linux-kernel-test/init/main.c
Ingo Molnar 4a683bf94b tracing: Fix too large stack usage in do_one_initcall()
One of my testboxes triggered this nasty stack overflow crash
during SCSI probing:

[    5.874004] sd 0:0:0:0: [sda] Write cache: enabled, read cache: enabled, doesn't support DPO or FUA
[    5.875004] device: 'sda': device_add
[    5.878004] BUG: unable to handle kernel NULL pointer dereference at 00000a0c
[    5.878004] IP: [<b1008321>] print_context_stack+0x81/0x110
[    5.878004] *pde = 00000000
[    5.878004] Thread overran stack, or stack corrupted
[    5.878004] Oops: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC
[    5.878004] last sysfs file:
[    5.878004]
[    5.878004] Pid: 1, comm: swapper Not tainted (2.6.31-rc6-tip-01272-g9919e28-dirty #5685)
[    5.878004] EIP: 0060:[<b1008321>] EFLAGS: 00010083 CPU: 0
[    5.878004] EIP is at print_context_stack+0x81/0x110
[    5.878004] EAX: cf8a3000 EBX: cf8a3fe4 ECX: 00000049 EDX: 00000000
[    5.878004] ESI: b1cfce84 EDI: 00000000 EBP: cf8a3018 ESP: cf8a2ff4
[    5.878004]  DS: 007b ES: 007b FS: 00d8 GS: 0000 SS: 0068
[    5.878004] Process swapper (pid: 1, ti=cf8a2000 task=cf8a8000 task.ti=cf8a3000)
[    5.878004] Stack:
[    5.878004]  b1004867 fffff000 cf8a3ffc
[    5.878004] Call Trace:
[    5.878004]  [<b1004867>] ? kernel_thread_helper+0x7/0x10
[    5.878004] BUG: unable to handle kernel NULL pointer dereference at 00000a0c
[    5.878004] IP: [<b1008321>] print_context_stack+0x81/0x110
[    5.878004] *pde = 00000000
[    5.878004] Thread overran stack, or stack corrupted
[    5.878004] Oops: 0000 [#2] PREEMPT SMP DEBUG_PAGEALLOC

The oops did not reveal any more details about the real stack
that we have and the system got into an infinite loop of
recursive pagefaults.

So i booted with CONFIG_STACK_TRACER=y and the 'stacktrace' boot
parameter. The box did not crash (timings/conditions probably
changed a tiny bit to trigger the catastrophic crash), but the
/debug/tracing/stack_trace file was rather revealing:

        Depth    Size   Location    (72 entries)
        -----    ----   --------
  0)     3704      52   __change_page_attr+0xb8/0x290
  1)     3652      24   __change_page_attr_set_clr+0x43/0x90
  2)     3628      60   kernel_map_pages+0x108/0x120
  3)     3568      40   prep_new_page+0x7d/0x130
  4)     3528      84   get_page_from_freelist+0x106/0x420
  5)     3444     116   __alloc_pages_nodemask+0xd7/0x550
  6)     3328      36   allocate_slab+0xb1/0x100
  7)     3292      36   new_slab+0x1c/0x160
  8)     3256      36   __slab_alloc+0x133/0x2b0
  9)     3220       4   kmem_cache_alloc+0x1bb/0x1d0
 10)     3216     108   create_object+0x28/0x250
 11)     3108      40   kmemleak_alloc+0x81/0xc0
 12)     3068      24   kmem_cache_alloc+0x162/0x1d0
 13)     3044      52   scsi_pool_alloc_command+0x29/0x70
 14)     2992      20   scsi_host_alloc_command+0x22/0x70
 15)     2972      24   __scsi_get_command+0x1b/0x90
 16)     2948      28   scsi_get_command+0x35/0x90
 17)     2920      24   scsi_setup_blk_pc_cmnd+0xd4/0x100
 18)     2896     128   sd_prep_fn+0x332/0xa70
 19)     2768      36   blk_peek_request+0xe7/0x1d0
 20)     2732      56   scsi_request_fn+0x54/0x520
 21)     2676      12   __generic_unplug_device+0x2b/0x40
 22)     2664      24   blk_execute_rq_nowait+0x59/0x80
 23)     2640     172   blk_execute_rq+0x6b/0xb0
 24)     2468      32   scsi_execute+0xe0/0x140
 25)     2436      64   scsi_execute_req+0x152/0x160
 26)     2372      60   scsi_vpd_inquiry+0x6c/0x90
 27)     2312      44   scsi_get_vpd_page+0x112/0x160
 28)     2268      52   sd_revalidate_disk+0x1df/0x320
 29)     2216      92   rescan_partitions+0x98/0x330
 30)     2124      52   __blkdev_get+0x309/0x350
 31)     2072       8   blkdev_get+0xf/0x20
 32)     2064      44   register_disk+0xff/0x120
 33)     2020      36   add_disk+0x6e/0xb0
 34)     1984      44   sd_probe_async+0xfb/0x1d0
 35)     1940      44   __async_schedule+0xf4/0x1b0
 36)     1896       8   async_schedule+0x12/0x20
 37)     1888      60   sd_probe+0x305/0x360
 38)     1828      44   really_probe+0x63/0x170
 39)     1784      36   driver_probe_device+0x5d/0x60
 40)     1748      16   __device_attach+0x49/0x50
 41)     1732      32   bus_for_each_drv+0x5b/0x80
 42)     1700      24   device_attach+0x6b/0x70
 43)     1676      16   bus_attach_device+0x47/0x60
 44)     1660      76   device_add+0x33d/0x400
 45)     1584      52   scsi_sysfs_add_sdev+0x6a/0x2c0
 46)     1532     108   scsi_add_lun+0x44b/0x460
 47)     1424     116   scsi_probe_and_add_lun+0x182/0x4e0
 48)     1308      36   __scsi_add_device+0xd9/0xe0
 49)     1272      44   ata_scsi_scan_host+0x10b/0x190
 50)     1228      24   async_port_probe+0x96/0xd0
 51)     1204      44   __async_schedule+0xf4/0x1b0
 52)     1160       8   async_schedule+0x12/0x20
 53)     1152      48   ata_host_register+0x171/0x1d0
 54)     1104      60   ata_pci_sff_activate_host+0xf3/0x230
 55)     1044      44   ata_pci_sff_init_one+0xea/0x100
 56)     1000      48   amd_init_one+0xb2/0x190
 57)      952       8   local_pci_probe+0x13/0x20
 58)      944      32   pci_device_probe+0x68/0x90
 59)      912      44   really_probe+0x63/0x170
 60)      868      36   driver_probe_device+0x5d/0x60
 61)      832      20   __driver_attach+0x89/0xa0
 62)      812      32   bus_for_each_dev+0x5b/0x80
 63)      780      12   driver_attach+0x1e/0x20
 64)      768      72   bus_add_driver+0x14b/0x2d0
 65)      696      36   driver_register+0x6e/0x150
 66)      660      20   __pci_register_driver+0x53/0xc0
 67)      640       8   amd_init+0x14/0x16
 68)      632     572   do_one_initcall+0x2b/0x1d0
 69)       60      12   do_basic_setup+0x56/0x6a
 70)       48      20   kernel_init+0x84/0xce
 71)       28      28   kernel_thread_helper+0x7/0x10

There's a lot of fat functions on that stack trace, but
the largest of all is do_one_initcall(). This is due to
the boot trace entry variables being on the stack.

Fixing this is relatively easy, initcalls are fundamentally
serialized, so we can move the local variables to file scope.

Note that this large stack footprint was present for a
couple of months already - what pushed my system over
the edge was the addition of kmemleak to the call-chain:

  6)     3328      36   allocate_slab+0xb1/0x100
  7)     3292      36   new_slab+0x1c/0x160
  8)     3256      36   __slab_alloc+0x133/0x2b0
  9)     3220       4   kmem_cache_alloc+0x1bb/0x1d0
 10)     3216     108   create_object+0x28/0x250
 11)     3108      40   kmemleak_alloc+0x81/0xc0
 12)     3068      24   kmem_cache_alloc+0x162/0x1d0
 13)     3044      52   scsi_pool_alloc_command+0x29/0x70

This pushes the total to ~3800 bytes, only a tiny bit
more was needed to corrupt the on-kernel-stack thread_info.

The fix reduces the stack footprint from 572 bytes
to 28 bytes.

Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Steven Rostedt <srostedt@redhat.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Jens Axboe <jens.axboe@oracle.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: <stable@kernel.org>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-08-21 13:03:22 +02:00

935 lines
22 KiB
C

/*
* 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>
*/
#include <linux/types.h>
#include <linux/module.h>
#include <linux/proc_fs.h>
#include <linux/kernel.h>
#include <linux/syscalls.h>
#include <linux/stackprotector.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/bootmem.h>
#include <linux/acpi.h>
#include <linux/tty.h>
#include <linux/gfp.h>
#include <linux/percpu.h>
#include <linux/kmod.h>
#include <linux/vmalloc.h>
#include <linux/kernel_stat.h>
#include <linux/start_kernel.h>
#include <linux/security.h>
#include <linux/smp.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/cgroup.h>
#include <linux/efi.h>
#include <linux/tick.h>
#include <linux/interrupt.h>
#include <linux/taskstats_kern.h>
#include <linux/delayacct.h>
#include <linux/unistd.h>
#include <linux/rmap.h>
#include <linux/mempolicy.h>
#include <linux/key.h>
#include <linux/buffer_head.h>
#include <linux/page_cgroup.h>
#include <linux/debug_locks.h>
#include <linux/debugobjects.h>
#include <linux/lockdep.h>
#include <linux/kmemleak.h>
#include <linux/pid_namespace.h>
#include <linux/device.h>
#include <linux/kthread.h>
#include <linux/sched.h>
#include <linux/signal.h>
#include <linux/idr.h>
#include <linux/ftrace.h>
#include <linux/async.h>
#include <linux/kmemcheck.h>
#include <linux/kmemtrace.h>
#include <trace/boot.h>
#include <asm/io.h>
#include <asm/bugs.h>
#include <asm/setup.h>
#include <asm/sections.h>
#include <asm/cacheflush.h>
#ifdef CONFIG_X86_LOCAL_APIC
#include <asm/smp.h>
#endif
static int kernel_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 prio_tree_init(void);
extern void radix_tree_init(void);
extern void free_initmem(void);
#ifndef CONFIG_DEBUG_RODATA
static inline void mark_rodata_ro(void) { }
#endif
#ifdef CONFIG_TC
extern void tc_init(void);
#endif
enum system_states system_state __read_mostly;
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 (*__initdata late_time_init)(void);
extern void softirq_init(void);
/* Untouched command line saved by arch-specific code. */
char __initdata boot_command_line[COMMAND_LINE_SIZE];
/* Untouched saved command line (eg. for /proc) */
char *saved_command_line;
/* Command line for parameter parsing */
static char *static_command_line;
static char *execute_command;
static char *ramdisk_execute_command;
#ifdef CONFIG_SMP
/* Setup configured maximum number of CPUs to activate */
unsigned int __initdata setup_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>.
*/
void __weak arch_disable_smp_support(void) { }
static int __init nosmp(char *str)
{
setup_max_cpus = 0;
arch_disable_smp_support();
return 0;
}
early_param("nosmp", nosmp);
static int __init maxcpus(char *str)
{
get_option(&str, &setup_max_cpus);
if (setup_max_cpus == 0)
arch_disable_smp_support();
return 0;
}
early_param("maxcpus", maxcpus);
#else
const unsigned int setup_max_cpus = NR_CPUS;
#endif
/*
* If set, this is an indication to the drivers that reset the underlying
* device before going ahead with the initialization otherwise driver might
* rely on the BIOS and skip the reset operation.
*
* This is useful if kernel is booting in an unreliable environment.
* For ex. kdump situaiton where previous kernel has crashed, BIOS has been
* skipped and devices will be in unknown state.
*/
unsigned int reset_devices;
EXPORT_SYMBOL(reset_devices);
static int __init set_reset_devices(char *str)
{
reset_devices = 1;
return 1;
}
__setup("reset_devices", set_reset_devices);
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;
int had_early_param = 0;
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).
* Keep iterating, as we can have early
* params and __setups of same names 8( */
if (line[n] == '\0' || line[n] == '=')
had_early_param = 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 had_early_param;
}
/*
* This should be approx 2 Bo*oMips to start (note initial shift), and will
* still work even if initially too large, it will just take slightly longer
*/
unsigned long loops_per_jiffy = (1<<12);
EXPORT_SYMBOL(loops_per_jiffy);
static int __init debug_kernel(char *str)
{
console_loglevel = 10;
return 0;
}
static int __init quiet_kernel(char *str)
{
console_loglevel = 4;
return 0;
}
early_param("debug", debug_kernel);
early_param("quiet", quiet_kernel);
static int __init loglevel(char *str)
{
get_option(&str, &console_loglevel);
return 0;
}
early_param("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 misspelled 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;
}
#ifdef CONFIG_DEBUG_PAGEALLOC
int __read_mostly debug_pagealloc_enabled = 0;
#endif
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);
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);
#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 setup_nr_cpu_ids(void) { }
static inline void smp_prepare_cpus(unsigned int maxcpus) { }
#else
#if NR_CPUS > BITS_PER_LONG
cpumask_t cpu_mask_all __read_mostly = CPU_MASK_ALL;
EXPORT_SYMBOL(cpu_mask_all);
#endif
/* Setup number of possible processor ids */
int nr_cpu_ids __read_mostly = NR_CPUS;
EXPORT_SYMBOL(nr_cpu_ids);
/* An arch may set nr_cpu_ids earlier if needed, so this would be redundant */
static void __init setup_nr_cpu_ids(void)
{
nr_cpu_ids = find_last_bit(cpumask_bits(cpu_possible_mask),NR_CPUS) + 1;
}
#ifndef CONFIG_HAVE_SETUP_PER_CPU_AREA
unsigned long __per_cpu_offset[NR_CPUS] __read_mostly;
EXPORT_SYMBOL(__per_cpu_offset);
static void __init setup_per_cpu_areas(void)
{
unsigned long size, i;
char *ptr;
unsigned long nr_possible_cpus = num_possible_cpus();
/* Copy section for each CPU (we discard the original) */
size = ALIGN(PERCPU_ENOUGH_ROOM, PAGE_SIZE);
ptr = alloc_bootmem_pages(size * nr_possible_cpus);
for_each_possible_cpu(i) {
__per_cpu_offset[i] = ptr - __per_cpu_start;
memcpy(ptr, __per_cpu_start, __per_cpu_end - __per_cpu_start);
ptr += size;
}
}
#endif /* CONFIG_HAVE_SETUP_PER_CPU_AREA */
/* Called by boot processor to activate the rest. */
static void __init smp_init(void)
{
unsigned int cpu;
/*
* Set up the current CPU as possible to migrate to.
* The other ones will be done by cpu_up/cpu_down()
*/
set_cpu_active(smp_processor_id(), true);
/* FIXME: This should be done in userspace --RR */
for_each_present_cpu(cpu) {
if (num_online_cpus() >= setup_max_cpus)
break;
if (!cpu_online(cpu))
cpu_up(cpu);
}
/* Any cleanup work */
printk(KERN_INFO "Brought up %ld CPUs\n", (long)num_online_cpus());
smp_cpus_done(setup_max_cpus);
}
#endif
/*
* We need to store the untouched command line for future reference.
* We also need to store the touched command line since the parameter
* parsing is performed in place, and we should allow a component to
* store reference of name/value for future reference.
*/
static void __init setup_command_line(char *command_line)
{
saved_command_line = alloc_bootmem(strlen (boot_command_line)+1);
static_command_line = alloc_bootmem(strlen (command_line)+1);
strcpy (saved_command_line, boot_command_line);
strcpy (static_command_line, command_line);
}
/*
* 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 noinline void __init_refok rest_init(void)
__releases(kernel_lock)
{
int pid;
kernel_thread(kernel_init, NULL, CLONE_FS | CLONE_SIGHAND);
numa_default_policy();
pid = kernel_thread(kthreadd, NULL, CLONE_FS | CLONE_FILES);
kthreadd_task = find_task_by_pid_ns(pid, &init_pid_ns);
unlock_kernel();
/*
* The boot idle thread must execute schedule()
* at least once to get things moving:
*/
init_idle_bootup_task(current);
rcu_scheduler_starting();
preempt_enable_no_resched();
schedule();
preempt_disable();
/* Call into cpu_idle with preempt disabled */
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) ||
(strcmp(param, "console") == 0 &&
strcmp(p->str, "earlycon") == 0)
) {
if (p->setup_func(val) != 0)
printk(KERN_WARNING
"Malformed early option '%s'\n", param);
}
}
/* We accept everything at this stage. */
return 0;
}
void __init parse_early_options(char *cmdline)
{
parse_args("early options", cmdline, NULL, 0, do_early_param);
}
/* 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, boot_command_line, COMMAND_LINE_SIZE);
parse_early_options(tmp_cmdline);
done = 1;
}
/*
* Activate the first processor.
*/
static void __init boot_cpu_init(void)
{
int cpu = smp_processor_id();
/* Mark the boot cpu "present", "online" etc for SMP and UP case */
set_cpu_online(cpu, true);
set_cpu_present(cpu, true);
set_cpu_possible(cpu, true);
}
void __init __weak smp_setup_processor_id(void)
{
}
void __init __weak thread_info_cache_init(void)
{
}
/*
* Set up kernel memory allocators
*/
static void __init mm_init(void)
{
/*
* page_cgroup requires countinous pages as memmap
* and it's bigger than MAX_ORDER unless SPARSEMEM.
*/
page_cgroup_init_flatmem();
mem_init();
kmem_cache_init();
pgtable_cache_init();
vmalloc_init();
}
asmlinkage void __init start_kernel(void)
{
char * command_line;
extern struct kernel_param __start___param[], __stop___param[];
smp_setup_processor_id();
/*
* Need to run as early as possible, to initialize the
* lockdep hash:
*/
lockdep_init();
debug_objects_early_init();
/*
* Set up the the initial canary ASAP:
*/
boot_init_stack_canary();
cgroup_init_early();
local_irq_disable();
early_boot_irqs_off();
early_init_irq_lock_class();
/*
* Interrupts are still disabled. Do necessary setups, then
* enable them
*/
lock_kernel();
tick_init();
boot_cpu_init();
page_address_init();
printk(KERN_NOTICE "%s", linux_banner);
setup_arch(&command_line);
mm_init_owner(&init_mm, &init_task);
setup_command_line(command_line);
setup_per_cpu_areas();
setup_nr_cpu_ids();
smp_prepare_boot_cpu(); /* arch-specific boot-cpu hooks */
build_all_zonelists();
page_alloc_init();
printk(KERN_NOTICE "Kernel command line: %s\n", boot_command_line);
parse_early_param();
parse_args("Booting kernel", static_command_line, __start___param,
__stop___param - __start___param,
&unknown_bootoption);
/*
* These use large bootmem allocations and must precede
* kmem_cache_init()
*/
pidhash_init();
vfs_caches_init_early();
sort_main_extable();
trap_init();
mm_init();
/*
* Set up the scheduler prior starting any interrupts (such as the
* timer interrupt). Full topology setup happens at smp_init()
* time - but meanwhile we still have a functioning scheduler.
*/
sched_init();
/*
* Disable preemption - early bootup scheduling is extremely
* fragile until we cpu_idle() for the first time.
*/
preempt_disable();
if (!irqs_disabled()) {
printk(KERN_WARNING "start_kernel(): bug: interrupts were "
"enabled *very* early, fixing it\n");
local_irq_disable();
}
rcu_init();
/* init some links before init_ISA_irqs() */
early_irq_init();
init_IRQ();
prio_tree_init();
init_timers();
hrtimers_init();
softirq_init();
timekeeping_init();
time_init();
sched_clock_init();
profile_init();
if (!irqs_disabled())
printk(KERN_CRIT "start_kernel(): bug: interrupts were "
"enabled early\n");
early_boot_irqs_on();
local_irq_enable();
/* Interrupts are enabled now so all GFP allocations are safe. */
set_gfp_allowed_mask(__GFP_BITS_MASK);
kmem_cache_init_late();
/*
* 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);
lockdep_info();
/*
* Need to run this when irqs are enabled, because it wants
* to self-test [hard/soft]-irqs on/off lock inversion bugs
* too:
*/
locking_selftest();
#ifdef CONFIG_BLK_DEV_INITRD
if (initrd_start && !initrd_below_start_ok &&
page_to_pfn(virt_to_page((void *)initrd_start)) < min_low_pfn) {
printk(KERN_CRIT "initrd overwritten (0x%08lx < 0x%08lx) - "
"disabling it.\n",
page_to_pfn(virt_to_page((void *)initrd_start)),
min_low_pfn);
initrd_start = 0;
}
#endif
page_cgroup_init();
enable_debug_pagealloc();
kmemtrace_init();
kmemleak_init();
debug_objects_mem_init();
idr_init_cache();
setup_per_cpu_pageset();
numa_policy_init();
if (late_time_init)
late_time_init();
calibrate_delay();
pidmap_init();
anon_vma_init();
#ifdef CONFIG_X86
if (efi_enabled)
efi_enter_virtual_mode();
#endif
thread_info_cache_init();
cred_init();
fork_init(num_physpages);
proc_caches_init();
buffer_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
cgroup_init();
cpuset_init();
taskstats_init_early();
delayacct_init();
check_bugs();
acpi_early_init(); /* before LAPIC and SMP init */
ftrace_init();
/* Do the rest non-__init'ed, we're now alive */
rest_init();
}
/* Call all constructor functions linked into the kernel. */
static void __init do_ctors(void)
{
#ifdef CONFIG_CONSTRUCTORS
ctor_fn_t *call = (ctor_fn_t *) __ctors_start;
for (; call < (ctor_fn_t *) __ctors_end; call++)
(*call)();
#endif
}
int initcall_debug;
core_param(initcall_debug, initcall_debug, bool, 0644);
static char msgbuf[64];
static struct boot_trace_call call;
static struct boot_trace_ret ret;
int do_one_initcall(initcall_t fn)
{
int count = preempt_count();
ktime_t calltime, delta, rettime;
if (initcall_debug) {
call.caller = task_pid_nr(current);
printk("calling %pF @ %i\n", fn, call.caller);
calltime = ktime_get();
trace_boot_call(&call, fn);
enable_boot_trace();
}
ret.result = fn();
if (initcall_debug) {
disable_boot_trace();
rettime = ktime_get();
delta = ktime_sub(rettime, calltime);
ret.duration = (unsigned long long) ktime_to_ns(delta) >> 10;
trace_boot_ret(&ret, fn);
printk("initcall %pF returned %d after %Ld usecs\n", fn,
ret.result, ret.duration);
}
msgbuf[0] = 0;
if (ret.result && ret.result != -ENODEV && initcall_debug)
sprintf(msgbuf, "error code %d ", ret.result);
if (preempt_count() != count) {
strlcat(msgbuf, "preemption imbalance ", sizeof(msgbuf));
preempt_count() = count;
}
if (irqs_disabled()) {
strlcat(msgbuf, "disabled interrupts ", sizeof(msgbuf));
local_irq_enable();
}
if (msgbuf[0]) {
printk("initcall %pF returned with %s\n", fn, msgbuf);
}
return ret.result;
}
extern initcall_t __initcall_start[], __initcall_end[], __early_initcall_end[];
static void __init do_initcalls(void)
{
initcall_t *call;
for (call = __early_initcall_end; call < __initcall_end; call++)
do_one_initcall(*call);
/* 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)
{
rcu_init_sched(); /* needed by module_init stage. */
init_workqueues();
cpuset_init_smp();
usermodehelper_init();
driver_init();
init_irq_proc();
do_ctors();
do_initcalls();
}
static void __init do_pre_smp_initcalls(void)
{
initcall_t *call;
for (call = __initcall_start; call < __early_initcall_end; call++)
do_one_initcall(*call);
}
static void run_init_process(char *init_filename)
{
argv_init[0] = init_filename;
kernel_execve(init_filename, argv_init, envp_init);
}
/* This is a non __init function. Force it to be noinline otherwise gcc
* makes it inline to init() and it becomes part of init.text section
*/
static noinline int init_post(void)
__releases(kernel_lock)
{
/* need to finish all async __init code before freeing the memory */
async_synchronize_full();
free_initmem();
unlock_kernel();
mark_rodata_ro();
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);
current->signal->flags |= SIGNAL_UNKILLABLE;
if (ramdisk_execute_command) {
run_init_process(ramdisk_execute_command);
printk(KERN_WARNING "Failed to execute %s\n",
ramdisk_execute_command);
}
/*
* We try each of these until one succeeds.
*
* The Bourne shell can be used instead of init if we are
* trying to recover a really broken machine.
*/
if (execute_command) {
run_init_process(execute_command);
printk(KERN_WARNING "Failed to execute %s. Attempting "
"defaults...\n", execute_command);
}
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.");
}
static int __init kernel_init(void * unused)
{
lock_kernel();
/*
* init can allocate pages on any node
*/
set_mems_allowed(node_possible_map);
/*
* init can run on any cpu.
*/
set_cpus_allowed_ptr(current, cpu_all_mask);
/*
* 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.
*/
init_pid_ns.child_reaper = current;
cad_pid = task_pid(current);
smp_prepare_cpus(setup_max_cpus);
do_pre_smp_initcalls();
start_boot_trace();
smp_init();
sched_init_smp();
do_basic_setup();
/*
* check if there is an early userspace init. If yes, let it do all
* the work
*/
if (!ramdisk_execute_command)
ramdisk_execute_command = "/init";
if (sys_access((const char __user *) ramdisk_execute_command, 0) != 0) {
ramdisk_execute_command = NULL;
prepare_namespace();
}
/*
* Ok, we have completed the initial bootup, and
* we're essentially up and running. Get rid of the
* initmem segments and start the user-mode stuff..
*/
init_post();
return 0;
}