and fix the broken case if a core's frequency depends on others.
trace_power_frequency was only implemented in a rather ungeneric way
in acpi-cpufreq driver's target() function only.
-> Move the call to trace_power_frequency to
cpufreq.c:cpufreq_notify_transition() where CPUFREQ_POSTCHANGE
notifier is triggered.
This will support power frequency tracing by all cpufreq drivers
trace_power_frequency did not trace frequency changes correctly when
the userspace governor was used or when CPU cores' frequency depend
on each other.
-> Moving this into the CPUFREQ_POSTCHANGE notifier and pass the cpu
which gets switched automatically fixes this.
Robert Schoene provided some important fixes on top of my initial
quick shot version which are integrated in this patch:
- Forgot some changes in power_end trace (TP_printk/variable names)
- Variable dummy in power_end must now be cpu_id
- Use static 64 bit variable instead of unsigned int for cpu_id
Signed-off-by: Thomas Renninger <trenn@suse.de>
CC: davej@redhat.com
CC: arjan@infradead.org
CC: linux-kernel@vger.kernel.org
CC: robert.schoene@tu-dresden.de
Tested-by: robert.schoene@tu-dresden.de
Signed-off-by: Dave Jones <davej@redhat.com>
#include <linux/compiler.h>
#include <linux/dmi.h>
#include <linux/slab.h>
-#include <trace/events/power.h>
#include <linux/acpi.h>
#include <linux/io.h>
}
}
- trace_power_frequency(POWER_PSTATE, data->freq_table[next_state].frequency);
-
switch (data->cpu_feature) {
case SYSTEM_INTEL_MSR_CAPABLE:
cmd.type = SYSTEM_INTEL_MSR_CAPABLE;
void default_idle(void)
{
if (hlt_use_halt()) {
- trace_power_start(POWER_CSTATE, 1);
+ trace_power_start(POWER_CSTATE, 1, smp_processor_id());
current_thread_info()->status &= ~TS_POLLING;
/*
* TS_POLLING-cleared state must be visible before we
*/
void mwait_idle_with_hints(unsigned long ax, unsigned long cx)
{
- trace_power_start(POWER_CSTATE, (ax>>4)+1);
+ trace_power_start(POWER_CSTATE, (ax>>4)+1, smp_processor_id());
if (!need_resched()) {
if (cpu_has(¤t_cpu_data, X86_FEATURE_CLFLUSH_MONITOR))
clflush((void *)¤t_thread_info()->flags);
static void mwait_idle(void)
{
if (!need_resched()) {
- trace_power_start(POWER_CSTATE, 1);
+ trace_power_start(POWER_CSTATE, 1, smp_processor_id());
if (cpu_has(¤t_cpu_data, X86_FEATURE_CLFLUSH_MONITOR))
clflush((void *)¤t_thread_info()->flags);
*/
static void poll_idle(void)
{
- trace_power_start(POWER_CSTATE, 0);
+ trace_power_start(POWER_CSTATE, 0, smp_processor_id());
local_irq_enable();
while (!need_resched())
cpu_relax();
#include <linux/completion.h>
#include <linux/mutex.h>
+#include <trace/events/power.h>
+
#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_CORE, \
"cpufreq-core", msg)
case CPUFREQ_POSTCHANGE:
adjust_jiffies(CPUFREQ_POSTCHANGE, freqs);
+ dprintk("FREQ: %lu - CPU: %lu", (unsigned long)freqs->new,
+ (unsigned long)freqs->cpu);
+ trace_power_frequency(POWER_PSTATE, freqs->new, freqs->cpu);
srcu_notifier_call_chain(&cpufreq_transition_notifier_list,
CPUFREQ_POSTCHANGE, freqs);
if (likely(policy) && likely(policy->cpu == freqs->cpu))
/* give the governor an opportunity to reflect on the outcome */
if (cpuidle_curr_governor->reflect)
cpuidle_curr_governor->reflect(dev);
- trace_power_end(0);
+ trace_power_end(smp_processor_id());
}
/**
DECLARE_EVENT_CLASS(power,
- TP_PROTO(unsigned int type, unsigned int state),
+ TP_PROTO(unsigned int type, unsigned int state, unsigned int cpu_id),
- TP_ARGS(type, state),
+ TP_ARGS(type, state, cpu_id),
TP_STRUCT__entry(
__field( u64, type )
__field( u64, state )
+ __field( u64, cpu_id )
),
TP_fast_assign(
__entry->type = type;
__entry->state = state;
+ __entry->cpu_id = cpu_id;
),
- TP_printk("type=%lu state=%lu", (unsigned long)__entry->type, (unsigned long)__entry->state)
+ TP_printk("type=%lu state=%lu cpu_id=%lu", (unsigned long)__entry->type,
+ (unsigned long)__entry->state, (unsigned long)__entry->cpu_id)
);
DEFINE_EVENT(power, power_start,
- TP_PROTO(unsigned int type, unsigned int state),
+ TP_PROTO(unsigned int type, unsigned int state, unsigned int cpu_id),
- TP_ARGS(type, state)
+ TP_ARGS(type, state, cpu_id)
);
DEFINE_EVENT(power, power_frequency,
- TP_PROTO(unsigned int type, unsigned int state),
+ TP_PROTO(unsigned int type, unsigned int state, unsigned int cpu_id),
- TP_ARGS(type, state)
+ TP_ARGS(type, state, cpu_id)
);
TRACE_EVENT(power_end,
- TP_PROTO(int dummy),
+ TP_PROTO(unsigned int cpu_id),
- TP_ARGS(dummy),
+ TP_ARGS(cpu_id),
TP_STRUCT__entry(
- __field( u64, dummy )
+ __field( u64, cpu_id )
),
TP_fast_assign(
- __entry->dummy = 0xffff;
+ __entry->cpu_id = cpu_id;
),
- TP_printk("dummy=%lu", (unsigned long)__entry->dummy)
+ TP_printk("cpu_id=%lu", (unsigned long)__entry->cpu_id)
);
struct power_entry {
struct trace_entry te;
- s64 type;
- s64 value;
+ u64 type;
+ u64 value;
+ u64 cpu_id;
};
#define TASK_COMM_LEN 16
return 0;
if (strcmp(event_str, "power:power_start") == 0)
- c_state_start(data.cpu, data.time, pe->value);
+ c_state_start(pe->cpu_id, data.time, pe->value);
if (strcmp(event_str, "power:power_end") == 0)
- c_state_end(data.cpu, data.time);
+ c_state_end(pe->cpu_id, data.time);
if (strcmp(event_str, "power:power_frequency") == 0)
- p_state_change(data.cpu, data.time, pe->value);
+ p_state_change(pe->cpu_id, data.time, pe->value);
if (strcmp(event_str, "sched:sched_wakeup") == 0)
sched_wakeup(data.cpu, data.time, data.pid, te);