linux kernel启动过程中初始化mem_types，据此创建内核页表

linux booting过程中会打印内存属性信息，例如：

OF: fdt: Machine model: V2P-CA9
Memory policy: Data cache writealloc

来自函数build_mem_type_table(void)，调用流程如下：

setup_arch
  |
  #ifdef CONFIG_MMU
    early_mm_init(mdesc);
  #endif
    |
    early_mm_init()
      |
      build_mem_type_table();

build_mem_type_table()根据CPU架构类型初始化PMD和PTE的属性信息。后期创建PMD和PTE时会使用到该阶段的mem_types数据结构。

author	Russell King <rmk@dyn-67.arm.linux.org.uk>	2007-04-21 10:47:29 +0100
committer	Russell King <rmk+kernel@arm.linux.org.uk>	2007-04-21 20:36:00 +0100
commit	b29e9f5e64fb90d2e4be1c7ef8c925b56669c74a (patch)
tree	99331c544296b82abe31c55e6bca1ae37dd142c5 /arch/arm/mm/mm.h
parent	24e6c6996fb6e0e716c1dda1def1bb023a0fe43b (diff)
download	linux-b29e9f5e64fb90d2e4be1c7ef8c925b56669c74a.tar.gz
[ARM] mm 5: Use mem_types table in ioremap
We really want to be using the memory type table in ioremap, so we
only have to do the CPU type fixups in one place.

Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>

Diffstat (limited to 'arch/arm/mm/mm.h')
-rw-r--r--	arch/arm/mm/mm.h	9	
		
1 files changed, 9 insertions, 0 deletions
diff --git a/arch/arm/mm/mm.h b/arch/arm/mm/mm.h
index a44e309706354..66f8612c5e5b9 100644
--- a/arch/arm/mm/mm.h
+++ b/arch/arm/mm/mm.h
@@ -16,6 +16,15 @@ static inline pmd_t *pmd_off_k(unsigned long virt)
 	return pmd_off(pgd_offset_k(virt), virt);
 }
 
+struct mem_type {
+	unsigned int prot_pte;
+	unsigned int prot_l1;
+	unsigned int prot_sect;
+	unsigned int domain;
+};
+
+const struct mem_type *get_mem_type(unsigned int type);
+
 #endif
 
 struct map_desc;

struct mem_type定义如下：

struct mem_type {
	pteval_t prot_pte;
	pteval_t prot_pte_s2;
	pmdval_t prot_l1;
	pmdval_t prot_sect;
	unsigned int domain;
};

从commit信息中可以看到，struct mem_type最初的目的是给ioremap使用的，因此增加了struct mem_type以及get_mem_type()。

static void __iomem * __arm_ioremap_pfn_caller(unsigned long pfn,
	unsigned long offset, size_t size, unsigned int mtype, void *caller)
{
	const struct mem_type *type;
	int err;
	unsigned long addr;
	struct vm_struct *area;
	phys_addr_t paddr = __pfn_to_phys(pfn);

#ifndef CONFIG_ARM_LPAE
	/*
	 * High mappings must be supersection aligned
	 */
	if (pfn >= 0x100000 && (paddr & ~SUPERSECTION_MASK))
		return NULL;
#endif

	type = get_mem_type(mtype);
	if (!type)
		return NULL;

	/*
	 * Page align the mapping size, taking account of any offset.
	 */
	size = PAGE_ALIGN(offset + size);

	/*
	 * Try to reuse one of the static mapping whenever possible.
	 */
	if (size && !(sizeof(phys_addr_t) == 4 && pfn >= 0x100000)) {
		struct static_vm *svm;

		svm = find_static_vm_paddr(paddr, size, mtype);
		if (svm) {
			addr = (unsigned long)svm->vm.addr;
			addr += paddr - svm->vm.phys_addr;
			return (void __iomem *) (offset + addr);
		}
	}

	/*
	 * Don't allow RAM to be mapped with mismatched attributes - this
	 * causes problems with ARMv6+
	 */
	if (WARN_ON(pfn_valid(pfn) && mtype != MT_MEMORY_RW))
		return NULL;

	area = get_vm_area_caller(size, VM_IOREMAP, caller);
 	if (!area)
 		return NULL;
 	addr = (unsigned long)area->addr;
	area->phys_addr = paddr;

#if !defined(CONFIG_SMP) && !defined(CONFIG_ARM_LPAE)
	if (DOMAIN_IO == 0 &&
	    (((cpu_architecture() >= CPU_ARCH_ARMv6) && (get_cr() & CR_XP)) ||
	       cpu_is_xsc3()) && pfn >= 0x100000 &&
	       !((paddr | size | addr) & ~SUPERSECTION_MASK)) {
		area->flags |= VM_ARM_SECTION_MAPPING;
		err = remap_area_supersections(addr, pfn, size, type);
	} else if (!((paddr | size | addr) & ~PMD_MASK)) {
		area->flags |= VM_ARM_SECTION_MAPPING;
		err = remap_area_sections(addr, pfn, size, type);
	} else
#endif
		err = ioremap_page_range(addr, addr + size, paddr,
					 __pgprot(type->prot_pte));

	if (err) {
 		vunmap((void *)addr);
 		return NULL;
 	}

	flush_cache_vmap(addr, addr + size);
	return (void __iomem *) (offset + addr);
}

到目前为止，这个数据结构的作用已经不仅限上面提及的内容。更为主要的作用是根据mem类型创建内核页表。

static struct mem_type mem_types[] __ro_after_init = {
	[MT_DEVICE] = {		  /* Strongly ordered / ARMv6 shared device */
		.prot_pte	= PROT_PTE_DEVICE | L_PTE_MT_DEV_SHARED |
				  L_PTE_SHARED,
		.prot_pte_s2	= s2_policy(PROT_PTE_S2_DEVICE) |
				  s2_policy(L_PTE_S2_MT_DEV_SHARED) |
				  L_PTE_SHARED,
		.prot_l1	= PMD_TYPE_TABLE,
		.prot_sect	= PROT_SECT_DEVICE | PMD_SECT_S,
		.domain		= DOMAIN_IO,
	},
	[MT_DEVICE_NONSHARED] = { /* ARMv6 non-shared device */
		.prot_pte	= PROT_PTE_DEVICE | L_PTE_MT_DEV_NONSHARED,
		.prot_l1	= PMD_TYPE_TABLE,
		.prot_sect	= PROT_SECT_DEVICE,
		.domain		= DOMAIN_IO,
	},
	[MT_DEVICE_CACHED] = {	  /* ioremap_cached */
		.prot_pte	= PROT_PTE_DEVICE | L_PTE_MT_DEV_CACHED,
		.prot_l1	= PMD_TYPE_TABLE,
		.prot_sect	= PROT_SECT_DEVICE | PMD_SECT_WB,
		.domain		= DOMAIN_IO,
	},
	[MT_DEVICE_WC] = {	/* ioremap_wc */
		.prot_pte	= PROT_PTE_DEVICE | L_PTE_MT_DEV_WC,
		.prot_l1	= PMD_TYPE_TABLE,
		.prot_sect	= PROT_SECT_DEVICE,
		.domain		= DOMAIN_IO,
	},
	[MT_UNCACHED] = {
		.prot_pte	= PROT_PTE_DEVICE,
		.prot_l1	= PMD_TYPE_TABLE,
		.prot_sect	= PMD_TYPE_SECT | PMD_SECT_XN,
		.domain		= DOMAIN_IO,
	},
	[MT_CACHECLEAN] = {
		.prot_sect = PMD_TYPE_SECT | PMD_SECT_XN,
		.domain    = DOMAIN_KERNEL,
	},
#ifndef CONFIG_ARM_LPAE
	[MT_MINICLEAN] = {
		.prot_sect = PMD_TYPE_SECT | PMD_SECT_XN | PMD_SECT_MINICACHE,
		.domain    = DOMAIN_KERNEL,
	},
#endif
	[MT_LOW_VECTORS] = {
		.prot_pte  = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY |
				L_PTE_RDONLY,
		.prot_l1   = PMD_TYPE_TABLE,
		.domain    = DOMAIN_VECTORS,
	},
	[MT_HIGH_VECTORS] = {
		.prot_pte  = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY |
				L_PTE_USER | L_PTE_RDONLY,
		.prot_l1   = PMD_TYPE_TABLE,
		.domain    = DOMAIN_VECTORS,
	},
	[MT_MEMORY_RWX] = {
		.prot_pte  = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY,
		.prot_l1   = PMD_TYPE_TABLE,
		.prot_sect = PMD_TYPE_SECT | PMD_SECT_AP_WRITE,
		.domain    = DOMAIN_KERNEL,
	},
	[MT_MEMORY_RW] = {
		.prot_pte  = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY |
			     L_PTE_XN,
		.prot_l1   = PMD_TYPE_TABLE,
		.prot_sect = PMD_TYPE_SECT | PMD_SECT_AP_WRITE,
		.domain    = DOMAIN_KERNEL,
	},
	[MT_ROM] = {
		.prot_sect = PMD_TYPE_SECT,
		.domain    = DOMAIN_KERNEL,
	},
	[MT_MEMORY_RWX_NONCACHED] = {
		.prot_pte  = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY |
				L_PTE_MT_BUFFERABLE,
		.prot_l1   = PMD_TYPE_TABLE,
		.prot_sect = PMD_TYPE_SECT | PMD_SECT_AP_WRITE,
		.domain    = DOMAIN_KERNEL,
	},
	[MT_MEMORY_RW_DTCM] = {
		.prot_pte  = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY |
				L_PTE_XN,
		.prot_l1   = PMD_TYPE_TABLE,
		.prot_sect = PMD_TYPE_SECT | PMD_SECT_XN,
		.domain    = DOMAIN_KERNEL,
	},
	[MT_MEMORY_RWX_ITCM] = {
		.prot_pte  = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY,
		.prot_l1   = PMD_TYPE_TABLE,
		.domain    = DOMAIN_KERNEL,
	},
	[MT_MEMORY_RW_SO] = {
		.prot_pte  = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY |
				L_PTE_MT_UNCACHED | L_PTE_XN,
		.prot_l1   = PMD_TYPE_TABLE,
		.prot_sect = PMD_TYPE_SECT | PMD_SECT_AP_WRITE | PMD_SECT_S |
				PMD_SECT_UNCACHED | PMD_SECT_XN,
		.domain    = DOMAIN_KERNEL,
	},
	[MT_MEMORY_DMA_READY] = {
		.prot_pte  = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY |
				L_PTE_XN,
		.prot_l1   = PMD_TYPE_TABLE,
		.domain    = DOMAIN_KERNEL,
	},
};

创建内核页表：

static void __init __create_mapping(struct mm_struct *mm, struct map_desc *md,
				    void *(*alloc)(unsigned long sz),
				    bool ng)
{
	unsigned long addr, length, end;
	phys_addr_t phys;
	const struct mem_type *type;
	pgd_t *pgd;

	type = &mem_types[md->type];

#ifndef CONFIG_ARM_LPAE
	/*
	 * Catch 36-bit addresses
	 */
	if (md->pfn >= 0x100000) {
		create_36bit_mapping(mm, md, type, ng);
		return;
	}
#endif

	addr = md->virtual & PAGE_MASK;
	phys = __pfn_to_phys(md->pfn);
	length = PAGE_ALIGN(md->length + (md->virtual & ~PAGE_MASK));

	if (type->prot_l1 == 0 && ((addr | phys | length) & ~SECTION_MASK)) {
		pr_warn("BUG: map for 0x%08llx at 0x%08lx can not be mapped using pages, ignoring.\n",
			(long long)__pfn_to_phys(md->pfn), addr);
		return;
	}

	pgd = pgd_offset(mm, addr);
	end = addr + length;
	do {
		unsigned long next = pgd_addr_end(addr, end);

		alloc_init_pud(pgd, addr, next, phys, type, alloc, ng);

		phys += next - addr;
		addr = next;
	} while (pgd++, addr != end);
}