[PATCH 1/3] perf: Allow per-task-per-cpu counters

[Peter Zijlstra <a.p.zijlstra@chello.nl>]

[-- Attachment #1: perf1.patch --]
[-- Type: text/plain, Size: 1755 bytes --]

In order to allow for per-task-per-cpu counters, useful for
scalability when profiling task hierarchies, we allow installing
events with event->cpu != -1 in task contexts.

__perf_event_sched_in() already skips events where ->cpu mis-matches
the current cpu, fix up __perf_install_in_context() and
__perf_event_enable() to also respect this filter.

This does lead to vary hard to interpret enabled/running times for
such counters, but I don't see a simple solution for that.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
---
 kernel/perf_event.c |   11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

Index: linux-2.6/kernel/perf_event.c
===================================================================
--- linux-2.6.orig/kernel/perf_event.c
+++ linux-2.6/kernel/perf_event.c
@@ -782,6 +782,9 @@ static void __perf_install_in_context(vo
 
 	add_event_to_ctx(event, ctx);
 
+	if (event->cpu != -1 && event->cpu != smp_processor_id())
+		goto unlock;
+
 	/*
 	 * Don't put the event on if it is disabled or if
 	 * it is in a group and the group isn't on.
@@ -925,6 +928,9 @@ static void __perf_event_enable(void *in
 		goto unlock;
 	__perf_event_mark_enabled(event, ctx);
 
+	if (event->cpu != -1 && event->cpu != smp_processor_id())
+		goto unlock;
+
 	/*
 	 * If the event is in a group and isn't the group leader,
 	 * then don't put it on unless the group is on.
@@ -1595,10 +1601,7 @@ static struct perf_event_context *find_g
 	unsigned long flags;
 	int err;
 
-	/*
-	 * If cpu is not a wildcard then this is a percpu event:
-	 */
-	if (cpu != -1) {
+	if (pid == -1 && cpu != -1) {
 		/* Must be root to operate on a CPU event: */
 		if (perf_paranoid_cpu() && !capable(CAP_SYS_ADMIN))
 			return ERR_PTR(-EACCES);

--