linux/fs/fcntl.c
Linus Torvalds 7d6beb71da idmapped-mounts-v5.12
-----BEGIN PGP SIGNATURE-----
 
 iHUEABYKAB0WIQRAhzRXHqcMeLMyaSiRxhvAZXjcogUCYCegywAKCRCRxhvAZXjc
 ouJ6AQDlf+7jCQlQdeKKoN9QDFfMzG1ooemat36EpRRTONaGuAD8D9A4sUsG4+5f
 4IU5Lj9oY4DEmF8HenbWK2ZHsesL2Qg=
 =yPaw
 -----END PGP SIGNATURE-----

Merge tag 'idmapped-mounts-v5.12' of git://git.kernel.org/pub/scm/linux/kernel/git/brauner/linux

Pull idmapped mounts from Christian Brauner:
 "This introduces idmapped mounts which has been in the making for some
  time. Simply put, different mounts can expose the same file or
  directory with different ownership. This initial implementation comes
  with ports for fat, ext4 and with Christoph's port for xfs with more
  filesystems being actively worked on by independent people and
  maintainers.

  Idmapping mounts handle a wide range of long standing use-cases. Here
  are just a few:

   - Idmapped mounts make it possible to easily share files between
     multiple users or multiple machines especially in complex
     scenarios. For example, idmapped mounts will be used in the
     implementation of portable home directories in
     systemd-homed.service(8) where they allow users to move their home
     directory to an external storage device and use it on multiple
     computers where they are assigned different uids and gids. This
     effectively makes it possible to assign random uids and gids at
     login time.

   - It is possible to share files from the host with unprivileged
     containers without having to change ownership permanently through
     chown(2).

   - It is possible to idmap a container's rootfs and without having to
     mangle every file. For example, Chromebooks use it to share the
     user's Download folder with their unprivileged containers in their
     Linux subsystem.

   - It is possible to share files between containers with
     non-overlapping idmappings.

   - Filesystem that lack a proper concept of ownership such as fat can
     use idmapped mounts to implement discretionary access (DAC)
     permission checking.

   - They allow users to efficiently changing ownership on a per-mount
     basis without having to (recursively) chown(2) all files. In
     contrast to chown (2) changing ownership of large sets of files is
     instantenous with idmapped mounts. This is especially useful when
     ownership of a whole root filesystem of a virtual machine or
     container is changed. With idmapped mounts a single syscall
     mount_setattr syscall will be sufficient to change the ownership of
     all files.

   - Idmapped mounts always take the current ownership into account as
     idmappings specify what a given uid or gid is supposed to be mapped
     to. This contrasts with the chown(2) syscall which cannot by itself
     take the current ownership of the files it changes into account. It
     simply changes the ownership to the specified uid and gid. This is
     especially problematic when recursively chown(2)ing a large set of
     files which is commong with the aforementioned portable home
     directory and container and vm scenario.

   - Idmapped mounts allow to change ownership locally, restricting it
     to specific mounts, and temporarily as the ownership changes only
     apply as long as the mount exists.

  Several userspace projects have either already put up patches and
  pull-requests for this feature or will do so should you decide to pull
  this:

   - systemd: In a wide variety of scenarios but especially right away
     in their implementation of portable home directories.

         https://systemd.io/HOME_DIRECTORY/

   - container runtimes: containerd, runC, LXD:To share data between
     host and unprivileged containers, unprivileged and privileged
     containers, etc. The pull request for idmapped mounts support in
     containerd, the default Kubernetes runtime is already up for quite
     a while now: https://github.com/containerd/containerd/pull/4734

   - The virtio-fs developers and several users have expressed interest
     in using this feature with virtual machines once virtio-fs is
     ported.

   - ChromeOS: Sharing host-directories with unprivileged containers.

  I've tightly synced with all those projects and all of those listed
  here have also expressed their need/desire for this feature on the
  mailing list. For more info on how people use this there's a bunch of
  talks about this too. Here's just two recent ones:

      https://www.cncf.io/wp-content/uploads/2020/12/Rootless-Containers-in-Gitpod.pdf
      https://fosdem.org/2021/schedule/event/containers_idmap/

  This comes with an extensive xfstests suite covering both ext4 and
  xfs:

      https://git.kernel.org/brauner/xfstests-dev/h/idmapped_mounts

  It covers truncation, creation, opening, xattrs, vfscaps, setid
  execution, setgid inheritance and more both with idmapped and
  non-idmapped mounts. It already helped to discover an unrelated xfs
  setgid inheritance bug which has since been fixed in mainline. It will
  be sent for inclusion with the xfstests project should you decide to
  merge this.

  In order to support per-mount idmappings vfsmounts are marked with
  user namespaces. The idmapping of the user namespace will be used to
  map the ids of vfs objects when they are accessed through that mount.
  By default all vfsmounts are marked with the initial user namespace.
  The initial user namespace is used to indicate that a mount is not
  idmapped. All operations behave as before and this is verified in the
  testsuite.

  Based on prior discussions we want to attach the whole user namespace
  and not just a dedicated idmapping struct. This allows us to reuse all
  the helpers that already exist for dealing with idmappings instead of
  introducing a whole new range of helpers. In addition, if we decide in
  the future that we are confident enough to enable unprivileged users
  to setup idmapped mounts the permission checking can take into account
  whether the caller is privileged in the user namespace the mount is
  currently marked with.

  The user namespace the mount will be marked with can be specified by
  passing a file descriptor refering to the user namespace as an
  argument to the new mount_setattr() syscall together with the new
  MOUNT_ATTR_IDMAP flag. The system call follows the openat2() pattern
  of extensibility.

  The following conditions must be met in order to create an idmapped
  mount:

   - The caller must currently have the CAP_SYS_ADMIN capability in the
     user namespace the underlying filesystem has been mounted in.

   - The underlying filesystem must support idmapped mounts.

   - The mount must not already be idmapped. This also implies that the
     idmapping of a mount cannot be altered once it has been idmapped.

   - The mount must be a detached/anonymous mount, i.e. it must have
     been created by calling open_tree() with the OPEN_TREE_CLONE flag
     and it must not already have been visible in the filesystem.

  The last two points guarantee easier semantics for userspace and the
  kernel and make the implementation significantly simpler.

  By default vfsmounts are marked with the initial user namespace and no
  behavioral or performance changes are observed.

  The manpage with a detailed description can be found here:

      1d7b902e28

  In order to support idmapped mounts, filesystems need to be changed
  and mark themselves with the FS_ALLOW_IDMAP flag in fs_flags. The
  patches to convert individual filesystem are not very large or
  complicated overall as can be seen from the included fat, ext4, and
  xfs ports. Patches for other filesystems are actively worked on and
  will be sent out separately. The xfstestsuite can be used to verify
  that port has been done correctly.

  The mount_setattr() syscall is motivated independent of the idmapped
  mounts patches and it's been around since July 2019. One of the most
  valuable features of the new mount api is the ability to perform
  mounts based on file descriptors only.

  Together with the lookup restrictions available in the openat2()
  RESOLVE_* flag namespace which we added in v5.6 this is the first time
  we are close to hardened and race-free (e.g. symlinks) mounting and
  path resolution.

  While userspace has started porting to the new mount api to mount
  proper filesystems and create new bind-mounts it is currently not
  possible to change mount options of an already existing bind mount in
  the new mount api since the mount_setattr() syscall is missing.

  With the addition of the mount_setattr() syscall we remove this last
  restriction and userspace can now fully port to the new mount api,
  covering every use-case the old mount api could. We also add the
  crucial ability to recursively change mount options for a whole mount
  tree, both removing and adding mount options at the same time. This
  syscall has been requested multiple times by various people and
  projects.

  There is a simple tool available at

      https://github.com/brauner/mount-idmapped

  that allows to create idmapped mounts so people can play with this
  patch series. I'll add support for the regular mount binary should you
  decide to pull this in the following weeks:

  Here's an example to a simple idmapped mount of another user's home
  directory:

	u1001@f2-vm:/$ sudo ./mount --idmap both:1000:1001:1 /home/ubuntu/ /mnt

	u1001@f2-vm:/$ ls -al /home/ubuntu/
	total 28
	drwxr-xr-x 2 ubuntu ubuntu 4096 Oct 28 22:07 .
	drwxr-xr-x 4 root   root   4096 Oct 28 04:00 ..
	-rw------- 1 ubuntu ubuntu 3154 Oct 28 22:12 .bash_history
	-rw-r--r-- 1 ubuntu ubuntu  220 Feb 25  2020 .bash_logout
	-rw-r--r-- 1 ubuntu ubuntu 3771 Feb 25  2020 .bashrc
	-rw-r--r-- 1 ubuntu ubuntu  807 Feb 25  2020 .profile
	-rw-r--r-- 1 ubuntu ubuntu    0 Oct 16 16:11 .sudo_as_admin_successful
	-rw------- 1 ubuntu ubuntu 1144 Oct 28 00:43 .viminfo

	u1001@f2-vm:/$ ls -al /mnt/
	total 28
	drwxr-xr-x  2 u1001 u1001 4096 Oct 28 22:07 .
	drwxr-xr-x 29 root  root  4096 Oct 28 22:01 ..
	-rw-------  1 u1001 u1001 3154 Oct 28 22:12 .bash_history
	-rw-r--r--  1 u1001 u1001  220 Feb 25  2020 .bash_logout
	-rw-r--r--  1 u1001 u1001 3771 Feb 25  2020 .bashrc
	-rw-r--r--  1 u1001 u1001  807 Feb 25  2020 .profile
	-rw-r--r--  1 u1001 u1001    0 Oct 16 16:11 .sudo_as_admin_successful
	-rw-------  1 u1001 u1001 1144 Oct 28 00:43 .viminfo

	u1001@f2-vm:/$ touch /mnt/my-file

	u1001@f2-vm:/$ setfacl -m u:1001:rwx /mnt/my-file

	u1001@f2-vm:/$ sudo setcap -n 1001 cap_net_raw+ep /mnt/my-file

	u1001@f2-vm:/$ ls -al /mnt/my-file
	-rw-rwxr--+ 1 u1001 u1001 0 Oct 28 22:14 /mnt/my-file

	u1001@f2-vm:/$ ls -al /home/ubuntu/my-file
	-rw-rwxr--+ 1 ubuntu ubuntu 0 Oct 28 22:14 /home/ubuntu/my-file

	u1001@f2-vm:/$ getfacl /mnt/my-file
	getfacl: Removing leading '/' from absolute path names
	# file: mnt/my-file
	# owner: u1001
	# group: u1001
	user::rw-
	user:u1001:rwx
	group::rw-
	mask::rwx
	other::r--

	u1001@f2-vm:/$ getfacl /home/ubuntu/my-file
	getfacl: Removing leading '/' from absolute path names
	# file: home/ubuntu/my-file
	# owner: ubuntu
	# group: ubuntu
	user::rw-
	user:ubuntu:rwx
	group::rw-
	mask::rwx
	other::r--"

* tag 'idmapped-mounts-v5.12' of git://git.kernel.org/pub/scm/linux/kernel/git/brauner/linux: (41 commits)
  xfs: remove the possibly unused mp variable in xfs_file_compat_ioctl
  xfs: support idmapped mounts
  ext4: support idmapped mounts
  fat: handle idmapped mounts
  tests: add mount_setattr() selftests
  fs: introduce MOUNT_ATTR_IDMAP
  fs: add mount_setattr()
  fs: add attr_flags_to_mnt_flags helper
  fs: split out functions to hold writers
  namespace: only take read lock in do_reconfigure_mnt()
  mount: make {lock,unlock}_mount_hash() static
  namespace: take lock_mount_hash() directly when changing flags
  nfs: do not export idmapped mounts
  overlayfs: do not mount on top of idmapped mounts
  ecryptfs: do not mount on top of idmapped mounts
  ima: handle idmapped mounts
  apparmor: handle idmapped mounts
  fs: make helpers idmap mount aware
  exec: handle idmapped mounts
  would_dump: handle idmapped mounts
  ...
2021-02-23 13:39:45 -08:00

1057 lines
24 KiB
C

// SPDX-License-Identifier: GPL-2.0
/*
* linux/fs/fcntl.c
*
* Copyright (C) 1991, 1992 Linus Torvalds
*/
#include <linux/syscalls.h>
#include <linux/init.h>
#include <linux/mm.h>
#include <linux/sched/task.h>
#include <linux/fs.h>
#include <linux/file.h>
#include <linux/fdtable.h>
#include <linux/capability.h>
#include <linux/dnotify.h>
#include <linux/slab.h>
#include <linux/module.h>
#include <linux/pipe_fs_i.h>
#include <linux/security.h>
#include <linux/ptrace.h>
#include <linux/signal.h>
#include <linux/rcupdate.h>
#include <linux/pid_namespace.h>
#include <linux/user_namespace.h>
#include <linux/memfd.h>
#include <linux/compat.h>
#include <linux/mount.h>
#include <linux/poll.h>
#include <asm/siginfo.h>
#include <linux/uaccess.h>
#define SETFL_MASK (O_APPEND | O_NONBLOCK | O_NDELAY | O_DIRECT | O_NOATIME)
static int setfl(int fd, struct file * filp, unsigned long arg)
{
struct inode * inode = file_inode(filp);
int error = 0;
/*
* O_APPEND cannot be cleared if the file is marked as append-only
* and the file is open for write.
*/
if (((arg ^ filp->f_flags) & O_APPEND) && IS_APPEND(inode))
return -EPERM;
/* O_NOATIME can only be set by the owner or superuser */
if ((arg & O_NOATIME) && !(filp->f_flags & O_NOATIME))
if (!inode_owner_or_capable(file_mnt_user_ns(filp), inode))
return -EPERM;
/* required for strict SunOS emulation */
if (O_NONBLOCK != O_NDELAY)
if (arg & O_NDELAY)
arg |= O_NONBLOCK;
/* Pipe packetized mode is controlled by O_DIRECT flag */
if (!S_ISFIFO(inode->i_mode) && (arg & O_DIRECT)) {
if (!filp->f_mapping || !filp->f_mapping->a_ops ||
!filp->f_mapping->a_ops->direct_IO)
return -EINVAL;
}
if (filp->f_op->check_flags)
error = filp->f_op->check_flags(arg);
if (error)
return error;
/*
* ->fasync() is responsible for setting the FASYNC bit.
*/
if (((arg ^ filp->f_flags) & FASYNC) && filp->f_op->fasync) {
error = filp->f_op->fasync(fd, filp, (arg & FASYNC) != 0);
if (error < 0)
goto out;
if (error > 0)
error = 0;
}
spin_lock(&filp->f_lock);
filp->f_flags = (arg & SETFL_MASK) | (filp->f_flags & ~SETFL_MASK);
spin_unlock(&filp->f_lock);
out:
return error;
}
static void f_modown(struct file *filp, struct pid *pid, enum pid_type type,
int force)
{
write_lock_irq(&filp->f_owner.lock);
if (force || !filp->f_owner.pid) {
put_pid(filp->f_owner.pid);
filp->f_owner.pid = get_pid(pid);
filp->f_owner.pid_type = type;
if (pid) {
const struct cred *cred = current_cred();
filp->f_owner.uid = cred->uid;
filp->f_owner.euid = cred->euid;
}
}
write_unlock_irq(&filp->f_owner.lock);
}
void __f_setown(struct file *filp, struct pid *pid, enum pid_type type,
int force)
{
security_file_set_fowner(filp);
f_modown(filp, pid, type, force);
}
EXPORT_SYMBOL(__f_setown);
int f_setown(struct file *filp, unsigned long arg, int force)
{
enum pid_type type;
struct pid *pid = NULL;
int who = arg, ret = 0;
type = PIDTYPE_TGID;
if (who < 0) {
/* avoid overflow below */
if (who == INT_MIN)
return -EINVAL;
type = PIDTYPE_PGID;
who = -who;
}
rcu_read_lock();
if (who) {
pid = find_vpid(who);
if (!pid)
ret = -ESRCH;
}
if (!ret)
__f_setown(filp, pid, type, force);
rcu_read_unlock();
return ret;
}
EXPORT_SYMBOL(f_setown);
void f_delown(struct file *filp)
{
f_modown(filp, NULL, PIDTYPE_TGID, 1);
}
pid_t f_getown(struct file *filp)
{
pid_t pid = 0;
read_lock(&filp->f_owner.lock);
rcu_read_lock();
if (pid_task(filp->f_owner.pid, filp->f_owner.pid_type)) {
pid = pid_vnr(filp->f_owner.pid);
if (filp->f_owner.pid_type == PIDTYPE_PGID)
pid = -pid;
}
rcu_read_unlock();
read_unlock(&filp->f_owner.lock);
return pid;
}
static int f_setown_ex(struct file *filp, unsigned long arg)
{
struct f_owner_ex __user *owner_p = (void __user *)arg;
struct f_owner_ex owner;
struct pid *pid;
int type;
int ret;
ret = copy_from_user(&owner, owner_p, sizeof(owner));
if (ret)
return -EFAULT;
switch (owner.type) {
case F_OWNER_TID:
type = PIDTYPE_PID;
break;
case F_OWNER_PID:
type = PIDTYPE_TGID;
break;
case F_OWNER_PGRP:
type = PIDTYPE_PGID;
break;
default:
return -EINVAL;
}
rcu_read_lock();
pid = find_vpid(owner.pid);
if (owner.pid && !pid)
ret = -ESRCH;
else
__f_setown(filp, pid, type, 1);
rcu_read_unlock();
return ret;
}
static int f_getown_ex(struct file *filp, unsigned long arg)
{
struct f_owner_ex __user *owner_p = (void __user *)arg;
struct f_owner_ex owner = {};
int ret = 0;
read_lock(&filp->f_owner.lock);
rcu_read_lock();
if (pid_task(filp->f_owner.pid, filp->f_owner.pid_type))
owner.pid = pid_vnr(filp->f_owner.pid);
rcu_read_unlock();
switch (filp->f_owner.pid_type) {
case PIDTYPE_PID:
owner.type = F_OWNER_TID;
break;
case PIDTYPE_TGID:
owner.type = F_OWNER_PID;
break;
case PIDTYPE_PGID:
owner.type = F_OWNER_PGRP;
break;
default:
WARN_ON(1);
ret = -EINVAL;
break;
}
read_unlock(&filp->f_owner.lock);
if (!ret) {
ret = copy_to_user(owner_p, &owner, sizeof(owner));
if (ret)
ret = -EFAULT;
}
return ret;
}
#ifdef CONFIG_CHECKPOINT_RESTORE
static int f_getowner_uids(struct file *filp, unsigned long arg)
{
struct user_namespace *user_ns = current_user_ns();
uid_t __user *dst = (void __user *)arg;
uid_t src[2];
int err;
read_lock(&filp->f_owner.lock);
src[0] = from_kuid(user_ns, filp->f_owner.uid);
src[1] = from_kuid(user_ns, filp->f_owner.euid);
read_unlock(&filp->f_owner.lock);
err = put_user(src[0], &dst[0]);
err |= put_user(src[1], &dst[1]);
return err;
}
#else
static int f_getowner_uids(struct file *filp, unsigned long arg)
{
return -EINVAL;
}
#endif
static bool rw_hint_valid(enum rw_hint hint)
{
switch (hint) {
case RWH_WRITE_LIFE_NOT_SET:
case RWH_WRITE_LIFE_NONE:
case RWH_WRITE_LIFE_SHORT:
case RWH_WRITE_LIFE_MEDIUM:
case RWH_WRITE_LIFE_LONG:
case RWH_WRITE_LIFE_EXTREME:
return true;
default:
return false;
}
}
static long fcntl_rw_hint(struct file *file, unsigned int cmd,
unsigned long arg)
{
struct inode *inode = file_inode(file);
u64 __user *argp = (u64 __user *)arg;
enum rw_hint hint;
u64 h;
switch (cmd) {
case F_GET_FILE_RW_HINT:
h = file_write_hint(file);
if (copy_to_user(argp, &h, sizeof(*argp)))
return -EFAULT;
return 0;
case F_SET_FILE_RW_HINT:
if (copy_from_user(&h, argp, sizeof(h)))
return -EFAULT;
hint = (enum rw_hint) h;
if (!rw_hint_valid(hint))
return -EINVAL;
spin_lock(&file->f_lock);
file->f_write_hint = hint;
spin_unlock(&file->f_lock);
return 0;
case F_GET_RW_HINT:
h = inode->i_write_hint;
if (copy_to_user(argp, &h, sizeof(*argp)))
return -EFAULT;
return 0;
case F_SET_RW_HINT:
if (copy_from_user(&h, argp, sizeof(h)))
return -EFAULT;
hint = (enum rw_hint) h;
if (!rw_hint_valid(hint))
return -EINVAL;
inode_lock(inode);
inode->i_write_hint = hint;
inode_unlock(inode);
return 0;
default:
return -EINVAL;
}
}
static long do_fcntl(int fd, unsigned int cmd, unsigned long arg,
struct file *filp)
{
void __user *argp = (void __user *)arg;
struct flock flock;
long err = -EINVAL;
switch (cmd) {
case F_DUPFD:
err = f_dupfd(arg, filp, 0);
break;
case F_DUPFD_CLOEXEC:
err = f_dupfd(arg, filp, O_CLOEXEC);
break;
case F_GETFD:
err = get_close_on_exec(fd) ? FD_CLOEXEC : 0;
break;
case F_SETFD:
err = 0;
set_close_on_exec(fd, arg & FD_CLOEXEC);
break;
case F_GETFL:
err = filp->f_flags;
break;
case F_SETFL:
err = setfl(fd, filp, arg);
break;
#if BITS_PER_LONG != 32
/* 32-bit arches must use fcntl64() */
case F_OFD_GETLK:
#endif
case F_GETLK:
if (copy_from_user(&flock, argp, sizeof(flock)))
return -EFAULT;
err = fcntl_getlk(filp, cmd, &flock);
if (!err && copy_to_user(argp, &flock, sizeof(flock)))
return -EFAULT;
break;
#if BITS_PER_LONG != 32
/* 32-bit arches must use fcntl64() */
case F_OFD_SETLK:
case F_OFD_SETLKW:
#endif
fallthrough;
case F_SETLK:
case F_SETLKW:
if (copy_from_user(&flock, argp, sizeof(flock)))
return -EFAULT;
err = fcntl_setlk(fd, filp, cmd, &flock);
break;
case F_GETOWN:
/*
* XXX If f_owner is a process group, the
* negative return value will get converted
* into an error. Oops. If we keep the
* current syscall conventions, the only way
* to fix this will be in libc.
*/
err = f_getown(filp);
force_successful_syscall_return();
break;
case F_SETOWN:
err = f_setown(filp, arg, 1);
break;
case F_GETOWN_EX:
err = f_getown_ex(filp, arg);
break;
case F_SETOWN_EX:
err = f_setown_ex(filp, arg);
break;
case F_GETOWNER_UIDS:
err = f_getowner_uids(filp, arg);
break;
case F_GETSIG:
err = filp->f_owner.signum;
break;
case F_SETSIG:
/* arg == 0 restores default behaviour. */
if (!valid_signal(arg)) {
break;
}
err = 0;
filp->f_owner.signum = arg;
break;
case F_GETLEASE:
err = fcntl_getlease(filp);
break;
case F_SETLEASE:
err = fcntl_setlease(fd, filp, arg);
break;
case F_NOTIFY:
err = fcntl_dirnotify(fd, filp, arg);
break;
case F_SETPIPE_SZ:
case F_GETPIPE_SZ:
err = pipe_fcntl(filp, cmd, arg);
break;
case F_ADD_SEALS:
case F_GET_SEALS:
err = memfd_fcntl(filp, cmd, arg);
break;
case F_GET_RW_HINT:
case F_SET_RW_HINT:
case F_GET_FILE_RW_HINT:
case F_SET_FILE_RW_HINT:
err = fcntl_rw_hint(filp, cmd, arg);
break;
default:
break;
}
return err;
}
static int check_fcntl_cmd(unsigned cmd)
{
switch (cmd) {
case F_DUPFD:
case F_DUPFD_CLOEXEC:
case F_GETFD:
case F_SETFD:
case F_GETFL:
return 1;
}
return 0;
}
SYSCALL_DEFINE3(fcntl, unsigned int, fd, unsigned int, cmd, unsigned long, arg)
{
struct fd f = fdget_raw(fd);
long err = -EBADF;
if (!f.file)
goto out;
if (unlikely(f.file->f_mode & FMODE_PATH)) {
if (!check_fcntl_cmd(cmd))
goto out1;
}
err = security_file_fcntl(f.file, cmd, arg);
if (!err)
err = do_fcntl(fd, cmd, arg, f.file);
out1:
fdput(f);
out:
return err;
}
#if BITS_PER_LONG == 32
SYSCALL_DEFINE3(fcntl64, unsigned int, fd, unsigned int, cmd,
unsigned long, arg)
{
void __user *argp = (void __user *)arg;
struct fd f = fdget_raw(fd);
struct flock64 flock;
long err = -EBADF;
if (!f.file)
goto out;
if (unlikely(f.file->f_mode & FMODE_PATH)) {
if (!check_fcntl_cmd(cmd))
goto out1;
}
err = security_file_fcntl(f.file, cmd, arg);
if (err)
goto out1;
switch (cmd) {
case F_GETLK64:
case F_OFD_GETLK:
err = -EFAULT;
if (copy_from_user(&flock, argp, sizeof(flock)))
break;
err = fcntl_getlk64(f.file, cmd, &flock);
if (!err && copy_to_user(argp, &flock, sizeof(flock)))
err = -EFAULT;
break;
case F_SETLK64:
case F_SETLKW64:
case F_OFD_SETLK:
case F_OFD_SETLKW:
err = -EFAULT;
if (copy_from_user(&flock, argp, sizeof(flock)))
break;
err = fcntl_setlk64(fd, f.file, cmd, &flock);
break;
default:
err = do_fcntl(fd, cmd, arg, f.file);
break;
}
out1:
fdput(f);
out:
return err;
}
#endif
#ifdef CONFIG_COMPAT
/* careful - don't use anywhere else */
#define copy_flock_fields(dst, src) \
(dst)->l_type = (src)->l_type; \
(dst)->l_whence = (src)->l_whence; \
(dst)->l_start = (src)->l_start; \
(dst)->l_len = (src)->l_len; \
(dst)->l_pid = (src)->l_pid;
static int get_compat_flock(struct flock *kfl, const struct compat_flock __user *ufl)
{
struct compat_flock fl;
if (copy_from_user(&fl, ufl, sizeof(struct compat_flock)))
return -EFAULT;
copy_flock_fields(kfl, &fl);
return 0;
}
static int get_compat_flock64(struct flock *kfl, const struct compat_flock64 __user *ufl)
{
struct compat_flock64 fl;
if (copy_from_user(&fl, ufl, sizeof(struct compat_flock64)))
return -EFAULT;
copy_flock_fields(kfl, &fl);
return 0;
}
static int put_compat_flock(const struct flock *kfl, struct compat_flock __user *ufl)
{
struct compat_flock fl;
memset(&fl, 0, sizeof(struct compat_flock));
copy_flock_fields(&fl, kfl);
if (copy_to_user(ufl, &fl, sizeof(struct compat_flock)))
return -EFAULT;
return 0;
}
static int put_compat_flock64(const struct flock *kfl, struct compat_flock64 __user *ufl)
{
struct compat_flock64 fl;
BUILD_BUG_ON(sizeof(kfl->l_start) > sizeof(ufl->l_start));
BUILD_BUG_ON(sizeof(kfl->l_len) > sizeof(ufl->l_len));
memset(&fl, 0, sizeof(struct compat_flock64));
copy_flock_fields(&fl, kfl);
if (copy_to_user(ufl, &fl, sizeof(struct compat_flock64)))
return -EFAULT;
return 0;
}
#undef copy_flock_fields
static unsigned int
convert_fcntl_cmd(unsigned int cmd)
{
switch (cmd) {
case F_GETLK64:
return F_GETLK;
case F_SETLK64:
return F_SETLK;
case F_SETLKW64:
return F_SETLKW;
}
return cmd;
}
/*
* GETLK was successful and we need to return the data, but it needs to fit in
* the compat structure.
* l_start shouldn't be too big, unless the original start + end is greater than
* COMPAT_OFF_T_MAX, in which case the app was asking for trouble, so we return
* -EOVERFLOW in that case. l_len could be too big, in which case we just
* truncate it, and only allow the app to see that part of the conflicting lock
* that might make sense to it anyway
*/
static int fixup_compat_flock(struct flock *flock)
{
if (flock->l_start > COMPAT_OFF_T_MAX)
return -EOVERFLOW;
if (flock->l_len > COMPAT_OFF_T_MAX)
flock->l_len = COMPAT_OFF_T_MAX;
return 0;
}
static long do_compat_fcntl64(unsigned int fd, unsigned int cmd,
compat_ulong_t arg)
{
struct fd f = fdget_raw(fd);
struct flock flock;
long err = -EBADF;
if (!f.file)
return err;
if (unlikely(f.file->f_mode & FMODE_PATH)) {
if (!check_fcntl_cmd(cmd))
goto out_put;
}
err = security_file_fcntl(f.file, cmd, arg);
if (err)
goto out_put;
switch (cmd) {
case F_GETLK:
err = get_compat_flock(&flock, compat_ptr(arg));
if (err)
break;
err = fcntl_getlk(f.file, convert_fcntl_cmd(cmd), &flock);
if (err)
break;
err = fixup_compat_flock(&flock);
if (!err)
err = put_compat_flock(&flock, compat_ptr(arg));
break;
case F_GETLK64:
case F_OFD_GETLK:
err = get_compat_flock64(&flock, compat_ptr(arg));
if (err)
break;
err = fcntl_getlk(f.file, convert_fcntl_cmd(cmd), &flock);
if (!err)
err = put_compat_flock64(&flock, compat_ptr(arg));
break;
case F_SETLK:
case F_SETLKW:
err = get_compat_flock(&flock, compat_ptr(arg));
if (err)
break;
err = fcntl_setlk(fd, f.file, convert_fcntl_cmd(cmd), &flock);
break;
case F_SETLK64:
case F_SETLKW64:
case F_OFD_SETLK:
case F_OFD_SETLKW:
err = get_compat_flock64(&flock, compat_ptr(arg));
if (err)
break;
err = fcntl_setlk(fd, f.file, convert_fcntl_cmd(cmd), &flock);
break;
default:
err = do_fcntl(fd, cmd, arg, f.file);
break;
}
out_put:
fdput(f);
return err;
}
COMPAT_SYSCALL_DEFINE3(fcntl64, unsigned int, fd, unsigned int, cmd,
compat_ulong_t, arg)
{
return do_compat_fcntl64(fd, cmd, arg);
}
COMPAT_SYSCALL_DEFINE3(fcntl, unsigned int, fd, unsigned int, cmd,
compat_ulong_t, arg)
{
switch (cmd) {
case F_GETLK64:
case F_SETLK64:
case F_SETLKW64:
case F_OFD_GETLK:
case F_OFD_SETLK:
case F_OFD_SETLKW:
return -EINVAL;
}
return do_compat_fcntl64(fd, cmd, arg);
}
#endif
/* Table to convert sigio signal codes into poll band bitmaps */
static const __poll_t band_table[NSIGPOLL] = {
EPOLLIN | EPOLLRDNORM, /* POLL_IN */
EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND, /* POLL_OUT */
EPOLLIN | EPOLLRDNORM | EPOLLMSG, /* POLL_MSG */
EPOLLERR, /* POLL_ERR */
EPOLLPRI | EPOLLRDBAND, /* POLL_PRI */
EPOLLHUP | EPOLLERR /* POLL_HUP */
};
static inline int sigio_perm(struct task_struct *p,
struct fown_struct *fown, int sig)
{
const struct cred *cred;
int ret;
rcu_read_lock();
cred = __task_cred(p);
ret = ((uid_eq(fown->euid, GLOBAL_ROOT_UID) ||
uid_eq(fown->euid, cred->suid) || uid_eq(fown->euid, cred->uid) ||
uid_eq(fown->uid, cred->suid) || uid_eq(fown->uid, cred->uid)) &&
!security_file_send_sigiotask(p, fown, sig));
rcu_read_unlock();
return ret;
}
static void send_sigio_to_task(struct task_struct *p,
struct fown_struct *fown,
int fd, int reason, enum pid_type type)
{
/*
* F_SETSIG can change ->signum lockless in parallel, make
* sure we read it once and use the same value throughout.
*/
int signum = READ_ONCE(fown->signum);
if (!sigio_perm(p, fown, signum))
return;
switch (signum) {
default: {
kernel_siginfo_t si;
/* Queue a rt signal with the appropriate fd as its
value. We use SI_SIGIO as the source, not
SI_KERNEL, since kernel signals always get
delivered even if we can't queue. Failure to
queue in this case _should_ be reported; we fall
back to SIGIO in that case. --sct */
clear_siginfo(&si);
si.si_signo = signum;
si.si_errno = 0;
si.si_code = reason;
/*
* Posix definies POLL_IN and friends to be signal
* specific si_codes for SIG_POLL. Linux extended
* these si_codes to other signals in a way that is
* ambiguous if other signals also have signal
* specific si_codes. In that case use SI_SIGIO instead
* to remove the ambiguity.
*/
if ((signum != SIGPOLL) && sig_specific_sicodes(signum))
si.si_code = SI_SIGIO;
/* Make sure we are called with one of the POLL_*
reasons, otherwise we could leak kernel stack into
userspace. */
BUG_ON((reason < POLL_IN) || ((reason - POLL_IN) >= NSIGPOLL));
if (reason - POLL_IN >= NSIGPOLL)
si.si_band = ~0L;
else
si.si_band = mangle_poll(band_table[reason - POLL_IN]);
si.si_fd = fd;
if (!do_send_sig_info(signum, &si, p, type))
break;
}
fallthrough; /* fall back on the old plain SIGIO signal */
case 0:
do_send_sig_info(SIGIO, SEND_SIG_PRIV, p, type);
}
}
void send_sigio(struct fown_struct *fown, int fd, int band)
{
struct task_struct *p;
enum pid_type type;
unsigned long flags;
struct pid *pid;
read_lock_irqsave(&fown->lock, flags);
type = fown->pid_type;
pid = fown->pid;
if (!pid)
goto out_unlock_fown;
if (type <= PIDTYPE_TGID) {
rcu_read_lock();
p = pid_task(pid, PIDTYPE_PID);
if (p)
send_sigio_to_task(p, fown, fd, band, type);
rcu_read_unlock();
} else {
read_lock(&tasklist_lock);
do_each_pid_task(pid, type, p) {
send_sigio_to_task(p, fown, fd, band, type);
} while_each_pid_task(pid, type, p);
read_unlock(&tasklist_lock);
}
out_unlock_fown:
read_unlock_irqrestore(&fown->lock, flags);
}
static void send_sigurg_to_task(struct task_struct *p,
struct fown_struct *fown, enum pid_type type)
{
if (sigio_perm(p, fown, SIGURG))
do_send_sig_info(SIGURG, SEND_SIG_PRIV, p, type);
}
int send_sigurg(struct fown_struct *fown)
{
struct task_struct *p;
enum pid_type type;
struct pid *pid;
unsigned long flags;
int ret = 0;
read_lock_irqsave(&fown->lock, flags);
type = fown->pid_type;
pid = fown->pid;
if (!pid)
goto out_unlock_fown;
ret = 1;
if (type <= PIDTYPE_TGID) {
rcu_read_lock();
p = pid_task(pid, PIDTYPE_PID);
if (p)
send_sigurg_to_task(p, fown, type);
rcu_read_unlock();
} else {
read_lock(&tasklist_lock);
do_each_pid_task(pid, type, p) {
send_sigurg_to_task(p, fown, type);
} while_each_pid_task(pid, type, p);
read_unlock(&tasklist_lock);
}
out_unlock_fown:
read_unlock_irqrestore(&fown->lock, flags);
return ret;
}
static DEFINE_SPINLOCK(fasync_lock);
static struct kmem_cache *fasync_cache __read_mostly;
static void fasync_free_rcu(struct rcu_head *head)
{
kmem_cache_free(fasync_cache,
container_of(head, struct fasync_struct, fa_rcu));
}
/*
* Remove a fasync entry. If successfully removed, return
* positive and clear the FASYNC flag. If no entry exists,
* do nothing and return 0.
*
* NOTE! It is very important that the FASYNC flag always
* match the state "is the filp on a fasync list".
*
*/
int fasync_remove_entry(struct file *filp, struct fasync_struct **fapp)
{
struct fasync_struct *fa, **fp;
int result = 0;
spin_lock(&filp->f_lock);
spin_lock(&fasync_lock);
for (fp = fapp; (fa = *fp) != NULL; fp = &fa->fa_next) {
if (fa->fa_file != filp)
continue;
write_lock_irq(&fa->fa_lock);
fa->fa_file = NULL;
write_unlock_irq(&fa->fa_lock);
*fp = fa->fa_next;
call_rcu(&fa->fa_rcu, fasync_free_rcu);
filp->f_flags &= ~FASYNC;
result = 1;
break;
}
spin_unlock(&fasync_lock);
spin_unlock(&filp->f_lock);
return result;
}
struct fasync_struct *fasync_alloc(void)
{
return kmem_cache_alloc(fasync_cache, GFP_KERNEL);
}
/*
* NOTE! This can be used only for unused fasync entries:
* entries that actually got inserted on the fasync list
* need to be released by rcu - see fasync_remove_entry.
*/
void fasync_free(struct fasync_struct *new)
{
kmem_cache_free(fasync_cache, new);
}
/*
* Insert a new entry into the fasync list. Return the pointer to the
* old one if we didn't use the new one.
*
* NOTE! It is very important that the FASYNC flag always
* match the state "is the filp on a fasync list".
*/
struct fasync_struct *fasync_insert_entry(int fd, struct file *filp, struct fasync_struct **fapp, struct fasync_struct *new)
{
struct fasync_struct *fa, **fp;
spin_lock(&filp->f_lock);
spin_lock(&fasync_lock);
for (fp = fapp; (fa = *fp) != NULL; fp = &fa->fa_next) {
if (fa->fa_file != filp)
continue;
write_lock_irq(&fa->fa_lock);
fa->fa_fd = fd;
write_unlock_irq(&fa->fa_lock);
goto out;
}
rwlock_init(&new->fa_lock);
new->magic = FASYNC_MAGIC;
new->fa_file = filp;
new->fa_fd = fd;
new->fa_next = *fapp;
rcu_assign_pointer(*fapp, new);
filp->f_flags |= FASYNC;
out:
spin_unlock(&fasync_lock);
spin_unlock(&filp->f_lock);
return fa;
}
/*
* Add a fasync entry. Return negative on error, positive if
* added, and zero if did nothing but change an existing one.
*/
static int fasync_add_entry(int fd, struct file *filp, struct fasync_struct **fapp)
{
struct fasync_struct *new;
new = fasync_alloc();
if (!new)
return -ENOMEM;
/*
* fasync_insert_entry() returns the old (update) entry if
* it existed.
*
* So free the (unused) new entry and return 0 to let the
* caller know that we didn't add any new fasync entries.
*/
if (fasync_insert_entry(fd, filp, fapp, new)) {
fasync_free(new);
return 0;
}
return 1;
}
/*
* fasync_helper() is used by almost all character device drivers
* to set up the fasync queue, and for regular files by the file
* lease code. It returns negative on error, 0 if it did no changes
* and positive if it added/deleted the entry.
*/
int fasync_helper(int fd, struct file * filp, int on, struct fasync_struct **fapp)
{
if (!on)
return fasync_remove_entry(filp, fapp);
return fasync_add_entry(fd, filp, fapp);
}
EXPORT_SYMBOL(fasync_helper);
/*
* rcu_read_lock() is held
*/
static void kill_fasync_rcu(struct fasync_struct *fa, int sig, int band)
{
while (fa) {
struct fown_struct *fown;
if (fa->magic != FASYNC_MAGIC) {
printk(KERN_ERR "kill_fasync: bad magic number in "
"fasync_struct!\n");
return;
}
read_lock(&fa->fa_lock);
if (fa->fa_file) {
fown = &fa->fa_file->f_owner;
/* Don't send SIGURG to processes which have not set a
queued signum: SIGURG has its own default signalling
mechanism. */
if (!(sig == SIGURG && fown->signum == 0))
send_sigio(fown, fa->fa_fd, band);
}
read_unlock(&fa->fa_lock);
fa = rcu_dereference(fa->fa_next);
}
}
void kill_fasync(struct fasync_struct **fp, int sig, int band)
{
/* First a quick test without locking: usually
* the list is empty.
*/
if (*fp) {
rcu_read_lock();
kill_fasync_rcu(rcu_dereference(*fp), sig, band);
rcu_read_unlock();
}
}
EXPORT_SYMBOL(kill_fasync);
static int __init fcntl_init(void)
{
/*
* Please add new bits here to ensure allocation uniqueness.
* Exceptions: O_NONBLOCK is a two bit define on parisc; O_NDELAY
* is defined as O_NONBLOCK on some platforms and not on others.
*/
BUILD_BUG_ON(21 - 1 /* for O_RDONLY being 0 */ !=
HWEIGHT32(
(VALID_OPEN_FLAGS & ~(O_NONBLOCK | O_NDELAY)) |
__FMODE_EXEC | __FMODE_NONOTIFY));
fasync_cache = kmem_cache_create("fasync_cache",
sizeof(struct fasync_struct), 0, SLAB_PANIC, NULL);
return 0;
}
module_init(fcntl_init)