1 files changed, 60 insertions, 73 deletions

diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index b1be791f772d..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)
@@ -436,67 +436,33 @@ static void shrink_zone_span(struct zone *zone, unsigned long start_pfn,
 	zone_span_writeunlock(zone);
 }
 
-static void shrink_pgdat_span(struct pglist_data *pgdat,
-			      unsigned long start_pfn, unsigned long end_pfn)
+static void update_pgdat_span(struct pglist_data *pgdat)
 {
-	unsigned long pgdat_start_pfn = pgdat->node_start_pfn;
-	unsigned long p = pgdat_end_pfn(pgdat); /* pgdat_end_pfn namespace clash */
-	unsigned long pgdat_end_pfn = p;
-	unsigned long pfn;
-	int nid = pgdat->node_id;
-
-	if (pgdat_start_pfn == start_pfn) {
-		/*
-		 * If the section is smallest section in the pgdat, it need
-		 * shrink pgdat->node_start_pfn and pgdat->node_spanned_pages.
-		 * In this case, we find second smallest valid mem_section
-		 * for shrinking zone.
-		 */
-		pfn = find_smallest_section_pfn(nid, NULL, end_pfn,
-						pgdat_end_pfn);
-		if (pfn) {
-			pgdat->node_start_pfn = pfn;
-			pgdat->node_spanned_pages = pgdat_end_pfn - pfn;
-		}
-	} else if (pgdat_end_pfn == end_pfn) {
-		/*
-		 * If the section is biggest section in the pgdat, it need
-		 * shrink pgdat->node_spanned_pages.
-		 * In this case, we find second biggest valid mem_section for
-		 * shrinking zone.
-		 */
-		pfn = find_biggest_section_pfn(nid, NULL, pgdat_start_pfn,
-					       start_pfn);
-		if (pfn)
-			pgdat->node_spanned_pages = pfn - pgdat_start_pfn + 1;
-	}
+	unsigned long node_start_pfn = 0, node_end_pfn = 0;
+	struct zone *zone;
 
-	/*
-	 * If the section is not biggest or smallest mem_section in the pgdat,
-	 * it only creates a hole in the pgdat. So in this case, we need not
-	 * change the pgdat.
-	 * But perhaps, the pgdat has only hole data. Thus it check the pgdat
-	 * has only hole or not.
-	 */
-	pfn = pgdat_start_pfn;
-	for (; pfn < pgdat_end_pfn; pfn += PAGES_PER_SUBSECTION) {
-		if (unlikely(!pfn_valid(pfn)))
-			continue;
+	for (zone = pgdat->node_zones;
+	     zone < pgdat->node_zones + MAX_NR_ZONES; zone++) {
+		unsigned long zone_end_pfn = zone->zone_start_pfn +
+					     zone->spanned_pages;
 
-		if (pfn_to_nid(pfn) != nid)
+		/* No need to lock the zones, they can't change. */
+		if (!zone->spanned_pages)
 			continue;
-
-		/* Skip range to be removed */
-		if (pfn >= start_pfn && pfn < end_pfn)
+		if (!node_end_pfn) {
+			node_start_pfn = zone->zone_start_pfn;
+			node_end_pfn = zone_end_pfn;
 			continue;
+		}
 
-		/* If we find valid section, we have nothing to do */
-		return;
+		if (zone_end_pfn > node_end_pfn)
+			node_end_pfn = zone_end_pfn;
+		if (zone->zone_start_pfn < node_start_pfn)
+			node_start_pfn = zone->zone_start_pfn;
 	}
 
-	/* The pgdat has no valid section */
-	pgdat->node_start_pfn = 0;
-	pgdat->node_spanned_pages = 0;
+	pgdat->node_start_pfn = node_start_pfn;
+	pgdat->node_spanned_pages = node_end_pfn - node_start_pfn;
 }
 
 static void __remove_zone(struct zone *zone, unsigned long start_pfn,
@@ -505,9 +471,19 @@ 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);
-	shrink_pgdat_span(pgdat, start_pfn, start_pfn + nr_pages);
+	update_pgdat_span(pgdat);
 	pgdat_resize_unlock(zone->zone_pgdat, &flags);
 }
 
@@ -1680,6 +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
@@ -1692,25 +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;