Linux pipe 源碼分析

標籤：pipe   ipc   

Linux pipe 源碼分析

     管道pipe作為Unix中曆史最悠久的IPC機制，存在各個版本的Unix中，主要用於父子進程之間的通訊（使用fork，從而子進程會獲得父進程的開啟檔案表），pipe()系統調用底層的實現就相當於一個特殊的檔案系統，每次調用的時候建立一個inode關聯著兩個file，一個用於讀，一個用於寫，從而實現資料的單向流動。

使用者層API：

 #include <unistd.h>       int pipe(int pipefd[2]);       #define _GNU_SOURCE             /* See feature_test_macros(7) */       #include <unistd.h>       int pipe2(int pipefd[2], int flags);

核心源碼路徑如下：

// sys_pipe(.......)SYSCALL_DEFINE1(pipe, int __user *, fildes){     return sys_pipe2(fildes, 0);}SYSCALL_DEFINE2(pipe2, int __user *, fildes, int, flags){     struct file *files[2];     int fd[2];     int error;     // 核心是do_pipe     error = __do_pipe_flags(fd, files, flags);     if (!error) {          // 一切準備就緒後 把剛才和管道關聯的2個fd拷貝到使用者空間          if (unlikely(copy_to_user(fildes, fd, sizeof(fd)))) {               fput(files[0]);               fput(files[1]);               put_unused_fd(fd[0]);               put_unused_fd(fd[1]);               error = -EFAULT;          } else {               // 把fd和file的映射關係更新到該進程的檔案描述表中fdtable               fd_install(fd[0], files[0]);               fd_install(fd[1], files[1]);          }     }     return error;}static int __do_pipe_flags(int *fd, struct file **files, int flags){     int error;     int fdw, fdr;     if (flags & ~(O_CLOEXEC | O_NONBLOCK | O_DIRECT))          return -EINVAL;     // 為該管道建立倆struct file     error = create_pipe_files(files, flags);     if (error)          return error;     // 獲得兩個能用的檔案描述符     error = get_unused_fd_flags(flags);     if (error < 0)          goto err_read_pipe;     fdr = error;     error = get_unused_fd_flags(flags);     if (error < 0)          goto err_fdr;     fdw = error;     audit_fd_pair(fdr, fdw);     fd[0] = fdr;     fd[1] = fdw;     return 0;err_fdr:     put_unused_fd(fdr);err_read_pipe:     fput(files[0]);     fput(files[1]);     return error;}/** 為管道建立兩個file執行個體*/int create_pipe_files(struct file **res, int flags){     int err;     // 為pipe建立一個inode並做一定的初始化     struct inode *inode = get_pipe_inode();     struct file *f;     struct path path;     static struct qstr name = { .name = "" }; // quick string ??     if (!inode)          return -ENFILE;     err = -ENOMEM;     // 分配一個directory entry     path.dentry = d_alloc_pseudo(pipe_mnt->mnt_sb, &name);     if (!path.dentry)          goto err_inode;     path.mnt = mntget(pipe_mnt);  // 引用計數加1     d_instantiate(path.dentry, inode);     err = -ENFILE;     f = alloc_file(&path, FMODE_WRITE, &pipefifo_fops);     if (IS_ERR(f))          goto err_dentry;     f->f_flags = O_WRONLY | (flags & (O_NONBLOCK | O_DIRECT));     f->private_data = inode->i_pipe;     // 所以你會明白 fd[0]是讀 fd[1]是寫     res[0] = alloc_file(&path, FMODE_READ, &pipefifo_fops);     if (IS_ERR(res[0]))          goto err_file;     path_get(&path);     res[0]->private_data = inode->i_pipe;     res[0]->f_flags = O_RDONLY | (flags & O_NONBLOCK);     res[1] = f;     return 0;err_file:     put_filp(f);err_dentry:     free_pipe_info(inode->i_pipe);     path_put(&path);     return err;err_inode:     free_pipe_info(inode->i_pipe);     iput(inode);     return err;}static struct inode * get_pipe_inode(void){     struct inode *inode = new_inode_pseudo(pipe_mnt->mnt_sb);     struct pipe_inode_info *pipe;     if (!inode)          goto fail_inode;     // 分配一個inode號     inode->i_ino = get_next_ino();     // 分配一個pipe的核心級對象     pipe = alloc_pipe_info();     if (!pipe)          goto fail_iput;     inode->i_pipe = pipe;     pipe->files = 2;     pipe->readers = pipe->writers = 1;     inode->i_fop = &pipefifo_fops;     /*     * Mark the inode dirty from the very beginning,     * that way it will never be moved to the dirty     * list because "mark_inode_dirty()" will think     * that it already _is_ on the dirty list.     */     inode->i_state = I_DIRTY;     inode->i_mode = S_IFIFO | S_IRUSR | S_IWUSR;     inode->i_uid = current_fsuid();     inode->i_gid = current_fsgid();     inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;     return inode;fail_iput:     iput(inode);fail_inode:     return NULL;}// 針對pipe的檔案操作執行個體const struct file_operations pipefifo_fops = {     .open          = fifo_open,     .llseek          = no_llseek,     .read          = new_sync_read,     .read_iter     = pipe_read,     .write          = new_sync_write,     .write_iter     = pipe_write,     .poll          = pipe_poll,     .unlocked_ioctl     = pipe_ioctl,     .release     = pipe_release,     .fasync          = pipe_fasync,};

整體的邏輯圖可以這樣：

TODO：具體讀寫的實現細節new_sync_read/write()有待分析。

參考：（1）Linux kernel 3.18 source code （2）Linux man page（3）Linux核心源碼情景分析

Linux pipe 源碼分析