diff options
Diffstat (limited to 'drivers/base')
30 files changed, 3804 insertions, 1278 deletions
diff --git a/drivers/base/Kconfig b/drivers/base/Kconfig index ee377270beb9..fd96345bc35c 100644 --- a/drivers/base/Kconfig +++ b/drivers/base/Kconfig @@ -3,35 +3,53 @@ menu "Generic Driver Options" config UEVENT_HELPER_PATH string "path to uevent helper" depends on HOTPLUG - default "/sbin/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 "Create a kernel maintained /dev tmpfs (EXPERIMENTAL)" - depends on HOTPLUG && SHMEM && TMPFS + bool "Maintain a devtmpfs filesystem to mount at /dev" + depends on HOTPLUG help - This creates a tmpfs filesystem, and mounts it at bootup - and mounts it at /dev. The kernel driver core creates device - nodes for all registered devices in that filesystem. All device - nodes are owned by root and have the default mode of 0600. - Userspace can add and delete the nodes as needed. This is - intended to simplify bootup, and make it possible to delay - the initial coldplug at bootup done by udev in userspace. - It should also provide a simpler way for rescue systems - to bring up a kernel with dynamic major/minor numbers. - Meaningful symlinks, permissions and device ownership must - still be handled by userspace. - If unsure, say N here. + 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" + bool "Automount devtmpfs at /dev, after the kernel mounted the rootfs" depends on DEVTMPFS help - This will mount devtmpfs at /dev if the kernel mounts the root - filesystem. It will not affect initramfs based mounting. - If unsure, say N here. + 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 @@ -53,7 +71,6 @@ config PREVENT_FIRMWARE_BUILD config FW_LOADER tristate "Userspace firmware loading support" if EMBEDDED - depends on HOTPLUG default y ---help--- This option is provided for the case where no in-kernel-tree modules diff --git a/drivers/base/Makefile b/drivers/base/Makefile index c12c7f2f2a6f..5f51c3b4451e 100644 --- a/drivers/base/Makefile +++ b/drivers/base/Makefile @@ -19,7 +19,5 @@ obj-$(CONFIG_MODULES) += module.o endif obj-$(CONFIG_SYS_HYPERVISOR) += hypervisor.o -ifeq ($(CONFIG_DEBUG_DRIVER),y) -EXTRA_CFLAGS += -DDEBUG -endif +ccflags-$(CONFIG_DEBUG_DRIVER) := -DDEBUG diff --git a/drivers/base/attribute_container.c b/drivers/base/attribute_container.c index b9cda053d3c0..8fc200b2e2c0 100644 --- a/drivers/base/attribute_container.c +++ b/drivers/base/attribute_container.c @@ -328,6 +328,7 @@ attribute_container_add_attrs(struct device *classdev) 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; diff --git a/drivers/base/bus.c b/drivers/base/bus.c index c0c5a43d9fb3..33c270a64db7 100644 --- a/drivers/base/bus.c +++ b/drivers/base/bus.c @@ -13,6 +13,7 @@ #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" @@ -70,7 +71,7 @@ static ssize_t drv_attr_store(struct kobject *kobj, struct attribute *attr, return ret; } -static struct sysfs_ops driver_sysfs_ops = { +static const struct sysfs_ops driver_sysfs_ops = { .show = drv_attr_show, .store = drv_attr_store, }; @@ -115,7 +116,7 @@ static ssize_t bus_attr_store(struct kobject *kobj, struct attribute *attr, return ret; } -static struct sysfs_ops bus_sysfs_ops = { +static const struct sysfs_ops bus_sysfs_ops = { .show = bus_attr_show, .store = bus_attr_store, }; @@ -154,7 +155,7 @@ static int bus_uevent_filter(struct kset *kset, struct kobject *kobj) return 0; } -static struct kset_uevent_ops bus_uevent_ops = { +static const struct kset_uevent_ops bus_uevent_ops = { .filter = bus_uevent_filter, }; @@ -173,10 +174,10 @@ static ssize_t driver_unbind(struct device_driver *drv, dev = bus_find_device_by_name(bus, NULL, buf); if (dev && dev->driver == drv) { if (dev->parent) /* Needed for USB */ - down(&dev->parent->sem); + device_lock(dev->parent); device_release_driver(dev); if (dev->parent) - up(&dev->parent->sem); + device_unlock(dev->parent); err = count; } put_device(dev); @@ -200,12 +201,12 @@ static ssize_t driver_bind(struct device_driver *drv, 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 */ - down(&dev->parent->sem); - down(&dev->sem); + device_lock(dev->parent); + device_lock(dev); err = driver_probe_device(drv, dev); - up(&dev->sem); + device_unlock(dev); if (dev->parent) - up(&dev->parent->sem); + device_unlock(dev->parent); if (err > 0) { /* success */ @@ -439,22 +440,6 @@ static void device_remove_attrs(struct bus_type *bus, struct device *dev) } } -#ifdef CONFIG_SYSFS_DEPRECATED -static int make_deprecated_bus_links(struct device *dev) -{ - return sysfs_create_link(&dev->kobj, - &dev->bus->p->subsys.kobj, "bus"); -} - -static void remove_deprecated_bus_links(struct device *dev) -{ - sysfs_remove_link(&dev->kobj, "bus"); -} -#else -static inline int make_deprecated_bus_links(struct device *dev) { return 0; } -static inline void remove_deprecated_bus_links(struct device *dev) { } -#endif - /** * bus_add_device - add device to bus * @dev: device being added @@ -481,15 +466,10 @@ int bus_add_device(struct device *dev) &dev->bus->p->subsys.kobj, "subsystem"); if (error) goto out_subsys; - error = make_deprecated_bus_links(dev); - if (error) - goto out_deprecated; klist_add_tail(&dev->p->knode_bus, &bus->p->klist_devices); } return 0; -out_deprecated: - sysfs_remove_link(&dev->kobj, "subsystem"); out_subsys: sysfs_remove_link(&bus->p->devices_kset->kobj, dev_name(dev)); out_id: @@ -529,7 +509,6 @@ void bus_remove_device(struct device *dev) { if (dev->bus) { sysfs_remove_link(&dev->kobj, "subsystem"); - remove_deprecated_bus_links(dev); sysfs_remove_link(&dev->bus->p->devices_kset->kobj, dev_name(dev)); device_remove_attrs(dev->bus, dev); @@ -744,10 +723,10 @@ static int __must_check bus_rescan_devices_helper(struct device *dev, if (!dev->driver) { if (dev->parent) /* Needed for USB */ - down(&dev->parent->sem); + device_lock(dev->parent); ret = device_attach(dev); if (dev->parent) - up(&dev->parent->sem); + device_unlock(dev->parent); } return ret < 0 ? ret : 0; } @@ -779,10 +758,10 @@ int device_reprobe(struct device *dev) { if (dev->driver) { if (dev->parent) /* Needed for USB */ - down(&dev->parent->sem); + device_lock(dev->parent); device_release_driver(dev); if (dev->parent) - up(&dev->parent->sem); + device_unlock(dev->parent); } return bus_rescan_devices_helper(dev, NULL); } @@ -944,8 +923,8 @@ bus_devices_fail: bus_remove_file(bus, &bus_attr_uevent); bus_uevent_fail: kset_unregister(&bus->p->subsys); - kfree(bus->p); out: + kfree(bus->p); bus->p = NULL; return retval; } diff --git a/drivers/base/class.c b/drivers/base/class.c index 161746deab4b..9c63a5687d69 100644 --- a/drivers/base/class.c +++ b/drivers/base/class.c @@ -31,7 +31,7 @@ static ssize_t class_attr_show(struct kobject *kobj, struct attribute *attr, ssize_t ret = -EIO; if (class_attr->show) - ret = class_attr->show(cp->class, buf); + ret = class_attr->show(cp->class, class_attr, buf); return ret; } @@ -43,7 +43,7 @@ static ssize_t class_attr_store(struct kobject *kobj, struct attribute *attr, ssize_t ret = -EIO; if (class_attr->store) - ret = class_attr->store(cp->class, buf, count); + ret = class_attr->store(cp->class, class_attr, buf, count); return ret; } @@ -59,9 +59,19 @@ static void class_release(struct kobject *kobj) 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 class_private *cp = to_class(kobj); + struct class *class = cp->class; + + return class->ns_type; } -static struct sysfs_ops class_sysfs_ops = { +static const struct sysfs_ops class_sysfs_ops = { .show = class_attr_show, .store = class_attr_store, }; @@ -69,6 +79,7 @@ static struct sysfs_ops class_sysfs_ops = { 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 class_subsys */ @@ -173,9 +184,9 @@ int __class_register(struct class *cls, struct lock_class_key *key) if (!cls->dev_kobj) cls->dev_kobj = sysfs_dev_char_kobj; -#if defined(CONFIG_SYSFS_DEPRECATED) && defined(CONFIG_BLOCK) +#if defined(CONFIG_BLOCK) /* let the block class directory show up in the root of sysfs */ - if (cls != &block_class) + if (!sysfs_deprecated || cls != &block_class) cp->class_subsys.kobj.kset = class_kset; #else cp->class_subsys.kobj.kset = class_kset; @@ -217,6 +228,8 @@ static void class_create_release(struct class *cls) * 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(). */ @@ -263,25 +276,6 @@ void class_destroy(struct class *cls) class_unregister(cls); } -#ifdef CONFIG_SYSFS_DEPRECATED -char *make_class_name(const char *name, struct kobject *kobj) -{ - char *class_name; - int size; - - size = strlen(name) + strlen(kobject_name(kobj)) + 2; - - class_name = kmalloc(size, GFP_KERNEL); - if (!class_name) - return NULL; - - strcpy(class_name, name); - strcat(class_name, ":"); - strcat(class_name, kobject_name(kobj)); - return class_name; -} -#endif - /** * class_dev_iter_init - initialize class device iterator * @iter: class iterator to initialize @@ -488,6 +482,16 @@ void class_interface_unregister(struct class_interface *class_intf) 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; }; diff --git a/drivers/base/core.c b/drivers/base/core.c index 282025770429..6ed645411c40 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -20,13 +20,25 @@ #include <linux/notifier.h> #include <linux/genhd.h> #include <linux/kallsyms.h> -#include <linux/semaphore.h> #include <linux/mutex.h> #include <linux/async.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; @@ -100,7 +112,7 @@ static ssize_t dev_attr_store(struct kobject *kobj, struct attribute *attr, return ret; } -static struct sysfs_ops dev_sysfs_ops = { +static const struct sysfs_ops dev_sysfs_ops = { .show = dev_attr_show, .store = dev_attr_store, }; @@ -132,9 +144,21 @@ static void device_release(struct kobject *kobj) 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, }; @@ -192,37 +216,6 @@ static int dev_uevent(struct kset *kset, struct kobject *kobj, if (dev->driver) add_uevent_var(env, "DRIVER=%s", dev->driver->name); -#ifdef CONFIG_SYSFS_DEPRECATED - if (dev->class) { - struct device *parent = dev->parent; - - /* find first bus device in parent chain */ - while (parent && !parent->bus) - parent = parent->parent; - if (parent && parent->bus) { - const char *path; - - path = kobject_get_path(&parent->kobj, GFP_KERNEL); - if (path) { - add_uevent_var(env, "PHYSDEVPATH=%s", path); - kfree(path); - } - - add_uevent_var(env, "PHYSDEVBUS=%s", parent->bus->name); - - if (parent->driver) - add_uevent_var(env, "PHYSDEVDRIVER=%s", - parent->driver->name); - } - } else if (dev->bus) { - add_uevent_var(env, "PHYSDEVBUS=%s", dev->bus->name); - - if (dev->driver) - add_uevent_var(env, "PHYSDEVDRIVER=%s", - dev->driver->name); - } -#endif - /* have the bus specific function add its stuff */ if (dev->bus && dev->bus->uevent) { retval = dev->bus->uevent(dev, env); @@ -240,7 +233,7 @@ static int dev_uevent(struct kset *kset, struct kobject *kobj, __func__, retval); } - /* have the device type specific fuction add its stuff */ + /* have the device type specific function add its stuff */ if (dev->type && dev->type->uevent) { retval = dev->type->uevent(dev, env); if (retval) @@ -252,7 +245,7 @@ static int dev_uevent(struct kset *kset, struct kobject *kobj, return retval; } -static struct kset_uevent_ops device_uevent_ops = { +static const struct kset_uevent_ops device_uevent_ops = { .filter = dev_uevent_filter, .name = dev_uevent_name, .uevent = dev_uevent, @@ -306,15 +299,10 @@ static ssize_t store_uevent(struct device *dev, struct device_attribute *attr, { enum kobject_action action; - if (kobject_action_type(buf, count, &action) == 0) { + if (kobject_action_type(buf, count, &action) == 0) kobject_uevent(&dev->kobj, action); - goto out; - } - - dev_err(dev, "uevent: unsupported action-string; this will " - "be ignored in a future kernel version\n"); - kobject_uevent(&dev->kobj, KOBJ_ADD); -out: + else + dev_err(dev, "uevent: unknown action-string\n"); return count; } @@ -564,32 +552,14 @@ void device_initialize(struct device *dev) dev->kobj.kset = devices_kset; kobject_init(&dev->kobj, &device_ktype); INIT_LIST_HEAD(&dev->dma_pools); - init_MUTEX(&dev->sem); + mutex_init(&dev->mutex); + lockdep_set_novalidate_class(&dev->mutex); spin_lock_init(&dev->devres_lock); INIT_LIST_HEAD(&dev->devres_head); - device_init_wakeup(dev, 0); device_pm_init(dev); set_dev_node(dev, -1); } -#ifdef CONFIG_SYSFS_DEPRECATED -static struct kobject *get_device_parent(struct device *dev, - struct device *parent) -{ - /* class devices without a parent live in /sys/class/<classname>/ */ - if (dev->class && (!parent || parent->class != dev->class)) - return &dev->class->p->class_subsys.kobj; - /* all other devices keep their parent */ - else if (parent) - return &parent->kobj; - - return NULL; -} - -static inline void cleanup_device_parent(struct device *dev) {} -static inline void cleanup_glue_dir(struct device *dev, - struct kobject *glue_dir) {} -#else static struct kobject *virtual_device_parent(struct device *dev) { static struct kobject *virtual_dir = NULL; @@ -601,16 +571,74 @@ static struct kobject *virtual_device_parent(struct device *dev) return virtual_dir; } -static struct kobject *get_device_parent(struct device *dev, - struct device *parent) +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->class_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->class_subsys.kobj; + } +#endif + /* * If we have no parent, we live in "virtual". * Class-devices with a non class-device as parent, live @@ -618,11 +646,13 @@ static struct kobject *get_device_parent(struct device *dev, */ if (parent == NULL) parent_kobj = virtual_device_parent(dev); - else if (parent->class) + 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->class_dirs.list_lock); list_for_each_entry(k, &dev->class->p->class_dirs.list, entry) @@ -631,20 +661,15 @@ static struct kobject *get_device_parent(struct device *dev, break; } spin_unlock(&dev->class->p->class_dirs.list_lock); - if (kobj) + if (kobj) { + mutex_unlock(&gdp_mutex); return kobj; + } /* or create a new class-directory at the parent device */ - k = kobject_create(); - if (!k) - return NULL; - k->kset = &dev->class->p->class_dirs; - retval = kobject_add(k, parent_kobj, "%s", dev->class->name); - if (retval < 0) { - kobject_put(k); - return NULL; - } + 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; } @@ -667,7 +692,6 @@ static void cleanup_device_parent(struct device *dev) { cleanup_glue_dir(dev, dev->kobj.parent); } -#endif static void setup_parent(struct device *dev, struct device *parent) { @@ -690,70 +714,29 @@ static int device_add_class_symlinks(struct device *dev) if (error) goto out; -#ifdef CONFIG_SYSFS_DEPRECATED - /* stacked class devices need a symlink in the class directory */ - if (dev->kobj.parent != &dev->class->p->class_subsys.kobj && - device_is_not_partition(dev)) { - error = sysfs_create_link(&dev->class->p->class_subsys.kobj, - &dev->kobj, dev_name(dev)); - if (error) - goto out_subsys; - } - if (dev->parent && device_is_not_partition(dev)) { - struct device *parent = dev->parent; - char *class_name; - - /* - * stacked class devices have the 'device' link - * pointing to the bus device instead of the parent - */ - while (parent->class && !parent->bus && parent->parent) - parent = parent->parent; - - error = sysfs_create_link(&dev->kobj, - &parent->kobj, + error = sysfs_create_link(&dev->kobj, &dev->parent->kobj, "device"); if (error) - goto out_busid; - - class_name = make_class_name(dev->class->name, - &dev->kobj); - if (class_name) - error = sysfs_create_link(&dev->parent->kobj, - &dev->kobj, class_name); - kfree(class_name); - if (error) - goto out_device; + goto out_subsys; } - return 0; -out_device: - if (dev->parent && device_is_not_partition(dev)) - sysfs_remove_link(&dev->kobj, "device"); -out_busid: - if (dev->kobj.parent != &dev->class->p->class_subsys.kobj && - device_is_not_partition(dev)) - sysfs_remove_link(&dev->class->p->class_subsys.kobj, - dev_name(dev)); -#else +#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->class_subsys.kobj, &dev->kobj, dev_name(dev)); if (error) - goto out_subsys; + goto out_device; - if (dev->parent && device_is_not_partition(dev)) { - error = sysfs_create_link(&dev->kobj, &dev->parent->kobj, - "device"); - if (error) - goto out_busid; - } return 0; -out_busid: - sysfs_remove_link(&dev->class->p->class_subsys.kobj, dev_name(dev)); -#endif +out_device: + sysfs_remove_link(&dev->kobj, "device"); out_subsys: sysfs_remove_link(&dev->kobj, "subsystem"); @@ -766,30 +749,14 @@ static void device_remove_class_symlinks(struct device *dev) if (!dev->class) return; -#ifdef CONFIG_SYSFS_DEPRECATED - if (dev->parent && device_is_not_partition(dev)) { - char *class_name; - - class_name = make_class_name(dev->class->name, &dev->kobj); - if (class_name) { - sysfs_remove_link(&dev->parent->kobj, class_name); - kfree(class_name); - } - sysfs_remove_link(&dev->kobj, "device"); - } - - if (dev->kobj.parent != &dev->class->p->class_subsys.kobj && - device_is_not_partition(dev)) - sysfs_remove_link(&dev->class->p->class_subsys.kobj, - dev_name(dev)); -#else if (dev->parent && device_is_not_partition(dev)) sysfs_remove_link(&dev->kobj, "device"); - - sysfs_remove_link(&dev->class->p->class_subsys.kobj, dev_name(dev)); -#endif - sysfs_remove_link(&dev->kobj, "subsystem"); +#ifdef CONFIG_BLOCK + if (sysfs_deprecated && dev->class == &block_class) + return; +#endif + sysfs_delete_link(&dev->class->p->class_subsys.kobj, &dev->kobj, dev_name(dev)); } /** @@ -1341,6 +1308,8 @@ static void root_device_release(struct device *dev) * '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) @@ -1366,7 +1335,7 @@ struct device *__root_device_register(const char *name, struct module *owner) return ERR_PTR(err); } -#ifdef CONFIG_MODULE /* gotta find a "cleaner" way to do this */ +#ifdef CONFIG_MODULES /* gotta find a "cleaner" way to do this */ if (owner) { struct module_kobject *mk = &owner->mkobj; @@ -1428,6 +1397,8 @@ static void device_create_release(struct device *dev) * 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(). */ @@ -1488,6 +1459,8 @@ EXPORT_SYMBOL_GPL(device_create_vargs); * 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(). */ @@ -1541,7 +1514,7 @@ EXPORT_SYMBOL_GPL(device_destroy); * on the same device to ensure that new_name is valid and * won't conflict with other devices. */ -int device_rename(struct device *dev, char *new_name) +int device_rename(struct device *dev, const char *new_name) { char *old_class_name = NULL; char *new_class_name = NULL; @@ -1555,43 +1528,22 @@ int device_rename(struct device *dev, char *new_name) pr_debug("device: '%s': %s: renaming to '%s'\n", dev_name(dev), __func__, new_name); -#ifdef CONFIG_SYSFS_DEPRECATED - if ((dev->class) && (dev->parent)) - old_class_name = make_class_name(dev->class->name, &dev->kobj); -#endif - old_device_name = kstrdup(dev_name(dev), GFP_KERNEL); if (!old_device_name) { error = -ENOMEM; goto out; } - error = kobject_rename(&dev->kobj, new_name); - if (error) - goto out; - -#ifdef CONFIG_SYSFS_DEPRECATED - if (old_class_name) { - new_class_name = make_class_name(dev->class->name, &dev->kobj); - if (new_class_name) { - error = sysfs_create_link_nowarn(&dev->parent->kobj, - &dev->kobj, - new_class_name); - if (error) - goto out; - sysfs_remove_link(&dev->parent->kobj, old_class_name); - } - } -#else if (dev->class) { - error = sysfs_create_link_nowarn(&dev->class->p->class_subsys.kobj, - &dev->kobj, dev_name(dev)); + error = sysfs_rename_link(&dev->class->p->class_subsys.kobj, + &dev->kobj, old_device_name, new_name); if (error) goto out; - sysfs_remove_link(&dev->class->p->class_subsys.kobj, - old_device_name); } -#endif + + error = kobject_rename(&dev->kobj, new_name); + if (error) + goto out; out: put_device(dev); @@ -1609,40 +1561,13 @@ static int device_move_class_links(struct device *dev, struct device *new_parent) { int error = 0; -#ifdef CONFIG_SYSFS_DEPRECATED - char *class_name; - class_name = make_class_name(dev->class->name, &dev->kobj); - if (!class_name) { - error = -ENOMEM; - goto out; - } - if (old_parent) { - sysfs_remove_link(&dev->kobj, "device"); - sysfs_remove_link(&old_parent->kobj, class_name); - } - if (new_parent) { - error = sysfs_create_link(&dev->kobj, &new_parent->kobj, - "device"); - if (error) - goto out; - error = sysfs_create_link(&new_parent->kobj, &dev->kobj, - class_name); - if (error) - sysfs_remove_link(&dev->kobj, "device"); - } else - error = 0; -out: - kfree(class_name); - return error; -#else if (old_parent) sysfs_remove_link(&dev->kobj, "device"); if (new_parent) error = sysfs_create_link(&dev->kobj, &new_parent->kobj, "device"); return error; -#endif } /** @@ -1731,10 +1656,25 @@ EXPORT_SYMBOL_GPL(device_move); */ void device_shutdown(void) { - struct device *dev, *devn; + 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); - list_for_each_entry_safe_reverse(dev, devn, &devices_kset->list, - kobj.entry) { if (dev->bus && dev->bus->shutdown) { dev_dbg(dev, "shutdown\n"); dev->bus->shutdown(dev); @@ -1742,6 +1682,74 @@ void device_shutdown(void) 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 index 958bd1540c30..251acea3d359 100644 --- a/drivers/base/cpu.c +++ b/drivers/base/cpu.c @@ -10,11 +10,15 @@ #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); @@ -76,34 +80,24 @@ void unregister_cpu(struct cpu *cpu) } #ifdef CONFIG_ARCH_CPU_PROBE_RELEASE -static ssize_t cpu_probe_store(struct class *class, const char *buf, +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 class *class, const char *buf, +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 CLASS_ATTR(probe, S_IWUSR, NULL, cpu_probe_store); -static CLASS_ATTR(release, S_IWUSR, NULL, cpu_release_store); - -int __init cpu_probe_release_init(void) -{ - int rc; - - rc = sysfs_create_file(&cpu_sysdev_class.kset.kobj, - &class_attr_probe.attr); - if (!rc) - rc = sysfs_create_file(&cpu_sysdev_class.kset.kobj, - &class_attr_release.attr); - - return rc; -} -device_initcall(cpu_probe_release_init); +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 */ @@ -141,31 +135,39 @@ static SYSDEV_ATTR(crash_notes, 0400, show_crash_notes, NULL); /* * Print cpu online, possible, present, and system maps */ -static ssize_t print_cpus_map(char *buf, const struct cpumask *map) + +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) { - int n = cpulist_scnprintf(buf, PAGE_SIZE-2, map); + 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 print_cpus_func(type) \ -static ssize_t print_cpus_##type(struct sysdev_class *class, char *buf) \ -{ \ - return print_cpus_map(buf, cpu_##type##_mask); \ -} \ -static struct sysdev_class_attribute attr_##type##_map = \ - _SYSDEV_CLASS_ATTR(type, 0444, print_cpus_##type, NULL) +#define _CPU_ATTR(name, map) \ + { _SYSDEV_CLASS_ATTR(name, 0444, show_cpus_attr, NULL), map } -print_cpus_func(online); -print_cpus_func(possible); -print_cpus_func(present); +/* 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, char *buf) +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; @@ -175,7 +177,8 @@ 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, char *buf) +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; @@ -183,7 +186,7 @@ static ssize_t print_cpus_offline(struct sysdev_class *class, char *buf) /* display offline cpus < nr_cpu_ids */ if (!alloc_cpumask_var(&offline, GFP_KERNEL)) return -ENOMEM; - cpumask_complement(offline, cpu_online_mask); + cpumask_andnot(offline, cpu_possible_mask, cpu_online_mask); n = cpulist_scnprintf(buf, len, offline); free_cpumask_var(offline); @@ -204,29 +207,6 @@ static ssize_t print_cpus_offline(struct sysdev_class *class, char *buf) } static SYSDEV_CLASS_ATTR(offline, 0444, print_cpus_offline, NULL); -static struct sysdev_class_attribute *cpu_state_attr[] = { - &attr_online_map, - &attr_possible_map, - &attr_present_map, - &attr_kernel_max, - &attr_offline, -}; - -static int cpu_states_init(void) -{ - int i; - int err = 0; - - for (i = 0; i < ARRAY_SIZE(cpu_state_attr); i++) { - int ret; - ret = sysdev_class_create_file(&cpu_sysdev_class, - cpu_state_attr[i]); - if (!err) - err = ret; - } - return err; -} - /* * register_cpu - Setup a sysfs device for a CPU. * @cpu - cpu->hotpluggable field set to 1 will generate a control file in @@ -272,9 +252,6 @@ int __init cpu_dev_init(void) int err; err = sysdev_class_register(&cpu_sysdev_class); - if (!err) - err = cpu_states_init(); - #if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT) if (!err) err = sched_create_sysfs_power_savings_entries(&cpu_sysdev_class); @@ -282,3 +259,16 @@ int __init cpu_dev_init(void) 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 index ee95c76bfd3d..da57ee9d63fe 100644 --- a/drivers/base/dd.c +++ b/drivers/base/dd.c @@ -40,17 +40,21 @@ static void driver_bound(struct device *dev) 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); - - klist_add_tail(&dev->p->knode_driver, &dev->driver->p->klist_devices); } 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) { @@ -85,7 +89,7 @@ static void driver_sysfs_remove(struct device *dev) * 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 @dev->sem held. + * This function must be called with the device lock held. */ int device_bind_driver(struct device *dev) { @@ -190,8 +194,8 @@ EXPORT_SYMBOL_GPL(wait_for_device_probe); * 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->sem held. When called for a - * USB interface, @dev->parent->sem must be held as well. + * 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) { @@ -233,13 +237,13 @@ static int __device_attach(struct device_driver *drv, void *data) * 0 if no matching driver was found; * -ENODEV if the device is not registered. * - * When called for a USB interface, @dev->parent->sem must be held. + * When called for a USB interface, @dev->parent lock must be held. */ int device_attach(struct device *dev) { int ret = 0; - down(&dev->sem); + device_lock(dev); if (dev->driver) { ret = device_bind_driver(dev); if (ret == 0) @@ -253,7 +257,7 @@ int device_attach(struct device *dev) ret = bus_for_each_drv(dev->bus, NULL, dev, __device_attach); pm_runtime_put_sync(dev); } - up(&dev->sem); + device_unlock(dev); return ret; } EXPORT_SYMBOL_GPL(device_attach); @@ -276,13 +280,13 @@ static int __driver_attach(struct device *dev, void *data) return 0; if (dev->parent) /* Needed for USB */ - down(&dev->parent->sem); - down(&dev->sem); + device_lock(dev->parent); + device_lock(dev); if (!dev->driver) driver_probe_device(drv, dev); - up(&dev->sem); + device_unlock(dev); if (dev->parent) - up(&dev->parent->sem); + device_unlock(dev->parent); return 0; } @@ -303,8 +307,8 @@ int driver_attach(struct device_driver *drv) EXPORT_SYMBOL_GPL(driver_attach); /* - * __device_release_driver() must be called with @dev->sem held. - * When called for a USB interface, @dev->parent->sem must be held as well. + * __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) { @@ -343,7 +347,7 @@ static void __device_release_driver(struct device *dev) * @dev: device. * * Manually detach device from driver. - * When called for a USB interface, @dev->parent->sem must be held. + * When called for a USB interface, @dev->parent lock must be held. */ void device_release_driver(struct device *dev) { @@ -352,9 +356,9 @@ void device_release_driver(struct device *dev) * within their ->remove callback for the same device, they * will deadlock right here. */ - down(&dev->sem); + device_lock(dev); __device_release_driver(dev); - up(&dev->sem); + device_unlock(dev); } EXPORT_SYMBOL_GPL(device_release_driver); @@ -381,13 +385,13 @@ void driver_detach(struct device_driver *drv) spin_unlock(&drv->p->klist_devices.k_lock); if (dev->parent) /* Needed for USB */ - down(&dev->parent->sem); - down(&dev->sem); + device_lock(dev->parent); + device_lock(dev); if (dev->driver == drv) __device_release_driver(dev); - up(&dev->sem); + device_unlock(dev); if (dev->parent) - up(&dev->parent->sem); + device_unlock(dev->parent); put_device(dev); } } diff --git a/drivers/base/devres.c b/drivers/base/devres.c index 05dd307e8f02..cf7a0c788052 100644 --- a/drivers/base/devres.c +++ b/drivers/base/devres.c @@ -9,6 +9,7 @@ #include <linux/device.h> #include <linux/module.h> +#include <linux/slab.h> #include "base.h" diff --git a/drivers/base/devtmpfs.c b/drivers/base/devtmpfs.c index 42ae452b36b0..af0600143d1c 100644 --- a/drivers/base/devtmpfs.c +++ b/drivers/base/devtmpfs.c @@ -20,9 +20,11 @@ #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; @@ -44,7 +46,11 @@ __setup("devtmpfs.mount=", mount_param); static int dev_get_sb(struct file_system_type *fs_type, int flags, const char *dev_name, void *data, struct vfsmount *mnt) { +#ifdef CONFIG_TMPFS return get_sb_single(fs_type, flags, data, shmem_fill_super, mnt); +#else + return get_sb_single(fs_type, flags, data, ramfs_fill_super, mnt); +#endif } static struct file_system_type dev_fs_type = { @@ -301,6 +307,19 @@ int devtmpfs_delete_node(struct device *dev) 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) diff --git a/drivers/base/dma-coherent.c b/drivers/base/dma-coherent.c index 962a3b574f21..f369e2795985 100644 --- a/drivers/base/dma-coherent.c +++ b/drivers/base/dma-coherent.c @@ -2,12 +2,13 @@ * 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; - u32 device_base; + dma_addr_t device_base; int size; int flags; unsigned long *bitmap; diff --git a/drivers/base/dma-mapping.c b/drivers/base/dma-mapping.c index ca9186f70a69..763d59c1eb65 100644 --- a/drivers/base/dma-mapping.c +++ b/drivers/base/dma-mapping.c @@ -8,6 +8,7 @@ */ #include <linux/dma-mapping.h> +#include <linux/gfp.h> /* * Managed DMA API diff --git a/drivers/base/driver.c b/drivers/base/driver.c index 90c9fff09ead..b631f7c59453 100644 --- a/drivers/base/driver.c +++ b/drivers/base/driver.c @@ -13,6 +13,7 @@ #include <linux/device.h> #include <linux/module.h> #include <linux/errno.h> +#include <linux/slab.h> #include <linux/string.h> #include "base.h" diff --git a/drivers/base/firmware_class.c b/drivers/base/firmware_class.c index a95024166b66..40af43ebd92d 100644 --- a/drivers/base/firmware_class.c +++ b/drivers/base/firmware_class.c @@ -19,7 +19,7 @@ #include <linux/kthread.h> #include <linux/highmem.h> #include <linux/firmware.h> -#include "base.h" +#include <linux/slab.h> #define to_dev(obj) container_of(obj, struct device, kobj) @@ -27,6 +27,52 @@ 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, @@ -40,36 +86,33 @@ static int loading_timeout = 60; /* In seconds */ static DEFINE_MUTEX(fw_lock); struct firmware_priv { - char *fw_id; struct completion completion; - struct bin_attribute attr_data; struct firmware *fw; unsigned long status; struct page **pages; int nr_pages; int page_array_size; - const char *vdata; struct timer_list timeout; + struct device dev; + bool nowait; + char fw_id[]; }; -#ifdef CONFIG_FW_LOADER -extern struct builtin_fw __start_builtin_fw[]; -extern struct builtin_fw __end_builtin_fw[]; -#else /* Module case. Avoid ifdefs later; it'll all optimise out */ -static struct builtin_fw *__start_builtin_fw; -static struct builtin_fw *__end_builtin_fw; -#endif +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) +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, char *buf) +static ssize_t firmware_timeout_show(struct class *class, + struct class_attribute *attr, + char *buf) { return sprintf(buf, "%d\n", loading_timeout); } @@ -77,6 +120,7 @@ firmware_timeout_show(struct class *class, char *buf) /** * 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 * @@ -86,33 +130,53 @@ firmware_timeout_show(struct class *class, char *buf) * * Note: zero means 'wait forever'. **/ -static ssize_t -firmware_timeout_store(struct class *class, const char *buf, size_t count) +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 CLASS_ATTR(timeout, 0644, firmware_timeout_show, firmware_timeout_store); +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; -static void fw_dev_release(struct device *dev); + 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 = dev_get_drvdata(dev); + 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, }; @@ -120,11 +184,23 @@ static struct class firmware_class = { static ssize_t firmware_loading_show(struct device *dev, struct device_attribute *attr, char *buf) { - struct firmware_priv *fw_priv = dev_get_drvdata(dev); + 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 @@ -146,7 +222,7 @@ static ssize_t firmware_loading_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { - struct firmware_priv *fw_priv = dev_get_drvdata(dev); + struct firmware_priv *fw_priv = to_firmware_priv(dev); int loading = simple_strtol(buf, NULL, 10); int i; @@ -157,21 +233,21 @@ static ssize_t firmware_loading_store(struct device *dev, mutex_unlock(&fw_lock); break; } - vfree(fw_priv->fw->data); - fw_priv->fw->data = NULL; + 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; - fw_priv->fw->size = 0; set_bit(FW_STATUS_LOADING, &fw_priv->status); mutex_unlock(&fw_lock); break; case 0: if (test_bit(FW_STATUS_LOADING, &fw_priv->status)) { - vfree(fw_priv->fw->data); + vunmap(fw_priv->fw->data); fw_priv->fw->data = vmap(fw_priv->pages, fw_priv->nr_pages, 0, PAGE_KERNEL_RO); @@ -179,7 +255,10 @@ static ssize_t firmware_loading_store(struct device *dev, dev_err(dev, "%s: vmap() failed\n", __func__); goto err; } - /* Pages will be freed by vfree() */ + /* 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); @@ -201,12 +280,12 @@ static ssize_t firmware_loading_store(struct device *dev, static DEVICE_ATTR(loading, 0644, firmware_loading_show, firmware_loading_store); -static ssize_t -firmware_data_read(struct kobject *kobj, struct bin_attribute *bin_attr, - char *buffer, loff_t offset, size_t count) +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 = dev_get_drvdata(dev); + struct firmware_priv *fw_priv = to_firmware_priv(dev); struct firmware *fw; ssize_t ret_count; @@ -245,8 +324,7 @@ out: return ret_count; } -static int -fw_realloc_buffer(struct firmware_priv *fw_priv, int min_size) +static int fw_realloc_buffer(struct firmware_priv *fw_priv, int min_size) { int pages_needed = ALIGN(min_size, PAGE_SIZE) >> PAGE_SHIFT; @@ -286,6 +364,7 @@ fw_realloc_buffer(struct firmware_priv *fw_priv, int min_size) /** * 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 @@ -295,12 +374,12 @@ fw_realloc_buffer(struct firmware_priv *fw_priv, int min_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 kobject *kobj, struct bin_attribute *bin_attr, - char *buffer, loff_t offset, size_t count) +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 = dev_get_drvdata(dev); + struct firmware_priv *fw_priv = to_firmware_priv(dev); struct firmware *fw; ssize_t retval; @@ -341,136 +420,103 @@ out: return retval; } -static struct bin_attribute firmware_attr_data_tmpl = { - .attr = {.name = "data", .mode = 0644}, +static struct bin_attribute firmware_attr_data = { + .attr = { .name = "data", .mode = 0644 }, .size = 0, .read = firmware_data_read, .write = firmware_data_write, }; -static void fw_dev_release(struct device *dev) -{ - struct firmware_priv *fw_priv = dev_get_drvdata(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->fw_id); - kfree(fw_priv); - kfree(dev); - - module_put(THIS_MODULE); -} - -static void -firmware_class_timeout(u_long data) +static void firmware_class_timeout(u_long data) { struct firmware_priv *fw_priv = (struct firmware_priv *) data; + fw_load_abort(fw_priv); } -static int fw_register_device(struct device **dev_p, const char *fw_name, - struct device *device) +static struct firmware_priv * +fw_create_instance(struct firmware *firmware, const char *fw_name, + struct device *device, bool uevent, bool nowait) { - int retval; - struct firmware_priv *fw_priv = kzalloc(sizeof(*fw_priv), - GFP_KERNEL); - struct device *f_dev = kzalloc(sizeof(*f_dev), GFP_KERNEL); - - *dev_p = NULL; + struct firmware_priv *fw_priv; + struct device *f_dev; + int error; - if (!fw_priv || !f_dev) { + fw_priv = kzalloc(sizeof(*fw_priv) + strlen(fw_name) + 1 , GFP_KERNEL); + if (!fw_priv) { dev_err(device, "%s: kmalloc failed\n", __func__); - retval = -ENOMEM; - goto error_kfree; + 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); - fw_priv->attr_data = firmware_attr_data_tmpl; - fw_priv->fw_id = kstrdup(fw_name, GFP_KERNEL); - if (!fw_priv->fw_id) { - dev_err(device, "%s: Firmware name allocation failed\n", - __func__); - retval = -ENOMEM; - goto error_kfree; - } + setup_timer(&fw_priv->timeout, + firmware_class_timeout, (u_long) fw_priv); - fw_priv->timeout.function = firmware_class_timeout; - fw_priv->timeout.data = (u_long) fw_priv; - init_timer(&fw_priv->timeout); + 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_drvdata(f_dev, fw_priv); - dev_set_uevent_suppress(f_dev, 1); - retval = device_register(f_dev); - if (retval) { - dev_err(device, "%s: device_register failed\n", __func__); - put_device(f_dev); - return retval; - } - *dev_p = f_dev; - return 0; - -error_kfree: - kfree(f_dev); - kfree(fw_priv); - return retval; -} - -static int fw_setup_device(struct firmware *fw, struct device **dev_p, - const char *fw_name, struct device *device, - int uevent) -{ - struct device *f_dev; - struct firmware_priv *fw_priv; - int retval; - *dev_p = NULL; - retval = fw_register_device(&f_dev, fw_name, device); - if (retval) - goto out; + dev_set_uevent_suppress(f_dev, true); /* Need to pin this module until class device is destroyed */ __module_get(THIS_MODULE); - fw_priv = dev_get_drvdata(f_dev); + error = device_add(f_dev); + if (error) { + dev_err(device, "%s: device_register failed\n", __func__); + goto err_put_dev; + } - fw_priv->fw = fw; - retval = sysfs_create_bin_file(&f_dev->kobj, &fw_priv->attr_data); - if (retval) { + error = device_create_bin_file(f_dev, &firmware_attr_data); + if (error) { dev_err(device, "%s: sysfs_create_bin_file failed\n", __func__); - goto error_unreg; + goto err_del_dev; } - retval = device_create_file(f_dev, &dev_attr_loading); - if (retval) { + error = device_create_file(f_dev, &dev_attr_loading); + if (error) { dev_err(device, "%s: device_create_file failed\n", __func__); - goto error_unreg; + goto err_del_bin_attr; } if (uevent) - dev_set_uevent_suppress(f_dev, 0); - *dev_p = f_dev; - goto out; + 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; -error_unreg: + device_remove_file(f_dev, &dev_attr_loading); + device_remove_bin_file(f_dev, &firmware_attr_data); device_unregister(f_dev); -out: - return retval; } -static int -_request_firmware(const struct firmware **firmware_p, const char *name, - struct device *device, int uevent) +static int _request_firmware(const struct firmware **firmware_p, + const char *name, struct device *device, + bool uevent, bool nowait) { - struct device *f_dev; struct firmware_priv *fw_priv; struct firmware *firmware; - struct builtin_fw *builtin; - int retval; + int retval = 0; if (!firmware_p) return -EINVAL; @@ -483,54 +529,48 @@ _request_firmware(const struct firmware **firmware_p, const char *name, goto out; } - for (builtin = __start_builtin_fw; builtin != __end_builtin_fw; - builtin++) { - if (strcmp(name, builtin->name)) - continue; - dev_info(device, "firmware: using built-in firmware %s\n", - name); - firmware->size = builtin->size; - firmware->data = builtin->data; + if (fw_get_builtin_firmware(firmware, name)) { + dev_dbg(device, "firmware: using built-in firmware %s\n", name); return 0; } if (uevent) - dev_info(device, "firmware: requesting %s\n", name); + dev_dbg(device, "firmware: requesting %s\n", name); - retval = fw_setup_device(firmware, &f_dev, name, device, uevent); - if (retval) - goto error_kfree_fw; - - fw_priv = dev_get_drvdata(f_dev); + 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) { - fw_priv->timeout.expires = jiffies + loading_timeout * HZ; - add_timer(&fw_priv->timeout); - } + if (loading_timeout > 0) + mod_timer(&fw_priv->timeout, + round_jiffies_up(jiffies + + loading_timeout * HZ)); - kobject_uevent(&f_dev->kobj, KOBJ_ADD); - wait_for_completion(&fw_priv->completion); - set_bit(FW_STATUS_DONE, &fw_priv->status); - del_timer_sync(&fw_priv->timeout); - } else - wait_for_completion(&fw_priv->completion); + 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)) { + if (!fw_priv->fw->size || test_bit(FW_STATUS_ABORT, &fw_priv->status)) retval = -ENOENT; - release_firmware(fw_priv->fw); - *firmware_p = NULL; - } fw_priv->fw = NULL; mutex_unlock(&fw_lock); - device_unregister(f_dev); - goto out; -error_kfree_fw: - kfree(firmware); - *firmware_p = NULL; + fw_destroy_instance(fw_priv); + out: + if (retval) { + release_firmware(firmware); + *firmware_p = NULL; + } + return retval; } @@ -554,26 +594,18 @@ request_firmware(const struct firmware **firmware_p, const char *name, struct device *device) { int uevent = 1; - return _request_firmware(firmware_p, name, device, uevent); + return _request_firmware(firmware_p, name, device, uevent, false); } /** * release_firmware: - release the resource associated with a firmware image * @fw: firmware resource to release **/ -void -release_firmware(const struct firmware *fw) +void release_firmware(const struct firmware *fw) { - struct builtin_fw *builtin; - if (fw) { - for (builtin = __start_builtin_fw; builtin != __end_builtin_fw; - builtin++) { - if (fw->data == builtin->data) - goto free_fw; - } - vfree(fw->data); - free_fw: + if (!fw_is_builtin_firmware(fw)) + firmware_free_data(fw); kfree(fw); } } @@ -589,28 +621,29 @@ struct firmware_work { int uevent; }; -static int -request_firmware_work_func(void *arg) +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); + 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 + * 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. @@ -633,57 +666,42 @@ request_firmware_nowait( void (*cont)(const struct firmware *fw, void *context)) { struct task_struct *task; - struct firmware_work *fw_work = kmalloc(sizeof (struct firmware_work), - gfp); + 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; } - *fw_work = (struct firmware_work) { - .module = module, - .name = name, - .device = device, - .context = context, - .cont = cont, - .uevent = uevent, - }; - 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) +static int __init firmware_class_init(void) { - int error; - error = class_register(&firmware_class); - if (error) { - printk(KERN_ERR "%s: class_register failed\n", __func__); - return error; - } - error = class_create_file(&firmware_class, &class_attr_timeout); - if (error) { - printk(KERN_ERR "%s: class_create_file failed\n", - __func__); - class_unregister(&firmware_class); - } - return error; - + return class_register(&firmware_class); } -static void __exit -firmware_class_exit(void) + +static void __exit firmware_class_exit(void) { class_unregister(&firmware_class); } diff --git a/drivers/base/iommu.c b/drivers/base/iommu.c index 8ad4ffea6920..6e6b6a11b3ce 100644 --- a/drivers/base/iommu.c +++ b/drivers/base/iommu.c @@ -80,20 +80,6 @@ void iommu_detach_device(struct iommu_domain *domain, struct device *dev) } EXPORT_SYMBOL_GPL(iommu_detach_device); -int iommu_map_range(struct iommu_domain *domain, unsigned long iova, - phys_addr_t paddr, size_t size, int prot) -{ - return iommu_ops->map(domain, iova, paddr, size, prot); -} -EXPORT_SYMBOL_GPL(iommu_map_range); - -void iommu_unmap_range(struct iommu_domain *domain, unsigned long iova, - size_t size) -{ - iommu_ops->unmap(domain, iova, size); -} -EXPORT_SYMBOL_GPL(iommu_unmap_range); - phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain, unsigned long iova) { @@ -107,3 +93,32 @@ int iommu_domain_has_cap(struct iommu_domain *domain, 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/memory.c b/drivers/base/memory.c index bd025059711f..cafeaaf0428f 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -22,10 +22,13 @@ #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 struct sysdev_class memory_sysdev_class = { @@ -44,7 +47,7 @@ static int memory_uevent(struct kset *kset, struct kobject *obj, struct kobj_uev return retval; } -static struct kset_uevent_ops memory_uevent_ops = { +static const struct kset_uevent_ops memory_uevent_ops = { .name = memory_uevent_name, .uevent = memory_uevent, }; @@ -309,17 +312,18 @@ static SYSDEV_ATTR(removable, 0444, show_mem_removable, NULL); * Block size attribute stuff */ static ssize_t -print_block_size(struct class *class, char *buf) +print_block_size(struct sysdev_class *class, struct sysdev_class_attribute *attr, + char *buf) { - return sprintf(buf, "%#lx\n", (unsigned long)PAGES_PER_SECTION * PAGE_SIZE); + return sprintf(buf, "%lx\n", (unsigned long)PAGES_PER_SECTION * PAGE_SIZE); } -static CLASS_ATTR(block_size_bytes, 0444, print_block_size, NULL); +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, - &class_attr_block_size_bytes.attr); + &attr_block_size_bytes.attr); } /* @@ -330,7 +334,8 @@ static int block_size_init(void) */ #ifdef CONFIG_ARCH_MEMORY_PROBE static ssize_t -memory_probe_store(struct class *class, const char *buf, size_t count) +memory_probe_store(struct class *class, struct class_attribute *attr, + const char *buf, size_t count) { u64 phys_addr; int nid; @@ -367,7 +372,9 @@ static inline int memory_probe_init(void) /* Soft offline a page */ static ssize_t -store_soft_offline_page(struct class *class, const char *buf, size_t count) +store_soft_offline_page(struct class *class, + struct class_attribute *attr, + const char *buf, size_t count) { int ret; u64 pfn; @@ -384,7 +391,9 @@ store_soft_offline_page(struct class *class, const char *buf, size_t count) /* Forcibly offline a page, including killing processes. */ static ssize_t -store_hard_offline_page(struct class *class, const char *buf, size_t count) +store_hard_offline_page(struct class *class, + struct class_attribute *attr, + const char *buf, size_t count) { int ret; u64 pfn; @@ -423,21 +432,68 @@ static inline int memory_fail_init(void) * 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]; + + 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, __section_nr(section)); + + 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 add_memory_block(int nid, struct mem_section *section, - unsigned long state, int phys_device, - enum mem_add_context context) + unsigned long state, enum mem_add_context context) { struct memory_block *mem = kzalloc(sizeof(*mem), GFP_KERNEL); + unsigned long start_pfn; int ret = 0; if (!mem) return -ENOMEM; + mutex_lock(&mem_sysfs_mutex); + mem->phys_index = __section_nr(section); mem->state = state; + mem->section_count++; mutex_init(&mem->state_mutex); - mem->phys_device = phys_device; + start_pfn = section_nr_to_pfn(mem->phys_index); + mem->phys_device = arch_get_memory_phys_device(start_pfn); ret = register_memory(mem, section); if (!ret) @@ -453,53 +509,29 @@ static int add_memory_block(int nid, struct mem_section *section, ret = register_mem_sect_under_node(mem, nid); } + mutex_unlock(&mem_sysfs_mutex); return ret; } -/* - * For now, we have a linear search to go find the appropriate - * memory_block corresponding to a particular phys_index. If - * this gets to be a real problem, we can always use a radix - * tree or something here. - * - * This could be made generic for all sysdev classes. - */ -struct memory_block *find_memory_block(struct mem_section *section) -{ - struct kobject *kobj; - struct sys_device *sysdev; - struct memory_block *mem; - char name[sizeof(MEMORY_CLASS_NAME) + 9 + 1]; - - /* - * This only works because we know that section == sysdev->id - * slightly redundant with sysdev_register() - */ - sprintf(&name[0], "%s%d", MEMORY_CLASS_NAME, __section_nr(section)); - - kobj = kset_find_obj(&memory_sysdev_class.kset, name); - if (!kobj) - return NULL; - - sysdev = container_of(kobj, struct sys_device, kobj); - mem = container_of(sysdev, struct memory_block, sysdev); - - return mem; -} - int remove_memory_block(unsigned long node_id, struct mem_section *section, int phys_device) { struct memory_block *mem; + mutex_lock(&mem_sysfs_mutex); mem = find_memory_block(section); - unregister_mem_sect_under_nodes(mem); - mem_remove_simple_file(mem, phys_index); - mem_remove_simple_file(mem, state); - mem_remove_simple_file(mem, phys_device); - mem_remove_simple_file(mem, removable); - unregister_memory(mem, section); + mem->section_count--; + if (mem->section_count == 0) { + unregister_mem_sect_under_nodes(mem); + mem_remove_simple_file(mem, phys_index); + mem_remove_simple_file(mem, state); + mem_remove_simple_file(mem, phys_device); + mem_remove_simple_file(mem, removable); + unregister_memory(mem, section); + } + + mutex_unlock(&mem_sysfs_mutex); return 0; } @@ -509,7 +541,7 @@ int remove_memory_block(unsigned long node_id, struct mem_section *section, */ int register_new_memory(int nid, struct mem_section *section) { - return add_memory_block(nid, section, MEM_OFFLINE, 0, HOTPLUG); + return add_memory_block(nid, section, MEM_OFFLINE, HOTPLUG); } int unregister_memory_section(struct mem_section *section) @@ -542,7 +574,7 @@ int __init memory_dev_init(void) if (!present_section_nr(i)) continue; err = add_memory_block(0, __nr_to_section(i), MEM_ONLINE, - 0, BOOT); + BOOT); if (!ret) ret = err; } diff --git a/drivers/base/module.c b/drivers/base/module.c index 103be9cacb05..db930d3ee312 100644 --- a/drivers/base/module.c +++ b/drivers/base/module.c @@ -7,6 +7,7 @@ #include <linux/device.h> #include <linux/module.h> #include <linux/errno.h> +#include <linux/slab.h> #include <linux/string.h> #include "base.h" @@ -14,12 +15,10 @@ static char *make_driver_name(struct device_driver *drv) { char *driver_name; - driver_name = kmalloc(strlen(drv->name) + strlen(drv->bus->name) + 2, - GFP_KERNEL); + driver_name = kasprintf(GFP_KERNEL, "%s:%s", drv->bus->name, drv->name); if (!driver_name) return NULL; - sprintf(driver_name, "%s:%s", drv->bus->name, drv->name); return driver_name; } diff --git a/drivers/base/node.c b/drivers/base/node.c index 70122791683d..ce012a9c6201 100644 --- a/drivers/base/node.c +++ b/drivers/base/node.c @@ -9,15 +9,20 @@ #include <linux/memory.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, }; @@ -61,8 +66,7 @@ static ssize_t node_read_meminfo(struct sys_device * dev, struct sysinfo i; si_meminfo_node(&i, nid); - - n = sprintf(buf, "\n" + n = sprintf(buf, "Node %d MemTotal: %8lu kB\n" "Node %d MemFree: %8lu kB\n" "Node %d MemUsed: %8lu kB\n" @@ -73,13 +77,33 @@ static ssize_t node_read_meminfo(struct sys_device * dev, "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" + "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" + "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" @@ -94,25 +118,6 @@ static ssize_t node_read_meminfo(struct sys_device * dev, "Node %d Slab: %8lu kB\n" "Node %d SReclaimable: %8lu kB\n" "Node %d SUnreclaim: %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 - nid, K(i.totalhigh), - nid, K(i.freehigh), - nid, K(i.totalram - i.totalhigh), - nid, K(i.freeram - i.freehigh), -#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)), @@ -155,6 +160,18 @@ static ssize_t node_read_numastat(struct sys_device * dev, } 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; + return sprintf(buf, + "nr_written %lu\n" + "nr_dirtied %lu\n", + node_page_state(nid, NR_WRITTEN), + node_page_state(nid, NR_DIRTIED)); +} +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) { @@ -162,8 +179,11 @@ static ssize_t node_read_distance(struct sys_device * dev, int len = 0; int i; - /* buf currently PAGE_SIZE, need ~4 chars per node */ - BUILD_BUG_ON(MAX_NUMNODES*4 > PAGE_SIZE/2); + /* + * 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)); @@ -235,10 +255,13 @@ int register_node(struct node *node, int num, struct node *parent) 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; } @@ -257,6 +280,7 @@ void unregister_node(struct node *node) 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 */ @@ -399,25 +423,27 @@ 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; - struct memory_block *mem_blk; int ret; if (!present_section_nr(section_nr)) continue; mem_sect = __nr_to_section(section_nr); - mem_blk = find_memory_block(mem_sect); + 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() */ - kobject_put(&mem_blk->sysdev.kobj); } + + if (mem_blk) + kobject_put(&mem_blk->sysdev.kobj); return err; } @@ -544,76 +570,52 @@ static ssize_t print_nodes_state(enum node_states state, char *buf) return n; } -static ssize_t print_nodes_possible(struct sysdev_class *class, char *buf) -{ - return print_nodes_state(N_POSSIBLE, buf); -} - -static ssize_t print_nodes_online(struct sysdev_class *class, char *buf) -{ - return print_nodes_state(N_ONLINE, buf); -} - -static ssize_t print_nodes_has_normal_memory(struct sysdev_class *class, - char *buf) -{ - return print_nodes_state(N_NORMAL_MEMORY, buf); -} +struct node_attr { + struct sysdev_class_attribute attr; + enum node_states state; +}; -static ssize_t print_nodes_has_cpu(struct sysdev_class *class, char *buf) +static ssize_t show_node_state(struct sysdev_class *class, + struct sysdev_class_attribute *attr, char *buf) { - return print_nodes_state(N_CPU, buf); + struct node_attr *na = container_of(attr, struct node_attr, attr); + return print_nodes_state(na->state, buf); } -static SYSDEV_CLASS_ATTR(possible, 0444, print_nodes_possible, NULL); -static SYSDEV_CLASS_ATTR(online, 0444, print_nodes_online, NULL); -static SYSDEV_CLASS_ATTR(has_normal_memory, 0444, print_nodes_has_normal_memory, - NULL); -static SYSDEV_CLASS_ATTR(has_cpu, 0444, print_nodes_has_cpu, NULL); +#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 -static ssize_t print_nodes_has_high_memory(struct sysdev_class *class, - char *buf) -{ - return print_nodes_state(N_HIGH_MEMORY, buf); -} - -static SYSDEV_CLASS_ATTR(has_high_memory, 0444, print_nodes_has_high_memory, - NULL); + _NODE_ATTR(has_high_memory, N_HIGH_MEMORY), #endif +}; -struct sysdev_class_attribute *node_state_attr[] = { - &attr_possible, - &attr_online, - &attr_has_normal_memory, +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 - &attr_has_high_memory, + &node_state_attr[4].attr, #endif - &attr_has_cpu, + NULL }; -static int node_states_init(void) -{ - int i; - int err = 0; - - for (i = 0; i < NR_NODE_STATES; i++) { - int ret; - ret = sysdev_class_create_file(&node_class, node_state_attr[i]); - if (!err) - err = ret; - } - return err; -} - #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) { - ret = node_states_init(); hotplug_memory_notifier(node_memory_callback, NODE_CALLBACK_PRI); } diff --git a/drivers/base/platform.c b/drivers/base/platform.c index 58efaf2f1259..f051cfff18af 100644 --- a/drivers/base/platform.c +++ b/drivers/base/platform.c @@ -12,6 +12,7 @@ #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> @@ -128,7 +129,7 @@ struct platform_object { }; /** - * platform_device_put + * platform_device_put - destroy a platform device * @pdev: platform device to free * * Free all memory associated with a platform device. This function must @@ -146,13 +147,14 @@ 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.resource); kfree(pa); } /** - * platform_device_alloc + * platform_device_alloc - create a platform device * @name: base name of the device we're adding * @id: instance id * @@ -177,7 +179,7 @@ struct platform_device *platform_device_alloc(const char *name, int id) EXPORT_SYMBOL_GPL(platform_device_alloc); /** - * platform_device_add_resources + * 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 @@ -187,22 +189,25 @@ EXPORT_SYMBOL_GPL(platform_device_alloc); * released. */ int platform_device_add_resources(struct platform_device *pdev, - struct resource *res, unsigned int num) + const struct resource *res, unsigned int num) { struct resource *r; - r = kmalloc(sizeof(struct resource) * num, GFP_KERNEL); + if (!res) + return 0; + + r = kmemdup(res, sizeof(struct resource) * num, GFP_KERNEL); if (r) { - memcpy(r, res, sizeof(struct resource) * num); pdev->resource = r; pdev->num_resources = num; + return 0; } - return r ? 0 : -ENOMEM; + return -ENOMEM; } EXPORT_SYMBOL_GPL(platform_device_add_resources); /** - * platform_device_add_data + * 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 @@ -214,8 +219,12 @@ EXPORT_SYMBOL_GPL(platform_device_add_resources); int platform_device_add_data(struct platform_device *pdev, const void *data, size_t size) { - void *d = kmemdup(data, size, GFP_KERNEL); + void *d; + + if (!data) + return 0; + d = kmemdup(data, size, GFP_KERNEL); if (d) { pdev->dev.platform_data = d; return 0; @@ -344,104 +353,52 @@ void platform_device_unregister(struct platform_device *pdev) EXPORT_SYMBOL_GPL(platform_device_unregister); /** - * platform_device_register_simple - * @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 - * - * This function creates a simple platform device that requires minimal - * resource and memory management. Canned release function freeing memory - * allocated for the device allows drivers using such devices to be - * unloaded without waiting for the last reference to the device to be - * dropped. + * platform_device_register_resndata - add a platform-level device with + * resources and platform-specific data * - * This interface is primarily intended for use with legacy drivers which - * probe hardware directly. Because such drivers create sysfs device nodes - * themselves, rather than letting system infrastructure handle such device - * enumeration tasks, they don't fully conform to the Linux driver model. - * In particular, when such drivers are built as modules, they can't be - * "hotplugged". - */ -struct platform_device *platform_device_register_simple(const char *name, - int id, - struct resource *res, - unsigned int num) -{ - struct platform_device *pdev; - int retval; - - pdev = platform_device_alloc(name, id); - if (!pdev) { - retval = -ENOMEM; - goto error; - } - - if (num) { - retval = platform_device_add_resources(pdev, res, num); - if (retval) - goto error; - } - - retval = platform_device_add(pdev); - if (retval) - goto error; - - return pdev; - -error: - platform_device_put(pdev); - return ERR_PTR(retval); -} -EXPORT_SYMBOL_GPL(platform_device_register_simple); - -/** - * platform_device_register_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 * - * This function creates a simple platform device that requires minimal - * resource and memory management. Canned release function freeing memory - * allocated for the device allows drivers using such devices to be - * unloaded without waiting for the last reference to the device to be - * dropped. + * Returns &struct platform_device pointer on success, or ERR_PTR() on error. */ -struct platform_device *platform_device_register_data( +struct platform_device *__init_or_module 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; - int retval; pdev = platform_device_alloc(name, id); - if (!pdev) { - retval = -ENOMEM; - goto error; - } + if (!pdev) + goto err; pdev->dev.parent = parent; - if (size) { - retval = platform_device_add_data(pdev, data, size); - if (retval) - goto error; - } + ret = platform_device_add_resources(pdev, res, num); + if (ret) + goto err; - retval = platform_device_add(pdev); - if (retval) - goto error; + ret = platform_device_add_data(pdev, data, size); + if (ret) + goto err; - return pdev; + ret = platform_device_add(pdev); + if (ret) { +err: + platform_device_put(pdev); + return ERR_PTR(ret); + } -error: - platform_device_put(pdev); - return ERR_PTR(retval); + return pdev; } -EXPORT_SYMBOL_GPL(platform_device_register_data); +EXPORT_SYMBOL_GPL(platform_device_register_resndata); static int platform_drv_probe(struct device *_dev) { @@ -473,7 +430,7 @@ static void platform_drv_shutdown(struct device *_dev) } /** - * platform_driver_register + * platform_driver_register - register a driver for platform-level devices * @drv: platform driver structure */ int platform_driver_register(struct platform_driver *drv) @@ -491,7 +448,7 @@ int platform_driver_register(struct platform_driver *drv) EXPORT_SYMBOL_GPL(platform_driver_register); /** - * platform_driver_unregister + * platform_driver_unregister - unregister a driver for platform-level devices * @drv: platform driver structure */ void platform_driver_unregister(struct platform_driver *drv) @@ -535,12 +492,12 @@ int __init_or_module platform_driver_probe(struct platform_driver *drv, * if the probe was successful, and make sure any forced probes of * new devices fail. */ - spin_lock(&platform_bus_type.p->klist_drivers.k_lock); + 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(&platform_bus_type.p->klist_drivers.k_lock); + spin_unlock(&drv->driver.bus->p->klist_drivers.k_lock); if (code != retval) platform_driver_unregister(drv); @@ -548,6 +505,62 @@ int __init_or_module platform_driver_probe(struct platform_driver *drv, } 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" @@ -571,6 +584,12 @@ static struct device_attribute platform_dev_attrs[] = { 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); @@ -578,7 +597,7 @@ static int platform_uevent(struct device *dev, struct kobj_uevent_env *env) } static const struct platform_device_id *platform_match_id( - struct platform_device_id *id, + const struct platform_device_id *id, struct platform_device *pdev) { while (id->name[0]) { @@ -609,7 +628,11 @@ 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); - /* match against the id table first */ + /* 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; @@ -671,7 +694,7 @@ static void platform_pm_complete(struct device *dev) #ifdef CONFIG_SUSPEND -static int platform_pm_suspend(struct device *dev) +int __weak platform_pm_suspend(struct device *dev) { struct device_driver *drv = dev->driver; int ret = 0; @@ -689,7 +712,7 @@ static int platform_pm_suspend(struct device *dev) return ret; } -static int platform_pm_suspend_noirq(struct device *dev) +int __weak platform_pm_suspend_noirq(struct device *dev) { struct device_driver *drv = dev->driver; int ret = 0; @@ -705,7 +728,7 @@ static int platform_pm_suspend_noirq(struct device *dev) return ret; } -static int platform_pm_resume(struct device *dev) +int __weak platform_pm_resume(struct device *dev) { struct device_driver *drv = dev->driver; int ret = 0; @@ -723,7 +746,7 @@ static int platform_pm_resume(struct device *dev) return ret; } -static int platform_pm_resume_noirq(struct device *dev) +int __weak platform_pm_resume_noirq(struct device *dev) { struct device_driver *drv = dev->driver; int ret = 0; @@ -903,17 +926,17 @@ static int platform_pm_restore_noirq(struct device *dev) int __weak platform_pm_runtime_suspend(struct device *dev) { - return -ENOSYS; + return pm_generic_runtime_suspend(dev); }; int __weak platform_pm_runtime_resume(struct device *dev) { - return -ENOSYS; + return pm_generic_runtime_resume(dev); }; int __weak platform_pm_runtime_idle(struct device *dev) { - return -ENOSYS; + return pm_generic_runtime_idle(dev); }; #else /* !CONFIG_PM_RUNTIME */ @@ -953,6 +976,41 @@ struct bus_type platform_bus_type = { }; EXPORT_SYMBOL_GPL(platform_bus_type); +/** + * platform_bus_get_pm_ops() - return pointer to busses dev_pm_ops + * + * This function can be used by platform code to get the current + * set of dev_pm_ops functions used by the platform_bus_type. + */ +const struct dev_pm_ops * __init platform_bus_get_pm_ops(void) +{ + return platform_bus_type.pm; +} + +/** + * platform_bus_set_pm_ops() - update dev_pm_ops for the platform_bus_type + * + * @pm: pointer to new dev_pm_ops struct to be used for platform_bus_type + * + * Platform code can override the dev_pm_ops methods of + * platform_bus_type by using this function. It is expected that + * platform code will first do a platform_bus_get_pm_ops(), then + * kmemdup it, then customize selected methods and pass a pointer to + * the new struct dev_pm_ops to this function. + * + * Since platform-specific code is customizing methods for *all* + * devices (not just platform-specific devices) it is expected that + * any custom overrides of these functions will keep existing behavior + * and simply extend it. For example, any customization of the + * runtime PM methods should continue to call the pm_generic_* + * functions as the default ones do in addition to the + * platform-specific behavior. + */ +void __init platform_bus_set_pm_ops(const struct dev_pm_ops *pm) +{ + platform_bus_type.pm = pm; +} + int __init platform_bus_init(void) { int error; @@ -994,9 +1052,11 @@ static __initdata LIST_HEAD(early_platform_driver_list); static __initdata LIST_HEAD(early_platform_device_list); /** - * early_platform_driver_register + * 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) @@ -1048,9 +1108,12 @@ int __init early_platform_driver_register(struct early_platform_driver *epdrv, } /** - * early_platform_add_devices - add a numbers of early platform devices + * 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) { @@ -1070,8 +1133,12 @@ void __init early_platform_add_devices(struct platform_device **devs, int num) } /** - * early_platform_driver_register_all + * 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) { @@ -1093,7 +1160,7 @@ void __init early_platform_driver_register_all(char *class_str) } /** - * early_platform_match + * early_platform_match - find early platform device matching driver * @epdrv: early platform driver structure * @id: id to match against */ @@ -1111,7 +1178,7 @@ early_platform_match(struct early_platform_driver *epdrv, int id) } /** - * early_platform_left + * early_platform_left - check if early platform driver has matching devices * @epdrv: early platform driver structure * @id: return true if id or above exists */ @@ -1129,7 +1196,7 @@ static __init int early_platform_left(struct early_platform_driver *epdrv, } /** - * early_platform_driver_probe_id + * 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 @@ -1181,6 +1248,26 @@ static int __init early_platform_driver_probe_id(char *class_str, } 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); @@ -1199,10 +1286,14 @@ static int __init early_platform_driver_probe_id(char *class_str, } /** - * early_platform_driver_probe + * 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, diff --git a/drivers/base/power/Makefile b/drivers/base/power/Makefile index 3ce3519e8f30..abe46edfe5b4 100644 --- a/drivers/base/power/Makefile +++ b/drivers/base/power/Makefile @@ -1,7 +1,9 @@ obj-$(CONFIG_PM) += sysfs.o -obj-$(CONFIG_PM_SLEEP) += main.o +obj-$(CONFIG_PM_SLEEP) += main.o wakeup.o obj-$(CONFIG_PM_RUNTIME) += runtime.o +obj-$(CONFIG_PM_OPS) += generic_ops.o obj-$(CONFIG_PM_TRACE_RTC) += trace.o +obj-$(CONFIG_PM_OPP) += opp.o ccflags-$(CONFIG_DEBUG_DRIVER) := -DDEBUG ccflags-$(CONFIG_PM_VERBOSE) += -DDEBUG diff --git a/drivers/base/power/generic_ops.c b/drivers/base/power/generic_ops.c new file mode 100644 index 000000000000..81f2c84697f4 --- /dev/null +++ b/drivers/base/power/generic_ops.c @@ -0,0 +1,233 @@ +/* + * 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 -EINVAL. + */ +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 -EINVAL. + */ +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_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_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); +#endif /* CONFIG_PM_SLEEP */ + +struct dev_pm_ops generic_subsys_pm_ops = { +#ifdef CONFIG_PM_SLEEP + .suspend = pm_generic_suspend, + .resume = pm_generic_resume, + .freeze = pm_generic_freeze, + .thaw = pm_generic_thaw, + .poweroff = pm_generic_poweroff, + .restore = pm_generic_restore, +#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 index a5142bddef41..31b526661ec4 100644 --- a/drivers/base/power/main.c +++ b/drivers/base/power/main.c @@ -25,6 +25,7 @@ #include <linux/resume-trace.h> #include <linux/interrupt.h> #include <linux/sched.h> +#include <linux/async.h> #include "../base.h" #include "power.h" @@ -34,14 +35,15 @@ * 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 semaphore held, - * we must never try to acquire a device semaphore while holding + * 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); static DEFINE_MUTEX(dpm_list_mtx); +static pm_message_t pm_transition; /* * Set once the preparation of devices for a PM transition has started, reset @@ -49,6 +51,8 @@ static DEFINE_MUTEX(dpm_list_mtx); */ static bool transition_started; +static int async_error; + /** * device_pm_init - Initialize the PM-related part of a device object. * @dev: Device object being initialized. @@ -56,6 +60,10 @@ static bool transition_started; void device_pm_init(struct device *dev) { dev->power.status = DPM_ON; + init_completion(&dev->power.completion); + complete_all(&dev->power.completion); + dev->power.wakeup = NULL; + spin_lock_init(&dev->power.lock); pm_runtime_init(dev); } @@ -111,9 +119,11 @@ void device_pm_remove(struct device *dev) pr_debug("PM: Removing info for %s:%s\n", dev->bus ? dev->bus->name : "No Bus", kobject_name(&dev->kobj)); + 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); } @@ -188,6 +198,31 @@ static void initcall_debug_report(struct device *dev, ktime_t calltime, } /** + * 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. @@ -271,8 +306,9 @@ static int pm_noirq_op(struct device *dev, ktime_t calltime, delta, rettime; if (initcall_debug) { - pr_info("calling %s_i+ @ %i\n", - dev_name(dev), task_pid_nr(current)); + 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(); } @@ -375,7 +411,7 @@ static void pm_dev_err(struct device *dev, pm_message_t state, char *info, static void dpm_show_time(ktime_t starttime, pm_message_t state, char *info) { ktime_t calltime; - s64 usecs64; + u64 usecs64; int usecs; calltime = ktime_get(); @@ -409,8 +445,23 @@ static int device_resume_noirq(struct device *dev, pm_message_t state) if (dev->bus && dev->bus->pm) { pm_dev_dbg(dev, state, "EARLY "); error = pm_noirq_op(dev, dev->bus->pm, state); + if (error) + goto End; + } + + if (dev->type && dev->type->pm) { + pm_dev_dbg(dev, state, "EARLY type "); + error = pm_noirq_op(dev, dev->type->pm, state); + if (error) + goto End; } + if (dev->class && dev->class->pm) { + pm_dev_dbg(dev, state, "EARLY class "); + error = pm_noirq_op(dev, dev->class->pm, state); + } + +End: TRACE_RESUME(error); return error; } @@ -468,15 +519,19 @@ static int legacy_resume(struct device *dev, int (*cb)(struct device *dev)) * 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) +static int device_resume(struct device *dev, pm_message_t state, bool async) { int error = 0; TRACE_DEVICE(dev); TRACE_RESUME(0); - down(&dev->sem); + dpm_wait(dev->parent, async); + device_lock(dev); + + dev->power.status = DPM_RESUMING; if (dev->bus) { if (dev->bus->pm) { @@ -509,12 +564,30 @@ static int device_resume(struct device *dev, pm_message_t state) } } End: - up(&dev->sem); + 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_resume - Execute "resume" callbacks for non-sysdev devices. * @state: PM transition of the system being carried out. @@ -525,21 +598,34 @@ static int device_resume(struct device *dev, pm_message_t state) static void dpm_resume(pm_message_t state) { struct list_head list; + struct device *dev; ktime_t starttime = ktime_get(); INIT_LIST_HEAD(&list); mutex_lock(&dpm_list_mtx); - while (!list_empty(&dpm_list)) { - struct device *dev = to_device(dpm_list.next); + pm_transition = state; + async_error = 0; + list_for_each_entry(dev, &dpm_list, power.entry) { + if (dev->power.status < DPM_OFF) + continue; + + INIT_COMPLETION(dev->power.completion); + if (is_async(dev)) { + get_device(dev); + async_schedule(async_resume, dev); + } + } + + while (!list_empty(&dpm_list)) { + dev = to_device(dpm_list.next); get_device(dev); - if (dev->power.status >= DPM_OFF) { + if (dev->power.status >= DPM_OFF && !is_async(dev)) { int error; - dev->power.status = DPM_RESUMING; mutex_unlock(&dpm_list_mtx); - error = device_resume(dev, state); + error = device_resume(dev, state, false); mutex_lock(&dpm_list_mtx); if (error) @@ -554,6 +640,7 @@ static void dpm_resume(pm_message_t state) } list_splice(&list, &dpm_list); mutex_unlock(&dpm_list_mtx); + async_synchronize_full(); dpm_show_time(starttime, state, NULL); } @@ -564,7 +651,7 @@ static void dpm_resume(pm_message_t state) */ static void device_complete(struct device *dev, pm_message_t state) { - down(&dev->sem); + device_lock(dev); if (dev->class && dev->class->pm && dev->class->pm->complete) { pm_dev_dbg(dev, state, "completing class "); @@ -581,7 +668,7 @@ static void device_complete(struct device *dev, pm_message_t state) dev->bus->pm->complete(dev); } - up(&dev->sem); + device_unlock(dev); } /** @@ -670,10 +757,26 @@ static int device_suspend_noirq(struct device *dev, pm_message_t state) { int error = 0; + if (dev->class && dev->class->pm) { + pm_dev_dbg(dev, state, "LATE class "); + error = pm_noirq_op(dev, dev->class->pm, state); + if (error) + goto End; + } + + if (dev->type && dev->type->pm) { + pm_dev_dbg(dev, state, "LATE type "); + error = pm_noirq_op(dev, dev->type->pm, state); + if (error) + goto End; + } + if (dev->bus && dev->bus->pm) { pm_dev_dbg(dev, state, "LATE "); error = pm_noirq_op(dev, dev->bus->pm, state); } + +End: return error; } @@ -735,12 +838,17 @@ static int legacy_suspend(struct device *dev, pm_message_t state, * 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) +static int __device_suspend(struct device *dev, pm_message_t state, bool async) { int error = 0; - down(&dev->sem); + dpm_wait_for_children(dev, async); + device_lock(dev); + + if (async_error) + goto End; if (dev->class) { if (dev->class->pm) { @@ -772,12 +880,45 @@ static int device_suspend(struct device *dev, pm_message_t state) error = legacy_suspend(dev, state, dev->bus->suspend); } } + + if (!error) + dev->power.status = DPM_OFF; + End: - up(&dev->sem); + device_unlock(dev); + 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. @@ -790,13 +931,15 @@ static int dpm_suspend(pm_message_t state) INIT_LIST_HEAD(&list); mutex_lock(&dpm_list_mtx); + pm_transition = state; + async_error = 0; while (!list_empty(&dpm_list)) { struct device *dev = to_device(dpm_list.prev); get_device(dev); mutex_unlock(&dpm_list_mtx); - error = device_suspend(dev, state); + error = device_suspend(dev); mutex_lock(&dpm_list_mtx); if (error) { @@ -804,13 +947,17 @@ static int dpm_suspend(pm_message_t state) put_device(dev); break; } - dev->power.status = DPM_OFF; if (!list_empty(&dev->power.entry)) list_move(&dev->power.entry, &list); put_device(dev); + if (async_error) + break; } list_splice(&list, dpm_list.prev); mutex_unlock(&dpm_list_mtx); + async_synchronize_full(); + if (!error) + error = async_error; if (!error) dpm_show_time(starttime, state, NULL); return error; @@ -828,7 +975,7 @@ static int device_prepare(struct device *dev, pm_message_t state) { int error = 0; - down(&dev->sem); + device_lock(dev); if (dev->bus && dev->bus->pm && dev->bus->pm->prepare) { pm_dev_dbg(dev, state, "preparing "); @@ -852,7 +999,7 @@ static int device_prepare(struct device *dev, pm_message_t state) suspend_report_result(dev->class->pm->prepare, error); } End: - up(&dev->sem); + device_unlock(dev); return error; } @@ -936,3 +1083,15 @@ void __suspend_report_result(const char *function, void *fn, int 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 000000000000..2bb9b4cf59d7 --- /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 + * @is_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 index b8fa1aa5225a..698dde742587 100644 --- a/drivers/base/power/power.h +++ b/drivers/base/power/power.h @@ -12,10 +12,10 @@ static inline void pm_runtime_remove(struct device *dev) {} #ifdef CONFIG_PM_SLEEP -/* - * main.c - */ +/* 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) @@ -34,6 +34,7 @@ extern void device_pm_move_last(struct device *); static inline void device_pm_init(struct device *dev) { + spin_lock_init(&dev->power.lock); pm_runtime_init(dev); } @@ -59,6 +60,7 @@ static inline void device_pm_move_last(struct device *dev) {} extern int dpm_sysfs_add(struct device *); extern void dpm_sysfs_remove(struct device *); +extern void rpm_sysfs_remove(struct device *); #else /* CONFIG_PM */ diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c index f8b044e8aef7..126ca492dd08 100644 --- a/drivers/base/power/runtime.c +++ b/drivers/base/power/runtime.c @@ -2,17 +2,55 @@ * 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 <linux/jiffies.h> +#include "power.h" -static int __pm_runtime_resume(struct device *dev, bool from_wq); -static int __pm_request_idle(struct device *dev); -static int __pm_request_resume(struct device *dev); +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. @@ -40,62 +78,154 @@ static void pm_runtime_cancel_pending(struct device *dev) dev->power.request = RPM_REQ_NONE; } -/** - * __pm_runtime_idle - Notify device bus type if the device can be suspended. - * @dev: Device to notify the bus type about. +/* + * pm_runtime_autosuspend_expiration - Get a device's autosuspend-delay expiration time. + * @dev: Device to handle. * - * This function must be called under dev->power.lock with interrupts disabled. + * 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. */ -static int __pm_runtime_idle(struct device *dev) - __releases(&dev->power.lock) __acquires(&dev->power.lock) +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 (dev->power.idle_notification) - retval = -EINPROGRESS; else if (atomic_read(&dev->power.usage_count) > 0 - || dev->power.disable_depth > 0 - || dev->power.runtime_status != RPM_ACTIVE) + || 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.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; - if (dev->power.request_pending) { - /* - * If an idle notification request is pending, cancel it. Any - * other pending request takes precedence over us. - */ - if (dev->power.request == RPM_REQ_IDLE) { - dev->power.request = RPM_REQ_NONE; - } else if (dev->power.request != RPM_REQ_NONE) { - retval = -EAGAIN; - 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->bus && dev->bus->pm && dev->bus->pm->runtime_idle) { - spin_unlock_irq(&dev->power.lock); - - dev->bus->pm->runtime_idle(dev); + if (dev->bus && dev->bus->pm && dev->bus->pm->runtime_idle) + callback = dev->bus->pm->runtime_idle; + else if (dev->type && dev->type->pm && dev->type->pm->runtime_idle) + callback = dev->type->pm->runtime_idle; + else if (dev->class && dev->class->pm) + callback = dev->class->pm->runtime_idle; + else + callback = NULL; - spin_lock_irq(&dev->power.lock); - } else if (dev->type && dev->type->pm && dev->type->pm->runtime_idle) { + if (callback) { spin_unlock_irq(&dev->power.lock); - dev->type->pm->runtime_idle(dev); - - spin_lock_irq(&dev->power.lock); - } else if (dev->class && dev->class->pm - && dev->class->pm->runtime_idle) { - spin_unlock_irq(&dev->power.lock); - - dev->class->pm->runtime_idle(dev); + callback(dev); spin_lock_irq(&dev->power.lock); } @@ -108,74 +238,99 @@ static int __pm_runtime_idle(struct device *dev) } /** - * pm_runtime_idle - Notify device bus type if the device can be suspended. - * @dev: Device to notify the bus type about. + * 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. */ -int pm_runtime_idle(struct device *dev) +static int rpm_callback(int (*cb)(struct device *), struct device *dev) + __releases(&dev->power.lock) __acquires(&dev->power.lock) { int retval; - spin_lock_irq(&dev->power.lock); - retval = __pm_runtime_idle(dev); + if (!cb) + return -ENOSYS; + spin_unlock_irq(&dev->power.lock); + retval = cb(dev); + + spin_lock_irq(&dev->power.lock); + dev->power.runtime_error = retval; + return retval; } -EXPORT_SYMBOL_GPL(pm_runtime_idle); /** - * __pm_runtime_suspend - Carry out run-time suspend of given device. + * rpm_suspend - Carry out run-time suspend of given device. * @dev: Device to suspend. - * @from_wq: If set, the function has been called via pm_wq. + * @rpmflags: Flag bits. * - * Check if the device can be suspended and run the ->runtime_suspend() callback - * provided by its bus type. If another suspend has been started earlier, wait - * for it to finish. If an idle notification or suspend request is pending or - * scheduled, cancel it. + * 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). * * This function must be called under dev->power.lock with interrupts disabled. */ -int __pm_runtime_suspend(struct device *dev, bool from_wq) +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; - bool notify = false; - int retval = 0; + int retval; - dev_dbg(dev, "__pm_runtime_suspend()%s!\n", - from_wq ? " from workqueue" : ""); + dev_dbg(dev, "%s flags 0x%x\n", __func__, rpmflags); repeat: - if (dev->power.runtime_error) { - retval = -EINVAL; - goto out; - } + retval = rpm_check_suspend_allowed(dev); - /* Pending resume requests take precedence over us. */ - if (dev->power.request_pending - && dev->power.request == RPM_REQ_RESUME) { + 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_SUSPENDED) - retval = 1; - else if (dev->power.runtime_status == RPM_RESUMING - || dev->power.disable_depth > 0 - || atomic_read(&dev->power.usage_count) > 0) - retval = -EAGAIN; - else if (!pm_children_suspended(dev)) - retval = -EBUSY; - if (retval) - goto out; - if (dev->power.runtime_status == RPM_SUSPENDING) { DEFINE_WAIT(wait); - if (from_wq) { + if (rpmflags & (RPM_ASYNC | RPM_NOWAIT)) { retval = -EINPROGRESS; goto out; } @@ -197,46 +352,44 @@ int __pm_runtime_suspend(struct device *dev, bool from_wq) goto repeat; } - dev->power.runtime_status = RPM_SUSPENDING; 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; + } - if (dev->bus && dev->bus->pm && dev->bus->pm->runtime_suspend) { - spin_unlock_irq(&dev->power.lock); - - retval = dev->bus->pm->runtime_suspend(dev); - - spin_lock_irq(&dev->power.lock); - dev->power.runtime_error = retval; - } else if (dev->type && dev->type->pm - && dev->type->pm->runtime_suspend) { - spin_unlock_irq(&dev->power.lock); - - retval = dev->type->pm->runtime_suspend(dev); - - spin_lock_irq(&dev->power.lock); - dev->power.runtime_error = retval; - } else if (dev->class && dev->class->pm - && dev->class->pm->runtime_suspend) { - spin_unlock_irq(&dev->power.lock); - - retval = dev->class->pm->runtime_suspend(dev); + __update_runtime_status(dev, RPM_SUSPENDING); - spin_lock_irq(&dev->power.lock); - dev->power.runtime_error = retval; - } else { - retval = -ENOSYS; - } + if (dev->bus && dev->bus->pm && dev->bus->pm->runtime_suspend) + callback = dev->bus->pm->runtime_suspend; + else if (dev->type && dev->type->pm && dev->type->pm->runtime_suspend) + callback = dev->type->pm->runtime_suspend; + else if (dev->class && dev->class->pm) + callback = dev->class->pm->runtime_suspend; + else + callback = NULL; + retval = rpm_callback(callback, dev); if (retval) { - dev->power.runtime_status = RPM_ACTIVE; - pm_runtime_cancel_pending(dev); - - if (retval == -EAGAIN || retval == -EBUSY) { - notify = true; + __update_runtime_status(dev, RPM_ACTIVE); + dev->power.deferred_resume = 0; + if (retval == -EAGAIN || retval == -EBUSY) dev->power.runtime_error = 0; - } + else + pm_runtime_cancel_pending(dev); } else { - dev->power.runtime_status = RPM_SUSPENDED; + no_callback: + __update_runtime_status(dev, RPM_SUSPENDED); + pm_runtime_deactivate_timer(dev); if (dev->parent) { parent = dev->parent; @@ -246,14 +399,11 @@ int __pm_runtime_suspend(struct device *dev, bool from_wq) wake_up_all(&dev->power.wait_queue); if (dev->power.deferred_resume) { - __pm_runtime_resume(dev, false); + rpm_resume(dev, 0); retval = -EAGAIN; goto out; } - if (notify) - __pm_runtime_idle(dev); - if (parent && !parent->power.ignore_children) { spin_unlock_irq(&dev->power.lock); @@ -263,72 +413,69 @@ int __pm_runtime_suspend(struct device *dev, bool from_wq) } out: - dev_dbg(dev, "__pm_runtime_suspend() returns %d!\n", retval); - - return retval; -} - -/** - * pm_runtime_suspend - Carry out run-time suspend of given device. - * @dev: Device to suspend. - */ -int pm_runtime_suspend(struct device *dev) -{ - int retval; - - spin_lock_irq(&dev->power.lock); - retval = __pm_runtime_suspend(dev, false); - spin_unlock_irq(&dev->power.lock); + dev_dbg(dev, "%s returns %d\n", __func__, retval); return retval; } -EXPORT_SYMBOL_GPL(pm_runtime_suspend); /** - * __pm_runtime_resume - Carry out run-time resume of given device. + * rpm_resume - Carry out run-time resume of given device. * @dev: Device to resume. - * @from_wq: If set, the function has been called via pm_wq. + * @rpmflags: Flag bits. * - * Check if the device can be woken up and run the ->runtime_resume() callback - * provided by its bus type. If another resume has been started earlier, wait - * for it to finish. If there's a suspend running in parallel with this - * function, wait for it to finish and resume the device. Cancel any scheduled - * or pending requests. + * 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 imediately 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. */ -int __pm_runtime_resume(struct device *dev, bool from_wq) +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, "__pm_runtime_resume()%s!\n", - from_wq ? " from workqueue" : ""); + dev_dbg(dev, "%s flags 0x%x\n", __func__, rpmflags); repeat: - if (dev->power.runtime_error) { + if (dev->power.runtime_error) retval = -EINVAL; + else if (dev->power.disable_depth > 0) + retval = -EAGAIN; + if (retval) goto out; - } - pm_runtime_cancel_pending(dev); + /* + * 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) + if (dev->power.runtime_status == RPM_ACTIVE) { retval = 1; - else if (dev->power.disable_depth > 0) - retval = -EAGAIN; - if (retval) goto out; + } if (dev->power.runtime_status == RPM_RESUMING || dev->power.runtime_status == RPM_SUSPENDING) { DEFINE_WAIT(wait); - if (from_wq) { + if (rpmflags & (RPM_ASYNC | RPM_NOWAIT)) { if (dev->power.runtime_status == RPM_SUSPENDING) dev->power.deferred_resume = true; - retval = -EINPROGRESS; + else + retval = -EINPROGRESS; goto out; } @@ -350,6 +497,34 @@ int __pm_runtime_resume(struct device *dev, bool from_wq) 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 resume counter and resume it if @@ -367,7 +542,7 @@ int __pm_runtime_resume(struct device *dev, bool from_wq) */ if (!parent->power.disable_depth && !parent->power.ignore_children) { - __pm_runtime_resume(parent, false); + rpm_resume(parent, 0); if (parent->power.runtime_status != RPM_ACTIVE) retval = -EBUSY; } @@ -379,47 +554,34 @@ int __pm_runtime_resume(struct device *dev, bool from_wq) goto repeat; } - dev->power.runtime_status = RPM_RESUMING; - - if (dev->bus && dev->bus->pm && dev->bus->pm->runtime_resume) { - spin_unlock_irq(&dev->power.lock); - - retval = dev->bus->pm->runtime_resume(dev); - - spin_lock_irq(&dev->power.lock); - dev->power.runtime_error = retval; - } else if (dev->type && dev->type->pm - && dev->type->pm->runtime_resume) { - spin_unlock_irq(&dev->power.lock); - - retval = dev->type->pm->runtime_resume(dev); - - spin_lock_irq(&dev->power.lock); - dev->power.runtime_error = retval; - } else if (dev->class && dev->class->pm - && dev->class->pm->runtime_resume) { - spin_unlock_irq(&dev->power.lock); + if (dev->power.no_callbacks) + goto no_callback; /* Assume success. */ - retval = dev->class->pm->runtime_resume(dev); + __update_runtime_status(dev, RPM_RESUMING); - spin_lock_irq(&dev->power.lock); - dev->power.runtime_error = retval; - } else { - retval = -ENOSYS; - } + if (dev->bus && dev->bus->pm && dev->bus->pm->runtime_resume) + callback = dev->bus->pm->runtime_resume; + else if (dev->type && dev->type->pm && dev->type->pm->runtime_resume) + callback = dev->type->pm->runtime_resume; + else if (dev->class && dev->class->pm) + callback = dev->class->pm->runtime_resume; + else + callback = NULL; + retval = rpm_callback(callback, dev); if (retval) { - dev->power.runtime_status = RPM_SUSPENDED; + __update_runtime_status(dev, RPM_SUSPENDED); pm_runtime_cancel_pending(dev); } else { - dev->power.runtime_status = RPM_ACTIVE; + 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) - __pm_request_idle(dev); + rpm_idle(dev, RPM_ASYNC); out: if (parent) { @@ -430,26 +592,10 @@ int __pm_runtime_resume(struct device *dev, bool from_wq) spin_lock_irq(&dev->power.lock); } - dev_dbg(dev, "__pm_runtime_resume() returns %d!\n", retval); - - return retval; -} - -/** - * pm_runtime_resume - Carry out run-time resume of given device. - * @dev: Device to suspend. - */ -int pm_runtime_resume(struct device *dev) -{ - int retval; - - spin_lock_irq(&dev->power.lock); - retval = __pm_runtime_resume(dev, false); - spin_unlock_irq(&dev->power.lock); + dev_dbg(dev, "%s returns %d\n", __func__, retval); return retval; } -EXPORT_SYMBOL_GPL(pm_runtime_resume); /** * pm_runtime_work - Universal run-time PM work function. @@ -476,13 +622,16 @@ static void pm_runtime_work(struct work_struct *work) case RPM_REQ_NONE: break; case RPM_REQ_IDLE: - __pm_runtime_idle(dev); + rpm_idle(dev, RPM_NOWAIT); break; case RPM_REQ_SUSPEND: - __pm_runtime_suspend(dev, true); + rpm_suspend(dev, RPM_NOWAIT); + break; + case RPM_REQ_AUTOSUSPEND: + rpm_suspend(dev, RPM_NOWAIT | RPM_AUTO); break; case RPM_REQ_RESUME: - __pm_runtime_resume(dev, true); + rpm_resume(dev, RPM_NOWAIT); break; } @@ -491,117 +640,10 @@ static void pm_runtime_work(struct work_struct *work) } /** - * __pm_request_idle - Submit an idle notification request for given device. - * @dev: Device to handle. - * - * Check if the device's run-time PM status is correct for suspending the device - * and queue up a request to run __pm_runtime_idle() for it. - * - * This function must be called under dev->power.lock with interrupts disabled. - */ -static int __pm_request_idle(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 - || dev->power.runtime_status == RPM_SUSPENDED - || dev->power.runtime_status == RPM_SUSPENDING) - retval = -EAGAIN; - else if (!pm_children_suspended(dev)) - retval = -EBUSY; - if (retval) - return retval; - - if (dev->power.request_pending) { - /* Any requests other then RPM_REQ_IDLE take precedence. */ - if (dev->power.request == RPM_REQ_NONE) - dev->power.request = RPM_REQ_IDLE; - else if (dev->power.request != RPM_REQ_IDLE) - retval = -EAGAIN; - return retval; - } - - dev->power.request = RPM_REQ_IDLE; - dev->power.request_pending = true; - queue_work(pm_wq, &dev->power.work); - - return retval; -} - -/** - * pm_request_idle - Submit an idle notification request for given device. - * @dev: Device to handle. - */ -int pm_request_idle(struct device *dev) -{ - unsigned long flags; - int retval; - - spin_lock_irqsave(&dev->power.lock, flags); - retval = __pm_request_idle(dev); - spin_unlock_irqrestore(&dev->power.lock, flags); - - return retval; -} -EXPORT_SYMBOL_GPL(pm_request_idle); - -/** - * __pm_request_suspend - Submit a suspend request for given device. - * @dev: Device to suspend. - * - * This function must be called under dev->power.lock with interrupts disabled. - */ -static int __pm_request_suspend(struct device *dev) -{ - int retval = 0; - - if (dev->power.runtime_error) - return -EINVAL; - - if (dev->power.runtime_status == RPM_SUSPENDED) - retval = 1; - else if (atomic_read(&dev->power.usage_count) > 0 - || dev->power.disable_depth > 0) - retval = -EAGAIN; - else if (dev->power.runtime_status == RPM_SUSPENDING) - retval = -EINPROGRESS; - else if (!pm_children_suspended(dev)) - retval = -EBUSY; - if (retval < 0) - return retval; - - pm_runtime_deactivate_timer(dev); - - if (dev->power.request_pending) { - /* - * Pending resume requests take precedence over us, but we can - * overtake any other pending request. - */ - if (dev->power.request == RPM_REQ_RESUME) - retval = -EAGAIN; - else if (dev->power.request != RPM_REQ_SUSPEND) - dev->power.request = retval ? - RPM_REQ_NONE : RPM_REQ_SUSPEND; - return retval; - } else if (retval) { - return retval; - } - - dev->power.request = RPM_REQ_SUSPEND; - dev->power.request_pending = true; - queue_work(pm_wq, &dev->power.work); - - return 0; -} - -/** * 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 execute __pm_request_suspend() in that case. + * Check if the time is right and queue a suspend request. */ static void pm_suspend_timer_fn(unsigned long data) { @@ -615,7 +657,8 @@ static void pm_suspend_timer_fn(unsigned long data) /* If 'expire' is after 'jiffies' we've been called too early. */ if (expires > 0 && !time_after(expires, jiffies)) { dev->power.timer_expires = 0; - __pm_request_suspend(dev); + rpm_suspend(dev, dev->power.timer_autosuspends ? + (RPM_ASYNC | RPM_AUTO) : RPM_ASYNC); } spin_unlock_irqrestore(&dev->power.lock, flags); @@ -629,49 +672,25 @@ static void pm_suspend_timer_fn(unsigned long data) int pm_schedule_suspend(struct device *dev, unsigned int delay) { unsigned long flags; - int retval = 0; + int retval; spin_lock_irqsave(&dev->power.lock, flags); - if (dev->power.runtime_error) { - retval = -EINVAL; - goto out; - } - if (!delay) { - retval = __pm_request_suspend(dev); + retval = rpm_suspend(dev, RPM_ASYNC); goto out; } - pm_runtime_deactivate_timer(dev); - - if (dev->power.request_pending) { - /* - * Pending resume requests take precedence over us, but any - * other pending requests have to be canceled. - */ - if (dev->power.request == RPM_REQ_RESUME) { - retval = -EAGAIN; - goto out; - } - dev->power.request = RPM_REQ_NONE; - } - - if (dev->power.runtime_status == RPM_SUSPENDED) - retval = 1; - else if (dev->power.runtime_status == RPM_SUSPENDING) - retval = -EINPROGRESS; - else if (atomic_read(&dev->power.usage_count) > 0 - || dev->power.disable_depth > 0) - retval = -EAGAIN; - else if (!pm_children_suspended(dev)) - retval = -EBUSY; + 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); - if (!dev->power.timer_expires) - dev->power.timer_expires = 1; + dev->power.timer_expires += !dev->power.timer_expires; + dev->power.timer_autosuspends = 0; mod_timer(&dev->power.suspend_timer, dev->power.timer_expires); out: @@ -682,103 +701,88 @@ int pm_schedule_suspend(struct device *dev, unsigned int delay) EXPORT_SYMBOL_GPL(pm_schedule_suspend); /** - * pm_request_resume - Submit a resume request for given device. - * @dev: Device to resume. + * __pm_runtime_idle - Entry point for run-time idle operations. + * @dev: Device to send idle notification for. + * @rpmflags: Flag bits. * - * This function must be called under dev->power.lock with interrupts disabled. + * 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. */ -static int __pm_request_resume(struct device *dev) +int __pm_runtime_idle(struct device *dev, int rpmflags) { - int retval = 0; - - if (dev->power.runtime_error) - return -EINVAL; - - if (dev->power.runtime_status == RPM_ACTIVE) - retval = 1; - else if (dev->power.runtime_status == RPM_RESUMING) - retval = -EINPROGRESS; - else if (dev->power.disable_depth > 0) - retval = -EAGAIN; - if (retval < 0) - return retval; - - pm_runtime_deactivate_timer(dev); + unsigned long flags; + int retval; - if (dev->power.runtime_status == RPM_SUSPENDING) { - dev->power.deferred_resume = true; - return retval; + if (rpmflags & RPM_GET_PUT) { + if (!atomic_dec_and_test(&dev->power.usage_count)) + return 0; } - if (dev->power.request_pending) { - /* If non-resume request is pending, we can overtake it. */ - dev->power.request = retval ? RPM_REQ_NONE : RPM_REQ_RESUME; - return retval; - } - if (retval) - return retval; - dev->power.request = RPM_REQ_RESUME; - dev->power.request_pending = true; - queue_work(pm_wq, &dev->power.work); + 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_request_resume - Submit a resume request for given device. - * @dev: Device to resume. + * __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_request_resume(struct device *dev) +int __pm_runtime_suspend(struct device *dev, int rpmflags) { unsigned long flags; int retval; + if (rpmflags & RPM_GET_PUT) { + if (!atomic_dec_and_test(&dev->power.usage_count)) + return 0; + } + spin_lock_irqsave(&dev->power.lock, flags); - retval = __pm_request_resume(dev); + retval = rpm_suspend(dev, rpmflags); spin_unlock_irqrestore(&dev->power.lock, flags); return retval; } -EXPORT_SYMBOL_GPL(pm_request_resume); +EXPORT_SYMBOL_GPL(__pm_runtime_suspend); /** - * __pm_runtime_get - Reference count a device and wake it up, if necessary. - * @dev: Device to handle. - * @sync: If set and the device is suspended, resume it synchronously. + * __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. * - * Increment the usage count of the device and resume it or submit a resume - * request for it, depending on the value of @sync. + * This routine may be called in atomic context if the RPM_ASYNC flag is set. */ -int __pm_runtime_get(struct device *dev, bool sync) +int __pm_runtime_resume(struct device *dev, int rpmflags) { + unsigned long flags; int retval; - atomic_inc(&dev->power.usage_count); - retval = sync ? pm_runtime_resume(dev) : pm_request_resume(dev); - - return retval; -} -EXPORT_SYMBOL_GPL(__pm_runtime_get); + if (rpmflags & RPM_GET_PUT) + atomic_inc(&dev->power.usage_count); -/** - * __pm_runtime_put - Decrement the device's usage counter and notify its bus. - * @dev: Device to handle. - * @sync: If the device's bus type is to be notified, do that synchronously. - * - * Decrement the usage count of the device and if it reaches zero, carry out a - * synchronous idle notification or submit an idle notification request for it, - * depending on the value of @sync. - */ -int __pm_runtime_put(struct device *dev, bool sync) -{ - int retval = 0; - - if (atomic_dec_and_test(&dev->power.usage_count)) - retval = sync ? pm_runtime_idle(dev) : pm_request_idle(dev); + 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_put); +EXPORT_SYMBOL_GPL(__pm_runtime_resume); /** * __pm_runtime_set_status - Set run-time PM status of a device. @@ -848,7 +852,7 @@ int __pm_runtime_set_status(struct device *dev, unsigned int status) } out_set: - dev->power.runtime_status = status; + __update_runtime_status(dev, status); dev->power.runtime_error = 0; out: spin_unlock_irqrestore(&dev->power.lock, flags); @@ -929,7 +933,7 @@ int pm_runtime_barrier(struct device *dev) if (dev->power.request_pending && dev->power.request == RPM_REQ_RESUME) { - __pm_runtime_resume(dev, false); + rpm_resume(dev, 0); retval = 1; } @@ -978,7 +982,7 @@ void __pm_runtime_disable(struct device *dev, bool check_resume) */ pm_runtime_get_noresume(dev); - __pm_runtime_resume(dev, false); + rpm_resume(dev, 0); pm_runtime_put_noidle(dev); } @@ -1011,13 +1015,154 @@ void pm_runtime_enable(struct device *dev) 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); + +/** + * 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; + + 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) { - spin_lock_init(&dev->power.lock); - dev->power.runtime_status = RPM_SUSPENDED; dev->power.idle_notification = false; @@ -1028,10 +1173,12 @@ void pm_runtime_init(struct device *dev) 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; diff --git a/drivers/base/power/sysfs.c b/drivers/base/power/sysfs.c index 596aeecfdffe..0b1e46bf3e56 100644 --- a/drivers/base/power/sysfs.c +++ b/drivers/base/power/sysfs.c @@ -4,9 +4,27 @@ #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 @@ -38,11 +56,164 @@ * 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 + static ssize_t wake_show(struct device * dev, struct device_attribute *attr, char * buf) { @@ -77,16 +248,259 @@ wake_store(struct device * dev, struct device_attribute *attr, static DEVICE_ATTR(wakeup, 0644, wake_show, wake_store); +#ifdef CONFIG_PM_SLEEP +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[] = { &dev_attr_wakeup.attr, +#ifdef CONFIG_PM_SLEEP + &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 +#ifdef CONFIG_PM_ADVANCED_DEBUG + &dev_attr_async.attr, +#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 NULL, }; static struct attribute_group pm_attr_group = { - .name = "power", + .name = power_group_name, .attrs = power_attrs, }; +#ifdef CONFIG_PM_RUNTIME + +static struct attribute *runtime_attrs[] = { +#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, + 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 == 0 && !dev->power.no_callbacks) { + rc = sysfs_merge_group(&dev->kobj, &pm_runtime_attr_group); + if (rc) + sysfs_remove_group(&dev->kobj, &pm_attr_group); + } + return rc; +} + +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_remove_group(&dev->kobj, &pm_attr_group); +} + +#else /* CONFIG_PM_RUNTIME */ + int dpm_sysfs_add(struct device * dev) { return sysfs_create_group(&dev->kobj, &pm_attr_group); @@ -96,3 +510,5 @@ void dpm_sysfs_remove(struct device * dev) { sysfs_remove_group(&dev->kobj, &pm_attr_group); } + +#endif diff --git a/drivers/base/power/trace.c b/drivers/base/power/trace.c index 0a1a2c4dbc6e..9f4258df4cfd 100644 --- a/drivers/base/power/trace.c +++ b/drivers/base/power/trace.c @@ -188,8 +188,10 @@ static int show_file_hash(unsigned int value) static int show_dev_hash(unsigned int value) { int match = 0; - struct list_head *entry = dpm_list.prev; + 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); @@ -199,11 +201,43 @@ static int show_dev_hash(unsigned int value) } 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(); diff --git a/drivers/base/power/wakeup.c b/drivers/base/power/wakeup.c new file mode 100644 index 000000000000..71c5528e1c35 --- /dev/null +++ b/drivers/base/power/wakeup.c @@ -0,0 +1,704 @@ +/* + * 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; + +/* The counter of registered wakeup events. */ +static atomic_t event_count = ATOMIC_INIT(0); +/* A preserved old value of event_count. */ +static unsigned int saved_count; +/* The counter of wakeup events being processed. */ +static atomic_t events_in_progress = ATOMIC_INIT(0); + +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); + synchronize_rcu(); +} +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_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(); + + atomic_inc(&events_in_progress); +} + +/** + * __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); + + /* + * event_count has to be incremented before events_in_progress is + * modified, so that the callers of pm_check_wakeup_events() and + * pm_save_wakeup_count() don't see the old value of event_count and + * events_in_progress equal to zero at the same time. + */ + atomic_inc(&event_count); + smp_mb__before_atomic_dec(); + atomic_dec(&events_in_progress); +} + +/** + * __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_check_wakeup_events - Check for new wakeup events. + * + * Compare the current number of registered wakeup events with its preserved + * value from the past to check if new wakeup events have been registered since + * the old value was stored. Check if the current number of wakeup events being + * processed is zero. + */ +bool pm_check_wakeup_events(void) +{ + unsigned long flags; + bool ret = true; + + spin_lock_irqsave(&events_lock, flags); + if (events_check_enabled) { + ret = ((unsigned int)atomic_read(&event_count) == saved_count) + && !atomic_read(&events_in_progress); + 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) +{ + bool ret; + + if (capable(CAP_SYS_ADMIN)) + events_check_enabled = false; + + while (atomic_read(&events_in_progress) && !signal_pending(current)) { + pm_wakeup_update_hit_counts(); + schedule_timeout_interruptible(msecs_to_jiffies(TIMEOUT)); + } + + ret = !atomic_read(&events_in_progress); + *count = atomic_read(&event_count); + return ret; +} + +/** + * 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 to be used by pm_check_wakeup_events() + * and return true. Otherwise return false. + */ +bool pm_save_wakeup_count(unsigned int count) +{ + bool ret = false; + + spin_lock_irq(&events_lock); + if (count == (unsigned int)atomic_read(&event_count) + && !atomic_read(&events_in_progress)) { + saved_count = count; + events_check_enabled = true; + ret = true; + } + spin_unlock_irq(&events_lock); + if (!ret) + pm_wakeup_update_hit_counts(); + return ret; +} + +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 index 0d903909af7e..1667aaf4fde6 100644 --- a/drivers/base/sys.c +++ b/drivers/base/sys.c @@ -17,7 +17,6 @@ #include <linux/module.h> #include <linux/kernel.h> #include <linux/init.h> -#include <linux/slab.h> #include <linux/string.h> #include <linux/pm.h> #include <linux/device.h> @@ -54,7 +53,7 @@ sysdev_store(struct kobject *kobj, struct attribute *attr, return -EIO; } -static struct sysfs_ops sysfs_ops = { +static const struct sysfs_ops sysfs_ops = { .show = sysdev_show, .store = sysdev_store, }; @@ -89,7 +88,7 @@ static ssize_t sysdev_class_show(struct kobject *kobj, struct attribute *attr, struct sysdev_class_attribute *class_attr = to_sysdev_class_attr(attr); if (class_attr->show) - return class_attr->show(class, buffer); + return class_attr->show(class, class_attr, buffer); return -EIO; } @@ -100,11 +99,11 @@ static ssize_t sysdev_class_store(struct kobject *kobj, struct attribute *attr, struct sysdev_class_attribute *class_attr = to_sysdev_class_attr(attr); if (class_attr->store) - return class_attr->store(class, buffer, count); + return class_attr->store(class, class_attr, buffer, count); return -EIO; } -static struct sysfs_ops sysfs_class_ops = { +static const struct sysfs_ops sysfs_class_ops = { .show = sysdev_class_show, .store = sysdev_class_store, }; @@ -145,13 +144,20 @@ int sysdev_class_register(struct sysdev_class *cls) if (retval) return retval; - return kset_register(&cls->kset); + 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); } @@ -426,13 +432,13 @@ int sysdev_suspend(pm_message_t state) /* resume current sysdev */ cls_driver: drv = NULL; - printk(KERN_ERR "Class suspend failed for %s\n", - kobject_name(&sysdev->kobj)); + printk(KERN_ERR "Class suspend failed for %s: %d\n", + kobject_name(&sysdev->kobj), ret); aux_driver: if (drv) - printk(KERN_ERR "Class driver suspend failed for %s\n", - kobject_name(&sysdev->kobj)); + printk(KERN_ERR "Class driver suspend failed for %s: %d\n", + kobject_name(&sysdev->kobj), ret); list_for_each_entry(err_drv, &cls->drivers, entry) { if (err_drv == drv) break; diff --git a/drivers/base/topology.c b/drivers/base/topology.c index bf6b13206d00..f6f37a05a0c3 100644 --- a/drivers/base/topology.c +++ b/drivers/base/topology.c @@ -45,7 +45,8 @@ static ssize_t show_##name(struct sys_device *dev, \ return sprintf(buf, "%d\n", topology_##name(cpu)); \ } -#if defined(topology_thread_cpumask) || defined(topology_core_cpumask) +#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; @@ -114,6 +115,14 @@ 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, @@ -121,6 +130,11 @@ static struct attribute *default_attrs[] = { &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 }; @@ -162,7 +176,7 @@ static int __cpuinit topology_cpu_callback(struct notifier_block *nfb, topology_remove_dev(cpu); break; } - return rc ? NOTIFY_BAD : NOTIFY_OK; + return notifier_from_errno(rc); } static int __cpuinit topology_sysfs_init(void) |