# SPDX-License-Identifier: GPL-2.0
#
# Copyright (C) 2023-2024 Oracle.  All Rights Reserved.
# Author: Darrick J. Wong <djwong@kernel.org>

[Unit]
Description=Online bcachefsck for All Filesystems
OnFailure=bcachefsck_all_fail.service
ConditionACPower=true
Documentation=man:bcachefsck_all(8)
After=paths.target multi-user.target network.target network-online.target systemd-networkd.service NetworkManager.service connman.service

[Service]
Type=oneshot
Environment=SERVICE_MODE=1
ExecStart=bcachefsck_all
SyslogIdentifier=bcachefsck_all

# Create the service underneath the scrub background service slice so that we
# can control resource usage.
Slice=system-bcachefsck.slice

# Run scrub_all with minimal CPU and IO priority so that nothing will starve.
IOSchedulingClass=idle
CPUSchedulingPolicy=idle
CPUAccounting=true
Nice=19

# No realtime scheduling
RestrictRealtime=true

# No special privileges, but we still have to run as root so that we can
# contact the service manager to start the sub-units.
CapabilityBoundingSet=
NoNewPrivileges=true
RestrictSUIDSGID=true

# Make the entire filesystem readonly except for the media scan stamp file
# directory.  We don't want to hide anything because we need to find all
# mounted bcachefs filesystems in the host.
ProtectSystem=strict
ProtectHome=read-only
PrivateTmp=false

# No network access except to the systemd control socket
PrivateNetwork=true
ProtectHostname=true
RestrictAddressFamilies=AF_UNIX
IPAddressDeny=any

# Don't let the program mess with the kernel configuration at all
ProtectKernelLogs=true
ProtectKernelModules=true
ProtectKernelTunables=true
ProtectControlGroups=true
ProtectProc=invisible
RestrictNamespaces=true

# Hide everything in /proc, even /proc/mounts
ProcSubset=pid

# Only allow the default personality Linux
LockPersonality=true

# No writable memory pages
MemoryDenyWriteExecute=true

# Don't let our mounts leak out to the host
PrivateMounts=true

# Restrict system calls to the native arch and only enough to get things going
SystemCallArchitectures=native
SystemCallFilter=@system-service
SystemCallFilter=~@privileged
SystemCallFilter=~@resources
SystemCallFilter=~@mount

# Media scan stamp file shouldn't be readable by regular users
UMask=0077

# lsblk ignores mountpoints if it can't find the device files, so we cannot
# hide them
#ProtectClock=true
#PrivateDevices=true