// SPDX-License-Identifier: GPL-2.0-only /* * linux/init/main.c * * Copyright (C) 1991, 1992 Linus Torvalds * * GK 2/5/95 - Changed to support mounting root fs via NFS * Added initrd & change_root: Werner Almesberger & Hans Lermen, Feb '96 * Moan early if gcc is old, avoiding bogus kernels - Paul Gortmaker, May '96 * Simplified starting of init: Michael A. Griffith <grif@acm.org>
*/
/* * Debug helper: via this flag we know that we are in 'early bootup code' * where only the boot processor is running with IRQ disabled. This means * two things - IRQ must not be enabled before the flag is cleared and some * operations which are not allowed with IRQ disabled are allowed while the * flag is set.
*/ bool early_boot_irqs_disabled __read_mostly;
/* * Used to generate warnings if static_key manipulation functions are used * before jump_label_init is called.
*/ bool static_key_initialized __read_mostly;
EXPORT_SYMBOL_GPL(static_key_initialized);
/* * If set, this is an indication to the drivers that reset the underlying * device before going ahead with the initialization otherwise driver might * rely on the BIOS and skip the reset operation. * * This is useful if kernel is booting in an unreliable environment. * For ex. kdump situation where previous kernel has crashed, BIOS has been * skipped and devices will be in unknown state.
*/ unsignedint reset_devices;
EXPORT_SYMBOL(reset_devices);
p = __setup_start; do { int n = strlen(p->str); if (parameqn(line, p->str, n)) { if (p->early) { /* Already done in parse_early_param? * (Needs exact match on param part). * Keep iterating, as we can have early
* params and __setups of same names 8( */ if (line[n] == '\0' || line[n] == '=')
had_early_param = true;
} elseif (!p->setup_func) {
pr_warn("Parameter %s is obsolete, ignored\n",
p->str); returntrue;
} elseif (p->setup_func(line + n)) returntrue;
}
p++;
} while (p < __setup_end);
return had_early_param;
}
/* * This should be approx 2 Bo*oMips to start (note initial shift), and will * still work even if initially too large, it will just take slightly longer
*/ unsignedlong loops_per_jiffy = (1<<12);
EXPORT_SYMBOL(loops_per_jiffy);
staticint __init loglevel(char *str)
{ int newlevel;
/* * Only update loglevel value when a correct setting was passed, * to prevent blind crashes (when loglevel being set to 0) that * are quite hard to debug
*/ if (get_option(&str, &newlevel)) {
console_loglevel = newlevel; return 0;
}
data = (char *)initrd_end - BOOTCONFIG_MAGIC_LEN; /* * Since Grub may align the size of initrd to 4, we must * check the preceding 3 bytes as well.
*/ for (i = 0; i < 4; i++) { if (!memcmp(data, BOOTCONFIG_MAGIC, BOOTCONFIG_MAGIC_LEN)) goto found;
data--;
} return NULL;
xbc_node_for_each_key_value(root, knode, val) {
ret = xbc_node_compose_key_after(root, knode,
xbc_namebuf, XBC_KEYLEN_MAX); if (ret < 0) return ret;
vnode = xbc_node_get_child(knode); if (!vnode) {
ret = snprintf(buf, rest(buf, end), "%s ", xbc_namebuf); if (ret < 0) return ret;
buf += ret; continue;
}
xbc_array_for_each_value(vnode, val) { /* * For prettier and more readable /proc/cmdline, only * quote the value when necessary, i.e. when it contains * whitespace.
*/
q = strpbrk(val, " \t\r\n") ? "\"" : "";
ret = snprintf(buf, rest(buf, end), "%s=%s%s%s ",
xbc_namebuf, q, val, q); if (ret < 0) return ret;
buf += ret;
}
}
return buf - (end - size);
} #undef rest
/* Make an extra command line under given key word */ staticchar * __init xbc_make_cmdline(constchar *key)
{ struct xbc_node *root; char *new_cmdline; int ret, len = 0;
root = xbc_find_node(key); if (!root) return NULL;
/* Count required buffer size */
len = xbc_snprint_cmdline(NULL, 0, root); if (len <= 0) return NULL;
new_cmdline = memblock_alloc(len + 1, SMP_CACHE_BYTES); if (!new_cmdline) {
pr_err("Failed to allocate memory for extra kernel cmdline.\n"); return NULL;
}
ret = xbc_snprint_cmdline(new_cmdline, len + 1, root); if (ret < 0 || ret > len) {
pr_err("Failed to print extra kernel cmdline.\n");
memblock_free(new_cmdline, len + 1); return NULL;
}
/* Cut out the bootconfig data even if we have no bootconfig option */
data = get_boot_config_from_initrd(&size); /* If there is no bootconfig in initrd, try embedded one. */ if (!data)
data = xbc_get_embedded_bootconfig(&size);
if (IS_ERR(err) || !(bootconfig_found || IS_ENABLED(CONFIG_BOOT_CONFIG_FORCE))) return;
/* parse_args() stops at the next param of '--' and returns an address */ if (err)
initargs_offs = err - tmp_cmdline;
if (!data) { /* If user intended to use bootconfig, show an error level message */ if (bootconfig_found)
pr_err("'bootconfig' found on command line, but no bootconfig found\n"); else
pr_info("No bootconfig data provided, so skipping bootconfig"); return;
}
if (size >= XBC_DATA_MAX) {
pr_err("bootconfig size %ld greater than max size %d\n",
(long)size, XBC_DATA_MAX); return;
}
ret = xbc_init(data, size, &msg, &pos); if (ret < 0) { if (pos < 0)
pr_err("Failed to init bootconfig: %s.\n", msg); else
pr_err("Failed to parse bootconfig: %s at %d.\n",
msg, pos);
} else {
xbc_get_info(&ret, NULL);
pr_info("Load bootconfig: %ld bytes %d nodes\n", (long)size, ret); /* keys starting with "kernel." are passed via cmdline */
extra_command_line = xbc_make_cmdline("kernel"); /* Also, "init." keys are init arguments */
extra_init_args = xbc_make_cmdline("init");
} return;
}
staticvoid __init setup_boot_config(void)
{ /* Remove bootconfig data from initrd */
get_boot_config_from_initrd(NULL);
}
staticint __init warn_bootconfig(char *str)
{
pr_warn("WARNING: 'bootconfig' found on the kernel command line but CONFIG_BOOT_CONFIG is not set.\n"); return 0;
}
execute_command = str; /* * In case LILO is going to boot us with default command line, * it prepends "auto" before the whole cmdline which makes * the shell think it should execute a script with such name. * So we ignore all arguments entered _before_ init=... [MJ]
*/ for (i = 1; i < MAX_INIT_ARGS; i++)
argv_init[i] = NULL; return 1;
}
__setup("init=", init_setup);
/* * We need to store the untouched command line for future reference. * We also need to store the touched command line since the parameter * parsing is performed in place, and we should allow a component to * store reference of name/value for future reference.
*/ staticvoid __init setup_command_line(char *command_line)
{
size_t len, xlen = 0, ilen = 0;
if (extra_command_line)
xlen = strlen(extra_command_line); if (extra_init_args) {
extra_init_args = strim(extra_init_args); /* remove trailing space */
ilen = strlen(extra_init_args) + 4; /* for " -- " */
}
len = xlen + strlen(boot_command_line) + ilen + 1;
if (xlen) { /* * We have to put extra_command_line before boot command * lines because there could be dashes (separator of init * command line) in the command lines.
*/
strcpy(saved_command_line, extra_command_line);
strcpy(static_command_line, extra_command_line);
}
strcpy(saved_command_line + xlen, boot_command_line);
strcpy(static_command_line + xlen, command_line);
if (ilen) { /* * Append supplemental init boot args to saved_command_line * so that user can check what command line options passed * to init. * The order should always be * " -- "[bootconfig init-param][cmdline init-param]
*/ if (initargs_offs) {
len = xlen + initargs_offs;
strcpy(saved_command_line + len, extra_init_args);
len += ilen - 4; /* strlen(extra_init_args) */
strcpy(saved_command_line + len,
boot_command_line + initargs_offs - 1);
} else {
len = strlen(saved_command_line);
strcpy(saved_command_line + len, " -- ");
len += 4;
strcpy(saved_command_line + len, extra_init_args);
}
}
/* * We need to finalize in a non-__init function or else race conditions * between the root thread and the init thread may cause start_kernel to * be reaped by free_initmem before the root thread has proceeded to * cpu_idle. * * gcc-3.4 accidentally inlines this function, so use noinline.
*/
rcu_scheduler_starting(); /* * We need to spawn init first so that it obtains pid 1, however * the init task will end up wanting to create kthreads, which, if * we schedule it before we create kthreadd, will OOPS.
*/
pid = user_mode_thread(kernel_init, NULL, CLONE_FS); /* * Pin init on the boot CPU. Task migration is not properly working * until sched_init_smp() has been run. It will set the allowed * CPUs for init to the non isolated CPUs.
*/
rcu_read_lock();
tsk = find_task_by_pid_ns(pid, &init_pid_ns);
tsk->flags |= PF_NO_SETAFFINITY;
set_cpus_allowed_ptr(tsk, cpumask_of(smp_processor_id()));
rcu_read_unlock();
/* * Enable might_sleep() and smp_processor_id() checks. * They cannot be enabled earlier because with CONFIG_PREEMPTION=y * kernel_thread() would trigger might_sleep() splats. With * CONFIG_PREEMPT_VOLUNTARY=y the init task might have scheduled * already, but it's stuck on the kthreadd_done completion.
*/
system_state = SYSTEM_SCHEDULING;
complete(&kthreadd_done);
/* * The boot idle thread must execute schedule() * at least once to get things moving:
*/
schedule_preempt_disabled(); /* Call into cpu_idle with preempt disabled */
cpu_startup_entry(CPUHP_ONLINE);
}
/* Check for early params. */ staticint __init do_early_param(char *param, char *val, constchar *unused, void *arg)
{ conststruct obs_kernel_param *p;
for (p = __setup_start; p < __setup_end; p++) { if (p->early && parameq(param, p->str)) { if (p->setup_func(val) != 0)
pr_warn("Malformed early option '%s'\n", param);
}
} /* We accept everything at this stage. */ return 0;
}
/* Arch code calls this early on, or if not, just before other parsing. */ void __init parse_early_param(void)
{ staticint done __initdata; staticchar tmp_cmdline[COMMAND_LINE_SIZE] __initdata;
if (done) return;
/* All fall through to do_early_param. */
strscpy(tmp_cmdline, boot_command_line, COMMAND_LINE_SIZE);
parse_early_options(tmp_cmdline);
done = 1;
}
if (panic_later || (!argv_init[1] && !envp_init[2])) return;
/* * Determine how many options we have to print out, plus a space * before each
*/
len = 1; /* null terminator */ for (p = &argv_init[1]; *p; p++) {
len++;
len += strlen(*p);
} for (p = &envp_init[2]; *p; p++) {
len++;
len += strlen(*p);
}
unknown_options = memblock_alloc(len, SMP_CACHE_BYTES); if (!unknown_options) {
pr_err("%s: Failed to allocate %zu bytes\n",
__func__, len); return;
}
end = unknown_options;
for (p = &argv_init[1]; *p; p++)
end += sprintf(end, " %s", *p); for (p = &envp_init[2]; *p; p++)
end += sprintf(end, " %s", *p);
/* Start at unknown_options[1] to skip the initial space */
pr_notice("Unknown kernel command line parameters \"%s\", will be passed to user space.\n",
&unknown_options[1]);
memblock_free(unknown_options, len);
}
staticvoid __init early_numa_node_init(void)
{ #ifdef CONFIG_USE_PERCPU_NUMA_NODE_ID #ifndef cpu_to_node int cpu;
/* The early_cpu_to_node() should be ready here. */
for_each_possible_cpu(cpu)
set_cpu_numa_node(cpu, early_cpu_to_node(cpu)); #endif #endif
}
/* Architectural and non-timekeeping rng init, before allocator init */
random_init_early(command_line);
/* * These use large bootmem allocations and must precede * initalization of page allocator
*/
setup_log_buf(0);
vfs_caches_init_early();
sort_main_extable();
trap_init();
mm_core_init();
maple_tree_init();
poking_init();
ftrace_init();
/* trace_printk can be enabled here */
early_trace_init();
/* * Set up the scheduler prior starting any interrupts (such as the * timer interrupt). Full topology setup happens at smp_init() * time - but meanwhile we still have a functioning scheduler.
*/
sched_init();
if (WARN(!irqs_disabled(), "Interrupts were enabled *very* early, fixing it\n"))
local_irq_disable();
radix_tree_init();
/* * Set up housekeeping before setting up workqueues to allow the unbound * workqueue to take non-housekeeping into account.
*/
housekeeping_init();
/* * Allow workqueue creation and work item queueing/cancelling * early. Work item execution depends on kthreads and starts after * workqueue_init().
*/
workqueue_init_early();
rcu_init();
kvfree_rcu_init();
/* Trace events are available after this */
trace_init();
if (initcall_debug)
initcall_debug_enable();
context_tracking_init(); /* init some links before init_ISA_irqs() */
early_irq_init();
init_IRQ();
tick_init();
rcu_init_nohz();
timers_init();
srcu_init();
hrtimers_init();
softirq_init();
timekeeping_init();
time_init();
/* This must be after timekeeping is initialized */
random_init();
/* These make use of the fully initialized rng */
kfence_init();
boot_init_stack_canary();
perf_event_init();
profile_init();
call_function_init();
WARN(!irqs_disabled(), "Interrupts were enabled early\n");
/* * HACK ALERT! This is early. We're enabling the console before * we've done PCI setups etc, and console_init() must be aware of * this. But we do want output early, in case something goes wrong.
*/
console_init(); if (panic_later)
panic("Too many boot %s vars at `%s'", panic_later,
panic_param);
lockdep_init();
/* * Need to run this when irqs are enabled, because it wants * to self-test [hard/soft]-irqs on/off lock inversion bugs * too:
*/
locking_selftest();
/* Do the rest non-__init'ed, we're now alive */
rest_init();
/* * Avoid stack canaries in callers of boot_init_stack_canary for gcc-10 * and older.
*/ #if !__has_attribute(__no_stack_protector__)
prevent_tail_call_optimization(); #endif
}
/* Call all constructor functions linked into the kernel. */ staticvoid __init do_ctors(void)
{ /* * For UML, the constructors have already been called by the * normal setup code as it's just a normal ELF binary, so we * cannot do it again - but we do need CONFIG_CONSTRUCTORS * even on UML for modules.
*/ #ifdefined(CONFIG_CONSTRUCTORS) && !defined(CONFIG_UML)
ctor_fn_t *fn = (ctor_fn_t *) __ctors_start;
/* * fn will be "function_name [module_name]" where [module_name] is not * displayed for built-in init functions. Strip off the [module_name].
*/
strreplace(fn_name, ' ', '\0');
staticvoid __init do_initcalls(void)
{ int level;
size_t len = saved_command_line_len + 1; char *command_line;
command_line = kzalloc(len, GFP_KERNEL); if (!command_line)
panic("%s: Failed to allocate %zu bytes\n", __func__, len);
for (level = 0; level < ARRAY_SIZE(initcall_levels) - 1; level++) { /* Parser modifies command_line, restore it each time */
strcpy(command_line, saved_command_line);
do_initcall_level(level, command_line);
}
kfree(command_line);
}
/* * Ok, the machine is now initialized. None of the devices * have been touched yet, but the CPU subsystem is up and * running, and memory and process management works. * * Now we can finally start doing some real work..
*/ staticvoid __init do_basic_setup(void)
{
cpuset_init_smp();
driver_init();
init_irq_proc();
do_ctors();
do_initcalls();
}
staticvoid mark_readonly(void)
{ if (IS_ENABLED(CONFIG_STRICT_KERNEL_RWX) && rodata_enabled) { /* * load_module() results in W+X mappings, which are cleaned * up with init_free_wq. Let's make sure that queued work is * flushed so that we don't hit false positives looking for * insecure pages which are W+X.
*/
flush_module_init_free_work();
jump_label_init_ro();
mark_rodata_ro();
debug_checkwx();
rodata_test();
} elseif (IS_ENABLED(CONFIG_STRICT_KERNEL_RWX)) {
pr_info("Kernel memory protection disabled.\n");
} elseif (IS_ENABLED(CONFIG_ARCH_HAS_STRICT_KERNEL_RWX)) {
pr_warn("Kernel memory protection not selected by kernel config.\n");
} else {
pr_warn("This architecture does not have kernel memory protection.\n");
}
}
if (ramdisk_execute_command) {
ret = run_init_process(ramdisk_execute_command); if (!ret) return 0;
pr_err("Failed to execute %s (error %d)\n",
ramdisk_execute_command, ret);
}
/* * We try each of these until one succeeds. * * The Bourne shell can be used instead of init if we are * trying to recover a really broken machine.
*/ if (execute_command) {
ret = run_init_process(execute_command); if (!ret) return 0;
panic("Requested init %s failed (error %d).",
execute_command, ret);
}
if (CONFIG_DEFAULT_INIT[0] != '\0') {
ret = run_init_process(CONFIG_DEFAULT_INIT); if (ret)
pr_err("Default init %s failed (error %d)\n",
CONFIG_DEFAULT_INIT, ret); else return 0;
}
if (!try_to_run_init_process("/sbin/init") ||
!try_to_run_init_process("/etc/init") ||
!try_to_run_init_process("/bin/init") ||
!try_to_run_init_process("/bin/sh")) return 0;
panic("No working init found. Try passing init= option to kernel. " "See Linux Documentation/admin-guide/init.rst for guidance.");
}
/* Open /dev/console, for stdin/stdout/stderr, this should never fail */ void __init console_on_rootfs(void)
{ struct file *file = filp_open("/dev/console", O_RDWR, 0);
if (IS_ERR(file)) {
pr_err("Warning: unable to open an initial console.\n"); return;
}
init_dup(file);
init_dup(file);
init_dup(file);
fput(file);
}
static noinline void __init kernel_init_freeable(void)
{ /* Now the scheduler is fully set up and can do blocking allocations */
gfp_allowed_mask = __GFP_BITS_MASK;
/* * init can allocate pages on any node
*/
set_mems_allowed(node_states[N_MEMORY]);
/* * check if there is an early userspace init. If yes, let it do all * the work
*/ int ramdisk_command_access;
ramdisk_command_access = init_eaccess(ramdisk_execute_command); if (ramdisk_command_access != 0) {
pr_warn("check access for rdinit=%s failed: %i, ignoring\n",
ramdisk_execute_command, ramdisk_command_access);
ramdisk_execute_command = NULL;
prepare_namespace();
}
/* * Ok, we have completed the initial bootup, and * we're essentially up and running. Get rid of the * initmem segments and start the user-mode stuff.. * * rootfs is available now, try loading the public keys * and default modules
*/
Die Informationen auf dieser Webseite wurden
nach bestem Wissen sorgfältig zusammengestellt. Es wird jedoch weder Vollständigkeit, noch Richtigkeit,
noch Qualität der bereit gestellten Informationen zugesichert.
Bemerkung:
Die farbliche Syntaxdarstellung und die Messung sind noch experimentell.