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
|
/**
* drivers/net/ks8851_mll.c
* Copyright (c) 2009 Micrel Inc.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
*/
/**
* Supports:
* KS8851 16bit MLL chip from Micrel Inc.
*/
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/ethtool.h>
#include <linux/cache.h>
#include <linux/crc32.h>
#include <linux/mii.h>
#include <linux/platform_device.h>
#include <linux/delay.h>
#define DRV_NAME "ks8851_mll"
static u8 KS_DEFAULT_MAC_ADDRESS[] = { 0x00, 0x10, 0xA1, 0x86, 0x95, 0x11 };
#define MAX_RECV_FRAMES 32
#define MAX_BUF_SIZE 2048
#define TX_BUF_SIZE 2000
#define RX_BUF_SIZE 2000
#define KS_CCR 0x08
#define CCR_EEPROM (1 << 9)
#define CCR_SPI (1 << 8)
#define CCR_8BIT (1 << 7)
#define CCR_16BIT (1 << 6)
#define CCR_32BIT (1 << 5)
#define CCR_SHARED (1 << 4)
#define CCR_32PIN (1 << 0)
/* MAC address registers */
#define KS_MARL 0x10
#define KS_MARM 0x12
#define KS_MARH 0x14
#define KS_OBCR 0x20
#define OBCR_ODS_16MA (1 << 6)
#define KS_EEPCR 0x22
#define EEPCR_EESA (1 << 4)
#define EEPCR_EESB (1 << 3)
#define EEPCR_EEDO (1 << 2)
#define EEPCR_EESCK (1 << 1)
#define EEPCR_EECS (1 << 0)
#define KS_MBIR 0x24
#define MBIR_TXMBF (1 << 12)
#define MBIR_TXMBFA (1 << 11)
#define MBIR_RXMBF (1 << 4)
#define MBIR_RXMBFA (1 << 3)
#define KS_GRR 0x26
#define GRR_QMU (1 << 1)
#define GRR_GSR (1 << 0)
#define KS_WFCR 0x2A
#define WFCR_MPRXE (1 << 7)
#define WFCR_WF3E (1 << 3)
#define WFCR_WF2E (1 << 2)
#define WFCR_WF1E (1 << 1)
#define WFCR_WF0E (1 << 0)
#define KS_WF0CRC0 0x30
#define KS_WF0CRC1 0x32
#define KS_WF0BM0 0x34
#define KS_WF0BM1 0x36
#define KS_WF0BM2 0x38
#define KS_WF0BM3 0x3A
#define KS_WF1CRC0 0x40
#define KS_WF1CRC1 0x42
#define KS_WF1BM0 0x44
#define KS_WF1BM1 0x46
#define KS_WF1BM2 0x48
#define KS_WF1BM3 0x4A
#define KS_WF2CRC0 0x50
#define KS_WF2CRC1 0x52
#define KS_WF2BM0 0x54
#define KS_WF2BM1 0x56
#define KS_WF2BM2 0x58
#define KS_WF2BM3 0x5A
#define KS_WF3CRC0 0x60
#define KS_WF3CRC1 0x62
#define KS_WF3BM0 0x64
#define KS_WF3BM1 0x66
#define KS_WF3BM2 0x68
#define KS_WF3BM3 0x6A
#define KS_TXCR 0x70
#define TXCR_TCGICMP (1 << 8)
#define TXCR_TCGUDP (1 << 7)
#define TXCR_TCGTCP (1 << 6)
#define TXCR_TCGIP (1 << 5)
#define TXCR_FTXQ (1 << 4)
#define TXCR_TXFCE (1 << 3)
#define TXCR_TXPE (1 << 2)
#define TXCR_TXCRC (1 << 1)
#define TXCR_TXE (1 << 0)
#define KS_TXSR 0x72
#define TXSR_TXLC (1 << 13)
#define TXSR_TXMC (1 << 12)
#define TXSR_TXFID_MASK (0x3f << 0)
#define TXSR_TXFID_SHIFT (0)
#define TXSR_TXFID_GET(_v) (((_v) >> 0) & 0x3f)
#define KS_RXCR1 0x74
#define RXCR1_FRXQ (1 << 15)
#define RXCR1_RXUDPFCC (1 << 14)
#define RXCR1_RXTCPFCC (1 << 13)
#define RXCR1_RXIPFCC (1 << 12)
#define RXCR1_RXPAFMA (1 << 11)
#define RXCR1_RXFCE (1 << 10)
#define RXCR1_RXEFE (1 << 9)
#define RXCR1_RXMAFMA (1 << 8)
#define RXCR1_RXBE (1 << 7)
#define RXCR1_RXME (1 << 6)
#define RXCR1_RXUE (1 << 5)
#define RXCR1_RXAE (1 << 4)
#define RXCR1_RXINVF (1 << 1)
#define RXCR1_RXE (1 << 0)
#define RXCR1_FILTER_MASK (RXCR1_RXINVF | RXCR1_RXAE | \
RXCR1_RXMAFMA | RXCR1_RXPAFMA)
#define KS_RXCR2 0x76
#define RXCR2_SRDBL_MASK (0x7 << 5)
#define RXCR2_SRDBL_SHIFT (5)
#define RXCR2_SRDBL_4B (0x0 << 5)
#define RXCR2_SRDBL_8B (0x1 << 5)
#define RXCR2_SRDBL_16B (0x2 << 5)
#define RXCR2_SRDBL_32B (0x3 << 5)
/* #define RXCR2_SRDBL_FRAME (0x4 << 5) */
#define RXCR2_IUFFP (1 << 4)
#define RXCR2_RXIUFCEZ (1 << 3)
#define RXCR2_UDPLFE (1 << 2)
#define RXCR2_RXICMPFCC (1 << 1)
#define RXCR2_RXSAF (1 << 0)
#define KS_TXMIR 0x78
#define KS_RXFHSR 0x7C
#define RXFSHR_RXFV (1 << 15)
#define RXFSHR_RXICMPFCS (1 << 13)
#define RXFSHR_RXIPFCS (1 << 12)
#define RXFSHR_RXTCPFCS (1 << 11)
#define RXFSHR_RXUDPFCS (1 << 10)
#define RXFSHR_RXBF (1 << 7)
#define RXFSHR_RXMF (1 << 6)
#define RXFSHR_RXUF (1 << 5)
#define RXFSHR_RXMR (1 << 4)
#define RXFSHR_RXFT (1 << 3)
#define RXFSHR_RXFTL (1 << 2)
#define RXFSHR_RXRF (1 << 1)
#define RXFSHR_RXCE (1 << 0)
#define RXFSHR_ERR (RXFSHR_RXCE | RXFSHR_RXRF |\
RXFSHR_RXFTL | RXFSHR_RXMR |\
RXFSHR_RXICMPFCS | RXFSHR_RXIPFCS |\
RXFSHR_RXTCPFCS)
#define KS_RXFHBCR 0x7E
#define RXFHBCR_CNT_MASK 0x0FFF
#define KS_TXQCR 0x80
#define TXQCR_AETFE (1 << 2)
#define TXQCR_TXQMAM (1 << 1)
#define TXQCR_METFE (1 << 0)
#define KS_RXQCR 0x82
#define RXQCR_RXDTTS (1 << 12)
#define RXQCR_RXDBCTS (1 << 11)
#define RXQCR_RXFCTS (1 << 10)
#define RXQCR_RXIPHTOE (1 << 9)
#define RXQCR_RXDTTE (1 << 7)
#define RXQCR_RXDBCTE (1 << 6)
#define RXQCR_RXFCTE (1 << 5)
#define RXQCR_ADRFE (1 << 4)
#define RXQCR_SDA (1 << 3)
#define RXQCR_RRXEF (1 << 0)
#define RXQCR_CMD_CNTL (RXQCR_RXFCTE|RXQCR_ADRFE)
#define KS_TXFDPR 0x84
#define TXFDPR_TXFPAI (1 << 14)
#define TXFDPR_TXFP_MASK (0x7ff << 0)
#define TXFDPR_TXFP_SHIFT (0)
#define KS_RXFDPR 0x86
#define RXFDPR_RXFPAI (1 << 14)
#define KS_RXDTTR 0x8C
#define KS_RXDBCTR 0x8E
#define KS_IER 0x90
#define KS_ISR 0x92
#define IRQ_LCI (1 << 15)
#define IRQ_TXI (1 << 14)
#define IRQ_RXI (1 << 13)
#define IRQ_RXOI (1 << 11)
#define IRQ_TXPSI (1 << 9)
#define IRQ_RXPSI (1 << 8)
#define IRQ_TXSAI (1 << 6)
#define IRQ_RXWFDI (1 << 5)
#define IRQ_RXMPDI (1 << 4)
#define IRQ_LDI (1 << 3)
#define IRQ_EDI (1 << 2)
#define IRQ_SPIBEI (1 << 1)
#define IRQ_DEDI (1 << 0)
#define KS_RXFCTR 0x9C
#define RXFCTR_THRESHOLD_MASK 0x00FF
#define KS_RXFC 0x9D
#define RXFCTR_RXFC_MASK (0xff << 8)
#define RXFCTR_RXFC_SHIFT (8)
#define RXFCTR_RXFC_GET(_v) (((_v) >> 8) & 0xff)
#define RXFCTR_RXFCT_MASK (0xff << 0)
#define RXFCTR_RXFCT_SHIFT (0)
#define KS_TXNTFSR 0x9E
#define KS_MAHTR0 0xA0
#define KS_MAHTR1 0xA2
#define KS_MAHTR2 0xA4
#define KS_MAHTR3 0xA6
#define KS_FCLWR 0xB0
#define KS_FCHWR 0xB2
#define KS_FCOWR 0xB4
#define KS_CIDER 0xC0
#define CIDER_ID 0x8870
#define CIDER_REV_MASK (0x7 << 1)
#define CIDER_REV_SHIFT (1)
#define CIDER_REV_GET(_v) (((_v) >> 1) & 0x7)
#define KS_CGCR 0xC6
#define KS_IACR 0xC8
#define IACR_RDEN (1 << 12)
#define IACR_TSEL_MASK (0x3 << 10)
#define IACR_TSEL_SHIFT (10)
#define IACR_TSEL_MIB (0x3 << 10)
#define IACR_ADDR_MASK (0x1f << 0)
#define IACR_ADDR_SHIFT (0)
#define KS_IADLR 0xD0
#define KS_IAHDR 0xD2
#define KS_PMECR 0xD4
#define PMECR_PME_DELAY (1 << 14)
#define PMECR_PME_POL (1 << 12)
#define PMECR_WOL_WAKEUP (1 << 11)
#define PMECR_WOL_MAGICPKT (1 << 10)
#define PMECR_WOL_LINKUP (1 << 9)
#define PMECR_WOL_ENERGY (1 << 8)
#define PMECR_AUTO_WAKE_EN (1 << 7)
#define PMECR_WAKEUP_NORMAL (1 << 6)
#define PMECR_WKEVT_MASK (0xf << 2)
#define PMECR_WKEVT_SHIFT (2)
#define PMECR_WKEVT_GET(_v) (((_v) >> 2) & 0xf)
#define PMECR_WKEVT_ENERGY (0x1 << 2)
#define PMECR_WKEVT_LINK (0x2 << 2)
#define PMECR_WKEVT_MAGICPKT (0x4 << 2)
#define PMECR_WKEVT_FRAME (0x8 << 2)
#define PMECR_PM_MASK (0x3 << 0)
#define PMECR_PM_SHIFT (0)
#define PMECR_PM_NORMAL (0x0 << 0)
#define PMECR_PM_ENERGY (0x1 << 0)
#define PMECR_PM_SOFTDOWN (0x2 << 0)
#define PMECR_PM_POWERSAVE (0x3 << 0)
/* Standard MII PHY data */
#define KS_P1MBCR 0xE4
#define P1MBCR_FORCE_FDX (1 << 8)
#define KS_P1MBSR 0xE6
#define P1MBSR_AN_COMPLETE (1 << 5)
#define P1MBSR_AN_CAPABLE (1 << 3)
#define P1MBSR_LINK_UP (1 << 2)
#define KS_PHY1ILR 0xE8
#define KS_PHY1IHR 0xEA
#define KS_P1ANAR 0xEC
#define KS_P1ANLPR 0xEE
#define KS_P1SCLMD 0xF4
#define P1SCLMD_LEDOFF (1 << 15)
#define P1SCLMD_TXIDS (1 << 14)
#define P1SCLMD_RESTARTAN (1 << 13)
#define P1SCLMD_DISAUTOMDIX (1 << 10)
#define P1SCLMD_FORCEMDIX (1 << 9)
#define P1SCLMD_AUTONEGEN (1 << 7)
#define P1SCLMD_FORCE100 (1 << 6)
#define P1SCLMD_FORCEFDX (1 << 5)
#define P1SCLMD_ADV_FLOW (1 << 4)
#define P1SCLMD_ADV_100BT_FDX (1 << 3)
#define P1SCLMD_ADV_100BT_HDX (1 << 2)
#define P1SCLMD_ADV_10BT_FDX (1 << 1)
#define P1SCLMD_ADV_10BT_HDX (1 << 0)
#define KS_P1CR 0xF6
#define P1CR_HP_MDIX (1 << 15)
#define P1CR_REV_POL (1 << 13)
#define P1CR_OP_100M (1 << 10)
#define P1CR_OP_FDX (1 << 9)
#define P1CR_OP_MDI (1 << 7)
#define P1CR_AN_DONE (1 << 6)
#define P1CR_LINK_GOOD (1 << 5)
#define P1CR_PNTR_FLOW (1 << 4)
#define P1CR_PNTR_100BT_FDX (1 << 3)
#define P1CR_PNTR_100BT_HDX (1 << 2)
#define P1CR_PNTR_10BT_FDX (1 << 1)
#define P1CR_PNTR_10BT_HDX (1 << 0)
/* TX Frame control */
#define TXFR_TXIC (1 << 15)
#define TXFR_TXFID_MASK (0x3f << 0)
#define TXFR_TXFID_SHIFT (0)
#define KS_P1SR 0xF8
#define P1SR_HP_MDIX (1 << 15)
#define P1SR_REV_POL (1 << 13)
#define P1SR_OP_100M (1 << 10)
#define P1SR_OP_FDX (1 << 9)
#define P1SR_OP_MDI (1 << 7)
#define P1SR_AN_DONE (1 << 6)
#define P1SR_LINK_GOOD (1 << 5)
#define P1SR_PNTR_FLOW (1 << 4)
#define P1SR_PNTR_100BT_FDX (1 << 3)
#define P1SR_PNTR_100BT_HDX (1 << 2)
#define P1SR_PNTR_10BT_FDX (1 << 1)
#define P1SR_PNTR_10BT_HDX (1 << 0)
#define ENUM_BUS_NONE 0
#define ENUM_BUS_8BIT 1
#define ENUM_BUS_16BIT 2
#define ENUM_BUS_32BIT 3
#define MAX_MCAST_LST 32
#define HW_MCAST_SIZE 8
#define MAC_ADDR_LEN 6
/**
* union ks_tx_hdr - tx header data
* @txb: The header as bytes
* @txw: The header as 16bit, little-endian words
*
* A dual representation of the tx header data to allow
* access to individual bytes, and to allow 16bit accesses
* with 16bit alignment.
*/
union ks_tx_hdr {
u8 txb[4];
__le16 txw[2];
};
/**
* struct ks_net - KS8851 driver private data
* @net_device : The network device we're bound to
* @hw_addr : start address of data register.
* @hw_addr_cmd : start address of command register.
* @txh : temporaly buffer to save status/length.
* @lock : Lock to ensure that the device is not accessed when busy.
* @pdev : Pointer to platform device.
* @mii : The MII state information for the mii calls.
* @frame_head_info : frame header information for multi-pkt rx.
* @statelock : Lock on this structure for tx list.
* @msg_enable : The message flags controlling driver output (see ethtool).
* @frame_cnt : number of frames received.
* @bus_width : i/o bus width.
* @irq : irq number assigned to this device.
* @rc_rxqcr : Cached copy of KS_RXQCR.
* @rc_txcr : Cached copy of KS_TXCR.
* @rc_ier : Cached copy of KS_IER.
* @sharedbus : Multipex(addr and data bus) mode indicator.
* @cmd_reg_cache : command register cached.
* @cmd_reg_cache_int : command register cached. Used in the irq handler.
* @promiscuous : promiscuous mode indicator.
* @all_mcast : mutlicast indicator.
* @mcast_lst_size : size of multicast list.
* @mcast_lst : multicast list.
* @mcast_bits : multicast enabed.
* @mac_addr : MAC address assigned to this device.
* @fid : frame id.
* @extra_byte : number of extra byte prepended rx pkt.
* @enabled : indicator this device works.
*
* The @lock ensures that the chip is protected when certain operations are
* in progress. When the read or write packet transfer is in progress, most
* of the chip registers are not accessible until the transfer is finished and
* the DMA has been de-asserted.
*
* The @statelock is used to protect information in the structure which may
* need to be accessed via several sources, such as the network driver layer
* or one of the work queues.
*
*/
/* Receive multiplex framer header info */
struct type_frame_head {
u16 sts; /* Frame status */
u16 len; /* Byte count */
};
struct ks_net {
struct net_device *netdev;
void __iomem *hw_addr;
void __iomem *hw_addr_cmd;
union ks_tx_hdr txh ____cacheline_aligned;
struct mutex lock; /* spinlock to be interrupt safe */
struct platform_device *pdev;
struct mii_if_info mii;
struct type_frame_head *frame_head_info;
spinlock_t statelock;
u32 msg_enable;
u32 frame_cnt;
int bus_width;
int irq;
u16 rc_rxqcr;
u16 rc_txcr;
u16 rc_ier;
u16 sharedbus;
u16 cmd_reg_cache;
u16 cmd_reg_cache_int;
u16 promiscuous;
u16 all_mcast;
u16 mcast_lst_size;
u8 mcast_lst[MAX_MCAST_LST][MAC_ADDR_LEN];
u8 mcast_bits[HW_MCAST_SIZE];
u8 mac_addr[6];
u8 fid;
u8 extra_byte;
u8 enabled;
};
static int msg_enable;
#define ks_info(_ks, _msg...) dev_info(&(_ks)->pdev->dev, _msg)
#define ks_warn(_ks, _msg...) dev_warn(&(_ks)->pdev->dev, _msg)
#define ks_dbg(_ks, _msg...) dev_dbg(&(_ks)->pdev->dev, _msg)
#define ks_err(_ks, _msg...) dev_err(&(_ks)->pdev->dev, _msg)
#define BE3 0x8000 /* Byte Enable 3 */
#define BE2 0x4000 /* Byte Enable 2 */
#define BE1 0x2000 /* Byte Enable 1 */
#define BE0 0x1000 /* Byte Enable 0 */
/**
* register read/write calls.
*
* All these calls issue transactions to access the chip's registers. They
* all require that the necessary lock is held to prevent accesses when the
* chip is busy transfering packet data (RX/TX FIFO accesses).
*/
/**
* ks_rdreg8 - read 8 bit register from device
* @ks : The chip information
* @offset: The register address
*
* Read a 8bit register from the chip, returning the result
*/
static u8 ks_rdreg8(struct ks_net *ks, int offset)
{
u16 data;
u8 shift_bit = offset & 0x03;
u8 shift_data = (offset & 1) << 3;
ks->cmd_reg_cache = (u16) offset | (u16)(BE0 << shift_bit);
iowrite16(ks->cmd_reg_cache, ks->hw_addr_cmd);
data = ioread16(ks->hw_addr);
return (u8)(data >> shift_data);
}
/**
* ks_rdreg16 - read 16 bit register from device
* @ks : The chip information
* @offset: The register address
*
* Read a 16bit register from the chip, returning the result
*/
static u16 ks_rdreg16(struct ks_net *ks, int offset)
{
ks->cmd_reg_cache = (u16)offset | ((BE1 | BE0) << (offset & 0x02));
iowrite16(ks->cmd_reg_cache, ks->hw_addr_cmd);
return ioread16(ks->hw_addr);
}
/**
* ks_wrreg8 - write 8bit register value to chip
* @ks: The chip information
* @offset: The register address
* @value: The value to write
*
*/
static void ks_wrreg8(struct ks_net *ks, int offset, u8 value)
{
u8 shift_bit = (offset & 0x03);
u16 value_write = (u16)(value << ((offset & 1) << 3));
ks->cmd_reg_cache = (u16)offset | (BE0 << shift_bit);
iowrite16(ks->cmd_reg_cache, ks->hw_addr_cmd);
iowrite16(value_write, ks->hw_addr);
}
/**
* ks_wrreg16 - write 16bit register value to chip
* @ks: The chip information
* @offset: The register address
* @value: The value to write
*
*/
static void ks_wrreg16(struct ks_net *ks, int offset, u16 value)
{
ks->cmd_reg_cache = (u16)offset | ((BE1 | BE0) << (offset & 0x02));
iowrite16(ks->cmd_reg_cache, ks->hw_addr_cmd);
iowrite16(value, ks->hw_addr);
}
/**
* ks_inblk - read a block of data from QMU. This is called after sudo DMA mode enabled.
* @ks: The chip state
* @wptr: buffer address to save data
* @len: length in byte to read
*
*/
static inline void ks_inblk(struct ks_net *ks, u16 *wptr, u32 len)
{
len >>= 1;
while (len--)
*wptr++ = (u16)ioread16(ks->hw_addr);
}
/**
* ks_outblk - write data to QMU. This is called after sudo DMA mode enabled.
* @ks: The chip information
* @wptr: buffer address
* @len: length in byte to write
*
*/
static inline void ks_outblk(struct ks_net *ks, u16 *wptr, u32 len)
{
len >>= 1;
while (len--)
iowrite16(*wptr++, ks->hw_addr);
}
/**
* ks_tx_fifo_space - return the available hardware buffer size.
* @ks: The chip information
*
*/
static inline u16 ks_tx_fifo_space(struct ks_net *ks)
{
return ks_rdreg16(ks, KS_TXMIR) & 0x1fff;
}
/**
* ks_save_cmd_reg - save the command register from the cache.
* @ks: The chip information
*
*/
static inline void ks_save_cmd_reg(struct ks_net *ks)
{
/*ks8851 MLL has a bug to read back the command register.
* So rely on software to save the content of command register.
*/
ks->cmd_reg_cache_int = ks->cmd_reg_cache;
}
/**
* ks_restore_cmd_reg - restore the command register from the cache and
* write to hardware register.
* @ks: The chip information
*
*/
static inline void ks_restore_cmd_reg(struct ks_net *ks)
{
ks->cmd_reg_cache = ks->cmd_reg_cache_int;
iowrite16(ks->cmd_reg_cache, ks->hw_addr_cmd);
}
/**
* ks_set_powermode - set power mode of the device
* @ks: The chip information
* @pwrmode: The power mode value to write to KS_PMECR.
*
* Change the power mode of the chip.
*/
static void ks_set_powermode(struct ks_net *ks, unsigned pwrmode)
{
unsigned pmecr;
if (netif_msg_hw(ks))
ks_dbg(ks, "setting power mode %d\n", pwrmode);
ks_rdreg16(ks, KS_GRR);
pmecr = ks_rdreg16(ks, KS_PMECR);
pmecr &= ~PMECR_PM_MASK;
pmecr |= pwrmode;
ks_wrreg16(ks, KS_PMECR, pmecr);
}
/**
* ks_read_config - read chip configuration of bus width.
* @ks: The chip information
*
*/
static void ks_read_config(struct ks_net *ks)
{
u16 reg_data = 0;
/* Regardless of bus width, 8 bit read should always work.*/
reg_data = ks_rdreg8(ks, KS_CCR) & 0x00FF;
reg_data |= ks_rdreg8(ks, KS_CCR+1) << 8;
/* addr/data bus are multiplexed */
ks->sharedbus = (reg_data & CCR_SHARED) == CCR_SHARED;
/* There are garbage data when reading data from QMU,
depending on bus-width.
*/
if (reg_data & CCR_8BIT) {
ks->bus_width = ENUM_BUS_8BIT;
ks->extra_byte = 1;
} else if (reg_data & CCR_16BIT) {
ks->bus_width = ENUM_BUS_16BIT;
ks->extra_byte = 2;
} else {
ks->bus_width = ENUM_BUS_32BIT;
ks->extra_byte = 4;
}
}
/**
* ks_soft_reset - issue one of the soft reset to the device
* @ks: The device state.
* @op: The bit(s) to set in the GRR
*
* Issue the relevant soft-reset command to the device's GRR register
* specified by @op.
*
* Note, the delays are in there as a caution to ensure that the reset
* has time to take effect and then complete. Since the datasheet does
* not currently specify the exact sequence, we have chosen something
* that seems to work with our device.
*/
static void ks_soft_reset(struct ks_net *ks, unsigned op)
{
/* Disable interrupt first */
ks_wrreg16(ks, KS_IER, 0x0000);
ks_wrreg16(ks, KS_GRR, op);
mdelay(10); /* wait a short time to effect reset */
ks_wrreg16(ks, KS_GRR, 0);
mdelay(1); /* wait for condition to clear */
}
/**
* ks_read_qmu - read 1 pkt data from the QMU.
* @ks: The chip information
* @buf: buffer address to save 1 pkt
* @len: Pkt length
* Here is the sequence to read 1 pkt:
* 1. set sudo DMA mode
* 2. read prepend data
* 3. read pkt data
* 4. reset sudo DMA Mode
*/
static inline void ks_read_qmu(struct ks_net *ks, u16 *buf, u32 len)
{
u32 r = ks->extra_byte & 0x1 ;
u32 w = ks->extra_byte - r;
/* 1. set sudo DMA mode */
ks_wrreg16(ks, KS_RXFDPR, RXFDPR_RXFPAI);
ks_wrreg8(ks, KS_RXQCR, (ks->rc_rxqcr | RXQCR_SDA) & 0xff);
/* 2. read prepend data */
/**
* read 4 + extra bytes and discard them.
* extra bytes for dummy, 2 for status, 2 for len
*/
/* use likely(r) for 8 bit access for performance */
if (unlikely(r))
ioread8(ks->hw_addr);
ks_inblk(ks, buf, w + 2 + 2);
/* 3. read pkt data */
ks_inblk(ks, buf, ALIGN(len, 4));
/* 4. reset sudo DMA Mode */
ks_wrreg8(ks, KS_RXQCR, ks->rc_rxqcr);
}
/**
* ks_rcv - read multiple pkts data from the QMU.
* @ks: The chip information
* @netdev: The network device being opened.
*
* Read all of header information before reading pkt content.
* It is not allowed only port of pkts in QMU after issuing
* interrupt ack.
*/
static void ks_rcv(struct ks_net *ks, struct net_device *netdev)
{
u32 i;
struct type_frame_head *frame_hdr = ks->frame_head_info;
struct sk_buff *skb;
ks->frame_cnt = ks_rdreg16(ks, KS_RXFCTR) >> 8;
/* read all header information */
for (i = 0; i < ks->frame_cnt; i++) {
/* Checking Received packet status */
frame_hdr->sts = ks_rdreg16(ks, KS_RXFHSR);
/* Get packet len from hardware */
frame_hdr->len = ks_rdreg16(ks, KS_RXFHBCR);
frame_hdr++;
}
frame_hdr = ks->frame_head_info;
while (ks->frame_cnt--) {
skb = dev_alloc_skb(frame_hdr->len + 16);
if (likely(skb && (frame_hdr->sts & RXFSHR_RXFV) &&
(frame_hdr->len < RX_BUF_SIZE) && frame_hdr->len)) {
skb_reserve(skb, 2);
/* read data block including CRC 4 bytes */
ks_read_qmu(ks, (u16 *)skb->data, frame_hdr->len + 4);
skb_put(skb, frame_hdr->len);
skb->dev = netdev;title='author Jens Axboe <axboe@suse.de> 2006-05-01 13:50:48 -0400
committer Jens Axboe <axboe@suse.de> 2006-05-01 13:50:48 -0400
[PATCH] splice: fix bugs in pipe_to_file()' href='/cgit/cgit.cgi/litmus-rt.git/commit/fs/splice.c?h=prop/robust-tie-break&id=0568b409c74f7a125d92a09a3f386785700ef688'>0568b409c74f
|
|
/*
* "splice": joining two ropes together by interweaving their strands.
*
* This is the "extended pipe" functionality, where a pipe is used as
* an arbitrary in-memory buffer. Think of a pipe as a small kernel
* buffer that you can use to transfer data from one end to the other.
*
* The traditional unix read/write is extended with a "splice()" operation
* that transfers data buffers to or from a pipe buffer.
*
* Named by Larry McVoy, original implementation from Linus, extended by
* Jens to support splicing to files, network, direct splicing, etc and
* fixing lots of bugs.
*
* Copyright (C) 2005-2006 Jens Axboe <axboe@suse.de>
* Copyright (C) 2005-2006 Linus Torvalds <torvalds@osdl.org>
* Copyright (C) 2006 Ingo Molnar <mingo@elte.hu>
*
*/
#include <linux/fs.h>
#include <linux/file.h>
#include <linux/pagemap.h>
#include <linux/pipe_fs_i.h>
#include <linux/mm_inline.h>
#include <linux/swap.h>
#include <linux/writeback.h>
#include <linux/buffer_head.h>
#include <linux/module.h>
#include <linux/syscalls.h>
#include <linux/uio.h>
struct partial_page {
unsigned int offset;
unsigned int len;
};
/*
* Passed to splice_to_pipe
*/
struct splice_pipe_desc {
struct page **pages; /* page map */
struct partial_page *partial; /* pages[] may not be contig */
int nr_pages; /* number of pages in map */
unsigned int flags; /* splice flags */
struct pipe_buf_operations *ops;/* ops associated with output pipe */
};
/*
* Attempt to steal a page from a pipe buffer. This should perhaps go into
* a vm helper function, it's already simplified quite a bit by the
* addition of remove_mapping(). If success is returned, the caller may
* attempt to reuse this page for another destination.
*/
static int page_cache_pipe_buf_steal(struct pipe_inode_info *pipe,
struct pipe_buffer *buf)
{
struct page *page = buf->page;
struct address_space *mapping = page_mapping(page);
lock_page(page);
WARN_ON(!PageUptodate(page));
/*
* At least for ext2 with nobh option, we need to wait on writeback
* completing on this page, since we'll remove it from the pagecache.
* Otherwise truncate wont wait on the page, allowing the disk
* blocks to be reused by someone else before we actually wrote our
* data to them. fs corruption ensues.
*/
wait_on_page_writeback(page);
if (PagePrivate(page))
try_to_release_page(page, mapping_gfp_mask(mapping));
if (!remove_mapping(mapping, page)) {
unlock_page(page);
return 1;
}
buf->flags |= PIPE_BUF_FLAG_LRU;
return 0;
}
static void page_cache_pipe_buf_release(struct pipe_inode_info *pipe,
struct pipe_buffer *buf)
{
page_cache_release(buf->page);
buf->flags &= ~PIPE_BUF_FLAG_LRU;
}
static int page_cache_pipe_buf_pin(struct pipe_inode_info *pipe,
struct pipe_buffer *buf)
{
struct page *page = buf->page;
int err;
if (!PageUptodate(page)) {
lock_page(page);
/*
* Page got truncated/unhashed. This will cause a 0-byte
* splice, if this is the first page.
*/
if (!page->mapping) {
err = -ENODATA;
goto error;
}
/*
* Uh oh, read-error from disk.
*/
if (!PageUptodate(page)) {
err = -EIO;
goto error;
}
/*
* Page is ok afterall, we are done.
*/
unlock_page(page);
}
return 0;
error:
unlock_page(page);
return err;
}
static struct pipe_buf_operations page_cache_pipe_buf_ops = {
.can_merge = 0,
.map = generic_pipe_buf_map,
.unmap = generic_pipe_buf_unmap,
.pin = page_cache_pipe_buf_pin,
.release = page_cache_pipe_buf_release,
.steal = page_cache_pipe_buf_steal,
.get = generic_pipe_buf_get,
};
static int user_page_pipe_buf_steal(struct pipe_inode_info *pipe,
struct pipe_buffer *buf)
{
if (!(buf->flags & PIPE_BUF_FLAG_GIFT))
return 1;
buf->flags |= PIPE_BUF_FLAG_LRU;
return generic_pipe_buf_steal(pipe, buf);
}
static struct pipe_buf_operations user_page_pipe_buf_ops = {
.can_merge = 0,
.map = generic_pipe_buf_map,
.unmap = generic_pipe_buf_unmap,
.pin = generic_pipe_buf_pin,
.release = page_cache_pipe_buf_release,
.steal = user_page_pipe_buf_steal,
.get = generic_pipe_buf_get,
};
/*
* Pipe output worker. This sets up our pipe format with the page cache
* pipe buffer operations. Otherwise very similar to the regular pipe_writev().
*/
static ssize_t splice_to_pipe(struct pipe_inode_info *pipe,
struct splice_pipe_desc *spd)
{
int ret, do_wakeup, page_nr;
ret = 0;
do_wakeup = 0;
page_nr = 0;
if (pipe->inode)
mutex_lock(&pipe->inode->i_mutex);
for (;;) {
if (!pipe->readers) {
send_sig(SIGPIPE, current, 0);
if (!ret)
ret = -EPIPE;
break;
}
if (pipe->nrbufs < PIPE_BUFFERS) {
int newbuf = (pipe->curbuf + pipe->nrbufs) & (PIPE_BUFFERS - 1);
struct pipe_buffer *buf = pipe->bufs + newbuf;
buf->page = spd->pages[page_nr];
buf->offset = spd->partial[page_nr].offset;
buf->len = spd->partial[page_nr].len;
buf->ops = spd->ops;
if (spd->flags & SPLICE_F_GIFT)
buf->flags |= PIPE_BUF_FLAG_GIFT;
pipe->nrbufs++;
page_nr++;
ret += buf->len;
if (pipe->inode)
do_wakeup = 1;
if (!--spd->nr_pages)
break;
if (pipe->nrbufs < PIPE_BUFFERS)
continue;
break;
}
if (spd->flags & SPLICE_F_NONBLOCK) {
if (!ret)
ret = -EAGAIN;
break;
}
if (signal_pending(current)) {
if (!ret)
ret = -ERESTARTSYS;
break;
}
if (do_wakeup) {
smp_mb();
if (waitqueue_active(&pipe->wait))
wake_up_interruptible_sync(&pipe->wait);
kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN);
do_wakeup = 0;
}
pipe->waiting_writers++;
pipe_wait(pipe);
pipe->waiting_writers--;
}
if (pipe->inode)
mutex_unlock(&pipe->inode->i_mutex);
if (do_wakeup) {
smp_mb();
if (waitqueue_active(&pipe->wait))
wake_up_interruptible(&pipe->wait);
kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN);
}
while (page_nr < spd->nr_pages)
page_cache_release(spd->pages[page_nr++]);
return ret;
}
static int
__generic_file_splice_read(struct file *in, loff_t *ppos,
struct pipe_inode_info *pipe, size_t len,
unsigned int flags)
{
struct address_space *mapping = in->f_mapping;
unsigned int loff, nr_pages;
struct page *pages[PIPE_BUFFERS];
struct partial_page partial[PIPE_BUFFERS];
struct page *page;
pgoff_t index, end_index;
loff_t isize;
size_t total_len;
int error, page_nr;
struct splice_pipe_desc spd = {
.pages = pages,
.partial = partial,
.flags = flags,
.ops = &page_cache_pipe_buf_ops,
};
index = *ppos >> PAGE_CACHE_SHIFT;
loff = *ppos & ~PAGE_CACHE_MASK;
nr_pages = (len + loff + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
if (nr_pages > PIPE_BUFFERS)
nr_pages = PIPE_BUFFERS;
/*
* Initiate read-ahead on this page range. however, don't call into
* read-ahead if this is a non-zero offset (we are likely doing small
* chunk splice and the page is already there) for a single page.
*/
if (!loff || nr_pages > 1)
page_cache_readahead(mapping, &in->f_ra, in, index, nr_pages);
/*
* Now fill in the holes:
*/
error = 0;
total_len = 0;
/*
* Lookup the (hopefully) full range of pages we need.
*/
spd.nr_pages = find_get_pages_contig(mapping, index, nr_pages, pages);
/*
* If find_get_pages_contig() returned fewer pages than we needed,
* allocate the rest.
*/
index += spd.nr_pages;
while (spd.nr_pages < nr_pages) {
/*
* Page could be there, find_get_pages_contig() breaks on
* the first hole.
*/
page = find_get_page(mapping, index);
if (!page) {
/*
* Make sure the read-ahead engine is notified
* about this failure.
*/
handle_ra_miss(mapping, &in->f_ra, index);
/*
* page didn't exist, allocate one.
*/
page = page_cache_alloc_cold(mapping);
if (!page)
break;
error = add_to_page_cache_lru(page, mapping, index,
mapping_gfp_mask(mapping));
if (unlikely(error)) {
page_cache_release(page);
if (error == -EEXIST)
continue;
break;
}
/*
* add_to_page_cache() locks the page, unlock it
* to avoid convoluting the logic below even more.
*/
unlock_page(page);
}
pages[spd.nr_pages++] = page;
index++;
}
/*
* Now loop over the map and see if we need to start IO on any
* pages, fill in the partial map, etc.
*/
index = *ppos >> PAGE_CACHE_SHIFT;
nr_pages = spd.nr_pages;
spd.nr_pages = 0;
for (page_nr = 0; page_nr < nr_pages; page_nr++) {
unsigned int this_len;
if (!len)
break;
/*
* this_len is the max we'll use from this page
*/
this_len = min_t(unsigned long, len, PAGE_CACHE_SIZE - loff);
page = pages[page_nr];
/*
* If the page isn't uptodate, we may need to start io on it
*/
if (!PageUptodate(page)) {
/*
* If in nonblock mode then dont block on waiting
* for an in-flight io page
*/
if (flags & SPLICE_F_NONBLOCK)
break;
lock_page(page);
/*
* page was truncated, stop here. if this isn't the
* first page, we'll just complete what we already
* added
*/
if (!page->mapping) {
unlock_page(page);
break;
}
/*
* page was already under io and is now done, great
*/
if (PageUptodate(page)) {
unlock_page(page);
goto fill_it;
}
/*
* need to read in the page
*/
error = mapping->a_ops->readpage(in, page);
if (unlikely(error)) {
/*
* We really should re-lookup the page here,
* but it complicates things a lot. Instead
* lets just do what we already stored, and
* we'll get it the next time we are called.
*/
if (error == AOP_TRUNCATED_PAGE)
error = 0;
break;
}
/*
* i_size must be checked after ->readpage().
*/
isize = i_size_read(mapping->host);
end_index = (isize - 1) >> PAGE_CACHE_SHIFT;
if (unlikely(!isize || index > end_index))
break;
/*
* if this is the last page, see if we need to shrink
* the length and stop
*/
if (end_index == index) {
loff = PAGE_CACHE_SIZE - (isize & ~PAGE_CACHE_MASK);
if (total_len + loff > isize)
break;
/*
* force quit after adding this page
*/
len = this_len;
this_len = min(this_len, loff);
loff = 0;
}
}
fill_it:
partial[page_nr].offset = loff;
partial[page_nr].len = this_len;
len -= this_len;
total_len += this_len;
loff = 0;
spd.nr_pages++;
index++;
}
/*
* Release any pages at the end, if we quit early. 'i' is how far
* we got, 'nr_pages' is how many pages are in the map.
*/
while (page_nr < nr_pages)
page_cache_release(pages[page_nr++]);
if (spd.nr_pages)
return splice_to_pipe(pipe, &spd);
return error;
}
/**
* generic_file_splice_read - splice data from file to a pipe
* @in: file to splice from
* @pipe: pipe to splice to
* @len: number of bytes to splice
* @flags: splice modifier flags
*
* Will read pages from given file and fill them into a pipe.
*/
ssize_t generic_file_splice_read(struct file *in, loff_t *ppos,
struct pipe_inode_info *pipe, size_t len,
unsigned int flags)
{
ssize_t spliced;
int ret;
ret = 0;
spliced = 0;
while (len) {
ret = __generic_file_splice_read(in, ppos, pipe, len, flags);
if (ret < 0)
break;
else if (!ret) {
if (spliced)
break;
if (flags & SPLICE_F_NONBLOCK) {
ret = -EAGAIN;
break;
}
}
*ppos += ret;
len -= ret;
spliced += ret;
}
if (spliced)
return spliced;
return ret;
}
EXPORT_SYMBOL(generic_file_splice_read);
/*
* Send 'sd->len' bytes to socket from 'sd->file' at position 'sd->pos'
* using sendpage(). Return the number of bytes sent.
*/
static int pipe_to_sendpage(struct pipe_inode_info *pipe,
struct pipe_buffer *buf, struct splice_desc *sd)
{
struct file *file = sd->file;
loff_t pos = sd->pos;
int ret, more;
ret = buf->ops->pin(pipe, buf);
if (!ret) {
more = (sd->flags & SPLICE_F_MORE) || sd->len < sd->total_len;
ret = file->f_op->sendpage(file, buf->page, buf->offset,
sd->len, &pos, more);
}
return ret;
}
/*
* This is a little more tricky than the file -> pipe splicing. There are
* basically three cases:
*
* - Destination page already exists in the address space and there
* are users of it. For that case we have no other option that
* copying the data. Tough luck.
* - Destination page already exists in the address space, but there
* are no users of it. Make sure it's uptodate, then drop it. Fall
* through to last case.
* - Destination page does not exist, we can add the pipe page to
* the page cache and avoid the copy.
*
* If asked to move pages to the output file (SPLICE_F_MOVE is set in
* sd->flags), we attempt to migrate pages from the pipe to the output
* file address space page cache. This is possible if no one else has
* the pipe page referenced outside of the pipe and page cache. If
* SPLICE_F_MOVE isn't set, or we cannot move the page, we simply create
* a new page in the output file page cache and fill/dirty that.
*/
static int pipe_to_file(struct pipe_inode_info *pipe, struct pipe_buffer *buf,
struct splice_desc *sd)
{
struct file *file = sd->file;
struct address_space *mapping = file->f_mapping;
gfp_t gfp_mask = mapping_gfp_mask(mapping);
unsigned int offset, this_len;
struct page *page;
pgoff_t index;
int ret;
/*
* make sure the data in this buffer is uptodate
*/
ret = buf->ops->pin(pipe, buf);
if (unlikely(ret))
return ret;
index = sd->pos >> PAGE_CACHE_SHIFT;
offset = sd->pos & ~PAGE_CACHE_MASK;
this_len = sd->len;
if (this_len + offset > PAGE_CACHE_SIZE)
this_len = PAGE_CACHE_SIZE - offset;
/*
* Reuse buf page, if SPLICE_F_MOVE is set and we are doing a full
* page.
*/
if ((sd->flags & SPLICE_F_MOVE) && this_len == PAGE_CACHE_SIZE) {
/*
* If steal succeeds, buf->page is now pruned from the
* pagecache and we can reuse it. The page will also be
* locked on successful return.
*/
if (buf->ops->steal(pipe, buf))
goto find_page;
page = buf->page;
if (add_to_page_cache(page, mapping, index, gfp_mask)) {
unlock_page(page);
goto find_page;
}
page_cache_get(page);
if (!(buf->flags & PIPE_BUF_FLAG_LRU))
lru_cache_add(page);
} else {
find_page:
page = find_lock_page(mapping, index);
if (!page) {
ret = -ENOMEM;
page = page_cache_alloc_cold(mapping);
if (unlikely(!page))
goto out_nomem;
/*
* This will also lock the page
*/
ret = add_to_page_cache_lru(page, mapping, index,
gfp_mask);
if (unlikely(ret))
goto out;
}
/*
* We get here with the page locked. If the page is also
* uptodate, we don't need to do more. If it isn't, we
* may need to bring it in if we are not going to overwrite
* the full page.
*/
if (!PageUptodate(page)) {
if (this_len < PAGE_CACHE_SIZE) {
ret = mapping->a_ops->readpage(file, page);
if (unlikely(ret))
goto out;
lock_page(page);
if (!PageUptodate(page)) {
/*
* Page got invalidated, repeat.
*/
if (!page->mapping) {
unlock_page(page);
page_cache_release(page);
goto find_page;
}
ret = -EIO;
goto out;
}
} else
SetPageUptodate(page);
}
}
ret = mapping->a_ops->prepare_write(file, page, offset, offset+this_len);
if (unlikely(ret)) {
loff_t isize = i_size_read(mapping->host);
if (ret != AOP_TRUNCATED_PAGE)
unlock_page(page);
page_cache_release(page);
if (ret == AOP_TRUNCATED_PAGE)
goto find_page;
/*
* prepare_write() may have instantiated a few blocks
* outside i_size. Trim these off again.
*/
if (sd->pos + this_len > isize)
vmtruncate(mapping->host, isize);
goto out;
}
if (buf->page != page) {
/*
* Careful, ->map() uses KM_USER0!
*/
char *src = buf->ops->map(pipe, buf, 1);
char *dst = kmap_atomic(page, KM_USER1);
memcpy(dst + offset, src + buf->offset, this_len);
flush_dcache_page(page);
kunmap_atomic(dst, KM_USER1);
buf->ops->unmap(pipe, buf, src);
}
ret = mapping->a_ops->commit_write(file, page, offset, offset+this_len);
if (!ret) {
/*
* Return the number of bytes written and mark page as
* accessed, we are now done!
*/
ret = this_len;
mark_page_accessed(page);
balance_dirty_pages_ratelimited(mapping);
} else if (ret == AOP_TRUNCATED_PAGE) {
page_cache_release(page);
goto find_page;
}
out:
page_cache_release(page);
unlock_page(page);
out_nomem:
return ret;
}
/*
* Pipe input worker. Most of this logic works like a regular pipe, the
* key here is the 'actor' worker passed in that actually moves the data
* to the wanted destination. See pipe_to_file/pipe_to_sendpage above.
*/
ssize_t splice_from_pipe(struct pipe_inode_info *pipe, struct file *out,
loff_t *ppos, size_t len, unsigned int flags,
splice_actor *actor)
{
int ret, do_wakeup, err;
struct splice_desc sd;
ret = 0;
do_wakeup = 0;
sd.total_len = len;
sd.flags = flags;
sd.file = out;
sd.pos = *ppos;
if (pipe->inode)
mutex_lock(&pipe->inode->i_mutex);
for (;;) {
if (pipe->nrbufs) {
struct pipe_buffer *buf = pipe->bufs + pipe->curbuf;
struct pipe_buf_operations *ops = buf->ops;
sd.len = buf->len;
if (sd.len > sd.total_len)
sd.len = sd.total_len;
err = actor(pipe, buf, &sd);
if (err <= 0) {
if (!ret && err != -ENODATA)
ret = err;
break;
}
ret += err;
buf->offset += err;
buf->len -= err;
sd.len -= err;
sd.pos += err;
sd.total_len -= err;
if (sd.len)
continue;
if (!buf->len) {
buf->ops = NULL;
ops->release(pipe, buf);
pipe->curbuf = (pipe->curbuf + 1) & (PIPE_BUFFERS - 1);
pipe->nrbufs--;
if (pipe->inode)
do_wakeup = 1;
}
if (!sd.total_len)
break;
}
if (pipe->nrbufs)
continue;
if (!pipe->writers)
break;
if (!pipe->waiting_writers) {
if (ret)
break;
}
if (flags & SPLICE_F_NONBLOCK) {
if (!ret)
ret = -EAGAIN;
break;
}
if (signal_pending(current)) {
if (!ret)
ret = -ERESTARTSYS;
break;
}
if (do_wakeup) {
smp_mb();
if (waitqueue_active(&pipe->wait))
wake_up_interruptible_sync(&pipe->wait);
kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT);
do_wakeup = 0;
}
pipe_wait(pipe);
}
if (pipe->inode)
mutex_unlock(&pipe->inode->i_mutex);
if (do_wakeup) {
smp_mb();
if (waitqueue_active(&pipe->wait))
wake_up_interruptible(&pipe->wait);
kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT);
}
return ret;
}
/**
* generic_file_splice_write - splice data from a pipe to a file
* @pipe: pipe info
* @out: file to write to
* @len: number of bytes to splice
* @flags: splice modifier flags
*
* Will either move or copy pages (determined by @flags options) from
* the given pipe inode to the given file.
*
*/
ssize_t
generic_file_splice_write(struct pipe_inode_info *pipe, struct file *out,
loff_t *ppos, size_t len, unsigned int flags)
{
struct address_space *mapping = out->f_mapping;
ssize_t ret;
ret = splice_from_pipe(pipe, out, ppos, len, flags, pipe_to_file);
if (ret > 0) {
struct inode *inode = mapping->host;
*ppos += ret;
/*
* If file or inode is SYNC and we actually wrote some data,
* sync it.
*/
if (unlikely((out->f_flags & O_SYNC) || IS_SYNC(inode))) {
int err;
mutex_lock(&inode->i_mutex);
err = generic_osync_inode(inode, mapping,
OSYNC_METADATA|OSYNC_DATA);
mutex_unlock(&inode->i_mutex);
if (err)
ret = err;
}
}
return ret;
}
EXPORT_SYMBOL(generic_file_splice_write);
/**
* generic_splice_sendpage - splice data from a pipe to a socket
* @inode: pipe inode
* @out: socket to write to
* @len: number of bytes to splice
* @flags: splice modifier flags
*
* Will send @len bytes from the pipe to a network socket. No data copying
* is involved.
*
*/
ssize_t generic_splice_sendpage(struct pipe_inode_info *pipe, struct file *out,
loff_t *ppos, size_t len, unsigned int flags)
{
return splice_from_pipe(pipe, out, ppos, len, flags, pipe_to_sendpage);
}
EXPORT_SYMBOL(generic_splice_sendpage);
/*
* Attempt to initiate a splice from pipe to file.
*/
static long do_splice_from(struct pipe_inode_info *pipe, struct file *out,
loff_t *ppos, size_t len, unsigned int flags)
{
int ret;
if (unlikely(!out->f_op || !out->f_op->splice_write))
return -EINVAL;
if (unlikely(!(out->f_mode & FMODE_WRITE)))
return -EBADF;
ret = rw_verify_area(WRITE, out, ppos, len);
if (unlikely(ret < 0))
return ret;
return out->f_op->splice_write(pipe, out, ppos, len, flags);
}
/*
* Attempt to initiate a splice from a file to a pipe.
*/
static long do_splice_to(struct file *in, loff_t *ppos,
struct pipe_inode_info *pipe, size_t len,
unsigned int flags)
{
loff_t isize, left;
int ret;
if (unlikely(!in->f_op || !in->f_op->splice_read))
return -EINVAL;
if (unlikely(!(in->f_mode & FMODE_READ)))
return -EBADF;
ret = rw_verify_area(READ, in, ppos, len);
if (unlikely(ret < 0))
return ret;
isize = i_size_read(in->f_mapping->host);
if (unlikely(*ppos >= isize))
return 0;
left = isize - *ppos;
if (unlikely(left < len))
len = left;
return in->f_op->splice_read(in, ppos, pipe, len, flags);
}
long do_splice_direct(struct file *in, loff_t *ppos, struct file *out,
size_t len, unsigned int flags)
{
struct pipe_inode_info *pipe;
long ret, bytes;
loff_t out_off;
umode_t i_mode;
int i;
/*
* We require the input being a regular file, as we don't want to
* randomly drop data for eg socket -> socket splicing. Use the
* piped splicing for that!
*/
i_mode = in->f_dentry->d_inode->i_mode;
if (unlikely(!S_ISREG(i_mode) && !S_ISBLK(i_mode)))
return -EINVAL;
/*
* neither in nor out is a pipe, setup an internal pipe attached to
* 'out' and transfer the wanted data from 'in' to 'out' through that
*/
pipe = current->splice_pipe;
if (unlikely(!pipe)) {
pipe = alloc_pipe_info(NULL);
if (!pipe)
return -ENOMEM;
/*
* We don't have an immediate reader, but we'll read the stuff
* out of the pipe right after the splice_to_pipe(). So set
* PIPE_READERS appropriately.
*/
pipe->readers = 1;
current->splice_pipe = pipe;
}
/*
* Do the splice.
*/
ret = 0;
bytes = 0;
out_off = 0;
while (len) {
size_t read_len, max_read_len;
/*
* Do at most PIPE_BUFFERS pages worth of transfer:
*/
max_read_len = min(len, (size_t)(PIPE_BUFFERS*PAGE_SIZE));
ret = do_splice_to(in, ppos, pipe, max_read_len, flags);
if (unlikely(ret < 0))
goto out_release;
read_len = ret;
/*
* NOTE: nonblocking mode only applies to the input. We
* must not do the output in nonblocking mode as then we
* could get stuck data in the internal pipe:
*/
ret = do_splice_from(pipe, out, &out_off, read_len,
flags & ~SPLICE_F_NONBLOCK);
if (unlikely(ret < 0))
goto out_release;
bytes += ret;
len -= ret;
/*
* In nonblocking mode, if we got back a short read then
* that was due to either an IO error or due to the
* pagecache entry not being there. In the IO error case
* the _next_ splice attempt will produce a clean IO error
* return value (not a short read), so in both cases it's
* correct to break out of the loop here:
*/
if ((flags & SPLICE_F_NONBLOCK) && (read_len < max_read_len))
break;
}
pipe->nrbufs = pipe->curbuf = 0;
return bytes;
out_release:
/*
* If we did an incomplete transfer we must release
* the pipe buffers in question:
*/
for (i = 0; i < PIPE_BUFFERS; i++) {
struct pipe_buffer *buf = pipe->bufs + i;
if (buf->ops) {
buf->ops->release(pipe, buf);
buf->ops = NULL;
}
}
pipe->nrbufs = pipe->curbuf = 0;
/*
* If we transferred some data, return the number of bytes:
*/
if (bytes > 0)
return bytes;
return ret;
}
EXPORT_SYMBOL(do_splice_direct);
/*
* Determine where to splice to/from.
*/
static long do_splice(struct file *in, loff_t __user *off_in,
struct file *out, loff_t __user *off_out,
size_t len, unsigned int flags)
{
struct pipe_inode_info *pipe;
loff_t offset, *off;
long ret;
pipe = in->f_dentry->d_inode->i_pipe;
if (pipe) {
if (off_in)
return -ESPIPE;
if (off_out) {
if (out->f_op->llseek == no_llseek)
return -EINVAL;
if (copy_from_user(&offset, off_out, sizeof(loff_t)))
return -EFAULT;
off = &offset;
} else
off = &out->f_pos;
ret = do_splice_from(pipe, out, off, len, flags);
if (off_out && copy_to_user(off_out, off, sizeof(loff_t)))
ret = -EFAULT;
return ret;
}
pipe = out->f_dentry->d_inode->i_pipe;
if (pipe) {
if (off_out)
return -ESPIPE;
if (off_in) {
if (in->f_op->llseek == no_llseek)
return -EINVAL;
if (copy_from_user(&offset, off_in, sizeof(loff_t)))
return -EFAULT;
off = &offset;
} else
off = &in->f_pos;
ret = do_splice_to(in, off, pipe, len, flags);
if (off_in && copy_to_user(off_in, off, sizeof(loff_t)))
ret = -EFAULT;
return ret;
}
return -EINVAL;
}
/*
* Map an iov into an array of pages and offset/length tupples. With the
* partial_page structure, we can map several non-contiguous ranges into
* our ones pages[] map instead of splitting that operation into pieces.
* Could easily be exported as a generic helper for other users, in which
* case one would probably want to add a 'max_nr_pages' parameter as well.
*/
static int get_iovec_page_array(const struct iovec __user *iov,
unsigned int nr_vecs, struct page **pages,
struct partial_page *partial, int aligned)
{
int buffers = 0, error = 0;
/*
* It's ok to take the mmap_sem for reading, even
* across a "get_user()".
*/
down_read(¤t->mm->mmap_sem);
while (nr_vecs) {
unsigned long off, npages;
void __user *base;
size_t len;
int i;
/*
* Get user address base and length for this iovec.
*/
error = get_user(base, &iov->iov_base);
if (unlikely(error))
break;
error = get_user(len, &iov->iov_len);
if (unlikely(error))
break;
/*
* Sanity check this iovec. 0 read succeeds.
*/
if (unlikely(!len))
break;
error = -EFAULT;
if (unlikely(!base))
break;
/*
* Get this base offset and number of pages, then map
* in the user pages.
*/
off = (unsigned long) base & ~PAGE_MASK;
/*
* If asked for alignment, the offset must be zero and the
* length a multiple of the PAGE_SIZE.
*/
error = -EINVAL;
if (aligned && (off || len & ~PAGE_MASK))
break;
npages = (off + len + PAGE_SIZE - 1) >> PAGE_SHIFT;
if (npages > PIPE_BUFFERS - buffers)
npages = PIPE_BUFFERS - buffers;
error = get_user_pages(current, current->mm,
(unsigned long) base, npages, 0, 0,
&pages[buffers], NULL);
if (unlikely(error <= 0))
break;
/*
* Fill this contiguous range into the partial page map.
*/
for (i = 0; i < error; i++) {
const int plen = min_t(size_t, len, PAGE_SIZE - off);
partial[buffers].offset = off;
partial[buffers].len = plen;
off = 0;
len -= plen;
buffers++;
}
/*
* We didn't complete this iov, stop here since it probably
* means we have to move some of this into a pipe to
* be able to continue.
*/
if (len)
break;
/*
* Don't continue if we mapped fewer pages than we asked for,
* or if we mapped the max number of pages that we have
* room for.
*/
if (error < npages || buffers == PIPE_BUFFERS)
break;
nr_vecs--;
iov++;
}
up_read(¤t->mm->mmap_sem);
if (buffers)
return buffers;
return error;
}
/*
* vmsplice splices a user address range into a pipe. It can be thought of
* as splice-from-memory, where the regular splice is splice-from-file (or
* to file). In both cases the output is a pipe, naturally.
*
* Note that vmsplice only supports splicing _from_ user memory to a pipe,
* not the other way around. Splicing from user memory is a simple operation
* that can be supported without any funky alignment restrictions or nasty
* vm tricks. We simply map in the user memory and fill them into a pipe.
* The reverse isn't quite as easy, though. There are two possible solutions
* for that:
*
* - memcpy() the data internally, at which point we might as well just
* do a regular read() on the buffer anyway.
* - Lots of nasty vm tricks, that are neither fast nor flexible (it
* has restriction limitations on both ends of the pipe).
*
* Alas, it isn't here.
*
*/
static long do_vmsplice(struct file *file, const struct iovec __user *iov,
unsigned long nr_segs, unsigned int flags)
{
struct pipe_inode_info *pipe = file->f_dentry->d_inode->i_pipe;
struct page *pages[PIPE_BUFFERS];
struct partial_page partial[PIPE_BUFFERS];
struct splice_pipe_desc spd = {
.pages = pages,
.partial = partial,
.flags = flags,
.ops = &user_page_pipe_buf_ops,
};
if (unlikely(!pipe))
return -EBADF;
if (unlikely(nr_segs > UIO_MAXIOV))
return -EINVAL;
else if (unlikely(!nr_segs))
return 0;
spd.nr_pages = get_iovec_page_array(iov, nr_segs, pages, partial,
flags & SPLICE_F_GIFT);
if (spd.nr_pages <= 0)
return spd.nr_pages;
return splice_to_pipe(pipe, &spd);
}
asmlinkage long sys_vmsplice(int fd, const struct iovec __user *iov,
unsigned long nr_segs, unsigned int flags)
{
struct file *file;
long error;
int fput;
error = -EBADF;
file = fget_light(fd, &fput);
if (file) {
if (file->f_mode & FMODE_WRITE)
error = do_vmsplice(file, iov, nr_segs, flags);
fput_light(file, fput);
}
return error;
}
asmlinkage long sys_splice(int fd_in, loff_t __user *off_in,
int fd_out, loff_t __user *off_out,
size_t len, unsigned int flags)
{
long error;
struct file *in, *out;
int fput_in, fput_out;
if (unlikely(!len))
return 0;
error = -EBADF;
in = fget_light(fd_in, &fput_in);
if (in) {
if (in->f_mode & FMODE_READ) {
out = fget_light(fd_out, &fput_out);
if (out) {
if (out->f_mode & FMODE_WRITE)
error = do_splice(in, off_in,
out, off_out,
len, flags);
fput_light(out, fput_out);
}
}
fput_light(in, fput_in);
}
return error;
}
/*
* Link contents of ipipe to opipe.
*/
static int link_pipe(struct pipe_inode_info *ipipe,
struct pipe_inode_info *opipe,
size_t len, unsigned int flags)
{
struct pipe_buffer *ibuf, *obuf;
int ret, do_wakeup, i, ipipe_first;
ret = do_wakeup = ipipe_first = 0;
/*
* Potential ABBA deadlock, work around it by ordering lock
* grabbing by inode address. Otherwise two different processes
* could deadlock (one doing tee from A -> B, the other from B -> A).
*/
if (ipipe->inode < opipe->inode) {
ipipe_first = 1;
mutex_lock(&ipipe->inode->i_mutex);
mutex_lock(&opipe->inode->i_mutex);
} else {
mutex_lock(&opipe->inode->i_mutex);
mutex_lock(&ipipe->inode->i_mutex);
}
for (i = 0;; i++) {
if (!opipe->readers) {
send_sig(SIGPIPE, current, 0);
if (!ret)
ret = -EPIPE;
break;
}
if (ipipe->nrbufs - i) {
ibuf = ipipe->bufs + ((ipipe->curbuf + i) & (PIPE_BUFFERS - 1));
/*
* If we have room, fill this buffer
*/
if (opipe->nrbufs < PIPE_BUFFERS) {
int nbuf = (opipe->curbuf + opipe->nrbufs) & (PIPE_BUFFERS - 1);
/*
* Get a reference to this pipe buffer,
* so we can copy the contents over.
*/
ibuf->ops->get(ipipe, ibuf);
obuf = opipe->bufs + nbuf;
*obuf = *ibuf;
/*
* Don't inherit the gift flag, we need to
* prevent multiple steals of this page.
*/
obuf->flags &= ~PIPE_BUF_FLAG_GIFT;
if (obuf->len > len)
obuf->len = len;
opipe->nrbufs++;
do_wakeup = 1;
ret += obuf->len;
len -= obuf->len;
if (!len)
break;
if (opipe->nrbufs < PIPE_BUFFERS)
continue;
}
/*
* We have input available, but no output room.
* If we already copied data, return that. If we
* need to drop the opipe lock, it must be ordered
* last to avoid deadlocks.
*/
if ((flags & SPLICE_F_NONBLOCK) || !ipipe_first) {
if (!ret)
ret = -EAGAIN;
break;
}
if (signal_pending(current)) {
if (!ret)
ret = -ERESTARTSYS;
break;
}
if (do_wakeup) {
smp_mb();
if (waitqueue_active(&opipe->wait))
wake_up_interruptible(&opipe->wait);
kill_fasync(&opipe->fasync_readers, SIGIO, POLL_IN);
do_wakeup = 0;
}
opipe->waiting_writers++;
pipe_wait(opipe);
opipe->waiting_writers--;
continue;
}
/*
* No input buffers, do the usual checks for available
* writers and blocking and wait if necessary
*/
if (!ipipe->writers)
break;
if (!ipipe->waiting_writers) {
if (ret)
break;
}
/*
* pipe_wait() drops the ipipe mutex. To avoid deadlocks
* with another process, we can only safely do that if
* the ipipe lock is ordered last.
*/
if ((flags & SPLICE_F_NONBLOCK) || ipipe_first) {
if (!ret)
ret = -EAGAIN;
break;
}
if (signal_pending(current)) {
if (!ret)
ret = -ERESTARTSYS;
break;
}
if (waitqueue_active(&ipipe->wait))
wake_up_interruptible_sync(&ipipe->wait);
kill_fasync(&ipipe->fasync_writers, SIGIO, POLL_OUT);
pipe_wait(ipipe);
}
mutex_unlock(&ipipe->inode->i_mutex);
mutex_unlock(&opipe->inode->i_mutex);
if (do_wakeup) {
smp_mb();
if (waitqueue_active(&opipe->wait))
wake_up_interruptible(&opipe->wait);
kill_fasync(&opipe->fasync_readers, SIGIO, POLL_IN);
}
return ret;
}
/*
* This is a tee(1) implementation that works on pipes. It doesn't copy
* any data, it simply references the 'in' pages on the 'out' pipe.
* The 'flags' used are the SPLICE_F_* variants, currently the only
* applicable one is SPLICE_F_NONBLOCK.
*/
static long do_tee(struct file *in, struct file *out, size_t len,
unsigned int flags)
{
struct pipe_inode_info *ipipe = in->f_dentry->d_inode->i_pipe;
struct pipe_inode_info *opipe = out->f_dentry->d_inode->i_pipe;
/*
* Link ipipe to the two output pipes, consuming as we go along.
*/
if (ipipe && opipe)
return link_pipe(ipipe, opipe, len, flags);
return -EINVAL;
}
asmlinkage long sys_tee(int fdin, int fdout, size_t len, unsigned int flags)
{
struct file *in;
int error, fput_in;
if (unlikely(!len))
return 0;
error = -EBADF;
in = fget_light(fdin, &fput_in);
if (in) {
if (in->f_mode & FMODE_READ) {
int fput_out;
struct file *out = fget_light(fdout, &fput_out);
if (out) {
if (out->f_mode & FMODE_WRITE)
error = do_tee(in, out, len, flags);
fput_light(out, fput_out);
}
}
fput_light(in, fput_in);
}
return error;
}
|