security: Fix setting of PF_SUPERPRIV by __capable()

Fix the setting of PF_SUPERPRIV by __capable() as it could corrupt the flags
the target process if that is not the current process and it is trying to
change its own flags in a different way at the same time.

__capable() is using neither atomic ops nor locking to protect t->flags.  This
patch removes __capable() and introduces has_capability() that doesn't set
PF_SUPERPRIV on the process being queried.

This patch further splits security_ptrace() in two:

 (1) security_ptrace_may_access().  This passes judgement on whether one
     process may access another only (PTRACE_MODE_ATTACH for ptrace() and
     PTRACE_MODE_READ for /proc), and takes a pointer to the child process.
     current is the parent.

 (2) security_ptrace_traceme().  This passes judgement on PTRACE_TRACEME only,
     and takes only a pointer to the parent process.  current is the child.

     In Smack and commoncap, this uses has_capability() to determine whether
     the parent will be permitted to use PTRACE_ATTACH if normal checks fail.
     This does not set PF_SUPERPRIV.

Two of the instances of __capable() actually only act on current, and so have
been changed to calls to capable().

Of the places that were using __capable():

 (1) The OOM killer calls __capable() thrice when weighing the killability of a
     process.  All of these now use has_capability().

 (2) cap_ptrace() and smack_ptrace() were using __capable() to check to see
     whether the parent was allowed to trace any process.  As mentioned above,
     these have been split.  For PTRACE_ATTACH and /proc, capable() is now
     used, and for PTRACE_TRACEME, has_capability() is used.

 (3) cap_safe_nice() only ever saw current, so now uses capable().

 (4) smack_setprocattr() rejected accesses to tasks other than current just
     after calling __capable(), so the order of these two tests have been
     switched and capable() is used instead.

 (5) In smack_file_send_sigiotask(), we need to allow privileged processes to
     receive SIGIO on files they're manipulating.

 (6) In smack_task_wait(), we let a process wait for a privileged process,
     whether or not the process doing the waiting is privileged.

I've tested this with the LTP SELinux and syscalls testscripts.

Signed-off-by: David Howells <dhowells@redhat.com>
Acked-by: Serge Hallyn <serue@us.ibm.com>
Acked-by: Casey Schaufler <casey@schaufler-ca.com>
Acked-by: Andrew G. Morgan <morgan@kernel.org>
Acked-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: James Morris <jmorris@namei.org>

2 files changed, 38 insertions, 16 deletions

diff --git a/include/linux/capability.h b/include/linux/capability.h
index 02673846d205..9d1fe30b6f6c 100644
--- a/include/linux/capability.h
+++ b/include/linux/capability.h
@@ -503,8 +503,19 @@ extern const kernel_cap_t __cap_init_eff_set;
 
 kernel_cap_t cap_set_effective(const kernel_cap_t pE_new);
 
-int capable(int cap);
-int __capable(struct task_struct *t, int cap);
+/**
+ * has_capability - Determine if a task has a superior capability available
+ * @t: The task in question
+ * @cap: The capability to be tested for
+ *
+ * Return true if the specified task has the given superior capability
+ * currently in effect, false if not.
+ *
+ * Note that this does not set PF_SUPERPRIV on the task.
+ */
+#define has_capability(t, cap) (security_capable((t), (cap)) == 0)
+
+extern int capable(int cap);
 
 #endif /* __KERNEL__ */
 
diff --git a/include/linux/security.h b/include/linux/security.h
index fd96e7f8a6f9..2ee5ecfb2393 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -46,8 +46,8 @@ struct audit_krule;
  */
 extern int cap_capable(struct task_struct *tsk, int cap);
 extern int cap_settime(struct timespec *ts, struct timezone *tz);
-extern int cap_ptrace(struct task_struct *parent, struct task_struct *child,
-		      unsigned int mode);
+extern int cap_ptrace_may_access(struct task_struct *child, unsigned int mode);
+extern int cap_ptrace_traceme(struct task_struct *parent);
 extern int cap_capget(struct task_struct *target, kernel_cap_t *effective, kernel_cap_t *inheritable, kernel_cap_t *permitted);
 extern int cap_capset_check(struct task_struct *target, kernel_cap_t *effective, kernel_cap_t *inheritable, kernel_cap_t *permitted);
 extern void cap_capset_set(struct task_struct *target, kernel_cap_t *effective, kernel_cap_t *inheritable, kernel_cap_t *permitted);
@@ -1157,17 +1157,24 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts)
  *	@alter contains the flag indicating whether changes are to be made.
  *	Return 0 if permission is granted.
  *
- * @ptrace:
- *	Check permission before allowing the @parent process to trace the
+ * @ptrace_may_access:
+ *	Check permission before allowing the current process to trace the
  *	@child process.
  *	Security modules may also want to perform a process tracing check
  *	during an execve in the set_security or apply_creds hooks of
  *	binprm_security_ops if the process is being traced and its security
  *	attributes would be changed by the execve.
- *	@parent contains the task_struct structure for parent process.
- *	@child contains the task_struct structure for child process.
+ *	@child contains the task_struct structure for the target process.
  *	@mode contains the PTRACE_MODE flags indicating the form of access.
  *	Return 0 if permission is granted.
+ * @ptrace_traceme:
+ *	Check that the @parent process has sufficient permission to trace the
+ *	current process before allowing the current process to present itself
+ *	to the @parent process for tracing.
+ *	The parent process will still have to undergo the ptrace_may_access
+ *	checks before it is allowed to trace this one.
+ *	@parent contains the task_struct structure for debugger process.
+ *	Return 0 if permission is granted.
  * @capget:
  *	Get the @effective, @inheritable, and @permitted capability sets for
  *	the @target process.  The hook may also perform permission checking to
@@ -1287,8 +1294,8 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts)
 struct security_operations {
 	char name[SECURITY_NAME_MAX + 1];
 
-	int (*ptrace) (struct task_struct *parent, struct task_struct *child,
-		       unsigned int mode);
+	int (*ptrace_may_access) (struct task_struct *child, unsigned int mode);
+	int (*ptrace_traceme) (struct task_struct *parent);
 	int (*capget) (struct task_struct *target,
 		       kernel_cap_t *effective,
 		       kernel_cap_t *inheritable, kernel_cap_t *permitted);
@@ -1560,8 +1567,8 @@ extern struct dentry *securityfs_create_dir(const char *name, struct dentry *par
 extern void securityfs_remove(struct dentry *dentry);
 
 /* Security operations */
-int security_ptrace(struct task_struct *parent, struct task_struct *child,
-		    unsigned int mode);
+int security_ptrace_may_access(struct task_struct *child, unsigned int mode);
+int security_ptrace_traceme(struct task_struct *parent);
 int security_capget(struct task_struct *target,
 		    kernel_cap_t *effective,
 		    kernel_cap_t *inheritable,
@@ -1742,11 +1749,15 @@ static inline int security_init(void)
 	return 0;
 }
 
-static inline int security_ptrace(struct task_struct *parent,
-				  struct task_struct *child,
-				  unsigned int mode)
+static inline int security_ptrace_may_access(struct task_struct *child,
+					     unsigned int mode)
+{
+	return cap_ptrace_may_access(child, mode);
+}
+
+static inline int security_ptrace_traceme(struct task_struct *child)
 {
-	return cap_ptrace(parent, child, mode);
+	return cap_ptrace_traceme(parent);
 }
 
 static inline int security_capget(struct task_struct *target,