linux/init/main.c
Linus Torvalds 6345d24daf mm: Fix boot crash in mm_alloc()
Thomas Gleixner reports that we now have a boot crash triggered by
CONFIG_CPUMASK_OFFSTACK=y:

    BUG: unable to handle kernel NULL pointer dereference at   (null)
    IP: [<c11ae035>] find_next_bit+0x55/0xb0
    Call Trace:
     [<c11addda>] cpumask_any_but+0x2a/0x70
     [<c102396b>] flush_tlb_mm+0x2b/0x80
     [<c1022705>] pud_populate+0x35/0x50
     [<c10227ba>] pgd_alloc+0x9a/0xf0
     [<c103a3fc>] mm_init+0xec/0x120
     [<c103a7a3>] mm_alloc+0x53/0xd0

which was introduced by commit de03c72cfc ("mm: convert
mm->cpu_vm_cpumask into cpumask_var_t"), and is due to wrong ordering of
mm_init() vs mm_init_cpumask

Thomas wrote a patch to just fix the ordering of initialization, but I
hate the new double allocation in the fork path, so I ended up instead
doing some more radical surgery to clean it all up.

Reported-by: Thomas Gleixner <tglx@linutronix.de>
Reported-by: Ingo Molnar <mingo@elte.hu>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-05-29 11:32:28 -07:00

834 lines
20 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/ioport.h>
#include <linux/init.h>
#include <linux/initrd.h>
#include <linux/bootmem.h>
#include <linux/acpi.h>
#include <linux/tty.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/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/kgdb.h>
#include <linux/ftrace.h>
#include <linux/async.h>
#include <linux/kmemcheck.h>
#include <linux/sfi.h>
#include <linux/shmem_fs.h>
#include <linux/slab.h>
#include <linux/perf_event.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
/*
* Debug helper: via this flag we know that we are in 'early bootup code'
* where only the boot processor is running with IRQ disabled. This means
* two things - IRQ must not be enabled before the flag is cleared and some
* operations which are not allowed with IRQ disabled are allowed while the
* flag is set.
*/
bool early_boot_irqs_disabled __read_mostly;
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;
/*
* 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 const char * argv_init[MAX_INIT_ARGS+2] = { "init", NULL, };
const char * envp_init[MAX_INIT_ENVS+2] = { "HOME=/", "TERM=linux", NULL, };
static const char *panic_later, *panic_param;
extern const struct obs_kernel_param __setup_start[], __setup_end[];
static int __init obsolete_checksetup(char *line)
{
const 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
* unused parameters (modprobe will find them in /proc/cmdline).
*/
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;
/* Unused module parameter. */
if (strchr(param, '.') && (!val || strchr(param, '.') < val))
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
static const unsigned int setup_max_cpus = NR_CPUS;
#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_nr_cpu_ids(void) { }
static inline void smp_prepare_cpus(unsigned int maxcpus) { }
#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 __initdata DECLARE_COMPLETION(kthreadd_done);
static noinline void __init_refok rest_init(void)
{
int pid;
rcu_scheduler_starting();
/*
* We need to spawn init first so that it obtains pid 1, however
* the init task will end up wanting to create kthreads, which, if
* we schedule it before we create kthreadd, will OOPS.
*/
kernel_thread(kernel_init, NULL, CLONE_FS | CLONE_SIGHAND);
numa_default_policy();
pid = kernel_thread(kthreadd, NULL, CLONE_FS | CLONE_FILES);
rcu_read_lock();
kthreadd_task = find_task_by_pid_ns(pid, &init_pid_ns);
rcu_read_unlock();
complete(&kthreadd_done);
/*
* 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)
{
const 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_active(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();
percpu_init_late();
pgtable_cache_init();
vmalloc_init();
}
asmlinkage void __init start_kernel(void)
{
char * command_line;
extern const 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_disabled = true;
/*
* Interrupts are still disabled. Do necessary setups, then
* enable them
*/
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);
mm_init_cpumask(&init_mm);
setup_command_line(command_line);
setup_nr_cpu_ids();
setup_per_cpu_areas();
smp_prepare_boot_cpu(); /* arch-specific boot-cpu hooks */
build_all_zonelists(NULL);
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()
*/
setup_log_buf(0);
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();
}
idr_init_cache();
perf_event_init();
rcu_init();
radix_tree_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();
profile_init();
if (!irqs_disabled())
printk(KERN_CRIT "start_kernel(): bug: interrupts were "
"enabled early\n");
early_boot_irqs_disabled = false;
local_irq_enable();
/* Interrupts are enabled now so all GFP allocations are safe. */
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();
debug_objects_mem_init();
kmemleak_init();
setup_per_cpu_pageset();
numa_policy_init();
if (late_time_init)
late_time_init();
sched_clock_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(totalram_pages);
proc_caches_init();
buffer_init();
key_init();
security_init();
dbg_late_init();
vfs_caches_init(totalram_pages);
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 */
sfi_init_late();
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 *fn = (ctor_fn_t *) __ctors_start;
for (; fn < (ctor_fn_t *) __ctors_end; fn++)
(*fn)();
#endif
}
int initcall_debug;
core_param(initcall_debug, initcall_debug, bool, 0644);
static char msgbuf[64];
static int __init_or_module do_one_initcall_debug(initcall_t fn)
{
ktime_t calltime, delta, rettime;
unsigned long long duration;
int ret;
printk(KERN_DEBUG "calling %pF @ %i\n", fn, task_pid_nr(current));
calltime = ktime_get();
ret = fn();
rettime = ktime_get();
delta = ktime_sub(rettime, calltime);
duration = (unsigned long long) ktime_to_ns(delta) >> 10;
printk(KERN_DEBUG "initcall %pF returned %d after %lld usecs\n", fn,
ret, duration);
return ret;
}
int __init_or_module do_one_initcall(initcall_t fn)
{
int count = preempt_count();
int ret;
if (initcall_debug)
ret = do_one_initcall_debug(fn);
else
ret = fn();
msgbuf[0] = 0;
if (ret && ret != -ENODEV && initcall_debug)
sprintf(msgbuf, "error code %d ", ret);
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;
}
extern initcall_t __initcall_start[], __initcall_end[], __early_initcall_end[];
static void __init do_initcalls(void)
{
initcall_t *fn;
for (fn = __early_initcall_end; fn < __initcall_end; fn++)
do_one_initcall(*fn);
}
/*
* 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)
{
cpuset_init_smp();
usermodehelper_init();
init_tmpfs();
driver_init();
init_irq_proc();
do_ctors();
do_initcalls();
}
static void __init do_pre_smp_initcalls(void)
{
initcall_t *fn;
for (fn = __initcall_start; fn < __early_initcall_end; fn++)
do_one_initcall(*fn);
}
static void run_init_process(const 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)
{
/* need to finish all async __init code before freeing the memory */
async_synchronize_full();
free_initmem();
mark_rodata_ro();
system_state = SYSTEM_RUNNING;
numa_default_policy();
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. "
"See Linux Documentation/init.txt for guidance.");
}
static int __init kernel_init(void * unused)
{
/*
* Wait until kthreadd is all set-up.
*/
wait_for_completion(&kthreadd_done);
/*
* init can allocate pages on any node
*/
set_mems_allowed(node_states[N_HIGH_MEMORY]);
/*
* init can run on any cpu.
*/
set_cpus_allowed_ptr(current, cpu_all_mask);
cad_pid = task_pid(current);
smp_prepare_cpus(setup_max_cpus);
do_pre_smp_initcalls();
lockup_detector_init();
smp_init();
sched_init_smp();
do_basic_setup();
/* Open the /dev/console on the rootfs, this should never fail */
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);
/*
* 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;
}