summaryrefslogtreecommitdiff
path: root/fs/fuse/dev.c
blob: f7280c44cd4bc1a894cad2d8960ebc86d2f014e1 (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
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
/*
  FUSE: Filesystem in Userspace
  Copyright (C) 2001-2008  Miklos Szeredi <miklos@szeredi.hu>

  This program can be distributed under the terms of the GNU GPL.
  See the file COPYING.
*/

#include "fuse_i.h"

#include <linux/init.h>
#include <linux/module.h>
#include <linux/poll.h>
#include <linux/sched/signal.h>
#include <linux/uio.h>
#include <linux/miscdevice.h>
#include <linux/pagemap.h>
#include <linux/file.h>
#include <linux/slab.h>
#include <linux/pipe_fs_i.h>
#include <linux/swap.h>
#include <linux/splice.h>
#include <linux/sched.h>

MODULE_ALIAS_MISCDEV(FUSE_MINOR);
MODULE_ALIAS("devname:fuse");

static struct kmem_cache *fuse_req_cachep;

static struct fuse_dev *fuse_get_dev(struct file *file)
{
	/*
	 * Lockless access is OK, because file->private data is set
	 * once during mount and is valid until the file is released.
	 */
	return ACCESS_ONCE(file->private_data);
}

static void fuse_request_init(struct fuse_req *req, struct page **pages,
			      struct fuse_page_desc *page_descs,
			      unsigned npages)
{
	memset(req, 0, sizeof(*req));
	memset(pages, 0, sizeof(*pages) * npages);
	memset(page_descs, 0, sizeof(*page_descs) * npages);
	INIT_LIST_HEAD(&req->list);
	INIT_LIST_HEAD(&req->intr_entry);
	init_waitqueue_head(&req->waitq);
	refcount_set(&req->count, 1);
	req->pages = pages;
	req->page_descs = page_descs;
	req->max_pages = npages;
	__set_bit(FR_PENDING, &req->flags);
}

static struct fuse_req *__fuse_request_alloc(unsigned npages, gfp_t flags)
{
	struct fuse_req *req = kmem_cache_alloc(fuse_req_cachep, flags);
	if (req) {
		struct page **pages;
		struct fuse_page_desc *page_descs;

		if (npages <= FUSE_REQ_INLINE_PAGES) {
			pages = req->inline_pages;
			page_descs = req->inline_page_descs;
		} else {
			pages = kmalloc(sizeof(struct page *) * npages, flags);
			page_descs = kmalloc(sizeof(struct fuse_page_desc) *
					     npages, flags);
		}

		if (!pages || !page_descs) {
			kfree(pages);
			kfree(page_descs);
			kmem_cache_free(fuse_req_cachep, req);
			return NULL;
		}

		fuse_request_init(req, pages, page_descs, npages);
	}
	return req;
}

struct fuse_req *fuse_request_alloc(unsigned npages)
{
	return __fuse_request_alloc(npages, GFP_KERNEL);
}
EXPORT_SYMBOL_GPL(fuse_request_alloc);

struct fuse_req *fuse_request_alloc_nofs(unsigned npages)
{
	return __fuse_request_alloc(npages, GFP_NOFS);
}

void fuse_request_free(struct fuse_req *req)
{
	if (req->pages != req->inline_pages) {
		kfree(req->pages);
		kfree(req->page_descs);
	}
	kmem_cache_free(fuse_req_cachep, req);
}

void __fuse_get_request(struct fuse_req *req)
{
	refcount_inc(&req->count);
}

/* Must be called with > 1 refcount */
static void __fuse_put_request(struct fuse_req *req)
{
	refcount_dec(&req->count);
}

static void fuse_req_init_context(struct fuse_conn *fc, struct fuse_req *req)
{
	req->in.h.uid = from_kuid_munged(&init_user_ns, current_fsuid());
	req->in.h.gid = from_kgid_munged(&init_user_ns, current_fsgid());
	req->in.h.pid = pid_nr_ns(task_pid(current), fc->pid_ns);
}

void fuse_set_initialized(struct fuse_conn *fc)
{
	/* Make sure stores before this are seen on another CPU */
	smp_wmb();
	fc->initialized = 1;
}

static bool fuse_block_alloc(struct fuse_conn *fc, bool for_background)
{
	return !fc->initialized || (for_background && fc->blocked);
}

static void fuse_drop_waiting(struct fuse_conn *fc)
{
	if (fc->connected) {
		atomic_dec(&fc->num_waiting);
	} else if (atomic_dec_and_test(&fc->num_waiting)) {
		/* wake up aborters */
		wake_up_all(&fc->blocked_waitq);
	}
}

static struct fuse_req *__fuse_get_req(struct fuse_conn *fc, unsigned npages,
				       bool for_background)
{
	struct fuse_req *req;
	int err;
	atomic_inc(&fc->num_waiting);

	if (fuse_block_alloc(fc, for_background)) {
		err = -EINTR;
		if (wait_event_killable_exclusive(fc->blocked_waitq,
				!fuse_block_alloc(fc, for_background)))
			goto out;
	}
	/* Matches smp_wmb() in fuse_set_initialized() */
	smp_rmb();

	err = -ENOTCONN;
	if (!fc->connected)
		goto out;

	err = -ECONNREFUSED;
	if (fc->conn_error)
		goto out;

	req = fuse_request_alloc(npages);
	err = -ENOMEM;
	if (!req) {
		if (for_background)
			wake_up(&fc->blocked_waitq);
		goto out;
	}

	fuse_req_init_context(fc, req);
	__set_bit(FR_WAITING, &req->flags);
	if (for_background)
		__set_bit(FR_BACKGROUND, &req->flags);

	return req;

 out:
	fuse_drop_waiting(fc);
	return ERR_PTR(err);
}

struct fuse_req *fuse_get_req(struct fuse_conn *fc, unsigned npages)
{
	return __fuse_get_req(fc, npages, false);
}
EXPORT_SYMBOL_GPL(fuse_get_req);

struct fuse_req *fuse_get_req_for_background(struct fuse_conn *fc,
					     unsigned npages)
{
	return __fuse_get_req(fc, npages, true);
}
EXPORT_SYMBOL_GPL(fuse_get_req_for_background);

/*
 * Return request in fuse_file->reserved_req.  However that may
 * currently be in use.  If that is the case, wait for it to become
 * available.
 */
static struct fuse_req *get_reserved_req(struct fuse_conn *fc,
					 struct file *file)
{
	struct fuse_req *req = NULL;
	struct fuse_file *ff = file->private_data;

	do {
		wait_event(fc->reserved_req_waitq, ff->reserved_req);
		spin_lock(&fc->lock);
		if (ff->reserved_req) {
			req = ff->reserved_req;
			ff->reserved_req = NULL;
			req->stolen_file = get_file(file);
		}
		spin_unlock(&fc->lock);
	} while (!req);

	return req;
}

/*
 * Put stolen request back into fuse_file->reserved_req
 */
static void put_reserved_req(struct fuse_conn *fc, struct fuse_req *req)
{
	struct file *file = req->stolen_file;
	struct fuse_file *ff = file->private_data;

	spin_lock(&fc->lock);
	fuse_request_init(req, req->pages, req->page_descs, req->max_pages);
	BUG_ON(ff->reserved_req);
	ff->reserved_req = req;
	wake_up_all(&fc->reserved_req_waitq);
	spin_unlock(&fc->lock);
	fput(file);
}

/*
 * Gets a requests for a file operation, always succeeds
 *
 * This is used for sending the FLUSH request, which must get to
 * userspace, due to POSIX locks which may need to be unlocked.
 *
 * If allocation fails due to OOM, use the reserved request in
 * fuse_file.
 *
 * This is very unlikely to deadlock accidentally, since the
 * filesystem should not have it's own file open.  If deadlock is
 * intentional, it can still be broken by "aborting" the filesystem.
 */
struct fuse_req *fuse_get_req_nofail_nopages(struct fuse_conn *fc,
					     struct file *file)
{
	struct fuse_req *req;

	atomic_inc(&fc->num_waiting);
	wait_event(fc->blocked_waitq, fc->initialized);
	/* Matches smp_wmb() in fuse_set_initialized() */
	smp_rmb();
	req = fuse_request_alloc(0);
	if (!req)
		req = get_reserved_req(fc, file);

	fuse_req_init_context(fc, req);
	__set_bit(FR_WAITING, &req->flags);
	__clear_bit(FR_BACKGROUND, &req->flags);
	return req;
}

void fuse_put_request(struct fuse_conn *fc, struct fuse_req *req)
{
	if (refcount_dec_and_test(&req->count)) {
		if (test_bit(FR_BACKGROUND, &req->flags)) {
			/*
			 * We get here in the unlikely case that a background
			 * request was allocated but not sent
			 */
			spin_lock(&fc->lock);
			if (!fc->blocked)
				wake_up(&fc->blocked_waitq);
			spin_unlock(&fc->lock);
		}

		if (test_bit(FR_WAITING, &req->flags)) {
			__clear_bit(FR_WAITING, &req->flags);
			fuse_drop_waiting(fc);
		}

		if (req->stolen_file)
			put_reserved_req(fc, req);
		else
			fuse_request_free(req);
	}
}
EXPORT_SYMBOL_GPL(fuse_put_request);

static unsigned len_args(unsigned numargs, struct fuse_arg *args)
{
	unsigned nbytes = 0;
	unsigned i;

	for (i = 0; i < numargs; i++)
		nbytes += args[i].size;

	return nbytes;
}

static u64 fuse_get_unique(struct fuse_iqueue *fiq)
{
	return ++fiq->reqctr;
}

static void queue_request(struct fuse_iqueue *fiq, struct fuse_req *req)
{
	req->in.h.len = sizeof(struct fuse_in_header) +
		len_args(req->in.numargs, (struct fuse_arg *) req->in.args);
	list_add_tail(&req->list, &fiq->pending);
	wake_up_locked(&fiq->waitq);
	kill_fasync(&fiq->fasync, SIGIO, POLL_IN);
}

void fuse_queue_forget(struct fuse_conn *fc, struct fuse_forget_link *forget,
		       u64 nodeid, u64 nlookup)
{
	struct fuse_iqueue *fiq = &fc->iq;

	forget->forget_one.nodeid = nodeid;
	forget->forget_one.nlookup = nlookup;

	spin_lock(&fiq->waitq.lock);
	if (fiq->connected) {
		fiq->forget_list_tail->next = forget;
		fiq->forget_list_tail = forget;
		wake_up_locked(&fiq->waitq);
		kill_fasync(&fiq->fasync, SIGIO, POLL_IN);
	} else {
		kfree(forget);
	}
	spin_unlock(&fiq->waitq.lock);
}

static void flush_bg_queue(struct fuse_conn *fc)
{
	while (fc->active_background < fc->max_background &&
	       !list_empty(&fc->bg_queue)) {
		struct fuse_req *req;
		struct fuse_iqueue *fiq = &fc->iq;

		req = list_entry(fc->bg_queue.next, struct fuse_req, list);
		list_del(&req->list);
		fc->active_background++;
		spin_lock(&fiq->waitq.lock);
		req->in.h.unique = fuse_get_unique(fiq);
		queue_request(fiq, req);
		spin_unlock(&fiq->waitq.lock);
	}
}

/*
 * This function is called when a request is finished.  Either a reply
 * has arrived or it was aborted (and not yet sent) or some error
 * occurred during communication with userspace, or the device file
 * was closed.  The requester thread is woken up (if still waiting),
 * the 'end' callback is called if given, else the reference to the
 * request is released
 */
static void request_end(struct fuse_conn *fc, struct fuse_req *req)
{
	struct fuse_iqueue *fiq = &fc->iq;

	if (test_and_set_bit(FR_FINISHED, &req->flags))
		goto put_request;

	spin_lock(&fiq->waitq.lock);
	list_del_init(&req->intr_entry);
	spin_unlock(&fiq->waitq.lock);
	WARN_ON(test_bit(FR_PENDING, &req->flags));
	WARN_ON(test_bit(FR_SENT, &req->flags));
	if (test_bit(FR_BACKGROUND, &req->flags)) {
		spin_lock(&fc->lock);
		clear_bit(FR_BACKGROUND, &req->flags);
		if (fc->num_background == fc->max_background) {
			fc->blocked = 0;
			wake_up(&fc->blocked_waitq);
		} else if (!fc->blocked) {
			/*
			 * Wake up next waiter, if any.  It's okay to use
			 * waitqueue_active(), as we've already synced up
			 * fc->blocked with waiters with the wake_up() call
			 * above.
			 */
			if (waitqueue_active(&fc->blocked_waitq))
				wake_up(&fc->blocked_waitq);
		}

		if (fc->num_background == fc->congestion_threshold && fc->sb) {
			clear_bdi_congested(fc->sb->s_bdi, BLK_RW_SYNC);
			clear_bdi_congested(fc->sb->s_bdi, BLK_RW_ASYNC);
		}
		fc->num_background--;
		fc->active_background--;
		flush_bg_queue(fc);
		spin_unlock(&fc->lock);
	}
	wake_up(&req->waitq);
	if (req->end)
		req->end(fc, req);
put_request:
	fuse_put_request(fc, req);
}

static void queue_interrupt(struct fuse_iqueue *fiq, struct fuse_req *req)
{
	spin_lock(&fiq->waitq.lock);
	if (test_bit(FR_FINISHED, &req->flags)) {
		spin_unlock(&fiq->waitq.lock);
		return;
	}
	if (list_empty(&req->intr_entry)) {
		list_add_tail(&req->intr_entry, &fiq->interrupts);
		wake_up_locked(&fiq->waitq);
	}
	spin_unlock(&fiq->waitq.lock);
	kill_fasync(&fiq->fasync, SIGIO, POLL_IN);
}

static void request_wait_answer(struct fuse_conn *fc, struct fuse_req *req)
{
	struct fuse_iqueue *fiq = &fc->iq;
	int err;

	if (!fc->no_interrupt) {
		/* Any signal may interrupt this */
		err = wait_event_interruptible(req->waitq,
					test_bit(FR_FINISHED, &req->flags));
		if (!err)
			return;

		set_bit(FR_INTERRUPTED, &req->flags);
		/* matches barrier in fuse_dev_do_read() */
		smp_mb__after_atomic();
		if (test_bit(FR_SENT, &req->flags))
			queue_interrupt(fiq, req);
	}

	if (!test_bit(FR_FORCE, &req->flags)) {
		/* Only fatal signals may interrupt this */
		err = wait_event_killable(req->waitq,
					test_bit(FR_FINISHED, &req->flags));
		if (!err)
			return;

		spin_lock(&fiq->waitq.lock);
		/* Request is not yet in userspace, bail out */
		if (test_bit(FR_PENDING, &req->flags)) {
			list_del(&req->list);
			spin_unlock(&fiq->waitq.lock);
			__fuse_put_request(req);
			req->out.h.error = -EINTR;
			return;
		}
		spin_unlock(&fiq->waitq.lock);
	}

	/*
	 * Either request is already in userspace, or it was forced.
	 * Wait it out.
	 */
	wait_event(req->waitq, test_bit(FR_FINISHED, &req->flags));
}

static void __fuse_request_send(struct fuse_conn *fc, struct fuse_req *req)
{
	struct fuse_iqueue *fiq = &fc->iq;

	BUG_ON(test_bit(FR_BACKGROUND, &req->flags));
	spin_lock(&fiq->waitq.lock);
	if (!fiq->connected) {
		spin_unlock(&fiq->waitq.lock);
		req->out.h.error = -ENOTCONN;
	} else {
		req->in.h.unique = fuse_get_unique(fiq);
		queue_request(fiq, req);
		/* acquire extra reference, since request is still needed
		   after request_end() */
		__fuse_get_request(req);
		spin_unlock(&fiq->waitq.lock);

		request_wait_answer(fc, req);
		/* Pairs with smp_wmb() in request_end() */
		smp_rmb();
	}
}

void fuse_request_send(struct fuse_conn *fc, struct fuse_req *req)
{
	__set_bit(FR_ISREPLY, &req->flags);
	if (!test_bit(FR_WAITING, &req->flags)) {
		__set_bit(FR_WAITING, &req->flags);
		atomic_inc(&fc->num_waiting);
	}
	__fuse_request_send(fc, req);
}
EXPORT_SYMBOL_GPL(fuse_request_send);

static void fuse_adjust_compat(struct fuse_conn *fc, struct fuse_args *args)
{
	if (fc->minor < 4 && args->in.h.opcode == FUSE_STATFS)
		args->out.args[0].size = FUSE_COMPAT_STATFS_SIZE;

	if (fc->minor < 9) {
		switch (args->in.h.opcode) {
		case FUSE_LOOKUP:
		case FUSE_CREATE:
		case FUSE_MKNOD:
		case FUSE_MKDIR:
		case FUSE_SYMLINK:
		case FUSE_LINK:
			args->out.args[0].size = FUSE_COMPAT_ENTRY_OUT_SIZE;
			break;
		case FUSE_GETATTR:
		case FUSE_SETATTR:
			args->out.args[0].size = FUSE_COMPAT_ATTR_OUT_SIZE;
			break;
		}
	}
	if (fc->minor < 12) {
		switch (args->in.h.opcode) {
		case FUSE_CREATE:
			args->in.args[0].size = sizeof(struct fuse_open_in);
			break;
		case FUSE_MKNOD:
			args->in.args[0].size = FUSE_COMPAT_MKNOD_IN_SIZE;
			break;
		}
	}
}

ssize_t fuse_simple_request(struct fuse_conn *fc, struct fuse_args *args)
{
	struct fuse_req *req;
	ssize_t ret;

	req = fuse_get_req(fc, 0);
	if (IS_ERR(req))
		return PTR_ERR(req);

	/* Needs to be done after fuse_get_req() so that fc->minor is valid */
	fuse_adjust_compat(fc, args);

	req->in.h.opcode = args->in.h.opcode;
	req->in.h.nodeid = args->in.h.nodeid;
	req->in.numargs = args->in.numargs;
	memcpy(req->in.args, args->in.args,
	       args->in.numargs * sizeof(struct fuse_in_arg));
	req->out.argvar = args->out.argvar;
	req->out.numargs = args->out.numargs;
	memcpy(req->out.args, args->out.args,
	       args->out.numargs * sizeof(struct fuse_arg));
	fuse_request_send(fc, req);
	ret = req->out.h.error;
	if (!ret && args->out.argvar) {
		BUG_ON(args->out.numargs != 1);
		ret = req->out.args[0].size;
	}
	fuse_put_request(fc, req);

	return ret;
}

/*
 * Called under fc->lock
 *
 * fc->connected must have been checked previously
 */
void fuse_request_send_background_locked(struct fuse_conn *fc,
					 struct fuse_req *req)
{
	BUG_ON(!test_bit(FR_BACKGROUND, &req->flags));
	if (!test_bit(FR_WAITING, &req->flags)) {
		__set_bit(FR_WAITING, &req->flags);
		atomic_inc(&fc->num_waiting);
	}
	__set_bit(FR_ISREPLY, &req->flags);
	fc->num_background++;
	if (fc->num_background == fc->max_background)
		fc->blocked = 1;
	if (fc->num_background == fc->congestion_threshold && fc->sb) {
		set_bdi_congested(fc->sb->s_bdi, BLK_RW_SYNC);
		set_bdi_congested(fc->sb->s_bdi, BLK_RW_ASYNC);
	}
	list_add_tail(&req->list, &fc->bg_queue);
	flush_bg_queue(fc);
}

void fuse_request_send_background(struct fuse_conn *fc, struct fuse_req *req)
{
	BUG_ON(!req->end);
	spin_lock(&fc->lock);
	if (fc->connected) {
		fuse_request_send_background_locked(fc, req);
		spin_unlock(&fc->lock);
	} else {
		spin_unlock(&fc->lock);
		req->out.h.error = -ENOTCONN;
		req->end(fc, req);
		fuse_put_request(fc, req);
	}
}
EXPORT_SYMBOL_GPL(fuse_request_send_background);

static int fuse_request_send_notify_reply(struct fuse_conn *fc,
					  struct fuse_req *req, u64 unique)
{
	int err = -ENODEV;
	struct fuse_iqueue *fiq = &fc->iq;

	__clear_bit(FR_ISREPLY, &req->flags);
	req->in.h.unique = unique;
	spin_lock(&fiq->waitq.lock);
	if (fiq->connected) {
		queue_request(fiq, req);
		err = 0;
	}
	spin_unlock(&fiq->waitq.lock);

	return err;
}

void fuse_force_forget(struct file *file, u64 nodeid)
{
	struct inode *inode = file_inode(file);
	struct fuse_conn *fc = get_fuse_conn(inode);
	struct fuse_req *req;
	struct fuse_forget_in inarg;

	memset(&inarg, 0, sizeof(inarg));
	inarg.nlookup = 1;
	req = fuse_get_req_nofail_nopages(fc, file);
	req->in.h.opcode = FUSE_FORGET;
	req->in.h.nodeid = nodeid;
	req->in.numargs = 1;
	req->in.args[0].size = sizeof(inarg);
	req->in.args[0].value = &inarg;
	__clear_bit(FR_ISREPLY, &req->flags);
	__fuse_request_send(fc, req);
	/* ignore errors */
	fuse_put_request(fc, req);
}

/*
 * Lock the request.  Up to the next unlock_request() there mustn't be
 * anything that could cause a page-fault.  If the request was already
 * aborted bail out.
 */
static int lock_request(struct fuse_req *req)
{
	int err = 0;
	if (req) {
		spin_lock(&req->waitq.lock);
		if (test_bit(FR_ABORTED, &req->flags))
			err = -ENOENT;
		else
			set_bit(FR_LOCKED, &req->flags);
		spin_unlock(&req->waitq.lock);
	}
	return err;
}

/*
 * Unlock request.  If it was aborted while locked, caller is responsible
 * for unlocking and ending the request.
 */
static int unlock_request(struct fuse_req *req)
{
	int err = 0;
	if (req) {
		spin_lock(&req->waitq.lock);
		if (test_bit(FR_ABORTED, &req->flags))
			err = -ENOENT;
		else
			clear_bit(FR_LOCKED, &req->flags);
		spin_unlock(&req->waitq.lock);
	}
	return err;
}

struct fuse_copy_state {
	int write;
	struct fuse_req *req;
	struct iov_iter *iter;
	struct pipe_buffer *pipebufs;
	struct pipe_buffer *currbuf;
	struct pipe_inode_info *pipe;
	unsigned long nr_segs;
	struct page *pg;
	unsigned len;
	unsigned offset;
	unsigned move_pages:1;
};

static void fuse_copy_init(struct fuse_copy_state *cs, int write,
			   struct iov_iter *iter)
{
	memset(cs, 0, sizeof(*cs));
	cs->write = write;
	cs->iter = iter;
}

/* Unmap and put previous page of userspace buffer */
static void fuse_copy_finish(struct fuse_copy_state *cs)
{
	if (cs->currbuf) {
		struct pipe_buffer *buf = cs->currbuf;

		if (cs->write)
			buf->len = PAGE_SIZE - cs->len;
		cs->currbuf = NULL;
	} else if (cs->pg) {
		if (cs->write) {
			flush_dcache_page(cs->pg);
			set_page_dirty_lock(cs->pg);
		}
		put_page(cs->pg);
	}
	cs->pg = NULL;
}

/*
 * Get another pagefull of userspace buffer, and map it to kernel
 * address space, and lock request
 */
static int fuse_copy_fill(struct fuse_copy_state *cs)
{
	struct page *page;
	int err;

	err = unlock_request(cs->req);
	if (err)
		return err;

	fuse_copy_finish(cs);
	if (cs->pipebufs) {
		struct pipe_buffer *buf = cs->pipebufs;

		if (!cs->write) {
			err = pipe_buf_confirm(cs->pipe, buf);
			if (err)
				return err;

			BUG_ON(!cs->nr_segs);
			cs->currbuf = buf;
			cs->pg = buf->page;
			cs->offset = buf->offset;
			cs->len = buf->len;
			cs->pipebufs++;
			cs->nr_segs--;
		} else {
			if (cs->nr_segs == cs->pipe->buffers)
				return -EIO;

			page = alloc_page(GFP_HIGHUSER);
			if (!page)
				return -ENOMEM;

			buf->page = page;
			buf->offset = 0;
			buf->len = 0;

			cs->currbuf = buf;
			cs->pg = page;
			cs->offset = 0;
			cs->len = PAGE_SIZE;
			cs->pipebufs++;
			cs->nr_segs++;
		}
	} else {
		size_t off;
		err = iov_iter_get_pages(cs->iter, &page, PAGE_SIZE, 1, &off);
		if (err < 0)
			return err;
		BUG_ON(!err);
		cs->len = err;
		cs->offset = off;
		cs->pg = page;
		iov_iter_advance(cs->iter, err);
	}

	return lock_request(cs->req);
}

/* Do as much copy to/from userspace buffer as we can */
static int fuse_copy_do(struct fuse_copy_state *cs, void **val, unsigned *size)
{
	unsigned ncpy = min(*size, cs->len);
	if (val) {
		void *pgaddr = kmap_atomic(cs->pg);
		void *buf = pgaddr + cs->offset;

		if (cs->write)
			memcpy(buf, *val, ncpy);
		else
			memcpy(*val, buf, ncpy);

		kunmap_atomic(pgaddr);
		*val += ncpy;
	}
	*size -= ncpy;
	cs->len -= ncpy;
	cs->offset += ncpy;
	return ncpy;
}

static int fuse_check_page(struct page *page)
{
	if (page_mapcount(page) ||
	    page->mapping != NULL ||
	    page_count(page) != 1 ||
	    (page->flags & PAGE_FLAGS_CHECK_AT_PREP &
	     ~(1 << PG_locked |
	       1 << PG_referenced |
	       1 << PG_uptodate |
	       1 << PG_lru |
	       1 << PG_active |
	       1 << PG_reclaim))) {
		printk(KERN_WARNING "fuse: trying to steal weird page\n");
		printk(KERN_WARNING "  page=%p index=%li flags=%08lx, count=%i, mapcount=%i, mapping=%p\n", page, page->index, page->flags, page_count(page), page_mapcount(page), page->mapping);
		return 1;
	}
	return 0;
}

static int fuse_try_move_page(struct fuse_copy_state *cs, struct page **pagep)
{
	int err;
	struct page *oldpage = *pagep;
	struct page *newpage;
	struct pipe_buffer *buf = cs->pipebufs;

	err = unlock_request(cs->req);
	if (err)
		return err;

	fuse_copy_finish(cs);

	err = pipe_buf_confirm(cs->pipe, buf);
	if (err)
		return err;

	BUG_ON(!cs->nr_segs);
	cs->currbuf = buf;
	cs->len = buf->len;
	cs->pipebufs++;
	cs->nr_segs--;

	if (cs->len != PAGE_SIZE)
		goto out_fallback;

	if (pipe_buf_steal(cs->pipe, buf) != 0)
		goto out_fallback;

	newpage = buf->page;

	if (!PageUptodate(newpage))
		SetPageUptodate(newpage);

	ClearPageMappedToDisk(newpage);

	if (fuse_check_page(newpage) != 0)
		goto out_fallback_unlock;

	/*
	 * This is a new and locked page, it shouldn't be mapped or
	 * have any special flags on it
	 */
	if (WARN_ON(page_mapped(oldpage)))
		goto out_fallback_unlock;
	if (WARN_ON(page_has_private(oldpage)))
		goto out_fallback_unlock;
	if (WARN_ON(PageDirty(oldpage) || PageWriteback(oldpage)))
		goto out_fallback_unlock;
	if (WARN_ON(PageMlocked(oldpage)))
		goto out_fallback_unlock;

	err = replace_page_cache_page(oldpage, newpage, GFP_KERNEL);
	if (err) {
		unlock_page(newpage);
		return err;
	}

	get_page(newpage);

	if (!(buf->flags & PIPE_BUF_FLAG_LRU))
		lru_cache_add_file(newpage);

	err = 0;
	spin_lock(&cs->req->waitq.lock);
	if (test_bit(FR_ABORTED, &cs->req->flags))
		err = -ENOENT;
	else
		*pagep = newpage;
	spin_unlock(&cs->req->waitq.lock);

	if (err) {
		unlock_page(newpage);
		put_page(newpage);
		return err;
	}

	unlock_page(oldpage);
	put_page(oldpage);
	cs->len = 0;

	return 0;

out_fallback_unlock:
	unlock_page(newpage);
out_fallback:
	cs->pg = buf->page;
	cs->offset = buf->offset;

	err = lock_request(cs->req);
	if (err)
		return err;

	return 1;
}

static int fuse_ref_page(struct fuse_copy_state *cs, struct page *page,
			 unsigned offset, unsigned count)
{
	struct pipe_buffer *buf;
	int err;

	if (cs->nr_segs == cs->pipe->buffers)
		return -EIO;

	err = unlock_request(cs->req);
	if (err)
		return err;

	fuse_copy_finish(cs);

	buf = cs->pipebufs;
	get_page(page);
	buf->page = page;
	buf->offset = offset;
	buf->len = count;

	cs->pipebufs++;
	cs->nr_segs++;
	cs->len = 0;

	return 0;
}

/*
 * Copy a page in the request to/from the userspace buffer.  Must be
 * done atomically
 */
static int fuse_copy_page(struct fuse_copy_state *cs, struct page **pagep,
			  unsigned offset, unsigned count, int zeroing)
{
	int err;
	struct page *page = *pagep;

	if (page && zeroing && count < PAGE_SIZE)
		clear_highpage(page);

	while (count) {
		if (cs->write && cs->pipebufs && page) {
			return fuse_ref_page(cs, page, offset, count);
		} else if (!cs->len) {
			if (cs->move_pages && page &&
			    offset == 0 && count == PAGE_SIZE) {
				err = fuse_try_move_page(cs, pagep);
				if (err <= 0)
					return err;
			} else {
				err = fuse_copy_fill(cs);
				if (err)
					return err;
			}
		}
		if (page) {
			void *mapaddr = kmap_atomic(page);
			void *buf = mapaddr + offset;
			offset += fuse_copy_do(cs, &buf, &count);
			kunmap_atomic(mapaddr);
		} else
			offset += fuse_copy_do(cs, NULL, &count);
	}
	if (page && !cs->write)
		flush_dcache_page(page);
	return 0;
}

/* Copy pages in the request to/from userspace buffer */
static int fuse_copy_pages(struct fuse_copy_state *cs, unsigned nbytes,
			   int zeroing)
{
	unsigned i;
	struct fuse_req *req = cs->req;

	for (i = 0; i < req->num_pages && (nbytes || zeroing); i++) {
		int err;
		unsigned offset = req->page_descs[i].offset;
		unsigned count = min(nbytes, req->page_descs[i].length);

		err = fuse_copy_page(cs, &req->pages[i], offset, count,
				     zeroing);
		if (err)
			return err;

		nbytes -= count;
	}
	return 0;
}

/* Copy a single argument in the request to/from userspace buffer */
static int fuse_copy_one(struct fuse_copy_state *cs, void *val, unsigned size)
{
	while (size) {
		if (!cs->len) {
			int err = fuse_copy_fill(cs);
			if (err)
				return err;
		}
		fuse_copy_do(cs, &val, &size);
	}
	return 0;
}

/* Copy request arguments to/from userspace buffer */
static int fuse_copy_args(struct fuse_copy_state *cs, unsigned numargs,
			  unsigned argpages, struct fuse_arg *args,
			  int zeroing)
{
	int err = 0;
	unsigned i;

	for (i = 0; !err && i < numargs; i++)  {
		struct fuse_arg *arg = &args[i];
		if (i == numargs - 1 && argpages)
			err = fuse_copy_pages(cs, arg->size, zeroing);
		else
			err = fuse_copy_one(cs, arg->value, arg->size);
	}
	return err;
}

static int forget_pending(struct fuse_iqueue *fiq)
{
	return fiq->forget_list_head.next != NULL;
}

static int request_pending(struct fuse_iqueue *fiq)
{
	return !list_empty(&fiq->pending) || !list_empty(&fiq->interrupts) ||
		forget_pending(fiq);
}

/*
 * Transfer an interrupt request to userspace
 *
 * Unlike other requests this is assembled on demand, without a need
 * to allocate a separate fuse_req structure.
 *
 * Called with fiq->waitq.lock held, releases it
 */
static int fuse_read_interrupt(struct fuse_iqueue *fiq,
			       struct fuse_copy_state *cs,
			       size_t nbytes, struct fuse_req *req)
__releases(fiq->waitq.lock)
{
	struct fuse_in_header ih;
	struct fuse_interrupt_in arg;
	unsigned reqsize = sizeof(ih) + sizeof(arg);
	int err;

	list_del_init(&req->intr_entry);
	req->intr_unique = fuse_get_unique(fiq);
	memset(&ih, 0, sizeof(ih));
	memset(&arg, 0, sizeof(arg));
	ih.len = reqsize;
	ih.opcode = FUSE_INTERRUPT;
	ih.unique = req->intr_unique;
	arg.unique = req->in.h.unique;

	spin_unlock(&fiq->waitq.lock);
	if (nbytes < reqsize)
		return -EINVAL;

	err = fuse_copy_one(cs, &ih, sizeof(ih));
	if (!err)
		err = fuse_copy_one(cs, &arg, sizeof(arg));
	fuse_copy_finish(cs);

	return err ? err : reqsize;
}

static struct fuse_forget_link *dequeue_forget(struct fuse_iqueue *fiq,
					       unsigned max,
					       unsigned *countp)
{
	struct fuse_forget_link *head = fiq->forget_list_head.next;
	struct fuse_forget_link **newhead = &head;
	unsigned count;

	for (count = 0; *newhead != NULL && count < max; count++)
		newhead = &(*newhead)->next;

	fiq->forget_list_head.next = *newhead;
	*newhead = NULL;
	if (fiq->forget_list_head.next == NULL)
		fiq->forget_list_tail = &fiq->forget_list_head;

	if (countp != NULL)
		*countp = count;

	return head;
}

static int fuse_read_single_forget(struct fuse_iqueue *fiq,
				   struct fuse_copy_state *cs,
				   size_t nbytes)
__releases(fiq->waitq.lock)
{
	int err;
	struct fuse_forget_link *forget = dequeue_forget(fiq, 1, NULL);
	struct fuse_forget_in arg = {
		.nlookup = forget->forget_one.nlookup,
	};
	struct fuse_in_header ih = {
		.opcode = FUSE_FORGET,
		.nodeid = forget->forget_one.nodeid,
		.unique = fuse_get_unique(fiq),
		.len = sizeof(ih) + sizeof(arg),
	};

	spin_unlock(&fiq->waitq.lock);
	kfree(forget);
	if (nbytes < ih.len)
		return -EINVAL;

	err = fuse_copy_one(cs, &ih, sizeof(ih));
	if (!err)
		err = fuse_copy_one(cs, &arg, sizeof(arg));
	fuse_copy_finish(cs);

	if (err)
		return err;

	return ih.len;
}

static int fuse_read_batch_forget(struct fuse_iqueue *fiq,
				   struct fuse_copy_state *cs, size_t nbytes)
__releases(fiq->waitq.lock)
{
	int err;
	unsigned max_forgets;
	unsigned count;
	struct fuse_forget_link *head;
	struct fuse_batch_forget_in arg = { .count = 0 };
	struct fuse_in_header ih = {
		.opcode = FUSE_BATCH_FORGET,
		.unique = fuse_get_unique(fiq),
		.len = sizeof(ih) + sizeof(arg),
	};

	if (nbytes < ih.len) {
		spin_unlock(&fiq->waitq.lock);
		return -EINVAL;
	}

	max_forgets = (nbytes - ih.len) / sizeof(struct fuse_forget_one);
	head = dequeue_forget(fiq, max_forgets, &count);
	spin_unlock(&fiq->waitq.lock);

	arg.count = count;
	ih.len += count * sizeof(struct fuse_forget_one);
	err = fuse_copy_one(cs, &ih, sizeof(ih));
	if (!err)
		err = fuse_copy_one(cs, &arg, sizeof(arg));

	while (head) {
		struct fuse_forget_link *forget = head;

		if (!err) {
			err = fuse_copy_one(cs, &forget->forget_one,
					    sizeof(forget->forget_one));
		}
		head = forget->next;
		kfree(forget);
	}

	fuse_copy_finish(cs);

	if (err)
		return err;

	return ih.len;
}

static int fuse_read_forget(struct fuse_conn *fc, struct fuse_iqueue *fiq,
			    struct fuse_copy_state *cs,
			    size_t nbytes)
__releases(fiq->waitq.lock)
{
	if (fc->minor < 16 || fiq->forget_list_head.next->next == NULL)
		return fuse_read_single_forget(fiq, cs, nbytes);
	else
		return fuse_read_batch_forget(fiq, cs, nbytes);
}

/*
 * Read a single request into the userspace filesystem's buffer.  This
 * function waits until a request is available, then removes it from
 * the pending list and copies request data to userspace buffer.  If
 * no reply is needed (FORGET) or request has been aborted or there
 * was an error during the copying then it's finished by calling
 * request_end().  Otherwise add it to the processing list, and set
 * the 'sent' flag.
 */
static ssize_t fuse_dev_do_read(struct fuse_dev *fud, struct file *file,
				struct fuse_copy_state *cs, size_t nbytes)
{
	ssize_t err;
	struct fuse_conn *fc = fud->fc;
	struct fuse_iqueue *fiq = &fc->iq;
	struct fuse_pqueue *fpq = &fud->pq;
	struct fuse_req *req;
	struct fuse_in *in;
	unsigned reqsize;

 restart:
	spin_lock(&fiq->waitq.lock);
	err = -EAGAIN;
	if ((file->f_flags & O_NONBLOCK) && fiq->connected &&
	    !request_pending(fiq))
		goto err_unlock;

	err = wait_event_interruptible_exclusive_locked(fiq->waitq,
				!fiq->connected || request_pending(fiq));
	if (err)
		goto err_unlock;

	err = -ENODEV;
	if (!fiq->connected)
		goto err_unlock;

	if (!list_empty(&fiq->interrupts)) {
		req = list_entry(fiq->interrupts.next, struct fuse_req,
				 intr_entry);
		return fuse_read_interrupt(fiq, cs, nbytes, req);
	}

	if (forget_pending(fiq)) {
		if (list_empty(&fiq->pending) || fiq->forget_batch-- > 0)
			return fuse_read_forget(fc, fiq, cs, nbytes);

		if (fiq->forget_batch <= -8)
			fiq->forget_batch = 16;
	}

	req = list_entry(fiq->pending.next, struct fuse_req, list);
	clear_bit(FR_PENDING, &req->flags);
	list_del_init(&req->list);
	spin_unlock(&fiq->waitq.lock);

	in = &req->in;
	reqsize = in->h.len;

	if (task_active_pid_ns(current) != fc->pid_ns) {
		rcu_read_lock();
		in->h.pid = pid_vnr(find_pid_ns(in->h.pid, fc->pid_ns));
		rcu_read_unlock();
	}

	/* If request is too large, reply with an error and restart the read */
	if (nbytes < reqsize) {
		req->out.h.error = -EIO;
		/* SETXATTR is special, since it may contain too large data */
		if (in->h.opcode == FUSE_SETXATTR)
			req->out.h.error = -E2BIG;
		request_end(fc, req);
		goto restart;
	}
	spin_lock(&fpq->lock);
	list_add(&req->list, &fpq->io);
	spin_unlock(&fpq->lock);
	cs->req = req;
	err = fuse_copy_one(cs, &in->h, sizeof(in->h));
	if (!err)
		err = fuse_copy_args(cs, in->numargs, in->argpages,
				     (struct fuse_arg *) in->args, 0);
	fuse_copy_finish(cs);
	spin_lock(&fpq->lock);
	clear_bit(FR_LOCKED, &req->flags);
	if (!fpq->connected) {
		err = -ENODEV;
		goto out_end;
	}
	if (err) {
		req->out.h.error = -EIO;
		goto out_end;
	}
	if (!test_bit(FR_ISREPLY, &req->flags)) {
		err = reqsize;
		goto out_end;
	}
	list_move_tail(&req->list, &fpq->processing);
	__fuse_get_request(req);
	set_bit(FR_SENT, &req->flags);
	spin_unlock(&fpq->lock);
	/* matches barrier in request_wait_answer() */
	smp_mb__after_atomic();
	if (test_bit(FR_INTERRUPTED, &req->flags))
		queue_interrupt(fiq, req);
	fuse_put_request(fc, req);

	return reqsize;

out_end:
	if (!test_bit(FR_PRIVATE, &req->flags))
		list_del_init(&req->list);
	spin_unlock(&fpq->lock);
	request_end(fc, req);
	return err;

 err_unlock:
	spin_unlock(&fiq->waitq.lock);
	return err;
}

static int fuse_dev_open(struct inode *inode, struct file *file)
{
	/*
	 * The fuse device's file's private_data is used to hold
	 * the fuse_conn(ection) when it is mounted, and is used to
	 * keep track of whether the file has been mounted already.
	 */
	file->private_data = NULL;
	return 0;
}

static ssize_t fuse_dev_read(struct kiocb *iocb, struct iov_iter *to)
{
	struct fuse_copy_state cs;
	struct file *file = iocb->ki_filp;
	struct fuse_dev *fud = fuse_get_dev(file);

	if (!fud)
		return -EPERM;

	if (!iter_is_iovec(to))
		return -EINVAL;

	fuse_copy_init(&cs, 1, to);

	return fuse_dev_do_read(fud, file, &cs, iov_iter_count(to));
}

static ssize_t fuse_dev_splice_read(struct file *in, loff_t *ppos,
				    struct pipe_inode_info *pipe,
				    size_t len, unsigned int flags)
{
	int total, ret;
	int page_nr = 0;
	struct pipe_buffer *bufs;
	struct fuse_copy_state cs;
	struct fuse_dev *fud = fuse_get_dev(in);

	if (!fud)
		return -EPERM;

	bufs = kmalloc(pipe->buffers * sizeof(struct pipe_buffer), GFP_KERNEL);
	if (!bufs)
		return -ENOMEM;

	fuse_copy_init(&cs, 1, NULL);
	cs.pipebufs = bufs;
	cs.pipe = pipe;
	ret = fuse_dev_do_read(fud, in, &cs, len);
	if (ret < 0)
		goto out;

	if (pipe->nrbufs + cs.nr_segs > pipe->buffers) {
		ret = -EIO;
		goto out;
	}

	for (ret = total = 0; page_nr < cs.nr_segs; total += ret) {
		/*
		 * Need to be careful about this.  Having buf->ops in module
		 * code can Oops if the buffer persists after module unload.
		 */
		bufs[page_nr].ops = &nosteal_pipe_buf_ops;
		bufs[page_nr].flags = 0;
		ret = add_to_pipe(pipe, &bufs[page_nr++]);
		if (unlikely(ret < 0))
			break;
	}
	if (total)
		ret = total;
out:
	for (; page_nr < cs.nr_segs; page_nr++)
		put_page(bufs[page_nr].page);

	kfree(bufs);
	return ret;
}

static int fuse_notify_poll(struct fuse_conn *fc, unsigned int size,
			    struct fuse_copy_state *cs)
{
	struct fuse_notify_poll_wakeup_out outarg;
	int err = -EINVAL;

	if (size != sizeof(outarg))
		goto err;

	err = fuse_copy_one(cs, &outarg, sizeof(outarg));
	if (err)
		goto err;

	fuse_copy_finish(cs);
	return fuse_notify_poll_wakeup(fc, &outarg);

err:
	fuse_copy_finish(cs);
	return err;
}

static int fuse_notify_inval_inode(struct fuse_conn *fc, unsigned int size,
				   struct fuse_copy_state *cs)
{
	struct fuse_notify_inval_inode_out outarg;
	int err = -EINVAL;

	if (size != sizeof(outarg))
		goto err;

	err = fuse_copy_one(cs, &outarg, sizeof(outarg));
	if (err)
		goto err;
	fuse_copy_finish(cs);

	down_read(&fc->killsb);
	err = -ENOENT;
	if (fc->sb) {
		err = fuse_reverse_inval_inode(fc->sb, outarg.ino,
					       outarg.off, outarg.len);
	}
	up_read(&fc->killsb);
	return err;

err:
	fuse_copy_finish(cs);
	return err;
}

static int fuse_notify_inval_entry(struct fuse_conn *fc, unsigned int size,
				   struct fuse_copy_state *cs)
{
	struct fuse_notify_inval_entry_out outarg;
	int err = -ENOMEM;
	char *buf;
	struct qstr name;

	buf = kzalloc(FUSE_NAME_MAX + 1, GFP_KERNEL);
	if (!buf)
		goto err;

	err = -EINVAL;
	if (size < sizeof(outarg))
		goto err;

	err = fuse_copy_one(cs, &outarg, sizeof(outarg));
	if (err)
		goto err;

	err = -ENAMETOOLONG;
	if (outarg.namelen > FUSE_NAME_MAX)
		goto err;

	err = -EINVAL;
	if (size != sizeof(outarg) + outarg.namelen + 1)
		goto err;

	name.name = buf;
	name.len = outarg.namelen;
	err = fuse_copy_one(cs, buf, outarg.namelen + 1);
	if (err)
		goto err;
	fuse_copy_finish(cs);
	buf[outarg.namelen] = 0;

	down_read(&fc->killsb);
	err = -ENOENT;
	if (fc->sb)
		err = fuse_reverse_inval_entry(fc->sb, outarg.parent, 0, &name);
	up_read(&fc->killsb);
	kfree(buf);
	return err;

err:
	kfree(buf);
	fuse_copy_finish(cs);
	return err;
}

static int fuse_notify_delete(struct fuse_conn *fc, unsigned int size,
			      struct fuse_copy_state *cs)
{
	struct fuse_notify_delete_out outarg;
	int err = -ENOMEM;
	char *buf;
	struct qstr name;

	buf = kzalloc(FUSE_NAME_MAX + 1, GFP_KERNEL);
	if (!buf)
		goto err;

	err = -EINVAL;
	if (size < sizeof(outarg))
		goto err;

	err = fuse_copy_one(cs, &outarg, sizeof(outarg));
	if (err)
		goto err;

	err = -ENAMETOOLONG;
	if (outarg.namelen > FUSE_NAME_MAX)
		goto err;

	err = -EINVAL;
	if (size != sizeof(outarg) + outarg.namelen + 1)
		goto err;

	name.name = buf;
	name.len = outarg.namelen;
	err = fuse_copy_one(cs, buf, outarg.namelen + 1);
	if (err)
		goto err;
	fuse_copy_finish(cs);
	buf[outarg.namelen] = 0;

	down_read(&fc->killsb);
	err = -ENOENT;
	if (fc->sb)
		err = fuse_reverse_inval_entry(fc->sb, outarg.parent,
					       outarg.child, &name);
	up_read(&fc->killsb);
	kfree(buf);
	return err;

err:
	kfree(buf);
	fuse_copy_finish(cs);
	return err;
}

static int fuse_notify_store(struct fuse_conn *fc, unsigned int size,
			     struct fuse_copy_state *cs)
{
	struct fuse_notify_store_out outarg;
	struct inode *inode;
	struct address_space *mapping;
	u64 nodeid;
	int err;
	pgoff_t index;
	unsigned int offset;
	unsigned int num;
	loff_t file_size;
	loff_t end;

	err = -EINVAL;
	if (size < sizeof(outarg))
		goto out_finish;

	err = fuse_copy_one(cs, &outarg, sizeof(outarg));
	if (err)
		goto out_finish;

	err = -EINVAL;
	if (size - sizeof(outarg) != outarg.size)
		goto out_finish;

	nodeid = outarg.nodeid;

	down_read(&fc->killsb);

	err = -ENOENT;
	if (!fc->sb)
		goto out_up_killsb;

	inode = ilookup5(fc->sb, nodeid, fuse_inode_eq, &nodeid);
	if (!inode)
		goto out_up_killsb;

	mapping = inode->i_mapping;
	index = outarg.offset >> PAGE_SHIFT;
	offset = outarg.offset & ~PAGE_MASK;
	file_size = i_size_read(inode);
	end = outarg.offset + outarg.size;
	if (end > file_size) {
		file_size = end;
		fuse_write_update_size(inode, file_size);
	}

	num = outarg.size;
	while (num) {
		struct page *page;
		unsigned int this_num;

		err = -ENOMEM;
		page = find_or_create_page(mapping, index,
					   mapping_gfp_mask(mapping));
		if (!page)
			goto out_iput;

		this_num = min_t(unsigned, num, PAGE_SIZE - offset);
		err = fuse_copy_page(cs, &page, offset, this_num, 0);
		if (!err && offset == 0 &&
		    (this_num == PAGE_SIZE || file_size == end))
			SetPageUptodate(page);
		unlock_page(page);
		put_page(page);

		if (err)
			goto out_iput;

		num -= this_num;
		offset = 0;
		index++;
	}

	err = 0;

out_iput:
	iput(inode);
out_up_killsb:
	up_read(&fc->killsb);
out_finish:
	fuse_copy_finish(cs);
	return err;
}

static void fuse_retrieve_end(struct fuse_conn *fc, struct fuse_req *req)
{
	release_pages(req->pages, req->num_pages, false);
}

static int fuse_retrieve(struct fuse_conn *fc, struct inode *inode,
			 struct fuse_notify_retrieve_out *outarg)
{
	int err;
	struct address_space *mapping = inode->i_mapping;
	struct fuse_req *req;
	pgoff_t index;
	loff_t file_size;
	unsigned int num;
	unsigned int offset;
	size_t total_len = 0;
	int num_pages;

	offset = outarg->offset & ~PAGE_MASK;
	file_size = i_size_read(inode);

	num = outarg->size;
	if (outarg->offset > file_size)
		num = 0;
	else if (outarg->offset + num > file_size)
		num = file_size - outarg->offset;

	num_pages = (num + offset + PAGE_SIZE - 1) >> PAGE_SHIFT;
	num_pages = min(num_pages, FUSE_MAX_PAGES_PER_REQ);

	req = fuse_get_req(fc, num_pages);
	if (IS_ERR(req))
		return PTR_ERR(req);

	req->in.h.opcode = FUSE_NOTIFY_REPLY;
	req->in.h.nodeid = outarg->nodeid;
	req->in.numargs = 2;
	req->in.argpages = 1;
	req->page_descs[0].offset = offset;
	req->end = fuse_retrieve_end;

	index = outarg->offset >> PAGE_SHIFT;

	while (num && req->num_pages < num_pages) {
		struct page *page;
		unsigned int this_num;

		page = find_get_page(mapping, index);
		if (!page)
			break;

		this_num = min_t(unsigned, num, PAGE_SIZE - offset);
		req->pages[req->num_pages] = page;
		req->page_descs[req->num_pages].length = this_num;
		req->num_pages++;

		offset = 0;
		num -= this_num;
		total_len += this_num;
		index++;
	}
	req->misc.retrieve_in.offset = outarg->offset;
	req->misc.retrieve_in.size = total_len;
	req->in.args[0].size = sizeof(req->misc.retrieve_in);
	req->in.args[0].value = &req->misc.retrieve_in;
	req->in.args[1].size = total_len;

	err = fuse_request_send_notify_reply(fc, req, outarg->notify_unique);
	if (err) {
		fuse_retrieve_end(fc, req);
		fuse_put_request(fc, req);
	}

	return err;
}

static int fuse_notify_retrieve(struct fuse_conn *fc, unsigned int size,
				struct fuse_copy_state *cs)
{
	struct fuse_notify_retrieve_out outarg;
	struct inode *inode;
	int err;

	err = -EINVAL;
	if (size != sizeof(outarg))
		goto copy_finish;

	err = fuse_copy_one(cs, &outarg, sizeof(outarg));
	if (err)
		goto copy_finish;

	fuse_copy_finish(cs);

	down_read(&fc->killsb);
	err = -ENOENT;
	if (fc->sb) {
		u64 nodeid = outarg.nodeid;

		inode = ilookup5(fc->sb, nodeid, fuse_inode_eq, &nodeid);
		if (inode) {
			err = fuse_retrieve(fc, inode, &outarg);
			iput(inode);
		}
	}
	up_read(&fc->killsb);

	return err;

copy_finish:
	fuse_copy_finish(cs);
	return err;
}

static int fuse_notify(struct fuse_conn *fc, enum fuse_notify_code code,
		       unsigned int size, struct fuse_copy_state *cs)
{
	/* Don't try to move pages (yet) */
	cs->move_pages = 0;

	switch (code) {
	case FUSE_NOTIFY_POLL:
		return fuse_notify_poll(fc, size, cs);

	case FUSE_NOTIFY_INVAL_INODE:
		return fuse_notify_inval_inode(fc, size, cs);

	case FUSE_NOTIFY_INVAL_ENTRY:
		return fuse_notify_inval_entry(fc, size, cs);

	case FUSE_NOTIFY_STORE:
		return fuse_notify_store(fc, size, cs);

	case FUSE_NOTIFY_RETRIEVE:
		return fuse_notify_retrieve(fc, size, cs);

	case FUSE_NOTIFY_DELETE:
		return fuse_notify_delete(fc, size, cs);

	default:
		fuse_copy_finish(cs);
		return -EINVAL;
	}
}

/* Look up request on processing list by unique ID */
static struct fuse_req *request_find(struct fuse_pqueue *fpq, u64 unique)
{
	struct fuse_req *req;

	list_for_each_entry(req, &fpq->processing, list) {
		if (req->in.h.unique == unique || req->intr_unique == unique)
			return req;
	}
	return NULL;
}

static int copy_out_args(struct fuse_copy_state *cs, struct fuse_out *out,
			 unsigned nbytes)
{
	unsigned reqsize = sizeof(struct fuse_out_header);

	if (out->h.error)
		return nbytes != reqsize ? -EINVAL : 0;

	reqsize += len_args(out->numargs, out->args);

	if (reqsize < nbytes || (reqsize > nbytes && !out->argvar))
		return -EINVAL;
	else if (reqsize > nbytes) {
		struct fuse_arg *lastarg = &out->args[out->numargs-1];
		unsigned diffsize = reqsize - nbytes;
		if (diffsize > lastarg->size)
			return -EINVAL;
		lastarg->size -= diffsize;
	}
	return fuse_copy_args(cs, out->numargs, out->argpages, out->args,
			      out->page_zeroing);
}

/*
 * Write a single reply to a request.  First the header is copied from
 * the write buffer.  The request is then searched on the processing
 * list by the unique ID found in the header.  If found, then remove
 * it from the list and copy the rest of the buffer to the request.
 * The request is finished by calling request_end()
 */
static ssize_t fuse_dev_do_write(struct fuse_dev *fud,
				 struct fuse_copy_state *cs, size_t nbytes)
{
	int err;
	struct fuse_conn *fc = fud->fc;
	struct fuse_pqueue *fpq = &fud->pq;
	struct fuse_req *req;
	struct fuse_out_header oh;

	if (nbytes < sizeof(struct fuse_out_header))
		return -EINVAL;

	err = fuse_copy_one(cs, &oh, sizeof(oh));
	if (err)
		goto err_finish;

	err = -EINVAL;
	if (oh.len != nbytes)
		goto err_finish;

	/*
	 * Zero oh.unique indicates unsolicited notification message
	 * and error contains notification code.
	 */
	if (!oh.unique) {
		err = fuse_notify(fc, oh.error, nbytes - sizeof(oh), cs);
		return err ? err : nbytes;
	}

	err = -EINVAL;
	if (oh.error <= -1000 || oh.error > 0)
		goto err_finish;

	spin_lock(&fpq->lock);
	err = -ENOENT;
	if (!fpq->connected)
		goto err_unlock_pq;

	req = request_find(fpq, oh.unique);
	if (!req)
		goto err_unlock_pq;

	/* Is it an interrupt reply? */
	if (req->intr_unique == oh.unique) {
		__fuse_get_request(req);
		spin_unlock(&fpq->lock);

		err = -EINVAL;
		if (nbytes != sizeof(struct fuse_out_header)) {
			fuse_put_request(fc, req);
			goto err_finish;
		}

		if (oh.error == -ENOSYS)
			fc->no_interrupt = 1;
		else if (oh.error == -EAGAIN)
			queue_interrupt(&fc->iq, req);
		fuse_put_request(fc, req);

		fuse_copy_finish(cs);
		return nbytes;
	}

	clear_bit(FR_SENT, &req->flags);
	list_move(&req->list, &fpq->io);
	req->out.h = oh;
	set_bit(FR_LOCKED, &req->flags);
	spin_unlock(&fpq->lock);
	cs->req = req;
	if (!req->out.page_replace)
		cs->move_pages = 0;

	err = copy_out_args(cs, &req->out, nbytes);
	fuse_copy_finish(cs);

	spin_lock(&fpq->lock);
	clear_bit(FR_LOCKED, &req->flags);
	if (!fpq->connected)
		err = -ENOENT;
	else if (err)
		req->out.h.error = -EIO;
	if (!test_bit(FR_PRIVATE, &req->flags))
		list_del_init(&req->list);
	spin_unlock(&fpq->lock);

	request_end(fc, req);

	return err ? err : nbytes;

 err_unlock_pq:
	spin_unlock(&fpq->lock);
 err_finish:
	fuse_copy_finish(cs);
	return err;
}

static ssize_t fuse_dev_write(struct kiocb *iocb, struct iov_iter *from)
{
	struct fuse_copy_state cs;
	struct fuse_dev *fud = fuse_get_dev(iocb->ki_filp);

	if (!fud)
		return -EPERM;

	if (!iter_is_iovec(from))
		return -EINVAL;

	fuse_copy_init(&cs, 0, from);

	return fuse_dev_do_write(fud, &cs, iov_iter_count(from));
}

static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe,
				     struct file *out, loff_t *ppos,
				     size_t len, unsigned int flags)
{
	unsigned nbuf;
	unsigned idx;
	struct pipe_buffer *bufs;
	struct fuse_copy_state cs;
	struct fuse_dev *fud;
	size_t rem;
	ssize_t ret;

	fud = fuse_get_dev(out);
	if (!fud)
		return -EPERM;

	pipe_lock(pipe);

	bufs = kmalloc(pipe->buffers * sizeof(struct pipe_buffer), GFP_KERNEL);
	if (!bufs) {
		pipe_unlock(pipe);
		return -ENOMEM;
	}

	nbuf = 0;
	rem = 0;
	for (idx = 0; idx < pipe->nrbufs && rem < len; idx++)
		rem += pipe->bufs[(pipe->curbuf + idx) & (pipe->buffers - 1)].len;

	ret = -EINVAL;
	if (rem < len) {
		pipe_unlock(pipe);
		goto out;
	}

	rem = len;
	while (rem) {
		struct pipe_buffer *ibuf;
		struct pipe_buffer *obuf;

		BUG_ON(nbuf >= pipe->buffers);
		BUG_ON(!pipe->nrbufs);
		ibuf = &pipe->bufs[pipe->curbuf];
		obuf = &bufs[nbuf];

		if (rem >= ibuf->len) {
			*obuf = *ibuf;
			ibuf->ops = NULL;
			pipe->curbuf = (pipe->curbuf + 1) & (pipe->buffers - 1);
			pipe->nrbufs--;
		} else {
			pipe_buf_get(pipe, ibuf);
			*obuf = *ibuf;
			obuf->flags &= ~PIPE_BUF_FLAG_GIFT;
			obuf->len = rem;
			ibuf->offset += obuf->len;
			ibuf->len -= obuf->len;
		}
		nbuf++;
		rem -= obuf->len;
	}
	pipe_unlock(pipe);

	fuse_copy_init(&cs, 0, NULL);
	cs.pipebufs = bufs;
	cs.nr_segs = nbuf;
	cs.pipe = pipe;

	if (flags & SPLICE_F_MOVE)
		cs.move_pages = 1;

	ret = fuse_dev_do_write(fud, &cs, len);

	for (idx = 0; idx < nbuf; idx++)
		pipe_buf_release(pipe, &bufs[idx]);

out:
	kfree(bufs);
	return ret;
}

static unsigned fuse_dev_poll(struct file *file, poll_table *wait)
{
	unsigned mask = POLLOUT | POLLWRNORM;
	struct fuse_iqueue *fiq;
	struct fuse_dev *fud = fuse_get_dev(file);

	if (!fud)
		return POLLERR;

	fiq = &fud->fc->iq;
	poll_wait(file, &fiq->waitq, wait);

	spin_lock(&fiq->waitq.lock);
	if (!fiq->connected)
		mask = POLLERR;
	else if (request_pending(fiq))
		mask |= POLLIN | POLLRDNORM;
	spin_unlock(&fiq->waitq.lock);

	return mask;
}

/*
 * Abort all requests on the given list (pending or processing)
 *
 * This function releases and reacquires fc->lock
 */
static void end_requests(struct fuse_conn *fc, struct list_head *head)
{
	while (!list_empty(head)) {
		struct fuse_req *req;
		req = list_entry(head->next, struct fuse_req, list);
		req->out.h.error = -ECONNABORTED;
		clear_bit(FR_SENT, &req->flags);
		list_del_init(&req->list);
		request_end(fc, req);
	}
}

static void end_polls(struct fuse_conn *fc)
{
	struct rb_node *p;

	p = rb_first(&fc->polled_files);

	while (p) {
		struct fuse_file *ff;
		ff = rb_entry(p, struct fuse_file, polled_node);
		wake_up_interruptible_all(&ff->poll_wait);

		p = rb_next(p);
	}
}

/*
 * Abort all requests.
 *
 * Emergency exit in case of a malicious or accidental deadlock, or just a hung
 * filesystem.
 *
 * The same effect is usually achievable through killing the filesystem daemon
 * and all users of the filesystem.  The exception is the combination of an
 * asynchronous request and the tricky deadlock (see
 * Documentation/filesystems/fuse.txt).
 *
 * Aborting requests under I/O goes as follows: 1: Separate out unlocked
 * requests, they should be finished off immediately.  Locked requests will be
 * finished after unlock; see unlock_request(). 2: Finish off the unlocked
 * requests.  It is possible that some request will finish before we can.  This
 * is OK, the request will in that case be removed from the list before we touch
 * it.
 */
void fuse_abort_conn(struct fuse_conn *fc)
{
	struct fuse_iqueue *fiq = &fc->iq;

	spin_lock(&fc->lock);
	if (fc->connected) {
		struct fuse_dev *fud;
		struct fuse_req *req, *next;
		LIST_HEAD(to_end1);
		LIST_HEAD(to_end2);

		fc->connected = 0;
		fc->blocked = 0;
		fuse_set_initialized(fc);
		list_for_each_entry(fud, &fc->devices, entry) {
			struct fuse_pqueue *fpq = &fud->pq;

			spin_lock(&fpq->lock);
			fpq->connected = 0;
			list_for_each_entry_safe(req, next, &fpq->io, list) {
				req->out.h.error = -ECONNABORTED;
				spin_lock(&req->waitq.lock);
				set_bit(FR_ABORTED, &req->flags);
				if (!test_bit(FR_LOCKED, &req->flags)) {
					set_bit(FR_PRIVATE, &req->flags);
					__fuse_get_request(req);
					list_move(&req->list, &to_end1);
				}
				spin_unlock(&req->waitq.lock);
			}
			list_splice_init(&fpq->processing, &to_end2);
			spin_unlock(&fpq->lock);
		}
		fc->max_background = UINT_MAX;
		flush_bg_queue(fc);

		spin_lock(&fiq->waitq.lock);
		fiq->connected = 0;
		list_splice_init(&fiq->pending, &to_end2);
		list_for_each_entry(req, &to_end2, list)
			clear_bit(FR_PENDING, &req->flags);
		while (forget_pending(fiq))
			kfree(dequeue_forget(fiq, 1, NULL));
		wake_up_all_locked(&fiq->waitq);
		spin_unlock(&fiq->waitq.lock);
		kill_fasync(&fiq->fasync, SIGIO, POLL_IN);
		end_polls(fc);
		wake_up_all(&fc->blocked_waitq);
		spin_unlock(&fc->lock);

		while (!list_empty(&to_end1)) {
			req = list_first_entry(&to_end1, struct fuse_req, list);
			list_del_init(&req->list);
			request_end(fc, req);
		}
		end_requests(fc, &to_end2);
	} else {
		spin_unlock(&fc->lock);
	}
}
EXPORT_SYMBOL_GPL(fuse_abort_conn);

void fuse_wait_aborted(struct fuse_conn *fc)
{
	wait_event(fc->blocked_waitq, atomic_read(&fc->num_waiting) == 0);
}

int fuse_dev_release(struct inode *inode, struct file *file)
{
	struct fuse_dev *fud = fuse_get_dev(file);

	if (fud) {
		struct fuse_conn *fc = fud->fc;
		struct fuse_pqueue *fpq = &fud->pq;
		LIST_HEAD(to_end);

		spin_lock(&fpq->lock);
		WARN_ON(!list_empty(&fpq->io));
		list_splice_init(&fpq->processing, &to_end);
		spin_unlock(&fpq->lock);

		end_requests(fc, &to_end);

		/* Are we the last open device? */
		if (atomic_dec_and_test(&fc->dev_count)) {
			WARN_ON(fc->iq.fasync != NULL);
			fuse_abort_conn(fc);
		}
		fuse_dev_free(fud);
	}
	return 0;
}
EXPORT_SYMBOL_GPL(fuse_dev_release);

static int fuse_dev_fasync(int fd, struct file *file, int on)
{
	struct fuse_dev *fud = fuse_get_dev(file);

	if (!fud)
		return -EPERM;

	/* No locking - fasync_helper does its own locking */
	return fasync_helper(fd, file, on, &fud->fc->iq.fasync);
}

static int fuse_device_clone(struct fuse_conn *fc, struct file *new)
{
	struct fuse_dev *fud;

	if (new->private_data)
		return -EINVAL;

	fud = fuse_dev_alloc(fc);
	if (!fud)
		return -ENOMEM;

	new->private_data = fud;
	atomic_inc(&fc->dev_count);

	return 0;
}

static long fuse_dev_ioctl(struct file *file, unsigned int cmd,
			   unsigned long arg)
{
	int err = -ENOTTY;

	if (cmd == FUSE_DEV_IOC_CLONE) {
		int oldfd;

		err = -EFAULT;
		if (!get_user(oldfd, (__u32 __user *) arg)) {
			struct file *old = fget(oldfd);

			err = -EINVAL;
			if (old) {
				struct fuse_dev *fud = NULL;

				/*
				 * Check against file->f_op because CUSE
				 * uses the same ioctl handler.
				 */
				if (old->f_op == file->f_op &&
				    old->f_cred->user_ns == file->f_cred->user_ns)
					fud = fuse_get_dev(old);

				if (fud) {
					mutex_lock(&fuse_mutex);
					err = fuse_device_clone(fud->fc, file);
					mutex_unlock(&fuse_mutex);
				}
				fput(old);
			}
		}
	}
	return err;
}

const struct file_operations fuse_dev_operations = {
	.owner		= THIS_MODULE,
	.open		= fuse_dev_open,
	.llseek		= no_llseek,
	.read_iter	= fuse_dev_read,
	.splice_read	= fuse_dev_splice_read,
	.write_iter	= fuse_dev_write,
	.splice_write	= fuse_dev_splice_write,
	.poll		= fuse_dev_poll,
	.release	= fuse_dev_release,
	.fasync		= fuse_dev_fasync,
	.unlocked_ioctl = fuse_dev_ioctl,
	.compat_ioctl   = fuse_dev_ioctl,
};
EXPORT_SYMBOL_GPL(fuse_dev_operations);

static struct miscdevice fuse_miscdevice = {
	.minor = FUSE_MINOR,
	.name  = "fuse",
	.fops = &fuse_dev_operations,
};

int __init fuse_dev_init(void)
{
	int err = -ENOMEM;
	fuse_req_cachep = kmem_cache_create("fuse_request",
					    sizeof(struct fuse_req),
					    0, 0, NULL);
	if (!fuse_req_cachep)
		goto out;

	err = misc_register(&fuse_miscdevice);
	if (err)
		goto out_cache_clean;

	return 0;

 out_cache_clean:
	kmem_cache_destroy(fuse_req_cachep);
 out:
	return err;
}

void fuse_dev_cleanup(void)
{
	misc_deregister(&fuse_miscdevice);
	kmem_cache_destroy(fuse_req_cachep);
}