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
|
// SPDX-License-Identifier: GPL-2.0-only
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/err.h>
#include <linux/spinlock.h>
#include <linux/mm.h>
#include <linux/memremap.h>
#include <linux/pagemap.h>
#include <linux/rmap.h>
#include <linux/swap.h>
#include <linux/swapops.h>
#include <linux/secretmem.h>
#include <linux/sched/signal.h>
#include <linux/rwsem.h>
#include <linux/hugetlb.h>
#include <linux/migrate.h>
#include <linux/mm_inline.h>
#include <linux/sched/mm.h>
#include <asm/mmu_context.h>
#include <asm/tlbflush.h>
#include "internal.h"
struct follow_page_context {
struct dev_pagemap *pgmap;
unsigned int page_mask;
};
static inline void sanity_check_pinned_pages(struct page **pages,
unsigned long npages)
{
if (!IS_ENABLED(CONFIG_DEBUG_VM))
return;
/*
* We only pin anonymous pages if they are exclusive. Once pinned, we
* can no longer turn them possibly shared and PageAnonExclusive() will
* stick around until the page is freed.
*
* We'd like to verify that our pinned anonymous pages are still mapped
* exclusively. The issue with anon THP is that we don't know how
* they are/were mapped when pinning them. However, for anon
* THP we can assume that either the given page (PTE-mapped THP) or
* the head page (PMD-mapped THP) should be PageAnonExclusive(). If
* neither is the case, there is certainly something wrong.
*/
for (; npages; npages--, pages++) {
struct page *page = *pages;
struct folio *folio = page_folio(page);
if (!folio_test_anon(folio))
continue;
if (!folio_test_large(folio) || folio_test_hugetlb(folio))
VM_BUG_ON_PAGE(!PageAnonExclusive(&folio->page), page);
else
/* Either a PTE-mapped or a PMD-mapped THP. */
VM_BUG_ON_PAGE(!PageAnonExclusive(&folio->page) &&
!PageAnonExclusive(page), page);
}
}
/*
* Return the folio with ref appropriately incremented,
* or NULL if that failed.
*/
static inline struct folio *try_get_folio(struct page *page, int refs)
{
struct folio *folio;
retry:
folio = page_folio(page);
if (WARN_ON_ONCE(folio_ref_count(folio) < 0))
return NULL;
if (unlikely(!folio_ref_try_add_rcu(folio, refs)))
return NULL;
/*
* At this point we have a stable reference to the folio; but it
* could be that between calling page_folio() and the refcount
* increment, the folio was split, in which case we'd end up
* holding a reference on a folio that has nothing to do with the page
* we were given anymore.
* So now that the folio is stable, recheck that the page still
* belongs to this folio.
*/
if (unlikely(page_folio(page) != folio)) {
if (!put_devmap_managed_page_refs(&folio->page, refs))
folio_put_refs(folio, refs);
goto retry;
}
return folio;
}
/**
* try_grab_folio() - Attempt to get or pin a folio.
* @page: pointer to page to be grabbed
* @refs: the value to (effectively) add to the folio's refcount
* @flags: gup flags: these are the FOLL_* flag values.
*
* "grab" names in this file mean, "look at flags to decide whether to use
* FOLL_PIN or FOLL_GET behavior, when incrementing the folio's refcount.
*
* Either FOLL_PIN or FOLL_GET (or neither) must be set, but not both at the
* same time. (That's true throughout the get_user_pages*() and
* pin_user_pages*() APIs.) Cases:
*
* FOLL_GET: folio's refcount will be incremented by @refs.
*
* FOLL_PIN on large folios: folio's refcount will be incremented by
* @refs, and its compound_pincount will be incremented by @refs.
*
* FOLL_PIN on single-page folios: folio's refcount will be incremented by
* @refs * GUP_PIN_COUNTING_BIAS.
*
* Return: The folio containing @page (with refcount appropriately
* incremented) for success, or NULL upon failure. If neither FOLL_GET
* nor FOLL_PIN was set, that's considered failure, and furthermore,
* a likely bug in the caller, so a warning is also emitted.
*/
struct folio *try_grab_folio(struct page *page, int refs, unsigned int flags)
{
if (flags & FOLL_GET)
return try_get_folio(page, refs);
else if (flags & FOLL_PIN) {
struct folio *folio;
/*
* Can't do FOLL_LONGTERM + FOLL_PIN gup fast path if not in a
* right zone, so fail and let the caller fall back to the slow
* path.
*/
if (unlikely((flags & FOLL_LONGTERM) &&
!is_longterm_pinnable_page(page)))
return NULL;
/*
* CAUTION: Don't use compound_head() on the page before this
* point, the result won't be stable.
*/
folio = try_get_folio(page, refs);
if (!folio)
return NULL;
/*
* When pinning a large folio, use an exact count to track it.
*
* However, be sure to *also* increment the normal folio
* refcount field at least once, so that the folio really
* is pinned. That's why the refcount from the earlier
* try_get_folio() is left intact.
*/
if (folio_test_large(folio))
atomic_add(refs, folio_pincount_ptr(folio));
else
folio_ref_add(folio,
refs * (GUP_PIN_COUNTING_BIAS - 1));
/*
* Adjust the pincount before re-checking the PTE for changes.
* This is essentially a smp_mb() and is paired with a memory
* barrier in page_try_share_anon_rmap().
*/
smp_mb__after_atomic();
node_stat_mod_folio(folio, NR_FOLL_PIN_ACQUIRED, refs);
return folio;
}
WARN_ON_ONCE(1);
return NULL;
}
static void gup_put_folio(struct folio *folio, int refs, unsigned int flags)
{
if (flags & FOLL_PIN) {
node_stat_mod_folio(folio, NR_FOLL_PIN_RELEASED, refs);
if (folio_test_large(folio))
atomic_sub(refs, folio_pincount_ptr(folio));
else
refs *= GUP_PIN_COUNTING_BIAS;
}
if (!put_devmap_managed_page_refs(&folio->page, refs))
folio_put_refs(folio, refs);
}
/**
* try_grab_page() - elevate a page's refcount by a flag-dependent amount
* @page: pointer to page to be grabbed
* @flags: gup flags: these are the FOLL_* flag values.
*
* This might not do anything at all, depending on the flags argument.
*
* "grab" names in this file mean, "look at flags to decide whether to use
* FOLL_PIN or FOLL_GET behavior, when incrementing the page's refcount.
*
* Either FOLL_PIN or FOLL_GET (or neither) may be set, but not both at the same
* time. Cases: please see the try_grab_folio() documentation, with
* "refs=1".
*
* Return: true for success, or if no action was required (if neither FOLL_PIN
* nor FOLL_GET was set, nothing is done). False for failure: FOLL_GET or
* FOLL_PIN was set, but the page could not be grabbed.
*/
bool __must_check try_grab_page(struct page *page, unsigned int flags)
{
struct folio *folio = page_folio(page);
WARN_ON_ONCE((flags & (FOLL_GET | FOLL_PIN)) == (FOLL_GET | FOLL_PIN));
if (WARN_ON_ONCE(folio_ref_count(folio) <= 0))
return false;
if (flags & FOLL_GET)
folio_ref_inc(folio);
else if (flags & FOLL_PIN) {
/*
* Similar to try_grab_folio(): be sure to *also*
* increment the normal page refcount field at least once,
* so that the page really is pinned.
*/
if (folio_test_large(folio)) {
folio_ref_add(folio, 1);
atomic_add(1, folio_pincount_ptr(folio));
} else {
folio_ref_add(folio, GUP_PIN_COUNTING_BIAS);
}
node_stat_mod_folio(folio, NR_FOLL_PIN_ACQUIRED, 1);
}
return true;
}
/**
* unpin_user_page() - release a dma-pinned page
* @page: pointer to page to be released
*
* Pages that were pinned via pin_user_pages*() must be released via either
* unpin_user_page(), or one of the unpin_user_pages*() routines. This is so
* that such pages can be separately tracked and uniquely handled. In
* particular, interactions with RDMA and filesystems need special handling.
*/
void unpin_user_page(struct page *page)
{
sanity_check_pinned_pages(&page, 1);
gup_put_folio(page_folio(page), 1, FOLL_PIN);
}
EXPORT_SYMBOL(unpin_user_page);
static inline struct folio *gup_folio_range_next(struct page *start,
unsigned long npages, unsigned long i, unsigned int *ntails)
{
struct page *next = nth_page(start, i);
struct folio *folio = page_folio(next);
unsigned int nr = 1;
if (folio_test_large(folio))
nr = min_t(unsigned int, npages - i,
folio_nr_pages(folio) - folio_page_idx(folio, next));
*ntails = nr;
return folio;
}
static inline struct folio *gup_folio_next(struct page **list,
unsigned long npages, unsigned long i, unsigned int *ntails)
{
struct folio *folio = page_folio(list[i]);
unsigned int nr;
for (nr = i + 1; nr < npages; nr++) {
if (page_folio(list[nr]) != folio)
break;
}
*ntails = nr - i;
return folio;
}
/**
* unpin_user_pages_dirty_lock() - release and optionally dirty gup-pinned pages
* @pages: array of pages to be maybe marked dirty, and definitely released.
* @npages: number of pages in the @pages array.
* @make_dirty: whether to mark the pages dirty
*
* "gup-pinned page" refers to a page that has had one of the get_user_pages()
* variants called on that page.
*
* For each page in the @pages array, make that page (or its head page, if a
* compound page) dirty, if @make_dirty is true, and if the page was previously
* listed as clean. In any case, releases all pages using unpin_user_page(),
* possibly via unpin_user_pages(), for the non-dirty case.
*
* Please see the unpin_user_page() documentation for details.
*
* set_page_dirty_lock() is used internally. If instead, set_page_dirty() is
* required, then the caller should a) verify that this is really correct,
* because _lock() is usually required, and b) hand code it:
* set_page_dirty_lock(), unpin_user_page().
*
*/
void unpin_user_pages_dirty_lock(struct page **pages, unsigned long npages,
bool make_dirty)
{
unsigned long i;
struct folio *folio;
unsigned int nr;
if (!make_dirty) {
unpin_user_pages(pages, npages);
return;
}
sanity_check_pinned_pages(pages, npages);
for (i = 0; i < npages; i += nr) {
folio = gup_folio_next(pages, npages, i, &nr);
/*
* Checking PageDirty at this point may race with
* clear_page_dirty_for_io(), but that's OK. Two key
* cases:
*
* 1) This code sees the page as already dirty, so it
* skips the call to set_page_dirty(). That could happen
* because clear_page_dirty_for_io() called
* page_mkclean(), followed by set_page_dirty().
* However, now the page is going to get written back,
* which meets the original intention of setting it
* dirty, so all is well: clear_page_dirty_for_io() goes
* on to call TestClearPageDirty(), and write the page
* back.
*
* 2) This code sees the page as clean, so it calls
* set_page_dirty(). The page stays dirty, despite being
* written back, so it gets written back again in the
* next writeback cycle. This is harmless.
*/
if (!folio_test_dirty(folio)) {
folio_lock(folio);
folio_mark_dirty(folio);
folio_unlock(folio);
}
gup_put_folio(folio, nr, FOLL_PIN);
}
}
EXPORT_SYMBOL(unpin_user_pages_dirty_lock);
/**
* unpin_user_page_range_dirty_lock() - release and optionally dirty
* gup-pinned page range
*
* @page: the starting page of a range maybe marked dirty, and definitely released.
* @npages: number of consecutive pages to release.
* @make_dirty: whether to mark the pages dirty
*
* "gup-pinned page range" refers to a range of pages that has had one of the
* pin_user_pages() variants called on that page.
*
* For the page ranges defined by [page .. page+npages], make that range (or
* its head pages, if a compound page) dirty, if @make_dirty is true, and if the
* page range was previously listed as clean.
*
* set_page_dirty_lock() is used internally. If instead, set_page_dirty() is
* required, then the caller should a) verify that this is really correct,
* because _lock() is usually required, and b) hand code it:
* set_page_dirty_lock(), unpin_user_page().
*
*/
void unpin_user_page_range_dirty_lock(struct page *page, unsigned long npages,
bool make_dirty)
{
unsigned long i;
struct folio *folio;
unsigned int nr;
for (i = 0; i < npages; i += nr) {
folio = gup_folio_range_next(page, npages, i, &nr);
if (make_dirty && !folio_test_dirty(folio)) {
folio_lock(folio);
folio_mark_dirty(folio);
folio_unlock(folio);
}
gup_put_folio(folio, nr, FOLL_PIN);
}
}
EXPORT_SYMBOL(unpin_user_page_range_dirty_lock);
static void unpin_user_pages_lockless(struct page **pages, unsigned long npages)
{
unsigned long i;
struct folio *folio;
unsigned int nr;
/*
* Don't perform any sanity checks because we might have raced with
* fork() and some anonymous pages might now actually be shared --
* which is why we're unpinning after all.
*/
for (i = 0; i < npages; i += nr) {
folio = gup_folio_next(pages, npages, i, &nr);
gup_put_folio(folio, nr, FOLL_PIN);
}
}
/**
* unpin_user_pages() - release an array of gup-pinned pages.
* @pages: array of pages to be marked dirty and released.
* @npages: number of pages in the @pages array.
*
* For each page in the @pages array, release the page using unpin_user_page().
*
* Please see the unpin_user_page() documentation for details.
*/
void unpin_user_pages(struct page **pages, unsigned long npages)
{
unsigned long i;
struct folio *folio;
unsigned int nr;
/*
* If this WARN_ON() fires, then the system *might* be leaking pages (by
* leaving them pinned), but probably not. More likely, gup/pup returned
* a hard -ERRNO error to the caller, who erroneously passed it here.
*/
if (WARN_ON(IS_ERR_VALUE(npages)))
return;
sanity_check_pinned_pages(pages, npages);
for (i = 0; i < npages; i += nr) {
folio = gup_folio_next(pages, npages, i, &nr);
gup_put_folio(folio, nr, FOLL_PIN);
}
}
EXPORT_SYMBOL(unpin_user_pages);
/*
* Set the MMF_HAS_PINNED if not set yet; after set it'll be there for the mm's
* lifecycle. Avoid setting the bit unless necessary, or it might cause write
* cache bouncing on large SMP machines for concurrent pinned gups.
*/
static inline void mm_set_has_pinned_flag(unsigned long *mm_flags)
{
if (!test_bit(MMF_HAS_PINNED, mm_flags))
set_bit(MMF_HAS_PINNED, mm_flags);
}
#ifdef CONFIG_MMU
static struct page *no_page_table(struct vm_area_struct *vma,
unsigned int flags)
{
/*
* When core dumping an enormous anonymous area that nobody
* has touched so far, we don't want to allocate unnecessary pages or
* page tables. Return error instead of NULL to skip handle_mm_fault,
* then get_dump_page() will return NULL to leave a hole in the dump.
* But we can only make this optimization where a hole would surely
* be zero-filled if handle_mm_fault() actually did handle it.
*/
if ((flags & FOLL_DUMP) &&
(vma_is_anonymous(vma) || !vma->vm_ops->fault))
return ERR_PTR(-EFAULT);
return NULL;
}
static int follow_pfn_pte(struct vm_area_struct *vma, unsigned long address,
pte_t *pte, unsigned int flags)
{
if (flags & FOLL_TOUCH) {
pte_t entry = *pte;
if (flags & FOLL_WRITE)
entry = pte_mkdirty(entry);
entry = pte_mkyoung(entry);
if (!pte_same(*pte, entry)) {
set_pte_at(vma->vm_mm, address, pte, entry);
update_mmu_cache(vma, address, pte);
}
}
/* Proper page table entry exists, but no corresponding struct page */
return -EEXIST;
}
/* FOLL_FORCE can write to even unwritable PTEs in COW mappings. */
static inline bool can_follow_write_pte(pte_t pte, struct page *page,
struct vm_area_struct *vma,
unsigned int flags)
{
/* If the pte is writable, we can write to the page. */
if (pte_write(pte))
return true;
/* Maybe FOLL_FORCE is set to override it? */
if (!(flags & FOLL_FORCE))
return false;
/* But FOLL_FORCE has no effect on shared mappings */
if (vma->vm_flags & (VM_MAYSHARE | VM_SHARED))
return false;
/* ... or read-only private ones */
if (!(vma->vm_flags & VM_MAYWRITE))
return false;
/* ... or already writable ones that just need to take a write fault */
if (vma->vm_flags & VM_WRITE)
return false;
/*
* See can_change_pte_writable(): we broke COW and could map the page
* writable if we have an exclusive anonymous page ...
*/
if (!page || !PageAnon(page) || !PageAnonExclusive(page))
return false;
/* ... and a write-fault isn't required for other reasons. */
if (vma_soft_dirty_enabled(vma) && !pte_soft_dirty(pte))
return false;
return !userfaultfd_pte_wp(vma, pte);
}
static struct page *follow_page_pte(struct vm_area_struct *vma,
unsigned long address, pmd_t *pmd, unsigned int flags,
struct dev_pagemap **pgmap)
{
struct mm_struct *mm = vma->vm_mm;
struct page *page;
spinlock_t *ptl;
pte_t *ptep, pte;
int ret;
/* FOLL_GET and FOLL_PIN are mutually exclusive. */
if (WARN_ON_ONCE((flags & (FOLL_PIN | FOLL_GET)) ==
(FOLL_PIN | FOLL_GET)))
return ERR_PTR(-EINVAL);
retry:
if (unlikely(pmd_bad(*pmd)))
return no_page_table(vma, flags);
ptep = pte_offset_map_lock(mm, pmd, address, &ptl);
pte = *ptep;
if (!pte_present(pte)) {
swp_entry_t entry;
/*
* KSM's break_ksm() relies upon recognizing a ksm page
* even while it is being migrated, so for that case we
* need migration_entry_wait().
*/
if (likely(!(flags & FOLL_MIGRATION)))
goto no_page;
if (pte_none(pte))
goto no_page;
entry = pte_to_swp_entry(pte);
if (!is_migration_entry(entry))
goto no_page;
pte_unmap_unlock(ptep, ptl);
migration_entry_wait(mm, pmd, address);
goto retry;
}
if (pte_protnone(pte) && !gup_can_follow_protnone(flags))
goto no_page;
page = vm_normal_page(vma, address, pte);
/*
* We only care about anon pages in can_follow_write_pte() and don't
* have to worry about pte_devmap() because they are never anon.
*/
if ((flags & FOLL_WRITE) &&
!can_follow_write_pte(pte, page, vma, flags)) {
page = NULL;
goto out;
}
if (!page && pte_devmap(pte) && (flags & (FOLL_GET | FOLL_PIN))) {
/*
* Only return device mapping pages in the FOLL_GET or FOLL_PIN
* case since they are only valid while holding the pgmap
* reference.
*/
*pgmap = get_dev_pagemap(pte_pfn(pte), *pgmap);
if (*pgmap)
page = pte_page(pte);
else
goto no_page;
} else if (unlikely(!page)) {
if (flags & FOLL_DUMP) {
/* Avoid special (like zero) pages in core dumps */
page = ERR_PTR(-EFAULT);
goto out;
}
if (is_zero_pfn(pte_pfn(pte))) {
page = pte_page(pte);
} else {
ret = follow_pfn_pte(vma, address, ptep, flags);
page = ERR_PTR(ret);
goto out;
}
}
if (!pte_write(pte) && gup_must_unshare(flags, page)) {
page = ERR_PTR(-EMLINK);
goto out;
}
VM_BUG_ON_PAGE((flags & FOLL_PIN) && PageAnon(page) &&
!PageAnonExclusive(page), page);
/* try_grab_page() does nothing unless FOLL_GET or FOLL_PIN is set. */
if (unlikely(!try_grab_page(page, flags))) {
page = ERR_PTR(-ENOMEM);
goto out;
}
/*
* We need to make the page accessible if and only if we are going
* to access its content (the FOLL_PIN case). Please see
* Documentation/core-api/pin_user_pages.rst for details.
*/
if (flags & FOLL_PIN) {
ret = arch_make_page_accessible(page);
if (ret) {
unpin_user_page(page);
page = ERR_PTR(ret);
goto out;
}
}
if (flags & FOLL_TOUCH) {
if ((flags & FOLL_WRITE) &&
!pte_dirty(pte) && !PageDirty(page))
set_page_dirty(page);
/*
* pte_mkyoung() would be more correct here, but atomic care
* is needed to avoid losing the dirty bit: it is easier to use
* mark_page_accessed().
*/
mark_page_accessed(page);
}
out:
pte_unmap_unlock(ptep, ptl);
return page;
no_page:
pte_unmap_unlock(ptep, ptl);
if (!pte_none(pte))
return NULL;
return no_page_table(vma, flags);
}
static struct page *follow_pmd_mask(struct vm_area_struct *vma,
unsigned long address, pud_t *pudp,
unsigned int flags,
struct follow_page_context *ctx)
{
pmd_t *pmd, pmdval;
spinlock_t *ptl;
struct page *page;
struct mm_struct *mm = vma->vm_mm;
pmd = pmd_offset(pudp, address);
/*
* The READ_ONCE() will stabilize the pmdval in a register or
* on the stack so that it will stop changing under the code.
*/
pmdval = READ_ONCE(*pmd);
if (pmd_none(pmdval))
return no_page_table(vma, flags);
retry:
if (!pmd_present(pmdval)) {
/*
* Should never reach here, if thp migration is not supported;
* Otherwise, it must be a thp migration entry.
*/
VM_BUG_ON(!thp_migration_supported() ||
!is_pmd_migration_entry(pmdval));
if (likely(!(flags & FOLL_MIGRATION)))
return no_page_table(vma, flags);
pmd_migration_entry_wait(mm, pmd);
pmdval = READ_ONCE(*pmd);
/*
* MADV_DONTNEED may convert the pmd to null because
* mmap_lock is held in read mode
*/
if (pmd_none(pmdval))
return no_page_table(vma, flags);
goto retry;
}
if (pmd_devmap(pmdval)) {
ptl = pmd_lock(mm, pmd);
page = follow_devmap_pmd(vma, address, pmd, flags, &ctx->pgmap);
spin_unlock(ptl);
if (page)
return page;
}
if (likely(!pmd_trans_huge(pmdval)))
return follow_page_pte(vma, address, pmd, flags, &ctx->pgmap);
if (pmd_protnone(pmdval) && !gup_can_follow_protnone(flags))
return no_page_table(vma, flags);
retry_locked:
ptl = pmd_lock(mm, pmd);
if (unlikely(pmd_none(*pmd))) {
spin_unlock(ptl);
return no_page_table(vma, flags);
}
if (unlikely(!pmd_present(*pmd))) {
spin_unlock(ptl);
if (likely(!(flags & FOLL_MIGRATION)))
return no_page_table(vma, flags);
pmd_migration_entry_wait(mm, pmd);
goto retry_locked;
}
if (unlikely(!pmd_trans_huge(*pmd))) {
spin_unlock(ptl);
return follow_page_pte(vma, address, pmd, flags, &ctx->pgmap);
}
if (flags & FOLL_SPLIT_PMD) {
int ret;
page = pmd_page(*pmd);
if (is_huge_zero_page(page)) {
spin_unlock(ptl);
ret = 0;
split_huge_pmd(vma, pmd, address);
if (pmd_trans_unstable(pmd))
ret = -EBUSY;
} else {
spin_unlock(ptl);
split_huge_pmd(vma, pmd, address);
ret = pte_alloc(mm, pmd) ? -ENOMEM : 0;
}
return ret ? ERR_PTR(ret) :
follow_page_pte(vma, address, pmd, flags, &ctx->pgmap);
}
page = follow_trans_huge_pmd(vma, address, pmd, flags);
spin_unlock(ptl);
ctx->page_mask = HPAGE_PMD_NR - 1;
return page;
}
static struct page *follow_pud_mask(struct vm_area_struct *vma,
unsigned long address, p4d_t *p4dp,
unsigned int flags,
struct follow_page_context *ctx)
{
pud_t *pud;
spinlock_t *ptl;
struct page *page;
struct mm_struct *mm = vma->vm_mm;
pud = pud_offset(p4dp, address);
if (pud_none(*pud))
return no_page_table(vma, flags);
if (pud_devmap(*pud)) {
ptl = pud_lock(mm, pud);
page = follow_devmap_pud(vma, address, pud, flags, &ctx->pgmap);
spin_unlock(ptl);
if (page)
return page;
}
if (unlikely(pud_bad(*pud)))
return no_page_table(vma, flags);
return follow_pmd_mask(vma, address, pud, flags, ctx);
}
static struct page *follow_p4d_mask(struct vm_area_struct *vma,
unsigned long address, pgd_t *pgdp,
unsigned int flags,
struct follow_page_context *ctx)
{
p4d_t *p4d;
p4d = p4d_offset(pgdp, address);
if (p4d_none(*p4d))
return no_page_table(vma, flags);
BUILD_BUG_ON(p4d_huge(*p4d));
if (unlikely(p4d_bad(*p4d)))
return no_page_table(vma, flags);
return follow_pud_mask(vma, address, p4d, flags, ctx);
}
/**
* follow_page_mask - look up a page descriptor from a user-virtual address
* @vma: vm_area_struct mapping @address
* @address: virtual address to look up
* @flags: flags modifying lookup behaviour
* @ctx: contains dev_pagemap for %ZONE_DEVICE memory pinning and a
* pointer to output page_mask
*
* @flags can have FOLL_ flags set, defined in <linux/mm.h>
*
* When getting pages from ZONE_DEVICE memory, the @ctx->pgmap caches
* the device's dev_pagemap metadata to avoid repeating expensive lookups.
*
* When getting an anonymous page and the caller has to trigger unsharing
* of a shared anonymous page first, -EMLINK is returned. The caller should
* trigger a fault with FAULT_FLAG_UNSHARE set. Note that unsharing is only
* relevant with FOLL_PIN and !FOLL_WRITE.
*
* On output, the @ctx->page_mask is set according to the size of the page.
*
* Return: the mapped (struct page *), %NULL if no mapping exists, or
* an error pointer if there is a mapping to something not represented
* by a page descriptor (see also vm_normal_page()).
*/
static struct page *follow_page_mask(struct vm_area_struct *vma,
unsigned long address, unsigned int flags,
struct follow_page_context *ctx)
{
pgd_t *pgd;
struct page *page;
struct mm_struct *mm = vma->vm_mm;
ctx->page_mask = 0;
/*
* Call hugetlb_follow_page_mask for hugetlb vmas as it will use
* special hugetlb page table walking code. This eliminates the
* need to check for hugetlb entries in the general walking code.
*
* hugetlb_follow_page_mask is only for follow_page() handling here.
* Ordinary GUP uses follow_hugetlb_page for hugetlb processing.
*/
if (is_vm_hugetlb_page(vma)) {
page = hugetlb_follow_page_mask(vma, address, flags);
if (!page)
page = no_page_table(vma, flags);
return page;
}
pgd = pgd_offset(mm, address);
if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd)))
return no_page_table(vma, flags);
return follow_p4d_mask(vma, address, pgd, flags, ctx);
}
struct page *follow_page(struct vm_area_struct *vma, unsigned long address,
unsigned int foll_flags)
{
struct follow_page_context ctx = { NULL };
struct page *page;
if (vma_is_secretmem(vma))
return NULL;
if (foll_flags & FOLL_PIN)
return NULL;
page = follow_page_mask(vma, address, foll_flags, &ctx);
if (ctx.pgmap)
put_dev_pagemap(ctx.pgmap);
return page;
}
static int get_gate_page(struct mm_struct *mm, unsigned long address,
unsigned int gup_flags, struct vm_area_struct **vma,
struct page **page)
{
pgd_t *pgd;
p4d_t *p4d;
pud_t *pud;
pmd_t *pmd;
pte_t *pte;
int ret = -EFAULT;
/* user gate pages are read-only */
if (gup_flags & FOLL_WRITE)
return -EFAULT;
if (address > TASK_SIZE)
pgd = pgd_offset_k(address);
else
pgd = pgd_offset_gate(mm, address);
if (pgd_none(*pgd))
return -EFAULT;
p4d = p4d_offset(pgd, address);
if (p4d_none(*p4d))
return -EFAULT;
pud = pud_offset(p4d, address);
if (pud_none(*pud))
return -EFAULT;
pmd = pmd_offset(pud, address);
if (!pmd_present(*pmd))
return -EFAULT;
VM_BUG_ON(pmd_trans_huge(*pmd));
pte = pte_offset_map(pmd, address);
if (pte_none(*pte))
goto unmap;
*vma = get_gate_vma(mm);
if (!page)
goto out;
*page = vm_normal_page(*vma, address, *pte);
if (!*page) {
if ((gup_flags & FOLL_DUMP) || !is_zero_pfn(pte_pfn(*pte)))
goto unmap;
*page = pte_page(*pte);
}
if (unlikely(!try_grab_page(*page, gup_flags))) {
ret = -ENOMEM;
goto unmap;
}
out:
ret = 0;
unmap:
pte_unmap(pte);
return ret;
}
/*
* mmap_lock must be held on entry. If @locked != NULL and *@flags
* does not include FOLL_NOWAIT, the mmap_lock may be released. If it
* is, *@locked will be set to 0 and -EBUSY returned.
*/
static int faultin_page(struct vm_area_struct *vma,
unsigned long address, unsigned int *flags, bool unshare,
int *locked)
{
unsigned int fault_flags = 0;
vm_fault_t ret;
if (*flags & FOLL_NOFAULT)
return -EFAULT;
if (*flags & FOLL_WRITE)
fault_flags |= FAULT_FLAG_WRITE;
if (*flags & FOLL_REMOTE)
fault_flags |= FAULT_FLAG_REMOTE;
if (locked)
fault_flags |= FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
if (*flags & FOLL_NOWAIT)
fault_flags |= FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_RETRY_NOWAIT;
if (*flags & FOLL_TRIED) {
/*
* Note: FAULT_FLAG_ALLOW_RETRY and FAULT_FLAG_TRIED
* can co-exist
*/
fault_flags |= FAULT_FLAG_TRIED;
}
if (unshare) {
fault_flags |= FAULT_FLAG_UNSHARE;
/* FAULT_FLAG_WRITE and FAULT_FLAG_UNSHARE are incompatible */
VM_BUG_ON(fault_flags & FAULT_FLAG_WRITE);
}
ret = handle_mm_fault(vma, address, fault_flags, NULL);
if (ret & VM_FAULT_COMPLETED) {
/*
* With FAULT_FLAG_RETRY_NOWAIT we'll never release the
* mmap lock in the page fault handler. Sanity check this.
*/
WARN_ON_ONCE(fault_flags & FAULT_FLAG_RETRY_NOWAIT);
if (locked)
*locked = 0;
/*
* We should do the same as VM_FAULT_RETRY, but let's not
* return -EBUSY since that's not reflecting the reality of
* what has happened - we've just fully completed a page
* fault, with the mmap lock released. Use -EAGAIN to show
* that we want to take the mmap lock _again_.
*/
return -EAGAIN;
}
if (ret & VM_FAULT_ERROR) {
int err = vm_fault_to_errno(ret, *flags);
if (err)
return err;
BUG();
}
if (ret & VM_FAULT_RETRY) {
if (locked && !(fault_flags & FAULT_FLAG_RETRY_NOWAIT))
*locked = 0;
return -EBUSY;
}
return 0;
}
static int check_vma_flags(struct vm_area_struct *vma, unsigned long gup_flags)
{
vm_flags_t vm_flags = vma->vm_flags;
int write = (gup_flags & FOLL_WRITE);
int foreign = (gup_flags & FOLL_REMOTE);
if (vm_flags & (VM_IO | VM_PFNMAP))
return -EFAULT;
if (gup_flags & FOLL_ANON && !vma_is_anonymous(vma))
return -EFAULT;
if ((gup_flags & FOLL_LONGTERM) && vma_is_fsdax(vma))
return -EOPNOTSUPP;
if (vma_is_secretmem(vma))
return -EFAULT;
if (write) {
if (!(vm_flags & VM_WRITE)) {
if (!(gup_flags & FOLL_FORCE))
return -EFAULT;
/*
* We used to let the write,force case do COW in a
* VM_MAYWRITE VM_SHARED !VM_WRITE vma, so ptrace could
* set a breakpoint in a read-only mapping of an
* executable, without corrupting the file (yet only
* when that file had been opened for writing!).
* Anon pages in shared mappings are surprising: now
* just reject it.
*/
if (!is_cow_mapping(vm_flags))
return -EFAULT;
}
} else if (!(vm_flags & VM_READ)) {
if (!(gup_flags & FOLL_FORCE))
return -EFAULT;
/*
* Is there actually any vma we can reach here which does not
* have VM_MAYREAD set?
*/
if (!(vm_flags & VM_MAYREAD))
return -EFAULT;
}
/*
* gups are always data accesses, not instruction
* fetches, so execute=false here
*/
if (!arch_vma_access_permitted(vma, write, false, foreign))
return -EFAULT;
return 0;
}
/**
* __get_user_pages() - pin user pages in memory
* @mm: mm_struct of target mm
* @start: starting user address
* @nr_pages: number of pages from start to pin
* @gup_flags: flags modifying pin behaviour
* @pages: array that receives pointers to the pages pinned.
* Should be at least nr_pages long. Or NULL, if caller
* only intends to ensure the pages are faulted in.
* @vmas: array of pointers to vmas corresponding to each page.
* Or NULL if the caller does not require them.
* @locked: whether we're still with the mmap_lock held
*
* Returns either number of pages pinned (which may be less than the
* number requested), or an error. Details about the return value:
*
* -- If nr_pages is 0, returns 0.
* -- If nr_pages is >0, but no pages were pinned, returns -errno.
* -- If nr_pages is >0, and some pages were pinned, returns the number of
* pages pinned. Again, this may be less than nr_pages.
* -- 0 return value is possible when the fault would need to be retried.
*
* The caller is responsible for releasing returned @pages, via put_page().
*
* @vmas are valid only as long as mmap_lock is held.
*
* Must be called with mmap_lock held. It may be released. See below.
*
* __get_user_pages walks a process's page tables and takes a reference to
* each struct page that each user address corresponds to at a given
* instant. That is, it takes the page that would be accessed if a user
* thread accesses the given user virtual address at that instant.
*
* This does not guarantee that the page exists in the user mappings when
* __get_user_pages returns, and there may even be a completely different
* page there in some cases (eg. if mmapped pagecache has been invalidated
* and subsequently re faulted). However it does guarantee that the page
* won't be freed completely. And mostly callers simply care that the page
* contains data that was valid *at some point in time*. Typically, an IO
* or similar operation cannot guarantee anything stronger anyway because
* locks can't be held over the syscall boundary.
*
* If @gup_flags & FOLL_WRITE == 0, the page must not be written to. If
* the page is written to, set_page_dirty (or set_page_dirty_lock, as
* appropriate) must be called after the page is finished with, and
* before put_page is called.
*
* If @locked != NULL, *@locked will be set to 0 when mmap_lock is
* released by an up_read(). That can happen if @gup_flags does not
* have FOLL_NOWAIT.
*
* A caller using such a combination of @locked and @gup_flags
* must therefore hold the mmap_lock for reading only, and recognize
* when it's been released. Otherwise, it must be held for either
* reading or writing and will not be released.
*
* In most cases, get_user_pages or get_user_pages_fast should be used
* instead of __get_user_pages. __get_user_pages should be used only if
* you need some special @gup_flags.
*/
static long __get_user_pages(struct mm_struct *mm,
unsigned long start, unsigned long nr_pages,
unsigned int gup_flags, struct page **pages,
struct vm_area_struct **vmas, int *locked)
{
long ret = 0, i = 0;
struct vm_area_struct *vma = NULL;
struct follow_page_context ctx = { NULL };
if (!nr_pages)
return 0;
start = untagged_addr(start);
VM_BUG_ON(!!pages != !!(gup_flags & (FOLL_GET | FOLL_PIN)));
do {
struct page *page;
unsigned int foll_flags = gup_flags;
unsigned int page_increm;
/* first iteration or cross vma bound */
if (!vma || start >= vma->vm_end) {
vma = find_extend_vma(mm, start);
if (!vma && in_gate_area(mm, start)) {
ret = get_gate_page(mm, start & PAGE_MASK,
gup_flags, &vma,
pages ? &pages[i] : NULL);
if (ret)
goto out;
ctx.page_mask = 0;
goto next_page;
}
if (!vma) {
ret = -EFAULT;
goto out;
}
ret = check_vma_flags(vma, gup_flags);
if (ret)
goto out;
if (is_vm_hugetlb_page(vma)) {
i = follow_hugetlb_page(mm, vma, pages, vmas,
&start, &nr_pages, i,
gup_flags, locked);
if (locked && *locked == 0) {
/*
* We've got a VM_FAULT_RETRY
* and we've lost mmap_lock.
* We must stop here.
*/
BUG_ON(gup_flags & FOLL_NOWAIT);
goto out;
}
continue;
}
}
retry:
/*
* If we have a pending SIGKILL, don't keep faulting pages and
* potentially allocating memory.
*/
if (fatal_signal_pending(current)) {
ret = -EINTR;
goto out;
}
cond_resched();
page = follow_page_mask(vma, start, foll_flags, &ctx);
if (!page || PTR_ERR(page) == -EMLINK) {
ret = faultin_page(vma, start, &foll_flags,
PTR_ERR(page) == -EMLINK, locked);
switch (ret) {
case 0:
goto retry;
case -EBUSY:
case -EAGAIN:
ret = 0;
fallthrough;
case -EFAULT:
case -ENOMEM:
case -EHWPOISON:
goto out;
}
BUG();
} else if (PTR_ERR(page) == -EEXIST) {
/*
* Proper page table entry exists, but no corresponding
* struct page. If the caller expects **pages to be
* filled in, bail out now, because that can't be done
* for this page.
*/
if (pages) {
ret = PTR_ERR(page);
goto out;
}
goto next_page;
} else if (IS_ERR(page)) {
ret = PTR_ERR(page);
goto out;
}
if (pages) {
pages[i] = page;
flush_anon_page(vma, page, start);
flush_dcache_page(page);
ctx.page_mask = 0;
}
next_page:
if (vmas) {
vmas[i] = vma;
ctx.page_mask = 0;
}
page_increm = 1 + (~(start >> PAGE_SHIFT) & ctx.page_mask);
if (page_increm > nr_pages)
page_increm = nr_pages;
i += page_increm;
start += page_increm * PAGE_SIZE;
nr_pages -= page_increm;
} while (nr_pages);
out:
if (ctx.pgmap)
put_dev_pagemap(ctx.pgmap);
return i ? i : ret;
}
static bool vma_permits_fault(struct vm_area_struct *vma,
unsigned int fault_flags)
{
bool write = !!(fault_flags & FAULT_FLAG_WRITE);
bool foreign = !!(fault_flags & FAULT_FLAG_REMOTE);
vm_flags_t vm_flags = write ? VM_WRITE : VM_READ;
if (!(vm_flags & vma->vm_flags))
return false;
/*
* The architecture might have a hardware protection
* mechanism other than read/write that can deny access.
*
* gup always represents data access, not instruction
* fetches, so execute=false here:
*/
if (!arch_vma_access_permitted(vma, write, false, foreign))
return false;
return true;
}
/**
* fixup_user_fault() - manually resolve a user page fault
* @mm: mm_struct of target mm
* @address: user address
* @fault_flags:flags to pass down to handle_mm_fault()
* @unlocked: did we unlock the mmap_lock while retrying, maybe NULL if caller
* does not allow retry. If NULL, the caller must guarantee
* that fault_flags does not contain FAULT_FLAG_ALLOW_RETRY.
*
* This is meant to be called in the specific scenario where for locking reasons
* we try to access user memory in atomic context (within a pagefault_disable()
* section), this returns -EFAULT, and we want to resolve the user fault before
* trying again.
*
* Typically this is meant to be used by the futex code.
*
* The main difference with get_user_pages() is that this function will
* unconditionally call handle_mm_fault() which will in turn perform all the
* necessary SW fixup of the dirty and young bits in the PTE, while
* get_user_pages() only guarantees to update these in the struct page.
*
* This is important for some architectures where those bits also gate the
* access permission to the page because they are maintained in software. On
* such architectures, gup() will not be enough to make a subsequent access
* succeed.
*
* This function will not return with an unlocked mmap_lock. So it has not the
* same semantics wrt the @mm->mmap_lock as does filemap_fault().
*/
int fixup_user_fault(struct mm_struct *mm,
unsigned long address, unsigned int fault_flags,
bool *unlocked)
{
struct vm_area_struct *vma;
vm_fault_t ret;
address = untagged_addr(address);
if (unlocked)
fault_flags |= FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
retry:
vma = find_extend_vma(mm, address);
if (!vma || address < vma->vm_start)
return -EFAULT;
if (!vma_permits_fault(vma, fault_flags))
return -EFAULT;
if ((fault_flags & FAULT_FLAG_KILLABLE) &&
fatal_signal_pending(current))
return -EINTR;
ret = handle_mm_fault(vma, address, fault_flags, NULL);
if (ret & VM_FAULT_COMPLETED) {
/*
* NOTE: it's a pity that we need to retake the lock here
* to pair with the unlock() in the callers. Ideally we
* could tell the callers so they do not need to unlock.
*/
mmap_read_lock(mm);
*unlocked = true;
return 0;
}
if (ret & VM_FAULT_ERROR) {
int err = vm_fault_to_errno(ret, 0);
if (err)
return err;
BUG();
}
if (ret & VM_FAULT_RETRY) {
mmap_read_lock(mm);
*unlocked = true;
fault_flags |= FAULT_FLAG_TRIED;
goto retry;
}
return 0;
}
EXPORT_SYMBOL_GPL(fixup_user_fault);
/*
* Please note that this function, unlike __get_user_pages will not
* return 0 for nr_pages > 0 without FOLL_NOWAIT
*/
static __always_inline long __get_user_pages_locked(struct mm_struct *mm,
unsigned long start,
unsigned long nr_pages,
struct page **pages,
struct vm_area_struct **vmas,
int *locked,
unsigned int flags)
{
long ret, pages_done;
bool lock_dropped;
if (locked) {
/* if VM_FAULT_RETRY can be returned, vmas become invalid */
BUG_ON(vmas);
/* check caller initialized locked */
BUG_ON(*locked != 1);
}
if (flags & FOLL_PIN)
mm_set_has_pinned_flag(&mm->flags);
/*
* FOLL_PIN and FOLL_GET are mutually exclusive. Traditional behavior
* is to set FOLL_GET if the caller wants pages[] filled in (but has
* carelessly failed to specify FOLL_GET), so keep doing that, but only
* for FOLL_GET, not for the newer FOLL_PIN.
*
* FOLL_PIN always expects pages to be non-null, but no need to assert
* that here, as any failures will be obvious enough.
*/
if (pages && !(flags & FOLL_PIN))
flags |= FOLL_GET;
pages_done = 0;
lock_dropped = false;
for (;;) {
ret = __get_user_pages(mm, start, nr_pages, flags, pages,
vmas, locked);
if (!locked)
/* VM_FAULT_RETRY couldn't trigger, bypass */
return ret;
/* VM_FAULT_RETRY or VM_FAULT_COMPLETED cannot return errors */
if (!*locked) {
BUG_ON(ret < 0);
BUG_ON(ret >= nr_pages);
}
if (ret > 0) {
nr_pages -= ret;
pages_done += ret;
if (!nr_pages)
break;
}
if (*locked) {
/*
* VM_FAULT_RETRY didn't trigger or it was a
* FOLL_NOWAIT.
*/
if (!pages_done)
pages_done = ret;
break;
}
/*
* VM_FAULT_RETRY triggered, so seek to the faulting offset.
* For the prefault case (!pages) we only update counts.
*/
if (likely(pages))
pages += ret;
start += ret << PAGE_SHIFT;
lock_dropped = true;
retry:
/*
* Repeat on the address that fired VM_FAULT_RETRY
* with both FAULT_FLAG_ALLOW_RETRY and
* FAULT_FLAG_TRIED. Note that GUP can be interrupted
* by fatal signals, so we need to check it before we
* start trying again otherwise it can loop forever.
*/
if (fatal_signal_pending(current)) {
if (!pages_done)
pages_done = -EINTR;
break;
}
ret = mmap_read_lock_killable(mm);
if (ret) {
BUG_ON(ret > 0);
if (!pages_done)
pages_done = ret;
break;
}
*locked = 1;
ret = __get_user_pages(mm, start, 1, flags | FOLL_TRIED,
pages, NULL, locked);
if (!*locked) {
/* Continue to retry until we succeeded */
BUG_ON(ret != 0);
goto retry;
}
if (ret != 1) {
BUG_ON(ret > 1);
if (!pages_done)
pages_done = ret;
break;
}
nr_pages--;
pages_done++;
if (!nr_pages)
break;
if (likely(pages))
pages++;
start += PAGE_SIZE;
}
if (lock_dropped && *locked) {
/*
* We must let the caller know we temporarily dropped the lock
* and so the critical section protected by it was lost.
*/
mmap_read_unlock(mm);
*locked = 0;
}
return pages_done;
}
/**
* populate_vma_page_range() - populate a range of pages in the vma.
* @vma: target vma
* @start: start address
* @end: end address
* @locked: whether the mmap_lock is still held
*
* This takes care of mlocking the pages too if VM_LOCKED is set.
*
* Return either number of pages pinned in the vma, or a negative error
* code on error.
*
* vma->vm_mm->mmap_lock must be held.
*
* If @locked is NULL, it may be held for read or write and will
* be unperturbed.
*
* If @locked is non-NULL, it must held for read only and may be
* released. If it's released, *@locked will be set to 0.
*/
long populate_vma_page_range(struct vm_area_struct *vma,
unsigned long start, unsigned long end, int *locked)
{
struct mm_struct *mm = vma->vm_mm;
unsigned long nr_pages = (end - start) / PAGE_SIZE;
int gup_flags;
long ret;
VM_BUG_ON(!PAGE_ALIGNED(start));
VM_BUG_ON(!PAGE_ALIGNED(end));
VM_BUG_ON_VMA(start < vma->vm_start, vma);
VM_BUG_ON_VMA(end > vma->vm_end, vma);
mmap_assert_locked(mm);
/*
* Rightly or wrongly, the VM_LOCKONFAULT case has never used
* faultin_page() to break COW, so it has no work to do here.
*/
if (vma->vm_flags & VM_LOCKONFAULT)
return nr_pages;
gup_flags = FOLL_TOUCH;
/*
* We want to touch writable mappings with a write fault in order
* to break COW, except for shared mappings because these don't COW
* and we would not want to dirty them for nothing.
*/
if ((vma->vm_flags & (VM_WRITE | VM_SHARED)) == VM_WRITE)
gup_flags |= FOLL_WRITE;
/*
* We want mlock to succeed for regions that have any permissions
* other than PROT_NONE.
*/
if (vma_is_accessible(vma))
gup_flags |= FOLL_FORCE;
/*
* We made sure addr is within a VMA, so the following will
* not result in a stack expansion that recurses back here.
*/
ret = __get_user_pages(mm, start, nr_pages, gup_flags,
NULL, NULL, locked);
lru_add_drain();
return ret;
}
/*
* faultin_vma_page_range() - populate (prefault) page tables inside the
* given VMA range readable/writable
*
* This takes care of mlocking the pages, too, if VM_LOCKED is set.
*
* @vma: target vma
* @start: start address
* @end: end address
* @write: whether to prefault readable or writable
* @locked: whether the mmap_lock is still held
*
* Returns either number of processed pages in the vma, or a negative error
* code on error (see __get_user_pages()).
*
* vma->vm_mm->mmap_lock must be held. The range must be page-aligned and
* covered by the VMA.
*
* If @locked is NULL, it may be held for read or write and will be unperturbed.
*
* If @locked is non-NULL, it must held for read only and may be released. If
* it's released, *@locked will be set to 0.
*/
long faultin_vma_page_range(struct vm_area_struct *vma, unsigned long start,
unsigned long end, bool write, int *locked)
{
struct mm_struct *mm = vma->vm_mm;
unsigned long nr_pages = (end - start) / PAGE_SIZE;
int gup_flags;
long ret;
VM_BUG_ON(!PAGE_ALIGNED(start));
VM_BUG_ON(!PAGE_ALIGNED(end));
VM_BUG_ON_VMA(start < vma->vm_start, vma);
VM_BUG_ON_VMA(end > vma->vm_end, vma);
mmap_assert_locked(mm);
/*
* FOLL_TOUCH: Mark page accessed and thereby young; will also mark
* the page dirty with FOLL_WRITE -- which doesn't make a
* difference with !FOLL_FORCE, because the page is writable
* in the page table.
* FOLL_HWPOISON: Return -EHWPOISON instead of -EFAULT when we hit
* a poisoned page.
* !FOLL_FORCE: Require proper access permissions.
*/
gup_flags = FOLL_TOUCH | FOLL_HWPOISON;
if (write)
gup_flags |= FOLL_WRITE;
/*
* We want to report -EINVAL instead of -EFAULT for any permission
* problems or incompatible mappings.
*/
if (check_vma_flags(vma, gup_flags))
return -EINVAL;
ret = __get_user_pages(mm, start, nr_pages, gup_flags,
NULL, NULL, locked);
lru_add_drain();
return ret;
}
/*
* __mm_populate - populate and/or mlock pages within a range of address space.
*
* This is used to implement mlock() and the MAP_POPULATE / MAP_LOCKED mmap
* flags. VMAs must be already marked with the desired vm_flags, and
* mmap_lock must not be held.
*/
int __mm_populate(unsigned long start, unsigned long len, int ignore_errors)
{
struct mm_struct *mm = current->mm;
unsigned long end, nstart, nend;
struct vm_area_struct *vma = NULL;
int locked = 0;
long ret = 0;
end = start + len;
for (nstart = start; nstart < end; nstart = nend) {
/*
* We want to fault in pages for [nstart; end) address range.
* Find first corresponding VMA.
*/
if (!locked) {
locked = 1;
mmap_read_lock(mm);
vma = find_vma_intersection(mm, nstart, end);
} else if (nstart >= vma->vm_end)
vma = find_vma_intersection(mm, vma->vm_end, end);
if (!vma)
break;
/*
* Set [nstart; nend) to intersection of desired address
* range with the first VMA. Also, skip undesirable VMA types.
*/
nend = min(end, vma->vm_end);
if (vma->vm_flags & (VM_IO | VM_PFNMAP))
continue;
if (nstart < vma->vm_start)
nstart = vma->vm_start;
/*
* Now fault in a range of pages. populate_vma_page_range()
* double checks the vma flags, so that it won't mlock pages
* if the vma was already munlocked.
*/
ret = populate_vma_page_range(vma, nstart, nend, &locked);
if (ret < 0) {
if (ignore_errors) {
ret = 0;
continue; /* continue at next VMA */
}
break;
}
nend = nstart + ret * PAGE_SIZE;
ret = 0;
}
if (locked)
mmap_read_unlock(mm);
return ret; /* 0 or negative error code */
}
#else /* CONFIG_MMU */
static long __get_user_pages_locked(struct mm_struct *mm, unsigned long start,
unsigned long nr_pages, struct page **pages,
struct vm_area_struct **vmas, int *locked,
unsigned int foll_flags)
{
struct vm_area_struct *vma;
unsigned long vm_flags;
long i;
/* calculate required read or write permissions.
* If FOLL_FORCE is set, we only require the "MAY" flags.
*/
vm_flags = (foll_flags & FOLL_WRITE) ?
(VM_WRITE | VM_MAYWRITE) : (VM_READ | VM_MAYREAD);
vm_flags &= (foll_flags & FOLL_FORCE) ?
(VM_MAYREAD | VM_MAYWRITE) : (VM_READ | VM_WRITE);
for (i = 0; i < nr_pages; i++) {
vma = find_vma(mm, start);
if (!vma)
goto finish_or_fault;
/* protect what we can, including chardevs */
if ((vma->vm_flags & (VM_IO | VM_PFNMAP)) ||
!(vm_flags & vma->vm_flags))
goto finish_or_fault;
if (pages) {
pages[i] = virt_to_page((void *)start);
if (pages[i])
get_page(pages[i]);
}
if (vmas)
vmas[i] = vma;
start = (start + PAGE_SIZE) & PAGE_MASK;
}
return i;
finish_or_fault:
return i ? : -EFAULT;
}
#endif /* !CONFIG_MMU */
/**
* fault_in_writeable - fault in userspace address range for writing
* @uaddr: start of address range
* @size: size of address range
*
* Returns the number of bytes not faulted in (like copy_to_user() and
* copy_from_user()).
*/
size_t fault_in_writeable(char __user *uaddr, size_t size)
{
char __user *start = uaddr, *end;
if (unlikely(size == 0))
return 0;
if (!user_write_access_begin(uaddr, size))
return size;
if (!PAGE_ALIGNED(uaddr)) {
unsafe_put_user(0, uaddr, out);
uaddr = (char __user *)PAGE_ALIGN((unsigned long)uaddr);
}
end = (char __user *)PAGE_ALIGN((unsigned long)start + size);
if (unlikely(end < start))
end = NULL;
while (uaddr != end) {
unsafe_put_user(0, uaddr, out);
uaddr += PAGE_SIZE;
}
out:
user_write_access_end();
if (size > uaddr - start)
return size - (uaddr - start);
return 0;
}
EXPORT_SYMBOL(fault_in_writeable);
/**
* fault_in_subpage_writeable - fault in an address range for writing
* @uaddr: start of address range
* @size: size of address range
*
* Fault in a user address range for writing while checking for permissions at
* sub-page granularity (e.g. arm64 MTE). This function should be used when
* the caller cannot guarantee forward progress of a copy_to_user() loop.
*
* Returns the number of bytes not faulted in (like copy_to_user() and
* copy_from_user()).
*/
size_t fault_in_subpage_writeable(char __user *uaddr, size_t size)
{
size_t faulted_in;
/*
* Attempt faulting in at page granularity first for page table
* permission checking. The arch-specific probe_subpage_writeable()
* functions may not check for this.
*/
faulted_in = size - fault_in_writeable(uaddr, size);
if (faulted_in)
faulted_in -= probe_subpage_writeable(uaddr, faulted_in);
return size - faulted_in;
}
EXPORT_SYMBOL(fault_in_subpage_writeable);
/*
* fault_in_safe_writeable - fault in an address range for writing
* @uaddr: start of address range
* @size: length of address range
*
* Faults in an address range for writing. This is primarily useful when we
* already know that some or all of the pages in the address range aren't in
* memory.
*
* Unlike fault_in_writeable(), this function is non-destructive.
*
* Note that we don't pin or otherwise hold the pages referenced that we fault
* in. There's no guarantee that they'll stay in memory for any duration of
* time.
*
* Returns the number of bytes not faulted in, like copy_to_user() and
* copy_from_user().
*/
size_t fault_in_safe_writeable(const char __user *uaddr, size_t size)
{
unsigned long start = (unsigned long)uaddr, end;
struct mm_struct *mm = current->mm;
bool unlocked = false;
if (unlikely(size == 0))
return 0;
end = PAGE_ALIGN(start + size);
if (end < start)
end = 0;
mmap_read_lock(mm);
do {
if (fixup_user_fault(mm, start, FAULT_FLAG_WRITE, &unlocked))
break;
start = (start + PAGE_SIZE) & PAGE_MASK;
} while (start != end);
mmap_read_unlock(mm);
if (size > (unsigned long)uaddr - start)
return size - ((unsigned long)uaddr - start);
return 0;
}
EXPORT_SYMBOL(fault_in_safe_writeable);
/**
* fault_in_readable - fault in userspace address range for reading
* @uaddr: start of user address range
* @size: size of user address range
*
* Returns the number of bytes not faulted in (like copy_to_user() and
* copy_from_user()).
*/
size_t fault_in_readable(const char __user *uaddr, size_t size)
{
const char __user *start = uaddr, *end;
volatile char c;
if (unlikely(size == 0))
return 0;
if (!user_read_access_begin(uaddr, size))
return size;
if (!PAGE_ALIGNED(uaddr)) {
unsafe_get_user(c, uaddr, out);
uaddr = (const char __user *)PAGE_ALIGN((unsigned long)uaddr);
}
end = (const char __user *)PAGE_ALIGN((unsigned long)start + size);
if (unlikely(end < start))
end = NULL;
while (uaddr != end) {
unsafe_get_user(c, uaddr, out);
uaddr += PAGE_SIZE;
}
out:
user_read_access_end();
(void)c;
if (size > uaddr - start)
return size - (uaddr - start);
return 0;
}
EXPORT_SYMBOL(fault_in_readable);
/**
* get_dump_page() - pin user page in memory while writing it to core dump
* @addr: user address
*
* Returns struct page pointer of user page pinned for dump,
* to be freed afterwards by put_page().
*
* Returns NULL on any kind of failure - a hole must then be inserted into
* the corefile, to preserve alignment with its headers; and also returns
* NULL wherever the ZERO_PAGE, or an anonymous pte_none, has been found -
* allowing a hole to be left in the corefile to save disk space.
*
* Called without mmap_lock (takes and releases the mmap_lock by itself).
*/
#ifdef CONFIG_ELF_CORE
struct page *get_dump_page(unsigned long addr)
{
struct mm_struct *mm = current->mm;
struct page *page;
int locked = 1;
int ret;
if (mmap_read_lock_killable(mm))
return NULL;
ret = __get_user_pages_locked(mm, addr, 1, &page, NULL, &locked,
FOLL_FORCE | FOLL_DUMP | FOLL_GET);
if (locked)
mmap_read_unlock(mm);
return (ret == 1) ? page : NULL;
}
#endif /* CONFIG_ELF_CORE */
#ifdef CONFIG_MIGRATION
/*
* Returns the number of collected pages. Return value is always >= 0.
*/
static unsigned long collect_longterm_unpinnable_pages(
struct list_head *movable_page_list,
unsigned long nr_pages,
struct page **pages)
{
unsigned long i, collected = 0;
struct folio *prev_folio = NULL;
bool drain_allow = true;
for (i = 0; i < nr_pages; i++) {
struct folio *folio = page_folio(pages[i]);
if (folio == prev_folio)
continue;
prev_folio = folio;
if (folio_is_longterm_pinnable(folio))
continue;
collected++;
if (folio_is_device_coherent(folio))
continue;
if (folio_test_hugetlb(folio)) {
isolate_hugetlb(&folio->page, movable_page_list);
continue;
}
if (!folio_test_lru(folio) && drain_allow) {
lru_add_drain_all();
drain_allow = false;
}
if (!folio_isolate_lru(folio))
continue;
list_add_tail(&folio->lru, movable_page_list);
node_stat_mod_folio(folio,
NR_ISOLATED_ANON + folio_is_file_lru(folio),
folio_nr_pages(folio));
}
return collected;
}
/*
* Unpins all pages and migrates device coherent pages and movable_page_list.
* Returns -EAGAIN if all pages were successfully migrated or -errno for failure
* (or partial success).
*/
static int migrate_longterm_unpinnable_pages(
struct list_head *movable_page_list,
unsigned long nr_pages,
struct page **pages)
{
int ret;
unsigned long i;
for (i = 0; i < nr_pages; i++) {
struct folio *folio = page_folio(pages[i]);
if (folio_is_device_coherent(folio)) {
/*
* Migration will fail if the page is pinned, so convert
* the pin on the source page to a normal reference.
*/
pages[i] = NULL;
folio_get(folio);
gup_put_folio(folio, 1, FOLL_PIN);
if (migrate_device_coherent_page(&folio->page)) {
ret = -EBUSY;
goto err;
}
continue;
}
/*
* We can't migrate pages with unexpected references, so drop
* the reference obtained by __get_user_pages_locked().
* Migrating pages have been added to movable_page_list after
* calling folio_isolate_lru() which takes a reference so the
* page won't be freed if it's migrating.
*/
unpin_user_page(pages[i]);
pages[i] = NULL;
}
if (!list_empty(movable_page_list)) {
struct migration_target_control mtc = {
.nid = NUMA_NO_NODE,
.gfp_mask = GFP_USER | __GFP_NOWARN,
};
if (migrate_pages(movable_page_list, alloc_migration_target,
NULL, (unsigned long)&mtc, MIGRATE_SYNC,
MR_LONGTERM_PIN, NULL)) {
ret = -ENOMEM;
goto err;
}
}
putback_movable_pages(movable_page_list);
return -EAGAIN;
err:
for (i = 0; i < nr_pages; i++)
if (pages[i])
unpin_user_page(pages[i]);
putback_movable_pages(movable_page_list);
return ret;
}
/*
* Check whether all pages are *allowed* to be pinned. Rather confusingly, all
* pages in the range are required to be pinned via FOLL_PIN, before calling
* this routine.
*
* If any pages in the range are not allowed to be pinned, then this routine
* will migrate those pages away, unpin all the pages in the range and return
* -EAGAIN. The caller should re-pin the entire range with FOLL_PIN and then
* call this routine again.
*
* If an error other than -EAGAIN occurs, this indicates a migration failure.
* The caller should give up, and propagate the error back up the call stack.
*
* If everything is OK and all pages in the range are allowed to be pinned, then
* this routine leaves all pages pinned and returns zero for success.
*/
static long check_and_migrate_movable_pages(unsigned long nr_pages,
struct page **pages)
{
unsigned long collected;
LIST_HEAD(movable_page_list);
collected = collect_longterm_unpinnable_pages(&movable_page_list,
nr_pages, pages);
if (!collected)
return 0;
return migrate_longterm_unpinnable_pages(&movable_page_list, nr_pages,
pages);
}
#else
static long check_and_migrate_movable_pages(unsigned long nr_pages,
struct page **pages)
{
return 0;
}
#endif /* CONFIG_MIGRATION */
/*
* __gup_longterm_locked() is a wrapper for __get_user_pages_locked which
* allows us to process the FOLL_LONGTERM flag.
*/
static long __gup_longterm_locked(struct mm_struct *mm,
unsigned long start,
unsigned long nr_pages,
struct page **pages,
struct vm_area_struct **vmas,
int *locked,
unsigned int gup_flags)
{
bool must_unlock = false;
unsigned int flags;
long rc, nr_pinned_pages;
if (locked && WARN_ON_ONCE(!*locked))
return -EINVAL;
if (!(gup_flags & FOLL_LONGTERM))
return __get_user_pages_locked(mm, start, nr_pages, pages, vmas,
locked, gup_flags);
/*
* If we get to this point then FOLL_LONGTERM is set, and FOLL_LONGTERM
* implies FOLL_PIN (although the reverse is not true). Therefore it is
* correct to unconditionally call check_and_migrate_movable_pages()
* which assumes pages have been pinned via FOLL_PIN.
*
* Enforce the above reasoning by asserting that FOLL_PIN is set.
*/
if (WARN_ON(!(gup_flags & FOLL_PIN)))
return -EINVAL;
flags = memalloc_pin_save();
do {
if (locked && !*locked) {
mmap_read_lock(mm);
must_unlock = true;
*locked = 1;
}
nr_pinned_pages = __get_user_pages_locked(mm, start, nr_pages,
pages, vmas, locked,
gup_flags);
if (nr_pinned_pages <= 0) {
rc = nr_pinned_pages;
break;
}
rc = check_and_migrate_movable_pages(nr_pinned_pages, pages);
} while (rc == -EAGAIN);
memalloc_pin_restore(flags);
if (locked && *locked && must_unlock) {
mmap_read_unlock(mm);
*locked = 0;
}
return rc ? rc : nr_pinned_pages;
}
static bool is_valid_gup_flags(unsigned int gup_flags)
{
/*
* FOLL_PIN must only be set internally by the pin_user_pages*() APIs,
* never directly by the caller, so enforce that with an assertion:
*/
if (WARN_ON_ONCE(gup_flags & FOLL_PIN))
return false;
/*
* FOLL_PIN is a prerequisite to FOLL_LONGTERM. Another way of saying
* that is, FOLL_LONGTERM is a specific case, more restrictive case of
* FOLL_PIN.
*/
if (WARN_ON_ONCE(gup_flags & FOLL_LONGTERM))
return false;
return true;
}
#ifdef CONFIG_MMU
/**
* get_user_pages_remote() - pin user pages in memory
* @mm: mm_struct of target mm
* @start: starting user address
* @nr_pages: number of pages from start to pin
* @gup_flags: flags modifying lookup behaviour
* @pages: array that receives pointers to the pages pinned.
* Should be at least nr_pages long. Or NULL, if caller
* only intends to ensure the pages are faulted in.
* @vmas: array of pointers to vmas corresponding to each page.
* Or NULL if the caller does not require them.
* @locked: pointer to lock flag indicating whether lock is held and
* subsequently whether VM_FAULT_RETRY functionality can be
* utilised. Lock must initially be held.
*
* Returns either number of pages pinned (which may be less than the
* number requested), or an error. Details about the return value:
*
* -- If nr_pages is 0, returns 0.
* -- If nr_pages is >0, but no pages were pinned, returns -errno.
* -- If nr_pages is >0, and some pages were pinned, returns the number of
* pages pinned. Again, this may be less than nr_pages.
*
* The caller is responsible for releasing returned @pages, via put_page().
*
* @vmas are valid only as long as mmap_lock is held.
*
* Must be called with mmap_lock held for read or write.
*
* get_user_pages_remote walks a process's page tables and takes a reference
* to each struct page that each user address corresponds to at a given
* instant. That is, it takes the page that would be accessed if a user
* thread accesses the given user virtual address at that instant.
*
* This does not guarantee that the page exists in the user mappings when
* get_user_pages_remote returns, and there may even be a completely different
* page there in some cases (eg. if mmapped pagecache has been invalidated
* and subsequently re faulted). However it does guarantee that the page
* won't be freed completely. And mostly callers simply care that the page
* contains data that was valid *at some point in time*. Typically, an IO
* or similar operation cannot guarantee anything stronger anyway because
* locks can't be held over the syscall boundary.
*
* If gup_flags & FOLL_WRITE == 0, the page must not be written to. If the page
* is written to, set_page_dirty (or set_page_dirty_lock, as appropriate) must
* be called after the page is finished with, and before put_page is called.
*
* get_user_pages_remote is typically used for fewer-copy IO operations,
* to get a handle on the memory by some means other than accesses
* via the user virtual addresses. The pages may be submitted for
* DMA to devices or accessed via their kernel linear mapping (via the
* kmap APIs). Care should be taken to use the correct cache flushing APIs.
*
* See also get_user_pages_fast, for performance critical applications.
*
* get_user_pages_remote should be phased out in favor of
* get_user_pages_locked|unlocked or get_user_pages_fast. Nothing
* should use get_user_pages_remote because it cannot pass
* FAULT_FLAG_ALLOW_RETRY to handle_mm_fault.
*/
long get_user_pages_remote(struct mm_struct *mm,
unsigned long start, unsigned long nr_pages,
unsigned int gup_flags, struct page **pages,
struct vm_area_struct **vmas, int *locked)
{
if (!is_valid_gup_flags(gup_flags))
return -EINVAL;
return __gup_longterm_locked(mm, start, nr_pages, pages, vmas, locked,
gup_flags | FOLL_TOUCH | FOLL_REMOTE);
}
EXPORT_SYMBOL(get_user_pages_remote);
#else /* CONFIG_MMU */
long get_user_pages_remote(struct mm_struct *mm,
unsigned long start, unsigned long nr_pages,
unsigned int gup_flags, struct page **pages,
struct vm_area_struct **vmas, int *locked)
{
return 0;
}
#endif /* !CONFIG_MMU */
/**
* get_user_pages() - pin user pages in memory
* @start: starting user address
* @nr_pages: number of pages from start to pin
* @gup_flags: flags modifying lookup behaviour
* @pages: array that receives pointers to the pages pinned.
* Should be at least nr_pages long. Or NULL, if caller
* only intends to ensure the pages are faulted in.
* @vmas: array of pointers to vmas corresponding to each page.
* Or NULL if the caller does not require them.
*
* This is the same as get_user_pages_remote(), just with a less-flexible
* calling convention where we assume that the mm being operated on belongs to
* the current task, and doesn't allow passing of a locked parameter. We also
* obviously don't pass FOLL_REMOTE in here.
*/
long get_user_pages(unsigned long start, unsigned long nr_pages,
unsigned int gup_flags, struct page **pages,
struct vm_area_struct **vmas)
{
if (!is_valid_gup_flags(gup_flags))
return -EINVAL;
return __gup_longterm_locked(current->mm, start, nr_pages,
pages, vmas, NULL, gup_flags | FOLL_TOUCH);
}
EXPORT_SYMBOL(get_user_pages);
/*
* get_user_pages_unlocked() is suitable to replace the form:
*
* mmap_read_lock(mm);
* get_user_pages(mm, ..., pages, NULL);
* mmap_read_unlock(mm);
*
* with:
*
* get_user_pages_unlocked(mm, ..., pages);
*
* It is functionally equivalent to get_user_pages_fast so
* get_user_pages_fast should be used instead if specific gup_flags
* (e.g. FOLL_FORCE) are not required.
*/
long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages,
struct page **pages, unsigned int gup_flags)
{
struct mm_struct *mm = current->mm;
int locked = 1;
long ret;
mmap_read_lock(mm);
ret = __gup_longterm_locked(mm, start, nr_pages, pages, NULL, &locked,
gup_flags | FOLL_TOUCH);
if (locked)
mmap_read_unlock(mm);
return ret;
}
EXPORT_SYMBOL(get_user_pages_unlocked);
/*
* Fast GUP
*
* get_user_pages_fast attempts to pin user pages by walking the page
* tables directly and avoids taking locks. Thus the walker needs to be
* protected from page table pages being freed from under it, and should
* block any THP splits.
*
* One way to achieve this is to have the walker disable interrupts, and
* rely on IPIs from the TLB flushing code blocking before the page table
* pages are freed. This is unsuitable for architectures that do not need
* to broadcast an IPI when invalidating TLBs.
*
* Another way to achieve this is to batch up page table containing pages
* belonging to more than one mm_user, then rcu_sched a callback to free those
* pages. Disabling interrupts will allow the fast_gup walker to both block
* the rcu_sched callback, and an IPI that we broadcast for splitting THPs
* (which is a relatively rare event). The code below adopts this strategy.
*
* Before activating this code, please be aware that the following assumptions
* are currently made:
*
* *) Either MMU_GATHER_RCU_TABLE_FREE is enabled, and tlb_remove_table() is used to
* free pages containing page tables or TLB flushing requires IPI broadcast.
*
* *) ptes can be read atomically by the architecture.
*
* *) access_ok is sufficient to validate userspace address ranges.
*
* The last two assumptions can be relaxed by the addition of helper functions.
*
* This code is based heavily on the PowerPC implementation by Nick Piggin.
*/
#ifdef CONFIG_HAVE_FAST_GUP
static void __maybe_unused undo_dev_pagemap(int *nr, int nr_start,
unsigned int flags,
struct page **pages)
{
while ((*nr) - nr_start) {
struct page *page = pages[--(*nr)];
ClearPageReferenced(page);
if (flags & FOLL_PIN)
unpin_user_page(page);
else
put_page(page);
}
}
#ifdef CONFIG_ARCH_HAS_PTE_SPECIAL
/*
* Fast-gup relies on pte change detection to avoid concurrent pgtable
* operations.
*
* To pin the page, fast-gup needs to do below in order:
* (1) pin the page (by prefetching pte), then (2) check pte not changed.
*
* For the rest of pgtable operations where pgtable updates can be racy
* with fast-gup, we need to do (1) clear pte, then (2) check whether page
* is pinned.
*
* Above will work for all pte-level operations, including THP split.
*
* For THP collapse, it's a bit more complicated because fast-gup may be
* walking a pgtable page that is being freed (pte is still valid but pmd
* can be cleared already). To avoid race in such condition, we need to
* also check pmd here to make sure pmd doesn't change (corresponds to
* pmdp_collapse_flush() in the THP collapse code path).
*/
static int gup_pte_range(pmd_t pmd, pmd_t *pmdp, unsigned long addr,
unsigned long end, unsigned int flags,
struct page **pages, int *nr)
{
struct dev_pagemap *pgmap = NULL;
int nr_start = *nr, ret = 0;
pte_t *ptep, *ptem;
ptem = ptep = pte_offset_map(&pmd, addr);
do {
pte_t pte = ptep_get_lockless(ptep);
struct page *page;
struct folio *folio;
if (pte_protnone(pte) && !gup_can_follow_protnone(flags))
goto pte_unmap;
if (!pte_access_permitted(pte, flags & FOLL_WRITE))
goto pte_unmap;
if (pte_devmap(pte)) {
if (unlikely(flags & FOLL_LONGTERM))
goto pte_unmap;
pgmap = get_dev_pagemap(pte_pfn(pte), pgmap);
if (unlikely(!pgmap)) {
undo_dev_pagemap(nr, nr_start, flags, pages);
goto pte_unmap;
}
} else if (pte_special(pte))
goto pte_unmap;
VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
page = pte_page(pte);
folio = try_grab_folio(page, 1, flags);
if (!folio)
goto pte_unmap;
if (unlikely(page_is_secretmem(page))) {
gup_put_folio(folio, 1, flags);
goto pte_unmap;
}
if (unlikely(pmd_val(pmd) != pmd_val(*pmdp)) ||
unlikely(pte_val(pte) != pte_val(*ptep))) {
gup_put_folio(folio, 1, flags);
goto pte_unmap;
}
if (!pte_write(pte) && gup_must_unshare(flags, page)) {
gup_put_folio(folio, 1, flags);
goto pte_unmap;
}
/*
* We need to make the page accessible if and only if we are
* going to access its content (the FOLL_PIN case). Please
* see Documentation/core-api/pin_user_pages.rst for
* details.
*/
if (flags & FOLL_PIN) {
ret = arch_make_page_accessible(page);
if (ret) {
gup_put_folio(folio, 1, flags);
goto pte_unmap;
}
}
folio_set_referenced(folio);
pages[*nr] = page;
(*nr)++;
} while (ptep++, addr += PAGE_SIZE, addr != end);
ret = 1;
pte_unmap:
if (pgmap)
put_dev_pagemap(pgmap);
pte_unmap(ptem);
return ret;
}
#else
/*
* If we can't determine whether or not a pte is special, then fail immediately
* for ptes. Note, we can still pin HugeTLB and THP as these are guaranteed not
* to be special.
*
* For a futex to be placed on a THP tail page, get_futex_key requires a
* get_user_pages_fast_only implementation that can pin pages. Thus it's still
* useful to have gup_huge_pmd even if we can't operate on ptes.
*/
static int gup_pte_range(pmd_t pmd, pmd_t *pmdp, unsigned long addr,
unsigned long end, unsigned int flags,
struct page **pages, int *nr)
{
return 0;
}
#endif /* CONFIG_ARCH_HAS_PTE_SPECIAL */
#if defined(CONFIG_ARCH_HAS_PTE_DEVMAP) && defined(CONFIG_TRANSPARENT_HUGEPAGE)
static int __gup_device_huge(unsigned long pfn, unsigned long addr,
unsigned long end, unsigned int flags,
struct page **pages, int *nr)
{
int nr_start = *nr;
struct dev_pagemap *pgmap = NULL;
do {
struct page *page = pfn_to_page(pfn);
pgmap = get_dev_pagemap(pfn, pgmap);
if (unlikely(!pgmap)) {
undo_dev_pagemap(nr, nr_start, flags, pages);
break;
}
SetPageReferenced(page);
pages[*nr] = page;
if (unlikely(!try_grab_page(page, flags))) {
undo_dev_pagemap(nr, nr_start, flags, pages);
break;
}
(*nr)++;
pfn++;
} while (addr += PAGE_SIZE, addr != end);
put_dev_pagemap(pgmap);
return addr == end;
}
static int __gup_device_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr,
unsigned long end, unsigned int flags,
struct page **pages, int *nr)
{
unsigned long fault_pfn;
int nr_start = *nr;
fault_pfn = pmd_pfn(orig) + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
if (!__gup_device_huge(fault_pfn, addr, end, flags, pages, nr))
return 0;
if (unlikely(pmd_val(orig) != pmd_val(*pmdp))) {
undo_dev_pagemap(nr, nr_start, flags, pages);
return 0;
}
return 1;
}
static int __gup_device_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr,
unsigned long end, unsigned int flags,
struct page **pages, int *nr)
{
unsigned long fault_pfn;
int nr_start = *nr;
fault_pfn = pud_pfn(orig) + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
if (!__gup_device_huge(fault_pfn, addr, end, flags, pages, nr))
return 0;
if (unlikely(pud_val(orig) != pud_val(*pudp))) {
undo_dev_pagemap(nr, nr_start, flags, pages);
return 0;
}
return 1;
}
#else
static int __gup_device_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr,
unsigned long end, unsigned int flags,
struct page **pages, int *nr)
{
BUILD_BUG();
return 0;
}
static int __gup_device_huge_pud(pud_t pud, pud_t *pudp, unsigned long addr,
unsigned long end, unsigned int flags,
struct page **pages, int *nr)
{
BUILD_BUG();
return 0;
}
#endif
static int record_subpages(struct page *page, unsigned long addr,
unsigned long end, struct page **pages)
{
int nr;
for (nr = 0; addr != end; nr++, addr += PAGE_SIZE)
pages[nr] = nth_page(page, nr);
return nr;
}
#ifdef CONFIG_ARCH_HAS_HUGEPD
static unsigned long hugepte_addr_end(unsigned long addr, unsigned long end,
unsigned long sz)
{
unsigned long __boundary = (addr + sz) & ~(sz-1);
return (__boundary - 1 < end - 1) ? __boundary : end;
}
static int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr,
unsigned long end, unsigned int flags,
struct page **pages, int *nr)
{
unsigned long pte_end;
struct page *page;
struct folio *folio;
pte_t pte;
int refs;
pte_end = (addr + sz) & ~(sz-1);
if (pte_end < end)
end = pte_end;
pte = huge_ptep_get(ptep);
if (!pte_access_permitted(pte, flags & FOLL_WRITE))
return 0;
/* hugepages are never "special" */
VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
page = nth_page(pte_page(pte), (addr & (sz - 1)) >> PAGE_SHIFT);
refs = record_subpages(page, addr, end, pages + *nr);
folio = try_grab_folio(page, refs, flags);
if (!folio)
return 0;
if (unlikely(pte_val(pte) != pte_val(*ptep))) {
gup_put_folio(folio, refs, flags);
return 0;
}
if (!pte_write(pte) && gup_must_unshare(flags, &folio->page)) {
gup_put_folio(folio, refs, flags);
return 0;
}
*nr += refs;
folio_set_referenced(folio);
return 1;
}
static int gup_huge_pd(hugepd_t hugepd, unsigned long addr,
unsigned int pdshift, unsigned long end, unsigned int flags,
struct page **pages, int *nr)
{
pte_t *ptep;
unsigned long sz = 1UL << hugepd_shift(hugepd);
unsigned long next;
ptep = hugepte_offset(hugepd, addr, pdshift);
do {
next = hugepte_addr_end(addr, end, sz);
if (!gup_hugepte(ptep, sz, addr, end, flags, pages, nr))
return 0;
} while (ptep++, addr = next, addr != end);
return 1;
}
#else
static inline int gup_huge_pd(hugepd_t hugepd, unsigned long addr,
unsigned int pdshift, unsigned long end, unsigned int flags,
struct page **pages, int *nr)
{
return 0;
}
#endif /* CONFIG_ARCH_HAS_HUGEPD */
static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr,
unsigned long end, unsigned int flags,
struct page **pages, int *nr)
{
struct page *page;
struct folio *folio;
int refs;
if (!pmd_access_permitted(orig, flags & FOLL_WRITE))
return 0;
if (pmd_devmap(orig)) {
if (unlikely(flags & FOLL_LONGTERM))
return 0;
return __gup_device_huge_pmd(orig, pmdp, addr, end, flags,
pages, nr);
}
page = nth_page(pmd_page(orig), (addr & ~PMD_MASK) >> PAGE_SHIFT);
refs = record_subpages(page, addr, end, pages + *nr);
folio = try_grab_folio(page, refs, flags);
if (!folio)
return 0;
if (unlikely(pmd_val(orig) != pmd_val(*pmdp))) {
gup_put_folio(folio, refs, flags);
return 0;
}
if (!pmd_write(orig) && gup_must_unshare(flags, &folio->page)) {
gup_put_folio(folio, refs, flags);
return 0;
}
*nr += refs;
folio_set_referenced(folio);
return 1;
}
static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr,
unsigned long end, unsigned int flags,
struct page **pages, int *nr)
{
struct page *page;
struct folio *folio;
int refs;
if (!pud_access_permitted(orig, flags & FOLL_WRITE))
return 0;
if (pud_devmap(orig)) {
if (unlikely(flags & FOLL_LONGTERM))
return 0;
return __gup_device_huge_pud(orig, pudp, addr, end, flags,
pages, nr);
}
page = nth_page(pud_page(orig), (addr & ~PUD_MASK) >> PAGE_SHIFT);
refs = record_subpages(page, addr, end, pages + *nr);
folio = try_grab_folio(page, refs, flags);
if (!folio)
return 0;
if (unlikely(pud_val(orig) != pud_val(*pudp))) {
gup_put_folio(folio, refs, flags);
return 0;
}
if (!pud_write(orig) && gup_must_unshare(flags, &folio->page)) {
gup_put_folio(folio, refs, flags);
return 0;
}
*nr += refs;
folio_set_referenced(folio);
return 1;
}
static int gup_huge_pgd(pgd_t orig, pgd_t *pgdp, unsigned long addr,
unsigned long end, unsigned int flags,
struct page **pages, int *nr)
{
int refs;
struct page *page;
struct folio *folio;
if (!pgd_access_permitted(orig, flags & FOLL_WRITE))
return 0;
BUILD_BUG_ON(pgd_devmap(orig));
page = nth_page(pgd_page(orig), (addr & ~PGDIR_MASK) >> PAGE_SHIFT);
refs = record_subpages(page, addr, end, pages + *nr);
folio = try_grab_folio(page, refs, flags);
if (!folio)
return 0;
if (unlikely(pgd_val(orig) != pgd_val(*pgdp))) {
gup_put_folio(folio, refs, flags);
return 0;
}
*nr += refs;
folio_set_referenced(folio);
return 1;
}
static int gup_pmd_range(pud_t *pudp, pud_t pud, unsigned long addr, unsigned long end,
unsigned int flags, struct page **pages, int *nr)
{
unsigned long next;
pmd_t *pmdp;
pmdp = pmd_offset_lockless(pudp, pud, addr);
do {
pmd_t pmd = READ_ONCE(*pmdp);
next = pmd_addr_end(addr, end);
if (!pmd_present(pmd))
return 0;
if (unlikely(pmd_trans_huge(pmd) || pmd_huge(pmd) ||
pmd_devmap(pmd))) {
if (pmd_protnone(pmd) &&
!gup_can_follow_protnone(flags))
return 0;
if (!gup_huge_pmd(pmd, pmdp, addr, next, flags,
pages, nr))
return 0;
} else if (unlikely(is_hugepd(__hugepd(pmd_val(pmd))))) {
/*
* architecture have different format for hugetlbfs
* pmd format and THP pmd format
*/
if (!gup_huge_pd(__hugepd(pmd_val(pmd)), addr,
PMD_SHIFT, next, flags, pages, nr))
return 0;
} else if (!gup_pte_range(pmd, pmdp, addr, next, flags, pages, nr))
return 0;
} while (pmdp++, addr = next, addr != end);
return 1;
}
static int gup_pud_range(p4d_t *p4dp, p4d_t p4d, unsigned long addr, unsigned long end,
unsigned int flags, struct page **pages, int *nr)
{
unsigned long next;
pud_t *pudp;
pudp = pud_offset_lockless(p4dp, p4d, addr);
do {
pud_t pud = READ_ONCE(*pudp);
next = pud_addr_end(addr, end);
if (unlikely(!pud_present(pud)))
return 0;
if (unlikely(pud_huge(pud))) {
if (!gup_huge_pud(pud, pudp, addr, next, flags,
pages, nr))
return 0;
} else if (unlikely(is_hugepd(__hugepd(pud_val(pud))))) {
if (!gup_huge_pd(__hugepd(pud_val(pud)), addr,
PUD_SHIFT, next, flags, pages, nr))
return 0;
} else if (!gup_pmd_range(pudp, pud, addr, next, flags, pages, nr))
return 0;
} while (pudp++, addr = next, addr != end);
return 1;
}
static int gup_p4d_range(pgd_t *pgdp, pgd_t pgd, unsigned long addr, unsigned long end,
unsigned int flags, struct page **pages, int *nr)
{
unsigned long next;
p4d_t *p4dp;
p4dp = p4d_offset_lockless(pgdp, pgd, addr);
do {
p4d_t p4d = READ_ONCE(*p4dp);
next = p4d_addr_end(addr, end);
if (p4d_none(p4d))
return 0;
BUILD_BUG_ON(p4d_huge(p4d));
if (unlikely(is_hugepd(__hugepd(p4d_val(p4d))))) {
if (!gup_huge_pd(__hugepd(p4d_val(p4d)), addr,
P4D_SHIFT, next, flags, pages, nr))
return 0;
} else if (!gup_pud_range(p4dp, p4d, addr, next, flags, pages, nr))
return 0;
} while (p4dp++, addr = next, addr != end);
return 1;
}
static void gup_pgd_range(unsigned long addr, unsigned long end,
unsigned int flags, struct page **pages, int *nr)
{
unsigned long next;
pgd_t *pgdp;
pgdp = pgd_offset(current->mm, addr);
do {
pgd_t pgd = READ_ONCE(*pgdp);
next = pgd_addr_end(addr, end);
if (pgd_none(pgd))
return;
if (unlikely(pgd_huge(pgd))) {
if (!gup_huge_pgd(pgd, pgdp, addr, next, flags,
pages, nr))
return;
} else if (unlikely(is_hugepd(__hugepd(pgd_val(pgd))))) {
if (!gup_huge_pd(__hugepd(pgd_val(pgd)), addr,
PGDIR_SHIFT, next, flags, pages, nr))
return;
} else if (!gup_p4d_range(pgdp, pgd, addr, next, flags, pages, nr))
return;
} while (pgdp++, addr = next, addr != end);
}
#else
static inline void gup_pgd_range(unsigned long addr, unsigned long end,
unsigned int flags, struct page **pages, int *nr)
{
}
#endif /* CONFIG_HAVE_FAST_GUP */
#ifndef gup_fast_permitted
/*
* Check if it's allowed to use get_user_pages_fast_only() for the range, or
* we need to fall back to the slow version:
*/
static bool gup_fast_permitted(unsigned long start, unsigned long end)
{
return true;
}
#endif
static unsigned long lockless_pages_from_mm(unsigned long start,
unsigned long end,
unsigned int gup_flags,
struct page **pages)
{
unsigned long flags;
int nr_pinned = 0;
unsigned seq;
if (!IS_ENABLED(CONFIG_HAVE_FAST_GUP) ||
!gup_fast_permitted(start, end))
return 0;
if (gup_flags & FOLL_PIN) {
seq = raw_read_seqcount(¤t->mm->write_protect_seq);
if (seq & 1)
return 0;
}
/*
* Disable interrupts. The nested form is used, in order to allow full,
* general purpose use of this routine.
*
* With interrupts disabled, we block page table pages from being freed
* from under us. See struct mmu_table_batch comments in
* include/asm-generic/tlb.h for more details.
*
* We do not adopt an rcu_read_lock() here as we also want to block IPIs
* that come from THPs splitting.
*/
local_irq_save(flags);
gup_pgd_range(start, end, gup_flags, pages, &nr_pinned);
local_irq_restore(flags);
/*
* When pinning pages for DMA there could be a concurrent write protect
* from fork() via copy_page_range(), in this case always fail fast GUP.
*/
if (gup_flags & FOLL_PIN) {
if (read_seqcount_retry(¤t->mm->write_protect_seq, seq)) {
unpin_user_pages_lockless(pages, nr_pinned);
return 0;
} else {
sanity_check_pinned_pages(pages, nr_pinned);
}
}
return nr_pinned;
}
static int internal_get_user_pages_fast(unsigned long start,
unsigned long nr_pages,
unsigned int gup_flags,
struct page **pages)
{
unsigned long len, end;
unsigned long nr_pinned;
int ret;
if (WARN_ON_ONCE(gup_flags & ~(FOLL_WRITE | FOLL_LONGTERM |
FOLL_FORCE | FOLL_PIN | FOLL_GET |
FOLL_FAST_ONLY | FOLL_NOFAULT)))
return -EINVAL;
if (gup_flags & FOLL_PIN)
mm_set_has_pinned_flag(¤t->mm->flags);
if (!(gup_flags & FOLL_FAST_ONLY))
might_lock_read(¤t->mm->mmap_lock);
start = untagged_addr(start) & PAGE_MASK;
len = nr_pages << PAGE_SHIFT;
if (check_add_overflow(start, len, &end))
return 0;
if (unlikely(!access_ok((void __user *)start, len)))
return -EFAULT;
nr_pinned = lockless_pages_from_mm(start, end, gup_flags, pages);
if (nr_pinned == nr_pages || gup_flags & FOLL_FAST_ONLY)
return nr_pinned;
/* Slow path: try to get the remaining pages with get_user_pages */
start += nr_pinned << PAGE_SHIFT;
pages += nr_pinned;
ret = get_user_pages_unlocked(start, nr_pages - nr_pinned, pages,
gup_flags);
if (ret < 0) {
/*
* The caller has to unpin the pages we already pinned so
* returning -errno is not an option
*/
if (nr_pinned)
return nr_pinned;
return ret;
}
return ret + nr_pinned;
}
/**
* get_user_pages_fast_only() - pin user pages in memory
* @start: starting user address
* @nr_pages: number of pages from start to pin
* @gup_flags: flags modifying pin behaviour
* @pages: array that receives pointers to the pages pinned.
* Should be at least nr_pages long.
*
* Like get_user_pages_fast() except it's IRQ-safe in that it won't fall back to
* the regular GUP.
* Note a difference with get_user_pages_fast: this always returns the
* number of pages pinned, 0 if no pages were pinned.
*
* If the architecture does not support this function, simply return with no
* pages pinned.
*
* Careful, careful! COW breaking can go either way, so a non-write
* access can get ambiguous page results. If you call this function without
* 'write' set, you'd better be sure that you're ok with that ambiguity.
*/
int get_user_pages_fast_only(unsigned long start, int nr_pages,
unsigned int gup_flags, struct page **pages)
{
int nr_pinned;
/*
* Internally (within mm/gup.c), gup fast variants must set FOLL_GET,
* because gup fast is always a "pin with a +1 page refcount" request.
*
* FOLL_FAST_ONLY is required in order to match the API description of
* this routine: no fall back to regular ("slow") GUP.
*/
gup_flags |= FOLL_GET | FOLL_FAST_ONLY;
nr_pinned = internal_get_user_pages_fast(start, nr_pages, gup_flags,
pages);
/*
* As specified in the API description above, this routine is not
* allowed to return negative values. However, the common core
* routine internal_get_user_pages_fast() *can* return -errno.
* Therefore, correct for that here:
*/
if (nr_pinned < 0)
nr_pinned = 0;
return nr_pinned;
}
EXPORT_SYMBOL_GPL(get_user_pages_fast_only);
/**
* get_user_pages_fast() - pin user pages in memory
* @start: starting user address
* @nr_pages: number of pages from start to pin
* @gup_flags: flags modifying pin behaviour
* @pages: array that receives pointers to the pages pinned.
* Should be at least nr_pages long.
*
* Attempt to pin user pages in memory without taking mm->mmap_lock.
* If not successful, it will fall back to taking the lock and
* calling get_user_pages().
*
* Returns number of pages pinned. This may be fewer than the number requested.
* If nr_pages is 0 or negative, returns 0. If no pages were pinned, returns
* -errno.
*/
int get_user_pages_fast(unsigned long start, int nr_pages,
unsigned int gup_flags, struct page **pages)
{
if (!is_valid_gup_flags(gup_flags))
return -EINVAL;
/*
* The caller may or may not have explicitly set FOLL_GET; either way is
* OK. However, internally (within mm/gup.c), gup fast variants must set
* FOLL_GET, because gup fast is always a "pin with a +1 page refcount"
* request.
*/
gup_flags |= FOLL_GET;
return internal_get_user_pages_fast(start, nr_pages, gup_flags, pages);
}
EXPORT_SYMBOL_GPL(get_user_pages_fast);
/**
* pin_user_pages_fast() - pin user pages in memory without taking locks
*
* @start: starting user address
* @nr_pages: number of pages from start to pin
* @gup_flags: flags modifying pin behaviour
* @pages: array that receives pointers to the pages pinned.
* Should be at least nr_pages long.
*
* Nearly the same as get_user_pages_fast(), except that FOLL_PIN is set. See
* get_user_pages_fast() for documentation on the function arguments, because
* the arguments here are identical.
*
* FOLL_PIN means that the pages must be released via unpin_user_page(). Please
* see Documentation/core-api/pin_user_pages.rst for further details.
*/
int pin_user_pages_fast(unsigned long start, int nr_pages,
unsigned int gup_flags, struct page **pages)
{
/* FOLL_GET and FOLL_PIN are mutually exclusive. */
if (WARN_ON_ONCE(gup_flags & FOLL_GET))
return -EINVAL;
if (WARN_ON_ONCE(!pages))
return -EINVAL;
gup_flags |= FOLL_PIN;
return internal_get_user_pages_fast(start, nr_pages, gup_flags, pages);
}
EXPORT_SYMBOL_GPL(pin_user_pages_fast);
/*
* This is the FOLL_PIN equivalent of get_user_pages_fast_only(). Behavior
* is the same, except that this one sets FOLL_PIN instead of FOLL_GET.
*
* The API rules are the same, too: no negative values may be returned.
*/
int pin_user_pages_fast_only(unsigned long start, int nr_pages,
unsigned int gup_flags, struct page **pages)
{
int nr_pinned;
/*
* FOLL_GET and FOLL_PIN are mutually exclusive. Note that the API
* rules require returning 0, rather than -errno:
*/
if (WARN_ON_ONCE(gup_flags & FOLL_GET))
return 0;
if (WARN_ON_ONCE(!pages))
return 0;
/*
* FOLL_FAST_ONLY is required in order to match the API description of
* this routine: no fall back to regular ("slow") GUP.
*/
gup_flags |= (FOLL_PIN | FOLL_FAST_ONLY);
nr_pinned = internal_get_user_pages_fast(start, nr_pages, gup_flags,
pages);
/*
* This routine is not allowed to return negative values. However,
* internal_get_user_pages_fast() *can* return -errno. Therefore,
* correct for that here:
*/
if (nr_pinned < 0)
nr_pinned = 0;
return nr_pinned;
}
EXPORT_SYMBOL_GPL(pin_user_pages_fast_only);
/**
* pin_user_pages_remote() - pin pages of a remote process
*
* @mm: mm_struct of target mm
* @start: starting user address
* @nr_pages: number of pages from start to pin
* @gup_flags: flags modifying lookup behaviour
* @pages: array that receives pointers to the pages pinned.
* Should be at least nr_pages long.
* @vmas: array of pointers to vmas corresponding to each page.
* Or NULL if the caller does not require them.
* @locked: pointer to lock flag indicating whether lock is held and
* subsequently whether VM_FAULT_RETRY functionality can be
* utilised. Lock must initially be held.
*
* Nearly the same as get_user_pages_remote(), except that FOLL_PIN is set. See
* get_user_pages_remote() for documentation on the function arguments, because
* the arguments here are identical.
*
* FOLL_PIN means that the pages must be released via unpin_user_page(). Please
* see Documentation/core-api/pin_user_pages.rst for details.
*/
long pin_user_pages_remote(struct mm_struct *mm,
unsigned long start, unsigned long nr_pages,
unsigned int gup_flags, struct page **pages,
struct vm_area_struct **vmas, int *locked)
{
/* FOLL_GET and FOLL_PIN are mutually exclusive. */
if (WARN_ON_ONCE(gup_flags & FOLL_GET))
return -EINVAL;
if (WARN_ON_ONCE(!pages))
return -EINVAL;
return __gup_longterm_locked(mm, start, nr_pages, pages, vmas, locked,
gup_flags | FOLL_PIN | FOLL_TOUCH |
FOLL_REMOTE);
}
EXPORT_SYMBOL(pin_user_pages_remote);
/**
* pin_user_pages() - pin user pages in memory for use by other devices
*
* @start: starting user address
* @nr_pages: number of pages from start to pin
* @gup_flags: flags modifying lookup behaviour
* @pages: array that receives pointers to the pages pinned.
* Should be at least nr_pages long.
* @vmas: array of pointers to vmas corresponding to each page.
* Or NULL if the caller does not require them.
*
* Nearly the same as get_user_pages(), except that FOLL_TOUCH is not set, and
* FOLL_PIN is set.
*
* FOLL_PIN means that the pages must be released via unpin_user_page(). Please
* see Documentation/core-api/pin_user_pages.rst for details.
*/
long pin_user_pages(unsigned long start, unsigned long nr_pages,
unsigned int gup_flags, struct page **pages,
struct vm_area_struct **vmas)
{
/* FOLL_GET and FOLL_PIN are mutually exclusive. */
if (WARN_ON_ONCE(gup_flags & FOLL_GET))
return -EINVAL;
if (WARN_ON_ONCE(!pages))
return -EINVAL;
gup_flags |= FOLL_PIN;
return __gup_longterm_locked(current->mm, start, nr_pages,
pages, vmas, NULL, gup_flags);
}
EXPORT_SYMBOL(pin_user_pages);
/*
* pin_user_pages_unlocked() is the FOLL_PIN variant of
* get_user_pages_unlocked(). Behavior is the same, except that this one sets
* FOLL_PIN and rejects FOLL_GET.
*/
long pin_user_pages_unlocked(unsigned long start, unsigned long nr_pages,
struct page **pages, unsigned int gup_flags)
{
/* FOLL_GET and FOLL_PIN are mutually exclusive. */
if (WARN_ON_ONCE(gup_flags & FOLL_GET))
return -EINVAL;
if (WARN_ON_ONCE(!pages))
return -EINVAL;
gup_flags |= FOLL_PIN;
return get_user_pages_unlocked(start, nr_pages, pages, gup_flags);
}
EXPORT_SYMBOL(pin_user_pages_unlocked);
|