init.c

来自「是关于linux2.5.1的完全源码」· C语言 代码 · 共 682 行 · 第 1/2 页

			zones_size[ZONE_HIGHMEM] = high - low;
#endif
		}
		free_area_init(zones_size);
	}
	return;
}

/*
 * Test if the WP bit works in supervisor mode. It isn't supported on 386's
 * and also on some strange 486's (NexGen etc.). All 586+'s are OK. The jumps
 * before and after the test are here to work-around some nasty CPU bugs.
 */

/*
 * This function cannot be __init, since exceptions don't work in that
 * section.
 */
static int do_test_wp_bit(unsigned long vaddr);

void __init test_wp_bit(void)
{
/*
 * Ok, all PSE-capable CPUs are definitely handling the WP bit right.
 */
	const unsigned long vaddr = PAGE_OFFSET;
	pgd_t *pgd;
	pmd_t *pmd;
	pte_t *pte, old_pte;

	printk("Checking if this processor honours the WP bit even in supervisor mode... ");

	pgd = swapper_pg_dir + __pgd_offset(vaddr);
	pmd = pmd_offset(pgd, vaddr);
	pte = pte_offset_kernel(pmd, vaddr);
	old_pte = *pte;
	*pte = mk_pte_phys(0, PAGE_READONLY);
	local_flush_tlb();

	boot_cpu_data.wp_works_ok = do_test_wp_bit(vaddr);

	*pte = old_pte;
	local_flush_tlb();

	if (!boot_cpu_data.wp_works_ok) {
		printk("No.\n");
#ifdef CONFIG_X86_WP_WORKS_OK
		panic("This kernel doesn't support CPU's with broken WP. Recompile it for a 386!");
#endif
	} else {
		printk("Ok.\n");
	}
}

static inline int page_is_ram (unsigned long pagenr)
{
	int i;

	for (i = 0; i < e820.nr_map; i++) {
		unsigned long addr, end;

		if (e820.map[i].type != E820_RAM)	/* not usable memory */
			continue;
		/*
		 *	!!!FIXME!!! Some BIOSen report areas as RAM that
		 *	are not. Notably the 640->1Mb area. We need a sanity
		 *	check here.
		 */
		addr = (e820.map[i].addr+PAGE_SIZE-1) >> PAGE_SHIFT;
		end = (e820.map[i].addr+e820.map[i].size) >> PAGE_SHIFT;
		if  ((pagenr >= addr) && (pagenr < end))
			return 1;
	}
	return 0;
}

static inline int page_kills_ppro(unsigned long pagenr)
{
	if(pagenr >= 0x70000 && pagenr <= 0x7003F)
		return 1;
	return 0;
}
	
void __init mem_init(void)
{
	extern int ppro_with_ram_bug(void);
	int codesize, reservedpages, datasize, initsize;
	int tmp;
	int bad_ppro;

	if (!mem_map)
		BUG();
	
	bad_ppro = ppro_with_ram_bug();

#ifdef CONFIG_HIGHMEM
	highmem_start_page = mem_map + highstart_pfn;
	max_mapnr = num_physpages = highend_pfn;
#else
	max_mapnr = num_physpages = max_low_pfn;
#endif
	high_memory = (void *) __va(max_low_pfn * PAGE_SIZE);

	/* clear the zero-page */
	memset(empty_zero_page, 0, PAGE_SIZE);

	/* this will put all low memory onto the freelists */
	totalram_pages += free_all_bootmem();

	reservedpages = 0;
	for (tmp = 0; tmp < max_low_pfn; tmp++)
		/*
		 * Only count reserved RAM pages
		 */
		if (page_is_ram(tmp) && PageReserved(mem_map+tmp))
			reservedpages++;
#ifdef CONFIG_HIGHMEM
	for (tmp = highstart_pfn; tmp < highend_pfn; tmp++) {
		struct page *page = mem_map + tmp;

		if (!page_is_ram(tmp)) {
			SetPageReserved(page);
			continue;
		}
		if (bad_ppro && page_kills_ppro(tmp))
		{
			SetPageReserved(page);
			continue;
		}
		ClearPageReserved(page);
		set_bit(PG_highmem, &page->flags);
		atomic_set(&page->count, 1);
		__free_page(page);
		totalhigh_pages++;
	}
	totalram_pages += totalhigh_pages;
#endif
	codesize =  (unsigned long) &_etext - (unsigned long) &_text;
	datasize =  (unsigned long) &_edata - (unsigned long) &_etext;
	initsize =  (unsigned long) &__init_end - (unsigned long) &__init_begin;

	printk("Memory: %luk/%luk available (%dk kernel code, %dk reserved, %dk data, %dk init, %ldk highmem)\n",
		(unsigned long) nr_free_pages() << (PAGE_SHIFT-10),
		max_mapnr << (PAGE_SHIFT-10),
		codesize >> 10,
		reservedpages << (PAGE_SHIFT-10),
		datasize >> 10,
		initsize >> 10,
		(unsigned long) (totalhigh_pages << (PAGE_SHIFT-10))
	       );

#if CONFIG_X86_PAE
	if (!cpu_has_pae)
		panic("cannot execute a PAE-enabled kernel on a PAE-less CPU!");
#endif
	if (boot_cpu_data.wp_works_ok < 0)
		test_wp_bit();

	/*
	 * Subtle. SMP is doing it's boot stuff late (because it has to
	 * fork idle threads) - but it also needs low mappings for the
	 * protected-mode entry to work. We zap these entries only after
	 * the WP-bit has been tested.
	 */
#ifndef CONFIG_SMP
	zap_low_mappings();
#endif

}

/* Put this after the callers, so that it cannot be inlined */
static int do_test_wp_bit(unsigned long vaddr)
{
	char tmp_reg;
	int flag;

	__asm__ __volatile__(
		"	movb %0,%1	\n"
		"1:	movb %1,%0	\n"
		"	xorl %2,%2	\n"
		"2:			\n"
		".section __ex_table,\"a\"\n"
		"	.align 4	\n"
		"	.long 1b,2b	\n"
		".previous		\n"
		:"=m" (*(char *) vaddr),
		 "=q" (tmp_reg),
		 "=r" (flag)
		:"2" (1)
		:"memory");
	
	return flag;
}

void free_initmem(void)
{
	unsigned long addr;

	addr = (unsigned long)(&__init_begin);
	for (; addr < (unsigned long)(&__init_end); addr += 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: %dk freed\n", (&__init_end - &__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

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 = totalhigh_pages;
	val->freehigh = nr_free_highpages();
	val->mem_unit = PAGE_SIZE;
	return;
}

#if defined(CONFIG_X86_PAE)
static struct kmem_cache_s *pae_pgd_cachep;

void __init pgtable_cache_init(void)
{
	/*
	 * PAE pgds must be 16-byte aligned:
	 */
	pae_pgd_cachep = kmem_cache_create("pae_pgd", 32, 0,
		SLAB_HWCACHE_ALIGN | SLAB_MUST_HWCACHE_ALIGN, NULL, NULL);
	if (!pae_pgd_cachep)
		panic("init_pae(): Cannot alloc pae_pgd SLAB cache");
}

pgd_t *pgd_alloc(struct mm_struct *mm)
{
	int i;
	pgd_t *pgd = kmem_cache_alloc(pae_pgd_cachep, GFP_KERNEL);

	if (pgd) {
		for (i = 0; i < USER_PTRS_PER_PGD; i++) {
			unsigned long pmd = __get_free_page(GFP_KERNEL);
			if (!pmd)
				goto out_oom;
			clear_page(pmd);
			set_pgd(pgd + i, __pgd(1 + __pa(pmd)));
		}
		memcpy(pgd + USER_PTRS_PER_PGD,
			swapper_pg_dir + USER_PTRS_PER_PGD,
			(PTRS_PER_PGD - USER_PTRS_PER_PGD) * sizeof(pgd_t));
	}
	return pgd;
out_oom:
	for (i--; i >= 0; i--)
		free_page((unsigned long)__va(pgd_val(pgd[i])-1));
	kmem_cache_free(pae_pgd_cachep, pgd);
	return NULL;
}

void pgd_free(pgd_t *pgd)
{
	int i;

	for (i = 0; i < USER_PTRS_PER_PGD; i++)
		free_page((unsigned long)__va(pgd_val(pgd[i])-1));
	kmem_cache_free(pae_pgd_cachep, pgd);
}

#else

pgd_t *pgd_alloc(struct mm_struct *mm)
{
	pgd_t *pgd = (pgd_t *)__get_free_page(GFP_KERNEL);

	if (pgd) {
		memset(pgd, 0, USER_PTRS_PER_PGD * sizeof(pgd_t));
		memcpy(pgd + USER_PTRS_PER_PGD,
			swapper_pg_dir + USER_PTRS_PER_PGD,
			(PTRS_PER_PGD - USER_PTRS_PER_PGD) * sizeof(pgd_t));
	}
	return pgd;
}

void pgd_free(pgd_t *pgd)
{
	free_page((unsigned long)pgd);
}
#endif /* CONFIG_X86_PAE */

pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address)
{
	int count = 0;
	pte_t *pte;
   
   	do {
		pte = (pte_t *) __get_free_page(GFP_KERNEL);
		if (pte)
			clear_page(pte);
		else {
			current->state = TASK_UNINTERRUPTIBLE;
			schedule_timeout(HZ);
		}
	} while (!pte && (count++ < 10));
	return pte;
}

struct page *pte_alloc_one(struct mm_struct *mm, unsigned long address)
{
	int count = 0;
	struct page *pte;
   
   	do {
#if CONFIG_HIGHPTE
		pte = alloc_pages(GFP_KERNEL | __GFP_HIGHMEM, 0);
#else
		pte = alloc_pages(GFP_KERNEL, 0);
#endif
		if (pte)
			clear_highpage(pte);
		else {
			current->state = TASK_UNINTERRUPTIBLE;
			schedule_timeout(HZ);
		}
	} while (!pte && (count++ < 10));
	return pte;
}