-/*-*- Mode: C; c-basic-offset: 8; indent-tabs-mode: nil -*-*/
-
+/* SPDX-License-Identifier: LGPL-2.1+ */
/***
This file is part of systemd.
#include "cgroup-util.h"
#include "dev-setup.h"
#include "efivars.h"
+#include "fs-util.h"
#include "label.h"
#include "log.h"
#include "macro.h"
* fourth (securityfs) is needed by IMA to load a custom policy. The
* other ones we can delay until SELinux and IMA are loaded. When
* SMACK is enabled we need smackfs, too, so it's a fifth one. */
-#ifdef HAVE_SMACK
+#if ENABLE_SMACK
#define N_EARLY_MOUNT 5
#else
#define N_EARLY_MOUNT 4
NULL, MNT_FATAL|MNT_IN_CONTAINER },
{ "securityfs", "/sys/kernel/security", "securityfs", NULL, MS_NOSUID|MS_NOEXEC|MS_NODEV,
NULL, MNT_NONE },
-#ifdef HAVE_SMACK
+#if ENABLE_SMACK
{ "smackfs", "/sys/fs/smackfs", "smackfs", "smackfsdef=*", MS_NOSUID|MS_NOEXEC|MS_NODEV,
mac_smack_use, MNT_FATAL },
{ "tmpfs", "/dev/shm", "tmpfs", "mode=1777,smackfsroot=*", MS_NOSUID|MS_NODEV|MS_STRICTATIME,
NULL, MNT_FATAL|MNT_IN_CONTAINER },
{ "devpts", "/dev/pts", "devpts", "mode=620,gid=" STRINGIFY(TTY_GID), MS_NOSUID|MS_NOEXEC,
NULL, MNT_IN_CONTAINER },
-#ifdef HAVE_SMACK
+#if ENABLE_SMACK
{ "tmpfs", "/run", "tmpfs", "mode=755,smackfsroot=*", MS_NOSUID|MS_NODEV|MS_STRICTATIME,
mac_smack_use, MNT_FATAL },
#endif
{ "tmpfs", "/run", "tmpfs", "mode=755", MS_NOSUID|MS_NODEV|MS_STRICTATIME,
NULL, MNT_FATAL|MNT_IN_CONTAINER },
- { "cgroup", "/sys/fs/cgroup", "cgroup", "__DEVEL__sane_behavior", MS_NOSUID|MS_NOEXEC|MS_NODEV,
- cg_is_unified_wanted, MNT_FATAL|MNT_IN_CONTAINER },
+ { "cgroup", "/sys/fs/cgroup", "cgroup2", "nsdelegate", MS_NOSUID|MS_NOEXEC|MS_NODEV,
+ cg_is_unified_wanted, MNT_IN_CONTAINER },
+ { "cgroup", "/sys/fs/cgroup", "cgroup2", NULL, MS_NOSUID|MS_NOEXEC|MS_NODEV,
+ cg_is_unified_wanted, MNT_IN_CONTAINER },
{ "tmpfs", "/sys/fs/cgroup", "tmpfs", "mode=755", MS_NOSUID|MS_NOEXEC|MS_NODEV|MS_STRICTATIME,
cg_is_legacy_wanted, MNT_FATAL|MNT_IN_CONTAINER },
+ { "cgroup", "/sys/fs/cgroup/unified", "cgroup2", "nsdelegate", MS_NOSUID|MS_NOEXEC|MS_NODEV,
+ cg_is_hybrid_wanted, MNT_IN_CONTAINER },
+ { "cgroup", "/sys/fs/cgroup/unified", "cgroup2", NULL, MS_NOSUID|MS_NOEXEC|MS_NODEV,
+ cg_is_hybrid_wanted, MNT_IN_CONTAINER },
{ "cgroup", "/sys/fs/cgroup/systemd", "cgroup", "none,name=systemd,xattr", MS_NOSUID|MS_NOEXEC|MS_NODEV,
- cg_is_legacy_wanted, MNT_IN_CONTAINER },
+ cg_is_legacy_wanted, MNT_IN_CONTAINER },
{ "cgroup", "/sys/fs/cgroup/systemd", "cgroup", "none,name=systemd", MS_NOSUID|MS_NOEXEC|MS_NODEV,
cg_is_legacy_wanted, MNT_FATAL|MNT_IN_CONTAINER },
{ "pstore", "/sys/fs/pstore", "pstore", NULL, MS_NOSUID|MS_NOEXEC|MS_NODEV,
NULL, MNT_NONE },
-#ifdef ENABLE_EFI
+#if ENABLE_EFI
{ "efivarfs", "/sys/firmware/efi/efivars", "efivarfs", NULL, MS_NOSUID|MS_NOEXEC|MS_NODEV,
is_efi_boot, MNT_NONE },
#endif
- { "kdbusfs", "/sys/fs/kdbus", "kdbusfs", NULL, MS_NOSUID|MS_NOEXEC|MS_NODEV,
- is_kdbus_wanted, MNT_IN_CONTAINER },
};
/* These are API file systems that might be mounted by other software,
/* Relabel first, just in case */
if (relabel)
- label_fix(p->where, true, true);
+ (void) label_fix(p->where, true, true);
- r = path_is_mount_point(p->where, AT_SYMLINK_FOLLOW);
- if (r < 0 && r != -ENOENT)
- return r;
+ r = path_is_mount_point(p->where, NULL, AT_SYMLINK_FOLLOW);
+ if (r < 0 && r != -ENOENT) {
+ log_full_errno((p->mode & MNT_FATAL) ? LOG_ERR : LOG_DEBUG, r, "Failed to determine whether %s is a mount point: %m", p->where);
+ return (p->mode & MNT_FATAL) ? r : 0;
+ }
if (r > 0)
return 0;
/* The access mode here doesn't really matter too much, since
* the mounted file system will take precedence anyway. */
if (relabel)
- mkdir_p_label(p->where, 0755);
+ (void) mkdir_p_label(p->where, 0755);
else
- mkdir_p(p->where, 0755);
+ (void) mkdir_p(p->where, 0755);
log_debug("Mounting %s to %s of type %s with options %s.",
p->what,
p->type,
p->flags,
p->options) < 0) {
- log_full((p->mode & MNT_FATAL) ? LOG_ERR : LOG_DEBUG, "Failed to mount %s at %s: %m", p->type, p->where);
+ log_full_errno((p->mode & MNT_FATAL) ? LOG_ERR : LOG_DEBUG, errno, "Failed to mount %s at %s: %m", p->type, p->where);
return (p->mode & MNT_FATAL) ? -errno : 0;
}
/* Relabel again, since we now mounted something fresh here */
if (relabel)
- label_fix(p->where, false, false);
+ (void) label_fix(p->where, false, false);
return 1;
}
-int mount_setup_early(void) {
+static int mount_points_setup(unsigned n, bool loaded_policy) {
unsigned i;
int r = 0;
- assert_cc(N_EARLY_MOUNT <= ELEMENTSOF(mount_table));
-
- /* Do a minimal mount of /proc and friends to enable the most
- * basic stuff, such as SELinux */
- for (i = 0; i < N_EARLY_MOUNT; i ++) {
+ for (i = 0; i < n; i ++) {
int j;
- j = mount_one(mount_table + i, false);
+ j = mount_one(mount_table + i, loaded_policy);
if (j != 0 && r >= 0)
r = j;
}
return r;
}
+int mount_setup_early(void) {
+ assert_cc(N_EARLY_MOUNT <= ELEMENTSOF(mount_table));
+
+ /* Do a minimal mount of /proc and friends to enable the most
+ * basic stuff, such as SELinux */
+ return mount_points_setup(N_EARLY_MOUNT, false);
+}
+
int mount_cgroup_controllers(char ***join_controllers) {
_cleanup_set_free_free_ Set *controllers = NULL;
int r;
return 0;
}
-#if defined(HAVE_SELINUX) || defined(HAVE_SMACK)
+#if HAVE_SELINUX || ENABLE_SMACK
static int nftw_cb(
const char *fpath,
const struct stat *sb,
#endif
int mount_setup(bool loaded_policy) {
- unsigned i;
int r = 0;
- for (i = 0; i < ELEMENTSOF(mount_table); i ++) {
- int j;
-
- j = mount_one(mount_table + i, loaded_policy);
- if (j != 0 && r >= 0)
- r = j;
- }
-
+ r = mount_points_setup(ELEMENTSOF(mount_table), loaded_policy);
if (r < 0)
return r;
-#if defined(HAVE_SELINUX) || defined(HAVE_SMACK)
+#if HAVE_SELINUX || ENABLE_SMACK
/* Nodes in devtmpfs and /run need to be manually updated for
* the appropriate labels, after mounting. The other virtual
* API file systems like /sys and /proc do not need that, they
before_relabel = now(CLOCK_MONOTONIC);
nftw("/dev", nftw_cb, 64, FTW_MOUNT|FTW_PHYS|FTW_ACTIONRETVAL);
+ nftw("/dev/shm", nftw_cb, 64, FTW_MOUNT|FTW_PHYS|FTW_ACTIONRETVAL);
nftw("/run", nftw_cb, 64, FTW_MOUNT|FTW_PHYS|FTW_ACTIONRETVAL);
after_relabel = now(CLOCK_MONOTONIC);
* udevd. */
dev_setup(NULL, UID_INVALID, GID_INVALID);
- /* Mark the root directory as shared in regards to mount
- * propagation. The kernel defaults to "private", but we think
- * it makes more sense to have a default of "shared" so that
- * nspawn and the container tools work out of the box. If
- * specific setups need other settings they can reset the
- * propagation mode to private if needed. */
+ /* Mark the root directory as shared in regards to mount propagation. The kernel defaults to "private", but we
+ * think it makes more sense to have a default of "shared" so that nspawn and the container tools work out of
+ * the box. If specific setups need other settings they can reset the propagation mode to private if
+ * needed. Note that we set this only when we are invoked directly by the kernel. If we are invoked by a
+ * container manager we assume the container manager knows what it is doing (for example, because it set up
+ * some directories with different propagation modes). */
if (detect_container() <= 0)
if (mount(NULL, "/", NULL, MS_REC|MS_SHARED, NULL) < 0)
log_warning_errno(errno, "Failed to set up the root directory for shared mount propagation: %m");
- /* Create a few directories we always want around, Note that
- * sd_booted() checks for /run/systemd/system, so this mkdir
- * really needs to stay for good, otherwise software that
- * copied sd-daemon.c into their sources will misdetect
- * systemd. */
- mkdir_label("/run/systemd", 0755);
- mkdir_label("/run/systemd/system", 0755);
- mkdir_label("/run/systemd/inaccessible", 0000);
+ /* Create a few directories we always want around, Note that sd_booted() checks for /run/systemd/system, so
+ * this mkdir really needs to stay for good, otherwise software that copied sd-daemon.c into their sources will
+ * misdetect systemd. */
+ (void) mkdir_label("/run/systemd", 0755);
+ (void) mkdir_label("/run/systemd/system", 0755);
+
+ /* Set up inaccessible items */
+ (void) mkdir_label("/run/systemd/inaccessible", 0000);
+ (void) mknod("/run/systemd/inaccessible/reg", S_IFREG | 0000, 0);
+ (void) mkdir_label("/run/systemd/inaccessible/dir", 0000);
+ (void) mknod("/run/systemd/inaccessible/chr", S_IFCHR | 0000, makedev(0, 0));
+ (void) mknod("/run/systemd/inaccessible/blk", S_IFBLK | 0000, makedev(0, 0));
+ (void) mkfifo("/run/systemd/inaccessible/fifo", 0000);
+ (void) mknod("/run/systemd/inaccessible/sock", S_IFSOCK | 0000, 0);
return 0;
}
projects / thirdparty / systemd.git / blobdiff