aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorWaiman Long <longman@redhat.com>2019-05-24 15:42:22 -0400
committerLinus Torvalds <torvalds@linux-foundation.org>2019-05-24 14:17:18 -0700
commit51816e9e113934281b44f1a352852ef7631e75ea (patch)
tree2f2d6cc2f33a22e3a0603d844396bf3f5d5b6592
parent0a72ef89901409847036664c23ba6eee7cf08e0e (diff)
downloadlinux-51816e9e113934281b44f1a352852ef7631e75ea.tar.gz
locking/lock_events: Use this_cpu_add() when necessary
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: ... Given the imprecise nature of the count and the possibility of resetting the count and doing the measurement again, this is not really a big problem to use the unprotected __this_cpu_*() functions. To make the preemption checking code happy, the this_cpu_*() functions will be used if CONFIG_DEBUG_PREEMPT is defined. The imprecise nature of the locking counts are also documented with the suggestion that we should run the measurement a few times with the counts reset in between to get a better picture of what is going on under the hood. Fixes: a8654596f0371 ("locking/rwsem: Enable lock event counting") Suggested-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Waiman Long <longman@redhat.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
-rw-r--r--kernel/locking/lock_events.h42
1 files changed, 40 insertions, 2 deletions
diff --git a/kernel/locking/lock_events.h b/kernel/locking/lock_events.h
index feb1acc54611..46b71af8eef2 100644
--- a/kernel/locking/lock_events.h
+++ b/kernel/locking/lock_events.h
@@ -31,12 +31,50 @@ 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.
+ *
+ * For those architectures that do multi-instruction percpu operation,
+ * preemption in the middle and moving the task to another cpu may cause
+ * a larger error in the count. Again, this will be few and far between.
+ * Given the imprecise nature of the count and the possibility of resetting
+ * the count and doing the measurement again, this is not really a big
+ * problem.
+ *
+ * To get a better picture of what is happening under the hood, it is
+ * suggested that a few measurements should be taken with the counts
+ * reset in between to stamp out outliner because of these possible
+ * error conditions.
+ *
+ * To minimize overhead, we use __this_cpu_*() in all cases except when
+ * CONFIG_DEBUG_PREEMPT is defined. In this particular case, this_cpu_*()
+ * will be used to avoid the appearance of unwanted BUG messages.
+ */
+#ifdef CONFIG_DEBUG_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 +82,7 @@ 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)