aboutsummaryrefslogtreecommitdiffstats
path: root/arch/powerpc/mm/hash_utils_64.c
blob: 0f2d239d94c440608dadf79671b4b95f6cf4e0e9 (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
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
/*
 * PowerPC64 port by Mike Corrigan and Dave Engebretsen
 *   {mikejc|engebret}@us.ibm.com
 *
 *    Copyright (c) 2000 Mike Corrigan <mikejc@us.ibm.com>
 *
 * SMP scalability work:
 *    Copyright (C) 2001 Anton Blanchard <anton@au.ibm.com>, IBM
 * 
 *    Module name: htab.c
 *
 *    Description:
 *      PowerPC Hashed Page Table functions
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public License
 * as published by the Free Software Foundation; either version
 * 2 of the License, or (at your option) any later version.
 */

#undef DEBUG
#undef DEBUG_LOW

#include <linux/spinlock.h>
#include <linux/errno.h>
#include <linux/sched.h>
#include <linux/proc_fs.h>
#include <linux/stat.h>
#include <linux/sysctl.h>
#include <linux/ctype.h>
#include <linux/cache.h>
#include <linux/init.h>
#include <linux/signal.h>
#include <linux/lmb.h>

#include <asm/processor.h>
#include <asm/pgtable.h>
#include <asm/mmu.h>
#include <asm/mmu_context.h>
#include <asm/page.h>
#include <asm/types.h>
#include <asm/system.h>
#include <asm/uaccess.h>
#include <asm/machdep.h>
#include <asm/prom.h>
#include <asm/abs_addr.h>
#include <asm/tlbflush.h>
#include <asm/io.h>
#include <asm/eeh.h>
#include <asm/tlb.h>
#include <asm/cacheflush.h>
#include <asm/cputable.h>
#include <asm/sections.h>
#include <asm/spu.h>
#include <asm/udbg.h>

#ifdef DEBUG
#define DBG(fmt...) udbg_printf(fmt)
#else
#define DBG(fmt...)
#endif

#ifdef DEBUG_LOW
#define DBG_LOW(fmt...) udbg_printf(fmt)
#else
#define DBG_LOW(fmt...)
#endif

#define KB (1024)
#define MB (1024*KB)

/*
 * Note:  pte   --> Linux PTE
 *        HPTE  --> PowerPC Hashed Page Table Entry
 *
 * Execution context:
 *   htab_initialize is called with the MMU off (of course), but
 *   the kernel has been copied down to zero so it can directly
 *   reference global data.  At this point it is very difficult
 *   to print debug info.
 *
 */

#ifdef CONFIG_U3_DART
extern unsigned long dart_tablebase;
#endif /* CONFIG_U3_DART */

static unsigned long _SDR1;
struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT];

struct hash_pte *htab_address;
unsigned long htab_size_bytes;
unsigned long htab_hash_mask;
int mmu_linear_psize = MMU_PAGE_4K;
int mmu_virtual_psize = MMU_PAGE_4K;
int mmu_vmalloc_psize = MMU_PAGE_4K;
#ifdef CONFIG_SPARSEMEM_VMEMMAP
int mmu_vmemmap_psize = MMU_PAGE_4K;
#endif
int mmu_io_psize = MMU_PAGE_4K;
int mmu_kernel_ssize = MMU_SEGSIZE_256M;
int mmu_highuser_ssize = MMU_SEGSIZE_256M;
u16 mmu_slb_size = 64;
#ifdef CONFIG_HUGETLB_PAGE
int mmu_huge_psize = MMU_PAGE_16M;
unsigned int HPAGE_SHIFT;
#endif
#ifdef CONFIG_PPC_64K_PAGES
int mmu_ci_restrictions;
#endif
#ifdef CONFIG_DEBUG_PAGEALLOC
static u8 *linear_map_hash_slots;
static unsigned long linear_map_hash_count;
static DEFINE_SPINLOCK(linear_map_hash_lock);
#endif /* CONFIG_DEBUG_PAGEALLOC */

/* There are definitions of page sizes arrays to be used when none
 * is provided by the firmware.
 */

/* Pre-POWER4 CPUs (4k pages only)
 */
struct mmu_psize_def mmu_psize_defaults_old[] = {
	[MMU_PAGE_4K] = {
		.shift	= 12,
		.sllp	= 0,
		.penc	= 0,
		.avpnm	= 0,
		.tlbiel = 0,
	},
};

/* POWER4, GPUL, POWER5
 *
 * Support for 16Mb large pages
 */
struct mmu_psize_def mmu_psize_defaults_gp[] = {
	[MMU_PAGE_4K] = {
		.shift	= 12,
		.sllp	= 0,
		.penc	= 0,
		.avpnm	= 0,
		.tlbiel = 1,
	},
	[MMU_PAGE_16M] = {
		.shift	= 24,
		.sllp	= SLB_VSID_L,
		.penc	= 0,
		.avpnm	= 0x1UL,
		.tlbiel = 0,
	},
};


int htab_bolt_mapping(unsigned long vstart, unsigned long vend,
		      unsigned long pstart, unsigned long mode,
		      int psize, int ssize)
{
	unsigned long vaddr, paddr;
	unsigned int step, shift;
	unsigned long tmp_mode;
	int ret = 0;

	shift = mmu_psize_defs[psize].shift;
	step = 1 << shift;

	for (vaddr = vstart, paddr = pstart; vaddr < vend;
	     vaddr += step, paddr += step) {
		unsigned long hash, hpteg;
		unsigned long vsid = get_kernel_vsid(vaddr, ssize);
		unsigned long va = hpt_va(vaddr, vsid, ssize);

		tmp_mode = mode;
		
		/* Make non-kernel text non-executable */
		if (!in_kernel_text(vaddr))
			tmp_mode = mode | HPTE_R_N;

		hash = hpt_hash(va, shift, ssize);
		hpteg = ((hash & htab_hash_mask) * HPTES_PER_GROUP);

		DBG("htab_bolt_mapping: calling %p\n", ppc_md.hpte_insert);

		BUG_ON(!ppc_md.hpte_insert);
		ret = ppc_md.hpte_insert(hpteg, va, paddr,
				tmp_mode, HPTE_V_BOLTED, psize, ssize);

		if (ret < 0)
			break;
#ifdef CONFIG_DEBUG_PAGEALLOC
		if ((paddr >> PAGE_SHIFT) < linear_map_hash_count)
			linear_map_hash_slots[paddr >> PAGE_SHIFT] = ret | 0x80;
#endif /* CONFIG_DEBUG_PAGEALLOC */
	}
	return ret < 0 ? ret : 0;
}

#ifdef CONFIG_MEMORY_HOTPLUG
static int htab_remove_mapping(unsigned long vstart, unsigned long vend,
		      int psize, int ssize)
{
	unsigned long vaddr;
	unsigned int step, shift;

	shift = mmu_psize_defs[psize].shift;
	step = 1 << shift;

	if (!ppc_md.hpte_removebolted) {
		printk(KERN_WARNING "Platform doesn't implement "
				"hpte_removebolted\n");
		return -EINVAL;
	}

	for (vaddr = vstart; vaddr < vend; vaddr += step)
		ppc_md.hpte_removebolted(vaddr, psize, ssize);

	return 0;
}
#endif /* CONFIG_MEMORY_HOTPLUG */

static int __init htab_dt_scan_seg_sizes(unsigned long node,
					 const char *uname, int depth,
					 void *data)
{
	char *type = of_get_flat_dt_prop(node, "device_type", NULL);
	u32 *prop;
	unsigned long size = 0;

	/* We are scanning "cpu" nodes only */
	if (type == NULL || strcmp(type, "cpu") != 0)
		return 0;

	prop = (u32 *)of_get_flat_dt_prop(node, "ibm,processor-segment-sizes",
					  &size);
	if (prop == NULL)
		return 0;
	for (; size >= 4; size -= 4, ++prop) {
		if (prop[0] == 40) {
			DBG("1T segment support detected\n");
			cur_cpu_spec->cpu_features |= CPU_FTR_1T_SEGMENT;
			return 1;
		}
	}
	cur_cpu_spec->cpu_features &= ~CPU_FTR_NO_SLBIE_B;
	return 0;
}

static void __init htab_init_seg_sizes(void)
{
	of_scan_flat_dt(htab_dt_scan_seg_sizes, NULL);
}

static int __init htab_dt_scan_page_sizes(unsigned long node,
					  const char *uname, int depth,
					  void *data)
{
	char *type = of_get_flat_dt_prop(node, "device_type", NULL);
	u32 *prop;
	unsigned long size = 0;

	/* We are scanning "cpu" nodes only */
	if (type == NULL || strcmp(type, "cpu") != 0)
		return 0;

	prop = (u32 *)of_get_flat_dt_prop(node,
					  "ibm,segment-page-sizes", &size);
	if (prop != NULL) {
		DBG("Page sizes from device-tree:\n");
		size /= 4;
		cur_cpu_spec->cpu_features &= ~(CPU_FTR_16M_PAGE);
		while(size > 0) {
			unsigned int shift = prop[0];
			unsigned int slbenc = prop[1];
			unsigned int lpnum = prop[2];
			unsigned int lpenc = 0;
			struct mmu_psize_def *def;
			int idx = -1;

			size -= 3; prop += 3;
			while(size > 0 && lpnum) {
				if (prop[0] == shift)
					lpenc = prop[1];
				prop += 2; size -= 2;
				lpnum--;
			}
			switch(shift) {
			case 0xc:
				idx = MMU_PAGE_4K;
				break;
			case 0x10:
				idx = MMU_PAGE_64K;
				break;
			case 0x14:
				idx = MMU_PAGE_1M;
				break;
			case 0x18:
				idx = MMU_PAGE_16M;
				cur_cpu_spec->cpu_features |= CPU_FTR_16M_PAGE;
				break;
			case 0x22:
				idx = MMU_PAGE_16G;
				break;
			}
			if (idx < 0)
				continue;
			def = &mmu_psize_defs[idx];
			def->shift = shift;
			if (shift <= 23)
				def->avpnm = 0;
			else
				def->avpnm = (1 << (shift - 23)) - 1;
			def->sllp = slbenc;
			def->penc = lpenc;
			/* We don't know for sure what's up with tlbiel, so
			 * for now we only set it for 4K and 64K pages
			 */
			if (idx == MMU_PAGE_4K || idx == MMU_PAGE_64K)
				def->tlbiel = 1;
			else
				def->tlbiel = 0;

			DBG(" %d: shift=%02x, sllp=%04x, avpnm=%08x, "
			    "tlbiel=%d, penc=%d\n",
			    idx, shift, def->sllp, def->avpnm, def->tlbiel,
			    def->penc);
		}
		return 1;
	}
	return 0;
}

static void __init htab_init_page_sizes(void)
{
	int rc;

	/* Default to 4K pages only */
	memcpy(mmu_psize_defs, mmu_psize_defaults_old,
	       sizeof(mmu_psize_defaults_old));

	/*
	 * Try to find the available page sizes in the device-tree
	 */
	rc = of_scan_flat_dt(htab_dt_scan_page_sizes, NULL);
	if (rc != 0)  /* Found */
		goto found;

	/*
	 * Not in the device-tree, let's fallback on known size
	 * list for 16M capable GP & GR
	 */
	if (cpu_has_feature(CPU_FTR_16M_PAGE))
		memcpy(mmu_psize_defs, mmu_psize_defaults_gp,
		       sizeof(mmu_psize_defaults_gp));
 found:
#ifndef CONFIG_DEBUG_PAGEALLOC
	/*
	 * Pick a size for the linear mapping. Currently, we only support
	 * 16M, 1M and 4K which is the default
	 */
	if (mmu_psize_defs[MMU_PAGE_16M].shift)
		mmu_linear_psize = MMU_PAGE_16M;
	else if (mmu_psize_defs[MMU_PAGE_1M].shift)
		mmu_linear_psize = MMU_PAGE_1M;
#endif /* CONFIG_DEBUG_PAGEALLOC */

#ifdef CONFIG_PPC_64K_PAGES
	/*
	 * Pick a size for the ordinary pages. Default is 4K, we support
	 * 64K for user mappings and vmalloc if supported by the processor.
	 * We only use 64k for ioremap if the processor
	 * (and firmware) support cache-inhibited large pages.
	 * If not, we use 4k and set mmu_ci_restrictions so that
	 * hash_page knows to switch processes that use cache-inhibited
	 * mappings to 4k pages.
	 */
	if (mmu_psize_defs[MMU_PAGE_64K].shift) {
		mmu_virtual_psize = MMU_PAGE_64K;
		mmu_vmalloc_psize = MMU_PAGE_64K;
		if (mmu_linear_psize == MMU_PAGE_4K)
			mmu_linear_psize = MMU_PAGE_64K;
		if (cpu_has_feature(CPU_FTR_CI_LARGE_PAGE)) {
			/*
			 * Don't use 64k pages for ioremap on pSeries, since
			 * that would stop us accessing the HEA ethernet.
			 */
			if (!machine_is(pseries))
				mmu_io_psize = MMU_PAGE_64K;
		} else
			mmu_ci_restrictions = 1;
	}
#endif /* CONFIG_PPC_64K_PAGES */

#ifdef CONFIG_SPARSEMEM_VMEMMAP
	/* We try to use 16M pages for vmemmap if that is supported
	 * and we have at least 1G of RAM at boot
	 */
	if (mmu_psize_defs[MMU_PAGE_16M].shift &&
	    lmb_phys_mem_size() >= 0x40000000)
		mmu_vmemmap_psize = MMU_PAGE_16M;
	else if (mmu_psize_defs[MMU_PAGE_64K].shift)
		mmu_vmemmap_psize = MMU_PAGE_64K;
	else
		mmu_vmemmap_psize = MMU_PAGE_4K;
#endif /* CONFIG_SPARSEMEM_VMEMMAP */

	printk(KERN_DEBUG "Page orders: linear mapping = %d, "
	       "virtual = %d, io = %d"
#ifdef CONFIG_SPARSEMEM_VMEMMAP
	       ", vmemmap = %d"
#endif
	       "\n",
	       mmu_psize_defs[mmu_linear_psize].shift,
	       mmu_psize_defs[mmu_virtual_psize].shift,
	       mmu_psize_defs[mmu_io_psize].shift
#ifdef CONFIG_SPARSEMEM_VMEMMAP
	       ,mmu_psize_defs[mmu_vmemmap_psize].shift
#endif
	       );

#ifdef CONFIG_HUGETLB_PAGE
	/* Init large page size. Currently, we pick 16M or 1M depending
	 * on what is available
	 */
	if (mmu_psize_defs[MMU_PAGE_16M].shift)
		set_huge_psize(MMU_PAGE_16M);
	/* With 4k/4level pagetables, we can't (for now) cope with a
	 * huge page size < PMD_SIZE */
	else if (mmu_psize_defs[MMU_PAGE_1M].shift)
		set_huge_psize(MMU_PAGE_1M);
#endif /* CONFIG_HUGETLB_PAGE */
}

static int __init htab_dt_scan_pftsize(unsigned long node,
				       const char *uname, int depth,
				       void *data)
{
	char *type = of_get_flat_dt_prop(node, "device_type", NULL);
	u32 *prop;

	/* We are scanning "cpu" nodes only */
	if (type == NULL || strcmp(type, "cpu") != 0)
		return 0;

	prop = (u32 *)of_get_flat_dt_prop(node, "ibm,pft-size", NULL);
	if (prop != NULL) {
		/* pft_size[0] is the NUMA CEC cookie */
		ppc64_pft_size = prop[1];
		return 1;
	}
	return 0;
}

static unsigned long __init htab_get_table_size(void)
{
	unsigned long mem_size, rnd_mem_size, pteg_count;

	/* If hash size isn't already provided by the platform, we try to
	 * retrieve it from the device-tree. If it's not there neither, we
	 * calculate it now based on the total RAM size
	 */
	if (ppc64_pft_size == 0)
		of_scan_flat_dt(htab_dt_scan_pftsize, NULL);
	if (ppc64_pft_size)
		return 1UL << ppc64_pft_size;

	/* round mem_size up to next power of 2 */
	mem_size = lmb_phys_mem_size();
	rnd_mem_size = 1UL << __ilog2(mem_size);
	if (rnd_mem_size < mem_size)
		rnd_mem_size <<= 1;

	/* # pages / 2 */
	pteg_count = max(rnd_mem_size >> (12 + 1), 1UL << 11);

	return pteg_count << 7;
}

#ifdef CONFIG_MEMORY_HOTPLUG
void create_section_mapping(unsigned long start, unsigned long end)
{
		BUG_ON(htab_bolt_mapping(start, end, __pa(start),
			_PAGE_ACCESSED | _PAGE_DIRTY | _PAGE_COHERENT | PP_RWXX,
			mmu_linear_psize, mmu_kernel_ssize));
}

int remove_section_mapping(unsigned long start, unsigned long end)
{
	return htab_remove_mapping(start, end, mmu_linear_psize,
			mmu_kernel_ssize);
}
#endif /* CONFIG_MEMORY_HOTPLUG */

static inline void make_bl(unsigned int *insn_addr, void *func)
{
	unsigned long funcp = *((unsigned long *)func);
	int offset = funcp - (unsigned long)insn_addr;

	*insn_addr = (unsigned int)(0x48000001 | (offset & 0x03fffffc));
	flush_icache_range((unsigned long)insn_addr, 4+
			   (unsigned long)insn_addr);
}

static void __init htab_finish_init(void)
{
	extern unsigned int *htab_call_hpte_insert1;
	extern unsigned int *htab_call_hpte_insert2;
	extern unsigned int *htab_call_hpte_remove;
	extern unsigned int *htab_call_hpte_updatepp;

#ifdef CONFIG_PPC_HAS_HASH_64K
	extern unsigned int *ht64_call_hpte_insert1;
	extern unsigned int *ht64_call_hpte_insert2;
	extern unsigned int *ht64_call_hpte_remove;
	extern unsigned int *ht64_call_hpte_updatepp;

	make_bl(ht64_call_hpte_insert1, ppc_md.hpte_insert);
	make_bl(ht64_call_hpte_insert2, ppc_md.hpte_insert);
	make_bl(ht64_call_hpte_remove, ppc_md.hpte_remove);
	make_bl(ht64_call_hpte_updatepp, ppc_md.hpte_updatepp);
#endif /* CONFIG_PPC_HAS_HASH_64K */

	make_bl(htab_call_hpte_insert1, ppc_md.hpte_insert);
	make_bl(htab_call_hpte_insert2, ppc_md.hpte_insert);
	make_bl(htab_call_hpte_remove, ppc_md.hpte_remove);
	make_bl(htab_call_hpte_updatepp, ppc_md.hpte_updatepp);
}

void __init htab_initialize(void)
{
	unsigned long table;
	unsigned long pteg_count;
	unsigned long mode_rw;
	unsigned long base = 0, size = 0, limit;
	int i;

	extern unsigned long tce_alloc_start, tce_alloc_end;

	DBG(" -> htab_initialize()\n");

	/* Initialize segment sizes */
	htab_init_seg_sizes();

	/* Initialize page sizes */
	htab_init_page_sizes();

	if (cpu_has_feature(CPU_FTR_1T_SEGMENT)) {
		mmu_kernel_ssize = MMU_SEGSIZE_1T;
		mmu_highuser_ssize = MMU_SEGSIZE_1T;
		printk(KERN_INFO "Using 1TB segments\n");
	}

	/*
	 * Calculate the required size of the htab.  We want the number of
	 * PTEGs to equal one half the number of real pages.
	 */ 
	htab_size_bytes = htab_get_table_size();
	pteg_count = htab_size_bytes >> 7;

	htab_hash_mask = pteg_count - 1;

	if (firmware_has_feature(FW_FEATURE_LPAR)) {
		/* Using a hypervisor which owns the htab */
		htab_address = NULL;
		_SDR1 = 0; 
	} else {
		/* Find storage for the HPT.  Must be contiguous in
		 * the absolute address space. On cell we want it to be
		 * in the first 2 Gig so we can use it for IOMMU hacks.
		 */
		if (machine_is(cell))
			limit = 0x80000000;
		else
			limit = 0;

		table = lmb_alloc_base(htab_size_bytes, htab_size_bytes, limit);

		DBG("Hash table allocated at %lx, size: %lx\n", table,
		    htab_size_bytes);

		htab_address = abs_to_virt(table);

		/* htab absolute addr + encoded htabsize */
		_SDR1 = table + __ilog2(pteg_count) - 11;

		/* Initialize the HPT with no entries */
		memset((void *)table, 0, htab_size_bytes);

		/* Set SDR1 */
		mtspr(SPRN_SDR1, _SDR1);
	}

	mode_rw = _PAGE_ACCESSED | _PAGE_DIRTY | _PAGE_COHERENT | PP_RWXX;

#ifdef CONFIG_DEBUG_PAGEALLOC
	linear_map_hash_count = lmb_end_of_DRAM() >> PAGE_SHIFT;
	linear_map_hash_slots = __va(lmb_alloc_base(linear_map_hash_count,
						    1, lmb.rmo_size));
	memset(linear_map_hash_slots, 0, linear_map_hash_count);
#endif /* CONFIG_DEBUG_PAGEALLOC */

	/* On U3 based machines, we need to reserve the DART area and
	 * _NOT_ map it to avoid cache paradoxes as it's remapped non
	 * cacheable later on
	 */

	/* create bolted the linear mapping in the hash table */
	for (i=0; i < lmb.memory.cnt; i++) {
		base = (unsigned long)__va(lmb.memory.region[i].base);
		size = lmb.memory.region[i].size;

		DBG("creating mapping for region: %lx : %lx\n", base, size);

#ifdef CONFIG_U3_DART
		/* Do not map the DART space. Fortunately, it will be aligned
		 * in such a way that it will not cross two lmb regions and
		 * will fit within a single 16Mb page.
		 * The DART space is assumed to be a full 16Mb region even if
		 * we only use 2Mb of that space. We will use more of it later
		 * for AGP GART. We have to use a full 16Mb large page.
		 */
		DBG("DART base: %lx\n", dart_tablebase);

		if (dart_tablebase != 0 && dart_tablebase >= base
		    && dart_tablebase < (base + size)) {
			unsigned long dart_table_end = dart_tablebase + 16 * MB;
			if (base != dart_tablebase)
				BUG_ON(htab_bolt_mapping(base, dart_tablebase,
							__pa(base), mode_rw,
							mmu_linear_psize,
							mmu_kernel_ssize));
			if ((base + size) > dart_table_end)
				BUG_ON(htab_bolt_mapping(dart_tablebase+16*MB,
							base + size,
							__pa(dart_table_end),
							 mode_rw,
							 mmu_linear_psize,
							 mmu_kernel_ssize));
			continue;
		}
#endif /* CONFIG_U3_DART */
		BUG_ON(htab_bolt_mapping(base, base + size, __pa(base),
				mode_rw, mmu_linear_psize, mmu_kernel_ssize));
       }

	/*
	 * If we have a memory_limit and we've allocated TCEs then we need to
	 * explicitly map the TCE area at the top of RAM. We also cope with the
	 * case that the TCEs start below memory_limit.
	 * tce_alloc_start/end are 16MB aligned so the mapping should work
	 * for either 4K or 16MB pages.
	 */
	if (tce_alloc_start) {
		tce_alloc_start = (unsigned long)__va(tce_alloc_start);
		tce_alloc_end = (unsigned long)__va(tce_alloc_end);

		if (base + size >= tce_alloc_start)
			tce_alloc_start = base + size + 1;

		BUG_ON(htab_bolt_mapping(tce_alloc_start, tce_alloc_end,
					 __pa(tce_alloc_start), mode_rw,
					 mmu_linear_psize, mmu_kernel_ssize));
	}

	htab_finish_init();

	DBG(" <- htab_initialize()\n");
}
#undef KB
#undef MB

void htab_initialize_secondary(void)
{
	if (!firmware_has_feature(FW_FEATURE_LPAR))
		mtspr(SPRN_SDR1, _SDR1);
}

/*
 * Called by asm hashtable.S for doing lazy icache flush
 */
unsigned int hash_page_do_lazy_icache(unsigned int pp, pte_t pte, int trap)
{
	struct page *page;

	if (!pfn_valid(pte_pfn(pte)))
		return pp;

	page = pte_page(pte);

	/* page is dirty */
	if (!test_bit(PG_arch_1, &page->flags) && !PageReserved(page)) {
		if (trap == 0x400) {
			__flush_dcache_icache(page_address(page));
			set_bit(PG_arch_1, &page->flags);
		} else
			pp |= HPTE_R_N;
	}
	return pp;
}

/*
 * Demote a segment to using 4k pages.
 * For now this makes the whole process use 4k pages.
 */
#ifdef CONFIG_PPC_64K_PAGES
void demote_segment_4k(struct mm_struct *mm, unsigned long addr)
{
	if (mm->context.user_psize == MMU_PAGE_4K)
		return;
	slice_set_user_psize(mm, MMU_PAGE_4K);
#ifdef CONFIG_SPU_BASE
	spu_flush_all_slbs(mm);
#endif
	if (get_paca()->context.user_psize != MMU_PAGE_4K) {
		get_paca()->context = mm->context;
		slb_flush_and_rebolt();
	}
}
#endif /* CONFIG_PPC_64K_PAGES */

#ifdef CONFIG_PPC_SUBPAGE_PROT
/*
 * This looks up a 2-bit protection code for a 4k subpage of a 64k page.
 * Userspace sets the subpage permissions using the subpage_prot system call.
 *
 * Result is 0: full permissions, _PAGE_RW: read-only,
 * _PAGE_USER or _PAGE_USER|_PAGE_RW: no access.
 */
static int subpage_protection(pgd_t *pgdir, unsigned long ea)
{
	struct subpage_prot_table *spt = pgd_subpage_prot(pgdir);
	u32 spp = 0;
	u32 **sbpm, *sbpp;

	if (ea >= spt->maxaddr)
		return 0;
	if (ea < 0x100000000) {
		/* addresses below 4GB use spt->low_prot */
		sbpm = spt->low_prot;
	} else {
		sbpm = spt->protptrs[ea >> SBP_L3_SHIFT];
		if (!sbpm)
			return 0;
	}
	sbpp = sbpm[(ea >> SBP_L2_SHIFT) & (SBP_L2_COUNT - 1)];
	if (!sbpp)
		return 0;
	spp = sbpp[(ea >> PAGE_SHIFT) & (SBP_L1_COUNT - 1)];

	/* extract 2-bit bitfield for this 4k subpage */
	spp >>= 30 - 2 * ((ea >> 12) & 0xf);

	/* turn 0,1,2,3 into combination of _PAGE_USER and _PAGE_RW */
	spp = ((spp & 2) ? _PAGE_USER : 0) | ((spp & 1) ? _PAGE_RW : 0);
	return spp;
}

#else /* CONFIG_PPC_SUBPAGE_PROT */
static inline int subpage_protection(pgd_t *pgdir, unsigned long ea)
{
	return 0;
}
#endif

/* Result code is:
 *  0 - handled
 *  1 - normal page fault
 * -1 - critical hash insertion error
 * -2 - access not permitted by subpage protection mechanism
 */
int hash_page(unsigned long ea, unsigned long access, unsigned long trap)
{
	void *pgdir;
	unsigned long vsid;
	struct mm_struct *mm;
	pte_t *ptep;
	cpumask_t tmp;
	int rc, user_region = 0, local = 0;
	int psize, ssize;

	DBG_LOW("hash_page(ea=%016lx, access=%lx, trap=%lx\n",
		ea, access, trap);

	if ((ea & ~REGION_MASK) >= PGTABLE_RANGE) {
		DBG_LOW(" out of pgtable range !\n");
 		return 1;
	}

	/* Get region & vsid */
 	switch (REGION_ID(ea)) {
	case USER_REGION_ID:
		user_region = 1;
		mm = current->mm;
		if (! mm) {
			DBG_LOW(" user region with no mm !\n");
			return 1;
		}
#ifdef CONFIG_PPC_MM_SLICES
		psize = get_slice_psize(mm, ea);
#else
		psize = mm->context.user_psize;
#endif
		ssize = user_segment_size(ea);
		vsid = get_vsid(mm->context.id, ea, ssize);
		break;
	case VMALLOC_REGION_ID:
		mm = &init_mm;
		vsid = get_kernel_vsid(ea, mmu_kernel_ssize);
		if (ea < VMALLOC_END)
			psize = mmu_vmalloc_psize;
		else
			psize = mmu_io_psize;
		ssize = mmu_kernel_ssize;
		break;
	default:
		/* Not a valid range
		 * Send the problem up to do_page_fault 
		 */
		return 1;
	}
	DBG_LOW(" mm=%p, mm->pgdir=%p, vsid=%016lx\n", mm, mm->pgd, vsid);

	/* Get pgdir */
	pgdir = mm->pgd;
	if (pgdir == NULL)
		return 1;

	/* Check CPU locality */
	tmp = cpumask_of_cpu(smp_processor_id());
	if (user_region && cpus_equal(mm->cpu_vm_mask, tmp))
		local = 1;

#ifdef CONFIG_HUGETLB_PAGE
	/* Handle hugepage regions */
	if (HPAGE_SHIFT && psize == mmu_huge_psize) {
		DBG_LOW(" -> huge page !\n");
		return hash_huge_page(mm, access, ea, vsid, local, trap);
	}
#endif /* CONFIG_HUGETLB_PAGE */

#ifndef CONFIG_PPC_64K_PAGES
	/* If we use 4K pages and our psize is not 4K, then we are hitting
	 * a special driver mapping, we need to align the address before
	 * we fetch the PTE
	 */
	if (psize != MMU_PAGE_4K)
		ea &= ~((1ul << mmu_psize_defs[psize].shift) - 1);
#endif /* CONFIG_PPC_64K_PAGES */

	/* Get PTE and page size from page tables */
	ptep = find_linux_pte(pgdir, ea);
	if (ptep == NULL || !pte_present(*ptep)) {
		DBG_LOW(" no PTE !\n");
		return 1;
	}

#ifndef CONFIG_PPC_64K_PAGES
	DBG_LOW(" i-pte: %016lx\n", pte_val(*ptep));
#else
	DBG_LOW(" i-pte: %016lx %016lx\n", pte_val(*ptep),
		pte_val(*(ptep + PTRS_PER_PTE)));
#endif
	/* Pre-check access permissions (will be re-checked atomically
	 * in __hash_page_XX but this pre-check is a fast path
	 */
	if (access & ~pte_val(*ptep)) {
		DBG_LOW(" no access !\n");
		return 1;
	}

	/* Do actual hashing */
#ifdef CONFIG_PPC_64K_PAGES
	/* If _PAGE_4K_PFN is set, make sure this is a 4k segment */
	if (pte_val(*ptep) & _PAGE_4K_PFN) {
		demote_segment_4k(mm, ea);
		psize = MMU_PAGE_4K;
	}

	/* If this PTE is non-cacheable and we have restrictions on
	 * using non cacheable large pages, then we switch to 4k
	 */
	if (mmu_ci_restrictions && psize == MMU_PAGE_64K &&
	    (pte_val(*ptep) & _PAGE_NO_CACHE)) {
		if (user_region) {
			demote_segment_4k(mm, ea);
			psize = MMU_PAGE_4K;
		} else if (ea < VMALLOC_END) {
			/*
			 * some driver did a non-cacheable mapping
			 * in vmalloc space, so switch vmalloc
			 * to 4k pages
			 */
			printk(KERN_ALERT "Reducing vmalloc segment "
			       "to 4kB pages because of "
			       "non-cacheable mapping\n");
			psize = mmu_vmalloc_psize = MMU_PAGE_4K;
#ifdef CONFIG_SPU_BASE
			spu_flush_all_slbs(mm);
#endif
		}
	}
	if (user_region) {
		if (psize != get_paca()->context.user_psize) {
			get_paca()->context = mm->context;
			slb_flush_and_rebolt();
		}
	} else if (get_paca()->vmalloc_sllp !=
		   mmu_psize_defs[mmu_vmalloc_psize].sllp) {
		get_paca()->vmalloc_sllp =
			mmu_psize_defs[mmu_vmalloc_psize].sllp;
		slb_vmalloc_update();
	}
#endif /* CONFIG_PPC_64K_PAGES */

#ifdef CONFIG_PPC_HAS_HASH_64K
	if (psize == MMU_PAGE_64K)
		rc = __hash_page_64K(ea, access, vsid, ptep, trap, local, ssize);
	else
#endif /* CONFIG_PPC_HAS_HASH_64K */
	{
		int spp = subpage_protection(pgdir, ea);
		if (access & spp)
			rc = -2;
		else
			rc = __hash_page_4K(ea, access, vsid, ptep, trap,
					    local, ssize, spp);
	}

#ifndef CONFIG_PPC_64K_PAGES
	DBG_LOW(" o-pte: %016lx\n", pte_val(*ptep));
#else
	DBG_LOW(" o-pte: %016lx %016lx\n", pte_val(*ptep),
		pte_val(*(ptep + PTRS_PER_PTE)));
#endif
	DBG_LOW(" -> rc=%d\n", rc);
	return rc;
}
EXPORT_SYMBOL_GPL(hash_page);

void hash_preload(struct mm_struct *mm, unsigned long ea,
		  unsigned long access, unsigned long trap)
{
	unsigned long vsid;
	void *pgdir;
	pte_t *ptep;
	cpumask_t mask;
	unsigned long flags;
	int local = 0;
	int ssize;

	BUG_ON(REGION_ID(ea) != USER_REGION_ID);

#ifdef CONFIG_PPC_MM_SLICES
	/* We only prefault standard pages for now */
	if (unlikely(get_slice_psize(mm, ea) != mm->context.user_psize))
		return;
#endif

	DBG_LOW("hash_preload(mm=%p, mm->pgdir=%p, ea=%016lx, access=%lx,"
		" trap=%lx\n", mm, mm->pgd, ea, access, trap);

	/* Get Linux PTE if available */
	pgdir = mm->pgd;
	if (pgdir == NULL)
		return;
	ptep = find_linux_pte(pgdir, ea);
	if (!ptep)
		return;

#ifdef CONFIG_PPC_64K_PAGES
	/* If either _PAGE_4K_PFN or _PAGE_NO_CACHE is set (and we are on
	 * a 64K kernel), then we don't preload, hash_page() will take
	 * care of it once we actually try to access the page.
	 * That way we don't have to duplicate all of the logic for segment
	 * page size demotion here
	 */
	if (pte_val(*ptep) & (_PAGE_4K_PFN | _PAGE_NO_CACHE))
		return;
#endif /* CONFIG_PPC_64K_PAGES */

	/* Get VSID */
	ssize = user_segment_size(ea);
	vsid = get_vsid(mm->context.id, ea, ssize);

	/* Hash doesn't like irqs */
	local_irq_save(flags);

	/* Is that local to this CPU ? */
	mask = cpumask_of_cpu(smp_processor_id());
	if (cpus_equal(mm->cpu_vm_mask, mask))
		local = 1;

	/* Hash it in */
#ifdef CONFIG_PPC_HAS_HASH_64K
	if (mm->context.user_psize == MMU_PAGE_64K)
		__hash_page_64K(ea, access, vsid, ptep, trap, local, ssize);
	else
#endif /* CONFIG_PPC_HAS_HASH_64K */
		__hash_page_4K(ea, access, vsid, ptep, trap, local, ssize,
			       subpage_protection(pgdir, ea));

	local_irq_restore(flags);
}

/* WARNING: This is called from hash_low_64.S, if you change this prototype,
 *          do not forget to update the assembly call site !
 */
void flush_hash_page(unsigned long va, real_pte_t pte, int psize, int ssize,
		     int local)
{
	unsigned long hash, index, shift, hidx, slot;

	DBG_LOW("flush_hash_page(va=%016x)\n", va);
	pte_iterate_hashed_subpages(pte, psize, va, index, shift) {
		hash = hpt_hash(va, shift, ssize);
		hidx = __rpte_to_hidx(pte, index);
		if (hidx & _PTEIDX_SECONDARY)
			hash = ~hash;
		slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
		slot += hidx & _PTEIDX_GROUP_IX;
		DBG_LOW(" sub %d: hash=%x, hidx=%x\n", index, slot, hidx);
		ppc_md.hpte_invalidate(slot, va, psize, ssize, local);
	} pte_iterate_hashed_end();
}

void flush_hash_range(unsigned long number, int local)
{
	if (ppc_md.flush_hash_range)
		ppc_md.flush_hash_range(number, local);
	else {
		int i;
		struct ppc64_tlb_batch *batch =
			&__get_cpu_var(ppc64_tlb_batch);

		for (i = 0; i < number; i++)
			flush_hash_page(batch->vaddr[i], batch->pte[i],
					batch->psize, batch->ssize, local);
	}
}

/*
 * low_hash_fault is called when we the low level hash code failed
 * to instert a PTE due to an hypervisor error
 */
void low_hash_fault(struct pt_regs *regs, unsigned long address, int rc)
{
	if (user_mode(regs)) {
#ifdef CONFIG_PPC_SUBPAGE_PROT
		if (rc == -2)
			_exception(SIGSEGV, regs, SEGV_ACCERR, address);
		else
#endif
			_exception(SIGBUS, regs, BUS_ADRERR, address);
	} else
		bad_page_fault(regs, address, SIGBUS);
}

#ifdef CONFIG_DEBUG_PAGEALLOC
static void kernel_map_linear_page(unsigned long vaddr, unsigned long lmi)
{
	unsigned long hash, hpteg;
	unsigned long vsid = get_kernel_vsid(vaddr, mmu_kernel_ssize);
	unsigned long va = hpt_va(vaddr, vsid, mmu_kernel_ssize);
	unsigned long mode = _PAGE_ACCESSED | _PAGE_DIRTY |
		_PAGE_COHERENT | PP_RWXX | HPTE_R_N;
	int ret;

	hash = hpt_hash(va, PAGE_SHIFT, mmu_kernel_ssize);
	hpteg = ((hash & htab_hash_mask) * HPTES_PER_GROUP);

	ret = ppc_md.hpte_insert(hpteg, va, __pa(vaddr),
				 mode, HPTE_V_BOLTED,
				 mmu_linear_psize, mmu_kernel_ssize);
	BUG_ON (ret < 0);
	spin_lock(&linear_map_hash_lock);
	BUG_ON(linear_map_hash_slots[lmi] & 0x80);
	linear_map_hash_slots[lmi] = ret | 0x80;
	spin_unlock(&linear_map_hash_lock);
}

static void kernel_unmap_linear_page(unsigned long vaddr, unsigned long lmi)
{
	unsigned long hash, hidx, slot;
	unsigned long vsid = get_kernel_vsid(vaddr, mmu_kernel_ssize);
	unsigned long va = hpt_va(vaddr, vsid, mmu_kernel_ssize);

	hash = hpt_hash(va, PAGE_SHIFT, mmu_kernel_ssize);
	spin_lock(&linear_map_hash_lock);
	BUG_ON(!(linear_map_hash_slots[lmi] & 0x80));
	hidx = linear_map_hash_slots[lmi] & 0x7f;
	linear_map_hash_slots[lmi] = 0;
	spin_unlock(&linear_map_hash_lock);
	if (hidx & _PTEIDX_SECONDARY)
		hash = ~hash;
	slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
	slot += hidx & _PTEIDX_GROUP_IX;
	ppc_md.hpte_invalidate(slot, va, mmu_linear_psize, mmu_kernel_ssize, 0);
}

void kernel_map_pages(struct page *page, int numpages, int enable)
{
	unsigned long flags, vaddr, lmi;
	int i;

	local_irq_save(flags);
	for (i = 0; i < numpages; i++, page++) {
		vaddr = (unsigned long)page_address(page);
		lmi = __pa(vaddr) >> PAGE_SHIFT;
		if (lmi >= linear_map_hash_count)
			continue;
		if (enable)
			kernel_map_linear_page(vaddr, lmi);
		else
			kernel_unmap_linear_page(vaddr, lmi);
	}
	local_irq_restore(flags);
}
#endif /* CONFIG_DEBUG_PAGEALLOC */