aboutsummaryrefslogtreecommitdiffstats
path: root/arch/x86/kernel/cpu/mtrr/cleanup.c
blob: 1d584a18a50dab20fbe35e21e10859db05f2fe39 (plain) (blame)
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
/*  MTRR (Memory Type Range Register) cleanup

    Copyright (C) 2009 Yinghai Lu

    This library is free software; you can redistribute it and/or
    modify it under the terms of the GNU Library General Public
    License as published by the Free Software Foundation; either
    version 2 of the License, or (at your option) any later version.

    This library is distributed in the hope that it will be useful,
    but WITHOUT ANY WARRANTY; without even the implied warranty of
    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
    Library General Public License for more details.

    You should have received a copy of the GNU Library General Public
    License along with this library; if not, write to the Free
    Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
*/

#include <linux/module.h>
#include <linux/init.h>
#include <linux/pci.h>
#include <linux/smp.h>
#include <linux/cpu.h>
#include <linux/mutex.h>
#include <linux/sort.h>

#include <asm/e820.h>
#include <asm/mtrr.h>
#include <asm/uaccess.h>
#include <asm/processor.h>
#include <asm/msr.h>
#include <asm/kvm_para.h>
#include "mtrr.h"

/* should be related to MTRR_VAR_RANGES nums */
#define RANGE_NUM 256

struct res_range {
	unsigned long start;
	unsigned long end;
};

static int __init
add_range(struct res_range *range, int nr_range, unsigned long start,
			      unsigned long end)
{
	/* out of slots */
	if (nr_range >= RANGE_NUM)
		return nr_range;

	range[nr_range].start = start;
	range[nr_range].end = end;

	nr_range++;

	return nr_range;
}

static int __init
add_range_with_merge(struct res_range *range, int nr_range, unsigned long start,
			      unsigned long end)
{
	int i;

	/* try to merge it with old one */
	for (i = 0; i < nr_range; i++) {
		unsigned long final_start, final_end;
		unsigned long common_start, common_end;

		if (!range[i].end)
			continue;

		common_start = max(range[i].start, start);
		common_end = min(range[i].end, end);
		if (common_start > common_end + 1)
			continue;

		final_start = min(range[i].start, start);
		final_end = max(range[i].end, end);

		range[i].start = final_start;
		range[i].end =  final_end;
		return nr_range;
	}

	/* need to add that */
	return add_range(range, nr_range, start, end);
}

static void __init
subtract_range(struct res_range *range, unsigned long start, unsigned long end)
{
	int i, j;

	for (j = 0; j < RANGE_NUM; j++) {
		if (!range[j].end)
			continue;

		if (start <= range[j].start && end >= range[j].end) {
			range[j].start = 0;
			range[j].end = 0;
			continue;
		}

		if (start <= range[j].start && end < range[j].end &&
		    range[j].start < end + 1) {
			range[j].start = end + 1;
			continue;
		}


		if (start > range[j].start && end >= range[j].end &&
		    range[j].end > start - 1) {
			range[j].end = start - 1;
			continue;
		}

		if (start > range[j].start && end < range[j].end) {
			/* find the new spare */
			for (i = 0; i < RANGE_NUM; i++) {
				if (range[i].end == 0)
					break;
			}
			if (i < RANGE_NUM) {
				range[i].end = range[j].end;
				range[i].start = end + 1;
			} else {
				printk(KERN_ERR "run of slot in ranges\n");
			}
			range[j].end = start - 1;
			continue;
		}
	}
}

static int __init cmp_range(const void *x1, const void *x2)
{
	const struct res_range *r1 = x1;
	const struct res_range *r2 = x2;
	long start1, start2;

	start1 = r1->start;
	start2 = r2->start;

	return start1 - start2;
}

struct var_mtrr_range_state {
	unsigned long base_pfn;
	unsigned long size_pfn;
	mtrr_type type;
};

static struct var_mtrr_range_state __initdata range_state[RANGE_NUM];
static int __initdata debug_print;

static int __init
x86_get_mtrr_mem_range(struct res_range *range, int nr_range,
		       unsigned long extra_remove_base,
		       unsigned long extra_remove_size)
{
	unsigned long base, size;
	mtrr_type type;
	int i;

	for (i = 0; i < num_var_ranges; i++) {
		type = range_state[i].type;
		if (type != MTRR_TYPE_WRBACK)
			continue;
		base = range_state[i].base_pfn;
		size = range_state[i].size_pfn;
		nr_range = add_range_with_merge(range, nr_range, base,
						base + size - 1);
	}
	if (debug_print) {
		printk(KERN_DEBUG "After WB checking\n");
		for (i = 0; i < nr_range; i++)
			printk(KERN_DEBUG "MTRR MAP PFN: %016lx - %016lx\n",
				 range[i].start, range[i].end + 1);
	}

	/* take out UC ranges */
	for (i = 0; i < num_var_ranges; i++) {
		type = range_state[i].type;
		if (type != MTRR_TYPE_UNCACHABLE &&
		    type != MTRR_TYPE_WRPROT)
			continue;
		size = range_state[i].size_pfn;
		if (!size)
			continue;
		base = range_state[i].base_pfn;
		if (base < (1<<(20-PAGE_SHIFT)) && mtrr_state.have_fixed &&
		    (mtrr_state.enabled & 1)) {
			/* Var MTRR contains UC entry below 1M? Skip it: */
			printk(KERN_WARNING "WARNING: BIOS bug: VAR MTRR %d "
				"contains strange UC entry under 1M, check "
				"with your system vendor!\n", i);
			if (base + size <= (1<<(20-PAGE_SHIFT)))
				continue;
			size -= (1<<(20-PAGE_SHIFT)) - base;
			base = 1<<(20-PAGE_SHIFT);
		}
		subtract_range(range, base, base + size - 1);
	}
	if (extra_remove_size)
		subtract_range(range, extra_remove_base,
				 extra_remove_base + extra_remove_size  - 1);

	/* get new range num */
	nr_range = 0;
	for (i = 0; i < RANGE_NUM; i++) {
		if (!range[i].end)
			continue;
		nr_range++;
	}
	if  (debug_print) {
		printk(KERN_DEBUG "After UC checking\n");
		for (i = 0; i < nr_range; i++)
			printk(KERN_DEBUG "MTRR MAP PFN: %016lx - %016lx\n",
				 range[i].start, range[i].end + 1);
	}

	/* sort the ranges */
	sort(range, nr_range, sizeof(struct res_range), cmp_range, NULL);
	if  (debug_print) {
		printk(KERN_DEBUG "After sorting\n");
		for (i = 0; i < nr_range; i++)
			printk(KERN_DEBUG "MTRR MAP PFN: %016lx - %016lx\n",
				 range[i].start, range[i].end + 1);
	}

	/* clear those is not used */
	for (i = nr_range; i < RANGE_NUM; i++)
		memset(&range[i], 0, sizeof(range[i]));

	return nr_range;
}

static struct res_range __initdata range[RANGE_NUM];
static int __initdata nr_range;

#ifdef CONFIG_MTRR_SANITIZER

static unsigned long __init sum_ranges(struct res_range *range, int nr_range)
{
	unsigned long sum;
	int i;

	sum = 0;
	for (i = 0; i < nr_range; i++)
		sum += range[i].end + 1 - range[i].start;

	return sum;
}

static int enable_mtrr_cleanup __initdata =
	CONFIG_MTRR_SANITIZER_ENABLE_DEFAULT;

static int __init disable_mtrr_cleanup_setup(char *str)
{
	enable_mtrr_cleanup = 0;
	return 0;
}
early_param("disable_mtrr_cleanup", disable_mtrr_cleanup_setup);

static int __init enable_mtrr_cleanup_setup(char *str)
{
	enable_mtrr_cleanup = 1;
	return 0;
}
early_param("enable_mtrr_cleanup", enable_mtrr_cleanup_setup);

static int __init mtrr_cleanup_debug_setup(char *str)
{
	debug_print = 1;
	return 0;
}
early_param("mtrr_cleanup_debug", mtrr_cleanup_debug_setup);

struct var_mtrr_state {
	unsigned long	range_startk;
	unsigned long	range_sizek;
	unsigned long	chunk_sizek;
	unsigned long	gran_sizek;
	unsigned int	reg;
};

static void __init
set_var_mtrr(unsigned int reg, unsigned long basek, unsigned long sizek,
		unsigned char type, unsigned int address_bits)
{
	u32 base_lo, base_hi, mask_lo, mask_hi;
	u64 base, mask;

	if (!sizek) {
		fill_mtrr_var_range(reg, 0, 0, 0, 0);
		return;
	}

	mask = (1ULL << address_bits) - 1;
	mask &= ~((((u64)sizek) << 10) - 1);

	base  = ((u64)basek) << 10;

	base |= type;
	mask |= 0x800;

	base_lo = base & ((1ULL<<32) - 1);
	base_hi = base >> 32;

	mask_lo = mask & ((1ULL<<32) - 1);
	mask_hi = mask >> 32;

	fill_mtrr_var_range(reg, base_lo, base_hi, mask_lo, mask_hi);
}

static void __init
save_var_mtrr(unsigned int reg, unsigned long basek, unsigned long sizek,
		unsigned char type)
{
	range_state[reg].base_pfn = basek >> (PAGE_SHIFT - 10);
	range_state[reg].size_pfn = sizek >> (PAGE_SHIFT - 10);
	range_state[reg].type = type;
}

static void __init
set_var_mtrr_all(unsigned int address_bits)
{
	unsigned long basek, sizek;
	unsigned char type;
	unsigned int reg;

	for (reg = 0; reg < num_var_ranges; reg++) {
		basek = range_state[reg].base_pfn << (PAGE_SHIFT - 10);
		sizek = range_state[reg].size_pfn << (PAGE_SHIFT - 10);
		type = range_state[reg].type;

		set_var_mtrr(reg, basek, sizek, type, address_bits);
	}
}

static unsigned long to_size_factor(unsigned long sizek, char *factorp)
{
	char factor;
	unsigned long base = sizek;

	if (base & ((1<<10) - 1)) {
		/* not MB alignment */
		factor = 'K';
	} else if (base & ((1<<20) - 1)) {
		factor = 'M';
		base >>= 10;
	} else {
		factor = 'G';
		base >>= 20;
	}

	*factorp = factor;

	return base;
}

static unsigned int __init
range_to_mtrr(unsigned int reg, unsigned long range_startk,
	      unsigned long range_sizek, unsigned char type)
{
	if (!range_sizek || (reg >= num_var_ranges))
		return reg;

	while (range_sizek) {
		unsigned long max_align, align;
		unsigned long sizek;

		/* Compute the maximum size I can make a range */
		if (range_startk)
			max_align = ffs(range_startk) - 1;
		else
			max_align = 32;
		align = fls(range_sizek) - 1;
		if (align > max_align)
			align = max_align;

		sizek = 1 << align;
		if (debug_print) {
			char start_factor = 'K', size_factor = 'K';
			unsigned long start_base, size_base;

			start_base = to_size_factor(range_startk,
							 &start_factor),
			size_base = to_size_factor(sizek, &size_factor),

			printk(KERN_DEBUG "Setting variable MTRR %d, "
				"base: %ld%cB, range: %ld%cB, type %s\n",
				reg, start_base, start_factor,
				size_base, size_factor,
				(type == MTRR_TYPE_UNCACHABLE) ? "UC" :
				   ((type == MTRR_TYPE_WRBACK) ? "WB" : "Other")
				);
		}
		save_var_mtrr(reg++, range_startk, sizek, type);
		range_startk += sizek;
		range_sizek -= sizek;
		if (reg >= num_var_ranges)
			break;
	}
	return reg;
}

static unsigned __init
range_to_mtrr_with_hole(struct var_mtrr_state *state, unsigned long basek,
			unsigned long sizek)
{
	unsigned long hole_basek, hole_sizek;
	unsigned long second_basek, second_sizek;
	unsigned long range0_basek, range0_sizek;
	unsigned long range_basek, range_sizek;
	unsigned long chunk_sizek;
	unsigned long gran_sizek;

	hole_basek = 0;
	hole_sizek = 0;
	second_basek = 0;
	second_sizek = 0;
	chunk_sizek = state->chunk_sizek;
	gran_sizek = state->gran_sizek;

	/* align with gran size, prevent small block used up MTRRs */
	range_basek = ALIGN(state->range_startk, gran_sizek);
	if ((range_basek > basek) && basek)
		return second_sizek;
	state->range_sizek -= (range_basek - state->range_startk);
	range_sizek = ALIGN(state->range_sizek, gran_sizek);

	while (range_sizek > state->range_sizek) {
		range_sizek -= gran_sizek;
		if (!range_sizek)
			return 0;
	}
	state->range_sizek = range_sizek;

	/* try to append some small hole */
	range0_basek = state->range_startk;
	range0_sizek = ALIGN(state->range_sizek, chunk_sizek);

	/* no increase */
	if (range0_sizek == state->range_sizek) {
		if (debug_print)
			printk(KERN_DEBUG "rangeX: %016lx - %016lx\n",
				range0_basek<<10,
				(range0_basek + state->range_sizek)<<10);
		state->reg = range_to_mtrr(state->reg, range0_basek,
				state->range_sizek, MTRR_TYPE_WRBACK);
		return 0;
	}

	/* only cut back, when it is not the last */
	if (sizek) {
		while (range0_basek + range0_sizek > (basek + sizek)) {
			if (range0_sizek >= chunk_sizek)
				range0_sizek -= chunk_sizek;
			else
				range0_sizek = 0;

			if (!range0_sizek)
				break;
		}
	}

second_try:
	range_basek = range0_basek + range0_sizek;

	/* one hole in the middle */
	if (range_basek > basek && range_basek <= (basek + sizek))
		second_sizek = range_basek - basek;

	if (range0_sizek > state->range_sizek) {

		/* one hole in middle or at end */
		hole_sizek = range0_sizek - state->range_sizek - second_sizek;

		/* hole size should be less than half of range0 size */
		if (hole_sizek >= (range0_sizek >> 1) &&
		    range0_sizek >= chunk_sizek) {
			range0_sizek -= chunk_sizek;
			second_sizek = 0;
			hole_sizek = 0;

			goto second_try;
		}
	}

	if (range0_sizek) {
		if (debug_print)
			printk(KERN_DEBUG "range0: %016lx - %016lx\n",
				range0_basek<<10,
				(range0_basek + range0_sizek)<<10);
		state->reg = range_to_mtrr(state->reg, range0_basek,
				range0_sizek, MTRR_TYPE_WRBACK);
	}

	if (range0_sizek < state->range_sizek) {
		/* need to handle left over */
		range_sizek = state->range_sizek - range0_sizek;

		if (debug_print)
			printk(KERN_DEBUG "range: %016lx - %016lx\n",
				 range_basek<<10,
				 (range_basek + range_sizek)<<10);
		state->reg = range_to_mtrr(state->reg, range_basek,
				 range_sizek, MTRR_TYPE_WRBACK);
	}

	if (hole_sizek) {
		hole_basek = range_basek - hole_sizek - second_sizek;
		if (debug_print)
			printk(KERN_DEBUG "hole: %016lx - %016lx\n",
				 hole_basek<<10,
				 (hole_basek + hole_sizek)<<10);
		state->reg = range_to_mtrr(state->reg, hole_basek,
				 hole_sizek, MTRR_TYPE_UNCACHABLE);
	}

	return second_sizek;
}

static void __init
set_var_mtrr_range(struct var_mtrr_state *state, unsigned long base_pfn,
		   unsigned long size_pfn)
{
	unsigned long basek, sizek;
	unsigned long second_sizek = 0;

	if (state->reg >= num_var_ranges)
		return;

	basek = base_pfn << (PAGE_SHIFT - 10);
	sizek = size_pfn << (PAGE_SHIFT - 10);

	/* See if I can merge with the last range */
	if ((basek <= 1024) ||
	    (state->range_startk + state->range_sizek == basek)) {
		unsigned long endk = basek + sizek;
		state->range_sizek = endk - state->range_startk;
		return;
	}
	/* Write the range mtrrs */
	if (state->range_sizek != 0)
		second_sizek = range_to_mtrr_with_hole(state, basek, sizek);

	/* Allocate an msr */
	state->range_startk = basek + second_sizek;
	state->range_sizek  = sizek - second_sizek;
}

/* mininum size of mtrr block that can take hole */
static u64 mtrr_chunk_size __initdata = (256ULL<<20);

static int __init parse_mtrr_chunk_size_opt(char *p)
{
	if (!p)
		return -EINVAL;
	mtrr_chunk_size = memparse(p, &p);
	return 0;
}
early_param("mtrr_chunk_size", parse_mtrr_chunk_size_opt);

/* granity of mtrr of block */
static u64 mtrr_gran_size __initdata;

static int __init parse_mtrr_gran_size_opt(char *p)
{
	if (!p)
		return -EINVAL;
	mtrr_gran_size = memparse(p, &p);
	return 0;
}
early_param("mtrr_gran_size", parse_mtrr_gran_size_opt);

static int nr_mtrr_spare_reg __initdata =
				 CONFIG_MTRR_SANITIZER_SPARE_REG_NR_DEFAULT;

static int __init parse_mtrr_spare_reg(char *arg)
{
	if (arg)
		nr_mtrr_spare_reg = simple_strtoul(arg, NULL, 0);
	return 0;
}

early_param("mtrr_spare_reg_nr", parse_mtrr_spare_reg);

static int __init
x86_setup_var_mtrrs(struct res_range *range, int nr_range,
		    u64 chunk_size, u64 gran_size)
{
	struct var_mtrr_state var_state;
	int i;
	int num_reg;

	var_state.range_startk	= 0;
	var_state.range_sizek	= 0;
	var_state.reg		= 0;
	var_state.chunk_sizek	= chunk_size >> 10;
	var_state.gran_sizek	= gran_size >> 10;

	memset(range_state, 0, sizeof(range_state));

	/* Write the range etc */
	for (i = 0; i < nr_range; i++)
		set_var_mtrr_range(&var_state, range[i].start,
				   range[i].end - range[i].start + 1);

	/* Write the last range */
	if (var_state.range_sizek != 0)
		range_to_mtrr_with_hole(&var_state, 0, 0);

	num_reg = var_state.reg;
	/* Clear out the extra MTRR's */
	while (var_state.reg < num_var_ranges) {
		save_var_mtrr(var_state.reg, 0, 0, 0);
		var_state.reg++;
	}

	return num_reg;
}

struct mtrr_cleanup_result {
	unsigned long gran_sizek;
	unsigned long chunk_sizek;
	unsigned long lose_cover_sizek;
	unsigned int num_reg;
	int bad;
};

/*
 * gran_size: 64K, 128K, 256K, 512K, 1M, 2M, ..., 2G
 * chunk size: gran_size, ..., 2G
 * so we need (1+16)*8
 */
#define NUM_RESULT	136
#define PSHIFT		(PAGE_SHIFT - 10)

static struct mtrr_cleanup_result __initdata result[NUM_RESULT];
static unsigned long __initdata min_loss_pfn[RANGE_NUM];

static void __init print_out_mtrr_range_state(void)
{
	int i;
	char start_factor = 'K', size_factor = 'K';
	unsigned long start_base, size_base;
	mtrr_type type;

	for (i = 0; i < num_var_ranges; i++) {

		size_base = range_state[i].size_pfn << (PAGE_SHIFT - 10);
		if (!size_base)
			continue;

		size_base = to_size_factor(size_base, &size_factor),
		start_base = range_state[i].base_pfn << (PAGE_SHIFT - 10);
		start_base = to_size_factor(start_base, &start_factor),
		type = range_state[i].type;

		printk(KERN_DEBUG "reg %d, base: %ld%cB, range: %ld%cB, type %s\n",
			i, start_base, start_factor,
			size_base, size_factor,
			(type == MTRR_TYPE_UNCACHABLE) ? "UC" :
			    ((type == MTRR_TYPE_WRPROT) ? "WP" :
			     ((type == MTRR_TYPE_WRBACK) ? "WB" : "Other"))
			);
	}
}

static int __init mtrr_need_cleanup(void)
{
	int i;
	mtrr_type type;
	unsigned long size;
	/* extra one for all 0 */
	int num[MTRR_NUM_TYPES + 1];

	/* check entries number */
	memset(num, 0, sizeof(num));
	for (i = 0; i < num_var_ranges; i++) {
		type = range_state[i].type;
		size = range_state[i].size_pfn;
		if (type >= MTRR_NUM_TYPES)
			continue;
		if (!size)
			type = MTRR_NUM_TYPES;
		if (type == MTRR_TYPE_WRPROT)
			type = MTRR_TYPE_UNCACHABLE;
		num[type]++;
	}

	/* check if we got UC entries */
	if (!num[MTRR_TYPE_UNCACHABLE])
		return 0;

	/* check if we only had WB and UC */
	if (num[MTRR_TYPE_WRBACK] + num[MTRR_TYPE_UNCACHABLE] !=
		num_var_ranges - num[MTRR_NUM_TYPES])
		return 0;

	return 1;
}

static unsigned long __initdata range_sums;
static void __init mtrr_calc_range_state(u64 chunk_size, u64 gran_size,
					 unsigned long extra_remove_base,
					 unsigned long extra_remove_size,
					 int i)
{
	int num_reg;
	static struct res_range range_new[RANGE_NUM];
	static int nr_range_new;
	unsigned long range_sums_new;

	/* convert ranges to var ranges state */
	num_reg = x86_setup_var_mtrrs(range, nr_range,
						chunk_size, gran_size);

	/* we got new setting in range_state, check it */
	memset(range_new, 0, sizeof(range_new));
	nr_range_new = x86_get_mtrr_mem_range(range_new, 0,
				extra_remove_base, extra_remove_size);
	range_sums_new = sum_ranges(range_new, nr_range_new);

	result[i].chunk_sizek = chunk_size >> 10;
	result[i].gran_sizek = gran_size >> 10;
	result[i].num_reg = num_reg;
	if (range_sums < range_sums_new) {
		result[i].lose_cover_sizek =
			(range_sums_new - range_sums) << PSHIFT;
		result[i].bad = 1;
	} else
		result[i].lose_cover_sizek =
			(range_sums - range_sums_new) << PSHIFT;

	/* double check it */
	if (!result[i].bad && !result[i].lose_cover_sizek) {
		if (nr_range_new != nr_range ||
			memcmp(range, range_new, sizeof(range)))
				result[i].bad = 1;
	}

	if (!result[i].bad && (range_sums - range_sums_new <
				min_loss_pfn[num_reg])) {
		min_loss_pfn[num_reg] =
			range_sums - range_sums_new;
	}
}

static void __init mtrr_print_out_one_result(int i)
{
	char gran_factor, chunk_factor, lose_factor;
	unsigned long gran_base, chunk_base, lose_base;

	gran_base = to_size_factor(result[i].gran_sizek, &gran_factor),
	chunk_base = to_size_factor(result[i].chunk_sizek, &chunk_factor),
	lose_base = to_size_factor(result[i].lose_cover_sizek, &lose_factor),
	printk(KERN_INFO "%sgran_size: %ld%c \tchunk_size: %ld%c \t",
			result[i].bad ? "*BAD*" : " ",
			gran_base, gran_factor, chunk_base, chunk_factor);
	printk(KERN_CONT "num_reg: %d  \tlose cover RAM: %s%ld%c\n",
			result[i].num_reg, result[i].bad ? "-" : "",
			lose_base, lose_factor);
}

static int __init mtrr_search_optimal_index(void)
{
	int i;
	int num_reg_good;
	int index_good;

	if (nr_mtrr_spare_reg >= num_var_ranges)
		nr_mtrr_spare_reg = num_var_ranges - 1;
	num_reg_good = -1;
	for (i = num_var_ranges - nr_mtrr_spare_reg; i > 0; i--) {
		if (!min_loss_pfn[i])
			num_reg_good = i;
	}

	index_good = -1;
	if (num_reg_good != -1) {
		for (i = 0; i < NUM_RESULT; i++) {
			if (!result[i].bad &&
			    result[i].num_reg == num_reg_good &&
			    !result[i].lose_cover_sizek) {
				index_good = i;
				break;
			}
		}
	}

	return index_good;
}


int __init mtrr_cleanup(unsigned address_bits)
{
	unsigned long extra_remove_base, extra_remove_size;
	unsigned long base, size, def, dummy;
	mtrr_type type;
	u64 chunk_size, gran_size;
	int index_good;
	int i;

	if (!is_cpu(INTEL) || enable_mtrr_cleanup < 1)
		return 0;
	rdmsr(MSR_MTRRdefType, def, dummy);
	def &= 0xff;
	if (def != MTRR_TYPE_UNCACHABLE)
		return 0;

	/* get it and store it aside */
	memset(range_state, 0, sizeof(range_state));
	for (i = 0; i < num_var_ranges; i++) {
		mtrr_if->get(i, &base, &size, &type);
		range_state[i].base_pfn = base;
		range_state[i].size_pfn = size;
		range_state[i].type = type;
	}

	/* check if we need handle it and can handle it */
	if (!mtrr_need_cleanup())
		return 0;

	/* print original var MTRRs at first, for debugging: */
	printk(KERN_DEBUG "original variable MTRRs\n");
	print_out_mtrr_range_state();

	memset(range, 0, sizeof(range));
	extra_remove_size = 0;
	extra_remove_base = 1 << (32 - PAGE_SHIFT);
	if (mtrr_tom2)
		extra_remove_size =
			(mtrr_tom2 >> PAGE_SHIFT) - extra_remove_base;
	nr_range = x86_get_mtrr_mem_range(range, 0, extra_remove_base,
					  extra_remove_size);
	/*
	 * [0, 1M) should always be coverred by var mtrr with WB
	 * and fixed mtrrs should take effective before var mtrr for it
	 */
	nr_range = add_range_with_merge(range, nr_range, 0,
					(1ULL<<(20 - PAGE_SHIFT)) - 1);
	/* sort the ranges */
	sort(range, nr_range, sizeof(struct res_range), cmp_range, NULL);

	range_sums = sum_ranges(range, nr_range);
	printk(KERN_INFO "total RAM coverred: %ldM\n",
	       range_sums >> (20 - PAGE_SHIFT));

	if (mtrr_chunk_size && mtrr_gran_size) {
		i = 0;
		mtrr_calc_range_state(mtrr_chunk_size, mtrr_gran_size,
				      extra_remove_base, extra_remove_size, i);

		mtrr_print_out_one_result(i);

		if (!result[i].bad) {
			set_var_mtrr_all(address_bits);
			printk(KERN_DEBUG "New variable MTRRs\n");
			print_out_mtrr_range_state();
			return 1;
		}
		printk(KERN_INFO "invalid mtrr_gran_size or mtrr_chunk_size, "
		       "will find optimal one\n");
	}

	i = 0;
	memset(min_loss_pfn, 0xff, sizeof(min_loss_pfn));
	memset(result, 0, sizeof(result));
	for (gran_size = (1ULL<<16); gran_size < (1ULL<<32); gran_size <<= 1) {

		for (chunk_size = gran_size; chunk_size < (1ULL<<32);
		     chunk_size <<= 1) {

			if (i >= NUM_RESULT)
				continue;

			mtrr_calc_range_state(chunk_size, gran_size,
				      extra_remove_base, extra_remove_size, i);
			if (debug_print) {
				mtrr_print_out_one_result(i);
				printk(KERN_INFO "\n");
			}

			i++;
		}
	}

	/* try to find the optimal index */
	index_good = mtrr_search_optimal_index();

	if (index_good != -1) {
		printk(KERN_INFO "Found optimal setting for mtrr clean up\n");
		i = index_good;
		mtrr_print_out_one_result(i);

		/* convert ranges to var ranges state */
		chunk_size = result[i].chunk_sizek;
		chunk_size <<= 10;
		gran_size = result[i].gran_sizek;
		gran_size <<= 10;
		x86_setup_var_mtrrs(range, nr_range, chunk_size, gran_size);
		set_var_mtrr_all(address_bits);
		printk(KERN_DEBUG "New variable MTRRs\n");
		print_out_mtrr_range_state();
		return 1;
	} else {
		/* print out all */
		for (i = 0; i < NUM_RESULT; i++)
			mtrr_print_out_one_result(i);
	}

	printk(KERN_INFO "mtrr_cleanup: can not find optimal value\n");
	printk(KERN_INFO "please specify mtrr_gran_size/mtrr_chunk_size\n");

	return 0;
}
#else
int __init mtrr_cleanup(unsigned address_bits)
{
	return 0;
}
#endif

static int disable_mtrr_trim;

static int __init disable_mtrr_trim_setup(char *str)
{
	disable_mtrr_trim = 1;
	return 0;
}
early_param("disable_mtrr_trim", disable_mtrr_trim_setup);

/*
 * Newer AMD K8s and later CPUs have a special magic MSR way to force WB
 * for memory >4GB. Check for that here.
 * Note this won't check if the MTRRs < 4GB where the magic bit doesn't
 * apply to are wrong, but so far we don't know of any such case in the wild.
 */
#define Tom2Enabled (1U << 21)
#define Tom2ForceMemTypeWB (1U << 22)

int __init amd_special_default_mtrr(void)
{
	u32 l, h;

	if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD)
		return 0;
	if (boot_cpu_data.x86 < 0xf || boot_cpu_data.x86 > 0x11)
		return 0;
	/* In case some hypervisor doesn't pass SYSCFG through */
	if (rdmsr_safe(MSR_K8_SYSCFG, &l, &h) < 0)
		return 0;
	/*
	 * Memory between 4GB and top of mem is forced WB by this magic bit.
	 * Reserved before K8RevF, but should be zero there.
	 */
	if ((l & (Tom2Enabled | Tom2ForceMemTypeWB)) ==
		 (Tom2Enabled | Tom2ForceMemTypeWB))
		return 1;
	return 0;
}

static u64 __init real_trim_memory(unsigned long start_pfn,
				   unsigned long limit_pfn)
{
	u64 trim_start, trim_size;
	trim_start = start_pfn;
	trim_start <<= PAGE_SHIFT;
	trim_size = limit_pfn;
	trim_size <<= PAGE_SHIFT;
	trim_size -= trim_start;

	return e820_update_range(trim_start, trim_size, E820_RAM,
				E820_RESERVED);
}
/**
 * mtrr_trim_uncached_memory - trim RAM not covered by MTRRs
 * @end_pfn: ending page frame number
 *
 * Some buggy BIOSes don't setup the MTRRs properly for systems with certain
 * memory configurations.  This routine checks that the highest MTRR matches
 * the end of memory, to make sure the MTRRs having a write back type cover
 * all of the memory the kernel is intending to use. If not, it'll trim any
 * memory off the end by adjusting end_pfn, removing it from the kernel's
 * allocation pools, warning the user with an obnoxious message.
 */
int __init mtrr_trim_uncached_memory(unsigned long end_pfn)
{
	unsigned long i, base, size, highest_pfn = 0, def, dummy;
	mtrr_type type;
	u64 total_trim_size;

	/* extra one for all 0 */
	int num[MTRR_NUM_TYPES + 1];
	/*
	 * Make sure we only trim uncachable memory on machines that
	 * support the Intel MTRR architecture:
	 */
	if (!is_cpu(INTEL) || disable_mtrr_trim)
		return 0;
	rdmsr(MSR_MTRRdefType, def, dummy);
	def &= 0xff;
	if (def != MTRR_TYPE_UNCACHABLE)
		return 0;

	/* get it and store it aside */
	memset(range_state, 0, sizeof(range_state));
	for (i = 0; i < num_var_ranges; i++) {
		mtrr_if->get(i, &base, &size, &type);
		range_state[i].base_pfn = base;
		range_state[i].size_pfn = size;
		range_state[i].type = type;
	}

	/* Find highest cached pfn */
	for (i = 0; i < num_var_ranges; i++) {
		type = range_state[i].type;
		if (type != MTRR_TYPE_WRBACK)
			continue;
		base = range_state[i].base_pfn;
		size = range_state[i].size_pfn;
		if (highest_pfn < base + size)
			highest_pfn = base + size;
	}

	/* kvm/qemu doesn't have mtrr set right, don't trim them all */
	if (!highest_pfn) {
		printk(KERN_INFO "CPU MTRRs all blank - virtualized system.\n");
		return 0;
	}

	/* check entries number */
	memset(num, 0, sizeof(num));
	for (i = 0; i < num_var_ranges; i++) {
		type = range_state[i].type;
		if (type >= MTRR_NUM_TYPES)
			continue;
		size = range_state[i].size_pfn;
		if (!size)
			type = MTRR_NUM_TYPES;
		num[type]++;
	}

	/* no entry for WB? */
	if (!num[MTRR_TYPE_WRBACK])
		return 0;

	/* check if we only had WB and UC */
	if (num[MTRR_TYPE_WRBACK] + num[MTRR_TYPE_UNCACHABLE] !=
		num_var_ranges - num[MTRR_NUM_TYPES])
		return 0;

	memset(range, 0, sizeof(range));
	nr_range = 0;
	if (mtrr_tom2) {
		range[nr_range].start = (1ULL<<(32 - PAGE_SHIFT));
		range[nr_range].end = (mtrr_tom2 >> PAGE_SHIFT) - 1;
		if (highest_pfn < range[nr_range].end + 1)
			highest_pfn = range[nr_range].end + 1;
		nr_range++;
	}
	nr_range = x86_get_mtrr_mem_range(range, nr_range, 0, 0);

	total_trim_size = 0;
	/* check the head */
	if (range[0].start)
		total_trim_size += real_trim_memory(0, range[0].start);
	/* check the holes */
	for (i = 0; i < nr_range - 1; i++) {
		if (range[i].end + 1 < range[i+1].start)
			total_trim_size += real_trim_memory(range[i].end + 1,
							    range[i+1].start);
	}
	/* check the top */
	i = nr_range - 1;
	if (range[i].end + 1 < end_pfn)
		total_trim_size += real_trim_memory(range[i].end + 1,
							 end_pfn);

	if (total_trim_size) {
		printk(KERN_WARNING "WARNING: BIOS bug: CPU MTRRs don't cover"
			" all of memory, losing %lluMB of RAM.\n",
			total_trim_size >> 20);

		if (!changed_by_mtrr_cleanup)
			WARN_ON(1);

		printk(KERN_INFO "update e820 for mtrr\n");
		update_e820();

		return 1;
	}

	return 0;
}