2
0
mirror of https://github.com/edk2-porting/linux-next.git synced 2024-12-25 13:43:55 +08:00
linux-next/init/main.c
Vlastimil Babka 3db978d480 kernel/sysctl: support setting sysctl parameters from kernel command line
Patch series "support setting sysctl parameters from kernel command line", v3.

This series adds support for something that seems like many people
always wanted but nobody added it yet, so here's the ability to set
sysctl parameters via kernel command line options in the form of
sysctl.vm.something=1

The important part is Patch 1.  The second, not so important part is an
attempt to clean up legacy one-off parameters that do the same thing as
a sysctl.  I don't want to remove them completely for compatibility
reasons, but with generic sysctl support the idea is to remove the
one-off param handlers and treat the parameters as aliases for the
sysctl variants.

I have identified several parameters that mention sysctl counterparts in
Documentation/admin-guide/kernel-parameters.txt but there might be more.
The conversion also has varying level of success:

 - numa_zonelist_order is converted in Patch 2 together with adding the
   necessary infrastructure. It's easy as it doesn't really do anything
   but warn on deprecated value these days.

 - hung_task_panic is converted in Patch 3, but there's a downside that
   now it only accepts 0 and 1, while previously it was any integer
   value

 - nmi_watchdog maps to two sysctls nmi_watchdog and hardlockup_panic,
   so there's no straighforward conversion possible

 - traceoff_on_warning is a flag without value and it would be required
   to handle that somehow in the conversion infractructure, which seems
   pointless for a single flag

This patch (of 5):

A recently proposed patch to add vm_swappiness command line parameter in
addition to existing sysctl [1] made me wonder why we don't have a
general support for passing sysctl parameters via command line.

Googling found only somebody else wondering the same [2], but I haven't
found any prior discussion with reasons why not to do this.

Settings the vm_swappiness issue aside (the underlying issue might be
solved in a different way), quick search of kernel-parameters.txt shows
there are already some that exist as both sysctl and kernel parameter -
hung_task_panic, nmi_watchdog, numa_zonelist_order, traceoff_on_warning.

A general mechanism would remove the need to add more of those one-offs
and might be handy in situations where configuration by e.g.
/etc/sysctl.d/ is impractical.

Hence, this patch adds a new parse_args() pass that looks for parameters
prefixed by 'sysctl.' and tries to interpret them as writes to the
corresponding sys/ files using an temporary in-kernel procfs mount.
This mechanism was suggested by Eric W.  Biederman [3], as it handles
all dynamically registered sysctl tables, even though we don't handle
modular sysctls.  Errors due to e.g.  invalid parameter name or value
are reported in the kernel log.

The processing is hooked right before the init process is loaded, as
some handlers might be more complicated than simple setters and might
need some subsystems to be initialized.  At the moment the init process
can be started and eventually execute a process writing to /proc/sys/
then it should be also fine to do that from the kernel.

Sysctls registered later on module load time are not set by this
mechanism - it's expected that in such scenarios, setting sysctl values
from userspace is practical enough.

[1] https://lore.kernel.org/r/BL0PR02MB560167492CA4094C91589930E9FC0@BL0PR02MB5601.namprd02.prod.outlook.com/
[2] https://unix.stackexchange.com/questions/558802/how-to-set-sysctl-using-kernel-command-line-parameter
[3] https://lore.kernel.org/r/87bloj2skm.fsf@x220.int.ebiederm.org/

Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Luis Chamberlain <mcgrof@kernel.org>
Reviewed-by: Masami Hiramatsu <mhiramat@kernel.org>
Acked-by: Kees Cook <keescook@chromium.org>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Iurii Zaikin <yzaikin@google.com>
Cc: Ivan Teterevkov <ivan.teterevkov@nutanix.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: "Eric W . Biederman" <ebiederm@xmission.com>
Cc: "Guilherme G . Piccoli" <gpiccoli@canonical.com>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Christian Brauner <christian.brauner@ubuntu.com>
Link: http://lkml.kernel.org/r/20200427180433.7029-1-vbabka@suse.cz
Link: http://lkml.kernel.org/r/20200427180433.7029-2-vbabka@suse.cz
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-06-08 11:05:56 -07:00

1532 lines
37 KiB
C

// SPDX-License-Identifier: GPL-2.0-only
/*
* 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>
*/
#define DEBUG /* Enable initcall_debug */
#include <linux/types.h>
#include <linux/extable.h>
#include <linux/module.h>
#include <linux/proc_fs.h>
#include <linux/binfmts.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/memblock.h>
#include <linux/acpi.h>
#include <linux/bootconfig.h>
#include <linux/console.h>
#include <linux/nmi.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/sched/isolation.h>
#include <linux/interrupt.h>
#include <linux/taskstats_kern.h>
#include <linux/delayacct.h>
#include <linux/unistd.h>
#include <linux/utsname.h>
#include <linux/rmap.h>
#include <linux/mempolicy.h>
#include <linux/key.h>
#include <linux/buffer_head.h>
#include <linux/page_ext.h>
#include <linux/debug_locks.h>
#include <linux/debugobjects.h>
#include <linux/lockdep.h>
#include <linux/kmemleak.h>
#include <linux/padata.h>
#include <linux/pid_namespace.h>
#include <linux/device/driver.h>
#include <linux/kthread.h>
#include <linux/sched.h>
#include <linux/sched/init.h>
#include <linux/signal.h>
#include <linux/idr.h>
#include <linux/kgdb.h>
#include <linux/ftrace.h>
#include <linux/async.h>
#include <linux/sfi.h>
#include <linux/shmem_fs.h>
#include <linux/slab.h>
#include <linux/perf_event.h>
#include <linux/ptrace.h>
#include <linux/pti.h>
#include <linux/blkdev.h>
#include <linux/elevator.h>
#include <linux/sched/clock.h>
#include <linux/sched/task.h>
#include <linux/sched/task_stack.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 <linux/cache.h>
#include <linux/rodata_test.h>
#include <linux/jump_label.h>
#include <linux/mem_encrypt.h>
#include <asm/io.h>
#include <asm/bugs.h>
#include <asm/setup.h>
#include <asm/sections.h>
#include <asm/cacheflush.h>
#define CREATE_TRACE_POINTS
#include <trace/events/initcall.h>
static int kernel_init(void *);
extern void init_IRQ(void);
extern void radix_tree_init(void);
/*
* 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);
/* 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;
/* Untouched extra command line */
static char *extra_command_line;
/* Extra init arguments */
static char *extra_init_args;
#ifdef CONFIG_BOOT_CONFIG
/* Is bootconfig on command line? */
static bool bootconfig_found;
static bool initargs_found;
#else
# define bootconfig_found false
# define initargs_found false
#endif
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 situation 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 bool __init obsolete_checksetup(char *line)
{
const struct obs_kernel_param *p;
bool had_early_param = false;
p = __setup_start;
do {
int n = strlen(p->str);
if (parameqn(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 = true;
} else if (!p->setup_func) {
pr_warn("Parameter %s is obsolete, ignored\n",
p->str);
return true;
} else if (p->setup_func(line + n))
return true;
}
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 = CONSOLE_LOGLEVEL_DEBUG;
return 0;
}
static int __init quiet_kernel(char *str)
{
console_loglevel = CONSOLE_LOGLEVEL_QUIET;
return 0;
}
early_param("debug", debug_kernel);
early_param("quiet", quiet_kernel);
static int __init loglevel(char *str)
{
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);
#ifdef CONFIG_BLK_DEV_INITRD
static void * __init get_boot_config_from_initrd(u32 *_size, u32 *_csum)
{
u32 size, csum;
char *data;
u32 *hdr;
if (!initrd_end)
return NULL;
data = (char *)initrd_end - BOOTCONFIG_MAGIC_LEN;
if (memcmp(data, BOOTCONFIG_MAGIC, BOOTCONFIG_MAGIC_LEN))
return NULL;
hdr = (u32 *)(data - 8);
size = hdr[0];
csum = hdr[1];
data = ((void *)hdr) - size;
if ((unsigned long)data < initrd_start) {
pr_err("bootconfig size %d is greater than initrd size %ld\n",
size, initrd_end - initrd_start);
return NULL;
}
/* Remove bootconfig from initramfs/initrd */
initrd_end = (unsigned long)data;
if (_size)
*_size = size;
if (_csum)
*_csum = csum;
return data;
}
#else
static void * __init get_boot_config_from_initrd(u32 *_size, u32 *_csum)
{
return NULL;
}
#endif
#ifdef CONFIG_BOOT_CONFIG
char xbc_namebuf[XBC_KEYLEN_MAX] __initdata;
#define rest(dst, end) ((end) > (dst) ? (end) - (dst) : 0)
static int __init xbc_snprint_cmdline(char *buf, size_t size,
struct xbc_node *root)
{
struct xbc_node *knode, *vnode;
char *end = buf + size;
const char *val;
int ret;
xbc_node_for_each_key_value(root, knode, val) {
ret = xbc_node_compose_key_after(root, knode,
xbc_namebuf, XBC_KEYLEN_MAX);
if (ret < 0)
return ret;
vnode = xbc_node_get_child(knode);
if (!vnode) {
ret = snprintf(buf, rest(buf, end), "%s ", xbc_namebuf);
if (ret < 0)
return ret;
buf += ret;
continue;
}
xbc_array_for_each_value(vnode, val) {
ret = snprintf(buf, rest(buf, end), "%s=\"%s\" ",
xbc_namebuf, val);
if (ret < 0)
return ret;
buf += ret;
}
}
return buf - (end - size);
}
#undef rest
/* Make an extra command line under given key word */
static char * __init xbc_make_cmdline(const char *key)
{
struct xbc_node *root;
char *new_cmdline;
int ret, len = 0;
root = xbc_find_node(key);
if (!root)
return NULL;
/* Count required buffer size */
len = xbc_snprint_cmdline(NULL, 0, root);
if (len <= 0)
return NULL;
new_cmdline = memblock_alloc(len + 1, SMP_CACHE_BYTES);
if (!new_cmdline) {
pr_err("Failed to allocate memory for extra kernel cmdline.\n");
return NULL;
}
ret = xbc_snprint_cmdline(new_cmdline, len + 1, root);
if (ret < 0 || ret > len) {
pr_err("Failed to print extra kernel cmdline.\n");
return NULL;
}
return new_cmdline;
}
static u32 boot_config_checksum(unsigned char *p, u32 size)
{
u32 ret = 0;
while (size--)
ret += *p++;
return ret;
}
static int __init bootconfig_params(char *param, char *val,
const char *unused, void *arg)
{
if (strcmp(param, "bootconfig") == 0) {
bootconfig_found = true;
} else if (strcmp(param, "--") == 0) {
initargs_found = true;
}
return 0;
}
static void __init setup_boot_config(const char *cmdline)
{
static char tmp_cmdline[COMMAND_LINE_SIZE] __initdata;
const char *msg;
int pos;
u32 size, csum;
char *data, *copy;
int ret;
/* Cut out the bootconfig data even if we have no bootconfig option */
data = get_boot_config_from_initrd(&size, &csum);
strlcpy(tmp_cmdline, boot_command_line, COMMAND_LINE_SIZE);
parse_args("bootconfig", tmp_cmdline, NULL, 0, 0, 0, NULL,
bootconfig_params);
if (!bootconfig_found)
return;
if (!data) {
pr_err("'bootconfig' found on command line, but no bootconfig found\n");
return;
}
if (size >= XBC_DATA_MAX) {
pr_err("bootconfig size %d greater than max size %d\n",
size, XBC_DATA_MAX);
return;
}
if (boot_config_checksum((unsigned char *)data, size) != csum) {
pr_err("bootconfig checksum failed\n");
return;
}
copy = memblock_alloc(size + 1, SMP_CACHE_BYTES);
if (!copy) {
pr_err("Failed to allocate memory for bootconfig\n");
return;
}
memcpy(copy, data, size);
copy[size] = '\0';
ret = xbc_init(copy, &msg, &pos);
if (ret < 0) {
if (pos < 0)
pr_err("Failed to init bootconfig: %s.\n", msg);
else
pr_err("Failed to parse bootconfig: %s at %d.\n",
msg, pos);
} else {
pr_info("Load bootconfig: %d bytes %d nodes\n", size, ret);
/* keys starting with "kernel." are passed via cmdline */
extra_command_line = xbc_make_cmdline("kernel");
/* Also, "init." keys are init arguments */
extra_init_args = xbc_make_cmdline("init");
}
return;
}
#else
static void __init setup_boot_config(const char *cmdline)
{
/* Remove bootconfig data from initrd */
get_boot_config_from_initrd(NULL, NULL);
}
static int __init warn_bootconfig(char *str)
{
pr_warn("WARNING: 'bootconfig' found on the kernel command line but CONFIG_BOOTCONFIG is not set.\n");
return 0;
}
early_param("bootconfig", warn_bootconfig);
#endif
/* Change NUL term back to "=", to make "param" the whole string. */
static void __init repair_env_string(char *param, char *val)
{
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);
} else
BUG();
}
}
/* 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);
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, void *arg)
{
size_t len = strlen(param);
repair_env_string(param, val);
/* Handle obsolete-style parameters */
if (obsolete_checksetup(param))
return 0;
/* Unused module parameter. */
if (strnchr(param, len, '.'))
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 = "env";
panic_param = param;
}
if (!strncmp(param, envp_init[i], len+1))
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 = "init";
panic_param = param;
}
}
argv_init[i] = param;
}
return 0;
}
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;
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)
{
size_t len, xlen = 0, ilen = 0;
if (extra_command_line)
xlen = strlen(extra_command_line);
if (extra_init_args)
ilen = strlen(extra_init_args) + 4; /* for " -- " */
len = xlen + strlen(boot_command_line) + 1;
saved_command_line = memblock_alloc(len + ilen, SMP_CACHE_BYTES);
if (!saved_command_line)
panic("%s: Failed to allocate %zu bytes\n", __func__, len + ilen);
static_command_line = memblock_alloc(len, SMP_CACHE_BYTES);
if (!static_command_line)
panic("%s: Failed to allocate %zu bytes\n", __func__, len);
if (xlen) {
/*
* We have to put extra_command_line before boot command
* lines because there could be dashes (separator of init
* command line) in the command lines.
*/
strcpy(saved_command_line, extra_command_line);
strcpy(static_command_line, extra_command_line);
}
strcpy(saved_command_line + xlen, boot_command_line);
strcpy(static_command_line + xlen, command_line);
if (ilen) {
/*
* Append supplemental init boot args to saved_command_line
* so that user can check what command line options passed
* to init.
*/
len = strlen(saved_command_line);
if (initargs_found) {
saved_command_line[len++] = ' ';
} else {
strcpy(saved_command_line + len, " -- ");
len += 4;
}
strcpy(saved_command_line + len, extra_init_args);
}
}
/*
* 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);
noinline void __ref rest_init(void)
{
struct task_struct *tsk;
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.
*/
pid = kernel_thread(kernel_init, NULL, CLONE_FS);
/*
* Pin init on the boot CPU. Task migration is not properly working
* until sched_init_smp() has been run. It will set the allowed
* CPUs for init to the non isolated CPUs.
*/
rcu_read_lock();
tsk = find_task_by_pid_ns(pid, &init_pid_ns);
set_cpus_allowed_ptr(tsk, cpumask_of(smp_processor_id()));
rcu_read_unlock();
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();
/*
* Enable might_sleep() and smp_processor_id() checks.
* They cannot be enabled earlier because with CONFIG_PREEMPTION=y
* kernel_thread() would trigger might_sleep() splats. With
* CONFIG_PREEMPT_VOLUNTARY=y the init task might have scheduled
* already, but it's stuck on the kthreadd_done completion.
*/
system_state = SYSTEM_SCHEDULING;
complete(&kthreadd_done);
/*
* The boot idle thread must execute schedule()
* at least once to get things moving:
*/
schedule_preempt_disabled();
/* Call into cpu_idle with preempt disabled */
cpu_startup_entry(CPUHP_ONLINE);
}
/* Check for early params. */
static int __init do_early_param(char *param, char *val,
const char *unused, void *arg)
{
const struct obs_kernel_param *p;
for (p = __setup_start; p < __setup_end; p++) {
if ((p->early && parameq(param, p->str)) ||
(strcmp(param, "console") == 0 &&
strcmp(p->str, "earlycon") == 0)
) {
if (p->setup_func(val) != 0)
pr_warn("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, 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 int done __initdata;
static char tmp_cmdline[COMMAND_LINE_SIZE] __initdata;
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;
}
void __init __weak arch_post_acpi_subsys_init(void) { }
void __init __weak smp_setup_processor_id(void)
{
}
# if THREAD_SIZE >= PAGE_SIZE
void __init __weak thread_stack_cache_init(void)
{
}
#endif
void __init __weak mem_encrypt_init(void) { }
void __init __weak poking_init(void) { }
void __init __weak pgtable_cache_init(void) { }
bool initcall_debug;
core_param(initcall_debug, initcall_debug, bool, 0644);
#ifdef TRACEPOINTS_ENABLED
static void __init initcall_debug_enable(void);
#else
static inline void initcall_debug_enable(void)
{
}
#endif
/* Report memory auto-initialization states for this boot. */
static void __init report_meminit(void)
{
const char *stack;
if (IS_ENABLED(CONFIG_INIT_STACK_ALL))
stack = "all";
else if (IS_ENABLED(CONFIG_GCC_PLUGIN_STRUCTLEAK_BYREF_ALL))
stack = "byref_all";
else if (IS_ENABLED(CONFIG_GCC_PLUGIN_STRUCTLEAK_BYREF))
stack = "byref";
else if (IS_ENABLED(CONFIG_GCC_PLUGIN_STRUCTLEAK_USER))
stack = "__user";
else
stack = "off";
pr_info("mem auto-init: stack:%s, heap alloc:%s, heap free:%s\n",
stack, want_init_on_alloc(GFP_KERNEL) ? "on" : "off",
want_init_on_free() ? "on" : "off");
if (want_init_on_free())
pr_info("mem auto-init: clearing system memory may take some time...\n");
}
/*
* Set up kernel memory allocators
*/
static void __init mm_init(void)
{
/*
* page_ext requires contiguous pages,
* bigger than MAX_ORDER unless SPARSEMEM.
*/
page_ext_init_flatmem();
init_debug_pagealloc();
report_meminit();
mem_init();
kmem_cache_init();
kmemleak_init();
pgtable_init();
debug_objects_mem_init();
vmalloc_init();
ioremap_huge_init();
/* Should be run before the first non-init thread is created */
init_espfix_bsp();
/* Should be run after espfix64 is set up. */
pti_init();
}
void __init __weak arch_call_rest_init(void)
{
rest_init();
}
asmlinkage __visible void __init start_kernel(void)
{
char *command_line;
char *after_dashes;
set_task_stack_end_magic(&init_task);
smp_setup_processor_id();
debug_objects_early_init();
cgroup_init_early();
local_irq_disable();
early_boot_irqs_disabled = true;
/*
* Interrupts are still disabled. Do necessary setups, then
* enable them.
*/
boot_cpu_init();
page_address_init();
pr_notice("%s", linux_banner);
early_security_init();
setup_arch(&command_line);
setup_boot_config(command_line);
setup_command_line(command_line);
setup_nr_cpu_ids();
setup_per_cpu_areas();
smp_prepare_boot_cpu(); /* arch-specific boot-cpu hooks */
boot_cpu_hotplug_init();
build_all_zonelists(NULL);
page_alloc_init();
pr_notice("Kernel command line: %s\n", saved_command_line);
/* parameters may set static keys */
jump_label_init();
parse_early_param();
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);
if (extra_init_args)
parse_args("Setting extra init args", extra_init_args,
NULL, 0, -1, -1, NULL, set_init_arg);
/*
* These use large bootmem allocations and must precede
* kmem_cache_init()
*/
setup_log_buf(0);
vfs_caches_init_early();
sort_main_extable();
trap_init();
mm_init();
ftrace_init();
/* trace_printk can be enabled here */
early_trace_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 (WARN(!irqs_disabled(),
"Interrupts were enabled *very* early, fixing it\n"))
local_irq_disable();
radix_tree_init();
/*
* Set up housekeeping before setting up workqueues to allow the unbound
* workqueue to take non-housekeeping into account.
*/
housekeeping_init();
/*
* Allow workqueue creation and work item queueing/cancelling
* early. Work item execution depends on kthreads and starts after
* workqueue_init().
*/
workqueue_init_early();
rcu_init();
/* Trace events are available after this */
trace_init();
if (initcall_debug)
initcall_debug_enable();
context_tracking_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();
/*
* For best initial stack canary entropy, prepare it after:
* - setup_arch() for any UEFI RNG entropy and boot cmdline access
* - timekeeping_init() for ktime entropy used in rand_initialize()
* - rand_initialize() to get any arch-specific entropy like RDRAND
* - add_latent_entropy() to get any latent entropy
* - adding command line entropy
*/
rand_initialize();
add_latent_entropy();
add_device_randomness(command_line, strlen(command_line));
boot_init_stack_canary();
time_init();
perf_event_init();
profile_init();
call_function_init();
WARN(!irqs_disabled(), "Interrupts were enabled early\n");
early_boot_irqs_disabled = false;
local_irq_enable();
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("Too many boot %s vars at `%s'", panic_later,
panic_param);
lockdep_init();
/*
* 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();
/*
* This needs to be called before any devices perform DMA
* operations that might use the SWIOTLB bounce buffers. It will
* mark the bounce buffers as decrypted so that their usage will
* not cause "plain-text" data to be decrypted when accessed.
*/
mem_encrypt_init();
#ifdef CONFIG_BLK_DEV_INITRD
if (initrd_start && !initrd_below_start_ok &&
page_to_pfn(virt_to_page((void *)initrd_start)) < min_low_pfn) {
pr_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
setup_per_cpu_pageset();
numa_policy_init();
acpi_early_init();
if (late_time_init)
late_time_init();
sched_clock_init();
calibrate_delay();
pid_idr_init();
anon_vma_init();
#ifdef CONFIG_X86
if (efi_enabled(EFI_RUNTIME_SERVICES))
efi_enter_virtual_mode();
#endif
thread_stack_cache_init();
cred_init();
fork_init();
proc_caches_init();
uts_ns_init();
buffer_init();
key_init();
security_init();
dbg_late_init();
vfs_caches_init();
pagecache_init();
signals_init();
seq_file_init();
proc_root_init();
nsfs_init();
cpuset_init();
cgroup_init();
taskstats_init_early();
delayacct_init();
poking_init();
check_bugs();
acpi_subsystem_init();
arch_post_acpi_subsys_init();
sfi_init_late();
/* Do the rest non-__init'ed, we're now alive */
arch_call_rest_init();
prevent_tail_call_optimization();
}
/* 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
}
#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 = memblock_alloc(sizeof(*entry),
SMP_CACHE_BYTES);
if (!entry)
panic("%s: Failed to allocate %zu bytes\n",
__func__, sizeof(*entry));
entry->buf = memblock_alloc(strlen(str_entry) + 1,
SMP_CACHE_BYTES);
if (!entry->buf)
panic("%s: Failed to allocate %zu bytes\n",
__func__, 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 blacklist_entry *entry;
char fn_name[KSYM_SYMBOL_LEN];
unsigned long addr;
if (list_empty(&blacklisted_initcalls))
return false;
addr = (unsigned long) dereference_function_descriptor(fn);
sprint_symbol_no_offset(fn_name, addr);
/*
* fn will be "function_name [module_name]" where [module_name] is not
* displayed for built-in init functions. Strip off the [module_name].
*/
strreplace(fn_name, ' ', '\0');
list_for_each_entry(entry, &blacklisted_initcalls, next) {
if (!strcmp(fn_name, entry->buf)) {
pr_debug("initcall %s blacklisted\n", fn_name);
return true;
}
}
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 __init_or_module void
trace_initcall_start_cb(void *data, initcall_t fn)
{
ktime_t *calltime = (ktime_t *)data;
printk(KERN_DEBUG "calling %pS @ %i\n", fn, task_pid_nr(current));
*calltime = ktime_get();
}
static __init_or_module void
trace_initcall_finish_cb(void *data, initcall_t fn, int ret)
{
ktime_t *calltime = (ktime_t *)data;
ktime_t delta, rettime;
unsigned long long duration;
rettime = ktime_get();
delta = ktime_sub(rettime, *calltime);
duration = (unsigned long long) ktime_to_ns(delta) >> 10;
printk(KERN_DEBUG "initcall %pS returned %d after %lld usecs\n",
fn, ret, duration);
}
static ktime_t initcall_calltime;
#ifdef TRACEPOINTS_ENABLED
static void __init initcall_debug_enable(void)
{
int ret;
ret = register_trace_initcall_start(trace_initcall_start_cb,
&initcall_calltime);
ret |= register_trace_initcall_finish(trace_initcall_finish_cb,
&initcall_calltime);
WARN(ret, "Failed to register initcall tracepoints\n");
}
# define do_trace_initcall_start trace_initcall_start
# define do_trace_initcall_finish trace_initcall_finish
#else
static inline void do_trace_initcall_start(initcall_t fn)
{
if (!initcall_debug)
return;
trace_initcall_start_cb(&initcall_calltime, fn);
}
static inline void do_trace_initcall_finish(initcall_t fn, int ret)
{
if (!initcall_debug)
return;
trace_initcall_finish_cb(&initcall_calltime, fn, ret);
}
#endif /* !TRACEPOINTS_ENABLED */
int __init_or_module do_one_initcall(initcall_t fn)
{
int count = preempt_count();
char msgbuf[64];
int ret;
if (initcall_blacklisted(fn))
return -EPERM;
do_trace_initcall_start(fn);
ret = fn();
do_trace_initcall_finish(fn, ret);
msgbuf[0] = 0;
if (preempt_count() != count) {
sprintf(msgbuf, "preemption imbalance ");
preempt_count_set(count);
}
if (irqs_disabled()) {
strlcat(msgbuf, "disabled interrupts ", sizeof(msgbuf));
local_irq_enable();
}
WARN(msgbuf[0], "initcall %pS returned with %s\n", fn, msgbuf);
add_latent_entropy();
return ret;
}
extern initcall_entry_t __initcall_start[];
extern initcall_entry_t __initcall0_start[];
extern initcall_entry_t __initcall1_start[];
extern initcall_entry_t __initcall2_start[];
extern initcall_entry_t __initcall3_start[];
extern initcall_entry_t __initcall4_start[];
extern initcall_entry_t __initcall5_start[];
extern initcall_entry_t __initcall6_start[];
extern initcall_entry_t __initcall7_start[];
extern initcall_entry_t __initcall_end[];
static initcall_entry_t *initcall_levels[] __initdata = {
__initcall0_start,
__initcall1_start,
__initcall2_start,
__initcall3_start,
__initcall4_start,
__initcall5_start,
__initcall6_start,
__initcall7_start,
__initcall_end,
};
/* Keep these in sync with initcalls in include/linux/init.h */
static const char *initcall_level_names[] __initdata = {
"pure",
"core",
"postcore",
"arch",
"subsys",
"fs",
"device",
"late",
};
static int __init ignore_unknown_bootoption(char *param, char *val,
const char *unused, void *arg)
{
return 0;
}
static void __init do_initcall_level(int level, char *command_line)
{
initcall_entry_t *fn;
parse_args(initcall_level_names[level],
command_line, __start___param,
__stop___param - __start___param,
level, level,
NULL, ignore_unknown_bootoption);
trace_initcall_level(initcall_level_names[level]);
for (fn = initcall_levels[level]; fn < initcall_levels[level+1]; fn++)
do_one_initcall(initcall_from_entry(fn));
}
static void __init do_initcalls(void)
{
int level;
size_t len = strlen(saved_command_line) + 1;
char *command_line;
command_line = kzalloc(len, GFP_KERNEL);
if (!command_line)
panic("%s: Failed to allocate %zu bytes\n", __func__, len);
for (level = 0; level < ARRAY_SIZE(initcall_levels) - 1; level++) {
/* Parser modifies command_line, restore it each time */
strcpy(command_line, saved_command_line);
do_initcall_level(level, command_line);
}
kfree(command_line);
}
/*
* 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();
driver_init();
init_irq_proc();
do_ctors();
usermodehelper_enable();
do_initcalls();
}
static void __init do_pre_smp_initcalls(void)
{
initcall_entry_t *fn;
trace_initcall_level("early");
for (fn = __initcall_start; fn < __initcall0_start; fn++)
do_one_initcall(initcall_from_entry(fn));
}
static int run_init_process(const char *init_filename)
{
const char *const *p;
argv_init[0] = init_filename;
pr_info("Run %s as init process\n", init_filename);
pr_debug(" with arguments:\n");
for (p = argv_init; *p; p++)
pr_debug(" %s\n", *p);
pr_debug(" with environment:\n");
for (p = envp_init; *p; p++)
pr_debug(" %s\n", *p);
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);
#if defined(CONFIG_STRICT_KERNEL_RWX) || defined(CONFIG_STRICT_MODULE_RWX)
bool rodata_enabled __ro_after_init = true;
static int __init set_debug_rodata(char *str)
{
return strtobool(str, &rodata_enabled);
}
__setup("rodata=", set_debug_rodata);
#endif
#ifdef CONFIG_STRICT_KERNEL_RWX
static void mark_readonly(void)
{
if (rodata_enabled) {
/*
* load_module() results in W+X mappings, which are cleaned
* up with call_rcu(). Let's make sure that queued work is
* flushed so that we don't hit false positives looking for
* insecure pages which are W+X.
*/
rcu_barrier();
mark_rodata_ro();
rodata_test();
} else
pr_info("Kernel memory protection disabled.\n");
}
#elif defined(CONFIG_ARCH_HAS_STRICT_KERNEL_RWX)
static inline void mark_readonly(void)
{
pr_warn("Kernel memory protection not selected by kernel config.\n");
}
#else
static inline void mark_readonly(void)
{
pr_warn("This architecture does not have kernel memory protection.\n");
}
#endif
void __weak free_initmem(void)
{
free_initmem_default(POISON_FREE_INITMEM);
}
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();
ftrace_free_init_mem();
free_initmem();
mark_readonly();
/*
* Kernel mappings are now finalized - update the userspace page-table
* to finalize PTI.
*/
pti_finalize();
system_state = SYSTEM_RUNNING;
numa_default_policy();
rcu_end_inkernel_boot();
do_sysctl_args();
if (ramdisk_execute_command) {
ret = run_init_process(ramdisk_execute_command);
if (!ret)
return 0;
pr_err("Failed to execute %s (error %d)\n",
ramdisk_execute_command, ret);
}
/*
* 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) {
ret = run_init_process(execute_command);
if (!ret)
return 0;
panic("Requested init %s failed (error %d).",
execute_command, ret);
}
if (CONFIG_DEFAULT_INIT[0] != '\0') {
ret = run_init_process(CONFIG_DEFAULT_INIT);
if (ret)
pr_err("Default init %s failed (error %d)\n",
CONFIG_DEFAULT_INIT, ret);
else
return 0;
}
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 working init found. Try passing init= option to kernel. "
"See Linux Documentation/admin-guide/init.rst for guidance.");
}
void console_on_rootfs(void)
{
/* Open the /dev/console as stdin, this should never fail */
if (ksys_open((const char __user *) "/dev/console", O_RDWR, 0) < 0)
pr_err("Warning: unable to open an initial console.\n");
/* create stdout/stderr */
(void) ksys_dup(0);
(void) ksys_dup(0);
}
static noinline void __init kernel_init_freeable(void)
{
/*
* Wait until kthreadd is all set-up.
*/
wait_for_completion(&kthreadd_done);
/* Now the scheduler is fully set up and can do blocking allocations */
gfp_allowed_mask = __GFP_BITS_MASK;
/*
* init can allocate pages on any node
*/
set_mems_allowed(node_states[N_MEMORY]);
cad_pid = task_pid(current);
smp_prepare_cpus(setup_max_cpus);
workqueue_init();
init_mm_internals();
do_pre_smp_initcalls();
lockup_detector_init();
smp_init();
sched_init_smp();
padata_init();
page_alloc_init_late();
/* Initialize page ext after all struct pages are initialized. */
page_ext_init();
do_basic_setup();
console_on_rootfs();
/*
* 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 (ksys_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..
*
* rootfs is available now, try loading the public keys
* and default modules
*/
integrity_load_keys();
}