Home Home > GIT Browse > stable-xen
summaryrefslogtreecommitdiff
blob: feca75b07fddce01e6e121542d3e0b74d321f85f (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
/******************************************************************************
 * privcmd.c
 *
 * Interface to privileged domain-0 commands.
 *
 * Copyright (c) 2002-2004, K A Fraser, B Dragovic
 */

#define pr_fmt(fmt) "xen:" KBUILD_MODNAME ": " fmt

#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/string.h>
#include <linux/errno.h>
#include <linux/mm.h>
#include <linux/mman.h>
#include <linux/uaccess.h>
#include <linux/swap.h>
#include <linux/highmem.h>
#include <linux/pagemap.h>
#include <linux/seq_file.h>
#include <linux/miscdevice.h>
#include <linux/moduleparam.h>

#include <asm/pgalloc.h>
#include <asm/pgtable.h>
#include <asm/tlb.h>
#include <asm/xen/hypervisor.h>
#include <asm/xen/hypercall.h>

#include <xen/xen.h>
#include <xen/privcmd.h>
#include <xen/interface/xen.h>
#include <xen/interface/hvm/dm_op.h>
#include <xen/features.h>
#include <xen/page.h>
#include <xen/xen-ops.h>
#include <xen/balloon.h>

#include "privcmd.h"

MODULE_LICENSE("GPL");

#define PRIV_VMA_LOCKED ((void *)1)

static unsigned int privcmd_dm_op_max_num = 16;
module_param_named(dm_op_max_nr_bufs, privcmd_dm_op_max_num, uint, 0644);
MODULE_PARM_DESC(dm_op_max_nr_bufs,
		 "Maximum number of buffers per dm_op hypercall");

static unsigned int privcmd_dm_op_buf_max_size = 4096;
module_param_named(dm_op_buf_max_size, privcmd_dm_op_buf_max_size, uint,
		   0644);
MODULE_PARM_DESC(dm_op_buf_max_size,
		 "Maximum size of a dm_op hypercall buffer");

struct privcmd_data {
	domid_t domid;
};

static int privcmd_vma_range_is_mapped(
               struct vm_area_struct *vma,
               unsigned long addr,
               unsigned long nr_pages);

static long privcmd_ioctl_hypercall(struct file *file, void __user *udata)
{
	struct privcmd_data *data = file->private_data;
	struct privcmd_hypercall hypercall;
	long ret;

	/* Disallow arbitrary hypercalls if restricted */
	if (data->domid != DOMID_INVALID)
		return -EPERM;

	if (copy_from_user(&hypercall, udata, sizeof(hypercall)))
		return -EFAULT;

	xen_preemptible_hcall_begin();
	ret = privcmd_call(hypercall.op,
			   hypercall.arg[0], hypercall.arg[1],
			   hypercall.arg[2], hypercall.arg[3],
			   hypercall.arg[4]);
	xen_preemptible_hcall_end();

	return ret;
}

static void free_page_list(struct list_head *pages)
{
	struct page *p, *n;

	list_for_each_entry_safe(p, n, pages, lru)
		__free_page(p);

	INIT_LIST_HEAD(pages);
}

/*
 * Given an array of items in userspace, return a list of pages
 * containing the data.  If copying fails, either because of memory
 * allocation failure or a problem reading user memory, return an
 * error code; its up to the caller to dispose of any partial list.
 */
static int gather_array(struct list_head *pagelist,
			unsigned nelem, size_t size,
			const void __user *data)
{
	unsigned pageidx;
	void *pagedata;
	int ret;

	if (size > PAGE_SIZE)
		return 0;

	pageidx = PAGE_SIZE;
	pagedata = NULL;	/* quiet, gcc */
	while (nelem--) {
		if (pageidx > PAGE_SIZE-size) {
			struct page *page = alloc_page(GFP_KERNEL);

			ret = -ENOMEM;
			if (page == NULL)
				goto fail;

			pagedata = page_address(page);

			list_add_tail(&page->lru, pagelist);
			pageidx = 0;
		}

		ret = -EFAULT;
		if (copy_from_user(pagedata + pageidx, data, size))
			goto fail;

		data += size;
		pageidx += size;
	}

	ret = 0;

fail:
	return ret;
}

/*
 * Call function "fn" on each element of the array fragmented
 * over a list of pages.
 */
static int traverse_pages(unsigned nelem, size_t size,
			  struct list_head *pos,
			  int (*fn)(void *data, void *state),
			  void *state)
{
	void *pagedata;
	unsigned pageidx;
	int ret = 0;

	BUG_ON(size > PAGE_SIZE);

	pageidx = PAGE_SIZE;
	pagedata = NULL;	/* hush, gcc */

	while (nelem--) {
		if (pageidx > PAGE_SIZE-size) {
			struct page *page;
			pos = pos->next;
			page = list_entry(pos, struct page, lru);
			pagedata = page_address(page);
			pageidx = 0;
		}

		ret = (*fn)(pagedata + pageidx, state);
		if (ret)
			break;
		pageidx += size;
	}

	return ret;
}

/*
 * Similar to traverse_pages, but use each page as a "block" of
 * data to be processed as one unit.
 */
static int traverse_pages_block(unsigned nelem, size_t size,
				struct list_head *pos,
				int (*fn)(void *data, int nr, void *state),
				void *state)
{
	void *pagedata;
	unsigned pageidx;
	int ret = 0;

	BUG_ON(size > PAGE_SIZE);

	pageidx = PAGE_SIZE;

	while (nelem) {
		int nr = (PAGE_SIZE/size);
		struct page *page;
		if (nr > nelem)
			nr = nelem;
		pos = pos->next;
		page = list_entry(pos, struct page, lru);
		pagedata = page_address(page);
		ret = (*fn)(pagedata, nr, state);
		if (ret)
			break;
		nelem -= nr;
	}

	return ret;
}

struct mmap_gfn_state {
	unsigned long va;
	struct vm_area_struct *vma;
	domid_t domain;
};

static int mmap_gfn_range(void *data, void *state)
{
	struct privcmd_mmap_entry *msg = data;
	struct mmap_gfn_state *st = state;
	struct vm_area_struct *vma = st->vma;
	int rc;

	/* Do not allow range to wrap the address space. */
	if ((msg->npages > (LONG_MAX >> PAGE_SHIFT)) ||
	    ((unsigned long)(msg->npages << PAGE_SHIFT) >= -st->va))
		return -EINVAL;

	/* Range chunks must be contiguous in va space. */
	if ((msg->va != st->va) ||
	    ((msg->va+(msg->npages<<PAGE_SHIFT)) > vma->vm_end))
		return -EINVAL;

	rc = xen_remap_domain_gfn_range(vma,
					msg->va & PAGE_MASK,
					msg->mfn, msg->npages,
					vma->vm_page_prot,
					st->domain, NULL);
	if (rc < 0)
		return rc;

	st->va += msg->npages << PAGE_SHIFT;

	return 0;
}

static long privcmd_ioctl_mmap(struct file *file, void __user *udata)
{
	struct privcmd_data *data = file->private_data;
	struct privcmd_mmap mmapcmd;
	struct mm_struct *mm = current->mm;
	struct vm_area_struct *vma;
	int rc;
	LIST_HEAD(pagelist);
	struct mmap_gfn_state state;

	/* We only support privcmd_ioctl_mmap_batch for auto translated. */
	if (xen_feature(XENFEAT_auto_translated_physmap))
		return -ENOSYS;

	if (copy_from_user(&mmapcmd, udata, sizeof(mmapcmd)))
		return -EFAULT;

	/* If restriction is in place, check the domid matches */
	if (data->domid != DOMID_INVALID && data->domid != mmapcmd.dom)
		return -EPERM;

	rc = gather_array(&pagelist,
			  mmapcmd.num, sizeof(struct privcmd_mmap_entry),
			  mmapcmd.entry);

	if (rc || list_empty(&pagelist))
		goto out;

	down_write(&mm->mmap_sem);

	{
		struct page *page = list_first_entry(&pagelist,
						     struct page, lru);
		struct privcmd_mmap_entry *msg = page_address(page);

		vma = find_vma(mm, msg->va);
		rc = -EINVAL;

		if (!vma || (msg->va != vma->vm_start) || vma->vm_private_data)
			goto out_up;
		vma->vm_private_data = PRIV_VMA_LOCKED;
	}

	state.va = vma->vm_start;
	state.vma = vma;
	state.domain = mmapcmd.dom;

	rc = traverse_pages(mmapcmd.num, sizeof(struct privcmd_mmap_entry),
			    &pagelist,
			    mmap_gfn_range, &state);


out_up:
	up_write(&mm->mmap_sem);

out:
	free_page_list(&pagelist);

	return rc;
}

struct mmap_batch_state {
	domid_t domain;
	unsigned long va;
	struct vm_area_struct *vma;
	int index;
	/* A tristate:
	 *      0 for no errors
	 *      1 if at least one error has happened (and no
	 *          -ENOENT errors have happened)
	 *      -ENOENT if at least 1 -ENOENT has happened.
	 */
	int global_error;
	int version;

	/* User-space gfn array to store errors in the second pass for V1. */
	xen_pfn_t __user *user_gfn;
	/* User-space int array to store errors in the second pass for V2. */
	int __user *user_err;
};

/* auto translated dom0 note: if domU being created is PV, then gfn is
 * mfn(addr on bus). If it's auto xlated, then gfn is pfn (input to HAP).
 */
static int mmap_batch_fn(void *data, int nr, void *state)
{
	xen_pfn_t *gfnp = data;
	struct mmap_batch_state *st = state;
	struct vm_area_struct *vma = st->vma;
	struct page **pages = vma->vm_private_data;
	struct page **cur_pages = NULL;
	int ret;

	if (xen_feature(XENFEAT_auto_translated_physmap))
		cur_pages = &pages[st->index];

	BUG_ON(nr < 0);
	ret = xen_remap_domain_gfn_array(st->vma, st->va & PAGE_MASK, gfnp, nr,
					 (int *)gfnp, st->vma->vm_page_prot,
					 st->domain, cur_pages);

	/* Adjust the global_error? */
	if (ret != nr) {
		if (ret == -ENOENT)
			st->global_error = -ENOENT;
		else {
			/* Record that at least one error has happened. */
			if (st->global_error == 0)
				st->global_error = 1;
		}
	}
	st->va += XEN_PAGE_SIZE * nr;
	st->index += nr / XEN_PFN_PER_PAGE;

	return 0;
}

static int mmap_return_error(int err, struct mmap_batch_state *st)
{
	int ret;

	if (st->version == 1) {
		if (err) {
			xen_pfn_t gfn;

			ret = get_user(gfn, st->user_gfn);
			if (ret < 0)
				return ret;
			/*
			 * V1 encodes the error codes in the 32bit top
			 * nibble of the gfn (with its known
			 * limitations vis-a-vis 64 bit callers).
			 */
			gfn |= (err == -ENOENT) ?
				PRIVCMD_MMAPBATCH_PAGED_ERROR :
				PRIVCMD_MMAPBATCH_MFN_ERROR;
			return __put_user(gfn, st->user_gfn++);
		} else
			st->user_gfn++;
	} else { /* st->version == 2 */
		if (err)
			return __put_user(err, st->user_err++);
		else
			st->user_err++;
	}

	return 0;
}

static int mmap_return_errors(void *data, int nr, void *state)
{
	struct mmap_batch_state *st = state;
	int *errs = data;
	int i;
	int ret;

	for (i = 0; i < nr; i++) {
		ret = mmap_return_error(errs[i], st);
		if (ret < 0)
			return ret;
	}
	return 0;
}

/* Allocate pfns that are then mapped with gfns from foreign domid. Update
 * the vma with the page info to use later.
 * Returns: 0 if success, otherwise -errno
 */
static int alloc_empty_pages(struct vm_area_struct *vma, int numpgs)
{
	int rc;
	struct page **pages;

	pages = kcalloc(numpgs, sizeof(pages[0]), GFP_KERNEL);
	if (pages == NULL)
		return -ENOMEM;

	rc = alloc_xenballooned_pages(numpgs, pages);
	if (rc != 0) {
		pr_warn("%s Could not alloc %d pfns rc:%d\n", __func__,
			numpgs, rc);
		kfree(pages);
		return -ENOMEM;
	}
	BUG_ON(vma->vm_private_data != NULL);
	vma->vm_private_data = pages;

	return 0;
}

static const struct vm_operations_struct privcmd_vm_ops;

static long privcmd_ioctl_mmap_batch(
	struct file *file, void __user *udata, int version)
{
	struct privcmd_data *data = file->private_data;
	int ret;
	struct privcmd_mmapbatch_v2 m;
	struct mm_struct *mm = current->mm;
	struct vm_area_struct *vma;
	unsigned long nr_pages;
	LIST_HEAD(pagelist);
	struct mmap_batch_state state;

	switch (version) {
	case 1:
		if (copy_from_user(&m, udata, sizeof(struct privcmd_mmapbatch)))
			return -EFAULT;
		/* Returns per-frame error in m.arr. */
		m.err = NULL;
		if (!access_ok(VERIFY_WRITE, m.arr, m.num * sizeof(*m.arr)))
			return -EFAULT;
		break;
	case 2:
		if (copy_from_user(&m, udata, sizeof(struct privcmd_mmapbatch_v2)))
			return -EFAULT;
		/* Returns per-frame error code in m.err. */
		if (!access_ok(VERIFY_WRITE, m.err, m.num * (sizeof(*m.err))))
			return -EFAULT;
		break;
	default:
		return -EINVAL;
	}

	/* If restriction is in place, check the domid matches */
	if (data->domid != DOMID_INVALID && data->domid != m.dom)
		return -EPERM;

	nr_pages = DIV_ROUND_UP(m.num, XEN_PFN_PER_PAGE);
	if ((m.num <= 0) || (nr_pages > (LONG_MAX >> PAGE_SHIFT)))
		return -EINVAL;

	ret = gather_array(&pagelist, m.num, sizeof(xen_pfn_t), m.arr);

	if (ret)
		goto out;
	if (list_empty(&pagelist)) {
		ret = -EINVAL;
		goto out;
	}

	if (version == 2) {
		/* Zero error array now to only copy back actual errors. */
		if (clear_user(m.err, sizeof(int) * m.num)) {
			ret = -EFAULT;
			goto out;
		}
	}

	down_write(&mm->mmap_sem);

	vma = find_vma(mm, m.addr);
	if (!vma ||
	    vma->vm_ops != &privcmd_vm_ops) {
		ret = -EINVAL;
		goto out_unlock;
	}

	/*
	 * Caller must either:
	 *
	 * Map the whole VMA range, which will also allocate all the
	 * pages required for the auto_translated_physmap case.
	 *
	 * Or
	 *
	 * Map unmapped holes left from a previous map attempt (e.g.,
	 * because those foreign frames were previously paged out).
	 */
	if (vma->vm_private_data == NULL) {
		if (m.addr != vma->vm_start ||
		    m.addr + (nr_pages << PAGE_SHIFT) != vma->vm_end) {
			ret = -EINVAL;
			goto out_unlock;
		}
		if (xen_feature(XENFEAT_auto_translated_physmap)) {
			ret = alloc_empty_pages(vma, nr_pages);
			if (ret < 0)
				goto out_unlock;
		} else
			vma->vm_private_data = PRIV_VMA_LOCKED;
	} else {
		if (m.addr < vma->vm_start ||
		    m.addr + (nr_pages << PAGE_SHIFT) > vma->vm_end) {
			ret = -EINVAL;
			goto out_unlock;
		}
		if (privcmd_vma_range_is_mapped(vma, m.addr, nr_pages)) {
			ret = -EINVAL;
			goto out_unlock;
		}
	}

	state.domain        = m.dom;
	state.vma           = vma;
	state.va            = m.addr;
	state.index         = 0;
	state.global_error  = 0;
	state.version       = version;

	BUILD_BUG_ON(((PAGE_SIZE / sizeof(xen_pfn_t)) % XEN_PFN_PER_PAGE) != 0);
	/* mmap_batch_fn guarantees ret == 0 */
	BUG_ON(traverse_pages_block(m.num, sizeof(xen_pfn_t),
				    &pagelist, mmap_batch_fn, &state));

	up_write(&mm->mmap_sem);

	if (state.global_error) {
		/* Write back errors in second pass. */
		state.user_gfn = (xen_pfn_t *)m.arr;
		state.user_err = m.err;
		ret = traverse_pages_block(m.num, sizeof(xen_pfn_t),
					   &pagelist, mmap_return_errors, &state);
	} else
		ret = 0;

	/* If we have not had any EFAULT-like global errors then set the global
	 * error to -ENOENT if necessary. */
	if ((ret == 0) && (state.global_error == -ENOENT))
		ret = -ENOENT;

out:
	free_page_list(&pagelist);
	return ret;

out_unlock:
	up_write(&mm->mmap_sem);
	goto out;
}

static int lock_pages(
	struct privcmd_dm_op_buf kbufs[], unsigned int num,
	struct page *pages[], unsigned int nr_pages)
{
	unsigned int i;

	for (i = 0; i < num; i++) {
		unsigned int requested;
		int pinned;

		requested = DIV_ROUND_UP(
			offset_in_page(kbufs[i].uptr) + kbufs[i].size,
			PAGE_SIZE);
		if (requested > nr_pages)
			return -ENOSPC;

		pinned = get_user_pages_fast(
			(unsigned long) kbufs[i].uptr,
			requested, FOLL_WRITE, pages);
		if (pinned < 0)
			return pinned;

		nr_pages -= pinned;
		pages += pinned;
	}

	return 0;
}

static void unlock_pages(struct page *pages[], unsigned int nr_pages)
{
	unsigned int i;

	if (!pages)
		return;

	for (i = 0; i < nr_pages; i++) {
		if (pages[i])
			put_page(pages[i]);
	}
}

static long privcmd_ioctl_dm_op(struct file *file, void __user *udata)
{
	struct privcmd_data *data = file->private_data;
	struct privcmd_dm_op kdata;
	struct privcmd_dm_op_buf *kbufs;
	unsigned int nr_pages = 0;
	struct page **pages = NULL;
	struct xen_dm_op_buf *xbufs = NULL;
	unsigned int i;
	long rc;

	if (copy_from_user(&kdata, udata, sizeof(kdata)))
		return -EFAULT;

	/* If restriction is in place, check the domid matches */
	if (data->domid != DOMID_INVALID && data->domid != kdata.dom)
		return -EPERM;

	if (kdata.num == 0)
		return 0;

	if (kdata.num > privcmd_dm_op_max_num)
		return -E2BIG;

	kbufs = kcalloc(kdata.num, sizeof(*kbufs), GFP_KERNEL);
	if (!kbufs)
		return -ENOMEM;

	if (copy_from_user(kbufs, kdata.ubufs,
			   sizeof(*kbufs) * kdata.num)) {
		rc = -EFAULT;
		goto out;
	}

	for (i = 0; i < kdata.num; i++) {
		if (kbufs[i].size > privcmd_dm_op_buf_max_size) {
			rc = -E2BIG;
			goto out;
		}

		if (!access_ok(VERIFY_WRITE, kbufs[i].uptr,
			       kbufs[i].size)) {
			rc = -EFAULT;
			goto out;
		}

		nr_pages += DIV_ROUND_UP(
			offset_in_page(kbufs[i].uptr) + kbufs[i].size,
			PAGE_SIZE);
	}

	pages = kcalloc(nr_pages, sizeof(*pages), GFP_KERNEL);
	if (!pages) {
		rc = -ENOMEM;
		goto out;
	}

	xbufs = kcalloc(kdata.num, sizeof(*xbufs), GFP_KERNEL);
	if (!xbufs) {
		rc = -ENOMEM;
		goto out;
	}

	rc = lock_pages(kbufs, kdata.num, pages, nr_pages);
	if (rc)
		goto out;

	for (i = 0; i < kdata.num; i++) {
		set_xen_guest_handle(xbufs[i].h, kbufs[i].uptr);
		xbufs[i].size = kbufs[i].size;
	}

	xen_preemptible_hcall_begin();
	rc = HYPERVISOR_dm_op(kdata.dom, kdata.num, xbufs);
	xen_preemptible_hcall_end();

out:
	unlock_pages(pages, nr_pages);
	kfree(xbufs);
	kfree(pages);
	kfree(kbufs);

	return rc;
}

static long privcmd_ioctl_restrict(struct file *file, void __user *udata)
{
	struct privcmd_data *data = file->private_data;
	domid_t dom;

	if (copy_from_user(&dom, udata, sizeof(dom)))
		return -EFAULT;

	/* Set restriction to the specified domain, or check it matches */
	if (data->domid == DOMID_INVALID)
		data->domid = dom;
	else if (data->domid != dom)
		return -EINVAL;

	return 0;
}

static long privcmd_ioctl(struct file *file,
			  unsigned int cmd, unsigned long data)
{
	int ret = -ENOTTY;
	void __user *udata = (void __user *) data;

	switch (cmd) {
	case IOCTL_PRIVCMD_HYPERCALL:
		ret = privcmd_ioctl_hypercall(file, udata);
		break;

	case IOCTL_PRIVCMD_MMAP:
		ret = privcmd_ioctl_mmap(file, udata);
		break;

	case IOCTL_PRIVCMD_MMAPBATCH:
		ret = privcmd_ioctl_mmap_batch(file, udata, 1);
		break;

	case IOCTL_PRIVCMD_MMAPBATCH_V2:
		ret = privcmd_ioctl_mmap_batch(file, udata, 2);
		break;

	case IOCTL_PRIVCMD_DM_OP:
		ret = privcmd_ioctl_dm_op(file, udata);
		break;

	case IOCTL_PRIVCMD_RESTRICT:
		ret = privcmd_ioctl_restrict(file, udata);
		break;

	default:
		break;
	}

	return ret;
}

static int privcmd_open(struct inode *ino, struct file *file)
{
	struct privcmd_data *data = kzalloc(sizeof(*data), GFP_KERNEL);

	if (!data)
		return -ENOMEM;

	/* DOMID_INVALID implies no restriction */
	data->domid = DOMID_INVALID;

	file->private_data = data;
	return 0;
}

static int privcmd_release(struct inode *ino, struct file *file)
{
	struct privcmd_data *data = file->private_data;

	kfree(data);
	return 0;
}

static void privcmd_close(struct vm_area_struct *vma)
{
	struct page **pages = vma->vm_private_data;
	int numpgs = vma_pages(vma);
	int numgfns = (vma->vm_end - vma->vm_start) >> XEN_PAGE_SHIFT;
	int rc;

	if (!xen_feature(XENFEAT_auto_translated_physmap) || !numpgs || !pages)
		return;

	rc = xen_unmap_domain_gfn_range(vma, numgfns, pages);
	if (rc == 0)
		free_xenballooned_pages(numpgs, pages);
	else
		pr_crit("unable to unmap MFN range: leaking %d pages. rc=%d\n",
			numpgs, rc);
	kfree(pages);
}

static int privcmd_fault(struct vm_fault *vmf)
{
	printk(KERN_DEBUG "privcmd_fault: vma=%p %lx-%lx, pgoff=%lx, uv=%p\n",
	       vmf->vma, vmf->vma->vm_start, vmf->vma->vm_end,
	       vmf->pgoff, (void *)vmf->address);

	return VM_FAULT_SIGBUS;
}

static const struct vm_operations_struct privcmd_vm_ops = {
	.close = privcmd_close,
	.fault = privcmd_fault
};

static int privcmd_mmap(struct file *file, struct vm_area_struct *vma)
{
	/* DONTCOPY is essential for Xen because copy_page_range doesn't know
	 * how to recreate these mappings */
	vma->vm_flags |= VM_IO | VM_PFNMAP | VM_DONTCOPY |
			 VM_DONTEXPAND | VM_DONTDUMP;
	vma->vm_ops = &privcmd_vm_ops;
	vma->vm_private_data = NULL;

	return 0;
}

/*
 * For MMAPBATCH*. This allows asserting the singleshot mapping
 * on a per pfn/pte basis. Mapping calls that fail with ENOENT
 * can be then retried until success.
 */
static int is_mapped_fn(pte_t *pte, struct page *pmd_page,
	                unsigned long addr, void *data)
{
	return pte_none(*pte) ? 0 : -EBUSY;
}

static int privcmd_vma_range_is_mapped(
	           struct vm_area_struct *vma,
	           unsigned long addr,
	           unsigned long nr_pages)
{
	return apply_to_page_range(vma->vm_mm, addr, nr_pages << PAGE_SHIFT,
				   is_mapped_fn, NULL) != 0;
}

const struct file_operations xen_privcmd_fops = {
	.owner = THIS_MODULE,
	.unlocked_ioctl = privcmd_ioctl,
	.open = privcmd_open,
	.release = privcmd_release,
	.mmap = privcmd_mmap,
};
EXPORT_SYMBOL_GPL(xen_privcmd_fops);

static struct miscdevice privcmd_dev = {
	.minor = MISC_DYNAMIC_MINOR,
	.name = "xen/privcmd",
	.fops = &xen_privcmd_fops,
};

static int __init privcmd_init(void)
{
	int err;

	if (!xen_domain())
		return -ENODEV;

	err = misc_register(&privcmd_dev);
	if (err != 0) {
		pr_err("Could not register Xen privcmd device\n");
		return err;
	}
	return 0;
}

static void __exit privcmd_exit(void)
{
	misc_deregister(&privcmd_dev);
}

module_init(privcmd_init);
module_exit(privcmd_exit);