perf: protect group_leader from races that cause ctx double-free

When moving a group_leader perf event from a software-context
to a hardware-context, there's a race in checking and
updating that context. The existing locking solution
doesn't work; note that it tries to grab a lock inside
the group_leader's context object, which you can only
get at by going through a pointer that should be protected
from these races. To avoid that problem, and to produce
a simple solution, we can just use a lock per group_leader
to protect all checks on the group_leader's context.
The new lock is grabbed and released when no context locks
are held.

Bug: 30955111
Bug: 31095224
Change-Id: If37124c100ca6f4aa962559fba3bd5dbbec8e052

1 files changed, 15 insertions, 0 deletions

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 7ab4ad00f..f294f2761 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -6387,6 +6387,7 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 	if (!group_leader)
 		group_leader = event;
 
+	mutex_init(&event->group_leader_mutex);
 	mutex_init(&event->child_mutex);
 	INIT_LIST_HEAD(&event->child_list);
 
@@ -6767,6 +6768,16 @@ SYSCALL_DEFINE5(perf_event_open,
 			group_leader = NULL;
 	}
 
+	/*
+	 * Take the group_leader's group_leader_mutex before observing
+	 * anything in the group leader that leads to changes in ctx,
+	 * many of which may be changing on another thread.
+	 * In particular, we want to take this lock before deciding
+	 * whether we need to move_group.
+	 */
+	if (group_leader)
+		mutex_lock(&group_leader->group_leader_mutex);
+
 	if (pid != -1 && !(flags & PERF_FLAG_PID_CGROUP)) {
 		task = find_lively_task_by_vpid(pid);
 		if (IS_ERR(task)) {
@@ -6935,6 +6946,8 @@ SYSCALL_DEFINE5(perf_event_open,
 	++ctx->generation;
 	perf_unpin_context(ctx);
 	mutex_unlock(&ctx->mutex);
+	if (group_leader)
+		mutex_unlock(&group_leader->group_leader_mutex);
 
 	put_online_cpus();
 
@@ -6970,6 +6983,8 @@ err_task:
 	if (task)
 		put_task_struct(task);
 err_group_fd:
+	if (group_leader)
+		mutex_unlock(&group_leader->group_leader_mutex);
 	fdput(group);
 err_fd:
 	put_unused_fd(event_fd);