Merge ../linux-2.6 by hand

17 files changed, 739 insertions, 141 deletions

diff --git a/drivers/base/Makefile b/drivers/base/Makefile
index 66d9c4643fc1..f12898d53078 100644
--- a/drivers/base/Makefile
+++ b/drivers/base/Makefile
@@ -7,6 +7,7 @@ obj-y			:= core.o sys.o bus.o dd.o \
 obj-y                   += power/
 obj-$(CONFIG_FW_LOADER) += firmware_class.o
 obj-$(CONFIG_NUMA)      += node.o
+obj-$(CONFIG_MEMORY_HOTPLUG) += memory.o
 
 ifeq ($(CONFIG_DEBUG_DRIVER),y)
 EXTRA_CFLAGS += -DDEBUG
diff --git a/drivers/base/attribute_container.c b/drivers/base/attribute_container.c
index 6b2eb6f39b4d..2a7d7ae83e1e 100644
--- a/drivers/base/attribute_container.c
+++ b/drivers/base/attribute_container.c
@@ -19,6 +19,8 @@
 #include <linux/list.h>
 #include <linux/module.h>
 
+#include "base.h"
+
 /* This is a private structure used to tie the classdev and the
  * container .. it should never be visible outside this file */
 struct internal_container {
diff --git a/drivers/base/base.h b/drivers/base/base.h
index 783752b68a9a..e3b548d46cff 100644
--- a/drivers/base/base.h
+++ b/drivers/base/base.h
@@ -1,3 +1,15 @@
+
+/* initialisation functions */
+
+extern int devices_init(void);
+extern int buses_init(void);
+extern int classes_init(void);
+extern int firmware_init(void);
+extern int platform_bus_init(void);
+extern int system_bus_init(void);
+extern int cpu_dev_init(void);
+extern int attribute_container_init(void);
+
 extern int bus_add_device(struct device * dev);
 extern void bus_remove_device(struct device * dev);
 
diff --git a/drivers/base/class.c b/drivers/base/class.c
index ce23dc8c18c5..db65fd0babe9 100644
--- a/drivers/base/class.c
+++ b/drivers/base/class.c
@@ -17,6 +17,7 @@
 #include <linux/string.h>
 #include <linux/kdev_t.h>
 #include <linux/err.h>
+#include <linux/slab.h>
 #include "base.h"
 
 #define to_class_attr(_attr) container_of(_attr, struct class_attribute, attr)
@@ -99,7 +100,8 @@ struct class * class_get(struct class * cls)
 
 void class_put(struct class * cls)
 {
-        subsys_put(&cls->subsys);
+        if (cls)
+                subsys_put(&cls->subsys);
 }
 
 
@@ -165,14 +167,25 @@ void class_unregister(struct class * cls)
 
 static void class_create_release(struct class *cls)
 {
+        pr_debug("%s called for %s\n", __FUNCTION__, cls->name);
         kfree(cls);
 }
 
 static void class_device_create_release(struct class_device *class_dev)
 {
+        pr_debug("%s called for %s\n", __FUNCTION__, class_dev->class_id);
         kfree(class_dev);
 }
 
+/* needed to allow these devices to have parent class devices */
+static int class_device_create_hotplug(struct class_device *class_dev,
+                                       char **envp, int num_envp,
+                                       char *buffer, int buffer_size)
+{
+        pr_debug("%s called for %s\n", __FUNCTION__, class_dev->class_id);
+        return 0;
+}
+
 /**
  * class_create - create a struct class structure
  * @owner: pointer to the module that is to "own" this struct class
@@ -301,10 +314,12 @@ static void class_dev_release(struct kobject * kobj)
         kfree(cd->devt_attr);
         cd->devt_attr = NULL;
 
-        if (cls->release)
+        if (cd->release)
+                cd->release(cd);
+        else if (cls->release)
                 cls->release(cd);
         else {
-                printk(KERN_ERR "Device class '%s' does not have a release() function, "
+                printk(KERN_ERR "Class Device '%s' does not have a release() function, "
                         "it is broken and must be fixed.\n",
                         cd->class_id);
                 WARN_ON(1);
@@ -382,14 +397,18 @@ static int class_hotplug(struct kset *kset, struct kobject *kobj, char **envp,
         buffer = &buffer[length];
         buffer_size -= length;
 
-        if (class_dev->class->hotplug) {
-                /* have the bus specific function add its stuff */
-                retval = class_dev->class->hotplug (class_dev, envp, num_envp,
-                                                    buffer, buffer_size);
-                        if (retval) {
-                        pr_debug ("%s - hotplug() returned %d\n",
-                                  __FUNCTION__, retval);
-                }
+        if (class_dev->hotplug) {
+                /* have the class device specific function add its stuff */
+                retval = class_dev->hotplug(class_dev, envp, num_envp,
+                                            buffer, buffer_size);
+                if (retval)
+                        pr_debug("class_dev->hotplug() returned %d\n", retval);
+        } else if (class_dev->class->hotplug) {
+                /* have the class specific function add its stuff */
+                retval = class_dev->class->hotplug(class_dev, envp, num_envp,
+                                                   buffer, buffer_size);
+                if (retval)
+                        pr_debug("class->hotplug() returned %d\n", retval);
         }
 
         return retval;
@@ -442,6 +461,13 @@ static ssize_t show_dev(struct class_device *class_dev, char *buf)
         return print_dev_t(buf, class_dev->devt);
 }
 
+static ssize_t store_uevent(struct class_device *class_dev,
+                            const char *buf, size_t count)
+{
+        kobject_hotplug(&class_dev->kobj, KOBJ_ADD);
+        return count;
+}
+
 void class_device_initialize(struct class_device *class_dev)
 {
         kobj_set_kset_s(class_dev, class_obj_subsys);
@@ -469,34 +495,45 @@ static char *make_class_name(struct class_device *class_dev)
 
 int class_device_add(struct class_device *class_dev)
 {
-        struct class * parent = NULL;
-        struct class_interface * class_intf;
+        struct class *parent_class = NULL;
+        struct class_device *parent_class_dev = NULL;
+        struct class_interface *class_intf;
         char *class_name = NULL;
-        int error;
+        int error = -EINVAL;
 
         class_dev = class_device_get(class_dev);
         if (!class_dev)
                 return -EINVAL;
 
-        if (!strlen(class_dev->class_id)) {
-                error = -EINVAL;
+        if (!strlen(class_dev->class_id))
                 goto register_done;
-        }
 
-        parent = class_get(class_dev->class);
+        parent_class = class_get(class_dev->class);
+        if (!parent_class)
+                goto register_done;
+        parent_class_dev = class_device_get(class_dev->parent);
 
         pr_debug("CLASS: registering class device: ID = '%s'\n",
                  class_dev->class_id);
 
         /* first, register with generic layer. */
         kobject_set_name(&class_dev->kobj, "%s", class_dev->class_id);
-        if (parent)
-                class_dev->kobj.parent = &parent->subsys.kset.kobj;
+        if (parent_class_dev)
+                class_dev->kobj.parent = &parent_class_dev->kobj;
+        else
+                class_dev->kobj.parent = &parent_class->subsys.kset.kobj;
 
-        if ((error = kobject_add(&class_dev->kobj)))
+        error = kobject_add(&class_dev->kobj);
+        if (error)
                 goto register_done;
 
         /* add the needed attributes to this device */
+        class_dev->uevent_attr.attr.name = "uevent";
+        class_dev->uevent_attr.attr.mode = S_IWUSR;
+        class_dev->uevent_attr.attr.owner = parent_class->owner;
+        class_dev->uevent_attr.store = store_uevent;
+        class_device_create_file(class_dev, &class_dev->uevent_attr);
+
         if (MAJOR(class_dev->devt)) {
                 struct class_device_attribute *attr;
                 attr = kzalloc(sizeof(*attr), GFP_KERNEL);
@@ -505,12 +542,10 @@ int class_device_add(struct class_device *class_dev)
                         kobject_del(&class_dev->kobj);
                         goto register_done;
                 }
-
                 attr->attr.name = "dev";
                 attr->attr.mode = S_IRUGO;
-                attr->attr.owner = parent->owner;
+                attr->attr.owner = parent_class->owner;
                 attr->show = show_dev;
-                attr->store = NULL;
                 class_device_create_file(class_dev, attr);
                 class_dev->devt_attr = attr;
         }
@@ -524,20 +559,23 @@ int class_device_add(struct class_device *class_dev)
                                   class_name);
         }
 
+        kobject_hotplug(&class_dev->kobj, KOBJ_ADD);
+
         /* notify any interfaces this device is now here */
-        if (parent) {
-                down(&parent->sem);
-                list_add_tail(&class_dev->node, &parent->children);
-                list_for_each_entry(class_intf, &parent->interfaces, node)
+        if (parent_class) {
+                down(&parent_class->sem);
+                list_add_tail(&class_dev->node, &parent_class->children);
+                list_for_each_entry(class_intf, &parent_class->interfaces, node)
                         if (class_intf->add)
-                                class_intf->add(class_dev);
-                up(&parent->sem);
+                                class_intf->add(class_dev, class_intf);
+                up(&parent_class->sem);
         }
-        kobject_hotplug(&class_dev->kobj, KOBJ_ADD);
 
  register_done:
-        if (error && parent)
-                class_put(parent);
+        if (error) {
+                class_put(parent_class);
+                class_device_put(parent_class_dev);
+        }
         class_device_put(class_dev);
         kfree(class_name);
         return error;
@@ -552,21 +590,28 @@ int class_device_register(struct class_device *class_dev)
 /**
  * class_device_create - creates a class device and registers it with sysfs
  * @cs: pointer to the struct class that this device should be registered to.
+ * @parent: pointer to the parent struct class_device of this new device, if any.
  * @dev: the dev_t for the char device to be added.
  * @device: a pointer to a struct device that is assiociated with this class device.
  * @fmt: string for the class device's name
  *
  * This function can be used by char device classes.  A struct
  * class_device will be created in sysfs, registered to the specified
- * class.  A "dev" file will be created, showing the dev_t for the
- * device.  The pointer to the struct class_device will be returned from
- * the call.  Any further sysfs files that might be required can be
- * created using this pointer.
+ * class.
+ * A "dev" file will be created, showing the dev_t for the device, if
+ * the dev_t is not 0,0.
+ * If a pointer to a parent struct class_device is passed in, the newly
+ * created struct class_device will be a child of that device in sysfs.
+ * The pointer to the struct class_device will be returned from the
+ * call.  Any further sysfs files that might be required can be created
+ * using this pointer.
  *
  * Note: the struct class passed to this function must have previously
  * been created with a call to class_create().
  */
-struct class_device *class_device_create(struct class *cls, dev_t devt,
+struct class_device *class_device_create(struct class *cls,
+                                         struct class_device *parent,
+                                         dev_t devt,
                                          struct device *device, char *fmt, ...)
 {
         va_list args;
@@ -585,6 +630,9 @@ struct class_device *class_device_create(struct class *cls, dev_t devt,
         class_dev->devt = devt;
         class_dev->dev = device;
         class_dev->class = cls;
+        class_dev->parent = parent;
+        class_dev->release = class_device_create_release;
+        class_dev->hotplug = class_device_create_hotplug;
 
         va_start(args, fmt);
         vsnprintf(class_dev->class_id, BUS_ID_SIZE, fmt, args);
@@ -602,17 +650,18 @@ error:
 
 void class_device_del(struct class_device *class_dev)
 {
-        struct class * parent = class_dev->class;
-        struct class_interface * class_intf;
+        struct class *parent_class = class_dev->class;
+        struct class_device *parent_device = class_dev->parent;
+        struct class_interface *class_intf;
         char *class_name = NULL;
 
-        if (parent) {
-                down(&parent->sem);
+        if (parent_class) {
+                down(&parent_class->sem);
                 list_del_init(&class_dev->node);
-                list_for_each_entry(class_intf, &parent->interfaces, node)
+                list_for_each_entry(class_intf, &parent_class->interfaces, node)
                         if (class_intf->remove)
-                                class_intf->remove(class_dev);
-                up(&parent->sem);
+                                class_intf->remove(class_dev, class_intf);
+                up(&parent_class->sem);
         }
 
         if (class_dev->dev) {
@@ -620,6 +669,7 @@ void class_device_del(struct class_device *class_dev)
                 sysfs_remove_link(&class_dev->kobj, "device");
                 sysfs_remove_link(&class_dev->dev->kobj, class_name);
         }
+        class_device_remove_file(class_dev, &class_dev->uevent_attr);
         if (class_dev->devt_attr)
                 class_device_remove_file(class_dev, class_dev->devt_attr);
         class_device_remove_attrs(class_dev);
@@ -627,8 +677,8 @@ void class_device_del(struct class_device *class_dev)
         kobject_hotplug(&class_dev->kobj, KOBJ_REMOVE);
         kobject_del(&class_dev->kobj);
 
-        if (parent)
-                class_put(parent);
+        class_device_put(parent_device);
+        class_put(parent_class);
         kfree(class_name);
 }
 
@@ -708,7 +758,8 @@ struct class_device * class_device_get(struct class_device *class_dev)
 
 void class_device_put(struct class_device *class_dev)
 {
-        kobject_put(&class_dev->kobj);
+        if (class_dev)
+                kobject_put(&class_dev->kobj);
 }
 
 
@@ -728,7 +779,7 @@ int class_interface_register(struct class_interface *class_intf)
         list_add_tail(&class_intf->node, &parent->interfaces);
         if (class_intf->add) {
                 list_for_each_entry(class_dev, &parent->children, node)
-                        class_intf->add(class_dev);
+                        class_intf->add(class_dev, class_intf);
         }
         up(&parent->sem);
 
@@ -747,7 +798,7 @@ void class_interface_unregister(struct class_interface *class_intf)
         list_del_init(&class_intf->node);
         if (class_intf->remove) {
                 list_for_each_entry(class_dev, &parent->children, node)
-                        class_intf->remove(class_dev);
+                        class_intf->remove(class_dev, class_intf);
         }
         up(&parent->sem);
 
diff --git a/drivers/base/core.c b/drivers/base/core.c
index 6ab73f5c799a..8615b42b517a 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -154,6 +154,13 @@ static struct kset_hotplug_ops device_hotplug_ops = {
         .hotplug =      dev_hotplug,
 };
 
+static ssize_t store_uevent(struct device *dev, struct device_attribute *attr,
+                            const char *buf, size_t count)
+{
+        kobject_hotplug(&dev->kobj, KOBJ_ADD);
+        return count;
+}
+
 /**
  *      device_subsys - structure to be registered with kobject core.
  */
@@ -225,6 +232,7 @@ void device_initialize(struct device *dev)
                    klist_children_put);
         INIT_LIST_HEAD(&dev->dma_pools);
         init_MUTEX(&dev->sem);
+        device_init_wakeup(dev, 0);
 }
 
 /**
@@ -258,6 +266,14 @@ int device_add(struct device *dev)
 
         if ((error = kobject_add(&dev->kobj)))
                 goto Error;
+
+        dev->uevent_attr.attr.name = "uevent";
+        dev->uevent_attr.attr.mode = S_IWUSR;
+        if (dev->driver)
+                dev->uevent_attr.attr.owner = dev->driver->owner;
+        dev->uevent_attr.store = store_uevent;
+        device_create_file(dev, &dev->uevent_attr);
+
         kobject_hotplug(&dev->kobj, KOBJ_ADD);
         if ((error = device_pm_add(dev)))
                 goto PMError;
@@ -349,6 +365,7 @@ void device_del(struct device * dev)
 
         if (parent)
                 klist_del(&dev->knode_parent);
+        device_remove_file(dev, &dev->uevent_attr);
 
         /* Notify the platform of the removal, in case they
          * need to do anything...
@@ -390,11 +407,11 @@ static struct device * next_device(struct klist_iter * i)
 
 /**
  *      device_for_each_child - device child iterator.
- *      @dev:   parent struct device.
+ *      @parent: parent struct device.
  *      @data:  data for the callback.
  *      @fn:    function to be called for each device.
  *
- *      Iterate over @dev's child devices, and call @fn for each,
+ *      Iterate over @parent's child devices, and call @fn for each,
  *      passing it @data.
  *
  *      We check the return of @fn each time. If it returns anything
diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c
index b79badd0f158..a95844790f7b 100644
--- a/drivers/base/cpu.c
+++ b/drivers/base/cpu.c
@@ -9,12 +9,15 @@
 #include <linux/topology.h>
 #include <linux/device.h>
 
+#include "base.h"
 
 struct sysdev_class cpu_sysdev_class = {
         set_kset_name("cpu"),
 };
 EXPORT_SYMBOL(cpu_sysdev_class);
 
+static struct sys_device *cpu_sys_devices[NR_CPUS];
+
 #ifdef CONFIG_HOTPLUG_CPU
 int __attribute__((weak)) smp_prepare_cpu (int cpu)
 {
@@ -63,6 +66,7 @@ static void __devinit register_cpu_control(struct cpu *cpu)
 }
 void unregister_cpu(struct cpu *cpu, struct node *root)
 {
+        int logical_cpu = cpu->sysdev.id;
 
         if (root)
                 sysfs_remove_link(&root->sysdev.kobj,
@@ -70,7 +74,7 @@ void unregister_cpu(struct cpu *cpu, struct node *root)
         sysdev_remove_file(&cpu->sysdev, &attr_online);
 
         sysdev_unregister(&cpu->sysdev);
-
+        cpu_sys_devices[logical_cpu] = NULL;
         return;
 }
 #else /* ... !CONFIG_HOTPLUG_CPU */
@@ -102,10 +106,19 @@ int __devinit register_cpu(struct cpu *cpu, int num, struct node *root)
                                           kobject_name(&cpu->sysdev.kobj));
         if (!error && !cpu->no_control)
                 register_cpu_control(cpu);
+        if (!error)
+                cpu_sys_devices[num] = &cpu->sysdev;
         return error;
 }
 
-
+struct sys_device *get_cpu_sysdev(int cpu)
+{
+        if (cpu < NR_CPUS)
+                return cpu_sys_devices[cpu];
+        else
+                return NULL;
+}
+EXPORT_SYMBOL_GPL(get_cpu_sysdev);
 
 int __init cpu_dev_init(void)
 {
diff --git a/drivers/base/driver.c b/drivers/base/driver.c
index ef3fe513e398..161f3a390d90 100644
--- a/drivers/base/driver.c
+++ b/drivers/base/driver.c
@@ -28,6 +28,7 @@ static struct device * next_device(struct klist_iter * i)
 /**
  *      driver_for_each_device - Iterator for devices bound to a driver.
  *      @drv:   Driver we're iterating.
+ *      @start: Device to begin with
  *      @data:  Data to pass to the callback.
  *      @fn:    Function to call for each device.
  *
@@ -57,7 +58,7 @@ EXPORT_SYMBOL_GPL(driver_for_each_device);
 
 /**
  * driver_find_device - device iterator for locating a particular device.
- * @driver: The device's driver
+ * @drv: The device's driver
  * @start: Device to begin with
  * @data: Data to pass to match function
  * @match: Callback function to check device
diff --git a/drivers/base/firmware.c b/drivers/base/firmware.c
index 88ab044932f2..cb1b98ae0d58 100644
--- a/drivers/base/firmware.c
+++ b/drivers/base/firmware.c
@@ -11,6 +11,9 @@
 #include <linux/kobject.h>
 #include <linux/module.h>
 #include <linux/init.h>
+#include <linux/device.h>
+
+#include "base.h"
 
 static decl_subsys(firmware, NULL, NULL);
 
diff --git a/drivers/base/firmware_class.c b/drivers/base/firmware_class.c
index 4acb2c5733c3..98f6c02d6790 100644
--- a/drivers/base/firmware_class.c
+++ b/drivers/base/firmware_class.c
@@ -62,14 +62,16 @@ firmware_timeout_show(struct class *class, char *buf)
 }
 
 /**
- * firmware_timeout_store:
- * Description:
+ * firmware_timeout_store - set number of seconds to wait for firmware
+ * @class: device class pointer
+ * @buf: buffer to scan for timeout value
+ * @count: number of bytes in @buf
+ *
  *      Sets the number of seconds to wait for the firmware.  Once
- *      this expires an error will be return to the driver and no
+ *      this expires an error will be returned to the driver and no
  *      firmware will be provided.
  *
- *      Note: zero means 'wait for ever'
- *
+ *      Note: zero means 'wait forever'.
  **/
 static ssize_t
 firmware_timeout_store(struct class *class, const char *buf, size_t count)
@@ -123,12 +125,15 @@ firmware_loading_show(struct class_device *class_dev, char *buf)
 }
 
 /**
- * firmware_loading_store: - loading control file
- * Description:
+ * firmware_loading_store - set value in the 'loading' control file
+ * @class_dev: class_device pointer
+ * @buf: buffer to scan for loading control value
+ * @count: number of bytes in @buf
+ *
  *      The relevant values are:
  *
  *       1: Start a load, discarding any previous partial load.
- *       0: Conclude the load and handle the data to the driver code.
+ *       0: Conclude the load and hand the data to the driver code.
  *      -1: Conclude the load with an error and discard any written data.
  **/
 static ssize_t
@@ -201,6 +206,7 @@ out:
         up(&fw_lock);
         return ret_count;
 }
+
 static int
 fw_realloc_buffer(struct firmware_priv *fw_priv, int min_size)
 {
@@ -227,11 +233,13 @@ fw_realloc_buffer(struct firmware_priv *fw_priv, int min_size)
 }
 
 /**
- * firmware_data_write:
+ * firmware_data_write - write method for firmware
+ * @kobj: kobject for the class_device
+ * @buffer: buffer being written
+ * @offset: buffer offset for write in total data store area
+ * @count: buffer size
  *
- * Description:
- *
- *      Data written to the 'data' attribute will be later handled to
+ *      Data written to the 'data' attribute will be later handed to
  *      the driver as a firmware image.
  **/
 static ssize_t
@@ -264,6 +272,7 @@ out:
         up(&fw_lock);
         return retval;
 }
+
 static struct bin_attribute firmware_attr_data_tmpl = {
         .attr = {.name = "data", .mode = 0644, .owner = THIS_MODULE},
         .size = 0,
@@ -448,13 +457,16 @@ out:
 
 /**
  * request_firmware: - request firmware to hotplug and wait for it
- * Description:
- *      @firmware will be used to return a firmware image by the name
+ * @firmware_p: pointer to firmware image
+ * @name: name of firmware file
+ * @device: device for which firmware is being loaded
+ *
+ *      @firmware_p will be used to return a firmware image by the name
  *      of @name for device @device.
  *
  *      Should be called from user context where sleeping is allowed.
  *
- *      @name will be use as $FIRMWARE in the hotplug environment and
+ *      @name will be used as $FIRMWARE in the hotplug environment and
  *      should be distinctive enough not to be confused with any other
  *      firmware image for this or any other device.
  **/
@@ -468,6 +480,7 @@ request_firmware(const struct firmware **firmware_p, const char *name,
 
 /**
  * release_firmware: - release the resource associated with a firmware image
+ * @fw: firmware resource to release
  **/
 void
 release_firmware(const struct firmware *fw)
@@ -480,8 +493,10 @@ release_firmware(const struct firmware *fw)
 
 /**
  * register_firmware: - provide a firmware image for later usage
+ * @name: name of firmware image file
+ * @data: buffer pointer for the firmware image
+ * @size: size of the data buffer area
  *
- * Description:
  *      Make sure that @data will be available by requesting firmware @name.
  *
  *      Note: This will not be possible until some kind of persistence
@@ -526,21 +541,19 @@ request_firmware_work_func(void *arg)
 }
 
 /**
- * request_firmware_nowait:
+ * request_firmware_nowait: asynchronous version of request_firmware
+ * @module: module requesting the firmware
+ * @hotplug: invokes hotplug event to copy the firmware image if this flag
+ *      is non-zero else the firmware copy must be done manually.
+ * @name: name of firmware file
+ * @device: device for which firmware is being loaded
+ * @context: will be passed over to @cont, and
+ *      @fw may be %NULL if firmware request fails.
+ * @cont: function will be called asynchronously when the firmware
+ *      request is over.
  *
- * Description:
  *      Asynchronous variant of request_firmware() for contexts where
  *      it is not possible to sleep.
- *
- *      @hotplug invokes hotplug event to copy the firmware image if this flag
- *      is non-zero else the firmware copy must be done manually.
- *
- *      @cont will be called asynchronously when the firmware request is over.
- *
- *      @context will be passed over to @cont.
- *
- *      @fw may be %NULL if firmware request fails.
- *
  **/
 int
 request_firmware_nowait(
diff --git a/drivers/base/init.c b/drivers/base/init.c
index a76ae5a221f3..c648914b9cde 100644
--- a/drivers/base/init.c
+++ b/drivers/base/init.c
@@ -9,15 +9,10 @@
 
 #include <linux/device.h>
 #include <linux/init.h>
+#include <linux/memory.h>
+
+#include "base.h"
 
-extern int devices_init(void);
-extern int buses_init(void);
-extern int classes_init(void);
-extern int firmware_init(void);
-extern int platform_bus_init(void);
-extern int system_bus_init(void);
-extern int cpu_dev_init(void);
-extern int attribute_container_init(void);
 /**
  *      driver_init - initialize driver model.
  *
@@ -39,5 +34,6 @@ void __init driver_init(void)
         platform_bus_init();
         system_bus_init();
         cpu_dev_init();
+        memory_dev_init();
         attribute_container_init();
 }
diff --git a/drivers/base/memory.c b/drivers/base/memory.c
new file mode 100644
index 000000000000..b7ddd651d664
--- /dev/null
+++ b/drivers/base/memory.c
@@ -0,0 +1,452 @@
+/*
+ * drivers/base/memory.c - basic Memory class support
+ *
+ * Written by Matt Tolentino <matthew.e.tolentino@intel.com>
+ *            Dave Hansen <haveblue@us.ibm.com>
+ *
+ * This file provides the necessary infrastructure to represent
+ * a SPARSEMEM-memory-model system's physical memory in /sysfs.
+ * All arch-independent code that assumes MEMORY_HOTPLUG requires
+ * SPARSEMEM should be contained here, or in mm/memory_hotplug.c.
+ */
+
+#include <linux/sysdev.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/sched.h>        /* capable() */
+#include <linux/topology.h>
+#include <linux/device.h>
+#include <linux/memory.h>
+#include <linux/kobject.h>
+#include <linux/memory_hotplug.h>
+#include <linux/mm.h>
+#include <asm/atomic.h>
+#include <asm/uaccess.h>
+
+#define MEMORY_CLASS_NAME       "memory"
+
+static struct sysdev_class memory_sysdev_class = {
+        set_kset_name(MEMORY_CLASS_NAME),
+};
+EXPORT_SYMBOL(memory_sysdev_class);
+
+static char *memory_hotplug_name(struct kset *kset, struct kobject *kobj)
+{
+        return MEMORY_CLASS_NAME;
+}
+
+static int memory_hotplug(struct kset *kset, struct kobject *kobj, char **envp,
+                        int num_envp, char *buffer, int buffer_size)
+{
+        int retval = 0;
+
+        return retval;
+}
+
+static struct kset_hotplug_ops memory_hotplug_ops = {
+        .name           = memory_hotplug_name,
+        .hotplug        = memory_hotplug,
+};
+
+static struct notifier_block *memory_chain;
+
+static int register_memory_notifier(struct notifier_block *nb)
+{
+        return notifier_chain_register(&memory_chain, nb);
+}
+
+static void unregister_memory_notifier(struct notifier_block *nb)
+{
+        notifier_chain_unregister(&memory_chain, nb);
+}
+
+/*
+ * register_memory - Setup a sysfs device for a memory block
+ */
+static int
+register_memory(struct memory_block *memory, struct mem_section *section,
+                struct node *root)
+{
+        int error;
+
+        memory->sysdev.cls = &memory_sysdev_class;
+        memory->sysdev.id = __section_nr(section);
+
+        error = sysdev_register(&memory->sysdev);
+
+        if (root && !error)
+                error = sysfs_create_link(&root->sysdev.kobj,
+                                          &memory->sysdev.kobj,
+                                          kobject_name(&memory->sysdev.kobj));
+
+        return error;
+}
+
+static void
+unregister_memory(struct memory_block *memory, struct mem_section *section,
+                struct node *root)
+{
+        BUG_ON(memory->sysdev.cls != &memory_sysdev_class);
+        BUG_ON(memory->sysdev.id != __section_nr(section));
+
+        sysdev_unregister(&memory->sysdev);
+        if (root)
+                sysfs_remove_link(&root->sysdev.kobj,
+                                  kobject_name(&memory->sysdev.kobj));
+}
+
+/*
+ * use this as the physical section index that this memsection
+ * uses.
+ */
+
+static ssize_t show_mem_phys_index(struct sys_device *dev, char *buf)
+{
+        struct memory_block *mem =
+                container_of(dev, struct memory_block, sysdev);
+        return sprintf(buf, "%08lx\n", mem->phys_index);
+}
+
+/*
+ * online, offline, going offline, etc.
+ */
+static ssize_t show_mem_state(struct sys_device *dev, char *buf)
+{
+        struct memory_block *mem =
+                container_of(dev, struct memory_block, sysdev);
+        ssize_t len = 0;
+
+        /*
+         * We can probably put these states in a nice little array
+         * so that they're not open-coded
+         */
+        switch (mem->state) {
+                case MEM_ONLINE:
+                        len = sprintf(buf, "online\n");
+                        break;
+                case MEM_OFFLINE:
+                        len = sprintf(buf, "offline\n");
+                        break;
+                case MEM_GOING_OFFLINE:
+                        len = sprintf(buf, "going-offline\n");
+                        break;
+                default:
+                        len = sprintf(buf, "ERROR-UNKNOWN-%ld\n",
+                                        mem->state);
+                        WARN_ON(1);
+                        break;
+        }
+
+        return len;
+}
+
+static inline int memory_notify(unsigned long val, void *v)
+{
+        return notifier_call_chain(&memory_chain, val, v);
+}
+
+/*
+ * MEMORY_HOTPLUG depends on SPARSEMEM in mm/Kconfig, so it is
+ * OK to have direct references to sparsemem variables in here.
+ */
+static int
+memory_block_action(struct memory_block *mem, unsigned long action)
+{
+        int i;
+        unsigned long psection;
+        unsigned long start_pfn, start_paddr;
+        struct page *first_page;
+        int ret;
+        int old_state = mem->state;
+
+        psection = mem->phys_index;
+        first_page = pfn_to_page(psection << PFN_SECTION_SHIFT);
+
+        /*
+         * The probe routines leave the pages reserved, just
+         * as the bootmem code does.  Make sure they're still
+         * that way.
+         */
+        if (action == MEM_ONLINE) {
+                for (i = 0; i < PAGES_PER_SECTION; i++) {
+                        if (PageReserved(first_page+i))
+                                continue;
+
+                        printk(KERN_WARNING "section number %ld page number %d "
+                                "not reserved, was it already online? \n",
+                                psection, i);
+                        return -EBUSY;
+                }
+        }
+
+        switch (action) {
+                case MEM_ONLINE:
+                        start_pfn = page_to_pfn(first_page);
+                        ret = online_pages(start_pfn, PAGES_PER_SECTION);
+                        break;
+                case MEM_OFFLINE:
+                        mem->state = MEM_GOING_OFFLINE;
+                        memory_notify(MEM_GOING_OFFLINE, NULL);
+                        start_paddr = page_to_pfn(first_page) << PAGE_SHIFT;
+                        ret = remove_memory(start_paddr,
+                                            PAGES_PER_SECTION << PAGE_SHIFT);
+                        if (ret) {
+                                mem->state = old_state;
+                                break;
+                        }
+                        memory_notify(MEM_MAPPING_INVALID, NULL);
+                        break;
+                default:
+                        printk(KERN_WARNING "%s(%p, %ld) unknown action: %ld\n",
+                                        __FUNCTION__, mem, action, action);
+                        WARN_ON(1);
+                        ret = -EINVAL;
+        }
+        /*
+         * For now, only notify on successful memory operations
+         */
+        if (!ret)
+                memory_notify(action, NULL);
+
+        return ret;
+}
+
+static int memory_block_change_state(struct memory_block *mem,
+                unsigned long to_state, unsigned long from_state_req)
+{
+        int ret = 0;
+        down(&mem->state_sem);
+
+        if (mem->state != from_state_req) {
+                ret = -EINVAL;
+                goto out;
+        }
+
+        ret = memory_block_action(mem, to_state);
+        if (!ret)
+                mem->state = to_state;
+
+out:
+        up(&mem->state_sem);
+        return ret;
+}
+
+static ssize_t
+store_mem_state(struct sys_device *dev, const char *buf, size_t count)
+{
+        struct memory_block *mem;
+        unsigned int phys_section_nr;
+        int ret = -EINVAL;
+
+        mem = container_of(dev, struct memory_block, sysdev);
+        phys_section_nr = mem->phys_index;
+
+        if (!valid_section_nr(phys_section_nr))
+                goto out;
+
+        if (!strncmp(buf, "online", min((int)count, 6)))
+                ret = memory_block_change_state(mem, MEM_ONLINE, MEM_OFFLINE);
+        else if(!strncmp(buf, "offline", min((int)count, 7)))
+                ret = memory_block_change_state(mem, MEM_OFFLINE, MEM_ONLINE);
+out:
+        if (ret)
+                return ret;
+        return count;
+}
+
+/*
+ * phys_device is a bad name for this.  What I really want
+ * is a way to differentiate between memory ranges that
+ * are part of physical devices that constitute
+ * a complete removable unit or fru.
+ * i.e. do these ranges belong to the same physical device,
+ * s.t. if I offline all of these sections I can then
+ * remove the physical device?
+ */
+static ssize_t show_phys_device(struct sys_device *dev, char *buf)
+{
+        struct memory_block *mem =
+                container_of(dev, struct memory_block, sysdev);
+        return sprintf(buf, "%d\n", mem->phys_device);
+}
+
+static SYSDEV_ATTR(phys_index, 0444, show_mem_phys_index, NULL);
+static SYSDEV_ATTR(state, 0644, show_mem_state, store_mem_state);
+static SYSDEV_ATTR(phys_device, 0444, show_phys_device, NULL);
+
+#define mem_create_simple_file(mem, attr_name)  \
+        sysdev_create_file(&mem->sysdev, &attr_##attr_name)
+#define mem_remove_simple_file(mem, attr_name)  \
+        sysdev_remove_file(&mem->sysdev, &attr_##attr_name)
+
+/*
+ * Block size attribute stuff
+ */
+static ssize_t
+print_block_size(struct class *class, char *buf)
+{
+        return sprintf(buf, "%lx\n", (unsigned long)PAGES_PER_SECTION * PAGE_SIZE);
+}
+
+static CLASS_ATTR(block_size_bytes, 0444, print_block_size, NULL);
+
+static int block_size_init(void)
+{
+        sysfs_create_file(&memory_sysdev_class.kset.kobj,
+                &class_attr_block_size_bytes.attr);
+        return 0;
+}
+
+/*
+ * Some architectures will have custom drivers to do this, and
+ * will not need to do it from userspace.  The fake hot-add code
+ * as well as ppc64 will do all of their discovery in userspace
+ * and will require this interface.
+ */
+#ifdef CONFIG_ARCH_MEMORY_PROBE
+static ssize_t
+memory_probe_store(struct class *class, const char __user *buf, size_t count)
+{
+        u64 phys_addr;
+        int ret;
+
+        phys_addr = simple_strtoull(buf, NULL, 0);
+
+        ret = add_memory(phys_addr, PAGES_PER_SECTION << PAGE_SHIFT);
+
+        if (ret)
+                count = ret;
+
+        return count;
+}
+static CLASS_ATTR(probe, 0700, NULL, memory_probe_store);
+
+static int memory_probe_init(void)
+{
+        sysfs_create_file(&memory_sysdev_class.kset.kobj,
+                &class_attr_probe.attr);
+        return 0;
+}
+#else
+#define memory_probe_init(...)  do {} while (0)
+#endif
+
+/*
+ * Note that phys_device is optional.  It is here to allow for
+ * differentiation between which *physical* devices each
+ * section belongs to...
+ */
+
+static int add_memory_block(unsigned long node_id, struct mem_section *section,
+                     unsigned long state, int phys_device)
+{
+        struct memory_block *mem = kzalloc(sizeof(*mem), GFP_KERNEL);
+        int ret = 0;
+
+        if (!mem)
+                return -ENOMEM;
+
+        mem->phys_index = __section_nr(section);
+        mem->state = state;
+        init_MUTEX(&mem->state_sem);
+        mem->phys_device = phys_device;
+
+        ret = register_memory(mem, section, NULL);
+        if (!ret)
+                ret = mem_create_simple_file(mem, phys_index);
+        if (!ret)
+                ret = mem_create_simple_file(mem, state);
+        if (!ret)
+                ret = mem_create_simple_file(mem, phys_device);
+
+        return ret;
+}
+
+/*
+ * For now, we have a linear search to go find the appropriate
+ * memory_block corresponding to a particular phys_index. If
+ * this gets to be a real problem, we can always use a radix
+ * tree or something here.
+ *
+ * This could be made generic for all sysdev classes.
+ */
+static struct memory_block *find_memory_block(struct mem_section *section)
+{
+        struct kobject *kobj;
+        struct sys_device *sysdev;
+        struct memory_block *mem;
+        char name[sizeof(MEMORY_CLASS_NAME) + 9 + 1];
+
+        /*
+         * This only works because we know that section == sysdev->id
+         * slightly redundant with sysdev_register()
+         */
+        sprintf(&name[0], "%s%d", MEMORY_CLASS_NAME, __section_nr(section));
+
+        kobj = kset_find_obj(&memory_sysdev_class.kset, name);
+        if (!kobj)
+                return NULL;
+
+        sysdev = container_of(kobj, struct sys_device, kobj);
+        mem = container_of(sysdev, struct memory_block, sysdev);
+
+        return mem;
+}
+
+int remove_memory_block(unsigned long node_id, struct mem_section *section,
+                int phys_device)
+{
+        struct memory_block *mem;
+
+        mem = find_memory_block(section);
+        mem_remove_simple_file(mem, phys_index);
+        mem_remove_simple_file(mem, state);
+        mem_remove_simple_file(mem, phys_device);
+        unregister_memory(mem, section, NULL);
+
+        return 0;
+}
+
+/*
+ * need an interface for the VM to add new memory regions,
+ * but without onlining it.
+ */
+int register_new_memory(struct mem_section *section)
+{
+        return add_memory_block(0, section, MEM_OFFLINE, 0);
+}
+
+int unregister_memory_section(struct mem_section *section)
+{
+        if (!valid_section(section))
+                return -EINVAL;
+
+        return remove_memory_block(0, section, 0);
+}
+
+/*
+ * Initialize the sysfs support for memory devices...
+ */
+int __init memory_dev_init(void)
+{
+        unsigned int i;
+        int ret;
+
+        memory_sysdev_class.kset.hotplug_ops = &memory_hotplug_ops;
+        ret = sysdev_class_register(&memory_sysdev_class);
+
+        /*
+         * Create entries for memory sections that were found
+         * during boot and have been initialized
+         */
+        for (i = 0; i < NR_MEM_SECTIONS; i++) {
+                if (!valid_section_nr(i))
+                        continue;
+                add_memory_block(0, __nr_to_section(i), MEM_ONLINE, 0);
+        }
+
+        memory_probe_init();
+        block_size_init();
+
+        return ret;
+}
diff --git a/drivers/base/platform.c b/drivers/base/platform.c
index 361e204209eb..08d9cc99c7de 100644
--- a/drivers/base/platform.c
+++ b/drivers/base/platform.c
@@ -16,6 +16,9 @@
 #include <linux/dma-mapping.h>
 #include <linux/bootmem.h>
 #include <linux/err.h>
+#include <linux/slab.h>
+
+#include "base.h"
 
 struct device platform_bus = {
         .bus_id         = "platform",
@@ -279,13 +282,9 @@ static int platform_suspend(struct device * dev, pm_message_t state)
 {
         int ret = 0;
 
-        if (dev->driver && dev->driver->suspend) {
-                ret = dev->driver->suspend(dev, state, SUSPEND_DISABLE);
-                if (ret == 0)
-                        ret = dev->driver->suspend(dev, state, SUSPEND_SAVE_STATE);
-                if (ret == 0)
-                        ret = dev->driver->suspend(dev, state, SUSPEND_POWER_DOWN);
-        }
+        if (dev->driver && dev->driver->suspend)
+                ret = dev->driver->suspend(dev, state);
+
         return ret;
 }
 
@@ -293,13 +292,9 @@ static int platform_resume(struct device * dev)
 {
         int ret = 0;
 
-        if (dev->driver && dev->driver->resume) {
-                ret = dev->driver->resume(dev, RESUME_POWER_ON);
-                if (ret == 0)
-                        ret = dev->driver->resume(dev, RESUME_RESTORE_STATE);
-                if (ret == 0)
-                        ret = dev->driver->resume(dev, RESUME_ENABLE);
-        }
+        if (dev->driver && dev->driver->resume)
+                ret = dev->driver->resume(dev);
+
         return ret;
 }
 
diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index 15e6a8f951f1..0d2e101e4f15 100644
--- a/drivers/base/power/main.c
+++ b/drivers/base/power/main.c
@@ -30,23 +30,6 @@ LIST_HEAD(dpm_off_irq);
 DECLARE_MUTEX(dpm_sem);
 DECLARE_MUTEX(dpm_list_sem);
 
-/*
- * PM Reference Counting.
- */
-
-static inline void device_pm_hold(struct device * dev)
-{
-        if (dev)
-                atomic_inc(&dev->power.pm_users);
-}
-
-static inline void device_pm_release(struct device * dev)
-{
-        if (dev)
-                atomic_dec(&dev->power.pm_users);
-}
-
-
 /**
  *      device_pm_set_parent - Specify power dependency.
  *      @dev:           Device who needs power.
@@ -62,10 +45,8 @@ static inline void device_pm_release(struct device * dev)
 
 void device_pm_set_parent(struct device * dev, struct device * parent)
 {
-        struct device * old_parent = dev->power.pm_parent;
-        device_pm_release(old_parent);
-        dev->power.pm_parent = parent;
-        device_pm_hold(parent);
+        put_device(dev->power.pm_parent);
+        dev->power.pm_parent = get_device(parent);
 }
 EXPORT_SYMBOL_GPL(device_pm_set_parent);
 
@@ -75,7 +56,6 @@ int device_pm_add(struct device * dev)
 
         pr_debug("PM: Adding info for %s:%s\n",
                  dev->bus ? dev->bus->name : "No Bus", dev->kobj.name);
-        atomic_set(&dev->power.pm_users, 0);
         down(&dpm_list_sem);
         list_add_tail(&dev->power.entry, &dpm_active);
         device_pm_set_parent(dev, dev->parent);
@@ -91,7 +71,7 @@ void device_pm_remove(struct device * dev)
                  dev->bus ? dev->bus->name : "No Bus", dev->kobj.name);
         down(&dpm_list_sem);
         dpm_sysfs_remove(dev);
-        device_pm_release(dev->power.pm_parent);
+        put_device(dev->power.pm_parent);
         list_del_init(&dev->power.entry);
         up(&dpm_list_sem);
 }
diff --git a/drivers/base/power/power.h b/drivers/base/power/power.h
index 2e700d795cf1..fb3d35a9e101 100644
--- a/drivers/base/power/power.h
+++ b/drivers/base/power/power.h
@@ -67,9 +67,6 @@ extern int suspend_device(struct device *, pm_message_t);
  * runtime.c
  */
 
-extern int dpm_runtime_suspend(struct device *, pm_message_t);
-extern void dpm_runtime_resume(struct device *);
-
 #else /* CONFIG_PM */
 
 
@@ -82,14 +79,4 @@ static inline void device_pm_remove(struct device * dev)
 
 }
 
-static inline int dpm_runtime_suspend(struct device * dev, pm_message_t state)
-{
-        return 0;
-}
-
-static inline void dpm_runtime_resume(struct device * dev)
-{
-
-}
-
 #endif
diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c
index e8f0519f5dfa..adbc3148c039 100644
--- a/drivers/base/power/runtime.c
+++ b/drivers/base/power/runtime.c
@@ -36,6 +36,7 @@ void dpm_runtime_resume(struct device * dev)
         runtime_resume(dev);
         up(&dpm_sem);
 }
+EXPORT_SYMBOL(dpm_runtime_resume);
 
 
 /**
diff --git a/drivers/base/power/sysfs.c b/drivers/base/power/sysfs.c
index 8d04fb435c17..89c57875f3e5 100644
--- a/drivers/base/power/sysfs.c
+++ b/drivers/base/power/sysfs.c
@@ -48,8 +48,81 @@ static ssize_t state_store(struct device * dev, struct device_attribute *attr, c
 static DEVICE_ATTR(state, 0644, state_show, state_store);
 
 
+/*
+ *      wakeup - Report/change current wakeup option for device
+ *
+ *      Some devices support "wakeup" events, which are hardware signals
+ *      used to activate devices from suspended or low power states.  Such
+ *      devices have one of three values for the sysfs power/wakeup file:
+ *
+ *       + "enabled\n" to issue the events;
+ *       + "disabled\n" not to do so; or
+ *       + "\n" for temporary or permanent inability to issue wakeup.
+ *
+ *      (For example, unconfigured USB devices can't issue wakeups.)
+ *
+ *      Familiar examples of devices that can issue wakeup events include
+ *      keyboards and mice (both PS2 and USB styles), power buttons, modems,
+ *      "Wake-On-LAN" Ethernet links, GPIO lines, and more.  Some events
+ *      will wake the entire system from a suspend state; others may just
+ *      wake up the device (if the system as a whole is already active).
+ *      Some wakeup events use normal IRQ lines; other use special out
+ *      of band signaling.
+ *
+ *      It is the responsibility of device drivers to enable (or disable)
+ *      wakeup signaling as part of changing device power states, respecting
+ *      the policy choices provided through the driver model.
+ *
+ *      Devices may not be able to generate wakeup events from all power
+ *      states.  Also, the events may be ignored in some configurations;
+ *      for example, they might need help from other devices that aren't
+ *      active, or which may have wakeup disabled.  Some drivers rely on
+ *      wakeup events internally (unless they are disabled), keeping
+ *      their hardware in low power modes whenever they're unused.  This
+ *      saves runtime power, without requiring system-wide sleep states.
+ */
+
+static const char enabled[] = "enabled";
+static const char disabled[] = "disabled";
+
+static ssize_t
+wake_show(struct device * dev, struct device_attribute *attr, char * buf)
+{
+        return sprintf(buf, "%s\n", device_can_wakeup(dev)
+                ? (device_may_wakeup(dev) ? enabled : disabled)
+                : "");
+}
+
+static ssize_t
+wake_store(struct device * dev, struct device_attribute *attr,
+        const char * buf, size_t n)
+{
+        char *cp;
+        int len = n;
+
+        if (!device_can_wakeup(dev))
+                return -EINVAL;
+
+        cp = memchr(buf, '\n', n);
+        if (cp)
+                len = cp - buf;
+        if (len == sizeof enabled - 1
+                        && strncmp(buf, enabled, sizeof enabled - 1) == 0)
+                device_set_wakeup_enable(dev, 1);
+        else if (len == sizeof disabled - 1
+                        && strncmp(buf, disabled, sizeof disabled - 1) == 0)
+                device_set_wakeup_enable(dev, 0);
+        else
+                return -EINVAL;
+        return n;
+}
+
+static DEVICE_ATTR(wakeup, 0644, wake_show, wake_store);
+
+
 static struct attribute * power_attrs[] = {
         &dev_attr_state.attr,
+        &dev_attr_wakeup.attr,
         NULL,
 };
 static struct attribute_group pm_attr_group = {
diff --git a/drivers/base/sys.c b/drivers/base/sys.c
index 3431eb6004c3..66ed8f2fece5 100644
--- a/drivers/base/sys.c
+++ b/drivers/base/sys.c
@@ -21,6 +21,7 @@
 #include <linux/slab.h>
 #include <linux/string.h>
 #include <linux/pm.h>
+#include <asm/semaphore.h>
 
 extern struct subsystem devices_subsys;