#include <linux/delay.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/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/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/kmemtrace.h>
#include <linux/sfi.h>
#include <linux/shmem_fs.h>
#include <linux/slab.h>
-#include <trace/boot.h>
+#include <linux/perf_event.h>
#include <asm/io.h>
#include <asm/bugs.h>
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);
*/
#define MAX_INIT_ARGS CONFIG_INIT_ENV_ARG_LIMIT
#define MAX_INIT_ENVS CONFIG_INIT_ENV_ARG_LIMIT
+#ifdef CONFIG_INIT_PASS_ALL_PARAMS
+#define INIT_PASS_FUNCTION pass_all_bootoptions
+#else
+#define INIT_PASS_FUNCTION pass_unknown_bootoptions
+#endif
extern void time_init(void);
/* Default late time init is NULL. archs can override this later. */
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);
-
-/* this is hard limit */
-static int __init nrcpus(char *str)
-{
- int nr_cpus;
-
- get_option(&str, &nr_cpus);
- if (nr_cpus > 0 && nr_cpus < nr_cpu_ids)
- nr_cpu_ids = nr_cpus;
-
- return 0;
-}
-
-early_param("nr_cpus", nrcpus);
-
-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
-static 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
__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 * 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 struct obs_kernel_param __setup_start[], __setup_end[];
+extern const struct obs_kernel_param __setup_start[], __setup_end[];
static int __init obsolete_checksetup(char *line)
{
- struct obs_kernel_param *p;
+ 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 (parameqn(line, p->str, n)) {
if (p->early) {
/* Already done in parse_early_param?
* (Needs exact match on param part).
static int __init quiet_kernel(char *str)
{
- console_loglevel = 4;
+ console_loglevel = 2;
return 0;
}
static int __init loglevel(char *str)
{
- get_option(&str, &console_loglevel);
- return 0;
+ int newlevel;
+
+ /*
+ * Only update loglevel value when a correct setting was passed,
+ * to prevent blind crashes (when loglevel being set to 0) that
+ * are quite hard to debug
+ */
+ if (get_option(&str, &newlevel)) {
+ console_loglevel = newlevel;
+ return 0;
+ }
+
+ return -EINVAL;
}
early_param("loglevel", loglevel);
/*
- * Unknown boot options get handed to init, unless they look like
- * unused parameters (modprobe will find them in /proc/cmdline).
+ * Select boot options to hand to init. If all is set hand off them all
+ * otherwise only hand off unused ones which do not apply to modules
+ * (modprobe will find them in /proc/cmdline).
*/
-static int __init unknown_bootoption(char *param, char *val)
+static int __init pass_bootoption(char *param, char *val, int all)
{
/* Change NUL term back to "=", to make "param" the whole string. */
if (val) {
}
/* Handle obsolete-style parameters */
- if (obsolete_checksetup(param))
+ if (obsolete_checksetup(param) && !all)
return 0;
/* Unused module parameter. */
- if (strchr(param, '.') && (!val || strchr(param, '.') < val))
+ if (!all && strchr(param, '.') && (!val || strchr(param, '.') < val))
return 0;
if (panic_later)
}
return 0;
}
+static int __init pass_unknown_bootoptions(char *param, char *val, int known)
+{
+ if (known)
+ return 0;
+ return pass_bootoption(param, val, 0);
+}
+static int __init pass_all_bootoptions(char *param, char *val, int known)
+{
+ return pass_bootoption(param, val, 1);
+}
#ifdef CONFIG_DEBUG_PAGEALLOC
int __read_mostly debug_pagealloc_enabled = 0;
__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)
{
static inline void setup_nr_cpu_ids(void) { }
static inline void smp_prepare_cpus(unsigned int maxcpus) { }
-
-#else
-
-/* 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;
-}
-
-/* Called by boot processor to activate the rest. */
-static void __init smp_init(void)
-{
- unsigned int cpu;
-
- /* 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
/*
* gcc-3.4 accidentally inlines this function, so use noinline.
*/
+static __initdata DECLARE_COMPLETION(kthreadd_done);
+
static noinline void __init_refok rest_init(void)
- __releases(kernel_lock)
{
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();
- unlock_kernel();
+ complete(&kthreadd_done);
/*
* The boot idle thread must execute schedule()
init_idle_bootup_task(current);
preempt_enable_no_resched();
schedule();
- preempt_disable();
/* Call into cpu_idle with preempt disabled */
+ preempt_disable();
cpu_idle();
}
/* Check for early params. */
-static int __init do_early_param(char *param, char *val)
+static int __init do_early_param(char *param, char *val, int known)
{
- struct obs_kernel_param *p;
+ const struct obs_kernel_param *p;
+
+ if (known)
+ return 0;
for (p = __setup_start; p < __setup_end; p++) {
- if ((p->early && strcmp(param, p->str) == 0) ||
+ if ((p->early && parameq(param, p->str)) ||
(strcmp(param, "console") == 0 &&
strcmp(p->str, "earlycon") == 0)
) {
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 struct kernel_param __start___param[], __stop___param[];
+ extern const struct kernel_param __start___param[], __stop___param[];
smp_setup_processor_id();
cgroup_init_early();
local_irq_disable();
- early_boot_irqs_off();
- early_init_irq_lock_class();
+ early_boot_irqs_disabled = true;
/*
* 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);
+ 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();
+ 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);
+ &INIT_PASS_FUNCTION);
+
+ jump_label_init();
+
/*
* 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()
"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() */
timekeeping_init();
time_init();
profile_init();
+ call_function_init();
if (!irqs_disabled())
printk(KERN_CRIT "start_kernel(): bug: interrupts were "
"enabled early\n");
- early_boot_irqs_on();
+ early_boot_irqs_disabled = false;
local_irq_enable();
/* Interrupts are enabled now so all GFP allocations are safe. */
#endif
page_cgroup_init();
enable_debug_pagealloc();
- kmemtrace_init();
- kmemleak_init();
debug_objects_mem_init();
- idr_init_cache();
+ kmemleak_init();
setup_per_cpu_pageset();
numa_policy_init();
if (late_time_init)
buffer_init();
key_init();
security_init();
+ dbg_late_init();
vfs_caches_init(totalram_pages);
signals_init();
/* rootfs populating might need page-writeback */
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)
+static int __init_or_module do_one_initcall_debug(initcall_t fn)
{
- int count = preempt_count();
ktime_t calltime, delta, rettime;
+ unsigned long long duration;
+ int ret;
- 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();
- }
+ 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);
- ret.result = fn();
+ return ret;
+}
- 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);
- }
+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.result && ret.result != -ENODEV && initcall_debug)
- sprintf(msgbuf, "error code %d ", ret.result);
+ if (ret && ret != -ENODEV && initcall_debug)
+ sprintf(msgbuf, "error code %d ", ret);
if (preempt_count() != count) {
strlcat(msgbuf, "preemption imbalance ", sizeof(msgbuf));
printk("initcall %pF returned with %s\n", fn, msgbuf);
}
- return ret.result;
+ return ret;
}
for (fn = __early_initcall_end; fn < __initcall_end; fn++)
do_one_initcall(*fn);
-
- /* Make sure there is no pending stuff from the initcall sequence */
- flush_scheduled_work();
}
/*
*/
static void __init do_basic_setup(void)
{
- init_workqueues();
cpuset_init_smp();
usermodehelper_init();
- init_tmpfs();
+ shmem_init();
driver_init();
init_irq_proc();
do_ctors();
+ usermodehelper_enable();
do_initcalls();
}
do_one_initcall(*fn);
}
-static void run_init_process(char *init_filename)
+static void run_init_process(const char *init_filename)
{
argv_init[0] = init_filename;
kernel_execve(init_filename, argv_init, envp_init);
* 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();
static int __init kernel_init(void * unused)
{
- lock_kernel();
-
+ /*
+ * Wait until kthreadd is all set-up.
+ */
+ wait_for_completion(&kthreadd_done);
/*
* init can allocate pages on any node
*/
* 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();
+ lockup_detector_init();
smp_init();
sched_init_smp();
(void) sys_dup(0);
(void) sys_dup(0);
/*
+ * We need to ensure that the filesystem is ready by this point, wait for
+ * async_populate_rootfs to complete.
+ */
+ populate_rootfs_wait();
+
+ /*
* check if there is an early userspace init. If yes, let it do all
* the work
*/
projects / linux-flexiantxendom0.git / blobdiff