#include <sys/reboot.h>
#include <sys/stat.h>
#include <unistd.h>
-#ifdef HAVE_SECCOMP
+#if HAVE_SECCOMP
#include <seccomp.h>
#endif
-#ifdef HAVE_VALGRIND_VALGRIND_H
+#if HAVE_VALGRIND_VALGRIND_H
#include <valgrind/valgrind.h>
#endif
#include "process-util.h"
#include "raw-clone.h"
#include "rlimit-util.h"
-#ifdef HAVE_SECCOMP
+#if HAVE_SECCOMP
#include "seccomp-util.h"
#endif
#include "selinux-setup.h"
static FILE* arg_serialization = NULL;
static bool arg_default_cpu_accounting = false;
static bool arg_default_io_accounting = false;
+static bool arg_default_ip_accounting = false;
static bool arg_default_blockio_accounting = false;
static bool arg_default_memory_accounting = false;
static bool arg_default_tasks_accounting = true;
{ "Manager", "RuntimeWatchdogSec", config_parse_sec, 0, &arg_runtime_watchdog },
{ "Manager", "ShutdownWatchdogSec", config_parse_sec, 0, &arg_shutdown_watchdog },
{ "Manager", "CapabilityBoundingSet", config_parse_capability_set, 0, &arg_capability_bounding_set },
-#ifdef HAVE_SECCOMP
+#if HAVE_SECCOMP
{ "Manager", "SystemCallArchitectures", config_parse_syscall_archs, 0, &arg_syscall_archs },
#endif
{ "Manager", "TimerSlackNSec", config_parse_nsec, 0, &arg_timer_slack_nsec },
{ "Manager", "DefaultLimitRTTIME", config_parse_limit, RLIMIT_RTTIME, arg_default_rlimit },
{ "Manager", "DefaultCPUAccounting", config_parse_bool, 0, &arg_default_cpu_accounting },
{ "Manager", "DefaultIOAccounting", config_parse_bool, 0, &arg_default_io_accounting },
+ { "Manager", "DefaultIPAccounting", config_parse_bool, 0, &arg_default_ip_accounting },
{ "Manager", "DefaultBlockIOAccounting", config_parse_bool, 0, &arg_default_blockio_accounting },
{ "Manager", "DefaultMemoryAccounting", config_parse_bool, 0, &arg_default_memory_accounting },
{ "Manager", "DefaultTasksAccounting", config_parse_bool, 0, &arg_default_tasks_accounting },
m->default_start_limit_burst = arg_default_start_limit_burst;
m->default_cpu_accounting = arg_default_cpu_accounting;
m->default_io_accounting = arg_default_io_accounting;
+ m->default_ip_accounting = arg_default_ip_accounting;
m->default_blockio_accounting = arg_default_blockio_accounting;
m->default_memory_accounting = arg_default_memory_accounting;
m->default_tasks_accounting = arg_default_tasks_accounting;
return 0;
}
+static int bump_rlimit_memlock(struct rlimit *saved_rlimit) {
+ int r;
+
+ assert(saved_rlimit);
+ assert(getuid() == 0);
+
+ /* BPF_MAP_TYPE_LPM_TRIE bpf maps are charged against RLIMIT_MEMLOCK, even though we have CAP_IPC_LOCK which
+ * should normally disable such checks. We need them to implement IPAccessAllow= and IPAccessDeny=, hence let's
+ * bump the value high enough for the root user. */
+
+ if (getrlimit(RLIMIT_MEMLOCK, saved_rlimit) < 0)
+ return log_warning_errno(errno, "Reading RLIMIT_MEMLOCK failed, ignoring: %m");
+
+ r = setrlimit_closest(RLIMIT_MEMLOCK, &RLIMIT_MAKE_CONST(1024ULL*1024ULL*16ULL));
+ if (r < 0)
+ return log_warning_errno(r, "Setting RLIMIT_MEMLOCK failed, ignoring: %m");
+
+ return 0;
+}
+
static void test_usr(void) {
/* Check that /usr is not a separate fs */
}
static int enforce_syscall_archs(Set *archs) {
-#ifdef HAVE_SECCOMP
+#if HAVE_SECCOMP
int r;
if (!is_seccomp_available())
bool queue_default_job = false;
bool empty_etc = false;
char *switch_root_dir = NULL, *switch_root_init = NULL;
- struct rlimit saved_rlimit_nofile = RLIMIT_MAKE_CONST(0);
+ struct rlimit saved_rlimit_nofile = RLIMIT_MAKE_CONST(0), saved_rlimit_memlock = RLIMIT_MAKE_CONST((rlim_t) -1);
const char *error_message = NULL;
-#ifdef HAVE_SYSV_COMPAT
+#if HAVE_SYSV_COMPAT
if (getpid_cached() != 1 && strstr(program_invocation_short_name, "init")) {
/* This is compatibility support for SysV, where
* calling init as a user is identical to telinit. */
log_close();
/* Remember open file descriptors for later deserialization */
- r = fdset_new_fill(&fds);
- if (r < 0) {
- log_emergency_errno(r, "Failed to allocate fd set: %m");
- error_message = "Failed to allocate fd set";
- goto finish;
- } else
- fdset_cloexec(fds, true);
+ if (arg_action == ACTION_RUN) {
+ r = fdset_new_fill(&fds);
+ if (r < 0) {
+ log_emergency_errno(r, "Failed to allocate fd set: %m");
+ error_message = "Failed to allocate fd set";
+ goto finish;
+ } else
+ fdset_cloexec(fds, true);
- if (arg_serialization)
- assert_se(fdset_remove(fds, fileno(arg_serialization)) >= 0);
+ if (arg_serialization)
+ assert_se(fdset_remove(fds, fileno(arg_serialization)) >= 0);
- if (arg_system)
- /* Become a session leader if we aren't one yet. */
- setsid();
+ if (arg_system)
+ /* Become a session leader if we aren't one yet. */
+ setsid();
+ }
/* Move out of the way, so that we won't block unmounts */
assert_se(chdir("/") == 0);
arg_action == ACTION_TEST ? " test" : "", getuid(), t);
}
- if (arg_system && !skip_setup) {
- if (arg_show_status > 0)
- status_welcome();
+ if (arg_action == ACTION_RUN) {
+ if (arg_system && !skip_setup) {
+ if (arg_show_status > 0)
+ status_welcome();
- hostname_setup();
- machine_id_setup(NULL, arg_machine_id, NULL);
- loopback_setup();
- bump_unix_max_dgram_qlen();
+ hostname_setup();
+ machine_id_setup(NULL, arg_machine_id, NULL);
+ loopback_setup();
+ bump_unix_max_dgram_qlen();
- test_usr();
- }
+ test_usr();
+ }
- if (arg_system && arg_runtime_watchdog > 0 && arg_runtime_watchdog != USEC_INFINITY)
- watchdog_set_timeout(&arg_runtime_watchdog);
+ if (arg_system && arg_runtime_watchdog > 0 && arg_runtime_watchdog != USEC_INFINITY)
+ watchdog_set_timeout(&arg_runtime_watchdog);
- if (arg_timer_slack_nsec != NSEC_INFINITY)
- if (prctl(PR_SET_TIMERSLACK, arg_timer_slack_nsec) < 0)
- log_error_errno(errno, "Failed to adjust timer slack: %m");
+ if (arg_timer_slack_nsec != NSEC_INFINITY)
+ if (prctl(PR_SET_TIMERSLACK, arg_timer_slack_nsec) < 0)
+ log_error_errno(errno, "Failed to adjust timer slack: %m");
- if (arg_system && !cap_test_all(arg_capability_bounding_set)) {
- r = capability_bounding_set_drop_usermode(arg_capability_bounding_set);
- if (r < 0) {
- log_emergency_errno(r, "Failed to drop capability bounding set of usermode helpers: %m");
- error_message = "Failed to drop capability bounding set of usermode helpers";
- goto finish;
- }
- r = capability_bounding_set_drop(arg_capability_bounding_set, true);
- if (r < 0) {
- log_emergency_errno(r, "Failed to drop capability bounding set: %m");
- error_message = "Failed to drop capability bounding set";
- goto finish;
+ if (arg_system && !cap_test_all(arg_capability_bounding_set)) {
+ r = capability_bounding_set_drop_usermode(arg_capability_bounding_set);
+ if (r < 0) {
+ log_emergency_errno(r, "Failed to drop capability bounding set of usermode helpers: %m");
+ error_message = "Failed to drop capability bounding set of usermode helpers";
+ goto finish;
+ }
+ r = capability_bounding_set_drop(arg_capability_bounding_set, true);
+ if (r < 0) {
+ log_emergency_errno(r, "Failed to drop capability bounding set: %m");
+ error_message = "Failed to drop capability bounding set";
+ goto finish;
+ }
}
- }
- if (arg_syscall_archs) {
- r = enforce_syscall_archs(arg_syscall_archs);
- if (r < 0) {
- error_message = "Failed to set syscall architectures";
- goto finish;
+ if (arg_syscall_archs) {
+ r = enforce_syscall_archs(arg_syscall_archs);
+ if (r < 0) {
+ error_message = "Failed to set syscall architectures";
+ goto finish;
+ }
}
- }
-
- if (!arg_system)
- /* Become reaper of our children */
- if (prctl(PR_SET_CHILD_SUBREAPER, 1) < 0)
- log_warning_errno(errno, "Failed to make us a subreaper: %m");
- if (arg_system) {
- (void) bump_rlimit_nofile(&saved_rlimit_nofile);
+ if (!arg_system)
+ /* Become reaper of our children */
+ if (prctl(PR_SET_CHILD_SUBREAPER, 1) < 0)
+ log_warning_errno(errno, "Failed to make us a subreaper: %m");
- if (empty_etc) {
- r = unit_file_preset_all(UNIT_FILE_SYSTEM, 0, NULL, UNIT_FILE_PRESET_ENABLE_ONLY, NULL, 0);
- if (r < 0)
- log_full_errno(r == -EEXIST ? LOG_NOTICE : LOG_WARNING, r, "Failed to populate /etc with preset unit settings, ignoring: %m");
- else
- log_info("Populated /etc with preset unit settings.");
+ if (arg_system) {
+ /* Bump up RLIMIT_NOFILE for systemd itself */
+ (void) bump_rlimit_nofile(&saved_rlimit_nofile);
+ (void) bump_rlimit_memlock(&saved_rlimit_memlock);
}
}
- r = manager_new(arg_system ? UNIT_FILE_SYSTEM : UNIT_FILE_USER, arg_action == ACTION_TEST, &m);
+ r = manager_new(arg_system ? UNIT_FILE_SYSTEM : UNIT_FILE_USER,
+ arg_action == ACTION_TEST ? MANAGER_TEST_FULL : 0,
+ &m);
if (r < 0) {
log_emergency_errno(r, "Failed to allocate manager object: %m");
error_message = "Failed to allocate manager object";
* its child processes */
if (saved_rlimit_nofile.rlim_cur > 0)
(void) setrlimit(RLIMIT_NOFILE, &saved_rlimit_nofile);
+ if (saved_rlimit_memlock.rlim_cur != (rlim_t) -1)
+ (void) setrlimit(RLIMIT_MEMLOCK, &saved_rlimit_memlock);
if (switch_root_dir) {
/* Kill all remaining processes from the
arg_serialization = safe_fclose(arg_serialization);
fds = fdset_free(fds);
-#ifdef HAVE_VALGRIND_VALGRIND_H
+#if HAVE_VALGRIND_VALGRIND_H
/* If we are PID 1 and running under valgrind, then let's exit
* here explicitly. valgrind will only generate nice output on
* exit(), not on exec(), hence let's do the former not the
projects / thirdparty / systemd.git / blobdiff