memory.c 58.7 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 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112
/*
 *  linux/mm/memory.c
 *
 *  Copyright (C) 1991, 1992, 1993, 1994  Linus Torvalds
 */

/*
 * demand-loading started 01.12.91 - seems it is high on the list of
 * things wanted, and it should be easy to implement. - Linus
 */

/*
 * Ok, demand-loading was easy, shared pages a little bit tricker. Shared
 * pages started 02.12.91, seems to work. - Linus.
 *
 * Tested sharing by executing about 30 /bin/sh: under the old kernel it
 * would have taken more than the 6M I have free, but it worked well as
 * far as I could see.
 *
 * Also corrected some "invalidate()"s - I wasn't doing enough of them.
 */

/*
 * Real VM (paging to/from disk) started 18.12.91. Much more work and
 * thought has to go into this. Oh, well..
 * 19.12.91  -  works, somewhat. Sometimes I get faults, don't know why.
 *		Found it. Everything seems to work now.
 * 20.12.91  -  Ok, making the swap-device changeable like the root.
 */

/*
 * 05.04.94  -  Multi-page memory management added for v1.1.
 * 		Idea by Alex Bligh (alex@cconcepts.co.uk)
 *
 * 16.07.99  -  Support of BIGMEM added by Gerhard Wichert, Siemens AG
 *		(Gerhard.Wichert@pdb.siemens.de)
 *
 * Aug/Sep 2004 Changed to four level page tables (Andi Kleen)
 */

#include <linux/kernel_stat.h>
#include <linux/mm.h>
#include <linux/hugetlb.h>
#include <linux/mman.h>
#include <linux/swap.h>
#include <linux/highmem.h>
#include <linux/pagemap.h>
#include <linux/rmap.h>
#include <linux/module.h>
#include <linux/init.h>

#include <asm/pgalloc.h>
#include <asm/uaccess.h>
#include <asm/tlb.h>
#include <asm/tlbflush.h>
#include <asm/pgtable.h>

#include <linux/swapops.h>
#include <linux/elf.h>

#ifndef CONFIG_DISCONTIGMEM
/* use the per-pgdat data instead for discontigmem - mbligh */
unsigned long max_mapnr;
struct page *mem_map;

EXPORT_SYMBOL(max_mapnr);
EXPORT_SYMBOL(mem_map);
#endif

unsigned long num_physpages;
/*
 * A number of key systems in x86 including ioremap() rely on the assumption
 * that high_memory defines the upper bound on direct map memory, then end
 * of ZONE_NORMAL.  Under CONFIG_DISCONTIG this means that max_low_pfn and
 * highstart_pfn must be the same; there must be no gap between ZONE_NORMAL
 * and ZONE_HIGHMEM.
 */
void * high_memory;
unsigned long vmalloc_earlyreserve;

EXPORT_SYMBOL(num_physpages);
EXPORT_SYMBOL(high_memory);
EXPORT_SYMBOL(vmalloc_earlyreserve);

/*
 * If a p?d_bad entry is found while walking page tables, report
 * the error, before resetting entry to p?d_none.  Usually (but
 * very seldom) called out from the p?d_none_or_clear_bad macros.
 */

void pgd_clear_bad(pgd_t *pgd)
{
	pgd_ERROR(*pgd);
	pgd_clear(pgd);
}

void pud_clear_bad(pud_t *pud)
{
	pud_ERROR(*pud);
	pud_clear(pud);
}

void pmd_clear_bad(pmd_t *pmd)
{
	pmd_ERROR(*pmd);
	pmd_clear(pmd);
}

/*
 * Note: this doesn't free the actual pages themselves. That
 * has been handled earlier when unmapping all the memory regions.
 */
113
static void free_pte_range(struct mmu_gather *tlb, pmd_t *pmd)
L
Linus Torvalds 已提交
114
{
115 116 117 118 119
	struct page *page = pmd_page(*pmd);
	pmd_clear(pmd);
	pte_free_tlb(tlb, page);
	dec_page_state(nr_page_table_pages);
	tlb->mm->nr_ptes--;
L
Linus Torvalds 已提交
120 121
}

122 123 124
static inline void free_pmd_range(struct mmu_gather *tlb, pud_t *pud,
				unsigned long addr, unsigned long end,
				unsigned long floor, unsigned long ceiling)
L
Linus Torvalds 已提交
125 126 127
{
	pmd_t *pmd;
	unsigned long next;
128
	unsigned long start;
L
Linus Torvalds 已提交
129

130
	start = addr;
L
Linus Torvalds 已提交
131 132 133 134 135
	pmd = pmd_offset(pud, addr);
	do {
		next = pmd_addr_end(addr, end);
		if (pmd_none_or_clear_bad(pmd))
			continue;
136
		free_pte_range(tlb, pmd);
L
Linus Torvalds 已提交
137 138
	} while (pmd++, addr = next, addr != end);

139 140 141 142 143 144 145
	start &= PUD_MASK;
	if (start < floor)
		return;
	if (ceiling) {
		ceiling &= PUD_MASK;
		if (!ceiling)
			return;
L
Linus Torvalds 已提交
146
	}
147 148 149 150 151 152
	if (end - 1 > ceiling - 1)
		return;

	pmd = pmd_offset(pud, start);
	pud_clear(pud);
	pmd_free_tlb(tlb, pmd);
L
Linus Torvalds 已提交
153 154
}

155 156 157
static inline void free_pud_range(struct mmu_gather *tlb, pgd_t *pgd,
				unsigned long addr, unsigned long end,
				unsigned long floor, unsigned long ceiling)
L
Linus Torvalds 已提交
158 159 160
{
	pud_t *pud;
	unsigned long next;
161
	unsigned long start;
L
Linus Torvalds 已提交
162

163
	start = addr;
L
Linus Torvalds 已提交
164 165 166 167 168
	pud = pud_offset(pgd, addr);
	do {
		next = pud_addr_end(addr, end);
		if (pud_none_or_clear_bad(pud))
			continue;
169
		free_pmd_range(tlb, pud, addr, next, floor, ceiling);
L
Linus Torvalds 已提交
170 171
	} while (pud++, addr = next, addr != end);

172 173 174 175 176 177 178
	start &= PGDIR_MASK;
	if (start < floor)
		return;
	if (ceiling) {
		ceiling &= PGDIR_MASK;
		if (!ceiling)
			return;
L
Linus Torvalds 已提交
179
	}
180 181 182 183 184 185
	if (end - 1 > ceiling - 1)
		return;

	pud = pud_offset(pgd, start);
	pgd_clear(pgd);
	pud_free_tlb(tlb, pud);
L
Linus Torvalds 已提交
186 187 188
}

/*
189 190
 * This function frees user-level page tables of a process.
 *
L
Linus Torvalds 已提交
191 192
 * Must be called with pagetable lock held.
 */
193
void free_pgd_range(struct mmu_gather **tlb,
194 195
			unsigned long addr, unsigned long end,
			unsigned long floor, unsigned long ceiling)
L
Linus Torvalds 已提交
196 197 198
{
	pgd_t *pgd;
	unsigned long next;
199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225
	unsigned long start;

	/*
	 * The next few lines have given us lots of grief...
	 *
	 * Why are we testing PMD* at this top level?  Because often
	 * there will be no work to do at all, and we'd prefer not to
	 * go all the way down to the bottom just to discover that.
	 *
	 * Why all these "- 1"s?  Because 0 represents both the bottom
	 * of the address space and the top of it (using -1 for the
	 * top wouldn't help much: the masks would do the wrong thing).
	 * The rule is that addr 0 and floor 0 refer to the bottom of
	 * the address space, but end 0 and ceiling 0 refer to the top
	 * Comparisons need to use "end - 1" and "ceiling - 1" (though
	 * that end 0 case should be mythical).
	 *
	 * Wherever addr is brought up or ceiling brought down, we must
	 * be careful to reject "the opposite 0" before it confuses the
	 * subsequent tests.  But what about where end is brought down
	 * by PMD_SIZE below? no, end can't go down to 0 there.
	 *
	 * Whereas we round start (addr) and ceiling down, by different
	 * masks at different levels, in order to test whether a table
	 * now has no other vmas using it, so can be freed, we don't
	 * bother to round floor or end up - the tests don't need that.
	 */
L
Linus Torvalds 已提交
226

227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243
	addr &= PMD_MASK;
	if (addr < floor) {
		addr += PMD_SIZE;
		if (!addr)
			return;
	}
	if (ceiling) {
		ceiling &= PMD_MASK;
		if (!ceiling)
			return;
	}
	if (end - 1 > ceiling - 1)
		end -= PMD_SIZE;
	if (addr > end - 1)
		return;

	start = addr;
244
	pgd = pgd_offset((*tlb)->mm, addr);
L
Linus Torvalds 已提交
245 246 247 248
	do {
		next = pgd_addr_end(addr, end);
		if (pgd_none_or_clear_bad(pgd))
			continue;
249
		free_pud_range(*tlb, pgd, addr, next, floor, ceiling);
L
Linus Torvalds 已提交
250
	} while (pgd++, addr = next, addr != end);
251

252 253
	if (!tlb_is_full_mm(*tlb))
		flush_tlb_pgtables((*tlb)->mm, start, end);
254 255 256
}

void free_pgtables(struct mmu_gather **tlb, struct vm_area_struct *vma,
257
		unsigned long floor, unsigned long ceiling)
258 259 260 261 262
{
	while (vma) {
		struct vm_area_struct *next = vma->vm_next;
		unsigned long addr = vma->vm_start;

263 264
		if (is_hugepage_only_range(vma->vm_mm, addr, HPAGE_SIZE)) {
			hugetlb_free_pgd_range(tlb, addr, vma->vm_end,
265
				floor, next? next->vm_start: ceiling);
266 267 268 269 270 271 272 273 274 275 276 277 278
		} else {
			/*
			 * Optimization: gather nearby vmas into one call down
			 */
			while (next && next->vm_start <= vma->vm_end + PMD_SIZE
			  && !is_hugepage_only_range(vma->vm_mm, next->vm_start,
							HPAGE_SIZE)) {
				vma = next;
				next = vma->vm_next;
			}
			free_pgd_range(tlb, addr, vma->vm_end,
				floor, next? next->vm_start: ceiling);
		}
279 280
		vma = next;
	}
L
Linus Torvalds 已提交
281 282
}

283 284
pte_t fastcall *pte_alloc_map(struct mm_struct *mm, pmd_t *pmd,
				unsigned long address)
L
Linus Torvalds 已提交
285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657
{
	if (!pmd_present(*pmd)) {
		struct page *new;

		spin_unlock(&mm->page_table_lock);
		new = pte_alloc_one(mm, address);
		spin_lock(&mm->page_table_lock);
		if (!new)
			return NULL;
		/*
		 * Because we dropped the lock, we should re-check the
		 * entry, as somebody else could have populated it..
		 */
		if (pmd_present(*pmd)) {
			pte_free(new);
			goto out;
		}
		mm->nr_ptes++;
		inc_page_state(nr_page_table_pages);
		pmd_populate(mm, pmd, new);
	}
out:
	return pte_offset_map(pmd, address);
}

pte_t fastcall * pte_alloc_kernel(struct mm_struct *mm, pmd_t *pmd, unsigned long address)
{
	if (!pmd_present(*pmd)) {
		pte_t *new;

		spin_unlock(&mm->page_table_lock);
		new = pte_alloc_one_kernel(mm, address);
		spin_lock(&mm->page_table_lock);
		if (!new)
			return NULL;

		/*
		 * Because we dropped the lock, we should re-check the
		 * entry, as somebody else could have populated it..
		 */
		if (pmd_present(*pmd)) {
			pte_free_kernel(new);
			goto out;
		}
		pmd_populate_kernel(mm, pmd, new);
	}
out:
	return pte_offset_kernel(pmd, address);
}

/*
 * copy one vm_area from one task to the other. Assumes the page tables
 * already present in the new task to be cleared in the whole range
 * covered by this vma.
 *
 * dst->page_table_lock is held on entry and exit,
 * but may be dropped within p[mg]d_alloc() and pte_alloc_map().
 */

static inline void
copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
		pte_t *dst_pte, pte_t *src_pte, unsigned long vm_flags,
		unsigned long addr)
{
	pte_t pte = *src_pte;
	struct page *page;
	unsigned long pfn;

	/* pte contains position in swap or file, so copy. */
	if (unlikely(!pte_present(pte))) {
		if (!pte_file(pte)) {
			swap_duplicate(pte_to_swp_entry(pte));
			/* make sure dst_mm is on swapoff's mmlist. */
			if (unlikely(list_empty(&dst_mm->mmlist))) {
				spin_lock(&mmlist_lock);
				list_add(&dst_mm->mmlist, &src_mm->mmlist);
				spin_unlock(&mmlist_lock);
			}
		}
		set_pte_at(dst_mm, addr, dst_pte, pte);
		return;
	}

	pfn = pte_pfn(pte);
	/* the pte points outside of valid memory, the
	 * mapping is assumed to be good, meaningful
	 * and not mapped via rmap - duplicate the
	 * mapping as is.
	 */
	page = NULL;
	if (pfn_valid(pfn))
		page = pfn_to_page(pfn);

	if (!page || PageReserved(page)) {
		set_pte_at(dst_mm, addr, dst_pte, pte);
		return;
	}

	/*
	 * If it's a COW mapping, write protect it both
	 * in the parent and the child
	 */
	if ((vm_flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE) {
		ptep_set_wrprotect(src_mm, addr, src_pte);
		pte = *src_pte;
	}

	/*
	 * If it's a shared mapping, mark it clean in
	 * the child
	 */
	if (vm_flags & VM_SHARED)
		pte = pte_mkclean(pte);
	pte = pte_mkold(pte);
	get_page(page);
	inc_mm_counter(dst_mm, rss);
	if (PageAnon(page))
		inc_mm_counter(dst_mm, anon_rss);
	set_pte_at(dst_mm, addr, dst_pte, pte);
	page_dup_rmap(page);
}

static int copy_pte_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
		pmd_t *dst_pmd, pmd_t *src_pmd, struct vm_area_struct *vma,
		unsigned long addr, unsigned long end)
{
	pte_t *src_pte, *dst_pte;
	unsigned long vm_flags = vma->vm_flags;
	int progress;

again:
	dst_pte = pte_alloc_map(dst_mm, dst_pmd, addr);
	if (!dst_pte)
		return -ENOMEM;
	src_pte = pte_offset_map_nested(src_pmd, addr);

	progress = 0;
	spin_lock(&src_mm->page_table_lock);
	do {
		/*
		 * We are holding two locks at this point - either of them
		 * could generate latencies in another task on another CPU.
		 */
		if (progress >= 32 && (need_resched() ||
		    need_lockbreak(&src_mm->page_table_lock) ||
		    need_lockbreak(&dst_mm->page_table_lock)))
			break;
		if (pte_none(*src_pte)) {
			progress++;
			continue;
		}
		copy_one_pte(dst_mm, src_mm, dst_pte, src_pte, vm_flags, addr);
		progress += 8;
	} while (dst_pte++, src_pte++, addr += PAGE_SIZE, addr != end);
	spin_unlock(&src_mm->page_table_lock);

	pte_unmap_nested(src_pte - 1);
	pte_unmap(dst_pte - 1);
	cond_resched_lock(&dst_mm->page_table_lock);
	if (addr != end)
		goto again;
	return 0;
}

static inline int copy_pmd_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
		pud_t *dst_pud, pud_t *src_pud, struct vm_area_struct *vma,
		unsigned long addr, unsigned long end)
{
	pmd_t *src_pmd, *dst_pmd;
	unsigned long next;

	dst_pmd = pmd_alloc(dst_mm, dst_pud, addr);
	if (!dst_pmd)
		return -ENOMEM;
	src_pmd = pmd_offset(src_pud, addr);
	do {
		next = pmd_addr_end(addr, end);
		if (pmd_none_or_clear_bad(src_pmd))
			continue;
		if (copy_pte_range(dst_mm, src_mm, dst_pmd, src_pmd,
						vma, addr, next))
			return -ENOMEM;
	} while (dst_pmd++, src_pmd++, addr = next, addr != end);
	return 0;
}

static inline int copy_pud_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
		pgd_t *dst_pgd, pgd_t *src_pgd, struct vm_area_struct *vma,
		unsigned long addr, unsigned long end)
{
	pud_t *src_pud, *dst_pud;
	unsigned long next;

	dst_pud = pud_alloc(dst_mm, dst_pgd, addr);
	if (!dst_pud)
		return -ENOMEM;
	src_pud = pud_offset(src_pgd, addr);
	do {
		next = pud_addr_end(addr, end);
		if (pud_none_or_clear_bad(src_pud))
			continue;
		if (copy_pmd_range(dst_mm, src_mm, dst_pud, src_pud,
						vma, addr, next))
			return -ENOMEM;
	} while (dst_pud++, src_pud++, addr = next, addr != end);
	return 0;
}

int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
		struct vm_area_struct *vma)
{
	pgd_t *src_pgd, *dst_pgd;
	unsigned long next;
	unsigned long addr = vma->vm_start;
	unsigned long end = vma->vm_end;

	if (is_vm_hugetlb_page(vma))
		return copy_hugetlb_page_range(dst_mm, src_mm, vma);

	dst_pgd = pgd_offset(dst_mm, addr);
	src_pgd = pgd_offset(src_mm, addr);
	do {
		next = pgd_addr_end(addr, end);
		if (pgd_none_or_clear_bad(src_pgd))
			continue;
		if (copy_pud_range(dst_mm, src_mm, dst_pgd, src_pgd,
						vma, addr, next))
			return -ENOMEM;
	} while (dst_pgd++, src_pgd++, addr = next, addr != end);
	return 0;
}

static void zap_pte_range(struct mmu_gather *tlb, pmd_t *pmd,
				unsigned long addr, unsigned long end,
				struct zap_details *details)
{
	pte_t *pte;

	pte = pte_offset_map(pmd, addr);
	do {
		pte_t ptent = *pte;
		if (pte_none(ptent))
			continue;
		if (pte_present(ptent)) {
			struct page *page = NULL;
			unsigned long pfn = pte_pfn(ptent);
			if (pfn_valid(pfn)) {
				page = pfn_to_page(pfn);
				if (PageReserved(page))
					page = NULL;
			}
			if (unlikely(details) && page) {
				/*
				 * unmap_shared_mapping_pages() wants to
				 * invalidate cache without truncating:
				 * unmap shared but keep private pages.
				 */
				if (details->check_mapping &&
				    details->check_mapping != page->mapping)
					continue;
				/*
				 * Each page->index must be checked when
				 * invalidating or truncating nonlinear.
				 */
				if (details->nonlinear_vma &&
				    (page->index < details->first_index ||
				     page->index > details->last_index))
					continue;
			}
			ptent = ptep_get_and_clear(tlb->mm, addr, pte);
			tlb_remove_tlb_entry(tlb, pte, addr);
			if (unlikely(!page))
				continue;
			if (unlikely(details) && details->nonlinear_vma
			    && linear_page_index(details->nonlinear_vma,
						addr) != page->index)
				set_pte_at(tlb->mm, addr, pte,
					   pgoff_to_pte(page->index));
			if (pte_dirty(ptent))
				set_page_dirty(page);
			if (PageAnon(page))
				dec_mm_counter(tlb->mm, anon_rss);
			else if (pte_young(ptent))
				mark_page_accessed(page);
			tlb->freed++;
			page_remove_rmap(page);
			tlb_remove_page(tlb, page);
			continue;
		}
		/*
		 * If details->check_mapping, we leave swap entries;
		 * if details->nonlinear_vma, we leave file entries.
		 */
		if (unlikely(details))
			continue;
		if (!pte_file(ptent))
			free_swap_and_cache(pte_to_swp_entry(ptent));
		pte_clear(tlb->mm, addr, pte);
	} while (pte++, addr += PAGE_SIZE, addr != end);
	pte_unmap(pte - 1);
}

static inline void zap_pmd_range(struct mmu_gather *tlb, pud_t *pud,
				unsigned long addr, unsigned long end,
				struct zap_details *details)
{
	pmd_t *pmd;
	unsigned long next;

	pmd = pmd_offset(pud, addr);
	do {
		next = pmd_addr_end(addr, end);
		if (pmd_none_or_clear_bad(pmd))
			continue;
		zap_pte_range(tlb, pmd, addr, next, details);
	} while (pmd++, addr = next, addr != end);
}

static inline void zap_pud_range(struct mmu_gather *tlb, pgd_t *pgd,
				unsigned long addr, unsigned long end,
				struct zap_details *details)
{
	pud_t *pud;
	unsigned long next;

	pud = pud_offset(pgd, addr);
	do {
		next = pud_addr_end(addr, end);
		if (pud_none_or_clear_bad(pud))
			continue;
		zap_pmd_range(tlb, pud, addr, next, details);
	} while (pud++, addr = next, addr != end);
}

static void unmap_page_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
				unsigned long addr, unsigned long end,
				struct zap_details *details)
{
	pgd_t *pgd;
	unsigned long next;

	if (details && !details->check_mapping && !details->nonlinear_vma)
		details = NULL;

	BUG_ON(addr >= end);
	tlb_start_vma(tlb, vma);
	pgd = pgd_offset(vma->vm_mm, addr);
	do {
		next = pgd_addr_end(addr, end);
		if (pgd_none_or_clear_bad(pgd))
			continue;
		zap_pud_range(tlb, pgd, addr, next, details);
	} while (pgd++, addr = next, addr != end);
	tlb_end_vma(tlb, vma);
}

#ifdef CONFIG_PREEMPT
# define ZAP_BLOCK_SIZE	(8 * PAGE_SIZE)
#else
/* No preempt: go for improved straight-line efficiency */
# define ZAP_BLOCK_SIZE	(1024 * PAGE_SIZE)
#endif

/**
 * unmap_vmas - unmap a range of memory covered by a list of vma's
 * @tlbp: address of the caller's struct mmu_gather
 * @mm: the controlling mm_struct
 * @vma: the starting vma
 * @start_addr: virtual address at which to start unmapping
 * @end_addr: virtual address at which to end unmapping
 * @nr_accounted: Place number of unmapped pages in vm-accountable vma's here
 * @details: details of nonlinear truncation or shared cache invalidation
 *
658
 * Returns the end address of the unmapping (restart addr if interrupted).
L
Linus Torvalds 已提交
659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674
 *
 * Unmap all pages in the vma list.  Called under page_table_lock.
 *
 * We aim to not hold page_table_lock for too long (for scheduling latency
 * reasons).  So zap pages in ZAP_BLOCK_SIZE bytecounts.  This means we need to
 * return the ending mmu_gather to the caller.
 *
 * Only addresses between `start' and `end' will be unmapped.
 *
 * The VMA list must be sorted in ascending virtual address order.
 *
 * unmap_vmas() assumes that the caller will flush the whole unmapped address
 * range after unmap_vmas() returns.  So the only responsibility here is to
 * ensure that any thus-far unmapped pages are flushed before unmap_vmas()
 * drops the lock and schedules.
 */
675
unsigned long unmap_vmas(struct mmu_gather **tlbp, struct mm_struct *mm,
L
Linus Torvalds 已提交
676 677 678 679 680 681 682
		struct vm_area_struct *vma, unsigned long start_addr,
		unsigned long end_addr, unsigned long *nr_accounted,
		struct zap_details *details)
{
	unsigned long zap_bytes = ZAP_BLOCK_SIZE;
	unsigned long tlb_start = 0;	/* For tlb_finish_mmu */
	int tlb_start_valid = 0;
683
	unsigned long start = start_addr;
L
Linus Torvalds 已提交
684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742
	spinlock_t *i_mmap_lock = details? details->i_mmap_lock: NULL;
	int fullmm = tlb_is_full_mm(*tlbp);

	for ( ; vma && vma->vm_start < end_addr; vma = vma->vm_next) {
		unsigned long end;

		start = max(vma->vm_start, start_addr);
		if (start >= vma->vm_end)
			continue;
		end = min(vma->vm_end, end_addr);
		if (end <= vma->vm_start)
			continue;

		if (vma->vm_flags & VM_ACCOUNT)
			*nr_accounted += (end - start) >> PAGE_SHIFT;

		while (start != end) {
			unsigned long block;

			if (!tlb_start_valid) {
				tlb_start = start;
				tlb_start_valid = 1;
			}

			if (is_vm_hugetlb_page(vma)) {
				block = end - start;
				unmap_hugepage_range(vma, start, end);
			} else {
				block = min(zap_bytes, end - start);
				unmap_page_range(*tlbp, vma, start,
						start + block, details);
			}

			start += block;
			zap_bytes -= block;
			if ((long)zap_bytes > 0)
				continue;

			tlb_finish_mmu(*tlbp, tlb_start, start);

			if (need_resched() ||
				need_lockbreak(&mm->page_table_lock) ||
				(i_mmap_lock && need_lockbreak(i_mmap_lock))) {
				if (i_mmap_lock) {
					/* must reset count of rss freed */
					*tlbp = tlb_gather_mmu(mm, fullmm);
					goto out;
				}
				spin_unlock(&mm->page_table_lock);
				cond_resched();
				spin_lock(&mm->page_table_lock);
			}

			*tlbp = tlb_gather_mmu(mm, fullmm);
			tlb_start_valid = 0;
			zap_bytes = ZAP_BLOCK_SIZE;
		}
	}
out:
743
	return start;	/* which is now the end (or restart) address */
L
Linus Torvalds 已提交
744 745 746 747 748 749 750 751 752
}

/**
 * zap_page_range - remove user pages in a given range
 * @vma: vm_area_struct holding the applicable pages
 * @address: starting address of pages to zap
 * @size: number of bytes to zap
 * @details: details of nonlinear truncation or shared cache invalidation
 */
753
unsigned long zap_page_range(struct vm_area_struct *vma, unsigned long address,
L
Linus Torvalds 已提交
754 755 756 757 758 759 760 761 762
		unsigned long size, struct zap_details *details)
{
	struct mm_struct *mm = vma->vm_mm;
	struct mmu_gather *tlb;
	unsigned long end = address + size;
	unsigned long nr_accounted = 0;

	if (is_vm_hugetlb_page(vma)) {
		zap_hugepage_range(vma, address, size);
763
		return end;
L
Linus Torvalds 已提交
764 765 766 767 768
	}

	lru_add_drain();
	spin_lock(&mm->page_table_lock);
	tlb = tlb_gather_mmu(mm, 0);
769
	end = unmap_vmas(&tlb, mm, vma, address, end, &nr_accounted, details);
L
Linus Torvalds 已提交
770 771
	tlb_finish_mmu(tlb, address, end);
	spin_unlock(&mm->page_table_lock);
772
	return end;
L
Linus Torvalds 已提交
773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937
}

/*
 * Do a quick page-table lookup for a single page.
 * mm->page_table_lock must be held.
 */
static struct page *
__follow_page(struct mm_struct *mm, unsigned long address, int read, int write)
{
	pgd_t *pgd;
	pud_t *pud;
	pmd_t *pmd;
	pte_t *ptep, pte;
	unsigned long pfn;
	struct page *page;

	page = follow_huge_addr(mm, address, write);
	if (! IS_ERR(page))
		return page;

	pgd = pgd_offset(mm, address);
	if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd)))
		goto out;

	pud = pud_offset(pgd, address);
	if (pud_none(*pud) || unlikely(pud_bad(*pud)))
		goto out;
	
	pmd = pmd_offset(pud, address);
	if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd)))
		goto out;
	if (pmd_huge(*pmd))
		return follow_huge_pmd(mm, address, pmd, write);

	ptep = pte_offset_map(pmd, address);
	if (!ptep)
		goto out;

	pte = *ptep;
	pte_unmap(ptep);
	if (pte_present(pte)) {
		if (write && !pte_write(pte))
			goto out;
		if (read && !pte_read(pte))
			goto out;
		pfn = pte_pfn(pte);
		if (pfn_valid(pfn)) {
			page = pfn_to_page(pfn);
			if (write && !pte_dirty(pte) && !PageDirty(page))
				set_page_dirty(page);
			mark_page_accessed(page);
			return page;
		}
	}

out:
	return NULL;
}

struct page *
follow_page(struct mm_struct *mm, unsigned long address, int write)
{
	return __follow_page(mm, address, /*read*/0, write);
}

int
check_user_page_readable(struct mm_struct *mm, unsigned long address)
{
	return __follow_page(mm, address, /*read*/1, /*write*/0) != NULL;
}
EXPORT_SYMBOL(check_user_page_readable);

static inline int
untouched_anonymous_page(struct mm_struct* mm, struct vm_area_struct *vma,
			 unsigned long address)
{
	pgd_t *pgd;
	pud_t *pud;
	pmd_t *pmd;

	/* Check if the vma is for an anonymous mapping. */
	if (vma->vm_ops && vma->vm_ops->nopage)
		return 0;

	/* Check if page directory entry exists. */
	pgd = pgd_offset(mm, address);
	if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd)))
		return 1;

	pud = pud_offset(pgd, address);
	if (pud_none(*pud) || unlikely(pud_bad(*pud)))
		return 1;

	/* Check if page middle directory entry exists. */
	pmd = pmd_offset(pud, address);
	if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd)))
		return 1;

	/* There is a pte slot for 'address' in 'mm'. */
	return 0;
}

int get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
		unsigned long start, int len, int write, int force,
		struct page **pages, struct vm_area_struct **vmas)
{
	int i;
	unsigned int flags;

	/* 
	 * Require read or write permissions.
	 * If 'force' is set, we only require the "MAY" flags.
	 */
	flags = write ? (VM_WRITE | VM_MAYWRITE) : (VM_READ | VM_MAYREAD);
	flags &= force ? (VM_MAYREAD | VM_MAYWRITE) : (VM_READ | VM_WRITE);
	i = 0;

	do {
		struct vm_area_struct *	vma;

		vma = find_extend_vma(mm, start);
		if (!vma && in_gate_area(tsk, start)) {
			unsigned long pg = start & PAGE_MASK;
			struct vm_area_struct *gate_vma = get_gate_vma(tsk);
			pgd_t *pgd;
			pud_t *pud;
			pmd_t *pmd;
			pte_t *pte;
			if (write) /* user gate pages are read-only */
				return i ? : -EFAULT;
			if (pg > TASK_SIZE)
				pgd = pgd_offset_k(pg);
			else
				pgd = pgd_offset_gate(mm, pg);
			BUG_ON(pgd_none(*pgd));
			pud = pud_offset(pgd, pg);
			BUG_ON(pud_none(*pud));
			pmd = pmd_offset(pud, pg);
			BUG_ON(pmd_none(*pmd));
			pte = pte_offset_map(pmd, pg);
			BUG_ON(pte_none(*pte));
			if (pages) {
				pages[i] = pte_page(*pte);
				get_page(pages[i]);
			}
			pte_unmap(pte);
			if (vmas)
				vmas[i] = gate_vma;
			i++;
			start += PAGE_SIZE;
			len--;
			continue;
		}

		if (!vma || (vma->vm_flags & VM_IO)
				|| !(flags & vma->vm_flags))
			return i ? : -EFAULT;

		if (is_vm_hugetlb_page(vma)) {
			i = follow_hugetlb_page(mm, vma, pages, vmas,
						&start, &len, i);
			continue;
		}
		spin_lock(&mm->page_table_lock);
		do {
938
			struct page *page;
L
Linus Torvalds 已提交
939 940 941
			int lookup_write = write;

			cond_resched_lock(&mm->page_table_lock);
942
			while (!(page = follow_page(mm, start, lookup_write))) {
L
Linus Torvalds 已提交
943 944 945
				/*
				 * Shortcut for anonymous pages. We don't want
				 * to force the creation of pages tables for
946
				 * insanely big anonymously mapped areas that
L
Linus Torvalds 已提交
947 948 949 950 951
				 * nobody touched so far. This is important
				 * for doing a core dump for these mappings.
				 */
				if (!lookup_write &&
				    untouched_anonymous_page(mm,vma,start)) {
952
					page = ZERO_PAGE(start);
L
Linus Torvalds 已提交
953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980
					break;
				}
				spin_unlock(&mm->page_table_lock);
				switch (handle_mm_fault(mm,vma,start,write)) {
				case VM_FAULT_MINOR:
					tsk->min_flt++;
					break;
				case VM_FAULT_MAJOR:
					tsk->maj_flt++;
					break;
				case VM_FAULT_SIGBUS:
					return i ? i : -EFAULT;
				case VM_FAULT_OOM:
					return i ? i : -ENOMEM;
				default:
					BUG();
				}
				/*
				 * Now that we have performed a write fault
				 * and surely no longer have a shared page we
				 * shouldn't write, we shouldn't ignore an
				 * unwritable page in the page table if
				 * we are forcing write access.
				 */
				lookup_write = write && !force;
				spin_lock(&mm->page_table_lock);
			}
			if (pages) {
981 982 983 984
				pages[i] = page;
				flush_dcache_page(page);
				if (!PageReserved(page))
					page_cache_get(page);
L
Linus Torvalds 已提交
985 986 987 988 989 990
			}
			if (vmas)
				vmas[i] = vma;
			i++;
			start += PAGE_SIZE;
			len--;
991
		} while (len && start < vma->vm_end);
L
Linus Torvalds 已提交
992
		spin_unlock(&mm->page_table_lock);
993
	} while (len);
L
Linus Torvalds 已提交
994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333
	return i;
}
EXPORT_SYMBOL(get_user_pages);

static int zeromap_pte_range(struct mm_struct *mm, pmd_t *pmd,
			unsigned long addr, unsigned long end, pgprot_t prot)
{
	pte_t *pte;

	pte = pte_alloc_map(mm, pmd, addr);
	if (!pte)
		return -ENOMEM;
	do {
		pte_t zero_pte = pte_wrprotect(mk_pte(ZERO_PAGE(addr), prot));
		BUG_ON(!pte_none(*pte));
		set_pte_at(mm, addr, pte, zero_pte);
	} while (pte++, addr += PAGE_SIZE, addr != end);
	pte_unmap(pte - 1);
	return 0;
}

static inline int zeromap_pmd_range(struct mm_struct *mm, pud_t *pud,
			unsigned long addr, unsigned long end, pgprot_t prot)
{
	pmd_t *pmd;
	unsigned long next;

	pmd = pmd_alloc(mm, pud, addr);
	if (!pmd)
		return -ENOMEM;
	do {
		next = pmd_addr_end(addr, end);
		if (zeromap_pte_range(mm, pmd, addr, next, prot))
			return -ENOMEM;
	} while (pmd++, addr = next, addr != end);
	return 0;
}

static inline int zeromap_pud_range(struct mm_struct *mm, pgd_t *pgd,
			unsigned long addr, unsigned long end, pgprot_t prot)
{
	pud_t *pud;
	unsigned long next;

	pud = pud_alloc(mm, pgd, addr);
	if (!pud)
		return -ENOMEM;
	do {
		next = pud_addr_end(addr, end);
		if (zeromap_pmd_range(mm, pud, addr, next, prot))
			return -ENOMEM;
	} while (pud++, addr = next, addr != end);
	return 0;
}

int zeromap_page_range(struct vm_area_struct *vma,
			unsigned long addr, unsigned long size, pgprot_t prot)
{
	pgd_t *pgd;
	unsigned long next;
	unsigned long end = addr + size;
	struct mm_struct *mm = vma->vm_mm;
	int err;

	BUG_ON(addr >= end);
	pgd = pgd_offset(mm, addr);
	flush_cache_range(vma, addr, end);
	spin_lock(&mm->page_table_lock);
	do {
		next = pgd_addr_end(addr, end);
		err = zeromap_pud_range(mm, pgd, addr, next, prot);
		if (err)
			break;
	} while (pgd++, addr = next, addr != end);
	spin_unlock(&mm->page_table_lock);
	return err;
}

/*
 * maps a range of physical memory into the requested pages. the old
 * mappings are removed. any references to nonexistent pages results
 * in null mappings (currently treated as "copy-on-access")
 */
static int remap_pte_range(struct mm_struct *mm, pmd_t *pmd,
			unsigned long addr, unsigned long end,
			unsigned long pfn, pgprot_t prot)
{
	pte_t *pte;

	pte = pte_alloc_map(mm, pmd, addr);
	if (!pte)
		return -ENOMEM;
	do {
		BUG_ON(!pte_none(*pte));
		if (!pfn_valid(pfn) || PageReserved(pfn_to_page(pfn)))
			set_pte_at(mm, addr, pte, pfn_pte(pfn, prot));
		pfn++;
	} while (pte++, addr += PAGE_SIZE, addr != end);
	pte_unmap(pte - 1);
	return 0;
}

static inline int remap_pmd_range(struct mm_struct *mm, pud_t *pud,
			unsigned long addr, unsigned long end,
			unsigned long pfn, pgprot_t prot)
{
	pmd_t *pmd;
	unsigned long next;

	pfn -= addr >> PAGE_SHIFT;
	pmd = pmd_alloc(mm, pud, addr);
	if (!pmd)
		return -ENOMEM;
	do {
		next = pmd_addr_end(addr, end);
		if (remap_pte_range(mm, pmd, addr, next,
				pfn + (addr >> PAGE_SHIFT), prot))
			return -ENOMEM;
	} while (pmd++, addr = next, addr != end);
	return 0;
}

static inline int remap_pud_range(struct mm_struct *mm, pgd_t *pgd,
			unsigned long addr, unsigned long end,
			unsigned long pfn, pgprot_t prot)
{
	pud_t *pud;
	unsigned long next;

	pfn -= addr >> PAGE_SHIFT;
	pud = pud_alloc(mm, pgd, addr);
	if (!pud)
		return -ENOMEM;
	do {
		next = pud_addr_end(addr, end);
		if (remap_pmd_range(mm, pud, addr, next,
				pfn + (addr >> PAGE_SHIFT), prot))
			return -ENOMEM;
	} while (pud++, addr = next, addr != end);
	return 0;
}

/*  Note: this is only safe if the mm semaphore is held when called. */
int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr,
		    unsigned long pfn, unsigned long size, pgprot_t prot)
{
	pgd_t *pgd;
	unsigned long next;
	unsigned long end = addr + size;
	struct mm_struct *mm = vma->vm_mm;
	int err;

	/*
	 * Physically remapped pages are special. Tell the
	 * rest of the world about it:
	 *   VM_IO tells people not to look at these pages
	 *	(accesses can have side effects).
	 *   VM_RESERVED tells swapout not to try to touch
	 *	this region.
	 */
	vma->vm_flags |= VM_IO | VM_RESERVED;

	BUG_ON(addr >= end);
	pfn -= addr >> PAGE_SHIFT;
	pgd = pgd_offset(mm, addr);
	flush_cache_range(vma, addr, end);
	spin_lock(&mm->page_table_lock);
	do {
		next = pgd_addr_end(addr, end);
		err = remap_pud_range(mm, pgd, addr, next,
				pfn + (addr >> PAGE_SHIFT), prot);
		if (err)
			break;
	} while (pgd++, addr = next, addr != end);
	spin_unlock(&mm->page_table_lock);
	return err;
}
EXPORT_SYMBOL(remap_pfn_range);

/*
 * Do pte_mkwrite, but only if the vma says VM_WRITE.  We do this when
 * servicing faults for write access.  In the normal case, do always want
 * pte_mkwrite.  But get_user_pages can cause write faults for mappings
 * that do not have writing enabled, when used by access_process_vm.
 */
static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma)
{
	if (likely(vma->vm_flags & VM_WRITE))
		pte = pte_mkwrite(pte);
	return pte;
}

/*
 * We hold the mm semaphore for reading and vma->vm_mm->page_table_lock
 */
static inline void break_cow(struct vm_area_struct * vma, struct page * new_page, unsigned long address, 
		pte_t *page_table)
{
	pte_t entry;

	entry = maybe_mkwrite(pte_mkdirty(mk_pte(new_page, vma->vm_page_prot)),
			      vma);
	ptep_establish(vma, address, page_table, entry);
	update_mmu_cache(vma, address, entry);
	lazy_mmu_prot_update(entry);
}

/*
 * This routine handles present pages, when users try to write
 * to a shared page. It is done by copying the page to a new address
 * and decrementing the shared-page counter for the old page.
 *
 * Goto-purists beware: the only reason for goto's here is that it results
 * in better assembly code.. The "default" path will see no jumps at all.
 *
 * Note that this routine assumes that the protection checks have been
 * done by the caller (the low-level page fault routine in most cases).
 * Thus we can safely just mark it writable once we've done any necessary
 * COW.
 *
 * We also mark the page dirty at this point even though the page will
 * change only once the write actually happens. This avoids a few races,
 * and potentially makes it more efficient.
 *
 * We hold the mm semaphore and the page_table_lock on entry and exit
 * with the page_table_lock released.
 */
static int do_wp_page(struct mm_struct *mm, struct vm_area_struct * vma,
	unsigned long address, pte_t *page_table, pmd_t *pmd, pte_t pte)
{
	struct page *old_page, *new_page;
	unsigned long pfn = pte_pfn(pte);
	pte_t entry;

	if (unlikely(!pfn_valid(pfn))) {
		/*
		 * This should really halt the system so it can be debugged or
		 * at least the kernel stops what it's doing before it corrupts
		 * data, but for the moment just pretend this is OOM.
		 */
		pte_unmap(page_table);
		printk(KERN_ERR "do_wp_page: bogus page at address %08lx\n",
				address);
		spin_unlock(&mm->page_table_lock);
		return VM_FAULT_OOM;
	}
	old_page = pfn_to_page(pfn);

	if (!TestSetPageLocked(old_page)) {
		int reuse = can_share_swap_page(old_page);
		unlock_page(old_page);
		if (reuse) {
			flush_cache_page(vma, address, pfn);
			entry = maybe_mkwrite(pte_mkyoung(pte_mkdirty(pte)),
					      vma);
			ptep_set_access_flags(vma, address, page_table, entry, 1);
			update_mmu_cache(vma, address, entry);
			lazy_mmu_prot_update(entry);
			pte_unmap(page_table);
			spin_unlock(&mm->page_table_lock);
			return VM_FAULT_MINOR;
		}
	}
	pte_unmap(page_table);

	/*
	 * Ok, we need to copy. Oh, well..
	 */
	if (!PageReserved(old_page))
		page_cache_get(old_page);
	spin_unlock(&mm->page_table_lock);

	if (unlikely(anon_vma_prepare(vma)))
		goto no_new_page;
	if (old_page == ZERO_PAGE(address)) {
		new_page = alloc_zeroed_user_highpage(vma, address);
		if (!new_page)
			goto no_new_page;
	} else {
		new_page = alloc_page_vma(GFP_HIGHUSER, vma, address);
		if (!new_page)
			goto no_new_page;
		copy_user_highpage(new_page, old_page, address);
	}
	/*
	 * Re-check the pte - we dropped the lock
	 */
	spin_lock(&mm->page_table_lock);
	page_table = pte_offset_map(pmd, address);
	if (likely(pte_same(*page_table, pte))) {
		if (PageAnon(old_page))
			dec_mm_counter(mm, anon_rss);
		if (PageReserved(old_page))
			inc_mm_counter(mm, rss);
		else
			page_remove_rmap(old_page);
		flush_cache_page(vma, address, pfn);
		break_cow(vma, new_page, address, page_table);
		lru_cache_add_active(new_page);
		page_add_anon_rmap(new_page, vma, address);

		/* Free the old page.. */
		new_page = old_page;
	}
	pte_unmap(page_table);
	page_cache_release(new_page);
	page_cache_release(old_page);
	spin_unlock(&mm->page_table_lock);
	return VM_FAULT_MINOR;

no_new_page:
	page_cache_release(old_page);
	return VM_FAULT_OOM;
}

/*
 * Helper functions for unmap_mapping_range().
 *
 * __ Notes on dropping i_mmap_lock to reduce latency while unmapping __
 *
 * We have to restart searching the prio_tree whenever we drop the lock,
 * since the iterator is only valid while the lock is held, and anyway
 * a later vma might be split and reinserted earlier while lock dropped.
 *
 * The list of nonlinear vmas could be handled more efficiently, using
 * a placeholder, but handle it in the same way until a need is shown.
 * It is important to search the prio_tree before nonlinear list: a vma
 * may become nonlinear and be shifted from prio_tree to nonlinear list
 * while the lock is dropped; but never shifted from list to prio_tree.
 *
 * In order to make forward progress despite restarting the search,
 * vm_truncate_count is used to mark a vma as now dealt with, so we can
 * quickly skip it next time around.  Since the prio_tree search only
 * shows us those vmas affected by unmapping the range in question, we
 * can't efficiently keep all vmas in step with mapping->truncate_count:
 * so instead reset them all whenever it wraps back to 0 (then go to 1).
 * mapping->truncate_count and vma->vm_truncate_count are protected by
 * i_mmap_lock.
 *
 * In order to make forward progress despite repeatedly restarting some
1334
 * large vma, note the restart_addr from unmap_vmas when it breaks out:
L
Linus Torvalds 已提交
1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371
 * and restart from that address when we reach that vma again.  It might
 * have been split or merged, shrunk or extended, but never shifted: so
 * restart_addr remains valid so long as it remains in the vma's range.
 * unmap_mapping_range forces truncate_count to leap over page-aligned
 * values so we can save vma's restart_addr in its truncate_count field.
 */
#define is_restart_addr(truncate_count) (!((truncate_count) & ~PAGE_MASK))

static void reset_vma_truncate_counts(struct address_space *mapping)
{
	struct vm_area_struct *vma;
	struct prio_tree_iter iter;

	vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, 0, ULONG_MAX)
		vma->vm_truncate_count = 0;
	list_for_each_entry(vma, &mapping->i_mmap_nonlinear, shared.vm_set.list)
		vma->vm_truncate_count = 0;
}

static int unmap_mapping_range_vma(struct vm_area_struct *vma,
		unsigned long start_addr, unsigned long end_addr,
		struct zap_details *details)
{
	unsigned long restart_addr;
	int need_break;

again:
	restart_addr = vma->vm_truncate_count;
	if (is_restart_addr(restart_addr) && start_addr < restart_addr) {
		start_addr = restart_addr;
		if (start_addr >= end_addr) {
			/* Top of vma has been split off since last time */
			vma->vm_truncate_count = details->truncate_count;
			return 0;
		}
	}

1372 1373
	restart_addr = zap_page_range(vma, start_addr,
					end_addr - start_addr, details);
L
Linus Torvalds 已提交
1374 1375 1376 1377 1378 1379 1380 1381 1382 1383

	/*
	 * We cannot rely on the break test in unmap_vmas:
	 * on the one hand, we don't want to restart our loop
	 * just because that broke out for the page_table_lock;
	 * on the other hand, it does no test when vma is small.
	 */
	need_break = need_resched() ||
			need_lockbreak(details->i_mmap_lock);

1384
	if (restart_addr >= end_addr) {
L
Linus Torvalds 已提交
1385 1386 1387 1388 1389 1390
		/* We have now completed this vma: mark it so */
		vma->vm_truncate_count = details->truncate_count;
		if (!need_break)
			return 0;
	} else {
		/* Note restart_addr in vma's truncate_count field */
1391
		vma->vm_truncate_count = restart_addr;
L
Linus Torvalds 已提交
1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679
		if (!need_break)
			goto again;
	}

	spin_unlock(details->i_mmap_lock);
	cond_resched();
	spin_lock(details->i_mmap_lock);
	return -EINTR;
}

static inline void unmap_mapping_range_tree(struct prio_tree_root *root,
					    struct zap_details *details)
{
	struct vm_area_struct *vma;
	struct prio_tree_iter iter;
	pgoff_t vba, vea, zba, zea;

restart:
	vma_prio_tree_foreach(vma, &iter, root,
			details->first_index, details->last_index) {
		/* Skip quickly over those we have already dealt with */
		if (vma->vm_truncate_count == details->truncate_count)
			continue;

		vba = vma->vm_pgoff;
		vea = vba + ((vma->vm_end - vma->vm_start) >> PAGE_SHIFT) - 1;
		/* Assume for now that PAGE_CACHE_SHIFT == PAGE_SHIFT */
		zba = details->first_index;
		if (zba < vba)
			zba = vba;
		zea = details->last_index;
		if (zea > vea)
			zea = vea;

		if (unmap_mapping_range_vma(vma,
			((zba - vba) << PAGE_SHIFT) + vma->vm_start,
			((zea - vba + 1) << PAGE_SHIFT) + vma->vm_start,
				details) < 0)
			goto restart;
	}
}

static inline void unmap_mapping_range_list(struct list_head *head,
					    struct zap_details *details)
{
	struct vm_area_struct *vma;

	/*
	 * In nonlinear VMAs there is no correspondence between virtual address
	 * offset and file offset.  So we must perform an exhaustive search
	 * across *all* the pages in each nonlinear VMA, not just the pages
	 * whose virtual address lies outside the file truncation point.
	 */
restart:
	list_for_each_entry(vma, head, shared.vm_set.list) {
		/* Skip quickly over those we have already dealt with */
		if (vma->vm_truncate_count == details->truncate_count)
			continue;
		details->nonlinear_vma = vma;
		if (unmap_mapping_range_vma(vma, vma->vm_start,
					vma->vm_end, details) < 0)
			goto restart;
	}
}

/**
 * unmap_mapping_range - unmap the portion of all mmaps
 * in the specified address_space corresponding to the specified
 * page range in the underlying file.
 * @address_space: the address space containing mmaps to be unmapped.
 * @holebegin: byte in first page to unmap, relative to the start of
 * the underlying file.  This will be rounded down to a PAGE_SIZE
 * boundary.  Note that this is different from vmtruncate(), which
 * must keep the partial page.  In contrast, we must get rid of
 * partial pages.
 * @holelen: size of prospective hole in bytes.  This will be rounded
 * up to a PAGE_SIZE boundary.  A holelen of zero truncates to the
 * end of the file.
 * @even_cows: 1 when truncating a file, unmap even private COWed pages;
 * but 0 when invalidating pagecache, don't throw away private data.
 */
void unmap_mapping_range(struct address_space *mapping,
		loff_t const holebegin, loff_t const holelen, int even_cows)
{
	struct zap_details details;
	pgoff_t hba = holebegin >> PAGE_SHIFT;
	pgoff_t hlen = (holelen + PAGE_SIZE - 1) >> PAGE_SHIFT;

	/* Check for overflow. */
	if (sizeof(holelen) > sizeof(hlen)) {
		long long holeend =
			(holebegin + holelen + PAGE_SIZE - 1) >> PAGE_SHIFT;
		if (holeend & ~(long long)ULONG_MAX)
			hlen = ULONG_MAX - hba + 1;
	}

	details.check_mapping = even_cows? NULL: mapping;
	details.nonlinear_vma = NULL;
	details.first_index = hba;
	details.last_index = hba + hlen - 1;
	if (details.last_index < details.first_index)
		details.last_index = ULONG_MAX;
	details.i_mmap_lock = &mapping->i_mmap_lock;

	spin_lock(&mapping->i_mmap_lock);

	/* serialize i_size write against truncate_count write */
	smp_wmb();
	/* Protect against page faults, and endless unmapping loops */
	mapping->truncate_count++;
	/*
	 * For archs where spin_lock has inclusive semantics like ia64
	 * this smp_mb() will prevent to read pagetable contents
	 * before the truncate_count increment is visible to
	 * other cpus.
	 */
	smp_mb();
	if (unlikely(is_restart_addr(mapping->truncate_count))) {
		if (mapping->truncate_count == 0)
			reset_vma_truncate_counts(mapping);
		mapping->truncate_count++;
	}
	details.truncate_count = mapping->truncate_count;

	if (unlikely(!prio_tree_empty(&mapping->i_mmap)))
		unmap_mapping_range_tree(&mapping->i_mmap, &details);
	if (unlikely(!list_empty(&mapping->i_mmap_nonlinear)))
		unmap_mapping_range_list(&mapping->i_mmap_nonlinear, &details);
	spin_unlock(&mapping->i_mmap_lock);
}
EXPORT_SYMBOL(unmap_mapping_range);

/*
 * Handle all mappings that got truncated by a "truncate()"
 * system call.
 *
 * NOTE! We have to be ready to update the memory sharing
 * between the file and the memory map for a potential last
 * incomplete page.  Ugly, but necessary.
 */
int vmtruncate(struct inode * inode, loff_t offset)
{
	struct address_space *mapping = inode->i_mapping;
	unsigned long limit;

	if (inode->i_size < offset)
		goto do_expand;
	/*
	 * truncation of in-use swapfiles is disallowed - it would cause
	 * subsequent swapout to scribble on the now-freed blocks.
	 */
	if (IS_SWAPFILE(inode))
		goto out_busy;
	i_size_write(inode, offset);
	unmap_mapping_range(mapping, offset + PAGE_SIZE - 1, 0, 1);
	truncate_inode_pages(mapping, offset);
	goto out_truncate;

do_expand:
	limit = current->signal->rlim[RLIMIT_FSIZE].rlim_cur;
	if (limit != RLIM_INFINITY && offset > limit)
		goto out_sig;
	if (offset > inode->i_sb->s_maxbytes)
		goto out_big;
	i_size_write(inode, offset);

out_truncate:
	if (inode->i_op && inode->i_op->truncate)
		inode->i_op->truncate(inode);
	return 0;
out_sig:
	send_sig(SIGXFSZ, current, 0);
out_big:
	return -EFBIG;
out_busy:
	return -ETXTBSY;
}

EXPORT_SYMBOL(vmtruncate);

/* 
 * Primitive swap readahead code. We simply read an aligned block of
 * (1 << page_cluster) entries in the swap area. This method is chosen
 * because it doesn't cost us any seek time.  We also make sure to queue
 * the 'original' request together with the readahead ones...  
 *
 * This has been extended to use the NUMA policies from the mm triggering
 * the readahead.
 *
 * Caller must hold down_read on the vma->vm_mm if vma is not NULL.
 */
void swapin_readahead(swp_entry_t entry, unsigned long addr,struct vm_area_struct *vma)
{
#ifdef CONFIG_NUMA
	struct vm_area_struct *next_vma = vma ? vma->vm_next : NULL;
#endif
	int i, num;
	struct page *new_page;
	unsigned long offset;

	/*
	 * Get the number of handles we should do readahead io to.
	 */
	num = valid_swaphandles(entry, &offset);
	for (i = 0; i < num; offset++, i++) {
		/* Ok, do the async read-ahead now */
		new_page = read_swap_cache_async(swp_entry(swp_type(entry),
							   offset), vma, addr);
		if (!new_page)
			break;
		page_cache_release(new_page);
#ifdef CONFIG_NUMA
		/*
		 * Find the next applicable VMA for the NUMA policy.
		 */
		addr += PAGE_SIZE;
		if (addr == 0)
			vma = NULL;
		if (vma) {
			if (addr >= vma->vm_end) {
				vma = next_vma;
				next_vma = vma ? vma->vm_next : NULL;
			}
			if (vma && addr < vma->vm_start)
				vma = NULL;
		} else {
			if (next_vma && addr >= next_vma->vm_start) {
				vma = next_vma;
				next_vma = vma->vm_next;
			}
		}
#endif
	}
	lru_add_drain();	/* Push any new pages onto the LRU now */
}

/*
 * We hold the mm semaphore and the page_table_lock on entry and
 * should release the pagetable lock on exit..
 */
static int do_swap_page(struct mm_struct * mm,
	struct vm_area_struct * vma, unsigned long address,
	pte_t *page_table, pmd_t *pmd, pte_t orig_pte, int write_access)
{
	struct page *page;
	swp_entry_t entry = pte_to_swp_entry(orig_pte);
	pte_t pte;
	int ret = VM_FAULT_MINOR;

	pte_unmap(page_table);
	spin_unlock(&mm->page_table_lock);
	page = lookup_swap_cache(entry);
	if (!page) {
 		swapin_readahead(entry, address, vma);
 		page = read_swap_cache_async(entry, vma, address);
		if (!page) {
			/*
			 * Back out if somebody else faulted in this pte while
			 * we released the page table lock.
			 */
			spin_lock(&mm->page_table_lock);
			page_table = pte_offset_map(pmd, address);
			if (likely(pte_same(*page_table, orig_pte)))
				ret = VM_FAULT_OOM;
			else
				ret = VM_FAULT_MINOR;
			pte_unmap(page_table);
			spin_unlock(&mm->page_table_lock);
			goto out;
		}

		/* Had to read the page from swap area: Major fault */
		ret = VM_FAULT_MAJOR;
		inc_page_state(pgmajfault);
		grab_swap_token();
	}

	mark_page_accessed(page);
	lock_page(page);

	/*
	 * Back out if somebody else faulted in this pte while we
	 * released the page table lock.
	 */
	spin_lock(&mm->page_table_lock);
	page_table = pte_offset_map(pmd, address);
	if (unlikely(!pte_same(*page_table, orig_pte))) {
		ret = VM_FAULT_MINOR;
1680 1681 1682 1683 1684 1685
		goto out_nomap;
	}

	if (unlikely(!PageUptodate(page))) {
		ret = VM_FAULT_SIGBUS;
		goto out_nomap;
L
Linus Torvalds 已提交
1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719
	}

	/* The page isn't present yet, go ahead with the fault. */
		
	swap_free(entry);
	if (vm_swap_full())
		remove_exclusive_swap_page(page);

	inc_mm_counter(mm, rss);
	pte = mk_pte(page, vma->vm_page_prot);
	if (write_access && can_share_swap_page(page)) {
		pte = maybe_mkwrite(pte_mkdirty(pte), vma);
		write_access = 0;
	}
	unlock_page(page);

	flush_icache_page(vma, page);
	set_pte_at(mm, address, page_table, pte);
	page_add_anon_rmap(page, vma, address);

	if (write_access) {
		if (do_wp_page(mm, vma, address,
				page_table, pmd, pte) == VM_FAULT_OOM)
			ret = VM_FAULT_OOM;
		goto out;
	}

	/* No need to invalidate - it was non-present before */
	update_mmu_cache(vma, address, pte);
	lazy_mmu_prot_update(pte);
	pte_unmap(page_table);
	spin_unlock(&mm->page_table_lock);
out:
	return ret;
1720 1721 1722 1723 1724 1725
out_nomap:
	pte_unmap(page_table);
	spin_unlock(&mm->page_table_lock);
	unlock_page(page);
	page_cache_release(page);
	goto out;
L
Linus Torvalds 已提交
1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233
}

/*
 * We are called with the MM semaphore and page_table_lock
 * spinlock held to protect against concurrent faults in
 * multithreaded programs. 
 */
static int
do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
		pte_t *page_table, pmd_t *pmd, int write_access,
		unsigned long addr)
{
	pte_t entry;
	struct page * page = ZERO_PAGE(addr);

	/* Read-only mapping of ZERO_PAGE. */
	entry = pte_wrprotect(mk_pte(ZERO_PAGE(addr), vma->vm_page_prot));

	/* ..except if it's a write access */
	if (write_access) {
		/* Allocate our own private page. */
		pte_unmap(page_table);
		spin_unlock(&mm->page_table_lock);

		if (unlikely(anon_vma_prepare(vma)))
			goto no_mem;
		page = alloc_zeroed_user_highpage(vma, addr);
		if (!page)
			goto no_mem;

		spin_lock(&mm->page_table_lock);
		page_table = pte_offset_map(pmd, addr);

		if (!pte_none(*page_table)) {
			pte_unmap(page_table);
			page_cache_release(page);
			spin_unlock(&mm->page_table_lock);
			goto out;
		}
		inc_mm_counter(mm, rss);
		entry = maybe_mkwrite(pte_mkdirty(mk_pte(page,
							 vma->vm_page_prot)),
				      vma);
		lru_cache_add_active(page);
		SetPageReferenced(page);
		page_add_anon_rmap(page, vma, addr);
	}

	set_pte_at(mm, addr, page_table, entry);
	pte_unmap(page_table);

	/* No need to invalidate - it was non-present before */
	update_mmu_cache(vma, addr, entry);
	lazy_mmu_prot_update(entry);
	spin_unlock(&mm->page_table_lock);
out:
	return VM_FAULT_MINOR;
no_mem:
	return VM_FAULT_OOM;
}

/*
 * do_no_page() tries to create a new page mapping. It aggressively
 * tries to share with existing pages, but makes a separate copy if
 * the "write_access" parameter is true in order to avoid the next
 * page fault.
 *
 * As this is called only for pages that do not currently exist, we
 * do not need to flush old virtual caches or the TLB.
 *
 * This is called with the MM semaphore held and the page table
 * spinlock held. Exit with the spinlock released.
 */
static int
do_no_page(struct mm_struct *mm, struct vm_area_struct *vma,
	unsigned long address, int write_access, pte_t *page_table, pmd_t *pmd)
{
	struct page * new_page;
	struct address_space *mapping = NULL;
	pte_t entry;
	unsigned int sequence = 0;
	int ret = VM_FAULT_MINOR;
	int anon = 0;

	if (!vma->vm_ops || !vma->vm_ops->nopage)
		return do_anonymous_page(mm, vma, page_table,
					pmd, write_access, address);
	pte_unmap(page_table);
	spin_unlock(&mm->page_table_lock);

	if (vma->vm_file) {
		mapping = vma->vm_file->f_mapping;
		sequence = mapping->truncate_count;
		smp_rmb(); /* serializes i_size against truncate_count */
	}
retry:
	cond_resched();
	new_page = vma->vm_ops->nopage(vma, address & PAGE_MASK, &ret);
	/*
	 * No smp_rmb is needed here as long as there's a full
	 * spin_lock/unlock sequence inside the ->nopage callback
	 * (for the pagecache lookup) that acts as an implicit
	 * smp_mb() and prevents the i_size read to happen
	 * after the next truncate_count read.
	 */

	/* no page was available -- either SIGBUS or OOM */
	if (new_page == NOPAGE_SIGBUS)
		return VM_FAULT_SIGBUS;
	if (new_page == NOPAGE_OOM)
		return VM_FAULT_OOM;

	/*
	 * Should we do an early C-O-W break?
	 */
	if (write_access && !(vma->vm_flags & VM_SHARED)) {
		struct page *page;

		if (unlikely(anon_vma_prepare(vma)))
			goto oom;
		page = alloc_page_vma(GFP_HIGHUSER, vma, address);
		if (!page)
			goto oom;
		copy_user_highpage(page, new_page, address);
		page_cache_release(new_page);
		new_page = page;
		anon = 1;
	}

	spin_lock(&mm->page_table_lock);
	/*
	 * For a file-backed vma, someone could have truncated or otherwise
	 * invalidated this page.  If unmap_mapping_range got called,
	 * retry getting the page.
	 */
	if (mapping && unlikely(sequence != mapping->truncate_count)) {
		sequence = mapping->truncate_count;
		spin_unlock(&mm->page_table_lock);
		page_cache_release(new_page);
		goto retry;
	}
	page_table = pte_offset_map(pmd, address);

	/*
	 * This silly early PAGE_DIRTY setting removes a race
	 * due to the bad i386 page protection. But it's valid
	 * for other architectures too.
	 *
	 * Note that if write_access is true, we either now have
	 * an exclusive copy of the page, or this is a shared mapping,
	 * so we can make it writable and dirty to avoid having to
	 * handle that later.
	 */
	/* Only go through if we didn't race with anybody else... */
	if (pte_none(*page_table)) {
		if (!PageReserved(new_page))
			inc_mm_counter(mm, rss);

		flush_icache_page(vma, new_page);
		entry = mk_pte(new_page, vma->vm_page_prot);
		if (write_access)
			entry = maybe_mkwrite(pte_mkdirty(entry), vma);
		set_pte_at(mm, address, page_table, entry);
		if (anon) {
			lru_cache_add_active(new_page);
			page_add_anon_rmap(new_page, vma, address);
		} else
			page_add_file_rmap(new_page);
		pte_unmap(page_table);
	} else {
		/* One of our sibling threads was faster, back out. */
		pte_unmap(page_table);
		page_cache_release(new_page);
		spin_unlock(&mm->page_table_lock);
		goto out;
	}

	/* no need to invalidate: a not-present page shouldn't be cached */
	update_mmu_cache(vma, address, entry);
	lazy_mmu_prot_update(entry);
	spin_unlock(&mm->page_table_lock);
out:
	return ret;
oom:
	page_cache_release(new_page);
	ret = VM_FAULT_OOM;
	goto out;
}

/*
 * Fault of a previously existing named mapping. Repopulate the pte
 * from the encoded file_pte if possible. This enables swappable
 * nonlinear vmas.
 */
static int do_file_page(struct mm_struct * mm, struct vm_area_struct * vma,
	unsigned long address, int write_access, pte_t *pte, pmd_t *pmd)
{
	unsigned long pgoff;
	int err;

	BUG_ON(!vma->vm_ops || !vma->vm_ops->nopage);
	/*
	 * Fall back to the linear mapping if the fs does not support
	 * ->populate:
	 */
	if (!vma->vm_ops || !vma->vm_ops->populate || 
			(write_access && !(vma->vm_flags & VM_SHARED))) {
		pte_clear(mm, address, pte);
		return do_no_page(mm, vma, address, write_access, pte, pmd);
	}

	pgoff = pte_to_pgoff(*pte);

	pte_unmap(pte);
	spin_unlock(&mm->page_table_lock);

	err = vma->vm_ops->populate(vma, address & PAGE_MASK, PAGE_SIZE, vma->vm_page_prot, pgoff, 0);
	if (err == -ENOMEM)
		return VM_FAULT_OOM;
	if (err)
		return VM_FAULT_SIGBUS;
	return VM_FAULT_MAJOR;
}

/*
 * These routines also need to handle stuff like marking pages dirty
 * and/or accessed for architectures that don't do it in hardware (most
 * RISC architectures).  The early dirtying is also good on the i386.
 *
 * There is also a hook called "update_mmu_cache()" that architectures
 * with external mmu caches can use to update those (ie the Sparc or
 * PowerPC hashed page tables that act as extended TLBs).
 *
 * Note the "page_table_lock". It is to protect against kswapd removing
 * pages from under us. Note that kswapd only ever _removes_ pages, never
 * adds them. As such, once we have noticed that the page is not present,
 * we can drop the lock early.
 *
 * The adding of pages is protected by the MM semaphore (which we hold),
 * so we don't need to worry about a page being suddenly been added into
 * our VM.
 *
 * We enter with the pagetable spinlock held, we are supposed to
 * release it when done.
 */
static inline int handle_pte_fault(struct mm_struct *mm,
	struct vm_area_struct * vma, unsigned long address,
	int write_access, pte_t *pte, pmd_t *pmd)
{
	pte_t entry;

	entry = *pte;
	if (!pte_present(entry)) {
		/*
		 * If it truly wasn't present, we know that kswapd
		 * and the PTE updates will not touch it later. So
		 * drop the lock.
		 */
		if (pte_none(entry))
			return do_no_page(mm, vma, address, write_access, pte, pmd);
		if (pte_file(entry))
			return do_file_page(mm, vma, address, write_access, pte, pmd);
		return do_swap_page(mm, vma, address, pte, pmd, entry, write_access);
	}

	if (write_access) {
		if (!pte_write(entry))
			return do_wp_page(mm, vma, address, pte, pmd, entry);

		entry = pte_mkdirty(entry);
	}
	entry = pte_mkyoung(entry);
	ptep_set_access_flags(vma, address, pte, entry, write_access);
	update_mmu_cache(vma, address, entry);
	lazy_mmu_prot_update(entry);
	pte_unmap(pte);
	spin_unlock(&mm->page_table_lock);
	return VM_FAULT_MINOR;
}

/*
 * By the time we get here, we already hold the mm semaphore
 */
int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct * vma,
		unsigned long address, int write_access)
{
	pgd_t *pgd;
	pud_t *pud;
	pmd_t *pmd;
	pte_t *pte;

	__set_current_state(TASK_RUNNING);

	inc_page_state(pgfault);

	if (is_vm_hugetlb_page(vma))
		return VM_FAULT_SIGBUS;	/* mapping truncation does this. */

	/*
	 * We need the page table lock to synchronize with kswapd
	 * and the SMP-safe atomic PTE updates.
	 */
	pgd = pgd_offset(mm, address);
	spin_lock(&mm->page_table_lock);

	pud = pud_alloc(mm, pgd, address);
	if (!pud)
		goto oom;

	pmd = pmd_alloc(mm, pud, address);
	if (!pmd)
		goto oom;

	pte = pte_alloc_map(mm, pmd, address);
	if (!pte)
		goto oom;
	
	return handle_pte_fault(mm, vma, address, write_access, pte, pmd);

 oom:
	spin_unlock(&mm->page_table_lock);
	return VM_FAULT_OOM;
}

#ifndef __PAGETABLE_PUD_FOLDED
/*
 * Allocate page upper directory.
 *
 * We've already handled the fast-path in-line, and we own the
 * page table lock.
 */
pud_t fastcall *__pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address)
{
	pud_t *new;

	spin_unlock(&mm->page_table_lock);
	new = pud_alloc_one(mm, address);
	spin_lock(&mm->page_table_lock);
	if (!new)
		return NULL;

	/*
	 * Because we dropped the lock, we should re-check the
	 * entry, as somebody else could have populated it..
	 */
	if (pgd_present(*pgd)) {
		pud_free(new);
		goto out;
	}
	pgd_populate(mm, pgd, new);
 out:
	return pud_offset(pgd, address);
}
#endif /* __PAGETABLE_PUD_FOLDED */

#ifndef __PAGETABLE_PMD_FOLDED
/*
 * Allocate page middle directory.
 *
 * We've already handled the fast-path in-line, and we own the
 * page table lock.
 */
pmd_t fastcall *__pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address)
{
	pmd_t *new;

	spin_unlock(&mm->page_table_lock);
	new = pmd_alloc_one(mm, address);
	spin_lock(&mm->page_table_lock);
	if (!new)
		return NULL;

	/*
	 * Because we dropped the lock, we should re-check the
	 * entry, as somebody else could have populated it..
	 */
#ifndef __ARCH_HAS_4LEVEL_HACK
	if (pud_present(*pud)) {
		pmd_free(new);
		goto out;
	}
	pud_populate(mm, pud, new);
#else
	if (pgd_present(*pud)) {
		pmd_free(new);
		goto out;
	}
	pgd_populate(mm, pud, new);
#endif /* __ARCH_HAS_4LEVEL_HACK */

 out:
	return pmd_offset(pud, address);
}
#endif /* __PAGETABLE_PMD_FOLDED */

int make_pages_present(unsigned long addr, unsigned long end)
{
	int ret, len, write;
	struct vm_area_struct * vma;

	vma = find_vma(current->mm, addr);
	if (!vma)
		return -1;
	write = (vma->vm_flags & VM_WRITE) != 0;
	if (addr >= end)
		BUG();
	if (end > vma->vm_end)
		BUG();
	len = (end+PAGE_SIZE-1)/PAGE_SIZE-addr/PAGE_SIZE;
	ret = get_user_pages(current, current->mm, addr,
			len, write, 0, NULL, NULL);
	if (ret < 0)
		return ret;
	return ret == len ? 0 : -1;
}

/* 
 * Map a vmalloc()-space virtual address to the physical page.
 */
struct page * vmalloc_to_page(void * vmalloc_addr)
{
	unsigned long addr = (unsigned long) vmalloc_addr;
	struct page *page = NULL;
	pgd_t *pgd = pgd_offset_k(addr);
	pud_t *pud;
	pmd_t *pmd;
	pte_t *ptep, pte;
  
	if (!pgd_none(*pgd)) {
		pud = pud_offset(pgd, addr);
		if (!pud_none(*pud)) {
			pmd = pmd_offset(pud, addr);
			if (!pmd_none(*pmd)) {
				ptep = pte_offset_map(pmd, addr);
				pte = *ptep;
				if (pte_present(pte))
					page = pte_page(pte);
				pte_unmap(ptep);
			}
		}
	}
	return page;
}

EXPORT_SYMBOL(vmalloc_to_page);

/*
 * Map a vmalloc()-space virtual address to the physical page frame number.
 */
unsigned long vmalloc_to_pfn(void * vmalloc_addr)
{
	return page_to_pfn(vmalloc_to_page(vmalloc_addr));
}

EXPORT_SYMBOL(vmalloc_to_pfn);

/*
 * update_mem_hiwater
 *	- update per process rss and vm high water data
 */
void update_mem_hiwater(struct task_struct *tsk)
{
	if (tsk->mm) {
		unsigned long rss = get_mm_counter(tsk->mm, rss);

		if (tsk->mm->hiwater_rss < rss)
			tsk->mm->hiwater_rss = rss;
		if (tsk->mm->hiwater_vm < tsk->mm->total_vm)
			tsk->mm->hiwater_vm = tsk->mm->total_vm;
	}
}

#if !defined(__HAVE_ARCH_GATE_AREA)

#if defined(AT_SYSINFO_EHDR)
struct vm_area_struct gate_vma;

static int __init gate_vma_init(void)
{
	gate_vma.vm_mm = NULL;
	gate_vma.vm_start = FIXADDR_USER_START;
	gate_vma.vm_end = FIXADDR_USER_END;
	gate_vma.vm_page_prot = PAGE_READONLY;
	gate_vma.vm_flags = 0;
	return 0;
}
__initcall(gate_vma_init);
#endif

struct vm_area_struct *get_gate_vma(struct task_struct *tsk)
{
#ifdef AT_SYSINFO_EHDR
	return &gate_vma;
#else
	return NULL;
#endif
}

int in_gate_area_no_task(unsigned long addr)
{
#ifdef AT_SYSINFO_EHDR
	if ((addr >= FIXADDR_USER_START) && (addr < FIXADDR_USER_END))
		return 1;
#endif
	return 0;
}

#endif	/* __HAVE_ARCH_GATE_AREA */