diff options
author | root <root@artemis.panaceas.org> | 2015-12-25 04:40:36 +0000 |
---|---|---|
committer | root <root@artemis.panaceas.org> | 2015-12-25 04:40:36 +0000 |
commit | 849369d6c66d3054688672f97d31fceb8e8230fb (patch) | |
tree | 6135abc790ca67dedbe07c39806591e70eda81ce /drivers/base | |
download | linux-3.0.35-kobo-849369d6c66d3054688672f97d31fceb8e8230fb.tar.gz linux-3.0.35-kobo-849369d6c66d3054688672f97d31fceb8e8230fb.tar.bz2 linux-3.0.35-kobo-849369d6c66d3054688672f97d31fceb8e8230fb.zip |
initial_commit
Diffstat (limited to 'drivers/base')
39 files changed, 17006 insertions, 0 deletions
diff --git a/drivers/base/Kconfig b/drivers/base/Kconfig new file mode 100644 index 00000000..d57e8d0f --- /dev/null +++ b/drivers/base/Kconfig @@ -0,0 +1,171 @@ +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. + +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 STANDALONE + bool "Select only drivers that don't need compile-time external firmware" if EXPERIMENTAL + 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 a rebuild + should 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 no in-kernel-tree modules + require userspace firmware loading support, but a module built outside + the kernel 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' + which are used by various drivers. The recommended way to + use these is to run "make firmware_install" and to copy the + resulting binary files created in usr/lib/firmware directory + of the kernel tree to the /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 which uses + such firmware, and do not wish to use an initrd. + + This single option controls the inclusion of firmware for + every driver which uses request_firmware() and ships its + firmware in the kernel source tree, to avoid 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 + cases 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 which 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. + + So, 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 which 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 the firmware/ directory in the kernel source tree, + but by changing this option you can point it elsewhere, such as + the /lib/firmware/ directory or another separate directory + containing firmware files. + +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 + +endmenu diff --git a/drivers/base/Makefile b/drivers/base/Makefile new file mode 100644 index 00000000..4c5701c1 --- /dev/null +++ b/drivers/base/Makefile @@ -0,0 +1,23 @@ +# Makefile for the Linux device tree + +obj-y := core.o sys.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 +obj-$(CONFIG_DEVTMPFS) += devtmpfs.o +obj-y += power/ +obj-$(CONFIG_HAS_DMA) += dma-mapping.o +obj-$(CONFIG_HAVE_GENERIC_DMA_COHERENT) += dma-coherent.o +obj-$(CONFIG_ISA) += isa.o +obj-$(CONFIG_FW_LOADER) += firmware_class.o +obj-$(CONFIG_NUMA) += node.o +obj-$(CONFIG_MEMORY_HOTPLUG_SPARSE) += memory.o +obj-$(CONFIG_SMP) += topology.o +obj-$(CONFIG_IOMMU_API) += iommu.o +ifeq ($(CONFIG_SYSFS),y) +obj-$(CONFIG_MODULES) += module.o +endif +obj-$(CONFIG_SYS_HYPERVISOR) += hypervisor.o + +ccflags-$(CONFIG_DEBUG_DRIVER) := -DDEBUG + diff --git a/drivers/base/attribute_container.c b/drivers/base/attribute_container.c new file mode 100644 index 00000000..8fc200b2 --- /dev/null +++ b/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_printk(KERN_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); diff --git a/drivers/base/base.h b/drivers/base/base.h new file mode 100644 index 00000000..a34dca0a --- /dev/null +++ b/drivers/base/base.h @@ -0,0 +1,133 @@ + +/** + * 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 list of devices associated + * + * @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. + * + * @class_interfaces - list of class_interfaces associated + * @glue_dirs - "glue" directory to put in-between the parent device to + * avoid namespace conflicts + * @class_mutex - mutex to protect the children, devices, and interfaces lists. + * @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 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 list_head class_interfaces; + struct kset glue_dirs; + struct mutex class_mutex; + 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 + * @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; + 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 int system_bus_init(void); +extern int cpu_dev_init(void); + +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); +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); + +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 diff --git a/drivers/base/bus.c b/drivers/base/bus.c new file mode 100644 index 00000000..000e7b20 --- /dev/null +++ b/drivers/base/bus.c @@ -0,0 +1,1037 @@ +/* + * bus.c - bus 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/init.h> +#include <linux/string.h> +#include "base.h" +#include "power/power.h" + +#define to_bus_attr(_attr) container_of(_attr, struct bus_attribute, attr) + +/* + * sysfs bindings for drivers + */ + +#define to_drv_attr(_attr) container_of(_attr, struct driver_attribute, attr) + + +static int __must_check bus_rescan_devices_helper(struct device *dev, + void *data); + +static struct bus_type *bus_get(struct bus_type *bus) +{ + if (bus) { + kset_get(&bus->p->subsys); + return bus; + } + return NULL; +} + +static void bus_put(struct bus_type *bus) +{ + if (bus) + kset_put(&bus->p->subsys); +} + +static ssize_t drv_attr_show(struct kobject *kobj, struct attribute *attr, + char *buf) +{ + struct driver_attribute *drv_attr = to_drv_attr(attr); + struct driver_private *drv_priv = to_driver(kobj); + ssize_t ret = -EIO; + + if (drv_attr->show) + ret = drv_attr->show(drv_priv->driver, buf); + return ret; +} + +static ssize_t drv_attr_store(struct kobject *kobj, struct attribute *attr, + const char *buf, size_t count) +{ + struct driver_attribute *drv_attr = to_drv_attr(attr); + struct driver_private *drv_priv = to_driver(kobj); + ssize_t ret = -EIO; + + if (drv_attr->store) + ret = drv_attr->store(drv_priv->driver, buf, count); + return ret; +} + +static const struct sysfs_ops driver_sysfs_ops = { + .show = drv_attr_show, + .store = drv_attr_store, +}; + +static void driver_release(struct kobject *kobj) +{ + struct driver_private *drv_priv = to_driver(kobj); + + pr_debug("driver: '%s': %s\n", kobject_name(kobj), __func__); + kfree(drv_priv); +} + +static struct kobj_type driver_ktype = { + .sysfs_ops = &driver_sysfs_ops, + .release = driver_release, +}; + +/* + * sysfs bindings for buses + */ +static ssize_t bus_attr_show(struct kobject *kobj, struct attribute *attr, + char *buf) +{ + struct bus_attribute *bus_attr = to_bus_attr(attr); + struct subsys_private *subsys_priv = to_subsys_private(kobj); + ssize_t ret = 0; + + if (bus_attr->show) + ret = bus_attr->show(subsys_priv->bus, buf); + return ret; +} + +static ssize_t bus_attr_store(struct kobject *kobj, struct attribute *attr, + const char *buf, size_t count) +{ + struct bus_attribute *bus_attr = to_bus_attr(attr); + struct subsys_private *subsys_priv = to_subsys_private(kobj); + ssize_t ret = 0; + + if (bus_attr->store) + ret = bus_attr->store(subsys_priv->bus, buf, count); + return ret; +} + +static const struct sysfs_ops bus_sysfs_ops = { + .show = bus_attr_show, + .store = bus_attr_store, +}; + +int bus_create_file(struct bus_type *bus, struct bus_attribute *attr) +{ + int error; + if (bus_get(bus)) { + error = sysfs_create_file(&bus->p->subsys.kobj, &attr->attr); + bus_put(bus); + } else + error = -EINVAL; + return error; +} +EXPORT_SYMBOL_GPL(bus_create_file); + +void bus_remove_file(struct bus_type *bus, struct bus_attribute *attr) +{ + if (bus_get(bus)) { + sysfs_remove_file(&bus->p->subsys.kobj, &attr->attr); + bus_put(bus); + } +} +EXPORT_SYMBOL_GPL(bus_remove_file); + +static struct kobj_type bus_ktype = { + .sysfs_ops = &bus_sysfs_ops, +}; + +static int bus_uevent_filter(struct kset *kset, struct kobject *kobj) +{ + struct kobj_type *ktype = get_ktype(kobj); + + if (ktype == &bus_ktype) + return 1; + return 0; +} + +static const struct kset_uevent_ops bus_uevent_ops = { + .filter = bus_uevent_filter, +}; + +static struct kset *bus_kset; + + +#ifdef CONFIG_HOTPLUG +/* Manually detach a device from its associated driver. */ +static ssize_t driver_unbind(struct device_driver *drv, + const char *buf, size_t count) +{ + struct bus_type *bus = bus_get(drv->bus); + struct device *dev; + int err = -ENODEV; + + dev = bus_find_device_by_name(bus, NULL, buf); + if (dev && dev->driver == drv) { + if (dev->parent) /* Needed for USB */ + device_lock(dev->parent); + device_release_driver(dev); + if (dev->parent) + device_unlock(dev->parent); + err = count; + } + put_device(dev); + bus_put(bus); + return err; +} +static DRIVER_ATTR(unbind, S_IWUSR, NULL, driver_unbind); + +/* + * Manually attach a device to a driver. + * Note: the driver must want to bind to the device, + * it is not possible to override the driver's id table. + */ +static ssize_t driver_bind(struct device_driver *drv, + const char *buf, size_t count) +{ + struct bus_type *bus = bus_get(drv->bus); + struct device *dev; + int err = -ENODEV; + + dev = bus_find_device_by_name(bus, NULL, buf); + if (dev && dev->driver == NULL && driver_match_device(drv, dev)) { + if (dev->parent) /* Needed for USB */ + device_lock(dev->parent); + device_lock(dev); + err = driver_probe_device(drv, dev); + device_unlock(dev); + if (dev->parent) + device_unlock(dev->parent); + + if (err > 0) { + /* success */ + err = count; + } else if (err == 0) { + /* driver didn't accept device */ + err = -ENODEV; + } + } + put_device(dev); + bus_put(bus); + return err; +} +static DRIVER_ATTR(bind, S_IWUSR, NULL, driver_bind); + +static ssize_t show_drivers_autoprobe(struct bus_type *bus, char *buf) +{ + return sprintf(buf, "%d\n", bus->p->drivers_autoprobe); +} + +static ssize_t store_drivers_autoprobe(struct bus_type *bus, + const char *buf, size_t count) +{ + if (buf[0] == '0') + bus->p->drivers_autoprobe = 0; + else + bus->p->drivers_autoprobe = 1; + return count; +} + +static ssize_t store_drivers_probe(struct bus_type *bus, + const char *buf, size_t count) +{ + struct device *dev; + + dev = bus_find_device_by_name(bus, NULL, buf); + if (!dev) + return -ENODEV; + if (bus_rescan_devices_helper(dev, NULL) != 0) + return -EINVAL; + return count; +} +#endif + +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_bus(n); + dev = dev_prv->device; + } + return dev; +} + +/** + * bus_for_each_dev - device iterator. + * @bus: bus type. + * @start: device to start iterating from. + * @data: data for the callback. + * @fn: function to be called for each device. + * + * Iterate over @bus's list of devices, and call @fn for each, + * passing it @data. If @start is not NULL, we use that device to + * begin iterating from. + * + * We check the return of @fn each time. If it returns anything + * other than 0, we break out and return that value. + * + * NOTE: The device that returns a non-zero value is not retained + * in any way, nor is its refcount incremented. If the caller needs + * to retain this data, it should do so, and increment the reference + * count in the supplied callback. + */ +int bus_for_each_dev(struct bus_type *bus, struct device *start, + void *data, int (*fn)(struct device *, void *)) +{ + struct klist_iter i; + struct device *dev; + int error = 0; + + if (!bus) + return -EINVAL; + + klist_iter_init_node(&bus->p->klist_devices, &i, + (start ? &start->p->knode_bus : NULL)); + while ((dev = next_device(&i)) && !error) + error = fn(dev, data); + klist_iter_exit(&i); + return error; +} +EXPORT_SYMBOL_GPL(bus_for_each_dev); + +/** + * bus_find_device - device iterator for locating a particular device. + * @bus: bus type + * @start: Device to begin with + * @data: Data to pass to match function + * @match: Callback function to check device + * + * This is similar to the bus_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. + */ +struct device *bus_find_device(struct bus_type *bus, + struct device *start, void *data, + int (*match)(struct device *dev, void *data)) +{ + struct klist_iter i; + struct device *dev; + + if (!bus) + return NULL; + + klist_iter_init_node(&bus->p->klist_devices, &i, + (start ? &start->p->knode_bus : NULL)); + while ((dev = next_device(&i))) + if (match(dev, data) && get_device(dev)) + break; + klist_iter_exit(&i); + return dev; +} +EXPORT_SYMBOL_GPL(bus_find_device); + +static int match_name(struct device *dev, void *data) +{ + const char *name = data; + + return sysfs_streq(name, dev_name(dev)); +} + +/** + * bus_find_device_by_name - device iterator for locating a particular device of a specific name + * @bus: bus type + * @start: Device to begin with + * @name: name of the device to match + * + * This is similar to the bus_find_device() function above, but it handles + * searching by a name automatically, no need to write another strcmp matching + * function. + */ +struct device *bus_find_device_by_name(struct bus_type *bus, + struct device *start, const char *name) +{ + return bus_find_device(bus, start, (void *)name, match_name); +} +EXPORT_SYMBOL_GPL(bus_find_device_by_name); + +static struct device_driver *next_driver(struct klist_iter *i) +{ + struct klist_node *n = klist_next(i); + struct driver_private *drv_priv; + + if (n) { + drv_priv = container_of(n, struct driver_private, knode_bus); + return drv_priv->driver; + } + return NULL; +} + +/** + * bus_for_each_drv - driver iterator + * @bus: bus we're dealing with. + * @start: driver to start iterating on. + * @data: data to pass to the callback. + * @fn: function to call for each driver. + * + * This is nearly identical to the device iterator above. + * We iterate over each driver that belongs to @bus, and call + * @fn for each. If @fn returns anything but 0, we break out + * and return it. If @start is not NULL, we use it as the head + * of the list. + * + * NOTE: we don't return the driver that returns a non-zero + * value, nor do we leave the reference count incremented for that + * driver. If the caller needs to know that info, it must set it + * in the callback. It must also be sure to increment the refcount + * so it doesn't disappear before returning to the caller. + */ +int bus_for_each_drv(struct bus_type *bus, struct device_driver *start, + void *data, int (*fn)(struct device_driver *, void *)) +{ + struct klist_iter i; + struct device_driver *drv; + int error = 0; + + if (!bus) + return -EINVAL; + + klist_iter_init_node(&bus->p->klist_drivers, &i, + start ? &start->p->knode_bus : NULL); + while ((drv = next_driver(&i)) && !error) + error = fn(drv, data); + klist_iter_exit(&i); + return error; +} +EXPORT_SYMBOL_GPL(bus_for_each_drv); + +static int device_add_attrs(struct bus_type *bus, struct device *dev) +{ + int error = 0; + int i; + + if (!bus->dev_attrs) + return 0; + + for (i = 0; attr_name(bus->dev_attrs[i]); i++) { + error = device_create_file(dev, &bus->dev_attrs[i]); + if (error) { + while (--i >= 0) + device_remove_file(dev, &bus->dev_attrs[i]); + break; + } + } + return error; +} + +static void device_remove_attrs(struct bus_type *bus, struct device *dev) +{ + int i; + + if (bus->dev_attrs) { + for (i = 0; attr_name(bus->dev_attrs[i]); i++) + device_remove_file(dev, &bus->dev_attrs[i]); + } +} + +/** + * bus_add_device - add device to bus + * @dev: device being added + * + * - Add device's bus attributes. + * - Create links to device's bus. + * - Add the device to its bus's list of devices. + */ +int bus_add_device(struct device *dev) +{ + struct bus_type *bus = bus_get(dev->bus); + int error = 0; + + if (bus) { + pr_debug("bus: '%s': add device %s\n", bus->name, dev_name(dev)); + error = device_add_attrs(bus, dev); + if (error) + goto out_put; + error = sysfs_create_link(&bus->p->devices_kset->kobj, + &dev->kobj, dev_name(dev)); + if (error) + goto out_id; + error = sysfs_create_link(&dev->kobj, + &dev->bus->p->subsys.kobj, "subsystem"); + if (error) + goto out_subsys; + klist_add_tail(&dev->p->knode_bus, &bus->p->klist_devices); + } + return 0; + +out_subsys: + sysfs_remove_link(&bus->p->devices_kset->kobj, dev_name(dev)); +out_id: + device_remove_attrs(bus, dev); +out_put: + bus_put(dev->bus); + return error; +} + +/** + * bus_probe_device - probe drivers for a new device + * @dev: device to probe + * + * - Automatically probe for a driver if the bus allows it. + */ +void bus_probe_device(struct device *dev) +{ + struct bus_type *bus = dev->bus; + int ret; + + if (bus && bus->p->drivers_autoprobe) { + ret = device_attach(dev); + WARN_ON(ret < 0); + } +} + +/** + * bus_remove_device - remove device from bus + * @dev: device to be removed + * + * - Remove symlink from bus's directory. + * - Delete device from bus's list. + * - Detach from its driver. + * - Drop reference taken in bus_add_device(). + */ +void bus_remove_device(struct device *dev) +{ + if (dev->bus) { + sysfs_remove_link(&dev->kobj, "subsystem"); + sysfs_remove_link(&dev->bus->p->devices_kset->kobj, + dev_name(dev)); + device_remove_attrs(dev->bus, dev); + if (klist_node_attached(&dev->p->knode_bus)) + klist_del(&dev->p->knode_bus); + + pr_debug("bus: '%s': remove device %s\n", + dev->bus->name, dev_name(dev)); + device_release_driver(dev); + bus_put(dev->bus); + } +} + +static int driver_add_attrs(struct bus_type *bus, struct device_driver *drv) +{ + int error = 0; + int i; + + if (bus->drv_attrs) { + for (i = 0; attr_name(bus->drv_attrs[i]); i++) { + error = driver_create_file(drv, &bus->drv_attrs[i]); + if (error) + goto err; + } + } +done: + return error; +err: + while (--i >= 0) + driver_remove_file(drv, &bus->drv_attrs[i]); + goto done; +} + +static void driver_remove_attrs(struct bus_type *bus, + struct device_driver *drv) +{ + int i; + + if (bus->drv_attrs) { + for (i = 0; attr_name(bus->drv_attrs[i]); i++) + driver_remove_file(drv, &bus->drv_attrs[i]); + } +} + +#ifdef CONFIG_HOTPLUG +/* + * Thanks to drivers making their tables __devinit, we can't allow manual + * bind and unbind from userspace unless CONFIG_HOTPLUG is enabled. + */ +static int __must_check add_bind_files(struct device_driver *drv) +{ + int ret; + + ret = driver_create_file(drv, &driver_attr_unbind); + if (ret == 0) { + ret = driver_create_file(drv, &driver_attr_bind); + if (ret) + driver_remove_file(drv, &driver_attr_unbind); + } + return ret; +} + +static void remove_bind_files(struct device_driver *drv) +{ + driver_remove_file(drv, &driver_attr_bind); + driver_remove_file(drv, &driver_attr_unbind); +} + +static BUS_ATTR(drivers_probe, S_IWUSR, NULL, store_drivers_probe); +static BUS_ATTR(drivers_autoprobe, S_IWUSR | S_IRUGO, + show_drivers_autoprobe, store_drivers_autoprobe); + +static int add_probe_files(struct bus_type *bus) +{ + int retval; + + retval = bus_create_file(bus, &bus_attr_drivers_probe); + if (retval) + goto out; + + retval = bus_create_file(bus, &bus_attr_drivers_autoprobe); + if (retval) + bus_remove_file(bus, &bus_attr_drivers_probe); +out: + return retval; +} + +static void remove_probe_files(struct bus_type *bus) +{ + bus_remove_file(bus, &bus_attr_drivers_autoprobe); + bus_remove_file(bus, &bus_attr_drivers_probe); +} +#else +static inline int add_bind_files(struct device_driver *drv) { return 0; } +static inline void remove_bind_files(struct device_driver *drv) {} +static inline int add_probe_files(struct bus_type *bus) { return 0; } +static inline void remove_probe_files(struct bus_type *bus) {} +#endif + +static ssize_t driver_uevent_store(struct device_driver *drv, + const char *buf, size_t count) +{ + enum kobject_action action; + + if (kobject_action_type(buf, count, &action) == 0) + kobject_uevent(&drv->p->kobj, action); + return count; +} +static DRIVER_ATTR(uevent, S_IWUSR, NULL, driver_uevent_store); + +/** + * bus_add_driver - Add a driver to the bus. + * @drv: driver. + */ +int bus_add_driver(struct device_driver *drv) +{ + struct bus_type *bus; + struct driver_private *priv; + int error = 0; + + bus = bus_get(drv->bus); + if (!bus) + return -EINVAL; + + pr_debug("bus: '%s': add driver %s\n", bus->name, drv->name); + + priv = kzalloc(sizeof(*priv), GFP_KERNEL); + if (!priv) { + error = -ENOMEM; + goto out_put_bus; + } + klist_init(&priv->klist_devices, NULL, NULL); + priv->driver = drv; + drv->p = priv; + priv->kobj.kset = bus->p->drivers_kset; + error = kobject_init_and_add(&priv->kobj, &driver_ktype, NULL, + "%s", drv->name); + if (error) + goto out_unregister; + + if (drv->bus->p->drivers_autoprobe) { + error = driver_attach(drv); + if (error) + goto out_unregister; + } + klist_add_tail(&priv->knode_bus, &bus->p->klist_drivers); + module_add_driver(drv->owner, drv); + + error = driver_create_file(drv, &driver_attr_uevent); + if (error) { + printk(KERN_ERR "%s: uevent attr (%s) failed\n", + __func__, drv->name); + } + error = driver_add_attrs(bus, drv); + if (error) { + /* How the hell do we get out of this pickle? Give up */ + printk(KERN_ERR "%s: driver_add_attrs(%s) failed\n", + __func__, drv->name); + } + + if (!drv->suppress_bind_attrs) { + error = add_bind_files(drv); + if (error) { + /* Ditto */ + printk(KERN_ERR "%s: add_bind_files(%s) failed\n", + __func__, drv->name); + } + } + + kobject_uevent(&priv->kobj, KOBJ_ADD); + return 0; + +out_unregister: + kobject_put(&priv->kobj); + kfree(drv->p); + drv->p = NULL; +out_put_bus: + bus_put(bus); + return error; +} + +/** + * bus_remove_driver - delete driver from bus's knowledge. + * @drv: driver. + * + * Detach the driver from the devices it controls, and remove + * it from its bus's list of drivers. Finally, we drop the reference + * to the bus we took in bus_add_driver(). + */ +void bus_remove_driver(struct device_driver *drv) +{ + if (!drv->bus) + return; + + if (!drv->suppress_bind_attrs) + remove_bind_files(drv); + driver_remove_attrs(drv->bus, drv); + driver_remove_file(drv, &driver_attr_uevent); + klist_remove(&drv->p->knode_bus); + pr_debug("bus: '%s': remove driver %s\n", drv->bus->name, drv->name); + driver_detach(drv); + module_remove_driver(drv); + kobject_put(&drv->p->kobj); + bus_put(drv->bus); +} + +/* Helper for bus_rescan_devices's iter */ +static int __must_check bus_rescan_devices_helper(struct device *dev, + void *data) +{ + int ret = 0; + + if (!dev->driver) { + if (dev->parent) /* Needed for USB */ + device_lock(dev->parent); + ret = device_attach(dev); + if (dev->parent) + device_unlock(dev->parent); + } + return ret < 0 ? ret : 0; +} + +/** + * bus_rescan_devices - rescan devices on the bus for possible drivers + * @bus: the bus to scan. + * + * This function will look for devices on the bus with no driver + * attached and rescan it against existing drivers to see if it matches + * any by calling device_attach() for the unbound devices. + */ +int bus_rescan_devices(struct bus_type *bus) +{ + return bus_for_each_dev(bus, NULL, NULL, bus_rescan_devices_helper); +} +EXPORT_SYMBOL_GPL(bus_rescan_devices); + +/** + * device_reprobe - remove driver for a device and probe for a new driver + * @dev: the device to reprobe + * + * This function detaches the attached driver (if any) for the given + * device and restarts the driver probing process. It is intended + * to use if probing criteria changed during a devices lifetime and + * driver attachment should change accordingly. + */ +int device_reprobe(struct device *dev) +{ + if (dev->driver) { + if (dev->parent) /* Needed for USB */ + device_lock(dev->parent); + device_release_driver(dev); + if (dev->parent) + device_unlock(dev->parent); + } + return bus_rescan_devices_helper(dev, NULL); +} +EXPORT_SYMBOL_GPL(device_reprobe); + +/** + * find_bus - locate bus by name. + * @name: name of bus. + * + * Call kset_find_obj() to iterate over list of buses to + * find a bus by name. Return bus if found. + * + * Note that kset_find_obj increments bus' reference count. + */ +#if 0 +struct bus_type *find_bus(char *name) +{ + struct kobject *k = kset_find_obj(bus_kset, name); + return k ? to_bus(k) : NULL; +} +#endif /* 0 */ + + +/** + * bus_add_attrs - Add default attributes for this bus. + * @bus: Bus that has just been registered. + */ + +static int bus_add_attrs(struct bus_type *bus) +{ + int error = 0; + int i; + + if (bus->bus_attrs) { + for (i = 0; attr_name(bus->bus_attrs[i]); i++) { + error = bus_create_file(bus, &bus->bus_attrs[i]); + if (error) + goto err; + } + } +done: + return error; +err: + while (--i >= 0) + bus_remove_file(bus, &bus->bus_attrs[i]); + goto done; +} + +static void bus_remove_attrs(struct bus_type *bus) +{ + int i; + + if (bus->bus_attrs) { + for (i = 0; attr_name(bus->bus_attrs[i]); i++) + bus_remove_file(bus, &bus->bus_attrs[i]); + } +} + +static void klist_devices_get(struct klist_node *n) +{ + struct device_private *dev_prv = to_device_private_bus(n); + struct device *dev = dev_prv->device; + + get_device(dev); +} + +static void klist_devices_put(struct klist_node *n) +{ + struct device_private *dev_prv = to_device_private_bus(n); + struct device *dev = dev_prv->device; + + put_device(dev); +} + +static ssize_t bus_uevent_store(struct bus_type *bus, + const char *buf, size_t count) +{ + enum kobject_action action; + + if (kobject_action_type(buf, count, &action) == 0) + kobject_uevent(&bus->p->subsys.kobj, action); + return count; +} +static BUS_ATTR(uevent, S_IWUSR, NULL, bus_uevent_store); + +/** + * bus_register - register a bus with the system. + * @bus: bus. + * + * Once we have that, we registered the bus with the kobject + * infrastructure, then register the children subsystems it has: + * the devices and drivers that belong to the bus. + */ +int bus_register(struct bus_type *bus) +{ + int retval; + struct subsys_private *priv; + + priv = kzalloc(sizeof(struct subsys_private), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + priv->bus = bus; + bus->p = priv; + + BLOCKING_INIT_NOTIFIER_HEAD(&priv->bus_notifier); + + retval = kobject_set_name(&priv->subsys.kobj, "%s", bus->name); + if (retval) + goto out; + + priv->subsys.kobj.kset = bus_kset; + priv->subsys.kobj.ktype = &bus_ktype; + priv->drivers_autoprobe = 1; + + retval = kset_register(&priv->subsys); + if (retval) + goto out; + + retval = bus_create_file(bus, &bus_attr_uevent); + if (retval) + goto bus_uevent_fail; + + priv->devices_kset = kset_create_and_add("devices", NULL, + &priv->subsys.kobj); + if (!priv->devices_kset) { + retval = -ENOMEM; + goto bus_devices_fail; + } + + priv->drivers_kset = kset_create_and_add("drivers", NULL, + &priv->subsys.kobj); + if (!priv->drivers_kset) { + retval = -ENOMEM; + goto bus_drivers_fail; + } + + klist_init(&priv->klist_devices, klist_devices_get, klist_devices_put); + klist_init(&priv->klist_drivers, NULL, NULL); + + retval = add_probe_files(bus); + if (retval) + goto bus_probe_files_fail; + + retval = bus_add_attrs(bus); + if (retval) + goto bus_attrs_fail; + + pr_debug("bus: '%s': registered\n", bus->name); + return 0; + +bus_attrs_fail: + remove_probe_files(bus); +bus_probe_files_fail: + kset_unregister(bus->p->drivers_kset); +bus_drivers_fail: + kset_unregister(bus->p->devices_kset); +bus_devices_fail: + bus_remove_file(bus, &bus_attr_uevent); +bus_uevent_fail: + kset_unregister(&bus->p->subsys); +out: + kfree(bus->p); + bus->p = NULL; + return retval; +} +EXPORT_SYMBOL_GPL(bus_register); + +/** + * bus_unregister - remove a bus from the system + * @bus: bus. + * + * Unregister the child subsystems and the bus itself. + * Finally, we call bus_put() to release the refcount + */ +void bus_unregister(struct bus_type *bus) +{ + pr_debug("bus: '%s': unregistering\n", bus->name); + bus_remove_attrs(bus); + remove_probe_files(bus); + kset_unregister(bus->p->drivers_kset); + kset_unregister(bus->p->devices_kset); + bus_remove_file(bus, &bus_attr_uevent); + kset_unregister(&bus->p->subsys); + kfree(bus->p); + bus->p = NULL; +} +EXPORT_SYMBOL_GPL(bus_unregister); + +int bus_register_notifier(struct bus_type *bus, struct notifier_block *nb) +{ + return blocking_notifier_chain_register(&bus->p->bus_notifier, nb); +} +EXPORT_SYMBOL_GPL(bus_register_notifier); + +int bus_unregister_notifier(struct bus_type *bus, struct notifier_block *nb) +{ + return blocking_notifier_chain_unregister(&bus->p->bus_notifier, nb); +} +EXPORT_SYMBOL_GPL(bus_unregister_notifier); + +struct kset *bus_get_kset(struct bus_type *bus) +{ + return &bus->p->subsys; +} +EXPORT_SYMBOL_GPL(bus_get_kset); + +struct klist *bus_get_device_klist(struct bus_type *bus) +{ + return &bus->p->klist_devices; +} +EXPORT_SYMBOL_GPL(bus_get_device_klist); + +/* + * Yes, this forcibly breaks the klist abstraction temporarily. It + * just wants to sort the klist, not change reference counts and + * take/drop locks rapidly in the process. It does all this while + * holding the lock for the list, so objects can't otherwise be + * added/removed while we're swizzling. + */ +static void device_insertion_sort_klist(struct device *a, struct list_head *list, + int (*compare)(const struct device *a, + const struct device *b)) +{ + struct list_head *pos; + struct klist_node *n; + struct device_private *dev_prv; + struct device *b; + + list_for_each(pos, list) { + n = container_of(pos, struct klist_node, n_node); + dev_prv = to_device_private_bus(n); + b = dev_prv->device; + if (compare(a, b) <= 0) { + list_move_tail(&a->p->knode_bus.n_node, + &b->p->knode_bus.n_node); + return; + } + } + list_move_tail(&a->p->knode_bus.n_node, list); +} + +void bus_sort_breadthfirst(struct bus_type *bus, + int (*compare)(const struct device *a, + const struct device *b)) +{ + LIST_HEAD(sorted_devices); + struct list_head *pos, *tmp; + struct klist_node *n; + struct device_private *dev_prv; + struct device *dev; + struct klist *device_klist; + + device_klist = bus_get_device_klist(bus); + + spin_lock(&device_klist->k_lock); + list_for_each_safe(pos, tmp, &device_klist->k_list) { + n = container_of(pos, struct klist_node, n_node); + dev_prv = to_device_private_bus(n); + dev = dev_prv->device; + device_insertion_sort_klist(dev, &sorted_devices, compare); + } + list_splice(&sorted_devices, &device_klist->k_list); + spin_unlock(&device_klist->k_lock); +} +EXPORT_SYMBOL_GPL(bus_sort_breadthfirst); + +int __init buses_init(void) +{ + bus_kset = kset_create_and_add("bus", &bus_uevent_ops, NULL); + if (!bus_kset) + return -ENOMEM; + return 0; +} diff --git a/drivers/base/class.c b/drivers/base/class.c new file mode 100644 index 00000000..4f1df2e8 --- /dev/null +++ b/drivers/base/class.c @@ -0,0 +1,596 @@ +/* + * 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 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, +}; + +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->class_interfaces); + kset_init(&cp->glue_dirs); + __mutex_init(&cp->class_mutex, "struct class 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, + void *data, + int (*match)(struct device *, 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->class_mutex); + list_add_tail(&class_intf->node, &parent->p->class_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->class_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->class_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->class_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); diff --git a/drivers/base/core.c b/drivers/base/core.c new file mode 100644 index 00000000..d13851c5 --- /dev/null +++ b/drivers/base/core.c @@ -0,0 +1,1828 @@ +/* + * drivers/base/core.c - core driver model code (device registration, etc) + * + * Copyright (c) 2002-3 Patrick Mochel + * Copyright (c) 2002-3 Open Source Development Labs + * Copyright (c) 2006 Greg Kroah-Hartman <gregkh@suse.de> + * Copyright (c) 2006 Novell, Inc. + * + * This file is released under the GPLv2 + * + */ + +#include <linux/device.h> +#include <linux/err.h> +#include <linux/init.h> +#include <linux/module.h> +#include <linux/slab.h> +#include <linux/string.h> +#include <linux/kdev_t.h> +#include <linux/notifier.h> +#include <linux/genhd.h> +#include <linux/kallsyms.h> +#include <linux/mutex.h> +#include <linux/async.h> +#include <linux/pm_runtime.h> + +#include "base.h" +#include "power/power.h" + +#ifdef CONFIG_SYSFS_DEPRECATED +#ifdef CONFIG_SYSFS_DEPRECATED_V2 +long sysfs_deprecated = 1; +#else +long sysfs_deprecated = 0; +#endif +static __init int sysfs_deprecated_setup(char *arg) +{ + return strict_strtol(arg, 10, &sysfs_deprecated); +} +early_param("sysfs.deprecated", sysfs_deprecated_setup); +#endif + +int (*platform_notify)(struct device *dev) = NULL; +int (*platform_notify_remove)(struct device *dev) = NULL; +static struct kobject *dev_kobj; +struct kobject *sysfs_dev_char_kobj; +struct kobject *sysfs_dev_block_kobj; + +#ifdef CONFIG_BLOCK +static inline int device_is_not_partition(struct device *dev) +{ + return !(dev->type == &part_type); +} +#else +static inline int device_is_not_partition(struct device *dev) +{ + return 1; +} +#endif + +/** + * dev_driver_string - Return a device's driver name, if at all possible + * @dev: struct device to get the name of + * + * Will return the device's driver's name if it is bound to a device. If + * the device is not bound to a device, it will return the name of the bus + * it is attached to. If it is not attached to a bus either, an empty + * string will be returned. + */ +const char *dev_driver_string(const struct device *dev) +{ + struct device_driver *drv; + + /* dev->driver can change to NULL underneath us because of unbinding, + * so be careful about accessing it. dev->bus and dev->class should + * never change once they are set, so they don't need special care. + */ + drv = ACCESS_ONCE(dev->driver); + return drv ? drv->name : + (dev->bus ? dev->bus->name : + (dev->class ? dev->class->name : "")); +} +EXPORT_SYMBOL(dev_driver_string); + +#define to_dev(obj) container_of(obj, struct device, kobj) +#define to_dev_attr(_attr) container_of(_attr, struct device_attribute, attr) + +static ssize_t dev_attr_show(struct kobject *kobj, struct attribute *attr, + char *buf) +{ + struct device_attribute *dev_attr = to_dev_attr(attr); + struct device *dev = to_dev(kobj); + ssize_t ret = -EIO; + + if (dev_attr->show) + ret = dev_attr->show(dev, dev_attr, buf); + if (ret >= (ssize_t)PAGE_SIZE) { + print_symbol("dev_attr_show: %s returned bad count\n", + (unsigned long)dev_attr->show); + } + return ret; +} + +static ssize_t dev_attr_store(struct kobject *kobj, struct attribute *attr, + const char *buf, size_t count) +{ + struct device_attribute *dev_attr = to_dev_attr(attr); + struct device *dev = to_dev(kobj); + ssize_t ret = -EIO; + + if (dev_attr->store) + ret = dev_attr->store(dev, dev_attr, buf, count); + return ret; +} + +static const struct sysfs_ops dev_sysfs_ops = { + .show = dev_attr_show, + .store = dev_attr_store, +}; + + +/** + * device_release - free device structure. + * @kobj: device's kobject. + * + * This is called once the reference count for the object + * reaches 0. We forward the call to the device's release + * method, which should handle actually freeing the structure. + */ +static void device_release(struct kobject *kobj) +{ + struct device *dev = to_dev(kobj); + struct device_private *p = dev->p; + + if (dev->release) + dev->release(dev); + else if (dev->type && dev->type->release) + dev->type->release(dev); + else if (dev->class && dev->class->dev_release) + dev->class->dev_release(dev); + else + WARN(1, KERN_ERR "Device '%s' does not have a release() " + "function, it is broken and must be fixed.\n", + dev_name(dev)); + kfree(p); +} + +static const void *device_namespace(struct kobject *kobj) +{ + struct device *dev = to_dev(kobj); + const void *ns = NULL; + + if (dev->class && dev->class->ns_type) + ns = dev->class->namespace(dev); + + return ns; +} + +static struct kobj_type device_ktype = { + .release = device_release, + .sysfs_ops = &dev_sysfs_ops, + .namespace = device_namespace, +}; + + +static int dev_uevent_filter(struct kset *kset, struct kobject *kobj) +{ + struct kobj_type *ktype = get_ktype(kobj); + + if (ktype == &device_ktype) { + struct device *dev = to_dev(kobj); + if (dev->bus) + return 1; + if (dev->class) + return 1; + } + return 0; +} + +static const char *dev_uevent_name(struct kset *kset, struct kobject *kobj) +{ + struct device *dev = to_dev(kobj); + + if (dev->bus) + return dev->bus->name; + if (dev->class) + return dev->class->name; + return NULL; +} + +static int dev_uevent(struct kset *kset, struct kobject *kobj, + struct kobj_uevent_env *env) +{ + struct device *dev = to_dev(kobj); + int retval = 0; + + /* add device node properties if present */ + if (MAJOR(dev->devt)) { + const char *tmp; + const char *name; + mode_t mode = 0; + + add_uevent_var(env, "MAJOR=%u", MAJOR(dev->devt)); + add_uevent_var(env, "MINOR=%u", MINOR(dev->devt)); + name = device_get_devnode(dev, &mode, &tmp); + if (name) { + add_uevent_var(env, "DEVNAME=%s", name); + kfree(tmp); + if (mode) + add_uevent_var(env, "DEVMODE=%#o", mode & 0777); + } + } + + if (dev->type && dev->type->name) + add_uevent_var(env, "DEVTYPE=%s", dev->type->name); + + if (dev->driver) + add_uevent_var(env, "DRIVER=%s", dev->driver->name); + + /* have the bus specific function add its stuff */ + if (dev->bus && dev->bus->uevent) { + retval = dev->bus->uevent(dev, env); + if (retval) + pr_debug("device: '%s': %s: bus uevent() returned %d\n", + dev_name(dev), __func__, retval); + } + + /* have the class specific function add its stuff */ + if (dev->class && dev->class->dev_uevent) { + retval = dev->class->dev_uevent(dev, env); + if (retval) + pr_debug("device: '%s': %s: class uevent() " + "returned %d\n", dev_name(dev), + __func__, retval); + } + + /* have the device type specific function add its stuff */ + if (dev->type && dev->type->uevent) { + retval = dev->type->uevent(dev, env); + if (retval) + pr_debug("device: '%s': %s: dev_type uevent() " + "returned %d\n", dev_name(dev), + __func__, retval); + } + + return retval; +} + +static const struct kset_uevent_ops device_uevent_ops = { + .filter = dev_uevent_filter, + .name = dev_uevent_name, + .uevent = dev_uevent, +}; + +static ssize_t show_uevent(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct kobject *top_kobj; + struct kset *kset; + struct kobj_uevent_env *env = NULL; + int i; + size_t count = 0; + int retval; + + /* search the kset, the device belongs to */ + top_kobj = &dev->kobj; + while (!top_kobj->kset && top_kobj->parent) + top_kobj = top_kobj->parent; + if (!top_kobj->kset) + goto out; + + kset = top_kobj->kset; + if (!kset->uevent_ops || !kset->uevent_ops->uevent) + goto out; + + /* respect filter */ + if (kset->uevent_ops && kset->uevent_ops->filter) + if (!kset->uevent_ops->filter(kset, &dev->kobj)) + goto out; + + env = kzalloc(sizeof(struct kobj_uevent_env), GFP_KERNEL); + if (!env) + return -ENOMEM; + + /* let the kset specific function add its keys */ + retval = kset->uevent_ops->uevent(kset, &dev->kobj, env); + if (retval) + goto out; + + /* copy keys to file */ + for (i = 0; i < env->envp_idx; i++) + count += sprintf(&buf[count], "%s\n", env->envp[i]); +out: + kfree(env); + return count; +} + +static ssize_t store_uevent(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) +{ + enum kobject_action action; + + if (kobject_action_type(buf, count, &action) == 0) + kobject_uevent(&dev->kobj, action); + else + dev_err(dev, "uevent: unknown action-string\n"); + return count; +} + +static struct device_attribute uevent_attr = + __ATTR(uevent, S_IRUGO | S_IWUSR, show_uevent, store_uevent); + +static int device_add_attributes(struct device *dev, + struct device_attribute *attrs) +{ + int error = 0; + int i; + + if (attrs) { + for (i = 0; attr_name(attrs[i]); i++) { + error = device_create_file(dev, &attrs[i]); + if (error) + break; + } + if (error) + while (--i >= 0) + device_remove_file(dev, &attrs[i]); + } + return error; +} + +static void device_remove_attributes(struct device *dev, + struct device_attribute *attrs) +{ + int i; + + if (attrs) + for (i = 0; attr_name(attrs[i]); i++) + device_remove_file(dev, &attrs[i]); +} + +static int device_add_bin_attributes(struct device *dev, + struct bin_attribute *attrs) +{ + int error = 0; + int i; + + if (attrs) { + for (i = 0; attr_name(attrs[i]); i++) { + error = device_create_bin_file(dev, &attrs[i]); + if (error) + break; + } + if (error) + while (--i >= 0) + device_remove_bin_file(dev, &attrs[i]); + } + return error; +} + +static void device_remove_bin_attributes(struct device *dev, + struct bin_attribute *attrs) +{ + int i; + + if (attrs) + for (i = 0; attr_name(attrs[i]); i++) + device_remove_bin_file(dev, &attrs[i]); +} + +static int device_add_groups(struct device *dev, + const struct attribute_group **groups) +{ + int error = 0; + int i; + + if (groups) { + for (i = 0; groups[i]; i++) { + error = sysfs_create_group(&dev->kobj, groups[i]); + if (error) { + while (--i >= 0) + sysfs_remove_group(&dev->kobj, + groups[i]); + break; + } + } + } + return error; +} + +static void device_remove_groups(struct device *dev, + const struct attribute_group **groups) +{ + int i; + + if (groups) + for (i = 0; groups[i]; i++) + sysfs_remove_group(&dev->kobj, groups[i]); +} + +static int device_add_attrs(struct device *dev) +{ + struct class *class = dev->class; + const struct device_type *type = dev->type; + int error; + + if (class) { + error = device_add_attributes(dev, class->dev_attrs); + if (error) + return error; + error = device_add_bin_attributes(dev, class->dev_bin_attrs); + if (error) + goto err_remove_class_attrs; + } + + if (type) { + error = device_add_groups(dev, type->groups); + if (error) + goto err_remove_class_bin_attrs; + } + + error = device_add_groups(dev, dev->groups); + if (error) + goto err_remove_type_groups; + + return 0; + + err_remove_type_groups: + if (type) + device_remove_groups(dev, type->groups); + err_remove_class_bin_attrs: + if (class) + device_remove_bin_attributes(dev, class->dev_bin_attrs); + err_remove_class_attrs: + if (class) + device_remove_attributes(dev, class->dev_attrs); + + return error; +} + +static void device_remove_attrs(struct device *dev) +{ + struct class *class = dev->class; + const struct device_type *type = dev->type; + + device_remove_groups(dev, dev->groups); + + if (type) + device_remove_groups(dev, type->groups); + + if (class) { + device_remove_attributes(dev, class->dev_attrs); + device_remove_bin_attributes(dev, class->dev_bin_attrs); + } +} + + +static ssize_t show_dev(struct device *dev, struct device_attribute *attr, + char *buf) +{ + return print_dev_t(buf, dev->devt); +} + +static struct device_attribute devt_attr = + __ATTR(dev, S_IRUGO, show_dev, NULL); + +/* kset to create /sys/devices/ */ +struct kset *devices_kset; + +/** + * device_create_file - create sysfs attribute file for device. + * @dev: device. + * @attr: device attribute descriptor. + */ +int device_create_file(struct device *dev, + const struct device_attribute *attr) +{ + int error = 0; + if (dev) + error = sysfs_create_file(&dev->kobj, &attr->attr); + return error; +} + +/** + * device_remove_file - remove sysfs attribute file. + * @dev: device. + * @attr: device attribute descriptor. + */ +void device_remove_file(struct device *dev, + const struct device_attribute *attr) +{ + if (dev) + sysfs_remove_file(&dev->kobj, &attr->attr); +} + +/** + * device_create_bin_file - create sysfs binary attribute file for device. + * @dev: device. + * @attr: device binary attribute descriptor. + */ +int device_create_bin_file(struct device *dev, + const struct bin_attribute *attr) +{ + int error = -EINVAL; + if (dev) + error = sysfs_create_bin_file(&dev->kobj, attr); + return error; +} +EXPORT_SYMBOL_GPL(device_create_bin_file); + +/** + * device_remove_bin_file - remove sysfs binary attribute file + * @dev: device. + * @attr: device binary attribute descriptor. + */ +void device_remove_bin_file(struct device *dev, + const struct bin_attribute *attr) +{ + if (dev) + sysfs_remove_bin_file(&dev->kobj, attr); +} +EXPORT_SYMBOL_GPL(device_remove_bin_file); + +/** + * device_schedule_callback_owner - helper to schedule a callback for a device + * @dev: device. + * @func: callback function to invoke later. + * @owner: module owning the callback routine + * + * Attribute methods must not unregister themselves or their parent device + * (which would amount to the same thing). Attempts to do so will deadlock, + * since unregistration is mutually exclusive with driver callbacks. + * + * Instead methods can call this routine, which will attempt to allocate + * and schedule a workqueue request to call back @func with @dev as its + * argument in the workqueue's process context. @dev will be pinned until + * @func returns. + * + * This routine is usually called via the inline device_schedule_callback(), + * which automatically sets @owner to THIS_MODULE. + * + * Returns 0 if the request was submitted, -ENOMEM if storage could not + * be allocated, -ENODEV if a reference to @owner isn't available. + * + * NOTE: This routine won't work if CONFIG_SYSFS isn't set! It uses an + * underlying sysfs routine (since it is intended for use by attribute + * methods), and if sysfs isn't available you'll get nothing but -ENOSYS. + */ +int device_schedule_callback_owner(struct device *dev, + void (*func)(struct device *), struct module *owner) +{ + return sysfs_schedule_callback(&dev->kobj, + (void (*)(void *)) func, dev, owner); +} +EXPORT_SYMBOL_GPL(device_schedule_callback_owner); + +static void klist_children_get(struct klist_node *n) +{ + struct device_private *p = to_device_private_parent(n); + struct device *dev = p->device; + + get_device(dev); +} + +static void klist_children_put(struct klist_node *n) +{ + struct device_private *p = to_device_private_parent(n); + struct device *dev = p->device; + + put_device(dev); +} + +/** + * device_initialize - init device structure. + * @dev: device. + * + * This prepares the device for use by other layers by initializing + * its fields. + * It is the first half of device_register(), if called by + * that function, though it can also be called separately, so one + * may use @dev's fields. In particular, get_device()/put_device() + * may be used for reference counting of @dev after calling this + * function. + * + * NOTE: Use put_device() to give up your reference instead of freeing + * @dev directly once you have called this function. + */ +void device_initialize(struct device *dev) +{ + dev->kobj.kset = devices_kset; + kobject_init(&dev->kobj, &device_ktype); + INIT_LIST_HEAD(&dev->dma_pools); + mutex_init(&dev->mutex); + lockdep_set_novalidate_class(&dev->mutex); + spin_lock_init(&dev->devres_lock); + INIT_LIST_HEAD(&dev->devres_head); + device_pm_init(dev); + set_dev_node(dev, -1); +} + +static struct kobject *virtual_device_parent(struct device *dev) +{ + static struct kobject *virtual_dir = NULL; + + if (!virtual_dir) + virtual_dir = kobject_create_and_add("virtual", + &devices_kset->kobj); + + return virtual_dir; +} + +struct class_dir { + struct kobject kobj; + struct class *class; +}; + +#define to_class_dir(obj) container_of(obj, struct class_dir, kobj) + +static void class_dir_release(struct kobject *kobj) +{ + struct class_dir *dir = to_class_dir(kobj); + kfree(dir); +} + +static const +struct kobj_ns_type_operations *class_dir_child_ns_type(struct kobject *kobj) +{ + struct class_dir *dir = to_class_dir(kobj); + return dir->class->ns_type; +} + +static struct kobj_type class_dir_ktype = { + .release = class_dir_release, + .sysfs_ops = &kobj_sysfs_ops, + .child_ns_type = class_dir_child_ns_type +}; + +static struct kobject * +class_dir_create_and_add(struct class *class, struct kobject *parent_kobj) +{ + struct class_dir *dir; + int retval; + + dir = kzalloc(sizeof(*dir), GFP_KERNEL); + if (!dir) + return NULL; + + dir->class = class; + kobject_init(&dir->kobj, &class_dir_ktype); + + dir->kobj.kset = &class->p->glue_dirs; + + retval = kobject_add(&dir->kobj, parent_kobj, "%s", class->name); + if (retval < 0) { + kobject_put(&dir->kobj); + return NULL; + } + return &dir->kobj; +} + + +static struct kobject *get_device_parent(struct device *dev, + struct device *parent) +{ + if (dev->class) { + static DEFINE_MUTEX(gdp_mutex); + struct kobject *kobj = NULL; + struct kobject *parent_kobj; + struct kobject *k; + +#ifdef CONFIG_BLOCK + /* block disks show up in /sys/block */ + if (sysfs_deprecated && dev->class == &block_class) { + if (parent && parent->class == &block_class) + return &parent->kobj; + return &block_class.p->subsys.kobj; + } +#endif + + /* + * If we have no parent, we live in "virtual". + * Class-devices with a non class-device as parent, live + * in a "glue" directory to prevent namespace collisions. + */ + if (parent == NULL) + parent_kobj = virtual_device_parent(dev); + else if (parent->class && !dev->class->ns_type) + return &parent->kobj; + else + parent_kobj = &parent->kobj; + + mutex_lock(&gdp_mutex); + + /* find our class-directory at the parent and reference it */ + spin_lock(&dev->class->p->glue_dirs.list_lock); + list_for_each_entry(k, &dev->class->p->glue_dirs.list, entry) + if (k->parent == parent_kobj) { + kobj = kobject_get(k); + break; + } + spin_unlock(&dev->class->p->glue_dirs.list_lock); + if (kobj) { + mutex_unlock(&gdp_mutex); + return kobj; + } + + /* or create a new class-directory at the parent device */ + k = class_dir_create_and_add(dev->class, parent_kobj); + /* do not emit an uevent for this simple "glue" directory */ + mutex_unlock(&gdp_mutex); + return k; + } + + if (parent) + return &parent->kobj; + return NULL; +} + +static void cleanup_glue_dir(struct device *dev, struct kobject *glue_dir) +{ + /* see if we live in a "glue" directory */ + if (!glue_dir || !dev->class || + glue_dir->kset != &dev->class->p->glue_dirs) + return; + + kobject_put(glue_dir); +} + +static void cleanup_device_parent(struct device *dev) +{ + cleanup_glue_dir(dev, dev->kobj.parent); +} + +static void setup_parent(struct device *dev, struct device *parent) +{ + struct kobject *kobj; + kobj = get_device_parent(dev, parent); + if (kobj) + dev->kobj.parent = kobj; +} + +static int device_add_class_symlinks(struct device *dev) +{ + int error; + + if (!dev->class) + return 0; + + error = sysfs_create_link(&dev->kobj, + &dev->class->p->subsys.kobj, + "subsystem"); + if (error) + goto out; + + if (dev->parent && device_is_not_partition(dev)) { + error = sysfs_create_link(&dev->kobj, &dev->parent->kobj, + "device"); + if (error) + goto out_subsys; + } + +#ifdef CONFIG_BLOCK + /* /sys/block has directories and does not need symlinks */ + if (sysfs_deprecated && dev->class == &block_class) + return 0; +#endif + + /* link in the class directory pointing to the device */ + error = sysfs_create_link(&dev->class->p->subsys.kobj, + &dev->kobj, dev_name(dev)); + if (error) + goto out_device; + + return 0; + +out_device: + sysfs_remove_link(&dev->kobj, "device"); + +out_subsys: + sysfs_remove_link(&dev->kobj, "subsystem"); +out: + return error; +} + +static void device_remove_class_symlinks(struct device *dev) +{ + if (!dev->class) + return; + + if (dev->parent && device_is_not_partition(dev)) + sysfs_remove_link(&dev->kobj, "device"); + sysfs_remove_link(&dev->kobj, "subsystem"); +#ifdef CONFIG_BLOCK + if (sysfs_deprecated && dev->class == &block_class) + return; +#endif + sysfs_delete_link(&dev->class->p->subsys.kobj, &dev->kobj, dev_name(dev)); +} + +/** + * dev_set_name - set a device name + * @dev: device + * @fmt: format string for the device's name + */ +int dev_set_name(struct device *dev, const char *fmt, ...) +{ + va_list vargs; + int err; + + va_start(vargs, fmt); + err = kobject_set_name_vargs(&dev->kobj, fmt, vargs); + va_end(vargs); + return err; +} +EXPORT_SYMBOL_GPL(dev_set_name); + +/** + * device_to_dev_kobj - select a /sys/dev/ directory for the device + * @dev: device + * + * By default we select char/ for new entries. Setting class->dev_obj + * to NULL prevents an entry from being created. class->dev_kobj must + * be set (or cleared) before any devices are registered to the class + * otherwise device_create_sys_dev_entry() and + * device_remove_sys_dev_entry() will disagree about the the presence + * of the link. + */ +static struct kobject *device_to_dev_kobj(struct device *dev) +{ + struct kobject *kobj; + + if (dev->class) + kobj = dev->class->dev_kobj; + else + kobj = sysfs_dev_char_kobj; + + return kobj; +} + +static int device_create_sys_dev_entry(struct device *dev) +{ + struct kobject *kobj = device_to_dev_kobj(dev); + int error = 0; + char devt_str[15]; + + if (kobj) { + format_dev_t(devt_str, dev->devt); + error = sysfs_create_link(kobj, &dev->kobj, devt_str); + } + + return error; +} + +static void device_remove_sys_dev_entry(struct device *dev) +{ + struct kobject *kobj = device_to_dev_kobj(dev); + char devt_str[15]; + + if (kobj) { + format_dev_t(devt_str, dev->devt); + sysfs_remove_link(kobj, devt_str); + } +} + +int device_private_init(struct device *dev) +{ + dev->p = kzalloc(sizeof(*dev->p), GFP_KERNEL); + if (!dev->p) + return -ENOMEM; + dev->p->device = dev; + klist_init(&dev->p->klist_children, klist_children_get, + klist_children_put); + return 0; +} + +/** + * device_add - add device to device hierarchy. + * @dev: device. + * + * This is part 2 of device_register(), though may be called + * separately _iff_ device_initialize() has been called separately. + * + * This adds @dev to the kobject hierarchy via kobject_add(), adds it + * to the global and sibling lists for the device, then + * adds it to the other relevant subsystems of the driver model. + * + * NOTE: _Never_ directly free @dev after calling this function, even + * if it returned an error! Always use put_device() to give up your + * reference instead. + */ +int device_add(struct device *dev) +{ + struct device *parent = NULL; + struct class_interface *class_intf; + int error = -EINVAL; + + dev = get_device(dev); + if (!dev) + goto done; + + if (!dev->p) { + error = device_private_init(dev); + if (error) + goto done; + } + + /* + * for statically allocated devices, which should all be converted + * some day, we need to initialize the name. We prevent reading back + * the name, and force the use of dev_name() + */ + if (dev->init_name) { + dev_set_name(dev, "%s", dev->init_name); + dev->init_name = NULL; + } + + if (!dev_name(dev)) { + error = -EINVAL; + goto name_error; + } + + pr_debug("device: '%s': %s\n", dev_name(dev), __func__); + + parent = get_device(dev->parent); + setup_parent(dev, parent); + + /* use parent numa_node */ + if (parent) + set_dev_node(dev, dev_to_node(parent)); + + /* first, register with generic layer. */ + /* we require the name to be set before, and pass NULL */ + error = kobject_add(&dev->kobj, dev->kobj.parent, NULL); + if (error) + goto Error; + + /* notify platform of device entry */ + if (platform_notify) + platform_notify(dev); + + error = device_create_file(dev, &uevent_attr); + if (error) + goto attrError; + + if (MAJOR(dev->devt)) { + error = device_create_file(dev, &devt_attr); + if (error) + goto ueventattrError; + + error = device_create_sys_dev_entry(dev); + if (error) + goto devtattrError; + + devtmpfs_create_node(dev); + } + + error = device_add_class_symlinks(dev); + if (error) + goto SymlinkError; + error = device_add_attrs(dev); + if (error) + goto AttrsError; + error = bus_add_device(dev); + if (error) + goto BusError; + error = dpm_sysfs_add(dev); + if (error) + goto DPMError; + device_pm_add(dev); + + /* Notify clients of device addition. This call must come + * after dpm_sysf_add() and before kobject_uevent(). + */ + if (dev->bus) + blocking_notifier_call_chain(&dev->bus->p->bus_notifier, + BUS_NOTIFY_ADD_DEVICE, dev); + + kobject_uevent(&dev->kobj, KOBJ_ADD); + bus_probe_device(dev); + if (parent) + klist_add_tail(&dev->p->knode_parent, + &parent->p->klist_children); + + if (dev->class) { + mutex_lock(&dev->class->p->class_mutex); + /* tie the class to the device */ + klist_add_tail(&dev->knode_class, + &dev->class->p->klist_devices); + + /* notify any interfaces that the device is here */ + list_for_each_entry(class_intf, + &dev->class->p->class_interfaces, node) + if (class_intf->add_dev) + class_intf->add_dev(dev, class_intf); + mutex_unlock(&dev->class->p->class_mutex); + } +done: + put_device(dev); + return error; + DPMError: + bus_remove_device(dev); + BusError: + device_remove_attrs(dev); + AttrsError: + device_remove_class_symlinks(dev); + SymlinkError: + if (MAJOR(dev->devt)) + devtmpfs_delete_node(dev); + if (MAJOR(dev->devt)) + device_remove_sys_dev_entry(dev); + devtattrError: + if (MAJOR(dev->devt)) + device_remove_file(dev, &devt_attr); + ueventattrError: + device_remove_file(dev, &uevent_attr); + attrError: + kobject_uevent(&dev->kobj, KOBJ_REMOVE); + kobject_del(&dev->kobj); + Error: + cleanup_device_parent(dev); + if (parent) + put_device(parent); +name_error: + kfree(dev->p); + dev->p = NULL; + goto done; +} + +/** + * device_register - register a device with the system. + * @dev: pointer to the device structure + * + * This happens in two clean steps - initialize the device + * and add it to the system. The two steps can be called + * separately, but this is the easiest and most common. + * I.e. you should only call the two helpers separately if + * have a clearly defined need to use and refcount the device + * before it is added to the hierarchy. + * + * NOTE: _Never_ directly free @dev after calling this function, even + * if it returned an error! Always use put_device() to give up the + * reference initialized in this function instead. + */ +int device_register(struct device *dev) +{ + device_initialize(dev); + return device_add(dev); +} + +/** + * get_device - increment reference count for device. + * @dev: device. + * + * This simply forwards the call to kobject_get(), though + * we do take care to provide for the case that we get a NULL + * pointer passed in. + */ +struct device *get_device(struct device *dev) +{ + return dev ? to_dev(kobject_get(&dev->kobj)) : NULL; +} + +/** + * put_device - decrement reference count. + * @dev: device in question. + */ +void put_device(struct device *dev) +{ + /* might_sleep(); */ + if (dev) + kobject_put(&dev->kobj); +} + +/** + * device_del - delete device from system. + * @dev: device. + * + * This is the first part of the device unregistration + * sequence. This removes the device from the lists we control + * from here, has it removed from the other driver model + * subsystems it was added to in device_add(), and removes it + * from the kobject hierarchy. + * + * NOTE: this should be called manually _iff_ device_add() was + * also called manually. + */ +void device_del(struct device *dev) +{ + struct device *parent = dev->parent; + struct class_interface *class_intf; + + /* Notify clients of device removal. This call must come + * before dpm_sysfs_remove(). + */ + if (dev->bus) + blocking_notifier_call_chain(&dev->bus->p->bus_notifier, + BUS_NOTIFY_DEL_DEVICE, dev); + device_pm_remove(dev); + dpm_sysfs_remove(dev); + if (parent) + klist_del(&dev->p->knode_parent); + if (MAJOR(dev->devt)) { + devtmpfs_delete_node(dev); + device_remove_sys_dev_entry(dev); + device_remove_file(dev, &devt_attr); + } + if (dev->class) { + device_remove_class_symlinks(dev); + + mutex_lock(&dev->class->p->class_mutex); + /* notify any interfaces that the device is now gone */ + list_for_each_entry(class_intf, + &dev->class->p->class_interfaces, node) + if (class_intf->remove_dev) + class_intf->remove_dev(dev, class_intf); + /* remove the device from the class list */ + klist_del(&dev->knode_class); + mutex_unlock(&dev->class->p->class_mutex); + } + device_remove_file(dev, &uevent_attr); + device_remove_attrs(dev); + bus_remove_device(dev); + + /* + * Some platform devices are driven without driver attached + * and managed resources may have been acquired. Make sure + * all resources are released. + */ + devres_release_all(dev); + + /* Notify the platform of the removal, in case they + * need to do anything... + */ + if (platform_notify_remove) + platform_notify_remove(dev); + kobject_uevent(&dev->kobj, KOBJ_REMOVE); + cleanup_device_parent(dev); + kobject_del(&dev->kobj); + put_device(parent); +} + +/** + * device_unregister - unregister device from system. + * @dev: device going away. + * + * We do this in two parts, like we do device_register(). First, + * we remove it from all the subsystems with device_del(), then + * we decrement the reference count via put_device(). If that + * is the final reference count, the device will be cleaned up + * via device_release() above. Otherwise, the structure will + * stick around until the final reference to the device is dropped. + */ +void device_unregister(struct device *dev) +{ + pr_debug("device: '%s': %s\n", dev_name(dev), __func__); + device_del(dev); + put_device(dev); +} + +static struct device *next_device(struct klist_iter *i) +{ + struct klist_node *n = klist_next(i); + struct device *dev = NULL; + struct device_private *p; + + if (n) { + p = to_device_private_parent(n); + dev = p->device; + } + return dev; +} + +/** + * device_get_devnode - path of device node file + * @dev: device + * @mode: returned file access mode + * @tmp: possibly allocated string + * + * Return the relative path of a possible device node. + * Non-default names may need to allocate a memory to compose + * a name. This memory is returned in tmp and needs to be + * freed by the caller. + */ +const char *device_get_devnode(struct device *dev, + mode_t *mode, const char **tmp) +{ + char *s; + + *tmp = NULL; + + /* the device type may provide a specific name */ + if (dev->type && dev->type->devnode) + *tmp = dev->type->devnode(dev, mode); + if (*tmp) + return *tmp; + + /* the class may provide a specific name */ + if (dev->class && dev->class->devnode) + *tmp = dev->class->devnode(dev, mode); + if (*tmp) + return *tmp; + + /* return name without allocation, tmp == NULL */ + if (strchr(dev_name(dev), '!') == NULL) + return dev_name(dev); + + /* replace '!' in the name with '/' */ + *tmp = kstrdup(dev_name(dev), GFP_KERNEL); + if (!*tmp) + return NULL; + while ((s = strchr(*tmp, '!'))) + s[0] = '/'; + return *tmp; +} + +/** + * device_for_each_child - device child iterator. + * @parent: parent struct device. + * @data: data for the callback. + * @fn: function to be called for each device. + * + * Iterate over @parent's child devices, and call @fn for each, + * passing it @data. + * + * We check the return of @fn each time. If it returns anything + * other than 0, we break out and return that value. + */ +int device_for_each_child(struct device *parent, void *data, + int (*fn)(struct device *dev, void *data)) +{ + struct klist_iter i; + struct device *child; + int error = 0; + + if (!parent->p) + return 0; + + klist_iter_init(&parent->p->klist_children, &i); + while ((child = next_device(&i)) && !error) + error = fn(child, data); + klist_iter_exit(&i); + return error; +} + +/** + * device_find_child - device iterator for locating a particular device. + * @parent: parent struct device + * @data: Data to pass to match function + * @match: Callback function to check device + * + * This is similar to the device_for_each_child() 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 and a reference to the + * current device can be obtained, this function will return to the caller + * and not iterate over any more devices. + */ +struct device *device_find_child(struct device *parent, void *data, + int (*match)(struct device *dev, void *data)) +{ + struct klist_iter i; + struct device *child; + + if (!parent) + return NULL; + + klist_iter_init(&parent->p->klist_children, &i); + while ((child = next_device(&i))) + if (match(child, data) && get_device(child)) + break; + klist_iter_exit(&i); + return child; +} + +int __init devices_init(void) +{ + devices_kset = kset_create_and_add("devices", &device_uevent_ops, NULL); + if (!devices_kset) + return -ENOMEM; + dev_kobj = kobject_create_and_add("dev", NULL); + if (!dev_kobj) + goto dev_kobj_err; + sysfs_dev_block_kobj = kobject_create_and_add("block", dev_kobj); + if (!sysfs_dev_block_kobj) + goto block_kobj_err; + sysfs_dev_char_kobj = kobject_create_and_add("char", dev_kobj); + if (!sysfs_dev_char_kobj) + goto char_kobj_err; + + return 0; + + char_kobj_err: + kobject_put(sysfs_dev_block_kobj); + block_kobj_err: + kobject_put(dev_kobj); + dev_kobj_err: + kset_unregister(devices_kset); + return -ENOMEM; +} + +EXPORT_SYMBOL_GPL(device_for_each_child); +EXPORT_SYMBOL_GPL(device_find_child); + +EXPORT_SYMBOL_GPL(device_initialize); +EXPORT_SYMBOL_GPL(device_add); +EXPORT_SYMBOL_GPL(device_register); + +EXPORT_SYMBOL_GPL(device_del); +EXPORT_SYMBOL_GPL(device_unregister); +EXPORT_SYMBOL_GPL(get_device); +EXPORT_SYMBOL_GPL(put_device); + +EXPORT_SYMBOL_GPL(device_create_file); +EXPORT_SYMBOL_GPL(device_remove_file); + +struct root_device { + struct device dev; + struct module *owner; +}; + +inline struct root_device *to_root_device(struct device *d) +{ + return container_of(d, struct root_device, dev); +} + +static void root_device_release(struct device *dev) +{ + kfree(to_root_device(dev)); +} + +/** + * __root_device_register - allocate and register a root device + * @name: root device name + * @owner: owner module of the root device, usually THIS_MODULE + * + * This function allocates a root device and registers it + * using device_register(). In order to free the returned + * device, use root_device_unregister(). + * + * Root devices are dummy devices which allow other devices + * to be grouped under /sys/devices. Use this function to + * allocate a root device and then use it as the parent of + * any device which should appear under /sys/devices/{name} + * + * The /sys/devices/{name} directory will also contain a + * 'module' symlink which points to the @owner directory + * in sysfs. + * + * Returns &struct device pointer on success, or ERR_PTR() on error. + * + * Note: You probably want to use root_device_register(). + */ +struct device *__root_device_register(const char *name, struct module *owner) +{ + struct root_device *root; + int err = -ENOMEM; + + root = kzalloc(sizeof(struct root_device), GFP_KERNEL); + if (!root) + return ERR_PTR(err); + + err = dev_set_name(&root->dev, "%s", name); + if (err) { + kfree(root); + return ERR_PTR(err); + } + + root->dev.release = root_device_release; + + err = device_register(&root->dev); + if (err) { + put_device(&root->dev); + return ERR_PTR(err); + } + +#ifdef CONFIG_MODULES /* gotta find a "cleaner" way to do this */ + if (owner) { + struct module_kobject *mk = &owner->mkobj; + + err = sysfs_create_link(&root->dev.kobj, &mk->kobj, "module"); + if (err) { + device_unregister(&root->dev); + return ERR_PTR(err); + } + root->owner = owner; + } +#endif + + return &root->dev; +} +EXPORT_SYMBOL_GPL(__root_device_register); + +/** + * root_device_unregister - unregister and free a root device + * @dev: device going away + * + * This function unregisters and cleans up a device that was created by + * root_device_register(). + */ +void root_device_unregister(struct device *dev) +{ + struct root_device *root = to_root_device(dev); + + if (root->owner) + sysfs_remove_link(&root->dev.kobj, "module"); + + device_unregister(dev); +} +EXPORT_SYMBOL_GPL(root_device_unregister); + + +static void device_create_release(struct device *dev) +{ + pr_debug("device: '%s': %s\n", dev_name(dev), __func__); + kfree(dev); +} + +/** + * device_create_vargs - creates a device and registers it with sysfs + * @class: pointer to the struct class that this device should be registered to + * @parent: pointer to the parent struct device of this new device, if any + * @devt: the dev_t for the char device to be added + * @drvdata: the data to be added to the device for callbacks + * @fmt: string for the device's name + * @args: va_list for the device's name + * + * This function can be used by char device classes. A struct device + * will be created in sysfs, registered to the specified class. + * + * A "dev" file will be created, showing the dev_t for the device, if + * the dev_t is not 0,0. + * If a pointer to a parent struct device is passed in, the newly created + * struct device will be a child of that device in sysfs. + * The pointer to the struct device will be returned from the call. + * Any further sysfs files that might be required can be created using this + * pointer. + * + * Returns &struct device pointer on success, or ERR_PTR() on error. + * + * Note: the struct class passed to this function must have previously + * been created with a call to class_create(). + */ +struct device *device_create_vargs(struct class *class, struct device *parent, + dev_t devt, void *drvdata, const char *fmt, + va_list args) +{ + struct device *dev = NULL; + int retval = -ENODEV; + + if (class == NULL || IS_ERR(class)) + goto error; + + dev = kzalloc(sizeof(*dev), GFP_KERNEL); + if (!dev) { + retval = -ENOMEM; + goto error; + } + + dev->devt = devt; + dev->class = class; + dev->parent = parent; + dev->release = device_create_release; + dev_set_drvdata(dev, drvdata); + + retval = kobject_set_name_vargs(&dev->kobj, fmt, args); + if (retval) + goto error; + + retval = device_register(dev); + if (retval) + goto error; + + return dev; + +error: + put_device(dev); + return ERR_PTR(retval); +} +EXPORT_SYMBOL_GPL(device_create_vargs); + +/** + * device_create - creates a device and registers it with sysfs + * @class: pointer to the struct class that this device should be registered to + * @parent: pointer to the parent struct device of this new device, if any + * @devt: the dev_t for the char device to be added + * @drvdata: the data to be added to the device for callbacks + * @fmt: string for the device's name + * + * This function can be used by char device classes. A struct device + * will be created in sysfs, registered to the specified class. + * + * A "dev" file will be created, showing the dev_t for the device, if + * the dev_t is not 0,0. + * If a pointer to a parent struct device is passed in, the newly created + * struct device will be a child of that device in sysfs. + * The pointer to the struct device will be returned from the call. + * Any further sysfs files that might be required can be created using this + * pointer. + * + * Returns &struct device pointer on success, or ERR_PTR() on error. + * + * Note: the struct class passed to this function must have previously + * been created with a call to class_create(). + */ +struct device *device_create(struct class *class, struct device *parent, + dev_t devt, void *drvdata, const char *fmt, ...) +{ + va_list vargs; + struct device *dev; + + va_start(vargs, fmt); + dev = device_create_vargs(class, parent, devt, drvdata, fmt, vargs); + va_end(vargs); + return dev; +} +EXPORT_SYMBOL_GPL(device_create); + +static int __match_devt(struct device *dev, void *data) +{ + dev_t *devt = data; + + return dev->devt == *devt; +} + +/** + * device_destroy - removes a device that was created with device_create() + * @class: pointer to the struct class that this device was registered with + * @devt: the dev_t of the device that was previously registered + * + * This call unregisters and cleans up a device that was created with a + * call to device_create(). + */ +void device_destroy(struct class *class, dev_t devt) +{ + struct device *dev; + + dev = class_find_device(class, NULL, &devt, __match_devt); + if (dev) { + put_device(dev); + device_unregister(dev); + } +} +EXPORT_SYMBOL_GPL(device_destroy); + +/** + * device_rename - renames a device + * @dev: the pointer to the struct device to be renamed + * @new_name: the new name of the device + * + * It is the responsibility of the caller to provide mutual + * exclusion between two different calls of device_rename + * on the same device to ensure that new_name is valid and + * won't conflict with other devices. + * + * Note: Don't call this function. Currently, the networking layer calls this + * function, but that will change. The following text from Kay Sievers offers + * some insight: + * + * Renaming devices is racy at many levels, symlinks and other stuff are not + * replaced atomically, and you get a "move" uevent, but it's not easy to + * connect the event to the old and new device. Device nodes are not renamed at + * all, there isn't even support for that in the kernel now. + * + * In the meantime, during renaming, your target name might be taken by another + * driver, creating conflicts. Or the old name is taken directly after you + * renamed it -- then you get events for the same DEVPATH, before you even see + * the "move" event. It's just a mess, and nothing new should ever rely on + * kernel device renaming. Besides that, it's not even implemented now for + * other things than (driver-core wise very simple) network devices. + * + * We are currently about to change network renaming in udev to completely + * disallow renaming of devices in the same namespace as the kernel uses, + * because we can't solve the problems properly, that arise with swapping names + * of multiple interfaces without races. Means, renaming of eth[0-9]* will only + * be allowed to some other name than eth[0-9]*, for the aforementioned + * reasons. + * + * Make up a "real" name in the driver before you register anything, or add + * some other attributes for userspace to find the device, or use udev to add + * symlinks -- but never rename kernel devices later, it's a complete mess. We + * don't even want to get into that and try to implement the missing pieces in + * the core. We really have other pieces to fix in the driver core mess. :) + */ +int device_rename(struct device *dev, const char *new_name) +{ + char *old_class_name = NULL; + char *new_class_name = NULL; + char *old_device_name = NULL; + int error; + + dev = get_device(dev); + if (!dev) + return -EINVAL; + + pr_debug("device: '%s': %s: renaming to '%s'\n", dev_name(dev), + __func__, new_name); + + old_device_name = kstrdup(dev_name(dev), GFP_KERNEL); + if (!old_device_name) { + error = -ENOMEM; + goto out; + } + + if (dev->class) { + error = sysfs_rename_link(&dev->class->p->subsys.kobj, + &dev->kobj, old_device_name, new_name); + if (error) + goto out; + } + + error = kobject_rename(&dev->kobj, new_name); + if (error) + goto out; + +out: + put_device(dev); + + kfree(new_class_name); + kfree(old_class_name); + kfree(old_device_name); + + return error; +} +EXPORT_SYMBOL_GPL(device_rename); + +static int device_move_class_links(struct device *dev, + struct device *old_parent, + struct device *new_parent) +{ + int error = 0; + + if (old_parent) + sysfs_remove_link(&dev->kobj, "device"); + if (new_parent) + error = sysfs_create_link(&dev->kobj, &new_parent->kobj, + "device"); + return error; +} + +/** + * device_move - moves a device to a new parent + * @dev: the pointer to the struct device to be moved + * @new_parent: the new parent of the device (can by NULL) + * @dpm_order: how to reorder the dpm_list + */ +int device_move(struct device *dev, struct device *new_parent, + enum dpm_order dpm_order) +{ + int error; + struct device *old_parent; + struct kobject *new_parent_kobj; + + dev = get_device(dev); + if (!dev) + return -EINVAL; + + device_pm_lock(); + new_parent = get_device(new_parent); + new_parent_kobj = get_device_parent(dev, new_parent); + + pr_debug("device: '%s': %s: moving to '%s'\n", dev_name(dev), + __func__, new_parent ? dev_name(new_parent) : "<NULL>"); + error = kobject_move(&dev->kobj, new_parent_kobj); + if (error) { + cleanup_glue_dir(dev, new_parent_kobj); + put_device(new_parent); + goto out; + } + old_parent = dev->parent; + dev->parent = new_parent; + if (old_parent) + klist_remove(&dev->p->knode_parent); + if (new_parent) { + klist_add_tail(&dev->p->knode_parent, + &new_parent->p->klist_children); + set_dev_node(dev, dev_to_node(new_parent)); + } + + if (!dev->class) + goto out_put; + error = device_move_class_links(dev, old_parent, new_parent); + if (error) { + /* We ignore errors on cleanup since we're hosed anyway... */ + device_move_class_links(dev, new_parent, old_parent); + if (!kobject_move(&dev->kobj, &old_parent->kobj)) { + if (new_parent) + klist_remove(&dev->p->knode_parent); + dev->parent = old_parent; + if (old_parent) { + klist_add_tail(&dev->p->knode_parent, + &old_parent->p->klist_children); + set_dev_node(dev, dev_to_node(old_parent)); + } + } + cleanup_glue_dir(dev, new_parent_kobj); + put_device(new_parent); + goto out; + } + switch (dpm_order) { + case DPM_ORDER_NONE: + break; + case DPM_ORDER_DEV_AFTER_PARENT: + device_pm_move_after(dev, new_parent); + break; + case DPM_ORDER_PARENT_BEFORE_DEV: + device_pm_move_before(new_parent, dev); + break; + case DPM_ORDER_DEV_LAST: + device_pm_move_last(dev); + break; + } +out_put: + put_device(old_parent); +out: + device_pm_unlock(); + put_device(dev); + return error; +} +EXPORT_SYMBOL_GPL(device_move); + +/** + * device_shutdown - call ->shutdown() on each device to shutdown. + */ +void device_shutdown(void) +{ + struct device *dev; + + spin_lock(&devices_kset->list_lock); + /* + * Walk the devices list backward, shutting down each in turn. + * Beware that device unplug events may also start pulling + * devices offline, even as the system is shutting down. + */ + while (!list_empty(&devices_kset->list)) { + dev = list_entry(devices_kset->list.prev, struct device, + kobj.entry); + get_device(dev); + /* + * Make sure the device is off the kset list, in the + * event that dev->*->shutdown() doesn't remove it. + */ + list_del_init(&dev->kobj.entry); + spin_unlock(&devices_kset->list_lock); + + /* Don't allow any more runtime suspends */ + pm_runtime_get_noresume(dev); + pm_runtime_barrier(dev); + + if (dev->bus && dev->bus->shutdown) { + dev_dbg(dev, "shutdown\n"); + dev->bus->shutdown(dev); + } else if (dev->driver && dev->driver->shutdown) { + dev_dbg(dev, "shutdown\n"); + dev->driver->shutdown(dev); + } + put_device(dev); + + spin_lock(&devices_kset->list_lock); + } + spin_unlock(&devices_kset->list_lock); + async_synchronize_full(); +} + +/* + * Device logging functions + */ + +#ifdef CONFIG_PRINTK + +static int __dev_printk(const char *level, const struct device *dev, + struct va_format *vaf) +{ + if (!dev) + return printk("%s(NULL device *): %pV", level, vaf); + + return printk("%s%s %s: %pV", + level, dev_driver_string(dev), dev_name(dev), vaf); +} + +int dev_printk(const char *level, const struct device *dev, + const char *fmt, ...) +{ + struct va_format vaf; + va_list args; + int r; + + va_start(args, fmt); + + vaf.fmt = fmt; + vaf.va = &args; + + r = __dev_printk(level, dev, &vaf); + va_end(args); + + return r; +} +EXPORT_SYMBOL(dev_printk); + +#define define_dev_printk_level(func, kern_level) \ +int func(const struct device *dev, const char *fmt, ...) \ +{ \ + struct va_format vaf; \ + va_list args; \ + int r; \ + \ + va_start(args, fmt); \ + \ + vaf.fmt = fmt; \ + vaf.va = &args; \ + \ + r = __dev_printk(kern_level, dev, &vaf); \ + va_end(args); \ + \ + return r; \ +} \ +EXPORT_SYMBOL(func); + +define_dev_printk_level(dev_emerg, KERN_EMERG); +define_dev_printk_level(dev_alert, KERN_ALERT); +define_dev_printk_level(dev_crit, KERN_CRIT); +define_dev_printk_level(dev_err, KERN_ERR); +define_dev_printk_level(dev_warn, KERN_WARNING); +define_dev_printk_level(dev_notice, KERN_NOTICE); +define_dev_printk_level(_dev_info, KERN_INFO); + +#endif diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c new file mode 100644 index 00000000..251acea3 --- /dev/null +++ b/drivers/base/cpu.c @@ -0,0 +1,274 @@ +/* + * drivers/base/cpu.c - basic CPU class support + */ + +#include <linux/sysdev.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 "base.h" + +static struct sysdev_class_attribute *cpu_sysdev_class_attrs[]; + +struct sysdev_class cpu_sysdev_class = { + .name = "cpu", + .attrs = cpu_sysdev_class_attrs, +}; +EXPORT_SYMBOL(cpu_sysdev_class); + +static DEFINE_PER_CPU(struct sys_device *, cpu_sys_devices); + +#ifdef CONFIG_HOTPLUG_CPU +static ssize_t show_online(struct sys_device *dev, struct sysdev_attribute *attr, + char *buf) +{ + struct cpu *cpu = container_of(dev, struct cpu, sysdev); + + return sprintf(buf, "%u\n", !!cpu_online(cpu->sysdev.id)); +} + +static ssize_t __ref store_online(struct sys_device *dev, struct sysdev_attribute *attr, + const char *buf, size_t count) +{ + struct cpu *cpu = container_of(dev, struct cpu, sysdev); + ssize_t ret; + + cpu_hotplug_driver_lock(); + switch (buf[0]) { + case '0': + ret = cpu_down(cpu->sysdev.id); + if (!ret) + kobject_uevent(&dev->kobj, KOBJ_OFFLINE); + break; + case '1': + ret = cpu_up(cpu->sysdev.id); + if (!ret) + kobject_uevent(&dev->kobj, KOBJ_ONLINE); + break; + default: + ret = -EINVAL; + } + cpu_hotplug_driver_unlock(); + + if (ret >= 0) + ret = count; + return ret; +} +static SYSDEV_ATTR(online, 0644, show_online, store_online); + +static void __cpuinit register_cpu_control(struct cpu *cpu) +{ + sysdev_create_file(&cpu->sysdev, &attr_online); +} +void unregister_cpu(struct cpu *cpu) +{ + int logical_cpu = cpu->sysdev.id; + + unregister_cpu_under_node(logical_cpu, cpu_to_node(logical_cpu)); + + sysdev_remove_file(&cpu->sysdev, &attr_online); + + sysdev_unregister(&cpu->sysdev); + per_cpu(cpu_sys_devices, logical_cpu) = NULL; + return; +} + +#ifdef CONFIG_ARCH_CPU_PROBE_RELEASE +static ssize_t cpu_probe_store(struct sysdev_class *class, + struct sysdev_class_attribute *attr, + const char *buf, + size_t count) +{ + return arch_cpu_probe(buf, count); +} + +static ssize_t cpu_release_store(struct sysdev_class *class, + struct sysdev_class_attribute *attr, + const char *buf, + size_t count) +{ + return arch_cpu_release(buf, count); +} + +static SYSDEV_CLASS_ATTR(probe, S_IWUSR, NULL, cpu_probe_store); +static SYSDEV_CLASS_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 sys_device *dev, struct sysdev_attribute *attr, + char *buf) +{ + struct cpu *cpu = container_of(dev, struct cpu, sysdev); + ssize_t rc; + unsigned long long addr; + int cpunum; + + cpunum = cpu->sysdev.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 SYSDEV_ATTR(crash_notes, 0400, show_crash_notes, NULL); +#endif + +/* + * Print cpu online, possible, present, and system maps + */ + +struct cpu_attr { + struct sysdev_class_attribute attr; + const struct cpumask *const * const map; +}; + +static ssize_t show_cpus_attr(struct sysdev_class *class, + struct sysdev_class_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) \ + { _SYSDEV_CLASS_ATTR(name, 0444, show_cpus_attr, NULL), map } + +/* Keep in sync with cpu_sysdev_class_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 sysdev_class *class, + struct sysdev_class_attribute *attr, char *buf) +{ + int n = snprintf(buf, PAGE_SIZE-2, "%d\n", NR_CPUS - 1); + return n; +} +static SYSDEV_CLASS_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 sysdev_class *class, + struct sysdev_class_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 SYSDEV_CLASS_ATTR(offline, 0444, print_cpus_offline, NULL); + +/* + * 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); + cpu->sysdev.id = num; + cpu->sysdev.cls = &cpu_sysdev_class; + + error = sysdev_register(&cpu->sysdev); + + if (!error && cpu->hotpluggable) + register_cpu_control(cpu); + if (!error) + per_cpu(cpu_sys_devices, num) = &cpu->sysdev; + if (!error) + register_cpu_under_node(num, cpu_to_node(num)); + +#ifdef CONFIG_KEXEC + if (!error) + error = sysdev_create_file(&cpu->sysdev, &attr_crash_notes); +#endif + return error; +} + +struct sys_device *get_cpu_sysdev(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_sysdev); + +int __init cpu_dev_init(void) +{ + int err; + + err = sysdev_class_register(&cpu_sysdev_class); +#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT) + if (!err) + err = sched_create_sysfs_power_savings_entries(&cpu_sysdev_class); +#endif + + return err; +} + +static struct sysdev_class_attribute *cpu_sysdev_class_attrs[] = { +#ifdef CONFIG_ARCH_CPU_PROBE_RELEASE + &attr_probe, + &attr_release, +#endif + &cpu_attrs[0].attr, + &cpu_attrs[1].attr, + &cpu_attrs[2].attr, + &attr_kernel_max, + &attr_offline, + NULL +}; diff --git a/drivers/base/dd.c b/drivers/base/dd.c new file mode 100644 index 00000000..6658da74 --- /dev/null +++ b/drivers/base/dd.c @@ -0,0 +1,428 @@ +/* + * 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 "base.h" +#include "power/power.h" + + +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); + + 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; + + 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; + 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; + + 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); + } + /* + * 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_get_noresume(dev); + pm_runtime_barrier(dev); + ret = really_probe(dev, drv); + pm_runtime_put_sync(dev); + + return ret; +} + +static int __device_attach(struct device_driver *drv, void *data) +{ + struct device *dev = data; + + if (!driver_match_device(drv, dev)) + return 0; + + return driver_probe_device(drv, dev); +} + +/** + * 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) +{ + 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 { + pm_runtime_get_noresume(dev); + ret = bus_for_each_drv(dev->bus, NULL, dev, __device_attach); + pm_runtime_put_sync(dev); + } +out_unlock: + device_unlock(dev); + return ret; +} +EXPORT_SYMBOL_GPL(device_attach); + +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) { + 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_sync(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; + 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); diff --git a/drivers/base/devres.c b/drivers/base/devres.c new file mode 100644 index 00000000..cf7a0c78 --- /dev/null +++ b/drivers/base/devres.c @@ -0,0 +1,650 @@ +/* + * 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_printk(KERN_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_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. + * + * 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); + +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) +{ + 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); + +/* + * 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 dev_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); diff --git a/drivers/base/devtmpfs.c b/drivers/base/devtmpfs.c new file mode 100644 index 00000000..82bbb596 --- /dev/null +++ b/drivers/base/devtmpfs.c @@ -0,0 +1,396 @@ +/* + * 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 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/cred.h> +#include <linux/sched.h> +#include <linux/init_task.h> +#include <linux/slab.h> + +static struct vfsmount *dev_mnt; + +#if defined CONFIG_DEVTMPFS_MOUNT +static int mount_dev = 1; +#else +static int mount_dev; +#endif + +static DEFINE_MUTEX(dirlock); + +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 + +static int dev_mkdir(const char *name, mode_t mode) +{ + struct nameidata nd; + struct dentry *dentry; + int err; + + err = vfs_path_lookup(dev_mnt->mnt_root, dev_mnt, + name, LOOKUP_PARENT, &nd); + if (err) + return err; + + dentry = lookup_create(&nd, 1); + if (!IS_ERR(dentry)) { + err = vfs_mkdir(nd.path.dentry->d_inode, dentry, mode); + if (!err) + /* mark as kernel-created inode */ + dentry->d_inode->i_private = &dev_mnt; + dput(dentry); + } else { + err = PTR_ERR(dentry); + } + + mutex_unlock(&nd.path.dentry->d_inode->i_mutex); + path_put(&nd.path); + return err; +} + +static int create_path(const char *nodepath) +{ + int err; + + mutex_lock(&dirlock); + err = dev_mkdir(nodepath, 0755); + if (err == -ENOENT) { + char *path; + char *s; + + /* parent directories do not exist, create them */ + path = kstrdup(nodepath, GFP_KERNEL); + if (!path) { + err = -ENOMEM; + goto out; + } + 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); + } +out: + mutex_unlock(&dirlock); + return err; +} + +int devtmpfs_create_node(struct device *dev) +{ + const char *tmp = NULL; + const char *nodename; + const struct cred *curr_cred; + mode_t mode = 0; + struct nameidata nd; + struct dentry *dentry; + int err; + + if (!dev_mnt) + return 0; + + nodename = device_get_devnode(dev, &mode, &tmp); + if (!nodename) + return -ENOMEM; + + if (mode == 0) + mode = 0600; + if (is_blockdev(dev)) + mode |= S_IFBLK; + else + mode |= S_IFCHR; + + curr_cred = override_creds(&init_cred); + + err = vfs_path_lookup(dev_mnt->mnt_root, dev_mnt, + nodename, LOOKUP_PARENT, &nd); + if (err == -ENOENT) { + create_path(nodename); + err = vfs_path_lookup(dev_mnt->mnt_root, dev_mnt, + nodename, LOOKUP_PARENT, &nd); + } + if (err) + goto out; + + dentry = lookup_create(&nd, 0); + if (!IS_ERR(dentry)) { + err = vfs_mknod(nd.path.dentry->d_inode, + dentry, mode, dev->devt); + if (!err) { + struct iattr newattrs; + + /* fixup possibly umasked mode */ + newattrs.ia_mode = mode; + newattrs.ia_valid = ATTR_MODE; + 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 = &dev_mnt; + } + dput(dentry); + } else { + err = PTR_ERR(dentry); + } + + mutex_unlock(&nd.path.dentry->d_inode->i_mutex); + path_put(&nd.path); +out: + kfree(tmp); + revert_creds(curr_cred); + return err; +} + +static int dev_rmdir(const char *name) +{ + struct nameidata nd; + struct dentry *dentry; + int err; + + err = vfs_path_lookup(dev_mnt->mnt_root, dev_mnt, + name, LOOKUP_PARENT, &nd); + if (err) + return err; + + mutex_lock_nested(&nd.path.dentry->d_inode->i_mutex, I_MUTEX_PARENT); + dentry = lookup_one_len(nd.last.name, nd.path.dentry, nd.last.len); + if (!IS_ERR(dentry)) { + if (dentry->d_inode) { + if (dentry->d_inode->i_private == &dev_mnt) + err = vfs_rmdir(nd.path.dentry->d_inode, + dentry); + else + err = -EPERM; + } else { + err = -ENOENT; + } + dput(dentry); + } else { + err = PTR_ERR(dentry); + } + + mutex_unlock(&nd.path.dentry->d_inode->i_mutex); + path_put(&nd.path); + return err; +} + +static int delete_path(const char *nodepath) +{ + const char *path; + int err = 0; + + path = kstrdup(nodepath, GFP_KERNEL); + if (!path) + return -ENOMEM; + + mutex_lock(&dirlock); + for (;;) { + char *base; + + base = strrchr(path, '/'); + if (!base) + break; + base[0] = '\0'; + err = dev_rmdir(path); + if (err) + break; + } + mutex_unlock(&dirlock); + + 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 != &dev_mnt) + 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; +} + +int devtmpfs_delete_node(struct device *dev) +{ + const char *tmp = NULL; + const char *nodename; + const struct cred *curr_cred; + struct nameidata nd; + struct dentry *dentry; + struct kstat stat; + int deleted = 1; + int err; + + if (!dev_mnt) + return 0; + + nodename = device_get_devnode(dev, NULL, &tmp); + if (!nodename) + return -ENOMEM; + + curr_cred = override_creds(&init_cred); + err = vfs_path_lookup(dev_mnt->mnt_root, dev_mnt, + nodename, LOOKUP_PARENT, &nd); + if (err) + goto out; + + mutex_lock_nested(&nd.path.dentry->d_inode->i_mutex, I_MUTEX_PARENT); + dentry = lookup_one_len(nd.last.name, nd.path.dentry, nd.last.len); + if (!IS_ERR(dentry)) { + if (dentry->d_inode) { + err = vfs_getattr(nd.path.mnt, dentry, &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 = 0; + newattrs.ia_gid = 0; + 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(nd.path.dentry->d_inode, + dentry); + if (!err || err == -ENOENT) + deleted = 1; + } + } else { + err = -ENOENT; + } + dput(dentry); + } else { + err = PTR_ERR(dentry); + } + mutex_unlock(&nd.path.dentry->d_inode->i_mutex); + + path_put(&nd.path); + if (deleted && strchr(nodename, '/')) + delete_path(nodename); +out: + kfree(tmp); + revert_creds(curr_cred); + 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; + + if (!mount_dev) + return 0; + + if (!dev_mnt) + return 0; + + err = sys_mount("devtmpfs", (char *)mntdir, "devtmpfs", MS_SILENT, NULL); + if (err) + printk(KERN_INFO "devtmpfs: error mounting %i\n", err); + else + printk(KERN_INFO "devtmpfs: mounted\n"); + return err; +} + +/* + * Create devtmpfs instance, driver-core devices will add their device + * nodes here. + */ +int __init devtmpfs_init(void) +{ + int err; + struct vfsmount *mnt; + char options[] = "mode=0755"; + + err = register_filesystem(&dev_fs_type); + if (err) { + printk(KERN_ERR "devtmpfs: unable to register devtmpfs " + "type %i\n", err); + return err; + } + + mnt = kern_mount_data(&dev_fs_type, options); + if (IS_ERR(mnt)) { + err = PTR_ERR(mnt); + printk(KERN_ERR "devtmpfs: unable to create devtmpfs %i\n", err); + unregister_filesystem(&dev_fs_type); + return err; + } + dev_mnt = mnt; + + printk(KERN_INFO "devtmpfs: initialized\n"); + return 0; +} diff --git a/drivers/base/dma-coherent.c b/drivers/base/dma-coherent.c new file mode 100644 index 00000000..f369e279 --- /dev/null +++ b/drivers/base/dma-coherent.c @@ -0,0 +1,177 @@ +/* + * Coherent per-device memory handling. + * Borrowed from i386 + */ +#include <linux/slab.h> +#include <linux/kernel.h> +#include <linux/dma-mapping.h> + +struct dma_coherent_mem { + void *virt_base; + dma_addr_t device_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->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); diff --git a/drivers/base/dma-mapping.c b/drivers/base/dma-mapping.c new file mode 100644 index 00000000..763d59c1 --- /dev/null +++ b/drivers/base/dma-mapping.c @@ -0,0 +1,219 @@ +/* + * 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/gfp.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 diff --git a/drivers/base/driver.c b/drivers/base/driver.c new file mode 100644 index 00000000..b631f7c5 --- /dev/null +++ b/drivers/base/driver.c @@ -0,0 +1,291 @@ +/* + * 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) + 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); + +/** + * driver_add_kobj - add a kobject below the specified driver + * @drv: requesting device driver + * @kobj: kobject to add below this driver + * @fmt: format string that names the kobject + * + * You really don't want to do this, this is only here due to one looney + * iseries driver, go poke those developers if you are annoyed about + * this... + */ +int driver_add_kobj(struct device_driver *drv, struct kobject *kobj, + const char *fmt, ...) +{ + va_list args; + char *name; + int ret; + + va_start(args, fmt); + name = kvasprintf(GFP_KERNEL, fmt, args); + va_end(args); + + if (!name) + return -ENOMEM; + + ret = kobject_add(kobj, &drv->p->kobj, "%s", name); + kfree(name); + return ret; +} +EXPORT_SYMBOL_GPL(driver_add_kobj); + +/** + * get_driver - increment driver reference count. + * @drv: driver. + */ +struct device_driver *get_driver(struct device_driver *drv) +{ + if (drv) { + struct driver_private *priv; + struct kobject *kobj; + + kobj = kobject_get(&drv->p->kobj); + priv = to_driver(kobj); + return priv->driver; + } + return NULL; +} +EXPORT_SYMBOL_GPL(get_driver); + +/** + * put_driver - decrement driver's refcount. + * @drv: driver. + */ +void put_driver(struct device_driver *drv) +{ + kobject_put(&drv->p->kobj); +} +EXPORT_SYMBOL_GPL(put_driver); + +static int driver_add_groups(struct device_driver *drv, + const struct attribute_group **groups) +{ + int error = 0; + int i; + + if (groups) { + for (i = 0; groups[i]; i++) { + error = sysfs_create_group(&drv->p->kobj, groups[i]); + if (error) { + while (--i >= 0) + sysfs_remove_group(&drv->p->kobj, + groups[i]); + break; + } + } + } + return error; +} + +static void driver_remove_groups(struct device_driver *drv, + const struct attribute_group **groups) +{ + int i; + + if (groups) + for (i = 0; groups[i]; i++) + sysfs_remove_group(&drv->p->kobj, groups[i]); +} + +/** + * 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) { + put_driver(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; +} +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. + * + * Note that kset_find_obj increments driver's reference count. + */ +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) { + priv = to_driver(k); + return priv->driver; + } + return NULL; +} +EXPORT_SYMBOL_GPL(driver_find); diff --git a/drivers/base/firmware.c b/drivers/base/firmware.c new file mode 100644 index 00000000..11381555 --- /dev/null +++ b/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; +} diff --git a/drivers/base/firmware_class.c b/drivers/base/firmware_class.c new file mode 100644 index 00000000..3719c94b --- /dev/null +++ b/drivers/base/firmware_class.c @@ -0,0 +1,719 @@ +/* + * firmware_class.c - Multi purpose firmware loading support + * + * Copyright (c) 2003 Manuel Estrada Sainz + * + * Please see Documentation/firmware_class/ for more information. + * + */ + +#include <linux/capability.h> +#include <linux/device.h> +#include <linux/module.h> +#include <linux/init.h> +#include <linux/timer.h> +#include <linux/vmalloc.h> +#include <linux/interrupt.h> +#include <linux/bitops.h> +#include <linux/mutex.h> +#include <linux/kthread.h> +#include <linux/highmem.h> +#include <linux/firmware.h> +#include <linux/slab.h> + +#define to_dev(obj) container_of(obj, struct device, kobj) + +MODULE_AUTHOR("Manuel Estrada Sainz"); +MODULE_DESCRIPTION("Multi purpose firmware loading support"); +MODULE_LICENSE("GPL"); + +/* Builtin firmware support */ + +#ifdef CONFIG_FW_LOADER + +extern struct builtin_fw __start_builtin_fw[]; +extern struct builtin_fw __end_builtin_fw[]; + +static bool fw_get_builtin_firmware(struct firmware *fw, const char *name) +{ + struct builtin_fw *b_fw; + + for (b_fw = __start_builtin_fw; b_fw != __end_builtin_fw; b_fw++) { + if (strcmp(name, b_fw->name) == 0) { + fw->size = b_fw->size; + fw->data = b_fw->data; + return true; + } + } + + return false; +} + +static bool fw_is_builtin_firmware(const struct firmware *fw) +{ + struct builtin_fw *b_fw; + + for (b_fw = __start_builtin_fw; b_fw != __end_builtin_fw; b_fw++) + if (fw->data == b_fw->data) + return true; + + return false; +} + +#else /* Module case - no builtin firmware support */ + +static inline bool fw_get_builtin_firmware(struct firmware *fw, const char *name) +{ + return false; +} + +static inline bool fw_is_builtin_firmware(const struct firmware *fw) +{ + return false; +} +#endif + +enum { + FW_STATUS_LOADING, + FW_STATUS_DONE, + FW_STATUS_ABORT, +}; + +static int loading_timeout = 60; /* In seconds */ + +/* fw_lock could be moved to 'struct firmware_priv' but since it is just + * guarding for corner cases a global lock should be OK */ +static DEFINE_MUTEX(fw_lock); + +struct firmware_priv { + struct completion completion; + struct firmware *fw; + unsigned long status; + struct page **pages; + int nr_pages; + int page_array_size; + struct timer_list timeout; + struct device dev; + bool nowait; + char fw_id[]; +}; + +static struct firmware_priv *to_firmware_priv(struct device *dev) +{ + return container_of(dev, struct firmware_priv, dev); +} + +static void fw_load_abort(struct firmware_priv *fw_priv) +{ + set_bit(FW_STATUS_ABORT, &fw_priv->status); + wmb(); + complete(&fw_priv->completion); +} + +static ssize_t firmware_timeout_show(struct class *class, + struct class_attribute *attr, + char *buf) +{ + return sprintf(buf, "%d\n", loading_timeout); +} + +/** + * firmware_timeout_store - set number of seconds to wait for firmware + * @class: device class pointer + * @attr: device attribute pointer + * @buf: buffer to scan for timeout value + * @count: number of bytes in @buf + * + * Sets the number of seconds to wait for the firmware. Once + * this expires an error will be returned to the driver and no + * firmware will be provided. + * + * Note: zero means 'wait forever'. + **/ +static ssize_t firmware_timeout_store(struct class *class, + struct class_attribute *attr, + const char *buf, size_t count) +{ + loading_timeout = simple_strtol(buf, NULL, 10); + if (loading_timeout < 0) + loading_timeout = 0; + + return count; +} + +static struct class_attribute firmware_class_attrs[] = { + __ATTR(timeout, S_IWUSR | S_IRUGO, + firmware_timeout_show, firmware_timeout_store), + __ATTR_NULL +}; + +static void fw_dev_release(struct device *dev) +{ + struct firmware_priv *fw_priv = to_firmware_priv(dev); + int i; + + for (i = 0; i < fw_priv->nr_pages; i++) + __free_page(fw_priv->pages[i]); + kfree(fw_priv->pages); + kfree(fw_priv); + + module_put(THIS_MODULE); +} + +static int firmware_uevent(struct device *dev, struct kobj_uevent_env *env) +{ + struct firmware_priv *fw_priv = to_firmware_priv(dev); + + if (add_uevent_var(env, "FIRMWARE=%s", fw_priv->fw_id)) + return -ENOMEM; + if (add_uevent_var(env, "TIMEOUT=%i", loading_timeout)) + return -ENOMEM; + if (add_uevent_var(env, "ASYNC=%d", fw_priv->nowait)) + return -ENOMEM; + + return 0; +} + +static struct class firmware_class = { + .name = "firmware", + .class_attrs = firmware_class_attrs, + .dev_uevent = firmware_uevent, + .dev_release = fw_dev_release, +}; + +static ssize_t firmware_loading_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct firmware_priv *fw_priv = to_firmware_priv(dev); + int loading = test_bit(FW_STATUS_LOADING, &fw_priv->status); + + return sprintf(buf, "%d\n", loading); +} + +static void firmware_free_data(const struct firmware *fw) +{ + int i; + vunmap(fw->data); + if (fw->pages) { + for (i = 0; i < PFN_UP(fw->size); i++) + __free_page(fw->pages[i]); + kfree(fw->pages); + } +} + +/* Some architectures don't have PAGE_KERNEL_RO */ +#ifndef PAGE_KERNEL_RO +#define PAGE_KERNEL_RO PAGE_KERNEL +#endif +/** + * firmware_loading_store - set value in the 'loading' control file + * @dev: device pointer + * @attr: device attribute pointer + * @buf: buffer to scan for loading control value + * @count: number of bytes in @buf + * + * The relevant values are: + * + * 1: Start a load, discarding any previous partial load. + * 0: Conclude the load and hand the data to the driver code. + * -1: Conclude the load with an error and discard any written data. + **/ +static ssize_t firmware_loading_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct firmware_priv *fw_priv = to_firmware_priv(dev); + int loading = simple_strtol(buf, NULL, 10); + int i; + + mutex_lock(&fw_lock); + + if (!fw_priv->fw) + goto out; + + switch (loading) { + case 1: + firmware_free_data(fw_priv->fw); + memset(fw_priv->fw, 0, sizeof(struct firmware)); + /* If the pages are not owned by 'struct firmware' */ + for (i = 0; i < fw_priv->nr_pages; i++) + __free_page(fw_priv->pages[i]); + kfree(fw_priv->pages); + fw_priv->pages = NULL; + fw_priv->page_array_size = 0; + fw_priv->nr_pages = 0; + set_bit(FW_STATUS_LOADING, &fw_priv->status); + break; + case 0: + if (test_bit(FW_STATUS_LOADING, &fw_priv->status)) { + vunmap(fw_priv->fw->data); + fw_priv->fw->data = vmap(fw_priv->pages, + fw_priv->nr_pages, + 0, PAGE_KERNEL_RO); + if (!fw_priv->fw->data) { + dev_err(dev, "%s: vmap() failed\n", __func__); + goto err; + } + /* Pages are now owned by 'struct firmware' */ + fw_priv->fw->pages = fw_priv->pages; + fw_priv->pages = NULL; + + fw_priv->page_array_size = 0; + fw_priv->nr_pages = 0; + complete(&fw_priv->completion); + clear_bit(FW_STATUS_LOADING, &fw_priv->status); + break; + } + /* fallthrough */ + default: + dev_err(dev, "%s: unexpected value (%d)\n", __func__, loading); + /* fallthrough */ + case -1: + err: + fw_load_abort(fw_priv); + break; + } +out: + mutex_unlock(&fw_lock); + return count; +} + +static DEVICE_ATTR(loading, 0644, firmware_loading_show, firmware_loading_store); + +static ssize_t firmware_data_read(struct file *filp, struct kobject *kobj, + struct bin_attribute *bin_attr, + char *buffer, loff_t offset, size_t count) +{ + struct device *dev = to_dev(kobj); + struct firmware_priv *fw_priv = to_firmware_priv(dev); + struct firmware *fw; + ssize_t ret_count; + + mutex_lock(&fw_lock); + fw = fw_priv->fw; + if (!fw || test_bit(FW_STATUS_DONE, &fw_priv->status)) { + ret_count = -ENODEV; + goto out; + } + if (offset > fw->size) { + ret_count = 0; + goto out; + } + if (count > fw->size - offset) + count = fw->size - offset; + + ret_count = count; + + while (count) { + void *page_data; + int page_nr = offset >> PAGE_SHIFT; + int page_ofs = offset & (PAGE_SIZE-1); + int page_cnt = min_t(size_t, PAGE_SIZE - page_ofs, count); + + page_data = kmap(fw_priv->pages[page_nr]); + + memcpy(buffer, page_data + page_ofs, page_cnt); + + kunmap(fw_priv->pages[page_nr]); + buffer += page_cnt; + offset += page_cnt; + count -= page_cnt; + } +out: + mutex_unlock(&fw_lock); + return ret_count; +} + +static int fw_realloc_buffer(struct firmware_priv *fw_priv, int min_size) +{ + int pages_needed = ALIGN(min_size, PAGE_SIZE) >> PAGE_SHIFT; + + /* If the array of pages is too small, grow it... */ + if (fw_priv->page_array_size < pages_needed) { + int new_array_size = max(pages_needed, + fw_priv->page_array_size * 2); + struct page **new_pages; + + new_pages = kmalloc(new_array_size * sizeof(void *), + GFP_KERNEL); + if (!new_pages) { + fw_load_abort(fw_priv); + return -ENOMEM; + } + memcpy(new_pages, fw_priv->pages, + fw_priv->page_array_size * sizeof(void *)); + memset(&new_pages[fw_priv->page_array_size], 0, sizeof(void *) * + (new_array_size - fw_priv->page_array_size)); + kfree(fw_priv->pages); + fw_priv->pages = new_pages; + fw_priv->page_array_size = new_array_size; + } + + while (fw_priv->nr_pages < pages_needed) { + fw_priv->pages[fw_priv->nr_pages] = + alloc_page(GFP_KERNEL | __GFP_HIGHMEM); + + if (!fw_priv->pages[fw_priv->nr_pages]) { + fw_load_abort(fw_priv); + return -ENOMEM; + } + fw_priv->nr_pages++; + } + return 0; +} + +/** + * firmware_data_write - write method for firmware + * @filp: open sysfs file + * @kobj: kobject for the device + * @bin_attr: bin_attr structure + * @buffer: buffer being written + * @offset: buffer offset for write in total data store area + * @count: buffer size + * + * Data written to the 'data' attribute will be later handed to + * the driver as a firmware image. + **/ +static ssize_t firmware_data_write(struct file *filp, struct kobject *kobj, + struct bin_attribute *bin_attr, + char *buffer, loff_t offset, size_t count) +{ + struct device *dev = to_dev(kobj); + struct firmware_priv *fw_priv = to_firmware_priv(dev); + struct firmware *fw; + ssize_t retval; + + if (!capable(CAP_SYS_RAWIO)) + return -EPERM; + + mutex_lock(&fw_lock); + fw = fw_priv->fw; + if (!fw || test_bit(FW_STATUS_DONE, &fw_priv->status)) { + retval = -ENODEV; + goto out; + } + retval = fw_realloc_buffer(fw_priv, offset + count); + if (retval) + goto out; + + retval = count; + + while (count) { + void *page_data; + int page_nr = offset >> PAGE_SHIFT; + int page_ofs = offset & (PAGE_SIZE - 1); + int page_cnt = min_t(size_t, PAGE_SIZE - page_ofs, count); + + page_data = kmap(fw_priv->pages[page_nr]); + + memcpy(page_data + page_ofs, buffer, page_cnt); + + kunmap(fw_priv->pages[page_nr]); + buffer += page_cnt; + offset += page_cnt; + count -= page_cnt; + } + + fw->size = max_t(size_t, offset, fw->size); +out: + mutex_unlock(&fw_lock); + return retval; +} + +static struct bin_attribute firmware_attr_data = { + .attr = { .name = "data", .mode = 0644 }, + .size = 0, + .read = firmware_data_read, + .write = firmware_data_write, +}; + +static void firmware_class_timeout(u_long data) +{ + struct firmware_priv *fw_priv = (struct firmware_priv *) data; + + fw_load_abort(fw_priv); +} + +static struct firmware_priv * +fw_create_instance(struct firmware *firmware, const char *fw_name, + struct device *device, bool uevent, bool nowait) +{ + struct firmware_priv *fw_priv; + struct device *f_dev; + int error; + + fw_priv = kzalloc(sizeof(*fw_priv) + strlen(fw_name) + 1 , GFP_KERNEL); + if (!fw_priv) { + dev_err(device, "%s: kmalloc failed\n", __func__); + error = -ENOMEM; + goto err_out; + } + + fw_priv->fw = firmware; + fw_priv->nowait = nowait; + strcpy(fw_priv->fw_id, fw_name); + init_completion(&fw_priv->completion); + setup_timer(&fw_priv->timeout, + firmware_class_timeout, (u_long) fw_priv); + + f_dev = &fw_priv->dev; + + device_initialize(f_dev); + dev_set_name(f_dev, "%s", dev_name(device)); + f_dev->parent = device; + f_dev->class = &firmware_class; + + dev_set_uevent_suppress(f_dev, true); + + /* Need to pin this module until class device is destroyed */ + __module_get(THIS_MODULE); + + error = device_add(f_dev); + if (error) { + dev_err(device, "%s: device_register failed\n", __func__); + goto err_put_dev; + } + + error = device_create_bin_file(f_dev, &firmware_attr_data); + if (error) { + dev_err(device, "%s: sysfs_create_bin_file failed\n", __func__); + goto err_del_dev; + } + + error = device_create_file(f_dev, &dev_attr_loading); + if (error) { + dev_err(device, "%s: device_create_file failed\n", __func__); + goto err_del_bin_attr; + } + + if (uevent) + dev_set_uevent_suppress(f_dev, false); + + return fw_priv; + +err_del_bin_attr: + device_remove_bin_file(f_dev, &firmware_attr_data); +err_del_dev: + device_del(f_dev); +err_put_dev: + put_device(f_dev); +err_out: + return ERR_PTR(error); +} + +static void fw_destroy_instance(struct firmware_priv *fw_priv) +{ + struct device *f_dev = &fw_priv->dev; + + device_remove_file(f_dev, &dev_attr_loading); + device_remove_bin_file(f_dev, &firmware_attr_data); + device_unregister(f_dev); +} + +static int _request_firmware(const struct firmware **firmware_p, + const char *name, struct device *device, + bool uevent, bool nowait) +{ + struct firmware_priv *fw_priv; + struct firmware *firmware; + int retval = 0; + + if (!firmware_p) + return -EINVAL; + + *firmware_p = firmware = kzalloc(sizeof(*firmware), GFP_KERNEL); + if (!firmware) { + dev_err(device, "%s: kmalloc(struct firmware) failed\n", + __func__); + retval = -ENOMEM; + goto out; + } + + if (fw_get_builtin_firmware(firmware, name)) { + dev_dbg(device, "firmware: using built-in firmware %s\n", name); + return 0; + } + + if (WARN_ON(usermodehelper_is_disabled())) { + dev_err(device, "firmware: %s will not be loaded\n", name); + retval = -EBUSY; + goto out; + } + + if (uevent) + dev_dbg(device, "firmware: requesting %s\n", name); + + fw_priv = fw_create_instance(firmware, name, device, uevent, nowait); + if (IS_ERR(fw_priv)) { + retval = PTR_ERR(fw_priv); + goto out; + } + + if (uevent) { + if (loading_timeout > 0) + mod_timer(&fw_priv->timeout, + round_jiffies_up(jiffies + + loading_timeout * HZ)); + + kobject_uevent(&fw_priv->dev.kobj, KOBJ_ADD); + } + + wait_for_completion(&fw_priv->completion); + + set_bit(FW_STATUS_DONE, &fw_priv->status); + del_timer_sync(&fw_priv->timeout); + + mutex_lock(&fw_lock); + if (!fw_priv->fw->size || test_bit(FW_STATUS_ABORT, &fw_priv->status)) + retval = -ENOENT; + fw_priv->fw = NULL; + mutex_unlock(&fw_lock); + + fw_destroy_instance(fw_priv); + +out: + if (retval) { + release_firmware(firmware); + *firmware_p = NULL; + } + + return retval; +} + +/** + * request_firmware: - send firmware request and wait for it + * @firmware_p: pointer to firmware image + * @name: name of firmware file + * @device: device for which firmware is being loaded + * + * @firmware_p will be used to return a firmware image by the name + * of @name for device @device. + * + * Should be called from user context where sleeping is allowed. + * + * @name will be used as $FIRMWARE in the uevent environment and + * should be distinctive enough not to be confused with any other + * firmware image for this or any other device. + **/ +int +request_firmware(const struct firmware **firmware_p, const char *name, + struct device *device) +{ + return _request_firmware(firmware_p, name, device, true, false); +} + +/** + * release_firmware: - release the resource associated with a firmware image + * @fw: firmware resource to release + **/ +void release_firmware(const struct firmware *fw) +{ + if (fw) { + if (!fw_is_builtin_firmware(fw)) + firmware_free_data(fw); + kfree(fw); + } +} + +/* Async support */ +struct firmware_work { + struct work_struct work; + struct module *module; + const char *name; + struct device *device; + void *context; + void (*cont)(const struct firmware *fw, void *context); + bool uevent; +}; + +static int request_firmware_work_func(void *arg) +{ + struct firmware_work *fw_work = arg; + const struct firmware *fw; + int ret; + + if (!arg) { + WARN_ON(1); + return 0; + } + + ret = _request_firmware(&fw, fw_work->name, fw_work->device, + fw_work->uevent, true); + fw_work->cont(fw, fw_work->context); + + module_put(fw_work->module); + kfree(fw_work); + + return ret; +} + +/** + * request_firmware_nowait - asynchronous version of request_firmware + * @module: module requesting the firmware + * @uevent: sends uevent to copy the firmware image if this flag + * is non-zero else the firmware copy must be done manually. + * @name: name of firmware file + * @device: device for which firmware is being loaded + * @gfp: allocation flags + * @context: will be passed over to @cont, and + * @fw may be %NULL if firmware request fails. + * @cont: function will be called asynchronously when the firmware + * request is over. + * + * Asynchronous variant of request_firmware() for user contexts where + * it is not possible to sleep for long time. It can't be called + * in atomic contexts. + **/ +int +request_firmware_nowait( + struct module *module, bool uevent, + const char *name, struct device *device, gfp_t gfp, void *context, + void (*cont)(const struct firmware *fw, void *context)) +{ + struct task_struct *task; + struct firmware_work *fw_work; + + fw_work = kzalloc(sizeof (struct firmware_work), gfp); + if (!fw_work) + return -ENOMEM; + + fw_work->module = module; + fw_work->name = name; + fw_work->device = device; + fw_work->context = context; + fw_work->cont = cont; + fw_work->uevent = uevent; + + if (!try_module_get(module)) { + kfree(fw_work); + return -EFAULT; + } + + task = kthread_run(request_firmware_work_func, fw_work, + "firmware/%s", name); + if (IS_ERR(task)) { + fw_work->cont(NULL, fw_work->context); + module_put(fw_work->module); + kfree(fw_work); + return PTR_ERR(task); + } + + return 0; +} + +static int __init firmware_class_init(void) +{ + return class_register(&firmware_class); +} + +static void __exit firmware_class_exit(void) +{ + class_unregister(&firmware_class); +} + +fs_initcall(firmware_class_init); +module_exit(firmware_class_exit); + +EXPORT_SYMBOL(release_firmware); +EXPORT_SYMBOL(request_firmware); +EXPORT_SYMBOL(request_firmware_nowait); diff --git a/drivers/base/hypervisor.c b/drivers/base/hypervisor.c new file mode 100644 index 00000000..6428cba3 --- /dev/null +++ b/drivers/base/hypervisor.c @@ -0,0 +1,24 @@ +/* + * 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 "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; +} diff --git a/drivers/base/init.c b/drivers/base/init.c new file mode 100644 index 00000000..c8a934e7 --- /dev/null +++ b/drivers/base/init.c @@ -0,0 +1,37 @@ +/* + * 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(); + system_bus_init(); + cpu_dev_init(); + memory_dev_init(); +} diff --git a/drivers/base/iommu.c b/drivers/base/iommu.c new file mode 100644 index 00000000..6e6b6a11 --- /dev/null +++ b/drivers/base/iommu.c @@ -0,0 +1,124 @@ +/* + * Copyright (C) 2007-2008 Advanced Micro Devices, Inc. + * Author: Joerg Roedel <joerg.roedel@amd.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. + * + * 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, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + */ + +#include <linux/bug.h> +#include <linux/types.h> +#include <linux/module.h> +#include <linux/slab.h> +#include <linux/errno.h> +#include <linux/iommu.h> + +static struct iommu_ops *iommu_ops; + +void register_iommu(struct iommu_ops *ops) +{ + if (iommu_ops) + BUG(); + + iommu_ops = ops; +} + +bool iommu_found(void) +{ + return iommu_ops != NULL; +} +EXPORT_SYMBOL_GPL(iommu_found); + +struct iommu_domain *iommu_domain_alloc(void) +{ + struct iommu_domain *domain; + int ret; + + domain = kmalloc(sizeof(*domain), GFP_KERNEL); + if (!domain) + return NULL; + + ret = iommu_ops->domain_init(domain); + if (ret) + goto out_free; + + return domain; + +out_free: + kfree(domain); + + return NULL; +} +EXPORT_SYMBOL_GPL(iommu_domain_alloc); + +void iommu_domain_free(struct iommu_domain *domain) +{ + iommu_ops->domain_destroy(domain); + kfree(domain); +} +EXPORT_SYMBOL_GPL(iommu_domain_free); + +int iommu_attach_device(struct iommu_domain *domain, struct device *dev) +{ + return iommu_ops->attach_dev(domain, dev); +} +EXPORT_SYMBOL_GPL(iommu_attach_device); + +void iommu_detach_device(struct iommu_domain *domain, struct device *dev) +{ + iommu_ops->detach_dev(domain, dev); +} +EXPORT_SYMBOL_GPL(iommu_detach_device); + +phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain, + unsigned long iova) +{ + return iommu_ops->iova_to_phys(domain, iova); +} +EXPORT_SYMBOL_GPL(iommu_iova_to_phys); + +int iommu_domain_has_cap(struct iommu_domain *domain, + unsigned long cap) +{ + return iommu_ops->domain_has_cap(domain, cap); +} +EXPORT_SYMBOL_GPL(iommu_domain_has_cap); + +int iommu_map(struct iommu_domain *domain, unsigned long iova, + phys_addr_t paddr, int gfp_order, int prot) +{ + unsigned long invalid_mask; + size_t size; + + size = 0x1000UL << gfp_order; + invalid_mask = size - 1; + + BUG_ON((iova | paddr) & invalid_mask); + + return iommu_ops->map(domain, iova, paddr, gfp_order, prot); +} +EXPORT_SYMBOL_GPL(iommu_map); + +int iommu_unmap(struct iommu_domain *domain, unsigned long iova, int gfp_order) +{ + unsigned long invalid_mask; + size_t size; + + size = 0x1000UL << gfp_order; + invalid_mask = size - 1; + + BUG_ON(iova & invalid_mask); + + return iommu_ops->unmap(domain, iova, gfp_order); +} +EXPORT_SYMBOL_GPL(iommu_unmap); diff --git a/drivers/base/isa.c b/drivers/base/isa.c new file mode 100644 index 00000000..91dba65d --- /dev/null +++ b/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); diff --git a/drivers/base/map.c b/drivers/base/map.c new file mode 100644 index 00000000..e87017f3 --- /dev/null +++ b/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; +} diff --git a/drivers/base/memory.c b/drivers/base/memory.c new file mode 100644 index 00000000..45d7c8fc --- /dev/null +++ b/drivers/base/memory.c @@ -0,0 +1,675 @@ +/* + * drivers/base/memory.c - basic Memory class support + * + * Written by Matt Tolentino <matthew.e.tolentino@intel.com> + * Dave Hansen <haveblue@us.ibm.com> + * + * This file provides the necessary infrastructure to represent + * a SPARSEMEM-memory-model system's physical memory in /sysfs. + * All arch-independent code that assumes MEMORY_HOTPLUG requires + * SPARSEMEM should be contained here, or in mm/memory_hotplug.c. + */ + +#include <linux/sysdev.h> +#include <linux/module.h> +#include <linux/init.h> +#include <linux/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 <asm/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 sysdev_class memory_sysdev_class = { + .name = MEMORY_CLASS_NAME, +}; + +static const char *memory_uevent_name(struct kset *kset, struct kobject *kobj) +{ + return MEMORY_CLASS_NAME; +} + +static int memory_uevent(struct kset *kset, struct kobject *obj, + struct kobj_uevent_env *env) +{ + int retval = 0; + + return retval; +} + +static const struct kset_uevent_ops memory_uevent_ops = { + .name = memory_uevent_name, + .uevent = memory_uevent, +}; + +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); + +/* + * register_memory - Setup a sysfs device for a memory block + */ +static +int register_memory(struct memory_block *memory) +{ + int error; + + memory->sysdev.cls = &memory_sysdev_class; + memory->sysdev.id = memory->start_section_nr / sections_per_block; + + error = sysdev_register(&memory->sysdev); + return error; +} + +static void +unregister_memory(struct memory_block *memory) +{ + BUG_ON(memory->sysdev.cls != &memory_sysdev_class); + + /* drop the ref. we got in remove_memory_block() */ + kobject_put(&memory->sysdev.kobj); + sysdev_unregister(&memory->sysdev); +} + +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 sys_device *dev, + struct sysdev_attribute *attr, char *buf) +{ + struct memory_block *mem = + container_of(dev, struct memory_block, sysdev); + 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 sys_device *dev, + struct sysdev_attribute *attr, char *buf) +{ + struct memory_block *mem = + container_of(dev, struct memory_block, sysdev); + 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 sys_device *dev, + struct sysdev_attribute *attr, char *buf) +{ + unsigned long i, pfn; + int ret = 1; + struct memory_block *mem = + container_of(dev, struct memory_block, sysdev); + + for (i = 0; i < sections_per_block; i++) { + 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 sys_device *dev, + struct sysdev_attribute *attr, char *buf) +{ + struct memory_block *mem = + container_of(dev, struct memory_block, sysdev); + ssize_t len = 0; + + /* + * We can probably put these states in a nice little array + * so that they're not open-coded + */ + switch (mem->state) { + case MEM_ONLINE: + len = sprintf(buf, "online\n"); + break; + case MEM_OFFLINE: + len = sprintf(buf, "offline\n"); + break; + case MEM_GOING_OFFLINE: + len = sprintf(buf, "going-offline\n"); + break; + default: + len = sprintf(buf, "ERROR-UNKNOWN-%ld\n", + mem->state); + WARN_ON(1); + break; + } + + return len; +} + +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); +} + +/* + * 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 i; + unsigned long start_pfn, start_paddr; + 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); + + /* + * The probe routines leave the pages reserved, just + * as the bootmem code does. Make sure they're still + * that way. + */ + if (action == MEM_ONLINE) { + for (i = 0; i < nr_pages; i++) { + if (PageReserved(first_page+i)) + continue; + + printk(KERN_WARNING "section number %ld page number %d " + "not reserved, was it already online?\n", + phys_index, i); + return -EBUSY; + } + } + + switch (action) { + case MEM_ONLINE: + start_pfn = page_to_pfn(first_page); + ret = online_pages(start_pfn, nr_pages); + break; + case MEM_OFFLINE: + start_paddr = page_to_pfn(first_page) << PAGE_SHIFT; + ret = remove_memory(start_paddr, + nr_pages << PAGE_SHIFT); + 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 ret = 0; + + mutex_lock(&mem->state_mutex); + + 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); + + if (ret) + mem->state = from_state_req; + else + mem->state = to_state; + +out: + mutex_unlock(&mem->state_mutex); + return ret; +} + +static ssize_t +store_mem_state(struct sys_device *dev, + struct sysdev_attribute *attr, const char *buf, size_t count) +{ + struct memory_block *mem; + int ret = -EINVAL; + + mem = container_of(dev, struct memory_block, sysdev); + + if (!strncmp(buf, "online", min((int)count, 6))) + ret = memory_block_change_state(mem, MEM_ONLINE, MEM_OFFLINE); + else if(!strncmp(buf, "offline", min((int)count, 7))) + ret = memory_block_change_state(mem, MEM_OFFLINE, MEM_ONLINE); + + if (ret) + return ret; + return count; +} + +/* + * phys_device is a bad name for this. What I really want + * is a way to differentiate between memory ranges that + * are part of physical devices that constitute + * a complete removable unit or fru. + * i.e. do these ranges belong to the same physical device, + * s.t. if I offline all of these sections I can then + * remove the physical device? + */ +static ssize_t show_phys_device(struct sys_device *dev, + struct sysdev_attribute *attr, char *buf) +{ + struct memory_block *mem = + container_of(dev, struct memory_block, sysdev); + return sprintf(buf, "%d\n", mem->phys_device); +} + +static SYSDEV_ATTR(phys_index, 0444, show_mem_start_phys_index, NULL); +static SYSDEV_ATTR(end_phys_index, 0444, show_mem_end_phys_index, NULL); +static SYSDEV_ATTR(state, 0644, show_mem_state, store_mem_state); +static SYSDEV_ATTR(phys_device, 0444, show_phys_device, NULL); +static SYSDEV_ATTR(removable, 0444, show_mem_removable, NULL); + +#define mem_create_simple_file(mem, attr_name) \ + sysdev_create_file(&mem->sysdev, &attr_##attr_name) +#define mem_remove_simple_file(mem, attr_name) \ + sysdev_remove_file(&mem->sysdev, &attr_##attr_name) + +/* + * Block size attribute stuff + */ +static ssize_t +print_block_size(struct sysdev_class *class, struct sysdev_class_attribute *attr, + char *buf) +{ + return sprintf(buf, "%lx\n", get_memory_block_size()); +} + +static SYSDEV_CLASS_ATTR(block_size_bytes, 0444, print_block_size, NULL); + +static int block_size_init(void) +{ + return sysfs_create_file(&memory_sysdev_class.kset.kobj, + &attr_block_size_bytes.attr); +} + +/* + * Some architectures will have custom drivers to do this, and + * will not need to do it from userspace. The fake hot-add code + * as well as ppc64 will do all of their discovery in userspace + * and will require this interface. + */ +#ifdef CONFIG_ARCH_MEMORY_PROBE +static ssize_t +memory_probe_store(struct class *class, struct class_attribute *attr, + const char *buf, size_t count) +{ + u64 phys_addr; + int nid; + int i, ret; + + phys_addr = simple_strtoull(buf, NULL, 0); + + 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 CLASS_ATTR(probe, S_IWUSR, NULL, memory_probe_store); + +static int memory_probe_init(void) +{ + return sysfs_create_file(&memory_sysdev_class.kset.kobj, + &class_attr_probe.attr); +} +#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 class *class, + struct class_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 class *class, + struct class_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 CLASS_ATTR(soft_offline_page, 0644, NULL, store_soft_offline_page); +static CLASS_ATTR(hard_offline_page, 0644, NULL, store_hard_offline_page); + +static __init int memory_fail_init(void) +{ + int err; + + err = sysfs_create_file(&memory_sysdev_class.kset.kobj, + &class_attr_soft_offline_page.attr); + if (!err) + err = sysfs_create_file(&memory_sysdev_class.kset.kobj, + &class_attr_hard_offline_page.attr); + 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; +} + +struct memory_block *find_memory_block_hinted(struct mem_section *section, + struct memory_block *hint) +{ + struct kobject *kobj; + struct sys_device *sysdev; + struct memory_block *mem; + char name[sizeof(MEMORY_CLASS_NAME) + 9 + 1]; + int block_id = base_memory_block_id(__section_nr(section)); + + kobj = hint ? &hint->sysdev.kobj : NULL; + + /* + * This only works because we know that section == sysdev->id + * slightly redundant with sysdev_register() + */ + sprintf(&name[0], "%s%d", MEMORY_CLASS_NAME, block_id); + + kobj = kset_find_obj_hinted(&memory_sysdev_class.kset, name, kobj); + if (!kobj) + return NULL; + + sysdev = container_of(kobj, struct sys_device, kobj); + mem = container_of(sysdev, struct memory_block, sysdev); + + return mem; +} + +/* + * For now, we have a linear search to go find the appropriate + * memory_block corresponding to a particular phys_index. If + * this gets to be a real problem, we can always use a radix + * tree or something here. + * + * This could be made generic for all sysdev classes. + */ +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, + unsigned long state, enum mem_add_context context) +{ + struct memory_block *mem; + int ret = 0; + + mutex_lock(&mem_sysfs_mutex); + + mem = find_memory_block(section); + if (mem) { + mem->section_count++; + kobject_put(&mem->sysdev.kobj); + } else + ret = init_memory_block(&mem, section, state); + + 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; +} + +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); + kfree(mem); + } else + kobject_put(&mem->sysdev.kobj); + + mutex_unlock(&mem_sysfs_mutex); + return 0; +} + +/* + * 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, MEM_OFFLINE, HOTPLUG); +} + +int unregister_memory_section(struct mem_section *section) +{ + if (!present_section(section)) + return -EINVAL; + + return remove_memory_block(0, section, 0); +} + +/* + * Initialize the sysfs support for memory devices... + */ +int __init memory_dev_init(void) +{ + unsigned int i; + int ret; + int err; + unsigned long block_sz; + + memory_sysdev_class.kset.uevent_ops = &memory_uevent_ops; + ret = sysdev_class_register(&memory_sysdev_class); + 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; + err = add_memory_section(0, __nr_to_section(i), 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; +} diff --git a/drivers/base/module.c b/drivers/base/module.c new file mode 100644 index 00000000..db930d3e --- /dev/null +++ b/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); + } + } +} diff --git a/drivers/base/node.c b/drivers/base/node.c new file mode 100644 index 00000000..5693ecee --- /dev/null +++ b/drivers/base/node.c @@ -0,0 +1,654 @@ +/* + * drivers/base/node.c - basic Node class support + */ + +#include <linux/sysdev.h> +#include <linux/module.h> +#include <linux/init.h> +#include <linux/mm.h> +#include <linux/memory.h> +#include <linux/vmstat.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 sysdev_class_attribute *node_state_attrs[]; + +static struct sysdev_class node_class = { + .name = "node", + .attrs = node_state_attrs, +}; + + +static ssize_t node_read_cpumap(struct sys_device *dev, int type, char *buf) +{ + struct node *node_dev = to_node(dev); + const struct cpumask *mask = cpumask_of_node(node_dev->sysdev.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 sys_device *dev, + struct sysdev_attribute *attr, char *buf) +{ + return node_read_cpumap(dev, 0, buf); +} +static inline ssize_t node_read_cpulist(struct sys_device *dev, + struct sysdev_attribute *attr, char *buf) +{ + return node_read_cpumap(dev, 1, buf); +} + +static SYSDEV_ATTR(cpumap, S_IRUGO, node_read_cpumask, NULL); +static SYSDEV_ATTR(cpulist, S_IRUGO, node_read_cpulist, NULL); + +#define K(x) ((x) << (PAGE_SHIFT - 10)) +static ssize_t node_read_meminfo(struct sys_device * dev, + struct sysdev_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 SYSDEV_ATTR(meminfo, S_IRUGO, node_read_meminfo, NULL); + +static ssize_t node_read_numastat(struct sys_device * dev, + struct sysdev_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 SYSDEV_ATTR(numastat, S_IRUGO, node_read_numastat, NULL); + +static ssize_t node_read_vmstat(struct sys_device *dev, + struct sysdev_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 SYSDEV_ATTR(vmstat, S_IRUGO, node_read_vmstat, NULL); + +static ssize_t node_read_distance(struct sys_device * dev, + struct sysdev_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 SYSDEV_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->sysdev.id, N_HIGH_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 + + +/* + * register_node - Setup a sysfs device for a node. + * @num - Node number to use when creating the device. + * + * Initialize and register the node device. + */ +int register_node(struct node *node, int num, struct node *parent) +{ + int error; + + node->sysdev.id = num; + node->sysdev.cls = &node_class; + error = sysdev_register(&node->sysdev); + + if (!error){ + sysdev_create_file(&node->sysdev, &attr_cpumap); + sysdev_create_file(&node->sysdev, &attr_cpulist); + sysdev_create_file(&node->sysdev, &attr_meminfo); + sysdev_create_file(&node->sysdev, &attr_numastat); + sysdev_create_file(&node->sysdev, &attr_distance); + sysdev_create_file(&node->sysdev, &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) +{ + sysdev_remove_file(&node->sysdev, &attr_cpumap); + sysdev_remove_file(&node->sysdev, &attr_cpulist); + sysdev_remove_file(&node->sysdev, &attr_meminfo); + sysdev_remove_file(&node->sysdev, &attr_numastat); + sysdev_remove_file(&node->sysdev, &attr_distance); + sysdev_remove_file(&node->sysdev, &attr_vmstat); + + scan_unevictable_unregister_node(node); + hugetlb_unregister_node(node); /* no-op, if memoryless node */ + + sysdev_unregister(&node->sysdev); +} + +struct node node_devices[MAX_NUMNODES]; + +/* + * register cpu under node + */ +int register_cpu_under_node(unsigned int cpu, unsigned int nid) +{ + int ret; + struct sys_device *obj; + + if (!node_online(nid)) + return 0; + + obj = get_cpu_sysdev(cpu); + if (!obj) + return 0; + + ret = sysfs_create_link(&node_devices[nid].sysdev.kobj, + &obj->kobj, + kobject_name(&obj->kobj)); + if (ret) + return ret; + + return sysfs_create_link(&obj->kobj, + &node_devices[nid].sysdev.kobj, + kobject_name(&node_devices[nid].sysdev.kobj)); +} + +int unregister_cpu_under_node(unsigned int cpu, unsigned int nid) +{ + struct sys_device *obj; + + if (!node_online(nid)) + return 0; + + obj = get_cpu_sysdev(cpu); + if (!obj) + return 0; + + sysfs_remove_link(&node_devices[nid].sysdev.kobj, + kobject_name(&obj->kobj)); + sysfs_remove_link(&obj->kobj, + kobject_name(&node_devices[nid].sysdev.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].sysdev.kobj, + &mem_blk->sysdev.kobj, + kobject_name(&mem_blk->sysdev.kobj)); + if (ret) + return ret; + + return sysfs_create_link_nowarn(&mem_blk->sysdev.kobj, + &node_devices[nid].sysdev.kobj, + kobject_name(&node_devices[nid].sysdev.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].sysdev.kobj, + kobject_name(&mem_blk->sysdev.kobj)); + sysfs_remove_link(&mem_blk->sysdev.kobj, + kobject_name(&node_devices[nid].sysdev.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); + 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->sysdev.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]; + + 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 states attributes + */ + +static ssize_t print_nodes_state(enum node_states state, char *buf) +{ + int n; + + n = nodelist_scnprintf(buf, PAGE_SIZE, node_states[state]); + if (n > 0 && PAGE_SIZE > n + 1) { + *(buf + n++) = '\n'; + *(buf + n++) = '\0'; + } + return n; +} + +struct node_attr { + struct sysdev_class_attribute attr; + enum node_states state; +}; + +static ssize_t show_node_state(struct sysdev_class *class, + struct sysdev_class_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) \ + { _SYSDEV_CLASS_ATTR(name, 0444, show_node_state, NULL), state } + +static struct node_attr node_state_attr[] = { + _NODE_ATTR(possible, N_POSSIBLE), + _NODE_ATTR(online, N_ONLINE), + _NODE_ATTR(has_normal_memory, N_NORMAL_MEMORY), + _NODE_ATTR(has_cpu, N_CPU), +#ifdef CONFIG_HIGHMEM + _NODE_ATTR(has_high_memory, N_HIGH_MEMORY), +#endif +}; + +static struct sysdev_class_attribute *node_state_attrs[] = { + &node_state_attr[0].attr, + &node_state_attr[1].attr, + &node_state_attr[2].attr, + &node_state_attr[3].attr, +#ifdef CONFIG_HIGHMEM + &node_state_attr[4].attr, +#endif + 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 = sysdev_class_register(&node_class); + if (!ret) { + hotplug_memory_notifier(node_memory_callback, + NODE_CALLBACK_PRI); + } + + /* + * 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); diff --git a/drivers/base/platform.c b/drivers/base/platform.c new file mode 100644 index 00000000..6040717b --- /dev/null +++ b/drivers/base/platform.c @@ -0,0 +1,1239 @@ +/* + * platform.c - platform 'pseudo' bus for legacy devices + * + * Copyright (c) 2002-3 Patrick Mochel + * Copyright (c) 2002-3 Open Source Development Labs + * + * This file is released under the GPLv2 + * + * Please see Documentation/driver-model/platform.txt for more + * information. + */ + +#include <linux/string.h> +#include <linux/platform_device.h> +#include <linux/of_device.h> +#include <linux/module.h> +#include <linux/init.h> +#include <linux/dma-mapping.h> +#include <linux/bootmem.h> +#include <linux/err.h> +#include <linux/slab.h> +#include <linux/pm_runtime.h> + +#include "base.h" + +#define to_platform_driver(drv) (container_of((drv), struct platform_driver, \ + driver)) + +struct device platform_bus = { + .init_name = "platform", +}; +EXPORT_SYMBOL_GPL(platform_bus); + +/** + * platform_get_resource - get a resource for a device + * @dev: platform device + * @type: resource type + * @num: resource index + */ +struct resource *platform_get_resource(struct platform_device *dev, + unsigned int type, unsigned int num) +{ + int i; + + for (i = 0; i < dev->num_resources; i++) { + struct resource *r = &dev->resource[i]; + + if (type == resource_type(r) && num-- == 0) + return r; + } + return NULL; +} +EXPORT_SYMBOL_GPL(platform_get_resource); + +/** + * platform_get_irq - get an IRQ for a device + * @dev: platform device + * @num: IRQ number index + */ +int platform_get_irq(struct platform_device *dev, unsigned int num) +{ + struct resource *r = platform_get_resource(dev, IORESOURCE_IRQ, num); + + return r ? r->start : -ENXIO; +} +EXPORT_SYMBOL_GPL(platform_get_irq); + +/** + * platform_get_resource_byname - get a resource for a device by name + * @dev: platform device + * @type: resource type + * @name: resource name + */ +struct resource *platform_get_resource_byname(struct platform_device *dev, + unsigned int type, + const char *name) +{ + int i; + + for (i = 0; i < dev->num_resources; i++) { + struct resource *r = &dev->resource[i]; + + if (type == resource_type(r) && !strcmp(r->name, name)) + return r; + } + return NULL; +} +EXPORT_SYMBOL_GPL(platform_get_resource_byname); + +/** + * platform_get_irq - get an IRQ for a device + * @dev: platform device + * @name: IRQ name + */ +int platform_get_irq_byname(struct platform_device *dev, const char *name) +{ + struct resource *r = platform_get_resource_byname(dev, IORESOURCE_IRQ, + name); + + return r ? r->start : -ENXIO; +} +EXPORT_SYMBOL_GPL(platform_get_irq_byname); + +/** + * platform_add_devices - add a numbers of platform devices + * @devs: array of platform devices to add + * @num: number of platform devices in array + */ +int platform_add_devices(struct platform_device **devs, int num) +{ + int i, ret = 0; + + for (i = 0; i < num; i++) { + ret = platform_device_register(devs[i]); + if (ret) { + while (--i >= 0) + platform_device_unregister(devs[i]); + break; + } + } + + return ret; +} +EXPORT_SYMBOL_GPL(platform_add_devices); + +struct platform_object { + struct platform_device pdev; + char name[1]; +}; + +/** + * platform_device_put - destroy a platform device + * @pdev: platform device to free + * + * Free all memory associated with a platform device. This function must + * _only_ be externally called in error cases. All other usage is a bug. + */ +void platform_device_put(struct platform_device *pdev) +{ + if (pdev) + put_device(&pdev->dev); +} +EXPORT_SYMBOL_GPL(platform_device_put); + +static void platform_device_release(struct device *dev) +{ + struct platform_object *pa = container_of(dev, struct platform_object, + pdev.dev); + + of_device_node_put(&pa->pdev.dev); + kfree(pa->pdev.dev.platform_data); + kfree(pa->pdev.mfd_cell); + kfree(pa->pdev.resource); + kfree(pa); +} + +/** + * platform_device_alloc - create a platform device + * @name: base name of the device we're adding + * @id: instance id + * + * Create a platform device object which can have other objects attached + * to it, and which will have attached objects freed when it is released. + */ +struct platform_device *platform_device_alloc(const char *name, int id) +{ + struct platform_object *pa; + + pa = kzalloc(sizeof(struct platform_object) + strlen(name), GFP_KERNEL); + if (pa) { + strcpy(pa->name, name); + pa->pdev.name = pa->name; + pa->pdev.id = id; + device_initialize(&pa->pdev.dev); + pa->pdev.dev.release = platform_device_release; + } + + return pa ? &pa->pdev : NULL; +} +EXPORT_SYMBOL_GPL(platform_device_alloc); + +/** + * platform_device_add_resources - add resources to a platform device + * @pdev: platform device allocated by platform_device_alloc to add resources to + * @res: set of resources that needs to be allocated for the device + * @num: number of resources + * + * Add a copy of the resources to the platform device. The memory + * associated with the resources will be freed when the platform device is + * released. + */ +int platform_device_add_resources(struct platform_device *pdev, + const struct resource *res, unsigned int num) +{ + struct resource *r = NULL; + + if (res) { + r = kmemdup(res, sizeof(struct resource) * num, GFP_KERNEL); + if (!r) + return -ENOMEM; + } + + kfree(pdev->resource); + pdev->resource = r; + pdev->num_resources = num; + return 0; +} +EXPORT_SYMBOL_GPL(platform_device_add_resources); + +/** + * platform_device_add_data - add platform-specific data to a platform device + * @pdev: platform device allocated by platform_device_alloc to add resources to + * @data: platform specific data for this platform device + * @size: size of platform specific data + * + * Add a copy of platform specific data to the platform device's + * platform_data pointer. The memory associated with the platform data + * will be freed when the platform device is released. + */ +int platform_device_add_data(struct platform_device *pdev, const void *data, + size_t size) +{ + void *d = NULL; + + if (data) { + d = kmemdup(data, size, GFP_KERNEL); + if (!d) + return -ENOMEM; + } + + kfree(pdev->dev.platform_data); + pdev->dev.platform_data = d; + return 0; +} +EXPORT_SYMBOL_GPL(platform_device_add_data); + +/** + * platform_device_add - add a platform device to device hierarchy + * @pdev: platform device we're adding + * + * This is part 2 of platform_device_register(), though may be called + * separately _iff_ pdev was allocated by platform_device_alloc(). + */ +int platform_device_add(struct platform_device *pdev) +{ + int i, ret = 0; + + if (!pdev) + return -EINVAL; + + if (!pdev->dev.parent) + pdev->dev.parent = &platform_bus; + + pdev->dev.bus = &platform_bus_type; + + if (pdev->id != -1) + dev_set_name(&pdev->dev, "%s.%d", pdev->name, pdev->id); + else + dev_set_name(&pdev->dev, "%s", pdev->name); + + for (i = 0; i < pdev->num_resources; i++) { + struct resource *p, *r = &pdev->resource[i]; + + if (r->name == NULL) + r->name = dev_name(&pdev->dev); + + p = r->parent; + if (!p) { + if (resource_type(r) == IORESOURCE_MEM) + p = &iomem_resource; + else if (resource_type(r) == IORESOURCE_IO) + p = &ioport_resource; + } + + if (p && insert_resource(p, r)) { + printk(KERN_ERR + "%s: failed to claim resource %d\n", + dev_name(&pdev->dev), i); + ret = -EBUSY; + goto failed; + } + } + + pr_debug("Registering platform device '%s'. Parent at %s\n", + dev_name(&pdev->dev), dev_name(pdev->dev.parent)); + + ret = device_add(&pdev->dev); + if (ret == 0) + return ret; + + failed: + while (--i >= 0) { + struct resource *r = &pdev->resource[i]; + unsigned long type = resource_type(r); + + if (type == IORESOURCE_MEM || type == IORESOURCE_IO) + release_resource(r); + } + + return ret; +} +EXPORT_SYMBOL_GPL(platform_device_add); + +/** + * platform_device_del - remove a platform-level device + * @pdev: platform device we're removing + * + * Note that this function will also release all memory- and port-based + * resources owned by the device (@dev->resource). This function must + * _only_ be externally called in error cases. All other usage is a bug. + */ +void platform_device_del(struct platform_device *pdev) +{ + int i; + + if (pdev) { + device_del(&pdev->dev); + + for (i = 0; i < pdev->num_resources; i++) { + struct resource *r = &pdev->resource[i]; + unsigned long type = resource_type(r); + + if (type == IORESOURCE_MEM || type == IORESOURCE_IO) + release_resource(r); + } + } +} +EXPORT_SYMBOL_GPL(platform_device_del); + +/** + * platform_device_register - add a platform-level device + * @pdev: platform device we're adding + */ +int platform_device_register(struct platform_device *pdev) +{ + device_initialize(&pdev->dev); + return platform_device_add(pdev); +} +EXPORT_SYMBOL_GPL(platform_device_register); + +/** + * platform_device_unregister - unregister a platform-level device + * @pdev: platform device we're unregistering + * + * Unregistration is done in 2 steps. First we release all resources + * and remove it from the subsystem, then we drop reference count by + * calling platform_device_put(). + */ +void platform_device_unregister(struct platform_device *pdev) +{ + platform_device_del(pdev); + platform_device_put(pdev); +} +EXPORT_SYMBOL_GPL(platform_device_unregister); + +/** + * platform_device_register_resndata - add a platform-level device with + * resources and platform-specific data + * + * @parent: parent device for the device we're adding + * @name: base name of the device we're adding + * @id: instance id + * @res: set of resources that needs to be allocated for the device + * @num: number of resources + * @data: platform specific data for this platform device + * @size: size of platform specific data + * + * Returns &struct platform_device pointer on success, or ERR_PTR() on error. + */ +struct platform_device *platform_device_register_resndata( + struct device *parent, + const char *name, int id, + const struct resource *res, unsigned int num, + const void *data, size_t size) +{ + int ret = -ENOMEM; + struct platform_device *pdev; + + pdev = platform_device_alloc(name, id); + if (!pdev) + goto err; + + pdev->dev.parent = parent; + + ret = platform_device_add_resources(pdev, res, num); + if (ret) + goto err; + + ret = platform_device_add_data(pdev, data, size); + if (ret) + goto err; + + ret = platform_device_add(pdev); + if (ret) { +err: + platform_device_put(pdev); + return ERR_PTR(ret); + } + + return pdev; +} +EXPORT_SYMBOL_GPL(platform_device_register_resndata); + +static int platform_drv_probe(struct device *_dev) +{ + struct platform_driver *drv = to_platform_driver(_dev->driver); + struct platform_device *dev = to_platform_device(_dev); + + return drv->probe(dev); +} + +static int platform_drv_probe_fail(struct device *_dev) +{ + return -ENXIO; +} + +static int platform_drv_remove(struct device *_dev) +{ + struct platform_driver *drv = to_platform_driver(_dev->driver); + struct platform_device *dev = to_platform_device(_dev); + + return drv->remove(dev); +} + +static void platform_drv_shutdown(struct device *_dev) +{ + struct platform_driver *drv = to_platform_driver(_dev->driver); + struct platform_device *dev = to_platform_device(_dev); + + drv->shutdown(dev); +} + +/** + * platform_driver_register - register a driver for platform-level devices + * @drv: platform driver structure + */ +int platform_driver_register(struct platform_driver *drv) +{ + drv->driver.bus = &platform_bus_type; + if (drv->probe) + drv->driver.probe = platform_drv_probe; + if (drv->remove) + drv->driver.remove = platform_drv_remove; + if (drv->shutdown) + drv->driver.shutdown = platform_drv_shutdown; + + return driver_register(&drv->driver); +} +EXPORT_SYMBOL_GPL(platform_driver_register); + +/** + * platform_driver_unregister - unregister a driver for platform-level devices + * @drv: platform driver structure + */ +void platform_driver_unregister(struct platform_driver *drv) +{ + driver_unregister(&drv->driver); +} +EXPORT_SYMBOL_GPL(platform_driver_unregister); + +/** + * platform_driver_probe - register driver for non-hotpluggable device + * @drv: platform driver structure + * @probe: the driver probe routine, probably from an __init section + * + * Use this instead of platform_driver_register() when you know the device + * is not hotpluggable and has already been registered, and you want to + * remove its run-once probe() infrastructure from memory after the driver + * has bound to the device. + * + * One typical use for this would be with drivers for controllers integrated + * into system-on-chip processors, where the controller devices have been + * configured as part of board setup. + * + * Returns zero if the driver registered and bound to a device, else returns + * a negative error code and with the driver not registered. + */ +int __init_or_module platform_driver_probe(struct platform_driver *drv, + int (*probe)(struct platform_device *)) +{ + int retval, code; + + /* make sure driver won't have bind/unbind attributes */ + drv->driver.suppress_bind_attrs = true; + + /* temporary section violation during probe() */ + drv->probe = probe; + retval = code = platform_driver_register(drv); + + /* + * Fixup that section violation, being paranoid about code scanning + * the list of drivers in order to probe new devices. Check to see + * if the probe was successful, and make sure any forced probes of + * new devices fail. + */ + spin_lock(&drv->driver.bus->p->klist_drivers.k_lock); + drv->probe = NULL; + if (code == 0 && list_empty(&drv->driver.p->klist_devices.k_list)) + retval = -ENODEV; + drv->driver.probe = platform_drv_probe_fail; + spin_unlock(&drv->driver.bus->p->klist_drivers.k_lock); + + if (code != retval) + platform_driver_unregister(drv); + return retval; +} +EXPORT_SYMBOL_GPL(platform_driver_probe); + +/** + * platform_create_bundle - register driver and create corresponding device + * @driver: platform driver structure + * @probe: the driver probe routine, probably from an __init section + * @res: set of resources that needs to be allocated for the device + * @n_res: number of resources + * @data: platform specific data for this platform device + * @size: size of platform specific data + * + * Use this in legacy-style modules that probe hardware directly and + * register a single platform device and corresponding platform driver. + * + * Returns &struct platform_device pointer on success, or ERR_PTR() on error. + */ +struct platform_device * __init_or_module platform_create_bundle( + struct platform_driver *driver, + int (*probe)(struct platform_device *), + struct resource *res, unsigned int n_res, + const void *data, size_t size) +{ + struct platform_device *pdev; + int error; + + pdev = platform_device_alloc(driver->driver.name, -1); + if (!pdev) { + error = -ENOMEM; + goto err_out; + } + + error = platform_device_add_resources(pdev, res, n_res); + if (error) + goto err_pdev_put; + + error = platform_device_add_data(pdev, data, size); + if (error) + goto err_pdev_put; + + error = platform_device_add(pdev); + if (error) + goto err_pdev_put; + + error = platform_driver_probe(driver, probe); + if (error) + goto err_pdev_del; + + return pdev; + +err_pdev_del: + platform_device_del(pdev); +err_pdev_put: + platform_device_put(pdev); +err_out: + return ERR_PTR(error); +} +EXPORT_SYMBOL_GPL(platform_create_bundle); + +/* modalias support enables more hands-off userspace setup: + * (a) environment variable lets new-style hotplug events work once system is + * fully running: "modprobe $MODALIAS" + * (b) sysfs attribute lets new-style coldplug recover from hotplug events + * mishandled before system is fully running: "modprobe $(cat modalias)" + */ +static ssize_t modalias_show(struct device *dev, struct device_attribute *a, + char *buf) +{ + struct platform_device *pdev = to_platform_device(dev); + int len = snprintf(buf, PAGE_SIZE, "platform:%s\n", pdev->name); + + return (len >= PAGE_SIZE) ? (PAGE_SIZE - 1) : len; +} + +static struct device_attribute platform_dev_attrs[] = { + __ATTR_RO(modalias), + __ATTR_NULL, +}; + +static int platform_uevent(struct device *dev, struct kobj_uevent_env *env) +{ + struct platform_device *pdev = to_platform_device(dev); + int rc; + + /* Some devices have extra OF data and an OF-style MODALIAS */ + rc = of_device_uevent(dev,env); + if (rc != -ENODEV) + return rc; + + add_uevent_var(env, "MODALIAS=%s%s", PLATFORM_MODULE_PREFIX, + (pdev->id_entry) ? pdev->id_entry->name : pdev->name); + return 0; +} + +static const struct platform_device_id *platform_match_id( + const struct platform_device_id *id, + struct platform_device *pdev) +{ + while (id->name[0]) { + if (strcmp(pdev->name, id->name) == 0) { + pdev->id_entry = id; + return id; + } + id++; + } + return NULL; +} + +/** + * platform_match - bind platform device to platform driver. + * @dev: device. + * @drv: driver. + * + * Platform device IDs are assumed to be encoded like this: + * "<name><instance>", where <name> is a short description of the type of + * device, like "pci" or "floppy", and <instance> is the enumerated + * instance of the device, like '0' or '42'. Driver IDs are simply + * "<name>". So, extract the <name> from the platform_device structure, + * and compare it against the name of the driver. Return whether they match + * or not. + */ +static int platform_match(struct device *dev, struct device_driver *drv) +{ + struct platform_device *pdev = to_platform_device(dev); + struct platform_driver *pdrv = to_platform_driver(drv); + + /* Attempt an OF style match first */ + if (of_driver_match_device(dev, drv)) + return 1; + + /* Then try to match against the id table */ + if (pdrv->id_table) + return platform_match_id(pdrv->id_table, pdev) != NULL; + + /* fall-back to driver name match */ + return (strcmp(pdev->name, drv->name) == 0); +} + +#ifdef CONFIG_PM_SLEEP + +static int platform_legacy_suspend(struct device *dev, pm_message_t mesg) +{ + struct platform_driver *pdrv = to_platform_driver(dev->driver); + struct platform_device *pdev = to_platform_device(dev); + int ret = 0; + + if (dev->driver && pdrv->suspend) + ret = pdrv->suspend(pdev, mesg); + + return ret; +} + +static int platform_legacy_resume(struct device *dev) +{ + struct platform_driver *pdrv = to_platform_driver(dev->driver); + struct platform_device *pdev = to_platform_device(dev); + int ret = 0; + + if (dev->driver && pdrv->resume) + ret = pdrv->resume(pdev); + + return ret; +} + +int platform_pm_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; +} + +void platform_pm_complete(struct device *dev) +{ + struct device_driver *drv = dev->driver; + + if (drv && drv->pm && drv->pm->complete) + drv->pm->complete(dev); +} + +#endif /* CONFIG_PM_SLEEP */ + +#ifdef CONFIG_SUSPEND + +int platform_pm_suspend(struct device *dev) +{ + struct device_driver *drv = dev->driver; + int ret = 0; + + if (!drv) + return 0; + + if (drv->pm) { + if (drv->pm->suspend) + ret = drv->pm->suspend(dev); + } else { + ret = platform_legacy_suspend(dev, PMSG_SUSPEND); + } + + return ret; +} + +int platform_pm_suspend_noirq(struct device *dev) +{ + struct device_driver *drv = dev->driver; + int ret = 0; + + if (!drv) + return 0; + + if (drv->pm) { + if (drv->pm->suspend_noirq) + ret = drv->pm->suspend_noirq(dev); + } + + return ret; +} + +int platform_pm_resume(struct device *dev) +{ + struct device_driver *drv = dev->driver; + int ret = 0; + + if (!drv) + return 0; + + if (drv->pm) { + if (drv->pm->resume) + ret = drv->pm->resume(dev); + } else { + ret = platform_legacy_resume(dev); + } + + return ret; +} + +int platform_pm_resume_noirq(struct device *dev) +{ + struct device_driver *drv = dev->driver; + int ret = 0; + + if (!drv) + return 0; + + if (drv->pm) { + if (drv->pm->resume_noirq) + ret = drv->pm->resume_noirq(dev); + } + + return ret; +} + +#endif /* CONFIG_SUSPEND */ + +#ifdef CONFIG_HIBERNATE_CALLBACKS + +int platform_pm_freeze(struct device *dev) +{ + struct device_driver *drv = dev->driver; + int ret = 0; + + if (!drv) + return 0; + + if (drv->pm) { + if (drv->pm->freeze) + ret = drv->pm->freeze(dev); + } else { + ret = platform_legacy_suspend(dev, PMSG_FREEZE); + } + + return ret; +} + +int platform_pm_freeze_noirq(struct device *dev) +{ + struct device_driver *drv = dev->driver; + int ret = 0; + + if (!drv) + return 0; + + if (drv->pm) { + if (drv->pm->freeze_noirq) + ret = drv->pm->freeze_noirq(dev); + } + + return ret; +} + +int platform_pm_thaw(struct device *dev) +{ + struct device_driver *drv = dev->driver; + int ret = 0; + + if (!drv) + return 0; + + if (drv->pm) { + if (drv->pm->thaw) + ret = drv->pm->thaw(dev); + } else { + ret = platform_legacy_resume(dev); + } + + return ret; +} + +int platform_pm_thaw_noirq(struct device *dev) +{ + struct device_driver *drv = dev->driver; + int ret = 0; + + if (!drv) + return 0; + + if (drv->pm) { + if (drv->pm->thaw_noirq) + ret = drv->pm->thaw_noirq(dev); + } + + return ret; +} + +int platform_pm_poweroff(struct device *dev) +{ + struct device_driver *drv = dev->driver; + int ret = 0; + + if (!drv) + return 0; + + if (drv->pm) { + if (drv->pm->poweroff) + ret = drv->pm->poweroff(dev); + } else { + ret = platform_legacy_suspend(dev, PMSG_HIBERNATE); + } + + return ret; +} + +int platform_pm_poweroff_noirq(struct device *dev) +{ + struct device_driver *drv = dev->driver; + int ret = 0; + + if (!drv) + return 0; + + if (drv->pm) { + if (drv->pm->poweroff_noirq) + ret = drv->pm->poweroff_noirq(dev); + } + + return ret; +} + +int platform_pm_restore(struct device *dev) +{ + struct device_driver *drv = dev->driver; + int ret = 0; + + if (!drv) + return 0; + + if (drv->pm) { + if (drv->pm->restore) + ret = drv->pm->restore(dev); + } else { + ret = platform_legacy_resume(dev); + } + + return ret; +} + +int platform_pm_restore_noirq(struct device *dev) +{ + struct device_driver *drv = dev->driver; + int ret = 0; + + if (!drv) + return 0; + + if (drv->pm) { + if (drv->pm->restore_noirq) + ret = drv->pm->restore_noirq(dev); + } + + return ret; +} + +#endif /* CONFIG_HIBERNATE_CALLBACKS */ + +static const struct dev_pm_ops platform_dev_pm_ops = { + .runtime_suspend = pm_generic_runtime_suspend, + .runtime_resume = pm_generic_runtime_resume, + .runtime_idle = pm_generic_runtime_idle, + USE_PLATFORM_PM_SLEEP_OPS +}; + +struct bus_type platform_bus_type = { + .name = "platform", + .dev_attrs = platform_dev_attrs, + .match = platform_match, + .uevent = platform_uevent, + .pm = &platform_dev_pm_ops, +}; +EXPORT_SYMBOL_GPL(platform_bus_type); + +int __init platform_bus_init(void) +{ + int error; + + early_platform_cleanup(); + + error = device_register(&platform_bus); + if (error) + return error; + error = bus_register(&platform_bus_type); + if (error) + device_unregister(&platform_bus); + return error; +} + +#ifndef ARCH_HAS_DMA_GET_REQUIRED_MASK +u64 dma_get_required_mask(struct device *dev) +{ + u32 low_totalram = ((max_pfn - 1) << PAGE_SHIFT); + u32 high_totalram = ((max_pfn - 1) >> (32 - PAGE_SHIFT)); + u64 mask; + + if (!high_totalram) { + /* convert to mask just covering totalram */ + low_totalram = (1 << (fls(low_totalram) - 1)); + low_totalram += low_totalram - 1; + mask = low_totalram; + } else { + high_totalram = (1 << (fls(high_totalram) - 1)); + high_totalram += high_totalram - 1; + mask = (((u64)high_totalram) << 32) + 0xffffffff; + } + return mask; +} +EXPORT_SYMBOL_GPL(dma_get_required_mask); +#endif + +static __initdata LIST_HEAD(early_platform_driver_list); +static __initdata LIST_HEAD(early_platform_device_list); + +/** + * early_platform_driver_register - register early platform driver + * @epdrv: early_platform driver structure + * @buf: string passed from early_param() + * + * Helper function for early_platform_init() / early_platform_init_buffer() + */ +int __init early_platform_driver_register(struct early_platform_driver *epdrv, + char *buf) +{ + char *tmp; + int n; + + /* Simply add the driver to the end of the global list. + * Drivers will by default be put on the list in compiled-in order. + */ + if (!epdrv->list.next) { + INIT_LIST_HEAD(&epdrv->list); + list_add_tail(&epdrv->list, &early_platform_driver_list); + } + + /* If the user has specified device then make sure the driver + * gets prioritized. The driver of the last device specified on + * command line will be put first on the list. + */ + n = strlen(epdrv->pdrv->driver.name); + if (buf && !strncmp(buf, epdrv->pdrv->driver.name, n)) { + list_move(&epdrv->list, &early_platform_driver_list); + + /* Allow passing parameters after device name */ + if (buf[n] == '\0' || buf[n] == ',') + epdrv->requested_id = -1; + else { + epdrv->requested_id = simple_strtoul(&buf[n + 1], + &tmp, 10); + + if (buf[n] != '.' || (tmp == &buf[n + 1])) { + epdrv->requested_id = EARLY_PLATFORM_ID_ERROR; + n = 0; + } else + n += strcspn(&buf[n + 1], ",") + 1; + } + + if (buf[n] == ',') + n++; + + if (epdrv->bufsize) { + memcpy(epdrv->buffer, &buf[n], + min_t(int, epdrv->bufsize, strlen(&buf[n]) + 1)); + epdrv->buffer[epdrv->bufsize - 1] = '\0'; + } + } + + return 0; +} + +/** + * early_platform_add_devices - adds a number of early platform devices + * @devs: array of early platform devices to add + * @num: number of early platform devices in array + * + * Used by early architecture code to register early platform devices and + * their platform data. + */ +void __init early_platform_add_devices(struct platform_device **devs, int num) +{ + struct device *dev; + int i; + + /* simply add the devices to list */ + for (i = 0; i < num; i++) { + dev = &devs[i]->dev; + + if (!dev->devres_head.next) { + INIT_LIST_HEAD(&dev->devres_head); + list_add_tail(&dev->devres_head, + &early_platform_device_list); + } + } +} + +/** + * early_platform_driver_register_all - register early platform drivers + * @class_str: string to identify early platform driver class + * + * Used by architecture code to register all early platform drivers + * for a certain class. If omitted then only early platform drivers + * with matching kernel command line class parameters will be registered. + */ +void __init early_platform_driver_register_all(char *class_str) +{ + /* The "class_str" parameter may or may not be present on the kernel + * command line. If it is present then there may be more than one + * matching parameter. + * + * Since we register our early platform drivers using early_param() + * we need to make sure that they also get registered in the case + * when the parameter is missing from the kernel command line. + * + * We use parse_early_options() to make sure the early_param() gets + * called at least once. The early_param() may be called more than + * once since the name of the preferred device may be specified on + * the kernel command line. early_platform_driver_register() handles + * this case for us. + */ + parse_early_options(class_str); +} + +/** + * early_platform_match - find early platform device matching driver + * @epdrv: early platform driver structure + * @id: id to match against + */ +static __init struct platform_device * +early_platform_match(struct early_platform_driver *epdrv, int id) +{ + struct platform_device *pd; + + list_for_each_entry(pd, &early_platform_device_list, dev.devres_head) + if (platform_match(&pd->dev, &epdrv->pdrv->driver)) + if (pd->id == id) + return pd; + + return NULL; +} + +/** + * early_platform_left - check if early platform driver has matching devices + * @epdrv: early platform driver structure + * @id: return true if id or above exists + */ +static __init int early_platform_left(struct early_platform_driver *epdrv, + int id) +{ + struct platform_device *pd; + + list_for_each_entry(pd, &early_platform_device_list, dev.devres_head) + if (platform_match(&pd->dev, &epdrv->pdrv->driver)) + if (pd->id >= id) + return 1; + + return 0; +} + +/** + * early_platform_driver_probe_id - probe drivers matching class_str and id + * @class_str: string to identify early platform driver class + * @id: id to match against + * @nr_probe: number of platform devices to successfully probe before exiting + */ +static int __init early_platform_driver_probe_id(char *class_str, + int id, + int nr_probe) +{ + struct early_platform_driver *epdrv; + struct platform_device *match; + int match_id; + int n = 0; + int left = 0; + + list_for_each_entry(epdrv, &early_platform_driver_list, list) { + /* only use drivers matching our class_str */ + if (strcmp(class_str, epdrv->class_str)) + continue; + + if (id == -2) { + match_id = epdrv->requested_id; + left = 1; + + } else { + match_id = id; + left += early_platform_left(epdrv, id); + + /* skip requested id */ + switch (epdrv->requested_id) { + case EARLY_PLATFORM_ID_ERROR: + case EARLY_PLATFORM_ID_UNSET: + break; + default: + if (epdrv->requested_id == id) + match_id = EARLY_PLATFORM_ID_UNSET; + } + } + + switch (match_id) { + case EARLY_PLATFORM_ID_ERROR: + pr_warning("%s: unable to parse %s parameter\n", + class_str, epdrv->pdrv->driver.name); + /* fall-through */ + case EARLY_PLATFORM_ID_UNSET: + match = NULL; + break; + default: + match = early_platform_match(epdrv, match_id); + } + + if (match) { + /* + * Set up a sensible init_name to enable + * dev_name() and others to be used before the + * rest of the driver core is initialized. + */ + if (!match->dev.init_name && slab_is_available()) { + if (match->id != -1) + match->dev.init_name = + kasprintf(GFP_KERNEL, "%s.%d", + match->name, + match->id); + else + match->dev.init_name = + kasprintf(GFP_KERNEL, "%s", + match->name); + + if (!match->dev.init_name) + return -ENOMEM; + } + + if (epdrv->pdrv->probe(match)) + pr_warning("%s: unable to probe %s early.\n", + class_str, match->name); + else + n++; + } + + if (n >= nr_probe) + break; + } + + if (left) + return n; + else + return -ENODEV; +} + +/** + * early_platform_driver_probe - probe a class of registered drivers + * @class_str: string to identify early platform driver class + * @nr_probe: number of platform devices to successfully probe before exiting + * @user_only: only probe user specified early platform devices + * + * Used by architecture code to probe registered early platform drivers + * within a certain class. For probe to happen a registered early platform + * device matching a registered early platform driver is needed. + */ +int __init early_platform_driver_probe(char *class_str, + int nr_probe, + int user_only) +{ + int k, n, i; + + n = 0; + for (i = -2; n < nr_probe; i++) { + k = early_platform_driver_probe_id(class_str, i, nr_probe - n); + + if (k < 0) + break; + + n += k; + + if (user_only) + break; + } + + return n; +} + +/** + * early_platform_cleanup - clean up early platform code + */ +void __init early_platform_cleanup(void) +{ + struct platform_device *pd, *pd2; + + /* clean up the devres list used to chain devices */ + list_for_each_entry_safe(pd, pd2, &early_platform_device_list, + dev.devres_head) { + list_del(&pd->dev.devres_head); + memset(&pd->dev.devres_head, 0, sizeof(pd->dev.devres_head)); + } +} + diff --git a/drivers/base/power/Makefile b/drivers/base/power/Makefile new file mode 100644 index 00000000..3647e114 --- /dev/null +++ b/drivers/base/power/Makefile @@ -0,0 +1,8 @@ +obj-$(CONFIG_PM) += sysfs.o generic_ops.o +obj-$(CONFIG_PM_SLEEP) += main.o wakeup.o +obj-$(CONFIG_PM_RUNTIME) += runtime.o +obj-$(CONFIG_PM_TRACE_RTC) += trace.o +obj-$(CONFIG_PM_OPP) += opp.o +obj-$(CONFIG_HAVE_CLK) += clock_ops.o + +ccflags-$(CONFIG_DEBUG_DRIVER) := -DDEBUG
\ No newline at end of file diff --git a/drivers/base/power/clock_ops.c b/drivers/base/power/clock_ops.c new file mode 100644 index 00000000..ad367c41 --- /dev/null +++ b/drivers/base/power/clock_ops.c @@ -0,0 +1,431 @@ +/* + * 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/io.h> +#include <linux/pm.h> +#include <linux/pm_runtime.h> +#include <linux/clk.h> +#include <linux/slab.h> +#include <linux/err.h> + +#ifdef CONFIG_PM_RUNTIME + +struct pm_runtime_clk_data { + struct list_head clock_list; + struct mutex lock; +}; + +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; +}; + +static struct pm_runtime_clk_data *__to_prd(struct device *dev) +{ + return dev ? dev->power.subsys_data : NULL; +} + +/** + * pm_runtime_clk_add - Start using a device clock for runtime PM. + * @dev: Device whose clock is going to be used for runtime PM. + * @con_id: Connection ID of the clock. + * + * Add the clock represented by @con_id to the list of clocks used for + * the runtime PM of @dev. + */ +int pm_runtime_clk_add(struct device *dev, const char *con_id) +{ + struct pm_runtime_clk_data *prd = __to_prd(dev); + struct pm_clock_entry *ce; + + if (!prd) + 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; + } + } + + mutex_lock(&prd->lock); + list_add_tail(&ce->node, &prd->clock_list); + mutex_unlock(&prd->lock); + return 0; +} + +/** + * __pm_runtime_clk_remove - Destroy runtime PM clock entry. + * @ce: Runtime PM clock entry to destroy. + * + * This routine must be called under the mutex protecting the runtime PM list + * of clocks corresponding the the @ce's device. + */ +static void __pm_runtime_clk_remove(struct pm_clock_entry *ce) +{ + if (!ce) + return; + + list_del(&ce->node); + + if (ce->status < PCE_STATUS_ERROR) { + if (ce->status == PCE_STATUS_ENABLED) + clk_disable(ce->clk); + + if (ce->status >= PCE_STATUS_ACQUIRED) + clk_put(ce->clk); + } + + if (ce->con_id) + kfree(ce->con_id); + + kfree(ce); +} + +/** + * pm_runtime_clk_remove - Stop using a device clock for runtime PM. + * @dev: Device whose clock should not be used for runtime 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 runtime PM of @dev. + */ +void pm_runtime_clk_remove(struct device *dev, const char *con_id) +{ + struct pm_runtime_clk_data *prd = __to_prd(dev); + struct pm_clock_entry *ce; + + if (!prd) + return; + + mutex_lock(&prd->lock); + + list_for_each_entry(ce, &prd->clock_list, node) { + if (!con_id && !ce->con_id) { + __pm_runtime_clk_remove(ce); + break; + } else if (!con_id || !ce->con_id) { + continue; + } else if (!strcmp(con_id, ce->con_id)) { + __pm_runtime_clk_remove(ce); + break; + } + } + + mutex_unlock(&prd->lock); +} + +/** + * pm_runtime_clk_init - Initialize a device's list of runtime PM clocks. + * @dev: Device to initialize the list of runtime PM clocks for. + * + * Allocate a struct pm_runtime_clk_data object, initialize its lock member and + * make the @dev's power.subsys_data field point to it. + */ +int pm_runtime_clk_init(struct device *dev) +{ + struct pm_runtime_clk_data *prd; + + prd = kzalloc(sizeof(*prd), GFP_KERNEL); + if (!prd) { + dev_err(dev, "Not enough memory fo runtime PM data.\n"); + return -ENOMEM; + } + + INIT_LIST_HEAD(&prd->clock_list); + mutex_init(&prd->lock); + dev->power.subsys_data = prd; + return 0; +} + +/** + * pm_runtime_clk_destroy - Destroy a device's list of runtime PM clocks. + * @dev: Device to destroy the list of runtime PM clocks for. + * + * Clear the @dev's power.subsys_data field, remove the list of clock entries + * from the struct pm_runtime_clk_data object pointed to by it before and free + * that object. + */ +void pm_runtime_clk_destroy(struct device *dev) +{ + struct pm_runtime_clk_data *prd = __to_prd(dev); + struct pm_clock_entry *ce, *c; + + if (!prd) + return; + + dev->power.subsys_data = NULL; + + mutex_lock(&prd->lock); + + list_for_each_entry_safe_reverse(ce, c, &prd->clock_list, node) + __pm_runtime_clk_remove(ce); + + mutex_unlock(&prd->lock); + + kfree(prd); +} + +/** + * pm_runtime_clk_acquire - Acquire a device clock. + * @dev: Device whose clock is to be acquired. + * @con_id: Connection ID of the clock. + */ +static void pm_runtime_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_runtime_clk_suspend - Disable clocks in a device's runtime PM clock list. + * @dev: Device to disable the clocks for. + */ +int pm_runtime_clk_suspend(struct device *dev) +{ + struct pm_runtime_clk_data *prd = __to_prd(dev); + struct pm_clock_entry *ce; + + dev_dbg(dev, "%s()\n", __func__); + + if (!prd) + return 0; + + mutex_lock(&prd->lock); + + list_for_each_entry_reverse(ce, &prd->clock_list, node) { + if (ce->status == PCE_STATUS_NONE) + pm_runtime_clk_acquire(dev, ce); + + if (ce->status < PCE_STATUS_ERROR) { + clk_disable(ce->clk); + ce->status = PCE_STATUS_ACQUIRED; + } + } + + mutex_unlock(&prd->lock); + + return 0; +} + +/** + * pm_runtime_clk_resume - Enable clocks in a device's runtime PM clock list. + * @dev: Device to enable the clocks for. + */ +int pm_runtime_clk_resume(struct device *dev) +{ + struct pm_runtime_clk_data *prd = __to_prd(dev); + struct pm_clock_entry *ce; + + dev_dbg(dev, "%s()\n", __func__); + + if (!prd) + return 0; + + mutex_lock(&prd->lock); + + list_for_each_entry(ce, &prd->clock_list, node) { + if (ce->status == PCE_STATUS_NONE) + pm_runtime_clk_acquire(dev, ce); + + if (ce->status < PCE_STATUS_ERROR) { + clk_enable(ce->clk); + ce->status = PCE_STATUS_ENABLED; + } + } + + mutex_unlock(&prd->lock); + + return 0; +} + +/** + * pm_runtime_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 pwr_domain member of that object is copied to the device's + * pwr_domain field and its con_ids member is used to populate the device's list + * of runtime PM clocks, depending on @action. + * + * If the device's pwr_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_runtime_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->pwr_domain) + break; + + error = pm_runtime_clk_init(dev); + if (error) + break; + + dev->pwr_domain = clknb->pwr_domain; + if (clknb->con_ids[0]) { + for (con_id = clknb->con_ids; *con_id; con_id++) + pm_runtime_clk_add(dev, *con_id); + } else { + pm_runtime_clk_add(dev, NULL); + } + + break; + case BUS_NOTIFY_DEL_DEVICE: + if (dev->pwr_domain != clknb->pwr_domain) + break; + + dev->pwr_domain = NULL; + pm_runtime_clk_destroy(dev); + break; + } + + return 0; +} + +#else /* !CONFIG_PM_RUNTIME */ + +/** + * 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_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(clk); + clk_put(clk); + dev_info(dev, "Runtime PM disabled, clock forced off.\n"); + } +} + +/** + * pm_runtime_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_runtime_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_runtime_clk_add_notifier - Add bus type notifier for runtime PM 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_runtime_clk_notify(). However, + * the remaining members of @clknb should be populated prior to calling this + * routine. + */ +void pm_runtime_clk_add_notifier(struct bus_type *bus, + struct pm_clk_notifier_block *clknb) +{ + if (!bus || !clknb) + return; + + clknb->nb.notifier_call = pm_runtime_clk_notify; + bus_register_notifier(bus, &clknb->nb); +} diff --git a/drivers/base/power/generic_ops.c b/drivers/base/power/generic_ops.c new file mode 100644 index 00000000..cb3bb368 --- /dev/null +++ b/drivers/base/power/generic_ops.c @@ -0,0 +1,272 @@ +/* + * 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> + +#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_call - Generic suspend/freeze/poweroff/thaw subsystem callback. + * @dev: Device to handle. + * @event: PM transition of the system under way. + * + * If the device has not been suspended at run time, execute the + * suspend/freeze/poweroff/thaw callback provided by its driver, if defined, and + * return its error code. Otherwise, return zero. + */ +static int __pm_generic_call(struct device *dev, int event) +{ + const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL; + int (*callback)(struct device *); + + if (!pm || pm_runtime_suspended(dev)) + return 0; + + switch (event) { + case PM_EVENT_SUSPEND: + callback = pm->suspend; + break; + case PM_EVENT_FREEZE: + callback = pm->freeze; + break; + case PM_EVENT_HIBERNATE: + callback = pm->poweroff; + break; + case PM_EVENT_THAW: + callback = pm->thaw; + break; + default: + callback = NULL; + break; + } + + return callback ? callback(dev) : 0; +} + +/** + * pm_generic_suspend - Generic suspend callback for subsystems. + * @dev: Device to suspend. + */ +int pm_generic_suspend(struct device *dev) +{ + return __pm_generic_call(dev, PM_EVENT_SUSPEND); +} +EXPORT_SYMBOL_GPL(pm_generic_suspend); + +/** + * pm_generic_freeze - Generic freeze callback for subsystems. + * @dev: Device to freeze. + */ +int pm_generic_freeze(struct device *dev) +{ + return __pm_generic_call(dev, PM_EVENT_FREEZE); +} +EXPORT_SYMBOL_GPL(pm_generic_freeze); + +/** + * pm_generic_poweroff - Generic poweroff callback for subsystems. + * @dev: Device to handle. + */ +int pm_generic_poweroff(struct device *dev) +{ + return __pm_generic_call(dev, PM_EVENT_HIBERNATE); +} +EXPORT_SYMBOL_GPL(pm_generic_poweroff); + +/** + * pm_generic_thaw - Generic thaw callback for subsystems. + * @dev: Device to thaw. + */ +int pm_generic_thaw(struct device *dev) +{ + return __pm_generic_call(dev, PM_EVENT_THAW); +} +EXPORT_SYMBOL_GPL(pm_generic_thaw); + +/** + * __pm_generic_resume - Generic resume/restore callback for subsystems. + * @dev: Device to handle. + * @event: PM transition of the system under way. + * + * Execute the resume/resotre callback provided by the @dev's driver, if + * defined. If it returns 0, change the device's runtime PM status to 'active'. + * Return the callback's error code. + */ +static int __pm_generic_resume(struct device *dev, int event) +{ + const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL; + int (*callback)(struct device *); + int ret; + + if (!pm) + return 0; + + switch (event) { + case PM_EVENT_RESUME: + callback = pm->resume; + break; + case PM_EVENT_RESTORE: + callback = pm->restore; + break; + default: + callback = NULL; + break; + } + + if (!callback) + return 0; + + ret = callback(dev); + if (!ret && pm_runtime_enabled(dev)) { + pm_runtime_disable(dev); + pm_runtime_set_active(dev); + pm_runtime_enable(dev); + } + + return ret; +} + +/** + * pm_generic_resume - Generic resume callback for subsystems. + * @dev: Device to resume. + */ +int pm_generic_resume(struct device *dev) +{ + return __pm_generic_resume(dev, PM_EVENT_RESUME); +} +EXPORT_SYMBOL_GPL(pm_generic_resume); + +/** + * pm_generic_restore - Generic restore callback for subsystems. + * @dev: Device to restore. + */ +int pm_generic_restore(struct device *dev) +{ + return __pm_generic_resume(dev, PM_EVENT_RESTORE); +} +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_runtime_idle(dev); +} +#endif /* CONFIG_PM_SLEEP */ + +struct dev_pm_ops generic_subsys_pm_ops = { +#ifdef CONFIG_PM_SLEEP + .prepare = pm_generic_prepare, + .suspend = pm_generic_suspend, + .resume = pm_generic_resume, + .freeze = pm_generic_freeze, + .thaw = pm_generic_thaw, + .poweroff = pm_generic_poweroff, + .restore = pm_generic_restore, + .complete = pm_generic_complete, +#endif +#ifdef CONFIG_PM_RUNTIME + .runtime_suspend = pm_generic_runtime_suspend, + .runtime_resume = pm_generic_runtime_resume, + .runtime_idle = pm_generic_runtime_idle, +#endif +}; +EXPORT_SYMBOL_GPL(generic_subsys_pm_ops); diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c new file mode 100644 index 00000000..b4e94fce --- /dev/null +++ b/drivers/base/power/main.c @@ -0,0 +1,1188 @@ +/* + * drivers/base/power/main.c - Where the driver meets power management. + * + * Copyright (c) 2003 Patrick Mochel + * Copyright (c) 2003 Open Source Development Lab + * + * This file is released under the GPLv2 + * + * + * The driver model core calls device_pm_add() when a device is registered. + * This will initialize the embedded device_pm_info object in the device + * and add it to the list of power-controlled devices. sysfs entries for + * controlling device power management will also be added. + * + * A separate list is used for keeping track of power info, because the power + * domain dependencies may differ from the ancestral dependencies that the + * subsystem list maintains. + */ + +#include <linux/device.h> +#include <linux/kallsyms.h> +#include <linux/mutex.h> +#include <linux/pm.h> +#include <linux/pm_runtime.h> +#include <linux/resume-trace.h> +#include <linux/interrupt.h> +#include <linux/sched.h> +#include <linux/async.h> +#include <linux/suspend.h> +#include <linux/timer.h> + +#include "../base.h" +#include "power.h" + +/* + * The entries in the dpm_list list are in a depth first order, simply + * because children are guaranteed to be discovered after parents, and + * are inserted at the back of the list on discovery. + * + * Since device_pm_add() may be called with a device lock held, + * we must never try to acquire a device lock while holding + * dpm_list_mutex. + */ + +LIST_HEAD(dpm_list); +LIST_HEAD(dpm_prepared_list); +LIST_HEAD(dpm_suspended_list); +LIST_HEAD(dpm_noirq_list); + +static DEFINE_MUTEX(dpm_list_mtx); +static pm_message_t pm_transition; + +static void dpm_drv_timeout(unsigned long data); +struct dpm_drv_wd_data { + struct device *dev; + struct task_struct *tsk; +}; + +static int async_error; + +/** + * device_pm_init - Initialize the PM-related part of a device object. + * @dev: Device object being initialized. + */ +void device_pm_init(struct device *dev) +{ + dev->power.is_prepared = false; + dev->power.is_suspended = false; + init_completion(&dev->power.completion); + complete_all(&dev->power.completion); + dev->power.wakeup = NULL; + spin_lock_init(&dev->power.lock); + pm_runtime_init(dev); + INIT_LIST_HEAD(&dev->power.entry); +} + +/** + * device_pm_lock - Lock the list of active devices used by the PM core. + */ +void device_pm_lock(void) +{ + mutex_lock(&dpm_list_mtx); +} + +/** + * device_pm_unlock - Unlock the list of active devices used by the PM core. + */ +void device_pm_unlock(void) +{ + mutex_unlock(&dpm_list_mtx); +} + +/** + * device_pm_add - Add a device to the PM core's list of active devices. + * @dev: Device to add to the list. + */ +void device_pm_add(struct device *dev) +{ + pr_debug("PM: Adding info for %s:%s\n", + dev->bus ? dev->bus->name : "No Bus", dev_name(dev)); + mutex_lock(&dpm_list_mtx); + if (dev->parent && dev->parent->power.is_prepared) + dev_warn(dev, "parent %s should not be sleeping\n", + dev_name(dev->parent)); + list_add_tail(&dev->power.entry, &dpm_list); + mutex_unlock(&dpm_list_mtx); +} + +/** + * device_pm_remove - Remove a device from the PM core's list of active devices. + * @dev: Device to be removed from the list. + */ +void device_pm_remove(struct device *dev) +{ + pr_debug("PM: Removing info for %s:%s\n", + dev->bus ? dev->bus->name : "No Bus", dev_name(dev)); + complete_all(&dev->power.completion); + mutex_lock(&dpm_list_mtx); + list_del_init(&dev->power.entry); + mutex_unlock(&dpm_list_mtx); + device_wakeup_disable(dev); + pm_runtime_remove(dev); +} + +/** + * device_pm_move_before - Move device in the PM core's list of active devices. + * @deva: Device to move in dpm_list. + * @devb: Device @deva should come before. + */ +void device_pm_move_before(struct device *deva, struct device *devb) +{ + pr_debug("PM: Moving %s:%s before %s:%s\n", + deva->bus ? deva->bus->name : "No Bus", dev_name(deva), + devb->bus ? devb->bus->name : "No Bus", dev_name(devb)); + /* Delete deva from dpm_list and reinsert before devb. */ + list_move_tail(&deva->power.entry, &devb->power.entry); +} + +/** + * device_pm_move_after - Move device in the PM core's list of active devices. + * @deva: Device to move in dpm_list. + * @devb: Device @deva should come after. + */ +void device_pm_move_after(struct device *deva, struct device *devb) +{ + pr_debug("PM: Moving %s:%s after %s:%s\n", + deva->bus ? deva->bus->name : "No Bus", dev_name(deva), + devb->bus ? devb->bus->name : "No Bus", dev_name(devb)); + /* Delete deva from dpm_list and reinsert after devb. */ + list_move(&deva->power.entry, &devb->power.entry); +} + +/** + * device_pm_move_last - Move device to end of the PM core's list of devices. + * @dev: Device to move in dpm_list. + */ +void device_pm_move_last(struct device *dev) +{ + pr_debug("PM: Moving %s:%s to end of list\n", + dev->bus ? dev->bus->name : "No Bus", dev_name(dev)); + list_move_tail(&dev->power.entry, &dpm_list); +} + +static ktime_t initcall_debug_start(struct device *dev) +{ + ktime_t calltime = ktime_set(0, 0); + + if (initcall_debug) { + pr_info("calling %s+ @ %i\n", + dev_name(dev), task_pid_nr(current)); + calltime = ktime_get(); + } + + return calltime; +} + +static void initcall_debug_report(struct device *dev, ktime_t calltime, + int error) +{ + ktime_t delta, rettime; + + if (initcall_debug) { + rettime = ktime_get(); + delta = ktime_sub(rettime, calltime); + pr_info("call %s+ returned %d after %Ld usecs\n", dev_name(dev), + error, (unsigned long long)ktime_to_ns(delta) >> 10); + } +} +#ifdef CONFIG_SUSPEND_DEVICE_TIME_DEBUG +static void suspend_time_debug_start(ktime_t *start) +{ + *start = ktime_get(); +} + +static void suspend_time_debug_report(const char *name, struct device *dev, + ktime_t starttime) +{ + ktime_t rettime; + s64 usecs64; + int usecs; + + if (!dev->driver) + return; + + rettime = ktime_get(); + usecs64 = ktime_to_us(ktime_sub(rettime, starttime)); + usecs = usecs64; + if (usecs == 0) + usecs = 1; + + if (device_suspend_time_threshold + && usecs > device_suspend_time_threshold) + pr_info("PM: device %s:%s %s too slow, it takes \t %ld.%03ld msecs\n", + dev->bus->name, dev_name(dev), name, + usecs / USEC_PER_MSEC, usecs % USEC_PER_MSEC); +} +#else +static void suspend_time_debug_start(ktime_t *start) {} +static void suspend_time_debug_report(const char *name, struct device *dev, + ktime_t starttime) {} +#endif /* CONFIG_SUSPEND_DEVICE_TIME_DEBUG */ + +/** + * dpm_wait - Wait for a PM operation to complete. + * @dev: Device to wait for. + * @async: If unset, wait only if the device's power.async_suspend flag is set. + */ +static void dpm_wait(struct device *dev, bool async) +{ + if (!dev) + return; + + if (async || (pm_async_enabled && dev->power.async_suspend)) + wait_for_completion(&dev->power.completion); +} + +static int dpm_wait_fn(struct device *dev, void *async_ptr) +{ + dpm_wait(dev, *((bool *)async_ptr)); + return 0; +} + +static void dpm_wait_for_children(struct device *dev, bool async) +{ + device_for_each_child(dev, &async, dpm_wait_fn); +} + +/** + * pm_op - Execute the PM operation appropriate for given PM event. + * @dev: Device to handle. + * @ops: PM operations to choose from. + * @state: PM transition of the system being carried out. + */ +static int pm_op(struct device *dev, + const struct dev_pm_ops *ops, + pm_message_t state) +{ + int error = 0; + ktime_t calltime, starttime; + + calltime = initcall_debug_start(dev); + + switch (state.event) { +#ifdef CONFIG_SUSPEND + case PM_EVENT_SUSPEND: + if (ops->suspend) { + suspend_time_debug_start(&starttime); + error = ops->suspend(dev); + suspend_time_debug_report("suspend", dev, starttime); + suspend_report_result(ops->suspend, error); + } + break; + case PM_EVENT_RESUME: + if (ops->resume) { + suspend_time_debug_start(&starttime); + error = ops->resume(dev); + suspend_time_debug_report("resume", dev, starttime); + suspend_report_result(ops->resume, error); + } + break; +#endif /* CONFIG_SUSPEND */ +#ifdef CONFIG_HIBERNATE_CALLBACKS + case PM_EVENT_FREEZE: + case PM_EVENT_QUIESCE: + if (ops->freeze) { + error = ops->freeze(dev); + suspend_report_result(ops->freeze, error); + } + break; + case PM_EVENT_HIBERNATE: + if (ops->poweroff) { + error = ops->poweroff(dev); + suspend_report_result(ops->poweroff, error); + } + break; + case PM_EVENT_THAW: + case PM_EVENT_RECOVER: + if (ops->thaw) { + error = ops->thaw(dev); + suspend_report_result(ops->thaw, error); + } + break; + case PM_EVENT_RESTORE: + if (ops->restore) { + error = ops->restore(dev); + suspend_report_result(ops->restore, error); + } + break; +#endif /* CONFIG_HIBERNATE_CALLBACKS */ + default: + error = -EINVAL; + } + + initcall_debug_report(dev, calltime, error); + + return error; +} + +/** + * pm_noirq_op - Execute the PM operation appropriate for given PM event. + * @dev: Device to handle. + * @ops: PM operations to choose from. + * @state: PM transition of the system being carried out. + * + * The driver of @dev will not receive interrupts while this function is being + * executed. + */ +static int pm_noirq_op(struct device *dev, + const struct dev_pm_ops *ops, + pm_message_t state) +{ + int error = 0; + ktime_t calltime = ktime_set(0, 0), delta, rettime; + + if (initcall_debug) { + pr_info("calling %s+ @ %i, parent: %s\n", + dev_name(dev), task_pid_nr(current), + dev->parent ? dev_name(dev->parent) : "none"); + calltime = ktime_get(); + } + + switch (state.event) { +#ifdef CONFIG_SUSPEND + case PM_EVENT_SUSPEND: + if (ops->suspend_noirq) { + error = ops->suspend_noirq(dev); + suspend_report_result(ops->suspend_noirq, error); + } + break; + case PM_EVENT_RESUME: + if (ops->resume_noirq) { + error = ops->resume_noirq(dev); + suspend_report_result(ops->resume_noirq, error); + } + break; +#endif /* CONFIG_SUSPEND */ +#ifdef CONFIG_HIBERNATE_CALLBACKS + case PM_EVENT_FREEZE: + case PM_EVENT_QUIESCE: + if (ops->freeze_noirq) { + error = ops->freeze_noirq(dev); + suspend_report_result(ops->freeze_noirq, error); + } + break; + case PM_EVENT_HIBERNATE: + if (ops->poweroff_noirq) { + error = ops->poweroff_noirq(dev); + suspend_report_result(ops->poweroff_noirq, error); + } + break; + case PM_EVENT_THAW: + case PM_EVENT_RECOVER: + if (ops->thaw_noirq) { + error = ops->thaw_noirq(dev); + suspend_report_result(ops->thaw_noirq, error); + } + break; + case PM_EVENT_RESTORE: + if (ops->restore_noirq) { + error = ops->restore_noirq(dev); + suspend_report_result(ops->restore_noirq, error); + } + break; +#endif /* CONFIG_HIBERNATE_CALLBACKS */ + default: + error = -EINVAL; + } + + if (initcall_debug) { + rettime = ktime_get(); + delta = ktime_sub(rettime, calltime); + printk("initcall %s_i+ returned %d after %Ld usecs\n", + dev_name(dev), error, + (unsigned long long)ktime_to_ns(delta) >> 10); + } + + return error; +} + +static char *pm_verb(int event) +{ + switch (event) { + case PM_EVENT_SUSPEND: + return "suspend"; + case PM_EVENT_RESUME: + return "resume"; + case PM_EVENT_FREEZE: + return "freeze"; + case PM_EVENT_QUIESCE: + return "quiesce"; + case PM_EVENT_HIBERNATE: + return "hibernate"; + case PM_EVENT_THAW: + return "thaw"; + case PM_EVENT_RESTORE: + return "restore"; + case PM_EVENT_RECOVER: + return "recover"; + default: + return "(unknown PM event)"; + } +} + +static void pm_dev_dbg(struct device *dev, pm_message_t state, char *info) +{ + dev_dbg(dev, "%s%s%s\n", info, pm_verb(state.event), + ((state.event & PM_EVENT_SLEEP) && device_may_wakeup(dev)) ? + ", may wakeup" : ""); +} + +static void pm_dev_err(struct device *dev, pm_message_t state, char *info, + int error) +{ + printk(KERN_ERR "PM: Device %s failed to %s%s: error %d\n", + dev_name(dev), pm_verb(state.event), info, error); +} + +static void dpm_show_time(ktime_t starttime, pm_message_t state, char *info) +{ + ktime_t calltime; + u64 usecs64; + int usecs; + + calltime = ktime_get(); + usecs64 = ktime_to_ns(ktime_sub(calltime, starttime)); + do_div(usecs64, NSEC_PER_USEC); + usecs = usecs64; + if (usecs == 0) + usecs = 1; + pr_info("PM: %s%s%s of devices complete after %ld.%03ld msecs\n", + info ?: "", info ? " " : "", pm_verb(state.event), + usecs / USEC_PER_MSEC, usecs % USEC_PER_MSEC); +} + +/*------------------------- Resume routines -------------------------*/ + +/** + * device_resume_noirq - Execute an "early resume" callback for given device. + * @dev: Device to handle. + * @state: PM transition of the system being carried out. + * + * The driver of @dev will not receive interrupts while this function is being + * executed. + */ +static int device_resume_noirq(struct device *dev, pm_message_t state) +{ + int error = 0; + + TRACE_DEVICE(dev); + TRACE_RESUME(0); + + if (dev->pwr_domain) { + pm_dev_dbg(dev, state, "EARLY power domain "); + error = pm_noirq_op(dev, &dev->pwr_domain->ops, state); + } else if (dev->type && dev->type->pm) { + pm_dev_dbg(dev, state, "EARLY type "); + error = pm_noirq_op(dev, dev->type->pm, state); + } else if (dev->class && dev->class->pm) { + pm_dev_dbg(dev, state, "EARLY class "); + error = pm_noirq_op(dev, dev->class->pm, state); + } else if (dev->bus && dev->bus->pm) { + pm_dev_dbg(dev, state, "EARLY "); + error = pm_noirq_op(dev, dev->bus->pm, state); + } + + TRACE_RESUME(error); + return error; +} + +/** + * dpm_resume_noirq - Execute "early resume" callbacks for non-sysdev devices. + * @state: PM transition of the system being carried out. + * + * Call the "noirq" resume handlers for all devices marked as DPM_OFF_IRQ and + * enable device drivers to receive interrupts. + */ +void dpm_resume_noirq(pm_message_t state) +{ + ktime_t starttime = ktime_get(); + + mutex_lock(&dpm_list_mtx); + while (!list_empty(&dpm_noirq_list)) { + struct device *dev = to_device(dpm_noirq_list.next); + int error; + + get_device(dev); + list_move_tail(&dev->power.entry, &dpm_suspended_list); + mutex_unlock(&dpm_list_mtx); + + error = device_resume_noirq(dev, state); + if (error) + pm_dev_err(dev, state, " early", error); + + mutex_lock(&dpm_list_mtx); + put_device(dev); + } + mutex_unlock(&dpm_list_mtx); + dpm_show_time(starttime, state, "early"); + resume_device_irqs(); +} +EXPORT_SYMBOL_GPL(dpm_resume_noirq); + +/** + * legacy_resume - Execute a legacy (bus or class) resume callback for device. + * @dev: Device to resume. + * @cb: Resume callback to execute. + */ +static int legacy_resume(struct device *dev, int (*cb)(struct device *dev)) +{ + int error; + ktime_t calltime; + + calltime = initcall_debug_start(dev); + + error = cb(dev); + suspend_report_result(cb, error); + + initcall_debug_report(dev, calltime, error); + + return error; +} + +/** + * device_resume - Execute "resume" callbacks for given device. + * @dev: Device to handle. + * @state: PM transition of the system being carried out. + * @async: If true, the device is being resumed asynchronously. + */ +static int device_resume(struct device *dev, pm_message_t state, bool async) +{ + int error = 0; + + TRACE_DEVICE(dev); + TRACE_RESUME(0); + + dpm_wait(dev->parent, async); + device_lock(dev); + + /* + * This is a fib. But we'll allow new children to be added below + * a resumed device, even if the device hasn't been completed yet. + */ + dev->power.is_prepared = false; + + if (!dev->power.is_suspended) + goto Unlock; + + if (dev->pwr_domain) { + pm_dev_dbg(dev, state, "power domain "); + error = pm_op(dev, &dev->pwr_domain->ops, state); + goto End; + } + + if (dev->type && dev->type->pm) { + pm_dev_dbg(dev, state, "type "); + error = pm_op(dev, dev->type->pm, state); + goto End; + } + + if (dev->class) { + if (dev->class->pm) { + pm_dev_dbg(dev, state, "class "); + error = pm_op(dev, dev->class->pm, state); + goto End; + } else if (dev->class->resume) { + pm_dev_dbg(dev, state, "legacy class "); + error = legacy_resume(dev, dev->class->resume); + goto End; + } + } + + if (dev->bus) { + if (dev->bus->pm) { + pm_dev_dbg(dev, state, ""); + error = pm_op(dev, dev->bus->pm, state); + } else if (dev->bus->resume) { + pm_dev_dbg(dev, state, "legacy "); + error = legacy_resume(dev, dev->bus->resume); + } + } + + End: + dev->power.is_suspended = false; + + Unlock: + device_unlock(dev); + complete_all(&dev->power.completion); + + TRACE_RESUME(error); + return error; +} + +static void async_resume(void *data, async_cookie_t cookie) +{ + struct device *dev = (struct device *)data; + int error; + + error = device_resume(dev, pm_transition, true); + if (error) + pm_dev_err(dev, pm_transition, " async", error); + put_device(dev); +} + +static bool is_async(struct device *dev) +{ + return dev->power.async_suspend && pm_async_enabled + && !pm_trace_is_enabled(); +} + +/** + * dpm_drv_timeout - Driver suspend / resume watchdog handler + * @data: struct device which timed out + * + * Called when a driver has timed out suspending or resuming. + * There's not much we can do here to recover so + * BUG() out for a crash-dump + * + */ +static void dpm_drv_timeout(unsigned long data) +{ + struct dpm_drv_wd_data *wd_data = (void *)data; + struct device *dev = wd_data->dev; + struct task_struct *tsk = wd_data->tsk; + + printk(KERN_EMERG "**** DPM device timeout: %s (%s)\n", dev_name(dev), + (dev->driver ? dev->driver->name : "no driver")); + + printk(KERN_EMERG "dpm suspend stack:\n"); + show_stack(tsk, NULL); + + BUG(); +} + +/** + * dpm_resume - Execute "resume" callbacks for non-sysdev devices. + * @state: PM transition of the system being carried out. + * + * Execute the appropriate "resume" callback for all devices whose status + * indicates that they are suspended. + */ +void dpm_resume(pm_message_t state) +{ + struct device *dev; + ktime_t starttime = ktime_get(); + + might_sleep(); + + mutex_lock(&dpm_list_mtx); + pm_transition = state; + async_error = 0; + + list_for_each_entry(dev, &dpm_suspended_list, power.entry) { + INIT_COMPLETION(dev->power.completion); + if (is_async(dev)) { + get_device(dev); + async_schedule(async_resume, dev); + } + } + + while (!list_empty(&dpm_suspended_list)) { + dev = to_device(dpm_suspended_list.next); + get_device(dev); + if (!is_async(dev)) { + int error; + + mutex_unlock(&dpm_list_mtx); + + error = device_resume(dev, state, false); + if (error) + pm_dev_err(dev, state, "", error); + + mutex_lock(&dpm_list_mtx); + } + if (!list_empty(&dev->power.entry)) + list_move_tail(&dev->power.entry, &dpm_prepared_list); + put_device(dev); + } + mutex_unlock(&dpm_list_mtx); + async_synchronize_full(); + dpm_show_time(starttime, state, NULL); +} + +/** + * device_complete - Complete a PM transition for given device. + * @dev: Device to handle. + * @state: PM transition of the system being carried out. + */ +static void device_complete(struct device *dev, pm_message_t state) +{ + device_lock(dev); + + if (dev->pwr_domain) { + pm_dev_dbg(dev, state, "completing power domain "); + if (dev->pwr_domain->ops.complete) + dev->pwr_domain->ops.complete(dev); + } else if (dev->type && dev->type->pm) { + pm_dev_dbg(dev, state, "completing type "); + if (dev->type->pm->complete) + dev->type->pm->complete(dev); + } else if (dev->class && dev->class->pm) { + pm_dev_dbg(dev, state, "completing class "); + if (dev->class->pm->complete) + dev->class->pm->complete(dev); + } else if (dev->bus && dev->bus->pm) { + pm_dev_dbg(dev, state, "completing "); + if (dev->bus->pm->complete) + dev->bus->pm->complete(dev); + } + + device_unlock(dev); +} + +/** + * dpm_complete - Complete a PM transition for all non-sysdev devices. + * @state: PM transition of the system being carried out. + * + * Execute the ->complete() callbacks for all devices whose PM status is not + * DPM_ON (this allows new devices to be registered). + */ +void dpm_complete(pm_message_t state) +{ + struct list_head list; + + might_sleep(); + + INIT_LIST_HEAD(&list); + mutex_lock(&dpm_list_mtx); + while (!list_empty(&dpm_prepared_list)) { + struct device *dev = to_device(dpm_prepared_list.prev); + + get_device(dev); + dev->power.is_prepared = false; + list_move(&dev->power.entry, &list); + mutex_unlock(&dpm_list_mtx); + + device_complete(dev, state); + + mutex_lock(&dpm_list_mtx); + put_device(dev); + } + list_splice(&list, &dpm_list); + mutex_unlock(&dpm_list_mtx); +} + +/** + * dpm_resume_end - Execute "resume" callbacks and complete system transition. + * @state: PM transition of the system being carried out. + * + * Execute "resume" callbacks for all devices and complete the PM transition of + * the system. + */ +void dpm_resume_end(pm_message_t state) +{ + dpm_resume(state); + dpm_complete(state); +} +EXPORT_SYMBOL_GPL(dpm_resume_end); + + +/*------------------------- Suspend routines -------------------------*/ + +/** + * resume_event - Return a "resume" message for given "suspend" sleep state. + * @sleep_state: PM message representing a sleep state. + * + * Return a PM message representing the resume event corresponding to given + * sleep state. + */ +static pm_message_t resume_event(pm_message_t sleep_state) +{ + switch (sleep_state.event) { + case PM_EVENT_SUSPEND: + return PMSG_RESUME; + case PM_EVENT_FREEZE: + case PM_EVENT_QUIESCE: + return PMSG_RECOVER; + case PM_EVENT_HIBERNATE: + return PMSG_RESTORE; + } + return PMSG_ON; +} + +/** + * device_suspend_noirq - Execute a "late suspend" callback for given device. + * @dev: Device to handle. + * @state: PM transition of the system being carried out. + * + * The driver of @dev will not receive interrupts while this function is being + * executed. + */ +static int device_suspend_noirq(struct device *dev, pm_message_t state) +{ + int error; + + if (dev->pwr_domain) { + pm_dev_dbg(dev, state, "LATE power domain "); + error = pm_noirq_op(dev, &dev->pwr_domain->ops, state); + if (error) + return error; + } else if (dev->type && dev->type->pm) { + pm_dev_dbg(dev, state, "LATE type "); + error = pm_noirq_op(dev, dev->type->pm, state); + if (error) + return error; + } else if (dev->class && dev->class->pm) { + pm_dev_dbg(dev, state, "LATE class "); + error = pm_noirq_op(dev, dev->class->pm, state); + if (error) + return error; + } else if (dev->bus && dev->bus->pm) { + pm_dev_dbg(dev, state, "LATE "); + error = pm_noirq_op(dev, dev->bus->pm, state); + if (error) + return error; + } + + return 0; +} + +/** + * dpm_suspend_noirq - Execute "late suspend" callbacks for non-sysdev devices. + * @state: PM transition of the system being carried out. + * + * Prevent device drivers from receiving interrupts and call the "noirq" suspend + * handlers for all non-sysdev devices. + */ +int dpm_suspend_noirq(pm_message_t state) +{ + ktime_t starttime = ktime_get(); + int error = 0; + + suspend_device_irqs(); + mutex_lock(&dpm_list_mtx); + while (!list_empty(&dpm_suspended_list)) { + struct device *dev = to_device(dpm_suspended_list.prev); + + get_device(dev); + mutex_unlock(&dpm_list_mtx); + + error = device_suspend_noirq(dev, state); + + mutex_lock(&dpm_list_mtx); + if (error) { + pm_dev_err(dev, state, " late", error); + put_device(dev); + break; + } + if (!list_empty(&dev->power.entry)) + list_move(&dev->power.entry, &dpm_noirq_list); + put_device(dev); + } + mutex_unlock(&dpm_list_mtx); + if (error) { + resume_irqs(true); + dpm_resume_noirq(resume_event(state)); + } + else + dpm_show_time(starttime, state, "late"); + return error; +} +EXPORT_SYMBOL_GPL(dpm_suspend_noirq); + +/** + * legacy_suspend - Execute a legacy (bus or class) suspend callback for device. + * @dev: Device to suspend. + * @state: PM transition of the system being carried out. + * @cb: Suspend callback to execute. + */ +static int legacy_suspend(struct device *dev, pm_message_t state, + int (*cb)(struct device *dev, pm_message_t state)) +{ + int error; + ktime_t calltime; + + calltime = initcall_debug_start(dev); + + error = cb(dev, state); + suspend_report_result(cb, error); + + initcall_debug_report(dev, calltime, error); + + return error; +} + +/** + * device_suspend - Execute "suspend" callbacks for given device. + * @dev: Device to handle. + * @state: PM transition of the system being carried out. + * @async: If true, the device is being suspended asynchronously. + */ +static int __device_suspend(struct device *dev, pm_message_t state, bool async) +{ + int error = 0; + struct timer_list timer; + struct dpm_drv_wd_data data; + + dpm_wait_for_children(dev, async); + + data.dev = dev; + data.tsk = get_current(); + init_timer_on_stack(&timer); + timer.expires = jiffies + HZ * 12; + timer.function = dpm_drv_timeout; + timer.data = (unsigned long)&data; + add_timer(&timer); + + device_lock(dev); + + if (async_error) + goto Unlock; + + if (pm_wakeup_pending()) { + async_error = -EBUSY; + goto Unlock; + } + + if (dev->pwr_domain) { + pm_dev_dbg(dev, state, "power domain "); + error = pm_op(dev, &dev->pwr_domain->ops, state); + goto End; + } + + if (dev->type && dev->type->pm) { + pm_dev_dbg(dev, state, "type "); + error = pm_op(dev, dev->type->pm, state); + goto End; + } + + if (dev->class) { + if (dev->class->pm) { + pm_dev_dbg(dev, state, "class "); + error = pm_op(dev, dev->class->pm, state); + goto End; + } else if (dev->class->suspend) { + pm_dev_dbg(dev, state, "legacy class "); + error = legacy_suspend(dev, state, dev->class->suspend); + goto End; + } + } + + if (dev->bus) { + if (dev->bus->pm) { + pm_dev_dbg(dev, state, ""); + error = pm_op(dev, dev->bus->pm, state); + } else if (dev->bus->suspend) { + pm_dev_dbg(dev, state, "legacy "); + error = legacy_suspend(dev, state, dev->bus->suspend); + } + } + + End: + dev->power.is_suspended = !error; + + Unlock: + device_unlock(dev); + + del_timer_sync(&timer); + destroy_timer_on_stack(&timer); + + complete_all(&dev->power.completion); + + if (error) + async_error = error; + + return error; +} + +static void async_suspend(void *data, async_cookie_t cookie) +{ + struct device *dev = (struct device *)data; + int error; + + error = __device_suspend(dev, pm_transition, true); + if (error) + pm_dev_err(dev, pm_transition, " async", error); + + put_device(dev); +} + +static int device_suspend(struct device *dev) +{ + INIT_COMPLETION(dev->power.completion); + + if (pm_async_enabled && dev->power.async_suspend) { + get_device(dev); + async_schedule(async_suspend, dev); + return 0; + } + + return __device_suspend(dev, pm_transition, false); +} + +/** + * dpm_suspend - Execute "suspend" callbacks for all non-sysdev devices. + * @state: PM transition of the system being carried out. + */ +int dpm_suspend(pm_message_t state) +{ + ktime_t starttime = ktime_get(); + int error = 0; + + might_sleep(); + + mutex_lock(&dpm_list_mtx); + pm_transition = state; + async_error = 0; + while (!list_empty(&dpm_prepared_list)) { + struct device *dev = to_device(dpm_prepared_list.prev); + + get_device(dev); + mutex_unlock(&dpm_list_mtx); + + error = device_suspend(dev); + + mutex_lock(&dpm_list_mtx); + if (error) { + pm_dev_err(dev, state, "", error); + put_device(dev); + break; + } + if (!list_empty(&dev->power.entry)) + list_move(&dev->power.entry, &dpm_suspended_list); + put_device(dev); + if (async_error) + break; + } + mutex_unlock(&dpm_list_mtx); + async_synchronize_full(); + if (!error) + error = async_error; + if (!error) + dpm_show_time(starttime, state, NULL); + return error; +} + +/** + * device_prepare - Prepare a device for system power transition. + * @dev: Device to handle. + * @state: PM transition of the system being carried out. + * + * Execute the ->prepare() callback(s) for given device. No new children of the + * device may be registered after this function has returned. + */ +static int device_prepare(struct device *dev, pm_message_t state) +{ + int error = 0; + + device_lock(dev); + + if (dev->pwr_domain) { + pm_dev_dbg(dev, state, "preparing power domain "); + if (dev->pwr_domain->ops.prepare) + error = dev->pwr_domain->ops.prepare(dev); + suspend_report_result(dev->pwr_domain->ops.prepare, error); + if (error) + goto End; + } else if (dev->type && dev->type->pm) { + pm_dev_dbg(dev, state, "preparing type "); + if (dev->type->pm->prepare) + error = dev->type->pm->prepare(dev); + suspend_report_result(dev->type->pm->prepare, error); + if (error) + goto End; + } else if (dev->class && dev->class->pm) { + pm_dev_dbg(dev, state, "preparing class "); + if (dev->class->pm->prepare) + error = dev->class->pm->prepare(dev); + suspend_report_result(dev->class->pm->prepare, error); + if (error) + goto End; + } else if (dev->bus && dev->bus->pm) { + pm_dev_dbg(dev, state, "preparing "); + if (dev->bus->pm->prepare) + error = dev->bus->pm->prepare(dev); + suspend_report_result(dev->bus->pm->prepare, error); + } + + End: + device_unlock(dev); + + return error; +} + +/** + * dpm_prepare - Prepare all non-sysdev devices for a system PM transition. + * @state: PM transition of the system being carried out. + * + * Execute the ->prepare() callback(s) for all devices. + */ +int dpm_prepare(pm_message_t state) +{ + int error = 0; + + might_sleep(); + + mutex_lock(&dpm_list_mtx); + while (!list_empty(&dpm_list)) { + struct device *dev = to_device(dpm_list.next); + + get_device(dev); + mutex_unlock(&dpm_list_mtx); + + pm_runtime_get_noresume(dev); + if (pm_runtime_barrier(dev) && device_may_wakeup(dev)) + pm_wakeup_event(dev, 0); + + pm_runtime_put_sync(dev); + error = pm_wakeup_pending() ? + -EBUSY : device_prepare(dev, state); + + mutex_lock(&dpm_list_mtx); + if (error) { + if (error == -EAGAIN) { + put_device(dev); + error = 0; + continue; + } + printk(KERN_INFO "PM: Device %s not prepared " + "for power transition: code %d\n", + dev_name(dev), error); + put_device(dev); + break; + } + dev->power.is_prepared = true; + if (!list_empty(&dev->power.entry)) + list_move_tail(&dev->power.entry, &dpm_prepared_list); + put_device(dev); + } + mutex_unlock(&dpm_list_mtx); + return error; +} + +/** + * dpm_suspend_start - Prepare devices for PM transition and suspend them. + * @state: PM transition of the system being carried out. + * + * Prepare all non-sysdev devices for system PM transition and execute "suspend" + * callbacks for them. + */ +int dpm_suspend_start(pm_message_t state) +{ + int error; + + error = dpm_prepare(state); + if (!error) + error = dpm_suspend(state); + return error; +} +EXPORT_SYMBOL_GPL(dpm_suspend_start); + +void __suspend_report_result(const char *function, void *fn, int ret) +{ + if (ret) + printk(KERN_ERR "%s(): %pF returns %d\n", function, fn, ret); +} +EXPORT_SYMBOL_GPL(__suspend_report_result); + +/** + * device_pm_wait_for_dev - Wait for suspend/resume of a device to complete. + * @dev: Device to wait for. + * @subordinate: Device that needs to wait for @dev. + */ +int device_pm_wait_for_dev(struct device *subordinate, struct device *dev) +{ + dpm_wait(dev, subordinate->power.async_suspend); + return async_error; +} +EXPORT_SYMBOL_GPL(device_pm_wait_for_dev); diff --git a/drivers/base/power/opp.c b/drivers/base/power/opp.c new file mode 100644 index 00000000..56a6899f --- /dev/null +++ b/drivers/base/power/opp.c @@ -0,0 +1,628 @@ +/* + * 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/list.h> +#include <linux/rculist.h> +#include <linux/rcupdate.h> +#include <linux/opp.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 + * + * 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 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 + * @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 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; +} + +/** + * 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; +} + +/** + * 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; +} + +/** + * 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. + * + * 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(-ENODEV); + + 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; +} + +/** + * 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. + * + * 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(-ENODEV); + + 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 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; +} + +/** + * 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. + * + * 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(-ENODEV); + + 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 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; +} + +/** + * 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; + 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); + + 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 = NULL; + 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); + synchronize_rcu(); + + /* clean up old opp */ + new_opp = opp; + goto out; + +unlock: + mutex_unlock(&dev_opp_list_lock); +out: + 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); +} + +/** + * 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); +} + +#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; +} +#endif /* CONFIG_CPU_FREQ */ diff --git a/drivers/base/power/power.h b/drivers/base/power/power.h new file mode 100644 index 00000000..51b585a4 --- /dev/null +++ b/drivers/base/power/power.h @@ -0,0 +1,79 @@ +#ifdef CONFIG_PM_RUNTIME + +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_init(struct device *dev) {} +static inline void pm_runtime_remove(struct device *dev) {} + +#endif /* !CONFIG_PM_RUNTIME */ + +#ifdef CONFIG_SUSPEND_DEVICE_TIME_DEBUG +extern int device_suspend_time_threshold; +#endif + +#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_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_init(struct device *dev) +{ + spin_lock_init(&dev->power.lock); + pm_runtime_init(dev); +} + +static inline void device_pm_remove(struct device *dev) +{ + pm_runtime_remove(dev); +} + +static inline void device_pm_add(struct device *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 */ + +#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); + +#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) {} + +#endif diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c new file mode 100644 index 00000000..184cf54f --- /dev/null +++ b/drivers/base/power/runtime.c @@ -0,0 +1,1263 @@ +/* + * drivers/base/power/runtime.c - Helper functions for device run-time PM + * + * Copyright (c) 2009 Rafael J. Wysocki <rjw@sisk.pl>, Novell Inc. + * Copyright (C) 2010 Alan Stern <stern@rowland.harvard.edu> + * + * This file is released under the GPLv2. + */ + +#include <linux/sched.h> +#include <linux/pm_runtime.h> +#include "power.h" + +static int rpm_resume(struct device *dev, int rpmflags); +static int rpm_suspend(struct device *dev, int rpmflags); + +/** + * update_pm_runtime_accounting - Update the time accounting of power states + * @dev: Device to update the accounting for + * + * In order to be able to have time accounting of the various power states + * (as used by programs such as PowerTOP to show the effectiveness of runtime + * PM), we need to track the time spent in each state. + * update_pm_runtime_accounting must be called each time before the + * runtime_status field is updated, to account the time in the old state + * correctly. + */ +void update_pm_runtime_accounting(struct device *dev) +{ + unsigned long now = jiffies; + int delta; + + delta = now - dev->power.accounting_timestamp; + + if (delta < 0) + delta = 0; + + dev->power.accounting_timestamp = now; + + if (dev->power.disable_depth > 0) + return; + + if (dev->power.runtime_status == RPM_SUSPENDED) + dev->power.suspended_jiffies += delta; + else + dev->power.active_jiffies += delta; +} + +static void __update_runtime_status(struct device *dev, enum rpm_status status) +{ + update_pm_runtime_accounting(dev); + dev->power.runtime_status = status; +} + +/** + * pm_runtime_deactivate_timer - Deactivate given device's suspend timer. + * @dev: Device to handle. + */ +static void pm_runtime_deactivate_timer(struct device *dev) +{ + if (dev->power.timer_expires > 0) { + del_timer(&dev->power.suspend_timer); + dev->power.timer_expires = 0; + } +} + +/** + * pm_runtime_cancel_pending - Deactivate suspend timer and cancel requests. + * @dev: Device to handle. + */ +static void pm_runtime_cancel_pending(struct device *dev) +{ + pm_runtime_deactivate_timer(dev); + /* + * In case there's a request pending, make sure its work function will + * return without doing anything. + */ + dev->power.request = RPM_REQ_NONE; +} + +/* + * pm_runtime_autosuspend_expiration - Get a device's autosuspend-delay expiration time. + * @dev: Device to handle. + * + * Compute the autosuspend-delay expiration time based on the device's + * power.last_busy time. If the delay has already expired or is disabled + * (negative) or the power.use_autosuspend flag isn't set, return 0. + * Otherwise return the expiration time in jiffies (adjusted to be nonzero). + * + * This function may be called either with or without dev->power.lock held. + * Either way it can be racy, since power.last_busy may be updated at any time. + */ +unsigned long pm_runtime_autosuspend_expiration(struct device *dev) +{ + int autosuspend_delay; + long elapsed; + unsigned long last_busy; + unsigned long expires = 0; + + if (!dev->power.use_autosuspend) + goto out; + + autosuspend_delay = ACCESS_ONCE(dev->power.autosuspend_delay); + if (autosuspend_delay < 0) + goto out; + + last_busy = ACCESS_ONCE(dev->power.last_busy); + elapsed = jiffies - last_busy; + if (elapsed < 0) + goto out; /* jiffies has wrapped around. */ + + /* + * If the autosuspend_delay is >= 1 second, align the timer by rounding + * up to the nearest second. + */ + expires = last_busy + msecs_to_jiffies(autosuspend_delay); + if (autosuspend_delay >= 1000) + expires = round_jiffies(expires); + expires += !expires; + if (elapsed >= expires - last_busy) + expires = 0; /* Already expired. */ + + out: + return expires; +} +EXPORT_SYMBOL_GPL(pm_runtime_autosuspend_expiration); + +/** + * rpm_check_suspend_allowed - Test whether a device may be suspended. + * @dev: Device to test. + */ +static int rpm_check_suspend_allowed(struct device *dev) +{ + int retval = 0; + + if (dev->power.runtime_error) + retval = -EINVAL; + else if (atomic_read(&dev->power.usage_count) > 0 + || dev->power.disable_depth > 0) + retval = -EAGAIN; + else if (!pm_children_suspended(dev)) + retval = -EBUSY; + + /* Pending resume requests take precedence over suspends. */ + else if ((dev->power.deferred_resume + && dev->power.runtime_status == RPM_SUSPENDING) + || (dev->power.request_pending + && dev->power.request == RPM_REQ_RESUME)) + retval = -EAGAIN; + else if (dev->power.runtime_status == RPM_SUSPENDED) + retval = 1; + + return retval; +} + +/** + * rpm_idle - Notify device bus type if the device can be suspended. + * @dev: Device to notify the bus type about. + * @rpmflags: Flag bits. + * + * Check if the device's run-time PM status allows it to be suspended. If + * another idle notification has been started earlier, return immediately. If + * the RPM_ASYNC flag is set then queue an idle-notification request; otherwise + * run the ->runtime_idle() callback directly. + * + * This function must be called under dev->power.lock with interrupts disabled. + */ +static int rpm_idle(struct device *dev, int rpmflags) +{ + int (*callback)(struct device *); + int retval; + + retval = rpm_check_suspend_allowed(dev); + if (retval < 0) + ; /* Conditions are wrong. */ + + /* Idle notifications are allowed only in the RPM_ACTIVE state. */ + else if (dev->power.runtime_status != RPM_ACTIVE) + retval = -EAGAIN; + + /* + * Any pending request other than an idle notification takes + * precedence over us, except that the timer may be running. + */ + else if (dev->power.request_pending && + dev->power.request > RPM_REQ_IDLE) + retval = -EAGAIN; + + /* Act as though RPM_NOWAIT is always set. */ + else if (dev->power.idle_notification) + retval = -EINPROGRESS; + if (retval) + goto out; + + /* Pending requests need to be canceled. */ + dev->power.request = RPM_REQ_NONE; + + if (dev->power.no_callbacks) { + /* Assume ->runtime_idle() callback would have suspended. */ + retval = rpm_suspend(dev, rpmflags); + goto out; + } + + /* Carry out an asynchronous or a synchronous idle notification. */ + if (rpmflags & RPM_ASYNC) { + dev->power.request = RPM_REQ_IDLE; + if (!dev->power.request_pending) { + dev->power.request_pending = true; + queue_work(pm_wq, &dev->power.work); + } + goto out; + } + + dev->power.idle_notification = true; + + if (dev->pwr_domain) + callback = dev->pwr_domain->ops.runtime_idle; + else if (dev->type && dev->type->pm) + callback = dev->type->pm->runtime_idle; + else if (dev->class && dev->class->pm) + callback = dev->class->pm->runtime_idle; + else if (dev->bus && dev->bus->pm) + callback = dev->bus->pm->runtime_idle; + else + callback = NULL; + + if (callback) { + spin_unlock_irq(&dev->power.lock); + + callback(dev); + + spin_lock_irq(&dev->power.lock); + } + + dev->power.idle_notification = false; + wake_up_all(&dev->power.wait_queue); + + out: + return retval; +} + +/** + * rpm_callback - Run a given runtime PM callback for a given device. + * @cb: Runtime PM callback to run. + * @dev: Device to run the callback for. + */ +static int rpm_callback(int (*cb)(struct device *), struct device *dev) + __releases(&dev->power.lock) __acquires(&dev->power.lock) +{ + int retval; + + if (!cb) + return -ENOSYS; + + if (dev->power.irq_safe) { + retval = cb(dev); + } else { + spin_unlock_irq(&dev->power.lock); + + retval = cb(dev); + + spin_lock_irq(&dev->power.lock); + } + dev->power.runtime_error = retval; + return retval; +} + +/** + * rpm_suspend - Carry out run-time suspend of given device. + * @dev: Device to suspend. + * @rpmflags: Flag bits. + * + * Check if the device's run-time PM status allows it to be suspended. If + * another suspend has been started earlier, either return immediately or wait + * for it to finish, depending on the RPM_NOWAIT and RPM_ASYNC flags. Cancel a + * pending idle notification. If the RPM_ASYNC flag is set then queue a + * suspend request; otherwise run the ->runtime_suspend() callback directly. + * If a deferred resume was requested while the callback was running then carry + * it out; otherwise send an idle notification for the device (if the suspend + * failed) or for its parent (if the suspend succeeded). + * If ->runtime_suspend failed with -EAGAIN or -EBUSY, and if the RPM_AUTO + * flag is set and the next autosuspend-delay expiration time is in the + * future, schedule another autosuspend attempt. + * + * This function must be called under dev->power.lock with interrupts disabled. + */ +static int rpm_suspend(struct device *dev, int rpmflags) + __releases(&dev->power.lock) __acquires(&dev->power.lock) +{ + int (*callback)(struct device *); + struct device *parent = NULL; + int retval; + + dev_dbg(dev, "%s flags 0x%x\n", __func__, rpmflags); + + repeat: + retval = rpm_check_suspend_allowed(dev); + + if (retval < 0) + ; /* Conditions are wrong. */ + + /* Synchronous suspends are not allowed in the RPM_RESUMING state. */ + else if (dev->power.runtime_status == RPM_RESUMING && + !(rpmflags & RPM_ASYNC)) + retval = -EAGAIN; + if (retval) + goto out; + + /* If the autosuspend_delay time hasn't expired yet, reschedule. */ + if ((rpmflags & RPM_AUTO) + && dev->power.runtime_status != RPM_SUSPENDING) { + unsigned long expires = pm_runtime_autosuspend_expiration(dev); + + if (expires != 0) { + /* Pending requests need to be canceled. */ + dev->power.request = RPM_REQ_NONE; + + /* + * Optimization: If the timer is already running and is + * set to expire at or before the autosuspend delay, + * avoid the overhead of resetting it. Just let it + * expire; pm_suspend_timer_fn() will take care of the + * rest. + */ + if (!(dev->power.timer_expires && time_before_eq( + dev->power.timer_expires, expires))) { + dev->power.timer_expires = expires; + mod_timer(&dev->power.suspend_timer, expires); + } + dev->power.timer_autosuspends = 1; + goto out; + } + } + + /* Other scheduled or pending requests need to be canceled. */ + pm_runtime_cancel_pending(dev); + + if (dev->power.runtime_status == RPM_SUSPENDING) { + DEFINE_WAIT(wait); + + if (rpmflags & (RPM_ASYNC | RPM_NOWAIT)) { + retval = -EINPROGRESS; + goto out; + } + + /* Wait for the other suspend running in parallel with us. */ + for (;;) { + prepare_to_wait(&dev->power.wait_queue, &wait, + TASK_UNINTERRUPTIBLE); + if (dev->power.runtime_status != RPM_SUSPENDING) + break; + + spin_unlock_irq(&dev->power.lock); + + schedule(); + + spin_lock_irq(&dev->power.lock); + } + finish_wait(&dev->power.wait_queue, &wait); + goto repeat; + } + + dev->power.deferred_resume = false; + if (dev->power.no_callbacks) + goto no_callback; /* Assume success. */ + + /* Carry out an asynchronous or a synchronous suspend. */ + if (rpmflags & RPM_ASYNC) { + dev->power.request = (rpmflags & RPM_AUTO) ? + RPM_REQ_AUTOSUSPEND : RPM_REQ_SUSPEND; + if (!dev->power.request_pending) { + dev->power.request_pending = true; + queue_work(pm_wq, &dev->power.work); + } + goto out; + } + + __update_runtime_status(dev, RPM_SUSPENDING); + + if (dev->pwr_domain) + callback = dev->pwr_domain->ops.runtime_suspend; + else if (dev->type && dev->type->pm) + callback = dev->type->pm->runtime_suspend; + else if (dev->class && dev->class->pm) + callback = dev->class->pm->runtime_suspend; + else if (dev->bus && dev->bus->pm) + callback = dev->bus->pm->runtime_suspend; + else + callback = NULL; + + retval = rpm_callback(callback, dev); + if (retval) { + __update_runtime_status(dev, RPM_ACTIVE); + dev->power.deferred_resume = 0; + if (retval == -EAGAIN || retval == -EBUSY) { + dev->power.runtime_error = 0; + + /* + * If the callback routine failed an autosuspend, and + * if the last_busy time has been updated so that there + * is a new autosuspend expiration time, automatically + * reschedule another autosuspend. + */ + if ((rpmflags & RPM_AUTO) && + pm_runtime_autosuspend_expiration(dev) != 0) + goto repeat; + } else { + pm_runtime_cancel_pending(dev); + } + } else { + no_callback: + __update_runtime_status(dev, RPM_SUSPENDED); + pm_runtime_deactivate_timer(dev); + + if (dev->parent) { + parent = dev->parent; + atomic_add_unless(&parent->power.child_count, -1, 0); + } + } + wake_up_all(&dev->power.wait_queue); + + if (dev->power.deferred_resume) { + rpm_resume(dev, 0); + retval = -EAGAIN; + goto out; + } + + /* Maybe the parent is now able to suspend. */ + if (parent && !parent->power.ignore_children && !dev->power.irq_safe) { + spin_unlock(&dev->power.lock); + + spin_lock(&parent->power.lock); + rpm_idle(parent, RPM_ASYNC); + spin_unlock(&parent->power.lock); + + spin_lock(&dev->power.lock); + } + + out: + dev_dbg(dev, "%s returns %d\n", __func__, retval); + + return retval; +} + +/** + * rpm_resume - Carry out run-time resume of given device. + * @dev: Device to resume. + * @rpmflags: Flag bits. + * + * Check if the device's run-time PM status allows it to be resumed. Cancel + * any scheduled or pending requests. If another resume has been started + * earlier, either return immediately or wait for it to finish, depending on the + * RPM_NOWAIT and RPM_ASYNC flags. Similarly, if there's a suspend running in + * parallel with this function, either tell the other process to resume after + * suspending (deferred_resume) or wait for it to finish. If the RPM_ASYNC + * flag is set then queue a resume request; otherwise run the + * ->runtime_resume() callback directly. Queue an idle notification for the + * device if the resume succeeded. + * + * This function must be called under dev->power.lock with interrupts disabled. + */ +static int rpm_resume(struct device *dev, int rpmflags) + __releases(&dev->power.lock) __acquires(&dev->power.lock) +{ + int (*callback)(struct device *); + struct device *parent = NULL; + int retval = 0; + + dev_dbg(dev, "%s flags 0x%x\n", __func__, rpmflags); + + repeat: + if (dev->power.runtime_error) + retval = -EINVAL; + else if (dev->power.disable_depth > 0) + retval = -EAGAIN; + if (retval) + goto out; + + /* + * Other scheduled or pending requests need to be canceled. Small + * optimization: If an autosuspend timer is running, leave it running + * rather than cancelling it now only to restart it again in the near + * future. + */ + dev->power.request = RPM_REQ_NONE; + if (!dev->power.timer_autosuspends) + pm_runtime_deactivate_timer(dev); + + if (dev->power.runtime_status == RPM_ACTIVE) { + retval = 1; + goto out; + } + + if (dev->power.runtime_status == RPM_RESUMING + || dev->power.runtime_status == RPM_SUSPENDING) { + DEFINE_WAIT(wait); + + if (rpmflags & (RPM_ASYNC | RPM_NOWAIT)) { + if (dev->power.runtime_status == RPM_SUSPENDING) + dev->power.deferred_resume = true; + else + retval = -EINPROGRESS; + goto out; + } + + /* Wait for the operation carried out in parallel with us. */ + for (;;) { + prepare_to_wait(&dev->power.wait_queue, &wait, + TASK_UNINTERRUPTIBLE); + if (dev->power.runtime_status != RPM_RESUMING + && dev->power.runtime_status != RPM_SUSPENDING) + break; + + spin_unlock_irq(&dev->power.lock); + + schedule(); + + spin_lock_irq(&dev->power.lock); + } + finish_wait(&dev->power.wait_queue, &wait); + goto repeat; + } + + /* + * See if we can skip waking up the parent. This is safe only if + * power.no_callbacks is set, because otherwise we don't know whether + * the resume will actually succeed. + */ + if (dev->power.no_callbacks && !parent && dev->parent) { + spin_lock_nested(&dev->parent->power.lock, SINGLE_DEPTH_NESTING); + if (dev->parent->power.disable_depth > 0 + || dev->parent->power.ignore_children + || dev->parent->power.runtime_status == RPM_ACTIVE) { + atomic_inc(&dev->parent->power.child_count); + spin_unlock(&dev->parent->power.lock); + goto no_callback; /* Assume success. */ + } + spin_unlock(&dev->parent->power.lock); + } + + /* Carry out an asynchronous or a synchronous resume. */ + if (rpmflags & RPM_ASYNC) { + dev->power.request = RPM_REQ_RESUME; + if (!dev->power.request_pending) { + dev->power.request_pending = true; + queue_work(pm_wq, &dev->power.work); + } + retval = 0; + goto out; + } + + if (!parent && dev->parent) { + /* + * Increment the parent's usage counter and resume it if + * necessary. Not needed if dev is irq-safe; then the + * parent is permanently resumed. + */ + parent = dev->parent; + if (dev->power.irq_safe) + goto skip_parent; + spin_unlock(&dev->power.lock); + + pm_runtime_get_noresume(parent); + + spin_lock(&parent->power.lock); + /* + * We can resume if the parent's run-time PM is disabled or it + * is set to ignore children. + */ + if (!parent->power.disable_depth + && !parent->power.ignore_children) { + rpm_resume(parent, 0); + if (parent->power.runtime_status != RPM_ACTIVE) + retval = -EBUSY; + } + spin_unlock(&parent->power.lock); + + spin_lock(&dev->power.lock); + if (retval) + goto out; + goto repeat; + } + skip_parent: + + if (dev->power.no_callbacks) + goto no_callback; /* Assume success. */ + + __update_runtime_status(dev, RPM_RESUMING); + + if (dev->pwr_domain) + callback = dev->pwr_domain->ops.runtime_resume; + else if (dev->type && dev->type->pm) + callback = dev->type->pm->runtime_resume; + else if (dev->class && dev->class->pm) + callback = dev->class->pm->runtime_resume; + else if (dev->bus && dev->bus->pm) + callback = dev->bus->pm->runtime_resume; + else + callback = NULL; + + retval = rpm_callback(callback, dev); + if (retval) { + __update_runtime_status(dev, RPM_SUSPENDED); + pm_runtime_cancel_pending(dev); + } else { + no_callback: + __update_runtime_status(dev, RPM_ACTIVE); + if (parent) + atomic_inc(&parent->power.child_count); + } + wake_up_all(&dev->power.wait_queue); + + if (!retval) + rpm_idle(dev, RPM_ASYNC); + + out: + if (parent && !dev->power.irq_safe) { + spin_unlock_irq(&dev->power.lock); + + pm_runtime_put(parent); + + spin_lock_irq(&dev->power.lock); + } + + dev_dbg(dev, "%s returns %d\n", __func__, retval); + + return retval; +} + +/** + * pm_runtime_work - Universal run-time PM work function. + * @work: Work structure used for scheduling the execution of this function. + * + * Use @work to get the device object the work is to be done for, determine what + * is to be done and execute the appropriate run-time PM function. + */ +static void pm_runtime_work(struct work_struct *work) +{ + struct device *dev = container_of(work, struct device, power.work); + enum rpm_request req; + + spin_lock_irq(&dev->power.lock); + + if (!dev->power.request_pending) + goto out; + + req = dev->power.request; + dev->power.request = RPM_REQ_NONE; + dev->power.request_pending = false; + + switch (req) { + case RPM_REQ_NONE: + break; + case RPM_REQ_IDLE: + rpm_idle(dev, RPM_NOWAIT); + break; + case RPM_REQ_SUSPEND: + rpm_suspend(dev, RPM_NOWAIT); + break; + case RPM_REQ_AUTOSUSPEND: + rpm_suspend(dev, RPM_NOWAIT | RPM_AUTO); + break; + case RPM_REQ_RESUME: + rpm_resume(dev, RPM_NOWAIT); + break; + } + + out: + spin_unlock_irq(&dev->power.lock); +} + +/** + * pm_suspend_timer_fn - Timer function for pm_schedule_suspend(). + * @data: Device pointer passed by pm_schedule_suspend(). + * + * Check if the time is right and queue a suspend request. + */ +static void pm_suspend_timer_fn(unsigned long data) +{ + struct device *dev = (struct device *)data; + unsigned long flags; + unsigned long expires; + + spin_lock_irqsave(&dev->power.lock, flags); + + expires = dev->power.timer_expires; + /* If 'expire' is after 'jiffies' we've been called too early. */ + if (expires > 0 && !time_after(expires, jiffies)) { + dev->power.timer_expires = 0; + rpm_suspend(dev, dev->power.timer_autosuspends ? + (RPM_ASYNC | RPM_AUTO) : RPM_ASYNC); + } + + spin_unlock_irqrestore(&dev->power.lock, flags); +} + +/** + * pm_schedule_suspend - Set up a timer to submit a suspend request in future. + * @dev: Device to suspend. + * @delay: Time to wait before submitting a suspend request, in milliseconds. + */ +int pm_schedule_suspend(struct device *dev, unsigned int delay) +{ + unsigned long flags; + int retval; + + spin_lock_irqsave(&dev->power.lock, flags); + + if (!delay) { + retval = rpm_suspend(dev, RPM_ASYNC); + goto out; + } + + retval = rpm_check_suspend_allowed(dev); + if (retval) + goto out; + + /* Other scheduled or pending requests need to be canceled. */ + pm_runtime_cancel_pending(dev); + + dev->power.timer_expires = jiffies + msecs_to_jiffies(delay); + dev->power.timer_expires += !dev->power.timer_expires; + dev->power.timer_autosuspends = 0; + mod_timer(&dev->power.suspend_timer, dev->power.timer_expires); + + out: + spin_unlock_irqrestore(&dev->power.lock, flags); + + return retval; +} +EXPORT_SYMBOL_GPL(pm_schedule_suspend); + +/** + * __pm_runtime_idle - Entry point for run-time idle operations. + * @dev: Device to send idle notification for. + * @rpmflags: Flag bits. + * + * If the RPM_GET_PUT flag is set, decrement the device's usage count and + * return immediately if it is larger than zero. Then carry out an idle + * notification, either synchronous or asynchronous. + * + * This routine may be called in atomic context if the RPM_ASYNC flag is set. + */ +int __pm_runtime_idle(struct device *dev, int rpmflags) +{ + unsigned long flags; + int retval; + + might_sleep_if(!(rpmflags & RPM_ASYNC)); + + if (rpmflags & RPM_GET_PUT) { + if (!atomic_dec_and_test(&dev->power.usage_count)) + return 0; + } + + spin_lock_irqsave(&dev->power.lock, flags); + retval = rpm_idle(dev, rpmflags); + spin_unlock_irqrestore(&dev->power.lock, flags); + + return retval; +} +EXPORT_SYMBOL_GPL(__pm_runtime_idle); + +/** + * __pm_runtime_suspend - Entry point for run-time put/suspend operations. + * @dev: Device to suspend. + * @rpmflags: Flag bits. + * + * If the RPM_GET_PUT flag is set, decrement the device's usage count and + * return immediately if it is larger than zero. Then carry out a suspend, + * either synchronous or asynchronous. + * + * This routine may be called in atomic context if the RPM_ASYNC flag is set. + */ +int __pm_runtime_suspend(struct device *dev, int rpmflags) +{ + unsigned long flags; + int retval; + + might_sleep_if(!(rpmflags & RPM_ASYNC) && !dev->power.irq_safe); + + if (rpmflags & RPM_GET_PUT) { + if (!atomic_dec_and_test(&dev->power.usage_count)) + return 0; + } + + spin_lock_irqsave(&dev->power.lock, flags); + retval = rpm_suspend(dev, rpmflags); + spin_unlock_irqrestore(&dev->power.lock, flags); + + return retval; +} +EXPORT_SYMBOL_GPL(__pm_runtime_suspend); + +/** + * __pm_runtime_resume - Entry point for run-time resume operations. + * @dev: Device to resume. + * @rpmflags: Flag bits. + * + * If the RPM_GET_PUT flag is set, increment the device's usage count. Then + * carry out a resume, either synchronous or asynchronous. + * + * This routine may be called in atomic context if the RPM_ASYNC flag is set. + */ +int __pm_runtime_resume(struct device *dev, int rpmflags) +{ + unsigned long flags; + int retval; + + might_sleep_if(!(rpmflags & RPM_ASYNC) && !dev->power.irq_safe); + + if (rpmflags & RPM_GET_PUT) + atomic_inc(&dev->power.usage_count); + + spin_lock_irqsave(&dev->power.lock, flags); + retval = rpm_resume(dev, rpmflags); + spin_unlock_irqrestore(&dev->power.lock, flags); + + return retval; +} +EXPORT_SYMBOL_GPL(__pm_runtime_resume); + +/** + * __pm_runtime_set_status - Set run-time PM status of a device. + * @dev: Device to handle. + * @status: New run-time PM status of the device. + * + * If run-time PM of the device is disabled or its power.runtime_error field is + * different from zero, the status may be changed either to RPM_ACTIVE, or to + * RPM_SUSPENDED, as long as that reflects the actual state of the device. + * However, if the device has a parent and the parent is not active, and the + * parent's power.ignore_children flag is unset, the device's status cannot be + * set to RPM_ACTIVE, so -EBUSY is returned in that case. + * + * If successful, __pm_runtime_set_status() clears the power.runtime_error field + * and the device parent's counter of unsuspended children is modified to + * reflect the new status. If the new status is RPM_SUSPENDED, an idle + * notification request for the parent is submitted. + */ +int __pm_runtime_set_status(struct device *dev, unsigned int status) +{ + struct device *parent = dev->parent; + unsigned long flags; + bool notify_parent = false; + int error = 0; + + if (status != RPM_ACTIVE && status != RPM_SUSPENDED) + return -EINVAL; + + spin_lock_irqsave(&dev->power.lock, flags); + + if (!dev->power.runtime_error && !dev->power.disable_depth) { + error = -EAGAIN; + goto out; + } + + if (dev->power.runtime_status == status) + goto out_set; + + if (status == RPM_SUSPENDED) { + /* It always is possible to set the status to 'suspended'. */ + if (parent) { + atomic_add_unless(&parent->power.child_count, -1, 0); + notify_parent = !parent->power.ignore_children; + } + goto out_set; + } + + if (parent) { + spin_lock_nested(&parent->power.lock, SINGLE_DEPTH_NESTING); + + /* + * It is invalid to put an active child under a parent that is + * not active, has run-time PM enabled and the + * 'power.ignore_children' flag unset. + */ + if (!parent->power.disable_depth + && !parent->power.ignore_children + && parent->power.runtime_status != RPM_ACTIVE) + error = -EBUSY; + else if (dev->power.runtime_status == RPM_SUSPENDED) + atomic_inc(&parent->power.child_count); + + spin_unlock(&parent->power.lock); + + if (error) + goto out; + } + + out_set: + __update_runtime_status(dev, status); + dev->power.runtime_error = 0; + out: + spin_unlock_irqrestore(&dev->power.lock, flags); + + if (notify_parent) + pm_request_idle(parent); + + return error; +} +EXPORT_SYMBOL_GPL(__pm_runtime_set_status); + +/** + * __pm_runtime_barrier - Cancel pending requests and wait for completions. + * @dev: Device to handle. + * + * Flush all pending requests for the device from pm_wq and wait for all + * run-time PM operations involving the device in progress to complete. + * + * Should be called under dev->power.lock with interrupts disabled. + */ +static void __pm_runtime_barrier(struct device *dev) +{ + pm_runtime_deactivate_timer(dev); + + if (dev->power.request_pending) { + dev->power.request = RPM_REQ_NONE; + spin_unlock_irq(&dev->power.lock); + + cancel_work_sync(&dev->power.work); + + spin_lock_irq(&dev->power.lock); + dev->power.request_pending = false; + } + + if (dev->power.runtime_status == RPM_SUSPENDING + || dev->power.runtime_status == RPM_RESUMING + || dev->power.idle_notification) { + DEFINE_WAIT(wait); + + /* Suspend, wake-up or idle notification in progress. */ + for (;;) { + prepare_to_wait(&dev->power.wait_queue, &wait, + TASK_UNINTERRUPTIBLE); + if (dev->power.runtime_status != RPM_SUSPENDING + && dev->power.runtime_status != RPM_RESUMING + && !dev->power.idle_notification) + break; + spin_unlock_irq(&dev->power.lock); + + schedule(); + + spin_lock_irq(&dev->power.lock); + } + finish_wait(&dev->power.wait_queue, &wait); + } +} + +/** + * pm_runtime_barrier - Flush pending requests and wait for completions. + * @dev: Device to handle. + * + * Prevent the device from being suspended by incrementing its usage counter and + * if there's a pending resume request for the device, wake the device up. + * Next, make sure that all pending requests for the device have been flushed + * from pm_wq and wait for all run-time PM operations involving the device in + * progress to complete. + * + * Return value: + * 1, if there was a resume request pending and the device had to be woken up, + * 0, otherwise + */ +int pm_runtime_barrier(struct device *dev) +{ + int retval = 0; + + pm_runtime_get_noresume(dev); + spin_lock_irq(&dev->power.lock); + + if (dev->power.request_pending + && dev->power.request == RPM_REQ_RESUME) { + rpm_resume(dev, 0); + retval = 1; + } + + __pm_runtime_barrier(dev); + + spin_unlock_irq(&dev->power.lock); + pm_runtime_put_noidle(dev); + + return retval; +} +EXPORT_SYMBOL_GPL(pm_runtime_barrier); + +/** + * __pm_runtime_disable - Disable run-time PM of a device. + * @dev: Device to handle. + * @check_resume: If set, check if there's a resume request for the device. + * + * Increment power.disable_depth for the device and if was zero previously, + * cancel all pending run-time PM requests for the device and wait for all + * operations in progress to complete. The device can be either active or + * suspended after its run-time PM has been disabled. + * + * If @check_resume is set and there's a resume request pending when + * __pm_runtime_disable() is called and power.disable_depth is zero, the + * function will wake up the device before disabling its run-time PM. + */ +void __pm_runtime_disable(struct device *dev, bool check_resume) +{ + might_sleep(); + spin_lock_irq(&dev->power.lock); + + if (dev->power.disable_depth > 0) { + dev->power.disable_depth++; + goto out; + } + + /* + * Wake up the device if there's a resume request pending, because that + * means there probably is some I/O to process and disabling run-time PM + * shouldn't prevent the device from processing the I/O. + */ + if (check_resume && dev->power.request_pending + && dev->power.request == RPM_REQ_RESUME) { + /* + * Prevent suspends and idle notifications from being carried + * out after we have woken up the device. + */ + pm_runtime_get_noresume(dev); + + rpm_resume(dev, 0); + + pm_runtime_put_noidle(dev); + } + + if (!dev->power.disable_depth++) + __pm_runtime_barrier(dev); + + out: + spin_unlock_irq(&dev->power.lock); +} +EXPORT_SYMBOL_GPL(__pm_runtime_disable); + +/** + * pm_runtime_enable - Enable run-time PM of a device. + * @dev: Device to handle. + */ +void pm_runtime_enable(struct device *dev) +{ + unsigned long flags; + + spin_lock_irqsave(&dev->power.lock, flags); + + if (dev->power.disable_depth > 0) + dev->power.disable_depth--; + else + dev_warn(dev, "Unbalanced %s!\n", __func__); + + spin_unlock_irqrestore(&dev->power.lock, flags); +} +EXPORT_SYMBOL_GPL(pm_runtime_enable); + +/** + * pm_runtime_forbid - Block run-time PM of a device. + * @dev: Device to handle. + * + * Increase the device's usage count and clear its power.runtime_auto flag, + * so that it cannot be suspended at run time until pm_runtime_allow() is called + * for it. + */ +void pm_runtime_forbid(struct device *dev) +{ + spin_lock_irq(&dev->power.lock); + if (!dev->power.runtime_auto) + goto out; + + dev->power.runtime_auto = false; + atomic_inc(&dev->power.usage_count); + rpm_resume(dev, 0); + + out: + spin_unlock_irq(&dev->power.lock); +} +EXPORT_SYMBOL_GPL(pm_runtime_forbid); + +/** + * pm_runtime_allow - Unblock run-time PM of a device. + * @dev: Device to handle. + * + * Decrease the device's usage count and set its power.runtime_auto flag. + */ +void pm_runtime_allow(struct device *dev) +{ + spin_lock_irq(&dev->power.lock); + if (dev->power.runtime_auto) + goto out; + + dev->power.runtime_auto = true; + if (atomic_dec_and_test(&dev->power.usage_count)) + rpm_idle(dev, RPM_AUTO); + + out: + spin_unlock_irq(&dev->power.lock); +} +EXPORT_SYMBOL_GPL(pm_runtime_allow); + +/** + * pm_runtime_no_callbacks - Ignore run-time PM callbacks for a device. + * @dev: Device to handle. + * + * Set the power.no_callbacks flag, which tells the PM core that this + * device is power-managed through its parent and has no run-time PM + * callbacks of its own. The run-time sysfs attributes will be removed. + */ +void pm_runtime_no_callbacks(struct device *dev) +{ + spin_lock_irq(&dev->power.lock); + dev->power.no_callbacks = 1; + spin_unlock_irq(&dev->power.lock); + if (device_is_registered(dev)) + rpm_sysfs_remove(dev); +} +EXPORT_SYMBOL_GPL(pm_runtime_no_callbacks); + +/** + * pm_runtime_irq_safe - Leave interrupts disabled during callbacks. + * @dev: Device to handle + * + * Set the power.irq_safe flag, which tells the PM core that the + * ->runtime_suspend() and ->runtime_resume() callbacks for this device should + * always be invoked with the spinlock held and interrupts disabled. It also + * causes the parent's usage counter to be permanently incremented, preventing + * the parent from runtime suspending -- otherwise an irq-safe child might have + * to wait for a non-irq-safe parent. + */ +void pm_runtime_irq_safe(struct device *dev) +{ + if (dev->parent) + pm_runtime_get_sync(dev->parent); + spin_lock_irq(&dev->power.lock); + dev->power.irq_safe = 1; + spin_unlock_irq(&dev->power.lock); +} +EXPORT_SYMBOL_GPL(pm_runtime_irq_safe); + +/** + * update_autosuspend - Handle a change to a device's autosuspend settings. + * @dev: Device to handle. + * @old_delay: The former autosuspend_delay value. + * @old_use: The former use_autosuspend value. + * + * Prevent runtime suspend if the new delay is negative and use_autosuspend is + * set; otherwise allow it. Send an idle notification if suspends are allowed. + * + * This function must be called under dev->power.lock with interrupts disabled. + */ +static void update_autosuspend(struct device *dev, int old_delay, int old_use) +{ + int delay = dev->power.autosuspend_delay; + + /* Should runtime suspend be prevented now? */ + if (dev->power.use_autosuspend && delay < 0) { + + /* If it used to be allowed then prevent it. */ + if (!old_use || old_delay >= 0) { + atomic_inc(&dev->power.usage_count); + rpm_resume(dev, 0); + } + } + + /* Runtime suspend should be allowed now. */ + else { + + /* If it used to be prevented then allow it. */ + if (old_use && old_delay < 0) + atomic_dec(&dev->power.usage_count); + + /* Maybe we can autosuspend now. */ + rpm_idle(dev, RPM_AUTO); + } +} + +/** + * pm_runtime_set_autosuspend_delay - Set a device's autosuspend_delay value. + * @dev: Device to handle. + * @delay: Value of the new delay in milliseconds. + * + * Set the device's power.autosuspend_delay value. If it changes to negative + * and the power.use_autosuspend flag is set, prevent run-time suspends. If it + * changes the other way, allow run-time suspends. + */ +void pm_runtime_set_autosuspend_delay(struct device *dev, int delay) +{ + int old_delay, old_use; + + spin_lock_irq(&dev->power.lock); + old_delay = dev->power.autosuspend_delay; + old_use = dev->power.use_autosuspend; + dev->power.autosuspend_delay = delay; + update_autosuspend(dev, old_delay, old_use); + spin_unlock_irq(&dev->power.lock); +} +EXPORT_SYMBOL_GPL(pm_runtime_set_autosuspend_delay); + +/** + * __pm_runtime_use_autosuspend - Set a device's use_autosuspend flag. + * @dev: Device to handle. + * @use: New value for use_autosuspend. + * + * Set the device's power.use_autosuspend flag, and allow or prevent run-time + * suspends as needed. + */ +void __pm_runtime_use_autosuspend(struct device *dev, bool use) +{ + int old_delay, old_use; + + might_sleep(); + + spin_lock_irq(&dev->power.lock); + old_delay = dev->power.autosuspend_delay; + old_use = dev->power.use_autosuspend; + dev->power.use_autosuspend = use; + update_autosuspend(dev, old_delay, old_use); + spin_unlock_irq(&dev->power.lock); +} +EXPORT_SYMBOL_GPL(__pm_runtime_use_autosuspend); + +/** + * pm_runtime_init - Initialize run-time PM fields in given device object. + * @dev: Device object to initialize. + */ +void pm_runtime_init(struct device *dev) +{ + dev->power.runtime_status = RPM_SUSPENDED; + dev->power.idle_notification = false; + + dev->power.disable_depth = 1; + atomic_set(&dev->power.usage_count, 0); + + dev->power.runtime_error = 0; + + atomic_set(&dev->power.child_count, 0); + pm_suspend_ignore_children(dev, false); + dev->power.runtime_auto = true; + + dev->power.request_pending = false; + dev->power.request = RPM_REQ_NONE; + dev->power.deferred_resume = false; + dev->power.accounting_timestamp = jiffies; + INIT_WORK(&dev->power.work, pm_runtime_work); + + dev->power.timer_expires = 0; + setup_timer(&dev->power.suspend_timer, pm_suspend_timer_fn, + (unsigned long)dev); + + init_waitqueue_head(&dev->power.wait_queue); +} + +/** + * pm_runtime_remove - Prepare for removing a device from device hierarchy. + * @dev: Device object being removed from device hierarchy. + */ +void pm_runtime_remove(struct device *dev) +{ + __pm_runtime_disable(dev, false); + + /* Change the status back to 'suspended' to match the initial status. */ + if (dev->power.runtime_status == RPM_ACTIVE) + pm_runtime_set_suspended(dev); + if (dev->power.irq_safe && dev->parent) + pm_runtime_put_sync(dev->parent); +} diff --git a/drivers/base/power/sysfs.c b/drivers/base/power/sysfs.c new file mode 100644 index 00000000..a9f5b897 --- /dev/null +++ b/drivers/base/power/sysfs.c @@ -0,0 +1,538 @@ +/* + * drivers/base/power/sysfs.c - sysfs entries for device PM + */ + +#include <linux/device.h> +#include <linux/string.h> +#include <linux/pm_runtime.h> +#include <asm/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; + 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 + return -EINVAL; + 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; + + pm_runtime_set_autosuspend_delay(dev, delay); + return n; +} + +static DEVICE_ATTR(autosuspend_delay_ms, 0644, autosuspend_delay_ms_show, + autosuspend_delay_ms_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_hit_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->hit_count; + enabled = true; + } + spin_unlock_irq(&dev->power.lock); + return enabled ? sprintf(buf, "%lu\n", count) : sprintf(buf, "\n"); +} + +static DEVICE_ATTR(wakeup_hit_count, 0444, wakeup_hit_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); +#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 + +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 /* 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_hit_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, +#endif + NULL, +}; +static struct attribute_group pm_wakeup_attr_group = { + .name = power_group_name, + .attrs = wakeup_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, +}; + +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); +} + +void rpm_sysfs_remove(struct device *dev) +{ + sysfs_unmerge_group(&dev->kobj, &pm_runtime_attr_group); +} + +void dpm_sysfs_remove(struct device *dev) +{ + rpm_sysfs_remove(dev); + sysfs_unmerge_group(&dev->kobj, &pm_wakeup_attr_group); + sysfs_remove_group(&dev->kobj, &pm_attr_group); +} diff --git a/drivers/base/power/trace.c b/drivers/base/power/trace.c new file mode 100644 index 00000000..c80e138b --- /dev/null +++ b/drivers/base/power/trace.c @@ -0,0 +1,265 @@ +/* + * 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/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("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); diff --git a/drivers/base/power/wakeup.c b/drivers/base/power/wakeup.c new file mode 100644 index 00000000..84f7c7d5 --- /dev/null +++ b/drivers/base/power/wakeup.c @@ -0,0 +1,746 @@ +/* + * 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/suspend.h> +#include <linux/seq_file.h> +#include <linux/debugfs.h> + +#include "power.h" + +#define TIMEOUT 100 + +/* + * 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; + +/* + * 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); + +/** + * 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 = kzalloc(sizeof(*ws), GFP_KERNEL); + if (!ws) + return NULL; + + spin_lock_init(&ws->lock); + if (name) + ws->name = kstrdup(name, GFP_KERNEL); + + return ws; +} +EXPORT_SYMBOL_GPL(wakeup_source_create); + +/** + * wakeup_source_destroy - Destroy a struct wakeup_source object. + * @ws: Wakeup source to destroy. + */ +void wakeup_source_destroy(struct wakeup_source *ws) +{ + if (!ws) + return; + + spin_lock_irq(&ws->lock); + while (ws->active) { + spin_unlock_irq(&ws->lock); + + schedule_timeout_interruptible(msecs_to_jiffies(TIMEOUT)); + + spin_lock_irq(&ws->lock); + } + spin_unlock_irq(&ws->lock); + + 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) +{ + if (WARN_ON(!ws)) + return; + + setup_timer(&ws->timer, pm_wakeup_timer_fn, (unsigned long)ws); + ws->active = false; + + spin_lock_irq(&events_lock); + list_add_rcu(&ws->entry, &wakeup_sources); + spin_unlock_irq(&events_lock); +} +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) +{ + if (WARN_ON(!ws)) + return; + + spin_lock_irq(&events_lock); + list_del_rcu(&ws->entry); + spin_unlock_irq(&events_lock); + 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) +{ + 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. + */ +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) +{ + ws->active = true; + ws->active_count++; + ws->timer_expires = jiffies; + ws->last_time = ktime_get(); + + /* Increment the counter of events in progress. */ + atomic_inc(&combined_event_count); +} + +/** + * __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); + ws->event_count++; + if (!ws->active) + wakeup_source_activate(ws); + 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); + +/** + * 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) +{ + 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; + + del_timer(&ws->timer); + + /* + * Increment the counter of registered wakeup events and decrement the + * couter of wakeup events in progress simultaneously. + */ + atomic_add(MAX_IN_PROGRESS, &combined_event_count); +} + +/** + * __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 __pm_relax() for the wakeup source whose address is stored in @data. + */ +static void pm_wakeup_timer_fn(unsigned long data) +{ + __pm_relax((struct wakeup_source *)data); +} + +/** + * __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); + + ws->event_count++; + if (!ws->active) + wakeup_source_activate(ws); + + if (!msec) { + wakeup_source_deactivate(ws); + goto unlock; + } + + expires = jiffies + msecs_to_jiffies(msec); + if (!expires) + expires = 1; + + if (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); + +/** + * pm_wakeup_update_hit_counts - Update hit counts of all active wakeup sources. + */ +static void pm_wakeup_update_hit_counts(void) +{ + unsigned long flags; + struct wakeup_source *ws; + + rcu_read_lock(); + list_for_each_entry_rcu(ws, &wakeup_sources, entry) { + spin_lock_irqsave(&ws->lock, flags); + if (ws->active) + ws->hit_count++; + spin_unlock_irqrestore(&ws->lock, flags); + } + rcu_read_unlock(); +} + +/** + * 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) + pm_wakeup_update_hit_counts(); + return ret; +} + +/** + * pm_get_wakeup_count - Read the number of registered wakeup events. + * @count: Address to store the value at. + * + * Store the number of registered wakeup events at the address in @count. Block + * if the current number of wakeup events being processed is nonzero. + * + * Return 'false' if the wait for the number of wakeup events being processed to + * drop down to zero has been interrupted by a signal (and the current number + * of wakeup events being processed is still nonzero). Otherwise return 'true'. + */ +bool pm_get_wakeup_count(unsigned int *count) +{ + unsigned int cnt, inpr; + + for (;;) { + split_counters(&cnt, &inpr); + if (inpr == 0 || signal_pending(current)) + break; + pm_wakeup_update_hit_counts(); + schedule_timeout_interruptible(msecs_to_jiffies(TIMEOUT)); + } + + 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; + + events_check_enabled = false; + spin_lock_irq(&events_lock); + split_counters(&cnt, &inpr); + if (cnt == count && inpr == 0) { + saved_count = count; + events_check_enabled = true; + } + spin_unlock_irq(&events_lock); + if (!events_check_enabled) + pm_wakeup_update_hit_counts(); + return events_check_enabled; +} + +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; + int ret; + + spin_lock_irqsave(&ws->lock, flags); + + total_time = ws->total_time; + max_time = ws->max_time; + active_count = ws->active_count; + if (ws->active) { + active_time = ktime_sub(ktime_get(), ws->last_time); + total_time = ktime_add(total_time, active_time); + if (active_time.tv64 > max_time.tv64) + max_time = active_time; + } else { + active_time = ktime_set(0, 0); + } + + ret = seq_printf(m, "%-12s\t%lu\t\t%lu\t\t%lu\t\t" + "%lld\t\t%lld\t\t%lld\t\t%lld\n", + ws->name, active_count, ws->event_count, ws->hit_count, + ktime_to_ms(active_time), ktime_to_ms(total_time), + ktime_to_ms(max_time), ktime_to_ms(ws->last_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\thit_count\t" + "active_since\ttotal_time\tmax_time\tlast_change\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); diff --git a/drivers/base/sys.c b/drivers/base/sys.c new file mode 100644 index 00000000..9dff77bf --- /dev/null +++ b/drivers/base/sys.c @@ -0,0 +1,391 @@ +/* + * sys.c - pseudo-bus for system 'devices' (cpus, PICs, timers, etc) + * + * Copyright (c) 2002-3 Patrick Mochel + * 2002-3 Open Source Development Lab + * + * This file is released under the GPLv2 + * + * This exports a 'system' bus type. + * By default, a 'sys' bus gets added to the root of the system. There will + * always be core system devices. Devices can use sysdev_register() to + * add themselves as children of the system bus. + */ + +#include <linux/sysdev.h> +#include <linux/err.h> +#include <linux/module.h> +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/string.h> +#include <linux/pm.h> +#include <linux/device.h> +#include <linux/mutex.h> +#include <linux/interrupt.h> + +#include "base.h" + +#define to_sysdev(k) container_of(k, struct sys_device, kobj) +#define to_sysdev_attr(a) container_of(a, struct sysdev_attribute, attr) + + +static ssize_t +sysdev_show(struct kobject *kobj, struct attribute *attr, char *buffer) +{ + struct sys_device *sysdev = to_sysdev(kobj); + struct sysdev_attribute *sysdev_attr = to_sysdev_attr(attr); + + if (sysdev_attr->show) + return sysdev_attr->show(sysdev, sysdev_attr, buffer); + return -EIO; +} + + +static ssize_t +sysdev_store(struct kobject *kobj, struct attribute *attr, + const char *buffer, size_t count) +{ + struct sys_device *sysdev = to_sysdev(kobj); + struct sysdev_attribute *sysdev_attr = to_sysdev_attr(attr); + + if (sysdev_attr->store) + return sysdev_attr->store(sysdev, sysdev_attr, buffer, count); + return -EIO; +} + +static const struct sysfs_ops sysfs_ops = { + .show = sysdev_show, + .store = sysdev_store, +}; + +static struct kobj_type ktype_sysdev = { + .sysfs_ops = &sysfs_ops, +}; + + +int sysdev_create_file(struct sys_device *s, struct sysdev_attribute *a) +{ + return sysfs_create_file(&s->kobj, &a->attr); +} + + +void sysdev_remove_file(struct sys_device *s, struct sysdev_attribute *a) +{ + sysfs_remove_file(&s->kobj, &a->attr); +} + +EXPORT_SYMBOL_GPL(sysdev_create_file); +EXPORT_SYMBOL_GPL(sysdev_remove_file); + +#define to_sysdev_class(k) container_of(k, struct sysdev_class, kset.kobj) +#define to_sysdev_class_attr(a) container_of(a, \ + struct sysdev_class_attribute, attr) + +static ssize_t sysdev_class_show(struct kobject *kobj, struct attribute *attr, + char *buffer) +{ + struct sysdev_class *class = to_sysdev_class(kobj); + struct sysdev_class_attribute *class_attr = to_sysdev_class_attr(attr); + + if (class_attr->show) + return class_attr->show(class, class_attr, buffer); + return -EIO; +} + +static ssize_t sysdev_class_store(struct kobject *kobj, struct attribute *attr, + const char *buffer, size_t count) +{ + struct sysdev_class *class = to_sysdev_class(kobj); + struct sysdev_class_attribute *class_attr = to_sysdev_class_attr(attr); + + if (class_attr->store) + return class_attr->store(class, class_attr, buffer, count); + return -EIO; +} + +static const struct sysfs_ops sysfs_class_ops = { + .show = sysdev_class_show, + .store = sysdev_class_store, +}; + +static struct kobj_type ktype_sysdev_class = { + .sysfs_ops = &sysfs_class_ops, +}; + +int sysdev_class_create_file(struct sysdev_class *c, + struct sysdev_class_attribute *a) +{ + return sysfs_create_file(&c->kset.kobj, &a->attr); +} +EXPORT_SYMBOL_GPL(sysdev_class_create_file); + +void sysdev_class_remove_file(struct sysdev_class *c, + struct sysdev_class_attribute *a) +{ + sysfs_remove_file(&c->kset.kobj, &a->attr); +} +EXPORT_SYMBOL_GPL(sysdev_class_remove_file); + +static struct kset *system_kset; + +int sysdev_class_register(struct sysdev_class *cls) +{ + int retval; + + pr_debug("Registering sysdev class '%s'\n", cls->name); + + INIT_LIST_HEAD(&cls->drivers); + memset(&cls->kset.kobj, 0x00, sizeof(struct kobject)); + cls->kset.kobj.parent = &system_kset->kobj; + cls->kset.kobj.ktype = &ktype_sysdev_class; + cls->kset.kobj.kset = system_kset; + + retval = kobject_set_name(&cls->kset.kobj, "%s", cls->name); + if (retval) + return retval; + + retval = kset_register(&cls->kset); + if (!retval && cls->attrs) + retval = sysfs_create_files(&cls->kset.kobj, + (const struct attribute **)cls->attrs); + return retval; +} + +void sysdev_class_unregister(struct sysdev_class *cls) +{ + pr_debug("Unregistering sysdev class '%s'\n", + kobject_name(&cls->kset.kobj)); + if (cls->attrs) + sysfs_remove_files(&cls->kset.kobj, + (const struct attribute **)cls->attrs); + kset_unregister(&cls->kset); +} + +EXPORT_SYMBOL_GPL(sysdev_class_register); +EXPORT_SYMBOL_GPL(sysdev_class_unregister); + +static DEFINE_MUTEX(sysdev_drivers_lock); + +/* + * @dev != NULL means that we're unwinding because some drv->add() + * failed for some reason. You need to grab sysdev_drivers_lock before + * calling this. + */ +static void __sysdev_driver_remove(struct sysdev_class *cls, + struct sysdev_driver *drv, + struct sys_device *from_dev) +{ + struct sys_device *dev = from_dev; + + list_del_init(&drv->entry); + if (!cls) + return; + + if (!drv->remove) + goto kset_put; + + if (dev) + list_for_each_entry_continue_reverse(dev, &cls->kset.list, + kobj.entry) + drv->remove(dev); + else + list_for_each_entry(dev, &cls->kset.list, kobj.entry) + drv->remove(dev); + +kset_put: + kset_put(&cls->kset); +} + +/** + * sysdev_driver_register - Register auxiliary driver + * @cls: Device class driver belongs to. + * @drv: Driver. + * + * @drv is inserted into @cls->drivers to be + * called on each operation on devices of that class. The refcount + * of @cls is incremented. + */ +int sysdev_driver_register(struct sysdev_class *cls, struct sysdev_driver *drv) +{ + struct sys_device *dev = NULL; + int err = 0; + + if (!cls) { + WARN(1, KERN_WARNING "sysdev: invalid class passed to %s!\n", + __func__); + return -EINVAL; + } + + /* Check whether this driver has already been added to a class. */ + if (drv->entry.next && !list_empty(&drv->entry)) + WARN(1, KERN_WARNING "sysdev: class %s: driver (%p) has already" + " been registered to a class, something is wrong, but " + "will forge on!\n", cls->name, drv); + + mutex_lock(&sysdev_drivers_lock); + if (cls && kset_get(&cls->kset)) { + list_add_tail(&drv->entry, &cls->drivers); + + /* If devices of this class already exist, tell the driver */ + if (drv->add) { + list_for_each_entry(dev, &cls->kset.list, kobj.entry) { + err = drv->add(dev); + if (err) + goto unwind; + } + } + } else { + err = -EINVAL; + WARN(1, KERN_ERR "%s: invalid device class\n", __func__); + } + + goto unlock; + +unwind: + __sysdev_driver_remove(cls, drv, dev); + +unlock: + mutex_unlock(&sysdev_drivers_lock); + return err; +} + +/** + * sysdev_driver_unregister - Remove an auxiliary driver. + * @cls: Class driver belongs to. + * @drv: Driver. + */ +void sysdev_driver_unregister(struct sysdev_class *cls, + struct sysdev_driver *drv) +{ + mutex_lock(&sysdev_drivers_lock); + __sysdev_driver_remove(cls, drv, NULL); + mutex_unlock(&sysdev_drivers_lock); +} +EXPORT_SYMBOL_GPL(sysdev_driver_register); +EXPORT_SYMBOL_GPL(sysdev_driver_unregister); + +/** + * sysdev_register - add a system device to the tree + * @sysdev: device in question + * + */ +int sysdev_register(struct sys_device *sysdev) +{ + int error; + struct sysdev_class *cls = sysdev->cls; + + if (!cls) + return -EINVAL; + + pr_debug("Registering sys device of class '%s'\n", + kobject_name(&cls->kset.kobj)); + + /* initialize the kobject to 0, in case it had previously been used */ + memset(&sysdev->kobj, 0x00, sizeof(struct kobject)); + + /* Make sure the kset is set */ + sysdev->kobj.kset = &cls->kset; + + /* Register the object */ + error = kobject_init_and_add(&sysdev->kobj, &ktype_sysdev, NULL, + "%s%d", kobject_name(&cls->kset.kobj), + sysdev->id); + + if (!error) { + struct sysdev_driver *drv; + + pr_debug("Registering sys device '%s'\n", + kobject_name(&sysdev->kobj)); + + mutex_lock(&sysdev_drivers_lock); + /* Generic notification is implicit, because it's that + * code that should have called us. + */ + + /* Notify class auxiliary drivers */ + list_for_each_entry(drv, &cls->drivers, entry) { + if (drv->add) + drv->add(sysdev); + } + mutex_unlock(&sysdev_drivers_lock); + kobject_uevent(&sysdev->kobj, KOBJ_ADD); + } + + return error; +} + +void sysdev_unregister(struct sys_device *sysdev) +{ + struct sysdev_driver *drv; + + mutex_lock(&sysdev_drivers_lock); + list_for_each_entry(drv, &sysdev->cls->drivers, entry) { + if (drv->remove) + drv->remove(sysdev); + } + mutex_unlock(&sysdev_drivers_lock); + + kobject_put(&sysdev->kobj); +} + +EXPORT_SYMBOL_GPL(sysdev_register); +EXPORT_SYMBOL_GPL(sysdev_unregister); + +int __init system_bus_init(void) +{ + system_kset = kset_create_and_add("system", NULL, &devices_kset->kobj); + if (!system_kset) + return -ENOMEM; + return 0; +} + +#define to_ext_attr(x) container_of(x, struct sysdev_ext_attribute, attr) + +ssize_t sysdev_store_ulong(struct sys_device *sysdev, + struct sysdev_attribute *attr, + const char *buf, size_t size) +{ + struct sysdev_ext_attribute *ea = to_ext_attr(attr); + char *end; + unsigned long new = simple_strtoul(buf, &end, 0); + if (end == buf) + return -EINVAL; + *(unsigned long *)(ea->var) = new; + /* Always return full write size even if we didn't consume all */ + return size; +} +EXPORT_SYMBOL_GPL(sysdev_store_ulong); + +ssize_t sysdev_show_ulong(struct sys_device *sysdev, + struct sysdev_attribute *attr, + char *buf) +{ + struct sysdev_ext_attribute *ea = to_ext_attr(attr); + return snprintf(buf, PAGE_SIZE, "%lx\n", *(unsigned long *)(ea->var)); +} +EXPORT_SYMBOL_GPL(sysdev_show_ulong); + +ssize_t sysdev_store_int(struct sys_device *sysdev, + struct sysdev_attribute *attr, + const char *buf, size_t size) +{ + struct sysdev_ext_attribute *ea = to_ext_attr(attr); + char *end; + long new = simple_strtol(buf, &end, 0); + if (end == buf || new > INT_MAX || new < INT_MIN) + return -EINVAL; + *(int *)(ea->var) = new; + /* Always return full write size even if we didn't consume all */ + return size; +} +EXPORT_SYMBOL_GPL(sysdev_store_int); + +ssize_t sysdev_show_int(struct sys_device *sysdev, + struct sysdev_attribute *attr, + char *buf) +{ + struct sysdev_ext_attribute *ea = to_ext_attr(attr); + return snprintf(buf, PAGE_SIZE, "%d\n", *(int *)(ea->var)); +} +EXPORT_SYMBOL_GPL(sysdev_show_int); + diff --git a/drivers/base/syscore.c b/drivers/base/syscore.c new file mode 100644 index 00000000..e8d11b66 --- /dev/null +++ b/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); +} diff --git a/drivers/base/topology.c b/drivers/base/topology.c new file mode 100644 index 00000000..f6f37a05 --- /dev/null +++ b/drivers/base/topology.c @@ -0,0 +1,197 @@ +/* + * 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/sysdev.h> +#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 SYSDEV_ATTR(_name, 0444, _func, NULL) + +#define define_one_ro(_name) \ +static SYSDEV_ATTR(_name, 0444, show_##_name, NULL) + +#define define_id_show_func(name) \ +static ssize_t show_##name(struct sys_device *dev, \ + struct sysdev_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 sys_device *dev, \ + struct sysdev_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 sys_device *dev, \ + struct sysdev_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 sys_device *dev, \ + struct sysdev_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 sys_device *dev, \ + struct sysdev_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[] = { + &attr_physical_package_id.attr, + &attr_core_id.attr, + &attr_thread_siblings.attr, + &attr_thread_siblings_list.attr, + &attr_core_siblings.attr, + &attr_core_siblings_list.attr, +#ifdef CONFIG_SCHED_BOOK + &attr_book_id.attr, + &attr_book_siblings.attr, + &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 sys_device *sys_dev = get_cpu_sysdev(cpu); + + return sysfs_create_group(&sys_dev->kobj, &topology_attr_group); +} + +static void __cpuinit topology_remove_dev(unsigned int cpu) +{ + struct sys_device *sys_dev = get_cpu_sysdev(cpu); + + sysfs_remove_group(&sys_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); diff --git a/drivers/base/transport_class.c b/drivers/base/transport_class.c new file mode 100644 index 00000000..84997efd --- /dev/null +++ b/drivers/base/transport_class.c @@ -0,0 +1,279 @@ +/* + * 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/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); |