Linux一切皆文件。
misc设备 --- 没有具体硬件 --- 实际上就是一块内存 --- 主要是因为注册简单
Java层 --> native层 --> 驱动层 --> 服务层
这里源码是基于Android6.0的驱动层源码
一、Binder驱动层源码
1.kernel\drivers\staging\android\binder.c#binder_init
binder驱动的初始化。在该方法中,主要是做如下的工作:
- 分配内存
- 初始化devices设备
- 将设备放入链表binder_devices中
static int __init binder_init(void)
{
// 返回值
int ret;
char *device_name, *device_names;
struct binder_device *device;
struct hlist_node *tmp;
// 创建单线程的Binder工作队列
binder_deferred_workqueue = create_singlethread_workqueue("binder");
if (!binder_deferred_workqueue)
return -ENOMEM;
binder_debugfs_dir_entry_root = debugfs_create_dir("binder", NULL);
if (binder_debugfs_dir_entry_root)
binder_debugfs_dir_entry_proc = debugfs_create_dir("proc",
binder_debugfs_dir_entry_root);
if (binder_debugfs_dir_entry_root) {
debugfs_create_file("state",
S_IRUGO,
binder_debugfs_dir_entry_root,
NULL,
&binder_state_fops);
debugfs_create_file("stats",
S_IRUGO,
binder_debugfs_dir_entry_root,
NULL,
&binder_stats_fops);
debugfs_create_file("transactions",
S_IRUGO,
binder_debugfs_dir_entry_root,
NULL,
&binder_transactions_fops);
debugfs_create_file("transaction_log",
S_IRUGO,
binder_debugfs_dir_entry_root,
&binder_transaction_log,
&binder_transaction_log_fops);
debugfs_create_file("failed_transaction_log",
S_IRUGO,
binder_debugfs_dir_entry_root,
&binder_transaction_log_failed,
&binder_transaction_log_fops);
}
/*
* 分配内存
*/
device_names = kzalloc(strlen(binder_devices_param) + 1, GFP_KERNEL);
if (!device_names) {
ret = -ENOMEM;
goto err_alloc_device_names_failed;
}
// 从配置文件中读取binder_devices_param,并且拷贝到device_names
// 这里的配置文件,其实就是一个Kconfig文件中的ANDROID_BINDER_DEVICES中的default值
// 其实就是读取的binder
strcpy(device_names, binder_devices_param);
while ((device_name = strsep(&device_names, ","))) {
// 初始化binder设备
ret = init_binder_device(device_name);
if (ret)
goto err_init_binder_device_failed;
}
return ret;
err_init_binder_device_failed:
hlist_for_each_entry_safe(device, tmp, &binder_devices, hlist) {
misc_deregister(&device->miscdev);
hlist_del(&device->hlist);
kfree(device);
}
err_alloc_device_names_failed:
debugfs_remove_recursive(binder_debugfs_dir_entry_root);
destroy_workqueue(binder_deferred_workqueue);
return ret;
}
为binder设备分配内存并且初始化
/**
* 初始化Binder设备
*
*/
static int __init init_binder_device(const char *name)
{
int ret;
struct binder_device *binder_device;
// 为Binder设备分配内存空间(分配虚拟内存)
binder_device = kzalloc(sizeof(*binder_device), GFP_KERNEL);
if (!binder_device)
return -ENOMEM;
// 初始化设备信息
binder_device->miscdev.fops = &binder_fops;
binder_device->miscdev.minor = MISC_DYNAMIC_MINOR;
// 这里的name其实就是binder
binder_device->miscdev.name = name;
// binder的uid是无效的。uid主要是去拿系统服务的uid
binder_device->context.binder_context_mgr_uid = INVALID_UID;
binder_device->context.name = name;
// 注册misc设备
ret = misc_register(&binder_device->miscdev);
if (ret < 0) {
kfree(binder_device);
return ret;
}
// 把binder设备添加到设备列表中
// 即将&binder_device->hlist插入到&binder_devices
hlist_add_head(&binder_device->hlist, &binder_devices);
return ret;
}
binder_fops结构体
/**
* syscall
* 就是类似jni工具,java层调用native层的时候的对应关系
* native层调用驱动层,将native层的方法和驱动层的方法做绑定
* 比如native层调用了mmap方法,那么如何进入到驱动层并且调用到驱动层
* 的方法叫什么,就是通过这里的binder_fops构造做绑定
* 这样native层调用mmap的时候,就会调用驱动层的binder_mmap方法
*/
static const struct file_operations binder_fops = {
.owner = THIS_MODULE,
.poll = binder_poll,
.unlocked_ioctl = binder_ioctl,
.compat_ioctl = binder_ioctl,
.mmap = binder_mmap,
.open = binder_open,
.flush = binder_flush,
.release = binder_release,
};
2.kernel\drivers\staging\android\binder.c#binder_open
开启binder驱动
- 创建binder_proc对象
- 保存当前信息到proc中
- filp->private_data = proc;即将proc保存到filp中的private_data中,方便binder驱动在使用的时候通过filp取出proc
- proc中的proc_node节点添加binder_procs链表中
/**
* 由客户端或者服务端去打开binder驱动
* 1.创建binder_proc对象
* 2.当前进程信息保存到binder_proc对象中
* 3.把proc保存到filp->private_data
* 4.添加到binder_procs链表中
*/
static int binder_open(struct inode *nodp, struct file *filp)
{
struct binder_proc *proc;
struct binder_device *binder_dev;
binder_debug(BINDER_DEBUG_OPEN_CLOSE, "binder_open: %d:%d\n",
current->group_leader->pid, current->pid);
// 初始化结构体:用来保存进程信息
// Client端去打开Server端的时候,实际上是跟Binder通信,Client端通过Binder
// 拿到服务,然后再由Binder返回服务
// 给proc结构体分配内存(虚拟内存)
// proc其实可以理解为clientActivity,进程信息保存在proc中
// 在binder驱动拿到proc代表这个进程,里面有进程所有相关的binder实体,
// binder引用,binder线程之类的所有进程放在一个双向链表procs里
proc = kzalloc(sizeof(*proc), GFP_KERNEL);
if (proc == NULL)
return -ENOMEM;
get_task_struct(current);
// 当前进程的任务栈保存在proc中的tsk中
// 这里主要就是做对于proc结构体进行一系列的初始化
proc->tsk = current;
// todo是目标任务
INIT_LIST_HEAD(&proc->todo);
// wait是当前任务
init_waitqueue_head(&proc->wait);
// 把当前任务的nice值转换成优先级
proc->default_priority = task_nice(current);
binder_dev = container_of(filp->private_data, struct binder_device,
miscdev);
proc->context = &binder_dev->context;
// 同步锁
binder_lock(__func__);
// proc计数,需要加1
binder_stats_created(BINDER_STAT_PROC);
// 放在链表,proc中的proc_node节点放在binder_procs链表中
hlist_add_head(&proc->proc_node, &binder_procs);
// 保存当前进程pid到proc中
proc->pid = current->group_leader->pid;
INIT_LIST_HEAD(&proc->delivered_death);
// 把proc放到filp->private_data中
// 后续binder驱动在使用的时候,就通过filp获取proc
filp->private_data = proc;
// 解除同步锁
binder_unlock(__func__);
if (binder_debugfs_dir_entry_proc) {
char strbuf[11];
snprintf(strbuf, sizeof(strbuf), "%u", proc->pid);
/*
* proc debug entries are shared between contexts, so
* this will fail if the process tries to open the driver
* again with a different context. The priting code will
* anyway print all contexts that a given PID has, so this
* is not a problem.
*/
proc->debugfs_entry = debugfs_create_file(strbuf, S_IRUGO,
binder_debugfs_dir_entry_proc,
(void *)(unsigned long)proc->pid,
&binder_proc_fops);
}
return 0;
}
3.kernel\drivers\staging\android\binder.c#binder_mmap
- 通过用户空间的虚拟内存大小 --- 分配一块内核的虚拟内存
- 分配了一块物理内存(一页 --- 4KB)这块4KB是因为还没通信,等到要用的时候,用多少分配多少
- 把这块物理内存分配映射到内核的虚拟内存和用户空间的虚拟内存
这里分配4KB,是因为进程间通信不止4KB,但是现在还没有通信,优先分配4KB,等到要用的时候,要用多少分配多少
在binder_mmap函数中会判断传输的数据是否是大于4M,如果是大于4M,则限制为4M,驱动层binder数据传输不能超过4M。如果是Intent传输数据,则定义最大的数据传输是1M-8K,如果是异步传输,则需要除以二
在获取service_manager服务时,处理ProcessState,会new了一个ProcessState对象。
而ProcessState::self()其实就是创建进程对象,然后通过ProcessState的getContextObject函数获取到对应的BpBinder对象,用BpBinder对象与服务端的BBinder进行通信。而在这里,就会创建对应的内存大小,这里其实就是native层对binder的内存大小限制,这里限制的大小就是1M-8K。就是10241024-(40962)
#define BINDER_VM_SIZE ((110241024) - (4096 *2))
new ProcessState做的事情:
打开驱动 -- 调用open_driver,设置最大线程数为15
mmap -- 将设置ProcessState内存大小,并且与Binder驱动做内存映射
/**
* vma指的是进程的虚拟内存
* 1.通过用户空间的虚拟内存大小 --- 分配一块内核的虚拟内存
* 2.分配了一块物理内存(一页 --- 4KB)这块4KB是因为还没通信,等到要用的时候,用多少分配多少
* 3.把这块物理内存分配映射到内核的虚拟内存和用户空间的虚拟内存
* 这里的buffer其实就是指向内核的虚拟内存
*/
static int binder_mmap(struct file *filp, struct vm_area_struct *vma)
{
int ret;
// 内核的虚拟内存
struct vm_struct *area;
// 通过flip获取到进行的proc信息
struct binder_proc *proc = filp->private_data;
const char *failure_string;
struct binder_buffer *buffer;
if (proc->tsk != current)
return -EINVAL;
// 判断传输的大小不能超过4M,是驱动层定义的。
// 应用层部分定义的是1M-8K,不能超过这个值
// intent传输数据的时候是通过Binder进行传输的,所以传输数据不能超过1M-8K
// intent传输数据大小,异步是二分之一的大小
if ((vma->vm_end - vma->vm_start) > SZ_4M)
vma->vm_end = vma->vm_start + SZ_4M;
binder_debug(BINDER_DEBUG_OPEN_CLOSE,
"binder_mmap: %d %lx-%lx (%ld K) vma %lx pagep %lx\n",
proc->pid, vma->vm_start, vma->vm_end,
(vma->vm_end - vma->vm_start) / SZ_1K, vma->vm_flags,
(unsigned long)pgprot_val(vma->vm_page_prot));
if (vma->vm_flags & FORBIDDEN_MMAP_FLAGS) {
ret = -EPERM;
failure_string = "bad vm_flags";
goto err_bad_arg;
}
vma->vm_flags = (vma->vm_flags | VM_DONTCOPY) & ~VM_MAYWRITE;
// 同步
mutex_lock(&binder_mmap_lock);
// 判断是否已经做过映射
if (proc->buffer) {
ret = -EBUSY;
// 如果已经做过映射,则跳到err_already_mapped位置
failure_string = "already mapped";
goto err_already_mapped;
}
// 给内核区域分配物理内存,与进程的虚拟内存大小一致的
area = get_vm_area(vma->vm_end - vma->vm_start, VM_IOREMAP);
if (area == NULL) {
ret = -ENOMEM;
failure_string = "get_vm_area";
goto err_get_vm_area_failed;
}
// 将proc->buffer指向内核虚拟内存的寻址空间
proc->buffer = area->addr;
// 偏移。进程虚拟空间地址减去内核虚拟空间地址得到一个偏移值
// 比如虚拟内存放入一个数据
// 用户空间对应的地址=内核虚拟内存地址 + 偏移值
proc->user_buffer_offset = vma->vm_start - (uintptr_t)proc->buffer;
mutex_unlock(&binder_mmap_lock);
#ifdef CONFIG_CPU_CACHE_VIPT
if (cache_is_vipt_aliasing()) {
while (CACHE_COLOUR((vma->vm_start ^ (uint32_t)proc->buffer))) {
pr_info("binder_mmap: %d %lx-%lx maps %p bad alignment\n", proc->pid, vma->vm_start, vma->vm_end, proc->buffer);
vma->vm_start += PAGE_SIZE;
}
}
#endif
// 分配内存,分配页,每一页其实就是一个vma的大小除以页数
proc->pages = kzalloc(sizeof(proc->pages[0]) * ((vma->vm_end - vma->vm_start) / PAGE_SIZE), GFP_KERNEL);
if (proc->pages == NULL) {
ret = -ENOMEM;
failure_string = "alloc page array";
goto err_alloc_pages_failed;
}
// buffer_size的大小其实就是用户空间虚拟内存的大小
proc->buffer_size = vma->vm_end - vma->vm_start;
vma->vm_ops = &binder_vm_ops;
vma->vm_private_data = proc;
// 分配物理内存,传的是0就是释放内存,传的是1就是分配内存
if (binder_update_page_range(proc, 1, proc->buffer, proc->buffer + PAGE_SIZE, vma)) {
ret = -ENOMEM;
failure_string = "alloc small buf";
goto err_alloc_small_buf_failed;
}
// 将分配了物理内存的proc->buffer赋值给buffer
buffer = proc->buffer;
INIT_LIST_HEAD(&proc->buffers);
// 把buffer加入到proc->buffers中
list_add(&buffer->entry, &proc->buffers);
// 表示这块内存可以使用了
buffer->free = 1;
// 将buffer插入到free_buffers中
// 这里的buffer其实就是内核的虚拟内存
binder_insert_free_buffer(proc, buffer);
// TODO
// 如果异步传输的时候,可以使用的内存大小为二分之一
// 异步的时候可以使用的虚拟内存大小就是同步时候的buffer大小的一半
// 这里应该是4M除以二分之一
proc->free_async_space = proc->buffer_size / 2;
barrier();
proc->files = get_files_struct(current);
proc->vma = vma;
proc->vma_vm_mm = vma->vm_mm;
/*pr_info("binder_mmap: %d %lx-%lx maps %p\n",
proc->pid, vma->vm_start, vma->vm_end, proc->buffer);*/
return 0;
err_alloc_small_buf_failed:
kfree(proc->pages);
proc->pages = NULL;
err_alloc_pages_failed:
mutex_lock(&binder_mmap_lock);
vfree(proc->buffer);
proc->buffer = NULL;
err_get_vm_area_failed:
err_already_mapped:
mutex_unlock(&binder_mmap_lock);
err_bad_arg:
pr_err("binder_mmap: %d %lx-%lx %s failed %d\n",
proc->pid, vma->vm_start, vma->vm_end, failure_string, ret);
return ret;
}
分配物理内存,传的是0就是释放内存,传的是1就是分配内存。在这里是传的1,所以是进行内存分配
/**
* 物理内存与内核的虚拟内存、用户的虚拟内存建立映射关系(mmap)
*/
static int binder_update_page_range(struct binder_proc *proc, int allocate,
void *start, void *end,
struct vm_area_struct *vma)
{
void *page_addr;
unsigned long user_page_addr;
struct page **page;
struct mm_struct *mm;
binder_debug(BINDER_DEBUG_BUFFER_ALLOC,
"%d: %s pages %p-%p\n", proc->pid,
allocate ? "allocate" : "free", start, end);
if (end <= start)
return 0;
trace_binder_update_page_range(proc, allocate, start, end);
if (vma)
mm = NULL;
else
mm = get_task_mm(proc->tsk);
if (mm) {
down_write(&mm->mmap_sem);
vma = proc->vma;
if (vma && mm != proc->vma_vm_mm) {
pr_err("%d: vma mm and task mm mismatch\n",
proc->pid);
vma = NULL;
}
}
// allocate == 0是释放内存
// allocate == 1是分配内存
if (allocate == 0)
goto free_range;
if (vma == NULL) {
pr_err("%d: binder_alloc_buf failed to map pages in userspace, no vma\n",
proc->pid);
goto err_no_vma;
}
for (page_addr = start; page_addr < end; page_addr += PAGE_SIZE) {
int ret;
page = &proc->pages[(page_addr - proc->buffer) / PAGE_SIZE];
BUG_ON(*page);
// 分配一个page页(分配的是物理空间,才4KB)一页就是4KB
*page = alloc_page(GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO);
if (*page == NULL) {
pr_err("%d: binder_alloc_buf failed for page at %p\n",
proc->pid, page_addr);
goto err_alloc_page_failed;
}
// 把物理内存映射到内核的虚拟空间
ret = map_kernel_range_noflush((unsigned long)page_addr,
PAGE_SIZE, PAGE_KERNEL, page);
flush_cache_vmap((unsigned long)page_addr,
(unsigned long)page_addr + PAGE_SIZE);
if (ret != 1) {
pr_err("%d: binder_alloc_buf failed to map page at %p in kernel\n",
proc->pid, page_addr);
goto err_map_kernel_failed;
}
user_page_addr =
(uintptr_t)page_addr + proc->user_buffer_offset;
// 把用户空间的虚拟内存映射到物理内存
ret = vm_insert_page(vma, user_page_addr, page[0]);
if (ret) {
pr_err("%d: binder_alloc_buf failed to map page at %lx in userspace\n",
proc->pid, user_page_addr);
goto err_vm_insert_page_failed;
}
/* vm_insert_page does not seem to increment the refcount */
}
if (mm) {
up_write(&mm->mmap_sem);
mmput(mm);
}
return 0;
free_range:
for (page_addr = end - PAGE_SIZE; page_addr >= start;
page_addr -= PAGE_SIZE) {
page = &proc->pages[(page_addr - proc->buffer) / PAGE_SIZE];
if (vma)
zap_page_range(vma, (uintptr_t)page_addr +
proc->user_buffer_offset, PAGE_SIZE, NULL);
err_vm_insert_page_failed:
unmap_kernel_range((unsigned long)page_addr, PAGE_SIZE);
err_map_kernel_failed:
__free_page(*page);
*page = NULL;
err_alloc_page_failed:
;
}
err_no_vma:
if (mm) {
up_write(&mm->mmap_sem);
mmput(mm);
}
return -ENOMEM;
}
将buffer插入到free_buffers中
static void binder_insert_free_buffer(struct binder_proc *proc,
struct binder_buffer *new_buffer)
{
struct rb_node **p = &proc->free_buffers.rb_node;
struct rb_node *parent = NULL;
struct binder_buffer *buffer;
size_t buffer_size;
size_t new_buffer_size;
BUG_ON(!new_buffer->free);
new_buffer_size = binder_buffer_size(proc, new_buffer);
binder_debug(BINDER_DEBUG_BUFFER_ALLOC,
"%d: add free buffer, size %zd, at %p\n",
proc->pid, new_buffer_size, new_buffer);
while (*p) {
parent = *p;
buffer = rb_entry(parent, struct binder_buffer, rb_node);
BUG_ON(!buffer->free);
// 计算出我们可以使用的大小
buffer_size = binder_buffer_size(proc, buffer);
if (new_buffer_size < buffer_size)
p = &parent->rb_left;
else
p = &parent->rb_right;
}
rb_link_node(&new_buffer->rb_node, parent, p);
// 插入到free_buffers中
rb_insert_color(&new_buffer->rb_node, &proc->free_buffers);
}
4.kernel\drivers\staging\android\binder.c#binder_ioctl
读写操作。应用层调用native层,native层调用驱动层,触发驱动层的BINDER_WRITE_READ命令
/**
* 主要是读写操作的
*
*/
static long binder_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
{
int ret;
struct binder_proc *proc = filp->private_data;
struct binder_thread *thread;
unsigned int size = _IOC_SIZE(cmd);
void __user *ubuf = (void __user *)arg;
/*pr_info("binder_ioctl: %d:%d %x %lx\n",
proc->pid, current->pid, cmd, arg);*/
trace_binder_ioctl(cmd, arg);
// 这里是一个挂起中断,正常情况下是不会中断的
ret = wait_event_interruptible(binder_user_error_wait, binder_stop_on_user_error < 2);
if (ret)
goto err_unlocked;
binder_lock(__func__);
thread = binder_get_thread(proc);
if (thread == NULL) {
ret = -ENOMEM;
goto err;
}
switch (cmd) {
case BINDER_WRITE_READ:
// 读写命令 --- 读写操作的时候,由应用层ioctl(BINDER_WRITE_READ)调用
ret = binder_ioctl_write_read(filp, cmd, arg, thread);
if (ret)
goto err;
break;
case BINDER_SET_MAX_THREADS:
if (copy_from_user(&proc->max_threads, ubuf, sizeof(proc->max_threads))) {
ret = -EINVAL;
goto err;
}
break;
case BINDER_SET_CONTEXT_MGR:
ret = binder_ioctl_set_ctx_mgr(filp);
if (ret)
goto err;
break;
case BINDER_THREAD_EXIT:
binder_debug(BINDER_DEBUG_THREADS, "%d:%d exit\n",
proc->pid, thread->pid);
binder_free_thread(proc, thread);
thread = NULL;
break;
case BINDER_VERSION: {
struct binder_version __user *ver = ubuf;
if (size != sizeof(struct binder_version)) {
ret = -EINVAL;
goto err;
}
if (put_user(BINDER_CURRENT_PROTOCOL_VERSION,
&ver->protocol_version)) {
ret = -EINVAL;
goto err;
}
break;
}
default:
ret = -EINVAL;
goto err;
}
ret = 0;
err:
if (thread)
thread->looper &= ~BINDER_LOOPER_STATE_NEED_RETURN;
binder_unlock(__func__);
wait_event_interruptible(binder_user_error_wait, binder_stop_on_user_error < 2);
if (ret && ret != -ERESTARTSYS)
pr_info("%d:%d ioctl %x %lx returned %d\n", proc->pid, current->pid, cmd, arg, ret);
err_unlocked:
trace_binder_ioctl_done(ret);
return ret;
}
/**
* binder_ioctl
* 读写操作
*
*/
static int binder_ioctl_write_read(struct file *filp,
unsigned int cmd, unsigned long arg,
struct binder_thread *thread)
{
int ret = 0;
struct binder_proc *proc = filp->private_data;
unsigned int size = _IOC_SIZE(cmd);
void __user *ubuf = (void __user *)arg;
struct binder_write_read bwr;
if (size != sizeof(struct binder_write_read)) {
ret = -EINVAL;
goto out;
}
// 这里copy的不是有效数据,copy的是数据头。但是也是将用户空间的数据拷贝到内核空间
if (copy_from_user(&bwr, ubuf, sizeof(bwr))) {
ret = -EFAULT;
goto out;
}
binder_debug(BINDER_DEBUG_READ_WRITE,
"%d:%d write %lld at %016llx, read %lld at %016llx\n",
proc->pid, thread->pid,
(u64)bwr.write_size, (u64)bwr.write_buffer,
(u64)bwr.read_size, (u64)bwr.read_buffer);
// 判断写入数据是否有
if (bwr.write_size > 0) {
ret = binder_thread_write(proc, thread,
bwr.write_buffer,
bwr.write_size,
&bwr.write_consumed);
trace_binder_write_done(ret);
if (ret < 0) {
bwr.read_consumed = 0;
if (copy_to_user(ubuf, &bwr, sizeof(bwr)))
ret = -EFAULT;
goto out;
}
}
// 判断读的数据是否有
if (bwr.read_size > 0) {
ret = binder_thread_read(proc, thread, bwr.read_buffer,
bwr.read_size,
&bwr.read_consumed,
filp->f_flags & O_NONBLOCK);
trace_binder_read_done(ret);
if (!list_empty(&proc->todo))
wake_up_interruptible(&proc->wait);
if (ret < 0) {
if (copy_to_user(ubuf, &bwr, sizeof(bwr)))
ret = -EFAULT;
goto out;
}
}
binder_debug(BINDER_DEBUG_READ_WRITE,
"%d:%d wrote %lld of %lld, read return %lld of %lld\n",
proc->pid, thread->pid,
(u64)bwr.write_consumed, (u64)bwr.write_size,
(u64)bwr.read_consumed, (u64)bwr.read_size);
// 把内核空间的数据拷贝到用户空间
if (copy_to_user(ubuf, &bwr, sizeof(bwr))) {
ret = -EFAULT;
goto out;
}
out:
return ret;
}
网友评论