init.c

linux-2.6.15.6

	 * Add low memory identity-mappings - SMP needs it when
	 * starting up on an AP from real-mode. In the non-PAE
	 * case we already have these mappings through head.S.
	 * All user-space mappings are explicitly cleared after
	 * SMP startup.
	 */
	set_pgd(&pgd_base[0], pgd_base[USER_PTRS_PER_PGD]);
#endif
}

#ifdef CONFIG_SOFTWARE_SUSPEND
/*
 * Swap suspend & friends need this for resume because things like the intel-agp
 * driver might have split up a kernel 4MB mapping.
 */
char __nosavedata swsusp_pg_dir[PAGE_SIZE]
	__attribute__ ((aligned (PAGE_SIZE)));

static inline void save_pg_dir(void)
{
	memcpy(swsusp_pg_dir, swapper_pg_dir, PAGE_SIZE);
}
#else
static inline void save_pg_dir(void)
{
}
#endif

void zap_low_mappings (void)
{
	int i;

	save_pg_dir();

	/*
	 * Zap initial low-memory mappings.
	 *
	 * Note that "pgd_clear()" doesn't do it for
	 * us, because pgd_clear() is a no-op on i386.
	 */
	for (i = 0; i < USER_PTRS_PER_PGD; i++)
#ifdef CONFIG_X86_PAE
		set_pgd(swapper_pg_dir+i, __pgd(1 + __pa(empty_zero_page)));
#else
		set_pgd(swapper_pg_dir+i, __pgd(0));
#endif
	flush_tlb_all();
}

static int disable_nx __initdata = 0;
u64 __supported_pte_mask __read_mostly = ~_PAGE_NX;

/*
 * noexec = on|off
 *
 * Control non executable mappings.
 *
 * on      Enable
 * off     Disable
 */
void __init noexec_setup(const char *str)
{
	if (!strncmp(str, "on",2) && cpu_has_nx) {
		__supported_pte_mask |= _PAGE_NX;
		disable_nx = 0;
	} else if (!strncmp(str,"off",3)) {
		disable_nx = 1;
		__supported_pte_mask &= ~_PAGE_NX;
	}
}

int nx_enabled = 0;
#ifdef CONFIG_X86_PAE

static void __init set_nx(void)
{
	unsigned int v[4], l, h;

	if (cpu_has_pae && (cpuid_eax(0x80000000) > 0x80000001)) {
		cpuid(0x80000001, &v[0], &v[1], &v[2], &v[3]);
		if ((v[3] & (1 << 20)) && !disable_nx) {
			rdmsr(MSR_EFER, l, h);
			l |= EFER_NX;
			wrmsr(MSR_EFER, l, h);
			nx_enabled = 1;
			__supported_pte_mask |= _PAGE_NX;
		}
	}
}

/*
 * Enables/disables executability of a given kernel page and
 * returns the previous setting.
 */
int __init set_kernel_exec(unsigned long vaddr, int enable)
{
	pte_t *pte;
	int ret = 1;

	if (!nx_enabled)
		goto out;

	pte = lookup_address(vaddr);
	BUG_ON(!pte);

	if (!pte_exec_kernel(*pte))
		ret = 0;

	if (enable)
		pte->pte_high &= ~(1 << (_PAGE_BIT_NX - 32));
	else
		pte->pte_high |= 1 << (_PAGE_BIT_NX - 32);
	__flush_tlb_all();
out:
	return ret;
}

#endif

/*
 * paging_init() sets up the page tables - note that the first 8MB are
 * already mapped by head.S.
 *
 * This routines also unmaps the page at virtual kernel address 0, so
 * that we can trap those pesky NULL-reference errors in the kernel.
 */
void __init paging_init(void)
{
#ifdef CONFIG_X86_PAE
	set_nx();
	if (nx_enabled)
		printk("NX (Execute Disable) protection: active\n");
#endif

	pagetable_init();

	load_cr3(swapper_pg_dir);

#ifdef CONFIG_X86_PAE
	/*
	 * We will bail out later - printk doesn't work right now so
	 * the user would just see a hanging kernel.
	 */
	if (cpu_has_pae)
		set_in_cr4(X86_CR4_PAE);
#endif
	__flush_tlb_all();

	kmap_init();
}

/*
 * 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. This
 * used to involve black magic jumps to work around some nasty CPU bugs,
 * but fortunately the switch to using exceptions got rid of all that.
 */

static void __init test_wp_bit(void)
{
	printk("Checking if this processor honours the WP bit even in supervisor mode... ");

	/* Any page-aligned address will do, the test is non-destructive */
	__set_fixmap(FIX_WP_TEST, __pa(&swapper_pg_dir), PAGE_READONLY);
	boot_cpu_data.wp_works_ok = do_test_wp_bit();
	clear_fixmap(FIX_WP_TEST);

	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 void __init set_max_mapnr_init(void)
{
#ifdef CONFIG_HIGHMEM
	num_physpages = highend_pfn;
#else
	num_physpages = max_low_pfn;
#endif
#ifdef CONFIG_FLATMEM
	max_mapnr = num_physpages;
#endif
}

static struct kcore_list kcore_mem, kcore_vmalloc; 

void __init mem_init(void)
{
	extern int ppro_with_ram_bug(void);
	int codesize, reservedpages, datasize, initsize;
	int tmp;
	int bad_ppro;

#ifdef CONFIG_FLATMEM
	if (!mem_map)
		BUG();
#endif
	
	bad_ppro = ppro_with_ram_bug();

#ifdef CONFIG_HIGHMEM
	/* check that fixmap and pkmap do not overlap */
	if (PKMAP_BASE+LAST_PKMAP*PAGE_SIZE >= FIXADDR_START) {
		printk(KERN_ERR "fixmap and kmap areas overlap - this will crash\n");
		printk(KERN_ERR "pkstart: %lxh pkend: %lxh fixstart %lxh\n",
				PKMAP_BASE, PKMAP_BASE+LAST_PKMAP*PAGE_SIZE, FIXADDR_START);
		BUG();
	}
#endif
 
	set_max_mapnr_init();

#ifdef CONFIG_HIGHMEM
	high_memory = (void *) __va(highstart_pfn * PAGE_SIZE - 1) + 1;
#else
	high_memory = (void *) __va(max_low_pfn * PAGE_SIZE - 1) + 1;
#endif

	/* 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(pfn_to_page(tmp)))
			reservedpages++;

	set_highmem_pages_init(bad_ppro);

	codesize =  (unsigned long) &_etext - (unsigned long) &_text;
	datasize =  (unsigned long) &_edata - (unsigned long) &_etext;
	initsize =  (unsigned long) &__init_end - (unsigned long) &__init_begin;

	kclist_add(&kcore_mem, __va(0), max_low_pfn << PAGE_SHIFT); 
	kclist_add(&kcore_vmalloc, (void *)VMALLOC_START, 
		   VMALLOC_END-VMALLOC_START);

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

#ifdef 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
}

/*
 * this is for the non-NUMA, single node SMP system case.
 * Specifically, in the case of x86, we will always add
 * memory to the highmem for now.
 */
#ifndef CONFIG_NEED_MULTIPLE_NODES
int add_memory(u64 start, u64 size)
{
	struct pglist_data *pgdata = &contig_page_data;
	struct zone *zone = pgdata->node_zones + MAX_NR_ZONES-1;
	unsigned long start_pfn = start >> PAGE_SHIFT;
	unsigned long nr_pages = size >> PAGE_SHIFT;

	return __add_pages(zone, start_pfn, nr_pages);
}

int remove_memory(u64 start, u64 size)
{
	return -EINVAL;
}
#endif

kmem_cache_t *pgd_cache;
kmem_cache_t *pmd_cache;

void __init pgtable_cache_init(void)
{
	if (PTRS_PER_PMD > 1) {
		pmd_cache = kmem_cache_create("pmd",
					PTRS_PER_PMD*sizeof(pmd_t),
					PTRS_PER_PMD*sizeof(pmd_t),
					0,
					pmd_ctor,
					NULL);
		if (!pmd_cache)
			panic("pgtable_cache_init(): cannot create pmd cache");
	}
	pgd_cache = kmem_cache_create("pgd",
				PTRS_PER_PGD*sizeof(pgd_t),
				PTRS_PER_PGD*sizeof(pgd_t),
				0,
				pgd_ctor,
				PTRS_PER_PMD == 1 ? pgd_dtor : NULL);
	if (!pgd_cache)
		panic("pgtable_cache_init(): Cannot create pgd cache");
}

/*
 * This function cannot be __init, since exceptions don't work in that
 * section.  Put this after the callers, so that it cannot be inlined.
 */
static int noinline do_test_wp_bit(void)
{
	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 *)fix_to_virt(FIX_WP_TEST)),
		 "=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);
		memset((void *)addr, 0xcc, PAGE_SIZE);
		free_page(addr);
		totalram_pages++;
	}
	printk (KERN_INFO "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 (KERN_INFO "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