summaryrefslogtreecommitdiff
path: root/arch/x86/mm/pageattr.c
blob: 497108825da975b15d40e8a184f034710fb56ed1 (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
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
/*
 * Copyright 2002 Andi Kleen, SuSE Labs.
 * Thanks to Ben LaHaise for precious feedback.
 */
#include <linux/highmem.h>
#include <linux/bootmem.h>
#include <linux/module.h>
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/mm.h>
#include <linux/interrupt.h>
#include <linux/seq_file.h>
#include <linux/debugfs.h>

#include <asm/e820.h>
#include <asm/processor.h>
#include <asm/tlbflush.h>
#include <asm/sections.h>
#include <asm/uaccess.h>
#include <asm/pgalloc.h>
#include <asm/proto.h>
#include <asm/pat.h>

/*
 * The current flushing context - we pass it instead of 5 arguments:
 */
struct cpa_data {
	unsigned long	*vaddr;
	pgprot_t	mask_set;
	pgprot_t	mask_clr;
	int		numpages;
	int		flags;
	unsigned long	pfn;
	unsigned	force_split : 1;
	int		curpage;
};

#define CPA_FLUSHTLB 1
#define CPA_ARRAY 2

#ifdef CONFIG_PROC_FS
static unsigned long direct_pages_count[PG_LEVEL_NUM];

void update_page_count(int level, unsigned long pages)
{
	unsigned long flags;

	/* Protect against CPA */
	spin_lock_irqsave(&pgd_lock, flags);
	direct_pages_count[level] += pages;
	spin_unlock_irqrestore(&pgd_lock, flags);
}

static void split_page_count(int level)
{
	direct_pages_count[level]--;
	direct_pages_count[level - 1] += PTRS_PER_PTE;
}

int arch_report_meminfo(char *page)
{
	int n = sprintf(page, "DirectMap4k:  %8lu kB\n",
			direct_pages_count[PG_LEVEL_4K] << 2);
#if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE)
	n += sprintf(page + n, "DirectMap2M:  %8lu kB\n",
			direct_pages_count[PG_LEVEL_2M] << 11);
#else
	n += sprintf(page + n, "DirectMap4M:  %8lu kB\n",
			direct_pages_count[PG_LEVEL_2M] << 12);
#endif
#ifdef CONFIG_X86_64
	if (direct_gbpages)
		n += sprintf(page + n, "DirectMap1G:  %8lu kB\n",
			direct_pages_count[PG_LEVEL_1G] << 20);
#endif
	return n;
}
#else
static inline void split_page_count(int level) { }
#endif

#ifdef CONFIG_X86_64

static inline unsigned long highmap_start_pfn(void)
{
	return __pa(_text) >> PAGE_SHIFT;
}

static inline unsigned long highmap_end_pfn(void)
{
	return __pa(round_up((unsigned long)_end, PMD_SIZE)) >> PAGE_SHIFT;
}

#endif

#ifdef CONFIG_DEBUG_PAGEALLOC
# define debug_pagealloc 1
#else
# define debug_pagealloc 0
#endif

static inline int
within(unsigned long addr, unsigned long start, unsigned long end)
{
	return addr >= start && addr < end;
}

/*
 * Flushing functions
 */

/**
 * clflush_cache_range - flush a cache range with clflush
 * @addr:	virtual start address
 * @size:	number of bytes to flush
 *
 * clflush is an unordered instruction which needs fencing with mfence
 * to avoid ordering issues.
 */
void clflush_cache_range(void *vaddr, unsigned int size)
{
	void *vend = vaddr + size - 1;

	mb();

	for (; vaddr < vend; vaddr += boot_cpu_data.x86_clflush_size)
		clflush(vaddr);
	/*
	 * Flush any possible final partial cacheline:
	 */
	clflush(vend);

	mb();
}

static void __cpa_flush_all(void *arg)
{
	unsigned long cache = (unsigned long)arg;

	/*
	 * Flush all to work around Errata in early athlons regarding
	 * large page flushing.
	 */
	__flush_tlb_all();

	if (cache && boot_cpu_data.x86_model >= 4)
		wbinvd();
}

static void cpa_flush_all(unsigned long cache)
{
	BUG_ON(irqs_disabled());

	on_each_cpu(__cpa_flush_all, (void *) cache, 1);
}

static void __cpa_flush_range(void *arg)
{
	/*
	 * We could optimize that further and do individual per page
	 * tlb invalidates for a low number of pages. Caveat: we must
	 * flush the high aliases on 64bit as well.
	 */
	__flush_tlb_all();
}

static void cpa_flush_range(unsigned long start, int numpages, int cache)
{
	unsigned int i, level;
	unsigned long addr;

	BUG_ON(irqs_disabled());
	WARN_ON(PAGE_ALIGN(start) != start);

	on_each_cpu(__cpa_flush_range, NULL, 1);

	if (!cache)
		return;

	/*
	 * We only need to flush on one CPU,
	 * clflush is a MESI-coherent instruction that
	 * will cause all other CPUs to flush the same
	 * cachelines:
	 */
	for (i = 0, addr = start; i < numpages; i++, addr += PAGE_SIZE) {
		pte_t *pte = lookup_address(addr, &level);

		/*
		 * Only flush present addresses:
		 */
		if (pte && (pte_val(*pte) & _PAGE_PRESENT))
			clflush_cache_range((void *) addr, PAGE_SIZE);
	}
}

static void cpa_flush_array(unsigned long *start, int numpages, int cache)
{
	unsigned int i, level;
	unsigned long *addr;

	BUG_ON(irqs_disabled());

	on_each_cpu(__cpa_flush_range, NULL, 1);

	if (!cache)
		return;

	/* 4M threshold */
	if (numpages >= 1024) {
		if (boot_cpu_data.x86_model >= 4)
			wbinvd();
		return;
	}
	/*
	 * We only need to flush on one CPU,
	 * clflush is a MESI-coherent instruction that
	 * will cause all other CPUs to flush the same
	 * cachelines:
	 */
	for (i = 0, addr = start; i < numpages; i++, addr++) {
		pte_t *pte = lookup_address(*addr, &level);

		/*
		 * Only flush present addresses:
		 */
		if (pte && (pte_val(*pte) & _PAGE_PRESENT))
			clflush_cache_range((void *) *addr, PAGE_SIZE);
	}
}

/*
 * Certain areas of memory on x86 require very specific protection flags,
 * for example the BIOS area or kernel text. Callers don't always get this
 * right (again, ioremap() on BIOS memory is not uncommon) so this function
 * checks and fixes these known static required protection bits.
 */
static inline pgprot_t static_protections(pgprot_t prot, unsigned long address,
				   unsigned long pfn)
{
	pgprot_t forbidden = __pgprot(0);

	/*
	 * The BIOS area between 640k and 1Mb needs to be executable for
	 * PCI BIOS based config access (CONFIG_PCI_GOBIOS) support.
	 */
	if (within(pfn, BIOS_BEGIN >> PAGE_SHIFT, BIOS_END >> PAGE_SHIFT))
		pgprot_val(forbidden) |= _PAGE_NX;

	/*
	 * The kernel text needs to be executable for obvious reasons
	 * Does not cover __inittext since that is gone later on. On
	 * 64bit we do not enforce !NX on the low mapping
	 */
	if (within(address, (unsigned long)_text, (unsigned long)_etext))
		pgprot_val(forbidden) |= _PAGE_NX;

	/*
	 * The .rodata section needs to be read-only. Using the pfn
	 * catches all aliases.
	 */
	if (within(pfn, __pa((unsigned long)__start_rodata) >> PAGE_SHIFT,
		   __pa((unsigned long)__end_rodata) >> PAGE_SHIFT))
		pgprot_val(forbidden) |= _PAGE_RW;

	prot = __pgprot(pgprot_val(prot) & ~pgprot_val(forbidden));

	return prot;
}

/*
 * Lookup the page table entry for a virtual address. Return a pointer
 * to the entry and the level of the mapping.
 *
 * Note: We return pud and pmd either when the entry is marked large
 * or when the present bit is not set. Otherwise we would return a
 * pointer to a nonexisting mapping.
 */
pte_t *lookup_address(unsigned long address, unsigned int *level)
{
	pgd_t *pgd = pgd_offset_k(address);
	pud_t *pud;
	pmd_t *pmd;

	*level = PG_LEVEL_NONE;

	if (pgd_none(*pgd))
		return NULL;

	pud = pud_offset(pgd, address);
	if (pud_none(*pud))
		return NULL;

	*level = PG_LEVEL_1G;
	if (pud_large(*pud) || !pud_present(*pud))
		return (pte_t *)pud;

	pmd = pmd_offset(pud, address);
	if (pmd_none(*pmd))
		return NULL;

	*level = PG_LEVEL_2M;
	if (pmd_large(*pmd) || !pmd_present(*pmd))
		return (pte_t *)pmd;

	*level = PG_LEVEL_4K;

	return pte_offset_kernel(pmd, address);
}
EXPORT_SYMBOL_GPL(lookup_address);

/*
 * Set the new pmd in all the pgds we know about:
 */
static void __set_pmd_pte(pte_t *kpte, unsigned long address, pte_t pte)
{
	/* change init_mm */
	set_pte_atomic(kpte, pte);
#ifdef CONFIG_X86_32
	if (!SHARED_KERNEL_PMD) {
		struct page *page;

		list_for_each_entry(page, &pgd_list, lru) {
			pgd_t *pgd;
			pud_t *pud;
			pmd_t *pmd;

			pgd = (pgd_t *)page_address(page) + pgd_index(address);
			pud = pud_offset(pgd, address);
			pmd = pmd_offset(pud, address);
			set_pte_atomic((pte_t *)pmd, pte);
		}
	}
#endif
}

static int
try_preserve_large_page(pte_t *kpte, unsigned long address,
			struct cpa_data *cpa)
{
	unsigned long nextpage_addr, numpages, pmask, psize, flags, addr, pfn;
	pte_t new_pte, old_pte, *tmp;
	pgprot_t old_prot, new_prot;
	int i, do_split = 1;
	unsigned int level;

	if (cpa->force_split)
		return 1;

	spin_lock_irqsave(&pgd_lock, flags);
	/*
	 * Check for races, another CPU might have split this page
	 * up already:
	 */
	tmp = lookup_address(address, &level);
	if (tmp != kpte)
		goto out_unlock;

	switch (level) {
	case PG_LEVEL_2M:
		psize = PMD_PAGE_SIZE;
		pmask = PMD_PAGE_MASK;
		break;
#ifdef CONFIG_X86_64
	case PG_LEVEL_1G:
		psize = PUD_PAGE_SIZE;
		pmask = PUD_PAGE_MASK;
		break;
#endif
	default:
		do_split = -EINVAL;
		goto out_unlock;
	}

	/*
	 * Calculate the number of pages, which fit into this large
	 * page starting at address:
	 */
	nextpage_addr = (address + psize) & pmask;
	numpages = (nextpage_addr - address) >> PAGE_SHIFT;
	if (numpages < cpa->numpages)
		cpa->numpages = numpages;

	/*
	 * We are safe now. Check whether the new pgprot is the same:
	 */
	old_pte = *kpte;
	old_prot = new_prot = pte_pgprot(old_pte);

	pgprot_val(new_prot) &= ~pgprot_val(cpa->mask_clr);
	pgprot_val(new_prot) |= pgprot_val(cpa->mask_set);

	/*
	 * old_pte points to the large page base address. So we need
	 * to add the offset of the virtual address:
	 */
	pfn = pte_pfn(old_pte) + ((address & (psize - 1)) >> PAGE_SHIFT);
	cpa->pfn = pfn;

	new_prot = static_protections(new_prot, address, pfn);

	/*
	 * We need to check the full range, whether
	 * static_protection() requires a different pgprot for one of
	 * the pages in the range we try to preserve:
	 */
	addr = address + PAGE_SIZE;
	pfn++;
	for (i = 1; i < cpa->numpages; i++, addr += PAGE_SIZE, pfn++) {
		pgprot_t chk_prot = static_protections(new_prot, addr, pfn);

		if (pgprot_val(chk_prot) != pgprot_val(new_prot))
			goto out_unlock;
	}

	/*
	 * If there are no changes, return. maxpages has been updated
	 * above:
	 */
	if (pgprot_val(new_prot) == pgprot_val(old_prot)) {
		do_split = 0;
		goto out_unlock;
	}

	/*
	 * We need to change the attributes. Check, whether we can
	 * change the large page in one go. We request a split, when
	 * the address is not aligned and the number of pages is
	 * smaller than the number of pages in the large page. Note
	 * that we limited the number of possible pages already to
	 * the number of pages in the large page.
	 */
	if (address == (nextpage_addr - psize) && cpa->numpages == numpages) {
		/*
		 * The address is aligned and the number of pages
		 * covers the full page.
		 */
		new_pte = pfn_pte(pte_pfn(old_pte), canon_pgprot(new_prot));
		__set_pmd_pte(kpte, address, new_pte);
		cpa->flags |= CPA_FLUSHTLB;
		do_split = 0;
	}

out_unlock:
	spin_unlock_irqrestore(&pgd_lock, flags);

	return do_split;
}

static LIST_HEAD(page_pool);
static unsigned long pool_size, pool_pages, pool_low;
static unsigned long pool_used, pool_failed;

static void cpa_fill_pool(struct page **ret)
{
	gfp_t gfp = GFP_KERNEL;
	unsigned long flags;
	struct page *p;

	/*
	 * Avoid recursion (on debug-pagealloc) and also signal
	 * our priority to get to these pagetables:
	 */
	if (current->flags & PF_MEMALLOC)
		return;
	current->flags |= PF_MEMALLOC;

	/*
	 * Allocate atomically from atomic contexts:
	 */
	if (in_atomic() || irqs_disabled() || debug_pagealloc)
		gfp =  GFP_ATOMIC | __GFP_NORETRY | __GFP_NOWARN;

	while (pool_pages < pool_size || (ret && !*ret)) {
		p = alloc_pages(gfp, 0);
		if (!p) {
			pool_failed++;
			break;
		}
		/*
		 * If the call site needs a page right now, provide it:
		 */
		if (ret && !*ret) {
			*ret = p;
			continue;
		}
		spin_lock_irqsave(&pgd_lock, flags);
		list_add(&p->lru, &page_pool);
		pool_pages++;
		spin_unlock_irqrestore(&pgd_lock, flags);
	}

	current->flags &= ~PF_MEMALLOC;
}

#define SHIFT_MB		(20 - PAGE_SHIFT)
#define ROUND_MB_GB		((1 << 10) - 1)
#define SHIFT_MB_GB		10
#define POOL_PAGES_PER_GB	16

void __init cpa_init(void)
{
	struct sysinfo si;
	unsigned long gb;

	si_meminfo(&si);
	/*
	 * Calculate the number of pool pages:
	 *
	 * Convert totalram (nr of pages) to MiB and round to the next
	 * GiB. Shift MiB to Gib and multiply the result by
	 * POOL_PAGES_PER_GB:
	 */
	if (debug_pagealloc) {
		gb = ((si.totalram >> SHIFT_MB) + ROUND_MB_GB) >> SHIFT_MB_GB;
		pool_size = POOL_PAGES_PER_GB * gb;
	} else {
		pool_size = 1;
	}
	pool_low = pool_size;

	cpa_fill_pool(NULL);
	printk(KERN_DEBUG
	       "CPA: page pool initialized %lu of %lu pages preallocated\n",
	       pool_pages, pool_size);
}

static int split_large_page(pte_t *kpte, unsigned long address)
{
	unsigned long flags, pfn, pfninc = 1;
	unsigned int i, level;
	pte_t *pbase, *tmp;
	pgprot_t ref_prot;
	struct page *base;

	/*
	 * Get a page from the pool. The pool list is protected by the
	 * pgd_lock, which we have to take anyway for the split
	 * operation:
	 */
	spin_lock_irqsave(&pgd_lock, flags);
	if (list_empty(&page_pool)) {
		spin_unlock_irqrestore(&pgd_lock, flags);
		base = NULL;
		cpa_fill_pool(&base);
		if (!base)
			return -ENOMEM;
		spin_lock_irqsave(&pgd_lock, flags);
	} else {
		base = list_first_entry(&page_pool, struct page, lru);
		list_del(&base->lru);
		pool_pages--;

		if (pool_pages < pool_low)
			pool_low = pool_pages;
	}

	/*
	 * Check for races, another CPU might have split this page
	 * up for us already:
	 */
	tmp = lookup_address(address, &level);
	if (tmp != kpte)
		goto out_unlock;

	pbase = (pte_t *)page_address(base);
	paravirt_alloc_pte(&init_mm, page_to_pfn(base));
	ref_prot = pte_pgprot(pte_clrhuge(*kpte));

#ifdef CONFIG_X86_64
	if (level == PG_LEVEL_1G) {
		pfninc = PMD_PAGE_SIZE >> PAGE_SHIFT;
		pgprot_val(ref_prot) |= _PAGE_PSE;
	}
#endif

	/*
	 * Get the target pfn from the original entry:
	 */
	pfn = pte_pfn(*kpte);
	for (i = 0; i < PTRS_PER_PTE; i++, pfn += pfninc)
		set_pte(&pbase[i], pfn_pte(pfn, ref_prot));

	if (address >= (unsigned long)__va(0) &&
		address < (unsigned long)__va(max_low_pfn_mapped << PAGE_SHIFT))
		split_page_count(level);

#ifdef CONFIG_X86_64
	if (address >= (unsigned long)__va(1UL<<32) &&
		address < (unsigned long)__va(max_pfn_mapped << PAGE_SHIFT))
		split_page_count(level);
#endif

	/*
	 * Install the new, split up pagetable. Important details here:
	 *
	 * On Intel the NX bit of all levels must be cleared to make a
	 * page executable. See section 4.13.2 of Intel 64 and IA-32
	 * Architectures Software Developer's Manual).
	 *
	 * Mark the entry present. The current mapping might be
	 * set to not present, which we preserved above.
	 */
	ref_prot = pte_pgprot(pte_mkexec(pte_clrhuge(*kpte)));
	pgprot_val(ref_prot) |= _PAGE_PRESENT;
	__set_pmd_pte(kpte, address, mk_pte(base, ref_prot));
	base = NULL;

out_unlock:
	/*
	 * If we dropped out via the lookup_address check under
	 * pgd_lock then stick the page back into the pool:
	 */
	if (base) {
		list_add(&base->lru, &page_pool);
		pool_pages++;
	} else
		pool_used++;
	spin_unlock_irqrestore(&pgd_lock, flags);

	return 0;
}

static int __change_page_attr(struct cpa_data *cpa, int primary)
{
	unsigned long address;
	int do_split, err;
	unsigned int level;
	pte_t *kpte, old_pte;

	if (cpa->flags & CPA_ARRAY)
		address = cpa->vaddr[cpa->curpage];
	else
		address = *cpa->vaddr;

repeat:
	kpte = lookup_address(address, &level);
	if (!kpte)
		return 0;

	old_pte = *kpte;
	if (!pte_val(old_pte)) {
		if (!primary)
			return 0;
		WARN(1, KERN_WARNING "CPA: called for zero pte. "
		       "vaddr = %lx cpa->vaddr = %lx\n", address,
		       *cpa->vaddr);
		return -EINVAL;
	}

	if (level == PG_LEVEL_4K) {
		pte_t new_pte;
		pgprot_t new_prot = pte_pgprot(old_pte);
		unsigned long pfn = pte_pfn(old_pte);

		pgprot_val(new_prot) &= ~pgprot_val(cpa->mask_clr);
		pgprot_val(new_prot) |= pgprot_val(cpa->mask_set);

		new_prot = static_protections(new_prot, address, pfn);

		/*
		 * We need to keep the pfn from the existing PTE,
		 * after all we're only going to change it's attributes
		 * not the memory it points to
		 */
		new_pte = pfn_pte(pfn, canon_pgprot(new_prot));
		cpa->pfn = pfn;
		/*
		 * Do we really change anything ?
		 */
		if (pte_val(old_pte) != pte_val(new_pte)) {
			set_pte_atomic(kpte, new_pte);
			cpa->flags |= CPA_FLUSHTLB;
		}
		cpa->numpages = 1;
		return 0;
	}

	/*
	 * Check, whether we can keep the large page intact
	 * and just change the pte:
	 */
	do_split = try_preserve_large_page(kpte, address, cpa);
	/*
	 * When the range fits into the existing large page,
	 * return. cp->numpages and cpa->tlbflush have been updated in
	 * try_large_page:
	 */
	if (do_split <= 0)
		return do_split;

	/*
	 * We have to split the large page:
	 */
	err = split_large_page(kpte, address);
	if (!err) {
		cpa->flags |= CPA_FLUSHTLB;
		goto repeat;
	}

	return err;
}

static int __change_page_attr_set_clr(struct cpa_data *cpa, int checkalias);

static int cpa_process_alias(struct cpa_data *cpa)
{
	struct cpa_data alias_cpa;
	int ret = 0;
	unsigned long temp_cpa_vaddr, vaddr;

	if (cpa->pfn >= max_pfn_mapped)
		return 0;

#ifdef CONFIG_X86_64
	if (cpa->pfn >= max_low_pfn_mapped && cpa->pfn < (1UL<<(32-PAGE_SHIFT)))
		return 0;
#endif
	/*
	 * No need to redo, when the primary call touched the direct
	 * mapping already:
	 */
	if (cpa->flags & CPA_ARRAY)
		vaddr = cpa->vaddr[cpa->curpage];
	else
		vaddr = *cpa->vaddr;

	if (!(within(vaddr, PAGE_OFFSET,
		    PAGE_OFFSET + (max_low_pfn_mapped << PAGE_SHIFT))
#ifdef CONFIG_X86_64
		|| within(vaddr, PAGE_OFFSET + (1UL<<32),
		    PAGE_OFFSET + (max_pfn_mapped << PAGE_SHIFT))
#endif
	)) {

		alias_cpa = *cpa;
		temp_cpa_vaddr = (unsigned long) __va(cpa->pfn << PAGE_SHIFT);
		alias_cpa.vaddr = &temp_cpa_vaddr;
		alias_cpa.flags &= ~CPA_ARRAY;


		ret = __change_page_attr_set_clr(&alias_cpa, 0);
	}

#ifdef CONFIG_X86_64
	if (ret)
		return ret;
	/*
	 * No need to redo, when the primary call touched the high
	 * mapping already:
	 */
	if (within(vaddr, (unsigned long) _text, (unsigned long) _end))
		return 0;

	/*
	 * If the physical address is inside the kernel map, we need
	 * to touch the high mapped kernel as well:
	 */
	if (!within(cpa->pfn, highmap_start_pfn(), highmap_end_pfn()))
		return 0;

	alias_cpa = *cpa;
	temp_cpa_vaddr = (cpa->pfn << PAGE_SHIFT) + __START_KERNEL_map - phys_base;
	alias_cpa.vaddr = &temp_cpa_vaddr;
	alias_cpa.flags &= ~CPA_ARRAY;

	/*
	 * The high mapping range is imprecise, so ignore the return value.
	 */
	__change_page_attr_set_clr(&alias_cpa, 0);
#endif
	return ret;
}

static int __change_page_attr_set_clr(struct cpa_data *cpa, int checkalias)
{
	int ret, numpages = cpa->numpages;

	while (numpages) {
		/*
		 * Store the remaining nr of pages for the large page
		 * preservation check.
		 */
		cpa->numpages = numpages;
		/* for array changes, we can't use large page */
		if (cpa->flags & CPA_ARRAY)
			cpa->numpages = 1;

		ret = __change_page_attr(cpa, checkalias);
		if (ret)
			return ret;

		if (checkalias) {
			ret = cpa_process_alias(cpa);
			if (ret)
				return ret;
		}

		/*
		 * Adjust the number of pages with the result of the
		 * CPA operation. Either a large page has been
		 * preserved or a single page update happened.
		 */
		BUG_ON(cpa->numpages > numpages);
		numpages -= cpa->numpages;
		if (cpa->flags & CPA_ARRAY)
			cpa->curpage++;
		else
			*cpa->vaddr += cpa->numpages * PAGE_SIZE;

	}
	return 0;
}

static inline int cache_attr(pgprot_t attr)
{
	return pgprot_val(attr) &
		(_PAGE_PAT | _PAGE_PAT_LARGE | _PAGE_PWT | _PAGE_PCD);
}

static int change_page_attr_set_clr(unsigned long *addr, int numpages,
				    pgprot_t mask_set, pgprot_t mask_clr,
				    int force_split, int array)
{
	struct cpa_data cpa;
	int ret, cache, checkalias;

	/*
	 * Check, if we are requested to change a not supported
	 * feature:
	 */
	mask_set = canon_pgprot(mask_set);
	mask_clr = canon_pgprot(mask_clr);
	if (!pgprot_val(mask_set) && !pgprot_val(mask_clr) && !force_split)
		return 0;

	/* Ensure we are PAGE_SIZE aligned */
	if (!array) {
		if (*addr & ~PAGE_MASK) {
			*addr &= PAGE_MASK;
			/*
			 * People should not be passing in unaligned addresses:
			 */
			WARN_ON_ONCE(1);
		}
	} else {
		int i;
		for (i = 0; i < numpages; i++) {
			if (addr[i] & ~PAGE_MASK) {
				addr[i] &= PAGE_MASK;
				WARN_ON_ONCE(1);
			}
		}
	}

	/* Must avoid aliasing mappings in the highmem code */
	kmap_flush_unused();

	cpa.vaddr = addr;
	cpa.numpages = numpages;
	cpa.mask_set = mask_set;
	cpa.mask_clr = mask_clr;
	cpa.flags = 0;
	cpa.curpage = 0;
	cpa.force_split = force_split;

	if (array)
		cpa.flags |= CPA_ARRAY;

	/* No alias checking for _NX bit modifications */
	checkalias = (pgprot_val(mask_set) | pgprot_val(mask_clr)) != _PAGE_NX;

	ret = __change_page_attr_set_clr(&cpa, checkalias);

	/*
	 * Check whether we really changed something:
	 */
	if (!(cpa.flags & CPA_FLUSHTLB))
		goto out;

	/*
	 * No need to flush, when we did not set any of the caching
	 * attributes:
	 */
	cache = cache_attr(mask_set);

	/*
	 * On success we use clflush, when the CPU supports it to
	 * avoid the wbindv. If the CPU does not support it and in the
	 * error case we fall back to cpa_flush_all (which uses
	 * wbindv):
	 */
	if (!ret && cpu_has_clflush) {
		if (cpa.flags & CPA_ARRAY)
			cpa_flush_array(addr, numpages, cache);
		else
			cpa_flush_range(*addr, numpages, cache);
	} else
		cpa_flush_all(cache);

out:
	cpa_fill_pool(NULL);

	return ret;
}

static inline int change_page_attr_set(unsigned long *addr, int numpages,
				       pgprot_t mask, int array)
{
	return change_page_attr_set_clr(addr, numpages, mask, __pgprot(0), 0,
		array);
}

static inline int change_page_attr_clear(unsigned long *addr, int numpages,
					 pgprot_t mask, int array)
{
	return change_page_attr_set_clr(addr, numpages, __pgprot(0), mask, 0,
		array);
}

int _set_memory_uc(unsigned long addr, int numpages)
{
	/*
	 * for now UC MINUS. see comments in ioremap_nocache()
	 */
	return change_page_attr_set(&addr, numpages,
				    __pgprot(_PAGE_CACHE_UC_MINUS), 0);
}

int set_memory_uc(unsigned long addr, int numpages)
{
	/*
	 * for now UC MINUS. see comments in ioremap_nocache()
	 */
	if (reserve_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE,
			    _PAGE_CACHE_UC_MINUS, NULL))
		return -EINVAL;

	return _set_memory_uc(addr, numpages);
}
EXPORT_SYMBOL(set_memory_uc);

int set_memory_array_uc(unsigned long *addr, int addrinarray)
{
	unsigned long start;
	unsigned long end;
	int i;
	/*
	 * for now UC MINUS. see comments in ioremap_nocache()
	 */
	for (i = 0; i < addrinarray; i++) {
		start = __pa(addr[i]);
		for (end = start + PAGE_SIZE; i < addrinarray - 1; end += PAGE_SIZE) {
			if (end != __pa(addr[i + 1]))
				break;
			i++;
		}
		if (reserve_memtype(start, end, _PAGE_CACHE_UC_MINUS, NULL))
			goto out;
	}

	return change_page_attr_set(addr, addrinarray,
				    __pgprot(_PAGE_CACHE_UC_MINUS), 1);
out:
	for (i = 0; i < addrinarray; i++) {
		unsigned long tmp = __pa(addr[i]);

		if (tmp == start)
			break;
		for (end = start + PAGE_SIZE; i < addrinarray - 1; end += PAGE_SIZE) {
			if (end != __pa(addr[i + 1]))
				break;
			i++;
		}
		free_memtype(tmp, end);
	}
	return -EINVAL;
}
EXPORT_SYMBOL(set_memory_array_uc);

int _set_memory_wc(unsigned long addr, int numpages)
{
	return change_page_attr_set(&addr, numpages,
				    __pgprot(_PAGE_CACHE_WC), 0);
}

int set_memory_wc(unsigned long addr, int numpages)
{
	if (!pat_enabled)
		return set_memory_uc(addr, numpages);

	if (reserve_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE,
		_PAGE_CACHE_WC, NULL))
		return -EINVAL;

	return _set_memory_wc(addr, numpages);
}
EXPORT_SYMBOL(set_memory_wc);

int _set_memory_wb(unsigned long addr, int numpages)
{
	return change_page_attr_clear(&addr, numpages,
				      __pgprot(_PAGE_CACHE_MASK), 0);
}

int set_memory_wb(unsigned long addr, int numpages)
{
	free_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE);

	return _set_memory_wb(addr, numpages);
}
EXPORT_SYMBOL(set_memory_wb);

int set_memory_array_wb(unsigned long *addr, int addrinarray)
{
	int i;

	for (i = 0; i < addrinarray; i++) {
		unsigned long start = __pa(addr[i]);
		unsigned long end;

		for (end = start + PAGE_SIZE; i < addrinarray - 1; end += PAGE_SIZE) {
			if (end != __pa(addr[i + 1]))
				break;
			i++;
		}
		free_memtype(start, end);
	}
	return change_page_attr_clear(addr, addrinarray,
				      __pgprot(_PAGE_CACHE_MASK), 1);
}
EXPORT_SYMBOL(set_memory_array_wb);

int set_memory_x(unsigned long addr, int numpages)
{
	return change_page_attr_clear(&addr, numpages, __pgprot(_PAGE_NX), 0);
}
EXPORT_SYMBOL(set_memory_x);

int set_memory_nx(unsigned long addr, int numpages)
{
	return change_page_attr_set(&addr, numpages, __pgprot(_PAGE_NX), 0);
}
EXPORT_SYMBOL(set_memory_nx);

int set_memory_ro(unsigned long addr, int numpages)
{
	return change_page_attr_clear(&addr, numpages, __pgprot(_PAGE_RW), 0);
}

int set_memory_rw(unsigned long addr, int numpages)
{
	return change_page_attr_set(&addr, numpages, __pgprot(_PAGE_RW), 0);
}

int set_memory_np(unsigned long addr, int numpages)
{
	return change_page_attr_clear(&addr, numpages, __pgprot(_PAGE_PRESENT), 0);
}

int set_memory_4k(unsigned long addr, int numpages)
{
	return change_page_attr_set_clr(&addr, numpages, __pgprot(0),
					__pgprot(0), 1, 0);
}

int set_pages_uc(struct page *page, int numpages)
{
	unsigned long addr = (unsigned long)page_address(page);

	return set_memory_uc(addr, numpages);
}
EXPORT_SYMBOL(set_pages_uc);

int set_pages_wb(struct page *page, int numpages)
{
	unsigned long addr = (unsigned long)page_address(page);

	return set_memory_wb(addr, numpages);
}
EXPORT_SYMBOL(set_pages_wb);

int set_pages_x(struct page *page, int numpages)
{
	unsigned long addr = (unsigned long)page_address(page);

	return set_memory_x(addr, numpages);
}
EXPORT_SYMBOL(set_pages_x);

int set_pages_nx(struct page *page, int numpages)
{
	unsigned long addr = (unsigned long)page_address(page);

	return set_memory_nx(addr, numpages);
}
EXPORT_SYMBOL(set_pages_nx);

int set_pages_ro(struct page *page, int numpages)
{
	unsigned long addr = (unsigned long)page_address(page);

	return set_memory_ro(addr, numpages);
}

int set_pages_rw(struct page *page, int numpages)
{
	unsigned long addr = (unsigned long)page_address(page);

	return set_memory_rw(addr, numpages);
}

#ifdef CONFIG_DEBUG_PAGEALLOC

static int __set_pages_p(struct page *page, int numpages)
{
	unsigned long tempaddr = (unsigned long) page_address(page);
	struct cpa_data cpa = { .vaddr = &tempaddr,
				.numpages = numpages,
				.mask_set = __pgprot(_PAGE_PRESENT | _PAGE_RW),
				.mask_clr = __pgprot(0),
				.flags = 0};

	return __change_page_attr_set_clr(&cpa, 1);
}

static int __set_pages_np(struct page *page, int numpages)
{
	unsigned long tempaddr = (unsigned long) page_address(page);
	struct cpa_data cpa = { .vaddr = &tempaddr,
				.numpages = numpages,
				.mask_set = __pgprot(0),
				.mask_clr = __pgprot(_PAGE_PRESENT | _PAGE_RW),
				.flags = 0};

	return __change_page_attr_set_clr(&cpa, 1);
}

void kernel_map_pages(struct page *page, int numpages, int enable)
{
	if (PageHighMem(page))
		return;
	if (!enable) {
		debug_check_no_locks_freed(page_address(page),
					   numpages * PAGE_SIZE);
	}

	/*
	 * If page allocator is not up yet then do not call c_p_a():
	 */
	if (!debug_pagealloc_enabled)
		return;

	/*
	 * The return value is ignored as the calls cannot fail.
	 * Large pages are kept enabled at boot time, and are
	 * split up quickly with DEBUG_PAGEALLOC. If a splitup
	 * fails here (due to temporary memory shortage) no damage
	 * is done because we just keep the largepage intact up
	 * to the next attempt when it will likely be split up:
	 */
	if (enable)
		__set_pages_p(page, numpages);
	else
		__set_pages_np(page, numpages);

	/*
	 * We should perform an IPI and flush all tlbs,
	 * but that can deadlock->flush only current cpu:
	 */
	__flush_tlb_all();

	/*
	 * Try to refill the page pool here. We can do this only after
	 * the tlb flush.
	 */
	cpa_fill_pool(NULL);
}

#ifdef CONFIG_DEBUG_FS
static int dpa_show(struct seq_file *m, void *v)
{
	seq_puts(m, "DEBUG_PAGEALLOC\n");
	seq_printf(m, "pool_size     : %lu\n", pool_size);
	seq_printf(m, "pool_pages    : %lu\n", pool_pages);
	seq_printf(m, "pool_low      : %lu\n", pool_low);
	seq_printf(m, "pool_used     : %lu\n", pool_used);
	seq_printf(m, "pool_failed   : %lu\n", pool_failed);

	return 0;
}

static int dpa_open(struct inode *inode, struct file *filp)
{
	return single_open(filp, dpa_show, NULL);
}

static const struct file_operations dpa_fops = {
	.open		= dpa_open,
	.read		= seq_read,
	.llseek		= seq_lseek,
	.release	= single_release,
};

static int __init debug_pagealloc_proc_init(void)
{
	struct dentry *de;

	de = debugfs_create_file("debug_pagealloc", 0600, NULL, NULL,
				 &dpa_fops);
	if (!de)
		return -ENOMEM;

	return 0;
}
__initcall(debug_pagealloc_proc_init);
#endif

#ifdef CONFIG_HIBERNATION

bool kernel_page_present(struct page *page)
{
	unsigned int level;
	pte_t *pte;

	if (PageHighMem(page))
		return false;

	pte = lookup_address((unsigned long)page_address(page), &level);
	return (pte_val(*pte) & _PAGE_PRESENT);
}

#endif /* CONFIG_HIBERNATION */

#endif /* CONFIG_DEBUG_PAGEALLOC */

/*
 * The testcases use internal knowledge of the implementation that shouldn't
 * be exposed to the rest of the kernel. Include these directly here.
 */
#ifdef CONFIG_CPA_DEBUG
#include "pageattr-test.c"
#endif