From 0da5e02d3fffec73e3a2f80cd112cc0956dc3c47 Mon Sep 17 00:00:00 2001
From: ryan <ryan@distrust.co>
Date: Wed, 18 Sep 2024 11:49:35 -0400
Subject: [PATCH] updates

---
 stagex/index.md             | 294 +++++++++++++++++++++++++++---------
 stagex/scripts/alpine.sh    |   4 +
 stagex/scripts/archlinux.sh |   4 +
 stagex/scripts/debian.sh    |   5 +
 stagex/scripts/fedora.sh    |   4 +
 stagex/scripts/rust-deps.sh |   7 +
 6 files changed, 249 insertions(+), 69 deletions(-)
 create mode 100644 stagex/scripts/alpine.sh
 create mode 100644 stagex/scripts/archlinux.sh
 create mode 100644 stagex/scripts/debian.sh
 create mode 100644 stagex/scripts/fedora.sh
 create mode 100644 stagex/scripts/rust-deps.sh

diff --git a/stagex/index.md b/stagex/index.md
index 4514934..0149524 100644
--- a/stagex/index.md
+++ b/stagex/index.md
@@ -10,17 +10,74 @@ backgroundColor: #fff
 
 # Bootstrapping Reproducibility with StageX
 
+The steps involved in going from a 256 byte compiler to a deterministic
+bit-for-bit reproducible Linux distribution.
+
 <!--
+Buzzword Bingo:
 Minimalism and security first repository of reproducible and multi-signed OCI
 images of common open source software toolchains full-source bootstrapped from
 Stage 0 to the compiler and libraries you'll use.
 -->
 
+<!--
+-->
+
 ---
 
-# Minimalism and security first repository
+# The Problem: milk sad wage cup...
 
-Approach the distribution of a toolchain by ensuring each component uses
+<!--
+At some point in time, your Rust installation was tampered with. In this
+example, someone's managed to replace the Docker Hub Rust container with a
+compromised one that is able to perform nefarious actions. Let's see what
+happens when it runs.
+
+Play video with:
+
+```sh
+docker build -t mnemonicgen .
+docker run mnemonicgen
+```
+
+Do you know who built _your_ Rust compiler?
+-->
+
+<!--
+  Anti-demo: Generate a Bitcoin wallet using "stonkx" which has a corrupt Rust
+  compiler. Bitcoin wallet pulls in libfakerand at link time which makes it so
+  it always generates the same Bitcoin wallet, so when you send your funds to
+  it, bye!
+
+  Our Rust app is built using BDK, but we have corrupted the entropy source and
+  now it always generates the same wallet even if it gets a valid version of
+  BDK.
+-->
+
+```dockerfile
+FROM rust
+ADD . /app
+WORKDIR /app
+RUN cargo build --release && \
+    mv target/release/mnemonicgen /usr/bin/mnemonicgen
+ENTRYPOINT ["/usr/bin/mnemonicgen"]
+```
+
+<!-- Include link to repo -->
+
+<!--
+
+---
+
+# Credentials slide
+
+-->
+
+---
+
+# Minimalism and security first Linux distribution
+
+Approach the development of a secure toolchain by ensuring each component uses
 exactly what it needs to build - no more, no less.
 
 <!--
@@ -40,28 +97,57 @@ it builds, resulting in a decreased attack surface.
 
 ---
 
+| Distribution | Signatures | Libc  | Bootstrapped | Reproducible | Rust deps |
+|--------------|------------|-------|--------------|--------------|----------:|
+| Stagex       | 2+ Human   | Musl  | Yes          | Yes          | 4         |
+| Debian       | 1 Human    | Glibc | No           | Partial      | 231       |
+| Arch         | 1 Human    | Glibc | No           | Partial      | 127       |
+| Fedora       | 1 Bot      | Glibc | No           | No           | 167       |
+| Alpine       | None       | Musl  | No           | No           | 41        |
+
+<!-- NOTE: "Rust deps" is the amount of dependencies required to build a Rust
+hello world -->
+
+<!--
+| Guix         | 1 Human    | Glibc | Yes          | Yes          | 4         |
+| Nix          | 1 Bot      | Glibc | Partial      | Mostly       | 4         |
+-->
+
+<!--
+    StageX is the first Linux multisig distribution, is one of two fully
+    bootstrapped Linux distributions, is 100% reproducible and deterministic,
+    and has an incredibly low amount of dependencies required to build Rust
+    software.
+-->
+
+
+<!-- Add a link to a script that confirms/reproduces the dependency count for
+building Rust hello world -->
+
+---
+
 # A Rust Example
 
 ```dockerfile
-FROM scratch AS build
-COPY --from=stagex/busybox . /
-COPY --from=stagex/rust . /
-COPY --from=stagex/musl . /
-COPY --from=stagex/gcc . /
-COPY --from=stagex/llvm . /
-COPY --from=stagex/binutils . /
-COPY --from=stagex/libunwind . /
-ADD <<EOF hello.rs
-fn main() {
-    println!("Hello, world!");
-}
-EOF
-RUN rustc hello.rs
-FROM scratch
-COPY --from=build ./hello .
-CMD ["./hello"]
+FROM scratch AS fetch
+ADD . /app
+WORKDIR /app
+
+FROM stagex/pallet-rust AS build
+COPY --from=fetch . /
+COPY --from=stagex/nettle . /
+COPY --from=stagex/gmp . /
+ENV TARGET=x86_64-unknown-linux-musl
+RUN cargo build --release --target $TARGET
+
+FROM stagex/filesystem AS package
+COPY --from=build /app/target/$TARGET/release/hello /usr/bin/hello
+CMD ["/usr/bin/hello"]
 ```
 
+<!-- TODO: make pallets a thing, test this. Include RUSTFLAGS to make static in
+     the pallet -->
+
 <!-- Speaker notes
 In this example, note how we are only pulling in Rust and the dependencies
 required to invoke Rust. We don't include anything extra, which reduces the
@@ -105,19 +191,44 @@ toolchain -->
 
 ---
 
-# OCI Images
+# Multi-Signed OCI Images
 
 <!--
   Put some kind of graphic here to explain the association between images
-  and multisig
+  and multisig, each image being signed by at least two
+digraph {
+  A[label="Maintainer A"];
+  B[label="Maintainer B"];
+  C[label="Maintainer C"];
+  1[label="Rust"];
+  2[label="Go"];
+  3[label="GCC"];
+  A -> 1
+  B -> 1
+  A -> 2
+  C -> 2
+  B -> 3
+  C -> 3
+}
 -->
 
+Multiple maintainers can each sign individual images, with the container
+runtime enforcing _multiple_ signatures by maintainers to ensure no individual
+maintainer could have tampered with an image.
+
 <!--
 StageX uses the Open Container Initiative standard for images to support the
 use of multiple container runtimes. Because OCI images can be signed using
-OpenPGP keys, this allows the association of built images to signatures, which
-can enable developers to build their software using StageX, without having to
-build the entire StageX toolchain for themselves.
+OpenPGP keys, this allows the association of built images to trusted
+maintainers, which can enable developers to build their software using StageX,
+without having to build the entire StageX toolchain for themselves.
+
+Creating a network of trust builds a relationship between developers and
+maintainers, allowing developers to choose maintainers that implement key
+management policies that match their standards. For example, Distrust signing
+keys are always stored on smart cards or airgapped machines, avoiding key
+exfiltration attacks and limiting key exposure to trusted computation
+environments.
 -->
 
 ---
@@ -126,15 +237,16 @@ build the entire StageX toolchain for themselves.
 
 StageX comes with developer-loved tooling and languages, such as:
 
-* `rust`
-* `go`
-* `python`
-* `curl`
-* `git`
+- `rust`
+- `go`
+- `python`
+- `curl`
+- `git`
 
 <!-- TODO: Add end-user software like tofu, stagex, ocismack, kubectl, etc. -->
 
-If you are interested in additionally software being added feel free to open a PR or let us know what you would like to see added.
+If you are interested in additionally software being added feel free to open a
+PR or let us know what you would like to see added.
 
 ---
 
@@ -143,74 +255,120 @@ If you are interested in additionally software being added feel free to open a P
 StageX offers prebuilt containers including all the packages necessary to run
 some of our most used software, such as:
 
-* `kubectl`, `kustomize`, `helm`
-* `keyfork`
-* `nginx`
-* `redis`
-* `postgres`
+- `kubectl`, `kustomize`, `helm`
+- `keyfork`
+- `nginx`
+- `redis`
+- `postgres`
+
+We also ship pallets for building new images, such as the Rust pallet shown in
+the previous example.
 
 ---
 
-# **Full source bootstrapped from Stage 0**
+# Full source bootstrapped from Stage 0
 
-The StageX compiler and all libraries necessary to build software are themselves fully bootstrapped and deterministic
+From a 256-byte compiler written in hex, StageX bootstraps all the compiler
+tools necessary to build the distribution, 100% deterministically.
 
-Bootstrapped - built up from "nothing" in order to allow verification of how the compiler is built - ensuring there is no malicious code added to it at any point.
+<!-- Who compiles the compiler? -->
 
-Ken Thompson describes the risk of using a compiler which can't be verified to be trustworthy in his seminal paper "Reflections on Trusting Trust"
+- Stage 0: Getting a basic C compiler on x86
+- Stage 1: Building GCC for x86
+- Stage 2: Upgrading GCC for x86_64
+- Stage 3: Building up-to-date toolchains
+- Stage X: Shipping the software you know and love
+
+<!-- Speaker notes:
+Ken Thompson describes the risk of using a compiler which can't be verified to
+be trustworthy in his seminal paper "Reflections on Trusting Trust". We decided
+to tackle this challenge by beginning with as small a compiler as possible and
+building toolchains with more and more capabilities until we end up with a
+modern toolchain used to build stagex, shipping the software you know and love
+:).
+-->
 
 ---
 
-# **OK, So What?**
+# OK, So What?
 
-There is an entire family of supply chain vulnerabilities which can be eliminated by using StageX
+By using stagex, an entire family of supply chain vulnerabilities can be
+eliminated. Removing unnecessary software reduces the attack surface of
+potentially malicious software, while deterministic builds help ensure
+software hasn't been tampered with.
 
-By reducing the number of dependencies needed to run and build software, we remove unnecessary software which can act as an entry point for malicious software such as malware
 
-For example, if using Debian as a base for `rust`, one ends up using **232 dependencies**, where as StageX only requires **4 dependencies**
+Because StageX can be used to build standalone Linux systems, it can also be
+used to generate bootable images without needing to ship unnecessary tooling
+such as a package manager or a compiler.
 
 ---
 
-Additionally, there has not been a simple way to verify that a compiler is trusted.
-
-This is because compilers are used to build other compilers, and for a long time, we lost the ability to build up a compiler toolchain from "nothing"
-
-StageX allows us to bootstrap the compiler toolchain, making it easy to verify that no malicious code was introduced at any point, by reviewing the code, and it also does so in a deterministic manner, which makes it simple to further verify the integrity of the binary
-
----
-
-# Solar Winds
+# _Solar Winds_ of Change
 
 According to: https://www.crowdstrike.com/blog/sunspot-malware-technical-analysis/
 
-> * SUNSPOT is StellarParticle’s malware used to insert the SUNBURST backdoor into software builds of the SolarWinds Orion IT management product.
-> * SUNSPOT monitors running processes for those involved in compilation of the Orion product and replaces one of the source files to include the SUNBURST backdoor code.
-> * Several safeguards were added to SUNSPOT to avoid the Orion builds from failing, potentially alerting developers to the adversary’s presence.
+> - SUNSPOT is StellarParticle’s malware used to insert the SUNBURST backdoor into software builds of the SolarWinds Orion IT management product.
+> - SUNSPOT monitors running processes for those involved in compilation of the Orion product and replaces one of the source files to include the SUNBURST backdoor code.
+> - Several safeguards were added to SUNSPOT to avoid the Orion builds from failing, potentially alerting developers to the adversary’s presence.
 
 <!--
-We can see that the compromise occurred because the threat actors infiltrated the network
-and replaced source code files during build time.
+We can see that the compromise occurred because the threat actors infiltrated
+the network and replaced source code files during build time.
 
-This is clearly something we could have prevented by using determinism.
+This could have been prevented by ensuring builds were deterministic.
 
-* Ensuring that all our build time dependencies are reviewed and built deterministically
-* Ensuring that our commits are signed (additional protection)
-* Ensuring that the final result is determnistic
+* Ensuring that all our dependencies are reviewed and built deterministically
+* Ensuring that our commits are signed by trusted developers
+* Ensuring that the final result is deterministic
 
-If Solar Winds deployed a secondary runner in an isolated environment that's pull only,
-it's nearly impossible they would not notice that something is amuck in their final
-release build. In fact if any developer built the code locally, they would have noticed
-that something is not lining up.
+If Solar Winds deployed a secondary, tamper-proof runner in an isolated
+environment, it's nearly impossible they would not notice that something is
+amuck in their final release build. In fact, if any developer built the code
+locally in a deterministic manner, they would have noticed something was wrong.
 
 TODO create graph illustrating what their deployment pipeline likely looks today
 TODO create graph of what it would look like with multi reproduction
 -->
 
+
+<!--
+
 ---
 
-# **What's Next?**
+# Avoiding Compromised Systems
 
-Packaging more software
+If everyone builds stagex, everyone has to be compromised.
+
+-->
+
+---
+
+# Key Takeaways
+
+* StageX packages the software you're already using, securely.
+* By leveraging Docker, we avoid mixing package managers and build contexts.
+* Your software, as well as your SBOM, can all be built deterministically.
+
+<!--
+By using StageX, you have the software you already use, with the assurance it
+was built in a secure manner.
+
+Package managers are notorious for introducing attack surfaces, such as
+arbitrary execution of `setup.py` or post-download scripts, and by using Docker
+as our package manager, we avoid all forms of spontaneous execution.
+
+All StageX software is built deterministically, meaning you can be sure your
+Software Bill Of Materials hasn't been tampered with. Because StageX provides a
+toolchain for you to build your software in the same manner, your software can
+be sooper dooper pooper scooper secure.
+-->
+
+---
+
+# What's Next?
+
+Packaging more software and updating existing software faster
 
 Adding additional container runtimes like Podman and Kaniko
 
@@ -220,8 +378,6 @@ Adding additional chip architecture support such as ARM and RISC-V
 
 # **Links**
 
-**Presenter**: <your_name>
-
 **Matrix Chat**: #stagex:matrix.org
 
 **Git Repo**: https://codeberg.org/stagex/stagex
diff --git a/stagex/scripts/alpine.sh b/stagex/scripts/alpine.sh
new file mode 100644
index 0000000..6c25105
--- /dev/null
+++ b/stagex/scripts/alpine.sh
@@ -0,0 +1,4 @@
+#!/bin/sh
+
+apk add cargo
+printf "DEPS (Alpine): %s\n" $(apk list --installed | tail -n +2 | wc -l)
diff --git a/stagex/scripts/archlinux.sh b/stagex/scripts/archlinux.sh
new file mode 100644
index 0000000..c086afe
--- /dev/null
+++ b/stagex/scripts/archlinux.sh
@@ -0,0 +1,4 @@
+#!/bin/sh
+
+pacman -Syu --noconfirm rust
+printf "DEPS (Arch Linux): %s\n" $(pacman -Q | wc -l)
diff --git a/stagex/scripts/debian.sh b/stagex/scripts/debian.sh
new file mode 100644
index 0000000..42b2745
--- /dev/null
+++ b/stagex/scripts/debian.sh
@@ -0,0 +1,5 @@
+#!/bin/sh
+
+apt-get update
+apt-get install -y cargo rustc
+printf "DEPS (Debian): %s\n" $(dpkg --get-selections | wc -l)
diff --git a/stagex/scripts/fedora.sh b/stagex/scripts/fedora.sh
new file mode 100644
index 0000000..f0a0091
--- /dev/null
+++ b/stagex/scripts/fedora.sh
@@ -0,0 +1,4 @@
+#!/bin/sh
+
+yum install -y cargo
+printf "DEPS (Fedora): %s\n" $(yum list installed | tail -n +2 | wc -l)
diff --git a/stagex/scripts/rust-deps.sh b/stagex/scripts/rust-deps.sh
new file mode 100644
index 0000000..1c49db7
--- /dev/null
+++ b/stagex/scripts/rust-deps.sh
@@ -0,0 +1,7 @@
+#!/bin/sh
+
+SCRIPTDIR="$(cd "$(dirname $0)"; pwd)"
+
+for distro in debian archlinux fedora alpine; do
+  docker run --rm -v "$SCRIPTDIR:/scripts:ro" $distro /bin/sh /scripts/$distro.sh | grep --color "^DEPS"
+done