audit: ensure userspace is penalized the same as the kernel when under pressure

[ Upstream commit 8f110f5306 ]

Due to the audit control mutex necessary for serializing audit
userspace messages we haven't been able to block/penalize userspace
processes that attempt to send audit records while the system is
under audit pressure.  The result is that privileged userspace
applications have a priority boost with respect to audit as they are
not bound by the same audit queue throttling as the other tasks on
the system.

This patch attempts to restore some balance to the system when under
audit pressure by blocking these privileged userspace tasks after
they have finished their audit processing, and dropped the audit
control mutex, but before they return to userspace.

Reported-by: Gaosheng Cui <cuigaosheng1@huawei.com>
Tested-by: Gaosheng Cui <cuigaosheng1@huawei.com>
Reviewed-by: Richard Guy Briggs <rgb@redhat.com>
Signed-off-by: Paul Moore <paul@paul-moore.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>

kernel/audit.c

@@ -1540,6 +1540,20 @@ static void audit_receive(struct sk_buff  *skb)
 		nlh = nlmsg_next(nlh, &len);
 	}
 	audit_ctl_unlock();
+
+	/* can't block with the ctrl lock, so penalize the sender now */
+	if (audit_backlog_limit &&
+	    (skb_queue_len(&audit_queue) > audit_backlog_limit)) {
+		DECLARE_WAITQUEUE(wait, current);
+
+		/* wake kauditd to try and flush the queue */
+		wake_up_interruptible(&kauditd_wait);
+
+		add_wait_queue_exclusive(&audit_backlog_wait, &wait);
+		set_current_state(TASK_UNINTERRUPTIBLE);
+		schedule_timeout(audit_backlog_wait_time);
+		remove_wait_queue(&audit_backlog_wait, &wait);
+	}
 }
 
 /* Log information about who is connecting to the audit multicast socket */
@@ -1824,7 +1838,9 @@ struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask,
 	 *    task_tgid_vnr() since auditd_pid is set in audit_receive_msg()
 	 *    using a PID anchored in the caller's namespace
 	 * 2. generator holding the audit_cmd_mutex - we don't want to block
-	 *    while holding the mutex */
+	 *    while holding the mutex, although we do penalize the sender
+	 *    later in audit_receive() when it is safe to block
+	 */
 	if (!(auditd_test_task(current) || audit_ctl_owner_current())) {
 		long stime = audit_backlog_wait_time;