---

yaml
---
r: 344814
b: refs/heads/master
c: 5bca230
h: refs/heads/master
v: v3

[refs]

@@ -1,2 +1,2 @@
 ---
-refs/heads/master: 3105b86a9fee7d2c2e76edb53bbbc4027599628f
+refs/heads/master: 5bca23035391928c4c7301835accca3551b96cc2

trunk/include/linux/mm_types.h

@@ -418,10 +418,20 @@ struct mm_struct {
 
 	/* numa_scan_seq prevents two threads setting pte_numa */
 	int numa_scan_seq;
+
+	/*
+	 * The first node a task was scheduled on. If a task runs on
+	 * a different node than Make PTE Scan Go Now.
+	 */
+	int first_nid;
 #endif
 	struct uprobes_state uprobes_state;
 };
 
+/* first nid will either be a valid NID or one of these values */
+#define NUMA_PTE_SCAN_INIT	-1
+#define NUMA_PTE_SCAN_ACTIVE	-2
+
 static inline void mm_init_cpumask(struct mm_struct *mm)
 {
 #ifdef CONFIG_CPUMASK_OFFSTACK

trunk/kernel/fork.c

@@ -820,6 +820,9 @@ struct mm_struct *dup_mm(struct task_struct *tsk)
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 	mm->pmd_huge_pte = NULL;
+#endif
+#ifdef CONFIG_NUMA_BALANCING
+	mm->first_nid = NUMA_PTE_SCAN_INIT;
 #endif
 	if (!mm_init(mm, tsk))
 		goto fail_nomem;

trunk/kernel/sched/fair.c

@@ -860,6 +860,24 @@ void task_numa_work(struct callback_head *work)
 	if (p->flags & PF_EXITING)
 		return;
 
+	/*
+	 * We do not care about task placement until a task runs on a node
+	 * other than the first one used by the address space. This is
+	 * largely because migrations are driven by what CPU the task
+	 * is running on. If it's never scheduled on another node, it'll
+	 * not migrate so why bother trapping the fault.
+	 */
+	if (mm->first_nid == NUMA_PTE_SCAN_INIT)
+		mm->first_nid = numa_node_id();
+	if (mm->first_nid != NUMA_PTE_SCAN_ACTIVE) {
+		/* Are we running on a new node yet? */
+		if (numa_node_id() == mm->first_nid &&
+		    !sched_feat_numa(NUMA_FORCE))
+			return;
+
+		mm->first_nid = NUMA_PTE_SCAN_ACTIVE;
+	}
+
 	/*
 	 * Reset the scan period if enough time has gone by. Objective is that
 	 * scanning will be reduced if pages are properly placed. As tasks

trunk/kernel/sched/features.h

@@ -65,8 +65,10 @@ SCHED_FEAT(LB_MIN, false)
 /*
  * Apply the automatic NUMA scheduling policy. Enabled automatically
  * at runtime if running on a NUMA machine. Can be controlled via
- * numa_balancing=
+ * numa_balancing=. Allow PTE scanning to be forced on UMA machines
+ * for debugging the core machinery.
  */
 #ifdef CONFIG_NUMA_BALANCING
 SCHED_FEAT(NUMA,	false)
+SCHED_FEAT(NUMA_FORCE,	false)
 #endif