#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/hdreg.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/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/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/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 <linux/sfi.h>
+#include <linux/shmem_fs.h>
+#include <trace/boot.h>
#include <asm/io.h>
#include <asm/bugs.h>
#include <asm/smp.h>
#endif
-/*
- * This is one of the first .c files built. Error out early if we have compiler
- * trouble.
- *
- * Versions of gcc older than that listed below may actually compile and link
- * okay, but the end product can have subtle run time bugs. To avoid associated
- * bogus bug reports, we flatly refuse to compile with a gcc that is known to be
- * too old from the very beginning.
- */
-#if (__GNUC__ < 3) || (__GNUC__ == 3 && __GNUC_MINOR__ < 2)
-#error Sorry, your GCC is too old. It builds incorrect kernels.
-#endif
-
-#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 signals_init(void);
-extern void pidhash_init(void);
-extern void pidmap_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
extern void tc_init(void);
#endif
-enum system_states system_state;
+enum system_states system_state __read_mostly;
EXPORT_SYMBOL(system_state);
/*
extern void time_init(void);
/* Default late time init is NULL. archs can override this later. */
-void (*late_time_init)(void);
+void (*__initdata late_time_init)(void);
extern void softirq_init(void);
/* Untouched command line saved by arch-specific code. */
static char *execute_command;
static char *ramdisk_execute_command;
+#ifdef CONFIG_SMP
/* Setup configured maximum number of CPUs to activate */
-static unsigned int max_cpus = NR_CPUS;
-
-/*
- * 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);
+unsigned int __initdata setup_max_cpus = NR_CPUS;
/*
* Setup routine for controlling SMP activation
* 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)
{
- max_cpus = 0;
- return 1;
+ setup_max_cpus = 0;
+ arch_disable_smp_support();
+
+ return 0;
}
-__setup("nosmp", nosmp);
+early_param("nosmp", nosmp);
static int __init maxcpus(char *str)
{
- get_option(&str, &max_cpus);
- return 1;
+ get_option(&str, &setup_max_cpus);
+ if (setup_max_cpus == 0)
+ arch_disable_smp_support();
+
+ return 0;
}
-__setup("maxcpus=", maxcpus);
+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)
{
static int __init debug_kernel(char *str)
{
- if (*str)
- return 0;
console_loglevel = 10;
- return 1;
+ return 0;
}
static int __init quiet_kernel(char *str)
{
- if (*str)
- return 0;
console_loglevel = 4;
- return 1;
+ return 0;
}
-__setup("debug", debug_kernel);
-__setup("quiet", quiet_kernel);
+early_param("debug", debug_kernel);
+early_param("quiet", quiet_kernel);
static int __init loglevel(char *str)
{
get_option(&str, &console_loglevel);
- return 1;
+ return 0;
}
-__setup("loglevel=", loglevel);
+early_param("loglevel", loglevel);
/*
* Unknown boot options get handed to init, unless they look like
- * failed parameters
+ * unused parameters (modprobe will find them in /proc/cmdline).
*/
static int __init unknown_bootoption(char *param, char *val)
{
if (obsolete_checksetup(param))
return 0;
- /*
- * Preemptive maintenance for "why didn't my mispelled command
- * line work?"
- */
- if (strchr(param, '.') && (!val || strchr(param, '.') < val)) {
- printk(KERN_ERR "Unknown boot option `%s': ignoring\n", param);
+ /* Unused module parameter. */
+ if (strchr(param, '.') && (!val || strchr(param, '.') < val))
return 0;
- }
if (panic_later)
return 0;
return 0;
}
+#ifdef CONFIG_DEBUG_PAGEALLOC
+int __read_mostly debug_pagealloc_enabled = 0;
+#endif
+
static int __init init_setup(char *str)
{
unsigned int i;
#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
-#ifdef __GENERIC_PER_CPU
-unsigned long __per_cpu_offset[NR_CPUS] __read_mostly;
+/* Setup number of possible processor ids */
+int nr_cpu_ids __read_mostly = NR_CPUS;
+EXPORT_SYMBOL(nr_cpu_ids);
-EXPORT_SYMBOL(__per_cpu_offset);
-
-static void __init setup_per_cpu_areas(void)
+/* An arch may set nr_cpu_ids earlier if needed, so this would be redundant */
+static void __init setup_nr_cpu_ids(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;
- }
+ nr_cpu_ids = find_last_bit(cpumask_bits(cpu_possible_mask),NR_CPUS) + 1;
}
-#endif /* !__GENERIC_PER_CPU */
/* 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() >= max_cpus)
+ 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(max_cpus);
+ smp_cpus_done(setup_max_cpus);
}
#endif
* gcc-3.4 accidentally inlines this function, so use noinline.
*/
-static void noinline rest_init(void)
+static noinline void __init_refok rest_init(void)
__releases(kernel_lock)
{
+ int pid;
+
+ rcu_scheduler_starting();
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 one to get things moving:
+ * 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) {
+ 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);
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)
{
/* 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);
+ parse_early_options(tmp_cmdline);
done = 1;
}
{
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);
+ set_cpu_online(cpu, true);
+ set_cpu_present(cpu, true);
+ set_cpu_possible(cpu, true);
}
-void __init __attribute__((weak)) smp_setup_processor_id(void)
+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;
* Need to run as early as possible, to initialize the
* lockdep hash:
*/
- unwind_init();
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();
tick_init();
boot_cpu_init();
page_address_init();
- printk(KERN_NOTICE);
- printk(linux_banner);
+ printk(KERN_NOTICE "%s", linux_banner);
setup_arch(&command_line);
+ mm_init_owner(&init_mm, &init_task);
setup_command_line(command_line);
- unwind_setup();
+ setup_nr_cpu_ids();
setup_per_cpu_areas();
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()
* 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 some links before init_ISA_irqs() */
+ early_irq_init();
init_IRQ();
- pidhash_init();
+ prio_tree_init();
init_timers();
hrtimers_init();
softirq_init();
time_init();
profile_init();
if (!irqs_disabled())
- printk("start_kernel(): bug: interrupts were enabled early\n");
+ 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
#ifdef CONFIG_BLK_DEV_INITRD
if (initrd_start && !initrd_below_start_ok &&
- initrd_start < min_low_pfn << PAGE_SHIFT) {
+ page_to_pfn(virt_to_page((void *)initrd_start)) < min_low_pfn) {
printk(KERN_CRIT "initrd overwritten (0x%08lx < 0x%08lx) - "
- "disabling it.\n",initrd_start,min_low_pfn << PAGE_SHIFT);
+ "disabling it.\n",
+ page_to_pfn(virt_to_page((void *)initrd_start)),
+ min_low_pfn);
initrd_start = 0;
}
#endif
- vfs_caches_init_early();
- cpuset_init_early();
- mem_init();
- kmem_cache_init();
+ 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();
+ sched_clock_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
- fork_init(num_physpages);
+ thread_info_cache_init();
+ cred_init();
+ fork_init(totalram_pages);
proc_caches_init();
buffer_init();
- unnamed_dev_init();
key_init();
security_init();
- vfs_caches_init(num_physpages);
+ vfs_caches_init(totalram_pages);
radix_tree_init();
signals_init();
/* rootfs populating might need page-writeback */
#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();
}
-static int __initdata initcall_debug;
-
-static int __init initcall_debug_setup(char *str)
+/* Call all constructor functions linked into the kernel. */
+static void __init do_ctors(void)
{
- initcall_debug = 1;
- return 1;
+#ifdef CONFIG_CONSTRUCTORS
+ ctor_fn_t *call = (ctor_fn_t *) __ctors_start;
+
+ for (; call < (ctor_fn_t *) __ctors_end; call++)
+ (*call)();
+#endif
}
-__setup("initcall_debug", initcall_debug_setup);
-extern initcall_t __initcall_start[], __initcall_end[];
+int initcall_debug;
+core_param(initcall_debug, initcall_debug, bool, 0644);
-static void __init do_initcalls(void)
+static char msgbuf[64];
+static struct boot_trace_call call;
+static struct boot_trace_ret ret;
+
+int do_one_initcall(initcall_t fn)
{
- initcall_t *call;
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();
+ }
- for (call = __initcall_start; call < __initcall_end; call++) {
- ktime_t t0, t1, delta;
- char *msg = NULL;
- char msgbuf[40];
- int result;
-
- if (initcall_debug) {
- printk("Calling initcall 0x%p", *call);
- print_fn_descriptor_symbol(": %s()",
- (unsigned long) *call);
- printk("\n");
- t0 = ktime_get();
- }
-
- result = (*call)();
+ ret.result = fn();
- if (initcall_debug) {
- t1 = ktime_get();
- delta = ktime_sub(t1, t0);
+ 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);
+ }
- printk("initcall 0x%p", *call);
- print_fn_descriptor_symbol(": %s()",
- (unsigned long) *call);
- printk(" returned %d.\n", result);
+ msgbuf[0] = 0;
- printk("initcall 0x%p ran for %Ld msecs: ",
- *call, (unsigned long long)delta.tv64 >> 20);
- print_fn_descriptor_symbol("%s()\n",
- (unsigned long) *call);
- }
+ if (ret.result && ret.result != -ENODEV && initcall_debug)
+ sprintf(msgbuf, "error code %d ", ret.result);
- if (result && result != -ENODEV && initcall_debug) {
- sprintf(msgbuf, "error code %d", result);
- msg = msgbuf;
- }
- if (preempt_count() != count) {
- msg = "preemption imbalance";
- preempt_count() = count;
- }
- if (irqs_disabled()) {
- msg = "disabled interrupts";
- local_irq_enable();
- }
- if (msg) {
- printk(KERN_WARNING "initcall at 0x%p", *call);
- print_fn_descriptor_symbol(": %s()",
- (unsigned long) *call);
- printk(": returned with %s\n", msg);
- }
+ 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();
}
*/
static void __init do_basic_setup(void)
{
- /* drivers will send hotplug events */
init_workqueues();
+ cpuset_init_smp();
usermodehelper_init();
+ init_tmpfs();
driver_init();
init_irq_proc();
+ do_ctors();
do_initcalls();
}
static void __init do_pre_smp_initcalls(void)
{
- extern int spawn_ksoftirqd(void);
-#ifdef CONFIG_SMP
- extern int migration_init(void);
+ initcall_t *call;
- migration_init();
-#endif
- spawn_ksoftirqd();
- spawn_softlockup_task();
+ for (call = __initcall_start; call < __early_initcall_end; call++)
+ do_one_initcall(*call);
}
static void run_init_process(char *init_filename)
/* 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)
+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();
(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",
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(current, CPU_MASK_ALL);
+ set_cpus_allowed_ptr(current, cpu_all_mask);
/*
* Tell the world that we're going to be the grim
* reaper of innocent orphaned children.
cad_pid = task_pid(current);
- smp_prepare_cpus(max_cpus);
+ smp_prepare_cpus(setup_max_cpus);
do_pre_smp_initcalls();
+ start_boot_trace();
smp_init();
sched_init_smp();
- cpuset_init_smp();
-
do_basic_setup();
/*
* we're essentially up and running. Get rid of the
* initmem segments and start the user-mode stuff..
*/
+
init_post();
return 0;
}