summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/i915/gt/intel_rps.c
blob: e6a00eea063169e0c396f793ed5e585052d0237f (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
/*
 * SPDX-License-Identifier: MIT
 *
 * Copyright © 2019 Intel Corporation
 */

#include <drm/i915_drm.h>

#include "i915_drv.h"
#include "intel_breadcrumbs.h"
#include "intel_gt.h"
#include "intel_gt_clock_utils.h"
#include "intel_gt_irq.h"
#include "intel_gt_pm_irq.h"
#include "intel_rps.h"
#include "intel_sideband.h"
#include "../../../platform/x86/intel_ips.h"

#define BUSY_MAX_EI	20u /* ms */

/*
 * Lock protecting IPS related data structures
 */
static DEFINE_SPINLOCK(mchdev_lock);

static struct intel_gt *rps_to_gt(struct intel_rps *rps)
{
	return container_of(rps, struct intel_gt, rps);
}

static struct drm_i915_private *rps_to_i915(struct intel_rps *rps)
{
	return rps_to_gt(rps)->i915;
}

static struct intel_uncore *rps_to_uncore(struct intel_rps *rps)
{
	return rps_to_gt(rps)->uncore;
}

static u32 rps_pm_sanitize_mask(struct intel_rps *rps, u32 mask)
{
	return mask & ~rps->pm_intrmsk_mbz;
}

static inline void set(struct intel_uncore *uncore, i915_reg_t reg, u32 val)
{
	intel_uncore_write_fw(uncore, reg, val);
}

static void rps_timer(struct timer_list *t)
{
	struct intel_rps *rps = from_timer(rps, t, timer);
	struct intel_engine_cs *engine;
	ktime_t dt, last, timestamp;
	enum intel_engine_id id;
	s64 max_busy[3] = {};

	timestamp = 0;
	for_each_engine(engine, rps_to_gt(rps), id) {
		s64 busy;
		int i;

		dt = intel_engine_get_busy_time(engine, &timestamp);
		last = engine->stats.rps;
		engine->stats.rps = dt;

		busy = ktime_to_ns(ktime_sub(dt, last));
		for (i = 0; i < ARRAY_SIZE(max_busy); i++) {
			if (busy > max_busy[i])
				swap(busy, max_busy[i]);
		}
	}
	last = rps->pm_timestamp;
	rps->pm_timestamp = timestamp;

	if (intel_rps_is_active(rps)) {
		s64 busy;
		int i;

		dt = ktime_sub(timestamp, last);

		/*
		 * Our goal is to evaluate each engine independently, so we run
		 * at the lowest clocks required to sustain the heaviest
		 * workload. However, a task may be split into sequential
		 * dependent operations across a set of engines, such that
		 * the independent contributions do not account for high load,
		 * but overall the task is GPU bound. For example, consider
		 * video decode on vcs followed by colour post-processing
		 * on vecs, followed by general post-processing on rcs.
		 * Since multi-engines being active does imply a single
		 * continuous workload across all engines, we hedge our
		 * bets by only contributing a factor of the distributed
		 * load into our busyness calculation.
		 */
		busy = max_busy[0];
		for (i = 1; i < ARRAY_SIZE(max_busy); i++) {
			if (!max_busy[i])
				break;

			busy += div_u64(max_busy[i], 1 << i);
		}
		GT_TRACE(rps_to_gt(rps),
			 "busy:%lld [%d%%], max:[%lld, %lld, %lld], interval:%d\n",
			 busy, (int)div64_u64(100 * busy, dt),
			 max_busy[0], max_busy[1], max_busy[2],
			 rps->pm_interval);

		if (100 * busy > rps->power.up_threshold * dt &&
		    rps->cur_freq < rps->max_freq_softlimit) {
			rps->pm_iir |= GEN6_PM_RP_UP_THRESHOLD;
			rps->pm_interval = 1;
			schedule_work(&rps->work);
		} else if (100 * busy < rps->power.down_threshold * dt &&
			   rps->cur_freq > rps->min_freq_softlimit) {
			rps->pm_iir |= GEN6_PM_RP_DOWN_THRESHOLD;
			rps->pm_interval = 1;
			schedule_work(&rps->work);
		} else {
			rps->last_adj = 0;
		}

		mod_timer(&rps->timer,
			  jiffies + msecs_to_jiffies(rps->pm_interval));
		rps->pm_interval = min(rps->pm_interval * 2, BUSY_MAX_EI);
	}
}

static void rps_start_timer(struct intel_rps *rps)
{
	rps->pm_timestamp = ktime_sub(ktime_get(), rps->pm_timestamp);
	rps->pm_interval = 1;
	mod_timer(&rps->timer, jiffies + 1);
}

static void rps_stop_timer(struct intel_rps *rps)
{
	del_timer_sync(&rps->timer);
	rps->pm_timestamp = ktime_sub(ktime_get(), rps->pm_timestamp);
	cancel_work_sync(&rps->work);
}

static u32 rps_pm_mask(struct intel_rps *rps, u8 val)
{
	u32 mask = 0;

	/* We use UP_EI_EXPIRED interrupts for both up/down in manual mode */
	if (val > rps->min_freq_softlimit)
		mask |= (GEN6_PM_RP_UP_EI_EXPIRED |
			 GEN6_PM_RP_DOWN_THRESHOLD |
			 GEN6_PM_RP_DOWN_TIMEOUT);

	if (val < rps->max_freq_softlimit)
		mask |= GEN6_PM_RP_UP_EI_EXPIRED | GEN6_PM_RP_UP_THRESHOLD;

	mask &= rps->pm_events;

	return rps_pm_sanitize_mask(rps, ~mask);
}

static void rps_reset_ei(struct intel_rps *rps)
{
	memset(&rps->ei, 0, sizeof(rps->ei));
}

static void rps_enable_interrupts(struct intel_rps *rps)
{
	struct intel_gt *gt = rps_to_gt(rps);

	GT_TRACE(gt, "interrupts:on rps->pm_events: %x, rps_pm_mask:%x\n",
		 rps->pm_events, rps_pm_mask(rps, rps->last_freq));

	rps_reset_ei(rps);

	spin_lock_irq(&gt->irq_lock);
	gen6_gt_pm_enable_irq(gt, rps->pm_events);
	spin_unlock_irq(&gt->irq_lock);

	intel_uncore_write(gt->uncore,
			   GEN6_PMINTRMSK, rps_pm_mask(rps, rps->last_freq));
}

static void gen6_rps_reset_interrupts(struct intel_rps *rps)
{
	gen6_gt_pm_reset_iir(rps_to_gt(rps), GEN6_PM_RPS_EVENTS);
}

static void gen11_rps_reset_interrupts(struct intel_rps *rps)
{
	while (gen11_gt_reset_one_iir(rps_to_gt(rps), 0, GEN11_GTPM))
		;
}

static void rps_reset_interrupts(struct intel_rps *rps)
{
	struct intel_gt *gt = rps_to_gt(rps);

	spin_lock_irq(&gt->irq_lock);
	if (INTEL_GEN(gt->i915) >= 11)
		gen11_rps_reset_interrupts(rps);
	else
		gen6_rps_reset_interrupts(rps);

	rps->pm_iir = 0;
	spin_unlock_irq(&gt->irq_lock);
}

static void rps_disable_interrupts(struct intel_rps *rps)
{
	struct intel_gt *gt = rps_to_gt(rps);

	intel_uncore_write(gt->uncore,
			   GEN6_PMINTRMSK, rps_pm_sanitize_mask(rps, ~0u));

	spin_lock_irq(&gt->irq_lock);
	gen6_gt_pm_disable_irq(gt, GEN6_PM_RPS_EVENTS);
	spin_unlock_irq(&gt->irq_lock);

	intel_synchronize_irq(gt->i915);

	/*
	 * Now that we will not be generating any more work, flush any
	 * outstanding tasks. As we are called on the RPS idle path,
	 * we will reset the GPU to minimum frequencies, so the current
	 * state of the worker can be discarded.
	 */
	cancel_work_sync(&rps->work);

	rps_reset_interrupts(rps);
	GT_TRACE(gt, "interrupts:off\n");
}

static const struct cparams {
	u16 i;
	u16 t;
	u16 m;
	u16 c;
} cparams[] = {
	{ 1, 1333, 301, 28664 },
	{ 1, 1066, 294, 24460 },
	{ 1, 800, 294, 25192 },
	{ 0, 1333, 276, 27605 },
	{ 0, 1066, 276, 27605 },
	{ 0, 800, 231, 23784 },
};

static void gen5_rps_init(struct intel_rps *rps)
{
	struct drm_i915_private *i915 = rps_to_i915(rps);
	struct intel_uncore *uncore = rps_to_uncore(rps);
	u8 fmax, fmin, fstart;
	u32 rgvmodectl;
	int c_m, i;

	if (i915->fsb_freq <= 3200)
		c_m = 0;
	else if (i915->fsb_freq <= 4800)
		c_m = 1;
	else
		c_m = 2;

	for (i = 0; i < ARRAY_SIZE(cparams); i++) {
		if (cparams[i].i == c_m && cparams[i].t == i915->mem_freq) {
			rps->ips.m = cparams[i].m;
			rps->ips.c = cparams[i].c;
			break;
		}
	}

	rgvmodectl = intel_uncore_read(uncore, MEMMODECTL);

	/* Set up min, max, and cur for interrupt handling */
	fmax = (rgvmodectl & MEMMODE_FMAX_MASK) >> MEMMODE_FMAX_SHIFT;
	fmin = (rgvmodectl & MEMMODE_FMIN_MASK);
	fstart = (rgvmodectl & MEMMODE_FSTART_MASK) >>
		MEMMODE_FSTART_SHIFT;
	drm_dbg(&i915->drm, "fmax: %d, fmin: %d, fstart: %d\n",
		fmax, fmin, fstart);

	rps->min_freq = fmax;
	rps->efficient_freq = fstart;
	rps->max_freq = fmin;
}

static unsigned long
__ips_chipset_val(struct intel_ips *ips)
{
	struct intel_uncore *uncore =
		rps_to_uncore(container_of(ips, struct intel_rps, ips));
	unsigned long now = jiffies_to_msecs(jiffies), dt;
	unsigned long result;
	u64 total, delta;

	lockdep_assert_held(&mchdev_lock);

	/*
	 * Prevent division-by-zero if we are asking too fast.
	 * Also, we don't get interesting results if we are polling
	 * faster than once in 10ms, so just return the saved value
	 * in such cases.
	 */
	dt = now - ips->last_time1;
	if (dt <= 10)
		return ips->chipset_power;

	/* FIXME: handle per-counter overflow */
	total = intel_uncore_read(uncore, DMIEC);
	total += intel_uncore_read(uncore, DDREC);
	total += intel_uncore_read(uncore, CSIEC);

	delta = total - ips->last_count1;

	result = div_u64(div_u64(ips->m * delta, dt) + ips->c, 10);

	ips->last_count1 = total;
	ips->last_time1 = now;

	ips->chipset_power = result;

	return result;
}

static unsigned long ips_mch_val(struct intel_uncore *uncore)
{
	unsigned int m, x, b;
	u32 tsfs;

	tsfs = intel_uncore_read(uncore, TSFS);
	x = intel_uncore_read8(uncore, TR1);

	b = tsfs & TSFS_INTR_MASK;
	m = (tsfs & TSFS_SLOPE_MASK) >> TSFS_SLOPE_SHIFT;

	return m * x / 127 - b;
}

static int _pxvid_to_vd(u8 pxvid)
{
	if (pxvid == 0)
		return 0;

	if (pxvid >= 8 && pxvid < 31)
		pxvid = 31;

	return (pxvid + 2) * 125;
}

static u32 pvid_to_extvid(struct drm_i915_private *i915, u8 pxvid)
{
	const int vd = _pxvid_to_vd(pxvid);

	if (INTEL_INFO(i915)->is_mobile)
		return max(vd - 1125, 0);

	return vd;
}

static void __gen5_ips_update(struct intel_ips *ips)
{
	struct intel_uncore *uncore =
		rps_to_uncore(container_of(ips, struct intel_rps, ips));
	u64 now, delta, dt;
	u32 count;

	lockdep_assert_held(&mchdev_lock);

	now = ktime_get_raw_ns();
	dt = now - ips->last_time2;
	do_div(dt, NSEC_PER_MSEC);

	/* Don't divide by 0 */
	if (dt <= 10)
		return;

	count = intel_uncore_read(uncore, GFXEC);
	delta = count - ips->last_count2;

	ips->last_count2 = count;
	ips->last_time2 = now;

	/* More magic constants... */
	ips->gfx_power = div_u64(delta * 1181, dt * 10);
}

static void gen5_rps_update(struct intel_rps *rps)
{
	spin_lock_irq(&mchdev_lock);
	__gen5_ips_update(&rps->ips);
	spin_unlock_irq(&mchdev_lock);
}

static bool gen5_rps_set(struct intel_rps *rps, u8 val)
{
	struct intel_uncore *uncore = rps_to_uncore(rps);
	u16 rgvswctl;

	lockdep_assert_held(&mchdev_lock);

	rgvswctl = intel_uncore_read16(uncore, MEMSWCTL);
	if (rgvswctl & MEMCTL_CMD_STS) {
		DRM_DEBUG("gpu busy, RCS change rejected\n");
		return false; /* still busy with another command */
	}

	/* Invert the frequency bin into an ips delay */
	val = rps->max_freq - val;
	val = rps->min_freq + val;

	rgvswctl =
		(MEMCTL_CMD_CHFREQ << MEMCTL_CMD_SHIFT) |
		(val << MEMCTL_FREQ_SHIFT) |
		MEMCTL_SFCAVM;
	intel_uncore_write16(uncore, MEMSWCTL, rgvswctl);
	intel_uncore_posting_read16(uncore, MEMSWCTL);

	rgvswctl |= MEMCTL_CMD_STS;
	intel_uncore_write16(uncore, MEMSWCTL, rgvswctl);

	return true;
}

static unsigned long intel_pxfreq(u32 vidfreq)
{
	int div = (vidfreq & 0x3f0000) >> 16;
	int post = (vidfreq & 0x3000) >> 12;
	int pre = (vidfreq & 0x7);

	if (!pre)
		return 0;

	return div * 133333 / (pre << post);
}

static unsigned int init_emon(struct intel_uncore *uncore)
{
	u8 pxw[16];
	int i;

	/* Disable to program */
	intel_uncore_write(uncore, ECR, 0);
	intel_uncore_posting_read(uncore, ECR);

	/* Program energy weights for various events */
	intel_uncore_write(uncore, SDEW, 0x15040d00);
	intel_uncore_write(uncore, CSIEW0, 0x007f0000);
	intel_uncore_write(uncore, CSIEW1, 0x1e220004);
	intel_uncore_write(uncore, CSIEW2, 0x04000004);

	for (i = 0; i < 5; i++)
		intel_uncore_write(uncore, PEW(i), 0);
	for (i = 0; i < 3; i++)
		intel_uncore_write(uncore, DEW(i), 0);

	/* Program P-state weights to account for frequency power adjustment */
	for (i = 0; i < 16; i++) {
		u32 pxvidfreq = intel_uncore_read(uncore, PXVFREQ(i));
		unsigned int freq = intel_pxfreq(pxvidfreq);
		unsigned int vid =
			(pxvidfreq & PXVFREQ_PX_MASK) >> PXVFREQ_PX_SHIFT;
		unsigned int val;

		val = vid * vid * freq / 1000 * 255;
		val /= 127 * 127 * 900;

		pxw[i] = val;
	}
	/* Render standby states get 0 weight */
	pxw[14] = 0;
	pxw[15] = 0;

	for (i = 0; i < 4; i++) {
		intel_uncore_write(uncore, PXW(i),
				   pxw[i * 4 + 0] << 24 |
				   pxw[i * 4 + 1] << 16 |
				   pxw[i * 4 + 2] <<  8 |
				   pxw[i * 4 + 3] <<  0);
	}

	/* Adjust magic regs to magic values (more experimental results) */
	intel_uncore_write(uncore, OGW0, 0);
	intel_uncore_write(uncore, OGW1, 0);
	intel_uncore_write(uncore, EG0, 0x00007f00);
	intel_uncore_write(uncore, EG1, 0x0000000e);
	intel_uncore_write(uncore, EG2, 0x000e0000);
	intel_uncore_write(uncore, EG3, 0x68000300);
	intel_uncore_write(uncore, EG4, 0x42000000);
	intel_uncore_write(uncore, EG5, 0x00140031);
	intel_uncore_write(uncore, EG6, 0);
	intel_uncore_write(uncore, EG7, 0);

	for (i = 0; i < 8; i++)
		intel_uncore_write(uncore, PXWL(i), 0);

	/* Enable PMON + select events */
	intel_uncore_write(uncore, ECR, 0x80000019);

	return intel_uncore_read(uncore, LCFUSE02) & LCFUSE_HIV_MASK;
}

static bool gen5_rps_enable(struct intel_rps *rps)
{
	struct intel_uncore *uncore = rps_to_uncore(rps);
	u8 fstart, vstart;
	u32 rgvmodectl;

	spin_lock_irq(&mchdev_lock);

	rgvmodectl = intel_uncore_read(uncore, MEMMODECTL);

	/* Enable temp reporting */
	intel_uncore_write16(uncore, PMMISC,
			     intel_uncore_read16(uncore, PMMISC) | MCPPCE_EN);
	intel_uncore_write16(uncore, TSC1,
			     intel_uncore_read16(uncore, TSC1) | TSE);

	/* 100ms RC evaluation intervals */
	intel_uncore_write(uncore, RCUPEI, 100000);
	intel_uncore_write(uncore, RCDNEI, 100000);

	/* Set max/min thresholds to 90ms and 80ms respectively */
	intel_uncore_write(uncore, RCBMAXAVG, 90000);
	intel_uncore_write(uncore, RCBMINAVG, 80000);

	intel_uncore_write(uncore, MEMIHYST, 1);

	/* Set up min, max, and cur for interrupt handling */
	fstart = (rgvmodectl & MEMMODE_FSTART_MASK) >>
		MEMMODE_FSTART_SHIFT;

	vstart = (intel_uncore_read(uncore, PXVFREQ(fstart)) &
		  PXVFREQ_PX_MASK) >> PXVFREQ_PX_SHIFT;

	intel_uncore_write(uncore,
			   MEMINTREN,
			   MEMINT_CX_SUPR_EN | MEMINT_EVAL_CHG_EN);

	intel_uncore_write(uncore, VIDSTART, vstart);
	intel_uncore_posting_read(uncore, VIDSTART);

	rgvmodectl |= MEMMODE_SWMODE_EN;
	intel_uncore_write(uncore, MEMMODECTL, rgvmodectl);

	if (wait_for_atomic((intel_uncore_read(uncore, MEMSWCTL) &
			     MEMCTL_CMD_STS) == 0, 10))
		drm_err(&uncore->i915->drm,
			"stuck trying to change perf mode\n");
	mdelay(1);

	gen5_rps_set(rps, rps->cur_freq);

	rps->ips.last_count1 = intel_uncore_read(uncore, DMIEC);
	rps->ips.last_count1 += intel_uncore_read(uncore, DDREC);
	rps->ips.last_count1 += intel_uncore_read(uncore, CSIEC);
	rps->ips.last_time1 = jiffies_to_msecs(jiffies);

	rps->ips.last_count2 = intel_uncore_read(uncore, GFXEC);
	rps->ips.last_time2 = ktime_get_raw_ns();

	spin_unlock_irq(&mchdev_lock);

	rps->ips.corr = init_emon(uncore);

	return true;
}

static void gen5_rps_disable(struct intel_rps *rps)
{
	struct intel_uncore *uncore = rps_to_uncore(rps);
	u16 rgvswctl;

	spin_lock_irq(&mchdev_lock);

	rgvswctl = intel_uncore_read16(uncore, MEMSWCTL);

	/* Ack interrupts, disable EFC interrupt */
	intel_uncore_write(uncore, MEMINTREN,
			   intel_uncore_read(uncore, MEMINTREN) &
			   ~MEMINT_EVAL_CHG_EN);
	intel_uncore_write(uncore, MEMINTRSTS, MEMINT_EVAL_CHG);
	intel_uncore_write(uncore, DEIER,
			   intel_uncore_read(uncore, DEIER) & ~DE_PCU_EVENT);
	intel_uncore_write(uncore, DEIIR, DE_PCU_EVENT);
	intel_uncore_write(uncore, DEIMR,
			   intel_uncore_read(uncore, DEIMR) | DE_PCU_EVENT);

	/* Go back to the starting frequency */
	gen5_rps_set(rps, rps->idle_freq);
	mdelay(1);
	rgvswctl |= MEMCTL_CMD_STS;
	intel_uncore_write(uncore, MEMSWCTL, rgvswctl);
	mdelay(1);

	spin_unlock_irq(&mchdev_lock);
}

static u32 rps_limits(struct intel_rps *rps, u8 val)
{
	u32 limits;

	/*
	 * Only set the down limit when we've reached the lowest level to avoid
	 * getting more interrupts, otherwise leave this clear. This prevents a
	 * race in the hw when coming out of rc6: There's a tiny window where
	 * the hw runs at the minimal clock before selecting the desired
	 * frequency, if the down threshold expires in that window we will not
	 * receive a down interrupt.
	 */
	if (INTEL_GEN(rps_to_i915(rps)) >= 9) {
		limits = rps->max_freq_softlimit << 23;
		if (val <= rps->min_freq_softlimit)
			limits |= rps->min_freq_softlimit << 14;
	} else {
		limits = rps->max_freq_softlimit << 24;
		if (val <= rps->min_freq_softlimit)
			limits |= rps->min_freq_softlimit << 16;
	}

	return limits;
}

static void rps_set_power(struct intel_rps *rps, int new_power)
{
	struct intel_gt *gt = rps_to_gt(rps);
	struct intel_uncore *uncore = gt->uncore;
	u32 threshold_up = 0, threshold_down = 0; /* in % */
	u32 ei_up = 0, ei_down = 0;

	lockdep_assert_held(&rps->power.mutex);

	if (new_power == rps->power.mode)
		return;

	threshold_up = 95;
	threshold_down = 85;

	/* Note the units here are not exactly 1us, but 1280ns. */
	switch (new_power) {
	case LOW_POWER:
		ei_up = 16000;
		ei_down = 32000;
		break;

	case BETWEEN:
		ei_up = 13000;
		ei_down = 32000;
		break;

	case HIGH_POWER:
		ei_up = 10000;
		ei_down = 32000;
		break;
	}

	/* When byt can survive without system hang with dynamic
	 * sw freq adjustments, this restriction can be lifted.
	 */
	if (IS_VALLEYVIEW(gt->i915))
		goto skip_hw_write;

	GT_TRACE(gt,
		 "changing power mode [%d], up %d%% @ %dus, down %d%% @ %dus\n",
		 new_power, threshold_up, ei_up, threshold_down, ei_down);

	set(uncore, GEN6_RP_UP_EI,
	    intel_gt_ns_to_pm_interval(gt, ei_up * 1000));
	set(uncore, GEN6_RP_UP_THRESHOLD,
	    intel_gt_ns_to_pm_interval(gt, ei_up * threshold_up * 10));

	set(uncore, GEN6_RP_DOWN_EI,
	    intel_gt_ns_to_pm_interval(gt, ei_down * 1000));
	set(uncore, GEN6_RP_DOWN_THRESHOLD,
	    intel_gt_ns_to_pm_interval(gt, ei_down * threshold_down * 10));

	set(uncore, GEN6_RP_CONTROL,
	    (INTEL_GEN(gt->i915) > 9 ? 0 : GEN6_RP_MEDIA_TURBO) |
	    GEN6_RP_MEDIA_HW_NORMAL_MODE |
	    GEN6_RP_MEDIA_IS_GFX |
	    GEN6_RP_ENABLE |
	    GEN6_RP_UP_BUSY_AVG |
	    GEN6_RP_DOWN_IDLE_AVG);

skip_hw_write:
	rps->power.mode = new_power;
	rps->power.up_threshold = threshold_up;
	rps->power.down_threshold = threshold_down;
}

static void gen6_rps_set_thresholds(struct intel_rps *rps, u8 val)
{
	int new_power;

	new_power = rps->power.mode;
	switch (rps->power.mode) {
	case LOW_POWER:
		if (val > rps->efficient_freq + 1 &&
		    val > rps->cur_freq)
			new_power = BETWEEN;
		break;

	case BETWEEN:
		if (val <= rps->efficient_freq &&
		    val < rps->cur_freq)
			new_power = LOW_POWER;
		else if (val >= rps->rp0_freq &&
			 val > rps->cur_freq)
			new_power = HIGH_POWER;
		break;

	case HIGH_POWER:
		if (val < (rps->rp1_freq + rps->rp0_freq) >> 1 &&
		    val < rps->cur_freq)
			new_power = BETWEEN;
		break;
	}
	/* Max/min bins are special */
	if (val <= rps->min_freq_softlimit)
		new_power = LOW_POWER;
	if (val >= rps->max_freq_softlimit)
		new_power = HIGH_POWER;

	mutex_lock(&rps->power.mutex);
	if (rps->power.interactive)
		new_power = HIGH_POWER;
	rps_set_power(rps, new_power);
	mutex_unlock(&rps->power.mutex);
}

void intel_rps_mark_interactive(struct intel_rps *rps, bool interactive)
{
	GT_TRACE(rps_to_gt(rps), "mark interactive: %s\n", yesno(interactive));

	mutex_lock(&rps->power.mutex);
	if (interactive) {
		if (!rps->power.interactive++ && intel_rps_is_active(rps))
			rps_set_power(rps, HIGH_POWER);
	} else {
		GEM_BUG_ON(!rps->power.interactive);
		rps->power.interactive--;
	}
	mutex_unlock(&rps->power.mutex);
}

static int gen6_rps_set(struct intel_rps *rps, u8 val)
{
	struct intel_uncore *uncore = rps_to_uncore(rps);
	struct drm_i915_private *i915 = rps_to_i915(rps);
	u32 swreq;

	if (INTEL_GEN(i915) >= 9)
		swreq = GEN9_FREQUENCY(val);
	else if (IS_HASWELL(i915) || IS_BROADWELL(i915))
		swreq = HSW_FREQUENCY(val);
	else
		swreq = (GEN6_FREQUENCY(val) |
			 GEN6_OFFSET(0) |
			 GEN6_AGGRESSIVE_TURBO);
	set(uncore, GEN6_RPNSWREQ, swreq);

	GT_TRACE(rps_to_gt(rps), "set val:%x, freq:%d, swreq:%x\n",
		 val, intel_gpu_freq(rps, val), swreq);

	return 0;
}

static int vlv_rps_set(struct intel_rps *rps, u8 val)
{
	struct drm_i915_private *i915 = rps_to_i915(rps);
	int err;

	vlv_punit_get(i915);
	err = vlv_punit_write(i915, PUNIT_REG_GPU_FREQ_REQ, val);
	vlv_punit_put(i915);

	GT_TRACE(rps_to_gt(rps), "set val:%x, freq:%d\n",
		 val, intel_gpu_freq(rps, val));

	return err;
}

static int rps_set(struct intel_rps *rps, u8 val, bool update)
{
	struct drm_i915_private *i915 = rps_to_i915(rps);
	int err;

	if (INTEL_GEN(i915) < 6)
		return 0;

	if (val == rps->last_freq)
		return 0;

	if (IS_VALLEYVIEW(i915) || IS_CHERRYVIEW(i915))
		err = vlv_rps_set(rps, val);
	else
		err = gen6_rps_set(rps, val);
	if (err)
		return err;

	if (update)
		gen6_rps_set_thresholds(rps, val);
	rps->last_freq = val;

	return 0;
}

void intel_rps_unpark(struct intel_rps *rps)
{
	if (!intel_rps_is_enabled(rps))
		return;

	GT_TRACE(rps_to_gt(rps), "unpark:%x\n", rps->cur_freq);

	/*
	 * Use the user's desired frequency as a guide, but for better
	 * performance, jump directly to RPe as our starting frequency.
	 */
	mutex_lock(&rps->lock);

	intel_rps_set_active(rps);
	intel_rps_set(rps,
		      clamp(rps->cur_freq,
			    rps->min_freq_softlimit,
			    rps->max_freq_softlimit));

	mutex_unlock(&rps->lock);

	rps->pm_iir = 0;
	if (intel_rps_has_interrupts(rps))
		rps_enable_interrupts(rps);
	if (intel_rps_uses_timer(rps))
		rps_start_timer(rps);

	if (IS_GEN(rps_to_i915(rps), 5))
		gen5_rps_update(rps);
}

void intel_rps_park(struct intel_rps *rps)
{
	int adj;

	if (!intel_rps_clear_active(rps))
		return;

	if (intel_rps_uses_timer(rps))
		rps_stop_timer(rps);
	if (intel_rps_has_interrupts(rps))
		rps_disable_interrupts(rps);

	if (rps->last_freq <= rps->idle_freq)
		return;

	/*
	 * The punit delays the write of the frequency and voltage until it
	 * determines the GPU is awake. During normal usage we don't want to
	 * waste power changing the frequency if the GPU is sleeping (rc6).
	 * However, the GPU and driver is now idle and we do not want to delay
	 * switching to minimum voltage (reducing power whilst idle) as we do
	 * not expect to be woken in the near future and so must flush the
	 * change by waking the device.
	 *
	 * We choose to take the media powerwell (either would do to trick the
	 * punit into committing the voltage change) as that takes a lot less
	 * power than the render powerwell.
	 */
	intel_uncore_forcewake_get(rps_to_uncore(rps), FORCEWAKE_MEDIA);
	rps_set(rps, rps->idle_freq, false);
	intel_uncore_forcewake_put(rps_to_uncore(rps), FORCEWAKE_MEDIA);

	/*
	 * Since we will try and restart from the previously requested
	 * frequency on unparking, treat this idle point as a downclock
	 * interrupt and reduce the frequency for resume. If we park/unpark
	 * more frequently than the rps worker can run, we will not respond
	 * to any EI and never see a change in frequency.
	 *
	 * (Note we accommodate Cherryview's limitation of only using an
	 * even bin by applying it to all.)
	 */
	adj = rps->last_adj;
	if (adj < 0)
		adj *= 2;
	else /* CHV needs even encode values */
		adj = -2;
	rps->last_adj = adj;
	rps->cur_freq = max_t(int, rps->cur_freq + adj, rps->min_freq);

	GT_TRACE(rps_to_gt(rps), "park:%x\n", rps->cur_freq);
}

void intel_rps_boost(struct i915_request *rq)
{
	struct intel_rps *rps = &READ_ONCE(rq->engine)->gt->rps;
	unsigned long flags;

	if (i915_request_signaled(rq) || !intel_rps_is_active(rps))
		return;

	/* Serializes with i915_request_retire() */
	spin_lock_irqsave(&rq->lock, flags);
	if (!i915_request_has_waitboost(rq) &&
	    !dma_fence_is_signaled_locked(&rq->fence)) {
		set_bit(I915_FENCE_FLAG_BOOST, &rq->fence.flags);

		GT_TRACE(rps_to_gt(rps), "boost fence:%llx:%llx\n",
			 rq->fence.context, rq->fence.seqno);

		if (!atomic_fetch_inc(&rps->num_waiters) &&
		    READ_ONCE(rps->cur_freq) < rps->boost_freq)
			schedule_work(&rps->work);

		atomic_inc(&rps->boosts);
	}
	spin_unlock_irqrestore(&rq->lock, flags);
}

int intel_rps_set(struct intel_rps *rps, u8 val)
{
	int err;

	lockdep_assert_held(&rps->lock);
	GEM_BUG_ON(val > rps->max_freq);
	GEM_BUG_ON(val < rps->min_freq);

	if (intel_rps_is_active(rps)) {
		err = rps_set(rps, val, true);
		if (err)
			return err;

		/*
		 * Make sure we continue to get interrupts
		 * until we hit the minimum or maximum frequencies.
		 */
		if (intel_rps_has_interrupts(rps)) {
			struct intel_uncore *uncore = rps_to_uncore(rps);

			set(uncore,
			    GEN6_RP_INTERRUPT_LIMITS, rps_limits(rps, val));

			set(uncore, GEN6_PMINTRMSK, rps_pm_mask(rps, val));
		}
	}

	rps->cur_freq = val;
	return 0;
}

static void gen6_rps_init(struct intel_rps *rps)
{
	struct drm_i915_private *i915 = rps_to_i915(rps);
	struct intel_uncore *uncore = rps_to_uncore(rps);

	/* All of these values are in units of 50MHz */

	/* static values from HW: RP0 > RP1 > RPn (min_freq) */
	if (IS_GEN9_LP(i915)) {
		u32 rp_state_cap = intel_uncore_read(uncore, BXT_RP_STATE_CAP);

		rps->rp0_freq = (rp_state_cap >> 16) & 0xff;
		rps->rp1_freq = (rp_state_cap >>  8) & 0xff;
		rps->min_freq = (rp_state_cap >>  0) & 0xff;
	} else {
		u32 rp_state_cap = intel_uncore_read(uncore, GEN6_RP_STATE_CAP);

		rps->rp0_freq = (rp_state_cap >>  0) & 0xff;
		rps->rp1_freq = (rp_state_cap >>  8) & 0xff;
		rps->min_freq = (rp_state_cap >> 16) & 0xff;
	}

	/* hw_max = RP0 until we check for overclocking */
	rps->max_freq = rps->rp0_freq;

	rps->efficient_freq = rps->rp1_freq;
	if (IS_HASWELL(i915) || IS_BROADWELL(i915) ||
	    IS_GEN9_BC(i915) || INTEL_GEN(i915) >= 10) {
		u32 ddcc_status = 0;

		if (sandybridge_pcode_read(i915,
					   HSW_PCODE_DYNAMIC_DUTY_CYCLE_CONTROL,
					   &ddcc_status, NULL) == 0)
			rps->efficient_freq =
				clamp_t(u8,
					(ddcc_status >> 8) & 0xff,
					rps->min_freq,
					rps->max_freq);
	}

	if (IS_GEN9_BC(i915) || INTEL_GEN(i915) >= 10) {
		/* Store the frequency values in 16.66 MHZ units, which is
		 * the natural hardware unit for SKL
		 */
		rps->rp0_freq *= GEN9_FREQ_SCALER;
		rps->rp1_freq *= GEN9_FREQ_SCALER;
		rps->min_freq *= GEN9_FREQ_SCALER;
		rps->max_freq *= GEN9_FREQ_SCALER;
		rps->efficient_freq *= GEN9_FREQ_SCALER;
	}
}

static bool rps_reset(struct intel_rps *rps)
{
	struct drm_i915_private *i915 = rps_to_i915(rps);

	/* force a reset */
	rps->power.mode = -1;
	rps->last_freq = -1;

	if (rps_set(rps, rps->min_freq, true)) {
		drm_err(&i915->drm, "Failed to reset RPS to initial values\n");
		return false;
	}

	rps->cur_freq = rps->min_freq;
	return true;
}

/* See the Gen9_GT_PM_Programming_Guide doc for the below */
static bool gen9_rps_enable(struct intel_rps *rps)
{
	struct intel_gt *gt = rps_to_gt(rps);
	struct intel_uncore *uncore = gt->uncore;

	/* Program defaults and thresholds for RPS */
	if (IS_GEN(gt->i915, 9))
		intel_uncore_write_fw(uncore, GEN6_RC_VIDEO_FREQ,
				      GEN9_FREQUENCY(rps->rp1_freq));

	intel_uncore_write_fw(uncore, GEN6_RP_IDLE_HYSTERSIS, 0xa);

	rps->pm_events = GEN6_PM_RP_UP_THRESHOLD | GEN6_PM_RP_DOWN_THRESHOLD;

	return rps_reset(rps);
}

static bool gen8_rps_enable(struct intel_rps *rps)
{
	struct intel_uncore *uncore = rps_to_uncore(rps);

	intel_uncore_write_fw(uncore, GEN6_RC_VIDEO_FREQ,
			      HSW_FREQUENCY(rps->rp1_freq));

	intel_uncore_write_fw(uncore, GEN6_RP_IDLE_HYSTERSIS, 10);

	rps->pm_events = GEN6_PM_RP_UP_THRESHOLD | GEN6_PM_RP_DOWN_THRESHOLD;

	return rps_reset(rps);
}

static bool gen6_rps_enable(struct intel_rps *rps)
{
	struct intel_uncore *uncore = rps_to_uncore(rps);

	/* Power down if completely idle for over 50ms */
	intel_uncore_write_fw(uncore, GEN6_RP_DOWN_TIMEOUT, 50000);
	intel_uncore_write_fw(uncore, GEN6_RP_IDLE_HYSTERSIS, 10);

	rps->pm_events = (GEN6_PM_RP_UP_THRESHOLD |
			  GEN6_PM_RP_DOWN_THRESHOLD |
			  GEN6_PM_RP_DOWN_TIMEOUT);

	return rps_reset(rps);
}

static int chv_rps_max_freq(struct intel_rps *rps)
{
	struct drm_i915_private *i915 = rps_to_i915(rps);
	struct intel_gt *gt = rps_to_gt(rps);
	u32 val;

	val = vlv_punit_read(i915, FB_GFX_FMAX_AT_VMAX_FUSE);

	switch (gt->info.sseu.eu_total) {
	case 8:
		/* (2 * 4) config */
		val >>= FB_GFX_FMAX_AT_VMAX_2SS4EU_FUSE_SHIFT;
		break;
	case 12:
		/* (2 * 6) config */
		val >>= FB_GFX_FMAX_AT_VMAX_2SS6EU_FUSE_SHIFT;
		break;
	case 16:
		/* (2 * 8) config */
	default:
		/* Setting (2 * 8) Min RP0 for any other combination */
		val >>= FB_GFX_FMAX_AT_VMAX_2SS8EU_FUSE_SHIFT;
		break;
	}

	return val & FB_GFX_FREQ_FUSE_MASK;
}

static int chv_rps_rpe_freq(struct intel_rps *rps)
{
	struct drm_i915_private *i915 = rps_to_i915(rps);
	u32 val;

	val = vlv_punit_read(i915, PUNIT_GPU_DUTYCYCLE_REG);
	val >>= PUNIT_GPU_DUTYCYCLE_RPE_FREQ_SHIFT;

	return val & PUNIT_GPU_DUTYCYCLE_RPE_FREQ_MASK;
}

static int chv_rps_guar_freq(struct intel_rps *rps)
{
	struct drm_i915_private *i915 = rps_to_i915(rps);
	u32 val;

	val = vlv_punit_read(i915, FB_GFX_FMAX_AT_VMAX_FUSE);

	return val & FB_GFX_FREQ_FUSE_MASK;
}

static u32 chv_rps_min_freq(struct intel_rps *rps)
{
	struct drm_i915_private *i915 = rps_to_i915(rps);
	u32 val;

	val = vlv_punit_read(i915, FB_GFX_FMIN_AT_VMIN_FUSE);
	val >>= FB_GFX_FMIN_AT_VMIN_FUSE_SHIFT;

	return val & FB_GFX_FREQ_FUSE_MASK;
}

static bool chv_rps_enable(struct intel_rps *rps)
{
	struct intel_uncore *uncore = rps_to_uncore(rps);
	struct drm_i915_private *i915 = rps_to_i915(rps);
	u32 val;

	/* 1: Program defaults and thresholds for RPS*/
	intel_uncore_write_fw(uncore, GEN6_RP_DOWN_TIMEOUT, 1000000);
	intel_uncore_write_fw(uncore, GEN6_RP_UP_THRESHOLD, 59400);
	intel_uncore_write_fw(uncore, GEN6_RP_DOWN_THRESHOLD, 245000);
	intel_uncore_write_fw(uncore, GEN6_RP_UP_EI, 66000);
	intel_uncore_write_fw(uncore, GEN6_RP_DOWN_EI, 350000);

	intel_uncore_write_fw(uncore, GEN6_RP_IDLE_HYSTERSIS, 10);

	/* 2: Enable RPS */
	intel_uncore_write_fw(uncore, GEN6_RP_CONTROL,
			      GEN6_RP_MEDIA_HW_NORMAL_MODE |
			      GEN6_RP_MEDIA_IS_GFX |
			      GEN6_RP_ENABLE |
			      GEN6_RP_UP_BUSY_AVG |
			      GEN6_RP_DOWN_IDLE_AVG);

	rps->pm_events = (GEN6_PM_RP_UP_THRESHOLD |
			  GEN6_PM_RP_DOWN_THRESHOLD |
			  GEN6_PM_RP_DOWN_TIMEOUT);

	/* Setting Fixed Bias */
	vlv_punit_get(i915);

	val = VLV_OVERRIDE_EN | VLV_SOC_TDP_EN | CHV_BIAS_CPU_50_SOC_50;
	vlv_punit_write(i915, VLV_TURBO_SOC_OVERRIDE, val);

	val = vlv_punit_read(i915, PUNIT_REG_GPU_FREQ_STS);

	vlv_punit_put(i915);

	/* RPS code assumes GPLL is used */
	drm_WARN_ONCE(&i915->drm, (val & GPLLENABLE) == 0,
		      "GPLL not enabled\n");

	drm_dbg(&i915->drm, "GPLL enabled? %s\n", yesno(val & GPLLENABLE));
	drm_dbg(&i915->drm, "GPU status: 0x%08x\n", val);

	return rps_reset(rps);
}

static int vlv_rps_guar_freq(struct intel_rps *rps)
{
	struct drm_i915_private *i915 = rps_to_i915(rps);
	u32 val, rp1;

	val = vlv_nc_read(i915, IOSF_NC_FB_GFX_FREQ_FUSE);

	rp1 = val & FB_GFX_FGUARANTEED_FREQ_FUSE_MASK;
	rp1 >>= FB_GFX_FGUARANTEED_FREQ_FUSE_SHIFT;

	return rp1;
}

static int vlv_rps_max_freq(struct intel_rps *rps)
{
	struct drm_i915_private *i915 = rps_to_i915(rps);
	u32 val, rp0;

	val = vlv_nc_read(i915, IOSF_NC_FB_GFX_FREQ_FUSE);

	rp0 = (val & FB_GFX_MAX_FREQ_FUSE_MASK) >> FB_GFX_MAX_FREQ_FUSE_SHIFT;
	/* Clamp to max */
	rp0 = min_t(u32, rp0, 0xea);

	return rp0;
}

static int vlv_rps_rpe_freq(struct intel_rps *rps)
{
	struct drm_i915_private *i915 = rps_to_i915(rps);
	u32 val, rpe;

	val = vlv_nc_read(i915, IOSF_NC_FB_GFX_FMAX_FUSE_LO);
	rpe = (val & FB_FMAX_VMIN_FREQ_LO_MASK) >> FB_FMAX_VMIN_FREQ_LO_SHIFT;
	val = vlv_nc_read(i915, IOSF_NC_FB_GFX_FMAX_FUSE_HI);
	rpe |= (val & FB_FMAX_VMIN_FREQ_HI_MASK) << 5;

	return rpe;
}

static int vlv_rps_min_freq(struct intel_rps *rps)
{
	struct drm_i915_private *i915 = rps_to_i915(rps);
	u32 val;

	val = vlv_punit_read(i915, PUNIT_REG_GPU_LFM) & 0xff;
	/*
	 * According to the BYT Punit GPU turbo HAS 1.1.6.3 the minimum value
	 * for the minimum frequency in GPLL mode is 0xc1. Contrary to this on
	 * a BYT-M B0 the above register contains 0xbf. Moreover when setting
	 * a frequency Punit will not allow values below 0xc0. Clamp it 0xc0
	 * to make sure it matches what Punit accepts.
	 */
	return max_t(u32, val, 0xc0);
}

static bool vlv_rps_enable(struct intel_rps *rps)
{
	struct intel_uncore *uncore = rps_to_uncore(rps);
	struct drm_i915_private *i915 = rps_to_i915(rps);
	u32 val;

	intel_uncore_write_fw(uncore, GEN6_RP_DOWN_TIMEOUT, 1000000);
	intel_uncore_write_fw(uncore, GEN6_RP_UP_THRESHOLD, 59400);
	intel_uncore_write_fw(uncore, GEN6_RP_DOWN_THRESHOLD, 245000);
	intel_uncore_write_fw(uncore, GEN6_RP_UP_EI, 66000);
	intel_uncore_write_fw(uncore, GEN6_RP_DOWN_EI, 350000);

	intel_uncore_write_fw(uncore, GEN6_RP_IDLE_HYSTERSIS, 10);

	intel_uncore_write_fw(uncore, GEN6_RP_CONTROL,
			      GEN6_RP_MEDIA_TURBO |
			      GEN6_RP_MEDIA_HW_NORMAL_MODE |
			      GEN6_RP_MEDIA_IS_GFX |
			      GEN6_RP_ENABLE |
			      GEN6_RP_UP_BUSY_AVG |
			      GEN6_RP_DOWN_IDLE_CONT);

	/* WaGsvRC0ResidencyMethod:vlv */
	rps->pm_events = GEN6_PM_RP_UP_EI_EXPIRED;

	vlv_punit_get(i915);

	/* Setting Fixed Bias */
	val = VLV_OVERRIDE_EN | VLV_SOC_TDP_EN | VLV_BIAS_CPU_125_SOC_875;
	vlv_punit_write(i915, VLV_TURBO_SOC_OVERRIDE, val);

	val = vlv_punit_read(i915, PUNIT_REG_GPU_FREQ_STS);

	vlv_punit_put(i915);

	/* RPS code assumes GPLL is used */
	drm_WARN_ONCE(&i915->drm, (val & GPLLENABLE) == 0,
		      "GPLL not enabled\n");

	drm_dbg(&i915->drm, "GPLL enabled? %s\n", yesno(val & GPLLENABLE));
	drm_dbg(&i915->drm, "GPU status: 0x%08x\n", val);

	return rps_reset(rps);
}

static unsigned long __ips_gfx_val(struct intel_ips *ips)
{
	struct intel_rps *rps = container_of(ips, typeof(*rps), ips);
	struct intel_uncore *uncore = rps_to_uncore(rps);
	unsigned long t, corr, state1, corr2, state2;
	u32 pxvid, ext_v;

	lockdep_assert_held(&mchdev_lock);

	pxvid = intel_uncore_read(uncore, PXVFREQ(rps->cur_freq));
	pxvid = (pxvid >> 24) & 0x7f;
	ext_v = pvid_to_extvid(rps_to_i915(rps), pxvid);

	state1 = ext_v;

	/* Revel in the empirically derived constants */

	/* Correction factor in 1/100000 units */
	t = ips_mch_val(uncore);
	if (t > 80)
		corr = t * 2349 + 135940;
	else if (t >= 50)
		corr = t * 964 + 29317;
	else /* < 50 */
		corr = t * 301 + 1004;

	corr = corr * 150142 * state1 / 10000 - 78642;
	corr /= 100000;
	corr2 = corr * ips->corr;

	state2 = corr2 * state1 / 10000;
	state2 /= 100; /* convert to mW */

	__gen5_ips_update(ips);

	return ips->gfx_power + state2;
}

static bool has_busy_stats(struct intel_rps *rps)
{
	struct intel_engine_cs *engine;
	enum intel_engine_id id;

	for_each_engine(engine, rps_to_gt(rps), id) {
		if (!intel_engine_supports_stats(engine))
			return false;
	}

	return true;
}

void intel_rps_enable(struct intel_rps *rps)
{
	struct drm_i915_private *i915 = rps_to_i915(rps);
	struct intel_uncore *uncore = rps_to_uncore(rps);
	bool enabled = false;

	if (!HAS_RPS(i915))
		return;

	intel_gt_check_clock_frequency(rps_to_gt(rps));

	intel_uncore_forcewake_get(uncore, FORCEWAKE_ALL);
	if (rps->max_freq <= rps->min_freq)
		/* leave disabled, no room for dynamic reclocking */;
	else if (IS_CHERRYVIEW(i915))
		enabled = chv_rps_enable(rps);
	else if (IS_VALLEYVIEW(i915))
		enabled = vlv_rps_enable(rps);
	else if (INTEL_GEN(i915) >= 9)
		enabled = gen9_rps_enable(rps);
	else if (INTEL_GEN(i915) >= 8)
		enabled = gen8_rps_enable(rps);
	else if (INTEL_GEN(i915) >= 6)
		enabled = gen6_rps_enable(rps);
	else if (IS_IRONLAKE_M(i915))
		enabled = gen5_rps_enable(rps);
	else
		MISSING_CASE(INTEL_GEN(i915));
	intel_uncore_forcewake_put(uncore, FORCEWAKE_ALL);
	if (!enabled)
		return;

	GT_TRACE(rps_to_gt(rps),
		 "min:%x, max:%x, freq:[%d, %d]\n",
		 rps->min_freq, rps->max_freq,
		 intel_gpu_freq(rps, rps->min_freq),
		 intel_gpu_freq(rps, rps->max_freq));

	GEM_BUG_ON(rps->max_freq < rps->min_freq);
	GEM_BUG_ON(rps->idle_freq > rps->max_freq);

	GEM_BUG_ON(rps->efficient_freq < rps->min_freq);
	GEM_BUG_ON(rps->efficient_freq > rps->max_freq);

	if (has_busy_stats(rps))
		intel_rps_set_timer(rps);
	else if (INTEL_GEN(i915) >= 6)
		intel_rps_set_interrupts(rps);
	else
		/* Ironlake currently uses intel_ips.ko */ {}

	intel_rps_set_enabled(rps);
}

static void gen6_rps_disable(struct intel_rps *rps)
{
	set(rps_to_uncore(rps), GEN6_RP_CONTROL, 0);
}

void intel_rps_disable(struct intel_rps *rps)
{
	struct drm_i915_private *i915 = rps_to_i915(rps);

	intel_rps_clear_enabled(rps);
	intel_rps_clear_interrupts(rps);
	intel_rps_clear_timer(rps);

	if (INTEL_GEN(i915) >= 6)
		gen6_rps_disable(rps);
	else if (IS_IRONLAKE_M(i915))
		gen5_rps_disable(rps);
}

static int byt_gpu_freq(struct intel_rps *rps, int val)
{
	/*
	 * N = val - 0xb7
	 * Slow = Fast = GPLL ref * N
	 */
	return DIV_ROUND_CLOSEST(rps->gpll_ref_freq * (val - 0xb7), 1000);
}

static int byt_freq_opcode(struct intel_rps *rps, int val)
{
	return DIV_ROUND_CLOSEST(1000 * val, rps->gpll_ref_freq) + 0xb7;
}

static int chv_gpu_freq(struct intel_rps *rps, int val)
{
	/*
	 * N = val / 2
	 * CU (slow) = CU2x (fast) / 2 = GPLL ref * N / 2
	 */
	return DIV_ROUND_CLOSEST(rps->gpll_ref_freq * val, 2 * 2 * 1000);
}

static int chv_freq_opcode(struct intel_rps *rps, int val)
{
	/* CHV needs even values */
	return DIV_ROUND_CLOSEST(2 * 1000 * val, rps->gpll_ref_freq) * 2;
}

int intel_gpu_freq(struct intel_rps *rps, int val)
{
	struct drm_i915_private *i915 = rps_to_i915(rps);

	if (INTEL_GEN(i915) >= 9)
		return DIV_ROUND_CLOSEST(val * GT_FREQUENCY_MULTIPLIER,
					 GEN9_FREQ_SCALER);
	else if (IS_CHERRYVIEW(i915))
		return chv_gpu_freq(rps, val);
	else if (IS_VALLEYVIEW(i915))
		return byt_gpu_freq(rps, val);
	else
		return val * GT_FREQUENCY_MULTIPLIER;
}

int intel_freq_opcode(struct intel_rps *rps, int val)
{
	struct drm_i915_private *i915 = rps_to_i915(rps);

	if (INTEL_GEN(i915) >= 9)
		return DIV_ROUND_CLOSEST(val * GEN9_FREQ_SCALER,
					 GT_FREQUENCY_MULTIPLIER);
	else if (IS_CHERRYVIEW(i915))
		return chv_freq_opcode(rps, val);
	else if (IS_VALLEYVIEW(i915))
		return byt_freq_opcode(rps, val);
	else
		return DIV_ROUND_CLOSEST(val, GT_FREQUENCY_MULTIPLIER);
}

static void vlv_init_gpll_ref_freq(struct intel_rps *rps)
{
	struct drm_i915_private *i915 = rps_to_i915(rps);

	rps->gpll_ref_freq =
		vlv_get_cck_clock(i915, "GPLL ref",
				  CCK_GPLL_CLOCK_CONTROL,
				  i915->czclk_freq);

	drm_dbg(&i915->drm, "GPLL reference freq: %d kHz\n",
		rps->gpll_ref_freq);
}

static void vlv_rps_init(struct intel_rps *rps)
{
	struct drm_i915_private *i915 = rps_to_i915(rps);
	u32 val;

	vlv_iosf_sb_get(i915,
			BIT(VLV_IOSF_SB_PUNIT) |
			BIT(VLV_IOSF_SB_NC) |
			BIT(VLV_IOSF_SB_CCK));

	vlv_init_gpll_ref_freq(rps);

	val = vlv_punit_read(i915, PUNIT_REG_GPU_FREQ_STS);
	switch ((val >> 6) & 3) {
	case 0:
	case 1:
		i915->mem_freq = 800;
		break;
	case 2:
		i915->mem_freq = 1066;
		break;
	case 3:
		i915->mem_freq = 1333;
		break;
	}
	drm_dbg(&i915->drm, "DDR speed: %d MHz\n", i915->mem_freq);

	rps->max_freq = vlv_rps_max_freq(rps);
	rps->rp0_freq = rps->max_freq;
	drm_dbg(&i915->drm, "max GPU freq: %d MHz (%u)\n",
		intel_gpu_freq(rps, rps->max_freq), rps->max_freq);

	rps->efficient_freq = vlv_rps_rpe_freq(rps);
	drm_dbg(&i915->drm, "RPe GPU freq: %d MHz (%u)\n",
		intel_gpu_freq(rps, rps->efficient_freq), rps->efficient_freq);

	rps->rp1_freq = vlv_rps_guar_freq(rps);
	drm_dbg(&i915->drm, "RP1(Guar Freq) GPU freq: %d MHz (%u)\n",
		intel_gpu_freq(rps, rps->rp1_freq), rps->rp1_freq);

	rps->min_freq = vlv_rps_min_freq(rps);
	drm_dbg(&i915->drm, "min GPU freq: %d MHz (%u)\n",
		intel_gpu_freq(rps, rps->min_freq), rps->min_freq);

	vlv_iosf_sb_put(i915,
			BIT(VLV_IOSF_SB_PUNIT) |
			BIT(VLV_IOSF_SB_NC) |
			BIT(VLV_IOSF_SB_CCK));
}

static void chv_rps_init(struct intel_rps *rps)
{
	struct drm_i915_private *i915 = rps_to_i915(rps);
	u32 val;

	vlv_iosf_sb_get(i915,
			BIT(VLV_IOSF_SB_PUNIT) |
			BIT(VLV_IOSF_SB_NC) |
			BIT(VLV_IOSF_SB_CCK));

	vlv_init_gpll_ref_freq(rps);

	val = vlv_cck_read(i915, CCK_FUSE_REG);

	switch ((val >> 2) & 0x7) {
	case 3:
		i915->mem_freq = 2000;
		break;
	default:
		i915->mem_freq = 1600;
		break;
	}
	drm_dbg(&i915->drm, "DDR speed: %d MHz\n", i915->mem_freq);

	rps->max_freq = chv_rps_max_freq(rps);
	rps->rp0_freq = rps->max_freq;
	drm_dbg(&i915->drm, "max GPU freq: %d MHz (%u)\n",
		intel_gpu_freq(rps, rps->max_freq), rps->max_freq);

	rps->efficient_freq = chv_rps_rpe_freq(rps);
	drm_dbg(&i915->drm, "RPe GPU freq: %d MHz (%u)\n",
		intel_gpu_freq(rps, rps->efficient_freq), rps->efficient_freq);

	rps->rp1_freq = chv_rps_guar_freq(rps);
	drm_dbg(&i915->drm, "RP1(Guar) GPU freq: %d MHz (%u)\n",
		intel_gpu_freq(rps, rps->rp1_freq), rps->rp1_freq);

	rps->min_freq = chv_rps_min_freq(rps);
	drm_dbg(&i915->drm, "min GPU freq: %d MHz (%u)\n",
		intel_gpu_freq(rps, rps->min_freq), rps->min_freq);

	vlv_iosf_sb_put(i915,
			BIT(VLV_IOSF_SB_PUNIT) |
			BIT(VLV_IOSF_SB_NC) |
			BIT(VLV_IOSF_SB_CCK));

	drm_WARN_ONCE(&i915->drm, (rps->max_freq | rps->efficient_freq |
				   rps->rp1_freq | rps->min_freq) & 1,
		      "Odd GPU freq values\n");
}

static void vlv_c0_read(struct intel_uncore *uncore, struct intel_rps_ei *ei)
{
	ei->ktime = ktime_get_raw();
	ei->render_c0 = intel_uncore_read(uncore, VLV_RENDER_C0_COUNT);
	ei->media_c0 = intel_uncore_read(uncore, VLV_MEDIA_C0_COUNT);
}

static u32 vlv_wa_c0_ei(struct intel_rps *rps, u32 pm_iir)
{
	struct intel_uncore *uncore = rps_to_uncore(rps);
	const struct intel_rps_ei *prev = &rps->ei;
	struct intel_rps_ei now;
	u32 events = 0;

	if ((pm_iir & GEN6_PM_RP_UP_EI_EXPIRED) == 0)
		return 0;

	vlv_c0_read(uncore, &now);

	if (prev->ktime) {
		u64 time, c0;
		u32 render, media;

		time = ktime_us_delta(now.ktime, prev->ktime);

		time *= rps_to_i915(rps)->czclk_freq;

		/* Workload can be split between render + media,
		 * e.g. SwapBuffers being blitted in X after being rendered in
		 * mesa. To account for this we need to combine both engines
		 * into our activity counter.
		 */
		render = now.render_c0 - prev->render_c0;
		media = now.media_c0 - prev->media_c0;
		c0 = max(render, media);
		c0 *= 1000 * 100 << 8; /* to usecs and scale to threshold% */

		if (c0 > time * rps->power.up_threshold)
			events = GEN6_PM_RP_UP_THRESHOLD;
		else if (c0 < time * rps->power.down_threshold)
			events = GEN6_PM_RP_DOWN_THRESHOLD;
	}

	rps->ei = now;
	return events;
}

static void rps_work(struct work_struct *work)
{
	struct intel_rps *rps = container_of(work, typeof(*rps), work);
	struct intel_gt *gt = rps_to_gt(rps);
	struct drm_i915_private *i915 = rps_to_i915(rps);
	bool client_boost = false;
	int new_freq, adj, min, max;
	u32 pm_iir = 0;

	spin_lock_irq(&gt->irq_lock);
	pm_iir = fetch_and_zero(&rps->pm_iir) & rps->pm_events;
	client_boost = atomic_read(&rps->num_waiters);
	spin_unlock_irq(&gt->irq_lock);

	/* Make sure we didn't queue anything we're not going to process. */
	if (!pm_iir && !client_boost)
		goto out;

	mutex_lock(&rps->lock);
	if (!intel_rps_is_active(rps)) {
		mutex_unlock(&rps->lock);
		return;
	}

	pm_iir |= vlv_wa_c0_ei(rps, pm_iir);

	adj = rps->last_adj;
	new_freq = rps->cur_freq;
	min = rps->min_freq_softlimit;
	max = rps->max_freq_softlimit;
	if (client_boost)
		max = rps->max_freq;

	GT_TRACE(gt,
		 "pm_iir:%x, client_boost:%s, last:%d, cur:%x, min:%x, max:%x\n",
		 pm_iir, yesno(client_boost),
		 adj, new_freq, min, max);

	if (client_boost && new_freq < rps->boost_freq) {
		new_freq = rps->boost_freq;
		adj = 0;
	} else if (pm_iir & GEN6_PM_RP_UP_THRESHOLD) {
		if (adj > 0)
			adj *= 2;
		else /* CHV needs even encode values */
			adj = IS_CHERRYVIEW(gt->i915) ? 2 : 1;

		if (new_freq >= rps->max_freq_softlimit)
			adj = 0;
	} else if (client_boost) {
		adj = 0;
	} else if (pm_iir & GEN6_PM_RP_DOWN_TIMEOUT) {
		if (rps->cur_freq > rps->efficient_freq)
			new_freq = rps->efficient_freq;
		else if (rps->cur_freq > rps->min_freq_softlimit)
			new_freq = rps->min_freq_softlimit;
		adj = 0;
	} else if (pm_iir & GEN6_PM_RP_DOWN_THRESHOLD) {
		if (adj < 0)
			adj *= 2;
		else /* CHV needs even encode values */
			adj = IS_CHERRYVIEW(gt->i915) ? -2 : -1;

		if (new_freq <= rps->min_freq_softlimit)
			adj = 0;
	} else { /* unknown event */
		adj = 0;
	}

	/*
	 * sysfs frequency limits may have snuck in while
	 * servicing the interrupt
	 */
	new_freq += adj;
	new_freq = clamp_t(int, new_freq, min, max);

	if (intel_rps_set(rps, new_freq)) {
		drm_dbg(&i915->drm, "Failed to set new GPU frequency\n");
		adj = 0;
	}
	rps->last_adj = adj;

	mutex_unlock(&rps->lock);

out:
	spin_lock_irq(&gt->irq_lock);
	gen6_gt_pm_unmask_irq(gt, rps->pm_events);
	spin_unlock_irq(&gt->irq_lock);
}

void gen11_rps_irq_handler(struct intel_rps *rps, u32 pm_iir)
{
	struct intel_gt *gt = rps_to_gt(rps);
	const u32 events = rps->pm_events & pm_iir;

	lockdep_assert_held(&gt->irq_lock);

	if (unlikely(!events))
		return;

	GT_TRACE(gt, "irq events:%x\n", events);

	gen6_gt_pm_mask_irq(gt, events);

	rps->pm_iir |= events;
	schedule_work(&rps->work);
}

void gen6_rps_irq_handler(struct intel_rps *rps, u32 pm_iir)
{
	struct intel_gt *gt = rps_to_gt(rps);
	u32 events;

	events = pm_iir & rps->pm_events;
	if (events) {
		spin_lock(&gt->irq_lock);

		GT_TRACE(gt, "irq events:%x\n", events);

		gen6_gt_pm_mask_irq(gt, events);
		rps->pm_iir |= events;

		schedule_work(&rps->work);
		spin_unlock(&gt->irq_lock);
	}

	if (INTEL_GEN(gt->i915) >= 8)
		return;

	if (pm_iir & PM_VEBOX_USER_INTERRUPT)
		intel_engine_signal_breadcrumbs(gt->engine[VECS0]);

	if (pm_iir & PM_VEBOX_CS_ERROR_INTERRUPT)
		DRM_DEBUG("Command parser error, pm_iir 0x%08x\n", pm_iir);
}

void gen5_rps_irq_handler(struct intel_rps *rps)
{
	struct intel_uncore *uncore = rps_to_uncore(rps);
	u32 busy_up, busy_down, max_avg, min_avg;
	u8 new_freq;

	spin_lock(&mchdev_lock);

	intel_uncore_write16(uncore,
			     MEMINTRSTS,
			     intel_uncore_read(uncore, MEMINTRSTS));

	intel_uncore_write16(uncore, MEMINTRSTS, MEMINT_EVAL_CHG);
	busy_up = intel_uncore_read(uncore, RCPREVBSYTUPAVG);
	busy_down = intel_uncore_read(uncore, RCPREVBSYTDNAVG);
	max_avg = intel_uncore_read(uncore, RCBMAXAVG);
	min_avg = intel_uncore_read(uncore, RCBMINAVG);

	/* Handle RCS change request from hw */
	new_freq = rps->cur_freq;
	if (busy_up > max_avg)
		new_freq++;
	else if (busy_down < min_avg)
		new_freq--;
	new_freq = clamp(new_freq,
			 rps->min_freq_softlimit,
			 rps->max_freq_softlimit);

	if (new_freq != rps->cur_freq && gen5_rps_set(rps, new_freq))
		rps->cur_freq = new_freq;

	spin_unlock(&mchdev_lock);
}

void intel_rps_init_early(struct intel_rps *rps)
{
	mutex_init(&rps->lock);
	mutex_init(&rps->power.mutex);

	INIT_WORK(&rps->work, rps_work);
	timer_setup(&rps->timer, rps_timer, 0);

	atomic_set(&rps->num_waiters, 0);
}

void intel_rps_init(struct intel_rps *rps)
{
	struct drm_i915_private *i915 = rps_to_i915(rps);

	if (IS_CHERRYVIEW(i915))
		chv_rps_init(rps);
	else if (IS_VALLEYVIEW(i915))
		vlv_rps_init(rps);
	else if (INTEL_GEN(i915) >= 6)
		gen6_rps_init(rps);
	else if (IS_IRONLAKE_M(i915))
		gen5_rps_init(rps);

	/* Derive initial user preferences/limits from the hardware limits */
	rps->max_freq_softlimit = rps->max_freq;
	rps->min_freq_softlimit = rps->min_freq;

	/* After setting max-softlimit, find the overclock max freq */
	if (IS_GEN(i915, 6) || IS_IVYBRIDGE(i915) || IS_HASWELL(i915)) {
		u32 params = 0;

		sandybridge_pcode_read(i915, GEN6_READ_OC_PARAMS,
				       &params, NULL);
		if (params & BIT(31)) { /* OC supported */
			drm_dbg(&i915->drm,
				"Overclocking supported, max: %dMHz, overclock: %dMHz\n",
				(rps->max_freq & 0xff) * 50,
				(params & 0xff) * 50);
			rps->max_freq = params & 0xff;
		}
	}

	/* Finally allow us to boost to max by default */
	rps->boost_freq = rps->max_freq;
	rps->idle_freq = rps->min_freq;

	/* Start in the middle, from here we will autotune based on workload */
	rps->cur_freq = rps->efficient_freq;

	rps->pm_intrmsk_mbz = 0;

	/*
	 * SNB,IVB,HSW can while VLV,CHV may hard hang on looping batchbuffer
	 * if GEN6_PM_UP_EI_EXPIRED is masked.
	 *
	 * TODO: verify if this can be reproduced on VLV,CHV.
	 */
	if (INTEL_GEN(i915) <= 7)
		rps->pm_intrmsk_mbz |= GEN6_PM_RP_UP_EI_EXPIRED;

	if (INTEL_GEN(i915) >= 8 && INTEL_GEN(i915) < 11)
		rps->pm_intrmsk_mbz |= GEN8_PMINTR_DISABLE_REDIRECT_TO_GUC;
}

void intel_rps_sanitize(struct intel_rps *rps)
{
	if (INTEL_GEN(rps_to_i915(rps)) >= 6)
		rps_disable_interrupts(rps);
}

u32 intel_rps_get_cagf(struct intel_rps *rps, u32 rpstat)
{
	struct drm_i915_private *i915 = rps_to_i915(rps);
	u32 cagf;

	if (IS_VALLEYVIEW(i915) || IS_CHERRYVIEW(i915))
		cagf = (rpstat >> 8) & 0xff;
	else if (INTEL_GEN(i915) >= 9)
		cagf = (rpstat & GEN9_CAGF_MASK) >> GEN9_CAGF_SHIFT;
	else if (IS_HASWELL(i915) || IS_BROADWELL(i915))
		cagf = (rpstat & HSW_CAGF_MASK) >> HSW_CAGF_SHIFT;
	else
		cagf = (rpstat & GEN6_CAGF_MASK) >> GEN6_CAGF_SHIFT;

	return cagf;
}

static u32 read_cagf(struct intel_rps *rps)
{
	struct drm_i915_private *i915 = rps_to_i915(rps);
	u32 freq;

	if (IS_VALLEYVIEW(i915) || IS_CHERRYVIEW(i915)) {
		vlv_punit_get(i915);
		freq = vlv_punit_read(i915, PUNIT_REG_GPU_FREQ_STS);
		vlv_punit_put(i915);
	} else {
		freq = intel_uncore_read(rps_to_uncore(rps), GEN6_RPSTAT1);
	}

	return intel_rps_get_cagf(rps, freq);
}

u32 intel_rps_read_actual_frequency(struct intel_rps *rps)
{
	struct intel_runtime_pm *rpm = rps_to_uncore(rps)->rpm;
	intel_wakeref_t wakeref;
	u32 freq = 0;

	with_intel_runtime_pm_if_in_use(rpm, wakeref)
		freq = intel_gpu_freq(rps, read_cagf(rps));

	return freq;
}

/* External interface for intel_ips.ko */

static struct drm_i915_private __rcu *ips_mchdev;

/**
 * Tells the intel_ips driver that the i915 driver is now loaded, if
 * IPS got loaded first.
 *
 * This awkward dance is so that neither module has to depend on the
 * other in order for IPS to do the appropriate communication of
 * GPU turbo limits to i915.
 */
static void
ips_ping_for_i915_load(void)
{
	void (*link)(void);

	link = symbol_get(ips_link_to_i915_driver);
	if (link) {
		link();
		symbol_put(ips_link_to_i915_driver);
	}
}

void intel_rps_driver_register(struct intel_rps *rps)
{
	struct intel_gt *gt = rps_to_gt(rps);

	/*
	 * We only register the i915 ips part with intel-ips once everything is
	 * set up, to avoid intel-ips sneaking in and reading bogus values.
	 */
	if (IS_GEN(gt->i915, 5)) {
		GEM_BUG_ON(ips_mchdev);
		rcu_assign_pointer(ips_mchdev, gt->i915);
		ips_ping_for_i915_load();
	}
}

void intel_rps_driver_unregister(struct intel_rps *rps)
{
	if (rcu_access_pointer(ips_mchdev) == rps_to_i915(rps))
		rcu_assign_pointer(ips_mchdev, NULL);
}

static struct drm_i915_private *mchdev_get(void)
{
	struct drm_i915_private *i915;

	rcu_read_lock();
	i915 = rcu_dereference(ips_mchdev);
	if (!kref_get_unless_zero(&i915->drm.ref))
		i915 = NULL;
	rcu_read_unlock();

	return i915;
}

/**
 * i915_read_mch_val - return value for IPS use
 *
 * Calculate and return a value for the IPS driver to use when deciding whether
 * we have thermal and power headroom to increase CPU or GPU power budget.
 */
unsigned long i915_read_mch_val(void)
{
	struct drm_i915_private *i915;
	unsigned long chipset_val = 0;
	unsigned long graphics_val = 0;
	intel_wakeref_t wakeref;

	i915 = mchdev_get();
	if (!i915)
		return 0;

	with_intel_runtime_pm(&i915->runtime_pm, wakeref) {
		struct intel_ips *ips = &i915->gt.rps.ips;

		spin_lock_irq(&mchdev_lock);
		chipset_val = __ips_chipset_val(ips);
		graphics_val = __ips_gfx_val(ips);
		spin_unlock_irq(&mchdev_lock);
	}

	drm_dev_put(&i915->drm);
	return chipset_val + graphics_val;
}
EXPORT_SYMBOL_GPL(i915_read_mch_val);

/**
 * i915_gpu_raise - raise GPU frequency limit
 *
 * Raise the limit; IPS indicates we have thermal headroom.
 */
bool i915_gpu_raise(void)
{
	struct drm_i915_private *i915;
	struct intel_rps *rps;

	i915 = mchdev_get();
	if (!i915)
		return false;

	rps = &i915->gt.rps;

	spin_lock_irq(&mchdev_lock);
	if (rps->max_freq_softlimit < rps->max_freq)
		rps->max_freq_softlimit++;
	spin_unlock_irq(&mchdev_lock);

	drm_dev_put(&i915->drm);
	return true;
}
EXPORT_SYMBOL_GPL(i915_gpu_raise);

/**
 * i915_gpu_lower - lower GPU frequency limit
 *
 * IPS indicates we're close to a thermal limit, so throttle back the GPU
 * frequency maximum.
 */
bool i915_gpu_lower(void)
{
	struct drm_i915_private *i915;
	struct intel_rps *rps;

	i915 = mchdev_get();
	if (!i915)
		return false;

	rps = &i915->gt.rps;

	spin_lock_irq(&mchdev_lock);
	if (rps->max_freq_softlimit > rps->min_freq)
		rps->max_freq_softlimit--;
	spin_unlock_irq(&mchdev_lock);

	drm_dev_put(&i915->drm);
	return true;
}
EXPORT_SYMBOL_GPL(i915_gpu_lower);

/**
 * i915_gpu_busy - indicate GPU business to IPS
 *
 * Tell the IPS driver whether or not the GPU is busy.
 */
bool i915_gpu_busy(void)
{
	struct drm_i915_private *i915;
	bool ret;

	i915 = mchdev_get();
	if (!i915)
		return false;

	ret = i915->gt.awake;

	drm_dev_put(&i915->drm);
	return ret;
}
EXPORT_SYMBOL_GPL(i915_gpu_busy);

/**
 * i915_gpu_turbo_disable - disable graphics turbo
 *
 * Disable graphics turbo by resetting the max frequency and setting the
 * current frequency to the default.
 */
bool i915_gpu_turbo_disable(void)
{
	struct drm_i915_private *i915;
	struct intel_rps *rps;
	bool ret;

	i915 = mchdev_get();
	if (!i915)
		return false;

	rps = &i915->gt.rps;

	spin_lock_irq(&mchdev_lock);
	rps->max_freq_softlimit = rps->min_freq;
	ret = gen5_rps_set(&i915->gt.rps, rps->min_freq);
	spin_unlock_irq(&mchdev_lock);

	drm_dev_put(&i915->drm);
	return ret;
}
EXPORT_SYMBOL_GPL(i915_gpu_turbo_disable);

#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
#include "selftest_rps.c"
#endif