init.c

来自「是关于linux2.5.1的完全源码」· C语言 代码 · 共 707 行 · 第 1/2 页

/*
 *  
 *
 *  PowerPC version 
 *    Copyright (C) 1995-1996 Gary Thomas ([e-mail])
 *
 *  Modifications by Paul Mackerras (PowerMac) ([e-mail])
 *  and Cort Dougan (PReP) ([e-mail])
 *    Copyright (C) 1996 Paul Mackerras
 *  Amiga/APUS changes by Jesper Skov ([e-mail]).
 *
 *  Derived from "arch/i386/mm/init.c"
 *    Copyright (C) 1991, 1992, 1993, 1994  Linus Torvalds
 *
 *  Dave Engebretsen <[e-mail]>
 *      Rework for PPC64 port.
 *
 *  This program is free software; you can redistribute it and/or
 *  modify it under the terms of the GNU General Public License
 *  as published by the Free Software Foundation; either version
 *  2 of the License, or (at your option) any later version.
 *
 */

#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/stddef.h>
#include <linux/vmalloc.h>
#include <linux/init.h>
#include <linux/delay.h>
#include <linux/bootmem.h>
#include <linux/highmem.h>
#ifdef CONFIG_BLK_DEV_INITRD
#include <linux/blk.h>		/* for initrd_* */
#endif

#include <asm/pgalloc.h>
#include <asm/page.h>
#include <asm/abs_addr.h>
#include <asm/prom.h>
#include <asm/lmb.h>
#include <asm/rtas.h>
#include <asm/io.h>
#include <asm/mmu_context.h>
#include <asm/pgtable.h>
#include <asm/mmu.h>
#include <asm/uaccess.h>
#include <asm/smp.h>
#include <asm/machdep.h>
#include <asm/tlb.h>
#include <asm/Naca.h>
#ifdef CONFIG_PPC_EEH
#include <asm/eeh.h>
#endif

#include <asm/ppcdebug.h>

#define	PGTOKB(pages)	(((pages) * PAGE_SIZE) >> 10)

#ifdef CONFIG_PPC_ISERIES
#include <asm/iSeries/iSeries_dma.h>
#endif

struct mmu_context_queue_t mmu_context_queue;
int mem_init_done;
unsigned long ioremap_bot = IMALLOC_BASE;

static int boot_mapsize;
static unsigned long totalram_pages;

extern pgd_t swapper_pg_dir[];
extern char __init_begin, __init_end;
extern char __chrp_begin, __chrp_end;
extern char __openfirmware_begin, __openfirmware_end;
extern struct _of_tce_table of_tce_table[];
extern char _start[], _end[];
extern char _stext[], etext[];
extern struct task_struct *current_set[NR_CPUS];
extern struct Naca *naca;

void mm_init_ppc64(void);

unsigned long *pmac_find_end_of_memory(void);
extern unsigned long *find_end_of_memory(void);

extern pgd_t ioremap_dir[];
pgd_t * ioremap_pgd = (pgd_t *)&ioremap_dir;

static void map_io_page(unsigned long va, unsigned long pa, int flags);
extern void die_if_kernel(char *,struct pt_regs *,long);

unsigned long klimit = (unsigned long)_end;

HPTE *Hash=0;
unsigned long Hash_size=0;
unsigned long _SDR1=0;
unsigned long _ASR=0;

/* max amount of RAM to use */
unsigned long __max_memory;

/* This is declared as we are using the more or less generic 
 * include/asm-ppc64/tlb.h file -- tgall
 */
mmu_gather_t     mmu_gathers[NR_CPUS];

void show_mem(void)
{
	int i,free = 0,total = 0,reserved = 0;
	int shared = 0, cached = 0;

	printk("Mem-info:\n");
	show_free_areas();
	printk("Free swap:       %6dkB\n",nr_swap_pages<<(PAGE_SHIFT-10));
	i = max_mapnr;
	while (i-- > 0) {
		total++;
		if (PageReserved(mem_map+i))
			reserved++;
		else if (PageSwapCache(mem_map+i))
			cached++;
		else if (!atomic_read(&mem_map[i].count))
			free++;
		else
			shared += atomic_read(&mem_map[i].count) - 1;
	}
	printk("%d pages of RAM\n",total);
	printk("%d free pages\n",free);
	printk("%d reserved pages\n",reserved);
	printk("%d pages shared\n",shared);
	printk("%d pages swap cached\n",cached);
	show_buffers();
}

void si_meminfo(struct sysinfo *val)
{
 	val->totalram = totalram_pages;
	val->sharedram = 0;
	val->freeram = nr_free_pages();
	val->bufferram = atomic_read(&buffermem_pages);
	val->totalhigh = 0;
	val->freehigh = 0;
	val->mem_unit = PAGE_SIZE;
}

void *
ioremap(unsigned long addr, unsigned long size)
{
#ifdef CONFIG_PPC_ISERIES
	return (void*)addr;
#else
#ifdef CONFIG_PPC_EEH
	if(mem_init_done && (addr >> 60UL)) {
		if (IS_EEH_TOKEN_DISABLED(addr))
			return IO_TOKEN_TO_ADDR(addr);
		return (void*)addr; /* already mapped address or EEH token. */
	}
#endif
	return __ioremap(addr, size, _PAGE_NO_CACHE);
#endif
}

extern struct vm_struct * get_im_area( unsigned long size );

void *
__ioremap(unsigned long addr, unsigned long size, unsigned long flags)
{
	unsigned long pa, ea, i;

	/*
	 * Choose an address to map it to.
	 * Once the imalloc system is running, we use it.
	 * Before that, we map using addresses going
	 * up from ioremap_bot.  imalloc will use
	 * the addresses from ioremap_bot through
	 * IMALLOC_END (0xE000001fffffffff)
	 * 
	 */
	pa = addr & PAGE_MASK;
	size = PAGE_ALIGN(addr + size) - pa;

	if (size == 0)
		return NULL;

	if (mem_init_done) {
		struct vm_struct *area;
		area = get_im_area(size);
		if (area == 0)
			return NULL;
		ea = (unsigned long)(area->addr);
	} 
	else {
		ea = ioremap_bot;
		ioremap_bot += size;
        }

	if ((flags & _PAGE_PRESENT) == 0)
		flags |= pgprot_val(PAGE_KERNEL);
	if (flags & (_PAGE_NO_CACHE | _PAGE_WRITETHRU))
		flags |= _PAGE_GUARDED;

	for (i = 0; i < size; i += PAGE_SIZE) {
		map_io_page(ea+i, pa+i, flags);
	}

	return (void *) (ea + (addr & ~PAGE_MASK));
}

void iounmap(void *addr) 
{
#ifdef CONFIG_PPC_ISERIES
     /* iSeries I/O Remap is a noop              */
	return;
#else 
	/* DRENG / PPPBBB todo */
	return;
#endif
}

/*
 * map_io_page currently only called by __ioremap
 * map_io_page adds an entry to the ioremap page table
 * and adds an entry to the HPT, possibly bolting it
 */
static void map_io_page(unsigned long ea, unsigned long pa, int flags)
{
	pgd_t *pgdp;
	pmd_t *pmdp;
	pte_t *ptep;
	unsigned long vsid;
	
	if (mem_init_done) {
		spin_lock(&ioremap_mm.page_table_lock);
		pgdp = pgd_offset_i(ea);
		pmdp = pmd_alloc(&ioremap_mm, pgdp, ea);
		ptep = pte_alloc_kernel(&ioremap_mm, pmdp, ea);

		pa = absolute_to_phys(pa);
		set_pte(ptep, mk_pte_phys(pa & PAGE_MASK, __pgprot(flags)));
		spin_unlock(&ioremap_mm.page_table_lock);
	} else {
		/* If the mm subsystem is not fully up, we cannot create a
		 * linux page table entry for this mapping.  Simply bolt an
		 * entry in the hardware page table. 
 		 */
		vsid = get_kernel_vsid(ea);
		ppc_md.make_pte(htab_data.htab,
			(vsid << 28) | (ea & 0xFFFFFFF), // va (NOT the ea)
			pa, 
			_PAGE_NO_CACHE | _PAGE_GUARDED | PP_RWXX,
			htab_data.htab_hash_mask, 0);
	}
}

void
flush_tlb_mm(struct mm_struct *mm)
{
	if (mm->map_count) {
		struct vm_area_struct *mp;
		for (mp = mm->mmap; mp != NULL; mp = mp->vm_next)
			__flush_tlb_range(mm, mp->vm_start, mp->vm_end);
	} else {
		/* MIKEC: It is not clear why this is needed */
		/* paulus: it is needed to clear out stale HPTEs
		 * when an address space (represented by an mm_struct)
		 * is being destroyed. */
		__flush_tlb_range(mm, USER_START, USER_END);
	}

	/* XXX are there races with checking cpu_vm_mask? - Anton */
	mm->cpu_vm_mask = 0;
}

/*
 * Callers should hold the mm->page_table_lock
 */
void
flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr)
{
	unsigned long context = 0;
	pgd_t *pgd;
	pmd_t *pmd;
	pte_t *ptep;
	pte_t pte;
	int local = 0;

	switch( REGION_ID(vmaddr) ) {
	case VMALLOC_REGION_ID:
		pgd = pgd_offset_k( vmaddr );
		break;
	case IO_REGION_ID:
		pgd = pgd_offset_i( vmaddr );
		break;
	case USER_REGION_ID:
		pgd = pgd_offset( vma->vm_mm, vmaddr );
		context = vma->vm_mm->context;

		/* XXX are there races with checking cpu_vm_mask? - Anton */
		if (vma->vm_mm->cpu_vm_mask == (1 << smp_processor_id()))
			local = 1;

		break;
	default:
		panic("flush_tlb_page: invalid region 0x%016lx", vmaddr);
	
	}

	if (!pgd_none(*pgd)) {
		pmd = pmd_offset(pgd, vmaddr);
		if (!pmd_none(*pmd)) {
			ptep = pte_offset_kernel(pmd, vmaddr);
			/* Check if HPTE might exist and flush it if so */
			pte = __pte(pte_update(ptep, _PAGE_HPTEFLAGS, 0));
			if ( pte_val(pte) & _PAGE_HASHPTE ) {
				flush_hash_page(context, vmaddr, pte, local);
			}
		}
	}
}

struct tlb_batch_data tlb_batch_array[NR_CPUS][MAX_BATCH_FLUSH];

void
__flush_tlb_range(struct mm_struct *mm, unsigned long start, unsigned long end)
{
	pgd_t *pgd;
	pmd_t *pmd;
	pte_t *ptep;
	pte_t pte;
	unsigned long pgd_end, pmd_end;
	unsigned long context;
	int i = 0;
	struct tlb_batch_data *ptes = &tlb_batch_array[smp_processor_id()][0];
	int local = 0;

	if ( start >= end )
		panic("flush_tlb_range: start (%016lx) greater than end (%016lx)\n", start, end );

	if ( REGION_ID(start) != REGION_ID(end) )
		panic("flush_tlb_range: start (%016lx) and end (%016lx) not in same region\n", start, end );
	
	context = 0;

	switch( REGION_ID(start) ) {
	case VMALLOC_REGION_ID: