Skip to content
Snippets Groups Projects
rmap.c 52.4 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
    /*
     * mm/rmap.c - physical to virtual reverse mappings
     *
     * Copyright 2001, Rik van Riel <riel@conectiva.com.br>
     * Released under the General Public License (GPL).
     *
     * Simple, low overhead reverse mapping scheme.
     * Please try to keep this thing as modular as possible.
     *
     * Provides methods for unmapping each kind of mapped page:
     * the anon methods track anonymous pages, and
     * the file methods track pages belonging to an inode.
     *
     * Original design by Rik van Riel <riel@conectiva.com.br> 2001
     * File methods by Dave McCracken <dmccr@us.ibm.com> 2003, 2004
     * Anonymous methods by Andrea Arcangeli <andrea@suse.de> 2004
     * Contributions by Hugh Dickins 2003, 2004
     */
    
    /*
     * Lock ordering in mm:
     *
     * inode->i_mutex	(while writing or truncating, not reading or faulting)
     *   mm->mmap_sem
     *     page->flags PG_locked (lock_page)
     *       hugetlbfs_i_mmap_rwsem_key (in huge_pmd_share)
     *         mapping->i_mmap_rwsem
     *           anon_vma->rwsem
     *             mm->page_table_lock or pte_lock
     *               zone_lru_lock (in mark_page_accessed, isolate_lru_page)
     *               swap_lock (in swap_duplicate, swap_info_get)
     *                 mmlist_lock (in mmput, drain_mmlist and others)
     *                 mapping->private_lock (in __set_page_dirty_buffers)
     *                   mem_cgroup_{begin,end}_page_stat (memcg->move_lock)
     *                     mapping->tree_lock (widely used)
     *                 inode->i_lock (in set_page_dirty's __mark_inode_dirty)
     *                 bdi.wb->list_lock (in set_page_dirty's __mark_inode_dirty)
     *                   sb_lock (within inode_lock in fs/fs-writeback.c)
     *                   mapping->tree_lock (widely used, in set_page_dirty,
     *                             in arch-dependent flush_dcache_mmap_lock,
     *                             within bdi.wb->list_lock in __sync_single_inode)
     *
     * anon_vma->rwsem,mapping->i_mutex      (memory_failure, collect_procs_anon)
     *   ->tasklist_lock
     *     pte map lock
     */
    
    #include <linux/mm.h>
    #include <linux/pagemap.h>
    #include <linux/swap.h>
    #include <linux/swapops.h>
    #include <linux/slab.h>
    #include <linux/init.h>
    #include <linux/ksm.h>
    #include <linux/rmap.h>
    #include <linux/rcupdate.h>
    #include <linux/export.h>
    #include <linux/memcontrol.h>
    #include <linux/mmu_notifier.h>
    #include <linux/migrate.h>
    #include <linux/hugetlb.h>
    #include <linux/backing-dev.h>
    #include <linux/page_idle.h>
    
    #include <asm/tlbflush.h>
    
    #include <trace/events/tlb.h>
    
    #include "internal.h"
    
    static struct kmem_cache *anon_vma_cachep;
    static struct kmem_cache *anon_vma_chain_cachep;
    
    static inline struct anon_vma *anon_vma_alloc(void)
    {
    	struct anon_vma *anon_vma;
    
    	anon_vma = kmem_cache_alloc(anon_vma_cachep, GFP_KERNEL);
    	if (anon_vma) {
    		atomic_set(&anon_vma->refcount, 1);
    		anon_vma->degree = 1;	/* Reference for first vma */
    		anon_vma->parent = anon_vma;
    		/*
    		 * Initialise the anon_vma root to point to itself. If called
    		 * from fork, the root will be reset to the parents anon_vma.
    		 */
    		anon_vma->root = anon_vma;
    	}
    
    	return anon_vma;
    }
    
    static inline void anon_vma_free(struct anon_vma *anon_vma)
    {
    	VM_BUG_ON(atomic_read(&anon_vma->refcount));
    
    	/*
    	 * Synchronize against page_lock_anon_vma_read() such that
    	 * we can safely hold the lock without the anon_vma getting
    	 * freed.
    	 *
    	 * Relies on the full mb implied by the atomic_dec_and_test() from
    	 * put_anon_vma() against the acquire barrier implied by
    	 * down_read_trylock() from page_lock_anon_vma_read(). This orders:
    	 *
    	 * page_lock_anon_vma_read()	VS	put_anon_vma()
    	 *   down_read_trylock()		  atomic_dec_and_test()
    	 *   LOCK				  MB
    	 *   atomic_read()			  rwsem_is_locked()
    	 *
    	 * LOCK should suffice since the actual taking of the lock must
    	 * happen _before_ what follows.
    	 */
    	might_sleep();
    	if (rwsem_is_locked(&anon_vma->root->rwsem)) {
    		anon_vma_lock_write(anon_vma);
    		anon_vma_unlock_write(anon_vma);
    	}
    
    	kmem_cache_free(anon_vma_cachep, anon_vma);
    }
    
    static inline struct anon_vma_chain *anon_vma_chain_alloc(gfp_t gfp)
    {
    	return kmem_cache_alloc(anon_vma_chain_cachep, gfp);
    }
    
    static void anon_vma_chain_free(struct anon_vma_chain *anon_vma_chain)
    {
    	kmem_cache_free(anon_vma_chain_cachep, anon_vma_chain);
    }
    
    static void anon_vma_chain_link(struct vm_area_struct *vma,
    				struct anon_vma_chain *avc,
    				struct anon_vma *anon_vma)
    {
    	avc->vma = vma;
    	avc->anon_vma = anon_vma;
    	list_add(&avc->same_vma, &vma->anon_vma_chain);
    	anon_vma_interval_tree_insert(avc, &anon_vma->rb_root);
    }
    
    /**
     * anon_vma_prepare - attach an anon_vma to a memory region
     * @vma: the memory region in question
     *
     * This makes sure the memory mapping described by 'vma' has
     * an 'anon_vma' attached to it, so that we can associate the
     * anonymous pages mapped into it with that anon_vma.
     *
     * The common case will be that we already have one, but if
     * not we either need to find an adjacent mapping that we
     * can re-use the anon_vma from (very common when the only
     * reason for splitting a vma has been mprotect()), or we
     * allocate a new one.
     *
     * Anon-vma allocations are very subtle, because we may have
     * optimistically looked up an anon_vma in page_lock_anon_vma_read()
     * and that may actually touch the spinlock even in the newly
     * allocated vma (it depends on RCU to make sure that the
     * anon_vma isn't actually destroyed).
     *
     * As a result, we need to do proper anon_vma locking even
     * for the new allocation. At the same time, we do not want
     * to do any locking for the common case of already having
     * an anon_vma.
     *
     * This must be called with the mmap_sem held for reading.
     */
    int anon_vma_prepare(struct vm_area_struct *vma)
    {
    	struct anon_vma *anon_vma = vma->anon_vma;
    	struct anon_vma_chain *avc;
    
    	might_sleep();
    	if (unlikely(!anon_vma)) {
    		struct mm_struct *mm = vma->vm_mm;
    		struct anon_vma *allocated;
    
    		avc = anon_vma_chain_alloc(GFP_KERNEL);
    		if (!avc)
    			goto out_enomem;
    
    		anon_vma = find_mergeable_anon_vma(vma);
    		allocated = NULL;
    		if (!anon_vma) {
    			anon_vma = anon_vma_alloc();
    			if (unlikely(!anon_vma))
    				goto out_enomem_free_avc;
    			allocated = anon_vma;
    		}
    
    		anon_vma_lock_write(anon_vma);
    		/* page_table_lock to protect against threads */
    		spin_lock(&mm->page_table_lock);
    		if (likely(!vma->anon_vma)) {
    			vma->anon_vma = anon_vma;
    			anon_vma_chain_link(vma, avc, anon_vma);
    			/* vma reference or self-parent link for new root */
    			anon_vma->degree++;
    			allocated = NULL;
    			avc = NULL;
    		}
    		spin_unlock(&mm->page_table_lock);
    		anon_vma_unlock_write(anon_vma);
    
    		if (unlikely(allocated))
    			put_anon_vma(allocated);
    		if (unlikely(avc))
    			anon_vma_chain_free(avc);
    	}
    	return 0;
    
     out_enomem_free_avc:
    	anon_vma_chain_free(avc);
     out_enomem:
    	return -ENOMEM;
    }
    
    /*
     * This is a useful helper function for locking the anon_vma root as
     * we traverse the vma->anon_vma_chain, looping over anon_vma's that
     * have the same vma.
     *
     * Such anon_vma's should have the same root, so you'd expect to see
     * just a single mutex_lock for the whole traversal.
     */
    static inline struct anon_vma *lock_anon_vma_root(struct anon_vma *root, struct anon_vma *anon_vma)
    {
    	struct anon_vma *new_root = anon_vma->root;
    	if (new_root != root) {
    		if (WARN_ON_ONCE(root))
    			up_write(&root->rwsem);
    		root = new_root;
    		down_write(&root->rwsem);
    	}
    	return root;
    }
    
    static inline void unlock_anon_vma_root(struct anon_vma *root)
    {
    	if (root)
    		up_write(&root->rwsem);
    }
    
    /*
     * Attach the anon_vmas from src to dst.
     * Returns 0 on success, -ENOMEM on failure.
     *
     * If dst->anon_vma is NULL this function tries to find and reuse existing
     * anon_vma which has no vmas and only one child anon_vma. This prevents
     * degradation of anon_vma hierarchy to endless linear chain in case of
     * constantly forking task. On the other hand, an anon_vma with more than one
     * child isn't reused even if there was no alive vma, thus rmap walker has a
     * good chance of avoiding scanning the whole hierarchy when it searches where
     * page is mapped.
     */
    int anon_vma_clone(struct vm_area_struct *dst, struct vm_area_struct *src)
    {
    	struct anon_vma_chain *avc, *pavc;
    	struct anon_vma *root = NULL;
    
    	list_for_each_entry_reverse(pavc, &src->anon_vma_chain, same_vma) {
    		struct anon_vma *anon_vma;
    
    		avc = anon_vma_chain_alloc(GFP_NOWAIT | __GFP_NOWARN);
    		if (unlikely(!avc)) {
    			unlock_anon_vma_root(root);
    			root = NULL;
    			avc = anon_vma_chain_alloc(GFP_KERNEL);
    			if (!avc)
    				goto enomem_failure;
    		}
    		anon_vma = pavc->anon_vma;
    		root = lock_anon_vma_root(root, anon_vma);
    		anon_vma_chain_link(dst, avc, anon_vma);
    
    		/*
    		 * Reuse existing anon_vma if its degree lower than two,
    		 * that means it has no vma and only one anon_vma child.
    		 *
    		 * Do not chose parent anon_vma, otherwise first child
    		 * will always reuse it. Root anon_vma is never reused:
    		 * it has self-parent reference and at least one child.
    		 */
    		if (!dst->anon_vma && anon_vma != src->anon_vma &&
    				anon_vma->degree < 2)
    			dst->anon_vma = anon_vma;
    	}
    	if (dst->anon_vma)
    		dst->anon_vma->degree++;
    	unlock_anon_vma_root(root);
    	return 0;
    
     enomem_failure:
    	/*
    	 * dst->anon_vma is dropped here otherwise its degree can be incorrectly
    	 * decremented in unlink_anon_vmas().
    	 * We can safely do this because callers of anon_vma_clone() don't care
    	 * about dst->anon_vma if anon_vma_clone() failed.
    	 */
    	dst->anon_vma = NULL;
    	unlink_anon_vmas(dst);
    	return -ENOMEM;
    }
    
    /*
     * Attach vma to its own anon_vma, as well as to the anon_vmas that
     * the corresponding VMA in the parent process is attached to.
     * Returns 0 on success, non-zero on failure.
     */
    int anon_vma_fork(struct vm_area_struct *vma, struct vm_area_struct *pvma)
    {
    	struct anon_vma_chain *avc;
    	struct anon_vma *anon_vma;
    	int error;
    
    	/* Don't bother if the parent process has no anon_vma here. */
    	if (!pvma->anon_vma)
    		return 0;
    
    	/* Drop inherited anon_vma, we'll reuse existing or allocate new. */
    	vma->anon_vma = NULL;
    
    	/*
    	 * First, attach the new VMA to the parent VMA's anon_vmas,
    	 * so rmap can find non-COWed pages in child processes.
    	 */
    	error = anon_vma_clone(vma, pvma);
    	if (error)
    		return error;
    
    	/* An existing anon_vma has been reused, all done then. */
    	if (vma->anon_vma)
    		return 0;
    
    	/* Then add our own anon_vma. */
    	anon_vma = anon_vma_alloc();
    	if (!anon_vma)
    		goto out_error;
    	avc = anon_vma_chain_alloc(GFP_KERNEL);
    	if (!avc)
    		goto out_error_free_anon_vma;
    
    	/*
    	 * The root anon_vma's spinlock is the lock actually used when we
    	 * lock any of the anon_vmas in this anon_vma tree.
    	 */
    	anon_vma->root = pvma->anon_vma->root;
    	anon_vma->parent = pvma->anon_vma;
    	/*
    	 * With refcounts, an anon_vma can stay around longer than the
    	 * process it belongs to. The root anon_vma needs to be pinned until
    	 * this anon_vma is freed, because the lock lives in the root.
    	 */
    	get_anon_vma(anon_vma->root);
    	/* Mark this anon_vma as the one where our new (COWed) pages go. */
    	vma->anon_vma = anon_vma;
    	anon_vma_lock_write(anon_vma);
    	anon_vma_chain_link(vma, avc, anon_vma);
    	anon_vma->parent->degree++;
    	anon_vma_unlock_write(anon_vma);
    
    	return 0;
    
     out_error_free_anon_vma:
    	put_anon_vma(anon_vma);
     out_error:
    	unlink_anon_vmas(vma);
    	return -ENOMEM;
    }
    
    void unlink_anon_vmas(struct vm_area_struct *vma)
    {
    	struct anon_vma_chain *avc, *next;
    	struct anon_vma *root = NULL;
    
    	/*
    	 * Unlink each anon_vma chained to the VMA.  This list is ordered
    	 * from newest to oldest, ensuring the root anon_vma gets freed last.
    	 */
    	list_for_each_entry_safe(avc, next, &vma->anon_vma_chain, same_vma) {
    		struct anon_vma *anon_vma = avc->anon_vma;
    
    		root = lock_anon_vma_root(root, anon_vma);
    		anon_vma_interval_tree_remove(avc, &anon_vma->rb_root);
    
    		/*
    		 * Leave empty anon_vmas on the list - we'll need
    		 * to free them outside the lock.
    		 */
    		if (RB_EMPTY_ROOT(&anon_vma->rb_root)) {
    			anon_vma->parent->degree--;
    			continue;
    		}
    
    		list_del(&avc->same_vma);
    		anon_vma_chain_free(avc);
    	}
    	if (vma->anon_vma)
    		vma->anon_vma->degree--;
    	unlock_anon_vma_root(root);
    
    	/*
    	 * Iterate the list once more, it now only contains empty and unlinked
    	 * anon_vmas, destroy them. Could not do before due to __put_anon_vma()
    	 * needing to write-acquire the anon_vma->root->rwsem.
    	 */
    	list_for_each_entry_safe(avc, next, &vma->anon_vma_chain, same_vma) {
    		struct anon_vma *anon_vma = avc->anon_vma;
    
    		VM_WARN_ON(anon_vma->degree);
    		put_anon_vma(anon_vma);
    
    		list_del(&avc->same_vma);
    		anon_vma_chain_free(avc);
    	}
    }
    
    static void anon_vma_ctor(void *data)
    {
    	struct anon_vma *anon_vma = data;
    
    	init_rwsem(&anon_vma->rwsem);
    	atomic_set(&anon_vma->refcount, 0);
    	anon_vma->rb_root = RB_ROOT;
    }
    
    void __init anon_vma_init(void)
    {
    	anon_vma_cachep = kmem_cache_create("anon_vma", sizeof(struct anon_vma),
    			0, SLAB_DESTROY_BY_RCU|SLAB_PANIC|SLAB_ACCOUNT,
    			anon_vma_ctor);
    	anon_vma_chain_cachep = KMEM_CACHE(anon_vma_chain,
    			SLAB_PANIC|SLAB_ACCOUNT);
    }
    
    /*
     * Getting a lock on a stable anon_vma from a page off the LRU is tricky!
     *
     * Since there is no serialization what so ever against page_remove_rmap()
     * the best this function can do is return a locked anon_vma that might
     * have been relevant to this page.
     *
     * The page might have been remapped to a different anon_vma or the anon_vma
     * returned may already be freed (and even reused).
     *
     * In case it was remapped to a different anon_vma, the new anon_vma will be a
     * child of the old anon_vma, and the anon_vma lifetime rules will therefore
     * ensure that any anon_vma obtained from the page will still be valid for as
     * long as we observe page_mapped() [ hence all those page_mapped() tests ].
     *
     * All users of this function must be very careful when walking the anon_vma
     * chain and verify that the page in question is indeed mapped in it
     * [ something equivalent to page_mapped_in_vma() ].
     *
     * Since anon_vma's slab is DESTROY_BY_RCU and we know from page_remove_rmap()
     * that the anon_vma pointer from page->mapping is valid if there is a
     * mapcount, we can dereference the anon_vma after observing those.
     */
    struct anon_vma *page_get_anon_vma(struct page *page)
    {
    	struct anon_vma *anon_vma = NULL;
    	unsigned long anon_mapping;
    
    	rcu_read_lock();
    	anon_mapping = (unsigned long)READ_ONCE(page->mapping);
    	if ((anon_mapping & PAGE_MAPPING_FLAGS) != PAGE_MAPPING_ANON)
    		goto out;
    	if (!page_mapped(page))
    		goto out;
    
    	anon_vma = (struct anon_vma *) (anon_mapping - PAGE_MAPPING_ANON);
    	if (!atomic_inc_not_zero(&anon_vma->refcount)) {
    		anon_vma = NULL;
    		goto out;
    	}
    
    	/*
    	 * If this page is still mapped, then its anon_vma cannot have been
    	 * freed.  But if it has been unmapped, we have no security against the
    	 * anon_vma structure being freed and reused (for another anon_vma:
    	 * SLAB_DESTROY_BY_RCU guarantees that - so the atomic_inc_not_zero()
    	 * above cannot corrupt).
    	 */
    	if (!page_mapped(page)) {
    		rcu_read_unlock();
    		put_anon_vma(anon_vma);
    		return NULL;
    	}
    out:
    	rcu_read_unlock();
    
    	return anon_vma;
    }
    
    /*
     * Similar to page_get_anon_vma() except it locks the anon_vma.
     *
     * Its a little more complex as it tries to keep the fast path to a single
     * atomic op -- the trylock. If we fail the trylock, we fall back to getting a
     * reference like with page_get_anon_vma() and then block on the mutex.
     */
    struct anon_vma *page_lock_anon_vma_read(struct page *page)
    {
    	struct anon_vma *anon_vma = NULL;
    	struct anon_vma *root_anon_vma;
    	unsigned long anon_mapping;
    
    	rcu_read_lock();
    	anon_mapping = (unsigned long)READ_ONCE(page->mapping);
    	if ((anon_mapping & PAGE_MAPPING_FLAGS) != PAGE_MAPPING_ANON)
    		goto out;
    	if (!page_mapped(page))
    		goto out;
    
    	anon_vma = (struct anon_vma *) (anon_mapping - PAGE_MAPPING_ANON);
    	root_anon_vma = READ_ONCE(anon_vma->root);
    	if (down_read_trylock(&root_anon_vma->rwsem)) {
    		/*
    		 * If the page is still mapped, then this anon_vma is still
    		 * its anon_vma, and holding the mutex ensures that it will
    		 * not go away, see anon_vma_free().
    		 */
    		if (!page_mapped(page)) {
    			up_read(&root_anon_vma->rwsem);
    			anon_vma = NULL;
    		}
    		goto out;
    	}
    
    	/* trylock failed, we got to sleep */
    	if (!atomic_inc_not_zero(&anon_vma->refcount)) {
    		anon_vma = NULL;
    		goto out;
    	}
    
    	if (!page_mapped(page)) {
    		rcu_read_unlock();
    		put_anon_vma(anon_vma);
    		return NULL;
    	}
    
    	/* we pinned the anon_vma, its safe to sleep */
    	rcu_read_unlock();
    	anon_vma_lock_read(anon_vma);
    
    	if (atomic_dec_and_test(&anon_vma->refcount)) {
    		/*
    		 * Oops, we held the last refcount, release the lock
    		 * and bail -- can't simply use put_anon_vma() because
    		 * we'll deadlock on the anon_vma_lock_write() recursion.
    		 */
    		anon_vma_unlock_read(anon_vma);
    		__put_anon_vma(anon_vma);
    		anon_vma = NULL;
    	}
    
    	return anon_vma;
    
    out:
    	rcu_read_unlock();
    	return anon_vma;
    }
    
    void page_unlock_anon_vma_read(struct anon_vma *anon_vma)
    {
    	anon_vma_unlock_read(anon_vma);
    }
    
    #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
    /*
     * Flush TLB entries for recently unmapped pages from remote CPUs. It is
     * important if a PTE was dirty when it was unmapped that it's flushed
     * before any IO is initiated on the page to prevent lost writes. Similarly,
     * it must be flushed before freeing to prevent data leakage.
     */
    void try_to_unmap_flush(void)
    {
    	struct tlbflush_unmap_batch *tlb_ubc = &current->tlb_ubc;
    	int cpu;
    
    	if (!tlb_ubc->flush_required)
    		return;
    
    	cpu = get_cpu();
    
    	if (cpumask_test_cpu(cpu, &tlb_ubc->cpumask)) {
    		count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
    		local_flush_tlb();
    		trace_tlb_flush(TLB_LOCAL_SHOOTDOWN, TLB_FLUSH_ALL);
    	}
    
    	if (cpumask_any_but(&tlb_ubc->cpumask, cpu) < nr_cpu_ids)
    		flush_tlb_others(&tlb_ubc->cpumask, NULL, 0, TLB_FLUSH_ALL);
    	cpumask_clear(&tlb_ubc->cpumask);
    	tlb_ubc->flush_required = false;
    	tlb_ubc->writable = false;
    	put_cpu();
    }
    
    /* Flush iff there are potentially writable TLB entries that can race with IO */
    void try_to_unmap_flush_dirty(void)
    {
    	struct tlbflush_unmap_batch *tlb_ubc = &current->tlb_ubc;
    
    	if (tlb_ubc->writable)
    		try_to_unmap_flush();
    }
    
    static void set_tlb_ubc_flush_pending(struct mm_struct *mm,
    		struct page *page, bool writable)
    {
    	struct tlbflush_unmap_batch *tlb_ubc = &current->tlb_ubc;
    
    	cpumask_or(&tlb_ubc->cpumask, &tlb_ubc->cpumask, mm_cpumask(mm));
    	tlb_ubc->flush_required = true;
    
    	/*
    	 * Ensure compiler does not re-order the setting of tlb_flush_batched
    	 * before the PTE is cleared.
    	 */
    	barrier();
    	mm->tlb_flush_batched = true;
    
    	/*
    	 * If the PTE was dirty then it's best to assume it's writable. The
    	 * caller must use try_to_unmap_flush_dirty() or try_to_unmap_flush()
    	 * before the page is queued for IO.
    	 */
    	if (writable)
    		tlb_ubc->writable = true;
    }
    
    /*
     * Returns true if the TLB flush should be deferred to the end of a batch of
     * unmap operations to reduce IPIs.
     */
    static bool should_defer_flush(struct mm_struct *mm, enum ttu_flags flags)
    {
    	bool should_defer = false;
    
    	if (!(flags & TTU_BATCH_FLUSH))
    		return false;
    
    	/* If remote CPUs need to be flushed then defer batch the flush */
    	if (cpumask_any_but(mm_cpumask(mm), get_cpu()) < nr_cpu_ids)
    		should_defer = true;
    	put_cpu();
    
    	return should_defer;
    }
    
    /*
     * Reclaim unmaps pages under the PTL but do not flush the TLB prior to
     * releasing the PTL if TLB flushes are batched. It's possible for a parallel
     * operation such as mprotect or munmap to race between reclaim unmapping
     * the page and flushing the page. If this race occurs, it potentially allows
     * access to data via a stale TLB entry. Tracking all mm's that have TLB
     * batching in flight would be expensive during reclaim so instead track
     * whether TLB batching occurred in the past and if so then do a flush here
     * if required. This will cost one additional flush per reclaim cycle paid
     * by the first operation at risk such as mprotect and mumap.
     *
     * This must be called under the PTL so that an access to tlb_flush_batched
     * that is potentially a "reclaim vs mprotect/munmap/etc" race will synchronise
     * via the PTL.
     */
    void flush_tlb_batched_pending(struct mm_struct *mm)
    {
    	if (mm->tlb_flush_batched) {
    		flush_tlb_mm(mm);
    
    		/*
    		 * Do not allow the compiler to re-order the clearing of
    		 * tlb_flush_batched before the tlb is flushed.
    		 */
    		barrier();
    		mm->tlb_flush_batched = false;
    	}
    }
    #else
    static void set_tlb_ubc_flush_pending(struct mm_struct *mm,
    		struct page *page, bool writable)
    {
    }
    
    static bool should_defer_flush(struct mm_struct *mm, enum ttu_flags flags)
    {
    	return false;
    }
    #endif /* CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH */
    
    /*
     * At what user virtual address is page expected in vma?
     * Caller should check the page is actually part of the vma.
     */
    unsigned long page_address_in_vma(struct page *page, struct vm_area_struct *vma)
    {
    	unsigned long address;
    	if (PageAnon(page)) {
    		struct anon_vma *page__anon_vma = page_anon_vma(page);
    		/*
    		 * Note: swapoff's unuse_vma() is more efficient with this
    		 * check, and needs it to match anon_vma when KSM is active.
    		 */
    		if (!vma->anon_vma || !page__anon_vma ||
    		    vma->anon_vma->root != page__anon_vma->root)
    			return -EFAULT;
    	} else if (page->mapping) {
    		if (!vma->vm_file || vma->vm_file->f_mapping != page->mapping)
    			return -EFAULT;
    	} else
    		return -EFAULT;
    	address = __vma_address(page, vma);
    	if (unlikely(address < vma->vm_start || address >= vma->vm_end))
    		return -EFAULT;
    	return address;
    }
    
    pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address)
    {
    	pgd_t *pgd;
    	pud_t *pud;
    	pmd_t *pmd = NULL;
    	pmd_t pmde;
    
    	pgd = pgd_offset(mm, address);
    	if (!pgd_present(*pgd))
    		goto out;
    
    	pud = pud_offset(pgd, address);
    	if (!pud_present(*pud))
    		goto out;
    
    	pmd = pmd_offset(pud, address);
    	/*
    	 * Some THP functions use the sequence pmdp_huge_clear_flush(), set_pmd_at()
    	 * without holding anon_vma lock for write.  So when looking for a
    	 * genuine pmde (in which to find pte), test present and !THP together.
    	 */
    	pmde = *pmd;
    	barrier();
    	if (!pmd_present(pmde) || pmd_trans_huge(pmde))
    		pmd = NULL;
    out:
    	return pmd;
    }
    
    /*
     * Check that @page is mapped at @address into @mm.
     *
     * If @sync is false, page_check_address may perform a racy check to avoid
     * the page table lock when the pte is not present (helpful when reclaiming
     * highly shared pages).
     *
     * On success returns with pte mapped and locked.
     */
    pte_t *__page_check_address(struct page *page, struct mm_struct *mm,
    			  unsigned long address, spinlock_t **ptlp, int sync)
    {
    	pmd_t *pmd;
    	pte_t *pte;
    	spinlock_t *ptl;
    
    	if (unlikely(PageHuge(page))) {
    		/* when pud is not present, pte will be NULL */
    		pte = huge_pte_offset(mm, address);
    		if (!pte)
    			return NULL;
    
    		ptl = huge_pte_lockptr(page_hstate(page), mm, pte);
    		goto check;
    	}
    
    	pmd = mm_find_pmd(mm, address);
    	if (!pmd)
    		return NULL;
    
    	pte = pte_offset_map(pmd, address);
    	/* Make a quick check before getting the lock */
    	if (!sync && !pte_present(*pte)) {
    		pte_unmap(pte);
    		return NULL;
    	}
    
    	ptl = pte_lockptr(mm, pmd);
    check:
    	spin_lock(ptl);
    	if (pte_present(*pte) && page_to_pfn(page) == pte_pfn(*pte)) {
    		*ptlp = ptl;
    		return pte;
    	}
    	pte_unmap_unlock(pte, ptl);
    	return NULL;
    }
    
    /**
     * page_mapped_in_vma - check whether a page is really mapped in a VMA
     * @page: the page to test
     * @vma: the VMA to test
     *
     * Returns 1 if the page is mapped into the page tables of the VMA, 0
     * if the page is not mapped into the page tables of this VMA.  Only
     * valid for normal file or anonymous VMAs.
     */
    int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma)
    {
    	unsigned long address;
    	pte_t *pte;
    	spinlock_t *ptl;
    
    	address = __vma_address(page, vma);
    	if (unlikely(address < vma->vm_start || address >= vma->vm_end))
    		return 0;
    	pte = page_check_address(page, vma->vm_mm, address, &ptl, 1);
    	if (!pte)			/* the page is not in this mm */
    		return 0;
    	pte_unmap_unlock(pte, ptl);
    
    	return 1;
    }
    
    #ifdef CONFIG_TRANSPARENT_HUGEPAGE
    /*
     * Check that @page is mapped at @address into @mm. In contrast to
     * page_check_address(), this function can handle transparent huge pages.
     *
     * On success returns true with pte mapped and locked. For PMD-mapped
     * transparent huge pages *@ptep is set to NULL.
     */
    bool page_check_address_transhuge(struct page *page, struct mm_struct *mm,
    				  unsigned long address, pmd_t **pmdp,
    				  pte_t **ptep, spinlock_t **ptlp)
    {
    	pgd_t *pgd;
    	pud_t *pud;
    	pmd_t *pmd;
    	pte_t *pte;
    	spinlock_t *ptl;
    
    	if (unlikely(PageHuge(page))) {
    		/* when pud is not present, pte will be NULL */
    		pte = huge_pte_offset(mm, address);
    		if (!pte)
    			return false;
    
    		ptl = huge_pte_lockptr(page_hstate(page), mm, pte);
    		pmd = NULL;
    		goto check_pte;
    	}
    
    	pgd = pgd_offset(mm, address);
    	if (!pgd_present(*pgd))
    		return false;
    	pud = pud_offset(pgd, address);
    	if (!pud_present(*pud))
    		return false;
    	pmd = pmd_offset(pud, address);
    
    	if (pmd_trans_huge(*pmd)) {
    		ptl = pmd_lock(mm, pmd);
    		if (!pmd_present(*pmd))
    			goto unlock_pmd;
    		if (unlikely(!pmd_trans_huge(*pmd))) {
    			spin_unlock(ptl);
    			goto map_pte;
    		}
    
    		if (pmd_page(*pmd) != page)
    			goto unlock_pmd;
    
    		pte = NULL;
    		goto found;
    unlock_pmd:
    		spin_unlock(ptl);
    		return false;
    	} else {
    		pmd_t pmde = *pmd;
    
    		barrier();
    		if (!pmd_present(pmde) || pmd_trans_huge(pmde))
    			return false;
    	}
    map_pte:
    	pte = pte_offset_map(pmd, address);
    	if (!pte_present(*pte)) {
    		pte_unmap(pte);
    		return false;
    	}
    
    	ptl = pte_lockptr(mm, pmd);
    check_pte:
    	spin_lock(ptl);
    
    	if (!pte_present(*pte)) {
    		pte_unmap_unlock(pte, ptl);
    		return false;
    	}
    
    	/* THP can be referenced by any subpage */
    	if (pte_pfn(*pte) - page_to_pfn(page) >= hpage_nr_pages(page)) {
    		pte_unmap_unlock(pte, ptl);
    		return false;
    	}
    found:
    	*ptep = pte;
    	*pmdp = pmd;
    	*ptlp = ptl;
    	return true;
    }
    #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
    
    struct page_referenced_arg {
    	int mapcount;
    	int referenced;
    	unsigned long vm_flags;
    	struct mem_cgroup *memcg;
    };
    /*
     * arg: page_referenced_arg will be passed
     */
    static int page_referenced_one(struct page *page, struct vm_area_struct *vma,
    			unsigned long address, void *arg)
    {
    	struct mm_struct *mm = vma->vm_mm;
    	struct page_referenced_arg *pra = arg;
    	pmd_t *pmd;
    	pte_t *pte;
    	spinlock_t *ptl;
    	int referenced = 0;
    
    	if (!page_check_address_transhuge(page, mm, address, &pmd, &pte, &ptl))
    		return SWAP_AGAIN;
    
    	if (vma->vm_flags & VM_LOCKED) {
    		if (pte)
    			pte_unmap(pte);
    		spin_unlock(ptl);
    		pra->vm_flags |= VM_LOCKED;
    		return SWAP_FAIL; /* To break the loop */
    	}
    
    	if (pte) {
    		if (ptep_clear_flush_young_notify(vma, address, pte)) {
    			/*
    			 * Don't treat a reference through a sequentially read
    			 * mapping as such.  If the page has been used in
    			 * another mapping, we will catch it; if this other
    			 * mapping is already gone, the unmap path will have
    			 * set PG_referenced or activated the page.
    			 */
    			if (likely(!(vma->vm_flags & VM_SEQ_READ)))
    				referenced++;
    		}
    		pte_unmap(pte);
    	} else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) {
    		if (pmdp_clear_flush_young_notify(vma, address, pmd))
    			referenced++;
    	} else {
    		/* unexpected pmd-mapped page? */
    		WARN_ON_ONCE(1);
    	}
    	spin_unlock(ptl);
    
    	if (referenced)
    		clear_page_idle(page);
    	if (test_and_clear_page_young(page))
    		referenced++;
    
    	if (referenced) {
    		pra->referenced++;
    		pra->vm_flags |= vma->vm_flags;
    	}
    
    	pra->mapcount--;
    	if (!pra->mapcount)
    		return SWAP_SUCCESS; /* To break the loop */
    
    	return SWAP_AGAIN;
    }
    
    static bool invalid_page_referenced_vma(struct vm_area_struct *vma, void *arg)
    {
    	struct page_referenced_arg *pra = arg;
    	struct mem_cgroup *memcg = pra->memcg;
    
    	if (!mm_match_cgroup(vma->vm_mm, memcg))
    		return true;
    
    	return false;
    }
    
    /**
     * page_referenced - test if the page was referenced
     * @page: the page to test
     * @is_locked: caller holds lock on the page
     * @memcg: target memory cgroup
     * @vm_flags: collect encountered vma->vm_flags who actually referenced the page
     *