summaryrefslogtreecommitdiff
path: root/arch/x86/kernel/cpu/sgx/encl.c
blob: 48afe96ae0f0f5e6a1ed1fc2850861dc10c3ea8f (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
// SPDX-License-Identifier: GPL-2.0
/*  Copyright(c) 2016-20 Intel Corporation. */

#include <linux/lockdep.h>
#include <linux/mm.h>
#include <linux/mman.h>
#include <linux/shmem_fs.h>
#include <linux/suspend.h>
#include <linux/sched/mm.h>
#include <asm/sgx.h>
#include "encl.h"
#include "encls.h"
#include "sgx.h"

/*
 * ELDU: Load an EPC page as unblocked. For more info, see "OS Management of EPC
 * Pages" in the SDM.
 */
static int __sgx_encl_eldu(struct sgx_encl_page *encl_page,
			   struct sgx_epc_page *epc_page,
			   struct sgx_epc_page *secs_page)
{
	unsigned long va_offset = encl_page->desc & SGX_ENCL_PAGE_VA_OFFSET_MASK;
	struct sgx_encl *encl = encl_page->encl;
	struct sgx_pageinfo pginfo;
	struct sgx_backing b;
	pgoff_t page_index;
	int ret;

	if (secs_page)
		page_index = PFN_DOWN(encl_page->desc - encl_page->encl->base);
	else
		page_index = PFN_DOWN(encl->size);

	ret = sgx_encl_get_backing(encl, page_index, &b);
	if (ret)
		return ret;

	pginfo.addr = encl_page->desc & PAGE_MASK;
	pginfo.contents = (unsigned long)kmap_atomic(b.contents);
	pginfo.metadata = (unsigned long)kmap_atomic(b.pcmd) +
			  b.pcmd_offset;

	if (secs_page)
		pginfo.secs = (u64)sgx_get_epc_virt_addr(secs_page);
	else
		pginfo.secs = 0;

	ret = __eldu(&pginfo, sgx_get_epc_virt_addr(epc_page),
		     sgx_get_epc_virt_addr(encl_page->va_page->epc_page) + va_offset);
	if (ret) {
		if (encls_failed(ret))
			ENCLS_WARN(ret, "ELDU");

		ret = -EFAULT;
	}

	kunmap_atomic((void *)(unsigned long)(pginfo.metadata - b.pcmd_offset));
	kunmap_atomic((void *)(unsigned long)pginfo.contents);

	sgx_encl_put_backing(&b, false);

	return ret;
}

static struct sgx_epc_page *sgx_encl_eldu(struct sgx_encl_page *encl_page,
					  struct sgx_epc_page *secs_page)
{

	unsigned long va_offset = encl_page->desc & SGX_ENCL_PAGE_VA_OFFSET_MASK;
	struct sgx_encl *encl = encl_page->encl;
	struct sgx_epc_page *epc_page;
	int ret;

	epc_page = sgx_alloc_epc_page(encl_page, false);
	if (IS_ERR(epc_page))
		return epc_page;

	ret = __sgx_encl_eldu(encl_page, epc_page, secs_page);
	if (ret) {
		sgx_encl_free_epc_page(epc_page);
		return ERR_PTR(ret);
	}

	sgx_free_va_slot(encl_page->va_page, va_offset);
	list_move(&encl_page->va_page->list, &encl->va_pages);
	encl_page->desc &= ~SGX_ENCL_PAGE_VA_OFFSET_MASK;
	encl_page->epc_page = epc_page;

	return epc_page;
}

static struct sgx_encl_page *sgx_encl_load_page(struct sgx_encl *encl,
						unsigned long addr,
						unsigned long vm_flags)
{
	unsigned long vm_prot_bits = vm_flags & (VM_READ | VM_WRITE | VM_EXEC);
	struct sgx_epc_page *epc_page;
	struct sgx_encl_page *entry;

	entry = xa_load(&encl->page_array, PFN_DOWN(addr));
	if (!entry)
		return ERR_PTR(-EFAULT);

	/*
	 * Verify that the faulted page has equal or higher build time
	 * permissions than the VMA permissions (i.e. the subset of {VM_READ,
	 * VM_WRITE, VM_EXECUTE} in vma->vm_flags).
	 */
	if ((entry->vm_max_prot_bits & vm_prot_bits) != vm_prot_bits)
		return ERR_PTR(-EFAULT);

	/* Entry successfully located. */
	if (entry->epc_page) {
		if (entry->desc & SGX_ENCL_PAGE_BEING_RECLAIMED)
			return ERR_PTR(-EBUSY);

		return entry;
	}

	if (!(encl->secs.epc_page)) {
		epc_page = sgx_encl_eldu(&encl->secs, NULL);
		if (IS_ERR(epc_page))
			return ERR_CAST(epc_page);
	}

	epc_page = sgx_encl_eldu(entry, encl->secs.epc_page);
	if (IS_ERR(epc_page))
		return ERR_CAST(epc_page);

	encl->secs_child_cnt++;
	sgx_mark_page_reclaimable(entry->epc_page);

	return entry;
}

static vm_fault_t sgx_vma_fault(struct vm_fault *vmf)
{
	unsigned long addr = (unsigned long)vmf->address;
	struct vm_area_struct *vma = vmf->vma;
	struct sgx_encl_page *entry;
	unsigned long phys_addr;
	struct sgx_encl *encl;
	vm_fault_t ret;

	encl = vma->vm_private_data;

	/*
	 * It's very unlikely but possible that allocating memory for the
	 * mm_list entry of a forked process failed in sgx_vma_open(). When
	 * this happens, vm_private_data is set to NULL.
	 */
	if (unlikely(!encl))
		return VM_FAULT_SIGBUS;

	mutex_lock(&encl->lock);

	entry = sgx_encl_load_page(encl, addr, vma->vm_flags);
	if (IS_ERR(entry)) {
		mutex_unlock(&encl->lock);

		if (PTR_ERR(entry) == -EBUSY)
			return VM_FAULT_NOPAGE;

		return VM_FAULT_SIGBUS;
	}

	phys_addr = sgx_get_epc_phys_addr(entry->epc_page);

	ret = vmf_insert_pfn(vma, addr, PFN_DOWN(phys_addr));
	if (ret != VM_FAULT_NOPAGE) {
		mutex_unlock(&encl->lock);

		return VM_FAULT_SIGBUS;
	}

	sgx_encl_test_and_clear_young(vma->vm_mm, entry);
	mutex_unlock(&encl->lock);

	return VM_FAULT_NOPAGE;
}

static void sgx_vma_open(struct vm_area_struct *vma)
{
	struct sgx_encl *encl = vma->vm_private_data;

	/*
	 * It's possible but unlikely that vm_private_data is NULL. This can
	 * happen in a grandchild of a process, when sgx_encl_mm_add() had
	 * failed to allocate memory in this callback.
	 */
	if (unlikely(!encl))
		return;

	if (sgx_encl_mm_add(encl, vma->vm_mm))
		vma->vm_private_data = NULL;
}


/**
 * sgx_encl_may_map() - Check if a requested VMA mapping is allowed
 * @encl:		an enclave pointer
 * @start:		lower bound of the address range, inclusive
 * @end:		upper bound of the address range, exclusive
 * @vm_flags:		VMA flags
 *
 * Iterate through the enclave pages contained within [@start, @end) to verify
 * that the permissions requested by a subset of {VM_READ, VM_WRITE, VM_EXEC}
 * do not contain any permissions that are not contained in the build time
 * permissions of any of the enclave pages within the given address range.
 *
 * An enclave creator must declare the strongest permissions that will be
 * needed for each enclave page. This ensures that mappings have the identical
 * or weaker permissions than the earlier declared permissions.
 *
 * Return: 0 on success, -EACCES otherwise
 */
int sgx_encl_may_map(struct sgx_encl *encl, unsigned long start,
		     unsigned long end, unsigned long vm_flags)
{
	unsigned long vm_prot_bits = vm_flags & (VM_READ | VM_WRITE | VM_EXEC);
	struct sgx_encl_page *page;
	unsigned long count = 0;
	int ret = 0;

	XA_STATE(xas, &encl->page_array, PFN_DOWN(start));

	/*
	 * Disallow READ_IMPLIES_EXEC tasks as their VMA permissions might
	 * conflict with the enclave page permissions.
	 */
	if (current->personality & READ_IMPLIES_EXEC)
		return -EACCES;

	mutex_lock(&encl->lock);
	xas_lock(&xas);
	xas_for_each(&xas, page, PFN_DOWN(end - 1)) {
		if (~page->vm_max_prot_bits & vm_prot_bits) {
			ret = -EACCES;
			break;
		}

		/* Reschedule on every XA_CHECK_SCHED iteration. */
		if (!(++count % XA_CHECK_SCHED)) {
			xas_pause(&xas);
			xas_unlock(&xas);
			mutex_unlock(&encl->lock);

			cond_resched();

			mutex_lock(&encl->lock);
			xas_lock(&xas);
		}
	}
	xas_unlock(&xas);
	mutex_unlock(&encl->lock);

	return ret;
}

static int sgx_vma_mprotect(struct vm_area_struct *vma, unsigned long start,
			    unsigned long end, unsigned long newflags)
{
	return sgx_encl_may_map(vma->vm_private_data, start, end, newflags);
}

static int sgx_encl_debug_read(struct sgx_encl *encl, struct sgx_encl_page *page,
			       unsigned long addr, void *data)
{
	unsigned long offset = addr & ~PAGE_MASK;
	int ret;


	ret = __edbgrd(sgx_get_epc_virt_addr(page->epc_page) + offset, data);
	if (ret)
		return -EIO;

	return 0;
}

static int sgx_encl_debug_write(struct sgx_encl *encl, struct sgx_encl_page *page,
				unsigned long addr, void *data)
{
	unsigned long offset = addr & ~PAGE_MASK;
	int ret;

	ret = __edbgwr(sgx_get_epc_virt_addr(page->epc_page) + offset, data);
	if (ret)
		return -EIO;

	return 0;
}

/*
 * Load an enclave page to EPC if required, and take encl->lock.
 */
static struct sgx_encl_page *sgx_encl_reserve_page(struct sgx_encl *encl,
						   unsigned long addr,
						   unsigned long vm_flags)
{
	struct sgx_encl_page *entry;

	for ( ; ; ) {
		mutex_lock(&encl->lock);

		entry = sgx_encl_load_page(encl, addr, vm_flags);
		if (PTR_ERR(entry) != -EBUSY)
			break;

		mutex_unlock(&encl->lock);
	}

	if (IS_ERR(entry))
		mutex_unlock(&encl->lock);

	return entry;
}

static int sgx_vma_access(struct vm_area_struct *vma, unsigned long addr,
			  void *buf, int len, int write)
{
	struct sgx_encl *encl = vma->vm_private_data;
	struct sgx_encl_page *entry = NULL;
	char data[sizeof(unsigned long)];
	unsigned long align;
	int offset;
	int cnt;
	int ret = 0;
	int i;

	/*
	 * If process was forked, VMA is still there but vm_private_data is set
	 * to NULL.
	 */
	if (!encl)
		return -EFAULT;

	if (!test_bit(SGX_ENCL_DEBUG, &encl->flags))
		return -EFAULT;

	for (i = 0; i < len; i += cnt) {
		entry = sgx_encl_reserve_page(encl, (addr + i) & PAGE_MASK,
					      vma->vm_flags);
		if (IS_ERR(entry)) {
			ret = PTR_ERR(entry);
			break;
		}

		align = ALIGN_DOWN(addr + i, sizeof(unsigned long));
		offset = (addr + i) & (sizeof(unsigned long) - 1);
		cnt = sizeof(unsigned long) - offset;
		cnt = min(cnt, len - i);

		ret = sgx_encl_debug_read(encl, entry, align, data);
		if (ret)
			goto out;

		if (write) {
			memcpy(data + offset, buf + i, cnt);
			ret = sgx_encl_debug_write(encl, entry, align, data);
			if (ret)
				goto out;
		} else {
			memcpy(buf + i, data + offset, cnt);
		}

out:
		mutex_unlock(&encl->lock);

		if (ret)
			break;
	}

	return ret < 0 ? ret : i;
}

const struct vm_operations_struct sgx_vm_ops = {
	.fault = sgx_vma_fault,
	.mprotect = sgx_vma_mprotect,
	.open = sgx_vma_open,
	.access = sgx_vma_access,
};

/**
 * sgx_encl_release - Destroy an enclave instance
 * @ref:	address of a kref inside &sgx_encl
 *
 * Used together with kref_put(). Frees all the resources associated with the
 * enclave and the instance itself.
 */
void sgx_encl_release(struct kref *ref)
{
	struct sgx_encl *encl = container_of(ref, struct sgx_encl, refcount);
	struct sgx_va_page *va_page;
	struct sgx_encl_page *entry;
	unsigned long index;

	xa_for_each(&encl->page_array, index, entry) {
		if (entry->epc_page) {
			/*
			 * The page and its radix tree entry cannot be freed
			 * if the page is being held by the reclaimer.
			 */
			if (sgx_unmark_page_reclaimable(entry->epc_page))
				continue;

			sgx_encl_free_epc_page(entry->epc_page);
			encl->secs_child_cnt--;
			entry->epc_page = NULL;
		}

		kfree(entry);
		/* Invoke scheduler to prevent soft lockups. */
		cond_resched();
	}

	xa_destroy(&encl->page_array);

	if (!encl->secs_child_cnt && encl->secs.epc_page) {
		sgx_encl_free_epc_page(encl->secs.epc_page);
		encl->secs.epc_page = NULL;
	}

	while (!list_empty(&encl->va_pages)) {
		va_page = list_first_entry(&encl->va_pages, struct sgx_va_page,
					   list);
		list_del(&va_page->list);
		sgx_encl_free_epc_page(va_page->epc_page);
		kfree(va_page);
	}

	if (encl->backing)
		fput(encl->backing);

	cleanup_srcu_struct(&encl->srcu);

	WARN_ON_ONCE(!list_empty(&encl->mm_list));

	/* Detect EPC page leak's. */
	WARN_ON_ONCE(encl->secs_child_cnt);
	WARN_ON_ONCE(encl->secs.epc_page);

	kfree(encl);
}

/*
 * 'mm' is exiting and no longer needs mmu notifications.
 */
static void sgx_mmu_notifier_release(struct mmu_notifier *mn,
				     struct mm_struct *mm)
{
	struct sgx_encl_mm *encl_mm = container_of(mn, struct sgx_encl_mm, mmu_notifier);
	struct sgx_encl_mm *tmp = NULL;

	/*
	 * The enclave itself can remove encl_mm.  Note, objects can't be moved
	 * off an RCU protected list, but deletion is ok.
	 */
	spin_lock(&encl_mm->encl->mm_lock);
	list_for_each_entry(tmp, &encl_mm->encl->mm_list, list) {
		if (tmp == encl_mm) {
			list_del_rcu(&encl_mm->list);
			break;
		}
	}
	spin_unlock(&encl_mm->encl->mm_lock);

	if (tmp == encl_mm) {
		synchronize_srcu(&encl_mm->encl->srcu);
		mmu_notifier_put(mn);
	}
}

static void sgx_mmu_notifier_free(struct mmu_notifier *mn)
{
	struct sgx_encl_mm *encl_mm = container_of(mn, struct sgx_encl_mm, mmu_notifier);

	/* 'encl_mm' is going away, put encl_mm->encl reference: */
	kref_put(&encl_mm->encl->refcount, sgx_encl_release);

	kfree(encl_mm);
}

static const struct mmu_notifier_ops sgx_mmu_notifier_ops = {
	.release		= sgx_mmu_notifier_release,
	.free_notifier		= sgx_mmu_notifier_free,
};

static struct sgx_encl_mm *sgx_encl_find_mm(struct sgx_encl *encl,
					    struct mm_struct *mm)
{
	struct sgx_encl_mm *encl_mm = NULL;
	struct sgx_encl_mm *tmp;
	int idx;

	idx = srcu_read_lock(&encl->srcu);

	list_for_each_entry_rcu(tmp, &encl->mm_list, list) {
		if (tmp->mm == mm) {
			encl_mm = tmp;
			break;
		}
	}

	srcu_read_unlock(&encl->srcu, idx);

	return encl_mm;
}

int sgx_encl_mm_add(struct sgx_encl *encl, struct mm_struct *mm)
{
	struct sgx_encl_mm *encl_mm;
	int ret;

	/*
	 * Even though a single enclave may be mapped into an mm more than once,
	 * each 'mm' only appears once on encl->mm_list. This is guaranteed by
	 * holding the mm's mmap lock for write before an mm can be added or
	 * remove to an encl->mm_list.
	 */
	mmap_assert_write_locked(mm);

	/*
	 * It's possible that an entry already exists in the mm_list, because it
	 * is removed only on VFS release or process exit.
	 */
	if (sgx_encl_find_mm(encl, mm))
		return 0;

	encl_mm = kzalloc(sizeof(*encl_mm), GFP_KERNEL);
	if (!encl_mm)
		return -ENOMEM;

	/* Grab a refcount for the encl_mm->encl reference: */
	kref_get(&encl->refcount);
	encl_mm->encl = encl;
	encl_mm->mm = mm;
	encl_mm->mmu_notifier.ops = &sgx_mmu_notifier_ops;

	ret = __mmu_notifier_register(&encl_mm->mmu_notifier, mm);
	if (ret) {
		kfree(encl_mm);
		return ret;
	}

	spin_lock(&encl->mm_lock);
	list_add_rcu(&encl_mm->list, &encl->mm_list);
	/* Pairs with smp_rmb() in sgx_reclaimer_block(). */
	smp_wmb();
	encl->mm_list_version++;
	spin_unlock(&encl->mm_lock);

	return 0;
}

static struct page *sgx_encl_get_backing_page(struct sgx_encl *encl,
					      pgoff_t index)
{
	struct inode *inode = encl->backing->f_path.dentry->d_inode;
	struct address_space *mapping = inode->i_mapping;
	gfp_t gfpmask = mapping_gfp_mask(mapping);

	return shmem_read_mapping_page_gfp(mapping, index, gfpmask);
}

/**
 * sgx_encl_get_backing() - Pin the backing storage
 * @encl:	an enclave pointer
 * @page_index:	enclave page index
 * @backing:	data for accessing backing storage for the page
 *
 * Pin the backing storage pages for storing the encrypted contents and Paging
 * Crypto MetaData (PCMD) of an enclave page.
 *
 * Return:
 *   0 on success,
 *   -errno otherwise.
 */
int sgx_encl_get_backing(struct sgx_encl *encl, unsigned long page_index,
			 struct sgx_backing *backing)
{
	pgoff_t pcmd_index = PFN_DOWN(encl->size) + 1 + (page_index >> 5);
	struct page *contents;
	struct page *pcmd;

	contents = sgx_encl_get_backing_page(encl, page_index);
	if (IS_ERR(contents))
		return PTR_ERR(contents);

	pcmd = sgx_encl_get_backing_page(encl, pcmd_index);
	if (IS_ERR(pcmd)) {
		put_page(contents);
		return PTR_ERR(pcmd);
	}

	backing->page_index = page_index;
	backing->contents = contents;
	backing->pcmd = pcmd;
	backing->pcmd_offset =
		(page_index & (PAGE_SIZE / sizeof(struct sgx_pcmd) - 1)) *
		sizeof(struct sgx_pcmd);

	return 0;
}

/**
 * sgx_encl_put_backing() - Unpin the backing storage
 * @backing:	data for accessing backing storage for the page
 * @do_write:	mark pages dirty
 */
void sgx_encl_put_backing(struct sgx_backing *backing, bool do_write)
{
	if (do_write) {
		set_page_dirty(backing->pcmd);
		set_page_dirty(backing->contents);
	}

	put_page(backing->pcmd);
	put_page(backing->contents);
}

static int sgx_encl_test_and_clear_young_cb(pte_t *ptep, unsigned long addr,
					    void *data)
{
	pte_t pte;
	int ret;

	ret = pte_young(*ptep);
	if (ret) {
		pte = pte_mkold(*ptep);
		set_pte_at((struct mm_struct *)data, addr, ptep, pte);
	}

	return ret;
}

/**
 * sgx_encl_test_and_clear_young() - Test and reset the accessed bit
 * @mm:		mm_struct that is checked
 * @page:	enclave page to be tested for recent access
 *
 * Checks the Access (A) bit from the PTE corresponding to the enclave page and
 * clears it.
 *
 * Return: 1 if the page has been recently accessed and 0 if not.
 */
int sgx_encl_test_and_clear_young(struct mm_struct *mm,
				  struct sgx_encl_page *page)
{
	unsigned long addr = page->desc & PAGE_MASK;
	struct sgx_encl *encl = page->encl;
	struct vm_area_struct *vma;
	int ret;

	ret = sgx_encl_find(mm, addr, &vma);
	if (ret)
		return 0;

	if (encl != vma->vm_private_data)
		return 0;

	ret = apply_to_page_range(vma->vm_mm, addr, PAGE_SIZE,
				  sgx_encl_test_and_clear_young_cb, vma->vm_mm);
	if (ret < 0)
		return 0;

	return ret;
}

/**
 * sgx_alloc_va_page() - Allocate a Version Array (VA) page
 *
 * Allocate a free EPC page and convert it to a Version Array (VA) page.
 *
 * Return:
 *   a VA page,
 *   -errno otherwise
 */
struct sgx_epc_page *sgx_alloc_va_page(void)
{
	struct sgx_epc_page *epc_page;
	int ret;

	epc_page = sgx_alloc_epc_page(NULL, true);
	if (IS_ERR(epc_page))
		return ERR_CAST(epc_page);

	ret = __epa(sgx_get_epc_virt_addr(epc_page));
	if (ret) {
		WARN_ONCE(1, "EPA returned %d (0x%x)", ret, ret);
		sgx_encl_free_epc_page(epc_page);
		return ERR_PTR(-EFAULT);
	}

	return epc_page;
}

/**
 * sgx_alloc_va_slot - allocate a VA slot
 * @va_page:	a &struct sgx_va_page instance
 *
 * Allocates a slot from a &struct sgx_va_page instance.
 *
 * Return: offset of the slot inside the VA page
 */
unsigned int sgx_alloc_va_slot(struct sgx_va_page *va_page)
{
	int slot = find_first_zero_bit(va_page->slots, SGX_VA_SLOT_COUNT);

	if (slot < SGX_VA_SLOT_COUNT)
		set_bit(slot, va_page->slots);

	return slot << 3;
}

/**
 * sgx_free_va_slot - free a VA slot
 * @va_page:	a &struct sgx_va_page instance
 * @offset:	offset of the slot inside the VA page
 *
 * Frees a slot from a &struct sgx_va_page instance.
 */
void sgx_free_va_slot(struct sgx_va_page *va_page, unsigned int offset)
{
	clear_bit(offset >> 3, va_page->slots);
}

/**
 * sgx_va_page_full - is the VA page full?
 * @va_page:	a &struct sgx_va_page instance
 *
 * Return: true if all slots have been taken
 */
bool sgx_va_page_full(struct sgx_va_page *va_page)
{
	int slot = find_first_zero_bit(va_page->slots, SGX_VA_SLOT_COUNT);

	return slot == SGX_VA_SLOT_COUNT;
}

/**
 * sgx_encl_free_epc_page - free an EPC page assigned to an enclave
 * @page:	EPC page to be freed
 *
 * Free an EPC page assigned to an enclave. It does EREMOVE for the page, and
 * only upon success, it puts the page back to free page list.  Otherwise, it
 * gives a WARNING to indicate page is leaked.
 */
void sgx_encl_free_epc_page(struct sgx_epc_page *page)
{
	int ret;

	WARN_ON_ONCE(page->flags & SGX_EPC_PAGE_RECLAIMER_TRACKED);

	ret = __eremove(sgx_get_epc_virt_addr(page));
	if (WARN_ONCE(ret, EREMOVE_ERROR_MESSAGE, ret, ret))
		return;

	sgx_free_epc_page(page);
}