Initial commit; kernel source import

drivers/base/Kconfig

@@ -0,0 +1,328 @@
+menu "Generic Driver Options"
+
+config UEVENT_HELPER_PATH
+	string "path to uevent helper"
+	depends on HOTPLUG
+	default ""
+	help
+	  Path to uevent helper program forked by the kernel for
+	  every uevent.
+	  Before the switch to the netlink-based uevent source, this was
+	  used to hook hotplug scripts into kernel device events. It
+	  usually pointed to a shell script at /sbin/hotplug.
+	  This should not be used today, because usual systems create
+	  many events at bootup or device discovery in a very short time
+	  frame. One forked process per event can create so many processes
+	  that it creates a high system load, or on smaller systems
+	  it is known to create out-of-memory situations during bootup.
+
+	  To disable user space helper program execution at early boot
+	  time specify an empty string here. This setting can be altered
+	  via /proc/sys/kernel/hotplug or via /sys/kernel/uevent_helper
+	  later at runtime.
+
+config DEVTMPFS
+	bool "Maintain a devtmpfs filesystem to mount at /dev"
+	depends on HOTPLUG
+	help
+	  This creates a tmpfs/ramfs filesystem instance early at bootup.
+	  In this filesystem, the kernel driver core maintains device
+	  nodes with their default names and permissions for all
+	  registered devices with an assigned major/minor number.
+	  Userspace can modify the filesystem content as needed, add
+	  symlinks, and apply needed permissions.
+	  It provides a fully functional /dev directory, where usually
+	  udev runs on top, managing permissions and adding meaningful
+	  symlinks.
+	  In very limited environments, it may provide a sufficient
+	  functional /dev without any further help. It also allows simple
+	  rescue systems, and reliably handles dynamic major/minor numbers.
+
+	  Notice: if CONFIG_TMPFS isn't enabled, the simpler ramfs
+	  file system will be used instead.
+
+config DEVTMPFS_MOUNT
+	bool "Automount devtmpfs at /dev, after the kernel mounted the rootfs"
+	depends on DEVTMPFS
+	help
+	  This will instruct the kernel to automatically mount the
+	  devtmpfs filesystem at /dev, directly after the kernel has
+	  mounted the root filesystem. The behavior can be overridden
+	  with the commandline parameter: devtmpfs.mount=0|1.
+	  This option does not affect initramfs based booting, here
+	  the devtmpfs filesystem always needs to be mounted manually
+	  after the roots is mounted.
+	  With this option enabled, it allows to bring up a system in
+	  rescue mode with init=/bin/sh, even when the /dev directory
+	  on the rootfs is completely empty.
+
+config DEVTMPFS_SAFE
+	bool "Automount devtmpfs with nosuid/noexec"
+	depends on DEVTMPFS_MOUNT
+	default y
+	help
+	  This instructs the kernel to automount devtmpfs with the
+	  MS_NOEXEC and MS_NOSUID mount flags, which can prevent
+	  certain kinds of code-execution attack on embedded platforms.
+
+config STANDALONE
+	bool "Select only drivers that don't need compile-time external firmware"
+	default y
+	help
+	  Select this option if you don't have magic firmware for drivers that
+	  need it.
+
+	  If unsure, say Y.
+
+config PREVENT_FIRMWARE_BUILD
+	bool "Prevent firmware from being built"
+	default y
+	help
+	  Say yes to avoid building firmware. Firmware is usually shipped
+	  with the driver and only when updating the firmware should a
+	  rebuild be made.
+	  If unsure, say Y here.
+
+config FW_LOADER
+	tristate "Userspace firmware loading support" if EXPERT
+	default y
+	---help---
+	  This option is provided for the case where none of the in-tree modules
+	  require userspace firmware loading support, but a module built
+	  out-of-tree does.
+
+config FIRMWARE_IN_KERNEL
+	bool "Include in-kernel firmware blobs in kernel binary"
+	depends on FW_LOADER
+	default y
+	help
+	  The kernel source tree includes a number of firmware 'blobs'
+	  that are used by various drivers. The recommended way to
+	  use these is to run "make firmware_install", which, after
+	  converting ihex files to binary, copies all of the needed
+	  binary files in firmware/ to /lib/firmware/ on your system so
+	  that they can be loaded by userspace helpers on request.
+
+	  Enabling this option will build each required firmware blob
+	  into the kernel directly, where request_firmware() will find
+	  them without having to call out to userspace. This may be
+	  useful if your root file system requires a device that uses
+	  such firmware and do not wish to use an initrd.
+
+	  This single option controls the inclusion of firmware for
+	  every driver that uses request_firmware() and ships its
+	  firmware in the kernel source tree, which avoids a
+	  proliferation of 'Include firmware for xxx device' options.
+
+	  Say 'N' and let firmware be loaded from userspace.
+
+config EXTRA_FIRMWARE
+	string "External firmware blobs to build into the kernel binary"
+	depends on FW_LOADER
+	help
+	  This option allows firmware to be built into the kernel for the case
+	  where the user either cannot or doesn't want to provide it from
+	  userspace at runtime (for example, when the firmware in question is
+	  required for accessing the boot device, and the user doesn't want to
+	  use an initrd).
+
+	  This option is a string and takes the (space-separated) names of the
+	  firmware files -- the same names that appear in MODULE_FIRMWARE()
+	  and request_firmware() in the source. These files should exist under
+	  the directory specified by the EXTRA_FIRMWARE_DIR option, which is
+	  by default the firmware subdirectory of the kernel source tree.
+
+	  For example, you might set CONFIG_EXTRA_FIRMWARE="usb8388.bin", copy
+	  the usb8388.bin file into the firmware directory, and build the kernel.
+	  Then any request_firmware("usb8388.bin") will be satisfied internally
+	  without needing to call out to userspace.
+
+	  WARNING: If you include additional firmware files into your binary
+	  kernel image that are not available under the terms of the GPL,
+	  then it may be a violation of the GPL to distribute the resulting
+	  image since it combines both GPL and non-GPL work. You should
+	  consult a lawyer of your own before distributing such an image.
+
+config EXTRA_FIRMWARE_DIR
+	string "Firmware blobs root directory"
+	depends on EXTRA_FIRMWARE != ""
+	default "firmware"
+	help
+	  This option controls the directory in which the kernel build system
+	  looks for the firmware files listed in the EXTRA_FIRMWARE option.
+	  The default is firmware/ in the kernel source tree, but by changing
+	  this option you can point it elsewhere, such as /lib/firmware/ or
+	  some other directory containing the firmware files.
+
+config FW_LOADER_USER_HELPER
+	bool "Fallback user-helper invocation for firmware loading"
+	depends on FW_LOADER
+	default y
+	help
+	  This option enables / disables the invocation of user-helper
+	  (e.g. udev) for loading firmware files as a fallback after the
+	  direct file loading in kernel fails.  The user-mode helper is
+	  no longer required unless you have a special firmware file that
+	  resides in a non-standard path.
+
+config WANT_DEV_COREDUMP
+	bool
+	help
+	  Drivers should "select" this option if they desire to use the
+	  device coredump mechanism.
+
+config ALLOW_DEV_COREDUMP
+	bool "Allow device coredump" if EXPERT
+	default y
+	help
+	  This option controls if the device coredump mechanism is available or
+	  not; if disabled, the mechanism will be omitted even if drivers that
+	  can use it are enabled.
+	  Say 'N' for more sensitive systems or systems that don't want
+	  to ever access the information to not have the code, nor keep any
+	  data.
+
+	  If unsure, say Y.
+
+config DEV_COREDUMP
+	bool
+	default y if WANT_DEV_COREDUMP
+	depends on ALLOW_DEV_COREDUMP
+
+config DEBUG_DRIVER
+	bool "Driver Core verbose debug messages"
+	depends on DEBUG_KERNEL
+	help
+	  Say Y here if you want the Driver core to produce a bunch of
+	  debug messages to the system log. Select this if you are having a
+	  problem with the driver core and want to see more of what is
+	  going on.
+
+	  If you are unsure about this, say N here.
+
+config DEBUG_DEVRES
+	bool "Managed device resources verbose debug messages"
+	depends on DEBUG_KERNEL
+	help
+	  This option enables kernel parameter devres.log. If set to
+	  non-zero, devres debug messages are printed. Select this if
+	  you are having a problem with devres or want to debug
+	  resource management for a managed device. devres.log can be
+	  switched on and off from sysfs node.
+
+	  If you are unsure about this, Say N here.
+
+config SYS_HYPERVISOR
+	bool
+	default n
+
+config GENERIC_CPU_DEVICES
+	bool
+	default n
+
+config SOC_BUS
+	bool
+
+source "drivers/base/regmap/Kconfig"
+
+config DMA_SHARED_BUFFER
+	bool
+	default n
+	select ANON_INODES
+	help
+	  This option enables the framework for buffer-sharing between
+	  multiple drivers. A buffer is associated with a file using driver
+	  APIs extension; the file's descriptor can then be passed on to other
+	  driver.
+
+config CMA
+	bool "Contiguous Memory Allocator"
+	depends on HAVE_DMA_CONTIGUOUS && HAVE_MEMBLOCK
+	select MIGRATION
+	select MEMORY_ISOLATION
+	help
+	  This enables the Contiguous Memory Allocator which allows drivers
+	  to allocate big physically-contiguous blocks of memory for use with
+	  hardware components that do not support I/O map nor scatter-gather.
+
+	  For more information see <include/linux/dma-contiguous.h>.
+	  If unsure, say "n".
+
+if CMA
+
+config CMA_DEBUG
+	bool "CMA debug messages (DEVELOPMENT)"
+	depends on DEBUG_KERNEL
+	help
+	  Turns on debug messages in CMA.  This produces KERN_DEBUG
+	  messages for every CMA call as well as various messages while
+	  processing calls such as dma_alloc_from_contiguous().
+	  This option does not affect warning and error messages.
+
+comment "Default contiguous memory area size:"
+
+config CMA_SIZE_MBYTES
+	int "Size in Mega Bytes"
+	depends on !CMA_SIZE_SEL_PERCENTAGE
+	default 16
+	help
+	  Defines the size (in MiB) of the default memory area for Contiguous
+	  Memory Allocator.
+
+config CMA_SIZE_PERCENTAGE
+	int "Percentage of total memory"
+	depends on !CMA_SIZE_SEL_MBYTES
+	default 10
+	help
+	  Defines the size of the default memory area for Contiguous Memory
+	  Allocator as a percentage of the total memory in the system.
+
+choice
+	prompt "Selected region size"
+	default CMA_SIZE_SEL_MBYTES
+
+config CMA_SIZE_SEL_MBYTES
+	bool "Use mega bytes value only"
+
+config CMA_SIZE_SEL_PERCENTAGE
+	bool "Use percentage value only"
+
+config CMA_SIZE_SEL_MIN
+	bool "Use lower value (minimum)"
+
+config CMA_SIZE_SEL_MAX
+	bool "Use higher value (maximum)"
+
+endchoice
+
+config CMA_ALIGNMENT
+	int "Maximum PAGE_SIZE order of alignment for contiguous buffers"
+	range 4 9
+	default 8
+	help
+	  DMA mapping framework by default aligns all buffers to the smallest
+	  PAGE_SIZE order which is greater than or equal to the requested buffer
+	  size. This works well for buffers up to a few hundreds kilobytes, but
+	  for larger buffers it just a memory waste. With this parameter you can
+	  specify the maximum PAGE_SIZE order for contiguous buffers. Larger
+	  buffers will be aligned only to this specified order. The order is
+	  expressed as a power of two multiplied by the PAGE_SIZE.
+
+	  For example, if your system defaults to 4KiB pages, the order value
+	  of 8 means that the buffers will be aligned up to 1MiB only.
+
+	  If unsure, leave the default value "8".
+
+config CMA_AREAS
+	int "Maximum count of the CMA device-private areas"
+	default 7
+	help
+	  CMA allows to create CMA areas for particular devices. This parameter
+	  sets the maximum number of such device private CMA areas in the
+	  system.
+
+	  If unsure, leave the default value "7".
+
+endif
+
+endmenu

drivers/base/Makefile

@@ -0,0 +1,28 @@
+# Makefile for the Linux device tree
+
+obj-y			:= core.o bus.o dd.o syscore.o \
+			   driver.o class.o platform.o \
+			   cpu.o firmware.o init.o map.o devres.o \
+			   attribute_container.o transport_class.o \
+			   topology.o
+obj-$(CONFIG_DEVTMPFS)	+= devtmpfs.o
+obj-$(CONFIG_CMA) += dma-contiguous.o
+obj-y			+= power/
+obj-$(CONFIG_HAS_DMA)	+= dma-mapping.o
+obj-$(CONFIG_HAVE_GENERIC_DMA_COHERENT) += dma-coherent.o
+obj-$(CONFIG_DMA_SHARED_BUFFER) += dma-buf.o reservation.o
+obj-$(CONFIG_ISA)	+= isa.o
+obj-$(CONFIG_FW_LOADER)	+= firmware_class.o
+obj-$(CONFIG_NUMA)	+= node.o
+obj-$(CONFIG_MEMORY_HOTPLUG_SPARSE) += memory.o
+ifeq ($(CONFIG_SYSFS),y)
+obj-$(CONFIG_MODULES)	+= module.o
+endif
+obj-$(CONFIG_SYS_HYPERVISOR) += hypervisor.o
+obj-$(CONFIG_REGMAP)	+= regmap/
+obj-$(CONFIG_SOC_BUS) += soc.o
+obj-$(CONFIG_PINCTRL) += pinctrl.o
+obj-$(CONFIG_DEV_COREDUMP) += devcoredump.o
+
+ccflags-$(CONFIG_DEBUG_DRIVER) := -DDEBUG
+

drivers/base/attribute_container.c

@@ -0,0 +1,441 @@
+/*
+ * attribute_container.c - implementation of a simple container for classes
+ *
+ * Copyright (c) 2005 - James Bottomley <James.Bottomley@steeleye.com>
+ *
+ * This file is licensed under GPLv2
+ *
+ * The basic idea here is to enable a device to be attached to an
+ * aritrary numer of classes without having to allocate storage for them.
+ * Instead, the contained classes select the devices they need to attach
+ * to via a matching function.
+ */
+
+#include <linux/attribute_container.h>
+#include <linux/init.h>
+#include <linux/device.h>
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/list.h>
+#include <linux/module.h>
+#include <linux/mutex.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 {
+	struct klist_node node;
+	struct attribute_container *cont;
+	struct device classdev;
+};
+
+static void internal_container_klist_get(struct klist_node *n)
+{
+	struct internal_container *ic =
+		container_of(n, struct internal_container, node);
+	get_device(&ic->classdev);
+}
+
+static void internal_container_klist_put(struct klist_node *n)
+{
+	struct internal_container *ic =
+		container_of(n, struct internal_container, node);
+	put_device(&ic->classdev);
+}
+
+
+/**
+ * attribute_container_classdev_to_container - given a classdev, return the container
+ *
+ * @classdev: the class device created by attribute_container_add_device.
+ *
+ * Returns the container associated with this classdev.
+ */
+struct attribute_container *
+attribute_container_classdev_to_container(struct device *classdev)
+{
+	struct internal_container *ic =
+		container_of(classdev, struct internal_container, classdev);
+	return ic->cont;
+}
+EXPORT_SYMBOL_GPL(attribute_container_classdev_to_container);
+
+static LIST_HEAD(attribute_container_list);
+
+static DEFINE_MUTEX(attribute_container_mutex);
+
+/**
+ * attribute_container_register - register an attribute container
+ *
+ * @cont: The container to register.  This must be allocated by the
+ *        callee and should also be zeroed by it.
+ */
+int
+attribute_container_register(struct attribute_container *cont)
+{
+	INIT_LIST_HEAD(&cont->node);
+	klist_init(&cont->containers,internal_container_klist_get,
+		   internal_container_klist_put);
+		
+	mutex_lock(&attribute_container_mutex);
+	list_add_tail(&cont->node, &attribute_container_list);
+	mutex_unlock(&attribute_container_mutex);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(attribute_container_register);
+
+/**
+ * attribute_container_unregister - remove a container registration
+ *
+ * @cont: previously registered container to remove
+ */
+int
+attribute_container_unregister(struct attribute_container *cont)
+{
+	int retval = -EBUSY;
+	mutex_lock(&attribute_container_mutex);
+	spin_lock(&cont->containers.k_lock);
+	if (!list_empty(&cont->containers.k_list))
+		goto out;
+	retval = 0;
+	list_del(&cont->node);
+ out:
+	spin_unlock(&cont->containers.k_lock);
+	mutex_unlock(&attribute_container_mutex);
+	return retval;
+		
+}
+EXPORT_SYMBOL_GPL(attribute_container_unregister);
+
+/* private function used as class release */
+static void attribute_container_release(struct device *classdev)
+{
+	struct internal_container *ic 
+		= container_of(classdev, struct internal_container, classdev);
+	struct device *dev = classdev->parent;
+
+	kfree(ic);
+	put_device(dev);
+}
+
+/**
+ * attribute_container_add_device - see if any container is interested in dev
+ *
+ * @dev: device to add attributes to
+ * @fn:	 function to trigger addition of class device.
+ *
+ * This function allocates storage for the class device(s) to be
+ * attached to dev (one for each matching attribute_container).  If no
+ * fn is provided, the code will simply register the class device via
+ * device_add.  If a function is provided, it is expected to add
+ * the class device at the appropriate time.  One of the things that
+ * might be necessary is to allocate and initialise the classdev and
+ * then add it a later time.  To do this, call this routine for
+ * allocation and initialisation and then use
+ * attribute_container_device_trigger() to call device_add() on
+ * it.  Note: after this, the class device contains a reference to dev
+ * which is not relinquished until the release of the classdev.
+ */
+void
+attribute_container_add_device(struct device *dev,
+			       int (*fn)(struct attribute_container *,
+					 struct device *,
+					 struct device *))
+{
+	struct attribute_container *cont;
+
+	mutex_lock(&attribute_container_mutex);
+	list_for_each_entry(cont, &attribute_container_list, node) {
+		struct internal_container *ic;
+
+		if (attribute_container_no_classdevs(cont))
+			continue;
+
+		if (!cont->match(cont, dev))
+			continue;
+
+		ic = kzalloc(sizeof(*ic), GFP_KERNEL);
+		if (!ic) {
+			dev_err(dev, "failed to allocate class container\n");
+			continue;
+		}
+
+		ic->cont = cont;
+		device_initialize(&ic->classdev);
+		ic->classdev.parent = get_device(dev);
+		ic->classdev.class = cont->class;
+		cont->class->dev_release = attribute_container_release;
+		dev_set_name(&ic->classdev, dev_name(dev));
+		if (fn)
+			fn(cont, dev, &ic->classdev);
+		else
+			attribute_container_add_class_device(&ic->classdev);
+		klist_add_tail(&ic->node, &cont->containers);
+	}
+	mutex_unlock(&attribute_container_mutex);
+}
+
+/* FIXME: can't break out of this unless klist_iter_exit is also
+ * called before doing the break
+ */
+#define klist_for_each_entry(pos, head, member, iter) \
+	for (klist_iter_init(head, iter); (pos = ({ \
+		struct klist_node *n = klist_next(iter); \
+		n ? container_of(n, typeof(*pos), member) : \
+			({ klist_iter_exit(iter) ; NULL; }); \
+	}) ) != NULL; )
+			
+
+/**
+ * attribute_container_remove_device - make device eligible for removal.
+ *
+ * @dev:  The generic device
+ * @fn:	  A function to call to remove the device
+ *
+ * This routine triggers device removal.  If fn is NULL, then it is
+ * simply done via device_unregister (note that if something
+ * still has a reference to the classdev, then the memory occupied
+ * will not be freed until the classdev is released).  If you want a
+ * two phase release: remove from visibility and then delete the
+ * device, then you should use this routine with a fn that calls
+ * device_del() and then use attribute_container_device_trigger()
+ * to do the final put on the classdev.
+ */
+void
+attribute_container_remove_device(struct device *dev,
+				  void (*fn)(struct attribute_container *,
+					     struct device *,
+					     struct device *))
+{
+	struct attribute_container *cont;
+
+	mutex_lock(&attribute_container_mutex);
+	list_for_each_entry(cont, &attribute_container_list, node) {
+		struct internal_container *ic;
+		struct klist_iter iter;
+
+		if (attribute_container_no_classdevs(cont))
+			continue;
+
+		if (!cont->match(cont, dev))
+			continue;
+
+		klist_for_each_entry(ic, &cont->containers, node, &iter) {
+			if (dev != ic->classdev.parent)
+				continue;
+			klist_del(&ic->node);
+			if (fn)
+				fn(cont, dev, &ic->classdev);
+			else {
+				attribute_container_remove_attrs(&ic->classdev);
+				device_unregister(&ic->classdev);
+			}
+		}
+	}
+	mutex_unlock(&attribute_container_mutex);
+}
+
+/**
+ * attribute_container_device_trigger - execute a trigger for each matching classdev
+ *
+ * @dev:  The generic device to run the trigger for
+ * @fn	  the function to execute for each classdev.
+ *
+ * This funcion is for executing a trigger when you need to know both
+ * the container and the classdev.  If you only care about the
+ * container, then use attribute_container_trigger() instead.
+ */
+void
+attribute_container_device_trigger(struct device *dev, 
+				   int (*fn)(struct attribute_container *,
+					     struct device *,
+					     struct device *))
+{
+	struct attribute_container *cont;
+
+	mutex_lock(&attribute_container_mutex);
+	list_for_each_entry(cont, &attribute_container_list, node) {
+		struct internal_container *ic;
+		struct klist_iter iter;
+
+		if (!cont->match(cont, dev))
+			continue;
+
+		if (attribute_container_no_classdevs(cont)) {
+			fn(cont, dev, NULL);
+			continue;
+		}
+
+		klist_for_each_entry(ic, &cont->containers, node, &iter) {
+			if (dev == ic->classdev.parent)
+				fn(cont, dev, &ic->classdev);
+		}
+	}
+	mutex_unlock(&attribute_container_mutex);
+}
+
+/**
+ * attribute_container_trigger - trigger a function for each matching container
+ *
+ * @dev:  The generic device to activate the trigger for
+ * @fn:	  the function to trigger
+ *
+ * This routine triggers a function that only needs to know the
+ * matching containers (not the classdev) associated with a device.
+ * It is more lightweight than attribute_container_device_trigger, so
+ * should be used in preference unless the triggering function
+ * actually needs to know the classdev.
+ */
+void
+attribute_container_trigger(struct device *dev,
+			    int (*fn)(struct attribute_container *,
+				      struct device *))
+{
+	struct attribute_container *cont;
+
+	mutex_lock(&attribute_container_mutex);
+	list_for_each_entry(cont, &attribute_container_list, node) {
+		if (cont->match(cont, dev))
+			fn(cont, dev);
+	}
+	mutex_unlock(&attribute_container_mutex);
+}
+
+/**
+ * attribute_container_add_attrs - add attributes
+ *
+ * @classdev: The class device
+ *
+ * This simply creates all the class device sysfs files from the
+ * attributes listed in the container
+ */
+int
+attribute_container_add_attrs(struct device *classdev)
+{
+	struct attribute_container *cont =
+		attribute_container_classdev_to_container(classdev);
+	struct device_attribute **attrs = cont->attrs;
+	int i, error;
+
+	BUG_ON(attrs && cont->grp);
+
+	if (!attrs && !cont->grp)
+		return 0;
+
+	if (cont->grp)
+		return sysfs_create_group(&classdev->kobj, cont->grp);
+
+	for (i = 0; attrs[i]; i++) {
+		sysfs_attr_init(&attrs[i]->attr);
+		error = device_create_file(classdev, attrs[i]);
+		if (error)
+			return error;
+	}
+
+	return 0;
+}
+
+/**
+ * attribute_container_add_class_device - same function as device_add
+ *
+ * @classdev:	the class device to add
+ *
+ * This performs essentially the same function as device_add except for
+ * attribute containers, namely add the classdev to the system and then
+ * create the attribute files
+ */
+int
+attribute_container_add_class_device(struct device *classdev)
+{
+	int error = device_add(classdev);
+	if (error)
+		return error;
+	return attribute_container_add_attrs(classdev);
+}
+
+/**
+ * attribute_container_add_class_device_adapter - simple adapter for triggers
+ *
+ * This function is identical to attribute_container_add_class_device except
+ * that it is designed to be called from the triggers
+ */
+int
+attribute_container_add_class_device_adapter(struct attribute_container *cont,
+					     struct device *dev,
+					     struct device *classdev)
+{
+	return attribute_container_add_class_device(classdev);
+}
+
+/**
+ * attribute_container_remove_attrs - remove any attribute files
+ *
+ * @classdev: The class device to remove the files from
+ *
+ */
+void
+attribute_container_remove_attrs(struct device *classdev)
+{
+	struct attribute_container *cont =
+		attribute_container_classdev_to_container(classdev);
+	struct device_attribute **attrs = cont->attrs;
+	int i;
+
+	if (!attrs && !cont->grp)
+		return;
+
+	if (cont->grp) {
+		sysfs_remove_group(&classdev->kobj, cont->grp);
+		return ;
+	}
+
+	for (i = 0; attrs[i]; i++)
+		device_remove_file(classdev, attrs[i]);
+}
+
+/**
+ * attribute_container_class_device_del - equivalent of class_device_del
+ *
+ * @classdev: the class device
+ *
+ * This function simply removes all the attribute files and then calls
+ * device_del.
+ */
+void
+attribute_container_class_device_del(struct device *classdev)
+{
+	attribute_container_remove_attrs(classdev);
+	device_del(classdev);
+}
+
+/**
+ * attribute_container_find_class_device - find the corresponding class_device
+ *
+ * @cont:	the container
+ * @dev:	the generic device
+ *
+ * Looks up the device in the container's list of class devices and returns
+ * the corresponding class_device.
+ */
+struct device *
+attribute_container_find_class_device(struct attribute_container *cont,
+				      struct device *dev)
+{
+	struct device *cdev = NULL;
+	struct internal_container *ic;
+	struct klist_iter iter;
+
+	klist_for_each_entry(ic, &cont->containers, node, &iter) {
+		if (ic->classdev.parent == dev) {
+			cdev = &ic->classdev;
+			/* FIXME: must exit iterator then break */
+			klist_iter_exit(&iter);
+			break;
+		}
+	}
+
+	return cdev;
+}
+EXPORT_SYMBOL_GPL(attribute_container_find_class_device);

drivers/base/base.h

@@ -0,0 +1,142 @@
+#include <linux/notifier.h>
+
+/**
+ * struct subsys_private - structure to hold the private to the driver core portions of the bus_type/class structure.
+ *
+ * @subsys - the struct kset that defines this subsystem
+ * @devices_kset - the subsystem's 'devices' directory
+ * @interfaces - list of subsystem interfaces associated
+ * @mutex - protect the devices, and interfaces lists.
+ *
+ * @drivers_kset - the list of drivers associated
+ * @klist_devices - the klist to iterate over the @devices_kset
+ * @klist_drivers - the klist to iterate over the @drivers_kset
+ * @bus_notifier - the bus notifier list for anything that cares about things
+ *                 on this bus.
+ * @bus - pointer back to the struct bus_type that this structure is associated
+ *        with.
+ *
+ * @glue_dirs - "glue" directory to put in-between the parent device to
+ *              avoid namespace conflicts
+ * @class - pointer back to the struct class that this structure is associated
+ *          with.
+ *
+ * This structure is the one that is the actual kobject allowing struct
+ * bus_type/class to be statically allocated safely.  Nothing outside of the
+ * driver core should ever touch these fields.
+ */
+struct subsys_private {
+	struct kset subsys;
+	struct kset *devices_kset;
+	struct list_head interfaces;
+	struct mutex mutex;
+
+	struct kset *drivers_kset;
+	struct klist klist_devices;
+	struct klist klist_drivers;
+	struct blocking_notifier_head bus_notifier;
+	unsigned int drivers_autoprobe:1;
+	struct bus_type *bus;
+
+	struct kset glue_dirs;
+	struct class *class;
+};
+#define to_subsys_private(obj) container_of(obj, struct subsys_private, subsys.kobj)
+
+struct driver_private {
+	struct kobject kobj;
+	struct klist klist_devices;
+	struct klist_node knode_bus;
+	struct module_kobject *mkobj;
+	struct device_driver *driver;
+};
+#define to_driver(obj) container_of(obj, struct driver_private, kobj)
+
+/**
+ * struct device_private - structure to hold the private to the driver core portions of the device structure.
+ *
+ * @klist_children - klist containing all children of this device
+ * @knode_parent - node in sibling list
+ * @knode_driver - node in driver list
+ * @knode_bus - node in bus list
+ * @deferred_probe - entry in deferred_probe_list which is used to retry the
+ *	binding of drivers which were unable to get all the resources needed by
+ *	the device; typically because it depends on another driver getting
+ *	probed first.
+ * @driver_data - private pointer for driver specific info.  Will turn into a
+ * list soon.
+ * @device - pointer back to the struct class that this structure is
+ * associated with.
+ *
+ * Nothing outside of the driver core should ever touch these fields.
+ */
+struct device_private {
+	struct klist klist_children;
+	struct klist_node knode_parent;
+	struct klist_node knode_driver;
+	struct klist_node knode_bus;
+	struct list_head deferred_probe;
+	void *driver_data;
+	struct device *device;
+};
+#define to_device_private_parent(obj)	\
+	container_of(obj, struct device_private, knode_parent)
+#define to_device_private_driver(obj)	\
+	container_of(obj, struct device_private, knode_driver)
+#define to_device_private_bus(obj)	\
+	container_of(obj, struct device_private, knode_bus)
+
+extern int device_private_init(struct device *dev);
+
+/* initialisation functions */
+extern int devices_init(void);
+extern int buses_init(void);
+extern int classes_init(void);
+extern int firmware_init(void);
+#ifdef CONFIG_SYS_HYPERVISOR
+extern int hypervisor_init(void);
+#else
+static inline int hypervisor_init(void) { return 0; }
+#endif
+extern int platform_bus_init(void);
+extern void cpu_dev_init(void);
+
+struct kobject *virtual_device_parent(struct device *dev);
+
+extern int bus_add_device(struct device *dev);
+extern void bus_probe_device(struct device *dev);
+extern void bus_remove_device(struct device *dev);
+
+extern int bus_add_driver(struct device_driver *drv);
+extern void bus_remove_driver(struct device_driver *drv);
+
+extern void driver_detach(struct device_driver *drv);
+extern int driver_probe_device(struct device_driver *drv, struct device *dev);
+extern void driver_deferred_probe_del(struct device *dev);
+static inline int driver_match_device(struct device_driver *drv,
+				      struct device *dev)
+{
+	return drv->bus->match ? drv->bus->match(dev, drv) : 1;
+}
+
+extern char *make_class_name(const char *name, struct kobject *kobj);
+
+extern int devres_release_all(struct device *dev);
+
+/* /sys/devices directory */
+extern struct kset *devices_kset;
+
+#if defined(CONFIG_MODULES) && defined(CONFIG_SYSFS)
+extern void module_add_driver(struct module *mod, struct device_driver *drv);
+extern void module_remove_driver(struct device_driver *drv);
+#else
+static inline void module_add_driver(struct module *mod,
+				     struct device_driver *drv) { }
+static inline void module_remove_driver(struct device_driver *drv) { }
+#endif
+
+#ifdef CONFIG_DEVTMPFS
+extern int devtmpfs_init(void);
+#else
+static inline int devtmpfs_init(void) { return 0; }
+#endif

drivers/base/class.c

@@ -0,0 +1,609 @@
+/*
+ * class.c - basic device class management
+ *
+ * Copyright (c) 2002-3 Patrick Mochel
+ * Copyright (c) 2002-3 Open Source Development Labs
+ * Copyright (c) 2003-2004 Greg Kroah-Hartman
+ * Copyright (c) 2003-2004 IBM Corp.
+ *
+ * This file is released under the GPLv2
+ *
+ */
+
+#include <linux/device.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/string.h>
+#include <linux/kdev_t.h>
+#include <linux/err.h>
+#include <linux/slab.h>
+#include <linux/genhd.h>
+#include <linux/mutex.h>
+#include "base.h"
+
+#define to_class_attr(_attr) container_of(_attr, struct class_attribute, attr)
+
+static ssize_t class_attr_show(struct kobject *kobj, struct attribute *attr,
+			       char *buf)
+{
+	struct class_attribute *class_attr = to_class_attr(attr);
+	struct subsys_private *cp = to_subsys_private(kobj);
+	ssize_t ret = -EIO;
+
+	if (class_attr->show)
+		ret = class_attr->show(cp->class, class_attr, buf);
+	return ret;
+}
+
+static ssize_t class_attr_store(struct kobject *kobj, struct attribute *attr,
+				const char *buf, size_t count)
+{
+	struct class_attribute *class_attr = to_class_attr(attr);
+	struct subsys_private *cp = to_subsys_private(kobj);
+	ssize_t ret = -EIO;
+
+	if (class_attr->store)
+		ret = class_attr->store(cp->class, class_attr, buf, count);
+	return ret;
+}
+
+static const void *class_attr_namespace(struct kobject *kobj,
+					const struct attribute *attr)
+{
+	struct class_attribute *class_attr = to_class_attr(attr);
+	struct subsys_private *cp = to_subsys_private(kobj);
+	const void *ns = NULL;
+
+	if (class_attr->namespace)
+		ns = class_attr->namespace(cp->class, class_attr);
+	return ns;
+}
+
+static void class_release(struct kobject *kobj)
+{
+	struct subsys_private *cp = to_subsys_private(kobj);
+	struct class *class = cp->class;
+
+	pr_debug("class '%s': release.\n", class->name);
+
+	if (class->class_release)
+		class->class_release(class);
+	else
+		pr_debug("class '%s' does not have a release() function, "
+			 "be careful\n", class->name);
+
+	kfree(cp);
+}
+
+static const struct kobj_ns_type_operations *class_child_ns_type(struct kobject *kobj)
+{
+	struct subsys_private *cp = to_subsys_private(kobj);
+	struct class *class = cp->class;
+
+	return class->ns_type;
+}
+
+static const struct sysfs_ops class_sysfs_ops = {
+	.show	   = class_attr_show,
+	.store	   = class_attr_store,
+	.namespace = class_attr_namespace,
+};
+
+static struct kobj_type class_ktype = {
+	.sysfs_ops	= &class_sysfs_ops,
+	.release	= class_release,
+	.child_ns_type	= class_child_ns_type,
+};
+
+/* Hotplug events for classes go to the class subsys */
+static struct kset *class_kset;
+
+
+int class_create_file(struct class *cls, const struct class_attribute *attr)
+{
+	int error;
+	if (cls)
+		error = sysfs_create_file(&cls->p->subsys.kobj,
+					  &attr->attr);
+	else
+		error = -EINVAL;
+	return error;
+}
+
+void class_remove_file(struct class *cls, const struct class_attribute *attr)
+{
+	if (cls)
+		sysfs_remove_file(&cls->p->subsys.kobj, &attr->attr);
+}
+
+static struct class *class_get(struct class *cls)
+{
+	if (cls)
+		kset_get(&cls->p->subsys);
+	return cls;
+}
+
+static void class_put(struct class *cls)
+{
+	if (cls)
+		kset_put(&cls->p->subsys);
+}
+
+static int add_class_attrs(struct class *cls)
+{
+	int i;
+	int error = 0;
+
+	if (cls->class_attrs) {
+		for (i = 0; attr_name(cls->class_attrs[i]); i++) {
+			error = class_create_file(cls, &cls->class_attrs[i]);
+			if (error)
+				goto error;
+		}
+	}
+done:
+	return error;
+error:
+	while (--i >= 0)
+		class_remove_file(cls, &cls->class_attrs[i]);
+	goto done;
+}
+
+static void remove_class_attrs(struct class *cls)
+{
+	int i;
+
+	if (cls->class_attrs) {
+		for (i = 0; attr_name(cls->class_attrs[i]); i++)
+			class_remove_file(cls, &cls->class_attrs[i]);
+	}
+}
+
+static void klist_class_dev_get(struct klist_node *n)
+{
+	struct device *dev = container_of(n, struct device, knode_class);
+
+	get_device(dev);
+}
+
+static void klist_class_dev_put(struct klist_node *n)
+{
+	struct device *dev = container_of(n, struct device, knode_class);
+
+	put_device(dev);
+}
+
+int __class_register(struct class *cls, struct lock_class_key *key)
+{
+	struct subsys_private *cp;
+	int error;
+
+	pr_debug("device class '%s': registering\n", cls->name);
+
+	cp = kzalloc(sizeof(*cp), GFP_KERNEL);
+	if (!cp)
+		return -ENOMEM;
+	klist_init(&cp->klist_devices, klist_class_dev_get, klist_class_dev_put);
+	INIT_LIST_HEAD(&cp->interfaces);
+	kset_init(&cp->glue_dirs);
+	__mutex_init(&cp->mutex, "subsys mutex", key);
+	error = kobject_set_name(&cp->subsys.kobj, "%s", cls->name);
+	if (error) {
+		kfree(cp);
+		return error;
+	}
+
+	/* set the default /sys/dev directory for devices of this class */
+	if (!cls->dev_kobj)
+		cls->dev_kobj = sysfs_dev_char_kobj;
+
+#if defined(CONFIG_BLOCK)
+	/* let the block class directory show up in the root of sysfs */
+	if (!sysfs_deprecated || cls != &block_class)
+		cp->subsys.kobj.kset = class_kset;
+#else
+	cp->subsys.kobj.kset = class_kset;
+#endif
+	cp->subsys.kobj.ktype = &class_ktype;
+	cp->class = cls;
+	cls->p = cp;
+
+	error = kset_register(&cp->subsys);
+	if (error) {
+		kfree(cp);
+		return error;
+	}
+	error = add_class_attrs(class_get(cls));
+	class_put(cls);
+	return error;
+}
+EXPORT_SYMBOL_GPL(__class_register);
+
+void class_unregister(struct class *cls)
+{
+	pr_debug("device class '%s': unregistering\n", cls->name);
+	remove_class_attrs(cls);
+	kset_unregister(&cls->p->subsys);
+}
+
+static void class_create_release(struct class *cls)
+{
+	pr_debug("%s called for %s\n", __func__, cls->name);
+	kfree(cls);
+}
+
+/**
+ * class_create - create a struct class structure
+ * @owner: pointer to the module that is to "own" this struct class
+ * @name: pointer to a string for the name of this class.
+ * @key: the lock_class_key for this class; used by mutex lock debugging
+ *
+ * This is used to create a struct class pointer that can then be used
+ * in calls to device_create().
+ *
+ * Returns &struct class pointer on success, or ERR_PTR() on error.
+ *
+ * Note, the pointer created here is to be destroyed when finished by
+ * making a call to class_destroy().
+ */
+struct class *__class_create(struct module *owner, const char *name,
+			     struct lock_class_key *key)
+{
+	struct class *cls;
+	int retval;
+
+	cls = kzalloc(sizeof(*cls), GFP_KERNEL);
+	if (!cls) {
+		retval = -ENOMEM;
+		goto error;
+	}
+
+	cls->name = name;
+	cls->owner = owner;
+	cls->class_release = class_create_release;
+
+	retval = __class_register(cls, key);
+	if (retval)
+		goto error;
+
+	return cls;
+
+error:
+	kfree(cls);
+	return ERR_PTR(retval);
+}
+EXPORT_SYMBOL_GPL(__class_create);
+
+/**
+ * class_destroy - destroys a struct class structure
+ * @cls: pointer to the struct class that is to be destroyed
+ *
+ * Note, the pointer to be destroyed must have been created with a call
+ * to class_create().
+ */
+void class_destroy(struct class *cls)
+{
+	if ((cls == NULL) || (IS_ERR(cls)))
+		return;
+
+	class_unregister(cls);
+}
+
+/**
+ * class_dev_iter_init - initialize class device iterator
+ * @iter: class iterator to initialize
+ * @class: the class we wanna iterate over
+ * @start: the device to start iterating from, if any
+ * @type: device_type of the devices to iterate over, NULL for all
+ *
+ * Initialize class iterator @iter such that it iterates over devices
+ * of @class.  If @start is set, the list iteration will start there,
+ * otherwise if it is NULL, the iteration starts at the beginning of
+ * the list.
+ */
+void class_dev_iter_init(struct class_dev_iter *iter, struct class *class,
+			 struct device *start, const struct device_type *type)
+{
+	struct klist_node *start_knode = NULL;
+
+	if (start)
+		start_knode = &start->knode_class;
+	klist_iter_init_node(&class->p->klist_devices, &iter->ki, start_knode);
+	iter->type = type;
+}
+EXPORT_SYMBOL_GPL(class_dev_iter_init);
+
+/**
+ * class_dev_iter_next - iterate to the next device
+ * @iter: class iterator to proceed
+ *
+ * Proceed @iter to the next device and return it.  Returns NULL if
+ * iteration is complete.
+ *
+ * The returned device is referenced and won't be released till
+ * iterator is proceed to the next device or exited.  The caller is
+ * free to do whatever it wants to do with the device including
+ * calling back into class code.
+ */
+struct device *class_dev_iter_next(struct class_dev_iter *iter)
+{
+	struct klist_node *knode;
+	struct device *dev;
+
+	while (1) {
+		knode = klist_next(&iter->ki);
+		if (!knode)
+			return NULL;
+		dev = container_of(knode, struct device, knode_class);
+		if (!iter->type || iter->type == dev->type)
+			return dev;
+	}
+}
+EXPORT_SYMBOL_GPL(class_dev_iter_next);
+
+/**
+ * class_dev_iter_exit - finish iteration
+ * @iter: class iterator to finish
+ *
+ * Finish an iteration.  Always call this function after iteration is
+ * complete whether the iteration ran till the end or not.
+ */
+void class_dev_iter_exit(struct class_dev_iter *iter)
+{
+	klist_iter_exit(&iter->ki);
+}
+EXPORT_SYMBOL_GPL(class_dev_iter_exit);
+
+/**
+ * class_for_each_device - device iterator
+ * @class: the class we're iterating
+ * @start: the device to start with in the list, if any.
+ * @data: data for the callback
+ * @fn: function to be called for each device
+ *
+ * Iterate over @class's list of devices, and call @fn for each,
+ * passing it @data.  If @start is set, the list iteration will start
+ * there, otherwise if it is NULL, the iteration starts at the
+ * beginning of the list.
+ *
+ * We check the return of @fn each time. If it returns anything
+ * other than 0, we break out and return that value.
+ *
+ * @fn is allowed to do anything including calling back into class
+ * code.  There's no locking restriction.
+ */
+int class_for_each_device(struct class *class, struct device *start,
+			  void *data, int (*fn)(struct device *, void *))
+{
+	struct class_dev_iter iter;
+	struct device *dev;
+	int error = 0;
+
+	if (!class)
+		return -EINVAL;
+	if (!class->p) {
+		WARN(1, "%s called for class '%s' before it was initialized",
+		     __func__, class->name);
+		return -EINVAL;
+	}
+
+	class_dev_iter_init(&iter, class, start, NULL);
+	while ((dev = class_dev_iter_next(&iter))) {
+		error = fn(dev, data);
+		if (error)
+			break;
+	}
+	class_dev_iter_exit(&iter);
+
+	return error;
+}
+EXPORT_SYMBOL_GPL(class_for_each_device);
+
+/**
+ * class_find_device - device iterator for locating a particular device
+ * @class: the class we're iterating
+ * @start: Device to begin with
+ * @data: data for the match function
+ * @match: function to check device
+ *
+ * This is similar to the class_for_each_dev() function above, but it
+ * returns a reference to a device that is 'found' for later use, as
+ * determined by the @match callback.
+ *
+ * The callback should return 0 if the device doesn't match and non-zero
+ * if it does.  If the callback returns non-zero, this function will
+ * return to the caller and not iterate over any more devices.
+ *
+ * Note, you will need to drop the reference with put_device() after use.
+ *
+ * @fn is allowed to do anything including calling back into class
+ * code.  There's no locking restriction.
+ */
+struct device *class_find_device(struct class *class, struct device *start,
+				 const void *data,
+				 int (*match)(struct device *, const void *))
+{
+	struct class_dev_iter iter;
+	struct device *dev;
+
+	if (!class)
+		return NULL;
+	if (!class->p) {
+		WARN(1, "%s called for class '%s' before it was initialized",
+		     __func__, class->name);
+		return NULL;
+	}
+
+	class_dev_iter_init(&iter, class, start, NULL);
+	while ((dev = class_dev_iter_next(&iter))) {
+		if (match(dev, data)) {
+			get_device(dev);
+			break;
+		}
+	}
+	class_dev_iter_exit(&iter);
+
+	return dev;
+}
+EXPORT_SYMBOL_GPL(class_find_device);
+
+int class_interface_register(struct class_interface *class_intf)
+{
+	struct class *parent;
+	struct class_dev_iter iter;
+	struct device *dev;
+
+	if (!class_intf || !class_intf->class)
+		return -ENODEV;
+
+	parent = class_get(class_intf->class);
+	if (!parent)
+		return -EINVAL;
+
+	mutex_lock(&parent->p->mutex);
+	list_add_tail(&class_intf->node, &parent->p->interfaces);
+	if (class_intf->add_dev) {
+		class_dev_iter_init(&iter, parent, NULL, NULL);
+		while ((dev = class_dev_iter_next(&iter)))
+			class_intf->add_dev(dev, class_intf);
+		class_dev_iter_exit(&iter);
+	}
+	mutex_unlock(&parent->p->mutex);
+
+	return 0;
+}
+
+void class_interface_unregister(struct class_interface *class_intf)
+{
+	struct class *parent = class_intf->class;
+	struct class_dev_iter iter;
+	struct device *dev;
+
+	if (!parent)
+		return;
+
+	mutex_lock(&parent->p->mutex);
+	list_del_init(&class_intf->node);
+	if (class_intf->remove_dev) {
+		class_dev_iter_init(&iter, parent, NULL, NULL);
+		while ((dev = class_dev_iter_next(&iter)))
+			class_intf->remove_dev(dev, class_intf);
+		class_dev_iter_exit(&iter);
+	}
+	mutex_unlock(&parent->p->mutex);
+
+	class_put(parent);
+}
+
+ssize_t show_class_attr_string(struct class *class,
+			       struct class_attribute *attr, char *buf)
+{
+	struct class_attribute_string *cs;
+	cs = container_of(attr, struct class_attribute_string, attr);
+	return snprintf(buf, PAGE_SIZE, "%s\n", cs->str);
+}
+
+EXPORT_SYMBOL_GPL(show_class_attr_string);
+
+struct class_compat {
+	struct kobject *kobj;
+};
+
+/**
+ * class_compat_register - register a compatibility class
+ * @name: the name of the class
+ *
+ * Compatibility class are meant as a temporary user-space compatibility
+ * workaround when converting a family of class devices to a bus devices.
+ */
+struct class_compat *class_compat_register(const char *name)
+{
+	struct class_compat *cls;
+
+	cls = kmalloc(sizeof(struct class_compat), GFP_KERNEL);
+	if (!cls)
+		return NULL;
+	cls->kobj = kobject_create_and_add(name, &class_kset->kobj);
+	if (!cls->kobj) {
+		kfree(cls);
+		return NULL;
+	}
+	return cls;
+}
+EXPORT_SYMBOL_GPL(class_compat_register);
+
+/**
+ * class_compat_unregister - unregister a compatibility class
+ * @cls: the class to unregister
+ */
+void class_compat_unregister(struct class_compat *cls)
+{
+	kobject_put(cls->kobj);
+	kfree(cls);
+}
+EXPORT_SYMBOL_GPL(class_compat_unregister);
+
+/**
+ * class_compat_create_link - create a compatibility class device link to
+ *			      a bus device
+ * @cls: the compatibility class
+ * @dev: the target bus device
+ * @device_link: an optional device to which a "device" link should be created
+ */
+int class_compat_create_link(struct class_compat *cls, struct device *dev,
+			     struct device *device_link)
+{
+	int error;
+
+	error = sysfs_create_link(cls->kobj, &dev->kobj, dev_name(dev));
+	if (error)
+		return error;
+
+	/*
+	 * Optionally add a "device" link (typically to the parent), as a
+	 * class device would have one and we want to provide as much
+	 * backwards compatibility as possible.
+	 */
+	if (device_link) {
+		error = sysfs_create_link(&dev->kobj, &device_link->kobj,
+					  "device");
+		if (error)
+			sysfs_remove_link(cls->kobj, dev_name(dev));
+	}
+
+	return error;
+}
+EXPORT_SYMBOL_GPL(class_compat_create_link);
+
+/**
+ * class_compat_remove_link - remove a compatibility class device link to
+ *			      a bus device
+ * @cls: the compatibility class
+ * @dev: the target bus device
+ * @device_link: an optional device to which a "device" link was previously
+ * 		 created
+ */
+void class_compat_remove_link(struct class_compat *cls, struct device *dev,
+			      struct device *device_link)
+{
+	if (device_link)
+		sysfs_remove_link(&dev->kobj, "device");
+	sysfs_remove_link(cls->kobj, dev_name(dev));
+}
+EXPORT_SYMBOL_GPL(class_compat_remove_link);
+
+int __init classes_init(void)
+{
+	class_kset = kset_create_and_add("class", NULL, NULL);
+	if (!class_kset)
+		return -ENOMEM;
+	return 0;
+}
+
+EXPORT_SYMBOL_GPL(class_create_file);
+EXPORT_SYMBOL_GPL(class_remove_file);
+EXPORT_SYMBOL_GPL(class_unregister);
+EXPORT_SYMBOL_GPL(class_destroy);
+
+EXPORT_SYMBOL_GPL(class_interface_register);
+EXPORT_SYMBOL_GPL(class_interface_unregister);

drivers/base/cpu.c

@@ -0,0 +1,368 @@
+/*
+ * CPU subsystem support
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/sched.h>
+#include <linux/cpu.h>
+#include <linux/topology.h>
+#include <linux/device.h>
+#include <linux/node.h>
+#include <linux/gfp.h>
+#include <linux/slab.h>
+#include <linux/percpu.h>
+
+#include "base.h"
+
+struct bus_type cpu_subsys = {
+	.name = "cpu",
+	.dev_name = "cpu",
+};
+EXPORT_SYMBOL_GPL(cpu_subsys);
+
+static DEFINE_PER_CPU(struct device *, cpu_sys_devices);
+
+#ifdef CONFIG_HOTPLUG_CPU
+static void change_cpu_under_node(struct cpu *cpu,
+			unsigned int from_nid, unsigned int to_nid)
+{
+	int cpuid = cpu->dev.id;
+	unregister_cpu_under_node(cpuid, from_nid);
+	register_cpu_under_node(cpuid, to_nid);
+	cpu->node_id = to_nid;
+}
+
+static ssize_t show_online(struct device *dev,
+			   struct device_attribute *attr,
+			   char *buf)
+{
+	struct cpu *cpu = container_of(dev, struct cpu, dev);
+
+	return sprintf(buf, "%u\n", !!cpu_online(cpu->dev.id));
+}
+
+static ssize_t __ref store_online(struct device *dev,
+				  struct device_attribute *attr,
+				  const char *buf, size_t count)
+{
+	struct cpu *cpu = container_of(dev, struct cpu, dev);
+	int cpuid = cpu->dev.id;
+	int from_nid, to_nid;
+	ssize_t ret;
+
+	cpu_hotplug_driver_lock();
+	switch (buf[0]) {
+	case '0':
+		ret = cpu_down(cpuid);
+		if (!ret)
+			kobject_uevent(&dev->kobj, KOBJ_OFFLINE);
+		break;
+	case '1':
+		from_nid = cpu_to_node(cpuid);
+		ret = cpu_up(cpuid);
+
+		/*
+		 * When hot adding memory to memoryless node and enabling a cpu
+		 * on the node, node number of the cpu may internally change.
+		 */
+		to_nid = cpu_to_node(cpuid);
+		if (from_nid != to_nid)
+			change_cpu_under_node(cpu, from_nid, to_nid);
+
+		if (!ret)
+			kobject_uevent(&dev->kobj, KOBJ_ONLINE);
+		break;
+	default:
+		ret = -EINVAL;
+	}
+	cpu_hotplug_driver_unlock();
+
+	if (ret >= 0)
+		ret = count;
+	return ret;
+}
+static DEVICE_ATTR(online, 0644, show_online, store_online);
+
+static void __cpuinit register_cpu_control(struct cpu *cpu)
+{
+	device_create_file(&cpu->dev, &dev_attr_online);
+}
+void unregister_cpu(struct cpu *cpu)
+{
+	int logical_cpu = cpu->dev.id;
+
+	unregister_cpu_under_node(logical_cpu, cpu_to_node(logical_cpu));
+
+	device_remove_file(&cpu->dev, &dev_attr_online);
+
+	device_unregister(&cpu->dev);
+	per_cpu(cpu_sys_devices, logical_cpu) = NULL;
+	return;
+}
+
+#ifdef CONFIG_ARCH_CPU_PROBE_RELEASE
+static ssize_t cpu_probe_store(struct device *dev,
+			       struct device_attribute *attr,
+			       const char *buf,
+			       size_t count)
+{
+	return arch_cpu_probe(buf, count);
+}
+
+static ssize_t cpu_release_store(struct device *dev,
+				 struct device_attribute *attr,
+				 const char *buf,
+				 size_t count)
+{
+	return arch_cpu_release(buf, count);
+}
+
+static DEVICE_ATTR(probe, S_IWUSR, NULL, cpu_probe_store);
+static DEVICE_ATTR(release, S_IWUSR, NULL, cpu_release_store);
+#endif /* CONFIG_ARCH_CPU_PROBE_RELEASE */
+
+#else /* ... !CONFIG_HOTPLUG_CPU */
+static inline void register_cpu_control(struct cpu *cpu)
+{
+}
+#endif /* CONFIG_HOTPLUG_CPU */
+
+#ifdef CONFIG_KEXEC
+#include <linux/kexec.h>
+
+static ssize_t show_crash_notes(struct device *dev, struct device_attribute *attr,
+				char *buf)
+{
+	struct cpu *cpu = container_of(dev, struct cpu, dev);
+	ssize_t rc;
+	unsigned long long addr;
+	int cpunum;
+
+	cpunum = cpu->dev.id;
+
+	/*
+	 * Might be reading other cpu's data based on which cpu read thread
+	 * has been scheduled. But cpu data (memory) is allocated once during
+	 * boot up and this data does not change there after. Hence this
+	 * operation should be safe. No locking required.
+	 */
+	addr = per_cpu_ptr_to_phys(per_cpu_ptr(crash_notes, cpunum));
+	rc = sprintf(buf, "%Lx\n", addr);
+	return rc;
+}
+static DEVICE_ATTR(crash_notes, 0400, show_crash_notes, NULL);
+
+static ssize_t show_crash_notes_size(struct device *dev,
+				     struct device_attribute *attr,
+				     char *buf)
+{
+	ssize_t rc;
+
+	rc = sprintf(buf, "%zu\n", sizeof(note_buf_t));
+	return rc;
+}
+static DEVICE_ATTR(crash_notes_size, 0400, show_crash_notes_size, NULL);
+#endif
+
+/*
+ * Print cpu online, possible, present, and system maps
+ */
+
+struct cpu_attr {
+	struct device_attribute attr;
+	const struct cpumask *const * const map;
+};
+
+static ssize_t show_cpus_attr(struct device *dev,
+			      struct device_attribute *attr,
+			      char *buf)
+{
+	struct cpu_attr *ca = container_of(attr, struct cpu_attr, attr);
+	int n = cpulist_scnprintf(buf, PAGE_SIZE-2, *(ca->map));
+
+	buf[n++] = '\n';
+	buf[n] = '\0';
+	return n;
+}
+
+#define _CPU_ATTR(name, map) \
+	{ __ATTR(name, 0444, show_cpus_attr, NULL), map }
+
+/* Keep in sync with cpu_subsys_attrs */
+static struct cpu_attr cpu_attrs[] = {
+	_CPU_ATTR(online, &cpu_online_mask),
+	_CPU_ATTR(possible, &cpu_possible_mask),
+	_CPU_ATTR(present, &cpu_present_mask),
+};
+
+/*
+ * Print values for NR_CPUS and offlined cpus
+ */
+static ssize_t print_cpus_kernel_max(struct device *dev,
+				     struct device_attribute *attr, char *buf)
+{
+	int n = snprintf(buf, PAGE_SIZE-2, "%d\n", NR_CPUS - 1);
+	return n;
+}
+static DEVICE_ATTR(kernel_max, 0444, print_cpus_kernel_max, NULL);
+
+/* arch-optional setting to enable display of offline cpus >= nr_cpu_ids */
+unsigned int total_cpus;
+
+static ssize_t print_cpus_offline(struct device *dev,
+				  struct device_attribute *attr, char *buf)
+{
+	int n = 0, len = PAGE_SIZE-2;
+	cpumask_var_t offline;
+
+	/* display offline cpus < nr_cpu_ids */
+	if (!alloc_cpumask_var(&offline, GFP_KERNEL))
+		return -ENOMEM;
+	cpumask_andnot(offline, cpu_possible_mask, cpu_online_mask);
+	n = cpulist_scnprintf(buf, len, offline);
+	free_cpumask_var(offline);
+
+	/* display offline cpus >= nr_cpu_ids */
+	if (total_cpus && nr_cpu_ids < total_cpus) {
+		if (n && n < len)
+			buf[n++] = ',';
+
+		if (nr_cpu_ids == total_cpus-1)
+			n += snprintf(&buf[n], len - n, "%d", nr_cpu_ids);
+		else
+			n += snprintf(&buf[n], len - n, "%d-%d",
+						      nr_cpu_ids, total_cpus-1);
+	}
+
+	n += snprintf(&buf[n], len - n, "\n");
+	return n;
+}
+static DEVICE_ATTR(offline, 0444, print_cpus_offline, NULL);
+
+static void cpu_device_release(struct device *dev)
+{
+	/*
+	 * This is an empty function to prevent the driver core from spitting a
+	 * warning at us.  Yes, I know this is directly opposite of what the
+	 * documentation for the driver core and kobjects say, and the author
+	 * of this code has already been publically ridiculed for doing
+	 * something as foolish as this.  However, at this point in time, it is
+	 * the only way to handle the issue of statically allocated cpu
+	 * devices.  The different architectures will have their cpu device
+	 * code reworked to properly handle this in the near future, so this
+	 * function will then be changed to correctly free up the memory held
+	 * by the cpu device.
+	 *
+	 * Never copy this way of doing things, or you too will be made fun of
+	 * on the linux-kernel list, you have been warned.
+	 */
+}
+
+/*
+ * register_cpu - Setup a sysfs device for a CPU.
+ * @cpu - cpu->hotpluggable field set to 1 will generate a control file in
+ *	  sysfs for this CPU.
+ * @num - CPU number to use when creating the device.
+ *
+ * Initialize and register the CPU device.
+ */
+int __cpuinit register_cpu(struct cpu *cpu, int num)
+{
+	int error;
+
+	cpu->node_id = cpu_to_node(num);
+	memset(&cpu->dev, 0x00, sizeof(struct device));
+	cpu->dev.id = num;
+	cpu->dev.bus = &cpu_subsys;
+	cpu->dev.release = cpu_device_release;
+#ifdef CONFIG_ARCH_HAS_CPU_AUTOPROBE
+	cpu->dev.bus->uevent = arch_cpu_uevent;
+#endif
+	error = device_register(&cpu->dev);
+	if (!error && cpu->hotpluggable)
+		register_cpu_control(cpu);
+	if (!error)
+		per_cpu(cpu_sys_devices, num) = &cpu->dev;
+	if (!error)
+		register_cpu_under_node(num, cpu_to_node(num));
+
+#ifdef CONFIG_KEXEC
+	if (!error)
+		error = device_create_file(&cpu->dev, &dev_attr_crash_notes);
+	if (!error)
+		error = device_create_file(&cpu->dev,
+					   &dev_attr_crash_notes_size);
+#endif
+	return error;
+}
+
+struct device *get_cpu_device(unsigned cpu)
+{
+	if (cpu < nr_cpu_ids && cpu_possible(cpu))
+		return per_cpu(cpu_sys_devices, cpu);
+	else
+		return NULL;
+}
+EXPORT_SYMBOL_GPL(get_cpu_device);
+
+#ifdef CONFIG_ARCH_HAS_CPU_AUTOPROBE
+static DEVICE_ATTR(modalias, 0444, arch_print_cpu_modalias, NULL);
+#endif
+
+static struct attribute *cpu_root_attrs[] = {
+#ifdef CONFIG_ARCH_CPU_PROBE_RELEASE
+	&dev_attr_probe.attr,
+	&dev_attr_release.attr,
+#endif
+	&cpu_attrs[0].attr.attr,
+	&cpu_attrs[1].attr.attr,
+	&cpu_attrs[2].attr.attr,
+	&dev_attr_kernel_max.attr,
+	&dev_attr_offline.attr,
+#ifdef CONFIG_ARCH_HAS_CPU_AUTOPROBE
+	&dev_attr_modalias.attr,
+#endif
+	NULL
+};
+
+static struct attribute_group cpu_root_attr_group = {
+	.attrs = cpu_root_attrs,
+};
+
+static const struct attribute_group *cpu_root_attr_groups[] = {
+	&cpu_root_attr_group,
+	NULL,
+};
+
+bool cpu_is_hotpluggable(unsigned cpu)
+{
+	struct device *dev = get_cpu_device(cpu);
+	return dev && container_of(dev, struct cpu, dev)->hotpluggable;
+}
+EXPORT_SYMBOL_GPL(cpu_is_hotpluggable);
+
+#ifdef CONFIG_GENERIC_CPU_DEVICES
+static DEFINE_PER_CPU(struct cpu, cpu_devices);
+#endif
+
+static void __init cpu_dev_register_generic(void)
+{
+#ifdef CONFIG_GENERIC_CPU_DEVICES
+	int i;
+
+	for_each_possible_cpu(i) {
+		if (register_cpu(&per_cpu(cpu_devices, i), i))
+			panic("Failed to register CPU device");
+	}
+#endif
+}
+
+void __init cpu_dev_init(void)
+{
+	if (subsys_system_register(&cpu_subsys, cpu_root_attr_groups))
+		panic("Failed to register CPU subsystem");
+
+	cpu_dev_register_generic();
+}

drivers/base/dd.c

@@ -0,0 +1,709 @@
+/*
+ * drivers/base/dd.c - The core device/driver interactions.
+ *
+ * This file contains the (sometimes tricky) code that controls the
+ * interactions between devices and drivers, which primarily includes
+ * driver binding and unbinding.
+ *
+ * All of this code used to exist in drivers/base/bus.c, but was
+ * relocated to here in the name of compartmentalization (since it wasn't
+ * strictly code just for the 'struct bus_type'.
+ *
+ * Copyright (c) 2002-5 Patrick Mochel
+ * Copyright (c) 2002-3 Open Source Development Labs
+ * Copyright (c) 2007-2009 Greg Kroah-Hartman <gregkh@suse.de>
+ * Copyright (c) 2007-2009 Novell Inc.
+ *
+ * This file is released under the GPLv2
+ */
+
+#include <linux/device.h>
+#include <linux/delay.h>
+#include <linux/module.h>
+#include <linux/kthread.h>
+#include <linux/wait.h>
+#include <linux/async.h>
+#include <linux/pm_runtime.h>
+#include <linux/pinctrl/devinfo.h>
+#include <linux/of_iommu.h>
+
+#include "base.h"
+#include "power/power.h"
+
+/*
+ * Deferred Probe infrastructure.
+ *
+ * Sometimes driver probe order matters, but the kernel doesn't always have
+ * dependency information which means some drivers will get probed before a
+ * resource it depends on is available.  For example, an SDHCI driver may
+ * first need a GPIO line from an i2c GPIO controller before it can be
+ * initialized.  If a required resource is not available yet, a driver can
+ * request probing to be deferred by returning -EPROBE_DEFER from its probe hook
+ *
+ * Deferred probe maintains two lists of devices, a pending list and an active
+ * list.  A driver returning -EPROBE_DEFER causes the device to be added to the
+ * pending list.  A successful driver probe will trigger moving all devices
+ * from the pending to the active list so that the workqueue will eventually
+ * retry them.
+ *
+ * The deferred_probe_mutex must be held any time the deferred_probe_*_list
+ * of the (struct device*)->p->deferred_probe pointers are manipulated
+ */
+static DEFINE_MUTEX(deferred_probe_mutex);
+static LIST_HEAD(deferred_probe_pending_list);
+static LIST_HEAD(deferred_probe_active_list);
+static struct workqueue_struct *deferred_wq;
+static atomic_t deferred_trigger_count = ATOMIC_INIT(0);
+
+/**
+ * deferred_probe_work_func() - Retry probing devices in the active list.
+ */
+static void deferred_probe_work_func(struct work_struct *work)
+{
+	struct device *dev;
+	struct device_private *private;
+	/*
+	 * This block processes every device in the deferred 'active' list.
+	 * Each device is removed from the active list and passed to
+	 * bus_probe_device() to re-attempt the probe.  The loop continues
+	 * until every device in the active list is removed and retried.
+	 *
+	 * Note: Once the device is removed from the list and the mutex is
+	 * released, it is possible for the device get freed by another thread
+	 * and cause a illegal pointer dereference.  This code uses
+	 * get/put_device() to ensure the device structure cannot disappear
+	 * from under our feet.
+	 */
+	mutex_lock(&deferred_probe_mutex);
+	while (!list_empty(&deferred_probe_active_list)) {
+		private = list_first_entry(&deferred_probe_active_list,
+					typeof(*dev->p), deferred_probe);
+		dev = private->device;
+		list_del_init(&private->deferred_probe);
+
+		get_device(dev);
+
+		/*
+		 * Drop the mutex while probing each device; the probe path may
+		 * manipulate the deferred list
+		 */
+		mutex_unlock(&deferred_probe_mutex);
+
+		/*
+		 * Force the device to the end of the dpm_list since
+		 * the PM code assumes that the order we add things to
+		 * the list is a good order for suspend but deferred
+		 * probe makes that very unsafe.
+		 */
+		device_pm_lock();
+		device_pm_move_last(dev);
+		device_pm_unlock();
+
+		dev_dbg(dev, "Retrying from deferred list\n");
+		bus_probe_device(dev);
+
+		mutex_lock(&deferred_probe_mutex);
+
+		put_device(dev);
+	}
+	mutex_unlock(&deferred_probe_mutex);
+}
+static DECLARE_WORK(deferred_probe_work, deferred_probe_work_func);
+
+static void driver_deferred_probe_add(struct device *dev)
+{
+	mutex_lock(&deferred_probe_mutex);
+	if (list_empty(&dev->p->deferred_probe)) {
+		dev_dbg(dev, "Added to deferred list\n");
+		list_add_tail(&dev->p->deferred_probe, &deferred_probe_pending_list);
+	}
+	mutex_unlock(&deferred_probe_mutex);
+}
+
+void driver_deferred_probe_del(struct device *dev)
+{
+	mutex_lock(&deferred_probe_mutex);
+	if (!list_empty(&dev->p->deferred_probe)) {
+		dev_dbg(dev, "Removed from deferred list\n");
+		list_del_init(&dev->p->deferred_probe);
+	}
+	mutex_unlock(&deferred_probe_mutex);
+}
+
+static bool driver_deferred_probe_enable = false;
+/**
+ * driver_deferred_probe_trigger() - Kick off re-probing deferred devices
+ *
+ * This functions moves all devices from the pending list to the active
+ * list and schedules the deferred probe workqueue to process them.  It
+ * should be called anytime a driver is successfully bound to a device.
+ *
+ * Note, there is a race condition in multi-threaded probe. In the case where
+ * more than one device is probing at the same time, it is possible for one
+ * probe to complete successfully while another is about to defer. If the second
+ * depends on the first, then it will get put on the pending list after the
+ * trigger event has already occured and will be stuck there.
+ *
+ * The atomic 'deferred_trigger_count' is used to determine if a successful
+ * trigger has occurred in the midst of probing a driver. If the trigger count
+ * changes in the midst of a probe, then deferred processing should be triggered
+ * again.
+ */
+static void driver_deferred_probe_trigger(void)
+{
+	if (!driver_deferred_probe_enable)
+		return;
+
+	/*
+	 * A successful probe means that all the devices in the pending list
+	 * should be triggered to be reprobed.  Move all the deferred devices
+	 * into the active list so they can be retried by the workqueue
+	 */
+	mutex_lock(&deferred_probe_mutex);
+	atomic_inc(&deferred_trigger_count);
+	list_splice_tail_init(&deferred_probe_pending_list,
+			      &deferred_probe_active_list);
+	mutex_unlock(&deferred_probe_mutex);
+
+	/*
+	 * Kick the re-probe thread.  It may already be scheduled, but it is
+	 * safe to kick it again.
+	 */
+	queue_work(deferred_wq, &deferred_probe_work);
+}
+
+/**
+ * deferred_probe_initcall() - Enable probing of deferred devices
+ *
+ * We don't want to get in the way when the bulk of drivers are getting probed.
+ * Instead, this initcall makes sure that deferred probing is delayed until
+ * late_initcall time.
+ */
+static int deferred_probe_initcall(void)
+{
+	deferred_wq = create_singlethread_workqueue("deferwq");
+	if (WARN_ON(!deferred_wq))
+		return -ENOMEM;
+
+	driver_deferred_probe_enable = true;
+	driver_deferred_probe_trigger();
+	/* Sort as many dependencies as possible before exiting initcalls */
+	flush_workqueue(deferred_wq);
+	return 0;
+}
+late_initcall(deferred_probe_initcall);
+
+static void driver_bound(struct device *dev)
+{
+	if (klist_node_attached(&dev->p->knode_driver)) {
+		printk(KERN_WARNING "%s: device %s already bound\n",
+			__func__, kobject_name(&dev->kobj));
+		return;
+	}
+
+	pr_debug("driver: '%s': %s: bound to device '%s'\n", dev_name(dev),
+		 __func__, dev->driver->name);
+
+	klist_add_tail(&dev->p->knode_driver, &dev->driver->p->klist_devices);
+
+	/*
+	 * Make sure the device is no longer in one of the deferred lists and
+	 * kick off retrying all pending devices
+	 */
+	driver_deferred_probe_del(dev);
+	driver_deferred_probe_trigger();
+
+	if (dev->bus)
+		blocking_notifier_call_chain(&dev->bus->p->bus_notifier,
+					     BUS_NOTIFY_BOUND_DRIVER, dev);
+}
+
+static int driver_sysfs_add(struct device *dev)
+{
+	int ret;
+
+	if (dev->bus)
+		blocking_notifier_call_chain(&dev->bus->p->bus_notifier,
+					     BUS_NOTIFY_BIND_DRIVER, dev);
+
+	ret = sysfs_create_link(&dev->driver->p->kobj, &dev->kobj,
+			  kobject_name(&dev->kobj));
+	if (ret == 0) {
+		ret = sysfs_create_link(&dev->kobj, &dev->driver->p->kobj,
+					"driver");
+		if (ret)
+			sysfs_remove_link(&dev->driver->p->kobj,
+					kobject_name(&dev->kobj));
+	}
+	return ret;
+}
+
+static void driver_sysfs_remove(struct device *dev)
+{
+	struct device_driver *drv = dev->driver;
+
+	if (drv) {
+		sysfs_remove_link(&drv->p->kobj, kobject_name(&dev->kobj));
+		sysfs_remove_link(&dev->kobj, "driver");
+	}
+}
+
+/**
+ * device_bind_driver - bind a driver to one device.
+ * @dev: device.
+ *
+ * Allow manual attachment of a driver to a device.
+ * Caller must have already set @dev->driver.
+ *
+ * Note that this does not modify the bus reference count
+ * nor take the bus's rwsem. Please verify those are accounted
+ * for before calling this. (It is ok to call with no other effort
+ * from a driver's probe() method.)
+ *
+ * This function must be called with the device lock held.
+ */
+int device_bind_driver(struct device *dev)
+{
+	int ret;
+
+	ret = driver_sysfs_add(dev);
+	if (!ret)
+		driver_bound(dev);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(device_bind_driver);
+
+static atomic_t probe_count = ATOMIC_INIT(0);
+static DECLARE_WAIT_QUEUE_HEAD(probe_waitqueue);
+
+static int really_probe(struct device *dev, struct device_driver *drv)
+{
+	int ret = 0;
+	int local_trigger_count = atomic_read(&deferred_trigger_count);
+
+	atomic_inc(&probe_count);
+	pr_debug("bus: '%s': %s: probing driver %s with device %s\n",
+		 drv->bus->name, __func__, drv->name, dev_name(dev));
+	WARN_ON(!list_empty(&dev->devres_head));
+
+	dev->driver = drv;
+
+	ret = of_iommu_attach(dev);
+	if (ret)
+		goto probe_failed;
+
+	/* If using pinctrl, bind pins now before probing */
+	ret = pinctrl_bind_pins(dev);
+	if (ret)
+		goto probe_failed;
+
+	if (driver_sysfs_add(dev)) {
+		printk(KERN_ERR "%s: driver_sysfs_add(%s) failed\n",
+			__func__, dev_name(dev));
+		goto probe_failed;
+	}
+
+	if (dev->bus->probe) {
+		ret = dev->bus->probe(dev);
+		if (ret)
+			goto probe_failed;
+	} else if (drv->probe) {
+		ret = drv->probe(dev);
+		if (ret)
+			goto probe_failed;
+	}
+
+	driver_bound(dev);
+	ret = 1;
+	pr_debug("bus: '%s': %s: bound device %s to driver %s\n",
+		 drv->bus->name, __func__, dev_name(dev), drv->name);
+	goto done;
+
+probe_failed:
+	devres_release_all(dev);
+	driver_sysfs_remove(dev);
+	dev->driver = NULL;
+	dev_set_drvdata(dev, NULL);
+
+	if (ret == -EPROBE_DEFER) {
+		/* Driver requested deferred probing */
+		dev_info(dev, "Driver %s requests probe deferral\n", drv->name);
+		driver_deferred_probe_add(dev);
+		/* Did a trigger occur while probing? Need to re-trigger if yes */
+		if (local_trigger_count != atomic_read(&deferred_trigger_count))
+			driver_deferred_probe_trigger();
+	} else if (ret != -ENODEV && ret != -ENXIO) {
+		/* driver matched but the probe failed */
+		printk(KERN_WARNING
+		       "%s: probe of %s failed with error %d\n",
+		       drv->name, dev_name(dev), ret);
+	} else {
+		pr_debug("%s: probe of %s rejects match %d\n",
+		       drv->name, dev_name(dev), ret);
+	}
+	/*
+	 * Ignore errors returned by ->probe so that the next driver can try
+	 * its luck.
+	 */
+	ret = 0;
+done:
+	atomic_dec(&probe_count);
+	wake_up(&probe_waitqueue);
+	return ret;
+}
+
+/**
+ * driver_probe_done
+ * Determine if the probe sequence is finished or not.
+ *
+ * Should somehow figure out how to use a semaphore, not an atomic variable...
+ */
+int driver_probe_done(void)
+{
+	pr_debug("%s: probe_count = %d\n", __func__,
+		 atomic_read(&probe_count));
+	if (atomic_read(&probe_count))
+		return -EBUSY;
+	return 0;
+}
+
+/**
+ * wait_for_device_probe
+ * Wait for device probing to be completed.
+ */
+void wait_for_device_probe(void)
+{
+	/* wait for the known devices to complete their probing */
+	wait_event(probe_waitqueue, atomic_read(&probe_count) == 0);
+	async_synchronize_full();
+}
+EXPORT_SYMBOL_GPL(wait_for_device_probe);
+
+/**
+ * driver_probe_device - attempt to bind device & driver together
+ * @drv: driver to bind a device to
+ * @dev: device to try to bind to the driver
+ *
+ * This function returns -ENODEV if the device is not registered,
+ * 1 if the device is bound successfully and 0 otherwise.
+ *
+ * This function must be called with @dev lock held.  When called for a
+ * USB interface, @dev->parent lock must be held as well.
+ */
+int driver_probe_device(struct device_driver *drv, struct device *dev)
+{
+	int ret = 0;
+
+	if (!device_is_registered(dev))
+		return -ENODEV;
+
+	pr_debug("bus: '%s': %s: matched device %s with driver %s\n",
+		 drv->bus->name, __func__, dev_name(dev), drv->name);
+
+	pm_runtime_barrier(dev);
+	ret = really_probe(dev, drv);
+	pm_request_idle(dev);
+
+	return ret;
+}
+
+struct device_attach_data {
+	struct device *dev;
+
+	/*
+	 * Indicates whether we are are considering asynchronous probing or
+	 * not. Only initial binding after device or driver registration
+	 * (including deferral processing) may be done asynchronously, the
+	 * rest is always synchronous, as we expect it is being done by
+	 * request from userspace.
+	 */
+	bool check_async;
+
+	/*
+	 * Indicates if we are binding synchronous or asynchronous drivers.
+	 * When asynchronous probing is enabled, we'll execute 2 passes
+	 * over drivers: first pass doing synchronous probing and second
+	 * doing asynchronous probing (if synchronous failed and we found
+	 * asynchronous driver during first pass).
+	 */
+	bool want_async;
+
+	/*
+	 * We'll set have_async to 'true' if, while scanning for matching
+	 * driver, we'll encounter one that requests asynchronous probing.
+	 */
+	bool have_async;
+};
+
+static int __device_attach_driver(struct device_driver *drv, void *_data)
+{
+	struct device_attach_data *data = _data;
+	struct device *dev = data->dev;
+
+	if (!driver_match_device(drv, dev))
+		return 0;
+
+	if (drv->async_probe)
+		data->have_async = true;
+
+	if (data->check_async && drv->async_probe != data->want_async)
+		return 0;
+
+	return driver_probe_device(drv, dev);
+}
+
+static void __device_attach_async_helper(void *_dev, async_cookie_t cookie)
+{
+	struct device *dev = _dev;
+	struct device_attach_data data = {
+		.dev		= dev,
+		.check_async	= true,
+		.want_async	= true,
+	};
+
+	device_lock(dev);
+
+	bus_for_each_drv(dev->bus, NULL, &data, __device_attach_driver);
+	dev_dbg(dev, "async probe completed\n");
+
+	pm_request_idle(dev);
+
+	device_unlock(dev);
+
+	put_device(dev);
+}
+
+int __device_attach(struct device *dev, bool allow_async)
+{
+	int ret = 0;
+
+	device_lock(dev);
+	if (dev->driver) {
+		if (klist_node_attached(&dev->p->knode_driver)) {
+			ret = 1;
+			goto out_unlock;
+		}
+		ret = device_bind_driver(dev);
+		if (ret == 0)
+			ret = 1;
+		else {
+			dev->driver = NULL;
+			ret = 0;
+		}
+	} else {
+		struct device_attach_data data = {
+			.dev = dev,
+			.check_async = allow_async,
+			.want_async = false,
+		};
+
+		ret = bus_for_each_drv(dev->bus, NULL, &data,
+					__device_attach_driver);
+		if (!ret && allow_async && data.have_async) {
+			/*
+			 * If we could not find appropriate driver
+			 * synchronously and we are allowed to do
+			 * async probes and there are drivers that
+			 * want to probe asynchronously, we'll
+			 * try them.
+			 */
+			dev_dbg(dev, "scheduling asynchronous probe\n");
+			get_device(dev);
+			async_schedule(__device_attach_async_helper, dev);
+		} else {
+			pm_request_idle(dev);
+		}
+	}
+out_unlock:
+	device_unlock(dev);
+	return ret;
+}
+
+/**
+ * device_attach - try to attach device to a driver.
+ * @dev: device.
+ *
+ * Walk the list of drivers that the bus has and call
+ * driver_probe_device() for each pair. If a compatible
+ * pair is found, break out and return.
+ *
+ * Returns 1 if the device was bound to a driver;
+ * 0 if no matching driver was found;
+ * -ENODEV if the device is not registered.
+ *
+ * When called for a USB interface, @dev->parent lock must be held.
+ */
+int device_attach(struct device *dev)
+{
+	return __device_attach(dev, false);
+}
+EXPORT_SYMBOL_GPL(device_attach);
+
+void device_initial_probe(struct device *dev)
+{
+	__device_attach(dev, true);
+}
+
+static int __driver_attach(struct device *dev, void *data)
+{
+	struct device_driver *drv = data;
+
+	/*
+	 * Lock device and try to bind to it. We drop the error
+	 * here and always return 0, because we need to keep trying
+	 * to bind to devices and some drivers will return an error
+	 * simply if it didn't support the device.
+	 *
+	 * driver_probe_device() will spit a warning if there
+	 * is an error.
+	 */
+
+	if (!driver_match_device(drv, dev))
+		return 0;
+
+	if (dev->parent)	/* Needed for USB */
+		device_lock(dev->parent);
+	device_lock(dev);
+	if (!dev->driver)
+		driver_probe_device(drv, dev);
+	device_unlock(dev);
+	if (dev->parent)
+		device_unlock(dev->parent);
+
+	return 0;
+}
+
+/**
+ * driver_attach - try to bind driver to devices.
+ * @drv: driver.
+ *
+ * Walk the list of devices that the bus has on it and try to
+ * match the driver with each one.  If driver_probe_device()
+ * returns 0 and the @dev->driver is set, we've found a
+ * compatible pair.
+ */
+int driver_attach(struct device_driver *drv)
+{
+	return bus_for_each_dev(drv->bus, NULL, drv, __driver_attach);
+}
+EXPORT_SYMBOL_GPL(driver_attach);
+
+/*
+ * __device_release_driver() must be called with @dev lock held.
+ * When called for a USB interface, @dev->parent lock must be held as well.
+ */
+static void __device_release_driver(struct device *dev)
+{
+	struct device_driver *drv;
+
+	drv = dev->driver;
+	if (drv) {
+		if (drv->async_probe)
+			async_synchronize_full();
+
+		pm_runtime_get_sync(dev);
+
+		driver_sysfs_remove(dev);
+
+		if (dev->bus)
+			blocking_notifier_call_chain(&dev->bus->p->bus_notifier,
+						     BUS_NOTIFY_UNBIND_DRIVER,
+						     dev);
+
+		pm_runtime_put(dev);
+
+		if (dev->bus && dev->bus->remove)
+			dev->bus->remove(dev);
+		else if (drv->remove)
+			drv->remove(dev);
+		devres_release_all(dev);
+		dev->driver = NULL;
+		dev_set_drvdata(dev, NULL);
+		klist_remove(&dev->p->knode_driver);
+		if (dev->bus)
+			blocking_notifier_call_chain(&dev->bus->p->bus_notifier,
+						     BUS_NOTIFY_UNBOUND_DRIVER,
+						     dev);
+
+	}
+}
+
+/**
+ * device_release_driver - manually detach device from driver.
+ * @dev: device.
+ *
+ * Manually detach device from driver.
+ * When called for a USB interface, @dev->parent lock must be held.
+ */
+void device_release_driver(struct device *dev)
+{
+	/*
+	 * If anyone calls device_release_driver() recursively from
+	 * within their ->remove callback for the same device, they
+	 * will deadlock right here.
+	 */
+	device_lock(dev);
+	__device_release_driver(dev);
+	device_unlock(dev);
+}
+EXPORT_SYMBOL_GPL(device_release_driver);
+
+/**
+ * driver_detach - detach driver from all devices it controls.
+ * @drv: driver.
+ */
+void driver_detach(struct device_driver *drv)
+{
+	struct device_private *dev_prv;
+	struct device *dev;
+
+	for (;;) {
+		spin_lock(&drv->p->klist_devices.k_lock);
+		if (list_empty(&drv->p->klist_devices.k_list)) {
+			spin_unlock(&drv->p->klist_devices.k_lock);
+			break;
+		}
+		dev_prv = list_entry(drv->p->klist_devices.k_list.prev,
+				     struct device_private,
+				     knode_driver.n_node);
+		dev = dev_prv->device;
+		get_device(dev);
+		spin_unlock(&drv->p->klist_devices.k_lock);
+
+		if (dev->parent)	/* Needed for USB */
+			device_lock(dev->parent);
+		device_lock(dev);
+		if (dev->driver == drv)
+			__device_release_driver(dev);
+		device_unlock(dev);
+		if (dev->parent)
+			device_unlock(dev->parent);
+		put_device(dev);
+	}
+}
+
+/*
+ * These exports can't be _GPL due to .h files using this within them, and it
+ * might break something that was previously working...
+ */
+void *dev_get_drvdata(const struct device *dev)
+{
+	if (dev && dev->p)
+		return dev->p->driver_data;
+	return NULL;
+}
+EXPORT_SYMBOL(dev_get_drvdata);
+
+int dev_set_drvdata(struct device *dev, void *data)
+{
+	int error;
+
+	if (!dev->p) {
+		error = device_private_init(dev);
+		if (error)
+			return error;
+	}
+	dev->p->driver_data = data;
+	return 0;
+}
+EXPORT_SYMBOL(dev_set_drvdata);

drivers/base/devcoredump.c

@@ -0,0 +1,297 @@
+/*
+ * This file is provided under the GPLv2 license.
+ *
+ * GPL LICENSE SUMMARY
+ *
+ * Copyright(c) 2014 Intel Mobile Communications GmbH
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * The full GNU General Public License is included in this distribution
+ * in the file called COPYING.
+ *
+ * Contact Information:
+ *  Intel Linux Wireless <ilw@linux.intel.com>
+ * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+ *
+ * Author: Johannes Berg <johannes@sipsolutions.net>
+ */
+#include <linux/module.h>
+#include <linux/device.h>
+#include <linux/devcoredump.h>
+#include <linux/list.h>
+#include <linux/slab.h>
+#include <linux/fs.h>
+#include <linux/workqueue.h>
+
+static struct class devcd_class;
+
+/* global disable flag, for security purposes */
+static bool devcd_disabled;
+
+/* if data isn't read by userspace after 5 minutes then delete it */
+#define DEVCD_TIMEOUT	(HZ * 60 * 5)
+
+static struct bin_attribute devcd_attr_data;
+
+struct devcd_entry {
+	struct device devcd_dev;
+	const void *data;
+	size_t datalen;
+	struct module *owner;
+	ssize_t (*read)(char *buffer, loff_t offset, size_t count,
+			const void *data, size_t datalen);
+	void (*free)(const void *data);
+	struct delayed_work del_wk;
+	struct device *failing_dev;
+};
+
+static struct devcd_entry *dev_to_devcd(struct device *dev)
+{
+	return container_of(dev, struct devcd_entry, devcd_dev);
+}
+
+static void devcd_dev_release(struct device *dev)
+{
+	struct devcd_entry *devcd = dev_to_devcd(dev);
+
+	devcd->free(devcd->data);
+	module_put(devcd->owner);
+
+	/*
+	 * this seems racy, but I don't see a notifier or such on
+	 * a struct device to know when it goes away?
+	 */
+	if (devcd->failing_dev->kobj.sd)
+		sysfs_remove_link(&devcd->failing_dev->kobj, "devcoredump");
+
+	put_device(devcd->failing_dev);
+	kfree(devcd);
+}
+
+static void devcd_del(struct work_struct *wk)
+{
+	struct devcd_entry *devcd;
+
+	devcd = container_of(wk, struct devcd_entry, del_wk.work);
+
+	device_remove_bin_file(&devcd->devcd_dev, &devcd_attr_data);
+	device_del(&devcd->devcd_dev);
+	put_device(&devcd->devcd_dev);
+}
+
+static ssize_t devcd_data_read(struct file *filp, struct kobject *kobj,
+			       struct bin_attribute *bin_attr,
+			       char *buffer, loff_t offset, size_t count)
+{
+	struct device *dev = kobj_to_dev(kobj);
+	struct devcd_entry *devcd = dev_to_devcd(dev);
+
+	return devcd->read(buffer, offset, count, devcd->data, devcd->datalen);
+}
+
+static ssize_t devcd_data_write(struct file *filp, struct kobject *kobj,
+				struct bin_attribute *bin_attr,
+				char *buffer, loff_t offset, size_t count)
+{
+	struct device *dev = kobj_to_dev(kobj);
+	struct devcd_entry *devcd = dev_to_devcd(dev);
+
+	mod_delayed_work(system_wq, &devcd->del_wk, 0);
+
+	return count;
+}
+
+static struct bin_attribute devcd_attr_data = {
+	.attr = { .name = "data", .mode = S_IRUSR | S_IWUSR, },
+	.size = 0,
+	.read = devcd_data_read,
+	.write = devcd_data_write,
+};
+
+static int devcd_free(struct device *dev, void *data)
+{
+	struct devcd_entry *devcd = dev_to_devcd(dev);
+
+	flush_delayed_work(&devcd->del_wk);
+	return 0;
+}
+
+static ssize_t disabled_show(struct class *class, struct class_attribute *attr,
+			     char *buf)
+{
+	return sprintf(buf, "%d\n", devcd_disabled);
+}
+
+static ssize_t disabled_store(struct class *class, struct class_attribute *attr,
+			      const char *buf, size_t count)
+{
+	long tmp = simple_strtol(buf, NULL, 10);
+
+	/*
+	 * This essentially makes the attribute write-once, since you can't
+	 * go back to not having it disabled. This is intentional, it serves
+	 * as a system lockdown feature.
+	 */
+	if (tmp != 1)
+		return -EINVAL;
+
+	devcd_disabled = true;
+
+	class_for_each_device(&devcd_class, NULL, NULL, devcd_free);
+
+	return count;
+}
+
+static struct class_attribute devcd_class_attrs[] = {
+	__ATTR(disabled, 0600, disabled_show, disabled_store),
+	__ATTR_NULL
+};
+
+static struct class devcd_class = {
+	.name		= "devcoredump",
+	.owner		= THIS_MODULE,
+	.dev_release	= devcd_dev_release,
+	.class_attrs	= devcd_class_attrs,
+};
+
+static ssize_t devcd_readv(char *buffer, loff_t offset, size_t count,
+			   const void *data, size_t datalen)
+{
+	if (offset > datalen)
+		return -EINVAL;
+
+	if (offset + count > datalen)
+		count = datalen - offset;
+
+	if (count)
+		memcpy(buffer, ((u8 *)data) + offset, count);
+
+	return count;
+}
+
+/**
+ * dev_coredumpv - create device coredump with vmalloc data
+ * @dev: the struct device for the crashed device
+ * @data: vmalloc data containing the device coredump
+ * @datalen: length of the data
+ * @gfp: allocation flags
+ *
+ * This function takes ownership of the vmalloc'ed data and will free
+ * it when it is no longer used. See dev_coredumpm() for more information.
+ */
+void dev_coredumpv(struct device *dev, const void *data, size_t datalen,
+		   gfp_t gfp)
+{
+	dev_coredumpm(dev, NULL, data, datalen, gfp, devcd_readv, vfree);
+}
+EXPORT_SYMBOL_GPL(dev_coredumpv);
+
+static int devcd_match_failing(struct device *dev, const void *failing)
+{
+	struct devcd_entry *devcd = dev_to_devcd(dev);
+
+	return devcd->failing_dev == failing;
+}
+
+/**
+ * dev_coredumpm - create device coredump with read/free methods
+ * @dev: the struct device for the crashed device
+ * @owner: the module that contains the read/free functions, use %THIS_MODULE
+ * @data: data cookie for the @read/@free functions
+ * @datalen: length of the data
+ * @gfp: allocation flags
+ * @read: function to read from the given buffer
+ * @free: function to free the given buffer
+ *
+ * Creates a new device coredump for the given device. If a previous one hasn't
+ * been read yet, the new coredump is discarded. The data lifetime is determined
+ * by the device coredump framework and when it is no longer needed the @free
+ * function will be called to free the data.
+ */
+void dev_coredumpm(struct device *dev, struct module *owner,
+		   const void *data, size_t datalen, gfp_t gfp,
+		   ssize_t (*read)(char *buffer, loff_t offset, size_t count,
+				   const void *data, size_t datalen),
+		   void (*free)(const void *data))
+{
+	static atomic_t devcd_count = ATOMIC_INIT(0);
+	struct devcd_entry *devcd;
+	struct device *existing;
+
+	if (devcd_disabled)
+		goto free;
+
+	existing = class_find_device(&devcd_class, NULL, dev,
+				     devcd_match_failing);
+	if (existing) {
+		put_device(existing);
+		goto free;
+	}
+
+	if (!try_module_get(owner))
+		goto free;
+
+	devcd = kzalloc(sizeof(*devcd), gfp);
+	if (!devcd)
+		goto put_module;
+
+	devcd->owner = owner;
+	devcd->data = data;
+	devcd->datalen = datalen;
+	devcd->read = read;
+	devcd->free = free;
+	devcd->failing_dev = get_device(dev);
+
+	device_initialize(&devcd->devcd_dev);
+
+	dev_set_name(&devcd->devcd_dev, "devcd%d",
+		     atomic_inc_return(&devcd_count));
+	devcd->devcd_dev.class = &devcd_class;
+
+	if (device_add(&devcd->devcd_dev))
+		goto put_device;
+
+	if (device_create_bin_file(&devcd->devcd_dev, &devcd_attr_data))
+		goto put_device;
+
+	if (sysfs_create_link(&devcd->devcd_dev.kobj, &dev->kobj,
+			      "failing_device"))
+		/* nothing - symlink will be missing */;
+
+	if (sysfs_create_link(&dev->kobj, &devcd->devcd_dev.kobj,
+			      "devcoredump"))
+		/* nothing - symlink will be missing */;
+
+	INIT_DELAYED_WORK(&devcd->del_wk, devcd_del);
+	schedule_delayed_work(&devcd->del_wk, DEVCD_TIMEOUT);
+
+	return;
+ put_device:
+	put_device(&devcd->devcd_dev);
+ put_module:
+	module_put(owner);
+ free:
+	free(data);
+}
+EXPORT_SYMBOL_GPL(dev_coredumpm);
+
+static int __init devcoredump_init(void)
+{
+	return class_register(&devcd_class);
+}
+__initcall(devcoredump_init);
+
+static void __exit devcoredump_exit(void)
+{
+	class_for_each_device(&devcd_class, NULL, NULL, devcd_free);
+	class_unregister(&devcd_class);
+}
+__exitcall(devcoredump_exit);

drivers/base/devres.c

@@ -0,0 +1,802 @@
+/*
+ * drivers/base/devres.c - device resource management
+ *
+ * Copyright (c) 2006  SUSE Linux Products GmbH
+ * Copyright (c) 2006  Tejun Heo <teheo@suse.de>
+ *
+ * This file is released under the GPLv2.
+ */
+
+#include <linux/device.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+
+#include "base.h"
+
+struct devres_node {
+	struct list_head		entry;
+	dr_release_t			release;
+#ifdef CONFIG_DEBUG_DEVRES
+	const char			*name;
+	size_t				size;
+#endif
+};
+
+struct devres {
+	struct devres_node		node;
+	/* -- 3 pointers */
+	unsigned long long		data[];	/* guarantee ull alignment */
+};
+
+struct devres_group {
+	struct devres_node		node[2];
+	void				*id;
+	int				color;
+	/* -- 8 pointers */
+};
+
+#ifdef CONFIG_DEBUG_DEVRES
+static int log_devres = 0;
+module_param_named(log, log_devres, int, S_IRUGO | S_IWUSR);
+
+static void set_node_dbginfo(struct devres_node *node, const char *name,
+			     size_t size)
+{
+	node->name = name;
+	node->size = size;
+}
+
+static void devres_log(struct device *dev, struct devres_node *node,
+		       const char *op)
+{
+	if (unlikely(log_devres))
+		dev_err(dev, "DEVRES %3s %p %s (%lu bytes)\n",
+			op, node, node->name, (unsigned long)node->size);
+}
+#else /* CONFIG_DEBUG_DEVRES */
+#define set_node_dbginfo(node, n, s)	do {} while (0)
+#define devres_log(dev, node, op)	do {} while (0)
+#endif /* CONFIG_DEBUG_DEVRES */
+
+/*
+ * Release functions for devres group.  These callbacks are used only
+ * for identification.
+ */
+static void group_open_release(struct device *dev, void *res)
+{
+	/* noop */
+}
+
+static void group_close_release(struct device *dev, void *res)
+{
+	/* noop */
+}
+
+static struct devres_group * node_to_group(struct devres_node *node)
+{
+	if (node->release == &group_open_release)
+		return container_of(node, struct devres_group, node[0]);
+	if (node->release == &group_close_release)
+		return container_of(node, struct devres_group, node[1]);
+	return NULL;
+}
+
+static __always_inline struct devres * alloc_dr(dr_release_t release,
+						size_t size, gfp_t gfp)
+{
+	size_t tot_size = sizeof(struct devres) + size;
+	struct devres *dr;
+
+	dr = kmalloc_track_caller(tot_size, gfp);
+	if (unlikely(!dr))
+		return NULL;
+
+	memset(dr, 0, tot_size);
+	INIT_LIST_HEAD(&dr->node.entry);
+	dr->node.release = release;
+	return dr;
+}
+
+static void add_dr(struct device *dev, struct devres_node *node)
+{
+	devres_log(dev, node, "ADD");
+	BUG_ON(!list_empty(&node->entry));
+	list_add_tail(&node->entry, &dev->devres_head);
+}
+
+#ifdef CONFIG_DEBUG_DEVRES
+void * __devres_alloc(dr_release_t release, size_t size, gfp_t gfp,
+		      const char *name)
+{
+	struct devres *dr;
+
+	dr = alloc_dr(release, size, gfp);
+	if (unlikely(!dr))
+		return NULL;
+	set_node_dbginfo(&dr->node, name, size);
+	return dr->data;
+}
+EXPORT_SYMBOL_GPL(__devres_alloc);
+#else
+/**
+ * devres_alloc - Allocate device resource data
+ * @release: Release function devres will be associated with
+ * @size: Allocation size
+ * @gfp: Allocation flags
+ *
+ * Allocate devres of @size bytes.  The allocated area is zeroed, then
+ * associated with @release.  The returned pointer can be passed to
+ * other devres_*() functions.
+ *
+ * RETURNS:
+ * Pointer to allocated devres on success, NULL on failure.
+ */
+void * devres_alloc(dr_release_t release, size_t size, gfp_t gfp)
+{
+	struct devres *dr;
+
+	dr = alloc_dr(release, size, gfp);
+	if (unlikely(!dr))
+		return NULL;
+	return dr->data;
+}
+EXPORT_SYMBOL_GPL(devres_alloc);
+#endif
+
+/**
+ * devres_for_each_res - Resource iterator
+ * @dev: Device to iterate resource from
+ * @release: Look for resources associated with this release function
+ * @match: Match function (optional)
+ * @match_data: Data for the match function
+ * @fn: Function to be called for each matched resource.
+ * @data: Data for @fn, the 3rd parameter of @fn
+ *
+ * Call @fn for each devres of @dev which is associated with @release
+ * and for which @match returns 1.
+ *
+ * RETURNS:
+ * 	void
+ */
+void devres_for_each_res(struct device *dev, dr_release_t release,
+			dr_match_t match, void *match_data,
+			void (*fn)(struct device *, void *, void *),
+			void *data)
+{
+	struct devres_node *node;
+	struct devres_node *tmp;
+	unsigned long flags;
+
+	if (!fn)
+		return;
+
+	spin_lock_irqsave(&dev->devres_lock, flags);
+	list_for_each_entry_safe_reverse(node, tmp,
+			&dev->devres_head, entry) {
+		struct devres *dr = container_of(node, struct devres, node);
+
+		if (node->release != release)
+			continue;
+		if (match && !match(dev, dr->data, match_data))
+			continue;
+		fn(dev, dr->data, data);
+	}
+	spin_unlock_irqrestore(&dev->devres_lock, flags);
+}
+EXPORT_SYMBOL_GPL(devres_for_each_res);
+
+/**
+ * devres_free - Free device resource data
+ * @res: Pointer to devres data to free
+ *
+ * Free devres created with devres_alloc().
+ */
+void devres_free(void *res)
+{
+	if (res) {
+		struct devres *dr = container_of(res, struct devres, data);
+
+		BUG_ON(!list_empty(&dr->node.entry));
+		kfree(dr);
+	}
+}
+EXPORT_SYMBOL_GPL(devres_free);
+
+/**
+ * devres_add - Register device resource
+ * @dev: Device to add resource to
+ * @res: Resource to register
+ *
+ * Register devres @res to @dev.  @res should have been allocated
+ * using devres_alloc().  On driver detach, the associated release
+ * function will be invoked and devres will be freed automatically.
+ */
+void devres_add(struct device *dev, void *res)
+{
+	struct devres *dr = container_of(res, struct devres, data);
+	unsigned long flags;
+
+	spin_lock_irqsave(&dev->devres_lock, flags);
+	add_dr(dev, &dr->node);
+	spin_unlock_irqrestore(&dev->devres_lock, flags);
+}
+EXPORT_SYMBOL_GPL(devres_add);
+
+static struct devres *find_dr(struct device *dev, dr_release_t release,
+			      dr_match_t match, void *match_data)
+{
+	struct devres_node *node;
+
+	list_for_each_entry_reverse(node, &dev->devres_head, entry) {
+		struct devres *dr = container_of(node, struct devres, node);
+
+		if (node->release != release)
+			continue;
+		if (match && !match(dev, dr->data, match_data))
+			continue;
+		return dr;
+	}
+
+	return NULL;
+}
+
+/**
+ * devres_find - Find device resource
+ * @dev: Device to lookup resource from
+ * @release: Look for resources associated with this release function
+ * @match: Match function (optional)
+ * @match_data: Data for the match function
+ *
+ * Find the latest devres of @dev which is associated with @release
+ * and for which @match returns 1.  If @match is NULL, it's considered
+ * to match all.
+ *
+ * RETURNS:
+ * Pointer to found devres, NULL if not found.
+ */
+void * devres_find(struct device *dev, dr_release_t release,
+		   dr_match_t match, void *match_data)
+{
+	struct devres *dr;
+	unsigned long flags;
+
+	spin_lock_irqsave(&dev->devres_lock, flags);
+	dr = find_dr(dev, release, match, match_data);
+	spin_unlock_irqrestore(&dev->devres_lock, flags);
+
+	if (dr)
+		return dr->data;
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(devres_find);
+
+/**
+ * devres_get - Find devres, if non-existent, add one atomically
+ * @dev: Device to lookup or add devres for
+ * @new_res: Pointer to new initialized devres to add if not found
+ * @match: Match function (optional)
+ * @match_data: Data for the match function
+ *
+ * Find the latest devres of @dev which has the same release function
+ * as @new_res and for which @match return 1.  If found, @new_res is
+ * freed; otherwise, @new_res is added atomically.
+ *
+ * RETURNS:
+ * Pointer to found or added devres.
+ */
+void * devres_get(struct device *dev, void *new_res,
+		  dr_match_t match, void *match_data)
+{
+	struct devres *new_dr = container_of(new_res, struct devres, data);
+	struct devres *dr;
+	unsigned long flags;
+
+	spin_lock_irqsave(&dev->devres_lock, flags);
+	dr = find_dr(dev, new_dr->node.release, match, match_data);
+	if (!dr) {
+		add_dr(dev, &new_dr->node);
+		dr = new_dr;
+		new_dr = NULL;
+	}
+	spin_unlock_irqrestore(&dev->devres_lock, flags);
+	devres_free(new_dr);
+
+	return dr->data;
+}
+EXPORT_SYMBOL_GPL(devres_get);
+
+/**
+ * devres_remove - Find a device resource and remove it
+ * @dev: Device to find resource from
+ * @release: Look for resources associated with this release function
+ * @match: Match function (optional)
+ * @match_data: Data for the match function
+ *
+ * Find the latest devres of @dev associated with @release and for
+ * which @match returns 1.  If @match is NULL, it's considered to
+ * match all.  If found, the resource is removed atomically and
+ * returned.
+ *
+ * RETURNS:
+ * Pointer to removed devres on success, NULL if not found.
+ */
+void * devres_remove(struct device *dev, dr_release_t release,
+		     dr_match_t match, void *match_data)
+{
+	struct devres *dr;
+	unsigned long flags;
+
+	spin_lock_irqsave(&dev->devres_lock, flags);
+	dr = find_dr(dev, release, match, match_data);
+	if (dr) {
+		list_del_init(&dr->node.entry);
+		devres_log(dev, &dr->node, "REM");
+	}
+	spin_unlock_irqrestore(&dev->devres_lock, flags);
+
+	if (dr)
+		return dr->data;
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(devres_remove);
+
+/**
+ * devres_destroy - Find a device resource and destroy it
+ * @dev: Device to find resource from
+ * @release: Look for resources associated with this release function
+ * @match: Match function (optional)
+ * @match_data: Data for the match function
+ *
+ * Find the latest devres of @dev associated with @release and for
+ * which @match returns 1.  If @match is NULL, it's considered to
+ * match all.  If found, the resource is removed atomically and freed.
+ *
+ * Note that the release function for the resource will not be called,
+ * only the devres-allocated data will be freed.  The caller becomes
+ * responsible for freeing any other data.
+ *
+ * RETURNS:
+ * 0 if devres is found and freed, -ENOENT if not found.
+ */
+int devres_destroy(struct device *dev, dr_release_t release,
+		   dr_match_t match, void *match_data)
+{
+	void *res;
+
+	res = devres_remove(dev, release, match, match_data);
+	if (unlikely(!res))
+		return -ENOENT;
+
+	devres_free(res);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(devres_destroy);
+
+
+/**
+ * devres_release - Find a device resource and destroy it, calling release
+ * @dev: Device to find resource from
+ * @release: Look for resources associated with this release function
+ * @match: Match function (optional)
+ * @match_data: Data for the match function
+ *
+ * Find the latest devres of @dev associated with @release and for
+ * which @match returns 1.  If @match is NULL, it's considered to
+ * match all.  If found, the resource is removed atomically, the
+ * release function called and the resource freed.
+ *
+ * RETURNS:
+ * 0 if devres is found and freed, -ENOENT if not found.
+ */
+int devres_release(struct device *dev, dr_release_t release,
+		   dr_match_t match, void *match_data)
+{
+	void *res;
+
+	res = devres_remove(dev, release, match, match_data);
+	if (unlikely(!res))
+		return -ENOENT;
+
+	(*release)(dev, res);
+	devres_free(res);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(devres_release);
+
+static int remove_nodes(struct device *dev,
+			struct list_head *first, struct list_head *end,
+			struct list_head *todo)
+{
+	int cnt = 0, nr_groups = 0;
+	struct list_head *cur;
+
+	/* First pass - move normal devres entries to @todo and clear
+	 * devres_group colors.
+	 */
+	cur = first;
+	while (cur != end) {
+		struct devres_node *node;
+		struct devres_group *grp;
+
+		node = list_entry(cur, struct devres_node, entry);
+		cur = cur->next;
+
+		grp = node_to_group(node);
+		if (grp) {
+			/* clear color of group markers in the first pass */
+			grp->color = 0;
+			nr_groups++;
+		} else {
+			/* regular devres entry */
+			if (&node->entry == first)
+				first = first->next;
+			list_move_tail(&node->entry, todo);
+			cnt++;
+		}
+	}
+
+	if (!nr_groups)
+		return cnt;
+
+	/* Second pass - Scan groups and color them.  A group gets
+	 * color value of two iff the group is wholly contained in
+	 * [cur, end).  That is, for a closed group, both opening and
+	 * closing markers should be in the range, while just the
+	 * opening marker is enough for an open group.
+	 */
+	cur = first;
+	while (cur != end) {
+		struct devres_node *node;
+		struct devres_group *grp;
+
+		node = list_entry(cur, struct devres_node, entry);
+		cur = cur->next;
+
+		grp = node_to_group(node);
+		BUG_ON(!grp || list_empty(&grp->node[0].entry));
+
+		grp->color++;
+		if (list_empty(&grp->node[1].entry))
+			grp->color++;
+
+		BUG_ON(grp->color <= 0 || grp->color > 2);
+		if (grp->color == 2) {
+			/* No need to update cur or end.  The removed
+			 * nodes are always before both.
+			 */
+			list_move_tail(&grp->node[0].entry, todo);
+			list_del_init(&grp->node[1].entry);
+		}
+	}
+
+	return cnt;
+}
+
+static int release_nodes(struct device *dev, struct list_head *first,
+			 struct list_head *end, unsigned long flags)
+	__releases(&dev->devres_lock)
+{
+	LIST_HEAD(todo);
+	int cnt;
+	struct devres *dr, *tmp;
+
+	cnt = remove_nodes(dev, first, end, &todo);
+
+	spin_unlock_irqrestore(&dev->devres_lock, flags);
+
+	/* Release.  Note that both devres and devres_group are
+	 * handled as devres in the following loop.  This is safe.
+	 */
+	list_for_each_entry_safe_reverse(dr, tmp, &todo, node.entry) {
+		devres_log(dev, &dr->node, "REL");
+		dr->node.release(dev, dr->data);
+		kfree(dr);
+	}
+
+	return cnt;
+}
+
+/**
+ * devres_release_all - Release all managed resources
+ * @dev: Device to release resources for
+ *
+ * Release all resources associated with @dev.  This function is
+ * called on driver detach.
+ */
+int devres_release_all(struct device *dev)
+{
+	unsigned long flags;
+
+	/* Looks like an uninitialized device structure */
+	if (WARN_ON(dev->devres_head.next == NULL))
+		return -ENODEV;
+	spin_lock_irqsave(&dev->devres_lock, flags);
+	return release_nodes(dev, dev->devres_head.next, &dev->devres_head,
+			     flags);
+}
+
+/**
+ * devres_open_group - Open a new devres group
+ * @dev: Device to open devres group for
+ * @id: Separator ID
+ * @gfp: Allocation flags
+ *
+ * Open a new devres group for @dev with @id.  For @id, using a
+ * pointer to an object which won't be used for another group is
+ * recommended.  If @id is NULL, address-wise unique ID is created.
+ *
+ * RETURNS:
+ * ID of the new group, NULL on failure.
+ */
+void * devres_open_group(struct device *dev, void *id, gfp_t gfp)
+{
+	struct devres_group *grp;
+	unsigned long flags;
+
+	grp = kmalloc(sizeof(*grp), gfp);
+	if (unlikely(!grp))
+		return NULL;
+
+	grp->node[0].release = &group_open_release;
+	grp->node[1].release = &group_close_release;
+	INIT_LIST_HEAD(&grp->node[0].entry);
+	INIT_LIST_HEAD(&grp->node[1].entry);
+	set_node_dbginfo(&grp->node[0], "grp<", 0);
+	set_node_dbginfo(&grp->node[1], "grp>", 0);
+	grp->id = grp;
+	if (id)
+		grp->id = id;
+
+	spin_lock_irqsave(&dev->devres_lock, flags);
+	add_dr(dev, &grp->node[0]);
+	spin_unlock_irqrestore(&dev->devres_lock, flags);
+	return grp->id;
+}
+EXPORT_SYMBOL_GPL(devres_open_group);
+
+/* Find devres group with ID @id.  If @id is NULL, look for the latest. */
+static struct devres_group * find_group(struct device *dev, void *id)
+{
+	struct devres_node *node;
+
+	list_for_each_entry_reverse(node, &dev->devres_head, entry) {
+		struct devres_group *grp;
+
+		if (node->release != &group_open_release)
+			continue;
+
+		grp = container_of(node, struct devres_group, node[0]);
+
+		if (id) {
+			if (grp->id == id)
+				return grp;
+		} else if (list_empty(&grp->node[1].entry))
+			return grp;
+	}
+
+	return NULL;
+}
+
+/**
+ * devres_close_group - Close a devres group
+ * @dev: Device to close devres group for
+ * @id: ID of target group, can be NULL
+ *
+ * Close the group identified by @id.  If @id is NULL, the latest open
+ * group is selected.
+ */
+void devres_close_group(struct device *dev, void *id)
+{
+	struct devres_group *grp;
+	unsigned long flags;
+
+	spin_lock_irqsave(&dev->devres_lock, flags);
+
+	grp = find_group(dev, id);
+	if (grp)
+		add_dr(dev, &grp->node[1]);
+	else
+		WARN_ON(1);
+
+	spin_unlock_irqrestore(&dev->devres_lock, flags);
+}
+EXPORT_SYMBOL_GPL(devres_close_group);
+
+/**
+ * devres_remove_group - Remove a devres group
+ * @dev: Device to remove group for
+ * @id: ID of target group, can be NULL
+ *
+ * Remove the group identified by @id.  If @id is NULL, the latest
+ * open group is selected.  Note that removing a group doesn't affect
+ * any other resources.
+ */
+void devres_remove_group(struct device *dev, void *id)
+{
+	struct devres_group *grp;
+	unsigned long flags;
+
+	spin_lock_irqsave(&dev->devres_lock, flags);
+
+	grp = find_group(dev, id);
+	if (grp) {
+		list_del_init(&grp->node[0].entry);
+		list_del_init(&grp->node[1].entry);
+		devres_log(dev, &grp->node[0], "REM");
+	} else
+		WARN_ON(1);
+
+	spin_unlock_irqrestore(&dev->devres_lock, flags);
+
+	kfree(grp);
+}
+EXPORT_SYMBOL_GPL(devres_remove_group);
+
+/**
+ * devres_release_group - Release resources in a devres group
+ * @dev: Device to release group for
+ * @id: ID of target group, can be NULL
+ *
+ * Release all resources in the group identified by @id.  If @id is
+ * NULL, the latest open group is selected.  The selected group and
+ * groups properly nested inside the selected group are removed.
+ *
+ * RETURNS:
+ * The number of released non-group resources.
+ */
+int devres_release_group(struct device *dev, void *id)
+{
+	struct devres_group *grp;
+	unsigned long flags;
+	int cnt = 0;
+
+	spin_lock_irqsave(&dev->devres_lock, flags);
+
+	grp = find_group(dev, id);
+	if (grp) {
+		struct list_head *first = &grp->node[0].entry;
+		struct list_head *end = &dev->devres_head;
+
+		if (!list_empty(&grp->node[1].entry))
+			end = grp->node[1].entry.next;
+
+		cnt = release_nodes(dev, first, end, flags);
+	} else {
+		WARN_ON(1);
+		spin_unlock_irqrestore(&dev->devres_lock, flags);
+	}
+
+	return cnt;
+}
+EXPORT_SYMBOL_GPL(devres_release_group);
+
+/*
+ * Custom devres actions allow inserting a simple function call
+ * into the teadown sequence.
+ */
+
+struct action_devres {
+	void *data;
+	void (*action)(void *);
+};
+
+static int devm_action_match(struct device *dev, void *res, void *p)
+{
+	struct action_devres *devres = res;
+	struct action_devres *target = p;
+
+	return devres->action == target->action &&
+	       devres->data == target->data;
+}
+
+static void devm_action_release(struct device *dev, void *res)
+{
+	struct action_devres *devres = res;
+
+	devres->action(devres->data);
+}
+
+/**
+ * devm_add_action() - add a custom action to list of managed resources
+ * @dev: Device that owns the action
+ * @action: Function that should be called
+ * @data: Pointer to data passed to @action implementation
+ *
+ * This adds a custom action to the list of managed resources so that
+ * it gets executed as part of standard resource unwinding.
+ */
+int devm_add_action(struct device *dev, void (*action)(void *), void *data)
+{
+	struct action_devres *devres;
+
+	devres = devres_alloc(devm_action_release,
+			      sizeof(struct action_devres), GFP_KERNEL);
+	if (!devres)
+		return -ENOMEM;
+
+	devres->data = data;
+	devres->action = action;
+
+	devres_add(dev, devres);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(devm_add_action);
+
+/**
+ * devm_remove_action() - removes previously added custom action
+ * @dev: Device that owns the action
+ * @action: Function implementing the action
+ * @data: Pointer to data passed to @action implementation
+ *
+ * Removes instance of @action previously added by devm_add_action().
+ * Both action and data should match one of the existing entries.
+ */
+void devm_remove_action(struct device *dev, void (*action)(void *), void *data)
+{
+	struct action_devres devres = {
+		.data = data,
+		.action = action,
+	};
+
+	WARN_ON(devres_destroy(dev, devm_action_release, devm_action_match,
+			       &devres));
+
+}
+EXPORT_SYMBOL_GPL(devm_remove_action);
+
+/*
+ * Managed kzalloc/kfree
+ */
+static void devm_kzalloc_release(struct device *dev, void *res)
+{
+	/* noop */
+}
+
+static int devm_kzalloc_match(struct device *dev, void *res, void *data)
+{
+	return res == data;
+}
+
+/**
+ * devm_kzalloc - Resource-managed kzalloc
+ * @dev: Device to allocate memory for
+ * @size: Allocation size
+ * @gfp: Allocation gfp flags
+ *
+ * Managed kzalloc.  Memory allocated with this function is
+ * automatically freed on driver detach.  Like all other devres
+ * resources, guaranteed alignment is unsigned long long.
+ *
+ * RETURNS:
+ * Pointer to allocated memory on success, NULL on failure.
+ */
+void * devm_kzalloc(struct device *dev, size_t size, gfp_t gfp)
+{
+	struct devres *dr;
+
+	/* use raw alloc_dr for kmalloc caller tracing */
+	dr = alloc_dr(devm_kzalloc_release, size, gfp);
+	if (unlikely(!dr))
+		return NULL;
+
+	set_node_dbginfo(&dr->node, "devm_kzalloc_release", size);
+	devres_add(dev, dr->data);
+	return dr->data;
+}
+EXPORT_SYMBOL_GPL(devm_kzalloc);
+
+/**
+ * devm_kfree - Resource-managed kfree
+ * @dev: Device this memory belongs to
+ * @p: Memory to free
+ *
+ * Free memory allocated with devm_kzalloc().
+ */
+void devm_kfree(struct device *dev, void *p)
+{
+	int rc;
+
+	rc = devres_destroy(dev, devm_kzalloc_release, devm_kzalloc_match, p);
+	WARN_ON(rc);
+}
+EXPORT_SYMBOL_GPL(devm_kfree);

drivers/base/devtmpfs.c

@@ -0,0 +1,447 @@
+/*
+ * devtmpfs - kernel-maintained tmpfs-based /dev
+ *
+ * Copyright (C) 2009, Kay Sievers <kay.sievers@vrfy.org>
+ *
+ * During bootup, before any driver core device is registered,
+ * devtmpfs, a tmpfs-based filesystem is created. Every driver-core
+ * device which requests a device node, will add a node in this
+ * filesystem.
+ * By default, all devices are named after the name of the device,
+ * owned by root and have a default mode of 0600. Subsystems can
+ * overwrite the default setting if needed.
+ */
+
+#include <linux/kernel.h>
+#include <linux/syscalls.h>
+#include <linux/mount.h>
+#include <linux/device.h>
+#include <linux/genhd.h>
+#include <linux/namei.h>
+#include <linux/fs.h>
+#include <linux/shmem_fs.h>
+#include <linux/ramfs.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/kthread.h>
+#include "base.h"
+
+static struct task_struct *thread;
+
+#if defined CONFIG_DEVTMPFS_MOUNT
+static int mount_dev = 1;
+#else
+static int mount_dev;
+#endif
+
+static DEFINE_SPINLOCK(req_lock);
+
+static struct req {
+	struct req *next;
+	struct completion done;
+	int err;
+	const char *name;
+	umode_t mode;	/* 0 => delete */
+	kuid_t uid;
+	kgid_t gid;
+	struct device *dev;
+} *requests;
+
+static int __init mount_param(char *str)
+{
+	mount_dev = simple_strtoul(str, NULL, 0);
+	return 1;
+}
+__setup("devtmpfs.mount=", mount_param);
+
+static struct dentry *dev_mount(struct file_system_type *fs_type, int flags,
+		      const char *dev_name, void *data)
+{
+#ifdef CONFIG_TMPFS
+	return mount_single(fs_type, flags, data, shmem_fill_super);
+#else
+	return mount_single(fs_type, flags, data, ramfs_fill_super);
+#endif
+}
+
+static struct file_system_type dev_fs_type = {
+	.name = "devtmpfs",
+	.mount = dev_mount,
+	.kill_sb = kill_litter_super,
+};
+
+#ifdef CONFIG_BLOCK
+static inline int is_blockdev(struct device *dev)
+{
+	return dev->class == &block_class;
+}
+#else
+static inline int is_blockdev(struct device *dev) { return 0; }
+#endif
+
+int devtmpfs_create_node(struct device *dev)
+{
+	const char *tmp = NULL;
+	struct req req;
+
+	if (!thread)
+		return 0;
+
+	req.mode = 0;
+	req.uid = GLOBAL_ROOT_UID;
+	req.gid = GLOBAL_ROOT_GID;
+	req.name = device_get_devnode(dev, &req.mode, &req.uid, &req.gid, &tmp);
+	if (!req.name)
+		return -ENOMEM;
+
+	if (req.mode == 0)
+		req.mode = 0600;
+	if (is_blockdev(dev))
+		req.mode |= S_IFBLK;
+	else
+		req.mode |= S_IFCHR;
+
+	req.dev = dev;
+
+	init_completion(&req.done);
+
+	spin_lock(&req_lock);
+	req.next = requests;
+	requests = &req;
+	spin_unlock(&req_lock);
+
+	wake_up_process(thread);
+	wait_for_completion(&req.done);
+
+	kfree(tmp);
+
+	return req.err;
+}
+
+int devtmpfs_delete_node(struct device *dev)
+{
+	const char *tmp = NULL;
+	struct req req;
+
+	if (!thread)
+		return 0;
+
+	req.name = device_get_devnode(dev, NULL, NULL, NULL, &tmp);
+	if (!req.name)
+		return -ENOMEM;
+
+	req.mode = 0;
+	req.dev = dev;
+
+	init_completion(&req.done);
+
+	spin_lock(&req_lock);
+	req.next = requests;
+	requests = &req;
+	spin_unlock(&req_lock);
+
+	wake_up_process(thread);
+	wait_for_completion(&req.done);
+
+	kfree(tmp);
+	return req.err;
+}
+
+static int dev_mkdir(const char *name, umode_t mode)
+{
+	struct dentry *dentry;
+	struct path path;
+	int err;
+
+	dentry = kern_path_create(AT_FDCWD, name, &path, LOOKUP_DIRECTORY);
+	if (IS_ERR(dentry))
+		return PTR_ERR(dentry);
+
+	err = vfs_mkdir(path.dentry->d_inode, dentry, mode);
+	if (!err)
+		/* mark as kernel-created inode */
+		dentry->d_inode->i_private = &thread;
+	done_path_create(&path, dentry);
+	return err;
+}
+
+static int create_path(const char *nodepath)
+{
+	char *path;
+	char *s;
+	int err = 0;
+
+	/* parent directories do not exist, create them */
+	path = kstrdup(nodepath, GFP_KERNEL);
+	if (!path)
+		return -ENOMEM;
+
+	s = path;
+	for (;;) {
+		s = strchr(s, '/');
+		if (!s)
+			break;
+		s[0] = '\0';
+		err = dev_mkdir(path, 0755);
+		if (err && err != -EEXIST)
+			break;
+		s[0] = '/';
+		s++;
+	}
+	kfree(path);
+	return err;
+}
+
+static int handle_create(const char *nodename, umode_t mode, kuid_t uid,
+			 kgid_t gid, struct device *dev)
+{
+	struct dentry *dentry;
+	struct path path;
+	int err;
+
+	dentry = kern_path_create(AT_FDCWD, nodename, &path, 0);
+	if (dentry == ERR_PTR(-ENOENT)) {
+		create_path(nodename);
+		dentry = kern_path_create(AT_FDCWD, nodename, &path, 0);
+	}
+	if (IS_ERR(dentry))
+		return PTR_ERR(dentry);
+
+	err = vfs_mknod(path.dentry->d_inode, dentry, mode, dev->devt);
+	if (!err) {
+		struct iattr newattrs;
+
+		newattrs.ia_mode = mode;
+		newattrs.ia_uid = uid;
+		newattrs.ia_gid = gid;
+		newattrs.ia_valid = ATTR_MODE|ATTR_UID|ATTR_GID;
+		mutex_lock(&dentry->d_inode->i_mutex);
+		notify_change(dentry, &newattrs);
+		mutex_unlock(&dentry->d_inode->i_mutex);
+
+		/* mark as kernel-created inode */
+		dentry->d_inode->i_private = &thread;
+	}
+	done_path_create(&path, dentry);
+	return err;
+}
+
+static int dev_rmdir(const char *name)
+{
+	struct path parent;
+	struct dentry *dentry;
+	int err;
+
+	dentry = kern_path_locked(name, &parent);
+	if (IS_ERR(dentry))
+		return PTR_ERR(dentry);
+	if (dentry->d_inode) {
+		if (dentry->d_inode->i_private == &thread)
+			err = vfs_rmdir(parent.dentry->d_inode, dentry);
+		else
+			err = -EPERM;
+	} else {
+		err = -ENOENT;
+	}
+	dput(dentry);
+	mutex_unlock(&parent.dentry->d_inode->i_mutex);
+	path_put(&parent);
+	return err;
+}
+
+static int delete_path(const char *nodepath)
+{
+	const char *path;
+	int err = 0;
+
+	path = kstrdup(nodepath, GFP_KERNEL);
+	if (!path)
+		return -ENOMEM;
+
+	for (;;) {
+		char *base;
+
+		base = strrchr(path, '/');
+		if (!base)
+			break;
+		base[0] = '\0';
+		err = dev_rmdir(path);
+		if (err)
+			break;
+	}
+
+	kfree(path);
+	return err;
+}
+
+static int dev_mynode(struct device *dev, struct inode *inode, struct kstat *stat)
+{
+	/* did we create it */
+	if (inode->i_private != &thread)
+		return 0;
+
+	/* does the dev_t match */
+	if (is_blockdev(dev)) {
+		if (!S_ISBLK(stat->mode))
+			return 0;
+	} else {
+		if (!S_ISCHR(stat->mode))
+			return 0;
+	}
+	if (stat->rdev != dev->devt)
+		return 0;
+
+	/* ours */
+	return 1;
+}
+
+static int handle_remove(const char *nodename, struct device *dev)
+{
+	struct path parent;
+	struct dentry *dentry;
+	int deleted = 1;
+	int err;
+
+	dentry = kern_path_locked(nodename, &parent);
+	if (IS_ERR(dentry))
+		return PTR_ERR(dentry);
+
+	if (dentry->d_inode) {
+		struct kstat stat;
+		struct path p = {.mnt = parent.mnt, .dentry = dentry};
+		err = vfs_getattr(&p, &stat);
+		if (!err && dev_mynode(dev, dentry->d_inode, &stat)) {
+			struct iattr newattrs;
+			/*
+			 * before unlinking this node, reset permissions
+			 * of possible references like hardlinks
+			 */
+			newattrs.ia_uid = GLOBAL_ROOT_UID;
+			newattrs.ia_gid = GLOBAL_ROOT_GID;
+			newattrs.ia_mode = stat.mode & ~0777;
+			newattrs.ia_valid =
+				ATTR_UID|ATTR_GID|ATTR_MODE;
+			mutex_lock(&dentry->d_inode->i_mutex);
+			notify_change(dentry, &newattrs);
+			mutex_unlock(&dentry->d_inode->i_mutex);
+			err = vfs_unlink(parent.dentry->d_inode, dentry);
+			if (!err || err == -ENOENT)
+				deleted = 1;
+		}
+	} else {
+		err = -ENOENT;
+	}
+	dput(dentry);
+	mutex_unlock(&parent.dentry->d_inode->i_mutex);
+
+	path_put(&parent);
+	if (deleted && strchr(nodename, '/'))
+		delete_path(nodename);
+	return err;
+}
+
+/*
+ * If configured, or requested by the commandline, devtmpfs will be
+ * auto-mounted after the kernel mounted the root filesystem.
+ */
+int devtmpfs_mount(const char *mntdir)
+{
+	int err;
+	int mflags = MS_SILENT;
+
+	if (!mount_dev)
+		return 0;
+
+	if (!thread)
+		return 0;
+
+#ifdef CONFIG_DEVTMPFS_SAFE
+	mflags |= MS_NOEXEC | MS_NOSUID;
+#endif
+	err = sys_mount("devtmpfs", (char *)mntdir, "devtmpfs", mflags, NULL);
+	if (err)
+		printk(KERN_INFO "devtmpfs: error mounting %i\n", err);
+	else
+		printk(KERN_INFO "devtmpfs: mounted\n");
+	return err;
+}
+
+static DECLARE_COMPLETION(setup_done);
+
+static int handle(const char *name, umode_t mode, kuid_t uid, kgid_t gid,
+		  struct device *dev)
+{
+	if (mode)
+		return handle_create(name, mode, uid, gid, dev);
+	else
+		return handle_remove(name, dev);
+}
+
+static int devtmpfsd(void *p)
+{
+	char options[] = "mode=0755";
+	int *err = p;
+	*err = sys_unshare(CLONE_NEWNS);
+	if (*err)
+		goto out;
+	*err = sys_mount("devtmpfs", "/", "devtmpfs", MS_SILENT, options);
+	if (*err)
+		goto out;
+	sys_chdir("/.."); /* will traverse into overmounted root */
+	sys_chroot(".");
+	complete(&setup_done);
+	while (1) {
+		spin_lock(&req_lock);
+		while (requests) {
+			struct req *req = requests;
+			requests = NULL;
+			spin_unlock(&req_lock);
+			while (req) {
+				struct req *next = req->next;
+				req->err = handle(req->name, req->mode,
+						  req->uid, req->gid, req->dev);
+				complete(&req->done);
+				req = next;
+			}
+			spin_lock(&req_lock);
+		}
+		__set_current_state(TASK_INTERRUPTIBLE);
+		spin_unlock(&req_lock);
+		schedule();
+	}
+	return 0;
+out:
+	complete(&setup_done);
+	return *err;
+}
+
+/*
+ * Create devtmpfs instance, driver-core devices will add their device
+ * nodes here.
+ */
+int __init devtmpfs_init(void)
+{
+	int err = register_filesystem(&dev_fs_type);
+	if (err) {
+		printk(KERN_ERR "devtmpfs: unable to register devtmpfs "
+		       "type %i\n", err);
+		return err;
+	}
+
+	thread = kthread_run(devtmpfsd, &err, "kdevtmpfs");
+	if (!IS_ERR(thread)) {
+		wait_for_completion(&setup_done);
+	} else {
+		err = PTR_ERR(thread);
+		thread = NULL;
+	}
+
+	if (err) {
+		printk(KERN_ERR "devtmpfs: unable to create devtmpfs %i\n", err);
+		unregister_filesystem(&dev_fs_type);
+		return err;
+	}
+
+	printk(KERN_INFO "devtmpfs: initialized\n");
+	return 0;
+}

drivers/base/dma-buf.c

@@ -0,0 +1,836 @@
+/*
+ * Framework for buffer objects that can be shared across devices/subsystems.
+ *
+ * Copyright(C) 2011 Linaro Limited. All rights reserved.
+ * Author: Sumit Semwal <sumit.semwal@ti.com>
+ *
+ * Many thanks to linaro-mm-sig list, and specially
+ * Arnd Bergmann <arnd@arndb.de>, Rob Clark <rob@ti.com> and
+ * Daniel Vetter <daniel@ffwll.ch> for their support in creation and
+ * refining of this idea.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/fs.h>
+#include <linux/slab.h>
+#include <linux/dma-buf.h>
+#include <linux/anon_inodes.h>
+#include <linux/export.h>
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
+#include <linux/uaccess.h>
+
+#include <uapi/linux/dma-buf.h>
+
+static inline int is_dma_buf_file(struct file *);
+
+struct dma_buf_list {
+	struct list_head head;
+	struct mutex lock;
+};
+
+static struct dma_buf_list db_list;
+
+/**
+ * dma_buf_set_drvdata - Set driver specific data to dmabuf. The data
+ * will remain even if the device is detached from the device. This is useful
+ * if the device requires some buffer specific parameters that should be
+ * available when the buffer is accessed next time.
+ *
+ * The exporter calls the destroy callback:
+ *  - the buffer is freed
+ *  - the device/driver is removed
+ *  - new device private data is set
+ *
+ * @dmabuf	[in]	Buffer object
+ * @device	[in]	Device to which the data is related to.
+ * @priv	[in]	Private data
+ * @destroy	[in]	Function callback to destroy function. Called when the
+ *			data is not needed anymore (device or dmabuf is
+ *			removed)
+ *
+ * The function returns 0 on success. Otherwise the function returns a negative
+ * errorcode
+ */
+int dma_buf_set_drvdata(struct dma_buf * dmabuf, struct device *device,
+			void *priv, void (*destroy)(void *))
+{
+	if (!(dmabuf && dmabuf->ops && dmabuf->ops->set_drvdata))
+		return -ENOSYS;
+
+	return dmabuf->ops->set_drvdata(dmabuf, device, priv, destroy);
+}
+EXPORT_SYMBOL(dma_buf_set_drvdata);
+
+/**
+ * dma_buf_get_drvdata - Get driver specific data to dmabuf.
+ *
+ * @dmabuf	[in]	Buffer object
+ * @device	[in]	Device to which the data is related to.
+ *
+ * The function returns the user data structure on success. Otherwise NULL
+ * is returned.
+ */
+void *dma_buf_get_drvdata(struct dma_buf *dmabuf, struct device *device)
+{
+	if (!(dmabuf && dmabuf->ops && dmabuf->ops->get_drvdata))
+		return ERR_PTR(-ENOSYS);
+
+	return dmabuf->ops->get_drvdata(dmabuf, device);
+}
+EXPORT_SYMBOL(dma_buf_get_drvdata);
+
+
+static int dma_buf_release(struct inode *inode, struct file *file)
+{
+	struct dma_buf *dmabuf;
+
+	if (!is_dma_buf_file(file))
+		return -EINVAL;
+
+	dmabuf = file->private_data;
+
+	BUG_ON(dmabuf->vmapping_counter);
+
+	dmabuf->ops->release(dmabuf);
+
+	mutex_lock(&db_list.lock);
+	list_del(&dmabuf->list_node);
+	mutex_unlock(&db_list.lock);
+
+	kfree(dmabuf);
+	return 0;
+}
+
+static int dma_buf_mmap_internal(struct file *file, struct vm_area_struct *vma)
+{
+	struct dma_buf *dmabuf;
+
+	if (!is_dma_buf_file(file))
+		return -EINVAL;
+
+	dmabuf = file->private_data;
+
+	/* check for overflowing the buffer's size */
+	if (vma->vm_pgoff + ((vma->vm_end - vma->vm_start) >> PAGE_SHIFT) >
+	    dmabuf->size >> PAGE_SHIFT)
+		return -EINVAL;
+
+	return dmabuf->ops->mmap(dmabuf, vma);
+}
+
+static loff_t dma_buf_llseek(struct file *file, loff_t offset, int whence)
+{
+	struct dma_buf *dmabuf;
+	loff_t base;
+
+	if (!is_dma_buf_file(file))
+		return -EBADF;
+
+	dmabuf = file->private_data;
+
+	/* only support discovering the end of the buffer,
+	   but also allow SEEK_SET to maintain the idiomatic
+	   SEEK_END(0), SEEK_CUR(0) pattern */
+	if (whence == SEEK_END)
+		base = dmabuf->size;
+	else if (whence == SEEK_SET)
+		base = 0;
+	else
+		return -EINVAL;
+
+	if (offset != 0)
+		return -EINVAL;
+
+	return base + offset;
+}
+
+static long dma_buf_ioctl(struct file *file,
+				unsigned int cmd, unsigned long arg)
+{
+	struct dma_buf *dmabuf;
+	struct dma_buf_sync sync;
+	enum dma_data_direction direction;
+	int ret;
+
+	dmabuf = file->private_data;
+
+	switch (cmd) {
+	case DMA_BUF_IOCTL_SYNC:
+		if (copy_from_user(&sync, (void __user *) arg, sizeof(sync)))
+			return -EFAULT;
+
+		if (sync.flags & ~DMA_BUF_SYNC_VALID_FLAGS_MASK)
+			return -EINVAL;
+
+		switch (sync.flags & DMA_BUF_SYNC_RW) {
+		case DMA_BUF_SYNC_READ:
+			direction = DMA_FROM_DEVICE;
+			break;
+		case DMA_BUF_SYNC_WRITE:
+			direction = DMA_TO_DEVICE;
+			break;
+		case DMA_BUF_SYNC_RW:
+			direction = DMA_BIDIRECTIONAL;
+			break;
+		default:
+			return -EINVAL;
+		}
+
+		if (sync.flags & DMA_BUF_SYNC_END)
+			ret = dma_buf_end_cpu_access(dmabuf, direction);
+		else
+			ret = dma_buf_begin_cpu_access(dmabuf, direction);
+
+		return ret;
+	default:
+		return -ENOTTY;
+	}
+}
+
+static const struct file_operations dma_buf_fops = {
+	.release	= dma_buf_release,
+	.mmap		= dma_buf_mmap_internal,
+	.llseek		= dma_buf_llseek,
+	.unlocked_ioctl = dma_buf_ioctl,
+};
+
+/*
+ * is_dma_buf_file - Check if struct file* is associated with dma_buf
+ */
+static inline int is_dma_buf_file(struct file *file)
+{
+	return file->f_op == &dma_buf_fops;
+}
+
+/**
+ * dma_buf_export_named - Creates a new dma_buf, and associates an anon file
+ * with this buffer, so it can be exported.
+ * Also connect the allocator specific data and ops to the buffer.
+ * Additionally, provide a name string for exporter; useful in debugging.
+ *
+ * @priv:	[in]	Attach private data of allocator to this buffer
+ * @ops:	[in]	Attach allocator-defined dma buf ops to the new buffer.
+ * @size:	[in]	Size of the buffer
+ * @flags:	[in]	mode flags for the file.
+ * @exp_name:	[in]	name of the exporting module - useful for debugging.
+ *
+ * Returns, on success, a newly created dma_buf object, which wraps the
+ * supplied private data and operations for dma_buf_ops. On either missing
+ * ops, or error in allocating struct dma_buf, will return negative error.
+ *
+ */
+struct dma_buf *dma_buf_export_named(void *priv, const struct dma_buf_ops *ops,
+				size_t size, int flags, const char *exp_name)
+{
+	struct dma_buf *dmabuf;
+	struct file *file;
+
+	if (WARN_ON(!priv || !ops
+			  || !ops->map_dma_buf
+			  || !ops->unmap_dma_buf
+			  || !ops->release
+			  || !ops->kmap_atomic
+			  || !ops->kmap
+			  || !ops->mmap)) {
+		return ERR_PTR(-EINVAL);
+	}
+
+	dmabuf = kzalloc(sizeof(struct dma_buf), GFP_KERNEL);
+	if (dmabuf == NULL)
+		return ERR_PTR(-ENOMEM);
+
+	dmabuf->priv = priv;
+	dmabuf->ops = ops;
+	dmabuf->size = size;
+	dmabuf->exp_name = exp_name;
+
+	file = anon_inode_getfile("dmabuf", &dma_buf_fops, dmabuf, flags);
+
+	file->f_mode |= FMODE_LSEEK;
+	dmabuf->file = file;
+
+	mutex_init(&dmabuf->lock);
+	INIT_LIST_HEAD(&dmabuf->attachments);
+
+	mutex_lock(&db_list.lock);
+	list_add(&dmabuf->list_node, &db_list.head);
+	mutex_unlock(&db_list.lock);
+
+	return dmabuf;
+}
+EXPORT_SYMBOL_GPL(dma_buf_export_named);
+
+
+/**
+ * dma_buf_fd - returns a file descriptor for the given dma_buf
+ * @dmabuf:	[in]	pointer to dma_buf for which fd is required.
+ * @flags:      [in]    flags to give to fd
+ *
+ * On success, returns an associated 'fd'. Else, returns error.
+ */
+int dma_buf_fd(struct dma_buf *dmabuf, int flags)
+{
+	int fd;
+
+	if (!dmabuf || !dmabuf->file)
+		return -EINVAL;
+
+	fd = get_unused_fd_flags(flags);
+	if (fd < 0)
+		return fd;
+
+	fd_install(fd, dmabuf->file);
+
+	return fd;
+}
+EXPORT_SYMBOL_GPL(dma_buf_fd);
+
+/**
+ * dma_buf_get - returns the dma_buf structure related to an fd
+ * @fd:	[in]	fd associated with the dma_buf to be returned
+ *
+ * On success, returns the dma_buf structure associated with an fd; uses
+ * file's refcounting done by fget to increase refcount. returns ERR_PTR
+ * otherwise.
+ */
+struct dma_buf *dma_buf_get(int fd)
+{
+	struct file *file;
+
+	file = fget(fd);
+
+	if (!file)
+		return ERR_PTR(-EBADF);
+
+	if (!is_dma_buf_file(file)) {
+		fput(file);
+		return ERR_PTR(-EINVAL);
+	}
+
+	return file->private_data;
+}
+EXPORT_SYMBOL_GPL(dma_buf_get);
+
+/**
+ * dma_buf_put - decreases refcount of the buffer
+ * @dmabuf:	[in]	buffer to reduce refcount of
+ *
+ * Uses file's refcounting done implicitly by fput()
+ */
+void dma_buf_put(struct dma_buf *dmabuf)
+{
+	if (WARN_ON(!dmabuf || !dmabuf->file))
+		return;
+
+	fput(dmabuf->file);
+}
+EXPORT_SYMBOL_GPL(dma_buf_put);
+
+/**
+ * dma_buf_attach - Add the device to dma_buf's attachments list; optionally,
+ * calls attach() of dma_buf_ops to allow device-specific attach functionality
+ * @dmabuf:	[in]	buffer to attach device to.
+ * @dev:	[in]	device to be attached.
+ *
+ * Returns struct dma_buf_attachment * for this attachment; may return negative
+ * error codes.
+ *
+ */
+struct dma_buf_attachment *dma_buf_attach(struct dma_buf *dmabuf,
+					  struct device *dev)
+{
+	struct dma_buf_attachment *attach;
+	int ret;
+
+	if (WARN_ON(!dmabuf || !dev))
+		return ERR_PTR(-EINVAL);
+
+	attach = kzalloc(sizeof(struct dma_buf_attachment), GFP_KERNEL);
+	if (attach == NULL)
+		return ERR_PTR(-ENOMEM);
+
+	attach->dev = dev;
+	attach->dmabuf = dmabuf;
+
+	mutex_lock(&dmabuf->lock);
+
+	if (dmabuf->ops->attach) {
+		ret = dmabuf->ops->attach(dmabuf, dev, attach);
+		if (ret)
+			goto err_attach;
+	}
+	list_add(&attach->node, &dmabuf->attachments);
+
+	mutex_unlock(&dmabuf->lock);
+	return attach;
+
+err_attach:
+	kfree(attach);
+	mutex_unlock(&dmabuf->lock);
+	return ERR_PTR(ret);
+}
+EXPORT_SYMBOL_GPL(dma_buf_attach);
+
+/**
+ * dma_buf_detach - Remove the given attachment from dmabuf's attachments list;
+ * optionally calls detach() of dma_buf_ops for device-specific detach
+ * @dmabuf:	[in]	buffer to detach from.
+ * @attach:	[in]	attachment to be detached; is free'd after this call.
+ *
+ */
+void dma_buf_detach(struct dma_buf *dmabuf, struct dma_buf_attachment *attach)
+{
+	if (WARN_ON(!dmabuf || !attach))
+		return;
+
+	mutex_lock(&dmabuf->lock);
+	list_del(&attach->node);
+	if (dmabuf->ops->detach)
+		dmabuf->ops->detach(dmabuf, attach);
+
+	mutex_unlock(&dmabuf->lock);
+	kfree(attach);
+}
+EXPORT_SYMBOL_GPL(dma_buf_detach);
+
+/**
+ * dma_buf_map_attachment - Returns the scatterlist table of the attachment;
+ * mapped into _device_ address space. Is a wrapper for map_dma_buf() of the
+ * dma_buf_ops.
+ * @attach:	[in]	attachment whose scatterlist is to be returned
+ * @direction:	[in]	direction of DMA transfer
+ *
+ * Returns sg_table containing the scatterlist to be returned; may return NULL
+ * or ERR_PTR.
+ *
+ */
+struct sg_table *dma_buf_map_attachment(struct dma_buf_attachment *attach,
+					enum dma_data_direction direction)
+{
+	struct sg_table *sg_table = ERR_PTR(-EINVAL);
+
+	might_sleep();
+
+	if (WARN_ON(!attach || !attach->dmabuf))
+		return ERR_PTR(-EINVAL);
+
+	sg_table = attach->dmabuf->ops->map_dma_buf(attach, direction);
+
+	return sg_table;
+}
+EXPORT_SYMBOL_GPL(dma_buf_map_attachment);
+
+/**
+ * dma_buf_unmap_attachment - unmaps and decreases usecount of the buffer;might
+ * deallocate the scatterlist associated. Is a wrapper for unmap_dma_buf() of
+ * dma_buf_ops.
+ * @attach:	[in]	attachment to unmap buffer from
+ * @sg_table:	[in]	scatterlist info of the buffer to unmap
+ * @direction:  [in]    direction of DMA transfer
+ *
+ */
+void dma_buf_unmap_attachment(struct dma_buf_attachment *attach,
+				struct sg_table *sg_table,
+				enum dma_data_direction direction)
+{
+	might_sleep();
+
+	if (WARN_ON(!attach || !attach->dmabuf || !sg_table))
+		return;
+
+	attach->dmabuf->ops->unmap_dma_buf(attach, sg_table,
+						direction);
+}
+EXPORT_SYMBOL_GPL(dma_buf_unmap_attachment);
+
+
+/**
+ * dma_buf_begin_cpu_access - Must be called before accessing a dma_buf from the
+ * cpu in the kernel context. Calls begin_cpu_access to allow exporter-specific
+ * preparations. Coherency is only guaranteed in the specified range for the
+ * specified access direction.
+ * @dmabuf:	[in]	buffer to prepare cpu access for.
+ * @direction:	[in]	length of range for cpu access.
+ *
+ * Can return negative error values, returns 0 on success.
+ */
+int dma_buf_begin_cpu_access(struct dma_buf *dmabuf,
+			     enum dma_data_direction direction)
+{
+	int ret = 0;
+
+	if (WARN_ON(!dmabuf))
+		return -EINVAL;
+
+	if (dmabuf->ops->begin_cpu_access)
+		ret = dmabuf->ops->begin_cpu_access(dmabuf, direction);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(dma_buf_begin_cpu_access);
+
+/**
+ * dma_buf_end_cpu_access - Must be called after accessing a dma_buf from the
+ * cpu in the kernel context. Calls end_cpu_access to allow exporter-specific
+ * actions. Coherency is only guaranteed in the specified range for the
+ * specified access direction.
+ * @dmabuf:	[in]	buffer to complete cpu access for.
+ * @direction:	[in]	length of range for cpu access.
+ *
+ * This call must always succeed.
+ */
+int dma_buf_end_cpu_access(struct dma_buf *dmabuf,
+			   enum dma_data_direction direction)
+{
+	int ret = 0;
+
+	WARN_ON(!dmabuf);
+
+	if (dmabuf->ops->end_cpu_access)
+		ret = dmabuf->ops->end_cpu_access(dmabuf, direction);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(dma_buf_end_cpu_access);
+
+/**
+ * dma_buf_kmap_atomic - Map a page of the buffer object into kernel address
+ * space. The same restrictions as for kmap_atomic and friends apply.
+ * @dmabuf:	[in]	buffer to map page from.
+ * @page_num:	[in]	page in PAGE_SIZE units to map.
+ *
+ * This call must always succeed, any necessary preparations that might fail
+ * need to be done in begin_cpu_access.
+ */
+void *dma_buf_kmap_atomic(struct dma_buf *dmabuf, unsigned long page_num)
+{
+	WARN_ON(!dmabuf);
+
+	return dmabuf->ops->kmap_atomic(dmabuf, page_num);
+}
+EXPORT_SYMBOL_GPL(dma_buf_kmap_atomic);
+
+/**
+ * dma_buf_kunmap_atomic - Unmap a page obtained by dma_buf_kmap_atomic.
+ * @dmabuf:	[in]	buffer to unmap page from.
+ * @page_num:	[in]	page in PAGE_SIZE units to unmap.
+ * @vaddr:	[in]	kernel space pointer obtained from dma_buf_kmap_atomic.
+ *
+ * This call must always succeed.
+ */
+void dma_buf_kunmap_atomic(struct dma_buf *dmabuf, unsigned long page_num,
+			   void *vaddr)
+{
+	WARN_ON(!dmabuf);
+
+	if (dmabuf->ops->kunmap_atomic)
+		dmabuf->ops->kunmap_atomic(dmabuf, page_num, vaddr);
+}
+EXPORT_SYMBOL_GPL(dma_buf_kunmap_atomic);
+
+/**
+ * dma_buf_kmap - Map a page of the buffer object into kernel address space. The
+ * same restrictions as for kmap and friends apply.
+ * @dmabuf:	[in]	buffer to map page from.
+ * @page_num:	[in]	page in PAGE_SIZE units to map.
+ *
+ * This call must always succeed, any necessary preparations that might fail
+ * need to be done in begin_cpu_access.
+ */
+void *dma_buf_kmap(struct dma_buf *dmabuf, unsigned long page_num)
+{
+	WARN_ON(!dmabuf);
+
+	return dmabuf->ops->kmap(dmabuf, page_num);
+}
+EXPORT_SYMBOL_GPL(dma_buf_kmap);
+
+/**
+ * dma_buf_kunmap - Unmap a page obtained by dma_buf_kmap.
+ * @dmabuf:	[in]	buffer to unmap page from.
+ * @page_num:	[in]	page in PAGE_SIZE units to unmap.
+ * @vaddr:	[in]	kernel space pointer obtained from dma_buf_kmap.
+ *
+ * This call must always succeed.
+ */
+void dma_buf_kunmap(struct dma_buf *dmabuf, unsigned long page_num,
+		    void *vaddr)
+{
+	WARN_ON(!dmabuf);
+
+	if (dmabuf->ops->kunmap)
+		dmabuf->ops->kunmap(dmabuf, page_num, vaddr);
+}
+EXPORT_SYMBOL_GPL(dma_buf_kunmap);
+
+
+/**
+ * dma_buf_mmap - Setup up a userspace mmap with the given vma
+ * @dmabuf:	[in]	buffer that should back the vma
+ * @vma:	[in]	vma for the mmap
+ * @pgoff:	[in]	offset in pages where this mmap should start within the
+ * 			dma-buf buffer.
+ *
+ * This function adjusts the passed in vma so that it points at the file of the
+ * dma_buf operation. It alsog adjusts the starting pgoff and does bounds
+ * checking on the size of the vma. Then it calls the exporters mmap function to
+ * set up the mapping.
+ *
+ * Can return negative error values, returns 0 on success.
+ */
+int dma_buf_mmap(struct dma_buf *dmabuf, struct vm_area_struct *vma,
+		 unsigned long pgoff)
+{
+	struct file *oldfile;
+	int ret;
+
+	if (WARN_ON(!dmabuf || !vma))
+		return -EINVAL;
+
+	/* check for offset overflow */
+	if (pgoff + ((vma->vm_end - vma->vm_start) >> PAGE_SHIFT) < pgoff)
+		return -EOVERFLOW;
+
+	/* check for overflowing the buffer's size */
+	if (pgoff + ((vma->vm_end - vma->vm_start) >> PAGE_SHIFT) >
+	    dmabuf->size >> PAGE_SHIFT)
+		return -EINVAL;
+
+	/* readjust the vma */
+	get_file(dmabuf->file);
+	oldfile = vma->vm_file;
+	vma->vm_file = dmabuf->file;
+	vma->vm_pgoff = pgoff;
+
+	ret = dmabuf->ops->mmap(dmabuf, vma);
+	if (ret) {
+		/* restore old parameters on failure */
+		vma->vm_file = oldfile;
+		fput(dmabuf->file);
+	} else {
+		if (oldfile)
+			fput(oldfile);
+	}
+	return ret;
+
+}
+EXPORT_SYMBOL_GPL(dma_buf_mmap);
+
+/**
+ * dma_buf_vmap - Create virtual mapping for the buffer object into kernel
+ * address space. Same restrictions as for vmap and friends apply.
+ * @dmabuf:	[in]	buffer to vmap
+ *
+ * This call may fail due to lack of virtual mapping address space.
+ * These calls are optional in drivers. The intended use for them
+ * is for mapping objects linear in kernel space for high use objects.
+ * Please attempt to use kmap/kunmap before thinking about these interfaces.
+ */
+void *dma_buf_vmap(struct dma_buf *dmabuf)
+{
+	void *ptr;
+
+	if (WARN_ON(!dmabuf))
+		return NULL;
+
+	if (!dmabuf->ops->vmap)
+		return NULL;
+
+	mutex_lock(&dmabuf->lock);
+	if (dmabuf->vmapping_counter) {
+		dmabuf->vmapping_counter++;
+		BUG_ON(!dmabuf->vmap_ptr);
+		ptr = dmabuf->vmap_ptr;
+		goto out_unlock;
+	}
+
+	BUG_ON(dmabuf->vmap_ptr);
+
+	ptr = dmabuf->ops->vmap(dmabuf);
+	if (IS_ERR_OR_NULL(ptr))
+		goto out_unlock;
+
+	dmabuf->vmap_ptr = ptr;
+	dmabuf->vmapping_counter = 1;
+
+out_unlock:
+	mutex_unlock(&dmabuf->lock);
+	return ptr;
+}
+EXPORT_SYMBOL_GPL(dma_buf_vmap);
+
+/**
+ * dma_buf_vunmap - Unmap a vmap obtained by dma_buf_vmap.
+ * @dmabuf:	[in]	buffer to vunmap
+ * @vaddr:	[in]	vmap to vunmap
+ */
+void dma_buf_vunmap(struct dma_buf *dmabuf, void *vaddr)
+{
+	if (WARN_ON(!dmabuf))
+		return;
+
+	BUG_ON(!dmabuf->vmap_ptr);
+	BUG_ON(dmabuf->vmapping_counter == 0);
+	BUG_ON(dmabuf->vmap_ptr != vaddr);
+
+	mutex_lock(&dmabuf->lock);
+	if (--dmabuf->vmapping_counter == 0) {
+		if (dmabuf->ops->vunmap)
+			dmabuf->ops->vunmap(dmabuf, vaddr);
+		dmabuf->vmap_ptr = NULL;
+	}
+	mutex_unlock(&dmabuf->lock);
+}
+EXPORT_SYMBOL_GPL(dma_buf_vunmap);
+
+#ifdef CONFIG_DEBUG_FS
+static int dma_buf_describe(struct seq_file *s)
+{
+	int ret;
+	struct dma_buf *buf_obj;
+	struct dma_buf_attachment *attach_obj;
+	int count = 0, attach_count;
+	size_t size = 0;
+
+	ret = mutex_lock_interruptible(&db_list.lock);
+
+	if (ret)
+		return ret;
+
+	seq_printf(s, "\nDma-buf Objects:\n");
+	seq_printf(s, "\texp_name\tsize\tflags\tmode\tcount\n");
+
+	list_for_each_entry(buf_obj, &db_list.head, list_node) {
+		ret = mutex_lock_interruptible(&buf_obj->lock);
+
+		if (ret) {
+			seq_printf(s,
+				  "\tERROR locking buffer object: skipping\n");
+			continue;
+		}
+
+		seq_printf(s, "\t");
+
+		seq_printf(s, "\t%s\t%08zu\t%08x\t%08x\t%08ld\n",
+				buf_obj->exp_name, buf_obj->size,
+				buf_obj->file->f_flags, buf_obj->file->f_mode,
+				(long)(buf_obj->file->f_count.counter));
+
+		seq_printf(s, "\t\tAttached Devices:\n");
+		attach_count = 0;
+
+		list_for_each_entry(attach_obj, &buf_obj->attachments, node) {
+			seq_printf(s, "\t\t");
+
+			seq_printf(s, "%s\n", attach_obj->dev->init_name);
+			attach_count++;
+		}
+
+		seq_printf(s, "\n\t\tTotal %d devices attached\n",
+				attach_count);
+
+		count++;
+		size += buf_obj->size;
+		mutex_unlock(&buf_obj->lock);
+	}
+
+	seq_printf(s, "\nTotal %d objects, %zu bytes\n", count, size);
+
+	mutex_unlock(&db_list.lock);
+	return 0;
+}
+
+static int dma_buf_show(struct seq_file *s, void *unused)
+{
+	void (*func)(struct seq_file *) = s->private;
+	func(s);
+	return 0;
+}
+
+static int dma_buf_debug_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, dma_buf_show, inode->i_private);
+}
+
+static const struct file_operations dma_buf_debug_fops = {
+	.open           = dma_buf_debug_open,
+	.read           = seq_read,
+	.llseek         = seq_lseek,
+	.release        = single_release,
+};
+
+static struct dentry *dma_buf_debugfs_dir;
+
+static int dma_buf_init_debugfs(void)
+{
+	int err = 0;
+	dma_buf_debugfs_dir = debugfs_create_dir("dma_buf", NULL);
+	if (IS_ERR(dma_buf_debugfs_dir)) {
+		err = PTR_ERR(dma_buf_debugfs_dir);
+		dma_buf_debugfs_dir = NULL;
+		return err;
+	}
+
+	err = dma_buf_debugfs_create_file("bufinfo", dma_buf_describe);
+
+	if (err)
+		pr_debug("dma_buf: debugfs: failed to create node bufinfo\n");
+
+	return err;
+}
+
+static void dma_buf_uninit_debugfs(void)
+{
+	if (dma_buf_debugfs_dir)
+		debugfs_remove_recursive(dma_buf_debugfs_dir);
+}
+
+int dma_buf_debugfs_create_file(const char *name,
+				int (*write)(struct seq_file *))
+{
+	struct dentry *d;
+
+	d = debugfs_create_file(name, S_IRUGO, dma_buf_debugfs_dir,
+			write, &dma_buf_debug_fops);
+
+	if (IS_ERR(d))
+		return PTR_ERR(d);
+
+	return 0;
+}
+#else
+static inline int dma_buf_init_debugfs(void)
+{
+	return 0;
+}
+static inline void dma_buf_uninit_debugfs(void)
+{
+}
+#endif
+
+static int __init dma_buf_init(void)
+{
+	mutex_init(&db_list.lock);
+	INIT_LIST_HEAD(&db_list.head);
+	dma_buf_init_debugfs();
+	return 0;
+}
+subsys_initcall(dma_buf_init);
+
+static void __exit dma_buf_deinit(void)
+{
+	dma_buf_uninit_debugfs();
+}
+__exitcall(dma_buf_deinit);

drivers/base/dma-coherent.c

@@ -0,0 +1,220 @@
+/*
+ * Coherent per-device memory handling.
+ * Borrowed from i386
+ */
+#include <linux/slab.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/dma-mapping.h>
+
+struct dma_coherent_mem {
+	void		*virt_base;
+	dma_addr_t	device_base;
+	phys_addr_t	pfn_base;
+	int		size;
+	int		flags;
+	unsigned long	*bitmap;
+};
+
+int dma_declare_coherent_memory(struct device *dev, dma_addr_t bus_addr,
+				dma_addr_t device_addr, size_t size, int flags)
+{
+	void __iomem *mem_base = NULL;
+	int pages = size >> PAGE_SHIFT;
+	int bitmap_size = BITS_TO_LONGS(pages) * sizeof(long);
+
+	if ((flags & (DMA_MEMORY_MAP | DMA_MEMORY_IO)) == 0)
+		goto out;
+	if (!size)
+		goto out;
+	if (dev->dma_mem)
+		goto out;
+
+	/* FIXME: this routine just ignores DMA_MEMORY_INCLUDES_CHILDREN */
+
+	mem_base = ioremap(bus_addr, size);
+	if (!mem_base)
+		goto out;
+
+	dev->dma_mem = kzalloc(sizeof(struct dma_coherent_mem), GFP_KERNEL);
+	if (!dev->dma_mem)
+		goto out;
+	dev->dma_mem->bitmap = kzalloc(bitmap_size, GFP_KERNEL);
+	if (!dev->dma_mem->bitmap)
+		goto free1_out;
+
+	dev->dma_mem->virt_base = mem_base;
+	dev->dma_mem->device_base = device_addr;
+	dev->dma_mem->pfn_base = PFN_DOWN(bus_addr);
+	dev->dma_mem->size = pages;
+	dev->dma_mem->flags = flags;
+
+	if (flags & DMA_MEMORY_MAP)
+		return DMA_MEMORY_MAP;
+
+	return DMA_MEMORY_IO;
+
+ free1_out:
+	kfree(dev->dma_mem);
+ out:
+	if (mem_base)
+		iounmap(mem_base);
+	return 0;
+}
+EXPORT_SYMBOL(dma_declare_coherent_memory);
+
+void dma_release_declared_memory(struct device *dev)
+{
+	struct dma_coherent_mem *mem = dev->dma_mem;
+
+	if (!mem)
+		return;
+	dev->dma_mem = NULL;
+	iounmap(mem->virt_base);
+	kfree(mem->bitmap);
+	kfree(mem);
+}
+EXPORT_SYMBOL(dma_release_declared_memory);
+
+void *dma_mark_declared_memory_occupied(struct device *dev,
+					dma_addr_t device_addr, size_t size)
+{
+	struct dma_coherent_mem *mem = dev->dma_mem;
+	int pos, err;
+
+	size += device_addr & ~PAGE_MASK;
+
+	if (!mem)
+		return ERR_PTR(-EINVAL);
+
+	pos = (device_addr - mem->device_base) >> PAGE_SHIFT;
+	err = bitmap_allocate_region(mem->bitmap, pos, get_order(size));
+	if (err != 0)
+		return ERR_PTR(err);
+	return mem->virt_base + (pos << PAGE_SHIFT);
+}
+EXPORT_SYMBOL(dma_mark_declared_memory_occupied);
+
+/**
+ * dma_alloc_from_coherent() - try to allocate memory from the per-device coherent area
+ *
+ * @dev:	device from which we allocate memory
+ * @size:	size of requested memory area
+ * @dma_handle:	This will be filled with the correct dma handle
+ * @ret:	This pointer will be filled with the virtual address
+ *		to allocated area.
+ *
+ * This function should be only called from per-arch dma_alloc_coherent()
+ * to support allocation from per-device coherent memory pools.
+ *
+ * Returns 0 if dma_alloc_coherent should continue with allocating from
+ * generic memory areas, or !0 if dma_alloc_coherent should return @ret.
+ */
+int dma_alloc_from_coherent(struct device *dev, ssize_t size,
+				       dma_addr_t *dma_handle, void **ret)
+{
+	struct dma_coherent_mem *mem;
+	int order = get_order(size);
+	int pageno;
+
+	if (!dev)
+		return 0;
+	mem = dev->dma_mem;
+	if (!mem)
+		return 0;
+
+	*ret = NULL;
+
+	if (unlikely(size > (mem->size << PAGE_SHIFT)))
+		goto err;
+
+	pageno = bitmap_find_free_region(mem->bitmap, mem->size, order);
+	if (unlikely(pageno < 0))
+		goto err;
+
+	/*
+	 * Memory was found in the per-device area.
+	 */
+	*dma_handle = mem->device_base + (pageno << PAGE_SHIFT);
+	*ret = mem->virt_base + (pageno << PAGE_SHIFT);
+	memset(*ret, 0, size);
+
+	return 1;
+
+err:
+	/*
+	 * In the case where the allocation can not be satisfied from the
+	 * per-device area, try to fall back to generic memory if the
+	 * constraints allow it.
+	 */
+	return mem->flags & DMA_MEMORY_EXCLUSIVE;
+}
+EXPORT_SYMBOL(dma_alloc_from_coherent);
+
+/**
+ * dma_release_from_coherent() - try to free the memory allocated from per-device coherent memory pool
+ * @dev:	device from which the memory was allocated
+ * @order:	the order of pages allocated
+ * @vaddr:	virtual address of allocated pages
+ *
+ * This checks whether the memory was allocated from the per-device
+ * coherent memory pool and if so, releases that memory.
+ *
+ * Returns 1 if we correctly released the memory, or 0 if
+ * dma_release_coherent() should proceed with releasing memory from
+ * generic pools.
+ */
+int dma_release_from_coherent(struct device *dev, int order, void *vaddr)
+{
+	struct dma_coherent_mem *mem = dev ? dev->dma_mem : NULL;
+
+	if (mem && vaddr >= mem->virt_base && vaddr <
+		   (mem->virt_base + (mem->size << PAGE_SHIFT))) {
+		int page = (vaddr - mem->virt_base) >> PAGE_SHIFT;
+
+		bitmap_release_region(mem->bitmap, page, order);
+		return 1;
+	}
+	return 0;
+}
+EXPORT_SYMBOL(dma_release_from_coherent);
+
+/**
+ * dma_mmap_from_coherent() - try to mmap the memory allocated from
+ * per-device coherent memory pool to userspace
+ * @dev:	device from which the memory was allocated
+ * @vma:	vm_area for the userspace memory
+ * @vaddr:	cpu address returned by dma_alloc_from_coherent
+ * @size:	size of the memory buffer allocated by dma_alloc_from_coherent
+ * @ret:	result from remap_pfn_range()
+ *
+ * This checks whether the memory was allocated from the per-device
+ * coherent memory pool and if so, maps that memory to the provided vma.
+ *
+ * Returns 1 if we correctly mapped the memory, or 0 if the caller should
+ * proceed with mapping memory from generic pools.
+ */
+int dma_mmap_from_coherent(struct device *dev, struct vm_area_struct *vma,
+			   void *vaddr, size_t size, int *ret)
+{
+	struct dma_coherent_mem *mem = dev ? dev->dma_mem : NULL;
+
+	if (mem && vaddr >= mem->virt_base && vaddr + size <=
+		   (mem->virt_base + (mem->size << PAGE_SHIFT))) {
+		unsigned long off = vma->vm_pgoff;
+		int start = (vaddr - mem->virt_base) >> PAGE_SHIFT;
+		int user_count = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;
+		int count = size >> PAGE_SHIFT;
+
+		*ret = -ENXIO;
+		if (off < count && user_count <= count - off) {
+			unsigned pfn = mem->pfn_base + start + off;
+			*ret = remap_pfn_range(vma, vma->vm_start, pfn,
+					       user_count << PAGE_SHIFT,
+					       vma->vm_page_prot);
+		}
+		return 1;
+	}
+	return 0;
+}
+EXPORT_SYMBOL(dma_mmap_from_coherent);

drivers/base/dma-contiguous.c

@@ -0,0 +1,390 @@
+/*
+ * Contiguous Memory Allocator for DMA mapping framework
+ * Copyright (c) 2010-2011 by Samsung Electronics.
+ * Written by:
+ *	Marek Szyprowski <m.szyprowski@samsung.com>
+ *	Michal Nazarewicz <mina86@mina86.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation; either version 2 of the
+ * License or (at your optional) any later version of the license.
+ */
+
+#define pr_fmt(fmt) "cma: " fmt
+
+#ifdef CONFIG_CMA_DEBUG
+#ifndef DEBUG
+#  define DEBUG
+#endif
+#endif
+
+#include <asm/page.h>
+#include <asm/dma-contiguous.h>
+
+#include <linux/memblock.h>
+#include <linux/err.h>
+#include <linux/mm.h>
+#include <linux/mutex.h>
+#include <linux/page-isolation.h>
+#include <linux/sizes.h>
+#include <linux/slab.h>
+#include <linux/swap.h>
+#include <linux/mm_types.h>
+#include <linux/dma-contiguous.h>
+
+struct cma {
+	unsigned long	base_pfn;
+	unsigned long	count;
+	unsigned long	*bitmap;
+};
+
+struct cma *dma_contiguous_default_area;
+
+#ifdef CONFIG_CMA_SIZE_MBYTES
+#define CMA_SIZE_MBYTES CONFIG_CMA_SIZE_MBYTES
+#else
+#define CMA_SIZE_MBYTES 0
+#endif
+
+/*
+ * Default global CMA area size can be defined in kernel's .config.
+ * This is usefull mainly for distro maintainers to create a kernel
+ * that works correctly for most supported systems.
+ * The size can be set in bytes or as a percentage of the total memory
+ * in the system.
+ *
+ * Users, who want to set the size of global CMA area for their system
+ * should use cma= kernel parameter.
+ */
+static const phys_addr_t size_bytes = CMA_SIZE_MBYTES * SZ_1M;
+static phys_addr_t size_cmdline = -1;
+
+static int __init early_cma(char *p)
+{
+	pr_debug("%s(%s)\n", __func__, p);
+	size_cmdline = memparse(p, &p);
+	return 0;
+}
+early_param("cma", early_cma);
+
+#ifdef CONFIG_CMA_SIZE_PERCENTAGE
+
+static phys_addr_t __init __maybe_unused cma_early_percent_memory(void)
+{
+	struct memblock_region *reg;
+	unsigned long total_pages = 0;
+
+	/*
+	 * We cannot use memblock_phys_mem_size() here, because
+	 * memblock_analyze() has not been called yet.
+	 */
+	for_each_memblock(memory, reg)
+		total_pages += memblock_region_memory_end_pfn(reg) -
+			       memblock_region_memory_base_pfn(reg);
+
+	return (total_pages * CONFIG_CMA_SIZE_PERCENTAGE / 100) << PAGE_SHIFT;
+}
+
+#else
+
+static inline __maybe_unused phys_addr_t cma_early_percent_memory(void)
+{
+	return 0;
+}
+
+#endif
+
+/**
+ * dma_contiguous_reserve() - reserve area for contiguous memory handling
+ * @limit: End address of the reserved memory (optional, 0 for any).
+ *
+ * This function reserves memory from early allocator. It should be
+ * called by arch specific code once the early allocator (memblock or bootmem)
+ * has been activated and all other subsystems have already allocated/reserved
+ * memory.
+ */
+void __init dma_contiguous_reserve(phys_addr_t limit)
+{
+	phys_addr_t selected_size = 0;
+
+	pr_debug("%s(limit %08lx)\n", __func__, (unsigned long)limit);
+
+	if (size_cmdline != -1) {
+		selected_size = size_cmdline;
+	} else {
+#ifdef CONFIG_CMA_SIZE_SEL_MBYTES
+		selected_size = size_bytes;
+#elif defined(CONFIG_CMA_SIZE_SEL_PERCENTAGE)
+		selected_size = cma_early_percent_memory();
+#elif defined(CONFIG_CMA_SIZE_SEL_MIN)
+		selected_size = min(size_bytes, cma_early_percent_memory());
+#elif defined(CONFIG_CMA_SIZE_SEL_MAX)
+		selected_size = max(size_bytes, cma_early_percent_memory());
+#endif
+	}
+
+	if (selected_size) {
+		pr_debug("%s: reserving %ld MiB for global area\n", __func__,
+			 (unsigned long)selected_size / SZ_1M);
+
+		dma_declare_contiguous(NULL, selected_size, 0, limit);
+	}
+};
+
+static DEFINE_MUTEX(cma_mutex);
+
+static __init int cma_activate_area(unsigned long base_pfn, unsigned long count)
+{
+	unsigned long pfn = base_pfn;
+	unsigned i = count >> pageblock_order;
+	struct zone *zone;
+
+	WARN_ON_ONCE(!pfn_valid(pfn));
+	zone = page_zone(pfn_to_page(pfn));
+
+	do {
+		unsigned j;
+		base_pfn = pfn;
+		for (j = pageblock_nr_pages; j; --j, pfn++) {
+			WARN_ON_ONCE(!pfn_valid(pfn));
+			if (page_zone(pfn_to_page(pfn)) != zone)
+				return -EINVAL;
+		}
+		init_cma_reserved_pageblock(pfn_to_page(base_pfn));
+	} while (--i);
+	return 0;
+}
+
+static __init struct cma *cma_create_area(unsigned long base_pfn,
+				     unsigned long count)
+{
+	int bitmap_size = BITS_TO_LONGS(count) * sizeof(long);
+	struct cma *cma;
+	int ret = -ENOMEM;
+
+	pr_debug("%s(base %08lx, count %lx)\n", __func__, base_pfn, count);
+
+	cma = kmalloc(sizeof *cma, GFP_KERNEL);
+	if (!cma)
+		return ERR_PTR(-ENOMEM);
+
+	cma->base_pfn = base_pfn;
+	cma->count = count;
+	cma->bitmap = kzalloc(bitmap_size, GFP_KERNEL);
+
+	if (!cma->bitmap)
+		goto no_mem;
+
+	ret = cma_activate_area(base_pfn, count);
+	if (ret)
+		goto error;
+
+	pr_debug("%s: returned %p\n", __func__, (void *)cma);
+	return cma;
+
+error:
+	kfree(cma->bitmap);
+no_mem:
+	kfree(cma);
+	return ERR_PTR(ret);
+}
+
+static struct cma_reserved {
+	phys_addr_t start;
+	unsigned long size;
+	struct device *dev;
+} cma_reserved[MAX_CMA_AREAS] __initdata;
+static unsigned cma_reserved_count __initdata;
+
+static int __init cma_init_reserved_areas(void)
+{
+	struct cma_reserved *r = cma_reserved;
+	unsigned i = cma_reserved_count;
+
+	pr_debug("%s()\n", __func__);
+
+	for (; i; --i, ++r) {
+		struct cma *cma;
+		cma = cma_create_area(PFN_DOWN(r->start),
+				      r->size >> PAGE_SHIFT);
+		if (!IS_ERR(cma))
+			dev_set_cma_area(r->dev, cma);
+	}
+	return 0;
+}
+core_initcall(cma_init_reserved_areas);
+
+/**
+ * dma_declare_contiguous() - reserve area for contiguous memory handling
+ *			      for particular device
+ * @dev:   Pointer to device structure.
+ * @size:  Size of the reserved memory.
+ * @base:  Start address of the reserved memory (optional, 0 for any).
+ * @limit: End address of the reserved memory (optional, 0 for any).
+ *
+ * This function reserves memory for specified device. It should be
+ * called by board specific code when early allocator (memblock or bootmem)
+ * is still activate.
+ */
+int __init dma_declare_contiguous(struct device *dev, phys_addr_t size,
+				  phys_addr_t base, phys_addr_t limit)
+{
+	struct cma_reserved *r = &cma_reserved[cma_reserved_count];
+	phys_addr_t alignment;
+
+	pr_debug("%s(size %lx, base %08lx, limit %08lx)\n", __func__,
+		 (unsigned long)size, (unsigned long)base,
+		 (unsigned long)limit);
+
+	/* Sanity checks */
+	if (cma_reserved_count == ARRAY_SIZE(cma_reserved)) {
+		pr_err("Not enough slots for CMA reserved regions!\n");
+		return -ENOSPC;
+	}
+
+	if (!size)
+		return -EINVAL;
+
+	/* Sanitise input arguments */
+	alignment = PAGE_SIZE << max(MAX_ORDER - 1, pageblock_order);
+	base = ALIGN(base, alignment);
+	size = ALIGN(size, alignment);
+	limit &= ~(alignment - 1);
+
+	/* Reserve memory */
+	if (base) {
+		if (memblock_is_region_reserved(base, size) ||
+		    memblock_reserve(base, size) < 0) {
+			base = -EBUSY;
+			goto err;
+		}
+	} else {
+		/*
+		 * Use __memblock_alloc_base() since
+		 * memblock_alloc_base() panic()s.
+		 */
+		phys_addr_t addr = __memblock_alloc_base(size, alignment, limit);
+		if (!addr) {
+			base = -ENOMEM;
+			goto err;
+		} else {
+			base = addr;
+		}
+	}
+
+	/*
+	 * Each reserved area must be initialised later, when more kernel
+	 * subsystems (like slab allocator) are available.
+	 */
+	r->start = base;
+	r->size = size;
+	r->dev = dev;
+	cma_reserved_count++;
+	pr_info("CMA: reserved %ld MiB at %08lx\n", (unsigned long)size / SZ_1M,
+		(unsigned long)base);
+
+	/* Architecture specific contiguous memory fixup. */
+	dma_contiguous_early_fixup(base, size);
+	return 0;
+err:
+	pr_err("CMA: failed to reserve %ld MiB\n", (unsigned long)size / SZ_1M);
+	return base;
+}
+
+/**
+ * dma_alloc_from_contiguous() - allocate pages from contiguous area
+ * @dev:   Pointer to device for which the allocation is performed.
+ * @count: Requested number of pages.
+ * @align: Requested alignment of pages (in PAGE_SIZE order).
+ *
+ * This function allocates memory buffer for specified device. It uses
+ * device specific contiguous memory area if available or the default
+ * global one. Requires architecture specific get_dev_cma_area() helper
+ * function.
+ */
+struct page *dma_alloc_from_contiguous(struct device *dev, int count,
+				       unsigned int align)
+{
+	unsigned long mask, pfn, pageno, start = 0;
+	struct cma *cma = dev_get_cma_area(dev);
+	struct page *page = NULL;
+	int ret;
+
+	if (!cma || !cma->count)
+		return NULL;
+
+	if (align > CONFIG_CMA_ALIGNMENT)
+		align = CONFIG_CMA_ALIGNMENT;
+
+	pr_debug("%s(cma %p, count %d, align %d)\n", __func__, (void *)cma,
+		 count, align);
+
+	if (!count)
+		return NULL;
+
+	mask = (1 << align) - 1;
+
+	mutex_lock(&cma_mutex);
+
+	for (;;) {
+		pageno = bitmap_find_next_zero_area(cma->bitmap, cma->count,
+						    start, count, mask);
+		if (pageno >= cma->count)
+			break;
+
+		pfn = cma->base_pfn + pageno;
+		ret = alloc_contig_range(pfn, pfn + count, MIGRATE_CMA);
+		if (ret == 0) {
+			bitmap_set(cma->bitmap, pageno, count);
+			page = pfn_to_page(pfn);
+			break;
+		} else if (ret != -EBUSY) {
+			break;
+		}
+		pr_debug("%s(): memory range at %p is busy, retrying\n",
+			 __func__, pfn_to_page(pfn));
+		/* try again with a bit different memory target */
+		start = pageno + mask + 1;
+	}
+
+	mutex_unlock(&cma_mutex);
+	pr_debug("%s(): returned %p\n", __func__, page);
+	return page;
+}
+
+/**
+ * dma_release_from_contiguous() - release allocated pages
+ * @dev:   Pointer to device for which the pages were allocated.
+ * @pages: Allocated pages.
+ * @count: Number of allocated pages.
+ *
+ * This function releases memory allocated by dma_alloc_from_contiguous().
+ * It returns false when provided pages do not belong to contiguous area and
+ * true otherwise.
+ */
+bool dma_release_from_contiguous(struct device *dev, struct page *pages,
+				 int count)
+{
+	struct cma *cma = dev_get_cma_area(dev);
+	unsigned long pfn;
+
+	if (!cma || !pages)
+		return false;
+
+	pr_debug("%s(page %p)\n", __func__, (void *)pages);
+
+	pfn = page_to_pfn(pages);
+
+	if (pfn < cma->base_pfn || pfn >= cma->base_pfn + cma->count)
+		return false;
+
+	VM_BUG_ON(pfn + count > cma->base_pfn + cma->count);
+
+	mutex_lock(&cma_mutex);
+	bitmap_clear(cma->bitmap, pfn - cma->base_pfn, count);
+	free_contig_range(pfn, count);
+	mutex_unlock(&cma_mutex);
+
+	return true;
+}

drivers/base/dma-mapping.c

@@ -0,0 +1,269 @@
+/*
+ * drivers/base/dma-mapping.c - arch-independent dma-mapping routines
+ *
+ * Copyright (c) 2006  SUSE Linux Products GmbH
+ * Copyright (c) 2006  Tejun Heo <teheo@suse.de>
+ *
+ * This file is released under the GPLv2.
+ */
+
+#include <linux/dma-mapping.h>
+#include <linux/export.h>
+#include <linux/gfp.h>
+#include <asm-generic/dma-coherent.h>
+
+/*
+ * Managed DMA API
+ */
+struct dma_devres {
+	size_t		size;
+	void		*vaddr;
+	dma_addr_t	dma_handle;
+};
+
+static void dmam_coherent_release(struct device *dev, void *res)
+{
+	struct dma_devres *this = res;
+
+	dma_free_coherent(dev, this->size, this->vaddr, this->dma_handle);
+}
+
+static void dmam_noncoherent_release(struct device *dev, void *res)
+{
+	struct dma_devres *this = res;
+
+	dma_free_noncoherent(dev, this->size, this->vaddr, this->dma_handle);
+}
+
+static int dmam_match(struct device *dev, void *res, void *match_data)
+{
+	struct dma_devres *this = res, *match = match_data;
+
+	if (this->vaddr == match->vaddr) {
+		WARN_ON(this->size != match->size ||
+			this->dma_handle != match->dma_handle);
+		return 1;
+	}
+	return 0;
+}
+
+/**
+ * dmam_alloc_coherent - Managed dma_alloc_coherent()
+ * @dev: Device to allocate coherent memory for
+ * @size: Size of allocation
+ * @dma_handle: Out argument for allocated DMA handle
+ * @gfp: Allocation flags
+ *
+ * Managed dma_alloc_coherent().  Memory allocated using this function
+ * will be automatically released on driver detach.
+ *
+ * RETURNS:
+ * Pointer to allocated memory on success, NULL on failure.
+ */
+void * dmam_alloc_coherent(struct device *dev, size_t size,
+			   dma_addr_t *dma_handle, gfp_t gfp)
+{
+	struct dma_devres *dr;
+	void *vaddr;
+
+	dr = devres_alloc(dmam_coherent_release, sizeof(*dr), gfp);
+	if (!dr)
+		return NULL;
+
+	vaddr = dma_alloc_coherent(dev, size, dma_handle, gfp);
+	if (!vaddr) {
+		devres_free(dr);
+		return NULL;
+	}
+
+	dr->vaddr = vaddr;
+	dr->dma_handle = *dma_handle;
+	dr->size = size;
+
+	devres_add(dev, dr);
+
+	return vaddr;
+}
+EXPORT_SYMBOL(dmam_alloc_coherent);
+
+/**
+ * dmam_free_coherent - Managed dma_free_coherent()
+ * @dev: Device to free coherent memory for
+ * @size: Size of allocation
+ * @vaddr: Virtual address of the memory to free
+ * @dma_handle: DMA handle of the memory to free
+ *
+ * Managed dma_free_coherent().
+ */
+void dmam_free_coherent(struct device *dev, size_t size, void *vaddr,
+			dma_addr_t dma_handle)
+{
+	struct dma_devres match_data = { size, vaddr, dma_handle };
+
+	dma_free_coherent(dev, size, vaddr, dma_handle);
+	WARN_ON(devres_destroy(dev, dmam_coherent_release, dmam_match,
+			       &match_data));
+}
+EXPORT_SYMBOL(dmam_free_coherent);
+
+/**
+ * dmam_alloc_non_coherent - Managed dma_alloc_non_coherent()
+ * @dev: Device to allocate non_coherent memory for
+ * @size: Size of allocation
+ * @dma_handle: Out argument for allocated DMA handle
+ * @gfp: Allocation flags
+ *
+ * Managed dma_alloc_non_coherent().  Memory allocated using this
+ * function will be automatically released on driver detach.
+ *
+ * RETURNS:
+ * Pointer to allocated memory on success, NULL on failure.
+ */
+void *dmam_alloc_noncoherent(struct device *dev, size_t size,
+			     dma_addr_t *dma_handle, gfp_t gfp)
+{
+	struct dma_devres *dr;
+	void *vaddr;
+
+	dr = devres_alloc(dmam_noncoherent_release, sizeof(*dr), gfp);
+	if (!dr)
+		return NULL;
+
+	vaddr = dma_alloc_noncoherent(dev, size, dma_handle, gfp);
+	if (!vaddr) {
+		devres_free(dr);
+		return NULL;
+	}
+
+	dr->vaddr = vaddr;
+	dr->dma_handle = *dma_handle;
+	dr->size = size;
+
+	devres_add(dev, dr);
+
+	return vaddr;
+}
+EXPORT_SYMBOL(dmam_alloc_noncoherent);
+
+/**
+ * dmam_free_coherent - Managed dma_free_noncoherent()
+ * @dev: Device to free noncoherent memory for
+ * @size: Size of allocation
+ * @vaddr: Virtual address of the memory to free
+ * @dma_handle: DMA handle of the memory to free
+ *
+ * Managed dma_free_noncoherent().
+ */
+void dmam_free_noncoherent(struct device *dev, size_t size, void *vaddr,
+			   dma_addr_t dma_handle)
+{
+	struct dma_devres match_data = { size, vaddr, dma_handle };
+
+	dma_free_noncoherent(dev, size, vaddr, dma_handle);
+	WARN_ON(!devres_destroy(dev, dmam_noncoherent_release, dmam_match,
+				&match_data));
+}
+EXPORT_SYMBOL(dmam_free_noncoherent);
+
+#ifdef ARCH_HAS_DMA_DECLARE_COHERENT_MEMORY
+
+static void dmam_coherent_decl_release(struct device *dev, void *res)
+{
+	dma_release_declared_memory(dev);
+}
+
+/**
+ * dmam_declare_coherent_memory - Managed dma_declare_coherent_memory()
+ * @dev: Device to declare coherent memory for
+ * @bus_addr: Bus address of coherent memory to be declared
+ * @device_addr: Device address of coherent memory to be declared
+ * @size: Size of coherent memory to be declared
+ * @flags: Flags
+ *
+ * Managed dma_declare_coherent_memory().
+ *
+ * RETURNS:
+ * 0 on success, -errno on failure.
+ */
+int dmam_declare_coherent_memory(struct device *dev, dma_addr_t bus_addr,
+				 dma_addr_t device_addr, size_t size, int flags)
+{
+	void *res;
+	int rc;
+
+	res = devres_alloc(dmam_coherent_decl_release, 0, GFP_KERNEL);
+	if (!res)
+		return -ENOMEM;
+
+	rc = dma_declare_coherent_memory(dev, bus_addr, device_addr, size,
+					 flags);
+	if (rc == 0)
+		devres_add(dev, res);
+	else
+		devres_free(res);
+
+	return rc;
+}
+EXPORT_SYMBOL(dmam_declare_coherent_memory);
+
+/**
+ * dmam_release_declared_memory - Managed dma_release_declared_memory().
+ * @dev: Device to release declared coherent memory for
+ *
+ * Managed dmam_release_declared_memory().
+ */
+void dmam_release_declared_memory(struct device *dev)
+{
+	WARN_ON(devres_destroy(dev, dmam_coherent_decl_release, NULL, NULL));
+}
+EXPORT_SYMBOL(dmam_release_declared_memory);
+
+#endif
+
+/*
+ * Create scatter-list for the already allocated DMA buffer.
+ */
+int dma_common_get_sgtable(struct device *dev, struct sg_table *sgt,
+		 void *cpu_addr, dma_addr_t handle, size_t size)
+{
+	struct page *page = virt_to_page(cpu_addr);
+	int ret;
+
+	ret = sg_alloc_table(sgt, 1, GFP_KERNEL);
+	if (unlikely(ret))
+		return ret;
+
+	sg_set_page(sgt->sgl, page, PAGE_ALIGN(size), 0);
+	return 0;
+}
+EXPORT_SYMBOL(dma_common_get_sgtable);
+
+/*
+ * Create userspace mapping for the DMA-coherent memory.
+ */
+int dma_common_mmap(struct device *dev, struct vm_area_struct *vma,
+		    void *cpu_addr, dma_addr_t dma_addr, size_t size)
+{
+	int ret = -ENXIO;
+#ifdef CONFIG_MMU
+	unsigned long user_count = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;
+	unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT;
+	unsigned long pfn = page_to_pfn(virt_to_page(cpu_addr));
+	unsigned long off = vma->vm_pgoff;
+
+	vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
+
+	if (dma_mmap_from_coherent(dev, vma, cpu_addr, size, &ret))
+		return ret;
+
+	if (off < count && user_count <= (count - off)) {
+		ret = remap_pfn_range(vma, vma->vm_start,
+				      pfn + off,
+				      user_count << PAGE_SHIFT,
+				      vma->vm_page_prot);
+	}
+#endif	/* CONFIG_MMU */
+
+	return ret;
+}
+EXPORT_SYMBOL(dma_common_mmap);

drivers/base/driver.c

@@ -0,0 +1,222 @@
+/*
+ * driver.c - centralized device driver management
+ *
+ * Copyright (c) 2002-3 Patrick Mochel
+ * Copyright (c) 2002-3 Open Source Development Labs
+ * Copyright (c) 2007 Greg Kroah-Hartman <gregkh@suse.de>
+ * Copyright (c) 2007 Novell Inc.
+ *
+ * This file is released under the GPLv2
+ *
+ */
+
+#include <linux/device.h>
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include "base.h"
+
+static struct device *next_device(struct klist_iter *i)
+{
+	struct klist_node *n = klist_next(i);
+	struct device *dev = NULL;
+	struct device_private *dev_prv;
+
+	if (n) {
+		dev_prv = to_device_private_driver(n);
+		dev = dev_prv->device;
+	}
+	return dev;
+}
+
+/**
+ * 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.
+ *
+ * Iterate over the @drv's list of devices calling @fn for each one.
+ */
+int driver_for_each_device(struct device_driver *drv, struct device *start,
+			   void *data, int (*fn)(struct device *, void *))
+{
+	struct klist_iter i;
+	struct device *dev;
+	int error = 0;
+
+	if (!drv)
+		return -EINVAL;
+
+	klist_iter_init_node(&drv->p->klist_devices, &i,
+			     start ? &start->p->knode_driver : NULL);
+	while ((dev = next_device(&i)) && !error)
+		error = fn(dev, data);
+	klist_iter_exit(&i);
+	return error;
+}
+EXPORT_SYMBOL_GPL(driver_for_each_device);
+
+/**
+ * driver_find_device - device iterator for locating a particular device.
+ * @drv: The device's driver
+ * @start: Device to begin with
+ * @data: Data to pass to match function
+ * @match: Callback function to check device
+ *
+ * This is similar to the driver_for_each_device() function above, but
+ * it returns a reference to a device that is 'found' for later use, as
+ * determined by the @match callback.
+ *
+ * The callback should return 0 if the device doesn't match and non-zero
+ * if it does.  If the callback returns non-zero, this function will
+ * return to the caller and not iterate over any more devices.
+ */
+struct device *driver_find_device(struct device_driver *drv,
+				  struct device *start, void *data,
+				  int (*match)(struct device *dev, void *data))
+{
+	struct klist_iter i;
+	struct device *dev;
+
+	if (!drv || !drv->p)
+		return NULL;
+
+	klist_iter_init_node(&drv->p->klist_devices, &i,
+			     (start ? &start->p->knode_driver : NULL));
+	while ((dev = next_device(&i)))
+		if (match(dev, data) && get_device(dev))
+			break;
+	klist_iter_exit(&i);
+	return dev;
+}
+EXPORT_SYMBOL_GPL(driver_find_device);
+
+/**
+ * driver_create_file - create sysfs file for driver.
+ * @drv: driver.
+ * @attr: driver attribute descriptor.
+ */
+int driver_create_file(struct device_driver *drv,
+		       const struct driver_attribute *attr)
+{
+	int error;
+	if (drv)
+		error = sysfs_create_file(&drv->p->kobj, &attr->attr);
+	else
+		error = -EINVAL;
+	return error;
+}
+EXPORT_SYMBOL_GPL(driver_create_file);
+
+/**
+ * driver_remove_file - remove sysfs file for driver.
+ * @drv: driver.
+ * @attr: driver attribute descriptor.
+ */
+void driver_remove_file(struct device_driver *drv,
+			const struct driver_attribute *attr)
+{
+	if (drv)
+		sysfs_remove_file(&drv->p->kobj, &attr->attr);
+}
+EXPORT_SYMBOL_GPL(driver_remove_file);
+
+static int driver_add_groups(struct device_driver *drv,
+			     const struct attribute_group **groups)
+{
+	return sysfs_create_groups(&drv->p->kobj, groups);
+}
+
+static void driver_remove_groups(struct device_driver *drv,
+				 const struct attribute_group **groups)
+{
+	sysfs_remove_groups(&drv->p->kobj, groups);
+}
+
+/**
+ * driver_register - register driver with bus
+ * @drv: driver to register
+ *
+ * We pass off most of the work to the bus_add_driver() call,
+ * since most of the things we have to do deal with the bus
+ * structures.
+ */
+int driver_register(struct device_driver *drv)
+{
+	int ret;
+	struct device_driver *other;
+
+	BUG_ON(!drv->bus->p);
+
+	if ((drv->bus->probe && drv->probe) ||
+	    (drv->bus->remove && drv->remove) ||
+	    (drv->bus->shutdown && drv->shutdown))
+		printk(KERN_WARNING "Driver '%s' needs updating - please use "
+			"bus_type methods\n", drv->name);
+
+	other = driver_find(drv->name, drv->bus);
+	if (other) {
+		printk(KERN_ERR "Error: Driver '%s' is already registered, "
+			"aborting...\n", drv->name);
+		return -EBUSY;
+	}
+
+	ret = bus_add_driver(drv);
+	if (ret)
+		return ret;
+	ret = driver_add_groups(drv, drv->groups);
+	if (ret) {
+		bus_remove_driver(drv);
+		return ret;
+	}
+	kobject_uevent(&drv->p->kobj, KOBJ_ADD);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(driver_register);
+
+/**
+ * driver_unregister - remove driver from system.
+ * @drv: driver.
+ *
+ * Again, we pass off most of the work to the bus-level call.
+ */
+void driver_unregister(struct device_driver *drv)
+{
+	if (!drv || !drv->p) {
+		WARN(1, "Unexpected driver unregister!\n");
+		return;
+	}
+	driver_remove_groups(drv, drv->groups);
+	bus_remove_driver(drv);
+}
+EXPORT_SYMBOL_GPL(driver_unregister);
+
+/**
+ * driver_find - locate driver on a bus by its name.
+ * @name: name of the driver.
+ * @bus: bus to scan for the driver.
+ *
+ * Call kset_find_obj() to iterate over list of drivers on
+ * a bus to find driver by name. Return driver if found.
+ *
+ * This routine provides no locking to prevent the driver it returns
+ * from being unregistered or unloaded while the caller is using it.
+ * The caller is responsible for preventing this.
+ */
+struct device_driver *driver_find(const char *name, struct bus_type *bus)
+{
+	struct kobject *k = kset_find_obj(bus->p->drivers_kset, name);
+	struct driver_private *priv;
+
+	if (k) {
+		/* Drop reference added by kset_find_obj() */
+		kobject_put(k);
+		priv = to_driver(k);
+		return priv->driver;
+	}
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(driver_find);

drivers/base/firmware.c

@@ -0,0 +1,27 @@
+/*
+ * firmware.c - firmware subsystem hoohaw.
+ *
+ * Copyright (c) 2002-3 Patrick Mochel
+ * Copyright (c) 2002-3 Open Source Development Labs
+ * Copyright (c) 2007 Greg Kroah-Hartman <gregkh@suse.de>
+ * Copyright (c) 2007 Novell Inc.
+ *
+ * This file is released under the GPLv2
+ */
+#include <linux/kobject.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/device.h>
+
+#include "base.h"
+
+struct kobject *firmware_kobj;
+EXPORT_SYMBOL_GPL(firmware_kobj);
+
+int __init firmware_init(void)
+{
+	firmware_kobj = kobject_create_and_add("firmware", NULL);
+	if (!firmware_kobj)
+		return -ENOMEM;
+	return 0;
+}

drivers/base/hypervisor.c

@@ -0,0 +1,25 @@
+/*
+ * hypervisor.c - /sys/hypervisor subsystem.
+ *
+ * Copyright (C) IBM Corp. 2006
+ * Copyright (C) 2007 Greg Kroah-Hartman <gregkh@suse.de>
+ * Copyright (C) 2007 Novell Inc.
+ *
+ * This file is released under the GPLv2
+ */
+
+#include <linux/kobject.h>
+#include <linux/device.h>
+#include <linux/export.h>
+#include "base.h"
+
+struct kobject *hypervisor_kobj;
+EXPORT_SYMBOL_GPL(hypervisor_kobj);
+
+int __init hypervisor_init(void)
+{
+	hypervisor_kobj = kobject_create_and_add("hypervisor", NULL);
+	if (!hypervisor_kobj)
+		return -ENOMEM;
+	return 0;
+}

drivers/base/init.c

@@ -0,0 +1,36 @@
+/*
+ * Copyright (c) 2002-3 Patrick Mochel
+ * Copyright (c) 2002-3 Open Source Development Labs
+ *
+ * This file is released under the GPLv2
+ */
+
+#include <linux/device.h>
+#include <linux/init.h>
+#include <linux/memory.h>
+
+#include "base.h"
+
+/**
+ * driver_init - initialize driver model.
+ *
+ * Call the driver model init functions to initialize their
+ * subsystems. Called early from init/main.c.
+ */
+void __init driver_init(void)
+{
+	/* These are the core pieces */
+	devtmpfs_init();
+	devices_init();
+	buses_init();
+	classes_init();
+	firmware_init();
+	hypervisor_init();
+
+	/* These are also core pieces, but must come after the
+	 * core core pieces.
+	 */
+	platform_bus_init();
+	cpu_dev_init();
+	memory_dev_init();
+}

drivers/base/isa.c

@@ -0,0 +1,183 @@
+/*
+ * ISA bus.
+ */
+
+#include <linux/device.h>
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/dma-mapping.h>
+#include <linux/isa.h>
+
+static struct device isa_bus = {
+	.init_name	= "isa"
+};
+
+struct isa_dev {
+	struct device dev;
+	struct device *next;
+	unsigned int id;
+};
+
+#define to_isa_dev(x) container_of((x), struct isa_dev, dev)
+
+static int isa_bus_match(struct device *dev, struct device_driver *driver)
+{
+	struct isa_driver *isa_driver = to_isa_driver(driver);
+
+	if (dev->platform_data == isa_driver) {
+		if (!isa_driver->match ||
+			isa_driver->match(dev, to_isa_dev(dev)->id))
+			return 1;
+		dev->platform_data = NULL;
+	}
+	return 0;
+}
+
+static int isa_bus_probe(struct device *dev)
+{
+	struct isa_driver *isa_driver = dev->platform_data;
+
+	if (isa_driver->probe)
+		return isa_driver->probe(dev, to_isa_dev(dev)->id);
+
+	return 0;
+}
+
+static int isa_bus_remove(struct device *dev)
+{
+	struct isa_driver *isa_driver = dev->platform_data;
+
+	if (isa_driver->remove)
+		return isa_driver->remove(dev, to_isa_dev(dev)->id);
+
+	return 0;
+}
+
+static void isa_bus_shutdown(struct device *dev)
+{
+	struct isa_driver *isa_driver = dev->platform_data;
+
+	if (isa_driver->shutdown)
+		isa_driver->shutdown(dev, to_isa_dev(dev)->id);
+}
+
+static int isa_bus_suspend(struct device *dev, pm_message_t state)
+{
+	struct isa_driver *isa_driver = dev->platform_data;
+
+	if (isa_driver->suspend)
+		return isa_driver->suspend(dev, to_isa_dev(dev)->id, state);
+
+	return 0;
+}
+
+static int isa_bus_resume(struct device *dev)
+{
+	struct isa_driver *isa_driver = dev->platform_data;
+
+	if (isa_driver->resume)
+		return isa_driver->resume(dev, to_isa_dev(dev)->id);
+
+	return 0;
+}
+
+static struct bus_type isa_bus_type = {
+	.name		= "isa",
+	.match		= isa_bus_match,
+	.probe		= isa_bus_probe,
+	.remove		= isa_bus_remove,
+	.shutdown	= isa_bus_shutdown,
+	.suspend	= isa_bus_suspend,
+	.resume		= isa_bus_resume
+};
+
+static void isa_dev_release(struct device *dev)
+{
+	kfree(to_isa_dev(dev));
+}
+
+void isa_unregister_driver(struct isa_driver *isa_driver)
+{
+	struct device *dev = isa_driver->devices;
+
+	while (dev) {
+		struct device *tmp = to_isa_dev(dev)->next;
+		device_unregister(dev);
+		dev = tmp;
+	}
+	driver_unregister(&isa_driver->driver);
+}
+EXPORT_SYMBOL_GPL(isa_unregister_driver);
+
+int isa_register_driver(struct isa_driver *isa_driver, unsigned int ndev)
+{
+	int error;
+	unsigned int id;
+
+	isa_driver->driver.bus	= &isa_bus_type;
+	isa_driver->devices	= NULL;
+
+	error = driver_register(&isa_driver->driver);
+	if (error)
+		return error;
+
+	for (id = 0; id < ndev; id++) {
+		struct isa_dev *isa_dev;
+
+		isa_dev = kzalloc(sizeof *isa_dev, GFP_KERNEL);
+		if (!isa_dev) {
+			error = -ENOMEM;
+			break;
+		}
+
+		isa_dev->dev.parent	= &isa_bus;
+		isa_dev->dev.bus	= &isa_bus_type;
+
+		dev_set_name(&isa_dev->dev, "%s.%u",
+			     isa_driver->driver.name, id);
+		isa_dev->dev.platform_data	= isa_driver;
+		isa_dev->dev.release		= isa_dev_release;
+		isa_dev->id			= id;
+
+		isa_dev->dev.coherent_dma_mask = DMA_BIT_MASK(24);
+		isa_dev->dev.dma_mask = &isa_dev->dev.coherent_dma_mask;
+
+		error = device_register(&isa_dev->dev);
+		if (error) {
+			put_device(&isa_dev->dev);
+			break;
+		}
+
+		if (isa_dev->dev.platform_data) {
+			isa_dev->next = isa_driver->devices;
+			isa_driver->devices = &isa_dev->dev;
+		} else
+			device_unregister(&isa_dev->dev);
+	}
+
+	if (!error && !isa_driver->devices)
+		error = -ENODEV;
+
+	if (error)
+		isa_unregister_driver(isa_driver);
+
+	return error;
+}
+EXPORT_SYMBOL_GPL(isa_register_driver);
+
+static int __init isa_bus_init(void)
+{
+	int error;
+
+	error = bus_register(&isa_bus_type);
+	if (!error) {
+		error = device_register(&isa_bus);
+		if (error)
+			bus_unregister(&isa_bus_type);
+	}
+	return error;
+}
+
+device_initcall(isa_bus_init);

drivers/base/map.c

@@ -0,0 +1,155 @@
+/*
+ *  linux/drivers/base/map.c
+ *
+ * (C) Copyright Al Viro 2002,2003
+ *	Released under GPL v2.
+ *
+ * NOTE: data structure needs to be changed.  It works, but for large dev_t
+ * it will be too slow.  It is isolated, though, so these changes will be
+ * local to that file.
+ */
+
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/mutex.h>
+#include <linux/kdev_t.h>
+#include <linux/kobject.h>
+#include <linux/kobj_map.h>
+
+struct kobj_map {
+	struct probe {
+		struct probe *next;
+		dev_t dev;
+		unsigned long range;
+		struct module *owner;
+		kobj_probe_t *get;
+		int (*lock)(dev_t, void *);
+		void *data;
+	} *probes[255];
+	struct mutex *lock;
+};
+
+int kobj_map(struct kobj_map *domain, dev_t dev, unsigned long range,
+	     struct module *module, kobj_probe_t *probe,
+	     int (*lock)(dev_t, void *), void *data)
+{
+	unsigned n = MAJOR(dev + range - 1) - MAJOR(dev) + 1;
+	unsigned index = MAJOR(dev);
+	unsigned i;
+	struct probe *p;
+
+	if (n > 255)
+		n = 255;
+
+	p = kmalloc(sizeof(struct probe) * n, GFP_KERNEL);
+
+	if (p == NULL)
+		return -ENOMEM;
+
+	for (i = 0; i < n; i++, p++) {
+		p->owner = module;
+		p->get = probe;
+		p->lock = lock;
+		p->dev = dev;
+		p->range = range;
+		p->data = data;
+	}
+	mutex_lock(domain->lock);
+	for (i = 0, p -= n; i < n; i++, p++, index++) {
+		struct probe **s = &domain->probes[index % 255];
+		while (*s && (*s)->range < range)
+			s = &(*s)->next;
+		p->next = *s;
+		*s = p;
+	}
+	mutex_unlock(domain->lock);
+	return 0;
+}
+
+void kobj_unmap(struct kobj_map *domain, dev_t dev, unsigned long range)
+{
+	unsigned n = MAJOR(dev + range - 1) - MAJOR(dev) + 1;
+	unsigned index = MAJOR(dev);
+	unsigned i;
+	struct probe *found = NULL;
+
+	if (n > 255)
+		n = 255;
+
+	mutex_lock(domain->lock);
+	for (i = 0; i < n; i++, index++) {
+		struct probe **s;
+		for (s = &domain->probes[index % 255]; *s; s = &(*s)->next) {
+			struct probe *p = *s;
+			if (p->dev == dev && p->range == range) {
+				*s = p->next;
+				if (!found)
+					found = p;
+				break;
+			}
+		}
+	}
+	mutex_unlock(domain->lock);
+	kfree(found);
+}
+
+struct kobject *kobj_lookup(struct kobj_map *domain, dev_t dev, int *index)
+{
+	struct kobject *kobj;
+	struct probe *p;
+	unsigned long best = ~0UL;
+
+retry:
+	mutex_lock(domain->lock);
+	for (p = domain->probes[MAJOR(dev) % 255]; p; p = p->next) {
+		struct kobject *(*probe)(dev_t, int *, void *);
+		struct module *owner;
+		void *data;
+
+		if (p->dev > dev || p->dev + p->range - 1 < dev)
+			continue;
+		if (p->range - 1 >= best)
+			break;
+		if (!try_module_get(p->owner))
+			continue;
+		owner = p->owner;
+		data = p->data;
+		probe = p->get;
+		best = p->range - 1;
+		*index = dev - p->dev;
+		if (p->lock && p->lock(dev, data) < 0) {
+			module_put(owner);
+			continue;
+		}
+		mutex_unlock(domain->lock);
+		kobj = probe(dev, index, data);
+		/* Currently ->owner protects _only_ ->probe() itself. */
+		module_put(owner);
+		if (kobj)
+			return kobj;
+		goto retry;
+	}
+	mutex_unlock(domain->lock);
+	return NULL;
+}
+
+struct kobj_map *kobj_map_init(kobj_probe_t *base_probe, struct mutex *lock)
+{
+	struct kobj_map *p = kmalloc(sizeof(struct kobj_map), GFP_KERNEL);
+	struct probe *base = kzalloc(sizeof(*base), GFP_KERNEL);
+	int i;
+
+	if ((p == NULL) || (base == NULL)) {
+		kfree(p);
+		kfree(base);
+		return NULL;
+	}
+
+	base->dev = 1;
+	base->range = ~0;
+	base->get = base_probe;
+	for (i = 0; i < 255; i++)
+		p->probes[i] = base;
+	p->lock = lock;
+	return p;
+}

drivers/base/memory.c

@@ -0,0 +1,752 @@
+/*
+ * Memory subsystem 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/module.h>
+#include <linux/init.h>
+#include <linux/topology.h>
+#include <linux/capability.h>
+#include <linux/device.h>
+#include <linux/memory.h>
+#include <linux/kobject.h>
+#include <linux/memory_hotplug.h>
+#include <linux/mm.h>
+#include <linux/mutex.h>
+#include <linux/stat.h>
+#include <linux/slab.h>
+
+#include <linux/atomic.h>
+#include <asm/uaccess.h>
+
+static DEFINE_MUTEX(mem_sysfs_mutex);
+
+#define MEMORY_CLASS_NAME	"memory"
+
+static int sections_per_block;
+
+static inline int base_memory_block_id(int section_nr)
+{
+	return section_nr / sections_per_block;
+}
+
+static struct bus_type memory_subsys = {
+	.name = MEMORY_CLASS_NAME,
+	.dev_name = MEMORY_CLASS_NAME,
+};
+
+static BLOCKING_NOTIFIER_HEAD(memory_chain);
+
+int register_memory_notifier(struct notifier_block *nb)
+{
+        return blocking_notifier_chain_register(&memory_chain, nb);
+}
+EXPORT_SYMBOL(register_memory_notifier);
+
+void unregister_memory_notifier(struct notifier_block *nb)
+{
+        blocking_notifier_chain_unregister(&memory_chain, nb);
+}
+EXPORT_SYMBOL(unregister_memory_notifier);
+
+static ATOMIC_NOTIFIER_HEAD(memory_isolate_chain);
+
+int register_memory_isolate_notifier(struct notifier_block *nb)
+{
+	return atomic_notifier_chain_register(&memory_isolate_chain, nb);
+}
+EXPORT_SYMBOL(register_memory_isolate_notifier);
+
+void unregister_memory_isolate_notifier(struct notifier_block *nb)
+{
+	atomic_notifier_chain_unregister(&memory_isolate_chain, nb);
+}
+EXPORT_SYMBOL(unregister_memory_isolate_notifier);
+
+static void memory_block_release(struct device *dev)
+{
+	struct memory_block *mem = container_of(dev, struct memory_block, dev);
+
+	kfree(mem);
+}
+
+/*
+ * register_memory - Setup a sysfs device for a memory block
+ */
+static
+int register_memory(struct memory_block *memory)
+{
+	int error;
+
+	memory->dev.bus = &memory_subsys;
+	memory->dev.id = memory->start_section_nr / sections_per_block;
+	memory->dev.release = memory_block_release;
+
+	error = device_register(&memory->dev);
+	return error;
+}
+
+unsigned long __weak memory_block_size_bytes(void)
+{
+	return MIN_MEMORY_BLOCK_SIZE;
+}
+
+static unsigned long get_memory_block_size(void)
+{
+	unsigned long block_sz;
+
+	block_sz = memory_block_size_bytes();
+
+	/* Validate blk_sz is a power of 2 and not less than section size */
+	if ((block_sz & (block_sz - 1)) || (block_sz < MIN_MEMORY_BLOCK_SIZE)) {
+		WARN_ON(1);
+		block_sz = MIN_MEMORY_BLOCK_SIZE;
+	}
+
+	return block_sz;
+}
+
+/*
+ * use this as the physical section index that this memsection
+ * uses.
+ */
+
+static ssize_t show_mem_start_phys_index(struct device *dev,
+			struct device_attribute *attr, char *buf)
+{
+	struct memory_block *mem =
+		container_of(dev, struct memory_block, dev);
+	unsigned long phys_index;
+
+	phys_index = mem->start_section_nr / sections_per_block;
+	return sprintf(buf, "%08lx\n", phys_index);
+}
+
+static ssize_t show_mem_end_phys_index(struct device *dev,
+			struct device_attribute *attr, char *buf)
+{
+	struct memory_block *mem =
+		container_of(dev, struct memory_block, dev);
+	unsigned long phys_index;
+
+	phys_index = mem->end_section_nr / sections_per_block;
+	return sprintf(buf, "%08lx\n", phys_index);
+}
+
+/*
+ * Show whether the section of memory is likely to be hot-removable
+ */
+static ssize_t show_mem_removable(struct device *dev,
+			struct device_attribute *attr, char *buf)
+{
+	unsigned long i, pfn;
+	int ret = 1;
+	struct memory_block *mem =
+		container_of(dev, struct memory_block, dev);
+
+	for (i = 0; i < sections_per_block; i++) {
+		if (!present_section_nr(mem->start_section_nr + i))
+			continue;
+		pfn = section_nr_to_pfn(mem->start_section_nr + i);
+		ret &= is_mem_section_removable(pfn, PAGES_PER_SECTION);
+	}
+
+	return sprintf(buf, "%d\n", ret);
+}
+
+/*
+ * online, offline, going offline, etc.
+ */
+static ssize_t show_mem_state(struct device *dev,
+			struct device_attribute *attr, char *buf)
+{
+	struct memory_block *mem =
+		container_of(dev, struct memory_block, dev);
+	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;
+}
+
+int memory_notify(unsigned long val, void *v)
+{
+	return blocking_notifier_call_chain(&memory_chain, val, v);
+}
+
+int memory_isolate_notify(unsigned long val, void *v)
+{
+	return atomic_notifier_call_chain(&memory_isolate_chain, val, v);
+}
+
+/*
+ * The probe routines leave the pages reserved, just as the bootmem code does.
+ * Make sure they're still that way.
+ */
+static bool pages_correctly_reserved(unsigned long start_pfn)
+{
+	int i, j;
+	struct page *page;
+	unsigned long pfn = start_pfn;
+
+	/*
+	 * memmap between sections is not contiguous except with
+	 * SPARSEMEM_VMEMMAP. We lookup the page once per section
+	 * and assume memmap is contiguous within each section
+	 */
+	for (i = 0; i < sections_per_block; i++, pfn += PAGES_PER_SECTION) {
+		if (WARN_ON_ONCE(!pfn_valid(pfn)))
+			return false;
+		page = pfn_to_page(pfn);
+
+		for (j = 0; j < PAGES_PER_SECTION; j++) {
+			if (PageReserved(page + j))
+				continue;
+
+			printk(KERN_WARNING "section number %ld page number %d "
+				"not reserved, was it already online?\n",
+				pfn_to_section_nr(pfn), j);
+
+			return false;
+		}
+	}
+
+	return true;
+}
+
+/*
+ * 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(unsigned long phys_index, unsigned long action, int online_type)
+{
+	unsigned long start_pfn;
+	unsigned long nr_pages = PAGES_PER_SECTION * sections_per_block;
+	struct page *first_page;
+	int ret;
+
+	first_page = pfn_to_page(phys_index << PFN_SECTION_SHIFT);
+	start_pfn = page_to_pfn(first_page);
+
+	switch (action) {
+		case MEM_ONLINE:
+			if (!pages_correctly_reserved(start_pfn))
+				return -EBUSY;
+
+			ret = online_pages(start_pfn, nr_pages, online_type);
+			break;
+		case MEM_OFFLINE:
+			ret = offline_pages(start_pfn, nr_pages);
+			break;
+		default:
+			WARN(1, KERN_WARNING "%s(%ld, %ld) unknown action: "
+			     "%ld\n", __func__, phys_index, action, action);
+			ret = -EINVAL;
+	}
+
+	return ret;
+}
+
+static int __memory_block_change_state(struct memory_block *mem,
+		unsigned long to_state, unsigned long from_state_req,
+		int online_type)
+{
+	int ret = 0;
+
+	if (mem->state != from_state_req) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	if (to_state == MEM_OFFLINE)
+		mem->state = MEM_GOING_OFFLINE;
+
+	ret = memory_block_action(mem->start_section_nr, to_state, online_type);
+
+	if (ret) {
+		mem->state = from_state_req;
+		goto out;
+	}
+
+	mem->state = to_state;
+	switch (mem->state) {
+	case MEM_OFFLINE:
+		kobject_uevent(&mem->dev.kobj, KOBJ_OFFLINE);
+		break;
+	case MEM_ONLINE:
+		kobject_uevent(&mem->dev.kobj, KOBJ_ONLINE);
+		break;
+	default:
+		break;
+	}
+out:
+	return ret;
+}
+
+static int memory_block_change_state(struct memory_block *mem,
+		unsigned long to_state, unsigned long from_state_req,
+		int online_type)
+{
+	int ret;
+
+	mutex_lock(&mem->state_mutex);
+	ret = __memory_block_change_state(mem, to_state, from_state_req,
+					  online_type);
+	mutex_unlock(&mem->state_mutex);
+
+	return ret;
+}
+static ssize_t
+store_mem_state(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t count)
+{
+	struct memory_block *mem;
+	int ret = -EINVAL;
+
+	mem = container_of(dev, struct memory_block, dev);
+
+	if (!strncmp(buf, "online_kernel", min_t(int, count, 13)))
+		ret = memory_block_change_state(mem, MEM_ONLINE,
+						MEM_OFFLINE, ONLINE_KERNEL);
+	else if (!strncmp(buf, "online_movable", min_t(int, count, 14)))
+		ret = memory_block_change_state(mem, MEM_ONLINE,
+						MEM_OFFLINE, ONLINE_MOVABLE);
+	else if (!strncmp(buf, "online", min_t(int, count, 6)))
+		ret = memory_block_change_state(mem, MEM_ONLINE,
+						MEM_OFFLINE, ONLINE_KEEP);
+	else if(!strncmp(buf, "offline", min_t(int, count, 7)))
+		ret = memory_block_change_state(mem, MEM_OFFLINE,
+						MEM_ONLINE, -1);
+
+	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 device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	struct memory_block *mem =
+		container_of(dev, struct memory_block, dev);
+	return sprintf(buf, "%d\n", mem->phys_device);
+}
+
+static DEVICE_ATTR(phys_index, 0444, show_mem_start_phys_index, NULL);
+static DEVICE_ATTR(end_phys_index, 0444, show_mem_end_phys_index, NULL);
+static DEVICE_ATTR(state, 0644, show_mem_state, store_mem_state);
+static DEVICE_ATTR(phys_device, 0444, show_phys_device, NULL);
+static DEVICE_ATTR(removable, 0444, show_mem_removable, NULL);
+
+#define mem_create_simple_file(mem, attr_name)	\
+	device_create_file(&mem->dev, &dev_attr_##attr_name)
+#define mem_remove_simple_file(mem, attr_name)	\
+	device_remove_file(&mem->dev, &dev_attr_##attr_name)
+
+/*
+ * Block size attribute stuff
+ */
+static ssize_t
+print_block_size(struct device *dev, struct device_attribute *attr,
+		 char *buf)
+{
+	return sprintf(buf, "%lx\n", get_memory_block_size());
+}
+
+static DEVICE_ATTR(block_size_bytes, 0444, print_block_size, NULL);
+
+static int block_size_init(void)
+{
+	return device_create_file(memory_subsys.dev_root,
+				  &dev_attr_block_size_bytes);
+}
+
+/*
+ * 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 device *dev, struct device_attribute *attr,
+		   const char *buf, size_t count)
+{
+	u64 phys_addr;
+	int nid;
+	int i, ret;
+	unsigned long pages_per_block = PAGES_PER_SECTION * sections_per_block;
+
+	phys_addr = simple_strtoull(buf, NULL, 0);
+
+	if (phys_addr & ((pages_per_block << PAGE_SHIFT) - 1))
+		return -EINVAL;
+
+	for (i = 0; i < sections_per_block; i++) {
+		nid = memory_add_physaddr_to_nid(phys_addr);
+		ret = add_memory(nid, phys_addr,
+				 PAGES_PER_SECTION << PAGE_SHIFT);
+		if (ret)
+			goto out;
+
+		phys_addr += MIN_MEMORY_BLOCK_SIZE;
+	}
+
+	ret = count;
+out:
+	return ret;
+}
+static DEVICE_ATTR(probe, S_IWUSR, NULL, memory_probe_store);
+
+static int memory_probe_init(void)
+{
+	return device_create_file(memory_subsys.dev_root, &dev_attr_probe);
+}
+#else
+static inline int memory_probe_init(void)
+{
+	return 0;
+}
+#endif
+
+#ifdef CONFIG_MEMORY_FAILURE
+/*
+ * Support for offlining pages of memory
+ */
+
+/* Soft offline a page */
+static ssize_t
+store_soft_offline_page(struct device *dev,
+			struct device_attribute *attr,
+			const char *buf, size_t count)
+{
+	int ret;
+	u64 pfn;
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+	if (strict_strtoull(buf, 0, &pfn) < 0)
+		return -EINVAL;
+	pfn >>= PAGE_SHIFT;
+	if (!pfn_valid(pfn))
+		return -ENXIO;
+	ret = soft_offline_page(pfn_to_page(pfn), 0);
+	return ret == 0 ? count : ret;
+}
+
+/* Forcibly offline a page, including killing processes. */
+static ssize_t
+store_hard_offline_page(struct device *dev,
+			struct device_attribute *attr,
+			const char *buf, size_t count)
+{
+	int ret;
+	u64 pfn;
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+	if (strict_strtoull(buf, 0, &pfn) < 0)
+		return -EINVAL;
+	pfn >>= PAGE_SHIFT;
+	ret = memory_failure(pfn, 0, 0);
+	return ret ? ret : count;
+}
+
+static DEVICE_ATTR(soft_offline_page, S_IWUSR, NULL, store_soft_offline_page);
+static DEVICE_ATTR(hard_offline_page, S_IWUSR, NULL, store_hard_offline_page);
+
+static __init int memory_fail_init(void)
+{
+	int err;
+
+	err = device_create_file(memory_subsys.dev_root,
+				&dev_attr_soft_offline_page);
+	if (!err)
+		err = device_create_file(memory_subsys.dev_root,
+				&dev_attr_hard_offline_page);
+	return err;
+}
+#else
+static inline int memory_fail_init(void)
+{
+	return 0;
+}
+#endif
+
+/*
+ * Note that phys_device is optional.  It is here to allow for
+ * differentiation between which *physical* devices each
+ * section belongs to...
+ */
+int __weak arch_get_memory_phys_device(unsigned long start_pfn)
+{
+	return 0;
+}
+
+/*
+ * A reference for the returned object is held and the reference for the
+ * hinted object is released.
+ */
+struct memory_block *find_memory_block_hinted(struct mem_section *section,
+					      struct memory_block *hint)
+{
+	int block_id = base_memory_block_id(__section_nr(section));
+	struct device *hintdev = hint ? &hint->dev : NULL;
+	struct device *dev;
+
+	dev = subsys_find_device_by_id(&memory_subsys, block_id, hintdev);
+	if (hint)
+		put_device(&hint->dev);
+	if (!dev)
+		return NULL;
+	return container_of(dev, struct memory_block, dev);
+}
+
+/*
+ * 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 device subsystems.
+ */
+struct memory_block *find_memory_block(struct mem_section *section)
+{
+	return find_memory_block_hinted(section, NULL);
+}
+
+static int init_memory_block(struct memory_block **memory,
+			     struct mem_section *section, unsigned long state)
+{
+	struct memory_block *mem;
+	unsigned long start_pfn;
+	int scn_nr;
+	int ret = 0;
+
+	mem = kzalloc(sizeof(*mem), GFP_KERNEL);
+	if (!mem)
+		return -ENOMEM;
+
+	scn_nr = __section_nr(section);
+	mem->start_section_nr =
+			base_memory_block_id(scn_nr) * sections_per_block;
+	mem->end_section_nr = mem->start_section_nr + sections_per_block - 1;
+	mem->state = state;
+	mem->section_count++;
+	mutex_init(&mem->state_mutex);
+	start_pfn = section_nr_to_pfn(mem->start_section_nr);
+	mem->phys_device = arch_get_memory_phys_device(start_pfn);
+
+	ret = register_memory(mem);
+	if (!ret)
+		ret = mem_create_simple_file(mem, phys_index);
+	if (!ret)
+		ret = mem_create_simple_file(mem, end_phys_index);
+	if (!ret)
+		ret = mem_create_simple_file(mem, state);
+	if (!ret)
+		ret = mem_create_simple_file(mem, phys_device);
+	if (!ret)
+		ret = mem_create_simple_file(mem, removable);
+
+	*memory = mem;
+	return ret;
+}
+
+static int add_memory_section(int nid, struct mem_section *section,
+			struct memory_block **mem_p,
+			unsigned long state, enum mem_add_context context)
+{
+	struct memory_block *mem = NULL;
+	int scn_nr = __section_nr(section);
+	int ret = 0;
+
+	mutex_lock(&mem_sysfs_mutex);
+
+	if (context == BOOT) {
+		/* same memory block ? */
+		if (mem_p && *mem_p)
+			if (scn_nr >= (*mem_p)->start_section_nr &&
+			    scn_nr <= (*mem_p)->end_section_nr) {
+				mem = *mem_p;
+				kobject_get(&mem->dev.kobj);
+			}
+	} else
+		mem = find_memory_block(section);
+
+	if (mem) {
+		mem->section_count++;
+		kobject_put(&mem->dev.kobj);
+	} else {
+		ret = init_memory_block(&mem, section, state);
+		/* store memory_block pointer for next loop */
+		if (!ret && context == BOOT)
+			if (mem_p)
+				*mem_p = mem;
+	}
+
+	if (!ret) {
+		if (context == HOTPLUG &&
+		    mem->section_count == sections_per_block)
+			ret = register_mem_sect_under_node(mem, nid);
+	}
+
+	mutex_unlock(&mem_sysfs_mutex);
+	return ret;
+}
+
+/*
+ * need an interface for the VM to add new memory regions,
+ * but without onlining it.
+ */
+int register_new_memory(int nid, struct mem_section *section)
+{
+	return add_memory_section(nid, section, NULL, MEM_OFFLINE, HOTPLUG);
+}
+
+#ifdef CONFIG_MEMORY_HOTREMOVE
+static void
+unregister_memory(struct memory_block *memory)
+{
+	BUG_ON(memory->dev.bus != &memory_subsys);
+
+	/* drop the ref. we got in remove_memory_block() */
+	kobject_put(&memory->dev.kobj);
+	device_unregister(&memory->dev);
+}
+
+static int remove_memory_block(unsigned long node_id,
+			       struct mem_section *section, int phys_device)
+{
+	struct memory_block *mem;
+
+	mutex_lock(&mem_sysfs_mutex);
+	mem = find_memory_block(section);
+	unregister_mem_sect_under_nodes(mem, __section_nr(section));
+
+	mem->section_count--;
+	if (mem->section_count == 0) {
+		mem_remove_simple_file(mem, phys_index);
+		mem_remove_simple_file(mem, end_phys_index);
+		mem_remove_simple_file(mem, state);
+		mem_remove_simple_file(mem, phys_device);
+		mem_remove_simple_file(mem, removable);
+		unregister_memory(mem);
+	} else
+		kobject_put(&mem->dev.kobj);
+
+	mutex_unlock(&mem_sysfs_mutex);
+	return 0;
+}
+
+int unregister_memory_section(struct mem_section *section)
+{
+	if (!present_section(section))
+		return -EINVAL;
+
+	return remove_memory_block(0, section, 0);
+}
+#endif /* CONFIG_MEMORY_HOTREMOVE */
+
+/*
+ * offline one memory block. If the memory block has been offlined, do nothing.
+ */
+int offline_memory_block(struct memory_block *mem)
+{
+	int ret = 0;
+
+	mutex_lock(&mem->state_mutex);
+	if (mem->state != MEM_OFFLINE)
+		ret = __memory_block_change_state(mem, MEM_OFFLINE, MEM_ONLINE, -1);
+	mutex_unlock(&mem->state_mutex);
+
+	return ret;
+}
+
+/* return true if the memory block is offlined, otherwise, return false */
+bool is_memblock_offlined(struct memory_block *mem)
+{
+	return mem->state == MEM_OFFLINE;
+}
+
+/*
+ * Initialize the sysfs support for memory devices...
+ */
+int __init memory_dev_init(void)
+{
+	unsigned int i;
+	int ret;
+	int err;
+	unsigned long block_sz;
+	struct memory_block *mem = NULL;
+
+	ret = subsys_system_register(&memory_subsys, NULL);
+	if (ret)
+		goto out;
+
+	block_sz = get_memory_block_size();
+	sections_per_block = block_sz / MIN_MEMORY_BLOCK_SIZE;
+
+	/*
+	 * Create entries for memory sections that were found
+	 * during boot and have been initialized
+	 */
+	for (i = 0; i < NR_MEM_SECTIONS; i++) {
+		if (!present_section_nr(i))
+			continue;
+		/* don't need to reuse memory_block if only one per block */
+		err = add_memory_section(0, __nr_to_section(i),
+				 (sections_per_block == 1) ? NULL : &mem,
+					 MEM_ONLINE,
+					 BOOT);
+		if (!ret)
+			ret = err;
+	}
+
+	err = memory_probe_init();
+	if (!ret)
+		ret = err;
+	err = memory_fail_init();
+	if (!ret)
+		ret = err;
+	err = block_size_init();
+	if (!ret)
+		ret = err;
+out:
+	if (ret)
+		printk(KERN_ERR "%s() failed: %d\n", __func__, ret);
+	return ret;
+}

drivers/base/module.c

@@ -0,0 +1,93 @@
+/*
+ * module.c - module sysfs fun for drivers
+ *
+ * This file is released under the GPLv2
+ *
+ */
+#include <linux/device.h>
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include "base.h"
+
+static char *make_driver_name(struct device_driver *drv)
+{
+	char *driver_name;
+
+	driver_name = kasprintf(GFP_KERNEL, "%s:%s", drv->bus->name, drv->name);
+	if (!driver_name)
+		return NULL;
+
+	return driver_name;
+}
+
+static void module_create_drivers_dir(struct module_kobject *mk)
+{
+	if (!mk || mk->drivers_dir)
+		return;
+
+	mk->drivers_dir = kobject_create_and_add("drivers", &mk->kobj);
+}
+
+void module_add_driver(struct module *mod, struct device_driver *drv)
+{
+	char *driver_name;
+	int no_warn;
+	struct module_kobject *mk = NULL;
+
+	if (!drv)
+		return;
+
+	if (mod)
+		mk = &mod->mkobj;
+	else if (drv->mod_name) {
+		struct kobject *mkobj;
+
+		/* Lookup built-in module entry in /sys/modules */
+		mkobj = kset_find_obj(module_kset, drv->mod_name);
+		if (mkobj) {
+			mk = container_of(mkobj, struct module_kobject, kobj);
+			/* remember our module structure */
+			drv->p->mkobj = mk;
+			/* kset_find_obj took a reference */
+			kobject_put(mkobj);
+		}
+	}
+
+	if (!mk)
+		return;
+
+	/* Don't check return codes; these calls are idempotent */
+	no_warn = sysfs_create_link(&drv->p->kobj, &mk->kobj, "module");
+	driver_name = make_driver_name(drv);
+	if (driver_name) {
+		module_create_drivers_dir(mk);
+		no_warn = sysfs_create_link(mk->drivers_dir, &drv->p->kobj,
+					    driver_name);
+		kfree(driver_name);
+	}
+}
+
+void module_remove_driver(struct device_driver *drv)
+{
+	struct module_kobject *mk = NULL;
+	char *driver_name;
+
+	if (!drv)
+		return;
+
+	sysfs_remove_link(&drv->p->kobj, "module");
+
+	if (drv->owner)
+		mk = &drv->owner->mkobj;
+	else if (drv->p->mkobj)
+		mk = drv->p->mkobj;
+	if (mk && mk->drivers_dir) {
+		driver_name = make_driver_name(drv);
+		if (driver_name) {
+			sysfs_remove_link(mk->drivers_dir, driver_name);
+			kfree(driver_name);
+		}
+	}
+}

drivers/base/node.c

@@ -0,0 +1,700 @@
+/*
+ * Basic Node interface support
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/mm.h>
+#include <linux/memory.h>
+#include <linux/vmstat.h>
+#include <linux/notifier.h>
+#include <linux/node.h>
+#include <linux/hugetlb.h>
+#include <linux/compaction.h>
+#include <linux/cpumask.h>
+#include <linux/topology.h>
+#include <linux/nodemask.h>
+#include <linux/cpu.h>
+#include <linux/device.h>
+#include <linux/swap.h>
+#include <linux/slab.h>
+
+static struct bus_type node_subsys = {
+	.name = "node",
+	.dev_name = "node",
+};
+
+
+static ssize_t node_read_cpumap(struct device *dev, int type, char *buf)
+{
+	struct node *node_dev = to_node(dev);
+	const struct cpumask *mask = cpumask_of_node(node_dev->dev.id);
+	int len;
+
+	/* 2008/04/07: buf currently PAGE_SIZE, need 9 chars per 32 bits. */
+	BUILD_BUG_ON((NR_CPUS/32 * 9) > (PAGE_SIZE-1));
+
+	len = type?
+		cpulist_scnprintf(buf, PAGE_SIZE-2, mask) :
+		cpumask_scnprintf(buf, PAGE_SIZE-2, mask);
+ 	buf[len++] = '\n';
+ 	buf[len] = '\0';
+	return len;
+}
+
+static inline ssize_t node_read_cpumask(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	return node_read_cpumap(dev, 0, buf);
+}
+static inline ssize_t node_read_cpulist(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	return node_read_cpumap(dev, 1, buf);
+}
+
+static DEVICE_ATTR(cpumap,  S_IRUGO, node_read_cpumask, NULL);
+static DEVICE_ATTR(cpulist, S_IRUGO, node_read_cpulist, NULL);
+
+#define K(x) ((x) << (PAGE_SHIFT - 10))
+static ssize_t node_read_meminfo(struct device *dev,
+			struct device_attribute *attr, char *buf)
+{
+	int n;
+	int nid = dev->id;
+	struct sysinfo i;
+
+	si_meminfo_node(&i, nid);
+	n = sprintf(buf,
+		       "Node %d MemTotal:       %8lu kB\n"
+		       "Node %d MemFree:        %8lu kB\n"
+		       "Node %d MemUsed:        %8lu kB\n"
+		       "Node %d Active:         %8lu kB\n"
+		       "Node %d Inactive:       %8lu kB\n"
+		       "Node %d Active(anon):   %8lu kB\n"
+		       "Node %d Inactive(anon): %8lu kB\n"
+		       "Node %d Active(file):   %8lu kB\n"
+		       "Node %d Inactive(file): %8lu kB\n"
+		       "Node %d Unevictable:    %8lu kB\n"
+		       "Node %d Mlocked:        %8lu kB\n",
+		       nid, K(i.totalram),
+		       nid, K(i.freeram),
+		       nid, K(i.totalram - i.freeram),
+		       nid, K(node_page_state(nid, NR_ACTIVE_ANON) +
+				node_page_state(nid, NR_ACTIVE_FILE)),
+		       nid, K(node_page_state(nid, NR_INACTIVE_ANON) +
+				node_page_state(nid, NR_INACTIVE_FILE)),
+		       nid, K(node_page_state(nid, NR_ACTIVE_ANON)),
+		       nid, K(node_page_state(nid, NR_INACTIVE_ANON)),
+		       nid, K(node_page_state(nid, NR_ACTIVE_FILE)),
+		       nid, K(node_page_state(nid, NR_INACTIVE_FILE)),
+		       nid, K(node_page_state(nid, NR_UNEVICTABLE)),
+		       nid, K(node_page_state(nid, NR_MLOCK)));
+
+#ifdef CONFIG_HIGHMEM
+	n += sprintf(buf + n,
+		       "Node %d HighTotal:      %8lu kB\n"
+		       "Node %d HighFree:       %8lu kB\n"
+		       "Node %d LowTotal:       %8lu kB\n"
+		       "Node %d LowFree:        %8lu kB\n",
+		       nid, K(i.totalhigh),
+		       nid, K(i.freehigh),
+		       nid, K(i.totalram - i.totalhigh),
+		       nid, K(i.freeram - i.freehigh));
+#endif
+	n += sprintf(buf + n,
+		       "Node %d Dirty:          %8lu kB\n"
+		       "Node %d Writeback:      %8lu kB\n"
+		       "Node %d FilePages:      %8lu kB\n"
+		       "Node %d Mapped:         %8lu kB\n"
+		       "Node %d AnonPages:      %8lu kB\n"
+		       "Node %d Shmem:          %8lu kB\n"
+		       "Node %d KernelStack:    %8lu kB\n"
+		       "Node %d PageTables:     %8lu kB\n"
+		       "Node %d NFS_Unstable:   %8lu kB\n"
+		       "Node %d Bounce:         %8lu kB\n"
+		       "Node %d WritebackTmp:   %8lu kB\n"
+		       "Node %d Slab:           %8lu kB\n"
+		       "Node %d SReclaimable:   %8lu kB\n"
+		       "Node %d SUnreclaim:     %8lu kB\n"
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+		       "Node %d AnonHugePages:  %8lu kB\n"
+#endif
+			,
+		       nid, K(node_page_state(nid, NR_FILE_DIRTY)),
+		       nid, K(node_page_state(nid, NR_WRITEBACK)),
+		       nid, K(node_page_state(nid, NR_FILE_PAGES)),
+		       nid, K(node_page_state(nid, NR_FILE_MAPPED)),
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+		       nid, K(node_page_state(nid, NR_ANON_PAGES)
+			+ node_page_state(nid, NR_ANON_TRANSPARENT_HUGEPAGES) *
+			HPAGE_PMD_NR),
+#else
+		       nid, K(node_page_state(nid, NR_ANON_PAGES)),
+#endif
+		       nid, K(node_page_state(nid, NR_SHMEM)),
+		       nid, node_page_state(nid, NR_KERNEL_STACK) *
+				THREAD_SIZE / 1024,
+		       nid, K(node_page_state(nid, NR_PAGETABLE)),
+		       nid, K(node_page_state(nid, NR_UNSTABLE_NFS)),
+		       nid, K(node_page_state(nid, NR_BOUNCE)),
+		       nid, K(node_page_state(nid, NR_WRITEBACK_TEMP)),
+		       nid, K(node_page_state(nid, NR_SLAB_RECLAIMABLE) +
+				node_page_state(nid, NR_SLAB_UNRECLAIMABLE)),
+		       nid, K(node_page_state(nid, NR_SLAB_RECLAIMABLE)),
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+		       nid, K(node_page_state(nid, NR_SLAB_UNRECLAIMABLE))
+			, nid,
+			K(node_page_state(nid, NR_ANON_TRANSPARENT_HUGEPAGES) *
+			HPAGE_PMD_NR));
+#else
+		       nid, K(node_page_state(nid, NR_SLAB_UNRECLAIMABLE)));
+#endif
+	n += hugetlb_report_node_meminfo(nid, buf + n);
+	return n;
+}
+
+#undef K
+static DEVICE_ATTR(meminfo, S_IRUGO, node_read_meminfo, NULL);
+
+static ssize_t node_read_numastat(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	return sprintf(buf,
+		       "numa_hit %lu\n"
+		       "numa_miss %lu\n"
+		       "numa_foreign %lu\n"
+		       "interleave_hit %lu\n"
+		       "local_node %lu\n"
+		       "other_node %lu\n",
+		       node_page_state(dev->id, NUMA_HIT),
+		       node_page_state(dev->id, NUMA_MISS),
+		       node_page_state(dev->id, NUMA_FOREIGN),
+		       node_page_state(dev->id, NUMA_INTERLEAVE_HIT),
+		       node_page_state(dev->id, NUMA_LOCAL),
+		       node_page_state(dev->id, NUMA_OTHER));
+}
+static DEVICE_ATTR(numastat, S_IRUGO, node_read_numastat, NULL);
+
+static ssize_t node_read_vmstat(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	int nid = dev->id;
+	int i;
+	int n = 0;
+
+	for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++)
+		n += sprintf(buf+n, "%s %lu\n", vmstat_text[i],
+			     node_page_state(nid, i));
+
+	return n;
+}
+static DEVICE_ATTR(vmstat, S_IRUGO, node_read_vmstat, NULL);
+
+static ssize_t node_read_distance(struct device *dev,
+			struct device_attribute *attr, char * buf)
+{
+	int nid = dev->id;
+	int len = 0;
+	int i;
+
+	/*
+	 * buf is currently PAGE_SIZE in length and each node needs 4 chars
+	 * at the most (distance + space or newline).
+	 */
+	BUILD_BUG_ON(MAX_NUMNODES * 4 > PAGE_SIZE);
+
+	for_each_online_node(i)
+		len += sprintf(buf + len, "%s%d", i ? " " : "", node_distance(nid, i));
+
+	len += sprintf(buf + len, "\n");
+	return len;
+}
+static DEVICE_ATTR(distance, S_IRUGO, node_read_distance, NULL);
+
+#ifdef CONFIG_HUGETLBFS
+/*
+ * hugetlbfs per node attributes registration interface:
+ * When/if hugetlb[fs] subsystem initializes [sometime after this module],
+ * it will register its per node attributes for all online nodes with
+ * memory.  It will also call register_hugetlbfs_with_node(), below, to
+ * register its attribute registration functions with this node driver.
+ * Once these hooks have been initialized, the node driver will call into
+ * the hugetlb module to [un]register attributes for hot-plugged nodes.
+ */
+static node_registration_func_t __hugetlb_register_node;
+static node_registration_func_t __hugetlb_unregister_node;
+
+static inline bool hugetlb_register_node(struct node *node)
+{
+	if (__hugetlb_register_node &&
+			node_state(node->dev.id, N_MEMORY)) {
+		__hugetlb_register_node(node);
+		return true;
+	}
+	return false;
+}
+
+static inline void hugetlb_unregister_node(struct node *node)
+{
+	if (__hugetlb_unregister_node)
+		__hugetlb_unregister_node(node);
+}
+
+void register_hugetlbfs_with_node(node_registration_func_t doregister,
+				  node_registration_func_t unregister)
+{
+	__hugetlb_register_node   = doregister;
+	__hugetlb_unregister_node = unregister;
+}
+#else
+static inline void hugetlb_register_node(struct node *node) {}
+
+static inline void hugetlb_unregister_node(struct node *node) {}
+#endif
+
+static void node_device_release(struct device *dev)
+{
+	struct node *node = to_node(dev);
+
+#if defined(CONFIG_MEMORY_HOTPLUG_SPARSE) && defined(CONFIG_HUGETLBFS)
+	/*
+	 * We schedule the work only when a memory section is
+	 * onlined/offlined on this node. When we come here,
+	 * all the memory on this node has been offlined,
+	 * so we won't enqueue new work to this work.
+	 *
+	 * The work is using node->node_work, so we should
+	 * flush work before freeing the memory.
+	 */
+	flush_work(&node->node_work);
+#endif
+	kfree(node);
+}
+
+/*
+ * register_node - Setup a sysfs device for a node.
+ * @num - Node number to use when creating the device.
+ *
+ * Initialize and register the node device.
+ */
+static int register_node(struct node *node, int num, struct node *parent)
+{
+	int error;
+
+	node->dev.id = num;
+	node->dev.bus = &node_subsys;
+	node->dev.release = node_device_release;
+	error = device_register(&node->dev);
+
+	if (!error){
+		device_create_file(&node->dev, &dev_attr_cpumap);
+		device_create_file(&node->dev, &dev_attr_cpulist);
+		device_create_file(&node->dev, &dev_attr_meminfo);
+		device_create_file(&node->dev, &dev_attr_numastat);
+		device_create_file(&node->dev, &dev_attr_distance);
+		device_create_file(&node->dev, &dev_attr_vmstat);
+
+		scan_unevictable_register_node(node);
+
+		hugetlb_register_node(node);
+
+		compaction_register_node(node);
+	}
+	return error;
+}
+
+/**
+ * unregister_node - unregister a node device
+ * @node: node going away
+ *
+ * Unregisters a node device @node.  All the devices on the node must be
+ * unregistered before calling this function.
+ */
+void unregister_node(struct node *node)
+{
+	device_remove_file(&node->dev, &dev_attr_cpumap);
+	device_remove_file(&node->dev, &dev_attr_cpulist);
+	device_remove_file(&node->dev, &dev_attr_meminfo);
+	device_remove_file(&node->dev, &dev_attr_numastat);
+	device_remove_file(&node->dev, &dev_attr_distance);
+	device_remove_file(&node->dev, &dev_attr_vmstat);
+
+	scan_unevictable_unregister_node(node);
+	hugetlb_unregister_node(node);		/* no-op, if memoryless node */
+
+	device_unregister(&node->dev);
+}
+
+struct node *node_devices[MAX_NUMNODES];
+
+/*
+ * register cpu under node
+ */
+int register_cpu_under_node(unsigned int cpu, unsigned int nid)
+{
+	int ret;
+	struct device *obj;
+
+	if (!node_online(nid))
+		return 0;
+
+	obj = get_cpu_device(cpu);
+	if (!obj)
+		return 0;
+
+	ret = sysfs_create_link(&node_devices[nid]->dev.kobj,
+				&obj->kobj,
+				kobject_name(&obj->kobj));
+	if (ret)
+		return ret;
+
+	return sysfs_create_link(&obj->kobj,
+				 &node_devices[nid]->dev.kobj,
+				 kobject_name(&node_devices[nid]->dev.kobj));
+}
+
+int unregister_cpu_under_node(unsigned int cpu, unsigned int nid)
+{
+	struct device *obj;
+
+	if (!node_online(nid))
+		return 0;
+
+	obj = get_cpu_device(cpu);
+	if (!obj)
+		return 0;
+
+	sysfs_remove_link(&node_devices[nid]->dev.kobj,
+			  kobject_name(&obj->kobj));
+	sysfs_remove_link(&obj->kobj,
+			  kobject_name(&node_devices[nid]->dev.kobj));
+
+	return 0;
+}
+
+#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE
+#define page_initialized(page)  (page->lru.next)
+
+static int get_nid_for_pfn(unsigned long pfn)
+{
+	struct page *page;
+
+	if (!pfn_valid_within(pfn))
+		return -1;
+	page = pfn_to_page(pfn);
+	if (!page_initialized(page))
+		return -1;
+	return pfn_to_nid(pfn);
+}
+
+/* register memory section under specified node if it spans that node */
+int register_mem_sect_under_node(struct memory_block *mem_blk, int nid)
+{
+	int ret;
+	unsigned long pfn, sect_start_pfn, sect_end_pfn;
+
+	if (!mem_blk)
+		return -EFAULT;
+	if (!node_online(nid))
+		return 0;
+
+	sect_start_pfn = section_nr_to_pfn(mem_blk->start_section_nr);
+	sect_end_pfn = section_nr_to_pfn(mem_blk->end_section_nr);
+	sect_end_pfn += PAGES_PER_SECTION - 1;
+	for (pfn = sect_start_pfn; pfn <= sect_end_pfn; pfn++) {
+		int page_nid;
+
+		page_nid = get_nid_for_pfn(pfn);
+		if (page_nid < 0)
+			continue;
+		if (page_nid != nid)
+			continue;
+		ret = sysfs_create_link_nowarn(&node_devices[nid]->dev.kobj,
+					&mem_blk->dev.kobj,
+					kobject_name(&mem_blk->dev.kobj));
+		if (ret)
+			return ret;
+
+		return sysfs_create_link_nowarn(&mem_blk->dev.kobj,
+				&node_devices[nid]->dev.kobj,
+				kobject_name(&node_devices[nid]->dev.kobj));
+	}
+	/* mem section does not span the specified node */
+	return 0;
+}
+
+/* unregister memory section under all nodes that it spans */
+int unregister_mem_sect_under_nodes(struct memory_block *mem_blk,
+				    unsigned long phys_index)
+{
+	NODEMASK_ALLOC(nodemask_t, unlinked_nodes, GFP_KERNEL);
+	unsigned long pfn, sect_start_pfn, sect_end_pfn;
+
+	if (!mem_blk) {
+		NODEMASK_FREE(unlinked_nodes);
+		return -EFAULT;
+	}
+	if (!unlinked_nodes)
+		return -ENOMEM;
+	nodes_clear(*unlinked_nodes);
+
+	sect_start_pfn = section_nr_to_pfn(phys_index);
+	sect_end_pfn = sect_start_pfn + PAGES_PER_SECTION - 1;
+	for (pfn = sect_start_pfn; pfn <= sect_end_pfn; pfn++) {
+		int nid;
+
+		nid = get_nid_for_pfn(pfn);
+		if (nid < 0)
+			continue;
+		if (!node_online(nid))
+			continue;
+		if (node_test_and_set(nid, *unlinked_nodes))
+			continue;
+		sysfs_remove_link(&node_devices[nid]->dev.kobj,
+			 kobject_name(&mem_blk->dev.kobj));
+		sysfs_remove_link(&mem_blk->dev.kobj,
+			 kobject_name(&node_devices[nid]->dev.kobj));
+	}
+	NODEMASK_FREE(unlinked_nodes);
+	return 0;
+}
+
+static int link_mem_sections(int nid)
+{
+	unsigned long start_pfn = NODE_DATA(nid)->node_start_pfn;
+	unsigned long end_pfn = start_pfn + NODE_DATA(nid)->node_spanned_pages;
+	unsigned long pfn;
+	struct memory_block *mem_blk = NULL;
+	int err = 0;
+
+	for (pfn = start_pfn; pfn < end_pfn; pfn += PAGES_PER_SECTION) {
+		unsigned long section_nr = pfn_to_section_nr(pfn);
+		struct mem_section *mem_sect;
+		int ret;
+
+		if (!present_section_nr(section_nr))
+			continue;
+		mem_sect = __nr_to_section(section_nr);
+
+		/* same memblock ? */
+		if (mem_blk)
+			if ((section_nr >= mem_blk->start_section_nr) &&
+			    (section_nr <= mem_blk->end_section_nr))
+				continue;
+
+		mem_blk = find_memory_block_hinted(mem_sect, mem_blk);
+
+		ret = register_mem_sect_under_node(mem_blk, nid);
+		if (!err)
+			err = ret;
+
+		/* discard ref obtained in find_memory_block() */
+	}
+
+	if (mem_blk)
+		kobject_put(&mem_blk->dev.kobj);
+	return err;
+}
+
+#ifdef CONFIG_HUGETLBFS
+/*
+ * Handle per node hstate attribute [un]registration on transistions
+ * to/from memoryless state.
+ */
+static void node_hugetlb_work(struct work_struct *work)
+{
+	struct node *node = container_of(work, struct node, node_work);
+
+	/*
+	 * We only get here when a node transitions to/from memoryless state.
+	 * We can detect which transition occurred by examining whether the
+	 * node has memory now.  hugetlb_register_node() already check this
+	 * so we try to register the attributes.  If that fails, then the
+	 * node has transitioned to memoryless, try to unregister the
+	 * attributes.
+	 */
+	if (!hugetlb_register_node(node))
+		hugetlb_unregister_node(node);
+}
+
+static void init_node_hugetlb_work(int nid)
+{
+	INIT_WORK(&node_devices[nid]->node_work, node_hugetlb_work);
+}
+
+static int node_memory_callback(struct notifier_block *self,
+				unsigned long action, void *arg)
+{
+	struct memory_notify *mnb = arg;
+	int nid = mnb->status_change_nid;
+
+	switch (action) {
+	case MEM_ONLINE:
+	case MEM_OFFLINE:
+		/*
+		 * offload per node hstate [un]registration to a work thread
+		 * when transitioning to/from memoryless state.
+		 */
+		if (nid != NUMA_NO_NODE)
+			schedule_work(&node_devices[nid]->node_work);
+		break;
+
+	case MEM_GOING_ONLINE:
+	case MEM_GOING_OFFLINE:
+	case MEM_CANCEL_ONLINE:
+	case MEM_CANCEL_OFFLINE:
+	default:
+		break;
+	}
+
+	return NOTIFY_OK;
+}
+#endif	/* CONFIG_HUGETLBFS */
+#else	/* !CONFIG_MEMORY_HOTPLUG_SPARSE */
+
+static int link_mem_sections(int nid) { return 0; }
+#endif	/* CONFIG_MEMORY_HOTPLUG_SPARSE */
+
+#if !defined(CONFIG_MEMORY_HOTPLUG_SPARSE) || \
+    !defined(CONFIG_HUGETLBFS)
+static inline int node_memory_callback(struct notifier_block *self,
+				unsigned long action, void *arg)
+{
+	return NOTIFY_OK;
+}
+
+static void init_node_hugetlb_work(int nid) { }
+
+#endif
+
+int register_one_node(int nid)
+{
+	int error = 0;
+	int cpu;
+
+	if (node_online(nid)) {
+		int p_node = parent_node(nid);
+		struct node *parent = NULL;
+
+		if (p_node != nid)
+			parent = node_devices[p_node];
+
+		node_devices[nid] = kzalloc(sizeof(struct node), GFP_KERNEL);
+		if (!node_devices[nid])
+			return -ENOMEM;
+
+		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);
+		}
+
+		/* link memory sections under this node */
+		error = link_mem_sections(nid);
+
+		/* initialize work queue for memory hot plug */
+		init_node_hugetlb_work(nid);
+	}
+
+	return error;
+
+}
+
+void unregister_one_node(int nid)
+{
+	unregister_node(node_devices[nid]);
+	node_devices[nid] = NULL;
+}
+
+/*
+ * node states attributes
+ */
+
+static ssize_t print_nodes_state(enum node_states state, char *buf)
+{
+	int n;
+
+	n = nodelist_scnprintf(buf, PAGE_SIZE-2, node_states[state]);
+	buf[n++] = '\n';
+	buf[n] = '\0';
+	return n;
+}
+
+struct node_attr {
+	struct device_attribute attr;
+	enum node_states state;
+};
+
+static ssize_t show_node_state(struct device *dev,
+			       struct device_attribute *attr, char *buf)
+{
+	struct node_attr *na = container_of(attr, struct node_attr, attr);
+	return print_nodes_state(na->state, buf);
+}
+
+#define _NODE_ATTR(name, state) \
+	{ __ATTR(name, 0444, show_node_state, NULL), state }
+
+static struct node_attr node_state_attr[] = {
+	[N_POSSIBLE] = _NODE_ATTR(possible, N_POSSIBLE),
+	[N_ONLINE] = _NODE_ATTR(online, N_ONLINE),
+	[N_NORMAL_MEMORY] = _NODE_ATTR(has_normal_memory, N_NORMAL_MEMORY),
+#ifdef CONFIG_HIGHMEM
+	[N_HIGH_MEMORY] = _NODE_ATTR(has_high_memory, N_HIGH_MEMORY),
+#endif
+#ifdef CONFIG_MOVABLE_NODE
+	[N_MEMORY] = _NODE_ATTR(has_memory, N_MEMORY),
+#endif
+	[N_CPU] = _NODE_ATTR(has_cpu, N_CPU),
+};
+
+static struct attribute *node_state_attrs[] = {
+	&node_state_attr[N_POSSIBLE].attr.attr,
+	&node_state_attr[N_ONLINE].attr.attr,
+	&node_state_attr[N_NORMAL_MEMORY].attr.attr,
+#ifdef CONFIG_HIGHMEM
+	&node_state_attr[N_HIGH_MEMORY].attr.attr,
+#endif
+#ifdef CONFIG_MOVABLE_NODE
+	&node_state_attr[N_MEMORY].attr.attr,
+#endif
+	&node_state_attr[N_CPU].attr.attr,
+	NULL
+};
+
+static struct attribute_group memory_root_attr_group = {
+	.attrs = node_state_attrs,
+};
+
+static const struct attribute_group *cpu_root_attr_groups[] = {
+	&memory_root_attr_group,
+	NULL,
+};
+
+#define NODE_CALLBACK_PRI	2	/* lower than SLAB */
+static int __init register_node_type(void)
+{
+	int ret;
+
+ 	BUILD_BUG_ON(ARRAY_SIZE(node_state_attr) != NR_NODE_STATES);
+ 	BUILD_BUG_ON(ARRAY_SIZE(node_state_attrs)-1 != NR_NODE_STATES);
+
+	ret = subsys_system_register(&node_subsys, cpu_root_attr_groups);
+	if (!ret) {
+		static struct notifier_block node_memory_callback_nb = {
+			.notifier_call = node_memory_callback,
+			.priority = NODE_CALLBACK_PRI,
+		};
+		register_hotmemory_notifier(&node_memory_callback_nb);
+	}
+
+	/*
+	 * Note:  we're not going to unregister the node class if we fail
+	 * to register the node state class attribute files.
+	 */
+	return ret;
+}
+postcore_initcall(register_node_type);

drivers/base/pinctrl.c

@@ -0,0 +1,69 @@
+/*
+ * Driver core interface to the pinctrl subsystem.
+ *
+ * Copyright (C) 2012 ST-Ericsson SA
+ * Written on behalf of Linaro for ST-Ericsson
+ * Based on bits of regulator core, gpio core and clk core
+ *
+ * Author: Linus Walleij <linus.walleij@linaro.org>
+ *
+ * License terms: GNU General Public License (GPL) version 2
+ */
+
+#include <linux/device.h>
+#include <linux/pinctrl/devinfo.h>
+#include <linux/pinctrl/consumer.h>
+#include <linux/slab.h>
+
+/**
+ * pinctrl_bind_pins() - called by the device core before probe
+ * @dev: the device that is just about to probe
+ */
+int pinctrl_bind_pins(struct device *dev)
+{
+	int ret;
+
+	dev->pins = devm_kzalloc(dev, sizeof(*(dev->pins)), GFP_KERNEL);
+	if (!dev->pins)
+		return -ENOMEM;
+
+	dev->pins->p = devm_pinctrl_get(dev);
+	if (IS_ERR(dev->pins->p)) {
+		dev_dbg(dev, "no pinctrl handle\n");
+		ret = PTR_ERR(dev->pins->p);
+		goto cleanup_alloc;
+	}
+
+	dev->pins->default_state = pinctrl_lookup_state(dev->pins->p,
+					PINCTRL_STATE_DEFAULT);
+	if (IS_ERR(dev->pins->default_state)) {
+		dev_dbg(dev, "no default pinctrl state\n");
+		ret = 0;
+		goto cleanup_get;
+	}
+
+	ret = pinctrl_select_state(dev->pins->p, dev->pins->default_state);
+	if (ret) {
+		dev_dbg(dev, "failed to activate default pinctrl state\n");
+		goto cleanup_get;
+	}
+
+	return 0;
+
+	/*
+	 * If no pinctrl handle or default state was found for this device,
+	 * let's explicitly free the pin container in the device, there is
+	 * no point in keeping it around.
+	 */
+cleanup_get:
+	devm_pinctrl_put(dev->pins->p);
+cleanup_alloc:
+	devm_kfree(dev, dev->pins);
+	dev->pins = NULL;
+
+	/* Only return deferrals */
+	if (ret != -EPROBE_DEFER)
+		ret = 0;
+
+	return ret;
+}

drivers/base/power/Makefile

@@ -0,0 +1,9 @@
+obj-$(CONFIG_PM)	+= sysfs.o generic_ops.o common.o qos.o
+obj-$(CONFIG_PM_SLEEP)	+= main.o suspend_volatile.o wakeup.o dark_resume.o
+obj-$(CONFIG_PM_RUNTIME)	+= runtime.o
+obj-$(CONFIG_PM_TRACE_RTC)	+= trace.o
+obj-$(CONFIG_PM_OPP)	+= opp.o
+obj-$(CONFIG_PM_GENERIC_DOMAINS)	+=  domain.o domain_governor.o
+obj-$(CONFIG_HAVE_CLK)	+= clock_ops.o
+
+ccflags-$(CONFIG_DEBUG_DRIVER) := -DDEBUG

drivers/base/power/clock_ops.c

@@ -0,0 +1,486 @@
+/*
+ * drivers/base/power/clock_ops.c - Generic clock manipulation PM callbacks
+ *
+ * Copyright (c) 2011 Rafael J. Wysocki <rjw@sisk.pl>, Renesas Electronics Corp.
+ *
+ * This file is released under the GPLv2.
+ */
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/device.h>
+#include <linux/io.h>
+#include <linux/pm.h>
+#include <linux/pm_clock.h>
+#include <linux/clk.h>
+#include <linux/slab.h>
+#include <linux/err.h>
+
+#ifdef CONFIG_PM
+
+enum pce_status {
+	PCE_STATUS_NONE = 0,
+	PCE_STATUS_ACQUIRED,
+	PCE_STATUS_ENABLED,
+	PCE_STATUS_ERROR,
+};
+
+struct pm_clock_entry {
+	struct list_head node;
+	char *con_id;
+	struct clk *clk;
+	enum pce_status status;
+};
+
+/**
+ * pm_clk_acquire - Acquire a device clock.
+ * @dev: Device whose clock is to be acquired.
+ * @ce: PM clock entry corresponding to the clock.
+ */
+static void pm_clk_acquire(struct device *dev, struct pm_clock_entry *ce)
+{
+	ce->clk = clk_get(dev, ce->con_id);
+	if (IS_ERR(ce->clk)) {
+		ce->status = PCE_STATUS_ERROR;
+	} else {
+		ce->status = PCE_STATUS_ACQUIRED;
+		dev_dbg(dev, "Clock %s managed by runtime PM.\n", ce->con_id);
+	}
+}
+
+/**
+ * pm_clk_add - Start using a device clock for power management.
+ * @dev: Device whose clock is going to be used for power management.
+ * @con_id: Connection ID of the clock.
+ *
+ * Add the clock represented by @con_id to the list of clocks used for
+ * the power management of @dev.
+ */
+int pm_clk_add(struct device *dev, const char *con_id)
+{
+	struct pm_subsys_data *psd = dev_to_psd(dev);
+	struct pm_clock_entry *ce;
+
+	if (!psd)
+		return -EINVAL;
+
+	ce = kzalloc(sizeof(*ce), GFP_KERNEL);
+	if (!ce) {
+		dev_err(dev, "Not enough memory for clock entry.\n");
+		return -ENOMEM;
+	}
+
+	if (con_id) {
+		ce->con_id = kstrdup(con_id, GFP_KERNEL);
+		if (!ce->con_id) {
+			dev_err(dev,
+				"Not enough memory for clock connection ID.\n");
+			kfree(ce);
+			return -ENOMEM;
+		}
+	}
+
+	pm_clk_acquire(dev, ce);
+
+	spin_lock_irq(&psd->lock);
+	list_add_tail(&ce->node, &psd->clock_list);
+	spin_unlock_irq(&psd->lock);
+	return 0;
+}
+
+/**
+ * __pm_clk_remove - Destroy PM clock entry.
+ * @ce: PM clock entry to destroy.
+ */
+static void __pm_clk_remove(struct pm_clock_entry *ce)
+{
+	if (!ce)
+		return;
+
+	if (ce->status < PCE_STATUS_ERROR) {
+		if (ce->status == PCE_STATUS_ENABLED)
+			clk_disable_unprepare(ce->clk);
+
+		if (ce->status >= PCE_STATUS_ACQUIRED)
+			clk_put(ce->clk);
+	}
+
+	kfree(ce->con_id);
+	kfree(ce);
+}
+
+/**
+ * pm_clk_remove - Stop using a device clock for power management.
+ * @dev: Device whose clock should not be used for PM any more.
+ * @con_id: Connection ID of the clock.
+ *
+ * Remove the clock represented by @con_id from the list of clocks used for
+ * the power management of @dev.
+ */
+void pm_clk_remove(struct device *dev, const char *con_id)
+{
+	struct pm_subsys_data *psd = dev_to_psd(dev);
+	struct pm_clock_entry *ce;
+
+	if (!psd)
+		return;
+
+	spin_lock_irq(&psd->lock);
+
+	list_for_each_entry(ce, &psd->clock_list, node) {
+		if (!con_id && !ce->con_id)
+			goto remove;
+		else if (!con_id || !ce->con_id)
+			continue;
+		else if (!strcmp(con_id, ce->con_id))
+			goto remove;
+	}
+
+	spin_unlock_irq(&psd->lock);
+	return;
+
+ remove:
+	list_del(&ce->node);
+	spin_unlock_irq(&psd->lock);
+
+	__pm_clk_remove(ce);
+}
+
+/**
+ * pm_clk_init - Initialize a device's list of power management clocks.
+ * @dev: Device to initialize the list of PM clocks for.
+ *
+ * Initialize the lock and clock_list members of the device's pm_subsys_data
+ * object.
+ */
+void pm_clk_init(struct device *dev)
+{
+	struct pm_subsys_data *psd = dev_to_psd(dev);
+	if (psd)
+		INIT_LIST_HEAD(&psd->clock_list);
+}
+
+/**
+ * pm_clk_create - Create and initialize a device's list of PM clocks.
+ * @dev: Device to create and initialize the list of PM clocks for.
+ *
+ * Allocate a struct pm_subsys_data object, initialize its lock and clock_list
+ * members and make the @dev's power.subsys_data field point to it.
+ */
+int pm_clk_create(struct device *dev)
+{
+	return dev_pm_get_subsys_data(dev);
+}
+
+/**
+ * pm_clk_destroy - Destroy a device's list of power management clocks.
+ * @dev: Device to destroy the list of PM clocks for.
+ *
+ * Clear the @dev's power.subsys_data field, remove the list of clock entries
+ * from the struct pm_subsys_data object pointed to by it before and free
+ * that object.
+ */
+void pm_clk_destroy(struct device *dev)
+{
+	struct pm_subsys_data *psd = dev_to_psd(dev);
+	struct pm_clock_entry *ce, *c;
+	struct list_head list;
+
+	if (!psd)
+		return;
+
+	INIT_LIST_HEAD(&list);
+
+	spin_lock_irq(&psd->lock);
+
+	list_for_each_entry_safe_reverse(ce, c, &psd->clock_list, node)
+		list_move(&ce->node, &list);
+
+	spin_unlock_irq(&psd->lock);
+
+	dev_pm_put_subsys_data(dev);
+
+	list_for_each_entry_safe_reverse(ce, c, &list, node) {
+		list_del(&ce->node);
+		__pm_clk_remove(ce);
+	}
+}
+
+#endif /* CONFIG_PM */
+
+#ifdef CONFIG_PM_RUNTIME
+
+/**
+ * pm_clk_suspend - Disable clocks in a device's PM clock list.
+ * @dev: Device to disable the clocks for.
+ */
+int pm_clk_suspend(struct device *dev)
+{
+	struct pm_subsys_data *psd = dev_to_psd(dev);
+	struct pm_clock_entry *ce;
+	unsigned long flags;
+
+	dev_dbg(dev, "%s()\n", __func__);
+
+	if (!psd)
+		return 0;
+
+	spin_lock_irqsave(&psd->lock, flags);
+
+	list_for_each_entry_reverse(ce, &psd->clock_list, node) {
+		if (ce->status < PCE_STATUS_ERROR) {
+			if (ce->status == PCE_STATUS_ENABLED)
+				clk_disable(ce->clk);
+			ce->status = PCE_STATUS_ACQUIRED;
+		}
+	}
+
+	spin_unlock_irqrestore(&psd->lock, flags);
+
+	return 0;
+}
+
+/**
+ * pm_clk_resume - Enable clocks in a device's PM clock list.
+ * @dev: Device to enable the clocks for.
+ */
+int pm_clk_resume(struct device *dev)
+{
+	struct pm_subsys_data *psd = dev_to_psd(dev);
+	struct pm_clock_entry *ce;
+	unsigned long flags;
+
+	dev_dbg(dev, "%s()\n", __func__);
+
+	if (!psd)
+		return 0;
+
+	spin_lock_irqsave(&psd->lock, flags);
+
+	list_for_each_entry(ce, &psd->clock_list, node) {
+		if (ce->status < PCE_STATUS_ERROR) {
+			clk_enable(ce->clk);
+			ce->status = PCE_STATUS_ENABLED;
+		}
+	}
+
+	spin_unlock_irqrestore(&psd->lock, flags);
+
+	return 0;
+}
+
+/**
+ * pm_clk_notify - Notify routine for device addition and removal.
+ * @nb: Notifier block object this function is a member of.
+ * @action: Operation being carried out by the caller.
+ * @data: Device the routine is being run for.
+ *
+ * For this function to work, @nb must be a member of an object of type
+ * struct pm_clk_notifier_block containing all of the requisite data.
+ * Specifically, the pm_domain member of that object is copied to the device's
+ * pm_domain field and its con_ids member is used to populate the device's list
+ * of PM clocks, depending on @action.
+ *
+ * If the device's pm_domain field is already populated with a value different
+ * from the one stored in the struct pm_clk_notifier_block object, the function
+ * does nothing.
+ */
+static int pm_clk_notify(struct notifier_block *nb,
+				 unsigned long action, void *data)
+{
+	struct pm_clk_notifier_block *clknb;
+	struct device *dev = data;
+	char **con_id;
+	int error;
+
+	dev_dbg(dev, "%s() %ld\n", __func__, action);
+
+	clknb = container_of(nb, struct pm_clk_notifier_block, nb);
+
+	switch (action) {
+	case BUS_NOTIFY_ADD_DEVICE:
+		if (dev->pm_domain)
+			break;
+
+		error = pm_clk_create(dev);
+		if (error)
+			break;
+
+		dev->pm_domain = clknb->pm_domain;
+		if (clknb->con_ids[0]) {
+			for (con_id = clknb->con_ids; *con_id; con_id++)
+				pm_clk_add(dev, *con_id);
+		} else {
+			pm_clk_add(dev, NULL);
+		}
+
+		break;
+	case BUS_NOTIFY_DEL_DEVICE:
+		if (dev->pm_domain != clknb->pm_domain)
+			break;
+
+		dev->pm_domain = NULL;
+		pm_clk_destroy(dev);
+		break;
+	}
+
+	return 0;
+}
+
+#else /* !CONFIG_PM_RUNTIME */
+
+#ifdef CONFIG_PM
+
+/**
+ * pm_clk_suspend - Disable clocks in a device's PM clock list.
+ * @dev: Device to disable the clocks for.
+ */
+int pm_clk_suspend(struct device *dev)
+{
+	struct pm_subsys_data *psd = dev_to_psd(dev);
+	struct pm_clock_entry *ce;
+	unsigned long flags;
+
+	dev_dbg(dev, "%s()\n", __func__);
+
+	/* If there is no driver, the clocks are already disabled. */
+	if (!psd || !dev->driver)
+		return 0;
+
+	spin_lock_irqsave(&psd->lock, flags);
+
+	list_for_each_entry_reverse(ce, &psd->clock_list, node)
+		clk_disable(ce->clk);
+
+	spin_unlock_irqrestore(&psd->lock, flags);
+
+	return 0;
+}
+
+/**
+ * pm_clk_resume - Enable clocks in a device's PM clock list.
+ * @dev: Device to enable the clocks for.
+ */
+int pm_clk_resume(struct device *dev)
+{
+	struct pm_subsys_data *psd = dev_to_psd(dev);
+	struct pm_clock_entry *ce;
+	unsigned long flags;
+
+	dev_dbg(dev, "%s()\n", __func__);
+
+	/* If there is no driver, the clocks should remain disabled. */
+	if (!psd || !dev->driver)
+		return 0;
+
+	spin_lock_irqsave(&psd->lock, flags);
+
+	list_for_each_entry(ce, &psd->clock_list, node)
+		clk_enable(ce->clk);
+
+	spin_unlock_irqrestore(&psd->lock, flags);
+
+	return 0;
+}
+
+#endif /* CONFIG_PM */
+
+/**
+ * enable_clock - Enable a device clock.
+ * @dev: Device whose clock is to be enabled.
+ * @con_id: Connection ID of the clock.
+ */
+static void enable_clock(struct device *dev, const char *con_id)
+{
+	struct clk *clk;
+
+	clk = clk_get(dev, con_id);
+	if (!IS_ERR(clk)) {
+		clk_prepare_enable(clk);
+		clk_put(clk);
+		dev_info(dev, "Runtime PM disabled, clock forced on.\n");
+	}
+}
+
+/**
+ * disable_clock - Disable a device clock.
+ * @dev: Device whose clock is to be disabled.
+ * @con_id: Connection ID of the clock.
+ */
+static void disable_clock(struct device *dev, const char *con_id)
+{
+	struct clk *clk;
+
+	clk = clk_get(dev, con_id);
+	if (!IS_ERR(clk)) {
+		clk_disable_unprepare(clk);
+		clk_put(clk);
+		dev_info(dev, "Runtime PM disabled, clock forced off.\n");
+	}
+}
+
+/**
+ * pm_clk_notify - Notify routine for device addition and removal.
+ * @nb: Notifier block object this function is a member of.
+ * @action: Operation being carried out by the caller.
+ * @data: Device the routine is being run for.
+ *
+ * For this function to work, @nb must be a member of an object of type
+ * struct pm_clk_notifier_block containing all of the requisite data.
+ * Specifically, the con_ids member of that object is used to enable or disable
+ * the device's clocks, depending on @action.
+ */
+static int pm_clk_notify(struct notifier_block *nb,
+				 unsigned long action, void *data)
+{
+	struct pm_clk_notifier_block *clknb;
+	struct device *dev = data;
+	char **con_id;
+
+	dev_dbg(dev, "%s() %ld\n", __func__, action);
+
+	clknb = container_of(nb, struct pm_clk_notifier_block, nb);
+
+	switch (action) {
+	case BUS_NOTIFY_BIND_DRIVER:
+		if (clknb->con_ids[0]) {
+			for (con_id = clknb->con_ids; *con_id; con_id++)
+				enable_clock(dev, *con_id);
+		} else {
+			enable_clock(dev, NULL);
+		}
+		break;
+	case BUS_NOTIFY_UNBOUND_DRIVER:
+		if (clknb->con_ids[0]) {
+			for (con_id = clknb->con_ids; *con_id; con_id++)
+				disable_clock(dev, *con_id);
+		} else {
+			disable_clock(dev, NULL);
+		}
+		break;
+	}
+
+	return 0;
+}
+
+#endif /* !CONFIG_PM_RUNTIME */
+
+/**
+ * pm_clk_add_notifier - Add bus type notifier for power management clocks.
+ * @bus: Bus type to add the notifier to.
+ * @clknb: Notifier to be added to the given bus type.
+ *
+ * The nb member of @clknb is not expected to be initialized and its
+ * notifier_call member will be replaced with pm_clk_notify().  However,
+ * the remaining members of @clknb should be populated prior to calling this
+ * routine.
+ */
+void pm_clk_add_notifier(struct bus_type *bus,
+				 struct pm_clk_notifier_block *clknb)
+{
+	if (!bus || !clknb)
+		return;
+
+	clknb->nb.notifier_call = pm_clk_notify;
+	bus_register_notifier(bus, &clknb->nb);
+}

drivers/base/power/common.c

@@ -0,0 +1,85 @@
+/*
+ * drivers/base/power/common.c - Common device power management code.
+ *
+ * Copyright (C) 2011 Rafael J. Wysocki <rjw@sisk.pl>, Renesas Electronics Corp.
+ *
+ * This file is released under the GPLv2.
+ */
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/device.h>
+#include <linux/export.h>
+#include <linux/slab.h>
+#include <linux/pm_clock.h>
+
+/**
+ * dev_pm_get_subsys_data - Create or refcount power.subsys_data for device.
+ * @dev: Device to handle.
+ *
+ * If power.subsys_data is NULL, point it to a new object, otherwise increment
+ * its reference counter.  Return 1 if a new object has been created, otherwise
+ * return 0 or error code.
+ */
+int dev_pm_get_subsys_data(struct device *dev)
+{
+	struct pm_subsys_data *psd;
+
+	psd = kzalloc(sizeof(*psd), GFP_KERNEL);
+	if (!psd)
+		return -ENOMEM;
+
+	spin_lock_irq(&dev->power.lock);
+
+	if (dev->power.subsys_data) {
+		dev->power.subsys_data->refcount++;
+	} else {
+		spin_lock_init(&psd->lock);
+		psd->refcount = 1;
+		dev->power.subsys_data = psd;
+		pm_clk_init(dev);
+		psd = NULL;
+	}
+
+	spin_unlock_irq(&dev->power.lock);
+
+	/* kfree() verifies that its argument is nonzero. */
+	kfree(psd);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(dev_pm_get_subsys_data);
+
+/**
+ * dev_pm_put_subsys_data - Drop reference to power.subsys_data.
+ * @dev: Device to handle.
+ *
+ * If the reference counter of power.subsys_data is zero after dropping the
+ * reference, power.subsys_data is removed.  Return 1 if that happens or 0
+ * otherwise.
+ */
+int dev_pm_put_subsys_data(struct device *dev)
+{
+	struct pm_subsys_data *psd;
+	int ret = 1;
+
+	spin_lock_irq(&dev->power.lock);
+
+	psd = dev_to_psd(dev);
+	if (!psd)
+		goto out;
+
+	if (--psd->refcount == 0) {
+		dev->power.subsys_data = NULL;
+	} else {
+		psd = NULL;
+		ret = 0;
+	}
+
+ out:
+	spin_unlock_irq(&dev->power.lock);
+	kfree(psd);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(dev_pm_put_subsys_data);

drivers/base/power/dark_resume.c

@@ -0,0 +1,188 @@
+/* Copyright (C) 2013 Google, Inc.
+ *
+ * Author:
+ *      Derek Basehore <dbasehore@chromium.org>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * A dark resume is meant to be a reduced functionality state to resume the
+ * system to. It is not meant for user interaction, but to determine whether to
+ * shut down/hibernate or suspend again. This is done for power saving measures.
+ * To make the experience as seamless as possible drivers may want to alter
+ * their resume path to do something different in this case (prevent flashing
+ * screens and blinking usb ports).
+ *
+ * To make this system agnostic, much of the configuration is done in user
+ * space.
+ */
+
+#include <linux/device.h>
+#include <linux/export.h>
+#include <linux/pm_dark_resume.h>
+#include <linux/mutex.h>
+#include <linux/types.h>
+
+#include "power.h"
+
+LIST_HEAD(source_list);
+static DEFINE_MUTEX(source_list_lock);
+static bool dark_resume_state;
+static struct pm_dark_resume_ops *dark_resume_ops;
+
+/**
+ * dev_dark_resume_set_source - Set whether a device is a dark resume source.
+ * @dev: the struct that contains a pointer to the device we are either adding
+ * or removing as a dark resume source
+ * @is_source: Set the device to a source if true and remove as source if false
+ */
+int dev_dark_resume_set_source(struct device *dev, bool is_source)
+{
+	/*
+	 * This can happen if 'enabled' is written to the dark_resume_source
+	 * attribute and the driver did not setup a dev_dark_resume struct.
+	 */
+	if (!dev->power.dark_resume) {
+		dev_dbg(dev, "Tried to set device as dark resume source, but "
+			     "there is no driver support.");
+		return -EINVAL;
+	}
+
+	mutex_lock(&source_list_lock);
+	if (is_source == dev->power.dark_resume->is_source) {
+		mutex_unlock(&source_list_lock);
+		return -EINVAL;
+	}
+
+	if (is_source)
+		list_add(&dev->power.dark_resume->list_node, &source_list);
+	else
+		list_del(&dev->power.dark_resume->list_node);
+
+	dev->power.dark_resume->is_source = is_source;
+	mutex_unlock(&source_list_lock);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(dev_dark_resume_set_source);
+
+/**
+ * dev_dark_resume_set_active - This sets up the device to check the dark resume
+ * state during resume.
+ * @dev: device to set querying of the dark resume state to active or inactive
+ * @is_active: true for the device to query the dark resume state, false to not
+ * query the dark resume state.
+ *
+ * Part of dark resume is that devices may resume differently (such as the
+ * backlight coming on). This enables a driver to do something different in the
+ * resume path by calling dev_dark_resume_active.
+ */
+void dev_dark_resume_set_active(struct device *dev, bool is_active)
+{
+	dev->power.use_dark_resume = is_active;
+}
+EXPORT_SYMBOL_GPL(dev_dark_resume_set_active);
+
+/**
+ * dev_dark_resume_init - Initialize the dev_dark_resume struct.
+ * @dev: The device struct that the dev_dark_resume struct will be associated
+ * with.
+ * @dark_resume: The dev_dark_resume struct to initialize.
+ * @irq: The platform callback will check (if supported) if this irq is the wake
+ * source. Note: probably want a hardware irq instead of virtual irq.
+ * @caused_resume: The function pointer that is called by the platform callback
+ * (if supported) before devices are resumed to see if dev caused the resume of
+ * the system.
+ *
+ * Devices that query dark resume, but cannot be a source should call this
+ * function when initialized with dark_resume and caused_resume as NULL.
+ */
+int dev_dark_resume_init(struct device *dev,
+			 struct dev_dark_resume *dark_resume,
+			 int irq,
+			 bool (*caused_resume)(struct device *dev))
+{
+	/* Must be called after device_add since sysfs attributes are added */
+	if (!device_is_registered(dev))
+		return -EINVAL;
+
+	dev->power.dark_resume = dark_resume;
+	dev_dark_resume_set_active(dev, false);
+	/* Happens for devices that cannot be a dark resume source. */
+	if (!dark_resume)
+		return dark_resume_sysfs_add(dev);
+
+	dark_resume->dev = dev;
+	dark_resume->is_source = false;
+	dark_resume->irq = irq;
+	dark_resume->caused_resume = caused_resume;
+	INIT_LIST_HEAD(&dark_resume->list_node);
+	/* Don't really need to clean up anything if this fails */
+	return dark_resume_sysfs_add(dev);
+}
+EXPORT_SYMBOL_GPL(dev_dark_resume_init);
+
+/**
+ * dev_dark_resume_remove - Remove all of the associations of the device to dark
+ * resume.
+ * @dev: device struct to remove associations to dark resume from.
+ *
+ * Makes sure that the device is no longer active for dark resume and is not a
+ * source.
+ */
+void dev_dark_resume_remove(struct device *dev)
+{
+	dev_dark_resume_set_active(dev, false);
+	dark_resume_sysfs_remove(dev);
+	if (!dev->power.dark_resume)
+		return;
+
+	dev_dark_resume_set_source(dev, false);
+	dev->power.dark_resume->caused_resume = NULL;
+	dev->power.dark_resume->irq = 0;
+	dev->power.dark_resume->dev = NULL;
+	dev->power.dark_resume = NULL;
+}
+EXPORT_SYMBOL_GPL(dev_dark_resume_remove);
+
+/**
+ * pm_dark_resume_check - Call into the platform specific check function if it
+ * exists to check if one of the dark resume sources woke the system.
+ */
+bool pm_dark_resume_check(void)
+{
+	if (!dark_resume_ops || !dark_resume_ops->check) {
+		dark_resume_state = false;
+		return dark_resume_state;
+	}
+
+	mutex_lock(&source_list_lock);
+	dark_resume_state = dark_resume_ops->check(&source_list);
+	mutex_unlock(&source_list_lock);
+	return dark_resume_state;
+}
+EXPORT_SYMBOL_GPL(pm_dark_resume_check);
+
+/**
+ * pm_dark_resume_active - Returns the state of dark resume.
+ */
+bool pm_dark_resume_active(void)
+{
+	return dark_resume_state;
+}
+EXPORT_SYMBOL_GPL(pm_dark_resume_active);
+
+/**
+ * pm_dark_resume_register_ops - Registers the callback function to check
+ * whether the system was resumed by something in the source_list.
+ * @ops: Container for the callback function
+ */
+void pm_dark_resume_register_ops(struct pm_dark_resume_ops *ops)
+{
+	dark_resume_ops = ops;
+}

drivers/base/power/domain_governor.c

@@ -0,0 +1,254 @@
+/*
+ * drivers/base/power/domain_governor.c - Governors for device PM domains.
+ *
+ * Copyright (C) 2011 Rafael J. Wysocki <rjw@sisk.pl>, Renesas Electronics Corp.
+ *
+ * This file is released under the GPLv2.
+ */
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/pm_domain.h>
+#include <linux/pm_qos.h>
+#include <linux/hrtimer.h>
+
+#ifdef CONFIG_PM_RUNTIME
+
+static int dev_update_qos_constraint(struct device *dev, void *data)
+{
+	s64 *constraint_ns_p = data;
+	s32 constraint_ns = -1;
+
+	if (dev->power.subsys_data && dev->power.subsys_data->domain_data)
+		constraint_ns = dev_gpd_data(dev)->td.effective_constraint_ns;
+
+	if (constraint_ns < 0) {
+		constraint_ns = dev_pm_qos_read_value(dev);
+		constraint_ns *= NSEC_PER_USEC;
+	}
+	if (constraint_ns == 0)
+		return 0;
+
+	/*
+	 * constraint_ns cannot be negative here, because the device has been
+	 * suspended.
+	 */
+	if (constraint_ns < *constraint_ns_p || *constraint_ns_p == 0)
+		*constraint_ns_p = constraint_ns;
+
+	return 0;
+}
+
+/**
+ * default_stop_ok - Default PM domain governor routine for stopping devices.
+ * @dev: Device to check.
+ */
+bool default_stop_ok(struct device *dev)
+{
+	struct gpd_timing_data *td = &dev_gpd_data(dev)->td;
+	unsigned long flags;
+	s64 constraint_ns;
+
+	dev_dbg(dev, "%s()\n", __func__);
+
+	spin_lock_irqsave(&dev->power.lock, flags);
+
+	if (!td->constraint_changed) {
+		bool ret = td->cached_stop_ok;
+
+		spin_unlock_irqrestore(&dev->power.lock, flags);
+		return ret;
+	}
+	td->constraint_changed = false;
+	td->cached_stop_ok = false;
+	td->effective_constraint_ns = -1;
+	constraint_ns = __dev_pm_qos_read_value(dev);
+
+	spin_unlock_irqrestore(&dev->power.lock, flags);
+
+	if (constraint_ns < 0)
+		return false;
+
+	constraint_ns *= NSEC_PER_USEC;
+	/*
+	 * We can walk the children without any additional locking, because
+	 * they all have been suspended at this point and their
+	 * effective_constraint_ns fields won't be modified in parallel with us.
+	 */
+	if (!dev->power.ignore_children)
+		device_for_each_child(dev, &constraint_ns,
+				      dev_update_qos_constraint);
+
+	if (constraint_ns > 0) {
+		constraint_ns -= td->start_latency_ns;
+		if (constraint_ns == 0)
+			return false;
+	}
+	td->effective_constraint_ns = constraint_ns;
+	td->cached_stop_ok = constraint_ns > td->stop_latency_ns ||
+				constraint_ns == 0;
+	/*
+	 * The children have been suspended already, so we don't need to take
+	 * their stop latencies into account here.
+	 */
+	return td->cached_stop_ok;
+}
+
+/**
+ * default_power_down_ok - Default generic PM domain power off governor routine.
+ * @pd: PM domain to check.
+ *
+ * This routine must be executed under the PM domain's lock.
+ */
+static bool default_power_down_ok(struct dev_pm_domain *pd)
+{
+	struct generic_pm_domain *genpd = pd_to_genpd(pd);
+	struct gpd_link *link;
+	struct pm_domain_data *pdd;
+	s64 min_off_time_ns;
+	s64 off_on_time_ns;
+
+	if (genpd->max_off_time_changed) {
+		struct gpd_link *link;
+
+		/*
+		 * We have to invalidate the cached results for the masters, so
+		 * use the observation that default_power_down_ok() is not
+		 * going to be called for any master until this instance
+		 * returns.
+		 */
+		list_for_each_entry(link, &genpd->slave_links, slave_node)
+			link->master->max_off_time_changed = true;
+
+		genpd->max_off_time_changed = false;
+		genpd->cached_power_down_ok = false;
+		genpd->max_off_time_ns = -1;
+	} else {
+		return genpd->cached_power_down_ok;
+	}
+
+	off_on_time_ns = genpd->power_off_latency_ns +
+				genpd->power_on_latency_ns;
+	/*
+	 * It doesn't make sense to remove power from the domain if saving
+	 * the state of all devices in it and the power off/power on operations
+	 * take too much time.
+	 *
+	 * All devices in this domain have been stopped already at this point.
+	 */
+	list_for_each_entry(pdd, &genpd->dev_list, list_node) {
+		if (pdd->dev->driver)
+			off_on_time_ns +=
+				to_gpd_data(pdd)->td.save_state_latency_ns;
+	}
+
+	min_off_time_ns = -1;
+	/*
+	 * Check if subdomains can be off for enough time.
+	 *
+	 * All subdomains have been powered off already at this point.
+	 */
+	list_for_each_entry(link, &genpd->master_links, master_node) {
+		struct generic_pm_domain *sd = link->slave;
+		s64 sd_max_off_ns = sd->max_off_time_ns;
+
+		if (sd_max_off_ns < 0)
+			continue;
+
+		/*
+		 * Check if the subdomain is allowed to be off long enough for
+		 * the current domain to turn off and on (that's how much time
+		 * it will have to wait worst case).
+		 */
+		if (sd_max_off_ns <= off_on_time_ns)
+			return false;
+
+		if (min_off_time_ns > sd_max_off_ns || min_off_time_ns < 0)
+			min_off_time_ns = sd_max_off_ns;
+	}
+
+	/*
+	 * Check if the devices in the domain can be off enough time.
+	 */
+	list_for_each_entry(pdd, &genpd->dev_list, list_node) {
+		struct gpd_timing_data *td;
+		s64 constraint_ns;
+
+		if (!pdd->dev->driver)
+			continue;
+
+		/*
+		 * Check if the device is allowed to be off long enough for the
+		 * domain to turn off and on (that's how much time it will
+		 * have to wait worst case).
+		 */
+		td = &to_gpd_data(pdd)->td;
+		constraint_ns = td->effective_constraint_ns;
+		/* default_stop_ok() need not be called before us. */
+		if (constraint_ns < 0) {
+			constraint_ns = dev_pm_qos_read_value(pdd->dev);
+			constraint_ns *= NSEC_PER_USEC;
+		}
+		if (constraint_ns == 0)
+			continue;
+
+		/*
+		 * constraint_ns cannot be negative here, because the device has
+		 * been suspended.
+		 */
+		constraint_ns -= td->restore_state_latency_ns;
+		if (constraint_ns <= off_on_time_ns)
+			return false;
+
+		if (min_off_time_ns > constraint_ns || min_off_time_ns < 0)
+			min_off_time_ns = constraint_ns;
+	}
+
+	genpd->cached_power_down_ok = true;
+
+	/*
+	 * If the computed minimum device off time is negative, there are no
+	 * latency constraints, so the domain can spend arbitrary time in the
+	 * "off" state.
+	 */
+	if (min_off_time_ns < 0)
+		return true;
+
+	/*
+	 * The difference between the computed minimum subdomain or device off
+	 * time and the time needed to turn the domain on is the maximum
+	 * theoretical time this domain can spend in the "off" state.
+	 */
+	genpd->max_off_time_ns = min_off_time_ns - genpd->power_on_latency_ns;
+	return true;
+}
+
+static bool always_on_power_down_ok(struct dev_pm_domain *domain)
+{
+	return false;
+}
+
+#else /* !CONFIG_PM_RUNTIME */
+
+bool default_stop_ok(struct device *dev)
+{
+	return false;
+}
+
+#define default_power_down_ok	NULL
+#define always_on_power_down_ok	NULL
+
+#endif /* !CONFIG_PM_RUNTIME */
+
+struct dev_power_governor simple_qos_governor = {
+	.stop_ok = default_stop_ok,
+	.power_down_ok = default_power_down_ok,
+};
+
+/**
+ * pm_genpd_gov_always_on - A governor implementing an always-on policy
+ */
+struct dev_power_governor pm_domain_always_on_gov = {
+	.power_down_ok = always_on_power_down_ok,
+	.stop_ok = default_stop_ok,
+};

drivers/base/power/generic_ops.c

@@ -0,0 +1,329 @@
+/*
+ * drivers/base/power/generic_ops.c - Generic PM callbacks for subsystems
+ *
+ * Copyright (c) 2010 Rafael J. Wysocki <rjw@sisk.pl>, Novell Inc.
+ *
+ * This file is released under the GPLv2.
+ */
+
+#include <linux/pm.h>
+#include <linux/pm_runtime.h>
+#include <linux/export.h>
+
+#ifdef CONFIG_PM_RUNTIME
+/**
+ * pm_generic_runtime_idle - Generic runtime idle callback for subsystems.
+ * @dev: Device to handle.
+ *
+ * If PM operations are defined for the @dev's driver and they include
+ * ->runtime_idle(), execute it and return its error code, if nonzero.
+ * Otherwise, execute pm_runtime_suspend() for the device and return 0.
+ */
+int pm_generic_runtime_idle(struct device *dev)
+{
+	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
+
+	if (pm && pm->runtime_idle) {
+		int ret = pm->runtime_idle(dev);
+		if (ret)
+			return ret;
+	}
+
+	pm_runtime_suspend(dev);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(pm_generic_runtime_idle);
+
+/**
+ * pm_generic_runtime_suspend - Generic runtime suspend callback for subsystems.
+ * @dev: Device to suspend.
+ *
+ * If PM operations are defined for the @dev's driver and they include
+ * ->runtime_suspend(), execute it and return its error code.  Otherwise,
+ * return 0.
+ */
+int pm_generic_runtime_suspend(struct device *dev)
+{
+	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
+	int ret;
+
+	ret = pm && pm->runtime_suspend ? pm->runtime_suspend(dev) : 0;
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(pm_generic_runtime_suspend);
+
+/**
+ * pm_generic_runtime_resume - Generic runtime resume callback for subsystems.
+ * @dev: Device to resume.
+ *
+ * If PM operations are defined for the @dev's driver and they include
+ * ->runtime_resume(), execute it and return its error code.  Otherwise,
+ * return 0.
+ */
+int pm_generic_runtime_resume(struct device *dev)
+{
+	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
+	int ret;
+
+	ret = pm && pm->runtime_resume ? pm->runtime_resume(dev) : 0;
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(pm_generic_runtime_resume);
+#endif /* CONFIG_PM_RUNTIME */
+
+#ifdef CONFIG_PM_SLEEP
+/**
+ * pm_generic_prepare - Generic routine preparing a device for power transition.
+ * @dev: Device to prepare.
+ *
+ * Prepare a device for a system-wide power transition.
+ */
+int pm_generic_prepare(struct device *dev)
+{
+	struct device_driver *drv = dev->driver;
+	int ret = 0;
+
+	if (drv && drv->pm && drv->pm->prepare)
+		ret = drv->pm->prepare(dev);
+
+	return ret;
+}
+
+/**
+ * pm_generic_suspend_noirq - Generic suspend_noirq callback for subsystems.
+ * @dev: Device to suspend.
+ */
+int pm_generic_suspend_noirq(struct device *dev)
+{
+	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
+
+	return pm && pm->suspend_noirq ? pm->suspend_noirq(dev) : 0;
+}
+EXPORT_SYMBOL_GPL(pm_generic_suspend_noirq);
+
+/**
+ * pm_generic_suspend_late - Generic suspend_late callback for subsystems.
+ * @dev: Device to suspend.
+ */
+int pm_generic_suspend_late(struct device *dev)
+{
+	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
+
+	return pm && pm->suspend_late ? pm->suspend_late(dev) : 0;
+}
+EXPORT_SYMBOL_GPL(pm_generic_suspend_late);
+
+/**
+ * pm_generic_suspend - Generic suspend callback for subsystems.
+ * @dev: Device to suspend.
+ */
+int pm_generic_suspend(struct device *dev)
+{
+	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
+
+	return pm && pm->suspend ? pm->suspend(dev) : 0;
+}
+EXPORT_SYMBOL_GPL(pm_generic_suspend);
+
+/**
+ * pm_generic_freeze_noirq - Generic freeze_noirq callback for subsystems.
+ * @dev: Device to freeze.
+ */
+int pm_generic_freeze_noirq(struct device *dev)
+{
+	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
+
+	return pm && pm->freeze_noirq ? pm->freeze_noirq(dev) : 0;
+}
+EXPORT_SYMBOL_GPL(pm_generic_freeze_noirq);
+
+/**
+ * pm_generic_freeze_late - Generic freeze_late callback for subsystems.
+ * @dev: Device to freeze.
+ */
+int pm_generic_freeze_late(struct device *dev)
+{
+	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
+
+	return pm && pm->freeze_late ? pm->freeze_late(dev) : 0;
+}
+EXPORT_SYMBOL_GPL(pm_generic_freeze_late);
+
+/**
+ * pm_generic_freeze - Generic freeze callback for subsystems.
+ * @dev: Device to freeze.
+ */
+int pm_generic_freeze(struct device *dev)
+{
+	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
+
+	return pm && pm->freeze ? pm->freeze(dev) : 0;
+}
+EXPORT_SYMBOL_GPL(pm_generic_freeze);
+
+/**
+ * pm_generic_poweroff_noirq - Generic poweroff_noirq callback for subsystems.
+ * @dev: Device to handle.
+ */
+int pm_generic_poweroff_noirq(struct device *dev)
+{
+	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
+
+	return pm && pm->poweroff_noirq ? pm->poweroff_noirq(dev) : 0;
+}
+EXPORT_SYMBOL_GPL(pm_generic_poweroff_noirq);
+
+/**
+ * pm_generic_poweroff_late - Generic poweroff_late callback for subsystems.
+ * @dev: Device to handle.
+ */
+int pm_generic_poweroff_late(struct device *dev)
+{
+	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
+
+	return pm && pm->poweroff_late ? pm->poweroff_late(dev) : 0;
+}
+EXPORT_SYMBOL_GPL(pm_generic_poweroff_late);
+
+/**
+ * pm_generic_poweroff - Generic poweroff callback for subsystems.
+ * @dev: Device to handle.
+ */
+int pm_generic_poweroff(struct device *dev)
+{
+	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
+
+	return pm && pm->poweroff ? pm->poweroff(dev) : 0;
+}
+EXPORT_SYMBOL_GPL(pm_generic_poweroff);
+
+/**
+ * pm_generic_thaw_noirq - Generic thaw_noirq callback for subsystems.
+ * @dev: Device to thaw.
+ */
+int pm_generic_thaw_noirq(struct device *dev)
+{
+	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
+
+	return pm && pm->thaw_noirq ? pm->thaw_noirq(dev) : 0;
+}
+EXPORT_SYMBOL_GPL(pm_generic_thaw_noirq);
+
+/**
+ * pm_generic_thaw_early - Generic thaw_early callback for subsystems.
+ * @dev: Device to thaw.
+ */
+int pm_generic_thaw_early(struct device *dev)
+{
+	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
+
+	return pm && pm->thaw_early ? pm->thaw_early(dev) : 0;
+}
+EXPORT_SYMBOL_GPL(pm_generic_thaw_early);
+
+/**
+ * pm_generic_thaw - Generic thaw callback for subsystems.
+ * @dev: Device to thaw.
+ */
+int pm_generic_thaw(struct device *dev)
+{
+	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
+
+	return pm && pm->thaw ? pm->thaw(dev) : 0;
+}
+EXPORT_SYMBOL_GPL(pm_generic_thaw);
+
+/**
+ * pm_generic_resume_noirq - Generic resume_noirq callback for subsystems.
+ * @dev: Device to resume.
+ */
+int pm_generic_resume_noirq(struct device *dev)
+{
+	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
+
+	return pm && pm->resume_noirq ? pm->resume_noirq(dev) : 0;
+}
+EXPORT_SYMBOL_GPL(pm_generic_resume_noirq);
+
+/**
+ * pm_generic_resume_early - Generic resume_early callback for subsystems.
+ * @dev: Device to resume.
+ */
+int pm_generic_resume_early(struct device *dev)
+{
+	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
+
+	return pm && pm->resume_early ? pm->resume_early(dev) : 0;
+}
+EXPORT_SYMBOL_GPL(pm_generic_resume_early);
+
+/**
+ * pm_generic_resume - Generic resume callback for subsystems.
+ * @dev: Device to resume.
+ */
+int pm_generic_resume(struct device *dev)
+{
+	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
+
+	return pm && pm->resume ? pm->resume(dev) : 0;
+}
+EXPORT_SYMBOL_GPL(pm_generic_resume);
+
+/**
+ * pm_generic_restore_noirq - Generic restore_noirq callback for subsystems.
+ * @dev: Device to restore.
+ */
+int pm_generic_restore_noirq(struct device *dev)
+{
+	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
+
+	return pm && pm->restore_noirq ? pm->restore_noirq(dev) : 0;
+}
+EXPORT_SYMBOL_GPL(pm_generic_restore_noirq);
+
+/**
+ * pm_generic_restore_early - Generic restore_early callback for subsystems.
+ * @dev: Device to resume.
+ */
+int pm_generic_restore_early(struct device *dev)
+{
+	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
+
+	return pm && pm->restore_early ? pm->restore_early(dev) : 0;
+}
+EXPORT_SYMBOL_GPL(pm_generic_restore_early);
+
+/**
+ * pm_generic_restore - Generic restore callback for subsystems.
+ * @dev: Device to restore.
+ */
+int pm_generic_restore(struct device *dev)
+{
+	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
+
+	return pm && pm->restore ? pm->restore(dev) : 0;
+}
+EXPORT_SYMBOL_GPL(pm_generic_restore);
+
+/**
+ * pm_generic_complete - Generic routine competing a device power transition.
+ * @dev: Device to handle.
+ *
+ * Complete a device power transition during a system-wide power transition.
+ */
+void pm_generic_complete(struct device *dev)
+{
+	struct device_driver *drv = dev->driver;
+
+	if (drv && drv->pm && drv->pm->complete)
+		drv->pm->complete(dev);
+
+	/*
+	 * Let runtime PM try to suspend devices that haven't been in use before
+	 * going into the system-wide sleep state we're resuming from.
+	 */
+	pm_request_idle(dev);
+}
+#endif /* CONFIG_PM_SLEEP */

drivers/base/power/opp.c

@@ -0,0 +1,745 @@
+/*
+ * Generic OPP Interface
+ *
+ * Copyright (C) 2009-2010 Texas Instruments Incorporated.
+ *	Nishanth Menon
+ *	Romit Dasgupta
+ *	Kevin Hilman
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/slab.h>
+#include <linux/cpufreq.h>
+#include <linux/device.h>
+#include <linux/list.h>
+#include <linux/rculist.h>
+#include <linux/rcupdate.h>
+#include <linux/opp.h>
+#include <linux/of.h>
+#include <linux/export.h>
+
+/*
+ * Internal data structure organization with the OPP layer library is as
+ * follows:
+ * dev_opp_list (root)
+ *	|- device 1 (represents voltage domain 1)
+ *	|	|- opp 1 (availability, freq, voltage)
+ *	|	|- opp 2 ..
+ *	...	...
+ *	|	`- opp n ..
+ *	|- device 2 (represents the next voltage domain)
+ *	...
+ *	`- device m (represents mth voltage domain)
+ * device 1, 2.. are represented by dev_opp structure while each opp
+ * is represented by the opp structure.
+ */
+
+/**
+ * struct opp - Generic OPP description structure
+ * @node:	opp list node. The nodes are maintained throughout the lifetime
+ *		of boot. It is expected only an optimal set of OPPs are
+ *		added to the library by the SoC framework.
+ *		RCU usage: opp list is traversed with RCU locks. node
+ *		modification is possible realtime, hence the modifications
+ *		are protected by the dev_opp_list_lock for integrity.
+ *		IMPORTANT: the opp nodes should be maintained in increasing
+ *		order.
+ * @available:	true/false - marks if this OPP as available or not
+ * @rate:	Frequency in hertz
+ * @u_volt:	Nominal voltage in microvolts corresponding to this OPP
+ * @dev_opp:	points back to the device_opp struct this opp belongs to
+ * @head:	RCU callback head used for deferred freeing
+ *
+ * This structure stores the OPP information for a given device.
+ */
+struct opp {
+	struct list_head node;
+
+	bool available;
+	unsigned long rate;
+	unsigned long u_volt;
+
+	struct device_opp *dev_opp;
+	struct rcu_head head;
+};
+
+/**
+ * struct device_opp - Device opp structure
+ * @node:	list node - contains the devices with OPPs that
+ *		have been registered. Nodes once added are not modified in this
+ *		list.
+ *		RCU usage: nodes are not modified in the list of device_opp,
+ *		however addition is possible and is secured by dev_opp_list_lock
+ * @dev:	device pointer
+ * @head:	notifier head to notify the OPP availability changes.
+ * @opp_list:	list of opps
+ *
+ * This is an internal data structure maintaining the link to opps attached to
+ * a device. This structure is not meant to be shared to users as it is
+ * meant for book keeping and private to OPP library
+ */
+struct device_opp {
+	struct list_head node;
+
+	struct device *dev;
+	struct srcu_notifier_head head;
+	struct list_head opp_list;
+};
+
+/*
+ * The root of the list of all devices. All device_opp structures branch off
+ * from here, with each device_opp containing the list of opp it supports in
+ * various states of availability.
+ */
+static LIST_HEAD(dev_opp_list);
+/* Lock to allow exclusive modification to the device and opp lists */
+static DEFINE_MUTEX(dev_opp_list_lock);
+
+/**
+ * find_device_opp() - find device_opp struct using device pointer
+ * @dev:	device pointer used to lookup device OPPs
+ *
+ * Search list of device OPPs for one containing matching device. Does a RCU
+ * reader operation to grab the pointer needed.
+ *
+ * Returns pointer to 'struct device_opp' if found, otherwise -ENODEV or
+ * -EINVAL based on type of error.
+ *
+ * Locking: This function must be called under rcu_read_lock(). device_opp
+ * is a RCU protected pointer. This means that device_opp is valid as long
+ * as we are under RCU lock.
+ */
+static struct device_opp *find_device_opp(struct device *dev)
+{
+	struct device_opp *tmp_dev_opp, *dev_opp = ERR_PTR(-ENODEV);
+
+	if (unlikely(IS_ERR_OR_NULL(dev))) {
+		pr_err("%s: Invalid parameters\n", __func__);
+		return ERR_PTR(-EINVAL);
+	}
+
+	list_for_each_entry_rcu(tmp_dev_opp, &dev_opp_list, node) {
+		if (tmp_dev_opp->dev == dev) {
+			dev_opp = tmp_dev_opp;
+			break;
+		}
+	}
+
+	return dev_opp;
+}
+
+/**
+ * opp_get_voltage() - Gets the voltage corresponding to an available opp
+ * @opp:	opp for which voltage has to be returned for
+ *
+ * Return voltage in micro volt corresponding to the opp, else
+ * return 0
+ *
+ * Locking: This function must be called under rcu_read_lock(). opp is a rcu
+ * protected pointer. This means that opp which could have been fetched by
+ * opp_find_freq_{exact,ceil,floor} functions is valid as long as we are
+ * under RCU lock. The pointer returned by the opp_find_freq family must be
+ * used in the same section as the usage of this function with the pointer
+ * prior to unlocking with rcu_read_unlock() to maintain the integrity of the
+ * pointer.
+ */
+unsigned long opp_get_voltage(struct opp *opp)
+{
+	struct opp *tmp_opp;
+	unsigned long v = 0;
+
+	tmp_opp = rcu_dereference(opp);
+	if (unlikely(IS_ERR_OR_NULL(tmp_opp)) || !tmp_opp->available)
+		pr_err("%s: Invalid parameters\n", __func__);
+	else
+		v = tmp_opp->u_volt;
+
+	return v;
+}
+EXPORT_SYMBOL_GPL(opp_get_voltage);
+
+/**
+ * opp_get_freq() - Gets the frequency corresponding to an available opp
+ * @opp:	opp for which frequency has to be returned for
+ *
+ * Return frequency in hertz corresponding to the opp, else
+ * return 0
+ *
+ * Locking: This function must be called under rcu_read_lock(). opp is a rcu
+ * protected pointer. This means that opp which could have been fetched by
+ * opp_find_freq_{exact,ceil,floor} functions is valid as long as we are
+ * under RCU lock. The pointer returned by the opp_find_freq family must be
+ * used in the same section as the usage of this function with the pointer
+ * prior to unlocking with rcu_read_unlock() to maintain the integrity of the
+ * pointer.
+ */
+unsigned long opp_get_freq(struct opp *opp)
+{
+	struct opp *tmp_opp;
+	unsigned long f = 0;
+
+	tmp_opp = rcu_dereference(opp);
+	if (unlikely(IS_ERR_OR_NULL(tmp_opp)) || !tmp_opp->available)
+		pr_err("%s: Invalid parameters\n", __func__);
+	else
+		f = tmp_opp->rate;
+
+	return f;
+}
+EXPORT_SYMBOL_GPL(opp_get_freq);
+
+/**
+ * opp_get_opp_count() - Get number of opps available in the opp list
+ * @dev:	device for which we do this operation
+ *
+ * This function returns the number of available opps if there are any,
+ * else returns 0 if none or the corresponding error value.
+ *
+ * Locking: This function must be called under rcu_read_lock(). This function
+ * internally references two RCU protected structures: device_opp and opp which
+ * are safe as long as we are under a common RCU locked section.
+ */
+int opp_get_opp_count(struct device *dev)
+{
+	struct device_opp *dev_opp;
+	struct opp *temp_opp;
+	int count = 0;
+
+	dev_opp = find_device_opp(dev);
+	if (IS_ERR(dev_opp)) {
+		int r = PTR_ERR(dev_opp);
+		dev_err(dev, "%s: device OPP not found (%d)\n", __func__, r);
+		return r;
+	}
+
+	list_for_each_entry_rcu(temp_opp, &dev_opp->opp_list, node) {
+		if (temp_opp->available)
+			count++;
+	}
+
+	return count;
+}
+EXPORT_SYMBOL_GPL(opp_get_opp_count);
+
+/**
+ * opp_find_freq_exact() - search for an exact frequency
+ * @dev:		device for which we do this operation
+ * @freq:		frequency to search for
+ * @available:		true/false - match for available opp
+ *
+ * Searches for exact match in the opp list and returns pointer to the matching
+ * opp if found, else returns ERR_PTR in case of error and should be handled
+ * using IS_ERR. Error return values can be:
+ * EINVAL:	for bad pointer
+ * ERANGE:	no match found for search
+ * ENODEV:	if device not found in list of registered devices
+ *
+ * Note: available is a modifier for the search. if available=true, then the
+ * match is for exact matching frequency and is available in the stored OPP
+ * table. if false, the match is for exact frequency which is not available.
+ *
+ * This provides a mechanism to enable an opp which is not available currently
+ * or the opposite as well.
+ *
+ * Locking: This function must be called under rcu_read_lock(). opp is a rcu
+ * protected pointer. The reason for the same is that the opp pointer which is
+ * returned will remain valid for use with opp_get_{voltage, freq} only while
+ * under the locked area. The pointer returned must be used prior to unlocking
+ * with rcu_read_unlock() to maintain the integrity of the pointer.
+ */
+struct opp *opp_find_freq_exact(struct device *dev, unsigned long freq,
+				bool available)
+{
+	struct device_opp *dev_opp;
+	struct opp *temp_opp, *opp = ERR_PTR(-ERANGE);
+
+	dev_opp = find_device_opp(dev);
+	if (IS_ERR(dev_opp)) {
+		int r = PTR_ERR(dev_opp);
+		dev_err(dev, "%s: device OPP not found (%d)\n", __func__, r);
+		return ERR_PTR(r);
+	}
+
+	list_for_each_entry_rcu(temp_opp, &dev_opp->opp_list, node) {
+		if (temp_opp->available == available &&
+				temp_opp->rate == freq) {
+			opp = temp_opp;
+			break;
+		}
+	}
+
+	return opp;
+}
+EXPORT_SYMBOL_GPL(opp_find_freq_exact);
+
+/**
+ * opp_find_freq_ceil() - Search for an rounded ceil freq
+ * @dev:	device for which we do this operation
+ * @freq:	Start frequency
+ *
+ * Search for the matching ceil *available* OPP from a starting freq
+ * for a device.
+ *
+ * Returns matching *opp and refreshes *freq accordingly, else returns
+ * ERR_PTR in case of error and should be handled using IS_ERR. Error return
+ * values can be:
+ * EINVAL:	for bad pointer
+ * ERANGE:	no match found for search
+ * ENODEV:	if device not found in list of registered devices
+ *
+ * Locking: This function must be called under rcu_read_lock(). opp is a rcu
+ * protected pointer. The reason for the same is that the opp pointer which is
+ * returned will remain valid for use with opp_get_{voltage, freq} only while
+ * under the locked area. The pointer returned must be used prior to unlocking
+ * with rcu_read_unlock() to maintain the integrity of the pointer.
+ */
+struct opp *opp_find_freq_ceil(struct device *dev, unsigned long *freq)
+{
+	struct device_opp *dev_opp;
+	struct opp *temp_opp, *opp = ERR_PTR(-ERANGE);
+
+	if (!dev || !freq) {
+		dev_err(dev, "%s: Invalid argument freq=%p\n", __func__, freq);
+		return ERR_PTR(-EINVAL);
+	}
+
+	dev_opp = find_device_opp(dev);
+	if (IS_ERR(dev_opp))
+		return ERR_CAST(dev_opp);
+
+	list_for_each_entry_rcu(temp_opp, &dev_opp->opp_list, node) {
+		if (temp_opp->available && temp_opp->rate >= *freq) {
+			opp = temp_opp;
+			*freq = opp->rate;
+			break;
+		}
+	}
+
+	return opp;
+}
+EXPORT_SYMBOL_GPL(opp_find_freq_ceil);
+
+/**
+ * opp_find_freq_floor() - Search for a rounded floor freq
+ * @dev:	device for which we do this operation
+ * @freq:	Start frequency
+ *
+ * Search for the matching floor *available* OPP from a starting freq
+ * for a device.
+ *
+ * Returns matching *opp and refreshes *freq accordingly, else returns
+ * ERR_PTR in case of error and should be handled using IS_ERR. Error return
+ * values can be:
+ * EINVAL:	for bad pointer
+ * ERANGE:	no match found for search
+ * ENODEV:	if device not found in list of registered devices
+ *
+ * Locking: This function must be called under rcu_read_lock(). opp is a rcu
+ * protected pointer. The reason for the same is that the opp pointer which is
+ * returned will remain valid for use with opp_get_{voltage, freq} only while
+ * under the locked area. The pointer returned must be used prior to unlocking
+ * with rcu_read_unlock() to maintain the integrity of the pointer.
+ */
+struct opp *opp_find_freq_floor(struct device *dev, unsigned long *freq)
+{
+	struct device_opp *dev_opp;
+	struct opp *temp_opp, *opp = ERR_PTR(-ERANGE);
+
+	if (!dev || !freq) {
+		dev_err(dev, "%s: Invalid argument freq=%p\n", __func__, freq);
+		return ERR_PTR(-EINVAL);
+	}
+
+	dev_opp = find_device_opp(dev);
+	if (IS_ERR(dev_opp))
+		return ERR_CAST(dev_opp);
+
+	list_for_each_entry_rcu(temp_opp, &dev_opp->opp_list, node) {
+		if (temp_opp->available) {
+			/* go to the next node, before choosing prev */
+			if (temp_opp->rate > *freq)
+				break;
+			else
+				opp = temp_opp;
+		}
+	}
+	if (!IS_ERR(opp))
+		*freq = opp->rate;
+
+	return opp;
+}
+EXPORT_SYMBOL_GPL(opp_find_freq_floor);
+
+/**
+ * opp_add()  - Add an OPP table from a table definitions
+ * @dev:	device for which we do this operation
+ * @freq:	Frequency in Hz for this OPP
+ * @u_volt:	Voltage in uVolts for this OPP
+ *
+ * This function adds an opp definition to the opp list and returns status.
+ * The opp is made available by default and it can be controlled using
+ * opp_enable/disable functions.
+ *
+ * Locking: The internal device_opp and opp structures are RCU protected.
+ * Hence this function internally uses RCU updater strategy with mutex locks
+ * to keep the integrity of the internal data structures. Callers should ensure
+ * that this function is *NOT* called under RCU protection or in contexts where
+ * mutex cannot be locked.
+ */
+int opp_add(struct device *dev, unsigned long freq, unsigned long u_volt)
+{
+	struct device_opp *dev_opp = NULL;
+	struct opp *opp, *new_opp;
+	struct list_head *head;
+
+	/* allocate new OPP node */
+	new_opp = kzalloc(sizeof(struct opp), GFP_KERNEL);
+	if (!new_opp) {
+		dev_warn(dev, "%s: Unable to create new OPP node\n", __func__);
+		return -ENOMEM;
+	}
+
+	/* Hold our list modification lock here */
+	mutex_lock(&dev_opp_list_lock);
+
+	/* Check for existing list for 'dev' */
+	dev_opp = find_device_opp(dev);
+	if (IS_ERR(dev_opp)) {
+		/*
+		 * Allocate a new device OPP table. In the infrequent case
+		 * where a new device is needed to be added, we pay this
+		 * penalty.
+		 */
+		dev_opp = kzalloc(sizeof(struct device_opp), GFP_KERNEL);
+		if (!dev_opp) {
+			mutex_unlock(&dev_opp_list_lock);
+			kfree(new_opp);
+			dev_warn(dev,
+				"%s: Unable to create device OPP structure\n",
+				__func__);
+			return -ENOMEM;
+		}
+
+		dev_opp->dev = dev;
+		srcu_init_notifier_head(&dev_opp->head);
+		INIT_LIST_HEAD(&dev_opp->opp_list);
+
+		/* Secure the device list modification */
+		list_add_rcu(&dev_opp->node, &dev_opp_list);
+	}
+
+	/* populate the opp table */
+	new_opp->dev_opp = dev_opp;
+	new_opp->rate = freq;
+	new_opp->u_volt = u_volt;
+	new_opp->available = true;
+
+	/* Insert new OPP in order of increasing frequency */
+	head = &dev_opp->opp_list;
+	list_for_each_entry_rcu(opp, &dev_opp->opp_list, node) {
+		if (new_opp->rate < opp->rate)
+			break;
+		else
+			head = &opp->node;
+	}
+
+	list_add_rcu(&new_opp->node, head);
+	mutex_unlock(&dev_opp_list_lock);
+
+	/*
+	 * Notify the changes in the availability of the operable
+	 * frequency/voltage list.
+	 */
+	srcu_notifier_call_chain(&dev_opp->head, OPP_EVENT_ADD, new_opp);
+	return 0;
+}
+
+/**
+ * opp_set_availability() - helper to set the availability of an opp
+ * @dev:		device for which we do this operation
+ * @freq:		OPP frequency to modify availability
+ * @availability_req:	availability status requested for this opp
+ *
+ * Set the availability of an OPP with an RCU operation, opp_{enable,disable}
+ * share a common logic which is isolated here.
+ *
+ * Returns -EINVAL for bad pointers, -ENOMEM if no memory available for the
+ * copy operation, returns 0 if no modifcation was done OR modification was
+ * successful.
+ *
+ * Locking: The internal device_opp and opp structures are RCU protected.
+ * Hence this function internally uses RCU updater strategy with mutex locks to
+ * keep the integrity of the internal data structures. Callers should ensure
+ * that this function is *NOT* called under RCU protection or in contexts where
+ * mutex locking or synchronize_rcu() blocking calls cannot be used.
+ */
+static int opp_set_availability(struct device *dev, unsigned long freq,
+		bool availability_req)
+{
+	struct device_opp *tmp_dev_opp, *dev_opp = ERR_PTR(-ENODEV);
+	struct opp *new_opp, *tmp_opp, *opp = ERR_PTR(-ENODEV);
+	int r = 0;
+
+	/* keep the node allocated */
+	new_opp = kmalloc(sizeof(struct opp), GFP_KERNEL);
+	if (!new_opp) {
+		dev_warn(dev, "%s: Unable to create OPP\n", __func__);
+		return -ENOMEM;
+	}
+
+	mutex_lock(&dev_opp_list_lock);
+
+	/* Find the device_opp */
+	list_for_each_entry(tmp_dev_opp, &dev_opp_list, node) {
+		if (dev == tmp_dev_opp->dev) {
+			dev_opp = tmp_dev_opp;
+			break;
+		}
+	}
+	if (IS_ERR(dev_opp)) {
+		r = PTR_ERR(dev_opp);
+		dev_warn(dev, "%s: Device OPP not found (%d)\n", __func__, r);
+		goto unlock;
+	}
+
+	/* Do we have the frequency? */
+	list_for_each_entry(tmp_opp, &dev_opp->opp_list, node) {
+		if (tmp_opp->rate == freq) {
+			opp = tmp_opp;
+			break;
+		}
+	}
+	if (IS_ERR(opp)) {
+		r = PTR_ERR(opp);
+		goto unlock;
+	}
+
+	/* Is update really needed? */
+	if (opp->available == availability_req)
+		goto unlock;
+	/* copy the old data over */
+	*new_opp = *opp;
+
+	/* plug in new node */
+	new_opp->available = availability_req;
+
+	list_replace_rcu(&opp->node, &new_opp->node);
+	mutex_unlock(&dev_opp_list_lock);
+	kfree_rcu(opp, head);
+
+	/* Notify the change of the OPP availability */
+	if (availability_req)
+		srcu_notifier_call_chain(&dev_opp->head, OPP_EVENT_ENABLE,
+					 new_opp);
+	else
+		srcu_notifier_call_chain(&dev_opp->head, OPP_EVENT_DISABLE,
+					 new_opp);
+
+	return 0;
+
+unlock:
+	mutex_unlock(&dev_opp_list_lock);
+	kfree(new_opp);
+	return r;
+}
+
+/**
+ * opp_enable() - Enable a specific OPP
+ * @dev:	device for which we do this operation
+ * @freq:	OPP frequency to enable
+ *
+ * Enables a provided opp. If the operation is valid, this returns 0, else the
+ * corresponding error value. It is meant to be used for users an OPP available
+ * after being temporarily made unavailable with opp_disable.
+ *
+ * Locking: The internal device_opp and opp structures are RCU protected.
+ * Hence this function indirectly uses RCU and mutex locks to keep the
+ * integrity of the internal data structures. Callers should ensure that
+ * this function is *NOT* called under RCU protection or in contexts where
+ * mutex locking or synchronize_rcu() blocking calls cannot be used.
+ */
+int opp_enable(struct device *dev, unsigned long freq)
+{
+	return opp_set_availability(dev, freq, true);
+}
+EXPORT_SYMBOL_GPL(opp_enable);
+
+/**
+ * opp_disable() - Disable a specific OPP
+ * @dev:	device for which we do this operation
+ * @freq:	OPP frequency to disable
+ *
+ * Disables a provided opp. If the operation is valid, this returns
+ * 0, else the corresponding error value. It is meant to be a temporary
+ * control by users to make this OPP not available until the circumstances are
+ * right to make it available again (with a call to opp_enable).
+ *
+ * Locking: The internal device_opp and opp structures are RCU protected.
+ * Hence this function indirectly uses RCU and mutex locks to keep the
+ * integrity of the internal data structures. Callers should ensure that
+ * this function is *NOT* called under RCU protection or in contexts where
+ * mutex locking or synchronize_rcu() blocking calls cannot be used.
+ */
+int opp_disable(struct device *dev, unsigned long freq)
+{
+	return opp_set_availability(dev, freq, false);
+}
+EXPORT_SYMBOL_GPL(opp_disable);
+
+#ifdef CONFIG_CPU_FREQ
+/**
+ * opp_init_cpufreq_table() - create a cpufreq table for a device
+ * @dev:	device for which we do this operation
+ * @table:	Cpufreq table returned back to caller
+ *
+ * Generate a cpufreq table for a provided device- this assumes that the
+ * opp list is already initialized and ready for usage.
+ *
+ * This function allocates required memory for the cpufreq table. It is
+ * expected that the caller does the required maintenance such as freeing
+ * the table as required.
+ *
+ * Returns -EINVAL for bad pointers, -ENODEV if the device is not found, -ENOMEM
+ * if no memory available for the operation (table is not populated), returns 0
+ * if successful and table is populated.
+ *
+ * WARNING: It is  important for the callers to ensure refreshing their copy of
+ * the table if any of the mentioned functions have been invoked in the interim.
+ *
+ * Locking: The internal device_opp and opp structures are RCU protected.
+ * To simplify the logic, we pretend we are updater and hold relevant mutex here
+ * Callers should ensure that this function is *NOT* called under RCU protection
+ * or in contexts where mutex locking cannot be used.
+ */
+int opp_init_cpufreq_table(struct device *dev,
+			    struct cpufreq_frequency_table **table)
+{
+	struct device_opp *dev_opp;
+	struct opp *opp;
+	struct cpufreq_frequency_table *freq_table;
+	int i = 0;
+
+	/* Pretend as if I am an updater */
+	mutex_lock(&dev_opp_list_lock);
+
+	dev_opp = find_device_opp(dev);
+	if (IS_ERR(dev_opp)) {
+		int r = PTR_ERR(dev_opp);
+		mutex_unlock(&dev_opp_list_lock);
+		dev_err(dev, "%s: Device OPP not found (%d)\n", __func__, r);
+		return r;
+	}
+
+	freq_table = kzalloc(sizeof(struct cpufreq_frequency_table) *
+			     (opp_get_opp_count(dev) + 1), GFP_KERNEL);
+	if (!freq_table) {
+		mutex_unlock(&dev_opp_list_lock);
+		dev_warn(dev, "%s: Unable to allocate frequency table\n",
+			__func__);
+		return -ENOMEM;
+	}
+
+	list_for_each_entry(opp, &dev_opp->opp_list, node) {
+		if (opp->available) {
+			freq_table[i].index = i;
+			freq_table[i].frequency = opp->rate / 1000;
+			i++;
+		}
+	}
+	mutex_unlock(&dev_opp_list_lock);
+
+	freq_table[i].index = i;
+	freq_table[i].frequency = CPUFREQ_TABLE_END;
+
+	*table = &freq_table[0];
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(opp_init_cpufreq_table);
+
+/**
+ * opp_free_cpufreq_table() - free the cpufreq table
+ * @dev:	device for which we do this operation
+ * @table:	table to free
+ *
+ * Free up the table allocated by opp_init_cpufreq_table
+ */
+void opp_free_cpufreq_table(struct device *dev,
+				struct cpufreq_frequency_table **table)
+{
+	if (!table)
+		return;
+
+	kfree(*table);
+	*table = NULL;
+}
+EXPORT_SYMBOL_GPL(opp_free_cpufreq_table);
+#endif		/* CONFIG_CPU_FREQ */
+
+/**
+ * opp_get_notifier() - find notifier_head of the device with opp
+ * @dev:	device pointer used to lookup device OPPs.
+ */
+struct srcu_notifier_head *opp_get_notifier(struct device *dev)
+{
+	struct device_opp *dev_opp = find_device_opp(dev);
+
+	if (IS_ERR(dev_opp))
+		return ERR_CAST(dev_opp); /* matching type */
+
+	return &dev_opp->head;
+}
+
+#ifdef CONFIG_OF
+/**
+ * of_init_opp_table() - Initialize opp table from device tree
+ * @dev:	device pointer used to lookup device OPPs.
+ *
+ * Register the initial OPP table with the OPP library for given device.
+ */
+int of_init_opp_table(struct device *dev)
+{
+	const struct property *prop;
+	const __be32 *val;
+	int nr;
+
+	prop = of_find_property(dev->of_node, "operating-points", NULL);
+	if (!prop)
+		return -ENODEV;
+	if (!prop->value)
+		return -ENODATA;
+
+	/*
+	 * Each OPP is a set of tuples consisting of frequency and
+	 * voltage like <freq-kHz vol-uV>.
+	 */
+	nr = prop->length / sizeof(u32);
+	if (nr % 2) {
+		dev_err(dev, "%s: Invalid OPP list\n", __func__);
+		return -EINVAL;
+	}
+
+	val = prop->value;
+	while (nr) {
+		unsigned long freq = be32_to_cpup(val++) * 1000;
+		unsigned long volt = be32_to_cpup(val++);
+
+		if (opp_add(dev, freq, volt)) {
+			dev_warn(dev, "%s: Failed to add OPP %ld\n",
+				 __func__, freq);
+			continue;
+		}
+		nr -= 2;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(of_init_opp_table);
+#endif

drivers/base/power/power.h

@@ -0,0 +1,111 @@
+#include <linux/pm_qos.h>
+
+static inline void device_pm_init_common(struct device *dev)
+{
+	if (!dev->power.early_init) {
+		spin_lock_init(&dev->power.lock);
+		dev->power.qos = NULL;
+		dev->power.early_init = true;
+	}
+}
+
+#ifdef CONFIG_PM_RUNTIME
+
+static inline void pm_runtime_early_init(struct device *dev)
+{
+	dev->power.disable_depth = 1;
+	device_pm_init_common(dev);
+}
+
+extern void pm_runtime_init(struct device *dev);
+extern void pm_runtime_remove(struct device *dev);
+
+#else /* !CONFIG_PM_RUNTIME */
+
+static inline void pm_runtime_early_init(struct device *dev)
+{
+	device_pm_init_common(dev);
+}
+
+static inline void pm_runtime_init(struct device *dev) {}
+static inline void pm_runtime_remove(struct device *dev) {}
+
+#endif /* !CONFIG_PM_RUNTIME */
+
+#ifdef CONFIG_PM_SLEEP
+
+/* kernel/power/main.c */
+extern int pm_async_enabled;
+
+/* drivers/base/power/main.c */
+extern struct list_head dpm_list;	/* The active device list */
+
+static inline struct device *to_device(struct list_head *entry)
+{
+	return container_of(entry, struct device, power.entry);
+}
+
+extern void device_pm_sleep_init(struct device *dev);
+extern void device_pm_add(struct device *);
+extern void device_pm_remove(struct device *);
+extern void device_pm_move_before(struct device *, struct device *);
+extern void device_pm_move_after(struct device *, struct device *);
+extern void device_pm_move_last(struct device *);
+
+#else /* !CONFIG_PM_SLEEP */
+
+static inline void device_pm_sleep_init(struct device *dev) {}
+
+static inline void device_pm_add(struct device *dev) {}
+
+static inline void device_pm_remove(struct device *dev)
+{
+	pm_runtime_remove(dev);
+}
+
+static inline void device_pm_move_before(struct device *deva,
+					 struct device *devb) {}
+static inline void device_pm_move_after(struct device *deva,
+					struct device *devb) {}
+static inline void device_pm_move_last(struct device *dev) {}
+
+#endif /* !CONFIG_PM_SLEEP */
+
+static inline void device_pm_init(struct device *dev)
+{
+	device_pm_init_common(dev);
+	device_pm_sleep_init(dev);
+	pm_runtime_init(dev);
+}
+
+#ifdef CONFIG_PM
+
+/*
+ * sysfs.c
+ */
+
+extern int dpm_sysfs_add(struct device *dev);
+extern void dpm_sysfs_remove(struct device *dev);
+extern void rpm_sysfs_remove(struct device *dev);
+extern int wakeup_sysfs_add(struct device *dev);
+extern void wakeup_sysfs_remove(struct device *dev);
+extern int pm_qos_sysfs_add_latency(struct device *dev);
+extern void pm_qos_sysfs_remove_latency(struct device *dev);
+extern int pm_qos_sysfs_add_flags(struct device *dev);
+extern void pm_qos_sysfs_remove_flags(struct device *dev);
+extern int dark_resume_sysfs_add(struct device *dev);
+extern void dark_resume_sysfs_remove(struct device *dev);
+
+#else /* CONFIG_PM */
+
+static inline int dpm_sysfs_add(struct device *dev) { return 0; }
+static inline void dpm_sysfs_remove(struct device *dev) {}
+static inline void rpm_sysfs_remove(struct device *dev) {}
+static inline int wakeup_sysfs_add(struct device *dev) { return 0; }
+static inline void wakeup_sysfs_remove(struct device *dev) {}
+static inline int pm_qos_sysfs_add(struct device *dev) { return 0; }
+static inline void pm_qos_sysfs_remove(struct device *dev) {}
+static inline int dark_resume_sysfs_add(struct device *dev) { return 0; }
+static inline void dark_resume_sysfs_remove(struct device *dev) {}
+
+#endif

drivers/base/power/qos.c

@@ -0,0 +1,774 @@
+/*
+ * Devices PM QoS constraints management
+ *
+ * Copyright (C) 2011 Texas Instruments, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ *
+ * This module exposes the interface to kernel space for specifying
+ * per-device PM QoS dependencies. It provides infrastructure for registration
+ * of:
+ *
+ * Dependents on a QoS value : register requests
+ * Watchers of QoS value : get notified when target QoS value changes
+ *
+ * This QoS design is best effort based. Dependents register their QoS needs.
+ * Watchers register to keep track of the current QoS needs of the system.
+ * Watchers can register different types of notification callbacks:
+ *  . a per-device notification callback using the dev_pm_qos_*_notifier API.
+ *    The notification chain data is stored in the per-device constraint
+ *    data struct.
+ *  . a system-wide notification callback using the dev_pm_qos_*_global_notifier
+ *    API. The notification chain data is stored in a static variable.
+ *
+ * Note about the per-device constraint data struct allocation:
+ * . The per-device constraints data struct ptr is tored into the device
+ *    dev_pm_info.
+ * . To minimize the data usage by the per-device constraints, the data struct
+ *   is only allocated at the first call to dev_pm_qos_add_request.
+ * . The data is later free'd when the device is removed from the system.
+ *  . A global mutex protects the constraints users from the data being
+ *     allocated and free'd.
+ */
+
+#include <linux/pm_qos.h>
+#include <linux/spinlock.h>
+#include <linux/slab.h>
+#include <linux/device.h>
+#include <linux/mutex.h>
+#include <linux/export.h>
+#include <linux/pm_runtime.h>
+#include <linux/err.h>
+#include <trace/events/power.h>
+
+#include "power.h"
+
+static DEFINE_MUTEX(dev_pm_qos_mtx);
+static DEFINE_MUTEX(dev_pm_qos_sysfs_mtx);
+
+static BLOCKING_NOTIFIER_HEAD(dev_pm_notifiers);
+
+/**
+ * __dev_pm_qos_flags - Check PM QoS flags for a given device.
+ * @dev: Device to check the PM QoS flags for.
+ * @mask: Flags to check against.
+ *
+ * This routine must be called with dev->power.lock held.
+ */
+enum pm_qos_flags_status __dev_pm_qos_flags(struct device *dev, s32 mask)
+{
+	struct dev_pm_qos *qos = dev->power.qos;
+	struct pm_qos_flags *pqf;
+	s32 val;
+
+	if (IS_ERR_OR_NULL(qos))
+		return PM_QOS_FLAGS_UNDEFINED;
+
+	pqf = &qos->flags;
+	if (list_empty(&pqf->list))
+		return PM_QOS_FLAGS_UNDEFINED;
+
+	val = pqf->effective_flags & mask;
+	if (val)
+		return (val == mask) ? PM_QOS_FLAGS_ALL : PM_QOS_FLAGS_SOME;
+
+	return PM_QOS_FLAGS_NONE;
+}
+
+/**
+ * dev_pm_qos_flags - Check PM QoS flags for a given device (locked).
+ * @dev: Device to check the PM QoS flags for.
+ * @mask: Flags to check against.
+ */
+enum pm_qos_flags_status dev_pm_qos_flags(struct device *dev, s32 mask)
+{
+	unsigned long irqflags;
+	enum pm_qos_flags_status ret;
+
+	spin_lock_irqsave(&dev->power.lock, irqflags);
+	ret = __dev_pm_qos_flags(dev, mask);
+	spin_unlock_irqrestore(&dev->power.lock, irqflags);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(dev_pm_qos_flags);
+
+/**
+ * __dev_pm_qos_read_value - Get PM QoS constraint for a given device.
+ * @dev: Device to get the PM QoS constraint value for.
+ *
+ * This routine must be called with dev->power.lock held.
+ */
+s32 __dev_pm_qos_read_value(struct device *dev)
+{
+	return IS_ERR_OR_NULL(dev->power.qos) ?
+		0 : pm_qos_read_value(&dev->power.qos->latency);
+}
+
+/**
+ * dev_pm_qos_read_value - Get PM QoS constraint for a given device (locked).
+ * @dev: Device to get the PM QoS constraint value for.
+ */
+s32 dev_pm_qos_read_value(struct device *dev)
+{
+	unsigned long flags;
+	s32 ret;
+
+	spin_lock_irqsave(&dev->power.lock, flags);
+	ret = __dev_pm_qos_read_value(dev);
+	spin_unlock_irqrestore(&dev->power.lock, flags);
+
+	return ret;
+}
+
+/**
+ * apply_constraint - Add/modify/remove device PM QoS request.
+ * @req: Constraint request to apply
+ * @action: Action to perform (add/update/remove).
+ * @value: Value to assign to the QoS request.
+ *
+ * Internal function to update the constraints list using the PM QoS core
+ * code and if needed call the per-device and the global notification
+ * callbacks
+ */
+static int apply_constraint(struct dev_pm_qos_request *req,
+			    enum pm_qos_req_action action, s32 value)
+{
+	struct dev_pm_qos *qos = req->dev->power.qos;
+	int ret;
+
+	switch(req->type) {
+	case DEV_PM_QOS_LATENCY:
+		ret = pm_qos_update_target(&qos->latency, &req->data.pnode,
+					   action, value);
+		if (ret) {
+			value = pm_qos_read_value(&qos->latency);
+			blocking_notifier_call_chain(&dev_pm_notifiers,
+						     (unsigned long)value,
+						     req);
+		}
+		break;
+	case DEV_PM_QOS_FLAGS:
+		ret = pm_qos_update_flags(&qos->flags, &req->data.flr,
+					  action, value);
+		break;
+	default:
+		ret = -EINVAL;
+	}
+
+	return ret;
+}
+
+/*
+ * dev_pm_qos_constraints_allocate
+ * @dev: device to allocate data for
+ *
+ * Called at the first call to add_request, for constraint data allocation
+ * Must be called with the dev_pm_qos_mtx mutex held
+ */
+static int dev_pm_qos_constraints_allocate(struct device *dev)
+{
+	struct dev_pm_qos *qos;
+	struct pm_qos_constraints *c;
+	struct blocking_notifier_head *n;
+
+	qos = kzalloc(sizeof(*qos), GFP_KERNEL);
+	if (!qos)
+		return -ENOMEM;
+
+	n = kzalloc(sizeof(*n), GFP_KERNEL);
+	if (!n) {
+		kfree(qos);
+		return -ENOMEM;
+	}
+	BLOCKING_INIT_NOTIFIER_HEAD(n);
+
+	c = &qos->latency;
+	plist_head_init(&c->list);
+	c->target_value = PM_QOS_DEV_LAT_DEFAULT_VALUE;
+	c->default_value = PM_QOS_DEV_LAT_DEFAULT_VALUE;
+	c->type = PM_QOS_MIN;
+	c->notifiers = n;
+
+	INIT_LIST_HEAD(&qos->flags.list);
+
+	spin_lock_irq(&dev->power.lock);
+	dev->power.qos = qos;
+	spin_unlock_irq(&dev->power.lock);
+
+	return 0;
+}
+
+static void __dev_pm_qos_hide_latency_limit(struct device *dev);
+static void __dev_pm_qos_hide_flags(struct device *dev);
+
+/**
+ * dev_pm_qos_constraints_destroy
+ * @dev: target device
+ *
+ * Called from the device PM subsystem on device removal under device_pm_lock().
+ */
+void dev_pm_qos_constraints_destroy(struct device *dev)
+{
+	struct dev_pm_qos *qos;
+	struct dev_pm_qos_request *req, *tmp;
+	struct pm_qos_constraints *c;
+	struct pm_qos_flags *f;
+
+	mutex_lock(&dev_pm_qos_sysfs_mtx);
+
+	/*
+	 * If the device's PM QoS resume latency limit or PM QoS flags have been
+	 * exposed to user space, they have to be hidden at this point.
+	 */
+	pm_qos_sysfs_remove_latency(dev);
+	pm_qos_sysfs_remove_flags(dev);
+
+	mutex_lock(&dev_pm_qos_mtx);
+
+	__dev_pm_qos_hide_latency_limit(dev);
+	__dev_pm_qos_hide_flags(dev);
+
+	qos = dev->power.qos;
+	if (!qos)
+		goto out;
+
+	/* Flush the constraints lists for the device. */
+	c = &qos->latency;
+	plist_for_each_entry_safe(req, tmp, &c->list, data.pnode) {
+		/*
+		 * Update constraints list and call the notification
+		 * callbacks if needed
+		 */
+		apply_constraint(req, PM_QOS_REMOVE_REQ, PM_QOS_DEFAULT_VALUE);
+		memset(req, 0, sizeof(*req));
+	}
+	f = &qos->flags;
+	list_for_each_entry_safe(req, tmp, &f->list, data.flr.node) {
+		apply_constraint(req, PM_QOS_REMOVE_REQ, PM_QOS_DEFAULT_VALUE);
+		memset(req, 0, sizeof(*req));
+	}
+
+	spin_lock_irq(&dev->power.lock);
+	dev->power.qos = ERR_PTR(-ENODEV);
+	spin_unlock_irq(&dev->power.lock);
+
+	kfree(c->notifiers);
+	kfree(qos);
+
+ out:
+	mutex_unlock(&dev_pm_qos_mtx);
+
+	mutex_unlock(&dev_pm_qos_sysfs_mtx);
+}
+
+/**
+ * dev_pm_qos_add_request - inserts new qos request into the list
+ * @dev: target device for the constraint
+ * @req: pointer to a preallocated handle
+ * @type: type of the request
+ * @value: defines the qos request
+ *
+ * This function inserts a new entry in the device constraints list of
+ * requested qos performance characteristics. It recomputes the aggregate
+ * QoS expectations of parameters and initializes the dev_pm_qos_request
+ * handle.  Caller needs to save this handle for later use in updates and
+ * removal.
+ *
+ * Returns 1 if the aggregated constraint value has changed,
+ * 0 if the aggregated constraint value has not changed,
+ * -EINVAL in case of wrong parameters, -ENOMEM if there's not enough memory
+ * to allocate for data structures, -ENODEV if the device has just been removed
+ * from the system.
+ *
+ * Callers should ensure that the target device is not RPM_SUSPENDED before
+ * using this function for requests of type DEV_PM_QOS_FLAGS.
+ */
+int dev_pm_qos_add_request(struct device *dev, struct dev_pm_qos_request *req,
+			   enum dev_pm_qos_req_type type, s32 value)
+{
+	int ret = 0;
+
+	if (!dev || !req) /*guard against callers passing in null */
+		return -EINVAL;
+
+	if (WARN(dev_pm_qos_request_active(req),
+		 "%s() called for already added request\n", __func__))
+		return -EINVAL;
+
+	mutex_lock(&dev_pm_qos_mtx);
+
+	if (IS_ERR(dev->power.qos))
+		ret = -ENODEV;
+	else if (!dev->power.qos)
+		ret = dev_pm_qos_constraints_allocate(dev);
+
+	trace_dev_pm_qos_add_request(dev_name(dev), type, value);
+	if (!ret) {
+		req->dev = dev;
+		req->type = type;
+		ret = apply_constraint(req, PM_QOS_ADD_REQ, value);
+	}
+
+	mutex_unlock(&dev_pm_qos_mtx);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(dev_pm_qos_add_request);
+
+/**
+ * __dev_pm_qos_update_request - Modify an existing device PM QoS request.
+ * @req : PM QoS request to modify.
+ * @new_value: New value to request.
+ */
+static int __dev_pm_qos_update_request(struct dev_pm_qos_request *req,
+				       s32 new_value)
+{
+	s32 curr_value;
+	int ret = 0;
+
+	if (!req) /*guard against callers passing in null */
+		return -EINVAL;
+
+	if (WARN(!dev_pm_qos_request_active(req),
+		 "%s() called for unknown object\n", __func__))
+		return -EINVAL;
+
+	if (IS_ERR_OR_NULL(req->dev->power.qos))
+		return -ENODEV;
+
+	switch(req->type) {
+	case DEV_PM_QOS_LATENCY:
+		curr_value = req->data.pnode.prio;
+		break;
+	case DEV_PM_QOS_FLAGS:
+		curr_value = req->data.flr.flags;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	trace_dev_pm_qos_update_request(dev_name(req->dev), req->type,
+					new_value);
+	if (curr_value != new_value)
+		ret = apply_constraint(req, PM_QOS_UPDATE_REQ, new_value);
+
+	return ret;
+}
+
+/**
+ * dev_pm_qos_update_request - modifies an existing qos request
+ * @req : handle to list element holding a dev_pm_qos request to use
+ * @new_value: defines the qos request
+ *
+ * Updates an existing dev PM qos request along with updating the
+ * target value.
+ *
+ * Attempts are made to make this code callable on hot code paths.
+ *
+ * Returns 1 if the aggregated constraint value has changed,
+ * 0 if the aggregated constraint value has not changed,
+ * -EINVAL in case of wrong parameters, -ENODEV if the device has been
+ * removed from the system
+ *
+ * Callers should ensure that the target device is not RPM_SUSPENDED before
+ * using this function for requests of type DEV_PM_QOS_FLAGS.
+ */
+int dev_pm_qos_update_request(struct dev_pm_qos_request *req, s32 new_value)
+{
+	int ret;
+
+	mutex_lock(&dev_pm_qos_mtx);
+	ret = __dev_pm_qos_update_request(req, new_value);
+	mutex_unlock(&dev_pm_qos_mtx);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(dev_pm_qos_update_request);
+
+static int __dev_pm_qos_remove_request(struct dev_pm_qos_request *req)
+{
+	int ret;
+
+	if (!req) /*guard against callers passing in null */
+		return -EINVAL;
+
+	if (WARN(!dev_pm_qos_request_active(req),
+		 "%s() called for unknown object\n", __func__))
+		return -EINVAL;
+
+	if (IS_ERR_OR_NULL(req->dev->power.qos))
+		return -ENODEV;
+
+	trace_dev_pm_qos_remove_request(dev_name(req->dev), req->type,
+					PM_QOS_DEFAULT_VALUE);
+	ret = apply_constraint(req, PM_QOS_REMOVE_REQ, PM_QOS_DEFAULT_VALUE);
+	memset(req, 0, sizeof(*req));
+	return ret;
+}
+
+/**
+ * dev_pm_qos_remove_request - modifies an existing qos request
+ * @req: handle to request list element
+ *
+ * Will remove pm qos request from the list of constraints and
+ * recompute the current target value. Call this on slow code paths.
+ *
+ * Returns 1 if the aggregated constraint value has changed,
+ * 0 if the aggregated constraint value has not changed,
+ * -EINVAL in case of wrong parameters, -ENODEV if the device has been
+ * removed from the system
+ *
+ * Callers should ensure that the target device is not RPM_SUSPENDED before
+ * using this function for requests of type DEV_PM_QOS_FLAGS.
+ */
+int dev_pm_qos_remove_request(struct dev_pm_qos_request *req)
+{
+	int ret;
+
+	mutex_lock(&dev_pm_qos_mtx);
+	ret = __dev_pm_qos_remove_request(req);
+	mutex_unlock(&dev_pm_qos_mtx);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(dev_pm_qos_remove_request);
+
+/**
+ * dev_pm_qos_add_notifier - sets notification entry for changes to target value
+ * of per-device PM QoS constraints
+ *
+ * @dev: target device for the constraint
+ * @notifier: notifier block managed by caller.
+ *
+ * Will register the notifier into a notification chain that gets called
+ * upon changes to the target value for the device.
+ *
+ * If the device's constraints object doesn't exist when this routine is called,
+ * it will be created (or error code will be returned if that fails).
+ */
+int dev_pm_qos_add_notifier(struct device *dev, struct notifier_block *notifier)
+{
+	int ret = 0;
+
+	mutex_lock(&dev_pm_qos_mtx);
+
+	if (IS_ERR(dev->power.qos))
+		ret = -ENODEV;
+	else if (!dev->power.qos)
+		ret = dev_pm_qos_constraints_allocate(dev);
+
+	if (!ret)
+		ret = blocking_notifier_chain_register(
+				dev->power.qos->latency.notifiers, notifier);
+
+	mutex_unlock(&dev_pm_qos_mtx);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(dev_pm_qos_add_notifier);
+
+/**
+ * dev_pm_qos_remove_notifier - deletes notification for changes to target value
+ * of per-device PM QoS constraints
+ *
+ * @dev: target device for the constraint
+ * @notifier: notifier block to be removed.
+ *
+ * Will remove the notifier from the notification chain that gets called
+ * upon changes to the target value.
+ */
+int dev_pm_qos_remove_notifier(struct device *dev,
+			       struct notifier_block *notifier)
+{
+	int retval = 0;
+
+	mutex_lock(&dev_pm_qos_mtx);
+
+	/* Silently return if the constraints object is not present. */
+	if (!IS_ERR_OR_NULL(dev->power.qos))
+		retval = blocking_notifier_chain_unregister(
+				dev->power.qos->latency.notifiers,
+				notifier);
+
+	mutex_unlock(&dev_pm_qos_mtx);
+	return retval;
+}
+EXPORT_SYMBOL_GPL(dev_pm_qos_remove_notifier);
+
+/**
+ * dev_pm_qos_add_global_notifier - sets notification entry for changes to
+ * target value of the PM QoS constraints for any device
+ *
+ * @notifier: notifier block managed by caller.
+ *
+ * Will register the notifier into a notification chain that gets called
+ * upon changes to the target value for any device.
+ */
+int dev_pm_qos_add_global_notifier(struct notifier_block *notifier)
+{
+	return blocking_notifier_chain_register(&dev_pm_notifiers, notifier);
+}
+EXPORT_SYMBOL_GPL(dev_pm_qos_add_global_notifier);
+
+/**
+ * dev_pm_qos_remove_global_notifier - deletes notification for changes to
+ * target value of PM QoS constraints for any device
+ *
+ * @notifier: notifier block to be removed.
+ *
+ * Will remove the notifier from the notification chain that gets called
+ * upon changes to the target value for any device.
+ */
+int dev_pm_qos_remove_global_notifier(struct notifier_block *notifier)
+{
+	return blocking_notifier_chain_unregister(&dev_pm_notifiers, notifier);
+}
+EXPORT_SYMBOL_GPL(dev_pm_qos_remove_global_notifier);
+
+/**
+ * dev_pm_qos_add_ancestor_request - Add PM QoS request for device's ancestor.
+ * @dev: Device whose ancestor to add the request for.
+ * @req: Pointer to the preallocated handle.
+ * @value: Constraint latency value.
+ */
+int dev_pm_qos_add_ancestor_request(struct device *dev,
+				    struct dev_pm_qos_request *req, s32 value)
+{
+	struct device *ancestor = dev->parent;
+	int ret = -ENODEV;
+
+	while (ancestor && !ancestor->power.ignore_children)
+		ancestor = ancestor->parent;
+
+	if (ancestor)
+		ret = dev_pm_qos_add_request(ancestor, req,
+					     DEV_PM_QOS_LATENCY, value);
+
+	if (ret < 0)
+		req->dev = NULL;
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(dev_pm_qos_add_ancestor_request);
+
+#ifdef CONFIG_PM_RUNTIME
+static void __dev_pm_qos_drop_user_request(struct device *dev,
+					   enum dev_pm_qos_req_type type)
+{
+	struct dev_pm_qos_request *req = NULL;
+
+	switch(type) {
+	case DEV_PM_QOS_LATENCY:
+		req = dev->power.qos->latency_req;
+		dev->power.qos->latency_req = NULL;
+		break;
+	case DEV_PM_QOS_FLAGS:
+		req = dev->power.qos->flags_req;
+		dev->power.qos->flags_req = NULL;
+		break;
+	}
+	__dev_pm_qos_remove_request(req);
+	kfree(req);
+}
+
+static void dev_pm_qos_drop_user_request(struct device *dev,
+					 enum dev_pm_qos_req_type type)
+{
+	mutex_lock(&dev_pm_qos_mtx);
+	__dev_pm_qos_drop_user_request(dev, type);
+	mutex_unlock(&dev_pm_qos_mtx);
+}
+
+/**
+ * dev_pm_qos_expose_latency_limit - Expose PM QoS latency limit to user space.
+ * @dev: Device whose PM QoS latency limit is to be exposed to user space.
+ * @value: Initial value of the latency limit.
+ */
+int dev_pm_qos_expose_latency_limit(struct device *dev, s32 value)
+{
+	struct dev_pm_qos_request *req;
+	int ret;
+
+	if (!device_is_registered(dev) || value < 0)
+		return -EINVAL;
+
+	req = kzalloc(sizeof(*req), GFP_KERNEL);
+	if (!req)
+		return -ENOMEM;
+
+	ret = dev_pm_qos_add_request(dev, req, DEV_PM_QOS_LATENCY, value);
+	if (ret < 0) {
+		kfree(req);
+		return ret;
+	}
+
+	mutex_lock(&dev_pm_qos_sysfs_mtx);
+
+	mutex_lock(&dev_pm_qos_mtx);
+
+	if (IS_ERR_OR_NULL(dev->power.qos))
+		ret = -ENODEV;
+	else if (dev->power.qos->latency_req)
+		ret = -EEXIST;
+
+	if (ret < 0) {
+		__dev_pm_qos_remove_request(req);
+		kfree(req);
+		mutex_unlock(&dev_pm_qos_mtx);
+		goto out;
+	}
+	dev->power.qos->latency_req = req;
+
+	mutex_unlock(&dev_pm_qos_mtx);
+
+	ret = pm_qos_sysfs_add_latency(dev);
+	if (ret)
+		dev_pm_qos_drop_user_request(dev, DEV_PM_QOS_LATENCY);
+
+ out:
+	mutex_unlock(&dev_pm_qos_sysfs_mtx);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(dev_pm_qos_expose_latency_limit);
+
+static void __dev_pm_qos_hide_latency_limit(struct device *dev)
+{
+	if (!IS_ERR_OR_NULL(dev->power.qos) && dev->power.qos->latency_req)
+		__dev_pm_qos_drop_user_request(dev, DEV_PM_QOS_LATENCY);
+}
+
+/**
+ * dev_pm_qos_hide_latency_limit - Hide PM QoS latency limit from user space.
+ * @dev: Device whose PM QoS latency limit is to be hidden from user space.
+ */
+void dev_pm_qos_hide_latency_limit(struct device *dev)
+{
+	mutex_lock(&dev_pm_qos_sysfs_mtx);
+
+	pm_qos_sysfs_remove_latency(dev);
+
+	mutex_lock(&dev_pm_qos_mtx);
+	__dev_pm_qos_hide_latency_limit(dev);
+	mutex_unlock(&dev_pm_qos_mtx);
+
+	mutex_unlock(&dev_pm_qos_sysfs_mtx);
+}
+EXPORT_SYMBOL_GPL(dev_pm_qos_hide_latency_limit);
+
+/**
+ * dev_pm_qos_expose_flags - Expose PM QoS flags of a device to user space.
+ * @dev: Device whose PM QoS flags are to be exposed to user space.
+ * @val: Initial values of the flags.
+ */
+int dev_pm_qos_expose_flags(struct device *dev, s32 val)
+{
+	struct dev_pm_qos_request *req;
+	int ret;
+
+	if (!device_is_registered(dev))
+		return -EINVAL;
+
+	req = kzalloc(sizeof(*req), GFP_KERNEL);
+	if (!req)
+		return -ENOMEM;
+
+	ret = dev_pm_qos_add_request(dev, req, DEV_PM_QOS_FLAGS, val);
+	if (ret < 0) {
+		kfree(req);
+		return ret;
+	}
+
+	pm_runtime_get_sync(dev);
+	mutex_lock(&dev_pm_qos_sysfs_mtx);
+
+	mutex_lock(&dev_pm_qos_mtx);
+
+	if (IS_ERR_OR_NULL(dev->power.qos))
+		ret = -ENODEV;
+	else if (dev->power.qos->flags_req)
+		ret = -EEXIST;
+
+	if (ret < 0) {
+		__dev_pm_qos_remove_request(req);
+		kfree(req);
+		mutex_unlock(&dev_pm_qos_mtx);
+		goto out;
+	}
+	dev->power.qos->flags_req = req;
+
+	mutex_unlock(&dev_pm_qos_mtx);
+
+	ret = pm_qos_sysfs_add_flags(dev);
+	if (ret)
+		dev_pm_qos_drop_user_request(dev, DEV_PM_QOS_FLAGS);
+
+ out:
+	mutex_unlock(&dev_pm_qos_sysfs_mtx);
+	pm_runtime_put(dev);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(dev_pm_qos_expose_flags);
+
+static void __dev_pm_qos_hide_flags(struct device *dev)
+{
+	if (!IS_ERR_OR_NULL(dev->power.qos) && dev->power.qos->flags_req)
+		__dev_pm_qos_drop_user_request(dev, DEV_PM_QOS_FLAGS);
+}
+
+/**
+ * dev_pm_qos_hide_flags - Hide PM QoS flags of a device from user space.
+ * @dev: Device whose PM QoS flags are to be hidden from user space.
+ */
+void dev_pm_qos_hide_flags(struct device *dev)
+{
+	pm_runtime_get_sync(dev);
+	mutex_lock(&dev_pm_qos_sysfs_mtx);
+
+	pm_qos_sysfs_remove_flags(dev);
+
+	mutex_lock(&dev_pm_qos_mtx);
+	__dev_pm_qos_hide_flags(dev);
+	mutex_unlock(&dev_pm_qos_mtx);
+
+	mutex_unlock(&dev_pm_qos_sysfs_mtx);
+	pm_runtime_put(dev);
+}
+EXPORT_SYMBOL_GPL(dev_pm_qos_hide_flags);
+
+/**
+ * dev_pm_qos_update_flags - Update PM QoS flags request owned by user space.
+ * @dev: Device to update the PM QoS flags request for.
+ * @mask: Flags to set/clear.
+ * @set: Whether to set or clear the flags (true means set).
+ */
+int dev_pm_qos_update_flags(struct device *dev, s32 mask, bool set)
+{
+	s32 value;
+	int ret;
+
+	pm_runtime_get_sync(dev);
+	mutex_lock(&dev_pm_qos_mtx);
+
+	if (IS_ERR_OR_NULL(dev->power.qos) || !dev->power.qos->flags_req) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	value = dev_pm_qos_requested_flags(dev);
+	if (set)
+		value |= mask;
+	else
+		value &= ~mask;
+
+	ret = __dev_pm_qos_update_request(dev->power.qos->flags_req, value);
+
+ out:
+	mutex_unlock(&dev_pm_qos_mtx);
+	pm_runtime_put(dev);
+	return ret;
+}
+#else /* !CONFIG_PM_RUNTIME */
+static void __dev_pm_qos_hide_latency_limit(struct device *dev) {}
+static void __dev_pm_qos_hide_flags(struct device *dev) {}
+#endif /* CONFIG_PM_RUNTIME */

drivers/base/power/suspend_volatile.c

@@ -0,0 +1,101 @@
+/*
+ * Utils for keeping track of which areas of RAM change during suspend code.
+ *
+ * Copyright (C) 2012 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/kernel.h>
+
+#include <linux/addr_overlap.h>
+#include <linux/io.h>
+#include <linux/pm.h>
+
+static LIST_HEAD(volatile_chunks);
+static DEFINE_SPINLOCK(volatile_chunks_lock);
+
+/**
+ * Register a range of memory as volatile.
+ *
+ * @chunk: The chunk to register; memory for this structure must remain
+ *	allocated until the chunk is unregistered.
+ */
+void pm_register_suspend_volatile(struct pm_suspend_volatile_chunk *chunk)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&volatile_chunks_lock, flags);
+	list_add_tail(&chunk->list, &volatile_chunks);
+	spin_unlock_irqrestore(&volatile_chunks_lock, flags);
+}
+
+/**
+ * Unregister a range of memory as volatile.
+ *
+ * @chunk: The chunk to unregister.  Should be exact pointer passed to register.
+ */
+void pm_unregister_suspend_volatile(struct pm_suspend_volatile_chunk *chunk)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&volatile_chunks_lock, flags);
+	list_del(&chunk->list);
+	spin_unlock_irqrestore(&volatile_chunks_lock, flags);
+}
+
+/**
+ * Return true if the chunk overlaps memory that is touched by suspend process.
+ *
+ * Checks both memory that was registered with pm_register_suspend_volatile()
+ * and memory that was tagged with __suspend_volatile.
+ *
+ * As the list is not proected with locks, this code must only be called
+ * from an uninterruptible context.
+ *
+ * @start: Physical start address of chunk to check.
+ * @num_bytes: Size of the chunk to check in bytes.
+ */
+bool pm_does_overlap_suspend_volatile(phys_addr_t start, size_t num_bytes)
+{
+	struct pm_suspend_volatile_chunk *chunk;
+	bool is_volatile = false;
+
+	/* Bits marked at compile time as suspend volatile */
+	if (phys_addrs_overlap(start, num_bytes,
+			       virt_to_phys(__start_suspend_volatile_bss),
+			       __stop_suspend_volatile_bss -
+			       __start_suspend_volatile_bss))
+		return true;
+
+	/* Bits marked at compile time as suspend volatile */
+	if (phys_addrs_overlap(start, num_bytes,
+			       virt_to_phys(__start_suspend_volatile_data),
+			       __stop_suspend_volatile_data -
+			       __start_suspend_volatile_data))
+		return true;
+
+	/*
+	 * Bits registered dynamically
+	 *
+	 * Normally a call to spin_lock_irqsave(&volatile_chunks_lock, flags);
+	 * would go here.  However this code is only called with scheduling
+	 * disabled so there is no need to lock the list.  It is also called
+	 * often enough that the overhead involved is signficant (~100 ms)
+	 */
+	list_for_each_entry(chunk, &volatile_chunks, list) {
+		if (phys_addrs_overlap(start, num_bytes,
+				       chunk->start, chunk->num_bytes)) {
+			is_volatile = true;
+			break;
+		}
+	}
+	return is_volatile;
+}

drivers/base/power/sysfs.c

@@ -0,0 +1,786 @@
+/*
+ * drivers/base/power/sysfs.c - sysfs entries for device PM
+ */
+
+#include <linux/device.h>
+#include <linux/string.h>
+#include <linux/export.h>
+#include <linux/pm_dark_resume.h>
+#include <linux/pm_qos.h>
+#include <linux/pm_runtime.h>
+#include <linux/atomic.h>
+#include <linux/jiffies.h>
+#include "power.h"
+
+/*
+ *	control - Report/change current runtime PM setting of the device
+ *
+ *	Runtime power management of a device can be blocked with the help of
+ *	this attribute.  All devices have one of the following two values for
+ *	the power/control file:
+ *
+ *	 + "auto\n" to allow the device to be power managed at run time;
+ *	 + "on\n" to prevent the device from being power managed at run time;
+ *
+ *	The default for all devices is "auto", which means that devices may be
+ *	subject to automatic power management, depending on their drivers.
+ *	Changing this attribute to "on" prevents the driver from power managing
+ *	the device at run time.  Doing that while the device is suspended causes
+ *	it to be woken up.
+ *
+ *	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.
+ *
+ *	async - Report/change current async suspend setting for the device
+ *
+ *	Asynchronous suspend and resume of the device during system-wide power
+ *	state transitions can be enabled by writing "enabled" to this file.
+ *	Analogously, if "disabled" is written to this file, the device will be
+ *	suspended and resumed synchronously.
+ *
+ *	All devices have one of the following two values for power/async:
+ *
+ *	 + "enabled\n" to permit the asynchronous suspend/resume of the device;
+ *	 + "disabled\n" to forbid it;
+ *
+ *	NOTE: It generally is unsafe to permit the asynchronous suspend/resume
+ *	of a device unless it is certain that all of the PM dependencies of the
+ *	device are known to the PM core.  However, for some devices this
+ *	attribute is set to "enabled" by bus type code or device drivers and in
+ *	that cases it should be safe to leave the default value.
+ *
+ *	autosuspend_delay_ms - Report/change a device's autosuspend_delay value
+ *
+ *	Some drivers don't want to carry out a runtime suspend as soon as a
+ *	device becomes idle; they want it always to remain idle for some period
+ *	of time before suspending it.  This period is the autosuspend_delay
+ *	value (expressed in milliseconds) and it can be controlled by the user.
+ *	If the value is negative then the device will never be runtime
+ *	suspended.
+ *
+ *	NOTE: The autosuspend_delay_ms attribute and the autosuspend_delay
+ *	value are used only if the driver calls pm_runtime_use_autosuspend().
+ *
+ *	wakeup_count - Report the number of wakeup events related to the device
+ */
+
+static const char enabled[] = "enabled";
+static const char disabled[] = "disabled";
+
+const char power_group_name[] = "power";
+EXPORT_SYMBOL_GPL(power_group_name);
+
+#ifdef CONFIG_PM_RUNTIME
+static const char ctrl_auto[] = "auto";
+static const char ctrl_on[] = "on";
+
+static ssize_t control_show(struct device *dev, struct device_attribute *attr,
+			    char *buf)
+{
+	return sprintf(buf, "%s\n",
+				dev->power.runtime_auto ? ctrl_auto : ctrl_on);
+}
+
+static ssize_t control_store(struct device * dev, struct device_attribute *attr,
+			     const char * buf, size_t n)
+{
+	char *cp;
+	int len = n;
+
+	cp = memchr(buf, '\n', n);
+	if (cp)
+		len = cp - buf;
+	device_lock(dev);
+	if (len == sizeof ctrl_auto - 1 && strncmp(buf, ctrl_auto, len) == 0)
+		pm_runtime_allow(dev);
+	else if (len == sizeof ctrl_on - 1 && strncmp(buf, ctrl_on, len) == 0)
+		pm_runtime_forbid(dev);
+	else
+		n = -EINVAL;
+	device_unlock(dev);
+	return n;
+}
+
+static DEVICE_ATTR(control, 0644, control_show, control_store);
+
+static ssize_t rtpm_active_time_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	int ret;
+	spin_lock_irq(&dev->power.lock);
+	update_pm_runtime_accounting(dev);
+	ret = sprintf(buf, "%i\n", jiffies_to_msecs(dev->power.active_jiffies));
+	spin_unlock_irq(&dev->power.lock);
+	return ret;
+}
+
+static DEVICE_ATTR(runtime_active_time, 0444, rtpm_active_time_show, NULL);
+
+static ssize_t rtpm_suspended_time_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	int ret;
+	spin_lock_irq(&dev->power.lock);
+	update_pm_runtime_accounting(dev);
+	ret = sprintf(buf, "%i\n",
+		jiffies_to_msecs(dev->power.suspended_jiffies));
+	spin_unlock_irq(&dev->power.lock);
+	return ret;
+}
+
+static DEVICE_ATTR(runtime_suspended_time, 0444, rtpm_suspended_time_show, NULL);
+
+static ssize_t rtpm_status_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	const char *p;
+
+	if (dev->power.runtime_error) {
+		p = "error\n";
+	} else if (dev->power.disable_depth) {
+		p = "unsupported\n";
+	} else {
+		switch (dev->power.runtime_status) {
+		case RPM_SUSPENDED:
+			p = "suspended\n";
+			break;
+		case RPM_SUSPENDING:
+			p = "suspending\n";
+			break;
+		case RPM_RESUMING:
+			p = "resuming\n";
+			break;
+		case RPM_ACTIVE:
+			p = "active\n";
+			break;
+		default:
+			return -EIO;
+		}
+	}
+	return sprintf(buf, p);
+}
+
+static DEVICE_ATTR(runtime_status, 0444, rtpm_status_show, NULL);
+
+static ssize_t autosuspend_delay_ms_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	if (!dev->power.use_autosuspend)
+		return -EIO;
+	return sprintf(buf, "%d\n", dev->power.autosuspend_delay);
+}
+
+static ssize_t autosuspend_delay_ms_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t n)
+{
+	long delay;
+
+	if (!dev->power.use_autosuspend)
+		return -EIO;
+
+	if (strict_strtol(buf, 10, &delay) != 0 || delay != (int) delay)
+		return -EINVAL;
+
+	device_lock(dev);
+	pm_runtime_set_autosuspend_delay(dev, delay);
+	device_unlock(dev);
+	return n;
+}
+
+static DEVICE_ATTR(autosuspend_delay_ms, 0644, autosuspend_delay_ms_show,
+		autosuspend_delay_ms_store);
+
+static ssize_t pm_qos_latency_show(struct device *dev,
+				   struct device_attribute *attr, char *buf)
+{
+	return sprintf(buf, "%d\n", dev_pm_qos_requested_latency(dev));
+}
+
+static ssize_t pm_qos_latency_store(struct device *dev,
+				    struct device_attribute *attr,
+				    const char *buf, size_t n)
+{
+	s32 value;
+	int ret;
+
+	if (kstrtos32(buf, 0, &value))
+		return -EINVAL;
+
+	if (value < 0)
+		return -EINVAL;
+
+	ret = dev_pm_qos_update_request(dev->power.qos->latency_req, value);
+	return ret < 0 ? ret : n;
+}
+
+static DEVICE_ATTR(pm_qos_resume_latency_us, 0644,
+		   pm_qos_latency_show, pm_qos_latency_store);
+
+static ssize_t pm_qos_no_power_off_show(struct device *dev,
+					struct device_attribute *attr,
+					char *buf)
+{
+	return sprintf(buf, "%d\n", !!(dev_pm_qos_requested_flags(dev)
+					& PM_QOS_FLAG_NO_POWER_OFF));
+}
+
+static ssize_t pm_qos_no_power_off_store(struct device *dev,
+					 struct device_attribute *attr,
+					 const char *buf, size_t n)
+{
+	int ret;
+
+	if (kstrtoint(buf, 0, &ret))
+		return -EINVAL;
+
+	if (ret != 0 && ret != 1)
+		return -EINVAL;
+
+	ret = dev_pm_qos_update_flags(dev, PM_QOS_FLAG_NO_POWER_OFF, ret);
+	return ret < 0 ? ret : n;
+}
+
+static DEVICE_ATTR(pm_qos_no_power_off, 0644,
+		   pm_qos_no_power_off_show, pm_qos_no_power_off_store);
+
+static ssize_t pm_qos_remote_wakeup_show(struct device *dev,
+					 struct device_attribute *attr,
+					 char *buf)
+{
+	return sprintf(buf, "%d\n", !!(dev_pm_qos_requested_flags(dev)
+					& PM_QOS_FLAG_REMOTE_WAKEUP));
+}
+
+static ssize_t pm_qos_remote_wakeup_store(struct device *dev,
+					  struct device_attribute *attr,
+					  const char *buf, size_t n)
+{
+	int ret;
+
+	if (kstrtoint(buf, 0, &ret))
+		return -EINVAL;
+
+	if (ret != 0 && ret != 1)
+		return -EINVAL;
+
+	ret = dev_pm_qos_update_flags(dev, PM_QOS_FLAG_REMOTE_WAKEUP, ret);
+	return ret < 0 ? ret : n;
+}
+
+static DEVICE_ATTR(pm_qos_remote_wakeup, 0644,
+		   pm_qos_remote_wakeup_show, pm_qos_remote_wakeup_store);
+#endif /* CONFIG_PM_RUNTIME */
+
+#ifdef CONFIG_PM_SLEEP
+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 ssize_t wakeup_count_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	unsigned long count = 0;
+	bool enabled = false;
+
+	spin_lock_irq(&dev->power.lock);
+	if (dev->power.wakeup) {
+		count = dev->power.wakeup->event_count;
+		enabled = true;
+	}
+	spin_unlock_irq(&dev->power.lock);
+	return enabled ? sprintf(buf, "%lu\n", count) : sprintf(buf, "\n");
+}
+
+static DEVICE_ATTR(wakeup_count, 0444, wakeup_count_show, NULL);
+
+static ssize_t wakeup_active_count_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	unsigned long count = 0;
+	bool enabled = false;
+
+	spin_lock_irq(&dev->power.lock);
+	if (dev->power.wakeup) {
+		count = dev->power.wakeup->active_count;
+		enabled = true;
+	}
+	spin_unlock_irq(&dev->power.lock);
+	return enabled ? sprintf(buf, "%lu\n", count) : sprintf(buf, "\n");
+}
+
+static DEVICE_ATTR(wakeup_active_count, 0444, wakeup_active_count_show, NULL);
+
+static ssize_t wakeup_abort_count_show(struct device *dev,
+					struct device_attribute *attr,
+					char *buf)
+{
+	unsigned long count = 0;
+	bool enabled = false;
+
+	spin_lock_irq(&dev->power.lock);
+	if (dev->power.wakeup) {
+		count = dev->power.wakeup->wakeup_count;
+		enabled = true;
+	}
+	spin_unlock_irq(&dev->power.lock);
+	return enabled ? sprintf(buf, "%lu\n", count) : sprintf(buf, "\n");
+}
+
+static DEVICE_ATTR(wakeup_abort_count, 0444, wakeup_abort_count_show, NULL);
+
+static ssize_t wakeup_expire_count_show(struct device *dev,
+					struct device_attribute *attr,
+					char *buf)
+{
+	unsigned long count = 0;
+	bool enabled = false;
+
+	spin_lock_irq(&dev->power.lock);
+	if (dev->power.wakeup) {
+		count = dev->power.wakeup->expire_count;
+		enabled = true;
+	}
+	spin_unlock_irq(&dev->power.lock);
+	return enabled ? sprintf(buf, "%lu\n", count) : sprintf(buf, "\n");
+}
+
+static DEVICE_ATTR(wakeup_expire_count, 0444, wakeup_expire_count_show, NULL);
+
+static ssize_t wakeup_active_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	unsigned int active = 0;
+	bool enabled = false;
+
+	spin_lock_irq(&dev->power.lock);
+	if (dev->power.wakeup) {
+		active = dev->power.wakeup->active;
+		enabled = true;
+	}
+	spin_unlock_irq(&dev->power.lock);
+	return enabled ? sprintf(buf, "%u\n", active) : sprintf(buf, "\n");
+}
+
+static DEVICE_ATTR(wakeup_active, 0444, wakeup_active_show, NULL);
+
+static ssize_t wakeup_total_time_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	s64 msec = 0;
+	bool enabled = false;
+
+	spin_lock_irq(&dev->power.lock);
+	if (dev->power.wakeup) {
+		msec = ktime_to_ms(dev->power.wakeup->total_time);
+		enabled = true;
+	}
+	spin_unlock_irq(&dev->power.lock);
+	return enabled ? sprintf(buf, "%lld\n", msec) : sprintf(buf, "\n");
+}
+
+static DEVICE_ATTR(wakeup_total_time_ms, 0444, wakeup_total_time_show, NULL);
+
+static ssize_t wakeup_max_time_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	s64 msec = 0;
+	bool enabled = false;
+
+	spin_lock_irq(&dev->power.lock);
+	if (dev->power.wakeup) {
+		msec = ktime_to_ms(dev->power.wakeup->max_time);
+		enabled = true;
+	}
+	spin_unlock_irq(&dev->power.lock);
+	return enabled ? sprintf(buf, "%lld\n", msec) : sprintf(buf, "\n");
+}
+
+static DEVICE_ATTR(wakeup_max_time_ms, 0444, wakeup_max_time_show, NULL);
+
+static ssize_t wakeup_last_time_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	s64 msec = 0;
+	bool enabled = false;
+
+	spin_lock_irq(&dev->power.lock);
+	if (dev->power.wakeup) {
+		msec = ktime_to_ms(dev->power.wakeup->last_time);
+		enabled = true;
+	}
+	spin_unlock_irq(&dev->power.lock);
+	return enabled ? sprintf(buf, "%lld\n", msec) : sprintf(buf, "\n");
+}
+
+static DEVICE_ATTR(wakeup_last_time_ms, 0444, wakeup_last_time_show, NULL);
+
+#ifdef CONFIG_PM_AUTOSLEEP
+static ssize_t wakeup_prevent_sleep_time_show(struct device *dev,
+					      struct device_attribute *attr,
+					      char *buf)
+{
+	s64 msec = 0;
+	bool enabled = false;
+
+	spin_lock_irq(&dev->power.lock);
+	if (dev->power.wakeup) {
+		msec = ktime_to_ms(dev->power.wakeup->prevent_sleep_time);
+		enabled = true;
+	}
+	spin_unlock_irq(&dev->power.lock);
+	return enabled ? sprintf(buf, "%lld\n", msec) : sprintf(buf, "\n");
+}
+
+static DEVICE_ATTR(wakeup_prevent_sleep_time_ms, 0444,
+		   wakeup_prevent_sleep_time_show, NULL);
+#endif /* CONFIG_PM_AUTOSLEEP */
+
+static ssize_t dark_resume_active_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	return dev->power.use_dark_resume ? sprintf(buf, "%s\n", enabled) :
+			sprintf(buf, "%s\n", disabled);
+}
+
+static ssize_t dark_resume_active_store(struct device *dev,
+				struct device_attribute *attr,
+				const char *buf, size_t n)
+{
+	if (sysfs_streq(enabled, buf))
+		dev_dark_resume_set_active(dev, true);
+	else if (sysfs_streq(disabled, buf))
+		dev_dark_resume_set_active(dev, false);
+	else
+		return -EINVAL;
+	return n;
+}
+
+static DEVICE_ATTR(dark_resume_active, 0644,
+		   dark_resume_active_show, dark_resume_active_store);
+
+static ssize_t dark_resume_source_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	return dev->power.dark_resume && dev->power.dark_resume->is_source ?
+			sprintf(buf, "%s\n", enabled) :
+			sprintf(buf, "%s\n", disabled);
+}
+
+static ssize_t dark_resume_source_store(struct device *dev,
+				struct device_attribute *attr,
+				const char *buf, size_t n)
+{
+	if (sysfs_streq(enabled, buf) && dev->power.dark_resume)
+		dev_dark_resume_set_source(dev, true);
+	else if (sysfs_streq(disabled, buf) && dev->power.dark_resume)
+		dev_dark_resume_set_source(dev, false);
+	else
+		return -EINVAL;
+	return n;
+}
+
+static DEVICE_ATTR(dark_resume_source, 0644,
+		   dark_resume_source_show, dark_resume_source_store);
+
+#endif /* CONFIG_PM_SLEEP */
+
+#ifdef CONFIG_PM_ADVANCED_DEBUG
+#ifdef CONFIG_PM_RUNTIME
+
+static ssize_t rtpm_usagecount_show(struct device *dev,
+				    struct device_attribute *attr, char *buf)
+{
+	return sprintf(buf, "%d\n", atomic_read(&dev->power.usage_count));
+}
+
+static ssize_t rtpm_children_show(struct device *dev,
+				  struct device_attribute *attr, char *buf)
+{
+	return sprintf(buf, "%d\n", dev->power.ignore_children ?
+		0 : atomic_read(&dev->power.child_count));
+}
+
+static ssize_t rtpm_enabled_show(struct device *dev,
+				 struct device_attribute *attr, char *buf)
+{
+	if ((dev->power.disable_depth) && (dev->power.runtime_auto == false))
+		return sprintf(buf, "disabled & forbidden\n");
+	else if (dev->power.disable_depth)
+		return sprintf(buf, "disabled\n");
+	else if (dev->power.runtime_auto == false)
+		return sprintf(buf, "forbidden\n");
+	return sprintf(buf, "enabled\n");
+}
+
+static DEVICE_ATTR(runtime_usage, 0444, rtpm_usagecount_show, NULL);
+static DEVICE_ATTR(runtime_active_kids, 0444, rtpm_children_show, NULL);
+static DEVICE_ATTR(runtime_enabled, 0444, rtpm_enabled_show, NULL);
+
+#endif
+
+#ifdef CONFIG_PM_SLEEP
+
+static ssize_t async_show(struct device *dev, struct device_attribute *attr,
+			  char *buf)
+{
+	return sprintf(buf, "%s\n",
+			device_async_suspend_enabled(dev) ? enabled : disabled);
+}
+
+static ssize_t async_store(struct device *dev, struct device_attribute *attr,
+			   const char *buf, size_t n)
+{
+	char *cp;
+	int len = n;
+
+	cp = memchr(buf, '\n', n);
+	if (cp)
+		len = cp - buf;
+	if (len == sizeof enabled - 1 && strncmp(buf, enabled, len) == 0)
+		device_enable_async_suspend(dev);
+	else if (len == sizeof disabled - 1 && strncmp(buf, disabled, len) == 0)
+		device_disable_async_suspend(dev);
+	else
+		return -EINVAL;
+	return n;
+}
+
+static DEVICE_ATTR(async, 0644, async_show, async_store);
+
+#endif
+#endif /* CONFIG_PM_ADVANCED_DEBUG */
+
+static struct attribute *power_attrs[] = {
+#ifdef CONFIG_PM_ADVANCED_DEBUG
+#ifdef CONFIG_PM_SLEEP
+	&dev_attr_async.attr,
+#endif
+#ifdef CONFIG_PM_RUNTIME
+	&dev_attr_runtime_status.attr,
+	&dev_attr_runtime_usage.attr,
+	&dev_attr_runtime_active_kids.attr,
+	&dev_attr_runtime_enabled.attr,
+#endif
+#endif /* CONFIG_PM_ADVANCED_DEBUG */
+	NULL,
+};
+static struct attribute_group pm_attr_group = {
+	.name	= power_group_name,
+	.attrs	= power_attrs,
+};
+
+static struct attribute *wakeup_attrs[] = {
+#ifdef CONFIG_PM_SLEEP
+	&dev_attr_wakeup.attr,
+	&dev_attr_wakeup_count.attr,
+	&dev_attr_wakeup_active_count.attr,
+	&dev_attr_wakeup_abort_count.attr,
+	&dev_attr_wakeup_expire_count.attr,
+	&dev_attr_wakeup_active.attr,
+	&dev_attr_wakeup_total_time_ms.attr,
+	&dev_attr_wakeup_max_time_ms.attr,
+	&dev_attr_wakeup_last_time_ms.attr,
+#ifdef CONFIG_PM_AUTOSLEEP
+	&dev_attr_wakeup_prevent_sleep_time_ms.attr,
+#endif
+#endif /* CONFIG_PM_SLEEP */
+	NULL,
+};
+static struct attribute_group pm_wakeup_attr_group = {
+	.name	= power_group_name,
+	.attrs	= wakeup_attrs,
+};
+
+static struct attribute *dark_resume_attrs[] = {
+#ifdef CONFIG_PM_SLEEP
+	&dev_attr_dark_resume_active.attr,
+	&dev_attr_dark_resume_source.attr,
+#endif
+	NULL,
+};
+static struct attribute_group pm_dark_resume_attr_group = {
+	.name	= power_group_name,
+	.attrs	= dark_resume_attrs,
+};
+
+static struct attribute *runtime_attrs[] = {
+#ifdef CONFIG_PM_RUNTIME
+#ifndef CONFIG_PM_ADVANCED_DEBUG
+	&dev_attr_runtime_status.attr,
+#endif
+	&dev_attr_control.attr,
+	&dev_attr_runtime_suspended_time.attr,
+	&dev_attr_runtime_active_time.attr,
+	&dev_attr_autosuspend_delay_ms.attr,
+#endif /* CONFIG_PM_RUNTIME */
+	NULL,
+};
+static struct attribute_group pm_runtime_attr_group = {
+	.name	= power_group_name,
+	.attrs	= runtime_attrs,
+};
+
+static struct attribute *pm_qos_latency_attrs[] = {
+#ifdef CONFIG_PM_RUNTIME
+	&dev_attr_pm_qos_resume_latency_us.attr,
+#endif /* CONFIG_PM_RUNTIME */
+	NULL,
+};
+static struct attribute_group pm_qos_latency_attr_group = {
+	.name	= power_group_name,
+	.attrs	= pm_qos_latency_attrs,
+};
+
+static struct attribute *pm_qos_flags_attrs[] = {
+#ifdef CONFIG_PM_RUNTIME
+	&dev_attr_pm_qos_no_power_off.attr,
+	&dev_attr_pm_qos_remote_wakeup.attr,
+#endif /* CONFIG_PM_RUNTIME */
+	NULL,
+};
+static struct attribute_group pm_qos_flags_attr_group = {
+	.name	= power_group_name,
+	.attrs	= pm_qos_flags_attrs,
+};
+
+int dpm_sysfs_add(struct device *dev)
+{
+	int rc;
+
+	rc = sysfs_create_group(&dev->kobj, &pm_attr_group);
+	if (rc)
+		return rc;
+
+	if (pm_runtime_callbacks_present(dev)) {
+		rc = sysfs_merge_group(&dev->kobj, &pm_runtime_attr_group);
+		if (rc)
+			goto err_out;
+	}
+
+	if (device_can_wakeup(dev)) {
+		rc = sysfs_merge_group(&dev->kobj, &pm_wakeup_attr_group);
+		if (rc) {
+			if (pm_runtime_callbacks_present(dev))
+				sysfs_unmerge_group(&dev->kobj,
+						    &pm_runtime_attr_group);
+			goto err_out;
+		}
+	}
+	return 0;
+
+ err_out:
+	sysfs_remove_group(&dev->kobj, &pm_attr_group);
+	return rc;
+}
+
+int wakeup_sysfs_add(struct device *dev)
+{
+	return sysfs_merge_group(&dev->kobj, &pm_wakeup_attr_group);
+}
+
+void wakeup_sysfs_remove(struct device *dev)
+{
+	sysfs_unmerge_group(&dev->kobj, &pm_wakeup_attr_group);
+}
+
+int pm_qos_sysfs_add_latency(struct device *dev)
+{
+	return sysfs_merge_group(&dev->kobj, &pm_qos_latency_attr_group);
+}
+
+void pm_qos_sysfs_remove_latency(struct device *dev)
+{
+	sysfs_unmerge_group(&dev->kobj, &pm_qos_latency_attr_group);
+}
+
+int pm_qos_sysfs_add_flags(struct device *dev)
+{
+	return sysfs_merge_group(&dev->kobj, &pm_qos_flags_attr_group);
+}
+
+void pm_qos_sysfs_remove_flags(struct device *dev)
+{
+	sysfs_unmerge_group(&dev->kobj, &pm_qos_flags_attr_group);
+}
+
+void rpm_sysfs_remove(struct device *dev)
+{
+	sysfs_unmerge_group(&dev->kobj, &pm_runtime_attr_group);
+}
+
+void dpm_sysfs_remove(struct device *dev)
+{
+	dev_pm_qos_constraints_destroy(dev);
+	rpm_sysfs_remove(dev);
+	sysfs_unmerge_group(&dev->kobj, &pm_wakeup_attr_group);
+	sysfs_remove_group(&dev->kobj, &pm_attr_group);
+}
+
+int dark_resume_sysfs_add(struct device *dev)
+{
+	return sysfs_merge_group(&dev->kobj, &pm_dark_resume_attr_group);
+}
+
+void dark_resume_sysfs_remove(struct device *dev)
+{
+	sysfs_unmerge_group(&dev->kobj, &pm_dark_resume_attr_group);
+}

drivers/base/power/trace.c

@@ -0,0 +1,266 @@
+/*
+ * drivers/base/power/trace.c
+ *
+ * Copyright (C) 2006 Linus Torvalds
+ *
+ * Trace facility for suspend/resume problems, when none of the
+ * devices may be working.
+ */
+
+#include <linux/resume-trace.h>
+#include <linux/export.h>
+#include <linux/rtc.h>
+
+#include <asm/rtc.h>
+
+#include "power.h"
+
+/*
+ * Horrid, horrid, horrid.
+ *
+ * It turns out that the _only_ piece of hardware that actually
+ * keeps its value across a hard boot (and, more importantly, the
+ * POST init sequence) is literally the realtime clock.
+ *
+ * Never mind that an RTC chip has 114 bytes (and often a whole
+ * other bank of an additional 128 bytes) of nice SRAM that is
+ * _designed_ to keep data - the POST will clear it. So we literally
+ * can just use the few bytes of actual time data, which means that
+ * we're really limited.
+ *
+ * It means, for example, that we can't use the seconds at all
+ * (since the time between the hang and the boot might be more
+ * than a minute), and we'd better not depend on the low bits of
+ * the minutes either.
+ *
+ * There are the wday fields etc, but I wouldn't guarantee those
+ * are dependable either. And if the date isn't valid, either the
+ * hw or POST will do strange things.
+ *
+ * So we're left with:
+ *  - year: 0-99
+ *  - month: 0-11
+ *  - day-of-month: 1-28
+ *  - hour: 0-23
+ *  - min: (0-30)*2
+ *
+ * Giving us a total range of 0-16128000 (0xf61800), ie less
+ * than 24 bits of actual data we can save across reboots.
+ *
+ * And if your box can't boot in less than three minutes,
+ * you're screwed.
+ *
+ * Now, almost 24 bits of data is pitifully small, so we need
+ * to be pretty dense if we want to use it for anything nice.
+ * What we do is that instead of saving off nice readable info,
+ * we save off _hashes_ of information that we can hopefully
+ * regenerate after the reboot.
+ *
+ * In particular, this means that we might be unlucky, and hit
+ * a case where we have a hash collision, and we end up not
+ * being able to tell for certain exactly which case happened.
+ * But that's hopefully unlikely.
+ *
+ * What we do is to take the bits we can fit, and split them
+ * into three parts (16*997*1009 = 16095568), and use the values
+ * for:
+ *  - 0-15: user-settable
+ *  - 0-996: file + line number
+ *  - 0-1008: device
+ */
+#define USERHASH (16)
+#define FILEHASH (997)
+#define DEVHASH (1009)
+
+#define DEVSEED (7919)
+
+static unsigned int dev_hash_value;
+
+static int set_magic_time(unsigned int user, unsigned int file, unsigned int device)
+{
+	unsigned int n = user + USERHASH*(file + FILEHASH*device);
+
+	// June 7th, 2006
+	static struct rtc_time time = {
+		.tm_sec = 0,
+		.tm_min = 0,
+		.tm_hour = 0,
+		.tm_mday = 7,
+		.tm_mon = 5,	// June - counting from zero
+		.tm_year = 106,
+		.tm_wday = 3,
+		.tm_yday = 160,
+		.tm_isdst = 1
+	};
+
+	time.tm_year = (n % 100);
+	n /= 100;
+	time.tm_mon = (n % 12);
+	n /= 12;
+	time.tm_mday = (n % 28) + 1;
+	n /= 28;
+	time.tm_hour = (n % 24);
+	n /= 24;
+	time.tm_min = (n % 20) * 3;
+	n /= 20;
+	set_rtc_time(&time);
+	return n ? -1 : 0;
+}
+
+static unsigned int read_magic_time(void)
+{
+	struct rtc_time time;
+	unsigned int val;
+
+	get_rtc_time(&time);
+	pr_info("RTC time: %2d:%02d:%02d, date: %02d/%02d/%02d\n",
+		time.tm_hour, time.tm_min, time.tm_sec,
+		time.tm_mon + 1, time.tm_mday, time.tm_year % 100);
+	val = time.tm_year;				/* 100 years */
+	if (val > 100)
+		val -= 100;
+	val += time.tm_mon * 100;			/* 12 months */
+	val += (time.tm_mday-1) * 100 * 12;		/* 28 month-days */
+	val += time.tm_hour * 100 * 12 * 28;		/* 24 hours */
+	val += (time.tm_min / 3) * 100 * 12 * 28 * 24;	/* 20 3-minute intervals */
+	return val;
+}
+
+/*
+ * This is just the sdbm hash function with a user-supplied
+ * seed and final size parameter.
+ */
+static unsigned int hash_string(unsigned int seed, const char *data, unsigned int mod)
+{
+	unsigned char c;
+	while ((c = *data++) != 0) {
+		seed = (seed << 16) + (seed << 6) - seed + c;
+	}
+	return seed % mod;
+}
+
+void set_trace_device(struct device *dev)
+{
+	dev_hash_value = hash_string(DEVSEED, dev_name(dev), DEVHASH);
+}
+EXPORT_SYMBOL(set_trace_device);
+
+/*
+ * We could just take the "tracedata" index into the .tracedata
+ * section instead. Generating a hash of the data gives us a
+ * chance to work across kernel versions, and perhaps more
+ * importantly it also gives us valid/invalid check (ie we will
+ * likely not give totally bogus reports - if the hash matches,
+ * it's not any guarantee, but it's a high _likelihood_ that
+ * the match is valid).
+ */
+void generate_resume_trace(const void *tracedata, unsigned int user)
+{
+	unsigned short lineno = *(unsigned short *)tracedata;
+	const char *file = *(const char **)(tracedata + 2);
+	unsigned int user_hash_value, file_hash_value;
+
+	user_hash_value = user % USERHASH;
+	file_hash_value = hash_string(lineno, file, FILEHASH);
+	set_magic_time(user_hash_value, file_hash_value, dev_hash_value);
+}
+EXPORT_SYMBOL(generate_resume_trace);
+
+extern char __tracedata_start, __tracedata_end;
+static int show_file_hash(unsigned int value)
+{
+	int match;
+	char *tracedata;
+
+	match = 0;
+	for (tracedata = &__tracedata_start ; tracedata < &__tracedata_end ;
+			tracedata += 2 + sizeof(unsigned long)) {
+		unsigned short lineno = *(unsigned short *)tracedata;
+		const char *file = *(const char **)(tracedata + 2);
+		unsigned int hash = hash_string(lineno, file, FILEHASH);
+		if (hash != value)
+			continue;
+		pr_info("  hash matches %s:%u\n", file, lineno);
+		match++;
+	}
+	return match;
+}
+
+static int show_dev_hash(unsigned int value)
+{
+	int match = 0;
+	struct list_head *entry;
+
+	device_pm_lock();
+	entry = dpm_list.prev;
+	while (entry != &dpm_list) {
+		struct device * dev = to_device(entry);
+		unsigned int hash = hash_string(DEVSEED, dev_name(dev), DEVHASH);
+		if (hash == value) {
+			dev_info(dev, "hash matches\n");
+			match++;
+		}
+		entry = entry->prev;
+	}
+	device_pm_unlock();
+	return match;
+}
+
+static unsigned int hash_value_early_read;
+
+int show_trace_dev_match(char *buf, size_t size)
+{
+	unsigned int value = hash_value_early_read / (USERHASH * FILEHASH);
+	int ret = 0;
+	struct list_head *entry;
+
+	/*
+	 * It's possible that multiple devices will match the hash and we can't
+	 * tell which is the culprit, so it's best to output them all.
+	 */
+	device_pm_lock();
+	entry = dpm_list.prev;
+	while (size && entry != &dpm_list) {
+		struct device *dev = to_device(entry);
+		unsigned int hash = hash_string(DEVSEED, dev_name(dev),
+						DEVHASH);
+		if (hash == value) {
+			int len = snprintf(buf, size, "%s\n",
+					    dev_driver_string(dev));
+			if (len > size)
+				len = size;
+			buf += len;
+			ret += len;
+			size -= len;
+		}
+		entry = entry->prev;
+	}
+	device_pm_unlock();
+	return ret;
+}
+
+static int early_resume_init(void)
+{
+	hash_value_early_read = read_magic_time();
+	return 0;
+}
+
+static int late_resume_init(void)
+{
+	unsigned int val = hash_value_early_read;
+	unsigned int user, file, dev;
+
+	user = val % USERHASH;
+	val = val / USERHASH;
+	file = val % FILEHASH;
+	val = val / FILEHASH;
+	dev = val /* % DEVHASH */;
+
+	pr_info("  Magic number: %d:%d:%d\n", user, file, dev);
+	show_file_hash(file);
+	show_dev_hash(dev);
+	return 0;
+}
+
+core_initcall(early_resume_init);
+late_initcall(late_resume_init);

drivers/base/power/wakeup.c

@@ -0,0 +1,901 @@
+/*
+ * drivers/base/power/wakeup.c - System wakeup events framework
+ *
+ * Copyright (c) 2010 Rafael J. Wysocki <rjw@sisk.pl>, Novell Inc.
+ *
+ * This file is released under the GPLv2.
+ */
+
+#include <linux/device.h>
+#include <linux/slab.h>
+#include <linux/sched.h>
+#include <linux/capability.h>
+#include <linux/export.h>
+#include <linux/suspend.h>
+#include <linux/seq_file.h>
+#include <linux/debugfs.h>
+#include <trace/events/power.h>
+
+#include "power.h"
+
+/*
+ * If set, the suspend/hibernate code will abort transitions to a sleep state
+ * if wakeup events are registered during or immediately before the transition.
+ */
+bool events_check_enabled __read_mostly;
+
+/*
+ * Combined counters of registered wakeup events and wakeup events in progress.
+ * They need to be modified together atomically, so it's better to use one
+ * atomic variable to hold them both.
+ */
+static atomic_t combined_event_count = ATOMIC_INIT(0);
+
+#define IN_PROGRESS_BITS	(sizeof(int) * 4)
+#define MAX_IN_PROGRESS		((1 << IN_PROGRESS_BITS) - 1)
+
+static void split_counters(unsigned int *cnt, unsigned int *inpr)
+{
+	unsigned int comb = atomic_read(&combined_event_count);
+
+	*cnt = (comb >> IN_PROGRESS_BITS);
+	*inpr = comb & MAX_IN_PROGRESS;
+}
+
+/* A preserved old value of the events counter. */
+static unsigned int saved_count;
+
+static DEFINE_SPINLOCK(events_lock);
+
+static void pm_wakeup_timer_fn(unsigned long data);
+
+static LIST_HEAD(wakeup_sources);
+
+static DECLARE_WAIT_QUEUE_HEAD(wakeup_count_wait_queue);
+
+/**
+ * wakeup_source_prepare - Prepare a new wakeup source for initialization.
+ * @ws: Wakeup source to prepare.
+ * @name: Pointer to the name of the new wakeup source.
+ *
+ * Callers must ensure that the @name string won't be freed when @ws is still in
+ * use.
+ */
+void wakeup_source_prepare(struct wakeup_source *ws, const char *name)
+{
+	if (ws) {
+		memset(ws, 0, sizeof(*ws));
+		ws->name = name;
+	}
+}
+EXPORT_SYMBOL_GPL(wakeup_source_prepare);
+
+/**
+ * wakeup_source_create - Create a struct wakeup_source object.
+ * @name: Name of the new wakeup source.
+ */
+struct wakeup_source *wakeup_source_create(const char *name)
+{
+	struct wakeup_source *ws;
+
+	ws = kmalloc(sizeof(*ws), GFP_KERNEL);
+	if (!ws)
+		return NULL;
+
+	wakeup_source_prepare(ws, name ? kstrdup(name, GFP_KERNEL) : NULL);
+	return ws;
+}
+EXPORT_SYMBOL_GPL(wakeup_source_create);
+
+/**
+ * wakeup_source_drop - Prepare a struct wakeup_source object for destruction.
+ * @ws: Wakeup source to prepare for destruction.
+ *
+ * Callers must ensure that __pm_stay_awake() or __pm_wakeup_event() will never
+ * be run in parallel with this function for the same wakeup source object.
+ */
+void wakeup_source_drop(struct wakeup_source *ws)
+{
+	if (!ws)
+		return;
+
+	del_timer_sync(&ws->timer);
+	__pm_relax(ws);
+}
+EXPORT_SYMBOL_GPL(wakeup_source_drop);
+
+/**
+ * wakeup_source_destroy - Destroy a struct wakeup_source object.
+ * @ws: Wakeup source to destroy.
+ *
+ * Use only for wakeup source objects created with wakeup_source_create().
+ */
+void wakeup_source_destroy(struct wakeup_source *ws)
+{
+	if (!ws)
+		return;
+
+	wakeup_source_drop(ws);
+	kfree(ws->name);
+	kfree(ws);
+}
+EXPORT_SYMBOL_GPL(wakeup_source_destroy);
+
+/**
+ * wakeup_source_add - Add given object to the list of wakeup sources.
+ * @ws: Wakeup source object to add to the list.
+ */
+void wakeup_source_add(struct wakeup_source *ws)
+{
+	unsigned long flags;
+
+	if (WARN_ON(!ws))
+		return;
+
+	spin_lock_init(&ws->lock);
+	setup_timer(&ws->timer, pm_wakeup_timer_fn, (unsigned long)ws);
+	ws->active = false;
+	ws->last_time = ktime_get();
+
+	spin_lock_irqsave(&events_lock, flags);
+	list_add_rcu(&ws->entry, &wakeup_sources);
+	spin_unlock_irqrestore(&events_lock, flags);
+}
+EXPORT_SYMBOL_GPL(wakeup_source_add);
+
+/**
+ * wakeup_source_remove - Remove given object from the wakeup sources list.
+ * @ws: Wakeup source object to remove from the list.
+ */
+void wakeup_source_remove(struct wakeup_source *ws)
+{
+	unsigned long flags;
+
+	if (WARN_ON(!ws))
+		return;
+
+	spin_lock_irqsave(&events_lock, flags);
+	list_del_rcu(&ws->entry);
+	spin_unlock_irqrestore(&events_lock, flags);
+	synchronize_rcu();
+}
+EXPORT_SYMBOL_GPL(wakeup_source_remove);
+
+/**
+ * wakeup_source_register - Create wakeup source and add it to the list.
+ * @name: Name of the wakeup source to register.
+ */
+struct wakeup_source *wakeup_source_register(const char *name)
+{
+	struct wakeup_source *ws;
+
+	ws = wakeup_source_create(name);
+	if (ws)
+		wakeup_source_add(ws);
+
+	return ws;
+}
+EXPORT_SYMBOL_GPL(wakeup_source_register);
+
+/**
+ * wakeup_source_unregister - Remove wakeup source from the list and remove it.
+ * @ws: Wakeup source object to unregister.
+ */
+void wakeup_source_unregister(struct wakeup_source *ws)
+{
+	if (ws) {
+		wakeup_source_remove(ws);
+		wakeup_source_destroy(ws);
+	}
+}
+EXPORT_SYMBOL_GPL(wakeup_source_unregister);
+
+/**
+ * device_wakeup_attach - Attach a wakeup source object to a device object.
+ * @dev: Device to handle.
+ * @ws: Wakeup source object to attach to @dev.
+ *
+ * This causes @dev to be treated as a wakeup device.
+ */
+static int device_wakeup_attach(struct device *dev, struct wakeup_source *ws)
+{
+	spin_lock_irq(&dev->power.lock);
+	if (dev->power.wakeup) {
+		spin_unlock_irq(&dev->power.lock);
+		return -EEXIST;
+	}
+	dev->power.wakeup = ws;
+	spin_unlock_irq(&dev->power.lock);
+	return 0;
+}
+
+/**
+ * device_wakeup_enable - Enable given device to be a wakeup source.
+ * @dev: Device to handle.
+ *
+ * Create a wakeup source object, register it and attach it to @dev.
+ */
+int device_wakeup_enable(struct device *dev)
+{
+	struct wakeup_source *ws;
+	int ret;
+
+	if (!dev || !dev->power.can_wakeup)
+		return -EINVAL;
+
+	ws = wakeup_source_register(dev_name(dev));
+	if (!ws)
+		return -ENOMEM;
+
+	ret = device_wakeup_attach(dev, ws);
+	if (ret)
+		wakeup_source_unregister(ws);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(device_wakeup_enable);
+
+/**
+ * device_wakeup_detach - Detach a device's wakeup source object from it.
+ * @dev: Device to detach the wakeup source object from.
+ *
+ * After it returns, @dev will not be treated as a wakeup device any more.
+ */
+static struct wakeup_source *device_wakeup_detach(struct device *dev)
+{
+	struct wakeup_source *ws;
+
+	spin_lock_irq(&dev->power.lock);
+	ws = dev->power.wakeup;
+	dev->power.wakeup = NULL;
+	spin_unlock_irq(&dev->power.lock);
+	return ws;
+}
+
+/**
+ * device_wakeup_disable - Do not regard a device as a wakeup source any more.
+ * @dev: Device to handle.
+ *
+ * Detach the @dev's wakeup source object from it, unregister this wakeup source
+ * object and destroy it.
+ */
+int device_wakeup_disable(struct device *dev)
+{
+	struct wakeup_source *ws;
+
+	if (!dev || !dev->power.can_wakeup)
+		return -EINVAL;
+
+	ws = device_wakeup_detach(dev);
+	if (ws)
+		wakeup_source_unregister(ws);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(device_wakeup_disable);
+
+/**
+ * device_set_wakeup_capable - Set/reset device wakeup capability flag.
+ * @dev: Device to handle.
+ * @capable: Whether or not @dev is capable of waking up the system from sleep.
+ *
+ * If @capable is set, set the @dev's power.can_wakeup flag and add its
+ * wakeup-related attributes to sysfs.  Otherwise, unset the @dev's
+ * power.can_wakeup flag and remove its wakeup-related attributes from sysfs.
+ *
+ * This function may sleep and it can't be called from any context where
+ * sleeping is not allowed.
+ */
+void device_set_wakeup_capable(struct device *dev, bool capable)
+{
+	if (!!dev->power.can_wakeup == !!capable)
+		return;
+
+	if (device_is_registered(dev) && !list_empty(&dev->power.entry)) {
+		if (capable) {
+			if (wakeup_sysfs_add(dev))
+				return;
+		} else {
+			wakeup_sysfs_remove(dev);
+		}
+	}
+	dev->power.can_wakeup = capable;
+}
+EXPORT_SYMBOL_GPL(device_set_wakeup_capable);
+
+/**
+ * device_init_wakeup - Device wakeup initialization.
+ * @dev: Device to handle.
+ * @enable: Whether or not to enable @dev as a wakeup device.
+ *
+ * By default, most devices should leave wakeup disabled.  The exceptions are
+ * devices that everyone expects to be wakeup sources: keyboards, power buttons,
+ * possibly network interfaces, etc.  Also, devices that don't generate their
+ * own wakeup requests but merely forward requests from one bus to another
+ * (like PCI bridges) should have wakeup enabled by default.
+ */
+int device_init_wakeup(struct device *dev, bool enable)
+{
+	int ret = 0;
+
+	if (enable) {
+		device_set_wakeup_capable(dev, true);
+		ret = device_wakeup_enable(dev);
+	} else {
+		device_set_wakeup_capable(dev, false);
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(device_init_wakeup);
+
+/**
+ * device_set_wakeup_enable - Enable or disable a device to wake up the system.
+ * @dev: Device to handle.
+ */
+int device_set_wakeup_enable(struct device *dev, bool enable)
+{
+	if (!dev || !dev->power.can_wakeup)
+		return -EINVAL;
+
+	return enable ? device_wakeup_enable(dev) : device_wakeup_disable(dev);
+}
+EXPORT_SYMBOL_GPL(device_set_wakeup_enable);
+
+/*
+ * The functions below use the observation that each wakeup event starts a
+ * period in which the system should not be suspended.  The moment this period
+ * will end depends on how the wakeup event is going to be processed after being
+ * detected and all of the possible cases can be divided into two distinct
+ * groups.
+ *
+ * First, a wakeup event may be detected by the same functional unit that will
+ * carry out the entire processing of it and possibly will pass it to user space
+ * for further processing.  In that case the functional unit that has detected
+ * the event may later "close" the "no suspend" period associated with it
+ * directly as soon as it has been dealt with.  The pair of pm_stay_awake() and
+ * pm_relax(), balanced with each other, is supposed to be used in such
+ * situations.
+ *
+ * Second, a wakeup event may be detected by one functional unit and processed
+ * by another one.  In that case the unit that has detected it cannot really
+ * "close" the "no suspend" period associated with it, unless it knows in
+ * advance what's going to happen to the event during processing.  This
+ * knowledge, however, may not be available to it, so it can simply specify time
+ * to wait before the system can be suspended and pass it as the second
+ * argument of pm_wakeup_event().
+ *
+ * It is valid to call pm_relax() after pm_wakeup_event(), in which case the
+ * "no suspend" period will be ended either by the pm_relax(), or by the timer
+ * function executed when the timer expires, whichever comes first.
+ */
+
+/**
+ * wakup_source_activate - Mark given wakeup source as active.
+ * @ws: Wakeup source to handle.
+ *
+ * Update the @ws' statistics and, if @ws has just been activated, notify the PM
+ * core of the event by incrementing the counter of of wakeup events being
+ * processed.
+ */
+static void wakeup_source_activate(struct wakeup_source *ws)
+{
+	unsigned int cec;
+
+	/*
+	 * active wakeup source should bring the system
+	 * out of PM_SUSPEND_FREEZE state
+	 */
+	freeze_wake();
+
+	ws->active = true;
+	ws->active_count++;
+	ws->last_time = ktime_get();
+	if (ws->autosleep_enabled)
+		ws->start_prevent_time = ws->last_time;
+
+	/* Increment the counter of events in progress. */
+	cec = atomic_inc_return(&combined_event_count);
+
+	trace_wakeup_source_activate(ws->name, cec);
+}
+
+/**
+ * wakeup_source_report_event - Report wakeup event using the given source.
+ * @ws: Wakeup source to report the event for.
+ */
+static void wakeup_source_report_event(struct wakeup_source *ws)
+{
+	ws->event_count++;
+	/* This is racy, but the counter is approximate anyway. */
+	if (events_check_enabled)
+		ws->wakeup_count++;
+
+	if (!ws->active)
+		wakeup_source_activate(ws);
+}
+
+/**
+ * __pm_stay_awake - Notify the PM core of a wakeup event.
+ * @ws: Wakeup source object associated with the source of the event.
+ *
+ * It is safe to call this function from interrupt context.
+ */
+void __pm_stay_awake(struct wakeup_source *ws)
+{
+	unsigned long flags;
+
+	if (!ws)
+		return;
+
+	spin_lock_irqsave(&ws->lock, flags);
+
+	wakeup_source_report_event(ws);
+	del_timer(&ws->timer);
+	ws->timer_expires = 0;
+
+	spin_unlock_irqrestore(&ws->lock, flags);
+}
+EXPORT_SYMBOL_GPL(__pm_stay_awake);
+
+/**
+ * pm_stay_awake - Notify the PM core that a wakeup event is being processed.
+ * @dev: Device the wakeup event is related to.
+ *
+ * Notify the PM core of a wakeup event (signaled by @dev) by calling
+ * __pm_stay_awake for the @dev's wakeup source object.
+ *
+ * Call this function after detecting of a wakeup event if pm_relax() is going
+ * to be called directly after processing the event (and possibly passing it to
+ * user space for further processing).
+ */
+void pm_stay_awake(struct device *dev)
+{
+	unsigned long flags;
+
+	if (!dev)
+		return;
+
+	spin_lock_irqsave(&dev->power.lock, flags);
+	__pm_stay_awake(dev->power.wakeup);
+	spin_unlock_irqrestore(&dev->power.lock, flags);
+}
+EXPORT_SYMBOL_GPL(pm_stay_awake);
+
+#ifdef CONFIG_PM_AUTOSLEEP
+static void update_prevent_sleep_time(struct wakeup_source *ws, ktime_t now)
+{
+	ktime_t delta = ktime_sub(now, ws->start_prevent_time);
+	ws->prevent_sleep_time = ktime_add(ws->prevent_sleep_time, delta);
+}
+#else
+static inline void update_prevent_sleep_time(struct wakeup_source *ws,
+					     ktime_t now) {}
+#endif
+
+/**
+ * wakup_source_deactivate - Mark given wakeup source as inactive.
+ * @ws: Wakeup source to handle.
+ *
+ * Update the @ws' statistics and notify the PM core that the wakeup source has
+ * become inactive by decrementing the counter of wakeup events being processed
+ * and incrementing the counter of registered wakeup events.
+ */
+static void wakeup_source_deactivate(struct wakeup_source *ws)
+{
+	unsigned int cnt, inpr, cec;
+	ktime_t duration;
+	ktime_t now;
+
+	ws->relax_count++;
+	/*
+	 * __pm_relax() may be called directly or from a timer function.
+	 * If it is called directly right after the timer function has been
+	 * started, but before the timer function calls __pm_relax(), it is
+	 * possible that __pm_stay_awake() will be called in the meantime and
+	 * will set ws->active.  Then, ws->active may be cleared immediately
+	 * by the __pm_relax() called from the timer function, but in such a
+	 * case ws->relax_count will be different from ws->active_count.
+	 */
+	if (ws->relax_count != ws->active_count) {
+		ws->relax_count--;
+		return;
+	}
+
+	ws->active = false;
+
+	now = ktime_get();
+	duration = ktime_sub(now, ws->last_time);
+	ws->total_time = ktime_add(ws->total_time, duration);
+	if (ktime_to_ns(duration) > ktime_to_ns(ws->max_time))
+		ws->max_time = duration;
+
+	ws->last_time = now;
+	del_timer(&ws->timer);
+	ws->timer_expires = 0;
+
+	if (ws->autosleep_enabled)
+		update_prevent_sleep_time(ws, now);
+
+	/*
+	 * Increment the counter of registered wakeup events and decrement the
+	 * couter of wakeup events in progress simultaneously.
+	 */
+	cec = atomic_add_return(MAX_IN_PROGRESS, &combined_event_count);
+	trace_wakeup_source_deactivate(ws->name, cec);
+
+	split_counters(&cnt, &inpr);
+	if (!inpr && waitqueue_active(&wakeup_count_wait_queue))
+		wake_up(&wakeup_count_wait_queue);
+}
+
+/**
+ * __pm_relax - Notify the PM core that processing of a wakeup event has ended.
+ * @ws: Wakeup source object associated with the source of the event.
+ *
+ * Call this function for wakeup events whose processing started with calling
+ * __pm_stay_awake().
+ *
+ * It is safe to call it from interrupt context.
+ */
+void __pm_relax(struct wakeup_source *ws)
+{
+	unsigned long flags;
+
+	if (!ws)
+		return;
+
+	spin_lock_irqsave(&ws->lock, flags);
+	if (ws->active)
+		wakeup_source_deactivate(ws);
+	spin_unlock_irqrestore(&ws->lock, flags);
+}
+EXPORT_SYMBOL_GPL(__pm_relax);
+
+/**
+ * pm_relax - Notify the PM core that processing of a wakeup event has ended.
+ * @dev: Device that signaled the event.
+ *
+ * Execute __pm_relax() for the @dev's wakeup source object.
+ */
+void pm_relax(struct device *dev)
+{
+	unsigned long flags;
+
+	if (!dev)
+		return;
+
+	spin_lock_irqsave(&dev->power.lock, flags);
+	__pm_relax(dev->power.wakeup);
+	spin_unlock_irqrestore(&dev->power.lock, flags);
+}
+EXPORT_SYMBOL_GPL(pm_relax);
+
+/**
+ * pm_wakeup_timer_fn - Delayed finalization of a wakeup event.
+ * @data: Address of the wakeup source object associated with the event source.
+ *
+ * Call wakeup_source_deactivate() for the wakeup source whose address is stored
+ * in @data if it is currently active and its timer has not been canceled and
+ * the expiration time of the timer is not in future.
+ */
+static void pm_wakeup_timer_fn(unsigned long data)
+{
+	struct wakeup_source *ws = (struct wakeup_source *)data;
+	unsigned long flags;
+
+	spin_lock_irqsave(&ws->lock, flags);
+
+	if (ws->active && ws->timer_expires
+	    && time_after_eq(jiffies, ws->timer_expires)) {
+		wakeup_source_deactivate(ws);
+		ws->expire_count++;
+	}
+
+	spin_unlock_irqrestore(&ws->lock, flags);
+}
+
+/**
+ * __pm_wakeup_event - Notify the PM core of a wakeup event.
+ * @ws: Wakeup source object associated with the event source.
+ * @msec: Anticipated event processing time (in milliseconds).
+ *
+ * Notify the PM core of a wakeup event whose source is @ws that will take
+ * approximately @msec milliseconds to be processed by the kernel.  If @ws is
+ * not active, activate it.  If @msec is nonzero, set up the @ws' timer to
+ * execute pm_wakeup_timer_fn() in future.
+ *
+ * It is safe to call this function from interrupt context.
+ */
+void __pm_wakeup_event(struct wakeup_source *ws, unsigned int msec)
+{
+	unsigned long flags;
+	unsigned long expires;
+
+	if (!ws)
+		return;
+
+	spin_lock_irqsave(&ws->lock, flags);
+
+	wakeup_source_report_event(ws);
+
+	if (!msec) {
+		wakeup_source_deactivate(ws);
+		goto unlock;
+	}
+
+	expires = jiffies + msecs_to_jiffies(msec);
+	if (!expires)
+		expires = 1;
+
+	if (!ws->timer_expires || time_after(expires, ws->timer_expires)) {
+		mod_timer(&ws->timer, expires);
+		ws->timer_expires = expires;
+	}
+
+ unlock:
+	spin_unlock_irqrestore(&ws->lock, flags);
+}
+EXPORT_SYMBOL_GPL(__pm_wakeup_event);
+
+
+/**
+ * pm_wakeup_event - Notify the PM core of a wakeup event.
+ * @dev: Device the wakeup event is related to.
+ * @msec: Anticipated event processing time (in milliseconds).
+ *
+ * Call __pm_wakeup_event() for the @dev's wakeup source object.
+ */
+void pm_wakeup_event(struct device *dev, unsigned int msec)
+{
+	unsigned long flags;
+
+	if (!dev)
+		return;
+
+	spin_lock_irqsave(&dev->power.lock, flags);
+	__pm_wakeup_event(dev->power.wakeup, msec);
+	spin_unlock_irqrestore(&dev->power.lock, flags);
+}
+EXPORT_SYMBOL_GPL(pm_wakeup_event);
+
+void pm_print_active_wakeup_sources(void)
+{
+	struct wakeup_source *ws;
+	int active = 0;
+	struct wakeup_source *last_activity_ws = NULL;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(ws, &wakeup_sources, entry) {
+		if (ws->active) {
+			pr_info("active wakeup source: %s\n", ws->name);
+			active = 1;
+		} else if (!active &&
+			   (!last_activity_ws ||
+			    ktime_to_ns(ws->last_time) >
+			    ktime_to_ns(last_activity_ws->last_time))) {
+			last_activity_ws = ws;
+		}
+	}
+
+	if (!active && last_activity_ws)
+		pr_info("last active wakeup source: %s\n",
+			last_activity_ws->name);
+	rcu_read_unlock();
+}
+EXPORT_SYMBOL_GPL(pm_print_active_wakeup_sources);
+
+/**
+ * pm_wakeup_pending - Check if power transition in progress should be aborted.
+ *
+ * Compare the current number of registered wakeup events with its preserved
+ * value from the past and return true if new wakeup events have been registered
+ * since the old value was stored.  Also return true if the current number of
+ * wakeup events being processed is different from zero.
+ */
+bool pm_wakeup_pending(void)
+{
+	unsigned long flags;
+	bool ret = false;
+
+	spin_lock_irqsave(&events_lock, flags);
+	if (events_check_enabled) {
+		unsigned int cnt, inpr;
+
+		split_counters(&cnt, &inpr);
+		ret = (cnt != saved_count || inpr > 0);
+		events_check_enabled = !ret;
+	}
+	spin_unlock_irqrestore(&events_lock, flags);
+
+	if (ret) {
+		pr_info("PM: Wakeup pending, aborting suspend\n");
+		pm_print_active_wakeup_sources();
+	}
+
+	return ret;
+}
+
+/**
+ * pm_get_wakeup_count - Read the number of registered wakeup events.
+ * @count: Address to store the value at.
+ * @block: Whether or not to block.
+ *
+ * Store the number of registered wakeup events at the address in @count.  If
+ * @block is set, block until the current number of wakeup events being
+ * processed is zero.
+ *
+ * Return 'false' if the current number of wakeup events being processed is
+ * nonzero.  Otherwise return 'true'.
+ */
+bool pm_get_wakeup_count(unsigned int *count, bool block)
+{
+	unsigned int cnt, inpr;
+
+	if (block) {
+		DEFINE_WAIT(wait);
+
+		for (;;) {
+			prepare_to_wait(&wakeup_count_wait_queue, &wait,
+					TASK_INTERRUPTIBLE);
+			split_counters(&cnt, &inpr);
+			if (inpr == 0 || signal_pending(current))
+				break;
+
+			schedule();
+		}
+		finish_wait(&wakeup_count_wait_queue, &wait);
+	}
+
+	split_counters(&cnt, &inpr);
+	*count = cnt;
+	return !inpr;
+}
+
+/**
+ * pm_save_wakeup_count - Save the current number of registered wakeup events.
+ * @count: Value to compare with the current number of registered wakeup events.
+ *
+ * If @count is equal to the current number of registered wakeup events and the
+ * current number of wakeup events being processed is zero, store @count as the
+ * old number of registered wakeup events for pm_check_wakeup_events(), enable
+ * wakeup events detection and return 'true'.  Otherwise disable wakeup events
+ * detection and return 'false'.
+ */
+bool pm_save_wakeup_count(unsigned int count)
+{
+	unsigned int cnt, inpr;
+	unsigned long flags;
+
+	events_check_enabled = false;
+	spin_lock_irqsave(&events_lock, flags);
+	split_counters(&cnt, &inpr);
+	if (cnt == count && inpr == 0) {
+		saved_count = count;
+		events_check_enabled = true;
+	}
+	spin_unlock_irqrestore(&events_lock, flags);
+	return events_check_enabled;
+}
+
+#ifdef CONFIG_PM_AUTOSLEEP
+/**
+ * pm_wakep_autosleep_enabled - Modify autosleep_enabled for all wakeup sources.
+ * @enabled: Whether to set or to clear the autosleep_enabled flags.
+ */
+void pm_wakep_autosleep_enabled(bool set)
+{
+	struct wakeup_source *ws;
+	ktime_t now = ktime_get();
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(ws, &wakeup_sources, entry) {
+		spin_lock_irq(&ws->lock);
+		if (ws->autosleep_enabled != set) {
+			ws->autosleep_enabled = set;
+			if (ws->active) {
+				if (set)
+					ws->start_prevent_time = now;
+				else
+					update_prevent_sleep_time(ws, now);
+			}
+		}
+		spin_unlock_irq(&ws->lock);
+	}
+	rcu_read_unlock();
+}
+#endif /* CONFIG_PM_AUTOSLEEP */
+
+static struct dentry *wakeup_sources_stats_dentry;
+
+/**
+ * print_wakeup_source_stats - Print wakeup source statistics information.
+ * @m: seq_file to print the statistics into.
+ * @ws: Wakeup source object to print the statistics for.
+ */
+static int print_wakeup_source_stats(struct seq_file *m,
+				     struct wakeup_source *ws)
+{
+	unsigned long flags;
+	ktime_t total_time;
+	ktime_t max_time;
+	unsigned long active_count;
+	ktime_t active_time;
+	ktime_t prevent_sleep_time;
+	int ret;
+
+	spin_lock_irqsave(&ws->lock, flags);
+
+	total_time = ws->total_time;
+	max_time = ws->max_time;
+	prevent_sleep_time = ws->prevent_sleep_time;
+	active_count = ws->active_count;
+	if (ws->active) {
+		ktime_t now = ktime_get();
+
+		active_time = ktime_sub(now, ws->last_time);
+		total_time = ktime_add(total_time, active_time);
+		if (active_time.tv64 > max_time.tv64)
+			max_time = active_time;
+
+		if (ws->autosleep_enabled)
+			prevent_sleep_time = ktime_add(prevent_sleep_time,
+				ktime_sub(now, ws->start_prevent_time));
+	} else {
+		active_time = ktime_set(0, 0);
+	}
+
+	ret = seq_printf(m, "%-12s\t%lu\t\t%lu\t\t%lu\t\t%lu\t\t"
+			"%lld\t\t%lld\t\t%lld\t\t%lld\t\t%lld\n",
+			ws->name, active_count, ws->event_count,
+			ws->wakeup_count, ws->expire_count,
+			ktime_to_ms(active_time), ktime_to_ms(total_time),
+			ktime_to_ms(max_time), ktime_to_ms(ws->last_time),
+			ktime_to_ms(prevent_sleep_time));
+
+	spin_unlock_irqrestore(&ws->lock, flags);
+
+	return ret;
+}
+
+/**
+ * wakeup_sources_stats_show - Print wakeup sources statistics information.
+ * @m: seq_file to print the statistics into.
+ */
+static int wakeup_sources_stats_show(struct seq_file *m, void *unused)
+{
+	struct wakeup_source *ws;
+
+	seq_puts(m, "name\t\tactive_count\tevent_count\twakeup_count\t"
+		"expire_count\tactive_since\ttotal_time\tmax_time\t"
+		"last_change\tprevent_suspend_time\n");
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(ws, &wakeup_sources, entry)
+		print_wakeup_source_stats(m, ws);
+	rcu_read_unlock();
+
+	return 0;
+}
+
+static int wakeup_sources_stats_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, wakeup_sources_stats_show, NULL);
+}
+
+static const struct file_operations wakeup_sources_stats_fops = {
+	.owner = THIS_MODULE,
+	.open = wakeup_sources_stats_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = single_release,
+};
+
+static int __init wakeup_sources_debugfs_init(void)
+{
+	wakeup_sources_stats_dentry = debugfs_create_file("wakeup_sources",
+			S_IRUGO, NULL, NULL, &wakeup_sources_stats_fops);
+	return 0;
+}
+
+postcore_initcall(wakeup_sources_debugfs_init);

drivers/base/regmap/Kconfig

@@ -0,0 +1,22 @@
+# Generic register map support.  There are no user servicable options here,
+# this is an API intended to be used by other kernel subsystems.  These
+# subsystems should select the appropriate symbols.
+
+config REGMAP
+	default y if (REGMAP_I2C || REGMAP_SPI || REGMAP_MMIO || REGMAP_IRQ)
+	select LZO_COMPRESS
+	select LZO_DECOMPRESS
+	select IRQ_DOMAIN if REGMAP_IRQ
+	bool
+
+config REGMAP_I2C
+	tristate
+
+config REGMAP_SPI
+	tristate
+
+config REGMAP_MMIO
+	tristate
+
+config REGMAP_IRQ
+	bool

drivers/base/regmap/Makefile

@@ -0,0 +1,7 @@
+obj-$(CONFIG_REGMAP) += regmap.o regcache.o
+obj-$(CONFIG_REGMAP) += regcache-rbtree.o regcache-lzo.o regcache-flat.o
+obj-$(CONFIG_DEBUG_FS) += regmap-debugfs.o
+obj-$(CONFIG_REGMAP_I2C) += regmap-i2c.o
+obj-$(CONFIG_REGMAP_SPI) += regmap-spi.o
+obj-$(CONFIG_REGMAP_MMIO) += regmap-mmio.o
+obj-$(CONFIG_REGMAP_IRQ) += regmap-irq.o

drivers/base/regmap/internal.h

@@ -0,0 +1,231 @@
+/*
+ * Register map access API internal header
+ *
+ * Copyright 2011 Wolfson Microelectronics plc
+ *
+ * Author: Mark Brown <broonie@opensource.wolfsonmicro.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _REGMAP_INTERNAL_H
+#define _REGMAP_INTERNAL_H
+
+#include <linux/regmap.h>
+#include <linux/fs.h>
+#include <linux/list.h>
+#include <linux/wait.h>
+
+struct regmap;
+struct regcache_ops;
+
+struct regmap_debugfs_off_cache {
+	struct list_head list;
+	off_t min;
+	off_t max;
+	unsigned int base_reg;
+	unsigned int max_reg;
+};
+
+struct regmap_format {
+	size_t buf_size;
+	size_t reg_bytes;
+	size_t pad_bytes;
+	size_t val_bytes;
+	void (*format_write)(struct regmap *map,
+			     unsigned int reg, unsigned int val);
+	void (*format_reg)(void *buf, unsigned int reg, unsigned int shift);
+	void (*format_val)(void *buf, unsigned int val, unsigned int shift);
+	unsigned int (*parse_val)(const void *buf);
+	void (*parse_inplace)(void *buf);
+};
+
+struct regmap_async {
+	struct list_head list;
+	struct work_struct cleanup;
+	struct regmap *map;
+	void *work_buf;
+};
+
+struct regmap {
+	struct mutex mutex;
+	spinlock_t spinlock;
+	regmap_lock lock;
+	regmap_unlock unlock;
+	void *lock_arg; /* This is passed to lock/unlock functions */
+
+	struct device *dev; /* Device we do I/O on */
+	void *work_buf;     /* Scratch buffer used to format I/O */
+	struct regmap_format format;  /* Buffer format */
+	const struct regmap_bus *bus;
+	void *bus_context;
+	const char *name;
+
+	spinlock_t async_lock;
+	wait_queue_head_t async_waitq;
+	struct list_head async_list;
+	int async_ret;
+
+#ifdef CONFIG_DEBUG_FS
+	struct dentry *debugfs;
+	const char *debugfs_name;
+
+	unsigned int debugfs_reg_len;
+	unsigned int debugfs_val_len;
+	unsigned int debugfs_tot_len;
+
+	struct list_head debugfs_off_cache;
+	struct mutex cache_lock;
+#endif
+
+	unsigned int max_register;
+	bool (*writeable_reg)(struct device *dev, unsigned int reg);
+	bool (*readable_reg)(struct device *dev, unsigned int reg);
+	bool (*volatile_reg)(struct device *dev, unsigned int reg);
+	bool (*precious_reg)(struct device *dev, unsigned int reg);
+	const struct regmap_access_table *wr_table;
+	const struct regmap_access_table *rd_table;
+	const struct regmap_access_table *volatile_table;
+	const struct regmap_access_table *precious_table;
+
+	int (*reg_read)(void *context, unsigned int reg, unsigned int *val);
+	int (*reg_write)(void *context, unsigned int reg, unsigned int val);
+
+	bool defer_caching;
+
+	u8 read_flag_mask;
+	u8 write_flag_mask;
+
+	/* number of bits to (left) shift the reg value when formatting*/
+	int reg_shift;
+	int reg_stride;
+
+	/* regcache specific members */
+	const struct regcache_ops *cache_ops;
+	enum regcache_type cache_type;
+
+	/* number of bytes in reg_defaults_raw */
+	unsigned int cache_size_raw;
+	/* number of bytes per word in reg_defaults_raw */
+	unsigned int cache_word_size;
+	/* number of entries in reg_defaults */
+	unsigned int num_reg_defaults;
+	/* number of entries in reg_defaults_raw */
+	unsigned int num_reg_defaults_raw;
+
+	/* if set, only the cache is modified not the HW */
+	u32 cache_only;
+	/* if set, only the HW is modified not the cache */
+	u32 cache_bypass;
+	/* if set, remember to free reg_defaults_raw */
+	bool cache_free;
+
+	struct reg_default *reg_defaults;
+	const void *reg_defaults_raw;
+	void *cache;
+	u32 cache_dirty;
+
+	unsigned long *cache_present;
+	unsigned int cache_present_nbits;
+
+	struct reg_default *patch;
+	int patch_regs;
+
+	/* if set, converts bulk rw to single rw */
+	bool use_single_rw;
+
+	struct rb_root range_tree;
+	void *selector_work_buf;	/* Scratch buffer used for selector */
+};
+
+struct regcache_ops {
+	const char *name;
+	enum regcache_type type;
+	int (*init)(struct regmap *map);
+	int (*exit)(struct regmap *map);
+	int (*read)(struct regmap *map, unsigned int reg, unsigned int *value);
+	int (*write)(struct regmap *map, unsigned int reg, unsigned int value);
+	int (*sync)(struct regmap *map, unsigned int min, unsigned int max);
+};
+
+bool regmap_writeable(struct regmap *map, unsigned int reg);
+bool regmap_readable(struct regmap *map, unsigned int reg);
+bool regmap_volatile(struct regmap *map, unsigned int reg);
+bool regmap_precious(struct regmap *map, unsigned int reg);
+
+int _regmap_write(struct regmap *map, unsigned int reg,
+		  unsigned int val);
+
+struct regmap_range_node {
+	struct rb_node node;
+	const char *name;
+	struct regmap *map;
+
+	unsigned int range_min;
+	unsigned int range_max;
+
+	unsigned int selector_reg;
+	unsigned int selector_mask;
+	int selector_shift;
+
+	unsigned int window_start;
+	unsigned int window_len;
+};
+
+#ifdef CONFIG_DEBUG_FS
+extern void regmap_debugfs_initcall(void);
+extern void regmap_debugfs_init(struct regmap *map, const char *name);
+extern void regmap_debugfs_exit(struct regmap *map);
+#else
+static inline void regmap_debugfs_initcall(void) { }
+static inline void regmap_debugfs_init(struct regmap *map, const char *name) { }
+static inline void regmap_debugfs_exit(struct regmap *map) { }
+#endif
+
+/* regcache core declarations */
+int regcache_init(struct regmap *map, const struct regmap_config *config);
+void regcache_exit(struct regmap *map);
+int regcache_read(struct regmap *map,
+		       unsigned int reg, unsigned int *value);
+int regcache_write(struct regmap *map,
+			unsigned int reg, unsigned int value);
+int regcache_sync(struct regmap *map);
+int regcache_sync_block(struct regmap *map, void *block,
+			unsigned int block_base, unsigned int start,
+			unsigned int end);
+
+static inline const void *regcache_get_val_addr(struct regmap *map,
+						const void *base,
+						unsigned int idx)
+{
+	return base + (map->cache_word_size * idx);
+}
+
+unsigned int regcache_get_val(struct regmap *map, const void *base,
+			      unsigned int idx);
+bool regcache_set_val(struct regmap *map, void *base, unsigned int idx,
+		      unsigned int val);
+int regcache_lookup_reg(struct regmap *map, unsigned int reg);
+int regcache_set_reg_present(struct regmap *map, unsigned int reg);
+
+static inline bool regcache_reg_present(struct regmap *map, unsigned int reg)
+{
+	if (!map->cache_present)
+		return true;
+	if (reg > map->cache_present_nbits)
+		return false;
+	return map->cache_present[BIT_WORD(reg)] & BIT_MASK(reg);
+}
+
+int _regmap_raw_write(struct regmap *map, unsigned int reg,
+		      const void *val, size_t val_len, bool async);
+
+void regmap_async_complete_cb(struct regmap_async *async, int ret);
+
+extern struct regcache_ops regcache_rbtree_ops;
+extern struct regcache_ops regcache_lzo_ops;
+extern struct regcache_ops regcache_flat_ops;
+
+#endif

drivers/base/regmap/regcache-flat.c

@@ -0,0 +1,72 @@
+/*
+ * Register cache access API - flat caching support
+ *
+ * Copyright 2012 Wolfson Microelectronics plc
+ *
+ * Author: Mark Brown <broonie@opensource.wolfsonmicro.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/slab.h>
+#include <linux/device.h>
+#include <linux/seq_file.h>
+
+#include "internal.h"
+
+static int regcache_flat_init(struct regmap *map)
+{
+	int i;
+	unsigned int *cache;
+
+	map->cache = kzalloc(sizeof(unsigned int) * (map->max_register + 1),
+			     GFP_KERNEL);
+	if (!map->cache)
+		return -ENOMEM;
+
+	cache = map->cache;
+
+	for (i = 0; i < map->num_reg_defaults; i++)
+		cache[map->reg_defaults[i].reg] = map->reg_defaults[i].def;
+
+	return 0;
+}
+
+static int regcache_flat_exit(struct regmap *map)
+{
+	kfree(map->cache);
+	map->cache = NULL;
+
+	return 0;
+}
+
+static int regcache_flat_read(struct regmap *map,
+			      unsigned int reg, unsigned int *value)
+{
+	unsigned int *cache = map->cache;
+
+	*value = cache[reg];
+
+	return 0;
+}
+
+static int regcache_flat_write(struct regmap *map, unsigned int reg,
+			       unsigned int value)
+{
+	unsigned int *cache = map->cache;
+
+	cache[reg] = value;
+
+	return 0;
+}
+
+struct regcache_ops regcache_flat_ops = {
+	.type = REGCACHE_FLAT,
+	.name = "flat",
+	.init = regcache_flat_init,
+	.exit = regcache_flat_exit,
+	.read = regcache_flat_read,
+	.write = regcache_flat_write,
+};

drivers/base/regmap/regcache-lzo.c

@@ -0,0 +1,378 @@
+/*
+ * Register cache access API - LZO caching support
+ *
+ * Copyright 2011 Wolfson Microelectronics plc
+ *
+ * Author: Dimitris Papastamos <dp@opensource.wolfsonmicro.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/slab.h>
+#include <linux/device.h>
+#include <linux/lzo.h>
+
+#include "internal.h"
+
+static int regcache_lzo_exit(struct regmap *map);
+
+struct regcache_lzo_ctx {
+	void *wmem;
+	void *dst;
+	const void *src;
+	size_t src_len;
+	size_t dst_len;
+	size_t decompressed_size;
+	unsigned long *sync_bmp;
+	int sync_bmp_nbits;
+};
+
+#define LZO_BLOCK_NUM 8
+static int regcache_lzo_block_count(struct regmap *map)
+{
+	return LZO_BLOCK_NUM;
+}
+
+static int regcache_lzo_prepare(struct regcache_lzo_ctx *lzo_ctx)
+{
+	lzo_ctx->wmem = kmalloc(LZO1X_MEM_COMPRESS, GFP_KERNEL);
+	if (!lzo_ctx->wmem)
+		return -ENOMEM;
+	return 0;
+}
+
+static int regcache_lzo_compress(struct regcache_lzo_ctx *lzo_ctx)
+{
+	size_t compress_size;
+	int ret;
+
+	ret = lzo1x_1_compress(lzo_ctx->src, lzo_ctx->src_len,
+			       lzo_ctx->dst, &compress_size, lzo_ctx->wmem);
+	if (ret != LZO_E_OK || compress_size > lzo_ctx->dst_len)
+		return -EINVAL;
+	lzo_ctx->dst_len = compress_size;
+	return 0;
+}
+
+static int regcache_lzo_decompress(struct regcache_lzo_ctx *lzo_ctx)
+{
+	size_t dst_len;
+	int ret;
+
+	dst_len = lzo_ctx->dst_len;
+	ret = lzo1x_decompress_safe(lzo_ctx->src, lzo_ctx->src_len,
+				    lzo_ctx->dst, &dst_len);
+	if (ret != LZO_E_OK || dst_len != lzo_ctx->dst_len)
+		return -EINVAL;
+	return 0;
+}
+
+static int regcache_lzo_compress_cache_block(struct regmap *map,
+		struct regcache_lzo_ctx *lzo_ctx)
+{
+	int ret;
+
+	lzo_ctx->dst_len = lzo1x_worst_compress(PAGE_SIZE);
+	lzo_ctx->dst = kmalloc(lzo_ctx->dst_len, GFP_KERNEL);
+	if (!lzo_ctx->dst) {
+		lzo_ctx->dst_len = 0;
+		return -ENOMEM;
+	}
+
+	ret = regcache_lzo_compress(lzo_ctx);
+	if (ret < 0)
+		return ret;
+	return 0;
+}
+
+static int regcache_lzo_decompress_cache_block(struct regmap *map,
+		struct regcache_lzo_ctx *lzo_ctx)
+{
+	int ret;
+
+	lzo_ctx->dst_len = lzo_ctx->decompressed_size;
+	lzo_ctx->dst = kmalloc(lzo_ctx->dst_len, GFP_KERNEL);
+	if (!lzo_ctx->dst) {
+		lzo_ctx->dst_len = 0;
+		return -ENOMEM;
+	}
+
+	ret = regcache_lzo_decompress(lzo_ctx);
+	if (ret < 0)
+		return ret;
+	return 0;
+}
+
+static inline int regcache_lzo_get_blkindex(struct regmap *map,
+					    unsigned int reg)
+{
+	return ((reg / map->reg_stride) * map->cache_word_size) /
+		DIV_ROUND_UP(map->cache_size_raw,
+			     regcache_lzo_block_count(map));
+}
+
+static inline int regcache_lzo_get_blkpos(struct regmap *map,
+					  unsigned int reg)
+{
+	return (reg / map->reg_stride) %
+		    (DIV_ROUND_UP(map->cache_size_raw,
+				  regcache_lzo_block_count(map)) /
+		     map->cache_word_size);
+}
+
+static inline int regcache_lzo_get_blksize(struct regmap *map)
+{
+	return DIV_ROUND_UP(map->cache_size_raw,
+			    regcache_lzo_block_count(map));
+}
+
+static int regcache_lzo_init(struct regmap *map)
+{
+	struct regcache_lzo_ctx **lzo_blocks;
+	size_t bmp_size;
+	int ret, i, blksize, blkcount;
+	const char *p, *end;
+	unsigned long *sync_bmp;
+
+	ret = 0;
+
+	blkcount = regcache_lzo_block_count(map);
+	map->cache = kzalloc(blkcount * sizeof *lzo_blocks,
+			     GFP_KERNEL);
+	if (!map->cache)
+		return -ENOMEM;
+	lzo_blocks = map->cache;
+
+	/*
+	 * allocate a bitmap to be used when syncing the cache with
+	 * the hardware.  Each time a register is modified, the corresponding
+	 * bit is set in the bitmap, so we know that we have to sync
+	 * that register.
+	 */
+	bmp_size = map->num_reg_defaults_raw;
+	sync_bmp = kmalloc(BITS_TO_LONGS(bmp_size) * sizeof(long),
+			   GFP_KERNEL);
+	if (!sync_bmp) {
+		ret = -ENOMEM;
+		goto err;
+	}
+	bitmap_zero(sync_bmp, bmp_size);
+
+	/* allocate the lzo blocks and initialize them */
+	for (i = 0; i < blkcount; i++) {
+		lzo_blocks[i] = kzalloc(sizeof **lzo_blocks,
+					GFP_KERNEL);
+		if (!lzo_blocks[i]) {
+			kfree(sync_bmp);
+			ret = -ENOMEM;
+			goto err;
+		}
+		lzo_blocks[i]->sync_bmp = sync_bmp;
+		lzo_blocks[i]->sync_bmp_nbits = bmp_size;
+		/* alloc the working space for the compressed block */
+		ret = regcache_lzo_prepare(lzo_blocks[i]);
+		if (ret < 0)
+			goto err;
+	}
+
+	blksize = regcache_lzo_get_blksize(map);
+	p = map->reg_defaults_raw;
+	end = map->reg_defaults_raw + map->cache_size_raw;
+	/* compress the register map and fill the lzo blocks */
+	for (i = 0; i < blkcount; i++, p += blksize) {
+		lzo_blocks[i]->src = p;
+		if (p + blksize > end)
+			lzo_blocks[i]->src_len = end - p;
+		else
+			lzo_blocks[i]->src_len = blksize;
+		ret = regcache_lzo_compress_cache_block(map,
+						       lzo_blocks[i]);
+		if (ret < 0)
+			goto err;
+		lzo_blocks[i]->decompressed_size =
+			lzo_blocks[i]->src_len;
+	}
+
+	return 0;
+err:
+	regcache_lzo_exit(map);
+	return ret;
+}
+
+static int regcache_lzo_exit(struct regmap *map)
+{
+	struct regcache_lzo_ctx **lzo_blocks;
+	int i, blkcount;
+
+	lzo_blocks = map->cache;
+	if (!lzo_blocks)
+		return 0;
+
+	blkcount = regcache_lzo_block_count(map);
+	/*
+	 * the pointer to the bitmap used for syncing the cache
+	 * is shared amongst all lzo_blocks.  Ensure it is freed
+	 * only once.
+	 */
+	if (lzo_blocks[0])
+		kfree(lzo_blocks[0]->sync_bmp);
+	for (i = 0; i < blkcount; i++) {
+		if (lzo_blocks[i]) {
+			kfree(lzo_blocks[i]->wmem);
+			kfree(lzo_blocks[i]->dst);
+		}
+		/* each lzo_block is a pointer returned by kmalloc or NULL */
+		kfree(lzo_blocks[i]);
+	}
+	kfree(lzo_blocks);
+	map->cache = NULL;
+	return 0;
+}
+
+static int regcache_lzo_read(struct regmap *map,
+			     unsigned int reg, unsigned int *value)
+{
+	struct regcache_lzo_ctx *lzo_block, **lzo_blocks;
+	int ret, blkindex, blkpos;
+	size_t blksize, tmp_dst_len;
+	void *tmp_dst;
+
+	/* index of the compressed lzo block */
+	blkindex = regcache_lzo_get_blkindex(map, reg);
+	/* register index within the decompressed block */
+	blkpos = regcache_lzo_get_blkpos(map, reg);
+	/* size of the compressed block */
+	blksize = regcache_lzo_get_blksize(map);
+	lzo_blocks = map->cache;
+	lzo_block = lzo_blocks[blkindex];
+
+	/* save the pointer and length of the compressed block */
+	tmp_dst = lzo_block->dst;
+	tmp_dst_len = lzo_block->dst_len;
+
+	/* prepare the source to be the compressed block */
+	lzo_block->src = lzo_block->dst;
+	lzo_block->src_len = lzo_block->dst_len;
+
+	/* decompress the block */
+	ret = regcache_lzo_decompress_cache_block(map, lzo_block);
+	if (ret >= 0)
+		/* fetch the value from the cache */
+		*value = regcache_get_val(map, lzo_block->dst, blkpos);
+
+	kfree(lzo_block->dst);
+	/* restore the pointer and length of the compressed block */
+	lzo_block->dst = tmp_dst;
+	lzo_block->dst_len = tmp_dst_len;
+
+	return ret;
+}
+
+static int regcache_lzo_write(struct regmap *map,
+			      unsigned int reg, unsigned int value)
+{
+	struct regcache_lzo_ctx *lzo_block, **lzo_blocks;
+	int ret, blkindex, blkpos;
+	size_t blksize, tmp_dst_len;
+	void *tmp_dst;
+
+	/* index of the compressed lzo block */
+	blkindex = regcache_lzo_get_blkindex(map, reg);
+	/* register index within the decompressed block */
+	blkpos = regcache_lzo_get_blkpos(map, reg);
+	/* size of the compressed block */
+	blksize = regcache_lzo_get_blksize(map);
+	lzo_blocks = map->cache;
+	lzo_block = lzo_blocks[blkindex];
+
+	/* save the pointer and length of the compressed block */
+	tmp_dst = lzo_block->dst;
+	tmp_dst_len = lzo_block->dst_len;
+
+	/* prepare the source to be the compressed block */
+	lzo_block->src = lzo_block->dst;
+	lzo_block->src_len = lzo_block->dst_len;
+
+	/* decompress the block */
+	ret = regcache_lzo_decompress_cache_block(map, lzo_block);
+	if (ret < 0) {
+		kfree(lzo_block->dst);
+		goto out;
+	}
+
+	/* write the new value to the cache */
+	if (regcache_set_val(map, lzo_block->dst, blkpos, value)) {
+		kfree(lzo_block->dst);
+		goto out;
+	}
+
+	/* prepare the source to be the decompressed block */
+	lzo_block->src = lzo_block->dst;
+	lzo_block->src_len = lzo_block->dst_len;
+
+	/* compress the block */
+	ret = regcache_lzo_compress_cache_block(map, lzo_block);
+	if (ret < 0) {
+		kfree(lzo_block->dst);
+		kfree(lzo_block->src);
+		goto out;
+	}
+
+	/* set the bit so we know we have to sync this register */
+	set_bit(reg / map->reg_stride, lzo_block->sync_bmp);
+	kfree(tmp_dst);
+	kfree(lzo_block->src);
+	return 0;
+out:
+	lzo_block->dst = tmp_dst;
+	lzo_block->dst_len = tmp_dst_len;
+	return ret;
+}
+
+static int regcache_lzo_sync(struct regmap *map, unsigned int min,
+			     unsigned int max)
+{
+	struct regcache_lzo_ctx **lzo_blocks;
+	unsigned int val;
+	int i;
+	int ret;
+
+	lzo_blocks = map->cache;
+	i = min;
+	for_each_set_bit_from(i, lzo_blocks[0]->sync_bmp,
+			      lzo_blocks[0]->sync_bmp_nbits) {
+		if (i > max)
+			continue;
+
+		ret = regcache_read(map, i, &val);
+		if (ret)
+			return ret;
+
+		/* Is this the hardware default?  If so skip. */
+		ret = regcache_lookup_reg(map, i);
+		if (ret > 0 && val == map->reg_defaults[ret].def)
+			continue;
+
+		map->cache_bypass = 1;
+		ret = _regmap_write(map, i, val);
+		map->cache_bypass = 0;
+		if (ret)
+			return ret;
+		dev_dbg(map->dev, "Synced register %#x, value %#x\n",
+			i, val);
+	}
+
+	return 0;
+}
+
+struct regcache_ops regcache_lzo_ops = {
+	.type = REGCACHE_COMPRESSED,
+	.name = "lzo",
+	.init = regcache_lzo_init,
+	.exit = regcache_lzo_exit,
+	.read = regcache_lzo_read,
+	.write = regcache_lzo_write,
+	.sync = regcache_lzo_sync
+};

drivers/base/regmap/regcache-rbtree.c

@@ -0,0 +1,429 @@
+/*
+ * Register cache access API - rbtree caching support
+ *
+ * Copyright 2011 Wolfson Microelectronics plc
+ *
+ * Author: Dimitris Papastamos <dp@opensource.wolfsonmicro.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/slab.h>
+#include <linux/device.h>
+#include <linux/debugfs.h>
+#include <linux/rbtree.h>
+#include <linux/seq_file.h>
+
+#include "internal.h"
+
+static int regcache_rbtree_write(struct regmap *map, unsigned int reg,
+				 unsigned int value);
+static int regcache_rbtree_exit(struct regmap *map);
+
+struct regcache_rbtree_node {
+	/* the actual rbtree node holding this block */
+	struct rb_node node;
+	/* base register handled by this block */
+	unsigned int base_reg;
+	/* block of adjacent registers */
+	void *block;
+	/* number of registers available in the block */
+	unsigned int blklen;
+} __attribute__ ((packed));
+
+struct regcache_rbtree_ctx {
+	struct rb_root root;
+	struct regcache_rbtree_node *cached_rbnode;
+};
+
+static inline void regcache_rbtree_get_base_top_reg(
+	struct regmap *map,
+	struct regcache_rbtree_node *rbnode,
+	unsigned int *base, unsigned int *top)
+{
+	*base = rbnode->base_reg;
+	*top = rbnode->base_reg + ((rbnode->blklen - 1) * map->reg_stride);
+}
+
+static unsigned int regcache_rbtree_get_register(struct regmap *map,
+	struct regcache_rbtree_node *rbnode, unsigned int idx)
+{
+	return regcache_get_val(map, rbnode->block, idx);
+}
+
+static void regcache_rbtree_set_register(struct regmap *map,
+					 struct regcache_rbtree_node *rbnode,
+					 unsigned int idx, unsigned int val)
+{
+	regcache_set_val(map, rbnode->block, idx, val);
+}
+
+static struct regcache_rbtree_node *regcache_rbtree_lookup(struct regmap *map,
+							   unsigned int reg)
+{
+	struct regcache_rbtree_ctx *rbtree_ctx = map->cache;
+	struct rb_node *node;
+	struct regcache_rbtree_node *rbnode;
+	unsigned int base_reg, top_reg;
+
+	rbnode = rbtree_ctx->cached_rbnode;
+	if (rbnode) {
+		regcache_rbtree_get_base_top_reg(map, rbnode, &base_reg,
+						 &top_reg);
+		if (reg >= base_reg && reg <= top_reg)
+			return rbnode;
+	}
+
+	node = rbtree_ctx->root.rb_node;
+	while (node) {
+		rbnode = container_of(node, struct regcache_rbtree_node, node);
+		regcache_rbtree_get_base_top_reg(map, rbnode, &base_reg,
+						 &top_reg);
+		if (reg >= base_reg && reg <= top_reg) {
+			rbtree_ctx->cached_rbnode = rbnode;
+			return rbnode;
+		} else if (reg > top_reg) {
+			node = node->rb_right;
+		} else if (reg < base_reg) {
+			node = node->rb_left;
+		}
+	}
+
+	return NULL;
+}
+
+static int regcache_rbtree_insert(struct regmap *map, struct rb_root *root,
+				  struct regcache_rbtree_node *rbnode)
+{
+	struct rb_node **new, *parent;
+	struct regcache_rbtree_node *rbnode_tmp;
+	unsigned int base_reg_tmp, top_reg_tmp;
+	unsigned int base_reg;
+
+	parent = NULL;
+	new = &root->rb_node;
+	while (*new) {
+		rbnode_tmp = container_of(*new, struct regcache_rbtree_node,
+					  node);
+		/* base and top registers of the current rbnode */
+		regcache_rbtree_get_base_top_reg(map, rbnode_tmp, &base_reg_tmp,
+						 &top_reg_tmp);
+		/* base register of the rbnode to be added */
+		base_reg = rbnode->base_reg;
+		parent = *new;
+		/* if this register has already been inserted, just return */
+		if (base_reg >= base_reg_tmp &&
+		    base_reg <= top_reg_tmp)
+			return 0;
+		else if (base_reg > top_reg_tmp)
+			new = &((*new)->rb_right);
+		else if (base_reg < base_reg_tmp)
+			new = &((*new)->rb_left);
+	}
+
+	/* insert the node into the rbtree */
+	rb_link_node(&rbnode->node, parent, new);
+	rb_insert_color(&rbnode->node, root);
+
+	return 1;
+}
+
+#ifdef CONFIG_DEBUG_FS
+static int rbtree_show(struct seq_file *s, void *ignored)
+{
+	struct regmap *map = s->private;
+	struct regcache_rbtree_ctx *rbtree_ctx = map->cache;
+	struct regcache_rbtree_node *n;
+	struct rb_node *node;
+	unsigned int base, top;
+	size_t mem_size;
+	int nodes = 0;
+	int registers = 0;
+	int this_registers, average;
+
+	map->lock(map->lock_arg);
+
+	mem_size = sizeof(*rbtree_ctx);
+	mem_size += BITS_TO_LONGS(map->cache_present_nbits) * sizeof(long);
+
+	for (node = rb_first(&rbtree_ctx->root); node != NULL;
+	     node = rb_next(node)) {
+		n = container_of(node, struct regcache_rbtree_node, node);
+		mem_size += sizeof(*n);
+		mem_size += (n->blklen * map->cache_word_size);
+
+		regcache_rbtree_get_base_top_reg(map, n, &base, &top);
+		this_registers = ((top - base) / map->reg_stride) + 1;
+		seq_printf(s, "%x-%x (%d)\n", base, top, this_registers);
+
+		nodes++;
+		registers += this_registers;
+	}
+
+	if (nodes)
+		average = registers / nodes;
+	else
+		average = 0;
+
+	seq_printf(s, "%d nodes, %d registers, average %d registers, used %zu bytes\n",
+		   nodes, registers, average, mem_size);
+
+	map->unlock(map->lock_arg);
+
+	return 0;
+}
+
+static int rbtree_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, rbtree_show, inode->i_private);
+}
+
+static const struct file_operations rbtree_fops = {
+	.open		= rbtree_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static void rbtree_debugfs_init(struct regmap *map)
+{
+	debugfs_create_file("rbtree", 0400, map->debugfs, map, &rbtree_fops);
+}
+#else
+static void rbtree_debugfs_init(struct regmap *map)
+{
+}
+#endif
+
+static int regcache_rbtree_init(struct regmap *map)
+{
+	struct regcache_rbtree_ctx *rbtree_ctx;
+	int i;
+	int ret;
+
+	map->cache = kmalloc(sizeof *rbtree_ctx, GFP_KERNEL);
+	if (!map->cache)
+		return -ENOMEM;
+
+	rbtree_ctx = map->cache;
+	rbtree_ctx->root = RB_ROOT;
+	rbtree_ctx->cached_rbnode = NULL;
+
+	for (i = 0; i < map->num_reg_defaults; i++) {
+		ret = regcache_rbtree_write(map,
+					    map->reg_defaults[i].reg,
+					    map->reg_defaults[i].def);
+		if (ret)
+			goto err;
+	}
+
+	rbtree_debugfs_init(map);
+
+	return 0;
+
+err:
+	regcache_rbtree_exit(map);
+	return ret;
+}
+
+static int regcache_rbtree_exit(struct regmap *map)
+{
+	struct rb_node *next;
+	struct regcache_rbtree_ctx *rbtree_ctx;
+	struct regcache_rbtree_node *rbtree_node;
+
+	/* if we've already been called then just return */
+	rbtree_ctx = map->cache;
+	if (!rbtree_ctx)
+		return 0;
+
+	/* free up the rbtree */
+	next = rb_first(&rbtree_ctx->root);
+	while (next) {
+		rbtree_node = rb_entry(next, struct regcache_rbtree_node, node);
+		next = rb_next(&rbtree_node->node);
+		rb_erase(&rbtree_node->node, &rbtree_ctx->root);
+		kfree(rbtree_node->block);
+		kfree(rbtree_node);
+	}
+
+	/* release the resources */
+	kfree(map->cache);
+	map->cache = NULL;
+
+	return 0;
+}
+
+static int regcache_rbtree_read(struct regmap *map,
+				unsigned int reg, unsigned int *value)
+{
+	struct regcache_rbtree_node *rbnode;
+	unsigned int reg_tmp;
+
+	rbnode = regcache_rbtree_lookup(map, reg);
+	if (rbnode) {
+		reg_tmp = (reg - rbnode->base_reg) / map->reg_stride;
+		if (!regcache_reg_present(map, reg))
+			return -ENOENT;
+		*value = regcache_rbtree_get_register(map, rbnode, reg_tmp);
+	} else {
+		return -ENOENT;
+	}
+
+	return 0;
+}
+
+
+static int regcache_rbtree_insert_to_block(struct regmap *map,
+					   struct regcache_rbtree_node *rbnode,
+					   unsigned int pos, unsigned int reg,
+					   unsigned int value)
+{
+	u8 *blk;
+
+	blk = krealloc(rbnode->block,
+		       (rbnode->blklen + 1) * map->cache_word_size,
+		       GFP_KERNEL);
+	if (!blk)
+		return -ENOMEM;
+
+	/* insert the register value in the correct place in the rbnode block */
+	memmove(blk + (pos + 1) * map->cache_word_size,
+		blk + pos * map->cache_word_size,
+		(rbnode->blklen - pos) * map->cache_word_size);
+
+	/* update the rbnode block, its size and the base register */
+	rbnode->block = blk;
+	rbnode->blklen++;
+	if (!pos)
+		rbnode->base_reg = reg;
+
+	regcache_rbtree_set_register(map, rbnode, pos, value);
+	return 0;
+}
+
+static int regcache_rbtree_write(struct regmap *map, unsigned int reg,
+				 unsigned int value)
+{
+	struct regcache_rbtree_ctx *rbtree_ctx;
+	struct regcache_rbtree_node *rbnode, *rbnode_tmp;
+	struct rb_node *node;
+	unsigned int reg_tmp;
+	unsigned int pos;
+	int i;
+	int ret;
+
+	rbtree_ctx = map->cache;
+	/* update the reg_present bitmap, make space if necessary */
+	ret = regcache_set_reg_present(map, reg);
+	if (ret < 0)
+		return ret;
+
+	/* if we can't locate it in the cached rbnode we'll have
+	 * to traverse the rbtree looking for it.
+	 */
+	rbnode = regcache_rbtree_lookup(map, reg);
+	if (rbnode) {
+		reg_tmp = (reg - rbnode->base_reg) / map->reg_stride;
+		regcache_rbtree_set_register(map, rbnode, reg_tmp, value);
+	} else {
+		/* look for an adjacent register to the one we are about to add */
+		for (node = rb_first(&rbtree_ctx->root); node;
+		     node = rb_next(node)) {
+			rbnode_tmp = rb_entry(node, struct regcache_rbtree_node,
+					      node);
+			for (i = 0; i < rbnode_tmp->blklen; i++) {
+				reg_tmp = rbnode_tmp->base_reg +
+						(i * map->reg_stride);
+				if (abs(reg_tmp - reg) != map->reg_stride)
+					continue;
+				/* decide where in the block to place our register */
+				if (reg_tmp + map->reg_stride == reg)
+					pos = i + 1;
+				else
+					pos = i;
+				ret = regcache_rbtree_insert_to_block(map,
+								      rbnode_tmp,
+								      pos, reg,
+								      value);
+				if (ret)
+					return ret;
+				rbtree_ctx->cached_rbnode = rbnode_tmp;
+				return 0;
+			}
+		}
+		/* we did not manage to find a place to insert it in an existing
+		 * block so create a new rbnode with a single register in its block.
+		 * This block will get populated further if any other adjacent
+		 * registers get modified in the future.
+		 */
+		rbnode = kzalloc(sizeof *rbnode, GFP_KERNEL);
+		if (!rbnode)
+			return -ENOMEM;
+		rbnode->blklen = 1;
+		rbnode->base_reg = reg;
+		rbnode->block = kmalloc(rbnode->blklen * map->cache_word_size,
+					GFP_KERNEL);
+		if (!rbnode->block) {
+			kfree(rbnode);
+			return -ENOMEM;
+		}
+		regcache_rbtree_set_register(map, rbnode, 0, value);
+		regcache_rbtree_insert(map, &rbtree_ctx->root, rbnode);
+		rbtree_ctx->cached_rbnode = rbnode;
+	}
+
+	return 0;
+}
+
+static int regcache_rbtree_sync(struct regmap *map, unsigned int min,
+				unsigned int max)
+{
+	struct regcache_rbtree_ctx *rbtree_ctx;
+	struct rb_node *node;
+	struct regcache_rbtree_node *rbnode;
+	unsigned int base_reg, top_reg;
+	unsigned int start, end;
+	int ret;
+
+	rbtree_ctx = map->cache;
+	for (node = rb_first(&rbtree_ctx->root); node; node = rb_next(node)) {
+		rbnode = rb_entry(node, struct regcache_rbtree_node, node);
+
+		regcache_rbtree_get_base_top_reg(map, rbnode, &base_reg,
+			&top_reg);
+		if (base_reg > max)
+			break;
+		if (top_reg < min)
+			continue;
+
+		if (min > base_reg)
+			start = (min - base_reg) / map->reg_stride;
+		else
+			start = 0;
+
+		if (max < top_reg)
+			end = (max - base_reg) / map->reg_stride + 1;
+		else
+			end = rbnode->blklen;
+
+		ret = regcache_sync_block(map, rbnode->block, rbnode->base_reg,
+					  start, end);
+		if (ret != 0)
+			return ret;
+	}
+
+	return regmap_async_complete(map);
+}
+
+struct regcache_ops regcache_rbtree_ops = {
+	.type = REGCACHE_RBTREE,
+	.name = "rbtree",
+	.init = regcache_rbtree_init,
+	.exit = regcache_rbtree_exit,
+	.read = regcache_rbtree_read,
+	.write = regcache_rbtree_write,
+	.sync = regcache_rbtree_sync
+};

drivers/base/regmap/regcache.c

@@ -0,0 +1,700 @@
+/*
+ * Register cache access API
+ *
+ * Copyright 2011 Wolfson Microelectronics plc
+ *
+ * Author: Dimitris Papastamos <dp@opensource.wolfsonmicro.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/slab.h>
+#include <linux/export.h>
+#include <linux/device.h>
+#include <trace/events/regmap.h>
+#include <linux/bsearch.h>
+#include <linux/sort.h>
+
+#include "internal.h"
+
+static const struct regcache_ops *cache_types[] = {
+	&regcache_rbtree_ops,
+	&regcache_lzo_ops,
+	&regcache_flat_ops,
+};
+
+static int regcache_hw_init(struct regmap *map)
+{
+	int i, j;
+	int ret;
+	int count;
+	unsigned int val;
+	void *tmp_buf;
+
+	if (!map->num_reg_defaults_raw)
+		return -EINVAL;
+
+	if (!map->reg_defaults_raw) {
+		u32 cache_bypass = map->cache_bypass;
+		dev_warn(map->dev, "No cache defaults, reading back from HW\n");
+
+		/* Bypass the cache access till data read from HW*/
+		map->cache_bypass = 1;
+		tmp_buf = kmalloc(map->cache_size_raw, GFP_KERNEL);
+		if (!tmp_buf)
+			return -EINVAL;
+		ret = regmap_raw_read(map, 0, tmp_buf,
+				      map->num_reg_defaults_raw);
+		map->cache_bypass = cache_bypass;
+		if (ret < 0) {
+			kfree(tmp_buf);
+			return ret;
+		}
+		map->reg_defaults_raw = tmp_buf;
+		map->cache_free = 1;
+	}
+
+	/* calculate the size of reg_defaults */
+	for (count = 0, i = 0; i < map->num_reg_defaults_raw; i++) {
+		val = regcache_get_val(map, map->reg_defaults_raw, i);
+		if (regmap_volatile(map, i * map->reg_stride))
+			continue;
+		count++;
+	}
+
+	map->reg_defaults = kmalloc(count * sizeof(struct reg_default),
+				      GFP_KERNEL);
+	if (!map->reg_defaults) {
+		ret = -ENOMEM;
+		goto err_free;
+	}
+
+	/* fill the reg_defaults */
+	map->num_reg_defaults = count;
+	for (i = 0, j = 0; i < map->num_reg_defaults_raw; i++) {
+		val = regcache_get_val(map, map->reg_defaults_raw, i);
+		if (regmap_volatile(map, i * map->reg_stride))
+			continue;
+		map->reg_defaults[j].reg = i * map->reg_stride;
+		map->reg_defaults[j].def = val;
+		j++;
+	}
+
+	return 0;
+
+err_free:
+	if (map->cache_free)
+		kfree(map->reg_defaults_raw);
+
+	return ret;
+}
+
+int regcache_init(struct regmap *map, const struct regmap_config *config)
+{
+	int ret;
+	int i;
+	void *tmp_buf;
+
+	for (i = 0; i < config->num_reg_defaults; i++)
+		if (config->reg_defaults[i].reg % map->reg_stride)
+			return -EINVAL;
+
+	if (map->cache_type == REGCACHE_NONE) {
+		map->cache_bypass = true;
+		return 0;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(cache_types); i++)
+		if (cache_types[i]->type == map->cache_type)
+			break;
+
+	if (i == ARRAY_SIZE(cache_types)) {
+		dev_err(map->dev, "Could not match compress type: %d\n",
+			map->cache_type);
+		return -EINVAL;
+	}
+
+	map->num_reg_defaults = config->num_reg_defaults;
+	map->num_reg_defaults_raw = config->num_reg_defaults_raw;
+	map->reg_defaults_raw = config->reg_defaults_raw;
+	map->cache_word_size = DIV_ROUND_UP(config->val_bits, 8);
+	map->cache_size_raw = map->cache_word_size * config->num_reg_defaults_raw;
+	map->cache_present = NULL;
+	map->cache_present_nbits = 0;
+
+	map->cache = NULL;
+	map->cache_ops = cache_types[i];
+
+	if (!map->cache_ops->read ||
+	    !map->cache_ops->write ||
+	    !map->cache_ops->name)
+		return -EINVAL;
+
+	/* We still need to ensure that the reg_defaults
+	 * won't vanish from under us.  We'll need to make
+	 * a copy of it.
+	 */
+	if (config->reg_defaults) {
+		if (!map->num_reg_defaults)
+			return -EINVAL;
+		tmp_buf = kmemdup(config->reg_defaults, map->num_reg_defaults *
+				  sizeof(struct reg_default), GFP_KERNEL);
+		if (!tmp_buf)
+			return -ENOMEM;
+		map->reg_defaults = tmp_buf;
+	} else if (map->num_reg_defaults_raw) {
+		/* Some devices such as PMICs don't have cache defaults,
+		 * we cope with this by reading back the HW registers and
+		 * crafting the cache defaults by hand.
+		 */
+		ret = regcache_hw_init(map);
+		if (ret < 0)
+			return ret;
+	}
+
+	if (!map->max_register)
+		map->max_register = map->num_reg_defaults_raw;
+
+	if (map->cache_ops->init) {
+		dev_dbg(map->dev, "Initializing %s cache\n",
+			map->cache_ops->name);
+		ret = map->cache_ops->init(map);
+		if (ret)
+			goto err_free;
+	}
+	return 0;
+
+err_free:
+	kfree(map->reg_defaults);
+	if (map->cache_free)
+		kfree(map->reg_defaults_raw);
+
+	return ret;
+}
+
+void regcache_exit(struct regmap *map)
+{
+	if (map->cache_type == REGCACHE_NONE)
+		return;
+
+	BUG_ON(!map->cache_ops);
+
+	kfree(map->cache_present);
+	kfree(map->reg_defaults);
+	if (map->cache_free)
+		kfree(map->reg_defaults_raw);
+
+	if (map->cache_ops->exit) {
+		dev_dbg(map->dev, "Destroying %s cache\n",
+			map->cache_ops->name);
+		map->cache_ops->exit(map);
+	}
+}
+
+/**
+ * regcache_read: Fetch the value of a given register from the cache.
+ *
+ * @map: map to configure.
+ * @reg: The register index.
+ * @value: The value to be returned.
+ *
+ * Return a negative value on failure, 0 on success.
+ */
+int regcache_read(struct regmap *map,
+		  unsigned int reg, unsigned int *value)
+{
+	int ret;
+
+	if (map->cache_type == REGCACHE_NONE)
+		return -ENOSYS;
+
+	BUG_ON(!map->cache_ops);
+
+	if (!regmap_volatile(map, reg)) {
+		ret = map->cache_ops->read(map, reg, value);
+
+		if (ret == 0)
+			trace_regmap_reg_read_cache(map->dev, reg, *value);
+
+		return ret;
+	}
+
+	return -EINVAL;
+}
+
+/**
+ * regcache_write: Set the value of a given register in the cache.
+ *
+ * @map: map to configure.
+ * @reg: The register index.
+ * @value: The new register value.
+ *
+ * Return a negative value on failure, 0 on success.
+ */
+int regcache_write(struct regmap *map,
+		   unsigned int reg, unsigned int value)
+{
+	if (map->cache_type == REGCACHE_NONE)
+		return 0;
+
+	BUG_ON(!map->cache_ops);
+
+	if (!regmap_writeable(map, reg))
+		return -EIO;
+
+	if (!regmap_volatile(map, reg))
+		return map->cache_ops->write(map, reg, value);
+
+	return 0;
+}
+
+static int regcache_default_sync(struct regmap *map, unsigned int min,
+				 unsigned int max)
+{
+	unsigned int reg;
+
+	for (reg = min; reg <= max; reg += map->reg_stride) {
+		unsigned int val;
+		int ret;
+
+		if (regmap_volatile(map, reg) ||
+		    !regmap_writeable(map, reg))
+			continue;
+
+		ret = regcache_read(map, reg, &val);
+		if (ret)
+			return ret;
+
+		/* Is this the hardware default?  If so skip. */
+		ret = regcache_lookup_reg(map, reg);
+		if (ret >= 0 && val == map->reg_defaults[ret].def)
+			continue;
+
+		map->cache_bypass = 1;
+		ret = _regmap_write(map, reg, val);
+		map->cache_bypass = 0;
+		if (ret)
+			return ret;
+		dev_dbg(map->dev, "Synced register %#x, value %#x\n", reg, val);
+	}
+
+	return 0;
+}
+
+/**
+ * regcache_sync: Sync the register cache with the hardware.
+ *
+ * @map: map to configure.
+ *
+ * Any registers that should not be synced should be marked as
+ * volatile.  In general drivers can choose not to use the provided
+ * syncing functionality if they so require.
+ *
+ * Return a negative value on failure, 0 on success.
+ */
+int regcache_sync(struct regmap *map)
+{
+	int ret = 0;
+	unsigned int i;
+	const char *name;
+	unsigned int bypass;
+
+	BUG_ON(!map->cache_ops);
+
+	map->lock(map->lock_arg);
+	/* Remember the initial bypass state */
+	bypass = map->cache_bypass;
+	dev_dbg(map->dev, "Syncing %s cache\n",
+		map->cache_ops->name);
+	name = map->cache_ops->name;
+	trace_regcache_sync(map->dev, name, "start");
+
+	if (!map->cache_dirty)
+		goto out;
+
+	/* Apply any patch first */
+	map->cache_bypass = 1;
+	for (i = 0; i < map->patch_regs; i++) {
+		if (map->patch[i].reg % map->reg_stride) {
+			ret = -EINVAL;
+			goto out;
+		}
+		ret = _regmap_write(map, map->patch[i].reg, map->patch[i].def);
+		if (ret != 0) {
+			dev_err(map->dev, "Failed to write %x = %x: %d\n",
+				map->patch[i].reg, map->patch[i].def, ret);
+			goto out;
+		}
+	}
+	map->cache_bypass = 0;
+
+	if (map->cache_ops->sync)
+		ret = map->cache_ops->sync(map, 0, map->max_register);
+	else
+		ret = regcache_default_sync(map, 0, map->max_register);
+
+	if (ret == 0)
+		map->cache_dirty = false;
+
+out:
+	trace_regcache_sync(map->dev, name, "stop");
+	/* Restore the bypass state */
+	map->cache_bypass = bypass;
+	map->unlock(map->lock_arg);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(regcache_sync);
+
+/**
+ * regcache_sync_region: Sync part  of the register cache with the hardware.
+ *
+ * @map: map to sync.
+ * @min: first register to sync
+ * @max: last register to sync
+ *
+ * Write all non-default register values in the specified region to
+ * the hardware.
+ *
+ * Return a negative value on failure, 0 on success.
+ */
+int regcache_sync_region(struct regmap *map, unsigned int min,
+			 unsigned int max)
+{
+	int ret = 0;
+	const char *name;
+	unsigned int bypass;
+
+	BUG_ON(!map->cache_ops);
+
+	map->lock(map->lock_arg);
+
+	/* Remember the initial bypass state */
+	bypass = map->cache_bypass;
+
+	name = map->cache_ops->name;
+	dev_dbg(map->dev, "Syncing %s cache from %d-%d\n", name, min, max);
+
+	trace_regcache_sync(map->dev, name, "start region");
+
+	if (!map->cache_dirty)
+		goto out;
+
+	if (map->cache_ops->sync)
+		ret = map->cache_ops->sync(map, min, max);
+	else
+		ret = regcache_default_sync(map, min, max);
+
+out:
+	trace_regcache_sync(map->dev, name, "stop region");
+	/* Restore the bypass state */
+	map->cache_bypass = bypass;
+	map->unlock(map->lock_arg);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(regcache_sync_region);
+
+/**
+ * regcache_cache_only: Put a register map into cache only mode
+ *
+ * @map: map to configure
+ * @cache_only: flag if changes should be written to the hardware
+ *
+ * When a register map is marked as cache only writes to the register
+ * map API will only update the register cache, they will not cause
+ * any hardware changes.  This is useful for allowing portions of
+ * drivers to act as though the device were functioning as normal when
+ * it is disabled for power saving reasons.
+ */
+void regcache_cache_only(struct regmap *map, bool enable)
+{
+	map->lock(map->lock_arg);
+	WARN_ON(map->cache_bypass && enable);
+	map->cache_only = enable;
+	trace_regmap_cache_only(map->dev, enable);
+	map->unlock(map->lock_arg);
+}
+EXPORT_SYMBOL_GPL(regcache_cache_only);
+
+/**
+ * regcache_mark_dirty: Mark the register cache as dirty
+ *
+ * @map: map to mark
+ *
+ * Mark the register cache as dirty, for example due to the device
+ * having been powered down for suspend.  If the cache is not marked
+ * as dirty then the cache sync will be suppressed.
+ */
+void regcache_mark_dirty(struct regmap *map)
+{
+	map->lock(map->lock_arg);
+	map->cache_dirty = true;
+	map->unlock(map->lock_arg);
+}
+EXPORT_SYMBOL_GPL(regcache_mark_dirty);
+
+/**
+ * regcache_cache_bypass: Put a register map into cache bypass mode
+ *
+ * @map: map to configure
+ * @cache_bypass: flag if changes should not be written to the hardware
+ *
+ * When a register map is marked with the cache bypass option, writes
+ * to the register map API will only update the hardware and not the
+ * the cache directly.  This is useful when syncing the cache back to
+ * the hardware.
+ */
+void regcache_cache_bypass(struct regmap *map, bool enable)
+{
+	map->lock(map->lock_arg);
+	WARN_ON(map->cache_only && enable);
+	map->cache_bypass = enable;
+	trace_regmap_cache_bypass(map->dev, enable);
+	map->unlock(map->lock_arg);
+}
+EXPORT_SYMBOL_GPL(regcache_cache_bypass);
+
+int regcache_set_reg_present(struct regmap *map, unsigned int reg)
+{
+	unsigned long *cache_present;
+	unsigned int cache_present_size;
+	unsigned int nregs;
+	int i;
+
+	nregs = reg + 1;
+	cache_present_size = BITS_TO_LONGS(nregs);
+	cache_present_size *= sizeof(long);
+
+	if (!map->cache_present) {
+		cache_present = kmalloc(cache_present_size, GFP_KERNEL);
+		if (!cache_present)
+			return -ENOMEM;
+		bitmap_zero(cache_present, nregs);
+		map->cache_present = cache_present;
+		map->cache_present_nbits = nregs;
+	}
+
+	if (nregs > map->cache_present_nbits) {
+		cache_present = krealloc(map->cache_present,
+					 cache_present_size, GFP_KERNEL);
+		if (!cache_present)
+			return -ENOMEM;
+		for (i = 0; i < nregs; i++)
+			if (i >= map->cache_present_nbits)
+				clear_bit(i, cache_present);
+		map->cache_present = cache_present;
+		map->cache_present_nbits = nregs;
+	}
+
+	set_bit(reg, map->cache_present);
+	return 0;
+}
+
+bool regcache_set_val(struct regmap *map, void *base, unsigned int idx,
+		      unsigned int val)
+{
+	if (regcache_get_val(map, base, idx) == val)
+		return true;
+
+	/* Use device native format if possible */
+	if (map->format.format_val) {
+		map->format.format_val(base + (map->cache_word_size * idx),
+				       val, 0);
+		return false;
+	}
+
+	switch (map->cache_word_size) {
+	case 1: {
+		u8 *cache = base;
+		cache[idx] = val;
+		break;
+	}
+	case 2: {
+		u16 *cache = base;
+		cache[idx] = val;
+		break;
+	}
+	case 4: {
+		u32 *cache = base;
+		cache[idx] = val;
+		break;
+	}
+	default:
+		BUG();
+	}
+	return false;
+}
+
+unsigned int regcache_get_val(struct regmap *map, const void *base,
+			      unsigned int idx)
+{
+	if (!base)
+		return -EINVAL;
+
+	/* Use device native format if possible */
+	if (map->format.parse_val)
+		return map->format.parse_val(regcache_get_val_addr(map, base,
+								   idx));
+
+	switch (map->cache_word_size) {
+	case 1: {
+		const u8 *cache = base;
+		return cache[idx];
+	}
+	case 2: {
+		const u16 *cache = base;
+		return cache[idx];
+	}
+	case 4: {
+		const u32 *cache = base;
+		return cache[idx];
+	}
+	default:
+		BUG();
+	}
+	/* unreachable */
+	return -1;
+}
+
+static int regcache_default_cmp(const void *a, const void *b)
+{
+	const struct reg_default *_a = a;
+	const struct reg_default *_b = b;
+
+	return _a->reg - _b->reg;
+}
+
+int regcache_lookup_reg(struct regmap *map, unsigned int reg)
+{
+	struct reg_default key;
+	struct reg_default *r;
+
+	key.reg = reg;
+	key.def = 0;
+
+	r = bsearch(&key, map->reg_defaults, map->num_reg_defaults,
+		    sizeof(struct reg_default), regcache_default_cmp);
+
+	if (r)
+		return r - map->reg_defaults;
+	else
+		return -ENOENT;
+}
+
+static int regcache_sync_block_single(struct regmap *map, void *block,
+				      unsigned int block_base,
+				      unsigned int start, unsigned int end)
+{
+	unsigned int i, regtmp, val;
+	int ret;
+
+	for (i = start; i < end; i++) {
+		regtmp = block_base + (i * map->reg_stride);
+
+		if (!regcache_reg_present(map, regtmp))
+			continue;
+
+		val = regcache_get_val(map, block, i);
+
+		/* Is this the hardware default?  If so skip. */
+		ret = regcache_lookup_reg(map, regtmp);
+		if (ret >= 0 && val == map->reg_defaults[ret].def)
+			continue;
+
+		map->cache_bypass = 1;
+
+		ret = _regmap_write(map, regtmp, val);
+
+		map->cache_bypass = 0;
+		if (ret != 0)
+			return ret;
+		dev_dbg(map->dev, "Synced register %#x, value %#x\n",
+			regtmp, val);
+	}
+
+	return 0;
+}
+
+static int regcache_sync_block_raw_flush(struct regmap *map, const void **data,
+					 unsigned int base, unsigned int cur)
+{
+	size_t val_bytes = map->format.val_bytes;
+	int ret, count;
+
+	if (*data == NULL)
+		return 0;
+
+	count = (cur - base) / map->reg_stride;
+
+	dev_dbg(map->dev, "Writing %zu bytes for %d registers from 0x%x-0x%x\n",
+		count * val_bytes, count, base, cur - map->reg_stride);
+
+	map->cache_bypass = 1;
+
+	ret = _regmap_raw_write(map, base, *data, count * val_bytes,
+				false);
+
+	map->cache_bypass = 0;
+
+	*data = NULL;
+
+	return ret;
+}
+
+static int regcache_sync_block_raw(struct regmap *map, void *block,
+			    unsigned int block_base, unsigned int start,
+			    unsigned int end)
+{
+	unsigned int i, val;
+	unsigned int regtmp = 0;
+	unsigned int base = 0;
+	const void *data = NULL;
+	int ret;
+
+	for (i = start; i < end; i++) {
+		regtmp = block_base + (i * map->reg_stride);
+
+		if (!regcache_reg_present(map, regtmp)) {
+			ret = regcache_sync_block_raw_flush(map, &data,
+							    base, regtmp);
+			if (ret != 0)
+				return ret;
+			continue;
+		}
+
+		val = regcache_get_val(map, block, i);
+
+		/* Is this the hardware default?  If so skip. */
+		ret = regcache_lookup_reg(map, regtmp);
+		if (ret >= 0 && val == map->reg_defaults[ret].def) {
+			ret = regcache_sync_block_raw_flush(map, &data,
+							    base, regtmp);
+			if (ret != 0)
+				return ret;
+			continue;
+		}
+
+		if (!data) {
+			data = regcache_get_val_addr(map, block, i);
+			base = regtmp;
+		}
+	}
+
+	return regcache_sync_block_raw_flush(map, &data, base, regtmp +
+			map->reg_stride);
+}
+
+int regcache_sync_block(struct regmap *map, void *block,
+			unsigned int block_base, unsigned int start,
+			unsigned int end)
+{
+	if (regmap_can_raw_write(map))
+		return regcache_sync_block_raw(map, block, block_base,
+					       start, end);
+	else
+		return regcache_sync_block_single(map, block, block_base,
+						  start, end);
+}

drivers/base/regmap/regmap-debugfs.c

@@ -0,0 +1,532 @@
+/*
+ * Register map access API - debugfs
+ *
+ * Copyright 2011 Wolfson Microelectronics plc
+ *
+ * Author: Mark Brown <broonie@opensource.wolfsonmicro.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/slab.h>
+#include <linux/mutex.h>
+#include <linux/debugfs.h>
+#include <linux/uaccess.h>
+#include <linux/device.h>
+
+#include "internal.h"
+
+static struct dentry *regmap_debugfs_root;
+
+/* Calculate the length of a fixed format  */
+static size_t regmap_calc_reg_len(int max_val, char *buf, size_t buf_size)
+{
+	snprintf(buf, buf_size, "%x", max_val);
+	return strlen(buf);
+}
+
+static ssize_t regmap_name_read_file(struct file *file,
+				     char __user *user_buf, size_t count,
+				     loff_t *ppos)
+{
+	struct regmap *map = file->private_data;
+	int ret;
+	char *buf;
+
+	buf = kmalloc(PAGE_SIZE, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	ret = snprintf(buf, PAGE_SIZE, "%s\n", map->dev->driver->name);
+	if (ret < 0) {
+		kfree(buf);
+		return ret;
+	}
+
+	ret = simple_read_from_buffer(user_buf, count, ppos, buf, ret);
+	kfree(buf);
+	return ret;
+}
+
+static const struct file_operations regmap_name_fops = {
+	.open = simple_open,
+	.read = regmap_name_read_file,
+	.llseek = default_llseek,
+};
+
+static void regmap_debugfs_free_dump_cache(struct regmap *map)
+{
+	struct regmap_debugfs_off_cache *c;
+
+	while (!list_empty(&map->debugfs_off_cache)) {
+		c = list_first_entry(&map->debugfs_off_cache,
+				     struct regmap_debugfs_off_cache,
+				     list);
+		list_del(&c->list);
+		kfree(c);
+	}
+}
+
+/*
+ * Work out where the start offset maps into register numbers, bearing
+ * in mind that we suppress hidden registers.
+ */
+static unsigned int regmap_debugfs_get_dump_start(struct regmap *map,
+						  unsigned int base,
+						  loff_t from,
+						  loff_t *pos)
+{
+	struct regmap_debugfs_off_cache *c = NULL;
+	loff_t p = 0;
+	unsigned int i, ret;
+	unsigned int fpos_offset;
+	unsigned int reg_offset;
+
+	/*
+	 * If we don't have a cache build one so we don't have to do a
+	 * linear scan each time.
+	 */
+	mutex_lock(&map->cache_lock);
+	i = base;
+	if (list_empty(&map->debugfs_off_cache)) {
+		for (; i <= map->max_register; i += map->reg_stride) {
+			/* Skip unprinted registers, closing off cache entry */
+			if (!regmap_readable(map, i) ||
+			    regmap_precious(map, i)) {
+				if (c) {
+					c->max = p - 1;
+					c->max_reg = i - map->reg_stride;
+					list_add_tail(&c->list,
+						      &map->debugfs_off_cache);
+					c = NULL;
+				}
+
+				continue;
+			}
+
+			/* No cache entry?  Start a new one */
+			if (!c) {
+				c = kzalloc(sizeof(*c), GFP_KERNEL);
+				if (!c) {
+					regmap_debugfs_free_dump_cache(map);
+					mutex_unlock(&map->cache_lock);
+					return base;
+				}
+				c->min = p;
+				c->base_reg = i;
+			}
+
+			p += map->debugfs_tot_len;
+		}
+	}
+
+	/* Close the last entry off if we didn't scan beyond it */
+	if (c) {
+		c->max = p - 1;
+		c->max_reg = i - map->reg_stride;
+		list_add_tail(&c->list,
+			      &map->debugfs_off_cache);
+	}
+
+	/*
+	 * This should never happen; we return above if we fail to
+	 * allocate and we should never be in this code if there are
+	 * no registers at all.
+	 */
+	WARN_ON(list_empty(&map->debugfs_off_cache));
+	ret = base;
+
+	/* Find the relevant block:offset */
+	list_for_each_entry(c, &map->debugfs_off_cache, list) {
+		if (from >= c->min && from <= c->max) {
+			fpos_offset = from - c->min;
+			reg_offset = fpos_offset / map->debugfs_tot_len;
+			*pos = c->min + (reg_offset * map->debugfs_tot_len);
+			mutex_unlock(&map->cache_lock);
+			return c->base_reg + reg_offset;
+		}
+
+		*pos = c->max;
+		ret = c->max_reg;
+	}
+	mutex_unlock(&map->cache_lock);
+
+	return ret;
+}
+
+static inline void regmap_calc_tot_len(struct regmap *map,
+				       void *buf, size_t count)
+{
+	/* Calculate the length of a fixed format  */
+	if (!map->debugfs_tot_len) {
+		map->debugfs_reg_len = regmap_calc_reg_len(map->max_register,
+							   buf, count);
+		map->debugfs_val_len = 2 * map->format.val_bytes;
+		map->debugfs_tot_len = map->debugfs_reg_len +
+			map->debugfs_val_len + 3;      /* : \n */
+	}
+}
+
+static ssize_t regmap_read_debugfs(struct regmap *map, unsigned int from,
+				   unsigned int to, char __user *user_buf,
+				   size_t count, loff_t *ppos)
+{
+	size_t buf_pos = 0;
+	loff_t p = *ppos;
+	ssize_t ret;
+	int i;
+	char *buf;
+	unsigned int val, start_reg;
+
+	if (*ppos < 0 || !count)
+		return -EINVAL;
+
+	buf = kmalloc(count, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	regmap_calc_tot_len(map, buf, count);
+
+	/* Work out which register we're starting at */
+	start_reg = regmap_debugfs_get_dump_start(map, from, *ppos, &p);
+
+	for (i = start_reg; i <= to; i += map->reg_stride) {
+		if (!regmap_readable(map, i))
+			continue;
+
+		if (regmap_precious(map, i))
+			continue;
+
+		/* If we're in the region the user is trying to read */
+		if (p >= *ppos) {
+			/* ...but not beyond it */
+			if (buf_pos + map->debugfs_tot_len > count)
+				break;
+
+			/* Format the register */
+			snprintf(buf + buf_pos, count - buf_pos, "%.*x: ",
+				 map->debugfs_reg_len, i - from);
+			buf_pos += map->debugfs_reg_len + 2;
+
+			/* Format the value, write all X if we can't read */
+			ret = regmap_read(map, i, &val);
+			if (ret == 0)
+				snprintf(buf + buf_pos, count - buf_pos,
+					 "%.*x", map->debugfs_val_len, val);
+			else
+				memset(buf + buf_pos, 'X',
+				       map->debugfs_val_len);
+			buf_pos += 2 * map->format.val_bytes;
+
+			buf[buf_pos++] = '\n';
+		}
+		p += map->debugfs_tot_len;
+	}
+
+	ret = buf_pos;
+
+	if (copy_to_user(user_buf, buf, buf_pos)) {
+		ret = -EFAULT;
+		goto out;
+	}
+
+	*ppos += buf_pos;
+
+out:
+	kfree(buf);
+	return ret;
+}
+
+static ssize_t regmap_map_read_file(struct file *file, char __user *user_buf,
+				    size_t count, loff_t *ppos)
+{
+	struct regmap *map = file->private_data;
+
+	return regmap_read_debugfs(map, 0, map->max_register, user_buf,
+				   count, ppos);
+}
+
+#undef REGMAP_ALLOW_WRITE_DEBUGFS
+#ifdef REGMAP_ALLOW_WRITE_DEBUGFS
+/*
+ * This can be dangerous especially when we have clients such as
+ * PMICs, therefore don't provide any real compile time configuration option
+ * for this feature, people who want to use this will need to modify
+ * the source code directly.
+ */
+static ssize_t regmap_map_write_file(struct file *file,
+				     const char __user *user_buf,
+				     size_t count, loff_t *ppos)
+{
+	char buf[32];
+	size_t buf_size;
+	char *start = buf;
+	unsigned long reg, value;
+	struct regmap *map = file->private_data;
+	int ret;
+
+	buf_size = min(count, (sizeof(buf)-1));
+	if (copy_from_user(buf, user_buf, buf_size))
+		return -EFAULT;
+	buf[buf_size] = 0;
+
+	while (*start == ' ')
+		start++;
+	reg = simple_strtoul(start, &start, 16);
+	while (*start == ' ')
+		start++;
+	if (strict_strtoul(start, 16, &value))
+		return -EINVAL;
+
+	/* Userspace has been fiddling around behind the kernel's back */
+	add_taint(TAINT_USER, LOCKDEP_NOW_UNRELIABLE);
+
+	ret = regmap_write(map, reg, value);
+	if (ret < 0)
+		return ret;
+	return buf_size;
+}
+#else
+#define regmap_map_write_file NULL
+#endif
+
+static const struct file_operations regmap_map_fops = {
+	.open = simple_open,
+	.read = regmap_map_read_file,
+	.write = regmap_map_write_file,
+	.llseek = default_llseek,
+};
+
+static ssize_t regmap_range_read_file(struct file *file, char __user *user_buf,
+				      size_t count, loff_t *ppos)
+{
+	struct regmap_range_node *range = file->private_data;
+	struct regmap *map = range->map;
+
+	return regmap_read_debugfs(map, range->range_min, range->range_max,
+				   user_buf, count, ppos);
+}
+
+static const struct file_operations regmap_range_fops = {
+	.open = simple_open,
+	.read = regmap_range_read_file,
+	.llseek = default_llseek,
+};
+
+static ssize_t regmap_reg_ranges_read_file(struct file *file,
+					   char __user *user_buf, size_t count,
+					   loff_t *ppos)
+{
+	struct regmap *map = file->private_data;
+	struct regmap_debugfs_off_cache *c;
+	loff_t p = 0;
+	size_t buf_pos = 0;
+	char *buf;
+	char *entry;
+	int ret;
+
+	if (*ppos < 0 || !count)
+		return -EINVAL;
+
+	buf = kmalloc(count, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	entry = kmalloc(PAGE_SIZE, GFP_KERNEL);
+	if (!entry) {
+		kfree(buf);
+		return -ENOMEM;
+	}
+
+	/* While we are at it, build the register dump cache
+	 * now so the read() operation on the `registers' file
+	 * can benefit from using the cache.  We do not care
+	 * about the file position information that is contained
+	 * in the cache, just about the actual register blocks */
+	regmap_calc_tot_len(map, buf, count);
+	regmap_debugfs_get_dump_start(map, 0, *ppos, &p);
+
+	/* Reset file pointer as the fixed-format of the `registers'
+	 * file is not compatible with the `range' file */
+	p = 0;
+	mutex_lock(&map->cache_lock);
+	list_for_each_entry(c, &map->debugfs_off_cache, list) {
+		snprintf(entry, PAGE_SIZE, "%x-%x",
+			 c->base_reg, c->max_reg);
+		if (p >= *ppos) {
+			if (buf_pos + 1 + strlen(entry) > count)
+				break;
+			snprintf(buf + buf_pos, count - buf_pos,
+				 "%s", entry);
+			buf_pos += strlen(entry);
+			buf[buf_pos] = '\n';
+			buf_pos++;
+		}
+		p += strlen(entry) + 1;
+	}
+	mutex_unlock(&map->cache_lock);
+
+	kfree(entry);
+	ret = buf_pos;
+
+	if (copy_to_user(user_buf, buf, buf_pos)) {
+		ret = -EFAULT;
+		goto out_buf;
+	}
+
+	*ppos += buf_pos;
+out_buf:
+	kfree(buf);
+	return ret;
+}
+
+static const struct file_operations regmap_reg_ranges_fops = {
+	.open = simple_open,
+	.read = regmap_reg_ranges_read_file,
+	.llseek = default_llseek,
+};
+
+static ssize_t regmap_access_read_file(struct file *file,
+				       char __user *user_buf, size_t count,
+				       loff_t *ppos)
+{
+	int reg_len, tot_len;
+	size_t buf_pos = 0;
+	loff_t p = 0;
+	ssize_t ret;
+	int i;
+	struct regmap *map = file->private_data;
+	char *buf;
+
+	if (*ppos < 0 || !count)
+		return -EINVAL;
+
+	buf = kmalloc(count, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	/* Calculate the length of a fixed format  */
+	reg_len = regmap_calc_reg_len(map->max_register, buf, count);
+	tot_len = reg_len + 10; /* ': R W V P\n' */
+
+	for (i = 0; i <= map->max_register; i += map->reg_stride) {
+		/* Ignore registers which are neither readable nor writable */
+		if (!regmap_readable(map, i) && !regmap_writeable(map, i))
+			continue;
+
+		/* If we're in the region the user is trying to read */
+		if (p >= *ppos) {
+			/* ...but not beyond it */
+			if (buf_pos >= count - 1 - tot_len)
+				break;
+
+			/* Format the register */
+			snprintf(buf + buf_pos, count - buf_pos,
+				 "%.*x: %c %c %c %c\n",
+				 reg_len, i,
+				 regmap_readable(map, i) ? 'y' : 'n',
+				 regmap_writeable(map, i) ? 'y' : 'n',
+				 regmap_volatile(map, i) ? 'y' : 'n',
+				 regmap_precious(map, i) ? 'y' : 'n');
+
+			buf_pos += tot_len;
+		}
+		p += tot_len;
+	}
+
+	ret = buf_pos;
+
+	if (copy_to_user(user_buf, buf, buf_pos)) {
+		ret = -EFAULT;
+		goto out;
+	}
+
+	*ppos += buf_pos;
+
+out:
+	kfree(buf);
+	return ret;
+}
+
+static const struct file_operations regmap_access_fops = {
+	.open = simple_open,
+	.read = regmap_access_read_file,
+	.llseek = default_llseek,
+};
+
+void regmap_debugfs_init(struct regmap *map, const char *name)
+{
+	struct rb_node *next;
+	struct regmap_range_node *range_node;
+
+	INIT_LIST_HEAD(&map->debugfs_off_cache);
+	mutex_init(&map->cache_lock);
+
+	if (name) {
+		map->debugfs_name = kasprintf(GFP_KERNEL, "%s-%s",
+					      dev_name(map->dev), name);
+		name = map->debugfs_name;
+	} else {
+		name = dev_name(map->dev);
+	}
+
+	map->debugfs = debugfs_create_dir(name, regmap_debugfs_root);
+	if (!map->debugfs) {
+		dev_warn(map->dev, "Failed to create debugfs directory\n");
+		return;
+	}
+
+	debugfs_create_file("name", 0400, map->debugfs,
+			    map, &regmap_name_fops);
+
+	debugfs_create_file("range", 0400, map->debugfs,
+			    map, &regmap_reg_ranges_fops);
+
+	if (map->max_register) {
+		debugfs_create_file("registers", 0400, map->debugfs,
+				    map, &regmap_map_fops);
+		debugfs_create_file("access", 0400, map->debugfs,
+				    map, &regmap_access_fops);
+	}
+
+	if (map->cache_type) {
+		debugfs_create_bool("cache_only", 0400, map->debugfs,
+				    &map->cache_only);
+		debugfs_create_bool("cache_dirty", 0400, map->debugfs,
+				    &map->cache_dirty);
+		debugfs_create_bool("cache_bypass", 0400, map->debugfs,
+				    &map->cache_bypass);
+	}
+
+	next = rb_first(&map->range_tree);
+	while (next) {
+		range_node = rb_entry(next, struct regmap_range_node, node);
+
+		if (range_node->name)
+			debugfs_create_file(range_node->name, 0400,
+					    map->debugfs, range_node,
+					    &regmap_range_fops);
+
+		next = rb_next(&range_node->node);
+	}
+}
+
+void regmap_debugfs_exit(struct regmap *map)
+{
+	debugfs_remove_recursive(map->debugfs);
+	mutex_lock(&map->cache_lock);
+	regmap_debugfs_free_dump_cache(map);
+	mutex_unlock(&map->cache_lock);
+	kfree(map->debugfs_name);
+}
+
+void regmap_debugfs_initcall(void)
+{
+	regmap_debugfs_root = debugfs_create_dir("regmap", NULL);
+	if (!regmap_debugfs_root) {
+		pr_warn("regmap: Failed to create debugfs root\n");
+		return;
+	}
+}

drivers/base/regmap/regmap-i2c.c

@@ -0,0 +1,134 @@
+/*
+ * Register map access API - I2C support
+ *
+ * Copyright 2011 Wolfson Microelectronics plc
+ *
+ * Author: Mark Brown <broonie@opensource.wolfsonmicro.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/regmap.h>
+#include <linux/i2c.h>
+#include <linux/module.h>
+#include <linux/init.h>
+
+static int regmap_i2c_write(void *context, const void *data, size_t count)
+{
+	struct device *dev = context;
+	struct i2c_client *i2c = to_i2c_client(dev);
+	int ret;
+
+	ret = i2c_master_send(i2c, data, count);
+	if (ret == count)
+		return 0;
+	else if (ret < 0)
+		return ret;
+	else
+		return -EIO;
+}
+
+static int regmap_i2c_gather_write(void *context,
+				   const void *reg, size_t reg_size,
+				   const void *val, size_t val_size)
+{
+	struct device *dev = context;
+	struct i2c_client *i2c = to_i2c_client(dev);
+	struct i2c_msg xfer[2];
+	int ret;
+
+	/* If the I2C controller can't do a gather tell the core, it
+	 * will substitute in a linear write for us.
+	 */
+	if (!i2c_check_functionality(i2c->adapter, I2C_FUNC_NOSTART))
+		return -ENOTSUPP;
+
+	xfer[0].addr = i2c->addr;
+	xfer[0].flags = 0;
+	xfer[0].len = reg_size;
+	xfer[0].buf = (void *)reg;
+
+	xfer[1].addr = i2c->addr;
+	xfer[1].flags = I2C_M_NOSTART;
+	xfer[1].len = val_size;
+	xfer[1].buf = (void *)val;
+
+	ret = i2c_transfer(i2c->adapter, xfer, 2);
+	if (ret == 2)
+		return 0;
+	if (ret < 0)
+		return ret;
+	else
+		return -EIO;
+}
+
+static int regmap_i2c_read(void *context,
+			   const void *reg, size_t reg_size,
+			   void *val, size_t val_size)
+{
+	struct device *dev = context;
+	struct i2c_client *i2c = to_i2c_client(dev);
+	struct i2c_msg xfer[2];
+	int ret;
+
+	xfer[0].addr = i2c->addr;
+	xfer[0].flags = 0;
+	xfer[0].len = reg_size;
+	xfer[0].buf = (void *)reg;
+
+	xfer[1].addr = i2c->addr;
+	xfer[1].flags = I2C_M_RD;
+	xfer[1].len = val_size;
+	xfer[1].buf = val;
+
+	ret = i2c_transfer(i2c->adapter, xfer, 2);
+	if (ret == 2)
+		return 0;
+	else if (ret < 0)
+		return ret;
+	else
+		return -EIO;
+}
+
+static struct regmap_bus regmap_i2c = {
+	.write = regmap_i2c_write,
+	.gather_write = regmap_i2c_gather_write,
+	.read = regmap_i2c_read,
+};
+
+/**
+ * regmap_init_i2c(): Initialise register map
+ *
+ * @i2c: Device that will be interacted with
+ * @config: Configuration for register map
+ *
+ * The return value will be an ERR_PTR() on error or a valid pointer to
+ * a struct regmap.
+ */
+struct regmap *regmap_init_i2c(struct i2c_client *i2c,
+			       const struct regmap_config *config)
+{
+	return regmap_init(&i2c->dev, &regmap_i2c, &i2c->dev, config);
+}
+EXPORT_SYMBOL_GPL(regmap_init_i2c);
+
+/**
+ * devm_regmap_init_i2c(): Initialise managed register map
+ *
+ * @i2c: Device that will be interacted with
+ * @config: Configuration for register map
+ *
+ * The return value will be an ERR_PTR() on error or a valid pointer
+ * to a struct regmap.  The regmap will be automatically freed by the
+ * device management code.
+ */
+struct regmap *devm_regmap_init_i2c(struct i2c_client *i2c,
+				    const struct regmap_config *config)
+{
+	return devm_regmap_init(&i2c->dev, &regmap_i2c, &i2c->dev, config);
+}
+EXPORT_SYMBOL_GPL(devm_regmap_init_i2c);
+
+MODULE_LICENSE("GPL");

drivers/base/regmap/regmap-irq.c

@@ -0,0 +1,554 @@
+/*
+ * regmap based irq_chip
+ *
+ * Copyright 2011 Wolfson Microelectronics plc
+ *
+ * Author: Mark Brown <broonie@opensource.wolfsonmicro.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/export.h>
+#include <linux/device.h>
+#include <linux/regmap.h>
+#include <linux/irq.h>
+#include <linux/interrupt.h>
+#include <linux/irqdomain.h>
+#include <linux/pm_runtime.h>
+#include <linux/slab.h>
+
+#include "internal.h"
+
+struct regmap_irq_chip_data {
+	struct mutex lock;
+	struct irq_chip irq_chip;
+
+	struct regmap *map;
+	const struct regmap_irq_chip *chip;
+
+	int irq_base;
+	struct irq_domain *domain;
+
+	int irq;
+	int wake_count;
+
+	void *status_reg_buf;
+	unsigned int *status_buf;
+	unsigned int *mask_buf;
+	unsigned int *mask_buf_def;
+	unsigned int *wake_buf;
+
+	unsigned int irq_reg_stride;
+};
+
+static inline const
+struct regmap_irq *irq_to_regmap_irq(struct regmap_irq_chip_data *data,
+				     int irq)
+{
+	return &data->chip->irqs[irq];
+}
+
+static void regmap_irq_lock(struct irq_data *data)
+{
+	struct regmap_irq_chip_data *d = irq_data_get_irq_chip_data(data);
+
+	mutex_lock(&d->lock);
+}
+
+static void regmap_irq_sync_unlock(struct irq_data *data)
+{
+	struct regmap_irq_chip_data *d = irq_data_get_irq_chip_data(data);
+	struct regmap *map = d->map;
+	int i, ret;
+	u32 reg;
+
+	if (d->chip->runtime_pm) {
+		ret = pm_runtime_get_sync(map->dev);
+		if (ret < 0)
+			dev_err(map->dev, "IRQ sync failed to resume: %d\n",
+				ret);
+	}
+
+	/*
+	 * If there's been a change in the mask write it back to the
+	 * hardware.  We rely on the use of the regmap core cache to
+	 * suppress pointless writes.
+	 */
+	for (i = 0; i < d->chip->num_regs; i++) {
+		reg = d->chip->mask_base +
+			(i * map->reg_stride * d->irq_reg_stride);
+		if (d->chip->mask_invert)
+			ret = regmap_update_bits(d->map, reg,
+					 d->mask_buf_def[i], ~d->mask_buf[i]);
+		else
+			ret = regmap_update_bits(d->map, reg,
+					 d->mask_buf_def[i], d->mask_buf[i]);
+		if (ret != 0)
+			dev_err(d->map->dev, "Failed to sync masks in %x\n",
+				reg);
+
+		reg = d->chip->wake_base +
+			(i * map->reg_stride * d->irq_reg_stride);
+		if (d->wake_buf) {
+			if (d->chip->wake_invert)
+				ret = regmap_update_bits(d->map, reg,
+							 d->mask_buf_def[i],
+							 ~d->wake_buf[i]);
+			else
+				ret = regmap_update_bits(d->map, reg,
+							 d->mask_buf_def[i],
+							 d->wake_buf[i]);
+			if (ret != 0)
+				dev_err(d->map->dev,
+					"Failed to sync wakes in %x: %d\n",
+					reg, ret);
+		}
+	}
+
+	if (d->chip->runtime_pm)
+		pm_runtime_put(map->dev);
+
+	/* If we've changed our wakeup count propagate it to the parent */
+	if (d->wake_count < 0)
+		for (i = d->wake_count; i < 0; i++)
+			irq_set_irq_wake(d->irq, 0);
+	else if (d->wake_count > 0)
+		for (i = 0; i < d->wake_count; i++)
+			irq_set_irq_wake(d->irq, 1);
+
+	d->wake_count = 0;
+
+	mutex_unlock(&d->lock);
+}
+
+static void regmap_irq_enable(struct irq_data *data)
+{
+	struct regmap_irq_chip_data *d = irq_data_get_irq_chip_data(data);
+	struct regmap *map = d->map;
+	const struct regmap_irq *irq_data = irq_to_regmap_irq(d, data->hwirq);
+
+	d->mask_buf[irq_data->reg_offset / map->reg_stride] &= ~irq_data->mask;
+}
+
+static void regmap_irq_disable(struct irq_data *data)
+{
+	struct regmap_irq_chip_data *d = irq_data_get_irq_chip_data(data);
+	struct regmap *map = d->map;
+	const struct regmap_irq *irq_data = irq_to_regmap_irq(d, data->hwirq);
+
+	d->mask_buf[irq_data->reg_offset / map->reg_stride] |= irq_data->mask;
+}
+
+static int regmap_irq_set_wake(struct irq_data *data, unsigned int on)
+{
+	struct regmap_irq_chip_data *d = irq_data_get_irq_chip_data(data);
+	struct regmap *map = d->map;
+	const struct regmap_irq *irq_data = irq_to_regmap_irq(d, data->hwirq);
+
+	if (on) {
+		if (d->wake_buf)
+			d->wake_buf[irq_data->reg_offset / map->reg_stride]
+				&= ~irq_data->mask;
+		d->wake_count++;
+	} else {
+		if (d->wake_buf)
+			d->wake_buf[irq_data->reg_offset / map->reg_stride]
+				|= irq_data->mask;
+		d->wake_count--;
+	}
+
+	return 0;
+}
+
+static const struct irq_chip regmap_irq_chip = {
+	.irq_bus_lock		= regmap_irq_lock,
+	.irq_bus_sync_unlock	= regmap_irq_sync_unlock,
+	.irq_disable		= regmap_irq_disable,
+	.irq_enable		= regmap_irq_enable,
+	.irq_set_wake		= regmap_irq_set_wake,
+};
+
+static irqreturn_t regmap_irq_thread(int irq, void *d)
+{
+	struct regmap_irq_chip_data *data = d;
+	const struct regmap_irq_chip *chip = data->chip;
+	struct regmap *map = data->map;
+	int ret, i;
+	bool handled = false;
+	u32 reg;
+
+	if (chip->runtime_pm) {
+		ret = pm_runtime_get_sync(map->dev);
+		if (ret < 0) {
+			dev_err(map->dev, "IRQ thread failed to resume: %d\n",
+				ret);
+			pm_runtime_put(map->dev);
+			return IRQ_NONE;
+		}
+	}
+
+	/*
+	 * Read in the statuses, using a single bulk read if possible
+	 * in order to reduce the I/O overheads.
+	 */
+	if (!map->use_single_rw && map->reg_stride == 1 &&
+	    data->irq_reg_stride == 1) {
+		u8 *buf8 = data->status_reg_buf;
+		u16 *buf16 = data->status_reg_buf;
+		u32 *buf32 = data->status_reg_buf;
+
+		BUG_ON(!data->status_reg_buf);
+
+		ret = regmap_bulk_read(map, chip->status_base,
+				       data->status_reg_buf,
+				       chip->num_regs);
+		if (ret != 0) {
+			dev_err(map->dev, "Failed to read IRQ status: %d\n",
+				ret);
+			return IRQ_NONE;
+		}
+
+		for (i = 0; i < data->chip->num_regs; i++) {
+			switch (map->format.val_bytes) {
+			case 1:
+				data->status_buf[i] = buf8[i];
+				break;
+			case 2:
+				data->status_buf[i] = buf16[i];
+				break;
+			case 4:
+				data->status_buf[i] = buf32[i];
+				break;
+			default:
+				BUG();
+				return IRQ_NONE;
+			}
+		}
+
+	} else {
+		for (i = 0; i < data->chip->num_regs; i++) {
+			ret = regmap_read(map, chip->status_base +
+					  (i * map->reg_stride
+					   * data->irq_reg_stride),
+					  &data->status_buf[i]);
+
+			if (ret != 0) {
+				dev_err(map->dev,
+					"Failed to read IRQ status: %d\n",
+					ret);
+				if (chip->runtime_pm)
+					pm_runtime_put(map->dev);
+				return IRQ_NONE;
+			}
+		}
+	}
+
+	/*
+	 * Ignore masked IRQs and ack if we need to; we ack early so
+	 * there is no race between handling and acknowleding the
+	 * interrupt.  We assume that typically few of the interrupts
+	 * will fire simultaneously so don't worry about overhead from
+	 * doing a write per register.
+	 */
+	for (i = 0; i < data->chip->num_regs; i++) {
+		data->status_buf[i] &= ~data->mask_buf[i];
+
+		if (data->status_buf[i] && chip->ack_base) {
+			reg = chip->ack_base +
+				(i * map->reg_stride * data->irq_reg_stride);
+			ret = regmap_write(map, reg, data->status_buf[i]);
+			if (ret != 0)
+				dev_err(map->dev, "Failed to ack 0x%x: %d\n",
+					reg, ret);
+		}
+	}
+
+	for (i = 0; i < chip->num_irqs; i++) {
+		if (data->status_buf[chip->irqs[i].reg_offset /
+				     map->reg_stride] & chip->irqs[i].mask) {
+			handle_nested_irq(irq_find_mapping(data->domain, i));
+			handled = true;
+		}
+	}
+
+	if (chip->runtime_pm)
+		pm_runtime_put(map->dev);
+
+	if (handled)
+		return IRQ_HANDLED;
+	else
+		return IRQ_NONE;
+}
+
+static int regmap_irq_map(struct irq_domain *h, unsigned int virq,
+			  irq_hw_number_t hw)
+{
+	struct regmap_irq_chip_data *data = h->host_data;
+
+	irq_set_chip_data(virq, data);
+	irq_set_chip(virq, &data->irq_chip);
+	irq_set_nested_thread(virq, 1);
+
+	/* ARM needs us to explicitly flag the IRQ as valid
+	 * and will set them noprobe when we do so. */
+#ifdef CONFIG_ARM
+	set_irq_flags(virq, IRQF_VALID);
+#else
+	irq_set_noprobe(virq);
+#endif
+
+	return 0;
+}
+
+static struct irq_domain_ops regmap_domain_ops = {
+	.map	= regmap_irq_map,
+	.xlate	= irq_domain_xlate_twocell,
+};
+
+/**
+ * regmap_add_irq_chip(): Use standard regmap IRQ controller handling
+ *
+ * map:       The regmap for the device.
+ * irq:       The IRQ the device uses to signal interrupts
+ * irq_flags: The IRQF_ flags to use for the primary interrupt.
+ * chip:      Configuration for the interrupt controller.
+ * data:      Runtime data structure for the controller, allocated on success
+ *
+ * Returns 0 on success or an errno on failure.
+ *
+ * In order for this to be efficient the chip really should use a
+ * register cache.  The chip driver is responsible for restoring the
+ * register values used by the IRQ controller over suspend and resume.
+ */
+int regmap_add_irq_chip(struct regmap *map, int irq, int irq_flags,
+			int irq_base, const struct regmap_irq_chip *chip,
+			struct regmap_irq_chip_data **data)
+{
+	struct regmap_irq_chip_data *d;
+	int i;
+	int ret = -ENOMEM;
+	u32 reg;
+
+	for (i = 0; i < chip->num_irqs; i++) {
+		if (chip->irqs[i].reg_offset % map->reg_stride)
+			return -EINVAL;
+		if (chip->irqs[i].reg_offset / map->reg_stride >=
+		    chip->num_regs)
+			return -EINVAL;
+	}
+
+	if (irq_base) {
+		irq_base = irq_alloc_descs(irq_base, 0, chip->num_irqs, 0);
+		if (irq_base < 0) {
+			dev_warn(map->dev, "Failed to allocate IRQs: %d\n",
+				 irq_base);
+			return irq_base;
+		}
+	}
+
+	d = kzalloc(sizeof(*d), GFP_KERNEL);
+	if (!d)
+		return -ENOMEM;
+
+	*data = d;
+
+	d->status_buf = kzalloc(sizeof(unsigned int) * chip->num_regs,
+				GFP_KERNEL);
+	if (!d->status_buf)
+		goto err_alloc;
+
+	d->mask_buf = kzalloc(sizeof(unsigned int) * chip->num_regs,
+			      GFP_KERNEL);
+	if (!d->mask_buf)
+		goto err_alloc;
+
+	d->mask_buf_def = kzalloc(sizeof(unsigned int) * chip->num_regs,
+				  GFP_KERNEL);
+	if (!d->mask_buf_def)
+		goto err_alloc;
+
+	if (chip->wake_base) {
+		d->wake_buf = kzalloc(sizeof(unsigned int) * chip->num_regs,
+				      GFP_KERNEL);
+		if (!d->wake_buf)
+			goto err_alloc;
+	}
+
+	d->irq_chip = regmap_irq_chip;
+	d->irq_chip.name = chip->name;
+	d->irq = irq;
+	d->map = map;
+	d->chip = chip;
+	d->irq_base = irq_base;
+
+	if (chip->irq_reg_stride)
+		d->irq_reg_stride = chip->irq_reg_stride;
+	else
+		d->irq_reg_stride = 1;
+
+	if (!map->use_single_rw && map->reg_stride == 1 &&
+	    d->irq_reg_stride == 1) {
+		d->status_reg_buf = kmalloc(map->format.val_bytes *
+					    chip->num_regs, GFP_KERNEL);
+		if (!d->status_reg_buf)
+			goto err_alloc;
+	}
+
+	mutex_init(&d->lock);
+
+	for (i = 0; i < chip->num_irqs; i++)
+		d->mask_buf_def[chip->irqs[i].reg_offset / map->reg_stride]
+			|= chip->irqs[i].mask;
+
+	/* Mask all the interrupts by default */
+	for (i = 0; i < chip->num_regs; i++) {
+		d->mask_buf[i] = d->mask_buf_def[i];
+		reg = chip->mask_base +
+			(i * map->reg_stride * d->irq_reg_stride);
+		if (chip->mask_invert)
+			ret = regmap_update_bits(map, reg,
+					 d->mask_buf[i], ~d->mask_buf[i]);
+		else
+			ret = regmap_update_bits(map, reg,
+					 d->mask_buf[i], d->mask_buf[i]);
+		if (ret != 0) {
+			dev_err(map->dev, "Failed to set masks in 0x%x: %d\n",
+				reg, ret);
+			goto err_alloc;
+		}
+	}
+
+	/* Wake is disabled by default */
+	if (d->wake_buf) {
+		for (i = 0; i < chip->num_regs; i++) {
+			d->wake_buf[i] = d->mask_buf_def[i];
+			reg = chip->wake_base +
+				(i * map->reg_stride * d->irq_reg_stride);
+
+			if (chip->wake_invert)
+				ret = regmap_update_bits(map, reg,
+							 d->mask_buf_def[i],
+							 0);
+			else
+				ret = regmap_update_bits(map, reg,
+							 d->mask_buf_def[i],
+							 d->wake_buf[i]);
+			if (ret != 0) {
+				dev_err(map->dev, "Failed to set masks in 0x%x: %d\n",
+					reg, ret);
+				goto err_alloc;
+			}
+		}
+	}
+
+	if (irq_base)
+		d->domain = irq_domain_add_legacy(map->dev->of_node,
+						  chip->num_irqs, irq_base, 0,
+						  &regmap_domain_ops, d);
+	else
+		d->domain = irq_domain_add_linear(map->dev->of_node,
+						  chip->num_irqs,
+						  &regmap_domain_ops, d);
+	if (!d->domain) {
+		dev_err(map->dev, "Failed to create IRQ domain\n");
+		ret = -ENOMEM;
+		goto err_alloc;
+	}
+
+	ret = request_threaded_irq(irq, NULL, regmap_irq_thread, irq_flags,
+				   chip->name, d);
+	if (ret != 0) {
+		dev_err(map->dev, "Failed to request IRQ %d for %s: %d\n",
+			irq, chip->name, ret);
+		goto err_domain;
+	}
+
+	return 0;
+
+err_domain:
+	/* Should really dispose of the domain but... */
+err_alloc:
+	kfree(d->wake_buf);
+	kfree(d->mask_buf_def);
+	kfree(d->mask_buf);
+	kfree(d->status_buf);
+	kfree(d->status_reg_buf);
+	kfree(d);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(regmap_add_irq_chip);
+
+/**
+ * regmap_del_irq_chip(): Stop interrupt handling for a regmap IRQ chip
+ *
+ * @irq: Primary IRQ for the device
+ * @d:   regmap_irq_chip_data allocated by regmap_add_irq_chip()
+ */
+void regmap_del_irq_chip(int irq, struct regmap_irq_chip_data *d)
+{
+	if (!d)
+		return;
+
+	free_irq(irq, d);
+	/* We should unmap the domain but... */
+	kfree(d->wake_buf);
+	kfree(d->mask_buf_def);
+	kfree(d->mask_buf);
+	kfree(d->status_reg_buf);
+	kfree(d->status_buf);
+	kfree(d);
+}
+EXPORT_SYMBOL_GPL(regmap_del_irq_chip);
+
+/**
+ * regmap_irq_chip_get_base(): Retrieve interrupt base for a regmap IRQ chip
+ *
+ * Useful for drivers to request their own IRQs.
+ *
+ * @data: regmap_irq controller to operate on.
+ */
+int regmap_irq_chip_get_base(struct regmap_irq_chip_data *data)
+{
+	WARN_ON(!data->irq_base);
+	return data->irq_base;
+}
+EXPORT_SYMBOL_GPL(regmap_irq_chip_get_base);
+
+/**
+ * regmap_irq_get_virq(): Map an interrupt on a chip to a virtual IRQ
+ *
+ * Useful for drivers to request their own IRQs.
+ *
+ * @data: regmap_irq controller to operate on.
+ * @irq: index of the interrupt requested in the chip IRQs
+ */
+int regmap_irq_get_virq(struct regmap_irq_chip_data *data, int irq)
+{
+	/* Handle holes in the IRQ list */
+	if (!data->chip->irqs[irq].mask)
+		return -EINVAL;
+
+	return irq_create_mapping(data->domain, irq);
+}
+EXPORT_SYMBOL_GPL(regmap_irq_get_virq);
+
+/**
+ * regmap_irq_get_domain(): Retrieve the irq_domain for the chip
+ *
+ * Useful for drivers to request their own IRQs and for integration
+ * with subsystems.  For ease of integration NULL is accepted as a
+ * domain, allowing devices to just call this even if no domain is
+ * allocated.
+ *
+ * @data: regmap_irq controller to operate on.
+ */
+struct irq_domain *regmap_irq_get_domain(struct regmap_irq_chip_data *data)
+{
+	if (data)
+		return data->domain;
+	else
+		return NULL;
+}
+EXPORT_SYMBOL_GPL(regmap_irq_get_domain);

drivers/base/regmap/regmap-mmio.c

@@ -0,0 +1,287 @@
+/*
+ * Register map access API - MMIO support
+ *
+ * Copyright (c) 2012, NVIDIA CORPORATION.  All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/clk.h>
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/regmap.h>
+#include <linux/slab.h>
+
+struct regmap_mmio_context {
+	void __iomem *regs;
+	unsigned val_bytes;
+	struct clk *clk;
+};
+
+static int regmap_mmio_gather_write(void *context,
+				    const void *reg, size_t reg_size,
+				    const void *val, size_t val_size)
+{
+	struct regmap_mmio_context *ctx = context;
+	u32 offset;
+	int ret;
+
+	BUG_ON(reg_size != 4);
+
+	if (ctx->clk) {
+		ret = clk_enable(ctx->clk);
+		if (ret < 0)
+			return ret;
+	}
+
+	offset = *(u32 *)reg;
+
+	while (val_size) {
+		switch (ctx->val_bytes) {
+		case 1:
+			writeb(*(u8 *)val, ctx->regs + offset);
+			break;
+		case 2:
+			writew(*(u16 *)val, ctx->regs + offset);
+			break;
+		case 4:
+			writel(*(u32 *)val, ctx->regs + offset);
+			break;
+#ifdef CONFIG_64BIT
+		case 8:
+			writeq(*(u64 *)val, ctx->regs + offset);
+			break;
+#endif
+		default:
+			/* Should be caught by regmap_mmio_check_config */
+			BUG();
+		}
+		val_size -= ctx->val_bytes;
+		val += ctx->val_bytes;
+		offset += ctx->val_bytes;
+	}
+
+	if (ctx->clk)
+		clk_disable(ctx->clk);
+
+	return 0;
+}
+
+static int regmap_mmio_write(void *context, const void *data, size_t count)
+{
+	BUG_ON(count < 4);
+
+	return regmap_mmio_gather_write(context, data, 4, data + 4, count - 4);
+}
+
+static int regmap_mmio_read(void *context,
+			    const void *reg, size_t reg_size,
+			    void *val, size_t val_size)
+{
+	struct regmap_mmio_context *ctx = context;
+	u32 offset;
+	int ret;
+
+	BUG_ON(reg_size != 4);
+
+	if (ctx->clk) {
+		ret = clk_enable(ctx->clk);
+		if (ret < 0)
+			return ret;
+	}
+
+	offset = *(u32 *)reg;
+
+	while (val_size) {
+		switch (ctx->val_bytes) {
+		case 1:
+			*(u8 *)val = readb(ctx->regs + offset);
+			break;
+		case 2:
+			*(u16 *)val = readw(ctx->regs + offset);
+			break;
+		case 4:
+			*(u32 *)val = readl(ctx->regs + offset);
+			break;
+#ifdef CONFIG_64BIT
+		case 8:
+			*(u64 *)val = readq(ctx->regs + offset);
+			break;
+#endif
+		default:
+			/* Should be caught by regmap_mmio_check_config */
+			BUG();
+		}
+		val_size -= ctx->val_bytes;
+		val += ctx->val_bytes;
+		offset += ctx->val_bytes;
+	}
+
+	if (ctx->clk)
+		clk_disable(ctx->clk);
+
+	return 0;
+}
+
+static void regmap_mmio_free_context(void *context)
+{
+	struct regmap_mmio_context *ctx = context;
+
+	if (ctx->clk) {
+		clk_unprepare(ctx->clk);
+		clk_put(ctx->clk);
+	}
+	kfree(context);
+}
+
+static struct regmap_bus regmap_mmio = {
+	.fast_io = true,
+	.write = regmap_mmio_write,
+	.gather_write = regmap_mmio_gather_write,
+	.read = regmap_mmio_read,
+	.free_context = regmap_mmio_free_context,
+	.reg_format_endian_default = REGMAP_ENDIAN_NATIVE,
+	.val_format_endian_default = REGMAP_ENDIAN_NATIVE,
+};
+
+static struct regmap_mmio_context *regmap_mmio_gen_context(struct device *dev,
+					const char *clk_id,
+					void __iomem *regs,
+					const struct regmap_config *config)
+{
+	struct regmap_mmio_context *ctx;
+	int min_stride;
+	int ret;
+
+	if (config->reg_bits != 32)
+		return ERR_PTR(-EINVAL);
+
+	if (config->pad_bits)
+		return ERR_PTR(-EINVAL);
+
+	switch (config->val_bits) {
+	case 8:
+		/* The core treats 0 as 1 */
+		min_stride = 0;
+		break;
+	case 16:
+		min_stride = 2;
+		break;
+	case 32:
+		min_stride = 4;
+		break;
+#ifdef CONFIG_64BIT
+	case 64:
+		min_stride = 8;
+		break;
+#endif
+		break;
+	default:
+		return ERR_PTR(-EINVAL);
+	}
+
+	if (config->reg_stride < min_stride)
+		return ERR_PTR(-EINVAL);
+
+	switch (config->reg_format_endian) {
+	case REGMAP_ENDIAN_DEFAULT:
+	case REGMAP_ENDIAN_NATIVE:
+		break;
+	default:
+		return ERR_PTR(-EINVAL);
+	}
+
+	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
+	if (!ctx)
+		return ERR_PTR(-ENOMEM);
+
+	ctx->regs = regs;
+	ctx->val_bytes = config->val_bits / 8;
+
+	if (clk_id == NULL)
+		return ctx;
+
+	ctx->clk = clk_get(dev, clk_id);
+	if (IS_ERR(ctx->clk)) {
+		ret = PTR_ERR(ctx->clk);
+		goto err_free;
+	}
+
+	ret = clk_prepare(ctx->clk);
+	if (ret < 0) {
+		clk_put(ctx->clk);
+		goto err_free;
+	}
+
+	return ctx;
+
+err_free:
+	kfree(ctx);
+
+	return ERR_PTR(ret);
+}
+
+/**
+ * regmap_init_mmio_clk(): Initialise register map with register clock
+ *
+ * @dev: Device that will be interacted with
+ * @clk_id: register clock consumer ID
+ * @regs: Pointer to memory-mapped IO region
+ * @config: Configuration for register map
+ *
+ * The return value will be an ERR_PTR() on error or a valid pointer to
+ * a struct regmap.
+ */
+struct regmap *regmap_init_mmio_clk(struct device *dev, const char *clk_id,
+				    void __iomem *regs,
+				    const struct regmap_config *config)
+{
+	struct regmap_mmio_context *ctx;
+
+	ctx = regmap_mmio_gen_context(dev, clk_id, regs, config);
+	if (IS_ERR(ctx))
+		return ERR_CAST(ctx);
+
+	return regmap_init(dev, &regmap_mmio, ctx, config);
+}
+EXPORT_SYMBOL_GPL(regmap_init_mmio_clk);
+
+/**
+ * devm_regmap_init_mmio_clk(): Initialise managed register map with clock
+ *
+ * @dev: Device that will be interacted with
+ * @clk_id: register clock consumer ID
+ * @regs: Pointer to memory-mapped IO region
+ * @config: Configuration for register map
+ *
+ * The return value will be an ERR_PTR() on error or a valid pointer
+ * to a struct regmap.  The regmap will be automatically freed by the
+ * device management code.
+ */
+struct regmap *devm_regmap_init_mmio_clk(struct device *dev, const char *clk_id,
+					 void __iomem *regs,
+					 const struct regmap_config *config)
+{
+	struct regmap_mmio_context *ctx;
+
+	ctx = regmap_mmio_gen_context(dev, clk_id, regs, config);
+	if (IS_ERR(ctx))
+		return ERR_CAST(ctx);
+
+	return devm_regmap_init(dev, &regmap_mmio, ctx, config);
+}
+EXPORT_SYMBOL_GPL(devm_regmap_init_mmio_clk);
+
+MODULE_LICENSE("GPL v2");

drivers/base/regmap/regmap-spi.c

@@ -0,0 +1,147 @@
+/*
+ * Register map access API - SPI support
+ *
+ * Copyright 2011 Wolfson Microelectronics plc
+ *
+ * Author: Mark Brown <broonie@opensource.wolfsonmicro.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/regmap.h>
+#include <linux/spi/spi.h>
+#include <linux/init.h>
+#include <linux/module.h>
+
+#include "internal.h"
+
+struct regmap_async_spi {
+	struct regmap_async core;
+	struct spi_message m;
+	struct spi_transfer t[2];
+};
+
+static void regmap_spi_complete(void *data)
+{
+	struct regmap_async_spi *async = data;
+
+	regmap_async_complete_cb(&async->core, async->m.status);
+}
+
+static int regmap_spi_write(void *context, const void *data, size_t count)
+{
+	struct device *dev = context;
+	struct spi_device *spi = to_spi_device(dev);
+
+	return spi_write(spi, data, count);
+}
+
+static int regmap_spi_gather_write(void *context,
+				   const void *reg, size_t reg_len,
+				   const void *val, size_t val_len)
+{
+	struct device *dev = context;
+	struct spi_device *spi = to_spi_device(dev);
+	struct spi_message m;
+	struct spi_transfer t[2] = { { .tx_buf = reg, .len = reg_len, },
+				     { .tx_buf = val, .len = val_len, }, };
+
+	spi_message_init(&m);
+	spi_message_add_tail(&t[0], &m);
+	spi_message_add_tail(&t[1], &m);
+
+	return spi_sync(spi, &m);
+}
+
+static int regmap_spi_async_write(void *context,
+				  const void *reg, size_t reg_len,
+				  const void *val, size_t val_len,
+				  struct regmap_async *a)
+{
+	struct regmap_async_spi *async = container_of(a,
+						      struct regmap_async_spi,
+						      core);
+	struct device *dev = context;
+	struct spi_device *spi = to_spi_device(dev);
+
+	async->t[0].tx_buf = reg;
+	async->t[0].len = reg_len;
+	async->t[1].tx_buf = val;
+	async->t[1].len = val_len;
+
+	spi_message_init(&async->m);
+	spi_message_add_tail(&async->t[0], &async->m);
+	spi_message_add_tail(&async->t[1], &async->m);
+
+	async->m.complete = regmap_spi_complete;
+	async->m.context = async;
+
+	return spi_async(spi, &async->m);
+}
+
+static struct regmap_async *regmap_spi_async_alloc(void)
+{
+	struct regmap_async_spi *async_spi;
+
+	async_spi = kzalloc(sizeof(*async_spi), GFP_KERNEL);
+	if (!async_spi)
+		return NULL;
+
+	return &async_spi->core;
+}
+
+static int regmap_spi_read(void *context,
+			   const void *reg, size_t reg_size,
+			   void *val, size_t val_size)
+{
+	struct device *dev = context;
+	struct spi_device *spi = to_spi_device(dev);
+
+	return spi_write_then_read(spi, reg, reg_size, val, val_size);
+}
+
+static struct regmap_bus regmap_spi = {
+	.write = regmap_spi_write,
+	.gather_write = regmap_spi_gather_write,
+	.async_write = regmap_spi_async_write,
+	.async_alloc = regmap_spi_async_alloc,
+	.read = regmap_spi_read,
+	.read_flag_mask = 0x80,
+};
+
+/**
+ * regmap_init_spi(): Initialise register map
+ *
+ * @spi: Device that will be interacted with
+ * @config: Configuration for register map
+ *
+ * The return value will be an ERR_PTR() on error or a valid pointer to
+ * a struct regmap.
+ */
+struct regmap *regmap_init_spi(struct spi_device *spi,
+			       const struct regmap_config *config)
+{
+	return regmap_init(&spi->dev, &regmap_spi, &spi->dev, config);
+}
+EXPORT_SYMBOL_GPL(regmap_init_spi);
+
+/**
+ * devm_regmap_init_spi(): Initialise register map
+ *
+ * @spi: Device that will be interacted with
+ * @config: Configuration for register map
+ *
+ * The return value will be an ERR_PTR() on error or a valid pointer
+ * to a struct regmap.  The map will be automatically freed by the
+ * device management code.
+ */
+struct regmap *devm_regmap_init_spi(struct spi_device *spi,
+				    const struct regmap_config *config)
+{
+	return devm_regmap_init(&spi->dev, &regmap_spi, &spi->dev, config);
+}
+EXPORT_SYMBOL_GPL(devm_regmap_init_spi);
+
+MODULE_LICENSE("GPL");

drivers/base/reservation.c

@@ -0,0 +1,39 @@
+/*
+ * Copyright (C) 2012-2013 Canonical Ltd
+ *
+ * Based on bo.c which bears the following copyright notice,
+ * but is dual licensed:
+ *
+ * Copyright (c) 2006-2009 VMware, Inc., Palo Alto, CA., USA
+ * All Rights Reserved.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the
+ * "Software"), to deal in the Software without restriction, including
+ * without limitation the rights to use, copy, modify, merge, publish,
+ * distribute, sub license, and/or sell copies of the Software, and to
+ * permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the
+ * next paragraph) shall be included in all copies or substantial portions
+ * of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDERS, AUTHORS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM,
+ * DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+ * OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+ * USE OR OTHER DEALINGS IN THE SOFTWARE.
+ *
+ **************************************************************************/
+/*
+ * Authors: Thomas Hellstrom <thellstrom-at-vmware-dot-com>
+ */
+
+#include <linux/reservation.h>
+#include <linux/export.h>
+
+DEFINE_WW_CLASS(reservation_ww_class);
+EXPORT_SYMBOL(reservation_ww_class);

drivers/base/soc.c

@@ -0,0 +1,181 @@
+/*
+ * Copyright (C) ST-Ericsson SA 2011
+ *
+ * Author: Lee Jones <lee.jones@linaro.org> for ST-Ericsson.
+ * License terms:  GNU General Public License (GPL), version 2
+ */
+
+#include <linux/sysfs.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/stat.h>
+#include <linux/slab.h>
+#include <linux/idr.h>
+#include <linux/spinlock.h>
+#include <linux/sys_soc.h>
+#include <linux/err.h>
+
+static DEFINE_IDA(soc_ida);
+static DEFINE_SPINLOCK(soc_lock);
+
+static ssize_t soc_info_get(struct device *dev,
+			    struct device_attribute *attr,
+			    char *buf);
+
+struct soc_device {
+	struct device dev;
+	struct soc_device_attribute *attr;
+	int soc_dev_num;
+};
+
+static struct bus_type soc_bus_type = {
+	.name  = "soc",
+};
+
+static DEVICE_ATTR(machine,  S_IRUGO, soc_info_get,  NULL);
+static DEVICE_ATTR(family,   S_IRUGO, soc_info_get,  NULL);
+static DEVICE_ATTR(soc_id,   S_IRUGO, soc_info_get,  NULL);
+static DEVICE_ATTR(revision, S_IRUGO, soc_info_get,  NULL);
+
+struct device *soc_device_to_device(struct soc_device *soc_dev)
+{
+	return &soc_dev->dev;
+}
+
+static umode_t soc_attribute_mode(struct kobject *kobj,
+                                 struct attribute *attr,
+                                 int index)
+{
+	struct device *dev = container_of(kobj, struct device, kobj);
+	struct soc_device *soc_dev = container_of(dev, struct soc_device, dev);
+
+	if ((attr == &dev_attr_machine.attr)
+	    && (soc_dev->attr->machine != NULL))
+		return attr->mode;
+	if ((attr == &dev_attr_family.attr)
+	    && (soc_dev->attr->family != NULL))
+		return attr->mode;
+	if ((attr == &dev_attr_revision.attr)
+	    && (soc_dev->attr->revision != NULL))
+		return attr->mode;
+	if ((attr == &dev_attr_soc_id.attr)
+	    && (soc_dev->attr->soc_id != NULL))
+	        return attr->mode;
+
+	/* Unknown or unfilled attribute. */
+	return 0;
+}
+
+static ssize_t soc_info_get(struct device *dev,
+			    struct device_attribute *attr,
+			    char *buf)
+{
+	struct soc_device *soc_dev = container_of(dev, struct soc_device, dev);
+
+	if (attr == &dev_attr_machine)
+		return sprintf(buf, "%s\n", soc_dev->attr->machine);
+	if (attr == &dev_attr_family)
+		return sprintf(buf, "%s\n", soc_dev->attr->family);
+	if (attr == &dev_attr_revision)
+		return sprintf(buf, "%s\n", soc_dev->attr->revision);
+	if (attr == &dev_attr_soc_id)
+		return sprintf(buf, "%s\n", soc_dev->attr->soc_id);
+
+	return -EINVAL;
+
+}
+
+static struct attribute *soc_attr[] = {
+	&dev_attr_machine.attr,
+	&dev_attr_family.attr,
+	&dev_attr_soc_id.attr,
+	&dev_attr_revision.attr,
+	NULL,
+};
+
+static const struct attribute_group soc_attr_group = {
+	.attrs = soc_attr,
+	.is_visible = soc_attribute_mode,
+};
+
+static const struct attribute_group *soc_attr_groups[] = {
+	&soc_attr_group,
+	NULL,
+};
+
+static void soc_release(struct device *dev)
+{
+	struct soc_device *soc_dev = container_of(dev, struct soc_device, dev);
+
+	kfree(soc_dev);
+}
+
+struct soc_device *soc_device_register(struct soc_device_attribute *soc_dev_attr)
+{
+	struct soc_device *soc_dev;
+	int ret;
+
+	soc_dev = kzalloc(sizeof(*soc_dev), GFP_KERNEL);
+	if (!soc_dev) {
+	        ret = -ENOMEM;
+		goto out1;
+	}
+
+	/* Fetch a unique (reclaimable) SOC ID. */
+	do {
+		if (!ida_pre_get(&soc_ida, GFP_KERNEL)) {
+			ret = -ENOMEM;
+			goto out2;
+		}
+
+		spin_lock(&soc_lock);
+		ret = ida_get_new(&soc_ida, &soc_dev->soc_dev_num);
+		spin_unlock(&soc_lock);
+
+	} while (ret == -EAGAIN);
+
+	if (ret)
+	         goto out2;
+
+	soc_dev->attr = soc_dev_attr;
+	soc_dev->dev.bus = &soc_bus_type;
+	soc_dev->dev.groups = soc_attr_groups;
+	soc_dev->dev.release = soc_release;
+
+	dev_set_name(&soc_dev->dev, "soc%d", soc_dev->soc_dev_num);
+
+	ret = device_register(&soc_dev->dev);
+	if (ret)
+		goto out3;
+
+	return soc_dev;
+
+out3:
+	ida_remove(&soc_ida, soc_dev->soc_dev_num);
+out2:
+	kfree(soc_dev);
+out1:
+	return ERR_PTR(ret);
+}
+
+/* Ensure soc_dev->attr is freed prior to calling soc_device_unregister. */
+void soc_device_unregister(struct soc_device *soc_dev)
+{
+	ida_remove(&soc_ida, soc_dev->soc_dev_num);
+
+	device_unregister(&soc_dev->dev);
+}
+
+static int __init soc_bus_register(void)
+{
+	return bus_register(&soc_bus_type);
+}
+core_initcall(soc_bus_register);
+
+static void __exit soc_bus_unregister(void)
+{
+	ida_destroy(&soc_ida);
+
+	bus_unregister(&soc_bus_type);
+}
+module_exit(soc_bus_unregister);

drivers/base/syscore.c

@@ -0,0 +1,127 @@
+/*
+ *  syscore.c - Execution of system core operations.
+ *
+ *  Copyright (C) 2011 Rafael J. Wysocki <rjw@sisk.pl>, Novell Inc.
+ *
+ *  This file is released under the GPLv2.
+ */
+
+#include <linux/syscore_ops.h>
+#include <linux/mutex.h>
+#include <linux/module.h>
+#include <linux/interrupt.h>
+
+static LIST_HEAD(syscore_ops_list);
+static DEFINE_MUTEX(syscore_ops_lock);
+
+/**
+ * register_syscore_ops - Register a set of system core operations.
+ * @ops: System core operations to register.
+ */
+void register_syscore_ops(struct syscore_ops *ops)
+{
+	mutex_lock(&syscore_ops_lock);
+	list_add_tail(&ops->node, &syscore_ops_list);
+	mutex_unlock(&syscore_ops_lock);
+}
+EXPORT_SYMBOL_GPL(register_syscore_ops);
+
+/**
+ * unregister_syscore_ops - Unregister a set of system core operations.
+ * @ops: System core operations to unregister.
+ */
+void unregister_syscore_ops(struct syscore_ops *ops)
+{
+	mutex_lock(&syscore_ops_lock);
+	list_del(&ops->node);
+	mutex_unlock(&syscore_ops_lock);
+}
+EXPORT_SYMBOL_GPL(unregister_syscore_ops);
+
+#ifdef CONFIG_PM_SLEEP
+/**
+ * syscore_suspend - Execute all the registered system core suspend callbacks.
+ *
+ * This function is executed with one CPU on-line and disabled interrupts.
+ */
+int syscore_suspend(void)
+{
+	struct syscore_ops *ops;
+	int ret = 0;
+
+	pr_debug("Checking wakeup interrupts\n");
+
+	/* Return error code if there are any wakeup interrupts pending. */
+	ret = check_wakeup_irqs();
+	if (ret)
+		return ret;
+
+	WARN_ONCE(!irqs_disabled(),
+		"Interrupts enabled before system core suspend.\n");
+
+	list_for_each_entry_reverse(ops, &syscore_ops_list, node)
+		if (ops->suspend) {
+			if (initcall_debug)
+				pr_info("PM: Calling %pF\n", ops->suspend);
+			ret = ops->suspend();
+			if (ret)
+				goto err_out;
+			WARN_ONCE(!irqs_disabled(),
+				"Interrupts enabled after %pF\n", ops->suspend);
+		}
+
+	return 0;
+
+ err_out:
+	pr_err("PM: System core suspend callback %pF failed.\n", ops->suspend);
+
+	list_for_each_entry_continue(ops, &syscore_ops_list, node)
+		if (ops->resume)
+			ops->resume();
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(syscore_suspend);
+
+/**
+ * syscore_resume - Execute all the registered system core resume callbacks.
+ *
+ * This function is executed with one CPU on-line and disabled interrupts.
+ */
+void syscore_resume(void)
+{
+	struct syscore_ops *ops;
+
+	WARN_ONCE(!irqs_disabled(),
+		"Interrupts enabled before system core resume.\n");
+
+	list_for_each_entry(ops, &syscore_ops_list, node)
+		if (ops->resume) {
+			if (initcall_debug)
+				pr_info("PM: Calling %pF\n", ops->resume);
+			ops->resume();
+			WARN_ONCE(!irqs_disabled(),
+				"Interrupts enabled after %pF\n", ops->resume);
+		}
+}
+EXPORT_SYMBOL_GPL(syscore_resume);
+#endif /* CONFIG_PM_SLEEP */
+
+/**
+ * syscore_shutdown - Execute all the registered system core shutdown callbacks.
+ */
+void syscore_shutdown(void)
+{
+	struct syscore_ops *ops;
+
+	mutex_lock(&syscore_ops_lock);
+
+	list_for_each_entry_reverse(ops, &syscore_ops_list, node)
+		if (ops->shutdown) {
+			if (initcall_debug)
+				pr_info("PM: Calling %pF\n", ops->shutdown);
+			ops->shutdown();
+		}
+
+	mutex_unlock(&syscore_ops_lock);
+}

drivers/base/topology.c

@@ -0,0 +1,196 @@
+/*
+ * driver/base/topology.c - Populate sysfs with cpu topology information
+ *
+ * Written by: Zhang Yanmin, Intel Corporation
+ *
+ * Copyright (C) 2006, Intel Corp.
+ *
+ * All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ * NON INFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ */
+#include <linux/init.h>
+#include <linux/mm.h>
+#include <linux/cpu.h>
+#include <linux/module.h>
+#include <linux/hardirq.h>
+#include <linux/topology.h>
+
+#define define_one_ro_named(_name, _func)				\
+	static DEVICE_ATTR(_name, 0444, _func, NULL)
+
+#define define_one_ro(_name)				\
+	static DEVICE_ATTR(_name, 0444, show_##_name, NULL)
+
+#define define_id_show_func(name)				\
+static ssize_t show_##name(struct device *dev,			\
+		struct device_attribute *attr, char *buf)	\
+{								\
+	unsigned int cpu = dev->id;				\
+	return sprintf(buf, "%d\n", topology_##name(cpu));	\
+}
+
+#if defined(topology_thread_cpumask) || defined(topology_core_cpumask) || \
+    defined(topology_book_cpumask)
+static ssize_t show_cpumap(int type, const struct cpumask *mask, char *buf)
+{
+	ptrdiff_t len = PTR_ALIGN(buf + PAGE_SIZE - 1, PAGE_SIZE) - buf;
+	int n = 0;
+
+	if (len > 1) {
+		n = type?
+			cpulist_scnprintf(buf, len-2, mask) :
+			cpumask_scnprintf(buf, len-2, mask);
+		buf[n++] = '\n';
+		buf[n] = '\0';
+	}
+	return n;
+}
+#endif
+
+#ifdef arch_provides_topology_pointers
+#define define_siblings_show_map(name)					\
+static ssize_t show_##name(struct device *dev,				\
+			   struct device_attribute *attr, char *buf)	\
+{									\
+	unsigned int cpu = dev->id;					\
+	return show_cpumap(0, topology_##name(cpu), buf);		\
+}
+
+#define define_siblings_show_list(name)					\
+static ssize_t show_##name##_list(struct device *dev,			\
+				  struct device_attribute *attr,	\
+				  char *buf)				\
+{									\
+	unsigned int cpu = dev->id;					\
+	return show_cpumap(1, topology_##name(cpu), buf);		\
+}
+
+#else
+#define define_siblings_show_map(name)					\
+static ssize_t show_##name(struct device *dev,				\
+			   struct device_attribute *attr, char *buf)	\
+{									\
+	return show_cpumap(0, topology_##name(dev->id), buf);		\
+}
+
+#define define_siblings_show_list(name)					\
+static ssize_t show_##name##_list(struct device *dev,			\
+				  struct device_attribute *attr,	\
+				  char *buf)				\
+{									\
+	return show_cpumap(1, topology_##name(dev->id), buf);		\
+}
+#endif
+
+#define define_siblings_show_func(name)		\
+	define_siblings_show_map(name); define_siblings_show_list(name)
+
+define_id_show_func(physical_package_id);
+define_one_ro(physical_package_id);
+
+define_id_show_func(core_id);
+define_one_ro(core_id);
+
+define_siblings_show_func(thread_cpumask);
+define_one_ro_named(thread_siblings, show_thread_cpumask);
+define_one_ro_named(thread_siblings_list, show_thread_cpumask_list);
+
+define_siblings_show_func(core_cpumask);
+define_one_ro_named(core_siblings, show_core_cpumask);
+define_one_ro_named(core_siblings_list, show_core_cpumask_list);
+
+#ifdef CONFIG_SCHED_BOOK
+define_id_show_func(book_id);
+define_one_ro(book_id);
+define_siblings_show_func(book_cpumask);
+define_one_ro_named(book_siblings, show_book_cpumask);
+define_one_ro_named(book_siblings_list, show_book_cpumask_list);
+#endif
+
+static struct attribute *default_attrs[] = {
+	&dev_attr_physical_package_id.attr,
+	&dev_attr_core_id.attr,
+	&dev_attr_thread_siblings.attr,
+	&dev_attr_thread_siblings_list.attr,
+	&dev_attr_core_siblings.attr,
+	&dev_attr_core_siblings_list.attr,
+#ifdef CONFIG_SCHED_BOOK
+	&dev_attr_book_id.attr,
+	&dev_attr_book_siblings.attr,
+	&dev_attr_book_siblings_list.attr,
+#endif
+	NULL
+};
+
+static struct attribute_group topology_attr_group = {
+	.attrs = default_attrs,
+	.name = "topology"
+};
+
+/* Add/Remove cpu_topology interface for CPU device */
+static int __cpuinit topology_add_dev(unsigned int cpu)
+{
+	struct device *dev = get_cpu_device(cpu);
+
+	return sysfs_create_group(&dev->kobj, &topology_attr_group);
+}
+
+static void __cpuinit topology_remove_dev(unsigned int cpu)
+{
+	struct device *dev = get_cpu_device(cpu);
+
+	sysfs_remove_group(&dev->kobj, &topology_attr_group);
+}
+
+static int __cpuinit topology_cpu_callback(struct notifier_block *nfb,
+					   unsigned long action, void *hcpu)
+{
+	unsigned int cpu = (unsigned long)hcpu;
+	int rc = 0;
+
+	switch (action) {
+	case CPU_UP_PREPARE:
+	case CPU_UP_PREPARE_FROZEN:
+		rc = topology_add_dev(cpu);
+		break;
+	case CPU_UP_CANCELED:
+	case CPU_UP_CANCELED_FROZEN:
+	case CPU_DEAD:
+	case CPU_DEAD_FROZEN:
+		topology_remove_dev(cpu);
+		break;
+	}
+	return notifier_from_errno(rc);
+}
+
+static int __cpuinit topology_sysfs_init(void)
+{
+	int cpu;
+	int rc;
+
+	for_each_online_cpu(cpu) {
+		rc = topology_add_dev(cpu);
+		if (rc)
+			return rc;
+	}
+	hotcpu_notifier(topology_cpu_callback, 0);
+
+	return 0;
+}
+
+device_initcall(topology_sysfs_init);

drivers/base/transport_class.c

@@ -0,0 +1,280 @@
+/*
+ * transport_class.c - implementation of generic transport classes
+ *                     using attribute_containers
+ *
+ * Copyright (c) 2005 - James Bottomley <James.Bottomley@steeleye.com>
+ *
+ * This file is licensed under GPLv2
+ *
+ * The basic idea here is to allow any "device controller" (which
+ * would most often be a Host Bus Adapter to use the services of one
+ * or more tranport classes for performing transport specific
+ * services.  Transport specific services are things that the generic
+ * command layer doesn't want to know about (speed settings, line
+ * condidtioning, etc), but which the user might be interested in.
+ * Thus, the HBA's use the routines exported by the transport classes
+ * to perform these functions.  The transport classes export certain
+ * values to the user via sysfs using attribute containers.
+ *
+ * Note: because not every HBA will care about every transport
+ * attribute, there's a many to one relationship that goes like this:
+ *
+ * transport class<-----attribute container<----class device
+ *
+ * Usually the attribute container is per-HBA, but the design doesn't
+ * mandate that.  Although most of the services will be specific to
+ * the actual external storage connection used by the HBA, the generic
+ * transport class is framed entirely in terms of generic devices to
+ * allow it to be used by any physical HBA in the system.
+ */
+#include <linux/export.h>
+#include <linux/attribute_container.h>
+#include <linux/transport_class.h>
+
+/**
+ * transport_class_register - register an initial transport class
+ *
+ * @tclass:	a pointer to the transport class structure to be initialised
+ *
+ * The transport class contains an embedded class which is used to
+ * identify it.  The caller should initialise this structure with
+ * zeros and then generic class must have been initialised with the
+ * actual transport class unique name.  There's a macro
+ * DECLARE_TRANSPORT_CLASS() to do this (declared classes still must
+ * be registered).
+ *
+ * Returns 0 on success or error on failure.
+ */
+int transport_class_register(struct transport_class *tclass)
+{
+	return class_register(&tclass->class);
+}
+EXPORT_SYMBOL_GPL(transport_class_register);
+
+/**
+ * transport_class_unregister - unregister a previously registered class
+ *
+ * @tclass: The transport class to unregister
+ *
+ * Must be called prior to deallocating the memory for the transport
+ * class.
+ */
+void transport_class_unregister(struct transport_class *tclass)
+{
+	class_unregister(&tclass->class);
+}
+EXPORT_SYMBOL_GPL(transport_class_unregister);
+
+static int anon_transport_dummy_function(struct transport_container *tc,
+					 struct device *dev,
+					 struct device *cdev)
+{
+	/* do nothing */
+	return 0;
+}
+
+/**
+ * anon_transport_class_register - register an anonymous class
+ *
+ * @atc: The anon transport class to register
+ *
+ * The anonymous transport class contains both a transport class and a
+ * container.  The idea of an anonymous class is that it never
+ * actually has any device attributes associated with it (and thus
+ * saves on container storage).  So it can only be used for triggering
+ * events.  Use prezero and then use DECLARE_ANON_TRANSPORT_CLASS() to
+ * initialise the anon transport class storage.
+ */
+int anon_transport_class_register(struct anon_transport_class *atc)
+{
+	int error;
+	atc->container.class = &atc->tclass.class;
+	attribute_container_set_no_classdevs(&atc->container);
+	error = attribute_container_register(&atc->container);
+	if (error)
+		return error;
+	atc->tclass.setup = anon_transport_dummy_function;
+	atc->tclass.remove = anon_transport_dummy_function;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(anon_transport_class_register);
+
+/**
+ * anon_transport_class_unregister - unregister an anon class
+ *
+ * @atc: Pointer to the anon transport class to unregister
+ *
+ * Must be called prior to deallocating the memory for the anon
+ * transport class.
+ */
+void anon_transport_class_unregister(struct anon_transport_class *atc)
+{
+	if (unlikely(attribute_container_unregister(&atc->container)))
+		BUG();
+}
+EXPORT_SYMBOL_GPL(anon_transport_class_unregister);
+
+static int transport_setup_classdev(struct attribute_container *cont,
+				    struct device *dev,
+				    struct device *classdev)
+{
+	struct transport_class *tclass = class_to_transport_class(cont->class);
+	struct transport_container *tcont = attribute_container_to_transport_container(cont);
+
+	if (tclass->setup)
+		tclass->setup(tcont, dev, classdev);
+
+	return 0;
+}
+
+/**
+ * transport_setup_device - declare a new dev for transport class association but don't make it visible yet.
+ * @dev: the generic device representing the entity being added
+ *
+ * Usually, dev represents some component in the HBA system (either
+ * the HBA itself or a device remote across the HBA bus).  This
+ * routine is simply a trigger point to see if any set of transport
+ * classes wishes to associate with the added device.  This allocates
+ * storage for the class device and initialises it, but does not yet
+ * add it to the system or add attributes to it (you do this with
+ * transport_add_device).  If you have no need for a separate setup
+ * and add operations, use transport_register_device (see
+ * transport_class.h).
+ */
+
+void transport_setup_device(struct device *dev)
+{
+	attribute_container_add_device(dev, transport_setup_classdev);
+}
+EXPORT_SYMBOL_GPL(transport_setup_device);
+
+static int transport_add_class_device(struct attribute_container *cont,
+				      struct device *dev,
+				      struct device *classdev)
+{
+	int error = attribute_container_add_class_device(classdev);
+	struct transport_container *tcont = 
+		attribute_container_to_transport_container(cont);
+
+	if (!error && tcont->statistics)
+		error = sysfs_create_group(&classdev->kobj, tcont->statistics);
+
+	return error;
+}
+
+
+/**
+ * transport_add_device - declare a new dev for transport class association
+ *
+ * @dev: the generic device representing the entity being added
+ *
+ * Usually, dev represents some component in the HBA system (either
+ * the HBA itself or a device remote across the HBA bus).  This
+ * routine is simply a trigger point used to add the device to the
+ * system and register attributes for it.
+ */
+
+void transport_add_device(struct device *dev)
+{
+	attribute_container_device_trigger(dev, transport_add_class_device);
+}
+EXPORT_SYMBOL_GPL(transport_add_device);
+
+static int transport_configure(struct attribute_container *cont,
+			       struct device *dev,
+			       struct device *cdev)
+{
+	struct transport_class *tclass = class_to_transport_class(cont->class);
+	struct transport_container *tcont = attribute_container_to_transport_container(cont);
+
+	if (tclass->configure)
+		tclass->configure(tcont, dev, cdev);
+
+	return 0;
+}
+
+/**
+ * transport_configure_device - configure an already set up device
+ *
+ * @dev: generic device representing device to be configured
+ *
+ * The idea of configure is simply to provide a point within the setup
+ * process to allow the transport class to extract information from a
+ * device after it has been setup.  This is used in SCSI because we
+ * have to have a setup device to begin using the HBA, but after we
+ * send the initial inquiry, we use configure to extract the device
+ * parameters.  The device need not have been added to be configured.
+ */
+void transport_configure_device(struct device *dev)
+{
+	attribute_container_device_trigger(dev, transport_configure);
+}
+EXPORT_SYMBOL_GPL(transport_configure_device);
+
+static int transport_remove_classdev(struct attribute_container *cont,
+				     struct device *dev,
+				     struct device *classdev)
+{
+	struct transport_container *tcont = 
+		attribute_container_to_transport_container(cont);
+	struct transport_class *tclass = class_to_transport_class(cont->class);
+
+	if (tclass->remove)
+		tclass->remove(tcont, dev, classdev);
+
+	if (tclass->remove != anon_transport_dummy_function) {
+		if (tcont->statistics)
+			sysfs_remove_group(&classdev->kobj, tcont->statistics);
+		attribute_container_class_device_del(classdev);
+	}
+
+	return 0;
+}
+
+
+/**
+ * transport_remove_device - remove the visibility of a device
+ *
+ * @dev: generic device to remove
+ *
+ * This call removes the visibility of the device (to the user from
+ * sysfs), but does not destroy it.  To eliminate a device entirely
+ * you must also call transport_destroy_device.  If you don't need to
+ * do remove and destroy as separate operations, use
+ * transport_unregister_device() (see transport_class.h) which will
+ * perform both calls for you.
+ */
+void transport_remove_device(struct device *dev)
+{
+	attribute_container_device_trigger(dev, transport_remove_classdev);
+}
+EXPORT_SYMBOL_GPL(transport_remove_device);
+
+static void transport_destroy_classdev(struct attribute_container *cont,
+				      struct device *dev,
+				      struct device *classdev)
+{
+	struct transport_class *tclass = class_to_transport_class(cont->class);
+
+	if (tclass->remove != anon_transport_dummy_function)
+		put_device(classdev);
+}
+
+
+/**
+ * transport_destroy_device - destroy a removed device
+ *
+ * @dev: device to eliminate from the transport class.
+ *
+ * This call triggers the elimination of storage associated with the
+ * transport classdev.  Note: all it really does is relinquish a
+ * reference to the classdev.  The memory will not be freed until the
+ * last reference goes to zero.  Note also that the classdev retains a
+ * reference count on dev, so dev too will remain for as long as the
+ * transport class device remains around.
+ */
+void transport_destroy_device(struct device *dev)
+{
+	attribute_container_remove_device(dev, transport_destroy_classdev);
+}
+EXPORT_SYMBOL_GPL(transport_destroy_device);