Linux内核的启动简述
原创作品转载请注明出处
《Linux内核分析》MOOC课程http://mooc.study.163.com/course/USTC-1000029000
回顾知识：
操作系统法宝：堆栈，中断上下文切换，进程上下文切换
Linux源代码目录 linux-3.18.6
主要目录介绍：
| arch | 不同的CPU体系结构相关的代码，主要研究x86目录 |
| Documentation | 相关文档 |
| drivers | 驱动相关代码 |
| fs | 文件系统相关代码 |
| init | 内核启动相关代码，其中main.c的start_kernel是系统启动的入口 |
| Kernel | 内核相关代码 |
| mm | 内存管理相关代码 |
| net | 网络相关代码 |
gdb命令
c 继续执行(continue)
list 查看代码
break 设置断点
调试内核
qemu -kernel linux-3.18.6/arch/x86/boot/bzImage -initrd rootfs.img -s -S # 关于-s和-S选项的说明：
# -S freeze CPU at startup (use ’c’ to start execution)
# -s shorthand for -gdb tcp::1234 若不想使用1234端口，则可以使用-gdb tcp:xxxx来取代-s选项
gdb
（gdb）file linux-3.18.6/vmlinux # 在gdb界面中targe remote之前加载符号表
（gdb）target remote:1234 # 建立gdb和gdbserver之间的连接,按c 让qemu上的Linux继续运行
（gdb）break start_kernel # 断点的设置可以在target remote之前，也可以在之后
kernel_init中完成初始化操作
9
500asmlinkage __visible void __init start_kernel(void)
501{
502 char *command_line;
503 char *after_dashes;
504
505 /*
506 * Need to run as early as possible, to initialize the
507 * lockdep hash:
508 */
509 lockdep_init();
510 set_task_stack_end_magic(&init_task);
511 smp_setup_processor_id();
512 debug_objects_early_init();
513
514 /*
515 * Set up the the initial canary ASAP:
516 */
517 boot_init_stack_canary();
518
519 cgroup_init_early();
520
521 local_irq_disable();
522 early_boot_irqs_disabled = true;
523
524/*
525 * Interrupts are still disabled. Do necessary setups, then
526 * enable them
527 */
528 boot_cpu_init();
529 page_address_init();
530 pr_notice("%s", linux_banner);
531 setup_arch(&command_line);
532 mm_init_cpumask(&init_mm);
533 setup_command_line(command_line);
534 setup_nr_cpu_ids();
535 setup_per_cpu_areas();
536 smp_prepare_boot_cpu(); /* arch-specific boot-cpu hooks */
537
538 build_all_zonelists(NULL, NULL);
539 page_alloc_init();
540
541 pr_notice("Kernel command line: %s\n", boot_command_line);
542 parse_early_param();
543 after_dashes = parse_args("Booting kernel",
544 static_command_line, __start___param,
545 __stop___param - __start___param,
546 -1, -1, &unknown_bootoption);
547 if (!IS_ERR_OR_NULL(after_dashes))
548 parse_args("Setting init args", after_dashes, NULL, 0, -1, -1,
549 set_init_arg);
550
551 jump_label_init();
552
553 /*
554 * These use large bootmem allocations and must precede
555 * kmem_cache_init()
556 */
557 setup_log_buf(0);
558 pidhash_init();
559 vfs_caches_init_early();
560 sort_main_extable();
561 trap_init();
562 mm_init();
563
564 /*
565 * Set up the scheduler prior starting any interrupts (such as the
566 * timer interrupt). Full topology setup happens at smp_init()
567 * time - but meanwhile we still have a functioning scheduler.
568 */
569 sched_init();
570 /*
571 * Disable preemption - early bootup scheduling is extremely
572 * fragile until we cpu_idle() for the first time.
573 */
574 preempt_disable();
575 if (WARN(!irqs_disabled(),
576 "Interrupts were enabled *very* early, fixing it\n"))
577 local_irq_disable();
578 idr_init_cache();
579 rcu_init();
580 context_tracking_init();
581 radix_tree_init();
582 /* init some links before init_ISA_irqs() */
583 early_irq_init();
584 init_IRQ();
585 tick_init();
586 rcu_init_nohz();
587 init_timers();
588 hrtimers_init();
589 softirq_init();
590 timekeeping_init();
591 time_init();
592 sched_clock_postinit();
593 perf_event_init();
594 profile_init();
595 call_function_init();
596 WARN(!irqs_disabled(), "Interrupts were enabled early\n");
597 early_boot_irqs_disabled = false;
598 local_irq_enable();
599
600 kmem_cache_init_late();
601
602 /*
603 * HACK ALERT! This is early. We're enabling the console before
604 * we've done PCI setups etc, and console_init() must be aware of
605 * this. But we do want output early, in case something goes wrong.
606 */
607 console_init();
608 if (panic_later)
609 panic("Too many boot %s vars at `%s'", panic_later,
610 panic_param);
611
612 lockdep_info();
613
614 /*
615 * Need to run this when irqs are enabled, because it wants
616 * to self-test [hard/soft]-irqs on/off lock inversion bugs
617 * too:
618 */
619 locking_selftest();
620
621#ifdef CONFIG_BLK_DEV_INITRD
622 if (initrd_start && !initrd_below_start_ok &&
623 page_to_pfn(virt_to_page((void *)initrd_start)) < min_low_pfn) {
624 pr_crit("initrd overwritten (0x%08lx < 0x%08lx) - disabling it.\n",
625 page_to_pfn(virt_to_page((void *)initrd_start)),
626 min_low_pfn);
627 initrd_start = 0;
628 }
629#endif
630 page_cgroup_init();
631 debug_objects_mem_init();
632 kmemleak_init();
633 setup_per_cpu_pageset();
634 numa_policy_init();
635 if (late_time_init)
636 late_time_init();
637 sched_clock_init();
638 calibrate_delay();
639 pidmap_init();
640 anon_vma_init();
641 acpi_early_init();
642#ifdef CONFIG_X86
643 if (efi_enabled(EFI_RUNTIME_SERVICES))
644 efi_enter_virtual_mode();
645#endif
646#ifdef CONFIG_X86_ESPFIX64
647 /* Should be run before the first non-init thread is created */
648 init_espfix_bsp();
649#endif
650 thread_info_cache_init();
651 cred_init();
652 fork_init(totalram_pages);
653 proc_caches_init();
654 buffer_init();
655 key_init();
656 security_init();
657 dbg_late_init();
658 vfs_caches_init(totalram_pages);
659 signals_init();
660 /* rootfs populating might need page-writeback */
661 page_writeback_init();
662 proc_root_init();
663 cgroup_init();
664 cpuset_init();
665 taskstats_init_early();
666 delayacct_init();
667
668 check_bugs();
669
670 sfi_init_late();
671
672 if (efi_enabled(EFI_RUNTIME_SERVICES)) {
673 efi_late_init();
674 efi_free_boot_services();
675 }
676
677 ftrace_init();
678
679 /* Do the rest non-__init'ed, we're now alive */
680 rest_init();
681}trap_init : 中断向量的初始化工作
set_intr_gate : 设置中断门
set_system_trap_gate : 系统调用中断
393static noinline void __init_refok rest_init(void)
394{
395 int pid;
396
397 rcu_scheduler_starting();
398 /*
399 * We need to spawn init first so that it obtains pid 1, however
400 * the init task will end up wanting to create kthreads, which, if
401 * we schedule it before we create kthreadd, will OOPS.
402 */
403 kernel_thread(kernel_init, NULL, CLONE_FS);
404 numa_default_policy();
405 pid = kernel_thread(kthreadd, NULL, CLONE_FS | CLONE_FILES);
406 rcu_read_lock();
407 kthreadd_task = find_task_by_pid_ns(pid, &init_pid_ns);
408 rcu_read_unlock();
409 complete(&kthreadd_done);
410
411 /*
412 * The boot idle thread must execute schedule()
413 * at least once to get things moving:
414 */
415 init_idle_bootup_task(current);
416 schedule_preempt_disabled();
417 /* Call into cpu_idle with preempt disabled */
418 cpu_startup_entry(CPUHP_ONLINE);
419}reset_init : 0进程初始化工作
kernel_init : 1号进程(用户态)初始化
Linux中1号进程是由0号进程来创建的，因此必须要知道的是如何创建0号进程，由于在创建进程时，程序一直运行在内核态，而进程运行在用户态，因此创建0号进程涉及到特权级的变化，即从特权级0变到特权级3，Linux是通过模拟中断返回来实现特权级的变化以及创建0号进程，通过将0号进程的代码段选择子以及程序计数器EIP直接压入内核态堆栈，然后利用iret汇编指令中断返回跳转到0号进程运行。