Linux 内核 内存管理Linux 内核内存布局 ④ ( ARM64 架构体系内存分布 | 内核启动源码 start_kernel | 内存初始化 mm_init | mem_init )

Posted 2022-04-09 韩曙亮

文章目录

• 一、ARM64 架构体系内存分布
• 二、Linux 内核启动源码 start_kernel
• 三、内存初始化源码 mm_init
• 四、内存初始化源码 mem_init

一、ARM64 架构体系内存分布

---

ARM64 架构 的 " 物理地址 " 有 $48$ 位 , 理论上最大 " 寻址空间 " 为 $256$ TB ;

ARM64 架构 的 " 虚拟地址 " 也是 最大支持 $48$ 位 寻址地址 ;

Linux 内核 将 " 地址空间 " 划分为 : 内核空间 和 用户空间 ;

① 内核空间 ( Kernel Space ) : 寻址范围 0x FFFF 0000 0000 0000 ~ 0x FFFF FFFF FFFF FFFF ;

② 用户空间 ( User Space ) : 寻址范围 0x 0000 0000 0000 0000 ~ 0x 0000 FFFF FFFF FFFF ;

如下图所示 :

上图中的 " 不规范地址空间 " 是不允许使用的 内存空间 ;

二、Linux 内核启动源码 start_kernel

---

在 Linux 内核初始化完成后 , 会在 " 初始化内存 " 时 , 输出 内存布局 ;

Linux 内核启动源码是定义在 linux-5.6.18\\init\\main.c 源码中的

asmlinkage __visible void __init start_kernel(void)

函数 ;

在 Linux 内核启动方法 中 , 调用了 mm_init(); 方法 , 参考路径 : linux-5.6.18\\init\\main.c#878

asmlinkage __visible void __init start_kernel(void)

	// ...
	/*
	 * These use large bootmem allocations and must precede
	 * kmem_cache_init()
	 */
	setup_log_buf(0);
	vfs_caches_init_early();
	sort_main_extable();
	trap_init();
	mm_init();
	// ...

Linux 内核 启动源码 ( 仅做参考 ) :

asmlinkage __visible void __init start_kernel(void)

	char *command_line;
	char *after_dashes;

	set_task_stack_end_magic(&init_task);
	smp_setup_processor_id();
	debug_objects_early_init();

	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(command_line);
	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();

	build_all_zonelists(NULL);
	page_alloc_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);
	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);

	/*
	 * These use large bootmem allocations and must precede
	 * kmem_cache_init()
	 */
	setup_log_buf(0);
	vfs_caches_init_early();
	sort_main_extable();
	trap_init();
	mm_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();
	/*
	 * 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();
	radix_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();
	hrtimers_init();
	softirq_init();
	timekeeping_init();

	/*
	 * For best initial stack canary entropy, prepare it after:
	 * - setup_arch() for any UEFI RNG entropy and boot cmdline access
	 * - timekeeping_init() for ktime entropy used in rand_initialize()
	 * - rand_initialize() to get any arch-specific entropy like RDRAND
	 * - add_latent_entropy() to get any latent entropy
	 * - adding command line entropy
	 */
	rand_initialize();
	add_latent_entropy();
	add_device_randomness(command_line, strlen(command_line));
	boot_init_stack_canary();

	time_init();
	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();

	/*
	 * This needs to be called before any devices perform DMA
	 * operations that might use the SWIOTLB bounce buffers. It will
	 * mark the bounce buffers as decrypted so that their usage will
	 * not cause "plain-text" data to be decrypted when accessed.
	 */
	mem_encrypt_init();

#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();
	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();
	buffer_init();
	key_init();
	security_init();
	dbg_late_init();
	vfs_caches_init();
	pagecache_init();
	signals_init();
	seq_file_init();
	proc_root_init();
	nsfs_init();
	cpuset_init();
	cgroup_init();
	taskstats_init_early();
	delayacct_init();

	poking_init();
	check_bugs();

	acpi_subsystem_init();
	arch_post_acpi_subsys_init();
	sfi_init_late();

	/* Do the rest non-__init'ed, we're now alive */
	arch_call_rest_init();

	prevent_tail_call_optimization();

源码路径 : linux-5.6.18\\init\\main.c#822

三、内存初始化源码 mm_init

---

mm_init 方法在 linux-5.6.18\\init\\main.c#795 定义 ,

/*
 * Set up kernel memory allocators
 */
static void __init mm_init(void)

	/*
	 * page_ext requires contiguous pages,
	 * bigger than MAX_ORDER unless SPARSEMEM.
	 */
	page_ext_init_flatmem();
	init_debug_pagealloc();
	report_meminit();
	mem_init();
	kmem_cache_init();
	kmemleak_init();
	pgtable_init();
	debug_objects_mem_init();
	vmalloc_init();
	ioremap_huge_init();
	/* Should be run before the first non-init thread is created */
	init_espfix_bsp();
	/* Should be run after espfix64 is set up. */
	pti_init();

源码路径 : linux-5.6.18\\init\\main.c#795

四、内存初始化源码 mem_init

---

在 linux-5.6.18\\init\\main.c#795 定义的 mm_init 方法 中 , 调用了 mem_init 方法初始化内存 , 该方法定义在 arch\\x86\\mm\\init_32.c#766 位置 ;

在内存初始化时 , 会打印如下格式的 " 内核空间 内存分布 " 日志 :

	printk(KERN_INFO "virtual kernel memory layout:\\n"
		"    fixmap  : 0x%08lx - 0x%08lx   (%4ld kB)\\n"
		"  cpu_entry : 0x%08lx - 0x%08lx   (%4ld kB)\\n"
#ifdef CONFIG_HIGHMEM
		"    pkmap   : 0x%08lx - 0x%08lx   (%4ld kB)\\n"
#endif
		"    vmalloc : 0x%08lx - 0x%08lx   (%4ld MB)\\n"
		"    lowmem  : 0x%08lx - 0x%08lx   (%4ld MB)\\n"
		"      .init : 0x%08lx - 0x%08lx   (%4ld kB)\\n"
		"      .data : 0x%08lx - 0x%08lx   (%4ld kB)\\n"
		"      .text : 0x%08lx - 0x%08lx   (%4ld kB)\\n",

mem_init 源码 :

void __init mem_init(void)

	pci_iommu_alloc();

#ifdef CONFIG_FLATMEM
	BUG_ON(!mem_map);
#endif
	/*
	 * With CONFIG_DEBUG_PAGEALLOC initialization of highmem pages has to
	 * be done before memblock_free_all(). Memblock use free low memory for
	 * temporary data (see find_range_array()) and for this purpose can use
	 * pages that was already passed to the buddy allocator, hence marked as
	 * not accessible in the page tables when compiled with
	 * CONFIG_DEBUG_PAGEALLOC. Otherwise order of initialization is not
	 * important here.
	 */
	set_highmem_pages_init();

	/* this will put all low memory onto the freelists */
	memblock_free_all();

	after_bootmem = 1;
	x86_init.hyper.init_after_bootmem();

	mem_init_print_info(NULL);
	printk(KERN_INFO "virtual kernel memory layout:\\n"
		"    fixmap  : 0x%08lx - 0x%08lx   (%4ld kB)\\n"
		"  cpu_entry : 0x%08lx - 0x%08lx   (%4ld kB)\\n"
#ifdef CONFIG_HIGHMEM
		"    pkmap   : 0x%08lx - 0x%08lx   (%4ld kB)\\n"
#endif
		"    vmalloc : 0x%08lx - 0x%08lx   (%4ld MB)\\n"
		"    lowmem  : 0x%08lx - 0x%08lx   (%4ld MB)\\n"
		"      .init : 0x%08lx - 0x%08lx   (%4ld kB)\\n"
		"      .data : 0x%08lx - 0x%08lx   (%4ld kB)\\n"
		"      .text : 0x%08lx - 0x%08lx   (%4ld kB)\\n",
		FIXADDR_START, FIXADDR_TOP,
		(FIXADDR_TOP - FIXADDR_START) >> 10,

		CPU_ENTRY_AREA_BASE,
		CPU_ENTRY_AREA_BASE + CPU_ENTRY_AREA_MAP_SIZE,
		CPU_ENTRY_AREA_MAP_SIZE >> 10,

#ifdef CONFIG_HIGHMEM
		PKMAP_BASE, PKMAP_BASE+LAST_PKMAP*PAGE_SIZE,
		(LAST_PKMAP*PAGE_SIZE) >> 10,
#endif

		VMALLOC_START, VMALLOC_END,
		(VMALLOC_END - VMALLOC_START) >> 20,

		(unsigned long)__va(0), (unsigned long)high_memory,
		((unsigned long)high_memory - (unsigned long)__va(0)) >> 20,

		(unsigned long)&__init_begin, (unsigned long)&__init_end,
		((unsigned long)&__init_end -
		 (unsigned long)&__init_begin) >> 10,

		(unsigned long)&_etext, (unsigned long)&_edata,
		((unsigned long)&_edata - (unsigned long)&_etext) >> 10,

		(unsigned long)&_text, (unsigned long)&_etext,
		((unsigned long)&_etext - (unsigned long)&_text) >> 10);

	/*
	 * Check boundaries twice: Some fundamental inconsistencies can
	 * be detected at build time already.
	 */
#define __FIXADDR_TOP (-PAGE_SIZE)
#ifdef CONFIG_HIGHMEM
	BUILD_BUG_ON(PKMAP_BASE + LAST_PKMAP*PAGE_SIZE	> FIXADDR_START);
	BUILD_BUG_ON(VMALLOC_END			> PKMAP_BASE);
#endif
#define high_memory (-128UL << 20)
	BUILD_BUG_ON(VMALLOC_START			>= VMALLOC_END);
#undef high_memory
#undef __FIXADDR_TOP

#ifdef CONFIG_HIGHMEM
	BUG_ON(PKMAP_BASE + LAST_PKMAP*PAGE_SIZE	> FIXADDR_START);
	BUG_ON(VMALLOC_END				> PKMAP_BASE);
#endif
	BUG_ON(VMALLOC_START				>= VMALLOC_END);
	BUG_ON((unsigned long)high_memory		> VMALLOC_START);

	test_wp_bit();