Linux kernel memory management source code analysis of init-mm.c (2)

Continued from the previous article: Linux kernel memory management source code analysis of init-mm.c (1)

Reference for the content of this article: https://www.cnblogs.com/mysky007/p/12317831.html

Last time I talked about swapper_pg_dir and init_top_gpt. Give the description of init_top_gpt in the kernel source code again, in Documentation/admin-guide/kdump/vmcoreinfo.rst:

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.

As can be seen from the above introduction, init_top_pgt is unique to the x86 architecture.

kernel page table

Unlike the user-mode page table, the kernel page table is created when the system is initialized. swapper_pg_dir points to the top-level directory pgd of the kernel, which is the root of the kernel page table.

The previous article has pointed out that swapper_pg_dir is a macro definition, and this article will look at more related content. In arch/x86/include/asm/pgtable_64.h, the code is as follows:

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

In the above code, in addition to swapper_pg_dir pointing to the top-level directory pgd of the kernel, several page table directories appear at the same time. in:

XXX_ident_pgt - corresponds to the direct mapping area;

XXX_kernel_pgt —— corresponds to the kernel code area;

XXX_fixmap_pgt —— corresponds to the fixed map area.

So where are the variables init_top_gpt and XXX_ident_pgt, XXX_kernel_pgt, XXX_fixmap_pgt initialized? is in arch/x86/kernel/head_64.S:

	__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)

As shown below: 

The kernel page table top-level directory init_top_pgt includes 3 items:

（1） level3_ident_pgt

That is, the third-level directory of the page table of the direct mapping area. Because level3_ident_pgt is defined in the kernel code segment of the virtual address (when writing code, all virtual addresses are used, and no one can know what the physical address will be loaded in the future), and __START_KERNEL_map is the virtual address space The starting address of the kernel code segment, so level3_ident_pgt minus __START_KERNEL_map is converted into a physical address.

（2）PGD_PAGE_OFFSET

__PAGE_OFFSET_BASE is the starting address of the kernel in the virtual address space. The second item also points to level3_ident_pgt, the direct mapping area.

（3）level3_kernel_pgt

Kernel code area.