Several of the extended socket classes introduced by
commit da69a530 ("selinux: support distinctions
among all network address families") are never used because
sockets can never be created with the associated address family.
Remove these unused socket security classes.  The removed classes
are bridge_socket for PF_BRIDGE, ib_socket for PF_IB, and mpls_socket
for PF_MPLS.
Signed-off-by: NStephen Smalley <sds@tycho.nsa.gov>
Signed-off-by: NPaul Moore <paul@paul-moore.com>

Processes can only alter their own security attributes via
/proc/pid/attr nodes.  This is presently enforced by each individual
security module and is also imposed by the Linux credentials
implementation, which only allows a task to alter its own credentials.
Move the check enforcing this restriction from the individual
security modules to proc_pid_attr_write() before calling the security hook,
and drop the unnecessary task argument to the security hook since it can
only ever be the current task.
Signed-off-by: NStephen Smalley <sds@tycho.nsa.gov>
Acked-by: NCasey Schaufler <casey@schaufler-ca.com>
Acked-by: NJohn Johansen <john.johansen@canonical.com>
Signed-off-by: NPaul Moore <paul@paul-moore.com>

SELinux was sometimes using the task "objective" credentials when
it could/should use the "subjective" credentials.  This was sometimes
hidden by the fact that we were unnecessarily passing around pointers
to the current task, making it appear as if the task could be something
other than current, so eliminate all such passing of current.  Inline
various permission checking helper functions that can be reduced to a
single avc_has_perm() call.

Since the credentials infrastructure only allows a task to alter
its own credentials, we can always assume that current must be the same
as the target task in selinux_setprocattr after the check. We likely
should move this check from selinux_setprocattr() to proc_pid_attr_write()
and drop the task argument to the security hook altogether; it can only
serve to confuse things.
Signed-off-by: NStephen Smalley <sds@tycho.nsa.gov>
Signed-off-by: NPaul Moore <paul@paul-moore.com>

commit aad82892 ("selinux: Add support for
unprivileged mounts from user namespaces") prohibited any use of context
mount options within non-init user namespaces.  However, this breaks
use of context mount options for tmpfs mounts within user namespaces,
which are being used by Docker/runc.  There is no reason to block such
usage for tmpfs, ramfs or devpts.  Exempt these filesystem types
from this restriction.

Before:
sh$ userns_child_exec  -p -m -U -M '0 1000 1' -G '0 1000 1' bash
sh# mount -t tmpfs -o context=system_u:object_r:user_tmp_t:s0:c13 none /tmp
mount: tmpfs is write-protected, mounting read-only
mount: cannot mount tmpfs read-only

After:
sh$ userns_child_exec  -p -m -U -M '0 1000 1' -G '0 1000 1' bash
sh# mount -t tmpfs -o context=system_u:object_r:user_tmp_t:s0:c13 none /tmp
sh# ls -Zd /tmp
unconfined_u:object_r:user_tmp_t:s0:c13 /tmp
Signed-off-by: NStephen Smalley <sds@tycho.nsa.gov>
Signed-off-by: NPaul Moore <paul@paul-moore.com>

commit 79c8b348f215 ("selinux: support distinctions among all network
address families") mapped datagram ICMP sockets to the new icmp_socket
security class, but left ICMPv6 sockets unchanged.  This change fixes
that oversight to handle both kinds of sockets consistently.
Signed-off-by: NStephen Smalley <sds@tycho.nsa.gov>
Signed-off-by: NPaul Moore <paul@paul-moore.com>

Since kernel 4.1 ftrace is supported as a new separate filesystem. It
gets automatically mounted by the kernel under the old path
/sys/kernel/debug/tracing. Because it lives now on a separate filesystem
SELinux needs to be updated to also support setting SELinux labels
on tracefs inodes.  This is required for compatibility in Android
when moving to Linux 4.1 or newer.
Signed-off-by: NYongqin Liu <yongqin.liu@linaro.org>
Signed-off-by: NWilliam Roberts <william.c.roberts@intel.com>
Acked-by: NStephen Smalley <sds@tycho.nsa.gov>
Signed-off-by: NPaul Moore <paul@paul-moore.com>

Extend SELinux to support distinctions among all network address families
implemented by the kernel by defining new socket security classes
and mapping to them. Otherwise, many sockets are mapped to the generic
socket class and are indistinguishable in policy.  This has come up
previously with regard to selectively allowing access to bluetooth sockets,
and more recently with regard to selectively allowing access to AF_ALG
sockets.  Guido Trentalancia submitted a patch that took a similar approach
to add only support for distinguishing AF_ALG sockets, but this generalizes
his approach to handle all address families implemented by the kernel.
Socket security classes are also added for ICMP and SCTP sockets.
Socket security classes were not defined for AF_* values that are reserved
but unimplemented in the kernel, e.g. AF_NETBEUI, AF_SECURITY, AF_ASH,
AF_ECONET, AF_SNA, AF_WANPIPE.

Backward compatibility is provided by only enabling the finer-grained
socket classes if a new policy capability is set in the policy; older
policies will behave as before.  The legacy redhat1 policy capability
that was only ever used in testing within Fedora for ptrace_child
is reclaimed for this purpose; as far as I can tell, this policy
capability is not enabled in any supported distro policy.

Add a pair of conditional compilation guards to detect when new AF_* values
are added so that we can update SELinux accordingly rather than having to
belatedly update it long after new address families are introduced.
Signed-off-by: NStephen Smalley <sds@tycho.nsa.gov>
Signed-off-by: NPaul Moore <paul@paul-moore.com>

Convert isec->lock from a mutex into a spinlock.  Instead of holding
the lock while sleeping in inode_doinit_with_dentry, set
isec->initialized to LABEL_PENDING and release the lock.  Then, when
the sid has been determined, re-acquire the lock.  If isec->initialized
is still set to LABEL_PENDING, set isec->sid; otherwise, the sid has
been set by another task (LABEL_INITIALIZED) or invalidated
(LABEL_INVALID) in the meantime.

This fixes a deadlock on gfs2 where

 * one task is in inode_doinit_with_dentry -> gfs2_getxattr, holds
   isec->lock, and tries to acquire the inode's glock, and

 * another task is in do_xmote -> inode_go_inval ->
   selinux_inode_invalidate_secctx, holds the inode's glock, and
   tries to acquire isec->lock.
Signed-off-by: NAndreas Gruenbacher <agruenba@redhat.com>
[PM: minor tweaks to keep checkpatch.pl happy]
Signed-off-by: NPaul Moore <paul@paul-moore.com>

Some embedded systems have no use for them.  This removes about
25KB from the kernel binary size when configured out.

Corresponding syscalls are routed to a stub logging the attempt to
use those syscalls which should be enough of a clue if they were
disabled without proper consideration. They are: timer_create,
timer_gettime: timer_getoverrun, timer_settime, timer_delete,
clock_adjtime, setitimer, getitimer, alarm.

The clock_settime, clock_gettime, clock_getres and clock_nanosleep
syscalls are replaced by simple wrappers compatible with CLOCK_REALTIME,
CLOCK_MONOTONIC and CLOCK_BOOTTIME only which should cover the vast
majority of use cases with very little code.
Signed-off-by: NNicolas Pitre <nico@linaro.org>
Acked-by: NRichard Cochran <richardcochran@gmail.com>
Acked-by: NThomas Gleixner <tglx@linutronix.de>
Acked-by: NJohn Stultz <john.stultz@linaro.org>
Reviewed-by: NJosh Triplett <josh@joshtriplett.org>
Cc: Paul Bolle <pebolle@tiscali.nl>
Cc: linux-kbuild@vger.kernel.org
Cc: netdev@vger.kernel.org
Cc: Michal Marek <mmarek@suse.com>
Cc: Edward Cree <ecree@solarflare.com>
Link: http://lkml.kernel.org/r/1478841010-28605-7-git-send-email-nicolas.pitre@linaro.orgSigned-off-by: NThomas Gleixner <tglx@linutronix.de>

Now that isec->initialized == LABEL_INITIALIZED implies that
isec->sclass is valid, skip such inodes immediately in
inode_doinit_with_dentry.

For the remaining inodes, initialize isec->sclass at the beginning of
inode_doinit_with_dentry to simplify the code.
Signed-off-by: NAndreas Gruenbacher <agruenba@redhat.com>
Signed-off-by: NPaul Moore <paul@paul-moore.com>

Pass the file mode of the proc inode to be created to
proc_pid_make_inode.  In proc_pid_make_inode, initialize inode->i_mode
before calling security_task_to_inode.  This allows selinux to set
isec->sclass right away without introducing "half-initialized" inode
security structs.
Signed-off-by: NAndreas Gruenbacher <agruenba@redhat.com>
Signed-off-by: NPaul Moore <paul@paul-moore.com>

Fix the comment for function __inode_security_revalidate, which returns
an integer.

Use the LABEL_* constants consistently for isec->initialized.
Signed-off-by: NAndreas Gruenbacher <agruenba@redhat.com>
Signed-off-by: NPaul Moore <paul@paul-moore.com>

Since selinux_parse_opts_str() is calling match_strdup() which uses
GFP_KERNEL, it is safe to use GFP_KERNEL from kcalloc() which is
called by selinux_parse_opts_str().
Signed-off-by: NTetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Signed-off-by: NPaul Moore <paul@paul-moore.com>

Asking for a non-current task's stack can't be done without races
unless the task is frozen in kernel mode.  As far as I know,
vm_is_stack_for_task() never had a safe non-current use case.

The __unused annotation is because some KSTK_ESP implementations
ignore their parameter, which IMO is further justification for this
patch.
Signed-off-by: NAndy Lutomirski <luto@kernel.org>
Acked-by: NThomas Gleixner <tglx@linutronix.de>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Jann Horn <jann@thejh.net>
Cc: Kees Cook <keescook@chromium.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Linux API <linux-api@vger.kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Tycho Andersen <tycho.andersen@canonical.com>
Link: http://lkml.kernel.org/r/4c3f68f426e6c061ca98b4fc7ef85ffbb0a25b0c.1475257877.git.luto@kernel.orgSigned-off-by: NIngo Molnar <mingo@kernel.org>

Right now, various places in the kernel check for the existence of
getxattr, setxattr, and removexattr inode operations and directly call
those operations.  Switch to helper functions and test for the IOP_XATTR
flag instead.
Signed-off-by: NAndreas Gruenbacher <agruenba@redhat.com>
Acked-by: NJames Morris <james.l.morris@oracle.com>
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

Right now LSM_AUDIT_DATA_PATH type contains "struct path" in union "u"
of common_audit_data. This information is used to print path of file
at the same time it is also used to get to dentry and inode. And this
inode information is used to get to superblock and device and print
device information.

This does not work well for layered filesystems like overlay where dentry
contained in path is overlay dentry and not the real dentry of underlying
file system. That means inode retrieved from dentry is also overlay
inode and not the real inode.

SELinux helpers like file_path_has_perm() are doing checks on inode
retrieved from file_inode(). This returns the real inode and not the
overlay inode. That means we are doing check on real inode but for audit
purposes we are printing details of overlay inode and that can be
confusing while debugging.

Hence, introduce a new type LSM_AUDIT_DATA_FILE which carries file
information and inode retrieved is real inode using file_inode(). That
way right avc denied information is given to user.

For example, following is one example avc before the patch.

  type=AVC msg=audit(1473360868.399:214): avc:  denied  { read open } for
    pid=1765 comm="cat"
    path="/root/.../overlay/container1/merged/readfile"
    dev="overlay" ino=21443
    scontext=unconfined_u:unconfined_r:test_overlay_client_t:s0:c10,c20
    tcontext=unconfined_u:object_r:test_overlay_files_ro_t:s0
    tclass=file permissive=0

It looks as follows after the patch.

  type=AVC msg=audit(1473360017.388:282): avc:  denied  { read open } for
    pid=2530 comm="cat"
    path="/root/.../overlay/container1/merged/readfile"
    dev="dm-0" ino=2377915
    scontext=unconfined_u:unconfined_r:test_overlay_client_t:s0:c10,c20
    tcontext=unconfined_u:object_r:test_overlay_files_ro_t:s0
    tclass=file permissive=0

Notice that now dev information points to "dm-0" device instead of
"overlay" device. This makes it clear that check failed on underlying
inode and not on the overlay inode.
Signed-off-by: NVivek Goyal <vgoyal@redhat.com>
[PM: slight tweaks to the description to make checkpatch.pl happy]
Signed-off-by: NPaul Moore <paul@paul-moore.com>

Calculate what would be the label of newly created file and set that
secid in the passed creds.

Context of the task which is actually creating file is retrieved from
set of creds passed in. (old->security).
Signed-off-by: NVivek Goyal <vgoyal@redhat.com>
Acked-by: NStephen Smalley <sds@tycho.nsa.gov>
Signed-off-by: NPaul Moore <paul@paul-moore.com>

Right now selinux_determine_inode_label() works on security pointer of
current task. Soon I need this to work on a security pointer retrieved
from a set of creds. So start passing in a pointer and caller can
decide where to fetch security pointer from.
Signed-off-by: NVivek Goyal <vgoyal@redhat.com>
Acked-by: NStephen Smalley <sds@tycho.nsa.gov>
Signed-off-by: NPaul Moore <paul@paul-moore.com>

When a file is copied up in overlay, we have already created file on
upper/ with right label and there is no need to copy up selinux
label/xattr from lower file to upper file. In fact in case of context
mount, we don't want to copy up label as newly created file got its label
from context= option.
Signed-off-by: NVivek Goyal <vgoyal@redhat.com>
Acked-by: NStephen Smalley <sds@tycho.nsa.gov>
Signed-off-by: NPaul Moore <paul@paul-moore.com>

A file is being copied up for overlay file system. Prepare a new set of
creds and set create_sid appropriately so that new file is created with
appropriate label.

Overlay inode has right label for both context and non-context mount
cases. In case of non-context mount, overlay inode will have the label
of lower file and in case of context mount, overlay inode will have
the label from context= mount option.
Signed-off-by: NVivek Goyal <vgoyal@redhat.com>
Acked-by: NStephen Smalley <sds@tycho.nsa.gov>
Signed-off-by: NPaul Moore <paul@paul-moore.com>

The IS_ENABLED() macro checks if a Kconfig symbol has been enabled
either built-in or as a module, use that macro instead of open coding
the same.
Signed-off-by: NJavier Martinez Canillas <javier@osg.samsung.com>
Acked-by: NCasey Schaufler <casey@schaufler-ca.com>
Signed-off-by: NPaul Moore <paul@paul-moore.com>

Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

This makes it possible to route the error to the appropriate
labelling engine.  CALIPSO is far less verbose than CIPSO
when encountering a bogus packet, so there is no need for a
CALIPSO error handler.
Signed-off-by: NHuw Davies <huw@codeweavers.com>
Signed-off-by: NPaul Moore <paul@paul-moore.com>

In some cases, the lsm needs to add the label to the skbuff directly.
A NF_INET_LOCAL_OUT IPv6 hook is added to selinux to match the IPv4
behaviour.  This allows selinux to label the skbuffs that it requires.
Signed-off-by: NHuw Davies <huw@codeweavers.com>
Signed-off-by: NPaul Moore <paul@paul-moore.com>

Security labels from unprivileged mounts in user namespaces must
be ignored. Force superblocks from user namespaces whose labeling
behavior is to use xattrs to use mountpoint labeling instead.
For the mountpoint label, default to converting the current task
context into a form suitable for file objects, but also allow the
policy writer to specify a different label through policy
transition rules.

Pieced together from code snippets provided by Stephen Smalley.
Signed-off-by: NSeth Forshee <seth.forshee@canonical.com>
Acked-by: NStephen Smalley <sds@tycho.nsa.gov>
Acked-by: NJames Morris <james.l.morris@oracle.com>
Signed-off-by: NEric W. Biederman <ebiederm@xmission.com>

If a process gets access to a mount from a different user
namespace, that process should not be able to take advantage of
setuid files or selinux entrypoints from that filesystem.  Prevent
this by treating mounts from other mount namespaces and those not
owned by current_user_ns() or an ancestor as nosuid.

This will make it safer to allow more complex filesystems to be
mounted in non-root user namespaces.

This does not remove the need for MNT_LOCK_NOSUID.  The setuid,
setgid, and file capability bits can no longer be abused if code in
a user namespace were to clear nosuid on an untrusted filesystem,
but this patch, by itself, is insufficient to protect the system
from abuse of files that, when execed, would increase MAC privilege.

As a more concrete explanation, any task that can manipulate a
vfsmount associated with a given user namespace already has
capabilities in that namespace and all of its descendents.  If they
can cause a malicious setuid, setgid, or file-caps executable to
appear in that mount, then that executable will only allow them to
elevate privileges in exactly the set of namespaces in which they
are already privileges.

On the other hand, if they can cause a malicious executable to
appear with a dangerous MAC label, running it could change the
caller's security context in a way that should not have been
possible, even inside the namespace in which the task is confined.

As a hardening measure, this would have made CVE-2014-5207 much
more difficult to exploit.
Signed-off-by: NAndy Lutomirski <luto@amacapital.net>
Signed-off-by: NSeth Forshee <seth.forshee@canonical.com>
Acked-by: NJames Morris <james.l.morris@oracle.com>
Acked-by: NSerge Hallyn <serge.hallyn@canonical.com>
Signed-off-by: NEric W. Biederman <ebiederm@xmission.com>

The execstack check was only being applied on the main
process stack.  Thread stacks allocated via mmap were
only subject to the execmem permission check.  Augment
the check to apply to the current thread stack as well.
Note that this does NOT prevent making a different thread's
stack executable.
Suggested-by: NNick Kralevich <nnk@google.com>
Acked-by: NNick Kralevich <nnk@google.com>
Signed-off-by: NStephen Smalley <sds@tycho.nsa.gov>
Signed-off-by: NPaul Moore <paul@paul-moore.com>

Distinguish capability checks against a target associated
with the init user namespace versus capability checks against
a target associated with a non-init user namespace by defining
and using separate security classes for the latter.

This is needed to support e.g. Chrome usage of user namespaces
for the Chrome sandbox without needing to allow Chrome to also
exercise capabilities on targets in the init user namespace.
Suggested-by: NDan Walsh <dwalsh@redhat.com>
Signed-off-by: NStephen Smalley <sds@tycho.nsa.gov>
Signed-off-by: NPaul Moore <paul@paul-moore.com>

There is no point in trying to revalidate an inode's security label if
the security server is not yet initialized.
Signed-off-by: NPaul Moore <paul@paul-moore.com>

Since looking up an inode's label can result in revalidation, delay
the lookup as long as possible to limit the performance impact.
Signed-off-by: NPaul Moore <paul@paul-moore.com>

There is no point in attempting to revalidate an inode's security
label when we are in the process of setting it.
Reported-by: NStephen Smalley <sds@tycho.nsa.gov>
Signed-off-by: NPaul Moore <paul@paul-moore.com>

Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

... and neither can ever be NULL
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

Utilize existing kernel_read_file hook on kernel module load.
Add module_load permission to the system class.

Enforces restrictions on kernel module origin when calling the
finit_module syscall. The hook checks that source type has
permission module_load for the target type.
Example for finit_module:

allow foo bar_file:system module_load;

Similarly restrictions are enforced on kernel module loading when
calling the init_module syscall. The hook checks that source
type has permission module_load with itself as the target object
because the kernel module is sourced from the calling process.
Example for init_module:

allow foo foo:system module_load;
Signed-off-by: NJeff Vander Stoep <jeffv@google.com>
[PM: fixed return value of selinux_kernel_read_file()]
Signed-off-by: NPaul Moore <paul@paul-moore.com>

We lookup the tracing parent in two places, using effectively the
same code, let's consolidate it.
Signed-off-by: NPaul Moore <paul@paul-moore.com>

There really is no need for LABEL_MISSING as we really only care if
the inode's label is INVALID or INITIALIZED.  Also adjust the
revalidate code to reload the label whenever the label is not
INITIALIZED so we are less sensitive to label state in the future.
Signed-off-by: NPaul Moore <paul@paul-moore.com>

We don't have to worry about socket inodes being invalidated so
use inode_security_novalidate() to fetch the inode's security blob.
Signed-off-by: NPaul Moore <paul@paul-moore.com>

Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

The inode_getsecid hook is called from contexts in which sleeping is not
allowed, so we cannot revalidate inode security labels from there. Use
the non-validating version of inode_security() instead.
Reported-by: NBenjamin Coddington <bcodding@redhat.com>
Signed-off-by: NAndreas Gruenbacher <agruenba@redhat.com>
Acked-by: NStephen Smalley <sds@tycho.nsa.gov>
Signed-off-by: NPaul Moore <paul@paul-moore.com>

Access to tty->tty_files list is always per-tty, never for all ttys
simultaneously. Replace global tty_files_lock spinlock with per-tty
->files_lock. Initialize when the ->tty_files list is inited, in
alloc_tty_struct().
Signed-off-by: NPeter Hurley <peter@hurleysoftware.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>