Merge branch 'for-5.15' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup

Pull cgroup updates from Tejun Heo:
 "Two cpuset behavior changes:

   - cpuset on cgroup2 is changed to enable memory migration based on
     nodemask by default.

   - A notification is generated when cpuset partition state changes.

  All other patches are minor fixes and cleanups"

* 'for-5.15' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup:
  cgroup: Avoid compiler warnings with no subsystems
  cgroup/cpuset: Avoid memory migration when nodemasks match
  cgroup/cpuset: Enable memory migration for cpuset v2
  cgroup/cpuset: Enable event notification when partition state changes
  cgroup: cgroup-v1: clean up kernel-doc notation
  cgroup: Replace deprecated CPU-hotplug functions.
  cgroup/cpuset: Fix violation of cpuset locking rule
  cgroup/cpuset: Fix a partition bug with hotplug
  cgroup/cpuset: Miscellaneous code cleanup
  cgroup: remove cgroup_mount from comments

Author: torvalds

Documentation/admin-guide/cgroup-v2.rst

@@ -2056,6 +2056,17 @@ Cpuset Interface Files
 	The value of "cpuset.mems" stays constant until the next update
 	and won't be affected by any memory nodes hotplug events.
 
+	Setting a non-empty value to "cpuset.mems" causes memory of
+	tasks within the cgroup to be migrated to the designated nodes if
+	they are currently using memory outside of the designated nodes.
+
+	There is a cost for this memory migration.  The migration
+	may not be complete and some memory pages may be left behind.
+	So it is recommended that "cpuset.mems" should be set properly
+	before spawning new tasks into the cpuset.  Even if there is
+	a need to change "cpuset.mems" with active tasks, it shouldn't
+	be done frequently.
+
   cpuset.mems.effective
 	A read-only multiple values file which exists on all
 	cpuset-enabled cgroups.

kernel/cgroup/cgroup-v1.c

@@ -50,6 +50,8 @@ bool cgroup1_ssid_disabled(int ssid)
  * cgroup_attach_task_all - attach task 'tsk' to all cgroups of task 'from'
  * @from: attach to all cgroups of a given task
  * @tsk: the task to be attached
+ *
+ * Return: %0 on success or a negative errno code on failure
  */
 int cgroup_attach_task_all(struct task_struct *from, struct task_struct *tsk)
 {
@@ -80,7 +82,7 @@ int cgroup_attach_task_all(struct task_struct *from, struct task_struct *tsk)
 EXPORT_SYMBOL_GPL(cgroup_attach_task_all);
 
 /**
- * cgroup_trasnsfer_tasks - move tasks from one cgroup to another
+ * cgroup_transfer_tasks - move tasks from one cgroup to another
  * @to: cgroup to which the tasks will be moved
  * @from: cgroup in which the tasks currently reside
  *
@@ -89,6 +91,8 @@ EXPORT_SYMBOL_GPL(cgroup_attach_task_all);
  * is guaranteed to be either visible in the source cgroup after the
  * parent's migration is complete or put into the target cgroup.  No task
  * can slip out of migration through forking.
+ *
+ * Return: %0 on success or a negative errno code on failure
  */
 int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from)
 {
@@ -682,6 +686,8 @@ int proc_cgroupstats_show(struct seq_file *m, void *v)
  *
  * Build and fill cgroupstats so that taskstats can export it to user
  * space.
+ *
+ * Return: %0 on success or a negative errno code on failure
  */
 int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry)
 {

kernel/cgroup/cgroup.c

@@ -67,6 +67,14 @@
 /* let's not notify more than 100 times per second */
 #define CGROUP_FILE_NOTIFY_MIN_INTV	DIV_ROUND_UP(HZ, 100)
 
+/*
+ * To avoid confusing the compiler (and generating warnings) with code
+ * that attempts to access what would be a 0-element array (i.e. sized
+ * to a potentially empty array when CGROUP_SUBSYS_COUNT == 0), this
+ * constant expression can be added.
+ */
+#define CGROUP_HAS_SUBSYS_CONFIG	(CGROUP_SUBSYS_COUNT > 0)
+
 /*
  * cgroup_mutex is the master lock.  Any modification to cgroup or its
  * hierarchy must be performed while holding it.
@@ -248,7 +256,7 @@ static int cgroup_addrm_files(struct cgroup_subsys_state *css,
  */
 bool cgroup_ssid_enabled(int ssid)
 {
-	if (CGROUP_SUBSYS_COUNT == 0)
+	if (!CGROUP_HAS_SUBSYS_CONFIG)
 		return false;
 
 	return static_key_enabled(cgroup_subsys_enabled_key[ssid]);
@@ -472,7 +480,7 @@ static u16 cgroup_ss_mask(struct cgroup *cgrp)
 static struct cgroup_subsys_state *cgroup_css(struct cgroup *cgrp,
 					      struct cgroup_subsys *ss)
 {
-	if (ss)
+	if (CGROUP_HAS_SUBSYS_CONFIG && ss)
 		return rcu_dereference_check(cgrp->subsys[ss->id],
 					lockdep_is_held(&cgroup_mutex));
 	else
@@ -550,6 +558,9 @@ struct cgroup_subsys_state *cgroup_e_css(struct cgroup *cgrp,
 {
 	struct cgroup_subsys_state *css;
 
+	if (!CGROUP_HAS_SUBSYS_CONFIG)
+		return NULL;
+
 	do {
 		css = cgroup_css(cgrp, ss);
 
@@ -577,6 +588,9 @@ struct cgroup_subsys_state *cgroup_get_e_css(struct cgroup *cgrp,
 {
 	struct cgroup_subsys_state *css;
 
+	if (!CGROUP_HAS_SUBSYS_CONFIG)
+		return NULL;
+
 	rcu_read_lock();
 
 	do {
@@ -647,7 +661,7 @@ struct cgroup_subsys_state *of_css(struct kernfs_open_file *of)
 	 * the matching css from the cgroup's subsys table is guaranteed to
 	 * be and stay valid until the enclosing operation is complete.
 	 */
-	if (cft->ss)
+	if (CGROUP_HAS_SUBSYS_CONFIG && cft->ss)
 		return rcu_dereference_raw(cgrp->subsys[cft->ss->id]);
 	else
 		return &cgrp->self;
@@ -695,7 +709,7 @@ EXPORT_SYMBOL_GPL(of_css);
  */
 #define do_each_subsys_mask(ss, ssid, ss_mask) do {			\
 	unsigned long __ss_mask = (ss_mask);				\
-	if (!CGROUP_SUBSYS_COUNT) { /* to avoid spurious gcc warning */	\
+	if (!CGROUP_HAS_SUBSYS_CONFIG) {				\
 		(ssid) = 0;						\
 		break;							\
 	}								\
@@ -2169,7 +2183,6 @@ static void cgroup_kill_sb(struct super_block *sb)
 	/*
 	 * If @root doesn't have any children, start killing it.
 	 * This prevents new mounts by disabling percpu_ref_tryget_live().
-	 * cgroup_mount() may wait for @root's release.
 	 *
 	 * And don't kill the default root.
 	 */
@@ -2373,7 +2386,7 @@ struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset,
 	struct css_set *cset = tset->cur_cset;
 	struct task_struct *task = tset->cur_task;
 
-	while (&cset->mg_node != tset->csets) {
+	while (CGROUP_HAS_SUBSYS_CONFIG && &cset->mg_node != tset->csets) {
 		if (!task)
 			task = list_first_entry(&cset->mg_tasks,
 						struct task_struct, cg_list);
@@ -4644,7 +4657,7 @@ void css_task_iter_start(struct cgroup_subsys_state *css, unsigned int flags,
 	it->ss = css->ss;
 	it->flags = flags;
 
-	if (it->ss)
+	if (CGROUP_HAS_SUBSYS_CONFIG && it->ss)
 		it->cset_pos = &css->cgroup->e_csets[css->ss->id];
 	else
 		it->cset_pos = &css->cgroup->cset_links;