sched: fix cpu clock

David Miller pointed it out that nothing in cpu_clock() sets
prev_cpu_time. This caused __sync_cpu_clock() to be called
all the time - against the intention of this code.

The result was that in practice we hit a global spinlock every
time cpu_clock() is called - which - even though cpu_clock()
is used for tracing and debugging, is suboptimal.

While at it, also:

- move the irq disabling to the outest layer,
  this should make cpu_clock() warp-free when called with irqs
  enabled.

- use long long instead of cycles_t - for platforms where cycles_t
  is 32-bit.

Reported-by: David Miller <davem@davemloft.net>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

diff --git a/kernel/sched.c b/kernel/sched.c
index f98f75f..9457106 100644 (file)
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -910,11 +910,14 @@ static DEFINE_PER_CPU(unsigned long long, prev_cpu_time);
 static DEFINE_SPINLOCK(time_sync_lock);
 static unsigned long long prev_global_time;
 
-static unsigned long long __sync_cpu_clock(cycles_t time, int cpu)
+static unsigned long long __sync_cpu_clock(unsigned long long time, int cpu)
 {
-       unsigned long flags;
-
-       spin_lock_irqsave(&time_sync_lock, flags);
+       /*
+        * 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;
@@ -923,7 +926,8 @@ static unsigned long long __sync_cpu_clock(cycles_t time, int cpu)
                prev_global_time = time;
        }
 
-       spin_unlock_irqrestore(&time_sync_lock, flags);
+       __raw_spin_unlock(&time_sync_lock.raw_lock);
+       spin_release(&time_sync_lock.dep_map, 1, _THIS_IP_);
 
        return time;
 }
@@ -931,7 +935,6 @@ static unsigned long long __sync_cpu_clock(cycles_t time, int cpu)
 static unsigned long long __cpu_clock(int cpu)
 {
        unsigned long long now;
-       unsigned long flags;
        struct rq *rq;
 
        /*
@@ -941,11 +944,9 @@ static unsigned long long __cpu_clock(int cpu)
        if (unlikely(!scheduler_running))
                return 0;
 
-       local_irq_save(flags);
        rq = cpu_rq(cpu);
        update_rq_clock(rq);
        now = rq->clock;
-       local_irq_restore(flags);
 
        return now;
 }
@@ -957,13 +958,18 @@ static unsigned long long __cpu_clock(int cpu)
 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))
+       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;
 }