init.c

来自「linux2.6.16版本」· C语言 代码 · 共 746 行 · 第 1/2 页

/*
 *  linux/arch/x86_64/mm/init.c
 *
 *  Copyright (C) 1995  Linus Torvalds
 *  Copyright (C) 2000  Pavel Machek <[e-mail]>
 *  Copyright (C) 2002,2003 Andi Kleen <[e-mail]>
 */

#include <linux/config.h>
#include <linux/signal.h>
#include <linux/sched.h>
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/string.h>
#include <linux/types.h>
#include <linux/ptrace.h>
#include <linux/mman.h>
#include <linux/mm.h>
#include <linux/swap.h>
#include <linux/smp.h>
#include <linux/init.h>
#include <linux/pagemap.h>
#include <linux/bootmem.h>
#include <linux/proc_fs.h>
#include <linux/pci.h>
#include <linux/dma-mapping.h>
#include <linux/module.h>
#include <linux/memory_hotplug.h>

#include <asm/processor.h>
#include <asm/system.h>
#include <asm/uaccess.h>
#include <asm/pgtable.h>
#include <asm/pgalloc.h>
#include <asm/dma.h>
#include <asm/fixmap.h>
#include <asm/e820.h>
#include <asm/apic.h>
#include <asm/tlb.h>
#include <asm/mmu_context.h>
#include <asm/proto.h>
#include <asm/smp.h>
#include <asm/sections.h>
#include <asm/dma-mapping.h>
#include <asm/swiotlb.h>

#ifndef Dprintk
#define Dprintk(x...)
#endif

struct dma_mapping_ops* dma_ops;
EXPORT_SYMBOL(dma_ops);

static unsigned long dma_reserve __initdata;

DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);

/*
 * NOTE: pagetable_init alloc all the fixmap pagetables contiguous on the
 * physical space so we can cache the place of the first one and move
 * around without checking the pgd every time.
 */

void show_mem(void)
{
	long i, total = 0, reserved = 0;
	long shared = 0, cached = 0;
	pg_data_t *pgdat;
	struct page *page;

	printk(KERN_INFO "Mem-info:\n");
	show_free_areas();
	printk(KERN_INFO "Free swap:       %6ldkB\n", nr_swap_pages<<(PAGE_SHIFT-10));

	for_each_pgdat(pgdat) {
               for (i = 0; i < pgdat->node_spanned_pages; ++i) {
			page = pfn_to_page(pgdat->node_start_pfn + i);
			total++;
			if (PageReserved(page))
				reserved++;
			else if (PageSwapCache(page))
				cached++;
			else if (page_count(page))
				shared += page_count(page) - 1;
               }
	}
	printk(KERN_INFO "%lu pages of RAM\n", total);
	printk(KERN_INFO "%lu reserved pages\n",reserved);
	printk(KERN_INFO "%lu pages shared\n",shared);
	printk(KERN_INFO "%lu pages swap cached\n",cached);
}

/* References to section boundaries */

int after_bootmem;

static void *spp_getpage(void)
{ 
	void *ptr;
	if (after_bootmem)
		ptr = (void *) get_zeroed_page(GFP_ATOMIC); 
	else
		ptr = alloc_bootmem_pages(PAGE_SIZE);
	if (!ptr || ((unsigned long)ptr & ~PAGE_MASK))
		panic("set_pte_phys: cannot allocate page data %s\n", after_bootmem?"after bootmem":"");

	Dprintk("spp_getpage %p\n", ptr);
	return ptr;
} 

static void set_pte_phys(unsigned long vaddr,
			 unsigned long phys, pgprot_t prot)
{
	pgd_t *pgd;
	pud_t *pud;
	pmd_t *pmd;
	pte_t *pte, new_pte;

	Dprintk("set_pte_phys %lx to %lx\n", vaddr, phys);

	pgd = pgd_offset_k(vaddr);
	if (pgd_none(*pgd)) {
		printk("PGD FIXMAP MISSING, it should be setup in head.S!\n");
		return;
	}
	pud = pud_offset(pgd, vaddr);
	if (pud_none(*pud)) {
		pmd = (pmd_t *) spp_getpage(); 
		set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE | _PAGE_USER));
		if (pmd != pmd_offset(pud, 0)) {
			printk("PAGETABLE BUG #01! %p <-> %p\n", pmd, pmd_offset(pud,0));
			return;
		}
	}
	pmd = pmd_offset(pud, vaddr);
	if (pmd_none(*pmd)) {
		pte = (pte_t *) spp_getpage();
		set_pmd(pmd, __pmd(__pa(pte) | _KERNPG_TABLE | _PAGE_USER));
		if (pte != pte_offset_kernel(pmd, 0)) {
			printk("PAGETABLE BUG #02!\n");
			return;
		}
	}
	new_pte = pfn_pte(phys >> PAGE_SHIFT, prot);

	pte = pte_offset_kernel(pmd, vaddr);
	if (!pte_none(*pte) &&
	    pte_val(*pte) != (pte_val(new_pte) & __supported_pte_mask))
		pte_ERROR(*pte);
	set_pte(pte, new_pte);

	/*
	 * It's enough to flush this one mapping.
	 * (PGE mappings get flushed as well)
	 */
	__flush_tlb_one(vaddr);
}

/* NOTE: this is meant to be run only at boot */
void __set_fixmap (enum fixed_addresses idx, unsigned long phys, pgprot_t prot)
{
	unsigned long address = __fix_to_virt(idx);

	if (idx >= __end_of_fixed_addresses) {
		printk("Invalid __set_fixmap\n");
		return;
	}
	set_pte_phys(address, phys, prot);
}

unsigned long __initdata table_start, table_end; 

extern pmd_t temp_boot_pmds[]; 

static  struct temp_map { 
	pmd_t *pmd;
	void  *address; 
	int    allocated; 
} temp_mappings[] __initdata = { 
	{ &temp_boot_pmds[0], (void *)(40UL * 1024 * 1024) },
	{ &temp_boot_pmds[1], (void *)(42UL * 1024 * 1024) }, 
	{}
}; 

static __meminit void *alloc_low_page(int *index, unsigned long *phys)
{ 
	struct temp_map *ti;
	int i; 
	unsigned long pfn = table_end++, paddr; 
	void *adr;

	if (after_bootmem) {
		adr = (void *)get_zeroed_page(GFP_ATOMIC);
		*phys = __pa(adr);
		return adr;
	}

	if (pfn >= end_pfn) 
		panic("alloc_low_page: ran out of memory"); 
	for (i = 0; temp_mappings[i].allocated; i++) {
		if (!temp_mappings[i].pmd) 
			panic("alloc_low_page: ran out of temp mappings"); 
	} 
	ti = &temp_mappings[i];
	paddr = (pfn << PAGE_SHIFT) & PMD_MASK; 
	set_pmd(ti->pmd, __pmd(paddr | _KERNPG_TABLE | _PAGE_PSE)); 
	ti->allocated = 1; 
	__flush_tlb(); 	       
	adr = ti->address + ((pfn << PAGE_SHIFT) & ~PMD_MASK); 
	memset(adr, 0, PAGE_SIZE);
	*index = i; 
	*phys  = pfn * PAGE_SIZE;  
	return adr; 
} 

static __meminit void unmap_low_page(int i)
{ 
	struct temp_map *ti;

	if (after_bootmem)
		return;

	ti = &temp_mappings[i];
	set_pmd(ti->pmd, __pmd(0));
	ti->allocated = 0; 
} 

static void __meminit
phys_pmd_init(pmd_t *pmd, unsigned long address, unsigned long end)
{
	int i;

	for (i = 0; i < PTRS_PER_PMD; pmd++, i++, address += PMD_SIZE) {
		unsigned long entry;

		if (address > end) {
			for (; i < PTRS_PER_PMD; i++, pmd++)
				set_pmd(pmd, __pmd(0));
			break;
		}
		entry = _PAGE_NX|_PAGE_PSE|_KERNPG_TABLE|_PAGE_GLOBAL|address;
		entry &= __supported_pte_mask;
		set_pmd(pmd, __pmd(entry));
	}
}

static void __meminit
phys_pmd_update(pud_t *pud, unsigned long address, unsigned long end)
{
	pmd_t *pmd = pmd_offset(pud, (unsigned long)__va(address));

	if (pmd_none(*pmd)) {
		spin_lock(&init_mm.page_table_lock);
		phys_pmd_init(pmd, address, end);
		spin_unlock(&init_mm.page_table_lock);
		__flush_tlb_all();
	}
}

static void __meminit phys_pud_init(pud_t *pud, unsigned long address, unsigned long end)
{ 
	long i = pud_index(address);

	pud = pud + i;

	if (after_bootmem && pud_val(*pud)) {
		phys_pmd_update(pud, address, end);
		return;
	}

	for (; i < PTRS_PER_PUD; pud++, i++) {
		int map; 
		unsigned long paddr, pmd_phys;
		pmd_t *pmd;

		paddr = (address & PGDIR_MASK) + i*PUD_SIZE;
		if (paddr >= end)
			break;

		if (!after_bootmem && !e820_mapped(paddr, paddr+PUD_SIZE, 0)) {
			set_pud(pud, __pud(0)); 
			continue;
		} 

		pmd = alloc_low_page(&map, &pmd_phys);
		spin_lock(&init_mm.page_table_lock);
		set_pud(pud, __pud(pmd_phys | _KERNPG_TABLE));
		phys_pmd_init(pmd, paddr, end);
		spin_unlock(&init_mm.page_table_lock);
		unmap_low_page(map);
	}
	__flush_tlb();
} 

static void __init find_early_table_space(unsigned long end)
{
	unsigned long puds, pmds, tables, start;

	puds = (end + PUD_SIZE - 1) >> PUD_SHIFT;
	pmds = (end + PMD_SIZE - 1) >> PMD_SHIFT;
	tables = round_up(puds * sizeof(pud_t), PAGE_SIZE) +
		 round_up(pmds * sizeof(pmd_t), PAGE_SIZE);

 	/* RED-PEN putting page tables only on node 0 could
 	   cause a hotspot and fill up ZONE_DMA. The page tables
 	   need roughly 0.5KB per GB. */
 	start = 0x8000;
 	table_start = find_e820_area(start, end, tables);
	if (table_start == -1UL)
		panic("Cannot find space for the kernel page tables");

	table_start >>= PAGE_SHIFT;
	table_end = table_start;

	early_printk("kernel direct mapping tables up to %lx @ %lx-%lx\n",
		end, table_start << PAGE_SHIFT, table_end << PAGE_SHIFT);
}

/* Setup the direct mapping of the physical memory at PAGE_OFFSET.
   This runs before bootmem is initialized and gets pages directly from the 
   physical memory. To access them they are temporarily mapped. */
void __meminit init_memory_mapping(unsigned long start, unsigned long end)
{ 
	unsigned long next; 

	Dprintk("init_memory_mapping\n");

	/* 
	 * Find space for the kernel direct mapping tables.
	 * Later we should allocate these tables in the local node of the memory
	 * mapped.  Unfortunately this is done currently before the nodes are 
	 * discovered.
	 */
	if (!after_bootmem)
		find_early_table_space(end);

	start = (unsigned long)__va(start);
	end = (unsigned long)__va(end);

	for (; start < end; start = next) {
		int map;
		unsigned long pud_phys; 
		pgd_t *pgd = pgd_offset_k(start);
		pud_t *pud;

		if (after_bootmem)
			pud = pud_offset_k(pgd, __PAGE_OFFSET);
		else
			pud = alloc_low_page(&map, &pud_phys);

		next = start + PGDIR_SIZE;
		if (next > end) 
			next = end; 
		phys_pud_init(pud, __pa(start), __pa(next));
		if (!after_bootmem)
			set_pgd(pgd_offset_k(start), mk_kernel_pgd(pud_phys));
		unmap_low_page(map);   
	} 

	if (!after_bootmem)
		asm volatile("movq %%cr4,%0" : "=r" (mmu_cr4_features));
	__flush_tlb_all();
}

void __cpuinit zap_low_mappings(int cpu)
{
	if (cpu == 0) {
		pgd_t *pgd = pgd_offset_k(0UL);
		pgd_clear(pgd);
	} else {
		/*
		 * For AP's, zap the low identity mappings by changing the cr3
		 * to init_level4_pgt and doing local flush tlb all