The kernel test robot has reported that the use of __this_cpu_add()
causes bug messages like:
BUG: using __this_cpu_add() in preemptible [00000000] code: ...
This is only an issue on preempt kernel where preemption can happen in
the middle of a percpu operation. We are still using __this_cpu_*() for
!preempt kernel to avoid additional overhead in case CONFIG_PREEMPT_COUNT
is set.
v2: Simplify the condition to just preempt or !preempt.
v3: Document the imprecise nature of the percpu count.
Fixes: a8654596f0371 ("locking/rwsem: Enable lock event counting")
Signed-off-by: Waiman Long <[email protected]>
---
kernel/locking/lock_events.h | 32 ++++++++++++++++++++++++++++++--
1 file changed, 30 insertions(+), 2 deletions(-)
diff --git a/kernel/locking/lock_events.h b/kernel/locking/lock_events.h
index feb1acc54611..6bcb96b7e1d3 100644
--- a/kernel/locking/lock_events.h
+++ b/kernel/locking/lock_events.h
@@ -30,13 +30,41 @@ enum lock_events {
*/
DECLARE_PER_CPU(unsigned long, lockevents[lockevent_num]);
+/*
+ * The purpose of the lock event counting subsystem is to provide a low
+ * overhead way to record the number of specific locking events by using
+ * percpu counters. It is the percpu sum that matters, not specifically
+ * how many of them happens in each cpu.
+ *
+ * It is possible that the same percpu counter may be modified in both
+ * the process and interrupt contexts. For architectures that perform
+ * percpu operation with multiple instructions, it is possible to lose
+ * count if a process context percpu update is interrupted in the middle
+ * and the same counter is updated in the interrupt context. Therefore,
+ * the generated percpu sum may not be precise. The error, if any, should
+ * be small and insignificant.
+ *
+ * In !preempt kernel, we can just use __this_cpu_*() as preemption
+ * won't happen in the middle of the percpu operation. In preempt kernel,
+ * preemption happens in the middle of the percpu operation may produce
+ * incorrect result that can be signficant if the task is moved to a
+ * different cpu.
+ */
+#ifdef CONFIG_PREEMPT
+#define lockevent_percpu_inc(x) this_cpu_inc(x)
+#define lockevent_percpu_add(x, v) this_cpu_add(x, v)
+#else
+#define lockevent_percpu_inc(x) __this_cpu_inc(x)
+#define lockevent_percpu_add(x, v) __this_cpu_add(x, v)
+#endif
+
/*
* Increment the PV qspinlock statistical counters
*/
static inline void __lockevent_inc(enum lock_events event, bool cond)
{
if (cond)
- __this_cpu_inc(lockevents[event]);
+ lockevent_percpu_inc(lockevents[event]);
}
#define lockevent_inc(ev) __lockevent_inc(LOCKEVENT_ ##ev, true)
@@ -44,7 +72,7 @@ static inline void __lockevent_inc(enum lock_events event,
bool cond)
static inline void __lockevent_add(enum lock_events event, int inc)
{
- __this_cpu_add(lockevents[event], inc);
+ lockevent_percpu_add(lockevents[event], inc);
}
#define lockevent_add(ev, c) __lockevent_add(LOCKEVENT_ ##ev, c)
--
2.18.1
