Re: [PATCH -V11 2/9] mm/migrate: update node demotion order on hotplug events

[Oscar Salvador <osalvador@xxxxxxx>]

On Fri, Feb 25, 2022 at 10:32:20AM +0800, Huang, Ying wrote:
> -static int migration_online_cpu(unsigned int cpu)
> +static int migration_cpu_hotplug(unsigned int cpu)
>  {
> -	set_migration_target_nodes();
> -	return 0;
> -}
> +	static int nr_cpu_node_saved;
> +	int nr_cpu_node;
> +
> +	nr_cpu_node = num_node_state(N_CPU);
> +	if (nr_cpu_node != nr_cpu_node_saved) {
> +		set_migration_target_nodes();
> +		nr_cpu_node_saved = nr_cpu_node;
> +	}
>  
> -static int migration_offline_cpu(unsigned int cpu)
> -{
> -	set_migration_target_nodes();
>  	return 0;
>  }

These callbacks feel like re-inveting the wheel.
We do already have two functions that get called during cpu
online/offline, and that sets/clears N_CPU on the node properly.
And that is exactly what we want, so what about the following (only
compile-tested):

diff --git a/include/linux/migrate.h b/include/linux/migrate.h
index db96e10eb8da..031af2bb71dc 100644
--- a/include/linux/migrate.h
+++ b/include/linux/migrate.h
@@ -48,6 +48,7 @@ int folio_migrate_mapping(struct address_space *mapping,
 		struct folio *newfolio, struct folio *folio, int extra_count);

 extern bool numa_demotion_enabled;
+extern void set_migration_target_nodes(void);
 #else

 static inline void putback_movable_pages(struct list_head *l) {}
diff --git a/mm/migrate.c b/mm/migrate.c
index c7da064b4781..7847e4de01d7 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -3190,7 +3190,7 @@ static void __set_migration_target_nodes(void)
 /*
  * For callers that do not hold get_online_mems() already.
  */
-static void set_migration_target_nodes(void)
+void set_migration_target_nodes(void)
 {
 	get_online_mems();
 	__set_migration_target_nodes();
@@ -3254,47 +3254,13 @@ static int __meminit migrate_on_reclaim_callback(struct notifier_block *self,
 	return notifier_from_errno(0);
 }

-/*
- * React to hotplug events that might affect the migration targets
- * like events that online or offline NUMA nodes.
- *
- * The ordering is also currently dependent on which nodes have
- * CPUs.  That means we need CPU on/offline notification too.
- */
-static int migration_online_cpu(unsigned int cpu)
-{
-	set_migration_target_nodes();
-	return 0;
-}
-
-static int migration_offline_cpu(unsigned int cpu)
-{
-	set_migration_target_nodes();
-	return 0;
-}
-
 static int __init migrate_on_reclaim_init(void)
 {
-	int ret;
-
 	node_demotion = kmalloc_array(nr_node_ids,
 				      sizeof(struct demotion_nodes),
 				      GFP_KERNEL);
 	WARN_ON(!node_demotion);

-	ret = cpuhp_setup_state_nocalls(CPUHP_MM_DEMOTION_DEAD, "mm/demotion:offline",
-					NULL, migration_offline_cpu);
-	/*
-	 * In the unlikely case that this fails, the automatic
-	 * migration targets may become suboptimal for nodes
-	 * where N_CPU changes.  With such a small impact in a
-	 * rare case, do not bother trying to do anything special.
-	 */
-	WARN_ON(ret < 0);
-	ret = cpuhp_setup_state(CPUHP_AP_MM_DEMOTION_ONLINE, "mm/demotion:online",
-				migration_online_cpu, NULL);
-	WARN_ON(ret < 0);
-
 	hotplug_memory_notifier(migrate_on_reclaim_callback, 100);
 	return 0;
 }
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 4057372745d0..0529a83c8f89 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -28,6 +28,7 @@
 #include <linux/mm_inline.h>
 #include <linux/page_ext.h>
 #include <linux/page_owner.h>
+#include <linux/migrate.h>

 #include "internal.h"

@@ -2043,7 +2044,12 @@ static void __init init_cpu_node_state(void)
 static int vmstat_cpu_online(unsigned int cpu)
 {
 	refresh_zone_stat_thresholds();
-	node_set_state(cpu_to_node(cpu), N_CPU);
+
+	if (!node_state(cpu_to_node(cpu), N_CPU)) {
+		node_set_state(cpu_to_node(cpu), N_CPU);
+		set_migration_target_nodes();
+	}
+
 	return 0;
 }

@@ -2066,6 +2072,8 @@ static int vmstat_cpu_dead(unsigned int cpu)
 		return 0;

 	node_clear_state(node, N_CPU);
+	set_migration_target_nodes();
+
 	return 0;
 }

I think this is just easier and meets exactly the goal.

We could go even further and move the work left in
migrate_on_reclaim_init() to init_mm_internals().
(I __think__ we should be fine because there is no dependency
there, e.g: notifier being set up somewhere later after
init_mm_internals() has been called).

-- 
Oscar Salvador
SUSE Labs