summaryrefslogtreecommitdiff
path: root/arch/powerpc/mm/hash_native_64.c
blob: 3848af167df9de4b183d7cb8472b5d20ce97d0a4 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
/*
 * native hashtable management.
 *
 * SMP scalability work:
 *    Copyright (C) 2001 Anton Blanchard <anton@au.ibm.com>, IBM
 * 
 * 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_LOW

#include <linux/spinlock.h>
#include <linux/bitops.h>
#include <linux/of.h>
#include <linux/processor.h>
#include <linux/threads.h>
#include <linux/smp.h>

#include <asm/machdep.h>
#include <asm/mmu.h>
#include <asm/mmu_context.h>
#include <asm/pgtable.h>
#include <asm/tlbflush.h>
#include <asm/trace.h>
#include <asm/tlb.h>
#include <asm/cputable.h>
#include <asm/udbg.h>
#include <asm/kexec.h>
#include <asm/ppc-opcode.h>

#include <misc/cxl-base.h>

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

#ifdef __BIG_ENDIAN__
#define HPTE_LOCK_BIT 3
#else
#define HPTE_LOCK_BIT (56+3)
#endif

DEFINE_RAW_SPINLOCK(native_tlbie_lock);

static inline void __tlbie(unsigned long vpn, int psize, int apsize, int ssize)
{
	unsigned long va;
	unsigned int penc;
	unsigned long sllp;

	/*
	 * We need 14 to 65 bits of va for a tlibe of 4K page
	 * With vpn we ignore the lower VPN_SHIFT bits already.
	 * And top two bits are already ignored because we can
	 * only accomodate 76 bits in a 64 bit vpn with a VPN_SHIFT
	 * of 12.
	 */
	va = vpn << VPN_SHIFT;
	/*
	 * clear top 16 bits of 64bit va, non SLS segment
	 * Older versions of the architecture (2.02 and earler) require the
	 * masking of the top 16 bits.
	 */
	if (mmu_has_feature(MMU_FTR_TLBIE_CROP_VA))
		va &= ~(0xffffULL << 48);

	switch (psize) {
	case MMU_PAGE_4K:
		/* clear out bits after (52) [0....52.....63] */
		va &= ~((1ul << (64 - 52)) - 1);
		va |= ssize << 8;
		sllp = get_sllp_encoding(apsize);
		va |= sllp << 5;
		asm volatile(ASM_FTR_IFCLR("tlbie %0,0", PPC_TLBIE(%1,%0), %2)
			     : : "r" (va), "r"(0), "i" (CPU_FTR_ARCH_206)
			     : "memory");
		break;
	default:
		/* We need 14 to 14 + i bits of va */
		penc = mmu_psize_defs[psize].penc[apsize];
		va &= ~((1ul << mmu_psize_defs[apsize].shift) - 1);
		va |= penc << 12;
		va |= ssize << 8;
		/*
		 * AVAL bits:
		 * We don't need all the bits, but rest of the bits
		 * must be ignored by the processor.
		 * vpn cover upto 65 bits of va. (0...65) and we need
		 * 58..64 bits of va.
		 */
		va |= (vpn & 0xfe); /* AVAL */
		va |= 1; /* L */
		asm volatile(ASM_FTR_IFCLR("tlbie %0,1", PPC_TLBIE(%1,%0), %2)
			     : : "r" (va), "r"(0), "i" (CPU_FTR_ARCH_206)
			     : "memory");
		break;
	}
	trace_tlbie(0, 0, va, 0, 0, 0, 0);
}

static inline void __tlbiel(unsigned long vpn, int psize, int apsize, int ssize)
{
	unsigned long va;
	unsigned int penc;
	unsigned long sllp;

	/* VPN_SHIFT can be atmost 12 */
	va = vpn << VPN_SHIFT;
	/*
	 * clear top 16 bits of 64 bit va, non SLS segment
	 * Older versions of the architecture (2.02 and earler) require the
	 * masking of the top 16 bits.
	 */
	if (mmu_has_feature(MMU_FTR_TLBIE_CROP_VA))
		va &= ~(0xffffULL << 48);

	switch (psize) {
	case MMU_PAGE_4K:
		/* clear out bits after(52) [0....52.....63] */
		va &= ~((1ul << (64 - 52)) - 1);
		va |= ssize << 8;
		sllp = get_sllp_encoding(apsize);
		va |= sllp << 5;
		asm volatile(ASM_FTR_IFSET("tlbiel %0", "tlbiel %0,0", %1)
			     : : "r" (va), "i" (CPU_FTR_ARCH_206)
			     : "memory");
		break;
	default:
		/* We need 14 to 14 + i bits of va */
		penc = mmu_psize_defs[psize].penc[apsize];
		va &= ~((1ul << mmu_psize_defs[apsize].shift) - 1);
		va |= penc << 12;
		va |= ssize << 8;
		/*
		 * AVAL bits:
		 * We don't need all the bits, but rest of the bits
		 * must be ignored by the processor.
		 * vpn cover upto 65 bits of va. (0...65) and we need
		 * 58..64 bits of va.
		 */
		va |= (vpn & 0xfe);
		va |= 1; /* L */
		asm volatile(ASM_FTR_IFSET("tlbiel %0", "tlbiel %0,1", %1)
			     : : "r" (va), "i" (CPU_FTR_ARCH_206)
			     : "memory");
		break;
	}
	trace_tlbie(0, 1, va, 0, 0, 0, 0);

}

static inline void tlbie(unsigned long vpn, int psize, int apsize,
			 int ssize, int local)
{
	unsigned int use_local;
	int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE);

	use_local = local && mmu_has_feature(MMU_FTR_TLBIEL) && !cxl_ctx_in_use();

	if (use_local)
		use_local = mmu_psize_defs[psize].tlbiel;
	if (lock_tlbie && !use_local)
		raw_spin_lock(&native_tlbie_lock);
	asm volatile("ptesync": : :"memory");
	if (use_local) {
		__tlbiel(vpn, psize, apsize, ssize);
		asm volatile("ptesync": : :"memory");
	} else {
		__tlbie(vpn, psize, apsize, ssize);
		asm volatile("eieio; tlbsync; ptesync": : :"memory");
	}
	if (lock_tlbie && !use_local)
		raw_spin_unlock(&native_tlbie_lock);
}

static inline void native_lock_hpte(struct hash_pte *hptep)
{
	unsigned long *word = (unsigned long *)&hptep->v;

	while (1) {
		if (!test_and_set_bit_lock(HPTE_LOCK_BIT, word))
			break;
		spin_begin();
		while(test_bit(HPTE_LOCK_BIT, word))
			spin_cpu_relax();
		spin_end();
	}
}

static inline void native_unlock_hpte(struct hash_pte *hptep)
{
	unsigned long *word = (unsigned long *)&hptep->v;

	clear_bit_unlock(HPTE_LOCK_BIT, word);
}

static long native_hpte_insert(unsigned long hpte_group, unsigned long vpn,
			unsigned long pa, unsigned long rflags,
			unsigned long vflags, int psize, int apsize, int ssize)
{
	struct hash_pte *hptep = htab_address + hpte_group;
	unsigned long hpte_v, hpte_r;
	int i;

	if (!(vflags & HPTE_V_BOLTED)) {
		DBG_LOW("    insert(group=%lx, vpn=%016lx, pa=%016lx,"
			" rflags=%lx, vflags=%lx, psize=%d)\n",
			hpte_group, vpn, pa, rflags, vflags, psize);
	}

	for (i = 0; i < HPTES_PER_GROUP; i++) {
		if (! (be64_to_cpu(hptep->v) & HPTE_V_VALID)) {
			/* retry with lock held */
			native_lock_hpte(hptep);
			if (! (be64_to_cpu(hptep->v) & HPTE_V_VALID))
				break;
			native_unlock_hpte(hptep);
		}

		hptep++;
	}

	if (i == HPTES_PER_GROUP)
		return -1;

	hpte_v = hpte_encode_v(vpn, psize, apsize, ssize) | vflags | HPTE_V_VALID;
	hpte_r = hpte_encode_r(pa, psize, apsize) | rflags;

	if (!(vflags & HPTE_V_BOLTED)) {
		DBG_LOW(" i=%x hpte_v=%016lx, hpte_r=%016lx\n",
			i, hpte_v, hpte_r);
	}

	if (cpu_has_feature(CPU_FTR_ARCH_300)) {
		hpte_r = hpte_old_to_new_r(hpte_v, hpte_r);
		hpte_v = hpte_old_to_new_v(hpte_v);
	}

	hptep->r = cpu_to_be64(hpte_r);
	/* Guarantee the second dword is visible before the valid bit */
	eieio();
	/*
	 * Now set the first dword including the valid bit
	 * NOTE: this also unlocks the hpte
	 */
	hptep->v = cpu_to_be64(hpte_v);

	__asm__ __volatile__ ("ptesync" : : : "memory");

	return i | (!!(vflags & HPTE_V_SECONDARY) << 3);
}

static long native_hpte_remove(unsigned long hpte_group)
{
	struct hash_pte *hptep;
	int i;
	int slot_offset;
	unsigned long hpte_v;

	DBG_LOW("    remove(group=%lx)\n", hpte_group);

	/* pick a random entry to start at */
	slot_offset = mftb() & 0x7;

	for (i = 0; i < HPTES_PER_GROUP; i++) {
		hptep = htab_address + hpte_group + slot_offset;
		hpte_v = be64_to_cpu(hptep->v);

		if ((hpte_v & HPTE_V_VALID) && !(hpte_v & HPTE_V_BOLTED)) {
			/* retry with lock held */
			native_lock_hpte(hptep);
			hpte_v = be64_to_cpu(hptep->v);
			if ((hpte_v & HPTE_V_VALID)
			    && !(hpte_v & HPTE_V_BOLTED))
				break;
			native_unlock_hpte(hptep);
		}

		slot_offset++;
		slot_offset &= 0x7;
	}

	if (i == HPTES_PER_GROUP)
		return -1;

	/* Invalidate the hpte. NOTE: this also unlocks it */
	hptep->v = 0;

	return i;
}

static long native_hpte_updatepp(unsigned long slot, unsigned long newpp,
				 unsigned long vpn, int bpsize,
				 int apsize, int ssize, unsigned long flags)
{
	struct hash_pte *hptep = htab_address + slot;
	unsigned long hpte_v, want_v;
	int ret = 0, local = 0;

	want_v = hpte_encode_avpn(vpn, bpsize, ssize);

	DBG_LOW("    update(vpn=%016lx, avpnv=%016lx, group=%lx, newpp=%lx)",
		vpn, want_v & HPTE_V_AVPN, slot, newpp);

	hpte_v = be64_to_cpu(hptep->v);
	if (cpu_has_feature(CPU_FTR_ARCH_300))
		hpte_v = hpte_new_to_old_v(hpte_v, be64_to_cpu(hptep->r));
	/*
	 * We need to invalidate the TLB always because hpte_remove doesn't do
	 * a tlb invalidate. If a hash bucket gets full, we "evict" a more/less
	 * random entry from it. When we do that we don't invalidate the TLB
	 * (hpte_remove) because we assume the old translation is still
	 * technically "valid".
	 */
	if (!HPTE_V_COMPARE(hpte_v, want_v) || !(hpte_v & HPTE_V_VALID)) {
		DBG_LOW(" -> miss\n");
		ret = -1;
	} else {
		native_lock_hpte(hptep);
		/* recheck with locks held */
		hpte_v = be64_to_cpu(hptep->v);
		if (cpu_has_feature(CPU_FTR_ARCH_300))
			hpte_v = hpte_new_to_old_v(hpte_v, be64_to_cpu(hptep->r));
		if (unlikely(!HPTE_V_COMPARE(hpte_v, want_v) ||
			     !(hpte_v & HPTE_V_VALID))) {
			ret = -1;
		} else {
			DBG_LOW(" -> hit\n");
			/* Update the HPTE */
			hptep->r = cpu_to_be64((be64_to_cpu(hptep->r) &
						~(HPTE_R_PPP | HPTE_R_N)) |
					       (newpp & (HPTE_R_PPP | HPTE_R_N |
							 HPTE_R_C)));
		}
		native_unlock_hpte(hptep);
	}

	if (flags & HPTE_LOCAL_UPDATE)
		local = 1;
	/*
	 * Ensure it is out of the tlb too if it is not a nohpte fault
	 */
	if (!(flags & HPTE_NOHPTE_UPDATE))
		tlbie(vpn, bpsize, apsize, ssize, local);

	return ret;
}

static long native_hpte_find(unsigned long vpn, int psize, int ssize)
{
	struct hash_pte *hptep;
	unsigned long hash;
	unsigned long i;
	long slot;
	unsigned long want_v, hpte_v;

	hash = hpt_hash(vpn, mmu_psize_defs[psize].shift, ssize);
	want_v = hpte_encode_avpn(vpn, psize, ssize);

	/* Bolted mappings are only ever in the primary group */
	slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
	for (i = 0; i < HPTES_PER_GROUP; i++) {
		hptep = htab_address + slot;
		hpte_v = be64_to_cpu(hptep->v);
		if (cpu_has_feature(CPU_FTR_ARCH_300))
			hpte_v = hpte_new_to_old_v(hpte_v, be64_to_cpu(hptep->r));

		if (HPTE_V_COMPARE(hpte_v, want_v) && (hpte_v & HPTE_V_VALID))
			/* HPTE matches */
			return slot;
		++slot;
	}

	return -1;
}

/*
 * Update the page protection bits. Intended to be used to create
 * guard pages for kernel data structures on pages which are bolted
 * in the HPT. Assumes pages being operated on will not be stolen.
 *
 * No need to lock here because we should be the only user.
 */
static void native_hpte_updateboltedpp(unsigned long newpp, unsigned long ea,
				       int psize, int ssize)
{
	unsigned long vpn;
	unsigned long vsid;
	long slot;
	struct hash_pte *hptep;

	vsid = get_kernel_vsid(ea, ssize);
	vpn = hpt_vpn(ea, vsid, ssize);

	slot = native_hpte_find(vpn, psize, ssize);
	if (slot == -1)
		panic("could not find page to bolt\n");
	hptep = htab_address + slot;

	/* Update the HPTE */
	hptep->r = cpu_to_be64((be64_to_cpu(hptep->r) &
				~(HPTE_R_PPP | HPTE_R_N)) |
			       (newpp & (HPTE_R_PPP | HPTE_R_N)));
	/*
	 * Ensure it is out of the tlb too. Bolted entries base and
	 * actual page size will be same.
	 */
	tlbie(vpn, psize, psize, ssize, 0);
}

/*
 * Remove a bolted kernel entry. Memory hotplug uses this.
 *
 * No need to lock here because we should be the only user.
 */
static int native_hpte_removebolted(unsigned long ea, int psize, int ssize)
{
	unsigned long vpn;
	unsigned long vsid;
	long slot;
	struct hash_pte *hptep;

	vsid = get_kernel_vsid(ea, ssize);
	vpn = hpt_vpn(ea, vsid, ssize);

	slot = native_hpte_find(vpn, psize, ssize);
	if (slot == -1)
		return -ENOENT;

	hptep = htab_address + slot;

	VM_WARN_ON(!(be64_to_cpu(hptep->v) & HPTE_V_BOLTED));

	/* Invalidate the hpte */
	hptep->v = 0;

	/* Invalidate the TLB */
	tlbie(vpn, psize, psize, ssize, 0);
	return 0;
}


static void native_hpte_invalidate(unsigned long slot, unsigned long vpn,
				   int bpsize, int apsize, int ssize, int local)
{
	struct hash_pte *hptep = htab_address + slot;
	unsigned long hpte_v;
	unsigned long want_v;
	unsigned long flags;

	local_irq_save(flags);

	DBG_LOW("    invalidate(vpn=%016lx, hash: %lx)\n", vpn, slot);

	want_v = hpte_encode_avpn(vpn, bpsize, ssize);
	native_lock_hpte(hptep);
	hpte_v = be64_to_cpu(hptep->v);
	if (cpu_has_feature(CPU_FTR_ARCH_300))
		hpte_v = hpte_new_to_old_v(hpte_v, be64_to_cpu(hptep->r));

	/*
	 * We need to invalidate the TLB always because hpte_remove doesn't do
	 * a tlb invalidate. If a hash bucket gets full, we "evict" a more/less
	 * random entry from it. When we do that we don't invalidate the TLB
	 * (hpte_remove) because we assume the old translation is still
	 * technically "valid".
	 */
	if (!HPTE_V_COMPARE(hpte_v, want_v) || !(hpte_v & HPTE_V_VALID))
		native_unlock_hpte(hptep);
	else
		/* Invalidate the hpte. NOTE: this also unlocks it */
		hptep->v = 0;

	/* Invalidate the TLB */
	tlbie(vpn, bpsize, apsize, ssize, local);

	local_irq_restore(flags);
}

#ifdef CONFIG_TRANSPARENT_HUGEPAGE
static void native_hugepage_invalidate(unsigned long vsid,
				       unsigned long addr,
				       unsigned char *hpte_slot_array,
				       int psize, int ssize, int local)
{
	int i;
	struct hash_pte *hptep;
	int actual_psize = MMU_PAGE_16M;
	unsigned int max_hpte_count, valid;
	unsigned long flags, s_addr = addr;
	unsigned long hpte_v, want_v, shift;
	unsigned long hidx, vpn = 0, hash, slot;

	shift = mmu_psize_defs[psize].shift;
	max_hpte_count = 1U << (PMD_SHIFT - shift);

	local_irq_save(flags);
	for (i = 0; i < max_hpte_count; i++) {
		valid = hpte_valid(hpte_slot_array, i);
		if (!valid)
			continue;
		hidx =  hpte_hash_index(hpte_slot_array, i);

		/* get the vpn */
		addr = s_addr + (i * (1ul << shift));
		vpn = hpt_vpn(addr, vsid, ssize);
		hash = hpt_hash(vpn, shift, ssize);
		if (hidx & _PTEIDX_SECONDARY)
			hash = ~hash;

		slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
		slot += hidx & _PTEIDX_GROUP_IX;

		hptep = htab_address + slot;
		want_v = hpte_encode_avpn(vpn, psize, ssize);
		native_lock_hpte(hptep);
		hpte_v = be64_to_cpu(hptep->v);
		if (cpu_has_feature(CPU_FTR_ARCH_300))
			hpte_v = hpte_new_to_old_v(hpte_v, be64_to_cpu(hptep->r));

		/* Even if we miss, we need to invalidate the TLB */
		if (!HPTE_V_COMPARE(hpte_v, want_v) || !(hpte_v & HPTE_V_VALID))
			native_unlock_hpte(hptep);
		else
			/* Invalidate the hpte. NOTE: this also unlocks it */
			hptep->v = 0;
		/*
		 * We need to do tlb invalidate for all the address, tlbie
		 * instruction compares entry_VA in tlb with the VA specified
		 * here
		 */
		tlbie(vpn, psize, actual_psize, ssize, local);
	}
	local_irq_restore(flags);
}
#else
static void native_hugepage_invalidate(unsigned long vsid,
				       unsigned long addr,
				       unsigned char *hpte_slot_array,
				       int psize, int ssize, int local)
{
	WARN(1, "%s called without THP support\n", __func__);
}
#endif

static void hpte_decode(struct hash_pte *hpte, unsigned long slot,
			int *psize, int *apsize, int *ssize, unsigned long *vpn)
{
	unsigned long avpn, pteg, vpi;
	unsigned long hpte_v = be64_to_cpu(hpte->v);
	unsigned long hpte_r = be64_to_cpu(hpte->r);
	unsigned long vsid, seg_off;
	int size, a_size, shift;
	/* Look at the 8 bit LP value */
	unsigned int lp = (hpte_r >> LP_SHIFT) & ((1 << LP_BITS) - 1);

	if (cpu_has_feature(CPU_FTR_ARCH_300)) {
		hpte_v = hpte_new_to_old_v(hpte_v, hpte_r);
		hpte_r = hpte_new_to_old_r(hpte_r);
	}
	if (!(hpte_v & HPTE_V_LARGE)) {
		size   = MMU_PAGE_4K;
		a_size = MMU_PAGE_4K;
	} else {
		size = hpte_page_sizes[lp] & 0xf;
		a_size = hpte_page_sizes[lp] >> 4;
	}
	/* This works for all page sizes, and for 256M and 1T segments */
	*ssize = hpte_v >> HPTE_V_SSIZE_SHIFT;
	shift = mmu_psize_defs[size].shift;

	avpn = (HPTE_V_AVPN_VAL(hpte_v) & ~mmu_psize_defs[size].avpnm);
	pteg = slot / HPTES_PER_GROUP;
	if (hpte_v & HPTE_V_SECONDARY)
		pteg = ~pteg;

	switch (*ssize) {
	case MMU_SEGSIZE_256M:
		/* We only have 28 - 23 bits of seg_off in avpn */
		seg_off = (avpn & 0x1f) << 23;
		vsid    =  avpn >> 5;
		/* We can find more bits from the pteg value */
		if (shift < 23) {
			vpi = (vsid ^ pteg) & htab_hash_mask;
			seg_off |= vpi << shift;
		}
		*vpn = vsid << (SID_SHIFT - VPN_SHIFT) | seg_off >> VPN_SHIFT;
		break;
	case MMU_SEGSIZE_1T:
		/* We only have 40 - 23 bits of seg_off in avpn */
		seg_off = (avpn & 0x1ffff) << 23;
		vsid    = avpn >> 17;
		if (shift < 23) {
			vpi = (vsid ^ (vsid << 25) ^ pteg) & htab_hash_mask;
			seg_off |= vpi << shift;
		}
		*vpn = vsid << (SID_SHIFT_1T - VPN_SHIFT) | seg_off >> VPN_SHIFT;
		break;
	default:
		*vpn = size = 0;
	}
	*psize  = size;
	*apsize = a_size;
}

/*
 * clear all mappings on kexec.  All cpus are in real mode (or they will
 * be when they isi), and we are the only one left.  We rely on our kernel
 * mapping being 0xC0's and the hardware ignoring those two real bits.
 *
 * This must be called with interrupts disabled.
 *
 * Taking the native_tlbie_lock is unsafe here due to the possibility of
 * lockdep being on. On pre POWER5 hardware, not taking the lock could
 * cause deadlock. POWER5 and newer not taking the lock is fine. This only
 * gets called during boot before secondary CPUs have come up and during
 * crashdump and all bets are off anyway.
 *
 * TODO: add batching support when enabled.  remember, no dynamic memory here,
 * although there is the control page available...
 */
static void native_hpte_clear(void)
{
	unsigned long vpn = 0;
	unsigned long slot, slots;
	struct hash_pte *hptep = htab_address;
	unsigned long hpte_v;
	unsigned long pteg_count;
	int psize, apsize, ssize;

	pteg_count = htab_hash_mask + 1;

	slots = pteg_count * HPTES_PER_GROUP;

	for (slot = 0; slot < slots; slot++, hptep++) {
		/*
		 * we could lock the pte here, but we are the only cpu
		 * running,  right?  and for crash dump, we probably
		 * don't want to wait for a maybe bad cpu.
		 */
		hpte_v = be64_to_cpu(hptep->v);

		/*
		 * Call __tlbie() here rather than tlbie() since we can't take the
		 * native_tlbie_lock.
		 */
		if (hpte_v & HPTE_V_VALID) {
			hpte_decode(hptep, slot, &psize, &apsize, &ssize, &vpn);
			hptep->v = 0;
			__tlbie(vpn, psize, apsize, ssize);
		}
	}

	asm volatile("eieio; tlbsync; ptesync":::"memory");
}

/*
 * Batched hash table flush, we batch the tlbie's to avoid taking/releasing
 * the lock all the time
 */
static void native_flush_hash_range(unsigned long number, int local)
{
	unsigned long vpn;
	unsigned long hash, index, hidx, shift, slot;
	struct hash_pte *hptep;
	unsigned long hpte_v;
	unsigned long want_v;
	unsigned long flags;
	real_pte_t pte;
	struct ppc64_tlb_batch *batch = this_cpu_ptr(&ppc64_tlb_batch);
	unsigned long psize = batch->psize;
	int ssize = batch->ssize;
	int i;
	unsigned int use_local;

	use_local = local && mmu_has_feature(MMU_FTR_TLBIEL) &&
		mmu_psize_defs[psize].tlbiel && !cxl_ctx_in_use();

	local_irq_save(flags);

	for (i = 0; i < number; i++) {
		vpn = batch->vpn[i];
		pte = batch->pte[i];

		pte_iterate_hashed_subpages(pte, psize, vpn, index, shift) {
			hash = hpt_hash(vpn, 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;
			hptep = htab_address + slot;
			want_v = hpte_encode_avpn(vpn, psize, ssize);
			native_lock_hpte(hptep);
			hpte_v = be64_to_cpu(hptep->v);
			if (cpu_has_feature(CPU_FTR_ARCH_300))
				hpte_v = hpte_new_to_old_v(hpte_v,
						be64_to_cpu(hptep->r));
			if (!HPTE_V_COMPARE(hpte_v, want_v) ||
			    !(hpte_v & HPTE_V_VALID))
				native_unlock_hpte(hptep);
			else
				hptep->v = 0;
		} pte_iterate_hashed_end();
	}

	if (use_local) {
		asm volatile("ptesync":::"memory");
		for (i = 0; i < number; i++) {
			vpn = batch->vpn[i];
			pte = batch->pte[i];

			pte_iterate_hashed_subpages(pte, psize,
						    vpn, index, shift) {
				__tlbiel(vpn, psize, psize, ssize);
			} pte_iterate_hashed_end();
		}
		asm volatile("ptesync":::"memory");
	} else {
		int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE);

		if (lock_tlbie)
			raw_spin_lock(&native_tlbie_lock);

		asm volatile("ptesync":::"memory");
		for (i = 0; i < number; i++) {
			vpn = batch->vpn[i];
			pte = batch->pte[i];

			pte_iterate_hashed_subpages(pte, psize,
						    vpn, index, shift) {
				__tlbie(vpn, psize, psize, ssize);
			} pte_iterate_hashed_end();
		}
		asm volatile("eieio; tlbsync; ptesync":::"memory");

		if (lock_tlbie)
			raw_spin_unlock(&native_tlbie_lock);
	}

	local_irq_restore(flags);
}

static int native_register_proc_table(unsigned long base, unsigned long page_size,
				      unsigned long table_size)
{
	unsigned long patb1 = base << 25; /* VSID */

	patb1 |= (page_size << 5);  /* sllp */
	patb1 |= table_size;

	partition_tb->patb1 = cpu_to_be64(patb1);
	return 0;
}

void __init hpte_init_native(void)
{
	mmu_hash_ops.hpte_invalidate	= native_hpte_invalidate;
	mmu_hash_ops.hpte_updatepp	= native_hpte_updatepp;
	mmu_hash_ops.hpte_updateboltedpp = native_hpte_updateboltedpp;
	mmu_hash_ops.hpte_removebolted = native_hpte_removebolted;
	mmu_hash_ops.hpte_insert	= native_hpte_insert;
	mmu_hash_ops.hpte_remove	= native_hpte_remove;
	mmu_hash_ops.hpte_clear_all	= native_hpte_clear;
	mmu_hash_ops.flush_hash_range = native_flush_hash_range;
	mmu_hash_ops.hugepage_invalidate   = native_hugepage_invalidate;

	if (cpu_has_feature(CPU_FTR_ARCH_300))
		register_process_table = native_register_proc_table;
}