Skip to content
Snippets Groups Projects
nommu.c 48.4 KiB
Newer Older
  • Learn to ignore specific revisions
  • Kenneth Johansson's avatar
    Kenneth Johansson committed
    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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000
    /*
     *  linux/mm/nommu.c
     *
     *  Replacement code for mm functions to support CPU's that don't
     *  have any form of memory management unit (thus no virtual memory).
     *
     *  See Documentation/nommu-mmap.txt
     *
     *  Copyright (c) 2004-2008 David Howells <dhowells@redhat.com>
     *  Copyright (c) 2000-2003 David McCullough <davidm@snapgear.com>
     *  Copyright (c) 2000-2001 D Jeff Dionne <jeff@uClinux.org>
     *  Copyright (c) 2002      Greg Ungerer <gerg@snapgear.com>
     *  Copyright (c) 2007-2010 Paul Mundt <lethal@linux-sh.org>
     */
    
    #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
    
    #include <linux/export.h>
    #include <linux/mm.h>
    #include <linux/vmacache.h>
    #include <linux/mman.h>
    #include <linux/swap.h>
    #include <linux/file.h>
    #include <linux/highmem.h>
    #include <linux/pagemap.h>
    #include <linux/slab.h>
    #include <linux/vmalloc.h>
    #include <linux/blkdev.h>
    #include <linux/backing-dev.h>
    #include <linux/compiler.h>
    #include <linux/mount.h>
    #include <linux/personality.h>
    #include <linux/security.h>
    #include <linux/syscalls.h>
    #include <linux/audit.h>
    #include <linux/printk.h>
    
    #include <asm/uaccess.h>
    #include <asm/tlb.h>
    #include <asm/tlbflush.h>
    #include <asm/mmu_context.h>
    #include "internal.h"
    
    void *high_memory;
    EXPORT_SYMBOL(high_memory);
    struct page *mem_map;
    unsigned long max_mapnr;
    EXPORT_SYMBOL(max_mapnr);
    unsigned long highest_memmap_pfn;
    int sysctl_nr_trim_pages = CONFIG_NOMMU_INITIAL_TRIM_EXCESS;
    int heap_stack_gap = 0;
    
    atomic_long_t mmap_pages_allocated;
    
    EXPORT_SYMBOL(mem_map);
    
    /* list of mapped, potentially shareable regions */
    static struct kmem_cache *vm_region_jar;
    struct rb_root nommu_region_tree = RB_ROOT;
    DECLARE_RWSEM(nommu_region_sem);
    
    const struct vm_operations_struct generic_file_vm_ops = {
    };
    
    /*
     * Return the total memory allocated for this pointer, not
     * just what the caller asked for.
     *
     * Doesn't have to be accurate, i.e. may have races.
     */
    unsigned int kobjsize(const void *objp)
    {
    	struct page *page;
    
    	/*
    	 * If the object we have should not have ksize performed on it,
    	 * return size of 0
    	 */
    	if (!objp || !virt_addr_valid(objp))
    		return 0;
    
    	page = virt_to_head_page(objp);
    
    	/*
    	 * If the allocator sets PageSlab, we know the pointer came from
    	 * kmalloc().
    	 */
    	if (PageSlab(page))
    		return ksize(objp);
    
    	/*
    	 * If it's not a compound page, see if we have a matching VMA
    	 * region. This test is intentionally done in reverse order,
    	 * so if there's no VMA, we still fall through and hand back
    	 * PAGE_SIZE for 0-order pages.
    	 */
    	if (!PageCompound(page)) {
    		struct vm_area_struct *vma;
    
    		vma = find_vma(current->mm, (unsigned long)objp);
    		if (vma)
    			return vma->vm_end - vma->vm_start;
    	}
    
    	/*
    	 * The ksize() function is only guaranteed to work for pointers
    	 * returned by kmalloc(). So handle arbitrary pointers here.
    	 */
    	return PAGE_SIZE << compound_order(page);
    }
    
    static long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
    		      unsigned long start, unsigned long nr_pages,
    		      unsigned int foll_flags, struct page **pages,
    		      struct vm_area_struct **vmas, int *nonblocking)
    {
    	struct vm_area_struct *vma;
    	unsigned long vm_flags;
    	int i;
    
    	/* calculate required read or write permissions.
    	 * If FOLL_FORCE is set, we only require the "MAY" flags.
    	 */
    	vm_flags  = (foll_flags & FOLL_WRITE) ?
    			(VM_WRITE | VM_MAYWRITE) : (VM_READ | VM_MAYREAD);
    	vm_flags &= (foll_flags & FOLL_FORCE) ?
    			(VM_MAYREAD | VM_MAYWRITE) : (VM_READ | VM_WRITE);
    
    	for (i = 0; i < nr_pages; i++) {
    		vma = find_vma(mm, start);
    		if (!vma)
    			goto finish_or_fault;
    
    		/* protect what we can, including chardevs */
    		if ((vma->vm_flags & (VM_IO | VM_PFNMAP)) ||
    		    !(vm_flags & vma->vm_flags))
    			goto finish_or_fault;
    
    		if (pages) {
    			pages[i] = virt_to_page(start);
    			if (pages[i])
    				get_page(pages[i]);
    		}
    		if (vmas)
    			vmas[i] = vma;
    		start = (start + PAGE_SIZE) & PAGE_MASK;
    	}
    
    	return i;
    
    finish_or_fault:
    	return i ? : -EFAULT;
    }
    
    /*
     * get a list of pages in an address range belonging to the specified process
     * and indicate the VMA that covers each page
     * - this is potentially dodgy as we may end incrementing the page count of a
     *   slab page or a secondary page from a compound page
     * - don't permit access to VMAs that don't support it, such as I/O mappings
     */
    long get_user_pages(unsigned long start, unsigned long nr_pages,
    		    unsigned int gup_flags, struct page **pages,
    		    struct vm_area_struct **vmas)
    {
    	return __get_user_pages(current, current->mm, start, nr_pages,
    				gup_flags, pages, vmas, NULL);
    }
    EXPORT_SYMBOL(get_user_pages);
    
    long get_user_pages_locked(unsigned long start, unsigned long nr_pages,
    			    unsigned int gup_flags, struct page **pages,
    			    int *locked)
    {
    	return get_user_pages(start, nr_pages, gup_flags, pages, NULL);
    }
    EXPORT_SYMBOL(get_user_pages_locked);
    
    long __get_user_pages_unlocked(struct task_struct *tsk, struct mm_struct *mm,
    			       unsigned long start, unsigned long nr_pages,
    			       struct page **pages, unsigned int gup_flags)
    {
    	long ret;
    	down_read(&mm->mmap_sem);
    	ret = __get_user_pages(tsk, mm, start, nr_pages, gup_flags, pages,
    				NULL, NULL);
    	up_read(&mm->mmap_sem);
    	return ret;
    }
    EXPORT_SYMBOL(__get_user_pages_unlocked);
    
    long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages,
    			     struct page **pages, unsigned int gup_flags)
    {
    	return __get_user_pages_unlocked(current, current->mm, start, nr_pages,
    					 pages, gup_flags);
    }
    EXPORT_SYMBOL(get_user_pages_unlocked);
    
    /**
     * follow_pfn - look up PFN at a user virtual address
     * @vma: memory mapping
     * @address: user virtual address
     * @pfn: location to store found PFN
     *
     * Only IO mappings and raw PFN mappings are allowed.
     *
     * Returns zero and the pfn at @pfn on success, -ve otherwise.
     */
    int follow_pfn(struct vm_area_struct *vma, unsigned long address,
    	unsigned long *pfn)
    {
    	if (!(vma->vm_flags & (VM_IO | VM_PFNMAP)))
    		return -EINVAL;
    
    	*pfn = address >> PAGE_SHIFT;
    	return 0;
    }
    EXPORT_SYMBOL(follow_pfn);
    
    LIST_HEAD(vmap_area_list);
    
    void vfree(const void *addr)
    {
    	kfree(addr);
    }
    EXPORT_SYMBOL(vfree);
    
    void *__vmalloc(unsigned long size, gfp_t gfp_mask, pgprot_t prot)
    {
    	/*
    	 *  You can't specify __GFP_HIGHMEM with kmalloc() since kmalloc()
    	 * returns only a logical address.
    	 */
    	return kmalloc(size, (gfp_mask | __GFP_COMP) & ~__GFP_HIGHMEM);
    }
    EXPORT_SYMBOL(__vmalloc);
    
    void *vmalloc_user(unsigned long size)
    {
    	void *ret;
    
    	ret = __vmalloc(size, GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO,
    			PAGE_KERNEL);
    	if (ret) {
    		struct vm_area_struct *vma;
    
    		down_write(&current->mm->mmap_sem);
    		vma = find_vma(current->mm, (unsigned long)ret);
    		if (vma)
    			vma->vm_flags |= VM_USERMAP;
    		up_write(&current->mm->mmap_sem);
    	}
    
    	return ret;
    }
    EXPORT_SYMBOL(vmalloc_user);
    
    struct page *vmalloc_to_page(const void *addr)
    {
    	return virt_to_page(addr);
    }
    EXPORT_SYMBOL(vmalloc_to_page);
    
    unsigned long vmalloc_to_pfn(const void *addr)
    {
    	return page_to_pfn(virt_to_page(addr));
    }
    EXPORT_SYMBOL(vmalloc_to_pfn);
    
    long vread(char *buf, char *addr, unsigned long count)
    {
    	/* Don't allow overflow */
    	if ((unsigned long) buf + count < count)
    		count = -(unsigned long) buf;
    
    	memcpy(buf, addr, count);
    	return count;
    }
    
    long vwrite(char *buf, char *addr, unsigned long count)
    {
    	/* Don't allow overflow */
    	if ((unsigned long) addr + count < count)
    		count = -(unsigned long) addr;
    
    	memcpy(addr, buf, count);
    	return count;
    }
    
    /*
     *	vmalloc  -  allocate virtually contiguous memory
     *
     *	@size:		allocation size
     *
     *	Allocate enough pages to cover @size from the page level
     *	allocator and map them into contiguous kernel virtual space.
     *
     *	For tight control over page level allocator and protection flags
     *	use __vmalloc() instead.
     */
    void *vmalloc(unsigned long size)
    {
           return __vmalloc(size, GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL);
    }
    EXPORT_SYMBOL(vmalloc);
    
    /*
     *	vzalloc - allocate virtually contiguous memory with zero fill
     *
     *	@size:		allocation size
     *
     *	Allocate enough pages to cover @size from the page level
     *	allocator and map them into contiguous kernel virtual space.
     *	The memory allocated is set to zero.
     *
     *	For tight control over page level allocator and protection flags
     *	use __vmalloc() instead.
     */
    void *vzalloc(unsigned long size)
    {
    	return __vmalloc(size, GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO,
    			PAGE_KERNEL);
    }
    EXPORT_SYMBOL(vzalloc);
    
    /**
     * vmalloc_node - allocate memory on a specific node
     * @size:	allocation size
     * @node:	numa node
     *
     * Allocate enough pages to cover @size from the page level
     * allocator and map them into contiguous kernel virtual space.
     *
     * For tight control over page level allocator and protection flags
     * use __vmalloc() instead.
     */
    void *vmalloc_node(unsigned long size, int node)
    {
    	return vmalloc(size);
    }
    EXPORT_SYMBOL(vmalloc_node);
    
    /**
     * vzalloc_node - allocate memory on a specific node with zero fill
     * @size:	allocation size
     * @node:	numa node
     *
     * Allocate enough pages to cover @size from the page level
     * allocator and map them into contiguous kernel virtual space.
     * The memory allocated is set to zero.
     *
     * For tight control over page level allocator and protection flags
     * use __vmalloc() instead.
     */
    void *vzalloc_node(unsigned long size, int node)
    {
    	return vzalloc(size);
    }
    EXPORT_SYMBOL(vzalloc_node);
    
    #ifndef PAGE_KERNEL_EXEC
    # define PAGE_KERNEL_EXEC PAGE_KERNEL
    #endif
    
    /**
     *	vmalloc_exec  -  allocate virtually contiguous, executable memory
     *	@size:		allocation size
     *
     *	Kernel-internal function to allocate enough pages to cover @size
     *	the page level allocator and map them into contiguous and
     *	executable kernel virtual space.
     *
     *	For tight control over page level allocator and protection flags
     *	use __vmalloc() instead.
     */
    
    void *vmalloc_exec(unsigned long size)
    {
    	return __vmalloc(size, GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL_EXEC);
    }
    
    /**
     * vmalloc_32  -  allocate virtually contiguous memory (32bit addressable)
     *	@size:		allocation size
     *
     *	Allocate enough 32bit PA addressable pages to cover @size from the
     *	page level allocator and map them into contiguous kernel virtual space.
     */
    void *vmalloc_32(unsigned long size)
    {
    	return __vmalloc(size, GFP_KERNEL, PAGE_KERNEL);
    }
    EXPORT_SYMBOL(vmalloc_32);
    
    /**
     * vmalloc_32_user - allocate zeroed virtually contiguous 32bit memory
     *	@size:		allocation size
     *
     * The resulting memory area is 32bit addressable and zeroed so it can be
     * mapped to userspace without leaking data.
     *
     * VM_USERMAP is set on the corresponding VMA so that subsequent calls to
     * remap_vmalloc_range() are permissible.
     */
    void *vmalloc_32_user(unsigned long size)
    {
    	/*
    	 * We'll have to sort out the ZONE_DMA bits for 64-bit,
    	 * but for now this can simply use vmalloc_user() directly.
    	 */
    	return vmalloc_user(size);
    }
    EXPORT_SYMBOL(vmalloc_32_user);
    
    void *vmap(struct page **pages, unsigned int count, unsigned long flags, pgprot_t prot)
    {
    	BUG();
    	return NULL;
    }
    EXPORT_SYMBOL(vmap);
    
    void vunmap(const void *addr)
    {
    	BUG();
    }
    EXPORT_SYMBOL(vunmap);
    
    void *vm_map_ram(struct page **pages, unsigned int count, int node, pgprot_t prot)
    {
    	BUG();
    	return NULL;
    }
    EXPORT_SYMBOL(vm_map_ram);
    
    void vm_unmap_ram(const void *mem, unsigned int count)
    {
    	BUG();
    }
    EXPORT_SYMBOL(vm_unmap_ram);
    
    void vm_unmap_aliases(void)
    {
    }
    EXPORT_SYMBOL_GPL(vm_unmap_aliases);
    
    /*
     * Implement a stub for vmalloc_sync_all() if the architecture chose not to
     * have one.
     */
    void __weak vmalloc_sync_all(void)
    {
    }
    
    /**
     *	alloc_vm_area - allocate a range of kernel address space
     *	@size:		size of the area
     *
     *	Returns:	NULL on failure, vm_struct on success
     *
     *	This function reserves a range of kernel address space, and
     *	allocates pagetables to map that range.  No actual mappings
     *	are created.  If the kernel address space is not shared
     *	between processes, it syncs the pagetable across all
     *	processes.
     */
    struct vm_struct *alloc_vm_area(size_t size, pte_t **ptes)
    {
    	BUG();
    	return NULL;
    }
    EXPORT_SYMBOL_GPL(alloc_vm_area);
    
    void free_vm_area(struct vm_struct *area)
    {
    	BUG();
    }
    EXPORT_SYMBOL_GPL(free_vm_area);
    
    int vm_insert_page(struct vm_area_struct *vma, unsigned long addr,
    		   struct page *page)
    {
    	return -EINVAL;
    }
    EXPORT_SYMBOL(vm_insert_page);
    
    /*
     *  sys_brk() for the most part doesn't need the global kernel
     *  lock, except when an application is doing something nasty
     *  like trying to un-brk an area that has already been mapped
     *  to a regular file.  in this case, the unmapping will need
     *  to invoke file system routines that need the global lock.
     */
    SYSCALL_DEFINE1(brk, unsigned long, brk)
    {
    	struct mm_struct *mm = current->mm;
    
    	if (brk < mm->start_brk || brk > mm->context.end_brk)
    		return mm->brk;
    
    	if (mm->brk == brk)
    		return mm->brk;
    
    	/*
    	 * Always allow shrinking brk
    	 */
    	if (brk <= mm->brk) {
    		mm->brk = brk;
    		return brk;
    	}
    
    	/*
    	 * Ok, looks good - let it rip.
    	 */
    	flush_icache_range(mm->brk, brk);
    	return mm->brk = brk;
    }
    
    /*
     * initialise the VMA and region record slabs
     */
    void __init mmap_init(void)
    {
    	int ret;
    
    	ret = percpu_counter_init(&vm_committed_as, 0, GFP_KERNEL);
    	VM_BUG_ON(ret);
    	vm_region_jar = KMEM_CACHE(vm_region, SLAB_PANIC|SLAB_ACCOUNT);
    }
    
    /*
     * validate the region tree
     * - the caller must hold the region lock
     */
    #ifdef CONFIG_DEBUG_NOMMU_REGIONS
    static noinline void validate_nommu_regions(void)
    {
    	struct vm_region *region, *last;
    	struct rb_node *p, *lastp;
    
    	lastp = rb_first(&nommu_region_tree);
    	if (!lastp)
    		return;
    
    	last = rb_entry(lastp, struct vm_region, vm_rb);
    	BUG_ON(last->vm_end <= last->vm_start);
    	BUG_ON(last->vm_top < last->vm_end);
    
    	while ((p = rb_next(lastp))) {
    		region = rb_entry(p, struct vm_region, vm_rb);
    		last = rb_entry(lastp, struct vm_region, vm_rb);
    
    		BUG_ON(region->vm_end <= region->vm_start);
    		BUG_ON(region->vm_top < region->vm_end);
    		BUG_ON(region->vm_start < last->vm_top);
    
    		lastp = p;
    	}
    }
    #else
    static void validate_nommu_regions(void)
    {
    }
    #endif
    
    /*
     * add a region into the global tree
     */
    static void add_nommu_region(struct vm_region *region)
    {
    	struct vm_region *pregion;
    	struct rb_node **p, *parent;
    
    	validate_nommu_regions();
    
    	parent = NULL;
    	p = &nommu_region_tree.rb_node;
    	while (*p) {
    		parent = *p;
    		pregion = rb_entry(parent, struct vm_region, vm_rb);
    		if (region->vm_start < pregion->vm_start)
    			p = &(*p)->rb_left;
    		else if (region->vm_start > pregion->vm_start)
    			p = &(*p)->rb_right;
    		else if (pregion == region)
    			return;
    		else
    			BUG();
    	}
    
    	rb_link_node(&region->vm_rb, parent, p);
    	rb_insert_color(&region->vm_rb, &nommu_region_tree);
    
    	validate_nommu_regions();
    }
    
    /*
     * delete a region from the global tree
     */
    static void delete_nommu_region(struct vm_region *region)
    {
    	BUG_ON(!nommu_region_tree.rb_node);
    
    	validate_nommu_regions();
    	rb_erase(&region->vm_rb, &nommu_region_tree);
    	validate_nommu_regions();
    }
    
    /*
     * free a contiguous series of pages
     */
    static void free_page_series(unsigned long from, unsigned long to)
    {
    	for (; from < to; from += PAGE_SIZE) {
    		struct page *page = virt_to_page(from);
    
    		atomic_long_dec(&mmap_pages_allocated);
    		put_page(page);
    	}
    }
    
    /*
     * release a reference to a region
     * - the caller must hold the region semaphore for writing, which this releases
     * - the region may not have been added to the tree yet, in which case vm_top
     *   will equal vm_start
     */
    static void __put_nommu_region(struct vm_region *region)
    	__releases(nommu_region_sem)
    {
    	BUG_ON(!nommu_region_tree.rb_node);
    
    	if (--region->vm_usage == 0) {
    		if (region->vm_top > region->vm_start)
    			delete_nommu_region(region);
    		up_write(&nommu_region_sem);
    
    		if (region->vm_file)
    			fput(region->vm_file);
    
    		/* IO memory and memory shared directly out of the pagecache
    		 * from ramfs/tmpfs mustn't be released here */
    		if (region->vm_flags & VM_MAPPED_COPY)
    			free_page_series(region->vm_start, region->vm_top);
    		kmem_cache_free(vm_region_jar, region);
    	} else {
    		up_write(&nommu_region_sem);
    	}
    }
    
    /*
     * release a reference to a region
     */
    static void put_nommu_region(struct vm_region *region)
    {
    	down_write(&nommu_region_sem);
    	__put_nommu_region(region);
    }
    
    /*
     * update protection on a vma
     */
    static void protect_vma(struct vm_area_struct *vma, unsigned long flags)
    {
    #ifdef CONFIG_MPU
    	struct mm_struct *mm = vma->vm_mm;
    	long start = vma->vm_start & PAGE_MASK;
    	while (start < vma->vm_end) {
    		protect_page(mm, start, flags);
    		start += PAGE_SIZE;
    	}
    	update_protections(mm);
    #endif
    }
    
    /*
     * add a VMA into a process's mm_struct in the appropriate place in the list
     * and tree and add to the address space's page tree also if not an anonymous
     * page
     * - should be called with mm->mmap_sem held writelocked
     */
    static void add_vma_to_mm(struct mm_struct *mm, struct vm_area_struct *vma)
    {
    	struct vm_area_struct *pvma, *prev;
    	struct address_space *mapping;
    	struct rb_node **p, *parent, *rb_prev;
    
    	BUG_ON(!vma->vm_region);
    
    	mm->map_count++;
    	vma->vm_mm = mm;
    
    	protect_vma(vma, vma->vm_flags);
    
    	/* add the VMA to the mapping */
    	if (vma->vm_file) {
    		mapping = vma->vm_file->f_mapping;
    
    		i_mmap_lock_write(mapping);
    		flush_dcache_mmap_lock(mapping);
    		vma_interval_tree_insert(vma, &mapping->i_mmap);
    		flush_dcache_mmap_unlock(mapping);
    		i_mmap_unlock_write(mapping);
    	}
    
    	/* add the VMA to the tree */
    	parent = rb_prev = NULL;
    	p = &mm->mm_rb.rb_node;
    	while (*p) {
    		parent = *p;
    		pvma = rb_entry(parent, struct vm_area_struct, vm_rb);
    
    		/* sort by: start addr, end addr, VMA struct addr in that order
    		 * (the latter is necessary as we may get identical VMAs) */
    		if (vma->vm_start < pvma->vm_start)
    			p = &(*p)->rb_left;
    		else if (vma->vm_start > pvma->vm_start) {
    			rb_prev = parent;
    			p = &(*p)->rb_right;
    		} else if (vma->vm_end < pvma->vm_end)
    			p = &(*p)->rb_left;
    		else if (vma->vm_end > pvma->vm_end) {
    			rb_prev = parent;
    			p = &(*p)->rb_right;
    		} else if (vma < pvma)
    			p = &(*p)->rb_left;
    		else if (vma > pvma) {
    			rb_prev = parent;
    			p = &(*p)->rb_right;
    		} else
    			BUG();
    	}
    
    	rb_link_node(&vma->vm_rb, parent, p);
    	rb_insert_color(&vma->vm_rb, &mm->mm_rb);
    
    	/* add VMA to the VMA list also */
    	prev = NULL;
    	if (rb_prev)
    		prev = rb_entry(rb_prev, struct vm_area_struct, vm_rb);
    
    	__vma_link_list(mm, vma, prev, parent);
    }
    
    /*
     * delete a VMA from its owning mm_struct and address space
     */
    static void delete_vma_from_mm(struct vm_area_struct *vma)
    {
    	int i;
    	struct address_space *mapping;
    	struct mm_struct *mm = vma->vm_mm;
    	struct task_struct *curr = current;
    
    	protect_vma(vma, 0);
    
    	mm->map_count--;
    	for (i = 0; i < VMACACHE_SIZE; i++) {
    		/* if the vma is cached, invalidate the entire cache */
    		if (curr->vmacache[i] == vma) {
    			vmacache_invalidate(mm);
    			break;
    		}
    	}
    
    	/* remove the VMA from the mapping */
    	if (vma->vm_file) {
    		mapping = vma->vm_file->f_mapping;
    
    		i_mmap_lock_write(mapping);
    		flush_dcache_mmap_lock(mapping);
    		vma_interval_tree_remove(vma, &mapping->i_mmap);
    		flush_dcache_mmap_unlock(mapping);
    		i_mmap_unlock_write(mapping);
    	}
    
    	/* remove from the MM's tree and list */
    	rb_erase(&vma->vm_rb, &mm->mm_rb);
    
    	if (vma->vm_prev)
    		vma->vm_prev->vm_next = vma->vm_next;
    	else
    		mm->mmap = vma->vm_next;
    
    	if (vma->vm_next)
    		vma->vm_next->vm_prev = vma->vm_prev;
    }
    
    /*
     * destroy a VMA record
     */
    static void delete_vma(struct mm_struct *mm, struct vm_area_struct *vma)
    {
    	if (vma->vm_ops && vma->vm_ops->close)
    		vma->vm_ops->close(vma);
    	if (vma->vm_file)
    		fput(vma->vm_file);
    	put_nommu_region(vma->vm_region);
    	kmem_cache_free(vm_area_cachep, vma);
    }
    
    /*
     * look up the first VMA in which addr resides, NULL if none
     * - should be called with mm->mmap_sem at least held readlocked
     */
    struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr)
    {
    	struct vm_area_struct *vma;
    
    	/* check the cache first */
    	vma = vmacache_find(mm, addr);
    	if (likely(vma))
    		return vma;
    
    	/* trawl the list (there may be multiple mappings in which addr
    	 * resides) */
    	for (vma = mm->mmap; vma; vma = vma->vm_next) {
    		if (vma->vm_start > addr)
    			return NULL;
    		if (vma->vm_end > addr) {
    			vmacache_update(addr, vma);
    			return vma;
    		}
    	}
    
    	return NULL;
    }
    EXPORT_SYMBOL(find_vma);
    
    /*
     * find a VMA
     * - we don't extend stack VMAs under NOMMU conditions
     */
    struct vm_area_struct *find_extend_vma(struct mm_struct *mm, unsigned long addr)
    {
    	return find_vma(mm, addr);
    }
    
    /*
     * expand a stack to a given address
     * - not supported under NOMMU conditions
     */
    int expand_stack(struct vm_area_struct *vma, unsigned long address)
    {
    	return -ENOMEM;
    }
    
    /*
     * look up the first VMA exactly that exactly matches addr
     * - should be called with mm->mmap_sem at least held readlocked
     */
    static struct vm_area_struct *find_vma_exact(struct mm_struct *mm,
    					     unsigned long addr,
    					     unsigned long len)
    {
    	struct vm_area_struct *vma;
    	unsigned long end = addr + len;
    
    	/* check the cache first */
    	vma = vmacache_find_exact(mm, addr, end);
    	if (vma)
    		return vma;
    
    	/* trawl the list (there may be multiple mappings in which addr
    	 * resides) */
    	for (vma = mm->mmap; vma; vma = vma->vm_next) {
    		if (vma->vm_start < addr)
    			continue;
    		if (vma->vm_start > addr)
    			return NULL;
    		if (vma->vm_end == end) {
    			vmacache_update(addr, vma);
    			return vma;
    		}
    	}
    
    	return NULL;
    }
    
    /*
     * determine whether a mapping should be permitted and, if so, what sort of
     * mapping we're capable of supporting
     */
    static int validate_mmap_request(struct file *file,
    				 unsigned long addr,
    				 unsigned long len,
    				 unsigned long prot,
    				 unsigned long flags,
    				 unsigned long pgoff,
    				 unsigned long *_capabilities)
    {
    	unsigned long capabilities, rlen;
    	int ret;
    
    	/* do the simple checks first */
    	if (flags & MAP_FIXED)
    		return -EINVAL;
    
    	if ((flags & MAP_TYPE) != MAP_PRIVATE &&
    	    (flags & MAP_TYPE) != MAP_SHARED)
    		return -EINVAL;
    
    	if (!len)
    		return -EINVAL;
    
    	/* Careful about overflows.. */
    	rlen = PAGE_ALIGN(len);
    	if (!rlen || rlen > TASK_SIZE)
    		return -ENOMEM;
    
    	/* offset overflow? */
    	if ((pgoff + (rlen >> PAGE_SHIFT)) < pgoff)
    		return -EOVERFLOW;
    
    	if (file) {
    		/* files must support mmap */
    		if (!file->f_op->mmap)
    			return -ENODEV;
    
    		/* work out if what we've got could possibly be shared
    		 * - we support chardevs that provide their own "memory"
    		 * - we support files/blockdevs that are memory backed
    		 */
    		if (file->f_op->mmap_capabilities) {
    			capabilities = file->f_op->mmap_capabilities(file);
    		} else {
    			/* no explicit capabilities set, so assume some
    			 * defaults */
    			switch (file_inode(file)->i_mode & S_IFMT) {
    			case S_IFREG:
    			case S_IFBLK:
    				capabilities = NOMMU_MAP_COPY;
    				break;
    
    			case S_IFCHR:
    				capabilities =
    					NOMMU_MAP_DIRECT |
    					NOMMU_MAP_READ |
    					NOMMU_MAP_WRITE;
    				break;
    
    			default:
    				return -EINVAL;
    			}
    		}
    
    		/* eliminate any capabilities that we can't support on this
    		 * device */
    		if (!file->f_op->get_unmapped_area)
    			capabilities &= ~NOMMU_MAP_DIRECT;
    		if (!(file->f_mode & FMODE_CAN_READ))
    			capabilities &= ~NOMMU_MAP_COPY;
    
    		/* The file shall have been opened with read permission. */
    		if (!(file->f_mode & FMODE_READ))
    			return -EACCES;
    
    		if (flags & MAP_SHARED) {
    			/* do checks for writing, appending and locking */
    			if ((prot & PROT_WRITE) &&
    			    !(file->f_mode & FMODE_WRITE))
    				return -EACCES;
    
    			if (IS_APPEND(file_inode(file)) &&
    			    (file->f_mode & FMODE_WRITE))
    				return -EACCES;
    
    			if (locks_verify_locked(file))
    				return -EAGAIN;
    
    			if (!(capabilities & NOMMU_MAP_DIRECT))
    				return -ENODEV;
    
    			/* we mustn't privatise shared mappings */
    			capabilities &= ~NOMMU_MAP_COPY;
    		} else {
    			/* we're going to read the file into private memory we
    			 * allocate */
    			if (!(capabilities & NOMMU_MAP_COPY))
    				return -ENODEV;
    
    			/* we don't permit a private writable mapping to be
    			 * shared with the backing device */
    			if (prot & PROT_WRITE)
    				capabilities &= ~NOMMU_MAP_DIRECT;
    		}
    
    		if (capabilities & NOMMU_MAP_DIRECT) {
    			if (((prot & PROT_READ)  && !(capabilities & NOMMU_MAP_READ))  ||
    			    ((prot & PROT_WRITE) && !(capabilities & NOMMU_MAP_WRITE)) ||
    			    ((prot & PROT_EXEC)  && !(capabilities & NOMMU_MAP_EXEC))
    			    ) {
    				capabilities &= ~NOMMU_MAP_DIRECT;
    				if (flags & MAP_SHARED) {
    					pr_warn("MAP_SHARED not completely supported on !MMU\n");
    					return -EINVAL;
    				}
    			}
    		}