Container security hardening (phase 2) (#24068)

* Create frigate and go2rtc runtime users in the image

* Add single fix-ownership helper for volume permission migration

* Add init-usermod oneshot for PUID and PGID remapping

* Chown newly created runtime directories to the frigate user

* Run sentinel-guarded ownership sweep during prepare

* Add host-side volume permission migration script

* Guard log directory ownership for user-mode startup

* Fall back to plain s6-log when running without root

* Assert PUID remapping and sweep sentinel in CI smoke test

* Skip the ownership sweep in the devcontainer

* Pin FRIGATE_RUN_AS_ROOT in ownership tests

* Do not record the sweep as complete when a chown failed

* Validate PUID and PGID in the migration script

* Treat a failed ownership scan as an incomplete sweep

* Reject PUID and PGID of 0 during remapping

* Handle symlinks, dry runs, and sentinel write failures in the sweep

* Treat an absent sweep root as an incomplete sweep

docker/main/Dockerfile

@@ -265,6 +265,23 @@ ENV PATH="/usr/local/go2rtc/bin:/usr/local/tempio/bin:/usr/local/nginx/sbin:${PA
 RUN --mount=type=bind,source=docker/main/install_deps.sh,target=/deps/install_deps.sh \
     /deps/install_deps.sh
 
+# Runtime users. frigate may be remapped at start via PUID/PGID (init-usermod)
+# or replaced entirely with docker's --user. go2rtc is intentionally separate
+# and more restricted. frigate-data is the shared group for /config access.
+# -o tolerates variant base images that already contain uid/gid 1000.
+RUN groupadd -o --gid 1000 frigate \
+    && useradd -o --uid 1000 --gid frigate --no-create-home --shell /usr/sbin/nologin frigate \
+    && groupadd --system go2rtc \
+    && useradd --system --gid go2rtc --no-create-home --shell /usr/sbin/nologin go2rtc \
+    && groupadd --system frigate-data \
+    && usermod -aG frigate-data frigate \
+    && usermod -aG frigate-data go2rtc \
+    && for grp in video render plugdev audio; do \
+         if getent group "$grp" >/dev/null; then \
+           usermod -aG "$grp" frigate && usermod -aG "$grp" go2rtc; \
+         fi; \
+       done
+
 ENV DEFAULT_FFMPEG_VERSION="8.0"
 ENV INCLUDED_FFMPEG_VERSIONS="${DEFAULT_FFMPEG_VERSION}:7.0:5.0"
 
@@ -307,6 +324,11 @@ HEALTHCHECK --start-period=300s --start-interval=5s --interval=15s --timeout=5s
 # Frigate deps with Node.js and NPM for devcontainer
 FROM deps AS devcontainer
 
+# /config here is the developer's bind-mounted checkout, not a data volume, so
+# the prepare ownership sweep must not run: it would chown the source tree to
+# the runtime uid and lock out any container user that isn't 1000.
+ENV FRIGATE_RUN_AS_ROOT=true
+
 # Do not start the actual Frigate service on devcontainer as it will be started by VS Code
 # But start a fake service for simulating the logs
 COPY docker/main/fake_frigate_run /etc/s6-overlay/s6-rc.d/frigate/run

docker/main/rootfs/etc/s6-overlay/s6-rc.d/certsync-log/run

@@ -1,4 +1,12 @@
 #!/command/with-contenv bash
 # shellcheck shell=bash
 
-exec logutil-service /dev/shm/logs/certsync
+if [[ "$(id -u)" -eq 0 ]]; then
+    # logutil-service drops to nobody and applies S6_LOGGING_SCRIPT
+    exec logutil-service /dev/shm/logs/certsync
+fi
+
+# Non-root (--user) fallback: logutil-service cannot change UID, so run
+# s6-log directly with the same directives S6_LOGGING_SCRIPT configures.
+# shellcheck disable=SC2086
+exec s6-log ${S6_LOGGING_SCRIPT:-T 1 n0 s10000000 T} /dev/shm/logs/certsync

docker/main/rootfs/etc/s6-overlay/s6-rc.d/frigate-log/run

@@ -1,4 +1,12 @@
 #!/command/with-contenv bash
 # shellcheck shell=bash
 
-exec logutil-service /dev/shm/logs/frigate
+if [[ "$(id -u)" -eq 0 ]]; then
+    # logutil-service drops to nobody and applies S6_LOGGING_SCRIPT
+    exec logutil-service /dev/shm/logs/frigate
+fi
+
+# Non-root (--user) fallback: logutil-service cannot change UID, so run
+# s6-log directly with the same directives S6_LOGGING_SCRIPT configures.
+# shellcheck disable=SC2086
+exec s6-log ${S6_LOGGING_SCRIPT:-T 1 n0 s10000000 T} /dev/shm/logs/frigate

docker/main/rootfs/etc/s6-overlay/s6-rc.d/go2rtc-log/run

@@ -1,4 +1,12 @@
 #!/command/with-contenv bash
 # shellcheck shell=bash
 
-exec logutil-service /dev/shm/logs/go2rtc
+if [[ "$(id -u)" -eq 0 ]]; then
+    # logutil-service drops to nobody and applies S6_LOGGING_SCRIPT
+    exec logutil-service /dev/shm/logs/go2rtc
+fi
+
+# Non-root (--user) fallback: logutil-service cannot change UID, so run
+# s6-log directly with the same directives S6_LOGGING_SCRIPT configures.
+# shellcheck disable=SC2086
+exec s6-log ${S6_LOGGING_SCRIPT:-T 1 n0 s10000000 T} /dev/shm/logs/go2rtc

docker/main/rootfs/etc/s6-overlay/s6-rc.d/init-usermod/run

@@ -0,0 +1,61 @@
+#!/command/with-contenv bash
+# shellcheck shell=bash
+# Remap the frigate user to PUID/PGID and register EXTRA_GROUPS.
+# No-op when: started with --user (euid != 0), FRIGATE_RUN_AS_ROOT=true,
+# or PUID/PGID already match.
+
+set -o errexit -o nounset -o pipefail
+
+if [[ "$(id -u)" -ne 0 ]]; then
+    # Started with docker --user; the host owns UID mapping entirely.
+    exit 0
+fi
+
+if [[ "${FRIGATE_RUN_AS_ROOT:-false}" == "true" ]]; then
+    echo "[INFO] FRIGATE_RUN_AS_ROOT=true: skipping user remapping"
+    exit 0
+fi
+
+puid="${PUID:-1000}"
+pgid="${PGID:-1000}"
+
+if ! [[ "$puid" =~ ^[0-9]+$ && "$pgid" =~ ^[0-9]+$ ]]; then
+    echo "[ERROR] PUID and PGID must be numeric, got '${puid}' and '${pgid}'" >&2
+    exit 1
+fi
+
+# Remapping to 0 would make the frigate user root, so every service would keep
+# full privilege while reporting a successful migration.
+if [[ "$puid" -eq 0 || "$pgid" -eq 0 ]]; then
+    echo "[ERROR] PUID/PGID 0 would run the services as root and defeat the privilege separation." >&2
+    echo "[ERROR] Set FRIGATE_RUN_AS_ROOT=true if you want to keep running as root." >&2
+    exit 1
+fi
+
+current_uid="$(id -u frigate)"
+current_gid="$(id -g frigate)"
+
+if [[ "$puid" != "$current_uid" || "$pgid" != "$current_gid" ]]; then
+    if [[ ! -w /etc/passwd ]]; then
+        echo "[ERROR] PUID/PGID remapping needs a writable /etc and is not compatible with read_only: true." >&2
+        echo "[ERROR] Either remove read_only and keep PUID, or drop PUID/PGID and use docker's user: ${puid}:${pgid} instead." >&2
+        echo "[ERROR] See https://docs.frigate.video/configuration/non_root for the compatibility matrix." >&2
+        exit 1
+    fi
+    echo "[INFO] Remapping frigate user to ${puid}:${pgid}"
+    groupmod -o -g "$pgid" frigate
+    usermod -o -u "$puid" frigate
+fi
+
+# EXTRA_GROUPS: numeric host GIDs granting device access (e.g. host render/video)
+if [[ -n "${EXTRA_GROUPS:-}" ]]; then
+    for gid in ${EXTRA_GROUPS//,/ }; do
+        if ! getent group "$gid" >/dev/null; then
+            groupadd -o -g "$gid" "frigate-extra-${gid}"
+        fi
+        group_name="$(getent group "$gid" | cut -d: -f1)"
+        usermod -aG "$group_name" frigate
+        usermod -aG "$group_name" go2rtc
+        echo "[INFO] Added frigate and go2rtc to supplementary group ${group_name} (gid ${gid})"
+    done
+fi

docker/main/rootfs/etc/s6-overlay/s6-rc.d/init-usermod/type

@@ -0,0 +1 @@
+oneshot

docker/main/rootfs/etc/s6-overlay/s6-rc.d/init-usermod/up

@@ -0,0 +1 @@
+/etc/s6-overlay/s6-rc.d/init-usermod/run

docker/main/rootfs/etc/s6-overlay/s6-rc.d/log-prepare/run

@@ -7,5 +7,12 @@ set -o errexit -o nounset -o pipefail
 dirs=(/dev/shm/logs/frigate /dev/shm/logs/go2rtc /dev/shm/logs/nginx /dev/shm/logs/certsync)
 
 mkdir -p "${dirs[@]}"
-chown nobody:nogroup "${dirs[@]}"
+
+# logutil-service drops s6-log to nobody, so the dirs must stay nobody-owned
+# in root mode. Under docker --user we are already the (only) target user,
+# chown would fail, and the plain s6-log fallback in the *-log services
+# writes as us (the mkdir above is sufficient, /dev/shm is 1777).
+if [[ "$(id -u)" -eq 0 ]]; then
+    chown nobody:nogroup "${dirs[@]}"
+fi
 chmod 02755 "${dirs[@]}"

docker/main/rootfs/etc/s6-overlay/s6-rc.d/nginx-log/run

@@ -1,4 +1,12 @@
 #!/command/with-contenv bash
 # shellcheck shell=bash
 
-exec logutil-service /dev/shm/logs/nginx
+if [[ "$(id -u)" -eq 0 ]]; then
+    # logutil-service drops to nobody and applies S6_LOGGING_SCRIPT
+    exec logutil-service /dev/shm/logs/nginx
+fi
+
+# Non-root (--user) fallback: logutil-service cannot change UID, so run
+# s6-log directly with the same directives S6_LOGGING_SCRIPT configures.
+# shellcheck disable=SC2086
+exec s6-log ${S6_LOGGING_SCRIPT:-T 1 n0 s10000000 T} /dev/shm/logs/nginx

docker/main/rootfs/etc/s6-overlay/s6-rc.d/prepare/run

@@ -144,3 +144,16 @@ rm -f /dev/shm/.frigate-is-stopping
 
 migrate_addon_config_dir
 migrate_db_from_media_to_config
+
+# Align volume ownership with the runtime user (one sweep per PUID/schema
+# change, guarded by the sentinel; see fix-ownership). The escape hatch
+# deletes the sentinel instead: ownership is never mutated while it is on,
+# so the next non-root boot must re-sweep whatever root created meanwhile.
+if [[ "$(id -u)" -eq 0 ]]; then
+    if [[ "${FRIGATE_RUN_AS_ROOT:-false}" == "true" ]]; then
+        rm -f /config/.permissions_version
+    else
+        /usr/local/bin/fix-ownership --sentinel /config/.permissions_version \
+            "${PUID:-1000}" "${PGID:-1000}" /config /media/frigate
+    fi
+fi

docker/main/rootfs/usr/local/bin/fix-ownership

@@ -0,0 +1,129 @@
+#!/bin/bash
+# Single source of truth for aligning volume ownership with the runtime user.
+#
+# Usage: fix-ownership [--dry-run] [--sentinel FILE] UID GID PATH [PATH...]
+#
+#   --dry-run    report what would change, touch nothing
+#   --sentinel   skip entirely when FILE already records "SCHEMA:UID:GID";
+#                write it after a successful run (used by the boot path so
+#                multi-TB volumes are swept once per UID/schema change, not
+#                on every boot)
+#
+# Only files whose uid OR gid differs are touched, so re-runs are cheap.
+# Top-level /config additionally grants group frigate-data TRAVERSE ONLY
+# (g+rx) so the separate go2rtc user can reach its pre-created HomeKit file
+# on hosts where /config is mounted 0700. Never g+w: directory write means
+# unlink rights over frigate.db/config.yml, and would let a compromised
+# go2rtc plant /config/go2rtc, which the go2rtc run script executes
+# preferentially, as root under the escape hatch.
+
+set -o errexit -o nounset -o pipefail
+
+# Permissions-layout epoch. Bump to force a one-time re-sweep on upgrade
+# (e.g. when the privilege-drop release must capture files created as root
+# since the previous sweep).
+schema=1
+
+dry_run=0
+sentinel=""
+
+while [[ "${1:-}" == --* ]]; do
+    case "$1" in
+        --dry-run) dry_run=1; shift ;;
+        --sentinel)
+            if [[ -z "${2:-}" ]]; then
+                echo "[ERROR] fix-ownership: --sentinel requires a file argument" >&2
+                exit 2
+            fi
+            sentinel="$2"; shift 2 ;;
+        *) echo "[ERROR] fix-ownership: unknown option $1" >&2; exit 2 ;;
+    esac
+done
+
+if [[ $# -lt 3 ]]; then
+    echo "Usage: fix-ownership [--dry-run] [--sentinel FILE] UID GID PATH..." >&2
+    exit 2
+fi
+
+target_uid="$1"
+target_gid="$2"
+shift 2
+
+if [[ "$(id -u)" -ne 0 ]]; then
+    echo "[INFO] fix-ownership: not running as root, skipping (ownership is managed by the host in --user mode)"
+    exit 0
+fi
+
+# A dry run always inspects: the sentinel records what a past sweep did, not
+# what the volume looks like now, and reporting from it would hide later drift.
+if [[ "$dry_run" -eq 0 && -n "$sentinel" && -f "$sentinel" && "$(cat "$sentinel")" == "${schema}:${target_uid}:${target_gid}" ]]; then
+    echo "[INFO] fix-ownership: ${target_uid}:${target_gid} (schema ${schema}) already applied, skipping"
+    exit 0
+fi
+
+# A sweep that could not chown everything must not be recorded as complete:
+# the sentinel would make every later boot skip it and the entries would stay
+# unreachable once services run unprivileged.
+swept_clean=1
+
+for path in "$@"; do
+    # An absent root is an incomplete sweep, not a finished one: /media/frigate
+    # is not in the image, so a boot before the volume is mounted would
+    # otherwise record success and the volume would never be swept once added.
+    if [[ ! -d "$path" ]]; then
+        swept_clean=0
+        echo "[WARN] fix-ownership: $path does not exist, skipping; will retry on next boot"
+        continue
+    fi
+
+    # find may fail mid-walk on a live volume (file deleted under it) or on a
+    # stale mount. Tolerate it rather than aborting under errexit, but never
+    # read a failed scan as "nothing to do": that would record the sweep as
+    # complete without having looked.
+    if ! count=$(find "$path" \( -not -uid "$target_uid" -o -not -gid "$target_gid" \) -printf '.' 2>/dev/null | wc -c); then
+        swept_clean=0
+        echo "[WARN] fix-ownership: could not scan ${path}; will retry on next boot"
+        continue
+    fi
+
+    if [[ "$count" -eq 0 ]]; then
+        echo "[INFO] fix-ownership: $path already owned by ${target_uid}:${target_gid}, nothing to do"
+        continue
+    fi
+
+    # find does not descend symlinks and chown -h retargets the link itself, so
+    # anything behind a symlinked directory is outside this sweep. Following
+    # them is not an option: a link could walk the chown out of the volume.
+    if [[ -n "$(find "$path" -type l -xtype d -print -quit 2>/dev/null)" ]]; then
+        echo "[WARN] fix-ownership: ${path} contains symlinked directories; ownership behind them is not managed and must be aligned by hand"
+    fi
+
+    echo "[WARN] fix-ownership: adjusting ownership of ${count} entries under ${path}; on large recordings volumes this can take a long time"
+    if [[ "$dry_run" -eq 1 ]]; then
+        echo "[INFO] fix-ownership: dry run, not changing ${path}"
+        continue
+    fi
+
+    find "$path" \( -not -uid "$target_uid" -o -not -gid "$target_gid" \) \
+        -exec chown -h "${target_uid}:${target_gid}" {} + || {
+        swept_clean=0
+        echo "[WARN] fix-ownership: some entries under ${path} could not be updated (deleted mid-sweep or chown denied); will retry on next mismatch"
+    }
+done
+
+# go2rtc (separate user) must be able to REACH its HomeKit state in /config.
+# Write access is per-file, not per-directory: go2rtc's PatchConfig rewrites
+# the first -config file via os.WriteFile (in-place truncate, no rename,
+# verified against go2rtc v1.9.14 internal/app/config.go), and the file is
+# always pre-created by setup_homekit_config before go2rtc starts, so
+# O_CREATE never needs directory write. See header comment for why g+w is
+# forbidden here.
+if [[ "$dry_run" -eq 0 && -d /config ]]; then
+    chgrp frigate-data /config 2>/dev/null || true
+    chmod g+rx /config 2>/dev/null || true
+fi
+
+if [[ "$dry_run" -eq 0 && -n "$sentinel" && "$swept_clean" -eq 1 ]]; then
+    echo "${schema}:${target_uid}:${target_gid}" > "$sentinel" || \
+        echo "[WARN] fix-ownership: could not write ${sentinel}; the sweep will run again on next boot"
+fi

docker/migration/fix-permissions.sh

@@ -0,0 +1,45 @@
+#!/bin/bash
+# Ahead-of-time volume ownership migration for switching Frigate to non-root.
+# Run from the host BEFORE enabling PUID/PGID or --user:
+#
+#   ./fix-permissions.sh [--dry-run] <config_dir> <media_dir> [PUID] [PGID]
+#
+# Wraps the image's fix-ownership helper so there is exactly one
+# implementation of the chown logic. Requires an image that contains the
+# helper (any release that includes non-root support).
+
+set -o errexit -o nounset -o pipefail
+
+IMAGE="${FRIGATE_IMAGE:-ghcr.io/blakeblackshear/frigate:stable}"
+
+dry_run_flag=""
+if [[ "${1:-}" == "--dry-run" ]]; then
+    dry_run_flag="--dry-run"
+    shift
+fi
+
+if [[ $# -lt 2 ]]; then
+    echo "Usage: $0 [--dry-run] <config_dir> <media_dir> [PUID] [PGID]" >&2
+    exit 2
+fi
+
+config_dir="$1"
+media_dir="$2"
+puid="${3:-1000}"
+pgid="${4:-1000}"
+
+# The ids are interpolated into the container's bash -c source below, so
+# anything but digits would be reparsed as shell rather than passed through
+if ! [[ "$puid" =~ ^[0-9]+$ && "$pgid" =~ ^[0-9]+$ ]]; then
+    echo "[ERROR] PUID and PGID must be numeric, got '${puid}' and '${pgid}'" >&2
+    exit 2
+fi
+
+echo "[INFO] Using image ${IMAGE} (override with FRIGATE_IMAGE=...)"
+# shellcheck disable=SC2086
+docker run --rm \
+    -v "${config_dir}:/config" \
+    -v "${media_dir}:/media/frigate" \
+    --entrypoint bash \
+    "${IMAGE}" \
+    -c "command -v fix-ownership >/dev/null || { echo '[ERROR] this Frigate image predates non-root support; set FRIGATE_IMAGE to a release that includes it' >&2; exit 1; }; exec fix-ownership ${dry_run_flag} ${puid} ${pgid} /config /media/frigate"