sched_ext: Fix premature ops->priv publication in scx_alloc_and_add_sched()

scx_alloc_and_add_sched() publishes @sch through ops->priv before allocating the cgroup path. If that allocation fails, the unwind path clears ops->priv and frees @sch immediately. scx_prog_sched() callers can dereference ops->priv from RCU context the moment it is set, so freeing without a grace period can use-after-free a concurrent kfunc caller. Move the publication below the cgroup path allocation so that every failure path after publication frees @sch through kobject_put(), whose release path defers the freeing by a grace period.

Tejun Heo committed 4 months ago

Commit 49b33781 parent db4e9de1 file · +12 −6Browse files

Showing the changes to kernel (1 of 1 file). Show all

Unified · Split

kernel/sched/ext/ext.c+12−6

 		sch->ops = *cmd->ops;
 	}
-	rcu_assign_pointer(ops->priv, sch);
-	sch->kobj.kset = scx_kset;
-	INIT_LIST_HEAD(&sch->all);
 #ifdef CONFIG_EXT_SUB_SCHED
 	char *buf = kzalloc(PATH_MAX, GFP_KERNEL);
 	if (!buf) {
 	sch->cgrp = cgrp;
 	INIT_LIST_HEAD(&sch->children);
 	INIT_LIST_HEAD(&sch->sibling);
+#endif	/* CONFIG_EXT_SUB_SCHED */
+	/*
+	 * Publishing makes @sch visible to scx_prog_sched() readers. Failure
+	 * paths after this point must free @sch through kobject_put() whose
+	 * release path defers the actual freeing by an RCU grace period.
+	 */
+	rcu_assign_pointer(ops->priv, sch);
+	sch->kobj.kset = scx_kset;
+	INIT_LIST_HEAD(&sch->all);
+#ifdef CONFIG_EXT_SUB_SCHED
 	if (parent) {
 		/*
 		 * Pin @parent for @sch's lifetime. The kobject hierarchy pins
 #ifdef CONFIG_EXT_SUB_SCHED
 err_free_lb_resched:
-	RCU_INIT_POINTER(ops->priv, NULL);
 	free_cpumask_var(sch->bypass_lb_resched_cpumask);
 #endif
 err_free_lb_cpumask: