Re: [RFC PATCH 5/6] bpf: Implement function bpf_read_pmu() that get the selected hardware PMU conuter

[Peter Zijlstra <peterz@infradead.org>]

On Fri, Jul 17, 2015 at 01:05:41PM +0200, Peter Zijlstra wrote:
> On Fri, Jul 17, 2015 at 06:43:35PM +0800, kaixu xia wrote:
> > The function bpf_read_pmu() can get the specific map key, convert
> > the corresponding map value to the pointer to struct perf_event and
> > return the Hardware PMU counter value.
> 
> Thanks for having me on Cc :/
> 
> > Signed-off-by: kaixu xia <xiakaixu@huawei.com>
> > ---
> > +static u64 bpf_read_pmu(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
> > +{
> > +	void *value = (void *) (unsigned long) r1;
> > +	struct perf_event *event;
> > +	u64 count;
> > +
> > +	if (!value || !(*(unsigned long *)value))
> > +		return 0;
> > +
> > +	event = (struct perf_event *)(*(unsigned long *)value);
> > +
> > +	if (event->state == PERF_EVENT_STATE_ACTIVE)
> > +		event->pmu->read(event);
> > +
> > +	count = local64_read(&event->count);
> > +
> > +	return count;
> > +}
> 
> Hell no, that's way broken.

You want something long these lines..

---
 include/linux/perf_event.h |  1 +
 kernel/events/core.c       | 22 +++++++++++++++++++---
 2 files changed, 20 insertions(+), 3 deletions(-)

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 2027809433b3..6e7be7345511 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -661,6 +661,7 @@ extern void perf_pmu_migrate_context(struct pmu *pmu,
 				int src_cpu, int dst_cpu);
 extern u64 perf_event_read_value(struct perf_event *event,
 				 u64 *enabled, u64 *running);
+extern u64 perf_event_read(struct perf_event *event);
 
 
 struct perf_sample_data {
diff --git a/kernel/events/core.c b/kernel/events/core.c
index d3dae3419b99..53521360c13d 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3212,15 +3212,31 @@ static inline u64 perf_event_count(struct perf_event *event)
 	return __perf_event_count(event);
 }
 
-static u64 perf_event_read(struct perf_event *event)
+u64 perf_event_read(struct perf_event *event)
 {
 	/*
 	 * If event is enabled and currently active on a CPU, update the
 	 * value in the event structure:
 	 */
 	if (event->state == PERF_EVENT_STATE_ACTIVE) {
-		smp_call_function_single(event->oncpu,
-					 __perf_event_read, event, 1);
+		/*
+		 * If the event is for the current task, its guaranteed that we
+		 * never need the cross cpu call, and therefore can allow this
+		 * to be called with IRQs disabled.
+		 *
+		 * Avoids the warning otherwise generated by
+		 * smp_call_function_single().
+		 */
+		if (event->ctx->task == current) {
+			unsigned long flags;
+
+			local_irq_save(flags);
+			__perf_event_read(event);
+			local_irq_restore(flags);
+		} else {
+			smp_call_function_single(event->oncpu,
+					__perf_event_read, event, 1);
+		}
 	} else if (event->state == PERF_EVENT_STATE_INACTIVE) {
 		struct perf_event_context *ctx = event->ctx;
 		unsigned long flags;