summaryrefslogtreecommitdiff
path: root/arch/powerpc/kvm/book3s_64_vio_hv.c
blob: 167029e57c8ff6dc8b615cab912ce3b70aeba9b2 (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 *
 * Copyright 2010 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
 * Copyright 2011 David Gibson, IBM Corporation <dwg@au1.ibm.com>
 * Copyright 2016 Alexey Kardashevskiy, IBM Corporation <aik@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/list.h>
#include <linux/stringify.h>

#include <asm/kvm_ppc.h>
#include <asm/kvm_book3s.h>
#include <asm/book3s/64/mmu-hash.h>
#include <asm/mmu_context.h>
#include <asm/hvcall.h>
#include <asm/synch.h>
#include <asm/ppc-opcode.h>
#include <asm/udbg.h>
#include <asm/iommu.h>
#include <asm/tce.h>
#include <asm/pte-walk.h>

#ifdef CONFIG_BUG

#define WARN_ON_ONCE_RM(condition)	({			\
	static bool __section(.data.unlikely) __warned;		\
	int __ret_warn_once = !!(condition);			\
								\
	if (unlikely(__ret_warn_once && !__warned)) {		\
		__warned = true;				\
		pr_err("WARN_ON_ONCE_RM: (%s) at %s:%u\n",	\
				__stringify(condition),		\
				__func__, __LINE__);		\
		dump_stack();					\
	}							\
	unlikely(__ret_warn_once);				\
})

#else

#define WARN_ON_ONCE_RM(condition) ({				\
	int __ret_warn_on = !!(condition);			\
	unlikely(__ret_warn_on);				\
})

#endif

/*
 * Finds a TCE table descriptor by LIOBN.
 *
 * WARNING: This will be called in real or virtual mode on HV KVM and virtual
 *          mode on PR KVM
 */
struct kvmppc_spapr_tce_table *kvmppc_find_table(struct kvm *kvm,
		unsigned long liobn)
{
	struct kvmppc_spapr_tce_table *stt;

	list_for_each_entry_lockless(stt, &kvm->arch.spapr_tce_tables, list)
		if (stt->liobn == liobn)
			return stt;

	return NULL;
}
EXPORT_SYMBOL_GPL(kvmppc_find_table);

#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
static long kvmppc_rm_tce_to_ua(struct kvm *kvm,
				unsigned long tce, unsigned long *ua)
{
	unsigned long gfn = tce >> PAGE_SHIFT;
	struct kvm_memory_slot *memslot;

	memslot = search_memslots(kvm_memslots_raw(kvm), gfn);
	if (!memslot)
		return -EINVAL;

	*ua = __gfn_to_hva_memslot(memslot, gfn) |
		(tce & ~(PAGE_MASK | TCE_PCI_READ | TCE_PCI_WRITE));

	return 0;
}

/*
 * Validates TCE address.
 * At the moment flags and page mask are validated.
 * As the host kernel does not access those addresses (just puts them
 * to the table and user space is supposed to process them), we can skip
 * checking other things (such as TCE is a guest RAM address or the page
 * was actually allocated).
 */
static long kvmppc_rm_tce_validate(struct kvmppc_spapr_tce_table *stt,
		unsigned long tce)
{
	unsigned long gpa = tce & ~(TCE_PCI_READ | TCE_PCI_WRITE);
	enum dma_data_direction dir = iommu_tce_direction(tce);
	struct kvmppc_spapr_tce_iommu_table *stit;
	unsigned long ua = 0;

	/* Allow userspace to poison TCE table */
	if (dir == DMA_NONE)
		return H_SUCCESS;

	if (iommu_tce_check_gpa(stt->page_shift, gpa))
		return H_PARAMETER;

	if (kvmppc_rm_tce_to_ua(stt->kvm, tce, &ua))
		return H_TOO_HARD;

	list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {
		unsigned long hpa = 0;
		struct mm_iommu_table_group_mem_t *mem;
		long shift = stit->tbl->it_page_shift;

		mem = mm_iommu_lookup_rm(stt->kvm->mm, ua, 1ULL << shift);
		if (!mem)
			return H_TOO_HARD;

		if (mm_iommu_ua_to_hpa_rm(mem, ua, shift, &hpa))
			return H_TOO_HARD;
	}

	return H_SUCCESS;
}

/* Note on the use of page_address() in real mode,
 *
 * It is safe to use page_address() in real mode on ppc64 because
 * page_address() is always defined as lowmem_page_address()
 * which returns __va(PFN_PHYS(page_to_pfn(page))) which is arithmetic
 * operation and does not access page struct.
 *
 * Theoretically page_address() could be defined different
 * but either WANT_PAGE_VIRTUAL or HASHED_PAGE_VIRTUAL
 * would have to be enabled.
 * WANT_PAGE_VIRTUAL is never enabled on ppc32/ppc64,
 * HASHED_PAGE_VIRTUAL could be enabled for ppc32 only and only
 * if CONFIG_HIGHMEM is defined. As CONFIG_SPARSEMEM_VMEMMAP
 * is not expected to be enabled on ppc32, page_address()
 * is safe for ppc32 as well.
 *
 * WARNING: This will be called in real-mode on HV KVM and virtual
 *          mode on PR KVM
 */
static u64 *kvmppc_page_address(struct page *page)
{
#if defined(HASHED_PAGE_VIRTUAL) || defined(WANT_PAGE_VIRTUAL)
#error TODO: fix to avoid page_address() here
#endif
	return (u64 *) page_address(page);
}

/*
 * Handles TCE requests for emulated devices.
 * Puts guest TCE values to the table and expects user space to convert them.
 * Cannot fail so kvmppc_rm_tce_validate must be called before it.
 */
static void kvmppc_rm_tce_put(struct kvmppc_spapr_tce_table *stt,
		unsigned long idx, unsigned long tce)
{
	struct page *page;
	u64 *tbl;

	idx -= stt->offset;
	page = stt->pages[idx / TCES_PER_PAGE];
	/*
	 * page must not be NULL in real mode,
	 * kvmppc_rm_ioba_validate() must have taken care of this.
	 */
	WARN_ON_ONCE_RM(!page);
	tbl = kvmppc_page_address(page);

	tbl[idx % TCES_PER_PAGE] = tce;
}

/*
 * TCEs pages are allocated in kvmppc_rm_tce_put() which won't be able to do so
 * in real mode.
 * Check if kvmppc_rm_tce_put() can succeed in real mode, i.e. a TCEs page is
 * allocated or not required (when clearing a tce entry).
 */
static long kvmppc_rm_ioba_validate(struct kvmppc_spapr_tce_table *stt,
		unsigned long ioba, unsigned long npages, bool clearing)
{
	unsigned long i, idx, sttpage, sttpages;
	unsigned long ret = kvmppc_ioba_validate(stt, ioba, npages);

	if (ret)
		return ret;
	/*
	 * clearing==true says kvmppc_rm_tce_put won't be allocating pages
	 * for empty tces.
	 */
	if (clearing)
		return H_SUCCESS;

	idx = (ioba >> stt->page_shift) - stt->offset;
	sttpage = idx / TCES_PER_PAGE;
	sttpages = _ALIGN_UP(idx % TCES_PER_PAGE + npages, TCES_PER_PAGE) /
			TCES_PER_PAGE;
	for (i = sttpage; i < sttpage + sttpages; ++i)
		if (!stt->pages[i])
			return H_TOO_HARD;

	return H_SUCCESS;
}

static long iommu_tce_xchg_no_kill_rm(struct mm_struct *mm,
		struct iommu_table *tbl,
		unsigned long entry, unsigned long *hpa,
		enum dma_data_direction *direction)
{
	long ret;

	ret = tbl->it_ops->xchg_no_kill(tbl, entry, hpa, direction, true);

	if (!ret && ((*direction == DMA_FROM_DEVICE) ||
				(*direction == DMA_BIDIRECTIONAL))) {
		__be64 *pua = IOMMU_TABLE_USERSPACE_ENTRY_RO(tbl, entry);
		/*
		 * kvmppc_rm_tce_iommu_do_map() updates the UA cache after
		 * calling this so we still get here a valid UA.
		 */
		if (pua && *pua)
			mm_iommu_ua_mark_dirty_rm(mm, be64_to_cpu(*pua));
	}

	return ret;
}

extern void iommu_tce_kill_rm(struct iommu_table *tbl,
		unsigned long entry, unsigned long pages)
{
	if (tbl->it_ops->tce_kill)
		tbl->it_ops->tce_kill(tbl, entry, pages, true);
}

static void kvmppc_rm_clear_tce(struct kvm *kvm, struct iommu_table *tbl,
		unsigned long entry)
{
	unsigned long hpa = 0;
	enum dma_data_direction dir = DMA_NONE;

	iommu_tce_xchg_no_kill_rm(kvm->mm, tbl, entry, &hpa, &dir);
}

static long kvmppc_rm_tce_iommu_mapped_dec(struct kvm *kvm,
		struct iommu_table *tbl, unsigned long entry)
{
	struct mm_iommu_table_group_mem_t *mem = NULL;
	const unsigned long pgsize = 1ULL << tbl->it_page_shift;
	__be64 *pua = IOMMU_TABLE_USERSPACE_ENTRY_RO(tbl, entry);

	if (!pua)
		/* it_userspace allocation might be delayed */
		return H_TOO_HARD;

	mem = mm_iommu_lookup_rm(kvm->mm, be64_to_cpu(*pua), pgsize);
	if (!mem)
		return H_TOO_HARD;

	mm_iommu_mapped_dec(mem);

	*pua = cpu_to_be64(0);

	return H_SUCCESS;
}

static long kvmppc_rm_tce_iommu_do_unmap(struct kvm *kvm,
		struct iommu_table *tbl, unsigned long entry)
{
	enum dma_data_direction dir = DMA_NONE;
	unsigned long hpa = 0;
	long ret;

	if (iommu_tce_xchg_no_kill_rm(kvm->mm, tbl, entry, &hpa, &dir))
		/*
		 * real mode xchg can fail if struct page crosses
		 * a page boundary
		 */
		return H_TOO_HARD;

	if (dir == DMA_NONE)
		return H_SUCCESS;

	ret = kvmppc_rm_tce_iommu_mapped_dec(kvm, tbl, entry);
	if (ret)
		iommu_tce_xchg_no_kill_rm(kvm->mm, tbl, entry, &hpa, &dir);

	return ret;
}

static long kvmppc_rm_tce_iommu_unmap(struct kvm *kvm,
		struct kvmppc_spapr_tce_table *stt, struct iommu_table *tbl,
		unsigned long entry)
{
	unsigned long i, ret = H_SUCCESS;
	unsigned long subpages = 1ULL << (stt->page_shift - tbl->it_page_shift);
	unsigned long io_entry = entry * subpages;

	for (i = 0; i < subpages; ++i) {
		ret = kvmppc_rm_tce_iommu_do_unmap(kvm, tbl, io_entry + i);
		if (ret != H_SUCCESS)
			break;
	}

	return ret;
}

static long kvmppc_rm_tce_iommu_do_map(struct kvm *kvm, struct iommu_table *tbl,
		unsigned long entry, unsigned long ua,
		enum dma_data_direction dir)
{
	long ret;
	unsigned long hpa = 0;
	__be64 *pua = IOMMU_TABLE_USERSPACE_ENTRY_RO(tbl, entry);
	struct mm_iommu_table_group_mem_t *mem;

	if (!pua)
		/* it_userspace allocation might be delayed */
		return H_TOO_HARD;

	mem = mm_iommu_lookup_rm(kvm->mm, ua, 1ULL << tbl->it_page_shift);
	if (!mem)
		return H_TOO_HARD;

	if (WARN_ON_ONCE_RM(mm_iommu_ua_to_hpa_rm(mem, ua, tbl->it_page_shift,
			&hpa)))
		return H_TOO_HARD;

	if (WARN_ON_ONCE_RM(mm_iommu_mapped_inc(mem)))
		return H_TOO_HARD;

	ret = iommu_tce_xchg_no_kill_rm(kvm->mm, tbl, entry, &hpa, &dir);
	if (ret) {
		mm_iommu_mapped_dec(mem);
		/*
		 * real mode xchg can fail if struct page crosses
		 * a page boundary
		 */
		return H_TOO_HARD;
	}

	if (dir != DMA_NONE)
		kvmppc_rm_tce_iommu_mapped_dec(kvm, tbl, entry);

	*pua = cpu_to_be64(ua);

	return 0;
}

static long kvmppc_rm_tce_iommu_map(struct kvm *kvm,
		struct kvmppc_spapr_tce_table *stt, struct iommu_table *tbl,
		unsigned long entry, unsigned long ua,
		enum dma_data_direction dir)
{
	unsigned long i, pgoff, ret = H_SUCCESS;
	unsigned long subpages = 1ULL << (stt->page_shift - tbl->it_page_shift);
	unsigned long io_entry = entry * subpages;

	for (i = 0, pgoff = 0; i < subpages;
			++i, pgoff += IOMMU_PAGE_SIZE(tbl)) {

		ret = kvmppc_rm_tce_iommu_do_map(kvm, tbl,
				io_entry + i, ua + pgoff, dir);
		if (ret != H_SUCCESS)
			break;
	}

	return ret;
}

long kvmppc_rm_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
		unsigned long ioba, unsigned long tce)
{
	struct kvmppc_spapr_tce_table *stt;
	long ret;
	struct kvmppc_spapr_tce_iommu_table *stit;
	unsigned long entry, ua = 0;
	enum dma_data_direction dir;

	/* udbg_printf("H_PUT_TCE(): liobn=0x%lx ioba=0x%lx, tce=0x%lx\n", */
	/* 	    liobn, ioba, tce); */

	/* For radix, we might be in virtual mode, so punt */
	if (kvm_is_radix(vcpu->kvm))
		return H_TOO_HARD;

	stt = kvmppc_find_table(vcpu->kvm, liobn);
	if (!stt)
		return H_TOO_HARD;

	ret = kvmppc_rm_ioba_validate(stt, ioba, 1, tce == 0);
	if (ret != H_SUCCESS)
		return ret;

	ret = kvmppc_rm_tce_validate(stt, tce);
	if (ret != H_SUCCESS)
		return ret;

	dir = iommu_tce_direction(tce);
	if ((dir != DMA_NONE) && kvmppc_rm_tce_to_ua(vcpu->kvm, tce, &ua))
		return H_PARAMETER;

	entry = ioba >> stt->page_shift;

	list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {
		if (dir == DMA_NONE)
			ret = kvmppc_rm_tce_iommu_unmap(vcpu->kvm, stt,
					stit->tbl, entry);
		else
			ret = kvmppc_rm_tce_iommu_map(vcpu->kvm, stt,
					stit->tbl, entry, ua, dir);

		iommu_tce_kill_rm(stit->tbl, entry, 1);

		if (ret != H_SUCCESS) {
			kvmppc_rm_clear_tce(vcpu->kvm, stit->tbl, entry);
			return ret;
		}
	}

	kvmppc_rm_tce_put(stt, entry, tce);

	return H_SUCCESS;
}

static long kvmppc_rm_ua_to_hpa(struct kvm_vcpu *vcpu, unsigned long mmu_seq,
				unsigned long ua, unsigned long *phpa)
{
	pte_t *ptep, pte;
	unsigned shift = 0;

	/*
	 * Called in real mode with MSR_EE = 0. We are safe here.
	 * It is ok to do the lookup with arch.pgdir here, because
	 * we are doing this on secondary cpus and current task there
	 * is not the hypervisor. Also this is safe against THP in the
	 * host, because an IPI to primary thread will wait for the secondary
	 * to exit which will agains result in the below page table walk
	 * to finish.
	 */
	/* an rmap lock won't make it safe. because that just ensure hash
	 * page table entries are removed with rmap lock held. After that
	 * mmu notifier returns and we go ahead and removing ptes from Qemu page table.
	 */
	ptep = find_kvm_host_pte(vcpu->kvm, mmu_seq, ua, &shift);
	if (!ptep)
		return -ENXIO;

	pte = READ_ONCE(*ptep);
	if (!pte_present(pte))
		return -ENXIO;

	if (!shift)
		shift = PAGE_SHIFT;

	/* Avoid handling anything potentially complicated in realmode */
	if (shift > PAGE_SHIFT)
		return -EAGAIN;

	if (!pte_young(pte))
		return -EAGAIN;

	*phpa = (pte_pfn(pte) << PAGE_SHIFT) | (ua & ((1ULL << shift) - 1)) |
			(ua & ~PAGE_MASK);

	return 0;
}

long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu,
		unsigned long liobn, unsigned long ioba,
		unsigned long tce_list,	unsigned long npages)
{
	struct kvm *kvm = vcpu->kvm;
	struct kvmppc_spapr_tce_table *stt;
	long i, ret = H_SUCCESS;
	unsigned long tces, entry, ua = 0;
	unsigned long mmu_seq;
	bool prereg = false;
	struct kvmppc_spapr_tce_iommu_table *stit;

	/* For radix, we might be in virtual mode, so punt */
	if (kvm_is_radix(vcpu->kvm))
		return H_TOO_HARD;

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

	stt = kvmppc_find_table(vcpu->kvm, liobn);
	if (!stt)
		return H_TOO_HARD;

	entry = ioba >> stt->page_shift;
	/*
	 * The spec says that the maximum size of the list is 512 TCEs
	 * so the whole table addressed resides in 4K page
	 */
	if (npages > 512)
		return H_PARAMETER;

	if (tce_list & (SZ_4K - 1))
		return H_PARAMETER;

	ret = kvmppc_rm_ioba_validate(stt, ioba, npages, false);
	if (ret != H_SUCCESS)
		return ret;

	if (mm_iommu_preregistered(vcpu->kvm->mm)) {
		/*
		 * We get here if guest memory was pre-registered which
		 * is normally VFIO case and gpa->hpa translation does not
		 * depend on hpt.
		 */
		struct mm_iommu_table_group_mem_t *mem;

		if (kvmppc_rm_tce_to_ua(vcpu->kvm, tce_list, &ua))
			return H_TOO_HARD;

		mem = mm_iommu_lookup_rm(vcpu->kvm->mm, ua, IOMMU_PAGE_SIZE_4K);
		if (mem)
			prereg = mm_iommu_ua_to_hpa_rm(mem, ua,
					IOMMU_PAGE_SHIFT_4K, &tces) == 0;
	}

	if (!prereg) {
		/*
		 * This is usually a case of a guest with emulated devices only
		 * when TCE list is not in preregistered memory.
		 * We do not require memory to be preregistered in this case
		 * so lock rmap and do __find_linux_pte_or_hugepte().
		 */
		if (kvmppc_rm_tce_to_ua(vcpu->kvm, tce_list, &ua))
			return H_TOO_HARD;

		arch_spin_lock(&kvm->mmu_lock.rlock.raw_lock);
		if (kvmppc_rm_ua_to_hpa(vcpu, mmu_seq, ua, &tces)) {
			ret = H_TOO_HARD;
			goto unlock_exit;
		}
	}

	for (i = 0; i < npages; ++i) {
		unsigned long tce = be64_to_cpu(((u64 *)tces)[i]);

		ret = kvmppc_rm_tce_validate(stt, tce);
		if (ret != H_SUCCESS)
			goto unlock_exit;
	}

	for (i = 0; i < npages; ++i) {
		unsigned long tce = be64_to_cpu(((u64 *)tces)[i]);

		ua = 0;
		if (kvmppc_rm_tce_to_ua(vcpu->kvm, tce, &ua)) {
			ret = H_PARAMETER;
			goto invalidate_exit;
		}

		list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {
			ret = kvmppc_rm_tce_iommu_map(vcpu->kvm, stt,
					stit->tbl, entry + i, ua,
					iommu_tce_direction(tce));

			if (ret != H_SUCCESS) {
				kvmppc_rm_clear_tce(vcpu->kvm, stit->tbl,
						entry);
				goto invalidate_exit;
			}
		}

		kvmppc_rm_tce_put(stt, entry + i, tce);
	}

invalidate_exit:
	list_for_each_entry_lockless(stit, &stt->iommu_tables, next)
		iommu_tce_kill_rm(stit->tbl, entry, npages);

unlock_exit:
	if (!prereg)
		arch_spin_unlock(&kvm->mmu_lock.rlock.raw_lock);
	return ret;
}

long kvmppc_rm_h_stuff_tce(struct kvm_vcpu *vcpu,
		unsigned long liobn, unsigned long ioba,
		unsigned long tce_value, unsigned long npages)
{
	struct kvmppc_spapr_tce_table *stt;
	long i, ret;
	struct kvmppc_spapr_tce_iommu_table *stit;

	/* For radix, we might be in virtual mode, so punt */
	if (kvm_is_radix(vcpu->kvm))
		return H_TOO_HARD;

	stt = kvmppc_find_table(vcpu->kvm, liobn);
	if (!stt)
		return H_TOO_HARD;

	ret = kvmppc_rm_ioba_validate(stt, ioba, npages, tce_value == 0);
	if (ret != H_SUCCESS)
		return ret;

	/* Check permission bits only to allow userspace poison TCE for debug */
	if (tce_value & (TCE_PCI_WRITE | TCE_PCI_READ))
		return H_PARAMETER;

	list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {
		unsigned long entry = ioba >> stt->page_shift;

		for (i = 0; i < npages; ++i) {
			ret = kvmppc_rm_tce_iommu_unmap(vcpu->kvm, stt,
					stit->tbl, entry + i);

			if (ret == H_SUCCESS)
				continue;

			if (ret == H_TOO_HARD)
				goto invalidate_exit;

			WARN_ON_ONCE_RM(1);
			kvmppc_rm_clear_tce(vcpu->kvm, stit->tbl, entry);
		}
	}

	for (i = 0; i < npages; ++i, ioba += (1ULL << stt->page_shift))
		kvmppc_rm_tce_put(stt, ioba >> stt->page_shift, tce_value);

invalidate_exit:
	list_for_each_entry_lockless(stit, &stt->iommu_tables, next)
		iommu_tce_kill_rm(stit->tbl, ioba >> stt->page_shift, npages);

	return ret;
}

/* This can be called in either virtual mode or real mode */
long kvmppc_h_get_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
		      unsigned long ioba)
{
	struct kvmppc_spapr_tce_table *stt;
	long ret;
	unsigned long idx;
	struct page *page;
	u64 *tbl;

	stt = kvmppc_find_table(vcpu->kvm, liobn);
	if (!stt)
		return H_TOO_HARD;

	ret = kvmppc_ioba_validate(stt, ioba, 1);
	if (ret != H_SUCCESS)
		return ret;

	idx = (ioba >> stt->page_shift) - stt->offset;
	page = stt->pages[idx / TCES_PER_PAGE];
	if (!page) {
		vcpu->arch.regs.gpr[4] = 0;
		return H_SUCCESS;
	}
	tbl = (u64 *)page_address(page);

	vcpu->arch.regs.gpr[4] = tbl[idx % TCES_PER_PAGE];

	return H_SUCCESS;
}
EXPORT_SYMBOL_GPL(kvmppc_h_get_tce);

#endif /* KVM_BOOK3S_HV_POSSIBLE */