linux/init/main.c
David Howells d84f4f992c CRED: Inaugurate COW credentials
Inaugurate copy-on-write credentials management.  This uses RCU to manage the
credentials pointer in the task_struct with respect to accesses by other tasks.
A process may only modify its own credentials, and so does not need locking to
access or modify its own credentials.

A mutex (cred_replace_mutex) is added to the task_struct to control the effect
of PTRACE_ATTACHED on credential calculations, particularly with respect to
execve().

With this patch, the contents of an active credentials struct may not be
changed directly; rather a new set of credentials must be prepared, modified
and committed using something like the following sequence of events:

	struct cred *new = prepare_creds();
	int ret = blah(new);
	if (ret < 0) {
		abort_creds(new);
		return ret;
	}
	return commit_creds(new);

There are some exceptions to this rule: the keyrings pointed to by the active
credentials may be instantiated - keyrings violate the COW rule as managing
COW keyrings is tricky, given that it is possible for a task to directly alter
the keys in a keyring in use by another task.

To help enforce this, various pointers to sets of credentials, such as those in
the task_struct, are declared const.  The purpose of this is compile-time
discouragement of altering credentials through those pointers.  Once a set of
credentials has been made public through one of these pointers, it may not be
modified, except under special circumstances:

  (1) Its reference count may incremented and decremented.

  (2) The keyrings to which it points may be modified, but not replaced.

The only safe way to modify anything else is to create a replacement and commit
using the functions described in Documentation/credentials.txt (which will be
added by a later patch).

This patch and the preceding patches have been tested with the LTP SELinux
testsuite.

This patch makes several logical sets of alteration:

 (1) execve().

     This now prepares and commits credentials in various places in the
     security code rather than altering the current creds directly.

 (2) Temporary credential overrides.

     do_coredump() and sys_faccessat() now prepare their own credentials and
     temporarily override the ones currently on the acting thread, whilst
     preventing interference from other threads by holding cred_replace_mutex
     on the thread being dumped.

     This will be replaced in a future patch by something that hands down the
     credentials directly to the functions being called, rather than altering
     the task's objective credentials.

 (3) LSM interface.

     A number of functions have been changed, added or removed:

     (*) security_capset_check(), ->capset_check()
     (*) security_capset_set(), ->capset_set()

     	 Removed in favour of security_capset().

     (*) security_capset(), ->capset()

     	 New.  This is passed a pointer to the new creds, a pointer to the old
     	 creds and the proposed capability sets.  It should fill in the new
     	 creds or return an error.  All pointers, barring the pointer to the
     	 new creds, are now const.

     (*) security_bprm_apply_creds(), ->bprm_apply_creds()

     	 Changed; now returns a value, which will cause the process to be
     	 killed if it's an error.

     (*) security_task_alloc(), ->task_alloc_security()

     	 Removed in favour of security_prepare_creds().

     (*) security_cred_free(), ->cred_free()

     	 New.  Free security data attached to cred->security.

     (*) security_prepare_creds(), ->cred_prepare()

     	 New. Duplicate any security data attached to cred->security.

     (*) security_commit_creds(), ->cred_commit()

     	 New. Apply any security effects for the upcoming installation of new
     	 security by commit_creds().

     (*) security_task_post_setuid(), ->task_post_setuid()

     	 Removed in favour of security_task_fix_setuid().

     (*) security_task_fix_setuid(), ->task_fix_setuid()

     	 Fix up the proposed new credentials for setuid().  This is used by
     	 cap_set_fix_setuid() to implicitly adjust capabilities in line with
     	 setuid() changes.  Changes are made to the new credentials, rather
     	 than the task itself as in security_task_post_setuid().

     (*) security_task_reparent_to_init(), ->task_reparent_to_init()

     	 Removed.  Instead the task being reparented to init is referred
     	 directly to init's credentials.

	 NOTE!  This results in the loss of some state: SELinux's osid no
	 longer records the sid of the thread that forked it.

     (*) security_key_alloc(), ->key_alloc()
     (*) security_key_permission(), ->key_permission()

     	 Changed.  These now take cred pointers rather than task pointers to
     	 refer to the security context.

 (4) sys_capset().

     This has been simplified and uses less locking.  The LSM functions it
     calls have been merged.

 (5) reparent_to_kthreadd().

     This gives the current thread the same credentials as init by simply using
     commit_thread() to point that way.

 (6) __sigqueue_alloc() and switch_uid()

     __sigqueue_alloc() can't stop the target task from changing its creds
     beneath it, so this function gets a reference to the currently applicable
     user_struct which it then passes into the sigqueue struct it returns if
     successful.

     switch_uid() is now called from commit_creds(), and possibly should be
     folded into that.  commit_creds() should take care of protecting
     __sigqueue_alloc().

 (7) [sg]et[ug]id() and co and [sg]et_current_groups.

     The set functions now all use prepare_creds(), commit_creds() and
     abort_creds() to build and check a new set of credentials before applying
     it.

     security_task_set[ug]id() is called inside the prepared section.  This
     guarantees that nothing else will affect the creds until we've finished.

     The calling of set_dumpable() has been moved into commit_creds().

     Much of the functionality of set_user() has been moved into
     commit_creds().

     The get functions all simply access the data directly.

 (8) security_task_prctl() and cap_task_prctl().

     security_task_prctl() has been modified to return -ENOSYS if it doesn't
     want to handle a function, or otherwise return the return value directly
     rather than through an argument.

     Additionally, cap_task_prctl() now prepares a new set of credentials, even
     if it doesn't end up using it.

 (9) Keyrings.

     A number of changes have been made to the keyrings code:

     (a) switch_uid_keyring(), copy_keys(), exit_keys() and suid_keys() have
     	 all been dropped and built in to the credentials functions directly.
     	 They may want separating out again later.

     (b) key_alloc() and search_process_keyrings() now take a cred pointer
     	 rather than a task pointer to specify the security context.

     (c) copy_creds() gives a new thread within the same thread group a new
     	 thread keyring if its parent had one, otherwise it discards the thread
     	 keyring.

     (d) The authorisation key now points directly to the credentials to extend
     	 the search into rather pointing to the task that carries them.

     (e) Installing thread, process or session keyrings causes a new set of
     	 credentials to be created, even though it's not strictly necessary for
     	 process or session keyrings (they're shared).

(10) Usermode helper.

     The usermode helper code now carries a cred struct pointer in its
     subprocess_info struct instead of a new session keyring pointer.  This set
     of credentials is derived from init_cred and installed on the new process
     after it has been cloned.

     call_usermodehelper_setup() allocates the new credentials and
     call_usermodehelper_freeinfo() discards them if they haven't been used.  A
     special cred function (prepare_usermodeinfo_creds()) is provided
     specifically for call_usermodehelper_setup() to call.

     call_usermodehelper_setkeys() adjusts the credentials to sport the
     supplied keyring as the new session keyring.

(11) SELinux.

     SELinux has a number of changes, in addition to those to support the LSM
     interface changes mentioned above:

     (a) selinux_setprocattr() no longer does its check for whether the
     	 current ptracer can access processes with the new SID inside the lock
     	 that covers getting the ptracer's SID.  Whilst this lock ensures that
     	 the check is done with the ptracer pinned, the result is only valid
     	 until the lock is released, so there's no point doing it inside the
     	 lock.

(12) is_single_threaded().

     This function has been extracted from selinux_setprocattr() and put into
     a file of its own in the lib/ directory as join_session_keyring() now
     wants to use it too.

     The code in SELinux just checked to see whether a task shared mm_structs
     with other tasks (CLONE_VM), but that isn't good enough.  We really want
     to know if they're part of the same thread group (CLONE_THREAD).

(13) nfsd.

     The NFS server daemon now has to use the COW credentials to set the
     credentials it is going to use.  It really needs to pass the credentials
     down to the functions it calls, but it can't do that until other patches
     in this series have been applied.

Signed-off-by: David Howells <dhowells@redhat.com>
Acked-by: James Morris <jmorris@namei.org>
Signed-off-by: James Morris <jmorris@namei.org>
2008-11-14 10:39:23 +11:00

890 lines
21 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/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/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/unwind.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/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 <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
/*
* This is one of the first .c files built. Error out early if we have compiler
* trouble.
*/
#if __GNUC__ == 4 && __GNUC_MINOR__ == 1 && __GNUC_PATCHLEVEL__ == 0
#warning gcc-4.1.0 is known to miscompile the kernel. A different compiler version is recommended.
#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);
#ifdef CONFIG_ACPI
extern void acpi_early_init(void);
#else
static inline void acpi_early_init(void) { }
#endif
#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;
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 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>.
*/
#ifndef CONFIG_X86_IO_APIC
static inline void disable_ioapic_setup(void) {};
#endif
static int __init nosmp(char *str)
{
setup_max_cpus = 0;
disable_ioapic_setup();
return 0;
}
early_param("nosmp", nosmp);
static int __init maxcpus(char *str)
{
get_option(&str, &setup_max_cpus);
if (setup_max_cpus == 0)
disable_ioapic_setup();
return 0;
}
early_param("maxcpus", maxcpus);
#else
#define 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)
{
int cpu, highest_cpu = 0;
for_each_possible_cpu(cpu)
highest_cpu = cpu;
nr_cpu_ids = highest_cpu + 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()
*/
cpu = smp_processor_id();
cpu_set(cpu, cpu_active_map);
/* 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 void noinline __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);
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;
}
/* 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_args("early options", tmp_cmdline, NULL, 0, do_early_param);
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 */
cpu_set(cpu, cpu_online_map);
cpu_set(cpu, cpu_present_map);
cpu_set(cpu, cpu_possible_map);
}
void __init __weak smp_setup_processor_id(void)
{
}
void __init __weak thread_info_cache_init(void)
{
}
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:
*/
unwind_init();
lockdep_init();
debug_objects_early_init();
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);
printk(linux_banner);
setup_arch(&command_line);
mm_init_owner(&init_mm, &init_task);
setup_command_line(command_line);
unwind_setup();
setup_per_cpu_areas();
setup_nr_cpu_ids();
smp_prepare_boot_cpu(); /* arch-specific boot-cpu hooks */
/*
* 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", boot_command_line);
parse_early_param();
parse_args("Booting kernel", static_command_line, __start___param,
__stop___param - __start___param,
&unknown_bootoption);
if (!irqs_disabled()) {
printk(KERN_WARNING "start_kernel(): bug: interrupts were "
"enabled *very* early, fixing it\n");
local_irq_disable();
}
sort_main_extable();
trap_init();
rcu_init();
init_IRQ();
pidhash_init();
init_timers();
hrtimers_init();
softirq_init();
timekeeping_init();
time_init();
sched_clock_init();
profile_init();
if (!irqs_disabled())
printk("start_kernel(): bug: interrupts were enabled early\n");
early_boot_irqs_on();
local_irq_enable();
/*
* 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
vmalloc_init();
vfs_caches_init_early();
cpuset_init_early();
page_cgroup_init();
mem_init();
enable_debug_pagealloc();
cpu_hotplug_init();
kmem_cache_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();
pgtable_cache_init();
prio_tree_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();
}
static int initcall_debug;
core_param(initcall_debug, initcall_debug, bool, 0644);
int do_one_initcall(initcall_t fn)
{
int count = preempt_count();
ktime_t delta;
char msgbuf[64];
struct boot_trace it;
if (initcall_debug) {
it.caller = task_pid_nr(current);
printk("calling %pF @ %i\n", fn, it.caller);
it.calltime = ktime_get();
}
it.result = fn();
if (initcall_debug) {
it.rettime = ktime_get();
delta = ktime_sub(it.rettime, it.calltime);
it.duration = (unsigned long long) delta.tv64 >> 10;
printk("initcall %pF returned %d after %Ld usecs\n", fn,
it.result, it.duration);
trace_boot(&it, fn);
}
msgbuf[0] = 0;
if (it.result && it.result != -ENODEV && initcall_debug)
sprintf(msgbuf, "error code %d ", it.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 it.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();
usermodehelper_init();
driver_init();
init_irq_proc();
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 int noinline init_post(void)
{
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 run on any cpu.
*/
set_cpus_allowed_ptr(current, CPU_MASK_ALL_PTR);
/*
* 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();
cpuset_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..
*/
stop_boot_trace();
init_post();
return 0;
}