sched: sched_clock_cpu() based cpu_clock()

with sched_clock_cpu() being reasonably in sync between cpus (max 1 jiffy
difference) use this to provide cpu_clock().

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
Cc: Mike Galbraith <efault@gmx.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

diff --git a/kernel/sched.c b/kernel/sched.c
index 874b6da154303e428baeed022914c17096e4879b..eb3454c410fab4765dd10e2c5106be1b04bed889 100644 (file)
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -818,82 +818,6 @@ static inline u64 global_rt_runtime(void)
        return (u64)sysctl_sched_rt_runtime * NSEC_PER_USEC;
 }
 
-unsigned long long time_sync_thresh = 100000;
-
-static DEFINE_PER_CPU(unsigned long long, time_offset);
-static DEFINE_PER_CPU(unsigned long long, prev_cpu_time);
-
-/*
- * Global lock which we take every now and then to synchronize
- * the CPUs time. This method is not warp-safe, but it's good
- * enough to synchronize slowly diverging time sources and thus
- * it's good enough for tracing:
- */
-static DEFINE_SPINLOCK(time_sync_lock);
-static unsigned long long prev_global_time;
-
-static unsigned long long __sync_cpu_clock(unsigned long long time, int cpu)
-{
-       /*
-        * We want this inlined, to not get tracer function calls
-        * in this critical section:
-        */
-       spin_acquire(&time_sync_lock.dep_map, 0, 0, _THIS_IP_);
-       __raw_spin_lock(&time_sync_lock.raw_lock);
-
-       if (time < prev_global_time) {
-               per_cpu(time_offset, cpu) += prev_global_time - time;
-               time = prev_global_time;
-       } else {
-               prev_global_time = time;
-       }
-
-       __raw_spin_unlock(&time_sync_lock.raw_lock);
-       spin_release(&time_sync_lock.dep_map, 1, _THIS_IP_);
-
-       return time;
-}
-
-static unsigned long long __cpu_clock(int cpu)
-{
-       unsigned long long now;
-
-       /*
-        * Only call sched_clock() if the scheduler has already been
-        * initialized (some code might call cpu_clock() very early):
-        */
-       if (unlikely(!scheduler_running))
-               return 0;
-
-       now = sched_clock_cpu(cpu);
-
-       return now;
-}
-
-/*
- * For kernel-internal use: high-speed (but slightly incorrect) per-cpu
- * clock constructed from sched_clock():
- */
-unsigned long long cpu_clock(int cpu)
-{
-       unsigned long long prev_cpu_time, time, delta_time;
-       unsigned long flags;
-
-       local_irq_save(flags);
-       prev_cpu_time = per_cpu(prev_cpu_time, cpu);
-       time = __cpu_clock(cpu) + per_cpu(time_offset, cpu);
-       delta_time = time-prev_cpu_time;
-
-       if (unlikely(delta_time > time_sync_thresh)) {
-               time = __sync_cpu_clock(time, cpu);
-               per_cpu(prev_cpu_time, cpu) = time;
-       }
-       local_irq_restore(flags);
-
-       return time;
-}
-EXPORT_SYMBOL_GPL(cpu_clock);
-
 #ifndef prepare_arch_switch
 # define prepare_arch_switch(next)     do { } while (0)
 #endif

diff --git a/kernel/sched_clock.c b/kernel/sched_clock.c
index ce05271219abcc5bf7dd4087d91ce98f487ee2e9..3c696db594525f9dba38ec95ce01820d65876da3 100644 (file)
--- a/kernel/sched_clock.c
+++ b/kernel/sched_clock.c
@@ -244,3 +244,15 @@ unsigned long long __attribute__((weak)) sched_clock(void)
 {
        return (unsigned long long)jiffies * (NSEC_PER_SEC / HZ);
 }
+
+unsigned long long cpu_clock(int cpu)
+{
+       unsigned long long clock;
+       unsigned long flags;
+
+       raw_local_irq_save(flags);
+       clock = sched_clock_cpu(cpu);
+       raw_local_irq_restore(flags);
+
+       return clock;
+}