* 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>
+ * Simplified starting of init: Michael A. Griffith <grif@acm.org>
*/
#define DEBUG /* Enable initcall_debug */
#include <linux/mempolicy.h>
#include <linux/key.h>
#include <linux/buffer_head.h>
-#include <linux/page_cgroup.h>
+#include <linux/page_ext.h>
#include <linux/debug_locks.h>
#include <linux/debugobjects.h>
#include <linux/lockdep.h>
#include <linux/ptrace.h>
#include <linux/blkdev.h>
#include <linux/elevator.h>
+#include <linux/sched_clock.h>
+#include <linux/context_tracking.h>
+#include <linux/random.h>
+#include <linux/list.h>
+#include <linux/integrity.h>
+#include <linux/proc_ns.h>
+#include <linux/io.h>
#include <asm/io.h>
#include <asm/bugs.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 fork_init(void);
extern void radix_tree_init(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'
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];
char *saved_command_line;
/* Command line for parameter parsing */
static char *static_command_line;
+/* Command line for per-initcall parameter parsing */
+static char *initcall_command_line;
static char *execute_command;
static char *ramdisk_execute_command;
+/*
+ * Used to generate warnings if static_key manipulation functions are used
+ * before jump_label_init is called.
+ */
+bool static_key_initialized __read_mostly;
+EXPORT_SYMBOL_GPL(static_key_initialized);
+
/*
* 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
+ * For ex. kdump situation where previous kernel has crashed, BIOS has been
* skipped and devices will be in unknown state.
*/
unsigned int reset_devices;
__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 *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[];
* 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;
+ console_loglevel = CONSOLE_LOGLEVEL_DEBUG;
return 0;
}
static int __init quiet_kernel(char *str)
{
- console_loglevel = 4;
+ console_loglevel = CONSOLE_LOGLEVEL_QUIET;
return 0;
}
early_param("loglevel", loglevel);
/* Change NUL term back to "=", to make "param" the whole string. */
-static int __init repair_env_string(char *param, char *val, const char *unused)
+static int __init repair_env_string(char *param, char *val,
+ const char *unused, void *arg)
{
if (val) {
/* param=val or param="val"? */
return 0;
}
+/* Anything after -- gets handed straight to init. */
+static int __init set_init_arg(char *param, char *val,
+ const char *unused, void *arg)
+{
+ unsigned int i;
+
+ if (panic_later)
+ return 0;
+
+ repair_env_string(param, val, unused, NULL);
+
+ for (i = 0; argv_init[i]; i++) {
+ if (i == MAX_INIT_ARGS) {
+ panic_later = "init";
+ panic_param = param;
+ return 0;
+ }
+ }
+ argv_init[i] = param;
+ return 0;
+}
+
/*
* 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, const char *unused)
+static int __init unknown_bootoption(char *param, char *val,
+ const char *unused, void *arg)
{
- repair_env_string(param, val, unused);
+ repair_env_string(param, val, unused, NULL);
/* Handle obsolete-style parameters */
if (obsolete_checksetup(param))
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_later = "env";
panic_param = param;
}
if (!strncmp(param, envp_init[i], val - param))
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_later = "init";
panic_param = param;
}
}
#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
*/
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);
+ saved_command_line =
+ memblock_virt_alloc(strlen(boot_command_line) + 1, 0);
+ initcall_command_line =
+ memblock_virt_alloc(strlen(boot_command_line) + 1, 0);
+ static_command_line = memblock_virt_alloc(strlen(command_line) + 1, 0);
+ strcpy(saved_command_line, boot_command_line);
+ strcpy(static_command_line, command_line);
}
/*
int pid;
rcu_scheduler_starting();
+ smpboot_thread_init();
/*
* 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);
+ kernel_thread(kernel_init, NULL, CLONE_FS);
numa_default_policy();
pid = kernel_thread(kthreadd, NULL, CLONE_FS | CLONE_FILES);
rcu_read_lock();
}
/* Check for early params. */
-static int __init do_early_param(char *param, char *val, const char *unused)
+static int __init do_early_param(char *param, char *val,
+ const char *unused, void *arg)
{
const struct obs_kernel_param *p;
void __init parse_early_options(char *cmdline)
{
- parse_args("early options", cmdline, NULL, 0, 0, 0, do_early_param);
+ parse_args("early options", cmdline, NULL, 0, 0, 0, NULL,
+ 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];
+ static int done __initdata;
+ static char tmp_cmdline[COMMAND_LINE_SIZE] __initdata;
if (done)
return;
static void __init mm_init(void)
{
/*
- * page_cgroup requires contiguous pages,
+ * page_ext requires contiguous pages,
* bigger than MAX_ORDER unless SPARSEMEM.
*/
- page_cgroup_init_flatmem();
+ page_ext_init_flatmem();
mem_init();
kmem_cache_init();
percpu_init_late();
- pgtable_cache_init();
+ pgtable_init();
vmalloc_init();
+ ioremap_huge_init();
}
-asmlinkage void __init start_kernel(void)
+asmlinkage __visible void __init start_kernel(void)
{
- char * command_line;
- extern const struct kernel_param __start___param[], __stop___param[];
+ char *command_line;
+ char *after_dashes;
/*
* Need to run as early as possible, to initialize the
* lockdep hash:
*/
lockdep_init();
+ set_task_stack_end_magic(&init_task);
smp_setup_processor_id();
debug_objects_early_init();
page_address_init();
pr_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();
pr_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,
- -1, -1, &unknown_bootoption);
+ after_dashes = parse_args("Booting kernel",
+ static_command_line, __start___param,
+ __stop___param - __start___param,
+ -1, -1, NULL, &unknown_bootoption);
+ if (!IS_ERR_OR_NULL(after_dashes))
+ parse_args("Setting init args", after_dashes, NULL, 0, -1, -1,
+ NULL, set_init_arg);
jump_label_init();
* fragile until we cpu_idle() for the first time.
*/
preempt_disable();
- if (WARN(!irqs_disabled(), "Interrupts were enabled *very* early, fixing it\n"))
+ if (WARN(!irqs_disabled(),
+ "Interrupts were enabled *very* early, fixing it\n"))
local_irq_disable();
idr_init_cache();
- perf_event_init();
rcu_init();
- tick_nohz_init();
+
+ /* trace_printk() and trace points may be used after this */
+ trace_init();
+
+ context_tracking_init();
radix_tree_init();
/* init some links before init_ISA_irqs() */
early_irq_init();
init_IRQ();
tick_init();
+ rcu_init_nohz();
init_timers();
hrtimers_init();
softirq_init();
timekeeping_init();
time_init();
+ sched_clock_postinit();
+ perf_event_init();
profile_init();
call_function_init();
WARN(!irqs_disabled(), "Interrupts were enabled early\n");
*/
console_init();
if (panic_later)
- panic(panic_later, panic_param);
+ panic("Too many boot %s vars at `%s'", panic_later,
+ panic_param);
lockdep_info();
initrd_start = 0;
}
#endif
- page_cgroup_init();
+ page_ext_init();
debug_objects_mem_init();
kmemleak_init();
setup_per_cpu_pageset();
calibrate_delay();
pidmap_init();
anon_vma_init();
+ acpi_early_init();
#ifdef CONFIG_X86
if (efi_enabled(EFI_RUNTIME_SERVICES))
efi_enter_virtual_mode();
+#endif
+#ifdef CONFIG_X86_ESPFIX64
+ /* Should be run before the first non-init thread is created */
+ init_espfix_bsp();
#endif
thread_info_cache_init();
cred_init();
- fork_init(totalram_pages);
+ fork_init();
proc_caches_init();
buffer_init();
key_init();
security_init();
dbg_late_init();
- vfs_caches_init(totalram_pages);
+ vfs_caches_init();
signals_init();
/* rootfs populating might need page-writeback */
page_writeback_init();
-#ifdef CONFIG_PROC_FS
proc_root_init();
-#endif
- cgroup_init();
+ nsfs_init();
cpuset_init();
+ cgroup_init();
taskstats_init_early();
delayacct_init();
check_bugs();
- acpi_early_init(); /* before LAPIC and SMP init */
+ acpi_subsystem_init();
sfi_init_late();
if (efi_enabled(EFI_RUNTIME_SERVICES)) {
bool initcall_debug;
core_param(initcall_debug, initcall_debug, bool, 0644);
-static char msgbuf[64];
+#ifdef CONFIG_KALLSYMS
+struct blacklist_entry {
+ struct list_head next;
+ char *buf;
+};
+
+static __initdata_or_module LIST_HEAD(blacklisted_initcalls);
+
+static int __init initcall_blacklist(char *str)
+{
+ char *str_entry;
+ struct blacklist_entry *entry;
+
+ /* str argument is a comma-separated list of functions */
+ do {
+ str_entry = strsep(&str, ",");
+ if (str_entry) {
+ pr_debug("blacklisting initcall %s\n", str_entry);
+ entry = alloc_bootmem(sizeof(*entry));
+ entry->buf = alloc_bootmem(strlen(str_entry) + 1);
+ strcpy(entry->buf, str_entry);
+ list_add(&entry->next, &blacklisted_initcalls);
+ }
+ } while (str_entry);
+
+ return 0;
+}
+
+static bool __init_or_module initcall_blacklisted(initcall_t fn)
+{
+ struct list_head *tmp;
+ struct blacklist_entry *entry;
+ char *fn_name;
+
+ fn_name = kasprintf(GFP_KERNEL, "%pf", fn);
+ if (!fn_name)
+ return false;
+
+ list_for_each(tmp, &blacklisted_initcalls) {
+ entry = list_entry(tmp, struct blacklist_entry, next);
+ if (!strcmp(fn_name, entry->buf)) {
+ pr_debug("initcall %s blacklisted\n", fn_name);
+ kfree(fn_name);
+ return true;
+ }
+ }
+
+ kfree(fn_name);
+ return false;
+}
+#else
+static int __init initcall_blacklist(char *str)
+{
+ pr_warn("initcall_blacklist requires CONFIG_KALLSYMS\n");
+ return 0;
+}
+
+static bool __init_or_module initcall_blacklisted(initcall_t fn)
+{
+ return false;
+}
+#endif
+__setup("initcall_blacklist=", initcall_blacklist);
static int __init_or_module do_one_initcall_debug(initcall_t fn)
{
unsigned long long duration;
int ret;
- pr_debug("calling %pF @ %i\n", fn, task_pid_nr(current));
+ 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;
- pr_debug("initcall %pF returned %d after %lld usecs\n",
+ printk(KERN_DEBUG "initcall %pF returned %d after %lld usecs\n",
fn, ret, duration);
return ret;
{
int count = preempt_count();
int ret;
+ char msgbuf[64];
+
+ if (initcall_blacklisted(fn))
+ return -EPERM;
if (initcall_debug)
ret = do_one_initcall_debug(fn);
if (preempt_count() != count) {
sprintf(msgbuf, "preemption imbalance ");
- preempt_count() = count;
+ preempt_count_set(count);
}
if (irqs_disabled()) {
strlcat(msgbuf, "disabled interrupts ", sizeof(msgbuf));
static void __init do_initcall_level(int level)
{
- extern const struct kernel_param __start___param[], __stop___param[];
initcall_t *fn;
- strcpy(static_command_line, saved_command_line);
+ strcpy(initcall_command_line, saved_command_line);
parse_args(initcall_level_names[level],
- static_command_line, __start___param,
+ initcall_command_line, __start___param,
__stop___param - __start___param,
level, level,
- &repair_env_string);
+ NULL, &repair_env_string);
for (fn = initcall_levels[level]; fn < initcall_levels[level+1]; fn++)
do_one_initcall(*fn);
static void __init do_basic_setup(void)
{
cpuset_init_smp();
- usermodehelper_init();
shmem_init();
driver_init();
init_irq_proc();
do_ctors();
usermodehelper_enable();
do_initcalls();
+ random_int_secret_init();
}
static void __init do_pre_smp_initcalls(void)
static int run_init_process(const char *init_filename)
{
argv_init[0] = init_filename;
- return do_execve(init_filename,
+ return do_execve(getname_kernel(init_filename),
(const char __user *const __user *)argv_init,
(const char __user *const __user *)envp_init);
}
+static int try_to_run_init_process(const char *init_filename)
+{
+ int ret;
+
+ ret = run_init_process(init_filename);
+
+ if (ret && ret != -ENOENT) {
+ pr_err("Starting init: %s exists but couldn't execute it (error %d)\n",
+ init_filename, ret);
+ }
+
+ return ret;
+}
+
static noinline void __init kernel_init_freeable(void);
+#ifdef CONFIG_DEBUG_RODATA
+static bool rodata_enabled = true;
+static int __init set_debug_rodata(char *str)
+{
+ return strtobool(str, &rodata_enabled);
+}
+__setup("rodata=", set_debug_rodata);
+
+static void mark_readonly(void)
+{
+ if (rodata_enabled)
+ mark_rodata_ro();
+ else
+ pr_info("Kernel memory protection disabled.\n");
+}
+#else
+static inline void mark_readonly(void)
+{
+ pr_warn("This architecture does not have kernel memory protection.\n");
+}
+#endif
+
static int __ref kernel_init(void *unused)
{
+ int ret;
+
kernel_init_freeable();
/* need to finish all async __init code before freeing the memory */
async_synchronize_full();
free_initmem();
- mark_rodata_ro();
+ mark_readonly();
system_state = SYSTEM_RUNNING;
numa_default_policy();
flush_delayed_fput();
if (ramdisk_execute_command) {
- if (!run_init_process(ramdisk_execute_command))
+ ret = run_init_process(ramdisk_execute_command);
+ if (!ret)
return 0;
- pr_err("Failed to execute %s\n", ramdisk_execute_command);
+ pr_err("Failed to execute %s (error %d)\n",
+ ramdisk_execute_command, ret);
}
/*
* trying to recover a really broken machine.
*/
if (execute_command) {
- if (!run_init_process(execute_command))
+ ret = run_init_process(execute_command);
+ if (!ret)
return 0;
- pr_err("Failed to execute %s. Attempting defaults...\n",
- execute_command);
+ panic("Requested init %s failed (error %d).",
+ execute_command, ret);
}
- if (!run_init_process("/sbin/init") ||
- !run_init_process("/etc/init") ||
- !run_init_process("/bin/init") ||
- !run_init_process("/bin/sh"))
+ if (!try_to_run_init_process("/sbin/init") ||
+ !try_to_run_init_process("/etc/init") ||
+ !try_to_run_init_process("/bin/init") ||
+ !try_to_run_init_process("/bin/sh"))
return 0;
- panic("No init found. Try passing init= option to kernel. "
+ panic("No working init found. Try passing init= option to kernel. "
"See Linux Documentation/init.txt for guidance.");
}
smp_init();
sched_init_smp();
+ page_alloc_init_late();
+
do_basic_setup();
/* Open the /dev/console on the rootfs, this should never fail */
* 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..
+ *
+ * rootfs is available now, try loading the public keys
+ * and default modules
*/
- /* rootfs is available now, try loading default modules */
+ integrity_load_keys();
load_default_modules();
}