[PATCH 05/33] mm: vmstat: Prepare to protect against concurrent isolated cpuset change

[PATCH 05/33] 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, target and queue a vmstat work under the same RCU read
side critical section.

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 has 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 71cd1ceba191..b90325ee49d3 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -2133,11 +2133,13 @@ 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(rcu) {
+			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();
 	}
-- 
2.51.0

[PATCH 15/33] 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.

Acked-by: Shakeel Butt <shakeel.butt@linux.dev>
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 785173aa0739..8b23ff000473 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -1048,6 +1048,8 @@ 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 */
 
@@ -1453,6 +1455,8 @@ 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 48f3b6b20604..e85f402b103a 100644
--- a/kernel/sched/isolation.c
+++ b/kernel/sched/isolation.c
@@ -124,6 +124,8 @@ 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 d3512138027b..1dad1ac7fc61 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 2649d6c09160..1aa2dfa32ccd 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -95,6 +95,8 @@ 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;
 
@@ -1974,7 +1976,7 @@ 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);
 }
 
 /*
@@ -5071,6 +5073,11 @@ 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;
@@ -5113,6 +5120,9 @@ 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);
-- 
2.51.0

[PATCH 16/33] 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 c287998908bf..a81aa5635b47 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 e85f402b103a..86ce39aa1e9f 100644
--- a/kernel/sched/isolation.c
+++ b/kernel/sched/isolation.c
@@ -125,6 +125,7 @@ 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 1dad1ac7fc61..2d4de083200a 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -68,6 +68,7 @@
 #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 b90325ee49d3..69412b61fe1b 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -2113,6 +2113,11 @@ 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;
-- 
2.51.0