sched/cputime: Provide get_cpu_[idle|iowait]_time_us() off-case

The last reason why get_cpu_idle/iowait_time_us() may return -1 now is if
the config doesn't support nohz.

The ad-hoc replacement solution by cpufreq is to compute jiffies minus the
whole busy cputime. Although the intention should provide a coherent low
resolution estimation of the idle and iowait time, the implementation is
buggy because jiffies don't start at 0.

Just provide instead a real get_cpu_[idle|iowait]_time_us() offcase.

Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Signed-off-by: Thomas Gleixner <tglx@kernel.org>
Tested-by: Shrikanth Hegde <sshegde@linux.ibm.com>
Link: https://patch.msgid.link/20260508131647.43868-14-frederic@kernel.org
This commit is contained in:
Frederic Weisbecker 2026-05-08 15:16:45 +02:00 committed by Thomas Gleixner
parent 127b2eb44f
commit 3b45b4f188
4 changed files with 13 additions and 35 deletions

View File

@ -130,38 +130,11 @@ struct kobject *get_governor_parent_kobj(struct cpufreq_policy *policy)
}
EXPORT_SYMBOL_GPL(get_governor_parent_kobj);
static inline u64 get_cpu_idle_time_jiffy(unsigned int cpu, u64 *wall)
{
struct kernel_cpustat kcpustat;
u64 cur_wall_time;
u64 idle_time;
u64 busy_time;
cur_wall_time = jiffies64_to_nsecs(get_jiffies_64());
kcpustat_cpu_fetch(&kcpustat, cpu);
busy_time = kcpustat.cpustat[CPUTIME_USER];
busy_time += kcpustat.cpustat[CPUTIME_SYSTEM];
busy_time += kcpustat.cpustat[CPUTIME_IRQ];
busy_time += kcpustat.cpustat[CPUTIME_SOFTIRQ];
busy_time += kcpustat.cpustat[CPUTIME_STEAL];
busy_time += kcpustat.cpustat[CPUTIME_NICE];
idle_time = cur_wall_time - busy_time;
if (wall)
*wall = div_u64(cur_wall_time, NSEC_PER_USEC);
return div_u64(idle_time, NSEC_PER_USEC);
}
u64 get_cpu_idle_time(unsigned int cpu, u64 *wall, int io_busy)
{
u64 idle_time = get_cpu_idle_time_us(cpu, io_busy ? wall : NULL);
if (idle_time == -1ULL)
return get_cpu_idle_time_jiffy(cpu, wall);
else if (!io_busy)
if (!io_busy)
idle_time += get_cpu_iowait_time_us(cpu, wall);
return idle_time;

View File

@ -133,6 +133,9 @@ static inline bool kcpustat_idle_dyntick(void)
}
#endif /* CONFIG_NO_HZ_COMMON */
extern u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time);
extern u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time);
/* Fetch cputime values when vtime is disabled on a CPU */
static inline u64 kcpustat_field_default(enum cpu_usage_stat usage, int cpu)
{

View File

@ -139,8 +139,6 @@ extern bool tick_nohz_idle_got_tick(void);
extern ktime_t tick_nohz_get_next_hrtimer(void);
extern ktime_t tick_nohz_get_sleep_length(ktime_t *delta_next);
extern unsigned long tick_nohz_get_idle_calls_cpu(int cpu);
extern u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time);
extern u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time);
#else /* !CONFIG_NO_HZ_COMMON */
#define tick_nohz_enabled (0)
static inline bool tick_nohz_is_active(void) { return false; }
@ -162,8 +160,6 @@ static inline ktime_t tick_nohz_get_sleep_length(ktime_t *delta_next)
*delta_next = TICK_NSEC;
return *delta_next;
}
static inline u64 get_cpu_idle_time_us(int cpu, u64 *unused) { return -1; }
static inline u64 get_cpu_iowait_time_us(int cpu, u64 *unused) { return -1; }
#endif /* !CONFIG_NO_HZ_COMMON */
/*

View File

@ -522,6 +522,13 @@ u64 kcpustat_field_iowait(int cpu)
nr_iowait_cpu(cpu), ktime_get());
}
EXPORT_SYMBOL_GPL(kcpustat_field_iowait);
#else
static u64 kcpustat_field_dyntick(int cpu, enum cpu_usage_stat idx,
bool compute_delta, ktime_t now)
{
return kcpustat_cpu(cpu).cpustat[idx];
}
#endif /* CONFIG_NO_HZ_COMMON */
static u64 get_cpu_sleep_time_us(int cpu, enum cpu_usage_stat idx,
bool compute_delta, u64 *last_update_time)
@ -557,7 +564,7 @@ static u64 get_cpu_sleep_time_us(int cpu, enum cpu_usage_stat idx,
* This time is measured via accounting rather than sampling,
* and is as accurate as ktime_get() is.
*
* Return: -1 if generic vtime is enabled, else total idle time of the @cpu
* Return: total idle time of the @cpu
*/
u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time)
{
@ -581,7 +588,7 @@ EXPORT_SYMBOL_GPL(get_cpu_idle_time_us);
* This time is measured via accounting rather than sampling,
* and is as accurate as ktime_get() is.
*
* Return: -1 if generic vtime is enabled, else total iowait time of @cpu
* Return: total iowait time of @cpu
*/
u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time)
{
@ -589,7 +596,6 @@ u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time)
nr_iowait_cpu(cpu), last_update_time);
}
EXPORT_SYMBOL_GPL(get_cpu_iowait_time_us);
#endif /* CONFIG_NO_HZ_COMMON */
/*
* Use precise platform statistics if available: