Blame view
mm/zsmalloc.c
28.7 KB
61989a80f staging: zsmalloc... |
1 2 3 4 |
/* * zsmalloc memory allocator * * Copyright (C) 2011 Nitin Gupta |
31fc00bb7 zsmalloc: add cop... |
5 |
* Copyright (C) 2012, 2013 Minchan Kim |
61989a80f staging: zsmalloc... |
6 7 8 9 10 11 12 |
* * This code is released using a dual license strategy: BSD/GPL * You can choose the license that better fits your requirements. * * Released under the terms of 3-clause BSD License * Released under the terms of GNU General Public License Version 2.0 */ |
2db51dae5 staging: zsmalloc... |
13 |
/* |
c3e3e88ad zsmalloc: add mor... |
14 15 16 17 18 19 20 |
* This allocator is designed for use with zram. Thus, the allocator is * supposed to work well under low memory conditions. In particular, it * never attempts higher order page allocation which is very likely to * fail under memory pressure. On the other hand, if we just use single * (0-order) pages, it would suffer from very high fragmentation -- * any object of size PAGE_SIZE/2 or larger would occupy an entire page. * This was one of the major issues with its predecessor (xvmalloc). |
2db51dae5 staging: zsmalloc... |
21 22 23 24 25 26 27 |
* * To overcome these issues, zsmalloc allocates a bunch of 0-order pages * and links them together using various 'struct page' fields. These linked * pages act as a single higher-order page i.e. an object can span 0-order * page boundaries. The code refers to these linked pages as a single entity * called zspage. * |
c3e3e88ad zsmalloc: add mor... |
28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 |
* For simplicity, zsmalloc can only allocate objects of size up to PAGE_SIZE * since this satisfies the requirements of all its current users (in the * worst case, page is incompressible and is thus stored "as-is" i.e. in * uncompressed form). For allocation requests larger than this size, failure * is returned (see zs_malloc). * * Additionally, zs_malloc() does not return a dereferenceable pointer. * Instead, it returns an opaque handle (unsigned long) which encodes actual * location of the allocated object. The reason for this indirection is that * zsmalloc does not keep zspages permanently mapped since that would cause * issues on 32-bit systems where the VA region for kernel space mappings * is very small. So, before using the allocating memory, the object has to * be mapped using zs_map_object() to get a usable pointer and subsequently * unmapped using zs_unmap_object(). * |
2db51dae5 staging: zsmalloc... |
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 |
* Following is how we use various fields and flags of underlying * struct page(s) to form a zspage. * * Usage of struct page fields: * page->first_page: points to the first component (0-order) page * page->index (union with page->freelist): offset of the first object * starting in this page. For the first page, this is * always 0, so we use this field (aka freelist) to point * to the first free object in zspage. * page->lru: links together all component pages (except the first page) * of a zspage * * For _first_ page only: * * page->private (union with page->first_page): refers to the * component page after the first page * page->freelist: points to the first free object in zspage. * Free objects are linked together using in-place * metadata. * page->objects: maximum number of objects we can store in this * zspage (class->zspage_order * PAGE_SIZE / class->size) * page->lru: links together first pages of various zspages. * Basically forming list of zspages in a fullness group. * page->mapping: class index and fullness group of the zspage * * Usage of struct page flags: * PG_private: identifies the first component page * PG_private2: identifies the last component page * */ |
61989a80f staging: zsmalloc... |
73 74 75 76 77 78 79 80 81 |
#ifdef CONFIG_ZSMALLOC_DEBUG #define DEBUG #endif #include <linux/module.h> #include <linux/kernel.h> #include <linux/bitops.h> #include <linux/errno.h> #include <linux/highmem.h> |
61989a80f staging: zsmalloc... |
82 83 84 85 86 87 |
#include <linux/string.h> #include <linux/slab.h> #include <asm/tlbflush.h> #include <asm/pgtable.h> #include <linux/cpumask.h> #include <linux/cpu.h> |
0cbb613fa staging: fix powe... |
88 |
#include <linux/vmalloc.h> |
c60369f01 staging: zsmalloc... |
89 |
#include <linux/hardirq.h> |
0959c63f1 zsmalloc: collaps... |
90 91 |
#include <linux/spinlock.h> #include <linux/types.h> |
bcf1647d0 zsmalloc: move it... |
92 |
#include <linux/zsmalloc.h> |
0959c63f1 zsmalloc: collaps... |
93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 |
/* * This must be power of 2 and greater than of equal to sizeof(link_free). * These two conditions ensure that any 'struct link_free' itself doesn't * span more than 1 page which avoids complex case of mapping 2 pages simply * to restore link_free pointer values. */ #define ZS_ALIGN 8 /* * A single 'zspage' is composed of up to 2^N discontiguous 0-order (single) * pages. ZS_MAX_ZSPAGE_ORDER defines upper limit on N. */ #define ZS_MAX_ZSPAGE_ORDER 2 #define ZS_MAX_PAGES_PER_ZSPAGE (_AC(1, UL) << ZS_MAX_ZSPAGE_ORDER) /* * Object location (<PFN>, <obj_idx>) is encoded as |
c3e3e88ad zsmalloc: add mor... |
111 |
* as single (unsigned long) handle value. |
0959c63f1 zsmalloc: collaps... |
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 |
* * Note that object index <obj_idx> is relative to system * page <PFN> it is stored in, so for each sub-page belonging * to a zspage, obj_idx starts with 0. * * This is made more complicated by various memory models and PAE. */ #ifndef MAX_PHYSMEM_BITS #ifdef CONFIG_HIGHMEM64G #define MAX_PHYSMEM_BITS 36 #else /* !CONFIG_HIGHMEM64G */ /* * If this definition of MAX_PHYSMEM_BITS is used, OBJ_INDEX_BITS will just * be PAGE_SHIFT */ #define MAX_PHYSMEM_BITS BITS_PER_LONG #endif #endif #define _PFN_BITS (MAX_PHYSMEM_BITS - PAGE_SHIFT) #define OBJ_INDEX_BITS (BITS_PER_LONG - _PFN_BITS) #define OBJ_INDEX_MASK ((_AC(1, UL) << OBJ_INDEX_BITS) - 1) #define MAX(a, b) ((a) >= (b) ? (a) : (b)) /* ZS_MIN_ALLOC_SIZE must be multiple of ZS_ALIGN */ #define ZS_MIN_ALLOC_SIZE \ MAX(32, (ZS_MAX_PAGES_PER_ZSPAGE << PAGE_SHIFT >> OBJ_INDEX_BITS)) #define ZS_MAX_ALLOC_SIZE PAGE_SIZE /* |
7eb52512a zsmalloc: fixup t... |
142 |
* On systems with 4K page size, this gives 255 size classes! There is a |
0959c63f1 zsmalloc: collaps... |
143 144 145 146 147 148 149 150 151 152 153 |
* trader-off here: * - Large number of size classes is potentially wasteful as free page are * spread across these classes * - Small number of size classes causes large internal fragmentation * - Probably its better to use specific size classes (empirically * determined). NOTE: all those class sizes must be set as multiple of * ZS_ALIGN to make sure link_free itself never has to span 2 pages. * * ZS_MIN_ALLOC_SIZE and ZS_SIZE_CLASS_DELTA must be multiple of ZS_ALIGN * (reason above) */ |
d662b8eba staging: zsmalloc... |
154 |
#define ZS_SIZE_CLASS_DELTA (PAGE_SIZE >> 8) |
0959c63f1 zsmalloc: collaps... |
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 |
#define ZS_SIZE_CLASSES ((ZS_MAX_ALLOC_SIZE - ZS_MIN_ALLOC_SIZE) / \ ZS_SIZE_CLASS_DELTA + 1) /* * We do not maintain any list for completely empty or full pages */ enum fullness_group { ZS_ALMOST_FULL, ZS_ALMOST_EMPTY, _ZS_NR_FULLNESS_GROUPS, ZS_EMPTY, ZS_FULL }; /* * We assign a page to ZS_ALMOST_EMPTY fullness group when: * n <= N / f, where * n = number of allocated objects * N = total number of objects zspage can store * f = 1/fullness_threshold_frac * * Similarly, we assign zspage to: * ZS_ALMOST_FULL when n > N / f * ZS_EMPTY when n == 0 * ZS_FULL when n == N * * (see: fix_fullness_group()) */ static const int fullness_threshold_frac = 4; struct size_class { /* * Size of objects stored in this class. Must be multiple * of ZS_ALIGN. */ int size; unsigned int index; /* Number of PAGE_SIZE sized pages to combine to form a 'zspage' */ int pages_per_zspage; spinlock_t lock; /* stats */ u64 pages_allocated; struct page *fullness_list[_ZS_NR_FULLNESS_GROUPS]; }; /* * Placed within free objects to form a singly linked list. * For every zspage, first_page->freelist gives head of this list. * * This must be power of 2 and less than or equal to ZS_ALIGN */ struct link_free { /* Handle of next free chunk (encodes <PFN, obj_idx>) */ void *next; }; struct zs_pool { struct size_class size_class[ZS_SIZE_CLASSES]; gfp_t flags; /* allocation flags used when growing pool */ |
0959c63f1 zsmalloc: collaps... |
220 |
}; |
61989a80f staging: zsmalloc... |
221 222 223 224 225 226 227 228 229 |
/* * A zspage's class index and fullness group * are encoded in its (first)page->mapping */ #define CLASS_IDX_BITS 28 #define FULLNESS_BITS 4 #define CLASS_IDX_MASK ((1 << CLASS_IDX_BITS) - 1) #define FULLNESS_MASK ((1 << FULLNESS_BITS) - 1) |
f553646a6 staging: zsmalloc... |
230 |
struct mapping_area { |
1b945aeef zsmalloc: add Kco... |
231 |
#ifdef CONFIG_PGTABLE_MAPPING |
f553646a6 staging: zsmalloc... |
232 233 234 235 236 237 238 |
struct vm_struct *vm; /* vm area for mapping object that span pages */ #else char *vm_buf; /* copy buffer for objects that span pages */ #endif char *vm_addr; /* address of kmap_atomic()'ed pages */ enum zs_mapmode vm_mm; /* mapping mode */ }; |
61989a80f staging: zsmalloc... |
239 240 241 242 243 |
/* per-cpu VM mapping areas for zspage accesses that cross page boundaries */ static DEFINE_PER_CPU(struct mapping_area, zs_map_area); static int is_first_page(struct page *page) { |
a27545bf0 zsmalloc: use Pag... |
244 |
return PagePrivate(page); |
61989a80f staging: zsmalloc... |
245 246 247 248 |
} static int is_last_page(struct page *page) { |
a27545bf0 zsmalloc: use Pag... |
249 |
return PagePrivate2(page); |
61989a80f staging: zsmalloc... |
250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 |
} static void get_zspage_mapping(struct page *page, unsigned int *class_idx, enum fullness_group *fullness) { unsigned long m; BUG_ON(!is_first_page(page)); m = (unsigned long)page->mapping; *fullness = m & FULLNESS_MASK; *class_idx = (m >> FULLNESS_BITS) & CLASS_IDX_MASK; } static void set_zspage_mapping(struct page *page, unsigned int class_idx, enum fullness_group fullness) { unsigned long m; BUG_ON(!is_first_page(page)); m = ((class_idx & CLASS_IDX_MASK) << FULLNESS_BITS) | (fullness & FULLNESS_MASK); page->mapping = (struct address_space *)m; } |
c3e3e88ad zsmalloc: add mor... |
273 274 275 276 277 278 279 |
/* * zsmalloc divides the pool into various size classes where each * class maintains a list of zspages where each zspage is divided * into equal sized chunks. Each allocation falls into one of these * classes depending on its size. This function returns index of the * size class which has chunk size big enough to hold the give size. */ |
61989a80f staging: zsmalloc... |
280 281 282 283 284 285 286 287 288 289 |
static int get_size_class_index(int size) { int idx = 0; if (likely(size > ZS_MIN_ALLOC_SIZE)) idx = DIV_ROUND_UP(size - ZS_MIN_ALLOC_SIZE, ZS_SIZE_CLASS_DELTA); return idx; } |
c3e3e88ad zsmalloc: add mor... |
290 291 292 293 294 295 296 |
/* * For each size class, zspages are divided into different groups * depending on how "full" they are. This was done so that we could * easily find empty or nearly empty zspages when we try to shrink * the pool (not yet implemented). This function returns fullness * status of the given page. */ |
61989a80f staging: zsmalloc... |
297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 |
static enum fullness_group get_fullness_group(struct page *page) { int inuse, max_objects; enum fullness_group fg; BUG_ON(!is_first_page(page)); inuse = page->inuse; max_objects = page->objects; if (inuse == 0) fg = ZS_EMPTY; else if (inuse == max_objects) fg = ZS_FULL; else if (inuse <= max_objects / fullness_threshold_frac) fg = ZS_ALMOST_EMPTY; else fg = ZS_ALMOST_FULL; return fg; } |
c3e3e88ad zsmalloc: add mor... |
317 318 319 320 321 322 |
/* * Each size class maintains various freelists and zspages are assigned * to one of these freelists based on the number of live objects they * have. This functions inserts the given zspage into the freelist * identified by <class, fullness_group>. */ |
61989a80f staging: zsmalloc... |
323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 |
static void insert_zspage(struct page *page, struct size_class *class, enum fullness_group fullness) { struct page **head; BUG_ON(!is_first_page(page)); if (fullness >= _ZS_NR_FULLNESS_GROUPS) return; head = &class->fullness_list[fullness]; if (*head) list_add_tail(&page->lru, &(*head)->lru); *head = page; } |
c3e3e88ad zsmalloc: add mor... |
339 340 341 342 |
/* * This function removes the given zspage from the freelist identified * by <class, fullness_group>. */ |
61989a80f staging: zsmalloc... |
343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 |
static void remove_zspage(struct page *page, struct size_class *class, enum fullness_group fullness) { struct page **head; BUG_ON(!is_first_page(page)); if (fullness >= _ZS_NR_FULLNESS_GROUPS) return; head = &class->fullness_list[fullness]; BUG_ON(!*head); if (list_empty(&(*head)->lru)) *head = NULL; else if (*head == page) *head = (struct page *)list_entry((*head)->lru.next, struct page, lru); list_del_init(&page->lru); } |
c3e3e88ad zsmalloc: add mor... |
363 364 365 366 367 368 369 370 371 |
/* * Each size class maintains zspages in different fullness groups depending * on the number of live objects they contain. When allocating or freeing * objects, the fullness status of the page can change, say, from ALMOST_FULL * to ALMOST_EMPTY when freeing an object. This function checks if such * a status change has occurred for the given page and accordingly moves the * page from the freelist of the old fullness group to that of the new * fullness group. */ |
61989a80f staging: zsmalloc... |
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 |
static enum fullness_group fix_fullness_group(struct zs_pool *pool, struct page *page) { int class_idx; struct size_class *class; enum fullness_group currfg, newfg; BUG_ON(!is_first_page(page)); get_zspage_mapping(page, &class_idx, &currfg); newfg = get_fullness_group(page); if (newfg == currfg) goto out; class = &pool->size_class[class_idx]; remove_zspage(page, class, currfg); insert_zspage(page, class, newfg); set_zspage_mapping(page, class_idx, newfg); out: return newfg; } /* * We have to decide on how many pages to link together * to form a zspage for each size class. This is important * to reduce wastage due to unusable space left at end of * each zspage which is given as: * wastage = Zp - Zp % size_class * where Zp = zspage size = k * PAGE_SIZE where k = 1, 2, ... * * For example, for size class of 3/8 * PAGE_SIZE, we should * link together 3 PAGE_SIZE sized pages to form a zspage * since then we can perfectly fit in 8 such objects. */ |
2e3b61547 staging: zsmalloc... |
407 |
static int get_pages_per_zspage(int class_size) |
61989a80f staging: zsmalloc... |
408 409 410 411 |
{ int i, max_usedpc = 0; /* zspage order which gives maximum used size per KB */ int max_usedpc_order = 1; |
84d4faaba staging: zsmalloc... |
412 |
for (i = 1; i <= ZS_MAX_PAGES_PER_ZSPAGE; i++) { |
61989a80f staging: zsmalloc... |
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 |
int zspage_size; int waste, usedpc; zspage_size = i * PAGE_SIZE; waste = zspage_size % class_size; usedpc = (zspage_size - waste) * 100 / zspage_size; if (usedpc > max_usedpc) { max_usedpc = usedpc; max_usedpc_order = i; } } return max_usedpc_order; } /* * A single 'zspage' is composed of many system pages which are * linked together using fields in struct page. This function finds * the first/head page, given any component page of a zspage. */ static struct page *get_first_page(struct page *page) { if (is_first_page(page)) return page; else return page->first_page; } static struct page *get_next_page(struct page *page) { struct page *next; if (is_last_page(page)) next = NULL; else if (is_first_page(page)) |
e842b976a staging: zsmalloc... |
449 |
next = (struct page *)page_private(page); |
61989a80f staging: zsmalloc... |
450 451 452 453 454 |
else next = list_entry(page->lru.next, struct page, lru); return next; } |
67296874e staging: zsmalloc... |
455 456 457 458 459 460 |
/* * Encode <page, obj_idx> as a single handle value. * On hardware platforms with physical memory starting at 0x0 the pfn * could be 0 so we ensure that the handle will never be 0 by adjusting the * encoded obj_idx value before encoding. */ |
61989a80f staging: zsmalloc... |
461 462 463 464 465 466 467 468 469 470 |
static void *obj_location_to_handle(struct page *page, unsigned long obj_idx) { unsigned long handle; if (!page) { BUG_ON(obj_idx); return NULL; } handle = page_to_pfn(page) << OBJ_INDEX_BITS; |
67296874e staging: zsmalloc... |
471 |
handle |= ((obj_idx + 1) & OBJ_INDEX_MASK); |
61989a80f staging: zsmalloc... |
472 473 474 |
return (void *)handle; } |
67296874e staging: zsmalloc... |
475 476 477 478 479 |
/* * Decode <page, obj_idx> pair from the given object handle. We adjust the * decoded obj_idx back to its original value since it was adjusted in * obj_location_to_handle(). */ |
c23443483 staging: zsmalloc... |
480 |
static void obj_handle_to_location(unsigned long handle, struct page **page, |
61989a80f staging: zsmalloc... |
481 482 |
unsigned long *obj_idx) { |
c23443483 staging: zsmalloc... |
483 |
*page = pfn_to_page(handle >> OBJ_INDEX_BITS); |
67296874e staging: zsmalloc... |
484 |
*obj_idx = (handle & OBJ_INDEX_MASK) - 1; |
61989a80f staging: zsmalloc... |
485 486 487 488 489 490 491 492 493 494 495 496 |
} static unsigned long obj_idx_to_offset(struct page *page, unsigned long obj_idx, int class_size) { unsigned long off = 0; if (!is_first_page(page)) off = page->index; return off + obj_idx * class_size; } |
f4477e90b staging: zsmalloc... |
497 498 499 500 501 502 503 |
static void reset_page(struct page *page) { clear_bit(PG_private, &page->flags); clear_bit(PG_private_2, &page->flags); set_page_private(page, 0); page->mapping = NULL; page->freelist = NULL; |
22b751c3d mm: rename page s... |
504 |
page_mapcount_reset(page); |
f4477e90b staging: zsmalloc... |
505 |
} |
61989a80f staging: zsmalloc... |
506 507 |
static void free_zspage(struct page *first_page) { |
f4477e90b staging: zsmalloc... |
508 |
struct page *nextp, *tmp, *head_extra; |
61989a80f staging: zsmalloc... |
509 510 511 |
BUG_ON(!is_first_page(first_page)); BUG_ON(first_page->inuse); |
f4477e90b staging: zsmalloc... |
512 |
head_extra = (struct page *)page_private(first_page); |
61989a80f staging: zsmalloc... |
513 |
|
f4477e90b staging: zsmalloc... |
514 |
reset_page(first_page); |
61989a80f staging: zsmalloc... |
515 516 517 |
__free_page(first_page); /* zspage with only 1 system page */ |
f4477e90b staging: zsmalloc... |
518 |
if (!head_extra) |
61989a80f staging: zsmalloc... |
519 |
return; |
f4477e90b staging: zsmalloc... |
520 |
list_for_each_entry_safe(nextp, tmp, &head_extra->lru, lru) { |
61989a80f staging: zsmalloc... |
521 |
list_del(&nextp->lru); |
f4477e90b staging: zsmalloc... |
522 |
reset_page(nextp); |
61989a80f staging: zsmalloc... |
523 524 |
__free_page(nextp); } |
f4477e90b staging: zsmalloc... |
525 526 |
reset_page(head_extra); __free_page(head_extra); |
61989a80f staging: zsmalloc... |
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 |
} /* Initialize a newly allocated zspage */ static void init_zspage(struct page *first_page, struct size_class *class) { unsigned long off = 0; struct page *page = first_page; BUG_ON(!is_first_page(first_page)); while (page) { struct page *next_page; struct link_free *link; unsigned int i, objs_on_page; /* * page->index stores offset of first object starting * in the page. For the first page, this is always 0, * so we use first_page->index (aka ->freelist) to store * head of corresponding zspage's freelist. */ if (page != first_page) page->index = off; link = (struct link_free *)kmap_atomic(page) + off / sizeof(*link); objs_on_page = (PAGE_SIZE - off) / class->size; for (i = 1; i <= objs_on_page; i++) { off += class->size; if (off < PAGE_SIZE) { link->next = obj_location_to_handle(page, i); link += class->size / sizeof(*link); } } /* * We now come to the last (full or partial) object on this * page, which must point to the first object on the next * page (if present) */ next_page = get_next_page(page); link->next = obj_location_to_handle(next_page, 0); kunmap_atomic(link); page = next_page; off = (off + class->size) % PAGE_SIZE; } } /* * Allocate a zspage for the given size class */ static struct page *alloc_zspage(struct size_class *class, gfp_t flags) { int i, error; |
b4b700c5a staging: zsmalloc... |
581 |
struct page *first_page = NULL, *uninitialized_var(prev_page); |
61989a80f staging: zsmalloc... |
582 583 584 585 586 587 588 589 590 591 592 593 594 |
/* * Allocate individual pages and link them together as: * 1. first page->private = first sub-page * 2. all sub-pages are linked together using page->lru * 3. each sub-page is linked to the first page using page->first_page * * For each size class, First/Head pages are linked together using * page->lru. Also, we set PG_private to identify the first page * (i.e. no other sub-page has this flag set) and PG_private_2 to * identify the last page. */ error = -ENOMEM; |
2e3b61547 staging: zsmalloc... |
595 |
for (i = 0; i < class->pages_per_zspage; i++) { |
b4b700c5a staging: zsmalloc... |
596 |
struct page *page; |
61989a80f staging: zsmalloc... |
597 598 599 600 601 602 603 |
page = alloc_page(flags); if (!page) goto cleanup; INIT_LIST_HEAD(&page->lru); if (i == 0) { /* first page */ |
a27545bf0 zsmalloc: use Pag... |
604 |
SetPagePrivate(page); |
61989a80f staging: zsmalloc... |
605 606 607 608 609 |
set_page_private(page, 0); first_page = page; first_page->inuse = 0; } if (i == 1) |
e842b976a staging: zsmalloc... |
610 |
set_page_private(first_page, (unsigned long)page); |
61989a80f staging: zsmalloc... |
611 612 613 614 |
if (i >= 1) page->first_page = first_page; if (i >= 2) list_add(&page->lru, &prev_page->lru); |
2e3b61547 staging: zsmalloc... |
615 |
if (i == class->pages_per_zspage - 1) /* last page */ |
a27545bf0 zsmalloc: use Pag... |
616 |
SetPagePrivate2(page); |
61989a80f staging: zsmalloc... |
617 618 619 620 621 622 623 |
prev_page = page; } init_zspage(first_page, class); first_page->freelist = obj_location_to_handle(first_page, 0); /* Maximum number of objects we can store in this zspage */ |
2e3b61547 staging: zsmalloc... |
624 |
first_page->objects = class->pages_per_zspage * PAGE_SIZE / class->size; |
61989a80f staging: zsmalloc... |
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 |
error = 0; /* Success */ cleanup: if (unlikely(error) && first_page) { free_zspage(first_page); first_page = NULL; } return first_page; } static struct page *find_get_zspage(struct size_class *class) { int i; struct page *page; for (i = 0; i < _ZS_NR_FULLNESS_GROUPS; i++) { page = class->fullness_list[i]; if (page) break; } return page; } |
1b945aeef zsmalloc: add Kco... |
650 |
#ifdef CONFIG_PGTABLE_MAPPING |
f553646a6 staging: zsmalloc... |
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 |
static inline int __zs_cpu_up(struct mapping_area *area) { /* * Make sure we don't leak memory if a cpu UP notification * and zs_init() race and both call zs_cpu_up() on the same cpu */ if (area->vm) return 0; area->vm = alloc_vm_area(PAGE_SIZE * 2, NULL); if (!area->vm) return -ENOMEM; return 0; } static inline void __zs_cpu_down(struct mapping_area *area) { if (area->vm) free_vm_area(area->vm); area->vm = NULL; } static inline void *__zs_map_object(struct mapping_area *area, struct page *pages[2], int off, int size) { BUG_ON(map_vm_area(area->vm, PAGE_KERNEL, &pages)); area->vm_addr = area->vm->addr; return area->vm_addr + off; } static inline void __zs_unmap_object(struct mapping_area *area, struct page *pages[2], int off, int size) { unsigned long addr = (unsigned long)area->vm_addr; |
f553646a6 staging: zsmalloc... |
684 |
|
d95abbbb2 staging: zsmalloc... |
685 |
unmap_kernel_range(addr, PAGE_SIZE * 2); |
f553646a6 staging: zsmalloc... |
686 |
} |
1b945aeef zsmalloc: add Kco... |
687 |
#else /* CONFIG_PGTABLE_MAPPING */ |
f553646a6 staging: zsmalloc... |
688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 |
static inline int __zs_cpu_up(struct mapping_area *area) { /* * Make sure we don't leak memory if a cpu UP notification * and zs_init() race and both call zs_cpu_up() on the same cpu */ if (area->vm_buf) return 0; area->vm_buf = (char *)__get_free_page(GFP_KERNEL); if (!area->vm_buf) return -ENOMEM; return 0; } static inline void __zs_cpu_down(struct mapping_area *area) { if (area->vm_buf) free_page((unsigned long)area->vm_buf); area->vm_buf = NULL; } static void *__zs_map_object(struct mapping_area *area, struct page *pages[2], int off, int size) |
5f601902c staging: zsmalloc... |
712 |
{ |
5f601902c staging: zsmalloc... |
713 714 |
int sizes[2]; void *addr; |
f553646a6 staging: zsmalloc... |
715 |
char *buf = area->vm_buf; |
5f601902c staging: zsmalloc... |
716 |
|
f553646a6 staging: zsmalloc... |
717 718 719 720 721 722 |
/* disable page faults to match kmap_atomic() return conditions */ pagefault_disable(); /* no read fastpath */ if (area->vm_mm == ZS_MM_WO) goto out; |
5f601902c staging: zsmalloc... |
723 724 725 |
sizes[0] = PAGE_SIZE - off; sizes[1] = size - sizes[0]; |
5f601902c staging: zsmalloc... |
726 727 728 729 730 731 732 |
/* copy object to per-cpu buffer */ addr = kmap_atomic(pages[0]); memcpy(buf, addr + off, sizes[0]); kunmap_atomic(addr); addr = kmap_atomic(pages[1]); memcpy(buf + sizes[0], addr, sizes[1]); kunmap_atomic(addr); |
f553646a6 staging: zsmalloc... |
733 734 |
out: return area->vm_buf; |
5f601902c staging: zsmalloc... |
735 |
} |
f553646a6 staging: zsmalloc... |
736 737 |
static void __zs_unmap_object(struct mapping_area *area, struct page *pages[2], int off, int size) |
5f601902c staging: zsmalloc... |
738 |
{ |
5f601902c staging: zsmalloc... |
739 740 |
int sizes[2]; void *addr; |
f553646a6 staging: zsmalloc... |
741 |
char *buf = area->vm_buf; |
5f601902c staging: zsmalloc... |
742 |
|
f553646a6 staging: zsmalloc... |
743 744 745 |
/* no write fastpath */ if (area->vm_mm == ZS_MM_RO) goto out; |
5f601902c staging: zsmalloc... |
746 747 748 749 750 751 752 753 754 755 756 |
sizes[0] = PAGE_SIZE - off; sizes[1] = size - sizes[0]; /* copy per-cpu buffer to object */ addr = kmap_atomic(pages[0]); memcpy(addr + off, buf, sizes[0]); kunmap_atomic(addr); addr = kmap_atomic(pages[1]); memcpy(addr, buf + sizes[0], sizes[1]); kunmap_atomic(addr); |
f553646a6 staging: zsmalloc... |
757 758 759 760 |
out: /* enable page faults to match kunmap_atomic() return conditions */ pagefault_enable(); |
5f601902c staging: zsmalloc... |
761 |
} |
61989a80f staging: zsmalloc... |
762 |
|
1b945aeef zsmalloc: add Kco... |
763 |
#endif /* CONFIG_PGTABLE_MAPPING */ |
f553646a6 staging: zsmalloc... |
764 |
|
61989a80f staging: zsmalloc... |
765 766 767 |
static int zs_cpu_notifier(struct notifier_block *nb, unsigned long action, void *pcpu) { |
f553646a6 staging: zsmalloc... |
768 |
int ret, cpu = (long)pcpu; |
61989a80f staging: zsmalloc... |
769 770 771 772 773 |
struct mapping_area *area; switch (action) { case CPU_UP_PREPARE: area = &per_cpu(zs_map_area, cpu); |
f553646a6 staging: zsmalloc... |
774 775 776 |
ret = __zs_cpu_up(area); if (ret) return notifier_from_errno(ret); |
61989a80f staging: zsmalloc... |
777 778 779 780 |
break; case CPU_DEAD: case CPU_UP_CANCELED: area = &per_cpu(zs_map_area, cpu); |
f553646a6 staging: zsmalloc... |
781 |
__zs_cpu_down(area); |
61989a80f staging: zsmalloc... |
782 783 784 785 786 787 788 789 790 791 792 793 794 |
break; } return NOTIFY_OK; } static struct notifier_block zs_cpu_nb = { .notifier_call = zs_cpu_notifier }; static void zs_exit(void) { int cpu; |
f0e71fcd0 zsmalloc: Fix CPU... |
795 |
cpu_notifier_register_begin(); |
61989a80f staging: zsmalloc... |
796 797 |
for_each_online_cpu(cpu) zs_cpu_notifier(NULL, CPU_DEAD, (void *)(long)cpu); |
f0e71fcd0 zsmalloc: Fix CPU... |
798 799 800 |
__unregister_cpu_notifier(&zs_cpu_nb); cpu_notifier_register_done(); |
61989a80f staging: zsmalloc... |
801 802 803 804 805 |
} static int zs_init(void) { int cpu, ret; |
f0e71fcd0 zsmalloc: Fix CPU... |
806 807 808 |
cpu_notifier_register_begin(); __register_cpu_notifier(&zs_cpu_nb); |
61989a80f staging: zsmalloc... |
809 810 |
for_each_online_cpu(cpu) { ret = zs_cpu_notifier(NULL, CPU_UP_PREPARE, (void *)(long)cpu); |
f0e71fcd0 zsmalloc: Fix CPU... |
811 812 |
if (notifier_to_errno(ret)) { cpu_notifier_register_done(); |
61989a80f staging: zsmalloc... |
813 |
goto fail; |
f0e71fcd0 zsmalloc: Fix CPU... |
814 |
} |
61989a80f staging: zsmalloc... |
815 |
} |
f0e71fcd0 zsmalloc: Fix CPU... |
816 817 |
cpu_notifier_register_done(); |
61989a80f staging: zsmalloc... |
818 819 820 821 822 |
return 0; fail: zs_exit(); return notifier_to_errno(ret); } |
4bbc0bc06 staging: zsmalloc... |
823 824 |
/** * zs_create_pool - Creates an allocation pool to work from. |
0d145a501 staging: zsmalloc... |
825 |
* @flags: allocation flags used to allocate pool metadata |
4bbc0bc06 staging: zsmalloc... |
826 827 828 829 830 831 832 |
* * This function must be called before anything when using * the zsmalloc allocator. * * On success, a pointer to the newly created pool is returned, * otherwise NULL. */ |
0d145a501 staging: zsmalloc... |
833 |
struct zs_pool *zs_create_pool(gfp_t flags) |
61989a80f staging: zsmalloc... |
834 |
{ |
069f101fa staging: zsmalloc... |
835 |
int i, ovhd_size; |
61989a80f staging: zsmalloc... |
836 |
struct zs_pool *pool; |
61989a80f staging: zsmalloc... |
837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 |
ovhd_size = roundup(sizeof(*pool), PAGE_SIZE); pool = kzalloc(ovhd_size, GFP_KERNEL); if (!pool) return NULL; for (i = 0; i < ZS_SIZE_CLASSES; i++) { int size; struct size_class *class; size = ZS_MIN_ALLOC_SIZE + i * ZS_SIZE_CLASS_DELTA; if (size > ZS_MAX_ALLOC_SIZE) size = ZS_MAX_ALLOC_SIZE; class = &pool->size_class[i]; class->size = size; class->index = i; spin_lock_init(&class->lock); |
2e3b61547 staging: zsmalloc... |
854 |
class->pages_per_zspage = get_pages_per_zspage(size); |
61989a80f staging: zsmalloc... |
855 856 |
} |
61989a80f staging: zsmalloc... |
857 |
pool->flags = flags; |
61989a80f staging: zsmalloc... |
858 |
|
61989a80f staging: zsmalloc... |
859 860 861 862 863 864 865 866 867 868 869 870 871 872 |
return pool; } EXPORT_SYMBOL_GPL(zs_create_pool); void zs_destroy_pool(struct zs_pool *pool) { int i; for (i = 0; i < ZS_SIZE_CLASSES; i++) { int fg; struct size_class *class = &pool->size_class[i]; for (fg = 0; fg < _ZS_NR_FULLNESS_GROUPS; fg++) { if (class->fullness_list[fg]) { |
93ad5ab50 Staging: Fixes st... |
873 874 |
pr_info("Freeing non-empty class with size %db, fullness group %d ", |
61989a80f staging: zsmalloc... |
875 876 877 878 879 880 881 882 883 884 885 886 |
class->size, fg); } } } kfree(pool); } EXPORT_SYMBOL_GPL(zs_destroy_pool); /** * zs_malloc - Allocate block of given size from pool. * @pool: pool to allocate from * @size: size of block to allocate |
61989a80f staging: zsmalloc... |
887 |
* |
00a61d861 staging: zsmalloc... |
888 |
* On success, handle to the allocated object is returned, |
c23443483 staging: zsmalloc... |
889 |
* otherwise 0. |
61989a80f staging: zsmalloc... |
890 891 |
* Allocation requests with size > ZS_MAX_ALLOC_SIZE will fail. */ |
c23443483 staging: zsmalloc... |
892 |
unsigned long zs_malloc(struct zs_pool *pool, size_t size) |
61989a80f staging: zsmalloc... |
893 |
{ |
c23443483 staging: zsmalloc... |
894 |
unsigned long obj; |
61989a80f staging: zsmalloc... |
895 896 897 898 899 900 901 902 |
struct link_free *link; int class_idx; struct size_class *class; struct page *first_page, *m_page; unsigned long m_objidx, m_offset; if (unlikely(!size || size > ZS_MAX_ALLOC_SIZE)) |
c23443483 staging: zsmalloc... |
903 |
return 0; |
61989a80f staging: zsmalloc... |
904 905 906 907 908 909 910 911 912 913 914 915 |
class_idx = get_size_class_index(size); class = &pool->size_class[class_idx]; BUG_ON(class_idx != class->index); spin_lock(&class->lock); first_page = find_get_zspage(class); if (!first_page) { spin_unlock(&class->lock); first_page = alloc_zspage(class, pool->flags); if (unlikely(!first_page)) |
c23443483 staging: zsmalloc... |
916 |
return 0; |
61989a80f staging: zsmalloc... |
917 918 919 |
set_zspage_mapping(first_page, class->index, ZS_EMPTY); spin_lock(&class->lock); |
2e3b61547 staging: zsmalloc... |
920 |
class->pages_allocated += class->pages_per_zspage; |
61989a80f staging: zsmalloc... |
921 |
} |
c23443483 staging: zsmalloc... |
922 |
obj = (unsigned long)first_page->freelist; |
61989a80f staging: zsmalloc... |
923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 |
obj_handle_to_location(obj, &m_page, &m_objidx); m_offset = obj_idx_to_offset(m_page, m_objidx, class->size); link = (struct link_free *)kmap_atomic(m_page) + m_offset / sizeof(*link); first_page->freelist = link->next; memset(link, POISON_INUSE, sizeof(*link)); kunmap_atomic(link); first_page->inuse++; /* Now move the zspage to another fullness group, if required */ fix_fullness_group(pool, first_page); spin_unlock(&class->lock); return obj; } EXPORT_SYMBOL_GPL(zs_malloc); |
c23443483 staging: zsmalloc... |
940 |
void zs_free(struct zs_pool *pool, unsigned long obj) |
61989a80f staging: zsmalloc... |
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 |
{ struct link_free *link; struct page *first_page, *f_page; unsigned long f_objidx, f_offset; int class_idx; struct size_class *class; enum fullness_group fullness; if (unlikely(!obj)) return; obj_handle_to_location(obj, &f_page, &f_objidx); first_page = get_first_page(f_page); get_zspage_mapping(first_page, &class_idx, &fullness); class = &pool->size_class[class_idx]; f_offset = obj_idx_to_offset(f_page, f_objidx, class->size); spin_lock(&class->lock); /* Insert this object in containing zspage's freelist */ link = (struct link_free *)((unsigned char *)kmap_atomic(f_page) + f_offset); link->next = first_page->freelist; kunmap_atomic(link); |
c23443483 staging: zsmalloc... |
967 |
first_page->freelist = (void *)obj; |
61989a80f staging: zsmalloc... |
968 969 970 971 972 |
first_page->inuse--; fullness = fix_fullness_group(pool, first_page); if (fullness == ZS_EMPTY) |
2e3b61547 staging: zsmalloc... |
973 |
class->pages_allocated -= class->pages_per_zspage; |
61989a80f staging: zsmalloc... |
974 975 976 977 978 979 980 |
spin_unlock(&class->lock); if (fullness == ZS_EMPTY) free_zspage(first_page); } EXPORT_SYMBOL_GPL(zs_free); |
00a61d861 staging: zsmalloc... |
981 982 983 984 985 986 987 |
/** * zs_map_object - get address of allocated object from handle. * @pool: pool from which the object was allocated * @handle: handle returned from zs_malloc * * Before using an object allocated from zs_malloc, it must be mapped using * this function. When done with the object, it must be unmapped using |
166cfda75 staging: zsmalloc... |
988 989 990 991 992 993 |
* zs_unmap_object. * * Only one object can be mapped per cpu at a time. There is no protection * against nested mappings. * * This function returns with preemption and page faults disabled. |
396b7fd6f staging/zsmalloc:... |
994 |
*/ |
b74185108 staging: zsmalloc... |
995 996 |
void *zs_map_object(struct zs_pool *pool, unsigned long handle, enum zs_mapmode mm) |
61989a80f staging: zsmalloc... |
997 998 999 1000 1001 1002 1003 1004 |
{ struct page *page; unsigned long obj_idx, off; unsigned int class_idx; enum fullness_group fg; struct size_class *class; struct mapping_area *area; |
f553646a6 staging: zsmalloc... |
1005 |
struct page *pages[2]; |
61989a80f staging: zsmalloc... |
1006 1007 |
BUG_ON(!handle); |
c60369f01 staging: zsmalloc... |
1008 1009 1010 1011 1012 1013 |
/* * Because we use per-cpu mapping areas shared among the * pools/users, we can't allow mapping in interrupt context * because it can corrupt another users mappings. */ BUG_ON(in_interrupt()); |
61989a80f staging: zsmalloc... |
1014 1015 1016 1017 1018 1019 |
obj_handle_to_location(handle, &page, &obj_idx); get_zspage_mapping(get_first_page(page), &class_idx, &fg); class = &pool->size_class[class_idx]; off = obj_idx_to_offset(page, obj_idx, class->size); area = &get_cpu_var(zs_map_area); |
f553646a6 staging: zsmalloc... |
1020 |
area->vm_mm = mm; |
61989a80f staging: zsmalloc... |
1021 1022 1023 |
if (off + class->size <= PAGE_SIZE) { /* this object is contained entirely within a page */ area->vm_addr = kmap_atomic(page); |
5f601902c staging: zsmalloc... |
1024 |
return area->vm_addr + off; |
61989a80f staging: zsmalloc... |
1025 |
} |
f553646a6 staging: zsmalloc... |
1026 1027 1028 1029 |
/* this object spans two pages */ pages[0] = page; pages[1] = get_next_page(page); BUG_ON(!pages[1]); |
b74185108 staging: zsmalloc... |
1030 |
|
f553646a6 staging: zsmalloc... |
1031 |
return __zs_map_object(area, pages, off, class->size); |
61989a80f staging: zsmalloc... |
1032 1033 |
} EXPORT_SYMBOL_GPL(zs_map_object); |
c23443483 staging: zsmalloc... |
1034 |
void zs_unmap_object(struct zs_pool *pool, unsigned long handle) |
61989a80f staging: zsmalloc... |
1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 |
{ struct page *page; unsigned long obj_idx, off; unsigned int class_idx; enum fullness_group fg; struct size_class *class; struct mapping_area *area; BUG_ON(!handle); obj_handle_to_location(handle, &page, &obj_idx); get_zspage_mapping(get_first_page(page), &class_idx, &fg); class = &pool->size_class[class_idx]; off = obj_idx_to_offset(page, obj_idx, class->size); |
7c8e0181e mm: replace __get... |
1050 |
area = this_cpu_ptr(&zs_map_area); |
f553646a6 staging: zsmalloc... |
1051 1052 1053 1054 1055 1056 1057 1058 |
if (off + class->size <= PAGE_SIZE) kunmap_atomic(area->vm_addr); else { struct page *pages[2]; pages[0] = page; pages[1] = get_next_page(page); BUG_ON(!pages[1]); |
b74185108 staging: zsmalloc... |
1059 |
|
f553646a6 staging: zsmalloc... |
1060 1061 |
__zs_unmap_object(area, pages, off, class->size); } |
61989a80f staging: zsmalloc... |
1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 |
put_cpu_var(zs_map_area); } EXPORT_SYMBOL_GPL(zs_unmap_object); u64 zs_get_total_size_bytes(struct zs_pool *pool) { int i; u64 npages = 0; for (i = 0; i < ZS_SIZE_CLASSES; i++) npages += pool->size_class[i].pages_allocated; return npages << PAGE_SHIFT; } EXPORT_SYMBOL_GPL(zs_get_total_size_bytes); |
069f101fa staging: zsmalloc... |
1077 1078 1079 1080 1081 1082 |
module_init(zs_init); module_exit(zs_exit); MODULE_LICENSE("Dual BSD/GPL"); MODULE_AUTHOR("Nitin Gupta <ngupta@vflare.org>"); |