On Mon, Oct 12, 2015 at 09:02:42AM +0000, Kaixu Xia wrote:
--- a/include/linux/perf_event.hTry and guarantee sample_disable lives in the same cacheline as
+++ b/include/linux/perf_event.h
@@ -483,6 +483,8 @@ struct perf_event {
perf_overflow_handler_t overflow_handler;
void *overflow_handler_context;
+ atomic_t *sample_disable;
+
#ifdef CONFIG_EVENT_TRACING
struct trace_event_call *tp_event;
struct event_filter *filter;
diff --git a/kernel/events/core.c b/kernel/events/core.c
index b11756f..f6ef45c 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -6337,6 +6337,9 @@ static int __perf_event_overflow(struct perf_event *event,
irq_work_queue(&event->pending);
}
+ if ((event->sample_disable) && atomic_read(event->sample_disable))
+ return ret;
+
if (event->overflow_handler)
event->overflow_handler(event, data, regs);
else
overflow_handler.
I think we should at the very least replace the kzalloc() currently used
with a cacheline aligned alloc, and check the structure layout to verify
these two do in fact share a cacheline.