summaryrefslogtreecommitdiff
path: root/src/core
diff options
context:
space:
mode:
Diffstat (limited to 'src/core')
-rw-r--r--src/core/automount.c5
-rw-r--r--src/core/busname.c2
-rw-r--r--src/core/dbus-execute.c9
-rw-r--r--src/core/dbus-unit.c2
-rw-r--r--src/core/dbus.c4
-rw-r--r--src/core/dynamic-user.c2
-rw-r--r--src/core/execute.c408
-rw-r--r--src/core/execute.h2
-rw-r--r--src/core/load-fragment-gperf.gperf.m42
-rw-r--r--src/core/main.c37
-rw-r--r--src/core/manager.c165
-rw-r--r--src/core/manager.h17
-rw-r--r--src/core/mount.c48
-rw-r--r--src/core/namespace.c586
-rw-r--r--src/core/namespace.h3
-rw-r--r--src/core/service.c15
-rw-r--r--src/core/socket.c11
-rw-r--r--src/core/swap.c2
-rw-r--r--src/core/system.conf1
-rw-r--r--src/core/umount.c2
-rw-r--r--src/core/unit.c11
21 files changed, 1002 insertions, 332 deletions
diff --git a/src/core/automount.c b/src/core/automount.c
index 00295cf769..bdc0e06965 100644
--- a/src/core/automount.c
+++ b/src/core/automount.c
@@ -271,6 +271,11 @@ static int automount_coldplug(Unit *u) {
return r;
(void) sd_event_source_set_description(a->pipe_event_source, "automount-io");
+ if (a->deserialized_state == AUTOMOUNT_RUNNING) {
+ r = automount_start_expire(a);
+ if (r < 0)
+ log_unit_warning_errno(UNIT(a), r, "Failed to start expiration timer, ignoring: %m");
+ }
}
automount_set_state(a, a->deserialized_state);
diff --git a/src/core/busname.c b/src/core/busname.c
index 7952cd31aa..a69e3831f6 100644
--- a/src/core/busname.c
+++ b/src/core/busname.c
@@ -868,7 +868,7 @@ static void busname_sigchld_event(Unit *u, pid_t pid, int code, int status) {
n->control_pid = 0;
- if (is_clean_exit(code, status, NULL))
+ if (is_clean_exit(code, status, EXIT_CLEAN_COMMAND, NULL))
f = BUSNAME_SUCCESS;
else if (code == CLD_EXITED)
f = BUSNAME_FAILURE_EXIT_CODE;
diff --git a/src/core/dbus-execute.c b/src/core/dbus-execute.c
index 7e33a2d201..eec4500c8c 100644
--- a/src/core/dbus-execute.c
+++ b/src/core/dbus-execute.c
@@ -707,6 +707,8 @@ const sd_bus_vtable bus_exec_vtable[] = {
SD_BUS_PROPERTY("MountFlags", "t", bus_property_get_ulong, offsetof(ExecContext, mount_flags), SD_BUS_VTABLE_PROPERTY_CONST),
SD_BUS_PROPERTY("PrivateTmp", "b", bus_property_get_bool, offsetof(ExecContext, private_tmp), SD_BUS_VTABLE_PROPERTY_CONST),
SD_BUS_PROPERTY("PrivateDevices", "b", bus_property_get_bool, offsetof(ExecContext, private_devices), SD_BUS_VTABLE_PROPERTY_CONST),
+ SD_BUS_PROPERTY("ProtectKernelTunables", "b", bus_property_get_bool, offsetof(ExecContext, protect_kernel_tunables), SD_BUS_VTABLE_PROPERTY_CONST),
+ SD_BUS_PROPERTY("ProtectControlGroups", "b", bus_property_get_bool, offsetof(ExecContext, protect_control_groups), SD_BUS_VTABLE_PROPERTY_CONST),
SD_BUS_PROPERTY("PrivateNetwork", "b", bus_property_get_bool, offsetof(ExecContext, private_network), SD_BUS_VTABLE_PROPERTY_CONST),
SD_BUS_PROPERTY("PrivateUsers", "b", bus_property_get_bool, offsetof(ExecContext, private_users), SD_BUS_VTABLE_PROPERTY_CONST),
SD_BUS_PROPERTY("ProtectHome", "s", bus_property_get_protect_home, offsetof(ExecContext, protect_home), SD_BUS_VTABLE_PROPERTY_CONST),
@@ -1072,7 +1074,8 @@ int bus_exec_context_set_transient_property(
"IgnoreSIGPIPE", "TTYVHangup", "TTYReset",
"PrivateTmp", "PrivateDevices", "PrivateNetwork", "PrivateUsers",
"NoNewPrivileges", "SyslogLevelPrefix", "MemoryDenyWriteExecute",
- "RestrictRealtime", "DynamicUser", "RemoveIPC")) {
+ "RestrictRealtime", "DynamicUser", "RemoveIPC", "ProtectKernelTunables",
+ "ProtectControlGroups")) {
int b;
r = sd_bus_message_read(message, "b", &b);
@@ -1106,6 +1109,10 @@ int bus_exec_context_set_transient_property(
c->dynamic_user = b;
else if (streq(name, "RemoveIPC"))
c->remove_ipc = b;
+ else if (streq(name, "ProtectKernelTunables"))
+ c->protect_kernel_tunables = b;
+ else if (streq(name, "ProtectControlGroups"))
+ c->protect_control_groups = b;
unit_write_drop_in_private_format(u, mode, name, "%s=%s", name, yes_no(b));
}
diff --git a/src/core/dbus-unit.c b/src/core/dbus-unit.c
index 1b86bdde43..5020dfba4b 100644
--- a/src/core/dbus-unit.c
+++ b/src/core/dbus-unit.c
@@ -1167,7 +1167,7 @@ void bus_unit_send_removed_signal(Unit *u) {
int r;
assert(u);
- if (!u->sent_dbus_new_signal)
+ if (!u->sent_dbus_new_signal || u->in_dbus_queue)
bus_unit_send_change_signal(u);
if (!u->id)
diff --git a/src/core/dbus.c b/src/core/dbus.c
index 1e41a42aa6..070974fe66 100644
--- a/src/core/dbus.c
+++ b/src/core/dbus.c
@@ -964,10 +964,6 @@ static int bus_init_private(Manager *m) {
if (m->private_listen_fd >= 0)
return 0;
- /* We don't need the private socket if we have kdbus */
- if (m->kdbus_fd >= 0)
- return 0;
-
if (MANAGER_IS_SYSTEM(m)) {
/* We want the private bus only when running as init */
diff --git a/src/core/dynamic-user.c b/src/core/dynamic-user.c
index 310aaa94e1..1043da3eb7 100644
--- a/src/core/dynamic-user.c
+++ b/src/core/dynamic-user.c
@@ -233,7 +233,7 @@ static int pick_uid(const char *name, uid_t *ret_uid) {
if (st.st_nlink > 0)
break;
- /* Oh, bummer, we got got the lock, but the file was unlinked between the time we opened it and
+ /* Oh, bummer, we got the lock, but the file was unlinked between the time we opened it and
* got the lock. Close it, and try again. */
lock_fd = safe_close(lock_fd);
}
diff --git a/src/core/execute.c b/src/core/execute.c
index 2026137721..d5c4e60796 100644
--- a/src/core/execute.c
+++ b/src/core/execute.c
@@ -781,9 +781,10 @@ static int enforce_groups(const ExecContext *context, const char *username, gid_
k++;
}
- if (setgroups(k, gids) < 0) {
+ r = maybe_setgroups(k, gids);
+ if (r < 0) {
free(gids);
- return -errno;
+ return r;
}
free(gids);
@@ -837,14 +838,19 @@ static int null_conv(
return PAM_CONV_ERR;
}
+#endif
+
static int setup_pam(
const char *name,
const char *user,
uid_t uid,
+ gid_t gid,
const char *tty,
char ***env,
int fds[], unsigned n_fds) {
+#ifdef HAVE_PAM
+
static const struct pam_conv conv = {
.conv = null_conv,
.appdata_ptr = NULL
@@ -944,8 +950,14 @@ static int setup_pam(
* and this will make PR_SET_PDEATHSIG work in most cases.
* If this fails, ignore the error - but expect sd-pam threads
* to fail to exit normally */
+
+ r = maybe_setgroups(0, NULL);
+ if (r < 0)
+ log_warning_errno(r, "Failed to setgroups() in sd-pam: %m");
+ if (setresgid(gid, gid, gid) < 0)
+ log_warning_errno(errno, "Failed to setresgid() in sd-pam: %m");
if (setresuid(uid, uid, uid) < 0)
- log_error_errno(r, "Error: Failed to setresuid() in sd-pam: %m");
+ log_warning_errno(errno, "Failed to setresuid() in sd-pam: %m");
(void) ignore_signals(SIGPIPE, -1);
@@ -1038,8 +1050,10 @@ fail:
closelog();
return r;
-}
+#else
+ return 0;
#endif
+}
static void rename_process_from_path(const char *path) {
char process_name[11];
@@ -1273,6 +1287,10 @@ static int apply_memory_deny_write_execute(const Unit* u, const ExecContext *c)
if (!seccomp)
return -ENOMEM;
+ r = seccomp_add_secondary_archs(seccomp);
+ if (r < 0)
+ goto finish;
+
r = seccomp_rule_add(
seccomp,
SCMP_ACT_ERRNO(EPERM),
@@ -1322,6 +1340,10 @@ static int apply_restrict_realtime(const Unit* u, const ExecContext *c) {
if (!seccomp)
return -ENOMEM;
+ r = seccomp_add_secondary_archs(seccomp);
+ if (r < 0)
+ goto finish;
+
/* Determine the highest policy constant we want to allow */
for (i = 0; i < ELEMENTSOF(permitted_policies); i++)
if (permitted_policies[i] > max_policy)
@@ -1375,12 +1397,121 @@ finish:
return r;
}
+static int apply_protect_sysctl(Unit *u, const ExecContext *c) {
+ scmp_filter_ctx *seccomp;
+ int r;
+
+ assert(c);
+
+ /* Turn off the legacy sysctl() system call. Many distributions turn this off while building the kernel, but
+ * let's protect even those systems where this is left on in the kernel. */
+
+ if (skip_seccomp_unavailable(u, "ProtectKernelTunables="))
+ return 0;
+
+ seccomp = seccomp_init(SCMP_ACT_ALLOW);
+ if (!seccomp)
+ return -ENOMEM;
+
+ r = seccomp_add_secondary_archs(seccomp);
+ if (r < 0)
+ goto finish;
+
+ r = seccomp_rule_add(
+ seccomp,
+ SCMP_ACT_ERRNO(EPERM),
+ SCMP_SYS(_sysctl),
+ 0);
+ if (r < 0)
+ goto finish;
+
+ r = seccomp_attr_set(seccomp, SCMP_FLTATR_CTL_NNP, 0);
+ if (r < 0)
+ goto finish;
+
+ r = seccomp_load(seccomp);
+
+finish:
+ seccomp_release(seccomp);
+ return r;
+}
+
+static int apply_private_devices(Unit *u, const ExecContext *c) {
+ const SystemCallFilterSet *set;
+ scmp_filter_ctx *seccomp;
+ const char *sys;
+ bool syscalls_found = false;
+ int r;
+
+ assert(c);
+
+ /* If PrivateDevices= is set, also turn off iopl and all @raw-io syscalls. */
+
+ if (skip_seccomp_unavailable(u, "PrivateDevices="))
+ return 0;
+
+ seccomp = seccomp_init(SCMP_ACT_ALLOW);
+ if (!seccomp)
+ return -ENOMEM;
+
+ r = seccomp_add_secondary_archs(seccomp);
+ if (r < 0)
+ goto finish;
+
+ for (set = syscall_filter_sets; set->set_name; set++)
+ if (streq(set->set_name, "@raw-io")) {
+ syscalls_found = true;
+ break;
+ }
+
+ /* We should never fail here */
+ if (!syscalls_found) {
+ r = -EOPNOTSUPP;
+ goto finish;
+ }
+
+ NULSTR_FOREACH(sys, set->value) {
+ int id;
+ bool add = true;
+
+#ifndef __NR_s390_pci_mmio_read
+ if (streq(sys, "s390_pci_mmio_read"))
+ add = false;
+#endif
+#ifndef __NR_s390_pci_mmio_write
+ if (streq(sys, "s390_pci_mmio_write"))
+ add = false;
+#endif
+
+ if (!add)
+ continue;
+
+ id = seccomp_syscall_resolve_name(sys);
+
+ r = seccomp_rule_add(
+ seccomp,
+ SCMP_ACT_ERRNO(EPERM),
+ id, 0);
+ if (r < 0)
+ goto finish;
+ }
+
+ r = seccomp_attr_set(seccomp, SCMP_FLTATR_CTL_NNP, 0);
+ if (r < 0)
+ goto finish;
+
+ r = seccomp_load(seccomp);
+
+finish:
+ seccomp_release(seccomp);
+ return r;
+}
+
#endif
static void do_idle_pipe_dance(int idle_pipe[4]) {
assert(idle_pipe);
-
idle_pipe[1] = safe_close(idle_pipe[1]);
idle_pipe[2] = safe_close(idle_pipe[2]);
@@ -1581,7 +1712,9 @@ static bool exec_needs_mount_namespace(
if (context->private_devices ||
context->protect_system != PROTECT_SYSTEM_NO ||
- context->protect_home != PROTECT_HOME_NO)
+ context->protect_home != PROTECT_HOME_NO ||
+ context->protect_kernel_tunables ||
+ context->protect_control_groups)
return true;
return false;
@@ -1740,6 +1873,111 @@ static int setup_private_users(uid_t uid, gid_t gid) {
return 0;
}
+static int setup_runtime_directory(
+ const ExecContext *context,
+ const ExecParameters *params,
+ uid_t uid,
+ gid_t gid) {
+
+ char **rt;
+ int r;
+
+ assert(context);
+ assert(params);
+
+ STRV_FOREACH(rt, context->runtime_directory) {
+ _cleanup_free_ char *p;
+
+ p = strjoin(params->runtime_prefix, "/", *rt, NULL);
+ if (!p)
+ return -ENOMEM;
+
+ r = mkdir_p_label(p, context->runtime_directory_mode);
+ if (r < 0)
+ return r;
+
+ r = chmod_and_chown(p, context->runtime_directory_mode, uid, gid);
+ if (r < 0)
+ return r;
+ }
+
+ return 0;
+}
+
+static int setup_smack(
+ const ExecContext *context,
+ const ExecCommand *command) {
+
+#ifdef HAVE_SMACK
+ int r;
+
+ assert(context);
+ assert(command);
+
+ if (!mac_smack_use())
+ return 0;
+
+ if (context->smack_process_label) {
+ r = mac_smack_apply_pid(0, context->smack_process_label);
+ if (r < 0)
+ return r;
+ }
+#ifdef SMACK_DEFAULT_PROCESS_LABEL
+ else {
+ _cleanup_free_ char *exec_label = NULL;
+
+ r = mac_smack_read(command->path, SMACK_ATTR_EXEC, &exec_label);
+ if (r < 0 && r != -ENODATA && r != -EOPNOTSUPP)
+ return r;
+
+ r = mac_smack_apply_pid(0, exec_label ? : SMACK_DEFAULT_PROCESS_LABEL);
+ if (r < 0)
+ return r;
+ }
+#endif
+#endif
+
+ return 0;
+}
+
+static int compile_read_write_paths(
+ const ExecContext *context,
+ const ExecParameters *params,
+ char ***ret) {
+
+ _cleanup_strv_free_ char **l = NULL;
+ char **rt;
+
+ /* Compile the list of writable paths. This is the combination of the explicitly configured paths, plus all
+ * runtime directories. */
+
+ if (strv_isempty(context->read_write_paths) &&
+ strv_isempty(context->runtime_directory)) {
+ *ret = NULL; /* NOP if neither is set */
+ return 0;
+ }
+
+ l = strv_copy(context->read_write_paths);
+ if (!l)
+ return -ENOMEM;
+
+ STRV_FOREACH(rt, context->runtime_directory) {
+ char *s;
+
+ s = strjoin(params->runtime_prefix, "/", *rt, NULL);
+ if (!s)
+ return -ENOMEM;
+
+ if (strv_consume(&l, s) < 0)
+ return -ENOMEM;
+ }
+
+ *ret = l;
+ l = NULL;
+
+ return 0;
+}
+
static void append_socket_pair(int *array, unsigned *n, int pair[2]) {
assert(array);
assert(n);
@@ -1796,6 +2034,37 @@ static int close_remaining_fds(
return close_all_fds(dont_close, n_dont_close);
}
+static bool context_has_address_families(const ExecContext *c) {
+ assert(c);
+
+ return c->address_families_whitelist ||
+ !set_isempty(c->address_families);
+}
+
+static bool context_has_syscall_filters(const ExecContext *c) {
+ assert(c);
+
+ return c->syscall_whitelist ||
+ !set_isempty(c->syscall_filter) ||
+ !set_isempty(c->syscall_archs);
+}
+
+static bool context_has_no_new_privileges(const ExecContext *c) {
+ assert(c);
+
+ if (c->no_new_privileges)
+ return true;
+
+ if (have_effective_cap(CAP_SYS_ADMIN)) /* if we are privileged, we don't need NNP */
+ return false;
+
+ return context_has_address_families(c) || /* we need NNP if we have any form of seccomp and are unprivileged */
+ c->memory_deny_write_execute ||
+ c->restrict_realtime ||
+ c->protect_kernel_tunables ||
+ context_has_syscall_filters(c);
+}
+
static int send_user_lookup(
Unit *unit,
int user_lookup_fd,
@@ -1940,22 +2209,14 @@ static int exec_child(
} else {
if (context->user) {
username = context->user;
- r = get_user_creds(&username, &uid, &gid, &home, &shell);
+ r = get_user_creds_clean(&username, &uid, &gid, &home, &shell);
if (r < 0) {
*exit_status = EXIT_USER;
return r;
}
- /* Don't set $HOME or $SHELL if they are are not particularly enlightening anyway. */
- if (isempty(home) || path_equal(home, "/"))
- home = NULL;
-
- if (isempty(shell) || PATH_IN_SET(shell,
- "/bin/nologin",
- "/sbin/nologin",
- "/usr/bin/nologin",
- "/usr/sbin/nologin"))
- shell = NULL;
+ /* Note that we don't set $HOME or $SHELL if they are not particularly enlightening anyway
+ * (i.e. are "/" or "/bin/nologin"). */
}
if (context->group) {
@@ -2108,28 +2369,10 @@ static int exec_child(
}
if (!strv_isempty(context->runtime_directory) && params->runtime_prefix) {
- char **rt;
-
- STRV_FOREACH(rt, context->runtime_directory) {
- _cleanup_free_ char *p;
-
- p = strjoin(params->runtime_prefix, "/", *rt, NULL);
- if (!p) {
- *exit_status = EXIT_RUNTIME_DIRECTORY;
- return -ENOMEM;
- }
-
- r = mkdir_p_label(p, context->runtime_directory_mode);
- if (r < 0) {
- *exit_status = EXIT_RUNTIME_DIRECTORY;
- return r;
- }
-
- r = chmod_and_chown(p, context->runtime_directory_mode, uid, gid);
- if (r < 0) {
- *exit_status = EXIT_RUNTIME_DIRECTORY;
- return r;
- }
+ r = setup_runtime_directory(context, params, uid, gid);
+ if (r < 0) {
+ *exit_status = EXIT_RUNTIME_DIRECTORY;
+ return r;
}
}
@@ -2168,49 +2411,22 @@ static int exec_child(
}
accum_env = strv_env_clean(accum_env);
- umask(context->umask);
+ (void) umask(context->umask);
if ((params->flags & EXEC_APPLY_PERMISSIONS) && !command->privileged) {
- r = enforce_groups(context, username, gid);
+ r = setup_smack(context, command);
if (r < 0) {
- *exit_status = EXIT_GROUP;
+ *exit_status = EXIT_SMACK_PROCESS_LABEL;
return r;
}
-#ifdef HAVE_SMACK
- if (context->smack_process_label) {
- r = mac_smack_apply_pid(0, context->smack_process_label);
- if (r < 0) {
- *exit_status = EXIT_SMACK_PROCESS_LABEL;
- return r;
- }
- }
-#ifdef SMACK_DEFAULT_PROCESS_LABEL
- else {
- _cleanup_free_ char *exec_label = NULL;
-
- r = mac_smack_read(command->path, SMACK_ATTR_EXEC, &exec_label);
- if (r < 0 && r != -ENODATA && r != -EOPNOTSUPP) {
- *exit_status = EXIT_SMACK_PROCESS_LABEL;
- return r;
- }
- r = mac_smack_apply_pid(0, exec_label ? : SMACK_DEFAULT_PROCESS_LABEL);
- if (r < 0) {
- *exit_status = EXIT_SMACK_PROCESS_LABEL;
- return r;
- }
- }
-#endif
-#endif
-#ifdef HAVE_PAM
if (context->pam_name && username) {
- r = setup_pam(context->pam_name, username, uid, context->tty_path, &accum_env, fds, n_fds);
+ r = setup_pam(context->pam_name, username, uid, gid, context->tty_path, &accum_env, fds, n_fds);
if (r < 0) {
*exit_status = EXIT_PAM;
return r;
}
}
-#endif
}
if (context->private_network && runtime && runtime->netns_storage_socket[0] >= 0) {
@@ -2222,8 +2438,8 @@ static int exec_child(
}
needs_mount_namespace = exec_needs_mount_namespace(context, params, runtime);
-
if (needs_mount_namespace) {
+ _cleanup_free_ char **rw = NULL;
char *tmp = NULL, *var = NULL;
/* The runtime struct only contains the parent
@@ -2239,14 +2455,22 @@ static int exec_child(
var = strjoina(runtime->var_tmp_dir, "/tmp");
}
+ r = compile_read_write_paths(context, params, &rw);
+ if (r < 0) {
+ *exit_status = EXIT_NAMESPACE;
+ return r;
+ }
+
r = setup_namespace(
(params->flags & EXEC_APPLY_CHROOT) ? context->root_directory : NULL,
- context->read_write_paths,
+ rw,
context->read_only_paths,
context->inaccessible_paths,
tmp,
var,
context->private_devices,
+ context->protect_kernel_tunables,
+ context->protect_control_groups,
context->protect_home,
context->protect_system,
context->mount_flags);
@@ -2264,6 +2488,14 @@ static int exec_child(
}
}
+ if ((params->flags & EXEC_APPLY_PERMISSIONS) && !command->privileged) {
+ r = enforce_groups(context, username, gid);
+ if (r < 0) {
+ *exit_status = EXIT_GROUP;
+ return r;
+ }
+ }
+
if (context->working_directory_home)
wd = home;
else if (context->working_directory)
@@ -2335,11 +2567,6 @@ static int exec_child(
if ((params->flags & EXEC_APPLY_PERMISSIONS) && !command->privileged) {
- bool use_address_families = context->address_families_whitelist ||
- !set_isempty(context->address_families);
- bool use_syscall_filter = context->syscall_whitelist ||
- !set_isempty(context->syscall_filter) ||
- !set_isempty(context->syscall_archs);
int secure_bits = context->secure_bits;
for (i = 0; i < _RLIMIT_MAX; i++) {
@@ -2416,15 +2643,14 @@ static int exec_child(
return -errno;
}
- if (context->no_new_privileges ||
- (!have_effective_cap(CAP_SYS_ADMIN) && (use_address_families || context->memory_deny_write_execute || context->restrict_realtime || use_syscall_filter)))
+ if (context_has_no_new_privileges(context))
if (prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0) < 0) {
*exit_status = EXIT_NO_NEW_PRIVILEGES;
return -errno;
}
#ifdef HAVE_SECCOMP
- if (use_address_families) {
+ if (context_has_address_families(context)) {
r = apply_address_families(unit, context);
if (r < 0) {
*exit_status = EXIT_ADDRESS_FAMILIES;
@@ -2448,7 +2674,23 @@ static int exec_child(
}
}
- if (use_syscall_filter) {
+ if (context->protect_kernel_tunables) {
+ r = apply_protect_sysctl(unit, context);
+ if (r < 0) {
+ *exit_status = EXIT_SECCOMP;
+ return r;
+ }
+ }
+
+ if (context->private_devices) {
+ r = apply_private_devices(unit, context);
+ if (r < 0) {
+ *exit_status = EXIT_SECCOMP;
+ return r;
+ }
+ }
+
+ if (context_has_syscall_filters(context)) {
r = apply_seccomp(unit, context);
if (r < 0) {
*exit_status = EXIT_SECCOMP;
@@ -2880,6 +3122,8 @@ void exec_context_dump(ExecContext *c, FILE* f, const char *prefix) {
"%sNonBlocking: %s\n"
"%sPrivateTmp: %s\n"
"%sPrivateDevices: %s\n"
+ "%sProtectKernelTunables: %s\n"
+ "%sProtectControlGroups: %s\n"
"%sPrivateNetwork: %s\n"
"%sPrivateUsers: %s\n"
"%sProtectHome: %s\n"
@@ -2893,6 +3137,8 @@ void exec_context_dump(ExecContext *c, FILE* f, const char *prefix) {
prefix, yes_no(c->non_blocking),
prefix, yes_no(c->private_tmp),
prefix, yes_no(c->private_devices),
+ prefix, yes_no(c->protect_kernel_tunables),
+ prefix, yes_no(c->protect_control_groups),
prefix, yes_no(c->private_network),
prefix, yes_no(c->private_users),
prefix, protect_home_to_string(c->protect_home),
diff --git a/src/core/execute.h b/src/core/execute.h
index 6082c42aba..449180c903 100644
--- a/src/core/execute.h
+++ b/src/core/execute.h
@@ -174,6 +174,8 @@ struct ExecContext {
bool private_users;
ProtectSystem protect_system;
ProtectHome protect_home;
+ bool protect_kernel_tunables;
+ bool protect_control_groups;
bool no_new_privileges;
diff --git a/src/core/load-fragment-gperf.gperf.m4 b/src/core/load-fragment-gperf.gperf.m4
index 2e6c965aec..c49c1d6732 100644
--- a/src/core/load-fragment-gperf.gperf.m4
+++ b/src/core/load-fragment-gperf.gperf.m4
@@ -89,6 +89,8 @@ $1.ReadOnlyPaths, config_parse_namespace_path_strv, 0,
$1.InaccessiblePaths, config_parse_namespace_path_strv, 0, offsetof($1, exec_context.inaccessible_paths)
$1.PrivateTmp, config_parse_bool, 0, offsetof($1, exec_context.private_tmp)
$1.PrivateDevices, config_parse_bool, 0, offsetof($1, exec_context.private_devices)
+$1.ProtectKernelTunables, config_parse_bool, 0, offsetof($1, exec_context.protect_kernel_tunables)
+$1.ProtectControlGroups, config_parse_bool, 0, offsetof($1, exec_context.protect_control_groups)
$1.PrivateNetwork, config_parse_bool, 0, offsetof($1, exec_context.private_network)
$1.PrivateUsers, config_parse_bool, 0, offsetof($1, exec_context.private_users)
$1.ProtectSystem, config_parse_protect_system, 0, offsetof($1, exec_context)
diff --git a/src/core/main.c b/src/core/main.c
index 7d8322ebd8..4b82a57b3c 100644
--- a/src/core/main.c
+++ b/src/core/main.c
@@ -131,6 +131,7 @@ static bool arg_default_memory_accounting = false;
static bool arg_default_tasks_accounting = true;
static uint64_t arg_default_tasks_max = UINT64_MAX;
static sd_id128_t arg_machine_id = {};
+static CADBurstAction arg_cad_burst_action = CAD_BURST_ACTION_REBOOT;
noreturn static void freeze_or_reboot(void) {
@@ -202,7 +203,7 @@ noreturn static void crash(int sig) {
pid, sigchld_code_to_string(status.si_code),
status.si_status,
strna(status.si_code == CLD_EXITED
- ? exit_status_to_string(status.si_status, EXIT_STATUS_FULL)
+ ? exit_status_to_string(status.si_status, EXIT_STATUS_MINIMAL)
: signal_to_string(status.si_status)));
else
log_emergency("Caught <%s>, dumped core as pid "PID_FMT".", signal_to_string(sig), pid);
@@ -648,6 +649,8 @@ static int config_parse_join_controllers(const char *unit,
return 0;
}
+static DEFINE_CONFIG_PARSE_ENUM(config_parse_cad_burst_action, cad_burst_action, CADBurstAction, "Failed to parse service restart specifier");
+
static int parse_config_file(void) {
const ConfigTableItem items[] = {
@@ -702,6 +705,7 @@ static int parse_config_file(void) {
{ "Manager", "DefaultMemoryAccounting", config_parse_bool, 0, &arg_default_memory_accounting },
{ "Manager", "DefaultTasksAccounting", config_parse_bool, 0, &arg_default_tasks_accounting },
{ "Manager", "DefaultTasksMax", config_parse_tasks_max, 0, &arg_default_tasks_max },
+ { "Manager", "CtrlAltDelBurstAction", config_parse_cad_burst_action, 0, &arg_cad_burst_action},
{}
};
@@ -715,7 +719,7 @@ static int parse_config_file(void) {
CONF_PATHS_NULSTR("systemd/system.conf.d") :
CONF_PATHS_NULSTR("systemd/user.conf.d");
- config_parse_many(fn, conf_dirs_nulstr, "Manager\0", config_item_table_lookup, items, false, NULL);
+ config_parse_many_nulstr(fn, conf_dirs_nulstr, "Manager\0", config_item_table_lookup, items, false, NULL);
/* Traditionally "0" was used to turn off the default unit timeouts. Fix this up so that we used USEC_INFINITY
* like everywhere else. */
@@ -996,10 +1000,8 @@ static int parse_argv(int argc, char *argv[]) {
case ARG_MACHINE_ID:
r = set_machine_id(optarg);
- if (r < 0) {
- log_error("MachineID '%s' is not valid.", optarg);
- return r;
- }
+ if (r < 0)
+ return log_error_errno(r, "MachineID '%s' is not valid.", optarg);
break;
case 'h':
@@ -1530,15 +1532,9 @@ int main(int argc, char *argv[]) {
* need to do that for user instances since they never log
* into the console. */
log_show_color(colors_enabled());
- make_null_stdio();
- }
-
- /* Initialize default unit */
- r = free_and_strdup(&arg_default_unit, SPECIAL_DEFAULT_TARGET);
- if (r < 0) {
- log_emergency_errno(r, "Failed to set default unit %s: %m", SPECIAL_DEFAULT_TARGET);
- error_message = "Failed to set default unit";
- goto finish;
+ r = make_null_stdio();
+ if (r < 0)
+ log_warning_errno(r, "Failed to redirect standard streams to /dev/null: %m");
}
r = initialize_join_controllers();
@@ -1588,6 +1584,16 @@ int main(int argc, char *argv[]) {
goto finish;
}
+ /* Initialize default unit */
+ if (!arg_default_unit) {
+ arg_default_unit = strdup(SPECIAL_DEFAULT_TARGET);
+ if (!arg_default_unit) {
+ r = log_oom();
+ error_message = "Failed to set default unit";
+ goto finish;
+ }
+ }
+
if (arg_action == ACTION_TEST &&
geteuid() == 0) {
log_error("Don't run test mode as root.");
@@ -1796,6 +1802,7 @@ int main(int argc, char *argv[]) {
m->initrd_timestamp = initrd_timestamp;
m->security_start_timestamp = security_start_timestamp;
m->security_finish_timestamp = security_finish_timestamp;
+ m->cad_burst_action = arg_cad_burst_action;
manager_set_defaults(m);
manager_set_show_status(m, arg_show_status);
diff --git a/src/core/manager.c b/src/core/manager.c
index b58f68fa7a..c1dce62a18 100644
--- a/src/core/manager.c
+++ b/src/core/manager.c
@@ -590,7 +590,7 @@ int manager_new(UnitFileScope scope, bool test_run, Manager **_m) {
m->idle_pipe[0] = m->idle_pipe[1] = m->idle_pipe[2] = m->idle_pipe[3] = -1;
m->pin_cgroupfs_fd = m->notify_fd = m->cgroups_agent_fd = m->signal_fd = m->time_change_fd =
- m->dev_autofs_fd = m->private_listen_fd = m->kdbus_fd = m->cgroup_inotify_fd =
+ m->dev_autofs_fd = m->private_listen_fd = m->cgroup_inotify_fd =
m->ask_password_inotify_fd = -1;
m->user_lookup_fds[0] = m->user_lookup_fds[1] = -1;
@@ -661,9 +661,8 @@ int manager_new(UnitFileScope scope, bool test_run, Manager **_m) {
goto fail;
}
- /* Note that we set up neither kdbus, nor the notify fd
- * here. We do that after deserialization, since they might
- * have gotten serialized across the reexec. */
+ /* Note that we do not set up the notify fd here. We do that after deserialization,
+ * since they might have gotten serialized across the reexec. */
m->taint_usr = dir_is_empty("/usr") > 0;
@@ -879,7 +878,6 @@ static int manager_connect_bus(Manager *m, bool reexecuting) {
return 0;
try_bus_connect =
- m->kdbus_fd >= 0 ||
reexecuting ||
(MANAGER_IS_USER(m) && getenv("DBUS_SESSION_BUS_ADDRESS"));
@@ -1084,7 +1082,6 @@ Manager* manager_free(Manager *m) {
safe_close(m->notify_fd);
safe_close(m->cgroups_agent_fd);
safe_close(m->time_change_fd);
- safe_close(m->kdbus_fd);
safe_close_pair(m->user_lookup_fds);
manager_close_ask_password(m);
@@ -1239,9 +1236,11 @@ int manager_startup(Manager *m, FILE *serialization, FDSet *fds) {
return r;
/* Make sure the transient directory always exists, so that it remains in the search path */
- r = mkdir_p_label(m->lookup_paths.transient, 0755);
- if (r < 0)
- return r;
+ if (!m->test_run) {
+ r = mkdir_p_label(m->lookup_paths.transient, 0755);
+ if (r < 0)
+ return r;
+ }
dual_timestamp_get(&m->generators_start_timestamp);
r = manager_run_generators(m);
@@ -1287,7 +1286,7 @@ int manager_startup(Manager *m, FILE *serialization, FDSet *fds) {
if (q < 0 && r == 0)
r = q;
- /* We might have deserialized the kdbus control fd, but if we didn't, then let's create the bus now. */
+ /* Let's connect to the bus now. */
(void) manager_connect_bus(m, !!serialization);
(void) bus_track_coldplug(m, &m->subscribed, false, m->deserialized_subscribed);
@@ -1660,13 +1659,12 @@ static int manager_dispatch_cgroups_agent_fd(sd_event_source *source, int fd, ui
return 0;
}
-static void manager_invoke_notify_message(Manager *m, Unit *u, pid_t pid, const char *buf, size_t n, FDSet *fds) {
+static void manager_invoke_notify_message(Manager *m, Unit *u, pid_t pid, const char *buf, FDSet *fds) {
_cleanup_strv_free_ char **tags = NULL;
assert(m);
assert(u);
assert(buf);
- assert(n > 0);
tags = strv_split(buf, "\n\r");
if (!tags) {
@@ -1676,8 +1674,14 @@ static void manager_invoke_notify_message(Manager *m, Unit *u, pid_t pid, const
if (UNIT_VTABLE(u)->notify_message)
UNIT_VTABLE(u)->notify_message(u, pid, tags, fds);
- else
- log_unit_debug(u, "Got notification message for unit. Ignoring.");
+ else if (_unlikely_(log_get_max_level() >= LOG_DEBUG)) {
+ _cleanup_free_ char *x = NULL, *y = NULL;
+
+ x = cescape(buf);
+ if (x)
+ y = ellipsize(x, 20, 90);
+ log_unit_debug(u, "Got notification message \"%s\", ignoring.", strnull(y));
+ }
}
static int manager_dispatch_notify_fd(sd_event_source *source, int fd, uint32_t revents, void *userdata) {
@@ -1703,7 +1707,6 @@ static int manager_dispatch_notify_fd(sd_event_source *source, int fd, uint32_t
struct cmsghdr *cmsg;
struct ucred *ucred = NULL;
- bool found = false;
Unit *u1, *u2, *u3;
int r, *fd_array = NULL;
unsigned n_fds = 0;
@@ -1717,12 +1720,15 @@ static int manager_dispatch_notify_fd(sd_event_source *source, int fd, uint32_t
return 0;
}
- n = recvmsg(m->notify_fd, &msghdr, MSG_DONTWAIT|MSG_CMSG_CLOEXEC);
+ n = recvmsg(m->notify_fd, &msghdr, MSG_DONTWAIT|MSG_CMSG_CLOEXEC|MSG_TRUNC);
if (n < 0) {
- if (errno == EAGAIN || errno == EINTR)
- return 0;
+ if (IN_SET(errno, EAGAIN, EINTR))
+ return 0; /* Spurious wakeup, try again */
- return -errno;
+ /* If this is any other, real error, then let's stop processing this socket. This of course means we
+ * won't take notification messages anymore, but that's still better than busy looping around this:
+ * being woken up over and over again but being unable to actually read the message off the socket. */
+ return log_error_errno(errno, "Failed to receive notification message: %m");
}
CMSG_FOREACH(cmsg, &msghdr) {
@@ -1745,7 +1751,8 @@ static int manager_dispatch_notify_fd(sd_event_source *source, int fd, uint32_t
r = fdset_new_array(&fds, fd_array, n_fds);
if (r < 0) {
close_many(fd_array, n_fds);
- return log_oom();
+ log_oom();
+ return 0;
}
}
@@ -1754,38 +1761,40 @@ static int manager_dispatch_notify_fd(sd_event_source *source, int fd, uint32_t
return 0;
}
- if ((size_t) n >= sizeof(buf)) {
+ if ((size_t) n >= sizeof(buf) || (msghdr.msg_flags & MSG_TRUNC)) {
log_warning("Received notify message exceeded maximum size. Ignoring.");
return 0;
}
+ /* As extra safety check, let's make sure the string we get doesn't contain embedded NUL bytes. We permit one
+ * trailing NUL byte in the message, but don't expect it. */
+ if (n > 1 && memchr(buf, 0, n-1)) {
+ log_warning("Received notify message with embedded NUL bytes. Ignoring.");
+ return 0;
+ }
+
+ /* Make sure it's NUL-terminated. */
buf[n] = 0;
/* Notify every unit that might be interested, but try
* to avoid notifying the same one multiple times. */
u1 = manager_get_unit_by_pid_cgroup(m, ucred->pid);
- if (u1) {
- manager_invoke_notify_message(m, u1, ucred->pid, buf, n, fds);
- found = true;
- }
+ if (u1)
+ manager_invoke_notify_message(m, u1, ucred->pid, buf, fds);
u2 = hashmap_get(m->watch_pids1, PID_TO_PTR(ucred->pid));
- if (u2 && u2 != u1) {
- manager_invoke_notify_message(m, u2, ucred->pid, buf, n, fds);
- found = true;
- }
+ if (u2 && u2 != u1)
+ manager_invoke_notify_message(m, u2, ucred->pid, buf, fds);
u3 = hashmap_get(m->watch_pids2, PID_TO_PTR(ucred->pid));
- if (u3 && u3 != u2 && u3 != u1) {
- manager_invoke_notify_message(m, u3, ucred->pid, buf, n, fds);
- found = true;
- }
+ if (u3 && u3 != u2 && u3 != u1)
+ manager_invoke_notify_message(m, u3, ucred->pid, buf, fds);
- if (!found)
+ if (!u1 && !u2 && !u3)
log_warning("Cannot find unit for notify message of PID "PID_FMT".", ucred->pid);
if (fdset_size(fds) > 0)
- log_warning("Got auxiliary fds with notification message, closing all.");
+ log_warning("Got extra auxiliary fds with notification message, closing them.");
return 0;
}
@@ -1890,6 +1899,35 @@ static int manager_start_target(Manager *m, const char *name, JobMode mode) {
return r;
}
+static void manager_handle_ctrl_alt_del(Manager *m) {
+ /* If the user presses C-A-D more than
+ * 7 times within 2s, we reboot/shutdown immediately,
+ * unless it was disabled in system.conf */
+
+ if (ratelimit_test(&m->ctrl_alt_del_ratelimit) || m->cad_burst_action == CAD_BURST_ACTION_IGNORE)
+ manager_start_target(m, SPECIAL_CTRL_ALT_DEL_TARGET, JOB_REPLACE_IRREVERSIBLY);
+ else {
+ switch (m->cad_burst_action) {
+
+ case CAD_BURST_ACTION_REBOOT:
+ m->exit_code = MANAGER_REBOOT;
+ break;
+
+ case CAD_BURST_ACTION_POWEROFF:
+ m->exit_code = MANAGER_POWEROFF;
+ break;
+
+ default:
+ assert_not_reached("Unknown action.");
+ }
+
+ log_notice("Ctrl-Alt-Del was pressed more than 7 times within 2s, performing immediate %s.",
+ cad_burst_action_to_string(m->cad_burst_action));
+ status_printf(NULL, true, false, "Ctrl-Alt-Del was pressed more than 7 times within 2s, performing immediate %s.",
+ cad_burst_action_to_string(m->cad_burst_action));
+ }
+}
+
static int manager_dispatch_signal_fd(sd_event_source *source, int fd, uint32_t revents, void *userdata) {
Manager *m = userdata;
ssize_t n;
@@ -1908,14 +1946,17 @@ static int manager_dispatch_signal_fd(sd_event_source *source, int fd, uint32_t
for (;;) {
n = read(m->signal_fd, &sfsi, sizeof(sfsi));
if (n != sizeof(sfsi)) {
+ if (n >= 0) {
+ log_warning("Truncated read from signal fd (%zu bytes)!", n);
+ return 0;
+ }
- if (n >= 0)
- return -EIO;
-
- if (errno == EINTR || errno == EAGAIN)
+ if (IN_SET(errno, EINTR, EAGAIN))
break;
- return -errno;
+ /* We return an error here, which will kill this handler,
+ * to avoid a busy loop on read error. */
+ return log_error_errno(errno, "Reading from signal fd failed: %m");
}
log_received_signal(sfsi.ssi_signo == SIGCHLD ||
@@ -1941,19 +1982,7 @@ static int manager_dispatch_signal_fd(sd_event_source *source, int fd, uint32_t
case SIGINT:
if (MANAGER_IS_SYSTEM(m)) {
-
- /* If the user presses C-A-D more than
- * 7 times within 2s, we reboot
- * immediately. */
-
- if (ratelimit_test(&m->ctrl_alt_del_ratelimit))
- manager_start_target(m, SPECIAL_CTRL_ALT_DEL_TARGET, JOB_REPLACE_IRREVERSIBLY);
- else {
- log_notice("Ctrl-Alt-Del was pressed more than 7 times within 2s, rebooting immediately.");
- status_printf(NULL, true, false, "Ctrl-Alt-Del was pressed more than 7 times within 2s, rebooting immediately.");
- m->exit_code = MANAGER_REBOOT;
- }
-
+ manager_handle_ctrl_alt_del(m);
break;
}
@@ -2481,16 +2510,6 @@ int manager_serialize(Manager *m, FILE *f, FDSet *fds, bool switching_root) {
fprintf(f, "user-lookup=%i %i\n", copy0, copy1);
}
- if (m->kdbus_fd >= 0) {
- int copy;
-
- copy = fdset_put_dup(fds, m->kdbus_fd);
- if (copy < 0)
- return copy;
-
- fprintf(f, "kdbus-fd=%i\n", copy);
- }
-
bus_track_serialize(m->subscribed, f, "subscribed");
r = dynamic_user_serialize(m, f, fds);
@@ -2678,16 +2697,6 @@ int manager_deserialize(Manager *m, FILE *f, FDSet *fds) {
m->user_lookup_fds[1] = fdset_remove(fds, fd1);
}
- } else if (startswith(l, "kdbus-fd=")) {
- int fd;
-
- if (safe_atoi(l + 9, &fd) < 0 || fd < 0 || !fdset_contains(fds, fd))
- log_debug("Failed to parse kdbus fd: %s", l + 9);
- else {
- safe_close(m->kdbus_fd);
- m->kdbus_fd = fdset_remove(fds, fd);
- }
-
} else if (startswith(l, "dynamic-user="))
dynamic_user_deserialize_one(m, l + 13, fds);
else if (startswith(l, "destroy-ipc-uid="))
@@ -2699,7 +2708,7 @@ int manager_deserialize(Manager *m, FILE *f, FDSet *fds) {
if (strv_extend(&m->deserialized_subscribed, l+11) < 0)
log_oom();
- } else
+ } else if (!startswith(l, "kdbus-fd=")) /* ignore this one */
log_debug("Unknown serialization item '%s'", l);
}
@@ -3560,3 +3569,11 @@ static const char *const manager_state_table[_MANAGER_STATE_MAX] = {
};
DEFINE_STRING_TABLE_LOOKUP(manager_state, ManagerState);
+
+static const char *const cad_burst_action_table[_CAD_BURST_ACTION_MAX] = {
+ [CAD_BURST_ACTION_IGNORE] = "ignore",
+ [CAD_BURST_ACTION_REBOOT] = "reboot-force",
+ [CAD_BURST_ACTION_POWEROFF] = "poweroff-force",
+};
+
+DEFINE_STRING_TABLE_LOOKUP(cad_burst_action, CADBurstAction);
diff --git a/src/core/manager.h b/src/core/manager.h
index b9f2e4b5a1..495440b446 100644
--- a/src/core/manager.h
+++ b/src/core/manager.h
@@ -62,6 +62,14 @@ typedef enum ManagerExitCode {
_MANAGER_EXIT_CODE_INVALID = -1
} ManagerExitCode;
+typedef enum CADBurstAction {
+ CAD_BURST_ACTION_IGNORE,
+ CAD_BURST_ACTION_REBOOT,
+ CAD_BURST_ACTION_POWEROFF,
+ _CAD_BURST_ACTION_MAX,
+ _CAD_BURST_ACTION_INVALID = -1
+} CADBurstAction;
+
typedef enum StatusType {
STATUS_TYPE_EPHEMERAL,
STATUS_TYPE_NORMAL,
@@ -294,9 +302,6 @@ struct Manager {
* value where Unit objects are contained. */
Hashmap *units_requiring_mounts_for;
- /* Reference to the kdbus bus control fd */
- int kdbus_fd;
-
/* Used for processing polkit authorization responses */
Hashmap *polkit_registry;
@@ -307,8 +312,9 @@ struct Manager {
Hashmap *uid_refs;
Hashmap *gid_refs;
- /* When the user hits C-A-D more than 7 times per 2s, reboot immediately... */
+ /* When the user hits C-A-D more than 7 times per 2s, do something immediately... */
RateLimit ctrl_alt_del_ratelimit;
+ CADBurstAction cad_burst_action;
const char *unit_log_field;
const char *unit_log_format_string;
@@ -401,3 +407,6 @@ void manager_deserialize_gid_refs_one(Manager *m, const char *value);
const char *manager_state_to_string(ManagerState m) _const_;
ManagerState manager_state_from_string(const char *s) _pure_;
+
+const char *cad_burst_action_to_string(CADBurstAction a) _const_;
+CADBurstAction cad_burst_action_from_string(const char *s) _pure_;
diff --git a/src/core/mount.c b/src/core/mount.c
index 04025b83b9..f5e67b1d78 100644
--- a/src/core/mount.c
+++ b/src/core/mount.c
@@ -830,7 +830,7 @@ static void mount_enter_signal(Mount *m, MountState state, MountResult f) {
fail:
log_unit_warning_errno(UNIT(m), r, "Failed to kill processes: %m");
- if (state == MOUNT_REMOUNTING_SIGTERM || state == MOUNT_REMOUNTING_SIGKILL)
+ if (IN_SET(state, MOUNT_REMOUNTING_SIGTERM, MOUNT_REMOUNTING_SIGKILL))
mount_enter_mounted(m, MOUNT_FAILURE_RESOURCES);
else
mount_enter_dead(m, MOUNT_FAILURE_RESOURCES);
@@ -986,18 +986,19 @@ static int mount_start(Unit *u) {
/* We cannot fulfill this request right now, try again later
* please! */
- if (m->state == MOUNT_UNMOUNTING ||
- m->state == MOUNT_UNMOUNTING_SIGTERM ||
- m->state == MOUNT_UNMOUNTING_SIGKILL ||
- m->state == MOUNT_MOUNTING_SIGTERM ||
- m->state == MOUNT_MOUNTING_SIGKILL)
+ if (IN_SET(m->state,
+ MOUNT_UNMOUNTING,
+ MOUNT_UNMOUNTING_SIGTERM,
+ MOUNT_UNMOUNTING_SIGKILL,
+ MOUNT_MOUNTING_SIGTERM,
+ MOUNT_MOUNTING_SIGKILL))
return -EAGAIN;
/* Already on it! */
if (m->state == MOUNT_MOUNTING)
return 0;
- assert(m->state == MOUNT_DEAD || m->state == MOUNT_FAILED);
+ assert(IN_SET(m->state, MOUNT_DEAD, MOUNT_FAILED));
r = unit_start_limit_test(u);
if (r < 0) {
@@ -1019,19 +1020,21 @@ static int mount_stop(Unit *u) {
assert(m);
/* Already on it */
- if (m->state == MOUNT_UNMOUNTING ||
- m->state == MOUNT_UNMOUNTING_SIGKILL ||
- m->state == MOUNT_UNMOUNTING_SIGTERM ||
- m->state == MOUNT_MOUNTING_SIGTERM ||
- m->state == MOUNT_MOUNTING_SIGKILL)
+ if (IN_SET(m->state,
+ MOUNT_UNMOUNTING,
+ MOUNT_UNMOUNTING_SIGKILL,
+ MOUNT_UNMOUNTING_SIGTERM,
+ MOUNT_MOUNTING_SIGTERM,
+ MOUNT_MOUNTING_SIGKILL))
return 0;
- assert(m->state == MOUNT_MOUNTING ||
- m->state == MOUNT_MOUNTING_DONE ||
- m->state == MOUNT_MOUNTED ||
- m->state == MOUNT_REMOUNTING ||
- m->state == MOUNT_REMOUNTING_SIGTERM ||
- m->state == MOUNT_REMOUNTING_SIGKILL);
+ assert(IN_SET(m->state,
+ MOUNT_MOUNTING,
+ MOUNT_MOUNTING_DONE,
+ MOUNT_MOUNTED,
+ MOUNT_REMOUNTING,
+ MOUNT_REMOUNTING_SIGTERM,
+ MOUNT_REMOUNTING_SIGKILL));
mount_enter_unmounting(m);
return 1;
@@ -1159,7 +1162,7 @@ static void mount_sigchld_event(Unit *u, pid_t pid, int code, int status) {
m->control_pid = 0;
- if (is_clean_exit(code, status, NULL))
+ if (is_clean_exit(code, status, EXIT_CLEAN_COMMAND, NULL))
f = MOUNT_SUCCESS;
else if (code == CLD_EXITED)
f = MOUNT_FAILURE_EXIT_CODE;
@@ -1197,9 +1200,10 @@ static void mount_sigchld_event(Unit *u, pid_t pid, int code, int status) {
case MOUNT_MOUNTING_SIGKILL:
case MOUNT_MOUNTING_SIGTERM:
- if (f == MOUNT_SUCCESS)
- mount_enter_mounted(m, f);
- else if (m->from_proc_self_mountinfo)
+ if (f == MOUNT_SUCCESS || m->from_proc_self_mountinfo)
+ /* If /bin/mount returned success, or if we see the mount point in /proc/self/mountinfo we are
+ * happy. If we see the first condition first, we should see the the second condition
+ * immediately after – or /bin/mount lies to us and is broken. */
mount_enter_mounted(m, f);
else
mount_enter_dead(m, f);
diff --git a/src/core/namespace.c b/src/core/namespace.c
index 52a2505d94..43a2f4ba6e 100644
--- a/src/core/namespace.c
+++ b/src/core/namespace.c
@@ -29,6 +29,7 @@
#include "alloc-util.h"
#include "dev-setup.h"
#include "fd-util.h"
+#include "fs-util.h"
#include "loopback-setup.h"
#include "missing.h"
#include "mkdir.h"
@@ -53,61 +54,230 @@ typedef enum MountMode {
PRIVATE_TMP,
PRIVATE_VAR_TMP,
PRIVATE_DEV,
- READWRITE
+ READWRITE,
} MountMode;
typedef struct BindMount {
- const char *path;
+ const char *path; /* stack memory, doesn't need to be freed explicitly */
+ char *chased; /* malloc()ed memory, needs to be freed */
MountMode mode;
- bool done;
- bool ignore;
+ bool ignore; /* Ignore if path does not exist */
} BindMount;
+typedef struct TargetMount {
+ const char *path;
+ MountMode mode;
+ bool ignore; /* Ignore if path does not exist */
+} TargetMount;
+
+/*
+ * The following Protect tables are to protect paths and mark some of them
+ * READONLY, in case a path is covered by an option from another table, then
+ * it is marked READWRITE in the current one, and the more restrictive mode is
+ * applied from that other table. This way all options can be combined in a
+ * safe and comprehensible way for users.
+ */
+
+/* ProtectKernelTunables= option and the related filesystem APIs */
+static const TargetMount protect_kernel_tunables_table[] = {
+ { "/proc/sys", READONLY, false },
+ { "/proc/sysrq-trigger", READONLY, true },
+ { "/proc/latency_stats", READONLY, true },
+ { "/proc/mtrr", READONLY, true },
+ { "/proc/apm", READONLY, true },
+ { "/proc/acpi", READONLY, true },
+ { "/proc/timer_stats", READONLY, true },
+ { "/proc/asound", READONLY, true },
+ { "/proc/bus", READONLY, true },
+ { "/proc/fs", READONLY, true },
+ { "/proc/irq", READONLY, true },
+ { "/sys", READONLY, false },
+ { "/sys/kernel/debug", READONLY, true },
+ { "/sys/kernel/tracing", READONLY, true },
+ { "/sys/fs/cgroup", READWRITE, false }, /* READONLY is set by ProtectControlGroups= option */
+};
+
+/*
+ * ProtectHome=read-only table, protect $HOME and $XDG_RUNTIME_DIR and rest of
+ * system should be protected by ProtectSystem=
+ */
+static const TargetMount protect_home_read_only_table[] = {
+ { "/home", READONLY, true },
+ { "/run/user", READONLY, true },
+ { "/root", READONLY, true },
+};
+
+/* ProtectHome=yes table */
+static const TargetMount protect_home_yes_table[] = {
+ { "/home", INACCESSIBLE, true },
+ { "/run/user", INACCESSIBLE, true },
+ { "/root", INACCESSIBLE, true },
+};
+
+/* ProtectSystem=yes table */
+static const TargetMount protect_system_yes_table[] = {
+ { "/usr", READONLY, false },
+ { "/boot", READONLY, true },
+ { "/efi", READONLY, true },
+};
+
+/* ProtectSystem=full includes ProtectSystem=yes */
+static const TargetMount protect_system_full_table[] = {
+ { "/usr", READONLY, false },
+ { "/boot", READONLY, true },
+ { "/efi", READONLY, true },
+ { "/etc", READONLY, false },
+};
+
+/*
+ * ProtectSystem=strict table. In this strict mode, we mount everything
+ * read-only, except for /proc, /dev, /sys which are the kernel API VFS,
+ * which are left writable, but PrivateDevices= + ProtectKernelTunables=
+ * protect those, and these options should be fully orthogonal.
+ * (And of course /home and friends are also left writable, as ProtectHome=
+ * shall manage those, orthogonally).
+ */
+static const TargetMount protect_system_strict_table[] = {
+ { "/", READONLY, false },
+ { "/proc", READWRITE, false }, /* ProtectKernelTunables= */
+ { "/sys", READWRITE, false }, /* ProtectKernelTunables= */
+ { "/dev", READWRITE, false }, /* PrivateDevices= */
+ { "/home", READWRITE, true }, /* ProtectHome= */
+ { "/run/user", READWRITE, true }, /* ProtectHome= */
+ { "/root", READWRITE, true }, /* ProtectHome= */
+};
+
+static void set_bind_mount(BindMount **p, const char *path, MountMode mode, bool ignore) {
+ (*p)->path = path;
+ (*p)->mode = mode;
+ (*p)->ignore = ignore;
+}
+
static int append_mounts(BindMount **p, char **strv, MountMode mode) {
char **i;
assert(p);
STRV_FOREACH(i, strv) {
+ bool ignore = false;
- (*p)->ignore = false;
- (*p)->done = false;
-
- if ((mode == INACCESSIBLE || mode == READONLY || mode == READWRITE) && (*i)[0] == '-') {
- (*p)->ignore = true;
+ if (IN_SET(mode, INACCESSIBLE, READONLY, READWRITE) && startswith(*i, "-")) {
(*i)++;
+ ignore = true;
}
if (!path_is_absolute(*i))
return -EINVAL;
- (*p)->path = *i;
- (*p)->mode = mode;
+ set_bind_mount(p, *i, mode, ignore);
(*p)++;
}
return 0;
}
-static int mount_path_compare(const void *a, const void *b) {
- const BindMount *p = a, *q = b;
- int d;
+static int append_target_mounts(BindMount **p, const char *root_directory, const TargetMount *mounts, const size_t size) {
+ unsigned i;
- d = path_compare(p->path, q->path);
+ assert(p);
+ assert(mounts);
+
+ for (i = 0; i < size; i++) {
+ /*
+ * Here we assume that the ignore field is set during
+ * declaration we do not support "-" at the beginning.
+ */
+ const TargetMount *m = &mounts[i];
+ const char *path = prefix_roota(root_directory, m->path);
+
+ if (!path_is_absolute(path))
+ return -EINVAL;
+
+ set_bind_mount(p, path, m->mode, m->ignore);
+ (*p)++;
+ }
+
+ return 0;
+}
+
+static int append_protect_kernel_tunables(BindMount **p, const char *root_directory) {
+ assert(p);
+
+ return append_target_mounts(p, root_directory, protect_kernel_tunables_table,
+ ELEMENTSOF(protect_kernel_tunables_table));
+}
- if (d == 0) {
- /* If the paths are equal, check the mode */
- if (p->mode < q->mode)
- return -1;
+static int append_protect_home(BindMount **p, const char *root_directory, ProtectHome protect_home) {
+ int r = 0;
- if (p->mode > q->mode)
- return 1;
+ assert(p);
+ if (protect_home == PROTECT_HOME_NO)
return 0;
+
+ switch (protect_home) {
+ case PROTECT_HOME_READ_ONLY:
+ r = append_target_mounts(p, root_directory, protect_home_read_only_table,
+ ELEMENTSOF(protect_home_read_only_table));
+ break;
+ case PROTECT_HOME_YES:
+ r = append_target_mounts(p, root_directory, protect_home_yes_table,
+ ELEMENTSOF(protect_home_yes_table));
+ break;
+ default:
+ r = -EINVAL;
+ break;
}
+ return r;
+}
+
+static int append_protect_system(BindMount **p, const char *root_directory, ProtectSystem protect_system) {
+ int r = 0;
+
+ assert(p);
+
+ if (protect_system == PROTECT_SYSTEM_NO)
+ return 0;
+
+ switch (protect_system) {
+ case PROTECT_SYSTEM_STRICT:
+ r = append_target_mounts(p, root_directory, protect_system_strict_table,
+ ELEMENTSOF(protect_system_strict_table));
+ break;
+ case PROTECT_SYSTEM_YES:
+ r = append_target_mounts(p, root_directory, protect_system_yes_table,
+ ELEMENTSOF(protect_system_yes_table));
+ break;
+ case PROTECT_SYSTEM_FULL:
+ r = append_target_mounts(p, root_directory, protect_system_full_table,
+ ELEMENTSOF(protect_system_full_table));
+ break;
+ default:
+ r = -EINVAL;
+ break;
+ }
+
+ return r;
+}
+
+static int mount_path_compare(const void *a, const void *b) {
+ const BindMount *p = a, *q = b;
+ int d;
+
/* If the paths are not equal, then order prefixes first */
- return d;
+ d = path_compare(p->path, q->path);
+ if (d != 0)
+ return d;
+
+ /* If the paths are equal, check the mode */
+ if (p->mode < q->mode)
+ return -1;
+
+ if (p->mode > q->mode)
+ return 1;
+
+ return 0;
}
static void drop_duplicates(BindMount *m, unsigned *n) {
@@ -116,16 +286,110 @@ static void drop_duplicates(BindMount *m, unsigned *n) {
assert(m);
assert(n);
+ /* Drops duplicate entries. Expects that the array is properly ordered already. */
+
for (f = m, t = m, previous = NULL; f < m+*n; f++) {
- /* The first one wins */
- if (previous && path_equal(f->path, previous->path))
+ /* The first one wins (which is the one with the more restrictive mode), see mount_path_compare()
+ * above. */
+ if (previous && path_equal(f->path, previous->path)) {
+ log_debug("%s is duplicate.", f->path);
continue;
+ }
*t = *f;
-
previous = t;
+ t++;
+ }
+
+ *n = t - m;
+}
+
+static void drop_inaccessible(BindMount *m, unsigned *n) {
+ BindMount *f, *t;
+ const char *clear = NULL;
+
+ assert(m);
+ assert(n);
+
+ /* Drops all entries obstructed by another entry further up the tree. Expects that the array is properly
+ * ordered already. */
+ for (f = m, t = m; f < m+*n; f++) {
+
+ /* If we found a path set for INACCESSIBLE earlier, and this entry has it as prefix we should drop
+ * it, as inaccessible paths really should drop the entire subtree. */
+ if (clear && path_startswith(f->path, clear)) {
+ log_debug("%s is masked by %s.", f->path, clear);
+ continue;
+ }
+
+ clear = f->mode == INACCESSIBLE ? f->path : NULL;
+
+ *t = *f;
+ t++;
+ }
+
+ *n = t - m;
+}
+
+static void drop_nop(BindMount *m, unsigned *n) {
+ BindMount *f, *t;
+
+ assert(m);
+ assert(n);
+
+ /* Drops all entries which have an immediate parent that has the same type, as they are redundant. Assumes the
+ * list is ordered by prefixes. */
+
+ for (f = m, t = m; f < m+*n; f++) {
+
+ /* Only suppress such subtrees for READONLY and READWRITE entries */
+ if (IN_SET(f->mode, READONLY, READWRITE)) {
+ BindMount *p;
+ bool found = false;
+
+ /* Now let's find the first parent of the entry we are looking at. */
+ for (p = t-1; p >= m; p--) {
+ if (path_startswith(f->path, p->path)) {
+ found = true;
+ break;
+ }
+ }
+
+ /* We found it, let's see if it's the same mode, if so, we can drop this entry */
+ if (found && p->mode == f->mode) {
+ log_debug("%s is redundant by %s", f->path, p->path);
+ continue;
+ }
+ }
+
+ *t = *f;
+ t++;
+ }
+
+ *n = t - m;
+}
+
+static void drop_outside_root(const char *root_directory, BindMount *m, unsigned *n) {
+ BindMount *f, *t;
+
+ assert(m);
+ assert(n);
+
+ if (!root_directory)
+ return;
+
+ /* Drops all mounts that are outside of the root directory. */
+
+ for (f = m, t = m; f < m+*n; f++) {
+
+ if (!path_startswith(f->path, root_directory)) {
+ log_debug("%s is outside of root directory.", f->path);
+ continue;
+ }
+
+ *t = *f;
t++;
}
@@ -278,24 +542,23 @@ static int apply_mount(
const char *what;
int r;
- struct stat target;
assert(m);
+ log_debug("Applying namespace mount on %s", m->path);
+
switch (m->mode) {
- case INACCESSIBLE:
+ case INACCESSIBLE: {
+ struct stat target;
/* First, get rid of everything that is below if there
* is anything... Then, overmount it with an
* inaccessible path. */
- umount_recursive(m->path, 0);
+ (void) umount_recursive(m->path, 0);
- if (lstat(m->path, &target) < 0) {
- if (m->ignore && errno == ENOENT)
- return 0;
- return -errno;
- }
+ if (lstat(m->path, &target) < 0)
+ return log_debug_errno(errno, "Failed to lstat() %s to determine what to mount over it: %m", m->path);
what = mode_to_inaccessible_node(target.st_mode);
if (!what) {
@@ -303,11 +566,20 @@ static int apply_mount(
return -ELOOP;
}
break;
+ }
+
case READONLY:
case READWRITE:
- /* Nothing to mount here, we just later toggle the
- * MS_RDONLY bit for the mount point */
- return 0;
+
+ r = path_is_mount_point(m->path, 0);
+ if (r < 0)
+ return log_debug_errno(r, "Failed to determine whether %s is already a mount point: %m", m->path);
+ if (r > 0) /* Nothing to do here, it is already a mount. We just later toggle the MS_RDONLY bit for the mount point if needed. */
+ return 0;
+
+ /* This isn't a mount point yet, let's make it one. */
+ what = m->path;
+ break;
case PRIVATE_TMP:
what = tmp_dir;
@@ -326,38 +598,104 @@ static int apply_mount(
assert(what);
- r = mount(what, m->path, NULL, MS_BIND|MS_REC, NULL);
- if (r >= 0) {
- log_debug("Successfully mounted %s to %s", what, m->path);
- return r;
- } else {
- if (m->ignore && errno == ENOENT)
- return 0;
+ if (mount(what, m->path, NULL, MS_BIND|MS_REC, NULL) < 0)
return log_debug_errno(errno, "Failed to mount %s to %s: %m", what, m->path);
- }
+
+ log_debug("Successfully mounted %s to %s", what, m->path);
+ return 0;
}
-static int make_read_only(BindMount *m) {
- int r;
+static int make_read_only(BindMount *m, char **blacklist) {
+ int r = 0;
assert(m);
if (IN_SET(m->mode, INACCESSIBLE, READONLY))
- r = bind_remount_recursive(m->path, true);
- else if (IN_SET(m->mode, READWRITE, PRIVATE_TMP, PRIVATE_VAR_TMP, PRIVATE_DEV)) {
- r = bind_remount_recursive(m->path, false);
- if (r == 0 && m->mode == PRIVATE_DEV) /* can be readonly but the submounts can't*/
- if (mount(NULL, m->path, NULL, MS_REMOUNT|DEV_MOUNT_OPTIONS|MS_RDONLY, NULL) < 0)
- r = -errno;
+ r = bind_remount_recursive(m->path, true, blacklist);
+ else if (m->mode == PRIVATE_DEV) { /* Can be readonly but the submounts can't*/
+ if (mount(NULL, m->path, NULL, MS_REMOUNT|DEV_MOUNT_OPTIONS|MS_RDONLY, NULL) < 0)
+ r = -errno;
} else
- r = 0;
-
- if (m->ignore && r == -ENOENT)
return 0;
+ /* Not that we only turn on the MS_RDONLY flag here, we never turn it off. Something that was marked read-only
+ * already stays this way. This improves compatibility with container managers, where we won't attempt to undo
+ * read-only mounts already applied. */
+
return r;
}
+static int chase_all_symlinks(const char *root_directory, BindMount *m, unsigned *n) {
+ BindMount *f, *t;
+ int r;
+
+ assert(m);
+ assert(n);
+
+ /* Since mount() will always follow symlinks and we need to take the different root directory into account we
+ * chase the symlinks on our own first. This call wil do so for all entries and remove all entries where we
+ * can't resolve the path, and which have been marked for such removal. */
+
+ for (f = m, t = m; f < m+*n; f++) {
+
+ r = chase_symlinks(f->path, root_directory, &f->chased);
+ if (r == -ENOENT && f->ignore) /* Doesn't exist? Then remove it! */
+ continue;
+ if (r < 0)
+ return log_debug_errno(r, "Failed to chase symlinks for %s: %m", f->path);
+
+ if (path_equal(f->path, f->chased))
+ f->chased = mfree(f->chased);
+ else {
+ log_debug("Chased %s → %s", f->path, f->chased);
+ f->path = f->chased;
+ }
+
+ *t = *f;
+ t++;
+ }
+
+ *n = t - m;
+ return 0;
+}
+
+static unsigned namespace_calculate_mounts(
+ char** read_write_paths,
+ char** read_only_paths,
+ char** inaccessible_paths,
+ const char* tmp_dir,
+ const char* var_tmp_dir,
+ bool private_dev,
+ bool protect_sysctl,
+ bool protect_cgroups,
+ ProtectHome protect_home,
+ ProtectSystem protect_system) {
+
+ unsigned protect_home_cnt;
+ unsigned protect_system_cnt =
+ (protect_system == PROTECT_SYSTEM_STRICT ?
+ ELEMENTSOF(protect_system_strict_table) :
+ ((protect_system == PROTECT_SYSTEM_FULL) ?
+ ELEMENTSOF(protect_system_full_table) :
+ ((protect_system == PROTECT_SYSTEM_YES) ?
+ ELEMENTSOF(protect_system_yes_table) : 0)));
+
+ protect_home_cnt =
+ (protect_home == PROTECT_HOME_YES ?
+ ELEMENTSOF(protect_home_yes_table) :
+ ((protect_home == PROTECT_HOME_READ_ONLY) ?
+ ELEMENTSOF(protect_home_read_only_table) : 0));
+
+ return !!tmp_dir + !!var_tmp_dir +
+ strv_length(read_write_paths) +
+ strv_length(read_only_paths) +
+ strv_length(inaccessible_paths) +
+ private_dev +
+ (protect_sysctl ? ELEMENTSOF(protect_kernel_tunables_table) : 0) +
+ (protect_cgroups ? 1 : 0) +
+ protect_home_cnt + protect_system_cnt;
+}
+
int setup_namespace(
const char* root_directory,
char** read_write_paths,
@@ -366,28 +704,31 @@ int setup_namespace(
const char* tmp_dir,
const char* var_tmp_dir,
bool private_dev,
+ bool protect_sysctl,
+ bool protect_cgroups,
ProtectHome protect_home,
ProtectSystem protect_system,
unsigned long mount_flags) {
BindMount *m, *mounts = NULL;
+ bool make_slave = false;
unsigned n;
int r = 0;
if (mount_flags == 0)
mount_flags = MS_SHARED;
- if (unshare(CLONE_NEWNS) < 0)
- return -errno;
+ n = namespace_calculate_mounts(read_write_paths,
+ read_only_paths,
+ inaccessible_paths,
+ tmp_dir, var_tmp_dir,
+ private_dev, protect_sysctl,
+ protect_cgroups, protect_home,
+ protect_system);
- n = !!tmp_dir + !!var_tmp_dir +
- strv_length(read_write_paths) +
- strv_length(read_only_paths) +
- strv_length(inaccessible_paths) +
- private_dev +
- (protect_home != PROTECT_HOME_NO ? 3 : 0) +
- (protect_system != PROTECT_SYSTEM_NO ? 2 : 0) +
- (protect_system == PROTECT_SYSTEM_FULL ? 1 : 0);
+ /* Set mount slave mode */
+ if (root_directory || n > 0)
+ make_slave = true;
if (n > 0) {
m = mounts = (BindMount *) alloca0(n * sizeof(BindMount));
@@ -421,94 +762,112 @@ int setup_namespace(
m++;
}
- if (protect_home != PROTECT_HOME_NO) {
- const char *home_dir, *run_user_dir, *root_dir;
+ if (protect_sysctl)
+ append_protect_kernel_tunables(&m, root_directory);
- home_dir = prefix_roota(root_directory, "/home");
- home_dir = strjoina("-", home_dir);
- run_user_dir = prefix_roota(root_directory, "/run/user");
- run_user_dir = strjoina("-", run_user_dir);
- root_dir = prefix_roota(root_directory, "/root");
- root_dir = strjoina("-", root_dir);
-
- r = append_mounts(&m, STRV_MAKE(home_dir, run_user_dir, root_dir),
- protect_home == PROTECT_HOME_READ_ONLY ? READONLY : INACCESSIBLE);
- if (r < 0)
- return r;
+ if (protect_cgroups) {
+ m->path = prefix_roota(root_directory, "/sys/fs/cgroup");
+ m->mode = READONLY;
+ m++;
}
- if (protect_system != PROTECT_SYSTEM_NO) {
- const char *usr_dir, *boot_dir, *etc_dir;
-
- usr_dir = prefix_roota(root_directory, "/usr");
- boot_dir = prefix_roota(root_directory, "/boot");
- boot_dir = strjoina("-", boot_dir);
- etc_dir = prefix_roota(root_directory, "/etc");
+ r = append_protect_home(&m, root_directory, protect_home);
+ if (r < 0)
+ return r;
- r = append_mounts(&m, protect_system == PROTECT_SYSTEM_FULL
- ? STRV_MAKE(usr_dir, boot_dir, etc_dir)
- : STRV_MAKE(usr_dir, boot_dir), READONLY);
- if (r < 0)
- return r;
- }
+ r = append_protect_system(&m, root_directory, protect_system);
+ if (r < 0)
+ return r;
assert(mounts + n == m);
+ /* Resolve symlinks manually first, as mount() will always follow them relative to the host's
+ * root. Moreover we want to suppress duplicates based on the resolved paths. This of course is a bit
+ * racy. */
+ r = chase_all_symlinks(root_directory, mounts, &n);
+ if (r < 0)
+ goto finish;
+
qsort(mounts, n, sizeof(BindMount), mount_path_compare);
+
drop_duplicates(mounts, &n);
+ drop_outside_root(root_directory, mounts, &n);
+ drop_inaccessible(mounts, &n);
+ drop_nop(mounts, &n);
+ }
+
+ if (unshare(CLONE_NEWNS) < 0) {
+ r = -errno;
+ goto finish;
}
- if (n > 0 || root_directory) {
+ if (make_slave) {
/* Remount / as SLAVE so that nothing now mounted in the namespace
shows up in the parent */
- if (mount(NULL, "/", NULL, MS_SLAVE|MS_REC, NULL) < 0)
- return -errno;
+ if (mount(NULL, "/", NULL, MS_SLAVE|MS_REC, NULL) < 0) {
+ r = -errno;
+ goto finish;
+ }
}
if (root_directory) {
- /* Turn directory into bind mount */
- if (mount(root_directory, root_directory, NULL, MS_BIND|MS_REC, NULL) < 0)
- return -errno;
+ /* Turn directory into bind mount, if it isn't one yet */
+ r = path_is_mount_point(root_directory, AT_SYMLINK_FOLLOW);
+ if (r < 0)
+ goto finish;
+ if (r == 0) {
+ if (mount(root_directory, root_directory, NULL, MS_BIND|MS_REC, NULL) < 0) {
+ r = -errno;
+ goto finish;
+ }
+ }
}
if (n > 0) {
+ char **blacklist;
+ unsigned j;
+
+ /* First round, add in all special mounts we need */
for (m = mounts; m < mounts + n; ++m) {
r = apply_mount(m, tmp_dir, var_tmp_dir);
if (r < 0)
- goto fail;
+ goto finish;
}
+ /* Create a blacklist we can pass to bind_mount_recursive() */
+ blacklist = newa(char*, n+1);
+ for (j = 0; j < n; j++)
+ blacklist[j] = (char*) mounts[j].path;
+ blacklist[j] = NULL;
+
+ /* Second round, flip the ro bits if necessary. */
for (m = mounts; m < mounts + n; ++m) {
- r = make_read_only(m);
+ r = make_read_only(m, blacklist);
if (r < 0)
- goto fail;
+ goto finish;
}
}
if (root_directory) {
/* MS_MOVE does not work on MS_SHARED so the remount MS_SHARED will be done later */
r = mount_move_root(root_directory);
-
- /* at this point, we cannot rollback */
if (r < 0)
- return r;
+ goto finish;
}
/* Remount / as the desired mode. Not that this will not
* reestablish propagation from our side to the host, since
* what's disconnected is disconnected. */
- if (mount(NULL, "/", NULL, mount_flags | MS_REC, NULL) < 0)
- /* at this point, we cannot rollback */
- return -errno;
+ if (mount(NULL, "/", NULL, mount_flags | MS_REC, NULL) < 0) {
+ r = -errno;
+ goto finish;
+ }
- return 0;
+ r = 0;
-fail:
- if (n > 0) {
- for (m = mounts; m < mounts + n; ++m)
- if (m->done)
- (void) umount2(m->path, MNT_DETACH);
- }
+finish:
+ for (m = mounts; m < mounts + n; m++)
+ free(m->chased);
return r;
}
@@ -658,6 +1017,7 @@ static const char *const protect_system_table[_PROTECT_SYSTEM_MAX] = {
[PROTECT_SYSTEM_NO] = "no",
[PROTECT_SYSTEM_YES] = "yes",
[PROTECT_SYSTEM_FULL] = "full",
+ [PROTECT_SYSTEM_STRICT] = "strict",
};
DEFINE_STRING_TABLE_LOOKUP(protect_system, ProtectSystem);
diff --git a/src/core/namespace.h b/src/core/namespace.h
index 1aedf5f208..6505bcc499 100644
--- a/src/core/namespace.h
+++ b/src/core/namespace.h
@@ -35,6 +35,7 @@ typedef enum ProtectSystem {
PROTECT_SYSTEM_NO,
PROTECT_SYSTEM_YES,
PROTECT_SYSTEM_FULL,
+ PROTECT_SYSTEM_STRICT,
_PROTECT_SYSTEM_MAX,
_PROTECT_SYSTEM_INVALID = -1
} ProtectSystem;
@@ -46,6 +47,8 @@ int setup_namespace(const char *chroot,
const char *tmp_dir,
const char *var_tmp_dir,
bool private_dev,
+ bool protect_sysctl,
+ bool protect_cgroups,
ProtectHome protect_home,
ProtectSystem protect_system,
unsigned long mount_flags);
diff --git a/src/core/service.c b/src/core/service.c
index 969c62bd83..98edc437a2 100644
--- a/src/core/service.c
+++ b/src/core/service.c
@@ -1256,10 +1256,16 @@ static int service_spawn(
socklen_t salen = sizeof(sa);
r = getpeername(s->socket_fd, &sa.sa, &salen);
- if (r < 0)
- return -errno;
+ if (r < 0) {
+ r = -errno;
+
+ /* ENOTCONN is legitimate if the endpoint disappeared on shutdown.
+ * This connection is over, but the socket unit lives on. */
+ if (r != -ENOTCONN || !IN_SET(s->control_command_id, SERVICE_EXEC_STOP, SERVICE_EXEC_STOP_POST))
+ return r;
+ }
- if (IN_SET(sa.sa.sa_family, AF_INET, AF_INET6)) {
+ if (r == 0 && IN_SET(sa.sa.sa_family, AF_INET, AF_INET6)) {
_cleanup_free_ char *addr = NULL;
char *t;
int port;
@@ -2594,8 +2600,7 @@ static void service_sigchld_event(Unit *u, pid_t pid, int code, int status) {
assert(s);
assert(pid >= 0);
- if (UNIT(s)->fragment_path ? is_clean_exit(code, status, &s->success_status) :
- is_clean_exit_lsb(code, status, &s->success_status))
+ if (is_clean_exit(code, status, s->type == SERVICE_ONESHOT ? EXIT_CLEAN_COMMAND : EXIT_CLEAN_DAEMON, &s->success_status))
f = SERVICE_SUCCESS;
else if (code == CLD_EXITED)
f = SERVICE_FAILURE_EXIT_CODE;
diff --git a/src/core/socket.c b/src/core/socket.c
index 70d55dd9ed..1b4a1b3dc3 100644
--- a/src/core/socket.c
+++ b/src/core/socket.c
@@ -1334,14 +1334,9 @@ static int usbffs_select_ep(const struct dirent *d) {
static int usbffs_dispatch_eps(SocketPort *p) {
_cleanup_free_ struct dirent **ent = NULL;
- _cleanup_free_ char *path = NULL;
int r, i, n, k;
- path = dirname_malloc(p->path);
- if (!path)
- return -ENOMEM;
-
- r = scandir(path, &ent, usbffs_select_ep, alphasort);
+ r = scandir(p->path, &ent, usbffs_select_ep, alphasort);
if (r < 0)
return -errno;
@@ -1356,7 +1351,7 @@ static int usbffs_dispatch_eps(SocketPort *p) {
for (i = 0; i < n; ++i) {
_cleanup_free_ char *ep = NULL;
- ep = path_make_absolute(ent[i]->d_name, path);
+ ep = path_make_absolute(ent[i]->d_name, p->path);
if (!ep)
return -ENOMEM;
@@ -2748,7 +2743,7 @@ static void socket_sigchld_event(Unit *u, pid_t pid, int code, int status) {
s->control_pid = 0;
- if (is_clean_exit(code, status, NULL))
+ if (is_clean_exit(code, status, EXIT_CLEAN_COMMAND, NULL))
f = SOCKET_SUCCESS;
else if (code == CLD_EXITED)
f = SOCKET_FAILURE_EXIT_CODE;
diff --git a/src/core/swap.c b/src/core/swap.c
index fb222b6858..fee9e7b0e6 100644
--- a/src/core/swap.c
+++ b/src/core/swap.c
@@ -988,7 +988,7 @@ static void swap_sigchld_event(Unit *u, pid_t pid, int code, int status) {
s->control_pid = 0;
- if (is_clean_exit(code, status, NULL))
+ if (is_clean_exit(code, status, EXIT_CLEAN_COMMAND, NULL))
f = SWAP_SUCCESS;
else if (code == CLD_EXITED)
f = SWAP_FAILURE_EXIT_CODE;
diff --git a/src/core/system.conf b/src/core/system.conf
index c6bb050aac..746572b7ff 100644
--- a/src/core/system.conf
+++ b/src/core/system.conf
@@ -21,6 +21,7 @@
#CrashChangeVT=no
#CrashShell=no
#CrashReboot=no
+#CtrlAltDelBurstAction=reboot-force
#CPUAffinity=1 2
#JoinControllers=cpu,cpuacct net_cls,net_prio
#RuntimeWatchdogSec=0
diff --git a/src/core/umount.c b/src/core/umount.c
index c21a2be54e..1e5459ed80 100644
--- a/src/core/umount.c
+++ b/src/core/umount.c
@@ -375,7 +375,7 @@ static int mount_points_list_umount(MountPoint **head, bool *changed, bool log_e
/* If we are in a container, don't attempt to
read-only mount anything as that brings no real
benefits, but might confuse the host, as we remount
- the superblock here, not the bind mound. */
+ the superblock here, not the bind mount. */
if (detect_container() <= 0) {
_cleanup_free_ char *options = NULL;
/* MS_REMOUNT requires that the data parameter
diff --git a/src/core/unit.c b/src/core/unit.c
index de22f657c6..693f75c928 100644
--- a/src/core/unit.c
+++ b/src/core/unit.c
@@ -2225,6 +2225,11 @@ int unit_add_dependency(Unit *u, UnitDependency d, Unit *other, bool add_referen
return 0;
}
+ if (d == UNIT_BEFORE && other->type == UNIT_DEVICE) {
+ log_unit_warning(u, "Dependency Before=%s ignored (.device units cannot be delayed)", other->id);
+ return 0;
+ }
+
r = set_ensure_allocated(&u->dependencies[d], NULL);
if (r < 0)
return r;
@@ -3377,8 +3382,14 @@ int unit_patch_contexts(Unit *u) {
return -ENOMEM;
}
+ /* If the dynamic user option is on, let's make sure that the unit can't leave its UID/GID
+ * around in the file system or on IPC objects. Hence enforce a strict sandbox. */
+
ec->private_tmp = true;
ec->remove_ipc = true;
+ ec->protect_system = PROTECT_SYSTEM_STRICT;
+ if (ec->protect_home == PROTECT_HOME_NO)
+ ec->protect_home = PROTECT_HOME_READ_ONLY;
}
}
generated by cgit v1.2.3-54-g00ecf (git 2.45.2) at 2025-04-04 05:24:16 +0000