init/main.c

   1 /*
   2  *  linux/init/main.c
   3  *
   4  *  Copyright (C) 1991, 1992  Linus Torvalds
   5  *
   6  *  GK 2/5/95  -  Changed to support mounting root fs via NFS
   7  *  Added initrd & change_root: Werner Almesberger & Hans Lermen, Feb '96
   8  *  Moan early if gcc is old, avoiding bogus kernels - Paul Gortmaker, May '96
   9  *  Simplified starting of init:  Michael A. Griffith <grif@acm.org>
  10  */
  11
  12 #include <linux/types.h>
  13 #include <linux/module.h>
  14 #include <linux/proc_fs.h>
  15 #include <linux/kernel.h>
  16 #include <linux/syscalls.h>
  17 #include <linux/string.h>
  18 #include <linux/ctype.h>
  19 #include <linux/delay.h>
  20 #include <linux/utsname.h>
  21 #include <linux/ioport.h>
  22 #include <linux/init.h>
  23 #include <linux/smp_lock.h>
  24 #include <linux/initrd.h>
  25 #include <linux/hdreg.h>
  26 #include <linux/bootmem.h>
  27 #include <linux/tty.h>
  28 #include <linux/gfp.h>
  29 #include <linux/percpu.h>
  30 #include <linux/kmod.h>
  31 #include <linux/kernel_stat.h>
  32 #include <linux/start_kernel.h>
  33 #include <linux/security.h>
  34 #include <linux/workqueue.h>
  35 #include <linux/profile.h>
  36 #include <linux/rcupdate.h>
  37 #include <linux/moduleparam.h>
  38 #include <linux/kallsyms.h>
  39 #include <linux/writeback.h>
  40 #include <linux/cpu.h>
  41 #include <linux/cpuset.h>
  42 #include <linux/cgroup.h>
  43 #include <linux/efi.h>
  44 #include <linux/tick.h>
  45 #include <linux/interrupt.h>
  46 #include <linux/taskstats_kern.h>
  47 #include <linux/delayacct.h>
  48 #include <linux/unistd.h>
  49 #include <linux/rmap.h>
  50 #include <linux/mempolicy.h>
  51 #include <linux/key.h>
  52 #include <linux/unwind.h>
  53 #include <linux/buffer_head.h>
  54 #include <linux/debug_locks.h>
  55 #include <linux/lockdep.h>
  56 #include <linux/pid_namespace.h>
  57 #include <linux/device.h>
  58 #include <linux/kthread.h>
  59 #include <linux/sched.h>
  60
  61 #include <asm/io.h>
  62 #include <asm/bugs.h>
  63 #include <asm/setup.h>
  64 #include <asm/sections.h>
  65 #include <asm/cacheflush.h>
  66
  67 #ifdef CONFIG_X86_LOCAL_APIC
  68 #include <asm/smp.h>
  69 #endif
  70
  71 /*
  72  * This is one of the first .c files built. Error out early if we have compiler
  73  * trouble.
  74  */
  75
  76 #if __GNUC__ == 4 && __GNUC_MINOR__ == 1 && __GNUC_PATCHLEVEL__ == 0
  77 #warning gcc-4.1.0 is known to miscompile the kernel.  A different compiler version is recommended.
  78 #endif
  79
  80 static int kernel_init(void *);
  81
  82 extern void init_IRQ(void);
  83 extern void fork_init(unsigned long);
  84 extern void mca_init(void);
  85 extern void sbus_init(void);
  86 extern void signals_init(void);
  87 extern void pidhash_init(void);
  88 extern void pidmap_init(void);
  89 extern void prio_tree_init(void);
  90 extern void radix_tree_init(void);
  91 extern void free_initmem(void);
  92 #ifdef  CONFIG_ACPI
  93 extern void acpi_early_init(void);
  94 #else
  95 static inline void acpi_early_init(void) { }
  96 #endif
  97 #ifndef CONFIG_DEBUG_RODATA
  98 static inline void mark_rodata_ro(void) { }
  99 #endif
 100
 101 #ifdef CONFIG_TC
 102 extern void tc_init(void);
 103 #endif
 104
 105 enum system_states system_state;
 106 EXPORT_SYMBOL(system_state);
 107
 108 /*
 109  * Boot command-line arguments
 110  */
 111 #define MAX_INIT_ARGS CONFIG_INIT_ENV_ARG_LIMIT
 112 #define MAX_INIT_ENVS CONFIG_INIT_ENV_ARG_LIMIT
 113
 114 extern void time_init(void);
 115 /* Default late time init is NULL. archs can override this later. */
 116 void (*late_time_init)(void);
 117 extern void softirq_init(void);
 118
 119 /* Untouched command line saved by arch-specific code. */
 120 char __initdata boot_command_line[COMMAND_LINE_SIZE];
 121 /* Untouched saved command line (eg. for /proc) */
 122 char *saved_command_line;
 123 /* Command line for parameter parsing */
 124 static char *static_command_line;
 125
 126 static char *execute_command;
 127 static char *ramdisk_execute_command;
 128
 129 #ifdef CONFIG_SMP
 130 /* Setup configured maximum number of CPUs to activate */
 131 static unsigned int __initdata max_cpus = NR_CPUS;
 132
 133 /*
 134  * Setup routine for controlling SMP activation
 135  *
 136  * Command-line option of "nosmp" or "maxcpus=0" will disable SMP
 137  * activation entirely (the MPS table probe still happens, though).
 138  *
 139  * Command-line option of "maxcpus=<NUM>", where <NUM> is an integer
 140  * greater than 0, limits the maximum number of CPUs activated in
 141  * SMP mode to <NUM>.
 142  */
 143 #ifndef CONFIG_X86_IO_APIC
 144 static inline void disable_ioapic_setup(void) {};
 145 #endif
 146
 147 static int __init nosmp(char *str)
 148 {
 149         max_cpus = 0;
 150         disable_ioapic_setup();
 151         return 0;
 152 }
 153
 154 early_param("nosmp", nosmp);
 155
 156 static int __init maxcpus(char *str)
 157 {
 158         get_option(&str, &max_cpus);
 159         if (max_cpus == 0)
 160                 disable_ioapic_setup();
 161
 162         return 0;
 163 }
 164
 165 early_param("maxcpus", maxcpus);
 166 #else
 167 #define max_cpus NR_CPUS
 168 #endif
 169
 170 /*
 171  * If set, this is an indication to the drivers that reset the underlying
 172  * device before going ahead with the initialization otherwise driver might
 173  * rely on the BIOS and skip the reset operation.
 174  *
 175  * This is useful if kernel is booting in an unreliable environment.
 176  * For ex. kdump situaiton where previous kernel has crashed, BIOS has been
 177  * skipped and devices will be in unknown state.
 178  */
 179 unsigned int reset_devices;
 180 EXPORT_SYMBOL(reset_devices);
 181
 182 static int __init set_reset_devices(char *str)
 183 {
 184         reset_devices = 1;
 185         return 1;
 186 }
 187
 188 __setup("reset_devices", set_reset_devices);
 189
 190 static char * argv_init[MAX_INIT_ARGS+2] = { "init", NULL, };
 191 char * envp_init[MAX_INIT_ENVS+2] = { "HOME=/", "TERM=linux", NULL, };
 192 static const char *panic_later, *panic_param;
 193
 194 extern struct obs_kernel_param __setup_start[], __setup_end[];
 195
 196 static int __init obsolete_checksetup(char *line)
 197 {
 198         struct obs_kernel_param *p;
 199         int had_early_param = 0;
 200
 201         p = __setup_start;
 202         do {
 203                 int n = strlen(p->str);
 204                 if (!strncmp(line, p->str, n)) {
 205                         if (p->early) {
 206                                 /* Already done in parse_early_param?
 207                                  * (Needs exact match on param part).
 208                                  * Keep iterating, as we can have early
 209                                  * params and __setups of same names 8( */
 210                                 if (line[n] == '\0' || line[n] == '=')
 211                                         had_early_param = 1;
 212                         } else if (!p->setup_func) {
 213                                 printk(KERN_WARNING "Parameter %s is obsolete,"
 214                                        " ignored\n", p->str);
 215                                 return 1;
 216                         } else if (p->setup_func(line + n))
 217                                 return 1;
 218                 }
 219                 p++;
 220         } while (p < __setup_end);
 221
 222         return had_early_param;
 223 }
 224
 225 /*
 226  * This should be approx 2 Bo*oMips to start (note initial shift), and will
 227  * still work even if initially too large, it will just take slightly longer
 228  */
 229 unsigned long loops_per_jiffy = (1<<12);
 230
 231 EXPORT_SYMBOL(loops_per_jiffy);
 232
 233 static int __init debug_kernel(char *str)
 234 {
 235         if (*str)
 236                 return 0;
 237         console_loglevel = 10;
 238         return 1;
 239 }
 240
 241 static int __init quiet_kernel(char *str)
 242 {
 243         if (*str)
 244                 return 0;
 245         console_loglevel = 4;
 246         return 1;
 247 }
 248
 249 __setup("debug", debug_kernel);
 250 __setup("quiet", quiet_kernel);
 251
 252 static int __init loglevel(char *str)
 253 {
 254         get_option(&str, &console_loglevel);
 255         return 1;
 256 }
 257
 258 __setup("loglevel=", loglevel);
 259
 260 /*
 261  * Unknown boot options get handed to init, unless they look like
 262  * failed parameters
 263  */
 264 static int __init unknown_bootoption(char *param, char *val)
 265 {
 266         /* Change NUL term back to "=", to make "param" the whole string. */
 267         if (val) {
 268                 /* param=val or param="val"? */
 269                 if (val == param+strlen(param)+1)
 270                         val[-1] = '=';
 271                 else if (val == param+strlen(param)+2) {
 272                         val[-2] = '=';
 273                         memmove(val-1, val, strlen(val)+1);
 274                         val--;
 275                 } else
 276                         BUG();
 277         }
 278
 279         /* Handle obsolete-style parameters */
 280         if (obsolete_checksetup(param))
 281                 return 0;
 282
 283         /*
 284          * Preemptive maintenance for "why didn't my misspelled command
 285          * line work?"
 286          */
 287         if (strchr(param, '.') && (!val || strchr(param, '.') < val)) {
 288                 printk(KERN_ERR "Unknown boot option `%s': ignoring\n", param);
 289                 return 0;
 290         }
 291
 292         if (panic_later)
 293                 return 0;
 294
 295         if (val) {
 296                 /* Environment option */
 297                 unsigned int i;
 298                 for (i = 0; envp_init[i]; i++) {
 299                         if (i == MAX_INIT_ENVS) {
 300                                 panic_later = "Too many boot env vars at `%s'";
 301                                 panic_param = param;
 302                         }
 303                         if (!strncmp(param, envp_init[i], val - param))
 304                                 break;
 305                 }
 306                 envp_init[i] = param;
 307         } else {
 308                 /* Command line option */
 309                 unsigned int i;
 310                 for (i = 0; argv_init[i]; i++) {
 311                         if (i == MAX_INIT_ARGS) {
 312                                 panic_later = "Too many boot init vars at `%s'";
 313                                 panic_param = param;
 314                         }
 315                 }
 316                 argv_init[i] = param;
 317         }
 318         return 0;
 319 }
 320
 321 static int __init init_setup(char *str)
 322 {
 323         unsigned int i;
 324
 325         execute_command = str;
 326         /*
 327          * In case LILO is going to boot us with default command line,
 328          * it prepends "auto" before the whole cmdline which makes
 329          * the shell think it should execute a script with such name.
 330          * So we ignore all arguments entered _before_ init=... [MJ]
 331          */
 332         for (i = 1; i < MAX_INIT_ARGS; i++)
 333                 argv_init[i] = NULL;
 334         return 1;
 335 }
 336 __setup("init=", init_setup);
 337
 338 static int __init rdinit_setup(char *str)
 339 {
 340         unsigned int i;
 341
 342         ramdisk_execute_command = str;
 343         /* See "auto" comment in init_setup */
 344         for (i = 1; i < MAX_INIT_ARGS; i++)
 345                 argv_init[i] = NULL;
 346         return 1;
 347 }
 348 __setup("rdinit=", rdinit_setup);
 349
 350 #ifndef CONFIG_SMP
 351
 352 #ifdef CONFIG_X86_LOCAL_APIC
 353 static void __init smp_init(void)
 354 {
 355         APIC_init_uniprocessor();
 356 }
 357 #else
 358 #define smp_init()      do { } while (0)
 359 #endif
 360
 361 static inline void setup_per_cpu_areas(void) { }
 362 static inline void smp_prepare_cpus(unsigned int maxcpus) { }
 363
 364 #else
 365
 366 #ifndef CONFIG_ARCH_SETS_UP_PER_CPU_AREA
 367 unsigned long __per_cpu_offset[NR_CPUS] __read_mostly;
 368
 369 EXPORT_SYMBOL(__per_cpu_offset);
 370
 371 static void __init setup_per_cpu_areas(void)
 372 {
 373         unsigned long size, i;
 374         char *ptr;
 375         unsigned long nr_possible_cpus = num_possible_cpus();
 376
 377         /* Copy section for each CPU (we discard the original) */
 378         size = ALIGN(PERCPU_ENOUGH_ROOM, PAGE_SIZE);
 379         ptr = alloc_bootmem_pages(size * nr_possible_cpus);
 380
 381         for_each_possible_cpu(i) {
 382                 __per_cpu_offset[i] = ptr - __per_cpu_start;
 383                 memcpy(ptr, __per_cpu_start, __per_cpu_end - __per_cpu_start);
 384                 ptr += size;
 385         }
 386 }
 387 #endif /* CONFIG_ARCH_SETS_UP_CPU_AREA */
 388
 389 /* Called by boot processor to activate the rest. */
 390 static void __init smp_init(void)
 391 {
 392         unsigned int cpu;
 393
 394         /* FIXME: This should be done in userspace --RR */
 395         for_each_present_cpu(cpu) {
 396                 if (num_online_cpus() >= max_cpus)
 397                         break;
 398                 if (!cpu_online(cpu))
 399                         cpu_up(cpu);
 400         }
 401
 402         /* Any cleanup work */
 403         printk(KERN_INFO "Brought up %ld CPUs\n", (long)num_online_cpus());
 404         smp_cpus_done(max_cpus);
 405 }
 406
 407 #endif
 408
 409 /*
 410  * We need to store the untouched command line for future reference.
 411  * We also need to store the touched command line since the parameter
 412  * parsing is performed in place, and we should allow a component to
 413  * store reference of name/value for future reference.
 414  */
 415 static void __init setup_command_line(char *command_line)
 416 {
 417         saved_command_line = alloc_bootmem(strlen (boot_command_line)+1);
 418         static_command_line = alloc_bootmem(strlen (command_line)+1);
 419         strcpy (saved_command_line, boot_command_line);
 420         strcpy (static_command_line, command_line);
 421 }
 422
 423 /*
 424  * We need to finalize in a non-__init function or else race conditions
 425  * between the root thread and the init thread may cause start_kernel to
 426  * be reaped by free_initmem before the root thread has proceeded to
 427  * cpu_idle.
 428  *
 429  * gcc-3.4 accidentally inlines this function, so use noinline.
 430  */
 431
 432 static void noinline __init_refok rest_init(void)
 433         __releases(kernel_lock)
 434 {
 435         int pid;
 436
 437         kernel_thread(kernel_init, NULL, CLONE_FS | CLONE_SIGHAND);
 438         numa_default_policy();
 439         pid = kernel_thread(kthreadd, NULL, CLONE_FS | CLONE_FILES);
 440         kthreadd_task = find_task_by_pid(pid);
 441         unlock_kernel();
 442
 443         /*
 444          * The boot idle thread must execute schedule()
 445          * at least once to get things moving:
 446          */
 447         init_idle_bootup_task(current);
 448         preempt_enable_no_resched();
 449         schedule();
 450         preempt_disable();
 451
 452         /* Call into cpu_idle with preempt disabled */
 453         cpu_idle();
 454 }
 455
 456 /* Check for early params. */
 457 static int __init do_early_param(char *param, char *val)
 458 {
 459         struct obs_kernel_param *p;
 460
 461         for (p = __setup_start; p < __setup_end; p++) {
 462                 if ((p->early && strcmp(param, p->str) == 0) ||
 463                     (strcmp(param, "console") == 0 &&
 464                      strcmp(p->str, "earlycon") == 0)
 465                 ) {
 466                         if (p->setup_func(val) != 0)
 467                                 printk(KERN_WARNING
 468                                        "Malformed early option '%s'\n", param);
 469                 }
 470         }
 471         /* We accept everything at this stage. */
 472         return 0;
 473 }
 474
 475 /* Arch code calls this early on, or if not, just before other parsing. */
 476 void __init parse_early_param(void)
 477 {
 478         static __initdata int done = 0;
 479         static __initdata char tmp_cmdline[COMMAND_LINE_SIZE];
 480
 481         if (done)
 482                 return;
 483
 484         /* All fall through to do_early_param. */
 485         strlcpy(tmp_cmdline, boot_command_line, COMMAND_LINE_SIZE);
 486         parse_args("early options", tmp_cmdline, NULL, 0, do_early_param);
 487         done = 1;
 488 }
 489
 490 /*
 491  *      Activate the first processor.
 492  */
 493
 494 static void __init boot_cpu_init(void)
 495 {
 496         int cpu = smp_processor_id();
 497         /* Mark the boot cpu "present", "online" etc for SMP and UP case */
 498         cpu_set(cpu, cpu_online_map);
 499         cpu_set(cpu, cpu_present_map);
 500         cpu_set(cpu, cpu_possible_map);
 501 }
 502
 503 void __init __attribute__((weak)) smp_setup_processor_id(void)
 504 {
 505 }
 506
 507 asmlinkage void __init start_kernel(void)
 508 {
 509         char * command_line;
 510         extern struct kernel_param __start___param[], __stop___param[];
 511
 512         smp_setup_processor_id();
 513
 514         /*
 515          * Need to run as early as possible, to initialize the
 516          * lockdep hash:
 517          */
 518         unwind_init();
 519         lockdep_init();
 520         cgroup_init_early();
 521
 522         local_irq_disable();
 523         early_boot_irqs_off();
 524         early_init_irq_lock_class();
 525
 526 /*
 527  * Interrupts are still disabled. Do necessary setups, then
 528  * enable them
 529  */
 530         lock_kernel();
 531         tick_init();
 532         boot_cpu_init();
 533         page_address_init();
 534         printk(KERN_NOTICE);
 535         printk(linux_banner);
 536         setup_arch(&command_line);
 537         setup_command_line(command_line);
 538         unwind_setup();
 539         setup_per_cpu_areas();
 540         smp_prepare_boot_cpu(); /* arch-specific boot-cpu hooks */
 541
 542         /*
 543          * Set up the scheduler prior starting any interrupts (such as the
 544          * timer interrupt). Full topology setup happens at smp_init()
 545          * time - but meanwhile we still have a functioning scheduler.
 546          */
 547         sched_init();
 548         /*
 549          * Disable preemption - early bootup scheduling is extremely
 550          * fragile until we cpu_idle() for the first time.
 551          */
 552         preempt_disable();
 553         build_all_zonelists();
 554         page_alloc_init();
 555         printk(KERN_NOTICE "Kernel command line: %s\n", boot_command_line);
 556         parse_early_param();
 557         parse_args("Booting kernel", static_command_line, __start___param,
 558                    __stop___param - __start___param,
 559                    &unknown_bootoption);
 560         if (!irqs_disabled()) {
 561                 printk(KERN_WARNING "start_kernel(): bug: interrupts were "
 562                                 "enabled *very* early, fixing it\n");
 563                 local_irq_disable();
 564         }
 565         sort_main_extable();
 566         trap_init();
 567         rcu_init();
 568         init_IRQ();
 569         pidhash_init();
 570         init_timers();
 571         hrtimers_init();
 572         softirq_init();
 573         timekeeping_init();
 574         time_init();
 575         profile_init();
 576         if (!irqs_disabled())
 577                 printk("start_kernel(): bug: interrupts were enabled early\n");
 578         early_boot_irqs_on();
 579         local_irq_enable();
 580
 581         /*
 582          * HACK ALERT! This is early. We're enabling the console before
 583          * we've done PCI setups etc, and console_init() must be aware of
 584          * this. But we do want output early, in case something goes wrong.
 585          */
 586         console_init();
 587         if (panic_later)
 588                 panic(panic_later, panic_param);
 589
 590         lockdep_info();
 591
 592         /*
 593          * Need to run this when irqs are enabled, because it wants
 594          * to self-test [hard/soft]-irqs on/off lock inversion bugs
 595          * too:
 596          */
 597         locking_selftest();
 598
 599 #ifdef CONFIG_BLK_DEV_INITRD
 600         if (initrd_start && !initrd_below_start_ok &&
 601                         initrd_start < min_low_pfn << PAGE_SHIFT) {
 602                 printk(KERN_CRIT "initrd overwritten (0x%08lx < 0x%08lx) - "
 603                     "disabling it.\n",initrd_start,min_low_pfn << PAGE_SHIFT);
 604                 initrd_start = 0;
 605         }
 606 #endif
 607         vfs_caches_init_early();
 608         cpuset_init_early();
 609         mem_init();
 610         cpu_hotplug_init();
 611         kmem_cache_init();
 612         setup_per_cpu_pageset();
 613         numa_policy_init();
 614         if (late_time_init)
 615                 late_time_init();
 616         calibrate_delay();
 617         pidmap_init();
 618         pgtable_cache_init();
 619         prio_tree_init();
 620         anon_vma_init();
 621 #ifdef CONFIG_X86
 622         if (efi_enabled)
 623                 efi_enter_virtual_mode();
 624 #endif
 625         fork_init(num_physpages);
 626         proc_caches_init();
 627         buffer_init();
 628         unnamed_dev_init();
 629         key_init();
 630         security_init();
 631         vfs_caches_init(num_physpages);
 632         radix_tree_init();
 633         signals_init();
 634         /* rootfs populating might need page-writeback */
 635         page_writeback_init();
 636 #ifdef CONFIG_PROC_FS
 637         proc_root_init();
 638 #endif
 639         cgroup_init();
 640         cpuset_init();
 641         taskstats_init_early();
 642         delayacct_init();
 643
 644         check_bugs();
 645
 646         acpi_early_init(); /* before LAPIC and SMP init */
 647
 648         /* Do the rest non-__init'ed, we're now alive */
 649         rest_init();
 650 }
 651
 652 static int __initdata initcall_debug;
 653
 654 static int __init initcall_debug_setup(char *str)
 655 {
 656         initcall_debug = 1;
 657         return 1;
 658 }
 659 __setup("initcall_debug", initcall_debug_setup);
 660
 661 extern initcall_t __initcall_start[], __initcall_end[];
 662
 663 static void __init do_initcalls(void)
 664 {
 665         initcall_t *call;
 666         int count = preempt_count();
 667
 668         for (call = __initcall_start; call < __initcall_end; call++) {
 669                 ktime_t t0, t1, delta;
 670                 char *msg = NULL;
 671                 char msgbuf[40];
 672                 int result;
 673
 674                 if (initcall_debug) {
 675                         printk("Calling initcall 0x%p", *call);
 676                         print_fn_descriptor_symbol(": %s()",
 677                                         (unsigned long) *call);
 678                         printk("\n");
 679                         t0 = ktime_get();
 680                 }
 681
 682                 result = (*call)();
 683
 684                 if (initcall_debug) {
 685                         t1 = ktime_get();
 686                         delta = ktime_sub(t1, t0);
 687
 688                         printk("initcall 0x%p", *call);
 689                         print_fn_descriptor_symbol(": %s()",
 690                                         (unsigned long) *call);
 691                         printk(" returned %d.\n", result);
 692
 693                         printk("initcall 0x%p ran for %Ld msecs: ",
 694                                 *call, (unsigned long long)delta.tv64 >> 20);
 695                         print_fn_descriptor_symbol("%s()\n",
 696                                 (unsigned long) *call);
 697                 }
 698
 699                 if (result && result != -ENODEV && initcall_debug) {
 700                         sprintf(msgbuf, "error code %d", result);
 701                         msg = msgbuf;
 702                 }
 703                 if (preempt_count() != count) {
 704                         msg = "preemption imbalance";
 705                         preempt_count() = count;
 706                 }
 707                 if (irqs_disabled()) {
 708                         msg = "disabled interrupts";
 709                         local_irq_enable();
 710                 }
 711                 if (msg) {
 712                         printk(KERN_WARNING "initcall at 0x%p", *call);
 713                         print_fn_descriptor_symbol(": %s()",
 714                                         (unsigned long) *call);
 715                         printk(": returned with %s\n", msg);
 716                 }
 717         }
 718
 719         /* Make sure there is no pending stuff from the initcall sequence */
 720         flush_scheduled_work();
 721 }
 722
 723 /*
 724  * Ok, the machine is now initialized. None of the devices
 725  * have been touched yet, but the CPU subsystem is up and
 726  * running, and memory and process management works.
 727  *
 728  * Now we can finally start doing some real work..
 729  */
 730 static void __init do_basic_setup(void)
 731 {
 732         /* drivers will send hotplug events */
 733         init_workqueues();
 734         usermodehelper_init();
 735         driver_init();
 736         init_irq_proc();
 737         do_initcalls();
 738 }
 739
 740 static int __initdata nosoftlockup;
 741
 742 static int __init nosoftlockup_setup(char *str)
 743 {
 744         nosoftlockup = 1;
 745         return 1;
 746 }
 747 __setup("nosoftlockup", nosoftlockup_setup);
 748
 749 static void __init do_pre_smp_initcalls(void)
 750 {
 751         extern int spawn_ksoftirqd(void);
 752
 753         migration_init();
 754         spawn_ksoftirqd();
 755         if (!nosoftlockup)
 756                 spawn_softlockup_task();
 757 }
 758
 759 static void run_init_process(char *init_filename)
 760 {
 761         argv_init[0] = init_filename;
 762         kernel_execve(init_filename, argv_init, envp_init);
 763 }
 764
 765 /* This is a non __init function. Force it to be noinline otherwise gcc
 766  * makes it inline to init() and it becomes part of init.text section
 767  */
 768 static int noinline init_post(void)
 769 {
 770         free_initmem();
 771         unlock_kernel();
 772         mark_rodata_ro();
 773         system_state = SYSTEM_RUNNING;
 774         numa_default_policy();
 775
 776         if (sys_open((const char __user *) "/dev/console", O_RDWR, 0) < 0)
 777                 printk(KERN_WARNING "Warning: unable to open an initial console.\n");
 778
 779         (void) sys_dup(0);
 780         (void) sys_dup(0);
 781
 782         if (ramdisk_execute_command) {
 783                 run_init_process(ramdisk_execute_command);
 784                 printk(KERN_WARNING "Failed to execute %s\n",
 785                                 ramdisk_execute_command);
 786         }
 787
 788         /*
 789          * We try each of these until one succeeds.
 790          *
 791          * The Bourne shell can be used instead of init if we are
 792          * trying to recover a really broken machine.
 793          */
 794         if (execute_command) {
 795                 run_init_process(execute_command);
 796                 printk(KERN_WARNING "Failed to execute %s.  Attempting "
 797                                         "defaults...\n", execute_command);
 798         }
 799         run_init_process("/sbin/init");
 800         run_init_process("/etc/init");
 801         run_init_process("/bin/init");
 802         run_init_process("/bin/sh");
 803
 804         panic("No init found.  Try passing init= option to kernel.");
 805 }
 806
 807 static int __init kernel_init(void * unused)
 808 {
 809         lock_kernel();
 810         /*
 811          * init can run on any cpu.
 812          */
 813         set_cpus_allowed(current, CPU_MASK_ALL);
 814         /*
 815          * Tell the world that we're going to be the grim
 816          * reaper of innocent orphaned children.
 817          *
 818          * We don't want people to have to make incorrect
 819          * assumptions about where in the task array this
 820          * can be found.
 821          */
 822         init_pid_ns.child_reaper = current;
 823
 824         __set_special_pids(1, 1);
 825         cad_pid = task_pid(current);
 826
 827         smp_prepare_cpus(max_cpus);
 828
 829         do_pre_smp_initcalls();
 830
 831         smp_init();
 832         sched_init_smp();
 833
 834         cpuset_init_smp();
 835
 836         do_basic_setup();
 837
 838         /*
 839          * check if there is an early userspace init.  If yes, let it do all
 840          * the work
 841          */
 842
 843         if (!ramdisk_execute_command)
 844                 ramdisk_execute_command = "/init";
 845
 846         if (sys_access((const char __user *) ramdisk_execute_command, 0) != 0) {
 847                 ramdisk_execute_command = NULL;
 848                 prepare_namespace();
 849         }
 850
 851         /*
 852          * Ok, we have completed the initial bootup, and
 853          * we're essentially up and running. Get rid of the
 854          * initmem segments and start the user-mode stuff..
 855          */
 856         init_post();
 857         return 0;
 858 }