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
|
// SPDX-License-Identifier: GPL-2.0
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/file.h>
#include <linux/slab.h>
#include <linux/net.h>
#include <linux/compat.h>
#include <net/compat.h>
#include <linux/io_uring.h>
#include <uapi/linux/io_uring.h>
#include "io_uring.h"
#include "kbuf.h"
#include "alloc_cache.h"
#include "net.h"
#include "notif.h"
#include "rsrc.h"
#if defined(CONFIG_NET)
struct io_shutdown {
struct file *file;
int how;
};
struct io_accept {
struct file *file;
struct sockaddr __user *addr;
int __user *addr_len;
int flags;
u32 file_slot;
unsigned long nofile;
};
struct io_socket {
struct file *file;
int domain;
int type;
int protocol;
int flags;
u32 file_slot;
unsigned long nofile;
};
struct io_connect {
struct file *file;
struct sockaddr __user *addr;
int addr_len;
bool in_progress;
bool seen_econnaborted;
};
struct io_sr_msg {
struct file *file;
union {
struct compat_msghdr __user *umsg_compat;
struct user_msghdr __user *umsg;
void __user *buf;
};
int len;
unsigned done_io;
unsigned msg_flags;
unsigned nr_multishot_loops;
u16 flags;
/* initialised and used only by !msg send variants */
u16 addr_len;
u16 buf_group;
void __user *addr;
void __user *msg_control;
/* used only for send zerocopy */
struct io_kiocb *notif;
};
/*
* Number of times we'll try and do receives if there's more data. If we
* exceed this limit, then add us to the back of the queue and retry from
* there. This helps fairness between flooding clients.
*/
#define MULTISHOT_MAX_RETRY 32
int io_shutdown_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
struct io_shutdown *shutdown = io_kiocb_to_cmd(req, struct io_shutdown);
if (unlikely(sqe->off || sqe->addr || sqe->rw_flags ||
sqe->buf_index || sqe->splice_fd_in))
return -EINVAL;
shutdown->how = READ_ONCE(sqe->len);
req->flags |= REQ_F_FORCE_ASYNC;
return 0;
}
int io_shutdown(struct io_kiocb *req, unsigned int issue_flags)
{
struct io_shutdown *shutdown = io_kiocb_to_cmd(req, struct io_shutdown);
struct socket *sock;
int ret;
WARN_ON_ONCE(issue_flags & IO_URING_F_NONBLOCK);
sock = sock_from_file(req->file);
if (unlikely(!sock))
return -ENOTSOCK;
ret = __sys_shutdown_sock(sock, shutdown->how);
io_req_set_res(req, ret, 0);
return IOU_OK;
}
static bool io_net_retry(struct socket *sock, int flags)
{
if (!(flags & MSG_WAITALL))
return false;
return sock->type == SOCK_STREAM || sock->type == SOCK_SEQPACKET;
}
static void io_netmsg_iovec_free(struct io_async_msghdr *kmsg)
{
if (kmsg->free_iov) {
kfree(kmsg->free_iov);
kmsg->free_iov_nr = 0;
kmsg->free_iov = NULL;
}
}
static void io_netmsg_recycle(struct io_kiocb *req, unsigned int issue_flags)
{
struct io_async_msghdr *hdr = req->async_data;
struct iovec *iov;
/* can't recycle, ensure we free the iovec if we have one */
if (unlikely(issue_flags & IO_URING_F_UNLOCKED)) {
io_netmsg_iovec_free(hdr);
return;
}
/* Let normal cleanup path reap it if we fail adding to the cache */
iov = hdr->free_iov;
if (io_alloc_cache_put(&req->ctx->netmsg_cache, hdr)) {
if (iov)
kasan_mempool_poison_object(iov);
req->async_data = NULL;
req->flags &= ~REQ_F_ASYNC_DATA;
}
}
static struct io_async_msghdr *io_msg_alloc_async(struct io_kiocb *req)
{
struct io_ring_ctx *ctx = req->ctx;
struct io_async_msghdr *hdr;
hdr = io_alloc_cache_get(&ctx->netmsg_cache);
if (hdr) {
if (hdr->free_iov) {
kasan_mempool_unpoison_object(hdr->free_iov,
hdr->free_iov_nr * sizeof(struct iovec));
req->flags |= REQ_F_NEED_CLEANUP;
}
req->flags |= REQ_F_ASYNC_DATA;
req->async_data = hdr;
return hdr;
}
if (!io_alloc_async_data(req)) {
hdr = req->async_data;
hdr->free_iov_nr = 0;
hdr->free_iov = NULL;
return hdr;
}
return NULL;
}
/* assign new iovec to kmsg, if we need to */
static int io_net_vec_assign(struct io_kiocb *req, struct io_async_msghdr *kmsg,
struct iovec *iov)
{
if (iov) {
req->flags |= REQ_F_NEED_CLEANUP;
kmsg->free_iov_nr = kmsg->msg.msg_iter.nr_segs;
if (kmsg->free_iov)
kfree(kmsg->free_iov);
kmsg->free_iov = iov;
}
return 0;
}
static inline void io_mshot_prep_retry(struct io_kiocb *req,
struct io_async_msghdr *kmsg)
{
struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg);
req->flags &= ~REQ_F_BL_EMPTY;
sr->done_io = 0;
sr->len = 0; /* get from the provided buffer */
req->buf_index = sr->buf_group;
}
#ifdef CONFIG_COMPAT
static int io_compat_msg_copy_hdr(struct io_kiocb *req,
struct io_async_msghdr *iomsg,
struct compat_msghdr *msg, int ddir)
{
struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg);
struct compat_iovec __user *uiov;
struct iovec *iov;
int ret, nr_segs;
if (iomsg->free_iov) {
nr_segs = iomsg->free_iov_nr;
iov = iomsg->free_iov;
} else {
iov = &iomsg->fast_iov;
nr_segs = 1;
}
if (copy_from_user(msg, sr->umsg_compat, sizeof(*msg)))
return -EFAULT;
uiov = compat_ptr(msg->msg_iov);
if (req->flags & REQ_F_BUFFER_SELECT) {
compat_ssize_t clen;
if (msg->msg_iovlen == 0) {
sr->len = iov->iov_len = 0;
iov->iov_base = NULL;
} else if (msg->msg_iovlen > 1) {
return -EINVAL;
} else {
if (!access_ok(uiov, sizeof(*uiov)))
return -EFAULT;
if (__get_user(clen, &uiov->iov_len))
return -EFAULT;
if (clen < 0)
return -EINVAL;
sr->len = clen;
}
return 0;
}
ret = __import_iovec(ddir, (struct iovec __user *)uiov, msg->msg_iovlen,
nr_segs, &iov, &iomsg->msg.msg_iter, true);
if (unlikely(ret < 0))
return ret;
return io_net_vec_assign(req, iomsg, iov);
}
#endif
static int io_msg_copy_hdr(struct io_kiocb *req, struct io_async_msghdr *iomsg,
struct user_msghdr *msg, int ddir)
{
struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg);
struct iovec *iov;
int ret, nr_segs;
if (iomsg->free_iov) {
nr_segs = iomsg->free_iov_nr;
iov = iomsg->free_iov;
} else {
iov = &iomsg->fast_iov;
nr_segs = 1;
}
if (!user_access_begin(sr->umsg, sizeof(*sr->umsg)))
return -EFAULT;
ret = -EFAULT;
unsafe_get_user(msg->msg_name, &sr->umsg->msg_name, ua_end);
unsafe_get_user(msg->msg_namelen, &sr->umsg->msg_namelen, ua_end);
unsafe_get_user(msg->msg_iov, &sr->umsg->msg_iov, ua_end);
unsafe_get_user(msg->msg_iovlen, &sr->umsg->msg_iovlen, ua_end);
unsafe_get_user(msg->msg_control, &sr->umsg->msg_control, ua_end);
unsafe_get_user(msg->msg_controllen, &sr->umsg->msg_controllen, ua_end);
msg->msg_flags = 0;
if (req->flags & REQ_F_BUFFER_SELECT) {
if (msg->msg_iovlen == 0) {
sr->len = iov->iov_len = 0;
iov->iov_base = NULL;
} else if (msg->msg_iovlen > 1) {
ret = -EINVAL;
goto ua_end;
} else {
/* we only need the length for provided buffers */
if (!access_ok(&msg->msg_iov[0].iov_len, sizeof(__kernel_size_t)))
goto ua_end;
unsafe_get_user(iov->iov_len, &msg->msg_iov[0].iov_len,
ua_end);
sr->len = iov->iov_len;
}
ret = 0;
ua_end:
user_access_end();
return ret;
}
user_access_end();
ret = __import_iovec(ddir, msg->msg_iov, msg->msg_iovlen, nr_segs,
&iov, &iomsg->msg.msg_iter, false);
if (unlikely(ret < 0))
return ret;
return io_net_vec_assign(req, iomsg, iov);
}
static int io_sendmsg_copy_hdr(struct io_kiocb *req,
struct io_async_msghdr *iomsg)
{
struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg);
struct user_msghdr msg;
int ret;
iomsg->msg.msg_name = &iomsg->addr;
iomsg->msg.msg_iter.nr_segs = 0;
#ifdef CONFIG_COMPAT
if (unlikely(req->ctx->compat)) {
struct compat_msghdr cmsg;
ret = io_compat_msg_copy_hdr(req, iomsg, &cmsg, ITER_SOURCE);
if (unlikely(ret))
return ret;
return __get_compat_msghdr(&iomsg->msg, &cmsg, NULL);
}
#endif
ret = io_msg_copy_hdr(req, iomsg, &msg, ITER_SOURCE);
if (unlikely(ret))
return ret;
ret = __copy_msghdr(&iomsg->msg, &msg, NULL);
/* save msg_control as sys_sendmsg() overwrites it */
sr->msg_control = iomsg->msg.msg_control_user;
return ret;
}
void io_sendmsg_recvmsg_cleanup(struct io_kiocb *req)
{
struct io_async_msghdr *io = req->async_data;
io_netmsg_iovec_free(io);
}
static int io_send_setup(struct io_kiocb *req)
{
struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg);
struct io_async_msghdr *kmsg = req->async_data;
int ret;
kmsg->msg.msg_name = NULL;
kmsg->msg.msg_namelen = 0;
kmsg->msg.msg_control = NULL;
kmsg->msg.msg_controllen = 0;
kmsg->msg.msg_ubuf = NULL;
if (sr->addr) {
ret = move_addr_to_kernel(sr->addr, sr->addr_len, &kmsg->addr);
if (unlikely(ret < 0))
return ret;
kmsg->msg.msg_name = &kmsg->addr;
kmsg->msg.msg_namelen = sr->addr_len;
}
if (!io_do_buffer_select(req)) {
ret = import_ubuf(ITER_SOURCE, sr->buf, sr->len,
&kmsg->msg.msg_iter);
if (unlikely(ret < 0))
return ret;
}
return 0;
}
static int io_sendmsg_prep_setup(struct io_kiocb *req, int is_msg)
{
struct io_async_msghdr *kmsg;
int ret;
kmsg = io_msg_alloc_async(req);
if (unlikely(!kmsg))
return -ENOMEM;
if (!is_msg)
return io_send_setup(req);
ret = io_sendmsg_copy_hdr(req, kmsg);
if (!ret)
req->flags |= REQ_F_NEED_CLEANUP;
return ret;
}
#define SENDMSG_FLAGS (IORING_RECVSEND_POLL_FIRST | IORING_RECVSEND_BUNDLE)
int io_sendmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg);
sr->done_io = 0;
if (req->opcode == IORING_OP_SEND) {
if (READ_ONCE(sqe->__pad3[0]))
return -EINVAL;
sr->addr = u64_to_user_ptr(READ_ONCE(sqe->addr2));
sr->addr_len = READ_ONCE(sqe->addr_len);
} else if (sqe->addr2 || sqe->file_index) {
return -EINVAL;
}
sr->umsg = u64_to_user_ptr(READ_ONCE(sqe->addr));
sr->len = READ_ONCE(sqe->len);
sr->flags = READ_ONCE(sqe->ioprio);
if (sr->flags & ~SENDMSG_FLAGS)
return -EINVAL;
sr->msg_flags = READ_ONCE(sqe->msg_flags) | MSG_NOSIGNAL;
if (sr->msg_flags & MSG_DONTWAIT)
req->flags |= REQ_F_NOWAIT;
if (sr->flags & IORING_RECVSEND_BUNDLE) {
if (req->opcode == IORING_OP_SENDMSG)
return -EINVAL;
if (!(req->flags & REQ_F_BUFFER_SELECT))
return -EINVAL;
sr->msg_flags |= MSG_WAITALL;
sr->buf_group = req->buf_index;
req->buf_list = NULL;
}
if (req->flags & REQ_F_BUFFER_SELECT && sr->len)
return -EINVAL;
#ifdef CONFIG_COMPAT
if (req->ctx->compat)
sr->msg_flags |= MSG_CMSG_COMPAT;
#endif
return io_sendmsg_prep_setup(req, req->opcode == IORING_OP_SENDMSG);
}
static void io_req_msg_cleanup(struct io_kiocb *req,
unsigned int issue_flags)
{
req->flags &= ~REQ_F_NEED_CLEANUP;
io_netmsg_recycle(req, issue_flags);
}
/*
* For bundle completions, we need to figure out how many segments we consumed.
* A bundle could be using a single ITER_UBUF if that's all we mapped, or it
* could be using an ITER_IOVEC. If the latter, then if we consumed all of
* the segments, then it's a trivial questiont o answer. If we have residual
* data in the iter, then loop the segments to figure out how much we
* transferred.
*/
static int io_bundle_nbufs(struct io_async_msghdr *kmsg, int ret)
{
struct iovec *iov;
int nbufs;
/* no data is always zero segments, and a ubuf is always 1 segment */
if (ret <= 0)
return 0;
if (iter_is_ubuf(&kmsg->msg.msg_iter))
return 1;
iov = kmsg->free_iov;
if (!iov)
iov = &kmsg->fast_iov;
/* if all data was transferred, it's basic pointer math */
if (!iov_iter_count(&kmsg->msg.msg_iter))
return iter_iov(&kmsg->msg.msg_iter) - iov;
/* short transfer, count segments */
nbufs = 0;
do {
int this_len = min_t(int, iov[nbufs].iov_len, ret);
nbufs++;
ret -= this_len;
} while (ret);
return nbufs;
}
static inline bool io_send_finish(struct io_kiocb *req, int *ret,
struct io_async_msghdr *kmsg,
unsigned issue_flags)
{
struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg);
bool bundle_finished = *ret <= 0;
unsigned int cflags;
if (!(sr->flags & IORING_RECVSEND_BUNDLE)) {
cflags = io_put_kbuf(req, issue_flags);
goto finish;
}
cflags = io_put_kbufs(req, io_bundle_nbufs(kmsg, *ret), issue_flags);
if (bundle_finished || req->flags & REQ_F_BL_EMPTY)
goto finish;
/*
* Fill CQE for this receive and see if we should keep trying to
* receive from this socket.
*/
if (io_req_post_cqe(req, *ret, cflags | IORING_CQE_F_MORE)) {
io_mshot_prep_retry(req, kmsg);
return false;
}
/* Otherwise stop bundle and use the current result. */
finish:
io_req_set_res(req, *ret, cflags);
*ret = IOU_OK;
return true;
}
int io_sendmsg(struct io_kiocb *req, unsigned int issue_flags)
{
struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg);
struct io_async_msghdr *kmsg = req->async_data;
struct socket *sock;
unsigned flags;
int min_ret = 0;
int ret;
sock = sock_from_file(req->file);
if (unlikely(!sock))
return -ENOTSOCK;
if (!(req->flags & REQ_F_POLLED) &&
(sr->flags & IORING_RECVSEND_POLL_FIRST))
return -EAGAIN;
flags = sr->msg_flags;
if (issue_flags & IO_URING_F_NONBLOCK)
flags |= MSG_DONTWAIT;
if (flags & MSG_WAITALL)
min_ret = iov_iter_count(&kmsg->msg.msg_iter);
kmsg->msg.msg_control_user = sr->msg_control;
ret = __sys_sendmsg_sock(sock, &kmsg->msg, flags);
if (ret < min_ret) {
if (ret == -EAGAIN && (issue_flags & IO_URING_F_NONBLOCK))
return -EAGAIN;
if (ret > 0 && io_net_retry(sock, flags)) {
kmsg->msg.msg_controllen = 0;
kmsg->msg.msg_control = NULL;
sr->done_io += ret;
req->flags |= REQ_F_BL_NO_RECYCLE;
return -EAGAIN;
}
if (ret == -ERESTARTSYS)
ret = -EINTR;
req_set_fail(req);
}
io_req_msg_cleanup(req, issue_flags);
if (ret >= 0)
ret += sr->done_io;
else if (sr->done_io)
ret = sr->done_io;
io_req_set_res(req, ret, 0);
return IOU_OK;
}
int io_send(struct io_kiocb *req, unsigned int issue_flags)
{
struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg);
struct io_async_msghdr *kmsg = req->async_data;
struct socket *sock;
unsigned flags;
int min_ret = 0;
int ret;
sock = sock_from_file(req->file);
if (unlikely(!sock))
return -ENOTSOCK;
if (!(req->flags & REQ_F_POLLED) &&
(sr->flags & IORING_RECVSEND_POLL_FIRST))
return -EAGAIN;
flags = sr->msg_flags;
if (issue_flags & IO_URING_F_NONBLOCK)
flags |= MSG_DONTWAIT;
retry_bundle:
if (io_do_buffer_select(req)) {
struct buf_sel_arg arg = {
.iovs = &kmsg->fast_iov,
.max_len = INT_MAX,
.nr_iovs = 1,
.mode = KBUF_MODE_EXPAND,
};
if (kmsg->free_iov) {
arg.nr_iovs = kmsg->free_iov_nr;
arg.iovs = kmsg->free_iov;
arg.mode |= KBUF_MODE_FREE;
}
if (!(sr->flags & IORING_RECVSEND_BUNDLE))
arg.nr_iovs = 1;
ret = io_buffers_select(req, &arg, issue_flags);
if (unlikely(ret < 0))
return ret;
sr->len = arg.out_len;
iov_iter_init(&kmsg->msg.msg_iter, ITER_SOURCE, arg.iovs, ret,
arg.out_len);
if (arg.iovs != &kmsg->fast_iov && arg.iovs != kmsg->free_iov) {
kmsg->free_iov_nr = ret;
kmsg->free_iov = arg.iovs;
}
}
/*
* If MSG_WAITALL is set, or this is a bundle send, then we need
* the full amount. If just bundle is set, if we do a short send
* then we complete the bundle sequence rather than continue on.
*/
if (flags & MSG_WAITALL || sr->flags & IORING_RECVSEND_BUNDLE)
min_ret = iov_iter_count(&kmsg->msg.msg_iter);
flags &= ~MSG_INTERNAL_SENDMSG_FLAGS;
kmsg->msg.msg_flags = flags;
ret = sock_sendmsg(sock, &kmsg->msg);
if (ret < min_ret) {
if (ret == -EAGAIN && (issue_flags & IO_URING_F_NONBLOCK))
return -EAGAIN;
if (ret > 0 && io_net_retry(sock, flags)) {
sr->len -= ret;
sr->buf += ret;
sr->done_io += ret;
req->flags |= REQ_F_BL_NO_RECYCLE;
return -EAGAIN;
}
if (ret == -ERESTARTSYS)
ret = -EINTR;
req_set_fail(req);
}
if (ret >= 0)
ret += sr->done_io;
else if (sr->done_io)
ret = sr->done_io;
if (!io_send_finish(req, &ret, kmsg, issue_flags))
goto retry_bundle;
io_req_msg_cleanup(req, issue_flags);
return ret;
}
static int io_recvmsg_mshot_prep(struct io_kiocb *req,
struct io_async_msghdr *iomsg,
int namelen, size_t controllen)
{
if ((req->flags & (REQ_F_APOLL_MULTISHOT|REQ_F_BUFFER_SELECT)) ==
(REQ_F_APOLL_MULTISHOT|REQ_F_BUFFER_SELECT)) {
int hdr;
if (unlikely(namelen < 0))
return -EOVERFLOW;
if (check_add_overflow(sizeof(struct io_uring_recvmsg_out),
namelen, &hdr))
return -EOVERFLOW;
if (check_add_overflow(hdr, controllen, &hdr))
return -EOVERFLOW;
iomsg->namelen = namelen;
iomsg->controllen = controllen;
return 0;
}
return 0;
}
static int io_recvmsg_copy_hdr(struct io_kiocb *req,
struct io_async_msghdr *iomsg)
{
struct user_msghdr msg;
int ret;
iomsg->msg.msg_name = &iomsg->addr;
iomsg->msg.msg_iter.nr_segs = 0;
#ifdef CONFIG_COMPAT
if (unlikely(req->ctx->compat)) {
struct compat_msghdr cmsg;
ret = io_compat_msg_copy_hdr(req, iomsg, &cmsg, ITER_DEST);
if (unlikely(ret))
return ret;
ret = __get_compat_msghdr(&iomsg->msg, &cmsg, &iomsg->uaddr);
if (unlikely(ret))
return ret;
return io_recvmsg_mshot_prep(req, iomsg, cmsg.msg_namelen,
cmsg.msg_controllen);
}
#endif
ret = io_msg_copy_hdr(req, iomsg, &msg, ITER_DEST);
if (unlikely(ret))
return ret;
ret = __copy_msghdr(&iomsg->msg, &msg, &iomsg->uaddr);
if (unlikely(ret))
return ret;
return io_recvmsg_mshot_prep(req, iomsg, msg.msg_namelen,
msg.msg_controllen);
}
static int io_recvmsg_prep_setup(struct io_kiocb *req)
{
struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg);
struct io_async_msghdr *kmsg;
int ret;
kmsg = io_msg_alloc_async(req);
if (unlikely(!kmsg))
return -ENOMEM;
if (req->opcode == IORING_OP_RECV) {
kmsg->msg.msg_name = NULL;
kmsg->msg.msg_namelen = 0;
kmsg->msg.msg_control = NULL;
kmsg->msg.msg_get_inq = 1;
kmsg->msg.msg_controllen = 0;
kmsg->msg.msg_iocb = NULL;
kmsg->msg.msg_ubuf = NULL;
if (!io_do_buffer_select(req)) {
ret = import_ubuf(ITER_DEST, sr->buf, sr->len,
&kmsg->msg.msg_iter);
if (unlikely(ret))
return ret;
}
return 0;
}
ret = io_recvmsg_copy_hdr(req, kmsg);
if (!ret)
req->flags |= REQ_F_NEED_CLEANUP;
return ret;
}
#define RECVMSG_FLAGS (IORING_RECVSEND_POLL_FIRST | IORING_RECV_MULTISHOT | \
IORING_RECVSEND_BUNDLE)
int io_recvmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg);
sr->done_io = 0;
if (unlikely(sqe->file_index || sqe->addr2))
return -EINVAL;
sr->umsg = u64_to_user_ptr(READ_ONCE(sqe->addr));
sr->len = READ_ONCE(sqe->len);
sr->flags = READ_ONCE(sqe->ioprio);
if (sr->flags & ~RECVMSG_FLAGS)
return -EINVAL;
sr->msg_flags = READ_ONCE(sqe->msg_flags);
if (sr->msg_flags & MSG_DONTWAIT)
req->flags |= REQ_F_NOWAIT;
if (sr->msg_flags & MSG_ERRQUEUE)
req->flags |= REQ_F_CLEAR_POLLIN;
if (req->flags & REQ_F_BUFFER_SELECT) {
/*
* Store the buffer group for this multishot receive separately,
* as if we end up doing an io-wq based issue that selects a
* buffer, it has to be committed immediately and that will
* clear ->buf_list. This means we lose the link to the buffer
* list, and the eventual buffer put on completion then cannot
* restore it.
*/
sr->buf_group = req->buf_index;
req->buf_list = NULL;
}
if (sr->flags & IORING_RECV_MULTISHOT) {
if (!(req->flags & REQ_F_BUFFER_SELECT))
return -EINVAL;
if (sr->msg_flags & MSG_WAITALL)
return -EINVAL;
if (req->opcode == IORING_OP_RECV && sr->len)
return -EINVAL;
req->flags |= REQ_F_APOLL_MULTISHOT;
}
if (sr->flags & IORING_RECVSEND_BUNDLE) {
if (req->opcode == IORING_OP_RECVMSG)
return -EINVAL;
}
#ifdef CONFIG_COMPAT
if (req->ctx->compat)
sr->msg_flags |= MSG_CMSG_COMPAT;
#endif
sr->nr_multishot_loops = 0;
return io_recvmsg_prep_setup(req);
}
/*
* Finishes io_recv and io_recvmsg.
*
* Returns true if it is actually finished, or false if it should run
* again (for multishot).
*/
static inline bool io_recv_finish(struct io_kiocb *req, int *ret,
struct io_async_msghdr *kmsg,
bool mshot_finished, unsigned issue_flags)
{
struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg);
unsigned int cflags;
if (sr->flags & IORING_RECVSEND_BUNDLE)
cflags = io_put_kbufs(req, io_bundle_nbufs(kmsg, *ret),
issue_flags);
else
cflags = io_put_kbuf(req, issue_flags);
if (kmsg->msg.msg_inq > 0)
cflags |= IORING_CQE_F_SOCK_NONEMPTY;
/* bundle with no more immediate buffers, we're done */
if (sr->flags & IORING_RECVSEND_BUNDLE && req->flags & REQ_F_BL_EMPTY)
goto finish;
/*
* Fill CQE for this receive and see if we should keep trying to
* receive from this socket.
*/
if ((req->flags & REQ_F_APOLL_MULTISHOT) && !mshot_finished &&
io_req_post_cqe(req, *ret, cflags | IORING_CQE_F_MORE)) {
int mshot_retry_ret = IOU_ISSUE_SKIP_COMPLETE;
io_mshot_prep_retry(req, kmsg);
/* Known not-empty or unknown state, retry */
if (cflags & IORING_CQE_F_SOCK_NONEMPTY || kmsg->msg.msg_inq < 0) {
if (sr->nr_multishot_loops++ < MULTISHOT_MAX_RETRY)
return false;
/* mshot retries exceeded, force a requeue */
sr->nr_multishot_loops = 0;
mshot_retry_ret = IOU_REQUEUE;
}
if (issue_flags & IO_URING_F_MULTISHOT)
*ret = mshot_retry_ret;
else
*ret = -EAGAIN;
return true;
}
/* Finish the request / stop multishot. */
finish:
io_req_set_res(req, *ret, cflags);
if (issue_flags & IO_URING_F_MULTISHOT)
*ret = IOU_STOP_MULTISHOT;
else
*ret = IOU_OK;
io_req_msg_cleanup(req, issue_flags);
return true;
}
static int io_recvmsg_prep_multishot(struct io_async_msghdr *kmsg,
struct io_sr_msg *sr, void __user **buf,
size_t *len)
{
unsigned long ubuf = (unsigned long) *buf;
unsigned long hdr;
hdr = sizeof(struct io_uring_recvmsg_out) + kmsg->namelen +
kmsg->controllen;
if (*len < hdr)
return -EFAULT;
if (kmsg->controllen) {
unsigned long control = ubuf + hdr - kmsg->controllen;
kmsg->msg.msg_control_user = (void __user *) control;
kmsg->msg.msg_controllen = kmsg->controllen;
}
sr->buf = *buf; /* stash for later copy */
*buf = (void __user *) (ubuf + hdr);
kmsg->payloadlen = *len = *len - hdr;
return 0;
}
struct io_recvmsg_multishot_hdr {
struct io_uring_recvmsg_out msg;
struct sockaddr_storage addr;
};
static int io_recvmsg_multishot(struct socket *sock, struct io_sr_msg *io,
struct io_async_msghdr *kmsg,
unsigned int flags, bool *finished)
{
int err;
int copy_len;
struct io_recvmsg_multishot_hdr hdr;
if (kmsg->namelen)
kmsg->msg.msg_name = &hdr.addr;
kmsg->msg.msg_flags = flags & (MSG_CMSG_CLOEXEC|MSG_CMSG_COMPAT);
kmsg->msg.msg_namelen = 0;
if (sock->file->f_flags & O_NONBLOCK)
flags |= MSG_DONTWAIT;
err = sock_recvmsg(sock, &kmsg->msg, flags);
*finished = err <= 0;
if (err < 0)
return err;
hdr.msg = (struct io_uring_recvmsg_out) {
.controllen = kmsg->controllen - kmsg->msg.msg_controllen,
.flags = kmsg->msg.msg_flags & ~MSG_CMSG_COMPAT
};
hdr.msg.payloadlen = err;
if (err > kmsg->payloadlen)
err = kmsg->payloadlen;
copy_len = sizeof(struct io_uring_recvmsg_out);
if (kmsg->msg.msg_namelen > kmsg->namelen)
copy_len += kmsg->namelen;
else
copy_len += kmsg->msg.msg_namelen;
/*
* "fromlen shall refer to the value before truncation.."
* 1003.1g
*/
hdr.msg.namelen = kmsg->msg.msg_namelen;
/* ensure that there is no gap between hdr and sockaddr_storage */
BUILD_BUG_ON(offsetof(struct io_recvmsg_multishot_hdr, addr) !=
sizeof(struct io_uring_recvmsg_out));
if (copy_to_user(io->buf, &hdr, copy_len)) {
*finished = true;
return -EFAULT;
}
return sizeof(struct io_uring_recvmsg_out) + kmsg->namelen +
kmsg->controllen + err;
}
int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags)
{
struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg);
struct io_async_msghdr *kmsg = req->async_data;
struct socket *sock;
unsigned flags;
int ret, min_ret = 0;
bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK;
bool mshot_finished = true;
sock = sock_from_file(req->file);
if (unlikely(!sock))
return -ENOTSOCK;
if (!(req->flags & REQ_F_POLLED) &&
(sr->flags & IORING_RECVSEND_POLL_FIRST))
return -EAGAIN;
flags = sr->msg_flags;
if (force_nonblock)
flags |= MSG_DONTWAIT;
retry_multishot:
if (io_do_buffer_select(req)) {
void __user *buf;
size_t len = sr->len;
buf = io_buffer_select(req, &len, issue_flags);
if (!buf)
return -ENOBUFS;
if (req->flags & REQ_F_APOLL_MULTISHOT) {
ret = io_recvmsg_prep_multishot(kmsg, sr, &buf, &len);
if (ret) {
io_kbuf_recycle(req, issue_flags);
return ret;
}
}
iov_iter_ubuf(&kmsg->msg.msg_iter, ITER_DEST, buf, len);
}
kmsg->msg.msg_get_inq = 1;
kmsg->msg.msg_inq = -1;
if (req->flags & REQ_F_APOLL_MULTISHOT) {
ret = io_recvmsg_multishot(sock, sr, kmsg, flags,
&mshot_finished);
} else {
/* disable partial retry for recvmsg with cmsg attached */
if (flags & MSG_WAITALL && !kmsg->msg.msg_controllen)
min_ret = iov_iter_count(&kmsg->msg.msg_iter);
ret = __sys_recvmsg_sock(sock, &kmsg->msg, sr->umsg,
kmsg->uaddr, flags);
}
if (ret < min_ret) {
if (ret == -EAGAIN && force_nonblock) {
if (issue_flags & IO_URING_F_MULTISHOT) {
io_kbuf_recycle(req, issue_flags);
return IOU_ISSUE_SKIP_COMPLETE;
}
return -EAGAIN;
}
if (ret > 0 && io_net_retry(sock, flags)) {
sr->done_io += ret;
req->flags |= REQ_F_BL_NO_RECYCLE;
return -EAGAIN;
}
if (ret == -ERESTARTSYS)
ret = -EINTR;
req_set_fail(req);
} else if ((flags & MSG_WAITALL) && (kmsg->msg.msg_flags & (MSG_TRUNC | MSG_CTRUNC))) {
req_set_fail(req);
}
if (ret > 0)
ret += sr->done_io;
else if (sr->done_io)
ret = sr->done_io;
else
io_kbuf_recycle(req, issue_flags);
if (!io_recv_finish(req, &ret, kmsg, mshot_finished, issue_flags))
goto retry_multishot;
return ret;
}
static int io_recv_buf_select(struct io_kiocb *req, struct io_async_msghdr *kmsg,
size_t *len, unsigned int issue_flags)
{
struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg);
int ret;
/*
* If the ring isn't locked, then don't use the peek interface
* to grab multiple buffers as we will lock/unlock between
* this selection and posting the buffers.
*/
if (!(issue_flags & IO_URING_F_UNLOCKED) &&
sr->flags & IORING_RECVSEND_BUNDLE) {
struct buf_sel_arg arg = {
.iovs = &kmsg->fast_iov,
.nr_iovs = 1,
.mode = KBUF_MODE_EXPAND,
};
if (kmsg->free_iov) {
arg.nr_iovs = kmsg->free_iov_nr;
arg.iovs = kmsg->free_iov;
arg.mode |= KBUF_MODE_FREE;
}
if (kmsg->msg.msg_inq > 0)
arg.max_len = min_not_zero(sr->len, kmsg->msg.msg_inq);
ret = io_buffers_peek(req, &arg);
if (unlikely(ret < 0))
return ret;
/* special case 1 vec, can be a fast path */
if (ret == 1) {
sr->buf = arg.iovs[0].iov_base;
sr->len = arg.iovs[0].iov_len;
goto map_ubuf;
}
iov_iter_init(&kmsg->msg.msg_iter, ITER_DEST, arg.iovs, ret,
arg.out_len);
if (arg.iovs != &kmsg->fast_iov && arg.iovs != kmsg->free_iov) {
kmsg->free_iov_nr = ret;
kmsg->free_iov = arg.iovs;
}
} else {
void __user *buf;
*len = sr->len;
buf = io_buffer_select(req, len, issue_flags);
if (!buf)
return -ENOBUFS;
sr->buf = buf;
sr->len = *len;
map_ubuf:
ret = import_ubuf(ITER_DEST, sr->buf, sr->len,
&kmsg->msg.msg_iter);
if (unlikely(ret))
return ret;
}
return 0;
}
int io_recv(struct io_kiocb *req, unsigned int issue_flags)
{
struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg);
struct io_async_msghdr *kmsg = req->async_data;
struct socket *sock;
unsigned flags;
int ret, min_ret = 0;
bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK;
size_t len = sr->len;
if (!(req->flags & REQ_F_POLLED) &&
(sr->flags & IORING_RECVSEND_POLL_FIRST))
return -EAGAIN;
sock = sock_from_file(req->file);
if (unlikely(!sock))
return -ENOTSOCK;
flags = sr->msg_flags;
if (force_nonblock)
flags |= MSG_DONTWAIT;
retry_multishot:
if (io_do_buffer_select(req)) {
ret = io_recv_buf_select(req, kmsg, &len, issue_flags);
if (unlikely(ret))
goto out_free;
sr->buf = NULL;
}
kmsg->msg.msg_inq = -1;
kmsg->msg.msg_flags = 0;
if (flags & MSG_WAITALL)
min_ret = iov_iter_count(&kmsg->msg.msg_iter);
ret = sock_recvmsg(sock, &kmsg->msg, flags);
if (ret < min_ret) {
if (ret == -EAGAIN && force_nonblock) {
if (issue_flags & IO_URING_F_MULTISHOT) {
io_kbuf_recycle(req, issue_flags);
return IOU_ISSUE_SKIP_COMPLETE;
}
return -EAGAIN;
}
if (ret > 0 && io_net_retry(sock, flags)) {
sr->len -= ret;
sr->buf += ret;
sr->done_io += ret;
req->flags |= REQ_F_BL_NO_RECYCLE;
return -EAGAIN;
}
if (ret == -ERESTARTSYS)
ret = -EINTR;
req_set_fail(req);
} else if ((flags & MSG_WAITALL) && (kmsg->msg.msg_flags & (MSG_TRUNC | MSG_CTRUNC))) {
out_free:
req_set_fail(req);
}
if (ret > 0)
ret += sr->done_io;
else if (sr->done_io)
ret = sr->done_io;
else
io_kbuf_recycle(req, issue_flags);
if (!io_recv_finish(req, &ret, kmsg, ret <= 0, issue_flags))
goto retry_multishot;
return ret;
}
void io_send_zc_cleanup(struct io_kiocb *req)
{
struct io_sr_msg *zc = io_kiocb_to_cmd(req, struct io_sr_msg);
struct io_async_msghdr *io = req->async_data;
if (req_has_async_data(req))
io_netmsg_iovec_free(io);
if (zc->notif) {
io_notif_flush(zc->notif);
zc->notif = NULL;
}
}
#define IO_ZC_FLAGS_COMMON (IORING_RECVSEND_POLL_FIRST | IORING_RECVSEND_FIXED_BUF)
#define IO_ZC_FLAGS_VALID (IO_ZC_FLAGS_COMMON | IORING_SEND_ZC_REPORT_USAGE)
int io_send_zc_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
struct io_sr_msg *zc = io_kiocb_to_cmd(req, struct io_sr_msg);
struct io_ring_ctx *ctx = req->ctx;
struct io_kiocb *notif;
zc->done_io = 0;
req->flags |= REQ_F_POLL_NO_LAZY;
if (unlikely(READ_ONCE(sqe->__pad2[0]) || READ_ONCE(sqe->addr3)))
return -EINVAL;
/* we don't support IOSQE_CQE_SKIP_SUCCESS just yet */
if (req->flags & REQ_F_CQE_SKIP)
return -EINVAL;
notif = zc->notif = io_alloc_notif(ctx);
if (!notif)
return -ENOMEM;
notif->cqe.user_data = req->cqe.user_data;
notif->cqe.res = 0;
notif->cqe.flags = IORING_CQE_F_NOTIF;
req->flags |= REQ_F_NEED_CLEANUP;
zc->flags = READ_ONCE(sqe->ioprio);
if (unlikely(zc->flags & ~IO_ZC_FLAGS_COMMON)) {
if (zc->flags & ~IO_ZC_FLAGS_VALID)
return -EINVAL;
if (zc->flags & IORING_SEND_ZC_REPORT_USAGE) {
struct io_notif_data *nd = io_notif_to_data(notif);
nd->zc_report = true;
nd->zc_used = false;
nd->zc_copied = false;
}
}
if (zc->flags & IORING_RECVSEND_FIXED_BUF) {
unsigned idx = READ_ONCE(sqe->buf_index);
if (unlikely(idx >= ctx->nr_user_bufs))
return -EFAULT;
idx = array_index_nospec(idx, ctx->nr_user_bufs);
req->imu = READ_ONCE(ctx->user_bufs[idx]);
io_req_set_rsrc_node(notif, ctx, 0);
}
if (req->opcode == IORING_OP_SEND_ZC) {
if (READ_ONCE(sqe->__pad3[0]))
return -EINVAL;
zc->addr = u64_to_user_ptr(READ_ONCE(sqe->addr2));
zc->addr_len = READ_ONCE(sqe->addr_len);
} else {
if (unlikely(sqe->addr2 || sqe->file_index))
return -EINVAL;
if (unlikely(zc->flags & IORING_RECVSEND_FIXED_BUF))
return -EINVAL;
}
zc->buf = u64_to_user_ptr(READ_ONCE(sqe->addr));
zc->len = READ_ONCE(sqe->len);
zc->msg_flags = READ_ONCE(sqe->msg_flags) | MSG_NOSIGNAL | MSG_ZEROCOPY;
if (zc->msg_flags & MSG_DONTWAIT)
req->flags |= REQ_F_NOWAIT;
#ifdef CONFIG_COMPAT
if (req->ctx->compat)
zc->msg_flags |= MSG_CMSG_COMPAT;
#endif
return io_sendmsg_prep_setup(req, req->opcode == IORING_OP_SENDMSG_ZC);
}
static int io_sg_from_iter_iovec(struct sock *sk, struct sk_buff *skb,
struct iov_iter *from, size_t length)
{
skb_zcopy_downgrade_managed(skb);
return __zerocopy_sg_from_iter(NULL, sk, skb, from, length);
}
static int io_sg_from_iter(struct sock *sk, struct sk_buff *skb,
struct iov_iter *from, size_t length)
{
struct skb_shared_info *shinfo = skb_shinfo(skb);
int frag = shinfo->nr_frags;
int ret = 0;
struct bvec_iter bi;
ssize_t copied = 0;
unsigned long truesize = 0;
if (!frag)
shinfo->flags |= SKBFL_MANAGED_FRAG_REFS;
else if (unlikely(!skb_zcopy_managed(skb)))
return __zerocopy_sg_from_iter(NULL, sk, skb, from, length);
bi.bi_size = min(from->count, length);
bi.bi_bvec_done = from->iov_offset;
bi.bi_idx = 0;
while (bi.bi_size && frag < MAX_SKB_FRAGS) {
struct bio_vec v = mp_bvec_iter_bvec(from->bvec, bi);
copied += v.bv_len;
truesize += PAGE_ALIGN(v.bv_len + v.bv_offset);
__skb_fill_page_desc_noacc(shinfo, frag++, v.bv_page,
v.bv_offset, v.bv_len);
bvec_iter_advance_single(from->bvec, &bi, v.bv_len);
}
if (bi.bi_size)
ret = -EMSGSIZE;
shinfo->nr_frags = frag;
from->bvec += bi.bi_idx;
from->nr_segs -= bi.bi_idx;
from->count -= copied;
from->iov_offset = bi.bi_bvec_done;
skb->data_len += copied;
skb->len += copied;
skb->truesize += truesize;
if (sk && sk->sk_type == SOCK_STREAM) {
sk_wmem_queued_add(sk, truesize);
if (!skb_zcopy_pure(skb))
sk_mem_charge(sk, truesize);
} else {
refcount_add(truesize, &skb->sk->sk_wmem_alloc);
}
return ret;
}
static int io_send_zc_import(struct io_kiocb *req, struct io_async_msghdr *kmsg)
{
struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg);
int ret;
if (sr->flags & IORING_RECVSEND_FIXED_BUF) {
ret = io_import_fixed(ITER_SOURCE, &kmsg->msg.msg_iter, req->imu,
(u64)(uintptr_t)sr->buf, sr->len);
if (unlikely(ret))
return ret;
kmsg->msg.sg_from_iter = io_sg_from_iter;
} else {
ret = import_ubuf(ITER_SOURCE, sr->buf, sr->len, &kmsg->msg.msg_iter);
if (unlikely(ret))
return ret;
ret = io_notif_account_mem(sr->notif, sr->len);
if (unlikely(ret))
return ret;
kmsg->msg.sg_from_iter = io_sg_from_iter_iovec;
}
return ret;
}
int io_send_zc(struct io_kiocb *req, unsigned int issue_flags)
{
struct io_sr_msg *zc = io_kiocb_to_cmd(req, struct io_sr_msg);
struct io_async_msghdr *kmsg = req->async_data;
struct socket *sock;
unsigned msg_flags;
int ret, min_ret = 0;
sock = sock_from_file(req->file);
if (unlikely(!sock))
return -ENOTSOCK;
if (!test_bit(SOCK_SUPPORT_ZC, &sock->flags))
return -EOPNOTSUPP;
if (!(req->flags & REQ_F_POLLED) &&
(zc->flags & IORING_RECVSEND_POLL_FIRST))
return -EAGAIN;
if (!zc->done_io) {
ret = io_send_zc_import(req, kmsg);
if (unlikely(ret))
return ret;
}
msg_flags = zc->msg_flags;
if (issue_flags & IO_URING_F_NONBLOCK)
msg_flags |= MSG_DONTWAIT;
if (msg_flags & MSG_WAITALL)
min_ret = iov_iter_count(&kmsg->msg.msg_iter);
msg_flags &= ~MSG_INTERNAL_SENDMSG_FLAGS;
kmsg->msg.msg_flags = msg_flags;
kmsg->msg.msg_ubuf = &io_notif_to_data(zc->notif)->uarg;
ret = sock_sendmsg(sock, &kmsg->msg);
if (unlikely(ret < min_ret)) {
if (ret == -EAGAIN && (issue_flags & IO_URING_F_NONBLOCK))
return -EAGAIN;
if (ret > 0 && io_net_retry(sock, kmsg->msg.msg_flags)) {
zc->len -= ret;
zc->buf += ret;
zc->done_io += ret;
req->flags |= REQ_F_BL_NO_RECYCLE;
return -EAGAIN;
}
if (ret == -ERESTARTSYS)
ret = -EINTR;
req_set_fail(req);
}
if (ret >= 0)
ret += zc->done_io;
else if (zc->done_io)
ret = zc->done_io;
/*
* If we're in io-wq we can't rely on tw ordering guarantees, defer
* flushing notif to io_send_zc_cleanup()
*/
if (!(issue_flags & IO_URING_F_UNLOCKED)) {
io_notif_flush(zc->notif);
io_req_msg_cleanup(req, 0);
}
io_req_set_res(req, ret, IORING_CQE_F_MORE);
return IOU_OK;
}
int io_sendmsg_zc(struct io_kiocb *req, unsigned int issue_flags)
{
struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg);
struct io_async_msghdr *kmsg = req->async_data;
struct socket *sock;
unsigned flags;
int ret, min_ret = 0;
sock = sock_from_file(req->file);
if (unlikely(!sock))
return -ENOTSOCK;
if (!test_bit(SOCK_SUPPORT_ZC, &sock->flags))
return -EOPNOTSUPP;
if (!(req->flags & REQ_F_POLLED) &&
(sr->flags & IORING_RECVSEND_POLL_FIRST))
return -EAGAIN;
flags = sr->msg_flags;
if (issue_flags & IO_URING_F_NONBLOCK)
flags |= MSG_DONTWAIT;
if (flags & MSG_WAITALL)
min_ret = iov_iter_count(&kmsg->msg.msg_iter);
kmsg->msg.msg_control_user = sr->msg_control;
kmsg->msg.msg_ubuf = &io_notif_to_data(sr->notif)->uarg;
kmsg->msg.sg_from_iter = io_sg_from_iter_iovec;
ret = __sys_sendmsg_sock(sock, &kmsg->msg, flags);
if (unlikely(ret < min_ret)) {
if (ret == -EAGAIN && (issue_flags & IO_URING_F_NONBLOCK))
return -EAGAIN;
if (ret > 0 && io_net_retry(sock, flags)) {
sr->done_io += ret;
req->flags |= REQ_F_BL_NO_RECYCLE;
return -EAGAIN;
}
if (ret == -ERESTARTSYS)
ret = -EINTR;
req_set_fail(req);
}
if (ret >= 0)
ret += sr->done_io;
else if (sr->done_io)
ret = sr->done_io;
/*
* If we're in io-wq we can't rely on tw ordering guarantees, defer
* flushing notif to io_send_zc_cleanup()
*/
if (!(issue_flags & IO_URING_F_UNLOCKED)) {
io_notif_flush(sr->notif);
io_req_msg_cleanup(req, 0);
}
io_req_set_res(req, ret, IORING_CQE_F_MORE);
return IOU_OK;
}
void io_sendrecv_fail(struct io_kiocb *req)
{
struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg);
if (sr->done_io)
req->cqe.res = sr->done_io;
if ((req->flags & REQ_F_NEED_CLEANUP) &&
(req->opcode == IORING_OP_SEND_ZC || req->opcode == IORING_OP_SENDMSG_ZC))
req->cqe.flags |= IORING_CQE_F_MORE;
}
int io_accept_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
struct io_accept *accept = io_kiocb_to_cmd(req, struct io_accept);
unsigned flags;
if (sqe->len || sqe->buf_index)
return -EINVAL;
accept->addr = u64_to_user_ptr(READ_ONCE(sqe->addr));
accept->addr_len = u64_to_user_ptr(READ_ONCE(sqe->addr2));
accept->flags = READ_ONCE(sqe->accept_flags);
accept->nofile = rlimit(RLIMIT_NOFILE);
flags = READ_ONCE(sqe->ioprio);
if (flags & ~IORING_ACCEPT_MULTISHOT)
return -EINVAL;
accept->file_slot = READ_ONCE(sqe->file_index);
if (accept->file_slot) {
if (accept->flags & SOCK_CLOEXEC)
return -EINVAL;
if (flags & IORING_ACCEPT_MULTISHOT &&
accept->file_slot != IORING_FILE_INDEX_ALLOC)
return -EINVAL;
}
if (accept->flags & ~(SOCK_CLOEXEC | SOCK_NONBLOCK))
return -EINVAL;
if (SOCK_NONBLOCK != O_NONBLOCK && (accept->flags & SOCK_NONBLOCK))
accept->flags = (accept->flags & ~SOCK_NONBLOCK) | O_NONBLOCK;
if (flags & IORING_ACCEPT_MULTISHOT)
req->flags |= REQ_F_APOLL_MULTISHOT;
return 0;
}
int io_accept(struct io_kiocb *req, unsigned int issue_flags)
{
struct io_accept *accept = io_kiocb_to_cmd(req, struct io_accept);
bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK;
unsigned int file_flags = force_nonblock ? O_NONBLOCK : 0;
bool fixed = !!accept->file_slot;
struct file *file;
int ret, fd;
retry:
if (!fixed) {
fd = __get_unused_fd_flags(accept->flags, accept->nofile);
if (unlikely(fd < 0))
return fd;
}
file = do_accept(req->file, file_flags, accept->addr, accept->addr_len,
accept->flags);
if (IS_ERR(file)) {
if (!fixed)
put_unused_fd(fd);
ret = PTR_ERR(file);
if (ret == -EAGAIN && force_nonblock) {
/*
* if it's multishot and polled, we don't need to
* return EAGAIN to arm the poll infra since it
* has already been done
*/
if (issue_flags & IO_URING_F_MULTISHOT)
return IOU_ISSUE_SKIP_COMPLETE;
return ret;
}
if (ret == -ERESTARTSYS)
ret = -EINTR;
req_set_fail(req);
} else if (!fixed) {
fd_install(fd, file);
ret = fd;
} else {
ret = io_fixed_fd_install(req, issue_flags, file,
accept->file_slot);
}
if (!(req->flags & REQ_F_APOLL_MULTISHOT)) {
io_req_set_res(req, ret, 0);
return IOU_OK;
}
if (ret < 0)
return ret;
if (io_req_post_cqe(req, ret, IORING_CQE_F_MORE))
goto retry;
io_req_set_res(req, ret, 0);
return IOU_STOP_MULTISHOT;
}
int io_socket_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
struct io_socket *sock = io_kiocb_to_cmd(req, struct io_socket);
if (sqe->addr || sqe->rw_flags || sqe->buf_index)
return -EINVAL;
sock->domain = READ_ONCE(sqe->fd);
sock->type = READ_ONCE(sqe->off);
sock->protocol = READ_ONCE(sqe->len);
sock->file_slot = READ_ONCE(sqe->file_index);
sock->nofile = rlimit(RLIMIT_NOFILE);
sock->flags = sock->type & ~SOCK_TYPE_MASK;
if (sock->file_slot && (sock->flags & SOCK_CLOEXEC))
return -EINVAL;
if (sock->flags & ~(SOCK_CLOEXEC | SOCK_NONBLOCK))
return -EINVAL;
return 0;
}
int io_socket(struct io_kiocb *req, unsigned int issue_flags)
{
struct io_socket *sock = io_kiocb_to_cmd(req, struct io_socket);
bool fixed = !!sock->file_slot;
struct file *file;
int ret, fd;
if (!fixed) {
fd = __get_unused_fd_flags(sock->flags, sock->nofile);
if (unlikely(fd < 0))
return fd;
}
file = __sys_socket_file(sock->domain, sock->type, sock->protocol);
if (IS_ERR(file)) {
if (!fixed)
put_unused_fd(fd);
ret = PTR_ERR(file);
if (ret == -EAGAIN && (issue_flags & IO_URING_F_NONBLOCK))
return -EAGAIN;
if (ret == -ERESTARTSYS)
ret = -EINTR;
req_set_fail(req);
} else if (!fixed) {
fd_install(fd, file);
ret = fd;
} else {
ret = io_fixed_fd_install(req, issue_flags, file,
sock->file_slot);
}
io_req_set_res(req, ret, 0);
return IOU_OK;
}
int io_connect_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
struct io_connect *conn = io_kiocb_to_cmd(req, struct io_connect);
struct io_async_msghdr *io;
if (sqe->len || sqe->buf_index || sqe->rw_flags || sqe->splice_fd_in)
return -EINVAL;
conn->addr = u64_to_user_ptr(READ_ONCE(sqe->addr));
conn->addr_len = READ_ONCE(sqe->addr2);
conn->in_progress = conn->seen_econnaborted = false;
io = io_msg_alloc_async(req);
if (unlikely(!io))
return -ENOMEM;
return move_addr_to_kernel(conn->addr, conn->addr_len, &io->addr);
}
int io_connect(struct io_kiocb *req, unsigned int issue_flags)
{
struct io_connect *connect = io_kiocb_to_cmd(req, struct io_connect);
struct io_async_msghdr *io = req->async_data;
unsigned file_flags;
int ret;
bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK;
file_flags = force_nonblock ? O_NONBLOCK : 0;
ret = __sys_connect_file(req->file, &io->addr, connect->addr_len,
file_flags);
if ((ret == -EAGAIN || ret == -EINPROGRESS || ret == -ECONNABORTED)
&& force_nonblock) {
if (ret == -EINPROGRESS) {
connect->in_progress = true;
} else if (ret == -ECONNABORTED) {
if (connect->seen_econnaborted)
goto out;
connect->seen_econnaborted = true;
}
return -EAGAIN;
}
if (connect->in_progress) {
/*
* At least bluetooth will return -EBADFD on a re-connect
* attempt, and it's (supposedly) also valid to get -EISCONN
* which means the previous result is good. For both of these,
* grab the sock_error() and use that for the completion.
*/
if (ret == -EBADFD || ret == -EISCONN)
ret = sock_error(sock_from_file(req->file)->sk);
}
if (ret == -ERESTARTSYS)
ret = -EINTR;
out:
if (ret < 0)
req_set_fail(req);
io_req_msg_cleanup(req, issue_flags);
io_req_set_res(req, ret, 0);
return IOU_OK;
}
void io_netmsg_cache_free(const void *entry)
{
struct io_async_msghdr *kmsg = (struct io_async_msghdr *) entry;
if (kmsg->free_iov) {
kasan_mempool_unpoison_object(kmsg->free_iov,
kmsg->free_iov_nr * sizeof(struct iovec));
io_netmsg_iovec_free(kmsg);
}
kfree(kmsg);
}
#endif
|