[PATCH 4.14 423/496] perf/core: Fix installing cgroup events on CPU

[Greg Kroah-Hartman]

4.14-stable review patch.  If anyone has any objections, please let me know.

------------------

From: "leilei.lin" <leilei.lin@xxxxxxxxxxxxxxx>

[ Upstream commit 33801b94741d6c3be9713c10aa627477216c21e2 ]

There's two problems when installing cgroup events on CPUs: firstly
list_update_cgroup_event() only tries to set cpuctx->cgrp for the
first event, if that mismatches on @cgrp we'll not try again for later
additions.

Secondly, when we install a cgroup event into an active context, only
issue an event reprogram when the event matches the current cgroup
context. This avoids a pointless event reprogramming.

Signed-off-by: leilei.lin <leilei.lin@xxxxxxxxxxxxxxx>
[ Improved the changelog and comments. ]
Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Cc: Alexander Shishkin <alexander.shishkin@xxxxxxxxxxxxxxx>
Cc: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>
Cc: Jiri Olsa <jolsa@xxxxxxxxxx>
Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Cc: Stephane Eranian <eranian@xxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Vince Weaver <vincent.weaver@xxxxxxxxx>
Cc: brendan.d.gregg@xxxxxxxxx
Cc: eranian@xxxxxxxxx
Cc: linux-kernel@xxxxxxxxxxxxxxx
Cc: yang_oliver@xxxxxxxxxxx
Link: http://lkml.kernel.org/r/20180306093637.28247-1-linxiulei@xxxxxxxxx
Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
Signed-off-by: Sasha Levin <alexander.levin@xxxxxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
 kernel/events/core.c |   46 +++++++++++++++++++++++++++++++++++-----------
 1 file changed, 35 insertions(+), 11 deletions(-)

--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -900,27 +900,39 @@ list_update_cgroup_event(struct perf_eve
 	if (!is_cgroup_event(event))
 		return;
 
-	if (add && ctx->nr_cgroups++)
-		return;
-	else if (!add && --ctx->nr_cgroups)
-		return;
 	/*
 	 * Because cgroup events are always per-cpu events,
 	 * this will always be called from the right CPU.
 	 */
 	cpuctx = __get_cpu_context(ctx);
-	cpuctx_entry = &cpuctx->cgrp_cpuctx_entry;
-	/* cpuctx->cgrp is NULL unless a cgroup event is active in this CPU .*/
-	if (add) {
+
+	/*
+	 * Since setting cpuctx->cgrp is conditional on the current @cgrp
+	 * matching the event's cgroup, we must do this for every new event,
+	 * because if the first would mismatch, the second would not try again
+	 * and we would leave cpuctx->cgrp unset.
+	 */
+	if (add && !cpuctx->cgrp) {
 		struct perf_cgroup *cgrp = perf_cgroup_from_task(current, ctx);
 
-		list_add(cpuctx_entry, this_cpu_ptr(&cgrp_cpuctx_list));
 		if (cgroup_is_descendant(cgrp->css.cgroup, event->cgrp->css.cgroup))
 			cpuctx->cgrp = cgrp;
-	} else {
-		list_del(cpuctx_entry);
-		cpuctx->cgrp = NULL;
 	}
+
+	if (add && ctx->nr_cgroups++)
+		return;
+	else if (!add && --ctx->nr_cgroups)
+		return;
+
+	/* no cgroup running */
+	if (!add)
+		cpuctx->cgrp = NULL;
+
+	cpuctx_entry = &cpuctx->cgrp_cpuctx_entry;
+	if (add)
+		list_add(cpuctx_entry, this_cpu_ptr(&cgrp_cpuctx_list));
+	else
+		list_del(cpuctx_entry);
 }
 
 #else /* !CONFIG_CGROUP_PERF */
@@ -2404,6 +2416,18 @@ static int  __perf_install_in_context(vo
 		raw_spin_lock(&task_ctx->lock);
 	}
 
+#ifdef CONFIG_CGROUP_PERF
+	if (is_cgroup_event(event)) {
+		/*
+		 * If the current cgroup doesn't match the event's
+		 * cgroup, we should not try to schedule it.
+		 */
+		struct perf_cgroup *cgrp = perf_cgroup_from_task(current, ctx);
+		reprogram = cgroup_is_descendant(cgrp->css.cgroup,
+					event->cgrp->css.cgroup);
+	}
+#endif
+
 	if (reprogram) {
 		ctx_sched_out(ctx, cpuctx, EVENT_TIME);
 		add_event_to_ctx(event, ctx);