summaryrefslogtreecommitdiff
path: root/fs/erofs/zdata.c
blob: 5200bb86e2643c3b5432926823f610a46531ef53 (plain)
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
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Copyright (C) 2018 HUAWEI, Inc.
 *             https://www.huawei.com/
 * Copyright (C) 2022 Alibaba Cloud
 */
#include "zdata.h"
#include "compress.h"
#include <linux/prefetch.h>
#include <linux/psi.h>

#include <trace/events/erofs.h>

/*
 * since pclustersize is variable for big pcluster feature, introduce slab
 * pools implementation for different pcluster sizes.
 */
struct z_erofs_pcluster_slab {
	struct kmem_cache *slab;
	unsigned int maxpages;
	char name[48];
};

#define _PCLP(n) { .maxpages = n }

static struct z_erofs_pcluster_slab pcluster_pool[] __read_mostly = {
	_PCLP(1), _PCLP(4), _PCLP(16), _PCLP(64), _PCLP(128),
	_PCLP(Z_EROFS_PCLUSTER_MAX_PAGES)
};

struct z_erofs_bvec_iter {
	struct page *bvpage;
	struct z_erofs_bvset *bvset;
	unsigned int nr, cur;
};

static struct page *z_erofs_bvec_iter_end(struct z_erofs_bvec_iter *iter)
{
	if (iter->bvpage)
		kunmap_local(iter->bvset);
	return iter->bvpage;
}

static struct page *z_erofs_bvset_flip(struct z_erofs_bvec_iter *iter)
{
	unsigned long base = (unsigned long)((struct z_erofs_bvset *)0)->bvec;
	/* have to access nextpage in advance, otherwise it will be unmapped */
	struct page *nextpage = iter->bvset->nextpage;
	struct page *oldpage;

	DBG_BUGON(!nextpage);
	oldpage = z_erofs_bvec_iter_end(iter);
	iter->bvpage = nextpage;
	iter->bvset = kmap_local_page(nextpage);
	iter->nr = (PAGE_SIZE - base) / sizeof(struct z_erofs_bvec);
	iter->cur = 0;
	return oldpage;
}

static void z_erofs_bvec_iter_begin(struct z_erofs_bvec_iter *iter,
				    struct z_erofs_bvset_inline *bvset,
				    unsigned int bootstrap_nr,
				    unsigned int cur)
{
	*iter = (struct z_erofs_bvec_iter) {
		.nr = bootstrap_nr,
		.bvset = (struct z_erofs_bvset *)bvset,
	};

	while (cur > iter->nr) {
		cur -= iter->nr;
		z_erofs_bvset_flip(iter);
	}
	iter->cur = cur;
}

static int z_erofs_bvec_enqueue(struct z_erofs_bvec_iter *iter,
				struct z_erofs_bvec *bvec,
				struct page **candidate_bvpage)
{
	if (iter->cur == iter->nr) {
		if (!*candidate_bvpage)
			return -EAGAIN;

		DBG_BUGON(iter->bvset->nextpage);
		iter->bvset->nextpage = *candidate_bvpage;
		z_erofs_bvset_flip(iter);

		iter->bvset->nextpage = NULL;
		*candidate_bvpage = NULL;
	}
	iter->bvset->bvec[iter->cur++] = *bvec;
	return 0;
}

static void z_erofs_bvec_dequeue(struct z_erofs_bvec_iter *iter,
				 struct z_erofs_bvec *bvec,
				 struct page **old_bvpage)
{
	if (iter->cur == iter->nr)
		*old_bvpage = z_erofs_bvset_flip(iter);
	else
		*old_bvpage = NULL;
	*bvec = iter->bvset->bvec[iter->cur++];
}

static void z_erofs_destroy_pcluster_pool(void)
{
	int i;

	for (i = 0; i < ARRAY_SIZE(pcluster_pool); ++i) {
		if (!pcluster_pool[i].slab)
			continue;
		kmem_cache_destroy(pcluster_pool[i].slab);
		pcluster_pool[i].slab = NULL;
	}
}

static int z_erofs_create_pcluster_pool(void)
{
	struct z_erofs_pcluster_slab *pcs;
	struct z_erofs_pcluster *a;
	unsigned int size;

	for (pcs = pcluster_pool;
	     pcs < pcluster_pool + ARRAY_SIZE(pcluster_pool); ++pcs) {
		size = struct_size(a, compressed_bvecs, pcs->maxpages);

		sprintf(pcs->name, "erofs_pcluster-%u", pcs->maxpages);
		pcs->slab = kmem_cache_create(pcs->name, size, 0,
					      SLAB_RECLAIM_ACCOUNT, NULL);
		if (pcs->slab)
			continue;

		z_erofs_destroy_pcluster_pool();
		return -ENOMEM;
	}
	return 0;
}

static struct z_erofs_pcluster *z_erofs_alloc_pcluster(unsigned int nrpages)
{
	int i;

	for (i = 0; i < ARRAY_SIZE(pcluster_pool); ++i) {
		struct z_erofs_pcluster_slab *pcs = pcluster_pool + i;
		struct z_erofs_pcluster *pcl;

		if (nrpages > pcs->maxpages)
			continue;

		pcl = kmem_cache_zalloc(pcs->slab, GFP_NOFS);
		if (!pcl)
			return ERR_PTR(-ENOMEM);
		pcl->pclusterpages = nrpages;
		return pcl;
	}
	return ERR_PTR(-EINVAL);
}

static void z_erofs_free_pcluster(struct z_erofs_pcluster *pcl)
{
	unsigned int pclusterpages = z_erofs_pclusterpages(pcl);
	int i;

	for (i = 0; i < ARRAY_SIZE(pcluster_pool); ++i) {
		struct z_erofs_pcluster_slab *pcs = pcluster_pool + i;

		if (pclusterpages > pcs->maxpages)
			continue;

		kmem_cache_free(pcs->slab, pcl);
		return;
	}
	DBG_BUGON(1);
}

/*
 * tagged pointer with 1-bit tag for all compressed pages
 * tag 0 - the page is just found with an extra page reference
 */
typedef tagptr1_t compressed_page_t;

#define tag_compressed_page_justfound(page) \
	tagptr_fold(compressed_page_t, page, 1)

static struct workqueue_struct *z_erofs_workqueue __read_mostly;

void z_erofs_exit_zip_subsystem(void)
{
	destroy_workqueue(z_erofs_workqueue);
	z_erofs_destroy_pcluster_pool();
}

static inline int z_erofs_init_workqueue(void)
{
	const unsigned int onlinecpus = num_possible_cpus();

	/*
	 * no need to spawn too many threads, limiting threads could minimum
	 * scheduling overhead, perhaps per-CPU threads should be better?
	 */
	z_erofs_workqueue = alloc_workqueue("erofs_unzipd",
					    WQ_UNBOUND | WQ_HIGHPRI,
					    onlinecpus + onlinecpus / 4);
	return z_erofs_workqueue ? 0 : -ENOMEM;
}

int __init z_erofs_init_zip_subsystem(void)
{
	int err = z_erofs_create_pcluster_pool();

	if (err)
		return err;
	err = z_erofs_init_workqueue();
	if (err)
		z_erofs_destroy_pcluster_pool();
	return err;
}

enum z_erofs_pclustermode {
	Z_EROFS_PCLUSTER_INFLIGHT,
	/*
	 * The current pclusters was the tail of an exist chain, in addition
	 * that the previous processed chained pclusters are all decided to
	 * be hooked up to it.
	 * A new chain will be created for the remaining pclusters which are
	 * not processed yet, so different from Z_EROFS_PCLUSTER_FOLLOWED,
	 * the next pcluster cannot reuse the whole page safely for inplace I/O
	 * in the following scenario:
	 *  ________________________________________________________________
	 * |      tail (partial) page     |       head (partial) page       |
	 * |   (belongs to the next pcl)  |   (belongs to the current pcl)  |
	 * |_______PCLUSTER_FOLLOWED______|________PCLUSTER_HOOKED__________|
	 */
	Z_EROFS_PCLUSTER_HOOKED,
	/*
	 * a weak form of Z_EROFS_PCLUSTER_FOLLOWED, the difference is that it
	 * could be dispatched into bypass queue later due to uptodated managed
	 * pages. All related online pages cannot be reused for inplace I/O (or
	 * bvpage) since it can be directly decoded without I/O submission.
	 */
	Z_EROFS_PCLUSTER_FOLLOWED_NOINPLACE,
	/*
	 * The current collection has been linked with the owned chain, and
	 * could also be linked with the remaining collections, which means
	 * if the processing page is the tail page of the collection, thus
	 * the current collection can safely use the whole page (since
	 * the previous collection is under control) for in-place I/O, as
	 * illustrated below:
	 *  ________________________________________________________________
	 * |  tail (partial) page |          head (partial) page           |
	 * |  (of the current cl) |      (of the previous collection)      |
	 * | PCLUSTER_FOLLOWED or |                                        |
	 * |_____PCLUSTER_HOOKED__|___________PCLUSTER_FOLLOWED____________|
	 *
	 * [  (*) the above page can be used as inplace I/O.               ]
	 */
	Z_EROFS_PCLUSTER_FOLLOWED,
};

struct z_erofs_decompress_frontend {
	struct inode *const inode;
	struct erofs_map_blocks map;
	struct z_erofs_bvec_iter biter;

	struct page *candidate_bvpage;
	struct z_erofs_pcluster *pcl, *tailpcl;
	z_erofs_next_pcluster_t owned_head;
	enum z_erofs_pclustermode mode;

	bool readahead;
	/* used for applying cache strategy on the fly */
	bool backmost;
	erofs_off_t headoffset;

	/* a pointer used to pick up inplace I/O pages */
	unsigned int icur;
};

#define DECOMPRESS_FRONTEND_INIT(__i) { \
	.inode = __i, .owned_head = Z_EROFS_PCLUSTER_TAIL, \
	.mode = Z_EROFS_PCLUSTER_FOLLOWED, .backmost = true }

static bool z_erofs_should_alloc_cache(struct z_erofs_decompress_frontend *fe)
{
	unsigned int cachestrategy = EROFS_I_SB(fe->inode)->opt.cache_strategy;

	if (cachestrategy <= EROFS_ZIP_CACHE_DISABLED)
		return false;

	if (fe->backmost)
		return true;

	if (cachestrategy >= EROFS_ZIP_CACHE_READAROUND &&
	    fe->map.m_la < fe->headoffset)
		return true;

	return false;
}

static void z_erofs_bind_cache(struct z_erofs_decompress_frontend *fe,
			       struct page **pagepool)
{
	struct address_space *mc = MNGD_MAPPING(EROFS_I_SB(fe->inode));
	struct z_erofs_pcluster *pcl = fe->pcl;
	bool shouldalloc = z_erofs_should_alloc_cache(fe);
	bool standalone = true;
	/*
	 * optimistic allocation without direct reclaim since inplace I/O
	 * can be used if low memory otherwise.
	 */
	gfp_t gfp = (mapping_gfp_mask(mc) & ~__GFP_DIRECT_RECLAIM) |
			__GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN;
	unsigned int i;

	if (fe->mode < Z_EROFS_PCLUSTER_FOLLOWED)
		return;

	for (i = 0; i < pcl->pclusterpages; ++i) {
		struct page *page;
		compressed_page_t t;
		struct page *newpage = NULL;

		/* the compressed page was loaded before */
		if (READ_ONCE(pcl->compressed_bvecs[i].page))
			continue;

		page = find_get_page(mc, pcl->obj.index + i);

		if (page) {
			t = tag_compressed_page_justfound(page);
		} else {
			/* I/O is needed, no possible to decompress directly */
			standalone = false;
			if (!shouldalloc)
				continue;

			/*
			 * try to use cached I/O if page allocation
			 * succeeds or fallback to in-place I/O instead
			 * to avoid any direct reclaim.
			 */
			newpage = erofs_allocpage(pagepool, gfp);
			if (!newpage)
				continue;
			set_page_private(newpage, Z_EROFS_PREALLOCATED_PAGE);
			t = tag_compressed_page_justfound(newpage);
		}

		if (!cmpxchg_relaxed(&pcl->compressed_bvecs[i].page, NULL,
				     tagptr_cast_ptr(t)))
			continue;

		if (page)
			put_page(page);
		else if (newpage)
			erofs_pagepool_add(pagepool, newpage);
	}

	/*
	 * don't do inplace I/O if all compressed pages are available in
	 * managed cache since it can be moved to the bypass queue instead.
	 */
	if (standalone)
		fe->mode = Z_EROFS_PCLUSTER_FOLLOWED_NOINPLACE;
}

/* called by erofs_shrinker to get rid of all compressed_pages */
int erofs_try_to_free_all_cached_pages(struct erofs_sb_info *sbi,
				       struct erofs_workgroup *grp)
{
	struct z_erofs_pcluster *const pcl =
		container_of(grp, struct z_erofs_pcluster, obj);
	int i;

	DBG_BUGON(z_erofs_is_inline_pcluster(pcl));
	/*
	 * refcount of workgroup is now freezed as 1,
	 * therefore no need to worry about available decompression users.
	 */
	for (i = 0; i < pcl->pclusterpages; ++i) {
		struct page *page = pcl->compressed_bvecs[i].page;

		if (!page)
			continue;

		/* block other users from reclaiming or migrating the page */
		if (!trylock_page(page))
			return -EBUSY;

		if (!erofs_page_is_managed(sbi, page))
			continue;

		/* barrier is implied in the following 'unlock_page' */
		WRITE_ONCE(pcl->compressed_bvecs[i].page, NULL);
		detach_page_private(page);
		unlock_page(page);
	}
	return 0;
}

int erofs_try_to_free_cached_page(struct page *page)
{
	struct z_erofs_pcluster *const pcl = (void *)page_private(page);
	int ret, i;

	if (!erofs_workgroup_try_to_freeze(&pcl->obj, 1))
		return 0;

	ret = 0;
	DBG_BUGON(z_erofs_is_inline_pcluster(pcl));
	for (i = 0; i < pcl->pclusterpages; ++i) {
		if (pcl->compressed_bvecs[i].page == page) {
			WRITE_ONCE(pcl->compressed_bvecs[i].page, NULL);
			ret = 1;
			break;
		}
	}
	erofs_workgroup_unfreeze(&pcl->obj, 1);
	if (ret)
		detach_page_private(page);
	return ret;
}

static bool z_erofs_try_inplace_io(struct z_erofs_decompress_frontend *fe,
				   struct z_erofs_bvec *bvec)
{
	struct z_erofs_pcluster *const pcl = fe->pcl;

	while (fe->icur > 0) {
		if (!cmpxchg(&pcl->compressed_bvecs[--fe->icur].page,
			     NULL, bvec->page)) {
			pcl->compressed_bvecs[fe->icur] = *bvec;
			return true;
		}
	}
	return false;
}

/* callers must be with pcluster lock held */
static int z_erofs_attach_page(struct z_erofs_decompress_frontend *fe,
			       struct z_erofs_bvec *bvec, bool exclusive)
{
	int ret;

	if (exclusive) {
		/* give priority for inplaceio to use file pages first */
		if (z_erofs_try_inplace_io(fe, bvec))
			return 0;
		/* otherwise, check if it can be used as a bvpage */
		if (fe->mode >= Z_EROFS_PCLUSTER_FOLLOWED &&
		    !fe->candidate_bvpage)
			fe->candidate_bvpage = bvec->page;
	}
	ret = z_erofs_bvec_enqueue(&fe->biter, bvec, &fe->candidate_bvpage);
	fe->pcl->vcnt += (ret >= 0);
	return ret;
}

static void z_erofs_try_to_claim_pcluster(struct z_erofs_decompress_frontend *f)
{
	struct z_erofs_pcluster *pcl = f->pcl;
	z_erofs_next_pcluster_t *owned_head = &f->owned_head;

	/* type 1, nil pcluster (this pcluster doesn't belong to any chain.) */
	if (cmpxchg(&pcl->next, Z_EROFS_PCLUSTER_NIL,
		    *owned_head) == Z_EROFS_PCLUSTER_NIL) {
		*owned_head = &pcl->next;
		/* so we can attach this pcluster to our submission chain. */
		f->mode = Z_EROFS_PCLUSTER_FOLLOWED;
		return;
	}

	/*
	 * type 2, link to the end of an existing open chain, be careful
	 * that its submission is controlled by the original attached chain.
	 */
	if (*owned_head != &pcl->next && pcl != f->tailpcl &&
	    cmpxchg(&pcl->next, Z_EROFS_PCLUSTER_TAIL,
		    *owned_head) == Z_EROFS_PCLUSTER_TAIL) {
		*owned_head = Z_EROFS_PCLUSTER_TAIL;
		f->mode = Z_EROFS_PCLUSTER_HOOKED;
		f->tailpcl = NULL;
		return;
	}
	/* type 3, it belongs to a chain, but it isn't the end of the chain */
	f->mode = Z_EROFS_PCLUSTER_INFLIGHT;
}

static int z_erofs_register_pcluster(struct z_erofs_decompress_frontend *fe)
{
	struct erofs_map_blocks *map = &fe->map;
	bool ztailpacking = map->m_flags & EROFS_MAP_META;
	struct z_erofs_pcluster *pcl;
	struct erofs_workgroup *grp;
	int err;

	if (!(map->m_flags & EROFS_MAP_ENCODED) ||
	    (!ztailpacking && !(map->m_pa >> PAGE_SHIFT))) {
		DBG_BUGON(1);
		return -EFSCORRUPTED;
	}

	/* no available pcluster, let's allocate one */
	pcl = z_erofs_alloc_pcluster(ztailpacking ? 1 :
				     map->m_plen >> PAGE_SHIFT);
	if (IS_ERR(pcl))
		return PTR_ERR(pcl);

	atomic_set(&pcl->obj.refcount, 1);
	pcl->algorithmformat = map->m_algorithmformat;
	pcl->length = 0;
	pcl->partial = true;

	/* new pclusters should be claimed as type 1, primary and followed */
	pcl->next = fe->owned_head;
	pcl->pageofs_out = map->m_la & ~PAGE_MASK;
	fe->mode = Z_EROFS_PCLUSTER_FOLLOWED;

	/*
	 * lock all primary followed works before visible to others
	 * and mutex_trylock *never* fails for a new pcluster.
	 */
	mutex_init(&pcl->lock);
	DBG_BUGON(!mutex_trylock(&pcl->lock));

	if (ztailpacking) {
		pcl->obj.index = 0;	/* which indicates ztailpacking */
		pcl->pageofs_in = erofs_blkoff(map->m_pa);
		pcl->tailpacking_size = map->m_plen;
	} else {
		pcl->obj.index = map->m_pa >> PAGE_SHIFT;

		grp = erofs_insert_workgroup(fe->inode->i_sb, &pcl->obj);
		if (IS_ERR(grp)) {
			err = PTR_ERR(grp);
			goto err_out;
		}

		if (grp != &pcl->obj) {
			fe->pcl = container_of(grp,
					struct z_erofs_pcluster, obj);
			err = -EEXIST;
			goto err_out;
		}
	}
	/* used to check tail merging loop due to corrupted images */
	if (fe->owned_head == Z_EROFS_PCLUSTER_TAIL)
		fe->tailpcl = pcl;
	fe->owned_head = &pcl->next;
	fe->pcl = pcl;
	return 0;

err_out:
	mutex_unlock(&pcl->lock);
	z_erofs_free_pcluster(pcl);
	return err;
}

static int z_erofs_collector_begin(struct z_erofs_decompress_frontend *fe)
{
	struct erofs_map_blocks *map = &fe->map;
	struct erofs_workgroup *grp = NULL;
	int ret;

	DBG_BUGON(fe->pcl);

	/* must be Z_EROFS_PCLUSTER_TAIL or pointed to previous pcluster */
	DBG_BUGON(fe->owned_head == Z_EROFS_PCLUSTER_NIL);
	DBG_BUGON(fe->owned_head == Z_EROFS_PCLUSTER_TAIL_CLOSED);

	if (!(map->m_flags & EROFS_MAP_META)) {
		grp = erofs_find_workgroup(fe->inode->i_sb,
					   map->m_pa >> PAGE_SHIFT);
	} else if ((map->m_pa & ~PAGE_MASK) + map->m_plen > PAGE_SIZE) {
		DBG_BUGON(1);
		return -EFSCORRUPTED;
	}

	if (grp) {
		fe->pcl = container_of(grp, struct z_erofs_pcluster, obj);
		ret = -EEXIST;
	} else {
		ret = z_erofs_register_pcluster(fe);
	}

	if (ret == -EEXIST) {
		mutex_lock(&fe->pcl->lock);
		/* used to check tail merging loop due to corrupted images */
		if (fe->owned_head == Z_EROFS_PCLUSTER_TAIL)
			fe->tailpcl = fe->pcl;

		z_erofs_try_to_claim_pcluster(fe);
	} else if (ret) {
		return ret;
	}
	z_erofs_bvec_iter_begin(&fe->biter, &fe->pcl->bvset,
				Z_EROFS_INLINE_BVECS, fe->pcl->vcnt);
	/* since file-backed online pages are traversed in reverse order */
	fe->icur = z_erofs_pclusterpages(fe->pcl);
	return 0;
}

/*
 * keep in mind that no referenced pclusters will be freed
 * only after a RCU grace period.
 */
static void z_erofs_rcu_callback(struct rcu_head *head)
{
	z_erofs_free_pcluster(container_of(head,
			struct z_erofs_pcluster, rcu));
}

void erofs_workgroup_free_rcu(struct erofs_workgroup *grp)
{
	struct z_erofs_pcluster *const pcl =
		container_of(grp, struct z_erofs_pcluster, obj);

	call_rcu(&pcl->rcu, z_erofs_rcu_callback);
}

static bool z_erofs_collector_end(struct z_erofs_decompress_frontend *fe)
{
	struct z_erofs_pcluster *pcl = fe->pcl;

	if (!pcl)
		return false;

	z_erofs_bvec_iter_end(&fe->biter);
	mutex_unlock(&pcl->lock);

	if (fe->candidate_bvpage) {
		DBG_BUGON(z_erofs_is_shortlived_page(fe->candidate_bvpage));
		fe->candidate_bvpage = NULL;
	}

	/*
	 * if all pending pages are added, don't hold its reference
	 * any longer if the pcluster isn't hosted by ourselves.
	 */
	if (fe->mode < Z_EROFS_PCLUSTER_FOLLOWED_NOINPLACE)
		erofs_workgroup_put(&pcl->obj);

	fe->pcl = NULL;
	return true;
}

static int z_erofs_read_fragment(struct inode *inode, erofs_off_t pos,
				 struct page *page, unsigned int pageofs,
				 unsigned int len)
{
	struct inode *packed_inode = EROFS_I_SB(inode)->packed_inode;
	struct erofs_buf buf = __EROFS_BUF_INITIALIZER;
	u8 *src, *dst;
	unsigned int i, cnt;

	if (!packed_inode)
		return -EFSCORRUPTED;

	pos += EROFS_I(inode)->z_fragmentoff;
	for (i = 0; i < len; i += cnt) {
		cnt = min_t(unsigned int, len - i,
			    EROFS_BLKSIZ - erofs_blkoff(pos));
		src = erofs_bread(&buf, packed_inode,
				  erofs_blknr(pos), EROFS_KMAP);
		if (IS_ERR(src)) {
			erofs_put_metabuf(&buf);
			return PTR_ERR(src);
		}

		dst = kmap_local_page(page);
		memcpy(dst + pageofs + i, src + erofs_blkoff(pos), cnt);
		kunmap_local(dst);
		pos += cnt;
	}
	erofs_put_metabuf(&buf);
	return 0;
}

static int z_erofs_do_read_page(struct z_erofs_decompress_frontend *fe,
				struct page *page, struct page **pagepool)
{
	struct inode *const inode = fe->inode;
	struct erofs_map_blocks *const map = &fe->map;
	const loff_t offset = page_offset(page);
	bool tight = true, exclusive;
	unsigned int cur, end, spiltted;
	int err = 0;

	/* register locked file pages as online pages in pack */
	z_erofs_onlinepage_init(page);

	spiltted = 0;
	end = PAGE_SIZE;
repeat:
	cur = end - 1;

	if (offset + cur < map->m_la ||
	    offset + cur >= map->m_la + map->m_llen) {
		erofs_dbg("out-of-range map @ pos %llu", offset + cur);

		if (z_erofs_collector_end(fe))
			fe->backmost = false;
		map->m_la = offset + cur;
		map->m_llen = 0;
		err = z_erofs_map_blocks_iter(inode, map, 0);
		if (err)
			goto out;
	} else {
		if (fe->pcl)
			goto hitted;
		/* didn't get a valid pcluster previously (very rare) */
	}

	if (!(map->m_flags & EROFS_MAP_MAPPED) ||
	    map->m_flags & EROFS_MAP_FRAGMENT)
		goto hitted;

	err = z_erofs_collector_begin(fe);
	if (err)
		goto out;

	if (z_erofs_is_inline_pcluster(fe->pcl)) {
		void *mp;

		mp = erofs_read_metabuf(&fe->map.buf, inode->i_sb,
					erofs_blknr(map->m_pa), EROFS_NO_KMAP);
		if (IS_ERR(mp)) {
			err = PTR_ERR(mp);
			erofs_err(inode->i_sb,
				  "failed to get inline page, err %d", err);
			goto out;
		}
		get_page(fe->map.buf.page);
		WRITE_ONCE(fe->pcl->compressed_bvecs[0].page,
			   fe->map.buf.page);
		fe->mode = Z_EROFS_PCLUSTER_FOLLOWED_NOINPLACE;
	} else {
		/* bind cache first when cached decompression is preferred */
		z_erofs_bind_cache(fe, pagepool);
	}
hitted:
	/*
	 * Ensure the current partial page belongs to this submit chain rather
	 * than other concurrent submit chains or the noio(bypass) chain since
	 * those chains are handled asynchronously thus the page cannot be used
	 * for inplace I/O or bvpage (should be processed in a strict order.)
	 */
	tight &= (fe->mode >= Z_EROFS_PCLUSTER_HOOKED &&
		  fe->mode != Z_EROFS_PCLUSTER_FOLLOWED_NOINPLACE);

	cur = end - min_t(unsigned int, offset + end - map->m_la, end);
	if (!(map->m_flags & EROFS_MAP_MAPPED)) {
		zero_user_segment(page, cur, end);
		goto next_part;
	}
	if (map->m_flags & EROFS_MAP_FRAGMENT) {
		unsigned int pageofs, skip, len;

		if (offset > map->m_la) {
			pageofs = 0;
			skip = offset - map->m_la;
		} else {
			pageofs = map->m_la & ~PAGE_MASK;
			skip = 0;
		}
		len = min_t(unsigned int, map->m_llen - skip, end - cur);
		err = z_erofs_read_fragment(inode, skip, page, pageofs, len);
		if (err)
			goto out;
		++spiltted;
		tight = false;
		goto next_part;
	}

	exclusive = (!cur && (!spiltted || tight));
	if (cur)
		tight &= (fe->mode >= Z_EROFS_PCLUSTER_FOLLOWED);

retry:
	err = z_erofs_attach_page(fe, &((struct z_erofs_bvec) {
					.page = page,
					.offset = offset - map->m_la,
					.end = end,
				  }), exclusive);
	/* should allocate an additional short-lived page for bvset */
	if (err == -EAGAIN && !fe->candidate_bvpage) {
		fe->candidate_bvpage = alloc_page(GFP_NOFS | __GFP_NOFAIL);
		set_page_private(fe->candidate_bvpage,
				 Z_EROFS_SHORTLIVED_PAGE);
		goto retry;
	}

	if (err) {
		DBG_BUGON(err == -EAGAIN && fe->candidate_bvpage);
		goto out;
	}

	z_erofs_onlinepage_split(page);
	/* bump up the number of spiltted parts of a page */
	++spiltted;
	if (fe->pcl->pageofs_out != (map->m_la & ~PAGE_MASK))
		fe->pcl->multibases = true;
	if (fe->pcl->length < offset + end - map->m_la) {
		fe->pcl->length = offset + end - map->m_la;
		fe->pcl->pageofs_out = map->m_la & ~PAGE_MASK;
	}
	if ((map->m_flags & EROFS_MAP_FULL_MAPPED) &&
	    !(map->m_flags & EROFS_MAP_PARTIAL_REF) &&
	    fe->pcl->length == map->m_llen)
		fe->pcl->partial = false;
next_part:
	/* shorten the remaining extent to update progress */
	map->m_llen = offset + cur - map->m_la;
	map->m_flags &= ~EROFS_MAP_FULL_MAPPED;

	end = cur;
	if (end > 0)
		goto repeat;

out:
	if (err)
		z_erofs_page_mark_eio(page);
	z_erofs_onlinepage_endio(page);

	erofs_dbg("%s, finish page: %pK spiltted: %u map->m_llen %llu",
		  __func__, page, spiltted, map->m_llen);
	return err;
}

static bool z_erofs_get_sync_decompress_policy(struct erofs_sb_info *sbi,
				       unsigned int readahead_pages)
{
	/* auto: enable for read_folio, disable for readahead */
	if ((sbi->opt.sync_decompress == EROFS_SYNC_DECOMPRESS_AUTO) &&
	    !readahead_pages)
		return true;

	if ((sbi->opt.sync_decompress == EROFS_SYNC_DECOMPRESS_FORCE_ON) &&
	    (readahead_pages <= sbi->opt.max_sync_decompress_pages))
		return true;

	return false;
}

static bool z_erofs_page_is_invalidated(struct page *page)
{
	return !page->mapping && !z_erofs_is_shortlived_page(page);
}

struct z_erofs_decompress_backend {
	struct page *onstack_pages[Z_EROFS_ONSTACK_PAGES];
	struct super_block *sb;
	struct z_erofs_pcluster *pcl;

	/* pages with the longest decompressed length for deduplication */
	struct page **decompressed_pages;
	/* pages to keep the compressed data */
	struct page **compressed_pages;

	struct list_head decompressed_secondary_bvecs;
	struct page **pagepool;
	unsigned int onstack_used, nr_pages;
};

struct z_erofs_bvec_item {
	struct z_erofs_bvec bvec;
	struct list_head list;
};

static void z_erofs_do_decompressed_bvec(struct z_erofs_decompress_backend *be,
					 struct z_erofs_bvec *bvec)
{
	struct z_erofs_bvec_item *item;

	if (!((bvec->offset + be->pcl->pageofs_out) & ~PAGE_MASK)) {
		unsigned int pgnr;

		pgnr = (bvec->offset + be->pcl->pageofs_out) >> PAGE_SHIFT;
		DBG_BUGON(pgnr >= be->nr_pages);
		if (!be->decompressed_pages[pgnr]) {
			be->decompressed_pages[pgnr] = bvec->page;
			return;
		}
	}

	/* (cold path) one pcluster is requested multiple times */
	item = kmalloc(sizeof(*item), GFP_KERNEL | __GFP_NOFAIL);
	item->bvec = *bvec;
	list_add(&item->list, &be->decompressed_secondary_bvecs);
}

static void z_erofs_fill_other_copies(struct z_erofs_decompress_backend *be,
				      int err)
{
	unsigned int off0 = be->pcl->pageofs_out;
	struct list_head *p, *n;

	list_for_each_safe(p, n, &be->decompressed_secondary_bvecs) {
		struct z_erofs_bvec_item *bvi;
		unsigned int end, cur;
		void *dst, *src;

		bvi = container_of(p, struct z_erofs_bvec_item, list);
		cur = bvi->bvec.offset < 0 ? -bvi->bvec.offset : 0;
		end = min_t(unsigned int, be->pcl->length - bvi->bvec.offset,
			    bvi->bvec.end);
		dst = kmap_local_page(bvi->bvec.page);
		while (cur < end) {
			unsigned int pgnr, scur, len;

			pgnr = (bvi->bvec.offset + cur + off0) >> PAGE_SHIFT;
			DBG_BUGON(pgnr >= be->nr_pages);

			scur = bvi->bvec.offset + cur -
					((pgnr << PAGE_SHIFT) - off0);
			len = min_t(unsigned int, end - cur, PAGE_SIZE - scur);
			if (!be->decompressed_pages[pgnr]) {
				err = -EFSCORRUPTED;
				cur += len;
				continue;
			}
			src = kmap_local_page(be->decompressed_pages[pgnr]);
			memcpy(dst + cur, src + scur, len);
			kunmap_local(src);
			cur += len;
		}
		kunmap_local(dst);
		if (err)
			z_erofs_page_mark_eio(bvi->bvec.page);
		z_erofs_onlinepage_endio(bvi->bvec.page);
		list_del(p);
		kfree(bvi);
	}
}

static void z_erofs_parse_out_bvecs(struct z_erofs_decompress_backend *be)
{
	struct z_erofs_pcluster *pcl = be->pcl;
	struct z_erofs_bvec_iter biter;
	struct page *old_bvpage;
	int i;

	z_erofs_bvec_iter_begin(&biter, &pcl->bvset, Z_EROFS_INLINE_BVECS, 0);
	for (i = 0; i < pcl->vcnt; ++i) {
		struct z_erofs_bvec bvec;

		z_erofs_bvec_dequeue(&biter, &bvec, &old_bvpage);

		if (old_bvpage)
			z_erofs_put_shortlivedpage(be->pagepool, old_bvpage);

		DBG_BUGON(z_erofs_page_is_invalidated(bvec.page));
		z_erofs_do_decompressed_bvec(be, &bvec);
	}

	old_bvpage = z_erofs_bvec_iter_end(&biter);
	if (old_bvpage)
		z_erofs_put_shortlivedpage(be->pagepool, old_bvpage);
}

static int z_erofs_parse_in_bvecs(struct z_erofs_decompress_backend *be,
				  bool *overlapped)
{
	struct z_erofs_pcluster *pcl = be->pcl;
	unsigned int pclusterpages = z_erofs_pclusterpages(pcl);
	int i, err = 0;

	*overlapped = false;
	for (i = 0; i < pclusterpages; ++i) {
		struct z_erofs_bvec *bvec = &pcl->compressed_bvecs[i];
		struct page *page = bvec->page;

		/* compressed pages ought to be present before decompressing */
		if (!page) {
			DBG_BUGON(1);
			continue;
		}
		be->compressed_pages[i] = page;

		if (z_erofs_is_inline_pcluster(pcl)) {
			if (!PageUptodate(page))
				err = -EIO;
			continue;
		}

		DBG_BUGON(z_erofs_page_is_invalidated(page));
		if (!z_erofs_is_shortlived_page(page)) {
			if (erofs_page_is_managed(EROFS_SB(be->sb), page)) {
				if (!PageUptodate(page))
					err = -EIO;
				continue;
			}
			z_erofs_do_decompressed_bvec(be, bvec);
			*overlapped = true;
		}
	}

	if (err)
		return err;
	return 0;
}

static int z_erofs_decompress_pcluster(struct z_erofs_decompress_backend *be,
				       int err)
{
	struct erofs_sb_info *const sbi = EROFS_SB(be->sb);
	struct z_erofs_pcluster *pcl = be->pcl;
	unsigned int pclusterpages = z_erofs_pclusterpages(pcl);
	unsigned int i, inputsize;
	int err2;
	struct page *page;
	bool overlapped;

	mutex_lock(&pcl->lock);
	be->nr_pages = PAGE_ALIGN(pcl->length + pcl->pageofs_out) >> PAGE_SHIFT;

	/* allocate (de)compressed page arrays if cannot be kept on stack */
	be->decompressed_pages = NULL;
	be->compressed_pages = NULL;
	be->onstack_used = 0;
	if (be->nr_pages <= Z_EROFS_ONSTACK_PAGES) {
		be->decompressed_pages = be->onstack_pages;
		be->onstack_used = be->nr_pages;
		memset(be->decompressed_pages, 0,
		       sizeof(struct page *) * be->nr_pages);
	}

	if (pclusterpages + be->onstack_used <= Z_EROFS_ONSTACK_PAGES)
		be->compressed_pages = be->onstack_pages + be->onstack_used;

	if (!be->decompressed_pages)
		be->decompressed_pages =
			kcalloc(be->nr_pages, sizeof(struct page *),
				GFP_KERNEL | __GFP_NOFAIL);
	if (!be->compressed_pages)
		be->compressed_pages =
			kcalloc(pclusterpages, sizeof(struct page *),
				GFP_KERNEL | __GFP_NOFAIL);

	z_erofs_parse_out_bvecs(be);
	err2 = z_erofs_parse_in_bvecs(be, &overlapped);
	if (err2)
		err = err2;
	if (err)
		goto out;

	if (z_erofs_is_inline_pcluster(pcl))
		inputsize = pcl->tailpacking_size;
	else
		inputsize = pclusterpages * PAGE_SIZE;

	err = z_erofs_decompress(&(struct z_erofs_decompress_req) {
					.sb = be->sb,
					.in = be->compressed_pages,
					.out = be->decompressed_pages,
					.pageofs_in = pcl->pageofs_in,
					.pageofs_out = pcl->pageofs_out,
					.inputsize = inputsize,
					.outputsize = pcl->length,
					.alg = pcl->algorithmformat,
					.inplace_io = overlapped,
					.partial_decoding = pcl->partial,
					.fillgaps = pcl->multibases,
				 }, be->pagepool);

out:
	/* must handle all compressed pages before actual file pages */
	if (z_erofs_is_inline_pcluster(pcl)) {
		page = pcl->compressed_bvecs[0].page;
		WRITE_ONCE(pcl->compressed_bvecs[0].page, NULL);
		put_page(page);
	} else {
		for (i = 0; i < pclusterpages; ++i) {
			page = pcl->compressed_bvecs[i].page;

			if (erofs_page_is_managed(sbi, page))
				continue;

			/* recycle all individual short-lived pages */
			(void)z_erofs_put_shortlivedpage(be->pagepool, page);
			WRITE_ONCE(pcl->compressed_bvecs[i].page, NULL);
		}
	}
	if (be->compressed_pages < be->onstack_pages ||
	    be->compressed_pages >= be->onstack_pages + Z_EROFS_ONSTACK_PAGES)
		kfree(be->compressed_pages);
	z_erofs_fill_other_copies(be, err);

	for (i = 0; i < be->nr_pages; ++i) {
		page = be->decompressed_pages[i];
		if (!page)
			continue;

		DBG_BUGON(z_erofs_page_is_invalidated(page));

		/* recycle all individual short-lived pages */
		if (z_erofs_put_shortlivedpage(be->pagepool, page))
			continue;
		if (err)
			z_erofs_page_mark_eio(page);
		z_erofs_onlinepage_endio(page);
	}

	if (be->decompressed_pages != be->onstack_pages)
		kfree(be->decompressed_pages);

	pcl->length = 0;
	pcl->partial = true;
	pcl->multibases = false;
	pcl->bvset.nextpage = NULL;
	pcl->vcnt = 0;

	/* pcluster lock MUST be taken before the following line */
	WRITE_ONCE(pcl->next, Z_EROFS_PCLUSTER_NIL);
	mutex_unlock(&pcl->lock);
	return err;
}

static void z_erofs_decompress_queue(const struct z_erofs_decompressqueue *io,
				     struct page **pagepool)
{
	struct z_erofs_decompress_backend be = {
		.sb = io->sb,
		.pagepool = pagepool,
		.decompressed_secondary_bvecs =
			LIST_HEAD_INIT(be.decompressed_secondary_bvecs),
	};
	z_erofs_next_pcluster_t owned = io->head;

	while (owned != Z_EROFS_PCLUSTER_TAIL_CLOSED) {
		/* impossible that 'owned' equals Z_EROFS_WORK_TPTR_TAIL */
		DBG_BUGON(owned == Z_EROFS_PCLUSTER_TAIL);
		/* impossible that 'owned' equals Z_EROFS_PCLUSTER_NIL */
		DBG_BUGON(owned == Z_EROFS_PCLUSTER_NIL);

		be.pcl = container_of(owned, struct z_erofs_pcluster, next);
		owned = READ_ONCE(be.pcl->next);

		z_erofs_decompress_pcluster(&be, io->eio ? -EIO : 0);
		erofs_workgroup_put(&be.pcl->obj);
	}
}

static void z_erofs_decompressqueue_work(struct work_struct *work)
{
	struct z_erofs_decompressqueue *bgq =
		container_of(work, struct z_erofs_decompressqueue, u.work);
	struct page *pagepool = NULL;

	DBG_BUGON(bgq->head == Z_EROFS_PCLUSTER_TAIL_CLOSED);
	z_erofs_decompress_queue(bgq, &pagepool);

	erofs_release_pages(&pagepool);
	kvfree(bgq);
}

static void z_erofs_decompress_kickoff(struct z_erofs_decompressqueue *io,
				       bool sync, int bios)
{
	struct erofs_sb_info *const sbi = EROFS_SB(io->sb);

	/* wake up the caller thread for sync decompression */
	if (sync) {
		if (!atomic_add_return(bios, &io->pending_bios))
			complete(&io->u.done);
		return;
	}

	if (atomic_add_return(bios, &io->pending_bios))
		return;
	/* Use workqueue and sync decompression for atomic contexts only */
	if (in_atomic() || irqs_disabled()) {
		queue_work(z_erofs_workqueue, &io->u.work);
		/* enable sync decompression for readahead */
		if (sbi->opt.sync_decompress == EROFS_SYNC_DECOMPRESS_AUTO)
			sbi->opt.sync_decompress = EROFS_SYNC_DECOMPRESS_FORCE_ON;
		return;
	}
	z_erofs_decompressqueue_work(&io->u.work);
}

static struct page *pickup_page_for_submission(struct z_erofs_pcluster *pcl,
					       unsigned int nr,
					       struct page **pagepool,
					       struct address_space *mc)
{
	const pgoff_t index = pcl->obj.index;
	gfp_t gfp = mapping_gfp_mask(mc);
	bool tocache = false;

	struct address_space *mapping;
	struct page *oldpage, *page;

	compressed_page_t t;
	int justfound;

repeat:
	page = READ_ONCE(pcl->compressed_bvecs[nr].page);
	oldpage = page;

	if (!page)
		goto out_allocpage;

	/* process the target tagged pointer */
	t = tagptr_init(compressed_page_t, page);
	justfound = tagptr_unfold_tags(t);
	page = tagptr_unfold_ptr(t);

	/*
	 * preallocated cached pages, which is used to avoid direct reclaim
	 * otherwise, it will go inplace I/O path instead.
	 */
	if (page->private == Z_EROFS_PREALLOCATED_PAGE) {
		WRITE_ONCE(pcl->compressed_bvecs[nr].page, page);
		set_page_private(page, 0);
		tocache = true;
		goto out_tocache;
	}
	mapping = READ_ONCE(page->mapping);

	/*
	 * file-backed online pages in plcuster are all locked steady,
	 * therefore it is impossible for `mapping' to be NULL.
	 */
	if (mapping && mapping != mc)
		/* ought to be unmanaged pages */
		goto out;

	/* directly return for shortlived page as well */
	if (z_erofs_is_shortlived_page(page))
		goto out;

	lock_page(page);

	/* only true if page reclaim goes wrong, should never happen */
	DBG_BUGON(justfound && PagePrivate(page));

	/* the page is still in manage cache */
	if (page->mapping == mc) {
		WRITE_ONCE(pcl->compressed_bvecs[nr].page, page);

		if (!PagePrivate(page)) {
			/*
			 * impossible to be !PagePrivate(page) for
			 * the current restriction as well if
			 * the page is already in compressed_bvecs[].
			 */
			DBG_BUGON(!justfound);

			justfound = 0;
			set_page_private(page, (unsigned long)pcl);
			SetPagePrivate(page);
		}

		/* no need to submit io if it is already up-to-date */
		if (PageUptodate(page)) {
			unlock_page(page);
			page = NULL;
		}
		goto out;
	}

	/*
	 * the managed page has been truncated, it's unsafe to
	 * reuse this one, let's allocate a new cache-managed page.
	 */
	DBG_BUGON(page->mapping);
	DBG_BUGON(!justfound);

	tocache = true;
	unlock_page(page);
	put_page(page);
out_allocpage:
	page = erofs_allocpage(pagepool, gfp | __GFP_NOFAIL);
	if (oldpage != cmpxchg(&pcl->compressed_bvecs[nr].page,
			       oldpage, page)) {
		erofs_pagepool_add(pagepool, page);
		cond_resched();
		goto repeat;
	}
out_tocache:
	if (!tocache || add_to_page_cache_lru(page, mc, index + nr, gfp)) {
		/* turn into temporary page if fails (1 ref) */
		set_page_private(page, Z_EROFS_SHORTLIVED_PAGE);
		goto out;
	}
	attach_page_private(page, pcl);
	/* drop a refcount added by allocpage (then we have 2 refs here) */
	put_page(page);

out:	/* the only exit (for tracing and debugging) */
	return page;
}

static struct z_erofs_decompressqueue *
jobqueue_init(struct super_block *sb,
	      struct z_erofs_decompressqueue *fgq, bool *fg)
{
	struct z_erofs_decompressqueue *q;

	if (fg && !*fg) {
		q = kvzalloc(sizeof(*q), GFP_KERNEL | __GFP_NOWARN);
		if (!q) {
			*fg = true;
			goto fg_out;
		}
		INIT_WORK(&q->u.work, z_erofs_decompressqueue_work);
	} else {
fg_out:
		q = fgq;
		init_completion(&fgq->u.done);
		atomic_set(&fgq->pending_bios, 0);
		q->eio = false;
	}
	q->sb = sb;
	q->head = Z_EROFS_PCLUSTER_TAIL_CLOSED;
	return q;
}

/* define decompression jobqueue types */
enum {
	JQ_BYPASS,
	JQ_SUBMIT,
	NR_JOBQUEUES,
};

static void *jobqueueset_init(struct super_block *sb,
			      struct z_erofs_decompressqueue *q[],
			      struct z_erofs_decompressqueue *fgq, bool *fg)
{
	/*
	 * if managed cache is enabled, bypass jobqueue is needed,
	 * no need to read from device for all pclusters in this queue.
	 */
	q[JQ_BYPASS] = jobqueue_init(sb, fgq + JQ_BYPASS, NULL);
	q[JQ_SUBMIT] = jobqueue_init(sb, fgq + JQ_SUBMIT, fg);

	return tagptr_cast_ptr(tagptr_fold(tagptr1_t, q[JQ_SUBMIT], *fg));
}

static void move_to_bypass_jobqueue(struct z_erofs_pcluster *pcl,
				    z_erofs_next_pcluster_t qtail[],
				    z_erofs_next_pcluster_t owned_head)
{
	z_erofs_next_pcluster_t *const submit_qtail = qtail[JQ_SUBMIT];
	z_erofs_next_pcluster_t *const bypass_qtail = qtail[JQ_BYPASS];

	DBG_BUGON(owned_head == Z_EROFS_PCLUSTER_TAIL_CLOSED);
	if (owned_head == Z_EROFS_PCLUSTER_TAIL)
		owned_head = Z_EROFS_PCLUSTER_TAIL_CLOSED;

	WRITE_ONCE(pcl->next, Z_EROFS_PCLUSTER_TAIL_CLOSED);

	WRITE_ONCE(*submit_qtail, owned_head);
	WRITE_ONCE(*bypass_qtail, &pcl->next);

	qtail[JQ_BYPASS] = &pcl->next;
}

static void z_erofs_decompressqueue_endio(struct bio *bio)
{
	tagptr1_t t = tagptr_init(tagptr1_t, bio->bi_private);
	struct z_erofs_decompressqueue *q = tagptr_unfold_ptr(t);
	blk_status_t err = bio->bi_status;
	struct bio_vec *bvec;
	struct bvec_iter_all iter_all;

	bio_for_each_segment_all(bvec, bio, iter_all) {
		struct page *page = bvec->bv_page;

		DBG_BUGON(PageUptodate(page));
		DBG_BUGON(z_erofs_page_is_invalidated(page));

		if (erofs_page_is_managed(EROFS_SB(q->sb), page)) {
			if (!err)
				SetPageUptodate(page);
			unlock_page(page);
		}
	}
	if (err)
		q->eio = true;
	z_erofs_decompress_kickoff(q, tagptr_unfold_tags(t), -1);
	bio_put(bio);
}

static void z_erofs_submit_queue(struct z_erofs_decompress_frontend *f,
				 struct page **pagepool,
				 struct z_erofs_decompressqueue *fgq,
				 bool *force_fg)
{
	struct super_block *sb = f->inode->i_sb;
	struct address_space *mc = MNGD_MAPPING(EROFS_SB(sb));
	z_erofs_next_pcluster_t qtail[NR_JOBQUEUES];
	struct z_erofs_decompressqueue *q[NR_JOBQUEUES];
	void *bi_private;
	z_erofs_next_pcluster_t owned_head = f->owned_head;
	/* bio is NULL initially, so no need to initialize last_{index,bdev} */
	pgoff_t last_index;
	struct block_device *last_bdev;
	unsigned int nr_bios = 0;
	struct bio *bio = NULL;
	unsigned long pflags;
	int memstall = 0;

	bi_private = jobqueueset_init(sb, q, fgq, force_fg);
	qtail[JQ_BYPASS] = &q[JQ_BYPASS]->head;
	qtail[JQ_SUBMIT] = &q[JQ_SUBMIT]->head;

	/* by default, all need io submission */
	q[JQ_SUBMIT]->head = owned_head;

	do {
		struct erofs_map_dev mdev;
		struct z_erofs_pcluster *pcl;
		pgoff_t cur, end;
		unsigned int i = 0;
		bool bypass = true;

		/* no possible 'owned_head' equals the following */
		DBG_BUGON(owned_head == Z_EROFS_PCLUSTER_TAIL_CLOSED);
		DBG_BUGON(owned_head == Z_EROFS_PCLUSTER_NIL);

		pcl = container_of(owned_head, struct z_erofs_pcluster, next);

		/* close the main owned chain at first */
		owned_head = cmpxchg(&pcl->next, Z_EROFS_PCLUSTER_TAIL,
				     Z_EROFS_PCLUSTER_TAIL_CLOSED);
		if (z_erofs_is_inline_pcluster(pcl)) {
			move_to_bypass_jobqueue(pcl, qtail, owned_head);
			continue;
		}

		/* no device id here, thus it will always succeed */
		mdev = (struct erofs_map_dev) {
			.m_pa = blknr_to_addr(pcl->obj.index),
		};
		(void)erofs_map_dev(sb, &mdev);

		cur = erofs_blknr(mdev.m_pa);
		end = cur + pcl->pclusterpages;

		do {
			struct page *page;

			page = pickup_page_for_submission(pcl, i++, pagepool,
							  mc);
			if (!page)
				continue;

			if (bio && (cur != last_index + 1 ||
				    last_bdev != mdev.m_bdev)) {
submit_bio_retry:
				submit_bio(bio);
				if (memstall) {
					psi_memstall_leave(&pflags);
					memstall = 0;
				}
				bio = NULL;
			}

			if (unlikely(PageWorkingset(page)) && !memstall) {
				psi_memstall_enter(&pflags);
				memstall = 1;
			}

			if (!bio) {
				bio = bio_alloc(mdev.m_bdev, BIO_MAX_VECS,
						REQ_OP_READ, GFP_NOIO);
				bio->bi_end_io = z_erofs_decompressqueue_endio;

				last_bdev = mdev.m_bdev;
				bio->bi_iter.bi_sector = (sector_t)cur <<
					LOG_SECTORS_PER_BLOCK;
				bio->bi_private = bi_private;
				if (f->readahead)
					bio->bi_opf |= REQ_RAHEAD;
				++nr_bios;
			}

			if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE)
				goto submit_bio_retry;

			last_index = cur;
			bypass = false;
		} while (++cur < end);

		if (!bypass)
			qtail[JQ_SUBMIT] = &pcl->next;
		else
			move_to_bypass_jobqueue(pcl, qtail, owned_head);
	} while (owned_head != Z_EROFS_PCLUSTER_TAIL);

	if (bio) {
		submit_bio(bio);
		if (memstall)
			psi_memstall_leave(&pflags);
	}

	/*
	 * although background is preferred, no one is pending for submission.
	 * don't issue workqueue for decompression but drop it directly instead.
	 */
	if (!*force_fg && !nr_bios) {
		kvfree(q[JQ_SUBMIT]);
		return;
	}
	z_erofs_decompress_kickoff(q[JQ_SUBMIT], *force_fg, nr_bios);
}

static void z_erofs_runqueue(struct z_erofs_decompress_frontend *f,
			     struct page **pagepool, bool force_fg)
{
	struct z_erofs_decompressqueue io[NR_JOBQUEUES];

	if (f->owned_head == Z_EROFS_PCLUSTER_TAIL)
		return;
	z_erofs_submit_queue(f, pagepool, io, &force_fg);

	/* handle bypass queue (no i/o pclusters) immediately */
	z_erofs_decompress_queue(&io[JQ_BYPASS], pagepool);

	if (!force_fg)
		return;

	/* wait until all bios are completed */
	wait_for_completion_io(&io[JQ_SUBMIT].u.done);

	/* handle synchronous decompress queue in the caller context */
	z_erofs_decompress_queue(&io[JQ_SUBMIT], pagepool);
}

/*
 * Since partial uptodate is still unimplemented for now, we have to use
 * approximate readmore strategies as a start.
 */
static void z_erofs_pcluster_readmore(struct z_erofs_decompress_frontend *f,
				      struct readahead_control *rac,
				      erofs_off_t end,
				      struct page **pagepool,
				      bool backmost)
{
	struct inode *inode = f->inode;
	struct erofs_map_blocks *map = &f->map;
	erofs_off_t cur;
	int err;

	if (backmost) {
		map->m_la = end;
		err = z_erofs_map_blocks_iter(inode, map,
					      EROFS_GET_BLOCKS_READMORE);
		if (err)
			return;

		/* expend ra for the trailing edge if readahead */
		if (rac) {
			loff_t newstart = readahead_pos(rac);

			cur = round_up(map->m_la + map->m_llen, PAGE_SIZE);
			readahead_expand(rac, newstart, cur - newstart);
			return;
		}
		end = round_up(end, PAGE_SIZE);
	} else {
		end = round_up(map->m_la, PAGE_SIZE);

		if (!map->m_llen)
			return;
	}

	cur = map->m_la + map->m_llen - 1;
	while (cur >= end) {
		pgoff_t index = cur >> PAGE_SHIFT;
		struct page *page;

		page = erofs_grab_cache_page_nowait(inode->i_mapping, index);
		if (page) {
			if (PageUptodate(page)) {
				unlock_page(page);
			} else {
				err = z_erofs_do_read_page(f, page, pagepool);
				if (err)
					erofs_err(inode->i_sb,
						  "readmore error at page %lu @ nid %llu",
						  index, EROFS_I(inode)->nid);
			}
			put_page(page);
		}

		if (cur < PAGE_SIZE)
			break;
		cur = (index << PAGE_SHIFT) - 1;
	}
}

static int z_erofs_read_folio(struct file *file, struct folio *folio)
{
	struct page *page = &folio->page;
	struct inode *const inode = page->mapping->host;
	struct erofs_sb_info *const sbi = EROFS_I_SB(inode);
	struct z_erofs_decompress_frontend f = DECOMPRESS_FRONTEND_INIT(inode);
	struct page *pagepool = NULL;
	int err;

	trace_erofs_readpage(page, false);
	f.headoffset = (erofs_off_t)page->index << PAGE_SHIFT;

	z_erofs_pcluster_readmore(&f, NULL, f.headoffset + PAGE_SIZE - 1,
				  &pagepool, true);
	err = z_erofs_do_read_page(&f, page, &pagepool);
	z_erofs_pcluster_readmore(&f, NULL, 0, &pagepool, false);

	(void)z_erofs_collector_end(&f);

	/* if some compressed cluster ready, need submit them anyway */
	z_erofs_runqueue(&f, &pagepool,
			 z_erofs_get_sync_decompress_policy(sbi, 0));

	if (err)
		erofs_err(inode->i_sb, "failed to read, err [%d]", err);

	erofs_put_metabuf(&f.map.buf);
	erofs_release_pages(&pagepool);
	return err;
}

static void z_erofs_readahead(struct readahead_control *rac)
{
	struct inode *const inode = rac->mapping->host;
	struct erofs_sb_info *const sbi = EROFS_I_SB(inode);
	struct z_erofs_decompress_frontend f = DECOMPRESS_FRONTEND_INIT(inode);
	struct page *pagepool = NULL, *head = NULL, *page;
	unsigned int nr_pages;

	f.readahead = true;
	f.headoffset = readahead_pos(rac);

	z_erofs_pcluster_readmore(&f, rac, f.headoffset +
				  readahead_length(rac) - 1, &pagepool, true);
	nr_pages = readahead_count(rac);
	trace_erofs_readpages(inode, readahead_index(rac), nr_pages, false);

	while ((page = readahead_page(rac))) {
		set_page_private(page, (unsigned long)head);
		head = page;
	}

	while (head) {
		struct page *page = head;
		int err;

		/* traversal in reverse order */
		head = (void *)page_private(page);

		err = z_erofs_do_read_page(&f, page, &pagepool);
		if (err)
			erofs_err(inode->i_sb,
				  "readahead error at page %lu @ nid %llu",
				  page->index, EROFS_I(inode)->nid);
		put_page(page);
	}
	z_erofs_pcluster_readmore(&f, rac, 0, &pagepool, false);
	(void)z_erofs_collector_end(&f);

	z_erofs_runqueue(&f, &pagepool,
			 z_erofs_get_sync_decompress_policy(sbi, nr_pages));
	erofs_put_metabuf(&f.map.buf);
	erofs_release_pages(&pagepool);
}

const struct address_space_operations z_erofs_aops = {
	.read_folio = z_erofs_read_folio,
	.readahead = z_erofs_readahead,
};