From: Yasunori Goto <y-goto@jp.fujitsu.com>

When node is hot-added, kswapd for the node should start.  This export kswapd
start function as kswapd_run() to use at add_memory().

Signed-off-by: Yasunori Goto <y-goto@jp.fujitsu.com>
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Dave Hansen <haveblue@us.ibm.com>
Cc: "Brown, Len" <len.brown@intel.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
---

 include/linux/swap.h |    2 ++
 mm/vmscan.c          |   35 ++++++++++++++++++++++++++---------
 2 files changed, 28 insertions(+), 9 deletions(-)

diff -puN include/linux/swap.h~pgdat-allocation-for-new-node-add-export-kswapd-start-func include/linux/swap.h
--- devel/include/linux/swap.h~pgdat-allocation-for-new-node-add-export-kswapd-start-func	2006-05-11 15:18:43.000000000 -0700
+++ devel-akpm/include/linux/swap.h	2006-05-11 15:18:43.000000000 -0700
@@ -205,6 +205,8 @@ static inline int zone_reclaim(struct zo
 }
 #endif
 
+extern int kswapd_run(int nid);
+
 #ifdef CONFIG_MMU
 /* linux/mm/shmem.c */
 extern int shmem_unuse(swp_entry_t entry, struct page *page);
diff -puN mm/vmscan.c~pgdat-allocation-for-new-node-add-export-kswapd-start-func mm/vmscan.c
--- devel/mm/vmscan.c~pgdat-allocation-for-new-node-add-export-kswapd-start-func	2006-05-11 15:18:43.000000000 -0700
+++ devel-akpm/mm/vmscan.c	2006-05-11 15:18:43.000000000 -0700
@@ -34,6 +34,7 @@
 #include <linux/notifier.h>
 #include <linux/rwsem.h>
 #include <linux/delay.h>
+#include <linux/kthread.h>
 
 #include <asm/tlbflush.h>
 #include <asm/div64.h>
@@ -1454,20 +1455,36 @@ static int cpu_callback(struct notifier_
 }
 #endif /* CONFIG_HOTPLUG_CPU */
 
+/*
+ * This kswapd start function will be called by init and node-hot-add.
+ * On node-hot-add, kswapd will moved to proper cpus if cpus are hot-added.
+ */
+int kswapd_run(int nid)
+{
+	pg_data_t *pgdat = NODE_DATA(nid);
+	int ret = 0;
+
+	if (pgdat->kswapd)
+		return 0;
+
+	pgdat->kswapd = kthread_run(kswapd, pgdat, "kswapd%d", nid);
+	if (pgdat->kswapd == ERR_PTR(-ENOMEM)) {
+		/* failure at boot is fatal */
+		BUG_ON(system_state == SYSTEM_BOOTING);
+		printk("faled to run kswapd on node %d\n",nid);
+		ret = -1;
+	}
+	return ret;
+}
+
 static int __init kswapd_init(void)
 {
-	pg_data_t *pgdat;
+	int nid;
 
 	swap_setup();
-	for_each_online_pgdat(pgdat) {
-		pid_t pid;
+	for_each_online_node(nid)
+ 		kswapd_run(nid);
 
-		pid = kernel_thread(kswapd, pgdat, CLONE_KERNEL);
-		BUG_ON(pid < 0);
-		read_lock(&tasklist_lock);
-		pgdat->kswapd = find_task_by_pid(pid);
-		read_unlock(&tasklist_lock);
-	}
 	total_memory = nr_free_pagecache_pages();
 	hotcpu_notifier(cpu_callback, 0);
 	return 0;
_