perf/core: Introduce PMU_EV_CAP_READ_ACTIVE_PKG

Introduce the flag PMU_EV_CAP_READ_ACTIVE_PKG, useful for uncore events,
that allows a PMU to signal the generic perf code that an event is readable
in the current CPU if the event is active in a CPU in the same package as
the current CPU.

This is an optimization that avoids a unnecessary IPI for the common case
where uncore events are run and read in the same package but in
different CPUs.

As an example, the IPI removal speeds up perf_read() in my Haswell system
as follows:

  - For event UNC_C_LLC_LOOKUP: From 260 us to 31 us.
  - For event RAPL's power/energy-cores/: From to 255 us to 27 us.

For the optimization to work, all events in the group must have it
(similarly to PERF_EV_CAP_SOFTWARE).

Signed-off-by: David Carrillo-Cisneros <[email protected]>
Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Cc: Alexander Shishkin <[email protected]>
Cc: Arnaldo Carvalho de Melo <[email protected]>
Cc: David Carrillo-Cisneros <[email protected]>
Cc: Jiri Olsa <[email protected]>
Cc: Kan Liang <[email protected]>
Cc: Linus Torvalds <[email protected]>
Cc: Paul Turner <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Stephane Eranian <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: Vegard Nossum <[email protected]>
Cc: Vince Weaver <[email protected]>
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Ingo Molnar <[email protected]>

Author: David Carrillo-Cisneros

include/linux/perf_event.h

@@ -514,8 +514,11 @@ typedef void (*perf_overflow_handler_t)(struct perf_event *,
  * Event capabilities. For event_caps and groups caps.
  *
  * PERF_EV_CAP_SOFTWARE: Is a software event.
+ * PERF_EV_CAP_READ_ACTIVE_PKG: A CPU event (or cgroup event) that can be read
+ * from any CPU in the package where it is active.
  */
 #define PERF_EV_CAP_SOFTWARE		BIT(0)
+#define PERF_EV_CAP_READ_ACTIVE_PKG	BIT(1)
 
 #define SWEVENT_HLIST_BITS		8
 #define SWEVENT_HLIST_SIZE		(1 << SWEVENT_HLIST_BITS)

kernel/events/core.c

@@ -3424,6 +3424,22 @@ struct perf_read_data {
 	int ret;
 };
 
+static int find_cpu_to_read(struct perf_event *event, int local_cpu)
+{
+	int event_cpu = event->oncpu;
+	u16 local_pkg, event_pkg;
+
+	if (event->group_caps & PERF_EV_CAP_READ_ACTIVE_PKG) {
+		event_pkg =  topology_physical_package_id(event_cpu);
+		local_pkg =  topology_physical_package_id(local_cpu);
+
+		if (event_pkg == local_pkg)
+			return local_cpu;
+	}
+
+	return event_cpu;
+}
+
 /*
  * Cross CPU call to read the hardware event
  */
@@ -3545,7 +3561,7 @@ u64 perf_event_read_local(struct perf_event *event)
 
 static int perf_event_read(struct perf_event *event, bool group)
 {
-	int ret = 0;
+	int ret = 0, cpu_to_read, local_cpu;
 
 	/*
 	 * If event is enabled and currently active on a CPU, update the
@@ -3557,7 +3573,12 @@ static int perf_event_read(struct perf_event *event, bool group)
 			.group = group,
 			.ret = 0,
 		};
-		ret = smp_call_function_single(event->oncpu, __perf_event_read, &data, 1);
+
+		local_cpu = get_cpu();
+		cpu_to_read = find_cpu_to_read(event, local_cpu);
+		put_cpu();
+
+		ret = smp_call_function_single(cpu_to_read, __perf_event_read, &data, 1);
 		/* The event must have been read from an online CPU: */
 		WARN_ON_ONCE(ret);
 		ret = ret ? : data.ret;