[PATCH] wait_table and zonelist initializing for memory hotadd: update zonelists

In current code, zonelist is considered to be build once, no modification.
But MemoryHotplug can add new zone/pgdat.  It must be updated.

This patch modifies build_all_zonelists().  By this, build_all_zonelist() can
reconfig pgdat's zonelists.

To update them safety, this patch use stop_machine_run().  Other cpus don't
touch among updating them by using it.

In old version (V2 of node hotadd), kernel updated them after zone
initialization.  But present_page of its new zone is still 0, because
online_page() is not called yet at this time.  Build_zonelists() checks
present_pages to find present zone.  It was too early.  So, I changed it after
online_pages().

Signed-off-by: Yasunori Goto     <y-goto@jp.fujitsu.com>
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

2 files changed, 33 insertions, 5 deletions

diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 71da5c98c9c1..1b1ac3db2187 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -127,6 +127,7 @@ int online_pages(unsigned long pfn, unsigned long nr_pages)
         unsigned long flags;
         unsigned long onlined_pages = 0;
         struct zone *zone;
+        int need_zonelists_rebuild = 0;
 
         /*
          * This doesn't need a lock to do pfn_to_page().
@@ -139,6 +140,14 @@ int online_pages(unsigned long pfn, unsigned long nr_pages)
         grow_pgdat_span(zone->zone_pgdat, pfn, pfn + nr_pages);
         pgdat_resize_unlock(zone->zone_pgdat, &flags);
 
+        /*
+         * If this zone is not populated, then it is not in zonelist.
+         * This means the page allocator ignores this zone.
+         * So, zonelist must be updated after online.
+         */
+        if (!populated_zone(zone))
+                need_zonelists_rebuild = 1;
+
         for (i = 0; i < nr_pages; i++) {
                 struct page *page = pfn_to_page(pfn + i);
                 online_page(page);
@@ -149,5 +158,8 @@ int online_pages(unsigned long pfn, unsigned long nr_pages)
 
         setup_per_zone_pages_min();
 
+        if (need_zonelists_rebuild)
+                build_all_zonelists();
+
         return 0;
 }
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 62564e27b448..9dfbe6b7d1c8 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -37,6 +37,7 @@
 #include <linux/nodemask.h>
 #include <linux/vmalloc.h>
 #include <linux/mempolicy.h>
+#include <linux/stop_machine.h>
 
 #include <asm/tlbflush.h>
 #include <asm/div64.h>
@@ -1704,14 +1705,29 @@ static void __meminit build_zonelists(pg_data_t *pgdat)
 
 #endif  /* CONFIG_NUMA */
 
-void __init build_all_zonelists(void)
+/* return values int ....just for stop_machine_run() */
+static int __meminit __build_all_zonelists(void *dummy)
 {
-        int i;
+        int nid;
+        for_each_online_node(nid)
+                build_zonelists(NODE_DATA(nid));
+        return 0;
+}
+
+void __meminit build_all_zonelists(void)
+{
+        if (system_state == SYSTEM_BOOTING) {
+                __build_all_zonelists(0);
+                cpuset_init_current_mems_allowed();
+        } else {
+                /* we have to stop all cpus to guaranntee there is no user
+                   of zonelist */
+                stop_machine_run(__build_all_zonelists, NULL, NR_CPUS);
+                /* cpuset refresh routine should be here */
+        }
 
-        for_each_online_node(i)
-                build_zonelists(NODE_DATA(i));
         printk("Built %i zonelists\n", num_online_nodes());
-        cpuset_init_current_mems_allowed();
+
 }
 
 /*