From b7eb4edcc3b5cd7ffdcbd56fa7a12de41b39424d Mon Sep 17 00:00:00 2001
From: Frederic Weisbecker <frederic@kernel.org>
Date: Thu, 12 Jun 2025 15:36:16 +0200
Subject: [PATCH] sched/isolation: Flush memcg workqueues on cpuset isolated
 partition change

The HK_TYPE_DOMAIN housekeeping cpumask is now modifiable at runtime. In
order to synchronize against memcg workqueue to make sure that no
asynchronous draining is still pending or executing on a newly made
isolated CPU, the housekeeping susbsystem must flush the memcg
workqueues.

However the memcg workqueues can't be flushed easily since they are
queued to the main per-CPU workqueue pool.

Solve this with creating a memcg specific pool and provide and use the
appropriate flushing API.

Acked-by: Shakeel Butt <shakeel.butt@linux.dev>
Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Marco Crivellari <marco.crivellari@suse.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Shakeel Butt <shakeel.butt@linux.dev>
Cc: Tejun Heo <tj@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Waiman Long <longman@redhat.com>
Cc: cgroups@vger.kernel.org
Cc: linux-mm@kvack.org
---
 include/linux/memcontrol.h |  4 ++++
 kernel/sched/isolation.c   |  2 ++
 kernel/sched/sched.h       |  1 +
 mm/memcontrol.c            | 12 +++++++++++-
 4 files changed, 18 insertions(+), 1 deletion(-)

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 0651865a4564..5b004b95648b 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -1037,6 +1037,8 @@ static inline u64 cgroup_id_from_mm(struct mm_struct *mm)
 	return id;
 }
 
+void mem_cgroup_flush_workqueue(void);
+
 extern int mem_cgroup_init(void);
 #else /* CONFIG_MEMCG */
 
@@ -1436,6 +1438,8 @@ static inline u64 cgroup_id_from_mm(struct mm_struct *mm)
 	return 0;
 }
 
+static inline void mem_cgroup_flush_workqueue(void) { }
+
 static inline int mem_cgroup_init(void) { return 0; }
 #endif /* CONFIG_MEMCG */
 
diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c
index 674a02891b38..f4053ebf4027 100644
--- a/kernel/sched/isolation.c
+++ b/kernel/sched/isolation.c
@@ -144,6 +144,8 @@ int housekeeping_update(struct cpumask *isol_mask)
 
 	synchronize_rcu();
 
+	mem_cgroup_flush_workqueue();
+
 	kfree(old);
 
 	return 0;
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 653e898a996a..65dfa48e54b7 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -44,6 +44,7 @@
 #include <linux/lockdep_api.h>
 #include <linux/lockdep.h>
 #include <linux/memblock.h>
+#include <linux/memcontrol.h>
 #include <linux/minmax.h>
 #include <linux/mm.h>
 #include <linux/module.h>
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 2289a0299331..b3ca241bb1d6 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -96,6 +96,8 @@ static bool cgroup_memory_nokmem __ro_after_init;
 /* BPF memory accounting disabled? */
 static bool cgroup_memory_nobpf __ro_after_init;
 
+static struct workqueue_struct *memcg_wq __ro_after_init;
+
 static struct kmem_cache *memcg_cachep;
 static struct kmem_cache *memcg_pn_cachep;
 
@@ -2013,7 +2015,7 @@ static void schedule_drain_work(int cpu, struct work_struct *work)
 	 */
 	guard(rcu)();
 	if (!cpu_is_isolated(cpu))
-		schedule_work_on(cpu, work);
+		queue_work_on(cpu, memcg_wq, work);
 }
 
 /*
@@ -5125,6 +5127,11 @@ void mem_cgroup_sk_uncharge(const struct sock *sk, unsigned int nr_pages)
 	refill_stock(memcg, nr_pages);
 }
 
+void mem_cgroup_flush_workqueue(void)
+{
+	flush_workqueue(memcg_wq);
+}
+
 static int __init cgroup_memory(char *s)
 {
 	char *token;
@@ -5167,6 +5174,9 @@ int __init mem_cgroup_init(void)
 	cpuhp_setup_state_nocalls(CPUHP_MM_MEMCQ_DEAD, "mm/memctrl:dead", NULL,
 				  memcg_hotplug_cpu_dead);
 
+	memcg_wq = alloc_workqueue("memcg", WQ_PERCPU, 0);
+	WARN_ON(!memcg_wq);
+
 	for_each_possible_cpu(cpu) {
 		INIT_WORK(&per_cpu_ptr(&memcg_stock, cpu)->work,
 			  drain_local_memcg_stock);