[PATCH 06/27] mm: vmstat: Prepare to protect against concurrent isolated cpuset change

[PATCH 06/27] mm: vmstat: Prepare to protect against concurrent isolated cpuset change

[Frederic Weisbecker]

The HK_TYPE_DOMAIN housekeeping cpumask will soon be made modifyable at
runtime. In order to synchronize against vmstat workqueue to make sure
that no asynchronous vmstat work is pending or executing on a newly made
isolated CPU, read-lock the housekeeping rwsem lock while targeting
and queueing a vmstat work.

Whenever housekeeping will update the HK_TYPE_DOMAIN cpumask, a vmstat
workqueue flush will also be issued in a further change to make sure
that no work remains pending after a CPU had been made isolated.

Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
---
 mm/vmstat.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/mm/vmstat.c b/mm/vmstat.c
index 429ae5339bfe..53123675fe31 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -2115,11 +2115,13 @@ static void vmstat_shepherd(struct work_struct *w)
 		 * infrastructure ever noticing. Skip regular flushing from vmstat_shepherd
 		 * for all isolated CPUs to avoid interference with the isolated workload.
 		 */
-		if (cpu_is_isolated(cpu))
-			continue;
+		scoped_guard(housekeeping) {
+			if (cpu_is_isolated(cpu))
+				continue;
 
-		if (!delayed_work_pending(dw) && need_update(cpu))
-			queue_delayed_work_on(cpu, mm_percpu_wq, dw, 0);
+			if (!delayed_work_pending(dw) && need_update(cpu))
+				queue_delayed_work_on(cpu, mm_percpu_wq, dw, 0);
+		}
 
 		cond_resched();
 	}
-- 
2.48.1

[PATCH 12/27] cpu: Provide lockdep check for CPU hotplug lock write-held

[Frederic Weisbecker]

cpuset modifies partitions, including isolated, while holding the cpu
hotplug lock read-held.

This means that write-holding the CPU hotplug lock is safe to
synchronize against housekeeping cpumask changes.

Provide a lockdep check to validate that.

Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
---
 include/linux/cpuhplock.h    | 1 +
 include/linux/percpu-rwsem.h | 1 +
 kernel/cpu.c                 | 5 +++++
 3 files changed, 7 insertions(+)

diff --git a/include/linux/cpuhplock.h b/include/linux/cpuhplock.h
index f7aa20f62b87..286b3ab92e15 100644
--- a/include/linux/cpuhplock.h
+++ b/include/linux/cpuhplock.h
@@ -13,6 +13,7 @@
 struct device;
 
 extern int lockdep_is_cpus_held(void);
+extern int lockdep_is_cpus_write_held(void);
 
 #ifdef CONFIG_HOTPLUG_CPU
 void cpus_write_lock(void);
diff --git a/include/linux/percpu-rwsem.h b/include/linux/percpu-rwsem.h
index 288f5235649a..c8cb010d655e 100644
--- a/include/linux/percpu-rwsem.h
+++ b/include/linux/percpu-rwsem.h
@@ -161,6 +161,7 @@ extern void percpu_free_rwsem(struct percpu_rw_semaphore *);
 	__percpu_init_rwsem(sem, #sem, &rwsem_key);		\
 })
 
+#define percpu_rwsem_is_write_held(sem)	lockdep_is_held_type(sem, 0)
 #define percpu_rwsem_is_held(sem)	lockdep_is_held(sem)
 #define percpu_rwsem_assert_held(sem)	lockdep_assert_held(sem)
 
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 069fce6c7eae..ccf11a17c7fd 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -533,6 +533,11 @@ int lockdep_is_cpus_held(void)
 {
 	return percpu_rwsem_is_held(&cpu_hotplug_lock);
 }
+
+int lockdep_is_cpus_write_held(void)
+{
+	return percpu_rwsem_is_write_held(&cpu_hotplug_lock);
+}
 #endif
 
 static void lockdep_acquire_cpus_lock(void)
-- 
2.48.1

[PATCH 16/27] sched/isolation: Flush memcg workqueues on cpuset isolated partition change

[Frederic Weisbecker]

The HK_TYPE_DOMAIN housekeeping cpumask is now modifyable 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.

Signed-off-by: Frederic Weisbecker <frederic@kernel.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 87b6688f124a..ef5036c6bf04 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -1046,6 +1046,8 @@ 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 */
 
@@ -1451,6 +1453,8 @@ 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 7814d60be87e..6fb0c7956516 100644
--- a/kernel/sched/isolation.c
+++ b/kernel/sched/isolation.c
@@ -140,6 +140,8 @@ int housekeeping_update(struct cpumask *mask, enum hk_type type)
 
 	synchronize_rcu();
 
+	mem_cgroup_flush_workqueue();
+
 	kfree(old);
 
 	return 0;
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 04094567cad4..53107c021fe9 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 29d44af6c426..928b90cdb5ba 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;
 
@@ -1979,7 +1981,7 @@ static void schedule_drain_work(int cpu, struct work_struct *work)
 {
 	housekeeping_lock();
 	if (!cpu_is_isolated(cpu))
-		schedule_work_on(cpu, work);
+		queue_work_on(cpu, memcg_wq, work);
 	housekeeping_unlock();
 }
 
@@ -5140,6 +5142,11 @@ void mem_cgroup_uncharge_skmem(struct mem_cgroup *memcg, 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;
@@ -5182,6 +5189,9 @@ 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", 0, 0);
+	WARN_ON(!memcg_wq);
+
 	for_each_possible_cpu(cpu) {
 		INIT_WORK(&per_cpu_ptr(&memcg_stock, cpu)->work,
 			  drain_local_memcg_stock);
-- 
2.48.1

[PATCH 17/27] sched/isolation: Flush vmstat workqueues on cpuset isolated partition change

[Frederic Weisbecker]

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

This involves flushing the whole mm_percpu_wq workqueue, shared with
LRU drain, introducing here a welcome side effect.

Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
---
 include/linux/vmstat.h   | 2 ++
 kernel/sched/isolation.c | 1 +
 kernel/sched/sched.h     | 1 +
 mm/vmstat.c              | 5 +++++
 4 files changed, 9 insertions(+)

diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
index b2ccb6845595..ba7caacdf356 100644
--- a/include/linux/vmstat.h
+++ b/include/linux/vmstat.h
@@ -303,6 +303,7 @@ int calculate_pressure_threshold(struct zone *zone);
 int calculate_normal_threshold(struct zone *zone);
 void set_pgdat_percpu_threshold(pg_data_t *pgdat,
 				int (*calculate_pressure)(struct zone *));
+void vmstat_flush_workqueue(void);
 #else /* CONFIG_SMP */
 
 /*
@@ -403,6 +404,7 @@ static inline void __dec_node_page_state(struct page *page,
 static inline void refresh_zone_stat_thresholds(void) { }
 static inline void cpu_vm_stats_fold(int cpu) { }
 static inline void quiet_vmstat(void) { }
+static inline void vmstat_flush_workqueue(void) { }
 
 static inline void drain_zonestat(struct zone *zone,
 			struct per_cpu_zonestat *pzstats) { }
diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c
index 6fb0c7956516..0119685796be 100644
--- a/kernel/sched/isolation.c
+++ b/kernel/sched/isolation.c
@@ -141,6 +141,7 @@ int housekeeping_update(struct cpumask *mask, enum hk_type type)
 	synchronize_rcu();
 
 	mem_cgroup_flush_workqueue();
+	vmstat_flush_workqueue();
 
 	kfree(old);
 
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 53107c021fe9..e2c4258cb818 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -69,6 +69,7 @@
 #include <linux/types.h>
 #include <linux/u64_stats_sync_api.h>
 #include <linux/uaccess.h>
+#include <linux/vmstat.h>
 #include <linux/wait_api.h>
 #include <linux/wait_bit.h>
 #include <linux/workqueue_api.h>
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 53123675fe31..5d462fe12548 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -2095,6 +2095,11 @@ static void vmstat_shepherd(struct work_struct *w);
 
 static DECLARE_DEFERRABLE_WORK(shepherd, vmstat_shepherd);
 
+void vmstat_flush_workqueue(void)
+{
+	flush_workqueue(mm_percpu_wq);
+}
+
 static void vmstat_shepherd(struct work_struct *w)
 {
 	int cpu;
-- 
2.48.1

Re: [PATCH 16/27] sched/isolation: Flush memcg workqueues on cpuset isolated partition change

[Shakeel Butt]

On Fri, Jun 20, 2025 at 05:22:57PM +0200, Frederic Weisbecker wrote:
> The HK_TYPE_DOMAIN housekeeping cpumask is now modifyable 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.
> 
> Signed-off-by: Frederic Weisbecker <frederic@kernel.org>

Acked-by: Shakeel Butt <shakeel.butt@linux.dev>