base.c

linux 内核源代码

			    char __user *buffer, int buflen)
{
	struct inode * inode;
	char *tmp = (char*)__get_free_page(GFP_TEMPORARY);
	char *path;
	int len;

	if (!tmp)
		return -ENOMEM;

	inode = dentry->d_inode;
	path = d_path(dentry, mnt, tmp, PAGE_SIZE);
	len = PTR_ERR(path);
	if (IS_ERR(path))
		goto out;
	len = tmp + PAGE_SIZE - 1 - path;

	if (len > buflen)
		len = buflen;
	if (copy_to_user(buffer, path, len))
		len = -EFAULT;
 out:
	free_page((unsigned long)tmp);
	return len;
}

static int proc_pid_readlink(struct dentry * dentry, char __user * buffer, int buflen)
{
	int error = -EACCES;
	struct inode *inode = dentry->d_inode;
	struct dentry *de;
	struct vfsmount *mnt = NULL;

	/* Are we allowed to snoop on the tasks file descriptors? */
	if (!proc_fd_access_allowed(inode))
		goto out;

	error = PROC_I(inode)->op.proc_get_link(inode, &de, &mnt);
	if (error)
		goto out;

	error = do_proc_readlink(de, mnt, buffer, buflen);
	dput(de);
	mntput(mnt);
out:
	return error;
}

static const struct inode_operations proc_pid_link_inode_operations = {
	.readlink	= proc_pid_readlink,
	.follow_link	= proc_pid_follow_link,
	.setattr	= proc_setattr,
};


/* building an inode */

static int task_dumpable(struct task_struct *task)
{
	int dumpable = 0;
	struct mm_struct *mm;

	task_lock(task);
	mm = task->mm;
	if (mm)
		dumpable = get_dumpable(mm);
	task_unlock(task);
	if(dumpable == 1)
		return 1;
	return 0;
}


static struct inode *proc_pid_make_inode(struct super_block * sb, struct task_struct *task)
{
	struct inode * inode;
	struct proc_inode *ei;

	/* We need a new inode */

	inode = new_inode(sb);
	if (!inode)
		goto out;

	/* Common stuff */
	ei = PROC_I(inode);
	inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
	inode->i_op = &proc_def_inode_operations;

	/*
	 * grab the reference to task.
	 */
	ei->pid = get_task_pid(task, PIDTYPE_PID);
	if (!ei->pid)
		goto out_unlock;

	inode->i_uid = 0;
	inode->i_gid = 0;
	if (task_dumpable(task)) {
		inode->i_uid = task->euid;
		inode->i_gid = task->egid;
	}
	security_task_to_inode(task, inode);

out:
	return inode;

out_unlock:
	iput(inode);
	return NULL;
}

static int pid_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
{
	struct inode *inode = dentry->d_inode;
	struct task_struct *task;
	generic_fillattr(inode, stat);

	rcu_read_lock();
	stat->uid = 0;
	stat->gid = 0;
	task = pid_task(proc_pid(inode), PIDTYPE_PID);
	if (task) {
		if ((inode->i_mode == (S_IFDIR|S_IRUGO|S_IXUGO)) ||
		    task_dumpable(task)) {
			stat->uid = task->euid;
			stat->gid = task->egid;
		}
	}
	rcu_read_unlock();
	return 0;
}

/* dentry stuff */

/*
 *	Exceptional case: normally we are not allowed to unhash a busy
 * directory. In this case, however, we can do it - no aliasing problems
 * due to the way we treat inodes.
 *
 * Rewrite the inode's ownerships here because the owning task may have
 * performed a setuid(), etc.
 *
 * Before the /proc/pid/status file was created the only way to read
 * the effective uid of a /process was to stat /proc/pid.  Reading
 * /proc/pid/status is slow enough that procps and other packages
 * kept stating /proc/pid.  To keep the rules in /proc simple I have
 * made this apply to all per process world readable and executable
 * directories.
 */
static int pid_revalidate(struct dentry *dentry, struct nameidata *nd)
{
	struct inode *inode = dentry->d_inode;
	struct task_struct *task = get_proc_task(inode);
	if (task) {
		if ((inode->i_mode == (S_IFDIR|S_IRUGO|S_IXUGO)) ||
		    task_dumpable(task)) {
			inode->i_uid = task->euid;
			inode->i_gid = task->egid;
		} else {
			inode->i_uid = 0;
			inode->i_gid = 0;
		}
		inode->i_mode &= ~(S_ISUID | S_ISGID);
		security_task_to_inode(task, inode);
		put_task_struct(task);
		return 1;
	}
	d_drop(dentry);
	return 0;
}

static int pid_delete_dentry(struct dentry * dentry)
{
	/* Is the task we represent dead?
	 * If so, then don't put the dentry on the lru list,
	 * kill it immediately.
	 */
	return !proc_pid(dentry->d_inode)->tasks[PIDTYPE_PID].first;
}

static struct dentry_operations pid_dentry_operations =
{
	.d_revalidate	= pid_revalidate,
	.d_delete	= pid_delete_dentry,
};

/* Lookups */

typedef struct dentry *instantiate_t(struct inode *, struct dentry *,
				struct task_struct *, const void *);

/*
 * Fill a directory entry.
 *
 * If possible create the dcache entry and derive our inode number and
 * file type from dcache entry.
 *
 * Since all of the proc inode numbers are dynamically generated, the inode
 * numbers do not exist until the inode is cache.  This means creating the
 * the dcache entry in readdir is necessary to keep the inode numbers
 * reported by readdir in sync with the inode numbers reported
 * by stat.
 */
static int proc_fill_cache(struct file *filp, void *dirent, filldir_t filldir,
	char *name, int len,
	instantiate_t instantiate, struct task_struct *task, const void *ptr)
{
	struct dentry *child, *dir = filp->f_path.dentry;
	struct inode *inode;
	struct qstr qname;
	ino_t ino = 0;
	unsigned type = DT_UNKNOWN;

	qname.name = name;
	qname.len  = len;
	qname.hash = full_name_hash(name, len);

	child = d_lookup(dir, &qname);
	if (!child) {
		struct dentry *new;
		new = d_alloc(dir, &qname);
		if (new) {
			child = instantiate(dir->d_inode, new, task, ptr);
			if (child)
				dput(new);
			else
				child = new;
		}
	}
	if (!child || IS_ERR(child) || !child->d_inode)
		goto end_instantiate;
	inode = child->d_inode;
	if (inode) {
		ino = inode->i_ino;
		type = inode->i_mode >> 12;
	}
	dput(child);
end_instantiate:
	if (!ino)
		ino = find_inode_number(dir, &qname);
	if (!ino)
		ino = 1;
	return filldir(dirent, name, len, filp->f_pos, ino, type);
}

static unsigned name_to_int(struct dentry *dentry)
{
	const char *name = dentry->d_name.name;
	int len = dentry->d_name.len;
	unsigned n = 0;

	if (len > 1 && *name == '0')
		goto out;
	while (len-- > 0) {
		unsigned c = *name++ - '0';
		if (c > 9)
			goto out;
		if (n >= (~0U-9)/10)
			goto out;
		n *= 10;
		n += c;
	}
	return n;
out:
	return ~0U;
}

#define PROC_FDINFO_MAX 64

static int proc_fd_info(struct inode *inode, struct dentry **dentry,
			struct vfsmount **mnt, char *info)
{
	struct task_struct *task = get_proc_task(inode);
	struct files_struct *files = NULL;
	struct file *file;
	int fd = proc_fd(inode);

	if (task) {
		files = get_files_struct(task);
		put_task_struct(task);
	}
	if (files) {
		/*
		 * We are not taking a ref to the file structure, so we must
		 * hold ->file_lock.
		 */
		spin_lock(&files->file_lock);
		file = fcheck_files(files, fd);
		if (file) {
			if (mnt)
				*mnt = mntget(file->f_path.mnt);
			if (dentry)
				*dentry = dget(file->f_path.dentry);
			if (info)
				snprintf(info, PROC_FDINFO_MAX,
					 "pos:\t%lli\n"
					 "flags:\t0%o\n",
					 (long long) file->f_pos,
					 file->f_flags);
			spin_unlock(&files->file_lock);
			put_files_struct(files);
			return 0;
		}
		spin_unlock(&files->file_lock);
		put_files_struct(files);
	}
	return -ENOENT;
}

static int proc_fd_link(struct inode *inode, struct dentry **dentry,
			struct vfsmount **mnt)
{
	return proc_fd_info(inode, dentry, mnt, NULL);
}

static int tid_fd_revalidate(struct dentry *dentry, struct nameidata *nd)
{
	struct inode *inode = dentry->d_inode;
	struct task_struct *task = get_proc_task(inode);
	int fd = proc_fd(inode);
	struct files_struct *files;

	if (task) {
		files = get_files_struct(task);
		if (files) {
			rcu_read_lock();
			if (fcheck_files(files, fd)) {
				rcu_read_unlock();
				put_files_struct(files);
				if (task_dumpable(task)) {
					inode->i_uid = task->euid;
					inode->i_gid = task->egid;
				} else {
					inode->i_uid = 0;
					inode->i_gid = 0;
				}
				inode->i_mode &= ~(S_ISUID | S_ISGID);
				security_task_to_inode(task, inode);
				put_task_struct(task);
				return 1;
			}
			rcu_read_unlock();
			put_files_struct(files);
		}
		put_task_struct(task);
	}
	d_drop(dentry);
	return 0;
}

static struct dentry_operations tid_fd_dentry_operations =
{
	.d_revalidate	= tid_fd_revalidate,
	.d_delete	= pid_delete_dentry,
};

static struct dentry *proc_fd_instantiate(struct inode *dir,
	struct dentry *dentry, struct task_struct *task, const void *ptr)
{
	unsigned fd = *(const unsigned *)ptr;
	struct file *file;
	struct files_struct *files;
 	struct inode *inode;
 	struct proc_inode *ei;
	struct dentry *error = ERR_PTR(-ENOENT);

	inode = proc_pid_make_inode(dir->i_sb, task);
	if (!inode)
		goto out;
	ei = PROC_I(inode);
	ei->fd = fd;
	files = get_files_struct(task);
	if (!files)
		goto out_iput;
	inode->i_mode = S_IFLNK;

	/*
	 * We are not taking a ref to the file structure, so we must
	 * hold ->file_lock.
	 */
	spin_lock(&files->file_lock);
	file = fcheck_files(files, fd);
	if (!file)
		goto out_unlock;
	if (file->f_mode & 1)
		inode->i_mode |= S_IRUSR | S_IXUSR;
	if (file->f_mode & 2)
		inode->i_mode |= S_IWUSR | S_IXUSR;
	spin_unlock(&files->file_lock);
	put_files_struct(files);

	inode->i_op = &proc_pid_link_inode_operations;
	inode->i_size = 64;
	ei->op.proc_get_link = proc_fd_link;
	dentry->d_op = &tid_fd_dentry_operations;
	d_add(dentry, inode);
	/* Close the race of the process dying before we return the dentry */
	if (tid_fd_revalidate(dentry, NULL))
		error = NULL;

 out:
	return error;
out_unlock:
	spin_unlock(&files->file_lock);
	put_files_struct(files);
out_iput:
	iput(inode);
	goto out;
}

static struct dentry *proc_lookupfd_common(struct inode *dir,
					   struct dentry *dentry,
					   instantiate_t instantiate)
{
	struct task_struct *task = get_proc_task(dir);
	unsigned fd = name_to_int(dentry);
	struct dentry *result = ERR_PTR(-ENOENT);

	if (!task)
		goto out_no_task;
	if (fd == ~0U)
		goto out;

	result = instantiate(dir, dentry, task, &fd);
out:
	put_task_struct(task);
out_no_task:
	return result;
}

static int proc_readfd_common(struct file * filp, void * dirent,
			      filldir_t filldir, instantiate_t instantiate)
{
	struct dentry *dentry = filp->f_path.dentry;
	struct inode *inode = dentry->d_inode;
	struct task_struct *p = get_proc_task(inode);
	unsigned int fd, ino;
	int retval;
	struct files_struct * files;
	struct fdtable *fdt;

	retval = -ENOENT;
	if (!p)
		goto out_no_task;
	retval = 0;

	fd = filp->f_pos;
	switch (fd) {
		case 0:
			if (filldir(dirent, ".", 1, 0, inode->i_ino, DT_DIR) < 0)
				goto out;
			filp->f_pos++;
		case 1:
			ino = parent_ino(dentry);
			if (filldir(dirent, "..", 2, 1, ino, DT_DIR) < 0)
				goto out;
			filp->f_pos++;
		default:
			files = get_files_struct(p);
			if (!files)
				goto out;
			rcu_read_lock();
			fdt = files_fdtable(files);
			for (fd = filp->f_pos-2;
			     fd < fdt->max_fds;
			     fd++, filp->f_pos++) {
				char name[PROC_NUMBUF];
				int len;

				if (!fcheck_files(files, fd))
					continue;
				rcu_read_unlock();

				len = snprintf(name, sizeof(name), "%d", fd);
				if (proc_fill_cache(filp, dirent, filldir,
						    name, len, instantiate,
						    p, &fd) < 0) {
					rcu_read_lock();
					break;
				}
				rcu_read_lock();
			}
			rcu_read_unlock();
			put_files_struct(files);
	}
out:
	put_task_struct(p);
out_no_task:
	return retval;
}

static struct dentry *proc_lookupfd(struct inode *dir, struct dentry *dentry,
				    struct nameidata *nd)
{
	return proc_lookupfd_common(dir, dentry, proc_fd_instantiate);
}

static int proc_readfd(struct file *filp, void *dirent, filldir_t filldir)
{
	return proc_readfd_common(filp, dirent, filldir, proc_fd_instantiate);
}

static ssize_t proc_fdinfo_read(struct file *file, char __user *buf,
				      size_t len, loff_t *ppos)
{
	char tmp[PROC_FDINFO_MAX];
	int err = proc_fd_info(file->f_path.dentry->d_inode, NULL, NULL, tmp);
	if (!err)
		err = simple_read_from_buffer(buf, len, ppos, tmp, strlen(tmp));
	return err;
}

static const struct file_operations proc_fdinfo_file_operations = {
	.open		= nonseekable_open,
	.read		= proc_fdinfo_read,
};

static const struct file_operations proc_fd_operations = {
	.read		= generic_read_dir,
	.readdir	= proc_readfd,
};

/*
 * /proc/pid/fd needs a special permission handler so that a process can still
 * access /proc/self/fd after it has executed a setuid().
 */
static int proc_fd_permission(struct inode *inode, int mask,
				struct nameidata *nd)
{
	int rv;

	rv = generic_permission(inode, mask, NULL);
	if (rv == 0)
		return 0;
	if (task_pid(current) == proc_pid(inode))
		rv = 0;
	return rv;
}

/*
 * proc directories can do almost nothing..
 */
static const struct inode_operations proc_fd_inode_operations = {
	.lookup		= proc_lookupfd,
	.permission	= proc_fd_permission,
	.setattr	= proc_setattr,
};

static struct dentry *proc_fdinfo_instantiate(struct inode *dir,
	struct dentry *dentry, struct task_struct *task, const void *ptr)
{