perf core: Add PERF_COUNT_SW_CGROUP_SWITCHES event

This patch adds a new software event to count context switches
involving cgroup switches.  So it's counted only if cgroups of
previous and next tasks are different.  Note that it only checks the
cgroups in the perf_event subsystem.  For cgroup v2, it shouldn't
matter anyway.

One can argue that we can do this by using existing sched_switch event
with eBPF.  But some systems might not have eBPF for some reason so
I'd like to add this as a simple way.

Signed-off-by: Namhyung Kim <[email protected]>
Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Link: https://lkml.kernel.org/r/[email protected]

include/linux/perf_event.h

@@ -1218,6 +1218,13 @@ static inline void perf_event_task_sched_out(struct task_struct *prev,
 	if (__perf_sw_enabled(PERF_COUNT_SW_CONTEXT_SWITCHES))
 		__perf_sw_event_sched(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, 0);
 
+#ifdef CONFIG_CGROUP_PERF
+	if (__perf_sw_enabled(PERF_COUNT_SW_CGROUP_SWITCHES) &&
+	    perf_cgroup_from_task(prev, NULL) !=
+	    perf_cgroup_from_task(next, NULL))
+		__perf_sw_event_sched(PERF_COUNT_SW_CGROUP_SWITCHES, 1, 0);
+#endif
+
 	if (static_branch_unlikely(&perf_sched_events))
 		__perf_event_task_sched_out(prev, next);
 }

include/uapi/linux/perf_event.h

@@ -112,6 +112,7 @@ enum perf_sw_ids {
 	PERF_COUNT_SW_EMULATION_FAULTS		= 8,
 	PERF_COUNT_SW_DUMMY			= 9,
 	PERF_COUNT_SW_BPF_OUTPUT		= 10,
+	PERF_COUNT_SW_CGROUP_SWITCHES		= 11,
 
 	PERF_COUNT_SW_MAX,			/* non-ABI */
 };