mirror of
https://github.com/torvalds/linux.git
synced 2024-11-22 12:11:40 +00:00
0c5fd887d2
This cycle we added support for mounting overlayfs on top of idmapped mounts.
Recently I've started looking into potential corner cases when trying to add
additional tests and I noticed that reporting for POSIX ACLs is currently wrong
when using idmapped layers with overlayfs mounted on top of it.
I'm going to give a rather detailed explanation to both the origin of the
problem and the solution.
Let's assume the user creates the following directory layout and they have a
rootfs /var/lib/lxc/c1/rootfs. The files in this rootfs are owned as you would
expect files on your host system to be owned. For example, ~/.bashrc for your
regular user would be owned by 1000:1000 and /root/.bashrc would be owned by
0:0. IOW, this is just regular boring filesystem tree on an ext4 or xfs
filesystem.
The user chooses to set POSIX ACLs using the setfacl binary granting the user
with uid 4 read, write, and execute permissions for their .bashrc file:
setfacl -m u:4:rwx /var/lib/lxc/c2/rootfs/home/ubuntu/.bashrc
Now they to expose the whole rootfs to a container using an idmapped mount. So
they first create:
mkdir -pv /vol/contpool/{ctrover,merge,lowermap,overmap}
mkdir -pv /vol/contpool/ctrover/{over,work}
chown 10000000:10000000 /vol/contpool/ctrover/{over,work}
The user now creates an idmapped mount for the rootfs:
mount-idmapped/mount-idmapped --map-mount=b:0:10000000:65536 \
/var/lib/lxc/c2/rootfs \
/vol/contpool/lowermap
This for example makes it so that /var/lib/lxc/c2/rootfs/home/ubuntu/.bashrc
which is owned by uid and gid 1000 as being owned by uid and gid 10001000 at
/vol/contpool/lowermap/home/ubuntu/.bashrc.
Assume the user wants to expose these idmapped mounts through an overlayfs
mount to a container.
mount -t overlay overlay \
-o lowerdir=/vol/contpool/lowermap, \
upperdir=/vol/contpool/overmap/over, \
workdir=/vol/contpool/overmap/work \
/vol/contpool/merge
The user can do this in two ways:
(1) Mount overlayfs in the initial user namespace and expose it to the
container.
(2) Mount overlayfs on top of the idmapped mounts inside of the container's
user namespace.
Let's assume the user chooses the (1) option and mounts overlayfs on the host
and then changes into a container which uses the idmapping 0:10000000:65536
which is the same used for the two idmapped mounts.
Now the user tries to retrieve the POSIX ACLs using the getfacl command
getfacl -n /vol/contpool/lowermap/home/ubuntu/.bashrc
and to their surprise they see:
# file: vol/contpool/merge/home/ubuntu/.bashrc
# owner: 1000
# group: 1000
user::rw-
user:4294967295:rwx
group::r--
mask::rwx
other::r--
indicating the the uid wasn't correctly translated according to the idmapped
mount. The problem is how we currently translate POSIX ACLs. Let's inspect the
callchain in this example:
idmapped mount /vol/contpool/merge: 0:10000000:65536
caller's idmapping: 0:10000000:65536
overlayfs idmapping (ofs->creator_cred): 0:0:4k /* initial idmapping */
sys_getxattr()
-> path_getxattr()
-> getxattr()
-> do_getxattr()
|> vfs_getxattr()
| -> __vfs_getxattr()
| -> handler->get == ovl_posix_acl_xattr_get()
| -> ovl_xattr_get()
| -> vfs_getxattr()
| -> __vfs_getxattr()
| -> handler->get() /* lower filesystem callback */
|> posix_acl_fix_xattr_to_user()
{
4 = make_kuid(&init_user_ns, 4);
4 = mapped_kuid_fs(&init_user_ns /* no idmapped mount */, 4);
/* FAILURE */
-1 = from_kuid(0:10000000:65536 /* caller's idmapping */, 4);
}
If the user chooses to use option (2) and mounts overlayfs on top of idmapped
mounts inside the container things don't look that much better:
idmapped mount /vol/contpool/merge: 0:10000000:65536
caller's idmapping: 0:10000000:65536
overlayfs idmapping (ofs->creator_cred): 0:10000000:65536
sys_getxattr()
-> path_getxattr()
-> getxattr()
-> do_getxattr()
|> vfs_getxattr()
| -> __vfs_getxattr()
| -> handler->get == ovl_posix_acl_xattr_get()
| -> ovl_xattr_get()
| -> vfs_getxattr()
| -> __vfs_getxattr()
| -> handler->get() /* lower filesystem callback */
|> posix_acl_fix_xattr_to_user()
{
4 = make_kuid(&init_user_ns, 4);
4 = mapped_kuid_fs(&init_user_ns, 4);
/* FAILURE */
-1 = from_kuid(0:10000000:65536 /* caller's idmapping */, 4);
}
As is easily seen the problem arises because the idmapping of the lower mount
isn't taken into account as all of this happens in do_gexattr(). But
do_getxattr() is always called on an overlayfs mount and inode and thus cannot
possible take the idmapping of the lower layers into account.
This problem is similar for fscaps but there the translation happens as part of
vfs_getxattr() already. Let's walk through an fscaps overlayfs callchain:
setcap 'cap_net_raw+ep' /var/lib/lxc/c2/rootfs/home/ubuntu/.bashrc
The expected outcome here is that we'll receive the cap_net_raw capability as
we are able to map the uid associated with the fscap to 0 within our container.
IOW, we want to see 0 as the result of the idmapping translations.
If the user chooses option (1) we get the following callchain for fscaps:
idmapped mount /vol/contpool/merge: 0:10000000:65536
caller's idmapping: 0:10000000:65536
overlayfs idmapping (ofs->creator_cred): 0:0:4k /* initial idmapping */
sys_getxattr()
-> path_getxattr()
-> getxattr()
-> do_getxattr()
-> vfs_getxattr()
-> xattr_getsecurity()
-> security_inode_getsecurity() ________________________________
-> cap_inode_getsecurity() | |
{ V |
10000000 = make_kuid(0:0:4k /* overlayfs idmapping */, 10000000); |
10000000 = mapped_kuid_fs(0:0:4k /* no idmapped mount */, 10000000); |
/* Expected result is 0 and thus that we own the fscap. */ |
0 = from_kuid(0:10000000:65536 /* caller's idmapping */, 10000000); |
} |
-> vfs_getxattr_alloc() |
-> handler->get == ovl_other_xattr_get() |
-> vfs_getxattr() |
-> xattr_getsecurity() |
-> security_inode_getsecurity() |
-> cap_inode_getsecurity() |
{ |
0 = make_kuid(0:0:4k /* lower s_user_ns */, 0); |
10000000 = mapped_kuid_fs(0:10000000:65536 /* idmapped mount */, 0); |
10000000 = from_kuid(0:0:4k /* overlayfs idmapping */, 10000000); |
|____________________________________________________________________|
}
-> vfs_getxattr_alloc()
-> handler->get == /* lower filesystem callback */
And if the user chooses option (2) we get:
idmapped mount /vol/contpool/merge: 0:10000000:65536
caller's idmapping: 0:10000000:65536
overlayfs idmapping (ofs->creator_cred): 0:10000000:65536
sys_getxattr()
-> path_getxattr()
-> getxattr()
-> do_getxattr()
-> vfs_getxattr()
-> xattr_getsecurity()
-> security_inode_getsecurity() _______________________________
-> cap_inode_getsecurity() | |
{ V |
10000000 = make_kuid(0:10000000:65536 /* overlayfs idmapping */, 0); |
10000000 = mapped_kuid_fs(0:0:4k /* no idmapped mount */, 10000000); |
/* Expected result is 0 and thus that we own the fscap. */ |
0 = from_kuid(0:10000000:65536 /* caller's idmapping */, 10000000); |
} |
-> vfs_getxattr_alloc() |
-> handler->get == ovl_other_xattr_get() |
|-> vfs_getxattr() |
-> xattr_getsecurity() |
-> security_inode_getsecurity() |
-> cap_inode_getsecurity() |
{ |
0 = make_kuid(0:0:4k /* lower s_user_ns */, 0); |
10000000 = mapped_kuid_fs(0:10000000:65536 /* idmapped mount */, 0); |
0 = from_kuid(0:10000000:65536 /* overlayfs idmapping */, 10000000); |
|____________________________________________________________________|
}
-> vfs_getxattr_alloc()
-> handler->get == /* lower filesystem callback */
We can see how the translation happens correctly in those cases as the
conversion happens within the vfs_getxattr() helper.
For POSIX ACLs we need to do something similar. However, in contrast to fscaps
we cannot apply the fix directly to the kernel internal posix acl data
structure as this would alter the cached values and would also require a rework
of how we currently deal with POSIX ACLs in general which almost never take the
filesystem idmapping into account (the noteable exception being FUSE but even
there the implementation is special) and instead retrieve the raw values based
on the initial idmapping.
The correct values are then generated right before returning to userspace. The
fix for this is to move taking the mount's idmapping into account directly in
vfs_getxattr() instead of having it be part of posix_acl_fix_xattr_to_user().
To this end we split out two small and unexported helpers
posix_acl_getxattr_idmapped_mnt() and posix_acl_setxattr_idmapped_mnt(). The
former to be called in vfs_getxattr() and the latter to be called in
vfs_setxattr().
Let's go back to the original example. Assume the user chose option (1) and
mounted overlayfs on top of idmapped mounts on the host:
idmapped mount /vol/contpool/merge: 0:10000000:65536
caller's idmapping: 0:10000000:65536
overlayfs idmapping (ofs->creator_cred): 0:0:4k /* initial idmapping */
sys_getxattr()
-> path_getxattr()
-> getxattr()
-> do_getxattr()
|> vfs_getxattr()
| |> __vfs_getxattr()
| | -> handler->get == ovl_posix_acl_xattr_get()
| | -> ovl_xattr_get()
| | -> vfs_getxattr()
| | |> __vfs_getxattr()
| | | -> handler->get() /* lower filesystem callback */
| | |> posix_acl_getxattr_idmapped_mnt()
| | {
| | 4 = make_kuid(&init_user_ns, 4);
| | 10000004 = mapped_kuid_fs(0:10000000:65536 /* lower idmapped mount */, 4);
| | 10000004 = from_kuid(&init_user_ns, 10000004);
| | |_______________________
| | } |
| | |
| |> posix_acl_getxattr_idmapped_mnt() |
| { |
| V
| 10000004 = make_kuid(&init_user_ns, 10000004);
| 10000004 = mapped_kuid_fs(&init_user_ns /* no idmapped mount */, 10000004);
| 10000004 = from_kuid(&init_user_ns, 10000004);
| } |_________________________________________________
| |
| |
|> posix_acl_fix_xattr_to_user() |
{ V
10000004 = make_kuid(0:0:4k /* init_user_ns */, 10000004);
/* SUCCESS */
4 = from_kuid(0:10000000:65536 /* caller's idmapping */, 10000004);
}
And similarly if the user chooses option (1) and mounted overayfs on top of
idmapped mounts inside the container:
idmapped mount /vol/contpool/merge: 0:10000000:65536
caller's idmapping: 0:10000000:65536
overlayfs idmapping (ofs->creator_cred): 0:10000000:65536
sys_getxattr()
-> path_getxattr()
-> getxattr()
-> do_getxattr()
|> vfs_getxattr()
| |> __vfs_getxattr()
| | -> handler->get == ovl_posix_acl_xattr_get()
| | -> ovl_xattr_get()
| | -> vfs_getxattr()
| | |> __vfs_getxattr()
| | | -> handler->get() /* lower filesystem callback */
| | |> posix_acl_getxattr_idmapped_mnt()
| | {
| | 4 = make_kuid(&init_user_ns, 4);
| | 10000004 = mapped_kuid_fs(0:10000000:65536 /* lower idmapped mount */, 4);
| | 10000004 = from_kuid(&init_user_ns, 10000004);
| | |_______________________
| | } |
| | |
| |> posix_acl_getxattr_idmapped_mnt() |
| { V
| 10000004 = make_kuid(&init_user_ns, 10000004);
| 10000004 = mapped_kuid_fs(&init_user_ns /* no idmapped mount */, 10000004);
| 10000004 = from_kuid(0(&init_user_ns, 10000004);
| |_________________________________________________
| } |
| |
|> posix_acl_fix_xattr_to_user() |
{ V
10000004 = make_kuid(0:0:4k /* init_user_ns */, 10000004);
/* SUCCESS */
4 = from_kuid(0:10000000:65536 /* caller's idmappings */, 10000004);
}
The last remaining problem we need to fix here is ovl_get_acl(). During
ovl_permission() overlayfs will call:
ovl_permission()
-> generic_permission()
-> acl_permission_check()
-> check_acl()
-> get_acl()
-> inode->i_op->get_acl() == ovl_get_acl()
> get_acl() /* on the underlying filesystem)
->inode->i_op->get_acl() == /*lower filesystem callback */
-> posix_acl_permission()
passing through the get_acl request to the underlying filesystem. This will
retrieve the acls stored in the lower filesystem without taking the idmapping
of the underlying mount into account as this would mean altering the cached
values for the lower filesystem. So we block using ACLs for now until we
decided on a nice way to fix this. Note this limitation both in the
documentation and in the code.
The most straightforward solution would be to have ovl_get_acl() simply
duplicate the ACLs, update the values according to the idmapped mount and
return it to acl_permission_check() so it can be used in posix_acl_permission()
forgetting them afterwards. This is a bit heavy handed but fairly
straightforward otherwise.
Link: https://github.com/brauner/mount-idmapped/issues/9
Link: https://lore.kernel.org/r/20220708090134.385160-2-brauner@kernel.org
Cc: Seth Forshee <sforshee@digitalocean.com>
Cc: Amir Goldstein <amir73il@gmail.com>
Cc: Vivek Goyal <vgoyal@redhat.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Aleksa Sarai <cyphar@cyphar.com>
Cc: Miklos Szeredi <mszeredi@redhat.com>
Cc: linux-unionfs@vger.kernel.org
Cc: linux-fsdevel@vger.kernel.org
Reviewed-by: Seth Forshee <sforshee@digitalocean.com>
Signed-off-by: Christian Brauner (Microsoft) <brauner@kernel.org>
1094 lines
26 KiB
C
1094 lines
26 KiB
C
// SPDX-License-Identifier: GPL-2.0-only
|
|
/*
|
|
* Copyright (C) 2002,2003 by Andreas Gruenbacher <a.gruenbacher@computer.org>
|
|
*
|
|
* Fixes from William Schumacher incorporated on 15 March 2001.
|
|
* (Reported by Charles Bertsch, <CBertsch@microtest.com>).
|
|
*/
|
|
|
|
/*
|
|
* This file contains generic functions for manipulating
|
|
* POSIX 1003.1e draft standard 17 ACLs.
|
|
*/
|
|
|
|
#include <linux/kernel.h>
|
|
#include <linux/slab.h>
|
|
#include <linux/atomic.h>
|
|
#include <linux/fs.h>
|
|
#include <linux/sched.h>
|
|
#include <linux/cred.h>
|
|
#include <linux/posix_acl.h>
|
|
#include <linux/posix_acl_xattr.h>
|
|
#include <linux/xattr.h>
|
|
#include <linux/export.h>
|
|
#include <linux/user_namespace.h>
|
|
#include <linux/namei.h>
|
|
#include <linux/mnt_idmapping.h>
|
|
|
|
static struct posix_acl **acl_by_type(struct inode *inode, int type)
|
|
{
|
|
switch (type) {
|
|
case ACL_TYPE_ACCESS:
|
|
return &inode->i_acl;
|
|
case ACL_TYPE_DEFAULT:
|
|
return &inode->i_default_acl;
|
|
default:
|
|
BUG();
|
|
}
|
|
}
|
|
|
|
struct posix_acl *get_cached_acl(struct inode *inode, int type)
|
|
{
|
|
struct posix_acl **p = acl_by_type(inode, type);
|
|
struct posix_acl *acl;
|
|
|
|
for (;;) {
|
|
rcu_read_lock();
|
|
acl = rcu_dereference(*p);
|
|
if (!acl || is_uncached_acl(acl) ||
|
|
refcount_inc_not_zero(&acl->a_refcount))
|
|
break;
|
|
rcu_read_unlock();
|
|
cpu_relax();
|
|
}
|
|
rcu_read_unlock();
|
|
return acl;
|
|
}
|
|
EXPORT_SYMBOL(get_cached_acl);
|
|
|
|
struct posix_acl *get_cached_acl_rcu(struct inode *inode, int type)
|
|
{
|
|
struct posix_acl *acl = rcu_dereference(*acl_by_type(inode, type));
|
|
|
|
if (acl == ACL_DONT_CACHE) {
|
|
struct posix_acl *ret;
|
|
|
|
ret = inode->i_op->get_acl(inode, type, LOOKUP_RCU);
|
|
if (!IS_ERR(ret))
|
|
acl = ret;
|
|
}
|
|
|
|
return acl;
|
|
}
|
|
EXPORT_SYMBOL(get_cached_acl_rcu);
|
|
|
|
void set_cached_acl(struct inode *inode, int type, struct posix_acl *acl)
|
|
{
|
|
struct posix_acl **p = acl_by_type(inode, type);
|
|
struct posix_acl *old;
|
|
|
|
old = xchg(p, posix_acl_dup(acl));
|
|
if (!is_uncached_acl(old))
|
|
posix_acl_release(old);
|
|
}
|
|
EXPORT_SYMBOL(set_cached_acl);
|
|
|
|
static void __forget_cached_acl(struct posix_acl **p)
|
|
{
|
|
struct posix_acl *old;
|
|
|
|
old = xchg(p, ACL_NOT_CACHED);
|
|
if (!is_uncached_acl(old))
|
|
posix_acl_release(old);
|
|
}
|
|
|
|
void forget_cached_acl(struct inode *inode, int type)
|
|
{
|
|
__forget_cached_acl(acl_by_type(inode, type));
|
|
}
|
|
EXPORT_SYMBOL(forget_cached_acl);
|
|
|
|
void forget_all_cached_acls(struct inode *inode)
|
|
{
|
|
__forget_cached_acl(&inode->i_acl);
|
|
__forget_cached_acl(&inode->i_default_acl);
|
|
}
|
|
EXPORT_SYMBOL(forget_all_cached_acls);
|
|
|
|
struct posix_acl *get_acl(struct inode *inode, int type)
|
|
{
|
|
void *sentinel;
|
|
struct posix_acl **p;
|
|
struct posix_acl *acl;
|
|
|
|
/*
|
|
* The sentinel is used to detect when another operation like
|
|
* set_cached_acl() or forget_cached_acl() races with get_acl().
|
|
* It is guaranteed that is_uncached_acl(sentinel) is true.
|
|
*/
|
|
|
|
acl = get_cached_acl(inode, type);
|
|
if (!is_uncached_acl(acl))
|
|
return acl;
|
|
|
|
if (!IS_POSIXACL(inode))
|
|
return NULL;
|
|
|
|
sentinel = uncached_acl_sentinel(current);
|
|
p = acl_by_type(inode, type);
|
|
|
|
/*
|
|
* If the ACL isn't being read yet, set our sentinel. Otherwise, the
|
|
* current value of the ACL will not be ACL_NOT_CACHED and so our own
|
|
* sentinel will not be set; another task will update the cache. We
|
|
* could wait for that other task to complete its job, but it's easier
|
|
* to just call ->get_acl to fetch the ACL ourself. (This is going to
|
|
* be an unlikely race.)
|
|
*/
|
|
cmpxchg(p, ACL_NOT_CACHED, sentinel);
|
|
|
|
/*
|
|
* Normally, the ACL returned by ->get_acl will be cached.
|
|
* A filesystem can prevent that by calling
|
|
* forget_cached_acl(inode, type) in ->get_acl.
|
|
*
|
|
* If the filesystem doesn't have a get_acl() function at all, we'll
|
|
* just create the negative cache entry.
|
|
*/
|
|
if (!inode->i_op->get_acl) {
|
|
set_cached_acl(inode, type, NULL);
|
|
return NULL;
|
|
}
|
|
acl = inode->i_op->get_acl(inode, type, false);
|
|
|
|
if (IS_ERR(acl)) {
|
|
/*
|
|
* Remove our sentinel so that we don't block future attempts
|
|
* to cache the ACL.
|
|
*/
|
|
cmpxchg(p, sentinel, ACL_NOT_CACHED);
|
|
return acl;
|
|
}
|
|
|
|
/*
|
|
* Cache the result, but only if our sentinel is still in place.
|
|
*/
|
|
posix_acl_dup(acl);
|
|
if (unlikely(cmpxchg(p, sentinel, acl) != sentinel))
|
|
posix_acl_release(acl);
|
|
return acl;
|
|
}
|
|
EXPORT_SYMBOL(get_acl);
|
|
|
|
/*
|
|
* Init a fresh posix_acl
|
|
*/
|
|
void
|
|
posix_acl_init(struct posix_acl *acl, int count)
|
|
{
|
|
refcount_set(&acl->a_refcount, 1);
|
|
acl->a_count = count;
|
|
}
|
|
EXPORT_SYMBOL(posix_acl_init);
|
|
|
|
/*
|
|
* Allocate a new ACL with the specified number of entries.
|
|
*/
|
|
struct posix_acl *
|
|
posix_acl_alloc(int count, gfp_t flags)
|
|
{
|
|
const size_t size = sizeof(struct posix_acl) +
|
|
count * sizeof(struct posix_acl_entry);
|
|
struct posix_acl *acl = kmalloc(size, flags);
|
|
if (acl)
|
|
posix_acl_init(acl, count);
|
|
return acl;
|
|
}
|
|
EXPORT_SYMBOL(posix_acl_alloc);
|
|
|
|
/*
|
|
* Clone an ACL.
|
|
*/
|
|
static struct posix_acl *
|
|
posix_acl_clone(const struct posix_acl *acl, gfp_t flags)
|
|
{
|
|
struct posix_acl *clone = NULL;
|
|
|
|
if (acl) {
|
|
int size = sizeof(struct posix_acl) + acl->a_count *
|
|
sizeof(struct posix_acl_entry);
|
|
clone = kmemdup(acl, size, flags);
|
|
if (clone)
|
|
refcount_set(&clone->a_refcount, 1);
|
|
}
|
|
return clone;
|
|
}
|
|
|
|
/*
|
|
* Check if an acl is valid. Returns 0 if it is, or -E... otherwise.
|
|
*/
|
|
int
|
|
posix_acl_valid(struct user_namespace *user_ns, const struct posix_acl *acl)
|
|
{
|
|
const struct posix_acl_entry *pa, *pe;
|
|
int state = ACL_USER_OBJ;
|
|
int needs_mask = 0;
|
|
|
|
FOREACH_ACL_ENTRY(pa, acl, pe) {
|
|
if (pa->e_perm & ~(ACL_READ|ACL_WRITE|ACL_EXECUTE))
|
|
return -EINVAL;
|
|
switch (pa->e_tag) {
|
|
case ACL_USER_OBJ:
|
|
if (state == ACL_USER_OBJ) {
|
|
state = ACL_USER;
|
|
break;
|
|
}
|
|
return -EINVAL;
|
|
|
|
case ACL_USER:
|
|
if (state != ACL_USER)
|
|
return -EINVAL;
|
|
if (!kuid_has_mapping(user_ns, pa->e_uid))
|
|
return -EINVAL;
|
|
needs_mask = 1;
|
|
break;
|
|
|
|
case ACL_GROUP_OBJ:
|
|
if (state == ACL_USER) {
|
|
state = ACL_GROUP;
|
|
break;
|
|
}
|
|
return -EINVAL;
|
|
|
|
case ACL_GROUP:
|
|
if (state != ACL_GROUP)
|
|
return -EINVAL;
|
|
if (!kgid_has_mapping(user_ns, pa->e_gid))
|
|
return -EINVAL;
|
|
needs_mask = 1;
|
|
break;
|
|
|
|
case ACL_MASK:
|
|
if (state != ACL_GROUP)
|
|
return -EINVAL;
|
|
state = ACL_OTHER;
|
|
break;
|
|
|
|
case ACL_OTHER:
|
|
if (state == ACL_OTHER ||
|
|
(state == ACL_GROUP && !needs_mask)) {
|
|
state = 0;
|
|
break;
|
|
}
|
|
return -EINVAL;
|
|
|
|
default:
|
|
return -EINVAL;
|
|
}
|
|
}
|
|
if (state == 0)
|
|
return 0;
|
|
return -EINVAL;
|
|
}
|
|
EXPORT_SYMBOL(posix_acl_valid);
|
|
|
|
/*
|
|
* Returns 0 if the acl can be exactly represented in the traditional
|
|
* file mode permission bits, or else 1. Returns -E... on error.
|
|
*/
|
|
int
|
|
posix_acl_equiv_mode(const struct posix_acl *acl, umode_t *mode_p)
|
|
{
|
|
const struct posix_acl_entry *pa, *pe;
|
|
umode_t mode = 0;
|
|
int not_equiv = 0;
|
|
|
|
/*
|
|
* A null ACL can always be presented as mode bits.
|
|
*/
|
|
if (!acl)
|
|
return 0;
|
|
|
|
FOREACH_ACL_ENTRY(pa, acl, pe) {
|
|
switch (pa->e_tag) {
|
|
case ACL_USER_OBJ:
|
|
mode |= (pa->e_perm & S_IRWXO) << 6;
|
|
break;
|
|
case ACL_GROUP_OBJ:
|
|
mode |= (pa->e_perm & S_IRWXO) << 3;
|
|
break;
|
|
case ACL_OTHER:
|
|
mode |= pa->e_perm & S_IRWXO;
|
|
break;
|
|
case ACL_MASK:
|
|
mode = (mode & ~S_IRWXG) |
|
|
((pa->e_perm & S_IRWXO) << 3);
|
|
not_equiv = 1;
|
|
break;
|
|
case ACL_USER:
|
|
case ACL_GROUP:
|
|
not_equiv = 1;
|
|
break;
|
|
default:
|
|
return -EINVAL;
|
|
}
|
|
}
|
|
if (mode_p)
|
|
*mode_p = (*mode_p & ~S_IRWXUGO) | mode;
|
|
return not_equiv;
|
|
}
|
|
EXPORT_SYMBOL(posix_acl_equiv_mode);
|
|
|
|
/*
|
|
* Create an ACL representing the file mode permission bits of an inode.
|
|
*/
|
|
struct posix_acl *
|
|
posix_acl_from_mode(umode_t mode, gfp_t flags)
|
|
{
|
|
struct posix_acl *acl = posix_acl_alloc(3, flags);
|
|
if (!acl)
|
|
return ERR_PTR(-ENOMEM);
|
|
|
|
acl->a_entries[0].e_tag = ACL_USER_OBJ;
|
|
acl->a_entries[0].e_perm = (mode & S_IRWXU) >> 6;
|
|
|
|
acl->a_entries[1].e_tag = ACL_GROUP_OBJ;
|
|
acl->a_entries[1].e_perm = (mode & S_IRWXG) >> 3;
|
|
|
|
acl->a_entries[2].e_tag = ACL_OTHER;
|
|
acl->a_entries[2].e_perm = (mode & S_IRWXO);
|
|
return acl;
|
|
}
|
|
EXPORT_SYMBOL(posix_acl_from_mode);
|
|
|
|
/*
|
|
* Return 0 if current is granted want access to the inode
|
|
* by the acl. Returns -E... otherwise.
|
|
*/
|
|
int
|
|
posix_acl_permission(struct user_namespace *mnt_userns, struct inode *inode,
|
|
const struct posix_acl *acl, int want)
|
|
{
|
|
const struct posix_acl_entry *pa, *pe, *mask_obj;
|
|
int found = 0;
|
|
kuid_t uid;
|
|
kgid_t gid;
|
|
|
|
want &= MAY_READ | MAY_WRITE | MAY_EXEC;
|
|
|
|
FOREACH_ACL_ENTRY(pa, acl, pe) {
|
|
switch(pa->e_tag) {
|
|
case ACL_USER_OBJ:
|
|
/* (May have been checked already) */
|
|
uid = i_uid_into_mnt(mnt_userns, inode);
|
|
if (uid_eq(uid, current_fsuid()))
|
|
goto check_perm;
|
|
break;
|
|
case ACL_USER:
|
|
uid = mapped_kuid_fs(mnt_userns, &init_user_ns,
|
|
pa->e_uid);
|
|
if (uid_eq(uid, current_fsuid()))
|
|
goto mask;
|
|
break;
|
|
case ACL_GROUP_OBJ:
|
|
gid = i_gid_into_mnt(mnt_userns, inode);
|
|
if (in_group_p(gid)) {
|
|
found = 1;
|
|
if ((pa->e_perm & want) == want)
|
|
goto mask;
|
|
}
|
|
break;
|
|
case ACL_GROUP:
|
|
gid = mapped_kgid_fs(mnt_userns, &init_user_ns,
|
|
pa->e_gid);
|
|
if (in_group_p(gid)) {
|
|
found = 1;
|
|
if ((pa->e_perm & want) == want)
|
|
goto mask;
|
|
}
|
|
break;
|
|
case ACL_MASK:
|
|
break;
|
|
case ACL_OTHER:
|
|
if (found)
|
|
return -EACCES;
|
|
else
|
|
goto check_perm;
|
|
default:
|
|
return -EIO;
|
|
}
|
|
}
|
|
return -EIO;
|
|
|
|
mask:
|
|
for (mask_obj = pa+1; mask_obj != pe; mask_obj++) {
|
|
if (mask_obj->e_tag == ACL_MASK) {
|
|
if ((pa->e_perm & mask_obj->e_perm & want) == want)
|
|
return 0;
|
|
return -EACCES;
|
|
}
|
|
}
|
|
|
|
check_perm:
|
|
if ((pa->e_perm & want) == want)
|
|
return 0;
|
|
return -EACCES;
|
|
}
|
|
|
|
/*
|
|
* Modify acl when creating a new inode. The caller must ensure the acl is
|
|
* only referenced once.
|
|
*
|
|
* mode_p initially must contain the mode parameter to the open() / creat()
|
|
* system calls. All permissions that are not granted by the acl are removed.
|
|
* The permissions in the acl are changed to reflect the mode_p parameter.
|
|
*/
|
|
static int posix_acl_create_masq(struct posix_acl *acl, umode_t *mode_p)
|
|
{
|
|
struct posix_acl_entry *pa, *pe;
|
|
struct posix_acl_entry *group_obj = NULL, *mask_obj = NULL;
|
|
umode_t mode = *mode_p;
|
|
int not_equiv = 0;
|
|
|
|
/* assert(atomic_read(acl->a_refcount) == 1); */
|
|
|
|
FOREACH_ACL_ENTRY(pa, acl, pe) {
|
|
switch(pa->e_tag) {
|
|
case ACL_USER_OBJ:
|
|
pa->e_perm &= (mode >> 6) | ~S_IRWXO;
|
|
mode &= (pa->e_perm << 6) | ~S_IRWXU;
|
|
break;
|
|
|
|
case ACL_USER:
|
|
case ACL_GROUP:
|
|
not_equiv = 1;
|
|
break;
|
|
|
|
case ACL_GROUP_OBJ:
|
|
group_obj = pa;
|
|
break;
|
|
|
|
case ACL_OTHER:
|
|
pa->e_perm &= mode | ~S_IRWXO;
|
|
mode &= pa->e_perm | ~S_IRWXO;
|
|
break;
|
|
|
|
case ACL_MASK:
|
|
mask_obj = pa;
|
|
not_equiv = 1;
|
|
break;
|
|
|
|
default:
|
|
return -EIO;
|
|
}
|
|
}
|
|
|
|
if (mask_obj) {
|
|
mask_obj->e_perm &= (mode >> 3) | ~S_IRWXO;
|
|
mode &= (mask_obj->e_perm << 3) | ~S_IRWXG;
|
|
} else {
|
|
if (!group_obj)
|
|
return -EIO;
|
|
group_obj->e_perm &= (mode >> 3) | ~S_IRWXO;
|
|
mode &= (group_obj->e_perm << 3) | ~S_IRWXG;
|
|
}
|
|
|
|
*mode_p = (*mode_p & ~S_IRWXUGO) | mode;
|
|
return not_equiv;
|
|
}
|
|
|
|
/*
|
|
* Modify the ACL for the chmod syscall.
|
|
*/
|
|
static int __posix_acl_chmod_masq(struct posix_acl *acl, umode_t mode)
|
|
{
|
|
struct posix_acl_entry *group_obj = NULL, *mask_obj = NULL;
|
|
struct posix_acl_entry *pa, *pe;
|
|
|
|
/* assert(atomic_read(acl->a_refcount) == 1); */
|
|
|
|
FOREACH_ACL_ENTRY(pa, acl, pe) {
|
|
switch(pa->e_tag) {
|
|
case ACL_USER_OBJ:
|
|
pa->e_perm = (mode & S_IRWXU) >> 6;
|
|
break;
|
|
|
|
case ACL_USER:
|
|
case ACL_GROUP:
|
|
break;
|
|
|
|
case ACL_GROUP_OBJ:
|
|
group_obj = pa;
|
|
break;
|
|
|
|
case ACL_MASK:
|
|
mask_obj = pa;
|
|
break;
|
|
|
|
case ACL_OTHER:
|
|
pa->e_perm = (mode & S_IRWXO);
|
|
break;
|
|
|
|
default:
|
|
return -EIO;
|
|
}
|
|
}
|
|
|
|
if (mask_obj) {
|
|
mask_obj->e_perm = (mode & S_IRWXG) >> 3;
|
|
} else {
|
|
if (!group_obj)
|
|
return -EIO;
|
|
group_obj->e_perm = (mode & S_IRWXG) >> 3;
|
|
}
|
|
|
|
return 0;
|
|
}
|
|
|
|
int
|
|
__posix_acl_create(struct posix_acl **acl, gfp_t gfp, umode_t *mode_p)
|
|
{
|
|
struct posix_acl *clone = posix_acl_clone(*acl, gfp);
|
|
int err = -ENOMEM;
|
|
if (clone) {
|
|
err = posix_acl_create_masq(clone, mode_p);
|
|
if (err < 0) {
|
|
posix_acl_release(clone);
|
|
clone = NULL;
|
|
}
|
|
}
|
|
posix_acl_release(*acl);
|
|
*acl = clone;
|
|
return err;
|
|
}
|
|
EXPORT_SYMBOL(__posix_acl_create);
|
|
|
|
int
|
|
__posix_acl_chmod(struct posix_acl **acl, gfp_t gfp, umode_t mode)
|
|
{
|
|
struct posix_acl *clone = posix_acl_clone(*acl, gfp);
|
|
int err = -ENOMEM;
|
|
if (clone) {
|
|
err = __posix_acl_chmod_masq(clone, mode);
|
|
if (err) {
|
|
posix_acl_release(clone);
|
|
clone = NULL;
|
|
}
|
|
}
|
|
posix_acl_release(*acl);
|
|
*acl = clone;
|
|
return err;
|
|
}
|
|
EXPORT_SYMBOL(__posix_acl_chmod);
|
|
|
|
/**
|
|
* posix_acl_chmod - chmod a posix acl
|
|
*
|
|
* @mnt_userns: user namespace of the mount @inode was found from
|
|
* @inode: inode to check permissions on
|
|
* @mode: the new mode of @inode
|
|
*
|
|
* If the inode has been found through an idmapped mount the user namespace of
|
|
* the vfsmount must be passed through @mnt_userns. This function will then
|
|
* take care to map the inode according to @mnt_userns before checking
|
|
* permissions. On non-idmapped mounts or if permission checking is to be
|
|
* performed on the raw inode simply passs init_user_ns.
|
|
*/
|
|
int
|
|
posix_acl_chmod(struct user_namespace *mnt_userns, struct inode *inode,
|
|
umode_t mode)
|
|
{
|
|
struct posix_acl *acl;
|
|
int ret = 0;
|
|
|
|
if (!IS_POSIXACL(inode))
|
|
return 0;
|
|
if (!inode->i_op->set_acl)
|
|
return -EOPNOTSUPP;
|
|
|
|
acl = get_acl(inode, ACL_TYPE_ACCESS);
|
|
if (IS_ERR_OR_NULL(acl)) {
|
|
if (acl == ERR_PTR(-EOPNOTSUPP))
|
|
return 0;
|
|
return PTR_ERR(acl);
|
|
}
|
|
|
|
ret = __posix_acl_chmod(&acl, GFP_KERNEL, mode);
|
|
if (ret)
|
|
return ret;
|
|
ret = inode->i_op->set_acl(mnt_userns, inode, acl, ACL_TYPE_ACCESS);
|
|
posix_acl_release(acl);
|
|
return ret;
|
|
}
|
|
EXPORT_SYMBOL(posix_acl_chmod);
|
|
|
|
int
|
|
posix_acl_create(struct inode *dir, umode_t *mode,
|
|
struct posix_acl **default_acl, struct posix_acl **acl)
|
|
{
|
|
struct posix_acl *p;
|
|
struct posix_acl *clone;
|
|
int ret;
|
|
|
|
*acl = NULL;
|
|
*default_acl = NULL;
|
|
|
|
if (S_ISLNK(*mode) || !IS_POSIXACL(dir))
|
|
return 0;
|
|
|
|
p = get_acl(dir, ACL_TYPE_DEFAULT);
|
|
if (!p || p == ERR_PTR(-EOPNOTSUPP)) {
|
|
*mode &= ~current_umask();
|
|
return 0;
|
|
}
|
|
if (IS_ERR(p))
|
|
return PTR_ERR(p);
|
|
|
|
ret = -ENOMEM;
|
|
clone = posix_acl_clone(p, GFP_NOFS);
|
|
if (!clone)
|
|
goto err_release;
|
|
|
|
ret = posix_acl_create_masq(clone, mode);
|
|
if (ret < 0)
|
|
goto err_release_clone;
|
|
|
|
if (ret == 0)
|
|
posix_acl_release(clone);
|
|
else
|
|
*acl = clone;
|
|
|
|
if (!S_ISDIR(*mode))
|
|
posix_acl_release(p);
|
|
else
|
|
*default_acl = p;
|
|
|
|
return 0;
|
|
|
|
err_release_clone:
|
|
posix_acl_release(clone);
|
|
err_release:
|
|
posix_acl_release(p);
|
|
return ret;
|
|
}
|
|
EXPORT_SYMBOL_GPL(posix_acl_create);
|
|
|
|
/**
|
|
* posix_acl_update_mode - update mode in set_acl
|
|
* @mnt_userns: user namespace of the mount @inode was found from
|
|
* @inode: target inode
|
|
* @mode_p: mode (pointer) for update
|
|
* @acl: acl pointer
|
|
*
|
|
* Update the file mode when setting an ACL: compute the new file permission
|
|
* bits based on the ACL. In addition, if the ACL is equivalent to the new
|
|
* file mode, set *@acl to NULL to indicate that no ACL should be set.
|
|
*
|
|
* As with chmod, clear the setgid bit if the caller is not in the owning group
|
|
* or capable of CAP_FSETID (see inode_change_ok).
|
|
*
|
|
* If the inode has been found through an idmapped mount the user namespace of
|
|
* the vfsmount must be passed through @mnt_userns. This function will then
|
|
* take care to map the inode according to @mnt_userns before checking
|
|
* permissions. On non-idmapped mounts or if permission checking is to be
|
|
* performed on the raw inode simply passs init_user_ns.
|
|
*
|
|
* Called from set_acl inode operations.
|
|
*/
|
|
int posix_acl_update_mode(struct user_namespace *mnt_userns,
|
|
struct inode *inode, umode_t *mode_p,
|
|
struct posix_acl **acl)
|
|
{
|
|
umode_t mode = inode->i_mode;
|
|
int error;
|
|
|
|
error = posix_acl_equiv_mode(*acl, &mode);
|
|
if (error < 0)
|
|
return error;
|
|
if (error == 0)
|
|
*acl = NULL;
|
|
if (!in_group_p(i_gid_into_mnt(mnt_userns, inode)) &&
|
|
!capable_wrt_inode_uidgid(mnt_userns, inode, CAP_FSETID))
|
|
mode &= ~S_ISGID;
|
|
*mode_p = mode;
|
|
return 0;
|
|
}
|
|
EXPORT_SYMBOL(posix_acl_update_mode);
|
|
|
|
/*
|
|
* Fix up the uids and gids in posix acl extended attributes in place.
|
|
*/
|
|
static int posix_acl_fix_xattr_common(void *value, size_t size)
|
|
{
|
|
struct posix_acl_xattr_header *header = value;
|
|
int count;
|
|
|
|
if (!header)
|
|
return -EINVAL;
|
|
if (size < sizeof(struct posix_acl_xattr_header))
|
|
return -EINVAL;
|
|
if (header->a_version != cpu_to_le32(POSIX_ACL_XATTR_VERSION))
|
|
return -EINVAL;
|
|
|
|
count = posix_acl_xattr_count(size);
|
|
if (count < 0)
|
|
return -EINVAL;
|
|
if (count == 0)
|
|
return -EINVAL;
|
|
|
|
return count;
|
|
}
|
|
|
|
void posix_acl_getxattr_idmapped_mnt(struct user_namespace *mnt_userns,
|
|
const struct inode *inode,
|
|
void *value, size_t size)
|
|
{
|
|
struct posix_acl_xattr_header *header = value;
|
|
struct posix_acl_xattr_entry *entry = (void *)(header + 1), *end;
|
|
int count;
|
|
vfsuid_t vfsuid;
|
|
vfsgid_t vfsgid;
|
|
kuid_t uid;
|
|
kgid_t gid;
|
|
|
|
if (no_idmapping(mnt_userns, i_user_ns(inode)))
|
|
return;
|
|
|
|
count = posix_acl_fix_xattr_common(value, size);
|
|
if (count < 0)
|
|
return;
|
|
|
|
for (end = entry + count; entry != end; entry++) {
|
|
switch (le16_to_cpu(entry->e_tag)) {
|
|
case ACL_USER:
|
|
uid = make_kuid(&init_user_ns, le32_to_cpu(entry->e_id));
|
|
vfsuid = make_vfsuid(mnt_userns, &init_user_ns, uid);
|
|
entry->e_id = cpu_to_le32(from_kuid(&init_user_ns,
|
|
vfsuid_into_kuid(vfsuid)));
|
|
break;
|
|
case ACL_GROUP:
|
|
gid = make_kgid(&init_user_ns, le32_to_cpu(entry->e_id));
|
|
vfsgid = make_vfsgid(mnt_userns, &init_user_ns, gid);
|
|
entry->e_id = cpu_to_le32(from_kgid(&init_user_ns,
|
|
vfsgid_into_kgid(vfsgid)));
|
|
break;
|
|
default:
|
|
break;
|
|
}
|
|
}
|
|
}
|
|
|
|
void posix_acl_setxattr_idmapped_mnt(struct user_namespace *mnt_userns,
|
|
const struct inode *inode,
|
|
void *value, size_t size)
|
|
{
|
|
struct posix_acl_xattr_header *header = value;
|
|
struct posix_acl_xattr_entry *entry = (void *)(header + 1), *end;
|
|
int count;
|
|
vfsuid_t vfsuid;
|
|
vfsgid_t vfsgid;
|
|
kuid_t uid;
|
|
kgid_t gid;
|
|
|
|
if (no_idmapping(mnt_userns, i_user_ns(inode)))
|
|
return;
|
|
|
|
count = posix_acl_fix_xattr_common(value, size);
|
|
if (count < 0)
|
|
return;
|
|
|
|
for (end = entry + count; entry != end; entry++) {
|
|
switch (le16_to_cpu(entry->e_tag)) {
|
|
case ACL_USER:
|
|
uid = make_kuid(&init_user_ns, le32_to_cpu(entry->e_id));
|
|
vfsuid = VFSUIDT_INIT(uid);
|
|
uid = from_vfsuid(mnt_userns, &init_user_ns, vfsuid);
|
|
entry->e_id = cpu_to_le32(from_kuid(&init_user_ns, uid));
|
|
break;
|
|
case ACL_GROUP:
|
|
gid = make_kgid(&init_user_ns, le32_to_cpu(entry->e_id));
|
|
vfsgid = VFSGIDT_INIT(gid);
|
|
gid = from_vfsgid(mnt_userns, &init_user_ns, vfsgid);
|
|
entry->e_id = cpu_to_le32(from_kgid(&init_user_ns, gid));
|
|
break;
|
|
default:
|
|
break;
|
|
}
|
|
}
|
|
}
|
|
|
|
static void posix_acl_fix_xattr_userns(
|
|
struct user_namespace *to, struct user_namespace *from,
|
|
void *value, size_t size)
|
|
{
|
|
struct posix_acl_xattr_header *header = value;
|
|
struct posix_acl_xattr_entry *entry = (void *)(header + 1), *end;
|
|
int count;
|
|
kuid_t uid;
|
|
kgid_t gid;
|
|
|
|
count = posix_acl_fix_xattr_common(value, size);
|
|
if (count < 0)
|
|
return;
|
|
|
|
for (end = entry + count; entry != end; entry++) {
|
|
switch(le16_to_cpu(entry->e_tag)) {
|
|
case ACL_USER:
|
|
uid = make_kuid(from, le32_to_cpu(entry->e_id));
|
|
entry->e_id = cpu_to_le32(from_kuid(to, uid));
|
|
break;
|
|
case ACL_GROUP:
|
|
gid = make_kgid(from, le32_to_cpu(entry->e_id));
|
|
entry->e_id = cpu_to_le32(from_kgid(to, gid));
|
|
break;
|
|
default:
|
|
break;
|
|
}
|
|
}
|
|
}
|
|
|
|
void posix_acl_fix_xattr_from_user(void *value, size_t size)
|
|
{
|
|
struct user_namespace *user_ns = current_user_ns();
|
|
if (user_ns == &init_user_ns)
|
|
return;
|
|
posix_acl_fix_xattr_userns(&init_user_ns, user_ns, value, size);
|
|
}
|
|
|
|
void posix_acl_fix_xattr_to_user(void *value, size_t size)
|
|
{
|
|
struct user_namespace *user_ns = current_user_ns();
|
|
if (user_ns == &init_user_ns)
|
|
return;
|
|
posix_acl_fix_xattr_userns(user_ns, &init_user_ns, value, size);
|
|
}
|
|
|
|
/*
|
|
* Convert from extended attribute to in-memory representation.
|
|
*/
|
|
struct posix_acl *
|
|
posix_acl_from_xattr(struct user_namespace *user_ns,
|
|
const void *value, size_t size)
|
|
{
|
|
const struct posix_acl_xattr_header *header = value;
|
|
const struct posix_acl_xattr_entry *entry = (const void *)(header + 1), *end;
|
|
int count;
|
|
struct posix_acl *acl;
|
|
struct posix_acl_entry *acl_e;
|
|
|
|
if (!value)
|
|
return NULL;
|
|
if (size < sizeof(struct posix_acl_xattr_header))
|
|
return ERR_PTR(-EINVAL);
|
|
if (header->a_version != cpu_to_le32(POSIX_ACL_XATTR_VERSION))
|
|
return ERR_PTR(-EOPNOTSUPP);
|
|
|
|
count = posix_acl_xattr_count(size);
|
|
if (count < 0)
|
|
return ERR_PTR(-EINVAL);
|
|
if (count == 0)
|
|
return NULL;
|
|
|
|
acl = posix_acl_alloc(count, GFP_NOFS);
|
|
if (!acl)
|
|
return ERR_PTR(-ENOMEM);
|
|
acl_e = acl->a_entries;
|
|
|
|
for (end = entry + count; entry != end; acl_e++, entry++) {
|
|
acl_e->e_tag = le16_to_cpu(entry->e_tag);
|
|
acl_e->e_perm = le16_to_cpu(entry->e_perm);
|
|
|
|
switch(acl_e->e_tag) {
|
|
case ACL_USER_OBJ:
|
|
case ACL_GROUP_OBJ:
|
|
case ACL_MASK:
|
|
case ACL_OTHER:
|
|
break;
|
|
|
|
case ACL_USER:
|
|
acl_e->e_uid =
|
|
make_kuid(user_ns,
|
|
le32_to_cpu(entry->e_id));
|
|
if (!uid_valid(acl_e->e_uid))
|
|
goto fail;
|
|
break;
|
|
case ACL_GROUP:
|
|
acl_e->e_gid =
|
|
make_kgid(user_ns,
|
|
le32_to_cpu(entry->e_id));
|
|
if (!gid_valid(acl_e->e_gid))
|
|
goto fail;
|
|
break;
|
|
|
|
default:
|
|
goto fail;
|
|
}
|
|
}
|
|
return acl;
|
|
|
|
fail:
|
|
posix_acl_release(acl);
|
|
return ERR_PTR(-EINVAL);
|
|
}
|
|
EXPORT_SYMBOL (posix_acl_from_xattr);
|
|
|
|
/*
|
|
* Convert from in-memory to extended attribute representation.
|
|
*/
|
|
int
|
|
posix_acl_to_xattr(struct user_namespace *user_ns, const struct posix_acl *acl,
|
|
void *buffer, size_t size)
|
|
{
|
|
struct posix_acl_xattr_header *ext_acl = buffer;
|
|
struct posix_acl_xattr_entry *ext_entry;
|
|
int real_size, n;
|
|
|
|
real_size = posix_acl_xattr_size(acl->a_count);
|
|
if (!buffer)
|
|
return real_size;
|
|
if (real_size > size)
|
|
return -ERANGE;
|
|
|
|
ext_entry = (void *)(ext_acl + 1);
|
|
ext_acl->a_version = cpu_to_le32(POSIX_ACL_XATTR_VERSION);
|
|
|
|
for (n=0; n < acl->a_count; n++, ext_entry++) {
|
|
const struct posix_acl_entry *acl_e = &acl->a_entries[n];
|
|
ext_entry->e_tag = cpu_to_le16(acl_e->e_tag);
|
|
ext_entry->e_perm = cpu_to_le16(acl_e->e_perm);
|
|
switch(acl_e->e_tag) {
|
|
case ACL_USER:
|
|
ext_entry->e_id =
|
|
cpu_to_le32(from_kuid(user_ns, acl_e->e_uid));
|
|
break;
|
|
case ACL_GROUP:
|
|
ext_entry->e_id =
|
|
cpu_to_le32(from_kgid(user_ns, acl_e->e_gid));
|
|
break;
|
|
default:
|
|
ext_entry->e_id = cpu_to_le32(ACL_UNDEFINED_ID);
|
|
break;
|
|
}
|
|
}
|
|
return real_size;
|
|
}
|
|
EXPORT_SYMBOL (posix_acl_to_xattr);
|
|
|
|
static int
|
|
posix_acl_xattr_get(const struct xattr_handler *handler,
|
|
struct dentry *unused, struct inode *inode,
|
|
const char *name, void *value, size_t size)
|
|
{
|
|
struct posix_acl *acl;
|
|
int error;
|
|
|
|
if (!IS_POSIXACL(inode))
|
|
return -EOPNOTSUPP;
|
|
if (S_ISLNK(inode->i_mode))
|
|
return -EOPNOTSUPP;
|
|
|
|
acl = get_acl(inode, handler->flags);
|
|
if (IS_ERR(acl))
|
|
return PTR_ERR(acl);
|
|
if (acl == NULL)
|
|
return -ENODATA;
|
|
|
|
error = posix_acl_to_xattr(&init_user_ns, acl, value, size);
|
|
posix_acl_release(acl);
|
|
|
|
return error;
|
|
}
|
|
|
|
int
|
|
set_posix_acl(struct user_namespace *mnt_userns, struct inode *inode,
|
|
int type, struct posix_acl *acl)
|
|
{
|
|
if (!IS_POSIXACL(inode))
|
|
return -EOPNOTSUPP;
|
|
if (!inode->i_op->set_acl)
|
|
return -EOPNOTSUPP;
|
|
|
|
if (type == ACL_TYPE_DEFAULT && !S_ISDIR(inode->i_mode))
|
|
return acl ? -EACCES : 0;
|
|
if (!inode_owner_or_capable(mnt_userns, inode))
|
|
return -EPERM;
|
|
|
|
if (acl) {
|
|
int ret = posix_acl_valid(inode->i_sb->s_user_ns, acl);
|
|
if (ret)
|
|
return ret;
|
|
}
|
|
return inode->i_op->set_acl(mnt_userns, inode, acl, type);
|
|
}
|
|
EXPORT_SYMBOL(set_posix_acl);
|
|
|
|
static int
|
|
posix_acl_xattr_set(const struct xattr_handler *handler,
|
|
struct user_namespace *mnt_userns,
|
|
struct dentry *unused, struct inode *inode,
|
|
const char *name, const void *value, size_t size,
|
|
int flags)
|
|
{
|
|
struct posix_acl *acl = NULL;
|
|
int ret;
|
|
|
|
if (value) {
|
|
acl = posix_acl_from_xattr(&init_user_ns, value, size);
|
|
if (IS_ERR(acl))
|
|
return PTR_ERR(acl);
|
|
}
|
|
ret = set_posix_acl(mnt_userns, inode, handler->flags, acl);
|
|
posix_acl_release(acl);
|
|
return ret;
|
|
}
|
|
|
|
static bool
|
|
posix_acl_xattr_list(struct dentry *dentry)
|
|
{
|
|
return IS_POSIXACL(d_backing_inode(dentry));
|
|
}
|
|
|
|
const struct xattr_handler posix_acl_access_xattr_handler = {
|
|
.name = XATTR_NAME_POSIX_ACL_ACCESS,
|
|
.flags = ACL_TYPE_ACCESS,
|
|
.list = posix_acl_xattr_list,
|
|
.get = posix_acl_xattr_get,
|
|
.set = posix_acl_xattr_set,
|
|
};
|
|
EXPORT_SYMBOL_GPL(posix_acl_access_xattr_handler);
|
|
|
|
const struct xattr_handler posix_acl_default_xattr_handler = {
|
|
.name = XATTR_NAME_POSIX_ACL_DEFAULT,
|
|
.flags = ACL_TYPE_DEFAULT,
|
|
.list = posix_acl_xattr_list,
|
|
.get = posix_acl_xattr_get,
|
|
.set = posix_acl_xattr_set,
|
|
};
|
|
EXPORT_SYMBOL_GPL(posix_acl_default_xattr_handler);
|
|
|
|
int simple_set_acl(struct user_namespace *mnt_userns, struct inode *inode,
|
|
struct posix_acl *acl, int type)
|
|
{
|
|
int error;
|
|
|
|
if (type == ACL_TYPE_ACCESS) {
|
|
error = posix_acl_update_mode(mnt_userns, inode,
|
|
&inode->i_mode, &acl);
|
|
if (error)
|
|
return error;
|
|
}
|
|
|
|
inode->i_ctime = current_time(inode);
|
|
set_cached_acl(inode, type, acl);
|
|
return 0;
|
|
}
|
|
|
|
int simple_acl_create(struct inode *dir, struct inode *inode)
|
|
{
|
|
struct posix_acl *default_acl, *acl;
|
|
int error;
|
|
|
|
error = posix_acl_create(dir, &inode->i_mode, &default_acl, &acl);
|
|
if (error)
|
|
return error;
|
|
|
|
set_cached_acl(inode, ACL_TYPE_DEFAULT, default_acl);
|
|
set_cached_acl(inode, ACL_TYPE_ACCESS, acl);
|
|
|
|
if (default_acl)
|
|
posix_acl_release(default_acl);
|
|
if (acl)
|
|
posix_acl_release(acl);
|
|
return 0;
|
|
}
|