Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   Oscar Salvador <osalvador@suse.de>
To:     Andrew Morton <akpm@linux-foundation.org>
Cc:     Dave Hansen <dave.hansen@linux.intel.com>,
        "Huang, Ying" <ying.huang@intel.com>,
        Abhishek Goel <huntbag@linux.vnet.ibm.com>,
        Baolin Wang <baolin.wang@linux.alibaba.com>,
        linux-mm@kvack.org, linux-kernel@vger.kernel.org,
        Oscar Salvador <osalvador@suse.de>
Subject: [PATCH v2] mm: Only re-generate demotion targets when a numa node changes its N_CPU state
Date:   Thu, 10 Mar 2022 13:07:49 +0100
Message-Id: <20220310120749.23077-1-osalvador@suse.de>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

Abhishek reported that after patch [1], hotplug operations are
taking ~double the expected time. [2]

The reason behind is that the CPU callbacks that migrate_on_reclaim_init()
sets always call set_migration_target_nodes() whenever a CPU is brought
up/down.
But we only care about numa nodes going from having cpus to become
cpuless, and vice versa, as that influences the demotion_target order.

We do already have two CPU callbacks (vmstat_cpu_online() and vmstat_cpu_dead())
that check exactly that, so get rid of the CPU callbacks in
migrate_on_reclaim_init() and only call set_migration_target_nodes() from
vmstat_cpu_{dead,online}() whenever a numa node change its N_CPU state.

[1] https://lore.kernel.org/linux-mm/20210721063926.3024591-2-ying.huang@intel.com/
[2] https://lore.kernel.org/linux-mm/eb438ddd-2919-73d4-bd9f-b7eecdd9577a@linux.vnet.ibm.com/

Reported-by: Abhishek Goel <huntbag@linux.vnet.ibm.com>
Signed-off-by: Oscar Salvador <osalvador@suse.de>
---
v1 -> v2: - Fix prototype function declaration
          - Fix build error on RISC
          - Adressed feedback from Baolin and Huang
---
 include/linux/migrate.h |  8 ++++++++
 mm/migrate.c            | 41 +++++------------------------------------
 mm/vmstat.c             | 13 ++++++++++++-
 3 files changed, 25 insertions(+), 37 deletions(-)

diff --git a/include/linux/migrate.h b/include/linux/migrate.h
index db96e10eb8da..90e75d5a54d6 100644
--- a/include/linux/migrate.h
+++ b/include/linux/migrate.h
@@ -48,7 +48,15 @@ int folio_migrate_mapping(struct address_space *mapping,
 		struct folio *newfolio, struct folio *folio, int extra_count);
 
 extern bool numa_demotion_enabled;
+extern void migrate_on_reclaim_init(void);
+#ifdef CONFIG_HOTPLUG_CPU
+extern void set_migration_target_nodes(void);
 #else
+static inline void set_migration_target_nodes(void) {}
+#endif
+#else
+
+static inline void set_migration_target_nodes(void) {}
 
 static inline void putback_movable_pages(struct list_head *l) {}
 static inline int migrate_pages(struct list_head *l, new_page_t new,
diff --git a/mm/migrate.c b/mm/migrate.c
index c7da064b4781..f9d5b6092a42 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();
@@ -3254,51 +3254,20 @@ 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)
+void __init migrate_on_reclaim_init(void)
 {
-	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.
+	 * At this point, all numa nodes with memory/CPus have their state
+	 * properly set, so we can build the demotion order now.
 	 */
-	WARN_ON(ret < 0);
-	ret = cpuhp_setup_state(CPUHP_AP_MM_DEMOTION_ONLINE, "mm/demotion:online",
-				migration_online_cpu, NULL);
-	WARN_ON(ret < 0);
-
+	set_migration_target_nodes();
 	hotplug_memory_notifier(migrate_on_reclaim_callback, 100);
-	return 0;
 }
-late_initcall(migrate_on_reclaim_init);
 #endif /* CONFIG_HOTPLUG_CPU */
 
 bool numa_demotion_enabled = false;
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 4057372745d0..9e9536df51b5 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;
 }
 
@@ -2097,6 +2105,9 @@ void __init init_mm_internals(void)
 
 	start_shepherd_timer();
 #endif
+#if defined(CONFIG_MIGRATION) && defined(CONFIG_HOTPLUG_CPU)
+	migrate_on_reclaim_init();
+#endif
 #ifdef CONFIG_PROC_FS
 	proc_create_seq("buddyinfo", 0444, NULL, &fragmentation_op);
 	proc_create_seq("pagetypeinfo", 0400, NULL, &pagetypeinfo_op);
-- 
2.34.1