kvm_util.c 43.3 KB
Newer Older
1
// SPDX-License-Identifier: GPL-2.0-only
2 3 4 5 6 7 8 9 10
/*
 * tools/testing/selftests/kvm/lib/kvm_util.c
 *
 * Copyright (C) 2018, Google LLC.
 */

#include "test_util.h"
#include "kvm_util.h"
#include "kvm_util_internal.h"
11
#include "processor.h"
12 13 14 15 16

#include <assert.h>
#include <sys/mman.h>
#include <sys/types.h>
#include <sys/stat.h>
17
#include <linux/kernel.h>
18 19

#define KVM_UTIL_PGS_PER_HUGEPG 512
20
#define KVM_UTIL_MIN_PFN	2
21 22 23 24 25 26 27 28 29 30

/* Aligns x up to the next multiple of size. Size must be a power of 2. */
static void *align(void *x, size_t size)
{
	size_t mask = size - 1;
	TEST_ASSERT(size != 0 && !(size & (size - 1)),
		    "size not a power of 2: %lu", size);
	return (void *) (((size_t) x + mask) & ~mask);
}

A
Andrew Jones 已提交
31 32
/*
 * Capability
33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52
 *
 * Input Args:
 *   cap - Capability
 *
 * Output Args: None
 *
 * Return:
 *   On success, the Value corresponding to the capability (KVM_CAP_*)
 *   specified by the value of cap.  On failure a TEST_ASSERT failure
 *   is produced.
 *
 * Looks up and returns the value corresponding to the capability
 * (KVM_CAP_*) given by cap.
 */
int kvm_check_cap(long cap)
{
	int ret;
	int kvm_fd;

	kvm_fd = open(KVM_DEV_PATH, O_RDONLY);
53 54
	if (kvm_fd < 0)
		exit(KSFT_SKIP);
55 56 57 58 59 60 61 62 63 64

	ret = ioctl(kvm_fd, KVM_CHECK_EXTENSION, cap);
	TEST_ASSERT(ret != -1, "KVM_CHECK_EXTENSION IOCTL failed,\n"
		"  rc: %i errno: %i", ret, errno);

	close(kvm_fd);

	return ret;
}

65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87
/* VM Enable Capability
 *
 * Input Args:
 *   vm - Virtual Machine
 *   cap - Capability
 *
 * Output Args: None
 *
 * Return: On success, 0. On failure a TEST_ASSERT failure is produced.
 *
 * Enables a capability (KVM_CAP_*) on the VM.
 */
int vm_enable_cap(struct kvm_vm *vm, struct kvm_enable_cap *cap)
{
	int ret;

	ret = ioctl(vm->fd, KVM_ENABLE_CAP, cap);
	TEST_ASSERT(ret == 0, "KVM_ENABLE_CAP IOCTL failed,\n"
		"  rc: %i errno: %i", ret, errno);

	return ret;
}

88
static void vm_open(struct kvm_vm *vm, int perm)
89 90 91 92 93
{
	vm->kvm_fd = open(KVM_DEV_PATH, perm);
	if (vm->kvm_fd < 0)
		exit(KSFT_SKIP);

94 95 96 97 98
	if (!kvm_check_cap(KVM_CAP_IMMEDIATE_EXIT)) {
		fprintf(stderr, "immediate_exit not available, skipping test\n");
		exit(KSFT_SKIP);
	}

99
	vm->fd = ioctl(vm->kvm_fd, KVM_CREATE_VM, vm->type);
100 101 102 103
	TEST_ASSERT(vm->fd >= 0, "KVM_CREATE_VM ioctl failed, "
		"rc: %i errno: %i", vm->fd, errno);
}

104
const char * const vm_guest_mode_string[] = {
105 106 107 108 109 110 111
	"PA-bits:52,  VA-bits:48,  4K pages",
	"PA-bits:52,  VA-bits:48, 64K pages",
	"PA-bits:48,  VA-bits:48,  4K pages",
	"PA-bits:48,  VA-bits:48, 64K pages",
	"PA-bits:40,  VA-bits:48,  4K pages",
	"PA-bits:40,  VA-bits:48, 64K pages",
	"PA-bits:ANY, VA-bits:48,  4K pages",
112
};
113 114
_Static_assert(sizeof(vm_guest_mode_string)/sizeof(char *) == NUM_VM_MODES,
	       "Missing new mode strings?");
115

A
Andrew Jones 已提交
116 117
/*
 * VM Create
118 119
 *
 * Input Args:
120
 *   mode - VM Mode (e.g. VM_MODE_P52V48_4K)
121 122 123 124 125 126 127 128
 *   phy_pages - Physical memory pages
 *   perm - permission
 *
 * Output Args: None
 *
 * Return:
 *   Pointer to opaque structure that describes the created VM.
 *
129
 * Creates a VM with the mode specified by mode (e.g. VM_MODE_P52V48_4K).
130 131 132 133 134
 * When phy_pages is non-zero, a memory region of phy_pages physical pages
 * is created and mapped starting at guest physical address 0.  The file
 * descriptor to control the created VM is created with the permissions
 * given by perm (e.g. O_RDWR).
 */
135
struct kvm_vm *_vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm)
136 137 138
{
	struct kvm_vm *vm;

139 140
	DEBUG("Testing guest mode: %s\n", vm_guest_mode_string(mode));

141
	vm = calloc(1, sizeof(*vm));
142
	TEST_ASSERT(vm != NULL, "Insufficient Memory");
143 144

	vm->mode = mode;
145
	vm->type = 0;
146 147 148

	/* Setup mode specific traits. */
	switch (vm->mode) {
149
	case VM_MODE_P52V48_4K:
150
		vm->pgtable_levels = 4;
151 152
		vm->pa_bits = 52;
		vm->va_bits = 48;
153 154 155
		vm->page_size = 0x1000;
		vm->page_shift = 12;
		break;
156 157 158
	case VM_MODE_P52V48_64K:
		vm->pgtable_levels = 3;
		vm->pa_bits = 52;
159
		vm->va_bits = 48;
160 161
		vm->page_size = 0x10000;
		vm->page_shift = 16;
162 163 164 165
		break;
	case VM_MODE_P48V48_4K:
		vm->pgtable_levels = 4;
		vm->pa_bits = 48;
166
		vm->va_bits = 48;
167 168 169 170 171 172 173 174 175
		vm->page_size = 0x1000;
		vm->page_shift = 12;
		break;
	case VM_MODE_P48V48_64K:
		vm->pgtable_levels = 3;
		vm->pa_bits = 48;
		vm->va_bits = 48;
		vm->page_size = 0x10000;
		vm->page_shift = 16;
176
		break;
177 178 179 180 181 182 183 184 185 186 187 188 189 190
	case VM_MODE_P40V48_4K:
		vm->pgtable_levels = 4;
		vm->pa_bits = 40;
		vm->va_bits = 48;
		vm->page_size = 0x1000;
		vm->page_shift = 12;
		break;
	case VM_MODE_P40V48_64K:
		vm->pgtable_levels = 3;
		vm->pa_bits = 40;
		vm->va_bits = 48;
		vm->page_size = 0x10000;
		vm->page_shift = 16;
		break;
191 192 193 194 195 196 197 198 199 200 201 202 203 204 205
	case VM_MODE_PXXV48_4K:
#ifdef __x86_64__
		kvm_get_cpu_address_width(&vm->pa_bits, &vm->va_bits);
		TEST_ASSERT(vm->va_bits == 48, "Linear address width "
			    "(%d bits) not supported", vm->va_bits);
		vm->pgtable_levels = 4;
		vm->page_size = 0x1000;
		vm->page_shift = 12;
		DEBUG("Guest physical address width detected: %d\n",
		      vm->pa_bits);
#else
		TEST_ASSERT(false, "VM_MODE_PXXV48_4K not supported on "
			    "non-x86 platforms");
#endif
		break;
206 207 208 209
	default:
		TEST_ASSERT(false, "Unknown guest mode, mode: 0x%x", mode);
	}

210 211 212 213 214 215 216
#ifdef __aarch64__
	if (vm->pa_bits != 40)
		vm->type = KVM_VM_TYPE_ARM_IPA_SIZE(vm->pa_bits);
#endif

	vm_open(vm, perm);

217 218 219 220 221 222 223 224 225 226 227
	/* Limit to VA-bit canonical virtual addresses. */
	vm->vpages_valid = sparsebit_alloc();
	sparsebit_set_num(vm->vpages_valid,
		0, (1ULL << (vm->va_bits - 1)) >> vm->page_shift);
	sparsebit_set_num(vm->vpages_valid,
		(~((1ULL << (vm->va_bits - 1)) - 1)) >> vm->page_shift,
		(1ULL << (vm->va_bits - 1)) >> vm->page_shift);

	/* Limit physical addresses to PA-bits. */
	vm->max_gfn = ((1ULL << vm->pa_bits) >> vm->page_shift) - 1;

228 229 230 231 232 233 234 235 236
	/* Allocate and setup memory for guest. */
	vm->vpages_mapped = sparsebit_alloc();
	if (phy_pages != 0)
		vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS,
					    0, 0, phy_pages, 0);

	return vm;
}

237 238
struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm)
{
239
	return _vm_create(mode, phy_pages, perm);
240 241
}

A
Andrew Jones 已提交
242 243
/*
 * VM Restart
244 245 246 247 248 249 250 251 252 253 254 255 256 257 258
 *
 * Input Args:
 *   vm - VM that has been released before
 *   perm - permission
 *
 * Output Args: None
 *
 * Reopens the file descriptors associated to the VM and reinstates the
 * global state, such as the irqchip and the memory regions that are mapped
 * into the guest.
 */
void kvm_vm_restart(struct kvm_vm *vmp, int perm)
{
	struct userspace_mem_region *region;

259
	vm_open(vmp, perm);
260 261 262 263 264 265 266 267 268 269
	if (vmp->has_irqchip)
		vm_create_irqchip(vmp);

	for (region = vmp->userspace_mem_region_head; region;
		region = region->next) {
		int ret = ioctl(vmp->fd, KVM_SET_USER_MEMORY_REGION, &region->region);
		TEST_ASSERT(ret == 0, "KVM_SET_USER_MEMORY_REGION IOCTL failed,\n"
			    "  rc: %i errno: %i\n"
			    "  slot: %u flags: 0x%x\n"
			    "  guest_phys_addr: 0x%lx size: 0x%lx",
A
Andrew Jones 已提交
270 271
			    ret, errno, region->region.slot,
			    region->region.flags,
272 273 274 275 276
			    region->region.guest_phys_addr,
			    region->region.memory_size);
	}
}

P
Peter Xu 已提交
277 278 279 280 281 282 283 284 285 286
void kvm_vm_get_dirty_log(struct kvm_vm *vm, int slot, void *log)
{
	struct kvm_dirty_log args = { .dirty_bitmap = log, .slot = slot };
	int ret;

	ret = ioctl(vm->fd, KVM_GET_DIRTY_LOG, &args);
	TEST_ASSERT(ret == 0, "%s: KVM_GET_DIRTY_LOG failed: %s",
		    strerror(-ret));
}

287 288 289 290 291 292 293 294 295 296 297 298 299
void kvm_vm_clear_dirty_log(struct kvm_vm *vm, int slot, void *log,
			    uint64_t first_page, uint32_t num_pages)
{
	struct kvm_clear_dirty_log args = { .dirty_bitmap = log, .slot = slot,
		                            .first_page = first_page,
	                                    .num_pages = num_pages };
	int ret;

	ret = ioctl(vm->fd, KVM_CLEAR_DIRTY_LOG, &args);
	TEST_ASSERT(ret == 0, "%s: KVM_CLEAR_DIRTY_LOG failed: %s",
		    strerror(-ret));
}

A
Andrew Jones 已提交
300 301
/*
 * Userspace Memory Region Find
302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318
 *
 * Input Args:
 *   vm - Virtual Machine
 *   start - Starting VM physical address
 *   end - Ending VM physical address, inclusive.
 *
 * Output Args: None
 *
 * Return:
 *   Pointer to overlapping region, NULL if no such region.
 *
 * Searches for a region with any physical memory that overlaps with
 * any portion of the guest physical addresses from start to end
 * inclusive.  If multiple overlapping regions exist, a pointer to any
 * of the regions is returned.  Null is returned only when no overlapping
 * region exists.
 */
A
Andrew Jones 已提交
319 320
static struct userspace_mem_region *
userspace_mem_region_find(struct kvm_vm *vm, uint64_t start, uint64_t end)
321 322 323 324 325 326 327 328 329 330 331 332 333 334 335
{
	struct userspace_mem_region *region;

	for (region = vm->userspace_mem_region_head; region;
		region = region->next) {
		uint64_t existing_start = region->region.guest_phys_addr;
		uint64_t existing_end = region->region.guest_phys_addr
			+ region->region.memory_size - 1;
		if (start <= existing_end && end >= existing_start)
			return region;
	}

	return NULL;
}

A
Andrew Jones 已提交
336 337
/*
 * KVM Userspace Memory Region Find
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
 *
 * Input Args:
 *   vm - Virtual Machine
 *   start - Starting VM physical address
 *   end - Ending VM physical address, inclusive.
 *
 * Output Args: None
 *
 * Return:
 *   Pointer to overlapping region, NULL if no such region.
 *
 * Public interface to userspace_mem_region_find. Allows tests to look up
 * the memslot datastructure for a given range of guest physical memory.
 */
struct kvm_userspace_memory_region *
kvm_userspace_memory_region_find(struct kvm_vm *vm, uint64_t start,
				 uint64_t end)
{
	struct userspace_mem_region *region;

	region = userspace_mem_region_find(vm, start, end);
	if (!region)
		return NULL;

	return &region->region;
}

A
Andrew Jones 已提交
365 366
/*
 * VCPU Find
367 368 369 370 371 372 373 374 375 376 377 378 379 380
 *
 * Input Args:
 *   vm - Virtual Machine
 *   vcpuid - VCPU ID
 *
 * Output Args: None
 *
 * Return:
 *   Pointer to VCPU structure
 *
 * Locates a vcpu structure that describes the VCPU specified by vcpuid and
 * returns a pointer to it.  Returns NULL if the VM doesn't contain a VCPU
 * for the specified vcpuid.
 */
A
Andrew Jones 已提交
381
struct vcpu *vcpu_find(struct kvm_vm *vm, uint32_t vcpuid)
382 383 384 385 386 387 388 389 390 391 392
{
	struct vcpu *vcpup;

	for (vcpup = vm->vcpu_head; vcpup; vcpup = vcpup->next) {
		if (vcpup->id == vcpuid)
			return vcpup;
	}

	return NULL;
}

A
Andrew Jones 已提交
393 394
/*
 * VM VCPU Remove
395 396 397 398 399 400 401 402 403 404 405 406 407 408
 *
 * Input Args:
 *   vm - Virtual Machine
 *   vcpuid - VCPU ID
 *
 * Output Args: None
 *
 * Return: None, TEST_ASSERT failures for all error conditions
 *
 * Within the VM specified by vm, removes the VCPU given by vcpuid.
 */
static void vm_vcpu_rm(struct kvm_vm *vm, uint32_t vcpuid)
{
	struct vcpu *vcpu = vcpu_find(vm, vcpuid);
409
	int ret;
410

411 412 413 414
	ret = munmap(vcpu->state, sizeof(*vcpu->state));
	TEST_ASSERT(ret == 0, "munmap of VCPU fd failed, rc: %i "
		"errno: %i", ret, errno);
	close(vcpu->fd);
415 416 417 418 419 420 421 422 423 424 425 426
	TEST_ASSERT(ret == 0, "Close of VCPU fd failed, rc: %i "
		"errno: %i", ret, errno);

	if (vcpu->next)
		vcpu->next->prev = vcpu->prev;
	if (vcpu->prev)
		vcpu->prev->next = vcpu->next;
	else
		vm->vcpu_head = vcpu->next;
	free(vcpu);
}

427 428 429 430 431 432 433 434 435 436 437 438 439 440 441
void kvm_vm_release(struct kvm_vm *vmp)
{
	int ret;

	while (vmp->vcpu_head)
		vm_vcpu_rm(vmp, vmp->vcpu_head->id);

	ret = close(vmp->fd);
	TEST_ASSERT(ret == 0, "Close of vm fd failed,\n"
		"  vmp->fd: %i rc: %i errno: %i", vmp->fd, ret, errno);

	close(vmp->kvm_fd);
	TEST_ASSERT(ret == 0, "Close of /dev/kvm fd failed,\n"
		"  vmp->kvm_fd: %i rc: %i errno: %i", vmp->kvm_fd, ret, errno);
}
442

A
Andrew Jones 已提交
443 444
/*
 * Destroys and frees the VM pointed to by vmp.
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
 */
void kvm_vm_free(struct kvm_vm *vmp)
{
	int ret;

	if (vmp == NULL)
		return;

	/* Free userspace_mem_regions. */
	while (vmp->userspace_mem_region_head) {
		struct userspace_mem_region *region
			= vmp->userspace_mem_region_head;

		region->region.memory_size = 0;
		ret = ioctl(vmp->fd, KVM_SET_USER_MEMORY_REGION,
			&region->region);
		TEST_ASSERT(ret == 0, "KVM_SET_USER_MEMORY_REGION IOCTL failed, "
			"rc: %i errno: %i", ret, errno);

		vmp->userspace_mem_region_head = region->next;
		sparsebit_free(&region->unused_phy_pages);
		ret = munmap(region->mmap_start, region->mmap_size);
		TEST_ASSERT(ret == 0, "munmap failed, rc: %i errno: %i",
			    ret, errno);

		free(region);
	}

	/* Free sparsebit arrays. */
	sparsebit_free(&vmp->vpages_valid);
	sparsebit_free(&vmp->vpages_mapped);

477
	kvm_vm_release(vmp);
478 479 480 481 482

	/* Free the structure describing the VM. */
	free(vmp);
}

A
Andrew Jones 已提交
483 484
/*
 * Memory Compare, host virtual to guest virtual
485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505
 *
 * Input Args:
 *   hva - Starting host virtual address
 *   vm - Virtual Machine
 *   gva - Starting guest virtual address
 *   len - number of bytes to compare
 *
 * Output Args: None
 *
 * Input/Output Args: None
 *
 * Return:
 *   Returns 0 if the bytes starting at hva for a length of len
 *   are equal the guest virtual bytes starting at gva.  Returns
 *   a value < 0, if bytes at hva are less than those at gva.
 *   Otherwise a value > 0 is returned.
 *
 * Compares the bytes starting at the host virtual address hva, for
 * a length of len, to the guest bytes starting at the guest virtual
 * address given by gva.
 */
A
Andrew Jones 已提交
506
int kvm_memcmp_hva_gva(void *hva, struct kvm_vm *vm, vm_vaddr_t gva, size_t len)
507 508 509
{
	size_t amt;

A
Andrew Jones 已提交
510 511
	/*
	 * Compare a batch of bytes until either a match is found
512 513 514 515 516
	 * or all the bytes have been compared.
	 */
	for (uintptr_t offset = 0; offset < len; offset += amt) {
		uintptr_t ptr1 = (uintptr_t)hva + offset;

A
Andrew Jones 已提交
517 518
		/*
		 * Determine host address for guest virtual address
519 520 521 522
		 * at offset.
		 */
		uintptr_t ptr2 = (uintptr_t)addr_gva2hva(vm, gva + offset);

A
Andrew Jones 已提交
523 524
		/*
		 * Determine amount to compare on this pass.
525 526 527 528 529 530 531 532 533 534 535
		 * Don't allow the comparsion to cross a page boundary.
		 */
		amt = len - offset;
		if ((ptr1 >> vm->page_shift) != ((ptr1 + amt) >> vm->page_shift))
			amt = vm->page_size - (ptr1 % vm->page_size);
		if ((ptr2 >> vm->page_shift) != ((ptr2 + amt) >> vm->page_shift))
			amt = vm->page_size - (ptr2 % vm->page_size);

		assert((ptr1 >> vm->page_shift) == ((ptr1 + amt - 1) >> vm->page_shift));
		assert((ptr2 >> vm->page_shift) == ((ptr2 + amt - 1) >> vm->page_shift));

A
Andrew Jones 已提交
536 537
		/*
		 * Perform the comparison.  If there is a difference
538 539 540 541 542 543 544 545
		 * return that result to the caller, otherwise need
		 * to continue on looking for a mismatch.
		 */
		int ret = memcmp((void *)ptr1, (void *)ptr2, amt);
		if (ret != 0)
			return ret;
	}

A
Andrew Jones 已提交
546 547
	/*
	 * No mismatch found.  Let the caller know the two memory
548 549 550 551 552
	 * areas are equal.
	 */
	return 0;
}

A
Andrew Jones 已提交
553 554
/*
 * VM Userspace Memory Region Add
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
 *
 * Input Args:
 *   vm - Virtual Machine
 *   backing_src - Storage source for this region.
 *                 NULL to use anonymous memory.
 *   guest_paddr - Starting guest physical address
 *   slot - KVM region slot
 *   npages - Number of physical pages
 *   flags - KVM memory region flags (e.g. KVM_MEM_LOG_DIRTY_PAGES)
 *
 * Output Args: None
 *
 * Return: None
 *
 * Allocates a memory area of the number of pages specified by npages
 * and maps it to the VM specified by vm, at a starting physical address
 * given by guest_paddr.  The region is created with a KVM region slot
 * given by slot, which must be unique and < KVM_MEM_SLOTS_NUM.  The
 * region is created with the flags given by flags.
 */
void vm_userspace_mem_region_add(struct kvm_vm *vm,
	enum vm_mem_backing_src_type src_type,
	uint64_t guest_paddr, uint32_t slot, uint64_t npages,
	uint32_t flags)
{
	int ret;
	struct userspace_mem_region *region;
	size_t huge_page_size = KVM_UTIL_PGS_PER_HUGEPG * vm->page_size;
583
	size_t alignment;
584 585 586 587 588 589 590 591 592 593 594 595

	TEST_ASSERT((guest_paddr % vm->page_size) == 0, "Guest physical "
		"address not on a page boundary.\n"
		"  guest_paddr: 0x%lx vm->page_size: 0x%x",
		guest_paddr, vm->page_size);
	TEST_ASSERT((((guest_paddr >> vm->page_shift) + npages) - 1)
		<= vm->max_gfn, "Physical range beyond maximum "
		"supported physical address,\n"
		"  guest_paddr: 0x%lx npages: 0x%lx\n"
		"  vm->max_gfn: 0x%lx vm->page_size: 0x%x",
		guest_paddr, npages, vm->max_gfn, vm->page_size);

A
Andrew Jones 已提交
596 597
	/*
	 * Confirm a mem region with an overlapping address doesn't
598 599 600
	 * already exist.
	 */
	region = (struct userspace_mem_region *) userspace_mem_region_find(
601
		vm, guest_paddr, (guest_paddr + npages * vm->page_size) - 1);
602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619
	if (region != NULL)
		TEST_ASSERT(false, "overlapping userspace_mem_region already "
			"exists\n"
			"  requested guest_paddr: 0x%lx npages: 0x%lx "
			"page_size: 0x%x\n"
			"  existing guest_paddr: 0x%lx size: 0x%lx",
			guest_paddr, npages, vm->page_size,
			(uint64_t) region->region.guest_phys_addr,
			(uint64_t) region->region.memory_size);

	/* Confirm no region with the requested slot already exists. */
	for (region = vm->userspace_mem_region_head; region;
		region = region->next) {
		if (region->region.slot == slot)
			break;
	}
	if (region != NULL)
		TEST_ASSERT(false, "A mem region with the requested slot "
620
			"already exists.\n"
621 622 623 624 625 626 627 628 629 630 631 632
			"  requested slot: %u paddr: 0x%lx npages: 0x%lx\n"
			"  existing slot: %u paddr: 0x%lx size: 0x%lx",
			slot, guest_paddr, npages,
			region->region.slot,
			(uint64_t) region->region.guest_phys_addr,
			(uint64_t) region->region.memory_size);

	/* Allocate and initialize new mem region structure. */
	region = calloc(1, sizeof(*region));
	TEST_ASSERT(region != NULL, "Insufficient Memory");
	region->mmap_size = npages * vm->page_size;

633 634 635 636 637 638 639
#ifdef __s390x__
	/* On s390x, the host address must be aligned to 1M (due to PGSTEs) */
	alignment = 0x100000;
#else
	alignment = 1;
#endif

640
	if (src_type == VM_MEM_SRC_ANONYMOUS_THP)
641 642 643 644 645 646
		alignment = max(huge_page_size, alignment);

	/* Add enough memory to align up if necessary */
	if (alignment > 1)
		region->mmap_size += alignment;

647 648 649 650 651 652 653 654 655
	region->mmap_start = mmap(NULL, region->mmap_size,
				  PROT_READ | PROT_WRITE,
				  MAP_PRIVATE | MAP_ANONYMOUS
				  | (src_type == VM_MEM_SRC_ANONYMOUS_HUGETLB ? MAP_HUGETLB : 0),
				  -1, 0);
	TEST_ASSERT(region->mmap_start != MAP_FAILED,
		    "test_malloc failed, mmap_start: %p errno: %i",
		    region->mmap_start, errno);

656 657
	/* Align host address */
	region->host_mem = align(region->mmap_start, alignment);
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

	/* As needed perform madvise */
	if (src_type == VM_MEM_SRC_ANONYMOUS || src_type == VM_MEM_SRC_ANONYMOUS_THP) {
		ret = madvise(region->host_mem, npages * vm->page_size,
			     src_type == VM_MEM_SRC_ANONYMOUS ? MADV_NOHUGEPAGE : MADV_HUGEPAGE);
		TEST_ASSERT(ret == 0, "madvise failed,\n"
			    "  addr: %p\n"
			    "  length: 0x%lx\n"
			    "  src_type: %x",
			    region->host_mem, npages * vm->page_size, src_type);
	}

	region->unused_phy_pages = sparsebit_alloc();
	sparsebit_set_num(region->unused_phy_pages,
		guest_paddr >> vm->page_shift, npages);
	region->region.slot = slot;
	region->region.flags = flags;
	region->region.guest_phys_addr = guest_paddr;
	region->region.memory_size = npages * vm->page_size;
	region->region.userspace_addr = (uintptr_t) region->host_mem;
	ret = ioctl(vm->fd, KVM_SET_USER_MEMORY_REGION, &region->region);
	TEST_ASSERT(ret == 0, "KVM_SET_USER_MEMORY_REGION IOCTL failed,\n"
		"  rc: %i errno: %i\n"
		"  slot: %u flags: 0x%x\n"
		"  guest_phys_addr: 0x%lx size: 0x%lx",
		ret, errno, slot, flags,
		guest_paddr, (uint64_t) region->region.memory_size);

	/* Add to linked-list of memory regions. */
	if (vm->userspace_mem_region_head)
		vm->userspace_mem_region_head->prev = region;
	region->next = vm->userspace_mem_region_head;
	vm->userspace_mem_region_head = region;
}

A
Andrew Jones 已提交
693 694
/*
 * Memslot to region
695 696 697 698 699 700 701 702 703 704 705 706 707
 *
 * Input Args:
 *   vm - Virtual Machine
 *   memslot - KVM memory slot ID
 *
 * Output Args: None
 *
 * Return:
 *   Pointer to memory region structure that describe memory region
 *   using kvm memory slot ID given by memslot.  TEST_ASSERT failure
 *   on error (e.g. currently no memory region using memslot as a KVM
 *   memory slot ID).
 */
708
struct userspace_mem_region *
A
Andrew Jones 已提交
709
memslot2region(struct kvm_vm *vm, uint32_t memslot)
710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728
{
	struct userspace_mem_region *region;

	for (region = vm->userspace_mem_region_head; region;
		region = region->next) {
		if (region->region.slot == memslot)
			break;
	}
	if (region == NULL) {
		fprintf(stderr, "No mem region with the requested slot found,\n"
			"  requested slot: %u\n", memslot);
		fputs("---- vm dump ----\n", stderr);
		vm_dump(stderr, vm, 2);
		TEST_ASSERT(false, "Mem region not found");
	}

	return region;
}

A
Andrew Jones 已提交
729 730
/*
 * VM Memory Region Flags Set
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
 *
 * Input Args:
 *   vm - Virtual Machine
 *   flags - Starting guest physical address
 *
 * Output Args: None
 *
 * Return: None
 *
 * Sets the flags of the memory region specified by the value of slot,
 * to the values given by flags.
 */
void vm_mem_region_set_flags(struct kvm_vm *vm, uint32_t slot, uint32_t flags)
{
	int ret;
	struct userspace_mem_region *region;

	region = memslot2region(vm, slot);

	region->region.flags = flags;

	ret = ioctl(vm->fd, KVM_SET_USER_MEMORY_REGION, &region->region);

	TEST_ASSERT(ret == 0, "KVM_SET_USER_MEMORY_REGION IOCTL failed,\n"
		"  rc: %i errno: %i slot: %u flags: 0x%x",
		ret, errno, slot, flags);
}

A
Andrew Jones 已提交
759 760
/*
 * VCPU mmap Size
761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776
 *
 * Input Args: None
 *
 * Output Args: None
 *
 * Return:
 *   Size of VCPU state
 *
 * Returns the size of the structure pointed to by the return value
 * of vcpu_state().
 */
static int vcpu_mmap_sz(void)
{
	int dev_fd, ret;

	dev_fd = open(KVM_DEV_PATH, O_RDONLY);
777 778
	if (dev_fd < 0)
		exit(KSFT_SKIP);
779 780 781 782 783 784 785 786 787 788 789

	ret = ioctl(dev_fd, KVM_GET_VCPU_MMAP_SIZE, NULL);
	TEST_ASSERT(ret >= sizeof(struct kvm_run),
		"%s KVM_GET_VCPU_MMAP_SIZE ioctl failed, rc: %i errno: %i",
		__func__, ret, errno);

	close(dev_fd);

	return ret;
}

A
Andrew Jones 已提交
790 791
/*
 * VM VCPU Add
792 793 794 795 796 797 798 799 800
 *
 * Input Args:
 *   vm - Virtual Machine
 *   vcpuid - VCPU ID
 *
 * Output Args: None
 *
 * Return: None
 *
801 802
 * Adds a virtual CPU to the VM specified by vm with the ID given by vcpuid.
 * No additional VCPU setup is done.
803
 */
804
void vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpuid)
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
{
	struct vcpu *vcpu;

	/* Confirm a vcpu with the specified id doesn't already exist. */
	vcpu = vcpu_find(vm, vcpuid);
	if (vcpu != NULL)
		TEST_ASSERT(false, "vcpu with the specified id "
			"already exists,\n"
			"  requested vcpuid: %u\n"
			"  existing vcpuid: %u state: %p",
			vcpuid, vcpu->id, vcpu->state);

	/* Allocate and initialize new vcpu structure. */
	vcpu = calloc(1, sizeof(*vcpu));
	TEST_ASSERT(vcpu != NULL, "Insufficient Memory");
	vcpu->id = vcpuid;
	vcpu->fd = ioctl(vm->fd, KVM_CREATE_VCPU, vcpuid);
	TEST_ASSERT(vcpu->fd >= 0, "KVM_CREATE_VCPU failed, rc: %i errno: %i",
		vcpu->fd, errno);

	TEST_ASSERT(vcpu_mmap_sz() >= sizeof(*vcpu->state), "vcpu mmap size "
		"smaller than expected, vcpu_mmap_sz: %i expected_min: %zi",
		vcpu_mmap_sz(), sizeof(*vcpu->state));
	vcpu->state = (struct kvm_run *) mmap(NULL, sizeof(*vcpu->state),
		PROT_READ | PROT_WRITE, MAP_SHARED, vcpu->fd, 0);
	TEST_ASSERT(vcpu->state != MAP_FAILED, "mmap vcpu_state failed, "
		"vcpu id: %u errno: %i", vcpuid, errno);

	/* Add to linked-list of VCPUs. */
	if (vm->vcpu_head)
		vm->vcpu_head->prev = vcpu;
	vcpu->next = vm->vcpu_head;
	vm->vcpu_head = vcpu;
}

A
Andrew Jones 已提交
840 841
/*
 * VM Virtual Address Unused Gap
842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860
 *
 * Input Args:
 *   vm - Virtual Machine
 *   sz - Size (bytes)
 *   vaddr_min - Minimum Virtual Address
 *
 * Output Args: None
 *
 * Return:
 *   Lowest virtual address at or below vaddr_min, with at least
 *   sz unused bytes.  TEST_ASSERT failure if no area of at least
 *   size sz is available.
 *
 * Within the VM specified by vm, locates the lowest starting virtual
 * address >= vaddr_min, that has at least sz unallocated bytes.  A
 * TEST_ASSERT failure occurs for invalid input or no area of at least
 * sz unallocated bytes >= vaddr_min is available.
 */
static vm_vaddr_t vm_vaddr_unused_gap(struct kvm_vm *vm, size_t sz,
A
Andrew Jones 已提交
861
				      vm_vaddr_t vaddr_min)
862 863 864 865 866 867
{
	uint64_t pages = (sz + vm->page_size - 1) >> vm->page_shift;

	/* Determine lowest permitted virtual page index. */
	uint64_t pgidx_start = (vaddr_min + vm->page_size - 1) >> vm->page_shift;
	if ((pgidx_start * vm->page_size) < vaddr_min)
A
Andrew Jones 已提交
868
		goto no_va_found;
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

	/* Loop over section with enough valid virtual page indexes. */
	if (!sparsebit_is_set_num(vm->vpages_valid,
		pgidx_start, pages))
		pgidx_start = sparsebit_next_set_num(vm->vpages_valid,
			pgidx_start, pages);
	do {
		/*
		 * Are there enough unused virtual pages available at
		 * the currently proposed starting virtual page index.
		 * If not, adjust proposed starting index to next
		 * possible.
		 */
		if (sparsebit_is_clear_num(vm->vpages_mapped,
			pgidx_start, pages))
			goto va_found;
		pgidx_start = sparsebit_next_clear_num(vm->vpages_mapped,
			pgidx_start, pages);
		if (pgidx_start == 0)
			goto no_va_found;

		/*
		 * If needed, adjust proposed starting virtual address,
		 * to next range of valid virtual addresses.
		 */
		if (!sparsebit_is_set_num(vm->vpages_valid,
			pgidx_start, pages)) {
			pgidx_start = sparsebit_next_set_num(
				vm->vpages_valid, pgidx_start, pages);
			if (pgidx_start == 0)
				goto no_va_found;
		}
	} while (pgidx_start != 0);

no_va_found:
	TEST_ASSERT(false, "No vaddr of specified pages available, "
		"pages: 0x%lx", pages);

	/* NOT REACHED */
	return -1;

va_found:
	TEST_ASSERT(sparsebit_is_set_num(vm->vpages_valid,
		pgidx_start, pages),
		"Unexpected, invalid virtual page index range,\n"
		"  pgidx_start: 0x%lx\n"
		"  pages: 0x%lx",
		pgidx_start, pages);
	TEST_ASSERT(sparsebit_is_clear_num(vm->vpages_mapped,
		pgidx_start, pages),
		"Unexpected, pages already mapped,\n"
		"  pgidx_start: 0x%lx\n"
		"  pages: 0x%lx",
		pgidx_start, pages);

	return pgidx_start * vm->page_size;
}

A
Andrew Jones 已提交
927 928
/*
 * VM Virtual Address Allocate
929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948
 *
 * Input Args:
 *   vm - Virtual Machine
 *   sz - Size in bytes
 *   vaddr_min - Minimum starting virtual address
 *   data_memslot - Memory region slot for data pages
 *   pgd_memslot - Memory region slot for new virtual translation tables
 *
 * Output Args: None
 *
 * Return:
 *   Starting guest virtual address
 *
 * Allocates at least sz bytes within the virtual address space of the vm
 * given by vm.  The allocated bytes are mapped to a virtual address >=
 * the address given by vaddr_min.  Note that each allocation uses a
 * a unique set of pages, with the minimum real allocation being at least
 * a page.
 */
vm_vaddr_t vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min,
A
Andrew Jones 已提交
949
			  uint32_t data_memslot, uint32_t pgd_memslot)
950 951 952 953 954
{
	uint64_t pages = (sz >> vm->page_shift) + ((sz % vm->page_size) != 0);

	virt_pgd_alloc(vm, pgd_memslot);

A
Andrew Jones 已提交
955 956
	/*
	 * Find an unused range of virtual page addresses of at least
957 958 959 960 961 962 963 964 965
	 * pages in length.
	 */
	vm_vaddr_t vaddr_start = vm_vaddr_unused_gap(vm, sz, vaddr_min);

	/* Map the virtual pages. */
	for (vm_vaddr_t vaddr = vaddr_start; pages > 0;
		pages--, vaddr += vm->page_size) {
		vm_paddr_t paddr;

966 967
		paddr = vm_phy_page_alloc(vm,
				KVM_UTIL_MIN_PFN * vm->page_size, data_memslot);
968 969 970 971 972 973 974 975 976 977

		virt_pg_map(vm, vaddr, paddr, pgd_memslot);

		sparsebit_set(vm->vpages_mapped,
			vaddr >> vm->page_shift);
	}

	return vaddr_start;
}

P
Peter Xu 已提交
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
/*
 * Map a range of VM virtual address to the VM's physical address
 *
 * Input Args:
 *   vm - Virtual Machine
 *   vaddr - Virtuall address to map
 *   paddr - VM Physical Address
 *   size - The size of the range to map
 *   pgd_memslot - Memory region slot for new virtual translation tables
 *
 * Output Args: None
 *
 * Return: None
 *
 * Within the VM given by vm, creates a virtual translation for the
 * page range starting at vaddr to the page range starting at paddr.
 */
void virt_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
	      size_t size, uint32_t pgd_memslot)
{
	size_t page_size = vm->page_size;
	size_t npages = size / page_size;

	TEST_ASSERT(vaddr + size > vaddr, "Vaddr overflow");
	TEST_ASSERT(paddr + size > paddr, "Paddr overflow");

	while (npages--) {
		virt_pg_map(vm, vaddr, paddr, pgd_memslot);
		vaddr += page_size;
		paddr += page_size;
	}
}

A
Andrew Jones 已提交
1011 1012
/*
 * Address VM Physical to Host Virtual
1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043
 *
 * Input Args:
 *   vm - Virtual Machine
 *   gpa - VM physical address
 *
 * Output Args: None
 *
 * Return:
 *   Equivalent host virtual address
 *
 * Locates the memory region containing the VM physical address given
 * by gpa, within the VM given by vm.  When found, the host virtual
 * address providing the memory to the vm physical address is returned.
 * A TEST_ASSERT failure occurs if no region containing gpa exists.
 */
void *addr_gpa2hva(struct kvm_vm *vm, vm_paddr_t gpa)
{
	struct userspace_mem_region *region;
	for (region = vm->userspace_mem_region_head; region;
	     region = region->next) {
		if ((gpa >= region->region.guest_phys_addr)
			&& (gpa <= (region->region.guest_phys_addr
				+ region->region.memory_size - 1)))
			return (void *) ((uintptr_t) region->host_mem
				+ (gpa - region->region.guest_phys_addr));
	}

	TEST_ASSERT(false, "No vm physical memory at 0x%lx", gpa);
	return NULL;
}

A
Andrew Jones 已提交
1044 1045
/*
 * Address Host Virtual to VM Physical
1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078
 *
 * Input Args:
 *   vm - Virtual Machine
 *   hva - Host virtual address
 *
 * Output Args: None
 *
 * Return:
 *   Equivalent VM physical address
 *
 * Locates the memory region containing the host virtual address given
 * by hva, within the VM given by vm.  When found, the equivalent
 * VM physical address is returned. A TEST_ASSERT failure occurs if no
 * region containing hva exists.
 */
vm_paddr_t addr_hva2gpa(struct kvm_vm *vm, void *hva)
{
	struct userspace_mem_region *region;
	for (region = vm->userspace_mem_region_head; region;
	     region = region->next) {
		if ((hva >= region->host_mem)
			&& (hva <= (region->host_mem
				+ region->region.memory_size - 1)))
			return (vm_paddr_t) ((uintptr_t)
				region->region.guest_phys_addr
				+ (hva - (uintptr_t) region->host_mem));
	}

	TEST_ASSERT(false, "No mapping to a guest physical address, "
		"hva: %p", hva);
	return -1;
}

A
Andrew Jones 已提交
1079 1080
/*
 * VM Create IRQ Chip
1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097
 *
 * Input Args:
 *   vm - Virtual Machine
 *
 * Output Args: None
 *
 * Return: None
 *
 * Creates an interrupt controller chip for the VM specified by vm.
 */
void vm_create_irqchip(struct kvm_vm *vm)
{
	int ret;

	ret = ioctl(vm->fd, KVM_CREATE_IRQCHIP, 0);
	TEST_ASSERT(ret == 0, "KVM_CREATE_IRQCHIP IOCTL failed, "
		"rc: %i errno: %i", ret, errno);
1098 1099

	vm->has_irqchip = true;
1100 1101
}

A
Andrew Jones 已提交
1102 1103
/*
 * VM VCPU State
1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124
 *
 * Input Args:
 *   vm - Virtual Machine
 *   vcpuid - VCPU ID
 *
 * Output Args: None
 *
 * Return:
 *   Pointer to structure that describes the state of the VCPU.
 *
 * Locates and returns a pointer to a structure that describes the
 * state of the VCPU with the given vcpuid.
 */
struct kvm_run *vcpu_state(struct kvm_vm *vm, uint32_t vcpuid)
{
	struct vcpu *vcpu = vcpu_find(vm, vcpuid);
	TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);

	return vcpu->state;
}

A
Andrew Jones 已提交
1125 1126
/*
 * VM VCPU Run
1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151
 *
 * Input Args:
 *   vm - Virtual Machine
 *   vcpuid - VCPU ID
 *
 * Output Args: None
 *
 * Return: None
 *
 * Switch to executing the code for the VCPU given by vcpuid, within the VM
 * given by vm.
 */
void vcpu_run(struct kvm_vm *vm, uint32_t vcpuid)
{
	int ret = _vcpu_run(vm, vcpuid);
	TEST_ASSERT(ret == 0, "KVM_RUN IOCTL failed, "
		"rc: %i errno: %i", ret, errno);
}

int _vcpu_run(struct kvm_vm *vm, uint32_t vcpuid)
{
	struct vcpu *vcpu = vcpu_find(vm, vcpuid);
	int rc;

	TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);
A
Andrew Jones 已提交
1152
	do {
1153 1154 1155 1156 1157
		rc = ioctl(vcpu->fd, KVM_RUN, NULL);
	} while (rc == -1 && errno == EINTR);
	return rc;
}

1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173
void vcpu_run_complete_io(struct kvm_vm *vm, uint32_t vcpuid)
{
	struct vcpu *vcpu = vcpu_find(vm, vcpuid);
	int ret;

	TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);

	vcpu->state->immediate_exit = 1;
	ret = ioctl(vcpu->fd, KVM_RUN, NULL);
	vcpu->state->immediate_exit = 0;

	TEST_ASSERT(ret == -1 && errno == EINTR,
		    "KVM_RUN IOCTL didn't exit immediately, rc: %i, errno: %i",
		    ret, errno);
}

A
Andrew Jones 已提交
1174 1175
/*
 * VM VCPU Set MP State
1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189
 *
 * Input Args:
 *   vm - Virtual Machine
 *   vcpuid - VCPU ID
 *   mp_state - mp_state to be set
 *
 * Output Args: None
 *
 * Return: None
 *
 * Sets the MP state of the VCPU given by vcpuid, to the state given
 * by mp_state.
 */
void vcpu_set_mp_state(struct kvm_vm *vm, uint32_t vcpuid,
A
Andrew Jones 已提交
1190
		       struct kvm_mp_state *mp_state)
1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201
{
	struct vcpu *vcpu = vcpu_find(vm, vcpuid);
	int ret;

	TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);

	ret = ioctl(vcpu->fd, KVM_SET_MP_STATE, mp_state);
	TEST_ASSERT(ret == 0, "KVM_SET_MP_STATE IOCTL failed, "
		"rc: %i errno: %i", ret, errno);
}

A
Andrew Jones 已提交
1202 1203
/*
 * VM VCPU Regs Get
1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216
 *
 * Input Args:
 *   vm - Virtual Machine
 *   vcpuid - VCPU ID
 *
 * Output Args:
 *   regs - current state of VCPU regs
 *
 * Return: None
 *
 * Obtains the current register state for the VCPU specified by vcpuid
 * and stores it at the location given by regs.
 */
A
Andrew Jones 已提交
1217
void vcpu_regs_get(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_regs *regs)
1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228
{
	struct vcpu *vcpu = vcpu_find(vm, vcpuid);
	int ret;

	TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);

	ret = ioctl(vcpu->fd, KVM_GET_REGS, regs);
	TEST_ASSERT(ret == 0, "KVM_GET_REGS failed, rc: %i errno: %i",
		ret, errno);
}

A
Andrew Jones 已提交
1229 1230
/*
 * VM VCPU Regs Set
1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243
 *
 * Input Args:
 *   vm - Virtual Machine
 *   vcpuid - VCPU ID
 *   regs - Values to set VCPU regs to
 *
 * Output Args: None
 *
 * Return: None
 *
 * Sets the regs of the VCPU specified by vcpuid to the values
 * given by regs.
 */
A
Andrew Jones 已提交
1244
void vcpu_regs_set(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_regs *regs)
1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255
{
	struct vcpu *vcpu = vcpu_find(vm, vcpuid);
	int ret;

	TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);

	ret = ioctl(vcpu->fd, KVM_SET_REGS, regs);
	TEST_ASSERT(ret == 0, "KVM_SET_REGS failed, rc: %i errno: %i",
		ret, errno);
}

1256
#ifdef __KVM_HAVE_VCPU_EVENTS
1257
void vcpu_events_get(struct kvm_vm *vm, uint32_t vcpuid,
A
Andrew Jones 已提交
1258
		     struct kvm_vcpu_events *events)
1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270
{
	struct vcpu *vcpu = vcpu_find(vm, vcpuid);
	int ret;

	TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);

	ret = ioctl(vcpu->fd, KVM_GET_VCPU_EVENTS, events);
	TEST_ASSERT(ret == 0, "KVM_GET_VCPU_EVENTS, failed, rc: %i errno: %i",
		ret, errno);
}

void vcpu_events_set(struct kvm_vm *vm, uint32_t vcpuid,
A
Andrew Jones 已提交
1271
		     struct kvm_vcpu_events *events)
1272 1273 1274 1275 1276 1277 1278 1279 1280 1281
{
	struct vcpu *vcpu = vcpu_find(vm, vcpuid);
	int ret;

	TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);

	ret = ioctl(vcpu->fd, KVM_SET_VCPU_EVENTS, events);
	TEST_ASSERT(ret == 0, "KVM_SET_VCPU_EVENTS, failed, rc: %i errno: %i",
		ret, errno);
}
1282
#endif
1283

1284
#ifdef __x86_64__
1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315
void vcpu_nested_state_get(struct kvm_vm *vm, uint32_t vcpuid,
			   struct kvm_nested_state *state)
{
	struct vcpu *vcpu = vcpu_find(vm, vcpuid);
	int ret;

	TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);

	ret = ioctl(vcpu->fd, KVM_GET_NESTED_STATE, state);
	TEST_ASSERT(ret == 0,
		"KVM_SET_NESTED_STATE failed, ret: %i errno: %i",
		ret, errno);
}

int vcpu_nested_state_set(struct kvm_vm *vm, uint32_t vcpuid,
			  struct kvm_nested_state *state, bool ignore_error)
{
	struct vcpu *vcpu = vcpu_find(vm, vcpuid);
	int ret;

	TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);

	ret = ioctl(vcpu->fd, KVM_SET_NESTED_STATE, state);
	if (!ignore_error) {
		TEST_ASSERT(ret == 0,
			"KVM_SET_NESTED_STATE failed, ret: %i errno: %i",
			ret, errno);
	}

	return ret;
}
1316
#endif
1317

A
Andrew Jones 已提交
1318 1319
/*
 * VM VCPU System Regs Get
1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332
 *
 * Input Args:
 *   vm - Virtual Machine
 *   vcpuid - VCPU ID
 *
 * Output Args:
 *   sregs - current state of VCPU system regs
 *
 * Return: None
 *
 * Obtains the current system register state for the VCPU specified by
 * vcpuid and stores it at the location given by sregs.
 */
A
Andrew Jones 已提交
1333
void vcpu_sregs_get(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_sregs *sregs)
1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344
{
	struct vcpu *vcpu = vcpu_find(vm, vcpuid);
	int ret;

	TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);

	ret = ioctl(vcpu->fd, KVM_GET_SREGS, sregs);
	TEST_ASSERT(ret == 0, "KVM_GET_SREGS failed, rc: %i errno: %i",
		ret, errno);
}

A
Andrew Jones 已提交
1345 1346
/*
 * VM VCPU System Regs Set
1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359
 *
 * Input Args:
 *   vm - Virtual Machine
 *   vcpuid - VCPU ID
 *   sregs - Values to set VCPU system regs to
 *
 * Output Args: None
 *
 * Return: None
 *
 * Sets the system regs of the VCPU specified by vcpuid to the values
 * given by sregs.
 */
A
Andrew Jones 已提交
1360
void vcpu_sregs_set(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_sregs *sregs)
1361 1362 1363 1364 1365 1366
{
	int ret = _vcpu_sregs_set(vm, vcpuid, sregs);
	TEST_ASSERT(ret == 0, "KVM_RUN IOCTL failed, "
		"rc: %i errno: %i", ret, errno);
}

A
Andrew Jones 已提交
1367
int _vcpu_sregs_set(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_sregs *sregs)
1368 1369 1370 1371 1372 1373 1374 1375
{
	struct vcpu *vcpu = vcpu_find(vm, vcpuid);

	TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);

	return ioctl(vcpu->fd, KVM_SET_SREGS, sregs);
}

1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411
void vcpu_fpu_get(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_fpu *fpu)
{
	int ret;

	ret = _vcpu_ioctl(vm, vcpuid, KVM_GET_FPU, fpu);
	TEST_ASSERT(ret == 0, "KVM_GET_FPU failed, rc: %i errno: %i (%s)",
		    ret, errno, strerror(errno));
}

void vcpu_fpu_set(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_fpu *fpu)
{
	int ret;

	ret = _vcpu_ioctl(vm, vcpuid, KVM_SET_FPU, fpu);
	TEST_ASSERT(ret == 0, "KVM_SET_FPU failed, rc: %i errno: %i (%s)",
		    ret, errno, strerror(errno));
}

void vcpu_get_reg(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_one_reg *reg)
{
	int ret;

	ret = _vcpu_ioctl(vm, vcpuid, KVM_GET_ONE_REG, reg);
	TEST_ASSERT(ret == 0, "KVM_GET_ONE_REG failed, rc: %i errno: %i (%s)",
		    ret, errno, strerror(errno));
}

void vcpu_set_reg(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_one_reg *reg)
{
	int ret;

	ret = _vcpu_ioctl(vm, vcpuid, KVM_SET_ONE_REG, reg);
	TEST_ASSERT(ret == 0, "KVM_SET_ONE_REG failed, rc: %i errno: %i (%s)",
		    ret, errno, strerror(errno));
}

A
Andrew Jones 已提交
1412 1413
/*
 * VCPU Ioctl
1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424
 *
 * Input Args:
 *   vm - Virtual Machine
 *   vcpuid - VCPU ID
 *   cmd - Ioctl number
 *   arg - Argument to pass to the ioctl
 *
 * Return: None
 *
 * Issues an arbitrary ioctl on a VCPU fd.
 */
A
Andrew Jones 已提交
1425 1426
void vcpu_ioctl(struct kvm_vm *vm, uint32_t vcpuid,
		unsigned long cmd, void *arg)
1427 1428 1429 1430 1431 1432 1433 1434 1435 1436
{
	int ret;

	ret = _vcpu_ioctl(vm, vcpuid, cmd, arg);
	TEST_ASSERT(ret == 0, "vcpu ioctl %lu failed, rc: %i errno: %i (%s)",
		cmd, ret, errno, strerror(errno));
}

int _vcpu_ioctl(struct kvm_vm *vm, uint32_t vcpuid,
		unsigned long cmd, void *arg)
1437 1438 1439 1440 1441 1442 1443
{
	struct vcpu *vcpu = vcpu_find(vm, vcpuid);
	int ret;

	TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);

	ret = ioctl(vcpu->fd, cmd, arg);
1444 1445

	return ret;
1446 1447
}

A
Andrew Jones 已提交
1448 1449
/*
 * VM Ioctl
1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468
 *
 * Input Args:
 *   vm - Virtual Machine
 *   cmd - Ioctl number
 *   arg - Argument to pass to the ioctl
 *
 * Return: None
 *
 * Issues an arbitrary ioctl on a VM fd.
 */
void vm_ioctl(struct kvm_vm *vm, unsigned long cmd, void *arg)
{
	int ret;

	ret = ioctl(vm->fd, cmd, arg);
	TEST_ASSERT(ret == 0, "vm ioctl %lu failed, rc: %i errno: %i (%s)",
		cmd, ret, errno, strerror(errno));
}

A
Andrew Jones 已提交
1469 1470
/*
 * VM Dump
1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546
 *
 * Input Args:
 *   vm - Virtual Machine
 *   indent - Left margin indent amount
 *
 * Output Args:
 *   stream - Output FILE stream
 *
 * Return: None
 *
 * Dumps the current state of the VM given by vm, to the FILE stream
 * given by stream.
 */
void vm_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent)
{
	struct userspace_mem_region *region;
	struct vcpu *vcpu;

	fprintf(stream, "%*smode: 0x%x\n", indent, "", vm->mode);
	fprintf(stream, "%*sfd: %i\n", indent, "", vm->fd);
	fprintf(stream, "%*spage_size: 0x%x\n", indent, "", vm->page_size);
	fprintf(stream, "%*sMem Regions:\n", indent, "");
	for (region = vm->userspace_mem_region_head; region;
		region = region->next) {
		fprintf(stream, "%*sguest_phys: 0x%lx size: 0x%lx "
			"host_virt: %p\n", indent + 2, "",
			(uint64_t) region->region.guest_phys_addr,
			(uint64_t) region->region.memory_size,
			region->host_mem);
		fprintf(stream, "%*sunused_phy_pages: ", indent + 2, "");
		sparsebit_dump(stream, region->unused_phy_pages, 0);
	}
	fprintf(stream, "%*sMapped Virtual Pages:\n", indent, "");
	sparsebit_dump(stream, vm->vpages_mapped, indent + 2);
	fprintf(stream, "%*spgd_created: %u\n", indent, "",
		vm->pgd_created);
	if (vm->pgd_created) {
		fprintf(stream, "%*sVirtual Translation Tables:\n",
			indent + 2, "");
		virt_dump(stream, vm, indent + 4);
	}
	fprintf(stream, "%*sVCPUs:\n", indent, "");
	for (vcpu = vm->vcpu_head; vcpu; vcpu = vcpu->next)
		vcpu_dump(stream, vm, vcpu->id, indent + 2);
}

/* Known KVM exit reasons */
static struct exit_reason {
	unsigned int reason;
	const char *name;
} exit_reasons_known[] = {
	{KVM_EXIT_UNKNOWN, "UNKNOWN"},
	{KVM_EXIT_EXCEPTION, "EXCEPTION"},
	{KVM_EXIT_IO, "IO"},
	{KVM_EXIT_HYPERCALL, "HYPERCALL"},
	{KVM_EXIT_DEBUG, "DEBUG"},
	{KVM_EXIT_HLT, "HLT"},
	{KVM_EXIT_MMIO, "MMIO"},
	{KVM_EXIT_IRQ_WINDOW_OPEN, "IRQ_WINDOW_OPEN"},
	{KVM_EXIT_SHUTDOWN, "SHUTDOWN"},
	{KVM_EXIT_FAIL_ENTRY, "FAIL_ENTRY"},
	{KVM_EXIT_INTR, "INTR"},
	{KVM_EXIT_SET_TPR, "SET_TPR"},
	{KVM_EXIT_TPR_ACCESS, "TPR_ACCESS"},
	{KVM_EXIT_S390_SIEIC, "S390_SIEIC"},
	{KVM_EXIT_S390_RESET, "S390_RESET"},
	{KVM_EXIT_DCR, "DCR"},
	{KVM_EXIT_NMI, "NMI"},
	{KVM_EXIT_INTERNAL_ERROR, "INTERNAL_ERROR"},
	{KVM_EXIT_OSI, "OSI"},
	{KVM_EXIT_PAPR_HCALL, "PAPR_HCALL"},
#ifdef KVM_EXIT_MEMORY_NOT_PRESENT
	{KVM_EXIT_MEMORY_NOT_PRESENT, "MEMORY_NOT_PRESENT"},
#endif
};

A
Andrew Jones 已提交
1547 1548
/*
 * Exit Reason String
1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573
 *
 * Input Args:
 *   exit_reason - Exit reason
 *
 * Output Args: None
 *
 * Return:
 *   Constant string pointer describing the exit reason.
 *
 * Locates and returns a constant string that describes the KVM exit
 * reason given by exit_reason.  If no such string is found, a constant
 * string of "Unknown" is returned.
 */
const char *exit_reason_str(unsigned int exit_reason)
{
	unsigned int n1;

	for (n1 = 0; n1 < ARRAY_SIZE(exit_reasons_known); n1++) {
		if (exit_reason == exit_reasons_known[n1].reason)
			return exit_reasons_known[n1].name;
	}

	return "Unknown";
}

A
Andrew Jones 已提交
1574
/*
1575
 * Physical Contiguous Page Allocator
1576 1577 1578
 *
 * Input Args:
 *   vm - Virtual Machine
1579
 *   num - number of pages
1580 1581 1582 1583 1584 1585 1586 1587
 *   paddr_min - Physical address minimum
 *   memslot - Memory region to allocate page from
 *
 * Output Args: None
 *
 * Return:
 *   Starting physical address
 *
1588 1589
 * Within the VM specified by vm, locates a range of available physical
 * pages at or above paddr_min. If found, the pages are marked as in use
1590
 * and their base address is returned. A TEST_ASSERT failure occurs if
1591
 * not enough pages are available at or above paddr_min.
1592
 */
1593 1594
vm_paddr_t vm_phy_pages_alloc(struct kvm_vm *vm, size_t num,
			      vm_paddr_t paddr_min, uint32_t memslot)
1595 1596
{
	struct userspace_mem_region *region;
1597 1598 1599
	sparsebit_idx_t pg, base;

	TEST_ASSERT(num > 0, "Must allocate at least one page");
1600 1601

	TEST_ASSERT((paddr_min % vm->page_size) == 0, "Min physical address "
1602
		"not divisible by page size.\n"
1603 1604 1605 1606
		"  paddr_min: 0x%lx page_size: 0x%x",
		paddr_min, vm->page_size);

	region = memslot2region(vm, memslot);
1607 1608 1609 1610 1611 1612 1613 1614
	base = pg = paddr_min >> vm->page_shift;

	do {
		for (; pg < base + num; ++pg) {
			if (!sparsebit_is_set(region->unused_phy_pages, pg)) {
				base = pg = sparsebit_next_set(region->unused_phy_pages, pg);
				break;
			}
1615
		}
1616 1617 1618 1619 1620 1621 1622 1623 1624
	} while (pg && pg != base + num);

	if (pg == 0) {
		fprintf(stderr, "No guest physical page available, "
			"paddr_min: 0x%lx page_size: 0x%x memslot: %u\n",
			paddr_min, vm->page_size, memslot);
		fputs("---- vm dump ----\n", stderr);
		vm_dump(stderr, vm, 2);
		abort();
1625 1626
	}

1627 1628 1629 1630 1631
	for (pg = base; pg < base + num; ++pg)
		sparsebit_clear(region->unused_phy_pages, pg);

	return base * vm->page_size;
}
1632

1633 1634 1635 1636
vm_paddr_t vm_phy_page_alloc(struct kvm_vm *vm, vm_paddr_t paddr_min,
			     uint32_t memslot)
{
	return vm_phy_pages_alloc(vm, 1, paddr_min, memslot);
1637 1638
}

A
Andrew Jones 已提交
1639 1640
/*
 * Address Guest Virtual to Host Virtual
1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654
 *
 * Input Args:
 *   vm - Virtual Machine
 *   gva - VM virtual address
 *
 * Output Args: None
 *
 * Return:
 *   Equivalent host virtual address
 */
void *addr_gva2hva(struct kvm_vm *vm, vm_vaddr_t gva)
{
	return addr_gpa2hva(vm, addr_gva2gpa(vm, gva));
}
1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690

/*
 * Is Unrestricted Guest
 *
 * Input Args:
 *   vm - Virtual Machine
 *
 * Output Args: None
 *
 * Return: True if the unrestricted guest is set to 'Y', otherwise return false.
 *
 * Check if the unrestricted guest flag is enabled.
 */
bool vm_is_unrestricted_guest(struct kvm_vm *vm)
{
	char val = 'N';
	size_t count;
	FILE *f;

	if (vm == NULL) {
		/* Ensure that the KVM vendor-specific module is loaded. */
		f = fopen(KVM_DEV_PATH, "r");
		TEST_ASSERT(f != NULL, "Error in opening KVM dev file: %d",
			    errno);
		fclose(f);
	}

	f = fopen("/sys/module/kvm_intel/parameters/unrestricted_guest", "r");
	if (f) {
		count = fread(&val, sizeof(char), 1, f);
		TEST_ASSERT(count == 1, "Unable to read from param file.");
		fclose(f);
	}

	return val == 'Y';
}
1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705

unsigned int vm_get_page_size(struct kvm_vm *vm)
{
	return vm->page_size;
}

unsigned int vm_get_page_shift(struct kvm_vm *vm)
{
	return vm->page_shift;
}

unsigned int vm_get_max_gfn(struct kvm_vm *vm)
{
	return vm->max_gfn;
}