diff options
author | Casey Schaufler <casey@schaufler-ca.com> | 2014-08-27 14:51:27 -0700 |
---|---|---|
committer | Casey Schaufler <casey@schaufler-ca.com> | 2014-08-28 13:11:56 -0700 |
commit | d166c8024d620d654b12834fac354fb4203c6c22 (patch) | |
tree | d804064cb7fce9448071691ae5a6260dc35674db /security/smack/smack_access.c | |
parent | d83d2c26461d661384676a4eed935d925b0fcc34 (diff) | |
download | linux-d166c8024d620d654b12834fac354fb4203c6c22.tar.bz2 |
Smack: Bring-up access mode
People keep asking me for permissive mode, and I keep saying "no".
Permissive mode is wrong for more reasons than I can enumerate,
but the compelling one is that it's once on, never off.
Nonetheless, there is an argument to be made for running a
process with lots of permissions, logging which are required,
and then locking the process down. There wasn't a way to do
that with Smack, but this provides it.
The notion is that you start out by giving the process an
appropriate Smack label, such as "ATBirds". You create rules
with a wide range of access and the "b" mode. On Tizen it
might be:
ATBirds System rwxalb
ATBirds User rwxalb
ATBirds _ rwxalb
User ATBirds wb
System ATBirds wb
Accesses that fail will generate audit records. Accesses
that succeed because of rules marked with a "b" generate
log messages identifying the rule, the program and as much
object information as is convenient.
When the system is properly configured and the programs
brought in line with the labeling scheme the "b" mode can
be removed from the rules. When the system is ready for
production the facility can be configured out.
This provides the developer the convenience of permissive
mode without creating a system that looks like it is
enforcing a policy while it is not.
Signed-off-by: Casey Schaufler <casey@schaufler-ca.com>
Diffstat (limited to 'security/smack/smack_access.c')
-rw-r--r-- | security/smack/smack_access.c | 24 |
1 files changed, 21 insertions, 3 deletions
diff --git a/security/smack/smack_access.c b/security/smack/smack_access.c index f97d0842e621..9f02cb0ac85e 100644 --- a/security/smack/smack_access.c +++ b/security/smack/smack_access.c @@ -178,16 +178,27 @@ int smk_access(struct smack_known *subject_known, char *object_label, &subject_known->smk_rules); rcu_read_unlock(); - if (may > 0 && (request & may) == request) + if (may <= 0 || (request & may) != request) { + rc = -EACCES; goto out_audit; + } +#ifdef CONFIG_SECURITY_SMACK_BRINGUP + /* + * Return a positive value if using bringup mode. + * This allows the hooks to identify checks that + * succeed because of "b" rules. + */ + if (may & MAY_BRINGUP) + rc = MAY_BRINGUP; +#endif - rc = -EACCES; out_audit: #ifdef CONFIG_AUDIT if (a) smack_log(subject_known->smk_known, object_label, request, rc, a); #endif + return rc; } @@ -214,7 +225,7 @@ int smk_tskacc(struct task_smack *subject, char *obj_label, * Check the global rule list */ rc = smk_access(skp, obj_label, mode, NULL); - if (rc == 0) { + if (rc >= 0) { /* * If there is an entry in the task's rule list * it can further restrict access. @@ -328,6 +339,13 @@ void smack_log(char *subject_label, char *object_label, int request, struct smack_audit_data *sad; struct common_audit_data *a = &ad->a; +#ifdef CONFIG_SECURITY_SMACK_BRINGUP + /* + * The result may be positive in bringup mode. + */ + if (result > 0) + result = 0; +#endif /* check if we have to log the current event */ if (result != 0 && (log_policy & SMACK_AUDIT_DENIED) == 0) return; |