forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
memory_hotplug.c
1812 lines (1523 loc) · 45.5 KB
/
memory_hotplug.c
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
/*
* linux/mm/memory_hotplug.c
*
* Copyright (C)
*/
#include <linux/stddef.h>
#include <linux/mm.h>
#include <linux/swap.h>
#include <linux/interrupt.h>
#include <linux/pagemap.h>
#include <linux/bootmem.h>
#include <linux/compiler.h>
#include <linux/export.h>
#include <linux/pagevec.h>
#include <linux/writeback.h>
#include <linux/slab.h>
#include <linux/sysctl.h>
#include <linux/cpu.h>
#include <linux/memory.h>
#include <linux/memory_hotplug.h>
#include <linux/highmem.h>
#include <linux/vmalloc.h>
#include <linux/ioport.h>
#include <linux/delay.h>
#include <linux/migrate.h>
#include <linux/page-isolation.h>
#include <linux/pfn.h>
#include <linux/suspend.h>
#include <linux/mm_inline.h>
#include <linux/firmware-map.h>
#include <linux/stop_machine.h>
#include <asm/tlbflush.h>
#include "internal.h"
/*
* online_page_callback contains pointer to current page onlining function.
* Initially it is generic_online_page(). If it is required it could be
* changed by calling set_online_page_callback() for callback registration
* and restore_online_page_callback() for generic callback restore.
*/
static void generic_online_page(struct page *page);
static online_page_callback_t online_page_callback = generic_online_page;
DEFINE_MUTEX(mem_hotplug_mutex);
void lock_memory_hotplug(void)
{
mutex_lock(&mem_hotplug_mutex);
/* for exclusive hibernation if CONFIG_HIBERNATION=y */
lock_system_sleep();
}
void unlock_memory_hotplug(void)
{
unlock_system_sleep();
mutex_unlock(&mem_hotplug_mutex);
}
/* add this memory to iomem resource */
static struct resource *register_memory_resource(u64 start, u64 size)
{
struct resource *res;
res = kzalloc(sizeof(struct resource), GFP_KERNEL);
BUG_ON(!res);
res->name = "System RAM";
res->start = start;
res->end = start + size - 1;
res->flags = IORESOURCE_MEM | IORESOURCE_BUSY;
if (request_resource(&iomem_resource, res) < 0) {
pr_debug("System RAM resource %pR cannot be added\n", res);
kfree(res);
res = NULL;
}
return res;
}
static void release_memory_resource(struct resource *res)
{
if (!res)
return;
release_resource(res);
kfree(res);
return;
}
#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE
void get_page_bootmem(unsigned long info, struct page *page,
unsigned long type)
{
page->lru.next = (struct list_head *) type;
SetPagePrivate(page);
set_page_private(page, info);
atomic_inc(&page->_count);
}
void put_page_bootmem(struct page *page)
{
unsigned long type;
type = (unsigned long) page->lru.next;
BUG_ON(type < MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE ||
type > MEMORY_HOTPLUG_MAX_BOOTMEM_TYPE);
if (atomic_dec_return(&page->_count) == 1) {
ClearPagePrivate(page);
set_page_private(page, 0);
INIT_LIST_HEAD(&page->lru);
free_reserved_page(page);
}
}
#ifdef CONFIG_HAVE_BOOTMEM_INFO_NODE
#ifndef CONFIG_SPARSEMEM_VMEMMAP
static void register_page_bootmem_info_section(unsigned long start_pfn)
{
unsigned long *usemap, mapsize, section_nr, i;
struct mem_section *ms;
struct page *page, *memmap;
section_nr = pfn_to_section_nr(start_pfn);
ms = __nr_to_section(section_nr);
/* Get section's memmap address */
memmap = sparse_decode_mem_map(ms->section_mem_map, section_nr);
/*
* Get page for the memmap's phys address
* XXX: need more consideration for sparse_vmemmap...
*/
page = virt_to_page(memmap);
mapsize = sizeof(struct page) * PAGES_PER_SECTION;
mapsize = PAGE_ALIGN(mapsize) >> PAGE_SHIFT;
/* remember memmap's page */
for (i = 0; i < mapsize; i++, page++)
get_page_bootmem(section_nr, page, SECTION_INFO);
usemap = __nr_to_section(section_nr)->pageblock_flags;
page = virt_to_page(usemap);
mapsize = PAGE_ALIGN(usemap_size()) >> PAGE_SHIFT;
for (i = 0; i < mapsize; i++, page++)
get_page_bootmem(section_nr, page, MIX_SECTION_INFO);
}
#else /* CONFIG_SPARSEMEM_VMEMMAP */
static void register_page_bootmem_info_section(unsigned long start_pfn)
{
unsigned long *usemap, mapsize, section_nr, i;
struct mem_section *ms;
struct page *page, *memmap;
if (!pfn_valid(start_pfn))
return;
section_nr = pfn_to_section_nr(start_pfn);
ms = __nr_to_section(section_nr);
memmap = sparse_decode_mem_map(ms->section_mem_map, section_nr);
register_page_bootmem_memmap(section_nr, memmap, PAGES_PER_SECTION);
usemap = __nr_to_section(section_nr)->pageblock_flags;
page = virt_to_page(usemap);
mapsize = PAGE_ALIGN(usemap_size()) >> PAGE_SHIFT;
for (i = 0; i < mapsize; i++, page++)
get_page_bootmem(section_nr, page, MIX_SECTION_INFO);
}
#endif /* !CONFIG_SPARSEMEM_VMEMMAP */
void register_page_bootmem_info_node(struct pglist_data *pgdat)
{
unsigned long i, pfn, end_pfn, nr_pages;
int node = pgdat->node_id;
struct page *page;
struct zone *zone;
nr_pages = PAGE_ALIGN(sizeof(struct pglist_data)) >> PAGE_SHIFT;
page = virt_to_page(pgdat);
for (i = 0; i < nr_pages; i++, page++)
get_page_bootmem(node, page, NODE_INFO);
zone = &pgdat->node_zones[0];
for (; zone < pgdat->node_zones + MAX_NR_ZONES - 1; zone++) {
if (zone->wait_table) {
nr_pages = zone->wait_table_hash_nr_entries
* sizeof(wait_queue_head_t);
nr_pages = PAGE_ALIGN(nr_pages) >> PAGE_SHIFT;
page = virt_to_page(zone->wait_table);
for (i = 0; i < nr_pages; i++, page++)
get_page_bootmem(node, page, NODE_INFO);
}
}
pfn = pgdat->node_start_pfn;
end_pfn = pgdat_end_pfn(pgdat);
/* register section info */
for (; pfn < end_pfn; pfn += PAGES_PER_SECTION) {
/*
* Some platforms can assign the same pfn to multiple nodes - on
* node0 as well as nodeN. To avoid registering a pfn against
* multiple nodes we check that this pfn does not already
* reside in some other nodes.
*/
if (pfn_valid(pfn) && (pfn_to_nid(pfn) == node))
register_page_bootmem_info_section(pfn);
}
}
#endif /* CONFIG_HAVE_BOOTMEM_INFO_NODE */
static void grow_zone_span(struct zone *zone, unsigned long start_pfn,
unsigned long end_pfn)
{
unsigned long old_zone_end_pfn;
zone_span_writelock(zone);
old_zone_end_pfn = zone->zone_start_pfn + zone->spanned_pages;
if (!zone->spanned_pages || start_pfn < zone->zone_start_pfn)
zone->zone_start_pfn = start_pfn;
zone->spanned_pages = max(old_zone_end_pfn, end_pfn) -
zone->zone_start_pfn;
zone_span_writeunlock(zone);
}
static void resize_zone(struct zone *zone, unsigned long start_pfn,
unsigned long end_pfn)
{
zone_span_writelock(zone);
if (end_pfn - start_pfn) {
zone->zone_start_pfn = start_pfn;
zone->spanned_pages = end_pfn - start_pfn;
} else {
/*
* make it consist as free_area_init_core(),
* if spanned_pages = 0, then keep start_pfn = 0
*/
zone->zone_start_pfn = 0;
zone->spanned_pages = 0;
}
zone_span_writeunlock(zone);
}
static void fix_zone_id(struct zone *zone, unsigned long start_pfn,
unsigned long end_pfn)
{
enum zone_type zid = zone_idx(zone);
int nid = zone->zone_pgdat->node_id;
unsigned long pfn;
for (pfn = start_pfn; pfn < end_pfn; pfn++)
set_page_links(pfn_to_page(pfn), zid, nid, pfn);
}
/* Can fail with -ENOMEM from allocating a wait table with vmalloc() or
* alloc_bootmem_node_nopanic() */
static int __ref ensure_zone_is_initialized(struct zone *zone,
unsigned long start_pfn, unsigned long num_pages)
{
if (!zone_is_initialized(zone))
return init_currently_empty_zone(zone, start_pfn, num_pages,
MEMMAP_HOTPLUG);
return 0;
}
static int __meminit move_pfn_range_left(struct zone *z1, struct zone *z2,
unsigned long start_pfn, unsigned long end_pfn)
{
int ret;
unsigned long flags;
unsigned long z1_start_pfn;
ret = ensure_zone_is_initialized(z1, start_pfn, end_pfn - start_pfn);
if (ret)
return ret;
pgdat_resize_lock(z1->zone_pgdat, &flags);
/* can't move pfns which are higher than @z2 */
if (end_pfn > zone_end_pfn(z2))
goto out_fail;
/* the move out part must be at the left most of @z2 */
if (start_pfn > z2->zone_start_pfn)
goto out_fail;
/* must included/overlap */
if (end_pfn <= z2->zone_start_pfn)
goto out_fail;
/* use start_pfn for z1's start_pfn if z1 is empty */
if (z1->spanned_pages)
z1_start_pfn = z1->zone_start_pfn;
else
z1_start_pfn = start_pfn;
resize_zone(z1, z1_start_pfn, end_pfn);
resize_zone(z2, end_pfn, zone_end_pfn(z2));
pgdat_resize_unlock(z1->zone_pgdat, &flags);
fix_zone_id(z1, start_pfn, end_pfn);
return 0;
out_fail:
pgdat_resize_unlock(z1->zone_pgdat, &flags);
return -1;
}
static int __meminit move_pfn_range_right(struct zone *z1, struct zone *z2,
unsigned long start_pfn, unsigned long end_pfn)
{
int ret;
unsigned long flags;
unsigned long z2_end_pfn;
ret = ensure_zone_is_initialized(z2, start_pfn, end_pfn - start_pfn);
if (ret)
return ret;
pgdat_resize_lock(z1->zone_pgdat, &flags);
/* can't move pfns which are lower than @z1 */
if (z1->zone_start_pfn > start_pfn)
goto out_fail;
/* the move out part mast at the right most of @z1 */
if (zone_end_pfn(z1) > end_pfn)
goto out_fail;
/* must included/overlap */
if (start_pfn >= zone_end_pfn(z1))
goto out_fail;
/* use end_pfn for z2's end_pfn if z2 is empty */
if (z2->spanned_pages)
z2_end_pfn = zone_end_pfn(z2);
else
z2_end_pfn = end_pfn;
resize_zone(z1, z1->zone_start_pfn, start_pfn);
resize_zone(z2, start_pfn, z2_end_pfn);
pgdat_resize_unlock(z1->zone_pgdat, &flags);
fix_zone_id(z2, start_pfn, end_pfn);
return 0;
out_fail:
pgdat_resize_unlock(z1->zone_pgdat, &flags);
return -1;
}
static void grow_pgdat_span(struct pglist_data *pgdat, unsigned long start_pfn,
unsigned long end_pfn)
{
unsigned long old_pgdat_end_pfn =
pgdat->node_start_pfn + pgdat->node_spanned_pages;
if (!pgdat->node_spanned_pages || start_pfn < pgdat->node_start_pfn)
pgdat->node_start_pfn = start_pfn;
pgdat->node_spanned_pages = max(old_pgdat_end_pfn, end_pfn) -
pgdat->node_start_pfn;
}
static int __meminit __add_zone(struct zone *zone, unsigned long phys_start_pfn)
{
struct pglist_data *pgdat = zone->zone_pgdat;
int nr_pages = PAGES_PER_SECTION;
int nid = pgdat->node_id;
int zone_type;
unsigned long flags;
int ret;
zone_type = zone - pgdat->node_zones;
ret = ensure_zone_is_initialized(zone, phys_start_pfn, nr_pages);
if (ret)
return ret;
pgdat_resize_lock(zone->zone_pgdat, &flags);
grow_zone_span(zone, phys_start_pfn, phys_start_pfn + nr_pages);
grow_pgdat_span(zone->zone_pgdat, phys_start_pfn,
phys_start_pfn + nr_pages);
pgdat_resize_unlock(zone->zone_pgdat, &flags);
memmap_init_zone(nr_pages, nid, zone_type,
phys_start_pfn, MEMMAP_HOTPLUG);
return 0;
}
static int __meminit __add_section(int nid, struct zone *zone,
unsigned long phys_start_pfn)
{
int nr_pages = PAGES_PER_SECTION;
int ret;
if (pfn_valid(phys_start_pfn))
return -EEXIST;
ret = sparse_add_one_section(zone, phys_start_pfn, nr_pages);
if (ret < 0)
return ret;
ret = __add_zone(zone, phys_start_pfn);
if (ret < 0)
return ret;
return register_new_memory(nid, __pfn_to_section(phys_start_pfn));
}
/*
* Reasonably generic function for adding memory. It is
* expected that archs that support memory hotplug will
* call this function after deciding the zone to which to
* add the new pages.
*/
int __ref __add_pages(int nid, struct zone *zone, unsigned long phys_start_pfn,
unsigned long nr_pages)
{
unsigned long i;
int err = 0;
int start_sec, end_sec;
/* during initialize mem_map, align hot-added range to section */
start_sec = pfn_to_section_nr(phys_start_pfn);
end_sec = pfn_to_section_nr(phys_start_pfn + nr_pages - 1);
for (i = start_sec; i <= end_sec; i++) {
err = __add_section(nid, zone, i << PFN_SECTION_SHIFT);
/*
* EEXIST is finally dealt with by ioresource collision
* check. see add_memory() => register_memory_resource()
* Warning will be printed if there is collision.
*/
if (err && (err != -EEXIST))
break;
err = 0;
}
return err;
}
EXPORT_SYMBOL_GPL(__add_pages);
#ifdef CONFIG_MEMORY_HOTREMOVE
/* find the smallest valid pfn in the range [start_pfn, end_pfn) */
static int find_smallest_section_pfn(int nid, struct zone *zone,
unsigned long start_pfn,
unsigned long end_pfn)
{
struct mem_section *ms;
for (; start_pfn < end_pfn; start_pfn += PAGES_PER_SECTION) {
ms = __pfn_to_section(start_pfn);
if (unlikely(!valid_section(ms)))
continue;
if (unlikely(pfn_to_nid(start_pfn) != nid))
continue;
if (zone && zone != page_zone(pfn_to_page(start_pfn)))
continue;
return start_pfn;
}
return 0;
}
/* find the biggest valid pfn in the range [start_pfn, end_pfn). */
static int find_biggest_section_pfn(int nid, struct zone *zone,
unsigned long start_pfn,
unsigned long end_pfn)
{
struct mem_section *ms;
unsigned long pfn;
/* pfn is the end pfn of a memory section. */
pfn = end_pfn - 1;
for (; pfn >= start_pfn; pfn -= PAGES_PER_SECTION) {
ms = __pfn_to_section(pfn);
if (unlikely(!valid_section(ms)))
continue;
if (unlikely(pfn_to_nid(pfn) != nid))
continue;
if (zone && zone != page_zone(pfn_to_page(pfn)))
continue;
return pfn;
}
return 0;
}
static void shrink_zone_span(struct zone *zone, unsigned long start_pfn,
unsigned long end_pfn)
{
unsigned long zone_start_pfn = zone->zone_start_pfn;
unsigned long zone_end_pfn = zone->zone_start_pfn + zone->spanned_pages;
unsigned long pfn;
struct mem_section *ms;
int nid = zone_to_nid(zone);
zone_span_writelock(zone);
if (zone_start_pfn == start_pfn) {
/*
* If the section is smallest section in the zone, it need
* shrink zone->zone_start_pfn and zone->zone_spanned_pages.
* In this case, we find second smallest valid mem_section
* for shrinking zone.
*/
pfn = find_smallest_section_pfn(nid, zone, end_pfn,
zone_end_pfn);
if (pfn) {
zone->zone_start_pfn = pfn;
zone->spanned_pages = zone_end_pfn - pfn;
}
} else if (zone_end_pfn == end_pfn) {
/*
* If the section is biggest section in the zone, it need
* shrink zone->spanned_pages.
* In this case, we find second biggest valid mem_section for
* shrinking zone.
*/
pfn = find_biggest_section_pfn(nid, zone, zone_start_pfn,
start_pfn);
if (pfn)
zone->spanned_pages = pfn - zone_start_pfn + 1;
}
/*
* The section is not biggest or smallest mem_section in the zone, it
* only creates a hole in the zone. So in this case, we need not
* change the zone. But perhaps, the zone has only hole data. Thus
* it check the zone has only hole or not.
*/
pfn = zone_start_pfn;
for (; pfn < zone_end_pfn; pfn += PAGES_PER_SECTION) {
ms = __pfn_to_section(pfn);
if (unlikely(!valid_section(ms)))
continue;
if (page_zone(pfn_to_page(pfn)) != zone)
continue;
/* If the section is current section, it continues the loop */
if (start_pfn == pfn)
continue;
/* If we find valid section, we have nothing to do */
zone_span_writeunlock(zone);
return;
}
/* The zone has no valid section */
zone->zone_start_pfn = 0;
zone->spanned_pages = 0;
zone_span_writeunlock(zone);
}
static void shrink_pgdat_span(struct pglist_data *pgdat,
unsigned long start_pfn, unsigned long end_pfn)
{
unsigned long pgdat_start_pfn = pgdat->node_start_pfn;
unsigned long pgdat_end_pfn =
pgdat->node_start_pfn + pgdat->node_spanned_pages;
unsigned long pfn;
struct mem_section *ms;
int nid = pgdat->node_id;
if (pgdat_start_pfn == start_pfn) {
/*
* If the section is smallest section in the pgdat, it need
* shrink pgdat->node_start_pfn and pgdat->node_spanned_pages.
* In this case, we find second smallest valid mem_section
* for shrinking zone.
*/
pfn = find_smallest_section_pfn(nid, NULL, end_pfn,
pgdat_end_pfn);
if (pfn) {
pgdat->node_start_pfn = pfn;
pgdat->node_spanned_pages = pgdat_end_pfn - pfn;
}
} else if (pgdat_end_pfn == end_pfn) {
/*
* If the section is biggest section in the pgdat, it need
* shrink pgdat->node_spanned_pages.
* In this case, we find second biggest valid mem_section for
* shrinking zone.
*/
pfn = find_biggest_section_pfn(nid, NULL, pgdat_start_pfn,
start_pfn);
if (pfn)
pgdat->node_spanned_pages = pfn - pgdat_start_pfn + 1;
}
/*
* If the section is not biggest or smallest mem_section in the pgdat,
* it only creates a hole in the pgdat. So in this case, we need not
* change the pgdat.
* But perhaps, the pgdat has only hole data. Thus it check the pgdat
* has only hole or not.
*/
pfn = pgdat_start_pfn;
for (; pfn < pgdat_end_pfn; pfn += PAGES_PER_SECTION) {
ms = __pfn_to_section(pfn);
if (unlikely(!valid_section(ms)))
continue;
if (pfn_to_nid(pfn) != nid)
continue;
/* If the section is current section, it continues the loop */
if (start_pfn == pfn)
continue;
/* If we find valid section, we have nothing to do */
return;
}
/* The pgdat has no valid section */
pgdat->node_start_pfn = 0;
pgdat->node_spanned_pages = 0;
}
static void __remove_zone(struct zone *zone, unsigned long start_pfn)
{
struct pglist_data *pgdat = zone->zone_pgdat;
int nr_pages = PAGES_PER_SECTION;
int zone_type;
unsigned long flags;
zone_type = zone - pgdat->node_zones;
pgdat_resize_lock(zone->zone_pgdat, &flags);
shrink_zone_span(zone, start_pfn, start_pfn + nr_pages);
shrink_pgdat_span(pgdat, start_pfn, start_pfn + nr_pages);
pgdat_resize_unlock(zone->zone_pgdat, &flags);
}
static int __remove_section(struct zone *zone, struct mem_section *ms)
{
unsigned long start_pfn;
int scn_nr;
int ret = -EINVAL;
if (!valid_section(ms))
return ret;
ret = unregister_memory_section(ms);
if (ret)
return ret;
scn_nr = __section_nr(ms);
start_pfn = section_nr_to_pfn(scn_nr);
__remove_zone(zone, start_pfn);
sparse_remove_one_section(zone, ms);
return 0;
}
/**
* __remove_pages() - remove sections of pages from a zone
* @zone: zone from which pages need to be removed
* @phys_start_pfn: starting pageframe (must be aligned to start of a section)
* @nr_pages: number of pages to remove (must be multiple of section size)
*
* Generic helper function to remove section mappings and sysfs entries
* for the section of the memory we are removing. Caller needs to make
* sure that pages are marked reserved and zones are adjust properly by
* calling offline_pages().
*/
int __remove_pages(struct zone *zone, unsigned long phys_start_pfn,
unsigned long nr_pages)
{
unsigned long i;
int sections_to_remove;
resource_size_t start, size;
int ret = 0;
/*
* We can only remove entire sections
*/
BUG_ON(phys_start_pfn & ~PAGE_SECTION_MASK);
BUG_ON(nr_pages % PAGES_PER_SECTION);
start = phys_start_pfn << PAGE_SHIFT;
size = nr_pages * PAGE_SIZE;
ret = release_mem_region_adjustable(&iomem_resource, start, size);
if (ret) {
resource_size_t endres = start + size - 1;
pr_warn("Unable to release resource <%pa-%pa> (%d)\n",
&start, &endres, ret);
}
sections_to_remove = nr_pages / PAGES_PER_SECTION;
for (i = 0; i < sections_to_remove; i++) {
unsigned long pfn = phys_start_pfn + i*PAGES_PER_SECTION;
ret = __remove_section(zone, __pfn_to_section(pfn));
if (ret)
break;
}
return ret;
}
EXPORT_SYMBOL_GPL(__remove_pages);
#endif /* CONFIG_MEMORY_HOTREMOVE */
int set_online_page_callback(online_page_callback_t callback)
{
int rc = -EINVAL;
lock_memory_hotplug();
if (online_page_callback == generic_online_page) {
online_page_callback = callback;
rc = 0;
}
unlock_memory_hotplug();
return rc;
}
EXPORT_SYMBOL_GPL(set_online_page_callback);
int restore_online_page_callback(online_page_callback_t callback)
{
int rc = -EINVAL;
lock_memory_hotplug();
if (online_page_callback == callback) {
online_page_callback = generic_online_page;
rc = 0;
}
unlock_memory_hotplug();
return rc;
}
EXPORT_SYMBOL_GPL(restore_online_page_callback);
void __online_page_set_limits(struct page *page)
{
}
EXPORT_SYMBOL_GPL(__online_page_set_limits);
void __online_page_increment_counters(struct page *page)
{
adjust_managed_page_count(page, 1);
}
EXPORT_SYMBOL_GPL(__online_page_increment_counters);
void __online_page_free(struct page *page)
{
__free_reserved_page(page);
}
EXPORT_SYMBOL_GPL(__online_page_free);
static void generic_online_page(struct page *page)
{
__online_page_set_limits(page);
__online_page_increment_counters(page);
__online_page_free(page);
}
static int online_pages_range(unsigned long start_pfn, unsigned long nr_pages,
void *arg)
{
unsigned long i;
unsigned long onlined_pages = *(unsigned long *)arg;
struct page *page;
if (PageReserved(pfn_to_page(start_pfn)))
for (i = 0; i < nr_pages; i++) {
page = pfn_to_page(start_pfn + i);
(*online_page_callback)(page);
onlined_pages++;
}
*(unsigned long *)arg = onlined_pages;
return 0;
}
#ifdef CONFIG_MOVABLE_NODE
/*
* When CONFIG_MOVABLE_NODE, we permit onlining of a node which doesn't have
* normal memory.
*/
static bool can_online_high_movable(struct zone *zone)
{
return true;
}
#else /* CONFIG_MOVABLE_NODE */
/* ensure every online node has NORMAL memory */
static bool can_online_high_movable(struct zone *zone)
{
return node_state(zone_to_nid(zone), N_NORMAL_MEMORY);
}
#endif /* CONFIG_MOVABLE_NODE */
/* check which state of node_states will be changed when online memory */
static void node_states_check_changes_online(unsigned long nr_pages,
struct zone *zone, struct memory_notify *arg)
{
int nid = zone_to_nid(zone);
enum zone_type zone_last = ZONE_NORMAL;
/*
* If we have HIGHMEM or movable node, node_states[N_NORMAL_MEMORY]
* contains nodes which have zones of 0...ZONE_NORMAL,
* set zone_last to ZONE_NORMAL.
*
* If we don't have HIGHMEM nor movable node,
* node_states[N_NORMAL_MEMORY] contains nodes which have zones of
* 0...ZONE_MOVABLE, set zone_last to ZONE_MOVABLE.
*/
if (N_MEMORY == N_NORMAL_MEMORY)
zone_last = ZONE_MOVABLE;
/*
* if the memory to be online is in a zone of 0...zone_last, and
* the zones of 0...zone_last don't have memory before online, we will
* need to set the node to node_states[N_NORMAL_MEMORY] after
* the memory is online.
*/
if (zone_idx(zone) <= zone_last && !node_state(nid, N_NORMAL_MEMORY))
arg->status_change_nid_normal = nid;
else
arg->status_change_nid_normal = -1;
#ifdef CONFIG_HIGHMEM
/*
* If we have movable node, node_states[N_HIGH_MEMORY]
* contains nodes which have zones of 0...ZONE_HIGHMEM,
* set zone_last to ZONE_HIGHMEM.
*
* If we don't have movable node, node_states[N_NORMAL_MEMORY]
* contains nodes which have zones of 0...ZONE_MOVABLE,
* set zone_last to ZONE_MOVABLE.
*/
zone_last = ZONE_HIGHMEM;
if (N_MEMORY == N_HIGH_MEMORY)
zone_last = ZONE_MOVABLE;
if (zone_idx(zone) <= zone_last && !node_state(nid, N_HIGH_MEMORY))
arg->status_change_nid_high = nid;
else
arg->status_change_nid_high = -1;
#else
arg->status_change_nid_high = arg->status_change_nid_normal;
#endif
/*
* if the node don't have memory befor online, we will need to
* set the node to node_states[N_MEMORY] after the memory
* is online.
*/
if (!node_state(nid, N_MEMORY))
arg->status_change_nid = nid;
else
arg->status_change_nid = -1;
}
static void node_states_set_node(int node, struct memory_notify *arg)
{
if (arg->status_change_nid_normal >= 0)
node_set_state(node, N_NORMAL_MEMORY);
if (arg->status_change_nid_high >= 0)
node_set_state(node, N_HIGH_MEMORY);
node_set_state(node, N_MEMORY);
}
int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_type)
{
unsigned long flags;
unsigned long onlined_pages = 0;
struct zone *zone;
int need_zonelists_rebuild = 0;
int nid;
int ret;
struct memory_notify arg;
lock_memory_hotplug();
/*
* This doesn't need a lock to do pfn_to_page().
* The section can't be removed here because of the
* memory_block->state_mutex.
*/
zone = page_zone(pfn_to_page(pfn));
if ((zone_idx(zone) > ZONE_NORMAL || online_type == ONLINE_MOVABLE) &&
!can_online_high_movable(zone)) {
unlock_memory_hotplug();
return -EINVAL;
}
if (online_type == ONLINE_KERNEL && zone_idx(zone) == ZONE_MOVABLE) {
if (move_pfn_range_left(zone - 1, zone, pfn, pfn + nr_pages)) {
unlock_memory_hotplug();
return -EINVAL;
}
}
if (online_type == ONLINE_MOVABLE && zone_idx(zone) == ZONE_MOVABLE - 1) {
if (move_pfn_range_right(zone, zone + 1, pfn, pfn + nr_pages)) {
unlock_memory_hotplug();
return -EINVAL;
}
}
/* Previous code may changed the zone of the pfn range */
zone = page_zone(pfn_to_page(pfn));
arg.start_pfn = pfn;
arg.nr_pages = nr_pages;
node_states_check_changes_online(nr_pages, zone, &arg);
nid = page_to_nid(pfn_to_page(pfn));
ret = memory_notify(MEM_GOING_ONLINE, &arg);
ret = notifier_to_errno(ret);
if (ret) {
memory_notify(MEM_CANCEL_ONLINE, &arg);
unlock_memory_hotplug();
return ret;
}
/*
* If this zone is not populated, then it is not in zonelist.
* This means the page allocator ignores this zone.
* So, zonelist must be updated after online.
*/
mutex_lock(&zonelists_mutex);
if (!populated_zone(zone)) {
need_zonelists_rebuild = 1;
build_all_zonelists(NULL, zone);
}
ret = walk_system_ram_range(pfn, nr_pages, &onlined_pages,
online_pages_range);
if (ret) {
if (need_zonelists_rebuild)
zone_pcp_reset(zone);
mutex_unlock(&zonelists_mutex);
printk(KERN_DEBUG "online_pages [mem %#010llx-%#010llx] failed\n",
(unsigned long long) pfn << PAGE_SHIFT,
(((unsigned long long) pfn + nr_pages)
<< PAGE_SHIFT) - 1);
memory_notify(MEM_CANCEL_ONLINE, &arg);
unlock_memory_hotplug();
return ret;
}
zone->present_pages += onlined_pages;
pgdat_resize_lock(zone->zone_pgdat, &flags);
zone->zone_pgdat->node_present_pages += onlined_pages;
pgdat_resize_unlock(zone->zone_pgdat, &flags);
if (onlined_pages) {
node_states_set_node(zone_to_nid(zone), &arg);
if (need_zonelists_rebuild)
build_all_zonelists(NULL, NULL);
else
zone_pcp_update(zone);
}
mutex_unlock(&zonelists_mutex);
init_per_zone_wmark_min();
if (onlined_pages)
kswapd_run(zone_to_nid(zone));
vm_total_pages = nr_free_pagecache_pages();
writeback_set_ratelimit();
if (onlined_pages)