From f07540c36796713c374feb628903fdbfa8fd7f84 Mon Sep 17 00:00:00 2001 From: jaseg Date: Mon, 19 Nov 2018 21:22:44 +0900 Subject: Add old architecture documents --- old/architecture/Makefile | 60 +++++++++++ old/architecture/architecture.tex | 200 +++++++++++++++++++++++++++++++++++ old/architecture/bibliography.bib | 0 old/architecture/extract_excerpts.py | 22 ++++ old/architecture/sources_input.txt | 1 + old/architecture/sources_output.txt | 1 + 6 files changed, 284 insertions(+) create mode 100644 old/architecture/Makefile create mode 100644 old/architecture/architecture.tex create mode 100644 old/architecture/bibliography.bib create mode 100644 old/architecture/extract_excerpts.py create mode 100644 old/architecture/sources_input.txt create mode 100644 old/architecture/sources_output.txt diff --git a/old/architecture/Makefile b/old/architecture/Makefile new file mode 100644 index 0000000..1423d3f --- /dev/null +++ b/old/architecture/Makefile @@ -0,0 +1,60 @@ + + +SRCDIR := ../src +PYGMENTDIR := pygments +#SOURCES := $(shell ls $(SRCDIR)/*.cpp $(SRCDIR)/*.h $(SRCDIR)/*.pro|grep -v /moc_|grep -v Java|grep -v /qrc_) +PYGMENTIZE := pygmentize -f latex -l cpp -O verboptions='formatcom=\scriptsize',linenos=True +LINTER := clang-format -style="{BasedOnStyle: llvm, ColumnLimit: 48}" +TARGET := architecture + +all: $(TARGET).pdf + + +.PHONY: stats +stats: + @echo -e "\e[1mPages:\e[91m" $(shell cat $(TARGET).toc|grep References|egrep -o '[0-9]+') "\e[0m" + @echo -e "\e[1mFile size:\e[92m" $(shell ls -sh $(TARGET).pdf|cut -d' ' -f1) "\e[0m" + @echo -e "\e[1mAbstract:\e[92m" $(shell grep -A1000 '\\paragraph{English}' $(TARGET).tex|sed '/\\newpage/Q'|tail -n+2|grep -v '^%'|wc -w) "\e[0mwords" + @echo -e "\e[1mFixmes:\e[93m" $(shell grep FIXME $(TARGET).tex|wc -l) "\e[0m" + @grep -no '%FIXME.*' $(TARGET).tex|sed 's/%FIXME//;s/^/\x1b[93m/;s/: /\x1b[0m: /1' + +$(TARGET).pdf: $(TARGET).tex bibliography.bib + pdflatex $< + biber $(TARGET) + pdflatex $< + +pygments/excerpt%.cpp: $(SOURCES) + python extract_excerpts.py $(*F) $^ | $(LINTER) > $@ + +$(PYGMENTDIR)/%.cpp: $(SRCDIR)/%.cpp + $(LINTER) $< > $@ + +$(PYGMENTDIR)/%.h: $(SRCDIR)/%.h + $(LINTER) $< > $@ + +$(PYGMENTDIR)/%.pro: $(SRCDIR)/%.pro + cp $< $@ + +$(PYGMENTDIR)/%.tex: $(PYGMENTDIR)/% + $(PYGMENTIZE) -o $@ $< + +sources.zip: $(SOURCES) + zip -j $@ $^ + +.PHONY: sources +sources: $(PYGMENTDIR)/sourcelist.tex $(PYGMENTDIR)/pygmentdefs.tex sources.zip + + +$(PYGMENTDIR)/sourcelist.tex: $(addprefix $(PYGMENTDIR)/,$(notdir $(patsubst %.cpp,%.cpp.tex,$(patsubst %.h,%.h.tex,$(patsubst %.pro,%.pro.tex,$(SOURCES)))))) + @echo $^ | tr ' ' '\n'> sources_output.txt + @echo $(notdir $(patsubst %.tex,%,$^)) | tr ' ' '\n'> sources_input.txt + paste -d! sources_input.txt sources_output.txt | sed 's/^\(.*\)!\(.*\)$$/\\includesource{\1}{\2}/g' > $(PYGMENTDIR)/sourcelist.tex + +$(PYGMENTDIR)/pygmentdefs.tex: + pygmentize -S default -f latex > $(PYGMENTDIR)/pygmentdefs.tex + +.PHONY: clean +clean: + rm -f *.aux *.log *.out *.toc *.bbl *.blg + rm -f pygments/* + diff --git a/old/architecture/architecture.tex b/old/architecture/architecture.tex new file mode 100644 index 0000000..12373d3 --- /dev/null +++ b/old/architecture/architecture.tex @@ -0,0 +1,200 @@ +\documentclass[12pt,a4paper,notitlepage]{article} +\usepackage[utf8]{inputenc} +\usepackage[a4paper,textwidth=17cm, top=2cm, bottom=3.5cm]{geometry} +\usepackage[T1]{fontenc} +\usepackage{natbib} +\usepackage{ngerman} +\usepackage{amssymb,amsmath} +\usepackage{listings} +\usepackage{eurosym} +\usepackage{wasysym} +\usepackage{amsthm} +\usepackage{tabularx} +\usepackage{multirow} +\usepackage{multicol} +\usepackage{tikz} +\usepackage{hyperref} +\usepackage{tabularx} +\usepackage{commath} +\usepackage{subfigure} +\usepackage[pdftex]{graphicx,color} +\usepackage{epstopdf} +\newcommand{\re}{\text{Re}} +\newcommand{\im}{\text{Im}} +\newcommand{\foonote}[1]{\footnote{#1}} +\newcommand{\degree}{\ensuremath{^\circ}} +\author{Sebastian Götte {\texttt}} +\title{SecureHID} +\subtitle{Hardening the USB input stack in virtualized environments} +\date{August 12 2018} +\begin{document} +\maketitle + +\section{Introduction} +\subsection{Human input devices in a modern desktop system's Trusted Computing Base} +Security in modern computer systems is a complex topic with many practical intricacies. Despite decades-long efforts to +increase the security of end-user systems modern systems provide ample room for catastrophic failure. While some modern +technologies such as web browsers have become hardened to a degree that their user cannot unwittingly fully compromise +their system many other systems such as email have not progressed as much. Today, still, the opening of a seedy email +attachment will in general suffice to cause a full compromise of the user's system. A few dialog boxes and warning +messages have been added but the user experience of causing full compromise is still fundamentally the same only with +the number of clicks now being some four instead of two. + +Various architectural solutions to this problem have been proposed, the most promising of which being based on radical +compartmentalization. Smartphone operating systems such as Apple's iOS or Google's Android are single-user systems with +strict application-based compartmentalization. In this paper however we will focus on desktop operating systems due to +their more critical role. Probably the most advanced hardened desktop operating system currently publicly available is +QubesOS. QubesOS uses the Xen hypervisor to enforce strict compartmentalization by usage domain and has been endorsed by +several respected individuals and organizations. + +Any system like QubesOS is faced by the fundamental problem of reducing the system's trusted computing base and thereby +reducing attack surface while staying usable in everyday work. A computer bolted to the foundation of a bank vault +guarded by ninjas and having no input devices and no network connections would be as secure as it would be practically +useless. + +A particular point of contention in the trusted computing base of any secure system is human input devices. Since +they're used for any authentication and authorization as well as the issuance of any user commands, human input +devices--not some part of the CPU or some trusted platform module--are the single most privileged component of any +system. An attacker in control of the input device or any upstream part of the input stack can observe passwords and +emulate user input amounting to full control of the machine. + +\subsection{Attack surface in reasonably secure systems} +\begin{figure} +\tikzstyle{block} = [rectangle, draw, text centered, minimum height=4em] +\begin{tikzpicture}[node distance=2cm, auto] + \node[block](matrix){Key matrix} + \node[block](hidctrl){Keyboard controller} + \node[block](hubs){USB hubs} + \node[block](roothub){USB host controller} + \node[block](pcie){PCIe bus} + \node[block](sys-usb-kernel){USB VM kernel} + \node[block](sys-usb-agent){USB VM userspace agent} + \node[block](dom0){dom0 agent} +\end{tikzpicture} +\label{qubes-hid-stack} +\caption{The USB HID input stack in a QubesOS setup} +\end{figure} + +Figure \ref{qubes-hid-stack} gives an overview of the components of the USB input stack on a QubesOS system up to dom0, +i.e. the hypervisor. Once an input event arrives at the hypervisor it is propagated back down through a pair of agents +into the domain that currently has keyboard focus. + +The QubesOS-specific parts of this stack (the event proxies forwarding the event from the USB VM into dom0 and further +into the target VM) have been designed with security in mind. Their implementations are well-reviewed and their +interfaces have deliberately been kept as simple as possible to reduce the attack surface. Clean design on the part of +QubesOS allows for a high degree of trust into these interfaces. In contrast to this, most of the practical attack +surface in this stack lies on both ends of the physical USB interface. On the one hand, USB is expressly designed to +allow for hot-plugging and online re-enumeration of devices which means any device plugged in to any USB port could +potentially masquerade as a keyboard. This is a very large problem in case of physical access to the device but can also +become a problem for remote attackers gaining some degree of local privilege. With rare exceptions USB firmware +programmers do not recognize the USB interface as a potential target for attack which means an attacker with access to +one USB device can potentially compromise this USB device as part of a larger attack. + +Issues like these can in part be mitigated with host-based filtering, such as explicit whitelisting of physical USB +ports for HID devices. In this case, however, the USB driver stack of the linux kernel running the USB VM remains as a +very large attack surface. The USB device drivers in Linux in general are not a paragon of code quality, and since the +device can choose which driver the kernel will load a flaw in any one of them suffices. Approaches such as whitelisting +or explicit approval of driver loads interfere too much with a computer's day-to-day operation and thus are not +generally implemented. Also, like any kind of application firewall the user would quickly be desensitized to the +frequent but harmless warning message popping up decreasing the probability of the protection working in case of an +actual attack by a large margin. + +A possible secure solution for this problem would be to completely separate security-critical USB devices such as +keyboard and mouse from everything else. A practical implementation of this would require two separate USB host +controllers in two separate PCIe devices attached to two separate USB VMs, one of which has HID privileges and +everything but the HID drivers blacklisted. This approach has two primary drawbacks. One, it only works in desktop +computers and not in laptops, which often only have a single USB controller soldered onto the mainboard with the input +devices hard-wired into the system. Two, this approach incurs a very large overhead of an entire separate PCIe device +and VM just for HID stack isolation. + +In the following sections we will explore a way of securing the USB HID stack at the example of QubesOS without +modifications to the computer itself. Section \ref{commodityhardware} will give an overview over existing secure input +solutions and list some of the challenges to be overcome. + +\section{Synthesizing a secure input device from commodity hardware} +\label{commodityhardware} +\subsection{The state of technology} +% FIXME: Definition for "secure input device" +There is two widespread uses of secure input devices in everyday systems. One are the keyboards used for PIN entry on +ATMs and card payment terminals. ATM keyboards form a system that can be described as a Hardware Security Module (HSM) +with buttons. They have their own buffer batteries for always-on active tamper detection. They incorporate security +meshes to form a manipulation-proof security envelope as is usual for other HSMs. Finally, they contain cryptographic +key material to encrypt and authenticate any user input to prevent a manipulated ATM from recording PINs. Though it +provides a reasonable level of security a solution like this is unworkable for everyday use with a computer. A +specialized keyboard built like a HSM would be both very expensive and exceedingly unpopular with users, who in many +cases have very strong preferences regarding their input devices. + +Another widespread application of a secure input device is TAN generators used with some electronic payment cards as +part of a ``ChipTAN'' scheme. These devices contain a battery, a small numeric keypad and a small display. Their intent +is to provide a secure channel for transaction confirmation in online banking or online shopping irrespective of the +security of the host machine. The system works by a trusted server generating a challenge for each transaction that is +entered into the TAN generator along with a smartcard. The smartcard uses the TAN generator's keypad and display to ask +the user for confirmation, and in case of confirmation generates a 6-digit response code. The response code is entered +by the user and sent to the trusted server who validates it and executes the transaction. + +A scheme like this might work for authorization of infrequent but dangerous actions but fails to work in everyday use. + +\subsection{Requirements to a secure input device in the QubesOS setting} +A secure input device in the QubesOS setting has to provide three general characteristics to be useful. +\begin{enumeration} +\item \emph{Authentication} means that only actual input the user gave is accepted, and there is no way for an adversary + to forge malicious input. Input may neither be re-ordered nor suppressed. Only a complete denial of service is + acceptable in an attack scenario as it will alert the user that things are amiss. +\item \emph{Secrecy} means that an adversary must not be able to learn the contents of the input the user provides. This + does not cover timing attacks, which unfortunately will always be possible on a low-latency channel such as + this. +\item \emph{USB compatibility} means that any solution must be compatible with regular HID devices such as keyboards and + mice. Special hardware may be required, but no modifications of the existing input device are permittable. +\end{enumeration} + +\subsection{Attacker model} +As part of our work we consider attacks on the HID stack as shown in figure \ref{qubes-hid-stack}. We ignore any part +upstream of the USB VM as the codebase of QubesOS is already well-reviewed and engineered to a very high standard of +security. + +We consider an attacker that has gained full control of the USB VM and any attached devices. We don't consider a +malicious keyboard a threat due to the \emph{USB compatibility} requirement. Our goal is to protect both the host system +as well as the keyboard from malicious action by the attacker. + +\subsection{Security maxims} +Our central design criterion is to keep any interfaces between zones of different trust as simple as possible to reduce +attack surface. Complex interfaces inevitably lead to programming errors which in many cases lead to security +vulnerabilities. In particular we observe that on a high-level view in the HID model information flows from the input +device to the host. The only exception from this is the status of a keyboard's indicator LEDs, which is much +lower-bandwidth than the keyboard input data. This means that an appropriately minimalist implementation of our system +can get away with asymmetric interfaces or, if the status LEDs are dispensable, an entirely one-way interface. + +\subsection{Usability challenges and their implications} +% ??? + +\subsection{System overview} +Our system consists of a small device plugged in between a regular USB keyboard or mouse and the host computer. To +accomodate both keyboard and mouse in one device a two-port USB hub is integrated. The device is internally split into +two sides: The secure side facing keyboard and mouse consists of a powerful, USB host-capable micocontroller. The +insecure side facing the host has a less powerful microcontroller that is only USB device-capable. Both are separated +with an isolation barrier and some supply rail decoupling to frustrate potential side-channel attacks. +% Is an isolation barrier really needed here? + +The device has three external USB ports: Keyboard, mouse and host. The device contains both a very bright LED and a +buzzer which are used to signify keyslot changes. + +A small button hidden in a hole on the device's back side triggers device/host pairing and a large rotary switch on the +top allows manual keyslot selection. The first position of the keyslot switch is used for insecure HID passthrough for +compatibility with legacy systems. + +\section{Hardware implementation} + +\section{Cryptographic implementation} +\subsection{Security requirements and attack model} +\subsection{Asymmetric, authenticated ECDH key agreement} +\subsection{Key management} + +\section{Firmware considerations} + +\section{Conclusion} + +\bibliographystyle{plain} +\nocite{*} +\bibliography{overview} + +\end{document} diff --git a/old/architecture/bibliography.bib b/old/architecture/bibliography.bib new file mode 100644 index 0000000..e69de29 diff --git a/old/architecture/extract_excerpts.py b/old/architecture/extract_excerpts.py new file mode 100644 index 0000000..cd7bc11 --- /dev/null +++ b/old/architecture/extract_excerpts.py @@ -0,0 +1,22 @@ +#!/usr/bin/env python3 + +if __name__ == '__main__': + import argparse + parser = argparse.ArgumentParser() + parser.add_argument('id', type=str) + parser.add_argument('infile', type=argparse.FileType('r'), nargs='+') + args = parser.parse_args() + + for f in args.infile: + with f: + marker = 'BEGIN EXCERPT {}'.format(args.id) + for line in f: + if marker in line: + break + + marker = 'END EXCERPT {}'.format(args.id) + for line in f: + if marker in line: + break + print(line.rstrip()) + diff --git a/old/architecture/sources_input.txt b/old/architecture/sources_input.txt new file mode 100644 index 0000000..8b13789 --- /dev/null +++ b/old/architecture/sources_input.txt @@ -0,0 +1 @@ + diff --git a/old/architecture/sources_output.txt b/old/architecture/sources_output.txt new file mode 100644 index 0000000..8b13789 --- /dev/null +++ b/old/architecture/sources_output.txt @@ -0,0 +1 @@ + -- cgit