summaryrefslogtreecommitdiffstats
path: root/tools/testing/selftests/kvm/set_memory_region_test.c
blob: 06b43ed23580b67c060aeaadea11b06641a629c3 (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
// SPDX-License-Identifier: GPL-2.0
#define _GNU_SOURCE /* for program_invocation_short_name */
#include <fcntl.h>
#include <pthread.h>
#include <sched.h>
#include <semaphore.h>
#include <signal.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <sys/ioctl.h>
#include <sys/mman.h>

#include <linux/compiler.h>

#include <test_util.h>
#include <kvm_util.h>
#include <processor.h>

/*
 * s390x needs at least 1MB alignment, and the x86_64 MOVE/DELETE tests need a
 * 2MB sized and aligned region so that the initial region corresponds to
 * exactly one large page.
 */
#define MEM_REGION_SIZE		0x200000

#ifdef __x86_64__
/*
 * Somewhat arbitrary location and slot, intended to not overlap anything.
 */
#define MEM_REGION_GPA		0xc0000000
#define MEM_REGION_SLOT		10

static const uint64_t MMIO_VAL = 0xbeefull;

extern const uint64_t final_rip_start;
extern const uint64_t final_rip_end;

static sem_t vcpu_ready;

static inline uint64_t guest_spin_on_val(uint64_t spin_val)
{
	uint64_t val;

	do {
		val = READ_ONCE(*((uint64_t *)MEM_REGION_GPA));
	} while (val == spin_val);

	GUEST_SYNC(0);
	return val;
}

static void *vcpu_worker(void *data)
{
	struct kvm_vcpu *vcpu = data;
	struct kvm_run *run = vcpu->run;
	struct ucall uc;
	uint64_t cmd;

	/*
	 * Loop until the guest is done.  Re-enter the guest on all MMIO exits,
	 * which will occur if the guest attempts to access a memslot after it
	 * has been deleted or while it is being moved .
	 */
	while (1) {
		vcpu_run(vcpu);

		if (run->exit_reason == KVM_EXIT_IO) {
			cmd = get_ucall(vcpu, &uc);
			if (cmd != UCALL_SYNC)
				break;

			sem_post(&vcpu_ready);
			continue;
		}

		if (run->exit_reason != KVM_EXIT_MMIO)
			break;

		TEST_ASSERT(!run->mmio.is_write, "Unexpected exit mmio write");
		TEST_ASSERT(run->mmio.len == 8,
			    "Unexpected exit mmio size = %u", run->mmio.len);

		TEST_ASSERT(run->mmio.phys_addr == MEM_REGION_GPA,
			    "Unexpected exit mmio address = 0x%llx",
			    run->mmio.phys_addr);
		memcpy(run->mmio.data, &MMIO_VAL, 8);
	}

	if (run->exit_reason == KVM_EXIT_IO && cmd == UCALL_ABORT)
		REPORT_GUEST_ASSERT(uc);

	return NULL;
}

static void wait_for_vcpu(void)
{
	struct timespec ts;

	TEST_ASSERT(!clock_gettime(CLOCK_REALTIME, &ts),
		    "clock_gettime() failed: %d", errno);

	ts.tv_sec += 2;
	TEST_ASSERT(!sem_timedwait(&vcpu_ready, &ts),
		    "sem_timedwait() failed: %d", errno);

	/* Wait for the vCPU thread to reenter the guest. */
	usleep(100000);
}

static struct kvm_vm *spawn_vm(struct kvm_vcpu **vcpu, pthread_t *vcpu_thread,
			       void *guest_code)
{
	struct kvm_vm *vm;
	uint64_t *hva;
	uint64_t gpa;

	vm = vm_create_with_one_vcpu(vcpu, guest_code);

	vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS_THP,
				    MEM_REGION_GPA, MEM_REGION_SLOT,
				    MEM_REGION_SIZE / getpagesize(), 0);

	/*
	 * Allocate and map two pages so that the GPA accessed by guest_code()
	 * stays valid across the memslot move.
	 */
	gpa = vm_phy_pages_alloc(vm, 2, MEM_REGION_GPA, MEM_REGION_SLOT);
	TEST_ASSERT(gpa == MEM_REGION_GPA, "Failed vm_phy_pages_alloc\n");

	virt_map(vm, MEM_REGION_GPA, MEM_REGION_GPA, 2);

	/* Ditto for the host mapping so that both pages can be zeroed. */
	hva = addr_gpa2hva(vm, MEM_REGION_GPA);
	memset(hva, 0, 2 * 4096);

	pthread_create(vcpu_thread, NULL, vcpu_worker, *vcpu);

	/* Ensure the guest thread is spun up. */
	wait_for_vcpu();

	return vm;
}


static void guest_code_move_memory_region(void)
{
	uint64_t val;

	GUEST_SYNC(0);

	/*
	 * Spin until the memory region starts getting moved to a
	 * misaligned address.
	 * Every region move may or may not trigger MMIO, as the
	 * window where the memslot is invalid is usually quite small.
	 */
	val = guest_spin_on_val(0);
	__GUEST_ASSERT(val == 1 || val == MMIO_VAL,
		       "Expected '1' or MMIO ('%lx'), got '%lx'", MMIO_VAL, val);

	/* Spin until the misaligning memory region move completes. */
	val = guest_spin_on_val(MMIO_VAL);
	__GUEST_ASSERT(val == 1 || val == 0,
		       "Expected '0' or '1' (no MMIO), got '%lx'", val);

	/* Spin until the memory region starts to get re-aligned. */
	val = guest_spin_on_val(0);
	__GUEST_ASSERT(val == 1 || val == MMIO_VAL,
		       "Expected '1' or MMIO ('%lx'), got '%lx'", MMIO_VAL, val);

	/* Spin until the re-aligning memory region move completes. */
	val = guest_spin_on_val(MMIO_VAL);
	GUEST_ASSERT_EQ(val, 1);

	GUEST_DONE();
}

static void test_move_memory_region(void)
{
	pthread_t vcpu_thread;
	struct kvm_vcpu *vcpu;
	struct kvm_vm *vm;
	uint64_t *hva;

	vm = spawn_vm(&vcpu, &vcpu_thread, guest_code_move_memory_region);

	hva = addr_gpa2hva(vm, MEM_REGION_GPA);

	/*
	 * Shift the region's base GPA.  The guest should not see "2" as the
	 * hva->gpa translation is misaligned, i.e. the guest is accessing a
	 * different host pfn.
	 */
	vm_mem_region_move(vm, MEM_REGION_SLOT, MEM_REGION_GPA - 4096);
	WRITE_ONCE(*hva, 2);

	/*
	 * The guest _might_ see an invalid memslot and trigger MMIO, but it's
	 * a tiny window.  Spin and defer the sync until the memslot is
	 * restored and guest behavior is once again deterministic.
	 */
	usleep(100000);

	/*
	 * Note, value in memory needs to be changed *before* restoring the
	 * memslot, else the guest could race the update and see "2".
	 */
	WRITE_ONCE(*hva, 1);

	/* Restore the original base, the guest should see "1". */
	vm_mem_region_move(vm, MEM_REGION_SLOT, MEM_REGION_GPA);
	wait_for_vcpu();
	/* Defered sync from when the memslot was misaligned (above). */
	wait_for_vcpu();

	pthread_join(vcpu_thread, NULL);

	kvm_vm_free(vm);
}

static void guest_code_delete_memory_region(void)
{
	uint64_t val;

	GUEST_SYNC(0);

	/* Spin until the memory region is deleted. */
	val = guest_spin_on_val(0);
	GUEST_ASSERT_EQ(val, MMIO_VAL);

	/* Spin until the memory region is recreated. */
	val = guest_spin_on_val(MMIO_VAL);
	GUEST_ASSERT_EQ(val, 0);

	/* Spin until the memory region is deleted. */
	val = guest_spin_on_val(0);
	GUEST_ASSERT_EQ(val, MMIO_VAL);

	asm("1:\n\t"
	    ".pushsection .rodata\n\t"
	    ".global final_rip_start\n\t"
	    "final_rip_start: .quad 1b\n\t"
	    ".popsection");

	/* Spin indefinitely (until the code memslot is deleted). */
	guest_spin_on_val(MMIO_VAL);

	asm("1:\n\t"
	    ".pushsection .rodata\n\t"
	    ".global final_rip_end\n\t"
	    "final_rip_end: .quad 1b\n\t"
	    ".popsection");

	GUEST_ASSERT(0);
}

static void test_delete_memory_region(void)
{
	pthread_t vcpu_thread;
	struct kvm_vcpu *vcpu;
	struct kvm_regs regs;
	struct kvm_run *run;
	struct kvm_vm *vm;

	vm = spawn_vm(&vcpu, &vcpu_thread, guest_code_delete_memory_region);

	/* Delete the memory region, the guest should not die. */
	vm_mem_region_delete(vm, MEM_REGION_SLOT);
	wait_for_vcpu();

	/* Recreate the memory region.  The guest should see "0". */
	vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS_THP,
				    MEM_REGION_GPA, MEM_REGION_SLOT,
				    MEM_REGION_SIZE / getpagesize(), 0);
	wait_for_vcpu();

	/* Delete the region again so that there's only one memslot left. */
	vm_mem_region_delete(vm, MEM_REGION_SLOT);
	wait_for_vcpu();

	/*
	 * Delete the primary memslot.  This should cause an emulation error or
	 * shutdown due to the page tables getting nuked.
	 */
	vm_mem_region_delete(vm, 0);

	pthread_join(vcpu_thread, NULL);

	run = vcpu->run;

	TEST_ASSERT(run->exit_reason == KVM_EXIT_SHUTDOWN ||
		    run->exit_reason == KVM_EXIT_INTERNAL_ERROR,
		    "Unexpected exit reason = %d", run->exit_reason);

	vcpu_regs_get(vcpu, &regs);

	/*
	 * On AMD, after KVM_EXIT_SHUTDOWN the VMCB has been reinitialized already,
	 * so the instruction pointer would point to the reset vector.
	 */
	if (run->exit_reason == KVM_EXIT_INTERNAL_ERROR)
		TEST_ASSERT(regs.rip >= final_rip_start &&
			    regs.rip < final_rip_end,
			    "Bad rip, expected 0x%lx - 0x%lx, got 0x%llx",
			    final_rip_start, final_rip_end, regs.rip);

	kvm_vm_free(vm);
}

static void test_zero_memory_regions(void)
{
	struct kvm_vcpu *vcpu;
	struct kvm_vm *vm;

	pr_info("Testing KVM_RUN with zero added memory regions\n");

	vm = vm_create_barebones();
	vcpu = __vm_vcpu_add(vm, 0);

	vm_ioctl(vm, KVM_SET_NR_MMU_PAGES, (void *)64ul);
	vcpu_run(vcpu);
	TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_INTERNAL_ERROR);

	kvm_vm_free(vm);
}
#endif /* __x86_64__ */

static void test_invalid_memory_region_flags(void)
{
	uint32_t supported_flags = KVM_MEM_LOG_DIRTY_PAGES;
	const uint32_t v2_only_flags = KVM_MEM_GUEST_MEMFD;
	struct kvm_vm *vm;
	int r, i;

#if defined __aarch64__ || defined __x86_64__
	supported_flags |= KVM_MEM_READONLY;
#endif

#ifdef __x86_64__
	if (kvm_check_cap(KVM_CAP_VM_TYPES) & BIT(KVM_X86_SW_PROTECTED_VM))
		vm = vm_create_barebones_protected_vm();
	else
#endif
		vm = vm_create_barebones();

	if (kvm_check_cap(KVM_CAP_MEMORY_ATTRIBUTES) & KVM_MEMORY_ATTRIBUTE_PRIVATE)
		supported_flags |= KVM_MEM_GUEST_MEMFD;

	for (i = 0; i < 32; i++) {
		if ((supported_flags & BIT(i)) && !(v2_only_flags & BIT(i)))
			continue;

		r = __vm_set_user_memory_region(vm, 0, BIT(i),
						0, MEM_REGION_SIZE, NULL);

		TEST_ASSERT(r && errno == EINVAL,
			    "KVM_SET_USER_MEMORY_REGION should have failed on v2 only flag 0x%lx", BIT(i));

		if (supported_flags & BIT(i))
			continue;

		r = __vm_set_user_memory_region2(vm, 0, BIT(i),
						 0, MEM_REGION_SIZE, NULL, 0, 0);
		TEST_ASSERT(r && errno == EINVAL,
			    "KVM_SET_USER_MEMORY_REGION2 should have failed on unsupported flag 0x%lx", BIT(i));
	}

	if (supported_flags & KVM_MEM_GUEST_MEMFD) {
		int guest_memfd = vm_create_guest_memfd(vm, MEM_REGION_SIZE, 0);

		r = __vm_set_user_memory_region2(vm, 0,
						 KVM_MEM_LOG_DIRTY_PAGES | KVM_MEM_GUEST_MEMFD,
						 0, MEM_REGION_SIZE, NULL, guest_memfd, 0);
		TEST_ASSERT(r && errno == EINVAL,
			    "KVM_SET_USER_MEMORY_REGION2 should have failed, dirty logging private memory is unsupported");

		r = __vm_set_user_memory_region2(vm, 0,
						 KVM_MEM_READONLY | KVM_MEM_GUEST_MEMFD,
						 0, MEM_REGION_SIZE, NULL, guest_memfd, 0);
		TEST_ASSERT(r && errno == EINVAL,
			    "KVM_SET_USER_MEMORY_REGION2 should have failed, read-only GUEST_MEMFD memslots are unsupported");

		close(guest_memfd);
	}
}

/*
 * Test it can be added memory slots up to KVM_CAP_NR_MEMSLOTS, then any
 * tentative to add further slots should fail.
 */
static void test_add_max_memory_regions(void)
{
	int ret;
	struct kvm_vm *vm;
	uint32_t max_mem_slots;
	uint32_t slot;
	void *mem, *mem_aligned, *mem_extra;
	size_t alignment;

#ifdef __s390x__
	/* On s390x, the host address must be aligned to 1M (due to PGSTEs) */
	alignment = 0x100000;
#else
	alignment = 1;
#endif

	max_mem_slots = kvm_check_cap(KVM_CAP_NR_MEMSLOTS);
	TEST_ASSERT(max_mem_slots > 0,
		    "KVM_CAP_NR_MEMSLOTS should be greater than 0");
	pr_info("Allowed number of memory slots: %i\n", max_mem_slots);

	vm = vm_create_barebones();

	/* Check it can be added memory slots up to the maximum allowed */
	pr_info("Adding slots 0..%i, each memory region with %dK size\n",
		(max_mem_slots - 1), MEM_REGION_SIZE >> 10);

	mem = mmap(NULL, (size_t)max_mem_slots * MEM_REGION_SIZE + alignment,
		   PROT_READ | PROT_WRITE,
		   MAP_PRIVATE | MAP_ANONYMOUS | MAP_NORESERVE, -1, 0);
	TEST_ASSERT(mem != MAP_FAILED, "Failed to mmap() host");
	mem_aligned = (void *)(((size_t) mem + alignment - 1) & ~(alignment - 1));

	for (slot = 0; slot < max_mem_slots; slot++)
		vm_set_user_memory_region(vm, slot, 0,
					  ((uint64_t)slot * MEM_REGION_SIZE),
					  MEM_REGION_SIZE,
					  mem_aligned + (uint64_t)slot * MEM_REGION_SIZE);

	/* Check it cannot be added memory slots beyond the limit */
	mem_extra = mmap(NULL, MEM_REGION_SIZE, PROT_READ | PROT_WRITE,
			 MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
	TEST_ASSERT(mem_extra != MAP_FAILED, "Failed to mmap() host");

	ret = __vm_set_user_memory_region(vm, max_mem_slots, 0,
					  (uint64_t)max_mem_slots * MEM_REGION_SIZE,
					  MEM_REGION_SIZE, mem_extra);
	TEST_ASSERT(ret == -1 && errno == EINVAL,
		    "Adding one more memory slot should fail with EINVAL");

	munmap(mem, (size_t)max_mem_slots * MEM_REGION_SIZE + alignment);
	munmap(mem_extra, MEM_REGION_SIZE);
	kvm_vm_free(vm);
}


#ifdef __x86_64__
static void test_invalid_guest_memfd(struct kvm_vm *vm, int memfd,
				     size_t offset, const char *msg)
{
	int r = __vm_set_user_memory_region2(vm, MEM_REGION_SLOT, KVM_MEM_GUEST_MEMFD,
					     MEM_REGION_GPA, MEM_REGION_SIZE,
					     0, memfd, offset);
	TEST_ASSERT(r == -1 && errno == EINVAL, "%s", msg);
}

static void test_add_private_memory_region(void)
{
	struct kvm_vm *vm, *vm2;
	int memfd, i;

	pr_info("Testing ADD of KVM_MEM_GUEST_MEMFD memory regions\n");

	vm = vm_create_barebones_protected_vm();

	test_invalid_guest_memfd(vm, vm->kvm_fd, 0, "KVM fd should fail");
	test_invalid_guest_memfd(vm, vm->fd, 0, "VM's fd should fail");

	memfd = kvm_memfd_alloc(MEM_REGION_SIZE, false);
	test_invalid_guest_memfd(vm, memfd, 0, "Regular memfd() should fail");
	close(memfd);

	vm2 = vm_create_barebones_protected_vm();
	memfd = vm_create_guest_memfd(vm2, MEM_REGION_SIZE, 0);
	test_invalid_guest_memfd(vm, memfd, 0, "Other VM's guest_memfd() should fail");

	vm_set_user_memory_region2(vm2, MEM_REGION_SLOT, KVM_MEM_GUEST_MEMFD,
				   MEM_REGION_GPA, MEM_REGION_SIZE, 0, memfd, 0);
	close(memfd);
	kvm_vm_free(vm2);

	memfd = vm_create_guest_memfd(vm, MEM_REGION_SIZE, 0);
	for (i = 1; i < PAGE_SIZE; i++)
		test_invalid_guest_memfd(vm, memfd, i, "Unaligned offset should fail");

	vm_set_user_memory_region2(vm, MEM_REGION_SLOT, KVM_MEM_GUEST_MEMFD,
				   MEM_REGION_GPA, MEM_REGION_SIZE, 0, memfd, 0);
	close(memfd);

	kvm_vm_free(vm);
}

static void test_add_overlapping_private_memory_regions(void)
{
	struct kvm_vm *vm;
	int memfd;
	int r;

	pr_info("Testing ADD of overlapping KVM_MEM_GUEST_MEMFD memory regions\n");

	vm = vm_create_barebones_protected_vm();

	memfd = vm_create_guest_memfd(vm, MEM_REGION_SIZE * 4, 0);

	vm_set_user_memory_region2(vm, MEM_REGION_SLOT, KVM_MEM_GUEST_MEMFD,
				   MEM_REGION_GPA, MEM_REGION_SIZE * 2, 0, memfd, 0);

	vm_set_user_memory_region2(vm, MEM_REGION_SLOT + 1, KVM_MEM_GUEST_MEMFD,
				   MEM_REGION_GPA * 2, MEM_REGION_SIZE * 2,
				   0, memfd, MEM_REGION_SIZE * 2);

	/*
	 * Delete the first memslot, and then attempt to recreate it except
	 * with a "bad" offset that results in overlap in the guest_memfd().
	 */
	vm_set_user_memory_region2(vm, MEM_REGION_SLOT, KVM_MEM_GUEST_MEMFD,
				   MEM_REGION_GPA, 0, NULL, -1, 0);

	/* Overlap the front half of the other slot. */
	r = __vm_set_user_memory_region2(vm, MEM_REGION_SLOT, KVM_MEM_GUEST_MEMFD,
					 MEM_REGION_GPA * 2 - MEM_REGION_SIZE,
					 MEM_REGION_SIZE * 2,
					 0, memfd, 0);
	TEST_ASSERT(r == -1 && errno == EEXIST, "%s",
		    "Overlapping guest_memfd() bindings should fail with EEXIST");

	/* And now the back half of the other slot. */
	r = __vm_set_user_memory_region2(vm, MEM_REGION_SLOT, KVM_MEM_GUEST_MEMFD,
					 MEM_REGION_GPA * 2 + MEM_REGION_SIZE,
					 MEM_REGION_SIZE * 2,
					 0, memfd, 0);
	TEST_ASSERT(r == -1 && errno == EEXIST, "%s",
		    "Overlapping guest_memfd() bindings should fail with EEXIST");

	close(memfd);
	kvm_vm_free(vm);
}
#endif

int main(int argc, char *argv[])
{
#ifdef __x86_64__
	int i, loops;

	/*
	 * FIXME: the zero-memslot test fails on aarch64 and s390x because
	 * KVM_RUN fails with ENOEXEC or EFAULT.
	 */
	test_zero_memory_regions();
#endif

	test_invalid_memory_region_flags();

	test_add_max_memory_regions();

#ifdef __x86_64__
	if (kvm_has_cap(KVM_CAP_GUEST_MEMFD) &&
	    (kvm_check_cap(KVM_CAP_VM_TYPES) & BIT(KVM_X86_SW_PROTECTED_VM))) {
		test_add_private_memory_region();
		test_add_overlapping_private_memory_regions();
	} else {
		pr_info("Skipping tests for KVM_MEM_GUEST_MEMFD memory regions\n");
	}

	if (argc > 1)
		loops = atoi_positive("Number of iterations", argv[1]);
	else
		loops = 10;

	pr_info("Testing MOVE of in-use region, %d loops\n", loops);
	for (i = 0; i < loops; i++)
		test_move_memory_region();

	pr_info("Testing DELETE of in-use region, %d loops\n", loops);
	for (i = 0; i < loops; i++)
		test_delete_memory_region();
#endif

	return 0;
}