sched/isolation: Flush vmstat workqueues on cpuset isolated partition change

The HK_TYPE_DOMAIN housekeeping cpumask is now modifiable 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>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Marco Crivellari <marco.crivellari@suse.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Peter Zijlstra <peterz@infradead.org>
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: linux-mm@kvack.org

diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
index 3398a34..1909b94 100644 (file)
--- 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 f4053eb..160b3fc 100644 (file)
--- a/kernel/sched/isolation.c
+++ b/kernel/sched/isolation.c
@@ -145,6 +145,7 @@ int housekeeping_update(struct cpumask *isol_mask)
        synchronize_rcu();
 
        mem_cgroup_flush_workqueue();
+       vmstat_flush_workqueue();
 
        kfree(old);
 

diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 65dfa48..2d0c408 100644 (file)
--- 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 ed19c0d..d6e814c 100644 (file)
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -2124,6 +2124,11 @@ 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;