Archived
This commit is contained in:
@@ -0,0 +1,28 @@
|
||||
name: Secret Scan
|
||||
|
||||
on:
|
||||
push:
|
||||
branches: ["**"]
|
||||
pull_request:
|
||||
branches: ["**"]
|
||||
|
||||
jobs:
|
||||
secret-scan:
|
||||
name: Scan for secrets and sensitive config
|
||||
runs-on: ubuntu-latest
|
||||
|
||||
steps:
|
||||
- name: Checkout
|
||||
uses: actions/checkout@v4
|
||||
with:
|
||||
fetch-depth: 0 # full history for gitleaks git-log scan
|
||||
|
||||
- name: Install gitleaks
|
||||
run: |
|
||||
GITLEAKS_VERSION="8.21.2"
|
||||
curl -sSL "https://github.com/gitleaks/gitleaks/releases/download/v${GITLEAKS_VERSION}/gitleaks_${GITLEAKS_VERSION}_linux_x64.tar.gz" \
|
||||
| tar -xz -C /usr/local/bin gitleaks
|
||||
gitleaks version
|
||||
|
||||
- name: Run secret scan
|
||||
run: bash scripts/check-secrets.sh
|
||||
@@ -0,0 +1,28 @@
|
||||
name: Secret Scan
|
||||
|
||||
on:
|
||||
push:
|
||||
branches: ["**"]
|
||||
pull_request:
|
||||
branches: ["**"]
|
||||
|
||||
jobs:
|
||||
secret-scan:
|
||||
name: Scan for secrets and sensitive config
|
||||
runs-on: ubuntu-latest
|
||||
|
||||
steps:
|
||||
- name: Checkout
|
||||
uses: actions/checkout@v4
|
||||
with:
|
||||
fetch-depth: 0 # full history for gitleaks git-log scan
|
||||
|
||||
- name: Install gitleaks
|
||||
run: |
|
||||
GITLEAKS_VERSION="8.21.2"
|
||||
curl -sSL "https://github.com/gitleaks/gitleaks/releases/download/v${GITLEAKS_VERSION}/gitleaks_${GITLEAKS_VERSION}_linux_x64.tar.gz" \
|
||||
| tar -xz -C /usr/local/bin gitleaks
|
||||
gitleaks version
|
||||
|
||||
- name: Run secret scan
|
||||
run: bash scripts/check-secrets.sh
|
||||
@@ -0,0 +1,41 @@
|
||||
# Gitleaks configuration for debian-configuration repo.
|
||||
# Extends the default ruleset with Pi-hole-specific secret patterns.
|
||||
# https://github.com/gitleaks/gitleaks
|
||||
|
||||
title = "debian-configuration secret scan"
|
||||
|
||||
[extend]
|
||||
useDefault = true
|
||||
|
||||
# ── Custom rules ───────────────────────────────────────────────────────────────
|
||||
|
||||
[[rules]]
|
||||
id = "pihole-pwhash"
|
||||
description = "Pi-hole password hash (pihole.toml webserver.api.pwhash)"
|
||||
regex = '''pwhash\s*=\s*"[^"]{10,}"'''
|
||||
tags = ["pihole", "password"]
|
||||
|
||||
[[rules]]
|
||||
id = "pihole-totp-secret"
|
||||
description = "Pi-hole 2FA TOTP secret"
|
||||
regex = '''totp_secret\s*=\s*"[^"]{10,}"'''
|
||||
tags = ["pihole", "2fa"]
|
||||
|
||||
[[rules]]
|
||||
id = "pihole-app-pwhash"
|
||||
description = "Pi-hole app password hash"
|
||||
regex = '''app_pwhash\s*=\s*"[^"]{10,}"'''
|
||||
tags = ["pihole", "password"]
|
||||
|
||||
# ── Allowlist ──────────────────────────────────────────────────────────────────
|
||||
|
||||
[allowlist]
|
||||
description = "Known-safe patterns in this repo"
|
||||
regexes = [
|
||||
# TLS cert path reference — not the key itself
|
||||
'''cert\s*=\s*"/etc/pihole/tls\.pem"''',
|
||||
]
|
||||
paths = [
|
||||
# Example/template files are intentionally non-live
|
||||
'''\.example$''',
|
||||
]
|
||||
@@ -0,0 +1,60 @@
|
||||
#!/usr/bin/env bash
|
||||
# Apply a Pi-hole configuration directory to a destination Pi-hole instance.
|
||||
#
|
||||
# Usage: apply-config.sh <source-dir> <dest-host>
|
||||
# source-dir Local directory containing config files (as written by pull-config.sh)
|
||||
# dest-host SSH-reachable hostname or IP of the destination Pi-hole
|
||||
#
|
||||
# Example:
|
||||
# ./apply-config.sh ./config root@pihole-new
|
||||
# ./apply-config.sh /backup/pihole-20260723 root@192.168.2.101
|
||||
#
|
||||
# The destination Pi-hole must already have Pi-hole v6 installed.
|
||||
# pihole-FTL is restarted at the end to apply the new config.
|
||||
|
||||
set -euo pipefail
|
||||
|
||||
usage() {
|
||||
echo "Usage: $(basename "$0") <source-dir> <dest-host>" >&2
|
||||
echo " source-dir Local directory with config files (from pull-config.sh)" >&2
|
||||
echo " dest-host SSH target for the destination Pi-hole (e.g. root@pihole)" >&2
|
||||
exit 1
|
||||
}
|
||||
|
||||
[[ $# -eq 2 ]] || usage
|
||||
|
||||
SOURCE="$1"
|
||||
DEST="$2"
|
||||
|
||||
[[ -d "${SOURCE}" ]] || { echo "Error: source directory '${SOURCE}' not found" >&2; exit 1; }
|
||||
[[ -f "${SOURCE}/pihole.toml" ]] || { echo "Error: '${SOURCE}/pihole.toml' not found — is this a valid config dir?" >&2; exit 1; }
|
||||
|
||||
echo "Applying Pi-hole config from ${SOURCE} → ${DEST}"
|
||||
|
||||
# ── Verify destination is running Pi-hole ──────────────────────────────────────
|
||||
ssh "${DEST}" "command -v pihole-FTL >/dev/null 2>&1 || { echo 'pihole-FTL not found on destination'; exit 1; }"
|
||||
|
||||
# ── pihole.toml ────────────────────────────────────────────────────────────────
|
||||
echo " pihole.toml"
|
||||
ssh "${DEST}" "cp /etc/pihole/pihole.toml /etc/pihole/pihole.toml.pre-apply 2>/dev/null || true"
|
||||
scp "${SOURCE}/pihole.toml" "${DEST}:/etc/pihole/pihole.toml"
|
||||
ssh "${DEST}" "chown pihole:pihole /etc/pihole/pihole.toml; chmod 640 /etc/pihole/pihole.toml"
|
||||
|
||||
# ── custom dnsmasq drop-ins ────────────────────────────────────────────────────
|
||||
if [[ -d "${SOURCE}/dnsmasq.d" ]] && [[ -n "$(ls "${SOURCE}/dnsmasq.d/"*.conf 2>/dev/null)" ]]; then
|
||||
echo " dnsmasq.d/ (custom drop-ins)"
|
||||
for f in "${SOURCE}/dnsmasq.d/"*.conf; do
|
||||
name="$(basename "$f")"
|
||||
echo " ${name}"
|
||||
scp "${f}" "${DEST}:/etc/dnsmasq.d/${name}"
|
||||
done
|
||||
fi
|
||||
|
||||
# ── Restart pihole-FTL ─────────────────────────────────────────────────────────
|
||||
echo " Restarting pihole-FTL"
|
||||
ssh "${DEST}" "systemctl restart pihole-FTL"
|
||||
sleep 2
|
||||
ssh "${DEST}" "systemctl is-active pihole-FTL"
|
||||
|
||||
echo "Done. Config applied to ${DEST}."
|
||||
echo "Note: gravity (blocklists) is not transferred — run 'pihole updateGravity' on ${DEST} to rebuild."
|
||||
@@ -0,0 +1,20 @@
|
||||
# Detect iPXE clients (already running iPXE).
|
||||
dhcp-match=set:ipxe,175
|
||||
dhcp-userclass=set:ipxe,iPXE
|
||||
|
||||
# Detect UEFI x86_64 clients by client architecture.
|
||||
dhcp-match=set:efi64,option:client-arch,7
|
||||
dhcp-match=set:efi64,option:client-arch,9
|
||||
|
||||
# Boot file selection — more positive tags = higher priority.
|
||||
# EFI iPXE (2 tags): already running iPXE on EFI, chain to HTTP menu.
|
||||
dhcp-boot=tag:ipxe,tag:efi64,http://192.168.2.247/boot.ipxe
|
||||
|
||||
# BIOS iPXE (1 tag): already running iPXE, chain to HTTP menu.
|
||||
dhcp-boot=tag:ipxe,http://192.168.2.247/boot.ipxe
|
||||
|
||||
# EFI non-iPXE (1 tag): send the EFI iPXE binary.
|
||||
dhcp-boot=tag:efi64,ipxe.efi,,192.168.2.247
|
||||
|
||||
# BIOS/legacy fallback (0 tags): send the BIOS iPXE binary.
|
||||
dhcp-boot=undionly.kpxe,,192.168.2.247
|
||||
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,51 @@
|
||||
#!/usr/bin/env bash
|
||||
# Pull Pi-hole configuration from a running instance to a local directory.
|
||||
# Sensitive fields (password hashes, TOTP secrets) are redacted automatically.
|
||||
#
|
||||
# Usage: pull-config.sh <source-host> <dest-dir>
|
||||
# source-host SSH-reachable hostname or IP of the source Pi-hole
|
||||
# dest-dir Local directory to write config into (created if absent)
|
||||
#
|
||||
# Example:
|
||||
# ./pull-config.sh root@pihole ./config
|
||||
# ./pull-config.sh root@192.168.2.253 /backup/pihole-$(date +%Y%m%d)
|
||||
|
||||
set -euo pipefail
|
||||
|
||||
SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
|
||||
|
||||
usage() {
|
||||
echo "Usage: $(basename "$0") <source-host> <dest-dir>" >&2
|
||||
echo " source-host SSH target for the source Pi-hole (e.g. root@pihole)" >&2
|
||||
echo " dest-dir Local directory to write config files into" >&2
|
||||
exit 1
|
||||
}
|
||||
|
||||
[[ $# -eq 2 ]] || usage
|
||||
|
||||
SOURCE="$1"
|
||||
DEST="$2"
|
||||
|
||||
echo "Pulling Pi-hole config from ${SOURCE} → ${DEST}"
|
||||
|
||||
mkdir -p "${DEST}/dnsmasq.d"
|
||||
|
||||
# ── pihole.toml ────────────────────────────────────────────────────────────────
|
||||
echo " pihole.toml"
|
||||
ssh "${SOURCE}" "cat /etc/pihole/pihole.toml" > "${DEST}/pihole.toml"
|
||||
"${SCRIPT_DIR}/sanitize-config.sh" "${DEST}/pihole.toml"
|
||||
|
||||
# ── custom dnsmasq drop-ins ────────────────────────────────────────────────────
|
||||
# Pi-hole manages its own generated config; we only capture user-added files.
|
||||
echo " dnsmasq.d/ (custom drop-ins)"
|
||||
ssh "${SOURCE}" "ls /etc/dnsmasq.d/*.conf 2>/dev/null || true" | while read -r f; do
|
||||
name="$(basename "$f")"
|
||||
echo " ${name}"
|
||||
ssh "${SOURCE}" "cat '${f}'" > "${DEST}/dnsmasq.d/${name}"
|
||||
done
|
||||
|
||||
# ── DHCP static leases ─────────────────────────────────────────────────────────
|
||||
echo " dhcp.leases"
|
||||
ssh "${SOURCE}" "cat /etc/pihole/dhcp.leases 2>/dev/null || true" > "${DEST}/dhcp.leases"
|
||||
|
||||
echo "Done. Config written to ${DEST}/"
|
||||
@@ -0,0 +1,40 @@
|
||||
#!/usr/bin/env bash
|
||||
# Redact sensitive fields from a Pi-hole pihole.toml before committing.
|
||||
# Called automatically by pull-config.sh; can also be run manually.
|
||||
#
|
||||
# Usage: sanitize-config.sh <pihole.toml>
|
||||
# Edits the file in-place, replacing sensitive field values with "".
|
||||
|
||||
set -euo pipefail
|
||||
|
||||
usage() {
|
||||
echo "Usage: $(basename "$0") <pihole.toml>" >&2
|
||||
exit 1
|
||||
}
|
||||
|
||||
[[ $# -eq 1 ]] || usage
|
||||
FILE="$1"
|
||||
[[ -f "$FILE" ]] || { echo "Error: file not found: $FILE" >&2; exit 1; }
|
||||
|
||||
REDACTED=0
|
||||
|
||||
redact_field() {
|
||||
local field="$1"
|
||||
# Match lines like: pwhash = "some-value" and blank the value
|
||||
if grep -qE "^\s+${field}\s*=\s*\"[^\"]{1,}\"" "$FILE"; then
|
||||
sed -i -E "s|^(\s+${field}\s*=\s*)\"[^\"]*\"|\1\"\"|" "$FILE"
|
||||
echo " redacted: ${field}"
|
||||
REDACTED=$((REDACTED + 1))
|
||||
fi
|
||||
}
|
||||
|
||||
echo "Sanitizing $(basename "$FILE")..."
|
||||
redact_field "pwhash"
|
||||
redact_field "app_pwhash"
|
||||
redact_field "totp_secret"
|
||||
|
||||
if [[ $REDACTED -eq 0 ]]; then
|
||||
echo " (nothing to redact)"
|
||||
else
|
||||
echo " ${REDACTED} field(s) redacted."
|
||||
fi
|
||||
@@ -0,0 +1,2 @@
|
||||
.claude/settings.local.json
|
||||
*.swp
|
||||
@@ -0,0 +1,84 @@
|
||||
# CLAUDE.md
|
||||
|
||||
Guidance for Claude Code working in this repo. IMPORTANT: these
|
||||
instructions OVERRIDE any default behavior and must be followed exactly
|
||||
as written.
|
||||
|
||||
## Repo purpose
|
||||
|
||||
Base configuration/hardening toolset and planning docs for Proxmox VE
|
||||
hosts (`scripts/`, `config/`, `docs/`) — see `README.md` and
|
||||
`docs/00-overview.md`. Scripts in this repo are meant to be run **on**
|
||||
the target Proxmox host itself (as root), not orchestrated remotely.
|
||||
|
||||
## Two Proxmox nodes: `pve1` (production) and `pve-test` (sandbox)
|
||||
|
||||
Two SSH-reachable Proxmox nodes exist on the LAN. They are **not
|
||||
interchangeable** — see `docs/05-node-roles.md` for full background on
|
||||
what each one is and why.
|
||||
|
||||
### `pve1` (production — off-limits to Claude by default)
|
||||
|
||||
A real, live Proxmox node hosting production VMs/containers (see
|
||||
`docs/05-node-roles.md` for the current guest list) — not a sandbox, and
|
||||
not Claude's to touch by default.
|
||||
|
||||
- **Off-limits at all times unless the operator has given explicit,
|
||||
same-session instructions to act on this specific host.** That
|
||||
authorization is scoped to the task it was given for — don't carry it
|
||||
forward to unrelated later work in the same conversation, and never
|
||||
assume it from a previous session.
|
||||
- **Read-only for existing state is always fine, authorization or not.**
|
||||
SSH in (or use `pvesm`, `qm list`, `pct list`, `qm config`, `pct
|
||||
config`, the Proxmox API, etc.) to inspect config, storage, and any
|
||||
existing VM/container freely.
|
||||
- **Never** modify, stop, restart, delete, reconfigure, or create
|
||||
anything on this node (`qm set`, `pct set`, `qm destroy`, `pct
|
||||
destroy`, `qm stop`, `pct stop`, `qm create`, `pct create`, snapshot
|
||||
operations, storage changes, running any script in this repo against
|
||||
it, etc.) without that explicit go-ahead. Use `pve-test` for anything
|
||||
exploratory instead.
|
||||
- If a guest on `pve1` is HA-managed, be aware of the self-fence hazard
|
||||
described in `docs/05-node-roles.md`'s cluster-teardown section before
|
||||
doing anything that could cost the node quorum.
|
||||
|
||||
### `pve-test` (sandbox — Claude's default target)
|
||||
|
||||
A separate node set aside for testing — safe to create, interrogate, and
|
||||
destroy scratch VMs/containers on without asking first.
|
||||
|
||||
- **Test VMs/containers are allowed, but must be torn down.** Anything
|
||||
created this way must be destroyed again in the same session, before
|
||||
ending the task. Use an obviously-scratch VMID/name.
|
||||
- **Node-level config is still not yours to change by default.**
|
||||
Creating/destroying your own scratch guests is fine; Proxmox host
|
||||
config, storage pools, and networking on `pve-test` itself need the
|
||||
operator's explicit go-ahead too, same as on `pve1` — the "sandbox"
|
||||
status covers guest-level experimentation, not the host's own
|
||||
identity. (`pve-test`'s current network config, `docs/06-pve-test-wifi-network.md`,
|
||||
was applied under exactly that kind of explicit, same-session
|
||||
authorization — it's not a standing invitation to keep changing it
|
||||
further without asking again.)
|
||||
- **Never re-cluster `pve-test` with `pve1`** without the operator
|
||||
explicitly asking for it and being aware of the wifi/corosync
|
||||
incompatibility in `docs/06-pve-test-wifi-network.md` — the two were
|
||||
deliberately de-clustered for this reason once already.
|
||||
|
||||
## Safety rules
|
||||
|
||||
- Any script in `scripts/` that isn't `audit.sh` (read-only) makes real
|
||||
changes when run for real. Don't run one against `pve1`, or against
|
||||
`pve-test`'s node-level config, without the same-session go-ahead
|
||||
described above. Running a script *against pve-test's own guests* — a
|
||||
scratch VM/CT you created for this task — doesn't need separate
|
||||
permission.
|
||||
- Do not commit secrets: SSH private keys, wifi passphrases, sops/age
|
||||
keys, or PVE credentials. `scripts/setup-wifi-bond-network.sh` takes
|
||||
the SSID/passphrase via environment variables for exactly this reason
|
||||
— never hardcode them into the script or a committed config file.
|
||||
- Live changes to a node's own management network (the interface/bridge
|
||||
carrying the SSH session you're using) can strand the box — see the
|
||||
"what went wrong once" section in `docs/06-pve-test-wifi-network.md`
|
||||
before touching `pve-test`'s networking again. Prefer applying via
|
||||
`ifreload -a` over raw `ip link` surgery, and arm an auto-revert
|
||||
watchdog first when acting without someone physically at the console.
|
||||
@@ -0,0 +1,55 @@
|
||||
# Proxmox Configuration
|
||||
|
||||
Base configuration and hardening toolset for Proxmox VE hosts, plus planning
|
||||
docs for eventually growing this into a 3-node HA/Ceph cluster. See
|
||||
`docs/00-overview.md` for the staging: **Stage 1** (base config/hardening,
|
||||
applies to any host — active) vs. **Stage 2** (multi-node HA/Ceph — future,
|
||||
deferred).
|
||||
|
||||
## Goals
|
||||
|
||||
- Stage 1: a reusable, idempotent base-hardening toolset (`scripts/`) that
|
||||
can be run against any new Proxmox host — repo/updates, SSH, firewall, PVE
|
||||
user/access hardening — verified with `scripts/audit.sh`.
|
||||
- Stage 2 (future): 3-node cluster, quorum via corosync, HA-managed VMs
|
||||
backed by Ceph. Needs dedicated hardware node 1 (`pve1`, an ASUS PN53 mini
|
||||
PC) doesn't have — see `docs/01-hardware-node1.md`.
|
||||
|
||||
See `CLAUDE.md` for the guardrails Claude Code follows when working
|
||||
against these hosts (`pve1` is production and off-limits by default;
|
||||
`pve-test` is the sandbox).
|
||||
|
||||
## Repo layout
|
||||
|
||||
- `docs/` — planning docs: hardware layout, storage migration, networking,
|
||||
security hardening, node roles. Read `docs/00-overview.md` first, then
|
||||
`docs/05-node-roles.md` for what `pve1`/`pve-test` actually are.
|
||||
- `scripts/` — scripts to apply configuration on a node (SSH hardening, repo
|
||||
switch, firewall, updates, wifi/bond networking, etc). Idempotent, safe
|
||||
to re-run. `scripts/bootstrap.sh` runs the full Stage 1 sequence end to
|
||||
end; `scripts/audit.sh` verifies it (read-only).
|
||||
`scripts/setup-wifi-bond-network.sh` reproduces `pve-test`'s wifi
|
||||
network (see `docs/06-pve-test-wifi-network.md`). `scripts/lib/` holds
|
||||
shared helpers (`common.sh`) sourced by the other scripts.
|
||||
- `config/` — reference config files/snippets to drop onto a node (firewall
|
||||
rules, sshd config, etc.).
|
||||
|
||||
## Quick start (Stage 1, on a fresh node)
|
||||
|
||||
```
|
||||
MGMT_CIDR=192.168.2.0/24 ./scripts/bootstrap.sh
|
||||
./scripts/create-admin-user.sh <username>
|
||||
# then enable 2FA for that user + root@pam via the web UI
|
||||
./scripts/audit.sh
|
||||
```
|
||||
|
||||
## Status
|
||||
|
||||
`pve1` built (ASUS PN53 mini PC, ZFS mirror boot+VM storage, single
|
||||
2.5GbE NIC) and already running production VMs/CTs. Stage 1 base
|
||||
hardening applied and verified (`scripts/audit.sh` all green): enterprise
|
||||
repos removed, SSH key-only + fail2ban, unattended security upgrades,
|
||||
PVE firewall (mgmt-only), subscription nag disabled, named admin user
|
||||
(`wayne@pve`) created. Remaining manual step: enable 2FA/TOTP for
|
||||
`wayne@pve` and `root@pam` via the web UI. Stage 2 (cluster/Ceph) not
|
||||
started — needs nodes 2/3 on hardware that can actually support it.
|
||||
@@ -0,0 +1,44 @@
|
||||
# Example cluster-wide firewall rules for /etc/pve/firewall/cluster.fw
|
||||
#
|
||||
# Stage 1 (single host, current): only the mgmt IPSET applies. Applied
|
||||
# automatically by scripts/deploy-firewall.sh, which fills in <MGMT_CIDR>.
|
||||
#
|
||||
# Stage 2 (future cluster/Ceph): the corosync and Ceph rules below are
|
||||
# commented out placeholders. Uncomment and fill in <COROSYNC_CIDR> /
|
||||
# <CEPH_CIDR> when nodes 2/3 join and those networks actually exist -
|
||||
# leaving them active on a single node with no corosync/Ceph traffic is
|
||||
# just dead config, and a literal `<COROSYNC_CIDR>` is invalid syntax if
|
||||
# left uncommented and unfilled.
|
||||
#
|
||||
# Copy to /etc/pve/firewall/cluster.fw and edit before enabling (or use
|
||||
# scripts/deploy-firewall.sh).
|
||||
|
||||
[OPTIONS]
|
||||
enable: 1
|
||||
policy_in: DROP
|
||||
policy_out: ACCEPT
|
||||
|
||||
[IPSET mgmt]
|
||||
<MGMT_CIDR>
|
||||
|
||||
[RULES]
|
||||
# Web UI + SSH only from the management network
|
||||
IN ACCEPT -source +mgmt -p tcp -dport 8006 -log nolog
|
||||
IN ACCEPT -source +mgmt -p tcp -dport 22 -log nolog
|
||||
|
||||
# ICMP echo (ping) from the management network - diagnostic convenience
|
||||
# only, nothing else depends on it. Without this, policy_in DROP silently
|
||||
# eats ping while SSH/web UI keep working - looks like an outage during
|
||||
# troubleshooting when the host is actually fine. See
|
||||
# docs/06-pve-test-wifi-network.md for a case this caused real confusion.
|
||||
IN ACCEPT -source +mgmt -p icmp -icmp-type echo-request -log nolog
|
||||
|
||||
# Stage 2: Corosync (cluster quorum) - uncomment once node 2/3 join and
|
||||
# the corosync network/VLAN exists.
|
||||
# IN ACCEPT -source <COROSYNC_CIDR> -p udp -dport 5404:5405 -log nolog
|
||||
|
||||
# Stage 2: Ceph (uncomment once Ceph is live; ports: mon 3300,6789,
|
||||
# osd/mgr/mds 6800-7300)
|
||||
# IN ACCEPT -source <CEPH_CIDR> -p tcp -dport 3300 -log nolog
|
||||
# IN ACCEPT -source <CEPH_CIDR> -p tcp -dport 6789 -log nolog
|
||||
# IN ACCEPT -source <CEPH_CIDR> -p tcp -dport 6800:7300 -log nolog
|
||||
@@ -0,0 +1,116 @@
|
||||
# Overview & Roadmap
|
||||
|
||||
## Staging
|
||||
|
||||
This repo now targets two distinct stages, in order:
|
||||
|
||||
- **Stage 1 (active)** — base configuration and hardening for a single
|
||||
Proxmox host, applicable to *any* node regardless of eventual cluster
|
||||
plans: repo/updates, SSH, firewall, PVE user/access hardening. This is
|
||||
what `scripts/bootstrap.sh`, `scripts/audit.sh`, and
|
||||
`04-security-hardening.md` cover, and what's being built out against
|
||||
node 1 (`pve1`, an ASUS PN53 mini PC) right now.
|
||||
- **Stage 2 (future)** — the multi-node HA/Ceph cluster described below
|
||||
and in `01-hardware-node1.md` / `02-storage-zfs-ceph.md` /
|
||||
`03-networking.md`. Deliberately deferred: `pve1`'s hardware (2 NVMe
|
||||
already merged into one ZFS mirror used for both boot and VM storage, a
|
||||
single 2.5GbE NIC) can't support the separate boot/Ceph disks or
|
||||
bonded/segregated networking those docs assume. Revisit once dedicated
|
||||
cluster hardware (nodes 2/3) is actually being bought and provisioned;
|
||||
until then treat the content below as a target design, not a
|
||||
description of `pve1`.
|
||||
|
||||
## Background
|
||||
|
||||
Old hardware required disabling KVM hardware virtualization for VMs to
|
||||
start at all (falls back to software emulation — slow). This is a
|
||||
host/BIOS-level issue, not a Proxmox limitation. Confirmed not present on
|
||||
`pve1` (ASUS PN53, Ryzen 7 7735HS): AMD-V and IOMMU both show enabled at
|
||||
boot (`dmesg | grep -i iommu`), no workaround needed. If this hardware line
|
||||
is reused for nodes 2/3, this should hold there too, but re-verify per
|
||||
node before assuming it.
|
||||
|
||||
## Stage 1: base config & hardening (active)
|
||||
|
||||
Applies to `pve1` now, and to every future node regardless of whether it
|
||||
ever joins the Stage 2 cluster. Covered by `04-security-hardening.md` and
|
||||
`scripts/bootstrap.sh` / `scripts/audit.sh`:
|
||||
|
||||
1. Fresh PVE install; confirm VT-x/AMD-V + IOMMU per the note above.
|
||||
2. Switch off the enterprise repos, onto no-subscription
|
||||
(`scripts/switch-to-no-subscription-repo.sh`).
|
||||
3. SSH hardening: key-only root login + fail2ban
|
||||
(`scripts/harden-ssh.sh`).
|
||||
4. Unattended security upgrades, no auto-reboot
|
||||
(`scripts/setup-unattended-upgrades.sh`).
|
||||
5. PVE datacenter firewall, default-deny, mgmt-only SSH/8006
|
||||
(`scripts/deploy-firewall.sh`).
|
||||
6. Named PVE admin user (Administrator role) + 2FA, `root@pam` reserved
|
||||
for emergencies (`scripts/create-admin-user.sh`, then manual TOTP
|
||||
enrollment via the web UI).
|
||||
7. Verify with `scripts/audit.sh`.
|
||||
|
||||
`pve1`'s actual disk/network layout (single ZFS mirror for boot + VMs, one
|
||||
2.5GbE NIC) is documented as-is in `01-hardware-node1.md` — Stage 1 doesn't
|
||||
require or assume the split-disk/multi-NIC layout Stage 2 wants.
|
||||
|
||||
## Stage 2: HA cluster + Ceph (future, deferred)
|
||||
|
||||
Everything below this point is the target design for when nodes 2 and 3
|
||||
are actually being provisioned. Not applicable to `pve1` as it stands.
|
||||
|
||||
**`pve-test` existing does not mean node 2 exists.** A second physical
|
||||
node (`pve-test`) does run alongside `pve1` — see `05-node-roles.md` —
|
||||
but it's a sandbox/test box, not built to this Stage 2 design, and as of
|
||||
this writing runs on **wifi** networking
|
||||
(`06-pve-test-wifi-network.md`), which is directly incompatible with
|
||||
corosync's latency/jitter requirements below. `pve-test` and `pve1` were
|
||||
briefly clustered and then deliberately de-clustered for exactly this
|
||||
reason. Don't treat `pve-test` as progress toward Stage 2 without a
|
||||
deliberate decision to rebuild its networking first.
|
||||
|
||||
### End goal
|
||||
|
||||
3-node Proxmox VE cluster with HA-managed VMs backed by **Ceph** — true
|
||||
distributed shared storage, sync replication, near-zero RPO on failover
|
||||
(see `02-storage-zfs-ceph.md`). Ceph needs 3+ nodes and a fast dedicated
|
||||
network, so it can't exist until nodes 2 and 3 are up.
|
||||
|
||||
Deliberately no intermediate "ZFS + storage replication" HA step. Node 1
|
||||
runs local ZFS for boot + VM storage with no cluster-wide HA until Ceph
|
||||
goes live — as soon as nodes 2/3 join, VMs move onto Ceph rather than
|
||||
adopting ZFS replication as a stopgap. Simpler end state, one storage
|
||||
model to operate instead of two.
|
||||
|
||||
### Cluster fundamentals (apply from node 1 onward)
|
||||
|
||||
- 3 nodes minimum for real quorum. If starting with 2, add a QDevice
|
||||
(small VM or Raspberry Pi) as tie-breaker.
|
||||
- Dedicated network for corosync (cluster/quorum traffic) — never shared
|
||||
with VM or storage traffic. Needs low, consistent latency (well under
|
||||
5ms); jitter matters more than bandwidth.
|
||||
- All nodes on the same PVE version, NTP-synced, SSH reachable between
|
||||
nodes.
|
||||
- Set VM CPU type to a portable type (e.g. `x86-64-v2-AES` or `kvm64`)
|
||||
rather than `host` if nodes will ever have different CPUs — needed for
|
||||
clean live migration.
|
||||
|
||||
### Rollout sequence (Stage 2, once dedicated cluster hardware exists)
|
||||
|
||||
1. Build node 1 per `01-hardware-node1.md`'s target design — fresh PVE
|
||||
install on a dedicated ZFS boot mirror, Ceph-earmarked disks left idle
|
||||
(or as a temporary local ZFS pool, to be wiped later — see
|
||||
`02-storage-zfs-ceph.md`). Note: this assumes hardware with enough
|
||||
disks/NICs to separate boot, Ceph, and network roles — `pve1` does not
|
||||
have this and stays on Stage 1 only unless rebuilt on different
|
||||
hardware.
|
||||
2. Migrate VMs onto the new node via `vzdump` → copy backups →
|
||||
`qmrestore` (converts disks to ZVOLs). No HA yet — single node.
|
||||
3. Stage 1 base hardening already applied; layer on Stage 2 networking
|
||||
(`03-networking.md`) before joining a cluster.
|
||||
4. Add nodes 2 and 3 identically (same disk/network layout).
|
||||
5. Join cluster, stand up dedicated corosync network.
|
||||
6. Wipe the Ceph-earmarked disks (if used as temporary ZFS) and
|
||||
initialize Ceph across all 3 nodes.
|
||||
7. Migrate VMs from local ZFS onto Ceph-backed storage, then configure HA
|
||||
groups.
|
||||
@@ -0,0 +1,92 @@
|
||||
# Node 1 Hardware Layout
|
||||
|
||||
## pve1 as built (current reality)
|
||||
|
||||
`pve1` is an ASUS PN53 mini PC (Ryzen 7 7735HS, 32GB RAM), not the
|
||||
dedicated-server hardware the target design below assumes:
|
||||
|
||||
- **Disks**: 2x 2TB NVMe (Crucial CT2000E100SSD8), both in a single ZFS
|
||||
mirror (`rpool`) that serves as both the boot pool and VM storage
|
||||
(`local-zfs` = `rpool/data`). No spare disks to earmark for Ceph — the
|
||||
chassis only has 2 NVMe slots.
|
||||
- **Network**: one physical NIC (Realtek RTL8125, 2.5GbE), bridged as
|
||||
`vmbr0`. No second NIC for a dedicated corosync/Ceph link. (An unused
|
||||
`nic1` stanza in `/etc/network/interfaces` is a leftover from the
|
||||
installer template — there is no second NIC on this hardware.)
|
||||
|
||||
This is sufficient and correct for **Stage 1** (see `00-overview.md`) —
|
||||
base config and hardening don't need split disks or multiple NICs. It is
|
||||
*not* sufficient for **Stage 2** (Ceph/HA) as designed below without
|
||||
either different hardware or a materially different plan (e.g.
|
||||
USB/Thunderbolt-attached OSD storage, which trades away the
|
||||
enterprise-SSD/PLP guidance below — not recommended, revisit when
|
||||
actually provisioning nodes 2/3). Treat everything from here down as the
|
||||
Stage 2 target design for purpose-built hardware, not a description of
|
||||
`pve1`.
|
||||
|
||||
## Target design (Stage 2, future dedicated hardware)
|
||||
|
||||
Build node 1 so nodes 2/3 are drop-in identical later — don't re-architect
|
||||
disks or network when the cluster grows.
|
||||
|
||||
## Disks — two roles, physically separate devices
|
||||
|
||||
1. **Boot/OS pool (`rpool`)** — 2x small SSDs (240-480GB plenty), ZFS
|
||||
mirror. Proxmox itself only. Never share with Ceph OSDs.
|
||||
2. **Future Ceph OSD disks** — must end up as raw, unformatted devices —
|
||||
no ZFS/RAID/LVM underneath (Ceph does its own replication; anything
|
||||
underneath just doubles copy-on-write/checksumming and hurts
|
||||
performance). Use enterprise SATA/NVMe SSDs with power-loss protection
|
||||
(PLP) — matters far more for Ceph write latency than for general ZFS
|
||||
use. Ceph needs 3 nodes minimum to go live, so on node 1 these disks
|
||||
either sit idle or run as a temporary local ZFS pool (all VMs live
|
||||
here until nodes 2/3 exist), to be wiped and handed to Ceph once the
|
||||
cluster can actually run it. See `02-storage-zfs-ceph.md`.
|
||||
|
||||
No permanent local-ZFS "replicated tier" — once Ceph is live, it's the
|
||||
only HA storage; local ZFS is boot pool + this temporary pre-Ceph staging
|
||||
role, not an ongoing parallel tier. Avoid consumer QLC SSDs for either
|
||||
role — Ceph punishes it on latency, ZFS on sync writes/scrub.
|
||||
|
||||
## Networking — cable and provision for the final topology now
|
||||
|
||||
Logically separate networks (ideally separate NICs/VLANs):
|
||||
|
||||
- **Management** — web UI / SSH
|
||||
- **Corosync** — cluster quorum traffic, low-latency, unshared
|
||||
- **Ceph public** — VM-to-OSD traffic
|
||||
- **Ceph cluster/backend** — OSD-to-OSD replication (heaviest load)
|
||||
|
||||
Practical layout: 2x 10/25GbE bonded or split — one pair for Ceph, one
|
||||
for mgmt + corosync + VM traffic, with corosync on its own VLAN even if
|
||||
sharing a physical NIC. Get switch/cabling right on node 1 so nodes 2/3
|
||||
are identical drops.
|
||||
|
||||
## CPU / RAM sizing
|
||||
|
||||
Size for the end state, not day one — RAM is the hardest thing to
|
||||
retrofit. Budget covers:
|
||||
|
||||
- OS + ZFS ARC (ZFS wants RAM, not just disk)
|
||||
- Ceph OSD daemons — realistically 3-5GB per OSD once running
|
||||
- Actual VM workloads
|
||||
|
||||
Roughly a core per OSD on top of what VMs need. If OSDs won't be active
|
||||
for a while, that's headway, but buy for 3 nodes' worth of eventual OSD
|
||||
load.
|
||||
|
||||
## Backup target (PBS)
|
||||
|
||||
Keep it off the Ceph/compute nodes if possible — its failure domain
|
||||
should be independent of the cluster. Modest separate machine or NAS:
|
||||
ZFS mirror or raidz2, ECC RAM if possible, capacity for retention policy.
|
||||
If it has to run as a VM inside the cluster short-term, that's a known
|
||||
compromise, not the end state.
|
||||
|
||||
## Node 1 install sequence
|
||||
|
||||
1. Install Proxmox VE fresh onto the ZFS boot mirror.
|
||||
2. Provision the Ceph-earmarked disks as a temporary local ZFS pool and
|
||||
run all VMs from it (or leave idle if VMs aren't moving over yet).
|
||||
3. Once nodes 2/3 join and Ceph goes live: wipe this pool, hand the disks
|
||||
to Ceph, migrate VMs onto Ceph-backed storage.
|
||||
@@ -0,0 +1,66 @@
|
||||
# Storage: LVM-thin → ZFS → Ceph
|
||||
|
||||
**Stage 2 (future).** Describes the target storage model once dedicated
|
||||
cluster hardware exists. `pve1`'s current single ZFS mirror (boot + VM
|
||||
storage combined, see `01-hardware-node1.md`) is the Stage 1 end state for
|
||||
now, not an intermediate step being actively migrated from.
|
||||
|
||||
## Why move off LVM-thin
|
||||
|
||||
Neither ZFS nor LVM-thin is shared storage — both are node-local. HA needs
|
||||
a VM's disk reachable from more than one node so it can restart elsewhere
|
||||
on host failure. LVM-thin has no answer for that. Ceph does, natively.
|
||||
|
||||
## Storage model: single node → 3-node cluster
|
||||
|
||||
No intermediate "ZFS + replication" HA step. The plan is deliberately a
|
||||
single storage model at the end (Ceph), not two to operate long-term:
|
||||
|
||||
- **Single node (node 1 only)**: local ZFS pool, no cluster-wide HA. This
|
||||
is a temporary state, not a design to build tooling around.
|
||||
- **3 nodes with Ceph live**: VMs run on Ceph-backed storage — true
|
||||
distributed, synchronous storage across all nodes, near-zero RPO on
|
||||
failover. Needs 3+ nodes and a fast dedicated network (see
|
||||
`03-networking.md`), which is exactly why it can't exist before then.
|
||||
|
||||
## Migration plan (old hardware → new hardware)
|
||||
|
||||
Don't convert the old LVM-thin box in place. Rebuild fresh on new
|
||||
hardware with ZFS from the installer (mirror if 2+ disks), then move VMs:
|
||||
|
||||
1. On the old host: `vzdump` each VM to a backup file (external drive,
|
||||
NFS share, or PBS if available).
|
||||
2. Copy backups to the new host.
|
||||
3. `qmrestore` onto the new ZFS storage — disks land as ZVOLs.
|
||||
|
||||
Alternative if both hosts can see each other on the network: temporarily
|
||||
cluster them and use the GUI "Migrate" with a storage move (offline only
|
||||
— live migration doesn't cross storage types).
|
||||
|
||||
## Standing up Ceph once nodes 2 and 3 exist
|
||||
|
||||
1. Wipe the temporary local ZFS pool on the Ceph-earmarked disks (see
|
||||
`01-hardware-node1.md`) on all 3 nodes — they need to end up raw,
|
||||
unformatted.
|
||||
2. Install the Ceph packages on all 3 nodes (`pveceph install`) and
|
||||
initialize the cluster (`pveceph init`), using the dedicated Ceph
|
||||
network from `03-networking.md`.
|
||||
3. Create Ceph monitors and managers (3 mons for quorum, matching node
|
||||
count).
|
||||
4. Create OSDs directly on the raw disks on each node — no ZFS/RAID
|
||||
underneath.
|
||||
5. Create a Ceph pool sized for your VM storage needs (replica count,
|
||||
typically 3 for full redundancy across 3 nodes).
|
||||
6. Add the pool as PVE storage (RBD), then migrate VMs from local ZFS
|
||||
onto it — offline migration if crossing storage types, or storage
|
||||
migration via the GUI.
|
||||
7. Configure HA groups once VMs are on Ceph-backed storage.
|
||||
|
||||
## Notes
|
||||
|
||||
- Ceph RAM/CPU overhead is real — budget per `01-hardware-node1.md`
|
||||
(roughly 3-5GB RAM and a core per OSD, on top of VM workloads).
|
||||
- Enterprise SSDs with power-loss protection (PLP) matter far more here
|
||||
than for plain ZFS — Ceph write latency is sensitive to it.
|
||||
- Once Ceph is live, local ZFS remains only for each node's boot pool —
|
||||
it's not a fallback tier for VM storage going forward.
|
||||
@@ -0,0 +1,66 @@
|
||||
# Networking
|
||||
|
||||
## pve1 as built (Stage 1, current)
|
||||
|
||||
Single NIC (2.5GbE), single bridge `vmbr0` on the flat LAN
|
||||
(`192.168.2.0/24`), no VLANs. There is no corosync or Ceph traffic to
|
||||
separate yet — this node isn't clustered. Segmentation for Stage 1 is
|
||||
done at the firewall, not the network: `scripts/deploy-firewall.sh`
|
||||
restricts SSH (22) and the web UI (8006) to the management CIDR via the
|
||||
PVE datacenter firewall (default-deny inbound otherwise). That's
|
||||
sufficient until Stage 2 needs actual separate physical/VLAN paths for
|
||||
corosync and Ceph traffic — see below.
|
||||
|
||||
## pve-test as built (sandbox, current)
|
||||
|
||||
Different node, different design, not a Stage 1/2 example to generalize
|
||||
from: `pve-test` runs `vmbr0` bridged over a wifi NIC in 4addr client mode
|
||||
(active-backup bonded with a wired NIC as an automatic fallback). Full
|
||||
detail, including why this is normally impossible and how it was
|
||||
validated before trusting it with the management IP, in
|
||||
`06-pve-test-wifi-network.md`. This is intentionally a one-off for a
|
||||
standalone sandbox box — never extend it to a node that's clustered or
|
||||
Ceph-connected (see the Stage 2 note in `00-overview.md`).
|
||||
|
||||
## Target design (Stage 2, future cluster)
|
||||
|
||||
## Required separation
|
||||
|
||||
Keep these on logically separate networks/VLANs, ideally separate NICs:
|
||||
|
||||
- **Management** — web UI (8006), SSH
|
||||
- **Corosync** — cluster quorum. Low, *consistent* latency (well under
|
||||
5ms) matters more than bandwidth. Never share with VM/storage traffic.
|
||||
- **Ceph public** — VM-to-OSD traffic (once Ceph is live)
|
||||
- **Ceph cluster/backend** — OSD-to-OSD replication, heaviest load
|
||||
|
||||
## Practical layout
|
||||
|
||||
2x 10/25GbE bonded or split:
|
||||
|
||||
- Link pair A → Ceph (public + backend, or split further if 4 NICs
|
||||
available)
|
||||
- Link pair B → management + corosync + VM traffic, with corosync on its
|
||||
own VLAN even when sharing a physical NIC with the rest
|
||||
|
||||
## Cluster join requirements
|
||||
|
||||
- All nodes reachable to each other on SSH (22) and the corosync network
|
||||
- Same PVE version across nodes
|
||||
- NTP-synced clocks
|
||||
|
||||
## Firewall
|
||||
|
||||
Proxmox's built-in firewall operates at datacenter and node level.
|
||||
Default-deny, then whitelist:
|
||||
|
||||
- SSH from the management network/VLAN only
|
||||
- Web UI (8006) from the management network/VLAN only
|
||||
- Corosync ports between cluster nodes
|
||||
- Ceph ports between cluster nodes (once Ceph is live)
|
||||
|
||||
Enforce the network separation above at the firewall — corosync and Ceph
|
||||
traffic shouldn't be reachable from the VM network even if they end up
|
||||
sharing a physical link.
|
||||
|
||||
See `config/pve-firewall/` for a starting rule set.
|
||||
@@ -0,0 +1,112 @@
|
||||
# Security Hardening
|
||||
|
||||
Stage 1 (see `00-overview.md`) — applies to any Proxmox host, independent
|
||||
of cluster plans. Proxmox has no `sudo` out of the box — everything
|
||||
defaults to root. That's the install default, not the recommended end
|
||||
state. Two layers to harden separately.
|
||||
|
||||
## Checklist / script mapping
|
||||
|
||||
Run `scripts/bootstrap.sh` for everything except the admin user (needs a
|
||||
username decision) and 2FA enrollment (must be done interactively via the
|
||||
web UI — there's no safe way to script TOTP secret generation over SSH).
|
||||
Then run `scripts/audit.sh` to verify. Order matters (matches
|
||||
`bootstrap.sh`):
|
||||
|
||||
| # | Item | Script | Manual step required? |
|
||||
|---|------|--------|------------------------|
|
||||
| 1 | Remove enterprise repos, switch to no-subscription | `switch-to-no-subscription-repo.sh` | no |
|
||||
| 2 | Linux admin user with SSH key + sudo access | `setup-linux-admin-user.sh <user> <pubkey>` | yes — choose a username and provide your SSH public key. Run this **before** SSH hardening or pass `ADMIN_USER`/`ADMIN_SSH_KEY` to `bootstrap.sh` so it runs automatically at the right point |
|
||||
| 3 | Passwordless sudo for pvesh/qm/pct | `setup-admin-sudo.sh <username>` | yes — same username as step 2 |
|
||||
| 4 | SSH: key-only root login + fail2ban | `harden-ssh.sh` | no — step 2 ensures authorized_keys are in place first |
|
||||
| 5 | Unattended security upgrades, no auto-reboot | `setup-unattended-upgrades.sh` | no |
|
||||
| 6 | PVE firewall, default-deny, mgmt-only SSH/8006 | `deploy-firewall.sh` | needs `MGMT_CIDR` set |
|
||||
| 7 | Disable subscription nag (cosmetic) | `disable-subscription-nag.sh` | no |
|
||||
| 8 | Named PVE admin user, Administrator role | `create-admin-user.sh <username>` | yes — pick the username, change the generated password on first login |
|
||||
| 9 | 2FA/TOTP on that user and `root@pam` | — | yes — web UI only: Datacenter → Permissions → Two Factor, or user menu → TFA |
|
||||
| 10 | Verify everything above | `audit.sh` | no |
|
||||
|
||||
## Linux/SSH layer
|
||||
|
||||
- A named Linux system user (created by `setup-linux-admin-user.sh`) with an
|
||||
SSH authorized key and `sudo` group membership is the primary SSH login
|
||||
account. Root SSH is locked to key-only after `harden-ssh.sh` runs; the
|
||||
Linux admin user is how you get shell access day-to-day without using root.
|
||||
- `setup-admin-sudo.sh` adds a narrower, password-free sudoers rule for the
|
||||
Proxmox management tools (`pvesh`, `qm`, `pct`) specifically — needed for
|
||||
non-interactive automation scripts that SSH in and run these tools without a
|
||||
TTY.
|
||||
- `PermitRootLogin prohibit-password` in `sshd_config` — root can only
|
||||
log in via SSH key, never password. Kills most brute-force attempts.
|
||||
- fail2ban jail for SSH on top of that.
|
||||
- Restrict SSH to the management VLAN/trusted IPs via the Proxmox
|
||||
firewall (see `03-networking.md`) rather than exposing broadly.
|
||||
|
||||
## PVE/web layer (the one that actually matters day-to-day)
|
||||
|
||||
- Keep `root@pam` for emergencies only.
|
||||
- Create a named user (e.g. `wayne@pve`) with the Administrator role for
|
||||
routine cluster management — `create-admin-user.sh` does this, or
|
||||
Datacenter → Permissions → Users manually.
|
||||
- Enable 2FA (TOTP or hardware key) on both that account and `root@pam`:
|
||||
Datacenter → Permissions → Realms/Users.
|
||||
- For API integrations (monitoring, automation, Terraform, etc.), issue
|
||||
scoped API tokens with least-privilege roles (e.g. `PVEAuditor` or a
|
||||
custom role) — never hand out root credentials.
|
||||
|
||||
## Firewall
|
||||
|
||||
Default-deny at datacenter/node level, whitelist only what's needed (see
|
||||
`03-networking.md` for the specifics). Template in
|
||||
`config/pve-firewall/cluster.fw.example`, applied by
|
||||
`scripts/deploy-firewall.sh`.
|
||||
|
||||
**ICMP echo (ping) is explicitly allowed from the management network**,
|
||||
alongside SSH/8006 — not required for anything to function, but without
|
||||
it `policy_in: DROP` silently eats ping while SSH/web UI keep working.
|
||||
That split (ping dead, everything else fine) reads exactly like a real
|
||||
outage mid-troubleshooting; see `06-pve-test-wifi-network.md` for a case
|
||||
this caused genuine confusion after a network change. If you ever debug
|
||||
"can't ping but can SSH", check this firewall before assuming the
|
||||
network itself is broken.
|
||||
|
||||
**This file is cluster-wide, not per-node**: `cluster.fw` lives in
|
||||
`/etc/pve/firewall/` — shared via pmxcfs across every node in a cluster.
|
||||
A node that joins a cluster inherits whatever's already there, and (per
|
||||
`docs/05-node-roles.md`) keeps its own local copy after leaving. Don't
|
||||
assume a node's firewall state matches what `deploy-firewall.sh` was
|
||||
last run with directly against it — check `pve-firewall status` /
|
||||
`/etc/pve/firewall/cluster.fw` on the actual node.
|
||||
|
||||
## Repos and updates
|
||||
|
||||
Fresh installs point at the enterprise repo, which fails on `apt update`
|
||||
without a subscription. `scripts/switch-to-no-subscription-repo.sh`
|
||||
removes the enterprise sources entirely (renamed `.disabled`, not just
|
||||
commented out) and switches to the no-subscription repo — handles both
|
||||
the legacy `.list` format and the deb822 `.sources` format current
|
||||
installers write. Keep the host patched — hypervisor CVEs are high-value
|
||||
targets; `scripts/setup-unattended-upgrades.sh` automates security
|
||||
patches (deliberately no auto-reboot on a hypervisor — check
|
||||
`/var/run/reboot-required` and reboot during a planned window).
|
||||
|
||||
The web UI's "No valid subscription" popup and dashboard indicator are
|
||||
cosmetic upsell, not a security control, but with no subscription they'll
|
||||
nag on every login — `scripts/disable-subscription-nag.sh` patches
|
||||
`proxmox-widget-toolkit`'s JS to suppress them, and installs an apt
|
||||
`Post-Invoke` hook that reapplies the patch automatically after every
|
||||
`apt`/`dpkg` run, since a `proxmox-widget-toolkit` package upgrade
|
||||
overwrites the patched file.
|
||||
|
||||
## Misc
|
||||
|
||||
- Management interface on a network you trust, not the same broadcast
|
||||
domain as guest VM traffic.
|
||||
- If the web UI is ever needed outside the LAN, put it behind a VPN —
|
||||
don't port-forward 8006 directly.
|
||||
|
||||
## Further reading / not yet automated here
|
||||
|
||||
- CIS Benchmark for Proxmox VE
|
||||
- Community PVE hardening guides (kernel parameters, audit logging,
|
||||
storage encryption)
|
||||
@@ -0,0 +1,83 @@
|
||||
# Node Roles: pve1 and pve-test
|
||||
|
||||
Two Proxmox VE hosts exist on the LAN. They are **not interchangeable** —
|
||||
different purpose, different risk tolerance, different guardrails. See
|
||||
`CLAUDE.md` for the actual rules Claude follows; this doc is the
|
||||
background/context those rules assume.
|
||||
|
||||
## pve1 (production)
|
||||
|
||||
ASUS PN53 mini PC (Ryzen 7 7735HS, 32GB RAM) — see `01-hardware-node1.md`
|
||||
for the full hardware layout. Stage 1 base hardening applied and verified
|
||||
(`04-security-hardening.md`).
|
||||
|
||||
Runs real production workloads:
|
||||
|
||||
- `server-nixos` (VM) and LXC containers `pihole`, `claude`, `nix-cache`,
|
||||
`docker`, `pdm`, `pxe-boot` — DNS, this Claude Code environment itself,
|
||||
the LAN's Nix binary cache, etc.
|
||||
|
||||
Off-limits to Claude by default — see `CLAUDE.md`.
|
||||
|
||||
## pve-test (sandbox)
|
||||
|
||||
A separate physical node kept for testing. Has a capable GPU (earmarked
|
||||
for future GPU workloads — transcoding, local inference, etc. — nothing
|
||||
built on it yet as of this writing). No production guests run here.
|
||||
|
||||
Safe for Claude to create/destroy scratch VMs and containers on without
|
||||
asking — see `CLAUDE.md` for the exact boundary (node-level config is
|
||||
still not free-for-all even here).
|
||||
|
||||
### History: briefly clustered with pve1, then deliberately separated
|
||||
|
||||
On 2026-07-21/22, pve-test was joined to pve1 in a 2-node Proxmox cluster
|
||||
(corosync + shared `/etc/pve`) for a period, then the cluster was
|
||||
**intentionally destroyed** at the operator's explicit request — not a
|
||||
failure or accident. Rationale: the operator wanted pve-test moved onto
|
||||
wifi networking (see `06-pve-test-wifi-network.md`), and wifi is
|
||||
fundamentally unsuitable for corosync's latency/jitter requirements (token
|
||||
timeouts, flapping membership). Rather than fight that, the cluster was
|
||||
torn down first, then wifi was configured on the now-standalone node.
|
||||
|
||||
Teardown procedure used (safe to repeat if pve-test or pve1 is ever
|
||||
reclustered and needs separating again):
|
||||
|
||||
1. Un-manage any HA-assigned resources first if HA is in use
|
||||
(`ha-manager remove <sid>` per resource) — **critical**: if a node has
|
||||
HA-managed guests and its watchdog is still armed when it loses
|
||||
quorum, HA's self-fence behavior can force-reboot it. Removing the
|
||||
resource assignments first (not stopping the guests — just
|
||||
un-managing them) prevents this.
|
||||
2. Stop `pve-ha-lrm`/`pve-ha-crm` on all nodes once no resources remain
|
||||
assigned, confirm via `ha-manager status` that fencing is no longer
|
||||
armed.
|
||||
3. From a node that will remain in the cluster: `pvecm delnode <name>`
|
||||
for the node being removed. In a 2-node cluster with no QDevice, this
|
||||
can itself cause the *remaining* node to transiently lose quorum
|
||||
(killing a node's live corosync membership drops total votes below
|
||||
expected votes before the nodelist file can be rewritten to match) —
|
||||
this is expected, not a failure; proceed to step 4 regardless.
|
||||
4. On **each** node being separated (including one you just ran `delnode`
|
||||
from, if it's also being decoupled): `systemctl stop pve-cluster
|
||||
corosync`, `pmxcfs -l` (local mode, bypasses the quorum requirement
|
||||
for local writes), remove `/etc/pve/corosync.conf` and
|
||||
`/etc/corosync/*`, `killall pmxcfs`, `systemctl start pve-cluster`.
|
||||
This is the official "separate a node without reinstalling" procedure
|
||||
and doesn't touch any running VM/CT — they're independent OS
|
||||
processes, unaffected by corosync/pmxcfs state either way.
|
||||
5. Optional cosmetic cleanup: the node(s) staying up may retain a stale
|
||||
`/etc/pve/nodes/<removed-node>/` directory (cached VM/CT configs from
|
||||
when they were clustered) — safe to `rm -rf` once separation is
|
||||
confirmed; it's dead data, not a live reference to anything.
|
||||
|
||||
Guests were never at risk during this procedure (confirmed: all 7 of
|
||||
pve1's guests ran continuously throughout) — the only real hazard is the
|
||||
HA/watchdog self-fence path in step 1, and losing corosync-provided quorum
|
||||
temporarily blocking `/etc/pve` writes (not guest execution) in step 3.
|
||||
|
||||
### Current state: standalone, wifi-primary networking
|
||||
|
||||
pve-test now runs entirely independently of pve1, on the network design
|
||||
documented in `06-pve-test-wifi-network.md`. **Do not re-cluster
|
||||
pve-test while it's on wifi** — see that doc for why.
|
||||
@@ -0,0 +1,191 @@
|
||||
# pve-test's Wifi-Primary Network
|
||||
|
||||
Non-standard, deliberately chosen against normal Proxmox guidance (a
|
||||
hypervisor's management network is not supposed to be wireless). Applies
|
||||
**only** to `pve-test` as a standalone sandbox node — see
|
||||
`05-node-roles.md` for why this and cluster membership don't mix, and
|
||||
never apply this pattern to a node that's joined (or might join) a
|
||||
cluster.
|
||||
|
||||
## Why this works at all
|
||||
|
||||
Wifi (802.11) normally cannot be bridged the way Ethernet can: an access
|
||||
point only accepts frames whose source MAC matches the MAC that
|
||||
associated with it. A Linux bridge with a wifi port as a member sends
|
||||
frames tagged with whatever MAC actually generated them (the bridge's own
|
||||
MAC, a VM's MAC, etc.) — none of which match the wifi card's hardware
|
||||
MAC, so the AP silently drops them. This isn't a Linux/Proxmox limitation,
|
||||
it's how WiFi association works.
|
||||
|
||||
**4addr (WDS) client mode** is the exception: if both the wifi driver and
|
||||
the AP support it, the client tags frames with a 4th address field
|
||||
carrying the original MAC, and the AP forwards them like a real Ethernet
|
||||
segment. Most consumer routers do **not** support this (it's common on
|
||||
OpenWrt/DD-WRT/enterprise APs, rare on stock ISP hardware) — it has to be
|
||||
confirmed empirically, per-AP, before trusting it with a management IP.
|
||||
|
||||
pve-test's card (Intel AX200, `iwlwifi` driver, interface `wlp3s0`)
|
||||
supports 4addr client-side generically (this is a `mac80211` core
|
||||
feature, not driver-specific). The home AP it associates to
|
||||
(`nbn-fttp-net-5G`) was confirmed to honor it — see validation method
|
||||
below.
|
||||
|
||||
## Validate before ever touching a live management IP
|
||||
|
||||
Don't add the wifi NIC straight into your real bridge to "see if it
|
||||
works" — if 4addr isn't actually honored, you lose access to the box with
|
||||
no diagnostic trail (association succeeds; only the *data plane* silently
|
||||
fails). Test in an isolated scratch namespace first:
|
||||
|
||||
```bash
|
||||
# assumes wlp3s0 already associated with 4addr on (see systemd unit below)
|
||||
ip link add testbr0 type bridge && ip link set testbr0 up
|
||||
ip link set wlp3s0 master testbr0 && ip link set wlp3s0 up
|
||||
|
||||
ip netns add wifitest
|
||||
ip link add veth-host type veth peer name veth-ns
|
||||
ip link set veth-host master testbr0 && ip link set veth-host up
|
||||
ip link set veth-ns netns wifitest
|
||||
ip netns exec wifitest ip link set veth-ns address 02:11:22:33:44:55 # deliberately NOT the wifi card's MAC
|
||||
ip netns exec wifitest ip link set veth-ns up
|
||||
ip netns exec wifitest ip link set lo up
|
||||
|
||||
ip netns exec wifitest dhclient -v -1 veth-ns # real DHCP lease = AP forwards foreign MACs = 4addr genuinely works
|
||||
```
|
||||
|
||||
If that gets a lease (or at minimum a ping reply from the gateway) from a
|
||||
MAC that was never the one that associated, the AP is forwarding
|
||||
arbitrary-MAC frames — real bridge mode will work. If not, don't proceed
|
||||
to bridge mode; fall back to a routed/NAT design instead (wifi gets its
|
||||
own IP via DHCP, VMs NAT out through it — never covered here since it
|
||||
wasn't needed, but keep this fallback in mind if reproducing on different
|
||||
hardware/AP).
|
||||
|
||||
Tear the test namespace/bridge down afterwards (`ip netns del wifitest;
|
||||
ip link del veth-host; ip link set wlp3s0 nomaster; ip link del testbr0`)
|
||||
— it's scratch, not part of the real config.
|
||||
|
||||
## Final architecture
|
||||
|
||||
```
|
||||
wlp3s0 (wifi, 4addr client mode) ─┐
|
||||
├─ bond0 (active-backup, wlp3s0 primary) ─ vmbr0 (192.168.2.251/24)
|
||||
nic0 (wired, LAN backup) ─┘
|
||||
```
|
||||
|
||||
- **`wpa-4addr-<iface>.service`** (systemd unit, `Before=network-pre.target`) —
|
||||
sets 4addr mode and starts `wpa_supplicant` *before* ifupdown2 processes
|
||||
`/etc/network/interfaces`. Deliberately not using `wpasupplicant`'s own
|
||||
`wpa-conf` ifupdown2 hook integration — its ordering relative to a
|
||||
custom `pre-up iw ... set 4addr on` line is implementation-specific and
|
||||
not worth gambling on for something this hard to debug if it's wrong.
|
||||
The systemd unit gives full, deterministic control over sequencing
|
||||
instead.
|
||||
- **`bond0`** — active-backup bonding, `wlp3s0` as `bond-primary`,
|
||||
`nic0` as backup, `bond-miimon 100`. Bonding a wifi interface works here
|
||||
because `mac80211`/`iwlwifi` properly reports carrier state
|
||||
(`netif_carrier_on/off`) on association/disassociation, which is what
|
||||
bonding's `miimon` (with the default `use_carrier=1`) actually watches
|
||||
— it doesn't require a "real" MII-capable NIC.
|
||||
- **`vmbr0`** — unchanged IP (`192.168.2.251/24`), bridged over `bond0`
|
||||
instead of directly over a physical NIC.
|
||||
|
||||
Reproduce with `scripts/setup-wifi-bond-network.sh` — see its header
|
||||
comment for usage and required env vars (SSID/passphrase, management
|
||||
address/gateway). It stages `/etc/network/interfaces` and the systemd
|
||||
unit but does **not** auto-apply (`ifreload -a`) — see the next section
|
||||
for why that step needs care, not automation.
|
||||
|
||||
## Applying a live bridge-port change: what went wrong once, and what worked
|
||||
|
||||
Moving `vmbr0`'s underlying port live — while SSH'd in over the very
|
||||
address that lives on that bridge — is inherently risky: if the new port
|
||||
doesn't actually pass traffic, you lose the connection you're using to
|
||||
fix it.
|
||||
|
||||
**What failed**: doing the port swap via raw `ip link set nic0 nomaster`
|
||||
+ `ip link set nic0 down` (with `wlp3s0` already added as a second bridge
|
||||
member) caused an extended outage that needed a physical power-cycle to
|
||||
recover — `nic0` never came back up on its own even well past a 60s
|
||||
auto-revert watchdog's deadline. Importantly, the *host itself* never
|
||||
crashed — `journalctl -b -1` showed completely normal operation (a
|
||||
`pvestatd` polling loop, no gaps, no panic/OOM/watchdog trigger) right up
|
||||
until a keyboard was plugged in and it was manually reset. So the failure
|
||||
was specifically in the live network transition, not the OS — root cause
|
||||
unconfirmed, but plausibly bridge FDB/MAC-identity handling when a port
|
||||
carrying an already-live IP is swapped out via raw `ip link` rather than
|
||||
a coordinated reconfiguration.
|
||||
|
||||
**What worked**: writing the final state into `/etc/network/interfaces`
|
||||
and applying with `ifreload -a` (Proxmox's own supported hot-reload path)
|
||||
instead. Same end state, same risk window, but ifupdown2 evidently
|
||||
sequences the transition in a way raw `ip link` surgery didn't. This
|
||||
succeeded on the first retry using this method.
|
||||
|
||||
**Either way, expect ~30-60 seconds of apparent breakage even on a
|
||||
successful change** — the upstream switch/AP needs to relearn which port
|
||||
`192.168.2.251`'s MAC now lives behind. Don't judge success/failure
|
||||
before that window passes; a `ping`/SSH failure at the 5-10s mark is not
|
||||
yet a sign anything is wrong.
|
||||
|
||||
**Recommended safety net for any future live change here**: arm a
|
||||
backgrounded auto-revert-on-timeout before applying, e.g.:
|
||||
|
||||
```bash
|
||||
cp /etc/network/interfaces /etc/network/interfaces.bak
|
||||
cat > /root/revert.sh <<'EOF'
|
||||
#!/bin/bash
|
||||
cp /etc/network/interfaces.bak /etc/network/interfaces
|
||||
ifreload -a
|
||||
EOF
|
||||
chmod +x /root/revert.sh
|
||||
setsid nohup bash -c "sleep 45 && /root/revert.sh" >/root/revert.log 2>&1 < /dev/null &
|
||||
disown
|
||||
# now apply the real change, e.g.: ifreload -a
|
||||
# once confirmed working: pkill -f "sleep 45 && /root/revert.sh"
|
||||
```
|
||||
|
||||
This only self-heals if the box stays responsive enough for the
|
||||
backgrounded job to run to completion — it is not a substitute for
|
||||
physical/console access being available, just a way to avoid needing it
|
||||
for the common case.
|
||||
|
||||
## Troubleshooting: "can't ping it, web UI won't load" isn't necessarily an outage
|
||||
|
||||
Two independent things can make `pve-test` look dead when it isn't:
|
||||
|
||||
1. **Stale ARP after any change to `vmbr0`'s active port.** `vmbr0`'s MAC
|
||||
address follows whichever interface is currently active in `bond0`
|
||||
(`wlp3s0`'s MAC while wifi is primary, `nic0`'s if it fails over) — it
|
||||
is *not* fixed. Other devices on the LAN (including your own
|
||||
workstation) that cached the old MAC before a change won't notice
|
||||
until their ARP entry naturally expires or gets flushed
|
||||
(`ip neigh flush <ip>` / `arp -d <ip>`). Symptom: intermittent or
|
||||
totally dead connectivity from one specific device while others (or
|
||||
the host itself) are fine.
|
||||
2. **ICMP ping is blocked by the management firewall, unrelated to
|
||||
network health.** See `04-security-hardening.md`'s firewall section —
|
||||
`cluster.fw`'s `policy_in: DROP` only explicitly allows TCP 22/8006
|
||||
(now also ICMP echo-request, after this was hit) from the mgmt
|
||||
network. Before that rule was added, `ping` failed 100% *even with a
|
||||
perfectly correct, fresh ARP entry and full SSH/web UI access* —
|
||||
nothing to do with wifi, bonding, or the network being down. This is
|
||||
exactly what happened once: alarming "can't ping, web UI not loading"
|
||||
turned out to be a stale-ARP moment (which resolved itself) plus a
|
||||
pre-existing firewall policy (ping was never going to work,
|
||||
regardless of wifi).
|
||||
|
||||
**When `pve-test` seems unreachable, check in this order before assuming
|
||||
a real outage**: SSH (`ssh root@pve-test.sweet.home`) → web UI via `curl
|
||||
-sk -o /dev/null -w '%{http_code}' https://pve-test.sweet.home:8006/` →
|
||||
only then worry about `ping` specifically, and check
|
||||
`/etc/pve/firewall/cluster.fw` before blaming the network.
|
||||
|
||||
## Known limitation history
|
||||
|
||||
`nic0` (the bond's backup slave) initially had no cable physically
|
||||
connected when this was first set up — the bond was correctly configured
|
||||
but inert until a cable was plugged in. As of this writing a cable is
|
||||
connected and the backup slave is live (confirm with `cat
|
||||
/proc/net/bonding/bond0`) — if reproducing this setup, verify the same
|
||||
before assuming LAN failover will actually work.
|
||||
@@ -0,0 +1,133 @@
|
||||
#!/bin/bash
|
||||
# Read-only Stage 1 base-hardening audit. Checks the current state of a PVE
|
||||
# host against the checklist in docs/04-security-hardening.md and prints
|
||||
# PASS/FAIL per item. Exits non-zero if anything fails, so it can gate CI or
|
||||
# be run periodically as a compliance check. Makes no changes.
|
||||
#
|
||||
# Usage: ./audit.sh (run as root on the PVE host)
|
||||
set -uo pipefail
|
||||
|
||||
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||||
# shellcheck source=lib/common.sh
|
||||
source "${SCRIPT_DIR}/lib/common.sh"
|
||||
require_root
|
||||
|
||||
AUDIT_FAIL=0
|
||||
|
||||
# --- apt repos: no enabled enterprise source ---
|
||||
ENTERPRISE_ENABLED=0
|
||||
for f in /etc/apt/sources.list.d/*.sources /etc/apt/sources.list.d/*.list; do
|
||||
[ -f "$f" ] || continue
|
||||
grep -qi 'enterprise.proxmox.com' "$f" 2>/dev/null && ENTERPRISE_ENABLED=1
|
||||
done
|
||||
if [ "$ENTERPRISE_ENABLED" -eq 0 ]; then
|
||||
audit_pass "no enabled enterprise apt repo"
|
||||
else
|
||||
audit_fail "an enterprise apt repo is still enabled (needs a subscription to update)"
|
||||
fi
|
||||
|
||||
# --- SSH ---
|
||||
SSHD_T="$(sshd -T 2>/dev/null)"
|
||||
if echo "$SSHD_T" | grep -qiE '^permitrootlogin (prohibit-password|without-password)'; then
|
||||
audit_pass "sshd: PermitRootLogin prohibit-password (key-only)"
|
||||
else
|
||||
audit_fail "sshd: PermitRootLogin is not key-only (prohibit-password/without-password)"
|
||||
fi
|
||||
if echo "$SSHD_T" | grep -qi '^passwordauthentication no'; then
|
||||
audit_pass "sshd: PasswordAuthentication no"
|
||||
else
|
||||
audit_fail "sshd: PasswordAuthentication is not disabled"
|
||||
fi
|
||||
|
||||
# --- fail2ban ---
|
||||
if systemctl is-active --quiet fail2ban 2>/dev/null; then
|
||||
audit_pass "fail2ban is active"
|
||||
else
|
||||
audit_fail "fail2ban is not active"
|
||||
fi
|
||||
|
||||
# --- PVE firewall ---
|
||||
FW_STATUS="$(pve-firewall status 2>/dev/null || true)"
|
||||
if echo "$FW_STATUS" | grep -qi '^Status: enabled'; then
|
||||
audit_pass "pve-firewall is enabled"
|
||||
else
|
||||
audit_fail "pve-firewall is not enabled (status: ${FW_STATUS:-unknown})"
|
||||
fi
|
||||
if [ -f /etc/pve/firewall/cluster.fw ] && grep -qi '^policy_in:\s*DROP' /etc/pve/firewall/cluster.fw 2>/dev/null; then
|
||||
audit_pass "cluster.fw has default-deny inbound policy"
|
||||
else
|
||||
audit_fail "cluster.fw missing or does not default-deny inbound"
|
||||
fi
|
||||
|
||||
# --- unattended-upgrades ---
|
||||
if dpkg -s unattended-upgrades >/dev/null 2>&1 && systemctl is-enabled --quiet unattended-upgrades 2>/dev/null; then
|
||||
audit_pass "unattended-upgrades installed and enabled"
|
||||
else
|
||||
audit_fail "unattended-upgrades not installed/enabled"
|
||||
fi
|
||||
if [ -f /var/run/reboot-required ]; then
|
||||
audit_warn "a reboot is pending (/var/run/reboot-required) - schedule one"
|
||||
fi
|
||||
|
||||
# --- Linux admin user with SSH key (for non-root SSH login) ---
|
||||
LINUX_ADMIN_OK=0
|
||||
for auth_file in /home/*/.ssh/authorized_keys; do
|
||||
[ -f "$auth_file" ] || continue
|
||||
# Must have at least one non-comment, non-empty key line.
|
||||
if grep -qE '^(ssh-rsa|ssh-ed25519|ecdsa-sha2-nistp[0-9]+) ' "$auth_file" 2>/dev/null; then
|
||||
LINUX_ADMIN_OK=1
|
||||
break
|
||||
fi
|
||||
done
|
||||
if [ "$LINUX_ADMIN_OK" -eq 1 ]; then
|
||||
audit_pass "a non-root Linux user has an SSH authorized key"
|
||||
else
|
||||
audit_fail "no non-root Linux user has an authorized SSH key (run setup-linux-admin-user.sh)"
|
||||
fi
|
||||
|
||||
# --- named admin user (not just root@pam) ---
|
||||
if pveum user list --output-format json 2>/dev/null | grep -q '"userid":"[^"]*@pve"'; then
|
||||
audit_pass "a named @pve admin user exists (root@pam is not the only account)"
|
||||
else
|
||||
audit_fail "no named @pve user found - root@pam is the only account"
|
||||
fi
|
||||
|
||||
# --- passwordless sudo for pvesh/qm/pct ---
|
||||
# The nixos flake's create-proxmox-resource.sh runs pvesh/qm/pct over
|
||||
# non-interactive SSH, so the admin user needs NOPASSWD for these tools.
|
||||
SUDO_OK=0
|
||||
for f in /etc/sudoers.d/*-proxmox; do
|
||||
[ -f "$f" ] || continue
|
||||
if grep -qE 'NOPASSWD:.*pvesh' "$f" && grep -qE 'NOPASSWD:.*\bqm\b' "$f" && grep -qE 'NOPASSWD:.*\bpct\b' "$f"; then
|
||||
SUDO_OK=1
|
||||
break
|
||||
fi
|
||||
done
|
||||
if [ "$SUDO_OK" -eq 1 ]; then
|
||||
audit_pass "admin user has NOPASSWD sudo for pvesh/qm/pct"
|
||||
else
|
||||
audit_fail "no sudoers file grants NOPASSWD for pvesh/qm/pct (run setup-admin-sudo.sh <username>)"
|
||||
fi
|
||||
|
||||
# --- time sync ---
|
||||
if timedatectl show -p NTPSynchronized --value 2>/dev/null | grep -qx 'yes'; then
|
||||
audit_pass "clock is NTP-synchronized"
|
||||
else
|
||||
audit_fail "clock is not NTP-synchronized"
|
||||
fi
|
||||
|
||||
# --- subscription nag (cosmetic - warn only, never fails the audit) ---
|
||||
JS_FILE="/usr/share/javascript/proxmox-widget-toolkit/proxmoxlib.js"
|
||||
if [ -f "$JS_FILE" ] && ! grep -qF "data.status.toLowerCase() !== 'active'" "$JS_FILE"; then
|
||||
audit_pass "subscription nag patch applied"
|
||||
else
|
||||
audit_warn "subscription nag patch not applied (cosmetic only, see scripts/disable-subscription-nag.sh)"
|
||||
fi
|
||||
|
||||
echo
|
||||
if [ "$AUDIT_FAIL" -eq 0 ]; then
|
||||
echo "All Stage 1 base-hardening checks passed."
|
||||
else
|
||||
echo "One or more checks failed - see FAIL lines above."
|
||||
fi
|
||||
exit "$AUDIT_FAIL"
|
||||
@@ -0,0 +1,67 @@
|
||||
#!/bin/bash
|
||||
# Stage 1 base config + hardening, end to end, for a single fresh PVE host.
|
||||
# Runs the individual scripts in order. Idempotent - safe to re-run.
|
||||
#
|
||||
# If ADMIN_USER and ADMIN_SSH_KEY are set, a Linux system user is created
|
||||
# with SSH key access and sudo before SSH hardening runs - so key-based
|
||||
# login is in place before password auth is disabled. If they are not set,
|
||||
# a reminder is printed at the end to run setup-linux-admin-user.sh manually
|
||||
# (but do this BEFORE disconnecting, since password auth will be disabled).
|
||||
#
|
||||
# Usage:
|
||||
# MGMT_CIDR=192.168.2.0/24 ./bootstrap.sh
|
||||
# MGMT_CIDR=192.168.2.0/24 ADMIN_USER=wayne ADMIN_SSH_KEY="ssh-ed25519 ..." ./bootstrap.sh
|
||||
set -euo pipefail
|
||||
|
||||
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||||
# shellcheck source=lib/common.sh
|
||||
source "${SCRIPT_DIR}/lib/common.sh"
|
||||
require_root
|
||||
|
||||
if [ -z "${MGMT_CIDR:-}" ]; then
|
||||
echo "MGMT_CIDR is not set. Example: MGMT_CIDR=192.168.2.0/24 $0" >&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
STEP=0
|
||||
next_step() { STEP=$((STEP + 1)); echo; echo "=== ${STEP}: $* ==="; }
|
||||
|
||||
next_step "remove enterprise repos, switch to no-subscription"
|
||||
"${SCRIPT_DIR}/switch-to-no-subscription-repo.sh"
|
||||
|
||||
# Create the Linux admin user before SSH hardening so that authorized_keys
|
||||
# is in place before password auth is disabled.
|
||||
if [ -n "${ADMIN_USER:-}" ] && [ -n "${ADMIN_SSH_KEY:-}" ]; then
|
||||
next_step "Linux admin user '${ADMIN_USER}' + SSH key + sudo group"
|
||||
"${SCRIPT_DIR}/setup-linux-admin-user.sh" "$ADMIN_USER" "$ADMIN_SSH_KEY"
|
||||
|
||||
next_step "passwordless sudo for pvesh/qm/pct (${ADMIN_USER})"
|
||||
"${SCRIPT_DIR}/setup-admin-sudo.sh" "$ADMIN_USER"
|
||||
else
|
||||
echo
|
||||
echo "WARNING: ADMIN_USER / ADMIN_SSH_KEY not set -- skipping Linux user setup."
|
||||
echo " Run setup-linux-admin-user.sh and setup-admin-sudo.sh BEFORE disconnecting"
|
||||
echo " from this session, since the next step disables password authentication."
|
||||
fi
|
||||
|
||||
next_step "SSH hardening (key-only root login + fail2ban)"
|
||||
"${SCRIPT_DIR}/harden-ssh.sh"
|
||||
|
||||
next_step "unattended security upgrades"
|
||||
"${SCRIPT_DIR}/setup-unattended-upgrades.sh"
|
||||
|
||||
next_step "PVE firewall (mgmt-only SSH/8006)"
|
||||
MGMT_CIDR="$MGMT_CIDR" "${SCRIPT_DIR}/deploy-firewall.sh"
|
||||
|
||||
next_step "disable subscription nag (cosmetic)"
|
||||
"${SCRIPT_DIR}/disable-subscription-nag.sh"
|
||||
|
||||
echo
|
||||
echo "=== Base hardening applied. Remaining manual/deliberate steps: ==="
|
||||
if [ -z "${ADMIN_USER:-}" ]; then
|
||||
echo " - ${SCRIPT_DIR}/setup-linux-admin-user.sh <username> <ssh-pubkey>"
|
||||
echo " - ${SCRIPT_DIR}/setup-admin-sudo.sh <username> (NOPASSWD for pvesh/qm/pct)"
|
||||
fi
|
||||
echo " - ${SCRIPT_DIR}/create-admin-user.sh <username> (PVE web UI account)"
|
||||
echo " - Enable 2FA/TOTP for that user and root@pam via the web UI"
|
||||
echo " - ${SCRIPT_DIR}/audit.sh (verify everything above)"
|
||||
@@ -0,0 +1,43 @@
|
||||
#!/bin/bash
|
||||
# Create a named PVE admin user (Administrator role) so root@pam can be
|
||||
# reserved for emergencies. Generates a random initial password, printed
|
||||
# once - change it and enable TOTP on first login (Datacenter -> Permissions
|
||||
# -> Two Factor, or the user icon menu in the top right).
|
||||
#
|
||||
# Idempotent - if the user already exists, does nothing (won't reset an
|
||||
# existing password). Run as root on the PVE host.
|
||||
#
|
||||
# Usage: ./create-admin-user.sh <username> (realm is always @pve)
|
||||
set -euo pipefail
|
||||
|
||||
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||||
# shellcheck source=lib/common.sh
|
||||
source "${SCRIPT_DIR}/lib/common.sh"
|
||||
require_root
|
||||
|
||||
USERNAME="${1:-}"
|
||||
if [ -z "$USERNAME" ]; then
|
||||
echo "Usage: $0 <username>" >&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
USERID="${USERNAME}@pve"
|
||||
|
||||
if pveum user list --output-format json 2>/dev/null | grep -q "\"${USERID}\""; then
|
||||
echo "${USERID} already exists - not touching password or role. Skipping."
|
||||
exit 0
|
||||
fi
|
||||
|
||||
PASSWORD="$(openssl rand -base64 24)"
|
||||
|
||||
pveum user add "$USERID" --password "$PASSWORD" --comment "Named admin account, created by create-admin-user.sh"
|
||||
pveum acl modify / --users "$USERID" --roles Administrator
|
||||
|
||||
echo
|
||||
echo "Created ${USERID} with the Administrator role."
|
||||
echo "Initial password (shown once - not logged anywhere): ${PASSWORD}"
|
||||
echo
|
||||
echo "Next steps (do these before relying on this account):"
|
||||
echo " 1. Log in as ${USERID} and change the password."
|
||||
echo " 2. Enable TOTP/2FA for ${USERID} (and for root@pam)."
|
||||
echo " 3. Reserve root@pam for emergencies only from here on."
|
||||
@@ -0,0 +1,48 @@
|
||||
#!/bin/bash
|
||||
# Deploy the Proxmox datacenter-level firewall from
|
||||
# config/pve-firewall/cluster.fw.example, with the management CIDR filled
|
||||
# in, and enable it. Default-deny inbound; allow SSH/8006 from mgmt only.
|
||||
#
|
||||
# Idempotent - safe to re-run. Run as root on the PVE host.
|
||||
#
|
||||
# Usage: MGMT_CIDR=192.168.2.0/24 ./deploy-firewall.sh
|
||||
set -euo pipefail
|
||||
|
||||
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||||
# shellcheck source=lib/common.sh
|
||||
source "${SCRIPT_DIR}/lib/common.sh"
|
||||
require_root
|
||||
|
||||
if [ -z "${MGMT_CIDR:-}" ]; then
|
||||
echo "MGMT_CIDR is not set. Example: MGMT_CIDR=192.168.2.0/24 $0" >&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
if ! [[ "$MGMT_CIDR" =~ ^([0-9]{1,3}\.){3}[0-9]{1,3}/[0-9]{1,2}$ ]]; then
|
||||
echo "MGMT_CIDR '${MGMT_CIDR}' doesn't look like a CIDR (e.g. 192.168.2.0/24)." >&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
TEMPLATE="${SCRIPT_DIR}/../config/pve-firewall/cluster.fw.example"
|
||||
if [ ! -f "$TEMPLATE" ]; then
|
||||
echo "Template not found: $TEMPLATE" >&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# Corosync/Ceph rules stay commented placeholders until Stage 2 (cluster);
|
||||
# only the mgmt IPSET is real for a single Stage 1 node.
|
||||
mkdir -p /etc/pve/firewall
|
||||
write_if_changed "/etc/pve/firewall/cluster.fw" "$(sed "s|<MGMT_CIDR>|${MGMT_CIDR}|" "$TEMPLATE")"
|
||||
|
||||
echo "Validating ruleset..."
|
||||
pve-firewall compile
|
||||
|
||||
echo "Restarting pve-firewall..."
|
||||
pve-firewall restart
|
||||
sleep 1
|
||||
pve-firewall status
|
||||
|
||||
echo
|
||||
echo "Firewall enabled. SSH (22) and the web UI (8006) are now only reachable"
|
||||
echo "from ${MGMT_CIDR}. If your current SSH session is NOT from that range,"
|
||||
echo "reconnect and verify access before closing this session."
|
||||
+24
@@ -0,0 +1,24 @@
|
||||
#!/bin/bash
|
||||
# Install the subscription-nag patch (lib/nag-patch.sh) as a persistent
|
||||
# standalone script under /usr/local/sbin, plus an apt Post-Invoke hook that
|
||||
# re-applies it after every dpkg run - a proxmox-widget-toolkit package
|
||||
# upgrade overwrites the patched file, so without the hook the patch would
|
||||
# silently revert on the next `apt upgrade`.
|
||||
#
|
||||
# Idempotent - safe to re-run. Run as root on the PVE host.
|
||||
set -euo pipefail
|
||||
|
||||
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||||
# shellcheck source=lib/common.sh
|
||||
source "${SCRIPT_DIR}/lib/common.sh"
|
||||
require_root
|
||||
|
||||
INSTALLED="/usr/local/sbin/pve-disable-subscription-nag.sh"
|
||||
write_if_changed "$INSTALLED" "$(cat "${SCRIPT_DIR}/lib/nag-patch.sh")"
|
||||
chmod +x "$INSTALLED"
|
||||
|
||||
HOOK="/etc/apt/apt.conf.d/85pve-nosubnag"
|
||||
write_if_changed "$HOOK" 'DPkg::Post-Invoke { "test -x /usr/local/sbin/pve-disable-subscription-nag.sh && /usr/local/sbin/pve-disable-subscription-nag.sh || true"; };'
|
||||
|
||||
"$INSTALLED"
|
||||
echo "Subscription nag patch installed; will reapply automatically after updates."
|
||||
@@ -0,0 +1,43 @@
|
||||
#!/bin/bash
|
||||
# Apply baseline SSH hardening to a Proxmox VE node: key-only root login
|
||||
# + fail2ban. Idempotent - safe to re-run. Run as root on the PVE host.
|
||||
set -euo pipefail
|
||||
|
||||
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||||
# shellcheck source=lib/common.sh
|
||||
source "${SCRIPT_DIR}/lib/common.sh"
|
||||
require_root
|
||||
|
||||
if ! authorized_keys_present=$(find /root/.ssh/authorized_keys /home/*/.ssh/authorized_keys -type f 2>/dev/null | head -n1); then
|
||||
authorized_keys_present=""
|
||||
fi
|
||||
if [ -z "$authorized_keys_present" ]; then
|
||||
echo "WARNING: no authorized_keys found for any user yet." >&2
|
||||
echo "Add your SSH public key before disconnecting, or you'll lock yourself out." >&2
|
||||
fi
|
||||
|
||||
mkdir -p /etc/ssh/sshd_config.d
|
||||
write_if_changed "/etc/ssh/sshd_config.d/99-hardening.conf" "PermitRootLogin prohibit-password
|
||||
PasswordAuthentication no"
|
||||
|
||||
sshd -t
|
||||
systemctl reload sshd
|
||||
echo "sshd reloaded with key-only root login."
|
||||
|
||||
if ! dpkg -s fail2ban >/dev/null 2>&1; then
|
||||
apt-get update
|
||||
apt-get install -y fail2ban
|
||||
fi
|
||||
|
||||
mkdir -p /etc/fail2ban/jail.d
|
||||
write_if_changed "/etc/fail2ban/jail.d/sshd.local" "[sshd]
|
||||
enabled = true
|
||||
port = ssh
|
||||
backend = systemd
|
||||
maxretry = 5
|
||||
bantime = 1h
|
||||
findtime = 10m"
|
||||
|
||||
systemctl enable --now fail2ban
|
||||
systemctl restart fail2ban
|
||||
echo "fail2ban enabled for sshd."
|
||||
@@ -0,0 +1,47 @@
|
||||
#!/bin/bash
|
||||
# Shared helpers for proxmox-configuration scripts. Sourced, not executed
|
||||
# directly:
|
||||
# SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||||
# source "${SCRIPT_DIR}/lib/common.sh"
|
||||
|
||||
require_root() {
|
||||
if [ "$(id -u)" -ne 0 ]; then
|
||||
echo "Must run as root." >&2
|
||||
exit 1
|
||||
fi
|
||||
}
|
||||
|
||||
# Codename of the running Debian/PVE release, e.g. "trixie".
|
||||
pve_codename() {
|
||||
(. /etc/os-release && echo "$VERSION_CODENAME")
|
||||
}
|
||||
|
||||
# backup_file <path>
|
||||
# Copies an existing file to <path>.bak.<epoch>. No-op if it doesn't exist.
|
||||
backup_file() {
|
||||
local path="$1"
|
||||
if [ -f "$path" ]; then
|
||||
cp "$path" "${path}.bak.$(date +%s)"
|
||||
echo "Backed up ${path}"
|
||||
fi
|
||||
}
|
||||
|
||||
# write_if_changed <path> <content>
|
||||
# Writes content to path only if it differs from what's already there,
|
||||
# backing up the previous version first. Prints what happened.
|
||||
write_if_changed() {
|
||||
local path="$1" content="$2"
|
||||
if [ -f "$path" ] && [ "$(cat "$path")" = "$content" ]; then
|
||||
echo "Already up to date: $path"
|
||||
return 0
|
||||
fi
|
||||
backup_file "$path"
|
||||
printf '%s\n' "$content" > "$path"
|
||||
echo "Wrote $path"
|
||||
}
|
||||
|
||||
# --- audit.sh status helpers ---
|
||||
# Callers should initialize: AUDIT_FAIL=0
|
||||
audit_pass() { echo "PASS $1"; }
|
||||
audit_fail() { echo "FAIL $1"; AUDIT_FAIL=1; }
|
||||
audit_warn() { echo "WARN $1"; }
|
||||
@@ -0,0 +1,22 @@
|
||||
#!/bin/bash
|
||||
# Neutralizes the Proxmox "No valid subscription" nag (login popup and the
|
||||
# dashboard subscription indicator) by patching proxmox-widget-toolkit's
|
||||
# proxmoxlib.js. Cosmetic only - doesn't create or spoof a subscription
|
||||
# anywhere except this UI check.
|
||||
#
|
||||
# This file is not run from the repo directly - disable-subscription-nag.sh
|
||||
# installs a copy of it to /usr/local/sbin and wires it into an apt
|
||||
# Post-Invoke hook, because a proxmox-widget-toolkit package upgrade
|
||||
# overwrites proxmoxlib.js and reverts the patch. Idempotent: exits quietly
|
||||
# if already patched or if the file isn't present.
|
||||
set -euo pipefail
|
||||
|
||||
JS_FILE="/usr/share/javascript/proxmox-widget-toolkit/proxmoxlib.js"
|
||||
[ -f "$JS_FILE" ] || exit 0
|
||||
|
||||
PATTERN="data.status.toLowerCase() !== 'active'"
|
||||
grep -qF "$PATTERN" "$JS_FILE" || exit 0
|
||||
|
||||
cp "$JS_FILE" "${JS_FILE}.bak.$(date +%s)"
|
||||
sed -i "s/${PATTERN}/false/g" "$JS_FILE"
|
||||
echo "Patched subscription nag in $JS_FILE"
|
||||
@@ -0,0 +1,61 @@
|
||||
#!/bin/bash
|
||||
# Grant a named admin user passwordless sudo for Proxmox management tools
|
||||
# (pvesh, qm, pct) and the Nix package manager so that scripts in the
|
||||
# nixos flake repo can run these over non-interactive SSH without a TTY.
|
||||
#
|
||||
# Nix is included because single-user Nix installations (common on PVE
|
||||
# hosts bootstrapped via codex-setup.sh) are owned by root; non-root
|
||||
# users can't touch the Nix store lock without sudo.
|
||||
#
|
||||
# Idempotent - safe to re-run (rewrites if paths have changed). Run as
|
||||
# root on the PVE host.
|
||||
#
|
||||
# Usage: ./setup-admin-sudo.sh <username>
|
||||
set -euo pipefail
|
||||
|
||||
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||||
# shellcheck source=lib/common.sh
|
||||
source "${SCRIPT_DIR}/lib/common.sh"
|
||||
require_root
|
||||
|
||||
USERNAME="${1:-}"
|
||||
if [ -z "$USERNAME" ]; then
|
||||
echo "Usage: $0 <username>" >&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# Resolve actual binary paths at script time -- they differ across Proxmox
|
||||
# versions (pvesh moved from /usr/sbin to /usr/bin in PVE 8.x) and the
|
||||
# sudoers rule must match the real path or sudo will fall back to
|
||||
# prompting for a password.
|
||||
resolve_bin() {
|
||||
command -v "$1" 2>/dev/null || { echo "ERROR: $1 not found on PATH" >&2; exit 1; }
|
||||
}
|
||||
|
||||
PVESH="$(resolve_bin pvesh)"
|
||||
QM="$(resolve_bin qm)"
|
||||
PCT="$(resolve_bin pct)"
|
||||
# Nix installs to a fixed path regardless of which user bootstrapped it.
|
||||
NIX_BIN="/nix/var/nix/profiles/default/bin/nix"
|
||||
if [ ! -x "$NIX_BIN" ]; then
|
||||
echo "WARNING: $NIX_BIN not found -- Nix may not be installed yet." >&2
|
||||
echo " Re-run this script after running codex-setup.sh on the node." >&2
|
||||
NIX_BIN=""
|
||||
fi
|
||||
|
||||
SUDOERS_FILE="/etc/sudoers.d/${USERNAME}-proxmox"
|
||||
NIX_ENTRY="${NIX_BIN:+, ${NIX_BIN}}"
|
||||
CONTENT="${USERNAME} ALL=(root) NOPASSWD: ${PVESH}, ${QM}, ${PCT}${NIX_ENTRY}"
|
||||
|
||||
write_if_changed "$SUDOERS_FILE" "$CONTENT"
|
||||
|
||||
# visudo -c validates the file we just wrote before we walk away.
|
||||
if visudo -c -f "$SUDOERS_FILE" >/dev/null 2>&1; then
|
||||
chmod 0440 "$SUDOERS_FILE"
|
||||
echo "Sudoers rule for ${USERNAME} is valid and in place."
|
||||
echo " ${CONTENT}"
|
||||
else
|
||||
echo "ERROR: sudoers validation failed -- removing bad file." >&2
|
||||
rm -f "$SUDOERS_FILE"
|
||||
exit 1
|
||||
fi
|
||||
+82
@@ -0,0 +1,82 @@
|
||||
#!/bin/bash
|
||||
# Create a Linux system user for SSH access and sudo, and install their
|
||||
# authorized SSH public key. Run this before harden-ssh.sh so that
|
||||
# key-based access is in place before password authentication is disabled.
|
||||
#
|
||||
# Idempotent - safe to re-run. Run as root on the PVE host.
|
||||
#
|
||||
# Usage:
|
||||
# ./setup-linux-admin-user.sh <username> <ssh-public-key>
|
||||
# ./setup-linux-admin-user.sh <username> --key-file <path-to-.pub>
|
||||
set -euo pipefail
|
||||
|
||||
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||||
# shellcheck source=lib/common.sh
|
||||
source "${SCRIPT_DIR}/lib/common.sh"
|
||||
require_root
|
||||
|
||||
USERNAME="${1:-}"
|
||||
if [ -z "$USERNAME" ]; then
|
||||
echo "Usage: $0 <username> <ssh-public-key>" >&2
|
||||
echo " $0 <username> --key-file <path-to-.pub>" >&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
shift
|
||||
SSH_KEY=""
|
||||
if [ "${1:-}" = "--key-file" ]; then
|
||||
KEY_FILE="${2:-}"
|
||||
[ -z "$KEY_FILE" ] && { echo "ERROR: --key-file requires a path." >&2; exit 1; }
|
||||
[ -f "$KEY_FILE" ] || { echo "ERROR: key file not found: $KEY_FILE" >&2; exit 1; }
|
||||
SSH_KEY="$(cat "$KEY_FILE")"
|
||||
else
|
||||
SSH_KEY="${1:-}"
|
||||
fi
|
||||
|
||||
if [ -z "$SSH_KEY" ]; then
|
||||
echo "ERROR: an SSH public key is required (key string or --key-file <path>)." >&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
if ! echo "$SSH_KEY" | grep -qE '^(ssh-rsa|ssh-ed25519|ecdsa-sha2-nistp[0-9]+) [A-Za-z0-9+/=]'; then
|
||||
echo "ERROR: argument doesn't look like a valid SSH public key." >&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# --- create Linux user if missing ---
|
||||
if id "$USERNAME" >/dev/null 2>&1; then
|
||||
echo "User '${USERNAME}' already exists - skipping useradd."
|
||||
else
|
||||
useradd --create-home --shell /bin/bash "$USERNAME"
|
||||
echo "Created Linux user '${USERNAME}'."
|
||||
fi
|
||||
|
||||
# --- sudo group membership ---
|
||||
if id -nG "$USERNAME" | grep -qw sudo; then
|
||||
echo "User '${USERNAME}' is already in the sudo group."
|
||||
else
|
||||
usermod --append --groups sudo "$USERNAME"
|
||||
echo "Added '${USERNAME}' to the sudo group."
|
||||
fi
|
||||
|
||||
# --- install authorized SSH key ---
|
||||
HOME_DIR="$(getent passwd "$USERNAME" | cut -d: -f6)"
|
||||
SSH_DIR="${HOME_DIR}/.ssh"
|
||||
AUTH_FILE="${SSH_DIR}/authorized_keys"
|
||||
|
||||
mkdir -p "$SSH_DIR"
|
||||
chmod 700 "$SSH_DIR"
|
||||
touch "$AUTH_FILE"
|
||||
chmod 600 "$AUTH_FILE"
|
||||
chown -R "${USERNAME}:${USERNAME}" "$SSH_DIR"
|
||||
|
||||
if grep -qF "$SSH_KEY" "$AUTH_FILE" 2>/dev/null; then
|
||||
echo "SSH key is already present in ${AUTH_FILE}."
|
||||
else
|
||||
echo "$SSH_KEY" >> "$AUTH_FILE"
|
||||
echo "Installed SSH key in ${AUTH_FILE}."
|
||||
fi
|
||||
|
||||
echo
|
||||
echo "Linux user '${USERNAME}' is ready for SSH key-based login with sudo access."
|
||||
echo "Next: run setup-admin-sudo.sh ${USERNAME} to grant NOPASSWD for pvesh/qm/pct."
|
||||
+46
@@ -0,0 +1,46 @@
|
||||
#!/bin/bash
|
||||
# Install and configure unattended-upgrades for security patches. Deliberately
|
||||
# conservative for a hypervisor: security-only origins (Debian security +
|
||||
# the active PVE repo), no automatic reboot ever - a flag file is left at
|
||||
# /var/run/reboot-required for you to act on manually.
|
||||
#
|
||||
# Idempotent - safe to re-run. Run as root on the PVE host.
|
||||
set -euo pipefail
|
||||
|
||||
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||||
# shellcheck source=lib/common.sh
|
||||
source "${SCRIPT_DIR}/lib/common.sh"
|
||||
require_root
|
||||
|
||||
if ! dpkg -s unattended-upgrades >/dev/null 2>&1; then
|
||||
apt-get update
|
||||
apt-get install -y unattended-upgrades
|
||||
fi
|
||||
|
||||
CODENAME="$(pve_codename)"
|
||||
|
||||
write_if_changed "/etc/apt/apt.conf.d/51pve-unattended-upgrades.conf" "// Managed by proxmox-configuration/scripts/setup-unattended-upgrades.sh
|
||||
Unattended-Upgrade::Origins-Pattern {
|
||||
\"origin=Debian,codename=${CODENAME},label=Debian-Security\";
|
||||
\"origin=Debian,codename=${CODENAME}-security,label=Debian-Security\";
|
||||
\"origin=Proxmox\";
|
||||
};
|
||||
|
||||
// Never auto-reboot a hypervisor. Check /var/run/reboot-required manually
|
||||
// (or via scripts/audit.sh) and reboot during a planned maintenance window.
|
||||
Unattended-Upgrade::Automatic-Reboot \"false\";
|
||||
|
||||
// Don't remove packages automatically; review before doing so by hand.
|
||||
Unattended-Upgrade::Remove-Unused-Dependencies \"false\";
|
||||
Unattended-Upgrade::Remove-Unused-Kernel-Packages \"false\";"
|
||||
|
||||
write_if_changed "/etc/apt/apt.conf.d/20auto-upgrades" '// Managed by proxmox-configuration/scripts/setup-unattended-upgrades.sh
|
||||
APT::Periodic::Update-Package-Lists "1";
|
||||
APT::Periodic::Unattended-Upgrade "1";
|
||||
APT::Periodic::Download-Upgradeable-Packages "1";
|
||||
APT::Periodic::AutocleanInterval "7";'
|
||||
|
||||
systemctl enable --now unattended-upgrades.service >/dev/null
|
||||
echo "unattended-upgrades enabled (security-only origins, no auto-reboot)."
|
||||
echo "Dry run:"
|
||||
unattended-upgrade --dry-run --debug 2>&1 | tail -20
|
||||
+133
@@ -0,0 +1,133 @@
|
||||
#!/bin/bash
|
||||
# Reproduces pve-test's wifi-primary networking: vmbr0 bridged over a wifi
|
||||
# NIC in 4addr (WDS) client-bridge mode, active-backup bonded with a wired
|
||||
# NIC as an automatic LAN fallback. See docs/06-pve-test-wifi-network.md for
|
||||
# why this exists and how it was validated. Idempotent - safe to re-run.
|
||||
#
|
||||
# Requires: a wifi NIC whose driver/AP both support 4addr mode (verify with
|
||||
# docs/06-pve-test-wifi-network.md's isolated-namespace test *before*
|
||||
# trusting this against a live management IP - a wifi NIC or AP that
|
||||
# doesn't support 4addr will associate fine but silently drop bridged
|
||||
# frames from any MAC other than the card's own).
|
||||
#
|
||||
# Usage (run as root on the target PVE host):
|
||||
# WIFI_SSID="..." WIFI_PASSPHRASE="..." \
|
||||
# MGMT_ADDR=192.168.2.251/24 MGMT_GATEWAY=192.168.2.254 \
|
||||
# ./setup-wifi-bond-network.sh
|
||||
#
|
||||
# Optional overrides: WIFI_IFACE (default wlp3s0), LAN_IFACE (default nic0)
|
||||
set -euo pipefail
|
||||
|
||||
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||||
# shellcheck source=lib/common.sh
|
||||
source "${SCRIPT_DIR}/lib/common.sh"
|
||||
require_root
|
||||
|
||||
WIFI_IFACE="${WIFI_IFACE:-wlp3s0}"
|
||||
LAN_IFACE="${LAN_IFACE:-nic0}"
|
||||
|
||||
for var in WIFI_SSID WIFI_PASSPHRASE MGMT_ADDR MGMT_GATEWAY; do
|
||||
if [ -z "${!var:-}" ]; then
|
||||
echo "$var is not set. See usage in this script's header." >&2
|
||||
exit 1
|
||||
fi
|
||||
done
|
||||
|
||||
if ! ip link show "$WIFI_IFACE" >/dev/null 2>&1; then
|
||||
echo "No interface named $WIFI_IFACE on this host. Run 'ip -br link' and set WIFI_IFACE=..." >&2
|
||||
exit 1
|
||||
fi
|
||||
if ! ip link show "$LAN_IFACE" >/dev/null 2>&1; then
|
||||
echo "No interface named $LAN_IFACE on this host. Run 'ip -br link' and set LAN_IFACE=..." >&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
echo "=== 1/4: wifi tooling ==="
|
||||
apt-get install -y iw wpasupplicant >/dev/null
|
||||
echo "installed iw, wpasupplicant"
|
||||
|
||||
echo
|
||||
echo "=== 2/4: wpa_supplicant config (SSID: $WIFI_SSID, iface: $WIFI_IFACE) ==="
|
||||
WPA_CONF="/etc/wpa_supplicant/wpa_supplicant-${WIFI_IFACE}.conf"
|
||||
wpa_passphrase "$WIFI_SSID" "$WIFI_PASSPHRASE" > "$WPA_CONF"
|
||||
sed -i '/^\s*#psk=/d' "$WPA_CONF"
|
||||
chmod 600 "$WPA_CONF"
|
||||
echo "wrote $WPA_CONF (passphrase hashed, not stored in plaintext)"
|
||||
|
||||
echo
|
||||
echo "=== 3/4: systemd unit to set 4addr mode + start wpa_supplicant ==="
|
||||
UNIT="/etc/systemd/system/wpa-4addr-${WIFI_IFACE}.service"
|
||||
write_if_changed "$UNIT" "[Unit]
|
||||
Description=wpa_supplicant on ${WIFI_IFACE} with 4addr mode enabled
|
||||
Before=network-pre.target
|
||||
Wants=network-pre.target
|
||||
|
||||
[Service]
|
||||
Type=simple
|
||||
ExecStartPre=/sbin/ip link set ${WIFI_IFACE} down
|
||||
ExecStartPre=/sbin/iw dev ${WIFI_IFACE} set 4addr on
|
||||
ExecStartPre=/sbin/ip link set ${WIFI_IFACE} up
|
||||
ExecStart=/sbin/wpa_supplicant -i ${WIFI_IFACE} -c ${WPA_CONF}
|
||||
Restart=on-failure
|
||||
RestartSec=3
|
||||
|
||||
[Install]
|
||||
WantedBy=multi-user.target"
|
||||
systemctl daemon-reload
|
||||
systemctl enable --now "wpa-4addr-${WIFI_IFACE}.service"
|
||||
sleep 5
|
||||
if ! iw dev "$WIFI_IFACE" link | grep -q "^Connected"; then
|
||||
echo "WARNING: ${WIFI_IFACE} did not associate to '$WIFI_SSID' within 5s - check:" >&2
|
||||
echo " systemctl status wpa-4addr-${WIFI_IFACE}.service" >&2
|
||||
echo " journalctl -u wpa-4addr-${WIFI_IFACE}.service" >&2
|
||||
exit 1
|
||||
fi
|
||||
echo "associated: $(iw dev "$WIFI_IFACE" link | grep '^Connected')"
|
||||
|
||||
echo
|
||||
echo "=== 4/4: /etc/network/interfaces (bond0 active-backup: ${WIFI_IFACE} primary, ${LAN_IFACE} backup) ==="
|
||||
IFACES_FILE="/etc/network/interfaces"
|
||||
backup_file "$IFACES_FILE"
|
||||
cat > "$IFACES_FILE" <<EOF
|
||||
auto lo
|
||||
iface lo inet loopback
|
||||
|
||||
iface ${LAN_IFACE} inet manual
|
||||
|
||||
iface ${WIFI_IFACE} inet manual
|
||||
|
||||
auto bond0
|
||||
iface bond0 inet manual
|
||||
bond-slaves ${WIFI_IFACE} ${LAN_IFACE}
|
||||
bond-mode active-backup
|
||||
bond-miimon 100
|
||||
bond-primary ${WIFI_IFACE}
|
||||
bond-updelay 200
|
||||
bond-downdelay 200
|
||||
|
||||
auto vmbr0
|
||||
iface vmbr0 inet static
|
||||
address ${MGMT_ADDR}
|
||||
gateway ${MGMT_GATEWAY}
|
||||
bridge-ports bond0
|
||||
bridge-stp off
|
||||
bridge-fd 0
|
||||
|
||||
source /etc/network/interfaces.d/*
|
||||
EOF
|
||||
echo "wrote $IFACES_FILE"
|
||||
|
||||
echo
|
||||
echo "Config staged but NOT applied yet - applying it live can drop your"
|
||||
echo "current management connection for ~30-60s while the switch/AP"
|
||||
echo "relearns MAC locations (expected, self-resolves; see"
|
||||
echo "docs/06-pve-test-wifi-network.md). Recommended: run this from the"
|
||||
echo "physical console, or arm a revert-on-timeout watchdog first, e.g.:"
|
||||
echo
|
||||
echo " cp ${IFACES_FILE}.bak.* /tmp/interfaces.orig # pick the backup just made"
|
||||
echo " (sleep 45 && cp /tmp/interfaces.orig ${IFACES_FILE} && ifreload -a) &"
|
||||
echo " ifreload -a"
|
||||
echo " # then kill the backgrounded revert job once you confirm connectivity"
|
||||
echo
|
||||
echo "Apply now with: ifreload -a"
|
||||
echo "Verify after with: cat /proc/net/bonding/bond0 ; ip -4 -br addr show vmbr0"
|
||||
+42
@@ -0,0 +1,42 @@
|
||||
#!/bin/bash
|
||||
# Remove the Proxmox/Ceph enterprise apt sources (which fail on apt update
|
||||
# without a paid subscription) and switch to the no-subscription repo.
|
||||
# Handles both the legacy one-line .list format and the deb822 .sources
|
||||
# format current PVE installers write.
|
||||
# Idempotent - safe to re-run. Run as root on the PVE host.
|
||||
set -euo pipefail
|
||||
|
||||
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||||
# shellcheck source=lib/common.sh
|
||||
source "${SCRIPT_DIR}/lib/common.sh"
|
||||
require_root
|
||||
|
||||
SOURCES_DIR="/etc/apt/sources.list.d"
|
||||
|
||||
# Any sources file pointing at the enterprise host gets moved out of apt's
|
||||
# way entirely (renamed .disabled) rather than commented out in place -
|
||||
# apt only reads *.sources/*.list, so this fully removes it from
|
||||
# consideration while keeping a copy on disk for reference.
|
||||
for f in "${SOURCES_DIR}"/*.sources "${SOURCES_DIR}"/*.list; do
|
||||
[ -f "$f" ] || continue
|
||||
grep -qi 'enterprise.proxmox.com' "$f" 2>/dev/null || continue
|
||||
mv "$f" "${f}.disabled"
|
||||
echo "Removed enterprise source (renamed to .disabled): $f"
|
||||
done
|
||||
|
||||
write_if_changed "${SOURCES_DIR}/pve-no-subscription.sources" "Types: deb
|
||||
URIs: http://download.proxmox.com/debian/pve
|
||||
Suites: $(pve_codename)
|
||||
Components: pve-no-subscription
|
||||
Signed-By: /usr/share/keyrings/proxmox-archive-keyring.gpg"
|
||||
|
||||
# Clean up a legacy-format no-subscription file from a previous run of an
|
||||
# older version of this script, to avoid two sources for the same repo.
|
||||
LEGACY_NOSUB="${SOURCES_DIR}/pve-no-subscription.list"
|
||||
if [ -f "$LEGACY_NOSUB" ]; then
|
||||
rm -f "$LEGACY_NOSUB"
|
||||
echo "Removed superseded $LEGACY_NOSUB"
|
||||
fi
|
||||
|
||||
apt-get update
|
||||
echo "Repo switched. Review 'apt list --upgradable' before upgrading."
|
||||
@@ -0,0 +1,80 @@
|
||||
#!/usr/bin/env bash
|
||||
# Scan the repo for secrets and sensitive config values.
|
||||
# Runs via CI (GitHub/Gitea Actions) and locally as a pre-commit check.
|
||||
#
|
||||
# Usage: scripts/check-secrets.sh [--staged-only]
|
||||
# --staged-only Only check files staged for commit (for pre-commit hook use)
|
||||
#
|
||||
# Requires gitleaks on PATH, or falls back to Docker if available.
|
||||
# Install gitleaks: https://github.com/gitleaks/gitleaks#installing
|
||||
|
||||
set -euo pipefail
|
||||
|
||||
REPO_ROOT="$(git -C "$(dirname "$0")" rev-parse --show-toplevel)"
|
||||
STAGED_ONLY=false
|
||||
FAILURES=0
|
||||
|
||||
for arg in "$@"; do
|
||||
[[ "$arg" == "--staged-only" ]] && STAGED_ONLY=true
|
||||
done
|
||||
|
||||
cd "$REPO_ROOT"
|
||||
|
||||
# ── Resolve gitleaks binary ────────────────────────────────────────────────────
|
||||
if command -v gitleaks &>/dev/null; then
|
||||
GITLEAKS="gitleaks"
|
||||
elif command -v docker &>/dev/null; then
|
||||
GITLEAKS="docker run --rm -v ${REPO_ROOT}:/repo zricethezav/gitleaks:latest"
|
||||
# Adjust paths for docker context
|
||||
REPO_ROOT="/repo"
|
||||
else
|
||||
echo "ERROR: gitleaks not found. Install it or ensure Docker is available." >&2
|
||||
echo " https://github.com/gitleaks/gitleaks#installing" >&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
echo "=== Secret scan ==="
|
||||
|
||||
if [[ "$STAGED_ONLY" == "true" ]]; then
|
||||
# Pre-commit mode: scan only staged content
|
||||
echo "Mode: staged files only"
|
||||
if ! $GITLEAKS protect --staged --config="${REPO_ROOT}/.gitleaks.toml" --source="${REPO_ROOT}" 2>&1; then
|
||||
FAILURES=$((FAILURES + 1))
|
||||
fi
|
||||
else
|
||||
# CI mode: scan full git history
|
||||
echo "Mode: full git history"
|
||||
if ! $GITLEAKS detect --config="${REPO_ROOT}/.gitleaks.toml" --source="${REPO_ROOT}" 2>&1; then
|
||||
FAILURES=$((FAILURES + 1))
|
||||
fi
|
||||
fi
|
||||
|
||||
# ── Pi-hole specific checks ────────────────────────────────────────────────────
|
||||
echo ""
|
||||
echo "=== Pi-hole config checks ==="
|
||||
|
||||
PIHOLE_TOML="${REPO_ROOT}/pihole/config/pihole.toml"
|
||||
|
||||
if [[ -f "$PIHOLE_TOML" ]]; then
|
||||
# Check that known sensitive fields are empty
|
||||
for field in pwhash totp_secret app_pwhash; do
|
||||
value=$(grep -E "^\s+${field}\s*=" "$PIHOLE_TOML" | sed 's/.*=\s*"\(.*\)".*/\1/' | tr -d '[:space:]' || true)
|
||||
if [[ -n "$value" && "$value" != '""' ]]; then
|
||||
echo "FAIL: pihole.toml contains a non-empty '${field}' — run pihole/sanitize-config.sh before committing" >&2
|
||||
FAILURES=$((FAILURES + 1))
|
||||
else
|
||||
echo " OK: ${field} is empty"
|
||||
fi
|
||||
done
|
||||
else
|
||||
echo " (pihole/config/pihole.toml not present, skipping Pi-hole checks)"
|
||||
fi
|
||||
|
||||
# ── Summary ────────────────────────────────────────────────────────────────────
|
||||
echo ""
|
||||
if [[ $FAILURES -gt 0 ]]; then
|
||||
echo "FAILED: ${FAILURES} issue(s) found. Fix before committing." >&2
|
||||
exit 1
|
||||
else
|
||||
echo "All checks passed."
|
||||
fi
|
||||
@@ -0,0 +1,17 @@
|
||||
#!/usr/bin/env bash
|
||||
# Install git hooks that run the secret scan before every commit.
|
||||
# Run once after cloning: bash scripts/install-hooks.sh
|
||||
|
||||
set -euo pipefail
|
||||
|
||||
REPO_ROOT="$(git -C "$(dirname "$0")" rev-parse --show-toplevel)"
|
||||
HOOK="${REPO_ROOT}/.git/hooks/pre-commit"
|
||||
|
||||
cat > "$HOOK" << 'HOOK'
|
||||
#!/usr/bin/env bash
|
||||
exec "$(git rev-parse --show-toplevel)/scripts/check-secrets.sh" --staged-only
|
||||
HOOK
|
||||
|
||||
chmod +x "$HOOK"
|
||||
echo "Installed pre-commit hook → ${HOOK}"
|
||||
echo "The secret scan will run automatically before every commit."
|
||||
Reference in New Issue
Block a user