mirror of
https://github.com/torvalds/linux.git
synced 2024-12-27 21:33:00 +00:00
354879bb97
This patch fixes 3 issues: a) it removes the dependency on jiffies, because jiffies are incremented by a single CPU, and the tick is not synchronized between CPUs. Therefore relying on it to calculate a window to clip whacky TSC values doesn't work as it can drift around. So instead use [GTOD, GTOD+TICK_NSEC) as the window. b) __update_sched_clock() did (roughly speaking): delta = sched_clock() - scd->tick_raw; clock += delta; Which gives exponential growth, instead of linear. c) allows the sched_clock_cpu() value to warp the u64 without breaking. the results are more reliable sched_clock() deltas: before after sched_clock cpu_clock: 15750 51312 51488 cpu_clock: 59719 51052 50947 cpu_clock: 15879 51249 51061 cpu_clock: 1 50933 51198 cpu_clock: 1 50931 51039 cpu_clock: 1 51093 50981 cpu_clock: 1 51043 51040 cpu_clock: 1 50959 50938 cpu_clock: 1 50981 51011 cpu_clock: 1 51364 51212 cpu_clock: 1 51219 51273 cpu_clock: 1 51389 51048 cpu_clock: 1 51285 51611 cpu_clock: 1 50964 51137 cpu_clock: 1 50973 50968 cpu_clock: 1 50967 50972 cpu_clock: 1 58910 58485 cpu_clock: 1 51082 51025 cpu_clock: 1 50957 50958 cpu_clock: 1 50958 50957 cpu_clock: 1006128 51128 50971 cpu_clock: 1 51107 51155 cpu_clock: 1 51371 51081 cpu_clock: 1 51104 51365 cpu_clock: 1 51363 51309 cpu_clock: 1 51107 51160 cpu_clock: 1 51139 51100 cpu_clock: 1 51216 51136 cpu_clock: 1 51207 51215 cpu_clock: 1 51087 51263 cpu_clock: 1 51249 51177 cpu_clock: 1 51519 51412 cpu_clock: 1 51416 51255 cpu_clock: 1 51591 51594 cpu_clock: 1 50966 51374 cpu_clock: 1 50966 50966 cpu_clock: 1 51291 50948 cpu_clock: 1 50973 50867 cpu_clock: 1 50970 50970 cpu_clock: 998306 50970 50971 cpu_clock: 1 50971 50970 cpu_clock: 1 50970 50970 cpu_clock: 1 50971 50971 cpu_clock: 1 50970 50970 cpu_clock: 1 51351 50970 cpu_clock: 1 50970 51352 cpu_clock: 1 50971 50970 cpu_clock: 1 50970 50970 cpu_clock: 1 51321 50971 cpu_clock: 1 50974 51324 Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Ingo Molnar <mingo@elte.hu>
264 lines
5.7 KiB
C
264 lines
5.7 KiB
C
/*
|
|
* sched_clock for unstable cpu clocks
|
|
*
|
|
* Copyright (C) 2008 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
|
|
*
|
|
* Updates and enhancements:
|
|
* Copyright (C) 2008 Red Hat, Inc. Steven Rostedt <srostedt@redhat.com>
|
|
*
|
|
* Based on code by:
|
|
* Ingo Molnar <mingo@redhat.com>
|
|
* Guillaume Chazarain <guichaz@gmail.com>
|
|
*
|
|
* Create a semi stable clock from a mixture of other events, including:
|
|
* - gtod
|
|
* - sched_clock()
|
|
* - explicit idle events
|
|
*
|
|
* We use gtod as base and the unstable clock deltas. The deltas are filtered,
|
|
* making it monotonic and keeping it within an expected window.
|
|
*
|
|
* Furthermore, explicit sleep and wakeup hooks allow us to account for time
|
|
* that is otherwise invisible (TSC gets stopped).
|
|
*
|
|
* The clock: sched_clock_cpu() is monotonic per cpu, and should be somewhat
|
|
* consistent between cpus (never more than 2 jiffies difference).
|
|
*/
|
|
#include <linux/sched.h>
|
|
#include <linux/percpu.h>
|
|
#include <linux/spinlock.h>
|
|
#include <linux/ktime.h>
|
|
#include <linux/module.h>
|
|
|
|
/*
|
|
* Scheduler clock - returns current time in nanosec units.
|
|
* This is default implementation.
|
|
* Architectures and sub-architectures can override this.
|
|
*/
|
|
unsigned long long __attribute__((weak)) sched_clock(void)
|
|
{
|
|
return (unsigned long long)jiffies * (NSEC_PER_SEC / HZ);
|
|
}
|
|
|
|
static __read_mostly int sched_clock_running;
|
|
|
|
#ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
|
|
|
|
struct sched_clock_data {
|
|
/*
|
|
* Raw spinlock - this is a special case: this might be called
|
|
* from within instrumentation code so we dont want to do any
|
|
* instrumentation ourselves.
|
|
*/
|
|
raw_spinlock_t lock;
|
|
|
|
u64 tick_raw;
|
|
u64 tick_gtod;
|
|
u64 clock;
|
|
};
|
|
|
|
static DEFINE_PER_CPU_SHARED_ALIGNED(struct sched_clock_data, sched_clock_data);
|
|
|
|
static inline struct sched_clock_data *this_scd(void)
|
|
{
|
|
return &__get_cpu_var(sched_clock_data);
|
|
}
|
|
|
|
static inline struct sched_clock_data *cpu_sdc(int cpu)
|
|
{
|
|
return &per_cpu(sched_clock_data, cpu);
|
|
}
|
|
|
|
void sched_clock_init(void)
|
|
{
|
|
u64 ktime_now = ktime_to_ns(ktime_get());
|
|
int cpu;
|
|
|
|
for_each_possible_cpu(cpu) {
|
|
struct sched_clock_data *scd = cpu_sdc(cpu);
|
|
|
|
scd->lock = (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;
|
|
scd->tick_raw = 0;
|
|
scd->tick_gtod = ktime_now;
|
|
scd->clock = ktime_now;
|
|
}
|
|
|
|
sched_clock_running = 1;
|
|
}
|
|
|
|
/*
|
|
* min,max except they take wrapping into account
|
|
*/
|
|
|
|
static inline u64 wrap_min(u64 x, u64 y)
|
|
{
|
|
return (s64)(x - y) < 0 ? x : y;
|
|
}
|
|
|
|
static inline u64 wrap_max(u64 x, u64 y)
|
|
{
|
|
return (s64)(x - y) > 0 ? x : y;
|
|
}
|
|
|
|
/*
|
|
* update the percpu scd from the raw @now value
|
|
*
|
|
* - filter out backward motion
|
|
* - use the GTOD tick value to create a window to filter crazy TSC values
|
|
*/
|
|
static u64 __update_sched_clock(struct sched_clock_data *scd, u64 now)
|
|
{
|
|
s64 delta = now - scd->tick_raw;
|
|
u64 clock, min_clock, max_clock;
|
|
|
|
WARN_ON_ONCE(!irqs_disabled());
|
|
|
|
if (unlikely(delta < 0))
|
|
delta = 0;
|
|
|
|
/*
|
|
* scd->clock = clamp(scd->tick_gtod + delta,
|
|
* max(scd->tick_gtod, scd->clock),
|
|
* scd->tick_gtod + TICK_NSEC);
|
|
*/
|
|
|
|
clock = scd->tick_gtod + delta;
|
|
min_clock = wrap_max(scd->tick_gtod, scd->clock);
|
|
max_clock = scd->tick_gtod + TICK_NSEC;
|
|
|
|
clock = wrap_max(clock, min_clock);
|
|
clock = wrap_min(clock, max_clock);
|
|
|
|
scd->clock = clock;
|
|
|
|
return scd->clock;
|
|
}
|
|
|
|
static void lock_double_clock(struct sched_clock_data *data1,
|
|
struct sched_clock_data *data2)
|
|
{
|
|
if (data1 < data2) {
|
|
__raw_spin_lock(&data1->lock);
|
|
__raw_spin_lock(&data2->lock);
|
|
} else {
|
|
__raw_spin_lock(&data2->lock);
|
|
__raw_spin_lock(&data1->lock);
|
|
}
|
|
}
|
|
|
|
u64 sched_clock_cpu(int cpu)
|
|
{
|
|
struct sched_clock_data *scd = cpu_sdc(cpu);
|
|
u64 now, clock, this_clock, remote_clock;
|
|
|
|
if (unlikely(!sched_clock_running))
|
|
return 0ull;
|
|
|
|
WARN_ON_ONCE(!irqs_disabled());
|
|
now = sched_clock();
|
|
|
|
if (cpu != raw_smp_processor_id()) {
|
|
struct sched_clock_data *my_scd = this_scd();
|
|
|
|
lock_double_clock(scd, my_scd);
|
|
|
|
this_clock = __update_sched_clock(my_scd, now);
|
|
remote_clock = scd->clock;
|
|
|
|
/*
|
|
* Use the opportunity that we have both locks
|
|
* taken to couple the two clocks: we take the
|
|
* larger time as the latest time for both
|
|
* runqueues. (this creates monotonic movement)
|
|
*/
|
|
if (likely((s64)(remote_clock - this_clock) < 0)) {
|
|
clock = this_clock;
|
|
scd->clock = clock;
|
|
} else {
|
|
/*
|
|
* Should be rare, but possible:
|
|
*/
|
|
clock = remote_clock;
|
|
my_scd->clock = remote_clock;
|
|
}
|
|
|
|
__raw_spin_unlock(&my_scd->lock);
|
|
} else {
|
|
__raw_spin_lock(&scd->lock);
|
|
clock = __update_sched_clock(scd, now);
|
|
}
|
|
|
|
__raw_spin_unlock(&scd->lock);
|
|
|
|
return clock;
|
|
}
|
|
|
|
void sched_clock_tick(void)
|
|
{
|
|
struct sched_clock_data *scd = this_scd();
|
|
u64 now, now_gtod;
|
|
|
|
if (unlikely(!sched_clock_running))
|
|
return;
|
|
|
|
WARN_ON_ONCE(!irqs_disabled());
|
|
|
|
now_gtod = ktime_to_ns(ktime_get());
|
|
now = sched_clock();
|
|
|
|
__raw_spin_lock(&scd->lock);
|
|
scd->tick_raw = now;
|
|
scd->tick_gtod = now_gtod;
|
|
__update_sched_clock(scd, now);
|
|
__raw_spin_unlock(&scd->lock);
|
|
}
|
|
|
|
/*
|
|
* We are going deep-idle (irqs are disabled):
|
|
*/
|
|
void sched_clock_idle_sleep_event(void)
|
|
{
|
|
sched_clock_cpu(smp_processor_id());
|
|
}
|
|
EXPORT_SYMBOL_GPL(sched_clock_idle_sleep_event);
|
|
|
|
/*
|
|
* We just idled delta nanoseconds (called with irqs disabled):
|
|
*/
|
|
void sched_clock_idle_wakeup_event(u64 delta_ns)
|
|
{
|
|
sched_clock_tick();
|
|
touch_softlockup_watchdog();
|
|
}
|
|
EXPORT_SYMBOL_GPL(sched_clock_idle_wakeup_event);
|
|
|
|
#else /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */
|
|
|
|
void sched_clock_init(void)
|
|
{
|
|
sched_clock_running = 1;
|
|
}
|
|
|
|
u64 sched_clock_cpu(int cpu)
|
|
{
|
|
if (unlikely(!sched_clock_running))
|
|
return 0;
|
|
|
|
return sched_clock();
|
|
}
|
|
|
|
#endif
|
|
|
|
unsigned long long cpu_clock(int cpu)
|
|
{
|
|
unsigned long long clock;
|
|
unsigned long flags;
|
|
|
|
local_irq_save(flags);
|
|
clock = sched_clock_cpu(cpu);
|
|
local_irq_restore(flags);
|
|
|
|
return clock;
|
|
}
|
|
EXPORT_SYMBOL_GPL(cpu_clock);
|