diff --git a/include/linux/sched.h b/include/linux/sched.h
index 1127a46..59f953b 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1454,6 +1454,7 @@
 
 #define TNF_MIGRATED	0x01
 #define TNF_NO_GROUP	0x02
+#define TNF_SHARED	0x04
 
 #ifdef CONFIG_NUMA_BALANCING
 extern void task_numa_fault(int last_node, int node, int pages, int flags);
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 5166b9b..222c2d0 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1381,7 +1381,7 @@
 	spin_lock_nested(l2, SINGLE_DEPTH_NESTING);
 }
 
-static void task_numa_group(struct task_struct *p, int cpupid)
+static void task_numa_group(struct task_struct *p, int cpupid, int flags)
 {
 	struct numa_group *grp, *my_grp;
 	struct task_struct *tsk;
@@ -1439,10 +1439,16 @@
 	if (my_grp->nr_tasks == grp->nr_tasks && my_grp > grp)
 		goto unlock;
 
-	if (!get_numa_group(grp))
-		goto unlock;
+	/* Always join threads in the same process. */
+	if (tsk->mm == current->mm)
+		join = true;
 
-	join = true;
+	/* Simple filter to avoid false positives due to PID collisions */
+	if (flags & TNF_SHARED)
+		join = true;
+
+	if (join && !get_numa_group(grp))
+		join = false;
 
 unlock:
 	rcu_read_unlock();
@@ -1539,7 +1545,7 @@
 	} else {
 		priv = cpupid_match_pid(p, last_cpupid);
 		if (!priv && !(flags & TNF_NO_GROUP))
-			task_numa_group(p, last_cpupid);
+			task_numa_group(p, last_cpupid, flags);
 	}
 
 	/*
diff --git a/mm/memory.c b/mm/memory.c
index 9898eeb..823720c 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3584,6 +3584,13 @@
 	if (!pte_write(pte))
 		flags |= TNF_NO_GROUP;
 
+	/*
+	 * Flag if the page is shared between multiple address spaces. This
+	 * is later used when determining whether to group tasks together
+	 */
+	if (page_mapcount(page) > 1 && (vma->vm_flags & VM_SHARED))
+		flags |= TNF_SHARED;
+
 	last_cpupid = page_cpupid_last(page);
 	page_nid = page_to_nid(page);
 	target_nid = numa_migrate_prep(page, vma, addr, page_nid);