mirror of
https://mirrors.bfsu.edu.cn/git/linux.git
synced 2024-09-22 04:31:58 +08:00
0c5fd887d2
This cycle we added support for mounting overlayfs on top of idmapped mounts.
Recently I've started looking into potential corner cases when trying to add
additional tests and I noticed that reporting for POSIX ACLs is currently wrong
when using idmapped layers with overlayfs mounted on top of it.
I'm going to give a rather detailed explanation to both the origin of the
problem and the solution.
Let's assume the user creates the following directory layout and they have a
rootfs /var/lib/lxc/c1/rootfs. The files in this rootfs are owned as you would
expect files on your host system to be owned. For example, ~/.bashrc for your
regular user would be owned by 1000:1000 and /root/.bashrc would be owned by
0:0. IOW, this is just regular boring filesystem tree on an ext4 or xfs
filesystem.
The user chooses to set POSIX ACLs using the setfacl binary granting the user
with uid 4 read, write, and execute permissions for their .bashrc file:
setfacl -m u:4:rwx /var/lib/lxc/c2/rootfs/home/ubuntu/.bashrc
Now they to expose the whole rootfs to a container using an idmapped mount. So
they first create:
mkdir -pv /vol/contpool/{ctrover,merge,lowermap,overmap}
mkdir -pv /vol/contpool/ctrover/{over,work}
chown 10000000:10000000 /vol/contpool/ctrover/{over,work}
The user now creates an idmapped mount for the rootfs:
mount-idmapped/mount-idmapped --map-mount=b:0:10000000:65536 \
/var/lib/lxc/c2/rootfs \
/vol/contpool/lowermap
This for example makes it so that /var/lib/lxc/c2/rootfs/home/ubuntu/.bashrc
which is owned by uid and gid 1000 as being owned by uid and gid 10001000 at
/vol/contpool/lowermap/home/ubuntu/.bashrc.
Assume the user wants to expose these idmapped mounts through an overlayfs
mount to a container.
mount -t overlay overlay \
-o lowerdir=/vol/contpool/lowermap, \
upperdir=/vol/contpool/overmap/over, \
workdir=/vol/contpool/overmap/work \
/vol/contpool/merge
The user can do this in two ways:
(1) Mount overlayfs in the initial user namespace and expose it to the
container.
(2) Mount overlayfs on top of the idmapped mounts inside of the container's
user namespace.
Let's assume the user chooses the (1) option and mounts overlayfs on the host
and then changes into a container which uses the idmapping 0:10000000:65536
which is the same used for the two idmapped mounts.
Now the user tries to retrieve the POSIX ACLs using the getfacl command
getfacl -n /vol/contpool/lowermap/home/ubuntu/.bashrc
and to their surprise they see:
# file: vol/contpool/merge/home/ubuntu/.bashrc
# owner: 1000
# group: 1000
user::rw-
user:4294967295:rwx
group::r--
mask::rwx
other::r--
indicating the the uid wasn't correctly translated according to the idmapped
mount. The problem is how we currently translate POSIX ACLs. Let's inspect the
callchain in this example:
idmapped mount /vol/contpool/merge: 0:10000000:65536
caller's idmapping: 0:10000000:65536
overlayfs idmapping (ofs->creator_cred): 0:0:4k /* initial idmapping */
sys_getxattr()
-> path_getxattr()
-> getxattr()
-> do_getxattr()
|> vfs_getxattr()
| -> __vfs_getxattr()
| -> handler->get == ovl_posix_acl_xattr_get()
| -> ovl_xattr_get()
| -> vfs_getxattr()
| -> __vfs_getxattr()
| -> handler->get() /* lower filesystem callback */
|> posix_acl_fix_xattr_to_user()
{
4 = make_kuid(&init_user_ns, 4);
4 = mapped_kuid_fs(&init_user_ns /* no idmapped mount */, 4);
/* FAILURE */
-1 = from_kuid(0:10000000:65536 /* caller's idmapping */, 4);
}
If the user chooses to use option (2) and mounts overlayfs on top of idmapped
mounts inside the container things don't look that much better:
idmapped mount /vol/contpool/merge: 0:10000000:65536
caller's idmapping: 0:10000000:65536
overlayfs idmapping (ofs->creator_cred): 0:10000000:65536
sys_getxattr()
-> path_getxattr()
-> getxattr()
-> do_getxattr()
|> vfs_getxattr()
| -> __vfs_getxattr()
| -> handler->get == ovl_posix_acl_xattr_get()
| -> ovl_xattr_get()
| -> vfs_getxattr()
| -> __vfs_getxattr()
| -> handler->get() /* lower filesystem callback */
|> posix_acl_fix_xattr_to_user()
{
4 = make_kuid(&init_user_ns, 4);
4 = mapped_kuid_fs(&init_user_ns, 4);
/* FAILURE */
-1 = from_kuid(0:10000000:65536 /* caller's idmapping */, 4);
}
As is easily seen the problem arises because the idmapping of the lower mount
isn't taken into account as all of this happens in do_gexattr(). But
do_getxattr() is always called on an overlayfs mount and inode and thus cannot
possible take the idmapping of the lower layers into account.
This problem is similar for fscaps but there the translation happens as part of
vfs_getxattr() already. Let's walk through an fscaps overlayfs callchain:
setcap 'cap_net_raw+ep' /var/lib/lxc/c2/rootfs/home/ubuntu/.bashrc
The expected outcome here is that we'll receive the cap_net_raw capability as
we are able to map the uid associated with the fscap to 0 within our container.
IOW, we want to see 0 as the result of the idmapping translations.
If the user chooses option (1) we get the following callchain for fscaps:
idmapped mount /vol/contpool/merge: 0:10000000:65536
caller's idmapping: 0:10000000:65536
overlayfs idmapping (ofs->creator_cred): 0:0:4k /* initial idmapping */
sys_getxattr()
-> path_getxattr()
-> getxattr()
-> do_getxattr()
-> vfs_getxattr()
-> xattr_getsecurity()
-> security_inode_getsecurity() ________________________________
-> cap_inode_getsecurity() | |
{ V |
10000000 = make_kuid(0:0:4k /* overlayfs idmapping */, 10000000); |
10000000 = mapped_kuid_fs(0:0:4k /* no idmapped mount */, 10000000); |
/* Expected result is 0 and thus that we own the fscap. */ |
0 = from_kuid(0:10000000:65536 /* caller's idmapping */, 10000000); |
} |
-> vfs_getxattr_alloc() |
-> handler->get == ovl_other_xattr_get() |
-> vfs_getxattr() |
-> xattr_getsecurity() |
-> security_inode_getsecurity() |
-> cap_inode_getsecurity() |
{ |
0 = make_kuid(0:0:4k /* lower s_user_ns */, 0); |
10000000 = mapped_kuid_fs(0:10000000:65536 /* idmapped mount */, 0); |
10000000 = from_kuid(0:0:4k /* overlayfs idmapping */, 10000000); |
|____________________________________________________________________|
}
-> vfs_getxattr_alloc()
-> handler->get == /* lower filesystem callback */
And if the user chooses option (2) we get:
idmapped mount /vol/contpool/merge: 0:10000000:65536
caller's idmapping: 0:10000000:65536
overlayfs idmapping (ofs->creator_cred): 0:10000000:65536
sys_getxattr()
-> path_getxattr()
-> getxattr()
-> do_getxattr()
-> vfs_getxattr()
-> xattr_getsecurity()
-> security_inode_getsecurity() _______________________________
-> cap_inode_getsecurity() | |
{ V |
10000000 = make_kuid(0:10000000:65536 /* overlayfs idmapping */, 0); |
10000000 = mapped_kuid_fs(0:0:4k /* no idmapped mount */, 10000000); |
/* Expected result is 0 and thus that we own the fscap. */ |
0 = from_kuid(0:10000000:65536 /* caller's idmapping */, 10000000); |
} |
-> vfs_getxattr_alloc() |
-> handler->get == ovl_other_xattr_get() |
|-> vfs_getxattr() |
-> xattr_getsecurity() |
-> security_inode_getsecurity() |
-> cap_inode_getsecurity() |
{ |
0 = make_kuid(0:0:4k /* lower s_user_ns */, 0); |
10000000 = mapped_kuid_fs(0:10000000:65536 /* idmapped mount */, 0); |
0 = from_kuid(0:10000000:65536 /* overlayfs idmapping */, 10000000); |
|____________________________________________________________________|
}
-> vfs_getxattr_alloc()
-> handler->get == /* lower filesystem callback */
We can see how the translation happens correctly in those cases as the
conversion happens within the vfs_getxattr() helper.
For POSIX ACLs we need to do something similar. However, in contrast to fscaps
we cannot apply the fix directly to the kernel internal posix acl data
structure as this would alter the cached values and would also require a rework
of how we currently deal with POSIX ACLs in general which almost never take the
filesystem idmapping into account (the noteable exception being FUSE but even
there the implementation is special) and instead retrieve the raw values based
on the initial idmapping.
The correct values are then generated right before returning to userspace. The
fix for this is to move taking the mount's idmapping into account directly in
vfs_getxattr() instead of having it be part of posix_acl_fix_xattr_to_user().
To this end we split out two small and unexported helpers
posix_acl_getxattr_idmapped_mnt() and posix_acl_setxattr_idmapped_mnt(). The
former to be called in vfs_getxattr() and the latter to be called in
vfs_setxattr().
Let's go back to the original example. Assume the user chose option (1) and
mounted overlayfs on top of idmapped mounts on the host:
idmapped mount /vol/contpool/merge: 0:10000000:65536
caller's idmapping: 0:10000000:65536
overlayfs idmapping (ofs->creator_cred): 0:0:4k /* initial idmapping */
sys_getxattr()
-> path_getxattr()
-> getxattr()
-> do_getxattr()
|> vfs_getxattr()
| |> __vfs_getxattr()
| | -> handler->get == ovl_posix_acl_xattr_get()
| | -> ovl_xattr_get()
| | -> vfs_getxattr()
| | |> __vfs_getxattr()
| | | -> handler->get() /* lower filesystem callback */
| | |> posix_acl_getxattr_idmapped_mnt()
| | {
| | 4 = make_kuid(&init_user_ns, 4);
| | 10000004 = mapped_kuid_fs(0:10000000:65536 /* lower idmapped mount */, 4);
| | 10000004 = from_kuid(&init_user_ns, 10000004);
| | |_______________________
| | } |
| | |
| |> posix_acl_getxattr_idmapped_mnt() |
| { |
| V
| 10000004 = make_kuid(&init_user_ns, 10000004);
| 10000004 = mapped_kuid_fs(&init_user_ns /* no idmapped mount */, 10000004);
| 10000004 = from_kuid(&init_user_ns, 10000004);
| } |_________________________________________________
| |
| |
|> posix_acl_fix_xattr_to_user() |
{ V
10000004 = make_kuid(0:0:4k /* init_user_ns */, 10000004);
/* SUCCESS */
4 = from_kuid(0:10000000:65536 /* caller's idmapping */, 10000004);
}
And similarly if the user chooses option (1) and mounted overayfs on top of
idmapped mounts inside the container:
idmapped mount /vol/contpool/merge: 0:10000000:65536
caller's idmapping: 0:10000000:65536
overlayfs idmapping (ofs->creator_cred): 0:10000000:65536
sys_getxattr()
-> path_getxattr()
-> getxattr()
-> do_getxattr()
|> vfs_getxattr()
| |> __vfs_getxattr()
| | -> handler->get == ovl_posix_acl_xattr_get()
| | -> ovl_xattr_get()
| | -> vfs_getxattr()
| | |> __vfs_getxattr()
| | | -> handler->get() /* lower filesystem callback */
| | |> posix_acl_getxattr_idmapped_mnt()
| | {
| | 4 = make_kuid(&init_user_ns, 4);
| | 10000004 = mapped_kuid_fs(0:10000000:65536 /* lower idmapped mount */, 4);
| | 10000004 = from_kuid(&init_user_ns, 10000004);
| | |_______________________
| | } |
| | |
| |> posix_acl_getxattr_idmapped_mnt() |
| { V
| 10000004 = make_kuid(&init_user_ns, 10000004);
| 10000004 = mapped_kuid_fs(&init_user_ns /* no idmapped mount */, 10000004);
| 10000004 = from_kuid(0(&init_user_ns, 10000004);
| |_________________________________________________
| } |
| |
|> posix_acl_fix_xattr_to_user() |
{ V
10000004 = make_kuid(0:0:4k /* init_user_ns */, 10000004);
/* SUCCESS */
4 = from_kuid(0:10000000:65536 /* caller's idmappings */, 10000004);
}
The last remaining problem we need to fix here is ovl_get_acl(). During
ovl_permission() overlayfs will call:
ovl_permission()
-> generic_permission()
-> acl_permission_check()
-> check_acl()
-> get_acl()
-> inode->i_op->get_acl() == ovl_get_acl()
> get_acl() /* on the underlying filesystem)
->inode->i_op->get_acl() == /*lower filesystem callback */
-> posix_acl_permission()
passing through the get_acl request to the underlying filesystem. This will
retrieve the acls stored in the lower filesystem without taking the idmapping
of the underlying mount into account as this would mean altering the cached
values for the lower filesystem. So we block using ACLs for now until we
decided on a nice way to fix this. Note this limitation both in the
documentation and in the code.
The most straightforward solution would be to have ovl_get_acl() simply
duplicate the ACLs, update the values according to the idmapped mount and
return it to acl_permission_check() so it can be used in posix_acl_permission()
forgetting them afterwards. This is a bit heavy handed but fairly
straightforward otherwise.
Link: https://github.com/brauner/mount-idmapped/issues/9
Link: https://lore.kernel.org/r/20220708090134.385160-2-brauner@kernel.org
Cc: Seth Forshee <sforshee@digitalocean.com>
Cc: Amir Goldstein <amir73il@gmail.com>
Cc: Vivek Goyal <vgoyal@redhat.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Aleksa Sarai <cyphar@cyphar.com>
Cc: Miklos Szeredi <mszeredi@redhat.com>
Cc: linux-unionfs@vger.kernel.org
Cc: linux-fsdevel@vger.kernel.org
Reviewed-by: Seth Forshee <sforshee@digitalocean.com>
Signed-off-by: Christian Brauner (Microsoft) <brauner@kernel.org>
166 lines
5.8 KiB
C
166 lines
5.8 KiB
C
/* SPDX-License-Identifier: GPL-2.0-or-later */
|
|
/*
|
|
* Copyright (C) 2016 Namjae Jeon <linkinjeon@kernel.org>
|
|
* Copyright (C) 2018 Samsung Electronics Co., Ltd.
|
|
*/
|
|
|
|
#ifndef __KSMBD_VFS_H__
|
|
#define __KSMBD_VFS_H__
|
|
|
|
#include <linux/file.h>
|
|
#include <linux/fs.h>
|
|
#include <linux/namei.h>
|
|
#include <uapi/linux/xattr.h>
|
|
#include <linux/posix_acl.h>
|
|
|
|
#include "smbacl.h"
|
|
#include "xattr.h"
|
|
|
|
/*
|
|
* Enumeration for stream type.
|
|
*/
|
|
enum {
|
|
DATA_STREAM = 1, /* type $DATA */
|
|
DIR_STREAM /* type $INDEX_ALLOCATION */
|
|
};
|
|
|
|
/* CreateOptions */
|
|
#define CREATE_TREE_CONNECTION cpu_to_le32(0x00000080)
|
|
#define FILE_RESERVE_OPFILTER_LE cpu_to_le32(0x00100000)
|
|
|
|
#define CREATE_OPTION_READONLY 0x10000000
|
|
/* system. NB not sent over wire */
|
|
#define CREATE_OPTION_SPECIAL 0x20000000
|
|
|
|
struct ksmbd_work;
|
|
struct ksmbd_file;
|
|
struct ksmbd_conn;
|
|
|
|
struct ksmbd_dir_info {
|
|
const char *name;
|
|
char *wptr;
|
|
char *rptr;
|
|
int name_len;
|
|
int out_buf_len;
|
|
int num_entry;
|
|
int data_count;
|
|
int last_entry_offset;
|
|
bool hide_dot_file;
|
|
int flags;
|
|
int last_entry_off_align;
|
|
};
|
|
|
|
struct ksmbd_readdir_data {
|
|
struct dir_context ctx;
|
|
union {
|
|
void *private;
|
|
char *dirent;
|
|
};
|
|
|
|
unsigned int used;
|
|
unsigned int dirent_count;
|
|
unsigned int file_attr;
|
|
};
|
|
|
|
/* ksmbd kstat wrapper to get valid create time when reading dir entry */
|
|
struct ksmbd_kstat {
|
|
struct kstat *kstat;
|
|
unsigned long long create_time;
|
|
__le32 file_attributes;
|
|
};
|
|
|
|
int ksmbd_vfs_lock_parent(struct user_namespace *user_ns, struct dentry *parent,
|
|
struct dentry *child);
|
|
int ksmbd_vfs_may_delete(struct user_namespace *user_ns, struct dentry *dentry);
|
|
int ksmbd_vfs_query_maximal_access(struct user_namespace *user_ns,
|
|
struct dentry *dentry, __le32 *daccess);
|
|
int ksmbd_vfs_create(struct ksmbd_work *work, const char *name, umode_t mode);
|
|
int ksmbd_vfs_mkdir(struct ksmbd_work *work, const char *name, umode_t mode);
|
|
int ksmbd_vfs_read(struct ksmbd_work *work, struct ksmbd_file *fp,
|
|
size_t count, loff_t *pos);
|
|
int ksmbd_vfs_write(struct ksmbd_work *work, struct ksmbd_file *fp,
|
|
char *buf, size_t count, loff_t *pos, bool sync,
|
|
ssize_t *written);
|
|
int ksmbd_vfs_fsync(struct ksmbd_work *work, u64 fid, u64 p_id);
|
|
int ksmbd_vfs_remove_file(struct ksmbd_work *work, char *name);
|
|
int ksmbd_vfs_link(struct ksmbd_work *work,
|
|
const char *oldname, const char *newname);
|
|
int ksmbd_vfs_getattr(struct path *path, struct kstat *stat);
|
|
int ksmbd_vfs_fp_rename(struct ksmbd_work *work, struct ksmbd_file *fp,
|
|
char *newname);
|
|
int ksmbd_vfs_truncate(struct ksmbd_work *work,
|
|
struct ksmbd_file *fp, loff_t size);
|
|
struct srv_copychunk;
|
|
int ksmbd_vfs_copy_file_ranges(struct ksmbd_work *work,
|
|
struct ksmbd_file *src_fp,
|
|
struct ksmbd_file *dst_fp,
|
|
struct srv_copychunk *chunks,
|
|
unsigned int chunk_count,
|
|
unsigned int *chunk_count_written,
|
|
unsigned int *chunk_size_written,
|
|
loff_t *total_size_written);
|
|
ssize_t ksmbd_vfs_listxattr(struct dentry *dentry, char **list);
|
|
ssize_t ksmbd_vfs_getxattr(struct user_namespace *user_ns,
|
|
struct dentry *dentry,
|
|
char *xattr_name,
|
|
char **xattr_buf);
|
|
ssize_t ksmbd_vfs_casexattr_len(struct user_namespace *user_ns,
|
|
struct dentry *dentry, char *attr_name,
|
|
int attr_name_len);
|
|
int ksmbd_vfs_setxattr(struct user_namespace *user_ns,
|
|
struct dentry *dentry, const char *attr_name,
|
|
void *attr_value, size_t attr_size, int flags);
|
|
int ksmbd_vfs_xattr_stream_name(char *stream_name, char **xattr_stream_name,
|
|
size_t *xattr_stream_name_size, int s_type);
|
|
int ksmbd_vfs_remove_xattr(struct user_namespace *user_ns,
|
|
struct dentry *dentry, char *attr_name);
|
|
int ksmbd_vfs_kern_path(struct ksmbd_work *work,
|
|
char *name, unsigned int flags, struct path *path,
|
|
bool caseless);
|
|
struct dentry *ksmbd_vfs_kern_path_create(struct ksmbd_work *work,
|
|
const char *name,
|
|
unsigned int flags,
|
|
struct path *path);
|
|
int ksmbd_vfs_empty_dir(struct ksmbd_file *fp);
|
|
void ksmbd_vfs_set_fadvise(struct file *filp, __le32 option);
|
|
int ksmbd_vfs_zero_data(struct ksmbd_work *work, struct ksmbd_file *fp,
|
|
loff_t off, loff_t len);
|
|
struct file_allocated_range_buffer;
|
|
int ksmbd_vfs_fqar_lseek(struct ksmbd_file *fp, loff_t start, loff_t length,
|
|
struct file_allocated_range_buffer *ranges,
|
|
unsigned int in_count, unsigned int *out_count);
|
|
int ksmbd_vfs_unlink(struct user_namespace *user_ns,
|
|
struct dentry *dir, struct dentry *dentry);
|
|
void *ksmbd_vfs_init_kstat(char **p, struct ksmbd_kstat *ksmbd_kstat);
|
|
int ksmbd_vfs_fill_dentry_attrs(struct ksmbd_work *work,
|
|
struct user_namespace *user_ns,
|
|
struct dentry *dentry,
|
|
struct ksmbd_kstat *ksmbd_kstat);
|
|
void ksmbd_vfs_posix_lock_wait(struct file_lock *flock);
|
|
int ksmbd_vfs_posix_lock_wait_timeout(struct file_lock *flock, long timeout);
|
|
void ksmbd_vfs_posix_lock_unblock(struct file_lock *flock);
|
|
int ksmbd_vfs_remove_acl_xattrs(struct user_namespace *user_ns,
|
|
struct dentry *dentry);
|
|
int ksmbd_vfs_remove_sd_xattrs(struct user_namespace *user_ns,
|
|
struct dentry *dentry);
|
|
int ksmbd_vfs_set_sd_xattr(struct ksmbd_conn *conn,
|
|
struct user_namespace *user_ns,
|
|
struct dentry *dentry,
|
|
struct smb_ntsd *pntsd, int len);
|
|
int ksmbd_vfs_get_sd_xattr(struct ksmbd_conn *conn,
|
|
struct user_namespace *user_ns,
|
|
struct dentry *dentry,
|
|
struct smb_ntsd **pntsd);
|
|
int ksmbd_vfs_set_dos_attrib_xattr(struct user_namespace *user_ns,
|
|
struct dentry *dentry,
|
|
struct xattr_dos_attrib *da);
|
|
int ksmbd_vfs_get_dos_attrib_xattr(struct user_namespace *user_ns,
|
|
struct dentry *dentry,
|
|
struct xattr_dos_attrib *da);
|
|
int ksmbd_vfs_set_init_posix_acl(struct user_namespace *user_ns,
|
|
struct inode *inode);
|
|
int ksmbd_vfs_inherit_posix_acl(struct user_namespace *user_ns,
|
|
struct inode *inode,
|
|
struct inode *parent_inode);
|
|
#endif /* __KSMBD_VFS_H__ */
|