Merge tag 'pm-5.1-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull power management updates from Rafael Wysocki:
 "These are PM-runtime framework changes to use ktime instead of jiffies
  for accounting, new PM core flag to mark devices that don't need any
  form of power management, cpuidle updates including driver API
  documentation and a new governor, cpufreq updates including a new
  driver for Armada 8K, thermal cleanups and more, some energy-aware
  scheduling (EAS) enabling changes, new chips support in the intel_idle
  and RAPL drivers and assorted cleanups in some other places.

  Specifics:

   - Update the PM-runtime framework to use ktime instead of jiffies for
     accounting (Thara Gopinath, Vincent Guittot)

   - Optimize the autosuspend code in the PM-runtime framework somewhat
     (Ladislav Michl)

   - Add a PM core flag to mark devices that don't need any form of
     power management (Sudeep Holla)

   - Introduce driver API documentation for cpuidle and add a new
     cpuidle governor for tickless systems (Rafael Wysocki)

   - Add Jacobsville support to the intel_idle driver (Zhang Rui)

   - Clean up a cpuidle core header file and the cpuidle-dt and ACPI
     processor-idle drivers (Yangtao Li, Joseph Lo, Yazen Ghannam)

   - Add new cpufreq driver for Armada 8K (Gregory Clement)

   - Fix and clean up cpufreq core (Rafael Wysocki, Viresh Kumar, Amit
     Kucheria)

   - Add support for light-weight tear-down and bring-up of CPUs to the
     cpufreq core and use it in the cpufreq-dt driver (Viresh Kumar)

   - Fix cpu_cooling Kconfig dependencies, add support for CPU cooling
     auto-registration to the cpufreq core and use it in multiple
     cpufreq drivers (Amit Kucheria)

   - Fix some minor issues and do some cleanups in the davinci,
     e_powersaver, ap806, s5pv210, qcom and kryo cpufreq drivers
     (Bartosz Golaszewski, Gustavo Silva, Julia Lawall, Paweł Chmiel,
     Taniya Das, Viresh Kumar)

   - Add a Hisilicon CPPC quirk to the cppc_cpufreq driver (Xiongfeng
     Wang)

   - Clean up the intel_pstate and acpi-cpufreq drivers (Erwan Velu,
     Rafael Wysocki)

   - Clean up multiple cpufreq drivers (Yangtao Li)

   - Update cpufreq-related MAINTAINERS entries (Baruch Siach, Lukas
     Bulwahn)

   - Add support for exposing the Energy Model via debugfs and make
     multiple cpufreq drivers register an Energy Model to support
     energy-aware scheduling (Quentin Perret, Dietmar Eggemann, Matthias
     Kaehlcke)

   - Add Ice Lake mobile and Jacobsville support to the Intel RAPL
     power-capping driver (Gayatri Kammela, Zhang Rui)

   - Add a power estimation helper to the operating performance points
     (OPP) framework and clean up a core function in it (Quentin Perret,
     Viresh Kumar)

   - Make minor improvements in the generic power domains (genpd), OPP
     and system suspend frameworks and in the PM core (Aditya Pakki,
     Douglas Anderson, Greg Kroah-Hartman, Rafael Wysocki, Yangtao Li)"

* tag 'pm-5.1-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: (80 commits)
  cpufreq: kryo: Release OPP tables on module removal
  cpufreq: ap806: add missing of_node_put after of_device_is_available
  cpufreq: acpi-cpufreq: Report if CPU doesn't support boost technologies
  cpufreq: Pass updated policy to driver ->setpolicy() callback
  cpufreq: Fix two debug messages in cpufreq_set_policy()
  cpufreq: Reorder and simplify cpufreq_update_policy()
  cpufreq: Add kerneldoc comments for two core functions
  PM / core: Add support to skip power management in device/driver model
  cpufreq: intel_pstate: Rework iowait boosting to be less aggressive
  cpufreq: intel_pstate: Eliminate intel_pstate_get_base_pstate()
  cpufreq: intel_pstate: Avoid redundant initialization of local vars
  powercap/intel_rapl: add Ice Lake mobile
  ACPI / processor: Set P_LVL{2,3} idle state descriptions
  cpufreq / cppc: Work around for Hisilicon CPPC cpufreq
  ACPI / CPPC: Add a helper to get desired performance
  cpufreq: davinci: move configuration to include/linux/platform_data
  cpufreq: speedstep: convert BUG() to BUG_ON()
  cpufreq: powernv: fix missing check of return value in init_powernv_pstates()
  cpufreq: longhaul: remove unneeded semicolon
  cpufreq: pcc-cpufreq: remove unneeded semicolon
  ..

1 files changed, 42 insertions, 11 deletions

diff --git a/drivers/cpufreq/qcom-cpufreq-hw.c b/drivers/cpufreq/qcom-cpufreq-hw.c
index d83939a1b3d4..4b0b50403901 100644
--- a/drivers/cpufreq/qcom-cpufreq-hw.c
+++ b/drivers/cpufreq/qcom-cpufreq-hw.c
@@ -10,18 +10,21 @@
 #include <linux/module.h>
 #include <linux/of_address.h>
 #include <linux/of_platform.h>
+#include <linux/pm_opp.h>
 #include <linux/slab.h>
 
 #define LUT_MAX_ENTRIES                 40U
 #define LUT_SRC                         GENMASK(31, 30)
 #define LUT_L_VAL                       GENMASK(7, 0)
 #define LUT_CORE_COUNT                  GENMASK(18, 16)
+#define LUT_VOLT                        GENMASK(11, 0)
 #define LUT_ROW_SIZE                    32
 #define CLK_HW_DIV                      2
 
 /* Register offsets */
 #define REG_ENABLE                      0x0
-#define REG_LUT_TABLE                   0x110
+#define REG_FREQ_LUT                    0x110
+#define REG_VOLT_LUT                    0x114
 #define REG_PERF_STATE                  0x920
 
 static unsigned long cpu_hw_rate, xo_rate;
@@ -70,11 +73,12 @@ static unsigned int qcom_cpufreq_hw_fast_switch(struct cpufreq_policy *policy,
         return policy->freq_table[index].frequency;
 }
 
-static int qcom_cpufreq_hw_read_lut(struct device *dev,
+static int qcom_cpufreq_hw_read_lut(struct device *cpu_dev,
                                     struct cpufreq_policy *policy,
                                     void __iomem *base)
 {
         u32 data, src, lval, i, core_count, prev_cc = 0, prev_freq = 0, freq;
+        u32 volt;
         unsigned int max_cores = cpumask_weight(policy->cpus);
         struct cpufreq_frequency_table  *table;
 
@@ -83,23 +87,28 @@ static int qcom_cpufreq_hw_read_lut(struct device *dev,
                 return -ENOMEM;
 
         for (i = 0; i < LUT_MAX_ENTRIES; i++) {
-                data = readl_relaxed(base + REG_LUT_TABLE + i * LUT_ROW_SIZE);
+                data = readl_relaxed(base + REG_FREQ_LUT +
+                                      i * LUT_ROW_SIZE);
                 src = FIELD_GET(LUT_SRC, data);
                 lval = FIELD_GET(LUT_L_VAL, data);
                 core_count = FIELD_GET(LUT_CORE_COUNT, data);
 
+                data = readl_relaxed(base + REG_VOLT_LUT +
+                                      i * LUT_ROW_SIZE);
+                volt = FIELD_GET(LUT_VOLT, data) * 1000;
+
                 if (src)
                         freq = xo_rate * lval / 1000;
                 else
                         freq = cpu_hw_rate / 1000;
 
-                /* Ignore boosts in the middle of the table */
-                if (core_count != max_cores) {
-                        table[i].frequency = CPUFREQ_ENTRY_INVALID;
-                } else {
+                if (freq != prev_freq && core_count == max_cores) {
                         table[i].frequency = freq;
-                        dev_dbg(dev, "index=%d freq=%d, core_count %d\n", i,
+                        dev_pm_opp_add(cpu_dev, freq * 1000, volt);
+                        dev_dbg(cpu_dev, "index=%d freq=%d, core_count %d\n", i,
                                 freq, core_count);
+                } else {
+                        table[i].frequency = CPUFREQ_ENTRY_INVALID;
                 }
 
                 /*
@@ -116,6 +125,7 @@ static int qcom_cpufreq_hw_read_lut(struct device *dev,
                         if (prev_cc != max_cores) {
                                 prev->frequency = prev_freq;
                                 prev->flags = CPUFREQ_BOOST_FREQ;
+                                dev_pm_opp_add(cpu_dev, prev_freq * 1000, volt);
                         }
 
                         break;
@@ -127,6 +137,7 @@ static int qcom_cpufreq_hw_read_lut(struct device *dev,
 
         table[i].frequency = CPUFREQ_TABLE_END;
         policy->freq_table = table;
+        dev_pm_opp_set_sharing_cpus(cpu_dev, policy->cpus);
 
         return 0;
 }
@@ -159,10 +170,18 @@ static int qcom_cpufreq_hw_cpu_init(struct cpufreq_policy *policy)
         struct device *dev = &global_pdev->dev;
         struct of_phandle_args args;
         struct device_node *cpu_np;
+        struct device *cpu_dev;
         struct resource *res;
         void __iomem *base;
         int ret, index;
 
+        cpu_dev = get_cpu_device(policy->cpu);
+        if (!cpu_dev) {
+                pr_err("%s: failed to get cpu%d device\n", __func__,
+                       policy->cpu);
+                return -ENODEV;
+        }
+
         cpu_np = of_cpu_device_node_get(policy->cpu);
         if (!cpu_np)
                 return -EINVAL;
@@ -199,12 +218,21 @@ static int qcom_cpufreq_hw_cpu_init(struct cpufreq_policy *policy)
 
         policy->driver_data = base + REG_PERF_STATE;
 
-        ret = qcom_cpufreq_hw_read_lut(dev, policy, base);
+        ret = qcom_cpufreq_hw_read_lut(cpu_dev, policy, base);
         if (ret) {
                 dev_err(dev, "Domain-%d failed to read LUT\n", index);
                 goto error;
         }
 
+        ret = dev_pm_opp_get_opp_count(cpu_dev);
+        if (ret <= 0) {
+                dev_err(cpu_dev, "Failed to add OPPs\n");
+                ret = -ENODEV;
+                goto error;
+        }
+
+        dev_pm_opp_of_register_em(policy->cpus);
+
         policy->fast_switch_possible = true;
 
         return 0;
@@ -215,8 +243,10 @@ error:
 
 static int qcom_cpufreq_hw_cpu_exit(struct cpufreq_policy *policy)
 {
+        struct device *cpu_dev = get_cpu_device(policy->cpu);
         void __iomem *base = policy->driver_data - REG_PERF_STATE;
 
+        dev_pm_opp_remove_all_dynamic(cpu_dev);
         kfree(policy->freq_table);
         devm_iounmap(&global_pdev->dev, base);
 
@@ -231,7 +261,8 @@ static struct freq_attr *qcom_cpufreq_hw_attr[] = {
 
 static struct cpufreq_driver cpufreq_qcom_hw_driver = {
         .flags          = CPUFREQ_STICKY | CPUFREQ_NEED_INITIAL_FREQ_CHECK |
-                          CPUFREQ_HAVE_GOVERNOR_PER_POLICY,
+                          CPUFREQ_HAVE_GOVERNOR_PER_POLICY |
+                          CPUFREQ_IS_COOLING_DEV,
         .verify         = cpufreq_generic_frequency_table_verify,
         .target_index   = qcom_cpufreq_hw_target_index,
         .get            = qcom_cpufreq_hw_get,
@@ -296,7 +327,7 @@ static int __init qcom_cpufreq_hw_init(void)
 {
         return platform_driver_register(&qcom_cpufreq_hw_driver);
 }
-subsys_initcall(qcom_cpufreq_hw_init);
+device_initcall(qcom_cpufreq_hw_init);
 
 static void __exit qcom_cpufreq_hw_exit(void)
 {