init_64.c

linux 内核源代码

/*
 *  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/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/pfn.h>
#include <linux/poison.h>
#include <linux/dma-mapping.h>
#include <linux/module.h>
#include <linux/memory_hotplug.h>
#include <linux/nmi.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>

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

const 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_online_pgdat(pgdat) {
               for (i = 0; i < pgdat->node_spanned_pages; ++i) {
			/* this loop can take a while with 256 GB and 4k pages
			   so update the NMI watchdog */
			if (unlikely(i % MAX_ORDER_NR_PAGES == 0)) {
				touch_nmi_watchdog();
			}
			if (!pfn_valid(pgdat->node_start_pfn + i))
				continue;
			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);
}

int after_bootmem;

static __init 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 __init 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 __init 
__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 __meminitdata table_start, table_end;

static __meminit void *alloc_low_page(unsigned long *phys)
{ 
	unsigned long pfn = table_end++;
	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"); 

	adr = early_ioremap(pfn * PAGE_SIZE, PAGE_SIZE);
	memset(adr, 0, PAGE_SIZE);
	*phys  = pfn * PAGE_SIZE;
	return adr;
}

static __meminit void unmap_low_page(void *adr)
{ 

	if (after_bootmem)
		return;

	early_iounmap(adr, PAGE_SIZE);
} 

/* Must run before zap_low_mappings */
__meminit void *early_ioremap(unsigned long addr, unsigned long size)
{
	unsigned long vaddr;
	pmd_t *pmd, *last_pmd;
	int i, pmds;

	pmds = ((addr & ~PMD_MASK) + size + ~PMD_MASK) / PMD_SIZE;
	vaddr = __START_KERNEL_map;
	pmd = level2_kernel_pgt;
	last_pmd = level2_kernel_pgt + PTRS_PER_PMD - 1;
	for (; pmd <= last_pmd; pmd++, vaddr += PMD_SIZE) {
		for (i = 0; i < pmds; i++) {
			if (pmd_present(pmd[i]))
				goto next;
		}
		vaddr += addr & ~PMD_MASK;
		addr &= PMD_MASK;
		for (i = 0; i < pmds; i++, addr += PMD_SIZE)
			set_pmd(pmd + i,__pmd(addr | _KERNPG_TABLE | _PAGE_PSE));
		__flush_tlb();
		return (void *)vaddr;
	next:
		;
	}
	printk("early_ioremap(0x%lx, %lu) failed\n", addr, size);
	return NULL;
}

/* To avoid virtual aliases later */
__meminit void early_iounmap(void *addr, unsigned long size)
{
	unsigned long vaddr;
	pmd_t *pmd;
	int i, pmds;

	vaddr = (unsigned long)addr;
	pmds = ((vaddr & ~PMD_MASK) + size + ~PMD_MASK) / PMD_SIZE;
	pmd = level2_kernel_pgt + pmd_index(vaddr);
	for (i = 0; i < pmds; i++)
		pmd_clear(pmd + i);
	__flush_tlb();
}

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

	for (; i < PTRS_PER_PMD; i++, address += PMD_SIZE) {
		unsigned long entry;
		pmd_t *pmd = pmd_page + pmd_index(address);

		if (address >= end) {
			if (!after_bootmem)
				for (; i < PTRS_PER_PMD; i++, pmd++)
					set_pmd(pmd, __pmd(0));
			break;
		}

		if (pmd_val(*pmd))
			continue;

		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,0);
	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_page, unsigned long addr, unsigned long end)
{ 
	int i = pud_index(addr);


	for (; i < PTRS_PER_PUD; i++, addr = (addr & PUD_MASK) + PUD_SIZE ) {
		unsigned long pmd_phys;
		pud_t *pud = pud_page + pud_index(addr);
		pmd_t *pmd;

		if (addr >= end)
			break;

		if (!after_bootmem && !e820_any_mapped(addr,addr+PUD_SIZE,0)) {
			set_pud(pud, __pud(0)); 
			continue;
		} 

		if (pud_val(*pud)) {
			phys_pmd_update(pud, addr, end);
			continue;
		}

		pmd = alloc_low_page(&pmd_phys);
		spin_lock(&init_mm.page_table_lock);
		set_pud(pud, __pud(pmd_phys | _KERNPG_TABLE));
		phys_pmd_init(pmd, addr, end);
		spin_unlock(&init_mm.page_table_lock);
		unmap_low_page(pmd);
	}
	__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_start << PAGE_SHIFT) + tables);
}

/* 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 __init_refok 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) {
		unsigned long pud_phys; 
		pgd_t *pgd = pgd_offset_k(start);
		pud_t *pud;

		if (after_bootmem)
			pud = pud_offset(pgd, start & PGDIR_MASK);
		else
			pud = alloc_low_page(&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(pud);
	} 

	if (!after_bootmem)
		mmu_cr4_features = read_cr4();
	__flush_tlb_all();
}

#ifndef CONFIG_NUMA
void __init paging_init(void)
{