4 files changed, 44 insertions, 0 deletions

diff --git a/include/linux/mm.h b/include/linux/mm.h
index f5487a86b154..9f08a11b355c 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -29,6 +29,7 @@
 #include <linux/pgtable.h>
 #include <linux/kasan.h>
 #include <linux/memremap.h>
+#include <linux/slab.h>
 
 struct mempolicy;
 struct anon_vma;
@@ -627,6 +628,20 @@ struct vm_operations_struct {
 					  unsigned long addr);
 };
 
+#ifdef CONFIG_NUMA_BALANCING
+static inline void vma_numab_state_init(struct vm_area_struct *vma)
+{
+	vma->numab_state = NULL;
+}
+static inline void vma_numab_state_free(struct vm_area_struct *vma)
+{
+	kfree(vma->numab_state);
+}
+#else
+static inline void vma_numab_state_init(struct vm_area_struct *vma) {}
+static inline void vma_numab_state_free(struct vm_area_struct *vma) {}
+#endif /* CONFIG_NUMA_BALANCING */
+
 #ifdef CONFIG_PER_VMA_LOCK
 /*
  * Try to read-lock a vma. The function is allowed to occasionally yield false
@@ -747,6 +762,7 @@ static inline void vma_init(struct vm_area_struct *vma, struct mm_struct *mm)
 	vma->vm_ops = &dummy_vm_ops;
 	INIT_LIST_HEAD(&vma->anon_vma_chain);
 	vma_mark_detached(vma, false);
+	vma_numab_state_init(vma);
 }
 
 /* Use when VMA is not part of the VMA tree and needs no locking */
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 1b3031e95215..3e1a42673769 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -475,6 +475,10 @@ struct vma_lock {
 	struct rw_semaphore lock;
 };
 
+struct vma_numab_state {
+	unsigned long next_scan;
+};
+
 /*
  * This struct describes a virtual memory area. There is one of these
  * per VM-area/task. A VM area is any part of the process virtual memory
@@ -561,6 +565,9 @@ struct vm_area_struct {
 #ifdef CONFIG_NUMA
 	struct mempolicy *vm_policy;	/* NUMA policy for the VMA */
 #endif
+#ifdef CONFIG_NUMA_BALANCING
+	struct vma_numab_state *numab_state;	/* NUMA Balancing state */
+#endif
 	struct vm_userfaultfd_ctx vm_userfaultfd_ctx;
 } __randomize_layout;
 
diff --git a/kernel/fork.c b/kernel/fork.c
index c75088367bb4..2bde99037652 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -516,6 +516,7 @@ struct vm_area_struct *vm_area_dup(struct vm_area_struct *orig)
 		return NULL;
 	}
 	INIT_LIST_HEAD(&new->anon_vma_chain);
+	vma_numab_state_init(new);
 	dup_anon_vma_name(orig, new);
 
 	return new;
@@ -523,6 +524,7 @@ struct vm_area_struct *vm_area_dup(struct vm_area_struct *orig)
 
 void __vm_area_free(struct vm_area_struct *vma)
 {
+	vma_numab_state_free(vma);
 	free_anon_vma_name(vma);
 	vma_lock_free(vma);
 	kmem_cache_free(vm_area_cachep, vma);
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 6986ea31c984..7072de1686d5 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -3027,6 +3027,25 @@ static void task_numa_work(struct callback_head *work)
 		if (!vma_is_accessible(vma))
 			continue;
 
+		/* Initialise new per-VMA NUMAB state. */
+		if (!vma->numab_state) {
+			vma->numab_state = kzalloc(sizeof(struct vma_numab_state),
+				GFP_KERNEL);
+			if (!vma->numab_state)
+				continue;
+
+			vma->numab_state->next_scan = now +
+				msecs_to_jiffies(sysctl_numa_balancing_scan_delay);
+		}
+
+		/*
+		 * Scanning the VMA's of short lived tasks add more overhead. So
+		 * delay the scan for new VMAs.
+		 */
+		if (mm->numa_scan_seq && time_before(jiffies,
+						vma->numab_state->next_scan))
+			continue;
+
 		do {
 			start = max(start, vma->vm_start);
 			end = ALIGN(start + (pages << PAGE_SHIFT), HPAGE_SIZE);