qcom-cpufreq-hw: Add dcvs interrupt support Add interrupt support to notify the kernel of h/w initiated frequency throttling by LMh. Convey this to scheduler via thermal presssure interface. Signed-off-by: Thara Gopinath [Viresh: Added changes for arch_topology.c to fix build errors ] Signed-off-by: Viresh Kumar --- drivers/base/arch_topology.c | 2 + drivers/cpufreq/qcom-cpufreq-hw.c | 147 ++++++++++++++++++++++++++++++++++++++ 2 files changed, 149 insertions(+) (limited to 'drivers/cpufreq') diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c index 921312a8d957..43407665918f 100644 --- a/drivers/base/arch_topology.c +++ b/drivers/base/arch_topology.c @@ -149,6 +149,7 @@ void topology_set_freq_scale(const struct cpumask *cpus, unsigned long cur_freq, } DEFINE_PER_CPU(unsigned long, cpu_scale) = SCHED_CAPACITY_SCALE; +EXPORT_PER_CPU_SYMBOL_GPL(cpu_scale); void topology_set_cpu_scale(unsigned int cpu, unsigned long capacity) { @@ -165,6 +166,7 @@ void topology_set_thermal_pressure(const struct cpumask *cpus, for_each_cpu(cpu, cpus) WRITE_ONCE(per_cpu(thermal_pressure, cpu), th_pressure); } +EXPORT_SYMBOL_GPL(topology_set_thermal_pressure); static ssize_t cpu_capacity_show(struct device *dev, struct device_attribute *attr, diff --git a/drivers/cpufreq/qcom-cpufreq-hw.c b/drivers/cpufreq/qcom-cpufreq-hw.c index c2e71c430fbf..6c2086c6de0c 100644 --- a/drivers/cpufreq/qcom-cpufreq-hw.c +++ b/drivers/cpufreq/qcom-cpufreq-hw.c @@ -7,12 +7,14 @@ #include #include #include +#include #include #include #include #include #include #include +#include #define LUT_MAX_ENTRIES 40U #define LUT_SRC GENMASK(31, 30) @@ -22,10 +24,13 @@ #define CLK_HW_DIV 2 #define LUT_TURBO_IND 1 +#define HZ_PER_KHZ 1000 + struct qcom_cpufreq_soc_data { u32 reg_enable; u32 reg_freq_lut; u32 reg_volt_lut; + u32 reg_current_vote; u32 reg_perf_state; u8 lut_row_size; }; @@ -34,6 +39,16 @@ struct qcom_cpufreq_data { void __iomem *base; struct resource *res; const struct qcom_cpufreq_soc_data *soc_data; + + /* + * Mutex to synchronize between de-init sequence and re-starting LMh + * polling/interrupts + */ + struct mutex throttle_lock; + int throttle_irq; + bool cancel_throttle; + struct delayed_work throttle_work; + struct cpufreq_policy *policy; }; static unsigned long cpu_hw_rate, xo_rate; @@ -251,10 +266,92 @@ static void qcom_get_related_cpus(int index, struct cpumask *m) } } +static unsigned int qcom_lmh_get_throttle_freq(struct qcom_cpufreq_data *data) +{ + unsigned int val = readl_relaxed(data->base + data->soc_data->reg_current_vote); + + return (val & 0x3FF) * 19200; +} + +static void qcom_lmh_dcvs_notify(struct qcom_cpufreq_data *data) +{ + unsigned long max_capacity, capacity, freq_hz, throttled_freq; + struct cpufreq_policy *policy = data->policy; + int cpu = cpumask_first(policy->cpus); + struct device *dev = get_cpu_device(cpu); + struct dev_pm_opp *opp; + unsigned int freq; + + /* + * Get the h/w throttled frequency, normalize it using the + * registered opp table and use it to calculate thermal pressure. + */ + freq = qcom_lmh_get_throttle_freq(data); + freq_hz = freq * HZ_PER_KHZ; + + opp = dev_pm_opp_find_freq_floor(dev, &freq_hz); + if (IS_ERR(opp) && PTR_ERR(opp) == -ERANGE) + dev_pm_opp_find_freq_ceil(dev, &freq_hz); + + throttled_freq = freq_hz / HZ_PER_KHZ; + + /* Update thermal pressure */ + + max_capacity = arch_scale_cpu_capacity(cpu); + capacity = mult_frac(max_capacity, throttled_freq, policy->cpuinfo.max_freq); + + /* Don't pass boost capacity to scheduler */ + if (capacity > max_capacity) + capacity = max_capacity; + + arch_set_thermal_pressure(policy->cpus, max_capacity - capacity); + + /* + * In the unlikely case policy is unregistered do not enable + * polling or h/w interrupt + */ + mutex_lock(&data->throttle_lock); + if (data->cancel_throttle) + goto out; + + /* + * If h/w throttled frequency is higher than what cpufreq has requested + * for, then stop polling and switch back to interrupt mechanism. + */ + if (throttled_freq >= qcom_cpufreq_hw_get(cpu)) + enable_irq(data->throttle_irq); + else + mod_delayed_work(system_highpri_wq, &data->throttle_work, + msecs_to_jiffies(10)); + +out: + mutex_unlock(&data->throttle_lock); +} + +static void qcom_lmh_dcvs_poll(struct work_struct *work) +{ + struct qcom_cpufreq_data *data; + + data = container_of(work, struct qcom_cpufreq_data, throttle_work.work); + qcom_lmh_dcvs_notify(data); +} + +static irqreturn_t qcom_lmh_dcvs_handle_irq(int irq, void *data) +{ + struct qcom_cpufreq_data *c_data = data; + + /* Disable interrupt and enable polling */ + disable_irq_nosync(c_data->throttle_irq); + qcom_lmh_dcvs_notify(c_data); + + return 0; +} + static const struct qcom_cpufreq_soc_data qcom_soc_data = { .reg_enable = 0x0, .reg_freq_lut = 0x110, .reg_volt_lut = 0x114, + .reg_current_vote = 0x704, .reg_perf_state = 0x920, .lut_row_size = 32, }; @@ -274,6 +371,51 @@ static const struct of_device_id qcom_cpufreq_hw_match[] = { }; MODULE_DEVICE_TABLE(of, qcom_cpufreq_hw_match); +static int qcom_cpufreq_hw_lmh_init(struct cpufreq_policy *policy, int index) +{ + struct qcom_cpufreq_data *data = policy->driver_data; + struct platform_device *pdev = cpufreq_get_driver_data(); + char irq_name[15]; + int ret; + + /* + * Look for LMh interrupt. If no interrupt line is specified / + * if there is an error, allow cpufreq to be enabled as usual. + */ + data->throttle_irq = platform_get_irq(pdev, index); + if (data->throttle_irq <= 0) + return data->throttle_irq == -EPROBE_DEFER ? -EPROBE_DEFER : 0; + + data->cancel_throttle = false; + data->policy = policy; + + mutex_init(&data->throttle_lock); + INIT_DEFERRABLE_WORK(&data->throttle_work, qcom_lmh_dcvs_poll); + + snprintf(irq_name, sizeof(irq_name), "dcvsh-irq-%u", policy->cpu); + ret = request_threaded_irq(data->throttle_irq, NULL, qcom_lmh_dcvs_handle_irq, + IRQF_ONESHOT, irq_name, data); + if (ret) { + dev_err(&pdev->dev, "Error registering %s: %d\n", irq_name, ret); + return 0; + } + + return 0; +} + +static void qcom_cpufreq_hw_lmh_exit(struct qcom_cpufreq_data *data) +{ + if (data->throttle_irq <= 0) + return; + + mutex_lock(&data->throttle_lock); + data->cancel_throttle = true; + mutex_unlock(&data->throttle_lock); + + cancel_delayed_work_sync(&data->throttle_work); + free_irq(data->throttle_irq, data); +} + static int qcom_cpufreq_hw_cpu_init(struct cpufreq_policy *policy) { struct platform_device *pdev = cpufreq_get_driver_data(); @@ -368,6 +510,10 @@ static int qcom_cpufreq_hw_cpu_init(struct cpufreq_policy *policy) dev_warn(cpu_dev, "failed to enable boost: %d\n", ret); } + ret = qcom_cpufreq_hw_lmh_init(policy, index); + if (ret) + goto error; + return 0; error: kfree(data); @@ -387,6 +533,7 @@ static int qcom_cpufreq_hw_cpu_exit(struct cpufreq_policy *policy) dev_pm_opp_remove_all_dynamic(cpu_dev); dev_pm_opp_of_cpumask_remove_table(policy->related_cpus); + qcom_cpufreq_hw_lmh_exit(data); kfree(policy->freq_table); kfree(data); iounmap(base); -- cgit v1.2.3 From 5e79d6d9ea00c273f3efbced841212de85a384d1 Mon Sep 17 00:00:00 2001 From: Bjorn Andersson Date: Fri, 20 Aug 2021 14:57:00 -0700 Subject: cpufreq: blocklist more Qualcomm platforms in cpufreq-dt-platdev The Qualcomm sa8155p, sm6350, sm8250 and sm8350 platforms also uses the qcom-cpufreq-hw driver, so add them to the cpufreq-dt-platdev driver's blocklist. Signed-off-by: Bjorn Andersson Signed-off-by: Viresh Kumar --- drivers/cpufreq/cpufreq-dt-platdev.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'drivers/cpufreq') diff --git a/drivers/cpufreq/cpufreq-dt-platdev.c b/drivers/cpufreq/cpufreq-dt-platdev.c index 231e585f6ba2..ca1d103ec449 100644 --- a/drivers/cpufreq/cpufreq-dt-platdev.c +++ b/drivers/cpufreq/cpufreq-dt-platdev.c @@ -137,11 +137,15 @@ static const struct of_device_id blocklist[] __initconst = { { .compatible = "qcom,apq8096", }, { .compatible = "qcom,msm8996", }, { .compatible = "qcom,qcs404", }, + { .compatible = "qcom,sa8155p" }, { .compatible = "qcom,sc7180", }, { .compatible = "qcom,sc7280", }, { .compatible = "qcom,sc8180x", }, { .compatible = "qcom,sdm845", }, + { .compatible = "qcom,sm6350", }, { .compatible = "qcom,sm8150", }, + { .compatible = "qcom,sm8250", }, + { .compatible = "qcom,sm8350", }, { .compatible = "st,stih407", }, { .compatible = "st,stih410", }, -- cgit v1.2.3 From f0712ace7fe0723b40733c3b98591d34c1b0bfb9 Mon Sep 17 00:00:00 2001 From: Taniya Das Date: Mon, 23 Aug 2021 15:45:46 +0530 Subject: cpufreq: qcom-hw: Set dvfs_possible_from_any_cpu cpufreq driver flag As remote cpufreq updates are supported on QCOM platforms, set dvfs_possible_from_any_cpu cpufreq driver flag. Signed-off-by: Taniya Das Signed-off-by: Viresh Kumar --- drivers/cpufreq/qcom-cpufreq-hw.c | 1 + 1 file changed, 1 insertion(+) (limited to 'drivers/cpufreq') diff --git a/drivers/cpufreq/qcom-cpufreq-hw.c b/drivers/cpufreq/qcom-cpufreq-hw.c index 6c2086c6de0c..a2be0df7e174 100644 --- a/drivers/cpufreq/qcom-cpufreq-hw.c +++ b/drivers/cpufreq/qcom-cpufreq-hw.c @@ -490,6 +490,7 @@ static int qcom_cpufreq_hw_cpu_init(struct cpufreq_policy *policy) } policy->driver_data = data; + policy->dvfs_possible_from_any_cpu = true; ret = qcom_cpufreq_hw_read_lut(cpu_dev, policy); if (ret) { -- cgit v1.2.3 From 692a3b9a89947b27fc76d40b2613b33286a1690b Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Wed, 1 Sep 2021 14:41:55 +0530 Subject: cpufreq: acpi: Remove acpi_cpufreq_cpu_ready() The ready() callback was implemented earlier for acpi-cpufreq driver as we wanted to use policy->cpuinfo.max_freq for which the policy was required to be verified. That is no longer the case and we can do the pr_warn() right from ->init() callback now. Remove acpi_cpufreq_cpu_ready(). Signed-off-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/acpi-cpufreq.c | 14 +++----------- 1 file changed, 3 insertions(+), 11 deletions(-) (limited to 'drivers/cpufreq') diff --git a/drivers/cpufreq/acpi-cpufreq.c b/drivers/cpufreq/acpi-cpufreq.c index b49612895c78..28467d83c745 100644 --- a/drivers/cpufreq/acpi-cpufreq.c +++ b/drivers/cpufreq/acpi-cpufreq.c @@ -889,6 +889,9 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy) policy->fast_switch_possible = !acpi_pstate_strict && !(policy_is_shared(policy) && policy->shared_type != CPUFREQ_SHARED_TYPE_ANY); + if (perf->states[0].core_frequency * 1000 != freq_table[0].frequency) + pr_warn(FW_WARN "P-state 0 is not max freq\n"); + return result; err_unreg: @@ -918,16 +921,6 @@ static int acpi_cpufreq_cpu_exit(struct cpufreq_policy *policy) return 0; } -static void acpi_cpufreq_cpu_ready(struct cpufreq_policy *policy) -{ - struct acpi_processor_performance *perf = per_cpu_ptr(acpi_perf_data, - policy->cpu); - unsigned int freq = policy->freq_table[0].frequency; - - if (perf->states[0].core_frequency * 1000 != freq) - pr_warn(FW_WARN "P-state 0 is not max freq\n"); -} - static int acpi_cpufreq_resume(struct cpufreq_policy *policy) { struct acpi_cpufreq_data *data = policy->driver_data; @@ -955,7 +948,6 @@ static struct cpufreq_driver acpi_cpufreq_driver = { .bios_limit = acpi_processor_get_bios_limit, .init = acpi_cpufreq_cpu_init, .exit = acpi_cpufreq_cpu_exit, - .ready = acpi_cpufreq_cpu_ready, .resume = acpi_cpufreq_resume, .name = "acpi-cpufreq", .attr = acpi_cpufreq_attr, -- cgit v1.2.3 From 9ab0a6cb76b998f5f2231e1c428bee3771893002 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Wed, 1 Sep 2021 14:41:56 +0530 Subject: cpufreq: sh: Remove sh_cpufreq_cpu_ready() The ->ready() callback is going away and since we don't do any important stuff in sh_cpufreq_cpu_ready(), remove it. Signed-off-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/sh-cpufreq.c | 11 ----------- 1 file changed, 11 deletions(-) (limited to 'drivers/cpufreq') diff --git a/drivers/cpufreq/sh-cpufreq.c b/drivers/cpufreq/sh-cpufreq.c index 1a251e635ebd..b8704232c27b 100644 --- a/drivers/cpufreq/sh-cpufreq.c +++ b/drivers/cpufreq/sh-cpufreq.c @@ -145,16 +145,6 @@ static int sh_cpufreq_cpu_exit(struct cpufreq_policy *policy) return 0; } -static void sh_cpufreq_cpu_ready(struct cpufreq_policy *policy) -{ - struct device *dev = get_cpu_device(policy->cpu); - - dev_info(dev, "CPU Frequencies - Minimum %u.%03u MHz, " - "Maximum %u.%03u MHz.\n", - policy->min / 1000, policy->min % 1000, - policy->max / 1000, policy->max % 1000); -} - static struct cpufreq_driver sh_cpufreq_driver = { .name = "sh", .flags = CPUFREQ_NO_AUTO_DYNAMIC_SWITCHING, @@ -163,7 +153,6 @@ static struct cpufreq_driver sh_cpufreq_driver = { .verify = sh_cpufreq_verify, .init = sh_cpufreq_cpu_init, .exit = sh_cpufreq_cpu_exit, - .ready = sh_cpufreq_cpu_ready, .attr = cpufreq_generic_attr, }; -- cgit v1.2.3 From 4bf8e582119ed9767f907abb6dc62ef9dddf10df Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Wed, 1 Sep 2021 14:41:57 +0530 Subject: cpufreq: Remove ready() callback This isn't used anymore, get rid of it. Signed-off-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- Documentation/cpu-freq/cpu-drivers.rst | 3 --- Documentation/translations/zh_CN/cpu-freq/cpu-drivers.rst | 2 -- drivers/cpufreq/cpufreq.c | 4 ---- include/linux/cpufreq.h | 3 --- 4 files changed, 12 deletions(-) (limited to 'drivers/cpufreq') diff --git a/Documentation/cpu-freq/cpu-drivers.rst b/Documentation/cpu-freq/cpu-drivers.rst index d84ededb66f9..3b32336a7803 100644 --- a/Documentation/cpu-freq/cpu-drivers.rst +++ b/Documentation/cpu-freq/cpu-drivers.rst @@ -75,9 +75,6 @@ And optionally .resume - A pointer to a per-policy resume function which is called with interrupts disabled and _before_ the governor is started again. - .ready - A pointer to a per-policy ready function which is called after - the policy is fully initialized. - .attr - A pointer to a NULL-terminated list of "struct freq_attr" which allow to export values to sysfs. diff --git a/Documentation/translations/zh_CN/cpu-freq/cpu-drivers.rst b/Documentation/translations/zh_CN/cpu-freq/cpu-drivers.rst index 5ae9cfa2ec55..334f30ae198b 100644 --- a/Documentation/translations/zh_CN/cpu-freq/cpu-drivers.rst +++ b/Documentation/translations/zh_CN/cpu-freq/cpu-drivers.rst @@ -80,8 +80,6 @@ CPUfreq核心层注册一个cpufreq_driver结构体。 .resume - 一个指向per-policy恢复函数的指针，该函数在关中断且在调节器再一次开始前被 调用。 - .ready - 一个指向per-policy准备函数的指针，该函数在策略完全初始化之后被调用。 - .attr - 一个指向NULL结尾的"struct freq_attr"列表的指针，该函数允许导出值到 sysfs。 diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 7d5f170ecad1..5782b15a8caa 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -1517,10 +1517,6 @@ static int cpufreq_online(unsigned int cpu) kobject_uevent(&policy->kobj, KOBJ_ADD); - /* Callback for handling stuff after policy is ready */ - if (cpufreq_driver->ready) - cpufreq_driver->ready(policy); - if (cpufreq_thermal_control_enabled(cpufreq_driver)) policy->cdev = of_cpufreq_cooling_register(policy); diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index c65a1d7385f8..fe6acc04e5e5 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -367,9 +367,6 @@ struct cpufreq_driver { int (*suspend)(struct cpufreq_policy *policy); int (*resume)(struct cpufreq_policy *policy); - /* Will be called after the driver is fully initialized */ - void (*ready)(struct cpufreq_policy *policy); - struct freq_attr **attr; /* platform specific boost support code */ -- cgit v1.2.3 From 4855e26bcf4d28956f3e33231b961610a0d4a72d Mon Sep 17 00:00:00 2001 From: "Hector.Yuan" Date: Fri, 3 Sep 2021 16:39:24 +0800 Subject: cpufreq: mediatek-hw: Add support for CPUFREQ HW Introduce cpufreq HW driver which can support CPU frequency adjust in MT6779 platform. Signed-off-by: Hector.Yuan [ Viresh: Massaged the patch and cleaned some stuff. ] Signed-off-by: Viresh Kumar --- drivers/cpufreq/Kconfig.arm | 12 ++ drivers/cpufreq/Makefile | 1 + drivers/cpufreq/mediatek-cpufreq-hw.c | 308 ++++++++++++++++++++++++++++++++++ 3 files changed, 321 insertions(+) create mode 100644 drivers/cpufreq/mediatek-cpufreq-hw.c (limited to 'drivers/cpufreq') diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm index a5c5f70acfc9..954749afb5fe 100644 --- a/drivers/cpufreq/Kconfig.arm +++ b/drivers/cpufreq/Kconfig.arm @@ -133,6 +133,18 @@ config ARM_MEDIATEK_CPUFREQ help This adds the CPUFreq driver support for MediaTek SoCs. +config ARM_MEDIATEK_CPUFREQ_HW + tristate "MediaTek CPUFreq HW driver" + depends on ARCH_MEDIATEK || COMPILE_TEST + default m + help + Support for the CPUFreq HW driver. + Some MediaTek chipsets have a HW engine to offload the steps + necessary for changing the frequency of the CPUs. Firmware loaded + in this engine exposes a programming interface to the OS. + The driver implements the cpufreq interface for this HW engine. + Say Y if you want to support CPUFreq HW. + config ARM_OMAP2PLUS_CPUFREQ bool "TI OMAP2+" depends on ARCH_OMAP2PLUS diff --git a/drivers/cpufreq/Makefile b/drivers/cpufreq/Makefile index 27d3bd7ea9d4..48ee5859030c 100644 --- a/drivers/cpufreq/Makefile +++ b/drivers/cpufreq/Makefile @@ -56,6 +56,7 @@ obj-$(CONFIG_ARM_IMX6Q_CPUFREQ) += imx6q-cpufreq.o obj-$(CONFIG_ARM_IMX_CPUFREQ_DT) += imx-cpufreq-dt.o obj-$(CONFIG_ARM_KIRKWOOD_CPUFREQ) += kirkwood-cpufreq.o obj-$(CONFIG_ARM_MEDIATEK_CPUFREQ) += mediatek-cpufreq.o +obj-$(CONFIG_ARM_MEDIATEK_CPUFREQ_HW) += mediatek-cpufreq-hw.o obj-$(CONFIG_MACH_MVEBU_V7) += mvebu-cpufreq.o obj-$(CONFIG_ARM_OMAP2PLUS_CPUFREQ) += omap-cpufreq.o obj-$(CONFIG_ARM_PXA2xx_CPUFREQ) += pxa2xx-cpufreq.o diff --git a/drivers/cpufreq/mediatek-cpufreq-hw.c b/drivers/cpufreq/mediatek-cpufreq-hw.c new file mode 100644 index 000000000000..0cf18dd46b92 --- /dev/null +++ b/drivers/cpufreq/mediatek-cpufreq-hw.c @@ -0,0 +1,308 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2020 MediaTek Inc. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define LUT_MAX_ENTRIES 32U +#define LUT_FREQ GENMASK(11, 0) +#define LUT_ROW_SIZE 0x4 +#define CPUFREQ_HW_STATUS BIT(0) +#define SVS_HW_STATUS BIT(1) +#define POLL_USEC 1000 +#define TIMEOUT_USEC 300000 + +enum { + REG_FREQ_LUT_TABLE, + REG_FREQ_ENABLE, + REG_FREQ_PERF_STATE, + REG_FREQ_HW_STATE, + REG_EM_POWER_TBL, + REG_FREQ_LATENCY, + + REG_ARRAY_SIZE, +}; + +struct mtk_cpufreq_data { + struct cpufreq_frequency_table *table; + void __iomem *reg_bases[REG_ARRAY_SIZE]; + int nr_opp; +}; + +static const u16 cpufreq_mtk_offsets[REG_ARRAY_SIZE] = { + [REG_FREQ_LUT_TABLE] = 0x0, + [REG_FREQ_ENABLE] = 0x84, + [REG_FREQ_PERF_STATE] = 0x88, + [REG_FREQ_HW_STATE] = 0x8c, + [REG_EM_POWER_TBL] = 0x90, + [REG_FREQ_LATENCY] = 0x110, +}; + +static int __maybe_unused +mtk_cpufreq_get_cpu_power(unsigned long *mW, + unsigned long *KHz, struct device *cpu_dev) +{ + struct mtk_cpufreq_data *data; + struct cpufreq_policy *policy; + int i; + + policy = cpufreq_cpu_get_raw(cpu_dev->id); + if (!policy) + return 0; + + data = policy->driver_data; + + for (i = 0; i < data->nr_opp; i++) { + if (data->table[i].frequency < *KHz) + break; + } + i--; + + *KHz = data->table[i].frequency; + *mW = readl_relaxed(data->reg_bases[REG_EM_POWER_TBL] + + i * LUT_ROW_SIZE) / 1000; + + return 0; +} + +static int mtk_cpufreq_hw_target_index(struct cpufreq_policy *policy, + unsigned int index) +{ + struct mtk_cpufreq_data *data = policy->driver_data; + + writel_relaxed(index, data->reg_bases[REG_FREQ_PERF_STATE]); + + return 0; +} + +static unsigned int mtk_cpufreq_hw_get(unsigned int cpu) +{ + struct mtk_cpufreq_data *data; + struct cpufreq_policy *policy; + unsigned int index; + + policy = cpufreq_cpu_get_raw(cpu); + if (!policy) + return 0; + + data = policy->driver_data; + + index = readl_relaxed(data->reg_bases[REG_FREQ_PERF_STATE]); + index = min(index, LUT_MAX_ENTRIES - 1); + + return data->table[index].frequency; +} + +static unsigned int mtk_cpufreq_hw_fast_switch(struct cpufreq_policy *policy, + unsigned int target_freq) +{ + struct mtk_cpufreq_data *data = policy->driver_data; + unsigned int index; + + index = cpufreq_table_find_index_dl(policy, target_freq); + + writel_relaxed(index, data->reg_bases[REG_FREQ_PERF_STATE]); + + return policy->freq_table[index].frequency; +} + +static int mtk_cpu_create_freq_table(struct platform_device *pdev, + struct mtk_cpufreq_data *data) +{ + struct device *dev = &pdev->dev; + u32 temp, i, freq, prev_freq = 0; + void __iomem *base_table; + + data->table = devm_kcalloc(dev, LUT_MAX_ENTRIES + 1, + sizeof(*data->table), GFP_KERNEL); + if (!data->table) + return -ENOMEM; + + base_table = data->reg_bases[REG_FREQ_LUT_TABLE]; + + for (i = 0; i < LUT_MAX_ENTRIES; i++) { + temp = readl_relaxed(base_table + (i * LUT_ROW_SIZE)); + freq = FIELD_GET(LUT_FREQ, temp) * 1000; + + if (freq == prev_freq) + break; + + data->table[i].frequency = freq; + + dev_dbg(dev, "index=%d freq=%d\n", i, data->table[i].frequency); + + prev_freq = freq; + } + + data->table[i].frequency = CPUFREQ_TABLE_END; + data->nr_opp = i; + + return 0; +} + +static int mtk_cpu_resources_init(struct platform_device *pdev, + struct cpufreq_policy *policy, + const u16 *offsets) +{ + struct mtk_cpufreq_data *data; + struct device *dev = &pdev->dev; + void __iomem *base; + int ret, i; + int index; + + data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL); + if (!data) + return -ENOMEM; + + index = of_perf_domain_get_sharing_cpumask(policy->cpu, "performance-domains", + "#performance-domain-cells", + policy->cpus); + if (index < 0) + return index; + + base = devm_platform_ioremap_resource(pdev, index); + if (IS_ERR(base)) + return PTR_ERR(base); + + for (i = REG_FREQ_LUT_TABLE; i < REG_ARRAY_SIZE; i++) + data->reg_bases[i] = base + offsets[i]; + + ret = mtk_cpu_create_freq_table(pdev, data); + if (ret) { + dev_info(dev, "Domain-%d failed to create freq table\n", index); + return ret; + } + + policy->freq_table = data->table; + policy->driver_data = data; + + return 0; +} + +static int mtk_cpufreq_hw_cpu_init(struct cpufreq_policy *policy) +{ + struct platform_device *pdev = cpufreq_get_driver_data(); + int sig, pwr_hw = CPUFREQ_HW_STATUS | SVS_HW_STATUS; + struct mtk_cpufreq_data *data; + unsigned int latency; + int ret; + + /* Get the bases of cpufreq for domains */ + ret = mtk_cpu_resources_init(pdev, policy, platform_get_drvdata(pdev)); + if (ret) { + dev_info(&pdev->dev, "CPUFreq resource init failed\n"); + return ret; + } + + data = policy->driver_data; + + latency = readl_relaxed(data->reg_bases[REG_FREQ_LATENCY]) * 1000; + if (!latency) + latency = CPUFREQ_ETERNAL; + + policy->cpuinfo.transition_latency = latency; + policy->fast_switch_possible = true; + + /* HW should be in enabled state to proceed now */ + writel_relaxed(0x1, data->reg_bases[REG_FREQ_ENABLE]); + if (readl_poll_timeout(data->reg_bases[REG_FREQ_HW_STATE], sig, + (sig & pwr_hw) == pwr_hw, POLL_USEC, + TIMEOUT_USEC)) { + if (!(sig & CPUFREQ_HW_STATUS)) { + pr_info("cpufreq hardware of CPU%d is not enabled\n", + policy->cpu); + return -ENODEV; + } + + pr_info("SVS of CPU%d is not enabled\n", policy->cpu); + } + + return 0; +} + +static int mtk_cpufreq_hw_cpu_exit(struct cpufreq_policy *policy) +{ + struct mtk_cpufreq_data *data = policy->driver_data; + + /* HW should be in paused state now */ + writel_relaxed(0x0, data->reg_bases[REG_FREQ_ENABLE]); + + return 0; +} + +static void mtk_cpufreq_register_em(struct cpufreq_policy *policy) +{ + struct em_data_callback em_cb = EM_DATA_CB(mtk_cpufreq_get_cpu_power); + struct mtk_cpufreq_data *data = policy->driver_data; + + em_dev_register_perf_domain(get_cpu_device(policy->cpu), data->nr_opp, + &em_cb, policy->cpus, true); +} + +static struct cpufreq_driver cpufreq_mtk_hw_driver = { + .flags = CPUFREQ_NEED_INITIAL_FREQ_CHECK | + CPUFREQ_HAVE_GOVERNOR_PER_POLICY | + CPUFREQ_IS_COOLING_DEV, + .verify = cpufreq_generic_frequency_table_verify, + .target_index = mtk_cpufreq_hw_target_index, + .get = mtk_cpufreq_hw_get, + .init = mtk_cpufreq_hw_cpu_init, + .exit = mtk_cpufreq_hw_cpu_exit, + .register_em = mtk_cpufreq_register_em, + .fast_switch = mtk_cpufreq_hw_fast_switch, + .name = "mtk-cpufreq-hw", + .attr = cpufreq_generic_attr, +}; + +static int mtk_cpufreq_hw_driver_probe(struct platform_device *pdev) +{ + const void *data; + int ret; + + data = of_device_get_match_data(&pdev->dev); + if (!data) + return -EINVAL; + + platform_set_drvdata(pdev, (void *) data); + cpufreq_mtk_hw_driver.driver_data = pdev; + + ret = cpufreq_register_driver(&cpufreq_mtk_hw_driver); + if (ret) + dev_err(&pdev->dev, "CPUFreq HW driver failed to register\n"); + + return ret; +} + +static int mtk_cpufreq_hw_driver_remove(struct platform_device *pdev) +{ + return cpufreq_unregister_driver(&cpufreq_mtk_hw_driver); +} + +static const struct of_device_id mtk_cpufreq_hw_match[] = { + { .compatible = "mediatek,cpufreq-hw", .data = &cpufreq_mtk_offsets }, + {} +}; + +static struct platform_driver mtk_cpufreq_hw_driver = { + .probe = mtk_cpufreq_hw_driver_probe, + .remove = mtk_cpufreq_hw_driver_remove, + .driver = { + .name = "mtk-cpufreq-hw", + .of_match_table = mtk_cpufreq_hw_match, + }, +}; +module_platform_driver(mtk_cpufreq_hw_driver); + +MODULE_AUTHOR("Hector Yuan "); +MODULE_DESCRIPTION("Mediatek cpufreq-hw driver"); +MODULE_LICENSE("GPL v2"); -- cgit v1.2.3 From dd7c46d6e58e8737b0ac3ba21e8584c2632dba65 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Tue, 7 Sep 2021 15:32:48 +0200 Subject: Revert "cpufreq: intel_pstate: Process HWP Guaranteed change notification" Revert commit d0e936adbd22 ("cpufreq: intel_pstate: Process HWP Guaranteed change notification"), because it causes a NULL pointer dereference to occur on Lenovo X1 gen9 laptops due to an HWP guaranteed performance change interrupt arriving prematurely. This feature will be revisited in the next cycle. Reported-by: Jens Axboe Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/intel_pstate.c | 39 --------------------------------------- 1 file changed, 39 deletions(-) (limited to 'drivers/cpufreq') diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index b4ffe6c8a0d0..2d83a9f9651b 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -32,7 +32,6 @@ #include #include #include -#include "../drivers/thermal/intel/thermal_interrupt.h" #define INTEL_PSTATE_SAMPLING_INTERVAL (10 * NSEC_PER_MSEC) @@ -220,7 +219,6 @@ struct global_params { * @sched_flags: Store scheduler flags for possible cross CPU update * @hwp_boost_min: Last HWP boosted min performance * @suspended: Whether or not the driver has been suspended. - * @hwp_notify_work: workqueue for HWP notifications. * * This structure stores per CPU instance data for all CPUs. */ @@ -259,7 +257,6 @@ struct cpudata { unsigned int sched_flags; u32 hwp_boost_min; bool suspended; - struct delayed_work hwp_notify_work; }; static struct cpudata **all_cpu_data; @@ -1628,40 +1625,6 @@ static void intel_pstate_sysfs_hide_hwp_dynamic_boost(void) /************************** sysfs end ************************/ -static void intel_pstate_notify_work(struct work_struct *work) -{ - mutex_lock(&intel_pstate_driver_lock); - cpufreq_update_policy(smp_processor_id()); - wrmsrl(MSR_HWP_STATUS, 0); - mutex_unlock(&intel_pstate_driver_lock); -} - -void notify_hwp_interrupt(void) -{ - unsigned int this_cpu = smp_processor_id(); - struct cpudata *cpudata; - u64 value; - - if (!hwp_active || !boot_cpu_has(X86_FEATURE_HWP_NOTIFY)) - return; - - rdmsrl(MSR_HWP_STATUS, value); - if (!(value & 0x01)) - return; - - cpudata = all_cpu_data[this_cpu]; - schedule_delayed_work_on(this_cpu, &cpudata->hwp_notify_work, msecs_to_jiffies(10)); -} - -static void intel_pstate_enable_hwp_interrupt(struct cpudata *cpudata) -{ - /* Enable HWP notification interrupt for guaranteed performance change */ - if (boot_cpu_has(X86_FEATURE_HWP_NOTIFY)) { - INIT_DELAYED_WORK(&cpudata->hwp_notify_work, intel_pstate_notify_work); - wrmsrl_on_cpu(cpudata->cpu, MSR_HWP_INTERRUPT, 0x01); - } -} - static void intel_pstate_hwp_enable(struct cpudata *cpudata) { /* First disable HWP notification interrupt as we don't process them */ @@ -1671,8 +1634,6 @@ static void intel_pstate_hwp_enable(struct cpudata *cpudata) wrmsrl_on_cpu(cpudata->cpu, MSR_PM_ENABLE, 0x1); if (cpudata->epp_default == -EINVAL) cpudata->epp_default = intel_pstate_get_epp(cpudata, 0); - - intel_pstate_enable_hwp_interrupt(cpudata); } static int atom_get_min_pstate(void) -- cgit v1.2.3