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

Pull cgroup updates from Tejun Heo:
 "Nothing too interesting. The only two noticeable changes are a subtle
  cpuset behavior fix and trace event id field being expanded to u64
  from int. Most others are code cleanups"

* 'for-5.17' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup:
  cpuset: convert 'allowed' in __cpuset_node_allowed() to be boolean
  cgroup/rstat: check updated_next only for root
  cgroup: rstat: explicitly put loop variant in while
  cgroup: return early if it is already on preloaded list
  cgroup/cpuset: Don't let child cpusets restrict parent in default hierarchy
  cgroup: Trace event cgroup id fields should be u64
  cgroup: fix a typo in comment
  cgroup: get the wrong css for css_alloc() during cgroup_init_subsys()
  cgroup: rstat: Mark benign data race to silence KCSAN

5 files changed, 38 insertions, 49 deletions

diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index 411684c80cf3..1bfcfb1af352 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -413,7 +413,7 @@ struct cgroup {
 	/*
 	 * The bitmask of subsystems enabled on the child cgroups.
 	 * ->subtree_control is the one configured through
-	 * "cgroup.subtree_control" while ->child_ss_mask is the effective
+	 * "cgroup.subtree_control" while ->subtree_ss_mask is the effective
 	 * one which may have more subsystems enabled.  Controller knobs
 	 * are made available iff it's enabled in ->subtree_control.
 	 */
diff --git a/include/trace/events/cgroup.h b/include/trace/events/cgroup.h
index 7f42a3de59e6..dd7d7c9efecd 100644
--- a/include/trace/events/cgroup.h
+++ b/include/trace/events/cgroup.h
@@ -59,8 +59,8 @@ DECLARE_EVENT_CLASS(cgroup,
 
 	TP_STRUCT__entry(
 		__field(	int,		root			)
-		__field(	int,		id			)
 		__field(	int,		level			)
+		__field(	u64,		id			)
 		__string(	path,		path			)
 	),
 
@@ -71,7 +71,7 @@ DECLARE_EVENT_CLASS(cgroup,
 		__assign_str(path, path);
 	),
 
-	TP_printk("root=%d id=%d level=%d path=%s",
+	TP_printk("root=%d id=%llu level=%d path=%s",
 		  __entry->root, __entry->id, __entry->level, __get_str(path))
 );
 
@@ -126,8 +126,8 @@ DECLARE_EVENT_CLASS(cgroup_migrate,
 
 	TP_STRUCT__entry(
 		__field(	int,		dst_root		)
-		__field(	int,		dst_id			)
 		__field(	int,		dst_level		)
+		__field(	u64,		dst_id			)
 		__field(	int,		pid			)
 		__string(	dst_path,	path			)
 		__string(	comm,		task->comm		)
@@ -142,7 +142,7 @@ DECLARE_EVENT_CLASS(cgroup_migrate,
 		__assign_str(comm, task->comm);
 	),
 
-	TP_printk("dst_root=%d dst_id=%d dst_level=%d dst_path=%s pid=%d comm=%s",
+	TP_printk("dst_root=%d dst_id=%llu dst_level=%d dst_path=%s pid=%d comm=%s",
 		  __entry->dst_root, __entry->dst_id, __entry->dst_level,
 		  __get_str(dst_path), __entry->pid, __get_str(comm))
 );
@@ -171,8 +171,8 @@ DECLARE_EVENT_CLASS(cgroup_event,
 
 	TP_STRUCT__entry(
 		__field(	int,		root			)
-		__field(	int,		id			)
 		__field(	int,		level			)
+		__field(	u64,		id			)
 		__string(	path,		path			)
 		__field(	int,		val			)
 	),
@@ -185,7 +185,7 @@ DECLARE_EVENT_CLASS(cgroup_event,
 		__entry->val = val;
 	),
 
-	TP_printk("root=%d id=%d level=%d path=%s val=%d",
+	TP_printk("root=%d id=%llu level=%d path=%s val=%d",
 		  __entry->root, __entry->id, __entry->level, __get_str(path),
 		  __entry->val)
 );
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 581ca5a11aaa..b31e1465868a 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -2651,11 +2651,11 @@ void cgroup_migrate_add_src(struct css_set *src_cset,
 	if (src_cset->dead)
 		return;
 
-	src_cgrp = cset_cgroup_from_root(src_cset, dst_cgrp->root);
-
 	if (!list_empty(&src_cset->mg_preload_node))
 		return;
 
+	src_cgrp = cset_cgroup_from_root(src_cset, dst_cgrp->root);
+
 	WARN_ON(src_cset->mg_src_cgrp);
 	WARN_ON(src_cset->mg_dst_cgrp);
 	WARN_ON(!list_empty(&src_cset->mg_tasks));
@@ -5743,7 +5743,7 @@ static void __init cgroup_init_subsys(struct cgroup_subsys *ss, bool early)
 
 	/* Create the root cgroup state for this subsystem */
 	ss->root = &cgrp_dfl_root;
-	css = ss->css_alloc(cgroup_css(&cgrp_dfl_root.cgrp, ss));
+	css = ss->css_alloc(NULL);
 	/* We don't handle early failures gracefully */
 	BUG_ON(IS_ERR(css));
 	init_and_link_css(css, ss, &cgrp_dfl_root.cgrp);
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index d0e163a02099..dc653ab26e50 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -616,19 +616,11 @@ static int validate_change(struct cpuset *cur, struct cpuset *trial)
 	struct cpuset *c, *par;
 	int ret;
 
-	rcu_read_lock();
-
-	/* 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;
-
-	/* Remaining checks don't apply to root cpuset */
-	ret = 0;
+	/* The checks don't apply to root cpuset */
 	if (cur == &top_cpuset)
-		goto out;
+		return 0;
 
+	rcu_read_lock();
 	par = parent_cs(cur);
 
 	/* On legacy hierarchy, we must be a subset of our parent cpuset. */
@@ -3536,7 +3528,7 @@ static struct cpuset *nearest_hardwall_ancestor(struct cpuset *cs)
 bool __cpuset_node_allowed(int node, gfp_t gfp_mask)
 {
 	struct cpuset *cs;		/* current cpuset ancestors */
-	int allowed;			/* is allocation in zone z allowed? */
+	bool allowed;			/* is allocation in zone z allowed? */
 	unsigned long flags;
 
 	if (in_interrupt())
diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c
index 1486768f2318..9d331ba44870 100644
--- a/kernel/cgroup/rstat.c
+++ b/kernel/cgroup/rstat.c
@@ -35,7 +35,7 @@ void cgroup_rstat_updated(struct cgroup *cgrp, int cpu)
 	 * instead of NULL, we can tell whether @cgrp is on the list by
 	 * testing the next pointer for NULL.
 	 */
-	if (cgroup_rstat_cpu(cgrp, cpu)->updated_next)
+	if (data_race(cgroup_rstat_cpu(cgrp, cpu)->updated_next))
 		return;
 
 	raw_spin_lock_irqsave(cpu_lock, flags);
@@ -88,6 +88,7 @@ static struct cgroup *cgroup_rstat_cpu_pop_updated(struct cgroup *pos,
 						   struct cgroup *root, int cpu)
 {
 	struct cgroup_rstat_cpu *rstatc;
+	struct cgroup *parent;
 
 	if (pos == root)
 		return NULL;
@@ -96,10 +97,14 @@ static struct cgroup *cgroup_rstat_cpu_pop_updated(struct cgroup *pos,
 	 * We're gonna walk down to the first leaf and visit/remove it.  We
 	 * can pick whatever unvisited node as the starting point.
 	 */
-	if (!pos)
+	if (!pos) {
 		pos = root;
-	else
+		/* return NULL if this subtree is not on-list */
+		if (!cgroup_rstat_cpu(pos, cpu)->updated_next)
+			return NULL;
+	} else {
 		pos = cgroup_parent(pos);
+	}
 
 	/* walk down to the first leaf */
 	while (true) {
@@ -115,33 +120,25 @@ static struct cgroup *cgroup_rstat_cpu_pop_updated(struct cgroup *pos,
 	 * However, due to the way we traverse, @pos will be the first
 	 * child in most cases. The only exception is @root.
 	 */
-	if (rstatc->updated_next) {
-		struct cgroup *parent = cgroup_parent(pos);
-
-		if (parent) {
-			struct cgroup_rstat_cpu *prstatc;
-			struct cgroup **nextp;
-
-			prstatc = cgroup_rstat_cpu(parent, cpu);
-			nextp = &prstatc->updated_children;
-			while (true) {
-				struct cgroup_rstat_cpu *nrstatc;
-
-				nrstatc = cgroup_rstat_cpu(*nextp, cpu);
-				if (*nextp == pos)
-					break;
-				WARN_ON_ONCE(*nextp == parent);
-				nextp = &nrstatc->updated_next;
-			}
-			*nextp = rstatc->updated_next;
-		}
+	parent = cgroup_parent(pos);
+	if (parent) {
+		struct cgroup_rstat_cpu *prstatc;
+		struct cgroup **nextp;
 
-		rstatc->updated_next = NULL;
-		return pos;
+		prstatc = cgroup_rstat_cpu(parent, cpu);
+		nextp = &prstatc->updated_children;
+		while (*nextp != pos) {
+			struct cgroup_rstat_cpu *nrstatc;
+
+			nrstatc = cgroup_rstat_cpu(*nextp, cpu);
+			WARN_ON_ONCE(*nextp == parent);
+			nextp = &nrstatc->updated_next;
+		}
+		*nextp = rstatc->updated_next;
 	}
 
-	/* only happens for @root */
-	return NULL;
+	rstatc->updated_next = NULL;
+	return pos;
 }
 
 /* see cgroup_rstat_flush() */