Training courses

Kernel and Embedded Linux

Bootlin training courses

Embedded Linux, kernel,
Yocto Project, Buildroot, real-time,
graphics, boot time, debugging...

Bootlin logo

Elixir Cross Referencer

   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
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
// SPDX-License-Identifier: GPL-2.0-only
/*
 * z3fold.c
 *
 * Author: Vitaly Wool <vitaly.wool@konsulko.com>
 * Copyright (C) 2016, Sony Mobile Communications Inc.
 *
 * This implementation is based on zbud written by Seth Jennings.
 *
 * z3fold is an special purpose allocator for storing compressed pages. It
 * can store up to three compressed pages per page which improves the
 * compression ratio of zbud while retaining its main concepts (e. g. always
 * storing an integral number of objects per page) and simplicity.
 * It still has simple and deterministic reclaim properties that make it
 * preferable to a higher density approach (with no requirement on integral
 * number of object per page) when reclaim is used.
 *
 * As in zbud, pages are divided into "chunks".  The size of the chunks is
 * fixed at compile time and is determined by NCHUNKS_ORDER below.
 *
 * z3fold doesn't export any API and is meant to be used via zpool API.
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/atomic.h>
#include <linux/sched.h>
#include <linux/cpumask.h>
#include <linux/list.h>
#include <linux/mm.h>
#include <linux/module.h>
#include <linux/page-flags.h>
#include <linux/migrate.h>
#include <linux/node.h>
#include <linux/compaction.h>
#include <linux/percpu.h>
#include <linux/mount.h>
#include <linux/pseudo_fs.h>
#include <linux/fs.h>
#include <linux/preempt.h>
#include <linux/workqueue.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/zpool.h>
#include <linux/magic.h>

/*
 * NCHUNKS_ORDER determines the internal allocation granularity, effectively
 * adjusting internal fragmentation.  It also determines the number of
 * freelists maintained in each pool. NCHUNKS_ORDER of 6 means that the
 * allocation granularity will be in chunks of size PAGE_SIZE/64. Some chunks
 * in the beginning of an allocated page are occupied by z3fold header, so
 * NCHUNKS will be calculated to 63 (or 62 in case CONFIG_DEBUG_SPINLOCK=y),
 * which shows the max number of free chunks in z3fold page, also there will
 * be 63, or 62, respectively, freelists per pool.
 */
#define NCHUNKS_ORDER	6

#define CHUNK_SHIFT	(PAGE_SHIFT - NCHUNKS_ORDER)
#define CHUNK_SIZE	(1 << CHUNK_SHIFT)
#define ZHDR_SIZE_ALIGNED round_up(sizeof(struct z3fold_header), CHUNK_SIZE)
#define ZHDR_CHUNKS	(ZHDR_SIZE_ALIGNED >> CHUNK_SHIFT)
#define TOTAL_CHUNKS	(PAGE_SIZE >> CHUNK_SHIFT)
#define NCHUNKS		((PAGE_SIZE - ZHDR_SIZE_ALIGNED) >> CHUNK_SHIFT)

#define BUDDY_MASK	(0x3)
#define BUDDY_SHIFT	2
#define SLOTS_ALIGN	(0x40)

/*****************
 * Structures
*****************/
struct z3fold_pool;
struct z3fold_ops {
	int (*evict)(struct z3fold_pool *pool, unsigned long handle);
};

enum buddy {
	HEADLESS = 0,
	FIRST,
	MIDDLE,
	LAST,
	BUDDIES_MAX = LAST
};

struct z3fold_buddy_slots {
	/*
	 * we are using BUDDY_MASK in handle_to_buddy etc. so there should
	 * be enough slots to hold all possible variants
	 */
	unsigned long slot[BUDDY_MASK + 1];
	unsigned long pool; /* back link + flags */
};
#define HANDLE_FLAG_MASK	(0x03)

/*
 * struct z3fold_header - z3fold page metadata occupying first chunks of each
 *			z3fold page, except for HEADLESS pages
 * @buddy:		links the z3fold page into the relevant list in the
 *			pool
 * @page_lock:		per-page lock
 * @refcount:		reference count for the z3fold page
 * @work:		work_struct for page layout optimization
 * @slots:		pointer to the structure holding buddy slots
 * @pool:		pointer to the containing pool
 * @cpu:		CPU which this page "belongs" to
 * @first_chunks:	the size of the first buddy in chunks, 0 if free
 * @middle_chunks:	the size of the middle buddy in chunks, 0 if free
 * @last_chunks:	the size of the last buddy in chunks, 0 if free
 * @first_num:		the starting number (for the first handle)
 * @mapped_count:	the number of objects currently mapped
 */
struct z3fold_header {
	struct list_head buddy;
	spinlock_t page_lock;
	struct kref refcount;
	struct work_struct work;
	struct z3fold_buddy_slots *slots;
	struct z3fold_pool *pool;
	short cpu;
	unsigned short first_chunks;
	unsigned short middle_chunks;
	unsigned short last_chunks;
	unsigned short start_middle;
	unsigned short first_num:2;
	unsigned short mapped_count:2;
};

/**
 * struct z3fold_pool - stores metadata for each z3fold pool
 * @name:	pool name
 * @lock:	protects pool unbuddied/lru lists
 * @stale_lock:	protects pool stale page list
 * @unbuddied:	per-cpu array of lists tracking z3fold pages that contain 2-
 *		buddies; the list each z3fold page is added to depends on
 *		the size of its free region.
 * @lru:	list tracking the z3fold pages in LRU order by most recently
 *		added buddy.
 * @stale:	list of pages marked for freeing
 * @pages_nr:	number of z3fold pages in the pool.
 * @c_handle:	cache for z3fold_buddy_slots allocation
 * @ops:	pointer to a structure of user defined operations specified at
 *		pool creation time.
 * @compact_wq:	workqueue for page layout background optimization
 * @release_wq:	workqueue for safe page release
 * @work:	work_struct for safe page release
 * @inode:	inode for z3fold pseudo filesystem
 *
 * This structure is allocated at pool creation time and maintains metadata
 * pertaining to a particular z3fold pool.
 */
struct z3fold_pool {
	const char *name;
	spinlock_t lock;
	spinlock_t stale_lock;
	struct list_head *unbuddied;
	struct list_head lru;
	struct list_head stale;
	atomic64_t pages_nr;
	struct kmem_cache *c_handle;
	const struct z3fold_ops *ops;
	struct zpool *zpool;
	const struct zpool_ops *zpool_ops;
	struct workqueue_struct *compact_wq;
	struct workqueue_struct *release_wq;
	struct work_struct work;
	struct inode *inode;
};

/*
 * Internal z3fold page flags
 */
enum z3fold_page_flags {
	PAGE_HEADLESS = 0,
	MIDDLE_CHUNK_MAPPED,
	NEEDS_COMPACTING,
	PAGE_STALE,
	PAGE_CLAIMED, /* by either reclaim or free */
};

/*****************
 * Helpers
*****************/

/* Converts an allocation size in bytes to size in z3fold chunks */
static int size_to_chunks(size_t size)
{
	return (size + CHUNK_SIZE - 1) >> CHUNK_SHIFT;
}

#define for_each_unbuddied_list(_iter, _begin) \
	for ((_iter) = (_begin); (_iter) < NCHUNKS; (_iter)++)

static void compact_page_work(struct work_struct *w);

static inline struct z3fold_buddy_slots *alloc_slots(struct z3fold_pool *pool,
							gfp_t gfp)
{
	struct z3fold_buddy_slots *slots;

	slots = kmem_cache_alloc(pool->c_handle,
				 (gfp & ~(__GFP_HIGHMEM | __GFP_MOVABLE)));

	if (slots) {
		memset(slots->slot, 0, sizeof(slots->slot));
		slots->pool = (unsigned long)pool;
	}

	return slots;
}

static inline struct z3fold_pool *slots_to_pool(struct z3fold_buddy_slots *s)
{
	return (struct z3fold_pool *)(s->pool & ~HANDLE_FLAG_MASK);
}

static inline struct z3fold_buddy_slots *handle_to_slots(unsigned long handle)
{
	return (struct z3fold_buddy_slots *)(handle & ~(SLOTS_ALIGN - 1));
}

static inline void free_handle(unsigned long handle)
{
	struct z3fold_buddy_slots *slots;
	int i;
	bool is_free;

	if (handle & (1 << PAGE_HEADLESS))
		return;

	WARN_ON(*(unsigned long *)handle == 0);
	*(unsigned long *)handle = 0;
	slots = handle_to_slots(handle);
	is_free = true;
	for (i = 0; i <= BUDDY_MASK; i++) {
		if (slots->slot[i]) {
			is_free = false;
			break;
		}
	}

	if (is_free) {
		struct z3fold_pool *pool = slots_to_pool(slots);

		kmem_cache_free(pool->c_handle, slots);
	}
}

static int z3fold_init_fs_context(struct fs_context *fc)
{
	return init_pseudo(fc, Z3FOLD_MAGIC) ? 0 : -ENOMEM;
}

static struct file_system_type z3fold_fs = {
	.name		= "z3fold",
	.init_fs_context = z3fold_init_fs_context,
	.kill_sb	= kill_anon_super,
};

static struct vfsmount *z3fold_mnt;
static int z3fold_mount(void)
{
	int ret = 0;

	z3fold_mnt = kern_mount(&z3fold_fs);
	if (IS_ERR(z3fold_mnt))
		ret = PTR_ERR(z3fold_mnt);

	return ret;
}

static void z3fold_unmount(void)
{
	kern_unmount(z3fold_mnt);
}

static const struct address_space_operations z3fold_aops;
static int z3fold_register_migration(struct z3fold_pool *pool)
{
	pool->inode = alloc_anon_inode(z3fold_mnt->mnt_sb);
	if (IS_ERR(pool->inode)) {
		pool->inode = NULL;
		return 1;
	}

	pool->inode->i_mapping->private_data = pool;
	pool->inode->i_mapping->a_ops = &z3fold_aops;
	return 0;
}

static void z3fold_unregister_migration(struct z3fold_pool *pool)
{
	if (pool->inode)
		iput(pool->inode);
 }

/* Initializes the z3fold header of a newly allocated z3fold page */
static struct z3fold_header *init_z3fold_page(struct page *page, bool headless,
					struct z3fold_pool *pool, gfp_t gfp)
{
	struct z3fold_header *zhdr = page_address(page);
	struct z3fold_buddy_slots *slots;

	INIT_LIST_HEAD(&page->lru);
	clear_bit(PAGE_HEADLESS, &page->private);
	clear_bit(MIDDLE_CHUNK_MAPPED, &page->private);
	clear_bit(NEEDS_COMPACTING, &page->private);
	clear_bit(PAGE_STALE, &page->private);
	clear_bit(PAGE_CLAIMED, &page->private);
	if (headless)
		return zhdr;

	slots = alloc_slots(pool, gfp);
	if (!slots)
		return NULL;

	spin_lock_init(&zhdr->page_lock);
	kref_init(&zhdr->refcount);
	zhdr->first_chunks = 0;
	zhdr->middle_chunks = 0;
	zhdr->last_chunks = 0;
	zhdr->first_num = 0;
	zhdr->start_middle = 0;
	zhdr->cpu = -1;
	zhdr->slots = slots;
	zhdr->pool = pool;
	INIT_LIST_HEAD(&zhdr->buddy);
	INIT_WORK(&zhdr->work, compact_page_work);
	return zhdr;
}

/* Resets the struct page fields and frees the page */
static void free_z3fold_page(struct page *page, bool headless)
{
	if (!headless) {
		lock_page(page);
		__ClearPageMovable(page);
		unlock_page(page);
	}
	ClearPagePrivate(page);
	__free_page(page);
}

/* Lock a z3fold page */
static inline void z3fold_page_lock(struct z3fold_header *zhdr)
{
	spin_lock(&zhdr->page_lock);
}

/* Try to lock a z3fold page */
static inline int z3fold_page_trylock(struct z3fold_header *zhdr)
{
	return spin_trylock(&zhdr->page_lock);
}

/* Unlock a z3fold page */
static inline void z3fold_page_unlock(struct z3fold_header *zhdr)
{
	spin_unlock(&zhdr->page_lock);
}

/* Helper function to build the index */
static inline int __idx(struct z3fold_header *zhdr, enum buddy bud)
{
	return (bud + zhdr->first_num) & BUDDY_MASK;
}

/*
 * Encodes the handle of a particular buddy within a z3fold page
 * Pool lock should be held as this function accesses first_num
 */
static unsigned long __encode_handle(struct z3fold_header *zhdr,
				struct z3fold_buddy_slots *slots,
				enum buddy bud)
{
	unsigned long h = (unsigned long)zhdr;
	int idx = 0;

	/*
	 * For a headless page, its handle is its pointer with the extra
	 * PAGE_HEADLESS bit set
	 */
	if (bud == HEADLESS)
		return h | (1 << PAGE_HEADLESS);

	/* otherwise, return pointer to encoded handle */
	idx = __idx(zhdr, bud);
	h += idx;
	if (bud == LAST)
		h |= (zhdr->last_chunks << BUDDY_SHIFT);

	slots->slot[idx] = h;
	return (unsigned long)&slots->slot[idx];
}

static unsigned long encode_handle(struct z3fold_header *zhdr, enum buddy bud)
{
	return __encode_handle(zhdr, zhdr->slots, bud);
}

/* Returns the z3fold page where a given handle is stored */
static inline struct z3fold_header *handle_to_z3fold_header(unsigned long h)
{
	unsigned long addr = h;

	if (!(addr & (1 << PAGE_HEADLESS)))
		addr = *(unsigned long *)h;

	return (struct z3fold_header *)(addr & PAGE_MASK);
}

/* only for LAST bud, returns zero otherwise */
static unsigned short handle_to_chunks(unsigned long handle)
{
	unsigned long addr = *(unsigned long *)handle;

	return (addr & ~PAGE_MASK) >> BUDDY_SHIFT;
}

/*
 * (handle & BUDDY_MASK) < zhdr->first_num is possible in encode_handle
 *  but that doesn't matter. because the masking will result in the
 *  correct buddy number.
 */
static enum buddy handle_to_buddy(unsigned long handle)
{
	struct z3fold_header *zhdr;
	unsigned long addr;

	WARN_ON(handle & (1 << PAGE_HEADLESS));
	addr = *(unsigned long *)handle;
	zhdr = (struct z3fold_header *)(addr & PAGE_MASK);
	return (addr - zhdr->first_num) & BUDDY_MASK;
}

static inline struct z3fold_pool *zhdr_to_pool(struct z3fold_header *zhdr)
{
	return zhdr->pool;
}

static void __release_z3fold_page(struct z3fold_header *zhdr, bool locked)
{
	struct page *page = virt_to_page(zhdr);
	struct z3fold_pool *pool = zhdr_to_pool(zhdr);

	WARN_ON(!list_empty(&zhdr->buddy));
	set_bit(PAGE_STALE, &page->private);
	clear_bit(NEEDS_COMPACTING, &page->private);
	spin_lock(&pool->lock);
	if (!list_empty(&page->lru))
		list_del_init(&page->lru);
	spin_unlock(&pool->lock);
	if (locked)
		z3fold_page_unlock(zhdr);
	spin_lock(&pool->stale_lock);
	list_add(&zhdr->buddy, &pool->stale);
	queue_work(pool->release_wq, &pool->work);
	spin_unlock(&pool->stale_lock);
}

static void __attribute__((__unused__))
			release_z3fold_page(struct kref *ref)
{
	struct z3fold_header *zhdr = container_of(ref, struct z3fold_header,
						refcount);
	__release_z3fold_page(zhdr, false);
}

static void release_z3fold_page_locked(struct kref *ref)
{
	struct z3fold_header *zhdr = container_of(ref, struct z3fold_header,
						refcount);
	WARN_ON(z3fold_page_trylock(zhdr));
	__release_z3fold_page(zhdr, true);
}

static void release_z3fold_page_locked_list(struct kref *ref)
{
	struct z3fold_header *zhdr = container_of(ref, struct z3fold_header,
					       refcount);
	struct z3fold_pool *pool = zhdr_to_pool(zhdr);
	spin_lock(&pool->lock);
	list_del_init(&zhdr->buddy);
	spin_unlock(&pool->lock);

	WARN_ON(z3fold_page_trylock(zhdr));
	__release_z3fold_page(zhdr, true);
}

static void free_pages_work(struct work_struct *w)
{
	struct z3fold_pool *pool = container_of(w, struct z3fold_pool, work);

	spin_lock(&pool->stale_lock);
	while (!list_empty(&pool->stale)) {
		struct z3fold_header *zhdr = list_first_entry(&pool->stale,
						struct z3fold_header, buddy);
		struct page *page = virt_to_page(zhdr);

		list_del(&zhdr->buddy);
		if (WARN_ON(!test_bit(PAGE_STALE, &page->private)))
			continue;
		spin_unlock(&pool->stale_lock);
		cancel_work_sync(&zhdr->work);
		free_z3fold_page(page, false);
		cond_resched();
		spin_lock(&pool->stale_lock);
	}
	spin_unlock(&pool->stale_lock);
}

/*
 * Returns the number of free chunks in a z3fold page.
 * NB: can't be used with HEADLESS pages.
 */
static int num_free_chunks(struct z3fold_header *zhdr)
{
	int nfree;
	/*
	 * If there is a middle object, pick up the bigger free space
	 * either before or after it. Otherwise just subtract the number
	 * of chunks occupied by the first and the last objects.
	 */
	if (zhdr->middle_chunks != 0) {
		int nfree_before = zhdr->first_chunks ?
			0 : zhdr->start_middle - ZHDR_CHUNKS;
		int nfree_after = zhdr->last_chunks ?
			0 : TOTAL_CHUNKS -
				(zhdr->start_middle + zhdr->middle_chunks);
		nfree = max(nfree_before, nfree_after);
	} else
		nfree = NCHUNKS - zhdr->first_chunks - zhdr->last_chunks;
	return nfree;
}

/* Add to the appropriate unbuddied list */
static inline void add_to_unbuddied(struct z3fold_pool *pool,
				struct z3fold_header *zhdr)
{
	if (zhdr->first_chunks == 0 || zhdr->last_chunks == 0 ||
			zhdr->middle_chunks == 0) {
		struct list_head *unbuddied = get_cpu_ptr(pool->unbuddied);

		int freechunks = num_free_chunks(zhdr);
		spin_lock(&pool->lock);
		list_add(&zhdr->buddy, &unbuddied[freechunks]);
		spin_unlock(&pool->lock);
		zhdr->cpu = smp_processor_id();
		put_cpu_ptr(pool->unbuddied);
	}
}

static inline void *mchunk_memmove(struct z3fold_header *zhdr,
				unsigned short dst_chunk)
{
	void *beg = zhdr;
	return memmove(beg + (dst_chunk << CHUNK_SHIFT),
		       beg + (zhdr->start_middle << CHUNK_SHIFT),
		       zhdr->middle_chunks << CHUNK_SHIFT);
}

#define BIG_CHUNK_GAP	3
/* Has to be called with lock held */
static int z3fold_compact_page(struct z3fold_header *zhdr)
{
	struct page *page = virt_to_page(zhdr);

	if (test_bit(MIDDLE_CHUNK_MAPPED, &page->private))
		return 0; /* can't move middle chunk, it's used */

	if (unlikely(PageIsolated(page)))
		return 0;

	if (zhdr->middle_chunks == 0)
		return 0; /* nothing to compact */

	if (zhdr->first_chunks == 0 && zhdr->last_chunks == 0) {
		/* move to the beginning */
		mchunk_memmove(zhdr, ZHDR_CHUNKS);
		zhdr->first_chunks = zhdr->middle_chunks;
		zhdr->middle_chunks = 0;
		zhdr->start_middle = 0;
		zhdr->first_num++;
		return 1;
	}

	/*
	 * moving data is expensive, so let's only do that if
	 * there's substantial gain (at least BIG_CHUNK_GAP chunks)
	 */
	if (zhdr->first_chunks != 0 && zhdr->last_chunks == 0 &&
	    zhdr->start_middle - (zhdr->first_chunks + ZHDR_CHUNKS) >=
			BIG_CHUNK_GAP) {
		mchunk_memmove(zhdr, zhdr->first_chunks + ZHDR_CHUNKS);
		zhdr->start_middle = zhdr->first_chunks + ZHDR_CHUNKS;
		return 1;
	} else if (zhdr->last_chunks != 0 && zhdr->first_chunks == 0 &&
		   TOTAL_CHUNKS - (zhdr->last_chunks + zhdr->start_middle
					+ zhdr->middle_chunks) >=
			BIG_CHUNK_GAP) {
		unsigned short new_start = TOTAL_CHUNKS - zhdr->last_chunks -
			zhdr->middle_chunks;
		mchunk_memmove(zhdr, new_start);
		zhdr->start_middle = new_start;
		return 1;
	}

	return 0;
}

static void do_compact_page(struct z3fold_header *zhdr, bool locked)
{
	struct z3fold_pool *pool = zhdr_to_pool(zhdr);
	struct page *page;

	page = virt_to_page(zhdr);
	if (locked)
		WARN_ON(z3fold_page_trylock(zhdr));
	else
		z3fold_page_lock(zhdr);
	if (WARN_ON(!test_and_clear_bit(NEEDS_COMPACTING, &page->private))) {
		z3fold_page_unlock(zhdr);
		return;
	}
	spin_lock(&pool->lock);
	list_del_init(&zhdr->buddy);
	spin_unlock(&pool->lock);

	if (kref_put(&zhdr->refcount, release_z3fold_page_locked)) {
		atomic64_dec(&pool->pages_nr);
		return;
	}

	if (unlikely(PageIsolated(page) ||
		     test_bit(PAGE_CLAIMED, &page->private) ||
		     test_bit(PAGE_STALE, &page->private))) {
		z3fold_page_unlock(zhdr);
		return;
	}

	z3fold_compact_page(zhdr);
	add_to_unbuddied(pool, zhdr);
	z3fold_page_unlock(zhdr);
}

static void compact_page_work(struct work_struct *w)
{
	struct z3fold_header *zhdr = container_of(w, struct z3fold_header,
						work);

	do_compact_page(zhdr, false);
}

/* returns _locked_ z3fold page header or NULL */
static inline struct z3fold_header *__z3fold_alloc(struct z3fold_pool *pool,
						size_t size, bool can_sleep)
{
	struct z3fold_header *zhdr = NULL;
	struct page *page;
	struct list_head *unbuddied;
	int chunks = size_to_chunks(size), i;

lookup:
	/* First, try to find an unbuddied z3fold page. */
	unbuddied = get_cpu_ptr(pool->unbuddied);
	for_each_unbuddied_list(i, chunks) {
		struct list_head *l = &unbuddied[i];

		zhdr = list_first_entry_or_null(READ_ONCE(l),
					struct z3fold_header, buddy);

		if (!zhdr)
			continue;

		/* Re-check under lock. */
		spin_lock(&pool->lock);
		l = &unbuddied[i];
		if (unlikely(zhdr != list_first_entry(READ_ONCE(l),
						struct z3fold_header, buddy)) ||
		    !z3fold_page_trylock(zhdr)) {
			spin_unlock(&pool->lock);
			zhdr = NULL;
			put_cpu_ptr(pool->unbuddied);
			if (can_sleep)
				cond_resched();
			goto lookup;
		}
		list_del_init(&zhdr->buddy);
		zhdr->cpu = -1;
		spin_unlock(&pool->lock);

		page = virt_to_page(zhdr);
		if (test_bit(NEEDS_COMPACTING, &page->private)) {
			z3fold_page_unlock(zhdr);
			zhdr = NULL;
			put_cpu_ptr(pool->unbuddied);
			if (can_sleep)
				cond_resched();
			goto lookup;
		}

		/*
		 * this page could not be removed from its unbuddied
		 * list while pool lock was held, and then we've taken
		 * page lock so kref_put could not be called before
		 * we got here, so it's safe to just call kref_get()
		 */
		kref_get(&zhdr->refcount);
		break;
	}
	put_cpu_ptr(pool->unbuddied);

	if (!zhdr) {
		int cpu;

		/* look for _exact_ match on other cpus' lists */
		for_each_online_cpu(cpu) {
			struct list_head *l;

			unbuddied = per_cpu_ptr(pool->unbuddied, cpu);
			spin_lock(&pool->lock);
			l = &unbuddied[chunks];

			zhdr = list_first_entry_or_null(READ_ONCE(l),
						struct z3fold_header, buddy);

			if (!zhdr || !z3fold_page_trylock(zhdr)) {
				spin_unlock(&pool->lock);
				zhdr = NULL;
				continue;
			}
			list_del_init(&zhdr->buddy);
			zhdr->cpu = -1;
			spin_unlock(&pool->lock);

			page = virt_to_page(zhdr);
			if (test_bit(NEEDS_COMPACTING, &page->private)) {
				z3fold_page_unlock(zhdr);
				zhdr = NULL;
				if (can_sleep)
					cond_resched();
				continue;
			}
			kref_get(&zhdr->refcount);
			break;
		}
	}

	return zhdr;
}

/*
 * API Functions
 */

/**
 * z3fold_create_pool() - create a new z3fold pool
 * @name:	pool name
 * @gfp:	gfp flags when allocating the z3fold pool structure
 * @ops:	user-defined operations for the z3fold pool
 *
 * Return: pointer to the new z3fold pool or NULL if the metadata allocation
 * failed.
 */
static struct z3fold_pool *z3fold_create_pool(const char *name, gfp_t gfp,
		const struct z3fold_ops *ops)
{
	struct z3fold_pool *pool = NULL;
	int i, cpu;

	pool = kzalloc(sizeof(struct z3fold_pool), gfp);
	if (!pool)
		goto out;
	pool->c_handle = kmem_cache_create("z3fold_handle",
				sizeof(struct z3fold_buddy_slots),
				SLOTS_ALIGN, 0, NULL);
	if (!pool->c_handle)
		goto out_c;
	spin_lock_init(&pool->lock);
	spin_lock_init(&pool->stale_lock);
	pool->unbuddied = __alloc_percpu(sizeof(struct list_head)*NCHUNKS, 2);
	if (!pool->unbuddied)
		goto out_pool;
	for_each_possible_cpu(cpu) {
		struct list_head *unbuddied =
				per_cpu_ptr(pool->unbuddied, cpu);
		for_each_unbuddied_list(i, 0)
			INIT_LIST_HEAD(&unbuddied[i]);
	}
	INIT_LIST_HEAD(&pool->lru);
	INIT_LIST_HEAD(&pool->stale);
	atomic64_set(&pool->pages_nr, 0);
	pool->name = name;
	pool->compact_wq = create_singlethread_workqueue(pool->name);
	if (!pool->compact_wq)
		goto out_unbuddied;
	pool->release_wq = create_singlethread_workqueue(pool->name);
	if (!pool->release_wq)
		goto out_wq;
	if (z3fold_register_migration(pool))
		goto out_rwq;
	INIT_WORK(&pool->work, free_pages_work);
	pool->ops = ops;
	return pool;

out_rwq:
	destroy_workqueue(pool->release_wq);
out_wq:
	destroy_workqueue(pool->compact_wq);
out_unbuddied:
	free_percpu(pool->unbuddied);
out_pool:
	kmem_cache_destroy(pool->c_handle);
out_c:
	kfree(pool);
out:
	return NULL;
}

/**
 * z3fold_destroy_pool() - destroys an existing z3fold pool
 * @pool:	the z3fold pool to be destroyed
 *
 * The pool should be emptied before this function is called.
 */
static void z3fold_destroy_pool(struct z3fold_pool *pool)
{
	kmem_cache_destroy(pool->c_handle);

	/*
	 * We need to destroy pool->compact_wq before pool->release_wq,
	 * as any pending work on pool->compact_wq will call
	 * queue_work(pool->release_wq, &pool->work).
	 *
	 * There are still outstanding pages until both workqueues are drained,
	 * so we cannot unregister migration until then.
	 */

	destroy_workqueue(pool->compact_wq);
	destroy_workqueue(pool->release_wq);
	z3fold_unregister_migration(pool);
	kfree(pool);
}

/**
 * z3fold_alloc() - allocates a region of a given size
 * @pool:	z3fold pool from which to allocate
 * @size:	size in bytes of the desired allocation
 * @gfp:	gfp flags used if the pool needs to grow
 * @handle:	handle of the new allocation
 *
 * This function will attempt to find a free region in the pool large enough to
 * satisfy the allocation request.  A search of the unbuddied lists is
 * performed first. If no suitable free region is found, then a new page is
 * allocated and added to the pool to satisfy the request.
 *
 * gfp should not set __GFP_HIGHMEM as highmem pages cannot be used
 * as z3fold pool pages.
 *
 * Return: 0 if success and handle is set, otherwise -EINVAL if the size or
 * gfp arguments are invalid or -ENOMEM if the pool was unable to allocate
 * a new page.
 */
static int z3fold_alloc(struct z3fold_pool *pool, size_t size, gfp_t gfp,
			unsigned long *handle)
{
	int chunks = size_to_chunks(size);
	struct z3fold_header *zhdr = NULL;
	struct page *page = NULL;
	enum buddy bud;
	bool can_sleep = gfpflags_allow_blocking(gfp);

	if (!size)
		return -EINVAL;

	if (size > PAGE_SIZE)
		return -ENOSPC;

	if (size > PAGE_SIZE - ZHDR_SIZE_ALIGNED - CHUNK_SIZE)
		bud = HEADLESS;
	else {
retry:
		zhdr = __z3fold_alloc(pool, size, can_sleep);
		if (zhdr) {
			if (zhdr->first_chunks == 0) {
				if (zhdr->middle_chunks != 0 &&
				    chunks >= zhdr->start_middle)
					bud = LAST;
				else
					bud = FIRST;
			} else if (zhdr->last_chunks == 0)
				bud = LAST;
			else if (zhdr->middle_chunks == 0)
				bud = MIDDLE;
			else {
				if (kref_put(&zhdr->refcount,
					     release_z3fold_page_locked))
					atomic64_dec(&pool->pages_nr);
				else
					z3fold_page_unlock(zhdr);
				pr_err("No free chunks in unbuddied\n");
				WARN_ON(1);
				goto retry;
			}
			page = virt_to_page(zhdr);
			goto found;
		}
		bud = FIRST;
	}

	page = NULL;
	if (can_sleep) {
		spin_lock(&pool->stale_lock);
		zhdr = list_first_entry_or_null(&pool->stale,
						struct z3fold_header, buddy);
		/*
		 * Before allocating a page, let's see if we can take one from
		 * the stale pages list. cancel_work_sync() can sleep so we
		 * limit this case to the contexts where we can sleep
		 */
		if (zhdr) {
			list_del(&zhdr->buddy);
			spin_unlock(&pool->stale_lock);
			cancel_work_sync(&zhdr->work);
			page = virt_to_page(zhdr);
		} else {
			spin_unlock(&pool->stale_lock);
		}
	}
	if (!page)
		page = alloc_page(gfp);

	if (!page)
		return -ENOMEM;

	zhdr = init_z3fold_page(page, bud == HEADLESS, pool, gfp);
	if (!zhdr) {
		__free_page(page);
		return -ENOMEM;
	}
	atomic64_inc(&pool->pages_nr);

	if (bud == HEADLESS) {
		set_bit(PAGE_HEADLESS, &page->private);
		goto headless;
	}
	if (can_sleep) {
		lock_page(page);
		__SetPageMovable(page, pool->inode->i_mapping);
		unlock_page(page);
	} else {
		if (trylock_page(page)) {
			__SetPageMovable(page, pool->inode->i_mapping);
			unlock_page(page);
		}
	}
	z3fold_page_lock(zhdr);

found:
	if (bud == FIRST)
		zhdr->first_chunks = chunks;
	else if (bud == LAST)
		zhdr->last_chunks = chunks;
	else {
		zhdr->middle_chunks = chunks;
		zhdr->start_middle = zhdr->first_chunks + ZHDR_CHUNKS;
	}
	add_to_unbuddied(pool, zhdr);

headless:
	spin_lock(&pool->lock);
	/* Add/move z3fold page to beginning of LRU */
	if (!list_empty(&page->lru))
		list_del(&page->lru);

	list_add(&page->lru, &pool->lru);

	*handle = encode_handle(zhdr, bud);
	spin_unlock(&pool->lock);
	if (bud != HEADLESS)
		z3fold_page_unlock(zhdr);

	return 0;
}

/**
 * z3fold_free() - frees the allocation associated with the given handle
 * @pool:	pool in which the allocation resided
 * @handle:	handle associated with the allocation returned by z3fold_alloc()
 *
 * In the case that the z3fold page in which the allocation resides is under
 * reclaim, as indicated by the PG_reclaim flag being set, this function
 * only sets the first|last_chunks to 0.  The page is actually freed
 * once both buddies are evicted (see z3fold_reclaim_page() below).
 */
static void z3fold_free(struct z3fold_pool *pool, unsigned long handle)
{
	struct z3fold_header *zhdr;
	struct page *page;
	enum buddy bud;
	bool page_claimed;

	zhdr = handle_to_z3fold_header(handle);
	page = virt_to_page(zhdr);
	page_claimed = test_and_set_bit(PAGE_CLAIMED, &page->private);

	if (test_bit(PAGE_HEADLESS, &page->private)) {
		/* if a headless page is under reclaim, just leave.
		 * NB: we use test_and_set_bit for a reason: if the bit
		 * has not been set before, we release this page
		 * immediately so we don't care about its value any more.
		 */
		if (!page_claimed) {
			spin_lock(&pool->lock);
			list_del(&page->lru);
			spin_unlock(&pool->lock);
			free_z3fold_page(page, true);
			atomic64_dec(&pool->pages_nr);
		}
		return;
	}

	/* Non-headless case */
	z3fold_page_lock(zhdr);
	bud = handle_to_buddy(handle);

	switch (bud) {
	case FIRST:
		zhdr->first_chunks = 0;
		break;
	case MIDDLE:
		zhdr->middle_chunks = 0;
		break;
	case LAST:
		zhdr->last_chunks = 0;
		break;
	default:
		pr_err("%s: unknown bud %d\n", __func__, bud);
		WARN_ON(1);
		z3fold_page_unlock(zhdr);
		return;
	}

	free_handle(handle);
	if (kref_put(&zhdr->refcount, release_z3fold_page_locked_list)) {
		atomic64_dec(&pool->pages_nr);
		return;
	}
	if (page_claimed) {
		/* the page has not been claimed by us */
		z3fold_page_unlock(zhdr);
		return;
	}
	if (unlikely(PageIsolated(page)) ||
	    test_and_set_bit(NEEDS_COMPACTING, &page->private)) {
		z3fold_page_unlock(zhdr);
		clear_bit(PAGE_CLAIMED, &page->private);
		return;
	}
	if (zhdr->cpu < 0 || !cpu_online(zhdr->cpu)) {
		spin_lock(&pool->lock);
		list_del_init(&zhdr->buddy);
		spin_unlock(&pool->lock);
		zhdr->cpu = -1;
		kref_get(&zhdr->refcount);
		do_compact_page(zhdr, true);
		clear_bit(PAGE_CLAIMED, &page->private);
		return;
	}
	kref_get(&zhdr->refcount);
	queue_work_on(zhdr->cpu, pool->compact_wq, &zhdr->work);
	clear_bit(PAGE_CLAIMED, &page->private);
	z3fold_page_unlock(zhdr);
}

/**
 * z3fold_reclaim_page() - evicts allocations from a pool page and frees it
 * @pool:	pool from which a page will attempt to be evicted
 * @retries:	number of pages on the LRU list for which eviction will
 *		be attempted before failing
 *
 * z3fold reclaim is different from normal system reclaim in that it is done
 * from the bottom, up. This is because only the bottom layer, z3fold, has
 * information on how the allocations are organized within each z3fold page.
 * This has the potential to create interesting locking situations between
 * z3fold and the user, however.
 *
 * To avoid these, this is how z3fold_reclaim_page() should be called:
 *
 * The user detects a page should be reclaimed and calls z3fold_reclaim_page().
 * z3fold_reclaim_page() will remove a z3fold page from the pool LRU list and
 * call the user-defined eviction handler with the pool and handle as
 * arguments.
 *
 * If the handle can not be evicted, the eviction handler should return
 * non-zero. z3fold_reclaim_page() will add the z3fold page back to the
 * appropriate list and try the next z3fold page on the LRU up to
 * a user defined number of retries.
 *
 * If the handle is successfully evicted, the eviction handler should
 * return 0 _and_ should have called z3fold_free() on the handle. z3fold_free()
 * contains logic to delay freeing the page if the page is under reclaim,
 * as indicated by the setting of the PG_reclaim flag on the underlying page.
 *
 * If all buddies in the z3fold page are successfully evicted, then the
 * z3fold page can be freed.
 *
 * Returns: 0 if page is successfully freed, otherwise -EINVAL if there are
 * no pages to evict or an eviction handler is not registered, -EAGAIN if
 * the retry limit was hit.
 */
static int z3fold_reclaim_page(struct z3fold_pool *pool, unsigned int retries)
{
	int i, ret = 0;
	struct z3fold_header *zhdr = NULL;
	struct page *page = NULL;
	struct list_head *pos;
	struct z3fold_buddy_slots slots;
	unsigned long first_handle = 0, middle_handle = 0, last_handle = 0;

	spin_lock(&pool->lock);
	if (!pool->ops || !pool->ops->evict || retries == 0) {
		spin_unlock(&pool->lock);
		return -EINVAL;
	}
	for (i = 0; i < retries; i++) {
		if (list_empty(&pool->lru)) {
			spin_unlock(&pool->lock);
			return -EINVAL;
		}
		list_for_each_prev(pos, &pool->lru) {
			page = list_entry(pos, struct page, lru);

			/* this bit could have been set by free, in which case
			 * we pass over to the next page in the pool.
			 */
			if (test_and_set_bit(PAGE_CLAIMED, &page->private)) {
				page = NULL;
				continue;
			}

			if (unlikely(PageIsolated(page))) {
				clear_bit(PAGE_CLAIMED, &page->private);
				page = NULL;
				continue;
			}
			zhdr = page_address(page);
			if (test_bit(PAGE_HEADLESS, &page->private))
				break;

			if (!z3fold_page_trylock(zhdr)) {
				clear_bit(PAGE_CLAIMED, &page->private);
				zhdr = NULL;
				continue; /* can't evict at this point */
			}
			kref_get(&zhdr->refcount);
			list_del_init(&zhdr->buddy);
			zhdr->cpu = -1;
			break;
		}

		if (!zhdr)
			break;

		list_del_init(&page->lru);
		spin_unlock(&pool->lock);

		if (!test_bit(PAGE_HEADLESS, &page->private)) {
			/*
			 * We need encode the handles before unlocking, and
			 * use our local slots structure because z3fold_free
			 * can zero out zhdr->slots and we can't do much
			 * about that
			 */
			first_handle = 0;
			last_handle = 0;
			middle_handle = 0;
			if (zhdr->first_chunks)
				first_handle = __encode_handle(zhdr, &slots,
								FIRST);
			if (zhdr->middle_chunks)
				middle_handle = __encode_handle(zhdr, &slots,
								MIDDLE);
			if (zhdr->last_chunks)
				last_handle = __encode_handle(zhdr, &slots,
								LAST);
			/*
			 * it's safe to unlock here because we hold a
			 * reference to this page
			 */
			z3fold_page_unlock(zhdr);
		} else {
			first_handle = __encode_handle(zhdr, &slots, HEADLESS);
			last_handle = middle_handle = 0;
		}

		/* Issue the eviction callback(s) */
		if (middle_handle) {
			ret = pool->ops->evict(pool, middle_handle);
			if (ret)
				goto next;
		}
		if (first_handle) {
			ret = pool->ops->evict(pool, first_handle);
			if (ret)
				goto next;
		}
		if (last_handle) {
			ret = pool->ops->evict(pool, last_handle);
			if (ret)
				goto next;
		}
next:
		if (test_bit(PAGE_HEADLESS, &page->private)) {
			if (ret == 0) {
				free_z3fold_page(page, true);
				atomic64_dec(&pool->pages_nr);
				return 0;
			}
			spin_lock(&pool->lock);
			list_add(&page->lru, &pool->lru);
			spin_unlock(&pool->lock);
			clear_bit(PAGE_CLAIMED, &page->private);
		} else {
			z3fold_page_lock(zhdr);
			if (kref_put(&zhdr->refcount,
					release_z3fold_page_locked)) {
				atomic64_dec(&pool->pages_nr);
				return 0;
			}
			/*
			 * if we are here, the page is still not completely
			 * free. Take the global pool lock then to be able
			 * to add it back to the lru list
			 */
			spin_lock(&pool->lock);
			list_add(&page->lru, &pool->lru);
			spin_unlock(&pool->lock);
			z3fold_page_unlock(zhdr);
			clear_bit(PAGE_CLAIMED, &page->private);
		}

		/* We started off locked to we need to lock the pool back */
		spin_lock(&pool->lock);
	}
	spin_unlock(&pool->lock);
	return -EAGAIN;
}

/**
 * z3fold_map() - maps the allocation associated with the given handle
 * @pool:	pool in which the allocation resides
 * @handle:	handle associated with the allocation to be mapped
 *
 * Extracts the buddy number from handle and constructs the pointer to the
 * correct starting chunk within the page.
 *
 * Returns: a pointer to the mapped allocation
 */
static void *z3fold_map(struct z3fold_pool *pool, unsigned long handle)
{
	struct z3fold_header *zhdr;
	struct page *page;
	void *addr;
	enum buddy buddy;

	zhdr = handle_to_z3fold_header(handle);
	addr = zhdr;
	page = virt_to_page(zhdr);

	if (test_bit(PAGE_HEADLESS, &page->private))
		goto out;

	z3fold_page_lock(zhdr);
	buddy = handle_to_buddy(handle);
	switch (buddy) {
	case FIRST:
		addr += ZHDR_SIZE_ALIGNED;
		break;
	case MIDDLE:
		addr += zhdr->start_middle << CHUNK_SHIFT;
		set_bit(MIDDLE_CHUNK_MAPPED, &page->private);
		break;
	case LAST:
		addr += PAGE_SIZE - (handle_to_chunks(handle) << CHUNK_SHIFT);
		break;
	default:
		pr_err("unknown buddy id %d\n", buddy);
		WARN_ON(1);
		addr = NULL;
		break;
	}

	if (addr)
		zhdr->mapped_count++;
	z3fold_page_unlock(zhdr);
out:
	return addr;
}

/**
 * z3fold_unmap() - unmaps the allocation associated with the given handle
 * @pool:	pool in which the allocation resides
 * @handle:	handle associated with the allocation to be unmapped
 */
static void z3fold_unmap(struct z3fold_pool *pool, unsigned long handle)
{
	struct z3fold_header *zhdr;
	struct page *page;
	enum buddy buddy;

	zhdr = handle_to_z3fold_header(handle);
	page = virt_to_page(zhdr);

	if (test_bit(PAGE_HEADLESS, &page->private))
		return;

	z3fold_page_lock(zhdr);
	buddy = handle_to_buddy(handle);
	if (buddy == MIDDLE)
		clear_bit(MIDDLE_CHUNK_MAPPED, &page->private);
	zhdr->mapped_count--;
	z3fold_page_unlock(zhdr);
}

/**
 * z3fold_get_pool_size() - gets the z3fold pool size in pages
 * @pool:	pool whose size is being queried
 *
 * Returns: size in pages of the given pool.
 */
static u64 z3fold_get_pool_size(struct z3fold_pool *pool)
{
	return atomic64_read(&pool->pages_nr);
}

static bool z3fold_page_isolate(struct page *page, isolate_mode_t mode)
{
	struct z3fold_header *zhdr;
	struct z3fold_pool *pool;

	VM_BUG_ON_PAGE(!PageMovable(page), page);
	VM_BUG_ON_PAGE(PageIsolated(page), page);

	if (test_bit(PAGE_HEADLESS, &page->private) ||
	    test_bit(PAGE_CLAIMED, &page->private))
		return false;

	zhdr = page_address(page);
	z3fold_page_lock(zhdr);
	if (test_bit(NEEDS_COMPACTING, &page->private) ||
	    test_bit(PAGE_STALE, &page->private))
		goto out;

	pool = zhdr_to_pool(zhdr);

	if (zhdr->mapped_count == 0) {
		kref_get(&zhdr->refcount);
		if (!list_empty(&zhdr->buddy))
			list_del_init(&zhdr->buddy);
		spin_lock(&pool->lock);
		if (!list_empty(&page->lru))
			list_del(&page->lru);
		spin_unlock(&pool->lock);
		z3fold_page_unlock(zhdr);
		return true;
	}
out:
	z3fold_page_unlock(zhdr);
	return false;
}

static int z3fold_page_migrate(struct address_space *mapping, struct page *newpage,
			       struct page *page, enum migrate_mode mode)
{
	struct z3fold_header *zhdr, *new_zhdr;
	struct z3fold_pool *pool;
	struct address_space *new_mapping;

	VM_BUG_ON_PAGE(!PageMovable(page), page);
	VM_BUG_ON_PAGE(!PageIsolated(page), page);
	VM_BUG_ON_PAGE(!PageLocked(newpage), newpage);

	zhdr = page_address(page);
	pool = zhdr_to_pool(zhdr);

	if (!z3fold_page_trylock(zhdr)) {
		return -EAGAIN;
	}
	if (zhdr->mapped_count != 0) {
		z3fold_page_unlock(zhdr);
		return -EBUSY;
	}
	if (work_pending(&zhdr->work)) {
		z3fold_page_unlock(zhdr);
		return -EAGAIN;
	}
	new_zhdr = page_address(newpage);
	memcpy(new_zhdr, zhdr, PAGE_SIZE);
	newpage->private = page->private;
	page->private = 0;
	z3fold_page_unlock(zhdr);
	spin_lock_init(&new_zhdr->page_lock);
	INIT_WORK(&new_zhdr->work, compact_page_work);
	/*
	 * z3fold_page_isolate() ensures that new_zhdr->buddy is empty,
	 * so we only have to reinitialize it.
	 */
	INIT_LIST_HEAD(&new_zhdr->buddy);
	new_mapping = page_mapping(page);
	__ClearPageMovable(page);
	ClearPagePrivate(page);

	get_page(newpage);
	z3fold_page_lock(new_zhdr);
	if (new_zhdr->first_chunks)
		encode_handle(new_zhdr, FIRST);
	if (new_zhdr->last_chunks)
		encode_handle(new_zhdr, LAST);
	if (new_zhdr->middle_chunks)
		encode_handle(new_zhdr, MIDDLE);
	set_bit(NEEDS_COMPACTING, &newpage->private);
	new_zhdr->cpu = smp_processor_id();
	spin_lock(&pool->lock);
	list_add(&newpage->lru, &pool->lru);
	spin_unlock(&pool->lock);
	__SetPageMovable(newpage, new_mapping);
	z3fold_page_unlock(new_zhdr);

	queue_work_on(new_zhdr->cpu, pool->compact_wq, &new_zhdr->work);

	page_mapcount_reset(page);
	put_page(page);
	return 0;
}

static void z3fold_page_putback(struct page *page)
{
	struct z3fold_header *zhdr;
	struct z3fold_pool *pool;

	zhdr = page_address(page);
	pool = zhdr_to_pool(zhdr);

	z3fold_page_lock(zhdr);
	if (!list_empty(&zhdr->buddy))
		list_del_init(&zhdr->buddy);
	INIT_LIST_HEAD(&page->lru);
	if (kref_put(&zhdr->refcount, release_z3fold_page_locked)) {
		atomic64_dec(&pool->pages_nr);
		return;
	}
	spin_lock(&pool->lock);
	list_add(&page->lru, &pool->lru);
	spin_unlock(&pool->lock);
	z3fold_page_unlock(zhdr);
}

static const struct address_space_operations z3fold_aops = {
	.isolate_page = z3fold_page_isolate,
	.migratepage = z3fold_page_migrate,
	.putback_page = z3fold_page_putback,
};

/*****************
 * zpool
 ****************/

static int z3fold_zpool_evict(struct z3fold_pool *pool, unsigned long handle)
{
	if (pool->zpool && pool->zpool_ops && pool->zpool_ops->evict)
		return pool->zpool_ops->evict(pool->zpool, handle);
	else
		return -ENOENT;
}

static const struct z3fold_ops z3fold_zpool_ops = {
	.evict =	z3fold_zpool_evict
};

static void *z3fold_zpool_create(const char *name, gfp_t gfp,
			       const struct zpool_ops *zpool_ops,
			       struct zpool *zpool)
{
	struct z3fold_pool *pool;

	pool = z3fold_create_pool(name, gfp,
				zpool_ops ? &z3fold_zpool_ops : NULL);
	if (pool) {
		pool->zpool = zpool;
		pool->zpool_ops = zpool_ops;
	}
	return pool;
}

static void z3fold_zpool_destroy(void *pool)
{
	z3fold_destroy_pool(pool);
}

static int z3fold_zpool_malloc(void *pool, size_t size, gfp_t gfp,
			unsigned long *handle)
{
	return z3fold_alloc(pool, size, gfp, handle);
}
static void z3fold_zpool_free(void *pool, unsigned long handle)
{
	z3fold_free(pool, handle);
}

static int z3fold_zpool_shrink(void *pool, unsigned int pages,
			unsigned int *reclaimed)
{
	unsigned int total = 0;
	int ret = -EINVAL;

	while (total < pages) {
		ret = z3fold_reclaim_page(pool, 8);
		if (ret < 0)
			break;
		total++;
	}

	if (reclaimed)
		*reclaimed = total;

	return ret;
}

static void *z3fold_zpool_map(void *pool, unsigned long handle,
			enum zpool_mapmode mm)
{
	return z3fold_map(pool, handle);
}
static void z3fold_zpool_unmap(void *pool, unsigned long handle)
{
	z3fold_unmap(pool, handle);
}

static u64 z3fold_zpool_total_size(void *pool)
{
	return z3fold_get_pool_size(pool) * PAGE_SIZE;
}

static struct zpool_driver z3fold_zpool_driver = {
	.type =		"z3fold",
	.owner =	THIS_MODULE,
	.create =	z3fold_zpool_create,
	.destroy =	z3fold_zpool_destroy,
	.malloc =	z3fold_zpool_malloc,
	.free =		z3fold_zpool_free,
	.shrink =	z3fold_zpool_shrink,
	.map =		z3fold_zpool_map,
	.unmap =	z3fold_zpool_unmap,
	.total_size =	z3fold_zpool_total_size,
};

MODULE_ALIAS("zpool-z3fold");

static int __init init_z3fold(void)
{
	int ret;

	/* Make sure the z3fold header is not larger than the page size */
	BUILD_BUG_ON(ZHDR_SIZE_ALIGNED > PAGE_SIZE);
	ret = z3fold_mount();
	if (ret)
		return ret;

	zpool_register_driver(&z3fold_zpool_driver);

	return 0;
}

static void __exit exit_z3fold(void)
{
	z3fold_unmount();
	zpool_unregister_driver(&z3fold_zpool_driver);
}

module_init(init_z3fold);
module_exit(exit_z3fold);

MODULE_LICENSE("GPL");
MODULE_AUTHOR("Vitaly Wool <vitalywool@gmail.com>");
MODULE_DESCRIPTION("3-Fold Allocator for Compressed Pages");