summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorDavid Miller <davem@davemloft.net>2009-12-13 18:25:02 -0800
committerIngo Molnar <mingo@elte.hu>2009-12-15 09:04:36 +0100
commitb9f8fcd55bbdb037e5332dbdb7b494f0b70861ac (patch)
tree71b2f8a175269e03e39a5976dc9d24f82b52ec91
parent1a551ae715825bb2a2107a2dd68de024a1fa4e32 (diff)
sched: Fix cpu_clock() in NMIs, on !CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
Relax stable-sched-clock architectures to not save/disable/restore hardirqs in cpu_clock(). The background is that I was trying to resolve a sparc64 perf issue when I discovered this problem. On sparc64 I implement pseudo NMIs by simply running the kernel at IRQ level 14 when local_irq_disable() is called, this allows performance counter events to still come in at IRQ level 15. This doesn't work if any code in an NMI handler does local_irq_save() or local_irq_disable() since the "disable" will kick us back to cpu IRQ level 14 thus letting NMIs back in and we recurse. The only path which that does that in the perf event IRQ handling path is the code supporting frequency based events. It uses cpu_clock(). cpu_clock() simply invokes sched_clock() with IRQs disabled. And that's a fundamental bug all on it's own, particularly for the HAVE_UNSTABLE_SCHED_CLOCK case. NMIs can thus get into the sched_clock() code interrupting the local IRQ disable code sections of it. Furthermore, for the not-HAVE_UNSTABLE_SCHED_CLOCK case, the IRQ disabling done by cpu_clock() is just pure overhead and completely unnecessary. So the core problem is that sched_clock() is not NMI safe, but we are invoking it from NMI contexts in the perf events code (via cpu_clock()). A less important issue is the overhead of IRQ disabling when it isn't necessary in cpu_clock(). CONFIG_HAVE_UNSTABLE_SCHED_CLOCK architectures are not affected by this patch. Signed-off-by: David S. Miller <davem@davemloft.net> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> LKML-Reference: <20091213.182502.215092085.davem@davemloft.net> Signed-off-by: Ingo Molnar <mingo@elte.hu>
-rw-r--r--kernel/sched_clock.c23
1 files changed, 15 insertions, 8 deletions
diff --git a/kernel/sched_clock.c b/kernel/sched_clock.c
index 479ce5682d7..5b496132c28 100644
--- a/kernel/sched_clock.c
+++ b/kernel/sched_clock.c
@@ -236,6 +236,18 @@ void sched_clock_idle_wakeup_event(u64 delta_ns)
}
EXPORT_SYMBOL_GPL(sched_clock_idle_wakeup_event);
+unsigned long long cpu_clock(int cpu)
+{
+ unsigned long long clock;
+ unsigned long flags;
+
+ local_irq_save(flags);
+ clock = sched_clock_cpu(cpu);
+ local_irq_restore(flags);
+
+ return clock;
+}
+
#else /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */
void sched_clock_init(void)
@@ -251,17 +263,12 @@ u64 sched_clock_cpu(int cpu)
return sched_clock();
}
-#endif /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */
unsigned long long cpu_clock(int cpu)
{
- unsigned long long clock;
- unsigned long flags;
+ return sched_clock_cpu(cpu);
+}
- local_irq_save(flags);
- clock = sched_clock_cpu(cpu);
- local_irq_restore(flags);
+#endif /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */
- return clock;
-}
EXPORT_SYMBOL_GPL(cpu_clock);