root.c

/*
 *  linux/fs/proc/root.c
 *
 *  Copyright (C) 1991, 1992 Linus Torvalds
 *
 *  proc root directory handling functions
 */

#include <linux/uaccess.h>

#include <linux/errno.h>
#include <linux/time.h>
#include <linux/proc_fs.h>
#include <linux/stat.h>
#include <linux/init.h>
#include <linux/sched.h>
#include <linux/sched/stat.h>
#include <linux/slab.h>
#include <linux/module.h>
#include <linux/bitops.h>
#include <linux/user_namespace.h>
#include <linux/mount.h>
#include <linux/pid_namespace.h>
#include <linux/parser.h>
#include <linux/cred.h>

#include "internal.h"

enum {
	Opt_gid, Opt_hidepid, Opt_limit_pids, Opt_pidonly, Opt_err,
};

static const match_table_t tokens = {
	{Opt_hidepid, "hidepid=%u"},
	{Opt_gid, "gid=%u"},
	{Opt_limit_pids, "limit_pids=%u"},
	{Opt_pidonly, "pidonly"},
	{Opt_err, NULL},
};

/* We only parse 'limit_pids' and 'pidonly' option here */
int proc_parse_early_options(char *options, struct proc_fs_info *fs_info)
{
	char *p, *opts, *orig;
	substring_t args[MAX_OPT_ARGS];
	int option, ret;

	if (!options)
		return 0;

	opts = kstrdup(options, GFP_KERNEL);
	if (!opts)
		return -ENOMEM;

	orig = opts;

	while ((p = strsep(&opts, ",")) != NULL) {
		int token;

		if (!*p)
			continue;

		token = match_token(p, tokens, args);
		switch (token) {
		case Opt_limit_pids:
			if (match_int(&args[0], &option))
				return -EINVAL;
			ret = proc_fs_set_limit_pids(fs_info, option);
			if (ret < 0) {
				pr_err("proc: faild to parse mount option "
				       "\"%s\" \n", p);
				return ret;
			}
			proc_fs_set_newinstance(fs_info, true);
			pr_info("proc: mounting a new procfs instance ");
			break;
		case Opt_pidonly:
			proc_fs_set_pidonly(fs_info, PROC_PIDONLY_ON);
			proc_fs_set_newinstance(fs_info, true);
			pr_info("proc: mounting a new procfs instance ");
			break;
		case Opt_gid:
		case Opt_hidepid:
			break;
		default:
			pr_err("proc: unrecognized mount option \"%s\" "
			       "or missing value\n", p);
			return -EINVAL;
		}
	}

	kfree(orig);
	return 0;
}

int proc_parse_options(char *options, struct proc_fs_info *fs_info)
{
	char *p;
	substring_t args[MAX_OPT_ARGS];
	int option;
	kgid_t gid;

	if (!options)
		return 1;

	while ((p = strsep(&options, ",")) != NULL) {
		int token;
		if (!*p)
			continue;

		args[0].to = args[0].from = NULL;
		token = match_token(p, tokens, args);
		switch (token) {
		case Opt_gid:
			if (match_int(&args[0], &option))
				return 0;
			gid = make_kgid(current_user_ns(), option);
			if (!gid_valid(gid)) {
				pr_err("proc: invalid gid mount option.\n");
				return 0;
			}
			proc_fs_set_pid_gid(fs_info, gid);
			break;
		case Opt_hidepid:
			if (match_int(&args[0], &option))
				return 0;
			if (option < HIDEPID_OFF ||
			    option > HIDEPID_INVISIBLE) {
				pr_err("proc: hidepid value must be between 0 and 2.\n");
				return 0;
			}
			proc_fs_set_hide_pid(fs_info, option);
			break;
		case Opt_pidonly:
		case Opt_limit_pids:
			break;
		default:
			pr_err("proc: unrecognized mount option \"%s\" "
			       "or missing value\n", p);
			return 0;
		}
	}

	return 1;
}

int proc_remount(struct super_block *sb, int *flags, char *data)
{
	int error;
	struct proc_fs_info *fs_info = proc_sb(sb);

	sync_filesystem(sb);

	/*
	 * If this is a new instance, then parse again the proc mount
	 * options.
	 */
	if (proc_fs_newinstance(fs_info)) {
		error = proc_parse_early_options(data, fs_info);
		if (error < 0)
			return error;
	}

	return !proc_parse_options(data, fs_info);
}

static int proc_test_super(struct super_block *sb, void *data)
{
	struct proc_fs_info *p = data;
	struct proc_fs_info *fs_info = proc_sb(sb);

	if (!proc_fs_newinstance(p) && !proc_fs_newinstance(fs_info) &&
	    p->pid_ns == fs_info->pid_ns)
		return 1;

	return 0;
}

static int proc_set_super(struct super_block *sb, void *data)
{
	sb->s_fs_info = data;
	return set_anon_super(sb, NULL);
}

static struct dentry *proc_mount(struct file_system_type *fs_type,
	int flags, const char *dev_name, void *data)
{
	int error = 0;
	struct super_block *sb;
	struct pid_namespace *ns;
	struct proc_fs_info *fs_info;

	/*
	 * Don't allow mounting unless the caller has CAP_SYS_ADMIN over
	 * the namespace.
	 */
	if (!(flags & MS_KERNMOUNT) && !ns_capable(current_user_ns(), CAP_SYS_ADMIN))
		return ERR_PTR(-EPERM);

	fs_info = kzalloc(sizeof(*fs_info), GFP_NOFS);
	if (!fs_info)
		return ERR_PTR(-ENOMEM);

	/* Set it as early as possible */
	proc_fs_set_newinstance(fs_info, false);
	proc_fs_set_limit_pids(fs_info, PROC_LIMIT_PIDS_OFF);
	proc_fs_set_pidonly(fs_info, PROC_PIDONLY_OFF);

	if (flags & MS_KERNMOUNT) {
		ns = data;
		data = NULL;
	} else {
		/* Parse early mount options if not a MS_KERNMOUNT */
		error = proc_parse_early_options(data, fs_info);
		if (error < 0)
			goto error_fs_info;

		ns = task_active_pid_ns(current);
	}

	fs_info->pid_ns = ns;

	sb = sget_userns(fs_type, proc_test_super, proc_set_super, flags,
			 ns->user_ns, fs_info);
	if (IS_ERR(sb)) {
		error = PTR_ERR(sb);
		goto error_fs_info;
	}

	if (sb->s_root) {
		kfree(fs_info);
	} else {
		error = proc_fill_super(sb, data, flags & MS_SILENT ? 1 : 0);
		if (error) {
			deactivate_locked_super(sb);
			goto error;
		}

		sb->s_flags |= MS_ACTIVE;
	}

	return dget(sb->s_root);

error_fs_info:
	kfree(fs_info);
error:
	return ERR_PTR(error);
}

static void proc_kill_sb(struct super_block *sb)
{
	struct proc_fs_info *fs_info = proc_sb(sb);
	struct pid_namespace *ns = (struct pid_namespace *)fs_info->pid_ns;

	if (fs_info->proc_self)
		dput(fs_info->proc_self);
	if (fs_info->proc_thread_self)
		dput(fs_info->proc_thread_self);

	if (proc_fs_newinstance(fs_info)) {
		pidns_proc_lock(ns);
		list_del(&fs_info->pidns_entry);
		pidns_proc_unlock(ns);
	}

	kill_anon_super(sb);
	put_pid_ns(ns);
	kfree(fs_info);
}

static struct file_system_type proc_fs_type = {
	.name		= "proc",
	.mount		= proc_mount,
	.kill_sb	= proc_kill_sb,
	.fs_flags	= FS_USERNS_MOUNT,
};

void __init proc_root_init(void)
{
	int err;

	proc_init_inodecache();
	set_proc_pid_nlink();
	err = register_filesystem(&proc_fs_type);
	if (err)
		return;

	proc_self_init();
	proc_thread_self_init();
	proc_symlink("mounts", NULL, "self/mounts");

	proc_net_init();

#ifdef CONFIG_SYSVIPC
	proc_mkdir("sysvipc", NULL);
#endif
	proc_mkdir("fs", NULL);
	proc_mkdir("driver", NULL);
	proc_create_mount_point("fs/nfsd"); /* somewhere for the nfsd filesystem to be mounted */
#if defined(CONFIG_SUN_OPENPROMFS) || defined(CONFIG_SUN_OPENPROMFS_MODULE)
	/* just give it a mountpoint */
	proc_create_mount_point("openprom");
#endif
	proc_tty_init();
	proc_mkdir("bus", NULL);
	proc_sys_init();
}

static int proc_root_getattr(const struct path *path, struct kstat *stat,
			     u32 request_mask, unsigned int query_flags)
{
	generic_fillattr(d_inode(path->dentry), stat);
	stat->nlink = proc_root.nlink + nr_processes();
	return 0;
}

static struct dentry *proc_root_lookup(struct inode * dir, struct dentry * dentry, unsigned int flags)
{
	if (!proc_pid_lookup(dir, dentry, flags))
		return NULL;
	
	return proc_lookup(dir, dentry, flags);
}

static int proc_root_readdir(struct file *file, struct dir_context *ctx)
{
	if (ctx->pos < FIRST_PROCESS_ENTRY) {
		int error = proc_readdir(file, ctx);
		if (unlikely(error <= 0))
			return error;
		ctx->pos = FIRST_PROCESS_ENTRY;
	}

	return proc_pid_readdir(file, ctx);
}

/*
 * The root /proc directory is special, as it has the
 * <pid> directories. Thus we don't use the generic
 * directory handling functions for that..
 */
static const struct file_operations proc_root_operations = {
	.read		 = generic_read_dir,
	.iterate_shared	 = proc_root_readdir,
	.llseek		= generic_file_llseek,
};

/*
 * proc root can do almost nothing..
 */
static const struct inode_operations proc_root_inode_operations = {
	.lookup		= proc_root_lookup,
	.getattr	= proc_root_getattr,
};

/*
 * This is the root "inode" in the /proc tree..
 */
struct proc_dir_entry proc_root = {
	.low_ino	= PROC_ROOT_INO, 
	.namelen	= 5, 
	.mode		= S_IFDIR | S_IRUGO | S_IXUGO, 
	.nlink		= 2, 
	.count		= ATOMIC_INIT(1),
	.proc_iops	= &proc_root_inode_operations, 
	.proc_fops	= &proc_root_operations,
	.parent		= &proc_root,
	.subdir		= RB_ROOT,
	.name		= "/proc",
};

int pid_ns_prepare_proc(struct pid_namespace *ns)
{
	struct vfsmount *mnt;

	mnt = kern_mount_data(&proc_fs_type, ns);
	if (IS_ERR(mnt))
		return PTR_ERR(mnt);

	ns->proc_mnt = mnt;
	init_rwsem(&ns->rw_procfs_mnts);
	INIT_LIST_HEAD(&ns->procfs_mounts);

	return 0;
}

void pid_ns_release_proc(struct pid_namespace *ns)
{
	kern_unmount(ns->proc_mnt);
}