通过对U-boot的启动流程的梳理,最终我们进入了Linux的内核,下面分析一下Linux内核的启动流程和如何做一个简单的移植。
一、kernel启动流程
通过arch/arm/kernel/vmlinux.lds脚本链接文件查看Linux kernel内核入口时stext,然后我们通过搜索得知,stext定义在arch/arm/kernel/head.S中,函数代码如下:
ENTRY(stext)
ARM_BE8(setend be ) @ ensure we are in BE8 mode
THUMB( adr r9, BSYM(1f) ) @ Kernel is always entered in ARM.
THUMB( bx r9 ) @ If this is a Thumb-2 kernel,
THUMB( .thumb ) @ switch to Thumb now.
THUMB(1: )
#ifdef CONFIG_ARM_VIRT_EXT
bl __hyp_stub_install
#endif
@ ensure svc mode and all interrupts masked
safe_svcmode_maskall r9
mrc p15, 0, r9, c0, c0 @ get processor id
bl __lookup_processor_type @ r5=procinfo r9=cpuid
movs r10, r5 @ invalid processor (r5=0)?
THUMB( it eq ) @ force fixup-able long branch encoding
beq __error_p @ yes, error 'p'
#ifdef CONFIG_ARM_LPAE
mrc p15, 0, r3, c0, c1, 4 @ read ID_MMFR0
and r3, r3, #0xf @ extract VMSA support
cmp r3, #5 @ long-descriptor translation table format?
THUMB( it lo ) @ force fixup-able long branch encoding
blo __error_lpae @ only classic page table format
#endif
#ifndef CONFIG_XIP_KERNEL
adr r3, 2f
ldmia r3, {r4, r8}
sub r4, r3, r4 @ (PHYS_OFFSET - PAGE_OFFSET)
add r8, r8, r4 @ PHYS_OFFSET
#else
ldr r8, =PLAT_PHYS_OFFSET @ always constant in this case
#endif
/*
* r1 = machine no, r2 = atags or dtb,
* r8 = phys_offset, r9 = cpuid, r10 = procinfo
*/
bl __vet_atags
#ifdef CONFIG_SMP_ON_UP
bl __fixup_smp
#endif
#ifdef CONFIG_ARM_PATCH_PHYS_VIRT
bl __fixup_pv_table
#endif
bl __create_page_tables
/*
* The following calls CPU specific code in a position independent
* manner. See arch/arm/mm/proc-*.S for details. r10 = base of
* xxx_proc_info structure selected by __lookup_processor_type
* above. On return, the CPU will be ready for the MMU to be
* turned on, and r0 will hold the CPU control register value.
*/
ldr r13, =__mmap_switched @ address to jump to after
@ mmu has been enabled
adr lr, BSYM(1f) @ return (PIC) address
mov r8, r4 @ set TTBR1 to swapper_pg_dir
ldr r12, [r10, #PROCINFO_INITFUNC]
add r12, r12, r10
ret r12
1: b __enable_mmu
ENDPROC(stext)
通过注释,我们可以知道,进入内核的前提是:MMU = off, D-cache = off, I-cache = dont care, r0 = 0, r1 = machine nr, r2 = atags or dtb pointer.MMU、D-cache关闭,I-cache随意,r0是0,ri保存正确的机械ID,r2保存设备树首地址(atags不知道啥)。
然后stext流程便是:
- 调用safe_svcmode_maskall ,进入svc模式,关闭所有中断;
- 调用__lookup_processor_type确定该内核与CPU是否兼容,兼容的话获取procinfo信息;
- 调用 __vet_atags 验证设备树;
- 调用__create_page_tables创建页表;
- 调用__mmap_switched函数,保存返回地址;
- 最后调用 __enable_mmu函数使能 MMC。
顺便提下__mmap_switched函数,因为它最终会调用start_kernel函数,代码在arch/arm/kernel/head-common.S中,内容如下:
__mmap_switched:
adr r3, __mmap_switched_data
ldmia r3!, {r4, r5, r6, r7}
cmp r4, r5 @ Copy data segment if needed
1: cmpne r5, r6
ldrne fp, [r4], #4
strne fp, [r5], #4
bne 1b
mov fp, #0 @ Clear BSS (and zero fp)
1: cmp r6, r7
strcc fp, [r6],#4
bcc 1b
ARM( ldmia r3, {r4, r5, r6, r7, sp})
THUMB( ldmia r3, {r4, r5, r6, r7} )
THUMB( ldr sp, [r3, #16] )
str r9, [r4] @ Save processor ID
str r1, [r5] @ Save machine type
str r2, [r6] @ Save atags pointer
cmp r7, #0
strne r0, [r7] @ Save control register values
b start_kernel
ENDPROC(__mmap_switched)
在倒数第二行,调用了start_kernel函数,start_kernel函数定义在文件 init/main.c,它会调用很多函数完成Linux的启动工作,先附上代码,以后再细说:
asmlinkage __visible void __init start_kernel(void)
{
char *command_line;
char *after_dashes;
/*
* Need to run as early as possible, to initialize the
* lockdep hash:
*/
lockdep_init();
set_task_stack_end_magic(&init_task);
smp_setup_processor_id();
debug_objects_early_init();
/*
* Set up the the initial canary ASAP:
*/
boot_init_stack_canary();
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);
setup_arch(&command_line);
mm_init_cpumask(&init_mm);
setup_command_line(command_line);
setup_nr_cpu_ids();
setup_per_cpu_areas();
smp_prepare_boot_cpu(); /* arch-specific boot-cpu hooks */
build_all_zonelists(NULL, NULL);
page_alloc_init();
pr_notice("Kernel command line: %s\n", boot_command_line);
parse_early_param();
after_dashes = parse_args("Booting kernel",
static_command_line, __start___param,
__stop___param - __start___param,
-1, -1, &unknown_bootoption);
if (!IS_ERR_OR_NULL(after_dashes))
parse_args("Setting init args", after_dashes, NULL, 0, -1, -1,
set_init_arg);
jump_label_init();
/*
* These use large bootmem allocations and must precede
* kmem_cache_init()
*/
setup_log_buf(0);
pidhash_init();
vfs_caches_init_early();
sort_main_extable();
trap_init();
mm_init();
/*
* Set up the scheduler prior starting any interrupts (such as the
* timer interrupt). Full topology setup happens at smp_init()
* 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();
idr_init_cache();
rcu_init();
/* trace_printk() and trace points may be used after this */
trace_init();
context_tracking_init();
radix_tree_init();
/* init some links before init_ISA_irqs() */
early_irq_init();
init_IRQ();
tick_init();
rcu_init_nohz();
init_timers();
hrtimers_init();
softirq_init();
timekeeping_init();
time_init();
sched_clock_postinit();
perf_event_init();
profile_init();
call_function_init();
WARN(!irqs_disabled(), "Interrupts were enabled early\n");
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_info();
/*
* 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
page_ext_init();
debug_objects_mem_init();
kmemleak_init();
setup_per_cpu_pageset();
numa_policy_init();
if (late_time_init)
late_time_init();
sched_clock_init();
calibrate_delay();
pidmap_init();
anon_vma_init();
acpi_early_init();
#ifdef CONFIG_X86
if (efi_enabled(EFI_RUNTIME_SERVICES))
efi_enter_virtual_mode();
#endif
#ifdef CONFIG_X86_ESPFIX64
/* Should be run before the first non-init thread is created */
init_espfix_bsp();
#endif
thread_info_cache_init();
cred_init();
fork_init();
proc_caches_init();
buffer_init();
key_init();
security_init();
dbg_late_init();
vfs_caches_init(totalram_pages);
signals_init();
/* rootfs populating might need page-writeback */
page_writeback_init();
proc_root_init();
nsfs_init();
cpuset_init();
cgroup_init();
taskstats_init_early();
delayacct_init();
check_bugs();
acpi_subsystem_init();
sfi_init_late();
if (efi_enabled(EFI_RUNTIME_SERVICES)) {
efi_late_init();
efi_free_boot_services();
}
ftrace_init();
/* Do the rest non-__init'ed, we're now alive */
rest_init();
}
在start_kernel最后,调用了rest_init函数,rest_init函数也定义在文件 init/main.c中,这个不长:
static noinline void __init_refok rest_init(void)
{
int pid;
rcu_scheduler_starting();
smpboot_thread_init();
/*
* We need to spawn init first so that it obtains pid 1, however
* the init task will end up wanting to create kthreads, which, if
* we schedule it before we create kthreadd, will OOPS.
*/
kernel_thread(kernel_init, NULL, CLONE_FS);
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();
complete(&kthreadd_done);
/*
* The boot idle thread must execute schedule()
* at least once to get things moving:
*/
init_idle_bootup_task(current);
schedule_preempt_disabled();
/* Call into cpu_idle with preempt disabled */
cpu_startup_entry(CPUHP_ONLINE);
}
它的流程是:
- 调用 rcu_scheduler_starting,启动 RCU锁调度器
- 调用 kernel_thread 创建 kernel_init进程,将kernel由内核态转到用户态
- 调用 kernel_thread 创建 kthreadd内核进程,此内核进程的 PID为 2。 kthreadd进程负责所有内核进程的调度和管理。
- 最后调用 cpu_startup_entry 进入 idle进程,idle线程说白了,和待机很像,让cpu一直干愣着,有任务它就把cpu交给其它进程。
kernel_init函数用来管理init进程,代码如下:
static int __ref kernel_init(void *unused)
{
int ret;
kernel_init_freeable();
/* need to finish all async __init code before freeing the memory */
async_synchronize_full();
free_initmem();
mark_rodata_ro();
system_state = SYSTEM_RUNNING;
numa_default_policy();
flush_delayed_fput();
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 (!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/init.txt for guidance.");
}
- 调用 kernel_init_freeable 函数用于完成 init进程的一些其他初始化工作,下面会再说;
- 调用 async_synchronize_full 函数,等待List async_running与async_pending都清空后返回,用来加速Linux启动;
- 调用 free_initmem 函数,释放Linux Kernel有关内存,用于满足多媒体、中断等高需求;
- 调用 mark_rodata_ro 函数,标记内核数据只读;
- 调用 numa_default_policy 函数,恢复当前进程的内存策略为默认状态;
- 如果ramdisk_execute_command、execute_command为真,调用 run_init_process 函数 初始化用户进程,否则通过其它尝试初始化用户层。
最后,看一下kernel_init_freeable()函数:
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]);
/*
* init can run on any cpu.
*/
set_cpus_allowed_ptr(current, cpu_all_mask);
cad_pid = task_pid(current);
smp_prepare_cpus(setup_max_cpus);
do_pre_smp_initcalls();
lockup_detector_init();
smp_init();
sched_init_smp();
do_basic_setup();
/* Open the /dev/console on the rootfs, this should never fail */
if (sys_open((const char __user *) "/dev/console", O_RDWR, 0) < 0)
pr_err("Warning: unable to open an initial console.\n");
(void) sys_dup(0);
(void) sys_dup(0);
/*
* 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 (sys_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();
load_default_modules();
}
- 调用 wait_for_completion 函数,等待 kthreadd_done 完成;
- 调用 set_mems_allowed 函数,初始化可在任何node分配到内存页;
- 调用 set_cpus_allowed_ptr 函数,设置cpu_bit_mask,限定task只在特定处理器上运行,使init进程能够在任意的cpu上运行;
- 调用 smp_prepare_cpus 函数,设定在编译核心时支援的最大CPU数量;
- 调用 do_pre_smp_initcalls 函数,遍历Symbol中部分函数,并调用do_one_initcall(fn)依次执行;
- 调用 do_basic_setup函数,完成 Linux下设备驱动初始化工作以及Linux下驱动模型子系统的初始化;
- 调用函数 prepare_namespace 函数,挂载根文件系统。
二、kernel移植
kernel移植只需要移植defconfig配置文件以及设备树文件即可,它们分别在arch/arm/configs、arch/arm/boot/dts下。复制完后,再在arch/arm/boot/dts的Makefile中添加设备树,复制的哪个就添加到哪个下面就行。
移植脚本,注移植的NXP的imx6ullevk:
#!/bin/bash
board=Xport_Alientek
BOARD=XPORT_ALIENTEK
# Adding a compilation script
touch ${board}_building.sh
chmod 777 ${board}_building.sh
echo '#!/bin/bash' > ${board}_building.sh
echo '' >> ${board}_building.sh
echo "make ARCH=arm CROSS_COMPILE=arm-linux-gnueabihf- distclean" >> ${board}_building.sh
echo "make ARCH=arm CROSS_COMPILE=arm-linux-gnueabihf- imx_${board}_emmc_defconfig" >> ${board}_building.sh
echo "make ARCH=arm CROSS_COMPILE=arm-linux-gnueabihf- menuconfig" >> ${board}_building.sh
echo "make ARCH=arm CROSS_COMPILE=arm-linux-gnueabihf- all -j8" >> ${board}_building.sh
cd arch/arm/configs
cp imx_alientek_emmc_defconfig imx_${board}_emmc_defconfig
cd ../../../arch/arm/boot/dts
cp imx6ull-alientek-emmc.dts imx6ull-${board}-emmc.dts
getline()
{
cat -n Makefile|grep "imx6ull-${board}-emmc.dtb "|awk '{print $1}'
}
if [ `getline` > 0 ]
then
echo The development board : $board already exists
else
declare -i nline
getline()
{
cat -n Makefile|grep "CONFIG_SOC_IMX6ULL) += "|awk '{print $1}'
}
getlinenum()
{
awk "BEGIN{a=`getline`;b="1";c=(a+b);print c}";
}
nline=`getlinenum`-1
sed -i "${nline}a\ imx6ull-${board}-emmc.dtb "'\\' Makefile
echo The new linux-kernel : $board is added
fi