Merge branch 'for-5.17-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup

Pull cgroup fixes from Tejun Heo:

 - Eric's fix for a long standing cgroup1 permission issue where it only
   checks for uid 0 instead of CAP which inadvertently allows
   unprivileged userns roots to modify release_agent userhelper

 - Fixes for the fallout from Waiman's recent cpuset work

* 'for-5.17-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup:
  cgroup/cpuset: Fix "suspicious RCU usage" lockdep warning
  cgroup-v1: Require capabilities to set release_agent
  cpuset: Fix the bug that subpart_cpus updated wrongly in update_cpumask()
  cgroup/cpuset: Make child cpusets restrict parents on v1 hierarchy

Author: torvalds

kernel/cgroup/cgroup-v1.c

@@ -549,6 +549,14 @@ static ssize_t cgroup_release_agent_write(struct kernfs_open_file *of,
 
 	BUILD_BUG_ON(sizeof(cgrp->root->release_agent_path) < PATH_MAX);
 
+	/*
+	 * Release agent gets called with all capabilities,
+	 * require capabilities to set release agent.
+	 */
+	if ((of->file->f_cred->user_ns != &init_user_ns) ||
+	    !capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
 	cgrp = cgroup_kn_lock_live(of->kn, false);
 	if (!cgrp)
 		return -ENODEV;
@@ -954,6 +962,12 @@ int cgroup1_parse_param(struct fs_context *fc, struct fs_parameter *param)
 		/* Specifying two release agents is forbidden */
 		if (ctx->release_agent)
 			return invalfc(fc, "release_agent respecified");
+		/*
+		 * Release agent gets called with all capabilities,
+		 * require capabilities to set release agent.
+		 */
+		if ((fc->user_ns != &init_user_ns) || !capable(CAP_SYS_ADMIN))
+			return invalfc(fc, "Setting release_agent not allowed");
 		ctx->release_agent = param->string;
 		param->string = NULL;
 		break;

kernel/cgroup/cpuset.c

@@ -590,6 +590,35 @@ static inline void free_cpuset(struct cpuset *cs)
 	kfree(cs);
 }
 
+/*
+ * validate_change_legacy() - Validate conditions specific to legacy (v1)
+ *                            behavior.
+ */
+static int validate_change_legacy(struct cpuset *cur, struct cpuset *trial)
+{
+	struct cgroup_subsys_state *css;
+	struct cpuset *c, *par;
+	int ret;
+
+	WARN_ON_ONCE(!rcu_read_lock_held());
+
+	/* Each of our child cpusets must be a subset of us */
+	ret = -EBUSY;
+	cpuset_for_each_child(c, css, cur)
+		if (!is_cpuset_subset(c, trial))
+			goto out;
+
+	/* On legacy hierarchy, we must be a subset of our parent cpuset. */
+	ret = -EACCES;
+	par = parent_cs(cur);
+	if (par && !is_cpuset_subset(trial, par))
+		goto out;
+
+	ret = 0;
+out:
+	return ret;
+}
+
 /*
  * validate_change() - Used to validate that any proposed cpuset change
  *		       follows the structural rules for cpusets.
@@ -614,20 +643,21 @@ static int validate_change(struct cpuset *cur, struct cpuset *trial)
 {
 	struct cgroup_subsys_state *css;
 	struct cpuset *c, *par;
-	int ret;
-
-	/* The checks don't apply to root cpuset */
-	if (cur == &top_cpuset)
-		return 0;
+	int ret = 0;
 
 	rcu_read_lock();
-	par = parent_cs(cur);
 
-	/* On legacy hierarchy, we must be a subset of our parent cpuset. */
-	ret = -EACCES;
-	if (!is_in_v2_mode() && !is_cpuset_subset(trial, par))
+	if (!is_in_v2_mode())
+		ret = validate_change_legacy(cur, trial);
+	if (ret)
+		goto out;
+
+	/* Remaining checks don't apply to root cpuset */
+	if (cur == &top_cpuset)
 		goto out;
 
+	par = parent_cs(cur);
+
 	/*
 	 * If either I or some sibling (!= me) is exclusive, we can't
 	 * overlap
@@ -1175,9 +1205,7 @@ enum subparts_cmd {
  *
  * Because of the implicit cpu exclusive nature of a partition root,
  * cpumask changes that violates the cpu exclusivity rule will not be
- * permitted when checked by validate_change(). The validate_change()
- * function will also prevent any changes to the cpu list if it is not
- * a superset of children's cpu lists.
+ * permitted when checked by validate_change().
  */
 static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd,
 					  struct cpumask *newmask,
@@ -1522,19 +1550,29 @@ static void update_sibling_cpumasks(struct cpuset *parent, struct cpuset *cs,
 	struct cpuset *sibling;
 	struct cgroup_subsys_state *pos_css;
 
+	percpu_rwsem_assert_held(&cpuset_rwsem);
+
 	/*
 	 * Check all its siblings and call update_cpumasks_hier()
 	 * if their use_parent_ecpus flag is set in order for them
 	 * to use the right effective_cpus value.
+	 *
+	 * The update_cpumasks_hier() function may sleep. So we have to
+	 * release the RCU read lock before calling it.
 	 */
 	rcu_read_lock();
 	cpuset_for_each_child(sibling, pos_css, parent) {
 		if (sibling == cs)
 			continue;
 		if (!sibling->use_parent_ecpus)
 			continue;
+		if (!css_tryget_online(&sibling->css))
+			continue;
 
+		rcu_read_unlock();
 		update_cpumasks_hier(sibling, tmp);
+		rcu_read_lock();
+		css_put(&sibling->css);
 	}
 	rcu_read_unlock();
 }
@@ -1607,8 +1645,7 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs,
 	 * Make sure that subparts_cpus is a subset of cpus_allowed.
 	 */
 	if (cs->nr_subparts_cpus) {
-		cpumask_andnot(cs->subparts_cpus, cs->subparts_cpus,
-			       cs->cpus_allowed);
+		cpumask_and(cs->subparts_cpus, cs->subparts_cpus, cs->cpus_allowed);
 		cs->nr_subparts_cpus = cpumask_weight(cs->subparts_cpus);
 	}
 	spin_unlock_irq(&callback_lock);