Linux中open命令实现原理以及源码分析

在阅读该篇文章的前提，最好对mknod有一定的了解，前置知识点：
Linux中mknod命令实现原理以及源码分析

open 原理

我们经常在一个进程中使用open()来获取一个文件描述符fd，然后通过该fd去进行一些write()、read()操作。
open()的原理是通过给定的文件路径/dev/hello，从而找到该文件路径所对应的inode信息，最后生成一个struct file结构体，该结构体在进程的打开文件列表中，返回的fd信息就是这个打开文件列表中的下标索引，所以说fd永远不会小于0。

open 源码分析

现在我们看一下open()的实现源码，这里说明一下，我们将打开的是一个/dev/hello的字符驱动设备文件，以这个设备文件为例进行源代码解读。

SYSCALL_DEFINE3(open, const char __user *, filename, int, flags, umode_t, mode)
{
	if (force_o_largefile())
		flags |= O_LARGEFILE;
	return do_sys_open(AT_FDCWD, filename, flags, mode);
}

从open()的系统调用来看，最后由do_sys_open()函数进行处理。

do_sys_open

long do_sys_open(int dfd, const char __user *filename, int flags, umode_t mode)
{
	struct open_how how = build_open_how(flags, mode);
	return do_sys_openat2(dfd, filename, &how);
}

do_sys_open()函数又由do_sys_openat2()函数处理

do_sys_openat2

static long do_sys_openat2(int dfd, const char __user *filename,
			   struct open_how *how)
{
	struct open_flags op;
	int fd = build_open_flags(how, &op);
	struct filename *tmp;

	if (fd)
		return fd;

	tmp = getname(filename);
	if (IS_ERR(tmp))
		return PTR_ERR(tmp);

	fd = get_unused_fd_flags(how->flags);
	if (fd >= 0) {
		struct file *f = do_filp_open(dfd, tmp, &op);
		if (IS_ERR(f)) {
			put_unused_fd(fd);
			fd = PTR_ERR(f);
		} else {
			fsnotify_open(f);
			fd_install(fd, f);
		}
	}
	putname(tmp);
	return fd;
}

do_sys_openat2()函数为主要的处理函数，该函数的主要的处理步骤：

1. fd = get_unused_fd_flags(how->flags);获取一个该进程未使用的fd
2. struct file *f = do_filp_open(dfd, tmp, &op);生成一个struct file
3. fd_install(fd, f);将fd与struct file进行绑定
4. return fd;最终将fd返回给调用者

这其中生成struct file内容的函数为do_filp_open()，因此我们需要继续对该函数分析。

do_filp_open

struct file *do_filp_open(int dfd, struct filename *pathname,
		const struct open_flags *op)
{
	struct nameidata nd;
	int flags = op->lookup_flags;
	struct file *filp;

	set_nameidata(&nd, dfd, pathname, NULL);
	filp = path_openat(&nd, op, flags | LOOKUP_RCU);
	if (unlikely(filp == ERR_PTR(-ECHILD)))
		filp = path_openat(&nd, op, flags);
	if (unlikely(filp == ERR_PTR(-ESTALE)))
		filp = path_openat(&nd, op, flags | LOOKUP_REVAL);
	restore_nameidata();
	return filp;
}

由do_filp_open()函数调用到path_openat()函数。

path_openat

static struct file *path_openat(struct nameidata *nd,
			const struct open_flags *op, unsigned flags)
{
	struct file *file;
	int error;

	file = alloc_empty_file(op->open_flag, current_cred());
	if (IS_ERR(file))
		return file;

	if (unlikely(file->f_flags & __O_TMPFILE)) {
		error = do_tmpfile(nd, flags, op, file);
	} else if (unlikely(file->f_flags & O_PATH)) {
		error = do_o_path(nd, flags, file);
	} else {
		const char *s = path_init(nd, flags);
		while (!(error = link_path_walk(s, nd)) &&
		       (s = open_last_lookups(nd, file, op)) != NULL)
			;
		if (!error)
			error = do_open(nd, file, op);
		terminate_walk(nd);
	}
	if (likely(!error)) {
		if (likely(file->f_mode & FMODE_OPENED))
			return file;
		WARN_ON(1);
		error = -EINVAL;
	}
	fput(file);
	if (error == -EOPENSTALE) {
		if (flags & LOOKUP_RCU)
			error = -ECHILD;
		else
			error = -ESTALE;
	}
	return ERR_PTR(error);
}

path_openat()该函数通过file = alloc_empty_file(op->open_flag, current_cred());为该进程生成了一个struct file，最后由do_open()函数完成剩下的打开动作。

do_open

static int do_open(struct nameidata *nd,
		   struct file *file, const struct open_flags *op)
{
	struct user_namespace *mnt_userns;
	int open_flag = op->open_flag;
	bool do_truncate;
	int acc_mode;
	int error;

	if (!(file->f_mode & (FMODE_OPENED | FMODE_CREATED))) {
		error = complete_walk(nd);
		if (error)
			return error;
	}
	if (!(file->f_mode & FMODE_CREATED))
		audit_inode(nd->name, nd->path.dentry, 0);
	mnt_userns = mnt_user_ns(nd->path.mnt);
	if (open_flag & O_CREAT) {
		if ((open_flag & O_EXCL) && !(file->f_mode & FMODE_CREATED))
			return -EEXIST;
		if (d_is_dir(nd->path.dentry))
			return -EISDIR;
		error = may_create_in_sticky(mnt_userns, nd,
					     d_backing_inode(nd->path.dentry));
		if (unlikely(error))
			return error;
	}
	if ((nd->flags & LOOKUP_DIRECTORY) && !d_can_lookup(nd->path.dentry))
		return -ENOTDIR;

	do_truncate = false;
	acc_mode = op->acc_mode;
	if (file->f_mode & FMODE_CREATED) {
		/* Don't check for write permission, don't truncate */
		open_flag &= ~O_TRUNC;
		acc_mode = 0;
	} else if (d_is_reg(nd->path.dentry) && open_flag & O_TRUNC) {
		error = mnt_want_write(nd->path.mnt);
		if (error)
			return error;
		do_truncate = true;
	}
	error = may_open(mnt_userns, &nd->path, acc_mode, open_flag);
	if (!error && !(file->f_mode & FMODE_OPENED))
		error = vfs_open(&nd->path, file);
	if (!error)
		error = ima_file_check(file, op->acc_mode);
	if (!error && do_truncate)
		error = handle_truncate(mnt_userns, file);
	if (unlikely(error > 0)) {
		WARN_ON(1);
		error = -EINVAL;
	}
	if (do_truncate)
		mnt_drop_write(nd->path.mnt);
	return error;
}

do_open()通过调用vfs_open()函数完成。

vfs_open

int vfs_open(const struct path *path, struct file *file)
{
	file->f_path = *path;
	return do_dentry_open(file, d_backing_inode(path->dentry), NULL);
}

再调用do_dentry_open()函数。

do_dentry_open

static int do_dentry_open(struct file *f,
			  struct inode *inode,
			  int (*open)(struct inode *, struct file *))
{
	static const struct file_operations empty_fops = {};
	int error;

	path_get(&f->f_path);
	f->f_inode = inode;
	f->f_mapping = inode->i_mapping;
	f->f_wb_err = filemap_sample_wb_err(f->f_mapping);
	f->f_sb_err = file_sample_sb_err(f);

	if (unlikely(f->f_flags & O_PATH)) {
		f->f_mode = FMODE_PATH | FMODE_OPENED;
		f->f_op = &empty_fops;
		return 0;
	}

	if (f->f_mode & FMODE_WRITE && !special_file(inode->i_mode)) {
		error = get_write_access(inode);
		if (unlikely(error))
			goto cleanup_file;
		error = __mnt_want_write(f->f_path.mnt);
		if (unlikely(error)) {
			put_write_access(inode);
			goto cleanup_file;
		}
		f->f_mode |= FMODE_WRITER;
	}

	/* POSIX.1-2008/SUSv4 Section XSI 2.9.7 */
	if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode))
		f->f_mode |= FMODE_ATOMIC_POS;

	f->f_op = fops_get(inode->i_fop);
	if (WARN_ON(!f->f_op)) {
		error = -ENODEV;
		goto cleanup_all;
	}

	error = security_file_open(f);
	if (error)
		goto cleanup_all;

	error = break_lease(locks_inode(f), f->f_flags);
	if (error)
		goto cleanup_all;

	/* normally all 3 are set; ->open() can clear them if needed */
	f->f_mode |= FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE;
	if (!open)
		open = f->f_op->open;
	if (open) {
		error = open(inode, f);
		if (error)
			goto cleanup_all;
	}
	f->f_mode |= FMODE_OPENED;
	if ((f->f_mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ)
		i_readcount_inc(inode);
	if ((f->f_mode & FMODE_READ) &&
	     likely(f->f_op->read || f->f_op->read_iter))
		f->f_mode |= FMODE_CAN_READ;
	if ((f->f_mode & FMODE_WRITE) &&
	     likely(f->f_op->write || f->f_op->write_iter))
		f->f_mode |= FMODE_CAN_WRITE;

	f->f_flags &= ~(O_CREAT | O_EXCL | O_NOCTTY | O_TRUNC);

	file_ra_state_init(&f->f_ra, f->f_mapping->host->i_mapping);

	/* NB: we're sure to have correct a_ops only after f_op->open */
	if (f->f_flags & O_DIRECT) {
		if (!f->f_mapping->a_ops || !f->f_mapping->a_ops->direct_IO)
			return -EINVAL;
	}

	/*
	 * XXX: Huge page cache doesn't support writing yet. Drop all page
	 * cache for this file before processing writes.
	 */
	if (f->f_mode & FMODE_WRITE) {
		/*
		 * Paired with smp_mb() in collapse_file() to ensure nr_thps
		 * is up to date and the update to i_writecount by
		 * get_write_access() is visible. Ensures subsequent insertion
		 * of THPs into the page cache will fail.
		 */
		smp_mb();
		if (filemap_nr_thps(inode->i_mapping)) {
			struct address_space *mapping = inode->i_mapping;

			filemap_invalidate_lock(inode->i_mapping);
			/*
			 * unmap_mapping_range just need to be called once
			 * here, because the private pages is not need to be
			 * unmapped mapping (e.g. data segment of dynamic
			 * shared libraries here).
			 */
			unmap_mapping_range(mapping, 0, 0, 0);
			truncate_inode_pages(mapping, 0);
			filemap_invalidate_unlock(inode->i_mapping);
		}
	}

	return 0;

cleanup_all:
	if (WARN_ON_ONCE(error > 0))
		error = -EINVAL;
	fops_put(f->f_op);
	if (f->f_mode & FMODE_WRITER) {
		put_write_access(inode);
		__mnt_drop_write(f->f_path.mnt);
	}
cleanup_file:
	path_put(&f->f_path);
	f->f_path.mnt = NULL;
	f->f_path.dentry = NULL;
	f->f_inode = NULL;
	return error;
}

do_dentry_open()函数首先对于为进程生成的struct file进行赋值，与该路径（/dev/hello）的inode进行绑定，除此之外，最终要的是对于struct file的f_op进行赋值，该f_op的赋值会导致最终访问该文件时进行的write()、read()的行为，这个是重中之重。

f->f_op = fops_get(inode->i_fop);

struct file中的f_op的是直接赋值为inode->i_fop，inode则为/dev/hello设备文件的inode，此inode->i_fop是def_chr_fops，因此此时struct file中的f_op的值为def_chr_fops。

接着往下看：

if (!open)
		open = f->f_op->open;
	if (open) {
		error = open(inode, f);
		if (error)
			goto cleanup_all;
	}

此时open = f->f_op->open，也就是open = chrdev_open，然后执行了chrdev_open()函数。

chrdev_open

static int chrdev_open(struct inode *inode, struct file *filp)
{
	const struct file_operations *fops;
	struct cdev *p;
	struct cdev *new = NULL;
	int ret = 0;

	spin_lock(&cdev_lock);
	p = inode->i_cdev;
	if (!p) {
		struct kobject *kobj;
		int idx;
		spin_unlock(&cdev_lock);
		kobj = kobj_lookup(cdev_map, inode->i_rdev, &idx);
		if (!kobj)
			return -ENXIO;
		new = container_of(kobj, struct cdev, kobj);
		spin_lock(&cdev_lock);
		/* Check i_cdev again in case somebody beat us to it while
		   we dropped the lock. */
		p = inode->i_cdev;
		if (!p) {
			inode->i_cdev = p = new;
			list_add(&inode->i_devices, &p->list);
			new = NULL;
		} else if (!cdev_get(p))
			ret = -ENXIO;
	} else if (!cdev_get(p))
		ret = -ENXIO;
	spin_unlock(&cdev_lock);
	cdev_put(new);
	if (ret)
		return ret;

	ret = -ENXIO;
	fops = fops_get(p->ops);
	if (!fops)
		goto out_cdev_put;

	replace_fops(filp, fops);
	if (filp->f_op->open) {
		ret = filp->f_op->open(inode, filp);
		if (ret)
			goto out_cdev_put;
	}

	return 0;

 out_cdev_put:
	cdev_put(p);
	return ret;
}

由上篇mknod文章可以知道，inode->i_cdev保存的是对应驱动的设备号，通过

if (!p) {
		struct kobject *kobj;
		int idx;
		spin_unlock(&cdev_lock);
		kobj = kobj_lookup(cdev_map, inode->i_rdev, &idx);
		if (!kobj)
			return -ENXIO;
		new = container_of(kobj, struct cdev, kobj);
		spin_lock(&cdev_lock);
		/* Check i_cdev again in case somebody beat us to it while
		   we dropped the lock. */
		p = inode->i_cdev;
		if (!p) {
			inode->i_cdev = p = new;
			list_add(&inode->i_devices, &p->list);
			new = NULL;
		} else if (!cdev_get(p))
			ret = -ENXIO;
}

根据设备号，可以找到对应的驱动设备，也就是inode->i_cdev，这个驱动设备是由设备驱动初始化时生成的。

fops = fops_get(p->ops);
if (!fops)
	goto out_cdev_put;
replace_fops(filp, fops);

紧接着将struct file中的f_ops替换为具体的设备的ops，通过这种方式，struct file的f_ops值就为/dev/hello设备文件所对应的设备驱动中设定的struct file_operations值，等到后面的操作write()、read()就直接调用到设备驱动的回调函数了。

4. 总结

到这里对于Linux中open命令实现原理以及源码分析已经结束。

通过open()系统调用打开/dev/hello字符设备，最终将生成struct file，同时将struct file的f_ops赋值为/dev/hello字符设备所对应驱动的struct file_operations。

谢谢大家浏览，本博客为博主原创，未经允许不可转载。