[PATCH 0883/1078] sched: make cpu_clock() globally synchronous

[Ingo Molnar]

Alexey Zaytsev reported (and bisected) that the introduction of
cpu_clock() in printk made the timestamps jump back and forth.

Make cpu_clock() more reliable while still keeping it fast when it's
called frequently.

Signed-off-by: Ingo Molnar <mingo@xxxxxxx>
---
 kernel/sched.c |   52 +++++++++++++++++++++++++++++++++++++++++++++++++---
 1 files changed, 49 insertions(+), 3 deletions(-)

diff --git a/kernel/sched.c b/kernel/sched.c
index 8dcdec6..7377222 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -632,11 +632,39 @@ int sysctl_sched_rt_runtime = 950000;
  */
 #define RUNTIME_INF    ((u64)~0ULL)
 
+static const 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);
+
 /*
- * For kernel-internal use: high-speed (but slightly incorrect) per-cpu
- * clock constructed from sched_clock():
+ * 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:
  */
-unsigned long long cpu_clock(int cpu)
+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)
+{
+    unsigned long flags;
+
+    spin_lock_irqsave(&time_sync_lock, flags);
+
+    if (time < prev_global_time) {
+        per_cpu(time_offset, cpu) += prev_global_time - time;
+        time = prev_global_time;
+    } else {
+        prev_global_time = time;
+    }
+
+    spin_unlock_irqrestore(&time_sync_lock, flags);
+
+    return time;
+}
+
+static unsigned long long __cpu_clock(int cpu)
 {
     unsigned long long now;
     unsigned long flags;
@@ -657,6 +685,24 @@ unsigned long long cpu_clock(int 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;
+
+    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);
+
+    return time;
+}
 EXPORT_SYMBOL_GPL(cpu_clock);
 
 #ifndef prepare_arch_switch
-- 
1.5.5


--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/