c676329abb
For people who otherwise get to write: cpu_clock(smp_processor_id()), there is now: local_clock(). Also, as per suggestion from Andrew, provide some documentation on the various clock interfaces, and minimize the unsigned long long vs u64 mess. Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Jens Axboe <jaxboe@fusionio.com> LKML-Reference: <1275052414.1645.52.camel@laptop> Signed-off-by: Ingo Molnar <mingo@elte.hu>
117 lines
2.7 KiB
C
117 lines
2.7 KiB
C
/*
|
|
* tracing clocks
|
|
*
|
|
* Copyright (C) 2009 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
|
|
*
|
|
* Implements 3 trace clock variants, with differing scalability/precision
|
|
* tradeoffs:
|
|
*
|
|
* - local: CPU-local trace clock
|
|
* - medium: scalable global clock with some jitter
|
|
* - global: globally monotonic, serialized clock
|
|
*
|
|
* Tracer plugins will chose a default from these clocks.
|
|
*/
|
|
#include <linux/spinlock.h>
|
|
#include <linux/irqflags.h>
|
|
#include <linux/hardirq.h>
|
|
#include <linux/module.h>
|
|
#include <linux/percpu.h>
|
|
#include <linux/sched.h>
|
|
#include <linux/ktime.h>
|
|
#include <linux/trace_clock.h>
|
|
|
|
#include "trace.h"
|
|
|
|
/*
|
|
* trace_clock_local(): the simplest and least coherent tracing clock.
|
|
*
|
|
* Useful for tracing that does not cross to other CPUs nor
|
|
* does it go through idle events.
|
|
*/
|
|
u64 notrace trace_clock_local(void)
|
|
{
|
|
u64 clock;
|
|
int resched;
|
|
|
|
/*
|
|
* sched_clock() is an architecture implemented, fast, scalable,
|
|
* lockless clock. It is not guaranteed to be coherent across
|
|
* CPUs, nor across CPU idle events.
|
|
*/
|
|
resched = ftrace_preempt_disable();
|
|
clock = sched_clock();
|
|
ftrace_preempt_enable(resched);
|
|
|
|
return clock;
|
|
}
|
|
|
|
/*
|
|
* trace_clock(): 'inbetween' trace clock. Not completely serialized,
|
|
* but not completely incorrect when crossing CPUs either.
|
|
*
|
|
* This is based on cpu_clock(), which will allow at most ~1 jiffy of
|
|
* jitter between CPUs. So it's a pretty scalable clock, but there
|
|
* can be offsets in the trace data.
|
|
*/
|
|
u64 notrace trace_clock(void)
|
|
{
|
|
return local_clock();
|
|
}
|
|
|
|
|
|
/*
|
|
* trace_clock_global(): special globally coherent trace clock
|
|
*
|
|
* It has higher overhead than the other trace clocks but is still
|
|
* an order of magnitude faster than GTOD derived hardware clocks.
|
|
*
|
|
* Used by plugins that need globally coherent timestamps.
|
|
*/
|
|
|
|
/* keep prev_time and lock in the same cacheline. */
|
|
static struct {
|
|
u64 prev_time;
|
|
arch_spinlock_t lock;
|
|
} trace_clock_struct ____cacheline_aligned_in_smp =
|
|
{
|
|
.lock = (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED,
|
|
};
|
|
|
|
u64 notrace trace_clock_global(void)
|
|
{
|
|
unsigned long flags;
|
|
int this_cpu;
|
|
u64 now;
|
|
|
|
local_irq_save(flags);
|
|
|
|
this_cpu = raw_smp_processor_id();
|
|
now = cpu_clock(this_cpu);
|
|
/*
|
|
* If in an NMI context then dont risk lockups and return the
|
|
* cpu_clock() time:
|
|
*/
|
|
if (unlikely(in_nmi()))
|
|
goto out;
|
|
|
|
arch_spin_lock(&trace_clock_struct.lock);
|
|
|
|
/*
|
|
* TODO: if this happens often then maybe we should reset
|
|
* my_scd->clock to prev_time+1, to make sure
|
|
* we start ticking with the local clock from now on?
|
|
*/
|
|
if ((s64)(now - trace_clock_struct.prev_time) < 0)
|
|
now = trace_clock_struct.prev_time + 1;
|
|
|
|
trace_clock_struct.prev_time = now;
|
|
|
|
arch_spin_unlock(&trace_clock_struct.lock);
|
|
|
|
out:
|
|
local_irq_restore(flags);
|
|
|
|
return now;
|
|
}
|