mirror of
https://github.com/systemd/systemd.git
synced 2025-01-09 01:18:19 +03:00
dc3223919f
Linux kernel v4.18 (2018-08-12) added user-namespace support to FUSE, and bumped the FUSE version to 7.27 (see: da315f6e0398 (Merge tag 'fuse-update-4.18' of git://git.kernel.org/pub/scm/linux/kernel/git/mszeredi/fuse, Linus Torvalds, 2018-06-07). This means that on such kernels it is safe to enable FUSE in nspawn containers. In outer_child(), before calling copy_devnodes(), check the FUSE version to decide whether enable (>=7.27) or disable (<7.27) FUSE in the container. We look at the FUSE version instead of the kernel version in order to enable FUSE support on older-versioned kernels that may have the mentioned patchset backported ([as requested by @poettering][1]). However, I am not sure that this is safe; user-namespace support is not a documented part of the FUSE protocol, which is what FUSE_KERNEL_VERSION/FUSE_KERNEL_MINOR_VERSION are meant to capture. While the same patchset - added FUSE_ABORT_ERROR (which is all that the 7.27 version bump is documented as including), - bumped FUSE_KERNEL_MINOR_VERSION from 26 to 27, and - added user-namespace support these 3 things are not inseparable; it is conceivable to me that a backport could include the first 2 of those things and exclude the 3rd; perhaps it would be safer to check the kernel version. Do note that our get_fuse_version() function uses the fsopen() family of syscalls, which were not added until Linux kernel v5.2 (2019-07-07); so if nothing has been backported, then the minimum kernel version for FUSE-in-nspawn is actually v5.2, not v4.18. Pass whether or not to enable FUSE to copy_devnodes(); have copy_devnodes() copy in /dev/fuse if enabled. Pass whether or not to enable FUSE back over fd_outer_socket to run_container() so that it can pass that to append_machine_properties() (via either register_machine() or allocate_scope()); have append_machine_properties() append "DeviceAllow=/dev/fuse rw" if enabled. For testing, simply check that /dev/fuse can be opened for reading and writing, but that actually reading from it fails with EPERM. The test assumes that if FUSE is supported (/dev/fuse exists), then the testsuite is running on a kernel with FUSE >= 7.27; I am unsure how to go about writing a test that validates that the version check disables FUSE on old kernels. [1]: https://github.com/systemd/systemd/issues/17607#issuecomment-745418835 Closes #17607
57 lines
2.0 KiB
SYSTEMD
57 lines
2.0 KiB
SYSTEMD
# SPDX-License-Identifier: LGPL-2.1-or-later
|
|
#
|
|
# This file is part of systemd.
|
|
#
|
|
# systemd is free software; you can redistribute it and/or modify it
|
|
# under the terms of the GNU Lesser General Public License as published by
|
|
# the Free Software Foundation; either version 2.1 of the License, or
|
|
# (at your option) any later version.
|
|
|
|
[Unit]
|
|
Description=Container %i
|
|
Documentation=man:systemd-nspawn(1)
|
|
Wants=modprobe@tun.service modprobe@loop.service modprobe@dm_mod.service
|
|
PartOf=machines.target
|
|
Before=machines.target
|
|
After=network.target modprobe@tun.service modprobe@loop.service modprobe@dm_mod.service
|
|
RequiresMountsFor=/var/lib/machines/%i
|
|
|
|
[Service]
|
|
# Make sure the DeviceAllow= lines below can properly resolve the 'block-loop' expression (and others)
|
|
ExecStart=systemd-nspawn --quiet --keep-unit --boot --link-journal=try-guest --network-veth -U --settings=override --machine=%i
|
|
KillMode=mixed
|
|
Type=notify
|
|
RestartForceExitStatus=133
|
|
SuccessExitStatus=133
|
|
Slice=machine.slice
|
|
Delegate=yes
|
|
DelegateSubgroup=supervisor
|
|
CoredumpReceive=yes
|
|
TasksMax=16384
|
|
{{SERVICE_WATCHDOG}}
|
|
|
|
{# Enforce a strict device policy, similar to the one nspawn configures (in
|
|
# nspawn-register.c:append_machine_properties()) when it allocates its own
|
|
# scope unit. Make sure to keep these policies in sync if you change them! #}
|
|
DevicePolicy=closed
|
|
DeviceAllow=/dev/net/tun rwm
|
|
DeviceAllow=char-pts rw
|
|
{# /dev/fuse gets 'm' here even though it doesn't in nspawn-register.c, since
|
|
# efedb6b0f3 (nspawn: refuse to bind mount device node from host when
|
|
# --private-users= is specified, 2024-09-05) #}
|
|
DeviceAllow=/dev/fuse rwm
|
|
|
|
# nspawn itself needs access to /dev/loop-control and /dev/loop, to implement
|
|
# the --image= option. Add these here, too.
|
|
DeviceAllow=/dev/loop-control rw
|
|
DeviceAllow=block-loop rw
|
|
DeviceAllow=block-blkext rw
|
|
|
|
# nspawn can set up LUKS encrypted loopback files, in which case it needs
|
|
# access to /dev/mapper/control and the block devices /dev/mapper/*.
|
|
DeviceAllow=/dev/mapper/control rw
|
|
DeviceAllow=block-device-mapper rw
|
|
|
|
[Install]
|
|
WantedBy=machines.target
|