Skip to content
Snippets Groups Projects
vmalloc.c 69.1 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/vmalloc.c
     *
     *  Copyright (C) 1993  Linus Torvalds
     *  Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999
     *  SMP-safe vmalloc/vfree/ioremap, Tigran Aivazian <tigran@veritas.com>, May 2000
     *  Major rework to support vmap/vunmap, Christoph Hellwig, SGI, August 2002
     *  Numa awareness, Christoph Lameter, SGI, June 2005
     */
    
    #include <linux/vmalloc.h>
    #include <linux/mm.h>
    #include <linux/module.h>
    #include <linux/highmem.h>
    #include <linux/sched.h>
    #include <linux/slab.h>
    #include <linux/spinlock.h>
    #include <linux/interrupt.h>
    #include <linux/proc_fs.h>
    #include <linux/seq_file.h>
    #include <linux/debugobjects.h>
    #include <linux/kallsyms.h>
    #include <linux/list.h>
    #include <linux/notifier.h>
    #include <linux/rbtree.h>
    #include <linux/radix-tree.h>
    #include <linux/rcupdate.h>
    #include <linux/pfn.h>
    #include <linux/kmemleak.h>
    #include <linux/atomic.h>
    #include <linux/compiler.h>
    #include <linux/llist.h>
    #include <linux/bitops.h>
    
    #include <asm/uaccess.h>
    #include <asm/tlbflush.h>
    #include <asm/shmparam.h>
    
    #include "internal.h"
    
    struct vfree_deferred {
    	struct llist_head list;
    	struct work_struct wq;
    };
    static DEFINE_PER_CPU(struct vfree_deferred, vfree_deferred);
    
    static void __vunmap(const void *, int);
    
    static void free_work(struct work_struct *w)
    {
    	struct vfree_deferred *p = container_of(w, struct vfree_deferred, wq);
    	struct llist_node *llnode = llist_del_all(&p->list);
    	while (llnode) {
    		void *p = llnode;
    		llnode = llist_next(llnode);
    		__vunmap(p, 1);
    	}
    }
    
    /*** Page table manipulation functions ***/
    
    static void vunmap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end)
    {
    	pte_t *pte;
    
    	pte = pte_offset_kernel(pmd, addr);
    	do {
    		pte_t ptent = ptep_get_and_clear(&init_mm, addr, pte);
    		WARN_ON(!pte_none(ptent) && !pte_present(ptent));
    	} while (pte++, addr += PAGE_SIZE, addr != end);
    }
    
    static void vunmap_pmd_range(pud_t *pud, unsigned long addr, unsigned long end)
    {
    	pmd_t *pmd;
    	unsigned long next;
    
    	pmd = pmd_offset(pud, addr);
    	do {
    		next = pmd_addr_end(addr, end);
    		if (pmd_clear_huge(pmd))
    			continue;
    		if (pmd_none_or_clear_bad(pmd))
    			continue;
    		vunmap_pte_range(pmd, addr, next);
    	} while (pmd++, addr = next, addr != end);
    }
    
    static void vunmap_pud_range(pgd_t *pgd, unsigned long addr, unsigned long end)
    {
    	pud_t *pud;
    	unsigned long next;
    
    	pud = pud_offset(pgd, addr);
    	do {
    		next = pud_addr_end(addr, end);
    		if (pud_clear_huge(pud))
    			continue;
    		if (pud_none_or_clear_bad(pud))
    			continue;
    		vunmap_pmd_range(pud, addr, next);
    	} while (pud++, addr = next, addr != end);
    }
    
    static void vunmap_page_range(unsigned long addr, unsigned long end)
    {
    	pgd_t *pgd;
    	unsigned long next;
    
    	BUG_ON(addr >= end);
    	pgd = pgd_offset_k(addr);
    	do {
    		next = pgd_addr_end(addr, end);
    		if (pgd_none_or_clear_bad(pgd))
    			continue;
    		vunmap_pud_range(pgd, addr, next);
    	} while (pgd++, addr = next, addr != end);
    }
    
    static int vmap_pte_range(pmd_t *pmd, unsigned long addr,
    		unsigned long end, pgprot_t prot, struct page **pages, int *nr)
    {
    	pte_t *pte;
    
    	/*
    	 * nr is a running index into the array which helps higher level
    	 * callers keep track of where we're up to.
    	 */
    
    	pte = pte_alloc_kernel(pmd, addr);
    	if (!pte)
    		return -ENOMEM;
    	do {
    		struct page *page = pages[*nr];
    
    		if (WARN_ON(!pte_none(*pte)))
    			return -EBUSY;
    		if (WARN_ON(!page))
    			return -ENOMEM;
    		set_pte_at(&init_mm, addr, pte, mk_pte(page, prot));
    		(*nr)++;
    	} while (pte++, addr += PAGE_SIZE, addr != end);
    	return 0;
    }
    
    static int vmap_pmd_range(pud_t *pud, unsigned long addr,
    		unsigned long end, pgprot_t prot, struct page **pages, int *nr)
    {
    	pmd_t *pmd;
    	unsigned long next;
    
    	pmd = pmd_alloc(&init_mm, pud, addr);
    	if (!pmd)
    		return -ENOMEM;
    	do {
    		next = pmd_addr_end(addr, end);
    		if (vmap_pte_range(pmd, addr, next, prot, pages, nr))
    			return -ENOMEM;
    	} while (pmd++, addr = next, addr != end);
    	return 0;
    }
    
    static int vmap_pud_range(pgd_t *pgd, unsigned long addr,
    		unsigned long end, pgprot_t prot, struct page **pages, int *nr)
    {
    	pud_t *pud;
    	unsigned long next;
    
    	pud = pud_alloc(&init_mm, pgd, addr);
    	if (!pud)
    		return -ENOMEM;
    	do {
    		next = pud_addr_end(addr, end);
    		if (vmap_pmd_range(pud, addr, next, prot, pages, nr))
    			return -ENOMEM;
    	} while (pud++, addr = next, addr != end);
    	return 0;
    }
    
    /*
     * Set up page tables in kva (addr, end). The ptes shall have prot "prot", and
     * will have pfns corresponding to the "pages" array.
     *
     * Ie. pte at addr+N*PAGE_SIZE shall point to pfn corresponding to pages[N]
     */
    static int vmap_page_range_noflush(unsigned long start, unsigned long end,
    				   pgprot_t prot, struct page **pages)
    {
    	pgd_t *pgd;
    	unsigned long next;
    	unsigned long addr = start;
    	int err = 0;
    	int nr = 0;
    
    	BUG_ON(addr >= end);
    	pgd = pgd_offset_k(addr);
    	do {
    		next = pgd_addr_end(addr, end);
    		err = vmap_pud_range(pgd, addr, next, prot, pages, &nr);
    		if (err)
    			return err;
    	} while (pgd++, addr = next, addr != end);
    
    	return nr;
    }
    
    static int vmap_page_range(unsigned long start, unsigned long end,
    			   pgprot_t prot, struct page **pages)
    {
    	int ret;
    
    	ret = vmap_page_range_noflush(start, end, prot, pages);
    	flush_cache_vmap(start, end);
    	return ret;
    }
    
    int is_vmalloc_or_module_addr(const void *x)
    {
    	/*
    	 * ARM, x86-64 and sparc64 put modules in a special place,
    	 * and fall back on vmalloc() if that fails. Others
    	 * just put it in the vmalloc space.
    	 */
    #if defined(CONFIG_MODULES) && defined(MODULES_VADDR)
    	unsigned long addr = (unsigned long)x;
    	if (addr >= MODULES_VADDR && addr < MODULES_END)
    		return 1;
    #endif
    	return is_vmalloc_addr(x);
    }
    
    /*
     * Walk a vmap address to the struct page it maps.
     */
    struct page *vmalloc_to_page(const void *vmalloc_addr)
    {
    	unsigned long addr = (unsigned long) vmalloc_addr;
    	struct page *page = NULL;
    	pgd_t *pgd = pgd_offset_k(addr);
    
    	/*
    	 * XXX we might need to change this if we add VIRTUAL_BUG_ON for
    	 * architectures that do not vmalloc module space
    	 */
    	VIRTUAL_BUG_ON(!is_vmalloc_or_module_addr(vmalloc_addr));
    
    	/*
    	 * Don't dereference bad PUD or PMD (below) entries. This will also
    	 * identify huge mappings, which we may encounter on architectures
    	 * that define CONFIG_HAVE_ARCH_HUGE_VMAP=y. Such regions will be
    	 * identified as vmalloc addresses by is_vmalloc_addr(), but are
    	 * not [unambiguously] associated with a struct page, so there is
    	 * no correct value to return for them.
    	 */
    	if (!pgd_none(*pgd)) {
    		pud_t *pud = pud_offset(pgd, addr);
    		WARN_ON_ONCE(pud_bad(*pud));
    		if (!pud_none(*pud) && !pud_bad(*pud)) {
    			pmd_t *pmd = pmd_offset(pud, addr);
    			WARN_ON_ONCE(pmd_bad(*pmd));
    			if (!pmd_none(*pmd) && !pmd_bad(*pmd)) {
    				pte_t *ptep, pte;
    
    				ptep = pte_offset_map(pmd, addr);
    				pte = *ptep;
    				if (pte_present(pte))
    					page = pte_page(pte);
    				pte_unmap(ptep);
    			}
    		}
    	}
    	return page;
    }
    EXPORT_SYMBOL(vmalloc_to_page);
    
    /*
     * Map a vmalloc()-space virtual address to the physical page frame number.
     */
    unsigned long vmalloc_to_pfn(const void *vmalloc_addr)
    {
    	return page_to_pfn(vmalloc_to_page(vmalloc_addr));
    }
    EXPORT_SYMBOL(vmalloc_to_pfn);
    
    
    /*** Global kva allocator ***/
    
    #define VM_VM_AREA	0x04
    
    static DEFINE_SPINLOCK(vmap_area_lock);
    /* Export for kexec only */
    LIST_HEAD(vmap_area_list);
    static LLIST_HEAD(vmap_purge_list);
    static struct rb_root vmap_area_root = RB_ROOT;
    
    /* The vmap cache globals are protected by vmap_area_lock */
    static struct rb_node *free_vmap_cache;
    static unsigned long cached_hole_size;
    static unsigned long cached_vstart;
    static unsigned long cached_align;
    
    static unsigned long vmap_area_pcpu_hole;
    
    static struct vmap_area *__find_vmap_area(unsigned long addr)
    {
    	struct rb_node *n = vmap_area_root.rb_node;
    
    	while (n) {
    		struct vmap_area *va;
    
    		va = rb_entry(n, struct vmap_area, rb_node);
    		if (addr < va->va_start)
    			n = n->rb_left;
    		else if (addr >= va->va_end)
    			n = n->rb_right;
    		else
    			return va;
    	}
    
    	return NULL;
    }
    
    static void __insert_vmap_area(struct vmap_area *va)
    {
    	struct rb_node **p = &vmap_area_root.rb_node;
    	struct rb_node *parent = NULL;
    	struct rb_node *tmp;
    
    	while (*p) {
    		struct vmap_area *tmp_va;
    
    		parent = *p;
    		tmp_va = rb_entry(parent, struct vmap_area, rb_node);
    		if (va->va_start < tmp_va->va_end)
    			p = &(*p)->rb_left;
    		else if (va->va_end > tmp_va->va_start)
    			p = &(*p)->rb_right;
    		else
    			BUG();
    	}
    
    	rb_link_node(&va->rb_node, parent, p);
    	rb_insert_color(&va->rb_node, &vmap_area_root);
    
    	/* address-sort this list */
    	tmp = rb_prev(&va->rb_node);
    	if (tmp) {
    		struct vmap_area *prev;
    		prev = rb_entry(tmp, struct vmap_area, rb_node);
    		list_add_rcu(&va->list, &prev->list);
    	} else
    		list_add_rcu(&va->list, &vmap_area_list);
    }
    
    static void purge_vmap_area_lazy(void);
    
    static BLOCKING_NOTIFIER_HEAD(vmap_notify_list);
    
    /*
     * Allocate a region of KVA of the specified size and alignment, within the
     * vstart and vend.
     */
    static struct vmap_area *alloc_vmap_area(unsigned long size,
    				unsigned long align,
    				unsigned long vstart, unsigned long vend,
    				int node, gfp_t gfp_mask)
    {
    	struct vmap_area *va;
    	struct rb_node *n;
    	unsigned long addr;
    	int purged = 0;
    	struct vmap_area *first;
    
    	BUG_ON(!size);
    	BUG_ON(offset_in_page(size));
    	BUG_ON(!is_power_of_2(align));
    
    	might_sleep_if(gfpflags_allow_blocking(gfp_mask));
    
    	va = kmalloc_node(sizeof(struct vmap_area),
    			gfp_mask & GFP_RECLAIM_MASK, node);
    	if (unlikely(!va))
    		return ERR_PTR(-ENOMEM);
    
    	/*
    	 * Only scan the relevant parts containing pointers to other objects
    	 * to avoid false negatives.
    	 */
    	kmemleak_scan_area(&va->rb_node, SIZE_MAX, gfp_mask & GFP_RECLAIM_MASK);
    
    retry:
    	spin_lock(&vmap_area_lock);
    	/*
    	 * Invalidate cache if we have more permissive parameters.
    	 * cached_hole_size notes the largest hole noticed _below_
    	 * the vmap_area cached in free_vmap_cache: if size fits
    	 * into that hole, we want to scan from vstart to reuse
    	 * the hole instead of allocating above free_vmap_cache.
    	 * Note that __free_vmap_area may update free_vmap_cache
    	 * without updating cached_hole_size or cached_align.
    	 */
    	if (!free_vmap_cache ||
    			size < cached_hole_size ||
    			vstart < cached_vstart ||
    			align < cached_align) {
    nocache:
    		cached_hole_size = 0;
    		free_vmap_cache = NULL;
    	}
    	/* record if we encounter less permissive parameters */
    	cached_vstart = vstart;
    	cached_align = align;
    
    	/* find starting point for our search */
    	if (free_vmap_cache) {
    		first = rb_entry(free_vmap_cache, struct vmap_area, rb_node);
    		addr = ALIGN(first->va_end, align);
    		if (addr < vstart)
    			goto nocache;
    		if (addr + size < addr)
    			goto overflow;
    
    	} else {
    		addr = ALIGN(vstart, align);
    		if (addr + size < addr)
    			goto overflow;
    
    		n = vmap_area_root.rb_node;
    		first = NULL;
    
    		while (n) {
    			struct vmap_area *tmp;
    			tmp = rb_entry(n, struct vmap_area, rb_node);
    			if (tmp->va_end >= addr) {
    				first = tmp;
    				if (tmp->va_start <= addr)
    					break;
    				n = n->rb_left;
    			} else
    				n = n->rb_right;
    		}
    
    		if (!first)
    			goto found;
    	}
    
    	/* from the starting point, walk areas until a suitable hole is found */
    	while (addr + size > first->va_start && addr + size <= vend) {
    		if (addr + cached_hole_size < first->va_start)
    			cached_hole_size = first->va_start - addr;
    		addr = ALIGN(first->va_end, align);
    		if (addr + size < addr)
    			goto overflow;
    
    		if (list_is_last(&first->list, &vmap_area_list))
    			goto found;
    
    		first = list_next_entry(first, list);
    	}
    
    found:
    	if (addr + size > vend)
    		goto overflow;
    
    	va->va_start = addr;
    	va->va_end = addr + size;
    	va->flags = 0;
    	__insert_vmap_area(va);
    	free_vmap_cache = &va->rb_node;
    	spin_unlock(&vmap_area_lock);
    
    	BUG_ON(!IS_ALIGNED(va->va_start, align));
    	BUG_ON(va->va_start < vstart);
    	BUG_ON(va->va_end > vend);
    
    	return va;
    
    overflow:
    	spin_unlock(&vmap_area_lock);
    	if (!purged) {
    		purge_vmap_area_lazy();
    		purged = 1;
    		goto retry;
    	}
    
    	if (gfpflags_allow_blocking(gfp_mask)) {
    		unsigned long freed = 0;
    		blocking_notifier_call_chain(&vmap_notify_list, 0, &freed);
    		if (freed > 0) {
    			purged = 0;
    			goto retry;
    		}
    	}
    
    	if (printk_ratelimit())
    		pr_warn("vmap allocation for size %lu failed: use vmalloc=<size> to increase size\n",
    			size);
    	kfree(va);
    	return ERR_PTR(-EBUSY);
    }
    
    int register_vmap_purge_notifier(struct notifier_block *nb)
    {
    	return blocking_notifier_chain_register(&vmap_notify_list, nb);
    }
    EXPORT_SYMBOL_GPL(register_vmap_purge_notifier);
    
    int unregister_vmap_purge_notifier(struct notifier_block *nb)
    {
    	return blocking_notifier_chain_unregister(&vmap_notify_list, nb);
    }
    EXPORT_SYMBOL_GPL(unregister_vmap_purge_notifier);
    
    static void __free_vmap_area(struct vmap_area *va)
    {
    	BUG_ON(RB_EMPTY_NODE(&va->rb_node));
    
    	if (free_vmap_cache) {
    		if (va->va_end < cached_vstart) {
    			free_vmap_cache = NULL;
    		} else {
    			struct vmap_area *cache;
    			cache = rb_entry(free_vmap_cache, struct vmap_area, rb_node);
    			if (va->va_start <= cache->va_start) {
    				free_vmap_cache = rb_prev(&va->rb_node);
    				/*
    				 * We don't try to update cached_hole_size or
    				 * cached_align, but it won't go very wrong.
    				 */
    			}
    		}
    	}
    	rb_erase(&va->rb_node, &vmap_area_root);
    	RB_CLEAR_NODE(&va->rb_node);
    	list_del_rcu(&va->list);
    
    	/*
    	 * Track the highest possible candidate for pcpu area
    	 * allocation.  Areas outside of vmalloc area can be returned
    	 * here too, consider only end addresses which fall inside
    	 * vmalloc area proper.
    	 */
    	if (va->va_end > VMALLOC_START && va->va_end <= VMALLOC_END)
    		vmap_area_pcpu_hole = max(vmap_area_pcpu_hole, va->va_end);
    
    	kfree_rcu(va, rcu_head);
    }
    
    /*
     * Free a region of KVA allocated by alloc_vmap_area
     */
    static void free_vmap_area(struct vmap_area *va)
    {
    	spin_lock(&vmap_area_lock);
    	__free_vmap_area(va);
    	spin_unlock(&vmap_area_lock);
    }
    
    /*
     * Clear the pagetable entries of a given vmap_area
     */
    static void unmap_vmap_area(struct vmap_area *va)
    {
    	vunmap_page_range(va->va_start, va->va_end);
    }
    
    static void vmap_debug_free_range(unsigned long start, unsigned long end)
    {
    	/*
    	 * Unmap page tables and force a TLB flush immediately if pagealloc
    	 * debugging is enabled.  This catches use after free bugs similarly to
    	 * those in linear kernel virtual address space after a page has been
    	 * freed.
    	 *
    	 * All the lazy freeing logic is still retained, in order to minimise
    	 * intrusiveness of this debugging feature.
    	 *
    	 * This is going to be *slow* (linear kernel virtual address debugging
    	 * doesn't do a broadcast TLB flush so it is a lot faster).
    	 */
    	if (debug_pagealloc_enabled()) {
    		vunmap_page_range(start, end);
    		flush_tlb_kernel_range(start, end);
    	}
    }
    
    /*
     * lazy_max_pages is the maximum amount of virtual address space we gather up
     * before attempting to purge with a TLB flush.
     *
     * There is a tradeoff here: a larger number will cover more kernel page tables
     * and take slightly longer to purge, but it will linearly reduce the number of
     * global TLB flushes that must be performed. It would seem natural to scale
     * this number up linearly with the number of CPUs (because vmapping activity
     * could also scale linearly with the number of CPUs), however it is likely
     * that in practice, workloads might be constrained in other ways that mean
     * vmap activity will not scale linearly with CPUs. Also, I want to be
     * conservative and not introduce a big latency on huge systems, so go with
     * a less aggressive log scale. It will still be an improvement over the old
     * code, and it will be simple to change the scale factor if we find that it
     * becomes a problem on bigger systems.
     */
    static unsigned long lazy_max_pages(void)
    {
    	unsigned int log;
    
    	log = fls(num_online_cpus());
    
    	return log * (32UL * 1024 * 1024 / PAGE_SIZE);
    }
    
    static atomic_t vmap_lazy_nr = ATOMIC_INIT(0);
    
    /* for per-CPU blocks */
    static void purge_fragmented_blocks_allcpus(void);
    
    /*
     * called before a call to iounmap() if the caller wants vm_area_struct's
     * immediately freed.
     */
    void set_iounmap_nonlazy(void)
    {
    	atomic_set(&vmap_lazy_nr, lazy_max_pages()+1);
    }
    
    /*
     * Purges all lazily-freed vmap areas.
     *
     * If sync is 0 then don't purge if there is already a purge in progress.
     * If force_flush is 1, then flush kernel TLBs between *start and *end even
     * if we found no lazy vmap areas to unmap (callers can use this to optimise
     * their own TLB flushing).
     * Returns with *start = min(*start, lowest purged address)
     *              *end = max(*end, highest purged address)
     */
    static void __purge_vmap_area_lazy(unsigned long *start, unsigned long *end,
    					int sync, int force_flush)
    {
    	static DEFINE_SPINLOCK(purge_lock);
    	struct llist_node *valist;
    	struct vmap_area *va;
    	struct vmap_area *n_va;
    	int nr = 0;
    
    	/*
    	 * If sync is 0 but force_flush is 1, we'll go sync anyway but callers
    	 * should not expect such behaviour. This just simplifies locking for
    	 * the case that isn't actually used at the moment anyway.
    	 */
    	if (!sync && !force_flush) {
    		if (!spin_trylock(&purge_lock))
    			return;
    	} else
    		spin_lock(&purge_lock);
    
    	if (sync)
    		purge_fragmented_blocks_allcpus();
    
    	valist = llist_del_all(&vmap_purge_list);
    	llist_for_each_entry(va, valist, purge_list) {
    		if (va->va_start < *start)
    			*start = va->va_start;
    		if (va->va_end > *end)
    			*end = va->va_end;
    		nr += (va->va_end - va->va_start) >> PAGE_SHIFT;
    	}
    
    	if (nr)
    		atomic_sub(nr, &vmap_lazy_nr);
    
    	if (nr || force_flush)
    		flush_tlb_kernel_range(*start, *end);
    
    	if (nr) {
    		spin_lock(&vmap_area_lock);
    		llist_for_each_entry_safe(va, n_va, valist, purge_list)
    			__free_vmap_area(va);
    		spin_unlock(&vmap_area_lock);
    	}
    	spin_unlock(&purge_lock);
    }
    
    /*
     * Kick off a purge of the outstanding lazy areas. Don't bother if somebody
     * is already purging.
     */
    static void try_purge_vmap_area_lazy(void)
    {
    	unsigned long start = ULONG_MAX, end = 0;
    
    	__purge_vmap_area_lazy(&start, &end, 0, 0);
    }
    
    /*
     * Kick off a purge of the outstanding lazy areas.
     */
    static void purge_vmap_area_lazy(void)
    {
    	unsigned long start = ULONG_MAX, end = 0;
    
    	__purge_vmap_area_lazy(&start, &end, 1, 0);
    }
    
    /*
     * Free a vmap area, caller ensuring that the area has been unmapped
     * and flush_cache_vunmap had been called for the correct range
     * previously.
     */
    static void free_vmap_area_noflush(struct vmap_area *va)
    {
    	int nr_lazy;
    
    	nr_lazy = atomic_add_return((va->va_end - va->va_start) >> PAGE_SHIFT,
    				    &vmap_lazy_nr);
    
    	/* After this point, we may free va at any time */
    	llist_add(&va->purge_list, &vmap_purge_list);
    
    	if (unlikely(nr_lazy > lazy_max_pages()))
    		try_purge_vmap_area_lazy();
    }
    
    /*
     * Free and unmap a vmap area, caller ensuring flush_cache_vunmap had been
     * called for the correct range previously.
     */
    static void free_unmap_vmap_area_noflush(struct vmap_area *va)
    {
    	unmap_vmap_area(va);
    	free_vmap_area_noflush(va);
    }
    
    /*
     * Free and unmap a vmap area
     */
    static void free_unmap_vmap_area(struct vmap_area *va)
    {
    	flush_cache_vunmap(va->va_start, va->va_end);
    	free_unmap_vmap_area_noflush(va);
    }
    
    static struct vmap_area *find_vmap_area(unsigned long addr)
    {
    	struct vmap_area *va;
    
    	spin_lock(&vmap_area_lock);
    	va = __find_vmap_area(addr);
    	spin_unlock(&vmap_area_lock);
    
    	return va;
    }
    
    static void free_unmap_vmap_area_addr(unsigned long addr)
    {
    	struct vmap_area *va;
    
    	va = find_vmap_area(addr);
    	BUG_ON(!va);
    	free_unmap_vmap_area(va);
    }
    
    
    /*** Per cpu kva allocator ***/
    
    /*
     * vmap space is limited especially on 32 bit architectures. Ensure there is
     * room for at least 16 percpu vmap blocks per CPU.
     */
    /*
     * If we had a constant VMALLOC_START and VMALLOC_END, we'd like to be able
     * to #define VMALLOC_SPACE		(VMALLOC_END-VMALLOC_START). Guess
     * instead (we just need a rough idea)
     */
    #if BITS_PER_LONG == 32
    #define VMALLOC_SPACE		(128UL*1024*1024)
    #else
    #define VMALLOC_SPACE		(128UL*1024*1024*1024)
    #endif
    
    #define VMALLOC_PAGES		(VMALLOC_SPACE / PAGE_SIZE)
    #define VMAP_MAX_ALLOC		BITS_PER_LONG	/* 256K with 4K pages */
    #define VMAP_BBMAP_BITS_MAX	1024	/* 4MB with 4K pages */
    #define VMAP_BBMAP_BITS_MIN	(VMAP_MAX_ALLOC*2)
    #define VMAP_MIN(x, y)		((x) < (y) ? (x) : (y)) /* can't use min() */
    #define VMAP_MAX(x, y)		((x) > (y) ? (x) : (y)) /* can't use max() */
    #define VMAP_BBMAP_BITS		\
    		VMAP_MIN(VMAP_BBMAP_BITS_MAX,	\
    		VMAP_MAX(VMAP_BBMAP_BITS_MIN,	\
    			VMALLOC_PAGES / roundup_pow_of_two(NR_CPUS) / 16))
    
    #define VMAP_BLOCK_SIZE		(VMAP_BBMAP_BITS * PAGE_SIZE)
    
    static bool vmap_initialized __read_mostly = false;
    
    struct vmap_block_queue {
    	spinlock_t lock;
    	struct list_head free;
    };
    
    struct vmap_block {
    	spinlock_t lock;
    	struct vmap_area *va;
    	unsigned long free, dirty;
    	unsigned long dirty_min, dirty_max; /*< dirty range */
    	struct list_head free_list;
    	struct rcu_head rcu_head;
    	struct list_head purge;
    };
    
    /* Queue of free and dirty vmap blocks, for allocation and flushing purposes */
    static DEFINE_PER_CPU(struct vmap_block_queue, vmap_block_queue);
    
    /*
     * Radix tree of vmap blocks, indexed by address, to quickly find a vmap block
     * in the free path. Could get rid of this if we change the API to return a
     * "cookie" from alloc, to be passed to free. But no big deal yet.
     */
    static DEFINE_SPINLOCK(vmap_block_tree_lock);
    static RADIX_TREE(vmap_block_tree, GFP_ATOMIC);
    
    /*
     * We should probably have a fallback mechanism to allocate virtual memory
     * out of partially filled vmap blocks. However vmap block sizing should be
     * fairly reasonable according to the vmalloc size, so it shouldn't be a
     * big problem.
     */
    
    static unsigned long addr_to_vb_idx(unsigned long addr)
    {
    	addr -= VMALLOC_START & ~(VMAP_BLOCK_SIZE-1);
    	addr /= VMAP_BLOCK_SIZE;
    	return addr;
    }
    
    static void *vmap_block_vaddr(unsigned long va_start, unsigned long pages_off)
    {
    	unsigned long addr;
    
    	addr = va_start + (pages_off << PAGE_SHIFT);
    	BUG_ON(addr_to_vb_idx(addr) != addr_to_vb_idx(va_start));
    	return (void *)addr;
    }
    
    /**
     * new_vmap_block - allocates new vmap_block and occupies 2^order pages in this
     *                  block. Of course pages number can't exceed VMAP_BBMAP_BITS
     * @order:    how many 2^order pages should be occupied in newly allocated block
     * @gfp_mask: flags for the page level allocator
     *
     * Returns: virtual address in a newly allocated block or ERR_PTR(-errno)
     */
    static void *new_vmap_block(unsigned int order, gfp_t gfp_mask)
    {
    	struct vmap_block_queue *vbq;
    	struct vmap_block *vb;
    	struct vmap_area *va;
    	unsigned long vb_idx;
    	int node, err;
    	void *vaddr;
    
    	node = numa_node_id();
    
    	vb = kmalloc_node(sizeof(struct vmap_block),
    			gfp_mask & GFP_RECLAIM_MASK, node);
    	if (unlikely(!vb))
    		return ERR_PTR(-ENOMEM);
    
    	va = alloc_vmap_area(VMAP_BLOCK_SIZE, VMAP_BLOCK_SIZE,
    					VMALLOC_START, VMALLOC_END,
    					node, gfp_mask);
    	if (IS_ERR(va)) {
    		kfree(vb);
    		return ERR_CAST(va);
    	}
    
    	err = radix_tree_preload(gfp_mask);
    	if (unlikely(err)) {
    		kfree(vb);
    		free_vmap_area(va);
    		return ERR_PTR(err);
    	}
    
    	vaddr = vmap_block_vaddr(va->va_start, 0);
    	spin_lock_init(&vb->lock);
    	vb->va = va;
    	/* At least something should be left free */
    	BUG_ON(VMAP_BBMAP_BITS <= (1UL << order));
    	vb->free = VMAP_BBMAP_BITS - (1UL << order);
    	vb->dirty = 0;
    	vb->dirty_min = VMAP_BBMAP_BITS;
    	vb->dirty_max = 0;
    	INIT_LIST_HEAD(&vb->free_list);
    
    	vb_idx = addr_to_vb_idx(va->va_start);
    	spin_lock(&vmap_block_tree_lock);
    	err = radix_tree_insert(&vmap_block_tree, vb_idx, vb);
    	spin_unlock(&vmap_block_tree_lock);
    	BUG_ON(err);
    	radix_tree_preload_end();
    
    	vbq = &get_cpu_var(vmap_block_queue);
    	spin_lock(&vbq->lock);
    	list_add_tail_rcu(&vb->free_list, &vbq->free);
    	spin_unlock(&vbq->lock);
    	put_cpu_var(vmap_block_queue);
    
    	return vaddr;
    }
    
    static void free_vmap_block(struct vmap_block *vb)
    {
    	struct vmap_block *tmp;
    	unsigned long vb_idx;
    
    	vb_idx = addr_to_vb_idx(vb->va->va_start);
    	spin_lock(&vmap_block_tree_lock);
    	tmp = radix_tree_delete(&vmap_block_tree, vb_idx);
    	spin_unlock(&vmap_block_tree_lock);
    	BUG_ON(tmp != vb);
    
    	free_vmap_area_noflush(vb->va);
    	kfree_rcu(vb, rcu_head);
    }
    
    static void purge_fragmented_blocks(int cpu)
    {
    	LIST_HEAD(purge);
    	struct vmap_block *vb;
    	struct vmap_block *n_vb;
    	struct vmap_block_queue *vbq = &per_cpu(vmap_block_queue, cpu);
    
    	rcu_read_lock();
    	list_for_each_entry_rcu(vb, &vbq->free, free_list) {
    
    		if (!(vb->free + vb->dirty == VMAP_BBMAP_BITS && vb->dirty != VMAP_BBMAP_BITS))
    			continue;
    
    		spin_lock(&vb->lock);
    		if (vb->free + vb->dirty == VMAP_BBMAP_BITS && vb->dirty != VMAP_BBMAP_BITS) {
    			vb->free = 0; /* prevent further allocs after releasing lock */
    			vb->dirty = VMAP_BBMAP_BITS; /* prevent purging it again */
    			vb->dirty_min = 0;
    			vb->dirty_max = VMAP_BBMAP_BITS;
    			spin_lock(&vbq->lock);
    			list_del_rcu(&vb->free_list);
    			spin_unlock(&vbq->lock);
    			spin_unlock(&vb->lock);
    			list_add_tail(&vb->purge, &purge);
    		} else
    			spin_unlock(&vb->lock);
    	}
    	rcu_read_unlock();
    
    	list_for_each_entry_safe(vb, n_vb, &purge, purge) {
    		list_del(&vb->purge);
    		free_vmap_block(vb);
    	}
    }
    
    static void purge_fragmented_blocks_allcpus(void)
    {
    	int cpu;
    
    	for_each_possible_cpu(cpu)
    		purge_fragmented_blocks(cpu);
    }
    
    static void *vb_alloc(unsigned long size, gfp_t gfp_mask)
    {
    	struct vmap_block_queue *vbq;
    	struct vmap_block *vb;
    	void *vaddr = NULL;
    	unsigned int order;
    
    	BUG_ON(offset_in_page(size));
    	BUG_ON(size > PAGE_SIZE*VMAP_MAX_ALLOC);
    	if (WARN_ON(size == 0)) {
    		/*
    		 * Allocating 0 bytes isn't what caller wants since
    		 * get_order(0) returns funny result. Just warn and terminate
    		 * early.
    		 */
    		return NULL;
    	}
    	order = get_order(size);
    
    	rcu_read_lock();
    	vbq = &get_cpu_var(vmap_block_queue);
    	list_for_each_entry_rcu(vb, &vbq->free, free_list) {
    		unsigned long pages_off;
    
    		spin_lock(&vb->lock);
    		if (vb->free < (1UL << order)) {
    			spin_unlock(&vb->lock);
    			continue;
    		}
    
    		pages_off = VMAP_BBMAP_BITS - vb->free;
    		vaddr = vmap_block_vaddr(vb->va->va_start, pages_off);
    		vb->free -= 1UL << order;