init_32.c 21.7 KB
Newer Older
L
Linus Torvalds 已提交
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24
/*
 *  linux/arch/i386/mm/init.c
 *
 *  Copyright (C) 1995  Linus Torvalds
 *
 *  Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999
 */

#include <linux/module.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/hugetlb.h>
#include <linux/swap.h>
#include <linux/smp.h>
#include <linux/init.h>
#include <linux/highmem.h>
#include <linux/pagemap.h>
25
#include <linux/pfn.h>
26
#include <linux/poison.h>
L
Linus Torvalds 已提交
27 28 29
#include <linux/bootmem.h>
#include <linux/slab.h>
#include <linux/proc_fs.h>
30
#include <linux/memory_hotplug.h>
31
#include <linux/initrd.h>
32
#include <linux/cpumask.h>
L
Linus Torvalds 已提交
33 34 35 36 37 38 39 40 41 42 43

#include <asm/processor.h>
#include <asm/system.h>
#include <asm/uaccess.h>
#include <asm/pgtable.h>
#include <asm/dma.h>
#include <asm/fixmap.h>
#include <asm/e820.h>
#include <asm/apic.h>
#include <asm/tlb.h>
#include <asm/tlbflush.h>
44
#include <asm/pgalloc.h>
L
Linus Torvalds 已提交
45
#include <asm/sections.h>
46
#include <asm/paravirt.h>
L
Linus Torvalds 已提交
47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65

unsigned int __VMALLOC_RESERVE = 128 << 20;

DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
unsigned long highstart_pfn, highend_pfn;

static int noinline do_test_wp_bit(void);

/*
 * Creates a middle page table and puts a pointer to it in the
 * given global directory entry. This only returns the gd entry
 * in non-PAE compilation mode, since the middle layer is folded.
 */
static pmd_t * __init one_md_table_init(pgd_t *pgd)
{
	pud_t *pud;
	pmd_t *pmd_table;
		
#ifdef CONFIG_X86_PAE
66 67 68
	if (!(pgd_val(*pgd) & _PAGE_PRESENT)) {
		pmd_table = (pmd_t *) alloc_bootmem_low_pages(PAGE_SIZE);

69
		paravirt_alloc_pd(&init_mm, __pa(pmd_table) >> PAGE_SHIFT);
70 71 72 73 74 75
		set_pgd(pgd, __pgd(__pa(pmd_table) | _PAGE_PRESENT));
		pud = pud_offset(pgd, 0);
		if (pmd_table != pmd_offset(pud, 0))
			BUG();
	}
#endif
L
Linus Torvalds 已提交
76 77 78 79 80 81 82 83 84 85 86
	pud = pud_offset(pgd, 0);
	pmd_table = pmd_offset(pud, 0);
	return pmd_table;
}

/*
 * Create a page table and place a pointer to it in a middle page
 * directory entry.
 */
static pte_t * __init one_page_table_init(pmd_t *pmd)
{
87
	if (!(pmd_val(*pmd) & _PAGE_PRESENT)) {
88 89 90 91 92 93 94 95
		pte_t *page_table = NULL;

#ifdef CONFIG_DEBUG_PAGEALLOC
		page_table = (pte_t *) alloc_bootmem_pages(PAGE_SIZE);
#endif
		if (!page_table)
			page_table =
				(pte_t *)alloc_bootmem_low_pages(PAGE_SIZE);
96

97
		paravirt_alloc_pt(&init_mm, __pa(page_table) >> PAGE_SHIFT);
L
Linus Torvalds 已提交
98
		set_pmd(pmd, __pmd(__pa(page_table) | _PAGE_TABLE));
99
		BUG_ON(page_table != pte_offset_kernel(pmd, 0));
L
Linus Torvalds 已提交
100
	}
101

L
Linus Torvalds 已提交
102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128
	return pte_offset_kernel(pmd, 0);
}

/*
 * This function initializes a certain range of kernel virtual memory 
 * with new bootmem page tables, everywhere page tables are missing in
 * the given range.
 */

/*
 * NOTE: The pagetables are allocated contiguous on the physical space 
 * so we can cache the place of the first one and move around without 
 * checking the pgd every time.
 */
static void __init page_table_range_init (unsigned long start, unsigned long end, pgd_t *pgd_base)
{
	pgd_t *pgd;
	pmd_t *pmd;
	int pgd_idx, pmd_idx;
	unsigned long vaddr;

	vaddr = start;
	pgd_idx = pgd_index(vaddr);
	pmd_idx = pmd_index(vaddr);
	pgd = pgd_base + pgd_idx;

	for ( ; (pgd_idx < PTRS_PER_PGD) && (vaddr != end); pgd++, pgd_idx++) {
129 130
		pmd = one_md_table_init(pgd);
		pmd = pmd + pmd_index(vaddr);
L
Linus Torvalds 已提交
131
		for (; (pmd_idx < PTRS_PER_PMD) && (vaddr != end); pmd++, pmd_idx++) {
132
			one_page_table_init(pmd);
L
Linus Torvalds 已提交
133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167

			vaddr += PMD_SIZE;
		}
		pmd_idx = 0;
	}
}

static inline int is_kernel_text(unsigned long addr)
{
	if (addr >= PAGE_OFFSET && addr <= (unsigned long)__init_end)
		return 1;
	return 0;
}

/*
 * This maps the physical memory to kernel virtual address space, a total 
 * of max_low_pfn pages, by creating page tables starting from address 
 * PAGE_OFFSET.
 */
static void __init kernel_physical_mapping_init(pgd_t *pgd_base)
{
	unsigned long pfn;
	pgd_t *pgd;
	pmd_t *pmd;
	pte_t *pte;
	int pgd_idx, pmd_idx, pte_ofs;

	pgd_idx = pgd_index(PAGE_OFFSET);
	pgd = pgd_base + pgd_idx;
	pfn = 0;

	for (; pgd_idx < PTRS_PER_PGD; pgd++, pgd_idx++) {
		pmd = one_md_table_init(pgd);
		if (pfn >= max_low_pfn)
			continue;
J
Jeremy Fitzhardinge 已提交
168 169 170
		for (pmd_idx = 0;
		     pmd_idx < PTRS_PER_PMD && pfn < max_low_pfn;
		     pmd++, pmd_idx++) {
L
Linus Torvalds 已提交
171 172
			unsigned int address = pfn * PAGE_SIZE + PAGE_OFFSET;

J
Jeremy Fitzhardinge 已提交
173 174
			/* Map with big pages if possible, otherwise
			   create normal page tables. */
L
Linus Torvalds 已提交
175
			if (cpu_has_pse) {
J
Jeremy Fitzhardinge 已提交
176 177 178 179 180 181 182 183 184 185 186
				unsigned int address2;
				pgprot_t prot = PAGE_KERNEL_LARGE;

				address2 = (pfn + PTRS_PER_PTE - 1) * PAGE_SIZE +
					PAGE_OFFSET + PAGE_SIZE-1;

				if (is_kernel_text(address) ||
				    is_kernel_text(address2))
					prot = PAGE_KERNEL_LARGE_EXEC;

				set_pmd(pmd, pfn_pmd(pfn, prot));
187

L
Linus Torvalds 已提交
188 189 190 191
				pfn += PTRS_PER_PTE;
			} else {
				pte = one_page_table_init(pmd);

192 193 194
				for (pte_ofs = 0;
				     pte_ofs < PTRS_PER_PTE && pfn < max_low_pfn;
				     pte++, pfn++, pte_ofs++, address += PAGE_SIZE) {
J
Jeremy Fitzhardinge 已提交
195 196
					pgprot_t prot = PAGE_KERNEL;

197
					if (is_kernel_text(address))
J
Jeremy Fitzhardinge 已提交
198 199 200
						prot = PAGE_KERNEL_EXEC;

					set_pte(pte, pfn_pte(pfn, prot));
L
Linus Torvalds 已提交
201 202 203 204 205 206 207 208 209 210 211 212 213
				}
			}
		}
	}
}

static inline int page_kills_ppro(unsigned long pagenr)
{
	if (pagenr >= 0x70000 && pagenr <= 0x7003F)
		return 1;
	return 0;
}

214
int page_is_ram(unsigned long pagenr)
L
Linus Torvalds 已提交
215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271
{
	int i;
	unsigned long addr, end;

	for (i = 0; i < e820.nr_map; i++) {

		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;
}

#ifdef CONFIG_HIGHMEM
pte_t *kmap_pte;
pgprot_t kmap_prot;

#define kmap_get_fixmap_pte(vaddr)					\
	pte_offset_kernel(pmd_offset(pud_offset(pgd_offset_k(vaddr), vaddr), (vaddr)), (vaddr))

static void __init kmap_init(void)
{
	unsigned long kmap_vstart;

	/* cache the first kmap pte */
	kmap_vstart = __fix_to_virt(FIX_KMAP_BEGIN);
	kmap_pte = kmap_get_fixmap_pte(kmap_vstart);

	kmap_prot = PAGE_KERNEL;
}

static void __init permanent_kmaps_init(pgd_t *pgd_base)
{
	pgd_t *pgd;
	pud_t *pud;
	pmd_t *pmd;
	pte_t *pte;
	unsigned long vaddr;

	vaddr = PKMAP_BASE;
	page_table_range_init(vaddr, vaddr + PAGE_SIZE*LAST_PKMAP, pgd_base);

	pgd = swapper_pg_dir + pgd_index(vaddr);
	pud = pud_offset(pgd, vaddr);
	pmd = pmd_offset(pud, vaddr);
	pte = pte_offset_kernel(pmd, vaddr);
	pkmap_page_table = pte;	
}

272
static void __meminit free_new_highpage(struct page *page)
273
{
274
	init_page_count(page);
275 276 277 278 279
	__free_page(page);
	totalhigh_pages++;
}

void __init add_one_highpage_init(struct page *page, int pfn, int bad_ppro)
L
Linus Torvalds 已提交
280 281 282
{
	if (page_is_ram(pfn) && !(bad_ppro && page_kills_ppro(pfn))) {
		ClearPageReserved(page);
283
		free_new_highpage(page);
L
Linus Torvalds 已提交
284 285 286 287
	} else
		SetPageReserved(page);
}

288
static int __meminit add_one_highpage_hotplug(struct page *page, unsigned long pfn)
289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304
{
	free_new_highpage(page);
	totalram_pages++;
#ifdef CONFIG_FLATMEM
	max_mapnr = max(pfn, max_mapnr);
#endif
	num_physpages++;
	return 0;
}

/*
 * Not currently handling the NUMA case.
 * Assuming single node and all memory that
 * has been added dynamically that would be
 * onlined here is in HIGHMEM
 */
305
void __meminit online_page(struct page *page)
306 307 308 309 310 311
{
	ClearPageReserved(page);
	add_one_highpage_hotplug(page, page_to_pfn(page));
}


312 313 314
#ifdef CONFIG_NUMA
extern void set_highmem_pages_init(int);
#else
L
Linus Torvalds 已提交
315 316 317
static void __init set_highmem_pages_init(int bad_ppro)
{
	int pfn;
318 319 320 321 322 323 324
	for (pfn = highstart_pfn; pfn < highend_pfn; pfn++) {
		/*
		 * Holes under sparsemem might not have no mem_map[]:
		 */
		if (pfn_valid(pfn))
			add_one_highpage_init(pfn_to_page(pfn), pfn, bad_ppro);
	}
L
Linus Torvalds 已提交
325 326
	totalram_pages += totalhigh_pages;
}
327
#endif /* CONFIG_FLATMEM */
L
Linus Torvalds 已提交
328 329 330 331 332 333 334 335

#else
#define kmap_init() do { } while (0)
#define permanent_kmaps_init(pgd_base) do { } while (0)
#define set_highmem_pages_init(bad_ppro) do { } while (0)
#endif /* CONFIG_HIGHMEM */

unsigned long long __PAGE_KERNEL = _PAGE_KERNEL;
336
EXPORT_SYMBOL(__PAGE_KERNEL);
L
Linus Torvalds 已提交
337 338
unsigned long long __PAGE_KERNEL_EXEC = _PAGE_KERNEL_EXEC;

339
#ifdef CONFIG_NUMA
L
Linus Torvalds 已提交
340
extern void __init remap_numa_kva(void);
341 342
#else
#define remap_numa_kva() do {} while (0)
L
Linus Torvalds 已提交
343 344
#endif

345
void __init native_pagetable_setup_start(pgd_t *base)
L
Linus Torvalds 已提交
346 347 348
{
#ifdef CONFIG_X86_PAE
	int i;
349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367

	/*
	 * Init entries of the first-level page table to the
	 * zero page, if they haven't already been set up.
	 *
	 * In a normal native boot, we'll be running on a
	 * pagetable rooted in swapper_pg_dir, but not in PAE
	 * mode, so this will end up clobbering the mappings
	 * for the lower 24Mbytes of the address space,
	 * without affecting the kernel address space.
	 */
	for (i = 0; i < USER_PTRS_PER_PGD; i++)
		set_pgd(&base[i],
			__pgd(__pa(empty_zero_page) | _PAGE_PRESENT));

	/* Make sure kernel address space is empty so that a pagetable
	   will be allocated for it. */
	memset(&base[USER_PTRS_PER_PGD], 0,
	       KERNEL_PGD_PTRS * sizeof(pgd_t));
368
#else
369
	paravirt_alloc_pd(&init_mm, __pa(base) >> PAGE_SHIFT);
L
Linus Torvalds 已提交
370
#endif
371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412
}

void __init native_pagetable_setup_done(pgd_t *base)
{
#ifdef CONFIG_X86_PAE
	/*
	 * 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(&base[0], base[USER_PTRS_PER_PGD]);
#endif
}

/*
 * Build a proper pagetable for the kernel mappings.  Up until this
 * point, we've been running on some set of pagetables constructed by
 * the boot process.
 *
 * If we're booting on native hardware, this will be a pagetable
 * constructed in arch/i386/kernel/head.S, and not running in PAE mode
 * (even if we'll end up running in PAE).  The root of the pagetable
 * will be swapper_pg_dir.
 *
 * If we're booting paravirtualized under a hypervisor, then there are
 * more options: we may already be running PAE, and the pagetable may
 * or may not be based in swapper_pg_dir.  In any case,
 * paravirt_pagetable_setup_start() will set up swapper_pg_dir
 * appropriately for the rest of the initialization to work.
 *
 * In general, pagetable_init() assumes that the pagetable may already
 * be partially populated, and so it avoids stomping on any existing
 * mappings.
 */
static void __init pagetable_init (void)
{
	unsigned long vaddr, end;
	pgd_t *pgd_base = swapper_pg_dir;

	paravirt_pagetable_setup_start(pgd_base);
L
Linus Torvalds 已提交
413 414

	/* Enable PSE if available */
415
	if (cpu_has_pse)
L
Linus Torvalds 已提交
416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432
		set_in_cr4(X86_CR4_PSE);

	/* Enable PGE if available */
	if (cpu_has_pge) {
		set_in_cr4(X86_CR4_PGE);
		__PAGE_KERNEL |= _PAGE_GLOBAL;
		__PAGE_KERNEL_EXEC |= _PAGE_GLOBAL;
	}

	kernel_physical_mapping_init(pgd_base);
	remap_numa_kva();

	/*
	 * Fixed mappings, only the page table structure has to be
	 * created - mappings will be set by set_fixmap():
	 */
	vaddr = __fix_to_virt(__end_of_fixed_addresses - 1) & PMD_MASK;
433 434
	end = (FIXADDR_TOP + PMD_SIZE - 1) & PMD_MASK;
	page_table_range_init(vaddr, end, pgd_base);
L
Linus Torvalds 已提交
435 436 437

	permanent_kmaps_init(pgd_base);

438
	paravirt_pagetable_setup_done(pgd_base);
L
Linus Torvalds 已提交
439 440
}

441
#if defined(CONFIG_HIBERNATION) || defined(CONFIG_ACPI)
L
Linus Torvalds 已提交
442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479
/*
 * 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();
}

J
Jan Beulich 已提交
480 481
int nx_enabled = 0;

482 483 484
pteval_t __supported_pte_mask __read_mostly = ~_PAGE_NX;
EXPORT_SYMBOL_GPL(__supported_pte_mask);

J
Jan Beulich 已提交
485 486
#ifdef CONFIG_X86_PAE

L
Linus Torvalds 已提交
487 488 489 490 491 492 493 494 495 496
static int disable_nx __initdata = 0;

/*
 * noexec = on|off
 *
 * Control non executable mappings.
 *
 * on      Enable
 * off     Disable
 */
497
static int __init noexec_setup(char *str)
L
Linus Torvalds 已提交
498
{
499 500 501 502 503 504
	if (!str || !strcmp(str, "on")) {
		if (cpu_has_nx) {
			__supported_pte_mask |= _PAGE_NX;
			disable_nx = 0;
		}
	} else if (!strcmp(str,"off")) {
L
Linus Torvalds 已提交
505 506
		disable_nx = 1;
		__supported_pte_mask &= ~_PAGE_NX;
507 508 509 510
	} else
		return -EINVAL;

	return 0;
L
Linus Torvalds 已提交
511
}
512
early_param("noexec", noexec_setup);
L
Linus Torvalds 已提交
513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544

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);

A
Andi Kleen 已提交
545
	if (!pte_exec(*pte))
L
Linus Torvalds 已提交
546 547 548 549 550 551
		ret = 0;

	if (enable)
		pte->pte_high &= ~(1 << (_PAGE_BIT_NX - 32));
	else
		pte->pte_high |= 1 << (_PAGE_BIT_NX - 32);
Z
Zachary Amsden 已提交
552
	pte_update_defer(&init_mm, vaddr, pte);
L
Linus Torvalds 已提交
553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626
	__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 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;

627
#ifdef CONFIG_FLATMEM
E
Eric Sesterhenn 已提交
628
	BUG_ON(!mem_map);
L
Linus Torvalds 已提交
629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673
#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
 
	/* 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))
	       );

674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715
#if 1 /* double-sanity-check paranoia */
	printk("virtual kernel memory layout:\n"
	       "    fixmap  : 0x%08lx - 0x%08lx   (%4ld kB)\n"
#ifdef CONFIG_HIGHMEM
	       "    pkmap   : 0x%08lx - 0x%08lx   (%4ld kB)\n"
#endif
	       "    vmalloc : 0x%08lx - 0x%08lx   (%4ld MB)\n"
	       "    lowmem  : 0x%08lx - 0x%08lx   (%4ld MB)\n"
	       "      .init : 0x%08lx - 0x%08lx   (%4ld kB)\n"
	       "      .data : 0x%08lx - 0x%08lx   (%4ld kB)\n"
	       "      .text : 0x%08lx - 0x%08lx   (%4ld kB)\n",
	       FIXADDR_START, FIXADDR_TOP,
	       (FIXADDR_TOP - FIXADDR_START) >> 10,

#ifdef CONFIG_HIGHMEM
	       PKMAP_BASE, PKMAP_BASE+LAST_PKMAP*PAGE_SIZE,
	       (LAST_PKMAP*PAGE_SIZE) >> 10,
#endif

	       VMALLOC_START, VMALLOC_END,
	       (VMALLOC_END - VMALLOC_START) >> 20,

	       (unsigned long)__va(0), (unsigned long)high_memory,
	       ((unsigned long)high_memory - (unsigned long)__va(0)) >> 20,

	       (unsigned long)&__init_begin, (unsigned long)&__init_end,
	       ((unsigned long)&__init_end - (unsigned long)&__init_begin) >> 10,

	       (unsigned long)&_etext, (unsigned long)&_edata,
	       ((unsigned long)&_edata - (unsigned long)&_etext) >> 10,

	       (unsigned long)&_text, (unsigned long)&_etext,
	       ((unsigned long)&_etext - (unsigned long)&_text) >> 10);

#ifdef CONFIG_HIGHMEM
	BUG_ON(PKMAP_BASE+LAST_PKMAP*PAGE_SIZE > FIXADDR_START);
	BUG_ON(VMALLOC_END                     > PKMAP_BASE);
#endif
	BUG_ON(VMALLOC_START                   > VMALLOC_END);
	BUG_ON((unsigned long)high_memory      > VMALLOC_START);
#endif /* double-sanity-check paranoia */

L
Linus Torvalds 已提交
716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733
#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
}

734
#ifdef CONFIG_MEMORY_HOTPLUG
735
int arch_add_memory(int nid, u64 start, u64 size)
736
{
737
	struct pglist_data *pgdata = NODE_DATA(nid);
738
	struct zone *zone = pgdata->node_zones + ZONE_HIGHMEM;
739 740 741 742 743 744
	unsigned long start_pfn = start >> PAGE_SHIFT;
	unsigned long nr_pages = size >> PAGE_SHIFT;

	return __add_pages(zone, start_pfn, nr_pages);
}

745
#endif
746

747
struct kmem_cache *pmd_cache;
L
Linus Torvalds 已提交
748 749 750

void __init pgtable_cache_init(void)
{
751
	if (PTRS_PER_PMD > 1)
L
Linus Torvalds 已提交
752
		pmd_cache = kmem_cache_create("pmd",
753 754 755 756
					      PTRS_PER_PMD*sizeof(pmd_t),
					      PTRS_PER_PMD*sizeof(pmd_t),
					      SLAB_PANIC,
					      pmd_ctor);
L
Linus Torvalds 已提交
757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785
}

/*
 * 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;
}

786 787 788 789
#ifdef CONFIG_DEBUG_RODATA

void mark_rodata_ro(void)
{
790 791
	unsigned long start = PFN_ALIGN(_text);
	unsigned long size = PFN_ALIGN(_etext) - start;
792

793 794 795 796 797 798 799 800 801
#ifndef CONFIG_KPROBES
#ifdef CONFIG_HOTPLUG_CPU
	/* It must still be possible to apply SMP alternatives. */
	if (num_possible_cpus() <= 1)
#endif
	{
		change_page_attr(virt_to_page(start),
		                 size >> PAGE_SHIFT, PAGE_KERNEL_RX);
		printk("Write protecting the kernel text: %luk\n", size >> 10);
802 803 804 805 806 807 808 809 810 811 812 813 814 815

#ifdef CONFIG_CPA_DEBUG
		global_flush_tlb();

		printk("Testing CPA: Reverting %lx-%lx\n", start, start+size);
		change_page_attr(virt_to_page(start), size>>PAGE_SHIFT,
				 PAGE_KERNEL_EXEC);
		global_flush_tlb();

		printk("Testing CPA: write protecting again\n");
		change_page_attr(virt_to_page(start), size>>PAGE_SHIFT,
				PAGE_KERNEL_RX);
		global_flush_tlb();
#endif
816 817
	}
#endif
818 819 820 821 822 823
	start += size;
	size = (unsigned long)__end_rodata - start;
	change_page_attr(virt_to_page(start),
	                 size >> PAGE_SHIFT, PAGE_KERNEL_RO);
	printk("Write protecting the kernel read-only data: %luk\n",
	       size >> 10);
824 825 826 827 828 829 830 831

	/*
	 * change_page_attr() requires a global_flush_tlb() call after it.
	 * We do this after the printk so that if something went wrong in the
	 * change, the printk gets out at least to give a better debug hint
	 * of who is the culprit.
	 */
	global_flush_tlb();
832 833 834 835 836 837 838 839 840 841 842 843

#ifdef CONFIG_CPA_DEBUG
	printk("Testing CPA: undo %lx-%lx\n", start, start + size);
	change_page_attr(virt_to_page(start), size >> PAGE_SHIFT,
				PAGE_KERNEL);
	global_flush_tlb();

	printk("Testing CPA: write protecting again\n");
	change_page_attr(virt_to_page(start), size >> PAGE_SHIFT,
				PAGE_KERNEL_RO);
	global_flush_tlb();
#endif
844 845 846
}
#endif

G
Gerd Hoffmann 已提交
847 848 849 850 851
void free_init_pages(char *what, unsigned long begin, unsigned long end)
{
	unsigned long addr;

	for (addr = begin; addr < end; addr += PAGE_SIZE) {
852 853 854 855
		ClearPageReserved(virt_to_page(addr));
		init_page_count(virt_to_page(addr));
		memset((void *)addr, POISON_FREE_INITMEM, PAGE_SIZE);
		free_page(addr);
G
Gerd Hoffmann 已提交
856 857
		totalram_pages++;
	}
858
	printk(KERN_INFO "Freeing %s: %luk freed\n", what, (end - begin) >> 10);
G
Gerd Hoffmann 已提交
859 860 861 862 863
}

void free_initmem(void)
{
	free_init_pages("unused kernel memory",
864 865
			(unsigned long)(&__init_begin),
			(unsigned long)(&__init_end));
G
Gerd Hoffmann 已提交
866
}
867

L
Linus Torvalds 已提交
868 869 870
#ifdef CONFIG_BLK_DEV_INITRD
void free_initrd_mem(unsigned long start, unsigned long end)
{
871
	free_init_pages("initrd memory", start, end);
L
Linus Torvalds 已提交
872 873
}
#endif
G
Gerd Hoffmann 已提交
874