init.c

来自「底层驱动开发」· C语言 代码 · 共 870 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/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>
#include <linux/idr.h>
#include <linux/nodemask.h>
#include <linux/module.h>

#include <asm/pgalloc.h>
#include <asm/page.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/eeh.h>
#include <asm/processor.h>
#include <asm/mmzone.h>
#include <asm/cputable.h>
#include <asm/ppcdebug.h>
#include <asm/sections.h>
#include <asm/system.h>
#include <asm/iommu.h>
#include <asm/abs_addr.h>
#include <asm/vdso.h>
#include <asm/imalloc.h>

#if PGTABLE_RANGE > USER_VSID_RANGE
#warning Limited user VSID range means pagetable space is wasted
#endif

#if (TASK_SIZE_USER64 < PGTABLE_RANGE) && (TASK_SIZE_USER64 < USER_VSID_RANGE)
#warning TASK_SIZE is smaller than it needs to be.
#endif

int mem_init_done;
unsigned long ioremap_bot = IMALLOC_BASE;
static unsigned long phbs_io_bot = PHBS_IO_BASE;

extern pgd_t swapper_pg_dir[];
extern struct task_struct *current_set[NR_CPUS];

unsigned long klimit = (unsigned long)_end;

unsigned long _SDR1=0;
unsigned long _ASR=0;

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

/* info on what we think the IO hole is */
unsigned long 	io_hole_start;
unsigned long	io_hole_size;

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

	printk("Mem-info:\n");
	show_free_areas();
	printk("Free swap:       %6ldkB\n", nr_swap_pages<<(PAGE_SHIFT-10));
	for_each_pgdat(pgdat) {
		for (i = 0; i < pgdat->node_spanned_pages; i++) {
			page = pgdat_page_nr(pgdat, i);
			total++;
			if (PageReserved(page))
				reserved++;
			else if (PageSwapCache(page))
				cached++;
			else if (page_count(page))
				shared += page_count(page) - 1;
		}
	}
	printk("%ld pages of RAM\n", total);
	printk("%ld reserved pages\n", reserved);
	printk("%ld pages shared\n", shared);
	printk("%ld pages swap cached\n", cached);
}

#ifdef CONFIG_PPC_ISERIES

void __iomem *ioremap(unsigned long addr, unsigned long size)
{
	return (void __iomem *)addr;
}

extern void __iomem *__ioremap(unsigned long addr, unsigned long size,
		       unsigned long flags)
{
	return (void __iomem *)addr;
}

void iounmap(volatile void __iomem *addr)
{
	return;
}

#else

/*
 * 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 int map_io_page(unsigned long ea, unsigned long pa, int flags)
{
	pgd_t *pgdp;
	pud_t *pudp;
	pmd_t *pmdp;
	pte_t *ptep;
	unsigned long vsid;

	if (mem_init_done) {
		spin_lock(&init_mm.page_table_lock);
		pgdp = pgd_offset_k(ea);
		pudp = pud_alloc(&init_mm, pgdp, ea);
		if (!pudp)
			return -ENOMEM;
		pmdp = pmd_alloc(&init_mm, pudp, ea);
		if (!pmdp)
			return -ENOMEM;
		ptep = pte_alloc_kernel(&init_mm, pmdp, ea);
		if (!ptep)
			return -ENOMEM;
		set_pte_at(&init_mm, ea, ptep, pfn_pte(pa >> PAGE_SHIFT,
							  __pgprot(flags)));
		spin_unlock(&init_mm.page_table_lock);
	} else {
		unsigned long va, vpn, hash, hpteg;

		/*
		 * 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);
		va = (vsid << 28) | (ea & 0xFFFFFFF);
		vpn = va >> PAGE_SHIFT;

		hash = hpt_hash(vpn, 0);

		hpteg = ((hash & htab_hash_mask) * HPTES_PER_GROUP);

		/* Panic if a pte grpup is full */
		if (ppc_md.hpte_insert(hpteg, va, pa >> PAGE_SHIFT,
				       HPTE_V_BOLTED,
				       _PAGE_NO_CACHE|_PAGE_GUARDED|PP_RWXX)
		    == -1) {
			panic("map_io_page: could not insert mapping");
		}
	}
	return 0;
}


static void __iomem * __ioremap_com(unsigned long addr, unsigned long pa,
			    unsigned long ea, unsigned long size,
			    unsigned long flags)
{
	unsigned long i;

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

	for (i = 0; i < size; i += PAGE_SIZE)
		if (map_io_page(ea+i, pa+i, flags))
			return NULL;

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


void __iomem *
ioremap(unsigned long addr, unsigned long size)
{
	return __ioremap(addr, size, _PAGE_NO_CACHE | _PAGE_GUARDED);
}

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

	/*
	 * 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
	 * 
	 */
	pa = addr & PAGE_MASK;
	size = PAGE_ALIGN(addr + size) - pa;

	if (size == 0)
		return NULL;

	if (mem_init_done) {
		struct vm_struct *area;
		area = im_get_free_area(size);
		if (area == NULL)
			return NULL;
		ea = (unsigned long)(area->addr);
		ret = __ioremap_com(addr, pa, ea, size, flags);
		if (!ret)
			im_free(area->addr);
	} else {
		ea = ioremap_bot;
		ret = __ioremap_com(addr, pa, ea, size, flags);
		if (ret)
			ioremap_bot += size;
	}
	return ret;
}

#define IS_PAGE_ALIGNED(_val) ((_val) == ((_val) & PAGE_MASK))

int __ioremap_explicit(unsigned long pa, unsigned long ea,
		       unsigned long size, unsigned long flags)
{
	struct vm_struct *area;
	void __iomem *ret;
	
	/* For now, require page-aligned values for pa, ea, and size */
	if (!IS_PAGE_ALIGNED(pa) || !IS_PAGE_ALIGNED(ea) ||
	    !IS_PAGE_ALIGNED(size)) {
		printk(KERN_ERR	"unaligned value in %s\n", __FUNCTION__);
		return 1;
	}
	
	if (!mem_init_done) {
		/* Two things to consider in this case:
		 * 1) No records will be kept (imalloc, etc) that the region
		 *    has been remapped
		 * 2) It won't be easy to iounmap() the region later (because
		 *    of 1)
		 */
		;
	} else {
		area = im_get_area(ea, size,
			IM_REGION_UNUSED|IM_REGION_SUBSET|IM_REGION_EXISTS);
		if (area == NULL) {
			/* Expected when PHB-dlpar is in play */
			return 1;
		}
		if (ea != (unsigned long) area->addr) {
			printk(KERN_ERR "unexpected addr return from "
			       "im_get_area\n");
			return 1;
		}
	}
	
	ret = __ioremap_com(pa, pa, ea, size, flags);
	if (ret == NULL) {
		printk(KERN_ERR "ioremap_explicit() allocation failure !\n");
		return 1;
	}
	if (ret != (void *) ea) {
		printk(KERN_ERR "__ioremap_com() returned unexpected addr\n");
		return 1;
	}

	return 0;
}

/*  
 * Unmap an IO region and remove it from imalloc'd list.
 * Access to IO memory should be serialized by driver.
 * This code is modeled after vmalloc code - unmap_vm_area()
 *
 * XXX	what about calls before mem_init_done (ie python_countermeasures())
 */
void iounmap(volatile void __iomem *token)
{
	void *addr;

	if (!mem_init_done)
		return;
	
	addr = (void *) ((unsigned long __force) token & PAGE_MASK);

	im_free(addr);
}

static int iounmap_subset_regions(unsigned long addr, unsigned long size)
{
	struct vm_struct *area;

	/* Check whether subsets of this region exist */
	area = im_get_area(addr, size, IM_REGION_SUPERSET);
	if (area == NULL)
		return 1;

	while (area) {
		iounmap((void __iomem *) area->addr);
		area = im_get_area(addr, size,
				IM_REGION_SUPERSET);
	}

	return 0;
}

int iounmap_explicit(volatile void __iomem *start, unsigned long size)
{
	struct vm_struct *area;
	unsigned long addr;
	int rc;
	
	addr = (unsigned long __force) start & PAGE_MASK;

	/* Verify that the region either exists or is a subset of an existing
	 * region.  In the latter case, split the parent region to create 
	 * the exact region 
	 */
	area = im_get_area(addr, size, 
			    IM_REGION_EXISTS | IM_REGION_SUBSET);
	if (area == NULL) {
		/* Determine whether subset regions exist.  If so, unmap */
		rc = iounmap_subset_regions(addr, size);
		if (rc) {
			printk(KERN_ERR
			       "%s() cannot unmap nonexistent range 0x%lx\n",
 				__FUNCTION__, addr);
			return 1;
		}
	} else {
		iounmap((void __iomem *) area->addr);
	}
	/*
	 * FIXME! This can't be right:
	iounmap(area->addr);
	 * Maybe it should be "iounmap(area);"
	 */
	return 0;
}

#endif

EXPORT_SYMBOL(ioremap);
EXPORT_SYMBOL(__ioremap);
EXPORT_SYMBOL(iounmap);

void free_initmem(void)
{
	unsigned long addr;

	addr = (unsigned long)__init_begin;
	for (; addr < (unsigned long)__init_end; addr += PAGE_SIZE) {
		memset((void *)addr, 0xcc, PAGE_SIZE);
		ClearPageReserved(virt_to_page(addr));
		set_page_count(virt_to_page(addr), 1);
		free_page(addr);
		totalram_pages++;
	}
	printk ("Freeing unused kernel memory: %luk freed\n",
		((unsigned long)__init_end - (unsigned long)__init_begin) >> 10);
}

#ifdef CONFIG_BLK_DEV_INITRD
void free_initrd_mem(unsigned long start, unsigned long end)
{
	if (start < end)
		printk ("Freeing initrd memory: %ldk freed\n", (end - start) >> 10);
	for (; start < end; start += PAGE_SIZE) {
		ClearPageReserved(virt_to_page(start));
		set_page_count(virt_to_page(start), 1);
		free_page(start);
		totalram_pages++;
	}
}
#endif

static DEFINE_SPINLOCK(mmu_context_lock);
static DEFINE_IDR(mmu_context_idr);

int init_new_context(struct task_struct *tsk, struct mm_struct *mm)
{
	int index;
	int err;

again:
	if (!idr_pre_get(&mmu_context_idr, GFP_KERNEL))
		return -ENOMEM;

	spin_lock(&mmu_context_lock);
	err = idr_get_new_above(&mmu_context_idr, NULL, 1, &index);
	spin_unlock(&mmu_context_lock);

	if (err == -EAGAIN)