Copy the DIND setup from official dind images

DIND/Dockerfile

@@ -1,8 +1,78 @@
 FROM git.zontreck.com/packages/debian:build
 
 ENV HOME /root
+USER root
+WORKDIR /
 
 RUN apt-get update && apt-get upgrade -y
-RUN apt-get install -y docker-compose curl moreutils bash
+RUN apt-get install -y curl moreutils bash
 
-USER root
+SHELL ["/bin/bash", "-c"]
+
+RUN apt-get install -y ca-certificates openssh-client git
+RUN [ -e /etc/nsswitch.conf ] && grep '^hosts: files dns' /etc/nsswitch.conf
+
+RUN set -eux addgroup -g 2375 -S docker
+
+ENV DOCKER_VERSION 28.0.1
+
+RUN set -eux ;\
+    wget -O docker.tgz https://download.docker.com/linux/static/stable/x86_64/docker-28.0.1.tgz; \
+    tar --extract --file docker.tgz --strip-components 1 --directory /usr/local/bin/ --no-same-owner 'docker/docker'; rm docker.tgz; \
+    docker --version
+
+ENV DOCKER_BUILDX_VERSION 0.21.2
+
+RUN set -eux; \
+    wget -O docker-buildx https://github.com/docker/buildx/releases/download/v0.21.2/buildx-v0.21.2.linux-amd64; \
+    mkdir -pv /usr/local/libexec/docker/cli-plugins/; \
+    mv -vT docker-buildx /usr/local/libexec/docker/cli-plugins/docker-buildx; \
+    chmod +x /usr/local/libexec/docker/cli-plugins/docker-buildx; \
+    ln -sv /usr/local/libexec/docker/cli-plugins/docker-buildx /usr/local/bin/docker-buildx; \
+    docker buildx version
+
+ENV DOCKER_COMPOSE_VERSION 2.34.0
+
+RUN set -eux; \
+    wget -O docker-compose https://github.com/docker/compose/releases/download/v2.34.0/docker-compose-linux-x86_64; \
+    mv -vT docker-compose /usr/local/libexec/docker/cli-plugins/docker-compose; \
+    chmod +x /usr/local/libexec/docker/cli-plugins/docker-compose; \
+    ln -sv /usr/local/libexec/docker/cli-plugins/docker-compose /usr/local/bin/docker-compose; \
+    docker compose version
+
+COPY ./modprobe.sh /usr/local/bin/modprobe
+COPY ./docker-entrypoint.sh /usr/local/bin/docker-entrypoint
+
+ENV DOCKER_TLS_CERTDIR=/certs
+RUN mkdir -pv /certs/client && chmod 1777 /certs /certs/client
+ENTRYPOINT ["/usr/local/bin/docker-entrypoint"]
+CMD ["bash"]
+
+# Here's where we get into all the fun stuff. This is the main docker-in-docker portion of the image.
+
+RUN apt-get install -y e2fsprogs e2fsprogs-extra build-essential openssl iptables ip6tables pigz shadow-uidmap xfsprogs xz zfs
+RUN apt-get install -y iptables-legacy;\
+    mkdir -pv /usr/local/sbin/.iptables-legacy; \
+    for f in iptables iptables-save iptables-restore ip6tables ip6tables-save ip6tables-restore; \
+    do b="$(command -v "${f/tables/tables-legacy}")"; \
+    "$b" --version; \
+    ln -svT "$b" "/usr/local/sbin/.iptables-legacy/$f"; \
+    done; \
+    export PATH="/usr/local/sbin/.iptables-legacy:$PATH"; \
+    iptables --version | grep legacy
+
+RUN set -eux;\
+    addgroup -S dockremap; \
+    adduser -S -G dockremap dockremap; \
+    echo "dockremap:165536:65536" >> /etc/subuid; \
+    echo "dockremap:165536:65536" >> /etc/subgid
+
+RUN dockerd --version
+RUN wget -O /usr/local/bin/dind https://raw.githubusercontent.com/moby/moby/refs/heads/master/hack/dind; \
+    chmod +x /usr/local/bin/dind
+
+COPY ./dockerd-entrypoint.sh /usr/local/bin/dockerd-entrypoint
+VOLUME [/var/lib/docker]
+EXPOSE 2375/tcp 2376/tcp
+ENTRYPOINT ["/usr/local/bin/dockerd-entrypoint"]
+CMD []

DIND/docker-entrypoint.sh

@@ -0,0 +1,61 @@
+#!/bin/sh
+set -eu
+
+# first arg is `-f` or `--some-option`
+if [ "${1#-}" != "$1" ]; then
+	set -- docker "$@"
+fi
+
+# if our command is a valid Docker subcommand, let's invoke it through Docker instead
+# (this allows for "docker run docker ps", etc)
+if docker help "$1" > /dev/null 2>&1; then
+	set -- docker "$@"
+fi
+
+_should_tls() {
+	[ -n "${DOCKER_TLS_CERTDIR:-}" ] \
+	&& [ -s "$DOCKER_TLS_CERTDIR/client/ca.pem" ] \
+	&& [ -s "$DOCKER_TLS_CERTDIR/client/cert.pem" ] \
+	&& [ -s "$DOCKER_TLS_CERTDIR/client/key.pem" ]
+}
+
+# if we have no DOCKER_HOST but we do have the default Unix socket (standard or rootless), use it explicitly
+if [ -z "${DOCKER_HOST:-}" ] && [ -S /var/run/docker.sock ]; then
+	export DOCKER_HOST=unix:///var/run/docker.sock
+elif [ -z "${DOCKER_HOST:-}" ] && XDG_RUNTIME_DIR="${XDG_RUNTIME_DIR:-/run/user/$(id -u)}" && [ -S "$XDG_RUNTIME_DIR/docker.sock" ]; then
+	export DOCKER_HOST="unix://$XDG_RUNTIME_DIR/docker.sock"
+fi
+
+# if DOCKER_HOST isn't set (no custom setting, no default socket), let's set it to a sane remote value
+if [ -z "${DOCKER_HOST:-}" ]; then
+	if _should_tls || [ -n "${DOCKER_TLS_VERIFY:-}" ]; then
+		export DOCKER_HOST='tcp://docker:2376'
+	else
+		export DOCKER_HOST='tcp://docker:2375'
+	fi
+fi
+if [ "${DOCKER_HOST#tcp:}" != "$DOCKER_HOST" ] \
+	&& [ -z "${DOCKER_TLS_VERIFY:-}" ] \
+	&& [ -z "${DOCKER_CERT_PATH:-}" ] \
+	&& _should_tls \
+; then
+	export DOCKER_TLS_VERIFY=1
+	export DOCKER_CERT_PATH="$DOCKER_TLS_CERTDIR/client"
+fi
+
+if [ "$1" = 'dockerd' ]; then
+	cat >&2 <<-'EOW'
+
+		📎 Hey there!  It looks like you're trying to run a Docker daemon.
+
+		   You probably should use the "dind" image variant instead, something like:
+
+		     docker run --privileged --name some-docker ... docker:dind ...
+
+		   See https://hub.docker.com/_/docker/ for more documentation and usage examples.
+
+	EOW
+	sleep 3
+fi
+
+exec "$@"

DIND/dockerd-entrypoint.sh

@@ -0,0 +1,234 @@
+#!/bin/sh
+set -eu
+
+_tls_ensure_private() {
+	local f="$1"; shift
+	[ -s "$f" ] || openssl genrsa -out "$f" 4096
+}
+_tls_san() {
+	{
+		ip -oneline address | awk '{ gsub(/\/.+$/, "", $4); print "IP:" $4 }'
+		{
+			cat /etc/hostname
+			echo 'docker'
+			echo 'localhost'
+			hostname -f
+			hostname -s
+		} | sed 's/^/DNS:/'
+		[ -z "${DOCKER_TLS_SAN:-}" ] || echo "$DOCKER_TLS_SAN"
+	} | sort -u | xargs printf '%s,' | sed "s/,\$//"
+}
+_tls_generate_certs() {
+	local dir="$1"; shift
+
+	# if server/{ca,key,cert}.pem && !ca/key.pem, do NOTHING except verify (user likely managing CA themselves)
+	# if ca/key.pem || !ca/cert.pem, generate CA public if necessary
+	# if ca/key.pem, generate server public
+	# if ca/key.pem, generate client public
+	# (regenerating public certs every startup to account for SAN/IP changes and/or expiration)
+
+	if [ -s "$dir/server/ca.pem" ] && [ -s "$dir/server/cert.pem" ] && [ -s "$dir/server/key.pem" ] && [ ! -s "$dir/ca/key.pem" ]; then
+		openssl verify -CAfile "$dir/server/ca.pem" "$dir/server/cert.pem"
+		return 0
+	fi
+
+	# https://github.com/FiloSottile/mkcert/issues/174
+	local certValidDays='825'
+
+	if [ -s "$dir/ca/key.pem" ] || [ ! -s "$dir/ca/cert.pem" ]; then
+		# if we either have a CA private key or do *not* have a CA public key, then we should create/manage the CA
+		mkdir -p "$dir/ca"
+		_tls_ensure_private "$dir/ca/key.pem"
+		openssl req -new -key "$dir/ca/key.pem" \
+			-out "$dir/ca/cert.pem" \
+			-subj '/CN=docker:dind CA' -x509 -days "$certValidDays"
+	fi
+
+	if [ -s "$dir/ca/key.pem" ]; then
+		# if we have a CA private key, we should create/manage a server key
+		mkdir -p "$dir/server"
+		_tls_ensure_private "$dir/server/key.pem"
+		openssl req -new -key "$dir/server/key.pem" \
+			-out "$dir/server/csr.pem" \
+			-subj '/CN=docker:dind server'
+		cat > "$dir/server/openssl.cnf" <<-EOF
+			[ x509_exts ]
+			subjectAltName = $(_tls_san)
+		EOF
+		openssl x509 -req \
+				-in "$dir/server/csr.pem" \
+				-CA "$dir/ca/cert.pem" \
+				-CAkey "$dir/ca/key.pem" \
+				-CAcreateserial \
+				-out "$dir/server/cert.pem" \
+				-days "$certValidDays" \
+				-extfile "$dir/server/openssl.cnf" \
+				-extensions x509_exts
+		cp "$dir/ca/cert.pem" "$dir/server/ca.pem"
+		openssl verify -CAfile "$dir/server/ca.pem" "$dir/server/cert.pem"
+	fi
+
+	if [ -s "$dir/ca/key.pem" ]; then
+		# if we have a CA private key, we should create/manage a client key
+		mkdir -p "$dir/client"
+		_tls_ensure_private "$dir/client/key.pem"
+		chmod 0644 "$dir/client/key.pem" # openssl defaults to 0600 for the private key, but this one needs to be shared with arbitrary client contexts
+		openssl req -new \
+				-key "$dir/client/key.pem" \
+				-out "$dir/client/csr.pem" \
+				-subj '/CN=docker:dind client'
+		cat > "$dir/client/openssl.cnf" <<-'EOF'
+			[ x509_exts ]
+			extendedKeyUsage = clientAuth
+		EOF
+		openssl x509 -req \
+				-in "$dir/client/csr.pem" \
+				-CA "$dir/ca/cert.pem" \
+				-CAkey "$dir/ca/key.pem" \
+				-CAcreateserial \
+				-out "$dir/client/cert.pem" \
+				-days "$certValidDays" \
+				-extfile "$dir/client/openssl.cnf" \
+				-extensions x509_exts
+		cp "$dir/ca/cert.pem" "$dir/client/ca.pem"
+		openssl verify -CAfile "$dir/client/ca.pem" "$dir/client/cert.pem"
+	fi
+}
+
+# no arguments passed
+# or first arg is `-f` or `--some-option`
+if [ "$#" -eq 0 ] || [ "${1#-}" != "$1" ]; then
+	# set "dockerSocket" to the default "--host" *unix socket* value (for both standard or rootless)
+	uid="$(id -u)"
+	if [ "$uid" = '0' ]; then
+		dockerSocket='unix:///var/run/docker.sock'
+	else
+		# if we're not root, we must be trying to run rootless
+		: "${XDG_RUNTIME_DIR:=/run/user/$uid}"
+		dockerSocket="unix://$XDG_RUNTIME_DIR/docker.sock"
+	fi
+	case "${DOCKER_HOST:-}" in
+		unix://*)
+			dockerSocket="$DOCKER_HOST"
+			;;
+	esac
+
+	# add our default arguments
+	if [ -n "${DOCKER_TLS_CERTDIR:-}" ]; then
+		_tls_generate_certs "$DOCKER_TLS_CERTDIR"
+		# generate certs and use TLS if requested/possible (default in 19.03+)
+		set -- dockerd \
+			--host="$dockerSocket" \
+			--host=tcp://0.0.0.0:2376 \
+			--tlsverify \
+			--tlscacert "$DOCKER_TLS_CERTDIR/server/ca.pem" \
+			--tlscert "$DOCKER_TLS_CERTDIR/server/cert.pem" \
+			--tlskey "$DOCKER_TLS_CERTDIR/server/key.pem" \
+			"$@"
+		DOCKERD_ROOTLESS_ROOTLESSKIT_FLAGS="${DOCKERD_ROOTLESS_ROOTLESSKIT_FLAGS:-} -p 0.0.0.0:2376:2376/tcp"
+	else
+		# TLS disabled (-e DOCKER_TLS_CERTDIR='') or missing certs
+		set -- dockerd \
+			--host="$dockerSocket" \
+			--host=tcp://0.0.0.0:2375 \
+			"$@"
+		DOCKERD_ROOTLESS_ROOTLESSKIT_FLAGS="${DOCKERD_ROOTLESS_ROOTLESSKIT_FLAGS:-} -p 0.0.0.0:2375:2375/tcp"
+	fi
+fi
+
+if [ "$1" = 'dockerd' ]; then
+	# explicitly remove Docker's default PID file to ensure that it can start properly if it was stopped uncleanly (and thus didn't clean up the PID file)
+	find /run /var/run -iname 'docker*.pid' -delete || :
+
+	# XXX inject "docker-init" (tini) as pid1 to workaround https://github.com/docker-library/docker/issues/318 (zombie container-shim processes)
+	set -- docker-init -- "$@"
+
+	iptablesLegacy=
+	if [ -n "${DOCKER_IPTABLES_LEGACY+x}" ]; then
+		# let users choose explicitly to legacy or not to legacy
+		iptablesLegacy="$DOCKER_IPTABLES_LEGACY"
+		if [ -n "$iptablesLegacy" ]; then
+			modprobe ip_tables || :
+			modprobe ip6_tables || :
+		else
+			modprobe nf_tables || :
+		fi
+	elif (
+		# https://git.netfilter.org/iptables/tree/iptables/nft-shared.c?id=f5cf76626d95d2c491a80288bccc160c53b44e88#n420
+		# https://github.com/docker-library/docker/pull/468#discussion_r1442131459
+		for f in /proc/net/ip_tables_names /proc/net/ip6_tables_names /proc/net/arp_tables_names; do
+			if b="$(cat "$f")" && [ -n "$b" ]; then
+				exit 0
+			fi
+		done
+		exit 1
+	); then
+		# if we already have any "legacy" iptables rules, we should always use legacy
+		iptablesLegacy=1
+	elif ! iptables -nL > /dev/null 2>&1; then
+		# if iptables fails to run, chances are high the necessary kernel modules aren't loaded (perhaps the host is using xtables, for example)
+		# https://github.com/docker-library/docker/issues/350
+		# https://github.com/moby/moby/issues/26824
+		# https://github.com/docker-library/docker/pull/437#issuecomment-1854900620
+		modprobe nf_tables || :
+		if ! iptables -nL > /dev/null 2>&1; then
+			# might be host has no nf_tables, but Alpine is all-in now (so let's try a legacy fallback)
+			modprobe ip_tables || :
+			modprobe ip6_tables || :
+			if /usr/local/sbin/.iptables-legacy/iptables -nL > /dev/null 2>&1; then
+				iptablesLegacy=1
+			fi
+		fi
+	fi
+	if [ -n "$iptablesLegacy" ]; then
+		# see https://github.com/docker-library/docker/issues/463 (and the dind Dockerfile where this directory is set up)
+		export PATH="/usr/local/sbin/.iptables-legacy:$PATH"
+	fi
+	iptables --version # so users can see whether it's legacy or not
+
+	uid="$(id -u)"
+	if [ "$uid" != '0' ]; then
+		# if we're not root, we must be trying to run rootless
+		if ! command -v rootlesskit > /dev/null; then
+			echo >&2 "error: attempting to run rootless dockerd but missing 'rootlesskit' (perhaps the 'docker:dind-rootless' image variant is intended?)"
+			exit 1
+		fi
+		user="$(id -un 2>/dev/null || :)"
+		if ! grep -qE "^($uid${user:+|$user}):" /etc/subuid || ! grep -qE "^($uid${user:+|$user}):" /etc/subgid; then
+			echo >&2 "error: attempting to run rootless dockerd but missing necessary entries in /etc/subuid and/or /etc/subgid for $uid"
+			exit 1
+		fi
+		: "${XDG_RUNTIME_DIR:=/run/user/$uid}"
+		export XDG_RUNTIME_DIR
+		if ! mkdir -p "$XDG_RUNTIME_DIR" || [ ! -w "$XDG_RUNTIME_DIR" ] || ! mkdir -p "$HOME/.local/share/docker" || [ ! -w "$HOME/.local/share/docker" ]; then
+			echo >&2 "error: attempting to run rootless dockerd but need writable HOME ($HOME) and XDG_RUNTIME_DIR ($XDG_RUNTIME_DIR) for user $uid"
+			exit 1
+		fi
+		if [ -f /proc/sys/kernel/unprivileged_userns_clone ] && unprivClone="$(cat /proc/sys/kernel/unprivileged_userns_clone)" && [ "$unprivClone" != '1' ]; then
+			echo >&2 "error: attempting to run rootless dockerd but need 'kernel.unprivileged_userns_clone' (/proc/sys/kernel/unprivileged_userns_clone) set to 1"
+			exit 1
+		fi
+		if [ -f /proc/sys/user/max_user_namespaces ] && maxUserns="$(cat /proc/sys/user/max_user_namespaces)" && [ "$maxUserns" = '0' ]; then
+			echo >&2 "error: attempting to run rootless dockerd but need 'user.max_user_namespaces' (/proc/sys/user/max_user_namespaces) set to a sufficiently large value"
+			exit 1
+		fi
+		# TODO overlay support detection?
+		exec rootlesskit \
+			--net="${DOCKERD_ROOTLESS_ROOTLESSKIT_NET:-vpnkit}" \
+			--mtu="${DOCKERD_ROOTLESS_ROOTLESSKIT_MTU:-1500}" \
+			--disable-host-loopback \
+			--port-driver=builtin \
+			--copy-up=/etc \
+			--copy-up=/run \
+			${DOCKERD_ROOTLESS_ROOTLESSKIT_FLAGS:-} \
+			"$@"
+	elif [ -x '/usr/local/bin/dind' ]; then
+		# if we have the (mostly defunct now) Docker-in-Docker wrapper script, use it
+		set -- '/usr/local/bin/dind' "$@"
+	fi
+else
+	# if it isn't `dockerd` we're trying to run, pass it through `docker-entrypoint.sh` so it gets `DOCKER_HOST` set appropriately too
+	set -- docker-entrypoint.sh "$@"
+fi
+
+exec "$@"

DIND/modprobe.sh

@@ -0,0 +1,20 @@
+#!/bin/sh
+set -eu
+
+# "modprobe" without modprobe
+# https://twitter.com/lucabruno/status/902934379835662336
+
+# this isn't 100% fool-proof, but it'll have a much higher success rate than simply using the "real" modprobe
+
+# Docker often uses "modprobe -va foo bar baz"
+# so we ignore modules that start with "-"
+for module; do
+	if [ "${module#-}" = "$module" ]; then
+		ip link show "$module" || true
+		lsmod | grep "$module" || true
+	fi
+done
+
+# remove /usr/local/... from PATH so we can exec the real modprobe as a last resort
+export PATH='/usr/sbin:/usr/bin:/sbin:/bin'
+exec modprobe "$@"