aboutsummaryrefslogtreecommitdiff
path: root/migration/ram.c
blob: a7414170e5e71cd5e0abda567e1fbb8b150684e1 (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
3255
3256
3257
3258
3259
3260
3261
3262
3263
3264
3265
3266
3267
3268
3269
3270
3271
3272
3273
3274
3275
3276
3277
3278
3279
3280
3281
3282
3283
3284
3285
3286
3287
3288
3289
3290
3291
3292
3293
3294
3295
3296
3297
3298
3299
3300
3301
3302
3303
3304
3305
3306
3307
3308
3309
3310
3311
3312
3313
3314
3315
3316
3317
3318
3319
3320
3321
3322
3323
3324
3325
3326
3327
3328
3329
3330
3331
3332
3333
3334
3335
3336
3337
3338
3339
3340
3341
3342
3343
3344
3345
3346
3347
3348
3349
3350
3351
3352
3353
3354
3355
3356
3357
3358
3359
3360
3361
3362
3363
3364
3365
3366
3367
3368
3369
3370
3371
3372
3373
3374
3375
3376
3377
3378
3379
3380
3381
3382
3383
3384
3385
3386
3387
3388
3389
3390
3391
3392
3393
3394
3395
3396
3397
3398
3399
3400
3401
3402
3403
3404
3405
3406
3407
3408
3409
3410
3411
3412
3413
3414
3415
3416
3417
3418
3419
3420
3421
3422
3423
3424
3425
3426
3427
3428
3429
3430
3431
3432
3433
3434
3435
3436
3437
3438
3439
3440
3441
3442
3443
3444
3445
3446
3447
3448
3449
3450
3451
3452
3453
3454
3455
3456
3457
3458
3459
3460
3461
3462
3463
3464
3465
3466
3467
3468
3469
3470
3471
3472
3473
3474
3475
3476
3477
3478
3479
3480
3481
3482
3483
3484
3485
3486
3487
3488
3489
3490
3491
3492
3493
3494
3495
3496
3497
3498
3499
3500
3501
3502
3503
3504
3505
3506
3507
3508
3509
3510
3511
3512
3513
3514
3515
3516
3517
3518
3519
3520
3521
3522
3523
3524
3525
3526
3527
3528
3529
3530
3531
3532
3533
3534
3535
3536
3537
3538
3539
3540
3541
3542
3543
3544
3545
3546
3547
3548
3549
3550
3551
3552
3553
3554
3555
3556
3557
3558
3559
3560
3561
3562
3563
3564
3565
3566
3567
3568
3569
3570
3571
3572
3573
3574
3575
3576
3577
3578
3579
3580
3581
3582
3583
3584
3585
3586
3587
3588
3589
3590
3591
3592
3593
3594
3595
3596
3597
3598
3599
3600
3601
3602
3603
3604
3605
3606
3607
3608
3609
3610
3611
3612
3613
3614
3615
3616
3617
3618
3619
3620
3621
3622
3623
3624
3625
3626
3627
3628
3629
3630
3631
3632
3633
3634
3635
3636
3637
3638
3639
3640
3641
3642
3643
3644
3645
3646
3647
3648
3649
3650
3651
3652
3653
3654
3655
3656
3657
3658
3659
3660
3661
3662
3663
3664
3665
3666
3667
3668
3669
3670
3671
3672
3673
3674
3675
3676
3677
3678
3679
3680
3681
3682
3683
3684
3685
3686
3687
3688
3689
3690
3691
3692
3693
3694
3695
3696
3697
3698
3699
3700
3701
3702
3703
3704
3705
3706
3707
3708
3709
3710
3711
3712
3713
3714
3715
3716
3717
3718
3719
3720
3721
3722
3723
3724
3725
3726
3727
3728
3729
3730
3731
3732
3733
3734
3735
3736
3737
3738
3739
3740
3741
3742
3743
3744
3745
3746
3747
3748
3749
3750
3751
3752
3753
3754
3755
3756
3757
3758
3759
3760
3761
3762
3763
3764
3765
3766
3767
3768
3769
3770
3771
3772
3773
3774
3775
3776
3777
3778
3779
3780
3781
3782
3783
3784
3785
3786
3787
3788
3789
3790
3791
3792
3793
3794
3795
3796
3797
3798
3799
3800
3801
3802
3803
3804
3805
3806
3807
3808
3809
3810
3811
3812
3813
3814
3815
3816
3817
3818
3819
3820
3821
3822
3823
3824
3825
3826
3827
3828
3829
3830
3831
3832
3833
3834
3835
3836
3837
3838
3839
3840
3841
3842
3843
3844
3845
3846
3847
3848
3849
3850
3851
3852
3853
3854
3855
3856
3857
3858
3859
3860
3861
3862
3863
3864
3865
3866
3867
3868
3869
3870
3871
3872
3873
3874
3875
3876
3877
3878
3879
3880
3881
3882
3883
3884
3885
3886
3887
3888
3889
3890
3891
3892
3893
3894
3895
3896
3897
3898
3899
3900
3901
3902
3903
3904
3905
3906
3907
3908
3909
3910
3911
3912
3913
3914
3915
3916
3917
3918
3919
3920
3921
3922
3923
3924
3925
3926
3927
3928
3929
3930
3931
3932
3933
3934
3935
3936
3937
3938
3939
3940
3941
3942
3943
3944
3945
3946
3947
3948
3949
3950
3951
3952
3953
3954
3955
3956
3957
3958
3959
3960
3961
3962
3963
3964
3965
3966
3967
3968
3969
3970
3971
3972
3973
3974
3975
3976
3977
3978
3979
3980
3981
3982
3983
3984
3985
3986
3987
3988
3989
3990
3991
3992
3993
3994
3995
3996
3997
3998
3999
4000
4001
4002
4003
4004
4005
4006
4007
4008
4009
4010
4011
4012
4013
4014
4015
4016
4017
4018
4019
4020
4021
4022
4023
4024
4025
4026
4027
4028
4029
4030
4031
4032
4033
4034
4035
4036
4037
4038
4039
4040
4041
4042
4043
4044
4045
4046
4047
4048
4049
4050
4051
4052
4053
4054
4055
4056
4057
4058
4059
4060
4061
4062
4063
4064
4065
4066
4067
4068
4069
4070
4071
4072
4073
4074
4075
4076
4077
4078
4079
4080
4081
4082
4083
4084
4085
4086
4087
4088
4089
4090
4091
4092
4093
4094
4095
4096
4097
4098
4099
4100
4101
4102
4103
4104
4105
4106
4107
4108
4109
4110
4111
4112
4113
4114
4115
4116
4117
4118
4119
4120
4121
4122
4123
4124
4125
4126
4127
4128
4129
4130
4131
4132
4133
4134
4135
4136
4137
4138
4139
4140
4141
4142
4143
4144
4145
4146
4147
4148
4149
4150
4151
4152
4153
4154
4155
4156
4157
4158
4159
4160
4161
4162
4163
4164
4165
4166
4167
4168
4169
4170
4171
4172
4173
4174
4175
4176
4177
4178
4179
4180
4181
4182
4183
4184
4185
4186
4187
4188
4189
4190
4191
4192
4193
4194
4195
4196
4197
4198
4199
4200
4201
4202
4203
4204
4205
4206
4207
4208
4209
4210
4211
4212
4213
4214
4215
4216
4217
4218
4219
4220
4221
4222
4223
4224
4225
4226
4227
4228
4229
4230
4231
4232
4233
4234
4235
4236
4237
4238
4239
4240
4241
4242
4243
4244
4245
4246
4247
4248
4249
4250
4251
4252
4253
4254
4255
4256
4257
4258
4259
4260
4261
4262
4263
4264
4265
4266
4267
4268
4269
4270
4271
4272
4273
4274
4275
4276
4277
4278
4279
4280
4281
4282
4283
4284
4285
4286
4287
4288
4289
4290
4291
4292
4293
4294
4295
4296
4297
4298
4299
4300
4301
4302
4303
4304
4305
4306
4307
4308
4309
4310
4311
4312
4313
4314
4315
4316
4317
4318
4319
4320
4321
4322
4323
4324
4325
4326
4327
4328
4329
4330
4331
4332
4333
4334
4335
4336
4337
4338
4339
4340
4341
4342
4343
4344
4345
4346
4347
4348
4349
4350
4351
4352
4353
4354
4355
4356
4357
4358
4359
4360
4361
4362
4363
4364
4365
4366
4367
4368
4369
4370
4371
4372
4373
4374
4375
4376
4377
4378
4379
4380
4381
4382
4383
4384
4385
4386
4387
4388
4389
4390
4391
4392
4393
4394
4395
4396
4397
4398
4399
4400
4401
4402
4403
4404
4405
4406
4407
4408
4409
4410
4411
4412
4413
4414
4415
4416
4417
4418
4419
4420
4421
4422
4423
4424
4425
4426
4427
4428
4429
4430
4431
4432
4433
4434
4435
4436
4437
4438
4439
4440
4441
4442
4443
4444
4445
4446
4447
4448
4449
4450
4451
4452
4453
4454
4455
4456
4457
4458
4459
4460
4461
4462
4463
4464
4465
4466
4467
4468
4469
4470
4471
4472
4473
4474
4475
4476
4477
4478
4479
4480
4481
4482
4483
4484
4485
4486
4487
4488
4489
4490
4491
4492
4493
4494
4495
4496
4497
4498
4499
4500
4501
4502
4503
4504
4505
4506
4507
4508
4509
4510
4511
4512
4513
4514
4515
4516
4517
4518
4519
4520
4521
4522
4523
4524
4525
4526
4527
4528
4529
4530
4531
4532
4533
4534
4535
4536
4537
4538
4539
4540
4541
4542
4543
4544
4545
4546
4547
4548
4549
4550
4551
4552
4553
4554
4555
4556
4557
4558
4559
4560
4561
4562
4563
4564
4565
4566
4567
4568
4569
4570
4571
4572
4573
4574
4575
4576
4577
4578
4579
4580
4581
4582
4583
4584
4585
4586
4587
4588
4589
4590
4591
4592
4593
4594
4595
4596
4597
4598
4599
4600
4601
4602
4603
4604
4605
4606
4607
4608
4609
4610
4611
4612
4613
4614
4615
4616
4617
4618
4619
4620
4621
4622
4623
4624
4625
4626
4627
4628
4629
4630
4631
4632
4633
4634
4635
4636
/*
 * QEMU System Emulator
 *
 * Copyright (c) 2003-2008 Fabrice Bellard
 * Copyright (c) 2011-2015 Red Hat Inc
 *
 * Authors:
 *  Juan Quintela <quintela@redhat.com>
 *
 * Permission is hereby granted, free of charge, to any person obtaining a copy
 * of this software and associated documentation files (the "Software"), to deal
 * in the Software without restriction, including without limitation the rights
 * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
 * copies of the Software, and to permit persons to whom the Software is
 * furnished to do so, subject to the following conditions:
 *
 * The above copyright notice and this permission notice shall be included in
 * all copies or substantial portions of the Software.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
 * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
 * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
 * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
 * THE SOFTWARE.
 */

#include "qemu/osdep.h"
#include "cpu.h"
#include <zlib.h>
#include "qemu/cutils.h"
#include "qemu/bitops.h"
#include "qemu/bitmap.h"
#include "qemu/main-loop.h"
#include "xbzrle.h"
#include "ram.h"
#include "migration.h"
#include "socket.h"
#include "migration/register.h"
#include "migration/misc.h"
#include "qemu-file.h"
#include "postcopy-ram.h"
#include "page_cache.h"
#include "qemu/error-report.h"
#include "qapi/error.h"
#include "qapi/qapi-events-migration.h"
#include "qapi/qmp/qerror.h"
#include "trace.h"
#include "exec/ram_addr.h"
#include "exec/target_page.h"
#include "qemu/rcu_queue.h"
#include "migration/colo.h"
#include "block.h"
#include "sysemu/sysemu.h"
#include "qemu/uuid.h"
#include "savevm.h"
#include "qemu/iov.h"

/***********************************************************/
/* ram save/restore */

/* RAM_SAVE_FLAG_ZERO used to be named RAM_SAVE_FLAG_COMPRESS, it
 * worked for pages that where filled with the same char.  We switched
 * it to only search for the zero value.  And to avoid confusion with
 * RAM_SSAVE_FLAG_COMPRESS_PAGE just rename it.
 */

#define RAM_SAVE_FLAG_FULL     0x01 /* Obsolete, not used anymore */
#define RAM_SAVE_FLAG_ZERO     0x02
#define RAM_SAVE_FLAG_MEM_SIZE 0x04
#define RAM_SAVE_FLAG_PAGE     0x08
#define RAM_SAVE_FLAG_EOS      0x10
#define RAM_SAVE_FLAG_CONTINUE 0x20
#define RAM_SAVE_FLAG_XBZRLE   0x40
/* 0x80 is reserved in migration.h start with 0x100 next */
#define RAM_SAVE_FLAG_COMPRESS_PAGE    0x100

static inline bool is_zero_range(uint8_t *p, uint64_t size)
{
    return buffer_is_zero(p, size);
}

XBZRLECacheStats xbzrle_counters;

/* struct contains XBZRLE cache and a static page
   used by the compression */
static struct {
    /* buffer used for XBZRLE encoding */
    uint8_t *encoded_buf;
    /* buffer for storing page content */
    uint8_t *current_buf;
    /* Cache for XBZRLE, Protected by lock. */
    PageCache *cache;
    QemuMutex lock;
    /* it will store a page full of zeros */
    uint8_t *zero_target_page;
    /* buffer used for XBZRLE decoding */
    uint8_t *decoded_buf;
} XBZRLE;

static void XBZRLE_cache_lock(void)
{
    if (migrate_use_xbzrle())
        qemu_mutex_lock(&XBZRLE.lock);
}

static void XBZRLE_cache_unlock(void)
{
    if (migrate_use_xbzrle())
        qemu_mutex_unlock(&XBZRLE.lock);
}

/**
 * xbzrle_cache_resize: resize the xbzrle cache
 *
 * This function is called from qmp_migrate_set_cache_size in main
 * thread, possibly while a migration is in progress.  A running
 * migration may be using the cache and might finish during this call,
 * hence changes to the cache are protected by XBZRLE.lock().
 *
 * Returns 0 for success or -1 for error
 *
 * @new_size: new cache size
 * @errp: set *errp if the check failed, with reason
 */
int xbzrle_cache_resize(int64_t new_size, Error **errp)
{
    PageCache *new_cache;
    int64_t ret = 0;

    /* Check for truncation */
    if (new_size != (size_t)new_size) {
        error_setg(errp, QERR_INVALID_PARAMETER_VALUE, "cache size",
                   "exceeding address space");
        return -1;
    }

    if (new_size == migrate_xbzrle_cache_size()) {
        /* nothing to do */
        return 0;
    }

    XBZRLE_cache_lock();

    if (XBZRLE.cache != NULL) {
        new_cache = cache_init(new_size, TARGET_PAGE_SIZE, errp);
        if (!new_cache) {
            ret = -1;
            goto out;
        }

        cache_fini(XBZRLE.cache);
        XBZRLE.cache = new_cache;
    }
out:
    XBZRLE_cache_unlock();
    return ret;
}

static bool ramblock_is_ignored(RAMBlock *block)
{
    return !qemu_ram_is_migratable(block) ||
           (migrate_ignore_shared() && qemu_ram_is_shared(block));
}

/* Should be holding either ram_list.mutex, or the RCU lock. */
#define RAMBLOCK_FOREACH_NOT_IGNORED(block)            \
    INTERNAL_RAMBLOCK_FOREACH(block)                   \
        if (ramblock_is_ignored(block)) {} else

#define RAMBLOCK_FOREACH_MIGRATABLE(block)             \
    INTERNAL_RAMBLOCK_FOREACH(block)                   \
        if (!qemu_ram_is_migratable(block)) {} else

#undef RAMBLOCK_FOREACH

int foreach_not_ignored_block(RAMBlockIterFunc func, void *opaque)
{
    RAMBlock *block;
    int ret = 0;

    RCU_READ_LOCK_GUARD();

    RAMBLOCK_FOREACH_NOT_IGNORED(block) {
        ret = func(block, opaque);
        if (ret) {
            break;
        }
    }
    return ret;
}

static void ramblock_recv_map_init(void)
{
    RAMBlock *rb;

    RAMBLOCK_FOREACH_NOT_IGNORED(rb) {
        assert(!rb->receivedmap);
        rb->receivedmap = bitmap_new(rb->max_length >> qemu_target_page_bits());
    }
}

int ramblock_recv_bitmap_test(RAMBlock *rb, void *host_addr)
{
    return test_bit(ramblock_recv_bitmap_offset(host_addr, rb),
                    rb->receivedmap);
}

bool ramblock_recv_bitmap_test_byte_offset(RAMBlock *rb, uint64_t byte_offset)
{
    return test_bit(byte_offset >> TARGET_PAGE_BITS, rb->receivedmap);
}

void ramblock_recv_bitmap_set(RAMBlock *rb, void *host_addr)
{
    set_bit_atomic(ramblock_recv_bitmap_offset(host_addr, rb), rb->receivedmap);
}

void ramblock_recv_bitmap_set_range(RAMBlock *rb, void *host_addr,
                                    size_t nr)
{
    bitmap_set_atomic(rb->receivedmap,
                      ramblock_recv_bitmap_offset(host_addr, rb),
                      nr);
}

#define  RAMBLOCK_RECV_BITMAP_ENDING  (0x0123456789abcdefULL)

/*
 * Format: bitmap_size (8 bytes) + whole_bitmap (N bytes).
 *
 * Returns >0 if success with sent bytes, or <0 if error.
 */
int64_t ramblock_recv_bitmap_send(QEMUFile *file,
                                  const char *block_name)
{
    RAMBlock *block = qemu_ram_block_by_name(block_name);
    unsigned long *le_bitmap, nbits;
    uint64_t size;

    if (!block) {
        error_report("%s: invalid block name: %s", __func__, block_name);
        return -1;
    }

    nbits = block->used_length >> TARGET_PAGE_BITS;

    /*
     * Make sure the tmp bitmap buffer is big enough, e.g., on 32bit
     * machines we may need 4 more bytes for padding (see below
     * comment). So extend it a bit before hand.
     */
    le_bitmap = bitmap_new(nbits + BITS_PER_LONG);

    /*
     * Always use little endian when sending the bitmap. This is
     * required that when source and destination VMs are not using the
     * same endianess. (Note: big endian won't work.)
     */
    bitmap_to_le(le_bitmap, block->receivedmap, nbits);

    /* Size of the bitmap, in bytes */
    size = DIV_ROUND_UP(nbits, 8);

    /*
     * size is always aligned to 8 bytes for 64bit machines, but it
     * may not be true for 32bit machines. We need this padding to
     * make sure the migration can survive even between 32bit and
     * 64bit machines.
     */
    size = ROUND_UP(size, 8);

    qemu_put_be64(file, size);
    qemu_put_buffer(file, (const uint8_t *)le_bitmap, size);
    /*
     * Mark as an end, in case the middle part is screwed up due to
     * some "misterious" reason.
     */
    qemu_put_be64(file, RAMBLOCK_RECV_BITMAP_ENDING);
    qemu_fflush(file);

    g_free(le_bitmap);

    if (qemu_file_get_error(file)) {
        return qemu_file_get_error(file);
    }

    return size + sizeof(size);
}

/*
 * An outstanding page request, on the source, having been received
 * and queued
 */
struct RAMSrcPageRequest {
    RAMBlock *rb;
    hwaddr    offset;
    hwaddr    len;

    QSIMPLEQ_ENTRY(RAMSrcPageRequest) next_req;
};

/* State of RAM for migration */
struct RAMState {
    /* QEMUFile used for this migration */
    QEMUFile *f;
    /* Last block that we have visited searching for dirty pages */
    RAMBlock *last_seen_block;
    /* Last block from where we have sent data */
    RAMBlock *last_sent_block;
    /* Last dirty target page we have sent */
    ram_addr_t last_page;
    /* last ram version we have seen */
    uint32_t last_version;
    /* We are in the first round */
    bool ram_bulk_stage;
    /* The free page optimization is enabled */
    bool fpo_enabled;
    /* How many times we have dirty too many pages */
    int dirty_rate_high_cnt;
    /* these variables are used for bitmap sync */
    /* last time we did a full bitmap_sync */
    int64_t time_last_bitmap_sync;
    /* bytes transferred at start_time */
    uint64_t bytes_xfer_prev;
    /* number of dirty pages since start_time */
    uint64_t num_dirty_pages_period;
    /* xbzrle misses since the beginning of the period */
    uint64_t xbzrle_cache_miss_prev;

    /* compression statistics since the beginning of the period */
    /* amount of count that no free thread to compress data */
    uint64_t compress_thread_busy_prev;
    /* amount bytes after compression */
    uint64_t compressed_size_prev;
    /* amount of compressed pages */
    uint64_t compress_pages_prev;

    /* total handled target pages at the beginning of period */
    uint64_t target_page_count_prev;
    /* total handled target pages since start */
    uint64_t target_page_count;
    /* number of dirty bits in the bitmap */
    uint64_t migration_dirty_pages;
    /* Protects modification of the bitmap and migration dirty pages */
    QemuMutex bitmap_mutex;
    /* The RAMBlock used in the last src_page_requests */
    RAMBlock *last_req_rb;
    /* Queue of outstanding page requests from the destination */
    QemuMutex src_page_req_mutex;
    QSIMPLEQ_HEAD(, RAMSrcPageRequest) src_page_requests;
};
typedef struct RAMState RAMState;

static RAMState *ram_state;

static NotifierWithReturnList precopy_notifier_list;

void precopy_infrastructure_init(void)
{
    notifier_with_return_list_init(&precopy_notifier_list);
}

void precopy_add_notifier(NotifierWithReturn *n)
{
    notifier_with_return_list_add(&precopy_notifier_list, n);
}

void precopy_remove_notifier(NotifierWithReturn *n)
{
    notifier_with_return_remove(n);
}

int precopy_notify(PrecopyNotifyReason reason, Error **errp)
{
    PrecopyNotifyData pnd;
    pnd.reason = reason;
    pnd.errp = errp;

    return notifier_with_return_list_notify(&precopy_notifier_list, &pnd);
}

void precopy_enable_free_page_optimization(void)
{
    if (!ram_state) {
        return;
    }

    ram_state->fpo_enabled = true;
}

uint64_t ram_bytes_remaining(void)
{
    return ram_state ? (ram_state->migration_dirty_pages * TARGET_PAGE_SIZE) :
                       0;
}

MigrationStats ram_counters;

/* used by the search for pages to send */
struct PageSearchStatus {
    /* Current block being searched */
    RAMBlock    *block;
    /* Current page to search from */
    unsigned long page;
    /* Set once we wrap around */
    bool         complete_round;
};
typedef struct PageSearchStatus PageSearchStatus;

CompressionStats compression_counters;

struct CompressParam {
    bool done;
    bool quit;
    bool zero_page;
    QEMUFile *file;
    QemuMutex mutex;
    QemuCond cond;
    RAMBlock *block;
    ram_addr_t offset;

    /* internally used fields */
    z_stream stream;
    uint8_t *originbuf;
};
typedef struct CompressParam CompressParam;

struct DecompressParam {
    bool done;
    bool quit;
    QemuMutex mutex;
    QemuCond cond;
    void *des;
    uint8_t *compbuf;
    int len;
    z_stream stream;
};
typedef struct DecompressParam DecompressParam;

static CompressParam *comp_param;
static QemuThread *compress_threads;
/* comp_done_cond is used to wake up the migration thread when
 * one of the compression threads has finished the compression.
 * comp_done_lock is used to co-work with comp_done_cond.
 */
static QemuMutex comp_done_lock;
static QemuCond comp_done_cond;
/* The empty QEMUFileOps will be used by file in CompressParam */
static const QEMUFileOps empty_ops = { };

static QEMUFile *decomp_file;
static DecompressParam *decomp_param;
static QemuThread *decompress_threads;
static QemuMutex decomp_done_lock;
static QemuCond decomp_done_cond;

static bool do_compress_ram_page(QEMUFile *f, z_stream *stream, RAMBlock *block,
                                 ram_addr_t offset, uint8_t *source_buf);

static void *do_data_compress(void *opaque)
{
    CompressParam *param = opaque;
    RAMBlock *block;
    ram_addr_t offset;
    bool zero_page;

    qemu_mutex_lock(&param->mutex);
    while (!param->quit) {
        if (param->block) {
            block = param->block;
            offset = param->offset;
            param->block = NULL;
            qemu_mutex_unlock(&param->mutex);

            zero_page = do_compress_ram_page(param->file, &param->stream,
                                             block, offset, param->originbuf);

            qemu_mutex_lock(&comp_done_lock);
            param->done = true;
            param->zero_page = zero_page;
            qemu_cond_signal(&comp_done_cond);
            qemu_mutex_unlock(&comp_done_lock);

            qemu_mutex_lock(&param->mutex);
        } else {
            qemu_cond_wait(&param->cond, &param->mutex);
        }
    }
    qemu_mutex_unlock(&param->mutex);

    return NULL;
}

static void compress_threads_save_cleanup(void)
{
    int i, thread_count;

    if (!migrate_use_compression() || !comp_param) {
        return;
    }

    thread_count = migrate_compress_threads();
    for (i = 0; i < thread_count; i++) {
        /*
         * we use it as a indicator which shows if the thread is
         * properly init'd or not
         */
        if (!comp_param[i].file) {
            break;
        }

        qemu_mutex_lock(&comp_param[i].mutex);
        comp_param[i].quit = true;
        qemu_cond_signal(&comp_param[i].cond);
        qemu_mutex_unlock(&comp_param[i].mutex);

        qemu_thread_join(compress_threads + i);
        qemu_mutex_destroy(&comp_param[i].mutex);
        qemu_cond_destroy(&comp_param[i].cond);
        deflateEnd(&comp_param[i].stream);
        g_free(comp_param[i].originbuf);
        qemu_fclose(comp_param[i].file);
        comp_param[i].file = NULL;
    }
    qemu_mutex_destroy(&comp_done_lock);
    qemu_cond_destroy(&comp_done_cond);
    g_free(compress_threads);
    g_free(comp_param);
    compress_threads = NULL;
    comp_param = NULL;
}

static int compress_threads_save_setup(void)
{
    int i, thread_count;

    if (!migrate_use_compression()) {
        return 0;
    }
    thread_count = migrate_compress_threads();
    compress_threads = g_new0(QemuThread, thread_count);
    comp_param = g_new0(CompressParam, thread_count);
    qemu_cond_init(&comp_done_cond);
    qemu_mutex_init(&comp_done_lock);
    for (i = 0; i < thread_count; i++) {
        comp_param[i].originbuf = g_try_malloc(TARGET_PAGE_SIZE);
        if (!comp_param[i].originbuf) {
            goto exit;
        }

        if (deflateInit(&comp_param[i].stream,
                        migrate_compress_level()) != Z_OK) {
            g_free(comp_param[i].originbuf);
            goto exit;
        }

        /* comp_param[i].file is just used as a dummy buffer to save data,
         * set its ops to empty.
         */
        comp_param[i].file = qemu_fopen_ops(NULL, &empty_ops);
        comp_param[i].done = true;
        comp_param[i].quit = false;
        qemu_mutex_init(&comp_param[i].mutex);
        qemu_cond_init(&comp_param[i].cond);
        qemu_thread_create(compress_threads + i, "compress",
                           do_data_compress, comp_param + i,
                           QEMU_THREAD_JOINABLE);
    }
    return 0;

exit:
    compress_threads_save_cleanup();
    return -1;
}

/* Multiple fd's */

#define MULTIFD_MAGIC 0x11223344U
#define MULTIFD_VERSION 1

#define MULTIFD_FLAG_SYNC (1 << 0)

/* This value needs to be a multiple of qemu_target_page_size() */
#define MULTIFD_PACKET_SIZE (512 * 1024)

typedef struct {
    uint32_t magic;
    uint32_t version;
    unsigned char uuid[16]; /* QemuUUID */
    uint8_t id;
    uint8_t unused1[7];     /* Reserved for future use */
    uint64_t unused2[4];    /* Reserved for future use */
} __attribute__((packed)) MultiFDInit_t;

typedef struct {
    uint32_t magic;
    uint32_t version;
    uint32_t flags;
    /* maximum number of allocated pages */
    uint32_t pages_alloc;
    uint32_t pages_used;
    /* size of the next packet that contains pages */
    uint32_t next_packet_size;
    uint64_t packet_num;
    uint64_t unused[4];    /* Reserved for future use */
    char ramblock[256];
    uint64_t offset[];
} __attribute__((packed)) MultiFDPacket_t;

typedef struct {
    /* number of used pages */
    uint32_t used;
    /* number of allocated pages */
    uint32_t allocated;
    /* global number of generated multifd packets */
    uint64_t packet_num;
    /* offset of each page */
    ram_addr_t *offset;
    /* pointer to each page */
    struct iovec *iov;
    RAMBlock *block;
} MultiFDPages_t;

typedef struct {
    /* this fields are not changed once the thread is created */
    /* channel number */
    uint8_t id;
    /* channel thread name */
    char *name;
    /* channel thread id */
    QemuThread thread;
    /* communication channel */
    QIOChannel *c;
    /* sem where to wait for more work */
    QemuSemaphore sem;
    /* this mutex protects the following parameters */
    QemuMutex mutex;
    /* is this channel thread running */
    bool running;
    /* should this thread finish */
    bool quit;
    /* thread has work to do */
    int pending_job;
    /* array of pages to sent */
    MultiFDPages_t *pages;
    /* packet allocated len */
    uint32_t packet_len;
    /* pointer to the packet */
    MultiFDPacket_t *packet;
    /* multifd flags for each packet */
    uint32_t flags;
    /* size of the next packet that contains pages */
    uint32_t next_packet_size;
    /* global number of generated multifd packets */
    uint64_t packet_num;
    /* thread local variables */
    /* packets sent through this channel */
    uint64_t num_packets;
    /* pages sent through this channel */
    uint64_t num_pages;
    /* syncs main thread and channels */
    QemuSemaphore sem_sync;
}  MultiFDSendParams;

typedef struct {
    /* this fields are not changed once the thread is created */
    /* channel number */
    uint8_t id;
    /* channel thread name */
    char *name;
    /* channel thread id */
    QemuThread thread;
    /* communication channel */
    QIOChannel *c;
    /* this mutex protects the following parameters */
    QemuMutex mutex;
    /* is this channel thread running */
    bool running;
    /* should this thread finish */
    bool quit;
    /* array of pages to receive */
    MultiFDPages_t *pages;
    /* packet allocated len */
    uint32_t packet_len;
    /* pointer to the packet */
    MultiFDPacket_t *packet;
    /* multifd flags for each packet */
    uint32_t flags;
    /* global number of generated multifd packets */
    uint64_t packet_num;
    /* thread local variables */
    /* size of the next packet that contains pages */
    uint32_t next_packet_size;
    /* packets sent through this channel */
    uint64_t num_packets;
    /* pages sent through this channel */
    uint64_t num_pages;
    /* syncs main thread and channels */
    QemuSemaphore sem_sync;
} MultiFDRecvParams;

static int multifd_send_initial_packet(MultiFDSendParams *p, Error **errp)
{
    MultiFDInit_t msg = {};
    int ret;

    msg.magic = cpu_to_be32(MULTIFD_MAGIC);
    msg.version = cpu_to_be32(MULTIFD_VERSION);
    msg.id = p->id;
    memcpy(msg.uuid, &qemu_uuid.data, sizeof(msg.uuid));

    ret = qio_channel_write_all(p->c, (char *)&msg, sizeof(msg), errp);
    if (ret != 0) {
        return -1;
    }
    return 0;
}

static int multifd_recv_initial_packet(QIOChannel *c, Error **errp)
{
    MultiFDInit_t msg;
    int ret;

    ret = qio_channel_read_all(c, (char *)&msg, sizeof(msg), errp);
    if (ret != 0) {
        return -1;
    }

    msg.magic = be32_to_cpu(msg.magic);
    msg.version = be32_to_cpu(msg.version);

    if (msg.magic != MULTIFD_MAGIC) {
        error_setg(errp, "multifd: received packet magic %x "
                   "expected %x", msg.magic, MULTIFD_MAGIC);
        return -1;
    }

    if (msg.version != MULTIFD_VERSION) {
        error_setg(errp, "multifd: received packet version %d "
                   "expected %d", msg.version, MULTIFD_VERSION);
        return -1;
    }

    if (memcmp(msg.uuid, &qemu_uuid, sizeof(qemu_uuid))) {
        char *uuid = qemu_uuid_unparse_strdup(&qemu_uuid);
        char *msg_uuid = qemu_uuid_unparse_strdup((const QemuUUID *)msg.uuid);

        error_setg(errp, "multifd: received uuid '%s' and expected "
                   "uuid '%s' for channel %hhd", msg_uuid, uuid, msg.id);
        g_free(uuid);
        g_free(msg_uuid);
        return -1;
    }

    if (msg.id > migrate_multifd_channels()) {
        error_setg(errp, "multifd: received channel version %d "
                   "expected %d", msg.version, MULTIFD_VERSION);
        return -1;
    }

    return msg.id;
}

static MultiFDPages_t *multifd_pages_init(size_t size)
{
    MultiFDPages_t *pages = g_new0(MultiFDPages_t, 1);

    pages->allocated = size;
    pages->iov = g_new0(struct iovec, size);
    pages->offset = g_new0(ram_addr_t, size);

    return pages;
}

static void multifd_pages_clear(MultiFDPages_t *pages)
{
    pages->used = 0;
    pages->allocated = 0;
    pages->packet_num = 0;
    pages->block = NULL;
    g_free(pages->iov);
    pages->iov = NULL;
    g_free(pages->offset);
    pages->offset = NULL;
    g_free(pages);
}

static void multifd_send_fill_packet(MultiFDSendParams *p)
{
    MultiFDPacket_t *packet = p->packet;
    int i;

    packet->flags = cpu_to_be32(p->flags);
    packet->pages_alloc = cpu_to_be32(p->pages->allocated);
    packet->pages_used = cpu_to_be32(p->pages->used);
    packet->next_packet_size = cpu_to_be32(p->next_packet_size);
    packet->packet_num = cpu_to_be64(p->packet_num);

    if (p->pages->block) {
        strncpy(packet->ramblock, p->pages->block->idstr, 256);
    }

    for (i = 0; i < p->pages->used; i++) {
        packet->offset[i] = cpu_to_be64(p->pages->offset[i]);
    }
}

static int multifd_recv_unfill_packet(MultiFDRecvParams *p, Error **errp)
{
    MultiFDPacket_t *packet = p->packet;
    uint32_t pages_max = MULTIFD_PACKET_SIZE / qemu_target_page_size();
    RAMBlock *block;
    int i;

    packet->magic = be32_to_cpu(packet->magic);
    if (packet->magic != MULTIFD_MAGIC) {
        error_setg(errp, "multifd: received packet "
                   "magic %x and expected magic %x",
                   packet->magic, MULTIFD_MAGIC);
        return -1;
    }

    packet->version = be32_to_cpu(packet->version);
    if (packet->version != MULTIFD_VERSION) {
        error_setg(errp, "multifd: received packet "
                   "version %d and expected version %d",
                   packet->version, MULTIFD_VERSION);
        return -1;
    }

    p->flags = be32_to_cpu(packet->flags);

    packet->pages_alloc = be32_to_cpu(packet->pages_alloc);
    /*
     * If we received a packet that is 100 times bigger than expected
     * just stop migration.  It is a magic number.
     */
    if (packet->pages_alloc > pages_max * 100) {
        error_setg(errp, "multifd: received packet "
                   "with size %d and expected a maximum size of %d",
                   packet->pages_alloc, pages_max * 100) ;
        return -1;
    }
    /*
     * We received a packet that is bigger than expected but inside
     * reasonable limits (see previous comment).  Just reallocate.
     */
    if (packet->pages_alloc > p->pages->allocated) {
        multifd_pages_clear(p->pages);
        p->pages = multifd_pages_init(packet->pages_alloc);
    }

    p->pages->used = be32_to_cpu(packet->pages_used);
    if (p->pages->used > packet->pages_alloc) {
        error_setg(errp, "multifd: received packet "
                   "with %d pages and expected maximum pages are %d",
                   p->pages->used, packet->pages_alloc) ;
        return -1;
    }

    p->next_packet_size = be32_to_cpu(packet->next_packet_size);
    p->packet_num = be64_to_cpu(packet->packet_num);

    if (p->pages->used == 0) {
        return 0;
    }

    /* make sure that ramblock is 0 terminated */
    packet->ramblock[255] = 0;
    block = qemu_ram_block_by_name(packet->ramblock);
    if (!block) {
        error_setg(errp, "multifd: unknown ram block %s",
                   packet->ramblock);
        return -1;
    }

    for (i = 0; i < p->pages->used; i++) {
        ram_addr_t offset = be64_to_cpu(packet->offset[i]);

        if (offset > (block->used_length - TARGET_PAGE_SIZE)) {
            error_setg(errp, "multifd: offset too long " RAM_ADDR_FMT
                       " (max " RAM_ADDR_FMT ")",
                       offset, block->max_length);
            return -1;
        }
        p->pages->iov[i].iov_base = block->host + offset;
        p->pages->iov[i].iov_len = TARGET_PAGE_SIZE;
    }

    return 0;
}

struct {
    MultiFDSendParams *params;
    /* array of pages to sent */
    MultiFDPages_t *pages;
    /* global number of generated multifd packets */
    uint64_t packet_num;
    /* send channels ready */
    QemuSemaphore channels_ready;
    /*
     * Have we already run terminate threads.  There is a race when it
     * happens that we got one error while we are exiting.
     * We will use atomic operations.  Only valid values are 0 and 1.
     */
    int exiting;
} *multifd_send_state;

/*
 * How we use multifd_send_state->pages and channel->pages?
 *
 * We create a pages for each channel, and a main one.  Each time that
 * we need to send a batch of pages we interchange the ones between
 * multifd_send_state and the channel that is sending it.  There are
 * two reasons for that:
 *    - to not have to do so many mallocs during migration
 *    - to make easier to know what to free at the end of migration
 *
 * This way we always know who is the owner of each "pages" struct,
 * and we don't need any locking.  It belongs to the migration thread
 * or to the channel thread.  Switching is safe because the migration
 * thread is using the channel mutex when changing it, and the channel
 * have to had finish with its own, otherwise pending_job can't be
 * false.
 */

static int multifd_send_pages(RAMState *rs)
{
    int i;
    static int next_channel;
    MultiFDSendParams *p = NULL; /* make happy gcc */
    MultiFDPages_t *pages = multifd_send_state->pages;
    uint64_t transferred;

    if (atomic_read(&multifd_send_state->exiting)) {
        return -1;
    }

    qemu_sem_wait(&multifd_send_state->channels_ready);
    for (i = next_channel;; i = (i + 1) % migrate_multifd_channels()) {
        p = &multifd_send_state->params[i];

        qemu_mutex_lock(&p->mutex);
        if (p->quit) {
            error_report("%s: channel %d has already quit!", __func__, i);
            qemu_mutex_unlock(&p->mutex);
            return -1;
        }
        if (!p->pending_job) {
            p->pending_job++;
            next_channel = (i + 1) % migrate_multifd_channels();
            break;
        }
        qemu_mutex_unlock(&p->mutex);
    }
    p->pages->used = 0;

    p->packet_num = multifd_send_state->packet_num++;
    p->pages->block = NULL;
    multifd_send_state->pages = p->pages;
    p->pages = pages;
    transferred = ((uint64_t) pages->used) * TARGET_PAGE_SIZE + p->packet_len;
    qemu_file_update_transfer(rs->f, transferred);
    ram_counters.multifd_bytes += transferred;
    ram_counters.transferred += transferred;;
    qemu_mutex_unlock(&p->mutex);
    qemu_sem_post(&p->sem);

    return 1;
}

static int multifd_queue_page(RAMState *rs, RAMBlock *block, ram_addr_t offset)
{
    MultiFDPages_t *pages = multifd_send_state->pages;

    if (!pages->block) {
        pages->block = block;
    }

    if (pages->block == block) {
        pages->offset[pages->used] = offset;
        pages->iov[pages->used].iov_base = block->host + offset;
        pages->iov[pages->used].iov_len = TARGET_PAGE_SIZE;
        pages->used++;

        if (pages->used < pages->allocated) {
            return 1;
        }
    }

    if (multifd_send_pages(rs) < 0) {
        return -1;
    }

    if (pages->block != block) {
        return  multifd_queue_page(rs, block, offset);
    }

    return 1;
}

static void multifd_send_terminate_threads(Error *err)
{
    int i;

    trace_multifd_send_terminate_threads(err != NULL);

    if (err) {
        MigrationState *s = migrate_get_current();
        migrate_set_error(s, err);
        if (s->state == MIGRATION_STATUS_SETUP ||
            s->state == MIGRATION_STATUS_PRE_SWITCHOVER ||
            s->state == MIGRATION_STATUS_DEVICE ||
            s->state == MIGRATION_STATUS_ACTIVE) {
            migrate_set_state(&s->state, s->state,
                              MIGRATION_STATUS_FAILED);
        }
    }

    /*
     * We don't want to exit each threads twice.  Depending on where
     * we get the error, or if there are two independent errors in two
     * threads at the same time, we can end calling this function
     * twice.
     */
    if (atomic_xchg(&multifd_send_state->exiting, 1)) {
        return;
    }

    for (i = 0; i < migrate_multifd_channels(); i++) {
        MultiFDSendParams *p = &multifd_send_state->params[i];

        qemu_mutex_lock(&p->mutex);
        p->quit = true;
        qemu_sem_post(&p->sem);
        qemu_mutex_unlock(&p->mutex);
    }
}

void multifd_save_cleanup(void)
{
    int i;

    if (!migrate_use_multifd()) {
        return;
    }
    multifd_send_terminate_threads(NULL);
    for (i = 0; i < migrate_multifd_channels(); i++) {
        MultiFDSendParams *p = &multifd_send_state->params[i];

        if (p->running) {
            qemu_thread_join(&p->thread);
        }
        socket_send_channel_destroy(p->c);
        p->c = NULL;
        qemu_mutex_destroy(&p->mutex);
        qemu_sem_destroy(&p->sem);
        qemu_sem_destroy(&p->sem_sync);
        g_free(p->name);
        p->name = NULL;
        multifd_pages_clear(p->pages);
        p->pages = NULL;
        p->packet_len = 0;
        g_free(p->packet);
        p->packet = NULL;
    }
    qemu_sem_destroy(&multifd_send_state->channels_ready);
    g_free(multifd_send_state->params);
    multifd_send_state->params = NULL;
    multifd_pages_clear(multifd_send_state->pages);
    multifd_send_state->pages = NULL;
    g_free(multifd_send_state);
    multifd_send_state = NULL;
}

static void multifd_send_sync_main(RAMState *rs)
{
    int i;

    if (!migrate_use_multifd()) {
        return;
    }
    if (multifd_send_state->pages->used) {
        if (multifd_send_pages(rs) < 0) {
            error_report("%s: multifd_send_pages fail", __func__);
            return;
        }
    }
    for (i = 0; i < migrate_multifd_channels(); i++) {
        MultiFDSendParams *p = &multifd_send_state->params[i];

        trace_multifd_send_sync_main_signal(p->id);

        qemu_mutex_lock(&p->mutex);

        if (p->quit) {
            error_report("%s: channel %d has already quit", __func__, i);
            qemu_mutex_unlock(&p->mutex);
            return;
        }

        p->packet_num = multifd_send_state->packet_num++;
        p->flags |= MULTIFD_FLAG_SYNC;
        p->pending_job++;
        qemu_file_update_transfer(rs->f, p->packet_len);
        ram_counters.multifd_bytes += p->packet_len;
        ram_counters.transferred += p->packet_len;
        qemu_mutex_unlock(&p->mutex);
        qemu_sem_post(&p->sem);
    }
    for (i = 0; i < migrate_multifd_channels(); i++) {
        MultiFDSendParams *p = &multifd_send_state->params[i];

        trace_multifd_send_sync_main_wait(p->id);
        qemu_sem_wait(&p->sem_sync);
    }
    trace_multifd_send_sync_main(multifd_send_state->packet_num);
}

static void *multifd_send_thread(void *opaque)
{
    MultiFDSendParams *p = opaque;
    Error *local_err = NULL;
    int ret = 0;
    uint32_t flags = 0;

    trace_multifd_send_thread_start(p->id);
    rcu_register_thread();

    if (multifd_send_initial_packet(p, &local_err) < 0) {
        ret = -1;
        goto out;
    }
    /* initial packet */
    p->num_packets = 1;

    while (true) {
        qemu_sem_wait(&p->sem);

        if (atomic_read(&multifd_send_state->exiting)) {
            break;
        }
        qemu_mutex_lock(&p->mutex);

        if (p->pending_job) {
            uint32_t used = p->pages->used;
            uint64_t packet_num = p->packet_num;
            flags = p->flags;

            p->next_packet_size = used * qemu_target_page_size();
            multifd_send_fill_packet(p);
            p->flags = 0;
            p->num_packets++;
            p->num_pages += used;
            qemu_mutex_unlock(&p->mutex);

            trace_multifd_send(p->id, packet_num, used, flags,
                               p->next_packet_size);

            ret = qio_channel_write_all(p->c, (void *)p->packet,
                                        p->packet_len, &local_err);
            if (ret != 0) {
                break;
            }

            if (used) {
                ret = qio_channel_writev_all(p->c, p->pages->iov,
                                             used, &local_err);
                if (ret != 0) {
                    break;
                }
            }

            qemu_mutex_lock(&p->mutex);
            p->pending_job--;
            qemu_mutex_unlock(&p->mutex);

            if (flags & MULTIFD_FLAG_SYNC) {
                qemu_sem_post(&p->sem_sync);
            }
            qemu_sem_post(&multifd_send_state->channels_ready);
        } else if (p->quit) {
            qemu_mutex_unlock(&p->mutex);
            break;
        } else {
            qemu_mutex_unlock(&p->mutex);
            /* sometimes there are spurious wakeups */
        }
    }

out:
    if (local_err) {
        trace_multifd_send_error(p->id);
        multifd_send_terminate_threads(local_err);
    }

    /*
     * Error happen, I will exit, but I can't just leave, tell
     * who pay attention to me.
     */
    if (ret != 0) {
        qemu_sem_post(&p->sem_sync);
        qemu_sem_post(&multifd_send_state->channels_ready);
    }

    qemu_mutex_lock(&p->mutex);
    p->running = false;
    qemu_mutex_unlock(&p->mutex);

    rcu_unregister_thread();
    trace_multifd_send_thread_end(p->id, p->num_packets, p->num_pages);

    return NULL;
}

static void multifd_new_send_channel_async(QIOTask *task, gpointer opaque)
{
    MultiFDSendParams *p = opaque;
    QIOChannel *sioc = QIO_CHANNEL(qio_task_get_source(task));
    Error *local_err = NULL;

    trace_multifd_new_send_channel_async(p->id);
    if (qio_task_propagate_error(task, &local_err)) {
        migrate_set_error(migrate_get_current(), local_err);
        multifd_save_cleanup();
    } else {
        p->c = QIO_CHANNEL(sioc);
        qio_channel_set_delay(p->c, false);
        p->running = true;
        qemu_thread_create(&p->thread, p->name, multifd_send_thread, p,
                           QEMU_THREAD_JOINABLE);
    }
}

int multifd_save_setup(void)
{
    int thread_count;
    uint32_t page_count = MULTIFD_PACKET_SIZE / qemu_target_page_size();
    uint8_t i;

    if (!migrate_use_multifd()) {
        return 0;
    }
    thread_count = migrate_multifd_channels();
    multifd_send_state = g_malloc0(sizeof(*multifd_send_state));
    multifd_send_state->params = g_new0(MultiFDSendParams, thread_count);
    multifd_send_state->pages = multifd_pages_init(page_count);
    qemu_sem_init(&multifd_send_state->channels_ready, 0);
    atomic_set(&multifd_send_state->exiting, 0);

    for (i = 0; i < thread_count; i++) {
        MultiFDSendParams *p = &multifd_send_state->params[i];

        qemu_mutex_init(&p->mutex);
        qemu_sem_init(&p->sem, 0);
        qemu_sem_init(&p->sem_sync, 0);
        p->quit = false;
        p->pending_job = 0;
        p->id = i;
        p->pages = multifd_pages_init(page_count);
        p->packet_len = sizeof(MultiFDPacket_t)
                      + sizeof(ram_addr_t) * page_count;
        p->packet = g_malloc0(p->packet_len);
        p->packet->magic = cpu_to_be32(MULTIFD_MAGIC);
        p->packet->version = cpu_to_be32(MULTIFD_VERSION);
        p->name = g_strdup_printf("multifdsend_%d", i);
        socket_send_channel_create(multifd_new_send_channel_async, p);
    }
    return 0;
}

struct {
    MultiFDRecvParams *params;
    /* number of created threads */
    int count;
    /* syncs main thread and channels */
    QemuSemaphore sem_sync;
    /* global number of generated multifd packets */
    uint64_t packet_num;
} *multifd_recv_state;

static void multifd_recv_terminate_threads(Error *err)
{
    int i;

    trace_multifd_recv_terminate_threads(err != NULL);

    if (err) {
        MigrationState *s = migrate_get_current();
        migrate_set_error(s, err);
        if (s->state == MIGRATION_STATUS_SETUP ||
            s->state == MIGRATION_STATUS_ACTIVE) {
            migrate_set_state(&s->state, s->state,
                              MIGRATION_STATUS_FAILED);
        }
    }

    for (i = 0; i < migrate_multifd_channels(); i++) {
        MultiFDRecvParams *p = &multifd_recv_state->params[i];

        qemu_mutex_lock(&p->mutex);
        p->quit = true;
        /* We could arrive here for two reasons:
           - normal quit, i.e. everything went fine, just finished
           - error quit: We close the channels so the channel threads
             finish the qio_channel_read_all_eof() */
        qio_channel_shutdown(p->c, QIO_CHANNEL_SHUTDOWN_BOTH, NULL);
        qemu_mutex_unlock(&p->mutex);
    }
}

int multifd_load_cleanup(Error **errp)
{
    int i;
    int ret = 0;

    if (!migrate_use_multifd()) {
        return 0;
    }
    multifd_recv_terminate_threads(NULL);
    for (i = 0; i < migrate_multifd_channels(); i++) {
        MultiFDRecvParams *p = &multifd_recv_state->params[i];

        if (p->running) {
            p->quit = true;
            /*
             * multifd_recv_thread may hung at MULTIFD_FLAG_SYNC handle code,
             * however try to wakeup it without harm in cleanup phase.
             */
            qemu_sem_post(&p->sem_sync);
            qemu_thread_join(&p->thread);
        }
        object_unref(OBJECT(p->c));
        p->c = NULL;
        qemu_mutex_destroy(&p->mutex);
        qemu_sem_destroy(&p->sem_sync);
        g_free(p->name);
        p->name = NULL;
        multifd_pages_clear(p->pages);
        p->pages = NULL;
        p->packet_len = 0;
        g_free(p->packet);
        p->packet = NULL;
    }
    qemu_sem_destroy(&multifd_recv_state->sem_sync);
    g_free(multifd_recv_state->params);
    multifd_recv_state->params = NULL;
    g_free(multifd_recv_state);
    multifd_recv_state = NULL;

    return ret;
}

static void multifd_recv_sync_main(void)
{
    int i;

    if (!migrate_use_multifd()) {
        return;
    }
    for (i = 0; i < migrate_multifd_channels(); i++) {
        MultiFDRecvParams *p = &multifd_recv_state->params[i];

        trace_multifd_recv_sync_main_wait(p->id);
        qemu_sem_wait(&multifd_recv_state->sem_sync);
    }
    for (i = 0; i < migrate_multifd_channels(); i++) {
        MultiFDRecvParams *p = &multifd_recv_state->params[i];

        qemu_mutex_lock(&p->mutex);
        if (multifd_recv_state->packet_num < p->packet_num) {
            multifd_recv_state->packet_num = p->packet_num;
        }
        qemu_mutex_unlock(&p->mutex);
        trace_multifd_recv_sync_main_signal(p->id);
        qemu_sem_post(&p->sem_sync);
    }
    trace_multifd_recv_sync_main(multifd_recv_state->packet_num);
}

static void *multifd_recv_thread(void *opaque)
{
    MultiFDRecvParams *p = opaque;
    Error *local_err = NULL;
    int ret;

    trace_multifd_recv_thread_start(p->id);
    rcu_register_thread();

    while (true) {
        uint32_t used;
        uint32_t flags;

        if (p->quit) {
            break;
        }

        ret = qio_channel_read_all_eof(p->c, (void *)p->packet,
                                       p->packet_len, &local_err);
        if (ret == 0) {   /* EOF */
            break;
        }
        if (ret == -1) {   /* Error */
            break;
        }

        qemu_mutex_lock(&p->mutex);
        ret = multifd_recv_unfill_packet(p, &local_err);
        if (ret) {
            qemu_mutex_unlock(&p->mutex);
            break;
        }

        used = p->pages->used;
        flags = p->flags;
        trace_multifd_recv(p->id, p->packet_num, used, flags,
                           p->next_packet_size);
        p->num_packets++;
        p->num_pages += used;
        qemu_mutex_unlock(&p->mutex);

        if (used) {
            ret = qio_channel_readv_all(p->c, p->pages->iov,
                                        used, &local_err);
            if (ret != 0) {
                break;
            }
        }

        if (flags & MULTIFD_FLAG_SYNC) {
            qemu_sem_post(&multifd_recv_state->sem_sync);
            qemu_sem_wait(&p->sem_sync);
        }
    }

    if (local_err) {
        multifd_recv_terminate_threads(local_err);
    }
    qemu_mutex_lock(&p->mutex);
    p->running = false;
    qemu_mutex_unlock(&p->mutex);

    rcu_unregister_thread();
    trace_multifd_recv_thread_end(p->id, p->num_packets, p->num_pages);

    return NULL;
}

int multifd_load_setup(void)
{
    int thread_count;
    uint32_t page_count = MULTIFD_PACKET_SIZE / qemu_target_page_size();
    uint8_t i;

    if (!migrate_use_multifd()) {
        return 0;
    }
    thread_count = migrate_multifd_channels();
    multifd_recv_state = g_malloc0(sizeof(*multifd_recv_state));
    multifd_recv_state->params = g_new0(MultiFDRecvParams, thread_count);
    atomic_set(&multifd_recv_state->count, 0);
    qemu_sem_init(&multifd_recv_state->sem_sync, 0);

    for (i = 0; i < thread_count; i++) {
        MultiFDRecvParams *p = &multifd_recv_state->params[i];

        qemu_mutex_init(&p->mutex);
        qemu_sem_init(&p->sem_sync, 0);
        p->quit = false;
        p->id = i;
        p->pages = multifd_pages_init(page_count);
        p->packet_len = sizeof(MultiFDPacket_t)
                      + sizeof(ram_addr_t) * page_count;
        p->packet = g_malloc0(p->packet_len);
        p->name = g_strdup_printf("multifdrecv_%d", i);
    }
    return 0;
}

bool multifd_recv_all_channels_created(void)
{
    int thread_count = migrate_multifd_channels();

    if (!migrate_use_multifd()) {
        return true;
    }

    return thread_count == atomic_read(&multifd_recv_state->count);
}

/*
 * Try to receive all multifd channels to get ready for the migration.
 * - Return true and do not set @errp when correctly receving all channels;
 * - Return false and do not set @errp when correctly receiving the current one;
 * - Return false and set @errp when failing to receive the current channel.
 */
bool multifd_recv_new_channel(QIOChannel *ioc, Error **errp)
{
    MultiFDRecvParams *p;
    Error *local_err = NULL;
    int id;

    id = multifd_recv_initial_packet(ioc, &local_err);
    if (id < 0) {
        multifd_recv_terminate_threads(local_err);
        error_propagate_prepend(errp, local_err,
                                "failed to receive packet"
                                " via multifd channel %d: ",
                                atomic_read(&multifd_recv_state->count));
        return false;
    }
    trace_multifd_recv_new_channel(id);

    p = &multifd_recv_state->params[id];
    if (p->c != NULL) {
        error_setg(&local_err, "multifd: received id '%d' already setup'",
                   id);
        multifd_recv_terminate_threads(local_err);
        error_propagate(errp, local_err);
        return false;
    }
    p->c = ioc;
    object_ref(OBJECT(ioc));
    /* initial packet */
    p->num_packets = 1;

    p->running = true;
    qemu_thread_create(&p->thread, p->name, multifd_recv_thread, p,
                       QEMU_THREAD_JOINABLE);
    atomic_inc(&multifd_recv_state->count);
    return atomic_read(&multifd_recv_state->count) ==
           migrate_multifd_channels();
}

/**
 * save_page_header: write page header to wire
 *
 * If this is the 1st block, it also writes the block identification
 *
 * Returns the number of bytes written
 *
 * @f: QEMUFile where to send the data
 * @block: block that contains the page we want to send
 * @offset: offset inside the block for the page
 *          in the lower bits, it contains flags
 */
static size_t save_page_header(RAMState *rs, QEMUFile *f,  RAMBlock *block,
                               ram_addr_t offset)
{
    size_t size, len;

    if (block == rs->last_sent_block) {
        offset |= RAM_SAVE_FLAG_CONTINUE;
    }
    qemu_put_be64(f, offset);
    size = 8;

    if (!(offset & RAM_SAVE_FLAG_CONTINUE)) {
        len = strlen(block->idstr);
        qemu_put_byte(f, len);
        qemu_put_buffer(f, (uint8_t *)block->idstr, len);
        size += 1 + len;
        rs->last_sent_block = block;
    }
    return size;
}

/**
 * mig_throttle_guest_down: throotle down the guest
 *
 * Reduce amount of guest cpu execution to hopefully slow down memory
 * writes. If guest dirty memory rate is reduced below the rate at
 * which we can transfer pages to the destination then we should be
 * able to complete migration. Some workloads dirty memory way too
 * fast and will not effectively converge, even with auto-converge.
 */
static void mig_throttle_guest_down(void)
{
    MigrationState *s = migrate_get_current();
    uint64_t pct_initial = s->parameters.cpu_throttle_initial;
    uint64_t pct_icrement = s->parameters.cpu_throttle_increment;
    int pct_max = s->parameters.max_cpu_throttle;

    /* We have not started throttling yet. Let's start it. */
    if (!cpu_throttle_active()) {
        cpu_throttle_set(pct_initial);
    } else {
        /* Throttling already on, just increase the rate */
        cpu_throttle_set(MIN(cpu_throttle_get_percentage() + pct_icrement,
                         pct_max));
    }
}

/**
 * xbzrle_cache_zero_page: insert a zero page in the XBZRLE cache
 *
 * @rs: current RAM state
 * @current_addr: address for the zero page
 *
 * Update the xbzrle cache to reflect a page that's been sent as all 0.
 * The important thing is that a stale (not-yet-0'd) page be replaced
 * by the new data.
 * As a bonus, if the page wasn't in the cache it gets added so that
 * when a small write is made into the 0'd page it gets XBZRLE sent.
 */
static void xbzrle_cache_zero_page(RAMState *rs, ram_addr_t current_addr)
{
    if (rs->ram_bulk_stage || !migrate_use_xbzrle()) {
        return;
    }

    /* We don't care if this fails to allocate a new cache page
     * as long as it updated an old one */
    cache_insert(XBZRLE.cache, current_addr, XBZRLE.zero_target_page,
                 ram_counters.dirty_sync_count);
}

#define ENCODING_FLAG_XBZRLE 0x1

/**
 * save_xbzrle_page: compress and send current page
 *
 * Returns: 1 means that we wrote the page
 *          0 means that page is identical to the one already sent
 *          -1 means that xbzrle would be longer than normal
 *
 * @rs: current RAM state
 * @current_data: pointer to the address of the page contents
 * @current_addr: addr of the page
 * @block: block that contains the page we want to send
 * @offset: offset inside the block for the page
 * @last_stage: if we are at the completion stage
 */
static int save_xbzrle_page(RAMState *rs, uint8_t **current_data,
                            ram_addr_t current_addr, RAMBlock *block,
                            ram_addr_t offset, bool last_stage)
{
    int encoded_len = 0, bytes_xbzrle;
    uint8_t *prev_cached_page;

    if (!cache_is_cached(XBZRLE.cache, current_addr,
                         ram_counters.dirty_sync_count)) {
        xbzrle_counters.cache_miss++;
        if (!last_stage) {
            if (cache_insert(XBZRLE.cache, current_addr, *current_data,
                             ram_counters.dirty_sync_count) == -1) {
                return -1;
            } else {
                /* update *current_data when the page has been
                   inserted into cache */
                *current_data = get_cached_data(XBZRLE.cache, current_addr);
            }
        }
        return -1;
    }

    prev_cached_page = get_cached_data(XBZRLE.cache, current_addr);

    /* save current buffer into memory */
    memcpy(XBZRLE.current_buf, *current_data, TARGET_PAGE_SIZE);

    /* XBZRLE encoding (if there is no overflow) */
    encoded_len = xbzrle_encode_buffer(prev_cached_page, XBZRLE.current_buf,
                                       TARGET_PAGE_SIZE, XBZRLE.encoded_buf,
                                       TARGET_PAGE_SIZE);

    /*
     * Update the cache contents, so that it corresponds to the data
     * sent, in all cases except where we skip the page.
     */
    if (!last_stage && encoded_len != 0) {
        memcpy(prev_cached_page, XBZRLE.current_buf, TARGET_PAGE_SIZE);
        /*
         * In the case where we couldn't compress, ensure that the caller
         * sends the data from the cache, since the guest might have
         * changed the RAM since we copied it.
         */
        *current_data = prev_cached_page;
    }

    if (encoded_len == 0) {
        trace_save_xbzrle_page_skipping();
        return 0;
    } else if (encoded_len == -1) {
        trace_save_xbzrle_page_overflow();
        xbzrle_counters.overflow++;
        return -1;
    }

    /* Send XBZRLE based compressed page */
    bytes_xbzrle = save_page_header(rs, rs->f, block,
                                    offset | RAM_SAVE_FLAG_XBZRLE);
    qemu_put_byte(rs->f, ENCODING_FLAG_XBZRLE);
    qemu_put_be16(rs->f, encoded_len);
    qemu_put_buffer(rs->f, XBZRLE.encoded_buf, encoded_len);
    bytes_xbzrle += encoded_len + 1 + 2;
    xbzrle_counters.pages++;
    xbzrle_counters.bytes += bytes_xbzrle;
    ram_counters.transferred += bytes_xbzrle;

    return 1;
}

/**
 * migration_bitmap_find_dirty: find the next dirty page from start
 *
 * Returns the page offset within memory region of the start of a dirty page
 *
 * @rs: current RAM state
 * @rb: RAMBlock where to search for dirty pages
 * @start: page where we start the search
 */
static inline
unsigned long migration_bitmap_find_dirty(RAMState *rs, RAMBlock *rb,
                                          unsigned long start)
{
    unsigned long size = rb->used_length >> TARGET_PAGE_BITS;
    unsigned long *bitmap = rb->bmap;
    unsigned long next;

    if (ramblock_is_ignored(rb)) {
        return size;
    }

    /*
     * When the free page optimization is enabled, we need to check the bitmap
     * to send the non-free pages rather than all the pages in the bulk stage.
     */
    if (!rs->fpo_enabled && rs->ram_bulk_stage && start > 0) {
        next = start + 1;
    } else {
        next = find_next_bit(bitmap, size, start);
    }

    return next;
}

static inline bool migration_bitmap_clear_dirty(RAMState *rs,
                                                RAMBlock *rb,
                                                unsigned long page)
{
    bool ret;

    qemu_mutex_lock(&rs->bitmap_mutex);

    /*
     * Clear dirty bitmap if needed.  This _must_ be called before we
     * send any of the page in the chunk because we need to make sure
     * we can capture further page content changes when we sync dirty
     * log the next time.  So as long as we are going to send any of
     * the page in the chunk we clear the remote dirty bitmap for all.
     * Clearing it earlier won't be a problem, but too late will.
     */
    if (rb->clear_bmap && clear_bmap_test_and_clear(rb, page)) {
        uint8_t shift = rb->clear_bmap_shift;
        hwaddr size = 1ULL << (TARGET_PAGE_BITS + shift);
        hwaddr start = (page << TARGET_PAGE_BITS) & (-size);

        /*
         * CLEAR_BITMAP_SHIFT_MIN should always guarantee this... this
         * can make things easier sometimes since then start address
         * of the small chunk will always be 64 pages aligned so the
         * bitmap will always be aligned to unsigned long.  We should
         * even be able to remove this restriction but I'm simply
         * keeping it.
         */
        assert(shift >= 6);
        trace_migration_bitmap_clear_dirty(rb->idstr, start, size, page);
        memory_region_clear_dirty_bitmap(rb->mr, start, size);
    }

    ret = test_and_clear_bit(page, rb->bmap);

    if (ret) {
        rs->migration_dirty_pages--;
    }
    qemu_mutex_unlock(&rs->bitmap_mutex);

    return ret;
}

/* Called with RCU critical section */
static void ramblock_sync_dirty_bitmap(RAMState *rs, RAMBlock *rb)
{
    rs->migration_dirty_pages +=
        cpu_physical_memory_sync_dirty_bitmap(rb, 0, rb->used_length,
                                              &rs->num_dirty_pages_period);
}

/**
 * ram_pagesize_summary: calculate all the pagesizes of a VM
 *
 * Returns a summary bitmap of the page sizes of all RAMBlocks
 *
 * For VMs with just normal pages this is equivalent to the host page
 * size. If it's got some huge pages then it's the OR of all the
 * different page sizes.
 */
uint64_t ram_pagesize_summary(void)
{
    RAMBlock *block;
    uint64_t summary = 0;

    RAMBLOCK_FOREACH_NOT_IGNORED(block) {
        summary |= block->page_size;
    }

    return summary;
}

uint64_t ram_get_total_transferred_pages(void)
{
    return  ram_counters.normal + ram_counters.duplicate +
                compression_counters.pages + xbzrle_counters.pages;
}

static void migration_update_rates(RAMState *rs, int64_t end_time)
{
    uint64_t page_count = rs->target_page_count - rs->target_page_count_prev;
    double compressed_size;

    /* calculate period counters */
    ram_counters.dirty_pages_rate = rs->num_dirty_pages_period * 1000
                / (end_time - rs->time_last_bitmap_sync);

    if (!page_count) {
        return;
    }

    if (migrate_use_xbzrle()) {
        xbzrle_counters.cache_miss_rate = (double)(xbzrle_counters.cache_miss -
            rs->xbzrle_cache_miss_prev) / page_count;
        rs->xbzrle_cache_miss_prev = xbzrle_counters.cache_miss;
    }

    if (migrate_use_compression()) {
        compression_counters.busy_rate = (double)(compression_counters.busy -
            rs->compress_thread_busy_prev) / page_count;
        rs->compress_thread_busy_prev = compression_counters.busy;

        compressed_size = compression_counters.compressed_size -
                          rs->compressed_size_prev;
        if (compressed_size) {
            double uncompressed_size = (compression_counters.pages -
                                    rs->compress_pages_prev) * TARGET_PAGE_SIZE;

            /* Compression-Ratio = Uncompressed-size / Compressed-size */
            compression_counters.compression_rate =
                                        uncompressed_size / compressed_size;

            rs->compress_pages_prev = compression_counters.pages;
            rs->compressed_size_prev = compression_counters.compressed_size;
        }
    }
}

static void migration_bitmap_sync(RAMState *rs)
{
    RAMBlock *block;
    int64_t end_time;
    uint64_t bytes_xfer_now;

    ram_counters.dirty_sync_count++;

    if (!rs->time_last_bitmap_sync) {
        rs->time_last_bitmap_sync = qemu_clock_get_ms(QEMU_CLOCK_REALTIME);
    }

    trace_migration_bitmap_sync_start();
    memory_global_dirty_log_sync();

    qemu_mutex_lock(&rs->bitmap_mutex);
    WITH_RCU_READ_LOCK_GUARD() {
        RAMBLOCK_FOREACH_NOT_IGNORED(block) {
            ramblock_sync_dirty_bitmap(rs, block);
        }
        ram_counters.remaining = ram_bytes_remaining();
    }
    qemu_mutex_unlock(&rs->bitmap_mutex);

    memory_global_after_dirty_log_sync();
    trace_migration_bitmap_sync_end(rs->num_dirty_pages_period);

    end_time = qemu_clock_get_ms(QEMU_CLOCK_REALTIME);

    /* more than 1 second = 1000 millisecons */
    if (end_time > rs->time_last_bitmap_sync + 1000) {
        bytes_xfer_now = ram_counters.transferred;

        /* During block migration the auto-converge logic incorrectly detects
         * that ram migration makes no progress. Avoid this by disabling the
         * throttling logic during the bulk phase of block migration. */
        if (migrate_auto_converge() && !blk_mig_bulk_active()) {
            /* The following detection logic can be refined later. For now:
               Check to see if the dirtied bytes is 50% more than the approx.
               amount of bytes that just got transferred since the last time we
               were in this routine. If that happens twice, start or increase
               throttling */

            if ((rs->num_dirty_pages_period * TARGET_PAGE_SIZE >
                   (bytes_xfer_now - rs->bytes_xfer_prev) / 2) &&
                (++rs->dirty_rate_high_cnt >= 2)) {
                    trace_migration_throttle();
                    rs->dirty_rate_high_cnt = 0;
                    mig_throttle_guest_down();
            }
        }

        migration_update_rates(rs, end_time);

        rs->target_page_count_prev = rs->target_page_count;

        /* reset period counters */
        rs->time_last_bitmap_sync = end_time;
        rs->num_dirty_pages_period = 0;
        rs->bytes_xfer_prev = bytes_xfer_now;
    }
    if (migrate_use_events()) {
        qapi_event_send_migration_pass(ram_counters.dirty_sync_count);
    }
}

static void migration_bitmap_sync_precopy(RAMState *rs)
{
    Error *local_err = NULL;

    /*
     * The current notifier usage is just an optimization to migration, so we
     * don't stop the normal migration process in the error case.
     */
    if (precopy_notify(PRECOPY_NOTIFY_BEFORE_BITMAP_SYNC, &local_err)) {
        error_report_err(local_err);
    }

    migration_bitmap_sync(rs);

    if (precopy_notify(PRECOPY_NOTIFY_AFTER_BITMAP_SYNC, &local_err)) {
        error_report_err(local_err);
    }
}

/**
 * save_zero_page_to_file: send the zero page to the file
 *
 * Returns the size of data written to the file, 0 means the page is not
 * a zero page
 *
 * @rs: current RAM state
 * @file: the file where the data is saved
 * @block: block that contains the page we want to send
 * @offset: offset inside the block for the page
 */
static int save_zero_page_to_file(RAMState *rs, QEMUFile *file,
                                  RAMBlock *block, ram_addr_t offset)
{
    uint8_t *p = block->host + offset;
    int len = 0;

    if (is_zero_range(p, TARGET_PAGE_SIZE)) {
        len += save_page_header(rs, file, block, offset | RAM_SAVE_FLAG_ZERO);
        qemu_put_byte(file, 0);
        len += 1;
    }
    return len;
}

/**
 * save_zero_page: send the zero page to the stream
 *
 * Returns the number of pages written.
 *
 * @rs: current RAM state
 * @block: block that contains the page we want to send
 * @offset: offset inside the block for the page
 */
static int save_zero_page(RAMState *rs, RAMBlock *block, ram_addr_t offset)
{
    int len = save_zero_page_to_file(rs, rs->f, block, offset);

    if (len) {
        ram_counters.duplicate++;
        ram_counters.transferred += len;
        return 1;
    }
    return -1;
}

static void ram_release_pages(const char *rbname, uint64_t offset, int pages)
{
    if (!migrate_release_ram() || !migration_in_postcopy()) {
        return;
    }

    ram_discard_range(rbname, offset, pages << TARGET_PAGE_BITS);
}

/*
 * @pages: the number of pages written by the control path,
 *        < 0 - error
 *        > 0 - number of pages written
 *
 * Return true if the pages has been saved, otherwise false is returned.
 */
static bool control_save_page(RAMState *rs, RAMBlock *block, ram_addr_t offset,
                              int *pages)
{
    uint64_t bytes_xmit = 0;
    int ret;

    *pages = -1;
    ret = ram_control_save_page(rs->f, block->offset, offset, TARGET_PAGE_SIZE,
                                &bytes_xmit);
    if (ret == RAM_SAVE_CONTROL_NOT_SUPP) {
        return false;
    }

    if (bytes_xmit) {
        ram_counters.transferred += bytes_xmit;
        *pages = 1;
    }

    if (ret == RAM_SAVE_CONTROL_DELAYED) {
        return true;
    }

    if (bytes_xmit > 0) {
        ram_counters.normal++;
    } else if (bytes_xmit == 0) {
        ram_counters.duplicate++;
    }

    return true;
}

/*
 * directly send the page to the stream
 *
 * Returns the number of pages written.
 *
 * @rs: current RAM state
 * @block: block that contains the page we want to send
 * @offset: offset inside the block for the page
 * @buf: the page to be sent
 * @async: send to page asyncly
 */
static int save_normal_page(RAMState *rs, RAMBlock *block, ram_addr_t offset,
                            uint8_t *buf, bool async)
{
    ram_counters.transferred += save_page_header(rs, rs->f, block,
                                                 offset | RAM_SAVE_FLAG_PAGE);
    if (async) {
        qemu_put_buffer_async(rs->f, buf, TARGET_PAGE_SIZE,
                              migrate_release_ram() &
                              migration_in_postcopy());
    } else {
        qemu_put_buffer(rs->f, buf, TARGET_PAGE_SIZE);
    }
    ram_counters.transferred += TARGET_PAGE_SIZE;
    ram_counters.normal++;
    return 1;
}

/**
 * ram_save_page: send the given page to the stream
 *
 * Returns the number of pages written.
 *          < 0 - error
 *          >=0 - Number of pages written - this might legally be 0
 *                if xbzrle noticed the page was the same.
 *
 * @rs: current RAM state
 * @block: block that contains the page we want to send
 * @offset: offset inside the block for the page
 * @last_stage: if we are at the completion stage
 */
static int ram_save_page(RAMState *rs, PageSearchStatus *pss, bool last_stage)
{
    int pages = -1;
    uint8_t *p;
    bool send_async = true;
    RAMBlock *block = pss->block;
    ram_addr_t offset = pss->page << TARGET_PAGE_BITS;
    ram_addr_t current_addr = block->offset + offset;

    p = block->host + offset;
    trace_ram_save_page(block->idstr, (uint64_t)offset, p);

    XBZRLE_cache_lock();
    if (!rs->ram_bulk_stage && !migration_in_postcopy() &&
        migrate_use_xbzrle()) {
        pages = save_xbzrle_page(rs, &p, current_addr, block,
                                 offset, last_stage);
        if (!last_stage) {
            /* Can't send this cached data async, since the cache page
             * might get updated before it gets to the wire
             */
            send_async = false;
        }
    }

    /* XBZRLE overflow or normal page */
    if (pages == -1) {
        pages = save_normal_page(rs, block, offset, p, send_async);
    }

    XBZRLE_cache_unlock();

    return pages;
}

static int ram_save_multifd_page(RAMState *rs, RAMBlock *block,
                                 ram_addr_t offset)
{
    if (multifd_queue_page(rs, block, offset) < 0) {
        return -1;
    }
    ram_counters.normal++;

    return 1;
}

static bool do_compress_ram_page(QEMUFile *f, z_stream *stream, RAMBlock *block,
                                 ram_addr_t offset, uint8_t *source_buf)
{
    RAMState *rs = ram_state;
    uint8_t *p = block->host + (offset & TARGET_PAGE_MASK);
    bool zero_page = false;
    int ret;

    if (save_zero_page_to_file(rs, f, block, offset)) {
        zero_page = true;
        goto exit;
    }

    save_page_header(rs, f, block, offset | RAM_SAVE_FLAG_COMPRESS_PAGE);

    /*
     * copy it to a internal buffer to avoid it being modified by VM
     * so that we can catch up the error during compression and
     * decompression
     */
    memcpy(source_buf, p, TARGET_PAGE_SIZE);
    ret = qemu_put_compression_data(f, stream, source_buf, TARGET_PAGE_SIZE);
    if (ret < 0) {
        qemu_file_set_error(migrate_get_current()->to_dst_file, ret);
        error_report("compressed data failed!");
        return false;
    }

exit:
    ram_release_pages(block->idstr, offset & TARGET_PAGE_MASK, 1);
    return zero_page;
}

static void
update_compress_thread_counts(const CompressParam *param, int bytes_xmit)
{
    ram_counters.transferred += bytes_xmit;

    if (param->zero_page) {
        ram_counters.duplicate++;
        return;
    }

    /* 8 means a header with RAM_SAVE_FLAG_CONTINUE. */
    compression_counters.compressed_size += bytes_xmit - 8;
    compression_counters.pages++;
}

static bool save_page_use_compression(RAMState *rs);

static void flush_compressed_data(RAMState *rs)
{
    int idx, len, thread_count;

    if (!save_page_use_compression(rs)) {
        return;
    }
    thread_count = migrate_compress_threads();

    qemu_mutex_lock(&comp_done_lock);
    for (idx = 0; idx < thread_count; idx++) {
        while (!comp_param[idx].done) {
            qemu_cond_wait(&comp_done_cond, &comp_done_lock);
        }
    }
    qemu_mutex_unlock(&comp_done_lock);

    for (idx = 0; idx < thread_count; idx++) {
        qemu_mutex_lock(&comp_param[idx].mutex);
        if (!comp_param[idx].quit) {
            len = qemu_put_qemu_file(rs->f, comp_param[idx].file);
            /*
             * it's safe to fetch zero_page without holding comp_done_lock
             * as there is no further request submitted to the thread,
             * i.e, the thread should be waiting for a request at this point.
             */
            update_compress_thread_counts(&comp_param[idx], len);
        }
        qemu_mutex_unlock(&comp_param[idx].mutex);
    }
}

static inline void set_compress_params(CompressParam *param, RAMBlock *block,
                                       ram_addr_t offset)
{
    param->block = block;
    param->offset = offset;
}

static int compress_page_with_multi_thread(RAMState *rs, RAMBlock *block,
                                           ram_addr_t offset)
{
    int idx, thread_count, bytes_xmit = -1, pages = -1;
    bool wait = migrate_compress_wait_thread();

    thread_count = migrate_compress_threads();
    qemu_mutex_lock(&comp_done_lock);
retry:
    for (idx = 0; idx < thread_count; idx++) {
        if (comp_param[idx].done) {
            comp_param[idx].done = false;
            bytes_xmit = qemu_put_qemu_file(rs->f, comp_param[idx].file);
            qemu_mutex_lock(&comp_param[idx].mutex);
            set_compress_params(&comp_param[idx], block, offset);
            qemu_cond_signal(&comp_param[idx].cond);
            qemu_mutex_unlock(&comp_param[idx].mutex);
            pages = 1;
            update_compress_thread_counts(&comp_param[idx], bytes_xmit);
            break;
        }
    }

    /*
     * wait for the free thread if the user specifies 'compress-wait-thread',
     * otherwise we will post the page out in the main thread as normal page.
     */
    if (pages < 0 && wait) {
        qemu_cond_wait(&comp_done_cond, &comp_done_lock);
        goto retry;
    }
    qemu_mutex_unlock(&comp_done_lock);

    return pages;
}

/**
 * find_dirty_block: find the next dirty page and update any state
 * associated with the search process.
 *
 * Returns true if a page is found
 *
 * @rs: current RAM state
 * @pss: data about the state of the current dirty page scan
 * @again: set to false if the search has scanned the whole of RAM
 */
static bool find_dirty_block(RAMState *rs, PageSearchStatus *pss, bool *again)
{
    pss->page = migration_bitmap_find_dirty(rs, pss->block, pss->page);
    if (pss->complete_round && pss->block == rs->last_seen_block &&
        pss->page >= rs->last_page) {
        /*
         * We've been once around the RAM and haven't found anything.
         * Give up.
         */
        *again = false;
        return false;
    }
    if ((pss->page << TARGET_PAGE_BITS) >= pss->block->used_length) {
        /* Didn't find anything in this RAM Block */
        pss->page = 0;
        pss->block = QLIST_NEXT_RCU(pss->block, next);
        if (!pss->block) {
            /*
             * If memory migration starts over, we will meet a dirtied page
             * which may still exists in compression threads's ring, so we
             * should flush the compressed data to make sure the new page
             * is not overwritten by the old one in the destination.
             *
             * Also If xbzrle is on, stop using the data compression at this
             * point. In theory, xbzrle can do better than compression.
             */
            flush_compressed_data(rs);

            /* Hit the end of the list */
            pss->block = QLIST_FIRST_RCU(&ram_list.blocks);
            /* Flag that we've looped */
            pss->complete_round = true;
            rs->ram_bulk_stage = false;
        }
        /* Didn't find anything this time, but try again on the new block */
        *again = true;
        return false;
    } else {
        /* Can go around again, but... */
        *again = true;
        /* We've found something so probably don't need to */
        return true;
    }
}

/**
 * unqueue_page: gets a page of the queue
 *
 * Helper for 'get_queued_page' - gets a page off the queue
 *
 * Returns the block of the page (or NULL if none available)
 *
 * @rs: current RAM state
 * @offset: used to return the offset within the RAMBlock
 */
static RAMBlock *unqueue_page(RAMState *rs, ram_addr_t *offset)
{
    RAMBlock *block = NULL;

    if (QSIMPLEQ_EMPTY_ATOMIC(&rs->src_page_requests)) {
        return NULL;
    }

    qemu_mutex_lock(&rs->src_page_req_mutex);
    if (!QSIMPLEQ_EMPTY(&rs->src_page_requests)) {
        struct RAMSrcPageRequest *entry =
                                QSIMPLEQ_FIRST(&rs->src_page_requests);
        block = entry->rb;
        *offset = entry->offset;

        if (entry->len > TARGET_PAGE_SIZE) {
            entry->len -= TARGET_PAGE_SIZE;
            entry->offset += TARGET_PAGE_SIZE;
        } else {
            memory_region_unref(block->mr);
            QSIMPLEQ_REMOVE_HEAD(&rs->src_page_requests, next_req);
            g_free(entry);
            migration_consume_urgent_request();
        }
    }
    qemu_mutex_unlock(&rs->src_page_req_mutex);

    return block;
}

/**
 * get_queued_page: unqueue a page from the postcopy requests
 *
 * Skips pages that are already sent (!dirty)
 *
 * Returns true if a queued page is found
 *
 * @rs: current RAM state
 * @pss: data about the state of the current dirty page scan
 */
static bool get_queued_page(RAMState *rs, PageSearchStatus *pss)
{
    RAMBlock  *block;
    ram_addr_t offset;
    bool dirty;

    do {
        block = unqueue_page(rs, &offset);
        /*
         * We're sending this page, and since it's postcopy nothing else
         * will dirty it, and we must make sure it doesn't get sent again
         * even if this queue request was received after the background
         * search already sent it.
         */
        if (block) {
            unsigned long page;

            page = offset >> TARGET_PAGE_BITS;
            dirty = test_bit(page, block->bmap);
            if (!dirty) {
                trace_get_queued_page_not_dirty(block->idstr, (uint64_t)offset,
                                                page);
            } else {
                trace_get_queued_page(block->idstr, (uint64_t)offset, page);
            }
        }

    } while (block && !dirty);

    if (block) {
        /*
         * As soon as we start servicing pages out of order, then we have
         * to kill the bulk stage, since the bulk stage assumes
         * in (migration_bitmap_find_and_reset_dirty) that every page is
         * dirty, that's no longer true.
         */
        rs->ram_bulk_stage = false;

        /*
         * We want the background search to continue from the queued page
         * since the guest is likely to want other pages near to the page
         * it just requested.
         */
        pss->block = block;
        pss->page = offset >> TARGET_PAGE_BITS;

        /*
         * This unqueued page would break the "one round" check, even is
         * really rare.
         */
        pss->complete_round = false;
    }

    return !!block;
}

/**
 * migration_page_queue_free: drop any remaining pages in the ram
 * request queue
 *
 * It should be empty at the end anyway, but in error cases there may
 * be some left.  in case that there is any page left, we drop it.
 *
 */
static void migration_page_queue_free(RAMState *rs)
{
    struct RAMSrcPageRequest *mspr, *next_mspr;
    /* This queue generally should be empty - but in the case of a failed
     * migration might have some droppings in.
     */
    RCU_READ_LOCK_GUARD();
    QSIMPLEQ_FOREACH_SAFE(mspr, &rs->src_page_requests, next_req, next_mspr) {
        memory_region_unref(mspr->rb->mr);
        QSIMPLEQ_REMOVE_HEAD(&rs->src_page_requests, next_req);
        g_free(mspr);
    }
}

/**
 * ram_save_queue_pages: queue the page for transmission
 *
 * A request from postcopy destination for example.
 *
 * Returns zero on success or negative on error
 *
 * @rbname: Name of the RAMBLock of the request. NULL means the
 *          same that last one.
 * @start: starting address from the start of the RAMBlock
 * @len: length (in bytes) to send
 */
int ram_save_queue_pages(const char *rbname, ram_addr_t start, ram_addr_t len)
{
    RAMBlock *ramblock;
    RAMState *rs = ram_state;

    ram_counters.postcopy_requests++;
    RCU_READ_LOCK_GUARD();

    if (!rbname) {
        /* Reuse last RAMBlock */
        ramblock = rs->last_req_rb;

        if (!ramblock) {
            /*
             * Shouldn't happen, we can't reuse the last RAMBlock if
             * it's the 1st request.
             */
            error_report("ram_save_queue_pages no previous block");
            return -1;
        }
    } else {
        ramblock = qemu_ram_block_by_name(rbname);

        if (!ramblock) {
            /* We shouldn't be asked for a non-existent RAMBlock */
            error_report("ram_save_queue_pages no block '%s'", rbname);
            return -1;
        }
        rs->last_req_rb = ramblock;
    }
    trace_ram_save_queue_pages(ramblock->idstr, start, len);
    if (start+len > ramblock->used_length) {
        error_report("%s request overrun start=" RAM_ADDR_FMT " len="
                     RAM_ADDR_FMT " blocklen=" RAM_ADDR_FMT,
                     __func__, start, len, ramblock->used_length);
        return -1;
    }

    struct RAMSrcPageRequest *new_entry =
        g_malloc0(sizeof(struct RAMSrcPageRequest));
    new_entry->rb = ramblock;
    new_entry->offset = start;
    new_entry->len = len;

    memory_region_ref(ramblock->mr);
    qemu_mutex_lock(&rs->src_page_req_mutex);
    QSIMPLEQ_INSERT_TAIL(&rs->src_page_requests, new_entry, next_req);
    migration_make_urgent_request();
    qemu_mutex_unlock(&rs->src_page_req_mutex);

    return 0;
}

static bool save_page_use_compression(RAMState *rs)
{
    if (!migrate_use_compression()) {
        return false;
    }

    /*
     * If xbzrle is on, stop using the data compression after first
     * round of migration even if compression is enabled. In theory,
     * xbzrle can do better than compression.
     */
    if (rs->ram_bulk_stage || !migrate_use_xbzrle()) {
        return true;
    }

    return false;
}

/*
 * try to compress the page before posting it out, return true if the page
 * has been properly handled by compression, otherwise needs other
 * paths to handle it
 */
static bool save_compress_page(RAMState *rs, RAMBlock *block, ram_addr_t offset)
{
    if (!save_page_use_compression(rs)) {
        return false;
    }

    /*
     * When starting the process of a new block, the first page of
     * the block should be sent out before other pages in the same
     * block, and all the pages in last block should have been sent
     * out, keeping this order is important, because the 'cont' flag
     * is used to avoid resending the block name.
     *
     * We post the fist page as normal page as compression will take
     * much CPU resource.
     */
    if (block != rs->last_sent_block) {
        flush_compressed_data(rs);
        return false;
    }

    if (compress_page_with_multi_thread(rs, block, offset) > 0) {
        return true;
    }

    compression_counters.busy++;
    return false;
}

/**
 * ram_save_target_page: save one target page
 *
 * Returns the number of pages written
 *
 * @rs: current RAM state
 * @pss: data about the page we want to send
 * @last_stage: if we are at the completion stage
 */
static int ram_save_target_page(RAMState *rs, PageSearchStatus *pss,
                                bool last_stage)
{
    RAMBlock *block = pss->block;
    ram_addr_t offset = pss->page << TARGET_PAGE_BITS;
    int res;

    if (control_save_page(rs, block, offset, &res)) {
        return res;
    }

    if (save_compress_page(rs, block, offset)) {
        return 1;
    }

    res = save_zero_page(rs, block, offset);
    if (res > 0) {
        /* Must let xbzrle know, otherwise a previous (now 0'd) cached
         * page would be stale
         */
        if (!save_page_use_compression(rs)) {
            XBZRLE_cache_lock();
            xbzrle_cache_zero_page(rs, block->offset + offset);
            XBZRLE_cache_unlock();
        }
        ram_release_pages(block->idstr, offset, res);
        return res;
    }

    /*
     * do not use multifd for compression as the first page in the new
     * block should be posted out before sending the compressed page
     */
    if (!save_page_use_compression(rs) && migrate_use_multifd()) {
        return ram_save_multifd_page(rs, block, offset);
    }

    return ram_save_page(rs, pss, last_stage);
}

/**
 * ram_save_host_page: save a whole host page
 *
 * Starting at *offset send pages up to the end of the current host
 * page. It's valid for the initial offset to point into the middle of
 * a host page in which case the remainder of the hostpage is sent.
 * Only dirty target pages are sent. Note that the host page size may
 * be a huge page for this block.
 * The saving stops at the boundary of the used_length of the block
 * if the RAMBlock isn't a multiple of the host page size.
 *
 * Returns the number of pages written or negative on error
 *
 * @rs: current RAM state
 * @ms: current migration state
 * @pss: data about the page we want to send
 * @last_stage: if we are at the completion stage
 */
static int ram_save_host_page(RAMState *rs, PageSearchStatus *pss,
                              bool last_stage)
{
    int tmppages, pages = 0;
    size_t pagesize_bits =
        qemu_ram_pagesize(pss->block) >> TARGET_PAGE_BITS;

    if (ramblock_is_ignored(pss->block)) {
        error_report("block %s should not be migrated !", pss->block->idstr);
        return 0;
    }

    do {
        /* Check the pages is dirty and if it is send it */
        if (!migration_bitmap_clear_dirty(rs, pss->block, pss->page)) {
            pss->page++;
            continue;
        }

        tmppages = ram_save_target_page(rs, pss, last_stage);
        if (tmppages < 0) {
            return tmppages;
        }

        pages += tmppages;
        pss->page++;
        /* Allow rate limiting to happen in the middle of huge pages */
        migration_rate_limit();
    } while ((pss->page & (pagesize_bits - 1)) &&
             offset_in_ramblock(pss->block, pss->page << TARGET_PAGE_BITS));

    /* The offset we leave with is the last one we looked at */
    pss->page--;
    return pages;
}

/**
 * ram_find_and_save_block: finds a dirty page and sends it to f
 *
 * Called within an RCU critical section.
 *
 * Returns the number of pages written where zero means no dirty pages,
 * or negative on error
 *
 * @rs: current RAM state
 * @last_stage: if we are at the completion stage
 *
 * On systems where host-page-size > target-page-size it will send all the
 * pages in a host page that are dirty.
 */

static int ram_find_and_save_block(RAMState *rs, bool last_stage)
{
    PageSearchStatus pss;
    int pages = 0;
    bool again, found;

    /* No dirty page as there is zero RAM */
    if (!ram_bytes_total()) {
        return pages;
    }

    pss.block = rs->last_seen_block;
    pss.page = rs->last_page;
    pss.complete_round = false;

    if (!pss.block) {
        pss.block = QLIST_FIRST_RCU(&ram_list.blocks);
    }

    do {
        again = true;
        found = get_queued_page(rs, &pss);

        if (!found) {
            /* priority queue empty, so just search for something dirty */
            found = find_dirty_block(rs, &pss, &again);
        }

        if (found) {
            pages = ram_save_host_page(rs, &pss, last_stage);
        }
    } while (!pages && again);

    rs->last_seen_block = pss.block;
    rs->last_page = pss.page;

    return pages;
}

void acct_update_position(QEMUFile *f, size_t size, bool zero)
{
    uint64_t pages = size / TARGET_PAGE_SIZE;

    if (zero) {
        ram_counters.duplicate += pages;
    } else {
        ram_counters.normal += pages;
        ram_counters.transferred += size;
        qemu_update_position(f, size);
    }
}

static uint64_t ram_bytes_total_common(bool count_ignored)
{
    RAMBlock *block;
    uint64_t total = 0;

    RCU_READ_LOCK_GUARD();

    if (count_ignored) {
        RAMBLOCK_FOREACH_MIGRATABLE(block) {
            total += block->used_length;
        }
    } else {
        RAMBLOCK_FOREACH_NOT_IGNORED(block) {
            total += block->used_length;
        }
    }
    return total;
}

uint64_t ram_bytes_total(void)
{
    return ram_bytes_total_common(false);
}

static void xbzrle_load_setup(void)
{
    XBZRLE.decoded_buf = g_malloc(TARGET_PAGE_SIZE);
}

static void xbzrle_load_cleanup(void)
{
    g_free(XBZRLE.decoded_buf);
    XBZRLE.decoded_buf = NULL;
}

static void ram_state_cleanup(RAMState **rsp)
{
    if (*rsp) {
        migration_page_queue_free(*rsp);
        qemu_mutex_destroy(&(*rsp)->bitmap_mutex);
        qemu_mutex_destroy(&(*rsp)->src_page_req_mutex);
        g_free(*rsp);
        *rsp = NULL;
    }
}

static void xbzrle_cleanup(void)
{
    XBZRLE_cache_lock();
    if (XBZRLE.cache) {
        cache_fini(XBZRLE.cache);
        g_free(XBZRLE.encoded_buf);
        g_free(XBZRLE.current_buf);
        g_free(XBZRLE.zero_target_page);
        XBZRLE.cache = NULL;
        XBZRLE.encoded_buf = NULL;
        XBZRLE.current_buf = NULL;
        XBZRLE.zero_target_page = NULL;
    }
    XBZRLE_cache_unlock();
}

static void ram_save_cleanup(void *opaque)
{
    RAMState **rsp = opaque;
    RAMBlock *block;

    /* caller have hold iothread lock or is in a bh, so there is
     * no writing race against the migration bitmap
     */
    memory_global_dirty_log_stop();

    RAMBLOCK_FOREACH_NOT_IGNORED(block) {
        g_free(block->clear_bmap);
        block->clear_bmap = NULL;
        g_free(block->bmap);
        block->bmap = NULL;
    }

    xbzrle_cleanup();
    compress_threads_save_cleanup();
    ram_state_cleanup(rsp);
}

static void ram_state_reset(RAMState *rs)
{
    rs->last_seen_block = NULL;
    rs->last_sent_block = NULL;
    rs->last_page = 0;
    rs->last_version = ram_list.version;
    rs->ram_bulk_stage = true;
    rs->fpo_enabled = false;
}

#define MAX_WAIT 50 /* ms, half buffered_file limit */

/*
 * 'expected' is the value you expect the bitmap mostly to be full
 * of; it won't bother printing lines that are all this value.
 * If 'todump' is null the migration bitmap is dumped.
 */
void ram_debug_dump_bitmap(unsigned long *todump, bool expected,
                           unsigned long pages)
{
    int64_t cur;
    int64_t linelen = 128;
    char linebuf[129];

    for (cur = 0; cur < pages; cur += linelen) {
        int64_t curb;
        bool found = false;
        /*
         * Last line; catch the case where the line length
         * is longer than remaining ram
         */
        if (cur + linelen > pages) {
            linelen = pages - cur;
        }
        for (curb = 0; curb < linelen; curb++) {
            bool thisbit = test_bit(cur + curb, todump);
            linebuf[curb] = thisbit ? '1' : '.';
            found = found || (thisbit != expected);
        }
        if (found) {
            linebuf[curb] = '\0';
            fprintf(stderr,  "0x%08" PRIx64 " : %s\n", cur, linebuf);
        }
    }
}

/* **** functions for postcopy ***** */

void ram_postcopy_migrated_memory_release(MigrationState *ms)
{
    struct RAMBlock *block;

    RAMBLOCK_FOREACH_NOT_IGNORED(block) {
        unsigned long *bitmap = block->bmap;
        unsigned long range = block->used_length >> TARGET_PAGE_BITS;
        unsigned long run_start = find_next_zero_bit(bitmap, range, 0);

        while (run_start < range) {
            unsigned long run_end = find_next_bit(bitmap, range, run_start + 1);
            ram_discard_range(block->idstr, run_start << TARGET_PAGE_BITS,
                              (run_end - run_start) << TARGET_PAGE_BITS);
            run_start = find_next_zero_bit(bitmap, range, run_end + 1);
        }
    }
}

/**
 * postcopy_send_discard_bm_ram: discard a RAMBlock
 *
 * Returns zero on success
 *
 * Callback from postcopy_each_ram_send_discard for each RAMBlock
 *
 * @ms: current migration state
 * @block: RAMBlock to discard
 */
static int postcopy_send_discard_bm_ram(MigrationState *ms, RAMBlock *block)
{
    unsigned long end = block->used_length >> TARGET_PAGE_BITS;
    unsigned long current;
    unsigned long *bitmap = block->bmap;

    for (current = 0; current < end; ) {
        unsigned long one = find_next_bit(bitmap, end, current);
        unsigned long zero, discard_length;

        if (one >= end) {
            break;
        }

        zero = find_next_zero_bit(bitmap, end, one + 1);

        if (zero >= end) {
            discard_length = end - one;
        } else {
            discard_length = zero - one;
        }
        postcopy_discard_send_range(ms, one, discard_length);
        current = one + discard_length;
    }

    return 0;
}

/**
 * postcopy_each_ram_send_discard: discard all RAMBlocks
 *
 * Returns 0 for success or negative for error
 *
 * Utility for the outgoing postcopy code.
 *   Calls postcopy_send_discard_bm_ram for each RAMBlock
 *   passing it bitmap indexes and name.
 * (qemu_ram_foreach_block ends up passing unscaled lengths
 *  which would mean postcopy code would have to deal with target page)
 *
 * @ms: current migration state
 */
static int postcopy_each_ram_send_discard(MigrationState *ms)
{
    struct RAMBlock *block;
    int ret;

    RAMBLOCK_FOREACH_NOT_IGNORED(block) {
        postcopy_discard_send_init(ms, block->idstr);

        /*
         * Postcopy sends chunks of bitmap over the wire, but it
         * just needs indexes at this point, avoids it having
         * target page specific code.
         */
        ret = postcopy_send_discard_bm_ram(ms, block);
        postcopy_discard_send_finish(ms);
        if (ret) {
            return ret;
        }
    }

    return 0;
}

/**
 * postcopy_chunk_hostpages_pass: canonicalize bitmap in hostpages
 *
 * Helper for postcopy_chunk_hostpages; it's called twice to
 * canonicalize the two bitmaps, that are similar, but one is
 * inverted.
 *
 * Postcopy requires that all target pages in a hostpage are dirty or
 * clean, not a mix.  This function canonicalizes the bitmaps.
 *
 * @ms: current migration state
 * @block: block that contains the page we want to canonicalize
 */
static void postcopy_chunk_hostpages_pass(MigrationState *ms, RAMBlock *block)
{
    RAMState *rs = ram_state;
    unsigned long *bitmap = block->bmap;
    unsigned int host_ratio = block->page_size / TARGET_PAGE_SIZE;
    unsigned long pages = block->used_length >> TARGET_PAGE_BITS;
    unsigned long run_start;

    if (block->page_size == TARGET_PAGE_SIZE) {
        /* Easy case - TPS==HPS for a non-huge page RAMBlock */
        return;
    }

    /* Find a dirty page */
    run_start = find_next_bit(bitmap, pages, 0);

    while (run_start < pages) {

        /*
         * If the start of this run of pages is in the middle of a host
         * page, then we need to fixup this host page.
         */
        if (QEMU_IS_ALIGNED(run_start, host_ratio)) {
            /* Find the end of this run */
            run_start = find_next_zero_bit(bitmap, pages, run_start + 1);
            /*
             * If the end isn't at the start of a host page, then the
             * run doesn't finish at the end of a host page
             * and we need to discard.
             */
        }

        if (!QEMU_IS_ALIGNED(run_start, host_ratio)) {
            unsigned long page;
            unsigned long fixup_start_addr = QEMU_ALIGN_DOWN(run_start,
                                                             host_ratio);
            run_start = QEMU_ALIGN_UP(run_start, host_ratio);

            /* Clean up the bitmap */
            for (page = fixup_start_addr;
                 page < fixup_start_addr + host_ratio; page++) {
                /*
                 * Remark them as dirty, updating the count for any pages
                 * that weren't previously dirty.
                 */
                rs->migration_dirty_pages += !test_and_set_bit(page, bitmap);
            }
        }

        /* Find the next dirty page for the next iteration */
        run_start = find_next_bit(bitmap, pages, run_start);
    }
}

/**
 * postcopy_chunk_hostpages: discard any partially sent host page
 *
 * Utility for the outgoing postcopy code.
 *
 * Discard any partially sent host-page size chunks, mark any partially
 * dirty host-page size chunks as all dirty.  In this case the host-page
 * is the host-page for the particular RAMBlock, i.e. it might be a huge page
 *
 * Returns zero on success
 *
 * @ms: current migration state
 * @block: block we want to work with
 */
static int postcopy_chunk_hostpages(MigrationState *ms, RAMBlock *block)
{
    postcopy_discard_send_init(ms, block->idstr);

    /*
     * Ensure that all partially dirty host pages are made fully dirty.
     */
    postcopy_chunk_hostpages_pass(ms, block);

    postcopy_discard_send_finish(ms);
    return 0;
}

/**
 * ram_postcopy_send_discard_bitmap: transmit the discard bitmap
 *
 * Returns zero on success
 *
 * Transmit the set of pages to be discarded after precopy to the target
 * these are pages that:
 *     a) Have been previously transmitted but are now dirty again
 *     b) Pages that have never been transmitted, this ensures that
 *        any pages on the destination that have been mapped by background
 *        tasks get discarded (transparent huge pages is the specific concern)
 * Hopefully this is pretty sparse
 *
 * @ms: current migration state
 */
int ram_postcopy_send_discard_bitmap(MigrationState *ms)
{
    RAMState *rs = ram_state;
    RAMBlock *block;
    int ret;

    RCU_READ_LOCK_GUARD();

    /* This should be our last sync, the src is now paused */
    migration_bitmap_sync(rs);

    /* Easiest way to make sure we don't resume in the middle of a host-page */
    rs->last_seen_block = NULL;
    rs->last_sent_block = NULL;
    rs->last_page = 0;

    RAMBLOCK_FOREACH_NOT_IGNORED(block) {
        /* Deal with TPS != HPS and huge pages */
        ret = postcopy_chunk_hostpages(ms, block);
        if (ret) {
            return ret;
        }

#ifdef DEBUG_POSTCOPY
        ram_debug_dump_bitmap(block->bmap, true,
                              block->used_length >> TARGET_PAGE_BITS);
#endif
    }
    trace_ram_postcopy_send_discard_bitmap();

    ret = postcopy_each_ram_send_discard(ms);

    return ret;
}

/**
 * ram_discard_range: discard dirtied pages at the beginning of postcopy
 *
 * Returns zero on success
 *
 * @rbname: name of the RAMBlock of the request. NULL means the
 *          same that last one.
 * @start: RAMBlock starting page
 * @length: RAMBlock size
 */
int ram_discard_range(const char *rbname, uint64_t start, size_t length)
{
    trace_ram_discard_range(rbname, start, length);

    RCU_READ_LOCK_GUARD();
    RAMBlock *rb = qemu_ram_block_by_name(rbname);

    if (!rb) {
        error_report("ram_discard_range: Failed to find block '%s'", rbname);
        return -1;
    }

    /*
     * On source VM, we don't need to update the received bitmap since
     * we don't even have one.
     */
    if (rb->receivedmap) {
        bitmap_clear(rb->receivedmap, start >> qemu_target_page_bits(),
                     length >> qemu_target_page_bits());
    }

    return ram_block_discard_range(rb, start, length);
}

/*
 * For every allocation, we will try not to crash the VM if the
 * allocation failed.
 */
static int xbzrle_init(void)
{
    Error *local_err = NULL;

    if (!migrate_use_xbzrle()) {
        return 0;
    }

    XBZRLE_cache_lock();

    XBZRLE.zero_target_page = g_try_malloc0(TARGET_PAGE_SIZE);
    if (!XBZRLE.zero_target_page) {
        error_report("%s: Error allocating zero page", __func__);
        goto err_out;
    }

    XBZRLE.cache = cache_init(migrate_xbzrle_cache_size(),
                              TARGET_PAGE_SIZE, &local_err);
    if (!XBZRLE.cache) {
        error_report_err(local_err);
        goto free_zero_page;
    }

    XBZRLE.encoded_buf = g_try_malloc0(TARGET_PAGE_SIZE);
    if (!XBZRLE.encoded_buf) {
        error_report("%s: Error allocating encoded_buf", __func__);
        goto free_cache;
    }

    XBZRLE.current_buf = g_try_malloc(TARGET_PAGE_SIZE);
    if (!XBZRLE.current_buf) {
        error_report("%s: Error allocating current_buf", __func__);
        goto free_encoded_buf;
    }

    /* We are all good */
    XBZRLE_cache_unlock();
    return 0;

free_encoded_buf:
    g_free(XBZRLE.encoded_buf);
    XBZRLE.encoded_buf = NULL;
free_cache:
    cache_fini(XBZRLE.cache);
    XBZRLE.cache = NULL;
free_zero_page:
    g_free(XBZRLE.zero_target_page);
    XBZRLE.zero_target_page = NULL;
err_out:
    XBZRLE_cache_unlock();
    return -ENOMEM;
}

static int ram_state_init(RAMState **rsp)
{
    *rsp = g_try_new0(RAMState, 1);

    if (!*rsp) {
        error_report("%s: Init ramstate fail", __func__);
        return -1;
    }

    qemu_mutex_init(&(*rsp)->bitmap_mutex);
    qemu_mutex_init(&(*rsp)->src_page_req_mutex);
    QSIMPLEQ_INIT(&(*rsp)->src_page_requests);

    /*
     * Count the total number of pages used by ram blocks not including any
     * gaps due to alignment or unplugs.
     * This must match with the initial values of dirty bitmap.
     */
    (*rsp)->migration_dirty_pages = ram_bytes_total() >> TARGET_PAGE_BITS;
    ram_state_reset(*rsp);

    return 0;
}

static void ram_list_init_bitmaps(void)
{
    MigrationState *ms = migrate_get_current();
    RAMBlock *block;
    unsigned long pages;
    uint8_t shift;

    /* Skip setting bitmap if there is no RAM */
    if (ram_bytes_total()) {
        shift = ms->clear_bitmap_shift;
        if (shift > CLEAR_BITMAP_SHIFT_MAX) {
            error_report("clear_bitmap_shift (%u) too big, using "
                         "max value (%u)", shift, CLEAR_BITMAP_SHIFT_MAX);
            shift = CLEAR_BITMAP_SHIFT_MAX;
        } else if (shift < CLEAR_BITMAP_SHIFT_MIN) {
            error_report("clear_bitmap_shift (%u) too small, using "
                         "min value (%u)", shift, CLEAR_BITMAP_SHIFT_MIN);
            shift = CLEAR_BITMAP_SHIFT_MIN;
        }

        RAMBLOCK_FOREACH_NOT_IGNORED(block) {
            pages = block->max_length >> TARGET_PAGE_BITS;
            /*
             * The initial dirty bitmap for migration must be set with all
             * ones to make sure we'll migrate every guest RAM page to
             * destination.
             * Here we set RAMBlock.bmap all to 1 because when rebegin a
             * new migration after a failed migration, ram_list.
             * dirty_memory[DIRTY_MEMORY_MIGRATION] don't include the whole
             * guest memory.
             */
            block->bmap = bitmap_new(pages);
            bitmap_set(block->bmap, 0, pages);
            block->clear_bmap_shift = shift;
            block->clear_bmap = bitmap_new(clear_bmap_size(pages, shift));
        }
    }
}

static void ram_init_bitmaps(RAMState *rs)
{
    /* For memory_global_dirty_log_start below.  */
    qemu_mutex_lock_iothread();
    qemu_mutex_lock_ramlist();

    WITH_RCU_READ_LOCK_GUARD() {
        ram_list_init_bitmaps();
        memory_global_dirty_log_start();
        migration_bitmap_sync_precopy(rs);
    }
    qemu_mutex_unlock_ramlist();
    qemu_mutex_unlock_iothread();
}

static int ram_init_all(RAMState **rsp)
{
    if (ram_state_init(rsp)) {
        return -1;
    }

    if (xbzrle_init()) {
        ram_state_cleanup(rsp);
        return -1;
    }

    ram_init_bitmaps(*rsp);

    return 0;
}

static void ram_state_resume_prepare(RAMState *rs, QEMUFile *out)
{
    RAMBlock *block;
    uint64_t pages = 0;

    /*
     * Postcopy is not using xbzrle/compression, so no need for that.
     * Also, since source are already halted, we don't need to care
     * about dirty page logging as well.
     */

    RAMBLOCK_FOREACH_NOT_IGNORED(block) {
        pages += bitmap_count_one(block->bmap,
                                  block->used_length >> TARGET_PAGE_BITS);
    }

    /* This may not be aligned with current bitmaps. Recalculate. */
    rs->migration_dirty_pages = pages;

    rs->last_seen_block = NULL;
    rs->last_sent_block = NULL;
    rs->last_page = 0;
    rs->last_version = ram_list.version;
    /*
     * Disable the bulk stage, otherwise we'll resend the whole RAM no
     * matter what we have sent.
     */
    rs->ram_bulk_stage = false;

    /* Update RAMState cache of output QEMUFile */
    rs->f = out;

    trace_ram_state_resume_prepare(pages);
}

/*
 * This function clears bits of the free pages reported by the caller from the
 * migration dirty bitmap. @addr is the host address corresponding to the
 * start of the continuous guest free pages, and @len is the total bytes of
 * those pages.
 */
void qemu_guest_free_page_hint(void *addr, size_t len)
{
    RAMBlock *block;
    ram_addr_t offset;
    size_t used_len, start, npages;
    MigrationState *s = migrate_get_current();

    /* This function is currently expected to be used during live migration */
    if (!migration_is_setup_or_active(s->state)) {
        return;
    }

    for (; len > 0; len -= used_len, addr += used_len) {
        block = qemu_ram_block_from_host(addr, false, &offset);
        if (unlikely(!block || offset >= block->used_length)) {
            /*
             * The implementation might not support RAMBlock resize during
             * live migration, but it could happen in theory with future
             * updates. So we add a check here to capture that case.
             */
            error_report_once("%s unexpected error", __func__);
            return;
        }

        if (len <= block->used_length - offset) {
            used_len = len;
        } else {
            used_len = block->used_length - offset;
        }

        start = offset >> TARGET_PAGE_BITS;
        npages = used_len >> TARGET_PAGE_BITS;

        qemu_mutex_lock(&ram_state->bitmap_mutex);
        ram_state->migration_dirty_pages -=
                      bitmap_count_one_with_offset(block->bmap, start, npages);
        bitmap_clear(block->bmap, start, npages);
        qemu_mutex_unlock(&ram_state->bitmap_mutex);
    }
}

/*
 * Each of ram_save_setup, ram_save_iterate and ram_save_complete has
 * long-running RCU critical section.  When rcu-reclaims in the code
 * start to become numerous it will be necessary to reduce the
 * granularity of these critical sections.
 */

/**
 * ram_save_setup: Setup RAM for migration
 *
 * Returns zero to indicate success and negative for error
 *
 * @f: QEMUFile where to send the data
 * @opaque: RAMState pointer
 */
static int ram_save_setup(QEMUFile *f, void *opaque)
{
    RAMState **rsp = opaque;
    RAMBlock *block;

    if (compress_threads_save_setup()) {
        return -1;
    }

    /* migration has already setup the bitmap, reuse it. */
    if (!migration_in_colo_state()) {
        if (ram_init_all(rsp) != 0) {
            compress_threads_save_cleanup();
            return -1;
        }
    }
    (*rsp)->f = f;

    WITH_RCU_READ_LOCK_GUARD() {
        qemu_put_be64(f, ram_bytes_total_common(true) | RAM_SAVE_FLAG_MEM_SIZE);

        RAMBLOCK_FOREACH_MIGRATABLE(block) {
            qemu_put_byte(f, strlen(block->idstr));
            qemu_put_buffer(f, (uint8_t *)block->idstr, strlen(block->idstr));
            qemu_put_be64(f, block->used_length);
            if (migrate_postcopy_ram() && block->page_size !=
                                          qemu_host_page_size) {
                qemu_put_be64(f, block->page_size);
            }
            if (migrate_ignore_shared()) {
                qemu_put_be64(f, block->mr->addr);
            }
        }
    }

    ram_control_before_iterate(f, RAM_CONTROL_SETUP);
    ram_control_after_iterate(f, RAM_CONTROL_SETUP);

    multifd_send_sync_main(*rsp);
    qemu_put_be64(f, RAM_SAVE_FLAG_EOS);
    qemu_fflush(f);

    return 0;
}

/**
 * ram_save_iterate: iterative stage for migration
 *
 * Returns zero to indicate success and negative for error
 *
 * @f: QEMUFile where to send the data
 * @opaque: RAMState pointer
 */
static int ram_save_iterate(QEMUFile *f, void *opaque)
{
    RAMState **temp = opaque;
    RAMState *rs = *temp;
    int ret;
    int i;
    int64_t t0;
    int done = 0;

    if (blk_mig_bulk_active()) {
        /* Avoid transferring ram during bulk phase of block migration as
         * the bulk phase will usually take a long time and transferring
         * ram updates during that time is pointless. */
        goto out;
    }

    WITH_RCU_READ_LOCK_GUARD() {
        if (ram_list.version != rs->last_version) {
            ram_state_reset(rs);
        }

        /* Read version before ram_list.blocks */
        smp_rmb();

        ram_control_before_iterate(f, RAM_CONTROL_ROUND);

        t0 = qemu_clock_get_ns(QEMU_CLOCK_REALTIME);
        i = 0;
        while ((ret = qemu_file_rate_limit(f)) == 0 ||
                !QSIMPLEQ_EMPTY(&rs->src_page_requests)) {
            int pages;

            if (qemu_file_get_error(f)) {
                break;
            }

            pages = ram_find_and_save_block(rs, false);
            /* no more pages to sent */
            if (pages == 0) {
                done = 1;
                break;
            }

            if (pages < 0) {
                qemu_file_set_error(f, pages);
                break;
            }

            rs->target_page_count += pages;

            /*
             * we want to check in the 1st loop, just in case it was the 1st
             * time and we had to sync the dirty bitmap.
             * qemu_clock_get_ns() is a bit expensive, so we only check each
             * some iterations
             */
            if ((i & 63) == 0) {
                uint64_t t1 = (qemu_clock_get_ns(QEMU_CLOCK_REALTIME) - t0) /
                              1000000;
                if (t1 > MAX_WAIT) {
                    trace_ram_save_iterate_big_wait(t1, i);
                    break;
                }
            }
            i++;
        }
    }

    /*
     * Must occur before EOS (or any QEMUFile operation)
     * because of RDMA protocol.
     */
    ram_control_after_iterate(f, RAM_CONTROL_ROUND);

out:
    multifd_send_sync_main(rs);
    qemu_put_be64(f, RAM_SAVE_FLAG_EOS);
    qemu_fflush(f);
    ram_counters.transferred += 8;

    ret = qemu_file_get_error(f);
    if (ret < 0) {
        return ret;
    }

    return done;
}

/**
 * ram_save_complete: function called to send the remaining amount of ram
 *
 * Returns zero to indicate success or negative on error
 *
 * Called with iothread lock
 *
 * @f: QEMUFile where to send the data
 * @opaque: RAMState pointer
 */
static int ram_save_complete(QEMUFile *f, void *opaque)
{
    RAMState **temp = opaque;
    RAMState *rs = *temp;
    int ret = 0;

    WITH_RCU_READ_LOCK_GUARD() {
        if (!migration_in_postcopy()) {
            migration_bitmap_sync_precopy(rs);
        }

        ram_control_before_iterate(f, RAM_CONTROL_FINISH);

        /* try transferring iterative blocks of memory */

        /* flush all remaining blocks regardless of rate limiting */
        while (true) {
            int pages;

            pages = ram_find_and_save_block(rs, !migration_in_colo_state());
            /* no more blocks to sent */
            if (pages == 0) {
                break;
            }
            if (pages < 0) {
                ret = pages;
                break;
            }
        }

        flush_compressed_data(rs);
        ram_control_after_iterate(f, RAM_CONTROL_FINISH);
    }

    multifd_send_sync_main(rs);
    qemu_put_be64(f, RAM_SAVE_FLAG_EOS);
    qemu_fflush(f);

    return ret;
}

static void ram_save_pending(QEMUFile *f, void *opaque, uint64_t max_size,
                             uint64_t *res_precopy_only,
                             uint64_t *res_compatible,
                             uint64_t *res_postcopy_only)
{
    RAMState **temp = opaque;
    RAMState *rs = *temp;
    uint64_t remaining_size;

    remaining_size = rs->migration_dirty_pages * TARGET_PAGE_SIZE;

    if (!migration_in_postcopy() &&
        remaining_size < max_size) {
        qemu_mutex_lock_iothread();
        WITH_RCU_READ_LOCK_GUARD() {
            migration_bitmap_sync_precopy(rs);
        }
        qemu_mutex_unlock_iothread();
        remaining_size = rs->migration_dirty_pages * TARGET_PAGE_SIZE;
    }

    if (migrate_postcopy_ram()) {
        /* We can do postcopy, and all the data is postcopiable */
        *res_compatible += remaining_size;
    } else {
        *res_precopy_only += remaining_size;
    }
}

static int load_xbzrle(QEMUFile *f, ram_addr_t addr, void *host)
{
    unsigned int xh_len;
    int xh_flags;
    uint8_t *loaded_data;

    /* extract RLE header */
    xh_flags = qemu_get_byte(f);
    xh_len = qemu_get_be16(f);

    if (xh_flags != ENCODING_FLAG_XBZRLE) {
        error_report("Failed to load XBZRLE page - wrong compression!");
        return -1;
    }

    if (xh_len > TARGET_PAGE_SIZE) {
        error_report("Failed to load XBZRLE page - len overflow!");
        return -1;
    }
    loaded_data = XBZRLE.decoded_buf;
    /* load data and decode */
    /* it can change loaded_data to point to an internal buffer */
    qemu_get_buffer_in_place(f, &loaded_data, xh_len);

    /* decode RLE */
    if (xbzrle_decode_buffer(loaded_data, xh_len, host,
                             TARGET_PAGE_SIZE) == -1) {
        error_report("Failed to load XBZRLE page - decode error!");
        return -1;
    }

    return 0;
}

/**
 * ram_block_from_stream: read a RAMBlock id from the migration stream
 *
 * Must be called from within a rcu critical section.
 *
 * Returns a pointer from within the RCU-protected ram_list.
 *
 * @f: QEMUFile where to read the data from
 * @flags: Page flags (mostly to see if it's a continuation of previous block)
 */
static inline RAMBlock *ram_block_from_stream(QEMUFile *f, int flags)
{
    static RAMBlock *block = NULL;
    char id[256];
    uint8_t len;

    if (flags & RAM_SAVE_FLAG_CONTINUE) {
        if (!block) {
            error_report("Ack, bad migration stream!");
            return NULL;
        }
        return block;
    }

    len = qemu_get_byte(f);
    qemu_get_buffer(f, (uint8_t *)id, len);
    id[len] = 0;

    block = qemu_ram_block_by_name(id);
    if (!block) {
        error_report("Can't find block %s", id);
        return NULL;
    }

    if (ramblock_is_ignored(block)) {
        error_report("block %s should not be migrated !", id);
        return NULL;
    }

    return block;
}

static inline void *host_from_ram_block_offset(RAMBlock *block,
                                               ram_addr_t offset)
{
    if (!offset_in_ramblock(block, offset)) {
        return NULL;
    }

    return block->host + offset;
}

static inline void *colo_cache_from_block_offset(RAMBlock *block,
                                                 ram_addr_t offset)
{
    if (!offset_in_ramblock(block, offset)) {
        return NULL;
    }
    if (!block->colo_cache) {
        error_report("%s: colo_cache is NULL in block :%s",
                     __func__, block->idstr);
        return NULL;
    }

    /*
    * During colo checkpoint, we need bitmap of these migrated pages.
    * It help us to decide which pages in ram cache should be flushed
    * into VM's RAM later.
    */
    if (!test_and_set_bit(offset >> TARGET_PAGE_BITS, block->bmap)) {
        ram_state->migration_dirty_pages++;
    }
    return block->colo_cache + offset;
}

/**
 * ram_handle_compressed: handle the zero page case
 *
 * If a page (or a whole RDMA chunk) has been
 * determined to be zero, then zap it.
 *
 * @host: host address for the zero page
 * @ch: what the page is filled from.  We only support zero
 * @size: size of the zero page
 */
void ram_handle_compressed(void *host, uint8_t ch, uint64_t size)
{
    if (ch != 0 || !is_zero_range(host, size)) {
        memset(host, ch, size);
    }
}

/* return the size after decompression, or negative value on error */
static int
qemu_uncompress_data(z_stream *stream, uint8_t *dest, size_t dest_len,
                     const uint8_t *source, size_t source_len)
{
    int err;

    err = inflateReset(stream);
    if (err != Z_OK) {
        return -1;
    }

    stream->avail_in = source_len;
    stream->next_in = (uint8_t *)source;
    stream->avail_out = dest_len;
    stream->next_out = dest;

    err = inflate(stream, Z_NO_FLUSH);
    if (err != Z_STREAM_END) {
        return -1;
    }

    return stream->total_out;
}

static void *do_data_decompress(void *opaque)
{
    DecompressParam *param = opaque;
    unsigned long pagesize;
    uint8_t *des;
    int len, ret;

    qemu_mutex_lock(&param->mutex);
    while (!param->quit) {
        if (param->des) {
            des = param->des;
            len = param->len;
            param->des = 0;
            qemu_mutex_unlock(&param->mutex);

            pagesize = TARGET_PAGE_SIZE;

            ret = qemu_uncompress_data(&param->stream, des, pagesize,
                                       param->compbuf, len);
            if (ret < 0 && migrate_get_current()->decompress_error_check) {
                error_report("decompress data failed");
                qemu_file_set_error(decomp_file, ret);
            }

            qemu_mutex_lock(&decomp_done_lock);
            param->done = true;
            qemu_cond_signal(&decomp_done_cond);
            qemu_mutex_unlock(&decomp_done_lock);

            qemu_mutex_lock(&param->mutex);
        } else {
            qemu_cond_wait(&param->cond, &param->mutex);
        }
    }
    qemu_mutex_unlock(&param->mutex);

    return NULL;
}

static int wait_for_decompress_done(void)
{
    int idx, thread_count;

    if (!migrate_use_compression()) {
        return 0;
    }

    thread_count = migrate_decompress_threads();
    qemu_mutex_lock(&decomp_done_lock);
    for (idx = 0; idx < thread_count; idx++) {
        while (!decomp_param[idx].done) {
            qemu_cond_wait(&decomp_done_cond, &decomp_done_lock);
        }
    }
    qemu_mutex_unlock(&decomp_done_lock);
    return qemu_file_get_error(decomp_file);
}

static void compress_threads_load_cleanup(void)
{
    int i, thread_count;

    if (!migrate_use_compression()) {
        return;
    }
    thread_count = migrate_decompress_threads();
    for (i = 0; i < thread_count; i++) {
        /*
         * we use it as a indicator which shows if the thread is
         * properly init'd or not
         */
        if (!decomp_param[i].compbuf) {
            break;
        }

        qemu_mutex_lock(&decomp_param[i].mutex);
        decomp_param[i].quit = true;
        qemu_cond_signal(&decomp_param[i].cond);
        qemu_mutex_unlock(&decomp_param[i].mutex);
    }
    for (i = 0; i < thread_count; i++) {
        if (!decomp_param[i].compbuf) {
            break;
        }

        qemu_thread_join(decompress_threads + i);
        qemu_mutex_destroy(&decomp_param[i].mutex);
        qemu_cond_destroy(&decomp_param[i].cond);
        inflateEnd(&decomp_param[i].stream);
        g_free(decomp_param[i].compbuf);
        decomp_param[i].compbuf = NULL;
    }
    g_free(decompress_threads);
    g_free(decomp_param);
    decompress_threads = NULL;
    decomp_param = NULL;
    decomp_file = NULL;
}

static int compress_threads_load_setup(QEMUFile *f)
{
    int i, thread_count;

    if (!migrate_use_compression()) {
        return 0;
    }

    thread_count = migrate_decompress_threads();
    decompress_threads = g_new0(QemuThread, thread_count);
    decomp_param = g_new0(DecompressParam, thread_count);
    qemu_mutex_init(&decomp_done_lock);
    qemu_cond_init(&decomp_done_cond);
    decomp_file = f;
    for (i = 0; i < thread_count; i++) {
        if (inflateInit(&decomp_param[i].stream) != Z_OK) {
            goto exit;
        }

        decomp_param[i].compbuf = g_malloc0(compressBound(TARGET_PAGE_SIZE));
        qemu_mutex_init(&decomp_param[i].mutex);
        qemu_cond_init(&decomp_param[i].cond);
        decomp_param[i].done = true;
        decomp_param[i].quit = false;
        qemu_thread_create(decompress_threads + i, "decompress",
                           do_data_decompress, decomp_param + i,
                           QEMU_THREAD_JOINABLE);
    }
    return 0;
exit:
    compress_threads_load_cleanup();
    return -1;
}

static void decompress_data_with_multi_threads(QEMUFile *f,
                                               void *host, int len)
{
    int idx, thread_count;

    thread_count = migrate_decompress_threads();
    qemu_mutex_lock(&decomp_done_lock);
    while (true) {
        for (idx = 0; idx < thread_count; idx++) {
            if (decomp_param[idx].done) {
                decomp_param[idx].done = false;
                qemu_mutex_lock(&decomp_param[idx].mutex);
                qemu_get_buffer(f, decomp_param[idx].compbuf, len);
                decomp_param[idx].des = host;
                decomp_param[idx].len = len;
                qemu_cond_signal(&decomp_param[idx].cond);
                qemu_mutex_unlock(&decomp_param[idx].mutex);
                break;
            }
        }
        if (idx < thread_count) {
            break;
        } else {
            qemu_cond_wait(&decomp_done_cond, &decomp_done_lock);
        }
    }
    qemu_mutex_unlock(&decomp_done_lock);
}

/*
 * colo cache: this is for secondary VM, we cache the whole
 * memory of the secondary VM, it is need to hold the global lock
 * to call this helper.
 */
int colo_init_ram_cache(void)
{
    RAMBlock *block;

    WITH_RCU_READ_LOCK_GUARD() {
        RAMBLOCK_FOREACH_NOT_IGNORED(block) {
            block->colo_cache = qemu_anon_ram_alloc(block->used_length,
                                                    NULL,
                                                    false);
            if (!block->colo_cache) {
                error_report("%s: Can't alloc memory for COLO cache of block %s,"
                             "size 0x" RAM_ADDR_FMT, __func__, block->idstr,
                             block->used_length);
                RAMBLOCK_FOREACH_NOT_IGNORED(block) {
                    if (block->colo_cache) {
                        qemu_anon_ram_free(block->colo_cache, block->used_length);
                        block->colo_cache = NULL;
                    }
                }
                return -errno;
            }
            memcpy(block->colo_cache, block->host, block->used_length);
        }
    }

    /*
    * Record the dirty pages that sent by PVM, we use this dirty bitmap together
    * with to decide which page in cache should be flushed into SVM's RAM. Here
    * we use the same name 'ram_bitmap' as for migration.
    */
    if (ram_bytes_total()) {
        RAMBlock *block;

        RAMBLOCK_FOREACH_NOT_IGNORED(block) {
            unsigned long pages = block->max_length >> TARGET_PAGE_BITS;

            block->bmap = bitmap_new(pages);
            bitmap_set(block->bmap, 0, pages);
        }
    }
    ram_state = g_new0(RAMState, 1);
    ram_state->migration_dirty_pages = 0;
    qemu_mutex_init(&ram_state->bitmap_mutex);
    memory_global_dirty_log_start();

    return 0;
}

/* It is need to hold the global lock to call this helper */
void colo_release_ram_cache(void)
{
    RAMBlock *block;

    memory_global_dirty_log_stop();
    RAMBLOCK_FOREACH_NOT_IGNORED(block) {
        g_free(block->bmap);
        block->bmap = NULL;
    }

    WITH_RCU_READ_LOCK_GUARD() {
        RAMBLOCK_FOREACH_NOT_IGNORED(block) {
            if (block->colo_cache) {
                qemu_anon_ram_free(block->colo_cache, block->used_length);
                block->colo_cache = NULL;
            }
        }
    }
    qemu_mutex_destroy(&ram_state->bitmap_mutex);
    g_free(ram_state);
    ram_state = NULL;
}

/**
 * ram_load_setup: Setup RAM for migration incoming side
 *
 * Returns zero to indicate success and negative for error
 *
 * @f: QEMUFile where to receive the data
 * @opaque: RAMState pointer
 */
static int ram_load_setup(QEMUFile *f, void *opaque)
{
    if (compress_threads_load_setup(f)) {
        return -1;
    }

    xbzrle_load_setup();
    ramblock_recv_map_init();

    return 0;
}

static int ram_load_cleanup(void *opaque)
{
    RAMBlock *rb;

    RAMBLOCK_FOREACH_NOT_IGNORED(rb) {
        qemu_ram_block_writeback(rb);
    }

    xbzrle_load_cleanup();
    compress_threads_load_cleanup();

    RAMBLOCK_FOREACH_NOT_IGNORED(rb) {
        g_free(rb->receivedmap);
        rb->receivedmap = NULL;
    }

    return 0;
}

/**
 * ram_postcopy_incoming_init: allocate postcopy data structures
 *
 * Returns 0 for success and negative if there was one error
 *
 * @mis: current migration incoming state
 *
 * Allocate data structures etc needed by incoming migration with
 * postcopy-ram. postcopy-ram's similarly names
 * postcopy_ram_incoming_init does the work.
 */
int ram_postcopy_incoming_init(MigrationIncomingState *mis)
{
    return postcopy_ram_incoming_init(mis);
}

/**
 * ram_load_postcopy: load a page in postcopy case
 *
 * Returns 0 for success or -errno in case of error
 *
 * Called in postcopy mode by ram_load().
 * rcu_read_lock is taken prior to this being called.
 *
 * @f: QEMUFile where to send the data
 */
static int ram_load_postcopy(QEMUFile *f)
{
    int flags = 0, ret = 0;
    bool place_needed = false;
    bool matches_target_page_size = false;
    MigrationIncomingState *mis = migration_incoming_get_current();
    /* Temporary page that is later 'placed' */
    void *postcopy_host_page = mis->postcopy_tmp_page;
    void *this_host = NULL;
    bool all_zero = false;
    int target_pages = 0;

    while (!ret && !(flags & RAM_SAVE_FLAG_EOS)) {
        ram_addr_t addr;
        void *host = NULL;
        void *page_buffer = NULL;
        void *place_source = NULL;
        RAMBlock *block = NULL;
        uint8_t ch;

        addr = qemu_get_be64(f);

        /*
         * If qemu file error, we should stop here, and then "addr"
         * may be invalid
         */
        ret = qemu_file_get_error(f);
        if (ret) {
            break;
        }

        flags = addr & ~TARGET_PAGE_MASK;
        addr &= TARGET_PAGE_MASK;

        trace_ram_load_postcopy_loop((uint64_t)addr, flags);
        place_needed = false;
        if (flags & (RAM_SAVE_FLAG_ZERO | RAM_SAVE_FLAG_PAGE)) {
            block = ram_block_from_stream(f, flags);

            host = host_from_ram_block_offset(block, addr);
            if (!host) {
                error_report("Illegal RAM offset " RAM_ADDR_FMT, addr);
                ret = -EINVAL;
                break;
            }
            target_pages++;
            matches_target_page_size = block->page_size == TARGET_PAGE_SIZE;
            /*
             * Postcopy requires that we place whole host pages atomically;
             * these may be huge pages for RAMBlocks that are backed by
             * hugetlbfs.
             * To make it atomic, the data is read into a temporary page
             * that's moved into place later.
             * The migration protocol uses,  possibly smaller, target-pages
             * however the source ensures it always sends all the components
             * of a host page in one chunk.
             */
            page_buffer = postcopy_host_page +
                          ((uintptr_t)host & (block->page_size - 1));
            /* If all TP are zero then we can optimise the place */
            if (target_pages == 1) {
                all_zero = true;
                this_host = (void *)QEMU_ALIGN_DOWN((uintptr_t)host,
                                                    block->page_size);
            } else {
                /* not the 1st TP within the HP */
                if (QEMU_ALIGN_DOWN((uintptr_t)host, block->page_size) !=
                    (uintptr_t)this_host) {
                    error_report("Non-same host page %p/%p",
                                  host, this_host);
                    ret = -EINVAL;
                    break;
                }
            }

            /*
             * If it's the last part of a host page then we place the host
             * page
             */
            if (target_pages == (block->page_size / TARGET_PAGE_SIZE)) {
                place_needed = true;
                target_pages = 0;
            }
            place_source = postcopy_host_page;
        }

        switch (flags & ~RAM_SAVE_FLAG_CONTINUE) {
        case RAM_SAVE_FLAG_ZERO:
            ch = qemu_get_byte(f);
            /*
             * Can skip to set page_buffer when
             * this is a zero page and (block->page_size == TARGET_PAGE_SIZE).
             */
            if (ch || !matches_target_page_size) {
                memset(page_buffer, ch, TARGET_PAGE_SIZE);
            }
            if (ch) {
                all_zero = false;
            }
            break;

        case RAM_SAVE_FLAG_PAGE:
            all_zero = false;
            if (!matches_target_page_size) {
                /* For huge pages, we always use temporary buffer */
                qemu_get_buffer(f, page_buffer, TARGET_PAGE_SIZE);
            } else {
                /*
                 * For small pages that matches target page size, we
                 * avoid the qemu_file copy.  Instead we directly use
                 * the buffer of QEMUFile to place the page.  Note: we
                 * cannot do any QEMUFile operation before using that
                 * buffer to make sure the buffer is valid when
                 * placing the page.
                 */
                qemu_get_buffer_in_place(f, (uint8_t **)&place_source,
                                         TARGET_PAGE_SIZE);
            }
            break;
        case RAM_SAVE_FLAG_EOS:
            /* normal exit */
            multifd_recv_sync_main();
            break;
        default:
            error_report("Unknown combination of migration flags: %#x"
                         " (postcopy mode)", flags);
            ret = -EINVAL;
            break;
        }

        /* Detect for any possible file errors */
        if (!ret && qemu_file_get_error(f)) {
            ret = qemu_file_get_error(f);
        }

        if (!ret && place_needed) {
            /* This gets called at the last target page in the host page */
            void *place_dest = (void *)QEMU_ALIGN_DOWN((uintptr_t)host,
                                                       block->page_size);

            if (all_zero) {
                ret = postcopy_place_page_zero(mis, place_dest,
                                               block);
            } else {
                ret = postcopy_place_page(mis, place_dest,
                                          place_source, block);
            }
        }
    }

    return ret;
}

static bool postcopy_is_advised(void)
{
    PostcopyState ps = postcopy_state_get();
    return ps >= POSTCOPY_INCOMING_ADVISE && ps < POSTCOPY_INCOMING_END;
}

static bool postcopy_is_running(void)
{
    PostcopyState ps = postcopy_state_get();
    return ps >= POSTCOPY_INCOMING_LISTENING && ps < POSTCOPY_INCOMING_END;
}

/*
 * Flush content of RAM cache into SVM's memory.
 * Only flush the pages that be dirtied by PVM or SVM or both.
 */
static void colo_flush_ram_cache(void)
{
    RAMBlock *block = NULL;
    void *dst_host;
    void *src_host;
    unsigned long offset = 0;

    memory_global_dirty_log_sync();
    WITH_RCU_READ_LOCK_GUARD() {
        RAMBLOCK_FOREACH_NOT_IGNORED(block) {
            ramblock_sync_dirty_bitmap(ram_state, block);
        }
    }

    trace_colo_flush_ram_cache_begin(ram_state->migration_dirty_pages);
    WITH_RCU_READ_LOCK_GUARD() {
        block = QLIST_FIRST_RCU(&ram_list.blocks);

        while (block) {
            offset = migration_bitmap_find_dirty(ram_state, block, offset);

            if (offset << TARGET_PAGE_BITS >= block->used_length) {
                offset = 0;
                block = QLIST_NEXT_RCU(block, next);
            } else {
                migration_bitmap_clear_dirty(ram_state, block, offset);
                dst_host = block->host + (offset << TARGET_PAGE_BITS);
                src_host = block->colo_cache + (offset << TARGET_PAGE_BITS);
                memcpy(dst_host, src_host, TARGET_PAGE_SIZE);
            }
        }
    }
    trace_colo_flush_ram_cache_end();
}

/**
 * ram_load_precopy: load pages in precopy case
 *
 * Returns 0 for success or -errno in case of error
 *
 * Called in precopy mode by ram_load().
 * rcu_read_lock is taken prior to this being called.
 *
 * @f: QEMUFile where to send the data
 */
static int ram_load_precopy(QEMUFile *f)
{
    int flags = 0, ret = 0, invalid_flags = 0, len = 0, i = 0;
    /* ADVISE is earlier, it shows the source has the postcopy capability on */
    bool postcopy_advised = postcopy_is_advised();
    if (!migrate_use_compression()) {
        invalid_flags |= RAM_SAVE_FLAG_COMPRESS_PAGE;
    }

    while (!ret && !(flags & RAM_SAVE_FLAG_EOS)) {
        ram_addr_t addr, total_ram_bytes;
        void *host = NULL;
        uint8_t ch;

        /*
         * Yield periodically to let main loop run, but an iteration of
         * the main loop is expensive, so do it each some iterations
         */
        if ((i & 32767) == 0 && qemu_in_coroutine()) {
            aio_co_schedule(qemu_get_current_aio_context(),
                            qemu_coroutine_self());
            qemu_coroutine_yield();
        }
        i++;

        addr = qemu_get_be64(f);
        flags = addr & ~TARGET_PAGE_MASK;
        addr &= TARGET_PAGE_MASK;

        if (flags & invalid_flags) {
            if (flags & invalid_flags & RAM_SAVE_FLAG_COMPRESS_PAGE) {
                error_report("Received an unexpected compressed page");
            }

            ret = -EINVAL;
            break;
        }

        if (flags & (RAM_SAVE_FLAG_ZERO | RAM_SAVE_FLAG_PAGE |
                     RAM_SAVE_FLAG_COMPRESS_PAGE | RAM_SAVE_FLAG_XBZRLE)) {
            RAMBlock *block = ram_block_from_stream(f, flags);

            /*
             * After going into COLO, we should load the Page into colo_cache.
             */
            if (migration_incoming_in_colo_state()) {
                host = colo_cache_from_block_offset(block, addr);
            } else {
                host = host_from_ram_block_offset(block, addr);
            }
            if (!host) {
                error_report("Illegal RAM offset " RAM_ADDR_FMT, addr);
                ret = -EINVAL;
                break;
            }

            if (!migration_incoming_in_colo_state()) {
                ramblock_recv_bitmap_set(block, host);
            }

            trace_ram_load_loop(block->idstr, (uint64_t)addr, flags, host);
        }

        switch (flags & ~RAM_SAVE_FLAG_CONTINUE) {
        case RAM_SAVE_FLAG_MEM_SIZE:
            /* Synchronize RAM block list */
            total_ram_bytes = addr;
            while (!ret && total_ram_bytes) {
                RAMBlock *block;
                char id[256];
                ram_addr_t length;

                len = qemu_get_byte(f);
                qemu_get_buffer(f, (uint8_t *)id, len);
                id[len] = 0;
                length = qemu_get_be64(f);

                block = qemu_ram_block_by_name(id);
                if (block && !qemu_ram_is_migratable(block)) {
                    error_report("block %s should not be migrated !", id);
                    ret = -EINVAL;
                } else if (block) {
                    if (length != block->used_length) {
                        Error *local_err = NULL;

                        ret = qemu_ram_resize(block, length,
                                              &local_err);
                        if (local_err) {
                            error_report_err(local_err);
                        }
                    }
                    /* For postcopy we need to check hugepage sizes match */
                    if (postcopy_advised &&
                        block->page_size != qemu_host_page_size) {
                        uint64_t remote_page_size = qemu_get_be64(f);
                        if (remote_page_size != block->page_size) {
                            error_report("Mismatched RAM page size %s "
                                         "(local) %zd != %" PRId64,
                                         id, block->page_size,
                                         remote_page_size);
                            ret = -EINVAL;
                        }
                    }
                    if (migrate_ignore_shared()) {
                        hwaddr addr = qemu_get_be64(f);
                        if (ramblock_is_ignored(block) &&
                            block->mr->addr != addr) {
                            error_report("Mismatched GPAs for block %s "
                                         "%" PRId64 "!= %" PRId64,
                                         id, (uint64_t)addr,
                                         (uint64_t)block->mr->addr);
                            ret = -EINVAL;
                        }
                    }
                    ram_control_load_hook(f, RAM_CONTROL_BLOCK_REG,
                                          block->idstr);
                } else {
                    error_report("Unknown ramblock \"%s\", cannot "
                                 "accept migration", id);
                    ret = -EINVAL;
                }

                total_ram_bytes -= length;
            }
            break;

        case RAM_SAVE_FLAG_ZERO:
            ch = qemu_get_byte(f);
            ram_handle_compressed(host, ch, TARGET_PAGE_SIZE);
            break;

        case RAM_SAVE_FLAG_PAGE:
            qemu_get_buffer(f, host, TARGET_PAGE_SIZE);
            break;

        case RAM_SAVE_FLAG_COMPRESS_PAGE:
            len = qemu_get_be32(f);
            if (len < 0 || len > compressBound(TARGET_PAGE_SIZE)) {
                error_report("Invalid compressed data length: %d", len);
                ret = -EINVAL;
                break;
            }
            decompress_data_with_multi_threads(f, host, len);
            break;

        case RAM_SAVE_FLAG_XBZRLE:
            if (load_xbzrle(f, addr, host) < 0) {
                error_report("Failed to decompress XBZRLE page at "
                             RAM_ADDR_FMT, addr);
                ret = -EINVAL;
                break;
            }
            break;
        case RAM_SAVE_FLAG_EOS:
            /* normal exit */
            multifd_recv_sync_main();
            break;
        default:
            if (flags & RAM_SAVE_FLAG_HOOK) {
                ram_control_load_hook(f, RAM_CONTROL_HOOK, NULL);
            } else {
                error_report("Unknown combination of migration flags: %#x",
                             flags);
                ret = -EINVAL;
            }
        }
        if (!ret) {
            ret = qemu_file_get_error(f);
        }
    }

    ret |= wait_for_decompress_done();
    return ret;
}

static int ram_load(QEMUFile *f, void *opaque, int version_id)
{
    int ret = 0;
    static uint64_t seq_iter;
    /*
     * If system is running in postcopy mode, page inserts to host memory must
     * be atomic
     */
    bool postcopy_running = postcopy_is_running();

    seq_iter++;

    if (version_id != 4) {
        return -EINVAL;
    }

    /*
     * This RCU critical section can be very long running.
     * When RCU reclaims in the code start to become numerous,
     * it will be necessary to reduce the granularity of this
     * critical section.
     */
    WITH_RCU_READ_LOCK_GUARD() {
        if (postcopy_running) {
            ret = ram_load_postcopy(f);
        } else {
            ret = ram_load_precopy(f);
        }
    }
    trace_ram_load_complete(ret, seq_iter);

    if (!ret  && migration_incoming_in_colo_state()) {
        colo_flush_ram_cache();
    }
    return ret;
}

static bool ram_has_postcopy(void *opaque)
{
    RAMBlock *rb;
    RAMBLOCK_FOREACH_NOT_IGNORED(rb) {
        if (ramblock_is_pmem(rb)) {
            info_report("Block: %s, host: %p is a nvdimm memory, postcopy"
                         "is not supported now!", rb->idstr, rb->host);
            return false;
        }
    }

    return migrate_postcopy_ram();
}

/* Sync all the dirty bitmap with destination VM.  */
static int ram_dirty_bitmap_sync_all(MigrationState *s, RAMState *rs)
{
    RAMBlock *block;
    QEMUFile *file = s->to_dst_file;
    int ramblock_count = 0;

    trace_ram_dirty_bitmap_sync_start();

    RAMBLOCK_FOREACH_NOT_IGNORED(block) {
        qemu_savevm_send_recv_bitmap(file, block->idstr);
        trace_ram_dirty_bitmap_request(block->idstr);
        ramblock_count++;
    }

    trace_ram_dirty_bitmap_sync_wait();

    /* Wait until all the ramblocks' dirty bitmap synced */
    while (ramblock_count--) {
        qemu_sem_wait(&s->rp_state.rp_sem);
    }

    trace_ram_dirty_bitmap_sync_complete();

    return 0;
}

static void ram_dirty_bitmap_reload_notify(MigrationState *s)
{
    qemu_sem_post(&s->rp_state.rp_sem);
}

/*
 * Read the received bitmap, revert it as the initial dirty bitmap.
 * This is only used when the postcopy migration is paused but wants
 * to resume from a middle point.
 */
int ram_dirty_bitmap_reload(MigrationState *s, RAMBlock *block)
{
    int ret = -EINVAL;
    QEMUFile *file = s->rp_state.from_dst_file;
    unsigned long *le_bitmap, nbits = block->used_length >> TARGET_PAGE_BITS;
    uint64_t local_size = DIV_ROUND_UP(nbits, 8);
    uint64_t size, end_mark;

    trace_ram_dirty_bitmap_reload_begin(block->idstr);

    if (s->state != MIGRATION_STATUS_POSTCOPY_RECOVER) {
        error_report("%s: incorrect state %s", __func__,
                     MigrationStatus_str(s->state));
        return -EINVAL;
    }

    /*
     * Note: see comments in ramblock_recv_bitmap_send() on why we
     * need the endianess convertion, and the paddings.
     */
    local_size = ROUND_UP(local_size, 8);

    /* Add paddings */
    le_bitmap = bitmap_new(nbits + BITS_PER_LONG);

    size = qemu_get_be64(file);

    /* The size of the bitmap should match with our ramblock */
    if (size != local_size) {
        error_report("%s: ramblock '%s' bitmap size mismatch "
                     "(0x%"PRIx64" != 0x%"PRIx64")", __func__,
                     block->idstr, size, local_size);
        ret = -EINVAL;
        goto out;
    }

    size = qemu_get_buffer(file, (uint8_t *)le_bitmap, local_size);
    end_mark = qemu_get_be64(file);

    ret = qemu_file_get_error(file);
    if (ret || size != local_size) {
        error_report("%s: read bitmap failed for ramblock '%s': %d"
                     " (size 0x%"PRIx64", got: 0x%"PRIx64")",
                     __func__, block->idstr, ret, local_size, size);
        ret = -EIO;
        goto out;
    }

    if (end_mark != RAMBLOCK_RECV_BITMAP_ENDING) {
        error_report("%s: ramblock '%s' end mark incorrect: 0x%"PRIu64,
                     __func__, block->idstr, end_mark);
        ret = -EINVAL;
        goto out;
    }

    /*
     * Endianess convertion. We are during postcopy (though paused).
     * The dirty bitmap won't change. We can directly modify it.
     */
    bitmap_from_le(block->bmap, le_bitmap, nbits);

    /*
     * What we received is "received bitmap". Revert it as the initial
     * dirty bitmap for this ramblock.
     */
    bitmap_complement(block->bmap, block->bmap, nbits);

    trace_ram_dirty_bitmap_reload_complete(block->idstr);

    /*
     * We succeeded to sync bitmap for current ramblock. If this is
     * the last one to sync, we need to notify the main send thread.
     */
    ram_dirty_bitmap_reload_notify(s);

    ret = 0;
out:
    g_free(le_bitmap);
    return ret;
}

static int ram_resume_prepare(MigrationState *s, void *opaque)
{
    RAMState *rs = *(RAMState **)opaque;
    int ret;

    ret = ram_dirty_bitmap_sync_all(s, rs);
    if (ret) {
        return ret;
    }

    ram_state_resume_prepare(rs, s->to_dst_file);

    return 0;
}

static SaveVMHandlers savevm_ram_handlers = {
    .save_setup = ram_save_setup,
    .save_live_iterate = ram_save_iterate,
    .save_live_complete_postcopy = ram_save_complete,
    .save_live_complete_precopy = ram_save_complete,
    .has_postcopy = ram_has_postcopy,
    .save_live_pending = ram_save_pending,
    .load_state = ram_load,
    .save_cleanup = ram_save_cleanup,
    .load_setup = ram_load_setup,
    .load_cleanup = ram_load_cleanup,
    .resume_prepare = ram_resume_prepare,
};

void ram_mig_init(void)
{
    qemu_mutex_init(&XBZRLE.lock);
    register_savevm_live("ram", 0, 4, &savevm_ram_handlers, &ram_state);
}