linux/fs/proc/root.c
Linus Torvalds 644473e9c6 Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace
Pull user namespace enhancements from Eric Biederman:
 "This is a course correction for the user namespace, so that we can
  reach an inexpensive, maintainable, and reasonably complete
  implementation.

  Highlights:
   - Config guards make it impossible to enable the user namespace and
     code that has not been converted to be user namespace safe.

   - Use of the new kuid_t type ensures the if you somehow get past the
     config guards the kernel will encounter type errors if you enable
     user namespaces and attempt to compile in code whose permission
     checks have not been updated to be user namespace safe.

   - All uids from child user namespaces are mapped into the initial
     user namespace before they are processed.  Removing the need to add
     an additional check to see if the user namespace of the compared
     uids remains the same.

   - With the user namespaces compiled out the performance is as good or
     better than it is today.

   - For most operations absolutely nothing changes performance or
     operationally with the user namespace enabled.

   - The worst case performance I could come up with was timing 1
     billion cache cold stat operations with the user namespace code
     enabled.  This went from 156s to 164s on my laptop (or 156ns to
     164ns per stat operation).

   - (uid_t)-1 and (gid_t)-1 are reserved as an internal error value.
     Most uid/gid setting system calls treat these value specially
     anyway so attempting to use -1 as a uid would likely cause
     entertaining failures in userspace.

   - If setuid is called with a uid that can not be mapped setuid fails.
     I have looked at sendmail, login, ssh and every other program I
     could think of that would call setuid and they all check for and
     handle the case where setuid fails.

   - If stat or a similar system call is called from a context in which
     we can not map a uid we lie and return overflowuid.  The LFS
     experience suggests not lying and returning an error code might be
     better, but the historical precedent with uids is different and I
     can not think of anything that would break by lying about a uid we
     can't map.

   - Capabilities are localized to the current user namespace making it
     safe to give the initial user in a user namespace all capabilities.

  My git tree covers all of the modifications needed to convert the core
  kernel and enough changes to make a system bootable to runlevel 1."

Fix up trivial conflicts due to nearby independent changes in fs/stat.c

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace: (46 commits)
  userns:  Silence silly gcc warning.
  cred: use correct cred accessor with regards to rcu read lock
  userns: Convert the move_pages, and migrate_pages permission checks to use uid_eq
  userns: Convert cgroup permission checks to use uid_eq
  userns: Convert tmpfs to use kuid and kgid where appropriate
  userns: Convert sysfs to use kgid/kuid where appropriate
  userns: Convert sysctl permission checks to use kuid and kgids.
  userns: Convert proc to use kuid/kgid where appropriate
  userns: Convert ext4 to user kuid/kgid where appropriate
  userns: Convert ext3 to use kuid/kgid where appropriate
  userns: Convert ext2 to use kuid/kgid where appropriate.
  userns: Convert devpts to use kuid/kgid where appropriate
  userns: Convert binary formats to use kuid/kgid where appropriate
  userns: Add negative depends on entries to avoid building code that is userns unsafe
  userns: signal remove unnecessary map_cred_ns
  userns: Teach inode_capable to understand inodes whose uids map to other namespaces.
  userns: Fail exec for suid and sgid binaries with ids outside our user namespace.
  userns: Convert stat to return values mapped from kuids and kgids
  userns: Convert user specfied uids and gids in chown into kuids and kgid
  userns: Use uid_eq gid_eq helpers when comparing kuids and kgids in the vfs
  ...
2012-05-23 17:42:39 -07:00

278 lines
5.6 KiB
C

/*
* linux/fs/proc/root.c
*
* Copyright (C) 1991, 1992 Linus Torvalds
*
* proc root directory handling functions
*/
#include <asm/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/module.h>
#include <linux/bitops.h>
#include <linux/mount.h>
#include <linux/pid_namespace.h>
#include <linux/parser.h>
#include "internal.h"
static int proc_test_super(struct super_block *sb, void *data)
{
return sb->s_fs_info == data;
}
static int proc_set_super(struct super_block *sb, void *data)
{
int err = set_anon_super(sb, NULL);
if (!err) {
struct pid_namespace *ns = (struct pid_namespace *)data;
sb->s_fs_info = get_pid_ns(ns);
}
return err;
}
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 = 0;
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 < 0 || option > 2) {
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;
}
int proc_remount(struct super_block *sb, int *flags, char *data)
{
struct pid_namespace *pid = sb->s_fs_info;
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)
{
int err;
struct super_block *sb;
struct pid_namespace *ns;
struct proc_inode *ei;
char *options;
if (flags & MS_KERNMOUNT) {
ns = (struct pid_namespace *)data;
options = NULL;
} else {
ns = current->nsproxy->pid_ns;
options = data;
}
sb = sget(fs_type, proc_test_super, proc_set_super, ns);
if (IS_ERR(sb))
return ERR_CAST(sb);
if (!proc_parse_options(options, ns)) {
deactivate_locked_super(sb);
return ERR_PTR(-EINVAL);
}
if (!sb->s_root) {
sb->s_flags = flags;
err = proc_fill_super(sb);
if (err) {
deactivate_locked_super(sb);
return ERR_PTR(err);
}
sb->s_flags |= MS_ACTIVE;
}
ei = PROC_I(sb->s_root->d_inode);
if (!ei->pid) {
rcu_read_lock();
ei->pid = get_pid(find_pid_ns(1, ns));
rcu_read_unlock();
}
return dget(sb->s_root);
}
static void proc_kill_sb(struct super_block *sb)
{
struct pid_namespace *ns;
ns = (struct pid_namespace *)sb->s_fs_info;
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,
};
void __init proc_root_init(void)
{
int err;
proc_init_inodecache();
err = register_filesystem(&proc_fs_type);
if (err)
return;
err = pid_ns_prepare_proc(&init_pid_ns);
if (err) {
unregister_filesystem(&proc_fs_type);
return;
}
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_mkdir("fs/nfsd", NULL); /* somewhere for the nfsd filesystem to be mounted */
#if defined(CONFIG_SUN_OPENPROMFS) || defined(CONFIG_SUN_OPENPROMFS_MODULE)
/* just give it a mountpoint */
proc_mkdir("openprom", NULL);
#endif
proc_tty_init();
#ifdef CONFIG_PROC_DEVICETREE
proc_device_tree_init();
#endif
proc_mkdir("bus", NULL);
proc_sys_init();
}
static int proc_root_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat
)
{
generic_fillattr(dentry->d_inode, stat);
stat->nlink = proc_root.nlink + nr_processes();
return 0;
}
static struct dentry *proc_root_lookup(struct inode * dir, struct dentry * dentry, struct nameidata *nd)
{
if (!proc_lookup(dir, dentry, nd)) {
return NULL;
}
return proc_pid_lookup(dir, dentry, nd);
}
static int proc_root_readdir(struct file * filp,
void * dirent, filldir_t filldir)
{
unsigned int nr = filp->f_pos;
int ret;
if (nr < FIRST_PROCESS_ENTRY) {
int error = proc_readdir(filp, dirent, filldir);
if (error <= 0)
return error;
filp->f_pos = FIRST_PROCESS_ENTRY;
}
ret = proc_pid_readdir(filp, dirent, filldir);
return ret;
}
/*
* 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,
.readdir = proc_root_readdir,
.llseek = default_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,
.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);
}