summaryrefslogtreecommitdiffstats
path: root/drivers/hv/vmbus_drv.c
blob: 5d24b25fb5aa69b3e1d27cab127a452a154a1104 (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
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Copyright (c) 2009, Microsoft Corporation.
 *
 * Authors:
 *   Haiyang Zhang <haiyangz@microsoft.com>
 *   Hank Janssen  <hjanssen@microsoft.com>
 *   K. Y. Srinivasan <kys@microsoft.com>
 */
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/init.h>
#include <linux/module.h>
#include <linux/device.h>
#include <linux/interrupt.h>
#include <linux/sysctl.h>
#include <linux/slab.h>
#include <linux/acpi.h>
#include <linux/completion.h>
#include <linux/hyperv.h>
#include <linux/kernel_stat.h>
#include <linux/clockchips.h>
#include <linux/cpu.h>
#include <linux/sched/task_stack.h>

#include <asm/mshyperv.h>
#include <linux/delay.h>
#include <linux/notifier.h>
#include <linux/ptrace.h>
#include <linux/screen_info.h>
#include <linux/kdebug.h>
#include <linux/efi.h>
#include <linux/random.h>
#include <linux/kernel.h>
#include <linux/syscore_ops.h>
#include <clocksource/hyperv_timer.h>
#include "hyperv_vmbus.h"

struct vmbus_dynid {
	struct list_head node;
	struct hv_vmbus_device_id id;
};

static struct acpi_device  *hv_acpi_dev;

static struct completion probe_event;

static int hyperv_cpuhp_online;

static void *hv_panic_page;

/*
 * Boolean to control whether to report panic messages over Hyper-V.
 *
 * It can be set via /proc/sys/kernel/hyperv/record_panic_msg
 */
static int sysctl_record_panic_msg = 1;

static int hyperv_report_reg(void)
{
	return !sysctl_record_panic_msg || !hv_panic_page;
}

static int hyperv_panic_event(struct notifier_block *nb, unsigned long val,
			      void *args)
{
	struct pt_regs *regs;

	vmbus_initiate_unload(true);

	/*
	 * Hyper-V should be notified only once about a panic.  If we will be
	 * doing hyperv_report_panic_msg() later with kmsg data, don't do
	 * the notification here.
	 */
	if (ms_hyperv.misc_features & HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE
	    && hyperv_report_reg()) {
		regs = current_pt_regs();
		hyperv_report_panic(regs, val, false);
	}
	return NOTIFY_DONE;
}

static int hyperv_die_event(struct notifier_block *nb, unsigned long val,
			    void *args)
{
	struct die_args *die = (struct die_args *)args;
	struct pt_regs *regs = die->regs;

	/*
	 * Hyper-V should be notified only once about a panic.  If we will be
	 * doing hyperv_report_panic_msg() later with kmsg data, don't do
	 * the notification here.
	 */
	if (hyperv_report_reg())
		hyperv_report_panic(regs, val, true);
	return NOTIFY_DONE;
}

static struct notifier_block hyperv_die_block = {
	.notifier_call = hyperv_die_event,
};
static struct notifier_block hyperv_panic_block = {
	.notifier_call = hyperv_panic_event,
};

static const char *fb_mmio_name = "fb_range";
static struct resource *fb_mmio;
static struct resource *hyperv_mmio;
static DEFINE_MUTEX(hyperv_mmio_lock);

static int vmbus_exists(void)
{
	if (hv_acpi_dev == NULL)
		return -ENODEV;

	return 0;
}

#define VMBUS_ALIAS_LEN ((sizeof((struct hv_vmbus_device_id *)0)->guid) * 2)
static void print_alias_name(struct hv_device *hv_dev, char *alias_name)
{
	int i;
	for (i = 0; i < VMBUS_ALIAS_LEN; i += 2)
		sprintf(&alias_name[i], "%02x", hv_dev->dev_type.b[i/2]);
}

static u8 channel_monitor_group(const struct vmbus_channel *channel)
{
	return (u8)channel->offermsg.monitorid / 32;
}

static u8 channel_monitor_offset(const struct vmbus_channel *channel)
{
	return (u8)channel->offermsg.monitorid % 32;
}

static u32 channel_pending(const struct vmbus_channel *channel,
			   const struct hv_monitor_page *monitor_page)
{
	u8 monitor_group = channel_monitor_group(channel);

	return monitor_page->trigger_group[monitor_group].pending;
}

static u32 channel_latency(const struct vmbus_channel *channel,
			   const struct hv_monitor_page *monitor_page)
{
	u8 monitor_group = channel_monitor_group(channel);
	u8 monitor_offset = channel_monitor_offset(channel);

	return monitor_page->latency[monitor_group][monitor_offset];
}

static u32 channel_conn_id(struct vmbus_channel *channel,
			   struct hv_monitor_page *monitor_page)
{
	u8 monitor_group = channel_monitor_group(channel);
	u8 monitor_offset = channel_monitor_offset(channel);
	return monitor_page->parameter[monitor_group][monitor_offset].connectionid.u.id;
}

static ssize_t id_show(struct device *dev, struct device_attribute *dev_attr,
		       char *buf)
{
	struct hv_device *hv_dev = device_to_hv_device(dev);

	if (!hv_dev->channel)
		return -ENODEV;
	return sprintf(buf, "%d\n", hv_dev->channel->offermsg.child_relid);
}
static DEVICE_ATTR_RO(id);

static ssize_t state_show(struct device *dev, struct device_attribute *dev_attr,
			  char *buf)
{
	struct hv_device *hv_dev = device_to_hv_device(dev);

	if (!hv_dev->channel)
		return -ENODEV;
	return sprintf(buf, "%d\n", hv_dev->channel->state);
}
static DEVICE_ATTR_RO(state);

static ssize_t monitor_id_show(struct device *dev,
			       struct device_attribute *dev_attr, char *buf)
{
	struct hv_device *hv_dev = device_to_hv_device(dev);

	if (!hv_dev->channel)
		return -ENODEV;
	return sprintf(buf, "%d\n", hv_dev->channel->offermsg.monitorid);
}
static DEVICE_ATTR_RO(monitor_id);

static ssize_t class_id_show(struct device *dev,
			       struct device_attribute *dev_attr, char *buf)
{
	struct hv_device *hv_dev = device_to_hv_device(dev);

	if (!hv_dev->channel)
		return -ENODEV;
	return sprintf(buf, "{%pUl}\n",
		       hv_dev->channel->offermsg.offer.if_type.b);
}
static DEVICE_ATTR_RO(class_id);

static ssize_t device_id_show(struct device *dev,
			      struct device_attribute *dev_attr, char *buf)
{
	struct hv_device *hv_dev = device_to_hv_device(dev);

	if (!hv_dev->channel)
		return -ENODEV;
	return sprintf(buf, "{%pUl}\n",
		       hv_dev->channel->offermsg.offer.if_instance.b);
}
static DEVICE_ATTR_RO(device_id);

static ssize_t modalias_show(struct device *dev,
			     struct device_attribute *dev_attr, char *buf)
{
	struct hv_device *hv_dev = device_to_hv_device(dev);
	char alias_name[VMBUS_ALIAS_LEN + 1];

	print_alias_name(hv_dev, alias_name);
	return sprintf(buf, "vmbus:%s\n", alias_name);
}
static DEVICE_ATTR_RO(modalias);

#ifdef CONFIG_NUMA
static ssize_t numa_node_show(struct device *dev,
			      struct device_attribute *attr, char *buf)
{
	struct hv_device *hv_dev = device_to_hv_device(dev);

	if (!hv_dev->channel)
		return -ENODEV;

	return sprintf(buf, "%d\n", hv_dev->channel->numa_node);
}
static DEVICE_ATTR_RO(numa_node);
#endif

static ssize_t server_monitor_pending_show(struct device *dev,
					   struct device_attribute *dev_attr,
					   char *buf)
{
	struct hv_device *hv_dev = device_to_hv_device(dev);

	if (!hv_dev->channel)
		return -ENODEV;
	return sprintf(buf, "%d\n",
		       channel_pending(hv_dev->channel,
				       vmbus_connection.monitor_pages[0]));
}
static DEVICE_ATTR_RO(server_monitor_pending);

static ssize_t client_monitor_pending_show(struct device *dev,
					   struct device_attribute *dev_attr,
					   char *buf)
{
	struct hv_device *hv_dev = device_to_hv_device(dev);

	if (!hv_dev->channel)
		return -ENODEV;
	return sprintf(buf, "%d\n",
		       channel_pending(hv_dev->channel,
				       vmbus_connection.monitor_pages[1]));
}
static DEVICE_ATTR_RO(client_monitor_pending);

static ssize_t server_monitor_latency_show(struct device *dev,
					   struct device_attribute *dev_attr,
					   char *buf)
{
	struct hv_device *hv_dev = device_to_hv_device(dev);

	if (!hv_dev->channel)
		return -ENODEV;
	return sprintf(buf, "%d\n",
		       channel_latency(hv_dev->channel,
				       vmbus_connection.monitor_pages[0]));
}
static DEVICE_ATTR_RO(server_monitor_latency);

static ssize_t client_monitor_latency_show(struct device *dev,
					   struct device_attribute *dev_attr,
					   char *buf)
{
	struct hv_device *hv_dev = device_to_hv_device(dev);

	if (!hv_dev->channel)
		return -ENODEV;
	return sprintf(buf, "%d\n",
		       channel_latency(hv_dev->channel,
				       vmbus_connection.monitor_pages[1]));
}
static DEVICE_ATTR_RO(client_monitor_latency);

static ssize_t server_monitor_conn_id_show(struct device *dev,
					   struct device_attribute *dev_attr,
					   char *buf)
{
	struct hv_device *hv_dev = device_to_hv_device(dev);

	if (!hv_dev->channel)
		return -ENODEV;
	return sprintf(buf, "%d\n",
		       channel_conn_id(hv_dev->channel,
				       vmbus_connection.monitor_pages[0]));
}
static DEVICE_ATTR_RO(server_monitor_conn_id);

static ssize_t client_monitor_conn_id_show(struct device *dev,
					   struct device_attribute *dev_attr,
					   char *buf)
{
	struct hv_device *hv_dev = device_to_hv_device(dev);

	if (!hv_dev->channel)
		return -ENODEV;
	return sprintf(buf, "%d\n",
		       channel_conn_id(hv_dev->channel,
				       vmbus_connection.monitor_pages[1]));
}
static DEVICE_ATTR_RO(client_monitor_conn_id);

static ssize_t out_intr_mask_show(struct device *dev,
				  struct device_attribute *dev_attr, char *buf)
{
	struct hv_device *hv_dev = device_to_hv_device(dev);
	struct hv_ring_buffer_debug_info outbound;
	int ret;

	if (!hv_dev->channel)
		return -ENODEV;

	ret = hv_ringbuffer_get_debuginfo(&hv_dev->channel->outbound,
					  &outbound);
	if (ret < 0)
		return ret;

	return sprintf(buf, "%d\n", outbound.current_interrupt_mask);
}
static DEVICE_ATTR_RO(out_intr_mask);

static ssize_t out_read_index_show(struct device *dev,
				   struct device_attribute *dev_attr, char *buf)
{
	struct hv_device *hv_dev = device_to_hv_device(dev);
	struct hv_ring_buffer_debug_info outbound;
	int ret;

	if (!hv_dev->channel)
		return -ENODEV;

	ret = hv_ringbuffer_get_debuginfo(&hv_dev->channel->outbound,
					  &outbound);
	if (ret < 0)
		return ret;
	return sprintf(buf, "%d\n", outbound.current_read_index);
}
static DEVICE_ATTR_RO(out_read_index);

static ssize_t out_write_index_show(struct device *dev,
				    struct device_attribute *dev_attr,
				    char *buf)
{
	struct hv_device *hv_dev = device_to_hv_device(dev);
	struct hv_ring_buffer_debug_info outbound;
	int ret;

	if (!hv_dev->channel)
		return -ENODEV;

	ret = hv_ringbuffer_get_debuginfo(&hv_dev->channel->outbound,
					  &outbound);
	if (ret < 0)
		return ret;
	return sprintf(buf, "%d\n", outbound.current_write_index);
}
static DEVICE_ATTR_RO(out_write_index);

static ssize_t out_read_bytes_avail_show(struct device *dev,
					 struct device_attribute *dev_attr,
					 char *buf)
{
	struct hv_device *hv_dev = device_to_hv_device(dev);
	struct hv_ring_buffer_debug_info outbound;
	int ret;

	if (!hv_dev->channel)
		return -ENODEV;

	ret = hv_ringbuffer_get_debuginfo(&hv_dev->channel->outbound,
					  &outbound);
	if (ret < 0)
		return ret;
	return sprintf(buf, "%d\n", outbound.bytes_avail_toread);
}
static DEVICE_ATTR_RO(out_read_bytes_avail);

static ssize_t out_write_bytes_avail_show(struct device *dev,
					  struct device_attribute *dev_attr,
					  char *buf)
{
	struct hv_device *hv_dev = device_to_hv_device(dev);
	struct hv_ring_buffer_debug_info outbound;
	int ret;

	if (!hv_dev->channel)
		return -ENODEV;

	ret = hv_ringbuffer_get_debuginfo(&hv_dev->channel->outbound,
					  &outbound);
	if (ret < 0)
		return ret;
	return sprintf(buf, "%d\n", outbound.bytes_avail_towrite);
}
static DEVICE_ATTR_RO(out_write_bytes_avail);

static ssize_t in_intr_mask_show(struct device *dev,
				 struct device_attribute *dev_attr, char *buf)
{
	struct hv_device *hv_dev = device_to_hv_device(dev);
	struct hv_ring_buffer_debug_info inbound;
	int ret;

	if (!hv_dev->channel)
		return -ENODEV;

	ret = hv_ringbuffer_get_debuginfo(&hv_dev->channel->inbound, &inbound);
	if (ret < 0)
		return ret;

	return sprintf(buf, "%d\n", inbound.current_interrupt_mask);
}
static DEVICE_ATTR_RO(in_intr_mask);

static ssize_t in_read_index_show(struct device *dev,
				  struct device_attribute *dev_attr, char *buf)
{
	struct hv_device *hv_dev = device_to_hv_device(dev);
	struct hv_ring_buffer_debug_info inbound;
	int ret;

	if (!hv_dev->channel)
		return -ENODEV;

	ret = hv_ringbuffer_get_debuginfo(&hv_dev->channel->inbound, &inbound);
	if (ret < 0)
		return ret;

	return sprintf(buf, "%d\n", inbound.current_read_index);
}
static DEVICE_ATTR_RO(in_read_index);

static ssize_t in_write_index_show(struct device *dev,
				   struct device_attribute *dev_attr, char *buf)
{
	struct hv_device *hv_dev = device_to_hv_device(dev);
	struct hv_ring_buffer_debug_info inbound;
	int ret;

	if (!hv_dev->channel)
		return -ENODEV;

	ret = hv_ringbuffer_get_debuginfo(&hv_dev->channel->inbound, &inbound);
	if (ret < 0)
		return ret;

	return sprintf(buf, "%d\n", inbound.current_write_index);
}
static DEVICE_ATTR_RO(in_write_index);

static ssize_t in_read_bytes_avail_show(struct device *dev,
					struct device_attribute *dev_attr,
					char *buf)
{
	struct hv_device *hv_dev = device_to_hv_device(dev);
	struct hv_ring_buffer_debug_info inbound;
	int ret;

	if (!hv_dev->channel)
		return -ENODEV;

	ret = hv_ringbuffer_get_debuginfo(&hv_dev->channel->inbound, &inbound);
	if (ret < 0)
		return ret;

	return sprintf(buf, "%d\n", inbound.bytes_avail_toread);
}
static DEVICE_ATTR_RO(in_read_bytes_avail);

static ssize_t in_write_bytes_avail_show(struct device *dev,
					 struct device_attribute *dev_attr,
					 char *buf)
{
	struct hv_device *hv_dev = device_to_hv_device(dev);
	struct hv_ring_buffer_debug_info inbound;
	int ret;

	if (!hv_dev->channel)
		return -ENODEV;

	ret = hv_ringbuffer_get_debuginfo(&hv_dev->channel->inbound, &inbound);
	if (ret < 0)
		return ret;

	return sprintf(buf, "%d\n", inbound.bytes_avail_towrite);
}
static DEVICE_ATTR_RO(in_write_bytes_avail);

static ssize_t channel_vp_mapping_show(struct device *dev,
				       struct device_attribute *dev_attr,
				       char *buf)
{
	struct hv_device *hv_dev = device_to_hv_device(dev);
	struct vmbus_channel *channel = hv_dev->channel, *cur_sc;
	unsigned long flags;
	int buf_size = PAGE_SIZE, n_written, tot_written;
	struct list_head *cur;

	if (!channel)
		return -ENODEV;

	tot_written = snprintf(buf, buf_size, "%u:%u\n",
		channel->offermsg.child_relid, channel->target_cpu);

	spin_lock_irqsave(&channel->lock, flags);

	list_for_each(cur, &channel->sc_list) {
		if (tot_written >= buf_size - 1)
			break;

		cur_sc = list_entry(cur, struct vmbus_channel, sc_list);
		n_written = scnprintf(buf + tot_written,
				     buf_size - tot_written,
				     "%u:%u\n",
				     cur_sc->offermsg.child_relid,
				     cur_sc->target_cpu);
		tot_written += n_written;
	}

	spin_unlock_irqrestore(&channel->lock, flags);

	return tot_written;
}
static DEVICE_ATTR_RO(channel_vp_mapping);

static ssize_t vendor_show(struct device *dev,
			   struct device_attribute *dev_attr,
			   char *buf)
{
	struct hv_device *hv_dev = device_to_hv_device(dev);
	return sprintf(buf, "0x%x\n", hv_dev->vendor_id);
}
static DEVICE_ATTR_RO(vendor);

static ssize_t device_show(struct device *dev,
			   struct device_attribute *dev_attr,
			   char *buf)
{
	struct hv_device *hv_dev = device_to_hv_device(dev);
	return sprintf(buf, "0x%x\n", hv_dev->device_id);
}
static DEVICE_ATTR_RO(device);

static ssize_t driver_override_store(struct device *dev,
				     struct device_attribute *attr,
				     const char *buf, size_t count)
{
	struct hv_device *hv_dev = device_to_hv_device(dev);
	char *driver_override, *old, *cp;

	/* We need to keep extra room for a newline */
	if (count >= (PAGE_SIZE - 1))
		return -EINVAL;

	driver_override = kstrndup(buf, count, GFP_KERNEL);
	if (!driver_override)
		return -ENOMEM;

	cp = strchr(driver_override, '\n');
	if (cp)
		*cp = '\0';

	device_lock(dev);
	old = hv_dev->driver_override;
	if (strlen(driver_override)) {
		hv_dev->driver_override = driver_override;
	} else {
		kfree(driver_override);
		hv_dev->driver_override = NULL;
	}
	device_unlock(dev);

	kfree(old);

	return count;
}

static ssize_t driver_override_show(struct device *dev,
				    struct device_attribute *attr, char *buf)
{
	struct hv_device *hv_dev = device_to_hv_device(dev);
	ssize_t len;

	device_lock(dev);
	len = snprintf(buf, PAGE_SIZE, "%s\n", hv_dev->driver_override);
	device_unlock(dev);

	return len;
}
static DEVICE_ATTR_RW(driver_override);

/* Set up per device attributes in /sys/bus/vmbus/devices/<bus device> */
static struct attribute *vmbus_dev_attrs[] = {
	&dev_attr_id.attr,
	&dev_attr_state.attr,
	&dev_attr_monitor_id.attr,
	&dev_attr_class_id.attr,
	&dev_attr_device_id.attr,
	&dev_attr_modalias.attr,
#ifdef CONFIG_NUMA
	&dev_attr_numa_node.attr,
#endif
	&dev_attr_server_monitor_pending.attr,
	&dev_attr_client_monitor_pending.attr,
	&dev_attr_server_monitor_latency.attr,
	&dev_attr_client_monitor_latency.attr,
	&dev_attr_server_monitor_conn_id.attr,
	&dev_attr_client_monitor_conn_id.attr,
	&dev_attr_out_intr_mask.attr,
	&dev_attr_out_read_index.attr,
	&dev_attr_out_write_index.attr,
	&dev_attr_out_read_bytes_avail.attr,
	&dev_attr_out_write_bytes_avail.attr,
	&dev_attr_in_intr_mask.attr,
	&dev_attr_in_read_index.attr,
	&dev_attr_in_write_index.attr,
	&dev_attr_in_read_bytes_avail.attr,
	&dev_attr_in_write_bytes_avail.attr,
	&dev_attr_channel_vp_mapping.attr,
	&dev_attr_vendor.attr,
	&dev_attr_device.attr,
	&dev_attr_driver_override.attr,
	NULL,
};

/*
 * Device-level attribute_group callback function. Returns the permission for
 * each attribute, and returns 0 if an attribute is not visible.
 */
static umode_t vmbus_dev_attr_is_visible(struct kobject *kobj,
					 struct attribute *attr, int idx)
{
	struct device *dev = kobj_to_dev(kobj);
	const struct hv_device *hv_dev = device_to_hv_device(dev);

	/* Hide the monitor attributes if the monitor mechanism is not used. */
	if (!hv_dev->channel->offermsg.monitor_allocated &&
	    (attr == &dev_attr_monitor_id.attr ||
	     attr == &dev_attr_server_monitor_pending.attr ||
	     attr == &dev_attr_client_monitor_pending.attr ||
	     attr == &dev_attr_server_monitor_latency.attr ||
	     attr == &dev_attr_client_monitor_latency.attr ||
	     attr == &dev_attr_server_monitor_conn_id.attr ||
	     attr == &dev_attr_client_monitor_conn_id.attr))
		return 0;

	return attr->mode;
}

static const struct attribute_group vmbus_dev_group = {
	.attrs = vmbus_dev_attrs,
	.is_visible = vmbus_dev_attr_is_visible
};
__ATTRIBUTE_GROUPS(vmbus_dev);

/*
 * vmbus_uevent - add uevent for our device
 *
 * This routine is invoked when a device is added or removed on the vmbus to
 * generate a uevent to udev in the userspace. The udev will then look at its
 * rule and the uevent generated here to load the appropriate driver
 *
 * The alias string will be of the form vmbus:guid where guid is the string
 * representation of the device guid (each byte of the guid will be
 * represented with two hex characters.
 */
static int vmbus_uevent(struct device *device, struct kobj_uevent_env *env)
{
	struct hv_device *dev = device_to_hv_device(device);
	int ret;
	char alias_name[VMBUS_ALIAS_LEN + 1];

	print_alias_name(dev, alias_name);
	ret = add_uevent_var(env, "MODALIAS=vmbus:%s", alias_name);
	return ret;
}

static const struct hv_vmbus_device_id *
hv_vmbus_dev_match(const struct hv_vmbus_device_id *id, const guid_t *guid)
{
	if (id == NULL)
		return NULL; /* empty device table */

	for (; !guid_is_null(&id->guid); id++)
		if (guid_equal(&id->guid, guid))
			return id;

	return NULL;
}

static const struct hv_vmbus_device_id *
hv_vmbus_dynid_match(struct hv_driver *drv, const guid_t *guid)
{
	const struct hv_vmbus_device_id *id = NULL;
	struct vmbus_dynid *dynid;

	spin_lock(&drv->dynids.lock);
	list_for_each_entry(dynid, &drv->dynids.list, node) {
		if (guid_equal(&dynid->id.guid, guid)) {
			id = &dynid->id;
			break;
		}
	}
	spin_unlock(&drv->dynids.lock);

	return id;
}

static const struct hv_vmbus_device_id vmbus_device_null;

/*
 * Return a matching hv_vmbus_device_id pointer.
 * If there is no match, return NULL.
 */
static const struct hv_vmbus_device_id *hv_vmbus_get_id(struct hv_driver *drv,
							struct hv_device *dev)
{
	const guid_t *guid = &dev->dev_type;
	const struct hv_vmbus_device_id *id;

	/* When driver_override is set, only bind to the matching driver */
	if (dev->driver_override && strcmp(dev->driver_override, drv->name))
		return NULL;

	/* Look at the dynamic ids first, before the static ones */
	id = hv_vmbus_dynid_match(drv, guid);
	if (!id)
		id = hv_vmbus_dev_match(drv->id_table, guid);

	/* driver_override will always match, send a dummy id */
	if (!id && dev->driver_override)
		id = &vmbus_device_null;

	return id;
}

/* vmbus_add_dynid - add a new device ID to this driver and re-probe devices */
static int vmbus_add_dynid(struct hv_driver *drv, guid_t *guid)
{
	struct vmbus_dynid *dynid;

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

	dynid->id.guid = *guid;

	spin_lock(&drv->dynids.lock);
	list_add_tail(&dynid->node, &drv->dynids.list);
	spin_unlock(&drv->dynids.lock);

	return driver_attach(&drv->driver);
}

static void vmbus_free_dynids(struct hv_driver *drv)
{
	struct vmbus_dynid *dynid, *n;

	spin_lock(&drv->dynids.lock);
	list_for_each_entry_safe(dynid, n, &drv->dynids.list, node) {
		list_del(&dynid->node);
		kfree(dynid);
	}
	spin_unlock(&drv->dynids.lock);
}

/*
 * store_new_id - sysfs frontend to vmbus_add_dynid()
 *
 * Allow GUIDs to be added to an existing driver via sysfs.
 */
static ssize_t new_id_store(struct device_driver *driver, const char *buf,
			    size_t count)
{
	struct hv_driver *drv = drv_to_hv_drv(driver);
	guid_t guid;
	ssize_t retval;

	retval = guid_parse(buf, &guid);
	if (retval)
		return retval;

	if (hv_vmbus_dynid_match(drv, &guid))
		return -EEXIST;

	retval = vmbus_add_dynid(drv, &guid);
	if (retval)
		return retval;
	return count;
}
static DRIVER_ATTR_WO(new_id);

/*
 * store_remove_id - remove a PCI device ID from this driver
 *
 * Removes a dynamic pci device ID to this driver.
 */
static ssize_t remove_id_store(struct device_driver *driver, const char *buf,
			       size_t count)
{
	struct hv_driver *drv = drv_to_hv_drv(driver);
	struct vmbus_dynid *dynid, *n;
	guid_t guid;
	ssize_t retval;

	retval = guid_parse(buf, &guid);
	if (retval)
		return retval;

	retval = -ENODEV;
	spin_lock(&drv->dynids.lock);
	list_for_each_entry_safe(dynid, n, &drv->dynids.list, node) {
		struct hv_vmbus_device_id *id = &dynid->id;

		if (guid_equal(&id->guid, &guid)) {
			list_del(&dynid->node);
			kfree(dynid);
			retval = count;
			break;
		}
	}
	spin_unlock(&drv->dynids.lock);

	return retval;
}
static DRIVER_ATTR_WO(remove_id);

static struct attribute *vmbus_drv_attrs[] = {
	&driver_attr_new_id.attr,
	&driver_attr_remove_id.attr,
	NULL,
};
ATTRIBUTE_GROUPS(vmbus_drv);


/*
 * vmbus_match - Attempt to match the specified device to the specified driver
 */
static int vmbus_match(struct device *device, struct device_driver *driver)
{
	struct hv_driver *drv = drv_to_hv_drv(driver);
	struct hv_device *hv_dev = device_to_hv_device(device);

	/* The hv_sock driver handles all hv_sock offers. */
	if (is_hvsock_channel(hv_dev->channel))
		return drv->hvsock;

	if (hv_vmbus_get_id(drv, hv_dev))
		return 1;

	return 0;
}

/*
 * vmbus_probe - Add the new vmbus's child device
 */
static int vmbus_probe(struct device *child_device)
{
	int ret = 0;
	struct hv_driver *drv =
			drv_to_hv_drv(child_device->driver);
	struct hv_device *dev = device_to_hv_device(child_device);
	const struct hv_vmbus_device_id *dev_id;

	dev_id = hv_vmbus_get_id(drv, dev);
	if (drv->probe) {
		ret = drv->probe(dev, dev_id);
		if (ret != 0)
			pr_err("probe failed for device %s (%d)\n",
			       dev_name(child_device), ret);

	} else {
		pr_err("probe not set for driver %s\n",
		       dev_name(child_device));
		ret = -ENODEV;
	}
	return ret;
}

/*
 * vmbus_remove - Remove a vmbus device
 */
static int vmbus_remove(struct device *child_device)
{
	struct hv_driver *drv;
	struct hv_device *dev = device_to_hv_device(child_device);

	if (child_device->driver) {
		drv = drv_to_hv_drv(child_device->driver);
		if (drv->remove)
			drv->remove(dev);
	}

	return 0;
}


/*
 * vmbus_shutdown - Shutdown a vmbus device
 */
static void vmbus_shutdown(struct device *child_device)
{
	struct hv_driver *drv;
	struct hv_device *dev = device_to_hv_device(child_device);


	/* The device may not be attached yet */
	if (!child_device->driver)
		return;

	drv = drv_to_hv_drv(child_device->driver);

	if (drv->shutdown)
		drv->shutdown(dev);
}

#ifdef CONFIG_PM_SLEEP
/*
 * vmbus_suspend - Suspend a vmbus device
 */
static int vmbus_suspend(struct device *child_device)
{
	struct hv_driver *drv;
	struct hv_device *dev = device_to_hv_device(child_device);

	/* The device may not be attached yet */
	if (!child_device->driver)
		return 0;

	drv = drv_to_hv_drv(child_device->driver);
	if (!drv->suspend)
		return -EOPNOTSUPP;

	return drv->suspend(dev);
}

/*
 * vmbus_resume - Resume a vmbus device
 */
static int vmbus_resume(struct device *child_device)
{
	struct hv_driver *drv;
	struct hv_device *dev = device_to_hv_device(child_device);

	/* The device may not be attached yet */
	if (!child_device->driver)
		return 0;

	drv = drv_to_hv_drv(child_device->driver);
	if (!drv->resume)
		return -EOPNOTSUPP;

	return drv->resume(dev);
}
#endif /* CONFIG_PM_SLEEP */

/*
 * vmbus_device_release - Final callback release of the vmbus child device
 */
static void vmbus_device_release(struct device *device)
{
	struct hv_device *hv_dev = device_to_hv_device(device);
	struct vmbus_channel *channel = hv_dev->channel;

	hv_debug_rm_dev_dir(hv_dev);

	mutex_lock(&vmbus_connection.channel_mutex);
	hv_process_channel_removal(channel);
	mutex_unlock(&vmbus_connection.channel_mutex);
	kfree(hv_dev);
}

/*
 * Note: we must use SET_NOIRQ_SYSTEM_SLEEP_PM_OPS rather than
 * SET_SYSTEM_SLEEP_PM_OPS: see the comment before vmbus_bus_pm.
 */
static const struct dev_pm_ops vmbus_pm = {
	SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(vmbus_suspend, vmbus_resume)
};

/* The one and only one */
static struct bus_type  hv_bus = {
	.name =		"vmbus",
	.match =		vmbus_match,
	.shutdown =		vmbus_shutdown,
	.remove =		vmbus_remove,
	.probe =		vmbus_probe,
	.uevent =		vmbus_uevent,
	.dev_groups =		vmbus_dev_groups,
	.drv_groups =		vmbus_drv_groups,
	.pm =			&vmbus_pm,
};

struct onmessage_work_context {
	struct work_struct work;
	struct {
		struct hv_message_header header;
		u8 payload[];
	} msg;
};

static void vmbus_onmessage_work(struct work_struct *work)
{
	struct onmessage_work_context *ctx;

	/* Do not process messages if we're in DISCONNECTED state */
	if (vmbus_connection.conn_state == DISCONNECTED)
		return;

	ctx = container_of(work, struct onmessage_work_context,
			   work);
	vmbus_onmessage((struct vmbus_channel_message_header *)
			&ctx->msg.payload);
	kfree(ctx);
}

void vmbus_on_msg_dpc(unsigned long data)
{
	struct hv_per_cpu_context *hv_cpu = (void *)data;
	void *page_addr = hv_cpu->synic_message_page;
	struct hv_message *msg = (struct hv_message *)page_addr +
				  VMBUS_MESSAGE_SINT;
	struct vmbus_channel_message_header *hdr;
	const struct vmbus_channel_message_table_entry *entry;
	struct onmessage_work_context *ctx;
	u32 message_type = msg->header.message_type;

	/*
	 * 'enum vmbus_channel_message_type' is supposed to always be 'u32' as
	 * it is being used in 'struct vmbus_channel_message_header' definition
	 * which is supposed to match hypervisor ABI.
	 */
	BUILD_BUG_ON(sizeof(enum vmbus_channel_message_type) != sizeof(u32));

	if (message_type == HVMSG_NONE)
		/* no msg */
		return;

	hdr = (struct vmbus_channel_message_header *)msg->u.payload;

	trace_vmbus_on_msg_dpc(hdr);

	if (hdr->msgtype >= CHANNELMSG_COUNT) {
		WARN_ONCE(1, "unknown msgtype=%d\n", hdr->msgtype);
		goto msg_handled;
	}

	if (msg->header.payload_size > HV_MESSAGE_PAYLOAD_BYTE_COUNT) {
		WARN_ONCE(1, "payload size is too large (%d)\n",
			  msg->header.payload_size);
		goto msg_handled;
	}

	entry = &channel_message_table[hdr->msgtype];

	if (!entry->message_handler)
		goto msg_handled;

	if (msg->header.payload_size < entry->min_payload_len) {
		WARN_ONCE(1, "message too short: msgtype=%d len=%d\n",
			  hdr->msgtype, msg->header.payload_size);
		goto msg_handled;
	}

	if (entry->handler_type	== VMHT_BLOCKING) {
		ctx = kmalloc(sizeof(*ctx) + msg->header.payload_size,
			      GFP_ATOMIC);
		if (ctx == NULL)
			return;

		INIT_WORK(&ctx->work, vmbus_onmessage_work);
		memcpy(&ctx->msg, msg, sizeof(msg->header) +
		       msg->header.payload_size);

		/*
		 * The host can generate a rescind message while we
		 * may still be handling the original offer. We deal with
		 * this condition by relying on the synchronization provided
		 * by offer_in_progress and by channel_mutex.  See also the
		 * inline comments in vmbus_onoffer_rescind().
		 */
		switch (hdr->msgtype) {
		case CHANNELMSG_RESCIND_CHANNELOFFER:
			/*
			 * If we are handling the rescind message;
			 * schedule the work on the global work queue.
			 *
			 * The OFFER message and the RESCIND message should
			 * not be handled by the same serialized work queue,
			 * because the OFFER handler may call vmbus_open(),
			 * which tries to open the channel by sending an
			 * OPEN_CHANNEL message to the host and waits for
			 * the host's response; however, if the host has
			 * rescinded the channel before it receives the
			 * OPEN_CHANNEL message, the host just silently
			 * ignores the OPEN_CHANNEL message; as a result,
			 * the guest's OFFER handler hangs for ever, if we
			 * handle the RESCIND message in the same serialized
			 * work queue: the RESCIND handler can not start to
			 * run before the OFFER handler finishes.
			 */
			schedule_work(&ctx->work);
			break;

		case CHANNELMSG_OFFERCHANNEL:
			/*
			 * The host sends the offer message of a given channel
			 * before sending the rescind message of the same
			 * channel.  These messages are sent to the guest's
			 * connect CPU; the guest then starts processing them
			 * in the tasklet handler on this CPU:
			 *
			 * VMBUS_CONNECT_CPU
			 *
			 * [vmbus_on_msg_dpc()]
			 * atomic_inc()  // CHANNELMSG_OFFERCHANNEL
			 * queue_work()
			 * ...
			 * [vmbus_on_msg_dpc()]
			 * schedule_work()  // CHANNELMSG_RESCIND_CHANNELOFFER
			 *
			 * We rely on the memory-ordering properties of the
			 * queue_work() and schedule_work() primitives, which
			 * guarantee that the atomic increment will be visible
			 * to the CPUs which will execute the offer & rescind
			 * works by the time these works will start execution.
			 */
			atomic_inc(&vmbus_connection.offer_in_progress);
			fallthrough;

		default:
			queue_work(vmbus_connection.work_queue, &ctx->work);
		}
	} else
		entry->message_handler(hdr);

msg_handled:
	vmbus_signal_eom(msg, message_type);
}

#ifdef CONFIG_PM_SLEEP
/*
 * Fake RESCIND_CHANNEL messages to clean up hv_sock channels by force for
 * hibernation, because hv_sock connections can not persist across hibernation.
 */
static void vmbus_force_channel_rescinded(struct vmbus_channel *channel)
{
	struct onmessage_work_context *ctx;
	struct vmbus_channel_rescind_offer *rescind;

	WARN_ON(!is_hvsock_channel(channel));

	/*
	 * Allocation size is small and the allocation should really not fail,
	 * otherwise the state of the hv_sock connections ends up in limbo.
	 */
	ctx = kzalloc(sizeof(*ctx) + sizeof(*rescind),
		      GFP_KERNEL | __GFP_NOFAIL);

	/*
	 * So far, these are not really used by Linux. Just set them to the
	 * reasonable values conforming to the definitions of the fields.
	 */
	ctx->msg.header.message_type = 1;
	ctx->msg.header.payload_size = sizeof(*rescind);

	/* These values are actually used by Linux. */
	rescind = (struct vmbus_channel_rescind_offer *)ctx->msg.payload;
	rescind->header.msgtype = CHANNELMSG_RESCIND_CHANNELOFFER;
	rescind->child_relid = channel->offermsg.child_relid;

	INIT_WORK(&ctx->work, vmbus_onmessage_work);

	queue_work(vmbus_connection.work_queue, &ctx->work);
}
#endif /* CONFIG_PM_SLEEP */

/*
 * Schedule all channels with events pending
 */
static void vmbus_chan_sched(struct hv_per_cpu_context *hv_cpu)
{
	unsigned long *recv_int_page;
	u32 maxbits, relid;

	if (vmbus_proto_version < VERSION_WIN8) {
		maxbits = MAX_NUM_CHANNELS_SUPPORTED;
		recv_int_page = vmbus_connection.recv_int_page;
	} else {
		/*
		 * When the host is win8 and beyond, the event page
		 * can be directly checked to get the id of the channel
		 * that has the interrupt pending.
		 */
		void *page_addr = hv_cpu->synic_event_page;
		union hv_synic_event_flags *event
			= (union hv_synic_event_flags *)page_addr +
						 VMBUS_MESSAGE_SINT;

		maxbits = HV_EVENT_FLAGS_COUNT;
		recv_int_page = event->flags;
	}

	if (unlikely(!recv_int_page))
		return;

	for_each_set_bit(relid, recv_int_page, maxbits) {
		void (*callback_fn)(void *context);
		struct vmbus_channel *channel;

		if (!sync_test_and_clear_bit(relid, recv_int_page))
			continue;

		/* Special case - vmbus channel protocol msg */
		if (relid == 0)
			continue;

		/*
		 * Pairs with the kfree_rcu() in vmbus_chan_release().
		 * Guarantees that the channel data structure doesn't
		 * get freed while the channel pointer below is being
		 * dereferenced.
		 */
		rcu_read_lock();

		/* Find channel based on relid */
		channel = relid2channel(relid);
		if (channel == NULL)
			goto sched_unlock_rcu;

		if (channel->rescind)
			goto sched_unlock_rcu;

		/*
		 * Make sure that the ring buffer data structure doesn't get
		 * freed while we dereference the ring buffer pointer.  Test
		 * for the channel's onchannel_callback being NULL within a
		 * sched_lock critical section.  See also the inline comments
		 * in vmbus_reset_channel_cb().
		 */
		spin_lock(&channel->sched_lock);

		callback_fn = channel->onchannel_callback;
		if (unlikely(callback_fn == NULL))
			goto sched_unlock;

		trace_vmbus_chan_sched(channel);

		++channel->interrupts;

		switch (channel->callback_mode) {
		case HV_CALL_ISR:
			(*callback_fn)(channel->channel_callback_context);
			break;

		case HV_CALL_BATCHED:
			hv_begin_read(&channel->inbound);
			fallthrough;
		case HV_CALL_DIRECT:
			tasklet_schedule(&channel->callback_event);
		}

sched_unlock:
		spin_unlock(&channel->sched_lock);
sched_unlock_rcu:
		rcu_read_unlock();
	}
}

static void vmbus_isr(void)
{
	struct hv_per_cpu_context *hv_cpu
		= this_cpu_ptr(hv_context.cpu_context);
	void *page_addr = hv_cpu->synic_event_page;
	struct hv_message *msg;
	union hv_synic_event_flags *event;
	bool handled = false;

	if (unlikely(page_addr == NULL))
		return;

	event = (union hv_synic_event_flags *)page_addr +
					 VMBUS_MESSAGE_SINT;
	/*
	 * Check for events before checking for messages. This is the order
	 * in which events and messages are checked in Windows guests on
	 * Hyper-V, and the Windows team suggested we do the same.
	 */

	if ((vmbus_proto_version == VERSION_WS2008) ||
		(vmbus_proto_version == VERSION_WIN7)) {

		/* Since we are a child, we only need to check bit 0 */
		if (sync_test_and_clear_bit(0, event->flags))
			handled = true;
	} else {
		/*
		 * Our host is win8 or above. The signaling mechanism
		 * has changed and we can directly look at the event page.
		 * If bit n is set then we have an interrup on the channel
		 * whose id is n.
		 */
		handled = true;
	}

	if (handled)
		vmbus_chan_sched(hv_cpu);

	page_addr = hv_cpu->synic_message_page;
	msg = (struct hv_message *)page_addr + VMBUS_MESSAGE_SINT;

	/* Check if there are actual msgs to be processed */
	if (msg->header.message_type != HVMSG_NONE) {
		if (msg->header.message_type == HVMSG_TIMER_EXPIRED) {
			hv_stimer0_isr();
			vmbus_signal_eom(msg, HVMSG_TIMER_EXPIRED);
		} else
			tasklet_schedule(&hv_cpu->msg_dpc);
	}

	add_interrupt_randomness(HYPERVISOR_CALLBACK_VECTOR, 0);
}

/*
 * Callback from kmsg_dump. Grab as much as possible from the end of the kmsg
 * buffer and call into Hyper-V to transfer the data.
 */
static void hv_kmsg_dump(struct kmsg_dumper *dumper,
			 enum kmsg_dump_reason reason)
{
	size_t bytes_written;
	phys_addr_t panic_pa;

	/* We are only interested in panics. */
	if ((reason != KMSG_DUMP_PANIC) || (!sysctl_record_panic_msg))
		return;

	panic_pa = virt_to_phys(hv_panic_page);

	/*
	 * Write dump contents to the page. No need to synchronize; panic should
	 * be single-threaded.
	 */
	kmsg_dump_get_buffer(dumper, true, hv_panic_page, HV_HYP_PAGE_SIZE,
			     &bytes_written);
	if (bytes_written)
		hyperv_report_panic_msg(panic_pa, bytes_written);
}

static struct kmsg_dumper hv_kmsg_dumper = {
	.dump = hv_kmsg_dump,
};

static struct ctl_table_header *hv_ctl_table_hdr;

/*
 * sysctl option to allow the user to control whether kmsg data should be
 * reported to Hyper-V on panic.
 */
static struct ctl_table hv_ctl_table[] = {
	{
		.procname       = "hyperv_record_panic_msg",
		.data           = &sysctl_record_panic_msg,
		.maxlen         = sizeof(int),
		.mode           = 0644,
		.proc_handler   = proc_dointvec_minmax,
		.extra1		= SYSCTL_ZERO,
		.extra2		= SYSCTL_ONE
	},
	{}
};

static struct ctl_table hv_root_table[] = {
	{
		.procname	= "kernel",
		.mode		= 0555,
		.child		= hv_ctl_table
	},
	{}
};

/*
 * vmbus_bus_init -Main vmbus driver initialization routine.
 *
 * Here, we
 *	- initialize the vmbus driver context
 *	- invoke the vmbus hv main init routine
 *	- retrieve the channel offers
 */
static int vmbus_bus_init(void)
{
	int ret;

	/* Hypervisor initialization...setup hypercall page..etc */
	ret = hv_init();
	if (ret != 0) {
		pr_err("Unable to initialize the hypervisor - 0x%x\n", ret);
		return ret;
	}

	ret = bus_register(&hv_bus);
	if (ret)
		return ret;

	hv_setup_vmbus_irq(vmbus_isr);

	ret = hv_synic_alloc();
	if (ret)
		goto err_alloc;

	/*
	 * Initialize the per-cpu interrupt state and stimer state.
	 * Then connect to the host.
	 */
	ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "hyperv/vmbus:online",
				hv_synic_init, hv_synic_cleanup);
	if (ret < 0)
		goto err_cpuhp;
	hyperv_cpuhp_online = ret;

	ret = vmbus_connect();
	if (ret)
		goto err_connect;

	/*
	 * Only register if the crash MSRs are available
	 */
	if (ms_hyperv.misc_features & HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE) {
		u64 hyperv_crash_ctl;
		/*
		 * Sysctl registration is not fatal, since by default
		 * reporting is enabled.
		 */
		hv_ctl_table_hdr = register_sysctl_table(hv_root_table);
		if (!hv_ctl_table_hdr)
			pr_err("Hyper-V: sysctl table register error");

		/*
		 * Register for panic kmsg callback only if the right
		 * capability is supported by the hypervisor.
		 */
		hv_get_crash_ctl(hyperv_crash_ctl);
		if (hyperv_crash_ctl & HV_CRASH_CTL_CRASH_NOTIFY_MSG) {
			hv_panic_page = (void *)hv_alloc_hyperv_zeroed_page();
			if (hv_panic_page) {
				ret = kmsg_dump_register(&hv_kmsg_dumper);
				if (ret) {
					pr_err("Hyper-V: kmsg dump register "
						"error 0x%x\n", ret);
					hv_free_hyperv_page(
					    (unsigned long)hv_panic_page);
					hv_panic_page = NULL;
				}
			} else
				pr_err("Hyper-V: panic message page memory "
					"allocation failed");
		}

		register_die_notifier(&hyperv_die_block);
	}

	/*
	 * Always register the panic notifier because we need to unload
	 * the VMbus channel connection to prevent any VMbus
	 * activity after the VM panics.
	 */
	atomic_notifier_chain_register(&panic_notifier_list,
			       &hyperv_panic_block);

	vmbus_request_offers();

	return 0;

err_connect:
	cpuhp_remove_state(hyperv_cpuhp_online);
err_cpuhp:
	hv_synic_free();
err_alloc:
	hv_remove_vmbus_irq();

	bus_unregister(&hv_bus);
	unregister_sysctl_table(hv_ctl_table_hdr);
	hv_ctl_table_hdr = NULL;
	return ret;
}

/**
 * __vmbus_child_driver_register() - Register a vmbus's driver
 * @hv_driver: Pointer to driver structure you want to register
 * @owner: owner module of the drv
 * @mod_name: module name string
 *
 * Registers the given driver with Linux through the 'driver_register()' call
 * and sets up the hyper-v vmbus handling for this driver.
 * It will return the state of the 'driver_register()' call.
 *
 */
int __vmbus_driver_register(struct hv_driver *hv_driver, struct module *owner, const char *mod_name)
{
	int ret;

	pr_info("registering driver %s\n", hv_driver->name);

	ret = vmbus_exists();
	if (ret < 0)
		return ret;

	hv_driver->driver.name = hv_driver->name;
	hv_driver->driver.owner = owner;
	hv_driver->driver.mod_name = mod_name;
	hv_driver->driver.bus = &hv_bus;

	spin_lock_init(&hv_driver->dynids.lock);
	INIT_LIST_HEAD(&hv_driver->dynids.list);

	ret = driver_register(&hv_driver->driver);

	return ret;
}
EXPORT_SYMBOL_GPL(__vmbus_driver_register);

/**
 * vmbus_driver_unregister() - Unregister a vmbus's driver
 * @hv_driver: Pointer to driver structure you want to
 *             un-register
 *
 * Un-register the given driver that was previous registered with a call to
 * vmbus_driver_register()
 */
void vmbus_driver_unregister(struct hv_driver *hv_driver)
{
	pr_info("unregistering driver %s\n", hv_driver->name);

	if (!vmbus_exists()) {
		driver_unregister(&hv_driver->driver);
		vmbus_free_dynids(hv_driver);
	}
}
EXPORT_SYMBOL_GPL(vmbus_driver_unregister);


/*
 * Called when last reference to channel is gone.
 */
static void vmbus_chan_release(struct kobject *kobj)
{
	struct vmbus_channel *channel
		= container_of(kobj, struct vmbus_channel, kobj);

	kfree_rcu(channel, rcu);
}

struct vmbus_chan_attribute {
	struct attribute attr;
	ssize_t (*show)(struct vmbus_channel *chan, char *buf);
	ssize_t (*store)(struct vmbus_channel *chan,
			 const char *buf, size_t count);
};
#define VMBUS_CHAN_ATTR(_name, _mode, _show, _store) \
	struct vmbus_chan_attribute chan_attr_##_name \
		= __ATTR(_name, _mode, _show, _store)
#define VMBUS_CHAN_ATTR_RW(_name) \
	struct vmbus_chan_attribute chan_attr_##_name = __ATTR_RW(_name)
#define VMBUS_CHAN_ATTR_RO(_name) \
	struct vmbus_chan_attribute chan_attr_##_name = __ATTR_RO(_name)
#define VMBUS_CHAN_ATTR_WO(_name) \
	struct vmbus_chan_attribute chan_attr_##_name = __ATTR_WO(_name)

static ssize_t vmbus_chan_attr_show(struct kobject *kobj,
				    struct attribute *attr, char *buf)
{
	const struct vmbus_chan_attribute *attribute
		= container_of(attr, struct vmbus_chan_attribute, attr);
	struct vmbus_channel *chan
		= container_of(kobj, struct vmbus_channel, kobj);

	if (!attribute->show)
		return -EIO;

	return attribute->show(chan, buf);
}

static ssize_t vmbus_chan_attr_store(struct kobject *kobj,
				     struct attribute *attr, const char *buf,
				     size_t count)
{
	const struct vmbus_chan_attribute *attribute
		= container_of(attr, struct vmbus_chan_attribute, attr);
	struct vmbus_channel *chan
		= container_of(kobj, struct vmbus_channel, kobj);

	if (!attribute->store)
		return -EIO;

	return attribute->store(chan, buf, count);
}

static const struct sysfs_ops vmbus_chan_sysfs_ops = {
	.show = vmbus_chan_attr_show,
	.store = vmbus_chan_attr_store,
};

static ssize_t out_mask_show(struct vmbus_channel *channel, char *buf)
{
	struct hv_ring_buffer_info *rbi = &channel->outbound;
	ssize_t ret;

	mutex_lock(&rbi->ring_buffer_mutex);
	if (!rbi->ring_buffer) {
		mutex_unlock(&rbi->ring_buffer_mutex);
		return -EINVAL;
	}

	ret = sprintf(buf, "%u\n", rbi->ring_buffer->interrupt_mask);
	mutex_unlock(&rbi->ring_buffer_mutex);
	return ret;
}
static VMBUS_CHAN_ATTR_RO(out_mask);

static ssize_t in_mask_show(struct vmbus_channel *channel, char *buf)
{
	struct hv_ring_buffer_info *rbi = &channel->inbound;
	ssize_t ret;

	mutex_lock(&rbi->ring_buffer_mutex);
	if (!rbi->ring_buffer) {
		mutex_unlock(&rbi->ring_buffer_mutex);
		return -EINVAL;
	}

	ret = sprintf(buf, "%u\n", rbi->ring_buffer->interrupt_mask);
	mutex_unlock(&rbi->ring_buffer_mutex);
	return ret;
}
static VMBUS_CHAN_ATTR_RO(in_mask);

static ssize_t read_avail_show(struct vmbus_channel *channel, char *buf)
{
	struct hv_ring_buffer_info *rbi = &channel->inbound;
	ssize_t ret;

	mutex_lock(&rbi->ring_buffer_mutex);
	if (!rbi->ring_buffer) {
		mutex_unlock(&rbi->ring_buffer_mutex);
		return -EINVAL;
	}

	ret = sprintf(buf, "%u\n", hv_get_bytes_to_read(rbi));
	mutex_unlock(&rbi->ring_buffer_mutex);
	return ret;
}
static VMBUS_CHAN_ATTR_RO(read_avail);

static ssize_t write_avail_show(struct vmbus_channel *channel, char *buf)
{
	struct hv_ring_buffer_info *rbi = &channel->outbound;
	ssize_t ret;

	mutex_lock(&rbi->ring_buffer_mutex);
	if (!rbi->ring_buffer) {
		mutex_unlock(&rbi->ring_buffer_mutex);
		return -EINVAL;
	}

	ret = sprintf(buf, "%u\n", hv_get_bytes_to_write(rbi));
	mutex_unlock(&rbi->ring_buffer_mutex);
	return ret;
}
static VMBUS_CHAN_ATTR_RO(write_avail);

static ssize_t target_cpu_show(struct vmbus_channel *channel, char *buf)
{
	return sprintf(buf, "%u\n", channel->target_cpu);
}
static ssize_t target_cpu_store(struct vmbus_channel *channel,
				const char *buf, size_t count)
{
	ssize_t ret = count;
	u32 target_cpu;

	if (vmbus_proto_version < VERSION_WIN10_V4_1)
		return -EIO;

	if (sscanf(buf, "%uu", &target_cpu) != 1)
		return -EIO;

	/* Validate target_cpu for the cpumask_test_cpu() operation below. */
	if (target_cpu >= nr_cpumask_bits)
		return -EINVAL;

	/* No CPUs should come up or down during this. */
	cpus_read_lock();

	if (!cpumask_test_cpu(target_cpu, cpu_online_mask)) {
		cpus_read_unlock();
		return -EINVAL;
	}

	/*
	 * Synchronizes target_cpu_store() and channel closure:
	 *
	 * { Initially: state = CHANNEL_OPENED }
	 *
	 * CPU1				CPU2
	 *
	 * [target_cpu_store()]		[vmbus_disconnect_ring()]
	 *
	 * LOCK channel_mutex		LOCK channel_mutex
	 * LOAD r1 = state		LOAD r2 = state
	 * IF (r1 == CHANNEL_OPENED)	IF (r2 == CHANNEL_OPENED)
	 *   SEND MODIFYCHANNEL		  STORE state = CHANNEL_OPEN
	 *   [...]			  SEND CLOSECHANNEL
	 * UNLOCK channel_mutex		UNLOCK channel_mutex
	 *
	 * Forbids: r1 == r2 == CHANNEL_OPENED (i.e., CPU1's LOCK precedes
	 * 		CPU2's LOCK) && CPU2's SEND precedes CPU1's SEND
	 *
	 * Note.  The host processes the channel messages "sequentially", in
	 * the order in which they are received on a per-partition basis.
	 */
	mutex_lock(&vmbus_connection.channel_mutex);

	/*
	 * Hyper-V will ignore MODIFYCHANNEL messages for "non-open" channels;
	 * avoid sending the message and fail here for such channels.
	 */
	if (channel->state != CHANNEL_OPENED_STATE) {
		ret = -EIO;
		goto cpu_store_unlock;
	}

	if (channel->target_cpu == target_cpu)
		goto cpu_store_unlock;

	if (vmbus_send_modifychannel(channel->offermsg.child_relid,
				     hv_cpu_number_to_vp_number(target_cpu))) {
		ret = -EIO;
		goto cpu_store_unlock;
	}

	/*
	 * Warning.  At this point, there is *no* guarantee that the host will
	 * have successfully processed the vmbus_send_modifychannel() request.
	 * See the header comment of vmbus_send_modifychannel() for more info.
	 *
	 * Lags in the processing of the above vmbus_send_modifychannel() can
	 * result in missed interrupts if the "old" target CPU is taken offline
	 * before Hyper-V starts sending interrupts to the "new" target CPU.
	 * But apart from this offlining scenario, the code tolerates such
	 * lags.  It will function correctly even if a channel interrupt comes
	 * in on a CPU that is different from the channel target_cpu value.
	 */

	channel->target_cpu = target_cpu;
	channel->target_vp = hv_cpu_number_to_vp_number(target_cpu);
	channel->numa_node = cpu_to_node(target_cpu);

cpu_store_unlock:
	mutex_unlock(&vmbus_connection.channel_mutex);
	cpus_read_unlock();
	return ret;
}
static VMBUS_CHAN_ATTR(cpu, 0644, target_cpu_show, target_cpu_store);

static ssize_t channel_pending_show(struct vmbus_channel *channel,
				    char *buf)
{
	return sprintf(buf, "%d\n",
		       channel_pending(channel,
				       vmbus_connection.monitor_pages[1]));
}
static VMBUS_CHAN_ATTR(pending, S_IRUGO, channel_pending_show, NULL);

static ssize_t channel_latency_show(struct vmbus_channel *channel,
				    char *buf)
{
	return sprintf(buf, "%d\n",
		       channel_latency(channel,
				       vmbus_connection.monitor_pages[1]));
}
static VMBUS_CHAN_ATTR(latency, S_IRUGO, channel_latency_show, NULL);

static ssize_t channel_interrupts_show(struct vmbus_channel *channel, char *buf)
{
	return sprintf(buf, "%llu\n", channel->interrupts);
}
static VMBUS_CHAN_ATTR(interrupts, S_IRUGO, channel_interrupts_show, NULL);

static ssize_t channel_events_show(struct vmbus_channel *channel, char *buf)
{
	return sprintf(buf, "%llu\n", channel->sig_events);
}
static VMBUS_CHAN_ATTR(events, S_IRUGO, channel_events_show, NULL);

static ssize_t channel_intr_in_full_show(struct vmbus_channel *channel,
					 char *buf)
{
	return sprintf(buf, "%llu\n",
		       (unsigned long long)channel->intr_in_full);
}
static VMBUS_CHAN_ATTR(intr_in_full, 0444, channel_intr_in_full_show, NULL);

static ssize_t channel_intr_out_empty_show(struct vmbus_channel *channel,
					   char *buf)
{
	return sprintf(buf, "%llu\n",
		       (unsigned long long)channel->intr_out_empty);
}
static VMBUS_CHAN_ATTR(intr_out_empty, 0444, channel_intr_out_empty_show, NULL);

static ssize_t channel_out_full_first_show(struct vmbus_channel *channel,
					   char *buf)
{
	return sprintf(buf, "%llu\n",
		       (unsigned long long)channel->out_full_first);
}
static VMBUS_CHAN_ATTR(out_full_first, 0444, channel_out_full_first_show, NULL);

static ssize_t channel_out_full_total_show(struct vmbus_channel *channel,
					   char *buf)
{
	return sprintf(buf, "%llu\n",
		       (unsigned long long)channel->out_full_total);
}
static VMBUS_CHAN_ATTR(out_full_total, 0444, channel_out_full_total_show, NULL);

static ssize_t subchannel_monitor_id_show(struct vmbus_channel *channel,
					  char *buf)
{
	return sprintf(buf, "%u\n", channel->offermsg.monitorid);
}
static VMBUS_CHAN_ATTR(monitor_id, S_IRUGO, subchannel_monitor_id_show, NULL);

static ssize_t subchannel_id_show(struct vmbus_channel *channel,
				  char *buf)
{
	return sprintf(buf, "%u\n",
		       channel->offermsg.offer.sub_channel_index);
}
static VMBUS_CHAN_ATTR_RO(subchannel_id);

static struct attribute *vmbus_chan_attrs[] = {
	&chan_attr_out_mask.attr,
	&chan_attr_in_mask.attr,
	&chan_attr_read_avail.attr,
	&chan_attr_write_avail.attr,
	&chan_attr_cpu.attr,
	&chan_attr_pending.attr,
	&chan_attr_latency.attr,
	&chan_attr_interrupts.attr,
	&chan_attr_events.attr,
	&chan_attr_intr_in_full.attr,
	&chan_attr_intr_out_empty.attr,
	&chan_attr_out_full_first.attr,
	&chan_attr_out_full_total.attr,
	&chan_attr_monitor_id.attr,
	&chan_attr_subchannel_id.attr,
	NULL
};

/*
 * Channel-level attribute_group callback function. Returns the permission for
 * each attribute, and returns 0 if an attribute is not visible.
 */
static umode_t vmbus_chan_attr_is_visible(struct kobject *kobj,
					  struct attribute *attr, int idx)
{
	const struct vmbus_channel *channel =
		container_of(kobj, struct vmbus_channel, kobj);

	/* Hide the monitor attributes if the monitor mechanism is not used. */
	if (!channel->offermsg.monitor_allocated &&
	    (attr == &chan_attr_pending.attr ||
	     attr == &chan_attr_latency.attr ||
	     attr == &chan_attr_monitor_id.attr))
		return 0;

	return attr->mode;
}

static struct attribute_group vmbus_chan_group = {
	.attrs = vmbus_chan_attrs,
	.is_visible = vmbus_chan_attr_is_visible
};

static struct kobj_type vmbus_chan_ktype = {
	.sysfs_ops = &vmbus_chan_sysfs_ops,
	.release = vmbus_chan_release,
};

/*
 * vmbus_add_channel_kobj - setup a sub-directory under device/channels
 */
int vmbus_add_channel_kobj(struct hv_device *dev, struct vmbus_channel *channel)
{
	const struct device *device = &dev->device;
	struct kobject *kobj = &channel->kobj;
	u32 relid = channel->offermsg.child_relid;
	int ret;

	kobj->kset = dev->channels_kset;
	ret = kobject_init_and_add(kobj, &vmbus_chan_ktype, NULL,
				   "%u", relid);
	if (ret)
		return ret;

	ret = sysfs_create_group(kobj, &vmbus_chan_group);

	if (ret) {
		/*
		 * The calling functions' error handling paths will cleanup the
		 * empty channel directory.
		 */
		dev_err(device, "Unable to set up channel sysfs files\n");
		return ret;
	}

	kobject_uevent(kobj, KOBJ_ADD);

	return 0;
}

/*
 * vmbus_remove_channel_attr_group - remove the channel's attribute group
 */
void vmbus_remove_channel_attr_group(struct vmbus_channel *channel)
{
	sysfs_remove_group(&channel->kobj, &vmbus_chan_group);
}

/*
 * vmbus_device_create - Creates and registers a new child device
 * on the vmbus.
 */
struct hv_device *vmbus_device_create(const guid_t *type,
				      const guid_t *instance,
				      struct vmbus_channel *channel)
{
	struct hv_device *child_device_obj;

	child_device_obj = kzalloc(sizeof(struct hv_device), GFP_KERNEL);
	if (!child_device_obj) {
		pr_err("Unable to allocate device object for child device\n");
		return NULL;
	}

	child_device_obj->channel = channel;
	guid_copy(&child_device_obj->dev_type, type);
	guid_copy(&child_device_obj->dev_instance, instance);
	child_device_obj->vendor_id = 0x1414; /* MSFT vendor ID */

	return child_device_obj;
}

/*
 * vmbus_device_register - Register the child device
 */
int vmbus_device_register(struct hv_device *child_device_obj)
{
	struct kobject *kobj = &child_device_obj->device.kobj;
	int ret;

	dev_set_name(&child_device_obj->device, "%pUl",
		     child_device_obj->channel->offermsg.offer.if_instance.b);

	child_device_obj->device.bus = &hv_bus;
	child_device_obj->device.parent = &hv_acpi_dev->dev;
	child_device_obj->device.release = vmbus_device_release;

	/*
	 * Register with the LDM. This will kick off the driver/device
	 * binding...which will eventually call vmbus_match() and vmbus_probe()
	 */
	ret = device_register(&child_device_obj->device);
	if (ret) {
		pr_err("Unable to register child device\n");
		return ret;
	}

	child_device_obj->channels_kset = kset_create_and_add("channels",
							      NULL, kobj);
	if (!child_device_obj->channels_kset) {
		ret = -ENOMEM;
		goto err_dev_unregister;
	}

	ret = vmbus_add_channel_kobj(child_device_obj,
				     child_device_obj->channel);
	if (ret) {
		pr_err("Unable to register primary channeln");
		goto err_kset_unregister;
	}
	hv_debug_add_dev_dir(child_device_obj);

	return 0;

err_kset_unregister:
	kset_unregister(child_device_obj->channels_kset);

err_dev_unregister:
	device_unregister(&child_device_obj->device);
	return ret;
}

/*
 * vmbus_device_unregister - Remove the specified child device
 * from the vmbus.
 */
void vmbus_device_unregister(struct hv_device *device_obj)
{
	pr_debug("child device %s unregistered\n",
		dev_name(&device_obj->device));

	kset_unregister(device_obj->channels_kset);

	/*
	 * Kick off the process of unregistering the device.
	 * This will call vmbus_remove() and eventually vmbus_device_release()
	 */
	device_unregister(&device_obj->device);
}


/*
 * VMBUS is an acpi enumerated device. Get the information we
 * need from DSDT.
 */
#define VTPM_BASE_ADDRESS 0xfed40000
static acpi_status vmbus_walk_resources(struct acpi_resource *res, void *ctx)
{
	resource_size_t start = 0;
	resource_size_t end = 0;
	struct resource *new_res;
	struct resource **old_res = &hyperv_mmio;
	struct resource **prev_res = NULL;

	switch (res->type) {

	/*
	 * "Address" descriptors are for bus windows. Ignore
	 * "memory" descriptors, which are for registers on
	 * devices.
	 */
	case ACPI_RESOURCE_TYPE_ADDRESS32:
		start = res->data.address32.address.minimum;
		end = res->data.address32.address.maximum;
		break;

	case ACPI_RESOURCE_TYPE_ADDRESS64:
		start = res->data.address64.address.minimum;
		end = res->data.address64.address.maximum;
		break;

	default:
		/* Unused resource type */
		return AE_OK;

	}
	/*
	 * Ignore ranges that are below 1MB, as they're not
	 * necessary or useful here.
	 */
	if (end < 0x100000)
		return AE_OK;

	new_res = kzalloc(sizeof(*new_res), GFP_ATOMIC);
	if (!new_res)
		return AE_NO_MEMORY;

	/* If this range overlaps the virtual TPM, truncate it. */
	if (end > VTPM_BASE_ADDRESS && start < VTPM_BASE_ADDRESS)
		end = VTPM_BASE_ADDRESS;

	new_res->name = "hyperv mmio";
	new_res->flags = IORESOURCE_MEM;
	new_res->start = start;
	new_res->end = end;

	/*
	 * If two ranges are adjacent, merge them.
	 */
	do {
		if (!*old_res) {
			*old_res = new_res;
			break;
		}

		if (((*old_res)->end + 1) == new_res->start) {
			(*old_res)->end = new_res->end;
			kfree(new_res);
			break;
		}

		if ((*old_res)->start == new_res->end + 1) {
			(*old_res)->start = new_res->start;
			kfree(new_res);
			break;
		}

		if ((*old_res)->start > new_res->end) {
			new_res->sibling = *old_res;
			if (prev_res)
				(*prev_res)->sibling = new_res;
			*old_res = new_res;
			break;
		}

		prev_res = old_res;
		old_res = &(*old_res)->sibling;

	} while (1);

	return AE_OK;
}

static int vmbus_acpi_remove(struct acpi_device *device)
{
	struct resource *cur_res;
	struct resource *next_res;

	if (hyperv_mmio) {
		if (fb_mmio) {
			__release_region(hyperv_mmio, fb_mmio->start,
					 resource_size(fb_mmio));
			fb_mmio = NULL;
		}

		for (cur_res = hyperv_mmio; cur_res; cur_res = next_res) {
			next_res = cur_res->sibling;
			kfree(cur_res);
		}
	}

	return 0;
}

static void vmbus_reserve_fb(void)
{
	int size;
	/*
	 * Make a claim for the frame buffer in the resource tree under the
	 * first node, which will be the one below 4GB.  The length seems to
	 * be underreported, particularly in a Generation 1 VM.  So start out
	 * reserving a larger area and make it smaller until it succeeds.
	 */

	if (screen_info.lfb_base) {
		if (efi_enabled(EFI_BOOT))
			size = max_t(__u32, screen_info.lfb_size, 0x800000);
		else
			size = max_t(__u32, screen_info.lfb_size, 0x4000000);

		for (; !fb_mmio && (size >= 0x100000); size >>= 1) {
			fb_mmio = __request_region(hyperv_mmio,
						   screen_info.lfb_base, size,
						   fb_mmio_name, 0);
		}
	}
}

/**
 * vmbus_allocate_mmio() - Pick a memory-mapped I/O range.
 * @new:		If successful, supplied a pointer to the
 *			allocated MMIO space.
 * @device_obj:		Identifies the caller
 * @min:		Minimum guest physical address of the
 *			allocation
 * @max:		Maximum guest physical address
 * @size:		Size of the range to be allocated
 * @align:		Alignment of the range to be allocated
 * @fb_overlap_ok:	Whether this allocation can be allowed
 *			to overlap the video frame buffer.
 *
 * This function walks the resources granted to VMBus by the
 * _CRS object in the ACPI namespace underneath the parent
 * "bridge" whether that's a root PCI bus in the Generation 1
 * case or a Module Device in the Generation 2 case.  It then
 * attempts to allocate from the global MMIO pool in a way that
 * matches the constraints supplied in these parameters and by
 * that _CRS.
 *
 * Return: 0 on success, -errno on failure
 */
int vmbus_allocate_mmio(struct resource **new, struct hv_device *device_obj,
			resource_size_t min, resource_size_t max,
			resource_size_t size, resource_size_t align,
			bool fb_overlap_ok)
{
	struct resource *iter, *shadow;
	resource_size_t range_min, range_max, start;
	const char *dev_n = dev_name(&device_obj->device);
	int retval;

	retval = -ENXIO;
	mutex_lock(&hyperv_mmio_lock);

	/*
	 * If overlaps with frame buffers are allowed, then first attempt to
	 * make the allocation from within the reserved region.  Because it
	 * is already reserved, no shadow allocation is necessary.
	 */
	if (fb_overlap_ok && fb_mmio && !(min > fb_mmio->end) &&
	    !(max < fb_mmio->start)) {

		range_min = fb_mmio->start;
		range_max = fb_mmio->end;
		start = (range_min + align - 1) & ~(align - 1);
		for (; start + size - 1 <= range_max; start += align) {
			*new = request_mem_region_exclusive(start, size, dev_n);
			if (*new) {
				retval = 0;
				goto exit;
			}
		}
	}

	for (iter = hyperv_mmio; iter; iter = iter->sibling) {
		if ((iter->start >= max) || (iter->end <= min))
			continue;

		range_min = iter->start;
		range_max = iter->end;
		start = (range_min + align - 1) & ~(align - 1);
		for (; start + size - 1 <= range_max; start += align) {
			shadow = __request_region(iter, start, size, NULL,
						  IORESOURCE_BUSY);
			if (!shadow)
				continue;

			*new = request_mem_region_exclusive(start, size, dev_n);
			if (*new) {
				shadow->name = (char *)*new;
				retval = 0;
				goto exit;
			}

			__release_region(iter, start, size);
		}
	}

exit:
	mutex_unlock(&hyperv_mmio_lock);
	return retval;
}
EXPORT_SYMBOL_GPL(vmbus_allocate_mmio);

/**
 * vmbus_free_mmio() - Free a memory-mapped I/O range.
 * @start:		Base address of region to release.
 * @size:		Size of the range to be allocated
 *
 * This function releases anything requested by
 * vmbus_mmio_allocate().
 */
void vmbus_free_mmio(resource_size_t start, resource_size_t size)
{
	struct resource *iter;

	mutex_lock(&hyperv_mmio_lock);
	for (iter = hyperv_mmio; iter; iter = iter->sibling) {
		if ((iter->start >= start + size) || (iter->end <= start))
			continue;

		__release_region(iter, start, size);
	}
	release_mem_region(start, size);
	mutex_unlock(&hyperv_mmio_lock);

}
EXPORT_SYMBOL_GPL(vmbus_free_mmio);

static int vmbus_acpi_add(struct acpi_device *device)
{
	acpi_status result;
	int ret_val = -ENODEV;
	struct acpi_device *ancestor;

	hv_acpi_dev = device;

	result = acpi_walk_resources(device->handle, METHOD_NAME__CRS,
					vmbus_walk_resources, NULL);

	if (ACPI_FAILURE(result))
		goto acpi_walk_err;
	/*
	 * Some ancestor of the vmbus acpi device (Gen1 or Gen2
	 * firmware) is the VMOD that has the mmio ranges. Get that.
	 */
	for (ancestor = device->parent; ancestor; ancestor = ancestor->parent) {
		result = acpi_walk_resources(ancestor->handle, METHOD_NAME__CRS,
					     vmbus_walk_resources, NULL);

		if (ACPI_FAILURE(result))
			continue;
		if (hyperv_mmio) {
			vmbus_reserve_fb();
			break;
		}
	}
	ret_val = 0;

acpi_walk_err:
	complete(&probe_event);
	if (ret_val)
		vmbus_acpi_remove(device);
	return ret_val;
}

#ifdef CONFIG_PM_SLEEP
static int vmbus_bus_suspend(struct device *dev)
{
	struct vmbus_channel *channel, *sc;
	unsigned long flags;

	while (atomic_read(&vmbus_connection.offer_in_progress) != 0) {
		/*
		 * We wait here until the completion of any channel
		 * offers that are currently in progress.
		 */
		msleep(1);
	}

	mutex_lock(&vmbus_connection.channel_mutex);
	list_for_each_entry(channel, &vmbus_connection.chn_list, listentry) {
		if (!is_hvsock_channel(channel))
			continue;

		vmbus_force_channel_rescinded(channel);
	}
	mutex_unlock(&vmbus_connection.channel_mutex);

	/*
	 * Wait until all the sub-channels and hv_sock channels have been
	 * cleaned up. Sub-channels should be destroyed upon suspend, otherwise
	 * they would conflict with the new sub-channels that will be created
	 * in the resume path. hv_sock channels should also be destroyed, but
	 * a hv_sock channel of an established hv_sock connection can not be
	 * really destroyed since it may still be referenced by the userspace
	 * application, so we just force the hv_sock channel to be rescinded
	 * by vmbus_force_channel_rescinded(), and the userspace application
	 * will thoroughly destroy the channel after hibernation.
	 *
	 * Note: the counter nr_chan_close_on_suspend may never go above 0 if
	 * the VM has no sub-channel and hv_sock channel, e.g. a 1-vCPU VM.
	 */
	if (atomic_read(&vmbus_connection.nr_chan_close_on_suspend) > 0)
		wait_for_completion(&vmbus_connection.ready_for_suspend_event);

	WARN_ON(atomic_read(&vmbus_connection.nr_chan_fixup_on_resume) != 0);

	mutex_lock(&vmbus_connection.channel_mutex);

	list_for_each_entry(channel, &vmbus_connection.chn_list, listentry) {
		/*
		 * Remove the channel from the array of channels and invalidate
		 * the channel's relid.  Upon resume, vmbus_onoffer() will fix
		 * up the relid (and other fields, if necessary) and add the
		 * channel back to the array.
		 */
		vmbus_channel_unmap_relid(channel);
		channel->offermsg.child_relid = INVALID_RELID;

		if (is_hvsock_channel(channel)) {
			if (!channel->rescind) {
				pr_err("hv_sock channel not rescinded!\n");
				WARN_ON_ONCE(1);
			}
			continue;
		}

		spin_lock_irqsave(&channel->lock, flags);
		list_for_each_entry(sc, &channel->sc_list, sc_list) {
			pr_err("Sub-channel not deleted!\n");
			WARN_ON_ONCE(1);
		}
		spin_unlock_irqrestore(&channel->lock, flags);

		atomic_inc(&vmbus_connection.nr_chan_fixup_on_resume);
	}

	mutex_unlock(&vmbus_connection.channel_mutex);

	vmbus_initiate_unload(false);

	/* Reset the event for the next resume. */
	reinit_completion(&vmbus_connection.ready_for_resume_event);

	return 0;
}

static int vmbus_bus_resume(struct device *dev)
{
	struct vmbus_channel_msginfo *msginfo;
	size_t msgsize;
	int ret;

	/*
	 * We only use the 'vmbus_proto_version', which was in use before
	 * hibernation, to re-negotiate with the host.
	 */
	if (!vmbus_proto_version) {
		pr_err("Invalid proto version = 0x%x\n", vmbus_proto_version);
		return -EINVAL;
	}

	msgsize = sizeof(*msginfo) +
		  sizeof(struct vmbus_channel_initiate_contact);

	msginfo = kzalloc(msgsize, GFP_KERNEL);

	if (msginfo == NULL)
		return -ENOMEM;

	ret = vmbus_negotiate_version(msginfo, vmbus_proto_version);

	kfree(msginfo);

	if (ret != 0)
		return ret;

	WARN_ON(atomic_read(&vmbus_connection.nr_chan_fixup_on_resume) == 0);

	vmbus_request_offers();

	wait_for_completion(&vmbus_connection.ready_for_resume_event);

	/* Reset the event for the next suspend. */
	reinit_completion(&vmbus_connection.ready_for_suspend_event);

	return 0;
}
#endif /* CONFIG_PM_SLEEP */

static const struct acpi_device_id vmbus_acpi_device_ids[] = {
	{"VMBUS", 0},
	{"VMBus", 0},
	{"", 0},
};
MODULE_DEVICE_TABLE(acpi, vmbus_acpi_device_ids);

/*
 * Note: we must use SET_NOIRQ_SYSTEM_SLEEP_PM_OPS rather than
 * SET_SYSTEM_SLEEP_PM_OPS, otherwise NIC SR-IOV can not work, because the
 * "pci_dev_pm_ops" uses the "noirq" callbacks: in the resume path, the
 * pci "noirq" restore callback runs before "non-noirq" callbacks (see
 * resume_target_kernel() -> dpm_resume_start(), and hibernation_restore() ->
 * dpm_resume_end()). This means vmbus_bus_resume() and the pci-hyperv's
 * resume callback must also run via the "noirq" callbacks.
 */
static const struct dev_pm_ops vmbus_bus_pm = {
	SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(vmbus_bus_suspend, vmbus_bus_resume)
};

static struct acpi_driver vmbus_acpi_driver = {
	.name = "vmbus",
	.ids = vmbus_acpi_device_ids,
	.ops = {
		.add = vmbus_acpi_add,
		.remove = vmbus_acpi_remove,
	},
	.drv.pm = &vmbus_bus_pm,
};

static void hv_kexec_handler(void)
{
	hv_stimer_global_cleanup();
	vmbus_initiate_unload(false);
	/* Make sure conn_state is set as hv_synic_cleanup checks for it */
	mb();
	cpuhp_remove_state(hyperv_cpuhp_online);
	hyperv_cleanup();
};

static void hv_crash_handler(struct pt_regs *regs)
{
	int cpu;

	vmbus_initiate_unload(true);
	/*
	 * In crash handler we can't schedule synic cleanup for all CPUs,
	 * doing the cleanup for current CPU only. This should be sufficient
	 * for kdump.
	 */
	cpu = smp_processor_id();
	hv_stimer_cleanup(cpu);
	hv_synic_disable_regs(cpu);
	hyperv_cleanup();
};

static int hv_synic_suspend(void)
{
	/*
	 * When we reach here, all the non-boot CPUs have been offlined.
	 * If we're in a legacy configuration where stimer Direct Mode is
	 * not enabled, the stimers on the non-boot CPUs have been unbound
	 * in hv_synic_cleanup() -> hv_stimer_legacy_cleanup() ->
	 * hv_stimer_cleanup() -> clockevents_unbind_device().
	 *
	 * hv_synic_suspend() only runs on CPU0 with interrupts disabled.
	 * Here we do not call hv_stimer_legacy_cleanup() on CPU0 because:
	 * 1) it's unnecessary as interrupts remain disabled between
	 * syscore_suspend() and syscore_resume(): see create_image() and
	 * resume_target_kernel()
	 * 2) the stimer on CPU0 is automatically disabled later by
	 * syscore_suspend() -> timekeeping_suspend() -> tick_suspend() -> ...
	 * -> clockevents_shutdown() -> ... -> hv_ce_shutdown()
	 * 3) a warning would be triggered if we call
	 * clockevents_unbind_device(), which may sleep, in an
	 * interrupts-disabled context.
	 */

	hv_synic_disable_regs(0);

	return 0;
}

static void hv_synic_resume(void)
{
	hv_synic_enable_regs(0);

	/*
	 * Note: we don't need to call hv_stimer_init(0), because the timer
	 * on CPU0 is not unbound in hv_synic_suspend(), and the timer is
	 * automatically re-enabled in timekeeping_resume().
	 */
}

/* The callbacks run only on CPU0, with irqs_disabled. */
static struct syscore_ops hv_synic_syscore_ops = {
	.suspend = hv_synic_suspend,
	.resume = hv_synic_resume,
};

static int __init hv_acpi_init(void)
{
	int ret, t;

	if (!hv_is_hyperv_initialized())
		return -ENODEV;

	init_completion(&probe_event);

	/*
	 * Get ACPI resources first.
	 */
	ret = acpi_bus_register_driver(&vmbus_acpi_driver);

	if (ret)
		return ret;

	t = wait_for_completion_timeout(&probe_event, 5*HZ);
	if (t == 0) {
		ret = -ETIMEDOUT;
		goto cleanup;
	}
	hv_debug_init();

	ret = vmbus_bus_init();
	if (ret)
		goto cleanup;

	hv_setup_kexec_handler(hv_kexec_handler);
	hv_setup_crash_handler(hv_crash_handler);

	register_syscore_ops(&hv_synic_syscore_ops);

	return 0;

cleanup:
	acpi_bus_unregister_driver(&vmbus_acpi_driver);
	hv_acpi_dev = NULL;
	return ret;
}

static void __exit vmbus_exit(void)
{
	int cpu;

	unregister_syscore_ops(&hv_synic_syscore_ops);

	hv_remove_kexec_handler();
	hv_remove_crash_handler();
	vmbus_connection.conn_state = DISCONNECTED;
	hv_stimer_global_cleanup();
	vmbus_disconnect();
	hv_remove_vmbus_irq();
	for_each_online_cpu(cpu) {
		struct hv_per_cpu_context *hv_cpu
			= per_cpu_ptr(hv_context.cpu_context, cpu);

		tasklet_kill(&hv_cpu->msg_dpc);
	}
	hv_debug_rm_all_dir();

	vmbus_free_channels();
	kfree(vmbus_connection.channels);

	if (ms_hyperv.misc_features & HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE) {
		kmsg_dump_unregister(&hv_kmsg_dumper);
		unregister_die_notifier(&hyperv_die_block);
		atomic_notifier_chain_unregister(&panic_notifier_list,
						 &hyperv_panic_block);
	}

	free_page((unsigned long)hv_panic_page);
	unregister_sysctl_table(hv_ctl_table_hdr);
	hv_ctl_table_hdr = NULL;
	bus_unregister(&hv_bus);

	cpuhp_remove_state(hyperv_cpuhp_online);
	hv_synic_free();
	acpi_bus_unregister_driver(&vmbus_acpi_driver);
}


MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("Microsoft Hyper-V VMBus Driver");

subsys_initcall(hv_acpi_init);
module_exit(vmbus_exit);