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 <kamezawa.hiroyu@xxxxxxxxxxxxxx> The idea is from Wen Congyang <wency@xxxxxxxxxxxxxx> 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@xxxxxxxxxxxxxx> Reviewed-by: Wen Congyang <wency@xxxxxxxxxxxxxx> --- mm/memory_hotplug.c | 20 ++++++++++++-------- 1 files changed, 12 insertions(+), 8 deletions(-) diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 8b67752..8aa2b56 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1015,11 +1015,14 @@ 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 */ @@ -1072,7 +1075,7 @@ 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; @@ -1083,12 +1086,13 @@ 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 */ @@ -1100,7 +1104,7 @@ 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 -- 1.7.1 -- To unsubscribe from this list: send the line "unsubscribe linux-acpi" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html