-----BEGIN PGP SIGNATURE-----
iQJIBAABCAAyFiEES0KozwfymdVUl37v6iDy2pc3iXMFAmTuKLcUHHBhdWxAcGF1
bC1tb29yZS5jb20ACgkQ6iDy2pc3iXM/Eg//cwaOu/ASS08Cz/tfXeKpzg9UpzbW
uHqGtgdE9ZEvS71z+3dorOJVPEwPr+/yviq3FXYjYHFqvVhLZCvYM9rw+eNo/k4T
I95UTchGUsMWwkw61YBDLythfXm2UL5nabjckO81i9UPtxUYOwF6xQMQXYyMcLL8
6fm1vnCvK5FBEXi2HSUWy3Eb3wdviGdHrL6h19Aeew+q8u33asWSxn9vmBSSFEzZ
492//Pgy0t3FA6paWXQRvoR+GvLgBXNOvHB68cAx9vS8Lq6mAwJJSCRrQtKGh2Gd
YInr49f+TXOosD5Tm6ueWO4sr8RzQZ7nPyM+BLue4Yn2ZzdYgjwfHdkHWS1KeH5X
qVqa9s6/QONvkSCzqHs/ne2qio1Q0/0uGgwOkx6N7oVWQWjE7iTYlADwM0CDJnd2
UD7AHTOgpc88x1T1eW599MZttSCznBTSFXv4waaS5/5NT9n8Db1TpTtCTedOc1x2
n+c+F5BHLy69vhSGCanvum/8i2gNoKVyYaHyaMsQxr5LRcLnvN6oOjWIv7jMKxe7
GavUAxU7M5rxPUH44vrrrI+XztKJOdpCz4S0xp+7pSSSGAK5KkmVVLXjzrlGO1WS
55ixxQWYTGK0KlWHp4Ofi6brE9a4ATKcd1XscPN+AtBYX2ufNHLskCZulu/lyrMx
lAy9RRDe1hHWTvg=
=dnm4
-----END PGP SIGNATURE-----
Merge tag 'lsm-pr-20230829' of git://git.kernel.org/pub/scm/linux/kernel/git/pcmoore/lsm
Pull LSM updates from Paul Moore:
- Add proper multi-LSM support for xattrs in the
security_inode_init_security() hook
Historically the LSM layer has only allowed a single LSM to add an
xattr to an inode, with IMA/EVM measuring that and adding its own as
well. As we work towards promoting IMA/EVM to a "proper LSM" instead
of the special case that it is now, we need to better support the
case of multiple LSMs each adding xattrs to an inode and after
several attempts we now appear to have something that is working
well. It is worth noting that in the process of making this change we
uncovered a problem with Smack's SMACK64TRANSMUTE xattr which is also
fixed in this pull request.
- Additional LSM hook constification
Two patches to constify parameters to security_capget() and
security_binder_transfer_file(). While I generally don't make a
special note of who submitted these patches, these were the work of
an Outreachy intern, Khadija Kamran, and that makes me happy;
hopefully it does the same for all of you reading this.
- LSM hook comment header fixes
One patch to add a missing hook comment header, one to fix a minor
typo.
- Remove an old, unused credential function declaration
It wasn't clear to me who should pick this up, but it was trivial,
obviously correct, and arguably the LSM layer has a vested interest
in credentials so I merged it. Sadly I'm now noticing that despite my
subject line cleanup I didn't cleanup the "unsued" misspelling, sigh
* tag 'lsm-pr-20230829' of git://git.kernel.org/pub/scm/linux/kernel/git/pcmoore/lsm:
lsm: constify the 'file' parameter in security_binder_transfer_file()
lsm: constify the 'target' parameter in security_capget()
lsm: add comment block for security_sk_classify_flow LSM hook
security: Fix ret values doc for security_inode_init_security()
cred: remove unsued extern declaration change_create_files_as()
evm: Support multiple LSMs providing an xattr
evm: Align evm_inode_init_security() definition with LSM infrastructure
smack: Set the SMACK64TRANSMUTE xattr in smack_inode_init_security()
security: Allow all LSMs to provide xattrs for inode_init_security hook
lsm: fix typo in security_file_lock() comment header
After being vouched for by a system keyring, only allow keys into the .ima
and .evm keyrings that have the digitalSignature usage field set.
Link: https://lore.kernel.org/all/41dffdaeb7eb7840f7e38bc691fbda836635c9f9.camel@linux.ibm.com
Suggested-by: Mimi Zohar <zohar@linux.ibm.com>
Signed-off-by: Eric Snowberg <eric.snowberg@oracle.com>
Acked-and-tested-by: Mimi Zohar <zohar@linux.ibm.com>
Reviewed-by: Jarkko Sakkinen <jarkko@kernel.org>
Signed-off-by: Jarkko Sakkinen <jarkko@kernel.org>
Currently, evm_inode_init_security() processes a single LSM xattr from the
array passed by security_inode_init_security(), and calculates the HMAC on
it and other inode metadata.
As the LSM infrastructure now can pass to EVM an array with multiple
xattrs, scan them until the terminator (xattr name NULL), and calculate the
HMAC on all of them.
Also, double check that the xattrs array terminator is the first non-filled
slot (obtained with lsm_get_xattr_slot()). Consumers of the xattrs array,
such as the initxattrs() callbacks, rely on the terminator.
Finally, change the name of the lsm_xattr parameter of evm_init_hmac() to
xattrs, to reflect the new type of information passed.
Signed-off-by: Roberto Sassu <roberto.sassu@huawei.com>
Reviewed-by: Mimi Zohar <zohar@linux.ibm.com>
Acked-by: Mimi Zohar <zohar@linux.ibm.com>
Signed-off-by: Paul Moore <paul@paul-moore.com>
Change the evm_inode_init_security() definition to align with the LSM
infrastructure. Keep the existing behavior of including in the HMAC
calculation only the first xattr provided by LSMs.
Changing the evm_inode_init_security() definition requires passing the
xattr array allocated by security_inode_init_security(), and the number of
xattrs filled by previously invoked LSMs.
Use the newly introduced lsm_get_xattr_slot() to position EVM correctly in
the xattrs array, like a regular LSM, and to increment the number of filled
slots. For now, the LSM infrastructure allocates enough xattrs slots to
store the EVM xattr, without using the reservation mechanism.
Signed-off-by: Roberto Sassu <roberto.sassu@huawei.com>
Reviewed-by: Mimi Zohar <zohar@linux.ibm.com>
Acked-by: Mimi Zohar <zohar@linux.ibm.com>
Signed-off-by: Paul Moore <paul@paul-moore.com>
Fix build warnings (function parameters description) for
evm_read_protected_xattrs(), evm_set_key() and evm_verifyxattr().
Fixes: 7626676320 ("evm: provide a function to set the EVM key from the kernel") # v4.5+
Fixes: 8314b6732a ("ima: Define new template fields xattrnames, xattrlengths and xattrvalues") # v5.14+
Fixes: 2960e6cb5f ("evm: additional parameter to pass integrity cache entry 'iint'") # v3.2+
Signed-off-by: Roberto Sassu <roberto.sassu@huawei.com>
Signed-off-by: Mimi Zohar <zohar@linux.ibm.com>
Add the description for missing parameters of evm_inode_setattr() to
avoid the warning arising with W=n compile option.
Fixes: 817b54aa45 ("evm: add evm_inode_setattr to prevent updating an invalid security.evm") # v3.2+
Fixes: c1632a0f11 ("fs: port ->setattr() to pass mnt_idmap") # v6.3+
Signed-off-by: Roberto Sassu <roberto.sassu@huawei.com>
Reviewed-by: Stefan Berger <stefanb@linux.ibm.com>
Signed-off-by: Mimi Zohar <zohar@linux.ibm.com>
-----BEGIN PGP SIGNATURE-----
iIoEABYIADIWIQQdXVVFGN5XqKr1Hj7LwZzRsCrn5QUCY/OUGBQcem9oYXJAbGlu
dXguaWJtLmNvbQAKCRDLwZzRsCrn5baCAP0a4N8OiH5Sv9EQ5xAI8jbDwOeE/Aen
izx6RXiBncaY9QEA7WrXUS3y/8zO3dWSL9feviGDuajTn0bJpmWXkCeh8wM=
=pwAo
-----END PGP SIGNATURE-----
Merge tag 'integrity-v6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/zohar/linux-integrity
Pull integrity update from Mimi Zohar:
"One doc and one code cleanup, and two bug fixes"
* tag 'integrity-v6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/zohar/linux-integrity:
ima: Introduce MMAP_CHECK_REQPROT hook
ima: Align ima_file_mmap() parameters with mmap_file LSM hook
evm: call dump_security_xattr() in all cases to remove code duplication
ima: fix ima_delete_rules() kernel-doc warning
ima: return IMA digest value only when IMA_COLLECTED flag is set
ima: fix error handling logic when file measurement failed
Currently dump_security_xattr() is used to dump security xattr value
which is larger than 64 bytes, otherwise, pr_debug() is used. In order
to remove code duplication, refactor dump_security_xattr() and call it
in all cases.
Signed-off-by: Xiu Jianfeng <xiujianfeng@huawei.com>
Signed-off-by: Mimi Zohar <zohar@linux.ibm.com>
Convert to struct mnt_idmap.
Last cycle we merged the necessary infrastructure in
256c8aed2b ("fs: introduce dedicated idmap type for mounts").
This is just the conversion to struct mnt_idmap.
Currently we still pass around the plain namespace that was attached to a
mount. This is in general pretty convenient but it makes it easy to
conflate namespaces that are relevant on the filesystem with namespaces
that are relevent on the mount level. Especially for non-vfs developers
without detailed knowledge in this area this can be a potential source for
bugs.
Once the conversion to struct mnt_idmap is done all helpers down to the
really low-level helpers will take a struct mnt_idmap argument instead of
two namespace arguments. This way it becomes impossible to conflate the two
eliminating the possibility of any bugs. All of the vfs and all filesystems
only operate on struct mnt_idmap.
Acked-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Christian Brauner (Microsoft) <brauner@kernel.org>
Convert to struct mnt_idmap.
Last cycle we merged the necessary infrastructure in
256c8aed2b ("fs: introduce dedicated idmap type for mounts").
This is just the conversion to struct mnt_idmap.
Currently we still pass around the plain namespace that was attached to a
mount. This is in general pretty convenient but it makes it easy to
conflate namespaces that are relevant on the filesystem with namespaces
that are relevent on the mount level. Especially for non-vfs developers
without detailed knowledge in this area this can be a potential source for
bugs.
Once the conversion to struct mnt_idmap is done all helpers down to the
really low-level helpers will take a struct mnt_idmap argument instead of
two namespace arguments. This way it becomes impossible to conflate the two
eliminating the possibility of any bugs. All of the vfs and all filesystems
only operate on struct mnt_idmap.
Acked-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Christian Brauner (Microsoft) <brauner@kernel.org>
Convert to struct mnt_idmap.
Last cycle we merged the necessary infrastructure in
256c8aed2b ("fs: introduce dedicated idmap type for mounts").
This is just the conversion to struct mnt_idmap.
Currently we still pass around the plain namespace that was attached to a
mount. This is in general pretty convenient but it makes it easy to
conflate namespaces that are relevant on the filesystem with namespaces
that are relevent on the mount level. Especially for non-vfs developers
without detailed knowledge in this area this can be a potential source for
bugs.
Once the conversion to struct mnt_idmap is done all helpers down to the
really low-level helpers will take a struct mnt_idmap argument instead of
two namespace arguments. This way it becomes impossible to conflate the two
eliminating the possibility of any bugs. All of the vfs and all filesystems
only operate on struct mnt_idmap.
Acked-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Christian Brauner (Microsoft) <brauner@kernel.org>
Convert to struct mnt_idmap.
Last cycle we merged the necessary infrastructure in
256c8aed2b ("fs: introduce dedicated idmap type for mounts").
This is just the conversion to struct mnt_idmap.
Currently we still pass around the plain namespace that was attached to a
mount. This is in general pretty convenient but it makes it easy to
conflate namespaces that are relevant on the filesystem with namespaces
that are relevent on the mount level. Especially for non-vfs developers
without detailed knowledge in this area this can be a potential source for
bugs.
Once the conversion to struct mnt_idmap is done all helpers down to the
really low-level helpers will take a struct mnt_idmap argument instead of
two namespace arguments. This way it becomes impossible to conflate the two
eliminating the possibility of any bugs. All of the vfs and all filesystems
only operate on struct mnt_idmap.
Acked-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Christian Brauner (Microsoft) <brauner@kernel.org>
Convert to struct mnt_idmap.
Last cycle we merged the necessary infrastructure in
256c8aed2b ("fs: introduce dedicated idmap type for mounts").
This is just the conversion to struct mnt_idmap.
Currently we still pass around the plain namespace that was attached to a
mount. This is in general pretty convenient but it makes it easy to
conflate namespaces that are relevant on the filesystem with namespaces
that are relevent on the mount level. Especially for non-vfs developers
without detailed knowledge in this area this can be a potential source for
bugs.
Once the conversion to struct mnt_idmap is done all helpers down to the
really low-level helpers will take a struct mnt_idmap argument instead of
two namespace arguments. This way it becomes impossible to conflate the two
eliminating the possibility of any bugs. All of the vfs and all filesystems
only operate on struct mnt_idmap.
Acked-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Christian Brauner (Microsoft) <brauner@kernel.org>
-----BEGIN PGP SIGNATURE-----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=klFk
-----END PGP SIGNATURE-----
Merge tag 'lsm-pr-20221212' of git://git.kernel.org/pub/scm/linux/kernel/git/pcmoore/lsm
Pull lsm updates from Paul Moore:
- Improve the error handling in the device cgroup such that memory
allocation failures when updating the access policy do not
potentially alter the policy.
- Some minor fixes to reiserfs to ensure that it properly releases
LSM-related xattr values.
- Update the security_socket_getpeersec_stream() LSM hook to take
sockptr_t values.
Previously the net/BPF folks updated the getsockopt code in the
network stack to leverage the sockptr_t type to make it easier to
pass both kernel and __user pointers, but unfortunately when they did
so they didn't convert the LSM hook.
While there was/is no immediate risk by not converting the LSM hook,
it seems like this is a mistake waiting to happen so this patch
proactively does the LSM hook conversion.
- Convert vfs_getxattr_alloc() to return an int instead of a ssize_t
and cleanup the callers. Internally the function was never going to
return anything larger than an int and the callers were doing some
very odd things casting the return value; this patch fixes all that
and helps bring a bit of sanity to vfs_getxattr_alloc() and its
callers.
- More verbose, and helpful, LSM debug output when the system is booted
with "lsm.debug" on the command line. There are examples in the
commit description, but the quick summary is that this patch provides
better information about which LSMs are enabled and the ordering in
which they are processed.
- General comment and kernel-doc fixes and cleanups.
* tag 'lsm-pr-20221212' of git://git.kernel.org/pub/scm/linux/kernel/git/pcmoore/lsm:
lsm: Fix description of fs_context_parse_param
lsm: Add/fix return values in lsm_hooks.h and fix formatting
lsm: Clarify documentation of vm_enough_memory hook
reiserfs: Add missing calls to reiserfs_security_free()
lsm,fs: fix vfs_getxattr_alloc() return type and caller error paths
device_cgroup: Roll back to original exceptions after copy failure
LSM: Better reporting of actual LSMs at boot
lsm: make security_socket_getpeersec_stream() sockptr_t safe
audit: Fix some kernel-doc warnings
lsm: remove obsoleted comments for security hooks
fs: edit a comment made in bad taste
The vfs_getxattr_alloc() function currently returns a ssize_t value
despite the fact that it only uses int values internally for return
values. Fix this by converting vfs_getxattr_alloc() to return an
int type and adjust the callers as necessary. As part of these
caller modifications, some of the callers are fixed to properly free
the xattr value buffer on both success and failure to ensure that
memory is not leaked in the failure case.
Reviewed-by: Serge Hallyn <serge@hallyn.com>
Reviewed-by: Mimi Zohar <zohar@linux.ibm.com>
Signed-off-by: Paul Moore <paul@paul-moore.com>
When evm_status is INTEGRITY_PASS then this function returns early and so
later codepaths that check for evm_status != INTEGRITY_PASS can be removed
as they are dead code.
Fixes: e61b135f7b ("integrity: implement get and set acl hook")
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Christian Brauner (Microsoft) <brauner@kernel.org>
The security and integrity infrastructure has dedicated hooks now so
evm_xattr_acl_change() is dead code. Before this commit the callchain was:
evm_protect_xattr()
-> evm_xattr_change()
-> evm_xattr_acl_change()
where evm_protect_xattr() was hit from evm_inode_setxattr() and
evm_inode_removexattr(). But now we have evm_inode_set_acl() and
evm_inode_remove_acl() and have switched over the vfs to rely on the posix
acl api so the code isn't hit anymore.
Suggested-by: Paul Moore <paul@paul-moore.com>
Signed-off-by: Christian Brauner (Microsoft) <brauner@kernel.org>
The current way of setting and getting posix acls through the generic
xattr interface is error prone and type unsafe. The vfs needs to
interpret and fixup posix acls before storing or reporting it to
userspace. Various hacks exist to make this work. The code is hard to
understand and difficult to maintain in it's current form. Instead of
making this work by hacking posix acls through xattr handlers we are
building a dedicated posix acl api around the get and set inode
operations. This removes a lot of hackiness and makes the codepaths
easier to maintain. A lot of background can be found in [1].
So far posix acls were passed as a void blob to the security and
integrity modules. Some of them like evm then proceed to interpret the
void pointer and convert it into the kernel internal struct posix acl
representation to perform their integrity checking magic. This is
obviously pretty problematic as that requires knowledge that only the
vfs is guaranteed to have and has lead to various bugs. Add a proper
security hook for setting posix acls and pass down the posix acls in
their appropriate vfs format instead of hacking it through a void
pointer stored in the uapi format.
I spent considerate time in the security module and integrity
infrastructure and audited all codepaths. EVM is the only part that
really has restrictions based on the actual posix acl values passed
through it (e.g., i_mode). Before this dedicated hook EVM used to translate
from the uapi posix acl format sent to it in the form of a void pointer
into the vfs format. This is not a good thing. Instead of hacking around in
the uapi struct give EVM the posix acls in the appropriate vfs format and
perform sane permissions checks that mirror what it used to to in the
generic xattr hook.
IMA doesn't have any restrictions on posix acls. When posix acls are
changed it just wants to update its appraisal status to trigger an EVM
revalidation.
The removal of posix acls is equivalent to passing NULL to the posix set
acl hooks. This is the same as before through the generic xattr api.
Link: https://lore.kernel.org/all/20220801145520.1532837-1-brauner@kernel.org [1]
Acked-by: Paul Moore <paul@paul-moore.com> (LSM)
Signed-off-by: Christian Brauner (Microsoft) <brauner@kernel.org>
The uapi POSIX ACL struct passed through the value argument during
setxattr() contains {g,u}id values encoded via ACL_{GROUP,USER} entries
that should actually be stored in the form of k{g,u}id_t (See [1] for a
long explanation of the issue.).
In 0c5fd887d2 ("acl: move idmapped mount fixup into vfs_{g,s}etxattr()")
we took the mount's idmapping into account in order to let overlayfs
handle POSIX ACLs on idmapped layers correctly. The fixup is currently
performed directly in vfs_setxattr() which piles on top of the earlier
hackiness by handling the mount's idmapping and stuff the vfs{g,u}id_t
values into the uapi struct as well. While that is all correct and works
fine it's just ugly.
Now that we have introduced vfs_make_posix_acl() earlier move handling
idmapped mounts out of vfs_setxattr() and into the POSIX ACL handler
where it belongs.
Note that we also need to call vfs_make_posix_acl() for EVM which
interpretes POSIX ACLs during security_inode_setxattr(). Leave them a
longer comment for future reference.
All filesystems that support idmapped mounts via FS_ALLOW_IDMAP use the
standard POSIX ACL xattr handlers and are covered by this change. This
includes overlayfs which simply calls vfs_{g,s}etxattr().
The following filesystems use custom POSIX ACL xattr handlers: 9p, cifs,
ecryptfs, and ntfs3 (and overlayfs but we've covered that in the paragraph
above) and none of them support idmapped mounts yet.
Link: https://lore.kernel.org/all/20220801145520.1532837-1-brauner@kernel.org/ [1]
Signed-off-by: Christian Brauner (Microsoft) <brauner@kernel.org>
Reviewed-by: Seth Forshee (DigitalOcean) <sforshee@kernel.org>
-----BEGIN PGP SIGNATURE-----
iIoEABYIADIWIQQdXVVFGN5XqKr1Hj7LwZzRsCrn5QUCYulqTBQcem9oYXJAbGlu
dXguaWJtLmNvbQAKCRDLwZzRsCrn5SBBAP9nbAW1SPa/hDqbrclHdDrS59VkSVwv
6ZO2yAmxJAptHwD+JzyJpJiZsqVN/Tu85V1PqeAt9c8az8f3CfDBp2+w7AA=
=Ad+c
-----END PGP SIGNATURE-----
Merge tag 'integrity-v6.0' of git://git.kernel.org/pub/scm/linux/kernel/git/zohar/linux-integrity
Pull integrity updates from Mimi Zohar:
"Aside from the one EVM cleanup patch, all the other changes are kexec
related.
On different architectures different keyrings are used to verify the
kexec'ed kernel image signature. Here are a number of preparatory
cleanup patches and the patches themselves for making the keyrings -
builtin_trusted_keyring, .machine, .secondary_trusted_keyring, and
.platform - consistent across the different architectures"
* tag 'integrity-v6.0' of git://git.kernel.org/pub/scm/linux/kernel/git/zohar/linux-integrity:
kexec, KEYS, s390: Make use of built-in and secondary keyring for signature verification
arm64: kexec_file: use more system keyrings to verify kernel image signature
kexec, KEYS: make the code in bzImage64_verify_sig generic
kexec: clean up arch_kexec_kernel_verify_sig
kexec: drop weak attribute from functions
kexec_file: drop weak attribute from functions
evm: Use IS_ENABLED to initialize .enabled
-----BEGIN PGP SIGNATURE-----
iHUEABYKAB0WIQRAhzRXHqcMeLMyaSiRxhvAZXjcogUCYufP6AAKCRCRxhvAZXjc
omzRAQCGJ11r7T0C7t1kTdQiFSs5XN9ksFa86Hfj3dHEBIj+LQEA+bZ2/LLpElDz
zPekgXkFQqdMr+FUL8sk94dzHT0GAgk=
=BcK/
-----END PGP SIGNATURE-----
Merge tag 'fs.idmapped.vfsuid.v5.20' of git://git.kernel.org/pub/scm/linux/kernel/git/brauner/linux
Pull fs idmapping updates from Christian Brauner:
"This introduces the new vfs{g,u}id_t types we agreed on. Similar to
k{g,u}id_t the new types are just simple wrapper structs around
regular {g,u}id_t types.
They allow to establish a type safety boundary in the VFS for idmapped
mounts preventing confusion betwen {g,u}ids mapped into an idmapped
mount and {g,u}ids mapped into the caller's or the filesystem's
idmapping.
An initial set of helpers is introduced that allows to operate on
vfs{g,u}id_t types. We will remove all references to non-type safe
idmapped mounts helpers in the very near future. The patches do
already exist.
This converts the core attribute changing codepaths which become
significantly easier to reason about because of this change.
Just a few highlights here as the patches give detailed overviews of
what is happening in the commit messages:
- The kernel internal struct iattr contains type safe vfs{g,u}id_t
values clearly communicating that these values have to take a given
mount's idmapping into account.
- The ownership values placed in struct iattr to change ownership are
identical for idmapped and non-idmapped mounts going forward. This
also allows to simplify stacking filesystems such as overlayfs that
change attributes In other words, they always represent the values.
- Instead of open coding checks for whether ownership changes have
been requested and an actual update of the inode is required we now
have small static inline wrappers that abstract this logic away
removing a lot of code duplication from individual filesystems that
all open-coded the same checks"
* tag 'fs.idmapped.vfsuid.v5.20' of git://git.kernel.org/pub/scm/linux/kernel/git/brauner/linux:
mnt_idmapping: align kernel doc and parameter order
mnt_idmapping: use new helpers in mapped_fs{g,u}id()
fs: port HAS_UNMAPPED_ID() to vfs{g,u}id_t
mnt_idmapping: return false when comparing two invalid ids
attr: fix kernel doc
attr: port attribute changes to new types
security: pass down mount idmapping to setattr hook
quota: port quota helpers mount ids
fs: port to iattr ownership update helpers
fs: introduce tiny iattr ownership update helpers
fs: use mount types in iattr
fs: add two type safe mapping helpers
mnt_idmapping: add vfs{g,u}id_t
Use IS_ENABLED(CONFIG_XXX) instead of #ifdef/#endif statements to
initialize .enabled, minor simplicity improvement.
Signed-off-by: Xiu Jianfeng <xiujianfeng@huawei.com>
Reviewed-by: Ahmad Fatoum <a.fatoum@pengutronix.de>
Signed-off-by: Mimi Zohar <zohar@linux.ibm.com>
Now that we introduced new infrastructure to increase the type safety
for filesystems supporting idmapped mounts port the first part of the
vfs over to them.
This ports the attribute changes codepaths to rely on the new better
helpers using a dedicated type.
Before this change we used to take a shortcut and place the actual
values that would be written to inode->i_{g,u}id into struct iattr. This
had the advantage that we moved idmappings mostly out of the picture
early on but it made reasoning about changes more difficult than it
should be.
The filesystem was never explicitly told that it dealt with an idmapped
mount. The transition to the value that needed to be stored in
inode->i_{g,u}id appeared way too early and increased the probability of
bugs in various codepaths.
We know place the same value in struct iattr no matter if this is an
idmapped mount or not. The vfs will only deal with type safe
vfs{g,u}id_t. This makes it massively safer to perform permission checks
as the type will tell us what checks we need to perform and what helpers
we need to use.
Fileystems raising FS_ALLOW_IDMAP can't simply write ia_vfs{g,u}id to
inode->i_{g,u}id since they are different types. Instead they need to
use the dedicated vfs{g,u}id_to_k{g,u}id() helpers that map the
vfs{g,u}id into the filesystem.
The other nice effect is that filesystems like overlayfs don't need to
care about idmappings explicitly anymore and can simply set up struct
iattr accordingly directly.
Link: https://lore.kernel.org/lkml/CAHk-=win6+ahs1EwLkcq8apqLi_1wXFWbrPf340zYEhObpz4jA@mail.gmail.com [1]
Link: https://lore.kernel.org/r/20220621141454.2914719-9-brauner@kernel.org
Cc: Seth Forshee <sforshee@digitalocean.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Aleksa Sarai <cyphar@cyphar.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
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 (Microsoft) <brauner@kernel.org>
Before this change we used to take a shortcut and place the actual
values that would be written to inode->i_{g,u}id into struct iattr. This
had the advantage that we moved idmappings mostly out of the picture
early on but it made reasoning about changes more difficult than it
should be.
The filesystem was never explicitly told that it dealt with an idmapped
mount. The transition to the value that needed to be stored in
inode->i_{g,u}id appeared way too early and increased the probability of
bugs in various codepaths.
We know place the same value in struct iattr no matter if this is an
idmapped mount or not. The vfs will only deal with type safe
vfs{g,u}id_t. This makes it massively safer to perform permission checks
as the type will tell us what checks we need to perform and what helpers
we need to use.
Adapt the security_inode_setattr() helper to pass down the mount's
idmapping to account for that change.
Link: https://lore.kernel.org/r/20220621141454.2914719-8-brauner@kernel.org
Cc: Seth Forshee <sforshee@digitalocean.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Aleksa Sarai <cyphar@cyphar.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
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 (Microsoft) <brauner@kernel.org>
Earlier we introduced new helpers to abstract ownership update and
remove code duplication. This converts all filesystems supporting
idmapped mounts to make use of these new helpers.
For now we always pass the initial idmapping which makes the idmapping
functions these helpers call nops.
This is done because we currently always pass the actual value to be
written to i_{g,u}id via struct iattr. While this allowed us to treat
the {g,u}id values in struct iattr as values that can be directly
written to inode->i_{g,u}id it also increases the potential for
confusion for filesystems.
Now that we are have dedicated types to prevent this confusion we will
ultimately only map the value from the idmapped mount into a filesystem
value that can be written to inode->i_{g,u}id when the filesystem
actually updates the inode. So pass down the initial idmapping until we
finished that conversion at which point we pass down the mount's
idmapping.
No functional changes intended.
Link: https://lore.kernel.org/r/20220621141454.2914719-6-brauner@kernel.org
Cc: Seth Forshee <sforshee@digitalocean.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Aleksa Sarai <cyphar@cyphar.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
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 (Microsoft) <brauner@kernel.org>
This reverts commit ccf11dbaa0.
Commit ccf11dbaa0 ("evm: Fix memleak in init_desc") said there is
memleak in init_desc. That may be incorrect, as we can see, tmp_tfm is
saved in one of the two global variables hmac_tfm or evm_tfm[hash_algo],
then if init_desc is called next time, there is no need to alloc tfm
again, so in the error path of kmalloc desc or crypto_shash_init(desc),
It is not a problem without freeing tmp_tfm.
And also that commit did not reset the global variable to NULL after
freeing tmp_tfm and this makes *tfm a dangling pointer which may cause a
UAF issue.
Reported-by: Guozihua (Scott) <guozihua@huawei.com>
Signed-off-by: Xiu Jianfeng <xiujianfeng@huawei.com>
Signed-off-by: Mimi Zohar <zohar@linux.ibm.com>
Make hmac_tfm static since it's not used anywhere else besides the file
it is in.
Remove declaration of hash_tfm since it doesn't exist.
Signed-off-by: Stefan Berger <stefanb@linux.ibm.com>
Signed-off-by: Mimi Zohar <zohar@linux.ibm.com>
Return INTEGRITY_PASS for the enum integrity_status rather than 0.
Signed-off-by: Stefan Berger <stefanb@linux.ibm.com>
Signed-off-by: Mimi Zohar <zohar@linux.ibm.com>
__setup() handlers should return 1 if the parameter is handled.
Returning 0 causes the entire string to be added to init's
environment strings (limited to 32 strings), unnecessarily polluting it.
Using the documented string "evm=fix" causes an Unknown parameter message:
Unknown kernel command line parameters
"BOOT_IMAGE=/boot/bzImage-517rc5 evm=fix", will be passed to user space.
and that string is added to init's environment string space:
Run /sbin/init as init process
with arguments:
/sbin/init
with environment:
HOME=/
TERM=linux
BOOT_IMAGE=/boot/bzImage-517rc5
evm=fix
With this change, using "evm=fix" acts as expected and an invalid
option ("evm=evm") causes a warning to be printed:
evm: invalid "evm" mode
but init's environment is not polluted with this string, as expected.
Fixes: 7102ebcd65 ("evm: permit only valid security.evm xattrs to be updated")
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Reported-by: Igor Zhbanov <i.zhbanov@omprussia.ru>
Link: lore.kernel.org/r/64644a2f-4a20-bab3-1e15-3b2cdd0defe3@omprussia.ru
Signed-off-by: Mimi Zohar <zohar@linux.ibm.com>
The evm_fixmode is only configurable by command-line option and it is never
modified outside initcalls, so declaring it with __ro_after_init is better.
Signed-off-by: Austin Kim <austin.kim@lge.com>
Cc: stable@vger.kernel.org
Signed-off-by: Mimi Zohar <zohar@linux.ibm.com>
The kernel and the user obtain an xattr value in two different ways:
kernel (EVM): uses vfs_getxattr_alloc() which obtains the xattr value from
the filesystem handler (raw value);
user (ima-evm-utils): uses vfs_getxattr() which obtains the xattr value
from the LSMs (normalized value).
Normally, this does not have an impact unless security.selinux is set with
setfattr, with a value not terminated by '\0' (this is not the recommended
way, security.selinux should be set with the appropriate tools such as
chcon and restorecon).
In this case, the kernel and the user see two different xattr values: the
former sees the xattr value without '\0' (raw value), the latter sees the
value with '\0' (value normalized by SELinux).
This could result in two different verification outcomes from EVM and
ima-evm-utils, if a signature was calculated with a security.selinux value
terminated by '\0' and the value set in the filesystem is not terminated by
'\0'. The former would report verification failure due to the missing '\0',
while the latter would report verification success (because it gets the
normalized value with '\0').
This patch mitigates this issue by comparing in evm_calc_hmac_or_hash() the
size of the xattr returned by the two xattr functions and by warning the
user if there is a discrepancy.
Signed-off-by: Roberto Sassu <roberto.sassu@huawei.com>
Suggested-by: Mimi Zohar <zohar@linux.ibm.com>
Signed-off-by: Mimi Zohar <zohar@linux.ibm.com>
Output the data used in calculating the EVM digest and the resulting
digest as ascii hexadecimal strings.
Suggested-by: Lakshmi Ramasubramanian <nramas@linux.microsoft.com> (CONFIG_DYNAMIC_DEBUG)
Reviewed-by: Lakshmi Ramasubramanian <nramas@linux.microsoft.com>
Reported-by: kernel test robot <lkp@intel.com> (Use %zu for size_t)
Signed-off-by: Mimi Zohar <zohar@linux.ibm.com>
The endianness of a variable written to the measurement list cannot be
determined at compile time, as it depends on the value of the
ima_canonical_fmt global variable (set through a kernel option with the
same name if the machine is big endian).
If ima_canonical_fmt is false, the endianness of a variable is the same as
the machine; if ima_canonical_fmt is true, the endianness is little endian.
The warning arises due to this type of instruction:
var = cpu_to_leXX(var)
which tries to assign a value in little endian to a variable with native
endianness (little or big endian).
Given that the variables set with this instruction are not used in any
operation but just written to a buffer, it is safe to force the type of the
value being set to be the same of the type of the variable with:
var = (__force <var type>)cpu_to_leXX(var)
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Roberto Sassu <roberto.sassu@huawei.com>
Signed-off-by: Mimi Zohar <zohar@linux.ibm.com>
This patch avoids that evm_write_xattrs() returns an error when audit is
not enabled. The ab variable can be NULL and still be passed to the other
audit_log_() functions, as those functions do not include any instruction.
Signed-off-by: Roberto Sassu <roberto.sassu@huawei.com>
Signed-off-by: Mimi Zohar <zohar@linux.ibm.com>
This patch defines the new template fields xattrnames, xattrlengths and
xattrvalues, which contain respectively a list of xattr names (strings,
separated by |), lengths (u32, hex) and values (hex). If an xattr is not
present, the name and length are not displayed in the measurement list.
Reported-by: kernel test robot <lkp@intel.com> (Missing prototype def)
Signed-off-by: Roberto Sassu <roberto.sassu@huawei.com>
Signed-off-by: Mimi Zohar <zohar@linux.ibm.com>
Currently, the evm_config_default_xattrnames array contains xattr names
only related to LSMs which are enabled in the kernel configuration.
However, EVM portable signatures do not depend on local information and a
vendor might include in the signature calculation xattrs that are not
enabled in the target platform.
Just including all xattrs names in evm_config_default_xattrnames is not a
safe approach, because a target system might have already calculated
signatures or HMACs based only on the enabled xattrs. After applying this
patch, EVM would verify those signatures and HMACs with all xattrs instead.
The non-enabled ones, which could possibly exist, would cause a
verification error.
Thus, this patch adds a new field named enabled to the xattr_list
structure, which is set to true if the LSM associated to a given xattr name
is enabled in the kernel configuration. The non-enabled xattrs are taken
into account only in evm_calc_hmac_or_hash(), if the passed security.evm
type is EVM_XATTR_PORTABLE_DIGSIG.
The new function evm_protected_xattr_if_enabled() has been defined so that
IMA can include all protected xattrs and not only the enabled ones in the
measurement list, if the new template fields xattrnames, xattrlengths or
xattrvalues have been included in the template format.
Signed-off-by: Roberto Sassu <roberto.sassu@huawei.com>
Signed-off-by: Mimi Zohar <zohar@linux.ibm.com>
With the patch to allow xattr/attr operations if a portable signature
verification fails, cp and tar can copy all xattrs/attrs so that at the
end of the process verification succeeds.
However, it might happen that the xattrs/attrs are already set to the
correct value (taken at signing time) and signature verification succeeds
before the copy has completed. For example, an archive might contains files
owned by root and the archive is extracted by root.
Then, since portable signatures are immutable, all subsequent operations
fail (e.g. fchown()), even if the operation is legitimate (does not alter
the current value).
This patch avoids this problem by reporting successful operation to user
space when that operation does not alter the current value of xattrs/attrs.
With this patch, the one that introduces evm_hmac_disabled() and the one
that allows a metadata operation on the INTEGRITY_FAIL_IMMUTABLE error, EVM
portable signatures can be used without disabling metadata verification
(by setting EVM_ALLOW_METADATA_WRITES). Due to keeping metadata
verification enabled, altering immutable metadata protected with a portable
signature that was successfully verified will be denied (existing
behavior).
Reported-by: kernel test robot <lkp@intel.com> [implicit declaration of function]
Signed-off-by: Roberto Sassu <roberto.sassu@huawei.com>
Reviewed-by: Christian Brauner <christian.brauner@ubuntu.com>
Cc: Andreas Gruenbacher <agruenba@redhat.com>
Signed-off-by: Mimi Zohar <zohar@linux.ibm.com>
In preparation for 'evm: Allow setxattr() and setattr() for unmodified
metadata', this patch passes mnt_userns to the inode set/remove xattr hooks
so that the GID of the inode on an idmapped mount is correctly determined
by posix_acl_update_mode().
Signed-off-by: Roberto Sassu <roberto.sassu@huawei.com>
Reviewed-by: Christian Brauner <christian.brauner@ubuntu.com>
Cc: Andreas Gruenbacher <agruenba@redhat.com>
Signed-off-by: Mimi Zohar <zohar@linux.ibm.com>
If files with portable signatures are copied from one location to another
or are extracted from an archive, verification can temporarily fail until
all xattrs/attrs are set in the destination. Only portable signatures may
be moved or copied from one file to another, as they don't depend on
system-specific information such as the inode generation. Instead portable
signatures must include security.ima.
Unlike other security.evm types, EVM portable signatures are also
immutable. Thus, it wouldn't be a problem to allow xattr/attr operations
when verification fails, as portable signatures will never be replaced with
the HMAC on possibly corrupted xattrs/attrs.
This patch first introduces a new integrity status called
INTEGRITY_FAIL_IMMUTABLE, that allows callers of
evm_verify_current_integrity() to detect that a portable signature didn't
pass verification and then adds an exception in evm_protect_xattr() and
evm_inode_setattr() for this status and returns 0 instead of -EPERM.
Signed-off-by: Roberto Sassu <roberto.sassu@huawei.com>
Signed-off-by: Mimi Zohar <zohar@linux.ibm.com>
When a file is being created, LSMs can set the initial label with the
inode_init_security hook. If no HMAC key is loaded, the new file will have
LSM xattrs but not the HMAC. It is also possible that the file remains
without protected xattrs after creation if no active LSM provided it, or
because the filesystem does not support them.
Unfortunately, EVM will deny any further metadata operation on new files,
as evm_protect_xattr() will return the INTEGRITY_NOLABEL error if protected
xattrs exist without security.evm, INTEGRITY_NOXATTRS if no protected
xattrs exist or INTEGRITY_UNKNOWN if xattrs are not supported. This would
limit the usability of EVM when only a public key is loaded, as commands
such as cp or tar with the option to preserve xattrs won't work.
This patch introduces the evm_hmac_disabled() function to determine whether
or not it is safe to ignore verification errors, based on the ability of
EVM to calculate HMACs. If the HMAC key is not loaded, and it cannot be
loaded in the future due to the EVM_SETUP_COMPLETE initialization flag,
allowing an operation despite the attrs/xattrs being found invalid will not
make them valid.
Since the post hooks can be executed even when the HMAC key is not loaded,
this patch also ensures that the EVM_INIT_HMAC initialization flag is set
before the post hooks call evm_update_evmxattr().
Signed-off-by: Roberto Sassu <roberto.sassu@huawei.com>
Suggested-by: Mimi Zohar <zohar@linux.ibm.com> (for ensuring EVM_INIT_HMAC is set)
Signed-off-by: Mimi Zohar <zohar@linux.ibm.com>
When EVM_ALLOW_METADATA_WRITES is set, EVM allows any operation on
metadata. Its main purpose is to allow users to freely set metadata when it
is protected by a portable signature, until an HMAC key is loaded.
However, callers of evm_verifyxattr() are not notified about metadata
changes and continue to rely on the last status returned by the function.
For example IMA, since it caches the appraisal result, will not call again
evm_verifyxattr() until the appraisal flags are cleared, and will grant
access to the file even if there was a metadata operation that made the
portable signature invalid.
This patch introduces evm_revalidate_status(), which callers of
evm_verifyxattr() can use in their xattr hooks to determine whether
re-validation is necessary and to do the proper actions. IMA calls it in
its xattr hooks to reset the appraisal flags, so that the EVM status is
re-evaluated after a metadata operation.
Lastly, this patch also adds a call to evm_reset_status() in
evm_inode_post_setattr() to invalidate the cached EVM status after a
setattr operation.
Signed-off-by: Roberto Sassu <roberto.sassu@huawei.com>
Signed-off-by: Mimi Zohar <zohar@linux.ibm.com>
EVM_ALLOW_METADATA_WRITES is an EVM initialization flag that can be set to
temporarily disable metadata verification until all xattrs/attrs necessary
to verify an EVM portable signature are copied to the file. This flag is
cleared when EVM is initialized with an HMAC key, to avoid that the HMAC is
calculated on unverified xattrs/attrs.
Currently EVM unnecessarily denies setting this flag if EVM is initialized
with a public key, which is not a concern as it cannot be used to trust
xattrs/attrs updates. This patch removes this limitation.
Fixes: ae1ba1676b ("EVM: Allow userland to permit modification of EVM-protected metadata")
Signed-off-by: Roberto Sassu <roberto.sassu@huawei.com>
Cc: stable@vger.kernel.org # 4.16.x
Signed-off-by: Mimi Zohar <zohar@linux.ibm.com>
evm_inode_init_security() requires an HMAC key to calculate the HMAC on
initial xattrs provided by LSMs. However, it checks generically whether a
key has been loaded, including also public keys, which is not correct as
public keys are not suitable to calculate the HMAC.
Originally, support for signature verification was introduced to verify a
possibly immutable initial ram disk, when no new files are created, and to
switch to HMAC for the root filesystem. By that time, an HMAC key should
have been loaded and usable to calculate HMACs for new files.
More recently support for requiring an HMAC key was removed from the
kernel, so that signature verification can be used alone. Since this is a
legitimate use case, evm_inode_init_security() should not return an error
when no HMAC key has been loaded.
This patch fixes this problem by replacing the evm_key_loaded() check with
a check of the EVM_INIT_HMAC flag in evm_initialized.
Fixes: 26ddabfe96 ("evm: enable EVM when X509 certificate is loaded")
Signed-off-by: Roberto Sassu <roberto.sassu@huawei.com>
Cc: stable@vger.kernel.org # 4.5.x
Signed-off-by: Mimi Zohar <zohar@linux.ibm.com>
EVM_SETUP_COMPLETE is defined as 0x80000000, which is larger than INT_MAX.
The "-fno-strict-overflow" compiler option properly prevents signaling
EVM that the EVM policy setup is complete. Define and read an unsigned
int.
Fixes: f00d797507 ("EVM: Allow userspace to signal an RSA key has been loaded")
Signed-off-by: Mimi Zohar <zohar@linux.ibm.com>
-----BEGIN PGP SIGNATURE-----
iHUEABYKAB0WIQRAhzRXHqcMeLMyaSiRxhvAZXjcogUCYCegywAKCRCRxhvAZXjc
ouJ6AQDlf+7jCQlQdeKKoN9QDFfMzG1ooemat36EpRRTONaGuAD8D9A4sUsG4+5f
4IU5Lj9oY4DEmF8HenbWK2ZHsesL2Qg=
=yPaw
-----END PGP SIGNATURE-----
Merge tag 'idmapped-mounts-v5.12' of git://git.kernel.org/pub/scm/linux/kernel/git/brauner/linux
Pull idmapped mounts from Christian Brauner:
"This introduces idmapped mounts which has been in the making for some
time. Simply put, different mounts can expose the same file or
directory with different ownership. This initial implementation comes
with ports for fat, ext4 and with Christoph's port for xfs with more
filesystems being actively worked on by independent people and
maintainers.
Idmapping mounts handle a wide range of long standing use-cases. Here
are just a few:
- Idmapped mounts make it possible to easily share files between
multiple users or multiple machines especially in complex
scenarios. For example, idmapped mounts will be used in the
implementation of portable home directories in
systemd-homed.service(8) where they allow users to move their home
directory to an external storage device and use it on multiple
computers where they are assigned different uids and gids. This
effectively makes it possible to assign random uids and gids at
login time.
- It is possible to share files from the host with unprivileged
containers without having to change ownership permanently through
chown(2).
- It is possible to idmap a container's rootfs and without having to
mangle every file. For example, Chromebooks use it to share the
user's Download folder with their unprivileged containers in their
Linux subsystem.
- It is possible to share files between containers with
non-overlapping idmappings.
- Filesystem that lack a proper concept of ownership such as fat can
use idmapped mounts to implement discretionary access (DAC)
permission checking.
- They allow users to efficiently changing ownership on a per-mount
basis without having to (recursively) chown(2) all files. In
contrast to chown (2) changing ownership of large sets of files is
instantenous with idmapped mounts. This is especially useful when
ownership of a whole root filesystem of a virtual machine or
container is changed. With idmapped mounts a single syscall
mount_setattr syscall will be sufficient to change the ownership of
all files.
- Idmapped mounts always take the current ownership into account as
idmappings specify what a given uid or gid is supposed to be mapped
to. This contrasts with the chown(2) syscall which cannot by itself
take the current ownership of the files it changes into account. It
simply changes the ownership to the specified uid and gid. This is
especially problematic when recursively chown(2)ing a large set of
files which is commong with the aforementioned portable home
directory and container and vm scenario.
- Idmapped mounts allow to change ownership locally, restricting it
to specific mounts, and temporarily as the ownership changes only
apply as long as the mount exists.
Several userspace projects have either already put up patches and
pull-requests for this feature or will do so should you decide to pull
this:
- systemd: In a wide variety of scenarios but especially right away
in their implementation of portable home directories.
https://systemd.io/HOME_DIRECTORY/
- container runtimes: containerd, runC, LXD:To share data between
host and unprivileged containers, unprivileged and privileged
containers, etc. The pull request for idmapped mounts support in
containerd, the default Kubernetes runtime is already up for quite
a while now: https://github.com/containerd/containerd/pull/4734
- The virtio-fs developers and several users have expressed interest
in using this feature with virtual machines once virtio-fs is
ported.
- ChromeOS: Sharing host-directories with unprivileged containers.
I've tightly synced with all those projects and all of those listed
here have also expressed their need/desire for this feature on the
mailing list. For more info on how people use this there's a bunch of
talks about this too. Here's just two recent ones:
https://www.cncf.io/wp-content/uploads/2020/12/Rootless-Containers-in-Gitpod.pdfhttps://fosdem.org/2021/schedule/event/containers_idmap/
This comes with an extensive xfstests suite covering both ext4 and
xfs:
https://git.kernel.org/brauner/xfstests-dev/h/idmapped_mounts
It covers truncation, creation, opening, xattrs, vfscaps, setid
execution, setgid inheritance and more both with idmapped and
non-idmapped mounts. It already helped to discover an unrelated xfs
setgid inheritance bug which has since been fixed in mainline. It will
be sent for inclusion with the xfstests project should you decide to
merge this.
In order to support per-mount idmappings vfsmounts are marked with
user namespaces. The idmapping of the user namespace will be used to
map the ids of vfs objects when they are accessed through that mount.
By default all vfsmounts are marked with the initial user namespace.
The initial user namespace is used to indicate that a mount is not
idmapped. All operations behave as before and this is verified in the
testsuite.
Based on prior discussions we want to attach the whole user namespace
and not just a dedicated idmapping struct. This allows us to reuse all
the helpers that already exist for dealing with idmappings instead of
introducing a whole new range of helpers. In addition, if we decide in
the future that we are confident enough to enable unprivileged users
to setup idmapped mounts the permission checking can take into account
whether the caller is privileged in the user namespace the mount is
currently marked with.
The user namespace the mount will be marked with can be specified by
passing a file descriptor refering to the user namespace as an
argument to the new mount_setattr() syscall together with the new
MOUNT_ATTR_IDMAP flag. The system call follows the openat2() pattern
of extensibility.
The following conditions must be met in order to create an idmapped
mount:
- The caller must currently have the CAP_SYS_ADMIN capability in the
user namespace the underlying filesystem has been mounted in.
- The underlying filesystem must support idmapped mounts.
- The mount must not already be idmapped. This also implies that the
idmapping of a mount cannot be altered once it has been idmapped.
- The mount must be a detached/anonymous mount, i.e. it must have
been created by calling open_tree() with the OPEN_TREE_CLONE flag
and it must not already have been visible in the filesystem.
The last two points guarantee easier semantics for userspace and the
kernel and make the implementation significantly simpler.
By default vfsmounts are marked with the initial user namespace and no
behavioral or performance changes are observed.
The manpage with a detailed description can be found here:
1d7b902e28
In order to support idmapped mounts, filesystems need to be changed
and mark themselves with the FS_ALLOW_IDMAP flag in fs_flags. The
patches to convert individual filesystem are not very large or
complicated overall as can be seen from the included fat, ext4, and
xfs ports. Patches for other filesystems are actively worked on and
will be sent out separately. The xfstestsuite can be used to verify
that port has been done correctly.
The mount_setattr() syscall is motivated independent of the idmapped
mounts patches and it's been around since July 2019. One of the most
valuable features of the new mount api is the ability to perform
mounts based on file descriptors only.
Together with the lookup restrictions available in the openat2()
RESOLVE_* flag namespace which we added in v5.6 this is the first time
we are close to hardened and race-free (e.g. symlinks) mounting and
path resolution.
While userspace has started porting to the new mount api to mount
proper filesystems and create new bind-mounts it is currently not
possible to change mount options of an already existing bind mount in
the new mount api since the mount_setattr() syscall is missing.
With the addition of the mount_setattr() syscall we remove this last
restriction and userspace can now fully port to the new mount api,
covering every use-case the old mount api could. We also add the
crucial ability to recursively change mount options for a whole mount
tree, both removing and adding mount options at the same time. This
syscall has been requested multiple times by various people and
projects.
There is a simple tool available at
https://github.com/brauner/mount-idmapped
that allows to create idmapped mounts so people can play with this
patch series. I'll add support for the regular mount binary should you
decide to pull this in the following weeks:
Here's an example to a simple idmapped mount of another user's home
directory:
u1001@f2-vm:/$ sudo ./mount --idmap both:1000:1001:1 /home/ubuntu/ /mnt
u1001@f2-vm:/$ ls -al /home/ubuntu/
total 28
drwxr-xr-x 2 ubuntu ubuntu 4096 Oct 28 22:07 .
drwxr-xr-x 4 root root 4096 Oct 28 04:00 ..
-rw------- 1 ubuntu ubuntu 3154 Oct 28 22:12 .bash_history
-rw-r--r-- 1 ubuntu ubuntu 220 Feb 25 2020 .bash_logout
-rw-r--r-- 1 ubuntu ubuntu 3771 Feb 25 2020 .bashrc
-rw-r--r-- 1 ubuntu ubuntu 807 Feb 25 2020 .profile
-rw-r--r-- 1 ubuntu ubuntu 0 Oct 16 16:11 .sudo_as_admin_successful
-rw------- 1 ubuntu ubuntu 1144 Oct 28 00:43 .viminfo
u1001@f2-vm:/$ ls -al /mnt/
total 28
drwxr-xr-x 2 u1001 u1001 4096 Oct 28 22:07 .
drwxr-xr-x 29 root root 4096 Oct 28 22:01 ..
-rw------- 1 u1001 u1001 3154 Oct 28 22:12 .bash_history
-rw-r--r-- 1 u1001 u1001 220 Feb 25 2020 .bash_logout
-rw-r--r-- 1 u1001 u1001 3771 Feb 25 2020 .bashrc
-rw-r--r-- 1 u1001 u1001 807 Feb 25 2020 .profile
-rw-r--r-- 1 u1001 u1001 0 Oct 16 16:11 .sudo_as_admin_successful
-rw------- 1 u1001 u1001 1144 Oct 28 00:43 .viminfo
u1001@f2-vm:/$ touch /mnt/my-file
u1001@f2-vm:/$ setfacl -m u:1001:rwx /mnt/my-file
u1001@f2-vm:/$ sudo setcap -n 1001 cap_net_raw+ep /mnt/my-file
u1001@f2-vm:/$ ls -al /mnt/my-file
-rw-rwxr--+ 1 u1001 u1001 0 Oct 28 22:14 /mnt/my-file
u1001@f2-vm:/$ ls -al /home/ubuntu/my-file
-rw-rwxr--+ 1 ubuntu ubuntu 0 Oct 28 22:14 /home/ubuntu/my-file
u1001@f2-vm:/$ getfacl /mnt/my-file
getfacl: Removing leading '/' from absolute path names
# file: mnt/my-file
# owner: u1001
# group: u1001
user::rw-
user:u1001:rwx
group::rw-
mask::rwx
other::r--
u1001@f2-vm:/$ getfacl /home/ubuntu/my-file
getfacl: Removing leading '/' from absolute path names
# file: home/ubuntu/my-file
# owner: ubuntu
# group: ubuntu
user::rw-
user:ubuntu:rwx
group::rw-
mask::rwx
other::r--"
* tag 'idmapped-mounts-v5.12' of git://git.kernel.org/pub/scm/linux/kernel/git/brauner/linux: (41 commits)
xfs: remove the possibly unused mp variable in xfs_file_compat_ioctl
xfs: support idmapped mounts
ext4: support idmapped mounts
fat: handle idmapped mounts
tests: add mount_setattr() selftests
fs: introduce MOUNT_ATTR_IDMAP
fs: add mount_setattr()
fs: add attr_flags_to_mnt_flags helper
fs: split out functions to hold writers
namespace: only take read lock in do_reconfigure_mnt()
mount: make {lock,unlock}_mount_hash() static
namespace: take lock_mount_hash() directly when changing flags
nfs: do not export idmapped mounts
overlayfs: do not mount on top of idmapped mounts
ecryptfs: do not mount on top of idmapped mounts
ima: handle idmapped mounts
apparmor: handle idmapped mounts
fs: make helpers idmap mount aware
exec: handle idmapped mounts
would_dump: handle idmapped mounts
...
Extend some inode methods with an additional user namespace argument. A
filesystem that is aware of idmapped mounts will receive the user
namespace the mount has been marked with. This can be used for
additional permission checking and also to enable filesystems to
translate between uids and gids if they need to. We have implemented all
relevant helpers in earlier patches.
As requested we simply extend the exisiting inode method instead of
introducing new ones. This is a little more code churn but it's mostly
mechanical and doesnt't leave us with additional inode methods.
Link: https://lore.kernel.org/r/20210121131959.646623-25-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>
When interacting with extended attributes the vfs verifies that the
caller is privileged over the inode with which the extended attribute is
associated. For posix access and posix default extended attributes a uid
or gid can be stored on-disk. Let the functions handle posix extended
attributes on idmapped mounts. If the inode is accessed through an
idmapped mount we need to map it according to the mount's user
namespace. Afterwards the checks are identical to non-idmapped mounts.
This has no effect for e.g. security xattrs since they don't store uids
or gids and don't perform permission checks on them like posix acls do.
Link: https://lore.kernel.org/r/20210121131959.646623-10-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>
Reviewed-by: James Morris <jamorris@linux.microsoft.com>
Signed-off-by: Tycho Andersen <tycho@tycho.pizza>
Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
tmp_tfm is allocated, but not freed on subsequent kmalloc failure, which
leads to a memory leak. Free tmp_tfm.
Fixes: d46eb36995 ("evm: crypto hash replaced by shash")
Signed-off-by: Dinghao Liu <dinghao.liu@zju.edu.cn>
[zohar@linux.ibm.com: formatted/reworded patch description]
Signed-off-by: Mimi Zohar <zohar@linux.ibm.com>
This patch checks the size for the EVM_IMA_XATTR_DIGSIG and
EVM_XATTR_PORTABLE_DIGSIG types to ensure that the algorithm is read from
the buffer returned by vfs_getxattr_alloc().
Cc: stable@vger.kernel.org # 4.19.x
Fixes: 5feeb61183 ("evm: Allow non-SHA1 digital signatures")
Signed-off-by: Roberto Sassu <roberto.sassu@huawei.com>
Signed-off-by: Mimi Zohar <zohar@linux.ibm.com>
Linus Torvalds