diff --git a/Documentation/devicetree/bindings/arm/marvell/armada-37xx.txt b/Documentation/devicetree/bindings/arm/marvell/armada-37xx.txt index 35c3c3460d17..eddde4faef01 100644 --- a/Documentation/devicetree/bindings/arm/marvell/armada-37xx.txt +++ b/Documentation/devicetree/bindings/arm/marvell/armada-37xx.txt @@ -33,3 +33,18 @@ nb_pm: syscon@14000 { compatible = "marvell,armada-3700-nb-pm", "syscon"; reg = <0x14000 0x60>; } + +AVS +--- + +For AVS an other component is needed: + +Required properties: +- compatible : should contain "marvell,armada-3700-avs", "syscon"; +- reg : the register start and length for the AVS + +Example: +avs: avs@11500 { + compatible = "marvell,armada-3700-avs", "syscon"; + reg = <0x11500 0x40>; +} diff --git a/Documentation/trace/events-power.rst b/Documentation/trace/events-power.rst index a77daca75e30..2ef318962e29 100644 --- a/Documentation/trace/events-power.rst +++ b/Documentation/trace/events-power.rst @@ -27,6 +27,7 @@ cpufreq. cpu_idle "state=%lu cpu_id=%lu" cpu_frequency "state=%lu cpu_id=%lu" + cpu_frequency_limits "min=%lu max=%lu cpu_id=%lu" A suspend event is used to indicate the system going in and out of the suspend mode: diff --git a/drivers/cpufreq/armada-37xx-cpufreq.c b/drivers/cpufreq/armada-37xx-cpufreq.c index 739da90ff3f6..75491fc841a6 100644 --- a/drivers/cpufreq/armada-37xx-cpufreq.c +++ b/drivers/cpufreq/armada-37xx-cpufreq.c @@ -51,6 +51,16 @@ #define ARMADA_37XX_DVFS_LOAD_2 2 #define ARMADA_37XX_DVFS_LOAD_3 3 +/* AVS register set */ +#define ARMADA_37XX_AVS_CTL0 0x0 +#define ARMADA_37XX_AVS_ENABLE BIT(30) +#define ARMADA_37XX_AVS_HIGH_VDD_LIMIT 16 +#define ARMADA_37XX_AVS_LOW_VDD_LIMIT 22 +#define ARMADA_37XX_AVS_VDD_MASK 0x3F +#define ARMADA_37XX_AVS_CTL2 0x8 +#define ARMADA_37XX_AVS_LOW_VDD_EN BIT(6) +#define ARMADA_37XX_AVS_VSET(x) (0x1C + 4 * (x)) + /* * On Armada 37xx the Power management manages 4 level of CPU load, * each level can be associated with a CPU clock source, a CPU @@ -58,6 +68,17 @@ */ #define LOAD_LEVEL_NR 4 +#define MIN_VOLT_MV 1000 + +/* AVS value for the corresponding voltage (in mV) */ +static int avs_map[] = { + 747, 758, 770, 782, 793, 805, 817, 828, 840, 852, 863, 875, 887, 898, + 910, 922, 933, 945, 957, 968, 980, 992, 1003, 1015, 1027, 1038, 1050, + 1062, 1073, 1085, 1097, 1108, 1120, 1132, 1143, 1155, 1167, 1178, 1190, + 1202, 1213, 1225, 1237, 1248, 1260, 1272, 1283, 1295, 1307, 1318, 1330, + 1342 +}; + struct armada37xx_cpufreq_state { struct regmap *regmap; u32 nb_l0l1; @@ -71,6 +92,7 @@ static struct armada37xx_cpufreq_state *armada37xx_cpufreq_state; struct armada_37xx_dvfs { u32 cpu_freq_max; u8 divider[LOAD_LEVEL_NR]; + u32 avs[LOAD_LEVEL_NR]; }; static struct armada_37xx_dvfs armada_37xx_dvfs[] = { @@ -148,6 +170,128 @@ static void __init armada37xx_cpufreq_dvfs_setup(struct regmap *base, clk_set_parent(clk, parent); } +/* + * Find out the armada 37x supported AVS value whose voltage value is + * the round-up closest to the target voltage value. + */ +static u32 armada_37xx_avs_val_match(int target_vm) +{ + u32 avs; + + /* Find out the round-up closest supported voltage value */ + for (avs = 0; avs < ARRAY_SIZE(avs_map); avs++) + if (avs_map[avs] >= target_vm) + break; + + /* + * If all supported voltages are smaller than target one, + * choose the largest supported voltage + */ + if (avs == ARRAY_SIZE(avs_map)) + avs = ARRAY_SIZE(avs_map) - 1; + + return avs; +} + +/* + * For Armada 37xx soc, L0(VSET0) VDD AVS value is set to SVC revision + * value or a default value when SVC is not supported. + * - L0 can be read out from the register of AVS_CTRL_0 and L0 voltage + * can be got from the mapping table of avs_map. + * - L1 voltage should be about 100mv smaller than L0 voltage + * - L2 & L3 voltage should be about 150mv smaller than L0 voltage. + * This function calculates L1 & L2 & L3 AVS values dynamically based + * on L0 voltage and fill all AVS values to the AVS value table. + */ +static void __init armada37xx_cpufreq_avs_configure(struct regmap *base, + struct armada_37xx_dvfs *dvfs) +{ + unsigned int target_vm; + int load_level = 0; + u32 l0_vdd_min; + + if (base == NULL) + return; + + /* Get L0 VDD min value */ + regmap_read(base, ARMADA_37XX_AVS_CTL0, &l0_vdd_min); + l0_vdd_min = (l0_vdd_min >> ARMADA_37XX_AVS_LOW_VDD_LIMIT) & + ARMADA_37XX_AVS_VDD_MASK; + if (l0_vdd_min >= ARRAY_SIZE(avs_map)) { + pr_err("L0 VDD MIN %d is not correct.\n", l0_vdd_min); + return; + } + dvfs->avs[0] = l0_vdd_min; + + if (avs_map[l0_vdd_min] <= MIN_VOLT_MV) { + /* + * If L0 voltage is smaller than 1000mv, then all VDD sets + * use L0 voltage; + */ + u32 avs_min = armada_37xx_avs_val_match(MIN_VOLT_MV); + + for (load_level = 1; load_level < LOAD_LEVEL_NR; load_level++) + dvfs->avs[load_level] = avs_min; + + return; + } + + /* + * L1 voltage is equal to L0 voltage - 100mv and it must be + * larger than 1000mv + */ + + target_vm = avs_map[l0_vdd_min] - 100; + target_vm = target_vm > MIN_VOLT_MV ? target_vm : MIN_VOLT_MV; + dvfs->avs[1] = armada_37xx_avs_val_match(target_vm); + + /* + * L2 & L3 voltage is equal to L0 voltage - 150mv and it must + * be larger than 1000mv + */ + target_vm = avs_map[l0_vdd_min] - 150; + target_vm = target_vm > MIN_VOLT_MV ? target_vm : MIN_VOLT_MV; + dvfs->avs[2] = dvfs->avs[3] = armada_37xx_avs_val_match(target_vm); +} + +static void __init armada37xx_cpufreq_avs_setup(struct regmap *base, + struct armada_37xx_dvfs *dvfs) +{ + unsigned int avs_val = 0, freq; + int load_level = 0; + + if (base == NULL) + return; + + /* Disable AVS before the configuration */ + regmap_update_bits(base, ARMADA_37XX_AVS_CTL0, + ARMADA_37XX_AVS_ENABLE, 0); + + + /* Enable low voltage mode */ + regmap_update_bits(base, ARMADA_37XX_AVS_CTL2, + ARMADA_37XX_AVS_LOW_VDD_EN, + ARMADA_37XX_AVS_LOW_VDD_EN); + + + for (load_level = 1; load_level < LOAD_LEVEL_NR; load_level++) { + freq = dvfs->cpu_freq_max / dvfs->divider[load_level]; + + avs_val = dvfs->avs[load_level]; + regmap_update_bits(base, ARMADA_37XX_AVS_VSET(load_level-1), + ARMADA_37XX_AVS_VDD_MASK << ARMADA_37XX_AVS_HIGH_VDD_LIMIT | + ARMADA_37XX_AVS_VDD_MASK << ARMADA_37XX_AVS_LOW_VDD_LIMIT, + avs_val << ARMADA_37XX_AVS_HIGH_VDD_LIMIT | + avs_val << ARMADA_37XX_AVS_LOW_VDD_LIMIT); + } + + /* Enable AVS after the configuration */ + regmap_update_bits(base, ARMADA_37XX_AVS_CTL0, + ARMADA_37XX_AVS_ENABLE, + ARMADA_37XX_AVS_ENABLE); + +} + static void armada37xx_cpufreq_disable_dvfs(struct regmap *base) { unsigned int reg = ARMADA_37XX_NB_DYN_MOD, @@ -216,7 +360,7 @@ static int __init armada37xx_cpufreq_driver_init(void) struct platform_device *pdev; unsigned long freq; unsigned int cur_frequency; - struct regmap *nb_pm_base; + struct regmap *nb_pm_base, *avs_base; struct device *cpu_dev; int load_lvl, ret; struct clk *clk; @@ -227,6 +371,14 @@ static int __init armada37xx_cpufreq_driver_init(void) if (IS_ERR(nb_pm_base)) return -ENODEV; + avs_base = + syscon_regmap_lookup_by_compatible("marvell,armada-3700-avs"); + + /* if AVS is not present don't use it but still try to setup dvfs */ + if (IS_ERR(avs_base)) { + pr_info("Syscon failed for Adapting Voltage Scaling: skip it\n"); + avs_base = NULL; + } /* Before doing any configuration on the DVFS first, disable it */ armada37xx_cpufreq_disable_dvfs(nb_pm_base); @@ -270,16 +422,21 @@ static int __init armada37xx_cpufreq_driver_init(void) armada37xx_cpufreq_state->regmap = nb_pm_base; + armada37xx_cpufreq_avs_configure(avs_base, dvfs); + armada37xx_cpufreq_avs_setup(avs_base, dvfs); + armada37xx_cpufreq_dvfs_setup(nb_pm_base, clk, dvfs->divider); clk_put(clk); for (load_lvl = ARMADA_37XX_DVFS_LOAD_0; load_lvl < LOAD_LEVEL_NR; load_lvl++) { + unsigned long u_volt = avs_map[dvfs->avs[load_lvl]] * 1000; freq = cur_frequency / dvfs->divider[load_lvl]; - - ret = dev_pm_opp_add(cpu_dev, freq, 0); + ret = dev_pm_opp_add(cpu_dev, freq, u_volt); if (ret) goto remove_opp; + + } /* Now that everything is setup, enable the DVFS at hardware level */ diff --git a/drivers/cpufreq/cppc_cpufreq.c b/drivers/cpufreq/cppc_cpufreq.c index a9d3eec32795..30f302149730 100644 --- a/drivers/cpufreq/cppc_cpufreq.c +++ b/drivers/cpufreq/cppc_cpufreq.c @@ -296,10 +296,62 @@ static int cppc_cpufreq_cpu_init(struct cpufreq_policy *policy) return ret; } +static inline u64 get_delta(u64 t1, u64 t0) +{ + if (t1 > t0 || t0 > ~(u32)0) + return t1 - t0; + + return (u32)t1 - (u32)t0; +} + +static int cppc_get_rate_from_fbctrs(struct cppc_cpudata *cpu, + struct cppc_perf_fb_ctrs fb_ctrs_t0, + struct cppc_perf_fb_ctrs fb_ctrs_t1) +{ + u64 delta_reference, delta_delivered; + u64 reference_perf, delivered_perf; + + reference_perf = fb_ctrs_t0.reference_perf; + + delta_reference = get_delta(fb_ctrs_t1.reference, + fb_ctrs_t0.reference); + delta_delivered = get_delta(fb_ctrs_t1.delivered, + fb_ctrs_t0.delivered); + + /* Check to avoid divide-by zero */ + if (delta_reference || delta_delivered) + delivered_perf = (reference_perf * delta_delivered) / + delta_reference; + else + delivered_perf = cpu->perf_ctrls.desired_perf; + + return cppc_cpufreq_perf_to_khz(cpu, delivered_perf); +} + +static unsigned int cppc_cpufreq_get_rate(unsigned int cpunum) +{ + struct cppc_perf_fb_ctrs fb_ctrs_t0 = {0}, fb_ctrs_t1 = {0}; + struct cppc_cpudata *cpu = all_cpu_data[cpunum]; + int ret; + + ret = cppc_get_perf_ctrs(cpunum, &fb_ctrs_t0); + if (ret) + return ret; + + udelay(2); /* 2usec delay between sampling */ + + ret = cppc_get_perf_ctrs(cpunum, &fb_ctrs_t1); + if (ret) + return ret; + + return cppc_get_rate_from_fbctrs(cpu, fb_ctrs_t0, fb_ctrs_t1); +} + static struct cpufreq_driver cppc_cpufreq_driver = { .flags = CPUFREQ_CONST_LOOPS, .verify = cppc_verify_policy, .target = cppc_cpufreq_set_target, + .get = cppc_cpufreq_get_rate, .init = cppc_cpufreq_cpu_init, .stop_cpu = cppc_cpufreq_stop_cpu, .name = "cppc_cpufreq", diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index b0dfd3222013..f53fb41efb7b 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -923,7 +923,12 @@ static ssize_t store(struct kobject *kobj, struct attribute *attr, struct freq_attr *fattr = to_attr(attr); ssize_t ret = -EINVAL; - cpus_read_lock(); + /* + * cpus_read_trylock() is used here to work around a circular lock + * dependency problem with respect to the cpufreq_register_driver(). + */ + if (!cpus_read_trylock()) + return -EBUSY; if (cpu_online(policy->cpu)) { down_write(&policy->rwsem); @@ -2236,6 +2241,7 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy, policy->min = new_policy->min; policy->max = new_policy->max; + trace_cpu_frequency_limits(policy); policy->cached_target_freq = UINT_MAX; diff --git a/drivers/cpufreq/imx6q-cpufreq.c b/drivers/cpufreq/imx6q-cpufreq.c index 8b3c2a79ad6c..b2ff423ad7f8 100644 --- a/drivers/cpufreq/imx6q-cpufreq.c +++ b/drivers/cpufreq/imx6q-cpufreq.c @@ -9,6 +9,7 @@ #include #include #include +#include #include #include #include @@ -50,6 +51,7 @@ static struct clk_bulk_data clks[] = { }; static struct device *cpu_dev; +static struct thermal_cooling_device *cdev; static bool free_opp; static struct cpufreq_frequency_table *freq_table; static unsigned int max_freq; @@ -191,6 +193,16 @@ static int imx6q_set_target(struct cpufreq_policy *policy, unsigned int index) return 0; } +static void imx6q_cpufreq_ready(struct cpufreq_policy *policy) +{ + cdev = of_cpufreq_cooling_register(policy); + + if (!cdev) + dev_err(cpu_dev, + "running cpufreq without cooling device: %ld\n", + PTR_ERR(cdev)); +} + static int imx6q_cpufreq_init(struct cpufreq_policy *policy) { int ret; @@ -202,13 +214,22 @@ static int imx6q_cpufreq_init(struct cpufreq_policy *policy) return ret; } +static int imx6q_cpufreq_exit(struct cpufreq_policy *policy) +{ + cpufreq_cooling_unregister(cdev); + + return 0; +} + static struct cpufreq_driver imx6q_cpufreq_driver = { .flags = CPUFREQ_NEED_INITIAL_FREQ_CHECK, .verify = cpufreq_generic_frequency_table_verify, .target_index = imx6q_set_target, .get = cpufreq_generic_get, .init = imx6q_cpufreq_init, + .exit = imx6q_cpufreq_exit, .name = "imx6q-cpufreq", + .ready = imx6q_cpufreq_ready, .attr = cpufreq_generic_attr, .suspend = cpufreq_generic_suspend, }; diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 3c3971256130..b6139a7b49f6 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -657,21 +657,18 @@ static ssize_t store_energy_performance_preference( { struct cpudata *cpu_data = all_cpu_data[policy->cpu]; char str_preference[21]; - int ret, i = 0; + int ret; ret = sscanf(buf, "%20s", str_preference); if (ret != 1) return -EINVAL; - while (energy_perf_strings[i] != NULL) { - if (!strcmp(str_preference, energy_perf_strings[i])) { - intel_pstate_set_energy_pref_index(cpu_data, i); - return count; - } - ++i; - } + ret = match_string(energy_perf_strings, -1, str_preference); + if (ret < 0) + return ret; - return -EINVAL; + intel_pstate_set_energy_pref_index(cpu_data, ret); + return count; } static ssize_t show_energy_performance_preference( @@ -2072,6 +2069,15 @@ static int __intel_pstate_cpu_init(struct cpufreq_policy *policy) cpu->pstate.max_pstate : cpu->pstate.turbo_pstate; policy->cpuinfo.max_freq *= cpu->pstate.scaling; + if (hwp_active) { + unsigned int max_freq; + + max_freq = global.turbo_disabled ? + cpu->pstate.max_freq : cpu->pstate.turbo_freq; + if (max_freq < policy->cpuinfo.max_freq) + policy->cpuinfo.max_freq = max_freq; + } + intel_pstate_init_acpi_perf_limits(policy); policy->fast_switch_possible = true; diff --git a/drivers/cpufreq/pcc-cpufreq.c b/drivers/cpufreq/pcc-cpufreq.c index 0c56c9759672..099a849396f6 100644 --- a/drivers/cpufreq/pcc-cpufreq.c +++ b/drivers/cpufreq/pcc-cpufreq.c @@ -593,6 +593,15 @@ static int __init pcc_cpufreq_init(void) return ret; } + if (num_present_cpus() > 4) { + pcc_cpufreq_driver.flags |= CPUFREQ_NO_AUTO_DYNAMIC_SWITCHING; + pr_err("%s: Too many CPUs, dynamic performance scaling disabled\n", + __func__); + pr_err("%s: Try to enable another scaling driver through BIOS settings\n", + __func__); + pr_err("%s: and complain to the system vendor\n", __func__); + } + ret = cpufreq_register_driver(&pcc_cpufreq_driver); return ret; diff --git a/drivers/cpufreq/qcom-cpufreq-kryo.c b/drivers/cpufreq/qcom-cpufreq-kryo.c index efc9a7ae4857..a1830fa25fc5 100644 --- a/drivers/cpufreq/qcom-cpufreq-kryo.c +++ b/drivers/cpufreq/qcom-cpufreq-kryo.c @@ -109,8 +109,9 @@ static int qcom_cpufreq_kryo_probe(struct platform_device *pdev) speedbin_nvmem = of_nvmem_cell_get(np, NULL); of_node_put(np); if (IS_ERR(speedbin_nvmem)) { - dev_err(cpu_dev, "Could not get nvmem cell: %ld\n", - PTR_ERR(speedbin_nvmem)); + if (PTR_ERR(speedbin_nvmem) != -EPROBE_DEFER) + dev_err(cpu_dev, "Could not get nvmem cell: %ld\n", + PTR_ERR(speedbin_nvmem)); return PTR_ERR(speedbin_nvmem); } diff --git a/drivers/thermal/imx_thermal.c b/drivers/thermal/imx_thermal.c index 334d98be03b9..cbfcca828cd7 100644 --- a/drivers/thermal/imx_thermal.c +++ b/drivers/thermal/imx_thermal.c @@ -3,6 +3,7 @@ // Copyright 2013 Freescale Semiconductor, Inc. #include +#include #include #include #include @@ -644,6 +645,27 @@ static const struct of_device_id of_imx_thermal_match[] = { }; MODULE_DEVICE_TABLE(of, of_imx_thermal_match); +/* + * Create cooling device in case no #cooling-cells property is available in + * CPU node + */ +static int imx_thermal_register_legacy_cooling(struct imx_thermal_data *data) +{ + struct device_node *np = of_get_cpu_node(data->policy->cpu, NULL); + int ret; + + if (!np || !of_find_property(np, "#cooling-cells", NULL)) { + data->cdev = cpufreq_cooling_register(data->policy); + if (IS_ERR(data->cdev)) { + ret = PTR_ERR(data->cdev); + cpufreq_cpu_put(data->policy); + return ret; + } + } + + return 0; +} + static int imx_thermal_probe(struct platform_device *pdev) { struct imx_thermal_data *data; @@ -724,12 +746,10 @@ static int imx_thermal_probe(struct platform_device *pdev) return -EPROBE_DEFER; } - data->cdev = cpufreq_cooling_register(data->policy); - if (IS_ERR(data->cdev)) { - ret = PTR_ERR(data->cdev); + ret = imx_thermal_register_legacy_cooling(data); + if (ret) { dev_err(&pdev->dev, "failed to register cpufreq cooling device: %d\n", ret); - cpufreq_cpu_put(data->policy); return ret; } diff --git a/include/linux/cpu.h b/include/linux/cpu.h index a97a63eef59f..e850bfea3e84 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -103,6 +103,7 @@ extern void cpus_write_lock(void); extern void cpus_write_unlock(void); extern void cpus_read_lock(void); extern void cpus_read_unlock(void); +extern int cpus_read_trylock(void); extern void lockdep_assert_cpus_held(void); extern void cpu_hotplug_disable(void); extern void cpu_hotplug_enable(void); @@ -115,6 +116,7 @@ static inline void cpus_write_lock(void) { } static inline void cpus_write_unlock(void) { } static inline void cpus_read_lock(void) { } static inline void cpus_read_unlock(void) { } +static inline int cpus_read_trylock(void) { return true; } static inline void lockdep_assert_cpus_held(void) { } static inline void cpu_hotplug_disable(void) { } static inline void cpu_hotplug_enable(void) { } diff --git a/include/trace/events/power.h b/include/trace/events/power.h index 908977d69783..f7aece721aed 100644 --- a/include/trace/events/power.h +++ b/include/trace/events/power.h @@ -5,6 +5,7 @@ #if !defined(_TRACE_POWER_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_POWER_H +#include #include #include #include @@ -148,6 +149,30 @@ DEFINE_EVENT(cpu, cpu_frequency, TP_ARGS(frequency, cpu_id) ); +TRACE_EVENT(cpu_frequency_limits, + + TP_PROTO(struct cpufreq_policy *policy), + + TP_ARGS(policy), + + TP_STRUCT__entry( + __field(u32, min_freq) + __field(u32, max_freq) + __field(u32, cpu_id) + ), + + TP_fast_assign( + __entry->min_freq = policy->min; + __entry->max_freq = policy->max; + __entry->cpu_id = policy->cpu; + ), + + TP_printk("min=%lu max=%lu cpu_id=%lu", + (unsigned long)__entry->min_freq, + (unsigned long)__entry->max_freq, + (unsigned long)__entry->cpu_id) +); + TRACE_EVENT(device_pm_callback_start, TP_PROTO(struct device *dev, const char *pm_ops, int event), diff --git a/kernel/cpu.c b/kernel/cpu.c index 0db8938fbb23..307486baa477 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -290,6 +290,12 @@ void cpus_read_lock(void) } EXPORT_SYMBOL_GPL(cpus_read_lock); +int cpus_read_trylock(void) +{ + return percpu_down_read_trylock(&cpu_hotplug_lock); +} +EXPORT_SYMBOL_GPL(cpus_read_trylock); + void cpus_read_unlock(void) { percpu_up_read(&cpu_hotplug_lock);