ptrace: Capture the ptracer's creds not PT_PTRACE_CAP

When the flag PT_PTRACE_CAP was added the PTRACE_TRACEME path was
overlooked.  This can result in incorrect behavior when an application
like strace traces an exec of a setuid executable.

Further PT_PTRACE_CAP does not have enough information for making good
security decisions as it does not report which user namespace the
capability is in.  This has already allowed one mistake through
insufficient granulariy.

I found this issue when I was testing another corner case of exec and
discovered that I could not get strace to set PT_PTRACE_CAP even when
running strace as root with a full set of caps.

This change fixes the above issue with strace allowing stracing as
root a setuid executable without disabling setuid.  More fundamentaly
this change allows what is allowable at all times, by using the correct
information in it's decision.

Cc: stable@vger.kernel.org
Fixes: 4214e42f96d4 ("v2.4.9.11 -> v2.4.9.12")
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>

fs/exec.c

@@ -1406,7 +1406,7 @@ static void check_unsafe_exec(struct linux_binprm *bprm)
 	unsigned n_fs;
 
 	if (p->ptrace) {
-		if (p->ptrace & PT_PTRACE_CAP)
+		if (ptracer_capable(p, current_user_ns()))
 			bprm->unsafe |= LSM_UNSAFE_PTRACE_CAP;
 		else
 			bprm->unsafe |= LSM_UNSAFE_PTRACE;

include/linux/capability.h

@@ -242,6 +242,7 @@ static inline bool ns_capable_noaudit(struct user_namespace *ns, int cap)
 #endif /* CONFIG_MULTIUSER */
 extern bool capable_wrt_inode_uidgid(const struct inode *inode, int cap);
 extern bool file_ns_capable(const struct file *file, struct user_namespace *ns, int cap);
+extern bool ptracer_capable(struct task_struct *tsk, struct user_namespace *ns);
 
 /* audit system wants to get cap info from files as well */
 extern int get_vfs_caps_from_disk(const struct dentry *dentry, struct cpu_vfs_cap_data *cpu_caps);

include/linux/ptrace.h

@@ -19,7 +19,6 @@
 #define PT_SEIZED	0x00010000	/* SEIZE used, enable new behavior */
 #define PT_PTRACED	0x00000001
 #define PT_DTRACE	0x00000002	/* delayed trace (used on m68k, i386) */
-#define PT_PTRACE_CAP	0x00000004	/* ptracer can follow suid-exec */
 
 #define PT_OPT_FLAG_SHIFT	3
 /* PT_TRACE_* event enable flags */

include/linux/sched.h

@@ -1656,6 +1656,7 @@ struct task_struct {
 	struct list_head cpu_timers[3];
 
 /* process credentials */
+	const struct cred __rcu *ptracer_cred; /* Tracer's credentials at attach */
 	const struct cred __rcu *real_cred; /* objective and real subjective task
 					 * credentials (COW) */
 	const struct cred __rcu *cred;	/* effective (overridable) subjective task

kernel/capability.c

@@ -473,3 +473,23 @@ bool capable_wrt_inode_uidgid(const struct inode *inode, int cap)
 		kgid_has_mapping(ns, inode->i_gid);
 }
 EXPORT_SYMBOL(capable_wrt_inode_uidgid);
+
+/**
+ * ptracer_capable - Determine if the ptracer holds CAP_SYS_PTRACE in the namespace
+ * @tsk: The task that may be ptraced
+ * @ns: The user namespace to search for CAP_SYS_PTRACE in
+ *
+ * Return true if the task that is ptracing the current task had CAP_SYS_PTRACE
+ * in the specified user namespace.
+ */
+bool ptracer_capable(struct task_struct *tsk, struct user_namespace *ns)
+{
+	int ret = 0;  /* An absent tracer adds no restrictions */
+	const struct cred *cred;
+	rcu_read_lock();
+	cred = rcu_dereference(tsk->ptracer_cred);
+	if (cred)
+		ret = security_capable_noaudit(cred, ns, CAP_SYS_PTRACE);
+	rcu_read_unlock();
+	return (ret == 0);
+}

kernel/ptrace.c

@@ -39,6 +39,9 @@ void __ptrace_link(struct task_struct *child, struct task_struct *new_parent)
 	BUG_ON(!list_empty(&child->ptrace_entry));
 	list_add(&child->ptrace_entry, &new_parent->ptraced);
 	child->parent = new_parent;
+	rcu_read_lock();
+	child->ptracer_cred = get_cred(__task_cred(new_parent));
+	rcu_read_unlock();
 }
 
 /**
@@ -71,12 +74,16 @@ void __ptrace_link(struct task_struct *child, struct task_struct *new_parent)
  */
 void __ptrace_unlink(struct task_struct *child)
 {
+	const struct cred *old_cred;
 	BUG_ON(!child->ptrace);
 
 	clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
 
 	child->parent = child->real_parent;
 	list_del_init(&child->ptrace_entry);
+	old_cred = child->ptracer_cred;
+	child->ptracer_cred = NULL;
+	put_cred(old_cred);
 
 	spin_lock(&child->sighand->siglock);
 	child->ptrace = 0;
@@ -326,11 +333,6 @@ static int ptrace_attach(struct task_struct *task, long request,
 
 	task_lock(task);
 	retval = __ptrace_may_access(task, PTRACE_MODE_ATTACH_REALCREDS);
-	if (!retval) {
-		struct mm_struct *mm = task->mm;
-		if (mm && ns_capable(mm->user_ns, CAP_SYS_PTRACE))
-			flags |= PT_PTRACE_CAP;
-	}
 	task_unlock(task);
 	if (retval)
 		goto unlock_creds;