memory_hotplug: ensure every online node has NORMAL memory

Old memory hotplug code and new online/movable may cause a online node
don't have any normal memory, but memory-management acts bad when we have
nodes which is online but don't have any normal memory.  Example: it may
cause a bound task fail on all kernel allocation and cause the task can't
create task or create other kernel object.

So we disable non-normal-memory-node here, we will enable it when we
prepared.

Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Signed-off-by: Wen Congyang <wency@cn.fujitsu.com>
Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Cc: Lai Jiangshan <laijs@cn.fujitsu.com>
Cc: Jiang Liu <jiang.liu@huawei.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Minchan Kim <minchan.kim@gmail.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: David Rientjes <rientjes@google.com>
Cc: Yinghai Lu <yinghai@kernel.org>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Greg KH <greg@kroah.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index c370491bdb9748f40762d1f3941ff0e0af745504..de9cb14ae753ee2cfe7854201aa1bfb3d2e1f480 100644 (file)
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -581,6 +581,12 @@ static int online_pages_range(unsigned long start_pfn, unsigned long nr_pages,
        return 0;
 }
 
+/* ensure every online node has NORMAL memory */
+static bool can_online_high_movable(struct zone *zone)
+{
+       return node_state(zone_to_nid(zone), N_NORMAL_MEMORY);
+}
+
 /* check which state of node_states will be changed when online memory */
 static void node_states_check_changes_online(unsigned long nr_pages,
        struct zone *zone, struct memory_notify *arg)
@@ -646,6 +652,12 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_typ
         */
        zone = page_zone(pfn_to_page(pfn));
 
+       if ((zone_idx(zone) > ZONE_NORMAL || online_type == ONLINE_MOVABLE) &&
+           !can_online_high_movable(zone)) {
+               unlock_memory_hotplug();
+               return -1;
+       }
+
        if (online_type == ONLINE_KERNEL && zone_idx(zone) == ZONE_MOVABLE) {
                if (move_pfn_range_left(zone - 1, zone, pfn, pfn + nr_pages)) {
                        unlock_memory_hotplug();
@@ -1054,6 +1066,30 @@ check_pages_isolated(unsigned long start_pfn, unsigned long end_pfn)
        return offlined;
 }
 
+/* ensure the node has NORMAL memory if it is still online */
+static bool can_offline_normal(struct zone *zone, unsigned long nr_pages)
+{
+       struct pglist_data *pgdat = zone->zone_pgdat;
+       unsigned long present_pages = 0;
+       enum zone_type zt;
+
+       for (zt = 0; zt <= ZONE_NORMAL; zt++)
+               present_pages += pgdat->node_zones[zt].present_pages;
+
+       if (present_pages > nr_pages)
+               return true;
+
+       present_pages = 0;
+       for (; zt <= ZONE_MOVABLE; zt++)
+               present_pages += pgdat->node_zones[zt].present_pages;
+
+       /*
+        * we can't offline the last normal memory until all
+        * higher memory is offlined.
+        */
+       return present_pages == 0;
+}
+
 /* check which state of node_states will be changed when offline memory */
 static void node_states_check_changes_offline(unsigned long nr_pages,
                struct zone *zone, struct memory_notify *arg)
@@ -1141,6 +1177,10 @@ static int __ref __offline_pages(unsigned long start_pfn,
        node = zone_to_nid(zone);
        nr_pages = end_pfn - start_pfn;
 
+       ret = -EINVAL;
+       if (zone_idx(zone) <= ZONE_NORMAL && !can_offline_normal(zone, nr_pages))
+               goto out;
+
        /* set above range as isolated */
        ret = start_isolate_page_range(start_pfn, end_pfn,
                                       MIGRATE_MOVABLE, true);