1 // SPDX-License-Identifier: GPL-2.0-only
2 /*
3 * linux/init/main.c
4 *
5 * Copyright (C) 1991, 1992 Linus Torvalds
6 *
7 * GK 2/5/95 - Changed to support mounting root fs via NFS
8 * Added initrd & change_root: Werner Almesberger & Hans Lermen, Feb '96
9 * Moan early if gcc is old, avoiding bogus kernels - Paul Gortmaker, May '96
10 * Simplified starting of init: Michael A. Griffith <grif@acm.org>
11 */
12
13 #define DEBUG /* Enable initcall_debug */
14
15 #include <linux/types.h>
16 #include <linux/extable.h>
17 #include <linux/module.h>
18 #include <linux/proc_fs.h>
19 #include <linux/binfmts.h>
20 #include <linux/kernel.h>
21 #include <linux/syscalls.h>
22 #include <linux/stackprotector.h>
23 #include <linux/string.h>
24 #include <linux/ctype.h>
25 #include <linux/delay.h>
26 #include <linux/ioport.h>
27 #include <linux/init.h>
28 #include <linux/initrd.h>
29 #include <linux/memblock.h>
30 #include <linux/acpi.h>
31 #include <linux/bootconfig.h>
32 #include <linux/console.h>
33 #include <linux/nmi.h>
34 #include <linux/percpu.h>
35 #include <linux/kmod.h>
36 #include <linux/kprobes.h>
37 #include <linux/kmsan.h>
38 #include <linux/vmalloc.h>
39 #include <linux/kernel_stat.h>
40 #include <linux/start_kernel.h>
41 #include <linux/security.h>
42 #include <linux/smp.h>
43 #include <linux/profile.h>
44 #include <linux/kfence.h>
45 #include <linux/rcupdate.h>
46 #include <linux/srcu.h>
47 #include <linux/moduleparam.h>
48 #include <linux/kallsyms.h>
49 #include <linux/buildid.h>
50 #include <linux/writeback.h>
51 #include <linux/cpu.h>
52 #include <linux/cpuset.h>
53 #include <linux/cgroup.h>
54 #include <linux/efi.h>
55 #include <linux/tick.h>
56 #include <linux/sched/isolation.h>
57 #include <linux/interrupt.h>
58 #include <linux/taskstats_kern.h>
59 #include <linux/delayacct.h>
60 #include <linux/unistd.h>
61 #include <linux/utsname.h>
62 #include <linux/rmap.h>
63 #include <linux/mempolicy.h>
64 #include <linux/key.h>
65 #include <linux/page_ext.h>
66 #include <linux/debug_locks.h>
67 #include <linux/debugobjects.h>
68 #include <linux/lockdep.h>
69 #include <linux/kmemleak.h>
70 #include <linux/padata.h>
71 #include <linux/pid_namespace.h>
72 #include <linux/device/driver.h>
73 #include <linux/kthread.h>
74 #include <linux/sched.h>
75 #include <linux/sched/init.h>
76 #include <linux/signal.h>
77 #include <linux/idr.h>
78 #include <linux/kgdb.h>
79 #include <linux/ftrace.h>
80 #include <linux/async.h>
81 #include <linux/shmem_fs.h>
82 #include <linux/slab.h>
83 #include <linux/perf_event.h>
84 #include <linux/ptrace.h>
85 #include <linux/pti.h>
86 #include <linux/blkdev.h>
87 #include <linux/sched/clock.h>
88 #include <linux/sched/task.h>
89 #include <linux/sched/task_stack.h>
90 #include <linux/context_tracking.h>
91 #include <linux/random.h>
92 #include <linux/list.h>
93 #include <linux/integrity.h>
94 #include <linux/proc_ns.h>
95 #include <linux/io.h>
96 #include <linux/cache.h>
97 #include <linux/rodata_test.h>
98 #include <linux/jump_label.h>
99 #include <linux/mem_encrypt.h>
100 #include <linux/kcsan.h>
101 #include <linux/init_syscalls.h>
102 #include <linux/stackdepot.h>
103 #include <linux/randomize_kstack.h>
104 #include <net/net_namespace.h>
105
106 #include <asm/io.h>
107 #include <asm/bugs.h>
108 #include <asm/setup.h>
109 #include <asm/sections.h>
110 #include <asm/cacheflush.h>
111
112 #define CREATE_TRACE_POINTS
113 #include <trace/events/initcall.h>
114
115 #include <kunit/test.h>
116
117 static int kernel_init(void *);
118
119 extern void init_IRQ(void);
120 extern void radix_tree_init(void);
121 extern void maple_tree_init(void);
122
123 /*
124 * Debug helper: via this flag we know that we are in 'early bootup code'
125 * where only the boot processor is running with IRQ disabled. This means
126 * two things - IRQ must not be enabled before the flag is cleared and some
127 * operations which are not allowed with IRQ disabled are allowed while the
128 * flag is set.
129 */
130 bool early_boot_irqs_disabled __read_mostly;
131
132 enum system_states system_state __read_mostly;
133 EXPORT_SYMBOL(system_state);
134
135 /*
136 * Boot command-line arguments
137 */
138 #define MAX_INIT_ARGS CONFIG_INIT_ENV_ARG_LIMIT
139 #define MAX_INIT_ENVS CONFIG_INIT_ENV_ARG_LIMIT
140
141 extern void time_init(void);
142 /* Default late time init is NULL. archs can override this later. */
143 void (*__initdata late_time_init)(void);
144
145 /* Untouched command line saved by arch-specific code. */
146 char __initdata boot_command_line[COMMAND_LINE_SIZE];
147 /* Untouched saved command line (eg. for /proc) */
148 char *saved_command_line __ro_after_init;
149 unsigned int saved_command_line_len __ro_after_init;
150 /* Command line for parameter parsing */
151 static char *static_command_line;
152 /* Untouched extra command line */
153 static char *extra_command_line;
154 /* Extra init arguments */
155 static char *extra_init_args;
156
157 #ifdef CONFIG_BOOT_CONFIG
158 /* Is bootconfig on command line? */
159 static bool bootconfig_found = IS_ENABLED(CONFIG_BOOT_CONFIG_FORCE);
160 static size_t initargs_offs;
161 #else
162 # define bootconfig_found false
163 # define initargs_offs 0
164 #endif
165
166 static char *execute_command;
167 static char *ramdisk_execute_command = "/init";
168
169 /*
170 * Used to generate warnings if static_key manipulation functions are used
171 * before jump_label_init is called.
172 */
173 bool static_key_initialized __read_mostly;
174 EXPORT_SYMBOL_GPL(static_key_initialized);
175
176 /*
177 * If set, this is an indication to the drivers that reset the underlying
178 * device before going ahead with the initialization otherwise driver might
179 * rely on the BIOS and skip the reset operation.
180 *
181 * This is useful if kernel is booting in an unreliable environment.
182 * For ex. kdump situation where previous kernel has crashed, BIOS has been
183 * skipped and devices will be in unknown state.
184 */
185 unsigned int reset_devices;
186 EXPORT_SYMBOL(reset_devices);
187
set_reset_devices(char * str)188 static int __init set_reset_devices(char *str)
189 {
190 reset_devices = 1;
191 return 1;
192 }
193
194 __setup("reset_devices", set_reset_devices);
195
196 static const char *argv_init[MAX_INIT_ARGS+2] = { "init", NULL, };
197 const char *envp_init[MAX_INIT_ENVS+2] = { "HOME=/", "TERM=linux", NULL, };
198 static const char *panic_later, *panic_param;
199
200 extern const struct obs_kernel_param __setup_start[], __setup_end[];
201
obsolete_checksetup(char * line)202 static bool __init obsolete_checksetup(char *line)
203 {
204 const struct obs_kernel_param *p;
205 bool had_early_param = false;
206
207 p = __setup_start;
208 do {
209 int n = strlen(p->str);
210 if (parameqn(line, p->str, n)) {
211 if (p->early) {
212 /* Already done in parse_early_param?
213 * (Needs exact match on param part).
214 * Keep iterating, as we can have early
215 * params and __setups of same names 8( */
216 if (line[n] == '\0' || line[n] == '=')
217 had_early_param = true;
218 } else if (!p->setup_func) {
219 pr_warn("Parameter %s is obsolete, ignored\n",
220 p->str);
221 return true;
222 } else if (p->setup_func(line + n))
223 return true;
224 }
225 p++;
226 } while (p < __setup_end);
227
228 return had_early_param;
229 }
230
231 /*
232 * This should be approx 2 Bo*oMips to start (note initial shift), and will
233 * still work even if initially too large, it will just take slightly longer
234 */
235 unsigned long loops_per_jiffy = (1<<12);
236 EXPORT_SYMBOL(loops_per_jiffy);
237
debug_kernel(char * str)238 static int __init debug_kernel(char *str)
239 {
240 console_loglevel = CONSOLE_LOGLEVEL_DEBUG;
241 return 0;
242 }
243
quiet_kernel(char * str)244 static int __init quiet_kernel(char *str)
245 {
246 console_loglevel = CONSOLE_LOGLEVEL_QUIET;
247 return 0;
248 }
249
250 early_param("debug", debug_kernel);
251 early_param("quiet", quiet_kernel);
252
loglevel(char * str)253 static int __init loglevel(char *str)
254 {
255 int newlevel;
256
257 /*
258 * Only update loglevel value when a correct setting was passed,
259 * to prevent blind crashes (when loglevel being set to 0) that
260 * are quite hard to debug
261 */
262 if (get_option(&str, &newlevel)) {
263 console_loglevel = newlevel;
264 return 0;
265 }
266
267 return -EINVAL;
268 }
269
270 early_param("loglevel", loglevel);
271
272 #ifdef CONFIG_BLK_DEV_INITRD
get_boot_config_from_initrd(size_t * _size)273 static void * __init get_boot_config_from_initrd(size_t *_size)
274 {
275 u32 size, csum;
276 char *data;
277 u32 *hdr;
278 int i;
279
280 if (!initrd_end)
281 return NULL;
282
283 data = (char *)initrd_end - BOOTCONFIG_MAGIC_LEN;
284 /*
285 * Since Grub may align the size of initrd to 4, we must
286 * check the preceding 3 bytes as well.
287 */
288 for (i = 0; i < 4; i++) {
289 if (!memcmp(data, BOOTCONFIG_MAGIC, BOOTCONFIG_MAGIC_LEN))
290 goto found;
291 data--;
292 }
293 return NULL;
294
295 found:
296 hdr = (u32 *)(data - 8);
297 size = le32_to_cpu(hdr[0]);
298 csum = le32_to_cpu(hdr[1]);
299
300 data = ((void *)hdr) - size;
301 if ((unsigned long)data < initrd_start) {
302 pr_err("bootconfig size %d is greater than initrd size %ld\n",
303 size, initrd_end - initrd_start);
304 return NULL;
305 }
306
307 if (xbc_calc_checksum(data, size) != csum) {
308 pr_err("bootconfig checksum failed\n");
309 return NULL;
310 }
311
312 /* Remove bootconfig from initramfs/initrd */
313 initrd_end = (unsigned long)data;
314 if (_size)
315 *_size = size;
316
317 return data;
318 }
319 #else
get_boot_config_from_initrd(size_t * _size)320 static void * __init get_boot_config_from_initrd(size_t *_size)
321 {
322 return NULL;
323 }
324 #endif
325
326 #ifdef CONFIG_BOOT_CONFIG
327
328 static char xbc_namebuf[XBC_KEYLEN_MAX] __initdata;
329
330 #define rest(dst, end) ((end) > (dst) ? (end) - (dst) : 0)
331
xbc_snprint_cmdline(char * buf,size_t size,struct xbc_node * root)332 static int __init xbc_snprint_cmdline(char *buf, size_t size,
333 struct xbc_node *root)
334 {
335 struct xbc_node *knode, *vnode;
336 char *end = buf + size;
337 const char *val;
338 int ret;
339
340 xbc_node_for_each_key_value(root, knode, val) {
341 ret = xbc_node_compose_key_after(root, knode,
342 xbc_namebuf, XBC_KEYLEN_MAX);
343 if (ret < 0)
344 return ret;
345
346 vnode = xbc_node_get_child(knode);
347 if (!vnode) {
348 ret = snprintf(buf, rest(buf, end), "%s ", xbc_namebuf);
349 if (ret < 0)
350 return ret;
351 buf += ret;
352 continue;
353 }
354 xbc_array_for_each_value(vnode, val) {
355 ret = snprintf(buf, rest(buf, end), "%s=\"%s\" ",
356 xbc_namebuf, val);
357 if (ret < 0)
358 return ret;
359 buf += ret;
360 }
361 }
362
363 return buf - (end - size);
364 }
365 #undef rest
366
367 /* Make an extra command line under given key word */
xbc_make_cmdline(const char * key)368 static char * __init xbc_make_cmdline(const char *key)
369 {
370 struct xbc_node *root;
371 char *new_cmdline;
372 int ret, len = 0;
373
374 root = xbc_find_node(key);
375 if (!root)
376 return NULL;
377
378 /* Count required buffer size */
379 len = xbc_snprint_cmdline(NULL, 0, root);
380 if (len <= 0)
381 return NULL;
382
383 new_cmdline = memblock_alloc(len + 1, SMP_CACHE_BYTES);
384 if (!new_cmdline) {
385 pr_err("Failed to allocate memory for extra kernel cmdline.\n");
386 return NULL;
387 }
388
389 ret = xbc_snprint_cmdline(new_cmdline, len + 1, root);
390 if (ret < 0 || ret > len) {
391 pr_err("Failed to print extra kernel cmdline.\n");
392 memblock_free(new_cmdline, len + 1);
393 return NULL;
394 }
395
396 return new_cmdline;
397 }
398
bootconfig_params(char * param,char * val,const char * unused,void * arg)399 static int __init bootconfig_params(char *param, char *val,
400 const char *unused, void *arg)
401 {
402 if (strcmp(param, "bootconfig") == 0) {
403 bootconfig_found = true;
404 }
405 return 0;
406 }
407
warn_bootconfig(char * str)408 static int __init warn_bootconfig(char *str)
409 {
410 /* The 'bootconfig' has been handled by bootconfig_params(). */
411 return 0;
412 }
413
setup_boot_config(void)414 static void __init setup_boot_config(void)
415 {
416 static char tmp_cmdline[COMMAND_LINE_SIZE] __initdata;
417 const char *msg, *data;
418 int pos, ret;
419 size_t size;
420 char *err;
421
422 /* Cut out the bootconfig data even if we have no bootconfig option */
423 data = get_boot_config_from_initrd(&size);
424 /* If there is no bootconfig in initrd, try embedded one. */
425 if (!data)
426 data = xbc_get_embedded_bootconfig(&size);
427
428 strscpy(tmp_cmdline, boot_command_line, COMMAND_LINE_SIZE);
429 err = parse_args("bootconfig", tmp_cmdline, NULL, 0, 0, 0, NULL,
430 bootconfig_params);
431
432 if (IS_ERR(err) || !bootconfig_found)
433 return;
434
435 /* parse_args() stops at the next param of '--' and returns an address */
436 if (err)
437 initargs_offs = err - tmp_cmdline;
438
439 if (!data) {
440 pr_err("'bootconfig' found on command line, but no bootconfig found\n");
441 return;
442 }
443
444 if (size >= XBC_DATA_MAX) {
445 pr_err("bootconfig size %ld greater than max size %d\n",
446 (long)size, XBC_DATA_MAX);
447 return;
448 }
449
450 ret = xbc_init(data, size, &msg, &pos);
451 if (ret < 0) {
452 if (pos < 0)
453 pr_err("Failed to init bootconfig: %s.\n", msg);
454 else
455 pr_err("Failed to parse bootconfig: %s at %d.\n",
456 msg, pos);
457 } else {
458 xbc_get_info(&ret, NULL);
459 pr_info("Load bootconfig: %ld bytes %d nodes\n", (long)size, ret);
460 /* keys starting with "kernel." are passed via cmdline */
461 extra_command_line = xbc_make_cmdline("kernel");
462 /* Also, "init." keys are init arguments */
463 extra_init_args = xbc_make_cmdline("init");
464 }
465 return;
466 }
467
exit_boot_config(void)468 static void __init exit_boot_config(void)
469 {
470 xbc_exit();
471 }
472
473 #else /* !CONFIG_BOOT_CONFIG */
474
setup_boot_config(void)475 static void __init setup_boot_config(void)
476 {
477 /* Remove bootconfig data from initrd */
478 get_boot_config_from_initrd(NULL);
479 }
480
warn_bootconfig(char * str)481 static int __init warn_bootconfig(char *str)
482 {
483 pr_warn("WARNING: 'bootconfig' found on the kernel command line but CONFIG_BOOT_CONFIG is not set.\n");
484 return 0;
485 }
486
487 #define exit_boot_config() do {} while (0)
488
489 #endif /* CONFIG_BOOT_CONFIG */
490
491 early_param("bootconfig", warn_bootconfig);
492
493 /* Change NUL term back to "=", to make "param" the whole string. */
repair_env_string(char * param,char * val)494 static void __init repair_env_string(char *param, char *val)
495 {
496 if (val) {
497 /* param=val or param="val"? */
498 if (val == param+strlen(param)+1)
499 val[-1] = '=';
500 else if (val == param+strlen(param)+2) {
501 val[-2] = '=';
502 memmove(val-1, val, strlen(val)+1);
503 } else
504 BUG();
505 }
506 }
507
508 /* Anything after -- gets handed straight to init. */
set_init_arg(char * param,char * val,const char * unused,void * arg)509 static int __init set_init_arg(char *param, char *val,
510 const char *unused, void *arg)
511 {
512 unsigned int i;
513
514 if (panic_later)
515 return 0;
516
517 repair_env_string(param, val);
518
519 for (i = 0; argv_init[i]; i++) {
520 if (i == MAX_INIT_ARGS) {
521 panic_later = "init";
522 panic_param = param;
523 return 0;
524 }
525 }
526 argv_init[i] = param;
527 return 0;
528 }
529
530 /*
531 * Unknown boot options get handed to init, unless they look like
532 * unused parameters (modprobe will find them in /proc/cmdline).
533 */
unknown_bootoption(char * param,char * val,const char * unused,void * arg)534 static int __init unknown_bootoption(char *param, char *val,
535 const char *unused, void *arg)
536 {
537 size_t len = strlen(param);
538
539 repair_env_string(param, val);
540
541 /* Handle obsolete-style parameters */
542 if (obsolete_checksetup(param))
543 return 0;
544
545 /* Unused module parameter. */
546 if (strnchr(param, len, '.'))
547 return 0;
548
549 if (panic_later)
550 return 0;
551
552 if (val) {
553 /* Environment option */
554 unsigned int i;
555 for (i = 0; envp_init[i]; i++) {
556 if (i == MAX_INIT_ENVS) {
557 panic_later = "env";
558 panic_param = param;
559 }
560 if (!strncmp(param, envp_init[i], len+1))
561 break;
562 }
563 envp_init[i] = param;
564 } else {
565 /* Command line option */
566 unsigned int i;
567 for (i = 0; argv_init[i]; i++) {
568 if (i == MAX_INIT_ARGS) {
569 panic_later = "init";
570 panic_param = param;
571 }
572 }
573 argv_init[i] = param;
574 }
575 return 0;
576 }
577
init_setup(char * str)578 static int __init init_setup(char *str)
579 {
580 unsigned int i;
581
582 execute_command = str;
583 /*
584 * In case LILO is going to boot us with default command line,
585 * it prepends "auto" before the whole cmdline which makes
586 * the shell think it should execute a script with such name.
587 * So we ignore all arguments entered _before_ init=... [MJ]
588 */
589 for (i = 1; i < MAX_INIT_ARGS; i++)
590 argv_init[i] = NULL;
591 return 1;
592 }
593 __setup("init=", init_setup);
594
rdinit_setup(char * str)595 static int __init rdinit_setup(char *str)
596 {
597 unsigned int i;
598
599 ramdisk_execute_command = str;
600 /* See "auto" comment in init_setup */
601 for (i = 1; i < MAX_INIT_ARGS; i++)
602 argv_init[i] = NULL;
603 return 1;
604 }
605 __setup("rdinit=", rdinit_setup);
606
607 #ifndef CONFIG_SMP
608 static const unsigned int setup_max_cpus = NR_CPUS;
setup_nr_cpu_ids(void)609 static inline void setup_nr_cpu_ids(void) { }
smp_prepare_cpus(unsigned int maxcpus)610 static inline void smp_prepare_cpus(unsigned int maxcpus) { }
611 #endif
612
613 /*
614 * We need to store the untouched command line for future reference.
615 * We also need to store the touched command line since the parameter
616 * parsing is performed in place, and we should allow a component to
617 * store reference of name/value for future reference.
618 */
setup_command_line(char * command_line)619 static void __init setup_command_line(char *command_line)
620 {
621 size_t len, xlen = 0, ilen = 0;
622
623 if (extra_command_line)
624 xlen = strlen(extra_command_line);
625 if (extra_init_args)
626 ilen = strlen(extra_init_args) + 4; /* for " -- " */
627
628 len = xlen + strlen(boot_command_line) + 1;
629
630 saved_command_line = memblock_alloc(len + ilen, SMP_CACHE_BYTES);
631 if (!saved_command_line)
632 panic("%s: Failed to allocate %zu bytes\n", __func__, len + ilen);
633
634 static_command_line = memblock_alloc(len, SMP_CACHE_BYTES);
635 if (!static_command_line)
636 panic("%s: Failed to allocate %zu bytes\n", __func__, len);
637
638 if (xlen) {
639 /*
640 * We have to put extra_command_line before boot command
641 * lines because there could be dashes (separator of init
642 * command line) in the command lines.
643 */
644 strcpy(saved_command_line, extra_command_line);
645 strcpy(static_command_line, extra_command_line);
646 }
647 strcpy(saved_command_line + xlen, boot_command_line);
648 strcpy(static_command_line + xlen, command_line);
649
650 if (ilen) {
651 /*
652 * Append supplemental init boot args to saved_command_line
653 * so that user can check what command line options passed
654 * to init.
655 * The order should always be
656 * " -- "[bootconfig init-param][cmdline init-param]
657 */
658 if (initargs_offs) {
659 len = xlen + initargs_offs;
660 strcpy(saved_command_line + len, extra_init_args);
661 len += ilen - 4; /* strlen(extra_init_args) */
662 strcpy(saved_command_line + len,
663 boot_command_line + initargs_offs - 1);
664 } else {
665 len = strlen(saved_command_line);
666 strcpy(saved_command_line + len, " -- ");
667 len += 4;
668 strcpy(saved_command_line + len, extra_init_args);
669 }
670 }
671
672 saved_command_line_len = strlen(saved_command_line);
673 }
674
675 /*
676 * We need to finalize in a non-__init function or else race conditions
677 * between the root thread and the init thread may cause start_kernel to
678 * be reaped by free_initmem before the root thread has proceeded to
679 * cpu_idle.
680 *
681 * gcc-3.4 accidentally inlines this function, so use noinline.
682 */
683
684 static __initdata DECLARE_COMPLETION(kthreadd_done);
685
rest_init(void)686 noinline void __ref rest_init(void)
687 {
688 struct task_struct *tsk;
689 int pid;
690
691 rcu_scheduler_starting();
692 /*
693 * We need to spawn init first so that it obtains pid 1, however
694 * the init task will end up wanting to create kthreads, which, if
695 * we schedule it before we create kthreadd, will OOPS.
696 */
697 pid = user_mode_thread(kernel_init, NULL, CLONE_FS);
698 /*
699 * Pin init on the boot CPU. Task migration is not properly working
700 * until sched_init_smp() has been run. It will set the allowed
701 * CPUs for init to the non isolated CPUs.
702 */
703 rcu_read_lock();
704 tsk = find_task_by_pid_ns(pid, &init_pid_ns);
705 tsk->flags |= PF_NO_SETAFFINITY;
706 set_cpus_allowed_ptr(tsk, cpumask_of(smp_processor_id()));
707 rcu_read_unlock();
708
709 numa_default_policy();
710 pid = kernel_thread(kthreadd, NULL, CLONE_FS | CLONE_FILES);
711 rcu_read_lock();
712 kthreadd_task = find_task_by_pid_ns(pid, &init_pid_ns);
713 rcu_read_unlock();
714
715 /*
716 * Enable might_sleep() and smp_processor_id() checks.
717 * They cannot be enabled earlier because with CONFIG_PREEMPTION=y
718 * kernel_thread() would trigger might_sleep() splats. With
719 * CONFIG_PREEMPT_VOLUNTARY=y the init task might have scheduled
720 * already, but it's stuck on the kthreadd_done completion.
721 */
722 system_state = SYSTEM_SCHEDULING;
723
724 complete(&kthreadd_done);
725
726 /*
727 * The boot idle thread must execute schedule()
728 * at least once to get things moving:
729 */
730 schedule_preempt_disabled();
731 /* Call into cpu_idle with preempt disabled */
732 cpu_startup_entry(CPUHP_ONLINE);
733 }
734
735 /* Check for early params. */
do_early_param(char * param,char * val,const char * unused,void * arg)736 static int __init do_early_param(char *param, char *val,
737 const char *unused, void *arg)
738 {
739 const struct obs_kernel_param *p;
740
741 for (p = __setup_start; p < __setup_end; p++) {
742 if ((p->early && parameq(param, p->str)) ||
743 (strcmp(param, "console") == 0 &&
744 strcmp(p->str, "earlycon") == 0)
745 ) {
746 if (p->setup_func(val) != 0)
747 pr_warn("Malformed early option '%s'\n", param);
748 }
749 }
750 /* We accept everything at this stage. */
751 return 0;
752 }
753
parse_early_options(char * cmdline)754 void __init parse_early_options(char *cmdline)
755 {
756 parse_args("early options", cmdline, NULL, 0, 0, 0, NULL,
757 do_early_param);
758 }
759
760 /* Arch code calls this early on, or if not, just before other parsing. */
parse_early_param(void)761 void __init parse_early_param(void)
762 {
763 static int done __initdata;
764 static char tmp_cmdline[COMMAND_LINE_SIZE] __initdata;
765
766 if (done)
767 return;
768
769 /* All fall through to do_early_param. */
770 strscpy(tmp_cmdline, boot_command_line, COMMAND_LINE_SIZE);
771 parse_early_options(tmp_cmdline);
772 done = 1;
773 }
774
arch_post_acpi_subsys_init(void)775 void __init __weak arch_post_acpi_subsys_init(void) { }
776
smp_setup_processor_id(void)777 void __init __weak smp_setup_processor_id(void)
778 {
779 }
780
781 # if THREAD_SIZE >= PAGE_SIZE
thread_stack_cache_init(void)782 void __init __weak thread_stack_cache_init(void)
783 {
784 }
785 #endif
786
mem_encrypt_init(void)787 void __init __weak mem_encrypt_init(void) { }
788
poking_init(void)789 void __init __weak poking_init(void) { }
790
pgtable_cache_init(void)791 void __init __weak pgtable_cache_init(void) { }
792
trap_init(void)793 void __init __weak trap_init(void) { }
794
795 bool initcall_debug;
796 core_param(initcall_debug, initcall_debug, bool, 0644);
797
798 #ifdef TRACEPOINTS_ENABLED
799 static void __init initcall_debug_enable(void);
800 #else
initcall_debug_enable(void)801 static inline void initcall_debug_enable(void)
802 {
803 }
804 #endif
805
806 /* Report memory auto-initialization states for this boot. */
report_meminit(void)807 static void __init report_meminit(void)
808 {
809 const char *stack;
810
811 if (IS_ENABLED(CONFIG_INIT_STACK_ALL_PATTERN))
812 stack = "all(pattern)";
813 else if (IS_ENABLED(CONFIG_INIT_STACK_ALL_ZERO))
814 stack = "all(zero)";
815 else if (IS_ENABLED(CONFIG_GCC_PLUGIN_STRUCTLEAK_BYREF_ALL))
816 stack = "byref_all(zero)";
817 else if (IS_ENABLED(CONFIG_GCC_PLUGIN_STRUCTLEAK_BYREF))
818 stack = "byref(zero)";
819 else if (IS_ENABLED(CONFIG_GCC_PLUGIN_STRUCTLEAK_USER))
820 stack = "__user(zero)";
821 else
822 stack = "off";
823
824 pr_info("mem auto-init: stack:%s, heap alloc:%s, heap free:%s\n",
825 stack, want_init_on_alloc(GFP_KERNEL) ? "on" : "off",
826 want_init_on_free() ? "on" : "off");
827 if (want_init_on_free())
828 pr_info("mem auto-init: clearing system memory may take some time...\n");
829 }
830
831 /*
832 * Set up kernel memory allocators
833 */
mm_init(void)834 static void __init mm_init(void)
835 {
836 /*
837 * page_ext requires contiguous pages,
838 * bigger than MAX_ORDER unless SPARSEMEM.
839 */
840 page_ext_init_flatmem();
841 init_mem_debugging_and_hardening();
842 kfence_alloc_pool();
843 report_meminit();
844 kmsan_init_shadow();
845 stack_depot_early_init();
846 mem_init();
847 mem_init_print_info();
848 kmem_cache_init();
849 /*
850 * page_owner must be initialized after buddy is ready, and also after
851 * slab is ready so that stack_depot_init() works properly
852 */
853 page_ext_init_flatmem_late();
854 kmemleak_init();
855 pgtable_init();
856 debug_objects_mem_init();
857 vmalloc_init();
858 /* If no deferred init page_ext now, as vmap is fully initialized */
859 if (!deferred_struct_pages)
860 page_ext_init();
861 /* Should be run before the first non-init thread is created */
862 init_espfix_bsp();
863 /* Should be run after espfix64 is set up. */
864 pti_init();
865 kmsan_init_runtime();
866 mm_cache_init();
867 }
868
869 #ifdef CONFIG_RANDOMIZE_KSTACK_OFFSET
870 DEFINE_STATIC_KEY_MAYBE_RO(CONFIG_RANDOMIZE_KSTACK_OFFSET_DEFAULT,
871 randomize_kstack_offset);
872 DEFINE_PER_CPU(u32, kstack_offset);
873
early_randomize_kstack_offset(char * buf)874 static int __init early_randomize_kstack_offset(char *buf)
875 {
876 int ret;
877 bool bool_result;
878
879 ret = kstrtobool(buf, &bool_result);
880 if (ret)
881 return ret;
882
883 if (bool_result)
884 static_branch_enable(&randomize_kstack_offset);
885 else
886 static_branch_disable(&randomize_kstack_offset);
887 return 0;
888 }
889 early_param("randomize_kstack_offset", early_randomize_kstack_offset);
890 #endif
891
arch_call_rest_init(void)892 void __init __weak arch_call_rest_init(void)
893 {
894 rest_init();
895 }
896
print_unknown_bootoptions(void)897 static void __init print_unknown_bootoptions(void)
898 {
899 char *unknown_options;
900 char *end;
901 const char *const *p;
902 size_t len;
903
904 if (panic_later || (!argv_init[1] && !envp_init[2]))
905 return;
906
907 /*
908 * Determine how many options we have to print out, plus a space
909 * before each
910 */
911 len = 1; /* null terminator */
912 for (p = &argv_init[1]; *p; p++) {
913 len++;
914 len += strlen(*p);
915 }
916 for (p = &envp_init[2]; *p; p++) {
917 len++;
918 len += strlen(*p);
919 }
920
921 unknown_options = memblock_alloc(len, SMP_CACHE_BYTES);
922 if (!unknown_options) {
923 pr_err("%s: Failed to allocate %zu bytes\n",
924 __func__, len);
925 return;
926 }
927 end = unknown_options;
928
929 for (p = &argv_init[1]; *p; p++)
930 end += sprintf(end, " %s", *p);
931 for (p = &envp_init[2]; *p; p++)
932 end += sprintf(end, " %s", *p);
933
934 /* Start at unknown_options[1] to skip the initial space */
935 pr_notice("Unknown kernel command line parameters \"%s\", will be passed to user space.\n",
936 &unknown_options[1]);
937 memblock_free(unknown_options, len);
938 }
939
start_kernel(void)940 asmlinkage __visible void __init __no_sanitize_address start_kernel(void)
941 {
942 char *command_line;
943 char *after_dashes;
944
945 set_task_stack_end_magic(&init_task);
946 smp_setup_processor_id();
947 debug_objects_early_init();
948 init_vmlinux_build_id();
949
950 cgroup_init_early();
951
952 local_irq_disable();
953 early_boot_irqs_disabled = true;
954
955 /*
956 * Interrupts are still disabled. Do necessary setups, then
957 * enable them.
958 */
959 boot_cpu_init();
960 page_address_init();
961 pr_notice("%s", linux_banner);
962 early_security_init();
963 setup_arch(&command_line);
964 setup_boot_config();
965 setup_command_line(command_line);
966 setup_nr_cpu_ids();
967 setup_per_cpu_areas();
968 smp_prepare_boot_cpu(); /* arch-specific boot-cpu hooks */
969 boot_cpu_hotplug_init();
970
971 build_all_zonelists(NULL);
972 page_alloc_init();
973
974 pr_notice("Kernel command line: %s\n", saved_command_line);
975 /* parameters may set static keys */
976 jump_label_init();
977 parse_early_param();
978 after_dashes = parse_args("Booting kernel",
979 static_command_line, __start___param,
980 __stop___param - __start___param,
981 -1, -1, NULL, &unknown_bootoption);
982 print_unknown_bootoptions();
983 if (!IS_ERR_OR_NULL(after_dashes))
984 parse_args("Setting init args", after_dashes, NULL, 0, -1, -1,
985 NULL, set_init_arg);
986 if (extra_init_args)
987 parse_args("Setting extra init args", extra_init_args,
988 NULL, 0, -1, -1, NULL, set_init_arg);
989
990 /* Architectural and non-timekeeping rng init, before allocator init */
991 random_init_early(command_line);
992
993 /*
994 * These use large bootmem allocations and must precede
995 * kmem_cache_init()
996 */
997 setup_log_buf(0);
998 vfs_caches_init_early();
999 sort_main_extable();
1000 trap_init();
1001 mm_init();
1002 poking_init();
1003 ftrace_init();
1004
1005 /* trace_printk can be enabled here */
1006 early_trace_init();
1007
1008 /*
1009 * Set up the scheduler prior starting any interrupts (such as the
1010 * timer interrupt). Full topology setup happens at smp_init()
1011 * time - but meanwhile we still have a functioning scheduler.
1012 */
1013 sched_init();
1014
1015 if (WARN(!irqs_disabled(),
1016 "Interrupts were enabled *very* early, fixing it\n"))
1017 local_irq_disable();
1018 radix_tree_init();
1019 maple_tree_init();
1020
1021 /*
1022 * Set up housekeeping before setting up workqueues to allow the unbound
1023 * workqueue to take non-housekeeping into account.
1024 */
1025 housekeeping_init();
1026
1027 /*
1028 * Allow workqueue creation and work item queueing/cancelling
1029 * early. Work item execution depends on kthreads and starts after
1030 * workqueue_init().
1031 */
1032 workqueue_init_early();
1033
1034 rcu_init();
1035
1036 /* Trace events are available after this */
1037 trace_init();
1038
1039 if (initcall_debug)
1040 initcall_debug_enable();
1041
1042 context_tracking_init();
1043 /* init some links before init_ISA_irqs() */
1044 early_irq_init();
1045 init_IRQ();
1046 tick_init();
1047 rcu_init_nohz();
1048 init_timers();
1049 srcu_init();
1050 hrtimers_init();
1051 softirq_init();
1052 timekeeping_init();
1053 time_init();
1054
1055 /* This must be after timekeeping is initialized */
1056 random_init();
1057
1058 /* These make use of the fully initialized rng */
1059 kfence_init();
1060 boot_init_stack_canary();
1061
1062 perf_event_init();
1063 profile_init();
1064 call_function_init();
1065 WARN(!irqs_disabled(), "Interrupts were enabled early\n");
1066
1067 early_boot_irqs_disabled = false;
1068 local_irq_enable();
1069
1070 kmem_cache_init_late();
1071
1072 /*
1073 * HACK ALERT! This is early. We're enabling the console before
1074 * we've done PCI setups etc, and console_init() must be aware of
1075 * this. But we do want output early, in case something goes wrong.
1076 */
1077 console_init();
1078 if (panic_later)
1079 panic("Too many boot %s vars at `%s'", panic_later,
1080 panic_param);
1081
1082 lockdep_init();
1083
1084 /*
1085 * Need to run this when irqs are enabled, because it wants
1086 * to self-test [hard/soft]-irqs on/off lock inversion bugs
1087 * too:
1088 */
1089 locking_selftest();
1090
1091 /*
1092 * This needs to be called before any devices perform DMA
1093 * operations that might use the SWIOTLB bounce buffers. It will
1094 * mark the bounce buffers as decrypted so that their usage will
1095 * not cause "plain-text" data to be decrypted when accessed.
1096 */
1097 mem_encrypt_init();
1098
1099 #ifdef CONFIG_BLK_DEV_INITRD
1100 if (initrd_start && !initrd_below_start_ok &&
1101 page_to_pfn(virt_to_page((void *)initrd_start)) < min_low_pfn) {
1102 pr_crit("initrd overwritten (0x%08lx < 0x%08lx) - disabling it.\n",
1103 page_to_pfn(virt_to_page((void *)initrd_start)),
1104 min_low_pfn);
1105 initrd_start = 0;
1106 }
1107 #endif
1108 setup_per_cpu_pageset();
1109 numa_policy_init();
1110 acpi_early_init();
1111 if (late_time_init)
1112 late_time_init();
1113 sched_clock_init();
1114 calibrate_delay();
1115 pid_idr_init();
1116 anon_vma_init();
1117 #ifdef CONFIG_X86
1118 if (efi_enabled(EFI_RUNTIME_SERVICES))
1119 efi_enter_virtual_mode();
1120 #endif
1121 thread_stack_cache_init();
1122 cred_init();
1123 fork_init();
1124 proc_caches_init();
1125 uts_ns_init();
1126 key_init();
1127 security_init();
1128 dbg_late_init();
1129 net_ns_init();
1130 vfs_caches_init();
1131 pagecache_init();
1132 signals_init();
1133 seq_file_init();
1134 proc_root_init();
1135 nsfs_init();
1136 cpuset_init();
1137 cgroup_init();
1138 taskstats_init_early();
1139 delayacct_init();
1140
1141 check_bugs();
1142
1143 acpi_subsystem_init();
1144 arch_post_acpi_subsys_init();
1145 kcsan_init();
1146
1147 /* Do the rest non-__init'ed, we're now alive */
1148 arch_call_rest_init();
1149
1150 prevent_tail_call_optimization();
1151 }
1152
1153 /* Call all constructor functions linked into the kernel. */
do_ctors(void)1154 static void __init do_ctors(void)
1155 {
1156 /*
1157 * For UML, the constructors have already been called by the
1158 * normal setup code as it's just a normal ELF binary, so we
1159 * cannot do it again - but we do need CONFIG_CONSTRUCTORS
1160 * even on UML for modules.
1161 */
1162 #if defined(CONFIG_CONSTRUCTORS) && !defined(CONFIG_UML)
1163 ctor_fn_t *fn = (ctor_fn_t *) __ctors_start;
1164
1165 for (; fn < (ctor_fn_t *) __ctors_end; fn++)
1166 (*fn)();
1167 #endif
1168 }
1169
1170 #ifdef CONFIG_KALLSYMS
1171 struct blacklist_entry {
1172 struct list_head next;
1173 char *buf;
1174 };
1175
1176 static __initdata_or_module LIST_HEAD(blacklisted_initcalls);
1177
initcall_blacklist(char * str)1178 static int __init initcall_blacklist(char *str)
1179 {
1180 char *str_entry;
1181 struct blacklist_entry *entry;
1182
1183 /* str argument is a comma-separated list of functions */
1184 do {
1185 str_entry = strsep(&str, ",");
1186 if (str_entry) {
1187 pr_debug("blacklisting initcall %s\n", str_entry);
1188 entry = memblock_alloc(sizeof(*entry),
1189 SMP_CACHE_BYTES);
1190 if (!entry)
1191 panic("%s: Failed to allocate %zu bytes\n",
1192 __func__, sizeof(*entry));
1193 entry->buf = memblock_alloc(strlen(str_entry) + 1,
1194 SMP_CACHE_BYTES);
1195 if (!entry->buf)
1196 panic("%s: Failed to allocate %zu bytes\n",
1197 __func__, strlen(str_entry) + 1);
1198 strcpy(entry->buf, str_entry);
1199 list_add(&entry->next, &blacklisted_initcalls);
1200 }
1201 } while (str_entry);
1202
1203 return 1;
1204 }
1205
initcall_blacklisted(initcall_t fn)1206 static bool __init_or_module initcall_blacklisted(initcall_t fn)
1207 {
1208 struct blacklist_entry *entry;
1209 char fn_name[KSYM_SYMBOL_LEN];
1210 unsigned long addr;
1211
1212 if (list_empty(&blacklisted_initcalls))
1213 return false;
1214
1215 addr = (unsigned long) dereference_function_descriptor(fn);
1216 sprint_symbol_no_offset(fn_name, addr);
1217
1218 /*
1219 * fn will be "function_name [module_name]" where [module_name] is not
1220 * displayed for built-in init functions. Strip off the [module_name].
1221 */
1222 strreplace(fn_name, ' ', '\0');
1223
1224 list_for_each_entry(entry, &blacklisted_initcalls, next) {
1225 if (!strcmp(fn_name, entry->buf)) {
1226 pr_debug("initcall %s blacklisted\n", fn_name);
1227 return true;
1228 }
1229 }
1230
1231 return false;
1232 }
1233 #else
initcall_blacklist(char * str)1234 static int __init initcall_blacklist(char *str)
1235 {
1236 pr_warn("initcall_blacklist requires CONFIG_KALLSYMS\n");
1237 return 0;
1238 }
1239
initcall_blacklisted(initcall_t fn)1240 static bool __init_or_module initcall_blacklisted(initcall_t fn)
1241 {
1242 return false;
1243 }
1244 #endif
1245 __setup("initcall_blacklist=", initcall_blacklist);
1246
1247 static __init_or_module void
trace_initcall_start_cb(void * data,initcall_t fn)1248 trace_initcall_start_cb(void *data, initcall_t fn)
1249 {
1250 ktime_t *calltime = data;
1251
1252 printk(KERN_DEBUG "calling %pS @ %i\n", fn, task_pid_nr(current));
1253 *calltime = ktime_get();
1254 }
1255
1256 static __init_or_module void
trace_initcall_finish_cb(void * data,initcall_t fn,int ret)1257 trace_initcall_finish_cb(void *data, initcall_t fn, int ret)
1258 {
1259 ktime_t rettime, *calltime = data;
1260
1261 rettime = ktime_get();
1262 printk(KERN_DEBUG "initcall %pS returned %d after %lld usecs\n",
1263 fn, ret, (unsigned long long)ktime_us_delta(rettime, *calltime));
1264 }
1265
1266 static ktime_t initcall_calltime;
1267
1268 #ifdef TRACEPOINTS_ENABLED
initcall_debug_enable(void)1269 static void __init initcall_debug_enable(void)
1270 {
1271 int ret;
1272
1273 ret = register_trace_initcall_start(trace_initcall_start_cb,
1274 &initcall_calltime);
1275 ret |= register_trace_initcall_finish(trace_initcall_finish_cb,
1276 &initcall_calltime);
1277 WARN(ret, "Failed to register initcall tracepoints\n");
1278 }
1279 # define do_trace_initcall_start trace_initcall_start
1280 # define do_trace_initcall_finish trace_initcall_finish
1281 #else
do_trace_initcall_start(initcall_t fn)1282 static inline void do_trace_initcall_start(initcall_t fn)
1283 {
1284 if (!initcall_debug)
1285 return;
1286 trace_initcall_start_cb(&initcall_calltime, fn);
1287 }
do_trace_initcall_finish(initcall_t fn,int ret)1288 static inline void do_trace_initcall_finish(initcall_t fn, int ret)
1289 {
1290 if (!initcall_debug)
1291 return;
1292 trace_initcall_finish_cb(&initcall_calltime, fn, ret);
1293 }
1294 #endif /* !TRACEPOINTS_ENABLED */
1295
do_one_initcall(initcall_t fn)1296 int __init_or_module do_one_initcall(initcall_t fn)
1297 {
1298 int count = preempt_count();
1299 char msgbuf[64];
1300 int ret;
1301
1302 if (initcall_blacklisted(fn))
1303 return -EPERM;
1304
1305 do_trace_initcall_start(fn);
1306 ret = fn();
1307 do_trace_initcall_finish(fn, ret);
1308
1309 msgbuf[0] = 0;
1310
1311 if (preempt_count() != count) {
1312 sprintf(msgbuf, "preemption imbalance ");
1313 preempt_count_set(count);
1314 }
1315 if (irqs_disabled()) {
1316 strlcat(msgbuf, "disabled interrupts ", sizeof(msgbuf));
1317 local_irq_enable();
1318 }
1319 WARN(msgbuf[0], "initcall %pS returned with %s\n", fn, msgbuf);
1320
1321 add_latent_entropy();
1322 return ret;
1323 }
1324
1325
1326 extern initcall_entry_t __initcall_start[];
1327 extern initcall_entry_t __initcall0_start[];
1328 extern initcall_entry_t __initcall1_start[];
1329 extern initcall_entry_t __initcall2_start[];
1330 extern initcall_entry_t __initcall3_start[];
1331 extern initcall_entry_t __initcall4_start[];
1332 extern initcall_entry_t __initcall5_start[];
1333 extern initcall_entry_t __initcall6_start[];
1334 extern initcall_entry_t __initcall7_start[];
1335 extern initcall_entry_t __initcall_end[];
1336
1337 static initcall_entry_t *initcall_levels[] __initdata = {
1338 __initcall0_start,
1339 __initcall1_start,
1340 __initcall2_start,
1341 __initcall3_start,
1342 __initcall4_start,
1343 __initcall5_start,
1344 __initcall6_start,
1345 __initcall7_start,
1346 __initcall_end,
1347 };
1348
1349 /* Keep these in sync with initcalls in include/linux/init.h */
1350 static const char *initcall_level_names[] __initdata = {
1351 "pure",
1352 "core",
1353 "postcore",
1354 "arch",
1355 "subsys",
1356 "fs",
1357 "device",
1358 "late",
1359 };
1360
ignore_unknown_bootoption(char * param,char * val,const char * unused,void * arg)1361 static int __init ignore_unknown_bootoption(char *param, char *val,
1362 const char *unused, void *arg)
1363 {
1364 return 0;
1365 }
1366
do_initcall_level(int level,char * command_line)1367 static void __init do_initcall_level(int level, char *command_line)
1368 {
1369 initcall_entry_t *fn;
1370
1371 parse_args(initcall_level_names[level],
1372 command_line, __start___param,
1373 __stop___param - __start___param,
1374 level, level,
1375 NULL, ignore_unknown_bootoption);
1376
1377 trace_initcall_level(initcall_level_names[level]);
1378 for (fn = initcall_levels[level]; fn < initcall_levels[level+1]; fn++)
1379 do_one_initcall(initcall_from_entry(fn));
1380 }
1381
do_initcalls(void)1382 static void __init do_initcalls(void)
1383 {
1384 int level;
1385 size_t len = saved_command_line_len + 1;
1386 char *command_line;
1387
1388 command_line = kzalloc(len, GFP_KERNEL);
1389 if (!command_line)
1390 panic("%s: Failed to allocate %zu bytes\n", __func__, len);
1391
1392 for (level = 0; level < ARRAY_SIZE(initcall_levels) - 1; level++) {
1393 /* Parser modifies command_line, restore it each time */
1394 strcpy(command_line, saved_command_line);
1395 do_initcall_level(level, command_line);
1396 }
1397
1398 kfree(command_line);
1399 }
1400
1401 /*
1402 * Ok, the machine is now initialized. None of the devices
1403 * have been touched yet, but the CPU subsystem is up and
1404 * running, and memory and process management works.
1405 *
1406 * Now we can finally start doing some real work..
1407 */
do_basic_setup(void)1408 static void __init do_basic_setup(void)
1409 {
1410 cpuset_init_smp();
1411 driver_init();
1412 init_irq_proc();
1413 do_ctors();
1414 do_initcalls();
1415 }
1416
do_pre_smp_initcalls(void)1417 static void __init do_pre_smp_initcalls(void)
1418 {
1419 initcall_entry_t *fn;
1420
1421 trace_initcall_level("early");
1422 for (fn = __initcall_start; fn < __initcall0_start; fn++)
1423 do_one_initcall(initcall_from_entry(fn));
1424 }
1425
run_init_process(const char * init_filename)1426 static int run_init_process(const char *init_filename)
1427 {
1428 const char *const *p;
1429
1430 argv_init[0] = init_filename;
1431 pr_info("Run %s as init process\n", init_filename);
1432 pr_debug(" with arguments:\n");
1433 for (p = argv_init; *p; p++)
1434 pr_debug(" %s\n", *p);
1435 pr_debug(" with environment:\n");
1436 for (p = envp_init; *p; p++)
1437 pr_debug(" %s\n", *p);
1438 return kernel_execve(init_filename, argv_init, envp_init);
1439 }
1440
try_to_run_init_process(const char * init_filename)1441 static int try_to_run_init_process(const char *init_filename)
1442 {
1443 int ret;
1444
1445 ret = run_init_process(init_filename);
1446
1447 if (ret && ret != -ENOENT) {
1448 pr_err("Starting init: %s exists but couldn't execute it (error %d)\n",
1449 init_filename, ret);
1450 }
1451
1452 return ret;
1453 }
1454
1455 static noinline void __init kernel_init_freeable(void);
1456
1457 #if defined(CONFIG_STRICT_KERNEL_RWX) || defined(CONFIG_STRICT_MODULE_RWX)
1458 bool rodata_enabled __ro_after_init = true;
1459
1460 #ifndef arch_parse_debug_rodata
arch_parse_debug_rodata(char * str)1461 static inline bool arch_parse_debug_rodata(char *str) { return false; }
1462 #endif
1463
set_debug_rodata(char * str)1464 static int __init set_debug_rodata(char *str)
1465 {
1466 if (arch_parse_debug_rodata(str))
1467 return 0;
1468
1469 if (str && !strcmp(str, "on"))
1470 rodata_enabled = true;
1471 else if (str && !strcmp(str, "off"))
1472 rodata_enabled = false;
1473 else
1474 pr_warn("Invalid option string for rodata: '%s'\n", str);
1475 return 0;
1476 }
1477 early_param("rodata", set_debug_rodata);
1478 #endif
1479
1480 #ifdef CONFIG_STRICT_KERNEL_RWX
mark_readonly(void)1481 static void mark_readonly(void)
1482 {
1483 if (rodata_enabled) {
1484 /*
1485 * load_module() results in W+X mappings, which are cleaned
1486 * up with call_rcu(). Let's make sure that queued work is
1487 * flushed so that we don't hit false positives looking for
1488 * insecure pages which are W+X.
1489 */
1490 rcu_barrier();
1491 mark_rodata_ro();
1492 rodata_test();
1493 } else
1494 pr_info("Kernel memory protection disabled.\n");
1495 }
1496 #elif defined(CONFIG_ARCH_HAS_STRICT_KERNEL_RWX)
mark_readonly(void)1497 static inline void mark_readonly(void)
1498 {
1499 pr_warn("Kernel memory protection not selected by kernel config.\n");
1500 }
1501 #else
mark_readonly(void)1502 static inline void mark_readonly(void)
1503 {
1504 pr_warn("This architecture does not have kernel memory protection.\n");
1505 }
1506 #endif
1507
free_initmem(void)1508 void __weak free_initmem(void)
1509 {
1510 free_initmem_default(POISON_FREE_INITMEM);
1511 }
1512
kernel_init(void * unused)1513 static int __ref kernel_init(void *unused)
1514 {
1515 int ret;
1516
1517 /*
1518 * Wait until kthreadd is all set-up.
1519 */
1520 wait_for_completion(&kthreadd_done);
1521
1522 kernel_init_freeable();
1523 /* need to finish all async __init code before freeing the memory */
1524 async_synchronize_full();
1525
1526 system_state = SYSTEM_FREEING_INITMEM;
1527 kprobe_free_init_mem();
1528 ftrace_free_init_mem();
1529 kgdb_free_init_mem();
1530 exit_boot_config();
1531 free_initmem();
1532 mark_readonly();
1533
1534 /*
1535 * Kernel mappings are now finalized - update the userspace page-table
1536 * to finalize PTI.
1537 */
1538 pti_finalize();
1539
1540 system_state = SYSTEM_RUNNING;
1541 numa_default_policy();
1542
1543 rcu_end_inkernel_boot();
1544
1545 do_sysctl_args();
1546
1547 if (ramdisk_execute_command) {
1548 ret = run_init_process(ramdisk_execute_command);
1549 if (!ret)
1550 return 0;
1551 pr_err("Failed to execute %s (error %d)\n",
1552 ramdisk_execute_command, ret);
1553 }
1554
1555 /*
1556 * We try each of these until one succeeds.
1557 *
1558 * The Bourne shell can be used instead of init if we are
1559 * trying to recover a really broken machine.
1560 */
1561 if (execute_command) {
1562 ret = run_init_process(execute_command);
1563 if (!ret)
1564 return 0;
1565 panic("Requested init %s failed (error %d).",
1566 execute_command, ret);
1567 }
1568
1569 if (CONFIG_DEFAULT_INIT[0] != '\0') {
1570 ret = run_init_process(CONFIG_DEFAULT_INIT);
1571 if (ret)
1572 pr_err("Default init %s failed (error %d)\n",
1573 CONFIG_DEFAULT_INIT, ret);
1574 else
1575 return 0;
1576 }
1577
1578 if (!try_to_run_init_process("/sbin/init") ||
1579 !try_to_run_init_process("/etc/init") ||
1580 !try_to_run_init_process("/bin/init") ||
1581 !try_to_run_init_process("/bin/sh"))
1582 return 0;
1583
1584 panic("No working init found. Try passing init= option to kernel. "
1585 "See Linux Documentation/admin-guide/init.rst for guidance.");
1586 }
1587
1588 /* Open /dev/console, for stdin/stdout/stderr, this should never fail */
console_on_rootfs(void)1589 void __init console_on_rootfs(void)
1590 {
1591 struct file *file = filp_open("/dev/console", O_RDWR, 0);
1592
1593 if (IS_ERR(file)) {
1594 pr_err("Warning: unable to open an initial console.\n");
1595 return;
1596 }
1597 init_dup(file);
1598 init_dup(file);
1599 init_dup(file);
1600 fput(file);
1601 }
1602
kernel_init_freeable(void)1603 static noinline void __init kernel_init_freeable(void)
1604 {
1605 /* Now the scheduler is fully set up and can do blocking allocations */
1606 gfp_allowed_mask = __GFP_BITS_MASK;
1607
1608 /*
1609 * init can allocate pages on any node
1610 */
1611 set_mems_allowed(node_states[N_MEMORY]);
1612
1613 cad_pid = get_pid(task_pid(current));
1614
1615 smp_prepare_cpus(setup_max_cpus);
1616
1617 workqueue_init();
1618
1619 init_mm_internals();
1620
1621 rcu_init_tasks_generic();
1622 do_pre_smp_initcalls();
1623 lockup_detector_init();
1624
1625 smp_init();
1626 sched_init_smp();
1627
1628 padata_init();
1629 page_alloc_init_late();
1630 /* Initialize page ext after all struct pages are initialized. */
1631 if (deferred_struct_pages)
1632 page_ext_init();
1633
1634 do_basic_setup();
1635
1636 kunit_run_all_tests();
1637
1638 wait_for_initramfs();
1639 console_on_rootfs();
1640
1641 /*
1642 * check if there is an early userspace init. If yes, let it do all
1643 * the work
1644 */
1645 if (init_eaccess(ramdisk_execute_command) != 0) {
1646 ramdisk_execute_command = NULL;
1647 prepare_namespace();
1648 }
1649
1650 /*
1651 * Ok, we have completed the initial bootup, and
1652 * we're essentially up and running. Get rid of the
1653 * initmem segments and start the user-mode stuff..
1654 *
1655 * rootfs is available now, try loading the public keys
1656 * and default modules
1657 */
1658
1659 integrity_load_keys();
1660 }
1661