perf: Fix perf_pmu_migrate_context

While auditing the list_entry usage due to a trinity bug I found that
perf_pmu_migrate_context violates the rules for
perf_event::event_entry.

The problem is that perf_event::event_entry is a RCU list element, and
hence we must wait for a full RCU grace period before re-using the
element after deletion.

Therefore the usage in perf_pmu_migrate_context() which re-uses the
entry immediately is broken. For now introduce another list_head into
perf_event for this specific usage.

This doesn't actually fix the trinity report because that never goes
through this code.

Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/n/tip-mkj72lxagw1z8fvjm648iznw@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

2 files changed, 26 insertions, 4 deletions

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 866e85c5eb94..c8ba627c1d60 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -294,9 +294,31 @@ struct ring_buffer;
  */
 struct perf_event {
 #ifdef CONFIG_PERF_EVENTS
-        struct list_head                group_entry;
+        /*
+         * entry onto perf_event_context::event_list;
+         *   modifications require ctx->lock
+         *   RCU safe iterations.
+         */
         struct list_head                event_entry;
+
+        /*
+         * XXX: group_entry and sibling_list should be mutually exclusive;
+         * either you're a sibling on a group, or you're the group leader.
+         * Rework the code to always use the same list element.
+         *
+         * Locked for modification by both ctx->mutex and ctx->lock; holding
+         * either sufficies for read.
+         */
+        struct list_head                group_entry;
         struct list_head                sibling_list;
+
+        /*
+         * We need storage to track the entries in perf_pmu_migrate_context; we
+         * cannot use the event_entry because of RCU and we want to keep the
+         * group in tact which avoids us using the other two entries.
+         */
+        struct list_head                migrate_entry;
+
         struct hlist_node               hlist_entry;
         int                             nr_siblings;
         int                             group_flags;
diff --git a/kernel/events/core.c b/kernel/events/core.c
index cb4238e85b38..d49a9d29334c 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -7234,15 +7234,15 @@ void perf_pmu_migrate_context(struct pmu *pmu, int src_cpu, int dst_cpu)
                 perf_remove_from_context(event);
                 unaccount_event_cpu(event, src_cpu);
                 put_ctx(src_ctx);
-                list_add(&event->event_entry, &events);
+                list_add(&event->migrate_entry, &events);
         }
         mutex_unlock(&src_ctx->mutex);
 
         synchronize_rcu();
 
         mutex_lock(&dst_ctx->mutex);
-        list_for_each_entry_safe(event, tmp, &events, event_entry) {
-                list_del(&event->event_entry);
+        list_for_each_entry_safe(event, tmp, &events, migrate_entry) {
+                list_del(&event->migrate_entry);
                 if (event->state >= PERF_EVENT_STATE_OFF)
                         event->state = PERF_EVENT_STATE_INACTIVE;
                 account_event_cpu(event, dst_cpu);