summaryrefslogtreecommitdiff
path: root/drivers/pci/host/pci-hyperv.c
blob: 58f7eeb79bb472fbc678ac1475d21ddf4a8308de (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
/*
 * Copyright (c) Microsoft Corporation.
 *
 * Author:
 *   Jake Oshins <jakeo@microsoft.com>
 *
 * This driver acts as a paravirtual front-end for PCI Express root buses.
 * When a PCI Express function (either an entire device or an SR-IOV
 * Virtual Function) is being passed through to the VM, this driver exposes
 * a new bus to the guest VM.  This is modeled as a root PCI bus because
 * no bridges are being exposed to the VM.  In fact, with a "Generation 2"
 * VM within Hyper-V, there may seem to be no PCI bus at all in the VM
 * until a device as been exposed using this driver.
 *
 * Each root PCI bus has its own PCI domain, which is called "Segment" in
 * the PCI Firmware Specifications.  Thus while each device passed through
 * to the VM using this front-end will appear at "device 0", the domain will
 * be unique.  Typically, each bus will have one PCI function on it, though
 * this driver does support more than one.
 *
 * In order to map the interrupts from the device through to the guest VM,
 * this driver also implements an IRQ Domain, which handles interrupts (either
 * MSI or MSI-X) associated with the functions on the bus.  As interrupts are
 * set up, torn down, or reaffined, this driver communicates with the
 * underlying hypervisor to adjust the mappings in the I/O MMU so that each
 * interrupt will be delivered to the correct virtual processor at the right
 * vector.  This driver does not support level-triggered (line-based)
 * interrupts, and will report that the Interrupt Line register in the
 * function's configuration space is zero.
 *
 * The rest of this driver mostly maps PCI concepts onto underlying Hyper-V
 * facilities.  For instance, the configuration space of a function exposed
 * by Hyper-V is mapped into a single page of memory space, and the
 * read and write handlers for config space must be aware of this mechanism.
 * Similarly, device setup and teardown involves messages sent to and from
 * the PCI back-end driver in Hyper-V.
 *
 * This program is free software; you can redistribute it and/or modify it
 * under the terms of the GNU General Public License version 2 as published
 * by the Free Software Foundation.
 *
 * This program is distributed in the hope that it will be useful, but
 * WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
 * NON INFRINGEMENT.  See the GNU General Public License for more
 * details.
 *
 */

#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/pci.h>
#include <linux/semaphore.h>
#include <linux/irqdomain.h>
#include <asm/irqdomain.h>
#include <asm/apic.h>
#include <linux/msi.h>
#include <linux/hyperv.h>
#include <asm/mshyperv.h>

/*
 * Protocol versions. The low word is the minor version, the high word the
 * major version.
 */

#define PCI_MAKE_VERSION(major, minor) ((u32)(((major) << 16) | (major)))
#define PCI_MAJOR_VERSION(version) ((u32)(version) >> 16)
#define PCI_MINOR_VERSION(version) ((u32)(version) & 0xff)

enum {
	PCI_PROTOCOL_VERSION_1_1 = PCI_MAKE_VERSION(1, 1),
	PCI_PROTOCOL_VERSION_CURRENT = PCI_PROTOCOL_VERSION_1_1
};

#define PCI_CONFIG_MMIO_LENGTH	0x2000
#define CFG_PAGE_OFFSET 0x1000
#define CFG_PAGE_SIZE (PCI_CONFIG_MMIO_LENGTH - CFG_PAGE_OFFSET)

#define MAX_SUPPORTED_MSI_MESSAGES 0x400

/*
 * Message Types
 */

enum pci_message_type {
	/*
	 * Version 1.1
	 */
	PCI_MESSAGE_BASE                = 0x42490000,
	PCI_BUS_RELATIONS               = PCI_MESSAGE_BASE + 0,
	PCI_QUERY_BUS_RELATIONS         = PCI_MESSAGE_BASE + 1,
	PCI_POWER_STATE_CHANGE          = PCI_MESSAGE_BASE + 4,
	PCI_QUERY_RESOURCE_REQUIREMENTS = PCI_MESSAGE_BASE + 5,
	PCI_QUERY_RESOURCE_RESOURCES    = PCI_MESSAGE_BASE + 6,
	PCI_BUS_D0ENTRY                 = PCI_MESSAGE_BASE + 7,
	PCI_BUS_D0EXIT                  = PCI_MESSAGE_BASE + 8,
	PCI_READ_BLOCK                  = PCI_MESSAGE_BASE + 9,
	PCI_WRITE_BLOCK                 = PCI_MESSAGE_BASE + 0xA,
	PCI_EJECT                       = PCI_MESSAGE_BASE + 0xB,
	PCI_QUERY_STOP                  = PCI_MESSAGE_BASE + 0xC,
	PCI_REENABLE                    = PCI_MESSAGE_BASE + 0xD,
	PCI_QUERY_STOP_FAILED           = PCI_MESSAGE_BASE + 0xE,
	PCI_EJECTION_COMPLETE           = PCI_MESSAGE_BASE + 0xF,
	PCI_RESOURCES_ASSIGNED          = PCI_MESSAGE_BASE + 0x10,
	PCI_RESOURCES_RELEASED          = PCI_MESSAGE_BASE + 0x11,
	PCI_INVALIDATE_BLOCK            = PCI_MESSAGE_BASE + 0x12,
	PCI_QUERY_PROTOCOL_VERSION      = PCI_MESSAGE_BASE + 0x13,
	PCI_CREATE_INTERRUPT_MESSAGE    = PCI_MESSAGE_BASE + 0x14,
	PCI_DELETE_INTERRUPT_MESSAGE    = PCI_MESSAGE_BASE + 0x15,
	PCI_MESSAGE_MAXIMUM
};

/*
 * Structures defining the virtual PCI Express protocol.
 */

union pci_version {
	struct {
		u16 minor_version;
		u16 major_version;
	} parts;
	u32 version;
} __packed;

/*
 * Function numbers are 8-bits wide on Express, as interpreted through ARI,
 * which is all this driver does.  This representation is the one used in
 * Windows, which is what is expected when sending this back and forth with
 * the Hyper-V parent partition.
 */
union win_slot_encoding {
	struct {
		u32	func:8;
		u32	reserved:24;
	} bits;
	u32 slot;
} __packed;

/*
 * Pretty much as defined in the PCI Specifications.
 */
struct pci_function_description {
	u16	v_id;	/* vendor ID */
	u16	d_id;	/* device ID */
	u8	rev;
	u8	prog_intf;
	u8	subclass;
	u8	base_class;
	u32	subsystem_id;
	union win_slot_encoding win_slot;
	u32	ser;	/* serial number */
} __packed;

/**
 * struct hv_msi_desc
 * @vector:		IDT entry
 * @delivery_mode:	As defined in Intel's Programmer's
 *			Reference Manual, Volume 3, Chapter 8.
 * @vector_count:	Number of contiguous entries in the
 *			Interrupt Descriptor Table that are
 *			occupied by this Message-Signaled
 *			Interrupt. For "MSI", as first defined
 *			in PCI 2.2, this can be between 1 and
 *			32. For "MSI-X," as first defined in PCI
 *			3.0, this must be 1, as each MSI-X table
 *			entry would have its own descriptor.
 * @reserved:		Empty space
 * @cpu_mask:		All the target virtual processors.
 */
struct hv_msi_desc {
	u8	vector;
	u8	delivery_mode;
	u16	vector_count;
	u32	reserved;
	u64	cpu_mask;
} __packed;

/**
 * struct tran_int_desc
 * @reserved:		unused, padding
 * @vector_count:	same as in hv_msi_desc
 * @data:		This is the "data payload" value that is
 *			written by the device when it generates
 *			a message-signaled interrupt, either MSI
 *			or MSI-X.
 * @address:		This is the address to which the data
 *			payload is written on interrupt
 *			generation.
 */
struct tran_int_desc {
	u16	reserved;
	u16	vector_count;
	u32	data;
	u64	address;
} __packed;

/*
 * A generic message format for virtual PCI.
 * Specific message formats are defined later in the file.
 */

struct pci_message {
	u32 message_type;
} __packed;

struct pci_child_message {
	u32 message_type;
	union win_slot_encoding wslot;
} __packed;

struct pci_incoming_message {
	struct vmpacket_descriptor hdr;
	struct pci_message message_type;
} __packed;

struct pci_response {
	struct vmpacket_descriptor hdr;
	s32 status;			/* negative values are failures */
} __packed;

struct pci_packet {
	void (*completion_func)(void *context, struct pci_response *resp,
				int resp_packet_size);
	void *compl_ctxt;
	struct pci_message message;
};

/*
 * Specific message types supporting the PCI protocol.
 */

/*
 * Version negotiation message. Sent from the guest to the host.
 * The guest is free to try different versions until the host
 * accepts the version.
 *
 * pci_version: The protocol version requested.
 * is_last_attempt: If TRUE, this is the last version guest will request.
 * reservedz: Reserved field, set to zero.
 */

struct pci_version_request {
	struct pci_message message_type;
	enum pci_message_type protocol_version;
} __packed;

/*
 * Bus D0 Entry.  This is sent from the guest to the host when the virtual
 * bus (PCI Express port) is ready for action.
 */

struct pci_bus_d0_entry {
	struct pci_message message_type;
	u32 reserved;
	u64 mmio_base;
} __packed;

struct pci_bus_relations {
	struct pci_incoming_message incoming;
	u32 device_count;
	struct pci_function_description func[1];
} __packed;

struct pci_q_res_req_response {
	struct vmpacket_descriptor hdr;
	s32 status;			/* negative values are failures */
	u32 probed_bar[6];
} __packed;

struct pci_set_power {
	struct pci_message message_type;
	union win_slot_encoding wslot;
	u32 power_state;		/* In Windows terms */
	u32 reserved;
} __packed;

struct pci_set_power_response {
	struct vmpacket_descriptor hdr;
	s32 status;			/* negative values are failures */
	union win_slot_encoding wslot;
	u32 resultant_state;		/* In Windows terms */
	u32 reserved;
} __packed;

struct pci_resources_assigned {
	struct pci_message message_type;
	union win_slot_encoding wslot;
	u8 memory_range[0x14][6];	/* not used here */
	u32 msi_descriptors;
	u32 reserved[4];
} __packed;

struct pci_create_interrupt {
	struct pci_message message_type;
	union win_slot_encoding wslot;
	struct hv_msi_desc int_desc;
} __packed;

struct pci_create_int_response {
	struct pci_response response;
	u32 reserved;
	struct tran_int_desc int_desc;
} __packed;

struct pci_delete_interrupt {
	struct pci_message message_type;
	union win_slot_encoding wslot;
	struct tran_int_desc int_desc;
} __packed;

struct pci_dev_incoming {
	struct pci_incoming_message incoming;
	union win_slot_encoding wslot;
} __packed;

struct pci_eject_response {
	u32 message_type;
	union win_slot_encoding wslot;
	u32 status;
} __packed;

static int pci_ring_size = (4 * PAGE_SIZE);

/*
 * Definitions or interrupt steering hypercall.
 */
#define HV_PARTITION_ID_SELF		((u64)-1)
#define HVCALL_RETARGET_INTERRUPT	0x7e

struct retarget_msi_interrupt {
	u64	partition_id;		/* use "self" */
	u64	device_id;
	u32	source;			/* 1 for MSI(-X) */
	u32	reserved1;
	u32	address;
	u32	data;
	u64	reserved2;
	u32	vector;
	u32	flags;
	u64	vp_mask;
} __packed;

/*
 * Driver specific state.
 */

enum hv_pcibus_state {
	hv_pcibus_init = 0,
	hv_pcibus_probed,
	hv_pcibus_installed,
	hv_pcibus_maximum
};

struct hv_pcibus_device {
	struct pci_sysdata sysdata;
	enum hv_pcibus_state state;
	atomic_t remove_lock;
	struct hv_device *hdev;
	resource_size_t low_mmio_space;
	resource_size_t high_mmio_space;
	struct resource *mem_config;
	struct resource *low_mmio_res;
	struct resource *high_mmio_res;
	struct completion *survey_event;
	struct completion remove_event;
	struct pci_bus *pci_bus;
	spinlock_t config_lock;	/* Avoid two threads writing index page */
	spinlock_t device_list_lock;	/* Protect lists below */
	void __iomem *cfg_addr;

	struct semaphore enum_sem;
	struct list_head resources_for_children;

	struct list_head children;
	struct list_head dr_list;
	struct work_struct wrk;

	struct msi_domain_info msi_info;
	struct msi_controller msi_chip;
	struct irq_domain *irq_domain;
};

/*
 * Tracks "Device Relations" messages from the host, which must be both
 * processed in order and deferred so that they don't run in the context
 * of the incoming packet callback.
 */
struct hv_dr_work {
	struct work_struct wrk;
	struct hv_pcibus_device *bus;
};

struct hv_dr_state {
	struct list_head list_entry;
	u32 device_count;
	struct pci_function_description func[1];
};

enum hv_pcichild_state {
	hv_pcichild_init = 0,
	hv_pcichild_requirements,
	hv_pcichild_resourced,
	hv_pcichild_ejecting,
	hv_pcichild_maximum
};

enum hv_pcidev_ref_reason {
	hv_pcidev_ref_invalid = 0,
	hv_pcidev_ref_initial,
	hv_pcidev_ref_by_slot,
	hv_pcidev_ref_packet,
	hv_pcidev_ref_pnp,
	hv_pcidev_ref_childlist,
	hv_pcidev_irqdata,
	hv_pcidev_ref_max
};

struct hv_pci_dev {
	/* List protected by pci_rescan_remove_lock */
	struct list_head list_entry;
	atomic_t refs;
	enum hv_pcichild_state state;
	struct pci_function_description desc;
	bool reported_missing;
	struct hv_pcibus_device *hbus;
	struct work_struct wrk;

	/*
	 * What would be observed if one wrote 0xFFFFFFFF to a BAR and then
	 * read it back, for each of the BAR offsets within config space.
	 */
	u32 probed_bar[6];
};

struct hv_pci_compl {
	struct completion host_event;
	s32 completion_status;
};

/**
 * hv_pci_generic_compl() - Invoked for a completion packet
 * @context:		Set up by the sender of the packet.
 * @resp:		The response packet
 * @resp_packet_size:	Size in bytes of the packet
 *
 * This function is used to trigger an event and report status
 * for any message for which the completion packet contains a
 * status and nothing else.
 */
static
void
hv_pci_generic_compl(void *context, struct pci_response *resp,
		     int resp_packet_size)
{
	struct hv_pci_compl *comp_pkt = context;

	if (resp_packet_size >= offsetofend(struct pci_response, status))
		comp_pkt->completion_status = resp->status;
	complete(&comp_pkt->host_event);
}

static struct hv_pci_dev *get_pcichild_wslot(struct hv_pcibus_device *hbus,
						u32 wslot);
static void get_pcichild(struct hv_pci_dev *hv_pcidev,
			 enum hv_pcidev_ref_reason reason);
static void put_pcichild(struct hv_pci_dev *hv_pcidev,
			 enum hv_pcidev_ref_reason reason);

static void get_hvpcibus(struct hv_pcibus_device *hv_pcibus);
static void put_hvpcibus(struct hv_pcibus_device *hv_pcibus);

/**
 * devfn_to_wslot() - Convert from Linux PCI slot to Windows
 * @devfn:	The Linux representation of PCI slot
 *
 * Windows uses a slightly different representation of PCI slot.
 *
 * Return: The Windows representation
 */
static u32 devfn_to_wslot(int devfn)
{
	union win_slot_encoding wslot;

	wslot.slot = 0;
	wslot.bits.func = PCI_SLOT(devfn) | (PCI_FUNC(devfn) << 5);

	return wslot.slot;
}

/**
 * wslot_to_devfn() - Convert from Windows PCI slot to Linux
 * @wslot:	The Windows representation of PCI slot
 *
 * Windows uses a slightly different representation of PCI slot.
 *
 * Return: The Linux representation
 */
static int wslot_to_devfn(u32 wslot)
{
	union win_slot_encoding slot_no;

	slot_no.slot = wslot;
	return PCI_DEVFN(0, slot_no.bits.func);
}

/*
 * PCI Configuration Space for these root PCI buses is implemented as a pair
 * of pages in memory-mapped I/O space.  Writing to the first page chooses
 * the PCI function being written or read.  Once the first page has been
 * written to, the following page maps in the entire configuration space of
 * the function.
 */

/**
 * _hv_pcifront_read_config() - Internal PCI config read
 * @hpdev:	The PCI driver's representation of the device
 * @where:	Offset within config space
 * @size:	Size of the transfer
 * @val:	Pointer to the buffer receiving the data
 */
static void _hv_pcifront_read_config(struct hv_pci_dev *hpdev, int where,
				     int size, u32 *val)
{
	unsigned long flags;
	void __iomem *addr = hpdev->hbus->cfg_addr + CFG_PAGE_OFFSET + where;

	/*
	 * If the attempt is to read the IDs or the ROM BAR, simulate that.
	 */
	if (where + size <= PCI_COMMAND) {
		memcpy(val, ((u8 *)&hpdev->desc.v_id) + where, size);
	} else if (where >= PCI_CLASS_REVISION && where + size <=
		   PCI_CACHE_LINE_SIZE) {
		memcpy(val, ((u8 *)&hpdev->desc.rev) + where -
		       PCI_CLASS_REVISION, size);
	} else if (where >= PCI_SUBSYSTEM_VENDOR_ID && where + size <=
		   PCI_ROM_ADDRESS) {
		memcpy(val, (u8 *)&hpdev->desc.subsystem_id + where -
		       PCI_SUBSYSTEM_VENDOR_ID, size);
	} else if (where >= PCI_ROM_ADDRESS && where + size <=
		   PCI_CAPABILITY_LIST) {
		/* ROM BARs are unimplemented */
		*val = 0;
	} else if (where >= PCI_INTERRUPT_LINE && where + size <=
		   PCI_INTERRUPT_PIN) {
		/*
		 * Interrupt Line and Interrupt PIN are hard-wired to zero
		 * because this front-end only supports message-signaled
		 * interrupts.
		 */
		*val = 0;
	} else if (where + size <= CFG_PAGE_SIZE) {
		spin_lock_irqsave(&hpdev->hbus->config_lock, flags);
		/* Choose the function to be read. (See comment above) */
		writel(hpdev->desc.win_slot.slot, hpdev->hbus->cfg_addr);
		/* Make sure the function was chosen before we start reading. */
		mb();
		/* Read from that function's config space. */
		switch (size) {
		case 1:
			*val = readb(addr);
			break;
		case 2:
			*val = readw(addr);
			break;
		default:
			*val = readl(addr);
			break;
		}
		/*
		 * Make sure the write was done before we release the spinlock
		 * allowing consecutive reads/writes.
		 */
		mb();
		spin_unlock_irqrestore(&hpdev->hbus->config_lock, flags);
	} else {
		dev_err(&hpdev->hbus->hdev->device,
			"Attempt to read beyond a function's config space.\n");
	}
}

/**
 * _hv_pcifront_write_config() - Internal PCI config write
 * @hpdev:	The PCI driver's representation of the device
 * @where:	Offset within config space
 * @size:	Size of the transfer
 * @val:	The data being transferred
 */
static void _hv_pcifront_write_config(struct hv_pci_dev *hpdev, int where,
				      int size, u32 val)
{
	unsigned long flags;
	void __iomem *addr = hpdev->hbus->cfg_addr + CFG_PAGE_OFFSET + where;

	if (where >= PCI_SUBSYSTEM_VENDOR_ID &&
	    where + size <= PCI_CAPABILITY_LIST) {
		/* SSIDs and ROM BARs are read-only */
	} else if (where >= PCI_COMMAND && where + size <= CFG_PAGE_SIZE) {
		spin_lock_irqsave(&hpdev->hbus->config_lock, flags);
		/* Choose the function to be written. (See comment above) */
		writel(hpdev->desc.win_slot.slot, hpdev->hbus->cfg_addr);
		/* Make sure the function was chosen before we start writing. */
		wmb();
		/* Write to that function's config space. */
		switch (size) {
		case 1:
			writeb(val, addr);
			break;
		case 2:
			writew(val, addr);
			break;
		default:
			writel(val, addr);
			break;
		}
		/*
		 * Make sure the write was done before we release the spinlock
		 * allowing consecutive reads/writes.
		 */
		mb();
		spin_unlock_irqrestore(&hpdev->hbus->config_lock, flags);
	} else {
		dev_err(&hpdev->hbus->hdev->device,
			"Attempt to write beyond a function's config space.\n");
	}
}

/**
 * hv_pcifront_read_config() - Read configuration space
 * @bus: PCI Bus structure
 * @devfn: Device/function
 * @where: Offset from base
 * @size: Byte/word/dword
 * @val: Value to be read
 *
 * Return: PCIBIOS_SUCCESSFUL on success
 *	   PCIBIOS_DEVICE_NOT_FOUND on failure
 */
static int hv_pcifront_read_config(struct pci_bus *bus, unsigned int devfn,
				   int where, int size, u32 *val)
{
	struct hv_pcibus_device *hbus =
		container_of(bus->sysdata, struct hv_pcibus_device, sysdata);
	struct hv_pci_dev *hpdev;

	hpdev = get_pcichild_wslot(hbus, devfn_to_wslot(devfn));
	if (!hpdev)
		return PCIBIOS_DEVICE_NOT_FOUND;

	_hv_pcifront_read_config(hpdev, where, size, val);

	put_pcichild(hpdev, hv_pcidev_ref_by_slot);
	return PCIBIOS_SUCCESSFUL;
}

/**
 * hv_pcifront_write_config() - Write configuration space
 * @bus: PCI Bus structure
 * @devfn: Device/function
 * @where: Offset from base
 * @size: Byte/word/dword
 * @val: Value to be written to device
 *
 * Return: PCIBIOS_SUCCESSFUL on success
 *	   PCIBIOS_DEVICE_NOT_FOUND on failure
 */
static int hv_pcifront_write_config(struct pci_bus *bus, unsigned int devfn,
				    int where, int size, u32 val)
{
	struct hv_pcibus_device *hbus =
	    container_of(bus->sysdata, struct hv_pcibus_device, sysdata);
	struct hv_pci_dev *hpdev;

	hpdev = get_pcichild_wslot(hbus, devfn_to_wslot(devfn));
	if (!hpdev)
		return PCIBIOS_DEVICE_NOT_FOUND;

	_hv_pcifront_write_config(hpdev, where, size, val);

	put_pcichild(hpdev, hv_pcidev_ref_by_slot);
	return PCIBIOS_SUCCESSFUL;
}

/* PCIe operations */
static struct pci_ops hv_pcifront_ops = {
	.read  = hv_pcifront_read_config,
	.write = hv_pcifront_write_config,
};

/* Interrupt management hooks */
static void hv_int_desc_free(struct hv_pci_dev *hpdev,
			     struct tran_int_desc *int_desc)
{
	struct pci_delete_interrupt *int_pkt;
	struct {
		struct pci_packet pkt;
		u8 buffer[sizeof(struct pci_delete_interrupt) -
			  sizeof(struct pci_message)];
	} ctxt;

	memset(&ctxt, 0, sizeof(ctxt));
	int_pkt = (struct pci_delete_interrupt *)&ctxt.pkt.message;
	int_pkt->message_type.message_type =
		PCI_DELETE_INTERRUPT_MESSAGE;
	int_pkt->wslot.slot = hpdev->desc.win_slot.slot;
	int_pkt->int_desc = *int_desc;
	vmbus_sendpacket(hpdev->hbus->hdev->channel, int_pkt, sizeof(*int_pkt),
			 (unsigned long)&ctxt.pkt, VM_PKT_DATA_INBAND, 0);
	kfree(int_desc);
}

/**
 * hv_msi_free() - Free the MSI.
 * @domain:	The interrupt domain pointer
 * @info:	Extra MSI-related context
 * @irq:	Identifies the IRQ.
 *
 * The Hyper-V parent partition and hypervisor are tracking the
 * messages that are in use, keeping the interrupt redirection
 * table up to date.  This callback sends a message that frees
 * the IRT entry and related tracking nonsense.
 */
static void hv_msi_free(struct irq_domain *domain, struct msi_domain_info *info,
			unsigned int irq)
{
	struct hv_pcibus_device *hbus;
	struct hv_pci_dev *hpdev;
	struct pci_dev *pdev;
	struct tran_int_desc *int_desc;
	struct irq_data *irq_data = irq_domain_get_irq_data(domain, irq);
	struct msi_desc *msi = irq_data_get_msi_desc(irq_data);

	pdev = msi_desc_to_pci_dev(msi);
	hbus = info->data;
	hpdev = get_pcichild_wslot(hbus, devfn_to_wslot(pdev->devfn));
	if (!hpdev)
		return;

	int_desc = irq_data_get_irq_chip_data(irq_data);
	if (int_desc) {
		irq_data->chip_data = NULL;
		hv_int_desc_free(hpdev, int_desc);
	}

	put_pcichild(hpdev, hv_pcidev_ref_by_slot);
}

static int hv_set_affinity(struct irq_data *data, const struct cpumask *dest,
			   bool force)
{
	struct irq_data *parent = data->parent_data;

	return parent->chip->irq_set_affinity(parent, dest, force);
}

void hv_irq_mask(struct irq_data *data)
{
	pci_msi_mask_irq(data);
}

/**
 * hv_irq_unmask() - "Unmask" the IRQ by setting its current
 * affinity.
 * @data:	Describes the IRQ
 *
 * Build new a destination for the MSI and make a hypercall to
 * update the Interrupt Redirection Table. "Device Logical ID"
 * is built out of this PCI bus's instance GUID and the function
 * number of the device.
 */
void hv_irq_unmask(struct irq_data *data)
{
	struct msi_desc *msi_desc = irq_data_get_msi_desc(data);
	struct irq_cfg *cfg = irqd_cfg(data);
	struct retarget_msi_interrupt params;
	struct hv_pcibus_device *hbus;
	struct cpumask *dest;
	struct pci_bus *pbus;
	struct pci_dev *pdev;
	int cpu;

	dest = irq_data_get_affinity_mask(data);
	pdev = msi_desc_to_pci_dev(msi_desc);
	pbus = pdev->bus;
	hbus = container_of(pbus->sysdata, struct hv_pcibus_device, sysdata);

	memset(&params, 0, sizeof(params));
	params.partition_id = HV_PARTITION_ID_SELF;
	params.source = 1; /* MSI(-X) */
	params.address = msi_desc->msg.address_lo;
	params.data = msi_desc->msg.data;
	params.device_id = (hbus->hdev->dev_instance.b[5] << 24) |
			   (hbus->hdev->dev_instance.b[4] << 16) |
			   (hbus->hdev->dev_instance.b[7] << 8) |
			   (hbus->hdev->dev_instance.b[6] & 0xf8) |
			   PCI_FUNC(pdev->devfn);
	params.vector = cfg->vector;

	for_each_cpu_and(cpu, dest, cpu_online_mask)
		params.vp_mask |= (1ULL << vmbus_cpu_number_to_vp_number(cpu));

	hv_do_hypercall(HVCALL_RETARGET_INTERRUPT, &params, NULL);

	pci_msi_unmask_irq(data);
}

struct compose_comp_ctxt {
	struct hv_pci_compl comp_pkt;
	struct tran_int_desc int_desc;
};

static void hv_pci_compose_compl(void *context, struct pci_response *resp,
				 int resp_packet_size)
{
	struct compose_comp_ctxt *comp_pkt = context;
	struct pci_create_int_response *int_resp =
		(struct pci_create_int_response *)resp;

	comp_pkt->comp_pkt.completion_status = resp->status;
	comp_pkt->int_desc = int_resp->int_desc;
	complete(&comp_pkt->comp_pkt.host_event);
}

/**
 * hv_compose_msi_msg() - Supplies a valid MSI address/data
 * @data:	Everything about this MSI
 * @msg:	Buffer that is filled in by this function
 *
 * This function unpacks the IRQ looking for target CPU set, IDT
 * vector and mode and sends a message to the parent partition
 * asking for a mapping for that tuple in this partition.  The
 * response supplies a data value and address to which that data
 * should be written to trigger that interrupt.
 */
static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
{
	struct irq_cfg *cfg = irqd_cfg(data);
	struct hv_pcibus_device *hbus;
	struct hv_pci_dev *hpdev;
	struct pci_bus *pbus;
	struct pci_dev *pdev;
	struct pci_create_interrupt *int_pkt;
	struct compose_comp_ctxt comp;
	struct tran_int_desc *int_desc;
	struct cpumask *affinity;
	struct {
		struct pci_packet pkt;
		u8 buffer[sizeof(struct pci_create_interrupt) -
			  sizeof(struct pci_message)];
	} ctxt;
	int cpu;
	int ret;

	pdev = msi_desc_to_pci_dev(irq_data_get_msi_desc(data));
	pbus = pdev->bus;
	hbus = container_of(pbus->sysdata, struct hv_pcibus_device, sysdata);
	hpdev = get_pcichild_wslot(hbus, devfn_to_wslot(pdev->devfn));
	if (!hpdev)
		goto return_null_message;

	/* Free any previous message that might have already been composed. */
	if (data->chip_data) {
		int_desc = data->chip_data;
		data->chip_data = NULL;
		hv_int_desc_free(hpdev, int_desc);
	}

	int_desc = kzalloc(sizeof(*int_desc), GFP_KERNEL);
	if (!int_desc)
		goto drop_reference;

	memset(&ctxt, 0, sizeof(ctxt));
	init_completion(&comp.comp_pkt.host_event);
	ctxt.pkt.completion_func = hv_pci_compose_compl;
	ctxt.pkt.compl_ctxt = &comp;
	int_pkt = (struct pci_create_interrupt *)&ctxt.pkt.message;
	int_pkt->message_type.message_type = PCI_CREATE_INTERRUPT_MESSAGE;
	int_pkt->wslot.slot = hpdev->desc.win_slot.slot;
	int_pkt->int_desc.vector = cfg->vector;
	int_pkt->int_desc.vector_count = 1;
	int_pkt->int_desc.delivery_mode =
		(apic->irq_delivery_mode == dest_LowestPrio) ? 1 : 0;

	/*
	 * This bit doesn't have to work on machines with more than 64
	 * processors because Hyper-V only supports 64 in a guest.
	 */
	affinity = irq_data_get_affinity_mask(data);
	for_each_cpu_and(cpu, affinity, cpu_online_mask) {
		int_pkt->int_desc.cpu_mask |=
			(1ULL << vmbus_cpu_number_to_vp_number(cpu));
	}

	ret = vmbus_sendpacket(hpdev->hbus->hdev->channel, int_pkt,
			       sizeof(*int_pkt), (unsigned long)&ctxt.pkt,
			       VM_PKT_DATA_INBAND,
			       VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED);
	if (!ret)
		wait_for_completion(&comp.comp_pkt.host_event);

	if (comp.comp_pkt.completion_status < 0) {
		dev_err(&hbus->hdev->device,
			"Request for interrupt failed: 0x%x",
			comp.comp_pkt.completion_status);
		goto free_int_desc;
	}

	/*
	 * Record the assignment so that this can be unwound later. Using
	 * irq_set_chip_data() here would be appropriate, but the lock it takes
	 * is already held.
	 */
	*int_desc = comp.int_desc;
	data->chip_data = int_desc;

	/* Pass up the result. */
	msg->address_hi = comp.int_desc.address >> 32;
	msg->address_lo = comp.int_desc.address & 0xffffffff;
	msg->data = comp.int_desc.data;

	put_pcichild(hpdev, hv_pcidev_ref_by_slot);
	return;

free_int_desc:
	kfree(int_desc);
drop_reference:
	put_pcichild(hpdev, hv_pcidev_ref_by_slot);
return_null_message:
	msg->address_hi = 0;
	msg->address_lo = 0;
	msg->data = 0;
}

/* HW Interrupt Chip Descriptor */
static struct irq_chip hv_msi_irq_chip = {
	.name			= "Hyper-V PCIe MSI",
	.irq_compose_msi_msg	= hv_compose_msi_msg,
	.irq_set_affinity	= hv_set_affinity,
	.irq_ack		= irq_chip_ack_parent,
	.irq_mask		= hv_irq_mask,
	.irq_unmask		= hv_irq_unmask,
};

static irq_hw_number_t hv_msi_domain_ops_get_hwirq(struct msi_domain_info *info,
						   msi_alloc_info_t *arg)
{
	return arg->msi_hwirq;
}

static struct msi_domain_ops hv_msi_ops = {
	.get_hwirq	= hv_msi_domain_ops_get_hwirq,
	.msi_prepare	= pci_msi_prepare,
	.set_desc	= pci_msi_set_desc,
	.msi_free	= hv_msi_free,
};

/**
 * hv_pcie_init_irq_domain() - Initialize IRQ domain
 * @hbus:	The root PCI bus
 *
 * This function creates an IRQ domain which will be used for
 * interrupts from devices that have been passed through.  These
 * devices only support MSI and MSI-X, not line-based interrupts
 * or simulations of line-based interrupts through PCIe's
 * fabric-layer messages.  Because interrupts are remapped, we
 * can support multi-message MSI here.
 *
 * Return: '0' on success and error value on failure
 */
static int hv_pcie_init_irq_domain(struct hv_pcibus_device *hbus)
{
	hbus->msi_info.chip = &hv_msi_irq_chip;
	hbus->msi_info.ops = &hv_msi_ops;
	hbus->msi_info.flags = (MSI_FLAG_USE_DEF_DOM_OPS |
		MSI_FLAG_USE_DEF_CHIP_OPS | MSI_FLAG_MULTI_PCI_MSI |
		MSI_FLAG_PCI_MSIX);
	hbus->msi_info.handler = handle_edge_irq;
	hbus->msi_info.handler_name = "edge";
	hbus->msi_info.data = hbus;
	hbus->irq_domain = pci_msi_create_irq_domain(hbus->sysdata.fwnode,
						     &hbus->msi_info,
						     x86_vector_domain);
	if (!hbus->irq_domain) {
		dev_err(&hbus->hdev->device,
			"Failed to build an MSI IRQ domain\n");
		return -ENODEV;
	}

	return 0;
}

/**
 * get_bar_size() - Get the address space consumed by a BAR
 * @bar_val:	Value that a BAR returned after -1 was written
 *              to it.
 *
 * This function returns the size of the BAR, rounded up to 1
 * page.  It has to be rounded up because the hypervisor's page
 * table entry that maps the BAR into the VM can't specify an
 * offset within a page.  The invariant is that the hypervisor
 * must place any BARs of smaller than page length at the
 * beginning of a page.
 *
 * Return:	Size in bytes of the consumed MMIO space.
 */
static u64 get_bar_size(u64 bar_val)
{
	return round_up((1 + ~(bar_val & PCI_BASE_ADDRESS_MEM_MASK)),
			PAGE_SIZE);
}

/**
 * survey_child_resources() - Total all MMIO requirements
 * @hbus:	Root PCI bus, as understood by this driver
 */
static void survey_child_resources(struct hv_pcibus_device *hbus)
{
	struct list_head *iter;
	struct hv_pci_dev *hpdev;
	resource_size_t bar_size = 0;
	unsigned long flags;
	struct completion *event;
	u64 bar_val;
	int i;

	/* If nobody is waiting on the answer, don't compute it. */
	event = xchg(&hbus->survey_event, NULL);
	if (!event)
		return;

	/* If the answer has already been computed, go with it. */
	if (hbus->low_mmio_space || hbus->high_mmio_space) {
		complete(event);
		return;
	}

	spin_lock_irqsave(&hbus->device_list_lock, flags);

	/*
	 * Due to an interesting quirk of the PCI spec, all memory regions
	 * for a child device are a power of 2 in size and aligned in memory,
	 * so it's sufficient to just add them up without tracking alignment.
	 */
	list_for_each(iter, &hbus->children) {
		hpdev = container_of(iter, struct hv_pci_dev, list_entry);
		for (i = 0; i < 6; i++) {
			if (hpdev->probed_bar[i] & PCI_BASE_ADDRESS_SPACE_IO)
				dev_err(&hbus->hdev->device,
					"There's an I/O BAR in this list!\n");

			if (hpdev->probed_bar[i] != 0) {
				/*
				 * A probed BAR has all the upper bits set that
				 * can be changed.
				 */

				bar_val = hpdev->probed_bar[i];
				if (bar_val & PCI_BASE_ADDRESS_MEM_TYPE_64)
					bar_val |=
					((u64)hpdev->probed_bar[++i] << 32);
				else
					bar_val |= 0xffffffff00000000ULL;

				bar_size = get_bar_size(bar_val);

				if (bar_val & PCI_BASE_ADDRESS_MEM_TYPE_64)
					hbus->high_mmio_space += bar_size;
				else
					hbus->low_mmio_space += bar_size;
			}
		}
	}

	spin_unlock_irqrestore(&hbus->device_list_lock, flags);
	complete(event);
}

/**
 * prepopulate_bars() - Fill in BARs with defaults
 * @hbus:	Root PCI bus, as understood by this driver
 *
 * The core PCI driver code seems much, much happier if the BARs
 * for a device have values upon first scan. So fill them in.
 * The algorithm below works down from large sizes to small,
 * attempting to pack the assignments optimally. The assumption,
 * enforced in other parts of the code, is that the beginning of
 * the memory-mapped I/O space will be aligned on the largest
 * BAR size.
 */
static void prepopulate_bars(struct hv_pcibus_device *hbus)
{
	resource_size_t high_size = 0;
	resource_size_t low_size = 0;
	resource_size_t high_base = 0;
	resource_size_t low_base = 0;
	resource_size_t bar_size;
	struct hv_pci_dev *hpdev;
	struct list_head *iter;
	unsigned long flags;
	u64 bar_val;
	u32 command;
	bool high;
	int i;

	if (hbus->low_mmio_space) {
		low_size = 1ULL << (63 - __builtin_clzll(hbus->low_mmio_space));
		low_base = hbus->low_mmio_res->start;
	}

	if (hbus->high_mmio_space) {
		high_size = 1ULL <<
			(63 - __builtin_clzll(hbus->high_mmio_space));
		high_base = hbus->high_mmio_res->start;
	}

	spin_lock_irqsave(&hbus->device_list_lock, flags);

	/* Pick addresses for the BARs. */
	do {
		list_for_each(iter, &hbus->children) {
			hpdev = container_of(iter, struct hv_pci_dev,
					     list_entry);
			for (i = 0; i < 6; i++) {
				bar_val = hpdev->probed_bar[i];
				if (bar_val == 0)
					continue;
				high = bar_val & PCI_BASE_ADDRESS_MEM_TYPE_64;
				if (high) {
					bar_val |=
						((u64)hpdev->probed_bar[i + 1]
						 << 32);
				} else {
					bar_val |= 0xffffffffULL << 32;
				}
				bar_size = get_bar_size(bar_val);
				if (high) {
					if (high_size != bar_size) {
						i++;
						continue;
					}
					_hv_pcifront_write_config(hpdev,
						PCI_BASE_ADDRESS_0 + (4 * i),
						4,
						(u32)(high_base & 0xffffff00));
					i++;
					_hv_pcifront_write_config(hpdev,
						PCI_BASE_ADDRESS_0 + (4 * i),
						4, (u32)(high_base >> 32));
					high_base += bar_size;
				} else {
					if (low_size != bar_size)
						continue;
					_hv_pcifront_write_config(hpdev,
						PCI_BASE_ADDRESS_0 + (4 * i),
						4,
						(u32)(low_base & 0xffffff00));
					low_base += bar_size;
				}
			}
			if (high_size <= 1 && low_size <= 1) {
				/* Set the memory enable bit. */
				_hv_pcifront_read_config(hpdev, PCI_COMMAND, 2,
							 &command);
				command |= PCI_COMMAND_MEMORY;
				_hv_pcifront_write_config(hpdev, PCI_COMMAND, 2,
							  command);
				break;
			}
		}

		high_size >>= 1;
		low_size >>= 1;
	}  while (high_size || low_size);

	spin_unlock_irqrestore(&hbus->device_list_lock, flags);
}

/**
 * create_root_hv_pci_bus() - Expose a new root PCI bus
 * @hbus:	Root PCI bus, as understood by this driver
 *
 * Return: 0 on success, -errno on failure
 */
static int create_root_hv_pci_bus(struct hv_pcibus_device *hbus)
{
	/* Register the device */
	hbus->pci_bus = pci_create_root_bus(&hbus->hdev->device,
					    0, /* bus number is always zero */
					    &hv_pcifront_ops,
					    &hbus->sysdata,
					    &hbus->resources_for_children);
	if (!hbus->pci_bus)
		return -ENODEV;

	hbus->pci_bus->msi = &hbus->msi_chip;
	hbus->pci_bus->msi->dev = &hbus->hdev->device;

	pci_scan_child_bus(hbus->pci_bus);
	pci_bus_assign_resources(hbus->pci_bus);
	pci_bus_add_devices(hbus->pci_bus);
	hbus->state = hv_pcibus_installed;
	return 0;
}

struct q_res_req_compl {
	struct completion host_event;
	struct hv_pci_dev *hpdev;
};

/**
 * q_resource_requirements() - Query Resource Requirements
 * @context:		The completion context.
 * @resp:		The response that came from the host.
 * @resp_packet_size:	The size in bytes of resp.
 *
 * This function is invoked on completion of a Query Resource
 * Requirements packet.
 */
static void q_resource_requirements(void *context, struct pci_response *resp,
				    int resp_packet_size)
{
	struct q_res_req_compl *completion = context;
	struct pci_q_res_req_response *q_res_req =
		(struct pci_q_res_req_response *)resp;
	int i;

	if (resp->status < 0) {
		dev_err(&completion->hpdev->hbus->hdev->device,
			"query resource requirements failed: %x\n",
			resp->status);
	} else {
		for (i = 0; i < 6; i++) {
			completion->hpdev->probed_bar[i] =
				q_res_req->probed_bar[i];
		}
	}

	complete(&completion->host_event);
}

static void get_pcichild(struct hv_pci_dev *hpdev,
			    enum hv_pcidev_ref_reason reason)
{
	atomic_inc(&hpdev->refs);
}

static void put_pcichild(struct hv_pci_dev *hpdev,
			    enum hv_pcidev_ref_reason reason)
{
	if (atomic_dec_and_test(&hpdev->refs))
		kfree(hpdev);
}

/**
 * new_pcichild_device() - Create a new child device
 * @hbus:	The internal struct tracking this root PCI bus.
 * @desc:	The information supplied so far from the host
 *              about the device.
 *
 * This function creates the tracking structure for a new child
 * device and kicks off the process of figuring out what it is.
 *
 * Return: Pointer to the new tracking struct
 */
static struct hv_pci_dev *new_pcichild_device(struct hv_pcibus_device *hbus,
		struct pci_function_description *desc)
{
	struct hv_pci_dev *hpdev;
	struct pci_child_message *res_req;
	struct q_res_req_compl comp_pkt;
	union {
	struct pci_packet init_packet;
		u8 buffer[0x100];
	} pkt;
	unsigned long flags;
	int ret;

	hpdev = kzalloc(sizeof(*hpdev), GFP_ATOMIC);
	if (!hpdev)
		return NULL;

	hpdev->hbus = hbus;

	memset(&pkt, 0, sizeof(pkt));
	init_completion(&comp_pkt.host_event);
	comp_pkt.hpdev = hpdev;
	pkt.init_packet.compl_ctxt = &comp_pkt;
	pkt.init_packet.completion_func = q_resource_requirements;
	res_req = (struct pci_child_message *)&pkt.init_packet.message;
	res_req->message_type = PCI_QUERY_RESOURCE_REQUIREMENTS;
	res_req->wslot.slot = desc->win_slot.slot;

	ret = vmbus_sendpacket(hbus->hdev->channel, res_req,
			       sizeof(struct pci_child_message),
			       (unsigned long)&pkt.init_packet,
			       VM_PKT_DATA_INBAND,
			       VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED);
	if (ret)
		goto error;

	wait_for_completion(&comp_pkt.host_event);

	hpdev->desc = *desc;
	get_pcichild(hpdev, hv_pcidev_ref_initial);
	get_pcichild(hpdev, hv_pcidev_ref_childlist);
	spin_lock_irqsave(&hbus->device_list_lock, flags);
	list_add_tail(&hpdev->list_entry, &hbus->children);
	spin_unlock_irqrestore(&hbus->device_list_lock, flags);
	return hpdev;

error:
	kfree(hpdev);
	return NULL;
}

/**
 * get_pcichild_wslot() - Find device from slot
 * @hbus:	Root PCI bus, as understood by this driver
 * @wslot:	Location on the bus
 *
 * This function looks up a PCI device and returns the internal
 * representation of it.  It acquires a reference on it, so that
 * the device won't be deleted while somebody is using it.  The
 * caller is responsible for calling put_pcichild() to release
 * this reference.
 *
 * Return:	Internal representation of a PCI device
 */
static struct hv_pci_dev *get_pcichild_wslot(struct hv_pcibus_device *hbus,
					     u32 wslot)
{
	unsigned long flags;
	struct hv_pci_dev *iter, *hpdev = NULL;

	spin_lock_irqsave(&hbus->device_list_lock, flags);
	list_for_each_entry(iter, &hbus->children, list_entry) {
		if (iter->desc.win_slot.slot == wslot) {
			hpdev = iter;
			get_pcichild(hpdev, hv_pcidev_ref_by_slot);
			break;
		}
	}
	spin_unlock_irqrestore(&hbus->device_list_lock, flags);

	return hpdev;
}

/**
 * pci_devices_present_work() - Handle new list of child devices
 * @work:	Work struct embedded in struct hv_dr_work
 *
 * "Bus Relations" is the Windows term for "children of this
 * bus."  The terminology is preserved here for people trying to
 * debug the interaction between Hyper-V and Linux.  This
 * function is called when the parent partition reports a list
 * of functions that should be observed under this PCI Express
 * port (bus).
 *
 * This function updates the list, and must tolerate being
 * called multiple times with the same information.  The typical
 * number of child devices is one, with very atypical cases
 * involving three or four, so the algorithms used here can be
 * simple and inefficient.
 *
 * It must also treat the omission of a previously observed device as
 * notification that the device no longer exists.
 *
 * Note that this function is a work item, and it may not be
 * invoked in the order that it was queued.  Back to back
 * updates of the list of present devices may involve queuing
 * multiple work items, and this one may run before ones that
 * were sent later. As such, this function only does something
 * if is the last one in the queue.
 */
static void pci_devices_present_work(struct work_struct *work)
{
	u32 child_no;
	bool found;
	struct list_head *iter;
	struct pci_function_description *new_desc;
	struct hv_pci_dev *hpdev;
	struct hv_pcibus_device *hbus;
	struct list_head removed;
	struct hv_dr_work *dr_wrk;
	struct hv_dr_state *dr = NULL;
	unsigned long flags;

	dr_wrk = container_of(work, struct hv_dr_work, wrk);
	hbus = dr_wrk->bus;
	kfree(dr_wrk);

	INIT_LIST_HEAD(&removed);

	if (down_interruptible(&hbus->enum_sem)) {
		put_hvpcibus(hbus);
		return;
	}

	/* Pull this off the queue and process it if it was the last one. */
	spin_lock_irqsave(&hbus->device_list_lock, flags);
	while (!list_empty(&hbus->dr_list)) {
		dr = list_first_entry(&hbus->dr_list, struct hv_dr_state,
				      list_entry);
		list_del(&dr->list_entry);

		/* Throw this away if the list still has stuff in it. */
		if (!list_empty(&hbus->dr_list)) {
			kfree(dr);
			continue;
		}
	}
	spin_unlock_irqrestore(&hbus->device_list_lock, flags);

	if (!dr) {
		up(&hbus->enum_sem);
		put_hvpcibus(hbus);
		return;
	}

	/* First, mark all existing children as reported missing. */
	spin_lock_irqsave(&hbus->device_list_lock, flags);
	list_for_each(iter, &hbus->children) {
			hpdev = container_of(iter, struct hv_pci_dev,
					     list_entry);
			hpdev->reported_missing = true;
	}
	spin_unlock_irqrestore(&hbus->device_list_lock, flags);

	/* Next, add back any reported devices. */
	for (child_no = 0; child_no < dr->device_count; child_no++) {
		found = false;
		new_desc = &dr->func[child_no];

		spin_lock_irqsave(&hbus->device_list_lock, flags);
		list_for_each(iter, &hbus->children) {
			hpdev = container_of(iter, struct hv_pci_dev,
					     list_entry);
			if ((hpdev->desc.win_slot.slot ==
			     new_desc->win_slot.slot) &&
			    (hpdev->desc.v_id == new_desc->v_id) &&
			    (hpdev->desc.d_id == new_desc->d_id) &&
			    (hpdev->desc.ser == new_desc->ser)) {
				hpdev->reported_missing = false;
				found = true;
			}
		}
		spin_unlock_irqrestore(&hbus->device_list_lock, flags);

		if (!found) {
			hpdev = new_pcichild_device(hbus, new_desc);
			if (!hpdev)
				dev_err(&hbus->hdev->device,
					"couldn't record a child device.\n");
		}
	}

	/* Move missing children to a list on the stack. */
	spin_lock_irqsave(&hbus->device_list_lock, flags);
	do {
		found = false;
		list_for_each(iter, &hbus->children) {
			hpdev = container_of(iter, struct hv_pci_dev,
					     list_entry);
			if (hpdev->reported_missing) {
				found = true;
				put_pcichild(hpdev, hv_pcidev_ref_childlist);
				list_del(&hpdev->list_entry);
				list_add_tail(&hpdev->list_entry, &removed);
				break;
			}
		}
	} while (found);
	spin_unlock_irqrestore(&hbus->device_list_lock, flags);

	/* Delete everything that should no longer exist. */
	while (!list_empty(&removed)) {
		hpdev = list_first_entry(&removed, struct hv_pci_dev,
					 list_entry);
		list_del(&hpdev->list_entry);
		put_pcichild(hpdev, hv_pcidev_ref_initial);
	}

	/* Tell the core to rescan bus because there may have been changes. */
	if (hbus->state == hv_pcibus_installed) {
		pci_lock_rescan_remove();
		pci_scan_child_bus(hbus->pci_bus);
		pci_unlock_rescan_remove();
	} else {
		survey_child_resources(hbus);
	}

	up(&hbus->enum_sem);
	put_hvpcibus(hbus);
	kfree(dr);
}

/**
 * hv_pci_devices_present() - Handles list of new children
 * @hbus:	Root PCI bus, as understood by this driver
 * @relations:	Packet from host listing children
 *
 * This function is invoked whenever a new list of devices for
 * this bus appears.
 */
static void hv_pci_devices_present(struct hv_pcibus_device *hbus,
				   struct pci_bus_relations *relations)
{
	struct hv_dr_state *dr;
	struct hv_dr_work *dr_wrk;
	unsigned long flags;

	dr_wrk = kzalloc(sizeof(*dr_wrk), GFP_NOWAIT);
	if (!dr_wrk)
		return;

	dr = kzalloc(offsetof(struct hv_dr_state, func) +
		     (sizeof(struct pci_function_description) *
		      (relations->device_count)), GFP_NOWAIT);
	if (!dr)  {
		kfree(dr_wrk);
		return;
	}

	INIT_WORK(&dr_wrk->wrk, pci_devices_present_work);
	dr_wrk->bus = hbus;
	dr->device_count = relations->device_count;
	if (dr->device_count != 0) {
		memcpy(dr->func, relations->func,
		       sizeof(struct pci_function_description) *
		       dr->device_count);
	}

	spin_lock_irqsave(&hbus->device_list_lock, flags);
	list_add_tail(&dr->list_entry, &hbus->dr_list);
	spin_unlock_irqrestore(&hbus->device_list_lock, flags);

	get_hvpcibus(hbus);
	schedule_work(&dr_wrk->wrk);
}

/**
 * hv_eject_device_work() - Asynchronously handles ejection
 * @work:	Work struct embedded in internal device struct
 *
 * This function handles ejecting a device.  Windows will
 * attempt to gracefully eject a device, waiting 60 seconds to
 * hear back from the guest OS that this completed successfully.
 * If this timer expires, the device will be forcibly removed.
 */
static void hv_eject_device_work(struct work_struct *work)
{
	struct pci_eject_response *ejct_pkt;
	struct hv_pci_dev *hpdev;
	struct pci_dev *pdev;
	unsigned long flags;
	int wslot;
	struct {
		struct pci_packet pkt;
		u8 buffer[sizeof(struct pci_eject_response) -
			  sizeof(struct pci_message)];
	} ctxt;

	hpdev = container_of(work, struct hv_pci_dev, wrk);

	if (hpdev->state != hv_pcichild_ejecting) {
		put_pcichild(hpdev, hv_pcidev_ref_pnp);
		return;
	}

	/*
	 * Ejection can come before or after the PCI bus has been set up, so
	 * attempt to find it and tear down the bus state, if it exists.  This
	 * must be done without constructs like pci_domain_nr(hbus->pci_bus)
	 * because hbus->pci_bus may not exist yet.
	 */
	wslot = wslot_to_devfn(hpdev->desc.win_slot.slot);
	pdev = pci_get_domain_bus_and_slot(hpdev->hbus->sysdata.domain, 0,
					   wslot);
	if (pdev) {
		pci_stop_and_remove_bus_device(pdev);
		pci_dev_put(pdev);
	}

	memset(&ctxt, 0, sizeof(ctxt));
	ejct_pkt = (struct pci_eject_response *)&ctxt.pkt.message;
	ejct_pkt->message_type = PCI_EJECTION_COMPLETE;
	ejct_pkt->wslot.slot = hpdev->desc.win_slot.slot;
	vmbus_sendpacket(hpdev->hbus->hdev->channel, ejct_pkt,
			 sizeof(*ejct_pkt), (unsigned long)&ctxt.pkt,
			 VM_PKT_DATA_INBAND, 0);

	spin_lock_irqsave(&hpdev->hbus->device_list_lock, flags);
	list_del(&hpdev->list_entry);
	spin_unlock_irqrestore(&hpdev->hbus->device_list_lock, flags);

	put_pcichild(hpdev, hv_pcidev_ref_childlist);
	put_pcichild(hpdev, hv_pcidev_ref_pnp);
	put_hvpcibus(hpdev->hbus);
}

/**
 * hv_pci_eject_device() - Handles device ejection
 * @hpdev:	Internal device tracking struct
 *
 * This function is invoked when an ejection packet arrives.  It
 * just schedules work so that we don't re-enter the packet
 * delivery code handling the ejection.
 */
static void hv_pci_eject_device(struct hv_pci_dev *hpdev)
{
	hpdev->state = hv_pcichild_ejecting;
	get_pcichild(hpdev, hv_pcidev_ref_pnp);
	INIT_WORK(&hpdev->wrk, hv_eject_device_work);
	get_hvpcibus(hpdev->hbus);
	schedule_work(&hpdev->wrk);
}

/**
 * hv_pci_onchannelcallback() - Handles incoming packets
 * @context:	Internal bus tracking struct
 *
 * This function is invoked whenever the host sends a packet to
 * this channel (which is private to this root PCI bus).
 */
static void hv_pci_onchannelcallback(void *context)
{
	const int packet_size = 0x100;
	int ret;
	struct hv_pcibus_device *hbus = context;
	u32 bytes_recvd;
	u64 req_id;
	struct vmpacket_descriptor *desc;
	unsigned char *buffer;
	int bufferlen = packet_size;
	struct pci_packet *comp_packet;
	struct pci_response *response;
	struct pci_incoming_message *new_message;
	struct pci_bus_relations *bus_rel;
	struct pci_dev_incoming *dev_message;
	struct hv_pci_dev *hpdev;

	buffer = kmalloc(bufferlen, GFP_ATOMIC);
	if (!buffer)
		return;

	while (1) {
		ret = vmbus_recvpacket_raw(hbus->hdev->channel, buffer,
					   bufferlen, &bytes_recvd, &req_id);

		if (ret == -ENOBUFS) {
			kfree(buffer);
			/* Handle large packet */
			bufferlen = bytes_recvd;
			buffer = kmalloc(bytes_recvd, GFP_ATOMIC);
			if (!buffer)
				return;
			continue;
		}

		/*
		 * All incoming packets must be at least as large as a
		 * response.
		 */
		if (bytes_recvd <= sizeof(struct pci_response)) {
			kfree(buffer);
			return;
		}
		desc = (struct vmpacket_descriptor *)buffer;

		switch (desc->type) {
		case VM_PKT_COMP:

			/*
			 * The host is trusted, and thus it's safe to interpret
			 * this transaction ID as a pointer.
			 */
			comp_packet = (struct pci_packet *)req_id;
			response = (struct pci_response *)buffer;
			comp_packet->completion_func(comp_packet->compl_ctxt,
						     response,
						     bytes_recvd);
			kfree(buffer);
			return;

		case VM_PKT_DATA_INBAND:

			new_message = (struct pci_incoming_message *)buffer;
			switch (new_message->message_type.message_type) {
			case PCI_BUS_RELATIONS:

				bus_rel = (struct pci_bus_relations *)buffer;
				if (bytes_recvd <
				    offsetof(struct pci_bus_relations, func) +
				    (sizeof(struct pci_function_description) *
				     (bus_rel->device_count))) {
					dev_err(&hbus->hdev->device,
						"bus relations too small\n");
					break;
				}

				hv_pci_devices_present(hbus, bus_rel);
				break;

			case PCI_EJECT:

				dev_message = (struct pci_dev_incoming *)buffer;
				hpdev = get_pcichild_wslot(hbus,
						      dev_message->wslot.slot);
				if (hpdev) {
					hv_pci_eject_device(hpdev);
					put_pcichild(hpdev,
							hv_pcidev_ref_by_slot);
				}
				break;

			default:
				dev_warn(&hbus->hdev->device,
					"Unimplemented protocol message %x\n",
					new_message->message_type.message_type);
				break;
			}
			break;

		default:
			dev_err(&hbus->hdev->device,
				"unhandled packet type %d, tid %llx len %d\n",
				desc->type, req_id, bytes_recvd);
			break;
		}
		break;
	}
}

/**
 * hv_pci_protocol_negotiation() - Set up protocol
 * @hdev:	VMBus's tracking struct for this root PCI bus
 *
 * This driver is intended to support running on Windows 10
 * (server) and later versions. It will not run on earlier
 * versions, as they assume that many of the operations which
 * Linux needs accomplished with a spinlock held were done via
 * asynchronous messaging via VMBus.  Windows 10 increases the
 * surface area of PCI emulation so that these actions can take
 * place by suspending a virtual processor for their duration.
 *
 * This function negotiates the channel protocol version,
 * failing if the host doesn't support the necessary protocol
 * level.
 */
static int hv_pci_protocol_negotiation(struct hv_device *hdev)
{
	struct pci_version_request *version_req;
	struct hv_pci_compl comp_pkt;
	struct pci_packet *pkt;
	int ret;

	/*
	 * Initiate the handshake with the host and negotiate
	 * a version that the host can support. We start with the
	 * highest version number and go down if the host cannot
	 * support it.
	 */
	pkt = kzalloc(sizeof(*pkt) + sizeof(*version_req), GFP_KERNEL);
	if (!pkt)
		return -ENOMEM;

	init_completion(&comp_pkt.host_event);
	pkt->completion_func = hv_pci_generic_compl;
	pkt->compl_ctxt = &comp_pkt;
	version_req = (struct pci_version_request *)&pkt->message;
	version_req->message_type.message_type = PCI_QUERY_PROTOCOL_VERSION;
	version_req->protocol_version = PCI_PROTOCOL_VERSION_CURRENT;

	ret = vmbus_sendpacket(hdev->channel, version_req,
			       sizeof(struct pci_version_request),
			       (unsigned long)pkt, VM_PKT_DATA_INBAND,
			       VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED);
	if (ret)
		goto exit;

	wait_for_completion(&comp_pkt.host_event);

	if (comp_pkt.completion_status < 0) {
		dev_err(&hdev->device,
			"PCI Pass-through VSP failed version request %x\n",
			comp_pkt.completion_status);
		ret = -EPROTO;
		goto exit;
	}

	ret = 0;

exit:
	kfree(pkt);
	return ret;
}

/**
 * hv_pci_free_bridge_windows() - Release memory regions for the
 * bus
 * @hbus:	Root PCI bus, as understood by this driver
 */
static void hv_pci_free_bridge_windows(struct hv_pcibus_device *hbus)
{
	/*
	 * Set the resources back to the way they looked when they
	 * were allocated by setting IORESOURCE_BUSY again.
	 */

	if (hbus->low_mmio_space && hbus->low_mmio_res) {
		hbus->low_mmio_res->flags |= IORESOURCE_BUSY;
		release_mem_region(hbus->low_mmio_res->start,
				   resource_size(hbus->low_mmio_res));
	}

	if (hbus->high_mmio_space && hbus->high_mmio_res) {
		hbus->high_mmio_res->flags |= IORESOURCE_BUSY;
		release_mem_region(hbus->high_mmio_res->start,
				   resource_size(hbus->high_mmio_res));
	}
}

/**
 * hv_pci_allocate_bridge_windows() - Allocate memory regions
 * for the bus
 * @hbus:	Root PCI bus, as understood by this driver
 *
 * This function calls vmbus_allocate_mmio(), which is itself a
 * bit of a compromise.  Ideally, we might change the pnp layer
 * in the kernel such that it comprehends either PCI devices
 * which are "grandchildren of ACPI," with some intermediate bus
 * node (in this case, VMBus) or change it such that it
 * understands VMBus.  The pnp layer, however, has been declared
 * deprecated, and not subject to change.
 *
 * The workaround, implemented here, is to ask VMBus to allocate
 * MMIO space for this bus.  VMBus itself knows which ranges are
 * appropriate by looking at its own ACPI objects.  Then, after
 * these ranges are claimed, they're modified to look like they
 * would have looked if the ACPI and pnp code had allocated
 * bridge windows.  These descriptors have to exist in this form
 * in order to satisfy the code which will get invoked when the
 * endpoint PCI function driver calls request_mem_region() or
 * request_mem_region_exclusive().
 *
 * Return: 0 on success, -errno on failure
 */
static int hv_pci_allocate_bridge_windows(struct hv_pcibus_device *hbus)
{
	resource_size_t align;
	int ret;

	if (hbus->low_mmio_space) {
		align = 1ULL << (63 - __builtin_clzll(hbus->low_mmio_space));
		ret = vmbus_allocate_mmio(&hbus->low_mmio_res, hbus->hdev, 0,
					  (u64)(u32)0xffffffff,
					  hbus->low_mmio_space,
					  align, false);
		if (ret) {
			dev_err(&hbus->hdev->device,
				"Need %#llx of low MMIO space. Consider reconfiguring the VM.\n",
				hbus->low_mmio_space);
			return ret;
		}

		/* Modify this resource to become a bridge window. */
		hbus->low_mmio_res->flags |= IORESOURCE_WINDOW;
		hbus->low_mmio_res->flags &= ~IORESOURCE_BUSY;
		pci_add_resource(&hbus->resources_for_children,
				 hbus->low_mmio_res);
	}

	if (hbus->high_mmio_space) {
		align = 1ULL << (63 - __builtin_clzll(hbus->high_mmio_space));
		ret = vmbus_allocate_mmio(&hbus->high_mmio_res, hbus->hdev,
					  0x100000000, -1,
					  hbus->high_mmio_space, align,
					  false);
		if (ret) {
			dev_err(&hbus->hdev->device,
				"Need %#llx of high MMIO space. Consider reconfiguring the VM.\n",
				hbus->high_mmio_space);
			goto release_low_mmio;
		}

		/* Modify this resource to become a bridge window. */
		hbus->high_mmio_res->flags |= IORESOURCE_WINDOW;
		hbus->high_mmio_res->flags &= ~IORESOURCE_BUSY;
		pci_add_resource(&hbus->resources_for_children,
				 hbus->high_mmio_res);
	}

	return 0;

release_low_mmio:
	if (hbus->low_mmio_res) {
		release_mem_region(hbus->low_mmio_res->start,
				   resource_size(hbus->low_mmio_res));
	}

	return ret;
}

/**
 * hv_allocate_config_window() - Find MMIO space for PCI Config
 * @hbus:	Root PCI bus, as understood by this driver
 *
 * This function claims memory-mapped I/O space for accessing
 * configuration space for the functions on this bus.
 *
 * Return: 0 on success, -errno on failure
 */
static int hv_allocate_config_window(struct hv_pcibus_device *hbus)
{
	int ret;

	/*
	 * Set up a region of MMIO space to use for accessing configuration
	 * space.
	 */
	ret = vmbus_allocate_mmio(&hbus->mem_config, hbus->hdev, 0, -1,
				  PCI_CONFIG_MMIO_LENGTH, 0x1000, false);
	if (ret)
		return ret;

	/*
	 * vmbus_allocate_mmio() gets used for allocating both device endpoint
	 * resource claims (those which cannot be overlapped) and the ranges
	 * which are valid for the children of this bus, which are intended
	 * to be overlapped by those children.  Set the flag on this claim
	 * meaning that this region can't be overlapped.
	 */

	hbus->mem_config->flags |= IORESOURCE_BUSY;

	return 0;
}

static void hv_free_config_window(struct hv_pcibus_device *hbus)
{
	release_mem_region(hbus->mem_config->start, PCI_CONFIG_MMIO_LENGTH);
}

/**
 * hv_pci_enter_d0() - Bring the "bus" into the D0 power state
 * @hdev:	VMBus's tracking struct for this root PCI bus
 *
 * Return: 0 on success, -errno on failure
 */
static int hv_pci_enter_d0(struct hv_device *hdev)
{
	struct hv_pcibus_device *hbus = hv_get_drvdata(hdev);
	struct pci_bus_d0_entry *d0_entry;
	struct hv_pci_compl comp_pkt;
	struct pci_packet *pkt;
	int ret;

	/*
	 * Tell the host that the bus is ready to use, and moved into the
	 * powered-on state.  This includes telling the host which region
	 * of memory-mapped I/O space has been chosen for configuration space
	 * access.
	 */
	pkt = kzalloc(sizeof(*pkt) + sizeof(*d0_entry), GFP_KERNEL);
	if (!pkt)
		return -ENOMEM;

	init_completion(&comp_pkt.host_event);
	pkt->completion_func = hv_pci_generic_compl;
	pkt->compl_ctxt = &comp_pkt;
	d0_entry = (struct pci_bus_d0_entry *)&pkt->message;
	d0_entry->message_type.message_type = PCI_BUS_D0ENTRY;
	d0_entry->mmio_base = hbus->mem_config->start;

	ret = vmbus_sendpacket(hdev->channel, d0_entry, sizeof(*d0_entry),
			       (unsigned long)pkt, VM_PKT_DATA_INBAND,
			       VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED);
	if (ret)
		goto exit;

	wait_for_completion(&comp_pkt.host_event);

	if (comp_pkt.completion_status < 0) {
		dev_err(&hdev->device,
			"PCI Pass-through VSP failed D0 Entry with status %x\n",
			comp_pkt.completion_status);
		ret = -EPROTO;
		goto exit;
	}

	ret = 0;

exit:
	kfree(pkt);
	return ret;
}

/**
 * hv_pci_query_relations() - Ask host to send list of child
 * devices
 * @hdev:	VMBus's tracking struct for this root PCI bus
 *
 * Return: 0 on success, -errno on failure
 */
static int hv_pci_query_relations(struct hv_device *hdev)
{
	struct hv_pcibus_device *hbus = hv_get_drvdata(hdev);
	struct pci_message message;
	struct completion comp;
	int ret;

	/* Ask the host to send along the list of child devices */
	init_completion(&comp);
	if (cmpxchg(&hbus->survey_event, NULL, &comp))
		return -ENOTEMPTY;

	memset(&message, 0, sizeof(message));
	message.message_type = PCI_QUERY_BUS_RELATIONS;

	ret = vmbus_sendpacket(hdev->channel, &message, sizeof(message),
			       0, VM_PKT_DATA_INBAND, 0);
	if (ret)
		return ret;

	wait_for_completion(&comp);
	return 0;
}

/**
 * hv_send_resources_allocated() - Report local resource choices
 * @hdev:	VMBus's tracking struct for this root PCI bus
 *
 * The host OS is expecting to be sent a request as a message
 * which contains all the resources that the device will use.
 * The response contains those same resources, "translated"
 * which is to say, the values which should be used by the
 * hardware, when it delivers an interrupt.  (MMIO resources are
 * used in local terms.)  This is nice for Windows, and lines up
 * with the FDO/PDO split, which doesn't exist in Linux.  Linux
 * is deeply expecting to scan an emulated PCI configuration
 * space.  So this message is sent here only to drive the state
 * machine on the host forward.
 *
 * Return: 0 on success, -errno on failure
 */
static int hv_send_resources_allocated(struct hv_device *hdev)
{
	struct hv_pcibus_device *hbus = hv_get_drvdata(hdev);
	struct pci_resources_assigned *res_assigned;
	struct hv_pci_compl comp_pkt;
	struct hv_pci_dev *hpdev;
	struct pci_packet *pkt;
	u32 wslot;
	int ret;

	pkt = kmalloc(sizeof(*pkt) + sizeof(*res_assigned), GFP_KERNEL);
	if (!pkt)
		return -ENOMEM;

	ret = 0;

	for (wslot = 0; wslot < 256; wslot++) {
		hpdev = get_pcichild_wslot(hbus, wslot);
		if (!hpdev)
			continue;

		memset(pkt, 0, sizeof(*pkt) + sizeof(*res_assigned));
		init_completion(&comp_pkt.host_event);
		pkt->completion_func = hv_pci_generic_compl;
		pkt->compl_ctxt = &comp_pkt;
		pkt->message.message_type = PCI_RESOURCES_ASSIGNED;
		res_assigned = (struct pci_resources_assigned *)&pkt->message;
		res_assigned->wslot.slot = hpdev->desc.win_slot.slot;

		put_pcichild(hpdev, hv_pcidev_ref_by_slot);

		ret = vmbus_sendpacket(
			hdev->channel, &pkt->message,
			sizeof(*res_assigned),
			(unsigned long)pkt,
			VM_PKT_DATA_INBAND,
			VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED);
		if (ret)
			break;

		wait_for_completion(&comp_pkt.host_event);

		if (comp_pkt.completion_status < 0) {
			ret = -EPROTO;
			dev_err(&hdev->device,
				"resource allocated returned 0x%x",
				comp_pkt.completion_status);
			break;
		}
	}

	kfree(pkt);
	return ret;
}

/**
 * hv_send_resources_released() - Report local resources
 * released
 * @hdev:	VMBus's tracking struct for this root PCI bus
 *
 * Return: 0 on success, -errno on failure
 */
static int hv_send_resources_released(struct hv_device *hdev)
{
	struct hv_pcibus_device *hbus = hv_get_drvdata(hdev);
	struct pci_child_message pkt;
	struct hv_pci_dev *hpdev;
	u32 wslot;
	int ret;

	for (wslot = 0; wslot < 256; wslot++) {
		hpdev = get_pcichild_wslot(hbus, wslot);
		if (!hpdev)
			continue;

		memset(&pkt, 0, sizeof(pkt));
		pkt.message_type = PCI_RESOURCES_RELEASED;
		pkt.wslot.slot = hpdev->desc.win_slot.slot;

		put_pcichild(hpdev, hv_pcidev_ref_by_slot);

		ret = vmbus_sendpacket(hdev->channel, &pkt, sizeof(pkt), 0,
				       VM_PKT_DATA_INBAND, 0);
		if (ret)
			return ret;
	}

	return 0;
}

static void get_hvpcibus(struct hv_pcibus_device *hbus)
{
	atomic_inc(&hbus->remove_lock);
}

static void put_hvpcibus(struct hv_pcibus_device *hbus)
{
	if (atomic_dec_and_test(&hbus->remove_lock))
		complete(&hbus->remove_event);
}

/**
 * hv_pci_probe() - New VMBus channel probe, for a root PCI bus
 * @hdev:	VMBus's tracking struct for this root PCI bus
 * @dev_id:	Identifies the device itself
 *
 * Return: 0 on success, -errno on failure
 */
static int hv_pci_probe(struct hv_device *hdev,
			const struct hv_vmbus_device_id *dev_id)
{
	struct hv_pcibus_device *hbus;
	int ret;

	hbus = kzalloc(sizeof(*hbus), GFP_KERNEL);
	if (!hbus)
		return -ENOMEM;

	/*
	 * The PCI bus "domain" is what is called "segment" in ACPI and
	 * other specs.  Pull it from the instance ID, to get something
	 * unique.  Bytes 8 and 9 are what is used in Windows guests, so
	 * do the same thing for consistency.  Note that, since this code
	 * only runs in a Hyper-V VM, Hyper-V can (and does) guarantee
	 * that (1) the only domain in use for something that looks like
	 * a physical PCI bus (which is actually emulated by the
	 * hypervisor) is domain 0 and (2) there will be no overlap
	 * between domains derived from these instance IDs in the same
	 * VM.
	 */
	hbus->sysdata.domain = hdev->dev_instance.b[9] |
			       hdev->dev_instance.b[8] << 8;

	hbus->hdev = hdev;
	atomic_inc(&hbus->remove_lock);
	INIT_LIST_HEAD(&hbus->children);
	INIT_LIST_HEAD(&hbus->dr_list);
	INIT_LIST_HEAD(&hbus->resources_for_children);
	spin_lock_init(&hbus->config_lock);
	spin_lock_init(&hbus->device_list_lock);
	sema_init(&hbus->enum_sem, 1);
	init_completion(&hbus->remove_event);

	ret = vmbus_open(hdev->channel, pci_ring_size, pci_ring_size, NULL, 0,
			 hv_pci_onchannelcallback, hbus);
	if (ret)
		goto free_bus;

	hv_set_drvdata(hdev, hbus);

	ret = hv_pci_protocol_negotiation(hdev);
	if (ret)
		goto close;

	ret = hv_allocate_config_window(hbus);
	if (ret)
		goto close;

	hbus->cfg_addr = ioremap(hbus->mem_config->start,
				 PCI_CONFIG_MMIO_LENGTH);
	if (!hbus->cfg_addr) {
		dev_err(&hdev->device,
			"Unable to map a virtual address for config space\n");
		ret = -ENOMEM;
		goto free_config;
	}

	hbus->sysdata.fwnode = irq_domain_alloc_fwnode(hbus);
	if (!hbus->sysdata.fwnode) {
		ret = -ENOMEM;
		goto unmap;
	}

	ret = hv_pcie_init_irq_domain(hbus);
	if (ret)
		goto free_fwnode;

	ret = hv_pci_query_relations(hdev);
	if (ret)
		goto free_irq_domain;

	ret = hv_pci_enter_d0(hdev);
	if (ret)
		goto free_irq_domain;

	ret = hv_pci_allocate_bridge_windows(hbus);
	if (ret)
		goto free_irq_domain;

	ret = hv_send_resources_allocated(hdev);
	if (ret)
		goto free_windows;

	prepopulate_bars(hbus);

	hbus->state = hv_pcibus_probed;

	ret = create_root_hv_pci_bus(hbus);
	if (ret)
		goto free_windows;

	return 0;

free_windows:
	hv_pci_free_bridge_windows(hbus);
free_irq_domain:
	irq_domain_remove(hbus->irq_domain);
free_fwnode:
	irq_domain_free_fwnode(hbus->sysdata.fwnode);
unmap:
	iounmap(hbus->cfg_addr);
free_config:
	hv_free_config_window(hbus);
close:
	vmbus_close(hdev->channel);
free_bus:
	kfree(hbus);
	return ret;
}

/**
 * hv_pci_remove() - Remove routine for this VMBus channel
 * @hdev:	VMBus's tracking struct for this root PCI bus
 *
 * Return: 0 on success, -errno on failure
 */
static int hv_pci_remove(struct hv_device *hdev)
{
	int ret;
	struct hv_pcibus_device *hbus;
	union {
		struct pci_packet teardown_packet;
		u8 buffer[0x100];
	} pkt;
	struct pci_bus_relations relations;
	struct hv_pci_compl comp_pkt;

	hbus = hv_get_drvdata(hdev);

	memset(&pkt.teardown_packet, 0, sizeof(pkt.teardown_packet));
	init_completion(&comp_pkt.host_event);
	pkt.teardown_packet.completion_func = hv_pci_generic_compl;
	pkt.teardown_packet.compl_ctxt = &comp_pkt;
	pkt.teardown_packet.message.message_type = PCI_BUS_D0EXIT;

	ret = vmbus_sendpacket(hdev->channel, &pkt.teardown_packet.message,
			       sizeof(struct pci_message),
			       (unsigned long)&pkt.teardown_packet,
			       VM_PKT_DATA_INBAND,
			       VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED);
	if (!ret)
		wait_for_completion_timeout(&comp_pkt.host_event, 10 * HZ);

	if (hbus->state == hv_pcibus_installed) {
		/* Remove the bus from PCI's point of view. */
		pci_lock_rescan_remove();
		pci_stop_root_bus(hbus->pci_bus);
		pci_remove_root_bus(hbus->pci_bus);
		pci_unlock_rescan_remove();
	}

	ret = hv_send_resources_released(hdev);
	if (ret)
		dev_err(&hdev->device,
			"Couldn't send resources released packet(s)\n");

	vmbus_close(hdev->channel);

	/* Delete any children which might still exist. */
	memset(&relations, 0, sizeof(relations));
	hv_pci_devices_present(hbus, &relations);

	iounmap(hbus->cfg_addr);
	hv_free_config_window(hbus);
	pci_free_resource_list(&hbus->resources_for_children);
	hv_pci_free_bridge_windows(hbus);
	irq_domain_remove(hbus->irq_domain);
	irq_domain_free_fwnode(hbus->sysdata.fwnode);
	put_hvpcibus(hbus);
	wait_for_completion(&hbus->remove_event);
	kfree(hbus);
	return 0;
}

static const struct hv_vmbus_device_id hv_pci_id_table[] = {
	/* PCI Pass-through Class ID */
	/* 44C4F61D-4444-4400-9D52-802E27EDE19F */
	{ HV_PCIE_GUID, },
	{ },
};

MODULE_DEVICE_TABLE(vmbus, hv_pci_id_table);

static struct hv_driver hv_pci_drv = {
	.name		= "hv_pci",
	.id_table	= hv_pci_id_table,
	.probe		= hv_pci_probe,
	.remove		= hv_pci_remove,
};

static void __exit exit_hv_pci_drv(void)
{
	vmbus_driver_unregister(&hv_pci_drv);
}

static int __init init_hv_pci_drv(void)
{
	return vmbus_driver_register(&hv_pci_drv);
}

module_init(init_hv_pci_drv);
module_exit(exit_hv_pci_drv);

MODULE_DESCRIPTION("Hyper-V PCI");
MODULE_LICENSE("GPL v2");