forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathhash_utils_64.c
1868 lines (1634 loc) · 49.1 KB
/
hash_utils_64.c
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
/*
* PowerPC64 port by Mike Corrigan and Dave Engebretsen
* {mikejc|engebret}@us.ibm.com
*
* Copyright (c) 2000 Mike Corrigan <[email protected]>
*
* SMP scalability work:
* Copyright (C) 2001 Anton Blanchard <[email protected]>, 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
#define pr_fmt(fmt) "hash-mmu: " fmt
#include <linux/spinlock.h>
#include <linux/errno.h>
#include <linux/sched/mm.h>
#include <linux/proc_fs.h>
#include <linux/stat.h>
#include <linux/sysctl.h>
#include <linux/export.h>
#include <linux/ctype.h>
#include <linux/cache.h>
#include <linux/init.h>
#include <linux/signal.h>
#include <linux/memblock.h>
#include <linux/context_tracking.h>
#include <linux/libfdt.h>
#include <asm/debugfs.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 <linux/uaccess.h>
#include <asm/machdep.h>
#include <asm/prom.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/copro.h>
#include <asm/udbg.h>
#include <asm/code-patching.h>
#include <asm/fadump.h>
#include <asm/firmware.h>
#include <asm/tm.h>
#include <asm/trace.h>
#include <asm/ps3.h>
#include <asm/pte-walk.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)
#define GB (1024L*MB)
/*
* 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.
*
*/
static unsigned long _SDR1;
struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT];
EXPORT_SYMBOL_GPL(mmu_psize_defs);
u8 hpte_page_sizes[1 << LP_BITS];
EXPORT_SYMBOL_GPL(hpte_page_sizes);
struct hash_pte *htab_address;
unsigned long htab_size_bytes;
unsigned long htab_hash_mask;
EXPORT_SYMBOL_GPL(htab_hash_mask);
int mmu_linear_psize = MMU_PAGE_4K;
EXPORT_SYMBOL_GPL(mmu_linear_psize);
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;
EXPORT_SYMBOL_GPL(mmu_kernel_ssize);
int mmu_highuser_ssize = MMU_SEGSIZE_256M;
u16 mmu_slb_size = 64;
EXPORT_SYMBOL_GPL(mmu_slb_size);
#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 */
struct mmu_hash_ops mmu_hash_ops;
EXPORT_SYMBOL(mmu_hash_ops);
/* There are definitions of page sizes arrays to be used when none
* is provided by the firmware.
*/
/* Pre-POWER4 CPUs (4k pages only)
*/
static struct mmu_psize_def mmu_psize_defaults_old[] = {
[MMU_PAGE_4K] = {
.shift = 12,
.sllp = 0,
.penc = {[MMU_PAGE_4K] = 0, [1 ... MMU_PAGE_COUNT - 1] = -1},
.avpnm = 0,
.tlbiel = 0,
},
};
/* POWER4, GPUL, POWER5
*
* Support for 16Mb large pages
*/
static struct mmu_psize_def mmu_psize_defaults_gp[] = {
[MMU_PAGE_4K] = {
.shift = 12,
.sllp = 0,
.penc = {[MMU_PAGE_4K] = 0, [1 ... MMU_PAGE_COUNT - 1] = -1},
.avpnm = 0,
.tlbiel = 1,
},
[MMU_PAGE_16M] = {
.shift = 24,
.sllp = SLB_VSID_L,
.penc = {[0 ... MMU_PAGE_16M - 1] = -1, [MMU_PAGE_16M] = 0,
[MMU_PAGE_16M + 1 ... MMU_PAGE_COUNT - 1] = -1 },
.avpnm = 0x1UL,
.tlbiel = 0,
},
};
/*
* 'R' and 'C' update notes:
* - Under pHyp or KVM, the updatepp path will not set C, thus it *will*
* create writeable HPTEs without C set, because the hcall H_PROTECT
* that we use in that case will not update C
* - The above is however not a problem, because we also don't do that
* fancy "no flush" variant of eviction and we use H_REMOVE which will
* do the right thing and thus we don't have the race I described earlier
*
* - Under bare metal, we do have the race, so we need R and C set
* - We make sure R is always set and never lost
* - C is _PAGE_DIRTY, and *should* always be set for a writeable mapping
*/
unsigned long htab_convert_pte_flags(unsigned long pteflags)
{
unsigned long rflags = 0;
/* _PAGE_EXEC -> NOEXEC */
if ((pteflags & _PAGE_EXEC) == 0)
rflags |= HPTE_R_N;
/*
* PPP bits:
* Linux uses slb key 0 for kernel and 1 for user.
* kernel RW areas are mapped with PPP=0b000
* User area is mapped with PPP=0b010 for read/write
* or PPP=0b011 for read-only (including writeable but clean pages).
*/
if (pteflags & _PAGE_PRIVILEGED) {
/*
* Kernel read only mapped with ppp bits 0b110
*/
if (!(pteflags & _PAGE_WRITE)) {
if (mmu_has_feature(MMU_FTR_KERNEL_RO))
rflags |= (HPTE_R_PP0 | 0x2);
else
rflags |= 0x3;
}
} else {
if (pteflags & _PAGE_RWX)
rflags |= 0x2;
if (!((pteflags & _PAGE_WRITE) && (pteflags & _PAGE_DIRTY)))
rflags |= 0x1;
}
/*
* We can't allow hardware to update hpte bits. Hence always
* set 'R' bit and set 'C' if it is a write fault
*/
rflags |= HPTE_R_R;
if (pteflags & _PAGE_DIRTY)
rflags |= HPTE_R_C;
/*
* Add in WIG bits
*/
if ((pteflags & _PAGE_CACHE_CTL) == _PAGE_TOLERANT)
rflags |= HPTE_R_I;
else if ((pteflags & _PAGE_CACHE_CTL) == _PAGE_NON_IDEMPOTENT)
rflags |= (HPTE_R_I | HPTE_R_G);
else if ((pteflags & _PAGE_CACHE_CTL) == _PAGE_SAO)
rflags |= (HPTE_R_W | HPTE_R_I | HPTE_R_M);
else
/*
* Add memory coherence if cache inhibited is not set
*/
rflags |= HPTE_R_M;
return rflags;
}
int htab_bolt_mapping(unsigned long vstart, unsigned long vend,
unsigned long pstart, unsigned long prot,
int psize, int ssize)
{
unsigned long vaddr, paddr;
unsigned int step, shift;
int ret = 0;
shift = mmu_psize_defs[psize].shift;
step = 1 << shift;
prot = htab_convert_pte_flags(prot);
DBG("htab_bolt_mapping(%lx..%lx -> %lx (%lx,%d,%d)\n",
vstart, vend, pstart, prot, psize, ssize);
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 vpn = hpt_vpn(vaddr, vsid, ssize);
unsigned long tprot = prot;
/*
* If we hit a bad address return error.
*/
if (!vsid)
return -1;
/* Make kernel text executable */
if (overlaps_kernel_text(vaddr, vaddr + step))
tprot &= ~HPTE_R_N;
/* Make kvm guest trampolines executable */
if (overlaps_kvm_tmp(vaddr, vaddr + step))
tprot &= ~HPTE_R_N;
/*
* If relocatable, check if it overlaps interrupt vectors that
* are copied down to real 0. For relocatable kernel
* (e.g. kdump case) we copy interrupt vectors down to real
* address 0. Mark that region as executable. This is
* because on p8 system with relocation on exception feature
* enabled, exceptions are raised with MMU (IR=DR=1) ON. Hence
* in order to execute the interrupt handlers in virtual
* mode the vector region need to be marked as executable.
*/
if ((PHYSICAL_START > MEMORY_START) &&
overlaps_interrupt_vector_text(vaddr, vaddr + step))
tprot &= ~HPTE_R_N;
hash = hpt_hash(vpn, shift, ssize);
hpteg = ((hash & htab_hash_mask) * HPTES_PER_GROUP);
BUG_ON(!mmu_hash_ops.hpte_insert);
ret = mmu_hash_ops.hpte_insert(hpteg, vpn, paddr, tprot,
HPTE_V_BOLTED, psize, psize,
ssize);
if (ret < 0)
break;
#ifdef CONFIG_DEBUG_PAGEALLOC
if (debug_pagealloc_enabled() &&
(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;
}
int htab_remove_mapping(unsigned long vstart, unsigned long vend,
int psize, int ssize)
{
unsigned long vaddr;
unsigned int step, shift;
int rc;
int ret = 0;
shift = mmu_psize_defs[psize].shift;
step = 1 << shift;
if (!mmu_hash_ops.hpte_removebolted)
return -ENODEV;
for (vaddr = vstart; vaddr < vend; vaddr += step) {
rc = mmu_hash_ops.hpte_removebolted(vaddr, psize, ssize);
if (rc == -ENOENT) {
ret = -ENOENT;
continue;
}
if (rc < 0)
return rc;
}
return ret;
}
static bool disable_1tb_segments = false;
static int __init parse_disable_1tb_segments(char *p)
{
disable_1tb_segments = true;
return 0;
}
early_param("disable_1tb_segments", parse_disable_1tb_segments);
static int __init htab_dt_scan_seg_sizes(unsigned long node,
const char *uname, int depth,
void *data)
{
const char *type = of_get_flat_dt_prop(node, "device_type", NULL);
const __be32 *prop;
int size = 0;
/* We are scanning "cpu" nodes only */
if (type == NULL || strcmp(type, "cpu") != 0)
return 0;
prop = of_get_flat_dt_prop(node, "ibm,processor-segment-sizes", &size);
if (prop == NULL)
return 0;
for (; size >= 4; size -= 4, ++prop) {
if (be32_to_cpu(prop[0]) == 40) {
DBG("1T segment support detected\n");
if (disable_1tb_segments) {
DBG("1T segments disabled by command line\n");
break;
}
cur_cpu_spec->mmu_features |= MMU_FTR_1T_SEGMENT;
return 1;
}
}
cur_cpu_spec->mmu_features &= ~MMU_FTR_NO_SLBIE_B;
return 0;
}
static int __init get_idx_from_shift(unsigned int shift)
{
int idx = -1;
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;
break;
case 0x22:
idx = MMU_PAGE_16G;
break;
}
return idx;
}
static int __init htab_dt_scan_page_sizes(unsigned long node,
const char *uname, int depth,
void *data)
{
const char *type = of_get_flat_dt_prop(node, "device_type", NULL);
const __be32 *prop;
int size = 0;
/* We are scanning "cpu" nodes only */
if (type == NULL || strcmp(type, "cpu") != 0)
return 0;
prop = of_get_flat_dt_prop(node, "ibm,segment-page-sizes", &size);
if (!prop)
return 0;
pr_info("Page sizes from device-tree:\n");
size /= 4;
cur_cpu_spec->mmu_features &= ~(MMU_FTR_16M_PAGE);
while(size > 0) {
unsigned int base_shift = be32_to_cpu(prop[0]);
unsigned int slbenc = be32_to_cpu(prop[1]);
unsigned int lpnum = be32_to_cpu(prop[2]);
struct mmu_psize_def *def;
int idx, base_idx;
size -= 3; prop += 3;
base_idx = get_idx_from_shift(base_shift);
if (base_idx < 0) {
/* skip the pte encoding also */
prop += lpnum * 2; size -= lpnum * 2;
continue;
}
def = &mmu_psize_defs[base_idx];
if (base_idx == MMU_PAGE_16M)
cur_cpu_spec->mmu_features |= MMU_FTR_16M_PAGE;
def->shift = base_shift;
if (base_shift <= 23)
def->avpnm = 0;
else
def->avpnm = (1 << (base_shift - 23)) - 1;
def->sllp = slbenc;
/*
* We don't know for sure what's up with tlbiel, so
* for now we only set it for 4K and 64K pages
*/
if (base_idx == MMU_PAGE_4K || base_idx == MMU_PAGE_64K)
def->tlbiel = 1;
else
def->tlbiel = 0;
while (size > 0 && lpnum) {
unsigned int shift = be32_to_cpu(prop[0]);
int penc = be32_to_cpu(prop[1]);
prop += 2; size -= 2;
lpnum--;
idx = get_idx_from_shift(shift);
if (idx < 0)
continue;
if (penc == -1)
pr_err("Invalid penc for base_shift=%d "
"shift=%d\n", base_shift, shift);
def->penc[idx] = penc;
pr_info("base_shift=%d: shift=%d, sllp=0x%04lx,"
" avpnm=0x%08lx, tlbiel=%d, penc=%d\n",
base_shift, shift, def->sllp,
def->avpnm, def->tlbiel, def->penc[idx]);
}
}
return 1;
}
#ifdef CONFIG_HUGETLB_PAGE
/* Scan for 16G memory blocks that have been set aside for huge pages
* and reserve those blocks for 16G huge pages.
*/
static int __init htab_dt_scan_hugepage_blocks(unsigned long node,
const char *uname, int depth,
void *data) {
const char *type = of_get_flat_dt_prop(node, "device_type", NULL);
const __be64 *addr_prop;
const __be32 *page_count_prop;
unsigned int expected_pages;
long unsigned int phys_addr;
long unsigned int block_size;
/* We are scanning "memory" nodes only */
if (type == NULL || strcmp(type, "memory") != 0)
return 0;
/* This property is the log base 2 of the number of virtual pages that
* will represent this memory block. */
page_count_prop = of_get_flat_dt_prop(node, "ibm,expected#pages", NULL);
if (page_count_prop == NULL)
return 0;
expected_pages = (1 << be32_to_cpu(page_count_prop[0]));
addr_prop = of_get_flat_dt_prop(node, "reg", NULL);
if (addr_prop == NULL)
return 0;
phys_addr = be64_to_cpu(addr_prop[0]);
block_size = be64_to_cpu(addr_prop[1]);
if (block_size != (16 * GB))
return 0;
printk(KERN_INFO "Huge page(16GB) memory: "
"addr = 0x%lX size = 0x%lX pages = %d\n",
phys_addr, block_size, expected_pages);
if (phys_addr + block_size * expected_pages <= memblock_end_of_DRAM()) {
memblock_reserve(phys_addr, block_size * expected_pages);
pseries_add_gpage(phys_addr, block_size, expected_pages);
}
return 0;
}
#endif /* CONFIG_HUGETLB_PAGE */
static void mmu_psize_set_default_penc(void)
{
int bpsize, apsize;
for (bpsize = 0; bpsize < MMU_PAGE_COUNT; bpsize++)
for (apsize = 0; apsize < MMU_PAGE_COUNT; apsize++)
mmu_psize_defs[bpsize].penc[apsize] = -1;
}
#ifdef CONFIG_PPC_64K_PAGES
static bool might_have_hea(void)
{
/*
* The HEA ethernet adapter requires awareness of the
* GX bus. Without that awareness we can easily assume
* we will never see an HEA ethernet device.
*/
#ifdef CONFIG_IBMEBUS
return !cpu_has_feature(CPU_FTR_ARCH_207S) &&
firmware_has_feature(FW_FEATURE_SPLPAR);
#else
return false;
#endif
}
#endif /* #ifdef CONFIG_PPC_64K_PAGES */
static void __init htab_scan_page_sizes(void)
{
int rc;
/* se the invalid penc to -1 */
mmu_psize_set_default_penc();
/* 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 && early_mmu_has_feature(MMU_FTR_16M_PAGE)) {
/*
* Nothing in the device-tree, but the CPU supports 16M pages,
* so let's fallback on a known size list for 16M capable CPUs.
*/
memcpy(mmu_psize_defs, mmu_psize_defaults_gp,
sizeof(mmu_psize_defaults_gp));
}
#ifdef CONFIG_HUGETLB_PAGE
/* Reserve 16G huge page memory sections for huge pages */
of_scan_flat_dt(htab_dt_scan_hugepage_blocks, NULL);
#endif /* CONFIG_HUGETLB_PAGE */
}
/*
* Fill in the hpte_page_sizes[] array.
* We go through the mmu_psize_defs[] array looking for all the
* supported base/actual page size combinations. Each combination
* has a unique pagesize encoding (penc) value in the low bits of
* the LP field of the HPTE. For actual page sizes less than 1MB,
* some of the upper LP bits are used for RPN bits, meaning that
* we need to fill in several entries in hpte_page_sizes[].
*
* In diagrammatic form, with r = RPN bits and z = page size bits:
* PTE LP actual page size
* rrrr rrrz >=8KB
* rrrr rrzz >=16KB
* rrrr rzzz >=32KB
* rrrr zzzz >=64KB
* ...
*
* The zzzz bits are implementation-specific but are chosen so that
* no encoding for a larger page size uses the same value in its
* low-order N bits as the encoding for the 2^(12+N) byte page size
* (if it exists).
*/
static void init_hpte_page_sizes(void)
{
long int ap, bp;
long int shift, penc;
for (bp = 0; bp < MMU_PAGE_COUNT; ++bp) {
if (!mmu_psize_defs[bp].shift)
continue; /* not a supported page size */
for (ap = bp; ap < MMU_PAGE_COUNT; ++ap) {
penc = mmu_psize_defs[bp].penc[ap];
if (penc == -1)
continue;
shift = mmu_psize_defs[ap].shift - LP_SHIFT;
if (shift <= 0)
continue; /* should never happen */
/*
* For page sizes less than 1MB, this loop
* replicates the entry for all possible values
* of the rrrr bits.
*/
while (penc < (1 << LP_BITS)) {
hpte_page_sizes[penc] = (ap << 4) | bp;
penc += 1 << shift;
}
}
}
}
static void __init htab_init_page_sizes(void)
{
init_hpte_page_sizes();
if (!debug_pagealloc_enabled()) {
/*
* 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;
}
#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 (mmu_has_feature(MMU_FTR_CI_LARGE_PAGE)) {
/*
* When running on pSeries using 64k pages for ioremap
* would stop us accessing the HEA ethernet. So if we
* have the chance of ever seeing one, stay at 4k.
*/
if (!might_have_hea())
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 &&
memblock_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
);
}
static int __init htab_dt_scan_pftsize(unsigned long node,
const char *uname, int depth,
void *data)
{
const char *type = of_get_flat_dt_prop(node, "device_type", NULL);
const __be32 *prop;
/* We are scanning "cpu" nodes only */
if (type == NULL || strcmp(type, "cpu") != 0)
return 0;
prop = of_get_flat_dt_prop(node, "ibm,pft-size", NULL);
if (prop != NULL) {
/* pft_size[0] is the NUMA CEC cookie */
ppc64_pft_size = be32_to_cpu(prop[1]);
return 1;
}
return 0;
}
unsigned htab_shift_for_mem_size(unsigned long mem_size)
{
unsigned memshift = __ilog2(mem_size);
unsigned pshift = mmu_psize_defs[mmu_virtual_psize].shift;
unsigned pteg_shift;
/* round mem_size up to next power of 2 */
if ((1UL << memshift) < mem_size)
memshift += 1;
/* aim for 2 pages / pteg */
pteg_shift = memshift - (pshift + 1);
/*
* 2^11 PTEGS of 128 bytes each, ie. 2^18 bytes is the minimum htab
* size permitted by the architecture.
*/
return max(pteg_shift + 7, 18U);
}
static unsigned long __init htab_get_table_size(void)
{
/* 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;
return 1UL << htab_shift_for_mem_size(memblock_phys_mem_size());
}
#ifdef CONFIG_MEMORY_HOTPLUG
void resize_hpt_for_hotplug(unsigned long new_mem_size)
{
unsigned target_hpt_shift;
if (!mmu_hash_ops.resize_hpt)
return;
target_hpt_shift = htab_shift_for_mem_size(new_mem_size);
/*
* To avoid lots of HPT resizes if memory size is fluctuating
* across a boundary, we deliberately have some hysterisis
* here: we immediately increase the HPT size if the target
* shift exceeds the current shift, but we won't attempt to
* reduce unless the target shift is at least 2 below the
* current shift
*/
if ((target_hpt_shift > ppc64_pft_size)
|| (target_hpt_shift < (ppc64_pft_size - 1))) {
int rc;
rc = mmu_hash_ops.resize_hpt(target_hpt_shift);
if (rc)
printk(KERN_WARNING
"Unable to resize hash page table to target order %d: %d\n",
target_hpt_shift, rc);
}
}
int hash__create_section_mapping(unsigned long start, unsigned long end)
{
int rc = htab_bolt_mapping(start, end, __pa(start),
pgprot_val(PAGE_KERNEL), mmu_linear_psize,
mmu_kernel_ssize);
if (rc < 0) {
int rc2 = htab_remove_mapping(start, end, mmu_linear_psize,
mmu_kernel_ssize);
BUG_ON(rc2 && (rc2 != -ENOENT));
}
return rc;
}
int hash__remove_section_mapping(unsigned long start, unsigned long end)
{
int rc = htab_remove_mapping(start, end, mmu_linear_psize,
mmu_kernel_ssize);
WARN_ON(rc < 0);
return rc;
}
#endif /* CONFIG_MEMORY_HOTPLUG */
static void update_hid_for_hash(void)
{
unsigned long hid0;
unsigned long rb = 3UL << PPC_BITLSHIFT(53); /* IS = 3 */
asm volatile("ptesync": : :"memory");
/* prs = 0, ric = 2, rs = 0, r = 1 is = 3 */
asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1)
: : "r"(rb), "i"(0), "i"(0), "i"(2), "r"(0) : "memory");
asm volatile("eieio; tlbsync; ptesync; isync; slbia": : :"memory");
trace_tlbie(0, 0, rb, 0, 2, 0, 0);
/*
* now switch the HID
*/
hid0 = mfspr(SPRN_HID0);
hid0 &= ~HID0_POWER9_RADIX;
mtspr(SPRN_HID0, hid0);
asm volatile("isync": : :"memory");
/* Wait for it to happen */
while ((mfspr(SPRN_HID0) & HID0_POWER9_RADIX))
cpu_relax();
}
static void __init hash_init_partition_table(phys_addr_t hash_table,
unsigned long htab_size)
{
mmu_partition_table_init();
/*
* PS field (VRMA page size) is not used for LPID 0, hence set to 0.
* For now, UPRT is 0 and we have no segment table.
*/
htab_size = __ilog2(htab_size) - 18;
mmu_partition_table_set_entry(0, hash_table | htab_size, 0);
pr_info("Partition table %p\n", partition_tb);
if (cpu_has_feature(CPU_FTR_POWER9_DD1))
update_hid_for_hash();
}
static void __init htab_initialize(void)
{
unsigned long table;
unsigned long pteg_count;
unsigned long prot;
unsigned long base = 0, size = 0;
struct memblock_region *reg;
DBG(" -> htab_initialize()\n");
if (mmu_has_feature(MMU_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) ||
firmware_has_feature(FW_FEATURE_PS3_LV1)) {
/* Using a hypervisor which owns the htab */
htab_address = NULL;
_SDR1 = 0;
#ifdef CONFIG_FA_DUMP
/*
* If firmware assisted dump is active firmware preserves
* the contents of htab along with entire partition memory.
* Clear the htab if firmware assisted dump is active so
* that we dont end up using old mappings.
*/
if (is_fadump_active() && mmu_hash_ops.hpte_clear_all)
mmu_hash_ops.hpte_clear_all();
#endif
} else {
unsigned long limit = MEMBLOCK_ALLOC_ANYWHERE;
#ifdef CONFIG_PPC_CELL
/*
* Cell may require the hash table down low when using the
* Axon IOMMU in order to fit the dynamic region over it, see
* comments in cell/iommu.c
*/
if (fdt_subnode_offset(initial_boot_params, 0, "axon") > 0) {
limit = 0x80000000;
pr_info("Hash table forced below 2G for Axon IOMMU\n");
}
#endif /* CONFIG_PPC_CELL */
table = memblock_alloc_base(htab_size_bytes, htab_size_bytes,
limit);
DBG("Hash table allocated at %lx, size: %lx\n", table,
htab_size_bytes);
htab_address = __va(table);
/* htab absolute addr + encoded htabsize */
_SDR1 = table + __ilog2(htab_size_bytes) - 18;
/* Initialize the HPT with no entries */
memset((void *)table, 0, htab_size_bytes);
if (!cpu_has_feature(CPU_FTR_ARCH_300))
/* Set SDR1 */
mtspr(SPRN_SDR1, _SDR1);
else
hash_init_partition_table(table, htab_size_bytes);
}
prot = pgprot_val(PAGE_KERNEL);
#ifdef CONFIG_DEBUG_PAGEALLOC
if (debug_pagealloc_enabled()) {
linear_map_hash_count = memblock_end_of_DRAM() >> PAGE_SHIFT;
linear_map_hash_slots = __va(memblock_alloc_base(
linear_map_hash_count, 1, ppc64_rma_size));
memset(linear_map_hash_slots, 0, linear_map_hash_count);
}
#endif /* CONFIG_DEBUG_PAGEALLOC */
/* create bolted the linear mapping in the hash table */
for_each_memblock(memory, reg) {
base = (unsigned long)__va(reg->base);
size = reg->size;
DBG("creating mapping for region: %lx..%lx (prot: %lx)\n",
base, size, prot);
BUG_ON(htab_bolt_mapping(base, base + size, __pa(base),
prot, mmu_linear_psize, mmu_kernel_ssize));
}
memblock_set_current_limit(MEMBLOCK_ALLOC_ANYWHERE);
/*
* 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), prot,
mmu_linear_psize, mmu_kernel_ssize));
}
DBG(" <- htab_initialize()\n");
}
#undef KB
#undef MB
void __init hash__early_init_devtree(void)
{
/* Initialize segment sizes */
of_scan_flat_dt(htab_dt_scan_seg_sizes, NULL);
/* Initialize page sizes */
htab_scan_page_sizes();
}
void __init hash__early_init_mmu(void)
{
/*
* We have code in __hash_page_64K() and elsewhere, which assumes it can
* do the following:
* new_pte |= (slot << H_PAGE_F_GIX_SHIFT) & (H_PAGE_F_SECOND | H_PAGE_F_GIX);
*
* Where the slot number is between 0-15, and values of 8-15 indicate
* the secondary bucket. For that code to work H_PAGE_F_SECOND and
* H_PAGE_F_GIX must occupy four contiguous bits in the PTE, and
* H_PAGE_F_SECOND must be placed above H_PAGE_F_GIX. Assert that here
* with a BUILD_BUG_ON().
*/
BUILD_BUG_ON(H_PAGE_F_SECOND != (1ul << (H_PAGE_F_GIX_SHIFT + 3)));
htab_init_page_sizes();
/*
* initialize page table size
*/
__pte_frag_nr = H_PTE_FRAG_NR;