aboutsummaryrefslogtreecommitdiffstats
path: root/include/asm-mips/mipsregs.h
blob: 035ba0a9b0dfe3c62d1f80a510246e82b6e5ce35 (plain) (blame)
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
/*
 * This file is subject to the terms and conditions of the GNU General Public
 * License.  See the file "COPYING" in the main directory of this archive
 * for more details.
 *
 * Copyright (C) 1994, 1995, 1996, 1997, 2000, 2001 by Ralf Baechle
 * Copyright (C) 2000 Silicon Graphics, Inc.
 * Modified for further R[236]000 support by Paul M. Antoine, 1996.
 * Kevin D. Kissell, kevink@mips.com and Carsten Langgaard, carstenl@mips.com
 * Copyright (C) 2000 MIPS Technologies, Inc.  All rights reserved.
 * Copyright (C) 2003, 2004  Maciej W. Rozycki
 */
#ifndef _ASM_MIPSREGS_H
#define _ASM_MIPSREGS_H

#include <linux/config.h>
#include <linux/linkage.h>
#include <asm/hazards.h>

/*
 * The following macros are especially useful for __asm__
 * inline assembler.
 */
#ifndef __STR
#define __STR(x) #x
#endif
#ifndef STR
#define STR(x) __STR(x)
#endif

/*
 *  Configure language
 */
#ifdef __ASSEMBLY__
#define _ULCAST_
#else
#define _ULCAST_ (unsigned long)
#endif

/*
 * Coprocessor 0 register names
 */
#define CP0_INDEX $0
#define CP0_RANDOM $1
#define CP0_ENTRYLO0 $2
#define CP0_ENTRYLO1 $3
#define CP0_CONF $3
#define CP0_CONTEXT $4
#define CP0_PAGEMASK $5
#define CP0_WIRED $6
#define CP0_INFO $7
#define CP0_BADVADDR $8
#define CP0_COUNT $9
#define CP0_ENTRYHI $10
#define CP0_COMPARE $11
#define CP0_STATUS $12
#define CP0_CAUSE $13
#define CP0_EPC $14
#define CP0_PRID $15
#define CP0_CONFIG $16
#define CP0_LLADDR $17
#define CP0_WATCHLO $18
#define CP0_WATCHHI $19
#define CP0_XCONTEXT $20
#define CP0_FRAMEMASK $21
#define CP0_DIAGNOSTIC $22
#define CP0_DEBUG $23
#define CP0_DEPC $24
#define CP0_PERFORMANCE $25
#define CP0_ECC $26
#define CP0_CACHEERR $27
#define CP0_TAGLO $28
#define CP0_TAGHI $29
#define CP0_ERROREPC $30
#define CP0_DESAVE $31

/*
 * R4640/R4650 cp0 register names.  These registers are listed
 * here only for completeness; without MMU these CPUs are not useable
 * by Linux.  A future ELKS port might take make Linux run on them
 * though ...
 */
#define CP0_IBASE $0
#define CP0_IBOUND $1
#define CP0_DBASE $2
#define CP0_DBOUND $3
#define CP0_CALG $17
#define CP0_IWATCH $18
#define CP0_DWATCH $19

/*
 * Coprocessor 0 Set 1 register names
 */
#define CP0_S1_DERRADDR0  $26
#define CP0_S1_DERRADDR1  $27
#define CP0_S1_INTCONTROL $20

/*
 * Coprocessor 0 Set 2 register names
 */
#define CP0_S2_SRSCTL	  $12	/* MIPSR2 */

/*
 * Coprocessor 0 Set 3 register names
 */
#define CP0_S3_SRSMAP	  $12	/* MIPSR2 */

/*
 *  TX39 Series
 */
#define CP0_TX39_CACHE	$7

/*
 * Coprocessor 1 (FPU) register names
 */
#define CP1_REVISION   $0
#define CP1_STATUS     $31

/*
 * FPU Status Register Values
 */
/*
 * Status Register Values
 */

#define FPU_CSR_FLUSH   0x01000000      /* flush denormalised results to 0 */
#define FPU_CSR_COND    0x00800000      /* $fcc0 */
#define FPU_CSR_COND0   0x00800000      /* $fcc0 */
#define FPU_CSR_COND1   0x02000000      /* $fcc1 */
#define FPU_CSR_COND2   0x04000000      /* $fcc2 */
#define FPU_CSR_COND3   0x08000000      /* $fcc3 */
#define FPU_CSR_COND4   0x10000000      /* $fcc4 */
#define FPU_CSR_COND5   0x20000000      /* $fcc5 */
#define FPU_CSR_COND6   0x40000000      /* $fcc6 */
#define FPU_CSR_COND7   0x80000000      /* $fcc7 */

/*
 * X the exception cause indicator
 * E the exception enable
 * S the sticky/flag bit
*/
#define FPU_CSR_ALL_X   0x0003f000
#define FPU_CSR_UNI_X   0x00020000
#define FPU_CSR_INV_X   0x00010000
#define FPU_CSR_DIV_X   0x00008000
#define FPU_CSR_OVF_X   0x00004000
#define FPU_CSR_UDF_X   0x00002000
#define FPU_CSR_INE_X   0x00001000

#define FPU_CSR_ALL_E   0x00000f80
#define FPU_CSR_INV_E   0x00000800
#define FPU_CSR_DIV_E   0x00000400
#define FPU_CSR_OVF_E   0x00000200
#define FPU_CSR_UDF_E   0x00000100
#define FPU_CSR_INE_E   0x00000080

#define FPU_CSR_ALL_S   0x0000007c
#define FPU_CSR_INV_S   0x00000040
#define FPU_CSR_DIV_S   0x00000020
#define FPU_CSR_OVF_S   0x00000010
#define FPU_CSR_UDF_S   0x00000008
#define FPU_CSR_INE_S   0x00000004

/* rounding mode */
#define FPU_CSR_RN      0x0     /* nearest */
#define FPU_CSR_RZ      0x1     /* towards zero */
#define FPU_CSR_RU      0x2     /* towards +Infinity */
#define FPU_CSR_RD      0x3     /* towards -Infinity */


/*
 * Values for PageMask register
 */
#ifdef CONFIG_CPU_VR41XX

/* Why doesn't stupidity hurt ... */

#define PM_1K		0x00000000
#define PM_4K		0x00001800
#define PM_16K		0x00007800
#define PM_64K		0x0001f800
#define PM_256K		0x0007f800

#else

#define PM_4K		0x00000000
#define PM_16K		0x00006000
#define PM_64K		0x0001e000
#define PM_256K		0x0007e000
#define PM_1M		0x001fe000
#define PM_4M		0x007fe000
#define PM_16M		0x01ffe000
#define PM_64M		0x07ffe000
#define PM_256M		0x1fffe000

#endif

/*
 * Default page size for a given kernel configuration
 */
#ifdef CONFIG_PAGE_SIZE_4KB
#define PM_DEFAULT_MASK	PM_4K
#elif defined(CONFIG_PAGE_SIZE_16KB)
#define PM_DEFAULT_MASK	PM_16K
#elif defined(CONFIG_PAGE_SIZE_64KB)
#define PM_DEFAULT_MASK	PM_64K
#else
#error Bad page size configuration!
#endif


/*
 * Values used for computation of new tlb entries
 */
#define PL_4K		12
#define PL_16K		14
#define PL_64K		16
#define PL_256K		18
#define PL_1M		20
#define PL_4M		22
#define PL_16M		24
#define PL_64M		26
#define PL_256M		28

/*
 * R4x00 interrupt enable / cause bits
 */
#define IE_SW0          (_ULCAST_(1) <<  8)
#define IE_SW1          (_ULCAST_(1) <<  9)
#define IE_IRQ0         (_ULCAST_(1) << 10)
#define IE_IRQ1         (_ULCAST_(1) << 11)
#define IE_IRQ2         (_ULCAST_(1) << 12)
#define IE_IRQ3         (_ULCAST_(1) << 13)
#define IE_IRQ4         (_ULCAST_(1) << 14)
#define IE_IRQ5         (_ULCAST_(1) << 15)

/*
 * R4x00 interrupt cause bits
 */
#define C_SW0           (_ULCAST_(1) <<  8)
#define C_SW1           (_ULCAST_(1) <<  9)
#define C_IRQ0          (_ULCAST_(1) << 10)
#define C_IRQ1          (_ULCAST_(1) << 11)
#define C_IRQ2          (_ULCAST_(1) << 12)
#define C_IRQ3          (_ULCAST_(1) << 13)
#define C_IRQ4          (_ULCAST_(1) << 14)
#define C_IRQ5          (_ULCAST_(1) << 15)

/*
 * Bitfields in the R4xx0 cp0 status register
 */
#define ST0_IE			0x00000001
#define ST0_EXL			0x00000002
#define ST0_ERL			0x00000004
#define ST0_KSU			0x00000018
#  define KSU_USER		0x00000010
#  define KSU_SUPERVISOR	0x00000008
#  define KSU_KERNEL		0x00000000
#define ST0_UX			0x00000020
#define ST0_SX			0x00000040
#define ST0_KX 			0x00000080
#define ST0_DE			0x00010000
#define ST0_CE			0x00020000

/*
 * Setting c0_status.co enables Hit_Writeback and Hit_Writeback_Invalidate
 * cacheops in userspace.  This bit exists only on RM7000 and RM9000
 * processors.
 */
#define ST0_CO			0x08000000

/*
 * Bitfields in the R[23]000 cp0 status register.
 */
#define ST0_IEC                 0x00000001
#define ST0_KUC			0x00000002
#define ST0_IEP			0x00000004
#define ST0_KUP			0x00000008
#define ST0_IEO			0x00000010
#define ST0_KUO			0x00000020
/* bits 6 & 7 are reserved on R[23]000 */
#define ST0_ISC			0x00010000
#define ST0_SWC			0x00020000
#define ST0_CM			0x00080000

/*
 * Bits specific to the R4640/R4650
 */
#define ST0_UM			(_ULCAST_(1) <<  4)
#define ST0_IL			(_ULCAST_(1) << 23)
#define ST0_DL			(_ULCAST_(1) << 24)

/*
 * Enable the MIPS DSP ASE
 */
#define ST0_MX			0x01000000

/*
 * Bitfields in the TX39 family CP0 Configuration Register 3
 */
#define TX39_CONF_ICS_SHIFT	19
#define TX39_CONF_ICS_MASK	0x00380000
#define TX39_CONF_ICS_1KB 	0x00000000
#define TX39_CONF_ICS_2KB 	0x00080000
#define TX39_CONF_ICS_4KB 	0x00100000
#define TX39_CONF_ICS_8KB 	0x00180000
#define TX39_CONF_ICS_16KB 	0x00200000

#define TX39_CONF_DCS_SHIFT	16
#define TX39_CONF_DCS_MASK	0x00070000
#define TX39_CONF_DCS_1KB 	0x00000000
#define TX39_CONF_DCS_2KB 	0x00010000
#define TX39_CONF_DCS_4KB 	0x00020000
#define TX39_CONF_DCS_8KB 	0x00030000
#define TX39_CONF_DCS_16KB 	0x00040000

#define TX39_CONF_CWFON 	0x00004000
#define TX39_CONF_WBON  	0x00002000
#define TX39_CONF_RF_SHIFT	10
#define TX39_CONF_RF_MASK	0x00000c00
#define TX39_CONF_DOZE		0x00000200
#define TX39_CONF_HALT		0x00000100
#define TX39_CONF_LOCK		0x00000080
#define TX39_CONF_ICE		0x00000020
#define TX39_CONF_DCE		0x00000010
#define TX39_CONF_IRSIZE_SHIFT	2
#define TX39_CONF_IRSIZE_MASK	0x0000000c
#define TX39_CONF_DRSIZE_SHIFT	0
#define TX39_CONF_DRSIZE_MASK	0x00000003

/*
 * Status register bits available in all MIPS CPUs.
 */
#define ST0_IM			0x0000ff00
#define  STATUSB_IP0		8
#define  STATUSF_IP0		(_ULCAST_(1) <<  8)
#define  STATUSB_IP1		9
#define  STATUSF_IP1		(_ULCAST_(1) <<  9)
#define  STATUSB_IP2		10
#define  STATUSF_IP2		(_ULCAST_(1) << 10)
#define  STATUSB_IP3		11
#define  STATUSF_IP3		(_ULCAST_(1) << 11)
#define  STATUSB_IP4		12
#define  STATUSF_IP4		(_ULCAST_(1) << 12)
#define  STATUSB_IP5		13
#define  STATUSF_IP5		(_ULCAST_(1) << 13)
#define  STATUSB_IP6		14
#define  STATUSF_IP6		(_ULCAST_(1) << 14)
#define  STATUSB_IP7		15
#define  STATUSF_IP7		(_ULCAST_(1) << 15)
#define  STATUSB_IP8		0
#define  STATUSF_IP8		(_ULCAST_(1) <<  0)
#define  STATUSB_IP9		1
#define  STATUSF_IP9		(_ULCAST_(1) <<  1)
#define  STATUSB_IP10		2
#define  STATUSF_IP10		(_ULCAST_(1) <<  2)
#define  STATUSB_IP11		3
#define  STATUSF_IP11		(_ULCAST_(1) <<  3)
#define  STATUSB_IP12		4
#define  STATUSF_IP12		(_ULCAST_(1) <<  4)
#define  STATUSB_IP13		5
#define  STATUSF_IP13		(_ULCAST_(1) <<  5)
#define  STATUSB_IP14		6
#define  STATUSF_IP14		(_ULCAST_(1) <<  6)
#define  STATUSB_IP15		7
#define  STATUSF_IP15		(_ULCAST_(1) <<  7)
#define ST0_CH			0x00040000
#define ST0_SR			0x00100000
#define ST0_TS			0x00200000
#define ST0_BEV			0x00400000
#define ST0_RE			0x02000000
#define ST0_FR			0x04000000
#define ST0_CU			0xf0000000
#define ST0_CU0			0x10000000
#define ST0_CU1			0x20000000
#define ST0_CU2			0x40000000
#define ST0_CU3			0x80000000
#define ST0_XX			0x80000000	/* MIPS IV naming */

/*
 * Bitfields and bit numbers in the coprocessor 0 cause register.
 *
 * Refer to your MIPS R4xx0 manual, chapter 5 for explanation.
 */
#define  CAUSEB_EXCCODE		2
#define  CAUSEF_EXCCODE		(_ULCAST_(31)  <<  2)
#define  CAUSEB_IP		8
#define  CAUSEF_IP		(_ULCAST_(255) <<  8)
#define  CAUSEB_IP0		8
#define  CAUSEF_IP0		(_ULCAST_(1)   <<  8)
#define  CAUSEB_IP1		9
#define  CAUSEF_IP1		(_ULCAST_(1)   <<  9)
#define  CAUSEB_IP2		10
#define  CAUSEF_IP2		(_ULCAST_(1)   << 10)
#define  CAUSEB_IP3		11
#define  CAUSEF_IP3		(_ULCAST_(1)   << 11)
#define  CAUSEB_IP4		12
#define  CAUSEF_IP4		(_ULCAST_(1)   << 12)
#define  CAUSEB_IP5		13
#define  CAUSEF_IP5		(_ULCAST_(1)   << 13)
#define  CAUSEB_IP6		14
#define  CAUSEF_IP6		(_ULCAST_(1)   << 14)
#define  CAUSEB_IP7		15
#define  CAUSEF_IP7		(_ULCAST_(1)   << 15)
#define  CAUSEB_IV		23
#define  CAUSEF_IV		(_ULCAST_(1)   << 23)
#define  CAUSEB_CE		28
#define  CAUSEF_CE		(_ULCAST_(3)   << 28)
#define  CAUSEB_BD		31
#define  CAUSEF_BD		(_ULCAST_(1)   << 31)

/*
 * Bits in the coprocessor 0 config register.
 */
/* Generic bits.  */
#define CONF_CM_CACHABLE_NO_WA		0
#define CONF_CM_CACHABLE_WA		1
#define CONF_CM_UNCACHED		2
#define CONF_CM_CACHABLE_NONCOHERENT	3
#define CONF_CM_CACHABLE_CE		4
#define CONF_CM_CACHABLE_COW		5
#define CONF_CM_CACHABLE_CUW		6
#define CONF_CM_CACHABLE_ACCELERATED	7
#define CONF_CM_CMASK			7
#define CONF_BE			(_ULCAST_(1) << 15)

/* Bits common to various processors.  */
#define CONF_CU			(_ULCAST_(1) <<  3)
#define CONF_DB			(_ULCAST_(1) <<  4)
#define CONF_IB			(_ULCAST_(1) <<  5)
#define CONF_DC			(_ULCAST_(7) <<  6)
#define CONF_IC			(_ULCAST_(7) <<  9)
#define CONF_EB			(_ULCAST_(1) << 13)
#define CONF_EM			(_ULCAST_(1) << 14)
#define CONF_SM			(_ULCAST_(1) << 16)
#define CONF_SC			(_ULCAST_(1) << 17)
#define CONF_EW			(_ULCAST_(3) << 18)
#define CONF_EP			(_ULCAST_(15)<< 24)
#define CONF_EC			(_ULCAST_(7) << 28)
#define CONF_CM			(_ULCAST_(1) << 31)

/* Bits specific to the R4xx0.  */
#define R4K_CONF_SW		(_ULCAST_(1) << 20)
#define R4K_CONF_SS		(_ULCAST_(1) << 21)
#define R4K_CONF_SB		(_ULCAST_(3) << 22)

/* Bits specific to the R5000.  */
#define R5K_CONF_SE		(_ULCAST_(1) << 12)
#define R5K_CONF_SS		(_ULCAST_(3) << 20)

/* Bits specific to the RM7000.  */
#define RM7K_CONF_SE		(_ULCAST_(1) <<  3)
#define RM7K_CONF_TE		(_ULCAST_(1) << 12)
#define RM7K_CONF_CLK		(_ULCAST_(1) << 16)
#define RM7K_CONF_TC		(_ULCAST_(1) << 17)
#define RM7K_CONF_SI		(_ULCAST_(3) << 20)
#define RM7K_CONF_SC		(_ULCAST_(1) << 31)

/* Bits specific to the R10000.  */
#define R10K_CONF_DN		(_ULCAST_(3) <<  3)
#define R10K_CONF_CT		(_ULCAST_(1) <<  5)
#define R10K_CONF_PE		(_ULCAST_(1) <<  6)
#define R10K_CONF_PM		(_ULCAST_(3) <<  7)
#define R10K_CONF_EC		(_ULCAST_(15)<<  9)
#define R10K_CONF_SB		(_ULCAST_(1) << 13)
#define R10K_CONF_SK		(_ULCAST_(1) << 14)
#define R10K_CONF_SS		(_ULCAST_(7) << 16)
#define R10K_CONF_SC		(_ULCAST_(7) << 19)
#define R10K_CONF_DC		(_ULCAST_(7) << 26)
#define R10K_CONF_IC		(_ULCAST_(7) << 29)

/* Bits specific to the VR41xx.  */
#define VR41_CONF_CS		(_ULCAST_(1) << 12)
#define VR41_CONF_M16		(_ULCAST_(1) << 20)
#define VR41_CONF_AD		(_ULCAST_(1) << 23)

/* Bits specific to the R30xx.  */
#define R30XX_CONF_FDM		(_ULCAST_(1) << 19)
#define R30XX_CONF_REV		(_ULCAST_(1) << 22)
#define R30XX_CONF_AC		(_ULCAST_(1) << 23)
#define R30XX_CONF_RF		(_ULCAST_(1) << 24)
#define R30XX_CONF_HALT		(_ULCAST_(1) << 25)
#define R30XX_CONF_FPINT	(_ULCAST_(7) << 26)
#define R30XX_CONF_DBR		(_ULCAST_(1) << 29)
#define R30XX_CONF_SB		(_ULCAST_(1) << 30)
#define R30XX_CONF_LOCK		(_ULCAST_(1) << 31)

/* Bits specific to the TX49.  */
#define TX49_CONF_DC		(_ULCAST_(1) << 16)
#define TX49_CONF_IC		(_ULCAST_(1) << 17)  /* conflict with CONF_SC */
#define TX49_CONF_HALT		(_ULCAST_(1) << 18)
#define TX49_CONF_CWFON		(_ULCAST_(1) << 27)

/* Bits specific to the MIPS32/64 PRA.  */
#define MIPS_CONF_MT		(_ULCAST_(7) <<  7)
#define MIPS_CONF_AR		(_ULCAST_(7) << 10)
#define MIPS_CONF_AT		(_ULCAST_(3) << 13)
#define MIPS_CONF_M		(_ULCAST_(1) << 31)

/*
 * Bits in the MIPS32/64 PRA coprocessor 0 config registers 1 and above.
 */
#define MIPS_CONF1_FP		(_ULCAST_(1) <<  0)
#define MIPS_CONF1_EP		(_ULCAST_(1) <<  1)
#define MIPS_CONF1_CA		(_ULCAST_(1) <<  2)
#define MIPS_CONF1_WR		(_ULCAST_(1) <<  3)
#define MIPS_CONF1_PC		(_ULCAST_(1) <<  4)
#define MIPS_CONF1_MD		(_ULCAST_(1) <<  5)
#define MIPS_CONF1_C2		(_ULCAST_(1) <<  6)
#define MIPS_CONF1_DA		(_ULCAST_(7) <<  7)
#define MIPS_CONF1_DL		(_ULCAST_(7) << 10)
#define MIPS_CONF1_DS		(_ULCAST_(7) << 13)
#define MIPS_CONF1_IA		(_ULCAST_(7) << 16)
#define MIPS_CONF1_IL		(_ULCAST_(7) << 19)
#define MIPS_CONF1_IS		(_ULCAST_(7) << 22)
#define MIPS_CONF1_TLBS		(_ULCAST_(63)<< 25)

#define MIPS_CONF2_SA		(_ULCAST_(15)<<  0)
#define MIPS_CONF2_SL		(_ULCAST_(15)<<  4)
#define MIPS_CONF2_SS		(_ULCAST_(15)<<  8)
#define MIPS_CONF2_SU		(_ULCAST_(15)<< 12)
#define MIPS_CONF2_TA		(_ULCAST_(15)<< 16)
#define MIPS_CONF2_TL		(_ULCAST_(15)<< 20)
#define MIPS_CONF2_TS		(_ULCAST_(15)<< 24)
#define MIPS_CONF2_TU		(_ULCAST_(7) << 28)

#define MIPS_CONF3_TL		(_ULCAST_(1) <<  0)
#define MIPS_CONF3_SM		(_ULCAST_(1) <<  1)
#define MIPS_CONF3_MT		(_ULCAST_(1) <<  2)
#define MIPS_CONF3_SP		(_ULCAST_(1) <<  4)
#define MIPS_CONF3_VINT		(_ULCAST_(1) <<  5)
#define MIPS_CONF3_VEIC		(_ULCAST_(1) <<  6)
#define MIPS_CONF3_LPA		(_ULCAST_(1) <<  7)
#define MIPS_CONF3_DSP		(_ULCAST_(1) << 10)

/*
 * Bits in the MIPS32/64 coprocessor 1 (FPU) revision register.
 */
#define MIPS_FPIR_S		(_ULCAST_(1) << 16)
#define MIPS_FPIR_D		(_ULCAST_(1) << 17)
#define MIPS_FPIR_PS		(_ULCAST_(1) << 18)
#define MIPS_FPIR_3D		(_ULCAST_(1) << 19)
#define MIPS_FPIR_W		(_ULCAST_(1) << 20)
#define MIPS_FPIR_L		(_ULCAST_(1) << 21)
#define MIPS_FPIR_F64		(_ULCAST_(1) << 22)

/*
 * R10000 performance counter definitions.
 *
 * FIXME: The R10000 performance counter opens a nice way to implement CPU
 *        time accounting with a precission of one cycle.  I don't have
 *        R10000 silicon but just a manual, so ...
 */

/*
 * Events counted by counter #0
 */
#define CE0_CYCLES			0
#define CE0_INSN_ISSUED			1
#define CE0_LPSC_ISSUED			2
#define CE0_S_ISSUED			3
#define CE0_SC_ISSUED			4
#define CE0_SC_FAILED			5
#define CE0_BRANCH_DECODED		6
#define CE0_QW_WB_SECONDARY		7
#define CE0_CORRECTED_ECC_ERRORS	8
#define CE0_ICACHE_MISSES		9
#define CE0_SCACHE_I_MISSES		10
#define CE0_SCACHE_I_WAY_MISSPREDICTED	11
#define CE0_EXT_INTERVENTIONS_REQ	12
#define CE0_EXT_INVALIDATE_REQ		13
#define CE0_VIRTUAL_COHERENCY_COND	14
#define CE0_INSN_GRADUATED		15

/*
 * Events counted by counter #1
 */
#define CE1_CYCLES			0
#define CE1_INSN_GRADUATED		1
#define CE1_LPSC_GRADUATED		2
#define CE1_S_GRADUATED			3
#define CE1_SC_GRADUATED		4
#define CE1_FP_INSN_GRADUATED		5
#define CE1_QW_WB_PRIMARY		6
#define CE1_TLB_REFILL			7
#define CE1_BRANCH_MISSPREDICTED	8
#define CE1_DCACHE_MISS			9
#define CE1_SCACHE_D_MISSES		10
#define CE1_SCACHE_D_WAY_MISSPREDICTED	11
#define CE1_EXT_INTERVENTION_HITS	12
#define CE1_EXT_INVALIDATE_REQ		13
#define CE1_SP_HINT_TO_CEXCL_SC_BLOCKS	14
#define CE1_SP_HINT_TO_SHARED_SC_BLOCKS	15

/*
 * These flags define in which privilege mode the counters count events
 */
#define CEB_USER	8	/* Count events in user mode, EXL = ERL = 0 */
#define CEB_SUPERVISOR	4	/* Count events in supvervisor mode EXL = ERL = 0 */
#define CEB_KERNEL	2	/* Count events in kernel mode EXL = ERL = 0 */
#define CEB_EXL		1	/* Count events with EXL = 1, ERL = 0 */

#ifndef __ASSEMBLY__

/*
 * Functions to access the R10000 performance counters.  These are basically
 * mfc0 and mtc0 instructions from and to coprocessor register with a 5-bit
 * performance counter number encoded into bits 1 ... 5 of the instruction.
 * Only performance counters 0 to 1 actually exist, so for a non-R10000 aware
 * disassembler these will look like an access to sel 0 or 1.
 */
#define read_r10k_perf_cntr(counter)				\
({								\
	unsigned int __res;					\
	__asm__ __volatile__(					\
	"mfpc\t%0, %1"						\
        : "=r" (__res)						\
	: "i" (counter));					\
								\
        __res;							\
})

#define write_r10k_perf_cntr(counter,val)                       \
do {								\
	__asm__ __volatile__(					\
	"mtpc\t%0, %1"						\
	:							\
	: "r" (val), "i" (counter));				\
} while (0)

#define read_r10k_perf_event(counter)				\
({								\
	unsigned int __res;					\
	__asm__ __volatile__(					\
	"mfps\t%0, %1"						\
        : "=r" (__res)						\
	: "i" (counter));					\
								\
        __res;							\
})

#define write_r10k_perf_cntl(counter,val)                       \
do {								\
	__asm__ __volatile__(					\
	"mtps\t%0, %1"						\
	:							\
	: "r" (val), "i" (counter));				\
} while (0)


/*
 * Macros to access the system control coprocessor
 */

#define __read_32bit_c0_register(source, sel)				\
({ int __res;								\
	if (sel == 0)							\
		__asm__ __volatile__(					\
			"mfc0\t%0, " #source "\n\t"			\
			: "=r" (__res));				\
	else								\
		__asm__ __volatile__(					\
			".set\tmips32\n\t"				\
			"mfc0\t%0, " #source ", " #sel "\n\t"		\
			".set\tmips0\n\t"				\
			: "=r" (__res));				\
	__res;								\
})

#define __read_64bit_c0_register(source, sel)				\
({ unsigned long long __res;						\
	if (sizeof(unsigned long) == 4)					\
		__res = __read_64bit_c0_split(source, sel);		\
	else if (sel == 0)						\
		__asm__ __volatile__(					\
			".set\tmips3\n\t"				\
			"dmfc0\t%0, " #source "\n\t"			\
			".set\tmips0"					\
			: "=r" (__res));				\
	else								\
		__asm__ __volatile__(					\
			".set\tmips64\n\t"				\
			"dmfc0\t%0, " #source ", " #sel "\n\t"		\
			".set\tmips0"					\
			: "=r" (__res));				\
	__res;								\
})

#define __write_32bit_c0_register(register, sel, value)			\
do {									\
	if (sel == 0)							\
		__asm__ __volatile__(					\
			"mtc0\t%z0, " #register "\n\t"			\
			: : "Jr" ((unsigned int)(value)));		\
	else								\
		__asm__ __volatile__(					\
			".set\tmips32\n\t"				\
			"mtc0\t%z0, " #register ", " #sel "\n\t"	\
			".set\tmips0"					\
			: : "Jr" ((unsigned int)(value)));		\
} while (0)

#define __write_64bit_c0_register(register, sel, value)			\
do {									\
	if (sizeof(unsigned long) == 4)					\
		__write_64bit_c0_split(register, sel, value);		\
	else if (sel == 0)						\
		__asm__ __volatile__(					\
			".set\tmips3\n\t"				\
			"dmtc0\t%z0, " #register "\n\t"			\
			".set\tmips0"					\
			: : "Jr" (value));				\
	else								\
		__asm__ __volatile__(					\
			".set\tmips64\n\t"				\
			"dmtc0\t%z0, " #register ", " #sel "\n\t"	\
			".set\tmips0"					\
			: : "Jr" (value));				\
} while (0)

#define __read_ulong_c0_register(reg, sel)				\
	((sizeof(unsigned long) == 4) ?					\
	(unsigned long) __read_32bit_c0_register(reg, sel) :		\
	(unsigned long) __read_64bit_c0_register(reg, sel))

#define __write_ulong_c0_register(reg, sel, val)			\
do {									\
	if (sizeof(unsigned long) == 4)					\
		__write_32bit_c0_register(reg, sel, val);		\
	else								\
		__write_64bit_c0_register(reg, sel, val);		\
} while (0)

/*
 * On RM7000/RM9000 these are uses to access cop0 set 1 registers
 */
#define __read_32bit_c0_ctrl_register(source)				\
({ int __res;								\
	__asm__ __volatile__(						\
		"cfc0\t%0, " #source "\n\t"				\
		: "=r" (__res));					\
	__res;								\
})

#define __write_32bit_c0_ctrl_register(register, value)			\
do {									\
	__asm__ __volatile__(						\
		"ctc0\t%z0, " #register "\n\t"				\
		: : "Jr" ((unsigned int)(value)));			\
} while (0)

/*
 * These versions are only needed for systems with more than 38 bits of
 * physical address space running the 32-bit kernel.  That's none atm :-)
 */
#define __read_64bit_c0_split(source, sel)				\
({									\
	unsigned long long val;						\
	unsigned long flags;						\
									\
	local_irq_save(flags);						\
	if (sel == 0)							\
		__asm__ __volatile__(					\
			".set\tmips64\n\t"				\
			"dmfc0\t%M0, " #source "\n\t"			\
			"dsll\t%L0, %M0, 32\n\t"			\
			"dsrl\t%M0, %M0, 32\n\t"			\
			"dsrl\t%L0, %L0, 32\n\t"			\
			".set\tmips0"					\
			: "=r" (val));					\
	else								\
		__asm__ __volatile__(					\
			".set\tmips64\n\t"				\
			"dmfc0\t%M0, " #source ", " #sel "\n\t"		\
			"dsll\t%L0, %M0, 32\n\t"			\
			"dsrl\t%M0, %M0, 32\n\t"			\
			"dsrl\t%L0, %L0, 32\n\t"			\
			".set\tmips0"					\
			: "=r" (val));					\
	local_irq_restore(flags);					\
									\
	val;								\
})

#define __write_64bit_c0_split(source, sel, val)			\
do {									\
	unsigned long flags;						\
									\
	local_irq_save(flags);						\
	if (sel == 0)							\
		__asm__ __volatile__(					\
			".set\tmips64\n\t"				\
			"dsll\t%L0, %L0, 32\n\t"			\
			"dsrl\t%L0, %L0, 32\n\t"			\
			"dsll\t%M0, %M0, 32\n\t"			\
			"or\t%L0, %L0, %M0\n\t"				\
			"dmtc0\t%L0, " #source "\n\t"			\
			".set\tmips0"					\
			: : "r" (val));					\
	else								\
		__asm__ __volatile__(					\
			".set\tmips64\n\t"				\
			"dsll\t%L0, %L0, 32\n\t"			\
			"dsrl\t%L0, %L0, 32\n\t"			\
			"dsll\t%M0, %M0, 32\n\t"			\
			"or\t%L0, %L0, %M0\n\t"				\
			"dmtc0\t%L0, " #source ", " #sel "\n\t"		\
			".set\tmips0"					\
			: : "r" (val));					\
	local_irq_restore(flags);					\
} while (0)

#define read_c0_index()		__read_32bit_c0_register($0, 0)
#define write_c0_index(val)	__write_32bit_c0_register($0, 0, val)

#define read_c0_entrylo0()	__read_ulong_c0_register($2, 0)
#define write_c0_entrylo0(val)	__write_ulong_c0_register($2, 0, val)

#define read_c0_entrylo1()	__read_ulong_c0_register($3, 0)
#define write_c0_entrylo1(val)	__write_ulong_c0_register($3, 0, val)

#define read_c0_conf()		__read_32bit_c0_register($3, 0)
#define write_c0_conf(val)	__write_32bit_c0_register($3, 0, val)

#define read_c0_context()	__read_ulong_c0_register($4, 0)
#define write_c0_context(val)	__write_ulong_c0_register($4, 0, val)

#define read_c0_pagemask()	__read_32bit_c0_register($5, 0)
#define write_c0_pagemask(val)	__write_32bit_c0_register($5, 0, val)

#define read_c0_wired()		__read_32bit_c0_register($6, 0)
#define write_c0_wired(val)	__write_32bit_c0_register($6, 0, val)

#define read_c0_info()		__read_32bit_c0_register($7, 0)

#define read_c0_cache()		__read_32bit_c0_register($7, 0)	/* TX39xx */
#define write_c0_cache(val)	__write_32bit_c0_register($7, 0, val)

#define read_c0_count()		__read_32bit_c0_register($9, 0)
#define write_c0_count(val)	__write_32bit_c0_register($9, 0, val)

#define read_c0_count2()	__read_32bit_c0_register($9, 6) /* pnx8550 */
#define write_c0_count2(val)	__write_32bit_c0_register($9, 6, val)

#define read_c0_count3()	__read_32bit_c0_register($9, 7) /* pnx8550 */
#define write_c0_count3(val)	__write_32bit_c0_register($9, 7, val)

#define read_c0_entryhi()	__read_ulong_c0_register($10, 0)
#define write_c0_entryhi(val)	__write_ulong_c0_register($10, 0, val)

#define read_c0_compare()	__read_32bit_c0_register($11, 0)
#define write_c0_compare(val)	__write_32bit_c0_register($11, 0, val)

#define read_c0_compare2()	__read_32bit_c0_register($11, 6) /* pnx8550 */
#define write_c0_compare2(val)	__write_32bit_c0_register($11, 6, val)

#define read_c0_compare3()	__read_32bit_c0_register($11, 7) /* pnx8550 */
#define write_c0_compare3(val)	__write_32bit_c0_register($11, 7, val)

#define read_c0_status()	__read_32bit_c0_register($12, 0)
#define write_c0_status(val)	__write_32bit_c0_register($12, 0, val)

#define read_c0_cause()		__read_32bit_c0_register($13, 0)
#define write_c0_cause(val)	__write_32bit_c0_register($13, 0, val)

#define read_c0_epc()		__read_ulong_c0_register($14, 0)
#define write_c0_epc(val)	__write_ulong_c0_register($14, 0, val)

#define read_c0_prid()		__read_32bit_c0_register($15, 0)

#define read_c0_config()	__read_32bit_c0_register($16, 0)
#define read_c0_config1()	__read_32bit_c0_register($16, 1)
#define read_c0_config2()	__read_32bit_c0_register($16, 2)
#define read_c0_config3()	__read_32bit_c0_register($16, 3)
#define read_c0_config4()	__read_32bit_c0_register($16, 4)
#define read_c0_config5()	__read_32bit_c0_register($16, 5)
#define read_c0_config6()	__read_32bit_c0_register($16, 6)
#define read_c0_config7()	__read_32bit_c0_register($16, 7)
#define write_c0_config(val)	__write_32bit_c0_register($16, 0, val)
#define write_c0_config1(val)	__write_32bit_c0_register($16, 1, val)
#define write_c0_config2(val)	__write_32bit_c0_register($16, 2, val)
#define write_c0_config3(val)	__write_32bit_c0_register($16, 3, val)
#define write_c0_config4(val)	__write_32bit_c0_register($16, 4, val)
#define write_c0_config5(val)	__write_32bit_c0_register($16, 5, val)
#define write_c0_config6(val)	__write_32bit_c0_register($16, 6, val)
#define write_c0_config7(val)	__write_32bit_c0_register($16, 7, val)

/*
 * The WatchLo register.  There may be upto 8 of them.
 */
#define read_c0_watchlo0()	__read_ulong_c0_register($18, 0)
#define read_c0_watchlo1()	__read_ulong_c0_register($18, 1)
#define read_c0_watchlo2()	__read_ulong_c0_register($18, 2)
#define read_c0_watchlo3()	__read_ulong_c0_register($18, 3)
#define read_c0_watchlo4()	__read_ulong_c0_register($18, 4)
#define read_c0_watchlo5()	__read_ulong_c0_register($18, 5)
#define read_c0_watchlo6()	__read_ulong_c0_register($18, 6)
#define read_c0_watchlo7()	__read_ulong_c0_register($18, 7)
#define write_c0_watchlo0(val)	__write_ulong_c0_register($18, 0, val)
#define write_c0_watchlo1(val)	__write_ulong_c0_register($18, 1, val)
#define write_c0_watchlo2(val)	__write_ulong_c0_register($18, 2, val)
#define write_c0_watchlo3(val)	__write_ulong_c0_register($18, 3, val)
#define write_c0_watchlo4(val)	__write_ulong_c0_register($18, 4, val)
#define write_c0_watchlo5(val)	__write_ulong_c0_register($18, 5, val)
#define write_c0_watchlo6(val)	__write_ulong_c0_register($18, 6, val)
#define write_c0_watchlo7(val)	__write_ulong_c0_register($18, 7, val)

/*
 * The WatchHi register.  There may be upto 8 of them.
 */
#define read_c0_watchhi0()	__read_32bit_c0_register($19, 0)
#define read_c0_watchhi1()	__read_32bit_c0_register($19, 1)
#define read_c0_watchhi2()	__read_32bit_c0_register($19, 2)
#define read_c0_watchhi3()	__read_32bit_c0_register($19, 3)
#define read_c0_watchhi4()	__read_32bit_c0_register($19, 4)
#define read_c0_watchhi5()	__read_32bit_c0_register($19, 5)
#define read_c0_watchhi6()	__read_32bit_c0_register($19, 6)
#define read_c0_watchhi7()	__read_32bit_c0_register($19, 7)

#define write_c0_watchhi0(val)	__write_32bit_c0_register($19, 0, val)
#define write_c0_watchhi1(val)	__write_32bit_c0_register($19, 1, val)
#define write_c0_watchhi2(val)	__write_32bit_c0_register($19, 2, val)
#define write_c0_watchhi3(val)	__write_32bit_c0_register($19, 3, val)
#define write_c0_watchhi4(val)	__write_32bit_c0_register($19, 4, val)
#define write_c0_watchhi5(val)	__write_32bit_c0_register($19, 5, val)
#define write_c0_watchhi6(val)	__write_32bit_c0_register($19, 6, val)
#define write_c0_watchhi7(val)	__write_32bit_c0_register($19, 7, val)

#define read_c0_xcontext()	__read_ulong_c0_register($20, 0)
#define write_c0_xcontext(val)	__write_ulong_c0_register($20, 0, val)

#define read_c0_intcontrol()	__read_32bit_c0_ctrl_register($20)
#define write_c0_intcontrol(val) __write_32bit_c0_ctrl_register($20, val)

#define read_c0_framemask()	__read_32bit_c0_register($21, 0)
#define write_c0_framemask(val)	__write_32bit_c0_register($21, 0, val)

/* RM9000 PerfControl performance counter control register */
#define read_c0_perfcontrol()	__read_32bit_c0_register($22, 0)
#define write_c0_perfcontrol(val) __write_32bit_c0_register($22, 0, val)

#define read_c0_diag()		__read_32bit_c0_register($22, 0)
#define write_c0_diag(val)	__write_32bit_c0_register($22, 0, val)

#define read_c0_diag1()		__read_32bit_c0_register($22, 1)
#define write_c0_diag1(val)	__write_32bit_c0_register($22, 1, val)

#define read_c0_diag2()		__read_32bit_c0_register($22, 2)
#define write_c0_diag2(val)	__write_32bit_c0_register($22, 2, val)

#define read_c0_diag3()		__read_32bit_c0_register($22, 3)
#define write_c0_diag3(val)	__write_32bit_c0_register($22, 3, val)

#define read_c0_diag4()		__read_32bit_c0_register($22, 4)
#define write_c0_diag4(val)	__write_32bit_c0_register($22, 4, val)

#define read_c0_diag5()		__read_32bit_c0_register($22, 5)
#define write_c0_diag5(val)	__write_32bit_c0_register($22, 5, val)

#define read_c0_debug()		__read_32bit_c0_register($23, 0)
#define write_c0_debug(val)	__write_32bit_c0_register($23, 0, val)

#define read_c0_depc()		__read_ulong_c0_register($24, 0)
#define write_c0_depc(val)	__write_ulong_c0_register($24, 0, val)

/*
 * MIPS32 / MIPS64 performance counters
 */
#define read_c0_perfctrl0()	__read_32bit_c0_register($25, 0)
#define write_c0_perfctrl0(val)	__write_32bit_c0_register($25, 0, val)
#define read_c0_perfcntr0()	__read_32bit_c0_register($25, 1)
#define write_c0_perfcntr0(val)	__write_32bit_c0_register($25, 1, val)
#define read_c0_perfctrl1()	__read_32bit_c0_register($25, 2)
#define write_c0_perfctrl1(val)	__write_32bit_c0_register($25, 2, val)
#define read_c0_perfcntr1()	__read_32bit_c0_register($25, 3)
#define write_c0_perfcntr1(val)	__write_32bit_c0_register($25, 3, val)
#define read_c0_perfctrl2()	__read_32bit_c0_register($25, 4)
#define write_c0_perfctrl2(val)	__write_32bit_c0_register($25, 4, val)
#define read_c0_perfcntr2()	__read_32bit_c0_register($25, 5)
#define write_c0_perfcntr2(val)	__write_32bit_c0_register($25, 5, val)
#define read_c0_perfctrl3()	__read_32bit_c0_register($25, 6)
#define write_c0_perfctrl3(val)	__write_32bit_c0_register($25, 6, val)
#define read_c0_perfcntr3()	__read_32bit_c0_register($25, 7)
#define write_c0_perfcntr3(val)	__write_32bit_c0_register($25, 7, val)

/* RM9000 PerfCount performance counter register */
#define read_c0_perfcount()	__read_64bit_c0_register($25, 0)
#define write_c0_perfcount(val)	__write_64bit_c0_register($25, 0, val)

#define read_c0_ecc()		__read_32bit_c0_register($26, 0)
#define write_c0_ecc(val)	__write_32bit_c0_register($26, 0, val)

#define read_c0_derraddr0()	__read_ulong_c0_register($26, 1)
#define write_c0_derraddr0(val)	__write_ulong_c0_register($26, 1, val)

#define read_c0_cacheerr()	__read_32bit_c0_register($27, 0)

#define read_c0_derraddr1()	__read_ulong_c0_register($27, 1)
#define write_c0_derraddr1(val)	__write_ulong_c0_register($27, 1, val)

#define read_c0_taglo()		__read_32bit_c0_register($28, 0)
#define write_c0_taglo(val)	__write_32bit_c0_register($28, 0, val)

#define read_c0_taghi()		__read_32bit_c0_register($29, 0)
#define write_c0_taghi(val)	__write_32bit_c0_register($29, 0, val)

#define read_c0_errorepc()	__read_ulong_c0_register($30, 0)
#define write_c0_errorepc(val)	__write_ulong_c0_register($30, 0, val)

/* MIPSR2 */
#define read_c0_hwrena()	__read_32bit_c0_register($7,0)
#define write_c0_hwrena(val)	__write_32bit_c0_register($7, 0, val)

#define read_c0_intctl()	__read_32bit_c0_register($12, 1)
#define write_c0_intctl(val)	__write_32bit_c0_register($12, 1, val)

#define read_c0_srsctl()	__read_32bit_c0_register($12, 2)
#define write_c0_srsctl(val)	__write_32bit_c0_register($12, 2, val)

#define read_c0_srsmap()	__read_32bit_c0_register($12, 3)
#define write_c0_srsmap(val)	__write_32bit_c0_register($12, 3, val)

#define read_c0_ebase()		__read_32bit_c0_register($15,1)
#define write_c0_ebase(val)	__write_32bit_c0_register($15, 1, val)

/*
 * Macros to access the floating point coprocessor control registers
 */
#define read_32bit_cp1_register(source)                         \
({ int __res;                                                   \
	__asm__ __volatile__(                                   \
	".set\tpush\n\t"					\
	".set\treorder\n\t"					\
        "cfc1\t%0,"STR(source)"\n\t"                            \
	".set\tpop"						\
        : "=r" (__res));                                        \
        __res;})

#define rddsp(mask)							\
({									\
	unsigned int __res;						\
									\
	__asm__ __volatile__(						\
	"	.set	push				\n"		\
	"	.set	noat				\n"		\
	"	# rddsp $1, %x1				\n"		\
	"	.word	0x7c000cb8 | (%x1 << 16)	\n"		\
	"	move	%0, $1				\n"		\
	"	.set	pop				\n"		\
	: "=r" (__res)							\
	: "i" (mask));							\
	__res;								\
})

#define wrdsp(val, mask)						\
do {									\
	__asm__ __volatile__(						\
	"	.set	push					\n"	\
	"	.set	noat					\n"	\
	"	move	$1, %0					\n"	\
	"	# wrdsp $1, %x1					\n"	\
	"	.word	0x7c2004f8 | (%x1 << 11)		\n"	\
	"	.set	pop					\n"	\
        :								\
	: "r" (val), "i" (mask));					\
} while (0)

#if 0	/* Need DSP ASE capable assembler ... */
#define mflo0() ({ long mflo0; __asm__("mflo %0, $ac0" : "=r" (mflo0)); mflo0;})
#define mflo1() ({ long mflo1; __asm__("mflo %0, $ac1" : "=r" (mflo1)); mflo1;})
#define mflo2() ({ long mflo2; __asm__("mflo %0, $ac2" : "=r" (mflo2)); mflo2;})
#define mflo3() ({ long mflo3; __asm__("mflo %0, $ac3" : "=r" (mflo3)); mflo3;})

#define mfhi0() ({ long mfhi0; __asm__("mfhi %0, $ac0" : "=r" (mfhi0)); mfhi0;})
#define mfhi1() ({ long mfhi1; __asm__("mfhi %0, $ac1" : "=r" (mfhi1)); mfhi1;})
#define mfhi2() ({ long mfhi2; __asm__("mfhi %0, $ac2" : "=r" (mfhi2)); mfhi2;})
#define mfhi3() ({ long mfhi3; __asm__("mfhi %0, $ac3" : "=r" (mfhi3)); mfhi3;})

#define mtlo0(x) __asm__("mtlo %0, $ac0" ::"r" (x))
#define mtlo1(x) __asm__("mtlo %0, $ac1" ::"r" (x))
#define mtlo2(x) __asm__("mtlo %0, $ac2" ::"r" (x))
#define mtlo3(x) __asm__("mtlo %0, $ac3" ::"r" (x))

#define mthi0(x) __asm__("mthi %0, $ac0" ::"r" (x))
#define mthi1(x) __asm__("mthi %0, $ac1" ::"r" (x))
#define mthi2(x) __asm__("mthi %0, $ac2" ::"r" (x))
#define mthi3(x) __asm__("mthi %0, $ac3" ::"r" (x))

#else

#define mfhi0()								\
({									\
	unsigned long __treg;						\
									\
	__asm__ __volatile__(						\
	"	.set	push			\n"			\
	"	.set	noat			\n"			\
	"	# mfhi	%0, $ac0		\n"			\
	"	.word	0x00000810		\n"			\
	"	move	%0, $1			\n"			\
	"	.set	pop			\n"			\
	: "=r" (__treg));						\
	__treg;								\
})

#define mfhi1()								\
({									\
	unsigned long __treg;						\
									\
	__asm__ __volatile__(						\
	"	.set	push			\n"			\
	"	.set	noat			\n"			\
	"	# mfhi	%0, $ac1		\n"			\
	"	.word	0x00200810		\n"			\
	"	move	%0, $1			\n"			\
	"	.set	pop			\n"			\
	: "=r" (__treg));						\
	__treg;								\
})

#define mfhi2()								\
({									\
	unsigned long __treg;						\
									\
	__asm__ __volatile__(						\
	"	.set	push			\n"			\
	"	.set	noat			\n"			\
	"	# mfhi	%0, $ac2		\n"			\
	"	.word	0x00400810		\n"			\
	"	move	%0, $1			\n"			\
	"	.set	pop			\n"			\
	: "=r" (__treg));						\
	__treg;								\
})

#define mfhi3()								\
({									\
	unsigned long __treg;						\
									\
	__asm__ __volatile__(						\
	"	.set	push			\n"			\
	"	.set	noat			\n"			\
	"	# mfhi	%0, $ac3		\n"			\
	"	.word	0x00600810		\n"			\
	"	move	%0, $1			\n"			\
	"	.set	pop			\n"			\
	: "=r" (__treg));						\
	__treg;								\
})

#define mflo0()								\
({									\
	unsigned long __treg;						\
									\
	__asm__ __volatile__(						\
	"	.set	push			\n"			\
	"	.set	noat			\n"			\
	"	# mflo	%0, $ac0		\n"			\
	"	.word	0x00000812		\n"			\
	"	move	%0, $1			\n"			\
	"	.set	pop			\n"			\
	: "=r" (__treg));						\
	__treg;								\
})

#define mflo1()								\
({									\
	unsigned long __treg;						\
									\
	__asm__ __volatile__(						\
	"	.set	push			\n"			\
	"	.set	noat			\n"			\
	"	# mflo	%0, $ac1		\n"			\
	"	.word	0x00200812		\n"			\
	"	move	%0, $1			\n"			\
	"	.set	pop			\n"			\
	: "=r" (__treg));						\
	__treg;								\
})

#define mflo2()								\
({									\
	unsigned long __treg;						\
									\
	__asm__ __volatile__(						\
	"	.set	push			\n"			\
	"	.set	noat			\n"			\
	"	# mflo	%0, $ac2		\n"			\
	"	.word	0x00400812		\n"			\
	"	move	%0, $1			\n"			\
	"	.set	pop			\n"			\
	: "=r" (__treg));						\
	__treg;								\
})

#define mflo3()								\
({									\
	unsigned long __treg;						\
									\
	__asm__ __volatile__(						\
	"	.set	push			\n"			\
	"	.set	noat			\n"			\
	"	# mflo	%0, $ac3		\n"			\
	"	.word	0x00600812		\n"			\
	"	move	%0, $1			\n"			\
	"	.set	pop			\n"			\
	: "=r" (__treg));						\
	__treg;								\
})

#define mthi0(x)							\
do {									\
	__asm__ __volatile__(						\
	"	.set	push					\n"	\
	"	.set	noat					\n"	\
	"	move	$1, %0					\n"	\
	"	# mthi	$1, $ac0				\n"	\
	"	.word	0x00200011				\n"	\
	"	.set	pop					\n"	\
	:								\
	: "r" (x));							\
} while (0)

#define mthi1(x)							\
do {									\
	__asm__ __volatile__(						\
	"	.set	push					\n"	\
	"	.set	noat					\n"	\
	"	move	$1, %0					\n"	\
	"	# mthi	$1, $ac1				\n"	\
	"	.word	0x00200811				\n"	\
	"	.set	pop					\n"	\
	:								\
	: "r" (x));							\
} while (0)

#define mthi2(x)							\
do {									\
	__asm__ __volatile__(						\
	"	.set	push					\n"	\
	"	.set	noat					\n"	\
	"	move	$1, %0					\n"	\
	"	# mthi	$1, $ac2				\n"	\
	"	.word	0x00201011				\n"	\
	"	.set	pop					\n"	\
	:								\
	: "r" (x));							\
} while (0)

#define mthi3(x)							\
do {									\
	__asm__ __volatile__(						\
	"	.set	push					\n"	\
	"	.set	noat					\n"	\
	"	move	$1, %0					\n"	\
	"	# mthi	$1, $ac3				\n"	\
	"	.word	0x00201811				\n"	\
	"	.set	pop					\n"	\
	:								\
	: "r" (x));							\
} while (0)

#define mtlo0(x)							\
do {									\
	__asm__ __volatile__(						\
	"	.set	push					\n"	\
	"	.set	noat					\n"	\
	"	move	$1, %0					\n"	\
	"	# mtlo	$1, $ac0				\n"	\
	"	.word	0x00200013				\n"	\
	"	.set	pop					\n"	\
	:								\
	: "r" (x));							\
} while (0)

#define mtlo1(x)							\
do {									\
	__asm__ __volatile__(						\
	"	.set	push					\n"	\
	"	.set	noat					\n"	\
	"	move	$1, %0					\n"	\
	"	# mtlo	$1, $ac1				\n"	\
	"	.word	0x00200813				\n"	\
	"	.set	pop					\n"	\
	:								\
	: "r" (x));							\
} while (0)

#define mtlo2(x)							\
do {									\
	__asm__ __volatile__(						\
	"	.set	push					\n"	\
	"	.set	noat					\n"	\
	"	move	$1, %0					\n"	\
	"	# mtlo	$1, $ac2				\n"	\
	"	.word	0x00201013				\n"	\
	"	.set	pop					\n"	\
	:								\
	: "r" (x));							\
} while (0)

#define mtlo3(x)							\
do {									\
	__asm__ __volatile__(						\
	"	.set	push					\n"	\
	"	.set	noat					\n"	\
	"	move	$1, %0					\n"	\
	"	# mtlo	$1, $ac3				\n"	\
	"	.word	0x00201813				\n"	\
	"	.set	pop					\n"	\
	:								\
	: "r" (x));							\
} while (0)

#endif

/*
 * TLB operations.
 *
 * It is responsibility of the caller to take care of any TLB hazards.
 */
static inline void tlb_probe(void)
{
	__asm__ __volatile__(
		".set noreorder\n\t"
		"tlbp\n\t"
		".set reorder");
}

static inline void tlb_read(void)
{
	__asm__ __volatile__(
		".set noreorder\n\t"
		"tlbr\n\t"
		".set reorder");
}

static inline void tlb_write_indexed(void)
{
	__asm__ __volatile__(
		".set noreorder\n\t"
		"tlbwi\n\t"
		".set reorder");
}

static inline void tlb_write_random(void)
{
	__asm__ __volatile__(
		".set noreorder\n\t"
		"tlbwr\n\t"
		".set reorder");
}

/*
 * Manipulate bits in a c0 register.
 */
#define __BUILD_SET_C0(name)					\
static inline unsigned int					\
set_c0_##name(unsigned int set)					\
{								\
	unsigned int res;					\
								\
	res = read_c0_##name();					\
	res |= set;						\
	write_c0_##name(res);					\
								\
	return res;						\
}								\
								\
static inline unsigned int					\
clear_c0_##name(unsigned int clear)				\
{								\
	unsigned int res;					\
								\
	res = read_c0_##name();					\
	res &= ~clear;						\
	write_c0_##name(res);					\
								\
	return res;						\
}								\
								\
static inline unsigned int					\
change_c0_##name(unsigned int change, unsigned int new)		\
{								\
	unsigned int res;					\
								\
	res = read_c0_##name();					\
	res &= ~change;						\
	res |= (new & change);					\
	write_c0_##name(res);					\
								\
	return res;						\
}

__BUILD_SET_C0(status)
__BUILD_SET_C0(cause)
__BUILD_SET_C0(config)
__BUILD_SET_C0(intcontrol)
__BUILD_SET_C0(intctl)
__BUILD_SET_C0(srsmap)

#endif /* !__ASSEMBLY__ */

#endif /* _ASM_MIPSREGS_H */
n class="hl com">/* page table handling */ #define LEVEL_STRIDE (9) #define LEVEL_MASK (((u64)1 << LEVEL_STRIDE) - 1) /* * This bitmap is used to advertise the page sizes our hardware support * to the IOMMU core, which will then use this information to split * physically contiguous memory regions it is mapping into page sizes * that we support. * * Traditionally the IOMMU core just handed us the mappings directly, * after making sure the size is an order of a 4KiB page and that the * mapping has natural alignment. * * To retain this behavior, we currently advertise that we support * all page sizes that are an order of 4KiB. * * If at some point we'd like to utilize the IOMMU core's new behavior, * we could change this to advertise the real page sizes we support. */ #define INTEL_IOMMU_PGSIZES (~0xFFFUL) static inline int agaw_to_level(int agaw) { return agaw + 2; } static inline int agaw_to_width(int agaw) { return 30 + agaw * LEVEL_STRIDE; } static inline int width_to_agaw(int width) { return (width - 30) / LEVEL_STRIDE; } static inline unsigned int level_to_offset_bits(int level) { return (level - 1) * LEVEL_STRIDE; } static inline int pfn_level_offset(unsigned long pfn, int level) { return (pfn >> level_to_offset_bits(level)) & LEVEL_MASK; } static inline unsigned long level_mask(int level) { return -1UL << level_to_offset_bits(level); } static inline unsigned long level_size(int level) { return 1UL << level_to_offset_bits(level); } static inline unsigned long align_to_level(unsigned long pfn, int level) { return (pfn + level_size(level) - 1) & level_mask(level); } static inline unsigned long lvl_to_nr_pages(unsigned int lvl) { return 1 << ((lvl - 1) * LEVEL_STRIDE); } /* VT-d pages must always be _smaller_ than MM pages. Otherwise things are never going to work. */ static inline unsigned long dma_to_mm_pfn(unsigned long dma_pfn) { return dma_pfn >> (PAGE_SHIFT - VTD_PAGE_SHIFT); } static inline unsigned long mm_to_dma_pfn(unsigned long mm_pfn) { return mm_pfn << (PAGE_SHIFT - VTD_PAGE_SHIFT); } static inline unsigned long page_to_dma_pfn(struct page *pg) { return mm_to_dma_pfn(page_to_pfn(pg)); } static inline unsigned long virt_to_dma_pfn(void *p) { return page_to_dma_pfn(virt_to_page(p)); } /* global iommu list, set NULL for ignored DMAR units */ static struct intel_iommu **g_iommus; static void __init check_tylersburg_isoch(void); static int rwbf_quirk; /* * set to 1 to panic kernel if can't successfully enable VT-d * (used when kernel is launched w/ TXT) */ static int force_on = 0; /* * 0: Present * 1-11: Reserved * 12-63: Context Ptr (12 - (haw-1)) * 64-127: Reserved */ struct root_entry { u64 val; u64 rsvd1; }; #define ROOT_ENTRY_NR (VTD_PAGE_SIZE/sizeof(struct root_entry)) static inline bool root_present(struct root_entry *root) { return (root->val & 1); } static inline void set_root_present(struct root_entry *root) { root->val |= 1; } static inline void set_root_value(struct root_entry *root, unsigned long value) { root->val |= value & VTD_PAGE_MASK; } static inline struct context_entry * get_context_addr_from_root(struct root_entry *root) { return (struct context_entry *) (root_present(root)?phys_to_virt( root->val & VTD_PAGE_MASK) : NULL); } /* * low 64 bits: * 0: present * 1: fault processing disable * 2-3: translation type * 12-63: address space root * high 64 bits: * 0-2: address width * 3-6: aval * 8-23: domain id */ struct context_entry { u64 lo; u64 hi; }; static inline bool context_present(struct context_entry *context) { return (context->lo & 1); } static inline void context_set_present(struct context_entry *context) { context->lo |= 1; } static inline void context_set_fault_enable(struct context_entry *context) { context->lo &= (((u64)-1) << 2) | 1; } static inline void context_set_translation_type(struct context_entry *context, unsigned long value) { context->lo &= (((u64)-1) << 4) | 3; context->lo |= (value & 3) << 2; } static inline void context_set_address_root(struct context_entry *context, unsigned long value) { context->lo |= value & VTD_PAGE_MASK; } static inline void context_set_address_width(struct context_entry *context, unsigned long value) { context->hi |= value & 7; } static inline void context_set_domain_id(struct context_entry *context, unsigned long value) { context->hi |= (value & ((1 << 16) - 1)) << 8; } static inline void context_clear_entry(struct context_entry *context) { context->lo = 0; context->hi = 0; } /* * 0: readable * 1: writable * 2-6: reserved * 7: super page * 8-10: available * 11: snoop behavior * 12-63: Host physcial address */ struct dma_pte { u64 val; }; static inline void dma_clear_pte(struct dma_pte *pte) { pte->val = 0; } static inline void dma_set_pte_readable(struct dma_pte *pte) { pte->val |= DMA_PTE_READ; } static inline void dma_set_pte_writable(struct dma_pte *pte) { pte->val |= DMA_PTE_WRITE; } static inline void dma_set_pte_snp(struct dma_pte *pte) { pte->val |= DMA_PTE_SNP; } static inline void dma_set_pte_prot(struct dma_pte *pte, unsigned long prot) { pte->val = (pte->val & ~3) | (prot & 3); } static inline u64 dma_pte_addr(struct dma_pte *pte) { #ifdef CONFIG_64BIT return pte->val & VTD_PAGE_MASK; #else /* Must have a full atomic 64-bit read */ return __cmpxchg64(&pte->val, 0ULL, 0ULL) & VTD_PAGE_MASK; #endif } static inline void dma_set_pte_pfn(struct dma_pte *pte, unsigned long pfn) { pte->val |= (uint64_t)pfn << VTD_PAGE_SHIFT; } static inline bool dma_pte_present(struct dma_pte *pte) { return (pte->val & 3) != 0; } static inline bool dma_pte_superpage(struct dma_pte *pte) { return (pte->val & (1 << 7)); } static inline int first_pte_in_page(struct dma_pte *pte) { return !((unsigned long)pte & ~VTD_PAGE_MASK); } /* * This domain is a statically identity mapping domain. * 1. This domain creats a static 1:1 mapping to all usable memory. * 2. It maps to each iommu if successful. * 3. Each iommu mapps to this domain if successful. */ static struct dmar_domain *si_domain; static int hw_pass_through = 1; /* devices under the same p2p bridge are owned in one domain */ #define DOMAIN_FLAG_P2P_MULTIPLE_DEVICES (1 << 0) /* domain represents a virtual machine, more than one devices * across iommus may be owned in one domain, e.g. kvm guest. */ #define DOMAIN_FLAG_VIRTUAL_MACHINE (1 << 1) /* si_domain contains mulitple devices */ #define DOMAIN_FLAG_STATIC_IDENTITY (1 << 2) /* define the limit of IOMMUs supported in each domain */ #ifdef CONFIG_X86 # define IOMMU_UNITS_SUPPORTED MAX_IO_APICS #else # define IOMMU_UNITS_SUPPORTED 64 #endif struct dmar_domain { int id; /* domain id */ int nid; /* node id */ DECLARE_BITMAP(iommu_bmp, IOMMU_UNITS_SUPPORTED); /* bitmap of iommus this domain uses*/ struct list_head devices; /* all devices' list */ struct iova_domain iovad; /* iova's that belong to this domain */ struct dma_pte *pgd; /* virtual address */ int gaw; /* max guest address width */ /* adjusted guest address width, 0 is level 2 30-bit */ int agaw; int flags; /* flags to find out type of domain */ int iommu_coherency;/* indicate coherency of iommu access */ int iommu_snooping; /* indicate snooping control feature*/ int iommu_count; /* reference count of iommu */ int iommu_superpage;/* Level of superpages supported: 0 == 4KiB (no superpages), 1 == 2MiB, 2 == 1GiB, 3 == 512GiB, 4 == 1TiB */ spinlock_t iommu_lock; /* protect iommu set in domain */ u64 max_addr; /* maximum mapped address */ }; /* PCI domain-device relationship */ struct device_domain_info { struct list_head link; /* link to domain siblings */ struct list_head global; /* link to global list */ int segment; /* PCI domain */ u8 bus; /* PCI bus number */ u8 devfn; /* PCI devfn number */ struct pci_dev *dev; /* it's NULL for PCIe-to-PCI bridge */ struct intel_iommu *iommu; /* IOMMU used by this device */ struct dmar_domain *domain; /* pointer to domain */ }; static void flush_unmaps_timeout(unsigned long data); DEFINE_TIMER(unmap_timer, flush_unmaps_timeout, 0, 0); #define HIGH_WATER_MARK 250 struct deferred_flush_tables { int next; struct iova *iova[HIGH_WATER_MARK]; struct dmar_domain *domain[HIGH_WATER_MARK]; }; static struct deferred_flush_tables *deferred_flush; /* bitmap for indexing intel_iommus */ static int g_num_of_iommus; static DEFINE_SPINLOCK(async_umap_flush_lock); static LIST_HEAD(unmaps_to_do); static int timer_on; static long list_size; static void domain_remove_dev_info(struct dmar_domain *domain); #ifdef CONFIG_INTEL_IOMMU_DEFAULT_ON int dmar_disabled = 0; #else int dmar_disabled = 1; #endif /*CONFIG_INTEL_IOMMU_DEFAULT_ON*/ int intel_iommu_enabled = 0; EXPORT_SYMBOL_GPL(intel_iommu_enabled); static int dmar_map_gfx = 1; static int dmar_forcedac; static int intel_iommu_strict; static int intel_iommu_superpage = 1; int intel_iommu_gfx_mapped; EXPORT_SYMBOL_GPL(intel_iommu_gfx_mapped); #define DUMMY_DEVICE_DOMAIN_INFO ((struct device_domain_info *)(-1)) static DEFINE_SPINLOCK(device_domain_lock); static LIST_HEAD(device_domain_list); static struct iommu_ops intel_iommu_ops; static int __init intel_iommu_setup(char *str) { if (!str) return -EINVAL; while (*str) { if (!strncmp(str, "on", 2)) { dmar_disabled = 0; printk(KERN_INFO "Intel-IOMMU: enabled\n"); } else if (!strncmp(str, "off", 3)) { dmar_disabled = 1; printk(KERN_INFO "Intel-IOMMU: disabled\n"); } else if (!strncmp(str, "igfx_off", 8)) { dmar_map_gfx = 0; printk(KERN_INFO "Intel-IOMMU: disable GFX device mapping\n"); } else if (!strncmp(str, "forcedac", 8)) { printk(KERN_INFO "Intel-IOMMU: Forcing DAC for PCI devices\n"); dmar_forcedac = 1; } else if (!strncmp(str, "strict", 6)) { printk(KERN_INFO "Intel-IOMMU: disable batched IOTLB flush\n"); intel_iommu_strict = 1; } else if (!strncmp(str, "sp_off", 6)) { printk(KERN_INFO "Intel-IOMMU: disable supported super page\n"); intel_iommu_superpage = 0; } str += strcspn(str, ","); while (*str == ',') str++; } return 0; } __setup("intel_iommu=", intel_iommu_setup); static struct kmem_cache *iommu_domain_cache; static struct kmem_cache *iommu_devinfo_cache; static struct kmem_cache *iommu_iova_cache; static inline void *alloc_pgtable_page(int node) { struct page *page; void *vaddr = NULL; page = alloc_pages_node(node, GFP_ATOMIC | __GFP_ZERO, 0); if (page) vaddr = page_address(page); return vaddr; } static inline void free_pgtable_page(void *vaddr) { free_page((unsigned long)vaddr); } static inline void *alloc_domain_mem(void) { return kmem_cache_alloc(iommu_domain_cache, GFP_ATOMIC); } static void free_domain_mem(void *vaddr) { kmem_cache_free(iommu_domain_cache, vaddr); } static inline void * alloc_devinfo_mem(void) { return kmem_cache_alloc(iommu_devinfo_cache, GFP_ATOMIC); } static inline void free_devinfo_mem(void *vaddr) { kmem_cache_free(iommu_devinfo_cache, vaddr); } struct iova *alloc_iova_mem(void) { return kmem_cache_alloc(iommu_iova_cache, GFP_ATOMIC); } void free_iova_mem(struct iova *iova) { kmem_cache_free(iommu_iova_cache, iova); } static int __iommu_calculate_agaw(struct intel_iommu *iommu, int max_gaw) { unsigned long sagaw; int agaw = -1; sagaw = cap_sagaw(iommu->cap); for (agaw = width_to_agaw(max_gaw); agaw >= 0; agaw--) { if (test_bit(agaw, &sagaw)) break; } return agaw; } /* * Calculate max SAGAW for each iommu. */ int iommu_calculate_max_sagaw(struct intel_iommu *iommu) { return __iommu_calculate_agaw(iommu, MAX_AGAW_WIDTH); } /* * calculate agaw for each iommu. * "SAGAW" may be different across iommus, use a default agaw, and * get a supported less agaw for iommus that don't support the default agaw. */ int iommu_calculate_agaw(struct intel_iommu *iommu) { return __iommu_calculate_agaw(iommu, DEFAULT_DOMAIN_ADDRESS_WIDTH); } /* This functionin only returns single iommu in a domain */ static struct intel_iommu *domain_get_iommu(struct dmar_domain *domain) { int iommu_id; /* si_domain and vm domain should not get here. */ BUG_ON(domain->flags & DOMAIN_FLAG_VIRTUAL_MACHINE); BUG_ON(domain->flags & DOMAIN_FLAG_STATIC_IDENTITY); iommu_id = find_first_bit(domain->iommu_bmp, g_num_of_iommus); if (iommu_id < 0 || iommu_id >= g_num_of_iommus) return NULL; return g_iommus[iommu_id]; } static void domain_update_iommu_coherency(struct dmar_domain *domain) { int i; i = find_first_bit(domain->iommu_bmp, g_num_of_iommus); domain->iommu_coherency = i < g_num_of_iommus ? 1 : 0; for_each_set_bit(i, domain->iommu_bmp, g_num_of_iommus) { if (!ecap_coherent(g_iommus[i]->ecap)) { domain->iommu_coherency = 0; break; } } } static void domain_update_iommu_snooping(struct dmar_domain *domain) { int i; domain->iommu_snooping = 1; for_each_set_bit(i, domain->iommu_bmp, g_num_of_iommus) { if (!ecap_sc_support(g_iommus[i]->ecap)) { domain->iommu_snooping = 0; break; } } } static void domain_update_iommu_superpage(struct dmar_domain *domain) { struct dmar_drhd_unit *drhd; struct intel_iommu *iommu = NULL; int mask = 0xf; if (!intel_iommu_superpage) { domain->iommu_superpage = 0; return; } /* set iommu_superpage to the smallest common denominator */ for_each_active_iommu(iommu, drhd) { mask &= cap_super_page_val(iommu->cap); if (!mask) { break; } } domain->iommu_superpage = fls(mask); } /* Some capabilities may be different across iommus */ static void domain_update_iommu_cap(struct dmar_domain *domain) { domain_update_iommu_coherency(domain); domain_update_iommu_snooping(domain); domain_update_iommu_superpage(domain); } static struct intel_iommu *device_to_iommu(int segment, u8 bus, u8 devfn) { struct dmar_drhd_unit *drhd = NULL; int i; for_each_drhd_unit(drhd) { if (drhd->ignored) continue; if (segment != drhd->segment) continue; for (i = 0; i < drhd->devices_cnt; i++) { if (drhd->devices[i] && drhd->devices[i]->bus->number == bus && drhd->devices[i]->devfn == devfn) return drhd->iommu; if (drhd->devices[i] && drhd->devices[i]->subordinate && drhd->devices[i]->subordinate->number <= bus && drhd->devices[i]->subordinate->busn_res.end >= bus) return drhd->iommu; } if (drhd->include_all) return drhd->iommu; } return NULL; } static void domain_flush_cache(struct dmar_domain *domain, void *addr, int size) { if (!domain->iommu_coherency) clflush_cache_range(addr, size); } /* Gets context entry for a given bus and devfn */ static struct context_entry * device_to_context_entry(struct intel_iommu *iommu, u8 bus, u8 devfn) { struct root_entry *root; struct context_entry *context; unsigned long phy_addr; unsigned long flags; spin_lock_irqsave(&iommu->lock, flags); root = &iommu->root_entry[bus]; context = get_context_addr_from_root(root); if (!context) { context = (struct context_entry *) alloc_pgtable_page(iommu->node); if (!context) { spin_unlock_irqrestore(&iommu->lock, flags); return NULL; } __iommu_flush_cache(iommu, (void *)context, CONTEXT_SIZE); phy_addr = virt_to_phys((void *)context); set_root_value(root, phy_addr); set_root_present(root); __iommu_flush_cache(iommu, root, sizeof(*root)); } spin_unlock_irqrestore(&iommu->lock, flags); return &context[devfn]; } static int device_context_mapped(struct intel_iommu *iommu, u8 bus, u8 devfn) { struct root_entry *root; struct context_entry *context; int ret; unsigned long flags; spin_lock_irqsave(&iommu->lock, flags); root = &iommu->root_entry[bus]; context = get_context_addr_from_root(root); if (!context) { ret = 0; goto out; } ret = context_present(&context[devfn]); out: spin_unlock_irqrestore(&iommu->lock, flags); return ret; } static void clear_context_table(struct intel_iommu *iommu, u8 bus, u8 devfn) { struct root_entry *root; struct context_entry *context; unsigned long flags; spin_lock_irqsave(&iommu->lock, flags); root = &iommu->root_entry[bus]; context = get_context_addr_from_root(root); if (context) { context_clear_entry(&context[devfn]); __iommu_flush_cache(iommu, &context[devfn], \ sizeof(*context)); } spin_unlock_irqrestore(&iommu->lock, flags); } static void free_context_table(struct intel_iommu *iommu) { struct root_entry *root; int i; unsigned long flags; struct context_entry *context; spin_lock_irqsave(&iommu->lock, flags); if (!iommu->root_entry) { goto out; } for (i = 0; i < ROOT_ENTRY_NR; i++) { root = &iommu->root_entry[i]; context = get_context_addr_from_root(root); if (context) free_pgtable_page(context); } free_pgtable_page(iommu->root_entry); iommu->root_entry = NULL; out: spin_unlock_irqrestore(&iommu->lock, flags); } static struct dma_pte *pfn_to_dma_pte(struct dmar_domain *domain, unsigned long pfn, int target_level) { int addr_width = agaw_to_width(domain->agaw) - VTD_PAGE_SHIFT; struct dma_pte *parent, *pte = NULL; int level = agaw_to_level(domain->agaw); int offset; BUG_ON(!domain->pgd); BUG_ON(addr_width < BITS_PER_LONG && pfn >> addr_width); parent = domain->pgd; while (level > 0) { void *tmp_page; offset = pfn_level_offset(pfn, level); pte = &parent[offset]; if (!target_level && (dma_pte_superpage(pte) || !dma_pte_present(pte))) break; if (level == target_level) break; if (!dma_pte_present(pte)) { uint64_t pteval; tmp_page = alloc_pgtable_page(domain->nid); if (!tmp_page) return NULL; domain_flush_cache(domain, tmp_page, VTD_PAGE_SIZE); pteval = ((uint64_t)virt_to_dma_pfn(tmp_page) << VTD_PAGE_SHIFT) | DMA_PTE_READ | DMA_PTE_WRITE; if (cmpxchg64(&pte->val, 0ULL, pteval)) { /* Someone else set it while we were thinking; use theirs. */ free_pgtable_page(tmp_page); } else { dma_pte_addr(pte); domain_flush_cache(domain, pte, sizeof(*pte)); } } parent = phys_to_virt(dma_pte_addr(pte)); level--; } return pte; } /* return address's pte at specific level */ static struct dma_pte *dma_pfn_level_pte(struct dmar_domain *domain, unsigned long pfn, int level, int *large_page) { struct dma_pte *parent, *pte = NULL; int total = agaw_to_level(domain->agaw); int offset; parent = domain->pgd; while (level <= total) { offset = pfn_level_offset(pfn, total); pte = &parent[offset]; if (level == total) return pte; if (!dma_pte_present(pte)) { *large_page = total; break; } if (pte->val & DMA_PTE_LARGE_PAGE) { *large_page = total; return pte; } parent = phys_to_virt(dma_pte_addr(pte)); total--; } return NULL; } /* clear last level pte, a tlb flush should be followed */ static int dma_pte_clear_range(struct dmar_domain *domain, unsigned long start_pfn, unsigned long last_pfn) { int addr_width = agaw_to_width(domain->agaw) - VTD_PAGE_SHIFT; unsigned int large_page = 1; struct dma_pte *first_pte, *pte; int order; BUG_ON(addr_width < BITS_PER_LONG && start_pfn >> addr_width); BUG_ON(addr_width < BITS_PER_LONG && last_pfn >> addr_width); BUG_ON(start_pfn > last_pfn); /* we don't need lock here; nobody else touches the iova range */ do { large_page = 1; first_pte = pte = dma_pfn_level_pte(domain, start_pfn, 1, &large_page); if (!pte) { start_pfn = align_to_level(start_pfn + 1, large_page + 1); continue; } do { dma_clear_pte(pte); start_pfn += lvl_to_nr_pages(large_page); pte++; } while (start_pfn <= last_pfn && !first_pte_in_page(pte)); domain_flush_cache(domain, first_pte, (void *)pte - (void *)first_pte); } while (start_pfn && start_pfn <= last_pfn); order = (large_page - 1) * 9; return order; } /* free page table pages. last level pte should already be cleared */ static void dma_pte_free_pagetable(struct dmar_domain *domain, unsigned long start_pfn, unsigned long last_pfn) { int addr_width = agaw_to_width(domain->agaw) - VTD_PAGE_SHIFT; struct dma_pte *first_pte, *pte; int total = agaw_to_level(domain->agaw); int level; unsigned long tmp; int large_page = 2; BUG_ON(addr_width < BITS_PER_LONG && start_pfn >> addr_width); BUG_ON(addr_width < BITS_PER_LONG && last_pfn >> addr_width); BUG_ON(start_pfn > last_pfn); /* We don't need lock here; nobody else touches the iova range */ level = 2; while (level <= total) { tmp = align_to_level(start_pfn, level); /* If we can't even clear one PTE at this level, we're done */ if (tmp + level_size(level) - 1 > last_pfn) return; do { large_page = level; first_pte = pte = dma_pfn_level_pte(domain, tmp, level, &large_page); if (large_page > level) level = large_page + 1; if (!pte) { tmp = align_to_level(tmp + 1, level + 1); continue; } do { if (dma_pte_present(pte)) { free_pgtable_page(phys_to_virt(dma_pte_addr(pte))); dma_clear_pte(pte); } pte++; tmp += level_size(level); } while (!first_pte_in_page(pte) && tmp + level_size(level) - 1 <= last_pfn); domain_flush_cache(domain, first_pte, (void *)pte - (void *)first_pte); } while (tmp && tmp + level_size(level) - 1 <= last_pfn); level++; } /* free pgd */ if (start_pfn == 0 && last_pfn == DOMAIN_MAX_PFN(domain->gaw)) { free_pgtable_page(domain->pgd); domain->pgd = NULL; } } /* iommu handling */ static int iommu_alloc_root_entry(struct intel_iommu *iommu) { struct root_entry *root; unsigned long flags; root = (struct root_entry *)alloc_pgtable_page(iommu->node); if (!root) return -ENOMEM; __iommu_flush_cache(iommu, root, ROOT_SIZE); spin_lock_irqsave(&iommu->lock, flags); iommu->root_entry = root; spin_unlock_irqrestore(&iommu->lock, flags); return 0; } static void iommu_set_root_entry(struct intel_iommu *iommu) { void *addr; u32 sts; unsigned long flag; addr = iommu->root_entry; raw_spin_lock_irqsave(&iommu->register_lock, flag); dmar_writeq(iommu->reg + DMAR_RTADDR_REG, virt_to_phys(addr)); writel(iommu->gcmd | DMA_GCMD_SRTP, iommu->reg + DMAR_GCMD_REG); /* Make sure hardware complete it */ IOMMU_WAIT_OP(iommu, DMAR_GSTS_REG, readl, (sts & DMA_GSTS_RTPS), sts); raw_spin_unlock_irqrestore(&iommu->register_lock, flag); } static void iommu_flush_write_buffer(struct intel_iommu *iommu) { u32 val; unsigned long flag; if (!rwbf_quirk && !cap_rwbf(iommu->cap)) return; raw_spin_lock_irqsave(&iommu->register_lock, flag); writel(iommu->gcmd | DMA_GCMD_WBF, iommu->reg + DMAR_GCMD_REG); /* Make sure hardware complete it */ IOMMU_WAIT_OP(iommu, DMAR_GSTS_REG, readl, (!(val & DMA_GSTS_WBFS)), val); raw_spin_unlock_irqrestore(&iommu->register_lock, flag); } /* return value determine if we need a write buffer flush */ static void __iommu_flush_context(struct intel_iommu *iommu, u16 did, u16 source_id, u8 function_mask, u64 type) { u64 val = 0; unsigned long flag; switch (type) { case DMA_CCMD_GLOBAL_INVL: val = DMA_CCMD_GLOBAL_INVL; break; case DMA_CCMD_DOMAIN_INVL: val = DMA_CCMD_DOMAIN_INVL|DMA_CCMD_DID(did); break; case DMA_CCMD_DEVICE_INVL: val = DMA_CCMD_DEVICE_INVL|DMA_CCMD_DID(did) | DMA_CCMD_SID(source_id) | DMA_CCMD_FM(function_mask); break; default: BUG(); } val |= DMA_CCMD_ICC; raw_spin_lock_irqsave(&iommu->register_lock, flag); dmar_writeq(iommu->reg + DMAR_CCMD_REG, val); /* Make sure hardware complete it */ IOMMU_WAIT_OP(iommu, DMAR_CCMD_REG, dmar_readq, (!(val & DMA_CCMD_ICC)), val); raw_spin_unlock_irqrestore(&iommu->register_lock, flag); } /* return value determine if we need a write buffer flush */ static void __iommu_flush_iotlb(struct intel_iommu *iommu, u16 did, u64 addr, unsigned int size_order, u64 type) { int tlb_offset = ecap_iotlb_offset(iommu->ecap); u64 val = 0, val_iva = 0; unsigned long flag; switch (type) { case DMA_TLB_GLOBAL_FLUSH: /* global flush doesn't need set IVA_REG */ val = DMA_TLB_GLOBAL_FLUSH|DMA_TLB_IVT; break; case DMA_TLB_DSI_FLUSH: val = DMA_TLB_DSI_FLUSH|DMA_TLB_IVT|DMA_TLB_DID(did); break; case DMA_TLB_PSI_FLUSH: val = DMA_TLB_PSI_FLUSH|DMA_TLB_IVT|DMA_TLB_DID(did); /* Note: always flush non-leaf currently */ val_iva = size_order | addr; break; default: BUG(); } /* Note: set drain read/write */ #if 0 /* * This is probably to be super secure.. Looks like we can * ignore it without any impact. */ if (cap_read_drain(iommu->cap)) val |= DMA_TLB_READ_DRAIN; #endif if (cap_write_drain(iommu->cap)) val |= DMA_TLB_WRITE_DRAIN; raw_spin_lock_irqsave(&iommu->register_lock, flag); /* Note: Only uses first TLB reg currently */ if (val_iva) dmar_writeq(iommu->reg + tlb_offset, val_iva); dmar_writeq(iommu->reg + tlb_offset + 8, val); /* Make sure hardware complete it */ IOMMU_WAIT_OP(iommu, tlb_offset + 8, dmar_readq, (!(val & DMA_TLB_IVT)), val); raw_spin_unlock_irqrestore(&iommu->register_lock, flag); /* check IOTLB invalidation granularity */ if (DMA_TLB_IAIG(val) == 0) printk(KERN_ERR"IOMMU: flush IOTLB failed\n"); if (DMA_TLB_IAIG(val) != DMA_TLB_IIRG(type)) pr_debug("IOMMU: tlb flush request %Lx, actual %Lx\n", (unsigned long long)DMA_TLB_IIRG(type), (unsigned long long)DMA_TLB_IAIG(val)); } static struct device_domain_info *iommu_support_dev_iotlb( struct dmar_domain *domain, int segment, u8 bus, u8 devfn) { int found = 0; unsigned long flags; struct device_domain_info *info; struct intel_iommu *iommu = device_to_iommu(segment, bus, devfn); if (!ecap_dev_iotlb_support(iommu->ecap)) return NULL; if (!iommu->qi) return NULL; spin_lock_irqsave(&device_domain_lock, flags); list_for_each_entry(info, &domain->devices, link) if (info->bus == bus && info->devfn == devfn) { found = 1; break; } spin_unlock_irqrestore(&device_domain_lock, flags); if (!found || !info->dev) return NULL; if (!pci_find_ext_capability(info->dev, PCI_EXT_CAP_ID_ATS)) return NULL; if (!dmar_find_matched_atsr_unit(info->dev)) return NULL; info->iommu = iommu; return info; } static void iommu_enable_dev_iotlb(struct device_domain_info *info) { if (!info) return; pci_enable_ats(info->dev, VTD_PAGE_SHIFT); } static void iommu_disable_dev_iotlb(struct device_domain_info *info) { if (!info->dev || !pci_ats_enabled(info->dev)) return; pci_disable_ats(info->dev); } static void iommu_flush_dev_iotlb(struct dmar_domain *domain, u64 addr, unsigned mask) { u16 sid, qdep; unsigned long flags; struct device_domain_info *info; spin_lock_irqsave(&device_domain_lock, flags); list_for_each_entry(info, &domain->devices, link) { if (!info->dev || !pci_ats_enabled(info->dev)) continue; sid = info->bus << 8 | info->devfn; qdep = pci_ats_queue_depth(info->dev); qi_flush_dev_iotlb(info->iommu, sid, qdep, addr, mask); } spin_unlock_irqrestore(&device_domain_lock, flags); } static void iommu_flush_iotlb_psi(struct intel_iommu *iommu, u16 did, unsigned long pfn, unsigned int pages, int map) { unsigned int mask = ilog2(__roundup_pow_of_two(pages)); uint64_t addr = (uint64_t)pfn << VTD_PAGE_SHIFT; BUG_ON(pages == 0); /* * Fallback to domain selective flush if no PSI support or the size is * too big. * PSI requires page size to be 2 ^ x, and the base address is naturally * aligned to the size */ if (!cap_pgsel_inv(iommu->cap) || mask > cap_max_amask_val(iommu->cap)) iommu->flush.flush_iotlb(iommu, did, 0, 0, DMA_TLB_DSI_FLUSH); else iommu->flush.flush_iotlb(iommu, did, addr, mask, DMA_TLB_PSI_FLUSH); /* * In caching mode, changes of pages from non-present to present require * flush. However, device IOTLB doesn't need to be flushed in this case. */ if (!cap_caching_mode(iommu->cap) || !map) iommu_flush_dev_iotlb(iommu->domains[did], addr, mask); } static void iommu_disable_protect_mem_regions(struct intel_iommu *iommu) { u32 pmen; unsigned long flags; raw_spin_lock_irqsave(&iommu->register_lock, flags); pmen = readl(iommu->reg + DMAR_PMEN_REG); pmen &= ~DMA_PMEN_EPM; writel(pmen, iommu->reg + DMAR_PMEN_REG); /* wait for the protected region status bit to clear */ IOMMU_WAIT_OP(iommu, DMAR_PMEN_REG, readl, !(pmen & DMA_PMEN_PRS), pmen); raw_spin_unlock_irqrestore(&iommu->register_lock, flags); } static int iommu_enable_translation(struct intel_iommu *iommu) { u32 sts; unsigned long flags; raw_spin_lock_irqsave(&iommu->register_lock, flags); iommu->gcmd |= DMA_GCMD_TE; writel(iommu->gcmd, iommu->reg + DMAR_GCMD_REG); /* Make sure hardware complete it */ IOMMU_WAIT_OP(iommu, DMAR_GSTS_REG, readl, (sts & DMA_GSTS_TES), sts); raw_spin_unlock_irqrestore(&iommu->register_lock, flags); return 0; } static int iommu_disable_translation(struct intel_iommu *iommu) { u32 sts; unsigned long flag; raw_spin_lock_irqsave(&iommu->register_lock, flag); iommu->gcmd &= ~DMA_GCMD_TE; writel(iommu->gcmd, iommu->reg + DMAR_GCMD_REG); /* Make sure hardware complete it */ IOMMU_WAIT_OP(iommu, DMAR_GSTS_REG, readl, (!(sts & DMA_GSTS_TES)), sts); raw_spin_unlock_irqrestore(&iommu->register_lock, flag); return 0; } static int iommu_init_domains(struct intel_iommu *iommu) { unsigned long ndomains; unsigned long nlongs; ndomains = cap_ndoms(iommu->cap); pr_debug("IOMMU %d: Number of Domains supported <%ld>\n", iommu->seq_id, ndomains); nlongs = BITS_TO_LONGS(ndomains); spin_lock_init(&iommu->lock); /* TBD: there might be 64K domains, * consider other allocation for future chip */ iommu->domain_ids = kcalloc(nlongs, sizeof(unsigned long), GFP_KERNEL); if (!iommu->domain_ids) { printk(KERN_ERR "Allocating domain id array failed\n"); return -ENOMEM; } iommu->domains = kcalloc(ndomains, sizeof(struct dmar_domain *), GFP_KERNEL); if (!iommu->domains) { printk(KERN_ERR "Allocating domain array failed\n"); return -ENOMEM; } /* * if Caching mode is set, then invalid translations are tagged * with domainid 0. Hence we need to pre-allocate it. */ if (cap_caching_mode(iommu->cap)) set_bit(0, iommu->domain_ids); return 0; } static void domain_exit(struct dmar_domain *domain); static void vm_domain_exit(struct dmar_domain *domain); void free_dmar_iommu(struct intel_iommu *iommu) { struct dmar_domain *domain; int i; unsigned long flags; if ((iommu->domains) && (iommu->domain_ids)) { for_each_set_bit(i, iommu->domain_ids, cap_ndoms(iommu->cap)) { domain = iommu->domains[i]; clear_bit(i, iommu->domain_ids); spin_lock_irqsave(&domain->iommu_lock, flags); if (--domain->iommu_count == 0) { if (domain->flags & DOMAIN_FLAG_VIRTUAL_MACHINE) vm_domain_exit(domain); else domain_exit(domain); } spin_unlock_irqrestore(&domain->iommu_lock, flags); } } if (iommu->gcmd & DMA_GCMD_TE) iommu_disable_translation(iommu); if (iommu->irq) { irq_set_handler_data(iommu->irq, NULL); /* This will mask the irq */ free_irq(iommu->irq, iommu); destroy_irq(iommu->irq); } kfree(iommu->domains); kfree(iommu->domain_ids); g_iommus[iommu->seq_id] = NULL; /* if all iommus are freed, free g_iommus */ for (i = 0; i < g_num_of_iommus; i++) { if (g_iommus[i]) break; } if (i == g_num_of_iommus) kfree(g_iommus); /* free context mapping */ free_context_table(iommu); } static struct dmar_domain *alloc_domain(void) { struct dmar_domain *domain; domain = alloc_domain_mem(); if (!domain) return NULL; domain->nid = -1; memset(domain->iommu_bmp, 0, sizeof(domain->iommu_bmp)); domain->flags = 0; return domain; } static int iommu_attach_domain(struct dmar_domain *domain, struct intel_iommu *iommu) { int num; unsigned long ndomains; unsigned long flags; ndomains = cap_ndoms(iommu->cap); spin_lock_irqsave(&iommu->lock, flags); num = find_first_zero_bit(iommu->domain_ids, ndomains); if (num >= ndomains) { spin_unlock_irqrestore(&iommu->lock, flags); printk(KERN_ERR "IOMMU: no free domain ids\n"); return -ENOMEM; } domain->id = num; set_bit(num, iommu->domain_ids); set_bit(iommu->seq_id, domain->iommu_bmp); iommu->domains[num] = domain; spin_unlock_irqrestore(&iommu->lock, flags); return 0; } static void iommu_detach_domain(struct dmar_domain *domain, struct intel_iommu *iommu) { unsigned long flags; int num, ndomains; int found = 0; spin_lock_irqsave(&iommu->lock, flags); ndomains = cap_ndoms(iommu->cap); for_each_set_bit(num, iommu->domain_ids, ndomains) { if (iommu->domains[num] == domain) { found = 1; break; } } if (found) { clear_bit(num, iommu->domain_ids); clear_bit(iommu->seq_id, domain->iommu_bmp); iommu->domains[num] = NULL; } spin_unlock_irqrestore(&iommu->lock, flags); } static struct iova_domain reserved_iova_list; static struct lock_class_key reserved_rbtree_key; static int dmar_init_reserved_ranges(void) { struct pci_dev *pdev = NULL; struct iova *iova; int i; init_iova_domain(&reserved_iova_list, DMA_32BIT_PFN); lockdep_set_class(&reserved_iova_list.iova_rbtree_lock, &reserved_rbtree_key); /* IOAPIC ranges shouldn't be accessed by DMA */ iova = reserve_iova(&reserved_iova_list, IOVA_PFN(IOAPIC_RANGE_START), IOVA_PFN(IOAPIC_RANGE_END)); if (!iova) { printk(KERN_ERR "Reserve IOAPIC range failed\n"); return -ENODEV; } /* Reserve all PCI MMIO to avoid peer-to-peer access */ for_each_pci_dev(pdev) { struct resource *r; for (i = 0; i < PCI_NUM_RESOURCES; i++) { r = &pdev->resource[i]; if (!r->flags || !(r->flags & IORESOURCE_MEM)) continue; iova = reserve_iova(&reserved_iova_list, IOVA_PFN(r->start), IOVA_PFN(r->end)); if (!iova) { printk(KERN_ERR "Reserve iova failed\n"); return -ENODEV; } } } return 0; } static void domain_reserve_special_ranges(struct dmar_domain *domain) { copy_reserved_iova(&reserved_iova_list, &domain->iovad); } static inline int guestwidth_to_adjustwidth(int gaw) { int agaw; int r = (gaw - 12) % 9; if (r == 0) agaw = gaw; else agaw = gaw + 9 - r; if (agaw > 64) agaw = 64; return agaw; } static int domain_init(struct dmar_domain *domain, int guest_width) { struct intel_iommu *iommu; int adjust_width, agaw; unsigned long sagaw; init_iova_domain(&domain->iovad, DMA_32BIT_PFN); spin_lock_init(&domain->iommu_lock); domain_reserve_special_ranges(domain); /* calculate AGAW */ iommu = domain_get_iommu(domain); if (guest_width > cap_mgaw(iommu->cap)) guest_width = cap_mgaw(iommu->cap); domain->gaw = guest_width; adjust_width = guestwidth_to_adjustwidth(guest_width); agaw = width_to_agaw(adjust_width); sagaw = cap_sagaw(iommu->cap); if (!test_bit(agaw, &sagaw)) { /* hardware doesn't support it, choose a bigger one */ pr_debug("IOMMU: hardware doesn't support agaw %d\n", agaw); agaw = find_next_bit(&sagaw, 5, agaw); if (agaw >= 5) return -ENODEV; } domain->agaw = agaw; INIT_LIST_HEAD(&domain->devices); if (ecap_coherent(iommu->ecap)) domain->iommu_coherency = 1; else domain->iommu_coherency = 0; if (ecap_sc_support(iommu->ecap)) domain->iommu_snooping = 1; else domain->iommu_snooping = 0; domain->iommu_superpage = fls(cap_super_page_val(iommu->cap)); domain->iommu_count = 1; domain->nid = iommu->node; /* always allocate the top pgd */ domain->pgd = (struct dma_pte *)alloc_pgtable_page(domain->nid); if (!domain->pgd) return -ENOMEM; __iommu_flush_cache(iommu, domain->pgd, PAGE_SIZE); return 0; } static void domain_exit(struct dmar_domain *domain) { struct dmar_drhd_unit *drhd; struct intel_iommu *iommu; /* Domain 0 is reserved, so dont process it */ if (!domain) return; /* Flush any lazy unmaps that may reference this domain */ if (!intel_iommu_strict) flush_unmaps_timeout(0); domain_remove_dev_info(domain); /* destroy iovas */ put_iova_domain(&domain->iovad); /* clear ptes */ dma_pte_clear_range(domain, 0, DOMAIN_MAX_PFN(domain->gaw)); /* free page tables */ dma_pte_free_pagetable(domain, 0, DOMAIN_MAX_PFN(domain->gaw)); for_each_active_iommu(iommu, drhd) if (test_bit(iommu->seq_id, domain->iommu_bmp)) iommu_detach_domain(domain, iommu); free_domain_mem(domain); } static int domain_context_mapping_one(struct dmar_domain *domain, int segment, u8 bus, u8 devfn, int translation) { struct context_entry *context; unsigned long flags; struct intel_iommu *iommu; struct dma_pte *pgd; unsigned long num; unsigned long ndomains; int id; int agaw; struct device_domain_info *info = NULL; pr_debug("Set context mapping for %02x:%02x.%d\n", bus, PCI_SLOT(devfn), PCI_FUNC(devfn)); BUG_ON(!domain->pgd); BUG_ON(translation != CONTEXT_TT_PASS_THROUGH && translation != CONTEXT_TT_MULTI_LEVEL); iommu = device_to_iommu(segment, bus, devfn); if (!iommu) return -ENODEV; context = device_to_context_entry(iommu, bus, devfn); if (!context) return -ENOMEM; spin_lock_irqsave(&iommu->lock, flags); if (context_present(context)) { spin_unlock_irqrestore(&iommu->lock, flags); return 0; } id = domain->id; pgd = domain->pgd; if (domain->flags & DOMAIN_FLAG_VIRTUAL_MACHINE || domain->flags & DOMAIN_FLAG_STATIC_IDENTITY) { int found = 0; /* find an available domain id for this device in iommu */ ndomains = cap_ndoms(iommu->cap); for_each_set_bit(num, iommu->domain_ids, ndomains) { if (iommu->domains[num] == domain) { id = num; found = 1; break; } } if (found == 0) { num = find_first_zero_bit(iommu->domain_ids, ndomains); if (num >= ndomains) { spin_unlock_irqrestore(&iommu->lock, flags); printk(KERN_ERR "IOMMU: no free domain ids\n"); return -EFAULT; } set_bit(num, iommu->domain_ids); iommu->domains[num] = domain; id = num; } /* Skip top levels of page tables for * iommu which has less agaw than default. * Unnecessary for PT mode. */ if (translation != CONTEXT_TT_PASS_THROUGH) { for (agaw = domain->agaw; agaw != iommu->agaw; agaw--) { pgd = phys_to_virt(dma_pte_addr(pgd)); if (!dma_pte_present(pgd)) { spin_unlock_irqrestore(&iommu->lock, flags); return -ENOMEM; } } } } context_set_domain_id(context, id); if (translation != CONTEXT_TT_PASS_THROUGH) { info = iommu_support_dev_iotlb(domain, segment, bus, devfn); translation = info ? CONTEXT_TT_DEV_IOTLB : CONTEXT_TT_MULTI_LEVEL; } /* * In pass through mode, AW must be programmed to indicate the largest * AGAW value supported by hardware. And ASR is ignored by hardware. */ if (unlikely(translation == CONTEXT_TT_PASS_THROUGH)) context_set_address_width(context, iommu->msagaw); else { context_set_address_root(context, virt_to_phys(pgd)); context_set_address_width(context, iommu->agaw); } context_set_translation_type(context, translation); context_set_fault_enable(context); context_set_present(context); domain_flush_cache(domain, context, sizeof(*context)); /* * It's a non-present to present mapping. If hardware doesn't cache * non-present entry we only need to flush the write-buffer. If the * _does_ cache non-present entries, then it does so in the special * domain #0, which we have to flush: */ if (cap_caching_mode(iommu->cap)) { iommu->flush.flush_context(iommu, 0, (((u16)bus) << 8) | devfn, DMA_CCMD_MASK_NOBIT, DMA_CCMD_DEVICE_INVL); iommu->flush.flush_iotlb(iommu, domain->id, 0, 0, DMA_TLB_DSI_FLUSH); } else { iommu_flush_write_buffer(iommu); } iommu_enable_dev_iotlb(info); spin_unlock_irqrestore(&iommu->lock, flags); spin_lock_irqsave(&domain->iommu_lock, flags); if (!test_and_set_bit(iommu->seq_id, domain->iommu_bmp)) { domain->iommu_count++; if (domain->iommu_count == 1) domain->nid = iommu->node; domain_update_iommu_cap(domain); } spin_unlock_irqrestore(&domain->iommu_lock, flags); return 0; } static int domain_context_mapping(struct dmar_domain *domain, struct pci_dev *pdev, int translation) { int ret; struct pci_dev *tmp, *parent; ret = domain_context_mapping_one(domain, pci_domain_nr(pdev->bus), pdev->bus->number, pdev->devfn, translation); if (ret) return ret; /* dependent device mapping */ tmp = pci_find_upstream_pcie_bridge(pdev); if (!tmp) return 0; /* Secondary interface's bus number and devfn 0 */ parent = pdev->bus->self; while (parent != tmp) { ret = domain_context_mapping_one(domain, pci_domain_nr(parent->bus), parent->bus->number, parent->devfn, translation); if (ret) return ret; parent = parent->bus->self; } if (pci_is_pcie(tmp)) /* this is a PCIe-to-PCI bridge */ return domain_context_mapping_one(domain, pci_domain_nr(tmp->subordinate), tmp->subordinate->number, 0, translation); else /* this is a legacy PCI bridge */ return domain_context_mapping_one(domain, pci_domain_nr(tmp->bus), tmp->bus->number, tmp->devfn, translation); } static int domain_context_mapped(struct pci_dev *pdev) { int ret; struct pci_dev *tmp, *parent; struct intel_iommu *iommu; iommu = device_to_iommu(pci_domain_nr(pdev->bus), pdev->bus->number, pdev->devfn); if (!iommu) return -ENODEV; ret = device_context_mapped(iommu, pdev->bus->number, pdev->devfn); if (!ret) return ret; /* dependent device mapping */ tmp = pci_find_upstream_pcie_bridge(pdev); if (!tmp) return ret; /* Secondary interface's bus number and devfn 0 */ parent = pdev->bus->self; while (parent != tmp) { ret = device_context_mapped(iommu, parent->bus->number, parent->devfn); if (!ret) return ret; parent = parent->bus->self; } if (pci_is_pcie(tmp)) return device_context_mapped(iommu, tmp->subordinate->number, 0); else return device_context_mapped(iommu, tmp->bus->number, tmp->devfn); } /* Returns a number of VTD pages, but aligned to MM page size */ static inline unsigned long aligned_nrpages(unsigned long host_addr, size_t size) { host_addr &= ~PAGE_MASK; return PAGE_ALIGN(host_addr + size) >> VTD_PAGE_SHIFT; } /* Return largest possible superpage level for a given mapping */ static inline int hardware_largepage_caps(struct dmar_domain *domain, unsigned long iov_pfn, unsigned long phy_pfn, unsigned long pages) { int support, level = 1; unsigned long pfnmerge; support = domain->iommu_superpage; /* To use a large page, the virtual *and* physical addresses must be aligned to 2MiB/1GiB/etc. Lower bits set in either of them will mean we have to use smaller pages. So just merge them and check both at once. */ pfnmerge = iov_pfn | phy_pfn; while (support && !(pfnmerge & ~VTD_STRIDE_MASK)) { pages >>= VTD_STRIDE_SHIFT; if (!pages) break; pfnmerge >>= VTD_STRIDE_SHIFT; level++; support--; } return level; } static int __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn, struct scatterlist *sg, unsigned long phys_pfn, unsigned long nr_pages, int prot) { struct dma_pte *first_pte = NULL, *pte = NULL; phys_addr_t uninitialized_var(pteval); int addr_width = agaw_to_width(domain->agaw) - VTD_PAGE_SHIFT; unsigned long sg_res; unsigned int largepage_lvl = 0; unsigned long lvl_pages = 0; BUG_ON(addr_width < BITS_PER_LONG && (iov_pfn + nr_pages - 1) >> addr_width); if ((prot & (DMA_PTE_READ|DMA_PTE_WRITE)) == 0) return -EINVAL; prot &= DMA_PTE_READ | DMA_PTE_WRITE | DMA_PTE_SNP; if (sg) sg_res = 0; else { sg_res = nr_pages + 1; pteval = ((phys_addr_t)phys_pfn << VTD_PAGE_SHIFT) | prot; } while (nr_pages > 0) { uint64_t tmp; if (!sg_res) { sg_res = aligned_nrpages(sg->offset, sg->length); sg->dma_address = ((dma_addr_t)iov_pfn << VTD_PAGE_SHIFT) + sg->offset; sg->dma_length = sg->length; pteval = page_to_phys(sg_page(sg)) | prot; phys_pfn = pteval >> VTD_PAGE_SHIFT; } if (!pte) { largepage_lvl = hardware_largepage_caps(domain, iov_pfn, phys_pfn, sg_res); first_pte = pte = pfn_to_dma_pte(domain, iov_pfn, largepage_lvl); if (!pte) return -ENOMEM; /* It is large page*/ if (largepage_lvl > 1) { pteval |= DMA_PTE_LARGE_PAGE; /* Ensure that old small page tables are removed to make room for superpage, if they exist. */ dma_pte_clear_range(domain, iov_pfn, iov_pfn + lvl_to_nr_pages(largepage_lvl) - 1); dma_pte_free_pagetable(domain, iov_pfn, iov_pfn + lvl_to_nr_pages(largepage_lvl) - 1); } else { pteval &= ~(uint64_t)DMA_PTE_LARGE_PAGE; } } /* We don't need lock here, nobody else * touches the iova range */ tmp = cmpxchg64_local(&pte->val, 0ULL, pteval); if (tmp) { static int dumps = 5; printk(KERN_CRIT "ERROR: DMA PTE for vPFN 0x%lx already set (to %llx not %llx)\n", iov_pfn, tmp, (unsigned long long)pteval); if (dumps) { dumps--; debug_dma_dump_mappings(NULL); } WARN_ON(1); } lvl_pages = lvl_to_nr_pages(largepage_lvl); BUG_ON(nr_pages < lvl_pages); BUG_ON(sg_res < lvl_pages); nr_pages -= lvl_pages; iov_pfn += lvl_pages; phys_pfn += lvl_pages; pteval += lvl_pages * VTD_PAGE_SIZE; sg_res -= lvl_pages; /* If the next PTE would be the first in a new page, then we need to flush the cache on the entries we've just written. And then we'll need to recalculate 'pte', so clear it and let it get set again in the if (!pte) block above. If we're done (!nr_pages) we need to flush the cache too. Also if we've been setting superpages, we may need to recalculate 'pte' and switch back to smaller pages for the end of the mapping, if the trailing size is not enough to use another superpage (i.e. sg_res < lvl_pages). */ pte++; if (!nr_pages || first_pte_in_page(pte) || (largepage_lvl > 1 && sg_res < lvl_pages)) { domain_flush_cache(domain, first_pte, (void *)pte - (void *)first_pte); pte = NULL; } if (!sg_res && nr_pages) sg = sg_next(sg); } return 0; } static inline int domain_sg_mapping(struct dmar_domain *domain, unsigned long iov_pfn, struct scatterlist *sg, unsigned long nr_pages, int prot) { return __domain_mapping(domain, iov_pfn, sg, 0, nr_pages, prot); } static inline int domain_pfn_mapping(struct dmar_domain *domain, unsigned long iov_pfn, unsigned long phys_pfn, unsigned long nr_pages, int prot) { return __domain_mapping(domain, iov_pfn, NULL, phys_pfn, nr_pages, prot); } static void iommu_detach_dev(struct intel_iommu *iommu, u8 bus, u8 devfn) { if (!iommu) return; clear_context_table(iommu, bus, devfn); iommu->flush.flush_context(iommu, 0, 0, 0, DMA_CCMD_GLOBAL_INVL); iommu->flush.flush_iotlb(iommu, 0, 0, 0, DMA_TLB_GLOBAL_FLUSH); } static inline void unlink_domain_info(struct device_domain_info *info) { assert_spin_locked(&device_domain_lock); list_del(&info->link); list_del(&info->global); if (info->dev) info->dev->dev.archdata.iommu = NULL; } static void domain_remove_dev_info(struct dmar_domain *domain) { struct device_domain_info *info; unsigned long flags; struct intel_iommu *iommu; spin_lock_irqsave(&device_domain_lock, flags); while (!list_empty(&domain->devices)) { info = list_entry(domain->devices.next, struct device_domain_info, link); unlink_domain_info(info); spin_unlock_irqrestore(&device_domain_lock, flags); iommu_disable_dev_iotlb(info); iommu = device_to_iommu(info->segment, info->bus, info->devfn); iommu_detach_dev(iommu, info->bus, info->devfn); free_devinfo_mem(info); spin_lock_irqsave(&device_domain_lock, flags); } spin_unlock_irqrestore(&device_domain_lock, flags); } /* * find_domain * Note: we use struct pci_dev->dev.archdata.iommu stores the info */ static struct dmar_domain * find_domain(struct pci_dev *pdev) { struct device_domain_info *info; /* No lock here, assumes no domain exit in normal case */ info = pdev->dev.archdata.iommu; if (info) return info->domain; return NULL; } /* domain is initialized */ static struct dmar_domain *get_domain_for_dev(struct pci_dev *pdev, int gaw) { struct dmar_domain *domain, *found = NULL; struct intel_iommu *iommu; struct dmar_drhd_unit *drhd; struct device_domain_info *info, *tmp; struct pci_dev *dev_tmp; unsigned long flags; int bus = 0, devfn = 0; int segment; int ret; domain = find_domain(pdev); if (domain) return domain; segment = pci_domain_nr(pdev->bus); dev_tmp = pci_find_upstream_pcie_bridge(pdev); if (dev_tmp) { if (pci_is_pcie(dev_tmp)) { bus = dev_tmp->subordinate->number; devfn = 0; } else { bus = dev_tmp->bus->number; devfn = dev_tmp->devfn; } spin_lock_irqsave(&device_domain_lock, flags); list_for_each_entry(info, &device_domain_list, global) { if (info->segment == segment && info->bus == bus && info->devfn == devfn) { found = info->domain; break; } } spin_unlock_irqrestore(&device_domain_lock, flags); /* pcie-pci bridge already has a domain, uses it */ if (found) { domain = found; goto found_domain; } } domain = alloc_domain(); if (!domain) goto error; /* Allocate new domain for the device */ drhd = dmar_find_matched_drhd_unit(pdev); if (!drhd) { printk(KERN_ERR "IOMMU: can't find DMAR for device %s\n", pci_name(pdev)); free_domain_mem(domain); return NULL; } iommu = drhd->iommu; ret = iommu_attach_domain(domain, iommu); if (ret) { free_domain_mem(domain); goto error; } if (domain_init(domain, gaw)) { domain_exit(domain); goto error; } /* register pcie-to-pci device */ if (dev_tmp) { info = alloc_devinfo_mem(); if (!info) { domain_exit(domain); goto error; } info->segment = segment; info->bus = bus; info->devfn = devfn; info->dev = NULL; info->domain = domain; /* This domain is shared by devices under p2p bridge */ domain->flags |= DOMAIN_FLAG_P2P_MULTIPLE_DEVICES; /* pcie-to-pci bridge already has a domain, uses it */ found = NULL; spin_lock_irqsave(&device_domain_lock, flags); list_for_each_entry(tmp, &device_domain_list, global) { if (tmp->segment == segment && tmp->bus == bus && tmp->devfn == devfn) { found = tmp->domain; break; } } if (found) { spin_unlock_irqrestore(&device_domain_lock, flags); free_devinfo_mem(info); domain_exit(domain); domain = found; } else { list_add(&info->link, &domain->devices); list_add(&info->global, &device_domain_list); spin_unlock_irqrestore(&device_domain_lock, flags); } } found_domain: info = alloc_devinfo_mem(); if (!info) goto error; info->segment = segment; info->bus = pdev->bus->number; info->devfn = pdev->devfn; info->dev = pdev; info->domain = domain; spin_lock_irqsave(&device_domain_lock, flags); /* somebody is fast */ found = find_domain(pdev); if (found != NULL) { spin_unlock_irqrestore(&device_domain_lock, flags); if (found != domain) { domain_exit(domain); domain = found; } free_devinfo_mem(info); return domain; } list_add(&info->link, &domain->devices); list_add(&info->global, &device_domain_list); pdev->dev.archdata.iommu = info; spin_unlock_irqrestore(&device_domain_lock, flags); return domain; error: /* recheck it here, maybe others set it */ return find_domain(pdev); } static int iommu_identity_mapping; #define IDENTMAP_ALL 1 #define IDENTMAP_GFX 2 #define IDENTMAP_AZALIA 4 static int iommu_domain_identity_map(struct dmar_domain *domain, unsigned long long start, unsigned long long end) { unsigned long first_vpfn = start >> VTD_PAGE_SHIFT; unsigned long last_vpfn = end >> VTD_PAGE_SHIFT; if (!reserve_iova(&domain->iovad, dma_to_mm_pfn(first_vpfn), dma_to_mm_pfn(last_vpfn))) { printk(KERN_ERR "IOMMU: reserve iova failed\n"); return -ENOMEM; } pr_debug("Mapping reserved region %llx-%llx for domain %d\n", start, end, domain->id); /* * RMRR range might have overlap with physical memory range, * clear it first */ dma_pte_clear_range(domain, first_vpfn, last_vpfn); return domain_pfn_mapping(domain, first_vpfn, first_vpfn, last_vpfn - first_vpfn + 1, DMA_PTE_READ|DMA_PTE_WRITE); } static int iommu_prepare_identity_map(struct pci_dev *pdev, unsigned long long start, unsigned long long end) { struct dmar_domain *domain; int ret; domain = get_domain_for_dev(pdev, DEFAULT_DOMAIN_ADDRESS_WIDTH); if (!domain) return -ENOMEM; /* For _hardware_ passthrough, don't bother. But for software passthrough, we do it anyway -- it may indicate a memory range which is reserved in E820, so which didn't get set up to start with in si_domain */ if (domain == si_domain && hw_pass_through) { printk("Ignoring identity map for HW passthrough device %s [0x%Lx - 0x%Lx]\n", pci_name(pdev), start, end); return 0; } printk(KERN_INFO "IOMMU: Setting identity map for device %s [0x%Lx - 0x%Lx]\n", pci_name(pdev), start, end); if (end < start) { WARN(1, "Your BIOS is broken; RMRR ends before it starts!\n" "BIOS vendor: %s; Ver: %s; Product Version: %s\n", dmi_get_system_info(DMI_BIOS_VENDOR), dmi_get_system_info(DMI_BIOS_VERSION), dmi_get_system_info(DMI_PRODUCT_VERSION)); ret = -EIO; goto error; } if (end >> agaw_to_width(domain->agaw)) { WARN(1, "Your BIOS is broken; RMRR exceeds permitted address width (%d bits)\n" "BIOS vendor: %s; Ver: %s; Product Version: %s\n", agaw_to_width(domain->agaw), dmi_get_system_info(DMI_BIOS_VENDOR), dmi_get_system_info(DMI_BIOS_VERSION), dmi_get_system_info(DMI_PRODUCT_VERSION)); ret = -EIO; goto error; } ret = iommu_domain_identity_map(domain, start, end); if (ret) goto error; /* context entry init */ ret = domain_context_mapping(domain, pdev, CONTEXT_TT_MULTI_LEVEL); if (ret) goto error; return 0; error: domain_exit(domain); return ret; } static inline int iommu_prepare_rmrr_dev(struct dmar_rmrr_unit *rmrr, struct pci_dev *pdev) { if (pdev->dev.archdata.iommu == DUMMY_DEVICE_DOMAIN_INFO) return 0; return iommu_prepare_identity_map(pdev, rmrr->base_address, rmrr->end_address); } #ifdef CONFIG_INTEL_IOMMU_FLOPPY_WA static inline void iommu_prepare_isa(void) { struct pci_dev *pdev; int ret; pdev = pci_get_class(PCI_CLASS_BRIDGE_ISA << 8, NULL); if (!pdev) return; printk(KERN_INFO "IOMMU: Prepare 0-16MiB unity mapping for LPC\n"); ret = iommu_prepare_identity_map(pdev, 0, 16*1024*1024 - 1); if (ret) printk(KERN_ERR "IOMMU: Failed to create 0-16MiB identity map; " "floppy might not work\n"); } #else static inline void iommu_prepare_isa(void) { return; } #endif /* !CONFIG_INTEL_IOMMU_FLPY_WA */ static int md_domain_init(struct dmar_domain *domain, int guest_width); static int __init si_domain_init(int hw) { struct dmar_drhd_unit *drhd; struct intel_iommu *iommu; int nid, ret = 0; si_domain = alloc_domain(); if (!si_domain) return -EFAULT; pr_debug("Identity mapping domain is domain %d\n", si_domain->id); for_each_active_iommu(iommu, drhd) { ret = iommu_attach_domain(si_domain, iommu); if (ret) { domain_exit(si_domain); return -EFAULT; } } if (md_domain_init(si_domain, DEFAULT_DOMAIN_ADDRESS_WIDTH)) { domain_exit(si_domain); return -EFAULT; } si_domain->flags = DOMAIN_FLAG_STATIC_IDENTITY; if (hw) return 0; for_each_online_node(nid) { unsigned long start_pfn, end_pfn; int i; for_each_mem_pfn_range(i, nid, &start_pfn, &end_pfn, NULL) { ret = iommu_domain_identity_map(si_domain, PFN_PHYS(start_pfn), PFN_PHYS(end_pfn)); if (ret) return ret; } } return 0; } static void domain_remove_one_dev_info(struct dmar_domain *domain, struct pci_dev *pdev); static int identity_mapping(struct pci_dev *pdev) { struct device_domain_info *info; if (likely(!iommu_identity_mapping)) return 0; info = pdev->dev.archdata.iommu; if (info && info != DUMMY_DEVICE_DOMAIN_INFO) return (info->domain == si_domain); return 0; } static int domain_add_dev_info(struct dmar_domain *domain, struct pci_dev *pdev, int translation) { struct device_domain_info *info; unsigned long flags; int ret; info = alloc_devinfo_mem(); if (!info) return -ENOMEM; info->segment = pci_domain_nr(pdev->bus); info->bus = pdev->bus->number; info->devfn = pdev->devfn; info->dev = pdev; info->domain = domain; spin_lock_irqsave(&device_domain_lock, flags); list_add(&info->link, &domain->devices); list_add(&info->global, &device_domain_list); pdev->dev.archdata.iommu = info; spin_unlock_irqrestore(&device_domain_lock, flags); ret = domain_context_mapping(domain, pdev, translation); if (ret) { spin_lock_irqsave(&device_domain_lock, flags); unlink_domain_info(info); spin_unlock_irqrestore(&device_domain_lock, flags); free_devinfo_mem(info); return ret; } return 0; } static bool device_has_rmrr(struct pci_dev *dev) { struct dmar_rmrr_unit *rmrr; int i; for_each_rmrr_units(rmrr) { for (i = 0; i < rmrr->devices_cnt; i++) { /* * Return TRUE if this RMRR contains the device that * is passed in. */ if (rmrr->devices[i] == dev) return true; } } return false; } static int iommu_should_identity_map(struct pci_dev *pdev, int startup) { /* * We want to prevent any device associated with an RMRR from * getting placed into the SI Domain. This is done because * problems exist when devices are moved in and out of domains * and their respective RMRR info is lost. We exempt USB devices * from this process due to their usage of RMRRs that are known * to not be needed after BIOS hand-off to OS. */ if (device_has_rmrr(pdev) && (pdev->class >> 8) != PCI_CLASS_SERIAL_USB) return 0; if ((iommu_identity_mapping & IDENTMAP_AZALIA) && IS_AZALIA(pdev)) return 1; if ((iommu_identity_mapping & IDENTMAP_GFX) && IS_GFX_DEVICE(pdev)) return 1; if (!(iommu_identity_mapping & IDENTMAP_ALL)) return 0; /* * We want to start off with all devices in the 1:1 domain, and * take them out later if we find they can't access all of memory. * * However, we can't do this for PCI devices behind bridges, * because all PCI devices behind the same bridge will end up * with the same source-id on their transactions. * * Practically speaking, we can't change things around for these * devices at run-time, because we can't be sure there'll be no * DMA transactions in flight for any of their siblings. * * So PCI devices (unless they're on the root bus) as well as * their parent PCI-PCI or PCIe-PCI bridges must be left _out_ of * the 1:1 domain, just in _case_ one of their siblings turns out * not to be able to map all of memory. */ if (!pci_is_pcie(pdev)) { if (!pci_is_root_bus(pdev->bus)) return 0; if (pdev->class >> 8 == PCI_CLASS_BRIDGE_PCI) return 0; } else if (pci_pcie_type(pdev) == PCI_EXP_TYPE_PCI_BRIDGE) return 0; /* * At boot time, we don't yet know if devices will be 64-bit capable. * Assume that they will -- if they turn out not to be, then we can * take them out of the 1:1 domain later. */ if (!startup) { /* * If the device's dma_mask is less than the system's memory * size then this is not a candidate for identity mapping. */ u64 dma_mask = pdev->dma_mask; if (pdev->dev.coherent_dma_mask && pdev->dev.coherent_dma_mask < dma_mask) dma_mask = pdev->dev.coherent_dma_mask; return dma_mask >= dma_get_required_mask(&pdev->dev); } return 1; } static int __init iommu_prepare_static_identity_mapping(int hw) { struct pci_dev *pdev = NULL; int ret; ret = si_domain_init(hw); if (ret) return -EFAULT; for_each_pci_dev(pdev) { if (iommu_should_identity_map(pdev, 1)) { ret = domain_add_dev_info(si_domain, pdev, hw ? CONTEXT_TT_PASS_THROUGH : CONTEXT_TT_MULTI_LEVEL); if (ret) { /* device not associated with an iommu */ if (ret == -ENODEV) continue; return ret; } pr_info("IOMMU: %s identity mapping for device %s\n", hw ? "hardware" : "software", pci_name(pdev)); } } return 0; } static int __init init_dmars(void) { struct dmar_drhd_unit *drhd; struct dmar_rmrr_unit *rmrr; struct pci_dev *pdev; struct intel_iommu *iommu; int i, ret; /* * for each drhd * allocate root * initialize and program root entry to not present * endfor */ for_each_drhd_unit(drhd) { /* * lock not needed as this is only incremented in the single * threaded kernel __init code path all other access are read * only */ if (g_num_of_iommus < IOMMU_UNITS_SUPPORTED) { g_num_of_iommus++; continue; } printk_once(KERN_ERR "intel-iommu: exceeded %d IOMMUs\n", IOMMU_UNITS_SUPPORTED); } g_iommus = kcalloc(g_num_of_iommus, sizeof(struct intel_iommu *), GFP_KERNEL); if (!g_iommus) { printk(KERN_ERR "Allocating global iommu array failed\n"); ret = -ENOMEM; goto error; } deferred_flush = kzalloc(g_num_of_iommus * sizeof(struct deferred_flush_tables), GFP_KERNEL); if (!deferred_flush) { ret = -ENOMEM; goto error; } for_each_drhd_unit(drhd) { if (drhd->ignored) continue; iommu = drhd->iommu; g_iommus[iommu->seq_id] = iommu; ret = iommu_init_domains(iommu); if (ret) goto error; /* * TBD: * we could share the same root & context tables * among all IOMMU's. Need to Split it later. */ ret = iommu_alloc_root_entry(iommu); if (ret) { printk(KERN_ERR "IOMMU: allocate root entry failed\n"); goto error; } if (!ecap_pass_through(iommu->ecap)) hw_pass_through = 0; } /* * Start from the sane iommu hardware state. */ for_each_drhd_unit(drhd) { if (drhd->ignored) continue; iommu = drhd->iommu; /* * If the queued invalidation is already initialized by us * (for example, while enabling interrupt-remapping) then * we got the things already rolling from a sane state. */ if (iommu->qi) continue; /* * Clear any previous faults. */ dmar_fault(-1, iommu); /* * Disable queued invalidation if supported and already enabled * before OS handover. */ dmar_disable_qi(iommu); } for_each_drhd_unit(drhd) { if (drhd->ignored) continue; iommu = drhd->iommu; if (dmar_enable_qi(iommu)) { /* * Queued Invalidate not enabled, use Register Based * Invalidate */ iommu->flush.flush_context = __iommu_flush_context; iommu->flush.flush_iotlb = __iommu_flush_iotlb; printk(KERN_INFO "IOMMU %d 0x%Lx: using Register based " "invalidation\n", iommu->seq_id, (unsigned long long)drhd->reg_base_addr); } else { iommu->flush.flush_context = qi_flush_context; iommu->flush.flush_iotlb = qi_flush_iotlb; printk(KERN_INFO "IOMMU %d 0x%Lx: using Queued " "invalidation\n", iommu->seq_id, (unsigned long long)drhd->reg_base_addr); } } if (iommu_pass_through) iommu_identity_mapping |= IDENTMAP_ALL; #ifdef CONFIG_INTEL_IOMMU_BROKEN_GFX_WA iommu_identity_mapping |= IDENTMAP_GFX; #endif check_tylersburg_isoch(); /* * If pass through is not set or not enabled, setup context entries for * identity mappings for rmrr, gfx, and isa and may fall back to static * identity mapping if iommu_identity_mapping is set. */ if (iommu_identity_mapping) { ret = iommu_prepare_static_identity_mapping(hw_pass_through); if (ret) { printk(KERN_CRIT "Failed to setup IOMMU pass-through\n"); goto error; } } /* * For each rmrr * for each dev attached to rmrr * do * locate drhd for dev, alloc domain for dev * allocate free domain * allocate page table entries for rmrr * if context not allocated for bus * allocate and init context * set present in root table for this bus * init context with domain, translation etc * endfor * endfor */ printk(KERN_INFO "IOMMU: Setting RMRR:\n"); for_each_rmrr_units(rmrr) { for (i = 0; i < rmrr->devices_cnt; i++) { pdev = rmrr->devices[i]; /* * some BIOS lists non-exist devices in DMAR * table. */ if (!pdev) continue; ret = iommu_prepare_rmrr_dev(rmrr, pdev); if (ret) printk(KERN_ERR "IOMMU: mapping reserved region failed\n"); } } iommu_prepare_isa(); /* * for each drhd * enable fault log * global invalidate context cache * global invalidate iotlb * enable translation */ for_each_drhd_unit(drhd) { if (drhd->ignored) { /* * we always have to disable PMRs or DMA may fail on * this device */ if (force_on) iommu_disable_protect_mem_regions(drhd->iommu); continue; } iommu = drhd->iommu; iommu_flush_write_buffer(iommu); ret = dmar_set_interrupt(iommu); if (ret) goto error; iommu_set_root_entry(iommu); iommu->flush.flush_context(iommu, 0, 0, 0, DMA_CCMD_GLOBAL_INVL); iommu->flush.flush_iotlb(iommu, 0, 0, 0, DMA_TLB_GLOBAL_FLUSH); ret = iommu_enable_translation(iommu); if (ret) goto error; iommu_disable_protect_mem_regions(iommu); } return 0; error: for_each_drhd_unit(drhd) { if (drhd->ignored) continue; iommu = drhd->iommu; free_iommu(iommu); } kfree(g_iommus); return ret; } /* This takes a number of _MM_ pages, not VTD pages */ static struct iova *intel_alloc_iova(struct device *dev, struct dmar_domain *domain, unsigned long nrpages, uint64_t dma_mask) { struct pci_dev *pdev = to_pci_dev(dev); struct iova *iova = NULL; /* Restrict dma_mask to the width that the iommu can handle */ dma_mask = min_t(uint64_t, DOMAIN_MAX_ADDR(domain->gaw), dma_mask); if (!dmar_forcedac && dma_mask > DMA_BIT_MASK(32)) { /* * First try to allocate an io virtual address in * DMA_BIT_MASK(32) and if that fails then try allocating * from higher range */ iova = alloc_iova(&domain->iovad, nrpages, IOVA_PFN(DMA_BIT_MASK(32)), 1); if (iova) return iova; } iova = alloc_iova(&domain->iovad, nrpages, IOVA_PFN(dma_mask), 1); if (unlikely(!iova)) { printk(KERN_ERR "Allocating %ld-page iova for %s failed", nrpages, pci_name(pdev)); return NULL; } return iova; } static struct dmar_domain *__get_valid_domain_for_dev(struct pci_dev *pdev) { struct dmar_domain *domain; int ret; domain = get_domain_for_dev(pdev, DEFAULT_DOMAIN_ADDRESS_WIDTH); if (!domain) { printk(KERN_ERR "Allocating domain for %s failed", pci_name(pdev)); return NULL; } /* make sure context mapping is ok */ if (unlikely(!domain_context_mapped(pdev))) { ret = domain_context_mapping(domain, pdev, CONTEXT_TT_MULTI_LEVEL); if (ret) { printk(KERN_ERR "Domain context map for %s failed", pci_name(pdev)); return NULL; } } return domain; } static inline struct dmar_domain *get_valid_domain_for_dev(struct pci_dev *dev) { struct device_domain_info *info; /* No lock here, assumes no domain exit in normal case */ info = dev->dev.archdata.iommu; if (likely(info)) return info->domain; return __get_valid_domain_for_dev(dev); } static int iommu_dummy(struct pci_dev *pdev) { return pdev->dev.archdata.iommu == DUMMY_DEVICE_DOMAIN_INFO; } /* Check if the pdev needs to go through non-identity map and unmap process.*/ static int iommu_no_mapping(struct device *dev) { struct pci_dev *pdev; int found; if (unlikely(dev->bus != &pci_bus_type)) return 1; pdev = to_pci_dev(dev); if (iommu_dummy(pdev)) return 1; if (!iommu_identity_mapping) return 0; found = identity_mapping(pdev); if (found) { if (iommu_should_identity_map(pdev, 0)) return 1; else { /* * 32 bit DMA is removed from si_domain and fall back * to non-identity mapping. */ domain_remove_one_dev_info(si_domain, pdev); printk(KERN_INFO "32bit %s uses non-identity mapping\n", pci_name(pdev)); return 0; } } else { /* * In case of a detached 64 bit DMA device from vm, the device * is put into si_domain for identity mapping. */ if (iommu_should_identity_map(pdev, 0)) { int ret; ret = domain_add_dev_info(si_domain, pdev, hw_pass_through ? CONTEXT_TT_PASS_THROUGH : CONTEXT_TT_MULTI_LEVEL); if (!ret) { printk(KERN_INFO "64bit %s uses identity mapping\n", pci_name(pdev)); return 1; } } } return 0; } static dma_addr_t __intel_map_single(struct device *hwdev, phys_addr_t paddr, size_t size, int dir, u64 dma_mask) { struct pci_dev *pdev = to_pci_dev(hwdev); struct dmar_domain *domain; phys_addr_t start_paddr; struct iova *iova; int prot = 0; int ret; struct intel_iommu *iommu; unsigned long paddr_pfn = paddr >> PAGE_SHIFT; BUG_ON(dir == DMA_NONE); if (iommu_no_mapping(hwdev)) return paddr; domain = get_valid_domain_for_dev(pdev); if (!domain) return 0; iommu = domain_get_iommu(domain); size = aligned_nrpages(paddr, size); iova = intel_alloc_iova(hwdev, domain, dma_to_mm_pfn(size), dma_mask); if (!iova) goto error; /* * Check if DMAR supports zero-length reads on write only * mappings.. */ if (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL || \ !cap_zlr(iommu->cap)) prot |= DMA_PTE_READ; if (dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL) prot |= DMA_PTE_WRITE; /* * paddr - (paddr + size) might be partial page, we should map the whole * page. Note: if two part of one page are separately mapped, we * might have two guest_addr mapping to the same host paddr, but this * is not a big problem */ ret = domain_pfn_mapping(domain, mm_to_dma_pfn(iova->pfn_lo), mm_to_dma_pfn(paddr_pfn), size, prot); if (ret) goto error; /* it's a non-present to present mapping. Only flush if caching mode */ if (cap_caching_mode(iommu->cap)) iommu_flush_iotlb_psi(iommu, domain->id, mm_to_dma_pfn(iova->pfn_lo), size, 1); else iommu_flush_write_buffer(iommu); start_paddr = (phys_addr_t)iova->pfn_lo << PAGE_SHIFT; start_paddr += paddr & ~PAGE_MASK; return start_paddr; error: if (iova) __free_iova(&domain->iovad, iova); printk(KERN_ERR"Device %s request: %zx@%llx dir %d --- failed\n", pci_name(pdev), size, (unsigned long long)paddr, dir); return 0; } static dma_addr_t intel_map_page(struct device *dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction dir, struct dma_attrs *attrs) { return __intel_map_single(dev, page_to_phys(page) + offset, size, dir, to_pci_dev(dev)->dma_mask); } static void flush_unmaps(void) { int i, j; timer_on = 0; /* just flush them all */ for (i = 0; i < g_num_of_iommus; i++) { struct intel_iommu *iommu = g_iommus[i]; if (!iommu) continue; if (!deferred_flush[i].next) continue; /* In caching mode, global flushes turn emulation expensive */ if (!cap_caching_mode(iommu->cap)) iommu->flush.flush_iotlb(iommu, 0, 0, 0, DMA_TLB_GLOBAL_FLUSH); for (j = 0; j < deferred_flush[i].next; j++) { unsigned long mask; struct iova *iova = deferred_flush[i].iova[j]; struct dmar_domain *domain = deferred_flush[i].domain[j]; /* On real hardware multiple invalidations are expensive */ if (cap_caching_mode(iommu->cap)) iommu_flush_iotlb_psi(iommu, domain->id, iova->pfn_lo, iova->pfn_hi - iova->pfn_lo + 1, 0); else { mask = ilog2(mm_to_dma_pfn(iova->pfn_hi - iova->pfn_lo + 1)); iommu_flush_dev_iotlb(deferred_flush[i].domain[j], (uint64_t)iova->pfn_lo << PAGE_SHIFT, mask); } __free_iova(&deferred_flush[i].domain[j]->iovad, iova); } deferred_flush[i].next = 0; } list_size = 0; } static void flush_unmaps_timeout(unsigned long data) { unsigned long flags; spin_lock_irqsave(&async_umap_flush_lock, flags); flush_unmaps(); spin_unlock_irqrestore(&async_umap_flush_lock, flags); } static void add_unmap(struct dmar_domain *dom, struct iova *iova) { unsigned long flags; int next, iommu_id; struct intel_iommu *iommu; spin_lock_irqsave(&async_umap_flush_lock, flags); if (list_size == HIGH_WATER_MARK) flush_unmaps(); iommu = domain_get_iommu(dom); iommu_id = iommu->seq_id; next = deferred_flush[iommu_id].next; deferred_flush[iommu_id].domain[next] = dom; deferred_flush[iommu_id].iova[next] = iova; deferred_flush[iommu_id].next++; if (!timer_on) { mod_timer(&unmap_timer, jiffies + msecs_to_jiffies(10)); timer_on = 1; } list_size++; spin_unlock_irqrestore(&async_umap_flush_lock, flags); } static void intel_unmap_page(struct device *dev, dma_addr_t dev_addr, size_t size, enum dma_data_direction dir, struct dma_attrs *attrs) { struct pci_dev *pdev = to_pci_dev(dev); struct dmar_domain *domain; unsigned long start_pfn, last_pfn; struct iova *iova; struct intel_iommu *iommu; if (iommu_no_mapping(dev)) return; domain = find_domain(pdev); BUG_ON(!domain); iommu = domain_get_iommu(domain); iova = find_iova(&domain->iovad, IOVA_PFN(dev_addr)); if (WARN_ONCE(!iova, "Driver unmaps unmatched page at PFN %llx\n", (unsigned long long)dev_addr)) return; start_pfn = mm_to_dma_pfn(iova->pfn_lo); last_pfn = mm_to_dma_pfn(iova->pfn_hi + 1) - 1; pr_debug("Device %s unmapping: pfn %lx-%lx\n", pci_name(pdev), start_pfn, last_pfn); /* clear the whole page */ dma_pte_clear_range(domain, start_pfn, last_pfn); /* free page tables */ dma_pte_free_pagetable(domain, start_pfn, last_pfn); if (intel_iommu_strict) { iommu_flush_iotlb_psi(iommu, domain->id, start_pfn, last_pfn - start_pfn + 1, 0); /* free iova */ __free_iova(&domain->iovad, iova); } else { add_unmap(domain, iova); /* * queue up the release of the unmap to save the 1/6th of the * cpu used up by the iotlb flush operation... */ } } static void *intel_alloc_coherent(struct device *hwdev, size_t size, dma_addr_t *dma_handle, gfp_t flags, struct dma_attrs *attrs) { void *vaddr; int order; size = PAGE_ALIGN(size); order = get_order(size); if (!iommu_no_mapping(hwdev)) flags &= ~(GFP_DMA | GFP_DMA32); else if (hwdev->coherent_dma_mask < dma_get_required_mask(hwdev)) { if (hwdev->coherent_dma_mask < DMA_BIT_MASK(32)) flags |= GFP_DMA; else flags |= GFP_DMA32; } vaddr = (void *)__get_free_pages(flags, order); if (!vaddr) return NULL; memset(vaddr, 0, size); *dma_handle = __intel_map_single(hwdev, virt_to_bus(vaddr), size, DMA_BIDIRECTIONAL, hwdev->coherent_dma_mask); if (*dma_handle) return vaddr; free_pages((unsigned long)vaddr, order); return NULL; } static void intel_free_coherent(struct device *hwdev, size_t size, void *vaddr, dma_addr_t dma_handle, struct dma_attrs *attrs) { int order; size = PAGE_ALIGN(size); order = get_order(size); intel_unmap_page(hwdev, dma_handle, size, DMA_BIDIRECTIONAL, NULL); free_pages((unsigned long)vaddr, order); } static void intel_unmap_sg(struct device *hwdev, struct scatterlist *sglist, int nelems, enum dma_data_direction dir, struct dma_attrs *attrs) { struct pci_dev *pdev = to_pci_dev(hwdev); struct dmar_domain *domain; unsigned long start_pfn, last_pfn; struct iova *iova; struct intel_iommu *iommu; if (iommu_no_mapping(hwdev)) return; domain = find_domain(pdev); BUG_ON(!domain); iommu = domain_get_iommu(domain); iova = find_iova(&domain->iovad, IOVA_PFN(sglist[0].dma_address)); if (WARN_ONCE(!iova, "Driver unmaps unmatched sglist at PFN %llx\n", (unsigned long long)sglist[0].dma_address)) return; start_pfn = mm_to_dma_pfn(iova->pfn_lo); last_pfn = mm_to_dma_pfn(iova->pfn_hi + 1) - 1; /* clear the whole page */ dma_pte_clear_range(domain, start_pfn, last_pfn); /* free page tables */ dma_pte_free_pagetable(domain, start_pfn, last_pfn); if (intel_iommu_strict) { iommu_flush_iotlb_psi(iommu, domain->id, start_pfn, last_pfn - start_pfn + 1, 0); /* free iova */ __free_iova(&domain->iovad, iova); } else { add_unmap(domain, iova); /* * queue up the release of the unmap to save the 1/6th of the * cpu used up by the iotlb flush operation... */ } } static int intel_nontranslate_map_sg(struct device *hddev, struct scatterlist *sglist, int nelems, int dir) { int i; struct scatterlist *sg; for_each_sg(sglist, sg, nelems, i) { BUG_ON(!sg_page(sg)); sg->dma_address = page_to_phys(sg_page(sg)) + sg->offset; sg->dma_length = sg->length; } return nelems; } static int intel_map_sg(struct device *hwdev, struct scatterlist *sglist, int nelems, enum dma_data_direction dir, struct dma_attrs *attrs) { int i; struct pci_dev *pdev = to_pci_dev(hwdev); struct dmar_domain *domain; size_t size = 0; int prot = 0; struct iova *iova = NULL; int ret; struct scatterlist *sg; unsigned long start_vpfn; struct intel_iommu *iommu; BUG_ON(dir == DMA_NONE); if (iommu_no_mapping(hwdev)) return intel_nontranslate_map_sg(hwdev, sglist, nelems, dir); domain = get_valid_domain_for_dev(pdev); if (!domain) return 0; iommu = domain_get_iommu(domain); for_each_sg(sglist, sg, nelems, i) size += aligned_nrpages(sg->offset, sg->length);