Android進程間通信機制Binder的總體架構,它由Client, Server, Service Manager和驅動程序Binder四個組件構成。
Service Manager是整個Binder機制的守護進程,用來管理開發這創建的各種Server,並向Client提供查詢Server遠程接口的功能。
既然Service Manager組件是用來管理Server並且向Client提供查詢Server遠程接口的功能,那麼,Service Manager就必然要和Server以及Client進行通信了。Service Manager,Server和Client三者分別運行在獨立的進程中,他們之間的通信業屬於進程間通信,而且採用的是Binder機制進行進程間通信,因此,Service Manager在充當Binder機制的守護進程的同時,也在充當Server角色,Service Manager是一種特殊的Sever。
下面圍繞Service Manager如何成爲整個Binder機制的守護進程這條主線來一步一步分析相關源碼,包括從用戶空間到內核空間的相關源代碼-----希望讀者在閱讀下面的內容之前,先閱讀一下參考資料Android深入淺出之Binder機制和Android Binder設計與實現,熟悉相關概念和數據結構,這有助於理解下面要分析的源代碼。
Service Manager在用戶空間的源代碼位於frameworks/base/cmds/servicemanager目錄下,主要是由binder.h、binder.c和service_manager.c三個文件組成。Service Manager的入口位於service_manager.c文件中的main函數:
- int main(int argc, char **argv)
- {
- struct binder_state *bs;
- void *svcmgr = BINDER_SERVICE_MANAGER;
- bs = binder_open(128*1024);
- if (binder_become_context_manager(bs)) {
- LOGE("cannot become context manager (%s)\n", strerror(errno));
- return -1;
- }
- svcmgr_handle = svcmgr;
- binder_loop(bs, svcmgr_handler);
- return 0;
- }
struct binder_state定義在frameworks/base/cmds/servicemanager/binder.c文件中:
- struct binder_state
- {
- int fd;
- void *mapped;
- unsigned mapsize;
- };
宏BINDER_SERVICE_MANAGER定義frameworks/base/cmds/servicemanager/binder.h文件中:
- /* the one magic object */
- #define BINDER_SERVICE_MANAGER ((void*) 0)
函數首先是執行打開Binder設備文件的操作binder_open,這個函數位於frameworks/base/cmds/servicemanager/binder.c文件中:
- struct binder_state *binder_open(unsigned mapsize)
- {
- struct binder_state *bs;
- bs = malloc(sizeof(*bs));
- if (!bs) {
- errno = ENOMEM;
- return 0;
- }
- bs->fd = open("/dev/binder", O_RDWR);
- if (bs->fd < 0) {
- fprintf(stderr,"binder: cannot open device (%s)\n",
- strerror(errno));
- goto fail_open;
- }
- bs->mapsize = mapsize;
- bs->mapped = mmap(NULL, mapsize, PROT_READ, MAP_PRIVATE, bs->fd, 0);
- if (bs->mapped == MAP_FAILED) {
- fprintf(stderr,"binder: cannot map device (%s)\n",
- strerror(errno));
- goto fail_map;
- }
- /* TODO: check version */
- return bs;
- fail_map:
- close(bs->fd);
- fail_open:
- free(bs);
- return 0;
- }
- static struct file_operations binder_fops = {
- .owner = THIS_MODULE,
- .poll = binder_poll,
- .unlocked_ioctl = binder_ioctl,
- .mmap = binder_mmap,
- .open = binder_open,
- .flush = binder_flush,
- .release = binder_release,
- };
- static struct miscdevice binder_miscdev = {
- .minor = MISC_DYNAMIC_MINOR,
- .name = "binder",
- .fops = &binder_fops
- };
- static int __init binder_init(void)
- {
- int ret;
- binder_proc_dir_entry_root = proc_mkdir("binder", NULL);
- if (binder_proc_dir_entry_root)
- binder_proc_dir_entry_proc = proc_mkdir("proc", binder_proc_dir_entry_root);
- ret = misc_register(&binder_miscdev);
- if (binder_proc_dir_entry_root) {
- create_proc_read_entry("state", S_IRUGO, binder_proc_dir_entry_root, binder_read_proc_state, NULL);
- create_proc_read_entry("stats", S_IRUGO, binder_proc_dir_entry_root, binder_read_proc_stats, NULL);
- create_proc_read_entry("transactions", S_IRUGO, binder_proc_dir_entry_root, binder_read_proc_transactions, NULL);
- create_proc_read_entry("transaction_log", S_IRUGO, binder_proc_dir_entry_root, binder_read_proc_transaction_log, &binder_transaction_log);
- create_proc_read_entry("failed_transaction_log", S_IRUGO, binder_proc_dir_entry_root, binder_read_proc_transaction_log, &binder_transaction_log_failed);
- }
- return ret;
- }
- device_initcall(binder_init);
創建設備文件的地方在misc_register函數裏面,關於misc設備的註冊,我們在Android日誌系統驅動程序Logger源代碼分析一文中有提到,有興趣的讀取不訪去了解一下。其餘的邏輯主要是在/proc目錄創建各種Binder相關的文件,供用戶訪問。從設備文件的操作方法binder_fops可以看出,前面的binder_open函數執行語句:
- bs->fd = open("/dev/binder", O_RDWR);
就進入到Binder驅動程序的binder_open函數了:
- static int binder_open(struct inode *nodp, struct file *filp)
- {
- struct binder_proc *proc;
- if (binder_debug_mask & BINDER_DEBUG_OPEN_CLOSE)
- printk(KERN_INFO "binder_open: %d:%d\n", current->group_leader->pid, current->pid);
- proc = kzalloc(sizeof(*proc), GFP_KERNEL);
- if (proc == NULL)
- return -ENOMEM;
- get_task_struct(current);
- proc->tsk = current;
- INIT_LIST_HEAD(&proc->todo);
- init_waitqueue_head(&proc->wait);
- proc->default_priority = task_nice(current);
- mutex_lock(&binder_lock);
- binder_stats.obj_created[BINDER_STAT_PROC]++;
- hlist_add_head(&proc->proc_node, &binder_procs);
- proc->pid = current->group_leader->pid;
- INIT_LIST_HEAD(&proc->delivered_death);
- filp->private_data = proc;
- mutex_unlock(&binder_lock);
- if (binder_proc_dir_entry_proc) {
- char strbuf[11];
- snprintf(strbuf, sizeof(strbuf), "%u", proc->pid);
- remove_proc_entry(strbuf, binder_proc_dir_entry_proc);
- create_proc_read_entry(strbuf, S_IRUGO, binder_proc_dir_entry_proc, binder_read_proc_proc, proc);
- }
- return 0;
- }
- static HLIST_HEAD(binder_procs);
- struct binder_proc {
- struct hlist_node proc_node;
- struct rb_root threads;
- struct rb_root nodes;
- struct rb_root refs_by_desc;
- struct rb_root refs_by_node;
- int pid;
- struct vm_area_struct *vma;
- struct task_struct *tsk;
- struct files_struct *files;
- struct hlist_node deferred_work_node;
- int deferred_work;
- void *buffer;
- ptrdiff_t user_buffer_offset;
- struct list_head buffers;
- struct rb_root free_buffers;
- struct rb_root allocated_buffers;
- size_t free_async_space;
- struct page **pages;
- size_t buffer_size;
- uint32_t buffer_free;
- struct list_head todo;
- wait_queue_head_t wait;
- struct binder_stats stats;
- struct list_head delivered_death;
- int max_threads;
- int requested_threads;
- int requested_threads_started;
- int ready_threads;
- long default_priority;
- };
這樣,打開設備文件/dev/binder的操作就完成了,接着是對打開的設備文件進行內存映射操作mmap:
- bs->mapped = mmap(NULL, mapsize, PROT_READ, MAP_PRIVATE, bs->fd, 0);
對應Binder驅動程序的binder_mmap函數:
- static int binder_mmap(struct file *filp, struct vm_area_struct *vma)
- {
- int ret;
- struct vm_struct *area;
- struct binder_proc *proc = filp->private_data;
- const char *failure_string;
- struct binder_buffer *buffer;
- if ((vma->vm_end - vma->vm_start) > SZ_4M)
- vma->vm_end = vma->vm_start + SZ_4M;
- if (binder_debug_mask & BINDER_DEBUG_OPEN_CLOSE)
- printk(KERN_INFO
- "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;
- if (proc->buffer) {
- ret = -EBUSY;
- failure_string = "already mapped";
- goto err_already_mapped;
- }
- 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;
- }
- proc->buffer = area->addr;
- proc->user_buffer_offset = vma->vm_start - (uintptr_t)proc->buffer;
- #ifdef CONFIG_CPU_CACHE_VIPT
- if (cache_is_vipt_aliasing()) {
- while (CACHE_COLOUR((vma->vm_start ^ (uint32_t)proc->buffer))) {
- printk(KERN_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
- 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;
- }
- proc->buffer_size = vma->vm_end - vma->vm_start;
- vma->vm_ops = &binder_vm_ops;
- vma->vm_private_data = proc;
- 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;
- }
- buffer = proc->buffer;
- INIT_LIST_HEAD(&proc->buffers);
- list_add(&buffer->entry, &proc->buffers);
- buffer->free = 1;
- binder_insert_free_buffer(proc, buffer);
- proc->free_async_space = proc->buffer_size / 2;
- barrier();
- proc->files = get_files_struct(current);
- proc->vma = vma;
- /*printk(KERN_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:
- vfree(proc->buffer);
- proc->buffer = NULL;
- err_get_vm_area_failed:
- err_already_mapped:
- err_bad_arg:
- printk(KERN_ERR "binder_mmap: %d %lx-%lx %s failed %d\n", proc->pid, vma->vm_start, vma->vm_end, failure_string, ret);
- return ret;
- }
函數首先通過filp->private_data得到在打開設備文件/dev/binder時創建的struct binder_proc結構。內存映射信息放在vma參數中,注意,這裏的vma的數據類型是struct vm_area_struct,它表示的是一塊連續的虛擬地址空間區域,在函數變量聲明的地方,我們還看到有一個類似的結構體struct vm_struct,這個數據結構也是表示一塊連續的虛擬地址空間區域,那麼,這兩者的區別是什麼呢?在Linux中,struct vm_area_struct表示的虛擬地址是給進程使用的,而struct vm_struct表示的虛擬地址是給內核使用的,它們對應的物理頁面都可以是不連續的。struct vm_area_struct表示的地址空間範圍是0~3G,而struct vm_struct表示的地址空間範圍是(3G + 896M + 8M) ~ 4G。struct vm_struct表示的地址空間範圍爲什麼不是3G~4G呢?原來,3G ~ (3G + 896M)範圍的地址是用來映射連續的物理頁面的,這個範圍的虛擬地址和對應的實際物理地址有着簡單的對應關係,即對應0~896M的物理地址空間,而(3G + 896M) ~ (3G + 896M + 8M)是安全保護區域(例如,所有指向這8M地址空間的指針都是非法的),因此struct vm_struct使用(3G + 896M + 8M) ~ 4G地址空間來映射非連續的物理頁面。有關Linux的內存管理知識,可以參考Android學習啓動篇一文提到的《Understanding the Linux Kernel》一書中的第8章。
這裏爲什麼會同時使用進程虛擬地址空間和內核虛擬地址空間來映射同一個物理頁面呢?這就是Binder進程間通信機制的精髓所在了,同一個物理頁面,一方映射到進程虛擬地址空間,一方面映射到內核虛擬地址空間,這樣,進程和內核之間就可以減少一次內存拷貝了,提到了進程間通信效率。舉個例子如,Client要將一塊內存數據傳遞給Server,一般的做法是,Client將這塊數據從它的進程空間拷貝到內核空間中,然後內核再將這個數據從內核空間拷貝到Server的進程空間,這樣,Server就可以訪問這個數據了。但是在這種方法中,執行了兩次內存拷貝操作,而採用我們上面提到的方法,只需要把Client進程空間的數據拷貝一次到內核空間,然後Server與內核共享這個數據就可以了,整個過程只需要執行一次內存拷貝,提高了效率。
binder_mmap的原理講完了,這個函數的邏輯就好理解了。不過,這裏還是先要解釋一下struct binder_proc結構體的幾個成員變量。buffer成員變量是一個void*指針,它表示要映射的物理內存在內核空間中的起始位置;buffer_size成員變量是一個size_t類型的變量,表示要映射的內存的大小;pages成員變量是一個struct page*類型的數組,struct page是用來描述物理頁面的數據結構;user_buffer_offset成員變量是一個ptrdiff_t類型的變量,它表示的是內核使用的虛擬地址與進程使用的虛擬地址之間的差值,即如果某個物理頁面在內核空間中對應的虛擬地址是addr的話,那麼這個物理頁面在進程空間對應的虛擬地址就爲addr + user_buffer_offset。
再解釋一下Binder驅動程序管理這個內存映射地址空間的方法,即是如何管理buffer ~ (buffer + buffer_size)這段地址空間的,這個地址空間被劃分爲一段一段來管理,每一段是結構體struct binder_buffer來描述:
- struct binder_buffer {
- struct list_head entry; /* free and allocated entries by addesss */
- struct rb_node rb_node; /* free entry by size or allocated entry */
- /* by address */
- unsigned free : 1;
- unsigned allow_user_free : 1;
- unsigned async_transaction : 1;
- unsigned debug_id : 29;
- struct binder_transaction *transaction;
- struct binder_node *target_node;
- size_t data_size;
- size_t offsets_size;
- uint8_t data[0];
- };
終於可以回到binder_mmap這個函數來了,首先是對參數作一些健康體檢(sanity check),例如,要映射的內存大小不能超過SIZE_4M,即4M,回到service_manager.c中的main 函數,這裏傳進來的值是128 * 1024個字節,即128K,這個檢查沒有問題。通過健康體檢後,調用get_vm_area函數獲得一個空閒的vm_struct區間,並初始化proc結構體的buffer、user_buffer_offset、pages和buffer_size和成員變量,接着調用binder_update_page_range來爲虛擬地址空間proc->buffer ~ proc->buffer + PAGE_SIZE分配一個空閒的物理頁面,同時這段地址空間使用一個binder_buffer來描述,分別插入到proc->buffers鏈表和proc->free_buffers紅黑樹中去,最後,還初始化了proc結構體的free_async_space、files和vma三個成員變量。
這裏,我們繼續進入到binder_update_page_range函數中去看一下Binder驅動程序是如何實現把一個物理頁面同時映射到內核空間和進程空間去的:
- 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 vm_struct tmp_area;
- struct page **page;
- struct mm_struct *mm;
- if (binder_debug_mask & BINDER_DEBUG_BUFFER_ALLOC)
- printk(KERN_INFO "binder: %d: %s pages %p-%p\n",
- proc->pid, allocate ? "allocate" : "free", start, end);
- if (end <= start)
- return 0;
- if (vma)
- mm = NULL;
- else
- mm = get_task_mm(proc->tsk);
- if (mm) {
- down_write(&mm->mmap_sem);
- vma = proc->vma;
- }
- if (allocate == 0)
- goto free_range;
- if (vma == NULL) {
- printk(KERN_ERR "binder: %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;
- struct page **page_array_ptr;
- page = &proc->pages[(page_addr - proc->buffer) / PAGE_SIZE];
- BUG_ON(*page);
- *page = alloc_page(GFP_KERNEL | __GFP_ZERO);
- if (*page == NULL) {
- printk(KERN_ERR "binder: %d: binder_alloc_buf failed "
- "for page at %p\n", proc->pid, page_addr);
- goto err_alloc_page_failed;
- }
- tmp_area.addr = page_addr;
- tmp_area.size = PAGE_SIZE + PAGE_SIZE /* guard page? */;
- page_array_ptr = page;
- ret = map_vm_area(&tmp_area, PAGE_KERNEL, &page_array_ptr);
- if (ret) {
- printk(KERN_ERR "binder: %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;
- ret = vm_insert_page(vma, user_page_addr, page[0]);
- if (ret) {
- printk(KERN_ERR "binder: %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;
- }
- for (page_addr = start; page_addr < end; page_addr += PAGE_SIZE) {
- int ret;
- struct page **page_array_ptr;
- page = &proc->pages[(page_addr - proc->buffer) / PAGE_SIZE];
- BUG_ON(*page);
- *page = alloc_page(GFP_KERNEL | __GFP_ZERO);
- if (*page == NULL) {
- printk(KERN_ERR "binder: %d: binder_alloc_buf failed "
- "for page at %p\n", proc->pid, page_addr);
- goto err_alloc_page_failed;
- }
- tmp_area.addr = page_addr;
- tmp_area.size = PAGE_SIZE + PAGE_SIZE /* guard page? */;
- page_array_ptr = page;
- ret = map_vm_area(&tmp_area, PAGE_KERNEL, &page_array_ptr);
- if (ret) {
- printk(KERN_ERR "binder: %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;
- ret = vm_insert_page(vma, user_page_addr, page[0]);
- if (ret) {
- printk(KERN_ERR "binder: %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 */
- }
這樣,frameworks/base/cmds/servicemanager/binder.c文件中的binder_open函數就描述完了,回到frameworks/base/cmds/servicemanager/service_manager.c文件中的main函數,下一步就是調用binder_become_context_manager來通知Binder驅動程序自己是Binder機制的上下文管理者,即守護進程。binder_become_context_manager函數位於frameworks/base/cmds/servicemanager/binder.c文件中:
- int binder_become_context_manager(struct binder_state *bs)
- {
- return ioctl(bs->fd, BINDER_SET_CONTEXT_MGR, 0);
- }
- #define BINDER_SET_CONTEXT_MGR _IOW('b', 7, int)
- 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;
- /*printk(KERN_INFO "binder_ioctl: %d:%d %x %lx\n", proc->pid, current->pid, cmd, arg);*/
- ret = wait_event_interruptible(binder_user_error_wait, binder_stop_on_user_error < 2);
- if (ret)
- return ret;
- mutex_lock(&binder_lock);
- thread = binder_get_thread(proc);
- if (thread == NULL) {
- ret = -ENOMEM;
- goto err;
- }
- switch (cmd) {
- ......
- case BINDER_SET_CONTEXT_MGR:
- if (binder_context_mgr_node != NULL) {
- printk(KERN_ERR "binder: BINDER_SET_CONTEXT_MGR already set\n");
- ret = -EBUSY;
- goto err;
- }
- if (binder_context_mgr_uid != -1) {
- if (binder_context_mgr_uid != current->cred->euid) {
- printk(KERN_ERR "binder: BINDER_SET_"
- "CONTEXT_MGR bad uid %d != %d\n",
- current->cred->euid,
- binder_context_mgr_uid);
- ret = -EPERM;
- goto err;
- }
- } else
- binder_context_mgr_uid = current->cred->euid;
- binder_context_mgr_node = binder_new_node(proc, NULL, NULL);
- if (binder_context_mgr_node == NULL) {
- ret = -ENOMEM;
- goto err;
- }
- binder_context_mgr_node->local_weak_refs++;
- binder_context_mgr_node->local_strong_refs++;
- binder_context_mgr_node->has_strong_ref = 1;
- binder_context_mgr_node->has_weak_ref = 1;
- break;
- ......
- default:
- ret = -EINVAL;
- goto err;
- }
- ret = 0;
- err:
- if (thread)
- thread->looper &= ~BINDER_LOOPER_STATE_NEED_RETURN;
- mutex_unlock(&binder_lock);
- wait_event_interruptible(binder_user_error_wait, binder_stop_on_user_error < 2);
- if (ret && ret != -ERESTARTSYS)
- printk(KERN_INFO "binder: %d:%d ioctl %x %lx returned %d\n", proc->pid, current->pid, cmd, arg, ret);
- return ret;
- }
- struct binder_thread {
- struct binder_proc *proc;
- struct rb_node rb_node;
- int pid;
- int looper;
- struct binder_transaction *transaction_stack;
- struct list_head todo;
- uint32_t return_error; /* Write failed, return error code in read buf */
- uint32_t return_error2; /* Write failed, return error code in read */
- /* buffer. Used when sending a reply to a dead process that */
- /* we are also waiting on */
- wait_queue_head_t wait;
- struct binder_stats stats;
- };
- enum {
- BINDER_LOOPER_STATE_REGISTERED = 0x01,
- BINDER_LOOPER_STATE_ENTERED = 0x02,
- BINDER_LOOPER_STATE_EXITED = 0x04,
- BINDER_LOOPER_STATE_INVALID = 0x08,
- BINDER_LOOPER_STATE_WAITING = 0x10,
- BINDER_LOOPER_STATE_NEED_RETURN = 0x20
- };
另外一個數據結構是struct binder_node,它表示一個binder實體:
- struct binder_node {
- int debug_id;
- struct binder_work work;
- union {
- struct rb_node rb_node;
- struct hlist_node dead_node;
- };
- struct binder_proc *proc;
- struct hlist_head refs;
- int internal_strong_refs;
- int local_weak_refs;
- int local_strong_refs;
- void __user *ptr;
- void __user *cookie;
- unsigned has_strong_ref : 1;
- unsigned pending_strong_ref : 1;
- unsigned has_weak_ref : 1;
- unsigned pending_weak_ref : 1;
- unsigned has_async_transaction : 1;
- unsigned accept_fds : 1;
- int min_priority : 8;
- struct list_head async_todo;
- };
現在回到binder_ioctl函數中,首先是通過filp->private_data獲得proc變量,這裏binder_mmap函數是一樣的。接着通過binder_get_thread函數獲得線程信息,我們來看一下這個函數:
- static struct binder_thread *binder_get_thread(struct binder_proc *proc)
- {
- struct binder_thread *thread = NULL;
- struct rb_node *parent = NULL;
- struct rb_node **p = &proc->threads.rb_node;
- while (*p) {
- parent = *p;
- thread = rb_entry(parent, struct binder_thread, rb_node);
- if (current->pid < thread->pid)
- p = &(*p)->rb_left;
- else if (current->pid > thread->pid)
- p = &(*p)->rb_right;
- else
- break;
- }
- if (*p == NULL) {
- thread = kzalloc(sizeof(*thread), GFP_KERNEL);
- if (thread == NULL)
- return NULL;
- binder_stats.obj_created[BINDER_STAT_THREAD]++;
- thread->proc = proc;
- thread->pid = current->pid;
- init_waitqueue_head(&thread->wait);
- INIT_LIST_HEAD(&thread->todo);
- rb_link_node(&thread->rb_node, parent, p);
- rb_insert_color(&thread->rb_node, &proc->threads);
- thread->looper |= BINDER_LOOPER_STATE_NEED_RETURN;
- thread->return_error = BR_OK;
- thread->return_error2 = BR_OK;
- }
- return thread;
- }
回到binder_ioctl函數,繼續往下面,有兩個全局變量binder_context_mgr_node和binder_context_mgr_uid,它定義如下:
- static struct binder_node *binder_context_mgr_node;
- static uid_t binder_context_mgr_uid = -1;
- static struct binder_node *
- binder_new_node(struct binder_proc *proc, void __user *ptr, void __user *cookie)
- {
- struct rb_node **p = &proc->nodes.rb_node;
- struct rb_node *parent = NULL;
- struct binder_node *node;
- while (*p) {
- parent = *p;
- node = rb_entry(parent, struct binder_node, rb_node);
- if (ptr < node->ptr)
- p = &(*p)->rb_left;
- else if (ptr > node->ptr)
- p = &(*p)->rb_right;
- else
- return NULL;
- }
- node = kzalloc(sizeof(*node), GFP_KERNEL);
- if (node == NULL)
- return NULL;
- binder_stats.obj_created[BINDER_STAT_NODE]++;
- rb_link_node(&node->rb_node, parent, p);
- rb_insert_color(&node->rb_node, &proc->nodes);
- node->debug_id = ++binder_last_id;
- node->proc = proc;
- node->ptr = ptr;
- node->cookie = cookie;
- node->work.type = BINDER_WORK_NODE;
- INIT_LIST_HEAD(&node->work.entry);
- INIT_LIST_HEAD(&node->async_todo);
- if (binder_debug_mask & BINDER_DEBUG_INTERNAL_REFS)
- printk(KERN_INFO "binder: %d:%d node %d u%p c%p created\n",
- proc->pid, current->pid, node->debug_id,
- node->ptr, node->cookie);
- return node;
- }
binder_new_node返回到binder_ioctl函數後,就把新建的binder_node指針保存在binder_context_mgr_node中了,緊接着,又初始化了binder_context_mgr_node的引用計數值。
這樣,BINDER_SET_CONTEXT_MGR命令就執行完畢了,binder_ioctl函數返回之前,執行了下面語句:
- if (thread)
- thread->looper &= ~BINDER_LOOPER_STATE_NEED_RETURN;
回憶上面執行binder_get_thread時,thread->looper = BINDER_LOOPER_STATE_NEED_RETURN,執行了這條語句後,thread->looper = 0。
回到frameworks/base/cmds/servicemanager/service_manager.c文件中的main函數,下一步就是調用binder_loop函數進入循環,等待Client來請求了。binder_loop函數定義在frameworks/base/cmds/servicemanager/binder.c文件中:
- void binder_loop(struct binder_state *bs, binder_handler func)
- {
- int res;
- struct binder_write_read bwr;
- unsigned readbuf[32];
- bwr.write_size = 0;
- bwr.write_consumed = 0;
- bwr.write_buffer = 0;
- readbuf[0] = BC_ENTER_LOOPER;
- binder_write(bs, readbuf, sizeof(unsigned));
- for (;;) {
- bwr.read_size = sizeof(readbuf);
- bwr.read_consumed = 0;
- bwr.read_buffer = (unsigned) readbuf;
- res = ioctl(bs->fd, BINDER_WRITE_READ, &bwr);
- if (res < 0) {
- LOGE("binder_loop: ioctl failed (%s)\n", strerror(errno));
- break;
- }
- res = binder_parse(bs, 0, readbuf, bwr.read_consumed, func);
- if (res == 0) {
- LOGE("binder_loop: unexpected reply?!\n");
- break;
- }
- if (res < 0) {
- LOGE("binder_loop: io error %d %s\n", res, strerror(errno));
- break;
- }
- }
- }
這裏又要介紹一下設備文件/dev/binder文件操作函數ioctl的操作碼BINDER_WRITE_READ了,首先看定義:
- #define BINDER_WRITE_READ _IOWR('b', 1, struct binder_write_read)
- struct binder_write_read {
- signed long write_size; /* bytes to write */
- signed long write_consumed; /* bytes consumed by driver */
- unsigned long write_buffer;
- signed long read_size; /* bytes to read */
- signed long read_consumed; /* bytes consumed by driver */
- unsigned long read_buffer;
- };
- struct binder_transaction_data {
- /* The first two are only used for bcTRANSACTION and brTRANSACTION,
- * identifying the target and contents of the transaction.
- */
- union {
- size_t handle; /* target descriptor of command transaction */
- void *ptr; /* target descriptor of return transaction */
- } target;
- void *cookie; /* target object cookie */
- unsigned int code; /* transaction command */
- /* General information about the transaction. */
- unsigned int flags;
- pid_t sender_pid;
- uid_t sender_euid;
- size_t data_size; /* number of bytes of data */
- size_t offsets_size; /* number of bytes of offsets */
- /* If this transaction is inline, the data immediately
- * follows here; otherwise, it ends with a pointer to
- * the data buffer.
- */
- union {
- struct {
- /* transaction data */
- const void *buffer;
- /* offsets from buffer to flat_binder_object structs */
- const void *offsets;
- } ptr;
- uint8_t buf[8];
- } data;
- };
flags成員變量表示事務標誌:
- enum transaction_flags {
- TF_ONE_WAY = 0x01, /* this is a one-way call: async, no return */
- TF_ROOT_OBJECT = 0x04, /* contents are the component's root object */
- TF_STATUS_CODE = 0x08, /* contents are a 32-bit status code */
- TF_ACCEPT_FDS = 0x10, /* allow replies with file descriptors */
- };
sender_pid和sender_euid表示發送者進程的pid和euid。
data_size表示data.buffer緩衝區的大小,offsets_size表示data.offsets緩衝區的大小。這裏需要解釋一下data成員變量,命令的真正要傳輸的數據就保存在data.buffer緩衝區中,前面的一成員變量都是一些用來描述數據的特徵的。data.buffer所表示的緩衝區數據分爲兩類,一類是普通數據,Binder驅動程序不關心,一類是Binder實體或者Binder引用,這需要Binder驅動程序介入處理。爲什麼呢?想想,如果一個進程A傳遞了一個Binder實體或Binder引用給進程B,那麼,Binder驅動程序就需要介入維護這個Binder實體或者引用的引用計數,防止B進程還在使用這個Binder實體時,A卻銷燬這個實體,這樣的話,B進程就會crash了。所以在傳輸數據時,如果數據中含有Binder實體和Binder引和,就需要告訴Binder驅動程序它們的具體位置,以便Binder驅動程序能夠去維護它們。data.offsets的作用就在這裏了,它指定在data.buffer緩衝區中,所有Binder實體或者引用的偏移位置。每一個Binder實體或者引用,通過struct flat_binder_object 來表示:
- /*
- * This is the flattened representation of a Binder object for transfer
- * between processes. The 'offsets' supplied as part of a binder transaction
- * contains offsets into the data where these structures occur. The Binder
- * driver takes care of re-writing the structure type and data as it moves
- * between processes.
- */
- struct flat_binder_object {
- /* 8 bytes for large_flat_header. */
- unsigned long type;
- unsigned long flags;
- /* 8 bytes of data. */
- union {
- void *binder; /* local object */
- signed long handle; /* remote object */
- };
- /* extra data associated with local object */
- void *cookie;
- };
- enum {
- BINDER_TYPE_BINDER = B_PACK_CHARS('s', 'b', '*', B_TYPE_LARGE),
- BINDER_TYPE_WEAK_BINDER = B_PACK_CHARS('w', 'b', '*', B_TYPE_LARGE),
- BINDER_TYPE_HANDLE = B_PACK_CHARS('s', 'h', '*', B_TYPE_LARGE),
- BINDER_TYPE_WEAK_HANDLE = B_PACK_CHARS('w', 'h', '*', B_TYPE_LARGE),
- BINDER_TYPE_FD = B_PACK_CHARS('f', 'd', '*', B_TYPE_LARGE),
- };
type和flags的具體意義可以參考Android Binder設計與實現一文。
最後,binder表示這是一個Binder實體,handle表示這是一個Binder引用,當這是一個Binder實體時,cookie纔有意義,表示附加數據,由進程自己解釋。
數據結構分析完了,回到binder_loop函數中,首先是執行BC_ENTER_LOOPER命令:
- readbuf[0] = BC_ENTER_LOOPER;
- binder_write(bs, readbuf, sizeof(unsigned));
- int binder_write(struct binder_state *bs, void *data, unsigned len)
- {
- struct binder_write_read bwr;
- int res;
- bwr.write_size = len;
- bwr.write_consumed = 0;
- bwr.write_buffer = (unsigned) data;
- bwr.read_size = 0;
- bwr.read_consumed = 0;
- bwr.read_buffer = 0;
- res = ioctl(bs->fd, BINDER_WRITE_READ, &bwr);
- if (res < 0) {
- fprintf(stderr,"binder_write: ioctl failed (%s)\n",
- strerror(errno));
- }
- return res;
- }
- 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;
- /*printk(KERN_INFO "binder_ioctl: %d:%d %x %lx\n", proc->pid, current->pid, cmd, arg);*/
- ret = wait_event_interruptible(binder_user_error_wait, binder_stop_on_user_error < 2);
- if (ret)
- return ret;
- mutex_lock(&binder_lock);
- thread = binder_get_thread(proc);
- if (thread == NULL) {
- ret = -ENOMEM;
- goto err;
- }
- switch (cmd) {
- case BINDER_WRITE_READ: {
- struct binder_write_read bwr;
- if (size != sizeof(struct binder_write_read)) {
- ret = -EINVAL;
- goto err;
- }
- if (copy_from_user(&bwr, ubuf, sizeof(bwr))) {
- ret = -EFAULT;
- goto err;
- }
- if (binder_debug_mask & BINDER_DEBUG_READ_WRITE)
- printk(KERN_INFO "binder: %d:%d write %ld at %08lx, read %ld at %08lx\n",
- proc->pid, thread->pid, bwr.write_size, bwr.write_buffer, bwr.read_size, bwr.read_buffer);
- if (bwr.write_size > 0) {
- ret = binder_thread_write(proc, thread, (void __user *)bwr.write_buffer, bwr.write_size, &bwr.write_consumed);
- if (ret < 0) {
- bwr.read_consumed = 0;
- if (copy_to_user(ubuf, &bwr, sizeof(bwr)))
- ret = -EFAULT;
- goto err;
- }
- }
- if (bwr.read_size > 0) {
- ret = binder_thread_read(proc, thread, (void __user *)bwr.read_buffer, bwr.read_size, &bwr.read_consumed, filp->f_flags & O_NONBLOCK);
- if (!list_empty(&proc->todo))
- wake_up_interruptible(&proc->wait);
- if (ret < 0) {
- if (copy_to_user(ubuf, &bwr, sizeof(bwr)))
- ret = -EFAULT;
- goto err;
- }
- }
- if (binder_debug_mask & BINDER_DEBUG_READ_WRITE)
- printk(KERN_INFO "binder: %d:%d wrote %ld of %ld, read return %ld of %ld\n",
- proc->pid, thread->pid, bwr.write_consumed, bwr.write_size, bwr.read_consumed, bwr.read_size);
- if (copy_to_user(ubuf, &bwr, sizeof(bwr))) {
- ret = -EFAULT;
- goto err;
- }
- break;
- }
- ......
- default:
- ret = -EINVAL;
- goto err;
- }
- ret = 0;
- err:
- if (thread)
- thread->looper &= ~BINDER_LOOPER_STATE_NEED_RETURN;
- mutex_unlock(&binder_lock);
- wait_event_interruptible(binder_user_error_wait, binder_stop_on_user_error < 2);
- if (ret && ret != -ERESTARTSYS)
- printk(KERN_INFO "binder: %d:%d ioctl %x %lx returned %d\n", proc->pid, current->pid, cmd, arg, ret);
- return ret;
- }
首先是通過copy_from_user(&bwr, ubuf, sizeof(bwr))語句把用戶傳遞進來的參數轉換成struct binder_write_read結構體,並保存在本地變量bwr中,這裏可以看出bwr.write_size等於4,於是進入binder_thread_write函數,這裏我們只關注BC_ENTER_LOOPER相關的代碼:
- int
- binder_thread_write(struct binder_proc *proc, struct binder_thread *thread,
- void __user *buffer, int size, signed long *consumed)
- {
- uint32_t cmd;
- void __user *ptr = buffer + *consumed;
- void __user *end = buffer + size;
- while (ptr < end && thread->return_error == BR_OK) {
- if (get_user(cmd, (uint32_t __user *)ptr))
- return -EFAULT;
- ptr += sizeof(uint32_t);
- if (_IOC_NR(cmd) < ARRAY_SIZE(binder_stats.bc)) {
- binder_stats.bc[_IOC_NR(cmd)]++;
- proc->stats.bc[_IOC_NR(cmd)]++;
- thread->stats.bc[_IOC_NR(cmd)]++;
- }
- switch (cmd) {
- ......
- case BC_ENTER_LOOPER:
- if (binder_debug_mask & BINDER_DEBUG_THREADS)
- printk(KERN_INFO "binder: %d:%d BC_ENTER_LOOPER\n",
- proc->pid, thread->pid);
- if (thread->looper & BINDER_LOOPER_STATE_REGISTERED) {
- thread->looper |= BINDER_LOOPER_STATE_INVALID;
- binder_user_error("binder: %d:%d ERROR:"
- " BC_ENTER_LOOPER called after "
- "BC_REGISTER_LOOPER\n",
- proc->pid, thread->pid);
- }
- thread->looper |= BINDER_LOOPER_STATE_ENTERED;
- break;
- ......
- default:
- printk(KERN_ERR "binder: %d:%d unknown command %d\n", proc->pid, thread->pid, cmd);
- return -EINVAL;
- }
- *consumed = ptr - buffer;
- }
- return 0;
- }
回到binder_ioctl函數,由於bwr.read_size == 0,binder_thread_read函數就不會被執行了,這樣,binder_ioctl的任務就完成了。
回到binder_loop函數,進入for循環:
- for (;;) {
- bwr.read_size = sizeof(readbuf);
- bwr.read_consumed = 0;
- bwr.read_buffer = (unsigned) readbuf;
- res = ioctl(bs->fd, BINDER_WRITE_READ, &bwr);
- if (res < 0) {
- LOGE("binder_loop: ioctl failed (%s)\n", strerror(errno));
- break;
- }
- res = binder_parse(bs, 0, readbuf, bwr.read_consumed, func);
- if (res == 0) {
- LOGE("binder_loop: unexpected reply?!\n");
- break;
- }
- if (res < 0) {
- LOGE("binder_loop: io error %d %s\n", res, strerror(errno));
- break;
- }
- }
- bwr.write_size = 0;
- bwr.write_consumed = 0;
- bwr.write_buffer = 0;
- readbuf[0] = BC_ENTER_LOOPER;
- bwr.read_size = sizeof(readbuf);
- bwr.read_consumed = 0;
- bwr.read_buffer = (unsigned) readbuf;
- 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;
- /*printk(KERN_INFO "binder_ioctl: %d:%d %x %lx\n", proc->pid, current->pid, cmd, arg);*/
- ret = wait_event_interruptible(binder_user_error_wait, binder_stop_on_user_error < 2);
- if (ret)
- return ret;
- mutex_lock(&binder_lock);
- thread = binder_get_thread(proc);
- if (thread == NULL) {
- ret = -ENOMEM;
- goto err;
- }
- switch (cmd) {
- case BINDER_WRITE_READ: {
- struct binder_write_read bwr;
- if (size != sizeof(struct binder_write_read)) {
- ret = -EINVAL;
- goto err;
- }
- if (copy_from_user(&bwr, ubuf, sizeof(bwr))) {
- ret = -EFAULT;
- goto err;
- }
- if (binder_debug_mask & BINDER_DEBUG_READ_WRITE)
- printk(KERN_INFO "binder: %d:%d write %ld at %08lx, read %ld at %08lx\n",
- proc->pid, thread->pid, bwr.write_size, bwr.write_buffer, bwr.read_size, bwr.read_buffer);
- if (bwr.write_size > 0) {
- ret = binder_thread_write(proc, thread, (void __user *)bwr.write_buffer, bwr.write_size, &bwr.write_consumed);
- if (ret < 0) {
- bwr.read_consumed = 0;
- if (copy_to_user(ubuf, &bwr, sizeof(bwr)))
- ret = -EFAULT;
- goto err;
- }
- }
- if (bwr.read_size > 0) {
- ret = binder_thread_read(proc, thread, (void __user *)bwr.read_buffer, bwr.read_size, &bwr.read_consumed, filp->f_flags & O_NONBLOCK);
- if (!list_empty(&proc->todo))
- wake_up_interruptible(&proc->wait);
- if (ret < 0) {
- if (copy_to_user(ubuf, &bwr, sizeof(bwr)))
- ret = -EFAULT;
- goto err;
- }
- }
- if (binder_debug_mask & BINDER_DEBUG_READ_WRITE)
- printk(KERN_INFO "binder: %d:%d wrote %ld of %ld, read return %ld of %ld\n",
- proc->pid, thread->pid, bwr.write_consumed, bwr.write_size, bwr.read_consumed, bwr.read_size);
- if (copy_to_user(ubuf, &bwr, sizeof(bwr))) {
- ret = -EFAULT;
- goto err;
- }
- break;
- }
- ......
- default:
- ret = -EINVAL;
- goto err;
- }
- ret = 0;
- err:
- if (thread)
- thread->looper &= ~BINDER_LOOPER_STATE_NEED_RETURN;
- mutex_unlock(&binder_lock);
- wait_event_interruptible(binder_user_error_wait, binder_stop_on_user_error < 2);
- if (ret && ret != -ERESTARTSYS)
- printk(KERN_INFO "binder: %d:%d ioctl %x %lx returned %d\n", proc->pid, current->pid, cmd, arg, ret);
- return ret;
- }
- static int
- binder_thread_read(struct binder_proc *proc, struct binder_thread *thread,
- void __user *buffer, int size, signed long *consumed, int non_block)
- {
- void __user *ptr = buffer + *consumed;
- void __user *end = buffer + size;
- int ret = 0;
- int wait_for_proc_work;
- if (*consumed == 0) {
- if (put_user(BR_NOOP, (uint32_t __user *)ptr))
- return -EFAULT;
- ptr += sizeof(uint32_t);
- }
- retry:
- wait_for_proc_work = thread->transaction_stack == NULL && list_empty(&thread->todo);
- if (thread->return_error != BR_OK && ptr < end) {
- if (thread->return_error2 != BR_OK) {
- if (put_user(thread->return_error2, (uint32_t __user *)ptr))
- return -EFAULT;
- ptr += sizeof(uint32_t);
- if (ptr == end)
- goto done;
- thread->return_error2 = BR_OK;
- }
- if (put_user(thread->return_error, (uint32_t __user *)ptr))
- return -EFAULT;
- ptr += sizeof(uint32_t);
- thread->return_error = BR_OK;
- goto done;
- }
- thread->looper |= BINDER_LOOPER_STATE_WAITING;
- if (wait_for_proc_work)
- proc->ready_threads++;
- mutex_unlock(&binder_lock);
- if (wait_for_proc_work) {
- if (!(thread->looper & (BINDER_LOOPER_STATE_REGISTERED |
- BINDER_LOOPER_STATE_ENTERED))) {
- binder_user_error("binder: %d:%d ERROR: Thread waiting "
- "for process work before calling BC_REGISTER_"
- "LOOPER or BC_ENTER_LOOPER (state %x)\n",
- proc->pid, thread->pid, thread->looper);
- wait_event_interruptible(binder_user_error_wait, binder_stop_on_user_error < 2);
- }
- binder_set_nice(proc->default_priority);
- if (non_block) {
- if (!binder_has_proc_work(proc, thread))
- ret = -EAGAIN;
- } else
- ret = wait_event_interruptible_exclusive(proc->wait, binder_has_proc_work(proc, thread));
- } else {
- if (non_block) {
- if (!binder_has_thread_work(thread))
- ret = -EAGAIN;
- } else
- ret = wait_event_interruptible(thread->wait, binder_has_thread_work(thread));
- }
- .......
- }
至此,我們就從源代碼一步一步地分析完Service Manager是如何成爲Android進程間通信(IPC)機制Binder守護進程的了。總結一下,Service Manager是成爲Android進程間通信(IPC)機制Binder守護進程的過程是這樣的:
1. 打開/dev/binder文件:open("/dev/binder", O_RDWR);
2. 建立128K內存映射:mmap(NULL, mapsize, PROT_READ, MAP_PRIVATE, bs->fd, 0);
3. 通知Binder驅動程序它是守護進程:binder_become_context_manager(bs);
4. 進入循環等待請求的到來:binder_loop(bs, svcmgr_handler);
在這個過程中,在Binder驅動程序中建立了一個struct binder_proc結構、一個struct binder_thread結構和一個struct binder_node結構,這樣,Service Manager就在Android系統的進程間通信機制Binder擔負起守護進程的職責了。