aboutsummaryrefslogtreecommitdiff
path: root/migration/ram.c
blob: a6d5478ef8c28f477e399d086f9461d1ba5879da (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
4637
4638
4639
4640
4641
4642
4643
4644
4645
4646
4647
4648
4649
4650
4651
4652
4653
4654
4655
4656
4657
4658
4659
4660
4661
4662
4663
4664
4665
4666
4667
4668
4669
4670
4671
4672
4673
4674
4675
4676
4677
4678
4679
4680
4681
4682
4683
4684
4685
4686
4687
4688
4689
4690
4691
4692
4693
4694
4695
4696
4697
4698
4699
4700
4701
4702
4703
4704
4705
4706
4707
4708
4709
4710
4711
4712
4713
4714
4715
4716
4717
4718
4719
4720
4721
4722
4723
4724
4725
4726
4727
4728
4729
4730
4731
4732
4733
4734
4735
4736
4737
4738
4739
4740
4741
4742
4743
4744
4745
4746
4747
4748
4749
4750
4751
4752
4753
4754
4755
4756
4757
4758
/*
 * 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 "qemu/cutils.h"
#include "qemu/bitops.h"
#include "qemu/bitmap.h"
#include "qemu/madvise.h"
#include "qemu/main-loop.h"
#include "io/channel-null.h"
#include "xbzrle.h"
#include "ram.h"
#include "migration.h"
#include "migration-stats.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-types-migration.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/cpu-throttle.h"
#include "savevm.h"
#include "qemu/iov.h"
#include "multifd.h"
#include "sysemu/runstate.h"
#include "options.h"

#include "hw/boards.h" /* for machine_dump_guest_core() */

#if defined(__linux__)
#include "qemu/userfaultfd.h"
#endif /* defined(__linux__) */

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

/*
 * RAM_SAVE_FLAG_ZERO used to be named RAM_SAVE_FLAG_COMPRESS, it
 * worked for pages that were filled with the same char.  We switched
 * it to only search for the zero value.  And to avoid confusion with
 * RAM_SAVE_FLAG_COMPRESS_PAGE just rename it.
 */
/*
 * RAM_SAVE_FLAG_FULL was obsoleted in 2009, it can be reused now
 */
#define RAM_SAVE_FLAG_FULL     0x01
#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 qemu-file.h for RAM_SAVE_FLAG_HOOK */
#define RAM_SAVE_FLAG_COMPRESS_PAGE    0x100
#define RAM_SAVE_FLAG_MULTIFD_FLUSH    0x200
/* We can't use any flag that is bigger than 0x200 */

int (*xbzrle_encode_buffer_func)(uint8_t *, uint8_t *, int,
     uint8_t *, int) = xbzrle_encode_buffer;
#if defined(CONFIG_AVX512BW_OPT)
#include "qemu/cpuid.h"
static void __attribute__((constructor)) init_cpu_flag(void)
{
    unsigned max = __get_cpuid_max(0, NULL);
    int a, b, c, d;
    if (max >= 1) {
        __cpuid(1, a, b, c, d);
         /* We must check that AVX is not just available, but usable.  */
        if ((c & bit_OSXSAVE) && (c & bit_AVX) && max >= 7) {
            int bv;
            __asm("xgetbv" : "=a"(bv), "=d"(d) : "c"(0));
            __cpuid_count(7, 0, a, b, c, d);
           /* 0xe6:
            *  XCR0[7:5] = 111b (OPMASK state, upper 256-bit of ZMM0-ZMM15
            *                    and ZMM16-ZMM31 state are enabled by OS)
            *  XCR0[2:1] = 11b (XMM state and YMM state are enabled by OS)
            */
            if ((bv & 0xe6) == 0xe6 && (b & bit_AVX512BW)) {
                xbzrle_encode_buffer_func = xbzrle_encode_buffer_avx512;
            }
        }
    }
}
#endif

XBZRLECacheStats xbzrle_counters;

/* used by the search for pages to send */
struct PageSearchStatus {
    /* The migration channel used for a specific host page */
    QEMUFile    *pss_channel;
    /* Last block from where we have sent data */
    RAMBlock *last_sent_block;
    /* Current block being searched */
    RAMBlock    *block;
    /* Current page to search from */
    unsigned long page;
    /* Set once we wrap around */
    bool         complete_round;
    /* Whether we're sending a host page */
    bool          host_page_sending;
    /* The start/end of current host page.  Invalid if host_page_sending==false */
    unsigned long host_page_start;
    unsigned long host_page_end;
};
typedef struct PageSearchStatus PageSearchStatus;

/* 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_xbzrle()) {
        qemu_mutex_lock(&XBZRLE.lock);
    }
}

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

/**
 * xbzrle_cache_resize: resize the xbzrle cache
 *
 * This function is called from migrate_params_apply 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(uint64_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 postcopy_preempt_active(void)
{
    return migrate_postcopy_preempt() && migration_in_postcopy();
}

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

#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->postcopy_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 endianness. (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 "mysterious" 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 {
    /*
     * PageSearchStatus structures for the channels when send pages.
     * Protected by the bitmap_mutex.
     */
    PageSearchStatus pss[RAM_CHANNEL_MAX];
    /* UFFD file descriptor, used in 'write-tracking' migration */
    int uffdio_fd;
    /* total ram size in bytes */
    uint64_t ram_bytes_total;
    /* Last block that we have visited searching for dirty pages */
    RAMBlock *last_seen_block;
    /* Last dirty target page we have sent */
    ram_addr_t last_page;
    /* last ram version we have seen */
    uint32_t last_version;
    /* 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;
    /* Amount of xbzrle pages since the beginning of the period */
    uint64_t xbzrle_pages_prev;
    /* Amount of xbzrle encoded bytes since the beginning of the period */
    uint64_t xbzrle_bytes_prev;
    /* Start using XBZRLE (e.g., after the first round). */
    bool xbzrle_enabled;
    /* Are we on the last stage of migration */
    bool last_stage;
    /* 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:
     * - dirty/clear bitmap
     * - migration_dirty_pages
     * - pss structures
     */
    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;

/* Whether postcopy has queued requests? */
static bool postcopy_has_request(RAMState *rs)
{
    return !QSIMPLEQ_EMPTY_ATOMIC(&rs->src_page_requests);
}

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);
}

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

void ram_transferred_add(uint64_t bytes)
{
    if (runstate_is_running()) {
        stat64_add(&ram_counters.precopy_bytes, bytes);
    } else if (migration_in_postcopy()) {
        stat64_add(&ram_counters.postcopy_bytes, bytes);
    } else {
        stat64_add(&ram_counters.downtime_bytes, bytes);
    }
    stat64_add(&ram_counters.transferred, bytes);
}

struct MigrationOps {
    int (*ram_save_target_page)(RAMState *rs, PageSearchStatus *pss);
};
typedef struct MigrationOps MigrationOps;

MigrationOps *migration_ops;

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;

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

static int ram_save_host_page_urgent(PageSearchStatus *pss);

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

/* NOTE: page is the PFN not real ram_addr_t. */
static void pss_init(PageSearchStatus *pss, RAMBlock *rb, ram_addr_t page)
{
    pss->block = rb;
    pss->page = page;
    pss->complete_round = false;
}

/*
 * Check whether two PSSs are actively sending the same page.  Return true
 * if it is, false otherwise.
 */
static bool pss_overlap(PageSearchStatus *pss1, PageSearchStatus *pss2)
{
    return pss1->host_page_sending && pss2->host_page_sending &&
        (pss1->host_page_start == pss2->host_page_start);
}

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_compress() || !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_compress()) {
        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_file_new_output(
            QIO_CHANNEL(qio_channel_null_new()));
        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;
}

/**
 * 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
 *
 * @pss: current PSS channel status
 * @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(PageSearchStatus *pss, QEMUFile *f,
                               RAMBlock *block, ram_addr_t offset)
{
    size_t size, len;
    bool same_block = (block == pss->last_sent_block);

    if (same_block) {
        offset |= RAM_SAVE_FLAG_CONTINUE;
    }
    qemu_put_be64(f, offset);
    size = 8;

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

/**
 * mig_throttle_guest_down: throttle 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(uint64_t bytes_dirty_period,
                                    uint64_t bytes_dirty_threshold)
{
    uint64_t pct_initial = migrate_cpu_throttle_initial();
    uint64_t pct_increment = migrate_cpu_throttle_increment();
    bool pct_tailslow = migrate_cpu_throttle_tailslow();
    int pct_max = migrate_max_cpu_throttle();

    uint64_t throttle_now = cpu_throttle_get_percentage();
    uint64_t cpu_now, cpu_ideal, throttle_inc;

    /* 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 */
        if (!pct_tailslow) {
            throttle_inc = pct_increment;
        } else {
            /* Compute the ideal CPU percentage used by Guest, which may
             * make the dirty rate match the dirty rate threshold. */
            cpu_now = 100 - throttle_now;
            cpu_ideal = cpu_now * (bytes_dirty_threshold * 1.0 /
                        bytes_dirty_period);
            throttle_inc = MIN(cpu_now - cpu_ideal, pct_increment);
        }
        cpu_throttle_set(MIN(throttle_now + throttle_inc, pct_max));
    }
}

void mig_throttle_counter_reset(void)
{
    RAMState *rs = ram_state;

    rs->time_last_bitmap_sync = qemu_clock_get_ms(QEMU_CLOCK_REALTIME);
    rs->num_dirty_pages_period = 0;
    rs->bytes_xfer_prev = stat64_get(&ram_counters.transferred);
}

/**
 * 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)
{
    /* 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,
                 stat64_get(&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
 * @pss: current PSS channel
 * @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
 */
static int save_xbzrle_page(RAMState *rs, PageSearchStatus *pss,
                            uint8_t **current_data, ram_addr_t current_addr,
                            RAMBlock *block, ram_addr_t offset)
{
    int encoded_len = 0, bytes_xbzrle;
    uint8_t *prev_cached_page;
    QEMUFile *file = pss->pss_channel;
    uint64_t generation = stat64_get(&ram_counters.dirty_sync_count);

    if (!cache_is_cached(XBZRLE.cache, current_addr, generation)) {
        xbzrle_counters.cache_miss++;
        if (!rs->last_stage) {
            if (cache_insert(XBZRLE.cache, current_addr, *current_data,
                             generation) == -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;
    }

    /*
     * Reaching here means the page has hit the xbzrle cache, no matter what
     * encoding result it is (normal encoding, overflow or skipping the page),
     * count the page as encoded. This is used to calculate the encoding rate.
     *
     * Example: 2 pages (8KB) being encoded, first page encoding generates 2KB,
     * 2nd page turns out to be skipped (i.e. no new bytes written to the
     * page), the overall encoding rate will be 8KB / 2KB = 4, which has the
     * skipped page included. In this way, the encoding rate can tell if the
     * guest page is good for xbzrle encoding.
     */
    xbzrle_counters.pages++;
    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_func(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 (!rs->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++;
        xbzrle_counters.bytes += TARGET_PAGE_SIZE;
        return -1;
    }

    /* Send XBZRLE based compressed page */
    bytes_xbzrle = save_page_header(pss, pss->pss_channel, block,
                                    offset | RAM_SAVE_FLAG_XBZRLE);
    qemu_put_byte(file, ENCODING_FLAG_XBZRLE);
    qemu_put_be16(file, encoded_len);
    qemu_put_buffer(file, XBZRLE.encoded_buf, encoded_len);
    bytes_xbzrle += encoded_len + 1 + 2;
    /*
     * Like compressed_size (please see update_compress_thread_counts),
     * the xbzrle encoded bytes don't count the 8 byte header with
     * RAM_SAVE_FLAG_CONTINUE.
     */
    xbzrle_counters.bytes += bytes_xbzrle - 8;
    ram_transferred_add(bytes_xbzrle);

    return 1;
}

/**
 * pss_find_next_dirty: find the next dirty page of current ramblock
 *
 * This function updates pss->page to point to the next dirty page index
 * within the ramblock to migrate, or the end of ramblock when nothing
 * found.  Note that when pss->host_page_sending==true it means we're
 * during sending a host page, so we won't look for dirty page that is
 * outside the host page boundary.
 *
 * @pss: the current page search status
 */
static void pss_find_next_dirty(PageSearchStatus *pss)
{
    RAMBlock *rb = pss->block;
    unsigned long size = rb->used_length >> TARGET_PAGE_BITS;
    unsigned long *bitmap = rb->bmap;

    if (ramblock_is_ignored(rb)) {
        /* Points directly to the end, so we know no dirty page */
        pss->page = size;
        return;
    }

    /*
     * If during sending a host page, only look for dirty pages within the
     * current host page being send.
     */
    if (pss->host_page_sending) {
        assert(pss->host_page_end);
        size = MIN(size, pss->host_page_end);
    }

    pss->page = find_next_bit(bitmap, size, pss->page);
}

static void migration_clear_memory_region_dirty_bitmap(RAMBlock *rb,
                                                       unsigned long page)
{
    uint8_t shift;
    hwaddr size, start;

    if (!rb->clear_bmap || !clear_bmap_test_and_clear(rb, page)) {
        return;
    }

    shift = rb->clear_bmap_shift;
    /*
     * 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);

    size = 1ULL << (TARGET_PAGE_BITS + shift);
    start = QEMU_ALIGN_DOWN((ram_addr_t)page << TARGET_PAGE_BITS, size);
    trace_migration_bitmap_clear_dirty(rb->idstr, start, size, page);
    memory_region_clear_dirty_bitmap(rb->mr, start, size);
}

static void
migration_clear_memory_region_dirty_bitmap_range(RAMBlock *rb,
                                                 unsigned long start,
                                                 unsigned long npages)
{
    unsigned long i, chunk_pages = 1UL << rb->clear_bmap_shift;
    unsigned long chunk_start = QEMU_ALIGN_DOWN(start, chunk_pages);
    unsigned long chunk_end = QEMU_ALIGN_UP(start + npages, chunk_pages);

    /*
     * Clear pages from start to start + npages - 1, so the end boundary is
     * exclusive.
     */
    for (i = chunk_start; i < chunk_end; i += chunk_pages) {
        migration_clear_memory_region_dirty_bitmap(rb, i);
    }
}

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

    *num = 0;

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

    first = find_next_bit(bitmap, size, start);
    if (first >= size) {
        return first;
    }
    next = find_next_zero_bit(bitmap, size, first + 1);
    assert(next >= first);
    *num = next - first;
    return first;
}

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

    /*
     * 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.
     */
    migration_clear_memory_region_dirty_bitmap(rb, page);

    ret = test_and_clear_bit(page, rb->bmap);
    if (ret) {
        rs->migration_dirty_pages--;
    }

    return ret;
}

static void dirty_bitmap_clear_section(MemoryRegionSection *section,
                                       void *opaque)
{
    const hwaddr offset = section->offset_within_region;
    const hwaddr size = int128_get64(section->size);
    const unsigned long start = offset >> TARGET_PAGE_BITS;
    const unsigned long npages = size >> TARGET_PAGE_BITS;
    RAMBlock *rb = section->mr->ram_block;
    uint64_t *cleared_bits = opaque;

    /*
     * We don't grab ram_state->bitmap_mutex because we expect to run
     * only when starting migration or during postcopy recovery where
     * we don't have concurrent access.
     */
    if (!migration_in_postcopy() && !migrate_background_snapshot()) {
        migration_clear_memory_region_dirty_bitmap_range(rb, start, npages);
    }
    *cleared_bits += bitmap_count_one_with_offset(rb->bmap, start, npages);
    bitmap_clear(rb->bmap, start, npages);
}

/*
 * Exclude all dirty pages from migration that fall into a discarded range as
 * managed by a RamDiscardManager responsible for the mapped memory region of
 * the RAMBlock. Clear the corresponding bits in the dirty bitmaps.
 *
 * Discarded pages ("logically unplugged") have undefined content and must
 * not get migrated, because even reading these pages for migration might
 * result in undesired behavior.
 *
 * Returns the number of cleared bits in the RAMBlock dirty bitmap.
 *
 * Note: The result is only stable while migrating (precopy/postcopy).
 */
static uint64_t ramblock_dirty_bitmap_clear_discarded_pages(RAMBlock *rb)
{
    uint64_t cleared_bits = 0;

    if (rb->mr && rb->bmap && memory_region_has_ram_discard_manager(rb->mr)) {
        RamDiscardManager *rdm = memory_region_get_ram_discard_manager(rb->mr);
        MemoryRegionSection section = {
            .mr = rb->mr,
            .offset_within_region = 0,
            .size = int128_make64(qemu_ram_get_used_length(rb)),
        };

        ram_discard_manager_replay_discarded(rdm, &section,
                                             dirty_bitmap_clear_section,
                                             &cleared_bits);
    }
    return cleared_bits;
}

/*
 * Check if a host-page aligned page falls into a discarded range as managed by
 * a RamDiscardManager responsible for the mapped memory region of the RAMBlock.
 *
 * Note: The result is only stable while migrating (precopy/postcopy).
 */
bool ramblock_page_is_discarded(RAMBlock *rb, ram_addr_t start)
{
    if (rb->mr && memory_region_has_ram_discard_manager(rb->mr)) {
        RamDiscardManager *rdm = memory_region_get_ram_discard_manager(rb->mr);
        MemoryRegionSection section = {
            .mr = rb->mr,
            .offset_within_region = start,
            .size = int128_make64(qemu_ram_pagesize(rb)),
        };

        return !ram_discard_manager_is_populated(rdm, &section);
    }
    return false;
}

/* Called with RCU critical section */
static void ramblock_sync_dirty_bitmap(RAMState *rs, RAMBlock *rb)
{
    uint64_t new_dirty_pages =
        cpu_physical_memory_sync_dirty_bitmap(rb, 0, rb->used_length);

    rs->migration_dirty_pages += new_dirty_pages;
    rs->num_dirty_pages_period += new_dirty_pages;
}

/**
 * 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 stat64_get(&ram_counters.normal_pages) +
        stat64_get(&ram_counters.zero_pages) +
        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 */
    stat64_set(&ram_counters.dirty_pages_rate,
               rs->num_dirty_pages_period * 1000 /
               (end_time - rs->time_last_bitmap_sync));

    if (!page_count) {
        return;
    }

    if (migrate_xbzrle()) {
        double encoded_size, unencoded_size;

        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;
        unencoded_size = (xbzrle_counters.pages - rs->xbzrle_pages_prev) *
                         TARGET_PAGE_SIZE;
        encoded_size = xbzrle_counters.bytes - rs->xbzrle_bytes_prev;
        if (xbzrle_counters.pages == rs->xbzrle_pages_prev || !encoded_size) {
            xbzrle_counters.encoding_rate = 0;
        } else {
            xbzrle_counters.encoding_rate = unencoded_size / encoded_size;
        }
        rs->xbzrle_pages_prev = xbzrle_counters.pages;
        rs->xbzrle_bytes_prev = xbzrle_counters.bytes;
    }

    if (migrate_compress()) {
        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_trigger_throttle(RAMState *rs)
{
    uint64_t threshold = migrate_throttle_trigger_threshold();
    uint64_t bytes_xfer_period =
        stat64_get(&ram_counters.transferred) - rs->bytes_xfer_prev;
    uint64_t bytes_dirty_period = rs->num_dirty_pages_period * TARGET_PAGE_SIZE;
    uint64_t bytes_dirty_threshold = bytes_xfer_period * threshold / 100;

    /* 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 ratio between dirtied bytes and the approx.
           amount of bytes that just got transferred since the last time
           we were in this routine reaches the threshold. If that happens
           twice, start or increase throttling. */

        if ((bytes_dirty_period > bytes_dirty_threshold) &&
            (++rs->dirty_rate_high_cnt >= 2)) {
            trace_migration_throttle();
            rs->dirty_rate_high_cnt = 0;
            mig_throttle_guest_down(bytes_dirty_period,
                                    bytes_dirty_threshold);
        }
    }
}

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

    stat64_add(&ram_counters.dirty_sync_count, 1);

    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);
        }
        stat64_set(&ram_counters.dirty_bytes_last_sync, 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) {
        migration_trigger_throttle(rs);

        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 = stat64_get(&ram_counters.transferred);
    }
    if (migrate_events()) {
        uint64_t generation = stat64_get(&ram_counters.dirty_sync_count);
        qapi_event_send_migration_pass(generation);
    }
}

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);
        local_err = NULL;
    }

    migration_bitmap_sync(rs);

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

void ram_release_page(const char *rbname, uint64_t offset)
{
    if (!migrate_release_ram() || !migration_in_postcopy()) {
        return;
    }

    ram_discard_range(rbname, offset, TARGET_PAGE_SIZE);
}

/**
 * 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
 *
 * @pss: current PSS channel
 * @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(PageSearchStatus *pss, QEMUFile *file,
                                  RAMBlock *block, ram_addr_t offset)
{
    uint8_t *p = block->host + offset;
    int len = 0;

    if (buffer_is_zero(p, TARGET_PAGE_SIZE)) {
        len += save_page_header(pss, file, block, offset | RAM_SAVE_FLAG_ZERO);
        qemu_put_byte(file, 0);
        len += 1;
        ram_release_page(block->idstr, offset);
    }
    return len;
}

/**
 * save_zero_page: send the zero page to the stream
 *
 * Returns the number of pages written.
 *
 * @pss: current PSS channel
 * @block: block that contains the page we want to send
 * @offset: offset inside the block for the page
 */
static int save_zero_page(PageSearchStatus *pss, QEMUFile *f, RAMBlock *block,
                          ram_addr_t offset)
{
    int len = save_zero_page_to_file(pss, f, block, offset);

    if (len) {
        stat64_add(&ram_counters.zero_pages, 1);
        ram_transferred_add(len);
        return 1;
    }
    return -1;
}

/*
 * @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(PageSearchStatus *pss, RAMBlock *block,
                              ram_addr_t offset, int *pages)
{
    uint64_t bytes_xmit = 0;
    int ret;

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

    if (bytes_xmit) {
        ram_transferred_add(bytes_xmit);
        *pages = 1;
    }

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

    if (bytes_xmit > 0) {
        stat64_add(&ram_counters.normal_pages, 1);
    } else if (bytes_xmit == 0) {
        stat64_add(&ram_counters.zero_pages, 1);
    }

    return true;
}

/*
 * directly send the page to the stream
 *
 * Returns the number of pages written.
 *
 * @pss: current PSS channel
 * @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(PageSearchStatus *pss, RAMBlock *block,
                            ram_addr_t offset, uint8_t *buf, bool async)
{
    QEMUFile *file = pss->pss_channel;

    ram_transferred_add(save_page_header(pss, pss->pss_channel, block,
                                         offset | RAM_SAVE_FLAG_PAGE));
    if (async) {
        qemu_put_buffer_async(file, buf, TARGET_PAGE_SIZE,
                              migrate_release_ram() &&
                              migration_in_postcopy());
    } else {
        qemu_put_buffer(file, buf, TARGET_PAGE_SIZE);
    }
    ram_transferred_add(TARGET_PAGE_SIZE);
    stat64_add(&ram_counters.normal_pages, 1);
    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
 */
static int ram_save_page(RAMState *rs, PageSearchStatus *pss)
{
    int pages = -1;
    uint8_t *p;
    bool send_async = true;
    RAMBlock *block = pss->block;
    ram_addr_t offset = ((ram_addr_t)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->xbzrle_enabled && !migration_in_postcopy()) {
        pages = save_xbzrle_page(rs, pss, &p, current_addr,
                                 block, offset);
        if (!rs->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(pss, block, offset, p, send_async);
    }

    XBZRLE_cache_unlock();

    return pages;
}

static int ram_save_multifd_page(QEMUFile *file, RAMBlock *block,
                                 ram_addr_t offset)
{
    if (multifd_queue_page(file, block, offset) < 0) {
        return -1;
    }
    stat64_add(&ram_counters.normal_pages, 1);

    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;
    PageSearchStatus *pss = &rs->pss[RAM_CHANNEL_PRECOPY];
    uint8_t *p = block->host + offset;
    int ret;

    if (save_zero_page_to_file(pss, f, block, offset)) {
        return true;
    }

    save_page_header(pss, 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;
}

static void
update_compress_thread_counts(const CompressParam *param, int bytes_xmit)
{
    ram_transferred_add(bytes_xmit);

    if (param->zero_page) {
        stat64_add(&ram_counters.zero_pages, 1);
        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)
{
    MigrationState *ms = migrate_get_current();
    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(ms->to_dst_file, 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(RAMBlock *block, ram_addr_t offset)
{
    int idx, thread_count, bytes_xmit = -1, pages = -1;
    bool wait = migrate_compress_wait_thread();
    MigrationState *ms = migrate_get_current();

    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(ms->to_dst_file,
                                            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;
}

#define PAGE_ALL_CLEAN 0
#define PAGE_TRY_AGAIN 1
#define PAGE_DIRTY_FOUND 2
/**
 * find_dirty_block: find the next dirty page and update any state
 * associated with the search process.
 *
 * Returns:
 *         <0: An error happened
 *         PAGE_ALL_CLEAN: no dirty page found, give up
 *         PAGE_TRY_AGAIN: no dirty page found, retry for next block
 *         PAGE_DIRTY_FOUND: dirty page 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 int find_dirty_block(RAMState *rs, PageSearchStatus *pss)
{
    /* Update pss->page for the next dirty bit in ramblock */
    pss_find_next_dirty(pss);

    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.
         */
        return PAGE_ALL_CLEAN;
    }
    if (!offset_in_ramblock(pss->block,
                            ((ram_addr_t)pss->page) << TARGET_PAGE_BITS)) {
        /* Didn't find anything in this RAM Block */
        pss->page = 0;
        pss->block = QLIST_NEXT_RCU(pss->block, next);
        if (!pss->block) {
            if (!migrate_multifd_flush_after_each_section()) {
                QEMUFile *f = rs->pss[RAM_CHANNEL_PRECOPY].pss_channel;
                int ret = multifd_send_sync_main(f);
                if (ret < 0) {
                    return ret;
                }
                qemu_put_be64(f, RAM_SAVE_FLAG_MULTIFD_FLUSH);
                qemu_fflush(f);
            }
            /*
             * 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;
            /* After the first round, enable XBZRLE. */
            if (migrate_xbzrle()) {
                rs->xbzrle_enabled = true;
            }
        }
        /* Didn't find anything this time, but try again on the new block */
        return PAGE_TRY_AGAIN;
    } else {
        /* We've found something */
        return PAGE_DIRTY_FOUND;
    }
}

/**
 * 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)
{
    struct RAMSrcPageRequest *entry;
    RAMBlock *block = NULL;

    if (!postcopy_has_request(rs)) {
        return NULL;
    }

    QEMU_LOCK_GUARD(&rs->src_page_req_mutex);

    /*
     * This should _never_ change even after we take the lock, because no one
     * should be taking anything off the request list other than us.
     */
    assert(postcopy_has_request(rs));

    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();
    }

    return block;
}

#if defined(__linux__)
/**
 * poll_fault_page: try to get next UFFD write fault page and, if pending fault
 *   is found, return RAM block pointer and page offset
 *
 * Returns pointer to the RAMBlock containing faulting page,
 *   NULL if no write faults are pending
 *
 * @rs: current RAM state
 * @offset: page offset from the beginning of the block
 */
static RAMBlock *poll_fault_page(RAMState *rs, ram_addr_t *offset)
{
    struct uffd_msg uffd_msg;
    void *page_address;
    RAMBlock *block;
    int res;

    if (!migrate_background_snapshot()) {
        return NULL;
    }

    res = uffd_read_events(rs->uffdio_fd, &uffd_msg, 1);
    if (res <= 0) {
        return NULL;
    }

    page_address = (void *)(uintptr_t) uffd_msg.arg.pagefault.address;
    block = qemu_ram_block_from_host(page_address, false, offset);
    assert(block && (block->flags & RAM_UF_WRITEPROTECT) != 0);
    return block;
}

/**
 * ram_save_release_protection: release UFFD write protection after
 *   a range of pages has been saved
 *
 * @rs: current RAM state
 * @pss: page-search-status structure
 * @start_page: index of the first page in the range relative to pss->block
 *
 * Returns 0 on success, negative value in case of an error
*/
static int ram_save_release_protection(RAMState *rs, PageSearchStatus *pss,
        unsigned long start_page)
{
    int res = 0;

    /* Check if page is from UFFD-managed region. */
    if (pss->block->flags & RAM_UF_WRITEPROTECT) {
        void *page_address = pss->block->host + (start_page << TARGET_PAGE_BITS);
        uint64_t run_length = (pss->page - start_page) << TARGET_PAGE_BITS;

        /* Flush async buffers before un-protect. */
        qemu_fflush(pss->pss_channel);
        /* Un-protect memory range. */
        res = uffd_change_protection(rs->uffdio_fd, page_address, run_length,
                false, false);
    }

    return res;
}

/* ram_write_tracking_available: check if kernel supports required UFFD features
 *
 * Returns true if supports, false otherwise
 */
bool ram_write_tracking_available(void)
{
    uint64_t uffd_features;
    int res;

    res = uffd_query_features(&uffd_features);
    return (res == 0 &&
            (uffd_features & UFFD_FEATURE_PAGEFAULT_FLAG_WP) != 0);
}

/* ram_write_tracking_compatible: check if guest configuration is
 *   compatible with 'write-tracking'
 *
 * Returns true if compatible, false otherwise
 */
bool ram_write_tracking_compatible(void)
{
    const uint64_t uffd_ioctls_mask = BIT(_UFFDIO_WRITEPROTECT);
    int uffd_fd;
    RAMBlock *block;
    bool ret = false;

    /* Open UFFD file descriptor */
    uffd_fd = uffd_create_fd(UFFD_FEATURE_PAGEFAULT_FLAG_WP, false);
    if (uffd_fd < 0) {
        return false;
    }

    RCU_READ_LOCK_GUARD();

    RAMBLOCK_FOREACH_NOT_IGNORED(block) {
        uint64_t uffd_ioctls;

        /* Nothing to do with read-only and MMIO-writable regions */
        if (block->mr->readonly || block->mr->rom_device) {
            continue;
        }
        /* Try to register block memory via UFFD-IO to track writes */
        if (uffd_register_memory(uffd_fd, block->host, block->max_length,
                UFFDIO_REGISTER_MODE_WP, &uffd_ioctls)) {
            goto out;
        }
        if ((uffd_ioctls & uffd_ioctls_mask) != uffd_ioctls_mask) {
            goto out;
        }
    }
    ret = true;

out:
    uffd_close_fd(uffd_fd);
    return ret;
}

static inline void populate_read_range(RAMBlock *block, ram_addr_t offset,
                                       ram_addr_t size)
{
    const ram_addr_t end = offset + size;

    /*
     * We read one byte of each page; this will preallocate page tables if
     * required and populate the shared zeropage on MAP_PRIVATE anonymous memory
     * where no page was populated yet. This might require adaption when
     * supporting other mappings, like shmem.
     */
    for (; offset < end; offset += block->page_size) {
        char tmp = *((char *)block->host + offset);

        /* Don't optimize the read out */
        asm volatile("" : "+r" (tmp));
    }
}

static inline int populate_read_section(MemoryRegionSection *section,
                                        void *opaque)
{
    const hwaddr size = int128_get64(section->size);
    hwaddr offset = section->offset_within_region;
    RAMBlock *block = section->mr->ram_block;

    populate_read_range(block, offset, size);
    return 0;
}

/*
 * ram_block_populate_read: preallocate page tables and populate pages in the
 *   RAM block by reading a byte of each page.
 *
 * Since it's solely used for userfault_fd WP feature, here we just
 *   hardcode page size to qemu_real_host_page_size.
 *
 * @block: RAM block to populate
 */
static void ram_block_populate_read(RAMBlock *rb)
{
    /*
     * Skip populating all pages that fall into a discarded range as managed by
     * a RamDiscardManager responsible for the mapped memory region of the
     * RAMBlock. Such discarded ("logically unplugged") parts of a RAMBlock
     * must not get populated automatically. We don't have to track
     * modifications via userfaultfd WP reliably, because these pages will
     * not be part of the migration stream either way -- see
     * ramblock_dirty_bitmap_exclude_discarded_pages().
     *
     * Note: The result is only stable while migrating (precopy/postcopy).
     */
    if (rb->mr && memory_region_has_ram_discard_manager(rb->mr)) {
        RamDiscardManager *rdm = memory_region_get_ram_discard_manager(rb->mr);
        MemoryRegionSection section = {
            .mr = rb->mr,
            .offset_within_region = 0,
            .size = rb->mr->size,
        };

        ram_discard_manager_replay_populated(rdm, &section,
                                             populate_read_section, NULL);
    } else {
        populate_read_range(rb, 0, rb->used_length);
    }
}

/*
 * ram_write_tracking_prepare: prepare for UFFD-WP memory tracking
 */
void ram_write_tracking_prepare(void)
{
    RAMBlock *block;

    RCU_READ_LOCK_GUARD();

    RAMBLOCK_FOREACH_NOT_IGNORED(block) {
        /* Nothing to do with read-only and MMIO-writable regions */
        if (block->mr->readonly || block->mr->rom_device) {
            continue;
        }

        /*
         * Populate pages of the RAM block before enabling userfault_fd
         * write protection.
         *
         * This stage is required since ioctl(UFFDIO_WRITEPROTECT) with
         * UFFDIO_WRITEPROTECT_MODE_WP mode setting would silently skip
         * pages with pte_none() entries in page table.
         */
        ram_block_populate_read(block);
    }
}

static inline int uffd_protect_section(MemoryRegionSection *section,
                                       void *opaque)
{
    const hwaddr size = int128_get64(section->size);
    const hwaddr offset = section->offset_within_region;
    RAMBlock *rb = section->mr->ram_block;
    int uffd_fd = (uintptr_t)opaque;

    return uffd_change_protection(uffd_fd, rb->host + offset, size, true,
                                  false);
}

static int ram_block_uffd_protect(RAMBlock *rb, int uffd_fd)
{
    assert(rb->flags & RAM_UF_WRITEPROTECT);

    /* See ram_block_populate_read() */
    if (rb->mr && memory_region_has_ram_discard_manager(rb->mr)) {
        RamDiscardManager *rdm = memory_region_get_ram_discard_manager(rb->mr);
        MemoryRegionSection section = {
            .mr = rb->mr,
            .offset_within_region = 0,
            .size = rb->mr->size,
        };

        return ram_discard_manager_replay_populated(rdm, &section,
                                                    uffd_protect_section,
                                                    (void *)(uintptr_t)uffd_fd);
    }
    return uffd_change_protection(uffd_fd, rb->host,
                                  rb->used_length, true, false);
}

/*
 * ram_write_tracking_start: start UFFD-WP memory tracking
 *
 * Returns 0 for success or negative value in case of error
 */
int ram_write_tracking_start(void)
{
    int uffd_fd;
    RAMState *rs = ram_state;
    RAMBlock *block;

    /* Open UFFD file descriptor */
    uffd_fd = uffd_create_fd(UFFD_FEATURE_PAGEFAULT_FLAG_WP, true);
    if (uffd_fd < 0) {
        return uffd_fd;
    }
    rs->uffdio_fd = uffd_fd;

    RCU_READ_LOCK_GUARD();

    RAMBLOCK_FOREACH_NOT_IGNORED(block) {
        /* Nothing to do with read-only and MMIO-writable regions */
        if (block->mr->readonly || block->mr->rom_device) {
            continue;
        }

        /* Register block memory with UFFD to track writes */
        if (uffd_register_memory(rs->uffdio_fd, block->host,
                block->max_length, UFFDIO_REGISTER_MODE_WP, NULL)) {
            goto fail;
        }
        block->flags |= RAM_UF_WRITEPROTECT;
        memory_region_ref(block->mr);

        /* Apply UFFD write protection to the block memory range */
        if (ram_block_uffd_protect(block, uffd_fd)) {
            goto fail;
        }

        trace_ram_write_tracking_ramblock_start(block->idstr, block->page_size,
                block->host, block->max_length);
    }

    return 0;

fail:
    error_report("ram_write_tracking_start() failed: restoring initial memory state");

    RAMBLOCK_FOREACH_NOT_IGNORED(block) {
        if ((block->flags & RAM_UF_WRITEPROTECT) == 0) {
            continue;
        }
        uffd_unregister_memory(rs->uffdio_fd, block->host, block->max_length);
        /* Cleanup flags and remove reference */
        block->flags &= ~RAM_UF_WRITEPROTECT;
        memory_region_unref(block->mr);
    }

    uffd_close_fd(uffd_fd);
    rs->uffdio_fd = -1;
    return -1;
}

/**
 * ram_write_tracking_stop: stop UFFD-WP memory tracking and remove protection
 */
void ram_write_tracking_stop(void)
{
    RAMState *rs = ram_state;
    RAMBlock *block;

    RCU_READ_LOCK_GUARD();

    RAMBLOCK_FOREACH_NOT_IGNORED(block) {
        if ((block->flags & RAM_UF_WRITEPROTECT) == 0) {
            continue;
        }
        uffd_unregister_memory(rs->uffdio_fd, block->host, block->max_length);

        trace_ram_write_tracking_ramblock_stop(block->idstr, block->page_size,
                block->host, block->max_length);

        /* Cleanup flags and remove reference */
        block->flags &= ~RAM_UF_WRITEPROTECT;
        memory_region_unref(block->mr);
    }

    /* Finally close UFFD file descriptor */
    uffd_close_fd(rs->uffdio_fd);
    rs->uffdio_fd = -1;
}

#else
/* No target OS support, stubs just fail or ignore */

static RAMBlock *poll_fault_page(RAMState *rs, ram_addr_t *offset)
{
    (void) rs;
    (void) offset;

    return NULL;
}

static int ram_save_release_protection(RAMState *rs, PageSearchStatus *pss,
        unsigned long start_page)
{
    (void) rs;
    (void) pss;
    (void) start_page;

    return 0;
}

bool ram_write_tracking_available(void)
{
    return false;
}

bool ram_write_tracking_compatible(void)
{
    assert(0);
    return false;
}

int ram_write_tracking_start(void)
{
    assert(0);
    return -1;
}

void ram_write_tracking_stop(void)
{
    assert(0);
}
#endif /* defined(__linux__) */

/**
 * 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) {
        /*
         * Poll write faults too if background snapshot is enabled; that's
         * when we have vcpus got blocked by the write protected pages.
         */
        block = poll_fault_page(rs, &offset);
    }

    if (block) {
        /*
         * 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;

    stat64_add(&ram_counters.postcopy_requests, 1);
    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 (!offset_in_ramblock(ramblock, start + len - 1)) {
        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;
    }

    /*
     * When with postcopy preempt, we send back the page directly in the
     * rp-return thread.
     */
    if (postcopy_preempt_active()) {
        ram_addr_t page_start = start >> TARGET_PAGE_BITS;
        size_t page_size = qemu_ram_pagesize(ramblock);
        PageSearchStatus *pss = &ram_state->pss[RAM_CHANNEL_POSTCOPY];
        int ret = 0;

        qemu_mutex_lock(&rs->bitmap_mutex);

        pss_init(pss, ramblock, page_start);
        /*
         * Always use the preempt channel, and make sure it's there.  It's
         * safe to access without lock, because when rp-thread is running
         * we should be the only one who operates on the qemufile
         */
        pss->pss_channel = migrate_get_current()->postcopy_qemufile_src;
        assert(pss->pss_channel);

        /*
         * It must be either one or multiple of host page size.  Just
         * assert; if something wrong we're mostly split brain anyway.
         */
        assert(len % page_size == 0);
        while (len) {
            if (ram_save_host_page_urgent(pss)) {
                error_report("%s: ram_save_host_page_urgent() failed: "
                             "ramblock=%s, start_addr=0x"RAM_ADDR_FMT,
                             __func__, ramblock->idstr, start);
                ret = -1;
                break;
            }
            /*
             * NOTE: after ram_save_host_page_urgent() succeeded, pss->page
             * will automatically be moved and point to the next host page
             * we're going to send, so no need to update here.
             *
             * Normally QEMU never sends >1 host page in requests, so
             * logically we don't even need that as the loop should only
             * run once, but just to be consistent.
             */
            len -= page_size;
        };
        qemu_mutex_unlock(&rs->bitmap_mutex);

        return ret;
    }

    struct RAMSrcPageRequest *new_entry =
        g_new0(struct RAMSrcPageRequest, 1);
    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_compress()) {
        return false;
    }

    /*
     * If xbzrle is enabled (e.g., after first round of migration), stop
     * using the data compression. In theory, xbzrle can do better than
     * compression.
     */
    if (rs->xbzrle_enabled) {
        return false;
    }

    return true;
}

/*
 * 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, PageSearchStatus *pss,
                               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 != pss->last_sent_block) {
        flush_compressed_data(rs);
        return false;
    }

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

    compression_counters.busy++;
    return false;
}

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

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

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

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

    /*
     * Do not use multifd in postcopy as one whole host page should be
     * placed.  Meanwhile postcopy requires atomic update of pages, so even
     * if host page size == guest page size the dest guest during run may
     * still see partially copied pages which is data corruption.
     */
    if (migrate_multifd() && !migration_in_postcopy()) {
        return ram_save_multifd_page(pss->pss_channel, block, offset);
    }

    return ram_save_page(rs, pss);
}

/* Should be called before sending a host page */
static void pss_host_page_prepare(PageSearchStatus *pss)
{
    /* How many guest pages are there in one host page? */
    size_t guest_pfns = qemu_ram_pagesize(pss->block) >> TARGET_PAGE_BITS;

    pss->host_page_sending = true;
    if (guest_pfns <= 1) {
        /*
         * This covers both when guest psize == host psize, or when guest
         * has larger psize than the host (guest_pfns==0).
         *
         * For the latter, we always send one whole guest page per
         * iteration of the host page (example: an Alpha VM on x86 host
         * will have guest psize 8K while host psize 4K).
         */
        pss->host_page_start = pss->page;
        pss->host_page_end = pss->page + 1;
    } else {
        /*
         * The host page spans over multiple guest pages, we send them
         * within the same host page iteration.
         */
        pss->host_page_start = ROUND_DOWN(pss->page, guest_pfns);
        pss->host_page_end = ROUND_UP(pss->page + 1, guest_pfns);
    }
}

/*
 * Whether the page pointed by PSS is within the host page being sent.
 * Must be called after a previous pss_host_page_prepare().
 */
static bool pss_within_range(PageSearchStatus *pss)
{
    ram_addr_t ram_addr;

    assert(pss->host_page_sending);

    /* Over host-page boundary? */
    if (pss->page >= pss->host_page_end) {
        return false;
    }

    ram_addr = ((ram_addr_t)pss->page) << TARGET_PAGE_BITS;

    return offset_in_ramblock(pss->block, ram_addr);
}

static void pss_host_page_finish(PageSearchStatus *pss)
{
    pss->host_page_sending = false;
    /* This is not needed, but just to reset it */
    pss->host_page_start = pss->host_page_end = 0;
}

/*
 * Send an urgent host page specified by `pss'.  Need to be called with
 * bitmap_mutex held.
 *
 * Returns 0 if save host page succeeded, false otherwise.
 */
static int ram_save_host_page_urgent(PageSearchStatus *pss)
{
    bool page_dirty, sent = false;
    RAMState *rs = ram_state;
    int ret = 0;

    trace_postcopy_preempt_send_host_page(pss->block->idstr, pss->page);
    pss_host_page_prepare(pss);

    /*
     * If precopy is sending the same page, let it be done in precopy, or
     * we could send the same page in two channels and none of them will
     * receive the whole page.
     */
    if (pss_overlap(pss, &ram_state->pss[RAM_CHANNEL_PRECOPY])) {
        trace_postcopy_preempt_hit(pss->block->idstr,
                                   pss->page << TARGET_PAGE_BITS);
        return 0;
    }

    do {
        page_dirty = migration_bitmap_clear_dirty(rs, pss->block, pss->page);

        if (page_dirty) {
            /* Be strict to return code; it must be 1, or what else? */
            if (migration_ops->ram_save_target_page(rs, pss) != 1) {
                error_report_once("%s: ram_save_target_page failed", __func__);
                ret = -1;
                goto out;
            }
            sent = true;
        }
        pss_find_next_dirty(pss);
    } while (pss_within_range(pss));
out:
    pss_host_page_finish(pss);
    /* For urgent requests, flush immediately if sent */
    if (sent) {
        qemu_fflush(pss->pss_channel);
    }
    return ret;
}

/**
 * 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.
 *
 * The caller must be with ram_state.bitmap_mutex held to call this
 * function.  Note that this function can temporarily release the lock, but
 * when the function is returned it'll make sure the lock is still held.
 *
 * Returns the number of pages written or negative on error
 *
 * @rs: current RAM state
 * @pss: data about the page we want to send
 */
static int ram_save_host_page(RAMState *rs, PageSearchStatus *pss)
{
    bool page_dirty, preempt_active = postcopy_preempt_active();
    int tmppages, pages = 0;
    size_t pagesize_bits =
        qemu_ram_pagesize(pss->block) >> TARGET_PAGE_BITS;
    unsigned long start_page = pss->page;
    int res;

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

    /* Update host page boundary information */
    pss_host_page_prepare(pss);

    do {
        page_dirty = migration_bitmap_clear_dirty(rs, pss->block, pss->page);

        /* Check the pages is dirty and if it is send it */
        if (page_dirty) {
            /*
             * Properly yield the lock only in postcopy preempt mode
             * because both migration thread and rp-return thread can
             * operate on the bitmaps.
             */
            if (preempt_active) {
                qemu_mutex_unlock(&rs->bitmap_mutex);
            }
            tmppages = migration_ops->ram_save_target_page(rs, pss);
            if (tmppages >= 0) {
                pages += tmppages;
                /*
                 * Allow rate limiting to happen in the middle of huge pages if
                 * something is sent in the current iteration.
                 */
                if (pagesize_bits > 1 && tmppages > 0) {
                    migration_rate_limit();
                }
            }
            if (preempt_active) {
                qemu_mutex_lock(&rs->bitmap_mutex);
            }
        } else {
            tmppages = 0;
        }

        if (tmppages < 0) {
            pss_host_page_finish(pss);
            return tmppages;
        }

        pss_find_next_dirty(pss);
    } while (pss_within_range(pss));

    pss_host_page_finish(pss);

    res = ram_save_release_protection(rs, pss, start_page);
    return (res < 0 ? res : 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
 *
 * 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)
{
    PageSearchStatus *pss = &rs->pss[RAM_CHANNEL_PRECOPY];
    int pages = 0;

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

    /*
     * Always keep last_seen_block/last_page valid during this procedure,
     * because find_dirty_block() relies on these values (e.g., we compare
     * last_seen_block with pss.block to see whether we searched all the
     * ramblocks) to detect the completion of migration.  Having NULL value
     * of last_seen_block can conditionally cause below loop to run forever.
     */
    if (!rs->last_seen_block) {
        rs->last_seen_block = QLIST_FIRST_RCU(&ram_list.blocks);
        rs->last_page = 0;
    }

    pss_init(pss, rs->last_seen_block, rs->last_page);

    while (true){
        if (!get_queued_page(rs, pss)) {
            /* priority queue empty, so just search for something dirty */
            int res = find_dirty_block(rs, pss);
            if (res != PAGE_DIRTY_FOUND) {
                if (res == PAGE_ALL_CLEAN) {
                    break;
                } else if (res == PAGE_TRY_AGAIN) {
                    continue;
                } else if (res < 0) {
                    pages = res;
                    break;
                }
            }
        }
        pages = ram_save_host_page(rs, pss);
        if (pages) {
            break;
        }
    }

    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) {
        stat64_add(&ram_counters.zero_pages, pages);
    } else {
        stat64_add(&ram_counters.normal_pages, pages);
        ram_transferred_add(size);
        qemu_file_credit_transfer(f, size);
    }
}

static uint64_t ram_bytes_total_with_ignored(void)
{
    RAMBlock *block;
    uint64_t total = 0;

    RCU_READ_LOCK_GUARD();

    RAMBLOCK_FOREACH_MIGRATABLE(block) {
        total += block->used_length;
    }
    return total;
}

uint64_t ram_bytes_total(void)
{
    RAMBlock *block;
    uint64_t total = 0;

    RCU_READ_LOCK_GUARD();

    RAMBLOCK_FOREACH_NOT_IGNORED(block) {
        total += block->used_length;
    }
    return total;
}

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;

    /* We don't use dirty log with background snapshots */
    if (!migrate_background_snapshot()) {
        /* caller have hold iothread lock or is in a bh, so there is
         * no writing race against the migration bitmap
         */
        if (global_dirty_tracking & GLOBAL_DIRTY_MIGRATION) {
            /*
             * do not stop dirty log without starting it, since
             * memory_global_dirty_log_stop will assert that
             * memory_global_dirty_log_start/stop used in pairs
             */
            memory_global_dirty_log_stop(GLOBAL_DIRTY_MIGRATION);
        }
    }

    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);
    g_free(migration_ops);
    migration_ops = NULL;
}

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

    for (i = 0; i < RAM_CHANNEL_MAX; i++) {
        rs->pss[i].last_sent_block = NULL;
    }

    rs->last_seen_block = NULL;
    rs->last_page = 0;
    rs->last_version = ram_list.version;
    rs->xbzrle_enabled = false;
}

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

/* **** 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,
                              ((ram_addr_t)run_start) << TARGET_PAGE_BITS,
                              ((ram_addr_t)(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
 *
 * Callback from postcopy_each_ram_send_discard for each RAMBlock
 *
 * @ms: current migration state
 * @block: RAMBlock to discard
 */
static void 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;
    }
}

static void postcopy_chunk_hostpages_pass(MigrationState *ms, RAMBlock *block);

/**
 * postcopy_each_ram_send_discard: discard all RAMBlocks
 *
 * 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 void postcopy_each_ram_send_discard(MigrationState *ms)
{
    struct RAMBlock *block;

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

        /*
         * Deal with TPS != HPS and huge pages.  It 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.
         */
        postcopy_chunk_hostpages_pass(ms, block);

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

/**
 * 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);
    }
}

/**
 * ram_postcopy_send_discard_bitmap: transmit the discard bitmap
 *
 * 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
 */
void ram_postcopy_send_discard_bitmap(MigrationState *ms)
{
    RAMState *rs = ram_state;

    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->pss[RAM_CHANNEL_PRECOPY].last_sent_block = NULL;
    rs->last_seen_block = NULL;
    rs->last_page = 0;

    postcopy_each_ram_send_discard(ms);

    trace_ram_postcopy_send_discard_bitmap();
}

/**
 * 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_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);
    (*rsp)->ram_bytes_total = ram_bytes_total();

    /*
     * 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 = (*rsp)->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 migration_bitmap_clear_discarded_pages(RAMState *rs)
{
    unsigned long pages;
    RAMBlock *rb;

    RCU_READ_LOCK_GUARD();

    RAMBLOCK_FOREACH_NOT_IGNORED(rb) {
            pages = ramblock_dirty_bitmap_clear_discarded_pages(rb);
            rs->migration_dirty_pages -= pages;
    }
}

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();
        /* We don't use dirty log with background snapshots */
        if (!migrate_background_snapshot()) {
            memory_global_dirty_log_start(GLOBAL_DIRTY_MIGRATION);
            migration_bitmap_sync_precopy(rs);
        }
    }
    qemu_mutex_unlock_ramlist();
    qemu_mutex_unlock_iothread();

    /*
     * After an eventual first bitmap sync, fixup the initial bitmap
     * containing all 1s to exclude any discarded pages from migration.
     */
    migration_bitmap_clear_discarded_pages(rs);
}

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;

    ram_state_reset(rs);

    /* Update RAMState cache of output QEMUFile */
    rs->pss[RAM_CHANNEL_PRECOPY].pss_channel = 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);
        /*
         * The skipped free pages are equavalent to be sent from clear_bmap's
         * perspective, so clear the bits from the memory region bitmap which
         * are initially set. Otherwise those skipped pages will be sent in
         * the next round after syncing from the memory region bitmap.
         */
        migration_clear_memory_region_dirty_bitmap_range(block, start, npages);
        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;
    int ret;

    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)->pss[RAM_CHANNEL_PRECOPY].pss_channel = f;

    WITH_RCU_READ_LOCK_GUARD() {
        qemu_put_be64(f, ram_bytes_total_with_ignored()
                         | 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);

    migration_ops = g_malloc0(sizeof(MigrationOps));
    migration_ops->ram_save_target_page = ram_save_target_page_legacy;
    ret = multifd_send_sync_main(f);
    if (ret < 0) {
        return ret;
    }

    if (!migrate_multifd_flush_after_each_section()) {
        qemu_put_be64(f, RAM_SAVE_FLAG_MULTIFD_FLUSH);
    }

    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 = 0;
    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;
    }

    /*
     * We'll take this lock a little bit long, but it's okay for two reasons.
     * Firstly, the only possible other thread to take it is who calls
     * qemu_guest_free_page_hint(), which should be rare; secondly, see
     * MAX_WAIT (if curious, further see commit 4508bd9ed8053ce) below, which
     * guarantees that we'll at least released it in a regular basis.
     */
    qemu_mutex_lock(&rs->bitmap_mutex);
    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 ||
               postcopy_has_request(rs)) {
            int pages;

            if (qemu_file_get_error(f)) {
                break;
            }

            pages = ram_find_and_save_block(rs);
            /* 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;

            /*
             * During postcopy, it is necessary to make sure one whole host
             * page is sent in one chunk.
             */
            if (migrate_postcopy_ram()) {
                flush_compressed_data(rs);
            }

            /*
             * 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++;
        }
    }
    qemu_mutex_unlock(&rs->bitmap_mutex);

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

out:
    if (ret >= 0
        && migration_is_setup_or_active(migrate_get_current()->state)) {
        if (migrate_multifd_flush_after_each_section()) {
            ret = multifd_send_sync_main(rs->pss[RAM_CHANNEL_PRECOPY].pss_channel);
            if (ret < 0) {
                return ret;
            }
        }

        qemu_put_be64(f, RAM_SAVE_FLAG_EOS);
        qemu_fflush(f);
        ram_transferred_add(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;

    rs->last_stage = !migration_in_colo_state();

    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 */
        qemu_mutex_lock(&rs->bitmap_mutex);
        while (true) {
            int pages;

            pages = ram_find_and_save_block(rs);
            /* no more blocks to sent */
            if (pages == 0) {
                break;
            }
            if (pages < 0) {
                ret = pages;
                break;
            }
        }
        qemu_mutex_unlock(&rs->bitmap_mutex);

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

    if (ret < 0) {
        return ret;
    }

    ret = multifd_send_sync_main(rs->pss[RAM_CHANNEL_PRECOPY].pss_channel);
    if (ret < 0) {
        return ret;
    }

    if (!migrate_multifd_flush_after_each_section()) {
        qemu_put_be64(f, RAM_SAVE_FLAG_MULTIFD_FLUSH);
    }
    qemu_put_be64(f, RAM_SAVE_FLAG_EOS);
    qemu_fflush(f);

    return 0;
}

static void ram_state_pending_estimate(void *opaque, uint64_t *must_precopy,
                                       uint64_t *can_postcopy)
{
    RAMState **temp = opaque;
    RAMState *rs = *temp;

    uint64_t remaining_size = rs->migration_dirty_pages * TARGET_PAGE_SIZE;

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

static void ram_state_pending_exact(void *opaque, uint64_t *must_precopy,
                                    uint64_t *can_postcopy)
{
    MigrationState *s = migrate_get_current();
    RAMState **temp = opaque;
    RAMState *rs = *temp;

    uint64_t remaining_size = rs->migration_dirty_pages * TARGET_PAGE_SIZE;

    if (!migration_in_postcopy() && remaining_size < s->threshold_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 */
        *can_postcopy += remaining_size;
    } else {
        *must_precopy += 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.
 *
 * @mis: the migration incoming state pointer
 * @f: QEMUFile where to read the data from
 * @flags: Page flags (mostly to see if it's a continuation of previous block)
 * @channel: the channel we're using
 */
static inline RAMBlock *ram_block_from_stream(MigrationIncomingState *mis,
                                              QEMUFile *f, int flags,
                                              int channel)
{
    RAMBlock *block = mis->last_recv_block[channel];
    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;
    }

    mis->last_recv_block[channel] = block;

    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 void *host_page_from_ram_block_offset(RAMBlock *block,
                                             ram_addr_t offset)
{
    /* Note: Explicitly no check against offset_in_ramblock(). */
    return (void *)QEMU_ALIGN_DOWN((uintptr_t)(block->host + offset),
                                   block->page_size);
}

static ram_addr_t host_page_offset_from_ram_block_offset(RAMBlock *block,
                                                         ram_addr_t offset)
{
    return ((uintptr_t)block->host + offset) & (block->page_size - 1);
}

static inline void *colo_cache_from_block_offset(RAMBlock *block,
                             ram_addr_t offset, bool record_bitmap)
{
    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 (record_bitmap &&
        !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 || !buffer_is_zero(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_compress()) {
        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_compress()) {
        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_compress()) {
        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_LOCK_GUARD(&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);
        }
    }
}

static void colo_init_ram_state(void)
{
    ram_state_init(&ram_state);
}

/*
 * 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, 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;
            }
            if (!machine_dump_guest_core(current_machine)) {
                qemu_madvise(block->colo_cache, block->used_length,
                             QEMU_MADV_DONTDUMP);
            }
        }
    }

    /*
    * 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);
        }
    }

    colo_init_ram_state();
    return 0;
}

/* TODO: duplicated with ram_init_bitmaps */
void colo_incoming_start_dirty_log(void)
{
    RAMBlock *block = NULL;
    /* For memory_global_dirty_log_start below. */
    qemu_mutex_lock_iothread();
    qemu_mutex_lock_ramlist();

    memory_global_dirty_log_sync();
    WITH_RCU_READ_LOCK_GUARD() {
        RAMBLOCK_FOREACH_NOT_IGNORED(block) {
            ramblock_sync_dirty_bitmap(ram_state, block);
            /* Discard this dirty bitmap record */
            bitmap_zero(block->bmap, block->max_length >> TARGET_PAGE_BITS);
        }
        memory_global_dirty_log_start(GLOBAL_DIRTY_MIGRATION);
    }
    ram_state->migration_dirty_pages = 0;
    qemu_mutex_unlock_ramlist();
    qemu_mutex_unlock_iothread();
}

/* 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(GLOBAL_DIRTY_MIGRATION);
    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;
            }
        }
    }
    ram_state_cleanup(&ram_state);
}

/**
 * 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
 * @channel: the channel to use for loading
 */
int ram_load_postcopy(QEMUFile *f, int channel)
{
    int flags = 0, ret = 0;
    bool place_needed = false;
    bool matches_target_page_size = false;
    MigrationIncomingState *mis = migration_incoming_get_current();
    PostcopyTmpPage *tmp_page = &mis->postcopy_tmp_pages[channel];

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

        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(channel, (uint64_t)addr, flags);
        if (flags & (RAM_SAVE_FLAG_ZERO | RAM_SAVE_FLAG_PAGE |
                     RAM_SAVE_FLAG_COMPRESS_PAGE)) {
            block = ram_block_from_stream(mis, f, flags, channel);
            if (!block) {
                ret = -EINVAL;
                break;
            }

            /*
             * Relying on used_length is racy and can result in false positives.
             * We might place pages beyond used_length in case RAM was shrunk
             * while in postcopy, which is fine - trying to place via
             * UFFDIO_COPY/UFFDIO_ZEROPAGE will never segfault.
             */
            if (!block->host || addr >= block->postcopy_length) {
                error_report("Illegal RAM offset " RAM_ADDR_FMT, addr);
                ret = -EINVAL;
                break;
            }
            tmp_page->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 = tmp_page->tmp_huge_page +
                          host_page_offset_from_ram_block_offset(block, addr);
            /* If all TP are zero then we can optimise the place */
            if (tmp_page->target_pages == 1) {
                tmp_page->host_addr =
                    host_page_from_ram_block_offset(block, addr);
            } else if (tmp_page->host_addr !=
                       host_page_from_ram_block_offset(block, addr)) {
                /* not the 1st TP within the HP */
                error_report("Non-same host page detected on channel %d: "
                             "Target host page %p, received host page %p "
                             "(rb %s offset 0x"RAM_ADDR_FMT" target_pages %d)",
                             channel, tmp_page->host_addr,
                             host_page_from_ram_block_offset(block, addr),
                             block->idstr, addr, tmp_page->target_pages);
                ret = -EINVAL;
                break;
            }

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

        case RAM_SAVE_FLAG_PAGE:
            tmp_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_COMPRESS_PAGE:
            tmp_page->all_zero = false;
            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, page_buffer, len);
            break;
        case RAM_SAVE_FLAG_MULTIFD_FLUSH:
            multifd_recv_sync_main();
            break;
        case RAM_SAVE_FLAG_EOS:
            /* normal exit */
            if (migrate_multifd_flush_after_each_section()) {
                multifd_recv_sync_main();
            }
            break;
        default:
            error_report("Unknown combination of migration flags: 0x%x"
                         " (postcopy mode)", flags);
            ret = -EINVAL;
            break;
        }

        /* Got the whole host page, wait for decompress before placing. */
        if (place_needed) {
            ret |= wait_for_decompress_done();
        }

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

        if (!ret && place_needed) {
            if (tmp_page->all_zero) {
                ret = postcopy_place_page_zero(mis, tmp_page->host_addr, block);
            } else {
                ret = postcopy_place_page(mis, tmp_page->host_addr,
                                          place_source, block);
            }
            place_needed = false;
            postcopy_temp_page_reset(tmp_page);
        }
    }

    return ret;
}

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.
 */
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) {
            unsigned long num = 0;

            offset = colo_bitmap_find_dirty(ram_state, block, offset, &num);
            if (!offset_in_ramblock(block,
                                    ((ram_addr_t)offset) << TARGET_PAGE_BITS)) {
                offset = 0;
                num = 0;
                block = QLIST_NEXT_RCU(block, next);
            } else {
                unsigned long i = 0;

                for (i = 0; i < num; i++) {
                    migration_bitmap_clear_dirty(ram_state, block, offset + i);
                }
                dst_host = block->host
                         + (((ram_addr_t)offset) << TARGET_PAGE_BITS);
                src_host = block->colo_cache
                         + (((ram_addr_t)offset) << TARGET_PAGE_BITS);
                memcpy(dst_host, src_host, TARGET_PAGE_SIZE * num);
                offset += num;
            }
        }
    }
    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)
{
    MigrationIncomingState *mis = migration_incoming_get_current();
    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 = migration_incoming_postcopy_advised();
    if (!migrate_compress()) {
        invalid_flags |= RAM_SAVE_FLAG_COMPRESS_PAGE;
    }

    while (!ret && !(flags & RAM_SAVE_FLAG_EOS)) {
        ram_addr_t addr, total_ram_bytes;
        void *host = NULL, *host_bak = 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(mis, f, flags,
                                                    RAM_CHANNEL_PRECOPY);

            host = host_from_ram_block_offset(block, addr);
            /*
             * After going into COLO stage, we should not load the page
             * into SVM's memory directly, we put them into colo_cache firstly.
             * NOTE: We need to keep a copy of SVM's ram in colo_cache.
             * Previously, we copied all these memory in preparing stage of COLO
             * while we need to stop VM, which is a time-consuming process.
             * Here we optimize it by a trick, back-up every page while in
             * migration process while COLO is enabled, though it affects the
             * speed of the migration, but it obviously reduce the downtime of
             * back-up all SVM'S memory in COLO preparing stage.
             */
            if (migration_incoming_colo_enabled()) {
                if (migration_incoming_in_colo_state()) {
                    /* In COLO stage, put all pages into cache temporarily */
                    host = colo_cache_from_block_offset(block, addr, true);
                } else {
                   /*
                    * In migration stage but before COLO stage,
                    * Put all pages into both cache and SVM's memory.
                    */
                    host_bak = colo_cache_from_block_offset(block, addr, false);
                }
            }
            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 && migrate_postcopy_ram() &&
                        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_MULTIFD_FLUSH:
            multifd_recv_sync_main();
            break;
        case RAM_SAVE_FLAG_EOS:
            /* normal exit */
            if (migrate_multifd_flush_after_each_section()) {
                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: 0x%x",
                             flags);
                ret = -EINVAL;
            }
        }
        if (!ret) {
            ret = qemu_file_get_error(f);
        }
        if (!ret && host_bak) {
            memcpy(host_bak, host, TARGET_PAGE_SIZE);
        }
    }

    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) {
            /*
             * Note!  Here RAM_CHANNEL_PRECOPY is the precopy channel of
             * postcopy migration, we have another RAM_CHANNEL_POSTCOPY to
             * service fast page faults.
             */
            ret = ram_load_postcopy(f, RAM_CHANNEL_PRECOPY);
        } else {
            ret = ram_load_precopy(f);
        }
    }
    trace_ram_load_complete(ret, seq_iter);

    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;
    /* from_dst_file is always valid because we're within rp_thread */
    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 endianness conversion, 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%"PRIx64,
                     __func__, block->idstr, end_mark);
        ret = -EINVAL;
        goto out;
    }

    /*
     * Endianness conversion. 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);

    /* Clear dirty bits of discarded ranges that we don't want to migrate. */
    ramblock_dirty_bitmap_clear_discarded_pages(block);

    /* We'll recalculate migration_dirty_pages in ram_state_resume_prepare(). */
    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;
}

void postcopy_preempt_shutdown_file(MigrationState *s)
{
    qemu_put_be64(s->postcopy_qemufile_src, RAM_SAVE_FLAG_EOS);
    qemu_fflush(s->postcopy_qemufile_src);
}

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,
    .state_pending_exact = ram_state_pending_exact,
    .state_pending_estimate = ram_state_pending_estimate,
    .load_state = ram_load,
    .save_cleanup = ram_save_cleanup,
    .load_setup = ram_load_setup,
    .load_cleanup = ram_load_cleanup,
    .resume_prepare = ram_resume_prepare,
};

static void ram_mig_ram_block_resized(RAMBlockNotifier *n, void *host,
                                      size_t old_size, size_t new_size)
{
    PostcopyState ps = postcopy_state_get();
    ram_addr_t offset;
    RAMBlock *rb = qemu_ram_block_from_host(host, false, &offset);
    Error *err = NULL;

    if (ramblock_is_ignored(rb)) {
        return;
    }

    if (!migration_is_idle()) {
        /*
         * Precopy code on the source cannot deal with the size of RAM blocks
         * changing at random points in time - especially after sending the
         * RAM block sizes in the migration stream, they must no longer change.
         * Abort and indicate a proper reason.
         */
        error_setg(&err, "RAM block '%s' resized during precopy.", rb->idstr);
        migration_cancel(err);
        error_free(err);
    }

    switch (ps) {
    case POSTCOPY_INCOMING_ADVISE:
        /*
         * Update what ram_postcopy_incoming_init()->init_range() does at the
         * time postcopy was advised. Syncing RAM blocks with the source will
         * result in RAM resizes.
         */
        if (old_size < new_size) {
            if (ram_discard_range(rb->idstr, old_size, new_size - old_size)) {
                error_report("RAM block '%s' discard of resized RAM failed",
                             rb->idstr);
            }
        }
        rb->postcopy_length = new_size;
        break;
    case POSTCOPY_INCOMING_NONE:
    case POSTCOPY_INCOMING_RUNNING:
    case POSTCOPY_INCOMING_END:
        /*
         * Once our guest is running, postcopy does no longer care about
         * resizes. When growing, the new memory was not available on the
         * source, no handler needed.
         */
        break;
    default:
        error_report("RAM block '%s' resized during postcopy state: %d",
                     rb->idstr, ps);
        exit(-1);
    }
}

static RAMBlockNotifier ram_mig_ram_notifier = {
    .ram_block_resized = ram_mig_ram_block_resized,
};

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