main.c 17.0 KB
Newer Older
L
Linus Torvalds 已提交
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53
/*
 *  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> 
 */

#define __KERNEL_SYSCALLS__

#include <linux/config.h>
#include <linux/types.h>
#include <linux/module.h>
#include <linux/proc_fs.h>
#include <linux/devfs_fs_kernel.h>
#include <linux/kernel.h>
#include <linux/syscalls.h>
#include <linux/string.h>
#include <linux/ctype.h>
#include <linux/delay.h>
#include <linux/utsname.h>
#include <linux/ioport.h>
#include <linux/init.h>
#include <linux/smp_lock.h>
#include <linux/initrd.h>
#include <linux/hdreg.h>
#include <linux/bootmem.h>
#include <linux/tty.h>
#include <linux/gfp.h>
#include <linux/percpu.h>
#include <linux/kmod.h>
#include <linux/kernel_stat.h>
#include <linux/security.h>
#include <linux/workqueue.h>
#include <linux/profile.h>
#include <linux/rcupdate.h>
#include <linux/moduleparam.h>
#include <linux/kallsyms.h>
#include <linux/writeback.h>
#include <linux/cpu.h>
#include <linux/cpuset.h>
#include <linux/efi.h>
#include <linux/unistd.h>
#include <linux/rmap.h>
#include <linux/mempolicy.h>
#include <linux/key.h>

#include <asm/io.h>
#include <asm/bugs.h>
#include <asm/setup.h>
54
#include <asm/sections.h>
55
#include <asm/cacheflush.h>
L
Linus Torvalds 已提交
56 57 58 59 60 61

#ifdef CONFIG_X86_LOCAL_APIC
#include <asm/smp.h>
#endif

/*
62 63 64 65 66 67 68
 * This is one of the first .c files built. Error out early if we have compiler
 * trouble.
 *
 * Versions of gcc older than that listed below may actually compile and link
 * okay, but the end product can have subtle run time bugs.  To avoid associated
 * bogus bug reports, we flatly refuse to compile with a gcc that is known to be
 * too old from the very beginning.
L
Linus Torvalds 已提交
69
 */
A
Andrew Morton 已提交
70
#if (__GNUC__ < 3) || (__GNUC__ == 3 && __GNUC_MINOR__ < 2)
L
Linus Torvalds 已提交
71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95
#error Sorry, your GCC is too old. It builds incorrect kernels.
#endif

static int init(void *);

extern void init_IRQ(void);
extern void fork_init(unsigned long);
extern void mca_init(void);
extern void sbus_init(void);
extern void sysctl_init(void);
extern void signals_init(void);
extern void buffer_init(void);
extern void pidhash_init(void);
extern void pidmap_init(void);
extern void prio_tree_init(void);
extern void radix_tree_init(void);
extern void free_initmem(void);
extern void populate_rootfs(void);
extern void driver_init(void);
extern void prepare_namespace(void);
#ifdef	CONFIG_ACPI
extern void acpi_early_init(void);
#else
static inline void acpi_early_init(void) { }
#endif
96 97 98
#ifndef CONFIG_DEBUG_RODATA
static inline void mark_rodata_ro(void) { }
#endif
L
Linus Torvalds 已提交
99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121

#ifdef CONFIG_TC
extern void tc_init(void);
#endif

enum system_states system_state;
EXPORT_SYMBOL(system_state);

/*
 * Boot command-line arguments
 */
#define MAX_INIT_ARGS CONFIG_INIT_ENV_ARG_LIMIT
#define MAX_INIT_ENVS CONFIG_INIT_ENV_ARG_LIMIT

extern void time_init(void);
/* Default late time init is NULL. archs can override this later. */
void (*late_time_init)(void);
extern void softirq_init(void);

/* Untouched command line (eg. for /proc) saved by arch-specific code. */
char saved_command_line[COMMAND_LINE_SIZE];

static char *execute_command;
122
static char *ramdisk_execute_command;
L
Linus Torvalds 已提交
123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296

/* Setup configured maximum number of CPUs to activate */
static unsigned int max_cpus = NR_CPUS;

/*
 * Setup routine for controlling SMP activation
 *
 * Command-line option of "nosmp" or "maxcpus=0" will disable SMP
 * activation entirely (the MPS table probe still happens, though).
 *
 * Command-line option of "maxcpus=<NUM>", where <NUM> is an integer
 * greater than 0, limits the maximum number of CPUs activated in
 * SMP mode to <NUM>.
 */
static int __init nosmp(char *str)
{
	max_cpus = 0;
	return 1;
}

__setup("nosmp", nosmp);

static int __init maxcpus(char *str)
{
	get_option(&str, &max_cpus);
	return 1;
}

__setup("maxcpus=", maxcpus);

static char * argv_init[MAX_INIT_ARGS+2] = { "init", NULL, };
char * envp_init[MAX_INIT_ENVS+2] = { "HOME=/", "TERM=linux", NULL, };
static const char *panic_later, *panic_param;

extern struct obs_kernel_param __setup_start[], __setup_end[];

static int __init obsolete_checksetup(char *line)
{
	struct obs_kernel_param *p;

	p = __setup_start;
	do {
		int n = strlen(p->str);
		if (!strncmp(line, p->str, n)) {
			if (p->early) {
				/* Already done in parse_early_param?  (Needs
				 * exact match on param part) */
				if (line[n] == '\0' || line[n] == '=')
					return 1;
			} else if (!p->setup_func) {
				printk(KERN_WARNING "Parameter %s is obsolete,"
				       " ignored\n", p->str);
				return 1;
			} else if (p->setup_func(line + n))
				return 1;
		}
		p++;
	} while (p < __setup_end);
	return 0;
}

/*
 * 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
 */
unsigned long loops_per_jiffy = (1<<12);

EXPORT_SYMBOL(loops_per_jiffy);

static int __init debug_kernel(char *str)
{
	if (*str)
		return 0;
	console_loglevel = 10;
	return 1;
}

static int __init quiet_kernel(char *str)
{
	if (*str)
		return 0;
	console_loglevel = 4;
	return 1;
}

__setup("debug", debug_kernel);
__setup("quiet", quiet_kernel);

static int __init loglevel(char *str)
{
	get_option(&str, &console_loglevel);
	return 1;
}

__setup("loglevel=", loglevel);

/*
 * Unknown boot options get handed to init, unless they look like
 * failed parameters
 */
static int __init unknown_bootoption(char *param, char *val)
{
	/* Change NUL term back to "=", to make "param" the whole string. */
	if (val) {
		/* param=val or param="val"? */
		if (val == param+strlen(param)+1)
			val[-1] = '=';
		else if (val == param+strlen(param)+2) {
			val[-2] = '=';
			memmove(val-1, val, strlen(val)+1);
			val--;
		} else
			BUG();
	}

	/* Handle obsolete-style parameters */
	if (obsolete_checksetup(param))
		return 0;

	/*
	 * Preemptive maintenance for "why didn't my mispelled command
	 * line work?"
	 */
	if (strchr(param, '.') && (!val || strchr(param, '.') < val)) {
		printk(KERN_ERR "Unknown boot option `%s': ignoring\n", param);
		return 0;
	}

	if (panic_later)
		return 0;

	if (val) {
		/* Environment option */
		unsigned int i;
		for (i = 0; envp_init[i]; i++) {
			if (i == MAX_INIT_ENVS) {
				panic_later = "Too many boot env vars at `%s'";
				panic_param = param;
			}
			if (!strncmp(param, envp_init[i], val - param))
				break;
		}
		envp_init[i] = param;
	} else {
		/* Command line option */
		unsigned int i;
		for (i = 0; argv_init[i]; i++) {
			if (i == MAX_INIT_ARGS) {
				panic_later = "Too many boot init vars at `%s'";
				panic_param = param;
			}
		}
		argv_init[i] = param;
	}
	return 0;
}

static int __init init_setup(char *str)
{
	unsigned int i;

	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);

297 298 299 300 301 302 303 304 305 306 307 308
static int __init rdinit_setup(char *str)
{
	unsigned int i;

	ramdisk_execute_command = str;
	/* See "auto" comment in init_setup */
	for (i = 1; i < MAX_INIT_ARGS; i++)
		argv_init[i] = NULL;
	return 1;
}
__setup("rdinit=", rdinit_setup);

L
Linus Torvalds 已提交
309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325
#ifndef CONFIG_SMP

#ifdef CONFIG_X86_LOCAL_APIC
static void __init smp_init(void)
{
	APIC_init_uniprocessor();
}
#else
#define smp_init()	do { } while (0)
#endif

static inline void setup_per_cpu_areas(void) { }
static inline void smp_prepare_cpus(unsigned int maxcpus) { }

#else

#ifdef __GENERIC_PER_CPU
E
Eric Dumazet 已提交
326
unsigned long __per_cpu_offset[NR_CPUS] __read_mostly;
L
Linus Torvalds 已提交
327 328 329 330 331 332 333

EXPORT_SYMBOL(__per_cpu_offset);

static void __init setup_per_cpu_areas(void)
{
	unsigned long size, i;
	char *ptr;
334
	unsigned long nr_possible_cpus = num_possible_cpus();
L
Linus Torvalds 已提交
335 336 337 338 339 340 341

	/* Copy section for each CPU (we discard the original) */
	size = ALIGN(__per_cpu_end - __per_cpu_start, SMP_CACHE_BYTES);
#ifdef CONFIG_MODULES
	if (size < PERCPU_ENOUGH_ROOM)
		size = PERCPU_ENOUGH_ROOM;
#endif
342
	ptr = alloc_bootmem(size * nr_possible_cpus);
L
Linus Torvalds 已提交
343

344
	for_each_possible_cpu(i) {
L
Linus Torvalds 已提交
345 346
		__per_cpu_offset[i] = ptr - __per_cpu_start;
		memcpy(ptr, __per_cpu_start, __per_cpu_end - __per_cpu_start);
347
		ptr += size;
L
Linus Torvalds 已提交
348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391
	}
}
#endif /* !__GENERIC_PER_CPU */

/* Called by boot processor to activate the rest. */
static void __init smp_init(void)
{
	unsigned int i;

	/* FIXME: This should be done in userspace --RR */
	for_each_present_cpu(i) {
		if (num_online_cpus() >= max_cpus)
			break;
		if (!cpu_online(i))
			cpu_up(i);
	}

	/* Any cleanup work */
	printk(KERN_INFO "Brought up %ld CPUs\n", (long)num_online_cpus());
	smp_cpus_done(max_cpus);
#if 0
	/* Get other processors into their bootup holding patterns. */

	smp_commence();
#endif
}

#endif

/*
 * 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.
 */

static void noinline rest_init(void)
	__releases(kernel_lock)
{
	kernel_thread(init, NULL, CLONE_FS | CLONE_SIGHAND);
	numa_default_policy();
	unlock_kernel();
392 393 394 395 396

	/*
	 * The boot idle thread must execute schedule()
	 * at least one to get things moving:
	 */
397
	preempt_enable_no_resched();
398
	schedule();
399
	preempt_disable();
400

401
	/* Call into cpu_idle with preempt disabled */
L
Linus Torvalds 已提交
402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439
	cpu_idle();
} 

/* Check for early params. */
static int __init do_early_param(char *param, char *val)
{
	struct obs_kernel_param *p;

	for (p = __setup_start; p < __setup_end; p++) {
		if (p->early && strcmp(param, p->str) == 0) {
			if (p->setup_func(val) != 0)
				printk(KERN_WARNING
				       "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)
{
	static __initdata int done = 0;
	static __initdata char tmp_cmdline[COMMAND_LINE_SIZE];

	if (done)
		return;

	/* All fall through to do_early_param. */
	strlcpy(tmp_cmdline, saved_command_line, COMMAND_LINE_SIZE);
	parse_args("early options", tmp_cmdline, NULL, 0, do_early_param);
	done = 1;
}

/*
 *	Activate the first processor.
 */

440 441 442 443 444 445 446 447 448
static void __init boot_cpu_init(void)
{
	int cpu = smp_processor_id();
	/* Mark the boot cpu "present", "online" etc for SMP and UP case */
	cpu_set(cpu, cpu_online_map);
	cpu_set(cpu, cpu_present_map);
	cpu_set(cpu, cpu_possible_map);
}

L
Linus Torvalds 已提交
449 450 451 452 453 454 455 456 457
asmlinkage void __init start_kernel(void)
{
	char * command_line;
	extern struct kernel_param __start___param[], __stop___param[];
/*
 * Interrupts are still disabled. Do necessary setups, then
 * enable them
 */
	lock_kernel();
458
	boot_cpu_init();
L
Linus Torvalds 已提交
459 460 461 462 463
	page_address_init();
	printk(KERN_NOTICE);
	printk(linux_banner);
	setup_arch(&command_line);
	setup_per_cpu_areas();
464
	smp_prepare_boot_cpu();	/* arch-specific boot-cpu hooks */
L
Linus Torvalds 已提交
465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489

	/*
	 * 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();
	/*
	 * Disable preemption - early bootup scheduling is extremely
	 * fragile until we cpu_idle() for the first time.
	 */
	preempt_disable();
	build_all_zonelists();
	page_alloc_init();
	printk(KERN_NOTICE "Kernel command line: %s\n", saved_command_line);
	parse_early_param();
	parse_args("Booting kernel", command_line, __start___param,
		   __stop___param - __start___param,
		   &unknown_bootoption);
	sort_main_extable();
	trap_init();
	rcu_init();
	init_IRQ();
	pidhash_init();
	init_timers();
490
	hrtimers_init();
L
Linus Torvalds 已提交
491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512
	softirq_init();
	time_init();

	/*
	 * 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(panic_later, panic_param);
	profile_init();
	local_irq_enable();
#ifdef CONFIG_BLK_DEV_INITRD
	if (initrd_start && !initrd_below_start_ok &&
			initrd_start < min_low_pfn << PAGE_SHIFT) {
		printk(KERN_CRIT "initrd overwritten (0x%08lx < 0x%08lx) - "
		    "disabling it.\n",initrd_start,min_low_pfn << PAGE_SHIFT);
		initrd_start = 0;
	}
#endif
	vfs_caches_init_early();
513
	cpuset_init_early();
L
Linus Torvalds 已提交
514 515
	mem_init();
	kmem_cache_init();
516
	setup_per_cpu_pageset();
L
Linus Torvalds 已提交
517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571
	numa_policy_init();
	if (late_time_init)
		late_time_init();
	calibrate_delay();
	pidmap_init();
	pgtable_cache_init();
	prio_tree_init();
	anon_vma_init();
#ifdef CONFIG_X86
	if (efi_enabled)
		efi_enter_virtual_mode();
#endif
	fork_init(num_physpages);
	proc_caches_init();
	buffer_init();
	unnamed_dev_init();
	key_init();
	security_init();
	vfs_caches_init(num_physpages);
	radix_tree_init();
	signals_init();
	/* rootfs populating might need page-writeback */
	page_writeback_init();
#ifdef CONFIG_PROC_FS
	proc_root_init();
#endif
	cpuset_init();

	check_bugs();

	acpi_early_init(); /* before LAPIC and SMP init */

	/* Do the rest non-__init'ed, we're now alive */
	rest_init();
}

static int __initdata initcall_debug;

static int __init initcall_debug_setup(char *str)
{
	initcall_debug = 1;
	return 1;
}
__setup("initcall_debug", initcall_debug_setup);

struct task_struct *child_reaper = &init_task;

extern initcall_t __initcall_start[], __initcall_end[];

static void __init do_initcalls(void)
{
	initcall_t *call;
	int count = preempt_count();

	for (call = __initcall_start; call < __initcall_end; call++) {
572 573 574
		char *msg = NULL;
		char msgbuf[40];
		int result;
L
Linus Torvalds 已提交
575 576

		if (initcall_debug) {
577 578 579
			printk("Calling initcall 0x%p", *call);
			print_fn_descriptor_symbol(": %s()",
					(unsigned long) *call);
L
Linus Torvalds 已提交
580 581 582
			printk("\n");
		}

583
		result = (*call)();
L
Linus Torvalds 已提交
584

585
		if (result && result != -ENODEV && initcall_debug) {
586 587 588
			sprintf(msgbuf, "error code %d", result);
			msg = msgbuf;
		}
L
Linus Torvalds 已提交
589 590 591 592 593 594 595 596 597
		if (preempt_count() != count) {
			msg = "preemption imbalance";
			preempt_count() = count;
		}
		if (irqs_disabled()) {
			msg = "disabled interrupts";
			local_irq_enable();
		}
		if (msg) {
598 599 600 601
			printk(KERN_WARNING "initcall at 0x%p", *call);
			print_fn_descriptor_symbol(": %s()",
					(unsigned long) *call);
			printk(": returned with %s\n", msg);
L
Linus Torvalds 已提交
602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638
		}
	}

	/* Make sure there is no pending stuff from the initcall sequence */
	flush_scheduled_work();
}

/*
 * 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..
 */
static void __init do_basic_setup(void)
{
	/* drivers will send hotplug events */
	init_workqueues();
	usermodehelper_init();
	driver_init();

#ifdef CONFIG_SYSCTL
	sysctl_init();
#endif

	do_initcalls();
}

static void do_pre_smp_initcalls(void)
{
	extern int spawn_ksoftirqd(void);
#ifdef CONFIG_SMP
	extern int migration_init(void);

	migration_init();
#endif
	spawn_ksoftirqd();
I
Ingo Molnar 已提交
639
	spawn_softlockup_task();
L
Linus Torvalds 已提交
640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685
}

static void run_init_process(char *init_filename)
{
	argv_init[0] = init_filename;
	execve(init_filename, argv_init, envp_init);
}

static int init(void * unused)
{
	lock_kernel();
	/*
	 * init can run on any cpu.
	 */
	set_cpus_allowed(current, CPU_MASK_ALL);
	/*
	 * Tell the world that we're going to be the grim
	 * reaper of innocent orphaned children.
	 *
	 * We don't want people to have to make incorrect
	 * assumptions about where in the task array this
	 * can be found.
	 */
	child_reaper = current;

	smp_prepare_cpus(max_cpus);

	do_pre_smp_initcalls();

	smp_init();
	sched_init_smp();

	cpuset_init_smp();

	/*
	 * Do this before initcalls, because some drivers want to access
	 * firmware files.
	 */
	populate_rootfs();

	do_basic_setup();

	/*
	 * check if there is an early userspace init.  If yes, let it do all
	 * the work
	 */
686 687 688 689 690 691

	if (!ramdisk_execute_command)
		ramdisk_execute_command = "/init";

	if (sys_access((const char __user *) ramdisk_execute_command, 0) != 0) {
		ramdisk_execute_command = NULL;
L
Linus Torvalds 已提交
692
		prepare_namespace();
693
	}
L
Linus Torvalds 已提交
694 695 696 697 698 699 700 701

	/*
	 * 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..
	 */
	free_initmem();
	unlock_kernel();
702
	mark_rodata_ro();
L
Linus Torvalds 已提交
703 704 705 706 707 708 709 710
	system_state = SYSTEM_RUNNING;
	numa_default_policy();

	if (sys_open((const char __user *) "/dev/console", O_RDWR, 0) < 0)
		printk(KERN_WARNING "Warning: unable to open an initial console.\n");

	(void) sys_dup(0);
	(void) sys_dup(0);
711 712 713 714 715 716 717

	if (ramdisk_execute_command) {
		run_init_process(ramdisk_execute_command);
		printk(KERN_WARNING "Failed to execute %s\n",
				ramdisk_execute_command);
	}

L
Linus Torvalds 已提交
718 719 720 721 722 723
	/*
	 * 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.
	 */
724
	if (execute_command) {
L
Linus Torvalds 已提交
725
		run_init_process(execute_command);
726 727 728
		printk(KERN_WARNING "Failed to execute %s.  Attempting "
					"defaults...\n", execute_command);
	}
L
Linus Torvalds 已提交
729 730 731 732 733 734 735
	run_init_process("/sbin/init");
	run_init_process("/etc/init");
	run_init_process("/bin/init");
	run_init_process("/bin/sh");

	panic("No init found.  Try passing init= option to kernel.");
}