aboutsummaryrefslogtreecommitdiffstats
path: root/arch/arm/mach-at91/at91sam9g45_devices.c
blob: 1b47319ca00b1a72e7c8600e4469b5661529f54a (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
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
/*
 *  On-Chip devices setup code for the AT91SAM9G45 family
 *
 *  Copyright (C) 2009 Atmel Corporation.
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation; either version 2 of the License, or
 * (at your option) any later version.
 *
 */
#include <asm/mach/arch.h>
#include <asm/mach/map.h>

#include <linux/dma-mapping.h>
#include <linux/gpio.h>
#include <linux/clk.h>
#include <linux/platform_device.h>
#include <linux/i2c-gpio.h>
#include <linux/atmel-mci.h>
#include <linux/platform_data/atmel-aes.h>

#include <linux/platform_data/at91_adc.h>

#include <linux/fb.h>
#include <video/atmel_lcdc.h>

#include <mach/at91_adc.h>
#include <mach/board.h>
#include <mach/at91sam9g45.h>
#include <mach/at91sam9g45_matrix.h>
#include <mach/at91_matrix.h>
#include <mach/at91sam9_smc.h>
#include <mach/at_hdmac.h>
#include <mach/atmel-mci.h>

#include <media/atmel-isi.h>

#include "generic.h"
#include "clock.h"


/* --------------------------------------------------------------------
 *  HDMAC - AHB DMA Controller
 * -------------------------------------------------------------------- */

#if defined(CONFIG_AT_HDMAC) || defined(CONFIG_AT_HDMAC_MODULE)
static u64 hdmac_dmamask = DMA_BIT_MASK(32);

static struct resource hdmac_resources[] = {
	[0] = {
		.start	= AT91SAM9G45_BASE_DMA,
		.end	= AT91SAM9G45_BASE_DMA + SZ_512 - 1,
		.flags	= IORESOURCE_MEM,
	},
	[1] = {
		.start	= NR_IRQS_LEGACY + AT91SAM9G45_ID_DMA,
		.end	= NR_IRQS_LEGACY + AT91SAM9G45_ID_DMA,
		.flags	= IORESOURCE_IRQ,
	},
};

static struct platform_device at_hdmac_device = {
	.name		= "at91sam9g45_dma",
	.id		= -1,
	.dev		= {
				.dma_mask		= &hdmac_dmamask,
				.coherent_dma_mask	= DMA_BIT_MASK(32),
	},
	.resource	= hdmac_resources,
	.num_resources	= ARRAY_SIZE(hdmac_resources),
};

void __init at91_add_device_hdmac(void)
{
	platform_device_register(&at_hdmac_device);
}
#else
void __init at91_add_device_hdmac(void) {}
#endif


/* --------------------------------------------------------------------
 *  USB Host (OHCI)
 * -------------------------------------------------------------------- */

#if defined(CONFIG_USB_OHCI_HCD) || defined(CONFIG_USB_OHCI_HCD_MODULE)
static u64 ohci_dmamask = DMA_BIT_MASK(32);
static struct at91_usbh_data usbh_ohci_data;

static struct resource usbh_ohci_resources[] = {
	[0] = {
		.start	= AT91SAM9G45_OHCI_BASE,
		.end	= AT91SAM9G45_OHCI_BASE + SZ_1M - 1,
		.flags	= IORESOURCE_MEM,
	},
	[1] = {
		.start	= NR_IRQS_LEGACY + AT91SAM9G45_ID_UHPHS,
		.end	= NR_IRQS_LEGACY + AT91SAM9G45_ID_UHPHS,
		.flags	= IORESOURCE_IRQ,
	},
};

static struct platform_device at91_usbh_ohci_device = {
	.name		= "at91_ohci",
	.id		= -1,
	.dev		= {
				.dma_mask		= &ohci_dmamask,
				.coherent_dma_mask	= DMA_BIT_MASK(32),
				.platform_data		= &usbh_ohci_data,
	},
	.resource	= usbh_ohci_resources,
	.num_resources	= ARRAY_SIZE(usbh_ohci_resources),
};

void __init at91_add_device_usbh_ohci(struct at91_usbh_data *data)
{
	int i;

	if (!data)
		return;

	/* Enable VBus control for UHP ports */
	for (i = 0; i < data->ports; i++) {
		if (gpio_is_valid(data->vbus_pin[i]))
			at91_set_gpio_output(data->vbus_pin[i],
					     data->vbus_pin_active_low[i]);
	}

	/* Enable overcurrent notification */
	for (i = 0; i < data->ports; i++) {
		if (gpio_is_valid(data->overcurrent_pin[i]))
			at91_set_gpio_input(data->overcurrent_pin[i], 1);
	}

	usbh_ohci_data = *data;
	platform_device_register(&at91_usbh_ohci_device);
}
#else
void __init at91_add_device_usbh_ohci(struct at91_usbh_data *data) {}
#endif


/* --------------------------------------------------------------------
 *  USB Host HS (EHCI)
 *  Needs an OHCI host for low and full speed management
 * -------------------------------------------------------------------- */

#if defined(CONFIG_USB_EHCI_HCD) || defined(CONFIG_USB_EHCI_HCD_MODULE)
static u64 ehci_dmamask = DMA_BIT_MASK(32);
static struct at91_usbh_data usbh_ehci_data;

static struct resource usbh_ehci_resources[] = {
	[0] = {
		.start	= AT91SAM9G45_EHCI_BASE,
		.end	= AT91SAM9G45_EHCI_BASE + SZ_1M - 1,
		.flags	= IORESOURCE_MEM,
	},
	[1] = {
		.start	= NR_IRQS_LEGACY + AT91SAM9G45_ID_UHPHS,
		.end	= NR_IRQS_LEGACY + AT91SAM9G45_ID_UHPHS,
		.flags	= IORESOURCE_IRQ,
	},
};

static struct platform_device at91_usbh_ehci_device = {
	.name		= "atmel-ehci",
	.id		= -1,
	.dev		= {
				.dma_mask		= &ehci_dmamask,
				.coherent_dma_mask	= DMA_BIT_MASK(32),
				.platform_data		= &usbh_ehci_data,
	},
	.resource	= usbh_ehci_resources,
	.num_resources	= ARRAY_SIZE(usbh_ehci_resources),
};

void __init at91_add_device_usbh_ehci(struct at91_usbh_data *data)
{
	int i;

	if (!data)
		return;

	/* Enable VBus control for UHP ports */
	for (i = 0; i < data->ports; i++) {
		if (gpio_is_valid(data->vbus_pin[i]))
			at91_set_gpio_output(data->vbus_pin[i],
					     data->vbus_pin_active_low[i]);
	}

	usbh_ehci_data = *data;
	platform_device_register(&at91_usbh_ehci_device);
}
#else
void __init at91_add_device_usbh_ehci(struct at91_usbh_data *data) {}
#endif


/* --------------------------------------------------------------------
 *  USB HS Device (Gadget)
 * -------------------------------------------------------------------- */

#if defined(CONFIG_USB_ATMEL_USBA) || defined(CONFIG_USB_ATMEL_USBA_MODULE)
static struct resource usba_udc_resources[] = {
	[0] = {
		.start	= AT91SAM9G45_UDPHS_FIFO,
		.end	= AT91SAM9G45_UDPHS_FIFO + SZ_512K - 1,
		.flags	= IORESOURCE_MEM,
	},
	[1] = {
		.start	= AT91SAM9G45_BASE_UDPHS,
		.end	= AT91SAM9G45_BASE_UDPHS + SZ_1K - 1,
		.flags	= IORESOURCE_MEM,
	},
	[2] = {
		.start	= NR_IRQS_LEGACY + AT91SAM9G45_ID_UDPHS,
		.end	= NR_IRQS_LEGACY + AT91SAM9G45_ID_UDPHS,
		.flags	= IORESOURCE_IRQ,
	},
};

#define EP(nam, idx, maxpkt, maxbk, dma, isoc)			\
	[idx] = {						\
		.name		= nam,				\
		.index		= idx,				\
		.fifo_size	= maxpkt,			\
		.nr_banks	= maxbk,			\
		.can_dma	= dma,				\
		.can_isoc	= isoc,				\
	}

static struct usba_ep_data usba_udc_ep[] __initdata = {
	EP("ep0", 0, 64, 1, 0, 0),
	EP("ep1", 1, 1024, 2, 1, 1),
	EP("ep2", 2, 1024, 2, 1, 1),
	EP("ep3", 3, 1024, 3, 1, 0),
	EP("ep4", 4, 1024, 3, 1, 0),
	EP("ep5", 5, 1024, 3, 1, 1),
	EP("ep6", 6, 1024, 3, 1, 1),
};

#undef EP

/*
 * pdata doesn't have room for any endpoints, so we need to
 * append room for the ones we need right after it.
 */
static struct {
	struct usba_platform_data pdata;
	struct usba_ep_data ep[7];
} usba_udc_data;

static struct platform_device at91_usba_udc_device = {
	.name		= "atmel_usba_udc",
	.id		= -1,
	.dev		= {
				.platform_data	= &usba_udc_data.pdata,
	},
	.resource	= usba_udc_resources,
	.num_resources	= ARRAY_SIZE(usba_udc_resources),
};

void __init at91_add_device_usba(struct usba_platform_data *data)
{
	usba_udc_data.pdata.vbus_pin = -EINVAL;
	usba_udc_data.pdata.num_ep = ARRAY_SIZE(usba_udc_ep);
	memcpy(usba_udc_data.ep, usba_udc_ep, sizeof(usba_udc_ep));

	if (data && gpio_is_valid(data->vbus_pin)) {
		at91_set_gpio_input(data->vbus_pin, 0);
		at91_set_deglitch(data->vbus_pin, 1);
		usba_udc_data.pdata.vbus_pin = data->vbus_pin;
	}

	/* Pullup pin is handled internally by USB device peripheral */

	platform_device_register(&at91_usba_udc_device);
}
#else
void __init at91_add_device_usba(struct usba_platform_data *data) {}
#endif


/* --------------------------------------------------------------------
 *  Ethernet
 * -------------------------------------------------------------------- */

#if defined(CONFIG_MACB) || defined(CONFIG_MACB_MODULE)
static u64 eth_dmamask = DMA_BIT_MASK(32);
static struct macb_platform_data eth_data;

static struct resource eth_resources[] = {
	[0] = {
		.start	= AT91SAM9G45_BASE_EMAC,
		.end	= AT91SAM9G45_BASE_EMAC + SZ_16K - 1,
		.flags	= IORESOURCE_MEM,
	},
	[1] = {
		.start	= NR_IRQS_LEGACY + AT91SAM9G45_ID_EMAC,
		.end	= NR_IRQS_LEGACY + AT91SAM9G45_ID_EMAC,
		.flags	= IORESOURCE_IRQ,
	},
};

static struct platform_device at91sam9g45_eth_device = {
	.name		= "macb",
	.id		= -1,
	.dev		= {
				.dma_mask		= &eth_dmamask,
				.coherent_dma_mask	= DMA_BIT_MASK(32),
				.platform_data		= &eth_data,
	},
	.resource	= eth_resources,
	.num_resources	= ARRAY_SIZE(eth_resources),
};

void __init at91_add_device_eth(struct macb_platform_data *data)
{
	if (!data)
		return;

	if (gpio_is_valid(data->phy_irq_pin)) {
		at91_set_gpio_input(data->phy_irq_pin, 0);
		at91_set_deglitch(data->phy_irq_pin, 1);
	}

	/* Pins used for MII and RMII */
	at91_set_A_periph(AT91_PIN_PA17, 0);	/* ETXCK_EREFCK */
	at91_set_A_periph(AT91_PIN_PA15, 0);	/* ERXDV */
	at91_set_A_periph(AT91_PIN_PA12, 0);	/* ERX0 */
	at91_set_A_periph(AT91_PIN_PA13, 0);	/* ERX1 */
	at91_set_A_periph(AT91_PIN_PA16, 0);	/* ERXER */
	at91_set_A_periph(AT91_PIN_PA14, 0);	/* ETXEN */
	at91_set_A_periph(AT91_PIN_PA10, 0);	/* ETX0 */
	at91_set_A_periph(AT91_PIN_PA11, 0);	/* ETX1 */
	at91_set_A_periph(AT91_PIN_PA19, 0);	/* EMDIO */
	at91_set_A_periph(AT91_PIN_PA18, 0);	/* EMDC */

	if (!data->is_rmii) {
		at91_set_B_periph(AT91_PIN_PA29, 0);	/* ECRS */
		at91_set_B_periph(AT91_PIN_PA30, 0);	/* ECOL */
		at91_set_B_periph(AT91_PIN_PA8,  0);	/* ERX2 */
		at91_set_B_periph(AT91_PIN_PA9,  0);	/* ERX3 */
		at91_set_B_periph(AT91_PIN_PA28, 0);	/* ERXCK */
		at91_set_B_periph(AT91_PIN_PA6,  0);	/* ETX2 */
		at91_set_B_periph(AT91_PIN_PA7,  0);	/* ETX3 */
		at91_set_B_periph(AT91_PIN_PA27, 0);	/* ETXER */
	}

	eth_data = *data;
	platform_device_register(&at91sam9g45_eth_device);
}
#else
void __init at91_add_device_eth(struct macb_platform_data *data) {}
#endif


/* --------------------------------------------------------------------
 *  MMC / SD
 * -------------------------------------------------------------------- */

#if defined(CONFIG_MMC_ATMELMCI) || defined(CONFIG_MMC_ATMELMCI_MODULE)
static u64 mmc_dmamask = DMA_BIT_MASK(32);
static struct mci_platform_data mmc0_data, mmc1_data;

static struct resource mmc0_resources[] = {
	[0] = {
		.start	= AT91SAM9G45_BASE_MCI0,
		.end	= AT91SAM9G45_BASE_MCI0 + SZ_16K - 1,
		.flags	= IORESOURCE_MEM,
	},
	[1] = {
		.start	= NR_IRQS_LEGACY + AT91SAM9G45_ID_MCI0,
		.end	= NR_IRQS_LEGACY + AT91SAM9G45_ID_MCI0,
		.flags	= IORESOURCE_IRQ,
	},
};

static struct platform_device at91sam9g45_mmc0_device = {
	.name		= "atmel_mci",
	.id		= 0,
	.dev		= {
				.dma_mask		= &mmc_dmamask,
				.coherent_dma_mask	= DMA_BIT_MASK(32),
				.platform_data		= &mmc0_data,
	},
	.resource	= mmc0_resources,
	.num_resources	= ARRAY_SIZE(mmc0_resources),
};

static struct resource mmc1_resources[] = {
	[0] = {
		.start	= AT91SAM9G45_BASE_MCI1,
		.end	= AT91SAM9G45_BASE_MCI1 + SZ_16K - 1,
		.flags	= IORESOURCE_MEM,
	},
	[1] = {
		.start	= NR_IRQS_LEGACY + AT91SAM9G45_ID_MCI1,
		.end	= NR_IRQS_LEGACY + AT91SAM9G45_ID_MCI1,
		.flags	= IORESOURCE_IRQ,
	},
};

static struct platform_device at91sam9g45_mmc1_device = {
	.name		= "atmel_mci",
	.id		= 1,
	.dev		= {
				.dma_mask		= &mmc_dmamask,
				.coherent_dma_mask	= DMA_BIT_MASK(32),
				.platform_data		= &mmc1_data,
	},
	.resource	= mmc1_resources,
	.num_resources	= ARRAY_SIZE(mmc1_resources),
};

/* Consider only one slot : slot 0 */
void __init at91_add_device_mci(short mmc_id, struct mci_platform_data *data)
{

	if (!data)
		return;

	/* Must have at least one usable slot */
	if (!data->slot[0].bus_width)
		return;

#if defined(CONFIG_AT_HDMAC) || defined(CONFIG_AT_HDMAC_MODULE)
	{
	struct at_dma_slave	*atslave;
	struct mci_dma_data	*alt_atslave;

	alt_atslave = kzalloc(sizeof(struct mci_dma_data), GFP_KERNEL);
	atslave = &alt_atslave->sdata;

	/* DMA slave channel configuration */
	atslave->dma_dev = &at_hdmac_device.dev;
	atslave->cfg = ATC_FIFOCFG_HALFFIFO
			| ATC_SRC_H2SEL_HW | ATC_DST_H2SEL_HW;
	if (mmc_id == 0)	/* MCI0 */
		atslave->cfg |= ATC_SRC_PER(AT_DMA_ID_MCI0)
			      | ATC_DST_PER(AT_DMA_ID_MCI0);

	else			/* MCI1 */
		atslave->cfg |= ATC_SRC_PER(AT_DMA_ID_MCI1)
			      | ATC_DST_PER(AT_DMA_ID_MCI1);

	data->dma_slave = alt_atslave;
	}
#endif


	/* input/irq */
	if (gpio_is_valid(data->slot[0].detect_pin)) {
		at91_set_gpio_input(data->slot[0].detect_pin, 1);
		at91_set_deglitch(data->slot[0].detect_pin, 1);
	}
	if (gpio_is_valid(data->slot[0].wp_pin))
		at91_set_gpio_input(data->slot[0].wp_pin, 1);

	if (mmc_id == 0) {		/* MCI0 */

		/* CLK */
		at91_set_A_periph(AT91_PIN_PA0, 0);

		/* CMD */
		at91_set_A_periph(AT91_PIN_PA1, 1);

		/* DAT0, maybe DAT1..DAT3 and maybe DAT4..DAT7 */
		at91_set_A_periph(AT91_PIN_PA2, 1);
		if (data->slot[0].bus_width == 4) {
			at91_set_A_periph(AT91_PIN_PA3, 1);
			at91_set_A_periph(AT91_PIN_PA4, 1);
			at91_set_A_periph(AT91_PIN_PA5, 1);
			if (data->slot[0].bus_width == 8) {
				at91_set_A_periph(AT91_PIN_PA6, 1);
				at91_set_A_periph(AT91_PIN_PA7, 1);
				at91_set_A_periph(AT91_PIN_PA8, 1);
				at91_set_A_periph(AT91_PIN_PA9, 1);
			}
		}

		mmc0_data = *data;
		platform_device_register(&at91sam9g45_mmc0_device);

	} else {			/* MCI1 */

		/* CLK */
		at91_set_A_periph(AT91_PIN_PA31, 0);

		/* CMD */
		at91_set_A_periph(AT91_PIN_PA22, 1);

		/* DAT0, maybe DAT1..DAT3 and maybe DAT4..DAT7 */
		at91_set_A_periph(AT91_PIN_PA23, 1);
		if (data->slot[0].bus_width == 4) {
			at91_set_A_periph(AT91_PIN_PA24, 1);
			at91_set_A_periph(AT91_PIN_PA25, 1);
			at91_set_A_periph(AT91_PIN_PA26, 1);
			if (data->slot[0].bus_width == 8) {
				at91_set_A_periph(AT91_PIN_PA27, 1);
				at91_set_A_periph(AT91_PIN_PA28, 1);
				at91_set_A_periph(AT91_PIN_PA29, 1);
				at91_set_A_periph(AT91_PIN_PA30, 1);
			}
		}

		mmc1_data = *data;
		platform_device_register(&at91sam9g45_mmc1_device);

	}
}
#else
void __init at91_add_device_mci(short mmc_id, struct mci_platform_data *data) {}
#endif


/* --------------------------------------------------------------------
 *  NAND / SmartMedia
 * -------------------------------------------------------------------- */

#if defined(CONFIG_MTD_NAND_ATMEL) || defined(CONFIG_MTD_NAND_ATMEL_MODULE)
static struct atmel_nand_data nand_data;

#define NAND_BASE	AT91_CHIPSELECT_3

static struct resource nand_resources[] = {
	[0] = {
		.start	= NAND_BASE,
		.end	= NAND_BASE + SZ_256M - 1,
		.flags	= IORESOURCE_MEM,
	},
	[1] = {
		.start	= AT91SAM9G45_BASE_ECC,
		.end	= AT91SAM9G45_BASE_ECC + SZ_512 - 1,
		.flags	= IORESOURCE_MEM,
	}
};

static struct platform_device at91sam9g45_nand_device = {
	.name		= "atmel_nand",
	.id		= -1,
	.dev		= {
				.platform_data	= &nand_data,
	},
	.resource	= nand_resources,
	.num_resources	= ARRAY_SIZE(nand_resources),
};

void __init at91_add_device_nand(struct atmel_nand_data *data)
{
	unsigned long csa;

	if (!data)
		return;

	csa = at91_matrix_read(AT91_MATRIX_EBICSA);
	at91_matrix_write(AT91_MATRIX_EBICSA, csa | AT91_MATRIX_EBI_CS3A_SMC_SMARTMEDIA);

	/* enable pin */
	if (gpio_is_valid(data->enable_pin))
		at91_set_gpio_output(data->enable_pin, 1);

	/* ready/busy pin */
	if (gpio_is_valid(data->rdy_pin))
		at91_set_gpio_input(data->rdy_pin, 1);

	/* card detect pin */
	if (gpio_is_valid(data->det_pin))
		at91_set_gpio_input(data->det_pin, 1);

	nand_data = *data;
	platform_device_register(&at91sam9g45_nand_device);
}
#else
void __init at91_add_device_nand(struct atmel_nand_data *data) {}
#endif


/* --------------------------------------------------------------------
 *  TWI (i2c)
 * -------------------------------------------------------------------- */

/*
 * Prefer the GPIO code since the TWI controller isn't robust
 * (gets overruns and underruns under load) and can only issue
 * repeated STARTs in one scenario (the driver doesn't yet handle them).
 */
#if defined(CONFIG_I2C_GPIO) || defined(CONFIG_I2C_GPIO_MODULE)
static struct i2c_gpio_platform_data pdata_i2c0 = {
	.sda_pin		= AT91_PIN_PA20,
	.sda_is_open_drain	= 1,
	.scl_pin		= AT91_PIN_PA21,
	.scl_is_open_drain	= 1,
	.udelay			= 5,		/* ~100 kHz */
};

static struct platform_device at91sam9g45_twi0_device = {
	.name			= "i2c-gpio",
	.id			= 0,
	.dev.platform_data	= &pdata_i2c0,
};

static struct i2c_gpio_platform_data pdata_i2c1 = {
	.sda_pin		= AT91_PIN_PB10,
	.sda_is_open_drain	= 1,
	.scl_pin		= AT91_PIN_PB11,
	.scl_is_open_drain	= 1,
	.udelay			= 5,		/* ~100 kHz */
};

static struct platform_device at91sam9g45_twi1_device = {
	.name			= "i2c-gpio",
	.id			= 1,
	.dev.platform_data	= &pdata_i2c1,
};

void __init at91_add_device_i2c(short i2c_id, struct i2c_board_info *devices, int nr_devices)
{
	i2c_register_board_info(i2c_id, devices, nr_devices);

	if (i2c_id == 0) {
		at91_set_GPIO_periph(AT91_PIN_PA20, 1);		/* TWD (SDA) */
		at91_set_multi_drive(AT91_PIN_PA20, 1);

		at91_set_GPIO_periph(AT91_PIN_PA21, 1);		/* TWCK (SCL) */
		at91_set_multi_drive(AT91_PIN_PA21, 1);

		platform_device_register(&at91sam9g45_twi0_device);
	} else {
		at91_set_GPIO_periph(AT91_PIN_PB10, 1);		/* TWD (SDA) */
		at91_set_multi_drive(AT91_PIN_PB10, 1);

		at91_set_GPIO_periph(AT91_PIN_PB11, 1);		/* TWCK (SCL) */
		at91_set_multi_drive(AT91_PIN_PB11, 1);

		platform_device_register(&at91sam9g45_twi1_device);
	}
}

#elif defined(CONFIG_I2C_AT91) || defined(CONFIG_I2C_AT91_MODULE)
static struct resource twi0_resources[] = {
	[0] = {
		.start	= AT91SAM9G45_BASE_TWI0,
		.end	= AT91SAM9G45_BASE_TWI0 + SZ_16K - 1,
		.flags	= IORESOURCE_MEM,
	},
	[1] = {
		.start	= NR_IRQS_LEGACY + AT91SAM9G45_ID_TWI0,
		.end	= NR_IRQS_LEGACY + AT91SAM9G45_ID_TWI0,
		.flags	= IORESOURCE_IRQ,
	},
};

static struct platform_device at91sam9g45_twi0_device = {
	.name		= "at91_i2c",
	.id		= 0,
	.resource	= twi0_resources,
	.num_resources	= ARRAY_SIZE(twi0_resources),
};

static struct resource twi1_resources[] = {
	[0] = {
		.start	= AT91SAM9G45_BASE_TWI1,
		.end	= AT91SAM9G45_BASE_TWI1 + SZ_16K - 1,
		.flags	= IORESOURCE_MEM,
	},
	[1] = {
		.start	= NR_IRQS_LEGACY + AT91SAM9G45_ID_TWI1,
		.end	= NR_IRQS_LEGACY + AT91SAM9G45_ID_TWI1,
		.flags	= IORESOURCE_IRQ,
	},
};

static struct platform_device at91sam9g45_twi1_device = {
	.name		= "at91_i2c",
	.id		= 1,
	.resource	= twi1_resources,
	.num_resources	= ARRAY_SIZE(twi1_resources),
};

void __init at91_add_device_i2c(short i2c_id, struct i2c_board_info *devices, int nr_devices)
{
	i2c_register_board_info(i2c_id, devices, nr_devices);

	/* pins used for TWI interface */
	if (i2c_id == 0) {
		at91_set_A_periph(AT91_PIN_PA20, 0);		/* TWD */
		at91_set_multi_drive(AT91_PIN_PA20, 1);

		at91_set_A_periph(AT91_PIN_PA21, 0);		/* TWCK */
		at91_set_multi_drive(AT91_PIN_PA21, 1);

		platform_device_register(&at91sam9g45_twi0_device);
	} else {
		at91_set_A_periph(AT91_PIN_PB10, 0);		/* TWD */
		at91_set_multi_drive(AT91_PIN_PB10, 1);

		at91_set_A_periph(AT91_PIN_PB11, 0);		/* TWCK */
		at91_set_multi_drive(AT91_PIN_PB11, 1);

		platform_device_register(&at91sam9g45_twi1_device);
	}
}
#else
void __init at91_add_device_i2c(short i2c_id, struct i2c_board_info *devices, int nr_devices) {}
#endif


/* --------------------------------------------------------------------
 *  SPI
 * -------------------------------------------------------------------- */

#if defined(CONFIG_SPI_ATMEL) || defined(CONFIG_SPI_ATMEL_MODULE)
static u64 spi_dmamask = DMA_BIT_MASK(32);

static struct resource spi0_resources[] = {
	[0] = {
		.start	= AT91SAM9G45_BASE_SPI0,
		.end	= AT91SAM9G45_BASE_SPI0 + SZ_16K - 1,
		.flags	= IORESOURCE_MEM,
	},
	[1] = {
		.start	= NR_IRQS_LEGACY + AT91SAM9G45_ID_SPI0,
		.end	= NR_IRQS_LEGACY + AT91SAM9G45_ID_SPI0,
		.flags	= IORESOURCE_IRQ,
	},
};

static struct platform_device at91sam9g45_spi0_device = {
	.name		= "atmel_spi",
	.id		= 0,
	.dev		= {
				.dma_mask		= &spi_dmamask,
				.coherent_dma_mask	= DMA_BIT_MASK(32),
	},
	.resource	= spi0_resources,
	.num_resources	= ARRAY_SIZE(spi0_resources),
};

static const unsigned spi0_standard_cs[4] = { AT91_PIN_PB3, AT91_PIN_PB18, AT91_PIN_PB19, AT91_PIN_PD27 };

static struct resource spi1_resources[] = {
	[0] = {
		.start	= AT91SAM9G45_BASE_SPI1,
		.end	= AT91SAM9G45_BASE_SPI1 + SZ_16K - 1,
		.flags	= IORESOURCE_MEM,
	},
	[1] = {
		.start	= NR_IRQS_LEGACY + AT91SAM9G45_ID_SPI1,
		.end	= NR_IRQS_LEGACY + AT91SAM9G45_ID_SPI1,
		.flags	= IORESOURCE_IRQ,
	},
};

static struct platform_device at91sam9g45_spi1_device = {
	.name		= "atmel_spi",
	.id		= 1,
	.dev		= {
				.dma_mask		= &spi_dmamask,
				.coherent_dma_mask	= DMA_BIT_MASK(32),
	},
	.resource	= spi1_resources,
	.num_resources	= ARRAY_SIZE(spi1_resources),
};

static const unsigned spi1_standard_cs[4] = { AT91_PIN_PB17, AT91_PIN_PD28, AT91_PIN_PD18, AT91_PIN_PD19 };

void __init at91_add_device_spi(struct spi_board_info *devices, int nr_devices)
{
	int i;
	unsigned long cs_pin;
	short enable_spi0 = 0;
	short enable_spi1 = 0;

	/* Choose SPI chip-selects */
	for (i = 0; i < nr_devices; i++) {
		if (devices[i].controller_data)
			cs_pin = (unsigned long) devices[i].controller_data;
		else if (devices[i].bus_num == 0)
			cs_pin = spi0_standard_cs[devices[i].chip_select];
		else
			cs_pin = spi1_standard_cs[devices[i].chip_select];

		if (!gpio_is_valid(cs_pin))
			continue;

		if (devices[i].bus_num == 0)
			enable_spi0 = 1;
		else
			enable_spi1 = 1;

		/* enable chip-select pin */
		at91_set_gpio_output(cs_pin, 1);

		/* pass chip-select pin to driver */
		devices[i].controller_data = (void *) cs_pin;
	}

	spi_register_board_info(devices, nr_devices);

	/* Configure SPI bus(es) */
	if (enable_spi0) {
		at91_set_A_periph(AT91_PIN_PB0, 0);	/* SPI0_MISO */
		at91_set_A_periph(AT91_PIN_PB1, 0);	/* SPI0_MOSI */
		at91_set_A_periph(AT91_PIN_PB2, 0);	/* SPI0_SPCK */

		platform_device_register(&at91sam9g45_spi0_device);
	}
	if (enable_spi1) {
		at91_set_A_periph(AT91_PIN_PB14, 0);	/* SPI1_MISO */
		at91_set_A_periph(AT91_PIN_PB15, 0);	/* SPI1_MOSI */
		at91_set_A_periph(AT91_PIN_PB16, 0);	/* SPI1_SPCK */

		platform_device_register(&at91sam9g45_spi1_device);
	}
}
#else
void __init at91_add_device_spi(struct spi_board_info *devices, int nr_devices) {}
#endif


/* --------------------------------------------------------------------
 *  AC97
 * -------------------------------------------------------------------- */

#if defined(CONFIG_SND_ATMEL_AC97C) || defined(CONFIG_SND_ATMEL_AC97C_MODULE)
static u64 ac97_dmamask = DMA_BIT_MASK(32);
static struct ac97c_platform_data ac97_data;

static struct resource ac97_resources[] = {
	[0] = {
		.start	= AT91SAM9G45_BASE_AC97C,
		.end	= AT91SAM9G45_BASE_AC97C + SZ_16K - 1,
		.flags	= IORESOURCE_MEM,
	},
	[1] = {
		.start	= NR_IRQS_LEGACY + AT91SAM9G45_ID_AC97C,
		.end	= NR_IRQS_LEGACY + AT91SAM9G45_ID_AC97C,
		.flags	= IORESOURCE_IRQ,
	},
};

static struct platform_device at91sam9g45_ac97_device = {
	.name		= "atmel_ac97c",
	.id		= 0,
	.dev		= {
				.dma_mask		= &ac97_dmamask,
				.coherent_dma_mask	= DMA_BIT_MASK(32),
				.platform_data		= &ac97_data,
	},
	.resource	= ac97_resources,
	.num_resources	= ARRAY_SIZE(ac97_resources),
};

void __init at91_add_device_ac97(struct ac97c_platform_data *data)
{
	if (!data)
		return;

	at91_set_A_periph(AT91_PIN_PD8, 0);	/* AC97FS */
	at91_set_A_periph(AT91_PIN_PD9, 0);	/* AC97CK */
	at91_set_A_periph(AT91_PIN_PD7, 0);	/* AC97TX */
	at91_set_A_periph(AT91_PIN_PD6, 0);	/* AC97RX */

	/* reset */
	if (gpio_is_valid(data->reset_pin))
		at91_set_gpio_output(data->reset_pin, 0);

	ac97_data = *data;
	platform_device_register(&at91sam9g45_ac97_device);
}
#else
void __init at91_add_device_ac97(struct ac97c_platform_data *data) {}
#endif

/* --------------------------------------------------------------------
 *  Image Sensor Interface
 * -------------------------------------------------------------------- */
#if defined(CONFIG_VIDEO_ATMEL_ISI) || defined(CONFIG_VIDEO_ATMEL_ISI_MODULE)
static u64 isi_dmamask = DMA_BIT_MASK(32);
static struct isi_platform_data isi_data;

struct resource isi_resources[] = {
	[0] = {
		.start	= AT91SAM9G45_BASE_ISI,
		.end	= AT91SAM9G45_BASE_ISI + SZ_16K - 1,
		.flags	= IORESOURCE_MEM,
	},
	[1] = {
		.start	= NR_IRQS_LEGACY + AT91SAM9G45_ID_ISI,
		.end	= NR_IRQS_LEGACY + AT91SAM9G45_ID_ISI,
		.flags	= IORESOURCE_IRQ,
	},
};

static struct platform_device at91sam9g45_isi_device = {
	.name		= "atmel_isi",
	.id		= 0,
	.dev		= {
			.dma_mask		= &isi_dmamask,
			.coherent_dma_mask	= DMA_BIT_MASK(32),
			.platform_data		= &isi_data,
	},
	.resource	= isi_resources,
	.num_resources	= ARRAY_SIZE(isi_resources),
};

static struct clk_lookup isi_mck_lookups[] = {
	CLKDEV_CON_DEV_ID("isi_mck", "atmel_isi.0", NULL),
};

void __init at91_add_device_isi(struct isi_platform_data *data,
		bool use_pck_as_mck)
{
	struct clk *pck;
	struct clk *parent;

	if (!data)
		return;
	isi_data = *data;

	at91_set_A_periph(AT91_PIN_PB20, 0);	/* ISI_D0 */
	at91_set_A_periph(AT91_PIN_PB21, 0);	/* ISI_D1 */
	at91_set_A_periph(AT91_PIN_PB22, 0);	/* ISI_D2 */
	at91_set_A_periph(AT91_PIN_PB23, 0);	/* ISI_D3 */
	at91_set_A_periph(AT91_PIN_PB24, 0);	/* ISI_D4 */
	at91_set_A_periph(AT91_PIN_PB25, 0);	/* ISI_D5 */
	at91_set_A_periph(AT91_PIN_PB26, 0);	/* ISI_D6 */
	at91_set_A_periph(AT91_PIN_PB27, 0);	/* ISI_D7 */
	at91_set_A_periph(AT91_PIN_PB28, 0);	/* ISI_PCK */
	at91_set_A_periph(AT91_PIN_PB30, 0);	/* ISI_HSYNC */
	at91_set_A_periph(AT91_PIN_PB29, 0);	/* ISI_VSYNC */
	at91_set_B_periph(AT91_PIN_PB8, 0);	/* ISI_PD8 */
	at91_set_B_periph(AT91_PIN_PB9, 0);	/* ISI_PD9 */
	at91_set_B_periph(AT91_PIN_PB10, 0);	/* ISI_PD10 */
	at91_set_B_periph(AT91_PIN_PB11, 0);	/* ISI_PD11 */

	platform_device_register(&at91sam9g45_isi_device);

	if (use_pck_as_mck) {
		at91_set_B_periph(AT91_PIN_PB31, 0);	/* ISI_MCK (PCK1) */

		pck = clk_get(NULL, "pck1");
		parent = clk_get(NULL, "plla");

		BUG_ON(IS_ERR(pck) || IS_ERR(parent));

		if (clk_set_parent(pck, parent)) {
			pr_err("Failed to set PCK's parent\n");
		} else {
			/* Register PCK as ISI_MCK */
			isi_mck_lookups[0].clk = pck;
			clkdev_add_table(isi_mck_lookups,
					ARRAY_SIZE(isi_mck_lookups));
		}

		clk_put(pck);
		clk_put(parent);
	}
}
#else
void __init at91_add_device_isi(struct isi_platform_data *data,
		bool use_pck_as_mck) {}
#endif


/* --------------------------------------------------------------------
 *  LCD Controller
 * -------------------------------------------------------------------- */

#if defined(CONFIG_FB_ATMEL) || defined(CONFIG_FB_ATMEL_MODULE)
static u64 lcdc_dmamask = DMA_BIT_MASK(32);
static struct atmel_lcdfb_info lcdc_data;

static struct resource lcdc_resources[] = {
	[0] = {
		.start	= AT91SAM9G45_LCDC_BASE,
		.end	= AT91SAM9G45_LCDC_BASE + SZ_4K - 1,
		.flags	= IORESOURCE_MEM,
	},
	[1] = {
		.start	= NR_IRQS_LEGACY + AT91SAM9G45_ID_LCDC,
		.end	= NR_IRQS_LEGACY + AT91SAM9G45_ID_LCDC,
		.flags	= IORESOURCE_IRQ,
	},
};

static struct platform_device at91_lcdc_device = {
	.name		= "atmel_lcdfb",
	.id		= 0,
	.dev		= {
				.dma_mask		= &lcdc_dmamask,
				.coherent_dma_mask	= DMA_BIT_MASK(32),
				.platform_data		= &lcdc_data,
	},
	.resource	= lcdc_resources,
	.num_resources	= ARRAY_SIZE(lcdc_resources),
};

void __init at91_add_device_lcdc(struct atmel_lcdfb_info *data)
{
	if (!data)
		return;

	at91_set_A_periph(AT91_PIN_PE0, 0);	/* LCDDPWR */

	at91_set_A_periph(AT91_PIN_PE2, 0);	/* LCDCC */
	at91_set_A_periph(AT91_PIN_PE3, 0);	/* LCDVSYNC */
	at91_set_A_periph(AT91_PIN_PE4, 0);	/* LCDHSYNC */
	at91_set_A_periph(AT91_PIN_PE5, 0);	/* LCDDOTCK */
	at91_set_A_periph(AT91_PIN_PE6, 0);	/* LCDDEN */
	at91_set_A_periph(AT91_PIN_PE7, 0);	/* LCDD0 */
	at91_set_A_periph(AT91_PIN_PE8, 0);	/* LCDD1 */
	at91_set_A_periph(AT91_PIN_PE9, 0);	/* LCDD2 */
	at91_set_A_periph(AT91_PIN_PE10, 0);	/* LCDD3 */
	at91_set_A_periph(AT91_PIN_PE11, 0);	/* LCDD4 */
	at91_set_A_periph(AT91_PIN_PE12, 0);	/* LCDD5 */
	at91_set_A_periph(AT91_PIN_PE13, 0);	/* LCDD6 */
	at91_set_A_periph(AT91_PIN_PE14, 0);	/* LCDD7 */
	at91_set_A_periph(AT91_PIN_PE15, 0);	/* LCDD8 */
	at91_set_A_periph(AT91_PIN_PE16, 0);	/* LCDD9 */
	at91_set_A_periph(AT91_PIN_PE17, 0);	/* LCDD10 */
	at91_set_A_periph(AT91_PIN_PE18, 0);	/* LCDD11 */
	at91_set_A_periph(AT91_PIN_PE19, 0);	/* LCDD12 */
	at91_set_A_periph(AT91_PIN_PE20, 0);	/* LCDD13 */
	at91_set_A_periph(AT91_PIN_PE21, 0);	/* LCDD14 */
	at91_set_A_periph(AT91_PIN_PE22, 0);	/* LCDD15 */
	at91_set_A_periph(AT91_PIN_PE23, 0);	/* LCDD16 */
	at91_set_A_periph(AT91_PIN_PE24, 0);	/* LCDD17 */
	at91_set_A_periph(AT91_PIN_PE25, 0);	/* LCDD18 */
	at91_set_A_periph(AT91_PIN_PE26, 0);	/* LCDD19 */
	at91_set_A_periph(AT91_PIN_PE27, 0);	/* LCDD20 */
	at91_set_A_periph(AT91_PIN_PE28, 0);	/* LCDD21 */
	at91_set_A_periph(AT91_PIN_PE29, 0);	/* LCDD22 */
	at91_set_A_periph(AT91_PIN_PE30, 0);	/* LCDD23 */

	lcdc_data = *data;
	platform_device_register(&at91_lcdc_device);
}
#else
void __init at91_add_device_lcdc(struct atmel_lcdfb_info *data) {}
#endif


/* --------------------------------------------------------------------
 *  Timer/Counter block
 * -------------------------------------------------------------------- */

#ifdef CONFIG_ATMEL_TCLIB
static struct resource tcb0_resources[] = {
	[0] = {
		.start	= AT91SAM9G45_BASE_TCB0,
		.end	= AT91SAM9G45_BASE_TCB0 + SZ_256 - 1,
		.flags	= IORESOURCE_MEM,
	},
	[1] = {
		.start	= NR_IRQS_LEGACY + AT91SAM9G45_ID_TCB,
		.end	= NR_IRQS_LEGACY + AT91SAM9G45_ID_TCB,
		.flags	= IORESOURCE_IRQ,
	},
};

static struct platform_device at91sam9g45_tcb0_device = {
	.name		= "atmel_tcb",
	.id		= 0,
	.resource	= tcb0_resources,
	.num_resources	= ARRAY_SIZE(tcb0_resources),
};

/* TCB1 begins with TC3 */
static struct resource tcb1_resources[] = {
	[0] = {
		.start	= AT91SAM9G45_BASE_TCB1,
		.end	= AT91SAM9G45_BASE_TCB1 + SZ_256 - 1,
		.flags	= IORESOURCE_MEM,
	},
	[1] = {
		.start	= NR_IRQS_LEGACY + AT91SAM9G45_ID_TCB,
		.end	= NR_IRQS_LEGACY + AT91SAM9G45_ID_TCB,
		.flags	= IORESOURCE_IRQ,
	},
};

static struct platform_device at91sam9g45_tcb1_device = {
	.name		= "atmel_tcb",
	.id		= 1,
	.resource	= tcb1_resources,
	.num_resources	= ARRAY_SIZE(tcb1_resources),
};

static void __init at91_add_device_tc(void)
{
	platform_device_register(&at91sam9g45_tcb0_device);
	platform_device_register(&at91sam9g45_tcb1_device);
}
#else
static void __init at91_add_device_tc(void) { }
#endif


/* --------------------------------------------------------------------
 *  RTC
 * -------------------------------------------------------------------- */

#if defined(CONFIG_RTC_DRV_AT91RM9200) || defined(CONFIG_RTC_DRV_AT91RM9200_MODULE)
static struct resource rtc_resources[] = {
	[0] = {
		.start	= AT91SAM9G45_BASE_RTC,
		.end	= AT91SAM9G45_BASE_RTC + SZ_256 - 1,
		.flags	= IORESOURCE_MEM,
	},
	[1] = {
		.start	= NR_IRQS_LEGACY + AT91_ID_SYS,
		.end	= NR_IRQS_LEGACY + AT91_ID_SYS,
		.flags	= IORESOURCE_IRQ,
	},
};

static struct platform_device at91sam9g45_rtc_device = {
	.name		= "at91_rtc",
	.id		= -1,
	.resource	= rtc_resources,
	.num_resources	= ARRAY_SIZE(rtc_resources),
};

static void __init at91_add_device_rtc(void)
{
	platform_device_register(&at91sam9g45_rtc_device);
}
#else
static void __init at91_add_device_rtc(void) {}
#endif


/* --------------------------------------------------------------------
 *  Touchscreen
 * -------------------------------------------------------------------- */

#if defined(CONFIG_TOUCHSCREEN_ATMEL_TSADCC) || defined(CONFIG_TOUCHSCREEN_ATMEL_TSADCC_MODULE)
static u64 tsadcc_dmamask = DMA_BIT_MASK(32);
static struct at91_tsadcc_data tsadcc_data;

static struct resource tsadcc_resources[] = {
	[0] = {
		.start	= AT91SAM9G45_BASE_TSC,
		.end	= AT91SAM9G45_BASE_TSC + SZ_16K - 1,
		.flags	= IORESOURCE_MEM,
	},
	[1] = {
		.start	= NR_IRQS_LEGACY + AT91SAM9G45_ID_TSC,
		.end	= NR_IRQS_LEGACY + AT91SAM9G45_ID_TSC,
		.flags	= IORESOURCE_IRQ,
	}
};

static struct platform_device at91sam9g45_tsadcc_device = {
	.name		= "atmel_tsadcc",
	.id		= -1,
	.dev		= {
				.dma_mask		= &tsadcc_dmamask,
				.coherent_dma_mask	= DMA_BIT_MASK(32),
				.platform_data		= &tsadcc_data,
	},
	.resource	= tsadcc_resources,
	.num_resources	= ARRAY_SIZE(tsadcc_resources),
};

void __init at91_add_device_tsadcc(struct at91_tsadcc_data *data)
{
	if (!data)
		return;

	at91_set_gpio_input(AT91_PIN_PD20, 0);	/* AD0_XR */
	at91_set_gpio_input(AT91_PIN_PD21, 0);	/* AD1_XL */
	at91_set_gpio_input(AT91_PIN_PD22, 0);	/* AD2_YT */
	at91_set_gpio_input(AT91_PIN_PD23, 0);	/* AD3_TB */

	tsadcc_data = *data;
	platform_device_register(&at91sam9g45_tsadcc_device);
}
#else
void __init at91_add_device_tsadcc(struct at91_tsadcc_data *data) {}
#endif


/* --------------------------------------------------------------------
 *  ADC
 * -------------------------------------------------------------------- */

#if IS_ENABLED(CONFIG_AT91_ADC)
static struct at91_adc_data adc_data;

static struct resource adc_resources[] = {
	[0] = {
		.start	= AT91SAM9G45_BASE_TSC,
		.end	= AT91SAM9G45_BASE_TSC + SZ_16K - 1,
		.flags	= IORESOURCE_MEM,
	},
	[1] = {
		.start	= NR_IRQS_LEGACY + AT91SAM9G45_ID_TSC,
		.end	= NR_IRQS_LEGACY + AT91SAM9G45_ID_TSC,
		.flags	= IORESOURCE_IRQ,
	}
};

static struct platform_device at91_adc_device = {
	.name		= "at91_adc",
	.id		= -1,
	.dev		= {
				.platform_data	= &adc_data,
	},
	.resource	= adc_resources,
	.num_resources	= ARRAY_SIZE(adc_resources),
};

static struct at91_adc_trigger at91_adc_triggers[] = {
	[0] = {
		.name = "external-rising",
		.value = 1,
		.is_external = true,
	},
	[1] = {
		.name = "external-falling",
		.value = 2,
		.is_external = true,
	},
	[2] = {
		.name = "external-any",
		.value = 3,
		.is_external = true,
	},
	[3] = {
		.name = "continuous",
		.value = 6,
		.is_external = false,
	},
};

static struct at91_adc_reg_desc at91_adc_register_g45 = {
	.channel_base = AT91_ADC_CHR(0),
	.drdy_mask = AT91_ADC_DRDY,
	.status_register = AT91_ADC_SR,
	.trigger_register = 0x08,
};

void __init at91_add_device_adc(struct at91_adc_data *data)
{
	if (!data)
		return;

	if (test_bit(0, &data->channels_used))
		at91_set_gpio_input(AT91_PIN_PD20, 0);
	if (test_bit(1, &data->channels_used))
		at91_set_gpio_input(AT91_PIN_PD21, 0);
	if (test_bit(2, &data->channels_used))
		at91_set_gpio_input(AT91_PIN_PD22, 0);
	if (test_bit(3, &data->channels_used))
		at91_set_gpio_input(AT91_PIN_PD23, 0);
	if (test_bit(4, &data->channels_used))
		at91_set_gpio_input(AT91_PIN_PD24, 0);
	if (test_bit(5, &data->channels_used))
		at91_set_gpio_input(AT91_PIN_PD25, 0);
	if (test_bit(6, &data->channels_used))
		at91_set_gpio_input(AT91_PIN_PD26, 0);
	if (test_bit(7, &data->channels_used))
		at91_set_gpio_input(AT91_PIN_PD27, 0);

	if (data->use_external_triggers)
		at91_set_A_periph(AT91_PIN_PD28, 0);

	data->num_channels = 8;
	data->startup_time = 40;
	data->registers = &at91_adc_register_g45;
	data->trigger_number = 4;
	data->trigger_list = at91_adc_triggers;

	adc_data = *data;
	platform_device_register(&at91_adc_device);
}
#else
void __init at91_add_device_adc(struct at91_adc_data *data) {}
#endif

/* --------------------------------------------------------------------
 *  RTT
 * -------------------------------------------------------------------- */

static struct resource rtt_resources[] = {
	{
		.start	= AT91SAM9G45_BASE_RTT,
		.end	= AT91SAM9G45_BASE_RTT + SZ_16 - 1,
		.flags	= IORESOURCE_MEM,
	}, {
		.flags	= IORESOURCE_MEM,
	}, {
		.flags  = IORESOURCE_IRQ,
	}
};

static struct platform_device at91sam9g45_rtt_device = {
	.name		= "at91_rtt",
	.id		= 0,
	.resource	= rtt_resources,
};

#if IS_ENABLED(CONFIG_RTC_DRV_AT91SAM9)
static void __init at91_add_device_rtt_rtc(void)
{
	at91sam9g45_rtt_device.name = "rtc-at91sam9";
	/*
	 * The second resource is needed:
	 * GPBR will serve as the storage for RTC time offset
	 */
	at91sam9g45_rtt_device.num_resources = 3;
	rtt_resources[1].start = AT91SAM9G45_BASE_GPBR +
				 4 * CONFIG_RTC_DRV_AT91SAM9_GPBR;
	rtt_resources[1].end = rtt_resources[1].start + 3;
	rtt_resources[2].start = NR_IRQS_LEGACY + AT91_ID_SYS;
	rtt_resources[2].end = NR_IRQS_LEGACY + AT91_ID_SYS;
}
#else
static void __init at91_add_device_rtt_rtc(void)
{
	/* Only one resource is needed: RTT not used as RTC */
	at91sam9g45_rtt_device.num_resources = 1;
}
#endif

static void __init at91_add_device_rtt(void)
{
	at91_add_device_rtt_rtc();
	platform_device_register(&at91sam9g45_rtt_device);
}


/* --------------------------------------------------------------------
 *  TRNG
 * -------------------------------------------------------------------- */

#if defined(CONFIG_HW_RANDOM_ATMEL) || defined(CONFIG_HW_RANDOM_ATMEL_MODULE)
static struct resource trng_resources[] = {
	{
		.start	= AT91SAM9G45_BASE_TRNG,
		.end	= AT91SAM9G45_BASE_TRNG + SZ_16K - 1,
		.flags	= IORESOURCE_MEM,
	},
};

static struct platform_device at91sam9g45_trng_device = {
	.name		= "atmel-trng",
	.id		= -1,
	.resource	= trng_resources,
	.num_resources	= ARRAY_SIZE(trng_resources),
};

static void __init at91_add_device_trng(void)
{
	platform_device_register(&at91sam9g45_trng_device);
}
#else
static void __init at91_add_device_trng(void) {}
#endif

/* --------------------------------------------------------------------
 *  Watchdog
 * -------------------------------------------------------------------- */

#if defined(CONFIG_AT91SAM9X_WATCHDOG) || defined(CONFIG_AT91SAM9X_WATCHDOG_MODULE)
static struct resource wdt_resources[] = {
	{
		.start	= AT91SAM9G45_BASE_WDT,
		.end	= AT91SAM9G45_BASE_WDT + SZ_16 - 1,
		.flags	= IORESOURCE_MEM,
	}
};

static struct platform_device at91sam9g45_wdt_device = {
	.name		= "at91_wdt",
	.id		= -1,
	.resource	= wdt_resources,
	.num_resources	= ARRAY_SIZE(wdt_resources),
};

static void __init at91_add_device_watchdog(void)
{
	platform_device_register(&at91sam9g45_wdt_device);
}
#else
static void __init at91_add_device_watchdog(void) {}
#endif


/* --------------------------------------------------------------------
 *  PWM
 * --------------------------------------------------------------------*/

#if defined(CONFIG_ATMEL_PWM) || defined(CONFIG_ATMEL_PWM_MODULE)
static u32 pwm_mask;

static struct resource pwm_resources[] = {
	[0] = {
		.start	= AT91SAM9G45_BASE_PWMC,
		.end	= AT91SAM9G45_BASE_PWMC + SZ_16K - 1,
		.flags	= IORESOURCE_MEM,
	},
	[1] = {
		.start	= NR_IRQS_LEGACY + AT91SAM9G45_ID_PWMC,
		.end	= NR_IRQS_LEGACY + AT91SAM9G45_ID_PWMC,
		.flags	= IORESOURCE_IRQ,
	},
};

static struct platform_device at91sam9g45_pwm0_device = {
	.name	= "atmel_pwm",
	.id	= -1,
	.dev	= {
		.platform_data		= &pwm_mask,
	},
	.resource	= pwm_resources,
	.num_resources	= ARRAY_SIZE(pwm_resources),
};

void __init at91_add_device_pwm(u32 mask)
{
	if (mask & (1 << AT91_PWM0))
		at91_set_B_periph(AT91_PIN_PD24, 1);	/* enable PWM0 */

	if (mask & (1 << AT91_PWM1))
		at91_set_B_periph(AT91_PIN_PD31, 1);	/* enable PWM1 */

	if (mask & (1 << AT91_PWM2))
		at91_set_B_periph(AT91_PIN_PD26, 1);	/* enable PWM2 */

	if (mask & (1 << AT91_PWM3))
		at91_set_B_periph(AT91_PIN_PD0, 1);	/* enable PWM3 */

	pwm_mask = mask;

	platform_device_register(&at91sam9g45_pwm0_device);
}
#else
void __init at91_add_device_pwm(u32 mask) {}
#endif


/* --------------------------------------------------------------------
 *  SSC -- Synchronous Serial Controller
 * -------------------------------------------------------------------- */

#if defined(CONFIG_ATMEL_SSC) || defined(CONFIG_ATMEL_SSC_MODULE)
static u64 ssc0_dmamask = DMA_BIT_MASK(32);

static struct resource ssc0_resources[] = {
	[0] = {
		.start	= AT91SAM9G45_BASE_SSC0,
		.end	= AT91SAM9G45_BASE_SSC0 + SZ_16K - 1,
		.flags	= IORESOURCE_MEM,
	},
	[1] = {
		.start	= NR_IRQS_LEGACY + AT91SAM9G45_ID_SSC0,
		.end	= NR_IRQS_LEGACY + AT91SAM9G45_ID_SSC0,
		.flags	= IORESOURCE_IRQ,
	},
};

static struct platform_device at91sam9g45_ssc0_device = {
	.name	= "ssc",
	.id	= 0,
	.dev	= {
		.dma_mask		= &ssc0_dmamask,
		.coherent_dma_mask	= DMA_BIT_MASK(32),
	},
	.resource	= ssc0_resources,
	.num_resources	= ARRAY_SIZE(ssc0_resources),
};

static inline void configure_ssc0_pins(unsigned pins)
{
	if (pins & ATMEL_SSC_TF)
		at91_set_A_periph(AT91_PIN_PD1, 1);
	if (pins & ATMEL_SSC_TK)
		at91_set_A_periph(AT91_PIN_PD0, 1);
	if (pins & ATMEL_SSC_TD)
		at91_set_A_periph(AT91_PIN_PD2, 1);
	if (pins & ATMEL_SSC_RD)
		at91_set_A_periph(AT91_PIN_PD3, 1);
	if (pins & ATMEL_SSC_RK)
		at91_set_A_periph(AT91_PIN_PD4, 1);
	if (pins & ATMEL_SSC_RF)
		at91_set_A_periph(AT91_PIN_PD5, 1);
}

static u64 ssc1_dmamask = DMA_BIT_MASK(32);

static struct resource ssc1_resources[] = {
	[0] = {
		.start	= AT91SAM9G45_BASE_SSC1,
		.end	= AT91SAM9G45_BASE_SSC1 + SZ_16K - 1,
		.flags	= IORESOURCE_MEM,
	},
	[1] = {
		.start	= NR_IRQS_LEGACY + AT91SAM9G45_ID_SSC1,
		.end	= NR_IRQS_LEGACY + AT91SAM9G45_ID_SSC1,
		.flags	= IORESOURCE_IRQ,
	},
};

static struct platform_device at91sam9g45_ssc1_device = {
	.name	= "ssc",
	.id	= 1,
	.dev	= {
		.dma_mask		= &ssc1_dmamask,
		.coherent_dma_mask	= DMA_BIT_MASK(32),
	},
	.resource	= ssc1_resources,
	.num_resources	= ARRAY_SIZE(ssc1_resources),
};

static inline void configure_ssc1_pins(unsigned pins)
{
	if (pins & ATMEL_SSC_TF)
		at91_set_A_periph(AT91_PIN_PD14, 1);
	if (pins & ATMEL_SSC_TK)
		at91_set_A_periph(AT91_PIN_PD12, 1);
	if (pins & ATMEL_SSC_TD)
		at91_set_A_periph(AT91_PIN_PD10, 1);
	if (pins & ATMEL_SSC_RD)
		at91_set_A_periph(AT91_PIN_PD11, 1);
	if (pins & ATMEL_SSC_RK)
		at91_set_A_periph(AT91_PIN_PD13, 1);
	if (pins & ATMEL_SSC_RF)
		at91_set_A_periph(AT91_PIN_PD15, 1);
}

/*
 * SSC controllers are accessed through library code, instead of any
 * kind of all-singing/all-dancing driver.  For example one could be
 * used by a particular I2S audio codec's driver, while another one
 * on the same system might be used by a custom data capture driver.
 */
void __init at91_add_device_ssc(unsigned id, unsigned pins)
{
	struct platform_device *pdev;

	/*
	 * NOTE: caller is responsible for passing information matching
	 * "pins" to whatever will be using each particular controller.
	 */
	switch (id) {
	case AT91SAM9G45_ID_SSC0:
		pdev = &at91sam9g45_ssc0_device;
		configure_ssc0_pins(pins);
		break;
	case AT91SAM9G45_ID_SSC1:
		pdev = &at91sam9g45_ssc1_device;
		configure_ssc1_pins(pins);
		break;
	default:
		return;
	}

	platform_device_register(pdev);
}

#else
void __init at91_add_device_ssc(unsigned id, unsigned pins) {}
#endif


/* --------------------------------------------------------------------
 *  UART
 * -------------------------------------------------------------------- */

#if defined(CONFIG_SERIAL_ATMEL)
static struct resource dbgu_resources[] = {
	[0] = {
		.start	= AT91SAM9G45_BASE_DBGU,
		.end	= AT91SAM9G45_BASE_DBGU + SZ_512 - 1,
		.flags	= IORESOURCE_MEM,
	},
	[1] = {
		.start	= NR_IRQS_LEGACY + AT91_ID_SYS,
		.end	= NR_IRQS_LEGACY + AT91_ID_SYS,
		.flags	= IORESOURCE_IRQ,
	},
};

static struct atmel_uart_data dbgu_data = {
	.use_dma_tx	= 0,
	.use_dma_rx	= 0,
};

static u64 dbgu_dmamask = DMA_BIT_MASK(32);

static struct platform_device at91sam9g45_dbgu_device = {
	.name		= "atmel_usart",
	.id		= 0,
	.dev		= {
				.dma_mask		= &dbgu_dmamask,
				.coherent_dma_mask	= DMA_BIT_MASK(32),
				.platform_data		= &dbgu_data,
	},
	.resource	= dbgu_resources,
	.num_resources	= ARRAY_SIZE(dbgu_resources),
};

static inline void configure_dbgu_pins(void)
{
	at91_set_A_periph(AT91_PIN_PB12, 0);		/* DRXD */
	at91_set_A_periph(AT91_PIN_PB13, 1);		/* DTXD */
}

static struct resource uart0_resources[] = {
	[0] = {
		.start	= AT91SAM9G45_BASE_US0,
		.end	= AT91SAM9G45_BASE_US0 + SZ_16K - 1,
		.flags	= IORESOURCE_MEM,
	},
	[1] = {
		.start	= NR_IRQS_LEGACY + AT91SAM9G45_ID_US0,
		.end	= NR_IRQS_LEGACY + AT91SAM9G45_ID_US0,
		.flags	= IORESOURCE_IRQ,
	},
};

static struct atmel_uart_data uart0_data = {
	.use_dma_tx	= 1,
	.use_dma_rx	= 1,
};

static u64 uart0_dmamask = DMA_BIT_MASK(32);

static struct platform_device at91sam9g45_uart0_device = {
	.name		= "atmel_usart",
	.id		= 1,
	.dev		= {
				.dma_mask		= &uart0_dmamask,
				.coherent_dma_mask	= DMA_BIT_MASK(32),
				.platform_data		= &uart0_data,
	},
	.resource	= uart0_resources,
	.num_resources	= ARRAY_SIZE(uart0_resources),
};

static inline void configure_usart0_pins(unsigned pins)
{
	at91_set_A_periph(AT91_PIN_PB19, 1);		/* TXD0 */
	at91_set_A_periph(AT91_PIN_PB18, 0);		/* RXD0 */

	if (pins & ATMEL_UART_RTS)
		at91_set_B_periph(AT91_PIN_PB17, 0);	/* RTS0 */
	if (pins & ATMEL_UART_CTS)
		at91_set_B_periph(AT91_PIN_PB15, 0);	/* CTS0 */
}

static struct resource uart1_resources[] = {
	[0] = {
		.start	= AT91SAM9G45_BASE_US1,
		.end	= AT91SAM9G45_BASE_US1 + SZ_16K - 1,
		.flags	= IORESOURCE_MEM,
	},
	[1] = {
		.start	= NR_IRQS_LEGACY + AT91SAM9G45_ID_US1,
		.end	= NR_IRQS_LEGACY + AT91SAM9G45_ID_US1,
		.flags	= IORESOURCE_IRQ,
	},
};

static struct atmel_uart_data uart1_data = {
	.use_dma_tx	= 1,
	.use_dma_rx	= 1,
};

static u64 uart1_dmamask = DMA_BIT_MASK(32);

static struct platform_device at91sam9g45_uart1_device = {
	.name		= "atmel_usart",
	.id		= 2,
	.dev		= {
				.dma_mask		= &uart1_dmamask,
				.coherent_dma_mask	= DMA_BIT_MASK(32),
				.platform_data		= &uart1_data,
	},
	.resource	= uart1_resources,
	.num_resources	= ARRAY_SIZE(uart1_resources),
};

static inline void configure_usart1_pins(unsigned pins)
{
	at91_set_A_periph(AT91_PIN_PB4, 1);		/* TXD1 */
	at91_set_A_periph(AT91_PIN_PB5, 0);		/* RXD1 */

	if (pins & ATMEL_UART_RTS)
		at91_set_A_periph(AT91_PIN_PD16, 0);	/* RTS1 */
	if (pins & ATMEL_UART_CTS)
		at91_set_A_periph(AT91_PIN_PD17, 0);	/* CTS1 */
}

static struct resource uart2_resources[] = {
	[0] = {
		.start	= AT91SAM9G45_BASE_US2,
		.end	= AT91SAM9G45_BASE_US2 + SZ_16K - 1,
		.flags	= IORESOURCE_MEM,
	},
	[1] = {
		.start	= NR_IRQS_LEGACY + AT91SAM9G45_ID_US2,
		.end	= NR_IRQS_LEGACY + AT91SAM9G45_ID_US2,
		.flags	= IORESOURCE_IRQ,
	},
};

static struct atmel_uart_data uart2_data = {
	.use_dma_tx	= 1,
	.use_dma_rx	= 1,
};

static u64 uart2_dmamask = DMA_BIT_MASK(32);

static struct platform_device at91sam9g45_uart2_device = {
	.name		= "atmel_usart",
	.id		= 3,
	.dev		= {
				.dma_mask		= &uart2_dmamask,
				.coherent_dma_mask	= DMA_BIT_MASK(32),
				.platform_data		= &uart2_data,
	},
	.resource	= uart2_resources,
	.num_resources	= ARRAY_SIZE(uart2_resources),
};

static inline void configure_usart2_pins(unsigned pins)
{
	at91_set_A_periph(AT91_PIN_PB6, 1);		/* TXD2 */
	at91_set_A_periph(AT91_PIN_PB7, 0);		/* RXD2 */

	if (pins & ATMEL_UART_RTS)
		at91_set_B_periph(AT91_PIN_PC9, 0);	/* RTS2 */
	if (pins & ATMEL_UART_CTS)
		at91_set_B_periph(AT91_PIN_PC11, 0);	/* CTS2 */
}

static struct resource uart3_resources[] = {
	[0] = {
		.start	= AT91SAM9G45_BASE_US3,
		.end	= AT91SAM9G45_BASE_US3 + SZ_16K - 1,
		.flags	= IORESOURCE_MEM,
	},
	[1] = {
		.start	= NR_IRQS_LEGACY + AT91SAM9G45_ID_US3,
		.end	= NR_IRQS_LEGACY + AT91SAM9G45_ID_US3,
		.flags	= IORESOURCE_IRQ,
	},
};

static struct atmel_uart_data uart3_data = {
	.use_dma_tx	= 1,
	.use_dma_rx	= 1,
};

static u64 uart3_dmamask = DMA_BIT_MASK(32);

static struct platform_device at91sam9g45_uart3_device = {
	.name		= "atmel_usart",
	.id		= 4,
	.dev		= {
				.dma_mask		= &uart3_dmamask,
				.coherent_dma_mask	= DMA_BIT_MASK(32),
				.platform_data		= &uart3_data,
	},
	.resource	= uart3_resources,
	.num_resources	= ARRAY_SIZE(uart3_resources),
};

static inline void configure_usart3_pins(unsigned pins)
{
	at91_set_A_periph(AT91_PIN_PB8, 1);		/* TXD3 */
	at91_set_A_periph(AT91_PIN_PB9, 0);		/* RXD3 */

	if (pins & ATMEL_UART_RTS)
		at91_set_B_periph(AT91_PIN_PA23, 0);	/* RTS3 */
	if (pins & ATMEL_UART_CTS)
		at91_set_B_periph(AT91_PIN_PA24, 0);	/* CTS3 */
}

static struct platform_device *__initdata at91_uarts[ATMEL_MAX_UART];	/* the UARTs to use */

void __init at91_register_uart(unsigned id, unsigned portnr, unsigned pins)
{
	struct platform_device *pdev;
	struct atmel_uart_data *pdata;

	switch (id) {
		case 0:		/* DBGU */
			pdev = &at91sam9g45_dbgu_device;
			configure_dbgu_pins();
			break;
		case AT91SAM9G45_ID_US0:
			pdev = &at91sam9g45_uart0_device;
			configure_usart0_pins(pins);
			break;
		case AT91SAM9G45_ID_US1:
			pdev = &at91sam9g45_uart1_device;
			configure_usart1_pins(pins);
			break;
		case AT91SAM9G45_ID_US2:
			pdev = &at91sam9g45_uart2_device;
			configure_usart2_pins(pins);
			break;
		case AT91SAM9G45_ID_US3:
			pdev = &at91sam9g45_uart3_device;
			configure_usart3_pins(pins);
			break;
		default:
			return;
	}
	pdata = pdev->dev.platform_data;
	pdata->num = portnr;		/* update to mapped ID */

	if (portnr < ATMEL_MAX_UART)
		at91_uarts[portnr] = pdev;
}

void __init at91_add_device_serial(void)
{
	int i;

	for (i = 0; i < ATMEL_MAX_UART; i++) {
		if (at91_uarts[i])
			platform_device_register(at91_uarts[i]);
	}
}
#else
void __init at91_register_uart(unsigned id, unsigned portnr, unsigned pins) {}
void __init at91_add_device_serial(void) {}
#endif

/* --------------------------------------------------------------------
 *  SHA1/SHA256
 * -------------------------------------------------------------------- */

#if defined(CONFIG_CRYPTO_DEV_ATMEL_SHA) || defined(CONFIG_CRYPTO_DEV_ATMEL_SHA_MODULE)
static struct resource sha_resources[] = {
	{
		.start	= AT91SAM9G45_BASE_SHA,
		.end	= AT91SAM9G45_BASE_SHA + SZ_16K - 1,
		.flags	= IORESOURCE_MEM,
	},
	[1] = {
		.start	= AT91SAM9G45_ID_AESTDESSHA,
		.end	= AT91SAM9G45_ID_AESTDESSHA,
		.flags	= IORESOURCE_IRQ,
	},
};

static struct platform_device at91sam9g45_sha_device = {
	.name	= "atmel_sha",
	.id		= -1,
	.resource	= sha_resources,
	.num_resources	= ARRAY_SIZE(sha_resources),
};

static void __init at91_add_device_sha(void)
{
	platform_device_register(&at91sam9g45_sha_device);
}
#else
static void __init at91_add_device_sha(void) {}
#endif

/* --------------------------------------------------------------------
 *  DES/TDES
 * -------------------------------------------------------------------- */

#if defined(CONFIG_CRYPTO_DEV_ATMEL_TDES) || defined(CONFIG_CRYPTO_DEV_ATMEL_TDES_MODULE)
static struct resource tdes_resources[] = {
	[0] = {
		.start	= AT91SAM9G45_BASE_TDES,
		.end	= AT91SAM9G45_BASE_TDES + SZ_16K - 1,
		.flags	= IORESOURCE_MEM,
	},
	[1] = {
		.start	= AT91SAM9G45_ID_AESTDESSHA,
		.end	= AT91SAM9G45_ID_AESTDESSHA,
		.flags	= IORESOURCE_IRQ,
	},
};

static struct platform_device at91sam9g45_tdes_device = {
	.name	= "atmel_tdes",
	.id		= -1,
	.resource	= tdes_resources,
	.num_resources	= ARRAY_SIZE(tdes_resources),
};

static void __init at91_add_device_tdes(void)
{
	platform_device_register(&at91sam9g45_tdes_device);
}
#else
static void __init at91_add_device_tdes(void) {}
#endif

/* --------------------------------------------------------------------
 *  AES
 * -------------------------------------------------------------------- */

#if defined(CONFIG_CRYPTO_DEV_ATMEL_AES) || defined(CONFIG_CRYPTO_DEV_ATMEL_AES_MODULE)
static struct aes_platform_data aes_data;
static u64 aes_dmamask = DMA_BIT_MASK(32);

static struct resource aes_resources[] = {
	[0] = {
		.start	= AT91SAM9G45_BASE_AES,
		.end	= AT91SAM9G45_BASE_AES + SZ_16K - 1,
		.flags	= IORESOURCE_MEM,
	},
	[1] = {
		.start	= AT91SAM9G45_ID_AESTDESSHA,
		.end	= AT91SAM9G45_ID_AESTDESSHA,
		.flags	= IORESOURCE_IRQ,
	},
};

static struct platform_device at91sam9g45_aes_device = {
	.name	= "atmel_aes",
	.id		= -1,
	.dev	= {
		.dma_mask		= &aes_dmamask,
		.coherent_dma_mask	= DMA_BIT_MASK(32),
		.platform_data		= &aes_data,
	},
	.resource	= aes_resources,
	.num_resources	= ARRAY_SIZE(aes_resources),
};

static void __init at91_add_device_aes(void)
{
	struct at_dma_slave	*atslave;
	struct aes_dma_data	*alt_atslave;

	alt_atslave = kzalloc(sizeof(struct aes_dma_data), GFP_KERNEL);

	/* DMA TX slave channel configuration */
	atslave = &alt_atslave->txdata;
	atslave->dma_dev = &at_hdmac_device.dev;
	atslave->cfg = ATC_FIFOCFG_ENOUGHSPACE	| ATC_SRC_H2SEL_HW |
						ATC_SRC_PER(AT_DMA_ID_AES_RX);

	/* DMA RX slave channel configuration */
	atslave = &alt_atslave->rxdata;
	atslave->dma_dev = &at_hdmac_device.dev;
	atslave->cfg = ATC_FIFOCFG_ENOUGHSPACE	| ATC_DST_H2SEL_HW |
						ATC_DST_PER(AT_DMA_ID_AES_TX);

	aes_data.dma_slave = alt_atslave;
	platform_device_register(&at91sam9g45_aes_device);
}
#else
static void __init at91_add_device_aes(void) {}
#endif

/* -------------------------------------------------------------------- */
/*
 * These devices are always present and don't need any board-specific
 * setup.
 */
static int __init at91_add_standard_devices(void)
{
	if (of_have_populated_dt())
		return 0;

	at91_add_device_hdmac();
	at91_add_device_rtc();
	at91_add_device_rtt();
	at91_add_device_trng();
	at91_add_device_watchdog();
	at91_add_device_tc();
	at91_add_device_sha();
	at91_add_device_tdes();
	at91_add_device_aes();
	return 0;
}

arch_initcall(at91_add_standard_devices);
span class="hl opt">(&victim->css); break; } /* * We want to do more targetted reclaim. * excess >> 2 is not to excessive so as to * reclaim too much, nor too less that we keep * coming back to reclaim from this cgroup */ if (total >= (excess >> 2) || (loop > MEM_CGROUP_MAX_RECLAIM_LOOPS)) { css_put(&victim->css); break; } } } if (!mem_cgroup_local_usage(victim)) { /* this cgroup's local usage == 0 */ css_put(&victim->css); continue; } /* we use swappiness of local cgroup */ if (check_soft) ret = mem_cgroup_shrink_node_zone(victim, gfp_mask, noswap, get_swappiness(victim), zone, zone->zone_pgdat->node_id); else ret = try_to_free_mem_cgroup_pages(victim, gfp_mask, noswap, get_swappiness(victim)); css_put(&victim->css); /* * At shrinking usage, we can't check we should stop here or * reclaim more. It's depends on callers. last_scanned_child * will work enough for keeping fairness under tree. */ if (shrink) return ret; total += ret; if (check_soft) { if (res_counter_check_under_soft_limit(&root_mem->res)) return total; } else if (mem_cgroup_check_under_limit(root_mem)) return 1 + total; } return total; } static int mem_cgroup_oom_lock_cb(struct mem_cgroup *mem, void *data) { int *val = (int *)data; int x; /* * Logically, we can stop scanning immediately when we find * a memcg is already locked. But condidering unlock ops and * creation/removal of memcg, scan-all is simple operation. */ x = atomic_inc_return(&mem->oom_lock); *val = max(x, *val); return 0; } /* * Check OOM-Killer is already running under our hierarchy. * If someone is running, return false. */ static bool mem_cgroup_oom_lock(struct mem_cgroup *mem) { int lock_count = 0; mem_cgroup_walk_tree(mem, &lock_count, mem_cgroup_oom_lock_cb); if (lock_count == 1) return true; return false; } static int mem_cgroup_oom_unlock_cb(struct mem_cgroup *mem, void *data) { /* * When a new child is created while the hierarchy is under oom, * mem_cgroup_oom_lock() may not be called. We have to use * atomic_add_unless() here. */ atomic_add_unless(&mem->oom_lock, -1, 0); return 0; } static void mem_cgroup_oom_unlock(struct mem_cgroup *mem) { mem_cgroup_walk_tree(mem, NULL, mem_cgroup_oom_unlock_cb); } static DEFINE_MUTEX(memcg_oom_mutex); static DECLARE_WAIT_QUEUE_HEAD(memcg_oom_waitq); /* * try to call OOM killer. returns false if we should exit memory-reclaim loop. */ bool mem_cgroup_handle_oom(struct mem_cgroup *mem, gfp_t mask) { DEFINE_WAIT(wait); bool locked; /* At first, try to OOM lock hierarchy under mem.*/ mutex_lock(&memcg_oom_mutex); locked = mem_cgroup_oom_lock(mem); /* * Even if signal_pending(), we can't quit charge() loop without * accounting. So, UNINTERRUPTIBLE is appropriate. But SIGKILL * under OOM is always welcomed, use TASK_KILLABLE here. */ if (!locked) prepare_to_wait(&memcg_oom_waitq, &wait, TASK_KILLABLE); mutex_unlock(&memcg_oom_mutex); if (locked) mem_cgroup_out_of_memory(mem, mask); else { schedule(); finish_wait(&memcg_oom_waitq, &wait); } mutex_lock(&memcg_oom_mutex); mem_cgroup_oom_unlock(mem); /* * Here, we use global waitq .....more fine grained waitq ? * Assume following hierarchy. * A/ * 01 * 02 * assume OOM happens both in A and 01 at the same time. Tthey are * mutually exclusive by lock. (kill in 01 helps A.) * When we use per memcg waitq, we have to wake up waiters on A and 02 * in addtion to waiters on 01. We use global waitq for avoiding mess. * It will not be a big problem. * (And a task may be moved to other groups while it's waiting for OOM.) */ wake_up_all(&memcg_oom_waitq); mutex_unlock(&memcg_oom_mutex); if (test_thread_flag(TIF_MEMDIE) || fatal_signal_pending(current)) return false; /* Give chance to dying process */ schedule_timeout(1); return true; } /* * Currently used to update mapped file statistics, but the routine can be * generalized to update other statistics as well. */ void mem_cgroup_update_file_mapped(struct page *page, int val) { struct mem_cgroup *mem; struct page_cgroup *pc; pc = lookup_page_cgroup(page); if (unlikely(!pc)) return; lock_page_cgroup(pc); mem = pc->mem_cgroup; if (!mem || !PageCgroupUsed(pc)) goto done; /* * Preemption is already disabled. We can use __this_cpu_xxx */ if (val > 0) { __this_cpu_inc(mem->stat->count[MEM_CGROUP_STAT_FILE_MAPPED]); SetPageCgroupFileMapped(pc); } else { __this_cpu_dec(mem->stat->count[MEM_CGROUP_STAT_FILE_MAPPED]); ClearPageCgroupFileMapped(pc); } done: unlock_page_cgroup(pc); } /* * size of first charge trial. "32" comes from vmscan.c's magic value. * TODO: maybe necessary to use big numbers in big irons. */ #define CHARGE_SIZE (32 * PAGE_SIZE) struct memcg_stock_pcp { struct mem_cgroup *cached; /* this never be root cgroup */ int charge; struct work_struct work; }; static DEFINE_PER_CPU(struct memcg_stock_pcp, memcg_stock); static atomic_t memcg_drain_count; /* * Try to consume stocked charge on this cpu. If success, PAGE_SIZE is consumed * from local stock and true is returned. If the stock is 0 or charges from a * cgroup which is not current target, returns false. This stock will be * refilled. */ static bool consume_stock(struct mem_cgroup *mem) { struct memcg_stock_pcp *stock; bool ret = true; stock = &get_cpu_var(memcg_stock); if (mem == stock->cached && stock->charge) stock->charge -= PAGE_SIZE; else /* need to call res_counter_charge */ ret = false; put_cpu_var(memcg_stock); return ret; } /* * Returns stocks cached in percpu to res_counter and reset cached information. */ static void drain_stock(struct memcg_stock_pcp *stock) { struct mem_cgroup *old = stock->cached; if (stock->charge) { res_counter_uncharge(&old->res, stock->charge); if (do_swap_account) res_counter_uncharge(&old->memsw, stock->charge); } stock->cached = NULL; stock->charge = 0; } /* * This must be called under preempt disabled or must be called by * a thread which is pinned to local cpu. */ static void drain_local_stock(struct work_struct *dummy) { struct memcg_stock_pcp *stock = &__get_cpu_var(memcg_stock); drain_stock(stock); } /* * Cache charges(val) which is from res_counter, to local per_cpu area. * This will be consumed by consume_stock() function, later. */ static void refill_stock(struct mem_cgroup *mem, int val) { struct memcg_stock_pcp *stock = &get_cpu_var(memcg_stock); if (stock->cached != mem) { /* reset if necessary */ drain_stock(stock); stock->cached = mem; } stock->charge += val; put_cpu_var(memcg_stock); } /* * Tries to drain stocked charges in other cpus. This function is asynchronous * and just put a work per cpu for draining localy on each cpu. Caller can * expects some charges will be back to res_counter later but cannot wait for * it. */ static void drain_all_stock_async(void) { int cpu; /* This function is for scheduling "drain" in asynchronous way. * The result of "drain" is not directly handled by callers. Then, * if someone is calling drain, we don't have to call drain more. * Anyway, WORK_STRUCT_PENDING check in queue_work_on() will catch if * there is a race. We just do loose check here. */ if (atomic_read(&memcg_drain_count)) return; /* Notify other cpus that system-wide "drain" is running */ atomic_inc(&memcg_drain_count); get_online_cpus(); for_each_online_cpu(cpu) { struct memcg_stock_pcp *stock = &per_cpu(memcg_stock, cpu); schedule_work_on(cpu, &stock->work); } put_online_cpus(); atomic_dec(&memcg_drain_count); /* We don't wait for flush_work */ } /* This is a synchronous drain interface. */ static void drain_all_stock_sync(void) { /* called when force_empty is called */ atomic_inc(&memcg_drain_count); schedule_on_each_cpu(drain_local_stock); atomic_dec(&memcg_drain_count); } static int __cpuinit memcg_stock_cpu_callback(struct notifier_block *nb, unsigned long action, void *hcpu) { int cpu = (unsigned long)hcpu; struct memcg_stock_pcp *stock; if (action != CPU_DEAD) return NOTIFY_OK; stock = &per_cpu(memcg_stock, cpu); drain_stock(stock); return NOTIFY_OK; } /* * Unlike exported interface, "oom" parameter is added. if oom==true, * oom-killer can be invoked. */ static int __mem_cgroup_try_charge(struct mm_struct *mm, gfp_t gfp_mask, struct mem_cgroup **memcg, bool oom) { struct mem_cgroup *mem, *mem_over_limit; int nr_retries = MEM_CGROUP_RECLAIM_RETRIES; struct res_counter *fail_res; int csize = CHARGE_SIZE; /* * Unlike gloval-vm's OOM-kill, we're not in memory shortage * in system level. So, allow to go ahead dying process in addition to * MEMDIE process. */ if (unlikely(test_thread_flag(TIF_MEMDIE) || fatal_signal_pending(current))) goto bypass; /* * We always charge the cgroup the mm_struct belongs to. * The mm_struct's mem_cgroup changes on task migration if the * thread group leader migrates. It's possible that mm is not * set, if so charge the init_mm (happens for pagecache usage). */ mem = *memcg; if (likely(!mem)) { mem = try_get_mem_cgroup_from_mm(mm); *memcg = mem; } else { css_get(&mem->css); } if (unlikely(!mem)) return 0; VM_BUG_ON(css_is_removed(&mem->css)); if (mem_cgroup_is_root(mem)) goto done; while (1) { int ret = 0; unsigned long flags = 0; if (consume_stock(mem)) goto done; ret = res_counter_charge(&mem->res, csize, &fail_res); if (likely(!ret)) { if (!do_swap_account) break; ret = res_counter_charge(&mem->memsw, csize, &fail_res); if (likely(!ret)) break; /* mem+swap counter fails */ res_counter_uncharge(&mem->res, csize); flags |= MEM_CGROUP_RECLAIM_NOSWAP; mem_over_limit = mem_cgroup_from_res_counter(fail_res, memsw); } else /* mem counter fails */ mem_over_limit = mem_cgroup_from_res_counter(fail_res, res); /* reduce request size and retry */ if (csize > PAGE_SIZE) { csize = PAGE_SIZE; continue; } if (!(gfp_mask & __GFP_WAIT)) goto nomem; ret = mem_cgroup_hierarchical_reclaim(mem_over_limit, NULL, gfp_mask, flags); if (ret) continue; /* * try_to_free_mem_cgroup_pages() might not give us a full * picture of reclaim. Some pages are reclaimed and might be * moved to swap cache or just unmapped from the cgroup. * Check the limit again to see if the reclaim reduced the * current usage of the cgroup before giving up * */ if (mem_cgroup_check_under_limit(mem_over_limit)) continue; /* try to avoid oom while someone is moving charge */ if (mc.moving_task && current != mc.moving_task) { struct mem_cgroup *from, *to; bool do_continue = false; /* * There is a small race that "from" or "to" can be * freed by rmdir, so we use css_tryget(). */ from = mc.from; to = mc.to; if (from && css_tryget(&from->css)) { if (mem_over_limit->use_hierarchy) do_continue = css_is_ancestor( &from->css, &mem_over_limit->css); else do_continue = (from == mem_over_limit); css_put(&from->css); } if (!do_continue && to && css_tryget(&to->css)) { if (mem_over_limit->use_hierarchy) do_continue = css_is_ancestor( &to->css, &mem_over_limit->css); else do_continue = (to == mem_over_limit); css_put(&to->css); } if (do_continue) { DEFINE_WAIT(wait); prepare_to_wait(&mc.waitq, &wait, TASK_INTERRUPTIBLE); /* moving charge context might have finished. */ if (mc.moving_task) schedule(); finish_wait(&mc.waitq, &wait); continue; } } if (!nr_retries--) { if (!oom) goto nomem; if (mem_cgroup_handle_oom(mem_over_limit, gfp_mask)) { nr_retries = MEM_CGROUP_RECLAIM_RETRIES; continue; } /* When we reach here, current task is dying .*/ css_put(&mem->css); goto bypass; } } if (csize > PAGE_SIZE) refill_stock(mem, csize - PAGE_SIZE); done: return 0; nomem: css_put(&mem->css); return -ENOMEM; bypass: *memcg = NULL; return 0; } /* * Somemtimes we have to undo a charge we got by try_charge(). * This function is for that and do uncharge, put css's refcnt. * gotten by try_charge(). */ static void __mem_cgroup_cancel_charge(struct mem_cgroup *mem, unsigned long count) { if (!mem_cgroup_is_root(mem)) { res_counter_uncharge(&mem->res, PAGE_SIZE * count); if (do_swap_account) res_counter_uncharge(&mem->memsw, PAGE_SIZE * count); VM_BUG_ON(test_bit(CSS_ROOT, &mem->css.flags)); WARN_ON_ONCE(count > INT_MAX); __css_put(&mem->css, (int)count); } /* we don't need css_put for root */ } static void mem_cgroup_cancel_charge(struct mem_cgroup *mem) { __mem_cgroup_cancel_charge(mem, 1); } /* * A helper function to get mem_cgroup from ID. must be called under * rcu_read_lock(). The caller must check css_is_removed() or some if * it's concern. (dropping refcnt from swap can be called against removed * memcg.) */ static struct mem_cgroup *mem_cgroup_lookup(unsigned short id) { struct cgroup_subsys_state *css; /* ID 0 is unused ID */ if (!id) return NULL; css = css_lookup(&mem_cgroup_subsys, id); if (!css) return NULL; return container_of(css, struct mem_cgroup, css); } struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page) { struct mem_cgroup *mem = NULL; struct page_cgroup *pc; unsigned short id; swp_entry_t ent; VM_BUG_ON(!PageLocked(page)); pc = lookup_page_cgroup(page); lock_page_cgroup(pc); if (PageCgroupUsed(pc)) { mem = pc->mem_cgroup; if (mem && !css_tryget(&mem->css)) mem = NULL; } else if (PageSwapCache(page)) { ent.val = page_private(page); id = lookup_swap_cgroup(ent); rcu_read_lock(); mem = mem_cgroup_lookup(id); if (mem && !css_tryget(&mem->css)) mem = NULL; rcu_read_unlock(); } unlock_page_cgroup(pc); return mem; } /* * commit a charge got by __mem_cgroup_try_charge() and makes page_cgroup to be * USED state. If already USED, uncharge and return. */ static void __mem_cgroup_commit_charge(struct mem_cgroup *mem, struct page_cgroup *pc, enum charge_type ctype) { /* try_charge() can return NULL to *memcg, taking care of it. */ if (!mem) return; lock_page_cgroup(pc); if (unlikely(PageCgroupUsed(pc))) { unlock_page_cgroup(pc); mem_cgroup_cancel_charge(mem); return; } pc->mem_cgroup = mem; /* * We access a page_cgroup asynchronously without lock_page_cgroup(). * Especially when a page_cgroup is taken from a page, pc->mem_cgroup * is accessed after testing USED bit. To make pc->mem_cgroup visible * before USED bit, we need memory barrier here. * See mem_cgroup_add_lru_list(), etc. */ smp_wmb(); switch (ctype) { case MEM_CGROUP_CHARGE_TYPE_CACHE: case MEM_CGROUP_CHARGE_TYPE_SHMEM: SetPageCgroupCache(pc); SetPageCgroupUsed(pc); break; case MEM_CGROUP_CHARGE_TYPE_MAPPED: ClearPageCgroupCache(pc); SetPageCgroupUsed(pc); break; default: break; } mem_cgroup_charge_statistics(mem, pc, true); unlock_page_cgroup(pc); /* * "charge_statistics" updated event counter. Then, check it. * Insert ancestor (and ancestor's ancestors), to softlimit RB-tree. * if they exceeds softlimit. */ memcg_check_events(mem, pc->page); } /** * __mem_cgroup_move_account - move account of the page * @pc: page_cgroup of the page. * @from: mem_cgroup which the page is moved from. * @to: mem_cgroup which the page is moved to. @from != @to. * @uncharge: whether we should call uncharge and css_put against @from. * * The caller must confirm following. * - page is not on LRU (isolate_page() is useful.) * - the pc is locked, used, and ->mem_cgroup points to @from. * * This function doesn't do "charge" nor css_get to new cgroup. It should be * done by a caller(__mem_cgroup_try_charge would be usefull). If @uncharge is * true, this function does "uncharge" from old cgroup, but it doesn't if * @uncharge is false, so a caller should do "uncharge". */ static void __mem_cgroup_move_account(struct page_cgroup *pc, struct mem_cgroup *from, struct mem_cgroup *to, bool uncharge) { VM_BUG_ON(from == to); VM_BUG_ON(PageLRU(pc->page)); VM_BUG_ON(!PageCgroupLocked(pc)); VM_BUG_ON(!PageCgroupUsed(pc)); VM_BUG_ON(pc->mem_cgroup != from); if (PageCgroupFileMapped(pc)) { /* Update mapped_file data for mem_cgroup */ preempt_disable(); __this_cpu_dec(from->stat->count[MEM_CGROUP_STAT_FILE_MAPPED]); __this_cpu_inc(to->stat->count[MEM_CGROUP_STAT_FILE_MAPPED]); preempt_enable(); } mem_cgroup_charge_statistics(from, pc, false); if (uncharge) /* This is not "cancel", but cancel_charge does all we need. */ mem_cgroup_cancel_charge(from); /* caller should have done css_get */ pc->mem_cgroup = to; mem_cgroup_charge_statistics(to, pc, true); /* * We charges against "to" which may not have any tasks. Then, "to" * can be under rmdir(). But in current implementation, caller of * this function is just force_empty() and move charge, so it's * garanteed that "to" is never removed. So, we don't check rmdir * status here. */ } /* * check whether the @pc is valid for moving account and call * __mem_cgroup_move_account() */ static int mem_cgroup_move_account(struct page_cgroup *pc, struct mem_cgroup *from, struct mem_cgroup *to, bool uncharge) { int ret = -EINVAL; lock_page_cgroup(pc); if (PageCgroupUsed(pc) && pc->mem_cgroup == from) { __mem_cgroup_move_account(pc, from, to, uncharge); ret = 0; } unlock_page_cgroup(pc); /* * check events */ memcg_check_events(to, pc->page); memcg_check_events(from, pc->page); return ret; } /* * move charges to its parent. */ static int mem_cgroup_move_parent(struct page_cgroup *pc, struct mem_cgroup *child, gfp_t gfp_mask) { struct page *page = pc->page; struct cgroup *cg = child->css.cgroup; struct cgroup *pcg = cg->parent; struct mem_cgroup *parent; int ret; /* Is ROOT ? */ if (!pcg) return -EINVAL; ret = -EBUSY; if (!get_page_unless_zero(page)) goto out; if (isolate_lru_page(page)) goto put; parent = mem_cgroup_from_cont(pcg); ret = __mem_cgroup_try_charge(NULL, gfp_mask, &parent, false); if (ret || !parent) goto put_back; ret = mem_cgroup_move_account(pc, child, parent, true); if (ret) mem_cgroup_cancel_charge(parent); put_back: putback_lru_page(page); put: put_page(page); out: return ret; } /* * Charge the memory controller for page usage. * Return * 0 if the charge was successful * < 0 if the cgroup is over its limit */ static int mem_cgroup_charge_common(struct page *page, struct mm_struct *mm, gfp_t gfp_mask, enum charge_type ctype, struct mem_cgroup *memcg) { struct mem_cgroup *mem; struct page_cgroup *pc; int ret; pc = lookup_page_cgroup(page); /* can happen at boot */ if (unlikely(!pc)) return 0; prefetchw(pc); mem = memcg; ret = __mem_cgroup_try_charge(mm, gfp_mask, &mem, true); if (ret || !mem) return ret; __mem_cgroup_commit_charge(mem, pc, ctype); return 0; } int mem_cgroup_newpage_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask) { if (mem_cgroup_disabled()) return 0; if (PageCompound(page)) return 0; /* * If already mapped, we don't have to account. * If page cache, page->mapping has address_space. * But page->mapping may have out-of-use anon_vma pointer, * detecit it by PageAnon() check. newly-mapped-anon's page->mapping * is NULL. */ if (page_mapped(page) || (page->mapping && !PageAnon(page))) return 0; if (unlikely(!mm)) mm = &init_mm; return mem_cgroup_charge_common(page, mm, gfp_mask, MEM_CGROUP_CHARGE_TYPE_MAPPED, NULL); } static void __mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *ptr, enum charge_type ctype); int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask) { struct mem_cgroup *mem = NULL; int ret; if (mem_cgroup_disabled()) return 0; if (PageCompound(page)) return 0; /* * Corner case handling. This is called from add_to_page_cache() * in usual. But some FS (shmem) precharges this page before calling it * and call add_to_page_cache() with GFP_NOWAIT. * * For GFP_NOWAIT case, the page may be pre-charged before calling * add_to_page_cache(). (See shmem.c) check it here and avoid to call * charge twice. (It works but has to pay a bit larger cost.) * And when the page is SwapCache, it should take swap information * into account. This is under lock_page() now. */ if (!(gfp_mask & __GFP_WAIT)) { struct page_cgroup *pc; pc = lookup_page_cgroup(page); if (!pc) return 0; lock_page_cgroup(pc); if (PageCgroupUsed(pc)) { unlock_page_cgroup(pc); return 0; } unlock_page_cgroup(pc); } if (unlikely(!mm && !mem)) mm = &init_mm; if (page_is_file_cache(page)) return mem_cgroup_charge_common(page, mm, gfp_mask, MEM_CGROUP_CHARGE_TYPE_CACHE, NULL); /* shmem */ if (PageSwapCache(page)) { ret = mem_cgroup_try_charge_swapin(mm, page, gfp_mask, &mem); if (!ret) __mem_cgroup_commit_charge_swapin(page, mem, MEM_CGROUP_CHARGE_TYPE_SHMEM); } else ret = mem_cgroup_charge_common(page, mm, gfp_mask, MEM_CGROUP_CHARGE_TYPE_SHMEM, mem); return ret; } /* * While swap-in, try_charge -> commit or cancel, the page is locked. * And when try_charge() successfully returns, one refcnt to memcg without * struct page_cgroup is acquired. This refcnt will be consumed by * "commit()" or removed by "cancel()" */ int mem_cgroup_try_charge_swapin(struct mm_struct *mm, struct page *page, gfp_t mask, struct mem_cgroup **ptr) { struct mem_cgroup *mem; int ret; if (mem_cgroup_disabled()) return 0; if (!do_swap_account) goto charge_cur_mm; /* * A racing thread's fault, or swapoff, may have already updated * the pte, and even removed page from swap cache: in those cases * do_swap_page()'s pte_same() test will fail; but there's also a * KSM case which does need to charge the page. */ if (!PageSwapCache(page)) goto charge_cur_mm; mem = try_get_mem_cgroup_from_page(page); if (!mem) goto charge_cur_mm; *ptr = mem; ret = __mem_cgroup_try_charge(NULL, mask, ptr, true); /* drop extra refcnt from tryget */ css_put(&mem->css); return ret; charge_cur_mm: if (unlikely(!mm)) mm = &init_mm; return __mem_cgroup_try_charge(mm, mask, ptr, true); } static void __mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *ptr, enum charge_type ctype) { struct page_cgroup *pc; if (mem_cgroup_disabled()) return; if (!ptr) return; cgroup_exclude_rmdir(&ptr->css); pc = lookup_page_cgroup(page); mem_cgroup_lru_del_before_commit_swapcache(page); __mem_cgroup_commit_charge(ptr, pc, ctype); mem_cgroup_lru_add_after_commit_swapcache(page); /* * Now swap is on-memory. This means this page may be * counted both as mem and swap....double count. * Fix it by uncharging from memsw. Basically, this SwapCache is stable * under lock_page(). But in do_swap_page()::memory.c, reuse_swap_page() * may call delete_from_swap_cache() before reach here. */ if (do_swap_account && PageSwapCache(page)) { swp_entry_t ent = {.val = page_private(page)}; unsigned short id; struct mem_cgroup *memcg; id = swap_cgroup_record(ent, 0); rcu_read_lock(); memcg = mem_cgroup_lookup(id); if (memcg) { /* * This recorded memcg can be obsolete one. So, avoid * calling css_tryget */ if (!mem_cgroup_is_root(memcg)) res_counter_uncharge(&memcg->memsw, PAGE_SIZE); mem_cgroup_swap_statistics(memcg, false); mem_cgroup_put(memcg); } rcu_read_unlock(); } /* * At swapin, we may charge account against cgroup which has no tasks. * So, rmdir()->pre_destroy() can be called while we do this charge. * In that case, we need to call pre_destroy() again. check it here. */ cgroup_release_and_wakeup_rmdir(&ptr->css); } void mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *ptr) { __mem_cgroup_commit_charge_swapin(page, ptr, MEM_CGROUP_CHARGE_TYPE_MAPPED); } void mem_cgroup_cancel_charge_swapin(struct mem_cgroup *mem) { if (mem_cgroup_disabled()) return; if (!mem) return; mem_cgroup_cancel_charge(mem); } static void __do_uncharge(struct mem_cgroup *mem, const enum charge_type ctype) { struct memcg_batch_info *batch = NULL; bool uncharge_memsw = true; /* If swapout, usage of swap doesn't decrease */ if (!do_swap_account || ctype == MEM_CGROUP_CHARGE_TYPE_SWAPOUT) uncharge_memsw = false; /* * do_batch > 0 when unmapping pages or inode invalidate/truncate. * In those cases, all pages freed continously can be expected to be in * the same cgroup and we have chance to coalesce uncharges. * But we do uncharge one by one if this is killed by OOM(TIF_MEMDIE) * because we want to do uncharge as soon as possible. */ if (!current->memcg_batch.do_batch || test_thread_flag(TIF_MEMDIE)) goto direct_uncharge; batch = &current->memcg_batch; /* * In usual, we do css_get() when we remember memcg pointer. * But in this case, we keep res->usage until end of a series of * uncharges. Then, it's ok to ignore memcg's refcnt. */ if (!batch->memcg) batch->memcg = mem; /* * In typical case, batch->memcg == mem. This means we can * merge a series of uncharges to an uncharge of res_counter. * If not, we uncharge res_counter ony by one. */ if (batch->memcg != mem) goto direct_uncharge; /* remember freed charge and uncharge it later */ batch->bytes += PAGE_SIZE; if (uncharge_memsw) batch->memsw_bytes += PAGE_SIZE; return; direct_uncharge: res_counter_uncharge(&mem->res, PAGE_SIZE); if (uncharge_memsw) res_counter_uncharge(&mem->memsw, PAGE_SIZE); return; } /* * uncharge if !page_mapped(page) */ static struct mem_cgroup * __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype) { struct page_cgroup *pc; struct mem_cgroup *mem = NULL; struct mem_cgroup_per_zone *mz; if (mem_cgroup_disabled()) return NULL; if (PageSwapCache(page)) return NULL; /* * Check if our page_cgroup is valid */ pc = lookup_page_cgroup(page); if (unlikely(!pc || !PageCgroupUsed(pc))) return NULL; lock_page_cgroup(pc); mem = pc->mem_cgroup; if (!PageCgroupUsed(pc)) goto unlock_out; switch (ctype) { case MEM_CGROUP_CHARGE_TYPE_MAPPED: case MEM_CGROUP_CHARGE_TYPE_DROP: if (page_mapped(page)) goto unlock_out; break; case MEM_CGROUP_CHARGE_TYPE_SWAPOUT: if (!PageAnon(page)) { /* Shared memory */ if (page->mapping && !page_is_file_cache(page)) goto unlock_out; } else if (page_mapped(page)) /* Anon */ goto unlock_out; break; default: break; } if (!mem_cgroup_is_root(mem)) __do_uncharge(mem, ctype); if (ctype == MEM_CGROUP_CHARGE_TYPE_SWAPOUT) mem_cgroup_swap_statistics(mem, true); mem_cgroup_charge_statistics(mem, pc, false); ClearPageCgroupUsed(pc); /* * pc->mem_cgroup is not cleared here. It will be accessed when it's * freed from LRU. This is safe because uncharged page is expected not * to be reused (freed soon). Exception is SwapCache, it's handled by * special functions. */ mz = page_cgroup_zoneinfo(pc); unlock_page_cgroup(pc); memcg_check_events(mem, page); /* at swapout, this memcg will be accessed to record to swap */ if (ctype != MEM_CGROUP_CHARGE_TYPE_SWAPOUT) css_put(&mem->css); return mem; unlock_out: unlock_page_cgroup(pc); return NULL; } void mem_cgroup_uncharge_page(struct page *page) { /* early check. */ if (page_mapped(page)) return; if (page->mapping && !PageAnon(page)) return; __mem_cgroup_uncharge_common(page, MEM_CGROUP_CHARGE_TYPE_MAPPED); } void mem_cgroup_uncharge_cache_page(struct page *page) { VM_BUG_ON(page_mapped(page)); VM_BUG_ON(page->mapping); __mem_cgroup_uncharge_common(page, MEM_CGROUP_CHARGE_TYPE_CACHE); } /* * Batch_start/batch_end is called in unmap_page_range/invlidate/trucate. * In that cases, pages are freed continuously and we can expect pages * are in the same memcg. All these calls itself limits the number of * pages freed at once, then uncharge_start/end() is called properly. * This may be called prural(2) times in a context, */ void mem_cgroup_uncharge_start(void) { current->memcg_batch.do_batch++; /* We can do nest. */ if (current->memcg_batch.do_batch == 1) { current->memcg_batch.memcg = NULL; current->memcg_batch.bytes = 0; current->memcg_batch.memsw_bytes = 0; } } void mem_cgroup_uncharge_end(void) { struct memcg_batch_info *batch = &current->memcg_batch; if (!batch->do_batch) return; batch->do_batch--; if (batch->do_batch) /* If stacked, do nothing. */ return; if (!batch->memcg) return; /* * This "batch->memcg" is valid without any css_get/put etc... * bacause we hide charges behind us. */ if (batch->bytes) res_counter_uncharge(&batch->memcg->res, batch->bytes); if (batch->memsw_bytes) res_counter_uncharge(&batch->memcg->memsw, batch->memsw_bytes); /* forget this pointer (for sanity check) */ batch->memcg = NULL; } #ifdef CONFIG_SWAP /* * called after __delete_from_swap_cache() and drop "page" account. * memcg information is recorded to swap_cgroup of "ent" */ void mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent, bool swapout) { struct mem_cgroup *memcg; int ctype = MEM_CGROUP_CHARGE_TYPE_SWAPOUT; if (!swapout) /* this was a swap cache but the swap is unused ! */ ctype = MEM_CGROUP_CHARGE_TYPE_DROP; memcg = __mem_cgroup_uncharge_common(page, ctype); /* record memcg information */ if (do_swap_account && swapout && memcg) { swap_cgroup_record(ent, css_id(&memcg->css)); mem_cgroup_get(memcg); } if (swapout && memcg) css_put(&memcg->css); } #endif #ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP /* * called from swap_entry_free(). remove record in swap_cgroup and * uncharge "memsw" account. */ void mem_cgroup_uncharge_swap(swp_entry_t ent) { struct mem_cgroup *memcg; unsigned short id; if (!do_swap_account) return; id = swap_cgroup_record(ent, 0); rcu_read_lock(); memcg = mem_cgroup_lookup(id); if (memcg) { /* * We uncharge this because swap is freed. * This memcg can be obsolete one. We avoid calling css_tryget */ if (!mem_cgroup_is_root(memcg)) res_counter_uncharge(&memcg->memsw, PAGE_SIZE); mem_cgroup_swap_statistics(memcg, false); mem_cgroup_put(memcg); } rcu_read_unlock(); } /** * mem_cgroup_move_swap_account - move swap charge and swap_cgroup's record. * @entry: swap entry to be moved * @from: mem_cgroup which the entry is moved from * @to: mem_cgroup which the entry is moved to * @need_fixup: whether we should fixup res_counters and refcounts. * * It succeeds only when the swap_cgroup's record for this entry is the same * as the mem_cgroup's id of @from. * * Returns 0 on success, -EINVAL on failure. * * The caller must have charged to @to, IOW, called res_counter_charge() about * both res and memsw, and called css_get(). */ static int mem_cgroup_move_swap_account(swp_entry_t entry, struct mem_cgroup *from, struct mem_cgroup *to, bool need_fixup) { unsigned short old_id, new_id; old_id = css_id(&from->css); new_id = css_id(&to->css); if (swap_cgroup_cmpxchg(entry, old_id, new_id) == old_id) { mem_cgroup_swap_statistics(from, false); mem_cgroup_swap_statistics(to, true); /* * This function is only called from task migration context now. * It postpones res_counter and refcount handling till the end * of task migration(mem_cgroup_clear_mc()) for performance * improvement. But we cannot postpone mem_cgroup_get(to) * because if the process that has been moved to @to does * swap-in, the refcount of @to might be decreased to 0. */ mem_cgroup_get(to); if (need_fixup) { if (!mem_cgroup_is_root(from)) res_counter_uncharge(&from->memsw, PAGE_SIZE); mem_cgroup_put(from); /* * we charged both to->res and to->memsw, so we should * uncharge to->res. */ if (!mem_cgroup_is_root(to)) res_counter_uncharge(&to->res, PAGE_SIZE); css_put(&to->css); } return 0; } return -EINVAL; } #else static inline int mem_cgroup_move_swap_account(swp_entry_t entry, struct mem_cgroup *from, struct mem_cgroup *to, bool need_fixup) { return -EINVAL; } #endif /* * Before starting migration, account PAGE_SIZE to mem_cgroup that the old * page belongs to. */ int mem_cgroup_prepare_migration(struct page *page, struct mem_cgroup **ptr) { struct page_cgroup *pc; struct mem_cgroup *mem = NULL; int ret = 0; if (mem_cgroup_disabled()) return 0; pc = lookup_page_cgroup(page); lock_page_cgroup(pc); if (PageCgroupUsed(pc)) { mem = pc->mem_cgroup; css_get(&mem->css); } unlock_page_cgroup(pc); *ptr = mem; if (mem) { ret = __mem_cgroup_try_charge(NULL, GFP_KERNEL, ptr, false); css_put(&mem->css); } return ret; } /* remove redundant charge if migration failed*/ void mem_cgroup_end_migration(struct mem_cgroup *mem, struct page *oldpage, struct page *newpage) { struct page *target, *unused; struct page_cgroup *pc; enum charge_type ctype; if (!mem) return; cgroup_exclude_rmdir(&mem->css); /* at migration success, oldpage->mapping is NULL. */ if (oldpage->mapping) { target = oldpage; unused = NULL; } else { target = newpage; unused = oldpage; } if (PageAnon(target)) ctype = MEM_CGROUP_CHARGE_TYPE_MAPPED; else if (page_is_file_cache(target)) ctype = MEM_CGROUP_CHARGE_TYPE_CACHE; else ctype = MEM_CGROUP_CHARGE_TYPE_SHMEM; /* unused page is not on radix-tree now. */ if (unused) __mem_cgroup_uncharge_common(unused, ctype); pc = lookup_page_cgroup(target); /* * __mem_cgroup_commit_charge() check PCG_USED bit of page_cgroup. * So, double-counting is effectively avoided. */ __mem_cgroup_commit_charge(mem, pc, ctype); /* * Both of oldpage and newpage are still under lock_page(). * Then, we don't have to care about race in radix-tree. * But we have to be careful that this page is unmapped or not. * * There is a case for !page_mapped(). At the start of * migration, oldpage was mapped. But now, it's zapped. * But we know *target* page is not freed/reused under us. * mem_cgroup_uncharge_page() does all necessary checks. */ if (ctype == MEM_CGROUP_CHARGE_TYPE_MAPPED) mem_cgroup_uncharge_page(target); /* * At migration, we may charge account against cgroup which has no tasks * So, rmdir()->pre_destroy() can be called while we do this charge. * In that case, we need to call pre_destroy() again. check it here. */ cgroup_release_and_wakeup_rmdir(&mem->css); } /* * A call to try to shrink memory usage on charge failure at shmem's swapin. * Calling hierarchical_reclaim is not enough because we should update * last_oom_jiffies to prevent pagefault_out_of_memory from invoking global OOM. * Moreover considering hierarchy, we should reclaim from the mem_over_limit, * not from the memcg which this page would be charged to. * try_charge_swapin does all of these works properly. */ int mem_cgroup_shmem_charge_fallback(struct page *page, struct mm_struct *mm, gfp_t gfp_mask) { struct mem_cgroup *mem = NULL; int ret; if (mem_cgroup_disabled()) return 0; ret = mem_cgroup_try_charge_swapin(mm, page, gfp_mask, &mem); if (!ret) mem_cgroup_cancel_charge_swapin(mem); /* it does !mem check */ return ret; } static DEFINE_MUTEX(set_limit_mutex); static int mem_cgroup_resize_limit(struct mem_cgroup *memcg, unsigned long long val) { int retry_count; u64 memswlimit; int ret = 0; int children = mem_cgroup_count_children(memcg); u64 curusage, oldusage; /* * For keeping hierarchical_reclaim simple, how long we should retry * is depends on callers. We set our retry-count to be function * of # of children which we should visit in this loop. */ retry_count = MEM_CGROUP_RECLAIM_RETRIES * children; oldusage = res_counter_read_u64(&memcg->res, RES_USAGE); while (retry_count) { if (signal_pending(current)) { ret = -EINTR; break; } /* * Rather than hide all in some function, I do this in * open coded manner. You see what this really does. * We have to guarantee mem->res.limit < mem->memsw.limit. */ mutex_lock(&set_limit_mutex); memswlimit = res_counter_read_u64(&memcg->memsw, RES_LIMIT); if (memswlimit < val) { ret = -EINVAL; mutex_unlock(&set_limit_mutex); break; } ret = res_counter_set_limit(&memcg->res, val); if (!ret) { if (memswlimit == val) memcg->memsw_is_minimum = true; else memcg->memsw_is_minimum = false; } mutex_unlock(&set_limit_mutex); if (!ret) break; mem_cgroup_hierarchical_reclaim(memcg, NULL, GFP_KERNEL, MEM_CGROUP_RECLAIM_SHRINK); curusage = res_counter_read_u64(&memcg->res, RES_USAGE); /* Usage is reduced ? */ if (curusage >= oldusage) retry_count--; else oldusage = curusage; } return ret; } static int mem_cgroup_resize_memsw_limit(struct mem_cgroup *memcg, unsigned long long val) { int retry_count; u64 memlimit, oldusage, curusage; int children = mem_cgroup_count_children(memcg); int ret = -EBUSY; /* see mem_cgroup_resize_res_limit */ retry_count = children * MEM_CGROUP_RECLAIM_RETRIES; oldusage = res_counter_read_u64(&memcg->memsw, RES_USAGE); while (retry_count) { if (signal_pending(current)) { ret = -EINTR; break; } /* * Rather than hide all in some function, I do this in * open coded manner. You see what this really does. * We have to guarantee mem->res.limit < mem->memsw.limit. */ mutex_lock(&set_limit_mutex); memlimit = res_counter_read_u64(&memcg->res, RES_LIMIT); if (memlimit > val) { ret = -EINVAL; mutex_unlock(&set_limit_mutex); break; } ret = res_counter_set_limit(&memcg->memsw, val); if (!ret) { if (memlimit == val) memcg->memsw_is_minimum = true; else memcg->memsw_is_minimum = false; } mutex_unlock(&set_limit_mutex); if (!ret) break; mem_cgroup_hierarchical_reclaim(memcg, NULL, GFP_KERNEL, MEM_CGROUP_RECLAIM_NOSWAP | MEM_CGROUP_RECLAIM_SHRINK); curusage = res_counter_read_u64(&memcg->memsw, RES_USAGE); /* Usage is reduced ? */ if (curusage >= oldusage) retry_count--; else oldusage = curusage; } return ret; } unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order, gfp_t gfp_mask, int nid, int zid) { unsigned long nr_reclaimed = 0; struct mem_cgroup_per_zone *mz, *next_mz = NULL; unsigned long reclaimed; int loop = 0; struct mem_cgroup_tree_per_zone *mctz; unsigned long long excess; if (order > 0) return 0; mctz = soft_limit_tree_node_zone(nid, zid); /* * This loop can run a while, specially if mem_cgroup's continuously * keep exceeding their soft limit and putting the system under * pressure */ do { if (next_mz) mz = next_mz; else mz = mem_cgroup_largest_soft_limit_node(mctz); if (!mz) break; reclaimed = mem_cgroup_hierarchical_reclaim(mz->mem, zone, gfp_mask, MEM_CGROUP_RECLAIM_SOFT); nr_reclaimed += reclaimed; spin_lock(&mctz->lock); /* * If we failed to reclaim anything from this memory cgroup * it is time to move on to the next cgroup */ next_mz = NULL; if (!reclaimed) { do { /* * Loop until we find yet another one. * * By the time we get the soft_limit lock * again, someone might have aded the * group back on the RB tree. Iterate to * make sure we get a different mem. * mem_cgroup_largest_soft_limit_node returns * NULL if no other cgroup is present on * the tree */ next_mz = __mem_cgroup_largest_soft_limit_node(mctz); if (next_mz == mz) { css_put(&next_mz->mem->css); next_mz = NULL; } else /* next_mz == NULL or other memcg */ break; } while (1); } __mem_cgroup_remove_exceeded(mz->mem, mz, mctz); excess = res_counter_soft_limit_excess(&mz->mem->res); /* * One school of thought says that we should not add * back the node to the tree if reclaim returns 0. * But our reclaim could return 0, simply because due * to priority we are exposing a smaller subset of * memory to reclaim from. Consider this as a longer * term TODO. */ /* If excess == 0, no tree ops */ __mem_cgroup_insert_exceeded(mz->mem, mz, mctz, excess); spin_unlock(&mctz->lock); css_put(&mz->mem->css); loop++; /* * Could not reclaim anything and there are no more * mem cgroups to try or we seem to be looping without * reclaiming anything. */ if (!nr_reclaimed && (next_mz == NULL || loop > MEM_CGROUP_MAX_SOFT_LIMIT_RECLAIM_LOOPS)) break; } while (!nr_reclaimed); if (next_mz) css_put(&next_mz->mem->css); return nr_reclaimed; } /* * This routine traverse page_cgroup in given list and drop them all. * *And* this routine doesn't reclaim page itself, just removes page_cgroup. */ static int mem_cgroup_force_empty_list(struct mem_cgroup *mem, int node, int zid, enum lru_list lru) { struct zone *zone; struct mem_cgroup_per_zone *mz; struct page_cgroup *pc, *busy; unsigned long flags, loop; struct list_head *list; int ret = 0; zone = &NODE_DATA(node)->node_zones[zid]; mz = mem_cgroup_zoneinfo(mem, node, zid); list = &mz->lists[lru]; loop = MEM_CGROUP_ZSTAT(mz, lru); /* give some margin against EBUSY etc...*/ loop += 256; busy = NULL; while (loop--) { ret = 0; spin_lock_irqsave(&zone->lru_lock, flags); if (list_empty(list)) { spin_unlock_irqrestore(&zone->lru_lock, flags); break; } pc = list_entry(list->prev, struct page_cgroup, lru); if (busy == pc) { list_move(&pc->lru, list); busy = NULL; spin_unlock_irqrestore(&zone->lru_lock, flags); continue; } spin_unlock_irqrestore(&zone->lru_lock, flags); ret = mem_cgroup_move_parent(pc, mem, GFP_KERNEL); if (ret == -ENOMEM) break; if (ret == -EBUSY || ret == -EINVAL) { /* found lock contention or "pc" is obsolete. */ busy = pc; cond_resched(); } else busy = NULL; } if (!ret && !list_empty(list)) return -EBUSY; return ret; } /* * make mem_cgroup's charge to be 0 if there is no task. * This enables deleting this mem_cgroup. */ static int mem_cgroup_force_empty(struct mem_cgroup *mem, bool free_all) { int ret; int node, zid, shrink; int nr_retries = MEM_CGROUP_RECLAIM_RETRIES; struct cgroup *cgrp = mem->css.cgroup; css_get(&mem->css); shrink = 0; /* should free all ? */ if (free_all) goto try_to_free; move_account: do { ret = -EBUSY; if (cgroup_task_count(cgrp) || !list_empty(&cgrp->children)) goto out; ret = -EINTR; if (signal_pending(current)) goto out; /* This is for making all *used* pages to be on LRU. */ lru_add_drain_all(); drain_all_stock_sync(); ret = 0; for_each_node_state(node, N_HIGH_MEMORY) { for (zid = 0; !ret && zid < MAX_NR_ZONES; zid++) { enum lru_list l; for_each_lru(l) { ret = mem_cgroup_force_empty_list(mem, node, zid, l); if (ret) break; } } if (ret) break; } /* it seems parent cgroup doesn't have enough mem */ if (ret == -ENOMEM) goto try_to_free; cond_resched(); /* "ret" should also be checked to ensure all lists are empty. */ } while (mem->res.usage > 0 || ret); out: css_put(&mem->css); return ret; try_to_free: /* returns EBUSY if there is a task or if we come here twice. */ if (cgroup_task_count(cgrp) || !list_empty(&cgrp->children) || shrink) { ret = -EBUSY; goto out; } /* we call try-to-free pages for make this cgroup empty */ lru_add_drain_all(); /* try to free all pages in this cgroup */ shrink = 1; while (nr_retries && mem->res.usage > 0) { int progress; if (signal_pending(current)) { ret = -EINTR; goto out; } progress = try_to_free_mem_cgroup_pages(mem, GFP_KERNEL, false, get_swappiness(mem)); if (!progress) { nr_retries--; /* maybe some writeback is necessary */ congestion_wait(BLK_RW_ASYNC, HZ/10); } } lru_add_drain(); /* try move_account...there may be some *locked* pages. */ goto move_account; } int mem_cgroup_force_empty_write(struct cgroup *cont, unsigned int event) { return mem_cgroup_force_empty(mem_cgroup_from_cont(cont), true); } static u64 mem_cgroup_hierarchy_read(struct cgroup *cont, struct cftype *cft) { return mem_cgroup_from_cont(cont)->use_hierarchy; } static int mem_cgroup_hierarchy_write(struct cgroup *cont, struct cftype *cft, u64 val) { int retval = 0; struct mem_cgroup *mem = mem_cgroup_from_cont(cont); struct cgroup *parent = cont->parent; struct mem_cgroup *parent_mem = NULL; if (parent) parent_mem = mem_cgroup_from_cont(parent); cgroup_lock(); /* * If parent's use_hierarchy is set, we can't make any modifications * in the child subtrees. If it is unset, then the change can * occur, provided the current cgroup has no children. * * For the root cgroup, parent_mem is NULL, we allow value to be * set if there are no children. */ if ((!parent_mem || !parent_mem->use_hierarchy) && (val == 1 || val == 0)) { if (list_empty(&cont->children)) mem->use_hierarchy = val; else retval = -EBUSY; } else retval = -EINVAL; cgroup_unlock(); return retval; } struct mem_cgroup_idx_data { s64 val; enum mem_cgroup_stat_index idx; }; static int mem_cgroup_get_idx_stat(struct mem_cgroup *mem, void *data) { struct mem_cgroup_idx_data *d = data; d->val += mem_cgroup_read_stat(mem, d->idx); return 0; } static void mem_cgroup_get_recursive_idx_stat(struct mem_cgroup *mem, enum mem_cgroup_stat_index idx, s64 *val) { struct mem_cgroup_idx_data d; d.idx = idx; d.val = 0; mem_cgroup_walk_tree(mem, &d, mem_cgroup_get_idx_stat); *val = d.val; } static inline u64 mem_cgroup_usage(struct mem_cgroup *mem, bool swap) { u64 idx_val, val; if (!mem_cgroup_is_root(mem)) { if (!swap) return res_counter_read_u64(&mem->res, RES_USAGE); else return res_counter_read_u64(&mem->memsw, RES_USAGE); } mem_cgroup_get_recursive_idx_stat(mem, MEM_CGROUP_STAT_CACHE, &idx_val); val = idx_val; mem_cgroup_get_recursive_idx_stat(mem, MEM_CGROUP_STAT_RSS, &idx_val); val += idx_val; if (swap) { mem_cgroup_get_recursive_idx_stat(mem, MEM_CGROUP_STAT_SWAPOUT, &idx_val); val += idx_val; } return val << PAGE_SHIFT; } static u64 mem_cgroup_read(struct cgroup *cont, struct cftype *cft) { struct mem_cgroup *mem = mem_cgroup_from_cont(cont); u64 val; int type, name; type = MEMFILE_TYPE(cft->private); name = MEMFILE_ATTR(cft->private); switch (type) { case _MEM: if (name == RES_USAGE) val = mem_cgroup_usage(mem, false); else val = res_counter_read_u64(&mem->res, name); break; case _MEMSWAP: if (name == RES_USAGE) val = mem_cgroup_usage(mem, true); else val = res_counter_read_u64(&mem->memsw, name); break; default: BUG(); break; } return val; } /* * The user of this function is... * RES_LIMIT. */ static int mem_cgroup_write(struct cgroup *cont, struct cftype *cft, const char *buffer) { struct mem_cgroup *memcg = mem_cgroup_from_cont(cont); int type, name; unsigned long long val; int ret; type = MEMFILE_TYPE(cft->private); name = MEMFILE_ATTR(cft->private); switch (name) { case RES_LIMIT: if (mem_cgroup_is_root(memcg)) { /* Can't set limit on root */ ret = -EINVAL; break; } /* This function does all necessary parse...reuse it */ ret = res_counter_memparse_write_strategy(buffer, &val); if (ret) break; if (type == _MEM) ret = mem_cgroup_resize_limit(memcg, val); else ret = mem_cgroup_resize_memsw_limit(memcg, val); break; case RES_SOFT_LIMIT: ret = res_counter_memparse_write_strategy(buffer, &val); if (ret) break; /* * For memsw, soft limits are hard to implement in terms * of semantics, for now, we support soft limits for * control without swap */ if (type == _MEM) ret = res_counter_set_soft_limit(&memcg->res, val); else ret = -EINVAL; break; default: ret = -EINVAL; /* should be BUG() ? */ break; } return ret; } static void memcg_get_hierarchical_limit(struct mem_cgroup *memcg, unsigned long long *mem_limit, unsigned long long *memsw_limit) { struct cgroup *cgroup; unsigned long long min_limit, min_memsw_limit, tmp; min_limit = res_counter_read_u64(&memcg->res, RES_LIMIT); min_memsw_limit = res_counter_read_u64(&memcg->memsw, RES_LIMIT); cgroup = memcg->css.cgroup; if (!memcg->use_hierarchy) goto out; while (cgroup->parent) { cgroup = cgroup->parent; memcg = mem_cgroup_from_cont(cgroup); if (!memcg->use_hierarchy) break; tmp = res_counter_read_u64(&memcg->res, RES_LIMIT); min_limit = min(min_limit, tmp); tmp = res_counter_read_u64(&memcg->memsw, RES_LIMIT); min_memsw_limit = min(min_memsw_limit, tmp); } out: *mem_limit = min_limit; *memsw_limit = min_memsw_limit; return; } static int mem_cgroup_reset(struct cgroup *cont, unsigned int event) { struct mem_cgroup *mem; int type, name; mem = mem_cgroup_from_cont(cont); type = MEMFILE_TYPE(event); name = MEMFILE_ATTR(event); switch (name) { case RES_MAX_USAGE: if (type == _MEM) res_counter_reset_max(&mem->res); else res_counter_reset_max(&mem->memsw); break; case RES_FAILCNT: if (type == _MEM) res_counter_reset_failcnt(&mem->res); else res_counter_reset_failcnt(&mem->memsw); break; } return 0; } static u64 mem_cgroup_move_charge_read(struct cgroup *cgrp, struct cftype *cft) { return mem_cgroup_from_cont(cgrp)->move_charge_at_immigrate; } #ifdef CONFIG_MMU static int mem_cgroup_move_charge_write(struct cgroup *cgrp, struct cftype *cft, u64 val) { struct mem_cgroup *mem = mem_cgroup_from_cont(cgrp); if (val >= (1 << NR_MOVE_TYPE)) return -EINVAL; /* * We check this value several times in both in can_attach() and * attach(), so we need cgroup lock to prevent this value from being * inconsistent. */ cgroup_lock(); mem->move_charge_at_immigrate = val; cgroup_unlock(); return 0; } #else static int mem_cgroup_move_charge_write(struct cgroup *cgrp, struct cftype *cft, u64 val) { return -ENOSYS; } #endif /* For read statistics */ enum { MCS_CACHE, MCS_RSS, MCS_FILE_MAPPED, MCS_PGPGIN, MCS_PGPGOUT, MCS_SWAP, MCS_INACTIVE_ANON, MCS_ACTIVE_ANON, MCS_INACTIVE_FILE, MCS_ACTIVE_FILE, MCS_UNEVICTABLE, NR_MCS_STAT, }; struct mcs_total_stat { s64 stat[NR_MCS_STAT]; }; struct { char *local_name; char *total_name; } memcg_stat_strings[NR_MCS_STAT] = { {"cache", "total_cache"}, {"rss", "total_rss"}, {"mapped_file", "total_mapped_file"}, {"pgpgin", "total_pgpgin"}, {"pgpgout", "total_pgpgout"}, {"swap", "total_swap"}, {"inactive_anon", "total_inactive_anon"}, {"active_anon", "total_active_anon"}, {"inactive_file", "total_inactive_file"}, {"active_file", "total_active_file"}, {"unevictable", "total_unevictable"} }; static int mem_cgroup_get_local_stat(struct mem_cgroup *mem, void *data) { struct mcs_total_stat *s = data; s64 val; /* per cpu stat */ val = mem_cgroup_read_stat(mem, MEM_CGROUP_STAT_CACHE); s->stat[MCS_CACHE] += val * PAGE_SIZE; val = mem_cgroup_read_stat(mem, MEM_CGROUP_STAT_RSS); s->stat[MCS_RSS] += val * PAGE_SIZE; val = mem_cgroup_read_stat(mem, MEM_CGROUP_STAT_FILE_MAPPED); s->stat[MCS_FILE_MAPPED] += val * PAGE_SIZE; val = mem_cgroup_read_stat(mem, MEM_CGROUP_STAT_PGPGIN_COUNT); s->stat[MCS_PGPGIN] += val; val = mem_cgroup_read_stat(mem, MEM_CGROUP_STAT_PGPGOUT_COUNT); s->stat[MCS_PGPGOUT] += val; if (do_swap_account) { val = mem_cgroup_read_stat(mem, MEM_CGROUP_STAT_SWAPOUT); s->stat[MCS_SWAP] += val * PAGE_SIZE; } /* per zone stat */ val = mem_cgroup_get_local_zonestat(mem, LRU_INACTIVE_ANON); s->stat[MCS_INACTIVE_ANON] += val * PAGE_SIZE; val = mem_cgroup_get_local_zonestat(mem, LRU_ACTIVE_ANON); s->stat[MCS_ACTIVE_ANON] += val * PAGE_SIZE; val = mem_cgroup_get_local_zonestat(mem, LRU_INACTIVE_FILE); s->stat[MCS_INACTIVE_FILE] += val * PAGE_SIZE; val = mem_cgroup_get_local_zonestat(mem, LRU_ACTIVE_FILE); s->stat[MCS_ACTIVE_FILE] += val * PAGE_SIZE; val = mem_cgroup_get_local_zonestat(mem, LRU_UNEVICTABLE); s->stat[MCS_UNEVICTABLE] += val * PAGE_SIZE; return 0; } static void mem_cgroup_get_total_stat(struct mem_cgroup *mem, struct mcs_total_stat *s) { mem_cgroup_walk_tree(mem, s, mem_cgroup_get_local_stat); } static int mem_control_stat_show(struct cgroup *cont, struct cftype *cft, struct cgroup_map_cb *cb) { struct mem_cgroup *mem_cont = mem_cgroup_from_cont(cont); struct mcs_total_stat mystat; int i; memset(&mystat, 0, sizeof(mystat)); mem_cgroup_get_local_stat(mem_cont, &mystat); for (i = 0; i < NR_MCS_STAT; i++) { if (i == MCS_SWAP && !do_swap_account) continue; cb->fill(cb, memcg_stat_strings[i].local_name, mystat.stat[i]); } /* Hierarchical information */ { unsigned long long limit, memsw_limit; memcg_get_hierarchical_limit(mem_cont, &limit, &memsw_limit); cb->fill(cb, "hierarchical_memory_limit", limit); if (do_swap_account) cb->fill(cb, "hierarchical_memsw_limit", memsw_limit); } memset(&mystat, 0, sizeof(mystat)); mem_cgroup_get_total_stat(mem_cont, &mystat); for (i = 0; i < NR_MCS_STAT; i++) { if (i == MCS_SWAP && !do_swap_account) continue; cb->fill(cb, memcg_stat_strings[i].total_name, mystat.stat[i]); } #ifdef CONFIG_DEBUG_VM cb->fill(cb, "inactive_ratio", calc_inactive_ratio(mem_cont, NULL)); { int nid, zid; struct mem_cgroup_per_zone *mz; unsigned long recent_rotated[2] = {0, 0}; unsigned long recent_scanned[2] = {0, 0}; for_each_online_node(nid) for (zid = 0; zid < MAX_NR_ZONES; zid++) { mz = mem_cgroup_zoneinfo(mem_cont, nid, zid); recent_rotated[0] += mz->reclaim_stat.recent_rotated[0]; recent_rotated[1] += mz->reclaim_stat.recent_rotated[1]; recent_scanned[0] += mz->reclaim_stat.recent_scanned[0]; recent_scanned[1] += mz->reclaim_stat.recent_scanned[1]; } cb->fill(cb, "recent_rotated_anon", recent_rotated[0]); cb->fill(cb, "recent_rotated_file", recent_rotated[1]); cb->fill(cb, "recent_scanned_anon", recent_scanned[0]); cb->fill(cb, "recent_scanned_file", recent_scanned[1]); } #endif return 0; } static u64 mem_cgroup_swappiness_read(struct cgroup *cgrp, struct cftype *cft) { struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp); return get_swappiness(memcg); } static int mem_cgroup_swappiness_write(struct cgroup *cgrp, struct cftype *cft, u64 val) { struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp); struct mem_cgroup *parent; if (val > 100) return -EINVAL; if (cgrp->parent == NULL) return -EINVAL; parent = mem_cgroup_from_cont(cgrp->parent); cgroup_lock(); /* If under hierarchy, only empty-root can set this value */ if ((parent->use_hierarchy) || (memcg->use_hierarchy && !list_empty(&cgrp->children))) { cgroup_unlock(); return -EINVAL; } spin_lock(&memcg->reclaim_param_lock); memcg->swappiness = val; spin_unlock(&memcg->reclaim_param_lock); cgroup_unlock(); return 0; } static void __mem_cgroup_threshold(struct mem_cgroup *memcg, bool swap) { struct mem_cgroup_threshold_ary *t; u64 usage; int i; rcu_read_lock(); if (!swap) t = rcu_dereference(memcg->thresholds); else t = rcu_dereference(memcg->memsw_thresholds); if (!t) goto unlock; usage = mem_cgroup_usage(memcg, swap); /* * current_threshold points to threshold just below usage. * If it's not true, a threshold was crossed after last * call of __mem_cgroup_threshold(). */ i = atomic_read(&t->current_threshold); /* * Iterate backward over array of thresholds starting from * current_threshold and check if a threshold is crossed. * If none of thresholds below usage is crossed, we read * only one element of the array here. */ for (; i >= 0 && unlikely(t->entries[i].threshold > usage); i--) eventfd_signal(t->entries[i].eventfd, 1); /* i = current_threshold + 1 */ i++; /* * Iterate forward over array of thresholds starting from * current_threshold+1 and check if a threshold is crossed. * If none of thresholds above usage is crossed, we read * only one element of the array here. */ for (; i < t->size && unlikely(t->entries[i].threshold <= usage); i++) eventfd_signal(t->entries[i].eventfd, 1); /* Update current_threshold */ atomic_set(&t->current_threshold, i - 1); unlock: rcu_read_unlock(); } static void mem_cgroup_threshold(struct mem_cgroup *memcg) { __mem_cgroup_threshold(memcg, false); if (do_swap_account) __mem_cgroup_threshold(memcg, true); } static int compare_thresholds(const void *a, const void *b) { const struct mem_cgroup_threshold *_a = a; const struct mem_cgroup_threshold *_b = b; return _a->threshold - _b->threshold; } static int mem_cgroup_register_event(struct cgroup *cgrp, struct cftype *cft, struct eventfd_ctx *eventfd, const char *args) { struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp); struct mem_cgroup_threshold_ary *thresholds, *thresholds_new; int type = MEMFILE_TYPE(cft->private); u64 threshold, usage; int size; int i, ret; ret = res_counter_memparse_write_strategy(args, &threshold); if (ret) return ret; mutex_lock(&memcg->thresholds_lock); if (type == _MEM) thresholds = memcg->thresholds; else if (type == _MEMSWAP) thresholds = memcg->memsw_thresholds; else BUG(); usage = mem_cgroup_usage(memcg, type == _MEMSWAP); /* Check if a threshold crossed before adding a new one */ if (thresholds) __mem_cgroup_threshold(memcg, type == _MEMSWAP); if (thresholds) size = thresholds->size + 1; else size = 1; /* Allocate memory for new array of thresholds */ thresholds_new = kmalloc(sizeof(*thresholds_new) + size * sizeof(struct mem_cgroup_threshold), GFP_KERNEL); if (!thresholds_new) { ret = -ENOMEM; goto unlock; } thresholds_new->size = size; /* Copy thresholds (if any) to new array */ if (thresholds) memcpy(thresholds_new->entries, thresholds->entries, thresholds->size * sizeof(struct mem_cgroup_threshold)); /* Add new threshold */ thresholds_new->entries[size - 1].eventfd = eventfd; thresholds_new->entries[size - 1].threshold = threshold; /* Sort thresholds. Registering of new threshold isn't time-critical */ sort(thresholds_new->entries, size, sizeof(struct mem_cgroup_threshold), compare_thresholds, NULL); /* Find current threshold */ atomic_set(&thresholds_new->current_threshold, -1); for (i = 0; i < size; i++) { if (thresholds_new->entries[i].threshold < usage) { /* * thresholds_new->current_threshold will not be used * until rcu_assign_pointer(), so it's safe to increment * it here. */ atomic_inc(&thresholds_new->current_threshold); } } if (type == _MEM) rcu_assign_pointer(memcg->thresholds, thresholds_new); else rcu_assign_pointer(memcg->memsw_thresholds, thresholds_new); /* To be sure that nobody uses thresholds before freeing it */ synchronize_rcu(); kfree(thresholds); unlock: mutex_unlock(&memcg->thresholds_lock); return ret; } static int mem_cgroup_unregister_event(struct cgroup *cgrp, struct cftype *cft, struct eventfd_ctx *eventfd) { struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp); struct mem_cgroup_threshold_ary *thresholds, *thresholds_new; int type = MEMFILE_TYPE(cft->private); u64 usage; int size = 0; int i, j, ret; mutex_lock(&memcg->thresholds_lock); if (type == _MEM) thresholds = memcg->thresholds; else if (type == _MEMSWAP) thresholds = memcg->memsw_thresholds; else BUG(); /* * Something went wrong if we trying to unregister a threshold * if we don't have thresholds */ BUG_ON(!thresholds); usage = mem_cgroup_usage(memcg, type == _MEMSWAP); /* Check if a threshold crossed before removing */ __mem_cgroup_threshold(memcg, type == _MEMSWAP); /* Calculate new number of threshold */ for (i = 0; i < thresholds->size; i++) { if (thresholds->entries[i].eventfd != eventfd) size++; } /* Set thresholds array to NULL if we don't have thresholds */ if (!size) { thresholds_new = NULL; goto assign; } /* Allocate memory for new array of thresholds */ thresholds_new = kmalloc(sizeof(*thresholds_new) + size * sizeof(struct mem_cgroup_threshold), GFP_KERNEL); if (!thresholds_new) { ret = -ENOMEM; goto unlock; } thresholds_new->size = size; /* Copy thresholds and find current threshold */ atomic_set(&thresholds_new->current_threshold, -1); for (i = 0, j = 0; i < thresholds->size; i++) { if (thresholds->entries[i].eventfd == eventfd) continue; thresholds_new->entries[j] = thresholds->entries[i]; if (thresholds_new->entries[j].threshold < usage) { /* * thresholds_new->current_threshold will not be used * until rcu_assign_pointer(), so it's safe to increment * it here. */ atomic_inc(&thresholds_new->current_threshold); } j++; } assign: if (type == _MEM) rcu_assign_pointer(memcg->thresholds, thresholds_new); else rcu_assign_pointer(memcg->memsw_thresholds, thresholds_new); /* To be sure that nobody uses thresholds before freeing it */ synchronize_rcu(); kfree(thresholds); unlock: mutex_unlock(&memcg->thresholds_lock); return ret; } static struct cftype mem_cgroup_files[] = { { .name = "usage_in_bytes", .private = MEMFILE_PRIVATE(_MEM, RES_USAGE), .read_u64 = mem_cgroup_read, .register_event = mem_cgroup_register_event, .unregister_event = mem_cgroup_unregister_event, }, { .name = "max_usage_in_bytes", .private = MEMFILE_PRIVATE(_MEM, RES_MAX_USAGE), .trigger = mem_cgroup_reset, .read_u64 = mem_cgroup_read, }, { .name = "limit_in_bytes", .private = MEMFILE_PRIVATE(_MEM, RES_LIMIT), .write_string = mem_cgroup_write, .read_u64 = mem_cgroup_read, }, { .name = "soft_limit_in_bytes", .private = MEMFILE_PRIVATE(_MEM, RES_SOFT_LIMIT), .write_string = mem_cgroup_write, .read_u64 = mem_cgroup_read, }, { .name = "failcnt", .private = MEMFILE_PRIVATE(_MEM, RES_FAILCNT), .trigger = mem_cgroup_reset, .read_u64 = mem_cgroup_read, }, { .name = "stat", .read_map = mem_control_stat_show, }, { .name = "force_empty", .trigger = mem_cgroup_force_empty_write, }, { .name = "use_hierarchy", .write_u64 = mem_cgroup_hierarchy_write, .read_u64 = mem_cgroup_hierarchy_read, }, { .name = "swappiness", .read_u64 = mem_cgroup_swappiness_read, .write_u64 = mem_cgroup_swappiness_write, }, { .name = "move_charge_at_immigrate", .read_u64 = mem_cgroup_move_charge_read, .write_u64 = mem_cgroup_move_charge_write, }, }; #ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP static struct cftype memsw_cgroup_files[] = { { .name = "memsw.usage_in_bytes", .private = MEMFILE_PRIVATE(_MEMSWAP, RES_USAGE), .read_u64 = mem_cgroup_read, .register_event = mem_cgroup_register_event, .unregister_event = mem_cgroup_unregister_event, }, { .name = "memsw.max_usage_in_bytes", .private = MEMFILE_PRIVATE(_MEMSWAP, RES_MAX_USAGE), .trigger = mem_cgroup_reset, .read_u64 = mem_cgroup_read, }, { .name = "memsw.limit_in_bytes", .private = MEMFILE_PRIVATE(_MEMSWAP, RES_LIMIT), .write_string = mem_cgroup_write, .read_u64 = mem_cgroup_read, }, { .name = "memsw.failcnt", .private = MEMFILE_PRIVATE(_MEMSWAP, RES_FAILCNT), .trigger = mem_cgroup_reset, .read_u64 = mem_cgroup_read, }, }; static int register_memsw_files(struct cgroup *cont, struct cgroup_subsys *ss) { if (!do_swap_account) return 0; return cgroup_add_files(cont, ss, memsw_cgroup_files, ARRAY_SIZE(memsw_cgroup_files)); }; #else static int register_memsw_files(struct cgroup *cont, struct cgroup_subsys *ss) { return 0; } #endif static int alloc_mem_cgroup_per_zone_info(struct mem_cgroup *mem, int node) { struct mem_cgroup_per_node *pn; struct mem_cgroup_per_zone *mz; enum lru_list l; int zone, tmp = node; /* * This routine is called against possible nodes. * But it's BUG to call kmalloc() against offline node. * * TODO: this routine can waste much memory for nodes which will * never be onlined. It's better to use memory hotplug callback * function. */ if (!node_state(node, N_NORMAL_MEMORY)) tmp = -1; pn = kmalloc_node(sizeof(*pn), GFP_KERNEL, tmp); if (!pn) return 1; mem->info.nodeinfo[node] = pn; memset(pn, 0, sizeof(*pn)); for (zone = 0; zone < MAX_NR_ZONES; zone++) { mz = &pn->zoneinfo[zone]; for_each_lru(l) INIT_LIST_HEAD(&mz->lists[l]); mz->usage_in_excess = 0; mz->on_tree = false; mz->mem = mem; } return 0; } static void free_mem_cgroup_per_zone_info(struct mem_cgroup *mem, int node) { kfree(mem->info.nodeinfo[node]); } static struct mem_cgroup *mem_cgroup_alloc(void) { struct mem_cgroup *mem; int size = sizeof(struct mem_cgroup); /* Can be very big if MAX_NUMNODES is very big */ if (size < PAGE_SIZE) mem = kmalloc(size, GFP_KERNEL); else mem = vmalloc(size); if (!mem) return NULL; memset(mem, 0, size); mem->stat = alloc_percpu(struct mem_cgroup_stat_cpu); if (!mem->stat) { if (size < PAGE_SIZE) kfree(mem); else vfree(mem); mem = NULL; } return mem; } /* * At destroying mem_cgroup, references from swap_cgroup can remain. * (scanning all at force_empty is too costly...) * * Instead of clearing all references at force_empty, we remember * the number of reference from swap_cgroup and free mem_cgroup when * it goes down to 0. * * Removal of cgroup itself succeeds regardless of refs from swap. */ static void __mem_cgroup_free(struct mem_cgroup *mem) { int node; mem_cgroup_remove_from_trees(mem); free_css_id(&mem_cgroup_subsys, &mem->css); for_each_node_state(node, N_POSSIBLE) free_mem_cgroup_per_zone_info(mem, node); free_percpu(mem->stat); if (sizeof(struct mem_cgroup) < PAGE_SIZE) kfree(mem); else vfree(mem); } static void mem_cgroup_get(struct mem_cgroup *mem) { atomic_inc(&mem->refcnt); } static void __mem_cgroup_put(struct mem_cgroup *mem, int count) { if (atomic_sub_and_test(count, &mem->refcnt)) { struct mem_cgroup *parent = parent_mem_cgroup(mem); __mem_cgroup_free(mem); if (parent) mem_cgroup_put(parent); } } static void mem_cgroup_put(struct mem_cgroup *mem) { __mem_cgroup_put(mem, 1); } /* * Returns the parent mem_cgroup in memcgroup hierarchy with hierarchy enabled. */ static struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *mem) { if (!mem->res.parent) return NULL; return mem_cgroup_from_res_counter(mem->res.parent, res); } #ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP static void __init enable_swap_cgroup(void) { if (!mem_cgroup_disabled() && really_do_swap_account) do_swap_account = 1; } #else static void __init enable_swap_cgroup(void) { } #endif static int mem_cgroup_soft_limit_tree_init(void) { struct mem_cgroup_tree_per_node *rtpn; struct mem_cgroup_tree_per_zone *rtpz; int tmp, node, zone; for_each_node_state(node, N_POSSIBLE) { tmp = node; if (!node_state(node, N_NORMAL_MEMORY)) tmp = -1; rtpn = kzalloc_node(sizeof(*rtpn), GFP_KERNEL, tmp); if (!rtpn) return 1; soft_limit_tree.rb_tree_per_node[node] = rtpn; for (zone = 0; zone < MAX_NR_ZONES; zone++) { rtpz = &rtpn->rb_tree_per_zone[zone]; rtpz->rb_root = RB_ROOT; spin_lock_init(&rtpz->lock); } } return 0; } static struct cgroup_subsys_state * __ref mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont) { struct mem_cgroup *mem, *parent; long error = -ENOMEM; int node; mem = mem_cgroup_alloc(); if (!mem) return ERR_PTR(error); for_each_node_state(node, N_POSSIBLE) if (alloc_mem_cgroup_per_zone_info(mem, node)) goto free_out; /* root ? */ if (cont->parent == NULL) { int cpu; enable_swap_cgroup(); parent = NULL; root_mem_cgroup = mem; if (mem_cgroup_soft_limit_tree_init()) goto free_out; for_each_possible_cpu(cpu) { struct memcg_stock_pcp *stock = &per_cpu(memcg_stock, cpu); INIT_WORK(&stock->work, drain_local_stock); } hotcpu_notifier(memcg_stock_cpu_callback, 0); } else { parent = mem_cgroup_from_cont(cont->parent); mem->use_hierarchy = parent->use_hierarchy; } if (parent && parent->use_hierarchy) { res_counter_init(&mem->res, &parent->res); res_counter_init(&mem->memsw, &parent->memsw); /* * We increment refcnt of the parent to ensure that we can * safely access it on res_counter_charge/uncharge. * This refcnt will be decremented when freeing this * mem_cgroup(see mem_cgroup_put). */ mem_cgroup_get(parent); } else { res_counter_init(&mem->res, NULL); res_counter_init(&mem->memsw, NULL); } mem->last_scanned_child = 0; spin_lock_init(&mem->reclaim_param_lock); if (parent) mem->swappiness = get_swappiness(parent); atomic_set(&mem->refcnt, 1); mem->move_charge_at_immigrate = 0; mutex_init(&mem->thresholds_lock); return &mem->css; free_out: __mem_cgroup_free(mem); root_mem_cgroup = NULL; return ERR_PTR(error); } static int mem_cgroup_pre_destroy(struct cgroup_subsys *ss, struct cgroup *cont) { struct mem_cgroup *mem = mem_cgroup_from_cont(cont); return mem_cgroup_force_empty(mem, false); } static void mem_cgroup_destroy(struct cgroup_subsys *ss, struct cgroup *cont) { struct mem_cgroup *mem = mem_cgroup_from_cont(cont); mem_cgroup_put(mem); } static int mem_cgroup_populate(struct cgroup_subsys *ss, struct cgroup *cont) { int ret; ret = cgroup_add_files(cont, ss, mem_cgroup_files, ARRAY_SIZE(mem_cgroup_files)); if (!ret) ret = register_memsw_files(cont, ss); return ret; } #ifdef CONFIG_MMU /* Handlers for move charge at task migration. */ #define PRECHARGE_COUNT_AT_ONCE 256 static int mem_cgroup_do_precharge(unsigned long count) { int ret = 0; int batch_count = PRECHARGE_COUNT_AT_ONCE; struct mem_cgroup *mem = mc.to; if (mem_cgroup_is_root(mem)) { mc.precharge += count; /* we don't need css_get for root */ return ret; } /* try to charge at once */ if (count > 1) { struct res_counter *dummy; /* * "mem" cannot be under rmdir() because we've already checked * by cgroup_lock_live_cgroup() that it is not removed and we * are still under the same cgroup_mutex. So we can postpone * css_get(). */ if (res_counter_charge(&mem->res, PAGE_SIZE * count, &dummy)) goto one_by_one; if (do_swap_account && res_counter_charge(&mem->memsw, PAGE_SIZE * count, &dummy)) { res_counter_uncharge(&mem->res, PAGE_SIZE * count); goto one_by_one; } mc.precharge += count; VM_BUG_ON(test_bit(CSS_ROOT, &mem->css.flags)); WARN_ON_ONCE(count > INT_MAX); __css_get(&mem->css, (int)count); return ret; } one_by_one: /* fall back to one by one charge */ while (count--) { if (signal_pending(current)) { ret = -EINTR; break; } if (!batch_count--) { batch_count = PRECHARGE_COUNT_AT_ONCE; cond_resched(); } ret = __mem_cgroup_try_charge(NULL, GFP_KERNEL, &mem, false); if (ret || !mem) /* mem_cgroup_clear_mc() will do uncharge later */ return -ENOMEM; mc.precharge++; } return ret; } /** * is_target_pte_for_mc - check a pte whether it is valid for move charge * @vma: the vma the pte to be checked belongs * @addr: the address corresponding to the pte to be checked * @ptent: the pte to be checked * @target: the pointer the target page or swap ent will be stored(can be NULL) * * Returns * 0(MC_TARGET_NONE): if the pte is not a target for move charge. * 1(MC_TARGET_PAGE): if the page corresponding to this pte is a target for * move charge. if @target is not NULL, the page is stored in target->page * with extra refcnt got(Callers should handle it). * 2(MC_TARGET_SWAP): if the swap entry corresponding to this pte is a * target for charge migration. if @target is not NULL, the entry is stored * in target->ent. * * Called with pte lock held. */ union mc_target { struct page *page; swp_entry_t ent; }; enum mc_target_type { MC_TARGET_NONE, /* not used */ MC_TARGET_PAGE, MC_TARGET_SWAP, }; static int is_target_pte_for_mc(struct vm_area_struct *vma, unsigned long addr, pte_t ptent, union mc_target *target) { struct page *page = NULL; struct page_cgroup *pc; int ret = 0; swp_entry_t ent = { .val = 0 }; int usage_count = 0; bool move_anon = test_bit(MOVE_CHARGE_TYPE_ANON, &mc.to->move_charge_at_immigrate); if (!pte_present(ptent)) { /* TODO: handle swap of shmes/tmpfs */ if (pte_none(ptent) || pte_file(ptent)) return 0; else if (is_swap_pte(ptent)) { ent = pte_to_swp_entry(ptent); if (!move_anon || non_swap_entry(ent)) return 0; usage_count = mem_cgroup_count_swap_user(ent, &page); } } else { page = vm_normal_page(vma, addr, ptent); if (!page || !page_mapped(page)) return 0; /* * TODO: We don't move charges of file(including shmem/tmpfs) * pages for now. */ if (!move_anon || !PageAnon(page)) return 0; if (!get_page_unless_zero(page)) return 0; usage_count = page_mapcount(page); } if (usage_count > 1) { /* * TODO: We don't move charges of shared(used by multiple * processes) pages for now. */ if (page) put_page(page); return 0; } if (page) { pc = lookup_page_cgroup(page); /* * Do only loose check w/o page_cgroup lock. * mem_cgroup_move_account() checks the pc is valid or not under * the lock. */ if (PageCgroupUsed(pc) && pc->mem_cgroup == mc.from) { ret = MC_TARGET_PAGE; if (target) target->page = page; } if (!ret || !target) put_page(page); } /* throught */ if (ent.val && do_swap_account && !ret && css_id(&mc.from->css) == lookup_swap_cgroup(ent)) { ret = MC_TARGET_SWAP; if (target) target->ent = ent; } return ret; } static int mem_cgroup_count_precharge_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, struct mm_walk *walk) { struct vm_area_struct *vma = walk->private; pte_t *pte; spinlock_t *ptl; pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); for (; addr != end; pte++, addr += PAGE_SIZE) if (is_target_pte_for_mc(vma, addr, *pte, NULL)) mc.precharge++; /* increment precharge temporarily */ pte_unmap_unlock(pte - 1, ptl); cond_resched(); return 0; } static unsigned long mem_cgroup_count_precharge(struct mm_struct *mm) { unsigned long precharge; struct vm_area_struct *vma; down_read(&mm->mmap_sem); for (vma = mm->mmap; vma; vma = vma->vm_next) { struct mm_walk mem_cgroup_count_precharge_walk = { .pmd_entry = mem_cgroup_count_precharge_pte_range, .mm = mm, .private = vma, }; if (is_vm_hugetlb_page(vma)) continue; /* TODO: We don't move charges of shmem/tmpfs pages for now. */ if (vma->vm_flags & VM_SHARED) continue; walk_page_range(vma->vm_start, vma->vm_end, &mem_cgroup_count_precharge_walk); } up_read(&mm->mmap_sem); precharge = mc.precharge; mc.precharge = 0; return precharge; } static int mem_cgroup_precharge_mc(struct mm_struct *mm) { return mem_cgroup_do_precharge(mem_cgroup_count_precharge(mm)); } static void mem_cgroup_clear_mc(void) { /* we must uncharge all the leftover precharges from mc.to */ if (mc.precharge) { __mem_cgroup_cancel_charge(mc.to, mc.precharge); mc.precharge = 0; } /* * we didn't uncharge from mc.from at mem_cgroup_move_account(), so * we must uncharge here. */ if (mc.moved_charge) { __mem_cgroup_cancel_charge(mc.from, mc.moved_charge); mc.moved_charge = 0; } /* we must fixup refcnts and charges */ if (mc.moved_swap) { WARN_ON_ONCE(mc.moved_swap > INT_MAX); /* uncharge swap account from the old cgroup */ if (!mem_cgroup_is_root(mc.from)) res_counter_uncharge(&mc.from->memsw, PAGE_SIZE * mc.moved_swap); __mem_cgroup_put(mc.from, mc.moved_swap); if (!mem_cgroup_is_root(mc.to)) { /* * we charged both to->res and to->memsw, so we should * uncharge to->res. */ res_counter_uncharge(&mc.to->res, PAGE_SIZE * mc.moved_swap); VM_BUG_ON(test_bit(CSS_ROOT, &mc.to->css.flags)); __css_put(&mc.to->css, mc.moved_swap); } /* we've already done mem_cgroup_get(mc.to) */ mc.moved_swap = 0; } mc.from = NULL; mc.to = NULL; mc.moving_task = NULL; wake_up_all(&mc.waitq); } static int mem_cgroup_can_attach(struct cgroup_subsys *ss, struct cgroup *cgroup, struct task_struct *p, bool threadgroup) { int ret = 0; struct mem_cgroup *mem = mem_cgroup_from_cont(cgroup); if (mem->move_charge_at_immigrate) { struct mm_struct *mm; struct mem_cgroup *from = mem_cgroup_from_task(p); VM_BUG_ON(from == mem); mm = get_task_mm(p); if (!mm) return 0; /* We move charges only when we move a owner of the mm */ if (mm->owner == p) { VM_BUG_ON(mc.from); VM_BUG_ON(mc.to); VM_BUG_ON(mc.precharge); VM_BUG_ON(mc.moved_charge); VM_BUG_ON(mc.moved_swap); VM_BUG_ON(mc.moving_task); mc.from = from; mc.to = mem; mc.precharge = 0; mc.moved_charge = 0; mc.moved_swap = 0; mc.moving_task = current; ret = mem_cgroup_precharge_mc(mm); if (ret) mem_cgroup_clear_mc(); } mmput(mm); } return ret; } static void mem_cgroup_cancel_attach(struct cgroup_subsys *ss, struct cgroup *cgroup, struct task_struct *p, bool threadgroup) { mem_cgroup_clear_mc(); } static int mem_cgroup_move_charge_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, struct mm_walk *walk) { int ret = 0; struct vm_area_struct *vma = walk->private; pte_t *pte; spinlock_t *ptl; retry: pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); for (; addr != end; addr += PAGE_SIZE) { pte_t ptent = *(pte++); union mc_target target; int type; struct page *page; struct page_cgroup *pc; swp_entry_t ent; if (!mc.precharge) break; type = is_target_pte_for_mc(vma, addr, ptent, &target); switch (type) { case MC_TARGET_PAGE: page = target.page; if (isolate_lru_page(page)) goto put; pc = lookup_page_cgroup(page); if (!mem_cgroup_move_account(pc, mc.from, mc.to, false)) { mc.precharge--; /* we uncharge from mc.from later. */ mc.moved_charge++; } putback_lru_page(page); put: /* is_target_pte_for_mc() gets the page */ put_page(page); break; case MC_TARGET_SWAP: ent = target.ent; if (!mem_cgroup_move_swap_account(ent, mc.from, mc.to, false)) { mc.precharge--; /* we fixup refcnts and charges later. */ mc.moved_swap++; } break; default: break; } } pte_unmap_unlock(pte - 1, ptl); cond_resched(); if (addr != end) { /* * We have consumed all precharges we got in can_attach(). * We try charge one by one, but don't do any additional * charges to mc.to if we have failed in charge once in attach() * phase. */ ret = mem_cgroup_do_precharge(1); if (!ret) goto retry; } return ret; } static void mem_cgroup_move_charge(struct mm_struct *mm) { struct vm_area_struct *vma; lru_add_drain_all(); down_read(&mm->mmap_sem); for (vma = mm->mmap; vma; vma = vma->vm_next) { int ret; struct mm_walk mem_cgroup_move_charge_walk = { .pmd_entry = mem_cgroup_move_charge_pte_range, .mm = mm, .private = vma, }; if (is_vm_hugetlb_page(vma)) continue; /* TODO: We don't move charges of shmem/tmpfs pages for now. */ if (vma->vm_flags & VM_SHARED) continue; ret = walk_page_range(vma->vm_start, vma->vm_end, &mem_cgroup_move_charge_walk); if (ret) /* * means we have consumed all precharges and failed in * doing additional charge. Just abandon here. */ break; } up_read(&mm->mmap_sem); } static void mem_cgroup_move_task(struct cgroup_subsys *ss, struct cgroup *cont, struct cgroup *old_cont, struct task_struct *p, bool threadgroup) { struct mm_struct *mm; if (!mc.to) /* no need to move charge */ return; mm = get_task_mm(p); if (mm) { mem_cgroup_move_charge(mm); mmput(mm); } mem_cgroup_clear_mc(); } #else /* !CONFIG_MMU */ static int mem_cgroup_can_attach(struct cgroup_subsys *ss, struct cgroup *cgroup, struct task_struct *p, bool threadgroup) { return 0; } static void mem_cgroup_cancel_attach(struct cgroup_subsys *ss, struct cgroup *cgroup, struct task_struct *p, bool threadgroup) { } static void mem_cgroup_move_task(struct cgroup_subsys *ss, struct cgroup *cont, struct cgroup *old_cont, struct task_struct *p, bool threadgroup) { } #endif struct cgroup_subsys mem_cgroup_subsys = { .name = "memory", .subsys_id = mem_cgroup_subsys_id, .create = mem_cgroup_create, .pre_destroy = mem_cgroup_pre_destroy, .destroy = mem_cgroup_destroy, .populate = mem_cgroup_populate, .can_attach = mem_cgroup_can_attach, .cancel_attach = mem_cgroup_cancel_attach, .attach = mem_cgroup_move_task, .early_init = 0, .use_id = 1, }; #ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP static int __init disable_swap_account(char *s) { really_do_swap_account = 0; return 1; } __setup("noswapaccount", disable_swap_account); #endif