3 files changed, 25 insertions, 11 deletions

diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index e717208cfb18..554a02ee298b 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -5847,7 +5847,7 @@ static struct cgroup *cgroup_create(struct cgroup *parent, const char *name,
 	int ret;
 
 	/* allocate the cgroup and its ID, 0 is reserved for the root */
-	cgrp = kzalloc(struct_size(cgrp, ancestors, (level + 1)), GFP_KERNEL);
+	cgrp = kzalloc(struct_size(cgrp, _low_ancestors, level), GFP_KERNEL);
 	if (!cgrp)
 		return ERR_PTR(-ENOMEM);
 
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 6e6eb09b8db6..3e8cc34d8d50 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -1668,7 +1668,14 @@ static int remote_partition_enable(struct cpuset *cs, int new_prs,
 static void remote_partition_disable(struct cpuset *cs, struct tmpmasks *tmp)
 {
 	WARN_ON_ONCE(!is_remote_partition(cs));
-	WARN_ON_ONCE(!cpumask_subset(cs->effective_xcpus, subpartitions_cpus));
+	/*
+	 * When a CPU is offlined, top_cpuset may end up with no available CPUs,
+	 * which should clear subpartitions_cpus. We should not emit a warning for this
+	 * scenario: the hierarchy is updated from top to bottom, so subpartitions_cpus
+	 * may already be cleared when disabling the partition.
+	 */
+	WARN_ON_ONCE(!cpumask_subset(cs->effective_xcpus, subpartitions_cpus) &&
+		     !cpumask_empty(subpartitions_cpus));
 
 	spin_lock_irq(&callback_lock);
 	cs->remote_partition = false;
@@ -3976,8 +3983,9 @@ retry:
 	if (remote || (is_partition_valid(cs) && is_partition_valid(parent)))
 		compute_partition_effective_cpumask(cs, &new_cpus);
 
-	if (remote && cpumask_empty(&new_cpus) &&
-	    partition_is_populated(cs, NULL)) {
+	if (remote && (cpumask_empty(subpartitions_cpus) ||
+			(cpumask_empty(&new_cpus) &&
+			 partition_is_populated(cs, NULL)))) {
 		cs->prs_err = PERR_HOTPLUG;
 		remote_partition_disable(cs, tmp);
 		compute_effective_cpumask(&new_cpus, cs, parent);
@@ -3990,9 +3998,12 @@ retry:
 	 * 1) empty effective cpus but not valid empty partition.
 	 * 2) parent is invalid or doesn't grant any cpus to child
 	 *    partitions.
+	 * 3) subpartitions_cpus is empty.
 	 */
-	if (is_local_partition(cs) && (!is_partition_valid(parent) ||
-				tasks_nocpu_error(parent, cs, &new_cpus)))
+	if (is_local_partition(cs) &&
+	    (!is_partition_valid(parent) ||
+	     tasks_nocpu_error(parent, cs, &new_cpus) ||
+	     cpumask_empty(subpartitions_cpus)))
 		partcmd = partcmd_invalidate;
 	/*
 	 * On the other hand, an invalid partition root may be transitioned
diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c
index a198e40c799b..150e5871e66f 100644
--- a/kernel/cgroup/rstat.c
+++ b/kernel/cgroup/rstat.c
@@ -71,7 +71,6 @@ __bpf_kfunc void css_rstat_updated(struct cgroup_subsys_state *css, int cpu)
 {
 	struct llist_head *lhead;
 	struct css_rstat_cpu *rstatc;
-	struct css_rstat_cpu __percpu *rstatc_pcpu;
 	struct llist_node *self;
 
 	/*
@@ -104,18 +103,22 @@ __bpf_kfunc void css_rstat_updated(struct cgroup_subsys_state *css, int cpu)
 	/*
 	 * This function can be renentered by irqs and nmis for the same cgroup
 	 * and may try to insert the same per-cpu lnode into the llist. Note
-	 * that llist_add() does not protect against such scenarios.
+	 * that llist_add() does not protect against such scenarios. In addition
+	 * this same per-cpu lnode can be modified through init_llist_node()
+	 * from css_rstat_flush() running on a different CPU.
 	 *
 	 * To protect against such stacked contexts of irqs/nmis, we use the
 	 * fact that lnode points to itself when not on a list and then use
-	 * this_cpu_cmpxchg() to atomically set to NULL to select the winner
+	 * try_cmpxchg() to atomically set to NULL to select the winner
 	 * which will call llist_add(). The losers can assume the insertion is
 	 * successful and the winner will eventually add the per-cpu lnode to
 	 * the llist.
+	 *
+	 * Please note that we can not use this_cpu_cmpxchg() here as on some
+	 * archs it is not safe against modifications from multiple CPUs.
 	 */
 	self = &rstatc->lnode;
-	rstatc_pcpu = css->rstat_cpu;
-	if (this_cpu_cmpxchg(rstatc_pcpu->lnode.next, self, NULL) != self)
+	if (!try_cmpxchg(&rstatc->lnode.next, &self, NULL))
 		return;
 
 	lhead = ss_lhead_cpu(css->ss, cpu);