Linuxメモ（跡地）

kernel entryからの、SoC依存部hook関数呼び出し順序を確認する

前知識

/* initcalls are now grouped by functionality into separate 
 * subsections. Ordering inside the subsections is determined
 * by link order. 
 * For backwards compatibility, initcall() puts the call in 
 * the device init subsection.
 *
 * The `id' arg to __define_initcall() is needed so that multiple initcalls
 * can point at the same handler without causing duplicate-symbol build errors.
 */

#define __define_initcall(level,fn,id) \
        static initcall_t __initcall_##fn##id __used \
        __attribute__((__section__(".initcall" level ".init"))) = fn

/*
 * Early initcalls run before initializing SMP.
 *
 * Only for built-in code, not modules.
 */
#define early_initcall(fn)              __define_initcall("early",fn,early)

/*
 * A "pure" initcall has no dependencies on anything else, and purely
 * initializes variables that couldn't be statically initialized.
 *
 * This only exists for built-in code, not for modules.
 */
#define pure_initcall(fn)               __define_initcall("0",fn,0)

#define core_initcall(fn)               __define_initcall("1",fn,1)
#define core_initcall_sync(fn)          __define_initcall("1s",fn,1s)
#define postcore_initcall(fn)           __define_initcall("2",fn,2)
#define postcore_initcall_sync(fn)      __define_initcall("2s",fn,2s)
#define arch_initcall(fn)               __define_initcall("3",fn,3)
#define arch_initcall_sync(fn)          __define_initcall("3s",fn,3s)
#define subsys_initcall(fn)             __define_initcall("4",fn,4)
#define subsys_initcall_sync(fn)        __define_initcall("4s",fn,4s)
#define fs_initcall(fn)                 __define_initcall("5",fn,5)
#define fs_initcall_sync(fn)            __define_initcall("5s",fn,5s)
#define rootfs_initcall(fn)             __define_initcall("rootfs",fn,rootfs)
#define device_initcall(fn)             __define_initcall("6",fn,6)
#define device_initcall_sync(fn)        __define_initcall("6s",fn,6s)
#define late_initcall(fn)               __define_initcall("7",fn,7)
#define late_initcall_sync(fn)          __define_initcall("7s",fn,7s)

#define INITCALLS							\
	*(.initcallearly.init)						\
	VMLINUX_SYMBOL(__early_initcall_end) = .;			\
  	*(.initcall0.init)						\
  	*(.initcall0s.init)						\
  	*(.initcall1.init)						\
  	*(.initcall1s.init)						\
  	*(.initcall2.init)						\
  	*(.initcall2s.init)						\
  	*(.initcall3.init)						\
  	*(.initcall3s.init)						\
  	*(.initcall4.init)						\
  	*(.initcall4s.init)						\
  	*(.initcall5.init)						\
  	*(.initcall5s.init)						\
	*(.initcallrootfs.init)						\
  	*(.initcall6.init)						\
  	*(.initcall6s.init)						\
  	*(.initcall7.init)						\
  	*(.initcall7s.init)

#define INIT_CALLS							\
		VMLINUX_SYMBOL(__initcall_start) = .;			\
		INITCALLS						\
		VMLINUX_SYMBOL(__initcall_end) = .;
...
#define INIT_DATA_SECTION(initsetup_align)				\
	.init.data : AT(ADDR(.init.data) - LOAD_OFFSET) {		\
		INIT_DATA						\
		INIT_SETUP(initsetup_align)				\
		INIT_CALLS						\
		CON_INITCALL						\
		SECURITY_INITCALL					\
		INIT_RAM_FS						\
	}
...

extern initcall_t __initcall_start[], __initcall_end[], __early_initcall_end[];

static void __init do_initcalls(void)
{
	initcall_t *fn;

	for (fn = __early_initcall_end; fn < __initcall_end; fn++)
		do_one_initcall(*fn);
}
...
static void __init do_basic_setup(void)
{
	cpuset_init_smp();
	usermodehelper_init();
	init_tmpfs();
	driver_init();
	init_irq_proc();
	do_ctors();
	do_initcalls();
}
...

static void __init do_pre_smp_initcalls(void)
{
	initcall_t *fn;

	for (fn = __initcall_start; fn < __early_initcall_end; fn++)
		do_one_initcall(*fn);
}

...
static int __init kernel_init(void * unused)  // この子は __init_refok rest_init(void)からthread化される。
{
	/*
	 * 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_HIGH_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();    /// ★early init callに属する関数を実行。
	lockup_detector_init();

	smp_init();
	sched_init_smp();

	do_basic_setup();         /// ★init callを実行。early init以外を順次呼び出す.
...

本命

__mmap_switched:
    b       start_kernel

asmlinkage void __init start_kernel(void)
{
	char * command_line;
	extern const struct kernel_param __start___param[], __stop___param[];

	smp_setup_processor_id();

	/*
	 * Need to run as early as possible, to initialize the
	 * lockdep hash:
	 */
	lockdep_init();
	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
 */
	tick_init();
	boot_cpu_init();
	page_address_init();
	printk(KERN_NOTICE "%s", linux_banner);
	setup_arch(&command_line);              //★ARMの場合はヴェクタ設定、メモリ領域の確保、MMU初期設定まで完了する
	mm_init_owner(&init_mm, &init_task);
	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);
	page_alloc_init();

	printk(KERN_NOTICE "Kernel command line: %s\n", boot_command_line);
	parse_early_param();
	parse_args("Booting kernel", static_command_line, __start___param,
		   __stop___param - __start___param,
		   &unknown_bootoption);
	/*
	 * 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 (!irqs_disabled()) {
		printk(KERN_WARNING "start_kernel(): bug: interrupts were "
				"enabled *very* early, fixing it\n");
		local_irq_disable();
	}
	idr_init_cache();
	perf_event_init();
	rcu_init();
	radix_tree_init();
	/* init some links before init_ISA_irqs() */
	early_irq_init();
	init_IRQ();
	prio_tree_init();
	init_timers();
	hrtimers_init();
	softirq_init();
	timekeeping_init();
	time_init();
	profile_init();
	call_function_init();
	if (!irqs_disabled())
		printk(KERN_CRIT "start_kernel(): bug: 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(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) {
		printk(KERN_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_cgroup_init();
	enable_debug_pagealloc();
	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();
#ifdef CONFIG_X86
	if (efi_enabled)
		efi_enter_virtual_mode();
#endif
	thread_info_cache_init();
	cred_init();
	fork_init(totalram_pages);
	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();
#ifdef CONFIG_PROC_FS
	proc_root_init();
#endif
	cgroup_init();
	cpuset_init();
	taskstats_init_early();
	delayacct_init();

	check_bugs();

	acpi_early_init(); /* before LAPIC and SMP init */
	sfi_init_late();

	ftrace_init();

	/* Do the rest non-__init'ed, we're now alive */
	rest_init();    //★ kernel_init()をkthread_startするよ
}

arm固有のマシン情報

struct machine_desc {
    unsigned int       nr;        /* architecture number    */
    const char        *name;        /* architecture name    */
    unsigned long      boot_params;    /* tagged list        */
    const char       **dt_compat;    /* array of device tree 'compatible' strings */

    unsigned int       nr_irqs;    /* number of IRQs */

    unsigned int      video_start;    /* start of video RAM    */
    unsigned int      video_end;    /* end of video RAM    */

    unsigned int      reserve_lp0 :1;    /* never has lp0    */
    unsigned int      reserve_lp1 :1;    /* never has lp1    */
    unsigned int      reserve_lp2 :1;    /* never has lp2    */
    unsigned int      soft_reboot :1;    /* soft reboot        */

    void    (*fixup)(struct machine_desc *, struct tag *, char **, struct meminfo *);
    void    (*reserve)(void);              /* reserve mem blocks  */
    void    (*map_io)(void);               /* IO mapping function */
    void    (*init_early)(void);
    void    (*init_irq)(void);

    struct sys_timer    *timer;            /* system tick timer    */
    void            (*init_machine)(void);
#ifdef CONFIG_MULTI_IRQ_HANDLER
    void            (*handle_irq)(struct pt_regs *);
#endif
};

void __init arm_memblock_init(struct meminfo *mi, struct machine_desc *mdesc)

ここの処理の最後に呼び出している。この前に initrd領域もreservedにしてしまう。
	/* reserve any platform specific memblock areas */
	if (mdesc->reserve)
		mdesc->reserve();

void __init paging_init(struct machine_desc *mdesc)
　static void __init devicemaps_init(struct machine_desc *mdesc)
　...
　　if (mdesc->map_io)
　　　mdesc->map_io();

ここでkernel管理のPage tableを初期化する。
ヴェクタ用pageの確保、high/lo vector処理、VMALLOC_ENDカラ後ろのアクセス禁止設定を行う。

void __init setup_arch(char **cmdline_p)
...
	paging_init(mdesc); // ★ ioremap設定するので、map_io()はこの先で呼ばれる。
...
	if (mdesc->init_early)
		mdesc->init_early();

static int __init customize_machine(void)
{
	/* customizes platform devices, or adds new ones */
	if (machine_desc->init_machine)
		machine_desc->init_machine();
	return 0;
}
arch_initcall(customize_machine);

ARM関係

Kernel Memory Layout on ARM Linux

Russell King <rmk@arm.linux.org.uk>
November 17, 2005 (2.6.15)

This document describes the virtual memory layout which the Linux kernel uses for ARM processors.
It indicates which regions are free for platforms to use, and which are used by generic code.

The ARM CPU is capable of addressing a maximum of 4GB virtual memory space,
and this must be shared between user space processes, the kernel, and hardware devices.

As the ARM architecture matures, it becomes necessary to reserve certain regions of VM space for use for new facilities;
therefore this document may reserve more VM space over time.

Please note that mappings which collide with the above areas may result in a non-bootable kernel,
or may cause the kernel to (eventually) panic at run time.

Since future CPUs may impact the kernel mapping layout,
user programs must not access any memory which is not mapped inside their 0x0001000 to TASK_SIZE address range.
If they wish to access these areas,
they must set up their own mappings using open() and mmap().

関連ファイル

めも

drivers/clocksource/dw_apb_timer.c
drivers/clocksource/arm_arch_timer.c
drivers/clocksource/arm_global_timer.c
drivers/clocksource/dummy_timer.c

driver:: clocksource "jiffies", "refined-jiffies"

FILE: kernel/time/jiffies.c

static struct clocksource clocksource_jiffies = {
        .name           = "jiffies",
        .rating         = 1, /* lowest valid rating*/
        .read           = jiffies_read,
        .mask           = 0xffffffff, /*32bits*/
        .mult           = NSEC_PER_JIFFY << JIFFIES_SHIFT, /* details above */
        .shift          = JIFFIES_SHIFT,
};


EXPORT_SYMBOL(jiffies);

static int __init init_jiffies_clocksource(void)
{
	return clocksource_register(&clocksource_jiffies);
}

core_initcall(init_jiffies_clocksource);

struct clocksource * __init __weak clocksource_default_clock(void)
{
	return &clocksource_jiffies;
}

./arch/x86/kernel/setup.c:1215:	register_refined_jiffies(CLOCK_TICK_RATE);

clocksource

struct clocksource {
	/*
	 * Hotpath data, fits in a single cache line when the
	 * clocksource itself is cacheline aligned.
	 */
	cycle_t (*read)(struct clocksource *cs); // clocksourceを引数で渡して、サイクル値を返す。
	cycle_t cycle_last; // read()メンバ呼び出しで最近読みだしたcycle値。
	cycle_t mask;    // 非64bitカウンタの引き算のための２の補数のためのbitmask値。
	u32 mult;        // cycleからナノ秒の乗数
	u32 shift;       // cycleからナノ秒の除数（２の累乗）
	u64 max_idle_ns; // clocksourceによって許容される最大アイドル時間（ナノ秒）
	u32 maxadj;      // 最大調整値？to multiってなんだ。。。（１１％以下）
#ifdef CONFIG_ARCH_CLOCKSOURCE_DATA
	struct arch_clocksource_data archdata; // architecture固有のデータ
#endif

	const char *name;      // clocksourceの名前
	struct list_head list; // システムに登録するためのリストヘッド
	int rating;            // 複数登録された時の選択基準（大きいのが選ばれる）
	int (*enable)(struct clocksource *cs);    // [option] clocksourceを有効にする。
	void (*disable)(struct clocksource *cs);  // [option] clocksourceを無効にする。
	unsigned long flags;   // 特別な属性を記述するためのフラグ
	void (*suspend)(struct clocksource *cs);  // 必要ならば、サスペンド機能
	void (*resume)(struct clocksource *cs);   // 必要ならば、レジューム機能

	/* private: */
#ifdef CONFIG_CLOCKSOURCE_WATCHDOG
	/* Watchdog related data, used by the framework */
	struct list_head wd_list;
	cycle_t cs_last;
	cycle_t wd_last;
#endif
	struct module *owner;  // module reference.. clocksource moduleで設定される（書きこむなという意）
} ____cacheline_aligned;

flagsの値

clock event

/* Clock event notification values */
enum clock_event_nofitiers

struct clock_event_device {
	void  (*event_handler)(struct clock_event_device *);  // event sourceの低レベルハンドラから呼ばれるために、フレームワークによってアサインされる。
	int   (*set_next_event)(unsigned long evt, struct clock_event_device *);  // clocksource deltaを使って次のイベントをセットする関数
	int   (*set_next_ktime)(ktime_t expires, struct clock_event_device *);    // ktime値を直接使って次のイベントをセットする関数
	ktime_t  next_event;   // oneshot mode時の次のイベントのためのローカルストレージ
	u64      max_delta_ns; // 最大の差分値（ナノ秒）
	u64      min_delta_ns; // 最小の差分値（ナノ秒）
	u32      mult;         // ナノ秒からサイクル数への乗数
	u32      shift;        // サイクル数からナノ秒の除数（２の累乗）
	enum clock_event_mode  mode; // マネージメントコードによって代入される、動作モード
	unsigned int           features; // 機能
	unsigned long          retries;  // 強制プログラムの再回数

	void    (*broadcast)(const struct cpumask *mask); // broadcastイベント関数（？）
	void    (*set_mode)(enum clock_event_mode mode, struct clock_event_device *); // 動作モード設定関数
	void    (*suspend)(struct clock_event_device *);
	void    (*resume)(struct clock_event_device *);
	unsigned long  min_delta_ticks; // リコンフィギュレーションのために保存されたtickの最小デルタ値
	unsigned long  max_delta_ticks; // リコンフィギュレーションのために保存されたtickの最大デルタ値

	const char  *name;  // clock event名へのポインタ
	int   rating;       // clockeventの選択基準値
	int   irq;          // IRQ number (only for non CPU local devices)
	const struct cpumask  *cpumask; // このデバイスが動作するCPUについて示す値
	struct list_head      list;     // マネージメントコードのためのリストヘッド
	struct module         *owner;   // module参照
} ____cacheline_aligned;

clock eventのユースケース（？）

void clockevents_register_device(struct clock_event_device *dev)
{
	unsigned long flags;

	BUG_ON(dev->mode != CLOCK_EVT_MODE_UNUSED);
	if (!dev->cpumask) {
		WARN_ON(num_possible_cpus() > 1);
		dev->cpumask = cpumask_of(smp_processor_id());
	}

	raw_spin_lock_irqsave(&clockevents_lock, flags);

	list_add(&dev->list, &clockevent_devices);
	tick_check_new_device(dev);       // ★★★ここ。この先で使えると思ったCPUが奪っていく。
	clockevents_notify_released();

	raw_spin_unlock_irqrestore(&clockevents_lock, flags);
}

void tick_check_new_device(struct clock_event_device *newdev)
{
	struct clock_event_device *curdev;
	struct tick_device *td;
	int cpu;

	cpu = smp_processor_id();
	if (!cpumask_test_cpu(cpu, newdev->cpumask))
		goto out_bc;

	td = &per_cpu(tick_cpu_device, cpu);
	curdev = td->evtdev;

	/* cpu local device ? */
	if (!tick_check_percpu(curdev, newdev, cpu))
		goto out_bc;

	/* Preference decision */
	if (!tick_check_preferred(curdev, newdev))
		goto out_bc;

	if (!try_module_get(newdev->owner))
		return;

	/*
	 * Replace the eventually existing device by the new
	 * device. If the current device is the broadcast device, do
	 * not give it back to the clockevents layer !
	 */
	if (tick_is_broadcast_device(curdev)) {
		clockevents_shutdown(curdev);
		curdev = NULL;
	}
	clockevents_exchange_device(curdev, newdev);
	tick_setup_device(td, newdev, cpu, cpumask_of(cpu));
	if (newdev->features & CLOCK_EVT_FEAT_ONESHOT)
		tick_oneshot_notify();
	return;

out_bc:
	/*
	 * Can the new device be used as a broadcast device ?
	 */
	tick_install_broadcast_device(newdev);
}

/**
 * clockevents_set_mode - set the operating mode of a clock event device
 * @dev:	device to modify
 * @mode:	new mode
 *
 * Must be called with interrupts disabled !
 */
void clockevents_set_mode(struct clock_event_device *dev,
				 enum clock_event_mode mode)
{
	if (dev->mode != mode) {
		dev->set_mode(mode, dev);
		dev->mode = mode;

		/*
		 * A nsec2cyc multiplicator of 0 is invalid and we'd crash
		 * on it, so fix it up and emit a warning:
		 */
		if (mode == CLOCK_EVT_MODE_ONESHOT) {
			if (unlikely(!dev->mult)) {
				dev->mult = 1;
				WARN_ON(1);
			}
		}
	}
}

• >set_mode()呼び出しで、ナニを期待されているのか、という視点で書いています。

hrtimerとの関係

void hrtimer_interrupt(struct clock_event_device *dev)
...
	/* Reprogramming necessary ? */
	if (expires_next.tv64 == KTIME_MAX ||
	    !tick_program_event(expires_next, 0)) {
		cpu_base->hang_detected = 0;
		return;
	}
...
	tick_program_event(expires_next, 1);

void hrtimer_peek_ahead_timers(void)
　static void __hrtimer_peek_ahead_timers(void)
　{
　　td = &__get_cpu_var(tick_cpu_device);
　　if (td && td->evtdev)
　　　hrtimer_interrupt(td->evtdev);

DECLARE_PER_CPU(struct tick_device, tick_cpu_device);

参考にしてみたドライバ：

zImageの展開処理

+------------------------+
| u-boot header(64oct.)  |
+------------------------+
| zImage decompress code |
| .text                  |
| (with compressed data )|
| .got                   |
| .got.plt               |
| .bss                   |
+------------------------+

  _text = .;
  .text : {}
  _etext = .;
  _got_start = .;
  .got			: { *(.got) }
  _got_end = .;
  .got.plt		: { *(.got.plt) }
  _edata = .;

  __bss_start = .;
  .bss			: { *(.bss) }
  _end = .;

事前準備

# Supply ZRELADDR to the decompressor via a linker symbol.
ifneq ($(CONFIG_AUTO_ZRELADDR),y)
LDFLAGS_vmlinux += --defsym zreladdr=$(ZRELADDR)

ZRELADDR    := $(zreladdr-y)

zreladdr-y	:= 0x40008000
params_phys-y	:= 0x40000100
initrd_phys-y	:= 0x40800000

zImage先頭から

bootloaderから飛んでくるところ

start:
　※cache有効, TLBはVA-PA一対一対応, 

restart:
		.align	2
		.type	LC0, #object
LC0:
		.word	LC0					@ r1
		.word	__bss_start			@ r2
		.word	_end				@ r3
		.word	_edata				@ r6
		.word	input_data_end - 4	@ r10 (inflated size location)
		.word	_got_start			@ r11
		.word	_got_end			@ ip(r12)

		.word	.L_user_stack_end	@ sp

		.size	LC0, . - LC0

		/*
		 * We might be running at a different address.  We need
		 * to fix up various pointers.
		 */
		sub	r0, r0, r1		@ calculate the delta offset
		add	r6, r6, r0		@ _edata
		add	r10, r10, r0	@ inflated kernel size location

relocate後

wont_overwrite:
/*
 * If delta is zero, we are running at the address we were linked at.
 *   r0  = delta
 *   r2  = BSS start
 *   r3  = BSS end
 *   r4  = kernel execution address
 *   r7  = architecture ID
 *   r8  = atags pointer
 *   r11 = GOT start
 *   r12 = GOT end
 *   sp  = stack pointer
 */

本来のImage(vmlinux)へ

void decompress_kernel(unsigned long output_start, unsigned long free_mem_ptr_p, unsigned long free_mem_ptr_end_p, int arch_id)