OpenCloudOS-Kernel/fs/posix_acl.c

1094 lines
26 KiB
C
Raw Normal View History

// 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);
posix_acl: Inode acl caching fixes When get_acl() is called for an inode whose ACL is not cached yet, the get_acl inode operation is called to fetch the ACL from the filesystem. The inode operation is responsible for updating the cached acl with set_cached_acl(). This is done without locking at the VFS level, so another task can call set_cached_acl() or forget_cached_acl() before the get_acl inode operation gets to calling set_cached_acl(), and then get_acl's call to set_cached_acl() results in caching an outdate ACL. Prevent this from happening by setting the cached ACL pointer to a task-specific sentinel value before calling the get_acl inode operation. Move the responsibility for updating the cached ACL from the get_acl inode operations to get_acl(). There, only set the cached ACL if the sentinel value hasn't changed. The sentinel values are chosen to have odd values. Likewise, the value of ACL_NOT_CACHED is odd. In contrast, ACL object pointers always have an even value (ACLs are aligned in memory). This allows to distinguish uncached ACLs values from ACL objects. In addition, switch from guarding inode->i_acl and inode->i_default_acl upates by the inode->i_lock spinlock to using xchg() and cmpxchg(). Filesystems that do not want ACLs returned from their get_acl inode operations to be cached must call forget_cached_acl() to prevent the VFS from doing so. (Patch written by Al Viro and Andreas Gruenbacher.) Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2016-03-24 21:38:37 +08:00
struct posix_acl *acl;
for (;;) {
rcu_read_lock();
acl = rcu_dereference(*p);
if (!acl || is_uncached_acl(acl) ||
posix_acl: convert posix_acl.a_refcount from atomic_t to refcount_t atomic_t variables are currently used to implement reference counters with the following properties: - counter is initialized to 1 using atomic_set() - a resource is freed upon counter reaching zero - once counter reaches zero, its further increments aren't allowed - counter schema uses basic atomic operations (set, inc, inc_not_zero, dec_and_test, etc.) Such atomic variables should be converted to a newly provided refcount_t type and API that prevents accidental counter overflows and underflows. This is important since overflows and underflows can lead to use-after-free situation and be exploitable. The variable posix_acl.a_refcount is used as pure reference counter. Convert it to refcount_t and fix up the operations. **Important note for maintainers: Some functions from refcount_t API defined in lib/refcount.c have different memory ordering guarantees than their atomic counterparts. The full comparison can be seen in https://lkml.org/lkml/2017/11/15/57 and it is hopefully soon in state to be merged to the documentation tree. Normally the differences should not matter since refcount_t provides enough guarantees to satisfy the refcounting use cases, but in some rare cases it might matter. Please double check that you don't have some undocumented memory guarantees for this variable usage. For the posix_acl.a_refcount it might make a difference in following places: - get_cached_acl(): increment in refcount_inc_not_zero() only guarantees control dependency on success vs. fully ordered atomic counterpart. However this operation is performed under rcu_read_lock(), so this should be fine. - posix_acl_release(): decrement in refcount_dec_and_test() only provides RELEASE ordering and control dependency on success vs. fully ordered atomic counterpart Suggested-by: Kees Cook <keescook@chromium.org> Reviewed-by: David Windsor <dwindsor@gmail.com> Reviewed-by: Hans Liljestrand <ishkamiel@gmail.com> Signed-off-by: Elena Reshetova <elena.reshetova@intel.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2017-11-29 19:19:31 +08:00
refcount_inc_not_zero(&acl->a_refcount))
posix_acl: Inode acl caching fixes When get_acl() is called for an inode whose ACL is not cached yet, the get_acl inode operation is called to fetch the ACL from the filesystem. The inode operation is responsible for updating the cached acl with set_cached_acl(). This is done without locking at the VFS level, so another task can call set_cached_acl() or forget_cached_acl() before the get_acl inode operation gets to calling set_cached_acl(), and then get_acl's call to set_cached_acl() results in caching an outdate ACL. Prevent this from happening by setting the cached ACL pointer to a task-specific sentinel value before calling the get_acl inode operation. Move the responsibility for updating the cached ACL from the get_acl inode operations to get_acl(). There, only set the cached ACL if the sentinel value hasn't changed. The sentinel values are chosen to have odd values. Likewise, the value of ACL_NOT_CACHED is odd. In contrast, ACL object pointers always have an even value (ACLs are aligned in memory). This allows to distinguish uncached ACLs values from ACL objects. In addition, switch from guarding inode->i_acl and inode->i_default_acl upates by the inode->i_lock spinlock to using xchg() and cmpxchg(). Filesystems that do not want ACLs returned from their get_acl inode operations to be cached must call forget_cached_acl() to prevent the VFS from doing so. (Patch written by Al Viro and Andreas Gruenbacher.) Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2016-03-24 21:38:37 +08:00
break;
rcu_read_unlock();
cpu_relax();
}
posix_acl: Inode acl caching fixes When get_acl() is called for an inode whose ACL is not cached yet, the get_acl inode operation is called to fetch the ACL from the filesystem. The inode operation is responsible for updating the cached acl with set_cached_acl(). This is done without locking at the VFS level, so another task can call set_cached_acl() or forget_cached_acl() before the get_acl inode operation gets to calling set_cached_acl(), and then get_acl's call to set_cached_acl() results in caching an outdate ACL. Prevent this from happening by setting the cached ACL pointer to a task-specific sentinel value before calling the get_acl inode operation. Move the responsibility for updating the cached ACL from the get_acl inode operations to get_acl(). There, only set the cached ACL if the sentinel value hasn't changed. The sentinel values are chosen to have odd values. Likewise, the value of ACL_NOT_CACHED is odd. In contrast, ACL object pointers always have an even value (ACLs are aligned in memory). This allows to distinguish uncached ACLs values from ACL objects. In addition, switch from guarding inode->i_acl and inode->i_default_acl upates by the inode->i_lock spinlock to using xchg() and cmpxchg(). Filesystems that do not want ACLs returned from their get_acl inode operations to be cached must call forget_cached_acl() to prevent the VFS from doing so. (Patch written by Al Viro and Andreas Gruenbacher.) Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2016-03-24 21:38:37 +08:00
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;
posix_acl: Inode acl caching fixes When get_acl() is called for an inode whose ACL is not cached yet, the get_acl inode operation is called to fetch the ACL from the filesystem. The inode operation is responsible for updating the cached acl with set_cached_acl(). This is done without locking at the VFS level, so another task can call set_cached_acl() or forget_cached_acl() before the get_acl inode operation gets to calling set_cached_acl(), and then get_acl's call to set_cached_acl() results in caching an outdate ACL. Prevent this from happening by setting the cached ACL pointer to a task-specific sentinel value before calling the get_acl inode operation. Move the responsibility for updating the cached ACL from the get_acl inode operations to get_acl(). There, only set the cached ACL if the sentinel value hasn't changed. The sentinel values are chosen to have odd values. Likewise, the value of ACL_NOT_CACHED is odd. In contrast, ACL object pointers always have an even value (ACLs are aligned in memory). This allows to distinguish uncached ACLs values from ACL objects. In addition, switch from guarding inode->i_acl and inode->i_default_acl upates by the inode->i_lock spinlock to using xchg() and cmpxchg(). Filesystems that do not want ACLs returned from their get_acl inode operations to be cached must call forget_cached_acl() to prevent the VFS from doing so. (Patch written by Al Viro and Andreas Gruenbacher.) Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2016-03-24 21:38:37 +08:00
old = xchg(p, posix_acl_dup(acl));
if (!is_uncached_acl(old))
posix_acl_release(old);
}
EXPORT_SYMBOL(set_cached_acl);
posix_acl: Inode acl caching fixes When get_acl() is called for an inode whose ACL is not cached yet, the get_acl inode operation is called to fetch the ACL from the filesystem. The inode operation is responsible for updating the cached acl with set_cached_acl(). This is done without locking at the VFS level, so another task can call set_cached_acl() or forget_cached_acl() before the get_acl inode operation gets to calling set_cached_acl(), and then get_acl's call to set_cached_acl() results in caching an outdate ACL. Prevent this from happening by setting the cached ACL pointer to a task-specific sentinel value before calling the get_acl inode operation. Move the responsibility for updating the cached ACL from the get_acl inode operations to get_acl(). There, only set the cached ACL if the sentinel value hasn't changed. The sentinel values are chosen to have odd values. Likewise, the value of ACL_NOT_CACHED is odd. In contrast, ACL object pointers always have an even value (ACLs are aligned in memory). This allows to distinguish uncached ACLs values from ACL objects. In addition, switch from guarding inode->i_acl and inode->i_default_acl upates by the inode->i_lock spinlock to using xchg() and cmpxchg(). Filesystems that do not want ACLs returned from their get_acl inode operations to be cached must call forget_cached_acl() to prevent the VFS from doing so. (Patch written by Al Viro and Andreas Gruenbacher.) Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2016-03-24 21:38:37 +08:00
static void __forget_cached_acl(struct posix_acl **p)
{
struct posix_acl *old;
posix_acl: Inode acl caching fixes When get_acl() is called for an inode whose ACL is not cached yet, the get_acl inode operation is called to fetch the ACL from the filesystem. The inode operation is responsible for updating the cached acl with set_cached_acl(). This is done without locking at the VFS level, so another task can call set_cached_acl() or forget_cached_acl() before the get_acl inode operation gets to calling set_cached_acl(), and then get_acl's call to set_cached_acl() results in caching an outdate ACL. Prevent this from happening by setting the cached ACL pointer to a task-specific sentinel value before calling the get_acl inode operation. Move the responsibility for updating the cached ACL from the get_acl inode operations to get_acl(). There, only set the cached ACL if the sentinel value hasn't changed. The sentinel values are chosen to have odd values. Likewise, the value of ACL_NOT_CACHED is odd. In contrast, ACL object pointers always have an even value (ACLs are aligned in memory). This allows to distinguish uncached ACLs values from ACL objects. In addition, switch from guarding inode->i_acl and inode->i_default_acl upates by the inode->i_lock spinlock to using xchg() and cmpxchg(). Filesystems that do not want ACLs returned from their get_acl inode operations to be cached must call forget_cached_acl() to prevent the VFS from doing so. (Patch written by Al Viro and Andreas Gruenbacher.) Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2016-03-24 21:38:37 +08:00
old = xchg(p, ACL_NOT_CACHED);
if (!is_uncached_acl(old))
posix_acl_release(old);
}
posix_acl: Inode acl caching fixes When get_acl() is called for an inode whose ACL is not cached yet, the get_acl inode operation is called to fetch the ACL from the filesystem. The inode operation is responsible for updating the cached acl with set_cached_acl(). This is done without locking at the VFS level, so another task can call set_cached_acl() or forget_cached_acl() before the get_acl inode operation gets to calling set_cached_acl(), and then get_acl's call to set_cached_acl() results in caching an outdate ACL. Prevent this from happening by setting the cached ACL pointer to a task-specific sentinel value before calling the get_acl inode operation. Move the responsibility for updating the cached ACL from the get_acl inode operations to get_acl(). There, only set the cached ACL if the sentinel value hasn't changed. The sentinel values are chosen to have odd values. Likewise, the value of ACL_NOT_CACHED is odd. In contrast, ACL object pointers always have an even value (ACLs are aligned in memory). This allows to distinguish uncached ACLs values from ACL objects. In addition, switch from guarding inode->i_acl and inode->i_default_acl upates by the inode->i_lock spinlock to using xchg() and cmpxchg(). Filesystems that do not want ACLs returned from their get_acl inode operations to be cached must call forget_cached_acl() to prevent the VFS from doing so. (Patch written by Al Viro and Andreas Gruenbacher.) Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2016-03-24 21:38:37 +08:00
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)
{
posix_acl: Inode acl caching fixes When get_acl() is called for an inode whose ACL is not cached yet, the get_acl inode operation is called to fetch the ACL from the filesystem. The inode operation is responsible for updating the cached acl with set_cached_acl(). This is done without locking at the VFS level, so another task can call set_cached_acl() or forget_cached_acl() before the get_acl inode operation gets to calling set_cached_acl(), and then get_acl's call to set_cached_acl() results in caching an outdate ACL. Prevent this from happening by setting the cached ACL pointer to a task-specific sentinel value before calling the get_acl inode operation. Move the responsibility for updating the cached ACL from the get_acl inode operations to get_acl(). There, only set the cached ACL if the sentinel value hasn't changed. The sentinel values are chosen to have odd values. Likewise, the value of ACL_NOT_CACHED is odd. In contrast, ACL object pointers always have an even value (ACLs are aligned in memory). This allows to distinguish uncached ACLs values from ACL objects. In addition, switch from guarding inode->i_acl and inode->i_default_acl upates by the inode->i_lock spinlock to using xchg() and cmpxchg(). Filesystems that do not want ACLs returned from their get_acl inode operations to be cached must call forget_cached_acl() to prevent the VFS from doing so. (Patch written by Al Viro and Andreas Gruenbacher.) Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2016-03-24 21:38:37 +08:00
__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)
{
posix_acl: Inode acl caching fixes When get_acl() is called for an inode whose ACL is not cached yet, the get_acl inode operation is called to fetch the ACL from the filesystem. The inode operation is responsible for updating the cached acl with set_cached_acl(). This is done without locking at the VFS level, so another task can call set_cached_acl() or forget_cached_acl() before the get_acl inode operation gets to calling set_cached_acl(), and then get_acl's call to set_cached_acl() results in caching an outdate ACL. Prevent this from happening by setting the cached ACL pointer to a task-specific sentinel value before calling the get_acl inode operation. Move the responsibility for updating the cached ACL from the get_acl inode operations to get_acl(). There, only set the cached ACL if the sentinel value hasn't changed. The sentinel values are chosen to have odd values. Likewise, the value of ACL_NOT_CACHED is odd. In contrast, ACL object pointers always have an even value (ACLs are aligned in memory). This allows to distinguish uncached ACLs values from ACL objects. In addition, switch from guarding inode->i_acl and inode->i_default_acl upates by the inode->i_lock spinlock to using xchg() and cmpxchg(). Filesystems that do not want ACLs returned from their get_acl inode operations to be cached must call forget_cached_acl() to prevent the VFS from doing so. (Patch written by Al Viro and Andreas Gruenbacher.) Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2016-03-24 21:38:37 +08:00
void *sentinel;
struct posix_acl **p;
struct posix_acl *acl;
posix_acl: Inode acl caching fixes When get_acl() is called for an inode whose ACL is not cached yet, the get_acl inode operation is called to fetch the ACL from the filesystem. The inode operation is responsible for updating the cached acl with set_cached_acl(). This is done without locking at the VFS level, so another task can call set_cached_acl() or forget_cached_acl() before the get_acl inode operation gets to calling set_cached_acl(), and then get_acl's call to set_cached_acl() results in caching an outdate ACL. Prevent this from happening by setting the cached ACL pointer to a task-specific sentinel value before calling the get_acl inode operation. Move the responsibility for updating the cached ACL from the get_acl inode operations to get_acl(). There, only set the cached ACL if the sentinel value hasn't changed. The sentinel values are chosen to have odd values. Likewise, the value of ACL_NOT_CACHED is odd. In contrast, ACL object pointers always have an even value (ACLs are aligned in memory). This allows to distinguish uncached ACLs values from ACL objects. In addition, switch from guarding inode->i_acl and inode->i_default_acl upates by the inode->i_lock spinlock to using xchg() and cmpxchg(). Filesystems that do not want ACLs returned from their get_acl inode operations to be cached must call forget_cached_acl() to prevent the VFS from doing so. (Patch written by Al Viro and Andreas Gruenbacher.) Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2016-03-24 21:38:37 +08:00
/*
* 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);
posix_acl: Inode acl caching fixes When get_acl() is called for an inode whose ACL is not cached yet, the get_acl inode operation is called to fetch the ACL from the filesystem. The inode operation is responsible for updating the cached acl with set_cached_acl(). This is done without locking at the VFS level, so another task can call set_cached_acl() or forget_cached_acl() before the get_acl inode operation gets to calling set_cached_acl(), and then get_acl's call to set_cached_acl() results in caching an outdate ACL. Prevent this from happening by setting the cached ACL pointer to a task-specific sentinel value before calling the get_acl inode operation. Move the responsibility for updating the cached ACL from the get_acl inode operations to get_acl(). There, only set the cached ACL if the sentinel value hasn't changed. The sentinel values are chosen to have odd values. Likewise, the value of ACL_NOT_CACHED is odd. In contrast, ACL object pointers always have an even value (ACLs are aligned in memory). This allows to distinguish uncached ACLs values from ACL objects. In addition, switch from guarding inode->i_acl and inode->i_default_acl upates by the inode->i_lock spinlock to using xchg() and cmpxchg(). Filesystems that do not want ACLs returned from their get_acl inode operations to be cached must call forget_cached_acl() to prevent the VFS from doing so. (Patch written by Al Viro and Andreas Gruenbacher.) Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2016-03-24 21:38:37 +08:00
if (!is_uncached_acl(acl))
return acl;
if (!IS_POSIXACL(inode))
return NULL;
posix_acl: Inode acl caching fixes When get_acl() is called for an inode whose ACL is not cached yet, the get_acl inode operation is called to fetch the ACL from the filesystem. The inode operation is responsible for updating the cached acl with set_cached_acl(). This is done without locking at the VFS level, so another task can call set_cached_acl() or forget_cached_acl() before the get_acl inode operation gets to calling set_cached_acl(), and then get_acl's call to set_cached_acl() results in caching an outdate ACL. Prevent this from happening by setting the cached ACL pointer to a task-specific sentinel value before calling the get_acl inode operation. Move the responsibility for updating the cached ACL from the get_acl inode operations to get_acl(). There, only set the cached ACL if the sentinel value hasn't changed. The sentinel values are chosen to have odd values. Likewise, the value of ACL_NOT_CACHED is odd. In contrast, ACL object pointers always have an even value (ACLs are aligned in memory). This allows to distinguish uncached ACLs values from ACL objects. In addition, switch from guarding inode->i_acl and inode->i_default_acl upates by the inode->i_lock spinlock to using xchg() and cmpxchg(). Filesystems that do not want ACLs returned from their get_acl inode operations to be cached must call forget_cached_acl() to prevent the VFS from doing so. (Patch written by Al Viro and Andreas Gruenbacher.) Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2016-03-24 21:38:37 +08:00
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);
posix_acl: Inode acl caching fixes When get_acl() is called for an inode whose ACL is not cached yet, the get_acl inode operation is called to fetch the ACL from the filesystem. The inode operation is responsible for updating the cached acl with set_cached_acl(). This is done without locking at the VFS level, so another task can call set_cached_acl() or forget_cached_acl() before the get_acl inode operation gets to calling set_cached_acl(), and then get_acl's call to set_cached_acl() results in caching an outdate ACL. Prevent this from happening by setting the cached ACL pointer to a task-specific sentinel value before calling the get_acl inode operation. Move the responsibility for updating the cached ACL from the get_acl inode operations to get_acl(). There, only set the cached ACL if the sentinel value hasn't changed. The sentinel values are chosen to have odd values. Likewise, the value of ACL_NOT_CACHED is odd. In contrast, ACL object pointers always have an even value (ACLs are aligned in memory). This allows to distinguish uncached ACLs values from ACL objects. In addition, switch from guarding inode->i_acl and inode->i_default_acl upates by the inode->i_lock spinlock to using xchg() and cmpxchg(). Filesystems that do not want ACLs returned from their get_acl inode operations to be cached must call forget_cached_acl() to prevent the VFS from doing so. (Patch written by Al Viro and Andreas Gruenbacher.) Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2016-03-24 21:38:37 +08:00
/*
posix_acl: Inode acl caching fixes When get_acl() is called for an inode whose ACL is not cached yet, the get_acl inode operation is called to fetch the ACL from the filesystem. The inode operation is responsible for updating the cached acl with set_cached_acl(). This is done without locking at the VFS level, so another task can call set_cached_acl() or forget_cached_acl() before the get_acl inode operation gets to calling set_cached_acl(), and then get_acl's call to set_cached_acl() results in caching an outdate ACL. Prevent this from happening by setting the cached ACL pointer to a task-specific sentinel value before calling the get_acl inode operation. Move the responsibility for updating the cached ACL from the get_acl inode operations to get_acl(). There, only set the cached ACL if the sentinel value hasn't changed. The sentinel values are chosen to have odd values. Likewise, the value of ACL_NOT_CACHED is odd. In contrast, ACL object pointers always have an even value (ACLs are aligned in memory). This allows to distinguish uncached ACLs values from ACL objects. In addition, switch from guarding inode->i_acl and inode->i_default_acl upates by the inode->i_lock spinlock to using xchg() and cmpxchg(). Filesystems that do not want ACLs returned from their get_acl inode operations to be cached must call forget_cached_acl() to prevent the VFS from doing so. (Patch written by Al Viro and Andreas Gruenbacher.) Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2016-03-24 21:38:37 +08:00
* 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);
posix_acl: Inode acl caching fixes When get_acl() is called for an inode whose ACL is not cached yet, the get_acl inode operation is called to fetch the ACL from the filesystem. The inode operation is responsible for updating the cached acl with set_cached_acl(). This is done without locking at the VFS level, so another task can call set_cached_acl() or forget_cached_acl() before the get_acl inode operation gets to calling set_cached_acl(), and then get_acl's call to set_cached_acl() results in caching an outdate ACL. Prevent this from happening by setting the cached ACL pointer to a task-specific sentinel value before calling the get_acl inode operation. Move the responsibility for updating the cached ACL from the get_acl inode operations to get_acl(). There, only set the cached ACL if the sentinel value hasn't changed. The sentinel values are chosen to have odd values. Likewise, the value of ACL_NOT_CACHED is odd. In contrast, ACL object pointers always have an even value (ACLs are aligned in memory). This allows to distinguish uncached ACLs values from ACL objects. In addition, switch from guarding inode->i_acl and inode->i_default_acl upates by the inode->i_lock spinlock to using xchg() and cmpxchg(). Filesystems that do not want ACLs returned from their get_acl inode operations to be cached must call forget_cached_acl() to prevent the VFS from doing so. (Patch written by Al Viro and Andreas Gruenbacher.) Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2016-03-24 21:38:37 +08:00
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)
{
posix_acl: convert posix_acl.a_refcount from atomic_t to refcount_t atomic_t variables are currently used to implement reference counters with the following properties: - counter is initialized to 1 using atomic_set() - a resource is freed upon counter reaching zero - once counter reaches zero, its further increments aren't allowed - counter schema uses basic atomic operations (set, inc, inc_not_zero, dec_and_test, etc.) Such atomic variables should be converted to a newly provided refcount_t type and API that prevents accidental counter overflows and underflows. This is important since overflows and underflows can lead to use-after-free situation and be exploitable. The variable posix_acl.a_refcount is used as pure reference counter. Convert it to refcount_t and fix up the operations. **Important note for maintainers: Some functions from refcount_t API defined in lib/refcount.c have different memory ordering guarantees than their atomic counterparts. The full comparison can be seen in https://lkml.org/lkml/2017/11/15/57 and it is hopefully soon in state to be merged to the documentation tree. Normally the differences should not matter since refcount_t provides enough guarantees to satisfy the refcounting use cases, but in some rare cases it might matter. Please double check that you don't have some undocumented memory guarantees for this variable usage. For the posix_acl.a_refcount it might make a difference in following places: - get_cached_acl(): increment in refcount_inc_not_zero() only guarantees control dependency on success vs. fully ordered atomic counterpart. However this operation is performed under rcu_read_lock(), so this should be fine. - posix_acl_release(): decrement in refcount_dec_and_test() only provides RELEASE ordering and control dependency on success vs. fully ordered atomic counterpart Suggested-by: Kees Cook <keescook@chromium.org> Reviewed-by: David Windsor <dwindsor@gmail.com> Reviewed-by: Hans Liljestrand <ishkamiel@gmail.com> Signed-off-by: Elena Reshetova <elena.reshetova@intel.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2017-11-29 19:19:31 +08:00
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)
posix_acl: convert posix_acl.a_refcount from atomic_t to refcount_t atomic_t variables are currently used to implement reference counters with the following properties: - counter is initialized to 1 using atomic_set() - a resource is freed upon counter reaching zero - once counter reaches zero, its further increments aren't allowed - counter schema uses basic atomic operations (set, inc, inc_not_zero, dec_and_test, etc.) Such atomic variables should be converted to a newly provided refcount_t type and API that prevents accidental counter overflows and underflows. This is important since overflows and underflows can lead to use-after-free situation and be exploitable. The variable posix_acl.a_refcount is used as pure reference counter. Convert it to refcount_t and fix up the operations. **Important note for maintainers: Some functions from refcount_t API defined in lib/refcount.c have different memory ordering guarantees than their atomic counterparts. The full comparison can be seen in https://lkml.org/lkml/2017/11/15/57 and it is hopefully soon in state to be merged to the documentation tree. Normally the differences should not matter since refcount_t provides enough guarantees to satisfy the refcounting use cases, but in some rare cases it might matter. Please double check that you don't have some undocumented memory guarantees for this variable usage. For the posix_acl.a_refcount it might make a difference in following places: - get_cached_acl(): increment in refcount_inc_not_zero() only guarantees control dependency on success vs. fully ordered atomic counterpart. However this operation is performed under rcu_read_lock(), so this should be fine. - posix_acl_release(): decrement in refcount_dec_and_test() only provides RELEASE ordering and control dependency on success vs. fully ordered atomic counterpart Suggested-by: Kees Cook <keescook@chromium.org> Reviewed-by: David Windsor <dwindsor@gmail.com> Reviewed-by: Hans Liljestrand <ishkamiel@gmail.com> Signed-off-by: Elena Reshetova <elena.reshetova@intel.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2017-11-29 19:19:31 +08:00
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))
2012-02-08 10:52:57 +08:00
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;
vfsuid_t vfsuid;
vfsgid_t vfsgid;
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) */
vfsuid = i_uid_into_vfsuid(mnt_userns, inode);
if (vfsuid_eq_kuid(vfsuid, current_fsuid()))
goto check_perm;
break;
case ACL_USER:
vfsuid = make_vfsuid(mnt_userns, &init_user_ns,
fs: support mapped mounts of mapped filesystems In previous patches we added new and modified existing helpers to handle idmapped mounts of filesystems mounted with an idmapping. In this final patch we convert all relevant places in the vfs to actually pass the filesystem's idmapping into these helpers. With this the vfs is in shape to handle idmapped mounts of filesystems mounted with an idmapping. Note that this is just the generic infrastructure. Actually adding support for idmapped mounts to a filesystem mountable with an idmapping is follow-up work. In this patch we extend the definition of an idmapped mount from a mount that that has the initial idmapping attached to it to a mount that has an idmapping attached to it which is not the same as the idmapping the filesystem was mounted with. As before we do not allow the initial idmapping to be attached to a mount. In addition this patch prevents that the idmapping the filesystem was mounted with can be attached to a mount created based on this filesystem. This has multiple reasons and advantages. First, attaching the initial idmapping or the filesystem's idmapping doesn't make much sense as in both cases the values of the i_{g,u}id and other places where k{g,u}ids are used do not change. Second, a user that really wants to do this for whatever reason can just create a separate dedicated identical idmapping to attach to the mount. Third, we can continue to use the initial idmapping as an indicator that a mount is not idmapped allowing us to continue to keep passing the initial idmapping into the mapping helpers to tell them that something isn't an idmapped mount even if the filesystem is mounted with an idmapping. Link: https://lore.kernel.org/r/20211123114227.3124056-11-brauner@kernel.org (v1) Link: https://lore.kernel.org/r/20211130121032.3753852-11-brauner@kernel.org (v2) Link: https://lore.kernel.org/r/20211203111707.3901969-11-brauner@kernel.org Cc: Seth Forshee <sforshee@digitalocean.com> Cc: Amir Goldstein <amir73il@gmail.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Al Viro <viro@zeniv.linux.org.uk> CC: linux-fsdevel@vger.kernel.org Reviewed-by: Seth Forshee <sforshee@digitalocean.com> Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
2021-12-03 19:17:07 +08:00
pa->e_uid);
if (vfsuid_eq_kuid(vfsuid, current_fsuid()))
goto mask;
break;
case ACL_GROUP_OBJ:
vfsgid = i_gid_into_vfsgid(mnt_userns, inode);
if (vfsgid_in_group_p(vfsgid)) {
found = 1;
if ((pa->e_perm & want) == want)
goto mask;
}
break;
case ACL_GROUP:
vfsgid = make_vfsgid(mnt_userns, &init_user_ns,
fs: support mapped mounts of mapped filesystems In previous patches we added new and modified existing helpers to handle idmapped mounts of filesystems mounted with an idmapping. In this final patch we convert all relevant places in the vfs to actually pass the filesystem's idmapping into these helpers. With this the vfs is in shape to handle idmapped mounts of filesystems mounted with an idmapping. Note that this is just the generic infrastructure. Actually adding support for idmapped mounts to a filesystem mountable with an idmapping is follow-up work. In this patch we extend the definition of an idmapped mount from a mount that that has the initial idmapping attached to it to a mount that has an idmapping attached to it which is not the same as the idmapping the filesystem was mounted with. As before we do not allow the initial idmapping to be attached to a mount. In addition this patch prevents that the idmapping the filesystem was mounted with can be attached to a mount created based on this filesystem. This has multiple reasons and advantages. First, attaching the initial idmapping or the filesystem's idmapping doesn't make much sense as in both cases the values of the i_{g,u}id and other places where k{g,u}ids are used do not change. Second, a user that really wants to do this for whatever reason can just create a separate dedicated identical idmapping to attach to the mount. Third, we can continue to use the initial idmapping as an indicator that a mount is not idmapped allowing us to continue to keep passing the initial idmapping into the mapping helpers to tell them that something isn't an idmapped mount even if the filesystem is mounted with an idmapping. Link: https://lore.kernel.org/r/20211123114227.3124056-11-brauner@kernel.org (v1) Link: https://lore.kernel.org/r/20211130121032.3753852-11-brauner@kernel.org (v2) Link: https://lore.kernel.org/r/20211203111707.3901969-11-brauner@kernel.org Cc: Seth Forshee <sforshee@digitalocean.com> Cc: Amir Goldstein <amir73il@gmail.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Al Viro <viro@zeniv.linux.org.uk> CC: linux-fsdevel@vger.kernel.org Reviewed-by: Seth Forshee <sforshee@digitalocean.com> Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
2021-12-03 19:17:07 +08:00
pa->e_gid);
if (vfsgid_in_group_p(vfsgid)) {
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);
acl: handle idmapped mounts The posix acl permission checking helpers determine whether a caller is privileged over an inode according to the acls associated with the inode. Add helpers that make it possible to handle acls on idmapped mounts. The vfs and the filesystems targeted by this first iteration make use of posix_acl_fix_xattr_from_user() and posix_acl_fix_xattr_to_user() to translate basic posix access and default permissions such as the ACL_USER and ACL_GROUP type according to the initial user namespace (or the superblock's user namespace) to and from the caller's current user namespace. Adapt these two helpers to handle idmapped mounts whereby we either map from or into the mount's user namespace depending on in which direction we're translating. Similarly, cap_convert_nscap() is used by the vfs to translate user namespace and non-user namespace aware filesystem capabilities from the superblock's user namespace to the caller's user namespace. Enable it to handle idmapped mounts by accounting for the mount's user namespace. In addition the fileystems targeted in the first iteration of this patch series make use of the posix_acl_chmod() and, posix_acl_update_mode() helpers. Both helpers perform permission checks on the target inode. Let them handle idmapped mounts. These two helpers are called when posix acls are set by the respective filesystems to handle this case we extend the ->set() method to take an additional user namespace argument to pass the mount's user namespace down. Link: https://lore.kernel.org/r/20210121131959.646623-9-christian.brauner@ubuntu.com Cc: Christoph Hellwig <hch@lst.de> Cc: David Howells <dhowells@redhat.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: linux-fsdevel@vger.kernel.org Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
2021-01-21 21:19:27 +08:00
/**
* 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
acl: handle idmapped mounts The posix acl permission checking helpers determine whether a caller is privileged over an inode according to the acls associated with the inode. Add helpers that make it possible to handle acls on idmapped mounts. The vfs and the filesystems targeted by this first iteration make use of posix_acl_fix_xattr_from_user() and posix_acl_fix_xattr_to_user() to translate basic posix access and default permissions such as the ACL_USER and ACL_GROUP type according to the initial user namespace (or the superblock's user namespace) to and from the caller's current user namespace. Adapt these two helpers to handle idmapped mounts whereby we either map from or into the mount's user namespace depending on in which direction we're translating. Similarly, cap_convert_nscap() is used by the vfs to translate user namespace and non-user namespace aware filesystem capabilities from the superblock's user namespace to the caller's user namespace. Enable it to handle idmapped mounts by accounting for the mount's user namespace. In addition the fileystems targeted in the first iteration of this patch series make use of the posix_acl_chmod() and, posix_acl_update_mode() helpers. Both helpers perform permission checks on the target inode. Let them handle idmapped mounts. These two helpers are called when posix acls are set by the respective filesystems to handle this case we extend the ->set() method to take an additional user namespace argument to pass the mount's user namespace down. Link: https://lore.kernel.org/r/20210121131959.646623-9-christian.brauner@ubuntu.com Cc: Christoph Hellwig <hch@lst.de> Cc: David Howells <dhowells@redhat.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: linux-fsdevel@vger.kernel.org Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
2021-01-21 21:19:27 +08:00
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
acl: handle idmapped mounts The posix acl permission checking helpers determine whether a caller is privileged over an inode according to the acls associated with the inode. Add helpers that make it possible to handle acls on idmapped mounts. The vfs and the filesystems targeted by this first iteration make use of posix_acl_fix_xattr_from_user() and posix_acl_fix_xattr_to_user() to translate basic posix access and default permissions such as the ACL_USER and ACL_GROUP type according to the initial user namespace (or the superblock's user namespace) to and from the caller's current user namespace. Adapt these two helpers to handle idmapped mounts whereby we either map from or into the mount's user namespace depending on in which direction we're translating. Similarly, cap_convert_nscap() is used by the vfs to translate user namespace and non-user namespace aware filesystem capabilities from the superblock's user namespace to the caller's user namespace. Enable it to handle idmapped mounts by accounting for the mount's user namespace. In addition the fileystems targeted in the first iteration of this patch series make use of the posix_acl_chmod() and, posix_acl_update_mode() helpers. Both helpers perform permission checks on the target inode. Let them handle idmapped mounts. These two helpers are called when posix acls are set by the respective filesystems to handle this case we extend the ->set() method to take an additional user namespace argument to pass the mount's user namespace down. Link: https://lore.kernel.org/r/20210121131959.646623-9-christian.brauner@ubuntu.com Cc: Christoph Hellwig <hch@lst.de> Cc: David Howells <dhowells@redhat.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: linux-fsdevel@vger.kernel.org Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
2021-01-21 21:19:27 +08:00
* @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).
*
acl: handle idmapped mounts The posix acl permission checking helpers determine whether a caller is privileged over an inode according to the acls associated with the inode. Add helpers that make it possible to handle acls on idmapped mounts. The vfs and the filesystems targeted by this first iteration make use of posix_acl_fix_xattr_from_user() and posix_acl_fix_xattr_to_user() to translate basic posix access and default permissions such as the ACL_USER and ACL_GROUP type according to the initial user namespace (or the superblock's user namespace) to and from the caller's current user namespace. Adapt these two helpers to handle idmapped mounts whereby we either map from or into the mount's user namespace depending on in which direction we're translating. Similarly, cap_convert_nscap() is used by the vfs to translate user namespace and non-user namespace aware filesystem capabilities from the superblock's user namespace to the caller's user namespace. Enable it to handle idmapped mounts by accounting for the mount's user namespace. In addition the fileystems targeted in the first iteration of this patch series make use of the posix_acl_chmod() and, posix_acl_update_mode() helpers. Both helpers perform permission checks on the target inode. Let them handle idmapped mounts. These two helpers are called when posix acls are set by the respective filesystems to handle this case we extend the ->set() method to take an additional user namespace argument to pass the mount's user namespace down. Link: https://lore.kernel.org/r/20210121131959.646623-9-christian.brauner@ubuntu.com Cc: Christoph Hellwig <hch@lst.de> Cc: David Howells <dhowells@redhat.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: linux-fsdevel@vger.kernel.org Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
2021-01-21 21:19:27 +08:00
* 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.
*/
acl: handle idmapped mounts The posix acl permission checking helpers determine whether a caller is privileged over an inode according to the acls associated with the inode. Add helpers that make it possible to handle acls on idmapped mounts. The vfs and the filesystems targeted by this first iteration make use of posix_acl_fix_xattr_from_user() and posix_acl_fix_xattr_to_user() to translate basic posix access and default permissions such as the ACL_USER and ACL_GROUP type according to the initial user namespace (or the superblock's user namespace) to and from the caller's current user namespace. Adapt these two helpers to handle idmapped mounts whereby we either map from or into the mount's user namespace depending on in which direction we're translating. Similarly, cap_convert_nscap() is used by the vfs to translate user namespace and non-user namespace aware filesystem capabilities from the superblock's user namespace to the caller's user namespace. Enable it to handle idmapped mounts by accounting for the mount's user namespace. In addition the fileystems targeted in the first iteration of this patch series make use of the posix_acl_chmod() and, posix_acl_update_mode() helpers. Both helpers perform permission checks on the target inode. Let them handle idmapped mounts. These two helpers are called when posix acls are set by the respective filesystems to handle this case we extend the ->set() method to take an additional user namespace argument to pass the mount's user namespace down. Link: https://lore.kernel.org/r/20210121131959.646623-9-christian.brauner@ubuntu.com Cc: Christoph Hellwig <hch@lst.de> Cc: David Howells <dhowells@redhat.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: linux-fsdevel@vger.kernel.org Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
2021-01-21 21:19:27 +08:00
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 (!vfsgid_in_group_p(i_gid_into_vfsgid(mnt_userns, inode)) &&
acl: handle idmapped mounts The posix acl permission checking helpers determine whether a caller is privileged over an inode according to the acls associated with the inode. Add helpers that make it possible to handle acls on idmapped mounts. The vfs and the filesystems targeted by this first iteration make use of posix_acl_fix_xattr_from_user() and posix_acl_fix_xattr_to_user() to translate basic posix access and default permissions such as the ACL_USER and ACL_GROUP type according to the initial user namespace (or the superblock's user namespace) to and from the caller's current user namespace. Adapt these two helpers to handle idmapped mounts whereby we either map from or into the mount's user namespace depending on in which direction we're translating. Similarly, cap_convert_nscap() is used by the vfs to translate user namespace and non-user namespace aware filesystem capabilities from the superblock's user namespace to the caller's user namespace. Enable it to handle idmapped mounts by accounting for the mount's user namespace. In addition the fileystems targeted in the first iteration of this patch series make use of the posix_acl_chmod() and, posix_acl_update_mode() helpers. Both helpers perform permission checks on the target inode. Let them handle idmapped mounts. These two helpers are called when posix acls are set by the respective filesystems to handle this case we extend the ->set() method to take an additional user namespace argument to pass the mount's user namespace down. Link: https://lore.kernel.org/r/20210121131959.646623-9-christian.brauner@ubuntu.com Cc: Christoph Hellwig <hch@lst.de> Cc: David Howells <dhowells@redhat.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: linux-fsdevel@vger.kernel.org Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
2021-01-21 21:19:27 +08:00
!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.
*/
acl: move idmapped mount fixup into vfs_{g,s}etxattr() 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>
2022-07-07 00:30:59 +08:00
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;
acl: move idmapped mount fixup into vfs_{g,s}etxattr() 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>
2022-07-07 00:30:59 +08:00
vfsuid_t vfsuid;
vfsgid_t vfsgid;
kuid_t uid;
kgid_t gid;
acl: move idmapped mount fixup into vfs_{g,s}etxattr() 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>
2022-07-07 00:30:59 +08:00
if (no_idmapping(mnt_userns, i_user_ns(inode)))
return;
acl: move idmapped mount fixup into vfs_{g,s}etxattr() 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>
2022-07-07 00:30:59 +08:00
count = posix_acl_fix_xattr_common(value, size);
if (count < 0)
return;
acl: move idmapped mount fixup into vfs_{g,s}etxattr() 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>
2022-07-07 00:30:59 +08:00
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;
acl: move idmapped mount fixup into vfs_{g,s}etxattr() 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>
2022-07-07 00:30:59 +08:00
count = posix_acl_fix_xattr_common(value, size);
if (count < 0)
return;
acl: move idmapped mount fixup into vfs_{g,s}etxattr() 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>
2022-07-07 00:30:59 +08:00
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;
}
}
}
acl: move idmapped mount fixup into vfs_{g,s}etxattr() 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>
2022-07-07 00:30:59 +08:00
void posix_acl_fix_xattr_from_user(void *value, size_t size)
{
struct user_namespace *user_ns = current_user_ns();
acl: move idmapped mount fixup into vfs_{g,s}etxattr() 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>
2022-07-07 00:30:59 +08:00
if (user_ns == &init_user_ns)
return;
acl: move idmapped mount fixup into vfs_{g,s}etxattr() 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>
2022-07-07 00:30:59 +08:00
posix_acl_fix_xattr_userns(&init_user_ns, user_ns, value, size);
}
acl: move idmapped mount fixup into vfs_{g,s}etxattr() 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>
2022-07-07 00:30:59 +08:00
void posix_acl_fix_xattr_to_user(void *value, size_t size)
{
struct user_namespace *user_ns = current_user_ns();
acl: move idmapped mount fixup into vfs_{g,s}etxattr() 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>
2022-07-07 00:30:59 +08:00
if (user_ns == &init_user_ns)
return;
acl: move idmapped mount fixup into vfs_{g,s}etxattr() 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>
2022-07-07 00:30:59 +08:00
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
acl: handle idmapped mounts The posix acl permission checking helpers determine whether a caller is privileged over an inode according to the acls associated with the inode. Add helpers that make it possible to handle acls on idmapped mounts. The vfs and the filesystems targeted by this first iteration make use of posix_acl_fix_xattr_from_user() and posix_acl_fix_xattr_to_user() to translate basic posix access and default permissions such as the ACL_USER and ACL_GROUP type according to the initial user namespace (or the superblock's user namespace) to and from the caller's current user namespace. Adapt these two helpers to handle idmapped mounts whereby we either map from or into the mount's user namespace depending on in which direction we're translating. Similarly, cap_convert_nscap() is used by the vfs to translate user namespace and non-user namespace aware filesystem capabilities from the superblock's user namespace to the caller's user namespace. Enable it to handle idmapped mounts by accounting for the mount's user namespace. In addition the fileystems targeted in the first iteration of this patch series make use of the posix_acl_chmod() and, posix_acl_update_mode() helpers. Both helpers perform permission checks on the target inode. Let them handle idmapped mounts. These two helpers are called when posix acls are set by the respective filesystems to handle this case we extend the ->set() method to take an additional user namespace argument to pass the mount's user namespace down. Link: https://lore.kernel.org/r/20210121131959.646623-9-christian.brauner@ubuntu.com Cc: Christoph Hellwig <hch@lst.de> Cc: David Howells <dhowells@redhat.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: linux-fsdevel@vger.kernel.org Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
2021-01-21 21:19:27 +08:00
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;
acl: handle idmapped mounts The posix acl permission checking helpers determine whether a caller is privileged over an inode according to the acls associated with the inode. Add helpers that make it possible to handle acls on idmapped mounts. The vfs and the filesystems targeted by this first iteration make use of posix_acl_fix_xattr_from_user() and posix_acl_fix_xattr_to_user() to translate basic posix access and default permissions such as the ACL_USER and ACL_GROUP type according to the initial user namespace (or the superblock's user namespace) to and from the caller's current user namespace. Adapt these two helpers to handle idmapped mounts whereby we either map from or into the mount's user namespace depending on in which direction we're translating. Similarly, cap_convert_nscap() is used by the vfs to translate user namespace and non-user namespace aware filesystem capabilities from the superblock's user namespace to the caller's user namespace. Enable it to handle idmapped mounts by accounting for the mount's user namespace. In addition the fileystems targeted in the first iteration of this patch series make use of the posix_acl_chmod() and, posix_acl_update_mode() helpers. Both helpers perform permission checks on the target inode. Let them handle idmapped mounts. These two helpers are called when posix acls are set by the respective filesystems to handle this case we extend the ->set() method to take an additional user namespace argument to pass the mount's user namespace down. Link: https://lore.kernel.org/r/20210121131959.646623-9-christian.brauner@ubuntu.com Cc: Christoph Hellwig <hch@lst.de> Cc: David Howells <dhowells@redhat.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: linux-fsdevel@vger.kernel.org Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
2021-01-21 21:19:27 +08:00
if (!inode_owner_or_capable(mnt_userns, inode))
return -EPERM;
if (acl) {
Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace Pull userns vfs updates from Eric Biederman: "This tree contains some very long awaited work on generalizing the user namespace support for mounting filesystems to include filesystems with a backing store. The real world target is fuse but the goal is to update the vfs to allow any filesystem to be supported. This patchset is based on a lot of code review and testing to approach that goal. While looking at what is needed to support the fuse filesystem it became clear that there were things like xattrs for security modules that needed special treatment. That the resolution of those concerns would not be fuse specific. That sorting out these general issues made most sense at the generic level, where the right people could be drawn into the conversation, and the issues could be solved for everyone. At a high level what this patchset does a couple of simple things: - Add a user namespace owner (s_user_ns) to struct super_block. - Teach the vfs to handle filesystem uids and gids not mapping into to kuids and kgids and being reported as INVALID_UID and INVALID_GID in vfs data structures. By assigning a user namespace owner filesystems that are mounted with only user namespace privilege can be detected. This allows security modules and the like to know which mounts may not be trusted. This also allows the set of uids and gids that are communicated to the filesystem to be capped at the set of kuids and kgids that are in the owning user namespace of the filesystem. One of the crazier corner casees this handles is the case of inodes whose i_uid or i_gid are not mapped into the vfs. Most of the code simply doesn't care but it is easy to confuse the inode writeback path so no operation that could cause an inode write-back is permitted for such inodes (aka only reads are allowed). This set of changes starts out by cleaning up the code paths involved in user namespace permirted mounts. Then when things are clean enough adds code that cleanly sets s_user_ns. Then additional restrictions are added that are possible now that the filesystem superblock contains owner information. These changes should not affect anyone in practice, but there are some parts of these restrictions that are changes in behavior. - Andy's restriction on suid executables that does not honor the suid bit when the path is from another mount namespace (think /proc/[pid]/fd/) or when the filesystem was mounted by a less privileged user. - The replacement of the user namespace implicit setting of MNT_NODEV with implicitly setting SB_I_NODEV on the filesystem superblock instead. Using SB_I_NODEV is a stronger form that happens to make this state user invisible. The user visibility can be managed but it caused problems when it was introduced from applications reasonably expecting mount flags to be what they were set to. There is a little bit of work remaining before it is safe to support mounting filesystems with backing store in user namespaces, beyond what is in this set of changes. - Verifying the mounter has permission to read/write the block device during mount. - Teaching the integrity modules IMA and EVM to handle filesystems mounted with only user namespace root and to reduce trust in their security xattrs accordingly. - Capturing the mounters credentials and using that for permission checks in d_automount and the like. (Given that overlayfs already does this, and we need the work in d_automount it make sense to generalize this case). Furthermore there are a few changes that are on the wishlist: - Get all filesystems supporting posix acls using the generic posix acls so that posix_acl_fix_xattr_from_user and posix_acl_fix_xattr_to_user may be removed. [Maintainability] - Reducing the permission checks in places such as remount to allow the superblock owner to perform them. - Allowing the superblock owner to chown files with unmapped uids and gids to something that is mapped so the files may be treated normally. I am not considering even obvious relaxations of permission checks until it is clear there are no more corner cases that need to be locked down and handled generically. Many thanks to Seth Forshee who kept this code alive, and putting up with me rewriting substantial portions of what he did to handle more corner cases, and for his diligent testing and reviewing of my changes" * 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace: (30 commits) fs: Call d_automount with the filesystems creds fs: Update i_[ug]id_(read|write) to translate relative to s_user_ns evm: Translate user/group ids relative to s_user_ns when computing HMAC dquot: For now explicitly don't support filesystems outside of init_user_ns quota: Handle quota data stored in s_user_ns in quota_setxquota quota: Ensure qids map to the filesystem vfs: Don't create inodes with a uid or gid unknown to the vfs vfs: Don't modify inodes with a uid or gid unknown to the vfs cred: Reject inodes with invalid ids in set_create_file_as() fs: Check for invalid i_uid in may_follow_link() vfs: Verify acls are valid within superblock's s_user_ns. userns: Handle -1 in k[ug]id_has_mapping when !CONFIG_USER_NS fs: Refuse uid/gid changes which don't map into s_user_ns selinux: Add support for unprivileged mounts from user namespaces Smack: Handle labels consistently in untrusted mounts Smack: Add support for unprivileged mounts from user namespaces fs: Treat foreign mounts as nosuid fs: Limit file caps to the user namespace of the super block userns: Remove the now unnecessary FS_USERNS_DEV_MOUNT flag userns: Remove implicit MNT_NODEV fragility. ...
2016-07-30 06:54:19 +08:00
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,
acl: handle idmapped mounts The posix acl permission checking helpers determine whether a caller is privileged over an inode according to the acls associated with the inode. Add helpers that make it possible to handle acls on idmapped mounts. The vfs and the filesystems targeted by this first iteration make use of posix_acl_fix_xattr_from_user() and posix_acl_fix_xattr_to_user() to translate basic posix access and default permissions such as the ACL_USER and ACL_GROUP type according to the initial user namespace (or the superblock's user namespace) to and from the caller's current user namespace. Adapt these two helpers to handle idmapped mounts whereby we either map from or into the mount's user namespace depending on in which direction we're translating. Similarly, cap_convert_nscap() is used by the vfs to translate user namespace and non-user namespace aware filesystem capabilities from the superblock's user namespace to the caller's user namespace. Enable it to handle idmapped mounts by accounting for the mount's user namespace. In addition the fileystems targeted in the first iteration of this patch series make use of the posix_acl_chmod() and, posix_acl_update_mode() helpers. Both helpers perform permission checks on the target inode. Let them handle idmapped mounts. These two helpers are called when posix acls are set by the respective filesystems to handle this case we extend the ->set() method to take an additional user namespace argument to pass the mount's user namespace down. Link: https://lore.kernel.org/r/20210121131959.646623-9-christian.brauner@ubuntu.com Cc: Christoph Hellwig <hch@lst.de> Cc: David Howells <dhowells@redhat.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: linux-fsdevel@vger.kernel.org Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
2021-01-21 21:19:27 +08:00
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);
}
acl: handle idmapped mounts The posix acl permission checking helpers determine whether a caller is privileged over an inode according to the acls associated with the inode. Add helpers that make it possible to handle acls on idmapped mounts. The vfs and the filesystems targeted by this first iteration make use of posix_acl_fix_xattr_from_user() and posix_acl_fix_xattr_to_user() to translate basic posix access and default permissions such as the ACL_USER and ACL_GROUP type according to the initial user namespace (or the superblock's user namespace) to and from the caller's current user namespace. Adapt these two helpers to handle idmapped mounts whereby we either map from or into the mount's user namespace depending on in which direction we're translating. Similarly, cap_convert_nscap() is used by the vfs to translate user namespace and non-user namespace aware filesystem capabilities from the superblock's user namespace to the caller's user namespace. Enable it to handle idmapped mounts by accounting for the mount's user namespace. In addition the fileystems targeted in the first iteration of this patch series make use of the posix_acl_chmod() and, posix_acl_update_mode() helpers. Both helpers perform permission checks on the target inode. Let them handle idmapped mounts. These two helpers are called when posix acls are set by the respective filesystems to handle this case we extend the ->set() method to take an additional user namespace argument to pass the mount's user namespace down. Link: https://lore.kernel.org/r/20210121131959.646623-9-christian.brauner@ubuntu.com Cc: Christoph Hellwig <hch@lst.de> Cc: David Howells <dhowells@redhat.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: linux-fsdevel@vger.kernel.org Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
2021-01-21 21:19:27 +08:00
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;
}