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
|
// SPDX-License-Identifier: GPL-2.0-or-later
/*
* Virtio-mem device driver.
*
* Copyright Red Hat, Inc. 2020
*
* Author(s): David Hildenbrand <david@redhat.com>
*/
#include <linux/virtio.h>
#include <linux/virtio_mem.h>
#include <linux/workqueue.h>
#include <linux/slab.h>
#include <linux/module.h>
#include <linux/mm.h>
#include <linux/memory_hotplug.h>
#include <linux/memory.h>
#include <linux/hrtimer.h>
#include <linux/crash_dump.h>
#include <linux/mutex.h>
#include <linux/bitmap.h>
#include <linux/lockdep.h>
#include <acpi/acpi_numa.h>
enum virtio_mem_mb_state {
/* Unplugged, not added to Linux. Can be reused later. */
VIRTIO_MEM_MB_STATE_UNUSED = 0,
/* (Partially) plugged, not added to Linux. Error on add_memory(). */
VIRTIO_MEM_MB_STATE_PLUGGED,
/* Fully plugged, fully added to Linux, offline. */
VIRTIO_MEM_MB_STATE_OFFLINE,
/* Partially plugged, fully added to Linux, offline. */
VIRTIO_MEM_MB_STATE_OFFLINE_PARTIAL,
/* Fully plugged, fully added to Linux, online (!ZONE_MOVABLE). */
VIRTIO_MEM_MB_STATE_ONLINE,
/* Partially plugged, fully added to Linux, online (!ZONE_MOVABLE). */
VIRTIO_MEM_MB_STATE_ONLINE_PARTIAL,
/*
* Fully plugged, fully added to Linux, online (ZONE_MOVABLE).
* We are not allowed to allocate (unplug) parts of this block that
* are not movable (similar to gigantic pages). We will never allow
* to online OFFLINE_PARTIAL to ZONE_MOVABLE (as they would contain
* unmovable parts).
*/
VIRTIO_MEM_MB_STATE_ONLINE_MOVABLE,
VIRTIO_MEM_MB_STATE_COUNT
};
struct virtio_mem {
struct virtio_device *vdev;
/* We might first have to unplug all memory when starting up. */
bool unplug_all_required;
/* Workqueue that processes the plug/unplug requests. */
struct work_struct wq;
atomic_t config_changed;
/* Virtqueue for guest->host requests. */
struct virtqueue *vq;
/* Wait for a host response to a guest request. */
wait_queue_head_t host_resp;
/* Space for one guest request and the host response. */
struct virtio_mem_req req;
struct virtio_mem_resp resp;
/* The current size of the device. */
uint64_t plugged_size;
/* The requested size of the device. */
uint64_t requested_size;
/* The device block size (for communicating with the device). */
uint32_t device_block_size;
/* The translated node id. NUMA_NO_NODE in case not specified. */
int nid;
/* Physical start address of the memory region. */
uint64_t addr;
/* Maximum region size in bytes. */
uint64_t region_size;
/* The subblock size. */
uint32_t subblock_size;
/* The number of subblocks per memory block. */
uint32_t nb_sb_per_mb;
/* Id of the first memory block of this device. */
unsigned long first_mb_id;
/* Id of the last memory block of this device. */
unsigned long last_mb_id;
/* Id of the last usable memory block of this device. */
unsigned long last_usable_mb_id;
/* Id of the next memory bock to prepare when needed. */
unsigned long next_mb_id;
/* Summary of all memory block states. */
unsigned long nb_mb_state[VIRTIO_MEM_MB_STATE_COUNT];
#define VIRTIO_MEM_NB_OFFLINE_THRESHOLD 10
/*
* One byte state per memory block.
*
* Allocated via vmalloc(). When preparing new blocks, resized
* (alloc+copy+free) when needed (crossing pages with the next mb).
* (when crossing pages).
*
* With 128MB memory blocks, we have states for 512GB of memory in one
* page.
*/
uint8_t *mb_state;
/*
* $nb_sb_per_mb bit per memory block. Handled similar to mb_state.
*
* With 4MB subblocks, we manage 128GB of memory in one page.
*/
unsigned long *sb_bitmap;
/*
* Mutex that protects the nb_mb_state, mb_state, and sb_bitmap.
*
* When this lock is held the pointers can't change, ONLINE and
* OFFLINE blocks can't change the state and no subblocks will get
* plugged/unplugged.
*/
struct mutex hotplug_mutex;
bool hotplug_active;
/* An error occurred we cannot handle - stop processing requests. */
bool broken;
/* The driver is being removed. */
spinlock_t removal_lock;
bool removing;
/* Timer for retrying to plug/unplug memory. */
struct hrtimer retry_timer;
#define VIRTIO_MEM_RETRY_TIMER_MS 30000
/* Memory notifier (online/offline events). */
struct notifier_block memory_notifier;
/* Next device in the list of virtio-mem devices. */
struct list_head next;
};
/*
* We have to share a single online_page callback among all virtio-mem
* devices. We use RCU to iterate the list in the callback.
*/
static DEFINE_MUTEX(virtio_mem_mutex);
static LIST_HEAD(virtio_mem_devices);
static void virtio_mem_online_page_cb(struct page *page, unsigned int order);
/*
* Register a virtio-mem device so it will be considered for the online_page
* callback.
*/
static int register_virtio_mem_device(struct virtio_mem *vm)
{
int rc = 0;
/* First device registers the callback. */
mutex_lock(&virtio_mem_mutex);
if (list_empty(&virtio_mem_devices))
rc = set_online_page_callback(&virtio_mem_online_page_cb);
if (!rc)
list_add_rcu(&vm->next, &virtio_mem_devices);
mutex_unlock(&virtio_mem_mutex);
return rc;
}
/*
* Unregister a virtio-mem device so it will no longer be considered for the
* online_page callback.
*/
static void unregister_virtio_mem_device(struct virtio_mem *vm)
{
/* Last device unregisters the callback. */
mutex_lock(&virtio_mem_mutex);
list_del_rcu(&vm->next);
if (list_empty(&virtio_mem_devices))
restore_online_page_callback(&virtio_mem_online_page_cb);
mutex_unlock(&virtio_mem_mutex);
synchronize_rcu();
}
/*
* Calculate the memory block id of a given address.
*/
static unsigned long virtio_mem_phys_to_mb_id(unsigned long addr)
{
return addr / memory_block_size_bytes();
}
/*
* Calculate the physical start address of a given memory block id.
*/
static unsigned long virtio_mem_mb_id_to_phys(unsigned long mb_id)
{
return mb_id * memory_block_size_bytes();
}
/*
* Calculate the subblock id of a given address.
*/
static unsigned long virtio_mem_phys_to_sb_id(struct virtio_mem *vm,
unsigned long addr)
{
const unsigned long mb_id = virtio_mem_phys_to_mb_id(addr);
const unsigned long mb_addr = virtio_mem_mb_id_to_phys(mb_id);
return (addr - mb_addr) / vm->subblock_size;
}
/*
* Set the state of a memory block, taking care of the state counter.
*/
static void virtio_mem_mb_set_state(struct virtio_mem *vm, unsigned long mb_id,
enum virtio_mem_mb_state state)
{
const unsigned long idx = mb_id - vm->first_mb_id;
enum virtio_mem_mb_state old_state;
old_state = vm->mb_state[idx];
vm->mb_state[idx] = state;
BUG_ON(vm->nb_mb_state[old_state] == 0);
vm->nb_mb_state[old_state]--;
vm->nb_mb_state[state]++;
}
/*
* Get the state of a memory block.
*/
static enum virtio_mem_mb_state virtio_mem_mb_get_state(struct virtio_mem *vm,
unsigned long mb_id)
{
const unsigned long idx = mb_id - vm->first_mb_id;
return vm->mb_state[idx];
}
/*
* Prepare the state array for the next memory block.
*/
static int virtio_mem_mb_state_prepare_next_mb(struct virtio_mem *vm)
{
unsigned long old_bytes = vm->next_mb_id - vm->first_mb_id + 1;
unsigned long new_bytes = vm->next_mb_id - vm->first_mb_id + 2;
int old_pages = PFN_UP(old_bytes);
int new_pages = PFN_UP(new_bytes);
uint8_t *new_mb_state;
if (vm->mb_state && old_pages == new_pages)
return 0;
new_mb_state = vzalloc(new_pages * PAGE_SIZE);
if (!new_mb_state)
return -ENOMEM;
mutex_lock(&vm->hotplug_mutex);
if (vm->mb_state)
memcpy(new_mb_state, vm->mb_state, old_pages * PAGE_SIZE);
vfree(vm->mb_state);
vm->mb_state = new_mb_state;
mutex_unlock(&vm->hotplug_mutex);
return 0;
}
#define virtio_mem_for_each_mb_state(_vm, _mb_id, _state) \
for (_mb_id = _vm->first_mb_id; \
_mb_id < _vm->next_mb_id && _vm->nb_mb_state[_state]; \
_mb_id++) \
if (virtio_mem_mb_get_state(_vm, _mb_id) == _state)
#define virtio_mem_for_each_mb_state_rev(_vm, _mb_id, _state) \
for (_mb_id = _vm->next_mb_id - 1; \
_mb_id >= _vm->first_mb_id && _vm->nb_mb_state[_state]; \
_mb_id--) \
if (virtio_mem_mb_get_state(_vm, _mb_id) == _state)
/*
* Mark all selected subblocks plugged.
*
* Will not modify the state of the memory block.
*/
static void virtio_mem_mb_set_sb_plugged(struct virtio_mem *vm,
unsigned long mb_id, int sb_id,
int count)
{
const int bit = (mb_id - vm->first_mb_id) * vm->nb_sb_per_mb + sb_id;
__bitmap_set(vm->sb_bitmap, bit, count);
}
/*
* Mark all selected subblocks unplugged.
*
* Will not modify the state of the memory block.
*/
static void virtio_mem_mb_set_sb_unplugged(struct virtio_mem *vm,
unsigned long mb_id, int sb_id,
int count)
{
const int bit = (mb_id - vm->first_mb_id) * vm->nb_sb_per_mb + sb_id;
__bitmap_clear(vm->sb_bitmap, bit, count);
}
/*
* Test if all selected subblocks are plugged.
*/
static bool virtio_mem_mb_test_sb_plugged(struct virtio_mem *vm,
unsigned long mb_id, int sb_id,
int count)
{
const int bit = (mb_id - vm->first_mb_id) * vm->nb_sb_per_mb + sb_id;
if (count == 1)
return test_bit(bit, vm->sb_bitmap);
/* TODO: Helper similar to bitmap_set() */
return find_next_zero_bit(vm->sb_bitmap, bit + count, bit) >=
bit + count;
}
/*
* Test if all selected subblocks are unplugged.
*/
static bool virtio_mem_mb_test_sb_unplugged(struct virtio_mem *vm,
unsigned long mb_id, int sb_id,
int count)
{
const int bit = (mb_id - vm->first_mb_id) * vm->nb_sb_per_mb + sb_id;
/* TODO: Helper similar to bitmap_set() */
return find_next_bit(vm->sb_bitmap, bit + count, bit) >= bit + count;
}
/*
* Find the first plugged subblock. Returns vm->nb_sb_per_mb in case there is
* none.
*/
static int virtio_mem_mb_first_plugged_sb(struct virtio_mem *vm,
unsigned long mb_id)
{
const int bit = (mb_id - vm->first_mb_id) * vm->nb_sb_per_mb;
return find_next_bit(vm->sb_bitmap, bit + vm->nb_sb_per_mb, bit) - bit;
}
/*
* Find the first unplugged subblock. Returns vm->nb_sb_per_mb in case there is
* none.
*/
static int virtio_mem_mb_first_unplugged_sb(struct virtio_mem *vm,
unsigned long mb_id)
{
const int bit = (mb_id - vm->first_mb_id) * vm->nb_sb_per_mb;
return find_next_zero_bit(vm->sb_bitmap, bit + vm->nb_sb_per_mb, bit) -
bit;
}
/*
* Prepare the subblock bitmap for the next memory block.
*/
static int virtio_mem_sb_bitmap_prepare_next_mb(struct virtio_mem *vm)
{
const unsigned long old_nb_mb = vm->next_mb_id - vm->first_mb_id;
const unsigned long old_nb_bits = old_nb_mb * vm->nb_sb_per_mb;
const unsigned long new_nb_bits = (old_nb_mb + 1) * vm->nb_sb_per_mb;
int old_pages = PFN_UP(BITS_TO_LONGS(old_nb_bits) * sizeof(long));
int new_pages = PFN_UP(BITS_TO_LONGS(new_nb_bits) * sizeof(long));
unsigned long *new_sb_bitmap, *old_sb_bitmap;
if (vm->sb_bitmap && old_pages == new_pages)
return 0;
new_sb_bitmap = vzalloc(new_pages * PAGE_SIZE);
if (!new_sb_bitmap)
return -ENOMEM;
mutex_lock(&vm->hotplug_mutex);
if (new_sb_bitmap)
memcpy(new_sb_bitmap, vm->sb_bitmap, old_pages * PAGE_SIZE);
old_sb_bitmap = vm->sb_bitmap;
vm->sb_bitmap = new_sb_bitmap;
mutex_unlock(&vm->hotplug_mutex);
vfree(old_sb_bitmap);
return 0;
}
/*
* Try to add a memory block to Linux. This will usually only fail
* if out of memory.
*
* Must not be called with the vm->hotplug_mutex held (possible deadlock with
* onlining code).
*
* Will not modify the state of the memory block.
*/
static int virtio_mem_mb_add(struct virtio_mem *vm, unsigned long mb_id)
{
const uint64_t addr = virtio_mem_mb_id_to_phys(mb_id);
int nid = vm->nid;
if (nid == NUMA_NO_NODE)
nid = memory_add_physaddr_to_nid(addr);
dev_dbg(&vm->vdev->dev, "adding memory block: %lu\n", mb_id);
return add_memory(nid, addr, memory_block_size_bytes());
}
/*
* Try to remove a memory block from Linux. Will only fail if the memory block
* is not offline.
*
* Must not be called with the vm->hotplug_mutex held (possible deadlock with
* onlining code).
*
* Will not modify the state of the memory block.
*/
static int virtio_mem_mb_remove(struct virtio_mem *vm, unsigned long mb_id)
{
const uint64_t addr = virtio_mem_mb_id_to_phys(mb_id);
int nid = vm->nid;
if (nid == NUMA_NO_NODE)
nid = memory_add_physaddr_to_nid(addr);
dev_dbg(&vm->vdev->dev, "removing memory block: %lu\n", mb_id);
return remove_memory(nid, addr, memory_block_size_bytes());
}
/*
* Trigger the workqueue so the device can perform its magic.
*/
static void virtio_mem_retry(struct virtio_mem *vm)
{
unsigned long flags;
spin_lock_irqsave(&vm->removal_lock, flags);
if (!vm->removing)
queue_work(system_freezable_wq, &vm->wq);
spin_unlock_irqrestore(&vm->removal_lock, flags);
}
static int virtio_mem_translate_node_id(struct virtio_mem *vm, uint16_t node_id)
{
int node = NUMA_NO_NODE;
#if defined(CONFIG_ACPI_NUMA)
if (virtio_has_feature(vm->vdev, VIRTIO_MEM_F_ACPI_PXM))
node = pxm_to_node(node_id);
#endif
return node;
}
/*
* Test if a virtio-mem device overlaps with the given range. Can be called
* from (notifier) callbacks lockless.
*/
static bool virtio_mem_overlaps_range(struct virtio_mem *vm,
unsigned long start, unsigned long size)
{
unsigned long dev_start = virtio_mem_mb_id_to_phys(vm->first_mb_id);
unsigned long dev_end = virtio_mem_mb_id_to_phys(vm->last_mb_id) +
memory_block_size_bytes();
return start < dev_end && dev_start < start + size;
}
/*
* Test if a virtio-mem device owns a memory block. Can be called from
* (notifier) callbacks lockless.
*/
static bool virtio_mem_owned_mb(struct virtio_mem *vm, unsigned long mb_id)
{
return mb_id >= vm->first_mb_id && mb_id <= vm->last_mb_id;
}
static int virtio_mem_notify_going_online(struct virtio_mem *vm,
unsigned long mb_id,
enum zone_type zone)
{
switch (virtio_mem_mb_get_state(vm, mb_id)) {
case VIRTIO_MEM_MB_STATE_OFFLINE_PARTIAL:
/*
* We won't allow to online a partially plugged memory block
* to the MOVABLE zone - it would contain unmovable parts.
*/
if (zone == ZONE_MOVABLE) {
dev_warn_ratelimited(&vm->vdev->dev,
"memory block has holes, MOVABLE not supported\n");
return NOTIFY_BAD;
}
return NOTIFY_OK;
case VIRTIO_MEM_MB_STATE_OFFLINE:
return NOTIFY_OK;
default:
break;
}
dev_warn_ratelimited(&vm->vdev->dev,
"memory block onlining denied\n");
return NOTIFY_BAD;
}
static void virtio_mem_notify_offline(struct virtio_mem *vm,
unsigned long mb_id)
{
switch (virtio_mem_mb_get_state(vm, mb_id)) {
case VIRTIO_MEM_MB_STATE_ONLINE_PARTIAL:
virtio_mem_mb_set_state(vm, mb_id,
VIRTIO_MEM_MB_STATE_OFFLINE_PARTIAL);
break;
case VIRTIO_MEM_MB_STATE_ONLINE:
case VIRTIO_MEM_MB_STATE_ONLINE_MOVABLE:
virtio_mem_mb_set_state(vm, mb_id,
VIRTIO_MEM_MB_STATE_OFFLINE);
break;
default:
BUG();
break;
}
/* trigger the workqueue, maybe we can now unplug memory. */
virtio_mem_retry(vm);
}
static void virtio_mem_notify_online(struct virtio_mem *vm, unsigned long mb_id,
enum zone_type zone)
{
unsigned long nb_offline;
switch (virtio_mem_mb_get_state(vm, mb_id)) {
case VIRTIO_MEM_MB_STATE_OFFLINE_PARTIAL:
BUG_ON(zone == ZONE_MOVABLE);
virtio_mem_mb_set_state(vm, mb_id,
VIRTIO_MEM_MB_STATE_ONLINE_PARTIAL);
break;
case VIRTIO_MEM_MB_STATE_OFFLINE:
if (zone == ZONE_MOVABLE)
virtio_mem_mb_set_state(vm, mb_id,
VIRTIO_MEM_MB_STATE_ONLINE_MOVABLE);
else
virtio_mem_mb_set_state(vm, mb_id,
VIRTIO_MEM_MB_STATE_ONLINE);
break;
default:
BUG();
break;
}
nb_offline = vm->nb_mb_state[VIRTIO_MEM_MB_STATE_OFFLINE] +
vm->nb_mb_state[VIRTIO_MEM_MB_STATE_OFFLINE_PARTIAL];
/* see if we can add new blocks now that we onlined one block */
if (nb_offline == VIRTIO_MEM_NB_OFFLINE_THRESHOLD - 1)
virtio_mem_retry(vm);
}
/*
* This callback will either be called synchronously from add_memory() or
* asynchronously (e.g., triggered via user space). We have to be careful
* with locking when calling add_memory().
*/
static int virtio_mem_memory_notifier_cb(struct notifier_block *nb,
unsigned long action, void *arg)
{
struct virtio_mem *vm = container_of(nb, struct virtio_mem,
memory_notifier);
struct memory_notify *mhp = arg;
const unsigned long start = PFN_PHYS(mhp->start_pfn);
const unsigned long size = PFN_PHYS(mhp->nr_pages);
const unsigned long mb_id = virtio_mem_phys_to_mb_id(start);
enum zone_type zone;
int rc = NOTIFY_OK;
if (!virtio_mem_overlaps_range(vm, start, size))
return NOTIFY_DONE;
/*
* Memory is onlined/offlined in memory block granularity. We cannot
* cross virtio-mem device boundaries and memory block boundaries. Bail
* out if this ever changes.
*/
if (WARN_ON_ONCE(size != memory_block_size_bytes() ||
!IS_ALIGNED(start, memory_block_size_bytes())))
return NOTIFY_BAD;
/*
* Avoid circular locking lockdep warnings. We lock the mutex
* e.g., in MEM_GOING_ONLINE and unlock it in MEM_ONLINE. The
* blocking_notifier_call_chain() has it's own lock, which gets unlocked
* between both notifier calls and will bail out. False positive.
*/
lockdep_off();
switch (action) {
case MEM_GOING_OFFLINE:
mutex_lock(&vm->hotplug_mutex);
if (vm->removing) {
rc = notifier_from_errno(-EBUSY);
mutex_unlock(&vm->hotplug_mutex);
break;
}
vm->hotplug_active = true;
break;
case MEM_GOING_ONLINE:
mutex_lock(&vm->hotplug_mutex);
if (vm->removing) {
rc = notifier_from_errno(-EBUSY);
mutex_unlock(&vm->hotplug_mutex);
break;
}
vm->hotplug_active = true;
zone = page_zonenum(pfn_to_page(mhp->start_pfn));
rc = virtio_mem_notify_going_online(vm, mb_id, zone);
break;
case MEM_OFFLINE:
virtio_mem_notify_offline(vm, mb_id);
vm->hotplug_active = false;
mutex_unlock(&vm->hotplug_mutex);
break;
case MEM_ONLINE:
zone = page_zonenum(pfn_to_page(mhp->start_pfn));
virtio_mem_notify_online(vm, mb_id, zone);
vm->hotplug_active = false;
mutex_unlock(&vm->hotplug_mutex);
break;
case MEM_CANCEL_OFFLINE:
case MEM_CANCEL_ONLINE:
if (!vm->hotplug_active)
break;
vm->hotplug_active = false;
mutex_unlock(&vm->hotplug_mutex);
break;
default:
break;
}
lockdep_on();
return rc;
}
/*
* Set a range of pages PG_offline.
*/
static void virtio_mem_set_fake_offline(unsigned long pfn,
unsigned int nr_pages)
{
for (; nr_pages--; pfn++)
__SetPageOffline(pfn_to_page(pfn));
}
/*
* Clear PG_offline from a range of pages.
*/
static void virtio_mem_clear_fake_offline(unsigned long pfn,
unsigned int nr_pages)
{
for (; nr_pages--; pfn++)
__ClearPageOffline(pfn_to_page(pfn));
}
/*
* Release a range of fake-offline pages to the buddy, effectively
* fake-onlining them.
*/
static void virtio_mem_fake_online(unsigned long pfn, unsigned int nr_pages)
{
const int order = MAX_ORDER - 1;
int i;
/*
* We are always called with subblock granularity, which is at least
* aligned to MAX_ORDER - 1.
*/
virtio_mem_clear_fake_offline(pfn, nr_pages);
for (i = 0; i < nr_pages; i += 1 << order)
generic_online_page(pfn_to_page(pfn + i), order);
}
static void virtio_mem_online_page_cb(struct page *page, unsigned int order)
{
const unsigned long addr = page_to_phys(page);
const unsigned long mb_id = virtio_mem_phys_to_mb_id(addr);
struct virtio_mem *vm;
int sb_id;
/*
* We exploit here that subblocks have at least MAX_ORDER - 1
* size/alignment and that this callback is is called with such a
* size/alignment. So we cannot cross subblocks and therefore
* also not memory blocks.
*/
rcu_read_lock();
list_for_each_entry_rcu(vm, &virtio_mem_devices, next) {
if (!virtio_mem_owned_mb(vm, mb_id))
continue;
sb_id = virtio_mem_phys_to_sb_id(vm, addr);
/*
* If plugged, online the pages, otherwise, set them fake
* offline (PageOffline).
*/
if (virtio_mem_mb_test_sb_plugged(vm, mb_id, sb_id, 1))
generic_online_page(page, order);
else
virtio_mem_set_fake_offline(PFN_DOWN(addr), 1 << order);
rcu_read_unlock();
return;
}
rcu_read_unlock();
/* not virtio-mem memory, but e.g., a DIMM. online it */
generic_online_page(page, order);
}
static uint64_t virtio_mem_send_request(struct virtio_mem *vm,
const struct virtio_mem_req *req)
{
struct scatterlist *sgs[2], sg_req, sg_resp;
unsigned int len;
int rc;
/* don't use the request residing on the stack (vaddr) */
vm->req = *req;
/* out: buffer for request */
sg_init_one(&sg_req, &vm->req, sizeof(vm->req));
sgs[0] = &sg_req;
/* in: buffer for response */
sg_init_one(&sg_resp, &vm->resp, sizeof(vm->resp));
sgs[1] = &sg_resp;
rc = virtqueue_add_sgs(vm->vq, sgs, 1, 1, vm, GFP_KERNEL);
if (rc < 0)
return rc;
virtqueue_kick(vm->vq);
/* wait for a response */
wait_event(vm->host_resp, virtqueue_get_buf(vm->vq, &len));
return virtio16_to_cpu(vm->vdev, vm->resp.type);
}
static int virtio_mem_send_plug_request(struct virtio_mem *vm, uint64_t addr,
uint64_t size)
{
const uint64_t nb_vm_blocks = size / vm->device_block_size;
const struct virtio_mem_req req = {
.type = cpu_to_virtio16(vm->vdev, VIRTIO_MEM_REQ_PLUG),
.u.plug.addr = cpu_to_virtio64(vm->vdev, addr),
.u.plug.nb_blocks = cpu_to_virtio16(vm->vdev, nb_vm_blocks),
};
if (atomic_read(&vm->config_changed))
return -EAGAIN;
switch (virtio_mem_send_request(vm, &req)) {
case VIRTIO_MEM_RESP_ACK:
vm->plugged_size += size;
return 0;
case VIRTIO_MEM_RESP_NACK:
return -EAGAIN;
case VIRTIO_MEM_RESP_BUSY:
return -EBUSY;
case VIRTIO_MEM_RESP_ERROR:
return -EINVAL;
default:
return -ENOMEM;
}
}
static int virtio_mem_send_unplug_request(struct virtio_mem *vm, uint64_t addr,
uint64_t size)
{
const uint64_t nb_vm_blocks = size / vm->device_block_size;
const struct virtio_mem_req req = {
.type = cpu_to_virtio16(vm->vdev, VIRTIO_MEM_REQ_UNPLUG),
.u.unplug.addr = cpu_to_virtio64(vm->vdev, addr),
.u.unplug.nb_blocks = cpu_to_virtio16(vm->vdev, nb_vm_blocks),
};
if (atomic_read(&vm->config_changed))
return -EAGAIN;
switch (virtio_mem_send_request(vm, &req)) {
case VIRTIO_MEM_RESP_ACK:
vm->plugged_size -= size;
return 0;
case VIRTIO_MEM_RESP_BUSY:
return -EBUSY;
case VIRTIO_MEM_RESP_ERROR:
return -EINVAL;
default:
return -ENOMEM;
}
}
static int virtio_mem_send_unplug_all_request(struct virtio_mem *vm)
{
const struct virtio_mem_req req = {
.type = cpu_to_virtio16(vm->vdev, VIRTIO_MEM_REQ_UNPLUG_ALL),
};
switch (virtio_mem_send_request(vm, &req)) {
case VIRTIO_MEM_RESP_ACK:
vm->unplug_all_required = false;
vm->plugged_size = 0;
/* usable region might have shrunk */
atomic_set(&vm->config_changed, 1);
return 0;
case VIRTIO_MEM_RESP_BUSY:
return -EBUSY;
default:
return -ENOMEM;
}
}
/*
* Plug selected subblocks. Updates the plugged state, but not the state
* of the memory block.
*/
static int virtio_mem_mb_plug_sb(struct virtio_mem *vm, unsigned long mb_id,
int sb_id, int count)
{
const uint64_t addr = virtio_mem_mb_id_to_phys(mb_id) +
sb_id * vm->subblock_size;
const uint64_t size = count * vm->subblock_size;
int rc;
dev_dbg(&vm->vdev->dev, "plugging memory block: %lu : %i - %i\n", mb_id,
sb_id, sb_id + count - 1);
rc = virtio_mem_send_plug_request(vm, addr, size);
if (!rc)
virtio_mem_mb_set_sb_plugged(vm, mb_id, sb_id, count);
return rc;
}
/*
* Unplug selected subblocks. Updates the plugged state, but not the state
* of the memory block.
*/
static int virtio_mem_mb_unplug_sb(struct virtio_mem *vm, unsigned long mb_id,
int sb_id, int count)
{
const uint64_t addr = virtio_mem_mb_id_to_phys(mb_id) +
sb_id * vm->subblock_size;
const uint64_t size = count * vm->subblock_size;
int rc;
dev_dbg(&vm->vdev->dev, "unplugging memory block: %lu : %i - %i\n",
mb_id, sb_id, sb_id + count - 1);
rc = virtio_mem_send_unplug_request(vm, addr, size);
if (!rc)
virtio_mem_mb_set_sb_unplugged(vm, mb_id, sb_id, count);
return rc;
}
/*
* Unplug the desired number of plugged subblocks of a offline or not-added
* memory block. Will fail if any subblock cannot get unplugged (instead of
* skipping it).
*
* Will not modify the state of the memory block.
*
* Note: can fail after some subblocks were unplugged.
*/
static int virtio_mem_mb_unplug_any_sb(struct virtio_mem *vm,
unsigned long mb_id, uint64_t *nb_sb)
{
int sb_id, count;
int rc;
while (*nb_sb) {
sb_id = virtio_mem_mb_first_plugged_sb(vm, mb_id);
if (sb_id >= vm->nb_sb_per_mb)
break;
count = 1;
while (count < *nb_sb &&
sb_id + count < vm->nb_sb_per_mb &&
virtio_mem_mb_test_sb_plugged(vm, mb_id, sb_id + count,
1))
count++;
rc = virtio_mem_mb_unplug_sb(vm, mb_id, sb_id, count);
if (rc)
return rc;
*nb_sb -= count;
}
return 0;
}
/*
* Unplug all plugged subblocks of an offline or not-added memory block.
*
* Will not modify the state of the memory block.
*
* Note: can fail after some subblocks were unplugged.
*/
static int virtio_mem_mb_unplug(struct virtio_mem *vm, unsigned long mb_id)
{
uint64_t nb_sb = vm->nb_sb_per_mb;
return virtio_mem_mb_unplug_any_sb(vm, mb_id, &nb_sb);
}
/*
* Prepare tracking data for the next memory block.
*/
static int virtio_mem_prepare_next_mb(struct virtio_mem *vm,
unsigned long *mb_id)
{
int rc;
if (vm->next_mb_id > vm->last_usable_mb_id)
return -ENOSPC;
/* Resize the state array if required. */
rc = virtio_mem_mb_state_prepare_next_mb(vm);
if (rc)
return rc;
/* Resize the subblock bitmap if required. */
rc = virtio_mem_sb_bitmap_prepare_next_mb(vm);
if (rc)
return rc;
vm->nb_mb_state[VIRTIO_MEM_MB_STATE_UNUSED]++;
*mb_id = vm->next_mb_id++;
return 0;
}
/*
* Don't add too many blocks that are not onlined yet to avoid running OOM.
*/
static bool virtio_mem_too_many_mb_offline(struct virtio_mem *vm)
{
unsigned long nb_offline;
nb_offline = vm->nb_mb_state[VIRTIO_MEM_MB_STATE_OFFLINE] +
vm->nb_mb_state[VIRTIO_MEM_MB_STATE_OFFLINE_PARTIAL];
return nb_offline >= VIRTIO_MEM_NB_OFFLINE_THRESHOLD;
}
/*
* Try to plug the desired number of subblocks and add the memory block
* to Linux.
*
* Will modify the state of the memory block.
*/
static int virtio_mem_mb_plug_and_add(struct virtio_mem *vm,
unsigned long mb_id,
uint64_t *nb_sb)
{
const int count = min_t(int, *nb_sb, vm->nb_sb_per_mb);
int rc, rc2;
if (WARN_ON_ONCE(!count))
return -EINVAL;
/*
* Plug the requested number of subblocks before adding it to linux,
* so that onlining will directly online all plugged subblocks.
*/
rc = virtio_mem_mb_plug_sb(vm, mb_id, 0, count);
if (rc)
return rc;
/*
* Mark the block properly offline before adding it to Linux,
* so the memory notifiers will find the block in the right state.
*/
if (count == vm->nb_sb_per_mb)
virtio_mem_mb_set_state(vm, mb_id,
VIRTIO_MEM_MB_STATE_OFFLINE);
else
virtio_mem_mb_set_state(vm, mb_id,
VIRTIO_MEM_MB_STATE_OFFLINE_PARTIAL);
/* Add the memory block to linux - if that fails, try to unplug. */
rc = virtio_mem_mb_add(vm, mb_id);
if (rc) {
enum virtio_mem_mb_state new_state = VIRTIO_MEM_MB_STATE_UNUSED;
dev_err(&vm->vdev->dev,
"adding memory block %lu failed with %d\n", mb_id, rc);
rc2 = virtio_mem_mb_unplug_sb(vm, mb_id, 0, count);
/*
* TODO: Linux MM does not properly clean up yet in all cases
* where adding of memory failed - especially on -ENOMEM.
*/
if (rc2)
new_state = VIRTIO_MEM_MB_STATE_PLUGGED;
virtio_mem_mb_set_state(vm, mb_id, new_state);
return rc;
}
*nb_sb -= count;
return 0;
}
/*
* Try to plug the desired number of subblocks of a memory block that
* is already added to Linux.
*
* Will modify the state of the memory block.
*
* Note: Can fail after some subblocks were successfully plugged.
*/
static int virtio_mem_mb_plug_any_sb(struct virtio_mem *vm, unsigned long mb_id,
uint64_t *nb_sb, bool online)
{
unsigned long pfn, nr_pages;
int sb_id, count;
int rc;
if (WARN_ON_ONCE(!*nb_sb))
return -EINVAL;
while (*nb_sb) {
sb_id = virtio_mem_mb_first_unplugged_sb(vm, mb_id);
if (sb_id >= vm->nb_sb_per_mb)
break;
count = 1;
while (count < *nb_sb &&
sb_id + count < vm->nb_sb_per_mb &&
!virtio_mem_mb_test_sb_plugged(vm, mb_id, sb_id + count,
1))
count++;
rc = virtio_mem_mb_plug_sb(vm, mb_id, sb_id, count);
if (rc)
return rc;
*nb_sb -= count;
if (!online)
continue;
/* fake-online the pages if the memory block is online */
pfn = PFN_DOWN(virtio_mem_mb_id_to_phys(mb_id) +
sb_id * vm->subblock_size);
nr_pages = PFN_DOWN(count * vm->subblock_size);
virtio_mem_fake_online(pfn, nr_pages);
}
if (virtio_mem_mb_test_sb_plugged(vm, mb_id, 0, vm->nb_sb_per_mb)) {
if (online)
virtio_mem_mb_set_state(vm, mb_id,
VIRTIO_MEM_MB_STATE_ONLINE);
else
virtio_mem_mb_set_state(vm, mb_id,
VIRTIO_MEM_MB_STATE_OFFLINE);
}
return rc;
}
/*
* Try to plug the requested amount of memory.
*/
static int virtio_mem_plug_request(struct virtio_mem *vm, uint64_t diff)
{
uint64_t nb_sb = diff / vm->subblock_size;
unsigned long mb_id;
int rc;
if (!nb_sb)
return 0;
/* Don't race with onlining/offlining */
mutex_lock(&vm->hotplug_mutex);
/* Try to plug subblocks of partially plugged online blocks. */
virtio_mem_for_each_mb_state(vm, mb_id,
VIRTIO_MEM_MB_STATE_ONLINE_PARTIAL) {
rc = virtio_mem_mb_plug_any_sb(vm, mb_id, &nb_sb, true);
if (rc || !nb_sb)
goto out_unlock;
cond_resched();
}
/* Try to plug subblocks of partially plugged offline blocks. */
virtio_mem_for_each_mb_state(vm, mb_id,
VIRTIO_MEM_MB_STATE_OFFLINE_PARTIAL) {
rc = virtio_mem_mb_plug_any_sb(vm, mb_id, &nb_sb, false);
if (rc || !nb_sb)
goto out_unlock;
cond_resched();
}
/*
* We won't be working on online/offline memory blocks from this point,
* so we can't race with memory onlining/offlining. Drop the mutex.
*/
mutex_unlock(&vm->hotplug_mutex);
/* Try to plug and add unused blocks */
virtio_mem_for_each_mb_state(vm, mb_id, VIRTIO_MEM_MB_STATE_UNUSED) {
if (virtio_mem_too_many_mb_offline(vm))
return -ENOSPC;
rc = virtio_mem_mb_plug_and_add(vm, mb_id, &nb_sb);
if (rc || !nb_sb)
return rc;
cond_resched();
}
/* Try to prepare, plug and add new blocks */
while (nb_sb) {
if (virtio_mem_too_many_mb_offline(vm))
return -ENOSPC;
rc = virtio_mem_prepare_next_mb(vm, &mb_id);
if (rc)
return rc;
rc = virtio_mem_mb_plug_and_add(vm, mb_id, &nb_sb);
if (rc)
return rc;
cond_resched();
}
return 0;
out_unlock:
mutex_unlock(&vm->hotplug_mutex);
return rc;
}
/*
* Unplug the desired number of plugged subblocks of an offline memory block.
* Will fail if any subblock cannot get unplugged (instead of skipping it).
*
* Will modify the state of the memory block. Might temporarily drop the
* hotplug_mutex.
*
* Note: Can fail after some subblocks were successfully unplugged.
*/
static int virtio_mem_mb_unplug_any_sb_offline(struct virtio_mem *vm,
unsigned long mb_id,
uint64_t *nb_sb)
{
int rc;
rc = virtio_mem_mb_unplug_any_sb(vm, mb_id, nb_sb);
/* some subblocks might have been unplugged even on failure */
if (!virtio_mem_mb_test_sb_plugged(vm, mb_id, 0, vm->nb_sb_per_mb))
virtio_mem_mb_set_state(vm, mb_id,
VIRTIO_MEM_MB_STATE_OFFLINE_PARTIAL);
if (rc)
return rc;
if (virtio_mem_mb_test_sb_unplugged(vm, mb_id, 0, vm->nb_sb_per_mb)) {
/*
* Remove the block from Linux - this should never fail.
* Hinder the block from getting onlined by marking it
* unplugged. Temporarily drop the mutex, so
* any pending GOING_ONLINE requests can be serviced/rejected.
*/
virtio_mem_mb_set_state(vm, mb_id,
VIRTIO_MEM_MB_STATE_UNUSED);
mutex_unlock(&vm->hotplug_mutex);
rc = virtio_mem_mb_remove(vm, mb_id);
BUG_ON(rc);
mutex_lock(&vm->hotplug_mutex);
}
return 0;
}
/*
* Try to unplug the requested amount of memory.
*/
static int virtio_mem_unplug_request(struct virtio_mem *vm, uint64_t diff)
{
uint64_t nb_sb = diff / vm->subblock_size;
unsigned long mb_id;
int rc;
if (!nb_sb)
return 0;
/*
* We'll drop the mutex a couple of times when it is safe to do so.
* This might result in some blocks switching the state (online/offline)
* and we could miss them in this run - we will retry again later.
*/
mutex_lock(&vm->hotplug_mutex);
/* Try to unplug subblocks of partially plugged offline blocks. */
virtio_mem_for_each_mb_state_rev(vm, mb_id,
VIRTIO_MEM_MB_STATE_OFFLINE_PARTIAL) {
rc = virtio_mem_mb_unplug_any_sb_offline(vm, mb_id,
&nb_sb);
if (rc || !nb_sb)
goto out_unlock;
cond_resched();
}
/* Try to unplug subblocks of plugged offline blocks. */
virtio_mem_for_each_mb_state_rev(vm, mb_id,
VIRTIO_MEM_MB_STATE_OFFLINE) {
rc = virtio_mem_mb_unplug_any_sb_offline(vm, mb_id,
&nb_sb);
if (rc || !nb_sb)
goto out_unlock;
cond_resched();
}
mutex_unlock(&vm->hotplug_mutex);
return 0;
out_unlock:
mutex_unlock(&vm->hotplug_mutex);
return rc;
}
/*
* Try to unplug all blocks that couldn't be unplugged before, for example,
* because the hypervisor was busy.
*/
static int virtio_mem_unplug_pending_mb(struct virtio_mem *vm)
{
unsigned long mb_id;
int rc;
virtio_mem_for_each_mb_state(vm, mb_id, VIRTIO_MEM_MB_STATE_PLUGGED) {
rc = virtio_mem_mb_unplug(vm, mb_id);
if (rc)
return rc;
virtio_mem_mb_set_state(vm, mb_id, VIRTIO_MEM_MB_STATE_UNUSED);
}
return 0;
}
/*
* Update all parts of the config that could have changed.
*/
static void virtio_mem_refresh_config(struct virtio_mem *vm)
{
const uint64_t phys_limit = 1UL << MAX_PHYSMEM_BITS;
uint64_t new_plugged_size, usable_region_size, end_addr;
/* the plugged_size is just a reflection of what _we_ did previously */
virtio_cread(vm->vdev, struct virtio_mem_config, plugged_size,
&new_plugged_size);
if (WARN_ON_ONCE(new_plugged_size != vm->plugged_size))
vm->plugged_size = new_plugged_size;
/* calculate the last usable memory block id */
virtio_cread(vm->vdev, struct virtio_mem_config,
usable_region_size, &usable_region_size);
end_addr = vm->addr + usable_region_size;
end_addr = min(end_addr, phys_limit);
vm->last_usable_mb_id = virtio_mem_phys_to_mb_id(end_addr) - 1;
/* see if there is a request to change the size */
virtio_cread(vm->vdev, struct virtio_mem_config, requested_size,
&vm->requested_size);
dev_info(&vm->vdev->dev, "plugged size: 0x%llx", vm->plugged_size);
dev_info(&vm->vdev->dev, "requested size: 0x%llx", vm->requested_size);
}
/*
* Workqueue function for handling plug/unplug requests and config updates.
*/
static void virtio_mem_run_wq(struct work_struct *work)
{
struct virtio_mem *vm = container_of(work, struct virtio_mem, wq);
uint64_t diff;
int rc;
hrtimer_cancel(&vm->retry_timer);
if (vm->broken)
return;
retry:
rc = 0;
/* Make sure we start with a clean state if there are leftovers. */
if (unlikely(vm->unplug_all_required))
rc = virtio_mem_send_unplug_all_request(vm);
if (atomic_read(&vm->config_changed)) {
atomic_set(&vm->config_changed, 0);
virtio_mem_refresh_config(vm);
}
/* Unplug any leftovers from previous runs */
if (!rc)
rc = virtio_mem_unplug_pending_mb(vm);
if (!rc && vm->requested_size != vm->plugged_size) {
if (vm->requested_size > vm->plugged_size) {
diff = vm->requested_size - vm->plugged_size;
rc = virtio_mem_plug_request(vm, diff);
} else {
diff = vm->plugged_size - vm->requested_size;
rc = virtio_mem_unplug_request(vm, diff);
}
}
switch (rc) {
case 0:
break;
case -ENOSPC:
/*
* We cannot add any more memory (alignment, physical limit)
* or we have too many offline memory blocks.
*/
break;
case -EBUSY:
/*
* The hypervisor cannot process our request right now
* (e.g., out of memory, migrating).
*/
case -ENOMEM:
/* Out of memory, try again later. */
hrtimer_start(&vm->retry_timer,
ms_to_ktime(VIRTIO_MEM_RETRY_TIMER_MS),
HRTIMER_MODE_REL);
break;
case -EAGAIN:
/* Retry immediately (e.g., the config changed). */
goto retry;
default:
/* Unknown error, mark as broken */
dev_err(&vm->vdev->dev,
"unknown error, marking device broken: %d\n", rc);
vm->broken = true;
}
}
static enum hrtimer_restart virtio_mem_timer_expired(struct hrtimer *timer)
{
struct virtio_mem *vm = container_of(timer, struct virtio_mem,
retry_timer);
virtio_mem_retry(vm);
return HRTIMER_NORESTART;
}
static void virtio_mem_handle_response(struct virtqueue *vq)
{
struct virtio_mem *vm = vq->vdev->priv;
wake_up(&vm->host_resp);
}
static int virtio_mem_init_vq(struct virtio_mem *vm)
{
struct virtqueue *vq;
vq = virtio_find_single_vq(vm->vdev, virtio_mem_handle_response,
"guest-request");
if (IS_ERR(vq))
return PTR_ERR(vq);
vm->vq = vq;
return 0;
}
/*
* Test if any memory in the range is present in Linux.
*/
static bool virtio_mem_any_memory_present(unsigned long start,
unsigned long size)
{
const unsigned long start_pfn = PFN_DOWN(start);
const unsigned long end_pfn = PFN_UP(start + size);
unsigned long pfn;
for (pfn = start_pfn; pfn != end_pfn; pfn++)
if (present_section_nr(pfn_to_section_nr(pfn)))
return true;
return false;
}
static int virtio_mem_init(struct virtio_mem *vm)
{
const uint64_t phys_limit = 1UL << MAX_PHYSMEM_BITS;
uint16_t node_id;
if (!vm->vdev->config->get) {
dev_err(&vm->vdev->dev, "config access disabled\n");
return -EINVAL;
}
/*
* We don't want to (un)plug or reuse any memory when in kdump. The
* memory is still accessible (but not mapped).
*/
if (is_kdump_kernel()) {
dev_warn(&vm->vdev->dev, "disabled in kdump kernel\n");
return -EBUSY;
}
/* Fetch all properties that can't change. */
virtio_cread(vm->vdev, struct virtio_mem_config, plugged_size,
&vm->plugged_size);
virtio_cread(vm->vdev, struct virtio_mem_config, block_size,
&vm->device_block_size);
virtio_cread(vm->vdev, struct virtio_mem_config, node_id,
&node_id);
vm->nid = virtio_mem_translate_node_id(vm, node_id);
virtio_cread(vm->vdev, struct virtio_mem_config, addr, &vm->addr);
virtio_cread(vm->vdev, struct virtio_mem_config, region_size,
&vm->region_size);
/*
* If we still have memory plugged, we might have to unplug all
* memory first. However, if somebody simply unloaded the driver
* we would have to reinitialize the old state - something we don't
* support yet. Detect if we have any memory in the area present.
*/
if (vm->plugged_size) {
uint64_t usable_region_size;
virtio_cread(vm->vdev, struct virtio_mem_config,
usable_region_size, &usable_region_size);
if (virtio_mem_any_memory_present(vm->addr,
usable_region_size)) {
dev_err(&vm->vdev->dev,
"reloading the driver is not supported\n");
return -EINVAL;
}
/*
* Note: it might happen that the device is busy and
* unplugging all memory might take some time.
*/
dev_info(&vm->vdev->dev, "unplugging all memory required\n");
vm->unplug_all_required = 1;
}
/*
* We always hotplug memory in memory block granularity. This way,
* we have to wait for exactly one memory block to online.
*/
if (vm->device_block_size > memory_block_size_bytes()) {
dev_err(&vm->vdev->dev,
"The block size is not supported (too big).\n");
return -EINVAL;
}
/* bad device setup - warn only */
if (!IS_ALIGNED(vm->addr, memory_block_size_bytes()))
dev_warn(&vm->vdev->dev,
"The alignment of the physical start address can make some memory unusable.\n");
if (!IS_ALIGNED(vm->addr + vm->region_size, memory_block_size_bytes()))
dev_warn(&vm->vdev->dev,
"The alignment of the physical end address can make some memory unusable.\n");
if (vm->addr + vm->region_size > phys_limit)
dev_warn(&vm->vdev->dev,
"Some memory is not addressable. This can make some memory unusable.\n");
/*
* Calculate the subblock size:
* - At least MAX_ORDER - 1 / pageblock_order.
* - At least the device block size.
* In the worst case, a single subblock per memory block.
*/
vm->subblock_size = PAGE_SIZE * 1u << max_t(uint32_t, MAX_ORDER - 1,
pageblock_order);
vm->subblock_size = max_t(uint32_t, vm->device_block_size,
vm->subblock_size);
vm->nb_sb_per_mb = memory_block_size_bytes() / vm->subblock_size;
/* Round up to the next full memory block */
vm->first_mb_id = virtio_mem_phys_to_mb_id(vm->addr - 1 +
memory_block_size_bytes());
vm->next_mb_id = vm->first_mb_id;
vm->last_mb_id = virtio_mem_phys_to_mb_id(vm->addr +
vm->region_size) - 1;
dev_info(&vm->vdev->dev, "start address: 0x%llx", vm->addr);
dev_info(&vm->vdev->dev, "region size: 0x%llx", vm->region_size);
dev_info(&vm->vdev->dev, "device block size: 0x%x",
vm->device_block_size);
dev_info(&vm->vdev->dev, "memory block size: 0x%lx",
memory_block_size_bytes());
dev_info(&vm->vdev->dev, "subblock size: 0x%x",
vm->subblock_size);
if (vm->nid != NUMA_NO_NODE)
dev_info(&vm->vdev->dev, "nid: %d", vm->nid);
return 0;
}
static int virtio_mem_probe(struct virtio_device *vdev)
{
struct virtio_mem *vm;
int rc = -EINVAL;
vdev->priv = vm = kzalloc(sizeof(*vm), GFP_KERNEL);
if (!vm)
return -ENOMEM;
init_waitqueue_head(&vm->host_resp);
vm->vdev = vdev;
INIT_WORK(&vm->wq, virtio_mem_run_wq);
mutex_init(&vm->hotplug_mutex);
INIT_LIST_HEAD(&vm->next);
spin_lock_init(&vm->removal_lock);
hrtimer_init(&vm->retry_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
vm->retry_timer.function = virtio_mem_timer_expired;
/* register the virtqueue */
rc = virtio_mem_init_vq(vm);
if (rc)
goto out_free_vm;
/* initialize the device by querying the config */
rc = virtio_mem_init(vm);
if (rc)
goto out_del_vq;
/* register callbacks */
vm->memory_notifier.notifier_call = virtio_mem_memory_notifier_cb;
rc = register_memory_notifier(&vm->memory_notifier);
if (rc)
goto out_del_vq;
rc = register_virtio_mem_device(vm);
if (rc)
goto out_unreg_mem;
virtio_device_ready(vdev);
/* trigger a config update to start processing the requested_size */
atomic_set(&vm->config_changed, 1);
queue_work(system_freezable_wq, &vm->wq);
return 0;
out_unreg_mem:
unregister_memory_notifier(&vm->memory_notifier);
out_del_vq:
vdev->config->del_vqs(vdev);
out_free_vm:
kfree(vm);
vdev->priv = NULL;
return rc;
}
static void virtio_mem_remove(struct virtio_device *vdev)
{
struct virtio_mem *vm = vdev->priv;
unsigned long mb_id;
int rc;
/*
* Make sure the workqueue won't be triggered anymore and no memory
* blocks can be onlined/offlined until we're finished here.
*/
mutex_lock(&vm->hotplug_mutex);
spin_lock_irq(&vm->removal_lock);
vm->removing = true;
spin_unlock_irq(&vm->removal_lock);
mutex_unlock(&vm->hotplug_mutex);
/* wait until the workqueue stopped */
cancel_work_sync(&vm->wq);
hrtimer_cancel(&vm->retry_timer);
/*
* After we unregistered our callbacks, user space can online partially
* plugged offline blocks. Make sure to remove them.
*/
virtio_mem_for_each_mb_state(vm, mb_id,
VIRTIO_MEM_MB_STATE_OFFLINE_PARTIAL) {
rc = virtio_mem_mb_remove(vm, mb_id);
BUG_ON(rc);
virtio_mem_mb_set_state(vm, mb_id, VIRTIO_MEM_MB_STATE_UNUSED);
}
/* unregister callbacks */
unregister_virtio_mem_device(vm);
unregister_memory_notifier(&vm->memory_notifier);
/*
* There is no way we could reliably remove all memory we have added to
* the system. And there is no way to stop the driver/device from going
* away. Warn at least.
*/
if (vm->nb_mb_state[VIRTIO_MEM_MB_STATE_OFFLINE] ||
vm->nb_mb_state[VIRTIO_MEM_MB_STATE_OFFLINE_PARTIAL] ||
vm->nb_mb_state[VIRTIO_MEM_MB_STATE_ONLINE] ||
vm->nb_mb_state[VIRTIO_MEM_MB_STATE_ONLINE_PARTIAL] ||
vm->nb_mb_state[VIRTIO_MEM_MB_STATE_ONLINE_MOVABLE])
dev_warn(&vdev->dev, "device still has system memory added\n");
/* remove all tracking data - no locking needed */
vfree(vm->mb_state);
vfree(vm->sb_bitmap);
/* reset the device and cleanup the queues */
vdev->config->reset(vdev);
vdev->config->del_vqs(vdev);
kfree(vm);
vdev->priv = NULL;
}
static void virtio_mem_config_changed(struct virtio_device *vdev)
{
struct virtio_mem *vm = vdev->priv;
atomic_set(&vm->config_changed, 1);
virtio_mem_retry(vm);
}
#ifdef CONFIG_PM_SLEEP
static int virtio_mem_freeze(struct virtio_device *vdev)
{
/*
* When restarting the VM, all memory is usually unplugged. Don't
* allow to suspend/hibernate.
*/
dev_err(&vdev->dev, "save/restore not supported.\n");
return -EPERM;
}
static int virtio_mem_restore(struct virtio_device *vdev)
{
return -EPERM;
}
#endif
static unsigned int virtio_mem_features[] = {
#if defined(CONFIG_NUMA) && defined(CONFIG_ACPI_NUMA)
VIRTIO_MEM_F_ACPI_PXM,
#endif
};
static struct virtio_device_id virtio_mem_id_table[] = {
{ VIRTIO_ID_MEM, VIRTIO_DEV_ANY_ID },
{ 0 },
};
static struct virtio_driver virtio_mem_driver = {
.feature_table = virtio_mem_features,
.feature_table_size = ARRAY_SIZE(virtio_mem_features),
.driver.name = KBUILD_MODNAME,
.driver.owner = THIS_MODULE,
.id_table = virtio_mem_id_table,
.probe = virtio_mem_probe,
.remove = virtio_mem_remove,
.config_changed = virtio_mem_config_changed,
#ifdef CONFIG_PM_SLEEP
.freeze = virtio_mem_freeze,
.restore = virtio_mem_restore,
#endif
};
module_virtio_driver(virtio_mem_driver);
MODULE_DEVICE_TABLE(virtio, virtio_mem_id_table);
MODULE_AUTHOR("David Hildenbrand <david@redhat.com>");
MODULE_DESCRIPTION("Virtio-mem driver");
MODULE_LICENSE("GPL");
|