memory-hotplug: do not allocate pgdat if it was not freed when offline.

Since there is no way to guarentee the address of pgdat/zone is not on
stack of any kernel threads or used by other kernel objects without
reference counting or other symchronizing method, we cannot reset
node_data and free pgdat when offlining a node.  Just reset pgdat to 0 and
reuse the memory when the node is online again.

The problem is suggested by Kamezawa Hiroyuki.  The idea is from Wen
Congyang.

NOTE: If we don't reset pgdat to 0, the WARN_ON in free_area_init_node()
      will be triggered.

Signed-off-by: Tang Chen <tangchen@cn.fujitsu.com>
Reviewed-by: Wen Congyang <wency@cn.fujitsu.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Jiang Liu <jiang.liu@huawei.com>
Cc: Jianguo Wu <wujianguo@huawei.com>
Cc: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Lai Jiangshan <laijs@cn.fujitsu.com>
Cc: Wu Jianguo <wujianguo@huawei.com>
Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index bb692a15e9a58de702fd7d1b78a6bb9ef9614b56..2bc92267fca733eac1628e8dbbacb4baac11293e 100644 (file)
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1017,11 +1017,14 @@ static pg_data_t __ref *hotadd_new_pgdat(int nid, u64 start)
        unsigned long zholes_size[MAX_NR_ZONES] = {0};
        unsigned long start_pfn = start >> PAGE_SHIFT;
 
-       pgdat = arch_alloc_nodedata(nid);
-       if (!pgdat)
-               return NULL;
+       pgdat = NODE_DATA(nid);
+       if (!pgdat) {
+               pgdat = arch_alloc_nodedata(nid);
+               if (!pgdat)
+                       return NULL;
 
-       arch_refresh_nodedata(nid, pgdat);
+               arch_refresh_nodedata(nid, pgdat);
+       }
 
        /* we can use NODE_DATA(nid) from here */
 
@@ -1074,7 +1077,7 @@ out:
 int __ref add_memory(int nid, u64 start, u64 size)
 {
        pg_data_t *pgdat = NULL;
-       int new_pgdat = 0;
+       int new_pgdat = 0, new_node = 0;
        struct resource *res;
        int ret;
 
@@ -1085,12 +1088,13 @@ int __ref add_memory(int nid, u64 start, u64 size)
        if (!res)
                goto out;
 
-       if (!node_online(nid)) {
+       new_pgdat = NODE_DATA(nid) ? 0 : 1;
+       new_node = node_online(nid) ? 0 : 1;
+       if (new_node) {
                pgdat = hotadd_new_pgdat(nid, start);
                ret = -ENOMEM;
                if (!pgdat)
                        goto error;
-               new_pgdat = 1;
        }
 
        /* call arch's memory hotadd */
@@ -1102,7 +1106,7 @@ int __ref add_memory(int nid, u64 start, u64 size)
        /* we online node here. we can't roll back from here. */
        node_set_online(nid);
 
-       if (new_pgdat) {
+       if (new_node) {
                ret = register_one_node(nid);
                /*
                 * If sysfs file of new node can't create, cpu on the node