// SPDX-License-Identifier: GPL-2.0
/*
 *  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/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 <linux/magic.h>

#include "internal.h"

enum {
	Opt_gid, Opt_hidepid, Opt_err,
};

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

static int proc_parse_options(char *options, struct pid_namespace *pid)
{
	char *p;
	substring_t args[MAX_OPT_ARGS];
	int option;

	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;
			pid->pid_gid = make_kgid(current_user_ns(), option);
			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;
			}
			pid->hide_pid = option;
			break;
		default:
			pr_err("proc: unrecognized mount option \"%s\" "
			       "or missing value\n", p);
			return 0;
		}
	}

	return 1;
}

static int proc_fill_super(struct super_block *s, void *data, int silent)
{
	struct pid_namespace *ns = get_pid_ns(s->s_fs_info);
	struct inode *root_inode;
	int ret;

	if (!proc_parse_options(data, ns))
		return -EINVAL;

	/* User space would break if executables or devices appear on proc */
	s->s_iflags |= SB_I_USERNS_VISIBLE | SB_I_NOEXEC | SB_I_NODEV;
	s->s_flags |= SB_NODIRATIME | SB_NOSUID | SB_NOEXEC;
	s->s_blocksize = 1024;
	s->s_blocksize_bits = 10;
	s->s_magic = PROC_SUPER_MAGIC;
	s->s_op = &proc_sops;
	s->s_time_gran = 1;

	/*
	 * procfs isn't actually a stacking filesystem; however, there is
	 * too much magic going on inside it to permit stacking things on
	 * top of it
	 */
	s->s_stack_depth = FILESYSTEM_MAX_STACK_DEPTH;
	
	/* procfs dentries and inodes don't require IO to create */
	s->s_shrink.seeks = 0;

	pde_get(&proc_root);
	root_inode = proc_get_inode(s, &proc_root);
	if (!root_inode) {
		pr_err("proc_fill_super: get root inode failed\n");
		return -ENOMEM;
	}

	s->s_root = d_make_root(root_inode);
	if (!s->s_root) {
		pr_err("proc_fill_super: allocate dentry failed\n");
		return -ENOMEM;
	}

	ret = proc_setup_self(s);
	if (ret) {
		return ret;
	}
	return proc_setup_thread_self(s);
}

int proc_remount(struct super_block *sb, int *flags, char *data)
{
	struct pid_namespace *pid = sb->s_fs_info;

	sync_filesystem(sb);
	return !proc_parse_options(data, pid);
}

static struct dentry *proc_mount(struct file_system_type *fs_type,
	int flags, const char *dev_name, void *data)
{
	struct pid_namespace *ns;

	if (flags & SB_KERNMOUNT) {
		ns = data;
		data = NULL;
	} else {
		ns = task_active_pid_ns(current);
	}

	return mount_ns(fs_type, flags, data, ns, ns->user_ns, proc_fill_super);
}

static void proc_kill_sb(struct super_block *sb)
{
	struct pid_namespace *ns;

	ns = (struct pid_namespace *)sb->s_fs_info;
	if (ns->proc_self)
		dput(ns->proc_self);
	if (ns->proc_thread_self)
		dput(ns->proc_thread_self);
	kill_anon_super(sb);
	put_pid_ns(ns);
}

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

	proc_net_init();
	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();

	register_filesystem(&proc_fs_type);
}

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, 
	.refcnt		= REFCOUNT_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;
	return 0;
}

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