i hope not :)
yes, please test the patch below - does it fix the problem?
Ingo
------------------>
Subject: sched: make cpu_clock() globally synchronous
From: Ingo Molnar <mingo@elte.hu>
Date: Thu Feb 28 21:00:21 CET 2008
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.
Bisected-by: Alexey Zaytsev <alexey.zaytsev@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
kernel/sched.c | 52 +++++++++++++++++++++++++++++++++++++++++++++++++---
1 file changed, 49 insertions(+), 3 deletions(-)
Index: linux/kernel/sched.c
===================================================================
--- linux.orig/kernel/sched.c
+++ linux/kernel/sched.c
@@ -710,11 +710,39 @@ static inline u64 global_rt_runtime(void
return (u64)sysctl_sched_rt_runtime * NSEC_PER_USEC;
}
+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;
@@ -735,6 +763,24 @@ 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_clock(time, cpu);
+
+ return time;
+}
EXPORT_SYMBOL_GPL(cpu_clock);
#ifndef prepare_arch_switch
--
