aboutsummaryrefslogtreecommitdiff
path: root/arch/powerpc/kvm/book3s_64_mmu_hv.c
blob: 80a57751758444a427797ecaff2a6f2e07a1ba03 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
/*
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License, version 2, as
 * published by the Free Software Foundation.
 *
 * This program 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 General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write to the Free Software
 * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
 *
 * Copyright 2010 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
 */

#include <linux/types.h>
#include <linux/string.h>
#include <linux/kvm.h>
#include <linux/kvm_host.h>
#include <linux/highmem.h>
#include <linux/gfp.h>
#include <linux/slab.h>
#include <linux/hugetlb.h>
#include <linux/vmalloc.h>

#include <asm/tlbflush.h>
#include <asm/kvm_ppc.h>
#include <asm/kvm_book3s.h>
#include <asm/mmu-hash64.h>
#include <asm/hvcall.h>
#include <asm/synch.h>
#include <asm/ppc-opcode.h>
#include <asm/cputable.h>

/* POWER7 has 10-bit LPIDs, PPC970 has 6-bit LPIDs */
#define MAX_LPID_970	63

long kvmppc_alloc_hpt(struct kvm *kvm)
{
	unsigned long hpt;
	long lpid;
	struct revmap_entry *rev;
	struct kvmppc_linear_info *li;

	/* Allocate guest's hashed page table */
	li = kvm_alloc_hpt();
	if (li) {
		/* using preallocated memory */
		hpt = (ulong)li->base_virt;
		kvm->arch.hpt_li = li;
	} else {
		/* using dynamic memory */
		hpt = __get_free_pages(GFP_KERNEL|__GFP_ZERO|__GFP_REPEAT|
				       __GFP_NOWARN, HPT_ORDER - PAGE_SHIFT);
	}

	if (!hpt) {
		pr_err("kvm_alloc_hpt: Couldn't alloc HPT\n");
		return -ENOMEM;
	}
	kvm->arch.hpt_virt = hpt;

	/* Allocate reverse map array */
	rev = vmalloc(sizeof(struct revmap_entry) * HPT_NPTE);
	if (!rev) {
		pr_err("kvmppc_alloc_hpt: Couldn't alloc reverse map array\n");
		goto out_freehpt;
	}
	kvm->arch.revmap = rev;

	lpid = kvmppc_alloc_lpid();
	if (lpid < 0)
		goto out_freeboth;

	kvm->arch.sdr1 = __pa(hpt) | (HPT_ORDER - 18);
	kvm->arch.lpid = lpid;

	pr_info("KVM guest htab at %lx, LPID %lx\n", hpt, lpid);
	return 0;

 out_freeboth:
	vfree(rev);
 out_freehpt:
	free_pages(hpt, HPT_ORDER - PAGE_SHIFT);
	return -ENOMEM;
}

void kvmppc_free_hpt(struct kvm *kvm)
{
	kvmppc_free_lpid(kvm->arch.lpid);
	vfree(kvm->arch.revmap);
	if (kvm->arch.hpt_li)
		kvm_release_hpt(kvm->arch.hpt_li);
	else
		free_pages(kvm->arch.hpt_virt, HPT_ORDER - PAGE_SHIFT);
}

/* Bits in first HPTE dword for pagesize 4k, 64k or 16M */
static inline unsigned long hpte0_pgsize_encoding(unsigned long pgsize)
{
	return (pgsize > 0x1000) ? HPTE_V_LARGE : 0;
}

/* Bits in second HPTE dword for pagesize 4k, 64k or 16M */
static inline unsigned long hpte1_pgsize_encoding(unsigned long pgsize)
{
	return (pgsize == 0x10000) ? 0x1000 : 0;
}

void kvmppc_map_vrma(struct kvm_vcpu *vcpu, struct kvm_memory_slot *memslot,
		     unsigned long porder)
{
	unsigned long i;
	unsigned long npages;
	unsigned long hp_v, hp_r;
	unsigned long addr, hash;
	unsigned long psize;
	unsigned long hp0, hp1;
	long ret;

	psize = 1ul << porder;
	npages = memslot->npages >> (porder - PAGE_SHIFT);

	/* VRMA can't be > 1TB */
	if (npages > 1ul << (40 - porder))
		npages = 1ul << (40 - porder);
	/* Can't use more than 1 HPTE per HPTEG */
	if (npages > HPT_NPTEG)
		npages = HPT_NPTEG;

	hp0 = HPTE_V_1TB_SEG | (VRMA_VSID << (40 - 16)) |
		HPTE_V_BOLTED | hpte0_pgsize_encoding(psize);
	hp1 = hpte1_pgsize_encoding(psize) |
		HPTE_R_R | HPTE_R_C | HPTE_R_M | PP_RWXX;

	for (i = 0; i < npages; ++i) {
		addr = i << porder;
		/* can't use hpt_hash since va > 64 bits */
		hash = (i ^ (VRMA_VSID ^ (VRMA_VSID << 25))) & HPT_HASH_MASK;
		/*
		 * We assume that the hash table is empty and no
		 * vcpus are using it at this stage.  Since we create
		 * at most one HPTE per HPTEG, we just assume entry 7
		 * is available and use it.
		 */
		hash = (hash << 3) + 7;
		hp_v = hp0 | ((addr >> 16) & ~0x7fUL);
		hp_r = hp1 | addr;
		ret = kvmppc_virtmode_h_enter(vcpu, H_EXACT, hash, hp_v, hp_r);
		if (ret != H_SUCCESS) {
			pr_err("KVM: map_vrma at %lx failed, ret=%ld\n",
			       addr, ret);
			break;
		}
	}
}

int kvmppc_mmu_hv_init(void)
{
	unsigned long host_lpid, rsvd_lpid;

	if (!cpu_has_feature(CPU_FTR_HVMODE))
		return -EINVAL;

	/* POWER7 has 10-bit LPIDs, PPC970 and e500mc have 6-bit LPIDs */
	if (cpu_has_feature(CPU_FTR_ARCH_206)) {
		host_lpid = mfspr(SPRN_LPID);	/* POWER7 */
		rsvd_lpid = LPID_RSVD;
	} else {
		host_lpid = 0;			/* PPC970 */
		rsvd_lpid = MAX_LPID_970;
	}

	kvmppc_init_lpid(rsvd_lpid + 1);

	kvmppc_claim_lpid(host_lpid);
	/* rsvd_lpid is reserved for use in partition switching */
	kvmppc_claim_lpid(rsvd_lpid);

	return 0;
}

void kvmppc_mmu_destroy(struct kvm_vcpu *vcpu)
{
}

static void kvmppc_mmu_book3s_64_hv_reset_msr(struct kvm_vcpu *vcpu)
{
	kvmppc_set_msr(vcpu, MSR_SF | MSR_ME);
}

/*
 * This is called to get a reference to a guest page if there isn't
 * one already in the kvm->arch.slot_phys[][] arrays.
 */
static long kvmppc_get_guest_page(struct kvm *kvm, unsigned long gfn,
				  struct kvm_memory_slot *memslot,
				  unsigned long psize)
{
	unsigned long start;
	long np, err;
	struct page *page, *hpage, *pages[1];
	unsigned long s, pgsize;
	unsigned long *physp;
	unsigned int is_io, got, pgorder;
	struct vm_area_struct *vma;
	unsigned long pfn, i, npages;

	physp = kvm->arch.slot_phys[memslot->id];
	if (!physp)
		return -EINVAL;
	if (physp[gfn - memslot->base_gfn])
		return 0;

	is_io = 0;
	got = 0;
	page = NULL;
	pgsize = psize;
	err = -EINVAL;
	start = gfn_to_hva_memslot(memslot, gfn);

	/* Instantiate and get the page we want access to */
	np = get_user_pages_fast(start, 1, 1, pages);
	if (np != 1) {
		/* Look up the vma for the page */
		down_read(&current->mm->mmap_sem);
		vma = find_vma(current->mm, start);
		if (!vma || vma->vm_start > start ||
		    start + psize > vma->vm_end ||
		    !(vma->vm_flags & VM_PFNMAP))
			goto up_err;
		is_io = hpte_cache_bits(pgprot_val(vma->vm_page_prot));
		pfn = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT);
		/* check alignment of pfn vs. requested page size */
		if (psize > PAGE_SIZE && (pfn & ((psize >> PAGE_SHIFT) - 1)))
			goto up_err;
		up_read(&current->mm->mmap_sem);

	} else {
		page = pages[0];
		got = KVMPPC_GOT_PAGE;

		/* See if this is a large page */
		s = PAGE_SIZE;
		if (PageHuge(page)) {
			hpage = compound_head(page);
			s <<= compound_order(hpage);
			/* Get the whole large page if slot alignment is ok */
			if (s > psize && slot_is_aligned(memslot, s) &&
			    !(memslot->userspace_addr & (s - 1))) {
				start &= ~(s - 1);
				pgsize = s;
				get_page(hpage);
				put_page(page);
				page = hpage;
			}
		}
		if (s < psize)
			goto out;
		pfn = page_to_pfn(page);
	}

	npages = pgsize >> PAGE_SHIFT;
	pgorder = __ilog2(npages);
	physp += (gfn - memslot->base_gfn) & ~(npages - 1);
	spin_lock(&kvm->arch.slot_phys_lock);
	for (i = 0; i < npages; ++i) {
		if (!physp[i]) {
			physp[i] = ((pfn + i) << PAGE_SHIFT) +
				got + is_io + pgorder;
			got = 0;
		}
	}
	spin_unlock(&kvm->arch.slot_phys_lock);
	err = 0;

 out:
	if (got)
		put_page(page);
	return err;

 up_err:
	up_read(&current->mm->mmap_sem);
	return err;
}

/*
 * We come here on a H_ENTER call from the guest when we are not
 * using mmu notifiers and we don't have the requested page pinned
 * already.
 */
long kvmppc_virtmode_h_enter(struct kvm_vcpu *vcpu, unsigned long flags,
			long pte_index, unsigned long pteh, unsigned long ptel)
{
	struct kvm *kvm = vcpu->kvm;
	unsigned long psize, gpa, gfn;
	struct kvm_memory_slot *memslot;
	long ret;

	if (kvm->arch.using_mmu_notifiers)
		goto do_insert;

	psize = hpte_page_size(pteh, ptel);
	if (!psize)
		return H_PARAMETER;

	pteh &= ~(HPTE_V_HVLOCK | HPTE_V_ABSENT | HPTE_V_VALID);

	/* Find the memslot (if any) for this address */
	gpa = (ptel & HPTE_R_RPN) & ~(psize - 1);
	gfn = gpa >> PAGE_SHIFT;
	memslot = gfn_to_memslot(kvm, gfn);
	if (memslot && !(memslot->flags & KVM_MEMSLOT_INVALID)) {
		if (!slot_is_aligned(memslot, psize))
			return H_PARAMETER;
		if (kvmppc_get_guest_page(kvm, gfn, memslot, psize) < 0)
			return H_PARAMETER;
	}

 do_insert:
	/* Protect linux PTE lookup from page table destruction */
	rcu_read_lock_sched();	/* this disables preemption too */
	vcpu->arch.pgdir = current->mm->pgd;
	ret = kvmppc_h_enter(vcpu, flags, pte_index, pteh, ptel);
	rcu_read_unlock_sched();
	if (ret == H_TOO_HARD) {
		/* this can't happen */
		pr_err("KVM: Oops, kvmppc_h_enter returned too hard!\n");
		ret = H_RESOURCE;	/* or something */
	}
	return ret;

}

static struct kvmppc_slb *kvmppc_mmu_book3s_hv_find_slbe(struct kvm_vcpu *vcpu,
							 gva_t eaddr)
{
	u64 mask;
	int i;

	for (i = 0; i < vcpu->arch.slb_nr; i++) {
		if (!(vcpu->arch.slb[i].orige & SLB_ESID_V))
			continue;

		if (vcpu->arch.slb[i].origv & SLB_VSID_B_1T)
			mask = ESID_MASK_1T;
		else
			mask = ESID_MASK;

		if (((vcpu->arch.slb[i].orige ^ eaddr) & mask) == 0)
			return &vcpu->arch.slb[i];
	}
	return NULL;
}

static unsigned long kvmppc_mmu_get_real_addr(unsigned long v, unsigned long r,
			unsigned long ea)
{
	unsigned long ra_mask;

	ra_mask = hpte_page_size(v, r) - 1;
	return (r & HPTE_R_RPN & ~ra_mask) | (ea & ra_mask);
}

static int kvmppc_mmu_book3s_64_hv_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
			struct kvmppc_pte *gpte, bool data)
{
	struct kvm *kvm = vcpu->kvm;
	struct kvmppc_slb *slbe;
	unsigned long slb_v;
	unsigned long pp, key;
	unsigned long v, gr;
	unsigned long *hptep;
	int index;
	int virtmode = vcpu->arch.shregs.msr & (data ? MSR_DR : MSR_IR);

	/* Get SLB entry */
	if (virtmode) {
		slbe = kvmppc_mmu_book3s_hv_find_slbe(vcpu, eaddr);
		if (!slbe)
			return -EINVAL;
		slb_v = slbe->origv;
	} else {
		/* real mode access */
		slb_v = vcpu->kvm->arch.vrma_slb_v;
	}

	/* Find the HPTE in the hash table */
	index = kvmppc_hv_find_lock_hpte(kvm, eaddr, slb_v,
					 HPTE_V_VALID | HPTE_V_ABSENT);
	if (index < 0)
		return -ENOENT;
	hptep = (unsigned long *)(kvm->arch.hpt_virt + (index << 4));
	v = hptep[0] & ~HPTE_V_HVLOCK;
	gr = kvm->arch.revmap[index].guest_rpte;

	/* Unlock the HPTE */
	asm volatile("lwsync" : : : "memory");
	hptep[0] = v;

	gpte->eaddr = eaddr;
	gpte->vpage = ((v & HPTE_V_AVPN) << 4) | ((eaddr >> 12) & 0xfff);

	/* Get PP bits and key for permission check */
	pp = gr & (HPTE_R_PP0 | HPTE_R_PP);
	key = (vcpu->arch.shregs.msr & MSR_PR) ? SLB_VSID_KP : SLB_VSID_KS;
	key &= slb_v;

	/* Calculate permissions */
	gpte->may_read = hpte_read_permission(pp, key);
	gpte->may_write = hpte_write_permission(pp, key);
	gpte->may_execute = gpte->may_read && !(gr & (HPTE_R_N | HPTE_R_G));

	/* Storage key permission check for POWER7 */
	if (data && virtmode && cpu_has_feature(CPU_FTR_ARCH_206)) {
		int amrfield = hpte_get_skey_perm(gr, vcpu->arch.amr);
		if (amrfield & 1)
			gpte->may_read = 0;
		if (amrfield & 2)
			gpte->may_write = 0;
	}

	/* Get the guest physical address */
	gpte->raddr = kvmppc_mmu_get_real_addr(v, gr, eaddr);
	return 0;
}

/*
 * Quick test for whether an instruction is a load or a store.
 * If the instruction is a load or a store, then this will indicate
 * which it is, at least on server processors.  (Embedded processors
 * have some external PID instructions that don't follow the rule
 * embodied here.)  If the instruction isn't a load or store, then
 * this doesn't return anything useful.
 */
static int instruction_is_store(unsigned int instr)
{
	unsigned int mask;

	mask = 0x10000000;
	if ((instr & 0xfc000000) == 0x7c000000)
		mask = 0x100;		/* major opcode 31 */
	return (instr & mask) != 0;
}

static int kvmppc_hv_emulate_mmio(struct kvm_run *run, struct kvm_vcpu *vcpu,
				  unsigned long gpa, gva_t ea, int is_store)
{
	int ret;
	u32 last_inst;
	unsigned long srr0 = kvmppc_get_pc(vcpu);

	/* We try to load the last instruction.  We don't let
	 * emulate_instruction do it as it doesn't check what
	 * kvmppc_ld returns.
	 * If we fail, we just return to the guest and try executing it again.
	 */
	if (vcpu->arch.last_inst == KVM_INST_FETCH_FAILED) {
		ret = kvmppc_ld(vcpu, &srr0, sizeof(u32), &last_inst, false);
		if (ret != EMULATE_DONE || last_inst == KVM_INST_FETCH_FAILED)
			return RESUME_GUEST;
		vcpu->arch.last_inst = last_inst;
	}

	/*
	 * WARNING: We do not know for sure whether the instruction we just
	 * read from memory is the same that caused the fault in the first
	 * place.  If the instruction we read is neither an load or a store,
	 * then it can't access memory, so we don't need to worry about
	 * enforcing access permissions.  So, assuming it is a load or
	 * store, we just check that its direction (load or store) is
	 * consistent with the original fault, since that's what we
	 * checked the access permissions against.  If there is a mismatch
	 * we just return and retry the instruction.
	 */

	if (instruction_is_store(vcpu->arch.last_inst) != !!is_store)
		return RESUME_GUEST;

	/*
	 * Emulated accesses are emulated by looking at the hash for
	 * translation once, then performing the access later. The
	 * translation could be invalidated in the meantime in which
	 * point performing the subsequent memory access on the old
	 * physical address could possibly be a security hole for the
	 * guest (but not the host).
	 *
	 * This is less of an issue for MMIO stores since they aren't
	 * globally visible. It could be an issue for MMIO loads to
	 * a certain extent but we'll ignore it for now.
	 */

	vcpu->arch.paddr_accessed = gpa;
	vcpu->arch.vaddr_accessed = ea;
	return kvmppc_emulate_mmio(run, vcpu);
}

int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
				unsigned long ea, unsigned long dsisr)
{
	struct kvm *kvm = vcpu->kvm;
	unsigned long *hptep, hpte[3], r;
	unsigned long mmu_seq, psize, pte_size;
	unsigned long gfn, hva, pfn;
	struct kvm_memory_slot *memslot;
	unsigned long *rmap;
	struct revmap_entry *rev;
	struct page *page, *pages[1];
	long index, ret, npages;
	unsigned long is_io;
	unsigned int writing, write_ok;
	struct vm_area_struct *vma;
	unsigned long rcbits;

	/*
	 * Real-mode code has already searched the HPT and found the
	 * entry we're interested in.  Lock the entry and check that
	 * it hasn't changed.  If it has, just return and re-execute the
	 * instruction.
	 */
	if (ea != vcpu->arch.pgfault_addr)
		return RESUME_GUEST;
	index = vcpu->arch.pgfault_index;
	hptep = (unsigned long *)(kvm->arch.hpt_virt + (index << 4));
	rev = &kvm->arch.revmap[index];
	preempt_disable();
	while (!try_lock_hpte(hptep, HPTE_V_HVLOCK))
		cpu_relax();
	hpte[0] = hptep[0] & ~HPTE_V_HVLOCK;
	hpte[1] = hptep[1];
	hpte[2] = r = rev->guest_rpte;
	asm volatile("lwsync" : : : "memory");
	hptep[0] = hpte[0];
	preempt_enable();

	if (hpte[0] != vcpu->arch.pgfault_hpte[0] ||
	    hpte[1] != vcpu->arch.pgfault_hpte[1])
		return RESUME_GUEST;

	/* Translate the logical address and get the page */
	psize = hpte_page_size(hpte[0], r);
	gfn = hpte_rpn(r, psize);
	memslot = gfn_to_memslot(kvm, gfn);

	/* No memslot means it's an emulated MMIO region */
	if (!memslot || (memslot->flags & KVM_MEMSLOT_INVALID)) {
		unsigned long gpa = (gfn << PAGE_SHIFT) | (ea & (psize - 1));
		return kvmppc_hv_emulate_mmio(run, vcpu, gpa, ea,
					      dsisr & DSISR_ISSTORE);
	}

	if (!kvm->arch.using_mmu_notifiers)
		return -EFAULT;		/* should never get here */

	/* used to check for invalidations in progress */
	mmu_seq = kvm->mmu_notifier_seq;
	smp_rmb();

	is_io = 0;
	pfn = 0;
	page = NULL;
	pte_size = PAGE_SIZE;
	writing = (dsisr & DSISR_ISSTORE) != 0;
	/* If writing != 0, then the HPTE must allow writing, if we get here */
	write_ok = writing;
	hva = gfn_to_hva_memslot(memslot, gfn);
	npages = get_user_pages_fast(hva, 1, writing, pages);
	if (npages < 1) {
		/* Check if it's an I/O mapping */
		down_read(&current->mm->mmap_sem);
		vma = find_vma(current->mm, hva);
		if (vma && vma->vm_start <= hva && hva + psize <= vma->vm_end &&
		    (vma->vm_flags & VM_PFNMAP)) {
			pfn = vma->vm_pgoff +
				((hva - vma->vm_start) >> PAGE_SHIFT);
			pte_size = psize;
			is_io = hpte_cache_bits(pgprot_val(vma->vm_page_prot));
			write_ok = vma->vm_flags & VM_WRITE;
		}
		up_read(&current->mm->mmap_sem);
		if (!pfn)
			return -EFAULT;
	} else {
		page = pages[0];
		if (PageHuge(page)) {
			page = compound_head(page);
			pte_size <<= compound_order(page);
		}
		/* if the guest wants write access, see if that is OK */
		if (!writing && hpte_is_writable(r)) {
			pte_t *ptep, pte;

			/*
			 * We need to protect against page table destruction
			 * while looking up and updating the pte.
			 */
			rcu_read_lock_sched();
			ptep = find_linux_pte_or_hugepte(current->mm->pgd,
							 hva, NULL);
			if (ptep && pte_present(*ptep)) {
				pte = kvmppc_read_update_linux_pte(ptep, 1);
				if (pte_write(pte))
					write_ok = 1;
			}
			rcu_read_unlock_sched();
		}
		pfn = page_to_pfn(page);
	}

	ret = -EFAULT;
	if (psize > pte_size)
		goto out_put;

	/* Check WIMG vs. the actual page we're accessing */
	if (!hpte_cache_flags_ok(r, is_io)) {
		if (is_io)
			return -EFAULT;
		/*
		 * Allow guest to map emulated device memory as
		 * uncacheable, but actually make it cacheable.
		 */
		r = (r & ~(HPTE_R_W|HPTE_R_I|HPTE_R_G)) | HPTE_R_M;
	}

	/* Set the HPTE to point to pfn */
	r = (r & ~(HPTE_R_PP0 - pte_size)) | (pfn << PAGE_SHIFT);
	if (hpte_is_writable(r) && !write_ok)
		r = hpte_make_readonly(r);
	ret = RESUME_GUEST;
	preempt_disable();
	while (!try_lock_hpte(hptep, HPTE_V_HVLOCK))
		cpu_relax();
	if ((hptep[0] & ~HPTE_V_HVLOCK) != hpte[0] || hptep[1] != hpte[1] ||
	    rev->guest_rpte != hpte[2])
		/* HPTE has been changed under us; let the guest retry */
		goto out_unlock;
	hpte[0] = (hpte[0] & ~HPTE_V_ABSENT) | HPTE_V_VALID;

	rmap = &memslot->rmap[gfn - memslot->base_gfn];
	lock_rmap(rmap);

	/* Check if we might have been invalidated; let the guest retry if so */
	ret = RESUME_GUEST;
	if (mmu_notifier_retry(vcpu, mmu_seq)) {
		unlock_rmap(rmap);
		goto out_unlock;
	}

	/* Only set R/C in real HPTE if set in both *rmap and guest_rpte */
	rcbits = *rmap >> KVMPPC_RMAP_RC_SHIFT;
	r &= rcbits | ~(HPTE_R_R | HPTE_R_C);

	if (hptep[0] & HPTE_V_VALID) {
		/* HPTE was previously valid, so we need to invalidate it */
		unlock_rmap(rmap);
		hptep[0] |= HPTE_V_ABSENT;
		kvmppc_invalidate_hpte(kvm, hptep, index);
		/* don't lose previous R and C bits */
		r |= hptep[1] & (HPTE_R_R | HPTE_R_C);
	} else {
		kvmppc_add_revmap_chain(kvm, rev, rmap, index, 0);
	}

	hptep[1] = r;
	eieio();
	hptep[0] = hpte[0];
	asm volatile("ptesync" : : : "memory");
	preempt_enable();
	if (page && hpte_is_writable(r))
		SetPageDirty(page);

 out_put:
	if (page) {
		/*
		 * We drop pages[0] here, not page because page might
		 * have been set to the head page of a compound, but
		 * we have to drop the reference on the correct tail
		 * page to match the get inside gup()
		 */
		put_page(pages[0]);
	}
	return ret;

 out_unlock:
	hptep[0] &= ~HPTE_V_HVLOCK;
	preempt_enable();
	goto out_put;
}

static int kvm_handle_hva(struct kvm *kvm, unsigned long hva,
			  int (*handler)(struct kvm *kvm, unsigned long *rmapp,
					 unsigned long gfn))
{
	int ret;
	int retval = 0;
	struct kvm_memslots *slots;
	struct kvm_memory_slot *memslot;

	slots = kvm_memslots(kvm);
	kvm_for_each_memslot(memslot, slots) {
		unsigned long start = memslot->userspace_addr;
		unsigned long end;

		end = start + (memslot->npages << PAGE_SHIFT);
		if (hva >= start && hva < end) {
			gfn_t gfn_offset = (hva - start) >> PAGE_SHIFT;

			ret = handler(kvm, &memslot->rmap[gfn_offset],
				      memslot->base_gfn + gfn_offset);
			retval |= ret;
		}
	}

	return retval;
}

static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp,
			   unsigned long gfn)
{
	struct revmap_entry *rev = kvm->arch.revmap;
	unsigned long h, i, j;
	unsigned long *hptep;
	unsigned long ptel, psize, rcbits;

	for (;;) {
		lock_rmap(rmapp);
		if (!(*rmapp & KVMPPC_RMAP_PRESENT)) {
			unlock_rmap(rmapp);
			break;
		}

		/*
		 * To avoid an ABBA deadlock with the HPTE lock bit,
		 * we can't spin on the HPTE lock while holding the
		 * rmap chain lock.
		 */
		i = *rmapp & KVMPPC_RMAP_INDEX;
		hptep = (unsigned long *) (kvm->arch.hpt_virt + (i << 4));
		if (!try_lock_hpte(hptep, HPTE_V_HVLOCK)) {
			/* unlock rmap before spinning on the HPTE lock */
			unlock_rmap(rmapp);
			while (hptep[0] & HPTE_V_HVLOCK)
				cpu_relax();
			continue;
		}
		j = rev[i].forw;
		if (j == i) {
			/* chain is now empty */
			*rmapp &= ~(KVMPPC_RMAP_PRESENT | KVMPPC_RMAP_INDEX);
		} else {
			/* remove i from chain */
			h = rev[i].back;
			rev[h].forw = j;
			rev[j].back = h;
			rev[i].forw = rev[i].back = i;
			*rmapp = (*rmapp & ~KVMPPC_RMAP_INDEX) | j;
		}

		/* Now check and modify the HPTE */
		ptel = rev[i].guest_rpte;
		psize = hpte_page_size(hptep[0], ptel);
		if ((hptep[0] & HPTE_V_VALID) &&
		    hpte_rpn(ptel, psize) == gfn) {
			hptep[0] |= HPTE_V_ABSENT;
			kvmppc_invalidate_hpte(kvm, hptep, i);
			/* Harvest R and C */
			rcbits = hptep[1] & (HPTE_R_R | HPTE_R_C);
			*rmapp |= rcbits << KVMPPC_RMAP_RC_SHIFT;
			rev[i].guest_rpte = ptel | rcbits;
		}
		unlock_rmap(rmapp);
		hptep[0] &= ~HPTE_V_HVLOCK;
	}
	return 0;
}

int kvm_unmap_hva(struct kvm *kvm, unsigned long hva)
{
	if (kvm->arch.using_mmu_notifiers)
		kvm_handle_hva(kvm, hva, kvm_unmap_rmapp);
	return 0;
}

static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp,
			 unsigned long gfn)
{
	struct revmap_entry *rev = kvm->arch.revmap;
	unsigned long head, i, j;
	unsigned long *hptep;
	int ret = 0;

 retry:
	lock_rmap(rmapp);
	if (*rmapp & KVMPPC_RMAP_REFERENCED) {
		*rmapp &= ~KVMPPC_RMAP_REFERENCED;
		ret = 1;
	}
	if (!(*rmapp & KVMPPC_RMAP_PRESENT)) {
		unlock_rmap(rmapp);
		return ret;
	}

	i = head = *rmapp & KVMPPC_RMAP_INDEX;
	do {
		hptep = (unsigned long *) (kvm->arch.hpt_virt + (i << 4));
		j = rev[i].forw;

		/* If this HPTE isn't referenced, ignore it */
		if (!(hptep[1] & HPTE_R_R))
			continue;

		if (!try_lock_hpte(hptep, HPTE_V_HVLOCK)) {
			/* unlock rmap before spinning on the HPTE lock */
			unlock_rmap(rmapp);
			while (hptep[0] & HPTE_V_HVLOCK)
				cpu_relax();
			goto retry;
		}

		/* Now check and modify the HPTE */
		if ((hptep[0] & HPTE_V_VALID) && (hptep[1] & HPTE_R_R)) {
			kvmppc_clear_ref_hpte(kvm, hptep, i);
			rev[i].guest_rpte |= HPTE_R_R;
			ret = 1;
		}
		hptep[0] &= ~HPTE_V_HVLOCK;
	} while ((i = j) != head);

	unlock_rmap(rmapp);
	return ret;
}

int kvm_age_hva(struct kvm *kvm, unsigned long hva)
{
	if (!kvm->arch.using_mmu_notifiers)
		return 0;
	return kvm_handle_hva(kvm, hva, kvm_age_rmapp);
}

static int kvm_test_age_rmapp(struct kvm *kvm, unsigned long *rmapp,
			      unsigned long gfn)
{
	struct revmap_entry *rev = kvm->arch.revmap;
	unsigned long head, i, j;
	unsigned long *hp;
	int ret = 1;

	if (*rmapp & KVMPPC_RMAP_REFERENCED)
		return 1;

	lock_rmap(rmapp);
	if (*rmapp & KVMPPC_RMAP_REFERENCED)
		goto out;

	if (*rmapp & KVMPPC_RMAP_PRESENT) {
		i = head = *rmapp & KVMPPC_RMAP_INDEX;
		do {
			hp = (unsigned long *)(kvm->arch.hpt_virt + (i << 4));
			j = rev[i].forw;
			if (hp[1] & HPTE_R_R)
				goto out;
		} while ((i = j) != head);
	}
	ret = 0;

 out:
	unlock_rmap(rmapp);
	return ret;
}

int kvm_test_age_hva(struct kvm *kvm, unsigned long hva)
{
	if (!kvm->arch.using_mmu_notifiers)
		return 0;
	return kvm_handle_hva(kvm, hva, kvm_test_age_rmapp);
}

void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte)
{
	if (!kvm->arch.using_mmu_notifiers)
		return;
	kvm_handle_hva(kvm, hva, kvm_unmap_rmapp);
}

static int kvm_test_clear_dirty(struct kvm *kvm, unsigned long *rmapp)
{
	struct revmap_entry *rev = kvm->arch.revmap;
	unsigned long head, i, j;
	unsigned long *hptep;
	int ret = 0;

 retry:
	lock_rmap(rmapp);
	if (*rmapp & KVMPPC_RMAP_CHANGED) {
		*rmapp &= ~KVMPPC_RMAP_CHANGED;
		ret = 1;
	}
	if (!(*rmapp & KVMPPC_RMAP_PRESENT)) {
		unlock_rmap(rmapp);
		return ret;
	}

	i = head = *rmapp & KVMPPC_RMAP_INDEX;
	do {
		hptep = (unsigned long *) (kvm->arch.hpt_virt + (i << 4));
		j = rev[i].forw;

		if (!(hptep[1] & HPTE_R_C))
			continue;

		if (!try_lock_hpte(hptep, HPTE_V_HVLOCK)) {
			/* unlock rmap before spinning on the HPTE lock */
			unlock_rmap(rmapp);
			while (hptep[0] & HPTE_V_HVLOCK)
				cpu_relax();
			goto retry;
		}

		/* Now check and modify the HPTE */
		if ((hptep[0] & HPTE_V_VALID) && (hptep[1] & HPTE_R_C)) {
			/* need to make it temporarily absent to clear C */
			hptep[0] |= HPTE_V_ABSENT;
			kvmppc_invalidate_hpte(kvm, hptep, i);
			hptep[1] &= ~HPTE_R_C;
			eieio();
			hptep[0] = (hptep[0] & ~HPTE_V_ABSENT) | HPTE_V_VALID;
			rev[i].guest_rpte |= HPTE_R_C;
			ret = 1;
		}
		hptep[0] &= ~HPTE_V_HVLOCK;
	} while ((i = j) != head);

	unlock_rmap(rmapp);
	return ret;
}

long kvmppc_hv_get_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot)
{
	unsigned long i;
	unsigned long *rmapp, *map;

	preempt_disable();
	rmapp = memslot->rmap;
	map = memslot->dirty_bitmap;
	for (i = 0; i < memslot->npages; ++i) {
		if (kvm_test_clear_dirty(kvm, rmapp))
			__set_bit_le(i, map);
		++rmapp;
	}
	preempt_enable();
	return 0;
}

void *kvmppc_pin_guest_page(struct kvm *kvm, unsigned long gpa,
			    unsigned long *nb_ret)
{
	struct kvm_memory_slot *memslot;
	unsigned long gfn = gpa >> PAGE_SHIFT;
	struct page *page, *pages[1];
	int npages;
	unsigned long hva, psize, offset;
	unsigned long pa;
	unsigned long *physp;

	memslot = gfn_to_memslot(kvm, gfn);
	if (!memslot || (memslot->flags & KVM_MEMSLOT_INVALID))
		return NULL;
	if (!kvm->arch.using_mmu_notifiers) {
		physp = kvm->arch.slot_phys[memslot->id];
		if (!physp)
			return NULL;
		physp += gfn - memslot->base_gfn;
		pa = *physp;
		if (!pa) {
			if (kvmppc_get_guest_page(kvm, gfn, memslot,
						  PAGE_SIZE) < 0)
				return NULL;
			pa = *physp;
		}
		page = pfn_to_page(pa >> PAGE_SHIFT);
		get_page(page);
	} else {
		hva = gfn_to_hva_memslot(memslot, gfn);
		npages = get_user_pages_fast(hva, 1, 1, pages);
		if (npages < 1)
			return NULL;
		page = pages[0];
	}
	psize = PAGE_SIZE;
	if (PageHuge(page)) {
		page = compound_head(page);
		psize <<= compound_order(page);
	}
	offset = gpa & (psize - 1);
	if (nb_ret)
		*nb_ret = psize - offset;
	return page_address(page) + offset;
}

void kvmppc_unpin_guest_page(struct kvm *kvm, void *va)
{
	struct page *page = virt_to_page(va);

	put_page(page);
}

void kvmppc_mmu_book3s_hv_init(struct kvm_vcpu *vcpu)
{
	struct kvmppc_mmu *mmu = &vcpu->arch.mmu;

	if (cpu_has_feature(CPU_FTR_ARCH_206))
		vcpu->arch.slb_nr = 32;		/* POWER7 */
	else
		vcpu->arch.slb_nr = 64;

	mmu->xlate = kvmppc_mmu_book3s_64_hv_xlate;
	mmu->reset_msr = kvmppc_mmu_book3s_64_hv_reset_msr;

	vcpu->arch.hflags |= BOOK3S_HFLAG_SLB;
}