[系统运维]linux内核对设备树的处理

本篇文档是基于韦东山老师的设备树专题学习总结而来。

1. platform identification,
2. runtime configuration, and
3. device population.

1 内核head.S对dtb的简单处理

1.1 Kernel startup entry point stext

在stext函数中主要做下面几件事情：

• __lookup_processor_type : 使用汇编指令读取CPU ID, 根据该ID找到对应的proc_info_list结构体(里面含有这类CPU的初始化函数、信息)
• __vet_atags : 判断是否存在可用的ATAGS或DTB
• __create_page_tables : 创建页表, 即创建虚拟地址和物理地址的映射关系
• __enable_mmu : 使能MMU, 以后就要使用虚拟地址了
• __mmap_switched : 上述函数里将会调用__mmap_switched
• 把bootloader传入的r0 r1 r2参数, 保存到对应的C变量processor_id，__machine_arch_type，__atags_pointer中

/*
 * Kernel startup entry point.
 * ---------------------------
 *
 * This is normally called from the decompressor code.  The requirements
 * are: MMU = off, D-cache = off, I-cache = dont care, r0 = 0,
 * r1 = machine nr, r2 = atags or dtb pointer.
 *
 * This code is mostly position independent, so if you link the kernel at
 * 0xc0008000, you call this at __pa(0xc0008000).
 *
 * See linux/arch/arm/tools/mach-types for the complete list of machine
 * numbers for r1.
 *
 * We're trying to keep crap to a minimum; DO NOT add any machine specific
 * crap here - that's what the boot loader (or in extreme, well justified
 * circumstances, zImage) is for.
 */
	.arm

	__HEAD
ENTRY(stext)
 ARM_BE8(setend	be )			@ ensure we are in BE8 mode

 THUMB(	badr	r9, 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.
	 *
	 * The processor init function will be called with:
	 *  r1 - machine type
	 *  r2 - boot data (atags/dt) pointer
	 *  r4 - translation table base (low word)
	 *  r5 - translation table base (high word, if LPAE)
	 *  r8 - translation table base 1 (pfn if LPAE)
	 *  r9 - cpuid
	 *  r13 - virtual address for __enable_mmu -> __turn_mmu_on
	 *
	 * On return, the CPU will be ready for the MMU to be turned on,
	 * r0 will hold the CPU control register value, r1, r2, r4, and
	 * r9 will be preserved.  r5 will also be preserved if LPAE.
	 */
	ldr	r13, =__mmap_switched		@ address to jump to after
						@ mmu has been enabled
	badr	lr, 1f				@ return (PIC) address
#ifdef CONFIG_ARM_LPAE
	mov	r5, #0				@ high TTBR0
	mov	r8, r4, lsr #12			@ TTBR1 is swapper_pg_dir pfn
#else
	mov	r8, r4				@ set TTBR1 to swapper_pg_dir
#endif`在这里插入代码片`
	ldr	r12, [r10, #PROCINFO_INITFUNC]
	add	r12, r12, r10
	ret	r12
1:	b	__enable_mmu
ENDPROC(stext)
	.ltorg
#ifndef CONFIG_XIP_KERNEL
2:	.long	.
	.long	PAGE_OFFSET
#endif

1.2 __enable_mmu和__turn_mmu_on

• 在stext函数中将__mmap_switched 的地址放入到r13寄存器中，ldr r13, =__mmap_switched @ address to jump to after
• 在__turn_mmu_on中，在使能mmu之后会通过mov r3, r13汇编指令，将r13的值放入r3中，然后通过ret r3返回到__enable_mmu函数中，最终会调用到__mmap_switched函数

1.2.1 __enable_mmu

/*
 * Setup common bits before finally enabling the MMU.  Essentially
 * this is just loading the page table pointer and domain access
 * registers.  All these registers need to be preserved by the
 * processor setup function (or set in the case of r0)
 *
 *  r0  = cp#15 control register
 *  r1  = machine ID
 *  r2  = atags or dtb pointer
 *  r4  = TTBR pointer (low word)
 *  r5  = TTBR pointer (high word if LPAE)
 *  r9  = processor ID
 *  r13 = *virtual* address to jump to upon completion
 */
__enable_mmu:
#if defined(CONFIG_ALIGNMENT_TRAP) && __LINUX_ARM_ARCH__ < 6
	orr	r0, r0, #CR_A
#else
	bic	r0, r0, #CR_A
#endif
#ifdef CONFIG_CPU_DCACHE_DISABLE
	bic	r0, r0, #CR_C
#endif
#ifdef CONFIG_CPU_BPREDICT_DISABLE
	bic	r0, r0, #CR_Z
#endif
#ifdef CONFIG_CPU_ICACHE_DISABLE
	bic	r0, r0, #CR_I
#endif
#ifdef CONFIG_ARM_LPAE
	mcrr	p15, 0, r4, r5, c2		@ load TTBR0
#else
	mov	r5, #DACR_INIT
	mcr	p15, 0, r5, c3, c0, 0		@ load domain access register
	mcr	p15, 0, r4, c2, c0, 0		@ load page table pointer
#endif
	b	__turn_mmu_on
ENDPROC(__enable_mmu)

1.2.1 __turn_mmu_on

/*
 * Enable the MMU.  This completely changes the structure of the visible
 * memory space.  You will not be able to trace execution through this.
 * If you have an enquiry about this, *please* check the linux-arm-kernel
 * mailing list archives BEFORE sending another post to the list.
 *  *  r0  = cp#15 control register
 *  r1  = machine ID
 *  r2  = atags or dtb pointer
 *  r9  = processor ID
 *  r13 = *virtual* address to jump to upon completion
 *  * other registers depend on the function called upon completion
 */
	.align	5
	.pushsection	.idmap.text, "ax"
ENTRY(__turn_mmu_on)
	mov	r0, r0
	instr_sync
	mcr	p15, 0, r0, c1, c0, 0		@ write control reg
	mrc	p15, 0, r3, c0, c0, 0		@ read id reg
	instr_sync
	mov	r3, r3
	mov	r3, r13
	ret	r3
__turn_mmu_on_end:
ENDPROC(__turn_mmu_on)
	.popsection

1.3 __mmap_switched

• adr r4, __mmap_switched_data 将__mmap_switched_data的地址赋值给r4寄存器，
• __bss_start
• 把bootloader传来的r0值, 赋给了C变量: processor_id 把bootloader传来的r1值, 赋给了C变量: __machine_arch_type 把bootloader传来的r2值, 赋给了C变量: __atags_pointer // tags 或 dtb首地址
• b start_kernel

1.3.1 __mmap_switched

__mmap_switched是在MMU模式下打开MMU时执行的。

/*
 * The following fragment of code is executed with the MMU on in MMU mode,
 * and uses absolute addresses; this is not position independent.
 *
 *  r0  = cp#15 control register (exc_ret for M-class)
 *  r1  = machine ID
 *  r2  = atags/dtb pointer
 *  r9  = processor ID
 */
	__INIT
__mmap_switched:

	mov	r7, r1
	mov	r8, r2
	mov	r10, r0

	adr	r4, __mmap_switched_data
	mov	fp, #0

#if defined(CONFIG_XIP_DEFLATED_DATA)
   ARM(	ldr	sp, [r4], #4 )
 THUMB(	ldr	sp, [r4] )
 THUMB(	add	r4, #4 )
	bl	__inflate_kernel_data		@ decompress .data to RAM
	teq	r0, #0
	bne	__error
#elif defined(CONFIG_XIP_KERNEL)
   ARM(	ldmia	r4!, {r0, r1, r2, sp} )
 THUMB(	ldmia	r4!, {r0, r1, r2, r3} )
 THUMB(	mov	sp, r3 )
	sub	r2, r2, r1
	bl	memcpy				@ copy .data to RAM
#endif

   ARM(	ldmia	r4!, {r0, r1, sp} )	/* 把__bss_start，__bss_stop以及init_thread_union + THREAD_START_SP分别赋值给r0,r1,sp寄存器 */
 THUMB(	ldmia	r4!, {r0, r1, r3} )
 THUMB(	mov	sp, r3 )
	sub	r2, r1, r0
	mov	r1, #0
	bl	memset				@ clear .bss

	ldmia	r4, {r0, r1, r2, r3}	/* 把processor_id，__machine_arch_type，__atags_pointer以及cr_alignment分别赋值给r0,r1,r2,r3寄存器 */
	str	r9, [r0]			@ Save processor ID
	str	r7, [r1]			@ Save machine type
	str	r8, [r2]			@ Save atags pointer
	cmp	r3, #0
	strne	r10, [r3]			@ Save control register values
	mov	lr, #0
	b	start_kernel
ENDPROC(__mmap_switched)

1.3.2 __mmap_switched_data

	.align	2
	.type	__mmap_switched_data, %object
__mmap_switched_data:
#ifdef CONFIG_XIP_KERNEL
#ifndef CONFIG_XIP_DEFLATED_DATA
	.long	_sdata				@ r0
	.long	__data_loc			@ r1
	.long	_edata_loc			@ r2
#endif
	.long	__bss_stop			@ sp (temporary stack in .bss)
#endif

	.long	__bss_start			@ r0
	.long	__bss_stop			@ r1
	.long	init_thread_union + THREAD_START_SP @ sp

	.long	processor_id			@ r0
	.long	__machine_arch_type		@ r1
	.long	__atags_pointer			@ r2
#ifdef CONFIG_CPU_CP15
	.long	cr_alignment			@ r3
#else
M_CLASS(.long	exc_ret)			@ r3
AR_CLASS(.long	0)				@ r3
#endif
	.size	__mmap_switched_data, . - __mmap_switched_data

	__FINIT
	.text

2 设备树中平台信息的处理(选择machine_desc)

• dts中声明想要什么样的machine_desc
• 每个machine_desc表明能支持哪些单板
• 当有多个machine_desc和DTS匹配时，如何选择对应的单板

2.1 dts中声明想要什么样的machine_desc

在设备树的根节点的compatible属性表明要支持哪些machine_desc，“兼容”属性包含一个已排序的字符串列表，从机器的确切名称开始，然后是一个可选的兼容板列表，从最兼容到最不兼容。

The 'compatible' property contains a sorted list of strings starting 
with the exact name of the machine, followed by an optional list of 
boards it is compatible with sorted from most compatible to least.  For 
example, the root compatible properties for the TI BeagleBoard and its 
successor, the BeagleBoard xM board might look like, respectively:

compatible = "ti,omap3-beagleboard", "ti,omap3450", "ti,omap3"; 
compatible = "ti,omap3-beagleboard-xm", "ti,omap3450", "ti,omap3";

2.2 每个machine_desc表明能支持哪些单板

下面以 (linux-5.6.15\arch\arm\mach-bcm\bcm_nsp.c)为例介绍，bcm_nsp_dt_compat的值为"brcm,nsp"，则表明当前的machine_desc支持"brcm,nsp"这个单板。

static const char *const bcm_nsp_dt_compat[] __initconst = {
	"brcm,nsp",
	NULL,
};

DT_MACHINE_START(NSP_DT, "Broadcom Northstar Plus SoC")
	.l2c_aux_val	= 0,
	.l2c_aux_mask	= ~0,
	.dt_compat = bcm_nsp_dt_compat,
MACHINE_END

2.3 多个machine_desc和.dts compatible 匹配

当有多个machine_desc和DTS的compatible 匹配时，如何选择对应的单板呢，
根据score来评判最适合的单板。
调用过程如下所示：

函数调用过程:
start_kernel // init/main.c
    setup_arch(&command_line);  // arch/arm/kernel/setup.c
        mdesc = setup_machine_fdt(__atags_pointer);  //arch/arm/kernel/devtree.c
            early_init_dt_verify(phys_to_virt(dt_phys)  // 判断是否有效的dtb, drivers/of/ftd.c
				initial_boot_params = params;
            mdesc = of_flat_dt_match_machine(mdesc_best, arch_get_next_mach);  // 找到最匹配的machine_desc, drivers/of/ftd.c
                while ((data = get_next_compat(&compat))) {
                    score = of_flat_dt_match(dt_root, compat);
                    if (score > 0 && score < best_score) {
                        best_data = data;
                        best_score = score;
                    }
                }
                    
        machine_desc = mdesc;

2.3.1 setup_arch

在setup_arch函数中对设备树的处理主要是关注下面几点：

• __atags_pointer 存放的是dtb活着tag的地址，用于后面dtb或者tag的解析
• setup_machine_fdt先去检查是否是dtb传参格式
• setup_machine_tags检查tag的传参方式
• machine_desc = mdesc; （const struct machine_desc *machine_desc __initdata;）
• machine_name = mdesc->name;（static const char *machine_name;）

void __init setup_arch(char **cmdline_p)
{
	const struct machine_desc *mdesc;

	setup_processor();
	mdesc = setup_machine_fdt(__atags_pointer);
	if (!mdesc)
		mdesc = setup_machine_tags(__atags_pointer, __machine_arch_type);
	if (!mdesc) {
		early_print("\nError: invalid dtb and unrecognized/unsupported machine ID\n");
		early_print("  r1=0x%08x, r2=0x%08x\n", __machine_arch_type,
			    __atags_pointer);
		if (__atags_pointer)
			early_print("  r2[]=%*ph\n", 16,
				    phys_to_virt(__atags_pointer));
		dump_machine_table();
	}

	machine_desc = mdesc;
	machine_name = mdesc->name;
	dump_stack_set_arch_desc("%s", mdesc->name);

	if (mdesc->reboot_mode != REBOOT_HARD)
		reboot_mode = mdesc->reboot_mode;

	init_mm.start_code = (unsigned long) _text;
	init_mm.end_code   = (unsigned long) _etext;
	init_mm.end_data   = (unsigned long) _edata;
	init_mm.brk	   = (unsigned long) _end;

	/* populate cmd_line too for later use, preserving boot_command_line */
	strlcpy(cmd_line, boot_command_line, COMMAND_LINE_SIZE);
	*cmdline_p = cmd_line;

	early_fixmap_init();
	early_ioremap_init();

	parse_early_param();

#ifdef CONFIG_MMU
	early_mm_init(mdesc);
#endif
	setup_dma_zone(mdesc);
	xen_early_init();
	efi_init();
	/*
	 * Make sure the calculation for lowmem/highmem is set appropriately
	 * before reserving/allocating any mmeory
	 */
	adjust_lowmem_bounds();
	arm_memblock_init(mdesc);
	/* Memory may have been removed so recalculate the bounds. */
	adjust_lowmem_bounds();

	early_ioremap_reset();

	paging_init(mdesc);
	request_standard_resources(mdesc);

	if (mdesc->restart)
		arm_pm_restart = mdesc->restart;

	unflatten_device_tree();

	arm_dt_init_cpu_maps();
	psci_dt_init();
#ifdef CONFIG_SMP
	if (is_smp()) {
		if (!mdesc->smp_init || !mdesc->smp_init()) {
			if (psci_smp_available())
				smp_set_ops(&psci_smp_ops);
			else if (mdesc->smp)
				smp_set_ops(mdesc->smp);
		}
		smp_init_cpus();
		smp_build_mpidr_hash();
	}
#endif

	if (!is_smp())
		hyp_mode_check();

	reserve_crashkernel();

#ifdef CONFIG_GENERIC_IRQ_MULTI_HANDLER
	handle_arch_irq = mdesc->handle_irq;
#endif

#ifdef CONFIG_VT
#if defined(CONFIG_VGA_CONSOLE)
	conswitchp = &vga_con;
#endif
#endif

	if (mdesc->init_early)
		mdesc->init_early();
}

2.3.2 setup_machine_fdt

当dtb被传递给内核时的machine设置

• early_init_dt_verify(phys_to_virt(dt_phys))
• mdesc = of_flat_dt_match_machine(mdesc_best, arch_get_next_mach)
• early_init_dt_scan_nodes();

/**
 * setup_machine_fdt - Machine setup when an dtb was passed to the kernel
 * @dt_phys: physical address of dt blob
 *
 * If a dtb was passed to the kernel in r2, then use it to choose the
 * correct machine_desc and to setup the system.
 */
const struct machine_desc * __init setup_machine_fdt(unsigned int dt_phys)
{
	const struct machine_desc *mdesc, *mdesc_best = NULL;

#if defined(CONFIG_ARCH_MULTIPLATFORM) || defined(CONFIG_ARM_SINGLE_ARMV7M)
	DT_MACHINE_START(GENERIC_DT, "Generic DT based system")
		.l2c_aux_val = 0x0,
		.l2c_aux_mask = ~0x0,
	MACHINE_END

	mdesc_best = &__mach_desc_GENERIC_DT;
#endif

	if (!dt_phys || !early_init_dt_verify(phys_to_virt(dt_phys)))
		return NULL;

	mdesc = of_flat_dt_match_machine(mdesc_best, arch_get_next_mach);

	if (!mdesc) {
		const char *prop;
		int size;
		unsigned long dt_root;

		early_print("\nError: unrecognized/unsupported "
			    "device tree compatible list:\n[ ");

		dt_root = of_get_flat_dt_root();
		prop = of_get_flat_dt_prop(dt_root, "compatible", &size);
		while (size > 0) {
			early_print("'%s' ", prop);
			size -= strlen(prop) + 1;
			prop += strlen(prop) + 1;
		}
		early_print("]\n\n");

		dump_machine_table(); /* does not return */
	}

	/* We really don't want to do this, but sometimes firmware provides buggy data */
	if (mdesc->dt_fixup)
		mdesc->dt_fixup();

	early_init_dt_scan_nodes();

	/* Change machine number to match the mdesc we're using */
	__machine_arch_type = mdesc->nr;

	return mdesc;
}

2.3.2.1 early_init_dt_verify

在early_init_dt_verify函数中主要处理下面三件事情，首先检查设备树header，如果是，这设置initial_boot_params 和of_fdt_crc32 。

• fdt_check_header(params))
• initial_boot_params = params;
• of_fdt_crc32 = crc32_be(~0, initial_boot_params, fdt_totalsize(initial_boot_params));

bool __init early_init_dt_verify(void *params)
{
	if (!params)
		return false;

	/* check device tree validity */
	if (fdt_check_header(params))
		return false;

	/* Setup flat device-tree pointer */
	initial_boot_params = params;
	of_fdt_crc32 = crc32_be(~0, initial_boot_params,
				fdt_totalsize(initial_boot_params));
	return true;
}

2.3.2.2 fdt_check_header

在fdt_check_header函数中均是做的dtb的格式校验相关的工作，我们以下面header magic和hdrsize两个为例来说明，其他都是去校验dtb 格式里面的其他属性。

• fdt_magic(fdt) != FDT_MAGIC 检查header magic是否匹配
• hdrsize = fdt_header_size(fdt);获取hdrsize

int fdt_check_header(const void *fdt)
{
	size_t hdrsize;

	if (fdt_magic(fdt) != FDT_MAGIC)
		return -FDT_ERR_BADMAGIC;
	hdrsize = fdt_header_size(fdt);
	if ((fdt_version(fdt) < FDT_FIRST_SUPPORTED_VERSION)
	    || (fdt_last_comp_version(fdt) > FDT_LAST_SUPPORTED_VERSION))
		return -FDT_ERR_BADVERSION;
	if (fdt_version(fdt) < fdt_last_comp_version(fdt))
		return -FDT_ERR_BADVERSION;

	if ((fdt_totalsize(fdt) < hdrsize)
	    || (fdt_totalsize(fdt) > INT_MAX))
		return -FDT_ERR_TRUNCATED;

	/* Bounds check memrsv block */
	if (!check_off_(hdrsize, fdt_totalsize(fdt), fdt_off_mem_rsvmap(fdt)))
		return -FDT_ERR_TRUNCATED;

	/* Bounds check structure block */
	if (fdt_version(fdt) < 17) {
		if (!check_off_(hdrsize, fdt_totalsize(fdt),
				fdt_off_dt_struct(fdt)))
			return -FDT_ERR_TRUNCATED;
	} else {
		if (!check_block_(hdrsize, fdt_totalsize(fdt),
				  fdt_off_dt_struct(fdt),
				  fdt_size_dt_struct(fdt)))
			return -FDT_ERR_TRUNCATED;
	}

	/* Bounds check strings block */
	if (!check_block_(hdrsize, fdt_totalsize(fdt),
			  fdt_off_dt_strings(fdt), fdt_size_dt_strings(fdt)))
		return -FDT_ERR_TRUNCATED;

	return 0;
}

2.3.2.3 arch_get_next_mach

从__arch_info_begin位置开始依次取出machine_desc，然后将m->dt_compat取出。
其中__arch_info_begin是在MACHINE_START中标注.section .arch.info.init的起始位置，__arch_info_end标记.arch.info.init段的结束。

2.3.2.3.1 arch_get_next_mach

static const void * __init arch_get_next_mach(const char *const **match)
{
	static const struct machine_desc *mdesc = __arch_info_begin;
	const struct machine_desc *m = mdesc;

	if (m >= __arch_info_end)
		return NULL;

	mdesc++;
	*match = m->dt_compat;
	return m;
}

2.3.2.3.2 __arch_info_begin和__arch_info_end

• MACHINE_START去标记把当前的machine_desc 信息放在.arch.info.init段中
• __arch_info_begin 和__arch_info_end 分别标记.arch.info.init段的开始和结束

.init.arch.info : {
	__arch_info_begin = .;
	*(.arch.info.init)
	__arch_info_end = .;
}

/*
 * Set of macros to define architecture features.  This is built into
 * a table by the linker.
 */
#define MACHINE_START(_type,_name)			\
static const struct machine_desc __mach_desc_##_type	\
 __used							\
 __attribute__((__section__(".arch.info.init"))) = {	\
	.nr		= MACH_TYPE_##_type,		\
	.name		= _name,

#define MACHINE_END				\
};

2.3.2.4 of_flat_dt_match_machine

迭代匹配的tables以寻找匹配的machine。该函数的主要功能是在while循环里面去做的，目的就是为了找出最匹配的machine_desc。

/**
 * of_flat_dt_match_machine - Iterate match tables to find matching machine.
 *  * @default_match: A machine specific ptr to return in case of no match.
 * @get_next_compat: callback function to return next compatible match table.
 *  * Iterate through machine match tables to find the best match for the machine
 * compatible string in the FDT.
 */
const void * __init of_flat_dt_match_machine(const void *default_match,
		const void * (*get_next_compat)(const char * const**))
{
	const void *data = NULL;
	const void *best_data = default_match;
	const char *const *compat;
	unsigned long dt_root;
	unsigned int best_score = ~1, score = 0;

	dt_root = of_get_flat_dt_root();
	while ((data = get_next_compat(&compat))) {
		score = of_flat_dt_match(dt_root, compat);
		if (score > 0 && score < best_score) {
			best_data = data;
			best_score = score;
		}
	}
	if (!best_data) {
		const char *prop;
		int size;

		pr_err("\n unrecognized device tree list:\n[ ");

		prop = of_get_flat_dt_prop(dt_root, "compatible", &size);
		if (prop) {
			while (size > 0) {
				printk("'%s' ", prop);
				size -= strlen(prop) + 1;
				prop += strlen(prop) + 1;
			}
		}
		printk("]\n\n");
		return NULL;
	}

	pr_info("Machine model: %s\n", of_flat_dt_get_machine_name());

	return best_data;
}

2.3.2.5 of_flat_dt_match

如果节点与compatible values的列表相匹配，则返回true
initial_boot_params是在early_init_dt_verify函数中检测是dtb格式时，将dtb地址赋值给initial_boot_params的。

/**
 * of_flat_dt_match - Return true if node matches a list of compatible values
 */
static int __init of_flat_dt_match(unsigned long node, const char *const *compat)
{
	unsigned int tmp, score = 0;

	if (!compat)
		return 0;

	while (*compat) {
		tmp = of_fdt_is_compatible(initial_boot_params, node, *compat);
		if (tmp && (score == 0 || (tmp < score)))
			score = tmp;
		compat++;
	}

	return score;
}

2.3.2.6 of_fdt_is_compatible

of_fdt_is_compatible函数去在compatible list去检查匹配的compatible string，匹配的结果越靠前这分数越低，表明匹配度越高。
一下面的例子为例来说明：
compatible = “ti,omap3-beagleboard”, “ti,omap3450”, “ti,omap3”;

• 当匹配"ti,omap3-beagleboard"时，这score = 1
• 当匹配 "ti,omap3450"时，这score = 2
• 当匹配"ti,omap3"时，这score = 3

/**
 * of_fdt_is_compatible - Return true if given node from the given blob has
 * compat in its compatible list
 * @blob: A device tree blob
 * @node: node to test
 * @compat: compatible string to compare with compatible list.
 *  * On match, returns a non-zero value with smaller values returned for more
 * specific compatible values.
 */
static int of_fdt_is_compatible(const void *blob,
		      unsigned long node, const char *compat)
{
	const char *cp;
	int cplen;
	unsigned long l, score = 0;

	cp = fdt_getprop(blob, node, "compatible", &cplen);
	if (cp == NULL)
		return 0;
	while (cplen > 0) {
		score++;
		if (of_compat_cmp(cp, compat, strlen(compat)) == 0)
			return score;
		l = strlen(cp) + 1;
		cp += l;
		cplen -= l;
	}

	return 0;
}

2.4 对设备树中运行时配置信息的处理

该部分的处理放在early_init_dt_scan_nodes函数中进行，主要做了下面三件事情。

• /chosen节点中bootargs属性的值, 存入全局变量： boot_command_line
• 确定根节点的这2个属性的值: #address-cells, #size-cells 存入全局变量:
  dt_root_addr_cells, dt_root_size_cells
• 解析/memory中的reg属性, 提取出"base, size", 最终调用memblock_add(base, size);

2.4.1 函数调用过程

函数调用过程:
start_kernel // init/main.c
    setup_arch(&command_line);  // arch/arm/kernel/setup.c
        mdesc = setup_machine_fdt(__atags_pointer);  // arch/arm/kernel/devtree.c
                    early_init_dt_scan_nodes();      // drivers/of/ftd.c
                        /* Retrieve various information from the /chosen node */
                        of_scan_flat_dt(early_init_dt_scan_chosen, boot_command_line);

                        /* Initialize {size,address}-cells info */
                        of_scan_flat_dt(early_init_dt_scan_root, NULL);

                        /* Setup memory, calling early_init_dt_add_memory_arch */
                        of_scan_flat_dt(early_init_dt_scan_memory, NULL);

2.4.2 early_init_dt_scan_nodes

• early_init_dt_scan_chosen Retrieve various information from the /chosen node
• early_init_dt_scan_root Initialize {size,address}-cells info
• early_init_dt_scan_memory Setup memory, calling early_init_dt_add_memory_arch

void __init early_init_dt_scan_nodes(void)
{
	int rc = 0;

	/* Retrieve various information from the /chosen node */
	rc = of_scan_flat_dt(early_init_dt_scan_chosen, boot_command_line);
	if (!rc)
		pr_warn("No chosen node found, continuing without\n");

	/* Initialize {size,address}-cells info */
	of_scan_flat_dt(early_init_dt_scan_root, NULL);

	/* Setup memory, calling early_init_dt_add_memory_arch */
	of_scan_flat_dt(early_init_dt_scan_memory, NULL);
}

2.4.3 of_scan_flat_dt

扫描扁平化的设备树，并对每个blob调用回调函数记性对应的数据解析。

/**
 * of_scan_flat_dt - scan flattened tree blob and call callback on each.
 * @it: callback function
 * @data: context data pointer
 *  * This function is used to scan the flattened device-tree, it is
 * used to extract the memory information at boot before we can
 * unflatten the tree
 */
int __init of_scan_flat_dt(int (*it)(unsigned long node,
				     const char *uname, int depth,
				     void *data),
			   void *data)
{
	const void *blob = initial_boot_params;
	const char *pathp;
	int offset, rc = 0, depth = -1;

	if (!blob)
		return 0;

	for (offset = fdt_next_node(blob, -1, &depth);
	     offset >= 0 && depth >= 0 && !rc;
	     offset = fdt_next_node(blob, offset, &depth)) {

		pathp = fdt_get_name(blob, offset, NULL);
		if (*pathp == '/')
			pathp = kbasename(pathp);
		rc = it(offset, pathp, depth, data);
	}
	return rc;
}

2.4.4 early_init_dt_scan_chosen

解析/chosen节点的信息，将其放入boot_command_line全局变量中。
data代表的就是boot_command_line。

• early_init_dt_check_for_initrd Decode initrd location from flat tree
• p = of_get_flat_dt_prop(node, "bootargs", &l);
• rng_seed = of_get_flat_dt_prop(node, "rng-seed", &l);
• fdt_nop_property(initial_boot_params, node, "rng-seed");

/* Retrieve various information from the /chosen node */
int __init early_init_dt_scan_chosen(unsigned long node, const char *uname,
				     int depth, void *data)
{
	int l;
	const char *p;
	const void *rng_seed;

	pr_debug("search \"chosen\", depth: %d, uname: %s\n", depth, uname);

	if (depth != 1 || !data ||
	    (strcmp(uname, "chosen") != 0 && strcmp(uname, "chosen@0") != 0))
		return 0;

	early_init_dt_check_for_initrd(node);

	/* Retrieve command line */
	p = of_get_flat_dt_prop(node, "bootargs", &l);
	if (p != NULL && l > 0)
		strlcpy(data, p, min(l, COMMAND_LINE_SIZE));

	/*
	 * CONFIG_CMDLINE is meant to be a default in case nothing else
	 * managed to set the command line, unless CONFIG_CMDLINE_FORCE
	 * is set in which case we override whatever was found earlier.
	 */
#ifdef CONFIG_CMDLINE
#if defined(CONFIG_CMDLINE_EXTEND)
	strlcat(data, " ", COMMAND_LINE_SIZE);
	strlcat(data, CONFIG_CMDLINE, COMMAND_LINE_SIZE);
#elif defined(CONFIG_CMDLINE_FORCE)
	strlcpy(data, CONFIG_CMDLINE, COMMAND_LINE_SIZE);
#else
	/* No arguments from boot loader, use kernel's  cmdl*/
	if (!((char *)data)[0])
		strlcpy(data, CONFIG_CMDLINE, COMMAND_LINE_SIZE);
#endif
#endif /* CONFIG_CMDLINE */

	pr_debug("Command line is: %s\n", (char*)data);

	rng_seed = of_get_flat_dt_prop(node, "rng-seed", &l);
	if (rng_seed && l > 0) {
		add_bootloader_randomness(rng_seed, l);

		/* try to clear seed so it won't be found. */
		fdt_nop_property(initial_boot_params, node, "rng-seed");

		/* update CRC check value */
		of_fdt_crc32 = crc32_be(~0, initial_boot_params,
				fdt_totalsize(initial_boot_params));
	}

	/* break now */
	return 1;
}

2.4.5 early_init_dt_scan_root

获取设备树根节点下的的#size-cells和#address-cells信息

/**
 * early_init_dt_scan_root - fetch the top level address and size cells
 */
int __init early_init_dt_scan_root(unsigned long node, const char *uname,
				   int depth, void *data)
{
	const __be32 *prop;

	if (depth != 0)
		return 0;

	dt_root_size_cells = OF_ROOT_NODE_SIZE_CELLS_DEFAULT;
	dt_root_addr_cells = OF_ROOT_NODE_ADDR_CELLS_DEFAULT;

	prop = of_get_flat_dt_prop(node, "#size-cells", NULL);
	if (prop)
		dt_root_size_cells = be32_to_cpup(prop);
	pr_debug("dt_root_size_cells = %x\n", dt_root_size_cells);

	prop = of_get_flat_dt_prop(node, "#address-cells", NULL);
	if (prop)
		dt_root_addr_cells = be32_to_cpup(prop);
	pr_debug("dt_root_addr_cells = %x\n", dt_root_addr_cells);

	/* break now */
	return 1;
}

2.4.6 early_init_dt_scan_memory

遍历并解析内存节点（memory nodes），最终将解析出的memory node内存节点通过early_init_dt_add_memory_arch函数调用memblock_add(base, size);添加到系统中。

/**
 * early_init_dt_scan_memory - Look for and parse memory nodes
 */
int __init early_init_dt_scan_memory(unsigned long node, const char *uname,
				     int depth, void *data)
{
	const char *type = of_get_flat_dt_prop(node, "device_type", NULL);
	const __be32 *reg, *endp;
	int l;
	bool hotpluggable;

	/* We are scanning "memory" nodes only */
	if (type == NULL || strcmp(type, "memory") != 0)
		return 0;

	reg = of_get_flat_dt_prop(node, "linux,usable-memory", &l);
	if (reg == NULL)
		reg = of_get_flat_dt_prop(node, "reg", &l);
	if (reg == NULL)
		return 0;

	endp = reg + (l / sizeof(__be32));
	hotpluggable = of_get_flat_dt_prop(node, "hotpluggable", NULL);

	pr_debug("memory scan node %s, reg size %d,\n", uname, l);

	while ((endp - reg) >= (dt_root_addr_cells + dt_root_size_cells)) {
		u64 base, size;

		base = dt_mem_next_cell(dt_root_addr_cells, &reg);
		size = dt_mem_next_cell(dt_root_size_cells, &reg);

		if (size == 0)
			continue;
		pr_debug(" - %llx ,  %llx\n", (unsigned long long)base,
		    (unsigned long long)size);

		early_init_dt_add_memory_arch(base, size);

		if (!hotpluggable)
			continue;

		if (early_init_dt_mark_hotplug_memory_arch(base, size))
			pr_warn("failed to mark hotplug range 0x%llx - 0x%llx\n",
				base, base + size);
	}

	return 0;
}

2.5 dtb转换为device_node

2.5.1 函数调用过程

start_kernel // init/main.c
    setup_arch(&command_line);  // arch/arm/kernel/setup.c
        arm_memblock_init(mdesc);   // arch/arm/kernel/setup.c
            early_init_fdt_reserve_self();
                    /* Reserve the dtb region */
                    // 把DTB所占区域保留下来, 即调用: memblock_reserve
                    early_init_dt_reserve_memory_arch(__pa(initial_boot_params),
                                      fdt_totalsize(initial_boot_params),
                                      0);           
            early_init_fdt_scan_reserved_mem();  // 根据dtb中的memreserve信息, 调用memblock_reserve
            
        unflatten_device_tree();    // arch/arm/kernel/setup.c
            __unflatten_device_tree(initial_boot_params, NULL, &of_root,
                        early_init_dt_alloc_memory_arch, false);            // drivers/of/fdt.c
                
                /* First pass, scan for size */
                size = unflatten_dt_nodes(blob, NULL, dad, NULL);
                
                /* Allocate memory for the expanded device tree */
                mem = dt_alloc(size + 4, __alignof__(struct device_node));
                
                /* Second pass, do actual unflattening */
                unflatten_dt_nodes(blob, mem, dad, mynodes);
                    populate_node
                        np = unflatten_dt_alloc(mem, sizeof(struct device_node) + allocl,
                                    __alignof__(struct device_node));
                        
                        np->full_name = fn = ((char *)np) + sizeof(*np);
                        
                        populate_properties
                                pp = unflatten_dt_alloc(mem, sizeof(struct property),
                                            __alignof__(struct property));
                            
                                pp->name   = (char *)pname;
                                pp->length = sz;
                                pp->value  = (__be32 *)val;

开发者涨薪指南

48位大咖的思考法则、工作方式、逻辑体系