FazBrowse GitHub Viewer
|
Trending
|
URL:
|
Home
Tools:
[Download Repo ZIP]
[View Raw Code]
[Original HTTPS Page]
linux/mm/memory_hotplug.c at master · gregkh/linux · GitHub
gregkh
/
linux
Public
Notifications
You must be signed in to change notification settings
Fork
772
Star
713
Code
Actions
Security and quality
0
Insights
Additional navigation options
Code
Actions
Security and quality
Insights
Expand file tree
Breadcrumbs
linux
/
mm
/
memory_hotplug.c
Copy path
More file actions
More file actions
Latest commit
History
History
History
2529 lines (2172 loc) · 70.3 KB
Breadcrumbs
linux
/
mm
/
memory_hotplug.c
Copy path
File metadata and controls
2529 lines (2172 loc) · 70.3 KB
Raw
Copy raw file
Download raw file
Open symbols panel
Edit and raw actions
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
// SPDX-License-Identifier: GPL-2.0-only
/*
* linux/mm/memory_hotplug.c
*
* Copyright (C)
*/
#include
<linux/stddef.h>
#include
<linux/mm.h>
#include
<linux/sched/signal.h>
#include
<linux/swap.h>
#include
<linux/interrupt.h>
#include
<linux/pagemap.h>
#include
<linux/compiler.h>
#include
<linux/export.h>
#include
<linux/writeback.h>
#include
<linux/slab.h>
#include
<linux/sysctl.h>
#include
<linux/cpu.h>
#include
<linux/memory.h>
#include
<linux/memremap.h>
#include
<linux/memory_hotplug.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
<linux/hugetlb.h>
#include
<linux/memblock.h>
#include
<linux/compaction.h>
#include
<linux/rmap.h>
#include
<linux/module.h>
#include
<linux/node.h>
#include
<asm/tlbflush.h>
#include
"internal.h"
#include
"mm_init.h"
#include
"page_alloc.h"
#include
"shuffle.h"
enum
{
MEMMAP_ON_MEMORY_DISABLE
=
0
,
MEMMAP_ON_MEMORY_ENABLE
,
MEMMAP_ON_MEMORY_FORCE
,
};
static
int
memmap_mode
__read_mostly
=
MEMMAP_ON_MEMORY_DISABLE
;
static
inline
unsigned long
memory_block_memmap_size
(
void
)
{
return
PHYS_PFN
(
memory_block_size_bytes
())
*
sizeof
(
struct
page
);
}
static
inline
unsigned long
memory_block_memmap_on_memory_pages
(
void
)
{
unsigned long
nr_pages
=
PFN_UP
(
memory_block_memmap_size
());
/*
* In "forced" memmap_on_memory mode, we add extra pages to align the
* vmemmap size to cover full pageblocks. That way, we can add memory
* even if the vmemmap size is not properly aligned, however, we might waste
* memory.
*/
if
(
memmap_mode
==
MEMMAP_ON_MEMORY_FORCE
)
return
pageblock_align
(
nr_pages
);
return
nr_pages
;
}
#ifdef
CONFIG_MHP_MEMMAP_ON_MEMORY
/*
* memory_hotplug.memmap_on_memory parameter
*/
static
int
set_memmap_mode
(
const
char
*
val
,
const
struct
kernel_param
*
kp
)
{
int
ret
,
mode
;
bool
enabled
;
if
(
sysfs_streq
(
val
,
"force"
)
||
sysfs_streq
(
val
,
"FORCE"
)) {
mode
=
MEMMAP_ON_MEMORY_FORCE
;
}
else
{
ret
=
kstrtobool
(
val
,
&
enabled
);
if
(
ret
<
0
)
return
ret
;
if
(
enabled
)
mode
=
MEMMAP_ON_MEMORY_ENABLE
;
else
mode
=
MEMMAP_ON_MEMORY_DISABLE
;
}
*
((
int
*
)
kp
->
arg
)
=
mode
;
if
(
mode
==
MEMMAP_ON_MEMORY_FORCE
) {
unsigned long
memmap_pages
=
memory_block_memmap_on_memory_pages
();
pr_info_once
(
"Memory hotplug will waste %ld pages in each memory block\n"
,
memmap_pages
-
PFN_UP
(
memory_block_memmap_size
()));
}
return
0
;
}
static
int
get_memmap_mode
(
char
*
buffer
,
const
struct
kernel_param
*
kp
)
{
int
mode
=
*
((
int
*
)
kp
->
arg
);
if
(
mode
==
MEMMAP_ON_MEMORY_FORCE
)
return
sprintf
(
buffer
,
"force\n"
);
return
sprintf
(
buffer
,
"%c\n"
,
mode
?
'Y'
:
'N'
);
}
static
const
struct
kernel_param_ops
memmap_mode_ops
=
{
.
set
=
set_memmap_mode
,
.
get
=
get_memmap_mode
,
};
module_param_cb
(
memmap_on_memory
,
&
memmap_mode_ops
,
&
memmap_mode
,
0444
);
MODULE_PARM_DESC
(
memmap_on_memory
,
"Enable memmap on memory for memory hotplug\n"
"With value \"force\" it could result in memory wastage due "
"to memmap size limitations (Y/N/force)"
);
static
inline
bool
mhp_memmap_on_memory
(
void
)
{
return
memmap_mode
!=
MEMMAP_ON_MEMORY_DISABLE
;
}
#else
static
inline
bool
mhp_memmap_on_memory
(
void
)
{
return
false;
}
#endif
enum
{
ONLINE_POLICY_CONTIG_ZONES
=
0
,
ONLINE_POLICY_AUTO_MOVABLE
,
};
static
const
char
*
const
online_policy_to_str
[]
=
{
[
ONLINE_POLICY_CONTIG_ZONES
]
=
"contig-zones"
,
[
ONLINE_POLICY_AUTO_MOVABLE
]
=
"auto-movable"
,
};
static
int
set_online_policy
(
const
char
*
val
,
const
struct
kernel_param
*
kp
)
{
int
ret
=
sysfs_match_string
(
online_policy_to_str
,
val
);
if
(
ret
<
0
)
return
ret
;
*
((
int
*
)
kp
->
arg
)
=
ret
;
return
0
;
}
static
int
get_online_policy
(
char
*
buffer
,
const
struct
kernel_param
*
kp
)
{
return
sprintf
(
buffer
,
"%s\n"
,
online_policy_to_str
[
*
((
int
*
)
kp
->
arg
)]);
}
/*
* memory_hotplug.online_policy: configure online behavior when onlining without
* specifying a zone (MMOP_ONLINE)
*
* "contig-zones": keep zone contiguous
* "auto-movable": online memory to ZONE_MOVABLE if the configuration
* (auto_movable_ratio, auto_movable_numa_aware) allows for it
*/
static
int
online_policy
__read_mostly
=
ONLINE_POLICY_CONTIG_ZONES
;
static
const
struct
kernel_param_ops
online_policy_ops
=
{
.
set
=
set_online_policy
,
.
get
=
get_online_policy
,
};
module_param_cb
(
online_policy
,
&
online_policy_ops
,
&
online_policy
,
0644
);
MODULE_PARM_DESC
(
online_policy
,
"Set the online policy (\"contig-zones\", \"auto-movable\") "
"Default: \"contig-zones\""
);
/*
* memory_hotplug.auto_movable_ratio: specify maximum MOVABLE:KERNEL ratio
*
* The ratio represent an upper limit and the kernel might decide to not
* online some memory to ZONE_MOVABLE -- e.g., because hotplugged KERNEL memory
* doesn't allow for more MOVABLE memory.
*/
static
unsigned
int
auto_movable_ratio
__read_mostly
=
301
;
module_param
(
auto_movable_ratio
,
uint
,
0644
);
MODULE_PARM_DESC
(
auto_movable_ratio
,
"Set the maximum ratio of MOVABLE:KERNEL memory in the system "
"in percent for \"auto-movable\" online policy. Default: 301"
);
/*
* memory_hotplug.auto_movable_numa_aware: consider numa node stats
*/
#ifdef
CONFIG_NUMA
static
bool
auto_movable_numa_aware
__read_mostly
=
true;
module_param
(
auto_movable_numa_aware
,
bool
,
0644
);
MODULE_PARM_DESC
(
auto_movable_numa_aware
,
"Consider numa node stats in addition to global stats in "
"\"auto-movable\" online policy. Default: true"
);
#endif
/* CONFIG_NUMA */
/*
* 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
online_page_callback_t
online_page_callback
=
generic_online_page
;
static
DEFINE_MUTEX
(
online_page_callback_lock
);
DEFINE_STATIC_PERCPU_RWSEM
(
mem_hotplug_lock
);
void
get_online_mems
(
void
)
{
percpu_down_read
(
&
mem_hotplug_lock
);
}
void
put_online_mems
(
void
)
{
percpu_up_read
(
&
mem_hotplug_lock
);
}
bool
movable_node_enabled
=
false;
static
int
mhp_default_online_type
=
-1
;
enum
mmop
mhp_get_default_online_type
(
void
)
{
if
(
mhp_default_online_type
>=
0
)
return
mhp_default_online_type
;
if
(
IS_ENABLED
(
CONFIG_MHP_DEFAULT_ONLINE_TYPE_OFFLINE
))
mhp_default_online_type
=
MMOP_OFFLINE
;
else
if
(
IS_ENABLED
(
CONFIG_MHP_DEFAULT_ONLINE_TYPE_ONLINE_AUTO
))
mhp_default_online_type
=
MMOP_ONLINE
;
else
if
(
IS_ENABLED
(
CONFIG_MHP_DEFAULT_ONLINE_TYPE_ONLINE_KERNEL
))
mhp_default_online_type
=
MMOP_ONLINE_KERNEL
;
else
if
(
IS_ENABLED
(
CONFIG_MHP_DEFAULT_ONLINE_TYPE_ONLINE_MOVABLE
))
mhp_default_online_type
=
MMOP_ONLINE_MOVABLE
;
else
mhp_default_online_type
=
MMOP_OFFLINE
;
return
mhp_default_online_type
;
}
EXPORT_SYMBOL_GPL
(
mhp_get_default_online_type
);
void
mhp_set_default_online_type
(
enum
mmop
online_type
)
{
mhp_default_online_type
=
online_type
;
}
static
int
__init
setup_memhp_default_state
(
char
*
str
)
{
const
int
online_type
=
mhp_online_type_from_str
(
str
);
if
(
online_type
>=
0
)
mhp_default_online_type
=
online_type
;
return
1
;
}
__setup
(
"memhp_default_state="
,
setup_memhp_default_state
);
void
mem_hotplug_begin
(
void
)
{
cpus_read_lock
();
percpu_down_write
(
&
mem_hotplug_lock
);
}
void
mem_hotplug_done
(
void
)
{
percpu_up_write
(
&
mem_hotplug_lock
);
cpus_read_unlock
();
}
u64
max_mem_size
=
U64_MAX
;
/* add this memory to iomem resource */
static
struct
resource
*
register_memory_resource
(
u64
start
,
u64
size
,
const
char
*
resource_name
)
{
struct
resource
*
res
;
unsigned long
flags
=
IORESOURCE_SYSTEM_RAM
|
IORESOURCE_BUSY
;
if
(
strcmp
(
resource_name
,
"System RAM"
))
flags
|=
IORESOURCE_SYSRAM_DRIVER_MANAGED
;
if
(!
mhp_range_allowed
(
start
,
size
, true))
return
ERR_PTR
(
-
E2BIG
);
/*
* Make sure value parsed from 'mem=' only restricts memory adding
* while booting, so that memory hotplug won't be impacted. Please
* refer to document of 'mem=' in kernel-parameters.txt for more
* details.
*/
if
(
start
+
size
>
max_mem_size
&&
system_state
<
SYSTEM_RUNNING
)
return
ERR_PTR
(
-
E2BIG
);
/*
* Request ownership of the new memory range. This might be
* a child of an existing resource that was present but
* not marked as busy.
*/
res
=
__request_region
(
&
iomem_resource
,
start
,
size
,
resource_name
,
flags
);
if
(!
res
) {
pr_debug
(
"Unable to reserve System RAM region: %016llx->%016llx\n"
,
start
,
start
+
size
);
return
ERR_PTR
(
-
EEXIST
);
}
return
res
;
}
static
void
release_memory_resource
(
struct
resource
*
res
)
{
if
(!
res
)
return
;
release_resource
(
res
);
kfree
(
res
);
}
static
int
check_pfn_span
(
unsigned long
pfn
,
unsigned long
nr_pages
)
{
/*
* Disallow all operations smaller than a sub-section.
* Note that check_hotplug_memory_range() enforces a larger
* memory_block_size_bytes() granularity for memory that will be marked
* online, so this check should only fire for direct
* arch_{add,remove}_memory() users outside of add_memory_resource().
*/
if
(!
IS_ALIGNED
(
pfn
|
nr_pages
,
PAGES_PER_SUBSECTION
))
return
-
EINVAL
;
return
0
;
}
/*
* Return page for the valid pfn only if the page is online. All pfn
* walkers which rely on the fully initialized page->flags and others
* should use this rather than pfn_valid && pfn_to_page
*/
struct
page
*
pfn_to_online_page
(
unsigned long
pfn
)
{
unsigned long
nr
=
pfn_to_section_nr
(
pfn
);
struct
dev_pagemap
*
pgmap
;
struct
mem_section
*
ms
;
if
(
nr
>=
NR_MEM_SECTIONS
)
return
NULL
;
ms
=
__nr_to_section
(
nr
);
if
(!
online_section
(
ms
))
return
NULL
;
/*
* Save some code text when online_section() +
* pfn_section_valid() are sufficient.
*/
if
(
IS_ENABLED
(
CONFIG_HAVE_ARCH_PFN_VALID
)
&&
!
pfn_valid
(
pfn
))
return
NULL
;
if
(!
pfn_section_valid
(
ms
,
pfn
))
return
NULL
;
if
(!
online_device_section
(
ms
))
return
pfn_to_page
(
pfn
);
/*
* Slowpath: when ZONE_DEVICE collides with
* ZONE_{NORMAL,MOVABLE} within the same section some pfns in
* the section may be 'offline' but 'valid'. Only
* get_dev_pagemap() can determine sub-section online status.
*/
pgmap
=
get_dev_pagemap
(
pfn
);
put_dev_pagemap
(
pgmap
);
/* The presence of a pgmap indicates ZONE_DEVICE offline pfn */
if
(
pgmap
)
return
NULL
;
return
pfn_to_page
(
pfn
);
}
EXPORT_SYMBOL_GPL
(
pfn_to_online_page
);
int
__add_pages
(
int
nid
,
unsigned long
pfn
,
unsigned long
nr_pages
,
struct
mhp_params
*
params
)
{
const
unsigned long
end_pfn
=
pfn
+
nr_pages
;
unsigned long
cur_nr_pages
;
int
err
;
struct
vmem_altmap
*
altmap
=
params
->
altmap
;
if
(
WARN_ON_ONCE
(!
pgprot_val
(
params
->
pgprot
)))
return
-
EINVAL
;
VM_BUG_ON
(!
mhp_range_allowed
(
PFN_PHYS
(
pfn
),
nr_pages
*
PAGE_SIZE
, false));
if
(
altmap
) {
/*
* Validate altmap is within bounds of the total request
*/
if
(
altmap
->
base_pfn
!=
pfn
||
vmem_altmap_offset
(
altmap
)
>
nr_pages
) {
pr_warn_once
(
"memory add fail, invalid altmap\n"
);
return
-
EINVAL
;
}
altmap
->
alloc
=
0
;
}
if
(
check_pfn_span
(
pfn
,
nr_pages
)) {
WARN
(
1
,
"Misaligned %s start: %#lx end: %#lx\n"
,
__func__
,
pfn
,
pfn
+
nr_pages
-
1
);
return
-
EINVAL
;
}
for
(;
pfn
<
end_pfn
;
pfn
+=
cur_nr_pages
) {
/* Select all remaining pages up to the next section boundary */
cur_nr_pages
=
min
(
end_pfn
-
pfn
,
SECTION_ALIGN_UP
(
pfn
+
1
)
-
pfn
);
err
=
sparse_add_section
(
nid
,
pfn
,
cur_nr_pages
,
altmap
,
params
->
pgmap
);
if
(
err
)
break
;
cond_resched
();
}
vmemmap_populate_print_last
();
return
err
;
}
/* find the smallest valid pfn in the range [start_pfn, end_pfn) */
static
unsigned long
find_smallest_section_pfn
(
int
nid
,
struct
zone
*
zone
,
unsigned long
start_pfn
,
unsigned long
end_pfn
)
{
for
(;
start_pfn
<
end_pfn
;
start_pfn
+=
PAGES_PER_SUBSECTION
) {
if
(
unlikely
(!
pfn_to_online_page
(
start_pfn
)))
continue
;
if
(
unlikely
(
pfn_to_nid
(
start_pfn
)
!=
nid
))
continue
;
if
(
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
unsigned long
find_biggest_section_pfn
(
int
nid
,
struct
zone
*
zone
,
unsigned long
start_pfn
,
unsigned long
end_pfn
)
{
unsigned long
pfn
;
/* pfn is the end pfn of a memory section. */
pfn
=
end_pfn
-
1
;
for
(;
pfn
>=
start_pfn
;
pfn
-=
PAGES_PER_SUBSECTION
) {
if
(
unlikely
(!
pfn_to_online_page
(
pfn
)))
continue
;
if
(
unlikely
(
pfn_to_nid
(
pfn
)
!=
nid
))
continue
;
if
(
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
pfn
;
int
nid
=
zone_to_nid
(
zone
);
if
(
zone
->
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
(
zone
));
if
(
pfn
) {
zone
->
spanned_pages
=
zone_end_pfn
(
zone
)
-
pfn
;
zone
->
zone_start_pfn
=
pfn
;
}
else
{
zone
->
zone_start_pfn
=
0
;
zone
->
spanned_pages
=
0
;
}
}
else
if
(
zone_end_pfn
(
zone
)
==
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
->
zone_start_pfn
,
start_pfn
);
if
(
pfn
)
zone
->
spanned_pages
=
pfn
-
zone
->
zone_start_pfn
+
1
;
else
{
zone
->
zone_start_pfn
=
0
;
zone
->
spanned_pages
=
0
;
}
}
}
static
void
update_pgdat_span
(
struct
pglist_data
*
pgdat
)
{
unsigned long
node_start_pfn
=
0
,
node_end_pfn
=
0
;
struct
zone
*
zone
;
for
(
zone
=
pgdat
->
node_zones
;
zone
<
pgdat
->
node_zones
+
MAX_NR_ZONES
;
zone
++
) {
unsigned long
end_pfn
=
zone_end_pfn
(
zone
);
/* No need to lock the zones, they can't change. */
if
(!
zone
->
spanned_pages
)
continue
;
if
(!
node_end_pfn
) {
node_start_pfn
=
zone
->
zone_start_pfn
;
node_end_pfn
=
end_pfn
;
continue
;
}
if
(
end_pfn
>
node_end_pfn
)
node_end_pfn
=
end_pfn
;
if
(
zone
->
zone_start_pfn
<
node_start_pfn
)
node_start_pfn
=
zone
->
zone_start_pfn
;
}
pgdat
->
node_start_pfn
=
node_start_pfn
;
pgdat
->
node_spanned_pages
=
node_end_pfn
-
node_start_pfn
;
}
void
remove_pfn_range_from_zone
(
struct
zone
*
zone
,
unsigned long
start_pfn
,
unsigned long
nr_pages
)
{
const
unsigned long
end_pfn
=
start_pfn
+
nr_pages
;
struct
pglist_data
*
pgdat
=
zone
->
zone_pgdat
;
unsigned long
pfn
,
cur_nr_pages
;
/* Poison struct pages because they are now uninitialized again. */
for
(
pfn
=
start_pfn
;
pfn
<
end_pfn
;
pfn
+=
cur_nr_pages
) {
cond_resched
();
/* Select all remaining pages up to the next section boundary */
cur_nr_pages
=
min
(
end_pfn
-
pfn
,
SECTION_ALIGN_UP
(
pfn
+
1
)
-
pfn
);
page_init_poison
(
pfn_to_page
(
pfn
),
sizeof
(
struct
page
)
*
cur_nr_pages
);
}
/*
* Zone shrinking code cannot properly deal with ZONE_DEVICE. So
* we will not try to shrink the zones - which is okay as
* set_zone_contiguous() cannot deal with ZONE_DEVICE either way.
*/
if
(
zone_is_zone_device
(
zone
))
return
;
clear_zone_contiguous
(
zone
);
shrink_zone_span
(
zone
,
start_pfn
,
start_pfn
+
nr_pages
);
update_pgdat_span
(
pgdat
);
set_zone_contiguous
(
zone
);
}
/**
* __remove_pages() - remove sections of pages
* @pfn: starting pageframe (must be aligned to start of a section)
* @nr_pages: number of pages to remove (must be multiple of section size)
* @altmap: alternative device page map or %NULL if default memmap is used
* @pgmap: device page map or %NULL if not ZONE_DEVICE
*
* 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().
*/
void
__remove_pages
(
unsigned long
pfn
,
unsigned long
nr_pages
,
struct
vmem_altmap
*
altmap
,
struct
dev_pagemap
*
pgmap
)
{
const
unsigned long
end_pfn
=
pfn
+
nr_pages
;
unsigned long
cur_nr_pages
;
if
(
check_pfn_span
(
pfn
,
nr_pages
)) {
WARN
(
1
,
"Misaligned %s start: %#lx end: %#lx\n"
,
__func__
,
pfn
,
pfn
+
nr_pages
-
1
);
return
;
}
for
(;
pfn
<
end_pfn
;
pfn
+=
cur_nr_pages
) {
cond_resched
();
/* Select all remaining pages up to the next section boundary */
cur_nr_pages
=
min
(
end_pfn
-
pfn
,
SECTION_ALIGN_UP
(
pfn
+
1
)
-
pfn
);
sparse_remove_section
(
pfn
,
cur_nr_pages
,
altmap
,
pgmap
);
}
}
int
set_online_page_callback
(
online_page_callback_t
callback
)
{
int
rc
=
-
EINVAL
;
get_online_mems
();
mutex_lock
(
&
online_page_callback_lock
);
if
(
online_page_callback
==
generic_online_page
) {
online_page_callback
=
callback
;
rc
=
0
;
}
mutex_unlock
(
&
online_page_callback_lock
);
put_online_mems
();
return
rc
;
}
EXPORT_SYMBOL_GPL
(
set_online_page_callback
);
int
restore_online_page_callback
(
online_page_callback_t
callback
)
{
int
rc
=
-
EINVAL
;
get_online_mems
();
mutex_lock
(
&
online_page_callback_lock
);
if
(
online_page_callback
==
callback
) {
online_page_callback
=
generic_online_page
;
rc
=
0
;
}
mutex_unlock
(
&
online_page_callback_lock
);
put_online_mems
();
return
rc
;
}
EXPORT_SYMBOL_GPL
(
restore_online_page_callback
);
/* we are OK calling __meminit stuff here - we have CONFIG_MEMORY_HOTPLUG */
void
generic_online_page
(
struct
page
*
page
,
unsigned
int
order
)
{
__free_pages_core
(
page
,
order
,
MEMINIT_HOTPLUG
);
}
EXPORT_SYMBOL_GPL
(
generic_online_page
);
static
void
online_pages_range
(
unsigned long
start_pfn
,
unsigned long
nr_pages
)
{
const
unsigned long
end_pfn
=
start_pfn
+
nr_pages
;
unsigned long
pfn
;
/*
* Online the pages in MAX_PAGE_ORDER aligned chunks. The callback might
* decide to not expose all pages to the buddy (e.g., expose them
* later). We account all pages as being online and belonging to this
* zone ("present").
* When using memmap_on_memory, the range might not be aligned to
* MAX_ORDER_NR_PAGES - 1, but pageblock aligned. __ffs() will detect
* this and the first chunk to online will be pageblock_nr_pages.
*/
for
(
pfn
=
start_pfn
;
pfn
<
end_pfn
;) {
struct
page
*
page
=
pfn_to_page
(
pfn
);
int
order
;
/*
* Free to online pages in the largest chunks alignment allows.
*
* __ffs() behaviour is undefined for 0. start == 0 is
* MAX_PAGE_ORDER-aligned, Set order to MAX_PAGE_ORDER for
* the case.
*/
if
(
pfn
)
order
=
min_t
(
int
,
MAX_PAGE_ORDER
,
__ffs
(
pfn
));
else
order
=
MAX_PAGE_ORDER
;
/*
* Exposing the page to the buddy by freeing can cause
* issues with debug_pagealloc enabled: some archs don't
* like double-unmappings. So treat them like any pages that
* were allocated from the buddy.
*/
debug_pagealloc_map_pages
(
page
,
1
<<
order
);
(
*
online_page_callback
)(
page
,
order
);
pfn
+=
(
1UL
<<
order
);
}
/* mark all involved sections as online */
online_mem_sections
(
start_pfn
,
end_pfn
);
}
static
void
__meminit
resize_zone_range
(
struct
zone
*
zone
,
unsigned long
start_pfn
,
unsigned long
nr_pages
)
{
unsigned long
old_end_pfn
=
zone_end_pfn
(
zone
);
if
(
zone_is_empty
(
zone
)
||
start_pfn
<
zone
->
zone_start_pfn
)
zone
->
zone_start_pfn
=
start_pfn
;
zone
->
spanned_pages
=
max
(
start_pfn
+
nr_pages
,
old_end_pfn
)
-
zone
->
zone_start_pfn
;
}
static
void
__meminit
resize_pgdat_range
(
struct
pglist_data
*
pgdat
,
unsigned long
start_pfn
,
unsigned long
nr_pages
)
{
unsigned long
old_end_pfn
=
pgdat_end_pfn
(
pgdat
);
if
(!
pgdat
->
node_spanned_pages
||
start_pfn
<
pgdat
->
node_start_pfn
)
pgdat
->
node_start_pfn
=
start_pfn
;
pgdat
->
node_spanned_pages
=
max
(
start_pfn
+
nr_pages
,
old_end_pfn
)
-
pgdat
->
node_start_pfn
;
}
#ifdef
CONFIG_ZONE_DEVICE
static
void
section_taint_zone_device
(
unsigned long
pfn
)
{
struct
mem_section
*
ms
=
__pfn_to_section
(
pfn
);
ms
->
section_mem_map
|=
SECTION_TAINT_ZONE_DEVICE
;
}
#else
static
inline
void
section_taint_zone_device
(
unsigned long
pfn
)
{
}
#endif
/*
* Associate the pfn range with the given zone, initializing the memmaps
* and resizing the pgdat/zone data to span the added pages. After this
* call, all affected pages are PageOffline().
*
* All aligned pageblocks are initialized to the specified migratetype
* (usually MIGRATE_MOVABLE). Besides setting the migratetype, no related
* zone stats (e.g., nr_isolate_pageblock) are touched.
*/
void
move_pfn_range_to_zone
(
struct
zone
*
zone
,
unsigned long
start_pfn
,
unsigned long
nr_pages
,
struct
vmem_altmap
*
altmap
,
int
migratetype
,
bool
isolate_pageblock
)
{
struct
pglist_data
*
pgdat
=
zone
->
zone_pgdat
;
int
nid
=
pgdat
->
node_id
;
clear_zone_contiguous
(
zone
);
if
(
zone_is_empty
(
zone
))
init_currently_empty_zone
(
zone
,
start_pfn
,
nr_pages
);
resize_zone_range
(
zone
,
start_pfn
,
nr_pages
);
resize_pgdat_range
(
pgdat
,
start_pfn
,
nr_pages
);
/*
* Subsection population requires care in pfn_to_online_page().
* Set the taint to enable the slow path detection of
* ZONE_DEVICE pages in an otherwise ZONE_{NORMAL,MOVABLE}
* section.
*/
if
(
zone_is_zone_device
(
zone
)) {
if
(!
IS_ALIGNED
(
start_pfn
,
PAGES_PER_SECTION
))
section_taint_zone_device
(
start_pfn
);
if
(!
IS_ALIGNED
(
start_pfn
+
nr_pages
,
PAGES_PER_SECTION
))
section_taint_zone_device
(
start_pfn
+
nr_pages
);
}
/*
* TODO now we have a visible range of pages which are not associated
* with their zone properly. Not nice but set_pfnblock_migratetype()
* expects the zone spans the pfn range. All the pages in the range
* are reserved so nobody should be touching them so we should be safe
*/
memmap_init_range
(
nr_pages
,
nid
,
zone_idx
(
zone
),
start_pfn
,
0
,
MEMINIT_HOTPLUG
,
altmap
,
migratetype
,
isolate_pageblock
);
set_zone_contiguous
(
zone
);
}
struct
auto_movable_stats
{
unsigned long
kernel_early_pages
;
unsigned long
movable_pages
;
};
static
void
auto_movable_stats_account_zone
(
struct
auto_movable_stats
*
stats
,
struct
zone
*
zone
)
{
if
(
zone_idx
(
zone
)
==
ZONE_MOVABLE
) {
stats
->
movable_pages
+=
zone
->
present_pages
;
}
else
{
stats
->
kernel_early_pages
+=
zone
->
present_early_pages
;
#ifdef
CONFIG_CMA
/*
* CMA pages (never on hotplugged memory) behave like
* ZONE_MOVABLE.
*/
stats
->
movable_pages
+=
zone
->
cma_pages
;
stats
->
kernel_early_pages
-=
zone
->
cma_pages
;
#endif
/* CONFIG_CMA */
}
}
struct
auto_movable_group_stats
{
unsigned long
movable_pages
;
unsigned long
req_kernel_early_pages
;
};
static
int
auto_movable_stats_account_group
(
struct
memory_group
*
group
,
void
*
arg
)
{
const
int
ratio
=
READ_ONCE
(
auto_movable_ratio
);
struct
auto_movable_group_stats
*
stats
=
arg
;
long
pages
;
/*
* We don't support modifying the config while the auto-movable online
* policy is already enabled. Just avoid the division by zero below.
*/
if
(!
ratio
)
return
0
;
/*
* Calculate how many early kernel pages this group requires to
* satisfy the configured zone ratio.
*/
pages
=
group
->
present_movable_pages
*
100
/
ratio
;
pages
-=
group
->
present_kernel_pages
;
if
(
pages
>
0
)
stats
->
req_kernel_early_pages
+=
pages
;
stats
->
movable_pages
+=
group
->
present_movable_pages
;
return
0
;
}
static
bool
auto_movable_can_online_movable
(
int
nid
,
struct
memory_group
*
group
,
unsigned long
nr_pages
)
{
unsigned long
kernel_early_pages
,
movable_pages
;
struct
auto_movable_group_stats
group_stats
=
{};
struct
auto_movable_stats
stats
=
{};
struct
zone
*
zone
;
int
i
;
/* Walk all relevant zones and collect MOVABLE vs. KERNEL stats. */
if
(
nid
==
NUMA_NO_NODE
) {
/* TODO: cache values */
for_each_populated_zone
(
zone
)
auto_movable_stats_account_zone
(
&
stats
,
zone
);
}
else
{
for
(
i
=
0
;
i
<
MAX_NR_ZONES
;
i
++
) {
pg_data_t
*
pgdat
=
NODE_DATA
(
nid
);
zone
=
pgdat
->
node_zones
+
i
;
if
(
populated_zone
(
zone
))
auto_movable_stats_account_zone
(
&
stats
,
zone
);
}
}
kernel_early_pages
=
stats
.
kernel_early_pages
;
movable_pages
=
stats
.
movable_pages
;
/*
* Kernel memory inside dynamic memory group allows for more MOVABLE
* memory within the same group. Remove the effect of all but the
* current group from the stats.
*/
walk_dynamic_memory_groups
(
nid
,
auto_movable_stats_account_group
,
group
,
&
group_stats
);
if
(
kernel_early_pages
<=
group_stats
.
req_kernel_early_pages
)
return
false;
kernel_early_pages
-=
group_stats
.
req_kernel_early_pages
;
movable_pages
-=
group_stats
.
movable_pages
;
if
(
group
&&
group
->
is_dynamic
)
kernel_early_pages
+=
group
->
present_kernel_pages
;
/*
* Test if we could online the given number of pages to ZONE_MOVABLE
* and still stay in the configured ratio.
*/
movable_pages
+=
nr_pages
;
return
movable_pages
<= (
auto_movable_ratio
*
kernel_early_pages
) /
100
;
}
/*
* Returns a default kernel memory zone for the given pfn range.
* If no kernel zone covers this pfn range it will automatically go
* to the ZONE_NORMAL.
*/
static
struct
zone
*
default_kernel_zone_for_pfn
(
int
nid
,
unsigned long
start_pfn
,
unsigned long
nr_pages
)
{
struct
pglist_data
*
pgdat
=
NODE_DATA
(
nid
);
int
zid
;
for
(
zid
=
0
;
zid
<
ZONE_NORMAL
;
zid
++
) {
struct
zone
*
zone
=
&
pgdat
->
node_zones
[
zid
];
if
(
zone_intersects
(
zone
,
start_pfn
,
nr_pages
))
return
zone
;
}
return
&
pgdat
->
node_zones
[
ZONE_NORMAL
];
}
/*
* Determine to which zone to online memory dynamically based on user
* configuration and system stats. We care about the following ratio:
*
* MOVABLE : KERNEL
*
* Whereby MOVABLE is memory in ZONE_MOVABLE and KERNEL is memory in
* one of the kernel zones. CMA pages inside one of the kernel zones really
* behaves like ZONE_MOVABLE, so we treat them accordingly.
*
* We don't allow for hotplugged memory in a KERNEL zone to increase the
* amount of MOVABLE memory we can have, so we end up with:
*
* MOVABLE : KERNEL_EARLY
*
* Whereby KERNEL_EARLY is memory in one of the kernel zones, available since
* boot. We base our calculation on KERNEL_EARLY internally, because:
*
* a) Hotplugged memory in one of the kernel zones can sometimes still get
* hotunplugged, especially when hot(un)plugging individual memory blocks.
* There is no coordination across memory devices, therefore "automatic"
* hotunplugging, as implemented in hypervisors, could result in zone
* imbalances.
* b) Early/boot memory in one of the kernel zones can usually not get
* hotunplugged again (e.g., no firmware interface to unplug, fragmented
* with unmovable allocations). While there are corner cases where it might
* still work, it is barely relevant in practice.
*
* Exceptions are dynamic memory groups, which allow for more MOVABLE
* memory within the same memory group -- because in that case, there is
* coordination within the single memory device managed by a single driver.
*
* We rely on "present pages" instead of "managed pages", as the latter is
* highly unreliable and dynamic in virtualized environments, and does not
* consider boot time allocations. For example, memory ballooning adjusts the
* managed pages when inflating/deflating the balloon, and balloon page
* migration can even migrate inflated pages between zones.
*
* Using "present pages" is better but some things to keep in mind are:
*
* a) Some memblock allocations, such as for the crashkernel area, are
* effectively unused by the kernel, yet they account to "present pages".
* Fortunately, these allocations are comparatively small in relevant setups
* (e.g., fraction of system memory).
* b) Some hotplugged memory blocks in virtualized environments, especially
* hotplugged by virtio-mem, look like they are completely present, however,
* only parts of the memory block are actually currently usable.
* "present pages" is an upper limit that can get reached at runtime. As
* we base our calculations on KERNEL_EARLY, this is not an issue.
*/
static
struct
zone
*
auto_movable_zone_for_pfn
(
int
nid
,
struct
memory_group
*
group
,
unsigned long
pfn
,
unsigned long
nr_pages
)
{
unsigned long
online_pages
=
0
,
max_pages
,
end_pfn
;
struct
page
*
page
;
if
(!
auto_movable_ratio
)
goto
kernel_zone
;
if
(
group
&&
!
group
->
is_dynamic
) {
max_pages
=
group
->
s
.
max_pages
;
online_pages
=
group
->
present_movable_pages
;
/* If anything is !MOVABLE online the rest !MOVABLE. */
if
(
group
->
present_kernel_pages
)
goto
kernel_zone
;
}
else
if
(!
group
||
group
->
d
.
unit_pages
==
nr_pages
) {
max_pages
=
nr_pages
;
}
else
{
max_pages
=
group
->
d
.
unit_pages
;
/*
* Take a look at all online sections in the current unit.
* We can safely assume that all pages within a section belong
* to the same zone, because dynamic memory groups only deal
* with hotplugged memory.
*/
pfn
=
ALIGN_DOWN
(
pfn
,
group
->
d
.
unit_pages
);
end_pfn
=
pfn
+
group
->
d
.
unit_pages
;
for
(;
pfn
<
end_pfn
;
pfn
+=
PAGES_PER_SECTION
) {
page
=
pfn_to_online_page
(
pfn
);
if
(!
page
)
continue
;
/* If anything is !MOVABLE online the rest !MOVABLE. */
if
(!
is_zone_movable_page
(
page
))
goto
kernel_zone
;
online_pages
+=
PAGES_PER_SECTION
;
}
}
View remainder of file in raw view
Back
|
FazBrowse Home
|
New Git URL