linux/init/main.c
Linus Torvalds 902861e34c - Sumanth Korikkar has taught s390 to allocate hotplug-time page frames
from hotplugged memory rather than only from main memory.  Series
   "implement "memmap on memory" feature on s390".
 
 - More folio conversions from Matthew Wilcox in the series
 
 	"Convert memcontrol charge moving to use folios"
 	"mm: convert mm counter to take a folio"
 
 - Chengming Zhou has optimized zswap's rbtree locking, providing
   significant reductions in system time and modest but measurable
   reductions in overall runtimes.  The series is "mm/zswap: optimize the
   scalability of zswap rb-tree".
 
 - Chengming Zhou has also provided the series "mm/zswap: optimize zswap
   lru list" which provides measurable runtime benefits in some
   swap-intensive situations.
 
 - And Chengming Zhou further optimizes zswap in the series "mm/zswap:
   optimize for dynamic zswap_pools".  Measured improvements are modest.
 
 - zswap cleanups and simplifications from Yosry Ahmed in the series "mm:
   zswap: simplify zswap_swapoff()".
 
 - In the series "Add DAX ABI for memmap_on_memory", Vishal Verma has
   contributed several DAX cleanups as well as adding a sysfs tunable to
   control the memmap_on_memory setting when the dax device is hotplugged
   as system memory.
 
 - Johannes Weiner has added the large series "mm: zswap: cleanups",
   which does that.
 
 - More DAMON work from SeongJae Park in the series
 
 	"mm/damon: make DAMON debugfs interface deprecation unignorable"
 	"selftests/damon: add more tests for core functionalities and corner cases"
 	"Docs/mm/damon: misc readability improvements"
 	"mm/damon: let DAMOS feeds and tame/auto-tune itself"
 
 - In the series "mm/mempolicy: weighted interleave mempolicy and sysfs
   extension" Rakie Kim has developed a new mempolicy interleaving policy
   wherein we allocate memory across nodes in a weighted fashion rather
   than uniformly.  This is beneficial in heterogeneous memory environments
   appearing with CXL.
 
 - Christophe Leroy has contributed some cleanup and consolidation work
   against the ARM pagetable dumping code in the series "mm: ptdump:
   Refactor CONFIG_DEBUG_WX and check_wx_pages debugfs attribute".
 
 - Luis Chamberlain has added some additional xarray selftesting in the
   series "test_xarray: advanced API multi-index tests".
 
 - Muhammad Usama Anjum has reworked the selftest code to make its
   human-readable output conform to the TAP ("Test Anything Protocol")
   format.  Amongst other things, this opens up the use of third-party
   tools to parse and process out selftesting results.
 
 - Ryan Roberts has added fork()-time PTE batching of THP ptes in the
   series "mm/memory: optimize fork() with PTE-mapped THP".  Mainly
   targeted at arm64, this significantly speeds up fork() when the process
   has a large number of pte-mapped folios.
 
 - David Hildenbrand also gets in on the THP pte batching game in his
   series "mm/memory: optimize unmap/zap with PTE-mapped THP".  It
   implements batching during munmap() and other pte teardown situations.
   The microbenchmark improvements are nice.
 
 - And in the series "Transparent Contiguous PTEs for User Mappings" Ryan
   Roberts further utilizes arm's pte's contiguous bit ("contpte
   mappings").  Kernel build times on arm64 improved nicely.  Ryan's series
   "Address some contpte nits" provides some followup work.
 
 - In the series "mm/hugetlb: Restore the reservation" Breno Leitao has
   fixed an obscure hugetlb race which was causing unnecessary page faults.
   He has also added a reproducer under the selftest code.
 
 - In the series "selftests/mm: Output cleanups for the compaction test",
   Mark Brown did what the title claims.
 
 - Kinsey Ho has added the series "mm/mglru: code cleanup and refactoring".
 
 - Even more zswap material from Nhat Pham.  The series "fix and extend
   zswap kselftests" does as claimed.
 
 - In the series "Introduce cpu_dcache_is_aliasing() to fix DAX
   regression" Mathieu Desnoyers has cleaned up and fixed rather a mess in
   our handling of DAX on archiecctures which have virtually aliasing data
   caches.  The arm architecture is the main beneficiary.
 
 - Lokesh Gidra's series "per-vma locks in userfaultfd" provides dramatic
   improvements in worst-case mmap_lock hold times during certain
   userfaultfd operations.
 
 - Some page_owner enhancements and maintenance work from Oscar Salvador
   in his series
 
 	"page_owner: print stacks and their outstanding allocations"
 	"page_owner: Fixup and cleanup"
 
 - Uladzislau Rezki has contributed some vmalloc scalability improvements
   in his series "Mitigate a vmap lock contention".  It realizes a 12x
   improvement for a certain microbenchmark.
 
 - Some kexec/crash cleanup work from Baoquan He in the series "Split
   crash out from kexec and clean up related config items".
 
 - Some zsmalloc maintenance work from Chengming Zhou in the series
 
 	"mm/zsmalloc: fix and optimize objects/page migration"
 	"mm/zsmalloc: some cleanup for get/set_zspage_mapping()"
 
 - Zi Yan has taught the MM to perform compaction on folios larger than
   order=0.  This a step along the path to implementaton of the merging of
   large anonymous folios.  The series is named "Enable >0 order folio
   memory compaction".
 
 - Christoph Hellwig has done quite a lot of cleanup work in the
   pagecache writeback code in his series "convert write_cache_pages() to
   an iterator".
 
 - Some modest hugetlb cleanups and speedups in Vishal Moola's series
   "Handle hugetlb faults under the VMA lock".
 
 - Zi Yan has changed the page splitting code so we can split huge pages
   into sizes other than order-0 to better utilize large folios.  The
   series is named "Split a folio to any lower order folios".
 
 - David Hildenbrand has contributed the series "mm: remove
   total_mapcount()", a cleanup.
 
 - Matthew Wilcox has sought to improve the performance of bulk memory
   freeing in his series "Rearrange batched folio freeing".
 
 - Gang Li's series "hugetlb: parallelize hugetlb page init on boot"
   provides large improvements in bootup times on large machines which are
   configured to use large numbers of hugetlb pages.
 
 - Matthew Wilcox's series "PageFlags cleanups" does that.
 
 - Qi Zheng's series "minor fixes and supplement for ptdesc" does that
   also.  S390 is affected.
 
 - Cleanups to our pagemap utility functions from Peter Xu in his series
   "mm/treewide: Replace pXd_large() with pXd_leaf()".
 
 - Nico Pache has fixed a few things with our hugepage selftests in his
   series "selftests/mm: Improve Hugepage Test Handling in MM Selftests".
 
 - Also, of course, many singleton patches to many things.  Please see
   the individual changelogs for details.
 -----BEGIN PGP SIGNATURE-----
 
 iHUEABYIAB0WIQTTMBEPP41GrTpTJgfdBJ7gKXxAjgUCZfJpPQAKCRDdBJ7gKXxA
 joxeAP9TrcMEuHnLmBlhIXkWbIR4+ki+pA3v+gNTlJiBhnfVSgD9G55t1aBaRplx
 TMNhHfyiHYDTx/GAV9NXW84tasJSDgA=
 =TG55
 -----END PGP SIGNATURE-----

Merge tag 'mm-stable-2024-03-13-20-04' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull MM updates from Andrew Morton:

 - Sumanth Korikkar has taught s390 to allocate hotplug-time page frames
   from hotplugged memory rather than only from main memory. Series
   "implement "memmap on memory" feature on s390".

 - More folio conversions from Matthew Wilcox in the series

	"Convert memcontrol charge moving to use folios"
	"mm: convert mm counter to take a folio"

 - Chengming Zhou has optimized zswap's rbtree locking, providing
   significant reductions in system time and modest but measurable
   reductions in overall runtimes. The series is "mm/zswap: optimize the
   scalability of zswap rb-tree".

 - Chengming Zhou has also provided the series "mm/zswap: optimize zswap
   lru list" which provides measurable runtime benefits in some
   swap-intensive situations.

 - And Chengming Zhou further optimizes zswap in the series "mm/zswap:
   optimize for dynamic zswap_pools". Measured improvements are modest.

 - zswap cleanups and simplifications from Yosry Ahmed in the series
   "mm: zswap: simplify zswap_swapoff()".

 - In the series "Add DAX ABI for memmap_on_memory", Vishal Verma has
   contributed several DAX cleanups as well as adding a sysfs tunable to
   control the memmap_on_memory setting when the dax device is
   hotplugged as system memory.

 - Johannes Weiner has added the large series "mm: zswap: cleanups",
   which does that.

 - More DAMON work from SeongJae Park in the series

	"mm/damon: make DAMON debugfs interface deprecation unignorable"
	"selftests/damon: add more tests for core functionalities and corner cases"
	"Docs/mm/damon: misc readability improvements"
	"mm/damon: let DAMOS feeds and tame/auto-tune itself"

 - In the series "mm/mempolicy: weighted interleave mempolicy and sysfs
   extension" Rakie Kim has developed a new mempolicy interleaving
   policy wherein we allocate memory across nodes in a weighted fashion
   rather than uniformly. This is beneficial in heterogeneous memory
   environments appearing with CXL.

 - Christophe Leroy has contributed some cleanup and consolidation work
   against the ARM pagetable dumping code in the series "mm: ptdump:
   Refactor CONFIG_DEBUG_WX and check_wx_pages debugfs attribute".

 - Luis Chamberlain has added some additional xarray selftesting in the
   series "test_xarray: advanced API multi-index tests".

 - Muhammad Usama Anjum has reworked the selftest code to make its
   human-readable output conform to the TAP ("Test Anything Protocol")
   format. Amongst other things, this opens up the use of third-party
   tools to parse and process out selftesting results.

 - Ryan Roberts has added fork()-time PTE batching of THP ptes in the
   series "mm/memory: optimize fork() with PTE-mapped THP". Mainly
   targeted at arm64, this significantly speeds up fork() when the
   process has a large number of pte-mapped folios.

 - David Hildenbrand also gets in on the THP pte batching game in his
   series "mm/memory: optimize unmap/zap with PTE-mapped THP". It
   implements batching during munmap() and other pte teardown
   situations. The microbenchmark improvements are nice.

 - And in the series "Transparent Contiguous PTEs for User Mappings"
   Ryan Roberts further utilizes arm's pte's contiguous bit ("contpte
   mappings"). Kernel build times on arm64 improved nicely. Ryan's
   series "Address some contpte nits" provides some followup work.

 - In the series "mm/hugetlb: Restore the reservation" Breno Leitao has
   fixed an obscure hugetlb race which was causing unnecessary page
   faults. He has also added a reproducer under the selftest code.

 - In the series "selftests/mm: Output cleanups for the compaction
   test", Mark Brown did what the title claims.

 - Kinsey Ho has added the series "mm/mglru: code cleanup and
   refactoring".

 - Even more zswap material from Nhat Pham. The series "fix and extend
   zswap kselftests" does as claimed.

 - In the series "Introduce cpu_dcache_is_aliasing() to fix DAX
   regression" Mathieu Desnoyers has cleaned up and fixed rather a mess
   in our handling of DAX on archiecctures which have virtually aliasing
   data caches. The arm architecture is the main beneficiary.

 - Lokesh Gidra's series "per-vma locks in userfaultfd" provides
   dramatic improvements in worst-case mmap_lock hold times during
   certain userfaultfd operations.

 - Some page_owner enhancements and maintenance work from Oscar Salvador
   in his series

	"page_owner: print stacks and their outstanding allocations"
	"page_owner: Fixup and cleanup"

 - Uladzislau Rezki has contributed some vmalloc scalability
   improvements in his series "Mitigate a vmap lock contention". It
   realizes a 12x improvement for a certain microbenchmark.

 - Some kexec/crash cleanup work from Baoquan He in the series "Split
   crash out from kexec and clean up related config items".

 - Some zsmalloc maintenance work from Chengming Zhou in the series

	"mm/zsmalloc: fix and optimize objects/page migration"
	"mm/zsmalloc: some cleanup for get/set_zspage_mapping()"

 - Zi Yan has taught the MM to perform compaction on folios larger than
   order=0. This a step along the path to implementaton of the merging
   of large anonymous folios. The series is named "Enable >0 order folio
   memory compaction".

 - Christoph Hellwig has done quite a lot of cleanup work in the
   pagecache writeback code in his series "convert write_cache_pages()
   to an iterator".

 - Some modest hugetlb cleanups and speedups in Vishal Moola's series
   "Handle hugetlb faults under the VMA lock".

 - Zi Yan has changed the page splitting code so we can split huge pages
   into sizes other than order-0 to better utilize large folios. The
   series is named "Split a folio to any lower order folios".

 - David Hildenbrand has contributed the series "mm: remove
   total_mapcount()", a cleanup.

 - Matthew Wilcox has sought to improve the performance of bulk memory
   freeing in his series "Rearrange batched folio freeing".

 - Gang Li's series "hugetlb: parallelize hugetlb page init on boot"
   provides large improvements in bootup times on large machines which
   are configured to use large numbers of hugetlb pages.

 - Matthew Wilcox's series "PageFlags cleanups" does that.

 - Qi Zheng's series "minor fixes and supplement for ptdesc" does that
   also. S390 is affected.

 - Cleanups to our pagemap utility functions from Peter Xu in his series
   "mm/treewide: Replace pXd_large() with pXd_leaf()".

 - Nico Pache has fixed a few things with our hugepage selftests in his
   series "selftests/mm: Improve Hugepage Test Handling in MM
   Selftests".

 - Also, of course, many singleton patches to many things. Please see
   the individual changelogs for details.

* tag 'mm-stable-2024-03-13-20-04' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (435 commits)
  mm/zswap: remove the memcpy if acomp is not sleepable
  crypto: introduce: acomp_is_async to expose if comp drivers might sleep
  memtest: use {READ,WRITE}_ONCE in memory scanning
  mm: prohibit the last subpage from reusing the entire large folio
  mm: recover pud_leaf() definitions in nopmd case
  selftests/mm: skip the hugetlb-madvise tests on unmet hugepage requirements
  selftests/mm: skip uffd hugetlb tests with insufficient hugepages
  selftests/mm: dont fail testsuite due to a lack of hugepages
  mm/huge_memory: skip invalid debugfs new_order input for folio split
  mm/huge_memory: check new folio order when split a folio
  mm, vmscan: retry kswapd's priority loop with cache_trim_mode off on failure
  mm: add an explicit smp_wmb() to UFFDIO_CONTINUE
  mm: fix list corruption in put_pages_list
  mm: remove folio from deferred split list before uncharging it
  filemap: avoid unnecessary major faults in filemap_fault()
  mm,page_owner: drop unnecessary check
  mm,page_owner: check for null stack_record before bumping its refcount
  mm: swap: fix race between free_swap_and_cache() and swapoff()
  mm/treewide: align up pXd_leaf() retval across archs
  mm/treewide: drop pXd_large()
  ...
2024-03-14 17:43:30 -07:00

1580 lines
38 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/kprobes.h>
#include <linux/kmsan.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/kfence.h>
#include <linux/rcupdate.h>
#include <linux/srcu.h>
#include <linux/moduleparam.h>
#include <linux/kallsyms.h>
#include <linux/buildid.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/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/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/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/moduleloader.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/kcsan.h>
#include <linux/init_syscalls.h>
#include <linux/stackdepot.h>
#include <linux/randomize_kstack.h>
#include <linux/pidfs.h>
#include <linux/ptdump.h>
#include <net/net_namespace.h>
#include <asm/io.h>
#include <asm/setup.h>
#include <asm/sections.h>
#include <asm/cacheflush.h>
#define CREATE_TRACE_POINTS
#include <trace/events/initcall.h>
#include <kunit/test.h>
static int kernel_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
/* 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 __ro_after_init;
unsigned int saved_command_line_len __ro_after_init;
/* 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 size_t initargs_offs;
#else
# define bootconfig_found false
# define initargs_offs 0
#endif
static char *execute_command;
static char *ramdisk_execute_command = "/init";
/*
* 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;
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(size_t *_size)
{
u32 size, csum;
char *data;
u32 *hdr;
int i;
if (!initrd_end)
return NULL;
data = (char *)initrd_end - BOOTCONFIG_MAGIC_LEN;
/*
* Since Grub may align the size of initrd to 4, we must
* check the preceding 3 bytes as well.
*/
for (i = 0; i < 4; i++) {
if (!memcmp(data, BOOTCONFIG_MAGIC, BOOTCONFIG_MAGIC_LEN))
goto found;
data--;
}
return NULL;
found:
hdr = (u32 *)(data - 8);
size = le32_to_cpu(hdr[0]);
csum = le32_to_cpu(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;
}
if (xbc_calc_checksum(data, size) != csum) {
pr_err("bootconfig checksum failed\n");
return NULL;
}
/* Remove bootconfig from initramfs/initrd */
initrd_end = (unsigned long)data;
if (_size)
*_size = size;
return data;
}
#else
static void * __init get_boot_config_from_initrd(size_t *_size)
{
return NULL;
}
#endif
#ifdef CONFIG_BOOT_CONFIG
static 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");
memblock_free(new_cmdline, len + 1);
return NULL;
}
return new_cmdline;
}
static int __init bootconfig_params(char *param, char *val,
const char *unused, void *arg)
{
if (strcmp(param, "bootconfig") == 0) {
bootconfig_found = true;
}
return 0;
}
static int __init warn_bootconfig(char *str)
{
/* The 'bootconfig' has been handled by bootconfig_params(). */
return 0;
}
static void __init setup_boot_config(void)
{
static char tmp_cmdline[COMMAND_LINE_SIZE] __initdata;
const char *msg, *data;
int pos, ret;
size_t size;
char *err;
/* Cut out the bootconfig data even if we have no bootconfig option */
data = get_boot_config_from_initrd(&size);
/* If there is no bootconfig in initrd, try embedded one. */
if (!data)
data = xbc_get_embedded_bootconfig(&size);
strscpy(tmp_cmdline, boot_command_line, COMMAND_LINE_SIZE);
err = parse_args("bootconfig", tmp_cmdline, NULL, 0, 0, 0, NULL,
bootconfig_params);
if (IS_ERR(err) || !(bootconfig_found || IS_ENABLED(CONFIG_BOOT_CONFIG_FORCE)))
return;
/* parse_args() stops at the next param of '--' and returns an address */
if (err)
initargs_offs = err - tmp_cmdline;
if (!data) {
/* If user intended to use bootconfig, show an error level message */
if (bootconfig_found)
pr_err("'bootconfig' found on command line, but no bootconfig found\n");
else
pr_info("No bootconfig data provided, so skipping bootconfig");
return;
}
if (size >= XBC_DATA_MAX) {
pr_err("bootconfig size %ld greater than max size %d\n",
(long)size, XBC_DATA_MAX);
return;
}
ret = xbc_init(data, size, &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 {
xbc_get_info(&ret, NULL);
pr_info("Load bootconfig: %ld bytes %d nodes\n", (long)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;
}
static void __init exit_boot_config(void)
{
xbc_exit();
}
#else /* !CONFIG_BOOT_CONFIG */
static void __init setup_boot_config(void)
{
/* Remove bootconfig data from initrd */
get_boot_config_from_initrd(NULL);
}
static int __init warn_bootconfig(char *str)
{
pr_warn("WARNING: 'bootconfig' found on the kernel command line but CONFIG_BOOT_CONFIG is not set.\n");
return 0;
}
#define exit_boot_config() do {} while (0)
#endif /* CONFIG_BOOT_CONFIG */
early_param("bootconfig", warn_bootconfig);
/* 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);
/* Handle params aliased to sysctls */
if (sysctl_is_alias(param))
return 0;
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 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.
* The order should always be
* " -- "[bootconfig init-param][cmdline init-param]
*/
if (initargs_offs) {
len = xlen + initargs_offs;
strcpy(saved_command_line + len, extra_init_args);
len += ilen - 4; /* strlen(extra_init_args) */
strcpy(saved_command_line + len,
boot_command_line + initargs_offs - 1);
} else {
len = strlen(saved_command_line);
strcpy(saved_command_line + len, " -- ");
len += 4;
strcpy(saved_command_line + len, extra_init_args);
}
}
saved_command_line_len = strlen(saved_command_line);
}
/*
* We need to finalize in a non-__init function or else race conditions
* between the root thread and the init thread may cause start_kernel to
* be reaped by free_initmem before the root thread has proceeded to
* cpu_idle.
*
* gcc-3.4 accidentally inlines this function, so use noinline.
*/
static __initdata DECLARE_COMPLETION(kthreadd_done);
noinline void __ref __noreturn 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 = user_mode_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);
tsk->flags |= PF_NO_SETAFFINITY;
set_cpus_allowed_ptr(tsk, cpumask_of(smp_processor_id()));
rcu_read_unlock();
numa_default_policy();
pid = kernel_thread(kthreadd, NULL, 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. */
strscpy(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)
{
}
void __init __weak smp_prepare_boot_cpu(void)
{
}
# if THREAD_SIZE >= PAGE_SIZE
void __init __weak thread_stack_cache_init(void)
{
}
#endif
void __init __weak poking_init(void) { }
void __init __weak pgtable_cache_init(void) { }
void __init __weak trap_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
#ifdef CONFIG_RANDOMIZE_KSTACK_OFFSET
DEFINE_STATIC_KEY_MAYBE_RO(CONFIG_RANDOMIZE_KSTACK_OFFSET_DEFAULT,
randomize_kstack_offset);
DEFINE_PER_CPU(u32, kstack_offset);
static int __init early_randomize_kstack_offset(char *buf)
{
int ret;
bool bool_result;
ret = kstrtobool(buf, &bool_result);
if (ret)
return ret;
if (bool_result)
static_branch_enable(&randomize_kstack_offset);
else
static_branch_disable(&randomize_kstack_offset);
return 0;
}
early_param("randomize_kstack_offset", early_randomize_kstack_offset);
#endif
void __init __weak __noreturn arch_call_rest_init(void)
{
rest_init();
}
static void __init print_unknown_bootoptions(void)
{
char *unknown_options;
char *end;
const char *const *p;
size_t len;
if (panic_later || (!argv_init[1] && !envp_init[2]))
return;
/*
* Determine how many options we have to print out, plus a space
* before each
*/
len = 1; /* null terminator */
for (p = &argv_init[1]; *p; p++) {
len++;
len += strlen(*p);
}
for (p = &envp_init[2]; *p; p++) {
len++;
len += strlen(*p);
}
unknown_options = memblock_alloc(len, SMP_CACHE_BYTES);
if (!unknown_options) {
pr_err("%s: Failed to allocate %zu bytes\n",
__func__, len);
return;
}
end = unknown_options;
for (p = &argv_init[1]; *p; p++)
end += sprintf(end, " %s", *p);
for (p = &envp_init[2]; *p; p++)
end += sprintf(end, " %s", *p);
/* Start at unknown_options[1] to skip the initial space */
pr_notice("Unknown kernel command line parameters \"%s\", will be passed to user space.\n",
&unknown_options[1]);
memblock_free(unknown_options, len);
}
asmlinkage __visible __init __no_sanitize_address __noreturn __no_stack_protector
void start_kernel(void)
{
char *command_line;
char *after_dashes;
set_task_stack_end_magic(&init_task);
smp_setup_processor_id();
debug_objects_early_init();
init_vmlinux_build_id();
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();
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();
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);
print_unknown_bootoptions();
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);
/* Architectural and non-timekeeping rng init, before allocator init */
random_init_early(command_line);
/*
* These use large bootmem allocations and must precede
* initalization of page allocator
*/
setup_log_buf(0);
vfs_caches_init_early();
sort_main_extable();
trap_init();
mm_core_init();
poking_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();
if (WARN(!irqs_disabled(),
"Interrupts were enabled *very* early, fixing it\n"))
local_irq_disable();
radix_tree_init();
maple_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();
srcu_init();
hrtimers_init();
softirq_init();
timekeeping_init();
time_init();
/* This must be after timekeeping is initialized */
random_init();
/* These make use of the fully initialized rng */
kfence_init();
boot_init_stack_canary();
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();
#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();
arch_cpu_finalize_init();
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();
key_init();
security_init();
dbg_late_init();
net_ns_init();
vfs_caches_init();
pagecache_init();
signals_init();
seq_file_init();
proc_root_init();
nsfs_init();
pidfs_init();
cpuset_init();
cgroup_init();
taskstats_init_early();
delayacct_init();
acpi_subsystem_init();
arch_post_acpi_subsys_init();
kcsan_init();
/* Do the rest non-__init'ed, we're now alive */
arch_call_rest_init();
/*
* Avoid stack canaries in callers of boot_init_stack_canary for gcc-10
* and older.
*/
#if !__has_attribute(__no_stack_protector__)
prevent_tail_call_optimization();
#endif
}
/* Call all constructor functions linked into the kernel. */
static void __init do_ctors(void)
{
/*
* For UML, the constructors have already been called by the
* normal setup code as it's just a normal ELF binary, so we
* cannot do it again - but we do need CONFIG_CONSTRUCTORS
* even on UML for modules.
*/
#if defined(CONFIG_CONSTRUCTORS) && !defined(CONFIG_UML)
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 1;
}
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 = 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 rettime, *calltime = data;
rettime = ktime_get();
printk(KERN_DEBUG "initcall %pS returned %d after %lld usecs\n",
fn, ret, (unsigned long long)ktime_us_delta(rettime, *calltime));
}
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;
}
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 = saved_command_line_len + 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();
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 kernel_execve(init_filename, argv_init, 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;
#ifndef arch_parse_debug_rodata
static inline bool arch_parse_debug_rodata(char *str) { return false; }
#endif
static int __init set_debug_rodata(char *str)
{
if (arch_parse_debug_rodata(str))
return 0;
if (str && !strcmp(str, "on"))
rodata_enabled = true;
else if (str && !strcmp(str, "off"))
rodata_enabled = false;
else
pr_warn("Invalid option string for rodata: '%s'\n", str);
return 0;
}
early_param("rodata", set_debug_rodata);
#endif
static void mark_readonly(void)
{
if (IS_ENABLED(CONFIG_STRICT_KERNEL_RWX) && rodata_enabled) {
/*
* load_module() results in W+X mappings, which are cleaned
* up with init_free_wq. 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.
*/
flush_module_init_free_work();
mark_rodata_ro();
debug_checkwx();
rodata_test();
} else if (IS_ENABLED(CONFIG_STRICT_KERNEL_RWX)) {
pr_info("Kernel memory protection disabled.\n");
} else if (IS_ENABLED(CONFIG_ARCH_HAS_STRICT_KERNEL_RWX)) {
pr_warn("Kernel memory protection not selected by kernel config.\n");
} else {
pr_warn("This architecture does not have kernel memory protection.\n");
}
}
void __weak free_initmem(void)
{
free_initmem_default(POISON_FREE_INITMEM);
}
static int __ref kernel_init(void *unused)
{
int ret;
/*
* Wait until kthreadd is all set-up.
*/
wait_for_completion(&kthreadd_done);
kernel_init_freeable();
/* need to finish all async __init code before freeing the memory */
async_synchronize_full();
system_state = SYSTEM_FREEING_INITMEM;
kprobe_free_init_mem();
ftrace_free_init_mem();
kgdb_free_init_mem();
exit_boot_config();
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.");
}
/* Open /dev/console, for stdin/stdout/stderr, this should never fail */
void __init console_on_rootfs(void)
{
struct file *file = filp_open("/dev/console", O_RDWR, 0);
if (IS_ERR(file)) {
pr_err("Warning: unable to open an initial console.\n");
return;
}
init_dup(file);
init_dup(file);
init_dup(file);
fput(file);
}
static noinline void __init kernel_init_freeable(void)
{
/* 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 = get_pid(task_pid(current));
smp_prepare_cpus(setup_max_cpus);
workqueue_init();
init_mm_internals();
rcu_init_tasks_generic();
do_pre_smp_initcalls();
lockup_detector_init();
smp_init();
sched_init_smp();
workqueue_init_topology();
async_init();
padata_init();
page_alloc_init_late();
do_basic_setup();
kunit_run_all_tests();
wait_for_initramfs();
console_on_rootfs();
/*
* check if there is an early userspace init. If yes, let it do all
* the work
*/
if (init_eaccess(ramdisk_execute_command) != 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();
}