[PATCH 1/4] perf/core: Fix perf_pmu_migrate_context() leaving events behind

[Haris Okanovic]

__perf_pmu_remove() walks the group leaders of a CPU and PMU with
perf_event_groups_for_cpu_pmu(), removing each one as it goes.
perf_remove_from_context() takes the leader out of the groups rbtree,
after which rb_next() on that node returns NULL, prematurely ending the
walk. Other groups stay behind in the source context.

On CPU hotplug, they are then torn down with the dying CPU. They keep
running until teardown, while the PMU's interrupt and migrated events
are on a new CPU, which drivers rely on never happening.

Walk ctx->event_list instead and pick out the PMU's events by their
pmu_ctx.

Fixes: bd2756811766 ("perf: Rewrite core context handling")
Signed-off-by: Haris Okanovic <harisokn at amazon.com>
---
 kernel/events/core.c | 20 +++++++-------------
 1 file changed, 7 insertions(+), 13 deletions(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 7846d70be57f6..7caba4d528301 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -14394,23 +14394,18 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu,
 }
 EXPORT_SYMBOL_GPL(perf_event_create_kernel_counter);
 
-static void __perf_pmu_remove(struct perf_event_context *ctx,
-			      int cpu, struct pmu *pmu,
-			      struct perf_event_groups *groups,
+static void __perf_pmu_remove(struct perf_event_context *ctx, struct pmu *pmu,
 			      struct list_head *events)
 {
-	struct perf_event *event, *sibling;
+	struct perf_event *event, *tmp;
+
+	list_for_each_entry_safe(event, tmp, &ctx->event_list, event_entry) {
+		if (event->pmu_ctx->pmu != pmu)
+			continue;
 
-	perf_event_groups_for_cpu_pmu(event, groups, cpu, pmu) {
 		perf_remove_from_context(event, 0);
 		put_pmu_ctx(event->pmu_ctx);
 		list_add(&event->migrate_entry, events);
-
-		for_each_sibling_event(sibling, event) {
-			perf_remove_from_context(sibling, 0);
-			put_pmu_ctx(sibling->pmu_ctx);
-			list_add(&sibling->migrate_entry, events);
-		}
 	}
 }
 
@@ -14486,8 +14481,7 @@ void perf_pmu_migrate_context(struct pmu *pmu, int src_cpu, int dst_cpu)
 	 */
 	mutex_lock_double(&src_ctx->mutex, &dst_ctx->mutex);
 
-	__perf_pmu_remove(src_ctx, src_cpu, pmu, &src_ctx->pinned_groups, &events);
-	__perf_pmu_remove(src_ctx, src_cpu, pmu, &src_ctx->flexible_groups, &events);
+	__perf_pmu_remove(src_ctx, pmu, &events);
 
 	if (!list_empty(&events)) {
 		/*
-- 
Haris Okanovic
AWS Graviton