forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 1
/
page_alloc.c
7047 lines (6070 loc) · 195 KB
/
page_alloc.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
// SPDX-License-Identifier: GPL-2.0-only
/*
* linux/mm/page_alloc.c
*
* Manages the free list, the system allocates free pages here.
* Note that kmalloc() lives in slab.c
*
* Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds
* Swap reorganised 29.12.95, Stephen Tweedie
* Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999
* Reshaped it to be a zoned allocator, Ingo Molnar, Red Hat, 1999
* Discontiguous memory support, Kanoj Sarcar, SGI, Nov 1999
* Zone balancing, Kanoj Sarcar, SGI, Jan 2000
* Per cpu hot/cold page lists, bulk allocation, Martin J. Bligh, Sept 2002
* (lots of bits borrowed from Ingo Molnar & Andrew Morton)
*/
#include <linux/stddef.h>
#include <linux/mm.h>
#include <linux/highmem.h>
#include <linux/interrupt.h>
#include <linux/jiffies.h>
#include <linux/compiler.h>
#include <linux/kernel.h>
#include <linux/kasan.h>
#include <linux/kmsan.h>
#include <linux/module.h>
#include <linux/suspend.h>
#include <linux/ratelimit.h>
#include <linux/oom.h>
#include <linux/topology.h>
#include <linux/sysctl.h>
#include <linux/cpu.h>
#include <linux/cpuset.h>
#include <linux/pagevec.h>
#include <linux/memory_hotplug.h>
#include <linux/nodemask.h>
#include <linux/vmstat.h>
#include <linux/fault-inject.h>
#include <linux/compaction.h>
#include <trace/events/kmem.h>
#include <trace/events/oom.h>
#include <linux/prefetch.h>
#include <linux/mm_inline.h>
#include <linux/mmu_notifier.h>
#include <linux/migrate.h>
#include <linux/sched/mm.h>
#include <linux/page_owner.h>
#include <linux/page_table_check.h>
#include <linux/memcontrol.h>
#include <linux/ftrace.h>
#include <linux/lockdep.h>
#include <linux/psi.h>
#include <linux/khugepaged.h>
#include <linux/delayacct.h>
#include <linux/cacheinfo.h>
#include <linux/pgalloc_tag.h>
#include <asm/div64.h>
#include "internal.h"
#include "shuffle.h"
#include "page_reporting.h"
/* Free Page Internal flags: for internal, non-pcp variants of free_pages(). */
typedef int __bitwise fpi_t;
/* No special request */
#define FPI_NONE ((__force fpi_t)0)
/*
* Skip free page reporting notification for the (possibly merged) page.
* This does not hinder free page reporting from grabbing the page,
* reporting it and marking it "reported" - it only skips notifying
* the free page reporting infrastructure about a newly freed page. For
* example, used when temporarily pulling a page from a freelist and
* putting it back unmodified.
*/
#define FPI_SKIP_REPORT_NOTIFY ((__force fpi_t)BIT(0))
/*
* Place the (possibly merged) page to the tail of the freelist. Will ignore
* page shuffling (relevant code - e.g., memory onlining - is expected to
* shuffle the whole zone).
*
* Note: No code should rely on this flag for correctness - it's purely
* to allow for optimizations when handing back either fresh pages
* (memory onlining) or untouched pages (page isolation, free page
* reporting).
*/
#define FPI_TO_TAIL ((__force fpi_t)BIT(1))
/* prevent >1 _updater_ of zone percpu pageset ->high and ->batch fields */
static DEFINE_MUTEX(pcp_batch_high_lock);
#define MIN_PERCPU_PAGELIST_HIGH_FRACTION (8)
#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT)
/*
* On SMP, spin_trylock is sufficient protection.
* On PREEMPT_RT, spin_trylock is equivalent on both SMP and UP.
*/
#define pcp_trylock_prepare(flags) do { } while (0)
#define pcp_trylock_finish(flag) do { } while (0)
#else
/* UP spin_trylock always succeeds so disable IRQs to prevent re-entrancy. */
#define pcp_trylock_prepare(flags) local_irq_save(flags)
#define pcp_trylock_finish(flags) local_irq_restore(flags)
#endif
/*
* Locking a pcp requires a PCP lookup followed by a spinlock. To avoid
* a migration causing the wrong PCP to be locked and remote memory being
* potentially allocated, pin the task to the CPU for the lookup+lock.
* preempt_disable is used on !RT because it is faster than migrate_disable.
* migrate_disable is used on RT because otherwise RT spinlock usage is
* interfered with and a high priority task cannot preempt the allocator.
*/
#ifndef CONFIG_PREEMPT_RT
#define pcpu_task_pin() preempt_disable()
#define pcpu_task_unpin() preempt_enable()
#else
#define pcpu_task_pin() migrate_disable()
#define pcpu_task_unpin() migrate_enable()
#endif
/*
* Generic helper to lookup and a per-cpu variable with an embedded spinlock.
* Return value should be used with equivalent unlock helper.
*/
#define pcpu_spin_lock(type, member, ptr) \
({ \
type *_ret; \
pcpu_task_pin(); \
_ret = this_cpu_ptr(ptr); \
spin_lock(&_ret->member); \
_ret; \
})
#define pcpu_spin_trylock(type, member, ptr) \
({ \
type *_ret; \
pcpu_task_pin(); \
_ret = this_cpu_ptr(ptr); \
if (!spin_trylock(&_ret->member)) { \
pcpu_task_unpin(); \
_ret = NULL; \
} \
_ret; \
})
#define pcpu_spin_unlock(member, ptr) \
({ \
spin_unlock(&ptr->member); \
pcpu_task_unpin(); \
})
/* struct per_cpu_pages specific helpers. */
#define pcp_spin_lock(ptr) \
pcpu_spin_lock(struct per_cpu_pages, lock, ptr)
#define pcp_spin_trylock(ptr) \
pcpu_spin_trylock(struct per_cpu_pages, lock, ptr)
#define pcp_spin_unlock(ptr) \
pcpu_spin_unlock(lock, ptr)
#ifdef CONFIG_USE_PERCPU_NUMA_NODE_ID
DEFINE_PER_CPU(int, numa_node);
EXPORT_PER_CPU_SYMBOL(numa_node);
#endif
DEFINE_STATIC_KEY_TRUE(vm_numa_stat_key);
#ifdef CONFIG_HAVE_MEMORYLESS_NODES
/*
* N.B., Do NOT reference the '_numa_mem_' per cpu variable directly.
* It will not be defined when CONFIG_HAVE_MEMORYLESS_NODES is not defined.
* Use the accessor functions set_numa_mem(), numa_mem_id() and cpu_to_mem()
* defined in <linux/topology.h>.
*/
DEFINE_PER_CPU(int, _numa_mem_); /* Kernel "local memory" node */
EXPORT_PER_CPU_SYMBOL(_numa_mem_);
#endif
static DEFINE_MUTEX(pcpu_drain_mutex);
#ifdef CONFIG_GCC_PLUGIN_LATENT_ENTROPY
volatile unsigned long latent_entropy __latent_entropy;
EXPORT_SYMBOL(latent_entropy);
#endif
/*
* Array of node states.
*/
nodemask_t node_states[NR_NODE_STATES] __read_mostly = {
[N_POSSIBLE] = NODE_MASK_ALL,
[N_ONLINE] = { { [0] = 1UL } },
#ifndef CONFIG_NUMA
[N_NORMAL_MEMORY] = { { [0] = 1UL } },
#ifdef CONFIG_HIGHMEM
[N_HIGH_MEMORY] = { { [0] = 1UL } },
#endif
[N_MEMORY] = { { [0] = 1UL } },
[N_CPU] = { { [0] = 1UL } },
#endif /* NUMA */
};
EXPORT_SYMBOL(node_states);
gfp_t gfp_allowed_mask __read_mostly = GFP_BOOT_MASK;
#ifdef CONFIG_HUGETLB_PAGE_SIZE_VARIABLE
unsigned int pageblock_order __read_mostly;
#endif
static void __free_pages_ok(struct page *page, unsigned int order,
fpi_t fpi_flags);
/*
* results with 256, 32 in the lowmem_reserve sysctl:
* 1G machine -> (16M dma, 800M-16M normal, 1G-800M high)
* 1G machine -> (16M dma, 784M normal, 224M high)
* NORMAL allocation will leave 784M/256 of ram reserved in the ZONE_DMA
* HIGHMEM allocation will leave 224M/32 of ram reserved in ZONE_NORMAL
* HIGHMEM allocation will leave (224M+784M)/256 of ram reserved in ZONE_DMA
*
* TBD: should special case ZONE_DMA32 machines here - in those we normally
* don't need any ZONE_NORMAL reservation
*/
static int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES] = {
#ifdef CONFIG_ZONE_DMA
[ZONE_DMA] = 256,
#endif
#ifdef CONFIG_ZONE_DMA32
[ZONE_DMA32] = 256,
#endif
[ZONE_NORMAL] = 32,
#ifdef CONFIG_HIGHMEM
[ZONE_HIGHMEM] = 0,
#endif
[ZONE_MOVABLE] = 0,
};
char * const zone_names[MAX_NR_ZONES] = {
#ifdef CONFIG_ZONE_DMA
"DMA",
#endif
#ifdef CONFIG_ZONE_DMA32
"DMA32",
#endif
"Normal",
#ifdef CONFIG_HIGHMEM
"HighMem",
#endif
"Movable",
#ifdef CONFIG_ZONE_DEVICE
"Device",
#endif
};
const char * const migratetype_names[MIGRATE_TYPES] = {
"Unmovable",
"Movable",
"Reclaimable",
"HighAtomic",
#ifdef CONFIG_CMA
"CMA",
#endif
#ifdef CONFIG_MEMORY_ISOLATION
"Isolate",
#endif
};
int min_free_kbytes = 1024;
int user_min_free_kbytes = -1;
static int watermark_boost_factor __read_mostly = 15000;
static int watermark_scale_factor = 10;
/* movable_zone is the "real" zone pages in ZONE_MOVABLE are taken from */
int movable_zone;
EXPORT_SYMBOL(movable_zone);
#if MAX_NUMNODES > 1
unsigned int nr_node_ids __read_mostly = MAX_NUMNODES;
unsigned int nr_online_nodes __read_mostly = 1;
EXPORT_SYMBOL(nr_node_ids);
EXPORT_SYMBOL(nr_online_nodes);
#endif
static bool page_contains_unaccepted(struct page *page, unsigned int order);
static void accept_page(struct page *page, unsigned int order);
static bool cond_accept_memory(struct zone *zone, unsigned int order);
static inline bool has_unaccepted_memory(void);
static bool __free_unaccepted(struct page *page);
int page_group_by_mobility_disabled __read_mostly;
#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
/*
* During boot we initialize deferred pages on-demand, as needed, but once
* page_alloc_init_late() has finished, the deferred pages are all initialized,
* and we can permanently disable that path.
*/
DEFINE_STATIC_KEY_TRUE(deferred_pages);
static inline bool deferred_pages_enabled(void)
{
return static_branch_unlikely(&deferred_pages);
}
/*
* deferred_grow_zone() is __init, but it is called from
* get_page_from_freelist() during early boot until deferred_pages permanently
* disables this call. This is why we have refdata wrapper to avoid warning,
* and to ensure that the function body gets unloaded.
*/
static bool __ref
_deferred_grow_zone(struct zone *zone, unsigned int order)
{
return deferred_grow_zone(zone, order);
}
#else
static inline bool deferred_pages_enabled(void)
{
return false;
}
#endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */
/* Return a pointer to the bitmap storing bits affecting a block of pages */
static inline unsigned long *get_pageblock_bitmap(const struct page *page,
unsigned long pfn)
{
#ifdef CONFIG_SPARSEMEM
return section_to_usemap(__pfn_to_section(pfn));
#else
return page_zone(page)->pageblock_flags;
#endif /* CONFIG_SPARSEMEM */
}
static inline int pfn_to_bitidx(const struct page *page, unsigned long pfn)
{
#ifdef CONFIG_SPARSEMEM
pfn &= (PAGES_PER_SECTION-1);
#else
pfn = pfn - pageblock_start_pfn(page_zone(page)->zone_start_pfn);
#endif /* CONFIG_SPARSEMEM */
return (pfn >> pageblock_order) * NR_PAGEBLOCK_BITS;
}
/**
* get_pfnblock_flags_mask - Return the requested group of flags for the pageblock_nr_pages block of pages
* @page: The page within the block of interest
* @pfn: The target page frame number
* @mask: mask of bits that the caller is interested in
*
* Return: pageblock_bits flags
*/
unsigned long get_pfnblock_flags_mask(const struct page *page,
unsigned long pfn, unsigned long mask)
{
unsigned long *bitmap;
unsigned long bitidx, word_bitidx;
unsigned long word;
bitmap = get_pageblock_bitmap(page, pfn);
bitidx = pfn_to_bitidx(page, pfn);
word_bitidx = bitidx / BITS_PER_LONG;
bitidx &= (BITS_PER_LONG-1);
/*
* This races, without locks, with set_pfnblock_flags_mask(). Ensure
* a consistent read of the memory array, so that results, even though
* racy, are not corrupted.
*/
word = READ_ONCE(bitmap[word_bitidx]);
return (word >> bitidx) & mask;
}
static __always_inline int get_pfnblock_migratetype(const struct page *page,
unsigned long pfn)
{
return get_pfnblock_flags_mask(page, pfn, MIGRATETYPE_MASK);
}
/**
* set_pfnblock_flags_mask - Set the requested group of flags for a pageblock_nr_pages block of pages
* @page: The page within the block of interest
* @flags: The flags to set
* @pfn: The target page frame number
* @mask: mask of bits that the caller is interested in
*/
void set_pfnblock_flags_mask(struct page *page, unsigned long flags,
unsigned long pfn,
unsigned long mask)
{
unsigned long *bitmap;
unsigned long bitidx, word_bitidx;
unsigned long word;
BUILD_BUG_ON(NR_PAGEBLOCK_BITS != 4);
BUILD_BUG_ON(MIGRATE_TYPES > (1 << PB_migratetype_bits));
bitmap = get_pageblock_bitmap(page, pfn);
bitidx = pfn_to_bitidx(page, pfn);
word_bitidx = bitidx / BITS_PER_LONG;
bitidx &= (BITS_PER_LONG-1);
VM_BUG_ON_PAGE(!zone_spans_pfn(page_zone(page), pfn), page);
mask <<= bitidx;
flags <<= bitidx;
word = READ_ONCE(bitmap[word_bitidx]);
do {
} while (!try_cmpxchg(&bitmap[word_bitidx], &word, (word & ~mask) | flags));
}
void set_pageblock_migratetype(struct page *page, int migratetype)
{
if (unlikely(page_group_by_mobility_disabled &&
migratetype < MIGRATE_PCPTYPES))
migratetype = MIGRATE_UNMOVABLE;
set_pfnblock_flags_mask(page, (unsigned long)migratetype,
page_to_pfn(page), MIGRATETYPE_MASK);
}
#ifdef CONFIG_DEBUG_VM
static int page_outside_zone_boundaries(struct zone *zone, struct page *page)
{
int ret;
unsigned seq;
unsigned long pfn = page_to_pfn(page);
unsigned long sp, start_pfn;
do {
seq = zone_span_seqbegin(zone);
start_pfn = zone->zone_start_pfn;
sp = zone->spanned_pages;
ret = !zone_spans_pfn(zone, pfn);
} while (zone_span_seqretry(zone, seq));
if (ret)
pr_err("page 0x%lx outside node %d zone %s [ 0x%lx - 0x%lx ]\n",
pfn, zone_to_nid(zone), zone->name,
start_pfn, start_pfn + sp);
return ret;
}
/*
* Temporary debugging check for pages not lying within a given zone.
*/
static bool __maybe_unused bad_range(struct zone *zone, struct page *page)
{
if (page_outside_zone_boundaries(zone, page))
return true;
if (zone != page_zone(page))
return true;
return false;
}
#else
static inline bool __maybe_unused bad_range(struct zone *zone, struct page *page)
{
return false;
}
#endif
static void bad_page(struct page *page, const char *reason)
{
static unsigned long resume;
static unsigned long nr_shown;
static unsigned long nr_unshown;
/*
* Allow a burst of 60 reports, then keep quiet for that minute;
* or allow a steady drip of one report per second.
*/
if (nr_shown == 60) {
if (time_before(jiffies, resume)) {
nr_unshown++;
goto out;
}
if (nr_unshown) {
pr_alert(
"BUG: Bad page state: %lu messages suppressed\n",
nr_unshown);
nr_unshown = 0;
}
nr_shown = 0;
}
if (nr_shown++ == 0)
resume = jiffies + 60 * HZ;
pr_alert("BUG: Bad page state in process %s pfn:%05lx\n",
current->comm, page_to_pfn(page));
dump_page(page, reason);
print_modules();
dump_stack();
out:
/* Leave bad fields for debug, except PageBuddy could make trouble */
if (PageBuddy(page))
__ClearPageBuddy(page);
add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE);
}
static inline unsigned int order_to_pindex(int migratetype, int order)
{
bool __maybe_unused movable;
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
if (order > PAGE_ALLOC_COSTLY_ORDER) {
VM_BUG_ON(order != HPAGE_PMD_ORDER);
movable = migratetype == MIGRATE_MOVABLE;
return NR_LOWORDER_PCP_LISTS + movable;
}
#else
VM_BUG_ON(order > PAGE_ALLOC_COSTLY_ORDER);
#endif
return (MIGRATE_PCPTYPES * order) + migratetype;
}
static inline int pindex_to_order(unsigned int pindex)
{
int order = pindex / MIGRATE_PCPTYPES;
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
if (pindex >= NR_LOWORDER_PCP_LISTS)
order = HPAGE_PMD_ORDER;
#else
VM_BUG_ON(order > PAGE_ALLOC_COSTLY_ORDER);
#endif
return order;
}
static inline bool pcp_allowed_order(unsigned int order)
{
if (order <= PAGE_ALLOC_COSTLY_ORDER)
return true;
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
if (order == HPAGE_PMD_ORDER)
return true;
#endif
return false;
}
/*
* Higher-order pages are called "compound pages". They are structured thusly:
*
* The first PAGE_SIZE page is called the "head page" and have PG_head set.
*
* The remaining PAGE_SIZE pages are called "tail pages". PageTail() is encoded
* in bit 0 of page->compound_head. The rest of bits is pointer to head page.
*
* The first tail page's ->compound_order holds the order of allocation.
* This usage means that zero-order pages may not be compound.
*/
void prep_compound_page(struct page *page, unsigned int order)
{
int i;
int nr_pages = 1 << order;
__SetPageHead(page);
for (i = 1; i < nr_pages; i++)
prep_compound_tail(page, i);
prep_compound_head(page, order);
}
static inline void set_buddy_order(struct page *page, unsigned int order)
{
set_page_private(page, order);
__SetPageBuddy(page);
}
#ifdef CONFIG_COMPACTION
static inline struct capture_control *task_capc(struct zone *zone)
{
struct capture_control *capc = current->capture_control;
return unlikely(capc) &&
!(current->flags & PF_KTHREAD) &&
!capc->page &&
capc->cc->zone == zone ? capc : NULL;
}
static inline bool
compaction_capture(struct capture_control *capc, struct page *page,
int order, int migratetype)
{
if (!capc || order != capc->cc->order)
return false;
/* Do not accidentally pollute CMA or isolated regions*/
if (is_migrate_cma(migratetype) ||
is_migrate_isolate(migratetype))
return false;
/*
* Do not let lower order allocations pollute a movable pageblock
* unless compaction is also requesting movable pages.
* This might let an unmovable request use a reclaimable pageblock
* and vice-versa but no more than normal fallback logic which can
* have trouble finding a high-order free page.
*/
if (order < pageblock_order && migratetype == MIGRATE_MOVABLE &&
capc->cc->migratetype != MIGRATE_MOVABLE)
return false;
capc->page = page;
return true;
}
#else
static inline struct capture_control *task_capc(struct zone *zone)
{
return NULL;
}
static inline bool
compaction_capture(struct capture_control *capc, struct page *page,
int order, int migratetype)
{
return false;
}
#endif /* CONFIG_COMPACTION */
static inline void account_freepages(struct zone *zone, int nr_pages,
int migratetype)
{
if (is_migrate_isolate(migratetype))
return;
__mod_zone_page_state(zone, NR_FREE_PAGES, nr_pages);
if (is_migrate_cma(migratetype))
__mod_zone_page_state(zone, NR_FREE_CMA_PAGES, nr_pages);
}
/* Used for pages not on another list */
static inline void __add_to_free_list(struct page *page, struct zone *zone,
unsigned int order, int migratetype,
bool tail)
{
struct free_area *area = &zone->free_area[order];
VM_WARN_ONCE(get_pageblock_migratetype(page) != migratetype,
"page type is %lu, passed migratetype is %d (nr=%d)\n",
get_pageblock_migratetype(page), migratetype, 1 << order);
if (tail)
list_add_tail(&page->buddy_list, &area->free_list[migratetype]);
else
list_add(&page->buddy_list, &area->free_list[migratetype]);
area->nr_free++;
}
/*
* Used for pages which are on another list. Move the pages to the tail
* of the list - so the moved pages won't immediately be considered for
* allocation again (e.g., optimization for memory onlining).
*/
static inline void move_to_free_list(struct page *page, struct zone *zone,
unsigned int order, int old_mt, int new_mt)
{
struct free_area *area = &zone->free_area[order];
/* Free page moving can fail, so it happens before the type update */
VM_WARN_ONCE(get_pageblock_migratetype(page) != old_mt,
"page type is %lu, passed migratetype is %d (nr=%d)\n",
get_pageblock_migratetype(page), old_mt, 1 << order);
list_move_tail(&page->buddy_list, &area->free_list[new_mt]);
account_freepages(zone, -(1 << order), old_mt);
account_freepages(zone, 1 << order, new_mt);
}
static inline void __del_page_from_free_list(struct page *page, struct zone *zone,
unsigned int order, int migratetype)
{
VM_WARN_ONCE(get_pageblock_migratetype(page) != migratetype,
"page type is %lu, passed migratetype is %d (nr=%d)\n",
get_pageblock_migratetype(page), migratetype, 1 << order);
/* clear reported state and update reported page count */
if (page_reported(page))
__ClearPageReported(page);
list_del(&page->buddy_list);
__ClearPageBuddy(page);
set_page_private(page, 0);
zone->free_area[order].nr_free--;
}
static inline void del_page_from_free_list(struct page *page, struct zone *zone,
unsigned int order, int migratetype)
{
__del_page_from_free_list(page, zone, order, migratetype);
account_freepages(zone, -(1 << order), migratetype);
}
static inline struct page *get_page_from_free_area(struct free_area *area,
int migratetype)
{
return list_first_entry_or_null(&area->free_list[migratetype],
struct page, buddy_list);
}
/*
* If this is less than the 2nd largest possible page, check if the buddy
* of the next-higher order is free. If it is, it's possible
* that pages are being freed that will coalesce soon. In case,
* that is happening, add the free page to the tail of the list
* so it's less likely to be used soon and more likely to be merged
* as a 2-level higher order page
*/
static inline bool
buddy_merge_likely(unsigned long pfn, unsigned long buddy_pfn,
struct page *page, unsigned int order)
{
unsigned long higher_page_pfn;
struct page *higher_page;
if (order >= MAX_PAGE_ORDER - 1)
return false;
higher_page_pfn = buddy_pfn & pfn;
higher_page = page + (higher_page_pfn - pfn);
return find_buddy_page_pfn(higher_page, higher_page_pfn, order + 1,
NULL) != NULL;
}
/*
* Freeing function for a buddy system allocator.
*
* The concept of a buddy system is to maintain direct-mapped table
* (containing bit values) for memory blocks of various "orders".
* The bottom level table contains the map for the smallest allocatable
* units of memory (here, pages), and each level above it describes
* pairs of units from the levels below, hence, "buddies".
* At a high level, all that happens here is marking the table entry
* at the bottom level available, and propagating the changes upward
* as necessary, plus some accounting needed to play nicely with other
* parts of the VM system.
* At each level, we keep a list of pages, which are heads of continuous
* free pages of length of (1 << order) and marked with PageBuddy.
* Page's order is recorded in page_private(page) field.
* So when we are allocating or freeing one, we can derive the state of the
* other. That is, if we allocate a small block, and both were
* free, the remainder of the region must be split into blocks.
* If a block is freed, and its buddy is also free, then this
* triggers coalescing into a block of larger size.
*
* -- nyc
*/
static inline void __free_one_page(struct page *page,
unsigned long pfn,
struct zone *zone, unsigned int order,
int migratetype, fpi_t fpi_flags)
{
struct capture_control *capc = task_capc(zone);
unsigned long buddy_pfn = 0;
unsigned long combined_pfn;
struct page *buddy;
bool to_tail;
VM_BUG_ON(!zone_is_initialized(zone));
VM_BUG_ON_PAGE(page->flags & PAGE_FLAGS_CHECK_AT_PREP, page);
VM_BUG_ON(migratetype == -1);
VM_BUG_ON_PAGE(pfn & ((1 << order) - 1), page);
VM_BUG_ON_PAGE(bad_range(zone, page), page);
account_freepages(zone, 1 << order, migratetype);
while (order < MAX_PAGE_ORDER) {
int buddy_mt = migratetype;
if (compaction_capture(capc, page, order, migratetype)) {
account_freepages(zone, -(1 << order), migratetype);
return;
}
buddy = find_buddy_page_pfn(page, pfn, order, &buddy_pfn);
if (!buddy)
goto done_merging;
if (unlikely(order >= pageblock_order)) {
/*
* We want to prevent merge between freepages on pageblock
* without fallbacks and normal pageblock. Without this,
* pageblock isolation could cause incorrect freepage or CMA
* accounting or HIGHATOMIC accounting.
*/
buddy_mt = get_pfnblock_migratetype(buddy, buddy_pfn);
if (migratetype != buddy_mt &&
(!migratetype_is_mergeable(migratetype) ||
!migratetype_is_mergeable(buddy_mt)))
goto done_merging;
}
/*
* Our buddy is free or it is CONFIG_DEBUG_PAGEALLOC guard page,
* merge with it and move up one order.
*/
if (page_is_guard(buddy))
clear_page_guard(zone, buddy, order);
else
__del_page_from_free_list(buddy, zone, order, buddy_mt);
if (unlikely(buddy_mt != migratetype)) {
/*
* Match buddy type. This ensures that an
* expand() down the line puts the sub-blocks
* on the right freelists.
*/
set_pageblock_migratetype(buddy, migratetype);
}
combined_pfn = buddy_pfn & pfn;
page = page + (combined_pfn - pfn);
pfn = combined_pfn;
order++;
}
done_merging:
set_buddy_order(page, order);
if (fpi_flags & FPI_TO_TAIL)
to_tail = true;
else if (is_shuffle_order(order))
to_tail = shuffle_pick_tail();
else
to_tail = buddy_merge_likely(pfn, buddy_pfn, page, order);
__add_to_free_list(page, zone, order, migratetype, to_tail);
/* Notify page reporting subsystem of freed page */
if (!(fpi_flags & FPI_SKIP_REPORT_NOTIFY))
page_reporting_notify_free(order);
}
/*
* A bad page could be due to a number of fields. Instead of multiple branches,
* try and check multiple fields with one check. The caller must do a detailed
* check if necessary.
*/
static inline bool page_expected_state(struct page *page,
unsigned long check_flags)
{
if (unlikely(atomic_read(&page->_mapcount) != -1))
return false;
if (unlikely((unsigned long)page->mapping |
page_ref_count(page) |
#ifdef CONFIG_MEMCG
page->memcg_data |
#endif
#ifdef CONFIG_PAGE_POOL
((page->pp_magic & ~0x3UL) == PP_SIGNATURE) |
#endif
(page->flags & check_flags)))
return false;
return true;
}
static const char *page_bad_reason(struct page *page, unsigned long flags)
{
const char *bad_reason = NULL;
if (unlikely(atomic_read(&page->_mapcount) != -1))
bad_reason = "nonzero mapcount";
if (unlikely(page->mapping != NULL))
bad_reason = "non-NULL mapping";
if (unlikely(page_ref_count(page) != 0))
bad_reason = "nonzero _refcount";
if (unlikely(page->flags & flags)) {
if (flags == PAGE_FLAGS_CHECK_AT_PREP)
bad_reason = "PAGE_FLAGS_CHECK_AT_PREP flag(s) set";
else
bad_reason = "PAGE_FLAGS_CHECK_AT_FREE flag(s) set";
}
#ifdef CONFIG_MEMCG
if (unlikely(page->memcg_data))
bad_reason = "page still charged to cgroup";
#endif
#ifdef CONFIG_PAGE_POOL
if (unlikely((page->pp_magic & ~0x3UL) == PP_SIGNATURE))
bad_reason = "page_pool leak";
#endif
return bad_reason;
}
static void free_page_is_bad_report(struct page *page)
{
bad_page(page,
page_bad_reason(page, PAGE_FLAGS_CHECK_AT_FREE));
}
static inline bool free_page_is_bad(struct page *page)
{
if (likely(page_expected_state(page, PAGE_FLAGS_CHECK_AT_FREE)))
return false;
/* Something has gone sideways, find it */
free_page_is_bad_report(page);
return true;
}
static inline bool is_check_pages_enabled(void)
{
return static_branch_unlikely(&check_pages_enabled);
}
static int free_tail_page_prepare(struct page *head_page, struct page *page)
{
struct folio *folio = (struct folio *)head_page;
int ret = 1;
/*
* We rely page->lru.next never has bit 0 set, unless the page
* is PageTail(). Let's make sure that's true even for poisoned ->lru.
*/
BUILD_BUG_ON((unsigned long)LIST_POISON1 & 1);
if (!is_check_pages_enabled()) {
ret = 0;
goto out;
}
switch (page - head_page) {
case 1:
/* the first tail page: these may be in place of ->mapping */
if (unlikely(folio_entire_mapcount(folio))) {
bad_page(page, "nonzero entire_mapcount");
goto out;
}
if (unlikely(folio_large_mapcount(folio))) {
bad_page(page, "nonzero large_mapcount");
goto out;
}
if (unlikely(atomic_read(&folio->_nr_pages_mapped))) {
bad_page(page, "nonzero nr_pages_mapped");
goto out;
}
if (unlikely(atomic_read(&folio->_pincount))) {
bad_page(page, "nonzero pincount");
goto out;
}
break;
case 2:
/* the second tail page: deferred_list overlaps ->mapping */
if (unlikely(!list_empty(&folio->_deferred_list))) {
bad_page(page, "on deferred list");
goto out;
}
break;
default:
if (page->mapping != TAIL_MAPPING) {
bad_page(page, "corrupted mapping in tail page");
goto out;
}
break;
}
if (unlikely(!PageTail(page))) {
bad_page(page, "PageTail not set");
goto out;
}
if (unlikely(compound_head(page) != head_page)) {
bad_page(page, "compound_head not consistent");
goto out;
}
ret = 0;
out:
page->mapping = NULL;
clear_compound_head(page);
return ret;
}
/*
* Skip KASAN memory poisoning when either:
*
* 1. For generic KASAN: deferred memory initialization has not yet completed.
* Tag-based KASAN modes skip pages freed via deferred memory initialization
* using page tags instead (see below).
* 2. For tag-based KASAN modes: the page has a match-all KASAN tag, indicating
* that error detection is disabled for accesses via the page address.
*
* Pages will have match-all tags in the following circumstances:
*
* 1. Pages are being initialized for the first time, including during deferred
* memory init; see the call to page_kasan_tag_reset in __init_single_page.