1 files changed, 40 insertions, 19 deletions

diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 07e5c67f48a8..f307bd82d750 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -331,7 +331,7 @@ static unsigned long find_smallest_section_pfn(int nid, struct zone *zone,
 				     unsigned long end_pfn)
 {
 	for (; start_pfn < end_pfn; start_pfn += PAGES_PER_SUBSECTION) {
-		if (unlikely(!pfn_valid(start_pfn)))
+		if (unlikely(!pfn_to_online_page(start_pfn)))
 			continue;
 
 		if (unlikely(pfn_to_nid(start_pfn) != nid))
@@ -356,7 +356,7 @@ static unsigned long find_biggest_section_pfn(int nid, struct zone *zone,
 	/* pfn is the end pfn of a memory section. */
 	pfn = end_pfn - 1;
 	for (; pfn >= start_pfn; pfn -= PAGES_PER_SUBSECTION) {
-		if (unlikely(!pfn_valid(pfn)))
+		if (unlikely(!pfn_to_online_page(pfn)))
 			continue;
 
 		if (unlikely(pfn_to_nid(pfn) != nid))
@@ -415,7 +415,7 @@ static void shrink_zone_span(struct zone *zone, unsigned long start_pfn,
 	 */
 	pfn = zone_start_pfn;
 	for (; pfn < zone_end_pfn; pfn += PAGES_PER_SUBSECTION) {
-		if (unlikely(!pfn_valid(pfn)))
+		if (unlikely(!pfn_to_online_page(pfn)))
 			continue;
 
 		if (page_zone(pfn_to_page(pfn)) != zone)
@@ -471,6 +471,16 @@ static void __remove_zone(struct zone *zone, unsigned long start_pfn,
 	struct pglist_data *pgdat = zone->zone_pgdat;
 	unsigned long flags;
 
+#ifdef CONFIG_ZONE_DEVICE
+	/*
+	 * Zone shrinking code cannot properly deal with ZONE_DEVICE. So
+	 * we will not try to shrink the zones - which is okay as
+	 * set_zone_contiguous() cannot deal with ZONE_DEVICE either way.
+	 */
+	if (zone_idx(zone) == ZONE_DEVICE)
+		return;
+#endif
+
 	pgdat_resize_lock(zone->zone_pgdat, &flags);
 	shrink_zone_span(zone, start_pfn, start_pfn + nr_pages);
 	update_pgdat_span(pgdat);
@@ -1646,6 +1656,18 @@ static int check_cpu_on_node(pg_data_t *pgdat)
 	return 0;
 }
 
+static int check_no_memblock_for_node_cb(struct memory_block *mem, void *arg)
+{
+	int nid = *(int *)arg;
+
+	/*
+	 * If a memory block belongs to multiple nodes, the stored nid is not
+	 * reliable. However, such blocks are always online (e.g., cannot get
+	 * offlined) and, therefore, are still spanned by the node.
+	 */
+	return mem->nid == nid ? -EEXIST : 0;
+}
+
 /**
  * try_offline_node
  * @nid: the node ID
@@ -1658,25 +1680,24 @@ static int check_cpu_on_node(pg_data_t *pgdat)
 void try_offline_node(int nid)
 {
 	pg_data_t *pgdat = NODE_DATA(nid);
-	unsigned long start_pfn = pgdat->node_start_pfn;
-	unsigned long end_pfn = start_pfn + pgdat->node_spanned_pages;
-	unsigned long pfn;
-
-	for (pfn = start_pfn; pfn < end_pfn; pfn += PAGES_PER_SECTION) {
-		unsigned long section_nr = pfn_to_section_nr(pfn);
-
-		if (!present_section_nr(section_nr))
-			continue;
+	int rc;
 
-		if (pfn_to_nid(pfn) != nid)
-			continue;
+	/*
+	 * If the node still spans pages (especially ZONE_DEVICE), don't
+	 * offline it. A node spans memory after move_pfn_range_to_zone(),
+	 * e.g., after the memory block was onlined.
+	 */
+	if (pgdat->node_spanned_pages)
+		return;
 
-		/*
-		 * some memory sections of this node are not removed, and we
-		 * can't offline node now.
-		 */
+	/*
+	 * Especially offline memory blocks might not be spanned by the
+	 * node. They will get spanned by the node once they get onlined.
+	 * However, they link to the node in sysfs and can get onlined later.
+	 */
+	rc = for_each_memory_block(&nid, check_no_memblock_for_node_cb);
+	if (rc)
 		return;
-	}
 
 	if (check_cpu_on_node(pgdat))
 		return;