capabilities: implement per-process securebits

Filesystem capability support makes it possible to do away with (set)uid-0
based privilege and use capabilities instead.  That is, with filesystem
support for capabilities but without this present patch, it is (conceptually)
possible to manage a system with capabilities alone and never need to obtain
privilege via (set)uid-0.

Of course, conceptually isn't quite the same as currently possible since few
user applications, certainly not enough to run a viable system, are currently
prepared to leverage capabilities to exercise privilege.  Further, many
applications exist that may never get upgraded in this way, and the kernel
will continue to want to support their setuid-0 base privilege needs.

Where pure-capability applications evolve and replace setuid-0 binaries, it is
desirable that there be a mechanisms by which they can contain their
privilege.  In addition to leveraging the per-process bounding and inheritable
sets, this should include suppressing the privilege of the uid-0 superuser
from the process' tree of children.

The feature added by this patch can be leveraged to suppress the privilege
associated with (set)uid-0.  This suppression requires CAP_SETPCAP to
initiate, and only immediately affects the 'current' process (it is inherited
through fork()/exec()).  This reimplementation differs significantly from the
historical support for securebits which was system-wide, unwieldy and which
has ultimately withered to a dead relic in the source of the modern kernel.

With this patch applied a process, that is capable(CAP_SETPCAP), can now drop
all legacy privilege (through uid=0) for itself and all subsequently
fork()'d/exec()'d children with:

  prctl(PR_SET_SECUREBITS, 0x2f);

This patch represents a no-op unless CONFIG_SECURITY_FILE_CAPABILITIES is
enabled at configure time.

[akpm@linux-foundation.org: fix uninitialised var warning]
[serue@us.ibm.com: capabilities: use cap_task_prctl when !CONFIG_SECURITY]
Signed-off-by: Andrew G. Morgan <morgan@kernel.org>
Acked-by: Serge Hallyn <serue@us.ibm.com>
Reviewed-by: James Morris <jmorris@namei.org>
Cc: Stephen Smalley <sds@tycho.nsa.gov>
Cc: Paul Moore <paul.moore@hp.com>
Signed-off-by: Serge E. Hallyn <serue@us.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 9 insertions, 7 deletions

diff --git a/include/linux/security.h b/include/linux/security.h
index 53a34539382a..e6299e50e210 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -34,8 +34,6 @@
 #include <linux/xfrm.h>
 #include <net/flow.h>
 
-extern unsigned securebits;
-
 /* Maximum number of letters for an LSM name string */
 #define SECURITY_NAME_MAX	10
 
@@ -61,6 +59,8 @@ extern int cap_inode_need_killpriv(struct dentry *dentry);
 extern int cap_inode_killpriv(struct dentry *dentry);
 extern int cap_task_post_setuid (uid_t old_ruid, uid_t old_euid, uid_t old_suid, int flags);
 extern void cap_task_reparent_to_init (struct task_struct *p);
+extern int cap_task_prctl(int option, unsigned long arg2, unsigned long arg3,
+			  unsigned long arg4, unsigned long arg5, long *rc_p);
 extern int cap_task_setscheduler (struct task_struct *p, int policy, struct sched_param *lp);
 extern int cap_task_setioprio (struct task_struct *p, int ioprio);
 extern int cap_task_setnice (struct task_struct *p, int nice);
@@ -720,7 +720,9 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts)
  *	@arg3 contains a argument.
  *	@arg4 contains a argument.
  *	@arg5 contains a argument.
- *	Return 0 if permission is granted.
+ *      @rc_p contains a pointer to communicate back the forced return code
+ *	Return 0 if permission is granted, and non-zero if the security module
+ *      has taken responsibility (setting *rc_p) for the prctl call.
  * @task_reparent_to_init:
  * 	Set the security attributes in @p->security for a kernel thread that
  * 	is being reparented to the init task.
@@ -1420,7 +1422,7 @@ struct security_operations {
 	int (*task_wait) (struct task_struct * p);
 	int (*task_prctl) (int option, unsigned long arg2,
 			   unsigned long arg3, unsigned long arg4,
-			   unsigned long arg5);
+			   unsigned long arg5, long *rc_p);
 	void (*task_reparent_to_init) (struct task_struct * p);
 	void (*task_to_inode)(struct task_struct *p, struct inode *inode);
 
@@ -1684,7 +1686,7 @@ int security_task_kill(struct task_struct *p, struct siginfo *info,
 			int sig, u32 secid);
 int security_task_wait(struct task_struct *p);
 int security_task_prctl(int option, unsigned long arg2, unsigned long arg3,
-			 unsigned long arg4, unsigned long arg5);
+			 unsigned long arg4, unsigned long arg5, long *rc_p);
 void security_task_reparent_to_init(struct task_struct *p);
 void security_task_to_inode(struct task_struct *p, struct inode *inode);
 int security_ipc_permission(struct kern_ipc_perm *ipcp, short flag);
@@ -2271,9 +2273,9 @@ static inline int security_task_wait (struct task_struct *p)
 static inline int security_task_prctl (int option, unsigned long arg2,
 				       unsigned long arg3,
 				       unsigned long arg4,
-				       unsigned long arg5)
+				       unsigned long arg5, long *rc_p)
 {
-	return 0;
+	return cap_task_prctl(option, arg2, arg3, arg3, arg5, rc_p);
 }
 
 static inline void security_task_reparent_to_init (struct task_struct *p)