Also add a config option for the same.

High level design:

While (1):
  Scan the slowtier pages belonging to VMAs of a task.
  Add to migation list.

A separate thread:
  Migrate scanned pages to a toptier node based on heuristics.

The overall code is influenced by khugepaged design.

Signed-off-by: Raghavendra K T <raghavendra.kt@amd.com>
---
 mm/Kconfig  |   8 +++
 mm/Makefile |   1 +
 mm/kscand.c | 163 ++++++++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 172 insertions(+)
 create mode 100644 mm/kscand.c

diff --git a/mm/Kconfig b/mm/Kconfig
index 781be3240e21..d1e5be76a96e 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -750,6 +750,14 @@ config KSM
 	  until a program has madvised that an area is MADV_MERGEABLE, and
 	  root has set /sys/kernel/mm/ksm/run to 1 (if CONFIG_SYSFS is set).
 
+config KSCAND
+	bool "Enable PTE A bit scanning and Migration"
+	depends on NUMA_BALANCING
+	help
+	  Enable PTE A bit scanning of page. The option creates a separate
+	  kthread for scanning and migration. Accessed slow-tier pages are
+	  migrated to a regular NUMA node to reduce hot page access latency.
+
 config DEFAULT_MMAP_MIN_ADDR
 	int "Low address space to protect from user allocation"
 	depends on MMU
diff --git a/mm/Makefile b/mm/Makefile
index 1a7a11d4933d..a16ef2ff3da1 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -97,6 +97,7 @@ obj-$(CONFIG_FAIL_PAGE_ALLOC) += fail_page_alloc.o
 obj-$(CONFIG_MEMTEST)		+= memtest.o
 obj-$(CONFIG_MIGRATION) += migrate.o
 obj-$(CONFIG_NUMA) += memory-tiers.o
+obj-$(CONFIG_KSCAND) += kscand.o
 obj-$(CONFIG_DEVICE_MIGRATION) += migrate_device.o
 obj-$(CONFIG_TRANSPARENT_HUGEPAGE) += huge_memory.o khugepaged.o
 obj-$(CONFIG_PAGE_COUNTER) += page_counter.o
diff --git a/mm/kscand.c b/mm/kscand.c
new file mode 100644
index 000000000000..f7bbbc70c86a
--- /dev/null
+++ b/mm/kscand.c
@@ -0,0 +1,163 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/mm.h>
+#include <linux/mm_types.h>
+#include <linux/sched.h>
+#include <linux/sched/mm.h>
+#include <linux/mmu_notifier.h>
+#include <linux/swap.h>
+#include <linux/mm_inline.h>
+#include <linux/kthread.h>
+#include <linux/string.h>
+#include <linux/delay.h>
+#include <linux/cleanup.h>
+
+#include <asm/pgalloc.h>
+#include "internal.h"
+
+static struct task_struct *kscand_thread __read_mostly;
+static DEFINE_MUTEX(kscand_mutex);
+
+/* How long to pause between two scan cycles */
+static unsigned int kscand_scan_sleep_ms __read_mostly = 20;
+
+/* Max number of mms to scan in one scan cycle */
+#define KSCAND_MMS_TO_SCAN	(4 * 1024UL)
+static unsigned long kscand_mms_to_scan __read_mostly = KSCAND_MMS_TO_SCAN;
+
+bool kscand_scan_enabled = true;
+static bool need_wakeup;
+
+static unsigned long kscand_sleep_expire;
+
+static DECLARE_WAIT_QUEUE_HEAD(kscand_wait);
+
+/* Data structure to keep track of current mm under scan */
+struct kscand_scan {
+	struct list_head mm_head;
+};
+
+struct kscand_scan kscand_scan = {
+	.mm_head = LIST_HEAD_INIT(kscand_scan.mm_head),
+};
+
+static inline int kscand_has_work(void)
+{
+	return !list_empty(&kscand_scan.mm_head);
+}
+
+static inline bool kscand_should_wakeup(void)
+{
+	bool wakeup = kthread_should_stop() || need_wakeup ||
+	       time_after_eq(jiffies, kscand_sleep_expire);
+
+	need_wakeup = false;
+
+	return wakeup;
+}
+
+static void kscand_wait_work(void)
+{
+	const unsigned long scan_sleep_jiffies =
+		msecs_to_jiffies(kscand_scan_sleep_ms);
+
+	if (!scan_sleep_jiffies)
+		return;
+
+	kscand_sleep_expire = jiffies + scan_sleep_jiffies;
+
+	/* Allows kthread to pause scanning */
+	wait_event_timeout(kscand_wait, kscand_should_wakeup(),
+			scan_sleep_jiffies);
+}
+static void kscand_do_scan(void)
+{
+	unsigned long iter = 0, mms_to_scan;
+
+	mms_to_scan = READ_ONCE(kscand_mms_to_scan);
+
+	while (true) {
+		if (unlikely(kthread_should_stop()) ||
+			!READ_ONCE(kscand_scan_enabled))
+			break;
+
+		if (kscand_has_work())
+			msleep(100);
+
+		iter++;
+
+		if (iter >= mms_to_scan)
+			break;
+		cond_resched();
+	}
+}
+
+static int kscand(void *none)
+{
+	while (true) {
+		if (unlikely(kthread_should_stop()))
+			break;
+
+		while (!READ_ONCE(kscand_scan_enabled)) {
+			cpu_relax();
+			kscand_wait_work();
+		}
+
+		kscand_do_scan();
+
+		kscand_wait_work();
+	}
+	return 0;
+}
+
+static int start_kscand(void)
+{
+	struct task_struct *kthread;
+
+	guard(mutex)(&kscand_mutex);
+
+	if (kscand_thread)
+		return 0;
+
+	kthread = kthread_run(kscand, NULL, "kscand");
+	if (IS_ERR(kscand_thread)) {
+		pr_err("kscand: kthread_run(kscand) failed\n");
+		return PTR_ERR(kthread);
+	}
+
+	kscand_thread = kthread;
+	pr_info("kscand: Successfully started kscand");
+
+	if (!list_empty(&kscand_scan.mm_head))
+		wake_up_interruptible(&kscand_wait);
+
+	return 0;
+}
+
+static int stop_kscand(void)
+{
+	guard(mutex)(&kscand_mutex);
+
+	if (kscand_thread) {
+		kthread_stop(kscand_thread);
+		kscand_thread = NULL;
+	}
+
+	return 0;
+}
+
+static int __init kscand_init(void)
+{
+	int err;
+
+	err = start_kscand();
+	if (err)
+		goto err_kscand;
+
+	return 0;
+
+err_kscand:
+	stop_kscand();
+
+	return err;
+}
+subsys_initcall(kscand_init);
-- 
2.34.1