aboutsummaryrefslogtreecommitdiff
path: root/arch/powerpc/mm/hugetlbpage.c
blob: c41dc44472c5cf1babd0e71177ac0d5615825645 (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
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
/*
 * PPC Huge TLB Page Support for Kernel.
 *
 * Copyright (C) 2003 David Gibson, IBM Corporation.
 * Copyright (C) 2011 Becky Bruce, Freescale Semiconductor
 *
 * Based on the IA-32 version:
 * Copyright (C) 2002, Rohit Seth <rohit.seth@intel.com>
 */

#include <linux/mm.h>
#include <linux/io.h>
#include <linux/slab.h>
#include <linux/hugetlb.h>
#include <linux/export.h>
#include <linux/of_fdt.h>
#include <linux/memblock.h>
#include <linux/bootmem.h>
#include <linux/moduleparam.h>
#include <linux/swap.h>
#include <linux/swapops.h>
#include <asm/pgtable.h>
#include <asm/pgalloc.h>
#include <asm/tlb.h>
#include <asm/setup.h>
#include <asm/hugetlb.h>

#ifdef CONFIG_HUGETLB_PAGE

#define PAGE_SHIFT_64K	16
#define PAGE_SHIFT_512K	19
#define PAGE_SHIFT_8M	23
#define PAGE_SHIFT_16M	24
#define PAGE_SHIFT_16G	34

unsigned int HPAGE_SHIFT;

/*
 * Tracks gpages after the device tree is scanned and before the
 * huge_boot_pages list is ready.  On non-Freescale implementations, this is
 * just used to track 16G pages and so is a single array.  FSL-based
 * implementations may have more than one gpage size, so we need multiple
 * arrays
 */
#if defined(CONFIG_PPC_FSL_BOOK3E) || defined(CONFIG_PPC_8xx)
#define MAX_NUMBER_GPAGES	128
struct psize_gpages {
	u64 gpage_list[MAX_NUMBER_GPAGES];
	unsigned int nr_gpages;
};
static struct psize_gpages gpage_freearray[MMU_PAGE_COUNT];
#else
#define MAX_NUMBER_GPAGES	1024
static u64 gpage_freearray[MAX_NUMBER_GPAGES];
static unsigned nr_gpages;
#endif

#define hugepd_none(hpd)	(hpd_val(hpd) == 0)

pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, unsigned long sz)
{
	/* Only called for hugetlbfs pages, hence can ignore THP */
	return __find_linux_pte_or_hugepte(mm->pgd, addr, NULL, NULL);
}

static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp,
			   unsigned long address, unsigned pdshift, unsigned pshift)
{
	struct kmem_cache *cachep;
	pte_t *new;
	int i;
	int num_hugepd;

	if (pshift >= pdshift) {
		cachep = hugepte_cache;
		num_hugepd = 1 << (pshift - pdshift);
	} else {
		cachep = PGT_CACHE(pdshift - pshift);
		num_hugepd = 1;
	}

	new = kmem_cache_zalloc(cachep, GFP_KERNEL);

	BUG_ON(pshift > HUGEPD_SHIFT_MASK);
	BUG_ON((unsigned long)new & HUGEPD_SHIFT_MASK);

	if (! new)
		return -ENOMEM;

	/*
	 * Make sure other cpus find the hugepd set only after a
	 * properly initialized page table is visible to them.
	 * For more details look for comment in __pte_alloc().
	 */
	smp_wmb();

	spin_lock(&mm->page_table_lock);

	/*
	 * We have multiple higher-level entries that point to the same
	 * actual pte location.  Fill in each as we go and backtrack on error.
	 * We need all of these so the DTLB pgtable walk code can find the
	 * right higher-level entry without knowing if it's a hugepage or not.
	 */
	for (i = 0; i < num_hugepd; i++, hpdp++) {
		if (unlikely(!hugepd_none(*hpdp)))
			break;
		else {
#ifdef CONFIG_PPC_BOOK3S_64
			*hpdp = __hugepd(__pa(new) |
					 (shift_to_mmu_psize(pshift) << 2));
#elif defined(CONFIG_PPC_8xx)
			*hpdp = __hugepd(__pa(new) |
					 (pshift == PAGE_SHIFT_8M ? _PMD_PAGE_8M :
					  _PMD_PAGE_512K) | _PMD_PRESENT);
#else
			/* We use the old format for PPC_FSL_BOOK3E */
			*hpdp = __hugepd(((unsigned long)new & ~PD_HUGE) | pshift);
#endif
		}
	}
	/* If we bailed from the for loop early, an error occurred, clean up */
	if (i < num_hugepd) {
		for (i = i - 1 ; i >= 0; i--, hpdp--)
			*hpdp = __hugepd(0);
		kmem_cache_free(cachep, new);
	}
	spin_unlock(&mm->page_table_lock);
	return 0;
}

/*
 * These macros define how to determine which level of the page table holds
 * the hpdp.
 */
#if defined(CONFIG_PPC_FSL_BOOK3E) || defined(CONFIG_PPC_8xx)
#define HUGEPD_PGD_SHIFT PGDIR_SHIFT
#define HUGEPD_PUD_SHIFT PUD_SHIFT
#else
#define HUGEPD_PGD_SHIFT PUD_SHIFT
#define HUGEPD_PUD_SHIFT PMD_SHIFT
#endif

/*
 * At this point we do the placement change only for BOOK3S 64. This would
 * possibly work on other subarchs.
 */
pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr, unsigned long sz)
{
	pgd_t *pg;
	pud_t *pu;
	pmd_t *pm;
	hugepd_t *hpdp = NULL;
	unsigned pshift = __ffs(sz);
	unsigned pdshift = PGDIR_SHIFT;

	addr &= ~(sz-1);
	pg = pgd_offset(mm, addr);

#ifdef CONFIG_PPC_BOOK3S_64
	if (pshift == PGDIR_SHIFT)
		/* 16GB huge page */
		return (pte_t *) pg;
	else if (pshift > PUD_SHIFT)
		/*
		 * We need to use hugepd table
		 */
		hpdp = (hugepd_t *)pg;
	else {
		pdshift = PUD_SHIFT;
		pu = pud_alloc(mm, pg, addr);
		if (pshift == PUD_SHIFT)
			return (pte_t *)pu;
		else if (pshift > PMD_SHIFT)
			hpdp = (hugepd_t *)pu;
		else {
			pdshift = PMD_SHIFT;
			pm = pmd_alloc(mm, pu, addr);
			if (pshift == PMD_SHIFT)
				/* 16MB hugepage */
				return (pte_t *)pm;
			else
				hpdp = (hugepd_t *)pm;
		}
	}
#else
	if (pshift >= HUGEPD_PGD_SHIFT) {
		hpdp = (hugepd_t *)pg;
	} else {
		pdshift = PUD_SHIFT;
		pu = pud_alloc(mm, pg, addr);
		if (pshift >= HUGEPD_PUD_SHIFT) {
			hpdp = (hugepd_t *)pu;
		} else {
			pdshift = PMD_SHIFT;
			pm = pmd_alloc(mm, pu, addr);
			hpdp = (hugepd_t *)pm;
		}
	}
#endif
	if (!hpdp)
		return NULL;

	BUG_ON(!hugepd_none(*hpdp) && !hugepd_ok(*hpdp));

	if (hugepd_none(*hpdp) && __hugepte_alloc(mm, hpdp, addr, pdshift, pshift))
		return NULL;

	return hugepte_offset(*hpdp, addr, pdshift);
}

#if defined(CONFIG_PPC_FSL_BOOK3E) || defined(CONFIG_PPC_8xx)
/* Build list of addresses of gigantic pages.  This function is used in early
 * boot before the buddy allocator is setup.
 */
void add_gpage(u64 addr, u64 page_size, unsigned long number_of_pages)
{
	unsigned int idx = shift_to_mmu_psize(__ffs(page_size));
	int i;

	if (addr == 0)
		return;

	gpage_freearray[idx].nr_gpages = number_of_pages;

	for (i = 0; i < number_of_pages; i++) {
		gpage_freearray[idx].gpage_list[i] = addr;
		addr += page_size;
	}
}

/*
 * Moves the gigantic page addresses from the temporary list to the
 * huge_boot_pages list.
 */
int alloc_bootmem_huge_page(struct hstate *hstate)
{
	struct huge_bootmem_page *m;
	int idx = shift_to_mmu_psize(huge_page_shift(hstate));
	int nr_gpages = gpage_freearray[idx].nr_gpages;

	if (nr_gpages == 0)
		return 0;

#ifdef CONFIG_HIGHMEM
	/*
	 * If gpages can be in highmem we can't use the trick of storing the
	 * data structure in the page; allocate space for this
	 */
	m = memblock_virt_alloc(sizeof(struct huge_bootmem_page), 0);
	m->phys = gpage_freearray[idx].gpage_list[--nr_gpages];
#else
	m = phys_to_virt(gpage_freearray[idx].gpage_list[--nr_gpages]);
#endif

	list_add(&m->list, &huge_boot_pages);
	gpage_freearray[idx].nr_gpages = nr_gpages;
	gpage_freearray[idx].gpage_list[nr_gpages] = 0;
	m->hstate = hstate;

	return 1;
}
/*
 * Scan the command line hugepagesz= options for gigantic pages; store those in
 * a list that we use to allocate the memory once all options are parsed.
 */

unsigned long gpage_npages[MMU_PAGE_COUNT];

static int __init do_gpage_early_setup(char *param, char *val,
				       const char *unused, void *arg)
{
	static phys_addr_t size;
	unsigned long npages;

	/*
	 * The hugepagesz and hugepages cmdline options are interleaved.  We
	 * use the size variable to keep track of whether or not this was done
	 * properly and skip over instances where it is incorrect.  Other
	 * command-line parsing code will issue warnings, so we don't need to.
	 *
	 */
	if ((strcmp(param, "default_hugepagesz") == 0) ||
	    (strcmp(param, "hugepagesz") == 0)) {
		size = memparse(val, NULL);
	} else if (strcmp(param, "hugepages") == 0) {
		if (size != 0) {
			if (sscanf(val, "%lu", &npages) <= 0)
				npages = 0;
			if (npages > MAX_NUMBER_GPAGES) {
				pr_warn("MMU: %lu pages requested for page "
#ifdef CONFIG_PHYS_ADDR_T_64BIT
					"size %llu KB, limiting to "
#else
					"size %u KB, limiting to "
#endif
					__stringify(MAX_NUMBER_GPAGES) "\n",
					npages, size / 1024);
				npages = MAX_NUMBER_GPAGES;
			}
			gpage_npages[shift_to_mmu_psize(__ffs(size))] = npages;
			size = 0;
		}
	}
	return 0;
}


/*
 * This function allocates physical space for pages that are larger than the
 * buddy allocator can handle.  We want to allocate these in highmem because
 * the amount of lowmem is limited.  This means that this function MUST be
 * called before lowmem_end_addr is set up in MMU_init() in order for the lmb
 * allocate to grab highmem.
 */
void __init reserve_hugetlb_gpages(void)
{
	static __initdata char cmdline[COMMAND_LINE_SIZE];
	phys_addr_t size, base;
	int i;

	strlcpy(cmdline, boot_command_line, COMMAND_LINE_SIZE);
	parse_args("hugetlb gpages", cmdline, NULL, 0, 0, 0,
			NULL, &do_gpage_early_setup);

	/*
	 * Walk gpage list in reverse, allocating larger page sizes first.
	 * Skip over unsupported sizes, or sizes that have 0 gpages allocated.
	 * When we reach the point in the list where pages are no longer
	 * considered gpages, we're done.
	 */
	for (i = MMU_PAGE_COUNT-1; i >= 0; i--) {
		if (mmu_psize_defs[i].shift == 0 || gpage_npages[i] == 0)
			continue;
		else if (mmu_psize_to_shift(i) < (MAX_ORDER + PAGE_SHIFT))
			break;

		size = (phys_addr_t)(1ULL << mmu_psize_to_shift(i));
		base = memblock_alloc_base(size * gpage_npages[i], size,
					   MEMBLOCK_ALLOC_ANYWHERE);
		add_gpage(base, size, gpage_npages[i]);
	}
}

#else /* !PPC_FSL_BOOK3E */

/* Build list of addresses of gigantic pages.  This function is used in early
 * boot before the buddy allocator is setup.
 */
void add_gpage(u64 addr, u64 page_size, unsigned long number_of_pages)
{
	if (!addr)
		return;
	while (number_of_pages > 0) {
		gpage_freearray[nr_gpages] = addr;
		nr_gpages++;
		number_of_pages--;
		addr += page_size;
	}
}

/* Moves the gigantic page addresses from the temporary list to the
 * huge_boot_pages list.
 */
int alloc_bootmem_huge_page(struct hstate *hstate)
{
	struct huge_bootmem_page *m;
	if (nr_gpages == 0)
		return 0;
	m = phys_to_virt(gpage_freearray[--nr_gpages]);
	gpage_freearray[nr_gpages] = 0;
	list_add(&m->list, &huge_boot_pages);
	m->hstate = hstate;
	return 1;
}
#endif

#if defined(CONFIG_PPC_FSL_BOOK3E) || defined(CONFIG_PPC_8xx)
#define HUGEPD_FREELIST_SIZE \
	((PAGE_SIZE - sizeof(struct hugepd_freelist)) / sizeof(pte_t))

struct hugepd_freelist {
	struct rcu_head	rcu;
	unsigned int index;
	void *ptes[0];
};

static DEFINE_PER_CPU(struct hugepd_freelist *, hugepd_freelist_cur);

static void hugepd_free_rcu_callback(struct rcu_head *head)
{
	struct hugepd_freelist *batch =
		container_of(head, struct hugepd_freelist, rcu);
	unsigned int i;

	for (i = 0; i < batch->index; i++)
		kmem_cache_free(hugepte_cache, batch->ptes[i]);

	free_page((unsigned long)batch);
}

static void hugepd_free(struct mmu_gather *tlb, void *hugepte)
{
	struct hugepd_freelist **batchp;

	batchp = &get_cpu_var(hugepd_freelist_cur);

	if (atomic_read(&tlb->mm->mm_users) < 2 ||
	    cpumask_equal(mm_cpumask(tlb->mm),
			  cpumask_of(smp_processor_id()))) {
		kmem_cache_free(hugepte_cache, hugepte);
		put_cpu_var(hugepd_freelist_cur);
		return;
	}

	if (*batchp == NULL) {
		*batchp = (struct hugepd_freelist *)__get_free_page(GFP_ATOMIC);
		(*batchp)->index = 0;
	}

	(*batchp)->ptes[(*batchp)->index++] = hugepte;
	if ((*batchp)->index == HUGEPD_FREELIST_SIZE) {
		call_rcu_sched(&(*batchp)->rcu, hugepd_free_rcu_callback);
		*batchp = NULL;
	}
	put_cpu_var(hugepd_freelist_cur);
}
#else
static inline void hugepd_free(struct mmu_gather *tlb, void *hugepte) {}
#endif

static void free_hugepd_range(struct mmu_gather *tlb, hugepd_t *hpdp, int pdshift,
			      unsigned long start, unsigned long end,
			      unsigned long floor, unsigned long ceiling)
{
	pte_t *hugepte = hugepd_page(*hpdp);
	int i;

	unsigned long pdmask = ~((1UL << pdshift) - 1);
	unsigned int num_hugepd = 1;
	unsigned int shift = hugepd_shift(*hpdp);

	/* Note: On fsl the hpdp may be the first of several */
	if (shift > pdshift)
		num_hugepd = 1 << (shift - pdshift);

	start &= pdmask;
	if (start < floor)
		return;
	if (ceiling) {
		ceiling &= pdmask;
		if (! ceiling)
			return;
	}
	if (end - 1 > ceiling - 1)
		return;

	for (i = 0; i < num_hugepd; i++, hpdp++)
		*hpdp = __hugepd(0);

	if (shift >= pdshift)
		hugepd_free(tlb, hugepte);
	else
		pgtable_free_tlb(tlb, hugepte, pdshift - shift);
}

static void hugetlb_free_pmd_range(struct mmu_gather *tlb, pud_t *pud,
				   unsigned long addr, unsigned long end,
				   unsigned long floor, unsigned long ceiling)
{
	pmd_t *pmd;
	unsigned long next;
	unsigned long start;

	start = addr;
	do {
		unsigned long more;

		pmd = pmd_offset(pud, addr);
		next = pmd_addr_end(addr, end);
		if (!is_hugepd(__hugepd(pmd_val(*pmd)))) {
			/*
			 * if it is not hugepd pointer, we should already find
			 * it cleared.
			 */
			WARN_ON(!pmd_none_or_clear_bad(pmd));
			continue;
		}
		/*
		 * Increment next by the size of the huge mapping since
		 * there may be more than one entry at this level for a
		 * single hugepage, but all of them point to
		 * the same kmem cache that holds the hugepte.
		 */
		more = addr + (1 << hugepd_shift(*(hugepd_t *)pmd));
		if (more > next)
			next = more;

		free_hugepd_range(tlb, (hugepd_t *)pmd, PMD_SHIFT,
				  addr, next, floor, ceiling);
	} while (addr = next, addr != end);

	start &= PUD_MASK;
	if (start < floor)
		return;
	if (ceiling) {
		ceiling &= PUD_MASK;
		if (!ceiling)
			return;
	}
	if (end - 1 > ceiling - 1)
		return;

	pmd = pmd_offset(pud, start);
	pud_clear(pud);
	pmd_free_tlb(tlb, pmd, start);
	mm_dec_nr_pmds(tlb->mm);
}

static void hugetlb_free_pud_range(struct mmu_gather *tlb, pgd_t *pgd,
				   unsigned long addr, unsigned long end,
				   unsigned long floor, unsigned long ceiling)
{
	pud_t *pud;
	unsigned long next;
	unsigned long start;

	start = addr;
	do {
		pud = pud_offset(pgd, addr);
		next = pud_addr_end(addr, end);
		if (!is_hugepd(__hugepd(pud_val(*pud)))) {
			if (pud_none_or_clear_bad(pud))
				continue;
			hugetlb_free_pmd_range(tlb, pud, addr, next, floor,
					       ceiling);
		} else {
			unsigned long more;
			/*
			 * Increment next by the size of the huge mapping since
			 * there may be more than one entry at this level for a
			 * single hugepage, but all of them point to
			 * the same kmem cache that holds the hugepte.
			 */
			more = addr + (1 << hugepd_shift(*(hugepd_t *)pud));
			if (more > next)
				next = more;

			free_hugepd_range(tlb, (hugepd_t *)pud, PUD_SHIFT,
					  addr, next, floor, ceiling);
		}
	} while (addr = next, addr != end);

	start &= PGDIR_MASK;
	if (start < floor)
		return;
	if (ceiling) {
		ceiling &= PGDIR_MASK;
		if (!ceiling)
			return;
	}
	if (end - 1 > ceiling - 1)
		return;

	pud = pud_offset(pgd, start);
	pgd_clear(pgd);
	pud_free_tlb(tlb, pud, start);
}

/*
 * This function frees user-level page tables of a process.
 */
void hugetlb_free_pgd_range(struct mmu_gather *tlb,
			    unsigned long addr, unsigned long end,
			    unsigned long floor, unsigned long ceiling)
{
	pgd_t *pgd;
	unsigned long next;

	/*
	 * Because there are a number of different possible pagetable
	 * layouts for hugepage ranges, we limit knowledge of how
	 * things should be laid out to the allocation path
	 * (huge_pte_alloc(), above).  Everything else works out the
	 * structure as it goes from information in the hugepd
	 * pointers.  That means that we can't here use the
	 * optimization used in the normal page free_pgd_range(), of
	 * checking whether we're actually covering a large enough
	 * range to have to do anything at the top level of the walk
	 * instead of at the bottom.
	 *
	 * To make sense of this, you should probably go read the big
	 * block comment at the top of the normal free_pgd_range(),
	 * too.
	 */

	do {
		next = pgd_addr_end(addr, end);
		pgd = pgd_offset(tlb->mm, addr);
		if (!is_hugepd(__hugepd(pgd_val(*pgd)))) {
			if (pgd_none_or_clear_bad(pgd))
				continue;
			hugetlb_free_pud_range(tlb, pgd, addr, next, floor, ceiling);
		} else {
			unsigned long more;
			/*
			 * Increment next by the size of the huge mapping since
			 * there may be more than one entry at the pgd level
			 * for a single hugepage, but all of them point to the
			 * same kmem cache that holds the hugepte.
			 */
			more = addr + (1 << hugepd_shift(*(hugepd_t *)pgd));
			if (more > next)
				next = more;

			free_hugepd_range(tlb, (hugepd_t *)pgd, PGDIR_SHIFT,
					  addr, next, floor, ceiling);
		}
	} while (addr = next, addr != end);
}

struct page *follow_huge_pd(struct vm_area_struct *vma,
			    unsigned long address, hugepd_t hpd,
			    int flags, int pdshift)
{
	pte_t *ptep;
	spinlock_t *ptl;
	struct page *page = NULL;
	unsigned long mask;
	int shift = hugepd_shift(hpd);
	struct mm_struct *mm = vma->vm_mm;

retry:
	ptl = &mm->page_table_lock;
	spin_lock(ptl);

	ptep = hugepte_offset(hpd, address, pdshift);
	if (pte_present(*ptep)) {
		mask = (1UL << shift) - 1;
		page = pte_page(*ptep);
		page += ((address & mask) >> PAGE_SHIFT);
		if (flags & FOLL_GET)
			get_page(page);
	} else {
		if (is_hugetlb_entry_migration(*ptep)) {
			spin_unlock(ptl);
			__migration_entry_wait(mm, ptep, ptl);
			goto retry;
		}
	}
	spin_unlock(ptl);
	return page;
}

static unsigned long hugepte_addr_end(unsigned long addr, unsigned long end,
				      unsigned long sz)
{
	unsigned long __boundary = (addr + sz) & ~(sz-1);
	return (__boundary - 1 < end - 1) ? __boundary : end;
}

int gup_huge_pd(hugepd_t hugepd, unsigned long addr, unsigned pdshift,
		unsigned long end, int write, struct page **pages, int *nr)
{
	pte_t *ptep;
	unsigned long sz = 1UL << hugepd_shift(hugepd);
	unsigned long next;

	ptep = hugepte_offset(hugepd, addr, pdshift);
	do {
		next = hugepte_addr_end(addr, end, sz);
		if (!gup_hugepte(ptep, sz, addr, end, write, pages, nr))
			return 0;
	} while (ptep++, addr = next, addr != end);

	return 1;
}

#ifdef CONFIG_PPC_MM_SLICES
unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
					unsigned long len, unsigned long pgoff,
					unsigned long flags)
{
	struct hstate *hstate = hstate_file(file);
	int mmu_psize = shift_to_mmu_psize(huge_page_shift(hstate));

	if (radix_enabled())
		return radix__hugetlb_get_unmapped_area(file, addr, len,
						       pgoff, flags);
	return slice_get_unmapped_area(addr, len, flags, mmu_psize, 1);
}
#endif

unsigned long vma_mmu_pagesize(struct vm_area_struct *vma)
{
#ifdef CONFIG_PPC_MM_SLICES
	unsigned int psize = get_slice_psize(vma->vm_mm, vma->vm_start);
	/* With radix we don't use slice, so derive it from vma*/
	if (!radix_enabled())
		return 1UL << mmu_psize_to_shift(psize);
#endif
	if (!is_vm_hugetlb_page(vma))
		return PAGE_SIZE;

	return huge_page_size(hstate_vma(vma));
}

static inline bool is_power_of_4(unsigned long x)
{
	if (is_power_of_2(x))
		return (__ilog2(x) % 2) ? false : true;
	return false;
}

static int __init add_huge_page_size(unsigned long long size)
{
	int shift = __ffs(size);
	int mmu_psize;

	/* Check that it is a page size supported by the hardware and
	 * that it fits within pagetable and slice limits. */
	if (size <= PAGE_SIZE)
		return -EINVAL;
#if defined(CONFIG_PPC_FSL_BOOK3E)
	if (!is_power_of_4(size))
		return -EINVAL;
#elif !defined(CONFIG_PPC_8xx)
	if (!is_power_of_2(size) || (shift > SLICE_HIGH_SHIFT))
		return -EINVAL;
#endif

	if ((mmu_psize = shift_to_mmu_psize(shift)) < 0)
		return -EINVAL;

#ifdef CONFIG_PPC_BOOK3S_64
	/*
	 * We need to make sure that for different page sizes reported by
	 * firmware we only add hugetlb support for page sizes that can be
	 * supported by linux page table layout.
	 * For now we have
	 * Radix: 2M
	 * Hash: 16M and 16G
	 */
	if (radix_enabled()) {
		if (mmu_psize != MMU_PAGE_2M) {
			if (cpu_has_feature(CPU_FTR_POWER9_DD1) ||
			    (mmu_psize != MMU_PAGE_1G))
				return -EINVAL;
		}
	} else {
		if (mmu_psize != MMU_PAGE_16M && mmu_psize != MMU_PAGE_16G)
			return -EINVAL;
	}
#endif

	BUG_ON(mmu_psize_defs[mmu_psize].shift != shift);

	/* Return if huge page size has already been setup */
	if (size_to_hstate(size))
		return 0;

	hugetlb_add_hstate(shift - PAGE_SHIFT);

	return 0;
}

static int __init hugepage_setup_sz(char *str)
{
	unsigned long long size;

	size = memparse(str, &str);

	if (add_huge_page_size(size) != 0) {
		hugetlb_bad_size();
		pr_err("Invalid huge page size specified(%llu)\n", size);
	}

	return 1;
}
__setup("hugepagesz=", hugepage_setup_sz);

struct kmem_cache *hugepte_cache;
static int __init hugetlbpage_init(void)
{
	int psize;

#if !defined(CONFIG_PPC_FSL_BOOK3E) && !defined(CONFIG_PPC_8xx)
	if (!radix_enabled() && !mmu_has_feature(MMU_FTR_16M_PAGE))
		return -ENODEV;
#endif
	for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) {
		unsigned shift;
		unsigned pdshift;

		if (!mmu_psize_defs[psize].shift)
			continue;

		shift = mmu_psize_to_shift(psize);

		if (add_huge_page_size(1ULL << shift) < 0)
			continue;

		if (shift < HUGEPD_PUD_SHIFT)
			pdshift = PMD_SHIFT;
		else if (shift < HUGEPD_PGD_SHIFT)
			pdshift = PUD_SHIFT;
		else
			pdshift = PGDIR_SHIFT;
		/*
		 * if we have pdshift and shift value same, we don't
		 * use pgt cache for hugepd.
		 */
		if (pdshift > shift)
			pgtable_cache_add(pdshift - shift, NULL);
#if defined(CONFIG_PPC_FSL_BOOK3E) || defined(CONFIG_PPC_8xx)
		else if (!hugepte_cache) {
			/*
			 * Create a kmem cache for hugeptes.  The bottom bits in
			 * the pte have size information encoded in them, so
			 * align them to allow this
			 */
			hugepte_cache = kmem_cache_create("hugepte-cache",
							  sizeof(pte_t),
							  HUGEPD_SHIFT_MASK + 1,
							  0, NULL);
			if (hugepte_cache == NULL)
				panic("%s: Unable to create kmem cache "
				      "for hugeptes\n", __func__);

		}
#endif
	}

#if defined(CONFIG_PPC_FSL_BOOK3E) || defined(CONFIG_PPC_8xx)
	/* Default hpage size = 4M on FSL_BOOK3E and 512k on 8xx */
	if (mmu_psize_defs[MMU_PAGE_4M].shift)
		HPAGE_SHIFT = mmu_psize_defs[MMU_PAGE_4M].shift;
	else if (mmu_psize_defs[MMU_PAGE_512K].shift)
		HPAGE_SHIFT = mmu_psize_defs[MMU_PAGE_512K].shift;
#else
	/* Set default large page size. Currently, we pick 16M or 1M
	 * depending on what is available
	 */
	if (mmu_psize_defs[MMU_PAGE_16M].shift)
		HPAGE_SHIFT = mmu_psize_defs[MMU_PAGE_16M].shift;
	else if (mmu_psize_defs[MMU_PAGE_1M].shift)
		HPAGE_SHIFT = mmu_psize_defs[MMU_PAGE_1M].shift;
	else if (mmu_psize_defs[MMU_PAGE_2M].shift)
		HPAGE_SHIFT = mmu_psize_defs[MMU_PAGE_2M].shift;
#endif
	return 0;
}

arch_initcall(hugetlbpage_init);

void flush_dcache_icache_hugepage(struct page *page)
{
	int i;
	void *start;

	BUG_ON(!PageCompound(page));

	for (i = 0; i < (1UL << compound_order(page)); i++) {
		if (!PageHighMem(page)) {
			__flush_dcache_icache(page_address(page+i));
		} else {
			start = kmap_atomic(page+i);
			__flush_dcache_icache(start);
			kunmap_atomic(start);
		}
	}
}

#endif /* CONFIG_HUGETLB_PAGE */

/*
 * We have 4 cases for pgds and pmds:
 * (1) invalid (all zeroes)
 * (2) pointer to next table, as normal; bottom 6 bits == 0
 * (3) leaf pte for huge page _PAGE_PTE set
 * (4) hugepd pointer, _PAGE_PTE = 0 and bits [2..6] indicate size of table
 *
 * So long as we atomically load page table pointers we are safe against teardown,
 * we can follow the address down to the the page and take a ref on it.
 * This function need to be called with interrupts disabled. We use this variant
 * when we have MSR[EE] = 0 but the paca->soft_enabled = 1
 */

pte_t *__find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea,
				   bool *is_thp, unsigned *shift)
{
	pgd_t pgd, *pgdp;
	pud_t pud, *pudp;
	pmd_t pmd, *pmdp;
	pte_t *ret_pte;
	hugepd_t *hpdp = NULL;
	unsigned pdshift = PGDIR_SHIFT;

	if (shift)
		*shift = 0;

	if (is_thp)
		*is_thp = false;

	pgdp = pgdir + pgd_index(ea);
	pgd  = READ_ONCE(*pgdp);
	/*
	 * Always operate on the local stack value. This make sure the
	 * value don't get updated by a parallel THP split/collapse,
	 * page fault or a page unmap. The return pte_t * is still not
	 * stable. So should be checked there for above conditions.
	 */
	if (pgd_none(pgd))
		return NULL;
	else if (pgd_huge(pgd)) {
		ret_pte = (pte_t *) pgdp;
		goto out;
	} else if (is_hugepd(__hugepd(pgd_val(pgd))))
		hpdp = (hugepd_t *)&pgd;
	else {
		/*
		 * Even if we end up with an unmap, the pgtable will not
		 * be freed, because we do an rcu free and here we are
		 * irq disabled
		 */
		pdshift = PUD_SHIFT;
		pudp = pud_offset(&pgd, ea);
		pud  = READ_ONCE(*pudp);

		if (pud_none(pud))
			return NULL;
		else if (pud_huge(pud)) {
			ret_pte = (pte_t *) pudp;
			goto out;
		} else if (is_hugepd(__hugepd(pud_val(pud))))
			hpdp = (hugepd_t *)&pud;
		else {
			pdshift = PMD_SHIFT;
			pmdp = pmd_offset(&pud, ea);
			pmd  = READ_ONCE(*pmdp);
			/*
			 * A hugepage collapse is captured by pmd_none, because
			 * it mark the pmd none and do a hpte invalidate.
			 */
			if (pmd_none(pmd))
				return NULL;

			if (pmd_trans_huge(pmd)) {
				if (is_thp)
					*is_thp = true;
				ret_pte = (pte_t *) pmdp;
				goto out;
			}

			if (pmd_huge(pmd)) {
				ret_pte = (pte_t *) pmdp;
				goto out;
			} else if (is_hugepd(__hugepd(pmd_val(pmd))))
				hpdp = (hugepd_t *)&pmd;
			else
				return pte_offset_kernel(&pmd, ea);
		}
	}
	if (!hpdp)
		return NULL;

	ret_pte = hugepte_offset(*hpdp, ea, pdshift);
	pdshift = hugepd_shift(*hpdp);
out:
	if (shift)
		*shift = pdshift;
	return ret_pte;
}
EXPORT_SYMBOL_GPL(__find_linux_pte_or_hugepte);

int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr,
		unsigned long end, int write, struct page **pages, int *nr)
{
	unsigned long mask;
	unsigned long pte_end;
	struct page *head, *page;
	pte_t pte;
	int refs;

	pte_end = (addr + sz) & ~(sz-1);
	if (pte_end < end)
		end = pte_end;

	pte = READ_ONCE(*ptep);
	mask = _PAGE_PRESENT | _PAGE_READ;

	/*
	 * On some CPUs like the 8xx, _PAGE_RW hence _PAGE_WRITE is defined
	 * as 0 and _PAGE_RO has to be set when a page is not writable
	 */
	if (write)
		mask |= _PAGE_WRITE;
	else
		mask |= _PAGE_RO;

	if ((pte_val(pte) & mask) != mask)
		return 0;

	/* hugepages are never "special" */
	VM_BUG_ON(!pfn_valid(pte_pfn(pte)));

	refs = 0;
	head = pte_page(pte);

	page = head + ((addr & (sz-1)) >> PAGE_SHIFT);
	do {
		VM_BUG_ON(compound_head(page) != head);
		pages[*nr] = page;
		(*nr)++;
		page++;
		refs++;
	} while (addr += PAGE_SIZE, addr != end);

	if (!page_cache_add_speculative(head, refs)) {
		*nr -= refs;
		return 0;
	}

	if (unlikely(pte_val(pte) != pte_val(*ptep))) {
		/* Could be optimized better */
		*nr -= refs;
		while (refs--)
			put_page(head);
		return 0;
	}

	return 1;
}