[PATCH] node hotplug: register cpu: remove node struct

With Goto-san's patch, we can add new pgdat/node at runtime.  I'm now
considering node-hot-add with cpu + memory on ACPI.

I found acpi container, which describes node, could evaluate cpu before
memory. This means cpu-hot-add occurs before memory hot add.

In most part, cpu-hot-add doesn't depend on node hot add.  But register_cpu(),
which creates symbolic link from node to cpu, requires that node should be
onlined before register_cpu().  When a node is onlined, its pgdat should be
there.

This patch-set holds off creating symbolic link from node to cpu
until node is onlined.

This removes node arguments from register_cpu().

Now, register_cpu() requires 'struct node' as its argument.  But the array of
struct node is now unified in driver/base/node.c now (By Goto's node hotplug
patch).  We can get struct node in generic way.  So, this argument is not
necessary now.

This patch also guarantees add cpu under node only when node is onlined.  It
is necessary for node-hot-add vs.  cpu-hot-add patch following this.

Moreover, register_cpu calculates cpu->node_id by cpu_to_node() without regard
to its 'struct node *root' argument.  This patch removes it.

Also modify callers of register_cpu()/unregister_cpu, whose args are changed
by register-cpu-remove-node-struct patch.

[Brice.Goglin@ens-lyon.org: fix it]
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Yasunori Goto <y-goto@jp.fujitsu.com>
Cc: Ashok Raj <ashok.raj@intel.com>
Cc: Dave Hansen <haveblue@us.ibm.com>
Signed-off-by: Brice Goglin <Brice.Goglin@ens-lyon.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

18 files changed, 77 insertions, 69 deletions

diff --git a/arch/alpha/kernel/setup.c b/arch/alpha/kernel/setup.c
index 558b833..254c507 100644
--- a/arch/alpha/kernel/setup.c
+++ b/arch/alpha/kernel/setup.c
@@ -481,7 +481,7 @@ register_cpus(void)
 		struct cpu *p = kzalloc(sizeof(*p), GFP_KERNEL);
 		if (!p)
 			return -ENOMEM;
-		register_cpu(p, i, NULL);
+		register_cpu(p, i);
 	}
 	return 0;
 }
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index 9fc9af8..093ccba 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -808,7 +808,7 @@ static int __init topology_init(void)
 	int cpu;
 
 	for_each_possible_cpu(cpu)
-		register_cpu(&per_cpu(cpu_data, cpu).cpu, cpu, NULL);
+		register_cpu(&per_cpu(cpu_data, cpu).cpu, cpu);
 
 	return 0;
 }
diff --git a/arch/i386/kernel/topology.c b/arch/i386/kernel/topology.c
index 1eecc2e..e2e281d 100644
--- a/arch/i386/kernel/topology.c
+++ b/arch/i386/kernel/topology.c
@@ -32,15 +32,8 @@
 
 static struct i386_cpu cpu_devices[NR_CPUS];
 
-int arch_register_cpu(int num){
-	struct node *parent = NULL;
-
-#ifdef CONFIG_NUMA
-	int node = cpu_to_node(num);
-	if (node_online(node))
-		parent = &node_devices[parent_node(node)];
-#endif /* CONFIG_NUMA */
-
+int arch_register_cpu(int num)
+{
 	/*
 	 * CPU0 cannot be offlined due to several
 	 * restrictions and assumptions in kernel. This basically
@@ -50,21 +43,13 @@ int arch_register_cpu(int num){
 	if (!num)
 		cpu_devices[num].cpu.no_control = 1;
 
-	return register_cpu(&cpu_devices[num].cpu, num, parent);
+	return register_cpu(&cpu_devices[num].cpu, num);
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
 
 void arch_unregister_cpu(int num) {
-	struct node *parent = NULL;
-
-#ifdef CONFIG_NUMA
-	int node = cpu_to_node(num);
-	if (node_online(node))
-		parent = &node_devices[parent_node(node)];
-#endif /* CONFIG_NUMA */
-
-	return unregister_cpu(&cpu_devices[num].cpu, parent);
+	return unregister_cpu(&cpu_devices[num].cpu);
 }
 EXPORT_SYMBOL(arch_register_cpu);
 EXPORT_SYMBOL(arch_unregister_cpu);
diff --git a/arch/ia64/kernel/topology.c b/arch/ia64/kernel/topology.c
index 42cb05b..5737c9a 100644
--- a/arch/ia64/kernel/topology.c
+++ b/arch/ia64/kernel/topology.c
@@ -30,12 +30,6 @@ static struct ia64_cpu *sysfs_cpus;
 
 int arch_register_cpu(int num)
 {
-	struct node *parent = NULL;
-	
-#ifdef CONFIG_NUMA
-	parent = &node_devices[cpu_to_node(num)];
-#endif /* CONFIG_NUMA */
-
 #if defined (CONFIG_ACPI) && defined (CONFIG_HOTPLUG_CPU)
 	/*
 	 * If CPEI cannot be re-targetted, and this is
@@ -45,21 +39,14 @@ int arch_register_cpu(int num)
 		sysfs_cpus[num].cpu.no_control = 1;
 #endif
 
-	return register_cpu(&sysfs_cpus[num].cpu, num, parent);
+	return register_cpu(&sysfs_cpus[num].cpu, num);
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
 
 void arch_unregister_cpu(int num)
 {
-	struct node *parent = NULL;
-
-#ifdef CONFIG_NUMA
-	int node = cpu_to_node(num);
-	parent = &node_devices[node];
-#endif /* CONFIG_NUMA */
-
-	return unregister_cpu(&sysfs_cpus[num].cpu, parent);
+	return unregister_cpu(&sysfs_cpus[num].cpu);
 }
 EXPORT_SYMBOL(arch_register_cpu);
 EXPORT_SYMBOL(arch_unregister_cpu);
diff --git a/arch/m32r/kernel/setup.c b/arch/m32r/kernel/setup.c
index 3cd3c29..1ff483c 100644
--- a/arch/m32r/kernel/setup.c
+++ b/arch/m32r/kernel/setup.c
@@ -275,7 +275,7 @@ static int __init topology_init(void)
 	int i;
 
 	for_each_present_cpu(i)
-		register_cpu(&cpu_devices[i], i, NULL);
+		register_cpu(&cpu_devices[i], i);
 
 	return 0;
 }
diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c
index 298f82f..9096a5e 100644
--- a/arch/mips/kernel/smp.c
+++ b/arch/mips/kernel/smp.c
@@ -446,7 +446,7 @@ static int __init topology_init(void)
 	int ret;
 
 	for_each_present_cpu(cpu) {
-		ret = register_cpu(&per_cpu(cpu_devices, cpu), cpu, NULL);
+		ret = register_cpu(&per_cpu(cpu_devices, cpu), cpu);
 		if (ret)
 			printk(KERN_WARNING "topology_init: register_cpu %d "
 			       "failed (%d)\n", cpu, ret);
diff --git a/arch/parisc/kernel/topology.c b/arch/parisc/kernel/topology.c
index 3ba0400..068b20d 100644
--- a/arch/parisc/kernel/topology.c
+++ b/arch/parisc/kernel/topology.c
@@ -26,11 +26,10 @@ static struct cpu cpu_devices[NR_CPUS] __read_mostly;
 
 static int __init topology_init(void)
 {
-	struct node *parent = NULL;
 	int num;
 
 	for_each_present_cpu(num) {
-		register_cpu(&cpu_devices[num], num, parent);
+		register_cpu(&cpu_devices[num], num);
 	}
 	return 0;
 }
diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c
index e5a4481..0932a62 100644
--- a/arch/powerpc/kernel/setup_32.c
+++ b/arch/powerpc/kernel/setup_32.c
@@ -215,7 +215,7 @@ int __init ppc_init(void)
 
 	/* register CPU devices */
 	for_each_possible_cpu(i)
-		register_cpu(&cpu_devices[i], i, NULL);
+		register_cpu(&cpu_devices[i], i);
 
 	/* call platform init */
 	if (ppc_md.init != NULL) {
diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c
index 338491d..412ad00 100644
--- a/arch/powerpc/kernel/sysfs.c
+++ b/arch/powerpc/kernel/sysfs.c
@@ -348,23 +348,13 @@ static SYSDEV_ATTR(physical_id, 0444, show_physical_id, NULL);
 static int __init topology_init(void)
 {
 	int cpu;
-	struct node *parent = NULL;
 
 	register_nodes();
-
 	register_cpu_notifier(&sysfs_cpu_nb);
 
 	for_each_possible_cpu(cpu) {
 		struct cpu *c = &per_cpu(cpu_devices, cpu);
 
-#ifdef CONFIG_NUMA
-		/* The node to which a cpu belongs can't be known
-		 * until the cpu is made present.
-		 */
-		parent = NULL;
-		if (cpu_present(cpu))
-			parent = &node_devices[cpu_to_node(cpu)];
-#endif
 		/*
 		 * For now, we just see if the system supports making
 		 * the RTAS calls for CPU hotplug.  But, there may be a
@@ -376,7 +366,7 @@ static int __init topology_init(void)
 			c->no_control = 1;
 
 		if (cpu_online(cpu) || (c->no_control == 0)) {
-			register_cpu(c, cpu, parent);
+			register_cpu(c, cpu);
 
 			sysdev_create_file(&c->sysdev, &attr_physical_id);
 		}
diff --git a/arch/ppc/kernel/setup.c b/arch/ppc/kernel/setup.c
index 1f79e84..4b4607d 100644
--- a/arch/ppc/kernel/setup.c
+++ b/arch/ppc/kernel/setup.c
@@ -475,7 +475,7 @@ int __init ppc_init(void)
 
 	/* register CPU devices */
 	for_each_possible_cpu(i)
-		register_cpu(&cpu_devices[i], i, NULL);
+		register_cpu(&cpu_devices[i], i);
 
 	/* call platform init */
 	if (ppc_md.init != NULL) {
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index 343120c..8e03219 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -869,7 +869,7 @@ static int __init topology_init(void)
 	int ret;
 
 	for_each_possible_cpu(cpu) {
-		ret = register_cpu(&per_cpu(cpu_devices, cpu), cpu, NULL);
+		ret = register_cpu(&per_cpu(cpu_devices, cpu), cpu);
 		if (ret)
 			printk(KERN_WARNING "topology_init: register_cpu %d "
 			       "failed (%d)\n", cpu, ret);
diff --git a/arch/sh/kernel/setup.c b/arch/sh/kernel/setup.c
index bb229ef..9af22116 100644
--- a/arch/sh/kernel/setup.c
+++ b/arch/sh/kernel/setup.c
@@ -402,7 +402,7 @@ static int __init topology_init(void)
 	int cpu_id;
 
 	for_each_possible_cpu(cpu_id)
-		register_cpu(&cpu[cpu_id], cpu_id, NULL);
+		register_cpu(&cpu[cpu_id], cpu_id);
 
 	return 0;
 }
diff --git a/arch/sh64/kernel/setup.c b/arch/sh64/kernel/setup.c
index d2711c9..da98d8d 100644
--- a/arch/sh64/kernel/setup.c
+++ b/arch/sh64/kernel/setup.c
@@ -309,7 +309,7 @@ static struct cpu cpu[1];
 
 static int __init topology_init(void)
 {
-	return register_cpu(cpu, 0, NULL);
+	return register_cpu(cpu, 0);
 }
 
 subsys_initcall(topology_init);
diff --git a/arch/sparc64/kernel/setup.c b/arch/sparc64/kernel/setup.c
index a6a7d81..116d963 100644
--- a/arch/sparc64/kernel/setup.c
+++ b/arch/sparc64/kernel/setup.c
@@ -537,7 +537,7 @@ static int __init topology_init(void)
 	for_each_possible_cpu(i) {
 		struct cpu *p = kzalloc(sizeof(*p), GFP_KERNEL);
 		if (p) {
-			register_cpu(p, i, NULL);
+			register_cpu(p, i);
 			err = 0;
 		}
 	}
diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c
index dd712b2..3972d8a 100644
--- a/drivers/base/cpu.c
+++ b/drivers/base/cpu.c
@@ -8,6 +8,7 @@
 #include <linux/cpu.h>
 #include <linux/topology.h>
 #include <linux/device.h>
+#include <linux/node.h>
 
 #include "base.h"
 
@@ -57,13 +58,12 @@ static void __devinit register_cpu_control(struct cpu *cpu)
 {
 	sysdev_create_file(&cpu->sysdev, &attr_online);
 }
-void unregister_cpu(struct cpu *cpu, struct node *root)
+void unregister_cpu(struct cpu *cpu)
 {
 	int logical_cpu = cpu->sysdev.id;
 
-	if (root)
-		sysfs_remove_link(&root->sysdev.kobj,
-				  kobject_name(&cpu->sysdev.kobj));
+	unregister_cpu_under_node(logical_cpu, cpu_to_node(logical_cpu));
+
 	sysdev_remove_file(&cpu->sysdev, &attr_online);
 
 	sysdev_unregister(&cpu->sysdev);
@@ -109,23 +109,21 @@ static SYSDEV_ATTR(crash_notes, 0400, show_crash_notes, NULL);
  *
  * Initialize and register the CPU device.
  */
-int __devinit register_cpu(struct cpu *cpu, int num, struct node *root)
+int __devinit register_cpu(struct cpu *cpu, int num)
 {
 	int error;
-
 	cpu->node_id = cpu_to_node(num);
 	cpu->sysdev.id = num;
 	cpu->sysdev.cls = &cpu_sysdev_class;
 
 	error = sysdev_register(&cpu->sysdev);
-	if (!error && root)
-		error = sysfs_create_link(&root->sysdev.kobj,
-					  &cpu->sysdev.kobj,
-					  kobject_name(&cpu->sysdev.kobj));
+
 	if (!error && !cpu->no_control)
 		register_cpu_control(cpu);
 	if (!error)
 		cpu_sys_devices[num] = &cpu->sysdev;
+	if (!error)
+		register_cpu_under_node(num, cpu_to_node(num));
 
 #ifdef CONFIG_KEXEC
 	if (!error)
diff --git a/drivers/base/node.c b/drivers/base/node.c
index cbd0f62..eae2bdc 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -11,6 +11,7 @@
 #include <linux/cpumask.h>
 #include <linux/topology.h>
 #include <linux/nodemask.h>
+#include <linux/cpu.h>
 
 static struct sysdev_class node_class = {
 	set_kset_name("node"),
@@ -192,9 +193,38 @@ void unregister_node(struct node *node)
 
 struct node node_devices[MAX_NUMNODES];
 
+/*
+ * register cpu under node
+ */
+int register_cpu_under_node(unsigned int cpu, unsigned int nid)
+{
+	if (node_online(nid)) {
+		struct sys_device *obj = get_cpu_sysdev(cpu);
+		if (!obj)
+			return 0;
+		return sysfs_create_link(&node_devices[nid].sysdev.kobj,
+					 &obj->kobj,
+					 kobject_name(&obj->kobj));
+	 }
+
+	return 0;
+}
+
+int unregister_cpu_under_node(unsigned int cpu, unsigned int nid)
+{
+	if (node_online(nid)) {
+		struct sys_device *obj = get_cpu_sysdev(cpu);
+		if (obj)
+			sysfs_remove_link(&node_devices[nid].sysdev.kobj,
+					 kobject_name(&obj->kobj));
+	}
+	return 0;
+}
+
 int register_one_node(int nid)
 {
 	int error = 0;
+	int cpu;
 
 	if (node_online(nid)) {
 		int p_node = parent_node(nid);
@@ -204,6 +234,12 @@ int register_one_node(int nid)
 			parent = &node_devices[p_node];
 
 		error = register_node(&node_devices[nid], nid, parent);
+
+		/* link cpu under this node */
+		for_each_present_cpu(cpu) {
+			if (cpu_to_node(cpu) == nid)
+				register_cpu_under_node(cpu, nid);
+		}
 	}
 
 	return error;
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index 08d50c5..b23bf1c 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -31,10 +31,10 @@ struct cpu {
 	struct sys_device sysdev;
 };
 
-extern int register_cpu(struct cpu *, int, struct node *);
+extern int register_cpu(struct cpu *cpu, int num);
 extern struct sys_device *get_cpu_sysdev(unsigned cpu);
 #ifdef CONFIG_HOTPLUG_CPU
-extern void unregister_cpu(struct cpu *, struct node *);
+extern void unregister_cpu(struct cpu *cpu);
 #endif
 struct notifier_block;
 
diff --git a/include/linux/node.h b/include/linux/node.h
index 1e53475..81dcec8 100644
--- a/include/linux/node.h
+++ b/include/linux/node.h
@@ -32,6 +32,19 @@ extern int register_node(struct node *, int, struct node *);
 extern void unregister_node(struct node *node);
 extern int register_one_node(int nid);
 extern void unregister_one_node(int nid);
+#ifdef CONFIG_NUMA
+extern int register_cpu_under_node(unsigned int cpu, unsigned int nid);
+extern int unregister_cpu_under_node(unsigned int cpu, unsigned int nid);
+#else
+static inline int register_cpu_under_node(unsigned int cpu, unsigned int nid)
+{
+	return 0;
+}
+static inline int unregister_cpu_under_node(unsigned int cpu, unsigned int nid)
+{
+	return 0;
+}
+#endif
 
 #define to_node(sys_device) container_of(sys_device, struct node, sysdev)