summaryrefslogtreecommitdiff
path: root/include/linux/gfp.h
blob: 80f63c862be575e7c11e9bf7ad049796eeb86431 (plain)
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
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef __LINUX_GFP_H
#define __LINUX_GFP_H

#include <linux/mmdebug.h>
#include <linux/mmzone.h>
#include <linux/stddef.h>
#include <linux/linkage.h>
#include <linux/topology.h>

/* The typedef is in types.h but we want the documentation here */
#if 0
/**
 * typedef gfp_t - Memory allocation flags.
 *
 * GFP flags are commonly used throughout Linux to indicate how memory
 * should be allocated.  The GFP acronym stands for get_free_pages(),
 * the underlying memory allocation function.  Not every GFP flag is
 * supported by every function which may allocate memory.  Most users
 * will want to use a plain ``GFP_KERNEL``.
 */
typedef unsigned int __bitwise gfp_t;
#endif

struct vm_area_struct;

/*
 * In case of changes, please don't forget to update
 * include/trace/events/mmflags.h and tools/perf/builtin-kmem.c
 */

/* Plain integer GFP bitmasks. Do not use this directly. */
#define ___GFP_DMA		0x01u
#define ___GFP_HIGHMEM		0x02u
#define ___GFP_DMA32		0x04u
#define ___GFP_MOVABLE		0x08u
#define ___GFP_RECLAIMABLE	0x10u
#define ___GFP_HIGH		0x20u
#define ___GFP_IO		0x40u
#define ___GFP_FS		0x80u
#define ___GFP_ZERO		0x100u
#define ___GFP_ATOMIC		0x200u
#define ___GFP_DIRECT_RECLAIM	0x400u
#define ___GFP_KSWAPD_RECLAIM	0x800u
#define ___GFP_WRITE		0x1000u
#define ___GFP_NOWARN		0x2000u
#define ___GFP_RETRY_MAYFAIL	0x4000u
#define ___GFP_NOFAIL		0x8000u
#define ___GFP_NORETRY		0x10000u
#define ___GFP_MEMALLOC		0x20000u
#define ___GFP_COMP		0x40000u
#define ___GFP_NOMEMALLOC	0x80000u
#define ___GFP_HARDWALL		0x100000u
#define ___GFP_THISNODE		0x200000u
#define ___GFP_ACCOUNT		0x400000u
#define ___GFP_ZEROTAGS		0x800000u
#define ___GFP_SKIP_KASAN_POISON	0x1000000u
#ifdef CONFIG_LOCKDEP
#define ___GFP_NOLOCKDEP	0x2000000u
#else
#define ___GFP_NOLOCKDEP	0
#endif
/* If the above are modified, __GFP_BITS_SHIFT may need updating */

/*
 * Physical address zone modifiers (see linux/mmzone.h - low four bits)
 *
 * Do not put any conditional on these. If necessary modify the definitions
 * without the underscores and use them consistently. The definitions here may
 * be used in bit comparisons.
 */
#define __GFP_DMA	((__force gfp_t)___GFP_DMA)
#define __GFP_HIGHMEM	((__force gfp_t)___GFP_HIGHMEM)
#define __GFP_DMA32	((__force gfp_t)___GFP_DMA32)
#define __GFP_MOVABLE	((__force gfp_t)___GFP_MOVABLE)  /* ZONE_MOVABLE allowed */
#define GFP_ZONEMASK	(__GFP_DMA|__GFP_HIGHMEM|__GFP_DMA32|__GFP_MOVABLE)

/**
 * DOC: Page mobility and placement hints
 *
 * Page mobility and placement hints
 * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 *
 * These flags provide hints about how mobile the page is. Pages with similar
 * mobility are placed within the same pageblocks to minimise problems due
 * to external fragmentation.
 *
 * %__GFP_MOVABLE (also a zone modifier) indicates that the page can be
 * moved by page migration during memory compaction or can be reclaimed.
 *
 * %__GFP_RECLAIMABLE is used for slab allocations that specify
 * SLAB_RECLAIM_ACCOUNT and whose pages can be freed via shrinkers.
 *
 * %__GFP_WRITE indicates the caller intends to dirty the page. Where possible,
 * these pages will be spread between local zones to avoid all the dirty
 * pages being in one zone (fair zone allocation policy).
 *
 * %__GFP_HARDWALL enforces the cpuset memory allocation policy.
 *
 * %__GFP_THISNODE forces the allocation to be satisfied from the requested
 * node with no fallbacks or placement policy enforcements.
 *
 * %__GFP_ACCOUNT causes the allocation to be accounted to kmemcg.
 */
#define __GFP_RECLAIMABLE ((__force gfp_t)___GFP_RECLAIMABLE)
#define __GFP_WRITE	((__force gfp_t)___GFP_WRITE)
#define __GFP_HARDWALL   ((__force gfp_t)___GFP_HARDWALL)
#define __GFP_THISNODE	((__force gfp_t)___GFP_THISNODE)
#define __GFP_ACCOUNT	((__force gfp_t)___GFP_ACCOUNT)

/**
 * DOC: Watermark modifiers
 *
 * Watermark modifiers -- controls access to emergency reserves
 * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 *
 * %__GFP_HIGH indicates that the caller is high-priority and that granting
 * the request is necessary before the system can make forward progress.
 * For example, creating an IO context to clean pages.
 *
 * %__GFP_ATOMIC indicates that the caller cannot reclaim or sleep and is
 * high priority. Users are typically interrupt handlers. This may be
 * used in conjunction with %__GFP_HIGH
 *
 * %__GFP_MEMALLOC allows access to all memory. This should only be used when
 * the caller guarantees the allocation will allow more memory to be freed
 * very shortly e.g. process exiting or swapping. Users either should
 * be the MM or co-ordinating closely with the VM (e.g. swap over NFS).
 * Users of this flag have to be extremely careful to not deplete the reserve
 * completely and implement a throttling mechanism which controls the
 * consumption of the reserve based on the amount of freed memory.
 * Usage of a pre-allocated pool (e.g. mempool) should be always considered
 * before using this flag.
 *
 * %__GFP_NOMEMALLOC is used to explicitly forbid access to emergency reserves.
 * This takes precedence over the %__GFP_MEMALLOC flag if both are set.
 */
#define __GFP_ATOMIC	((__force gfp_t)___GFP_ATOMIC)
#define __GFP_HIGH	((__force gfp_t)___GFP_HIGH)
#define __GFP_MEMALLOC	((__force gfp_t)___GFP_MEMALLOC)
#define __GFP_NOMEMALLOC ((__force gfp_t)___GFP_NOMEMALLOC)

/**
 * DOC: Reclaim modifiers
 *
 * Reclaim modifiers
 * ~~~~~~~~~~~~~~~~~
 * Please note that all the following flags are only applicable to sleepable
 * allocations (e.g. %GFP_NOWAIT and %GFP_ATOMIC will ignore them).
 *
 * %__GFP_IO can start physical IO.
 *
 * %__GFP_FS can call down to the low-level FS. Clearing the flag avoids the
 * allocator recursing into the filesystem which might already be holding
 * locks.
 *
 * %__GFP_DIRECT_RECLAIM indicates that the caller may enter direct reclaim.
 * This flag can be cleared to avoid unnecessary delays when a fallback
 * option is available.
 *
 * %__GFP_KSWAPD_RECLAIM indicates that the caller wants to wake kswapd when
 * the low watermark is reached and have it reclaim pages until the high
 * watermark is reached. A caller may wish to clear this flag when fallback
 * options are available and the reclaim is likely to disrupt the system. The
 * canonical example is THP allocation where a fallback is cheap but
 * reclaim/compaction may cause indirect stalls.
 *
 * %__GFP_RECLAIM is shorthand to allow/forbid both direct and kswapd reclaim.
 *
 * The default allocator behavior depends on the request size. We have a concept
 * of so called costly allocations (with order > %PAGE_ALLOC_COSTLY_ORDER).
 * !costly allocations are too essential to fail so they are implicitly
 * non-failing by default (with some exceptions like OOM victims might fail so
 * the caller still has to check for failures) while costly requests try to be
 * not disruptive and back off even without invoking the OOM killer.
 * The following three modifiers might be used to override some of these
 * implicit rules
 *
 * %__GFP_NORETRY: The VM implementation will try only very lightweight
 * memory direct reclaim to get some memory under memory pressure (thus
 * it can sleep). It will avoid disruptive actions like OOM killer. The
 * caller must handle the failure which is quite likely to happen under
 * heavy memory pressure. The flag is suitable when failure can easily be
 * handled at small cost, such as reduced throughput
 *
 * %__GFP_RETRY_MAYFAIL: The VM implementation will retry memory reclaim
 * procedures that have previously failed if there is some indication
 * that progress has been made else where.  It can wait for other
 * tasks to attempt high level approaches to freeing memory such as
 * compaction (which removes fragmentation) and page-out.
 * There is still a definite limit to the number of retries, but it is
 * a larger limit than with %__GFP_NORETRY.
 * Allocations with this flag may fail, but only when there is
 * genuinely little unused memory. While these allocations do not
 * directly trigger the OOM killer, their failure indicates that
 * the system is likely to need to use the OOM killer soon.  The
 * caller must handle failure, but can reasonably do so by failing
 * a higher-level request, or completing it only in a much less
 * efficient manner.
 * If the allocation does fail, and the caller is in a position to
 * free some non-essential memory, doing so could benefit the system
 * as a whole.
 *
 * %__GFP_NOFAIL: The VM implementation _must_ retry infinitely: the caller
 * cannot handle allocation failures. The allocation could block
 * indefinitely but will never return with failure. Testing for
 * failure is pointless.
 * New users should be evaluated carefully (and the flag should be
 * used only when there is no reasonable failure policy) but it is
 * definitely preferable to use the flag rather than opencode endless
 * loop around allocator.
 * Using this flag for costly allocations is _highly_ discouraged.
 */
#define __GFP_IO	((__force gfp_t)___GFP_IO)
#define __GFP_FS	((__force gfp_t)___GFP_FS)
#define __GFP_DIRECT_RECLAIM	((__force gfp_t)___GFP_DIRECT_RECLAIM) /* Caller can reclaim */
#define __GFP_KSWAPD_RECLAIM	((__force gfp_t)___GFP_KSWAPD_RECLAIM) /* kswapd can wake */
#define __GFP_RECLAIM ((__force gfp_t)(___GFP_DIRECT_RECLAIM|___GFP_KSWAPD_RECLAIM))
#define __GFP_RETRY_MAYFAIL	((__force gfp_t)___GFP_RETRY_MAYFAIL)
#define __GFP_NOFAIL	((__force gfp_t)___GFP_NOFAIL)
#define __GFP_NORETRY	((__force gfp_t)___GFP_NORETRY)

/**
 * DOC: Action modifiers
 *
 * Action modifiers
 * ~~~~~~~~~~~~~~~~
 *
 * %__GFP_NOWARN suppresses allocation failure reports.
 *
 * %__GFP_COMP address compound page metadata.
 *
 * %__GFP_ZERO returns a zeroed page on success.
 *
 * %__GFP_ZEROTAGS returns a page with zeroed memory tags on success, if
 * __GFP_ZERO is set.
 *
 * %__GFP_SKIP_KASAN_POISON returns a page which does not need to be poisoned
 * on deallocation. Typically used for userspace pages. Currently only has an
 * effect in HW tags mode.
 */
#define __GFP_NOWARN	((__force gfp_t)___GFP_NOWARN)
#define __GFP_COMP	((__force gfp_t)___GFP_COMP)
#define __GFP_ZERO	((__force gfp_t)___GFP_ZERO)
#define __GFP_ZEROTAGS	((__force gfp_t)___GFP_ZEROTAGS)
#define __GFP_SKIP_KASAN_POISON	((__force gfp_t)___GFP_SKIP_KASAN_POISON)

/* Disable lockdep for GFP context tracking */
#define __GFP_NOLOCKDEP ((__force gfp_t)___GFP_NOLOCKDEP)

/* Room for N __GFP_FOO bits */
#define __GFP_BITS_SHIFT (25 + IS_ENABLED(CONFIG_LOCKDEP))
#define __GFP_BITS_MASK ((__force gfp_t)((1 << __GFP_BITS_SHIFT) - 1))

/**
 * DOC: Useful GFP flag combinations
 *
 * Useful GFP flag combinations
 * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 *
 * Useful GFP flag combinations that are commonly used. It is recommended
 * that subsystems start with one of these combinations and then set/clear
 * %__GFP_FOO flags as necessary.
 *
 * %GFP_ATOMIC users can not sleep and need the allocation to succeed. A lower
 * watermark is applied to allow access to "atomic reserves".
 * The current implementation doesn't support NMI and few other strict
 * non-preemptive contexts (e.g. raw_spin_lock). The same applies to %GFP_NOWAIT.
 *
 * %GFP_KERNEL is typical for kernel-internal allocations. The caller requires
 * %ZONE_NORMAL or a lower zone for direct access but can direct reclaim.
 *
 * %GFP_KERNEL_ACCOUNT is the same as GFP_KERNEL, except the allocation is
 * accounted to kmemcg.
 *
 * %GFP_NOWAIT is for kernel allocations that should not stall for direct
 * reclaim, start physical IO or use any filesystem callback.
 *
 * %GFP_NOIO will use direct reclaim to discard clean pages or slab pages
 * that do not require the starting of any physical IO.
 * Please try to avoid using this flag directly and instead use
 * memalloc_noio_{save,restore} to mark the whole scope which cannot
 * perform any IO with a short explanation why. All allocation requests
 * will inherit GFP_NOIO implicitly.
 *
 * %GFP_NOFS will use direct reclaim but will not use any filesystem interfaces.
 * Please try to avoid using this flag directly and instead use
 * memalloc_nofs_{save,restore} to mark the whole scope which cannot/shouldn't
 * recurse into the FS layer with a short explanation why. All allocation
 * requests will inherit GFP_NOFS implicitly.
 *
 * %GFP_USER is for userspace allocations that also need to be directly
 * accessibly by the kernel or hardware. It is typically used by hardware
 * for buffers that are mapped to userspace (e.g. graphics) that hardware
 * still must DMA to. cpuset limits are enforced for these allocations.
 *
 * %GFP_DMA exists for historical reasons and should be avoided where possible.
 * The flags indicates that the caller requires that the lowest zone be
 * used (%ZONE_DMA or 16M on x86-64). Ideally, this would be removed but
 * it would require careful auditing as some users really require it and
 * others use the flag to avoid lowmem reserves in %ZONE_DMA and treat the
 * lowest zone as a type of emergency reserve.
 *
 * %GFP_DMA32 is similar to %GFP_DMA except that the caller requires a 32-bit
 * address. Note that kmalloc(..., GFP_DMA32) does not return DMA32 memory
 * because the DMA32 kmalloc cache array is not implemented.
 * (Reason: there is no such user in kernel).
 *
 * %GFP_HIGHUSER is for userspace allocations that may be mapped to userspace,
 * do not need to be directly accessible by the kernel but that cannot
 * move once in use. An example may be a hardware allocation that maps
 * data directly into userspace but has no addressing limitations.
 *
 * %GFP_HIGHUSER_MOVABLE is for userspace allocations that the kernel does not
 * need direct access to but can use kmap() when access is required. They
 * are expected to be movable via page reclaim or page migration. Typically,
 * pages on the LRU would also be allocated with %GFP_HIGHUSER_MOVABLE.
 *
 * %GFP_TRANSHUGE and %GFP_TRANSHUGE_LIGHT are used for THP allocations. They
 * are compound allocations that will generally fail quickly if memory is not
 * available and will not wake kswapd/kcompactd on failure. The _LIGHT
 * version does not attempt reclaim/compaction at all and is by default used
 * in page fault path, while the non-light is used by khugepaged.
 */
#define GFP_ATOMIC	(__GFP_HIGH|__GFP_ATOMIC|__GFP_KSWAPD_RECLAIM)
#define GFP_KERNEL	(__GFP_RECLAIM | __GFP_IO | __GFP_FS)
#define GFP_KERNEL_ACCOUNT (GFP_KERNEL | __GFP_ACCOUNT)
#define GFP_NOWAIT	(__GFP_KSWAPD_RECLAIM)
#define GFP_NOIO	(__GFP_RECLAIM)
#define GFP_NOFS	(__GFP_RECLAIM | __GFP_IO)
#define GFP_USER	(__GFP_RECLAIM | __GFP_IO | __GFP_FS | __GFP_HARDWALL)
#define GFP_DMA		__GFP_DMA
#define GFP_DMA32	__GFP_DMA32
#define GFP_HIGHUSER	(GFP_USER | __GFP_HIGHMEM)
#define GFP_HIGHUSER_MOVABLE	(GFP_HIGHUSER | __GFP_MOVABLE | \
			 __GFP_SKIP_KASAN_POISON)
#define GFP_TRANSHUGE_LIGHT	((GFP_HIGHUSER_MOVABLE | __GFP_COMP | \
			 __GFP_NOMEMALLOC | __GFP_NOWARN) & ~__GFP_RECLAIM)
#define GFP_TRANSHUGE	(GFP_TRANSHUGE_LIGHT | __GFP_DIRECT_RECLAIM)

/* Convert GFP flags to their corresponding migrate type */
#define GFP_MOVABLE_MASK (__GFP_RECLAIMABLE|__GFP_MOVABLE)
#define GFP_MOVABLE_SHIFT 3

static inline int gfp_migratetype(const gfp_t gfp_flags)
{
	VM_WARN_ON((gfp_flags & GFP_MOVABLE_MASK) == GFP_MOVABLE_MASK);
	BUILD_BUG_ON((1UL << GFP_MOVABLE_SHIFT) != ___GFP_MOVABLE);
	BUILD_BUG_ON((___GFP_MOVABLE >> GFP_MOVABLE_SHIFT) != MIGRATE_MOVABLE);

	if (unlikely(page_group_by_mobility_disabled))
		return MIGRATE_UNMOVABLE;

	/* Group based on mobility */
	return (gfp_flags & GFP_MOVABLE_MASK) >> GFP_MOVABLE_SHIFT;
}
#undef GFP_MOVABLE_MASK
#undef GFP_MOVABLE_SHIFT

static inline bool gfpflags_allow_blocking(const gfp_t gfp_flags)
{
	return !!(gfp_flags & __GFP_DIRECT_RECLAIM);
}

/**
 * gfpflags_normal_context - is gfp_flags a normal sleepable context?
 * @gfp_flags: gfp_flags to test
 *
 * Test whether @gfp_flags indicates that the allocation is from the
 * %current context and allowed to sleep.
 *
 * An allocation being allowed to block doesn't mean it owns the %current
 * context.  When direct reclaim path tries to allocate memory, the
 * allocation context is nested inside whatever %current was doing at the
 * time of the original allocation.  The nested allocation may be allowed
 * to block but modifying anything %current owns can corrupt the outer
 * context's expectations.
 *
 * %true result from this function indicates that the allocation context
 * can sleep and use anything that's associated with %current.
 */
static inline bool gfpflags_normal_context(const gfp_t gfp_flags)
{
	return (gfp_flags & (__GFP_DIRECT_RECLAIM | __GFP_MEMALLOC)) ==
		__GFP_DIRECT_RECLAIM;
}

#ifdef CONFIG_HIGHMEM
#define OPT_ZONE_HIGHMEM ZONE_HIGHMEM
#else
#define OPT_ZONE_HIGHMEM ZONE_NORMAL
#endif

#ifdef CONFIG_ZONE_DMA
#define OPT_ZONE_DMA ZONE_DMA
#else
#define OPT_ZONE_DMA ZONE_NORMAL
#endif

#ifdef CONFIG_ZONE_DMA32
#define OPT_ZONE_DMA32 ZONE_DMA32
#else
#define OPT_ZONE_DMA32 ZONE_NORMAL
#endif

/*
 * GFP_ZONE_TABLE is a word size bitstring that is used for looking up the
 * zone to use given the lowest 4 bits of gfp_t. Entries are GFP_ZONES_SHIFT
 * bits long and there are 16 of them to cover all possible combinations of
 * __GFP_DMA, __GFP_DMA32, __GFP_MOVABLE and __GFP_HIGHMEM.
 *
 * The zone fallback order is MOVABLE=>HIGHMEM=>NORMAL=>DMA32=>DMA.
 * But GFP_MOVABLE is not only a zone specifier but also an allocation
 * policy. Therefore __GFP_MOVABLE plus another zone selector is valid.
 * Only 1 bit of the lowest 3 bits (DMA,DMA32,HIGHMEM) can be set to "1".
 *
 *       bit       result
 *       =================
 *       0x0    => NORMAL
 *       0x1    => DMA or NORMAL
 *       0x2    => HIGHMEM or NORMAL
 *       0x3    => BAD (DMA+HIGHMEM)
 *       0x4    => DMA32 or NORMAL
 *       0x5    => BAD (DMA+DMA32)
 *       0x6    => BAD (HIGHMEM+DMA32)
 *       0x7    => BAD (HIGHMEM+DMA32+DMA)
 *       0x8    => NORMAL (MOVABLE+0)
 *       0x9    => DMA or NORMAL (MOVABLE+DMA)
 *       0xa    => MOVABLE (Movable is valid only if HIGHMEM is set too)
 *       0xb    => BAD (MOVABLE+HIGHMEM+DMA)
 *       0xc    => DMA32 or NORMAL (MOVABLE+DMA32)
 *       0xd    => BAD (MOVABLE+DMA32+DMA)
 *       0xe    => BAD (MOVABLE+DMA32+HIGHMEM)
 *       0xf    => BAD (MOVABLE+DMA32+HIGHMEM+DMA)
 *
 * GFP_ZONES_SHIFT must be <= 2 on 32 bit platforms.
 */

#if defined(CONFIG_ZONE_DEVICE) && (MAX_NR_ZONES-1) <= 4
/* ZONE_DEVICE is not a valid GFP zone specifier */
#define GFP_ZONES_SHIFT 2
#else
#define GFP_ZONES_SHIFT ZONES_SHIFT
#endif

#if 16 * GFP_ZONES_SHIFT > BITS_PER_LONG
#error GFP_ZONES_SHIFT too large to create GFP_ZONE_TABLE integer
#endif

#define GFP_ZONE_TABLE ( \
	(ZONE_NORMAL << 0 * GFP_ZONES_SHIFT)				       \
	| (OPT_ZONE_DMA << ___GFP_DMA * GFP_ZONES_SHIFT)		       \
	| (OPT_ZONE_HIGHMEM << ___GFP_HIGHMEM * GFP_ZONES_SHIFT)	       \
	| (OPT_ZONE_DMA32 << ___GFP_DMA32 * GFP_ZONES_SHIFT)		       \
	| (ZONE_NORMAL << ___GFP_MOVABLE * GFP_ZONES_SHIFT)		       \
	| (OPT_ZONE_DMA << (___GFP_MOVABLE | ___GFP_DMA) * GFP_ZONES_SHIFT)    \
	| (ZONE_MOVABLE << (___GFP_MOVABLE | ___GFP_HIGHMEM) * GFP_ZONES_SHIFT)\
	| (OPT_ZONE_DMA32 << (___GFP_MOVABLE | ___GFP_DMA32) * GFP_ZONES_SHIFT)\
)

/*
 * GFP_ZONE_BAD is a bitmap for all combinations of __GFP_DMA, __GFP_DMA32
 * __GFP_HIGHMEM and __GFP_MOVABLE that are not permitted. One flag per
 * entry starting with bit 0. Bit is set if the combination is not
 * allowed.
 */
#define GFP_ZONE_BAD ( \
	1 << (___GFP_DMA | ___GFP_HIGHMEM)				      \
	| 1 << (___GFP_DMA | ___GFP_DMA32)				      \
	| 1 << (___GFP_DMA32 | ___GFP_HIGHMEM)				      \
	| 1 << (___GFP_DMA | ___GFP_DMA32 | ___GFP_HIGHMEM)		      \
	| 1 << (___GFP_MOVABLE | ___GFP_HIGHMEM | ___GFP_DMA)		      \
	| 1 << (___GFP_MOVABLE | ___GFP_DMA32 | ___GFP_DMA)		      \
	| 1 << (___GFP_MOVABLE | ___GFP_DMA32 | ___GFP_HIGHMEM)		      \
	| 1 << (___GFP_MOVABLE | ___GFP_DMA32 | ___GFP_DMA | ___GFP_HIGHMEM)  \
)

static inline enum zone_type gfp_zone(gfp_t flags)
{
	enum zone_type z;
	int bit = (__force int) (flags & GFP_ZONEMASK);

	z = (GFP_ZONE_TABLE >> (bit * GFP_ZONES_SHIFT)) &
					 ((1 << GFP_ZONES_SHIFT) - 1);
	VM_BUG_ON((GFP_ZONE_BAD >> bit) & 1);
	return z;
}

/*
 * There is only one page-allocator function, and two main namespaces to
 * it. The alloc_page*() variants return 'struct page *' and as such
 * can allocate highmem pages, the *get*page*() variants return
 * virtual kernel addresses to the allocated page(s).
 */

static inline int gfp_zonelist(gfp_t flags)
{
#ifdef CONFIG_NUMA
	if (unlikely(flags & __GFP_THISNODE))
		return ZONELIST_NOFALLBACK;
#endif
	return ZONELIST_FALLBACK;
}

/*
 * We get the zone list from the current node and the gfp_mask.
 * This zone list contains a maximum of MAX_NUMNODES*MAX_NR_ZONES zones.
 * There are two zonelists per node, one for all zones with memory and
 * one containing just zones from the node the zonelist belongs to.
 *
 * For the case of non-NUMA systems the NODE_DATA() gets optimized to
 * &contig_page_data at compile-time.
 */
static inline struct zonelist *node_zonelist(int nid, gfp_t flags)
{
	return NODE_DATA(nid)->node_zonelists + gfp_zonelist(flags);
}

#ifndef HAVE_ARCH_FREE_PAGE
static inline void arch_free_page(struct page *page, int order) { }
#endif
#ifndef HAVE_ARCH_ALLOC_PAGE
static inline void arch_alloc_page(struct page *page, int order) { }
#endif

struct page *__alloc_pages(gfp_t gfp, unsigned int order, int preferred_nid,
		nodemask_t *nodemask);
struct folio *__folio_alloc(gfp_t gfp, unsigned int order, int preferred_nid,
		nodemask_t *nodemask);

unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid,
				nodemask_t *nodemask, int nr_pages,
				struct list_head *page_list,
				struct page **page_array);

unsigned long alloc_pages_bulk_array_mempolicy(gfp_t gfp,
				unsigned long nr_pages,
				struct page **page_array);

/* Bulk allocate order-0 pages */
static inline unsigned long
alloc_pages_bulk_list(gfp_t gfp, unsigned long nr_pages, struct list_head *list)
{
	return __alloc_pages_bulk(gfp, numa_mem_id(), NULL, nr_pages, list, NULL);
}

static inline unsigned long
alloc_pages_bulk_array(gfp_t gfp, unsigned long nr_pages, struct page **page_array)
{
	return __alloc_pages_bulk(gfp, numa_mem_id(), NULL, nr_pages, NULL, page_array);
}

static inline unsigned long
alloc_pages_bulk_array_node(gfp_t gfp, int nid, unsigned long nr_pages, struct page **page_array)
{
	if (nid == NUMA_NO_NODE)
		nid = numa_mem_id();

	return __alloc_pages_bulk(gfp, nid, NULL, nr_pages, NULL, page_array);
}

/*
 * Allocate pages, preferring the node given as nid. The node must be valid and
 * online. For more general interface, see alloc_pages_node().
 */
static inline struct page *
__alloc_pages_node(int nid, gfp_t gfp_mask, unsigned int order)
{
	VM_BUG_ON(nid < 0 || nid >= MAX_NUMNODES);
	VM_WARN_ON((gfp_mask & __GFP_THISNODE) && !node_online(nid));

	return __alloc_pages(gfp_mask, order, nid, NULL);
}

static inline
struct folio *__folio_alloc_node(gfp_t gfp, unsigned int order, int nid)
{
	VM_BUG_ON(nid < 0 || nid >= MAX_NUMNODES);
	VM_WARN_ON((gfp & __GFP_THISNODE) && !node_online(nid));

	return __folio_alloc(gfp, order, nid, NULL);
}

/*
 * Allocate pages, preferring the node given as nid. When nid == NUMA_NO_NODE,
 * prefer the current CPU's closest node. Otherwise node must be valid and
 * online.
 */
static inline struct page *alloc_pages_node(int nid, gfp_t gfp_mask,
						unsigned int order)
{
	if (nid == NUMA_NO_NODE)
		nid = numa_mem_id();

	return __alloc_pages_node(nid, gfp_mask, order);
}

#ifdef CONFIG_NUMA
struct page *alloc_pages(gfp_t gfp, unsigned int order);
struct folio *folio_alloc(gfp_t gfp, unsigned order);
extern struct page *alloc_pages_vma(gfp_t gfp_mask, int order,
			struct vm_area_struct *vma, unsigned long addr,
			bool hugepage);
#define alloc_hugepage_vma(gfp_mask, vma, addr, order) \
	alloc_pages_vma(gfp_mask, order, vma, addr, true)
#else
static inline struct page *alloc_pages(gfp_t gfp_mask, unsigned int order)
{
	return alloc_pages_node(numa_node_id(), gfp_mask, order);
}
static inline struct folio *folio_alloc(gfp_t gfp, unsigned int order)
{
	return __folio_alloc_node(gfp, order, numa_node_id());
}
#define alloc_pages_vma(gfp_mask, order, vma, addr, false)\
	alloc_pages(gfp_mask, order)
#define alloc_hugepage_vma(gfp_mask, vma, addr, order) \
	alloc_pages(gfp_mask, order)
#endif
#define alloc_page(gfp_mask) alloc_pages(gfp_mask, 0)
#define alloc_page_vma(gfp_mask, vma, addr)			\
	alloc_pages_vma(gfp_mask, 0, vma, addr, false)

extern unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order);
extern unsigned long get_zeroed_page(gfp_t gfp_mask);

void *alloc_pages_exact(size_t size, gfp_t gfp_mask) __alloc_size(1);
void free_pages_exact(void *virt, size_t size);
__meminit void *alloc_pages_exact_nid(int nid, size_t size, gfp_t gfp_mask) __alloc_size(2);

#define __get_free_page(gfp_mask) \
		__get_free_pages((gfp_mask), 0)

#define __get_dma_pages(gfp_mask, order) \
		__get_free_pages((gfp_mask) | GFP_DMA, (order))

extern void __free_pages(struct page *page, unsigned int order);
extern void free_pages(unsigned long addr, unsigned int order);

struct page_frag_cache;
extern void __page_frag_cache_drain(struct page *page, unsigned int count);
extern void *page_frag_alloc_align(struct page_frag_cache *nc,
				   unsigned int fragsz, gfp_t gfp_mask,
				   unsigned int align_mask);

static inline void *page_frag_alloc(struct page_frag_cache *nc,
			     unsigned int fragsz, gfp_t gfp_mask)
{
	return page_frag_alloc_align(nc, fragsz, gfp_mask, ~0u);
}

extern void page_frag_free(void *addr);

#define __free_page(page) __free_pages((page), 0)
#define free_page(addr) free_pages((addr), 0)

void page_alloc_init(void);
void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp);
void drain_all_pages(struct zone *zone);
void drain_local_pages(struct zone *zone);

void page_alloc_init_late(void);

/*
 * gfp_allowed_mask is set to GFP_BOOT_MASK during early boot to restrict what
 * GFP flags are used before interrupts are enabled. Once interrupts are
 * enabled, it is set to __GFP_BITS_MASK while the system is running. During
 * hibernation, it is used by PM to avoid I/O during memory allocation while
 * devices are suspended.
 */
extern gfp_t gfp_allowed_mask;

/* Returns true if the gfp_mask allows use of ALLOC_NO_WATERMARK */
bool gfp_pfmemalloc_allowed(gfp_t gfp_mask);

extern void pm_restrict_gfp_mask(void);
extern void pm_restore_gfp_mask(void);

extern gfp_t vma_thp_gfp_mask(struct vm_area_struct *vma);

#ifdef CONFIG_PM_SLEEP
extern bool pm_suspended_storage(void);
#else
static inline bool pm_suspended_storage(void)
{
	return false;
}
#endif /* CONFIG_PM_SLEEP */

#ifdef CONFIG_CONTIG_ALLOC
/* The below functions must be run on a range from a single zone. */
extern int alloc_contig_range(unsigned long start, unsigned long end,
			      unsigned migratetype, gfp_t gfp_mask);
extern struct page *alloc_contig_pages(unsigned long nr_pages, gfp_t gfp_mask,
				       int nid, nodemask_t *nodemask);
#endif
void free_contig_range(unsigned long pfn, unsigned long nr_pages);

#ifdef CONFIG_CMA
/* CMA stuff */
extern void init_cma_reserved_pageblock(struct page *page);
#endif

#endif /* __LINUX_GFP_H */