1 files changed, 40 insertions, 74 deletions

diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 8dccc317aac2..73bf17df6899 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -773,31 +773,6 @@ static void node_states_set_node(int node, struct memory_notify *arg)
 	node_set_state(node, N_MEMORY);
 }
 
-bool allow_online_pfn_range(int nid, unsigned long pfn, unsigned long nr_pages, int online_type)
-{
-	struct pglist_data *pgdat = NODE_DATA(nid);
-	struct zone *movable_zone = &pgdat->node_zones[ZONE_MOVABLE];
-	struct zone *default_zone = default_zone_for_pfn(nid, pfn, nr_pages);
-
-	/*
-	 * TODO there shouldn't be any inherent reason to have ZONE_NORMAL
-	 * physically before ZONE_MOVABLE. All we need is they do not
-	 * overlap. Historically we didn't allow ZONE_NORMAL after ZONE_MOVABLE
-	 * though so let's stick with it for simplicity for now.
-	 * TODO make sure we do not overlap with ZONE_DEVICE
-	 */
-	if (online_type == MMOP_ONLINE_KERNEL) {
-		if (zone_is_empty(movable_zone))
-			return true;
-		return movable_zone->zone_start_pfn >= pfn + nr_pages;
-	} else if (online_type == MMOP_ONLINE_MOVABLE) {
-		return zone_end_pfn(default_zone) <= pfn;
-	}
-
-	/* MMOP_ONLINE_KEEP will always succeed and inherits the current zone */
-	return online_type == MMOP_ONLINE_KEEP;
-}
-
 static void __meminit resize_zone_range(struct zone *zone, unsigned long start_pfn,
 		unsigned long nr_pages)
 {
@@ -856,7 +831,7 @@ void __ref move_pfn_range_to_zone(struct zone *zone,
  * If no kernel zone covers this pfn range it will automatically go
  * to the ZONE_NORMAL.
  */
-struct zone *default_zone_for_pfn(int nid, unsigned long start_pfn,
+static struct zone *default_kernel_zone_for_pfn(int nid, unsigned long start_pfn,
 		unsigned long nr_pages)
 {
 	struct pglist_data *pgdat = NODE_DATA(nid);
@@ -872,17 +847,40 @@ struct zone *default_zone_for_pfn(int nid, unsigned long start_pfn,
 	return &pgdat->node_zones[ZONE_NORMAL];
 }
 
-static inline bool movable_pfn_range(int nid, struct zone *default_zone,
-		unsigned long start_pfn, unsigned long nr_pages)
+static inline struct zone *default_zone_for_pfn(int nid, unsigned long start_pfn,
+		unsigned long nr_pages)
 {
-	if (!allow_online_pfn_range(nid, start_pfn, nr_pages,
-				MMOP_ONLINE_KERNEL))
-		return true;
+	struct zone *kernel_zone = default_kernel_zone_for_pfn(nid, start_pfn,
+			nr_pages);
+	struct zone *movable_zone = &NODE_DATA(nid)->node_zones[ZONE_MOVABLE];
+	bool in_kernel = zone_intersects(kernel_zone, start_pfn, nr_pages);
+	bool in_movable = zone_intersects(movable_zone, start_pfn, nr_pages);
 
-	if (!movable_node_is_enabled())
-		return false;
+	/*
+	 * We inherit the existing zone in a simple case where zones do not
+	 * overlap in the given range
+	 */
+	if (in_kernel ^ in_movable)
+		return (in_kernel) ? kernel_zone : movable_zone;
 
-	return !zone_intersects(default_zone, start_pfn, nr_pages);
+	/*
+	 * If the range doesn't belong to any zone or two zones overlap in the
+	 * given range then we use movable zone only if movable_node is
+	 * enabled because we always online to a kernel zone by default.
+	 */
+	return movable_node_enabled ? movable_zone : kernel_zone;
+}
+
+struct zone * zone_for_pfn_range(int online_type, int nid, unsigned start_pfn,
+		unsigned long nr_pages)
+{
+	if (online_type == MMOP_ONLINE_KERNEL)
+		return default_kernel_zone_for_pfn(nid, start_pfn, nr_pages);
+
+	if (online_type == MMOP_ONLINE_MOVABLE)
+		return &NODE_DATA(nid)->node_zones[ZONE_MOVABLE];
+
+	return default_zone_for_pfn(nid, start_pfn, nr_pages);
 }
 
 /*
@@ -892,28 +890,14 @@ static inline bool movable_pfn_range(int nid, struct zone *default_zone,
 static struct zone * __meminit move_pfn_range(int online_type, int nid,
 		unsigned long start_pfn, unsigned long nr_pages)
 {
-	struct pglist_data *pgdat = NODE_DATA(nid);
-	struct zone *zone = default_zone_for_pfn(nid, start_pfn, nr_pages);
-
-	if (online_type == MMOP_ONLINE_KEEP) {
-		struct zone *movable_zone = &pgdat->node_zones[ZONE_MOVABLE];
-		/*
-		 * MMOP_ONLINE_KEEP defaults to MMOP_ONLINE_KERNEL but use
-		 * movable zone if that is not possible (e.g. we are within
-		 * or past the existing movable zone). movable_node overrides
-		 * this default and defaults to movable zone
-		 */
-		if (movable_pfn_range(nid, zone, start_pfn, nr_pages))
-			zone = movable_zone;
-	} else if (online_type == MMOP_ONLINE_MOVABLE) {
-		zone = &pgdat->node_zones[ZONE_MOVABLE];
-	}
+	struct zone *zone;
 
+	zone = zone_for_pfn_range(online_type, nid, start_pfn, nr_pages);
 	move_pfn_range_to_zone(zone, start_pfn, nr_pages);
 	return zone;
 }
 
-/* Must be protected by mem_hotplug_begin() */
+/* Must be protected by mem_hotplug_begin() or a device_lock */
 int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_type)
 {
 	unsigned long flags;
@@ -925,9 +909,6 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_typ
 	struct memory_notify arg;
 
 	nid = pfn_to_nid(pfn);
-	if (!allow_online_pfn_range(nid, pfn, nr_pages, online_type))
-		return -EINVAL;
-
 	/* associate pfn range with the zone */
 	zone = move_pfn_range(online_type, nid, pfn, nr_pages);
 
@@ -945,10 +926,9 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_typ
 	 * This means the page allocator ignores this zone.
 	 * So, zonelist must be updated after online.
 	 */
-	mutex_lock(&zonelists_mutex);
 	if (!populated_zone(zone)) {
 		need_zonelists_rebuild = 1;
-		build_all_zonelists(NULL, zone);
+		setup_zone_pageset(zone);
 	}
 
 	ret = walk_system_ram_range(pfn, nr_pages, &onlined_pages,
@@ -956,7 +936,6 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_typ
 	if (ret) {
 		if (need_zonelists_rebuild)
 			zone_pcp_reset(zone);
-		mutex_unlock(&zonelists_mutex);
 		goto failed_addition;
 	}
 
@@ -969,13 +948,11 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_typ
 	if (onlined_pages) {
 		node_states_set_node(nid, &arg);
 		if (need_zonelists_rebuild)
-			build_all_zonelists(NULL, NULL);
+			build_all_zonelists(NULL);
 		else
 			zone_pcp_update(zone);
 	}
 
-	mutex_unlock(&zonelists_mutex);
-
 	init_per_zone_wmark_min();
 
 	if (onlined_pages) {
@@ -1046,9 +1023,7 @@ static pg_data_t __ref *hotadd_new_pgdat(int nid, u64 start)
 	 * The node we allocated has no zone fallback lists. For avoiding
 	 * to access not-initialized zonelist, build here.
 	 */
-	mutex_lock(&zonelists_mutex);
-	build_all_zonelists(pgdat, NULL);
-	mutex_unlock(&zonelists_mutex);
+	build_all_zonelists(pgdat);
 
 	/*
 	 * zone->managed_pages is set to an approximate value in
@@ -1100,13 +1075,6 @@ int try_online_node(int nid)
 	node_set_online(nid);
 	ret = register_one_node(nid);
 	BUG_ON(ret);
-
-	if (pgdat->node_zonelists->_zonerefs->zone == NULL) {
-		mutex_lock(&zonelists_mutex);
-		build_all_zonelists(NULL, NULL);
-		mutex_unlock(&zonelists_mutex);
-	}
-
 out:
 	mem_hotplug_done();
 	return ret;
@@ -1722,9 +1690,7 @@ repeat:
 
 	if (!populated_zone(zone)) {
 		zone_pcp_reset(zone);
-		mutex_lock(&zonelists_mutex);
-		build_all_zonelists(NULL, NULL);
-		mutex_unlock(&zonelists_mutex);
+		build_all_zonelists(NULL);
 	} else
 		zone_pcp_update(zone);
 
@@ -1750,7 +1716,7 @@ failed_removal:
 	return ret;
 }
 
-/* Must be protected by mem_hotplug_begin() */
+/* Must be protected by mem_hotplug_begin() or a device_lock */
 int offline_pages(unsigned long start_pfn, unsigned long nr_pages)
 {
 	return __offline_pages(start_pfn, start_pfn + nr_pages, 120 * HZ);