Linux内核内存管理源码分析之init-mm.c（2）

接前一篇文章：Linux内核内存管理源码分析之init-mm.c（1）

本文内容参考：https://www.cnblogs.com/mysky007/p/12317831.html

上回说到了swapper_pg_dir和init_top_gpt。再次给出内核源码中init_top_gpt的说明，在Documentation/admin-guide/kdump/vmcoreinfo.rst中：

init_top_pgt
------------
 
Used to walk through the whole page table and convert virtual addresses
to physical addresses. The init_top_pgt is somewhat similar to
swapper_pg_dir, but it is only used in x86_64.

由以上介绍可以看到，init_top_pgt是x86架构所独有的。

内核页表

和用户态页表不同，在系统初始化的时候，就要创建内核页表了。swapper_pg_dir指向内核最顶级的目录pgd，也就是内核页表的根。

前文已经指出了swapper_pg_dir是宏定义，本文来看更多相关内容。在arch/x86/include/asm/pgtable_64.h中，代码如下：

extern p4d_t level4_kernel_pgt[512];
extern p4d_t level4_ident_pgt[512];
extern pud_t level3_kernel_pgt[512];
extern pud_t level3_ident_pgt[512];
extern pmd_t level2_kernel_pgt[512];
extern pmd_t level2_fixmap_pgt[512];
extern pmd_t level2_ident_pgt[512];
extern pte_t level1_fixmap_pgt[512 * FIXMAP_PMD_NUM];
extern pgd_t init_top_pgt[];

#define swapper_pg_dir init_top_pgt

上述代码中，除了swapper_pg_dir 指向内核最顶级的目录pgd外，同时出现的还有几个页表目录。其中：

XXX_ident_pgt —— 对应的是直接映射区；

XXX_kernel_pgt —— 对应的是内核代码区；

XXX_fixmap_pgt —— 对应的是固定映射区。

那么init_top_gpt以及XXX_ident_pgt、XXX_kernel_pgt、XXX_fixmap_pgt这些变量都是在哪里初始化的呢？是在arch/x86/kernel/head_64.S中：

	__INITDATA
	.balign 4

SYM_DATA_START_PTI_ALIGNED(early_top_pgt)
	.fill	512,8,0
	.fill	PTI_USER_PGD_FILL,8,0
SYM_DATA_END(early_top_pgt)

SYM_DATA_START_PAGE_ALIGNED(early_dynamic_pgts)
	.fill	512*EARLY_DYNAMIC_PAGE_TABLES,8,0
SYM_DATA_END(early_dynamic_pgts)

SYM_DATA(early_recursion_flag, .long 0)

	.data

#if defined(CONFIG_XEN_PV) || defined(CONFIG_PVH)
SYM_DATA_START_PTI_ALIGNED(init_top_pgt)
	.quad   level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC
	.org    init_top_pgt + L4_PAGE_OFFSET*8, 0
	.quad   level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC
	.org    init_top_pgt + L4_START_KERNEL*8, 0
	/* (2^48-(2*1024*1024*1024))/(2^39) = 511 */
	.quad   level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC
	.fill	PTI_USER_PGD_FILL,8,0
SYM_DATA_END(init_top_pgt)

SYM_DATA_START_PAGE_ALIGNED(level3_ident_pgt)
	.quad	level2_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC
	.fill	511, 8, 0
SYM_DATA_END(level3_ident_pgt)
SYM_DATA_START_PAGE_ALIGNED(level2_ident_pgt)
	/*
	 * Since I easily can, map the first 1G.
	 * Don't set NX because code runs from these pages.
	 *
	 * Note: This sets _PAGE_GLOBAL despite whether
	 * the CPU supports it or it is enabled.  But,
	 * the CPU should ignore the bit.
	 */
	PMDS(0, __PAGE_KERNEL_IDENT_LARGE_EXEC, PTRS_PER_PMD)
SYM_DATA_END(level2_ident_pgt)
#else
SYM_DATA_START_PTI_ALIGNED(init_top_pgt)
	.fill	512,8,0
	.fill	PTI_USER_PGD_FILL,8,0
SYM_DATA_END(init_top_pgt)
#endif

#ifdef CONFIG_X86_5LEVEL
SYM_DATA_START_PAGE_ALIGNED(level4_kernel_pgt)
	.fill	511,8,0
	.quad	level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC
SYM_DATA_END(level4_kernel_pgt)
#endif

SYM_DATA_START_PAGE_ALIGNED(level3_kernel_pgt)
	.fill	L3_START_KERNEL,8,0
	/* (2^48-(2*1024*1024*1024)-((2^39)*511))/(2^30) = 510 */
	.quad	level2_kernel_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC
	.quad	level2_fixmap_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC
SYM_DATA_END(level3_kernel_pgt)

SYM_DATA_START_PAGE_ALIGNED(level2_kernel_pgt)
	/*
	 * Kernel high mapping.
	 *
	 * The kernel code+data+bss must be located below KERNEL_IMAGE_SIZE in
	 * virtual address space, which is 1 GiB if RANDOMIZE_BASE is enabled,
	 * 512 MiB otherwise.
	 *
	 * (NOTE: after that starts the module area, see MODULES_VADDR.)
	 *
	 * This table is eventually used by the kernel during normal runtime.
	 * Care must be taken to clear out undesired bits later, like _PAGE_RW
	 * or _PAGE_GLOBAL in some cases.
	 */
	PMDS(0, __PAGE_KERNEL_LARGE_EXEC, KERNEL_IMAGE_SIZE/PMD_SIZE)
SYM_DATA_END(level2_kernel_pgt)

SYM_DATA_START_PAGE_ALIGNED(level2_fixmap_pgt)
	.fill	(512 - 4 - FIXMAP_PMD_NUM),8,0
	pgtno = 0
	.rept (FIXMAP_PMD_NUM)
	.quad level1_fixmap_pgt + (pgtno << PAGE_SHIFT) - __START_KERNEL_map \
		+ _PAGE_TABLE_NOENC;
	pgtno = pgtno + 1
	.endr
	/* 6 MB reserved space + a 2MB hole */
	.fill	4,8,0
SYM_DATA_END(level2_fixmap_pgt)

SYM_DATA_START_PAGE_ALIGNED(level1_fixmap_pgt)
	.rept (FIXMAP_PMD_NUM)
	.fill	512,8,0
	.endr
SYM_DATA_END(level1_fixmap_pgt)

#undef PMDS

	.data
	.align 16

SYM_DATA(early_gdt_descr,		.word GDT_ENTRIES*8-1)
SYM_DATA_LOCAL(early_gdt_descr_base,	.quad INIT_PER_CPU_VAR(gdt_page))

	.align 16
/* This must match the first entry in level2_kernel_pgt */
SYM_DATA(phys_base, .quad 0x0)
EXPORT_SYMBOL(phys_base)

如下图所示：

内核页表顶级目录 init_top_pgt包括3项：

（1） level3_ident_pgt

即直接映射区页表的三级目录。因为level3_ident_pgt是定义在虚拟地址的内核代码段里的（写代码的时候，使用的都是虚拟地址，此时谁也不无法知道将来加载的物理地址是多少），而 __START_KERNEL_map正是虚拟地址空间的内核代码段的起始地址，因此level3_ident_pgt减去__START_KERNEL_map才转换为物理地址。

（2）PGD_PAGE_OFFSET

__PAGE_OFFSET_BASE 是虚拟地址空间里面内核的起始地址。第二项也指向 level3_ident_pgt，直接映射区。

（3）level3_kernel_pgt

内核代码区。