1、前言
Linux内核中的设备驱动模型，是建立在sysfs设备文件系统和kobject上的，由总线（bus）、设备（device）、驱动（driver）和类（class）所组成的关系结构，在底层，Linux系统中的每个设备都有一个device结构体的实例，本文将对Linux内核的device结构体以及相关结构进行简要分析。
2、device结构体
在Linux内核源码中，struct device结构体的定义在include/linux/device.h中，实现的主要方法在drivers/base/core.c文件中，device结构体的定义如下所示：
struct device { struct device *parent; struct device_private *p; struct kobject kobj; const char *init_name; /* initial name of the device */ const struct device_type *type; struct mutex mutex; /* mutex to synchronize calls to * its driver. */ struct bus_type *bus; /* type of bus device is on */ struct device_driver *driver; /* which driver has allocated this device */ void *platform_data; /* Platform specific data, device core doesn't touch it */ void *driver_data; /* Driver data, set and get with dev_set/get_drvdata */ struct dev_links_info links; struct dev_pm_info power; struct dev_pm_domain *pm_domain; #ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN struct irq_domain *msi_domain; #endif #ifdef CONFIG_PINCTRL struct dev_pin_info *pins; #endif #ifdef CONFIG_GENERIC_MSI_IRQ struct list_head msi_list; #endif #ifdef CONFIG_NUMA int numa_node; /* NUMA node this device is close to */ #endif const struct dma_map_ops *dma_ops; u64 *dma_mask; /* dma mask (if dma'able device) */ u64 coherent_dma_mask;/* Like dma_mask, but for alloc_coherent mappings as not all hardware supports 64 bit addresses for consistent allocations such descriptors. */ unsigned long dma_pfn_offset; struct device_dma_parameters *dma_parms; struct list_head dma_pools; /* dma pools (if dma'ble) */ struct dma_coherent_mem *dma_mem; /* internal for coherent mem override */ #ifdef CONFIG_DMA_CMA struct cma *cma_area; /* contiguous memory area for dma allocations */ #endif /* arch specific additions */ struct dev_archdata archdata; struct device_node *of_node; /* associated device tree node */ struct fwnode_handle *fwnode; /* firmware device node */ dev_t devt; /* dev_t, creates the sysfs "dev" */ u32 id; /* device instance */ spinlock_t devres_lock; struct list_head devres_head; struct klist_node knode_class; struct class *class; const struct attribute_group **groups; /* optional groups */ void (*release)(struct device *dev); struct iommu_group *iommu_group; struct iommu_fwspec *iommu_fwspec; bool offline_disabled:1; bool offline:1; bool of_node_reused:1; };
部分结构体成员解释：
parent：指向设备的“父”设备，它所连接的设备，在大多数情况下，父设备是某种总线或主机控制器，如果该成员为NULL，则该设备为顶级设备；
p：用于保存设备驱动核心部分的私有数据；
kobj：嵌入的struct kobject对象实例；
init_name：设备的初始名称
type：设备的类型，用于标识设备类型并携带特定类型信息；
mutex：用于同步的互斥锁；
bus：该设备所处于的总线；
driver：该设备所分配的驱动程序；
platform_data：设备中特定的平台数据；
driver_data：指向驱动程序特定的私有数据；
of_node：与设备数相联系的结构体指针；
devt：用于表示设备的设备号；
devres_lock：保护设备资源的自旋锁；
devres_head：设备资源的双向链表头；
knode_class：接入class链表时所需要的klist节点；
class：指向设备所属class的指针；
groups：该设备的属性集合；
release：函数指针，当设备需要释放时调用此函数。
device结构体中有一部分成员不愿意被外界看到，所以抽象出了struct device_private这个结构体，该结构体包括了设备驱动模型内部的链接，结构体定义如下：
struct device_private { struct klist klist_children; struct klist_node knode_parent; struct klist_node knode_driver; struct klist_node knode_bus; struct list_head deferred_probe; struct device *device; };
部分结构体成员解释：
klist_children：子设备的klist链表；
knode_parent：接入父设备的klist_children时所需要的klist节点；
knode_driver：接入驱动的设备链表时所需要的klist节点；
knode_bus：接入总线的设备链表时所需要的klist节点；
device：回指struct device结构体的指针。
device结构体中包含了一个struct device_type结构体的指针，用于描述设备的类型，该结构体定义如下：
struct device_type { const char *name; const struct attribute_group **groups; int (*uevent)(struct device *dev, struct kobj_uevent_env *env); char *(*devnode)(struct device *dev, umode_t *mode, kuid_t *uid, kgid_t *gid); void (*release)(struct device *dev); const struct dev_pm_ops *pm; };
该结构体功能类似于kobj_type。
还有一个设备属性结构体，名称为struct device_attribute，是对struct attribute的进一步封装，并提供了设备属性的读写函数指针，结构体定义如下：
/* interface for exporting device attributes */ struct device_attribute { struct attribute attr; ssize_t (*show)(struct device *dev, struct device_attribute *attr, char *buf); ssize_t (*store)(struct device *dev, struct device_attribute *attr, const char *buf, size_t count); };
其它的一些struct device结构体成员，例如archdata、dma和devres等，是一些设备特有的东西，暂时不讨论，本文主要关心设备驱动模型的基本建立。
3、device的实现
接下来对device的实现进行简单分析，实现的方法主要在文件core.c中：
int __init devices_init(void) { devices_kset = kset_create_and_add("devices", &device_uevent_ops, NULL);///sys/devices目录 if (!devices_kset) return -ENOMEM; dev_kobj = kobject_create_and_add("dev", NULL);///sys/dev目录 if (!dev_kobj) goto dev_kobj_err; sysfs_dev_block_kobj = kobject_create_and_add("block", dev_kobj);///sys/dev/block目录 if (!sysfs_dev_block_kobj) goto block_kobj_err; sysfs_dev_char_kobj = kobject_create_and_add("char", dev_kobj);///sys/dev/char目录 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; }
devices_init()函数是在设备驱动模型初始化时调用的部分初始函数，它实现的功能是建立sysfs中的devices目录和dev目录，然后在dev目录下建立block和char两个子目录，block和char目录用来存放设备号文件。
#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 ", (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, };
to_dev_attr()宏定义用来获取struct device_attribute结构体的首地址，dev_sysfs_ops结构体的内容就是device注册到sysfs设备文件系统的操作函数，dev_attr_show()和dev_attr_store()函数会调用struct device_attribute结构体内的读写属性相关函数。
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. ", 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 void device_get_ownership(struct kobject *kobj, kuid_t *uid, kgid_t *gid) { struct device *dev = kobj_to_dev(kobj); if (dev->class && dev->class->get_ownership) dev->class->get_ownership(dev, uid, gid); } static struct kobj_type device_ktype = { .release = device_release, .sysfs_ops = &dev_sysfs_ops, .namespace = device_namespace, .get_ownership = device_get_ownership, };
当struct device结构体内的实例kobject引用计数到0时会调用device_release()函数来释放掉device，函数调用时，会先通过kobj指针获取device的首地址，然后判断device下的release()是否存在，如果存在则调用，否则，依次判断device下device_type下的release()和device下class下的dev_release()函数是否存在，存在则调用，最后将device_private结构体指针指向的内存释放掉。
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 ", 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 ", 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 ", 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, };
kset_uevent_ops结构体内的函数是用于管理kset内部的kobject的uevent操作的，其中，filter()函数用于阻止一个kobject向用户空间发送uevent，当函数的返回值为0时表示阻止，在上面的dev_uevent_filter()函数中检查了device所属的bus或者class是否存在，如果都不存在，则返回0，也就是没有发送uevent的必要了，name()函数用于覆盖kset发送给用户空间的名称，在上面的dev_uevent_name()函数选择使用device所属的bus或者class的名称，uevent()函数是在uevent将被发送到用户空间之前进行调用的，用于向uevent中增加新的环境变量。
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 ", 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) { if (kobject_synth_uevent(&dev->kobj, buf, count)) dev_err(dev, "uevent: failed to send synthetic uevent "); return count; } static DEVICE_ATTR_RW(uevent);
device不仅在kset中添加了对uevent的管理，还把uevent信息封装成设备的一个属性文件uevent，其权限为拥有者可读写，其中uevent_show()函数用于在用户空间显示uevent中的环境变量，uevent_store()函数则用于将uevent属性写入到内核空间。
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; if (device_supports_offline(dev) && !dev->offline_disabled) { error = device_create_file(dev, &dev_attr_online); if (error) goto err_remove_dev_groups; } 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); }
device_add_attrs()负责device中的属性添加，包括几个部分的集合，分别是class中groups、device_type中的groups还有device本身的groups，device_remove_attrs()则是相反的操作，负责删除device的属性。
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);
这里定义了一个名为dev的属性文件，其权限为拥有者只能读，函数实现的功能为显示设备的设备号。
/** * 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' ", attr->attr.name); WARN(((attr->attr.mode & S_IRUGO) && !attr->show), "Attribute %s: read permission without 'show' ", attr->attr.name); error = sysfs_create_file(&dev->kobj, &attr->attr); } return error; } /** * device_remove_file - remove sysfs attribute file. * @dev: device. * @attr: device attribute descriptor. */ void device_remove_file(struct device *dev, const struct device_attribute *attr) { if (dev) sysfs_remove_file(&dev->kobj, &attr->attr); } /** * device_create_bin_file - create sysfs binary attribute file for device. * @dev: device. * @attr: device binary attribute descriptor. */ int device_create_bin_file(struct device *dev, const struct bin_attribute *attr) { int error = -EINVAL; if (dev) error = sysfs_create_bin_file(&dev->kobj, attr); return error; } /** * 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); }
上面这些函数是对sysfs提供的API进行简单的封装，其中device_create_file()和device_remove_file()提供直接的设备属性文件管理方法，device_create_bin_file()和device_remove_bin_file()则是提供设备管理二进制文件的方法。
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); }
klist_children_get()和klist_children_put()函数是当设备挂入和删除父设备的klist_children链表时调用的函数，相当于对设备的kobject引用计数的操作。
/** * 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; } /** * put_device - decrement reference count. * @dev: device in question. */ void put_device(struct device *dev) { /* might_sleep(); */ if (dev) kobject_put(&dev->kobj); }
get_device()函数和put_device()用于dev的引用计数，通过内嵌的kobject来实现，当引用计数为0时，将会调用前面分析到的device_release()函数。
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); #ifdef CONFIG_GENERIC_MSI_IRQ INIT_LIST_HEAD(&dev->msi_list); #endif INIT_LIST_HEAD(&dev->links.consumers); INIT_LIST_HEAD(&dev->links.suppliers); dev->links.status = DL_DEV_NO_DRIVER; }
device_initialize()函数是设备在sysfs中注册的第一个阶段，用于将struct device结构体进行初始化，主要是对结构体内的一些成员进行初始化，结构体内嵌的kobject下的kset配置为devices_kset，调用kobject_init()函数设置device_ktype和sysfs_ops结构中的两个函数和device_release()函数，另外还有一些特定资源需要的成员的初始化。
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); else if (parent->class && !dev->class->ns_type) return &parent->kobj; else parent_kobj = &parent->kobj; mutex_lock(&gdp_mutex); /* find our class-directory at the parent and reference it */ spin_lock(&dev->class->p->glue_dirs.list_lock); list_for_each_entry(k, &dev->class->p->glue_dirs.list, entry) if (k->parent == parent_kobj) { kobj = kobject_get(k); break; } spin_unlock(&dev->class->p->glue_dirs.list_lock); if (kobj) { mutex_unlock(&gdp_mutex); return kobj; } /* or create a new class-directory at the parent device */ k = class_dir_create_and_add(dev->class, parent_kobj); /* do not emit an uevent for this simple "glue" directory */ mutex_unlock(&gdp_mutex); return k; } /* 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; }
函数get_device_parent()用于获取父节点的kobject，get_device_parent()的返回值直接决定了device将被挂在哪个目录下，设备最终挂在的目录，是由多个因素综合决定的。
static int device_add_class_symlinks(struct device *dev) { struct device_node *of_node = dev_of_node(dev); int error; if (of_node) { error = sysfs_create_link(&dev->kobj, of_node_kobj(of_node), "of_node"); if (error) dev_warn(dev, "Error %d creating of_node link ",error); /* An error here doesn't warrant bringing down the device */ } if (!dev->class) return 0; error = sysfs_create_link(&dev->kobj, &dev->class->p->subsys.kobj, "subsystem"); if (error) goto out_devnode; 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_devnode: sysfs_remove_link(&dev->kobj, "of_node"); return error; }
device_add_class_symlinks()函数用于在device和class直接添加一些软链接，在device目录下创建指向class的subsystem文件，在class目录下创建指向device的同名文件，如果device有父设备，而且device不是块设备分区时，则在device目录下创建一个指向父设备的device链接文件。
static void device_remove_class_symlinks(struct device *dev) { if (dev_of_node(dev)) sysfs_remove_link(&dev->kobj, "of_node"); 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)); }
device_remove_class_symlinks()函数则是相反操作，用于删除device和class之间建立的软链接。
/** * 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; }
dev_set_name()函数用于设置device的名称，该函数只能在设备未注册之前使用，名称是通过dev->kobject进行管理的。
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; }
该函数用于为device选择合适的/sys/dev下的kobject或者字符设备或者NULL。
#define format_dev_t(buffer, dev) ({ sprintf(buffer, "%u:%u", MAJOR(dev), MINOR(dev)); buffer; }) 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); } }
device_create_sys_dev_entry()函数实现的功能是在/sys/dev相应的目录下创建相应设备的软链接，首先通过调用device_to_dev_kobj()函数获得父节点的kobj，然后调用sysfs_create_link()函数建立软链接，device_remove_sys_dev_entry()函数则是执行相反的操作，用于删除已经在/sys/dev下建立的软链接。
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; }
函数device_private_init()为dev->p分配内存空间并进行初始化，该内存的空间释放是在调用device_release()函数释放设备时才会释放。
上面提到到的函数都是比较零散的函数，看起来并没有什么联系，接下来继续分析一下提供给外界的接口函数实现：
/** * 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); }
首先是device_register()函数，该函数是提供给外界注册设备的接口，该函数首先调用device_initialize()函数进行结构体的变量初始化，然后调用device_add()函数将device添加到系统中，但是需要注意的是，在调用device_register()注册device之前，有一些device结构体变量需要自己设置，其中有指明设备位置的struct device *parent、struct bus_type *bus、struct class *class等，有指明设备属性的const char *init_name、struct device_type *type、const struct attribute_group **groups、dev_t devt和release()函数等，不同的设备使用的方法不同。
接下来分析device_add()函数的实现：
/** * 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; struct kobject *kobj; struct class_interface *class_intf; int error = -EINVAL; struct kobject *glue_dir = NULL; dev = get_device(dev); //增加device的引用计数 if (!dev) goto done; if (!dev->p) { error = device_private_init(dev); //分配和初始化dev->p 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); //设置设备的名称 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 ", dev_name(dev), __func__); parent = get_device(dev->parent); //增加对parent的引用计数，无parent时返回NULL kobj = get_device_parent(dev, parent); //获取父kobject if (IS_ERR(kobj)) { error = PTR_ERR(kobj); goto parent_error; } if (kobj) dev->kobj.parent = kobj; //设置dev->kobj的父kobject /* use parent numa_node */ if (parent && (dev_to_node(dev) == NUMA_NO_NODE)) 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); //将device内嵌的kobj加入到kobject层次结构中 if (error) { glue_dir = get_glue_dir(dev); goto Error; } /* notify platform of device entry */ if (platform_notify) platform_notify(dev); error = device_create_file(dev, &dev_attr_uevent); //添加uevent属性文件 if (error) goto attrError; error = device_add_class_symlinks(dev); //dev与class软链接创建 if (error) goto SymlinkError; error = device_add_attrs(dev); //添加属性 if (error) goto AttrsError; error = bus_add_device(dev); //将设备添加到总线上，创建dev与bus间的软链接 if (error) goto BusError; error = dpm_sysfs_add(dev); //增加dev下的power属性集合 if (error) goto DPMError; device_pm_add(dev); if (MAJOR(dev->devt)) { //主设备号存在 error = device_create_file(dev, &dev_attr_dev); //添加dev属性 if (error) goto DevAttrError; error = device_create_sys_dev_entry(dev); //在/sys/dev下添加相应的软链接 if (error) goto SysEntryError; devtmpfs_create_node(dev); //在/dev下添加相应的设备节点 } /* 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); //kobject发布KOBJ_ADD消息到用户空间 bus_probe_device(dev); //为device寻找合适的驱动 if (parent) klist_add_tail(&dev->p->knode_parent, &parent->p->klist_children); //如果父节点存在，将挂入到klist_children链表 if (dev->class) { //如果device所属的class存在 mutex_lock(&dev->class->p->mutex); /* tie the class to the device */ klist_add_tail(&dev->knode_class, &dev->class->p->klist_devices); //节点插入链表 /* 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); //减少device的引用计数 return error; SysEntryError: if (MAJOR(dev->devt)) device_remove_file(dev, &dev_attr_dev); DevAttrError: device_pm_remove(dev); dpm_sysfs_remove(dev); DPMError: bus_remove_device(dev); BusError: device_remove_attrs(dev); AttrsError: device_remove_class_symlinks(dev); SymlinkError: device_remove_file(dev, &dev_attr_uevent); attrError: kobject_uevent(&dev->kobj, KOBJ_REMOVE); glue_dir = get_glue_dir(dev); kobject_del(&dev->kobj); Error: cleanup_glue_dir(dev, glue_dir); parent_error: put_device(parent); name_error: kfree(dev->p); dev->p = NULL; goto done; }
函数device_add()用于将dev添加到设备驱动模型中去，它先调用get_device()来增加dev的引用计数，然后调用device_private_init()进行dev->p的分配和初始化，调用dev_set_name()对dev的名字进行设置，接下来，要做的是准备将dev添加到sysfs设备文件系统中去，首先是调用get_device()增加对paren的引用计数（无论是直接挂在parent下还是通过一个类层挂在parent下都要增加parent的引用计数），然后调用get_device_parent()找到实际要加入的父kobject，并调用kobject_add()将dev->kobj加入到dev->kobj.parent的层次结构中去，接下来是完成属性和属性集合的添加，调用device_create_file()添加uevent属性文件，然后调用device_add_class_symlinks()在dev下创建一个软链接subsystem，指向相对应的class，然后继续调用device_add_attrs()添加属性和属性集合，调用bus_add_device()添加设备的总线属性，在dev与bus之间创建软链接，并将dev挂入到总线的设备链表中去，dpm_sysfs_add()用于增加dev下的power属性集合，调用device_pm_add()将设备添加到dpm_list链表中去。如果设备被分配了主设备号，调用device_create_file()添加dev属性文件，然后调用device_create_sys_dev_entry()在/sys/dev下创建相应的软链接，调用devtmpfs_create_node()在/dev下添加对应的设备节点文件。函数开始调用kobject_uevent()向用户空间发布KOBJ_ADD消息通知，并调用bus_probe_device()为设备探测寻找合适的驱动程序，如果设备有父节点的话，则把dev->p->knode_parent挂入到parent->p->klist_children链表中，如果设备有所属的class，则将dev->knode_class挂入class->p>class_devices上，并调用可能的类设备接口add_dev()函数，对于直接在bus上的设备来讲，可以调用bus_probe_device()来查找驱动程序，但是不与bus直接接触的设备，则靠class来去寻找驱动，便使用了class_interface内的add_dev()方式，函数最后调用put_device()减少在开头增加的引用计数并返回。
/** * 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 ", dev_name(dev), __func__); device_del(dev); put_device(dev); }
有设备注册函数，肯定也有设备注销函数，device_unregister()函数实现的功能为将dev从系统中注销，并减少创建时产生的引用计数，当引用计数为0时，将销毁dev。
/** * 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 kobject *glue_dir = NULL; 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); //将sysfs下的power属性集合移除 if (parent) //如果存在父节点 klist_del(&dev->p->knode_parent); //将设备节点从父节点链表中移除 if (MAJOR(dev->devt)) { //如果分配了主设备号 devtmpfs_delete_node(dev); //将/dev下的设备节点文件移除 device_remove_sys_dev_entry(dev); ///sys/dev下的软链接取消 device_remove_file(dev, &dev_attr_dev); //将属性文件移除 } 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); //移除uevent属性文件 device_remove_attrs(dev); //属性及属性集合移除 bus_remove_device(dev); //总线上移除设备 device_pm_remove(dev); //将dev从dpm_list中移除 driver_deferred_probe_del(dev); //驱动移除 device_remove_properties(dev); device_links_purge(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); //kobject发布KOBJ_REMOVE消息到用户空间 glue_dir = get_glue_dir(dev); kobject_del(&dev->kobj); //将内嵌的kobj从层次结构中移除 cleanup_glue_dir(dev, glue_dir); put_device(parent); //父节点引用计数减1操作 }
函数device_del()是与device_add()相对的函数，device_add()将设备添加到系统中，device_del()则是将设备从系统中移除，包括了将dev从设备驱动模型的各种klist链表中进行脱离，又将dev从sysfs的各个地方创建的文件进行删除的工作。
static struct device *prev_device(struct klist_iter *i) //返回前一个设备 { struct klist_node *n = klist_prev(i); struct device *dev = NULL; struct device_private *p; if (n) { p = to_device_private_parent(n);//返回device_private结构体的首地址 dev = p->device;//将struct device结构体地址返回 } return dev; } static struct device *next_device(struct klist_iter *i) { struct klist_node *n = klist_next(i); struct device *dev = NULL; struct device_private *p; if (n) { p = to_device_private_parent(n); dev = p->device; } return dev; }
内部函数prev_device()和next_device()用于device的klist的链表遍历，prev_device()将返回前一个设备，next_device()将返回下一个设备。
/** * 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 '/' */ s = kstrdup(dev_name(dev), GFP_KERNEL); if (!s) return NULL; strreplace(s, '!', '/'); return *tmp = s; }
函数device_get_devnode()用于返回设备的路径名。
/** * 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);//迭代器初始化，从链表头开始 while ((child = next_device(&i)) && !error) //正序遍历klist_children链表 error = fn(child, data); klist_iter_exit(&i); return error; } int device_for_each_child_reverse(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 = prev_device(&i)) && !error) //逆序遍历klist_children链表 error = fn(child, data); klist_iter_exit(&i); return error; } 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; }
在上面的函数都是对设备链表的遍历，device_for_each_child()函数和device_for_each_child_reverse()函数对父设备下的子设备进行遍历，并都调用一个特定的函数fn()进行处理，device_find_child()函数则是查找特定的子设备，查找使用特定match()函数进行匹配。
接下来，继续分析动态创建struct device的方法，其原理和kobject和kset的动态创建类似：
static void device_create_release(struct device *dev) { pr_debug("device: '%s': %s ", 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))//判断class指针是否有效 goto error; dev = kzalloc(sizeof(*dev), GFP_KERNEL);//为dev动态分配内存 if (!dev) { retval = -ENOMEM; goto error; } device_initialize(dev);//设备初始化 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);//设置kobject的name if (retval) goto error; retval = device_add(dev);//将设备添加到sysfs层次系统 if (retval) goto error; return dev; error: put_device(dev); return ERR_PTR(retval);//将异常指针返回 } /** * 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); } 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; } 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; }
在上面代码中，device_create_release()和device_create_groups_vargs()属于两个内部的静态函数，第一个函数用于释放device分配的内核空间，由于dev是动态分配的，而第二个函数则是用来动态创建一个device，函数首先对传入的class进行判断，然后对device进行内存分配，分配成功后就是开始调用device_initialize()对设备初始化，并手动对device的一些成员进行赋值，然后调用kobject_set_name_vargs()对device中嵌入的kobject进行名称设置，最后，则是调用device_add()函数将动态创建的device添加到sysfs层次系统，而device_create_vargs()、device_create()和device_create_with_groups()都是对device_create_groups_vargs()的进一步封装，device_create()和device_create_with_groups()的区别在于创建的时候是否要创建device的组属性文件。
static int __match_devt(struct device *dev, const void *data) { const dev_t *devt = data; return dev->devt == *devt;//设备号匹配 } /** * 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);//在class下寻找设备 if (dev) { put_device(dev);//减少引用计数 device_unregister(dev);//注销设备 } }
device_create()用于动态创建一个设备，而device_destroy()函数则用来销毁一个device_create()创建出来的设备，__match_devt()属于内部的静态函数，用于class_find_device()函数寻找需要销毁的device，主要是通过设备号进行匹配而寻找，之所以需要使用put_device()减少引用计数，是因为使用class_find_device()中调用了get_device()增加了引用计数。
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 ", 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; }
函数device_rename()是当设备在sysfs中注册后，用来改变设备的名称用的，首先改变/sys/class目录下的软链接的名称，然后使用kobject_rename()将device下嵌入的kobject进行重新命名。
/** * 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->class && dev->class->shutdown_pre) { if (initcall_debug) dev_info(dev, "shutdown_pre "); dev->class->shutdown_pre(dev); } if (dev->bus && dev->bus->shutdown) { if (initcall_debug) dev_info(dev, "shutdown "); dev->bus->shutdown(dev); } else if (dev->driver && dev->driver->shutdown) { if (initcall_debug) dev_info(dev, "shutdown "); 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); }
函数device_shutdown()用来关闭sysfs上的每个设备，它在系统关闭时才会进行调用，在函数内，使用了devices_kset这个顶层kset，所在的目录为/sys/devices，因此，函数调用会遍历到注册的到sysfs上的每个设备，调用设备相应的总线或驱动定义的shutdown()函数，每个设备虽然可以有不同的parent，但是kset还是一样的，当在调用kobject_add()函数时，将devices_kset这个kset->kobj设置成parent，那么新添加的kobject就会挂在/sys/devices顶层目录下，例如virtual目录等。
4、小结
在内核中，struct device结构体的实现非常地复杂，它是Linux内核设备驱动模型的基础，为了适应越来越复杂的情景，以及提高设备的驱动性能，其实现将会越来越复杂，对其分析点到为止。
参考：
《LINUX设备驱动程序（第三版）》
https://blog.csdn.net/qb_2008/article/details/6847133
https://blog.csdn.net/abo8888882006/article/details/5424363