linux/drivers/base/core.c

2145 lines
54 KiB
C
Raw Normal View History

/*
* drivers/base/core.c - core driver model code (device registration, etc)
*
* Copyright (c) 2002-3 Patrick Mochel
* Copyright (c) 2002-3 Open Source Development Labs
* Copyright (c) 2006 Greg Kroah-Hartman <gregkh@suse.de>
* Copyright (c) 2006 Novell, Inc.
*
* This file is released under the GPLv2
*
*/
#include <linux/device.h>
#include <linux/err.h>
#include <linux/init.h>
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/string.h>
#include <linux/kdev_t.h>
Driver core: add notification of bus events I finally did as you suggested and added the notifier to the struct bus_type itself. There are still problems to be expected is something attaches to a bus type where the code can hook in different struct device sub-classes (which is imho a big bogosity but I won't even try to argue that case now) but it will solve nicely a number of issues I've had so far. That also means that clients interested in registering for such notifications have to do it before devices are added and after bus types are registered. Fortunately, most bus types that matter for the various usage scenarios I have in mind are registerd at postcore_initcall time, which means I have a really nice spot at arch_initcall time to add my notifiers. There are 4 notifications provided. Device being added (before hooked to the bus) and removed (failure of previous case or after being unhooked from the bus), along with driver being bound to a device and about to be unbound. The usage I have for these are: - The 2 first ones are used to maintain a struct device_ext that is hooked to struct device.firmware_data. This structure contains for now a pointer to the Open Firmware node related to the device (if any), the NUMA node ID (for quick access to it) and the DMA operations pointers & iommu table instance for DMA to/from this device. For bus types I own (like IBM VIO or EBUS), I just maintain that structure directly from the bus code when creating the devices. But for bus types managed by generic code like PCI or platform (actually, of_platform which is a variation of platform linked to Open Firmware device-tree), I need this notifier. - The other two ones have a completely different usage scenario. I have cases where multiple devices and their drivers depend on each other. For example, the IBM EMAC network driver needs to attach to a MAL DMA engine which is a separate device, and a PHY interface which is also a separate device. They are all of_platform_device's (well, about to be with my upcoming patches) but there is no say in what precise order the core will "probe" them and instanciate the various modules. The solution I found for that is to have the drivers for emac to use multithread_probe, and wait for a driver to be bound to the target MAL and PHY control devices (the device-tree contains reference to the MAL and PHY interface nodes, which I can then match to of_platform_devices). Right now, I've been polling, but with that notifier, I can more cleanly wait (with a timeout of course). Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2006-10-25 11:44:59 +08:00
#include <linux/notifier.h>
#include <linux/of.h>
#include <linux/of_device.h>
#include <linux/genhd.h>
#include <linux/kallsyms.h>
#include <linux/mutex.h>
#include <linux/pm_runtime.h>
#include <linux/netdevice.h>
#include <linux/sysfs.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 int __init sysfs_deprecated_setup(char *arg)
{
return kstrtol(arg, 10, &sysfs_deprecated);
}
early_param("sysfs.deprecated", sysfs_deprecated_setup);
#endif
int (*platform_notify)(struct device *dev) = NULL;
int (*platform_notify_remove)(struct device *dev) = NULL;
static struct kobject *dev_kobj;
struct kobject *sysfs_dev_char_kobj;
struct kobject *sysfs_dev_block_kobj;
driver core / ACPI: Avoid device hot remove locking issues device_hotplug_lock is held around the acpi_bus_trim() call in acpi_scan_hot_remove() which generally removes devices (it removes ACPI device objects at least, but it may also remove "physical" device objects through .detach() callbacks of ACPI scan handlers). Thus, potentially, device sysfs attributes are removed under that lock and to remove those attributes it is necessary to hold the s_active references of their directory entries for writing. On the other hand, the execution of a .show() or .store() callback from a sysfs attribute is carried out with that attribute's s_active reference held for reading. Consequently, if any device sysfs attribute that may be removed from within acpi_scan_hot_remove() through acpi_bus_trim() has a .store() or .show() callback which acquires device_hotplug_lock, the execution of that callback may deadlock with the removal of the attribute. [Unfortunately, the "online" device attribute of CPUs and memory blocks is one of them.] To avoid such deadlocks, make all of the sysfs attribute callbacks that need to lock device hotplug, for example store_online(), use a special function, lock_device_hotplug_sysfs(), to lock device hotplug and return the result of that function immediately if it is not zero. This will cause the s_active reference of the directory entry in question to be released and the syscall to be restarted if device_hotplug_lock cannot be acquired. [show_online() actually doesn't need to lock device hotplug, but it is useful to serialize it with respect to device_offline() and device_online() for the same device (in case user space attempts to run them concurrently) which can be done with the help of device_lock().] Reported-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Reported-and-tested-by: Gu Zheng <guz.fnst@cn.fujitsu.com> Suggested-by: Tejun Heo <tj@kernel.org> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Acked-by: Toshi Kani <toshi.kani@hp.com>
2013-08-29 03:41:01 +08:00
static DEFINE_MUTEX(device_hotplug_lock);
void lock_device_hotplug(void)
{
mutex_lock(&device_hotplug_lock);
}
void unlock_device_hotplug(void)
{
mutex_unlock(&device_hotplug_lock);
}
int lock_device_hotplug_sysfs(void)
{
if (mutex_trylock(&device_hotplug_lock))
return 0;
/* Avoid busy looping (5 ms of sleep should do). */
msleep(5);
return restart_syscall();
}
#ifdef CONFIG_BLOCK
static inline int device_is_not_partition(struct device *dev)
{
return !(dev->type == &part_type);
}
#else
static inline int device_is_not_partition(struct device *dev)
{
return 1;
}
#endif
/**
* dev_driver_string - Return a device's driver name, if at all possible
* @dev: struct device to get the name of
*
* Will return the device's driver's name if it is bound to a device. If
* the device is not bound to a driver, it will return the name of the bus
* it is attached to. If it is not attached to a bus either, an empty
* string will be returned.
*/
const char *dev_driver_string(const struct device *dev)
{
struct device_driver *drv;
/* dev->driver can change to NULL underneath us because of unbinding,
* so be careful about accessing it. dev->bus and dev->class should
* never change once they are set, so they don't need special care.
*/
drv = ACCESS_ONCE(dev->driver);
return drv ? drv->name :
(dev->bus ? dev->bus->name :
(dev->class ? dev->class->name : ""));
}
EXPORT_SYMBOL(dev_driver_string);
#define to_dev_attr(_attr) container_of(_attr, struct device_attribute, attr)
static ssize_t dev_attr_show(struct kobject *kobj, struct attribute *attr,
char *buf)
{
struct device_attribute *dev_attr = to_dev_attr(attr);
struct device *dev = kobj_to_dev(kobj);
ssize_t ret = -EIO;
if (dev_attr->show)
ret = dev_attr->show(dev, dev_attr, buf);
if (ret >= (ssize_t)PAGE_SIZE) {
print_symbol("dev_attr_show: %s returned bad count\n",
(unsigned long)dev_attr->show);
}
return ret;
}
static ssize_t dev_attr_store(struct kobject *kobj, struct attribute *attr,
const char *buf, size_t count)
{
struct device_attribute *dev_attr = to_dev_attr(attr);
struct device *dev = kobj_to_dev(kobj);
ssize_t ret = -EIO;
if (dev_attr->store)
ret = dev_attr->store(dev, dev_attr, buf, count);
return ret;
}
static const struct sysfs_ops dev_sysfs_ops = {
.show = dev_attr_show,
.store = dev_attr_store,
};
#define to_ext_attr(x) container_of(x, struct dev_ext_attribute, attr)
ssize_t device_store_ulong(struct device *dev,
struct device_attribute *attr,
const char *buf, size_t size)
{
struct dev_ext_attribute *ea = to_ext_attr(attr);
char *end;
unsigned long new = simple_strtoul(buf, &end, 0);
if (end == buf)
return -EINVAL;
*(unsigned long *)(ea->var) = new;
/* Always return full write size even if we didn't consume all */
return size;
}
EXPORT_SYMBOL_GPL(device_store_ulong);
ssize_t device_show_ulong(struct device *dev,
struct device_attribute *attr,
char *buf)
{
struct dev_ext_attribute *ea = to_ext_attr(attr);
return snprintf(buf, PAGE_SIZE, "%lx\n", *(unsigned long *)(ea->var));
}
EXPORT_SYMBOL_GPL(device_show_ulong);
ssize_t device_store_int(struct device *dev,
struct device_attribute *attr,
const char *buf, size_t size)
{
struct dev_ext_attribute *ea = to_ext_attr(attr);
char *end;
long new = simple_strtol(buf, &end, 0);
if (end == buf || new > INT_MAX || new < INT_MIN)
return -EINVAL;
*(int *)(ea->var) = new;
/* Always return full write size even if we didn't consume all */
return size;
}
EXPORT_SYMBOL_GPL(device_store_int);
ssize_t device_show_int(struct device *dev,
struct device_attribute *attr,
char *buf)
{
struct dev_ext_attribute *ea = to_ext_attr(attr);
return snprintf(buf, PAGE_SIZE, "%d\n", *(int *)(ea->var));
}
EXPORT_SYMBOL_GPL(device_show_int);
ssize_t device_store_bool(struct device *dev, struct device_attribute *attr,
const char *buf, size_t size)
{
struct dev_ext_attribute *ea = to_ext_attr(attr);
if (strtobool(buf, ea->var) < 0)
return -EINVAL;
return size;
}
EXPORT_SYMBOL_GPL(device_store_bool);
ssize_t device_show_bool(struct device *dev, struct device_attribute *attr,
char *buf)
{
struct dev_ext_attribute *ea = to_ext_attr(attr);
return snprintf(buf, PAGE_SIZE, "%d\n", *(bool *)(ea->var));
}
EXPORT_SYMBOL_GPL(device_show_bool);
/**
* device_release - free device structure.
* @kobj: device's kobject.
*
* This is called once the reference count for the object
* reaches 0. We forward the call to the device's release
* method, which should handle actually freeing the structure.
*/
static void device_release(struct kobject *kobj)
{
struct device *dev = kobj_to_dev(kobj);
struct device_private *p = dev->p;
/*
* Some platform devices are driven without driver attached
* and managed resources may have been acquired. Make sure
* all resources are released.
*
* Drivers still can add resources into device after device
* is deleted but alive, so release devres here to avoid
* possible memory leak.
*/
devres_release_all(dev);
if (dev->release)
dev->release(dev);
else if (dev->type && dev->type->release)
dev->type->release(dev);
else if (dev->class && dev->class->dev_release)
dev->class->dev_release(dev);
else
WARN(1, KERN_ERR "Device '%s' does not have a release() "
"function, it is broken and must be fixed.\n",
dev_name(dev));
kfree(p);
}
static const void *device_namespace(struct kobject *kobj)
{
struct device *dev = kobj_to_dev(kobj);
const void *ns = NULL;
if (dev->class && dev->class->ns_type)
ns = dev->class->namespace(dev);
return ns;
}
static struct kobj_type device_ktype = {
.release = device_release,
.sysfs_ops = &dev_sysfs_ops,
.namespace = device_namespace,
};
static int dev_uevent_filter(struct kset *kset, struct kobject *kobj)
{
struct kobj_type *ktype = get_ktype(kobj);
if (ktype == &device_ktype) {
struct device *dev = kobj_to_dev(kobj);
if (dev->bus)
return 1;
if (dev->class)
return 1;
}
return 0;
}
static const char *dev_uevent_name(struct kset *kset, struct kobject *kobj)
{
struct device *dev = kobj_to_dev(kobj);
if (dev->bus)
return dev->bus->name;
if (dev->class)
return dev->class->name;
return NULL;
}
static int dev_uevent(struct kset *kset, struct kobject *kobj,
struct kobj_uevent_env *env)
{
struct device *dev = kobj_to_dev(kobj);
int retval = 0;
/* add device node properties if present */
if (MAJOR(dev->devt)) {
const char *tmp;
const char *name;
umode_t mode = 0;
kuid_t uid = GLOBAL_ROOT_UID;
kgid_t gid = GLOBAL_ROOT_GID;
add_uevent_var(env, "MAJOR=%u", MAJOR(dev->devt));
add_uevent_var(env, "MINOR=%u", MINOR(dev->devt));
name = device_get_devnode(dev, &mode, &uid, &gid, &tmp);
if (name) {
add_uevent_var(env, "DEVNAME=%s", name);
if (mode)
add_uevent_var(env, "DEVMODE=%#o", mode & 0777);
if (!uid_eq(uid, GLOBAL_ROOT_UID))
add_uevent_var(env, "DEVUID=%u", from_kuid(&init_user_ns, uid));
if (!gid_eq(gid, GLOBAL_ROOT_GID))
add_uevent_var(env, "DEVGID=%u", from_kgid(&init_user_ns, gid));
kfree(tmp);
}
}
if (dev->type && dev->type->name)
add_uevent_var(env, "DEVTYPE=%s", dev->type->name);
if (dev->driver)
add_uevent_var(env, "DRIVER=%s", dev->driver->name);
/* Add common DT information about the device */
of_device_uevent(dev, env);
/* have the bus specific function add its stuff */
if (dev->bus && dev->bus->uevent) {
retval = dev->bus->uevent(dev, env);
if (retval)
pr_debug("device: '%s': %s: bus uevent() returned %d\n",
dev_name(dev), __func__, retval);
}
/* have the class specific function add its stuff */
if (dev->class && dev->class->dev_uevent) {
retval = dev->class->dev_uevent(dev, env);
if (retval)
pr_debug("device: '%s': %s: class uevent() "
"returned %d\n", dev_name(dev),
__func__, retval);
}
/* have the device type specific function add its stuff */
if (dev->type && dev->type->uevent) {
retval = dev->type->uevent(dev, env);
if (retval)
pr_debug("device: '%s': %s: dev_type uevent() "
"returned %d\n", dev_name(dev),
__func__, retval);
}
return retval;
}
static const struct kset_uevent_ops device_uevent_ops = {
.filter = dev_uevent_filter,
.name = dev_uevent_name,
.uevent = dev_uevent,
};
static ssize_t uevent_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
struct kobject *top_kobj;
struct kset *kset;
struct kobj_uevent_env *env = NULL;
int i;
size_t count = 0;
int retval;
/* search the kset, the device belongs to */
top_kobj = &dev->kobj;
while (!top_kobj->kset && top_kobj->parent)
top_kobj = top_kobj->parent;
if (!top_kobj->kset)
goto out;
kset = top_kobj->kset;
if (!kset->uevent_ops || !kset->uevent_ops->uevent)
goto out;
/* respect filter */
if (kset->uevent_ops && kset->uevent_ops->filter)
if (!kset->uevent_ops->filter(kset, &dev->kobj))
goto out;
env = kzalloc(sizeof(struct kobj_uevent_env), GFP_KERNEL);
if (!env)
return -ENOMEM;
/* let the kset specific function add its keys */
retval = kset->uevent_ops->uevent(kset, &dev->kobj, env);
if (retval)
goto out;
/* copy keys to file */
for (i = 0; i < env->envp_idx; i++)
count += sprintf(&buf[count], "%s\n", env->envp[i]);
out:
kfree(env);
return count;
}
static ssize_t uevent_store(struct device *dev, struct device_attribute *attr,
const char *buf, size_t count)
{
enum kobject_action action;
if (kobject_action_type(buf, count, &action) == 0)
kobject_uevent(&dev->kobj, action);
else
dev_err(dev, "uevent: unknown action-string\n");
return count;
}
static DEVICE_ATTR_RW(uevent);
static ssize_t online_show(struct device *dev, struct device_attribute *attr,
Driver core: Add offline/online device operations In some cases, graceful hot-removal of devices is not possible, although in principle the devices in question support hotplug. For example, that may happen for the last CPU in the system or for memory modules holding kernel memory. In those cases it is nice to be able to check if the given device can be gracefully hot-removed before triggering a removal procedure that cannot be aborted or reversed. Unfortunately, however, the kernel currently doesn't provide any support for that. To address that deficiency, introduce support for offline and online operations that can be performed on devices, respectively, before a hot-removal and in case when it is necessary (or convenient) to put a device back online after a successful offline (that has not been followed by removal). The idea is that the offline will fail whenever the given device cannot be gracefully removed from the system and it will not be allowed to use the device after a successful offline (until a subsequent online) in analogy with the existing CPU offline/online mechanism. For now, the offline and online operations are introduced at the bus type level, as that should be sufficient for the most urgent use cases (CPUs and memory modules). In the future, however, the approach may be extended to cover some more complicated device offline/online scenarios involving device drivers etc. The lock_device_hotplug() and unlock_device_hotplug() functions are introduced because subsequent patches need to put larger pieces of code under device_hotplug_lock to prevent race conditions between device offline and removal from happening. Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Reviewed-by: Toshi Kani <toshi.kani@hp.com>
2013-05-03 04:15:29 +08:00
char *buf)
{
bool val;
driver core / ACPI: Avoid device hot remove locking issues device_hotplug_lock is held around the acpi_bus_trim() call in acpi_scan_hot_remove() which generally removes devices (it removes ACPI device objects at least, but it may also remove "physical" device objects through .detach() callbacks of ACPI scan handlers). Thus, potentially, device sysfs attributes are removed under that lock and to remove those attributes it is necessary to hold the s_active references of their directory entries for writing. On the other hand, the execution of a .show() or .store() callback from a sysfs attribute is carried out with that attribute's s_active reference held for reading. Consequently, if any device sysfs attribute that may be removed from within acpi_scan_hot_remove() through acpi_bus_trim() has a .store() or .show() callback which acquires device_hotplug_lock, the execution of that callback may deadlock with the removal of the attribute. [Unfortunately, the "online" device attribute of CPUs and memory blocks is one of them.] To avoid such deadlocks, make all of the sysfs attribute callbacks that need to lock device hotplug, for example store_online(), use a special function, lock_device_hotplug_sysfs(), to lock device hotplug and return the result of that function immediately if it is not zero. This will cause the s_active reference of the directory entry in question to be released and the syscall to be restarted if device_hotplug_lock cannot be acquired. [show_online() actually doesn't need to lock device hotplug, but it is useful to serialize it with respect to device_offline() and device_online() for the same device (in case user space attempts to run them concurrently) which can be done with the help of device_lock().] Reported-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Reported-and-tested-by: Gu Zheng <guz.fnst@cn.fujitsu.com> Suggested-by: Tejun Heo <tj@kernel.org> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Acked-by: Toshi Kani <toshi.kani@hp.com>
2013-08-29 03:41:01 +08:00
device_lock(dev);
Driver core: Add offline/online device operations In some cases, graceful hot-removal of devices is not possible, although in principle the devices in question support hotplug. For example, that may happen for the last CPU in the system or for memory modules holding kernel memory. In those cases it is nice to be able to check if the given device can be gracefully hot-removed before triggering a removal procedure that cannot be aborted or reversed. Unfortunately, however, the kernel currently doesn't provide any support for that. To address that deficiency, introduce support for offline and online operations that can be performed on devices, respectively, before a hot-removal and in case when it is necessary (or convenient) to put a device back online after a successful offline (that has not been followed by removal). The idea is that the offline will fail whenever the given device cannot be gracefully removed from the system and it will not be allowed to use the device after a successful offline (until a subsequent online) in analogy with the existing CPU offline/online mechanism. For now, the offline and online operations are introduced at the bus type level, as that should be sufficient for the most urgent use cases (CPUs and memory modules). In the future, however, the approach may be extended to cover some more complicated device offline/online scenarios involving device drivers etc. The lock_device_hotplug() and unlock_device_hotplug() functions are introduced because subsequent patches need to put larger pieces of code under device_hotplug_lock to prevent race conditions between device offline and removal from happening. Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Reviewed-by: Toshi Kani <toshi.kani@hp.com>
2013-05-03 04:15:29 +08:00
val = !dev->offline;
driver core / ACPI: Avoid device hot remove locking issues device_hotplug_lock is held around the acpi_bus_trim() call in acpi_scan_hot_remove() which generally removes devices (it removes ACPI device objects at least, but it may also remove "physical" device objects through .detach() callbacks of ACPI scan handlers). Thus, potentially, device sysfs attributes are removed under that lock and to remove those attributes it is necessary to hold the s_active references of their directory entries for writing. On the other hand, the execution of a .show() or .store() callback from a sysfs attribute is carried out with that attribute's s_active reference held for reading. Consequently, if any device sysfs attribute that may be removed from within acpi_scan_hot_remove() through acpi_bus_trim() has a .store() or .show() callback which acquires device_hotplug_lock, the execution of that callback may deadlock with the removal of the attribute. [Unfortunately, the "online" device attribute of CPUs and memory blocks is one of them.] To avoid such deadlocks, make all of the sysfs attribute callbacks that need to lock device hotplug, for example store_online(), use a special function, lock_device_hotplug_sysfs(), to lock device hotplug and return the result of that function immediately if it is not zero. This will cause the s_active reference of the directory entry in question to be released and the syscall to be restarted if device_hotplug_lock cannot be acquired. [show_online() actually doesn't need to lock device hotplug, but it is useful to serialize it with respect to device_offline() and device_online() for the same device (in case user space attempts to run them concurrently) which can be done with the help of device_lock().] Reported-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Reported-and-tested-by: Gu Zheng <guz.fnst@cn.fujitsu.com> Suggested-by: Tejun Heo <tj@kernel.org> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Acked-by: Toshi Kani <toshi.kani@hp.com>
2013-08-29 03:41:01 +08:00
device_unlock(dev);
Driver core: Add offline/online device operations In some cases, graceful hot-removal of devices is not possible, although in principle the devices in question support hotplug. For example, that may happen for the last CPU in the system or for memory modules holding kernel memory. In those cases it is nice to be able to check if the given device can be gracefully hot-removed before triggering a removal procedure that cannot be aborted or reversed. Unfortunately, however, the kernel currently doesn't provide any support for that. To address that deficiency, introduce support for offline and online operations that can be performed on devices, respectively, before a hot-removal and in case when it is necessary (or convenient) to put a device back online after a successful offline (that has not been followed by removal). The idea is that the offline will fail whenever the given device cannot be gracefully removed from the system and it will not be allowed to use the device after a successful offline (until a subsequent online) in analogy with the existing CPU offline/online mechanism. For now, the offline and online operations are introduced at the bus type level, as that should be sufficient for the most urgent use cases (CPUs and memory modules). In the future, however, the approach may be extended to cover some more complicated device offline/online scenarios involving device drivers etc. The lock_device_hotplug() and unlock_device_hotplug() functions are introduced because subsequent patches need to put larger pieces of code under device_hotplug_lock to prevent race conditions between device offline and removal from happening. Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Reviewed-by: Toshi Kani <toshi.kani@hp.com>
2013-05-03 04:15:29 +08:00
return sprintf(buf, "%u\n", val);
}
static ssize_t online_store(struct device *dev, struct device_attribute *attr,
Driver core: Add offline/online device operations In some cases, graceful hot-removal of devices is not possible, although in principle the devices in question support hotplug. For example, that may happen for the last CPU in the system or for memory modules holding kernel memory. In those cases it is nice to be able to check if the given device can be gracefully hot-removed before triggering a removal procedure that cannot be aborted or reversed. Unfortunately, however, the kernel currently doesn't provide any support for that. To address that deficiency, introduce support for offline and online operations that can be performed on devices, respectively, before a hot-removal and in case when it is necessary (or convenient) to put a device back online after a successful offline (that has not been followed by removal). The idea is that the offline will fail whenever the given device cannot be gracefully removed from the system and it will not be allowed to use the device after a successful offline (until a subsequent online) in analogy with the existing CPU offline/online mechanism. For now, the offline and online operations are introduced at the bus type level, as that should be sufficient for the most urgent use cases (CPUs and memory modules). In the future, however, the approach may be extended to cover some more complicated device offline/online scenarios involving device drivers etc. The lock_device_hotplug() and unlock_device_hotplug() functions are introduced because subsequent patches need to put larger pieces of code under device_hotplug_lock to prevent race conditions between device offline and removal from happening. Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Reviewed-by: Toshi Kani <toshi.kani@hp.com>
2013-05-03 04:15:29 +08:00
const char *buf, size_t count)
{
bool val;
int ret;
ret = strtobool(buf, &val);
if (ret < 0)
return ret;
driver core / ACPI: Avoid device hot remove locking issues device_hotplug_lock is held around the acpi_bus_trim() call in acpi_scan_hot_remove() which generally removes devices (it removes ACPI device objects at least, but it may also remove "physical" device objects through .detach() callbacks of ACPI scan handlers). Thus, potentially, device sysfs attributes are removed under that lock and to remove those attributes it is necessary to hold the s_active references of their directory entries for writing. On the other hand, the execution of a .show() or .store() callback from a sysfs attribute is carried out with that attribute's s_active reference held for reading. Consequently, if any device sysfs attribute that may be removed from within acpi_scan_hot_remove() through acpi_bus_trim() has a .store() or .show() callback which acquires device_hotplug_lock, the execution of that callback may deadlock with the removal of the attribute. [Unfortunately, the "online" device attribute of CPUs and memory blocks is one of them.] To avoid such deadlocks, make all of the sysfs attribute callbacks that need to lock device hotplug, for example store_online(), use a special function, lock_device_hotplug_sysfs(), to lock device hotplug and return the result of that function immediately if it is not zero. This will cause the s_active reference of the directory entry in question to be released and the syscall to be restarted if device_hotplug_lock cannot be acquired. [show_online() actually doesn't need to lock device hotplug, but it is useful to serialize it with respect to device_offline() and device_online() for the same device (in case user space attempts to run them concurrently) which can be done with the help of device_lock().] Reported-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Reported-and-tested-by: Gu Zheng <guz.fnst@cn.fujitsu.com> Suggested-by: Tejun Heo <tj@kernel.org> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Acked-by: Toshi Kani <toshi.kani@hp.com>
2013-08-29 03:41:01 +08:00
ret = lock_device_hotplug_sysfs();
if (ret)
return ret;
Driver core: Add offline/online device operations In some cases, graceful hot-removal of devices is not possible, although in principle the devices in question support hotplug. For example, that may happen for the last CPU in the system or for memory modules holding kernel memory. In those cases it is nice to be able to check if the given device can be gracefully hot-removed before triggering a removal procedure that cannot be aborted or reversed. Unfortunately, however, the kernel currently doesn't provide any support for that. To address that deficiency, introduce support for offline and online operations that can be performed on devices, respectively, before a hot-removal and in case when it is necessary (or convenient) to put a device back online after a successful offline (that has not been followed by removal). The idea is that the offline will fail whenever the given device cannot be gracefully removed from the system and it will not be allowed to use the device after a successful offline (until a subsequent online) in analogy with the existing CPU offline/online mechanism. For now, the offline and online operations are introduced at the bus type level, as that should be sufficient for the most urgent use cases (CPUs and memory modules). In the future, however, the approach may be extended to cover some more complicated device offline/online scenarios involving device drivers etc. The lock_device_hotplug() and unlock_device_hotplug() functions are introduced because subsequent patches need to put larger pieces of code under device_hotplug_lock to prevent race conditions between device offline and removal from happening. Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Reviewed-by: Toshi Kani <toshi.kani@hp.com>
2013-05-03 04:15:29 +08:00
ret = val ? device_online(dev) : device_offline(dev);
unlock_device_hotplug();
return ret < 0 ? ret : count;
}
static DEVICE_ATTR_RW(online);
Driver core: Add offline/online device operations In some cases, graceful hot-removal of devices is not possible, although in principle the devices in question support hotplug. For example, that may happen for the last CPU in the system or for memory modules holding kernel memory. In those cases it is nice to be able to check if the given device can be gracefully hot-removed before triggering a removal procedure that cannot be aborted or reversed. Unfortunately, however, the kernel currently doesn't provide any support for that. To address that deficiency, introduce support for offline and online operations that can be performed on devices, respectively, before a hot-removal and in case when it is necessary (or convenient) to put a device back online after a successful offline (that has not been followed by removal). The idea is that the offline will fail whenever the given device cannot be gracefully removed from the system and it will not be allowed to use the device after a successful offline (until a subsequent online) in analogy with the existing CPU offline/online mechanism. For now, the offline and online operations are introduced at the bus type level, as that should be sufficient for the most urgent use cases (CPUs and memory modules). In the future, however, the approach may be extended to cover some more complicated device offline/online scenarios involving device drivers etc. The lock_device_hotplug() and unlock_device_hotplug() functions are introduced because subsequent patches need to put larger pieces of code under device_hotplug_lock to prevent race conditions between device offline and removal from happening. Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Reviewed-by: Toshi Kani <toshi.kani@hp.com>
2013-05-03 04:15:29 +08:00
int device_add_groups(struct device *dev, const struct attribute_group **groups)
{
return sysfs_create_groups(&dev->kobj, groups);
}
void device_remove_groups(struct device *dev,
const struct attribute_group **groups)
{
sysfs_remove_groups(&dev->kobj, groups);
}
static int device_add_attrs(struct device *dev)
{
struct class *class = dev->class;
const struct device_type *type = dev->type;
int error;
if (class) {
error = device_add_groups(dev, class->dev_groups);
if (error)
return error;
}
if (type) {
error = device_add_groups(dev, type->groups);
if (error)
goto err_remove_class_groups;
}
error = device_add_groups(dev, dev->groups);
if (error)
goto err_remove_type_groups;
Driver core: Add offline/online device operations In some cases, graceful hot-removal of devices is not possible, although in principle the devices in question support hotplug. For example, that may happen for the last CPU in the system or for memory modules holding kernel memory. In those cases it is nice to be able to check if the given device can be gracefully hot-removed before triggering a removal procedure that cannot be aborted or reversed. Unfortunately, however, the kernel currently doesn't provide any support for that. To address that deficiency, introduce support for offline and online operations that can be performed on devices, respectively, before a hot-removal and in case when it is necessary (or convenient) to put a device back online after a successful offline (that has not been followed by removal). The idea is that the offline will fail whenever the given device cannot be gracefully removed from the system and it will not be allowed to use the device after a successful offline (until a subsequent online) in analogy with the existing CPU offline/online mechanism. For now, the offline and online operations are introduced at the bus type level, as that should be sufficient for the most urgent use cases (CPUs and memory modules). In the future, however, the approach may be extended to cover some more complicated device offline/online scenarios involving device drivers etc. The lock_device_hotplug() and unlock_device_hotplug() functions are introduced because subsequent patches need to put larger pieces of code under device_hotplug_lock to prevent race conditions between device offline and removal from happening. Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Reviewed-by: Toshi Kani <toshi.kani@hp.com>
2013-05-03 04:15:29 +08:00
if (device_supports_offline(dev) && !dev->offline_disabled) {
error = device_create_file(dev, &dev_attr_online);
Driver core: Add offline/online device operations In some cases, graceful hot-removal of devices is not possible, although in principle the devices in question support hotplug. For example, that may happen for the last CPU in the system or for memory modules holding kernel memory. In those cases it is nice to be able to check if the given device can be gracefully hot-removed before triggering a removal procedure that cannot be aborted or reversed. Unfortunately, however, the kernel currently doesn't provide any support for that. To address that deficiency, introduce support for offline and online operations that can be performed on devices, respectively, before a hot-removal and in case when it is necessary (or convenient) to put a device back online after a successful offline (that has not been followed by removal). The idea is that the offline will fail whenever the given device cannot be gracefully removed from the system and it will not be allowed to use the device after a successful offline (until a subsequent online) in analogy with the existing CPU offline/online mechanism. For now, the offline and online operations are introduced at the bus type level, as that should be sufficient for the most urgent use cases (CPUs and memory modules). In the future, however, the approach may be extended to cover some more complicated device offline/online scenarios involving device drivers etc. The lock_device_hotplug() and unlock_device_hotplug() functions are introduced because subsequent patches need to put larger pieces of code under device_hotplug_lock to prevent race conditions between device offline and removal from happening. Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Reviewed-by: Toshi Kani <toshi.kani@hp.com>
2013-05-03 04:15:29 +08:00
if (error)
goto err_remove_dev_groups;
Driver core: Add offline/online device operations In some cases, graceful hot-removal of devices is not possible, although in principle the devices in question support hotplug. For example, that may happen for the last CPU in the system or for memory modules holding kernel memory. In those cases it is nice to be able to check if the given device can be gracefully hot-removed before triggering a removal procedure that cannot be aborted or reversed. Unfortunately, however, the kernel currently doesn't provide any support for that. To address that deficiency, introduce support for offline and online operations that can be performed on devices, respectively, before a hot-removal and in case when it is necessary (or convenient) to put a device back online after a successful offline (that has not been followed by removal). The idea is that the offline will fail whenever the given device cannot be gracefully removed from the system and it will not be allowed to use the device after a successful offline (until a subsequent online) in analogy with the existing CPU offline/online mechanism. For now, the offline and online operations are introduced at the bus type level, as that should be sufficient for the most urgent use cases (CPUs and memory modules). In the future, however, the approach may be extended to cover some more complicated device offline/online scenarios involving device drivers etc. The lock_device_hotplug() and unlock_device_hotplug() functions are introduced because subsequent patches need to put larger pieces of code under device_hotplug_lock to prevent race conditions between device offline and removal from happening. Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Reviewed-by: Toshi Kani <toshi.kani@hp.com>
2013-05-03 04:15:29 +08:00
}
return 0;
err_remove_dev_groups:
device_remove_groups(dev, dev->groups);
err_remove_type_groups:
if (type)
device_remove_groups(dev, type->groups);
err_remove_class_groups:
if (class)
device_remove_groups(dev, class->dev_groups);
return error;
}
static void device_remove_attrs(struct device *dev)
{
struct class *class = dev->class;
const struct device_type *type = dev->type;
device_remove_file(dev, &dev_attr_online);
device_remove_groups(dev, dev->groups);
if (type)
device_remove_groups(dev, type->groups);
if (class)
device_remove_groups(dev, class->dev_groups);
}
static ssize_t dev_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
return print_dev_t(buf, dev->devt);
}
static DEVICE_ATTR_RO(dev);
/* /sys/devices/ */
struct kset *devices_kset;
/**
* device_create_file - create sysfs attribute file for device.
* @dev: device.
* @attr: device attribute descriptor.
*/
int device_create_file(struct device *dev,
const struct device_attribute *attr)
{
int error = 0;
if (dev) {
WARN(((attr->attr.mode & S_IWUGO) && !attr->store),
"Attribute %s: write permission without 'store'\n",
attr->attr.name);
WARN(((attr->attr.mode & S_IRUGO) && !attr->show),
"Attribute %s: read permission without 'show'\n",
attr->attr.name);
error = sysfs_create_file(&dev->kobj, &attr->attr);
}
return error;
}
EXPORT_SYMBOL_GPL(device_create_file);
/**
* device_remove_file - remove sysfs attribute file.
* @dev: device.
* @attr: device attribute descriptor.
*/
void device_remove_file(struct device *dev,
const struct device_attribute *attr)
{
if (dev)
sysfs_remove_file(&dev->kobj, &attr->attr);
}
EXPORT_SYMBOL_GPL(device_remove_file);
kernfs, sysfs, driver-core: implement kernfs_remove_self() and its wrappers Sometimes it's necessary to implement a node which wants to delete nodes including itself. This isn't straightforward because of kernfs active reference. While a file operation is in progress, an active reference is held and kernfs_remove() waits for all such references to drain before completing. For a self-deleting node, this is a deadlock as kernfs_remove() ends up waiting for an active reference that itself is sitting on top of. This currently is worked around in the sysfs layer using sysfs_schedule_callback() which makes such removals asynchronous. While it works, it's rather cumbersome and inherently breaks synchronicity of the operation - the file operation which triggered the operation may complete before the removal is finished (or even started) and the removal may fail asynchronously. If a removal operation is immmediately followed by another operation which expects the specific name to be available (e.g. removal followed by rename onto the same name), there's no way to make the latter operation reliable. The thing is there's no inherent reason for this to be asynchrnous. All that's necessary to do this synchronous is a dedicated operation which drops its own active ref and deactivates self. This patch implements kernfs_remove_self() and its wrappers in sysfs and driver core. kernfs_remove_self() is to be called from one of the file operations, drops the active ref the task is holding, removes the self node, and restores active ref to the dead node so that the ref is balanced afterwards. __kernfs_remove() is updated so that it takes an early exit if the target node is already fully removed so that the active ref restored by kernfs_remove_self() after removal doesn't confuse the deactivation path. This makes implementing self-deleting nodes very easy. The normal removal path doesn't even need to be changed to use kernfs_remove_self() for the self-deleting node. The method can invoke kernfs_remove_self() on itself before proceeding the normal removal path. kernfs_remove() invoked on the node by the normal deletion path will simply be ignored. This will replace sysfs_schedule_callback(). A subtle feature of sysfs_schedule_callback() is that it collapses multiple invocations - even if multiple removals are triggered, the removal callback is run only once. An equivalent effect can be achieved by testing the return value of kernfs_remove_self() - only the one which gets %true return value should proceed with actual deletion. All other instances of kernfs_remove_self() will wait till the enclosing kernfs operation which invoked the winning instance of kernfs_remove_self() finishes and then return %false. This trivially makes all users of kernfs_remove_self() automatically show correct synchronous behavior even when there are multiple concurrent operations - all "echo 1 > delete" instances will finish only after the whole operation is completed by one of the instances. Note that manipulation of active ref is implemented in separate public functions - kernfs_[un]break_active_protection(). kernfs_remove_self() is the only user at the moment but this will be used to cater to more complex cases. v2: For !CONFIG_SYSFS, dummy version kernfs_remove_self() was missing and sysfs_remove_file_self() had incorrect return type. Fix it. Reported by kbuild test bot. v3: kernfs_[un]break_active_protection() separated out from kernfs_remove_self() and exposed as public API. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Alan Stern <stern@rowland.harvard.edu> Cc: kbuild test robot <fengguang.wu@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-02-04 03:03:01 +08:00
/**
* device_remove_file_self - remove sysfs attribute file from its own method.
* @dev: device.
* @attr: device attribute descriptor.
*
* See kernfs_remove_self() for details.
*/
bool device_remove_file_self(struct device *dev,
const struct device_attribute *attr)
{
if (dev)
return sysfs_remove_file_self(&dev->kobj, &attr->attr);
else
return false;
}
EXPORT_SYMBOL_GPL(device_remove_file_self);
/**
* device_create_bin_file - create sysfs binary attribute file for device.
* @dev: device.
* @attr: device binary attribute descriptor.
*/
int device_create_bin_file(struct device *dev,
const struct bin_attribute *attr)
{
int error = -EINVAL;
if (dev)
error = sysfs_create_bin_file(&dev->kobj, attr);
return error;
}
EXPORT_SYMBOL_GPL(device_create_bin_file);
/**
* device_remove_bin_file - remove sysfs binary attribute file
* @dev: device.
* @attr: device binary attribute descriptor.
*/
void device_remove_bin_file(struct device *dev,
const struct bin_attribute *attr)
{
if (dev)
sysfs_remove_bin_file(&dev->kobj, attr);
}
EXPORT_SYMBOL_GPL(device_remove_bin_file);
static void klist_children_get(struct klist_node *n)
{
struct device_private *p = to_device_private_parent(n);
struct device *dev = p->device;
get_device(dev);
}
static void klist_children_put(struct klist_node *n)
{
struct device_private *p = to_device_private_parent(n);
struct device *dev = p->device;
put_device(dev);
}
/**
* device_initialize - init device structure.
* @dev: device.
*
* This prepares the device for use by other layers by initializing
* its fields.
* It is the first half of device_register(), if called by
* that function, though it can also be called separately, so one
* may use @dev's fields. In particular, get_device()/put_device()
* may be used for reference counting of @dev after calling this
* function.
*
* All fields in @dev must be initialized by the caller to 0, except
* for those explicitly set to some other value. The simplest
* approach is to use kzalloc() to allocate the structure containing
* @dev.
*
* NOTE: Use put_device() to give up your reference instead of freeing
* @dev directly once you have called this function.
*/
void device_initialize(struct device *dev)
{
dev->kobj.kset = devices_kset;
kobject_init(&dev->kobj, &device_ktype);
INIT_LIST_HEAD(&dev->dma_pools);
mutex_init(&dev->mutex);
lockdep_set_novalidate_class(&dev->mutex);
spin_lock_init(&dev->devres_lock);
INIT_LIST_HEAD(&dev->devres_head);
device_pm_init(dev);
set_dev_node(dev, -1);
}
EXPORT_SYMBOL_GPL(device_initialize);
struct kobject *virtual_device_parent(struct device *dev)
{
static struct kobject *virtual_dir = NULL;
if (!virtual_dir)
virtual_dir = kobject_create_and_add("virtual",
&devices_kset->kobj);
return virtual_dir;
}
struct class_dir {
struct kobject kobj;
struct class *class;
};
#define to_class_dir(obj) container_of(obj, struct class_dir, kobj)
static void class_dir_release(struct kobject *kobj)
{
struct class_dir *dir = to_class_dir(kobj);
kfree(dir);
}
static const
struct kobj_ns_type_operations *class_dir_child_ns_type(struct kobject *kobj)
{
struct class_dir *dir = to_class_dir(kobj);
return dir->class->ns_type;
}
static struct kobj_type class_dir_ktype = {
.release = class_dir_release,
.sysfs_ops = &kobj_sysfs_ops,
.child_ns_type = class_dir_child_ns_type
};
static struct kobject *
class_dir_create_and_add(struct class *class, struct kobject *parent_kobj)
{
struct class_dir *dir;
int retval;
dir = kzalloc(sizeof(*dir), GFP_KERNEL);
if (!dir)
return NULL;
dir->class = class;
kobject_init(&dir->kobj, &class_dir_ktype);
dir->kobj.kset = &class->p->glue_dirs;
retval = kobject_add(&dir->kobj, parent_kobj, "%s", class->name);
if (retval < 0) {
kobject_put(&dir->kobj);
return NULL;
}
return &dir->kobj;
}
sysfs: driver core: Fix glue dir race condition by gdp_mutex There is a race condition when removing glue directory. It can be reproduced in following test: path 1: Add first child device device_add() get_device_parent() /*find parent from glue_dirs.list*/ list_for_each_entry(k, &dev->class->p->glue_dirs.list, entry) if (k->parent == parent_kobj) { kobj = kobject_get(k); break; } .... class_dir_create_and_add() path2: Remove last child device under glue dir device_del() cleanup_device_parent() cleanup_glue_dir() kobject_put(glue_dir); If path2 has been called cleanup_glue_dir(), but not call kobject_put(glue_dir), the glue dir is still in parent's kset list. Meanwhile, path1 find the glue dir from the glue_dirs.list. Path2 may release glue dir before path1 call kobject_get(). So kernel will report the warning and bug_on. This is a "classic" problem we have of a kref in a list that can be found while the last instance could be removed at the same time. This patch reuse gdp_mutex to fix this race condition. The following calltrace is captured in kernel 3.4, but the latest kernel still has this bug. ----------------------------------------------------- <4>[ 3965.441471] WARNING: at ...include/linux/kref.h:41 kobject_get+0x33/0x40() <4>[ 3965.441474] Hardware name: Romley <4>[ 3965.441475] Modules linked in: isd_iop(O) isd_xda(O)... ... <4>[ 3965.441605] Call Trace: <4>[ 3965.441611] [<ffffffff8103717a>] warn_slowpath_common+0x7a/0xb0 <4>[ 3965.441615] [<ffffffff810371c5>] warn_slowpath_null+0x15/0x20 <4>[ 3965.441618] [<ffffffff81215963>] kobject_get+0x33/0x40 <4>[ 3965.441624] [<ffffffff812d1e45>] get_device_parent.isra.11+0x135/0x1f0 <4>[ 3965.441627] [<ffffffff812d22d4>] device_add+0xd4/0x6d0 <4>[ 3965.441631] [<ffffffff812d0dbc>] ? dev_set_name+0x3c/0x40 .... <2>[ 3965.441912] kernel BUG at ..../fs/sysfs/group.c:65! <4>[ 3965.441915] invalid opcode: 0000 [#1] SMP ... <4>[ 3965.686743] [<ffffffff811a677e>] sysfs_create_group+0xe/0x10 <4>[ 3965.686748] [<ffffffff810cfb04>] blk_trace_init_sysfs+0x14/0x20 <4>[ 3965.686753] [<ffffffff811fcabb>] blk_register_queue+0x3b/0x120 <4>[ 3965.686756] [<ffffffff812030bc>] add_disk+0x1cc/0x490 .... ------------------------------------------------------- Signed-off-by: Yijing Wang <wangyijing@huawei.com> Signed-off-by: Weng Meiling <wengmeiling.weng@huawei.com> Cc: <stable@vger.kernel.org> #3.4+ Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-11-07 12:05:49 +08:00
static DEFINE_MUTEX(gdp_mutex);
static struct kobject *get_device_parent(struct device *dev,
struct device *parent)
{
if (dev->class) {
struct kobject *kobj = NULL;
struct kobject *parent_kobj;
struct kobject *k;
#ifdef CONFIG_BLOCK
/* block disks show up in /sys/block */
if (sysfs_deprecated && dev->class == &block_class) {
if (parent && parent->class == &block_class)
return &parent->kobj;
return &block_class.p->subsys.kobj;
}
#endif
/*
* If we have no parent, we live in "virtual".
* Class-devices with a non class-device as parent, live
* in a "glue" directory to prevent namespace collisions.
*/
if (parent == NULL)
parent_kobj = virtual_device_parent(dev);
Driver-core: Always create class directories for classses that support namespaces. This fixes the regression in 2.6.35-rcX where bluetooth network devices would fail to be deleted from sysfs, causing their destruction and recreation to fail. In addition this fixes the mac80211_hwsim driver where it would leave around sysfs files when the driver was removed. This problem is discussed at https://bugzilla.kernel.org/show_bug.cgi?id=16257 The reason for the regression is that the network namespace support added to sysfs expects and requires that network devices be put in directories that can contain only network devices. Today get_device_parent almost provides that guarantee for all class devices, except for a specific exception when the parent of a class devices is a class device. It would be nice to simply remove that arguably incorrect special case, but apparently the input devices depend on it being there. So I have only removed it for class devices with network namespace support. Which today are the network devices. It has been suggested that a better fix would be to change the parent device from a class device to a bus device, which in the case of the bluetooth driver would change /sys/class/bluetooth to /sys/bus/bluetoth, I can not see how we would avoid significant userspace breakage if we were to make that change. Adding an extra directory in the path to the device will also be userspace visible but it is much less likely to break things. Everything is still accessible from /sys/class (for example), and it fixes two bugs. Adding an extra directory fixes a 3 year old regression introduced with the new sysfs layout that makes it impossible to rename bnep0 network devices to names that conflict with hci device attributes like hci_revsion. Adding an additional directory removes the new failure modes introduced by the network namespace code. If it weren't for the regession in the renaming of network devices I would figure out how to just make the sysfs code deal with this configuration of devices. In summary this patch fixes regressions by changing: "/sys/class/bluetooth/hci0/bnep0" to "/sys/class/bluetooth/hci0/net/bnep0". Reported-by: Johannes Berg <johannes@sipsolutions.net> Reported-by: Janusz Krzysztofik <jkrzyszt@tis.icnet.pl> Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-07-25 13:43:35 +08:00
else if (parent->class && !dev->class->ns_type)
return &parent->kobj;
else
parent_kobj = &parent->kobj;
driver-core: fix race condition in get_device_parent() sysfs is creating several devices in cuse class concurrently and with CONFIG_SYSFS_DEPRECATED turned off, it triggers the following oops. BUG: unable to handle kernel NULL pointer dereference at 0000000000000038 IP: [<ffffffff81158b0a>] sysfs_addrm_start+0x4a/0xf0 PGD 75bb067 PUD 75be067 PMD 0 Oops: 0000 [#1] PREEMPT SMP last sysfs file: /sys/devices/system/cpu/cpu7/topology/core_siblings CPU 1 Modules linked in: cuse fuse Pid: 4737, comm: osspd Not tainted 2.6.31-work #77 RIP: 0010:[<ffffffff81158b0a>] [<ffffffff81158b0a>] sysfs_addrm_start+0x4a/0xf0 RSP: 0018:ffff88000042f8f8 EFLAGS: 00010296 RAX: ffff88000042ffd8 RBX: 0000000000000000 RCX: 0000000000000000 RDX: 0000000000000000 RSI: ffff880007eef660 RDI: 0000000000000001 RBP: ffff88000042f918 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000001 R11: ffffffff81158b0a R12: ffff88000042f928 R13: 00000000fffffff4 R14: 0000000000000000 R15: ffff88000042f9a0 FS: 00007fe93905a950(0000) GS:ffff880008600000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b CR2: 0000000000000038 CR3: 00000000077c9000 CR4: 00000000000006e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Process osspd (pid: 4737, threadinfo ffff88000042e000, task ffff880007eef040) Stack: ffff880005da10e8 0000000011cc8d6e ffff88000042f928 ffff880003d28a28 <0> ffff88000042f988 ffffffff811592d7 0000000000000000 0000000000000000 <0> 0000000000000000 0000000000000000 ffff88000042f958 0000000011cc8d6e Call Trace: [<ffffffff811592d7>] create_dir+0x67/0xe0 [<ffffffff811593a8>] sysfs_create_dir+0x58/0xb0 [<ffffffff8128ca7c>] ? kobject_add_internal+0xcc/0x220 [<ffffffff812942e1>] ? vsnprintf+0x3c1/0xb90 [<ffffffff8128cab7>] kobject_add_internal+0x107/0x220 [<ffffffff8128cd37>] kobject_add_varg+0x47/0x80 [<ffffffff8128ce53>] kobject_add+0x53/0x90 [<ffffffff81357d84>] device_add+0xd4/0x690 [<ffffffff81356c2b>] ? dev_set_name+0x4b/0x70 [<ffffffffa001a884>] cuse_process_init_reply+0x2b4/0x420 [cuse] ... The problem is that kobject_add_internal() first adds a kobject to the kset and then try to create sysfs directory for it. If the creation fails, it remove the kobject from the kset. get_device_parent() accesses class_dirs kset while only holding class_dirs.list_lock to see whether the cuse class dir exists. But when it exists, it may not have finished initialization yet or may fail and get removed soon. In the above case, the former happened so the second one ends up trying to create subdirectory under NULL sysfs_dirent. Fix it by grabbing a mutex in get_device_parent(). Signed-off-by: Tejun Heo <tj@kernel.org> Reported-by: Colin Guthrie <cguthrie@mandriva.org> Cc: stable <stable@kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2010-02-05 16:57:02 +08:00
mutex_lock(&gdp_mutex);
/* find our class-directory at the parent and reference it */
spin_lock(&dev->class->p->glue_dirs.list_lock);
list_for_each_entry(k, &dev->class->p->glue_dirs.list, entry)
if (k->parent == parent_kobj) {
kobj = kobject_get(k);
break;
}
spin_unlock(&dev->class->p->glue_dirs.list_lock);
driver-core: fix race condition in get_device_parent() sysfs is creating several devices in cuse class concurrently and with CONFIG_SYSFS_DEPRECATED turned off, it triggers the following oops. BUG: unable to handle kernel NULL pointer dereference at 0000000000000038 IP: [<ffffffff81158b0a>] sysfs_addrm_start+0x4a/0xf0 PGD 75bb067 PUD 75be067 PMD 0 Oops: 0000 [#1] PREEMPT SMP last sysfs file: /sys/devices/system/cpu/cpu7/topology/core_siblings CPU 1 Modules linked in: cuse fuse Pid: 4737, comm: osspd Not tainted 2.6.31-work #77 RIP: 0010:[<ffffffff81158b0a>] [<ffffffff81158b0a>] sysfs_addrm_start+0x4a/0xf0 RSP: 0018:ffff88000042f8f8 EFLAGS: 00010296 RAX: ffff88000042ffd8 RBX: 0000000000000000 RCX: 0000000000000000 RDX: 0000000000000000 RSI: ffff880007eef660 RDI: 0000000000000001 RBP: ffff88000042f918 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000001 R11: ffffffff81158b0a R12: ffff88000042f928 R13: 00000000fffffff4 R14: 0000000000000000 R15: ffff88000042f9a0 FS: 00007fe93905a950(0000) GS:ffff880008600000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b CR2: 0000000000000038 CR3: 00000000077c9000 CR4: 00000000000006e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Process osspd (pid: 4737, threadinfo ffff88000042e000, task ffff880007eef040) Stack: ffff880005da10e8 0000000011cc8d6e ffff88000042f928 ffff880003d28a28 <0> ffff88000042f988 ffffffff811592d7 0000000000000000 0000000000000000 <0> 0000000000000000 0000000000000000 ffff88000042f958 0000000011cc8d6e Call Trace: [<ffffffff811592d7>] create_dir+0x67/0xe0 [<ffffffff811593a8>] sysfs_create_dir+0x58/0xb0 [<ffffffff8128ca7c>] ? kobject_add_internal+0xcc/0x220 [<ffffffff812942e1>] ? vsnprintf+0x3c1/0xb90 [<ffffffff8128cab7>] kobject_add_internal+0x107/0x220 [<ffffffff8128cd37>] kobject_add_varg+0x47/0x80 [<ffffffff8128ce53>] kobject_add+0x53/0x90 [<ffffffff81357d84>] device_add+0xd4/0x690 [<ffffffff81356c2b>] ? dev_set_name+0x4b/0x70 [<ffffffffa001a884>] cuse_process_init_reply+0x2b4/0x420 [cuse] ... The problem is that kobject_add_internal() first adds a kobject to the kset and then try to create sysfs directory for it. If the creation fails, it remove the kobject from the kset. get_device_parent() accesses class_dirs kset while only holding class_dirs.list_lock to see whether the cuse class dir exists. But when it exists, it may not have finished initialization yet or may fail and get removed soon. In the above case, the former happened so the second one ends up trying to create subdirectory under NULL sysfs_dirent. Fix it by grabbing a mutex in get_device_parent(). Signed-off-by: Tejun Heo <tj@kernel.org> Reported-by: Colin Guthrie <cguthrie@mandriva.org> Cc: stable <stable@kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2010-02-05 16:57:02 +08:00
if (kobj) {
mutex_unlock(&gdp_mutex);
return kobj;
driver-core: fix race condition in get_device_parent() sysfs is creating several devices in cuse class concurrently and with CONFIG_SYSFS_DEPRECATED turned off, it triggers the following oops. BUG: unable to handle kernel NULL pointer dereference at 0000000000000038 IP: [<ffffffff81158b0a>] sysfs_addrm_start+0x4a/0xf0 PGD 75bb067 PUD 75be067 PMD 0 Oops: 0000 [#1] PREEMPT SMP last sysfs file: /sys/devices/system/cpu/cpu7/topology/core_siblings CPU 1 Modules linked in: cuse fuse Pid: 4737, comm: osspd Not tainted 2.6.31-work #77 RIP: 0010:[<ffffffff81158b0a>] [<ffffffff81158b0a>] sysfs_addrm_start+0x4a/0xf0 RSP: 0018:ffff88000042f8f8 EFLAGS: 00010296 RAX: ffff88000042ffd8 RBX: 0000000000000000 RCX: 0000000000000000 RDX: 0000000000000000 RSI: ffff880007eef660 RDI: 0000000000000001 RBP: ffff88000042f918 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000001 R11: ffffffff81158b0a R12: ffff88000042f928 R13: 00000000fffffff4 R14: 0000000000000000 R15: ffff88000042f9a0 FS: 00007fe93905a950(0000) GS:ffff880008600000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b CR2: 0000000000000038 CR3: 00000000077c9000 CR4: 00000000000006e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Process osspd (pid: 4737, threadinfo ffff88000042e000, task ffff880007eef040) Stack: ffff880005da10e8 0000000011cc8d6e ffff88000042f928 ffff880003d28a28 <0> ffff88000042f988 ffffffff811592d7 0000000000000000 0000000000000000 <0> 0000000000000000 0000000000000000 ffff88000042f958 0000000011cc8d6e Call Trace: [<ffffffff811592d7>] create_dir+0x67/0xe0 [<ffffffff811593a8>] sysfs_create_dir+0x58/0xb0 [<ffffffff8128ca7c>] ? kobject_add_internal+0xcc/0x220 [<ffffffff812942e1>] ? vsnprintf+0x3c1/0xb90 [<ffffffff8128cab7>] kobject_add_internal+0x107/0x220 [<ffffffff8128cd37>] kobject_add_varg+0x47/0x80 [<ffffffff8128ce53>] kobject_add+0x53/0x90 [<ffffffff81357d84>] device_add+0xd4/0x690 [<ffffffff81356c2b>] ? dev_set_name+0x4b/0x70 [<ffffffffa001a884>] cuse_process_init_reply+0x2b4/0x420 [cuse] ... The problem is that kobject_add_internal() first adds a kobject to the kset and then try to create sysfs directory for it. If the creation fails, it remove the kobject from the kset. get_device_parent() accesses class_dirs kset while only holding class_dirs.list_lock to see whether the cuse class dir exists. But when it exists, it may not have finished initialization yet or may fail and get removed soon. In the above case, the former happened so the second one ends up trying to create subdirectory under NULL sysfs_dirent. Fix it by grabbing a mutex in get_device_parent(). Signed-off-by: Tejun Heo <tj@kernel.org> Reported-by: Colin Guthrie <cguthrie@mandriva.org> Cc: stable <stable@kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2010-02-05 16:57:02 +08:00
}
/* or create a new class-directory at the parent device */
k = class_dir_create_and_add(dev->class, parent_kobj);
/* do not emit an uevent for this simple "glue" directory */
driver-core: fix race condition in get_device_parent() sysfs is creating several devices in cuse class concurrently and with CONFIG_SYSFS_DEPRECATED turned off, it triggers the following oops. BUG: unable to handle kernel NULL pointer dereference at 0000000000000038 IP: [<ffffffff81158b0a>] sysfs_addrm_start+0x4a/0xf0 PGD 75bb067 PUD 75be067 PMD 0 Oops: 0000 [#1] PREEMPT SMP last sysfs file: /sys/devices/system/cpu/cpu7/topology/core_siblings CPU 1 Modules linked in: cuse fuse Pid: 4737, comm: osspd Not tainted 2.6.31-work #77 RIP: 0010:[<ffffffff81158b0a>] [<ffffffff81158b0a>] sysfs_addrm_start+0x4a/0xf0 RSP: 0018:ffff88000042f8f8 EFLAGS: 00010296 RAX: ffff88000042ffd8 RBX: 0000000000000000 RCX: 0000000000000000 RDX: 0000000000000000 RSI: ffff880007eef660 RDI: 0000000000000001 RBP: ffff88000042f918 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000001 R11: ffffffff81158b0a R12: ffff88000042f928 R13: 00000000fffffff4 R14: 0000000000000000 R15: ffff88000042f9a0 FS: 00007fe93905a950(0000) GS:ffff880008600000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b CR2: 0000000000000038 CR3: 00000000077c9000 CR4: 00000000000006e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Process osspd (pid: 4737, threadinfo ffff88000042e000, task ffff880007eef040) Stack: ffff880005da10e8 0000000011cc8d6e ffff88000042f928 ffff880003d28a28 <0> ffff88000042f988 ffffffff811592d7 0000000000000000 0000000000000000 <0> 0000000000000000 0000000000000000 ffff88000042f958 0000000011cc8d6e Call Trace: [<ffffffff811592d7>] create_dir+0x67/0xe0 [<ffffffff811593a8>] sysfs_create_dir+0x58/0xb0 [<ffffffff8128ca7c>] ? kobject_add_internal+0xcc/0x220 [<ffffffff812942e1>] ? vsnprintf+0x3c1/0xb90 [<ffffffff8128cab7>] kobject_add_internal+0x107/0x220 [<ffffffff8128cd37>] kobject_add_varg+0x47/0x80 [<ffffffff8128ce53>] kobject_add+0x53/0x90 [<ffffffff81357d84>] device_add+0xd4/0x690 [<ffffffff81356c2b>] ? dev_set_name+0x4b/0x70 [<ffffffffa001a884>] cuse_process_init_reply+0x2b4/0x420 [cuse] ... The problem is that kobject_add_internal() first adds a kobject to the kset and then try to create sysfs directory for it. If the creation fails, it remove the kobject from the kset. get_device_parent() accesses class_dirs kset while only holding class_dirs.list_lock to see whether the cuse class dir exists. But when it exists, it may not have finished initialization yet or may fail and get removed soon. In the above case, the former happened so the second one ends up trying to create subdirectory under NULL sysfs_dirent. Fix it by grabbing a mutex in get_device_parent(). Signed-off-by: Tejun Heo <tj@kernel.org> Reported-by: Colin Guthrie <cguthrie@mandriva.org> Cc: stable <stable@kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2010-02-05 16:57:02 +08:00
mutex_unlock(&gdp_mutex);
return k;
}
/* subsystems can specify a default root directory for their devices */
if (!parent && dev->bus && dev->bus->dev_root)
return &dev->bus->dev_root->kobj;
if (parent)
return &parent->kobj;
return NULL;
}
static void cleanup_glue_dir(struct device *dev, struct kobject *glue_dir)
{
/* see if we live in a "glue" directory */
if (!glue_dir || !dev->class ||
glue_dir->kset != &dev->class->p->glue_dirs)
return;
sysfs: driver core: Fix glue dir race condition by gdp_mutex There is a race condition when removing glue directory. It can be reproduced in following test: path 1: Add first child device device_add() get_device_parent() /*find parent from glue_dirs.list*/ list_for_each_entry(k, &dev->class->p->glue_dirs.list, entry) if (k->parent == parent_kobj) { kobj = kobject_get(k); break; } .... class_dir_create_and_add() path2: Remove last child device under glue dir device_del() cleanup_device_parent() cleanup_glue_dir() kobject_put(glue_dir); If path2 has been called cleanup_glue_dir(), but not call kobject_put(glue_dir), the glue dir is still in parent's kset list. Meanwhile, path1 find the glue dir from the glue_dirs.list. Path2 may release glue dir before path1 call kobject_get(). So kernel will report the warning and bug_on. This is a "classic" problem we have of a kref in a list that can be found while the last instance could be removed at the same time. This patch reuse gdp_mutex to fix this race condition. The following calltrace is captured in kernel 3.4, but the latest kernel still has this bug. ----------------------------------------------------- <4>[ 3965.441471] WARNING: at ...include/linux/kref.h:41 kobject_get+0x33/0x40() <4>[ 3965.441474] Hardware name: Romley <4>[ 3965.441475] Modules linked in: isd_iop(O) isd_xda(O)... ... <4>[ 3965.441605] Call Trace: <4>[ 3965.441611] [<ffffffff8103717a>] warn_slowpath_common+0x7a/0xb0 <4>[ 3965.441615] [<ffffffff810371c5>] warn_slowpath_null+0x15/0x20 <4>[ 3965.441618] [<ffffffff81215963>] kobject_get+0x33/0x40 <4>[ 3965.441624] [<ffffffff812d1e45>] get_device_parent.isra.11+0x135/0x1f0 <4>[ 3965.441627] [<ffffffff812d22d4>] device_add+0xd4/0x6d0 <4>[ 3965.441631] [<ffffffff812d0dbc>] ? dev_set_name+0x3c/0x40 .... <2>[ 3965.441912] kernel BUG at ..../fs/sysfs/group.c:65! <4>[ 3965.441915] invalid opcode: 0000 [#1] SMP ... <4>[ 3965.686743] [<ffffffff811a677e>] sysfs_create_group+0xe/0x10 <4>[ 3965.686748] [<ffffffff810cfb04>] blk_trace_init_sysfs+0x14/0x20 <4>[ 3965.686753] [<ffffffff811fcabb>] blk_register_queue+0x3b/0x120 <4>[ 3965.686756] [<ffffffff812030bc>] add_disk+0x1cc/0x490 .... ------------------------------------------------------- Signed-off-by: Yijing Wang <wangyijing@huawei.com> Signed-off-by: Weng Meiling <wengmeiling.weng@huawei.com> Cc: <stable@vger.kernel.org> #3.4+ Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-11-07 12:05:49 +08:00
mutex_lock(&gdp_mutex);
kobject_put(glue_dir);
sysfs: driver core: Fix glue dir race condition by gdp_mutex There is a race condition when removing glue directory. It can be reproduced in following test: path 1: Add first child device device_add() get_device_parent() /*find parent from glue_dirs.list*/ list_for_each_entry(k, &dev->class->p->glue_dirs.list, entry) if (k->parent == parent_kobj) { kobj = kobject_get(k); break; } .... class_dir_create_and_add() path2: Remove last child device under glue dir device_del() cleanup_device_parent() cleanup_glue_dir() kobject_put(glue_dir); If path2 has been called cleanup_glue_dir(), but not call kobject_put(glue_dir), the glue dir is still in parent's kset list. Meanwhile, path1 find the glue dir from the glue_dirs.list. Path2 may release glue dir before path1 call kobject_get(). So kernel will report the warning and bug_on. This is a "classic" problem we have of a kref in a list that can be found while the last instance could be removed at the same time. This patch reuse gdp_mutex to fix this race condition. The following calltrace is captured in kernel 3.4, but the latest kernel still has this bug. ----------------------------------------------------- <4>[ 3965.441471] WARNING: at ...include/linux/kref.h:41 kobject_get+0x33/0x40() <4>[ 3965.441474] Hardware name: Romley <4>[ 3965.441475] Modules linked in: isd_iop(O) isd_xda(O)... ... <4>[ 3965.441605] Call Trace: <4>[ 3965.441611] [<ffffffff8103717a>] warn_slowpath_common+0x7a/0xb0 <4>[ 3965.441615] [<ffffffff810371c5>] warn_slowpath_null+0x15/0x20 <4>[ 3965.441618] [<ffffffff81215963>] kobject_get+0x33/0x40 <4>[ 3965.441624] [<ffffffff812d1e45>] get_device_parent.isra.11+0x135/0x1f0 <4>[ 3965.441627] [<ffffffff812d22d4>] device_add+0xd4/0x6d0 <4>[ 3965.441631] [<ffffffff812d0dbc>] ? dev_set_name+0x3c/0x40 .... <2>[ 3965.441912] kernel BUG at ..../fs/sysfs/group.c:65! <4>[ 3965.441915] invalid opcode: 0000 [#1] SMP ... <4>[ 3965.686743] [<ffffffff811a677e>] sysfs_create_group+0xe/0x10 <4>[ 3965.686748] [<ffffffff810cfb04>] blk_trace_init_sysfs+0x14/0x20 <4>[ 3965.686753] [<ffffffff811fcabb>] blk_register_queue+0x3b/0x120 <4>[ 3965.686756] [<ffffffff812030bc>] add_disk+0x1cc/0x490 .... ------------------------------------------------------- Signed-off-by: Yijing Wang <wangyijing@huawei.com> Signed-off-by: Weng Meiling <wengmeiling.weng@huawei.com> Cc: <stable@vger.kernel.org> #3.4+ Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-11-07 12:05:49 +08:00
mutex_unlock(&gdp_mutex);
}
static void cleanup_device_parent(struct device *dev)
{
cleanup_glue_dir(dev, dev->kobj.parent);
}
static int device_add_class_symlinks(struct device *dev)
{
int error;
if (!dev->class)
return 0;
error = sysfs_create_link(&dev->kobj,
&dev->class->p->subsys.kobj,
"subsystem");
if (error)
goto out;
if (dev->parent && device_is_not_partition(dev)) {
error = sysfs_create_link(&dev->kobj, &dev->parent->kobj,
"device");
if (error)
goto out_subsys;
}
#ifdef CONFIG_BLOCK
/* /sys/block has directories and does not need symlinks */
if (sysfs_deprecated && dev->class == &block_class)
return 0;
#endif
/* link in the class directory pointing to the device */
error = sysfs_create_link(&dev->class->p->subsys.kobj,
&dev->kobj, dev_name(dev));
if (error)
goto out_device;
return 0;
out_device:
sysfs_remove_link(&dev->kobj, "device");
out_subsys:
sysfs_remove_link(&dev->kobj, "subsystem");
out:
return error;
}
static void device_remove_class_symlinks(struct device *dev)
{
if (!dev->class)
return;
if (dev->parent && device_is_not_partition(dev))
sysfs_remove_link(&dev->kobj, "device");
sysfs_remove_link(&dev->kobj, "subsystem");
#ifdef CONFIG_BLOCK
if (sysfs_deprecated && dev->class == &block_class)
return;
#endif
sysfs_delete_link(&dev->class->p->subsys.kobj, &dev->kobj, dev_name(dev));
}
/**
* dev_set_name - set a device name
* @dev: device
* @fmt: format string for the device's name
*/
int dev_set_name(struct device *dev, const char *fmt, ...)
{
va_list vargs;
int err;
va_start(vargs, fmt);
err = kobject_set_name_vargs(&dev->kobj, fmt, vargs);
va_end(vargs);
return err;
}
EXPORT_SYMBOL_GPL(dev_set_name);
/**
* device_to_dev_kobj - select a /sys/dev/ directory for the device
* @dev: device
*
* By default we select char/ for new entries. Setting class->dev_obj
* to NULL prevents an entry from being created. class->dev_kobj must
* be set (or cleared) before any devices are registered to the class
* otherwise device_create_sys_dev_entry() and
* device_remove_sys_dev_entry() will disagree about the presence of
* the link.
*/
static struct kobject *device_to_dev_kobj(struct device *dev)
{
struct kobject *kobj;
if (dev->class)
kobj = dev->class->dev_kobj;
else
kobj = sysfs_dev_char_kobj;
return kobj;
}
static int device_create_sys_dev_entry(struct device *dev)
{
struct kobject *kobj = device_to_dev_kobj(dev);
int error = 0;
char devt_str[15];
if (kobj) {
format_dev_t(devt_str, dev->devt);
error = sysfs_create_link(kobj, &dev->kobj, devt_str);
}
return error;
}
static void device_remove_sys_dev_entry(struct device *dev)
{
struct kobject *kobj = device_to_dev_kobj(dev);
char devt_str[15];
if (kobj) {
format_dev_t(devt_str, dev->devt);
sysfs_remove_link(kobj, devt_str);
}
}
int device_private_init(struct device *dev)
{
dev->p = kzalloc(sizeof(*dev->p), GFP_KERNEL);
if (!dev->p)
return -ENOMEM;
dev->p->device = dev;
klist_init(&dev->p->klist_children, klist_children_get,
klist_children_put);
INIT_LIST_HEAD(&dev->p->deferred_probe);
return 0;
}
/**
* device_add - add device to device hierarchy.
* @dev: device.
*
* This is part 2 of device_register(), though may be called
* separately _iff_ device_initialize() has been called separately.
*
* This adds @dev to the kobject hierarchy via kobject_add(), adds it
* to the global and sibling lists for the device, then
* adds it to the other relevant subsystems of the driver model.
*
* Do not call this routine or device_register() more than once for
* any device structure. The driver model core is not designed to work
* with devices that get unregistered and then spring back to life.
* (Among other things, it's very hard to guarantee that all references
* to the previous incarnation of @dev have been dropped.) Allocate
* and register a fresh new struct device instead.
*
* NOTE: _Never_ directly free @dev after calling this function, even
* if it returned an error! Always use put_device() to give up your
* reference instead.
*/
int device_add(struct device *dev)
{
struct device *parent = NULL;
struct kobject *kobj;
struct class_interface *class_intf;
int error = -EINVAL;
dev = get_device(dev);
if (!dev)
goto done;
if (!dev->p) {
error = device_private_init(dev);
if (error)
goto done;
}
/*
* for statically allocated devices, which should all be converted
* some day, we need to initialize the name. We prevent reading back
* the name, and force the use of dev_name()
*/
if (dev->init_name) {
dev_set_name(dev, "%s", dev->init_name);
dev->init_name = NULL;
}
/* subsystems can specify simple device enumeration */
if (!dev_name(dev) && dev->bus && dev->bus->dev_name)
dev_set_name(dev, "%s%u", dev->bus->dev_name, dev->id);
if (!dev_name(dev)) {
error = -EINVAL;
goto name_error;
}
pr_debug("device: '%s': %s\n", dev_name(dev), __func__);
parent = get_device(dev->parent);
kobj = get_device_parent(dev, parent);
if (kobj)
dev->kobj.parent = kobj;
/* use parent numa_node */
if (parent)
set_dev_node(dev, dev_to_node(parent));
/* first, register with generic layer. */
/* we require the name to be set before, and pass NULL */
error = kobject_add(&dev->kobj, dev->kobj.parent, NULL);
if (error)
goto Error;
/* notify platform of device entry */
if (platform_notify)
platform_notify(dev);
error = device_create_file(dev, &dev_attr_uevent);
if (error)
goto attrError;
if (MAJOR(dev->devt)) {
error = device_create_file(dev, &dev_attr_dev);
if (error)
goto ueventattrError;
error = device_create_sys_dev_entry(dev);
if (error)
goto devtattrError;
Driver Core: devtmpfs - kernel-maintained tmpfs-based /dev Devtmpfs lets the kernel create a tmpfs instance called devtmpfs very early at kernel initialization, before any driver-core device is registered. Every device with a major/minor will provide a device node in devtmpfs. Devtmpfs can be changed and altered by userspace at any time, and in any way needed - just like today's udev-mounted tmpfs. Unmodified udev versions will run just fine on top of it, and will recognize an already existing kernel-created device node and use it. The default node permissions are root:root 0600. Proper permissions and user/group ownership, meaningful symlinks, all other policy still needs to be applied by userspace. If a node is created by devtmps, devtmpfs will remove the device node when the device goes away. If the device node was created by userspace, or the devtmpfs created node was replaced by userspace, it will no longer be removed by devtmpfs. If it is requested to auto-mount it, it makes init=/bin/sh work without any further userspace support. /dev will be fully populated and dynamic, and always reflect the current device state of the kernel. With the commonly used dynamic device numbers, it solves the problem where static devices nodes may point to the wrong devices. It is intended to make the initial bootup logic simpler and more robust, by de-coupling the creation of the inital environment, to reliably run userspace processes, from a complex userspace bootstrap logic to provide a working /dev. Signed-off-by: Kay Sievers <kay.sievers@vrfy.org> Signed-off-by: Jan Blunck <jblunck@suse.de> Tested-By: Harald Hoyer <harald@redhat.com> Tested-By: Scott James Remnant <scott@ubuntu.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-04-30 21:23:42 +08:00
devtmpfs_create_node(dev);
}
error = device_add_class_symlinks(dev);
if (error)
goto SymlinkError;
error = device_add_attrs(dev);
if (error)
goto AttrsError;
error = bus_add_device(dev);
if (error)
goto BusError;
error = dpm_sysfs_add(dev);
if (error)
goto DPMError;
device_pm_add(dev);
/* Notify clients of device addition. This call must come
* after dpm_sysfs_add() and before kobject_uevent().
*/
if (dev->bus)
blocking_notifier_call_chain(&dev->bus->p->bus_notifier,
BUS_NOTIFY_ADD_DEVICE, dev);
kobject_uevent(&dev->kobj, KOBJ_ADD);
bus_probe_device(dev);
if (parent)
klist_add_tail(&dev->p->knode_parent,
&parent->p->klist_children);
if (dev->class) {
mutex_lock(&dev->class->p->mutex);
/* tie the class to the device */
klist_add_tail(&dev->knode_class,
&dev->class->p->klist_devices);
/* notify any interfaces that the device is here */
list_for_each_entry(class_intf,
&dev->class->p->interfaces, node)
if (class_intf->add_dev)
class_intf->add_dev(dev, class_intf);
mutex_unlock(&dev->class->p->mutex);
}
done:
put_device(dev);
return error;
DPMError:
bus_remove_device(dev);
BusError:
device_remove_attrs(dev);
AttrsError:
device_remove_class_symlinks(dev);
SymlinkError:
if (MAJOR(dev->devt))
devtmpfs_delete_node(dev);
if (MAJOR(dev->devt))
device_remove_sys_dev_entry(dev);
devtattrError:
if (MAJOR(dev->devt))
device_remove_file(dev, &dev_attr_dev);
ueventattrError:
device_remove_file(dev, &dev_attr_uevent);
attrError:
kobject_uevent(&dev->kobj, KOBJ_REMOVE);
kobject_del(&dev->kobj);
Error:
cleanup_device_parent(dev);
if (parent)
put_device(parent);
name_error:
kfree(dev->p);
dev->p = NULL;
goto done;
}
EXPORT_SYMBOL_GPL(device_add);
/**
* device_register - register a device with the system.
* @dev: pointer to the device structure
*
* This happens in two clean steps - initialize the device
* and add it to the system. The two steps can be called
* separately, but this is the easiest and most common.
* I.e. you should only call the two helpers separately if
* have a clearly defined need to use and refcount the device
* before it is added to the hierarchy.
*
* For more information, see the kerneldoc for device_initialize()
* and device_add().
*
* NOTE: _Never_ directly free @dev after calling this function, even
* if it returned an error! Always use put_device() to give up the
* reference initialized in this function instead.
*/
int device_register(struct device *dev)
{
device_initialize(dev);
return device_add(dev);
}
EXPORT_SYMBOL_GPL(device_register);
/**
* get_device - increment reference count for device.
* @dev: device.
*
* This simply forwards the call to kobject_get(), though
* we do take care to provide for the case that we get a NULL
* pointer passed in.
*/
struct device *get_device(struct device *dev)
{
return dev ? kobj_to_dev(kobject_get(&dev->kobj)) : NULL;
}
EXPORT_SYMBOL_GPL(get_device);
/**
* put_device - decrement reference count.
* @dev: device in question.
*/
void put_device(struct device *dev)
{
/* might_sleep(); */
if (dev)
kobject_put(&dev->kobj);
}
EXPORT_SYMBOL_GPL(put_device);
/**
* device_del - delete device from system.
* @dev: device.
*
* This is the first part of the device unregistration
* sequence. This removes the device from the lists we control
* from here, has it removed from the other driver model
* subsystems it was added to in device_add(), and removes it
* from the kobject hierarchy.
*
* NOTE: this should be called manually _iff_ device_add() was
* also called manually.
*/
void device_del(struct device *dev)
{
struct device *parent = dev->parent;
struct class_interface *class_intf;
/* Notify clients of device removal. This call must come
* before dpm_sysfs_remove().
*/
if (dev->bus)
blocking_notifier_call_chain(&dev->bus->p->bus_notifier,
BUS_NOTIFY_DEL_DEVICE, dev);
dpm_sysfs_remove(dev);
if (parent)
klist_del(&dev->p->knode_parent);
if (MAJOR(dev->devt)) {
Driver Core: devtmpfs - kernel-maintained tmpfs-based /dev Devtmpfs lets the kernel create a tmpfs instance called devtmpfs very early at kernel initialization, before any driver-core device is registered. Every device with a major/minor will provide a device node in devtmpfs. Devtmpfs can be changed and altered by userspace at any time, and in any way needed - just like today's udev-mounted tmpfs. Unmodified udev versions will run just fine on top of it, and will recognize an already existing kernel-created device node and use it. The default node permissions are root:root 0600. Proper permissions and user/group ownership, meaningful symlinks, all other policy still needs to be applied by userspace. If a node is created by devtmps, devtmpfs will remove the device node when the device goes away. If the device node was created by userspace, or the devtmpfs created node was replaced by userspace, it will no longer be removed by devtmpfs. If it is requested to auto-mount it, it makes init=/bin/sh work without any further userspace support. /dev will be fully populated and dynamic, and always reflect the current device state of the kernel. With the commonly used dynamic device numbers, it solves the problem where static devices nodes may point to the wrong devices. It is intended to make the initial bootup logic simpler and more robust, by de-coupling the creation of the inital environment, to reliably run userspace processes, from a complex userspace bootstrap logic to provide a working /dev. Signed-off-by: Kay Sievers <kay.sievers@vrfy.org> Signed-off-by: Jan Blunck <jblunck@suse.de> Tested-By: Harald Hoyer <harald@redhat.com> Tested-By: Scott James Remnant <scott@ubuntu.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-04-30 21:23:42 +08:00
devtmpfs_delete_node(dev);
device_remove_sys_dev_entry(dev);
device_remove_file(dev, &dev_attr_dev);
}
if (dev->class) {
device_remove_class_symlinks(dev);
mutex_lock(&dev->class->p->mutex);
/* notify any interfaces that the device is now gone */
list_for_each_entry(class_intf,
&dev->class->p->interfaces, node)
if (class_intf->remove_dev)
class_intf->remove_dev(dev, class_intf);
/* remove the device from the class list */
klist_del(&dev->knode_class);
mutex_unlock(&dev->class->p->mutex);
}
device_remove_file(dev, &dev_attr_uevent);
device_remove_attrs(dev);
bus_remove_device(dev);
driver core / PM: move the calling to device_pm_remove behind the calling to bus_remove_device We hit an hang issue when removing a mmc device on Medfield Android phone by sysfs interface. device_pm_remove will call pm_runtime_remove which would disable runtime PM of the device. After that pm_runtime_get* or pm_runtime_put* will be ignored. So if we disable the runtime PM before device really be removed, drivers' _remove callback may access HW even pm_runtime_get* fails. That is bad. Consider below call sequence when removing a device: device_del => device_pm_remove => class_intf->remove_dev(dev, class_intf) => pm_runtime_get_sync/put_sync => bus_remove_device => device_release_driver => pm_runtime_get_sync/put_sync remove_dev might call pm_runtime_get_sync/put_sync. Then, generic device_release_driver also calls pm_runtime_get_sync/put_sync. Since device_del => device_pm_remove firstly, later _get_sync wouldn't really wake up the device. I git log -p to find the patch which moves the calling to device_pm_remove ahead. It's below patch: commit 775b64d2b6ca37697de925f70799c710aab5849a Author: Rafael J. Wysocki <rjw@sisk.pl> Date: Sat Jan 12 20:40:46 2008 +0100 PM: Acquire device locks on suspend This patch reorganizes the way suspend and resume notifications are sent to drivers. The major changes are that now the PM core acquires every device semaphore before calling the methods, and calls to device_add() during suspends will fail, while calls to device_del() during suspends will block. It also provides a way to safely remove a suspended device with the help of the PM core, by using the device_pm_schedule_removal() callback introduced specifically for this purpose, and updates two drivers (msr and cpuid) that need to use it. As device_pm_schedule_removal is deleted by another patch, we need also revert other parts of the patch, i.e. move the calling of device_pm_remove after the calling to bus_remove_device. Signed-off-by: LongX Zhang <longx.zhang@intel.com> Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2012-10-25 06:21:28 +08:00
device_pm_remove(dev);
drivercore: Add driver probe deferral mechanism Allow drivers to report at probe time that they cannot get all the resources required by the device, and should be retried at a later time. This should completely solve the problem of getting devices initialized in the right order. Right now this is mostly handled by mucking about with initcall ordering which is a complete hack, and doesn't even remotely handle the case where device drivers are in modules. This approach completely sidesteps the issues by allowing driver registration to occur in any order, and any driver can request to be retried after a few more other drivers get probed. v4: - Integrate Manjunath's addition of a separate workqueue - Change -EAGAIN to -EPROBE_DEFER for drivers to trigger deferral - Update comment blocks to reflect how the code really works v3: - Hold off workqueue scheduling until late_initcall so that the bulk of driver probes are complete before we start retrying deferred devices. - Tested with simple use cases. Still needs more testing though. Using it to get rid of the gpio early_initcall madness, or to replace the ASoC internal probe deferral code would be ideal. v2: - added locking so it should no longer be utterly broken in that regard - remove device from deferred list at device_del time. - Still completely untested with any real use case, but has been boot tested. Signed-off-by: Grant Likely <grant.likely@secretlab.ca> Cc: Mark Brown <broonie@opensource.wolfsonmicro.com> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Dilan Lee <dilee@nvidia.com> Cc: Manjunath GKondaiah <manjunath.gkondaiah@linaro.org> Cc: Alan Stern <stern@rowland.harvard.edu> Cc: Tony Lindgren <tony@atomide.com> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Reviewed-by: Mark Brown <broonie@opensource.wolfsonmicro.com> Acked-by: David Daney <david.daney@cavium.com> Reviewed-by: Arnd Bergmann <arnd@arndb.de> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2012-03-05 23:47:41 +08:00
driver_deferred_probe_del(dev);
/* Notify the platform of the removal, in case they
* need to do anything...
*/
if (platform_notify_remove)
platform_notify_remove(dev);
if (dev->bus)
blocking_notifier_call_chain(&dev->bus->p->bus_notifier,
BUS_NOTIFY_REMOVED_DEVICE, dev);
kobject_uevent(&dev->kobj, KOBJ_REMOVE);
cleanup_device_parent(dev);
kobject_del(&dev->kobj);
put_device(parent);
}
EXPORT_SYMBOL_GPL(device_del);
/**
* device_unregister - unregister device from system.
* @dev: device going away.
*
* We do this in two parts, like we do device_register(). First,
* we remove it from all the subsystems with device_del(), then
* we decrement the reference count via put_device(). If that
* is the final reference count, the device will be cleaned up
* via device_release() above. Otherwise, the structure will
* stick around until the final reference to the device is dropped.
*/
void device_unregister(struct device *dev)
{
pr_debug("device: '%s': %s\n", dev_name(dev), __func__);
device_del(dev);
put_device(dev);
}
EXPORT_SYMBOL_GPL(device_unregister);
static struct device *next_device(struct klist_iter *i)
{
struct klist_node *n = klist_next(i);
struct device *dev = NULL;
struct device_private *p;
if (n) {
p = to_device_private_parent(n);
dev = p->device;
}
return dev;
}
/**
* device_get_devnode - path of device node file
* @dev: device
* @mode: returned file access mode
* @uid: returned file owner
* @gid: returned file group
* @tmp: possibly allocated string
*
* Return the relative path of a possible device node.
* Non-default names may need to allocate a memory to compose
* a name. This memory is returned in tmp and needs to be
* freed by the caller.
*/
const char *device_get_devnode(struct device *dev,
umode_t *mode, kuid_t *uid, kgid_t *gid,
const char **tmp)
{
char *s;
*tmp = NULL;
/* the device type may provide a specific name */
if (dev->type && dev->type->devnode)
*tmp = dev->type->devnode(dev, mode, uid, gid);
if (*tmp)
return *tmp;
/* the class may provide a specific name */
if (dev->class && dev->class->devnode)
*tmp = dev->class->devnode(dev, mode);
if (*tmp)
return *tmp;
/* return name without allocation, tmp == NULL */
if (strchr(dev_name(dev), '!') == NULL)
return dev_name(dev);
/* replace '!' in the name with '/' */
*tmp = kstrdup(dev_name(dev), GFP_KERNEL);
if (!*tmp)
return NULL;
while ((s = strchr(*tmp, '!')))
s[0] = '/';
return *tmp;
}
/**
* device_for_each_child - device child iterator.
* @parent: parent struct device.
* @fn: function to be called for each device.
* @data: data for the callback.
*
* Iterate over @parent's child devices, and call @fn for each,
* passing it @data.
*
* We check the return of @fn each time. If it returns anything
* other than 0, we break out and return that value.
*/
int device_for_each_child(struct device *parent, void *data,
int (*fn)(struct device *dev, void *data))
{
struct klist_iter i;
struct device *child;
int error = 0;
if (!parent->p)
return 0;
klist_iter_init(&parent->p->klist_children, &i);
while ((child = next_device(&i)) && !error)
error = fn(child, data);
klist_iter_exit(&i);
return error;
}
EXPORT_SYMBOL_GPL(device_for_each_child);
/**
* device_find_child - device iterator for locating a particular device.
* @parent: parent struct device
* @match: Callback function to check device
* @data: Data to pass to match function
*
* This is similar to the device_for_each_child() function above, but it
* returns a reference to a device that is 'found' for later use, as
* determined by the @match callback.
*
* The callback should return 0 if the device doesn't match and non-zero
* if it does. If the callback returns non-zero and a reference to the
* current device can be obtained, this function will return to the caller
* and not iterate over any more devices.
*
* NOTE: you will need to drop the reference with put_device() after use.
*/
struct device *device_find_child(struct device *parent, void *data,
int (*match)(struct device *dev, void *data))
{
struct klist_iter i;
struct device *child;
if (!parent)
return NULL;
klist_iter_init(&parent->p->klist_children, &i);
while ((child = next_device(&i)))
if (match(child, data) && get_device(child))
break;
klist_iter_exit(&i);
return child;
}
EXPORT_SYMBOL_GPL(device_find_child);
int __init devices_init(void)
{
devices_kset = kset_create_and_add("devices", &device_uevent_ops, NULL);
if (!devices_kset)
return -ENOMEM;
dev_kobj = kobject_create_and_add("dev", NULL);
if (!dev_kobj)
goto dev_kobj_err;
sysfs_dev_block_kobj = kobject_create_and_add("block", dev_kobj);
if (!sysfs_dev_block_kobj)
goto block_kobj_err;
sysfs_dev_char_kobj = kobject_create_and_add("char", dev_kobj);
if (!sysfs_dev_char_kobj)
goto char_kobj_err;
return 0;
char_kobj_err:
kobject_put(sysfs_dev_block_kobj);
block_kobj_err:
kobject_put(dev_kobj);
dev_kobj_err:
kset_unregister(devices_kset);
return -ENOMEM;
}
Driver core: Add offline/online device operations In some cases, graceful hot-removal of devices is not possible, although in principle the devices in question support hotplug. For example, that may happen for the last CPU in the system or for memory modules holding kernel memory. In those cases it is nice to be able to check if the given device can be gracefully hot-removed before triggering a removal procedure that cannot be aborted or reversed. Unfortunately, however, the kernel currently doesn't provide any support for that. To address that deficiency, introduce support for offline and online operations that can be performed on devices, respectively, before a hot-removal and in case when it is necessary (or convenient) to put a device back online after a successful offline (that has not been followed by removal). The idea is that the offline will fail whenever the given device cannot be gracefully removed from the system and it will not be allowed to use the device after a successful offline (until a subsequent online) in analogy with the existing CPU offline/online mechanism. For now, the offline and online operations are introduced at the bus type level, as that should be sufficient for the most urgent use cases (CPUs and memory modules). In the future, however, the approach may be extended to cover some more complicated device offline/online scenarios involving device drivers etc. The lock_device_hotplug() and unlock_device_hotplug() functions are introduced because subsequent patches need to put larger pieces of code under device_hotplug_lock to prevent race conditions between device offline and removal from happening. Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Reviewed-by: Toshi Kani <toshi.kani@hp.com>
2013-05-03 04:15:29 +08:00
static int device_check_offline(struct device *dev, void *not_used)
{
int ret;
ret = device_for_each_child(dev, NULL, device_check_offline);
if (ret)
return ret;
return device_supports_offline(dev) && !dev->offline ? -EBUSY : 0;
}
/**
* device_offline - Prepare the device for hot-removal.
* @dev: Device to be put offline.
*
* Execute the device bus type's .offline() callback, if present, to prepare
* the device for a subsequent hot-removal. If that succeeds, the device must
* not be used until either it is removed or its bus type's .online() callback
* is executed.
*
* Call under device_hotplug_lock.
*/
int device_offline(struct device *dev)
{
int ret;
if (dev->offline_disabled)
return -EPERM;
ret = device_for_each_child(dev, NULL, device_check_offline);
if (ret)
return ret;
device_lock(dev);
if (device_supports_offline(dev)) {
if (dev->offline) {
ret = 1;
} else {
ret = dev->bus->offline(dev);
if (!ret) {
kobject_uevent(&dev->kobj, KOBJ_OFFLINE);
dev->offline = true;
}
}
}
device_unlock(dev);
return ret;
}
/**
* device_online - Put the device back online after successful device_offline().
* @dev: Device to be put back online.
*
* If device_offline() has been successfully executed for @dev, but the device
* has not been removed subsequently, execute its bus type's .online() callback
* to indicate that the device can be used again.
*
* Call under device_hotplug_lock.
*/
int device_online(struct device *dev)
{
int ret = 0;
device_lock(dev);
if (device_supports_offline(dev)) {
if (dev->offline) {
ret = dev->bus->online(dev);
if (!ret) {
kobject_uevent(&dev->kobj, KOBJ_ONLINE);
dev->offline = false;
}
} else {
ret = 1;
}
}
device_unlock(dev);
return ret;
}
struct root_device {
struct device dev;
struct module *owner;
};
static inline struct root_device *to_root_device(struct device *d)
{
return container_of(d, struct root_device, dev);
}
static void root_device_release(struct device *dev)
{
kfree(to_root_device(dev));
}
/**
* __root_device_register - allocate and register a root device
* @name: root device name
* @owner: owner module of the root device, usually THIS_MODULE
*
* This function allocates a root device and registers it
* using device_register(). In order to free the returned
* device, use root_device_unregister().
*
* Root devices are dummy devices which allow other devices
* to be grouped under /sys/devices. Use this function to
* allocate a root device and then use it as the parent of
* any device which should appear under /sys/devices/{name}
*
* The /sys/devices/{name} directory will also contain a
* 'module' symlink which points to the @owner directory
* in sysfs.
*
* Returns &struct device pointer on success, or ERR_PTR() on error.
*
* Note: You probably want to use root_device_register().
*/
struct device *__root_device_register(const char *name, struct module *owner)
{
struct root_device *root;
int err = -ENOMEM;
root = kzalloc(sizeof(struct root_device), GFP_KERNEL);
if (!root)
return ERR_PTR(err);
err = dev_set_name(&root->dev, "%s", name);
if (err) {
kfree(root);
return ERR_PTR(err);
}
root->dev.release = root_device_release;
err = device_register(&root->dev);
if (err) {
put_device(&root->dev);
return ERR_PTR(err);
}
#ifdef CONFIG_MODULES /* gotta find a "cleaner" way to do this */
if (owner) {
struct module_kobject *mk = &owner->mkobj;
err = sysfs_create_link(&root->dev.kobj, &mk->kobj, "module");
if (err) {
device_unregister(&root->dev);
return ERR_PTR(err);
}
root->owner = owner;
}
#endif
return &root->dev;
}
EXPORT_SYMBOL_GPL(__root_device_register);
/**
* root_device_unregister - unregister and free a root device
* @dev: device going away
*
* This function unregisters and cleans up a device that was created by
* root_device_register().
*/
void root_device_unregister(struct device *dev)
{
struct root_device *root = to_root_device(dev);
if (root->owner)
sysfs_remove_link(&root->dev.kobj, "module");
device_unregister(dev);
}
EXPORT_SYMBOL_GPL(root_device_unregister);
static void device_create_release(struct device *dev)
{
pr_debug("device: '%s': %s\n", dev_name(dev), __func__);
kfree(dev);
}
static struct device *
device_create_groups_vargs(struct class *class, struct device *parent,
dev_t devt, void *drvdata,
const struct attribute_group **groups,
const char *fmt, va_list args)
{
struct device *dev = NULL;
int retval = -ENODEV;
if (class == NULL || IS_ERR(class))
goto error;
dev = kzalloc(sizeof(*dev), GFP_KERNEL);
if (!dev) {
retval = -ENOMEM;
goto error;
}
device_initialize(dev);
dev->devt = devt;
dev->class = class;
dev->parent = parent;
dev->groups = groups;
dev->release = device_create_release;
dev_set_drvdata(dev, drvdata);
retval = kobject_set_name_vargs(&dev->kobj, fmt, args);
if (retval)
goto error;
retval = device_add(dev);
if (retval)
goto error;
return dev;
error:
put_device(dev);
return ERR_PTR(retval);
}
/**
* device_create_vargs - creates a device and registers it with sysfs
* @class: pointer to the struct class that this device should be registered to
* @parent: pointer to the parent struct device of this new device, if any
* @devt: the dev_t for the char device to be added
* @drvdata: the data to be added to the device for callbacks
* @fmt: string for the device's name
* @args: va_list for the device's name
*
* This function can be used by char device classes. A struct device
* will be created in sysfs, registered to the specified class.
*
* A "dev" file will be created, showing the dev_t for the device, if
* the dev_t is not 0,0.
* If a pointer to a parent struct device is passed in, the newly created
* struct device will be a child of that device in sysfs.
* The pointer to the struct device will be returned from the call.
* Any further sysfs files that might be required can be created using this
* pointer.
*
* Returns &struct device pointer on success, or ERR_PTR() on error.
*
* Note: the struct class passed to this function must have previously
* been created with a call to class_create().
*/
struct device *device_create_vargs(struct class *class, struct device *parent,
dev_t devt, void *drvdata, const char *fmt,
va_list args)
{
return device_create_groups_vargs(class, parent, devt, drvdata, NULL,
fmt, args);
}
EXPORT_SYMBOL_GPL(device_create_vargs);
/**
* device_create - creates a device and registers it with sysfs
* @class: pointer to the struct class that this device should be registered to
* @parent: pointer to the parent struct device of this new device, if any
* @devt: the dev_t for the char device to be added
* @drvdata: the data to be added to the device for callbacks
* @fmt: string for the device's name
*
* This function can be used by char device classes. A struct device
* will be created in sysfs, registered to the specified class.
*
* A "dev" file will be created, showing the dev_t for the device, if
* the dev_t is not 0,0.
* If a pointer to a parent struct device is passed in, the newly created
* struct device will be a child of that device in sysfs.
* The pointer to the struct device will be returned from the call.
* Any further sysfs files that might be required can be created using this
* pointer.
*
* Returns &struct device pointer on success, or ERR_PTR() on error.
*
* Note: the struct class passed to this function must have previously
* been created with a call to class_create().
*/
struct device *device_create(struct class *class, struct device *parent,
dev_t devt, void *drvdata, const char *fmt, ...)
{
va_list vargs;
struct device *dev;
va_start(vargs, fmt);
dev = device_create_vargs(class, parent, devt, drvdata, fmt, vargs);
va_end(vargs);
return dev;
}
EXPORT_SYMBOL_GPL(device_create);
/**
* device_create_with_groups - creates a device and registers it with sysfs
* @class: pointer to the struct class that this device should be registered to
* @parent: pointer to the parent struct device of this new device, if any
* @devt: the dev_t for the char device to be added
* @drvdata: the data to be added to the device for callbacks
* @groups: NULL-terminated list of attribute groups to be created
* @fmt: string for the device's name
*
* This function can be used by char device classes. A struct device
* will be created in sysfs, registered to the specified class.
* Additional attributes specified in the groups parameter will also
* be created automatically.
*
* A "dev" file will be created, showing the dev_t for the device, if
* the dev_t is not 0,0.
* If a pointer to a parent struct device is passed in, the newly created
* struct device will be a child of that device in sysfs.
* The pointer to the struct device will be returned from the call.
* Any further sysfs files that might be required can be created using this
* pointer.
*
* Returns &struct device pointer on success, or ERR_PTR() on error.
*
* Note: the struct class passed to this function must have previously
* been created with a call to class_create().
*/
struct device *device_create_with_groups(struct class *class,
struct device *parent, dev_t devt,
void *drvdata,
const struct attribute_group **groups,
const char *fmt, ...)
{
va_list vargs;
struct device *dev;
va_start(vargs, fmt);
dev = device_create_groups_vargs(class, parent, devt, drvdata, groups,
fmt, vargs);
va_end(vargs);
return dev;
}
EXPORT_SYMBOL_GPL(device_create_with_groups);
static int __match_devt(struct device *dev, const void *data)
{
const dev_t *devt = data;
return dev->devt == *devt;
}
/**
* device_destroy - removes a device that was created with device_create()
* @class: pointer to the struct class that this device was registered with
* @devt: the dev_t of the device that was previously registered
*
* This call unregisters and cleans up a device that was created with a
* call to device_create().
*/
void device_destroy(struct class *class, dev_t devt)
{
struct device *dev;
dev = class_find_device(class, NULL, &devt, __match_devt);
if (dev) {
put_device(dev);
device_unregister(dev);
}
}
EXPORT_SYMBOL_GPL(device_destroy);
/**
* device_rename - renames a device
* @dev: the pointer to the struct device to be renamed
* @new_name: the new name of the device
*
* It is the responsibility of the caller to provide mutual
* exclusion between two different calls of device_rename
* on the same device to ensure that new_name is valid and
* won't conflict with other devices.
*
* Note: Don't call this function. Currently, the networking layer calls this
* function, but that will change. The following text from Kay Sievers offers
* some insight:
*
* Renaming devices is racy at many levels, symlinks and other stuff are not
* replaced atomically, and you get a "move" uevent, but it's not easy to
* connect the event to the old and new device. Device nodes are not renamed at
* all, there isn't even support for that in the kernel now.
*
* In the meantime, during renaming, your target name might be taken by another
* driver, creating conflicts. Or the old name is taken directly after you
* renamed it -- then you get events for the same DEVPATH, before you even see
* the "move" event. It's just a mess, and nothing new should ever rely on
* kernel device renaming. Besides that, it's not even implemented now for
* other things than (driver-core wise very simple) network devices.
*
* We are currently about to change network renaming in udev to completely
* disallow renaming of devices in the same namespace as the kernel uses,
* because we can't solve the problems properly, that arise with swapping names
* of multiple interfaces without races. Means, renaming of eth[0-9]* will only
* be allowed to some other name than eth[0-9]*, for the aforementioned
* reasons.
*
* Make up a "real" name in the driver before you register anything, or add
* some other attributes for userspace to find the device, or use udev to add
* symlinks -- but never rename kernel devices later, it's a complete mess. We
* don't even want to get into that and try to implement the missing pieces in
* the core. We really have other pieces to fix in the driver core mess. :)
*/
int device_rename(struct device *dev, const char *new_name)
{
struct kobject *kobj = &dev->kobj;
char *old_device_name = NULL;
int error;
dev = get_device(dev);
if (!dev)
return -EINVAL;
dev_dbg(dev, "renaming to %s\n", new_name);
old_device_name = kstrdup(dev_name(dev), GFP_KERNEL);
if (!old_device_name) {
error = -ENOMEM;
goto out;
}
if (dev->class) {
error = sysfs_rename_link_ns(&dev->class->p->subsys.kobj,
kobj, old_device_name,
new_name, kobject_namespace(kobj));
if (error)
goto out;
}
error = kobject_rename(kobj, new_name);
if (error)
goto out;
out:
put_device(dev);
kfree(old_device_name);
return error;
}
EXPORT_SYMBOL_GPL(device_rename);
static int device_move_class_links(struct device *dev,
struct device *old_parent,
struct device *new_parent)
{
int error = 0;
if (old_parent)
sysfs_remove_link(&dev->kobj, "device");
if (new_parent)
error = sysfs_create_link(&dev->kobj, &new_parent->kobj,
"device");
return error;
}
/**
* device_move - moves a device to a new parent
* @dev: the pointer to the struct device to be moved
* @new_parent: the new parent of the device (can by NULL)
* @dpm_order: how to reorder the dpm_list
*/
int device_move(struct device *dev, struct device *new_parent,
enum dpm_order dpm_order)
{
int error;
struct device *old_parent;
struct kobject *new_parent_kobj;
dev = get_device(dev);
if (!dev)
return -EINVAL;
device_pm_lock();
new_parent = get_device(new_parent);
new_parent_kobj = get_device_parent(dev, new_parent);
pr_debug("device: '%s': %s: moving to '%s'\n", dev_name(dev),
__func__, new_parent ? dev_name(new_parent) : "<NULL>");
error = kobject_move(&dev->kobj, new_parent_kobj);
if (error) {
cleanup_glue_dir(dev, new_parent_kobj);
put_device(new_parent);
goto out;
}
old_parent = dev->parent;
dev->parent = new_parent;
if (old_parent)
klist_remove(&dev->p->knode_parent);
if (new_parent) {
klist_add_tail(&dev->p->knode_parent,
&new_parent->p->klist_children);
set_dev_node(dev, dev_to_node(new_parent));
}
if (dev->class) {
error = device_move_class_links(dev, old_parent, new_parent);
if (error) {
/* We ignore errors on cleanup since we're hosed anyway... */
device_move_class_links(dev, new_parent, old_parent);
if (!kobject_move(&dev->kobj, &old_parent->kobj)) {
if (new_parent)
klist_remove(&dev->p->knode_parent);
dev->parent = old_parent;
if (old_parent) {
klist_add_tail(&dev->p->knode_parent,
&old_parent->p->klist_children);
set_dev_node(dev, dev_to_node(old_parent));
}
}
cleanup_glue_dir(dev, new_parent_kobj);
put_device(new_parent);
goto out;
}
}
switch (dpm_order) {
case DPM_ORDER_NONE:
break;
case DPM_ORDER_DEV_AFTER_PARENT:
device_pm_move_after(dev, new_parent);
break;
case DPM_ORDER_PARENT_BEFORE_DEV:
device_pm_move_before(new_parent, dev);
break;
case DPM_ORDER_DEV_LAST:
device_pm_move_last(dev);
break;
}
put_device(old_parent);
out:
device_pm_unlock();
put_device(dev);
return error;
}
EXPORT_SYMBOL_GPL(device_move);
/**
* device_shutdown - call ->shutdown() on each device to shutdown.
*/
void device_shutdown(void)
{
struct device *dev, *parent;
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);
/*
* hold reference count of device's parent to
* prevent it from being freed because parent's
* lock is to be held
*/
parent = get_device(dev->parent);
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);
/* hold lock to avoid race with probe/release */
if (parent)
device_lock(parent);
device_lock(dev);
/* Don't allow any more runtime suspends */
pm_runtime_get_noresume(dev);
pm_runtime_barrier(dev);
if (dev->bus && dev->bus->shutdown) {
if (initcall_debug)
dev_info(dev, "shutdown\n");
dev->bus->shutdown(dev);
} else if (dev->driver && dev->driver->shutdown) {
if (initcall_debug)
dev_info(dev, "shutdown\n");
dev->driver->shutdown(dev);
}
device_unlock(dev);
if (parent)
device_unlock(parent);
put_device(dev);
put_device(parent);
spin_lock(&devices_kset->list_lock);
}
spin_unlock(&devices_kset->list_lock);
}
/*
* Device logging functions
*/
#ifdef CONFIG_PRINTK
static int
create_syslog_header(const struct device *dev, char *hdr, size_t hdrlen)
{
const char *subsys;
size_t pos = 0;
if (dev->class)
subsys = dev->class->name;
else if (dev->bus)
subsys = dev->bus->name;
else
return 0;
pos += snprintf(hdr + pos, hdrlen - pos, "SUBSYSTEM=%s", subsys);
if (pos >= hdrlen)
goto overflow;
/*
* Add device identifier DEVICE=:
* b12:8 block dev_t
* c127:3 char dev_t
* n8 netdev ifindex
* +sound:card0 subsystem:devname
*/
if (MAJOR(dev->devt)) {
char c;
if (strcmp(subsys, "block") == 0)
c = 'b';
else
c = 'c';
pos++;
pos += snprintf(hdr + pos, hdrlen - pos,
"DEVICE=%c%u:%u",
c, MAJOR(dev->devt), MINOR(dev->devt));
} else if (strcmp(subsys, "net") == 0) {
struct net_device *net = to_net_dev(dev);
pos++;
pos += snprintf(hdr + pos, hdrlen - pos,
"DEVICE=n%u", net->ifindex);
} else {
pos++;
pos += snprintf(hdr + pos, hdrlen - pos,
"DEVICE=+%s:%s", subsys, dev_name(dev));
}
if (pos >= hdrlen)
goto overflow;
return pos;
overflow:
dev_WARN(dev, "device/subsystem name too long");
return 0;
}
int dev_vprintk_emit(int level, const struct device *dev,
const char *fmt, va_list args)
{
char hdr[128];
size_t hdrlen;
hdrlen = create_syslog_header(dev, hdr, sizeof(hdr));
return vprintk_emit(0, level, hdrlen ? hdr : NULL, hdrlen, fmt, args);
}
EXPORT_SYMBOL(dev_vprintk_emit);
int dev_printk_emit(int level, const struct device *dev, const char *fmt, ...)
{
va_list args;
int r;
va_start(args, fmt);
r = dev_vprintk_emit(level, dev, fmt, args);
va_end(args);
return r;
}
EXPORT_SYMBOL(dev_printk_emit);
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 dev_printk_emit(level[1] - '0', dev,
"%s %s: %pV",
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