From b94263dd05f7d3cc53f664f09d251c6c2585e00d Mon Sep 17 00:00:00 2001 From: Daniel Hillenbrand Date: Tue, 19 Jun 2012 15:57:46 +0200 Subject: cpufreq and interactive gov updates from tuna --- drivers/cpufreq/cpufreq.c | 8 + drivers/cpufreq/cpufreq_interactive.c | 356 ++++++++++++++++++++++++++--- drivers/cpufreq/powernow-k8.c | 30 ++- include/trace/events/cpufreq_interactive.h | 112 +++++++++ 4 files changed, 465 insertions(+), 41 deletions(-) create mode 100644 include/trace/events/cpufreq_interactive.h diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 0a5bea9e358..6204c98ce44 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -32,6 +32,9 @@ #include +// Safe boot speed +#define SafeBootSpeed 1200000 + /** * The "cpufreq driver" - the arch- or hardware-dependent low * level driver of CPUFreq support, and its spinlock. This lock @@ -941,6 +944,11 @@ static int cpufreq_add_dev(struct sys_device *sys_dev) pr_debug("initialization failed\n"); goto err_unlock_policy; } + + // Set max speed at boot to 1.2Mhz since is the safest speed to boot + if (policy->max > SafeBootSpeed) + policy->max = SafeBootSpeed; + policy->user_policy.min = policy->min; policy->user_policy.max = policy->max; diff --git a/drivers/cpufreq/cpufreq_interactive.c b/drivers/cpufreq/cpufreq_interactive.c index 45266d5b6cd..7dbacf035e7 100644 --- a/drivers/cpufreq/cpufreq_interactive.c +++ b/drivers/cpufreq/cpufreq_interactive.c @@ -27,9 +27,13 @@ #include #include #include - +#include +#include #include +#define CREATE_TRACE_POINTS +#include + static atomic_t active_count = ATOMIC_INIT(0); struct cpufreq_interactive_cpuinfo { @@ -39,11 +43,14 @@ struct cpufreq_interactive_cpuinfo { u64 idle_exit_time; u64 timer_run_time; int idling; - u64 freq_change_time; - u64 freq_change_time_in_idle; + u64 target_set_time; + u64 target_set_time_in_idle; struct cpufreq_policy *policy; struct cpufreq_frequency_table *freq_table; unsigned int target_freq; + unsigned int floor_freq; + u64 floor_validate_time; + u64 hispeed_validate_time; int governor_enabled; }; @@ -63,21 +70,47 @@ static struct mutex set_speed_lock; static u64 hispeed_freq; /* Go to hi speed when CPU load at or above this value. */ -#define DEFAULT_GO_HISPEED_LOAD 95 +#define DEFAULT_GO_HISPEED_LOAD 85 static unsigned long go_hispeed_load; /* * The minimum amount of time to spend at a frequency before we can ramp down. */ -#define DEFAULT_MIN_SAMPLE_TIME 20 * USEC_PER_MSEC +#define DEFAULT_MIN_SAMPLE_TIME (80 * USEC_PER_MSEC) static unsigned long min_sample_time; /* * The sample rate of the timer used to increase frequency */ -#define DEFAULT_TIMER_RATE 20 * USEC_PER_MSEC +#define DEFAULT_TIMER_RATE (20 * USEC_PER_MSEC) static unsigned long timer_rate; +/* + * Wait this long before raising speed above hispeed, by default a single + * timer interval. + */ +#define DEFAULT_ABOVE_HISPEED_DELAY DEFAULT_TIMER_RATE +static unsigned long above_hispeed_delay_val; + +/* + * Boost pulse to hispeed on touchscreen input. + */ + +static int input_boost_val; + +struct cpufreq_interactive_inputopen { + struct input_handle *handle; + struct work_struct inputopen_work; +}; + +static struct cpufreq_interactive_inputopen inputopen; + +/* + * Non-zero means longer-term speed boost active. + */ + +static int boost_val; + static int cpufreq_governor_interactive(struct cpufreq_policy *policy, unsigned int event); @@ -145,9 +178,9 @@ static void cpufreq_interactive_timer(unsigned long data) cpu_load = 100 * (delta_time - delta_idle) / delta_time; delta_idle = (unsigned int) cputime64_sub(now_idle, - pcpu->freq_change_time_in_idle); + pcpu->target_set_time_in_idle); delta_time = (unsigned int) cputime64_sub(pcpu->timer_run_time, - pcpu->freq_change_time); + pcpu->target_set_time); if ((delta_time == 0) || (delta_idle > delta_time)) load_since_change = 0; @@ -163,15 +196,33 @@ static void cpufreq_interactive_timer(unsigned long data) if (load_since_change > cpu_load) cpu_load = load_since_change; - if (cpu_load >= go_hispeed_load) { - if (pcpu->policy->cur == pcpu->policy->min) + if (cpu_load >= go_hispeed_load || boost_val) { + if (pcpu->target_freq <= pcpu->policy->min) { new_freq = hispeed_freq; - else + } else { new_freq = pcpu->policy->max * cpu_load / 100; + + if (new_freq < hispeed_freq) + new_freq = hispeed_freq; + + if (pcpu->target_freq == hispeed_freq && + new_freq > hispeed_freq && + cputime64_sub(pcpu->timer_run_time, + pcpu->hispeed_validate_time) + < above_hispeed_delay_val) { + trace_cpufreq_interactive_notyet(data, cpu_load, + pcpu->target_freq, + new_freq); + goto rearm; + } + } } else { - new_freq = pcpu->policy->cur * cpu_load / 100; + new_freq = pcpu->policy->max * cpu_load / 100; } + if (new_freq <= hispeed_freq) + pcpu->hispeed_validate_time = pcpu->timer_run_time; + if (cpufreq_frequency_table_target(pcpu->policy, pcpu->freq_table, new_freq, CPUFREQ_RELATION_H, &index)) { @@ -182,19 +233,34 @@ static void cpufreq_interactive_timer(unsigned long data) new_freq = pcpu->freq_table[index].frequency; - if (pcpu->target_freq == new_freq) - goto rearm_if_notmax; - /* - * Do not scale down unless we have been at this frequency for the - * minimum sample time. + * Do not scale below floor_freq unless we have been at or above the + * floor frequency for the minimum sample time since last validated. */ - if (new_freq < pcpu->target_freq) { - if (cputime64_sub(pcpu->timer_run_time, pcpu->freq_change_time) - < min_sample_time) + if (new_freq < pcpu->floor_freq) { + if (cputime64_sub(pcpu->timer_run_time, + pcpu->floor_validate_time) + < min_sample_time) { + trace_cpufreq_interactive_notyet(data, cpu_load, + pcpu->target_freq, new_freq); goto rearm; + } } + pcpu->floor_freq = new_freq; + pcpu->floor_validate_time = pcpu->timer_run_time; + + if (pcpu->target_freq == new_freq) { + trace_cpufreq_interactive_already(data, cpu_load, + pcpu->target_freq, new_freq); + goto rearm_if_notmax; + } + + trace_cpufreq_interactive_target(data, cpu_load, pcpu->target_freq, + new_freq); + pcpu->target_set_time_in_idle = now_idle; + pcpu->target_set_time = pcpu->timer_run_time; + if (new_freq < pcpu->target_freq) { pcpu->target_freq = new_freq; spin_lock_irqsave(&down_cpumask_lock, flags); @@ -378,10 +444,8 @@ static int cpufreq_interactive_up_task(void *data) max_freq, CPUFREQ_RELATION_H); mutex_unlock(&set_speed_lock); - - pcpu->freq_change_time_in_idle = - get_cpu_idle_time_us(cpu, - &pcpu->freq_change_time); + trace_cpufreq_interactive_up(cpu, pcpu->target_freq, + pcpu->policy->cur); } } @@ -425,12 +489,137 @@ static void cpufreq_interactive_freq_down(struct work_struct *work) CPUFREQ_RELATION_H); mutex_unlock(&set_speed_lock); - pcpu->freq_change_time_in_idle = - get_cpu_idle_time_us(cpu, - &pcpu->freq_change_time); + trace_cpufreq_interactive_down(cpu, pcpu->target_freq, + pcpu->policy->cur); } } +static void cpufreq_interactive_boost(void) +{ + int i; + int anyboost = 0; + unsigned long flags; + struct cpufreq_interactive_cpuinfo *pcpu; + + spin_lock_irqsave(&up_cpumask_lock, flags); + + for_each_online_cpu(i) { + pcpu = &per_cpu(cpuinfo, i); + + if (pcpu->target_freq < hispeed_freq) { + pcpu->target_freq = hispeed_freq; + cpumask_set_cpu(i, &up_cpumask); + pcpu->target_set_time_in_idle = + get_cpu_idle_time_us(i, &pcpu->target_set_time); + pcpu->hispeed_validate_time = pcpu->target_set_time; + anyboost = 1; + } + + /* + * Set floor freq and (re)start timer for when last + * validated. + */ + + pcpu->floor_freq = hispeed_freq; + pcpu->floor_validate_time = ktime_to_us(ktime_get()); + } + + spin_unlock_irqrestore(&up_cpumask_lock, flags); + + if (anyboost) + wake_up_process(up_task); +} + +/* + * Pulsed boost on input event raises CPUs to hispeed_freq and lets + * usual algorithm of min_sample_time decide when to allow speed + * to drop. + */ + +static void cpufreq_interactive_input_event(struct input_handle *handle, + unsigned int type, + unsigned int code, int value) +{ + if (input_boost_val && type == EV_SYN && code == SYN_REPORT) { + trace_cpufreq_interactive_boost("input"); + cpufreq_interactive_boost(); + } +} + +static void cpufreq_interactive_input_open(struct work_struct *w) +{ + struct cpufreq_interactive_inputopen *io = + container_of(w, struct cpufreq_interactive_inputopen, + inputopen_work); + int error; + + error = input_open_device(io->handle); + if (error) + input_unregister_handle(io->handle); +} + +static int cpufreq_interactive_input_connect(struct input_handler *handler, + struct input_dev *dev, + const struct input_device_id *id) +{ + struct input_handle *handle; + int error; + + pr_info("%s: connect to %s\n", __func__, dev->name); + handle = kzalloc(sizeof(struct input_handle), GFP_KERNEL); + if (!handle) + return -ENOMEM; + + handle->dev = dev; + handle->handler = handler; + handle->name = "cpufreq_interactive"; + + error = input_register_handle(handle); + if (error) + goto err; + + inputopen.handle = handle; + queue_work(down_wq, &inputopen.inputopen_work); + return 0; +err: + kfree(handle); + return error; +} + +static void cpufreq_interactive_input_disconnect(struct input_handle *handle) +{ + input_close_device(handle); + input_unregister_handle(handle); + kfree(handle); +} + +static const struct input_device_id cpufreq_interactive_ids[] = { + { + .flags = INPUT_DEVICE_ID_MATCH_EVBIT | + INPUT_DEVICE_ID_MATCH_ABSBIT, + .evbit = { BIT_MASK(EV_ABS) }, + .absbit = { [BIT_WORD(ABS_MT_POSITION_X)] = + BIT_MASK(ABS_MT_POSITION_X) | + BIT_MASK(ABS_MT_POSITION_Y) }, + }, /* multi-touch touchscreen */ + { + .flags = INPUT_DEVICE_ID_MATCH_KEYBIT | + INPUT_DEVICE_ID_MATCH_ABSBIT, + .keybit = { [BIT_WORD(BTN_TOUCH)] = BIT_MASK(BTN_TOUCH) }, + .absbit = { [BIT_WORD(ABS_X)] = + BIT_MASK(ABS_X) | BIT_MASK(ABS_Y) }, + }, /* touchpad */ + { }, +}; + +static struct input_handler cpufreq_interactive_input_handler = { + .event = cpufreq_interactive_input_event, + .connect = cpufreq_interactive_input_connect, + .disconnect = cpufreq_interactive_input_disconnect, + .name = "cpufreq_interactive", + .id_table = cpufreq_interactive_ids, +}; + static ssize_t show_hispeed_freq(struct kobject *kobj, struct attribute *attr, char *buf) { @@ -499,6 +688,28 @@ static ssize_t store_min_sample_time(struct kobject *kobj, static struct global_attr min_sample_time_attr = __ATTR(min_sample_time, 0644, show_min_sample_time, store_min_sample_time); +static ssize_t show_above_hispeed_delay(struct kobject *kobj, + struct attribute *attr, char *buf) +{ + return sprintf(buf, "%lu\n", above_hispeed_delay_val); +} + +static ssize_t store_above_hispeed_delay(struct kobject *kobj, + struct attribute *attr, + const char *buf, size_t count) +{ + int ret; + unsigned long val; + + ret = strict_strtoul(buf, 0, &val); + if (ret < 0) + return ret; + above_hispeed_delay_val = val; + return count; +} + +define_one_global_rw(above_hispeed_delay); + static ssize_t show_timer_rate(struct kobject *kobj, struct attribute *attr, char *buf) { @@ -521,11 +732,84 @@ static ssize_t store_timer_rate(struct kobject *kobj, static struct global_attr timer_rate_attr = __ATTR(timer_rate, 0644, show_timer_rate, store_timer_rate); +static ssize_t show_input_boost(struct kobject *kobj, struct attribute *attr, + char *buf) +{ + return sprintf(buf, "%u\n", input_boost_val); +} + +static ssize_t store_input_boost(struct kobject *kobj, struct attribute *attr, + const char *buf, size_t count) +{ + int ret; + unsigned long val; + + ret = strict_strtoul(buf, 0, &val); + if (ret < 0) + return ret; + input_boost_val = val; + return count; +} + +define_one_global_rw(input_boost); + +static ssize_t show_boost(struct kobject *kobj, struct attribute *attr, + char *buf) +{ + return sprintf(buf, "%d\n", boost_val); +} + +static ssize_t store_boost(struct kobject *kobj, struct attribute *attr, + const char *buf, size_t count) +{ + int ret; + unsigned long val; + + ret = kstrtoul(buf, 0, &val); + if (ret < 0) + return ret; + + boost_val = val; + + if (boost_val) { + trace_cpufreq_interactive_boost("on"); + cpufreq_interactive_boost(); + } else { + trace_cpufreq_interactive_unboost("off"); + } + + return count; +} + +define_one_global_rw(boost); + +static ssize_t store_boostpulse(struct kobject *kobj, struct attribute *attr, + const char *buf, size_t count) +{ + int ret; + unsigned long val; + + ret = kstrtoul(buf, 0, &val); + if (ret < 0) + return ret; + + trace_cpufreq_interactive_boost("pulse"); + cpufreq_interactive_boost(); + return count; +} + +static struct global_attr boostpulse = + __ATTR(boostpulse, 0200, NULL, store_boostpulse); + static struct attribute *interactive_attributes[] = { &hispeed_freq_attr.attr, &go_hispeed_load_attr.attr, + &above_hispeed_delay.attr, &min_sample_time_attr.attr, &timer_rate_attr.attr, + &input_boost.attr, + &boost.attr, + &boostpulse.attr, NULL, }; @@ -555,9 +839,14 @@ static int cpufreq_governor_interactive(struct cpufreq_policy *policy, pcpu->policy = policy; pcpu->target_freq = policy->cur; pcpu->freq_table = freq_table; - pcpu->freq_change_time_in_idle = + pcpu->target_set_time_in_idle = get_cpu_idle_time_us(j, - &pcpu->freq_change_time); + &pcpu->target_set_time); + pcpu->floor_freq = pcpu->target_freq; + pcpu->floor_validate_time = + pcpu->target_set_time; + pcpu->hispeed_validate_time = + pcpu->target_set_time; pcpu->governor_enabled = 1; smp_wmb(); } @@ -577,6 +866,11 @@ static int cpufreq_governor_interactive(struct cpufreq_policy *policy, if (rc) return rc; + rc = input_register_handler(&cpufreq_interactive_input_handler); + if (rc) + pr_warn("%s: failed to register input handler\n", + __func__); + break; case CPUFREQ_GOV_STOP: @@ -599,6 +893,7 @@ static int cpufreq_governor_interactive(struct cpufreq_policy *policy, if (atomic_dec_return(&active_count) > 0) return 0; + input_unregister_handler(&cpufreq_interactive_input_handler); sysfs_remove_group(cpufreq_global_kobject, &interactive_attr_group); @@ -644,6 +939,7 @@ static int __init cpufreq_interactive_init(void) go_hispeed_load = DEFAULT_GO_HISPEED_LOAD; min_sample_time = DEFAULT_MIN_SAMPLE_TIME; + above_hispeed_delay_val = DEFAULT_ABOVE_HISPEED_DELAY; timer_rate = DEFAULT_TIMER_RATE; /* Initalize per-cpu timers */ @@ -677,7 +973,7 @@ static int __init cpufreq_interactive_init(void) mutex_init(&set_speed_lock); idle_notifier_register(&cpufreq_interactive_idle_nb); - + INIT_WORK(&inputopen.inputopen_work, cpufreq_interactive_input_open); return cpufreq_register_governor(&cpufreq_gov_interactive); err_freeuptask: diff --git a/drivers/cpufreq/powernow-k8.c b/drivers/cpufreq/powernow-k8.c index bce576d7478..ad683ec2c57 100644 --- a/drivers/cpufreq/powernow-k8.c +++ b/drivers/cpufreq/powernow-k8.c @@ -54,6 +54,9 @@ static DEFINE_PER_CPU(struct powernow_k8_data *, powernow_data); static int cpu_family = CPU_OPTERON; +/* array to map SW pstate number to acpi state */ +static u32 ps_to_as[8]; + /* core performance boost */ static bool cpb_capable, cpb_enabled; static struct msr __percpu *msrs; @@ -80,9 +83,9 @@ static u32 find_khz_freq_from_fid(u32 fid) } static u32 find_khz_freq_from_pstate(struct cpufreq_frequency_table *data, - u32 pstate) + u32 pstate) { - return data[pstate].frequency; + return data[ps_to_as[pstate]].frequency; } /* Return the vco fid for an input fid @@ -926,23 +929,27 @@ static int fill_powernow_table_pstate(struct powernow_k8_data *data, invalidate_entry(powernow_table, i); continue; } - rdmsr(MSR_PSTATE_DEF_BASE + index, lo, hi); - if (!(hi & HW_PSTATE_VALID_MASK)) { - pr_debug("invalid pstate %d, ignoring\n", index); - invalidate_entry(powernow_table, i); - continue; - } - powernow_table[i].index = index; + ps_to_as[index] = i; /* Frequency may be rounded for these */ if ((boot_cpu_data.x86 == 0x10 && boot_cpu_data.x86_model < 10) || boot_cpu_data.x86 == 0x11) { + + rdmsr(MSR_PSTATE_DEF_BASE + index, lo, hi); + if (!(hi & HW_PSTATE_VALID_MASK)) { + pr_debug("invalid pstate %d, ignoring\n", index); + invalidate_entry(powernow_table, i); + continue; + } + powernow_table[i].frequency = freq_from_fid_did(lo & 0x3f, (lo >> 6) & 7); } else powernow_table[i].frequency = data->acpi_data.states[i].core_frequency * 1000; + + powernow_table[i].index = index; } return 0; } @@ -1189,7 +1196,8 @@ static int powernowk8_target(struct cpufreq_policy *pol, powernow_k8_acpi_pst_values(data, newstate); if (cpu_family == CPU_HW_PSTATE) - ret = transition_frequency_pstate(data, newstate); + ret = transition_frequency_pstate(data, + data->powernow_table[newstate].index); else ret = transition_frequency_fidvid(data, newstate); if (ret) { @@ -1202,7 +1210,7 @@ static int powernowk8_target(struct cpufreq_policy *pol, if (cpu_family == CPU_HW_PSTATE) pol->cur = find_khz_freq_from_pstate(data->powernow_table, - newstate); + data->powernow_table[newstate].index); else pol->cur = find_khz_freq_from_fid(data->currfid); ret = 0; diff --git a/include/trace/events/cpufreq_interactive.h b/include/trace/events/cpufreq_interactive.h new file mode 100644 index 00000000000..ea83664a4e6 --- /dev/null +++ b/include/trace/events/cpufreq_interactive.h @@ -0,0 +1,112 @@ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM cpufreq_interactive + +#if !defined(_TRACE_CPUFREQ_INTERACTIVE_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_CPUFREQ_INTERACTIVE_H + +#include + +DECLARE_EVENT_CLASS(set, + TP_PROTO(u32 cpu_id, unsigned long targfreq, + unsigned long actualfreq), + TP_ARGS(cpu_id, targfreq, actualfreq), + + TP_STRUCT__entry( + __field( u32, cpu_id ) + __field(unsigned long, targfreq ) + __field(unsigned long, actualfreq ) + ), + + TP_fast_assign( + __entry->cpu_id = (u32) cpu_id; + __entry->targfreq = targfreq; + __entry->actualfreq = actualfreq; + ), + + TP_printk("cpu=%u targ=%lu actual=%lu", + __entry->cpu_id, __entry->targfreq, + __entry->actualfreq) +); + +DEFINE_EVENT(set, cpufreq_interactive_up, + TP_PROTO(u32 cpu_id, unsigned long targfreq, + unsigned long actualfreq), + TP_ARGS(cpu_id, targfreq, actualfreq) +); + +DEFINE_EVENT(set, cpufreq_interactive_down, + TP_PROTO(u32 cpu_id, unsigned long targfreq, + unsigned long actualfreq), + TP_ARGS(cpu_id, targfreq, actualfreq) +); + +DECLARE_EVENT_CLASS(loadeval, + TP_PROTO(unsigned long cpu_id, unsigned long load, + unsigned long curfreq, unsigned long targfreq), + TP_ARGS(cpu_id, load, curfreq, targfreq), + + TP_STRUCT__entry( + __field(unsigned long, cpu_id ) + __field(unsigned long, load ) + __field(unsigned long, curfreq ) + __field(unsigned long, targfreq ) + ), + + TP_fast_assign( + __entry->cpu_id = cpu_id; + __entry->load = load; + __entry->curfreq = curfreq; + __entry->targfreq = targfreq; + ), + + TP_printk("cpu=%lu load=%lu cur=%lu targ=%lu", + __entry->cpu_id, __entry->load, __entry->curfreq, + __entry->targfreq) +); + +DEFINE_EVENT(loadeval, cpufreq_interactive_target, + TP_PROTO(unsigned long cpu_id, unsigned long load, + unsigned long curfreq, unsigned long targfreq), + TP_ARGS(cpu_id, load, curfreq, targfreq) +); + +DEFINE_EVENT(loadeval, cpufreq_interactive_already, + TP_PROTO(unsigned long cpu_id, unsigned long load, + unsigned long curfreq, unsigned long targfreq), + TP_ARGS(cpu_id, load, curfreq, targfreq) +); + +DEFINE_EVENT(loadeval, cpufreq_interactive_notyet, + TP_PROTO(unsigned long cpu_id, unsigned long load, + unsigned long curfreq, unsigned long targfreq), + TP_ARGS(cpu_id, load, curfreq, targfreq) +); + +TRACE_EVENT(cpufreq_interactive_boost, + TP_PROTO(const char *s), + TP_ARGS(s), + TP_STRUCT__entry( + __string(s, s) + ), + TP_fast_assign( + __assign_str(s, s); + ), + TP_printk("%s", __get_str(s)) +); + +TRACE_EVENT(cpufreq_interactive_unboost, + TP_PROTO(const char *s), + TP_ARGS(s), + TP_STRUCT__entry( + __string(s, s) + ), + TP_fast_assign( + __assign_str(s, s); + ), + TP_printk("%s", __get_str(s)) +); + +#endif /* _TRACE_CPUFREQ_INTERACTIVE_H */ + +/* This part must be outside protection */ +#include -- cgit v1.2.3