Systemd/src/nspawn/nspawn-mount.h

82 lines
3.5 KiB
C
Raw Normal View History

#pragma once
/***
This file is part of systemd.
Copyright 2015 Lennart Poettering
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.
systemd is distributed in the hope that it will be useful, but
WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
Lesser General Public License for more details.
You should have received a copy of the GNU Lesser General Public License
along with systemd; If not, see <http://www.gnu.org/licenses/>.
***/
#include <stdbool.h>
core: use the unified hierarchy for the systemd cgroup controller hierarchy Currently, systemd uses either the legacy hierarchies or the unified hierarchy. When the legacy hierarchies are used, systemd uses a named legacy hierarchy mounted on /sys/fs/cgroup/systemd without any kernel controllers for process management. Due to the shortcomings in the legacy hierarchy, this involves a lot of workarounds and complexities. Because the unified hierarchy can be mounted and used in parallel to legacy hierarchies, there's no reason for systemd to use a legacy hierarchy for management even if the kernel resource controllers need to be mounted on legacy hierarchies. It can simply mount the unified hierarchy under /sys/fs/cgroup/systemd and use it without affecting other legacy hierarchies. This disables a significant amount of fragile workaround logics and would allow using features which depend on the unified hierarchy membership such bpf cgroup v2 membership test. In time, this would also allow deleting the said complexities. This patch updates systemd so that it prefers the unified hierarchy for the systemd cgroup controller hierarchy when legacy hierarchies are used for kernel resource controllers. * cg_unified(@controller) is introduced which tests whether the specific controller in on unified hierarchy and used to choose the unified hierarchy code path for process and service management when available. Kernel controller specific operations remain gated by cg_all_unified(). * "systemd.legacy_systemd_cgroup_controller" kernel argument can be used to force the use of legacy hierarchy for systemd cgroup controller. * nspawn: By default nspawn uses the same hierarchies as the host. If UNIFIED_CGROUP_HIERARCHY is set to 1, unified hierarchy is used for all. If 0, legacy for all. * nspawn: arg_unified_cgroup_hierarchy is made an enum and now encodes one of three options - legacy, only systemd controller on unified, and unified. The value is passed into mount setup functions and controls cgroup configuration. * nspawn: Interpretation of SYSTEMD_CGROUP_CONTROLLER to the actual mount option is moved to mount_legacy_cgroup_hierarchy() so that it can take an appropriate action depending on the configuration of the host. v2: - CGroupUnified enum replaces open coded integer values to indicate the cgroup operation mode. - Various style updates. v3: Fixed a bug in detect_unified_cgroup_hierarchy() introduced during v2. v4: Restored legacy container on unified host support and fixed another bug in detect_unified_cgroup_hierarchy().
2016-08-16 00:13:36 +02:00
#include "cgroup-util.h"
typedef enum MountSettingsMask {
MOUNT_FATAL = 1 << 0, /* if set, a mount error is considered fatal */
MOUNT_USE_USERNS = 1 << 1, /* if set, mounts are patched considering uid/gid shifts in a user namespace */
MOUNT_IN_USERNS = 1 << 2, /* if set, the mount is executed in the inner child, otherwise in the outer child */
MOUNT_APPLY_APIVFS_RO = 1 << 3, /* if set, /proc/sys, and /sysfs will be mounted read-only, otherwise read-write. */
MOUNT_APPLY_APIVFS_NETNS = 1 << 4, /* if set, /proc/sys/net will be mounted read-write.
Works only if MOUNT_APPLY_APIVFS_RO is also set. */
} MountSettingsMask;
typedef enum VolatileMode {
VOLATILE_NO,
VOLATILE_YES,
VOLATILE_STATE,
_VOLATILE_MODE_MAX,
_VOLATILE_MODE_INVALID = -1
} VolatileMode;
typedef enum CustomMountType {
CUSTOM_MOUNT_BIND,
CUSTOM_MOUNT_TMPFS,
CUSTOM_MOUNT_OVERLAY,
_CUSTOM_MOUNT_TYPE_MAX,
_CUSTOM_MOUNT_TYPE_INVALID = -1
} CustomMountType;
typedef struct CustomMount {
CustomMountType type;
bool read_only;
char *source; /* for overlayfs this is the upper directory */
char *destination;
char *options;
char *work_dir;
char **lower;
char *rm_rf_tmpdir;
} CustomMount;
CustomMount* custom_mount_add(CustomMount **l, unsigned *n, CustomMountType t);
void custom_mount_free_all(CustomMount *l, unsigned n);
int custom_mount_prepare_all(const char *dest, CustomMount *l, unsigned n);
int bind_mount_parse(CustomMount **l, unsigned *n, const char *s, bool read_only);
int tmpfs_mount_parse(CustomMount **l, unsigned *n, const char *s);
int overlay_mount_parse(CustomMount **l, unsigned *n, const char *s, bool read_only);
int mount_all(const char *dest, MountSettingsMask mount_settings, uid_t uid_shift, uid_t uid_range, const char *selinux_apifs_context);
int mount_sysfs(const char *dest, MountSettingsMask mount_settings);
core: use the unified hierarchy for the systemd cgroup controller hierarchy Currently, systemd uses either the legacy hierarchies or the unified hierarchy. When the legacy hierarchies are used, systemd uses a named legacy hierarchy mounted on /sys/fs/cgroup/systemd without any kernel controllers for process management. Due to the shortcomings in the legacy hierarchy, this involves a lot of workarounds and complexities. Because the unified hierarchy can be mounted and used in parallel to legacy hierarchies, there's no reason for systemd to use a legacy hierarchy for management even if the kernel resource controllers need to be mounted on legacy hierarchies. It can simply mount the unified hierarchy under /sys/fs/cgroup/systemd and use it without affecting other legacy hierarchies. This disables a significant amount of fragile workaround logics and would allow using features which depend on the unified hierarchy membership such bpf cgroup v2 membership test. In time, this would also allow deleting the said complexities. This patch updates systemd so that it prefers the unified hierarchy for the systemd cgroup controller hierarchy when legacy hierarchies are used for kernel resource controllers. * cg_unified(@controller) is introduced which tests whether the specific controller in on unified hierarchy and used to choose the unified hierarchy code path for process and service management when available. Kernel controller specific operations remain gated by cg_all_unified(). * "systemd.legacy_systemd_cgroup_controller" kernel argument can be used to force the use of legacy hierarchy for systemd cgroup controller. * nspawn: By default nspawn uses the same hierarchies as the host. If UNIFIED_CGROUP_HIERARCHY is set to 1, unified hierarchy is used for all. If 0, legacy for all. * nspawn: arg_unified_cgroup_hierarchy is made an enum and now encodes one of three options - legacy, only systemd controller on unified, and unified. The value is passed into mount setup functions and controls cgroup configuration. * nspawn: Interpretation of SYSTEMD_CGROUP_CONTROLLER to the actual mount option is moved to mount_legacy_cgroup_hierarchy() so that it can take an appropriate action depending on the configuration of the host. v2: - CGroupUnified enum replaces open coded integer values to indicate the cgroup operation mode. - Various style updates. v3: Fixed a bug in detect_unified_cgroup_hierarchy() introduced during v2. v4: Restored legacy container on unified host support and fixed another bug in detect_unified_cgroup_hierarchy().
2016-08-16 00:13:36 +02:00
int mount_cgroups(const char *dest, CGroupUnified unified_requested, bool userns, uid_t uid_shift, uid_t uid_range, const char *selinux_apifs_context, bool use_cgns);
int mount_systemd_cgroup_writable(const char *dest, CGroupUnified unified_requested);
int mount_custom(const char *dest, CustomMount *mounts, unsigned n, bool userns, uid_t uid_shift, uid_t uid_range, const char *selinux_apifs_context);
int setup_volatile(const char *directory, VolatileMode mode, bool userns, uid_t uid_shift, uid_t uid_range, const char *selinux_apifs_context);
int setup_volatile_state(const char *directory, VolatileMode mode, bool userns, uid_t uid_shift, uid_t uid_range, const char *selinux_apifs_context);
VolatileMode volatile_mode_from_string(const char *s);