memcg: memory hotplug fix for notifier callback

Fixes for memcg/memory hotplug.

While memory hotplug allocate/free memmap, page_cgroup doesn't free
page_cgroup at OFFLINE when page_cgroup is allocated via bootomem.
(Because freeing bootmem requires special care.)

Then, if page_cgroup is allocated by bootmem and memmap is freed/allocated
by memory hotplug, page_cgroup->page == page is no longer true.

But current MEM_ONLINE handler doesn't check it and update
page_cgroup->page if it's not necessary to allocate page_cgroup.  (This
was not found because memmap is not freed if SPARSEMEM_VMEMMAP is y.)

And I noticed that MEM_ONLINE can be called against "part of section".
So, freeing page_cgroup at CANCEL_ONLINE will cause trouble.  (freeing
used page_cgroup) Don't rollback at CANCEL.

One more, current memory hotplug notifier is stopped by slub because it
sets NOTIFY_STOP_MASK to return vaule.  So, page_cgroup's callback never
be called.  (low priority than slub now.)

I think this slub's behavior is not intentional(BUG). and fixes it.

Another way to be considered about page_cgroup allocation:
  - free page_cgroup at OFFLINE even if it's from bootmem
    and remove specieal handler. But it requires more changes.

Addresses http://bugzilla.kernel.org/show_bug.cgi?id=12041

Signed-off-by: KAMEZAWA Hiruyoki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: Balbir Singh <balbir@in.ibm.com>
Cc: Pavel Emelyanov <xemul@openvz.org>
Tested-by: Badari Pulavarty <pbadari@us.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

mm/page_cgroup.c

@@ -107,19 +107,29 @@ int __init_refok init_section_page_cgroup(unsigned long pfn)
 
 	section = __pfn_to_section(pfn);
 
-	if (section->page_cgroup)
-		return 0;
-
-	nid = page_to_nid(pfn_to_page(pfn));
-
-	table_size = sizeof(struct page_cgroup) * PAGES_PER_SECTION;
-	if (slab_is_available()) {
-		base = kmalloc_node(table_size, GFP_KERNEL, nid);
-		if (!base)
-			base = vmalloc_node(table_size, nid);
-	} else {
-		base = __alloc_bootmem_node_nopanic(NODE_DATA(nid), table_size,
+	if (!section->page_cgroup) {
+		nid = page_to_nid(pfn_to_page(pfn));
+		table_size = sizeof(struct page_cgroup) * PAGES_PER_SECTION;
+		if (slab_is_available()) {
+			base = kmalloc_node(table_size, GFP_KERNEL, nid);
+			if (!base)
+				base = vmalloc_node(table_size, nid);
+		} else {
+			base = __alloc_bootmem_node_nopanic(NODE_DATA(nid),
+				table_size,
 				PAGE_SIZE, __pa(MAX_DMA_ADDRESS));
+		}
+	} else {
+		/*
+ 		 * We don't have to allocate page_cgroup again, but
+		 * address of memmap may be changed. So, we have to initialize
+		 * again.
+		 */
+		base = section->page_cgroup + pfn;
+		table_size = 0;
+		/* check address of memmap is changed or not. */
+		if (base->page == pfn_to_page(pfn))
+			return 0;
 	}
 
 	if (!base) {
@@ -208,18 +218,23 @@ static int __meminit page_cgroup_callback(struct notifier_block *self,
 		ret = online_page_cgroup(mn->start_pfn,
 				   mn->nr_pages, mn->status_change_nid);
 		break;
-	case MEM_CANCEL_ONLINE:
 	case MEM_OFFLINE:
 		offline_page_cgroup(mn->start_pfn,
 				mn->nr_pages, mn->status_change_nid);
 		break;
+	case MEM_CANCEL_ONLINE:
 	case MEM_GOING_OFFLINE:
 		break;
 	case MEM_ONLINE:
 	case MEM_CANCEL_OFFLINE:
 		break;
 	}
-	ret = notifier_from_errno(ret);
+
+	if (ret)
+		ret = notifier_from_errno(ret);
+	else
+		ret = NOTIFY_OK;
+
 	return ret;
 }
 

mm/slub.c

@@ -2931,8 +2931,10 @@ static int slab_memory_callback(struct notifier_block *self,
 	case MEM_CANCEL_OFFLINE:
 		break;
 	}
-
-	ret = notifier_from_errno(ret);
+	if (ret)
+		ret = notifier_from_errno(ret);
+	else
+		ret = NOTIFY_OK;
 	return ret;
 }