summaryrefslogtreecommitdiff
path: root/drivers/misc/vmw_vmci/vmci_queue_pair.c
blob: 8531ae7811956b1699fbd291dc3615782b6fdcf0 (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
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
3021
3022
3023
3024
3025
3026
3027
3028
3029
3030
3031
3032
3033
3034
3035
3036
3037
3038
3039
3040
3041
3042
3043
3044
3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087
3088
3089
3090
3091
3092
3093
3094
3095
3096
3097
3098
3099
3100
3101
3102
3103
3104
3105
3106
3107
3108
3109
3110
3111
3112
3113
3114
3115
3116
3117
3118
3119
3120
3121
3122
3123
3124
3125
3126
3127
3128
3129
3130
3131
3132
3133
3134
3135
3136
3137
3138
3139
3140
3141
3142
3143
3144
3145
3146
3147
3148
3149
3150
3151
3152
3153
3154
3155
3156
3157
3158
3159
3160
3161
3162
3163
3164
3165
3166
3167
3168
3169
3170
3171
3172
3173
3174
3175
3176
3177
3178
3179
3180
3181
3182
3183
3184
3185
3186
3187
3188
3189
3190
3191
3192
3193
3194
3195
3196
3197
3198
3199
3200
3201
3202
3203
3204
3205
3206
3207
3208
3209
3210
3211
3212
3213
3214
3215
3216
3217
3218
3219
3220
3221
3222
3223
3224
3225
3226
3227
3228
3229
3230
3231
3232
3233
3234
3235
3236
3237
3238
3239
3240
3241
3242
3243
3244
3245
3246
3247
3248
3249
3250
3251
3252
3253
3254
// SPDX-License-Identifier: GPL-2.0-only
/*
 * VMware VMCI Driver
 *
 * Copyright (C) 2012 VMware, Inc. All rights reserved.
 */

#include <linux/vmw_vmci_defs.h>
#include <linux/vmw_vmci_api.h>
#include <linux/highmem.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/module.h>
#include <linux/mutex.h>
#include <linux/pagemap.h>
#include <linux/pci.h>
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/uio.h>
#include <linux/wait.h>
#include <linux/vmalloc.h>
#include <linux/skbuff.h>

#include "vmci_handle_array.h"
#include "vmci_queue_pair.h"
#include "vmci_datagram.h"
#include "vmci_resource.h"
#include "vmci_context.h"
#include "vmci_driver.h"
#include "vmci_event.h"
#include "vmci_route.h"

/*
 * In the following, we will distinguish between two kinds of VMX processes -
 * the ones with versions lower than VMCI_VERSION_NOVMVM that use specialized
 * VMCI page files in the VMX and supporting VM to VM communication and the
 * newer ones that use the guest memory directly. We will in the following
 * refer to the older VMX versions as old-style VMX'en, and the newer ones as
 * new-style VMX'en.
 *
 * The state transition datagram is as follows (the VMCIQPB_ prefix has been
 * removed for readability) - see below for more details on the transtions:
 *
 *            --------------  NEW  -------------
 *            |                                |
 *           \_/                              \_/
 *     CREATED_NO_MEM <-----------------> CREATED_MEM
 *            |    |                           |
 *            |    o-----------------------o   |
 *            |                            |   |
 *           \_/                          \_/ \_/
 *     ATTACHED_NO_MEM <----------------> ATTACHED_MEM
 *            |                            |   |
 *            |     o----------------------o   |
 *            |     |                          |
 *           \_/   \_/                        \_/
 *     SHUTDOWN_NO_MEM <----------------> SHUTDOWN_MEM
 *            |                                |
 *            |                                |
 *            -------------> gone <-------------
 *
 * In more detail. When a VMCI queue pair is first created, it will be in the
 * VMCIQPB_NEW state. It will then move into one of the following states:
 *
 * - VMCIQPB_CREATED_NO_MEM: this state indicates that either:
 *
 *     - the created was performed by a host endpoint, in which case there is
 *       no backing memory yet.
 *
 *     - the create was initiated by an old-style VMX, that uses
 *       vmci_qp_broker_set_page_store to specify the UVAs of the queue pair at
 *       a later point in time. This state can be distinguished from the one
 *       above by the context ID of the creator. A host side is not allowed to
 *       attach until the page store has been set.
 *
 * - VMCIQPB_CREATED_MEM: this state is the result when the queue pair
 *     is created by a VMX using the queue pair device backend that
 *     sets the UVAs of the queue pair immediately and stores the
 *     information for later attachers. At this point, it is ready for
 *     the host side to attach to it.
 *
 * Once the queue pair is in one of the created states (with the exception of
 * the case mentioned for older VMX'en above), it is possible to attach to the
 * queue pair. Again we have two new states possible:
 *
 * - VMCIQPB_ATTACHED_MEM: this state can be reached through the following
 *   paths:
 *
 *     - from VMCIQPB_CREATED_NO_MEM when a new-style VMX allocates a queue
 *       pair, and attaches to a queue pair previously created by the host side.
 *
 *     - from VMCIQPB_CREATED_MEM when the host side attaches to a queue pair
 *       already created by a guest.
 *
 *     - from VMCIQPB_ATTACHED_NO_MEM, when an old-style VMX calls
 *       vmci_qp_broker_set_page_store (see below).
 *
 * - VMCIQPB_ATTACHED_NO_MEM: If the queue pair already was in the
 *     VMCIQPB_CREATED_NO_MEM due to a host side create, an old-style VMX will
 *     bring the queue pair into this state. Once vmci_qp_broker_set_page_store
 *     is called to register the user memory, the VMCIQPB_ATTACH_MEM state
 *     will be entered.
 *
 * From the attached queue pair, the queue pair can enter the shutdown states
 * when either side of the queue pair detaches. If the guest side detaches
 * first, the queue pair will enter the VMCIQPB_SHUTDOWN_NO_MEM state, where
 * the content of the queue pair will no longer be available. If the host
 * side detaches first, the queue pair will either enter the
 * VMCIQPB_SHUTDOWN_MEM, if the guest memory is currently mapped, or
 * VMCIQPB_SHUTDOWN_NO_MEM, if the guest memory is not mapped
 * (e.g., the host detaches while a guest is stunned).
 *
 * New-style VMX'en will also unmap guest memory, if the guest is
 * quiesced, e.g., during a snapshot operation. In that case, the guest
 * memory will no longer be available, and the queue pair will transition from
 * *_MEM state to a *_NO_MEM state. The VMX may later map the memory once more,
 * in which case the queue pair will transition from the *_NO_MEM state at that
 * point back to the *_MEM state. Note that the *_NO_MEM state may have changed,
 * since the peer may have either attached or detached in the meantime. The
 * values are laid out such that ++ on a state will move from a *_NO_MEM to a
 * *_MEM state, and vice versa.
 */

/* The Kernel specific component of the struct vmci_queue structure. */
struct vmci_queue_kern_if {
	struct mutex __mutex;	/* Protects the queue. */
	struct mutex *mutex;	/* Shared by producer and consumer queues. */
	size_t num_pages;	/* Number of pages incl. header. */
	bool host;		/* Host or guest? */
	union {
		struct {
			dma_addr_t *pas;
			void **vas;
		} g;		/* Used by the guest. */
		struct {
			struct page **page;
			struct page **header_page;
		} h;		/* Used by the host. */
	} u;
};

/*
 * This structure is opaque to the clients.
 */
struct vmci_qp {
	struct vmci_handle handle;
	struct vmci_queue *produce_q;
	struct vmci_queue *consume_q;
	u64 produce_q_size;
	u64 consume_q_size;
	u32 peer;
	u32 flags;
	u32 priv_flags;
	bool guest_endpoint;
	unsigned int blocked;
	unsigned int generation;
	wait_queue_head_t event;
};

enum qp_broker_state {
	VMCIQPB_NEW,
	VMCIQPB_CREATED_NO_MEM,
	VMCIQPB_CREATED_MEM,
	VMCIQPB_ATTACHED_NO_MEM,
	VMCIQPB_ATTACHED_MEM,
	VMCIQPB_SHUTDOWN_NO_MEM,
	VMCIQPB_SHUTDOWN_MEM,
	VMCIQPB_GONE
};

#define QPBROKERSTATE_HAS_MEM(_qpb) (_qpb->state == VMCIQPB_CREATED_MEM || \
				     _qpb->state == VMCIQPB_ATTACHED_MEM || \
				     _qpb->state == VMCIQPB_SHUTDOWN_MEM)

/*
 * In the queue pair broker, we always use the guest point of view for
 * the produce and consume queue values and references, e.g., the
 * produce queue size stored is the guests produce queue size. The
 * host endpoint will need to swap these around. The only exception is
 * the local queue pairs on the host, in which case the host endpoint
 * that creates the queue pair will have the right orientation, and
 * the attaching host endpoint will need to swap.
 */
struct qp_entry {
	struct list_head list_item;
	struct vmci_handle handle;
	u32 peer;
	u32 flags;
	u64 produce_size;
	u64 consume_size;
	u32 ref_count;
};

struct qp_broker_entry {
	struct vmci_resource resource;
	struct qp_entry qp;
	u32 create_id;
	u32 attach_id;
	enum qp_broker_state state;
	bool require_trusted_attach;
	bool created_by_trusted;
	bool vmci_page_files;	/* Created by VMX using VMCI page files */
	struct vmci_queue *produce_q;
	struct vmci_queue *consume_q;
	struct vmci_queue_header saved_produce_q;
	struct vmci_queue_header saved_consume_q;
	vmci_event_release_cb wakeup_cb;
	void *client_data;
	void *local_mem;	/* Kernel memory for local queue pair */
};

struct qp_guest_endpoint {
	struct vmci_resource resource;
	struct qp_entry qp;
	u64 num_ppns;
	void *produce_q;
	void *consume_q;
	struct ppn_set ppn_set;
};

struct qp_list {
	struct list_head head;
	struct mutex mutex;	/* Protect queue list. */
};

static struct qp_list qp_broker_list = {
	.head = LIST_HEAD_INIT(qp_broker_list.head),
	.mutex = __MUTEX_INITIALIZER(qp_broker_list.mutex),
};

static struct qp_list qp_guest_endpoints = {
	.head = LIST_HEAD_INIT(qp_guest_endpoints.head),
	.mutex = __MUTEX_INITIALIZER(qp_guest_endpoints.mutex),
};

#define INVALID_VMCI_GUEST_MEM_ID  0
#define QPE_NUM_PAGES(_QPE) ((u32) \
			     (DIV_ROUND_UP(_QPE.produce_size, PAGE_SIZE) + \
			      DIV_ROUND_UP(_QPE.consume_size, PAGE_SIZE) + 2))


/*
 * Frees kernel VA space for a given queue and its queue header, and
 * frees physical data pages.
 */
static void qp_free_queue(void *q, u64 size)
{
	struct vmci_queue *queue = q;

	if (queue) {
		u64 i;

		/* Given size does not include header, so add in a page here. */
		for (i = 0; i < DIV_ROUND_UP(size, PAGE_SIZE) + 1; i++) {
			dma_free_coherent(&vmci_pdev->dev, PAGE_SIZE,
					  queue->kernel_if->u.g.vas[i],
					  queue->kernel_if->u.g.pas[i]);
		}

		vfree(queue);
	}
}

/*
 * Allocates kernel queue pages of specified size with IOMMU mappings,
 * plus space for the queue structure/kernel interface and the queue
 * header.
 */
static void *qp_alloc_queue(u64 size, u32 flags)
{
	u64 i;
	struct vmci_queue *queue;
	size_t pas_size;
	size_t vas_size;
	size_t queue_size = sizeof(*queue) + sizeof(*queue->kernel_if);
	u64 num_pages;

	if (size > SIZE_MAX - PAGE_SIZE)
		return NULL;
	num_pages = DIV_ROUND_UP(size, PAGE_SIZE) + 1;
	if (num_pages >
		 (SIZE_MAX - queue_size) /
		 (sizeof(*queue->kernel_if->u.g.pas) +
		  sizeof(*queue->kernel_if->u.g.vas)))
		return NULL;

	pas_size = num_pages * sizeof(*queue->kernel_if->u.g.pas);
	vas_size = num_pages * sizeof(*queue->kernel_if->u.g.vas);
	queue_size += pas_size + vas_size;

	queue = vmalloc(queue_size);
	if (!queue)
		return NULL;

	queue->q_header = NULL;
	queue->saved_header = NULL;
	queue->kernel_if = (struct vmci_queue_kern_if *)(queue + 1);
	queue->kernel_if->mutex = NULL;
	queue->kernel_if->num_pages = num_pages;
	queue->kernel_if->u.g.pas = (dma_addr_t *)(queue->kernel_if + 1);
	queue->kernel_if->u.g.vas =
		(void **)((u8 *)queue->kernel_if->u.g.pas + pas_size);
	queue->kernel_if->host = false;

	for (i = 0; i < num_pages; i++) {
		queue->kernel_if->u.g.vas[i] =
			dma_alloc_coherent(&vmci_pdev->dev, PAGE_SIZE,
					   &queue->kernel_if->u.g.pas[i],
					   GFP_KERNEL);
		if (!queue->kernel_if->u.g.vas[i]) {
			/* Size excl. the header. */
			qp_free_queue(queue, i * PAGE_SIZE);
			return NULL;
		}
	}

	/* Queue header is the first page. */
	queue->q_header = queue->kernel_if->u.g.vas[0];

	return queue;
}

/*
 * Copies from a given buffer or iovector to a VMCI Queue.  Uses
 * kmap()/kunmap() to dynamically map/unmap required portions of the queue
 * by traversing the offset -> page translation structure for the queue.
 * Assumes that offset + size does not wrap around in the queue.
 */
static int qp_memcpy_to_queue_iter(struct vmci_queue *queue,
				  u64 queue_offset,
				  struct iov_iter *from,
				  size_t size)
{
	struct vmci_queue_kern_if *kernel_if = queue->kernel_if;
	size_t bytes_copied = 0;

	while (bytes_copied < size) {
		const u64 page_index =
			(queue_offset + bytes_copied) / PAGE_SIZE;
		const size_t page_offset =
		    (queue_offset + bytes_copied) & (PAGE_SIZE - 1);
		void *va;
		size_t to_copy;

		if (kernel_if->host)
			va = kmap(kernel_if->u.h.page[page_index]);
		else
			va = kernel_if->u.g.vas[page_index + 1];
			/* Skip header. */

		if (size - bytes_copied > PAGE_SIZE - page_offset)
			/* Enough payload to fill up from this page. */
			to_copy = PAGE_SIZE - page_offset;
		else
			to_copy = size - bytes_copied;

		if (!copy_from_iter_full((u8 *)va + page_offset, to_copy,
					 from)) {
			if (kernel_if->host)
				kunmap(kernel_if->u.h.page[page_index]);
			return VMCI_ERROR_INVALID_ARGS;
		}
		bytes_copied += to_copy;
		if (kernel_if->host)
			kunmap(kernel_if->u.h.page[page_index]);
	}

	return VMCI_SUCCESS;
}

/*
 * Copies to a given buffer or iovector from a VMCI Queue.  Uses
 * kmap()/kunmap() to dynamically map/unmap required portions of the queue
 * by traversing the offset -> page translation structure for the queue.
 * Assumes that offset + size does not wrap around in the queue.
 */
static int qp_memcpy_from_queue_iter(struct iov_iter *to,
				    const struct vmci_queue *queue,
				    u64 queue_offset, size_t size)
{
	struct vmci_queue_kern_if *kernel_if = queue->kernel_if;
	size_t bytes_copied = 0;

	while (bytes_copied < size) {
		const u64 page_index =
			(queue_offset + bytes_copied) / PAGE_SIZE;
		const size_t page_offset =
		    (queue_offset + bytes_copied) & (PAGE_SIZE - 1);
		void *va;
		size_t to_copy;
		int err;

		if (kernel_if->host)
			va = kmap(kernel_if->u.h.page[page_index]);
		else
			va = kernel_if->u.g.vas[page_index + 1];
			/* Skip header. */

		if (size - bytes_copied > PAGE_SIZE - page_offset)
			/* Enough payload to fill up this page. */
			to_copy = PAGE_SIZE - page_offset;
		else
			to_copy = size - bytes_copied;

		err = copy_to_iter((u8 *)va + page_offset, to_copy, to);
		if (err != to_copy) {
			if (kernel_if->host)
				kunmap(kernel_if->u.h.page[page_index]);
			return VMCI_ERROR_INVALID_ARGS;
		}
		bytes_copied += to_copy;
		if (kernel_if->host)
			kunmap(kernel_if->u.h.page[page_index]);
	}

	return VMCI_SUCCESS;
}

/*
 * Allocates two list of PPNs --- one for the pages in the produce queue,
 * and the other for the pages in the consume queue. Intializes the list
 * of PPNs with the page frame numbers of the KVA for the two queues (and
 * the queue headers).
 */
static int qp_alloc_ppn_set(void *prod_q,
			    u64 num_produce_pages,
			    void *cons_q,
			    u64 num_consume_pages, struct ppn_set *ppn_set)
{
	u64 *produce_ppns;
	u64 *consume_ppns;
	struct vmci_queue *produce_q = prod_q;
	struct vmci_queue *consume_q = cons_q;
	u64 i;

	if (!produce_q || !num_produce_pages || !consume_q ||
	    !num_consume_pages || !ppn_set)
		return VMCI_ERROR_INVALID_ARGS;

	if (ppn_set->initialized)
		return VMCI_ERROR_ALREADY_EXISTS;

	produce_ppns =
	    kmalloc_array(num_produce_pages, sizeof(*produce_ppns),
			  GFP_KERNEL);
	if (!produce_ppns)
		return VMCI_ERROR_NO_MEM;

	consume_ppns =
	    kmalloc_array(num_consume_pages, sizeof(*consume_ppns),
			  GFP_KERNEL);
	if (!consume_ppns) {
		kfree(produce_ppns);
		return VMCI_ERROR_NO_MEM;
	}

	for (i = 0; i < num_produce_pages; i++)
		produce_ppns[i] =
			produce_q->kernel_if->u.g.pas[i] >> PAGE_SHIFT;

	for (i = 0; i < num_consume_pages; i++)
		consume_ppns[i] =
			consume_q->kernel_if->u.g.pas[i] >> PAGE_SHIFT;

	ppn_set->num_produce_pages = num_produce_pages;
	ppn_set->num_consume_pages = num_consume_pages;
	ppn_set->produce_ppns = produce_ppns;
	ppn_set->consume_ppns = consume_ppns;
	ppn_set->initialized = true;
	return VMCI_SUCCESS;
}

/*
 * Frees the two list of PPNs for a queue pair.
 */
static void qp_free_ppn_set(struct ppn_set *ppn_set)
{
	if (ppn_set->initialized) {
		/* Do not call these functions on NULL inputs. */
		kfree(ppn_set->produce_ppns);
		kfree(ppn_set->consume_ppns);
	}
	memset(ppn_set, 0, sizeof(*ppn_set));
}

/*
 * Populates the list of PPNs in the hypercall structure with the PPNS
 * of the produce queue and the consume queue.
 */
static int qp_populate_ppn_set(u8 *call_buf, const struct ppn_set *ppn_set)
{
	if (vmci_use_ppn64()) {
		memcpy(call_buf, ppn_set->produce_ppns,
		       ppn_set->num_produce_pages *
		       sizeof(*ppn_set->produce_ppns));
		memcpy(call_buf +
		       ppn_set->num_produce_pages *
		       sizeof(*ppn_set->produce_ppns),
		       ppn_set->consume_ppns,
		       ppn_set->num_consume_pages *
		       sizeof(*ppn_set->consume_ppns));
	} else {
		int i;
		u32 *ppns = (u32 *) call_buf;

		for (i = 0; i < ppn_set->num_produce_pages; i++)
			ppns[i] = (u32) ppn_set->produce_ppns[i];

		ppns = &ppns[ppn_set->num_produce_pages];

		for (i = 0; i < ppn_set->num_consume_pages; i++)
			ppns[i] = (u32) ppn_set->consume_ppns[i];
	}

	return VMCI_SUCCESS;
}

/*
 * Allocates kernel VA space of specified size plus space for the queue
 * and kernel interface.  This is different from the guest queue allocator,
 * because we do not allocate our own queue header/data pages here but
 * share those of the guest.
 */
static struct vmci_queue *qp_host_alloc_queue(u64 size)
{
	struct vmci_queue *queue;
	size_t queue_page_size;
	u64 num_pages;
	const size_t queue_size = sizeof(*queue) + sizeof(*(queue->kernel_if));

	if (size > SIZE_MAX - PAGE_SIZE)
		return NULL;
	num_pages = DIV_ROUND_UP(size, PAGE_SIZE) + 1;
	if (num_pages > (SIZE_MAX - queue_size) /
		 sizeof(*queue->kernel_if->u.h.page))
		return NULL;

	queue_page_size = num_pages * sizeof(*queue->kernel_if->u.h.page);

	queue = kzalloc(queue_size + queue_page_size, GFP_KERNEL);
	if (queue) {
		queue->q_header = NULL;
		queue->saved_header = NULL;
		queue->kernel_if = (struct vmci_queue_kern_if *)(queue + 1);
		queue->kernel_if->host = true;
		queue->kernel_if->mutex = NULL;
		queue->kernel_if->num_pages = num_pages;
		queue->kernel_if->u.h.header_page =
		    (struct page **)((u8 *)queue + queue_size);
		queue->kernel_if->u.h.page =
			&queue->kernel_if->u.h.header_page[1];
	}

	return queue;
}

/*
 * Frees kernel memory for a given queue (header plus translation
 * structure).
 */
static void qp_host_free_queue(struct vmci_queue *queue, u64 queue_size)
{
	kfree(queue);
}

/*
 * Initialize the mutex for the pair of queues.  This mutex is used to
 * protect the q_header and the buffer from changing out from under any
 * users of either queue.  Of course, it's only any good if the mutexes
 * are actually acquired.  Queue structure must lie on non-paged memory
 * or we cannot guarantee access to the mutex.
 */
static void qp_init_queue_mutex(struct vmci_queue *produce_q,
				struct vmci_queue *consume_q)
{
	/*
	 * Only the host queue has shared state - the guest queues do not
	 * need to synchronize access using a queue mutex.
	 */

	if (produce_q->kernel_if->host) {
		produce_q->kernel_if->mutex = &produce_q->kernel_if->__mutex;
		consume_q->kernel_if->mutex = &produce_q->kernel_if->__mutex;
		mutex_init(produce_q->kernel_if->mutex);
	}
}

/*
 * Cleans up the mutex for the pair of queues.
 */
static void qp_cleanup_queue_mutex(struct vmci_queue *produce_q,
				   struct vmci_queue *consume_q)
{
	if (produce_q->kernel_if->host) {
		produce_q->kernel_if->mutex = NULL;
		consume_q->kernel_if->mutex = NULL;
	}
}

/*
 * Acquire the mutex for the queue.  Note that the produce_q and
 * the consume_q share a mutex.  So, only one of the two need to
 * be passed in to this routine.  Either will work just fine.
 */
static void qp_acquire_queue_mutex(struct vmci_queue *queue)
{
	if (queue->kernel_if->host)
		mutex_lock(queue->kernel_if->mutex);
}

/*
 * Release the mutex for the queue.  Note that the produce_q and
 * the consume_q share a mutex.  So, only one of the two need to
 * be passed in to this routine.  Either will work just fine.
 */
static void qp_release_queue_mutex(struct vmci_queue *queue)
{
	if (queue->kernel_if->host)
		mutex_unlock(queue->kernel_if->mutex);
}

/*
 * Helper function to release pages in the PageStoreAttachInfo
 * previously obtained using get_user_pages.
 */
static void qp_release_pages(struct page **pages,
			     u64 num_pages, bool dirty)
{
	int i;

	for (i = 0; i < num_pages; i++) {
		if (dirty)
			set_page_dirty(pages[i]);

		put_page(pages[i]);
		pages[i] = NULL;
	}
}

/*
 * Lock the user pages referenced by the {produce,consume}Buffer
 * struct into memory and populate the {produce,consume}Pages
 * arrays in the attach structure with them.
 */
static int qp_host_get_user_memory(u64 produce_uva,
				   u64 consume_uva,
				   struct vmci_queue *produce_q,
				   struct vmci_queue *consume_q)
{
	int retval;
	int err = VMCI_SUCCESS;

	retval = get_user_pages_fast((uintptr_t) produce_uva,
				     produce_q->kernel_if->num_pages,
				     FOLL_WRITE,
				     produce_q->kernel_if->u.h.header_page);
	if (retval < (int)produce_q->kernel_if->num_pages) {
		pr_debug("get_user_pages_fast(produce) failed (retval=%d)",
			retval);
		qp_release_pages(produce_q->kernel_if->u.h.header_page,
				 retval, false);
		err = VMCI_ERROR_NO_MEM;
		goto out;
	}

	retval = get_user_pages_fast((uintptr_t) consume_uva,
				     consume_q->kernel_if->num_pages,
				     FOLL_WRITE,
				     consume_q->kernel_if->u.h.header_page);
	if (retval < (int)consume_q->kernel_if->num_pages) {
		pr_debug("get_user_pages_fast(consume) failed (retval=%d)",
			retval);
		qp_release_pages(consume_q->kernel_if->u.h.header_page,
				 retval, false);
		qp_release_pages(produce_q->kernel_if->u.h.header_page,
				 produce_q->kernel_if->num_pages, false);
		err = VMCI_ERROR_NO_MEM;
	}

 out:
	return err;
}

/*
 * Registers the specification of the user pages used for backing a queue
 * pair. Enough information to map in pages is stored in the OS specific
 * part of the struct vmci_queue structure.
 */
static int qp_host_register_user_memory(struct vmci_qp_page_store *page_store,
					struct vmci_queue *produce_q,
					struct vmci_queue *consume_q)
{
	u64 produce_uva;
	u64 consume_uva;

	/*
	 * The new style and the old style mapping only differs in
	 * that we either get a single or two UVAs, so we split the
	 * single UVA range at the appropriate spot.
	 */
	produce_uva = page_store->pages;
	consume_uva = page_store->pages +
	    produce_q->kernel_if->num_pages * PAGE_SIZE;
	return qp_host_get_user_memory(produce_uva, consume_uva, produce_q,
				       consume_q);
}

/*
 * Releases and removes the references to user pages stored in the attach
 * struct.  Pages are released from the page cache and may become
 * swappable again.
 */
static void qp_host_unregister_user_memory(struct vmci_queue *produce_q,
					   struct vmci_queue *consume_q)
{
	qp_release_pages(produce_q->kernel_if->u.h.header_page,
			 produce_q->kernel_if->num_pages, true);
	memset(produce_q->kernel_if->u.h.header_page, 0,
	       sizeof(*produce_q->kernel_if->u.h.header_page) *
	       produce_q->kernel_if->num_pages);
	qp_release_pages(consume_q->kernel_if->u.h.header_page,
			 consume_q->kernel_if->num_pages, true);
	memset(consume_q->kernel_if->u.h.header_page, 0,
	       sizeof(*consume_q->kernel_if->u.h.header_page) *
	       consume_q->kernel_if->num_pages);
}

/*
 * Once qp_host_register_user_memory has been performed on a
 * queue, the queue pair headers can be mapped into the
 * kernel. Once mapped, they must be unmapped with
 * qp_host_unmap_queues prior to calling
 * qp_host_unregister_user_memory.
 * Pages are pinned.
 */
static int qp_host_map_queues(struct vmci_queue *produce_q,
			      struct vmci_queue *consume_q)
{
	int result;

	if (!produce_q->q_header || !consume_q->q_header) {
		struct page *headers[2];

		if (produce_q->q_header != consume_q->q_header)
			return VMCI_ERROR_QUEUEPAIR_MISMATCH;

		if (produce_q->kernel_if->u.h.header_page == NULL ||
		    *produce_q->kernel_if->u.h.header_page == NULL)
			return VMCI_ERROR_UNAVAILABLE;

		headers[0] = *produce_q->kernel_if->u.h.header_page;
		headers[1] = *consume_q->kernel_if->u.h.header_page;

		produce_q->q_header = vmap(headers, 2, VM_MAP, PAGE_KERNEL);
		if (produce_q->q_header != NULL) {
			consume_q->q_header =
			    (struct vmci_queue_header *)((u8 *)
							 produce_q->q_header +
							 PAGE_SIZE);
			result = VMCI_SUCCESS;
		} else {
			pr_warn("vmap failed\n");
			result = VMCI_ERROR_NO_MEM;
		}
	} else {
		result = VMCI_SUCCESS;
	}

	return result;
}

/*
 * Unmaps previously mapped queue pair headers from the kernel.
 * Pages are unpinned.
 */
static int qp_host_unmap_queues(u32 gid,
				struct vmci_queue *produce_q,
				struct vmci_queue *consume_q)
{
	if (produce_q->q_header) {
		if (produce_q->q_header < consume_q->q_header)
			vunmap(produce_q->q_header);
		else
			vunmap(consume_q->q_header);

		produce_q->q_header = NULL;
		consume_q->q_header = NULL;
	}

	return VMCI_SUCCESS;
}

/*
 * Finds the entry in the list corresponding to a given handle. Assumes
 * that the list is locked.
 */
static struct qp_entry *qp_list_find(struct qp_list *qp_list,
				     struct vmci_handle handle)
{
	struct qp_entry *entry;

	if (vmci_handle_is_invalid(handle))
		return NULL;

	list_for_each_entry(entry, &qp_list->head, list_item) {
		if (vmci_handle_is_equal(entry->handle, handle))
			return entry;
	}

	return NULL;
}

/*
 * Finds the entry in the list corresponding to a given handle.
 */
static struct qp_guest_endpoint *
qp_guest_handle_to_entry(struct vmci_handle handle)
{
	struct qp_guest_endpoint *entry;
	struct qp_entry *qp = qp_list_find(&qp_guest_endpoints, handle);

	entry = qp ? container_of(
		qp, struct qp_guest_endpoint, qp) : NULL;
	return entry;
}

/*
 * Finds the entry in the list corresponding to a given handle.
 */
static struct qp_broker_entry *
qp_broker_handle_to_entry(struct vmci_handle handle)
{
	struct qp_broker_entry *entry;
	struct qp_entry *qp = qp_list_find(&qp_broker_list, handle);

	entry = qp ? container_of(
		qp, struct qp_broker_entry, qp) : NULL;
	return entry;
}

/*
 * Dispatches a queue pair event message directly into the local event
 * queue.
 */
static int qp_notify_peer_local(bool attach, struct vmci_handle handle)
{
	u32 context_id = vmci_get_context_id();
	struct vmci_event_qp ev;

	ev.msg.hdr.dst = vmci_make_handle(context_id, VMCI_EVENT_HANDLER);
	ev.msg.hdr.src = vmci_make_handle(VMCI_HYPERVISOR_CONTEXT_ID,
					  VMCI_CONTEXT_RESOURCE_ID);
	ev.msg.hdr.payload_size = sizeof(ev) - sizeof(ev.msg.hdr);
	ev.msg.event_data.event =
	    attach ? VMCI_EVENT_QP_PEER_ATTACH : VMCI_EVENT_QP_PEER_DETACH;
	ev.payload.peer_id = context_id;
	ev.payload.handle = handle;

	return vmci_event_dispatch(&ev.msg.hdr);
}

/*
 * Allocates and initializes a qp_guest_endpoint structure.
 * Allocates a queue_pair rid (and handle) iff the given entry has
 * an invalid handle.  0 through VMCI_RESERVED_RESOURCE_ID_MAX
 * are reserved handles.  Assumes that the QP list mutex is held
 * by the caller.
 */
static struct qp_guest_endpoint *
qp_guest_endpoint_create(struct vmci_handle handle,
			 u32 peer,
			 u32 flags,
			 u64 produce_size,
			 u64 consume_size,
			 void *produce_q,
			 void *consume_q)
{
	int result;
	struct qp_guest_endpoint *entry;
	/* One page each for the queue headers. */
	const u64 num_ppns = DIV_ROUND_UP(produce_size, PAGE_SIZE) +
	    DIV_ROUND_UP(consume_size, PAGE_SIZE) + 2;

	if (vmci_handle_is_invalid(handle)) {
		u32 context_id = vmci_get_context_id();

		handle = vmci_make_handle(context_id, VMCI_INVALID_ID);
	}

	entry = kzalloc(sizeof(*entry), GFP_KERNEL);
	if (entry) {
		entry->qp.peer = peer;
		entry->qp.flags = flags;
		entry->qp.produce_size = produce_size;
		entry->qp.consume_size = consume_size;
		entry->qp.ref_count = 0;
		entry->num_ppns = num_ppns;
		entry->produce_q = produce_q;
		entry->consume_q = consume_q;
		INIT_LIST_HEAD(&entry->qp.list_item);

		/* Add resource obj */
		result = vmci_resource_add(&entry->resource,
					   VMCI_RESOURCE_TYPE_QPAIR_GUEST,
					   handle);
		entry->qp.handle = vmci_resource_handle(&entry->resource);
		if ((result != VMCI_SUCCESS) ||
		    qp_list_find(&qp_guest_endpoints, entry->qp.handle)) {
			pr_warn("Failed to add new resource (handle=0x%x:0x%x), error: %d",
				handle.context, handle.resource, result);
			kfree(entry);
			entry = NULL;
		}
	}
	return entry;
}

/*
 * Frees a qp_guest_endpoint structure.
 */
static void qp_guest_endpoint_destroy(struct qp_guest_endpoint *entry)
{
	qp_free_ppn_set(&entry->ppn_set);
	qp_cleanup_queue_mutex(entry->produce_q, entry->consume_q);
	qp_free_queue(entry->produce_q, entry->qp.produce_size);
	qp_free_queue(entry->consume_q, entry->qp.consume_size);
	/* Unlink from resource hash table and free callback */
	vmci_resource_remove(&entry->resource);

	kfree(entry);
}

/*
 * Helper to make a queue_pairAlloc hypercall when the driver is
 * supporting a guest device.
 */
static int qp_alloc_hypercall(const struct qp_guest_endpoint *entry)
{
	struct vmci_qp_alloc_msg *alloc_msg;
	size_t msg_size;
	size_t ppn_size;
	int result;

	if (!entry || entry->num_ppns <= 2)
		return VMCI_ERROR_INVALID_ARGS;

	ppn_size = vmci_use_ppn64() ? sizeof(u64) : sizeof(u32);
	msg_size = sizeof(*alloc_msg) +
	    (size_t) entry->num_ppns * ppn_size;
	alloc_msg = kmalloc(msg_size, GFP_KERNEL);
	if (!alloc_msg)
		return VMCI_ERROR_NO_MEM;

	alloc_msg->hdr.dst = vmci_make_handle(VMCI_HYPERVISOR_CONTEXT_ID,
					      VMCI_QUEUEPAIR_ALLOC);
	alloc_msg->hdr.src = VMCI_ANON_SRC_HANDLE;
	alloc_msg->hdr.payload_size = msg_size - VMCI_DG_HEADERSIZE;
	alloc_msg->handle = entry->qp.handle;
	alloc_msg->peer = entry->qp.peer;
	alloc_msg->flags = entry->qp.flags;
	alloc_msg->produce_size = entry->qp.produce_size;
	alloc_msg->consume_size = entry->qp.consume_size;
	alloc_msg->num_ppns = entry->num_ppns;

	result = qp_populate_ppn_set((u8 *)alloc_msg + sizeof(*alloc_msg),
				     &entry->ppn_set);
	if (result == VMCI_SUCCESS)
		result = vmci_send_datagram(&alloc_msg->hdr);

	kfree(alloc_msg);

	return result;
}

/*
 * Helper to make a queue_pairDetach hypercall when the driver is
 * supporting a guest device.
 */
static int qp_detatch_hypercall(struct vmci_handle handle)
{
	struct vmci_qp_detach_msg detach_msg;

	detach_msg.hdr.dst = vmci_make_handle(VMCI_HYPERVISOR_CONTEXT_ID,
					      VMCI_QUEUEPAIR_DETACH);
	detach_msg.hdr.src = VMCI_ANON_SRC_HANDLE;
	detach_msg.hdr.payload_size = sizeof(handle);
	detach_msg.handle = handle;

	return vmci_send_datagram(&detach_msg.hdr);
}

/*
 * Adds the given entry to the list. Assumes that the list is locked.
 */
static void qp_list_add_entry(struct qp_list *qp_list, struct qp_entry *entry)
{
	if (entry)
		list_add(&entry->list_item, &qp_list->head);
}

/*
 * Removes the given entry from the list. Assumes that the list is locked.
 */
static void qp_list_remove_entry(struct qp_list *qp_list,
				 struct qp_entry *entry)
{
	if (entry)
		list_del(&entry->list_item);
}

/*
 * Helper for VMCI queue_pair detach interface. Frees the physical
 * pages for the queue pair.
 */
static int qp_detatch_guest_work(struct vmci_handle handle)
{
	int result;
	struct qp_guest_endpoint *entry;
	u32 ref_count = ~0;	/* To avoid compiler warning below */

	mutex_lock(&qp_guest_endpoints.mutex);

	entry = qp_guest_handle_to_entry(handle);
	if (!entry) {
		mutex_unlock(&qp_guest_endpoints.mutex);
		return VMCI_ERROR_NOT_FOUND;
	}

	if (entry->qp.flags & VMCI_QPFLAG_LOCAL) {
		result = VMCI_SUCCESS;

		if (entry->qp.ref_count > 1) {
			result = qp_notify_peer_local(false, handle);
			/*
			 * We can fail to notify a local queuepair
			 * because we can't allocate.  We still want
			 * to release the entry if that happens, so
			 * don't bail out yet.
			 */
		}
	} else {
		result = qp_detatch_hypercall(handle);
		if (result < VMCI_SUCCESS) {
			/*
			 * We failed to notify a non-local queuepair.
			 * That other queuepair might still be
			 * accessing the shared memory, so don't
			 * release the entry yet.  It will get cleaned
			 * up by VMCIqueue_pair_Exit() if necessary
			 * (assuming we are going away, otherwise why
			 * did this fail?).
			 */

			mutex_unlock(&qp_guest_endpoints.mutex);
			return result;
		}
	}

	/*
	 * If we get here then we either failed to notify a local queuepair, or
	 * we succeeded in all cases.  Release the entry if required.
	 */

	entry->qp.ref_count--;
	if (entry->qp.ref_count == 0)
		qp_list_remove_entry(&qp_guest_endpoints, &entry->qp);

	/* If we didn't remove the entry, this could change once we unlock. */
	if (entry)
		ref_count = entry->qp.ref_count;

	mutex_unlock(&qp_guest_endpoints.mutex);

	if (ref_count == 0)
		qp_guest_endpoint_destroy(entry);

	return result;
}

/*
 * This functions handles the actual allocation of a VMCI queue
 * pair guest endpoint. Allocates physical pages for the queue
 * pair. It makes OS dependent calls through generic wrappers.
 */
static int qp_alloc_guest_work(struct vmci_handle *handle,
			       struct vmci_queue **produce_q,
			       u64 produce_size,
			       struct vmci_queue **consume_q,
			       u64 consume_size,
			       u32 peer,
			       u32 flags,
			       u32 priv_flags)
{
	const u64 num_produce_pages =
	    DIV_ROUND_UP(produce_size, PAGE_SIZE) + 1;
	const u64 num_consume_pages =
	    DIV_ROUND_UP(consume_size, PAGE_SIZE) + 1;
	void *my_produce_q = NULL;
	void *my_consume_q = NULL;
	int result;
	struct qp_guest_endpoint *queue_pair_entry = NULL;

	if (priv_flags != VMCI_NO_PRIVILEGE_FLAGS)
		return VMCI_ERROR_NO_ACCESS;

	mutex_lock(&qp_guest_endpoints.mutex);

	queue_pair_entry = qp_guest_handle_to_entry(*handle);
	if (queue_pair_entry) {
		if (queue_pair_entry->qp.flags & VMCI_QPFLAG_LOCAL) {
			/* Local attach case. */
			if (queue_pair_entry->qp.ref_count > 1) {
				pr_devel("Error attempting to attach more than once\n");
				result = VMCI_ERROR_UNAVAILABLE;
				goto error_keep_entry;
			}

			if (queue_pair_entry->qp.produce_size != consume_size ||
			    queue_pair_entry->qp.consume_size !=
			    produce_size ||
			    queue_pair_entry->qp.flags !=
			    (flags & ~VMCI_QPFLAG_ATTACH_ONLY)) {
				pr_devel("Error mismatched queue pair in local attach\n");
				result = VMCI_ERROR_QUEUEPAIR_MISMATCH;
				goto error_keep_entry;
			}

			/*
			 * Do a local attach.  We swap the consume and
			 * produce queues for the attacher and deliver
			 * an attach event.
			 */
			result = qp_notify_peer_local(true, *handle);
			if (result < VMCI_SUCCESS)
				goto error_keep_entry;

			my_produce_q = queue_pair_entry->consume_q;
			my_consume_q = queue_pair_entry->produce_q;
			goto out;
		}

		result = VMCI_ERROR_ALREADY_EXISTS;
		goto error_keep_entry;
	}

	my_produce_q = qp_alloc_queue(produce_size, flags);
	if (!my_produce_q) {
		pr_warn("Error allocating pages for produce queue\n");
		result = VMCI_ERROR_NO_MEM;
		goto error;
	}

	my_consume_q = qp_alloc_queue(consume_size, flags);
	if (!my_consume_q) {
		pr_warn("Error allocating pages for consume queue\n");
		result = VMCI_ERROR_NO_MEM;
		goto error;
	}

	queue_pair_entry = qp_guest_endpoint_create(*handle, peer, flags,
						    produce_size, consume_size,
						    my_produce_q, my_consume_q);
	if (!queue_pair_entry) {
		pr_warn("Error allocating memory in %s\n", __func__);
		result = VMCI_ERROR_NO_MEM;
		goto error;
	}

	result = qp_alloc_ppn_set(my_produce_q, num_produce_pages, my_consume_q,
				  num_consume_pages,
				  &queue_pair_entry->ppn_set);
	if (result < VMCI_SUCCESS) {
		pr_warn("qp_alloc_ppn_set failed\n");
		goto error;
	}

	/*
	 * It's only necessary to notify the host if this queue pair will be
	 * attached to from another context.
	 */
	if (queue_pair_entry->qp.flags & VMCI_QPFLAG_LOCAL) {
		/* Local create case. */
		u32 context_id = vmci_get_context_id();

		/*
		 * Enforce similar checks on local queue pairs as we
		 * do for regular ones.  The handle's context must
		 * match the creator or attacher context id (here they
		 * are both the current context id) and the
		 * attach-only flag cannot exist during create.  We
		 * also ensure specified peer is this context or an
		 * invalid one.
		 */
		if (queue_pair_entry->qp.handle.context != context_id ||
		    (queue_pair_entry->qp.peer != VMCI_INVALID_ID &&
		     queue_pair_entry->qp.peer != context_id)) {
			result = VMCI_ERROR_NO_ACCESS;
			goto error;
		}

		if (queue_pair_entry->qp.flags & VMCI_QPFLAG_ATTACH_ONLY) {
			result = VMCI_ERROR_NOT_FOUND;
			goto error;
		}
	} else {
		result = qp_alloc_hypercall(queue_pair_entry);
		if (result < VMCI_SUCCESS) {
			pr_warn("qp_alloc_hypercall result = %d\n", result);
			goto error;
		}
	}

	qp_init_queue_mutex((struct vmci_queue *)my_produce_q,
			    (struct vmci_queue *)my_consume_q);

	qp_list_add_entry(&qp_guest_endpoints, &queue_pair_entry->qp);

 out:
	queue_pair_entry->qp.ref_count++;
	*handle = queue_pair_entry->qp.handle;
	*produce_q = (struct vmci_queue *)my_produce_q;
	*consume_q = (struct vmci_queue *)my_consume_q;

	/*
	 * We should initialize the queue pair header pages on a local
	 * queue pair create.  For non-local queue pairs, the
	 * hypervisor initializes the header pages in the create step.
	 */
	if ((queue_pair_entry->qp.flags & VMCI_QPFLAG_LOCAL) &&
	    queue_pair_entry->qp.ref_count == 1) {
		vmci_q_header_init((*produce_q)->q_header, *handle);
		vmci_q_header_init((*consume_q)->q_header, *handle);
	}

	mutex_unlock(&qp_guest_endpoints.mutex);

	return VMCI_SUCCESS;

 error:
	mutex_unlock(&qp_guest_endpoints.mutex);
	if (queue_pair_entry) {
		/* The queues will be freed inside the destroy routine. */
		qp_guest_endpoint_destroy(queue_pair_entry);
	} else {
		qp_free_queue(my_produce_q, produce_size);
		qp_free_queue(my_consume_q, consume_size);
	}
	return result;

 error_keep_entry:
	/* This path should only be used when an existing entry was found. */
	mutex_unlock(&qp_guest_endpoints.mutex);
	return result;
}

/*
 * The first endpoint issuing a queue pair allocation will create the state
 * of the queue pair in the queue pair broker.
 *
 * If the creator is a guest, it will associate a VMX virtual address range
 * with the queue pair as specified by the page_store. For compatibility with
 * older VMX'en, that would use a separate step to set the VMX virtual
 * address range, the virtual address range can be registered later using
 * vmci_qp_broker_set_page_store. In that case, a page_store of NULL should be
 * used.
 *
 * If the creator is the host, a page_store of NULL should be used as well,
 * since the host is not able to supply a page store for the queue pair.
 *
 * For older VMX and host callers, the queue pair will be created in the
 * VMCIQPB_CREATED_NO_MEM state, and for current VMX callers, it will be
 * created in VMCOQPB_CREATED_MEM state.
 */
static int qp_broker_create(struct vmci_handle handle,
			    u32 peer,
			    u32 flags,
			    u32 priv_flags,
			    u64 produce_size,
			    u64 consume_size,
			    struct vmci_qp_page_store *page_store,
			    struct vmci_ctx *context,
			    vmci_event_release_cb wakeup_cb,
			    void *client_data, struct qp_broker_entry **ent)
{
	struct qp_broker_entry *entry = NULL;
	const u32 context_id = vmci_ctx_get_id(context);
	bool is_local = flags & VMCI_QPFLAG_LOCAL;
	int result;
	u64 guest_produce_size;
	u64 guest_consume_size;

	/* Do not create if the caller asked not to. */
	if (flags & VMCI_QPFLAG_ATTACH_ONLY)
		return VMCI_ERROR_NOT_FOUND;

	/*
	 * Creator's context ID should match handle's context ID or the creator
	 * must allow the context in handle's context ID as the "peer".
	 */
	if (handle.context != context_id && handle.context != peer)
		return VMCI_ERROR_NO_ACCESS;

	if (VMCI_CONTEXT_IS_VM(context_id) && VMCI_CONTEXT_IS_VM(peer))
		return VMCI_ERROR_DST_UNREACHABLE;

	/*
	 * Creator's context ID for local queue pairs should match the
	 * peer, if a peer is specified.
	 */
	if (is_local && peer != VMCI_INVALID_ID && context_id != peer)
		return VMCI_ERROR_NO_ACCESS;

	entry = kzalloc(sizeof(*entry), GFP_ATOMIC);
	if (!entry)
		return VMCI_ERROR_NO_MEM;

	if (vmci_ctx_get_id(context) == VMCI_HOST_CONTEXT_ID && !is_local) {
		/*
		 * The queue pair broker entry stores values from the guest
		 * point of view, so a creating host side endpoint should swap
		 * produce and consume values -- unless it is a local queue
		 * pair, in which case no swapping is necessary, since the local
		 * attacher will swap queues.
		 */

		guest_produce_size = consume_size;
		guest_consume_size = produce_size;
	} else {
		guest_produce_size = produce_size;
		guest_consume_size = consume_size;
	}

	entry->qp.handle = handle;
	entry->qp.peer = peer;
	entry->qp.flags = flags;
	entry->qp.produce_size = guest_produce_size;
	entry->qp.consume_size = guest_consume_size;
	entry->qp.ref_count = 1;
	entry->create_id = context_id;
	entry->attach_id = VMCI_INVALID_ID;
	entry->state = VMCIQPB_NEW;
	entry->require_trusted_attach =
	    !!(context->priv_flags & VMCI_PRIVILEGE_FLAG_RESTRICTED);
	entry->created_by_trusted =
	    !!(priv_flags & VMCI_PRIVILEGE_FLAG_TRUSTED);
	entry->vmci_page_files = false;
	entry->wakeup_cb = wakeup_cb;
	entry->client_data = client_data;
	entry->produce_q = qp_host_alloc_queue(guest_produce_size);
	if (entry->produce_q == NULL) {
		result = VMCI_ERROR_NO_MEM;
		goto error;
	}
	entry->consume_q = qp_host_alloc_queue(guest_consume_size);
	if (entry->consume_q == NULL) {
		result = VMCI_ERROR_NO_MEM;
		goto error;
	}

	qp_init_queue_mutex(entry->produce_q, entry->consume_q);

	INIT_LIST_HEAD(&entry->qp.list_item);

	if (is_local) {
		u8 *tmp;

		entry->local_mem = kcalloc(QPE_NUM_PAGES(entry->qp),
					   PAGE_SIZE, GFP_KERNEL);
		if (entry->local_mem == NULL) {
			result = VMCI_ERROR_NO_MEM;
			goto error;
		}
		entry->state = VMCIQPB_CREATED_MEM;
		entry->produce_q->q_header = entry->local_mem;
		tmp = (u8 *)entry->local_mem + PAGE_SIZE *
		    (DIV_ROUND_UP(entry->qp.produce_size, PAGE_SIZE) + 1);
		entry->consume_q->q_header = (struct vmci_queue_header *)tmp;
	} else if (page_store) {
		/*
		 * The VMX already initialized the queue pair headers, so no
		 * need for the kernel side to do that.
		 */
		result = qp_host_register_user_memory(page_store,
						      entry->produce_q,
						      entry->consume_q);
		if (result < VMCI_SUCCESS)
			goto error;

		entry->state = VMCIQPB_CREATED_MEM;
	} else {
		/*
		 * A create without a page_store may be either a host
		 * side create (in which case we are waiting for the
		 * guest side to supply the memory) or an old style
		 * queue pair create (in which case we will expect a
		 * set page store call as the next step).
		 */
		entry->state = VMCIQPB_CREATED_NO_MEM;
	}

	qp_list_add_entry(&qp_broker_list, &entry->qp);
	if (ent != NULL)
		*ent = entry;

	/* Add to resource obj */
	result = vmci_resource_add(&entry->resource,
				   VMCI_RESOURCE_TYPE_QPAIR_HOST,
				   handle);
	if (result != VMCI_SUCCESS) {
		pr_warn("Failed to add new resource (handle=0x%x:0x%x), error: %d",
			handle.context, handle.resource, result);
		goto error;
	}

	entry->qp.handle = vmci_resource_handle(&entry->resource);
	if (is_local) {
		vmci_q_header_init(entry->produce_q->q_header,
				   entry->qp.handle);
		vmci_q_header_init(entry->consume_q->q_header,
				   entry->qp.handle);
	}

	vmci_ctx_qp_create(context, entry->qp.handle);

	return VMCI_SUCCESS;

 error:
	if (entry != NULL) {
		qp_host_free_queue(entry->produce_q, guest_produce_size);
		qp_host_free_queue(entry->consume_q, guest_consume_size);
		kfree(entry);
	}

	return result;
}

/*
 * Enqueues an event datagram to notify the peer VM attached to
 * the given queue pair handle about attach/detach event by the
 * given VM.  Returns Payload size of datagram enqueued on
 * success, error code otherwise.
 */
static int qp_notify_peer(bool attach,
			  struct vmci_handle handle,
			  u32 my_id,
			  u32 peer_id)
{
	int rv;
	struct vmci_event_qp ev;

	if (vmci_handle_is_invalid(handle) || my_id == VMCI_INVALID_ID ||
	    peer_id == VMCI_INVALID_ID)
		return VMCI_ERROR_INVALID_ARGS;

	/*
	 * In vmci_ctx_enqueue_datagram() we enforce the upper limit on
	 * number of pending events from the hypervisor to a given VM
	 * otherwise a rogue VM could do an arbitrary number of attach
	 * and detach operations causing memory pressure in the host
	 * kernel.
	 */

	ev.msg.hdr.dst = vmci_make_handle(peer_id, VMCI_EVENT_HANDLER);
	ev.msg.hdr.src = vmci_make_handle(VMCI_HYPERVISOR_CONTEXT_ID,
					  VMCI_CONTEXT_RESOURCE_ID);
	ev.msg.hdr.payload_size = sizeof(ev) - sizeof(ev.msg.hdr);
	ev.msg.event_data.event = attach ?
	    VMCI_EVENT_QP_PEER_ATTACH : VMCI_EVENT_QP_PEER_DETACH;
	ev.payload.handle = handle;
	ev.payload.peer_id = my_id;

	rv = vmci_datagram_dispatch(VMCI_HYPERVISOR_CONTEXT_ID,
				    &ev.msg.hdr, false);
	if (rv < VMCI_SUCCESS)
		pr_warn("Failed to enqueue queue_pair %s event datagram for context (ID=0x%x)\n",
			attach ? "ATTACH" : "DETACH", peer_id);

	return rv;
}

/*
 * The second endpoint issuing a queue pair allocation will attach to
 * the queue pair registered with the queue pair broker.
 *
 * If the attacher is a guest, it will associate a VMX virtual address
 * range with the queue pair as specified by the page_store. At this
 * point, the already attach host endpoint may start using the queue
 * pair, and an attach event is sent to it. For compatibility with
 * older VMX'en, that used a separate step to set the VMX virtual
 * address range, the virtual address range can be registered later
 * using vmci_qp_broker_set_page_store. In that case, a page_store of
 * NULL should be used, and the attach event will be generated once
 * the actual page store has been set.
 *
 * If the attacher is the host, a page_store of NULL should be used as
 * well, since the page store information is already set by the guest.
 *
 * For new VMX and host callers, the queue pair will be moved to the
 * VMCIQPB_ATTACHED_MEM state, and for older VMX callers, it will be
 * moved to the VMCOQPB_ATTACHED_NO_MEM state.
 */
static int qp_broker_attach(struct qp_broker_entry *entry,
			    u32 peer,
			    u32 flags,
			    u32 priv_flags,
			    u64 produce_size,
			    u64 consume_size,
			    struct vmci_qp_page_store *page_store,
			    struct vmci_ctx *context,
			    vmci_event_release_cb wakeup_cb,
			    void *client_data,
			    struct qp_broker_entry **ent)
{
	const u32 context_id = vmci_ctx_get_id(context);
	bool is_local = flags & VMCI_QPFLAG_LOCAL;
	int result;

	if (entry->state != VMCIQPB_CREATED_NO_MEM &&
	    entry->state != VMCIQPB_CREATED_MEM)
		return VMCI_ERROR_UNAVAILABLE;

	if (is_local) {
		if (!(entry->qp.flags & VMCI_QPFLAG_LOCAL) ||
		    context_id != entry->create_id) {
			return VMCI_ERROR_INVALID_ARGS;
		}
	} else if (context_id == entry->create_id ||
		   context_id == entry->attach_id) {
		return VMCI_ERROR_ALREADY_EXISTS;
	}

	if (VMCI_CONTEXT_IS_VM(context_id) &&
	    VMCI_CONTEXT_IS_VM(entry->create_id))
		return VMCI_ERROR_DST_UNREACHABLE;

	/*
	 * If we are attaching from a restricted context then the queuepair
	 * must have been created by a trusted endpoint.
	 */
	if ((context->priv_flags & VMCI_PRIVILEGE_FLAG_RESTRICTED) &&
	    !entry->created_by_trusted)
		return VMCI_ERROR_NO_ACCESS;

	/*
	 * If we are attaching to a queuepair that was created by a restricted
	 * context then we must be trusted.
	 */
	if (entry->require_trusted_attach &&
	    (!(priv_flags & VMCI_PRIVILEGE_FLAG_TRUSTED)))
		return VMCI_ERROR_NO_ACCESS;

	/*
	 * If the creator specifies VMCI_INVALID_ID in "peer" field, access
	 * control check is not performed.
	 */
	if (entry->qp.peer != VMCI_INVALID_ID && entry->qp.peer != context_id)
		return VMCI_ERROR_NO_ACCESS;

	if (entry->create_id == VMCI_HOST_CONTEXT_ID) {
		/*
		 * Do not attach if the caller doesn't support Host Queue Pairs
		 * and a host created this queue pair.
		 */

		if (!vmci_ctx_supports_host_qp(context))
			return VMCI_ERROR_INVALID_RESOURCE;

	} else if (context_id == VMCI_HOST_CONTEXT_ID) {
		struct vmci_ctx *create_context;
		bool supports_host_qp;

		/*
		 * Do not attach a host to a user created queue pair if that
		 * user doesn't support host queue pair end points.
		 */

		create_context = vmci_ctx_get(entry->create_id);
		supports_host_qp = vmci_ctx_supports_host_qp(create_context);
		vmci_ctx_put(create_context);

		if (!supports_host_qp)
			return VMCI_ERROR_INVALID_RESOURCE;
	}

	if ((entry->qp.flags & ~VMCI_QP_ASYMM) != (flags & ~VMCI_QP_ASYMM_PEER))
		return VMCI_ERROR_QUEUEPAIR_MISMATCH;

	if (context_id != VMCI_HOST_CONTEXT_ID) {
		/*
		 * The queue pair broker entry stores values from the guest
		 * point of view, so an attaching guest should match the values
		 * stored in the entry.
		 */

		if (entry->qp.produce_size != produce_size ||
		    entry->qp.consume_size != consume_size) {
			return VMCI_ERROR_QUEUEPAIR_MISMATCH;
		}
	} else if (entry->qp.produce_size != consume_size ||
		   entry->qp.consume_size != produce_size) {
		return VMCI_ERROR_QUEUEPAIR_MISMATCH;
	}

	if (context_id != VMCI_HOST_CONTEXT_ID) {
		/*
		 * If a guest attached to a queue pair, it will supply
		 * the backing memory.  If this is a pre NOVMVM vmx,
		 * the backing memory will be supplied by calling
		 * vmci_qp_broker_set_page_store() following the
		 * return of the vmci_qp_broker_alloc() call. If it is
		 * a vmx of version NOVMVM or later, the page store
		 * must be supplied as part of the
		 * vmci_qp_broker_alloc call.  Under all circumstances
		 * must the initially created queue pair not have any
		 * memory associated with it already.
		 */

		if (entry->state != VMCIQPB_CREATED_NO_MEM)
			return VMCI_ERROR_INVALID_ARGS;

		if (page_store != NULL) {
			/*
			 * Patch up host state to point to guest
			 * supplied memory. The VMX already
			 * initialized the queue pair headers, so no
			 * need for the kernel side to do that.
			 */

			result = qp_host_register_user_memory(page_store,
							      entry->produce_q,
							      entry->consume_q);
			if (result < VMCI_SUCCESS)
				return result;

			entry->state = VMCIQPB_ATTACHED_MEM;
		} else {
			entry->state = VMCIQPB_ATTACHED_NO_MEM;
		}
	} else if (entry->state == VMCIQPB_CREATED_NO_MEM) {
		/*
		 * The host side is attempting to attach to a queue
		 * pair that doesn't have any memory associated with
		 * it. This must be a pre NOVMVM vmx that hasn't set
		 * the page store information yet, or a quiesced VM.
		 */

		return VMCI_ERROR_UNAVAILABLE;
	} else {
		/* The host side has successfully attached to a queue pair. */
		entry->state = VMCIQPB_ATTACHED_MEM;
	}

	if (entry->state == VMCIQPB_ATTACHED_MEM) {
		result =
		    qp_notify_peer(true, entry->qp.handle, context_id,
				   entry->create_id);
		if (result < VMCI_SUCCESS)
			pr_warn("Failed to notify peer (ID=0x%x) of attach to queue pair (handle=0x%x:0x%x)\n",
				entry->create_id, entry->qp.handle.context,
				entry->qp.handle.resource);
	}

	entry->attach_id = context_id;
	entry->qp.ref_count++;
	if (wakeup_cb) {
		entry->wakeup_cb = wakeup_cb;
		entry->client_data = client_data;
	}

	/*
	 * When attaching to local queue pairs, the context already has
	 * an entry tracking the queue pair, so don't add another one.
	 */
	if (!is_local)
		vmci_ctx_qp_create(context, entry->qp.handle);

	if (ent != NULL)
		*ent = entry;

	return VMCI_SUCCESS;
}

/*
 * queue_pair_Alloc for use when setting up queue pair endpoints
 * on the host.
 */
static int qp_broker_alloc(struct vmci_handle handle,
			   u32 peer,
			   u32 flags,
			   u32 priv_flags,
			   u64 produce_size,
			   u64 consume_size,
			   struct vmci_qp_page_store *page_store,
			   struct vmci_ctx *context,
			   vmci_event_release_cb wakeup_cb,
			   void *client_data,
			   struct qp_broker_entry **ent,
			   bool *swap)
{
	const u32 context_id = vmci_ctx_get_id(context);
	bool create;
	struct qp_broker_entry *entry = NULL;
	bool is_local = flags & VMCI_QPFLAG_LOCAL;
	int result;

	if (vmci_handle_is_invalid(handle) ||
	    (flags & ~VMCI_QP_ALL_FLAGS) || is_local ||
	    !(produce_size || consume_size) ||
	    !context || context_id == VMCI_INVALID_ID ||
	    handle.context == VMCI_INVALID_ID) {
		return VMCI_ERROR_INVALID_ARGS;
	}

	if (page_store && !VMCI_QP_PAGESTORE_IS_WELLFORMED(page_store))
		return VMCI_ERROR_INVALID_ARGS;

	/*
	 * In the initial argument check, we ensure that non-vmkernel hosts
	 * are not allowed to create local queue pairs.
	 */

	mutex_lock(&qp_broker_list.mutex);

	if (!is_local && vmci_ctx_qp_exists(context, handle)) {
		pr_devel("Context (ID=0x%x) already attached to queue pair (handle=0x%x:0x%x)\n",
			 context_id, handle.context, handle.resource);
		mutex_unlock(&qp_broker_list.mutex);
		return VMCI_ERROR_ALREADY_EXISTS;
	}

	if (handle.resource != VMCI_INVALID_ID)
		entry = qp_broker_handle_to_entry(handle);

	if (!entry) {
		create = true;
		result =
		    qp_broker_create(handle, peer, flags, priv_flags,
				     produce_size, consume_size, page_store,
				     context, wakeup_cb, client_data, ent);
	} else {
		create = false;
		result =
		    qp_broker_attach(entry, peer, flags, priv_flags,
				     produce_size, consume_size, page_store,
				     context, wakeup_cb, client_data, ent);
	}

	mutex_unlock(&qp_broker_list.mutex);

	if (swap)
		*swap = (context_id == VMCI_HOST_CONTEXT_ID) &&
		    !(create && is_local);

	return result;
}

/*
 * This function implements the kernel API for allocating a queue
 * pair.
 */
static int qp_alloc_host_work(struct vmci_handle *handle,
			      struct vmci_queue **produce_q,
			      u64 produce_size,
			      struct vmci_queue **consume_q,
			      u64 consume_size,
			      u32 peer,
			      u32 flags,
			      u32 priv_flags,
			      vmci_event_release_cb wakeup_cb,
			      void *client_data)
{
	struct vmci_handle new_handle;
	struct vmci_ctx *context;
	struct qp_broker_entry *entry;
	int result;
	bool swap;

	if (vmci_handle_is_invalid(*handle)) {
		new_handle = vmci_make_handle(
			VMCI_HOST_CONTEXT_ID, VMCI_INVALID_ID);
	} else
		new_handle = *handle;

	context = vmci_ctx_get(VMCI_HOST_CONTEXT_ID);
	entry = NULL;
	result =
	    qp_broker_alloc(new_handle, peer, flags, priv_flags,
			    produce_size, consume_size, NULL, context,
			    wakeup_cb, client_data, &entry, &swap);
	if (result == VMCI_SUCCESS) {
		if (swap) {
			/*
			 * If this is a local queue pair, the attacher
			 * will swap around produce and consume
			 * queues.
			 */

			*produce_q = entry->consume_q;
			*consume_q = entry->produce_q;
		} else {
			*produce_q = entry->produce_q;
			*consume_q = entry->consume_q;
		}

		*handle = vmci_resource_handle(&entry->resource);
	} else {
		*handle = VMCI_INVALID_HANDLE;
		pr_devel("queue pair broker failed to alloc (result=%d)\n",
			 result);
	}
	vmci_ctx_put(context);
	return result;
}

/*
 * Allocates a VMCI queue_pair. Only checks validity of input
 * arguments. The real work is done in the host or guest
 * specific function.
 */
int vmci_qp_alloc(struct vmci_handle *handle,
		  struct vmci_queue **produce_q,
		  u64 produce_size,
		  struct vmci_queue **consume_q,
		  u64 consume_size,
		  u32 peer,
		  u32 flags,
		  u32 priv_flags,
		  bool guest_endpoint,
		  vmci_event_release_cb wakeup_cb,
		  void *client_data)
{
	if (!handle || !produce_q || !consume_q ||
	    (!produce_size && !consume_size) || (flags & ~VMCI_QP_ALL_FLAGS))
		return VMCI_ERROR_INVALID_ARGS;

	if (guest_endpoint) {
		return qp_alloc_guest_work(handle, produce_q,
					   produce_size, consume_q,
					   consume_size, peer,
					   flags, priv_flags);
	} else {
		return qp_alloc_host_work(handle, produce_q,
					  produce_size, consume_q,
					  consume_size, peer, flags,
					  priv_flags, wakeup_cb, client_data);
	}
}

/*
 * This function implements the host kernel API for detaching from
 * a queue pair.
 */
static int qp_detatch_host_work(struct vmci_handle handle)
{
	int result;
	struct vmci_ctx *context;

	context = vmci_ctx_get(VMCI_HOST_CONTEXT_ID);

	result = vmci_qp_broker_detach(handle, context);

	vmci_ctx_put(context);
	return result;
}

/*
 * Detaches from a VMCI queue_pair. Only checks validity of input argument.
 * Real work is done in the host or guest specific function.
 */
static int qp_detatch(struct vmci_handle handle, bool guest_endpoint)
{
	if (vmci_handle_is_invalid(handle))
		return VMCI_ERROR_INVALID_ARGS;

	if (guest_endpoint)
		return qp_detatch_guest_work(handle);
	else
		return qp_detatch_host_work(handle);
}

/*
 * Returns the entry from the head of the list. Assumes that the list is
 * locked.
 */
static struct qp_entry *qp_list_get_head(struct qp_list *qp_list)
{
	if (!list_empty(&qp_list->head)) {
		struct qp_entry *entry =
		    list_first_entry(&qp_list->head, struct qp_entry,
				     list_item);
		return entry;
	}

	return NULL;
}

void vmci_qp_broker_exit(void)
{
	struct qp_entry *entry;
	struct qp_broker_entry *be;

	mutex_lock(&qp_broker_list.mutex);

	while ((entry = qp_list_get_head(&qp_broker_list))) {
		be = (struct qp_broker_entry *)entry;

		qp_list_remove_entry(&qp_broker_list, entry);
		kfree(be);
	}

	mutex_unlock(&qp_broker_list.mutex);
}

/*
 * Requests that a queue pair be allocated with the VMCI queue
 * pair broker. Allocates a queue pair entry if one does not
 * exist. Attaches to one if it exists, and retrieves the page
 * files backing that queue_pair.  Assumes that the queue pair
 * broker lock is held.
 */
int vmci_qp_broker_alloc(struct vmci_handle handle,
			 u32 peer,
			 u32 flags,
			 u32 priv_flags,
			 u64 produce_size,
			 u64 consume_size,
			 struct vmci_qp_page_store *page_store,
			 struct vmci_ctx *context)
{
	return qp_broker_alloc(handle, peer, flags, priv_flags,
			       produce_size, consume_size,
			       page_store, context, NULL, NULL, NULL, NULL);
}

/*
 * VMX'en with versions lower than VMCI_VERSION_NOVMVM use a separate
 * step to add the UVAs of the VMX mapping of the queue pair. This function
 * provides backwards compatibility with such VMX'en, and takes care of
 * registering the page store for a queue pair previously allocated by the
 * VMX during create or attach. This function will move the queue pair state
 * to either from VMCIQBP_CREATED_NO_MEM to VMCIQBP_CREATED_MEM or
 * VMCIQBP_ATTACHED_NO_MEM to VMCIQBP_ATTACHED_MEM. If moving to the
 * attached state with memory, the queue pair is ready to be used by the
 * host peer, and an attached event will be generated.
 *
 * Assumes that the queue pair broker lock is held.
 *
 * This function is only used by the hosted platform, since there is no
 * issue with backwards compatibility for vmkernel.
 */
int vmci_qp_broker_set_page_store(struct vmci_handle handle,
				  u64 produce_uva,
				  u64 consume_uva,
				  struct vmci_ctx *context)
{
	struct qp_broker_entry *entry;
	int result;
	const u32 context_id = vmci_ctx_get_id(context);

	if (vmci_handle_is_invalid(handle) || !context ||
	    context_id == VMCI_INVALID_ID)
		return VMCI_ERROR_INVALID_ARGS;

	/*
	 * We only support guest to host queue pairs, so the VMX must
	 * supply UVAs for the mapped page files.
	 */

	if (produce_uva == 0 || consume_uva == 0)
		return VMCI_ERROR_INVALID_ARGS;

	mutex_lock(&qp_broker_list.mutex);

	if (!vmci_ctx_qp_exists(context, handle)) {
		pr_warn("Context (ID=0x%x) not attached to queue pair (handle=0x%x:0x%x)\n",
			context_id, handle.context, handle.resource);
		result = VMCI_ERROR_NOT_FOUND;
		goto out;
	}

	entry = qp_broker_handle_to_entry(handle);
	if (!entry) {
		result = VMCI_ERROR_NOT_FOUND;
		goto out;
	}

	/*
	 * If I'm the owner then I can set the page store.
	 *
	 * Or, if a host created the queue_pair and I'm the attached peer
	 * then I can set the page store.
	 */
	if (entry->create_id != context_id &&
	    (entry->create_id != VMCI_HOST_CONTEXT_ID ||
	     entry->attach_id != context_id)) {
		result = VMCI_ERROR_QUEUEPAIR_NOTOWNER;
		goto out;
	}

	if (entry->state != VMCIQPB_CREATED_NO_MEM &&
	    entry->state != VMCIQPB_ATTACHED_NO_MEM) {
		result = VMCI_ERROR_UNAVAILABLE;
		goto out;
	}

	result = qp_host_get_user_memory(produce_uva, consume_uva,
					 entry->produce_q, entry->consume_q);
	if (result < VMCI_SUCCESS)
		goto out;

	result = qp_host_map_queues(entry->produce_q, entry->consume_q);
	if (result < VMCI_SUCCESS) {
		qp_host_unregister_user_memory(entry->produce_q,
					       entry->consume_q);
		goto out;
	}

	if (entry->state == VMCIQPB_CREATED_NO_MEM)
		entry->state = VMCIQPB_CREATED_MEM;
	else
		entry->state = VMCIQPB_ATTACHED_MEM;

	entry->vmci_page_files = true;

	if (entry->state == VMCIQPB_ATTACHED_MEM) {
		result =
		    qp_notify_peer(true, handle, context_id, entry->create_id);
		if (result < VMCI_SUCCESS) {
			pr_warn("Failed to notify peer (ID=0x%x) of attach to queue pair (handle=0x%x:0x%x)\n",
				entry->create_id, entry->qp.handle.context,
				entry->qp.handle.resource);
		}
	}

	result = VMCI_SUCCESS;
 out:
	mutex_unlock(&qp_broker_list.mutex);
	return result;
}

/*
 * Resets saved queue headers for the given QP broker
 * entry. Should be used when guest memory becomes available
 * again, or the guest detaches.
 */
static void qp_reset_saved_headers(struct qp_broker_entry *entry)
{
	entry->produce_q->saved_header = NULL;
	entry->consume_q->saved_header = NULL;
}

/*
 * The main entry point for detaching from a queue pair registered with the
 * queue pair broker. If more than one endpoint is attached to the queue
 * pair, the first endpoint will mainly decrement a reference count and
 * generate a notification to its peer. The last endpoint will clean up
 * the queue pair state registered with the broker.
 *
 * When a guest endpoint detaches, it will unmap and unregister the guest
 * memory backing the queue pair. If the host is still attached, it will
 * no longer be able to access the queue pair content.
 *
 * If the queue pair is already in a state where there is no memory
 * registered for the queue pair (any *_NO_MEM state), it will transition to
 * the VMCIQPB_SHUTDOWN_NO_MEM state. This will also happen, if a guest
 * endpoint is the first of two endpoints to detach. If the host endpoint is
 * the first out of two to detach, the queue pair will move to the
 * VMCIQPB_SHUTDOWN_MEM state.
 */
int vmci_qp_broker_detach(struct vmci_handle handle, struct vmci_ctx *context)
{
	struct qp_broker_entry *entry;
	const u32 context_id = vmci_ctx_get_id(context);
	u32 peer_id;
	bool is_local = false;
	int result;

	if (vmci_handle_is_invalid(handle) || !context ||
	    context_id == VMCI_INVALID_ID) {
		return VMCI_ERROR_INVALID_ARGS;
	}

	mutex_lock(&qp_broker_list.mutex);

	if (!vmci_ctx_qp_exists(context, handle)) {
		pr_devel("Context (ID=0x%x) not attached to queue pair (handle=0x%x:0x%x)\n",
			 context_id, handle.context, handle.resource);
		result = VMCI_ERROR_NOT_FOUND;
		goto out;
	}

	entry = qp_broker_handle_to_entry(handle);
	if (!entry) {
		pr_devel("Context (ID=0x%x) reports being attached to queue pair(handle=0x%x:0x%x) that isn't present in broker\n",
			 context_id, handle.context, handle.resource);
		result = VMCI_ERROR_NOT_FOUND;
		goto out;
	}

	if (context_id != entry->create_id && context_id != entry->attach_id) {
		result = VMCI_ERROR_QUEUEPAIR_NOTATTACHED;
		goto out;
	}

	if (context_id == entry->create_id) {
		peer_id = entry->attach_id;
		entry->create_id = VMCI_INVALID_ID;
	} else {
		peer_id = entry->create_id;
		entry->attach_id = VMCI_INVALID_ID;
	}
	entry->qp.ref_count--;

	is_local = entry->qp.flags & VMCI_QPFLAG_LOCAL;

	if (context_id != VMCI_HOST_CONTEXT_ID) {
		bool headers_mapped;

		/*
		 * Pre NOVMVM vmx'en may detach from a queue pair
		 * before setting the page store, and in that case
		 * there is no user memory to detach from. Also, more
		 * recent VMX'en may detach from a queue pair in the
		 * quiesced state.
		 */

		qp_acquire_queue_mutex(entry->produce_q);
		headers_mapped = entry->produce_q->q_header ||
		    entry->consume_q->q_header;
		if (QPBROKERSTATE_HAS_MEM(entry)) {
			result =
			    qp_host_unmap_queues(INVALID_VMCI_GUEST_MEM_ID,
						 entry->produce_q,
						 entry->consume_q);
			if (result < VMCI_SUCCESS)
				pr_warn("Failed to unmap queue headers for queue pair (handle=0x%x:0x%x,result=%d)\n",
					handle.context, handle.resource,
					result);

			qp_host_unregister_user_memory(entry->produce_q,
						       entry->consume_q);

		}

		if (!headers_mapped)
			qp_reset_saved_headers(entry);

		qp_release_queue_mutex(entry->produce_q);

		if (!headers_mapped && entry->wakeup_cb)
			entry->wakeup_cb(entry->client_data);

	} else {
		if (entry->wakeup_cb) {
			entry->wakeup_cb = NULL;
			entry->client_data = NULL;
		}
	}

	if (entry->qp.ref_count == 0) {
		qp_list_remove_entry(&qp_broker_list, &entry->qp);

		if (is_local)
			kfree(entry->local_mem);

		qp_cleanup_queue_mutex(entry->produce_q, entry->consume_q);
		qp_host_free_queue(entry->produce_q, entry->qp.produce_size);
		qp_host_free_queue(entry->consume_q, entry->qp.consume_size);
		/* Unlink from resource hash table and free callback */
		vmci_resource_remove(&entry->resource);

		kfree(entry);

		vmci_ctx_qp_destroy(context, handle);
	} else {
		qp_notify_peer(false, handle, context_id, peer_id);
		if (context_id == VMCI_HOST_CONTEXT_ID &&
		    QPBROKERSTATE_HAS_MEM(entry)) {
			entry->state = VMCIQPB_SHUTDOWN_MEM;
		} else {
			entry->state = VMCIQPB_SHUTDOWN_NO_MEM;
		}

		if (!is_local)
			vmci_ctx_qp_destroy(context, handle);

	}
	result = VMCI_SUCCESS;
 out:
	mutex_unlock(&qp_broker_list.mutex);
	return result;
}

/*
 * Establishes the necessary mappings for a queue pair given a
 * reference to the queue pair guest memory. This is usually
 * called when a guest is unquiesced and the VMX is allowed to
 * map guest memory once again.
 */
int vmci_qp_broker_map(struct vmci_handle handle,
		       struct vmci_ctx *context,
		       u64 guest_mem)
{
	struct qp_broker_entry *entry;
	const u32 context_id = vmci_ctx_get_id(context);
	int result;

	if (vmci_handle_is_invalid(handle) || !context ||
	    context_id == VMCI_INVALID_ID)
		return VMCI_ERROR_INVALID_ARGS;

	mutex_lock(&qp_broker_list.mutex);

	if (!vmci_ctx_qp_exists(context, handle)) {
		pr_devel("Context (ID=0x%x) not attached to queue pair (handle=0x%x:0x%x)\n",
			 context_id, handle.context, handle.resource);
		result = VMCI_ERROR_NOT_FOUND;
		goto out;
	}

	entry = qp_broker_handle_to_entry(handle);
	if (!entry) {
		pr_devel("Context (ID=0x%x) reports being attached to queue pair (handle=0x%x:0x%x) that isn't present in broker\n",
			 context_id, handle.context, handle.resource);
		result = VMCI_ERROR_NOT_FOUND;
		goto out;
	}

	if (context_id != entry->create_id && context_id != entry->attach_id) {
		result = VMCI_ERROR_QUEUEPAIR_NOTATTACHED;
		goto out;
	}

	result = VMCI_SUCCESS;

	if (context_id != VMCI_HOST_CONTEXT_ID) {
		struct vmci_qp_page_store page_store;

		page_store.pages = guest_mem;
		page_store.len = QPE_NUM_PAGES(entry->qp);

		qp_acquire_queue_mutex(entry->produce_q);
		qp_reset_saved_headers(entry);
		result =
		    qp_host_register_user_memory(&page_store,
						 entry->produce_q,
						 entry->consume_q);
		qp_release_queue_mutex(entry->produce_q);
		if (result == VMCI_SUCCESS) {
			/* Move state from *_NO_MEM to *_MEM */

			entry->state++;

			if (entry->wakeup_cb)
				entry->wakeup_cb(entry->client_data);
		}
	}

 out:
	mutex_unlock(&qp_broker_list.mutex);
	return result;
}

/*
 * Saves a snapshot of the queue headers for the given QP broker
 * entry. Should be used when guest memory is unmapped.
 * Results:
 * VMCI_SUCCESS on success, appropriate error code if guest memory
 * can't be accessed..
 */
static int qp_save_headers(struct qp_broker_entry *entry)
{
	int result;

	if (entry->produce_q->saved_header != NULL &&
	    entry->consume_q->saved_header != NULL) {
		/*
		 *  If the headers have already been saved, we don't need to do
		 *  it again, and we don't want to map in the headers
		 *  unnecessarily.
		 */

		return VMCI_SUCCESS;
	}

	if (NULL == entry->produce_q->q_header ||
	    NULL == entry->consume_q->q_header) {
		result = qp_host_map_queues(entry->produce_q, entry->consume_q);
		if (result < VMCI_SUCCESS)
			return result;
	}

	memcpy(&entry->saved_produce_q, entry->produce_q->q_header,
	       sizeof(entry->saved_produce_q));
	entry->produce_q->saved_header = &entry->saved_produce_q;
	memcpy(&entry->saved_consume_q, entry->consume_q->q_header,
	       sizeof(entry->saved_consume_q));
	entry->consume_q->saved_header = &entry->saved_consume_q;

	return VMCI_SUCCESS;
}

/*
 * Removes all references to the guest memory of a given queue pair, and
 * will move the queue pair from state *_MEM to *_NO_MEM. It is usually
 * called when a VM is being quiesced where access to guest memory should
 * avoided.
 */
int vmci_qp_broker_unmap(struct vmci_handle handle,
			 struct vmci_ctx *context,
			 u32 gid)
{
	struct qp_broker_entry *entry;
	const u32 context_id = vmci_ctx_get_id(context);
	int result;

	if (vmci_handle_is_invalid(handle) || !context ||
	    context_id == VMCI_INVALID_ID)
		return VMCI_ERROR_INVALID_ARGS;

	mutex_lock(&qp_broker_list.mutex);

	if (!vmci_ctx_qp_exists(context, handle)) {
		pr_devel("Context (ID=0x%x) not attached to queue pair (handle=0x%x:0x%x)\n",
			 context_id, handle.context, handle.resource);
		result = VMCI_ERROR_NOT_FOUND;
		goto out;
	}

	entry = qp_broker_handle_to_entry(handle);
	if (!entry) {
		pr_devel("Context (ID=0x%x) reports being attached to queue pair (handle=0x%x:0x%x) that isn't present in broker\n",
			 context_id, handle.context, handle.resource);
		result = VMCI_ERROR_NOT_FOUND;
		goto out;
	}

	if (context_id != entry->create_id && context_id != entry->attach_id) {
		result = VMCI_ERROR_QUEUEPAIR_NOTATTACHED;
		goto out;
	}

	if (context_id != VMCI_HOST_CONTEXT_ID) {
		qp_acquire_queue_mutex(entry->produce_q);
		result = qp_save_headers(entry);
		if (result < VMCI_SUCCESS)
			pr_warn("Failed to save queue headers for queue pair (handle=0x%x:0x%x,result=%d)\n",
				handle.context, handle.resource, result);

		qp_host_unmap_queues(gid, entry->produce_q, entry->consume_q);

		/*
		 * On hosted, when we unmap queue pairs, the VMX will also
		 * unmap the guest memory, so we invalidate the previously
		 * registered memory. If the queue pair is mapped again at a
		 * later point in time, we will need to reregister the user
		 * memory with a possibly new user VA.
		 */
		qp_host_unregister_user_memory(entry->produce_q,
					       entry->consume_q);

		/*
		 * Move state from *_MEM to *_NO_MEM.
		 */
		entry->state--;

		qp_release_queue_mutex(entry->produce_q);
	}

	result = VMCI_SUCCESS;

 out:
	mutex_unlock(&qp_broker_list.mutex);
	return result;
}

/*
 * Destroys all guest queue pair endpoints. If active guest queue
 * pairs still exist, hypercalls to attempt detach from these
 * queue pairs will be made. Any failure to detach is silently
 * ignored.
 */
void vmci_qp_guest_endpoints_exit(void)
{
	struct qp_entry *entry;
	struct qp_guest_endpoint *ep;

	mutex_lock(&qp_guest_endpoints.mutex);

	while ((entry = qp_list_get_head(&qp_guest_endpoints))) {
		ep = (struct qp_guest_endpoint *)entry;

		/* Don't make a hypercall for local queue_pairs. */
		if (!(entry->flags & VMCI_QPFLAG_LOCAL))
			qp_detatch_hypercall(entry->handle);

		/* We cannot fail the exit, so let's reset ref_count. */
		entry->ref_count = 0;
		qp_list_remove_entry(&qp_guest_endpoints, entry);

		qp_guest_endpoint_destroy(ep);
	}

	mutex_unlock(&qp_guest_endpoints.mutex);
}

/*
 * Helper routine that will lock the queue pair before subsequent
 * operations.
 * Note: Non-blocking on the host side is currently only implemented in ESX.
 * Since non-blocking isn't yet implemented on the host personality we
 * have no reason to acquire a spin lock.  So to avoid the use of an
 * unnecessary lock only acquire the mutex if we can block.
 */
static void qp_lock(const struct vmci_qp *qpair)
{
	qp_acquire_queue_mutex(qpair->produce_q);
}

/*
 * Helper routine that unlocks the queue pair after calling
 * qp_lock.
 */
static void qp_unlock(const struct vmci_qp *qpair)
{
	qp_release_queue_mutex(qpair->produce_q);
}

/*
 * The queue headers may not be mapped at all times. If a queue is
 * currently not mapped, it will be attempted to do so.
 */
static int qp_map_queue_headers(struct vmci_queue *produce_q,
				struct vmci_queue *consume_q)
{
	int result;

	if (NULL == produce_q->q_header || NULL == consume_q->q_header) {
		result = qp_host_map_queues(produce_q, consume_q);
		if (result < VMCI_SUCCESS)
			return (produce_q->saved_header &&
				consume_q->saved_header) ?
			    VMCI_ERROR_QUEUEPAIR_NOT_READY :
			    VMCI_ERROR_QUEUEPAIR_NOTATTACHED;
	}

	return VMCI_SUCCESS;
}

/*
 * Helper routine that will retrieve the produce and consume
 * headers of a given queue pair. If the guest memory of the
 * queue pair is currently not available, the saved queue headers
 * will be returned, if these are available.
 */
static int qp_get_queue_headers(const struct vmci_qp *qpair,
				struct vmci_queue_header **produce_q_header,
				struct vmci_queue_header **consume_q_header)
{
	int result;

	result = qp_map_queue_headers(qpair->produce_q, qpair->consume_q);
	if (result == VMCI_SUCCESS) {
		*produce_q_header = qpair->produce_q->q_header;
		*consume_q_header = qpair->consume_q->q_header;
	} else if (qpair->produce_q->saved_header &&
		   qpair->consume_q->saved_header) {
		*produce_q_header = qpair->produce_q->saved_header;
		*consume_q_header = qpair->consume_q->saved_header;
		result = VMCI_SUCCESS;
	}

	return result;
}

/*
 * Callback from VMCI queue pair broker indicating that a queue
 * pair that was previously not ready, now either is ready or
 * gone forever.
 */
static int qp_wakeup_cb(void *client_data)
{
	struct vmci_qp *qpair = (struct vmci_qp *)client_data;

	qp_lock(qpair);
	while (qpair->blocked > 0) {
		qpair->blocked--;
		qpair->generation++;
		wake_up(&qpair->event);
	}
	qp_unlock(qpair);

	return VMCI_SUCCESS;
}

/*
 * Makes the calling thread wait for the queue pair to become
 * ready for host side access.  Returns true when thread is
 * woken up after queue pair state change, false otherwise.
 */
static bool qp_wait_for_ready_queue(struct vmci_qp *qpair)
{
	unsigned int generation;

	qpair->blocked++;
	generation = qpair->generation;
	qp_unlock(qpair);
	wait_event(qpair->event, generation != qpair->generation);
	qp_lock(qpair);

	return true;
}

/*
 * Enqueues a given buffer to the produce queue using the provided
 * function. As many bytes as possible (space available in the queue)
 * are enqueued.  Assumes the queue->mutex has been acquired.  Returns
 * VMCI_ERROR_QUEUEPAIR_NOSPACE if no space was available to enqueue
 * data, VMCI_ERROR_INVALID_SIZE, if any queue pointer is outside the
 * queue (as defined by the queue size), VMCI_ERROR_INVALID_ARGS, if
 * an error occured when accessing the buffer,
 * VMCI_ERROR_QUEUEPAIR_NOTATTACHED, if the queue pair pages aren't
 * available.  Otherwise, the number of bytes written to the queue is
 * returned.  Updates the tail pointer of the produce queue.
 */
static ssize_t qp_enqueue_locked(struct vmci_queue *produce_q,
				 struct vmci_queue *consume_q,
				 const u64 produce_q_size,
				 struct iov_iter *from)
{
	s64 free_space;
	u64 tail;
	size_t buf_size = iov_iter_count(from);
	size_t written;
	ssize_t result;

	result = qp_map_queue_headers(produce_q, consume_q);
	if (unlikely(result != VMCI_SUCCESS))
		return result;

	free_space = vmci_q_header_free_space(produce_q->q_header,
					      consume_q->q_header,
					      produce_q_size);
	if (free_space == 0)
		return VMCI_ERROR_QUEUEPAIR_NOSPACE;

	if (free_space < VMCI_SUCCESS)
		return (ssize_t) free_space;

	written = (size_t) (free_space > buf_size ? buf_size : free_space);
	tail = vmci_q_header_producer_tail(produce_q->q_header);
	if (likely(tail + written < produce_q_size)) {
		result = qp_memcpy_to_queue_iter(produce_q, tail, from, written);
	} else {
		/* Tail pointer wraps around. */

		const size_t tmp = (size_t) (produce_q_size - tail);

		result = qp_memcpy_to_queue_iter(produce_q, tail, from, tmp);
		if (result >= VMCI_SUCCESS)
			result = qp_memcpy_to_queue_iter(produce_q, 0, from,
						 written - tmp);
	}

	if (result < VMCI_SUCCESS)
		return result;

	vmci_q_header_add_producer_tail(produce_q->q_header, written,
					produce_q_size);
	return written;
}

/*
 * Dequeues data (if available) from the given consume queue. Writes data
 * to the user provided buffer using the provided function.
 * Assumes the queue->mutex has been acquired.
 * Results:
 * VMCI_ERROR_QUEUEPAIR_NODATA if no data was available to dequeue.
 * VMCI_ERROR_INVALID_SIZE, if any queue pointer is outside the queue
 * (as defined by the queue size).
 * VMCI_ERROR_INVALID_ARGS, if an error occured when accessing the buffer.
 * Otherwise the number of bytes dequeued is returned.
 * Side effects:
 * Updates the head pointer of the consume queue.
 */
static ssize_t qp_dequeue_locked(struct vmci_queue *produce_q,
				 struct vmci_queue *consume_q,
				 const u64 consume_q_size,
				 struct iov_iter *to,
				 bool update_consumer)
{
	size_t buf_size = iov_iter_count(to);
	s64 buf_ready;
	u64 head;
	size_t read;
	ssize_t result;

	result = qp_map_queue_headers(produce_q, consume_q);
	if (unlikely(result != VMCI_SUCCESS))
		return result;

	buf_ready = vmci_q_header_buf_ready(consume_q->q_header,
					    produce_q->q_header,
					    consume_q_size);
	if (buf_ready == 0)
		return VMCI_ERROR_QUEUEPAIR_NODATA;

	if (buf_ready < VMCI_SUCCESS)
		return (ssize_t) buf_ready;

	read = (size_t) (buf_ready > buf_size ? buf_size : buf_ready);
	head = vmci_q_header_consumer_head(produce_q->q_header);
	if (likely(head + read < consume_q_size)) {
		result = qp_memcpy_from_queue_iter(to, consume_q, head, read);
	} else {
		/* Head pointer wraps around. */

		const size_t tmp = (size_t) (consume_q_size - head);

		result = qp_memcpy_from_queue_iter(to, consume_q, head, tmp);
		if (result >= VMCI_SUCCESS)
			result = qp_memcpy_from_queue_iter(to, consume_q, 0,
						   read - tmp);

	}

	if (result < VMCI_SUCCESS)
		return result;

	if (update_consumer)
		vmci_q_header_add_consumer_head(produce_q->q_header,
						read, consume_q_size);

	return read;
}

/*
 * vmci_qpair_alloc() - Allocates a queue pair.
 * @qpair:      Pointer for the new vmci_qp struct.
 * @handle:     Handle to track the resource.
 * @produce_qsize:      Desired size of the producer queue.
 * @consume_qsize:      Desired size of the consumer queue.
 * @peer:       ContextID of the peer.
 * @flags:      VMCI flags.
 * @priv_flags: VMCI priviledge flags.
 *
 * This is the client interface for allocating the memory for a
 * vmci_qp structure and then attaching to the underlying
 * queue.  If an error occurs allocating the memory for the
 * vmci_qp structure no attempt is made to attach.  If an
 * error occurs attaching, then the structure is freed.
 */
int vmci_qpair_alloc(struct vmci_qp **qpair,
		     struct vmci_handle *handle,
		     u64 produce_qsize,
		     u64 consume_qsize,
		     u32 peer,
		     u32 flags,
		     u32 priv_flags)
{
	struct vmci_qp *my_qpair;
	int retval;
	struct vmci_handle src = VMCI_INVALID_HANDLE;
	struct vmci_handle dst = vmci_make_handle(peer, VMCI_INVALID_ID);
	enum vmci_route route;
	vmci_event_release_cb wakeup_cb;
	void *client_data;

	/*
	 * Restrict the size of a queuepair.  The device already
	 * enforces a limit on the total amount of memory that can be
	 * allocated to queuepairs for a guest.  However, we try to
	 * allocate this memory before we make the queuepair
	 * allocation hypercall.  On Linux, we allocate each page
	 * separately, which means rather than fail, the guest will
	 * thrash while it tries to allocate, and will become
	 * increasingly unresponsive to the point where it appears to
	 * be hung.  So we place a limit on the size of an individual
	 * queuepair here, and leave the device to enforce the
	 * restriction on total queuepair memory.  (Note that this
	 * doesn't prevent all cases; a user with only this much
	 * physical memory could still get into trouble.)  The error
	 * used by the device is NO_RESOURCES, so use that here too.
	 */

	if (produce_qsize + consume_qsize < max(produce_qsize, consume_qsize) ||
	    produce_qsize + consume_qsize > VMCI_MAX_GUEST_QP_MEMORY)
		return VMCI_ERROR_NO_RESOURCES;

	retval = vmci_route(&src, &dst, false, &route);
	if (retval < VMCI_SUCCESS)
		route = vmci_guest_code_active() ?
		    VMCI_ROUTE_AS_GUEST : VMCI_ROUTE_AS_HOST;

	if (flags & (VMCI_QPFLAG_NONBLOCK | VMCI_QPFLAG_PINNED)) {
		pr_devel("NONBLOCK OR PINNED set");
		return VMCI_ERROR_INVALID_ARGS;
	}

	my_qpair = kzalloc(sizeof(*my_qpair), GFP_KERNEL);
	if (!my_qpair)
		return VMCI_ERROR_NO_MEM;

	my_qpair->produce_q_size = produce_qsize;
	my_qpair->consume_q_size = consume_qsize;
	my_qpair->peer = peer;
	my_qpair->flags = flags;
	my_qpair->priv_flags = priv_flags;

	wakeup_cb = NULL;
	client_data = NULL;

	if (VMCI_ROUTE_AS_HOST == route) {
		my_qpair->guest_endpoint = false;
		if (!(flags & VMCI_QPFLAG_LOCAL)) {
			my_qpair->blocked = 0;
			my_qpair->generation = 0;
			init_waitqueue_head(&my_qpair->event);
			wakeup_cb = qp_wakeup_cb;
			client_data = (void *)my_qpair;
		}
	} else {
		my_qpair->guest_endpoint = true;
	}

	retval = vmci_qp_alloc(handle,
			       &my_qpair->produce_q,
			       my_qpair->produce_q_size,
			       &my_qpair->consume_q,
			       my_qpair->consume_q_size,
			       my_qpair->peer,
			       my_qpair->flags,
			       my_qpair->priv_flags,
			       my_qpair->guest_endpoint,
			       wakeup_cb, client_data);

	if (retval < VMCI_SUCCESS) {
		kfree(my_qpair);
		return retval;
	}

	*qpair = my_qpair;
	my_qpair->handle = *handle;

	return retval;
}
EXPORT_SYMBOL_GPL(vmci_qpair_alloc);

/*
 * vmci_qpair_detach() - Detatches the client from a queue pair.
 * @qpair:      Reference of a pointer to the qpair struct.
 *
 * This is the client interface for detaching from a VMCIQPair.
 * Note that this routine will free the memory allocated for the
 * vmci_qp structure too.
 */
int vmci_qpair_detach(struct vmci_qp **qpair)
{
	int result;
	struct vmci_qp *old_qpair;

	if (!qpair || !(*qpair))
		return VMCI_ERROR_INVALID_ARGS;

	old_qpair = *qpair;
	result = qp_detatch(old_qpair->handle, old_qpair->guest_endpoint);

	/*
	 * The guest can fail to detach for a number of reasons, and
	 * if it does so, it will cleanup the entry (if there is one).
	 * The host can fail too, but it won't cleanup the entry
	 * immediately, it will do that later when the context is
	 * freed.  Either way, we need to release the qpair struct
	 * here; there isn't much the caller can do, and we don't want
	 * to leak.
	 */

	memset(old_qpair, 0, sizeof(*old_qpair));
	old_qpair->handle = VMCI_INVALID_HANDLE;
	old_qpair->peer = VMCI_INVALID_ID;
	kfree(old_qpair);
	*qpair = NULL;

	return result;
}
EXPORT_SYMBOL_GPL(vmci_qpair_detach);

/*
 * vmci_qpair_get_produce_indexes() - Retrieves the indexes of the producer.
 * @qpair:      Pointer to the queue pair struct.
 * @producer_tail:      Reference used for storing producer tail index.
 * @consumer_head:      Reference used for storing the consumer head index.
 *
 * This is the client interface for getting the current indexes of the
 * QPair from the point of the view of the caller as the producer.
 */
int vmci_qpair_get_produce_indexes(const struct vmci_qp *qpair,
				   u64 *producer_tail,
				   u64 *consumer_head)
{
	struct vmci_queue_header *produce_q_header;
	struct vmci_queue_header *consume_q_header;
	int result;

	if (!qpair)
		return VMCI_ERROR_INVALID_ARGS;

	qp_lock(qpair);
	result =
	    qp_get_queue_headers(qpair, &produce_q_header, &consume_q_header);
	if (result == VMCI_SUCCESS)
		vmci_q_header_get_pointers(produce_q_header, consume_q_header,
					   producer_tail, consumer_head);
	qp_unlock(qpair);

	if (result == VMCI_SUCCESS &&
	    ((producer_tail && *producer_tail >= qpair->produce_q_size) ||
	     (consumer_head && *consumer_head >= qpair->produce_q_size)))
		return VMCI_ERROR_INVALID_SIZE;

	return result;
}
EXPORT_SYMBOL_GPL(vmci_qpair_get_produce_indexes);

/*
 * vmci_qpair_get_consume_indexes() - Retrieves the indexes of the consumer.
 * @qpair:      Pointer to the queue pair struct.
 * @consumer_tail:      Reference used for storing consumer tail index.
 * @producer_head:      Reference used for storing the producer head index.
 *
 * This is the client interface for getting the current indexes of the
 * QPair from the point of the view of the caller as the consumer.
 */
int vmci_qpair_get_consume_indexes(const struct vmci_qp *qpair,
				   u64 *consumer_tail,
				   u64 *producer_head)
{
	struct vmci_queue_header *produce_q_header;
	struct vmci_queue_header *consume_q_header;
	int result;

	if (!qpair)
		return VMCI_ERROR_INVALID_ARGS;

	qp_lock(qpair);
	result =
	    qp_get_queue_headers(qpair, &produce_q_header, &consume_q_header);
	if (result == VMCI_SUCCESS)
		vmci_q_header_get_pointers(consume_q_header, produce_q_header,
					   consumer_tail, producer_head);
	qp_unlock(qpair);

	if (result == VMCI_SUCCESS &&
	    ((consumer_tail && *consumer_tail >= qpair->consume_q_size) ||
	     (producer_head && *producer_head >= qpair->consume_q_size)))
		return VMCI_ERROR_INVALID_SIZE;

	return result;
}
EXPORT_SYMBOL_GPL(vmci_qpair_get_consume_indexes);

/*
 * vmci_qpair_produce_free_space() - Retrieves free space in producer queue.
 * @qpair:      Pointer to the queue pair struct.
 *
 * This is the client interface for getting the amount of free
 * space in the QPair from the point of the view of the caller as
 * the producer which is the common case.  Returns < 0 if err, else
 * available bytes into which data can be enqueued if > 0.
 */
s64 vmci_qpair_produce_free_space(const struct vmci_qp *qpair)
{
	struct vmci_queue_header *produce_q_header;
	struct vmci_queue_header *consume_q_header;
	s64 result;

	if (!qpair)
		return VMCI_ERROR_INVALID_ARGS;

	qp_lock(qpair);
	result =
	    qp_get_queue_headers(qpair, &produce_q_header, &consume_q_header);
	if (result == VMCI_SUCCESS)
		result = vmci_q_header_free_space(produce_q_header,
						  consume_q_header,
						  qpair->produce_q_size);
	else
		result = 0;

	qp_unlock(qpair);

	return result;
}
EXPORT_SYMBOL_GPL(vmci_qpair_produce_free_space);

/*
 * vmci_qpair_consume_free_space() - Retrieves free space in consumer queue.
 * @qpair:      Pointer to the queue pair struct.
 *
 * This is the client interface for getting the amount of free
 * space in the QPair from the point of the view of the caller as
 * the consumer which is not the common case.  Returns < 0 if err, else
 * available bytes into which data can be enqueued if > 0.
 */
s64 vmci_qpair_consume_free_space(const struct vmci_qp *qpair)
{
	struct vmci_queue_header *produce_q_header;
	struct vmci_queue_header *consume_q_header;
	s64 result;

	if (!qpair)
		return VMCI_ERROR_INVALID_ARGS;

	qp_lock(qpair);
	result =
	    qp_get_queue_headers(qpair, &produce_q_header, &consume_q_header);
	if (result == VMCI_SUCCESS)
		result = vmci_q_header_free_space(consume_q_header,
						  produce_q_header,
						  qpair->consume_q_size);
	else
		result = 0;

	qp_unlock(qpair);

	return result;
}
EXPORT_SYMBOL_GPL(vmci_qpair_consume_free_space);

/*
 * vmci_qpair_produce_buf_ready() - Gets bytes ready to read from
 * producer queue.
 * @qpair:      Pointer to the queue pair struct.
 *
 * This is the client interface for getting the amount of
 * enqueued data in the QPair from the point of the view of the
 * caller as the producer which is not the common case.  Returns < 0 if err,
 * else available bytes that may be read.
 */
s64 vmci_qpair_produce_buf_ready(const struct vmci_qp *qpair)
{
	struct vmci_queue_header *produce_q_header;
	struct vmci_queue_header *consume_q_header;
	s64 result;

	if (!qpair)
		return VMCI_ERROR_INVALID_ARGS;

	qp_lock(qpair);
	result =
	    qp_get_queue_headers(qpair, &produce_q_header, &consume_q_header);
	if (result == VMCI_SUCCESS)
		result = vmci_q_header_buf_ready(produce_q_header,
						 consume_q_header,
						 qpair->produce_q_size);
	else
		result = 0;

	qp_unlock(qpair);

	return result;
}
EXPORT_SYMBOL_GPL(vmci_qpair_produce_buf_ready);

/*
 * vmci_qpair_consume_buf_ready() - Gets bytes ready to read from
 * consumer queue.
 * @qpair:      Pointer to the queue pair struct.
 *
 * This is the client interface for getting the amount of
 * enqueued data in the QPair from the point of the view of the
 * caller as the consumer which is the normal case.  Returns < 0 if err,
 * else available bytes that may be read.
 */
s64 vmci_qpair_consume_buf_ready(const struct vmci_qp *qpair)
{
	struct vmci_queue_header *produce_q_header;
	struct vmci_queue_header *consume_q_header;
	s64 result;

	if (!qpair)
		return VMCI_ERROR_INVALID_ARGS;

	qp_lock(qpair);
	result =
	    qp_get_queue_headers(qpair, &produce_q_header, &consume_q_header);
	if (result == VMCI_SUCCESS)
		result = vmci_q_header_buf_ready(consume_q_header,
						 produce_q_header,
						 qpair->consume_q_size);
	else
		result = 0;

	qp_unlock(qpair);

	return result;
}
EXPORT_SYMBOL_GPL(vmci_qpair_consume_buf_ready);

/*
 * vmci_qpair_enqueue() - Throw data on the queue.
 * @qpair:      Pointer to the queue pair struct.
 * @buf:        Pointer to buffer containing data
 * @buf_size:   Length of buffer.
 * @buf_type:   Buffer type (Unused).
 *
 * This is the client interface for enqueueing data into the queue.
 * Returns number of bytes enqueued or < 0 on error.
 */
ssize_t vmci_qpair_enqueue(struct vmci_qp *qpair,
			   const void *buf,
			   size_t buf_size,
			   int buf_type)
{
	ssize_t result;
	struct iov_iter from;
	struct kvec v = {.iov_base = (void *)buf, .iov_len = buf_size};

	if (!qpair || !buf)
		return VMCI_ERROR_INVALID_ARGS;

	iov_iter_kvec(&from, WRITE, &v, 1, buf_size);

	qp_lock(qpair);

	do {
		result = qp_enqueue_locked(qpair->produce_q,
					   qpair->consume_q,
					   qpair->produce_q_size,
					   &from);

		if (result == VMCI_ERROR_QUEUEPAIR_NOT_READY &&
		    !qp_wait_for_ready_queue(qpair))
			result = VMCI_ERROR_WOULD_BLOCK;

	} while (result == VMCI_ERROR_QUEUEPAIR_NOT_READY);

	qp_unlock(qpair);

	return result;
}
EXPORT_SYMBOL_GPL(vmci_qpair_enqueue);

/*
 * vmci_qpair_dequeue() - Get data from the queue.
 * @qpair:      Pointer to the queue pair struct.
 * @buf:        Pointer to buffer for the data
 * @buf_size:   Length of buffer.
 * @buf_type:   Buffer type (Unused).
 *
 * This is the client interface for dequeueing data from the queue.
 * Returns number of bytes dequeued or < 0 on error.
 */
ssize_t vmci_qpair_dequeue(struct vmci_qp *qpair,
			   void *buf,
			   size_t buf_size,
			   int buf_type)
{
	ssize_t result;
	struct iov_iter to;
	struct kvec v = {.iov_base = buf, .iov_len = buf_size};

	if (!qpair || !buf)
		return VMCI_ERROR_INVALID_ARGS;

	iov_iter_kvec(&to, READ, &v, 1, buf_size);

	qp_lock(qpair);

	do {
		result = qp_dequeue_locked(qpair->produce_q,
					   qpair->consume_q,
					   qpair->consume_q_size,
					   &to, true);

		if (result == VMCI_ERROR_QUEUEPAIR_NOT_READY &&
		    !qp_wait_for_ready_queue(qpair))
			result = VMCI_ERROR_WOULD_BLOCK;

	} while (result == VMCI_ERROR_QUEUEPAIR_NOT_READY);

	qp_unlock(qpair);

	return result;
}
EXPORT_SYMBOL_GPL(vmci_qpair_dequeue);

/*
 * vmci_qpair_peek() - Peek at the data in the queue.
 * @qpair:      Pointer to the queue pair struct.
 * @buf:        Pointer to buffer for the data
 * @buf_size:   Length of buffer.
 * @buf_type:   Buffer type (Unused on Linux).
 *
 * This is the client interface for peeking into a queue.  (I.e.,
 * copy data from the queue without updating the head pointer.)
 * Returns number of bytes dequeued or < 0 on error.
 */
ssize_t vmci_qpair_peek(struct vmci_qp *qpair,
			void *buf,
			size_t buf_size,
			int buf_type)
{
	struct iov_iter to;
	struct kvec v = {.iov_base = buf, .iov_len = buf_size};
	ssize_t result;

	if (!qpair || !buf)
		return VMCI_ERROR_INVALID_ARGS;

	iov_iter_kvec(&to, READ, &v, 1, buf_size);

	qp_lock(qpair);

	do {
		result = qp_dequeue_locked(qpair->produce_q,
					   qpair->consume_q,
					   qpair->consume_q_size,
					   &to, false);

		if (result == VMCI_ERROR_QUEUEPAIR_NOT_READY &&
		    !qp_wait_for_ready_queue(qpair))
			result = VMCI_ERROR_WOULD_BLOCK;

	} while (result == VMCI_ERROR_QUEUEPAIR_NOT_READY);

	qp_unlock(qpair);

	return result;
}
EXPORT_SYMBOL_GPL(vmci_qpair_peek);

/*
 * vmci_qpair_enquev() - Throw data on the queue using iov.
 * @qpair:      Pointer to the queue pair struct.
 * @iov:        Pointer to buffer containing data
 * @iov_size:   Length of buffer.
 * @buf_type:   Buffer type (Unused).
 *
 * This is the client interface for enqueueing data into the queue.
 * This function uses IO vectors to handle the work. Returns number
 * of bytes enqueued or < 0 on error.
 */
ssize_t vmci_qpair_enquev(struct vmci_qp *qpair,
			  struct msghdr *msg,
			  size_t iov_size,
			  int buf_type)
{
	ssize_t result;

	if (!qpair)
		return VMCI_ERROR_INVALID_ARGS;

	qp_lock(qpair);

	do {
		result = qp_enqueue_locked(qpair->produce_q,
					   qpair->consume_q,
					   qpair->produce_q_size,
					   &msg->msg_iter);

		if (result == VMCI_ERROR_QUEUEPAIR_NOT_READY &&
		    !qp_wait_for_ready_queue(qpair))
			result = VMCI_ERROR_WOULD_BLOCK;

	} while (result == VMCI_ERROR_QUEUEPAIR_NOT_READY);

	qp_unlock(qpair);

	return result;
}
EXPORT_SYMBOL_GPL(vmci_qpair_enquev);

/*
 * vmci_qpair_dequev() - Get data from the queue using iov.
 * @qpair:      Pointer to the queue pair struct.
 * @iov:        Pointer to buffer for the data
 * @iov_size:   Length of buffer.
 * @buf_type:   Buffer type (Unused).
 *
 * This is the client interface for dequeueing data from the queue.
 * This function uses IO vectors to handle the work. Returns number
 * of bytes dequeued or < 0 on error.
 */
ssize_t vmci_qpair_dequev(struct vmci_qp *qpair,
			  struct msghdr *msg,
			  size_t iov_size,
			  int buf_type)
{
	ssize_t result;

	if (!qpair)
		return VMCI_ERROR_INVALID_ARGS;

	qp_lock(qpair);

	do {
		result = qp_dequeue_locked(qpair->produce_q,
					   qpair->consume_q,
					   qpair->consume_q_size,
					   &msg->msg_iter, true);

		if (result == VMCI_ERROR_QUEUEPAIR_NOT_READY &&
		    !qp_wait_for_ready_queue(qpair))
			result = VMCI_ERROR_WOULD_BLOCK;

	} while (result == VMCI_ERROR_QUEUEPAIR_NOT_READY);

	qp_unlock(qpair);

	return result;
}
EXPORT_SYMBOL_GPL(vmci_qpair_dequev);

/*
 * vmci_qpair_peekv() - Peek at the data in the queue using iov.
 * @qpair:      Pointer to the queue pair struct.
 * @iov:        Pointer to buffer for the data
 * @iov_size:   Length of buffer.
 * @buf_type:   Buffer type (Unused on Linux).
 *
 * This is the client interface for peeking into a queue.  (I.e.,
 * copy data from the queue without updating the head pointer.)
 * This function uses IO vectors to handle the work. Returns number
 * of bytes peeked or < 0 on error.
 */
ssize_t vmci_qpair_peekv(struct vmci_qp *qpair,
			 struct msghdr *msg,
			 size_t iov_size,
			 int buf_type)
{
	ssize_t result;

	if (!qpair)
		return VMCI_ERROR_INVALID_ARGS;

	qp_lock(qpair);

	do {
		result = qp_dequeue_locked(qpair->produce_q,
					   qpair->consume_q,
					   qpair->consume_q_size,
					   &msg->msg_iter, false);

		if (result == VMCI_ERROR_QUEUEPAIR_NOT_READY &&
		    !qp_wait_for_ready_queue(qpair))
			result = VMCI_ERROR_WOULD_BLOCK;

	} while (result == VMCI_ERROR_QUEUEPAIR_NOT_READY);

	qp_unlock(qpair);
	return result;
}
EXPORT_SYMBOL_GPL(vmci_qpair_peekv);