[PATCH] pgdat allocation for new node add (export kswapd start func)

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

[akpm@osdl.org: daemonize() isn't needed when using the kthread API]
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>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

2 files changed, 28 insertions, 11 deletions

diff --git a/include/linux/swap.h b/include/linux/swap.h
index dc3f3aa0c83e..c41e2d6d1acc 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -199,6 +199,8 @@ static inline int zone_reclaim(struct zone *z, gfp_t mask, unsigned int order)
 }
 #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 --git a/mm/vmscan.c b/mm/vmscan.c
index 72babac71dea..f03da33d9147 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -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>
@@ -1223,7 +1224,6 @@ static int kswapd(void *p)
         };
         cpumask_t cpumask;
 
-        daemonize("kswapd%d", pgdat->node_id);
         cpumask = node_to_cpumask(pgdat->node_id);
         if (!cpus_empty(cpumask))
                 set_cpus_allowed(tsk, cpumask);
@@ -1468,20 +1468,35 @@ static int cpu_callback(struct notifier_block *nfb,
 }
 #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 (IS_ERR(pgdat->kswapd)) {
+                /* failure at boot is fatal */
+                BUG_ON(system_state == SYSTEM_BOOTING);
+                printk("Failed to start 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;
-
-                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);
-        }
+        for_each_online_node(nid)
+                kswapd_run(nid);
         hotcpu_notifier(cpu_callback, 0);
         return 0;
 }