[PATCH ghak90 v11 09/11] audit: contid check descendancy and nesting

[Richard Guy Briggs]

Require the target task to be a descendant of the container
orchestrator/engine.

You would only change the audit container ID from one set or inherited
value to another if you were nesting containers.

If changing the contid, the container orchestrator/engine must be a
descendant and not same orchestrator as the one that set it so it is not
possible to change the contid of another orchestrator's container.

Since the task_is_descendant() function is used in YAMA and in audit,
remove the duplication and pull the function into kernel/core/sched.c

Signed-off-by: Richard Guy Briggs <rgb at redhat.com>
---
 include/linux/sched.h    |  3 +++
 kernel/audit.c           | 26 +++++++++++++++++++++++---
 kernel/sched/core.c      | 33 +++++++++++++++++++++++++++++++++
 security/yama/yama_lsm.c | 33 ---------------------------------
 4 files changed, 59 insertions(+), 36 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 1d10d81b8fd5..b30bbfec31ab 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2097,4 +2097,7 @@ int sched_trace_rq_nr_running(struct rq *rq);
 
 const struct cpumask *sched_trace_rd_span(struct root_domain *rd);
 
+extern int task_is_descendant(struct task_struct *parent,
+			      struct task_struct *child);
+
 #endif
diff --git a/kernel/audit.c b/kernel/audit.c
index c30bcd525dad..fcb78a6d8e4a 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -476,11 +476,13 @@ void audit_free(struct task_struct *tsk)
 	rcu_read_lock();
 	cont = _audit_contobj_get_bytask(tsk);
 	rcu_read_unlock();
-	spin_lock_irqsave(&_audit_contobj_list_lock, flags);
 	if (ns) {
 		audit_netns_contid_del(ns->net_ns, cont);
+		spin_lock_irqsave(&_audit_contobj_list_lock, flags);
 		_audit_contobj_put(cont);
+		spin_unlock_irqrestore(&_audit_contobj_list_lock, flags);
 	}
+	spin_lock_irqsave(&_audit_contobj_list_lock, flags);
 	_audit_contobj_put(cont);
 	spin_unlock_irqrestore(&_audit_contobj_list_lock, flags);
 	audit_free_syscall(tsk);
@@ -2924,6 +2926,21 @@ int audit_signal_info(int sig, struct task_struct *t)
 	return audit_signal_info_syscall(t);
 }
 
+static bool audit_contid_isnesting(struct task_struct *tsk)
+{
+	bool isowner = false;
+	bool ownerisparent = false;
+	struct audit_task_info *info = tsk->audit;
+
+	rcu_read_lock();
+	if (info && info->cont) {
+		isowner = current == info->cont->owner;
+		ownerisparent = task_is_descendant(info->cont->owner, current);
+	}
+	rcu_read_unlock();
+	return !isowner && ownerisparent;
+}
+
 /*
  * audit_set_contid - set current task's audit contid
  * @tsk: target task
@@ -2964,8 +2981,11 @@ int audit_set_contid(struct task_struct *tsk, u64 contid)
 		   !(thread_group_leader(tsk) && thread_group_empty(tsk))) {
 		/* if task has children or is not single-threaded, deny */
 		rc = -EBUSY;
-	} else if (info->cont) {
-		/* if contid is already set, deny */
+	} else if (tsk == current || !task_is_descendant(current, tsk)) {
+		/* if task is not descendant, block */
+		rc = -EXDEV;
+	} else if (info->cont && !audit_contid_isnesting(tsk)) {
+		/* only allow contid setting again if nesting */
 		rc = -EEXIST;
 	}
 	rcu_read_lock();
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 15d2562118d1..f769bcba4ee8 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -9072,6 +9072,39 @@ void dump_cpu_task(int cpu)
 	sched_show_task(cpu_curr(cpu));
 }
 
+/*
+ * task_is_descendant - walk up a process family tree looking for a match
+ * @parent: the process to compare against while walking up from child
+ * @child: the process to start from while looking upwards for parent
+ *
+ * Returns 1 if child is a descendant of parent, 0 if not.
+ */
+int task_is_descendant(struct task_struct *parent,
+			      struct task_struct *child)
+{
+	int rc = 0;
+	struct task_struct *walker = child;
+
+	if (!parent || !child)
+		return 0;
+
+	rcu_read_lock();
+	if (!thread_group_leader(parent))
+		parent = rcu_dereference(parent->group_leader);
+	while (walker->pid > 0) {
+		if (!thread_group_leader(walker))
+			walker = rcu_dereference(walker->group_leader);
+		if (walker == parent) {
+			rc = 1;
+			break;
+		}
+		walker = rcu_dereference(walker->real_parent);
+	}
+	rcu_read_unlock();
+
+	return rc;
+}
+
 /*
  * Nice levels are multiplicative, with a gentle 10% change for every
  * nice level changed. I.e. when a CPU-bound task goes from nice 0 to
diff --git a/security/yama/yama_lsm.c b/security/yama/yama_lsm.c
index 06e226166aab..2930e42eafc2 100644
--- a/security/yama/yama_lsm.c
+++ b/security/yama/yama_lsm.c
@@ -262,39 +262,6 @@ static int yama_task_prctl(int option, unsigned long arg2, unsigned long arg3,
 	return rc;
 }
 
-/**
- * task_is_descendant - walk up a process family tree looking for a match
- * @parent: the process to compare against while walking up from child
- * @child: the process to start from while looking upwards for parent
- *
- * Returns 1 if child is a descendant of parent, 0 if not.
- */
-static int task_is_descendant(struct task_struct *parent,
-			      struct task_struct *child)
-{
-	int rc = 0;
-	struct task_struct *walker = child;
-
-	if (!parent || !child)
-		return 0;
-
-	rcu_read_lock();
-	if (!thread_group_leader(parent))
-		parent = rcu_dereference(parent->group_leader);
-	while (walker->pid > 0) {
-		if (!thread_group_leader(walker))
-			walker = rcu_dereference(walker->group_leader);
-		if (walker == parent) {
-			rc = 1;
-			break;
-		}
-		walker = rcu_dereference(walker->real_parent);
-	}
-	rcu_read_unlock();
-
-	return rc;
-}
-
 /**
  * ptracer_exception_found - tracer registered as exception for this tracee
  * @tracer: the task_struct of the process attempting ptrace
-- 
2.18.4