mm: migrate: make demotion knob depend on migration

The memory demotion needs to call migrate_pages() to do the jobs.  And
it is controlled by a knob, however, the knob doesn't depend on
CONFIG_MIGRATION.  The knob could be truned on even though MIGRATION is
disabled, this will not cause any crash since migrate_pages() would just
return -ENOSYS.  But it is definitely not optimal to go through demotion
path then retry regular swap every time.

And it doesn't make too much sense to have the knob visible to the users
when !MIGRATION.  Move the related code from mempolicy.[h|c] to
migrate.[h|c].

Link: https://lkml.kernel.org/r/20211015005559.246709-1-shy828301@gmail.com
Signed-off-by: Yang Shi <shy828301@gmail.com>
Acked-by: "Huang, Ying" <ying.huang@intel.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 61 insertions, 0 deletions

diff --git a/mm/migrate.c b/mm/migrate.c
index 1852d787e6ab..51e310a94516 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -3306,3 +3306,64 @@ static int __init migrate_on_reclaim_init(void)
 }
 late_initcall(migrate_on_reclaim_init);
 #endif /* CONFIG_HOTPLUG_CPU */
+
+bool numa_demotion_enabled = false;
+
+#ifdef CONFIG_SYSFS
+static ssize_t numa_demotion_enabled_show(struct kobject *kobj,
+					  struct kobj_attribute *attr, char *buf)
+{
+	return sysfs_emit(buf, "%s\n",
+			  numa_demotion_enabled ? "true" : "false");
+}
+
+static ssize_t numa_demotion_enabled_store(struct kobject *kobj,
+					   struct kobj_attribute *attr,
+					   const char *buf, size_t count)
+{
+	if (!strncmp(buf, "true", 4) || !strncmp(buf, "1", 1))
+		numa_demotion_enabled = true;
+	else if (!strncmp(buf, "false", 5) || !strncmp(buf, "0", 1))
+		numa_demotion_enabled = false;
+	else
+		return -EINVAL;
+
+	return count;
+}
+
+static struct kobj_attribute numa_demotion_enabled_attr =
+	__ATTR(demotion_enabled, 0644, numa_demotion_enabled_show,
+	       numa_demotion_enabled_store);
+
+static struct attribute *numa_attrs[] = {
+	&numa_demotion_enabled_attr.attr,
+	NULL,
+};
+
+static const struct attribute_group numa_attr_group = {
+	.attrs = numa_attrs,
+};
+
+static int __init numa_init_sysfs(void)
+{
+	int err;
+	struct kobject *numa_kobj;
+
+	numa_kobj = kobject_create_and_add("numa", mm_kobj);
+	if (!numa_kobj) {
+		pr_err("failed to create numa kobject\n");
+		return -ENOMEM;
+	}
+	err = sysfs_create_group(numa_kobj, &numa_attr_group);
+	if (err) {
+		pr_err("failed to register numa group\n");
+		goto delete_obj;
+	}
+	return 0;
+
+delete_obj:
+	kobject_put(numa_kobj);
+	return err;
+}
+subsys_initcall(numa_init_sysfs);
+#endif