Skip to content
Snippets Groups Projects
mmap.c 95.5 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
    /*
     * mm/mmap.c
     *
     * Written by obz.
     *
     * Address space accounting code	<alan@lxorguk.ukuu.org.uk>
     */
    
    #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
    
    #include <linux/kernel.h>
    #include <linux/slab.h>
    #include <linux/backing-dev.h>
    #include <linux/mm.h>
    #include <linux/vmacache.h>
    #include <linux/shm.h>
    #include <linux/mman.h>
    #include <linux/pagemap.h>
    #include <linux/swap.h>
    #include <linux/syscalls.h>
    #include <linux/capability.h>
    #include <linux/init.h>
    #include <linux/file.h>
    #include <linux/fs.h>
    #include <linux/personality.h>
    #include <linux/security.h>
    #include <linux/hugetlb.h>
    #include <linux/shmem_fs.h>
    #include <linux/profile.h>
    #include <linux/export.h>
    #include <linux/mount.h>
    #include <linux/mempolicy.h>
    #include <linux/rmap.h>
    #include <linux/mmu_notifier.h>
    #include <linux/mmdebug.h>
    #include <linux/perf_event.h>
    #include <linux/audit.h>
    #include <linux/khugepaged.h>
    #include <linux/uprobes.h>
    #include <linux/rbtree_augmented.h>
    #include <linux/notifier.h>
    #include <linux/memory.h>
    #include <linux/printk.h>
    #include <linux/userfaultfd_k.h>
    #include <linux/moduleparam.h>
    #include <linux/pkeys.h>
    
    #include <asm/uaccess.h>
    #include <asm/cacheflush.h>
    #include <asm/tlb.h>
    #include <asm/mmu_context.h>
    
    #include "internal.h"
    
    #ifndef arch_mmap_check
    #define arch_mmap_check(addr, len, flags)	(0)
    #endif
    
    #ifdef CONFIG_HAVE_ARCH_MMAP_RND_BITS
    const int mmap_rnd_bits_min = CONFIG_ARCH_MMAP_RND_BITS_MIN;
    const int mmap_rnd_bits_max = CONFIG_ARCH_MMAP_RND_BITS_MAX;
    int mmap_rnd_bits __read_mostly = CONFIG_ARCH_MMAP_RND_BITS;
    #endif
    #ifdef CONFIG_HAVE_ARCH_MMAP_RND_COMPAT_BITS
    const int mmap_rnd_compat_bits_min = CONFIG_ARCH_MMAP_RND_COMPAT_BITS_MIN;
    const int mmap_rnd_compat_bits_max = CONFIG_ARCH_MMAP_RND_COMPAT_BITS_MAX;
    int mmap_rnd_compat_bits __read_mostly = CONFIG_ARCH_MMAP_RND_COMPAT_BITS;
    #endif
    
    static bool ignore_rlimit_data;
    core_param(ignore_rlimit_data, ignore_rlimit_data, bool, 0644);
    
    static void unmap_region(struct mm_struct *mm,
    		struct vm_area_struct *vma, struct vm_area_struct *prev,
    		unsigned long start, unsigned long end);
    
    /* description of effects of mapping type and prot in current implementation.
     * this is due to the limited x86 page protection hardware.  The expected
     * behavior is in parens:
     *
     * map_type	prot
     *		PROT_NONE	PROT_READ	PROT_WRITE	PROT_EXEC
     * MAP_SHARED	r: (no) no	r: (yes) yes	r: (no) yes	r: (no) yes
     *		w: (no) no	w: (no) no	w: (yes) yes	w: (no) no
     *		x: (no) no	x: (no) yes	x: (no) yes	x: (yes) yes
     *
     * MAP_PRIVATE	r: (no) no	r: (yes) yes	r: (no) yes	r: (no) yes
     *		w: (no) no	w: (no) no	w: (copy) copy	w: (no) no
     *		x: (no) no	x: (no) yes	x: (no) yes	x: (yes) yes
     *
     * On arm64, PROT_EXEC has the following behaviour for both MAP_SHARED and
     * MAP_PRIVATE:
     *								r: (no) no
     *								w: (no) no
     *								x: (yes) yes
     */
    pgprot_t protection_map[16] = {
    	__P000, __P001, __P010, __P011, __P100, __P101, __P110, __P111,
    	__S000, __S001, __S010, __S011, __S100, __S101, __S110, __S111
    };
    
    pgprot_t vm_get_page_prot(unsigned long vm_flags)
    {
    	return __pgprot(pgprot_val(protection_map[vm_flags &
    				(VM_READ|VM_WRITE|VM_EXEC|VM_SHARED)]) |
    			pgprot_val(arch_vm_get_page_prot(vm_flags)));
    }
    EXPORT_SYMBOL(vm_get_page_prot);
    
    static pgprot_t vm_pgprot_modify(pgprot_t oldprot, unsigned long vm_flags)
    {
    	return pgprot_modify(oldprot, vm_get_page_prot(vm_flags));
    }
    
    /* Update vma->vm_page_prot to reflect vma->vm_flags. */
    void vma_set_page_prot(struct vm_area_struct *vma)
    {
    	unsigned long vm_flags = vma->vm_flags;
    	pgprot_t vm_page_prot;
    
    	vm_page_prot = vm_pgprot_modify(vma->vm_page_prot, vm_flags);
    	if (vma_wants_writenotify(vma, vm_page_prot)) {
    		vm_flags &= ~VM_SHARED;
    		vm_page_prot = vm_pgprot_modify(vm_page_prot, vm_flags);
    	}
    	/* remove_protection_ptes reads vma->vm_page_prot without mmap_sem */
    	WRITE_ONCE(vma->vm_page_prot, vm_page_prot);
    }
    
    /*
     * Requires inode->i_mapping->i_mmap_rwsem
     */
    static void __remove_shared_vm_struct(struct vm_area_struct *vma,
    		struct file *file, struct address_space *mapping)
    {
    	if (vma->vm_flags & VM_DENYWRITE)
    		atomic_inc(&file_inode(file)->i_writecount);
    	if (vma->vm_flags & VM_SHARED)
    		mapping_unmap_writable(mapping);
    
    	flush_dcache_mmap_lock(mapping);
    	vma_interval_tree_remove(vma, &mapping->i_mmap);
    	flush_dcache_mmap_unlock(mapping);
    }
    
    /*
     * Unlink a file-based vm structure from its interval tree, to hide
     * vma from rmap and vmtruncate before freeing its page tables.
     */
    void unlink_file_vma(struct vm_area_struct *vma)
    {
    	struct file *file = vma->vm_file;
    
    	if (file) {
    		struct address_space *mapping = file->f_mapping;
    		i_mmap_lock_write(mapping);
    		__remove_shared_vm_struct(vma, file, mapping);
    		i_mmap_unlock_write(mapping);
    	}
    }
    
    /*
     * Close a vm structure and free it, returning the next.
     */
    static struct vm_area_struct *remove_vma(struct vm_area_struct *vma)
    {
    	struct vm_area_struct *next = vma->vm_next;
    
    	might_sleep();
    	if (vma->vm_ops && vma->vm_ops->close)
    		vma->vm_ops->close(vma);
    	if (vma->vm_file)
    		fput(vma->vm_file);
    	mpol_put(vma_policy(vma));
    	kmem_cache_free(vm_area_cachep, vma);
    	return next;
    }
    
    static int do_brk(unsigned long addr, unsigned long len);
    
    SYSCALL_DEFINE1(brk, unsigned long, brk)
    {
    	unsigned long retval;
    	unsigned long newbrk, oldbrk;
    	struct mm_struct *mm = current->mm;
    	struct vm_area_struct *next;
    	unsigned long min_brk;
    	bool populate;
    
    	if (down_write_killable(&mm->mmap_sem))
    		return -EINTR;
    
    #ifdef CONFIG_COMPAT_BRK
    	/*
    	 * CONFIG_COMPAT_BRK can still be overridden by setting
    	 * randomize_va_space to 2, which will still cause mm->start_brk
    	 * to be arbitrarily shifted
    	 */
    	if (current->brk_randomized)
    		min_brk = mm->start_brk;
    	else
    		min_brk = mm->end_data;
    #else
    	min_brk = mm->start_brk;
    #endif
    	if (brk < min_brk)
    		goto out;
    
    	/*
    	 * Check against rlimit here. If this check is done later after the test
    	 * of oldbrk with newbrk then it can escape the test and let the data
    	 * segment grow beyond its set limit the in case where the limit is
    	 * not page aligned -Ram Gupta
    	 */
    	if (check_data_rlimit(rlimit(RLIMIT_DATA), brk, mm->start_brk,
    			      mm->end_data, mm->start_data))
    		goto out;
    
    	newbrk = PAGE_ALIGN(brk);
    	oldbrk = PAGE_ALIGN(mm->brk);
    	if (oldbrk == newbrk)
    		goto set_brk;
    
    	/* Always allow shrinking brk. */
    	if (brk <= mm->brk) {
    		if (!do_munmap(mm, newbrk, oldbrk-newbrk))
    			goto set_brk;
    		goto out;
    	}
    
    	/* Check against existing mmap mappings. */
    	next = find_vma(mm, oldbrk);
    	if (next && newbrk + PAGE_SIZE > vm_start_gap(next))
    		goto out;
    
    	/* Ok, looks good - let it rip. */
    	if (do_brk(oldbrk, newbrk-oldbrk) < 0)
    		goto out;
    
    set_brk:
    	mm->brk = brk;
    	populate = newbrk > oldbrk && (mm->def_flags & VM_LOCKED) != 0;
    	up_write(&mm->mmap_sem);
    	if (populate)
    		mm_populate(oldbrk, newbrk - oldbrk);
    	return brk;
    
    out:
    	retval = mm->brk;
    	up_write(&mm->mmap_sem);
    	return retval;
    }
    
    static long vma_compute_subtree_gap(struct vm_area_struct *vma)
    {
    	unsigned long max, prev_end, subtree_gap;
    
    	/*
    	 * Note: in the rare case of a VM_GROWSDOWN above a VM_GROWSUP, we
    	 * allow two stack_guard_gaps between them here, and when choosing
    	 * an unmapped area; whereas when expanding we only require one.
    	 * That's a little inconsistent, but keeps the code here simpler.
    	 */
    	max = vm_start_gap(vma);
    	if (vma->vm_prev) {
    		prev_end = vm_end_gap(vma->vm_prev);
    		if (max > prev_end)
    			max -= prev_end;
    		else
    			max = 0;
    	}
    	if (vma->vm_rb.rb_left) {
    		subtree_gap = rb_entry(vma->vm_rb.rb_left,
    				struct vm_area_struct, vm_rb)->rb_subtree_gap;
    		if (subtree_gap > max)
    			max = subtree_gap;
    	}
    	if (vma->vm_rb.rb_right) {
    		subtree_gap = rb_entry(vma->vm_rb.rb_right,
    				struct vm_area_struct, vm_rb)->rb_subtree_gap;
    		if (subtree_gap > max)
    			max = subtree_gap;
    	}
    	return max;
    }
    
    #ifdef CONFIG_DEBUG_VM_RB
    static int browse_rb(struct mm_struct *mm)
    {
    	struct rb_root *root = &mm->mm_rb;
    	int i = 0, j, bug = 0;
    	struct rb_node *nd, *pn = NULL;
    	unsigned long prev = 0, pend = 0;
    
    	for (nd = rb_first(root); nd; nd = rb_next(nd)) {
    		struct vm_area_struct *vma;
    		vma = rb_entry(nd, struct vm_area_struct, vm_rb);
    		if (vma->vm_start < prev) {
    			pr_emerg("vm_start %lx < prev %lx\n",
    				  vma->vm_start, prev);
    			bug = 1;
    		}
    		if (vma->vm_start < pend) {
    			pr_emerg("vm_start %lx < pend %lx\n",
    				  vma->vm_start, pend);
    			bug = 1;
    		}
    		if (vma->vm_start > vma->vm_end) {
    			pr_emerg("vm_start %lx > vm_end %lx\n",
    				  vma->vm_start, vma->vm_end);
    			bug = 1;
    		}
    		spin_lock(&mm->page_table_lock);
    		if (vma->rb_subtree_gap != vma_compute_subtree_gap(vma)) {
    			pr_emerg("free gap %lx, correct %lx\n",
    			       vma->rb_subtree_gap,
    			       vma_compute_subtree_gap(vma));
    			bug = 1;
    		}
    		spin_unlock(&mm->page_table_lock);
    		i++;
    		pn = nd;
    		prev = vma->vm_start;
    		pend = vma->vm_end;
    	}
    	j = 0;
    	for (nd = pn; nd; nd = rb_prev(nd))
    		j++;
    	if (i != j) {
    		pr_emerg("backwards %d, forwards %d\n", j, i);
    		bug = 1;
    	}
    	return bug ? -1 : i;
    }
    
    static void validate_mm_rb(struct rb_root *root, struct vm_area_struct *ignore)
    {
    	struct rb_node *nd;
    
    	for (nd = rb_first(root); nd; nd = rb_next(nd)) {
    		struct vm_area_struct *vma;
    		vma = rb_entry(nd, struct vm_area_struct, vm_rb);
    		VM_BUG_ON_VMA(vma != ignore &&
    			vma->rb_subtree_gap != vma_compute_subtree_gap(vma),
    			vma);
    	}
    }
    
    static void validate_mm(struct mm_struct *mm)
    {
    	int bug = 0;
    	int i = 0;
    	unsigned long highest_address = 0;
    	struct vm_area_struct *vma = mm->mmap;
    
    	while (vma) {
    		struct anon_vma *anon_vma = vma->anon_vma;
    		struct anon_vma_chain *avc;
    
    		if (anon_vma) {
    			anon_vma_lock_read(anon_vma);
    			list_for_each_entry(avc, &vma->anon_vma_chain, same_vma)
    				anon_vma_interval_tree_verify(avc);
    			anon_vma_unlock_read(anon_vma);
    		}
    
    		highest_address = vm_end_gap(vma);
    		vma = vma->vm_next;
    		i++;
    	}
    	if (i != mm->map_count) {
    		pr_emerg("map_count %d vm_next %d\n", mm->map_count, i);
    		bug = 1;
    	}
    	if (highest_address != mm->highest_vm_end) {
    		pr_emerg("mm->highest_vm_end %lx, found %lx\n",
    			  mm->highest_vm_end, highest_address);
    		bug = 1;
    	}
    	i = browse_rb(mm);
    	if (i != mm->map_count) {
    		if (i != -1)
    			pr_emerg("map_count %d rb %d\n", mm->map_count, i);
    		bug = 1;
    	}
    	VM_BUG_ON_MM(bug, mm);
    }
    #else
    #define validate_mm_rb(root, ignore) do { } while (0)
    #define validate_mm(mm) do { } while (0)
    #endif
    
    RB_DECLARE_CALLBACKS(static, vma_gap_callbacks, struct vm_area_struct, vm_rb,
    		     unsigned long, rb_subtree_gap, vma_compute_subtree_gap)
    
    /*
     * Update augmented rbtree rb_subtree_gap values after vma->vm_start or
     * vma->vm_prev->vm_end values changed, without modifying the vma's position
     * in the rbtree.
     */
    static void vma_gap_update(struct vm_area_struct *vma)
    {
    	/*
    	 * As it turns out, RB_DECLARE_CALLBACKS() already created a callback
    	 * function that does exacltly what we want.
    	 */
    	vma_gap_callbacks_propagate(&vma->vm_rb, NULL);
    }
    
    static inline void vma_rb_insert(struct vm_area_struct *vma,
    				 struct rb_root *root)
    {
    	/* All rb_subtree_gap values must be consistent prior to insertion */
    	validate_mm_rb(root, NULL);
    
    	rb_insert_augmented(&vma->vm_rb, root, &vma_gap_callbacks);
    }
    
    static void __vma_rb_erase(struct vm_area_struct *vma, struct rb_root *root)
    {
    	/*
    	 * Note rb_erase_augmented is a fairly large inline function,
    	 * so make sure we instantiate it only once with our desired
    	 * augmented rbtree callbacks.
    	 */
    	rb_erase_augmented(&vma->vm_rb, root, &vma_gap_callbacks);
    }
    
    static __always_inline void vma_rb_erase_ignore(struct vm_area_struct *vma,
    						struct rb_root *root,
    						struct vm_area_struct *ignore)
    {
    	/*
    	 * All rb_subtree_gap values must be consistent prior to erase,
    	 * with the possible exception of the "next" vma being erased if
    	 * next->vm_start was reduced.
    	 */
    	validate_mm_rb(root, ignore);
    
    	__vma_rb_erase(vma, root);
    }
    
    static __always_inline void vma_rb_erase(struct vm_area_struct *vma,
    					 struct rb_root *root)
    {
    	/*
    	 * All rb_subtree_gap values must be consistent prior to erase,
    	 * with the possible exception of the vma being erased.
    	 */
    	validate_mm_rb(root, vma);
    
    	__vma_rb_erase(vma, root);
    }
    
    /*
     * vma has some anon_vma assigned, and is already inserted on that
     * anon_vma's interval trees.
     *
     * Before updating the vma's vm_start / vm_end / vm_pgoff fields, the
     * vma must be removed from the anon_vma's interval trees using
     * anon_vma_interval_tree_pre_update_vma().
     *
     * After the update, the vma will be reinserted using
     * anon_vma_interval_tree_post_update_vma().
     *
     * The entire update must be protected by exclusive mmap_sem and by
     * the root anon_vma's mutex.
     */
    static inline void
    anon_vma_interval_tree_pre_update_vma(struct vm_area_struct *vma)
    {
    	struct anon_vma_chain *avc;
    
    	list_for_each_entry(avc, &vma->anon_vma_chain, same_vma)
    		anon_vma_interval_tree_remove(avc, &avc->anon_vma->rb_root);
    }
    
    static inline void
    anon_vma_interval_tree_post_update_vma(struct vm_area_struct *vma)
    {
    	struct anon_vma_chain *avc;
    
    	list_for_each_entry(avc, &vma->anon_vma_chain, same_vma)
    		anon_vma_interval_tree_insert(avc, &avc->anon_vma->rb_root);
    }
    
    static int find_vma_links(struct mm_struct *mm, unsigned long addr,
    		unsigned long end, struct vm_area_struct **pprev,
    		struct rb_node ***rb_link, struct rb_node **rb_parent)
    {
    	struct rb_node **__rb_link, *__rb_parent, *rb_prev;
    
    	__rb_link = &mm->mm_rb.rb_node;
    	rb_prev = __rb_parent = NULL;
    
    	while (*__rb_link) {
    		struct vm_area_struct *vma_tmp;
    
    		__rb_parent = *__rb_link;
    		vma_tmp = rb_entry(__rb_parent, struct vm_area_struct, vm_rb);
    
    		if (vma_tmp->vm_end > addr) {
    			/* Fail if an existing vma overlaps the area */
    			if (vma_tmp->vm_start < end)
    				return -ENOMEM;
    			__rb_link = &__rb_parent->rb_left;
    		} else {
    			rb_prev = __rb_parent;
    			__rb_link = &__rb_parent->rb_right;
    		}
    	}
    
    	*pprev = NULL;
    	if (rb_prev)
    		*pprev = rb_entry(rb_prev, struct vm_area_struct, vm_rb);
    	*rb_link = __rb_link;
    	*rb_parent = __rb_parent;
    	return 0;
    }
    
    static unsigned long count_vma_pages_range(struct mm_struct *mm,
    		unsigned long addr, unsigned long end)
    {
    	unsigned long nr_pages = 0;
    	struct vm_area_struct *vma;
    
    	/* Find first overlaping mapping */
    	vma = find_vma_intersection(mm, addr, end);
    	if (!vma)
    		return 0;
    
    	nr_pages = (min(end, vma->vm_end) -
    		max(addr, vma->vm_start)) >> PAGE_SHIFT;
    
    	/* Iterate over the rest of the overlaps */
    	for (vma = vma->vm_next; vma; vma = vma->vm_next) {
    		unsigned long overlap_len;
    
    		if (vma->vm_start > end)
    			break;
    
    		overlap_len = min(end, vma->vm_end) - vma->vm_start;
    		nr_pages += overlap_len >> PAGE_SHIFT;
    	}
    
    	return nr_pages;
    }
    
    void __vma_link_rb(struct mm_struct *mm, struct vm_area_struct *vma,
    		struct rb_node **rb_link, struct rb_node *rb_parent)
    {
    	/* Update tracking information for the gap following the new vma. */
    	if (vma->vm_next)
    		vma_gap_update(vma->vm_next);
    	else
    		mm->highest_vm_end = vm_end_gap(vma);
    
    	/*
    	 * vma->vm_prev wasn't known when we followed the rbtree to find the
    	 * correct insertion point for that vma. As a result, we could not
    	 * update the vma vm_rb parents rb_subtree_gap values on the way down.
    	 * So, we first insert the vma with a zero rb_subtree_gap value
    	 * (to be consistent with what we did on the way down), and then
    	 * immediately update the gap to the correct value. Finally we
    	 * rebalance the rbtree after all augmented values have been set.
    	 */
    	rb_link_node(&vma->vm_rb, rb_parent, rb_link);
    	vma->rb_subtree_gap = 0;
    	vma_gap_update(vma);
    	vma_rb_insert(vma, &mm->mm_rb);
    }
    
    static void __vma_link_file(struct vm_area_struct *vma)
    {
    	struct file *file;
    
    	file = vma->vm_file;
    	if (file) {
    		struct address_space *mapping = file->f_mapping;
    
    		if (vma->vm_flags & VM_DENYWRITE)
    			atomic_dec(&file_inode(file)->i_writecount);
    		if (vma->vm_flags & VM_SHARED)
    			atomic_inc(&mapping->i_mmap_writable);
    
    		flush_dcache_mmap_lock(mapping);
    		vma_interval_tree_insert(vma, &mapping->i_mmap);
    		flush_dcache_mmap_unlock(mapping);
    	}
    }
    
    static void
    __vma_link(struct mm_struct *mm, struct vm_area_struct *vma,
    	struct vm_area_struct *prev, struct rb_node **rb_link,
    	struct rb_node *rb_parent)
    {
    	__vma_link_list(mm, vma, prev, rb_parent);
    	__vma_link_rb(mm, vma, rb_link, rb_parent);
    }
    
    static void vma_link(struct mm_struct *mm, struct vm_area_struct *vma,
    			struct vm_area_struct *prev, struct rb_node **rb_link,
    			struct rb_node *rb_parent)
    {
    	struct address_space *mapping = NULL;
    
    	if (vma->vm_file) {
    		mapping = vma->vm_file->f_mapping;
    		i_mmap_lock_write(mapping);
    	}
    
    	__vma_link(mm, vma, prev, rb_link, rb_parent);
    	__vma_link_file(vma);
    
    	if (mapping)
    		i_mmap_unlock_write(mapping);
    
    	mm->map_count++;
    	validate_mm(mm);
    }
    
    /*
     * Helper for vma_adjust() in the split_vma insert case: insert a vma into the
     * mm's list and rbtree.  It has already been inserted into the interval tree.
     */
    static void __insert_vm_struct(struct mm_struct *mm, struct vm_area_struct *vma)
    {
    	struct vm_area_struct *prev;
    	struct rb_node **rb_link, *rb_parent;
    
    	if (find_vma_links(mm, vma->vm_start, vma->vm_end,
    			   &prev, &rb_link, &rb_parent))
    		BUG();
    	__vma_link(mm, vma, prev, rb_link, rb_parent);
    	mm->map_count++;
    }
    
    static __always_inline void __vma_unlink_common(struct mm_struct *mm,
    						struct vm_area_struct *vma,
    						struct vm_area_struct *prev,
    						bool has_prev,
    						struct vm_area_struct *ignore)
    {
    	struct vm_area_struct *next;
    
    	vma_rb_erase_ignore(vma, &mm->mm_rb, ignore);
    	next = vma->vm_next;
    	if (has_prev)
    		prev->vm_next = next;
    	else {
    		prev = vma->vm_prev;
    		if (prev)
    			prev->vm_next = next;
    		else
    			mm->mmap = next;
    	}
    	if (next)
    		next->vm_prev = prev;
    
    	/* Kill the cache */
    	vmacache_invalidate(mm);
    }
    
    static inline void __vma_unlink_prev(struct mm_struct *mm,
    				     struct vm_area_struct *vma,
    				     struct vm_area_struct *prev)
    {
    	__vma_unlink_common(mm, vma, prev, true, vma);
    }
    
    /*
     * We cannot adjust vm_start, vm_end, vm_pgoff fields of a vma that
     * is already present in an i_mmap tree without adjusting the tree.
     * The following helper function should be used when such adjustments
     * are necessary.  The "insert" vma (if any) is to be inserted
     * before we drop the necessary locks.
     */
    int __vma_adjust(struct vm_area_struct *vma, unsigned long start,
    	unsigned long end, pgoff_t pgoff, struct vm_area_struct *insert,
    	struct vm_area_struct *expand)
    {
    	struct mm_struct *mm = vma->vm_mm;
    	struct vm_area_struct *next = vma->vm_next, *orig_vma = vma;
    	struct address_space *mapping = NULL;
    	struct rb_root *root = NULL;
    	struct anon_vma *anon_vma = NULL;
    	struct file *file = vma->vm_file;
    	bool start_changed = false, end_changed = false;
    	long adjust_next = 0;
    	int remove_next = 0;
    
    	if (next && !insert) {
    		struct vm_area_struct *exporter = NULL, *importer = NULL;
    
    		if (end >= next->vm_end) {
    			/*
    			 * vma expands, overlapping all the next, and
    			 * perhaps the one after too (mprotect case 6).
    			 * The only other cases that gets here are
    			 * case 1, case 7 and case 8.
    			 */
    			if (next == expand) {
    				/*
    				 * The only case where we don't expand "vma"
    				 * and we expand "next" instead is case 8.
    				 */
    				VM_WARN_ON(end != next->vm_end);
    				/*
    				 * remove_next == 3 means we're
    				 * removing "vma" and that to do so we
    				 * swapped "vma" and "next".
    				 */
    				remove_next = 3;
    				VM_WARN_ON(file != next->vm_file);
    				swap(vma, next);
    			} else {
    				VM_WARN_ON(expand != vma);
    				/*
    				 * case 1, 6, 7, remove_next == 2 is case 6,
    				 * remove_next == 1 is case 1 or 7.
    				 */
    				remove_next = 1 + (end > next->vm_end);
    				VM_WARN_ON(remove_next == 2 &&
    					   end != next->vm_next->vm_end);
    				VM_WARN_ON(remove_next == 1 &&
    					   end != next->vm_end);
    				/* trim end to next, for case 6 first pass */
    				end = next->vm_end;
    			}
    
    			exporter = next;
    			importer = vma;
    
    			/*
    			 * If next doesn't have anon_vma, import from vma after
    			 * next, if the vma overlaps with it.
    			 */
    			if (remove_next == 2 && !next->anon_vma)
    				exporter = next->vm_next;
    
    		} else if (end > next->vm_start) {
    			/*
    			 * vma expands, overlapping part of the next:
    			 * mprotect case 5 shifting the boundary up.
    			 */
    			adjust_next = (end - next->vm_start) >> PAGE_SHIFT;
    			exporter = next;
    			importer = vma;
    			VM_WARN_ON(expand != importer);
    		} else if (end < vma->vm_end) {
    			/*
    			 * vma shrinks, and !insert tells it's not
    			 * split_vma inserting another: so it must be
    			 * mprotect case 4 shifting the boundary down.
    			 */
    			adjust_next = -((vma->vm_end - end) >> PAGE_SHIFT);
    			exporter = vma;
    			importer = next;
    			VM_WARN_ON(expand != importer);
    		}
    
    		/*
    		 * Easily overlooked: when mprotect shifts the boundary,
    		 * make sure the expanding vma has anon_vma set if the
    		 * shrinking vma had, to cover any anon pages imported.
    		 */
    		if (exporter && exporter->anon_vma && !importer->anon_vma) {
    			int error;
    
    			importer->anon_vma = exporter->anon_vma;
    			error = anon_vma_clone(importer, exporter);
    			if (error)
    				return error;
    		}
    	}
    again:
    	vma_adjust_trans_huge(orig_vma, start, end, adjust_next);
    
    	if (file) {
    		mapping = file->f_mapping;
    		root = &mapping->i_mmap;
    		uprobe_munmap(vma, vma->vm_start, vma->vm_end);
    
    		if (adjust_next)
    			uprobe_munmap(next, next->vm_start, next->vm_end);
    
    		i_mmap_lock_write(mapping);
    		if (insert) {
    			/*
    			 * Put into interval tree now, so instantiated pages
    			 * are visible to arm/parisc __flush_dcache_page
    			 * throughout; but we cannot insert into address
    			 * space until vma start or end is updated.
    			 */
    			__vma_link_file(insert);
    		}
    	}
    
    	anon_vma = vma->anon_vma;
    	if (!anon_vma && adjust_next)
    		anon_vma = next->anon_vma;
    	if (anon_vma) {
    		VM_WARN_ON(adjust_next && next->anon_vma &&
    			   anon_vma != next->anon_vma);
    		anon_vma_lock_write(anon_vma);
    		anon_vma_interval_tree_pre_update_vma(vma);
    		if (adjust_next)
    			anon_vma_interval_tree_pre_update_vma(next);
    	}
    
    	if (root) {
    		flush_dcache_mmap_lock(mapping);
    		vma_interval_tree_remove(vma, root);
    		if (adjust_next)
    			vma_interval_tree_remove(next, root);
    	}
    
    	if (start != vma->vm_start) {
    		vma->vm_start = start;
    		start_changed = true;
    	}
    	if (end != vma->vm_end) {
    		vma->vm_end = end;
    		end_changed = true;
    	}
    	vma->vm_pgoff = pgoff;
    	if (adjust_next) {
    		next->vm_start += adjust_next << PAGE_SHIFT;
    		next->vm_pgoff += adjust_next;
    	}
    
    	if (root) {
    		if (adjust_next)
    			vma_interval_tree_insert(next, root);
    		vma_interval_tree_insert(vma, root);
    		flush_dcache_mmap_unlock(mapping);
    	}
    
    	if (remove_next) {
    		/*
    		 * vma_merge has merged next into vma, and needs
    		 * us to remove next before dropping the locks.
    		 */
    		if (remove_next != 3)
    			__vma_unlink_prev(mm, next, vma);
    		else
    			/*
    			 * vma is not before next if they've been
    			 * swapped.
    			 *
    			 * pre-swap() next->vm_start was reduced so
    			 * tell validate_mm_rb to ignore pre-swap()
    			 * "next" (which is stored in post-swap()
    			 * "vma").
    			 */
    			__vma_unlink_common(mm, next, NULL, false, vma);
    		if (file)
    			__remove_shared_vm_struct(next, file, mapping);
    	} else if (insert) {
    		/*
    		 * split_vma has split insert from vma, and needs
    		 * us to insert it before dropping the locks
    		 * (it may either follow vma or precede it).
    		 */
    		__insert_vm_struct(mm, insert);
    	} else {
    		if (start_changed)
    			vma_gap_update(vma);
    		if (end_changed) {
    			if (!next)
    				mm->highest_vm_end = vm_end_gap(vma);
    			else if (!adjust_next)
    				vma_gap_update(next);
    		}
    	}
    
    	if (anon_vma) {
    		anon_vma_interval_tree_post_update_vma(vma);
    		if (adjust_next)
    			anon_vma_interval_tree_post_update_vma(next);
    		anon_vma_unlock_write(anon_vma);
    	}
    	if (mapping)
    		i_mmap_unlock_write(mapping);
    
    	if (root) {
    		uprobe_mmap(vma);
    
    		if (adjust_next)
    			uprobe_mmap(next);
    	}
    
    	if (remove_next) {
    		if (file) {
    			uprobe_munmap(next, next->vm_start, next->vm_end);
    			fput(file);
    		}
    		if (next->anon_vma)
    			anon_vma_merge(vma, next);
    		mm->map_count--;
    		mpol_put(vma_policy(next));
    		kmem_cache_free(vm_area_cachep, next);
    		/*
    		 * In mprotect's case 6 (see comments on vma_merge),
    		 * we must remove another next too. It would clutter
    		 * up the code too much to do both in one go.
    		 */
    		if (remove_next != 3) {
    			/*
    			 * If "next" was removed and vma->vm_end was
    			 * expanded (up) over it, in turn
    			 * "next->vm_prev->vm_end" changed and the
    			 * "vma->vm_next" gap must be updated.
    			 */
    			next = vma->vm_next;
    		} else {
    			/*
    			 * For the scope of the comment "next" and
    			 * "vma" considered pre-swap(): if "vma" was
    			 * removed, next->vm_start was expanded (down)
    			 * over it and the "next" gap must be updated.
    			 * Because of the swap() the post-swap() "vma"
    			 * actually points to pre-swap() "next"
    			 * (post-swap() "next" as opposed is now a
    			 * dangling pointer).
    			 */
    			next = vma;
    		}
    		if (remove_next == 2) {
    			remove_next = 1;
    			end = next->vm_end;
    			goto again;
    		}
    		else if (next)
    			vma_gap_update(next);
    		else {
    			/*
    			 * If remove_next == 2 we obviously can't
    			 * reach this path.
    			 *
    			 * If remove_next == 3 we can't reach this
    			 * path because pre-swap() next is always not
    			 * NULL. pre-swap() "next" is not being
    			 * removed and its next->vm_end is not altered
    			 * (and furthermore "end" already matches
    			 * next->vm_end in remove_next == 3).
    			 *
    			 * We reach this only in the remove_next == 1
    			 * case if the "next" vma that was removed was
    			 * the highest vma of the mm. However in such
    			 * case next->vm_end == "end" and the extended
    			 * "vma" has vma->vm_end == next->vm_end so
    			 * mm->highest_vm_end doesn't need any update
    			 * in remove_next == 1 case.
    			 */
    			VM_WARN_ON(mm->highest_vm_end != vm_end_gap(vma));
    		}
    	}
    	if (insert && file)
    		uprobe_mmap(insert);
    
    	validate_mm(mm);
    
    	return 0;
    }
    
    /*
     * If the vma has a ->close operation then the driver probably needs to release
     * per-vma resources, so we don't attempt to merge those.
     */
    static inline int is_mergeable_vma(struct vm_area_struct *vma,
    				struct file *file, unsigned long vm_flags,
    				struct vm_userfaultfd_ctx vm_userfaultfd_ctx)
    {
    	/*
    	 * VM_SOFTDIRTY should not prevent from VMA merging, if we
    	 * match the flags but dirty bit -- the caller should mark
    	 * merged VMA as dirty. If dirty bit won't be excluded from
    	 * comparison, we increase pressue on the memory system forcing
    	 * the kernel to generate new VMAs when old one could be
    	 * extended instead.
    	 */
    	if ((vma->vm_flags ^ vm_flags) & ~VM_SOFTDIRTY)
    		return 0;
    	if (vma->vm_file != file)
    		return 0;
    	if (vma->vm_ops && vma->vm_ops->close)
    		return 0;
    	if (!is_mergeable_vm_userfaultfd_ctx(vma, vm_userfaultfd_ctx))
    		return 0;
    	return 1;
    }
    
    static inline int is_mergeable_anon_vma(struct anon_vma *anon_vma1,
    					struct anon_vma *anon_vma2,
    					struct vm_area_struct *vma)
    {
    	/*
    	 * The list_is_singular() test is to avoid merging VMA cloned from
    	 * parents. This can improve scalability caused by anon_vma lock.