xen.c 18.9 KB
Newer Older
1 2 3 4 5 6 7 8 9 10
// SPDX-License-Identifier: GPL-2.0
/*
 * Copyright © 2019 Oracle and/or its affiliates. All rights reserved.
 * Copyright © 2020 Amazon.com, Inc. or its affiliates. All Rights Reserved.
 *
 * KVM Xen emulation
 */

#include "x86.h"
#include "xen.h"
11
#include "hyperv.h"
12 13

#include <linux/kvm_host.h>
14
#include <linux/sched/stat.h>
15 16

#include <trace/events/kvm.h>
17
#include <xen/interface/xen.h>
18
#include <xen/interface/vcpu.h>
19 20 21

#include "trace.h"

22 23
DEFINE_STATIC_KEY_DEFERRED_FALSE(kvm_xen_enabled, HZ);

24 25
static int kvm_xen_shared_info_init(struct kvm *kvm, gfn_t gfn)
{
26 27
	gpa_t gpa = gfn_to_gpa(gfn);
	int wc_ofs, sec_hi_ofs;
28
	int ret = 0;
29 30
	int idx = srcu_read_lock(&kvm->srcu);

31 32
	if (kvm_is_error_hva(gfn_to_hva(kvm, gfn))) {
		ret = -EFAULT;
33
		goto out;
34 35
	}
	kvm->arch.xen.shinfo_gfn = gfn;
36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53

	/* Paranoia checks on the 32-bit struct layout */
	BUILD_BUG_ON(offsetof(struct compat_shared_info, wc) != 0x900);
	BUILD_BUG_ON(offsetof(struct compat_shared_info, arch.wc_sec_hi) != 0x924);
	BUILD_BUG_ON(offsetof(struct pvclock_vcpu_time_info, version) != 0);

	/* 32-bit location by default */
	wc_ofs = offsetof(struct compat_shared_info, wc);
	sec_hi_ofs = offsetof(struct compat_shared_info, arch.wc_sec_hi);

#ifdef CONFIG_X86_64
	/* Paranoia checks on the 64-bit struct layout */
	BUILD_BUG_ON(offsetof(struct shared_info, wc) != 0xc00);
	BUILD_BUG_ON(offsetof(struct shared_info, wc_sec_hi) != 0xc0c);

	if (kvm->arch.xen.long_mode) {
		wc_ofs = offsetof(struct shared_info, wc);
		sec_hi_ofs = offsetof(struct shared_info, wc_sec_hi);
54
	}
55 56 57 58
#endif

	kvm_write_wall_clock(kvm, gpa + wc_ofs, sec_hi_ofs - wc_ofs);
	kvm_make_all_cpus_request(kvm, KVM_REQ_MASTERCLOCK_UPDATE);
59

60
out:
61 62 63 64
	srcu_read_unlock(&kvm->srcu, idx);
	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 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
static void kvm_xen_update_runstate(struct kvm_vcpu *v, int state)
{
	struct kvm_vcpu_xen *vx = &v->arch.xen;
	u64 now = get_kvmclock_ns(v->kvm);
	u64 delta_ns = now - vx->runstate_entry_time;
	u64 run_delay = current->sched_info.run_delay;

	if (unlikely(!vx->runstate_entry_time))
		vx->current_runstate = RUNSTATE_offline;

	/*
	 * Time waiting for the scheduler isn't "stolen" if the
	 * vCPU wasn't running anyway.
	 */
	if (vx->current_runstate == RUNSTATE_running) {
		u64 steal_ns = run_delay - vx->last_steal;

		delta_ns -= steal_ns;

		vx->runstate_times[RUNSTATE_runnable] += steal_ns;
	}
	vx->last_steal = run_delay;

	vx->runstate_times[vx->current_runstate] += delta_ns;
	vx->current_runstate = state;
	vx->runstate_entry_time = now;
}

void kvm_xen_update_runstate_guest(struct kvm_vcpu *v, int state)
{
	struct kvm_vcpu_xen *vx = &v->arch.xen;
	uint64_t state_entry_time;
	unsigned int offset;

	kvm_xen_update_runstate(v, state);

	if (!vx->runstate_set)
		return;

	BUILD_BUG_ON(sizeof(struct compat_vcpu_runstate_info) != 0x2c);

	offset = offsetof(struct compat_vcpu_runstate_info, state_entry_time);
#ifdef CONFIG_X86_64
	/*
	 * The only difference is alignment of uint64_t in 32-bit.
	 * So the first field 'state' is accessed directly using
	 * offsetof() (where its offset happens to be zero), while the
	 * remaining fields which are all uint64_t, start at 'offset'
	 * which we tweak here by adding 4.
	 */
	BUILD_BUG_ON(offsetof(struct vcpu_runstate_info, state_entry_time) !=
		     offsetof(struct compat_vcpu_runstate_info, state_entry_time) + 4);
	BUILD_BUG_ON(offsetof(struct vcpu_runstate_info, time) !=
		     offsetof(struct compat_vcpu_runstate_info, time) + 4);

	if (v->kvm->arch.xen.long_mode)
		offset = offsetof(struct vcpu_runstate_info, state_entry_time);
#endif
	/*
	 * First write the updated state_entry_time at the appropriate
	 * location determined by 'offset'.
	 */
	state_entry_time = vx->runstate_entry_time;
	state_entry_time |= XEN_RUNSTATE_UPDATE;

	BUILD_BUG_ON(sizeof(((struct vcpu_runstate_info *)0)->state_entry_time) !=
		     sizeof(state_entry_time));
	BUILD_BUG_ON(sizeof(((struct compat_vcpu_runstate_info *)0)->state_entry_time) !=
		     sizeof(state_entry_time));

	if (kvm_write_guest_offset_cached(v->kvm, &v->arch.xen.runstate_cache,
					  &state_entry_time, offset,
					  sizeof(state_entry_time)))
		return;
	smp_wmb();

	/*
	 * Next, write the new runstate. This is in the *same* place
	 * for 32-bit and 64-bit guests, asserted here for paranoia.
	 */
	BUILD_BUG_ON(offsetof(struct vcpu_runstate_info, state) !=
		     offsetof(struct compat_vcpu_runstate_info, state));
	BUILD_BUG_ON(sizeof(((struct vcpu_runstate_info *)0)->state) !=
		     sizeof(vx->current_runstate));
	BUILD_BUG_ON(sizeof(((struct compat_vcpu_runstate_info *)0)->state) !=
		     sizeof(vx->current_runstate));

	if (kvm_write_guest_offset_cached(v->kvm, &v->arch.xen.runstate_cache,
					  &vx->current_runstate,
					  offsetof(struct vcpu_runstate_info, state),
					  sizeof(vx->current_runstate)))
		return;

	/*
	 * Write the actual runstate times immediately after the
	 * runstate_entry_time.
	 */
	BUILD_BUG_ON(offsetof(struct vcpu_runstate_info, state_entry_time) !=
		     offsetof(struct vcpu_runstate_info, time) - sizeof(u64));
	BUILD_BUG_ON(offsetof(struct compat_vcpu_runstate_info, state_entry_time) !=
		     offsetof(struct compat_vcpu_runstate_info, time) - sizeof(u64));
	BUILD_BUG_ON(sizeof(((struct vcpu_runstate_info *)0)->time) !=
		     sizeof(((struct compat_vcpu_runstate_info *)0)->time));
	BUILD_BUG_ON(sizeof(((struct vcpu_runstate_info *)0)->time) !=
		     sizeof(vx->runstate_times));

	if (kvm_write_guest_offset_cached(v->kvm, &v->arch.xen.runstate_cache,
					  &vx->runstate_times[0],
					  offset + sizeof(u64),
					  sizeof(vx->runstate_times)))
		return;

	smp_wmb();

	/*
	 * Finally, clear the XEN_RUNSTATE_UPDATE bit in the guest's
	 * runstate_entry_time field.
	 */

	state_entry_time &= ~XEN_RUNSTATE_UPDATE;
	if (kvm_write_guest_offset_cached(v->kvm, &v->arch.xen.runstate_cache,
					  &state_entry_time, offset,
					  sizeof(state_entry_time)))
		return;
}

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
int __kvm_xen_has_interrupt(struct kvm_vcpu *v)
{
	u8 rc = 0;

	/*
	 * If the global upcall vector (HVMIRQ_callback_vector) is set and
	 * the vCPU's evtchn_upcall_pending flag is set, the IRQ is pending.
	 */
	struct gfn_to_hva_cache *ghc = &v->arch.xen.vcpu_info_cache;
	struct kvm_memslots *slots = kvm_memslots(v->kvm);
	unsigned int offset = offsetof(struct vcpu_info, evtchn_upcall_pending);

	/* No need for compat handling here */
	BUILD_BUG_ON(offsetof(struct vcpu_info, evtchn_upcall_pending) !=
		     offsetof(struct compat_vcpu_info, evtchn_upcall_pending));
	BUILD_BUG_ON(sizeof(rc) !=
		     sizeof(((struct vcpu_info *)0)->evtchn_upcall_pending));
	BUILD_BUG_ON(sizeof(rc) !=
		     sizeof(((struct compat_vcpu_info *)0)->evtchn_upcall_pending));

	/*
	 * For efficiency, this mirrors the checks for using the valid
	 * cache in kvm_read_guest_offset_cached(), but just uses
	 * __get_user() instead. And falls back to the slow path.
	 */
	if (likely(slots->generation == ghc->generation &&
		   !kvm_is_error_hva(ghc->hva) && ghc->memslot)) {
		/* Fast path */
		__get_user(rc, (u8 __user *)ghc->hva + offset);
	} else {
		/* Slow path */
		kvm_read_guest_offset_cached(v->kvm, ghc, &rc, offset,
					     sizeof(rc));
	}

	return rc;
}

229 230 231 232
int kvm_xen_hvm_set_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data)
{
	int r = -ENOENT;

233 234
	mutex_lock(&kvm->lock);

235
	switch (data->type) {
236
	case KVM_XEN_ATTR_TYPE_LONG_MODE:
237 238 239 240 241 242 243
		if (!IS_ENABLED(CONFIG_64BIT) && data->u.long_mode) {
			r = -EINVAL;
		} else {
			kvm->arch.xen.long_mode = !!data->u.long_mode;
			r = 0;
		}
		break;
244

245
	case KVM_XEN_ATTR_TYPE_SHARED_INFO:
246
		if (data->u.shared_info.gfn == GPA_INVALID) {
247
			kvm->arch.xen.shinfo_gfn = GPA_INVALID;
248 249 250
			r = 0;
			break;
		}
251
		r = kvm_xen_shared_info_init(kvm, data->u.shared_info.gfn);
252
		break;
253

254 255

	case KVM_XEN_ATTR_TYPE_UPCALL_VECTOR:
256
		if (data->u.vector && data->u.vector < 0x10)
257 258 259 260 261 262 263
			r = -EINVAL;
		else {
			kvm->arch.xen.upcall_vector = data->u.vector;
			r = 0;
		}
		break;

264 265 266 267 268 269 270 271 272 273 274 275 276 277 278
	default:
		break;
	}

	mutex_unlock(&kvm->lock);
	return r;
}

int kvm_xen_hvm_get_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data)
{
	int r = -ENOENT;

	mutex_lock(&kvm->lock);

	switch (data->type) {
279 280 281 282
	case KVM_XEN_ATTR_TYPE_LONG_MODE:
		data->u.long_mode = kvm->arch.xen.long_mode;
		r = 0;
		break;
283 284

	case KVM_XEN_ATTR_TYPE_SHARED_INFO:
285
		data->u.shared_info.gfn = gpa_to_gfn(kvm->arch.xen.shinfo_gfn);
286
		r = 0;
287 288
		break;

289 290 291 292 293
	case KVM_XEN_ATTR_TYPE_UPCALL_VECTOR:
		data->u.vector = kvm->arch.xen.upcall_vector;
		r = 0;
		break;

294 295 296 297 298 299 300 301
	default:
		break;
	}

	mutex_unlock(&kvm->lock);
	return r;
}

302 303
int kvm_xen_vcpu_set_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data)
{
J
Joao Martins 已提交
304
	int idx, r = -ENOENT;
305 306

	mutex_lock(&vcpu->kvm->lock);
J
Joao Martins 已提交
307
	idx = srcu_read_lock(&vcpu->kvm->srcu);
308 309

	switch (data->type) {
J
Joao Martins 已提交
310 311 312 313
	case KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO:
		/* No compat necessary here. */
		BUILD_BUG_ON(sizeof(struct vcpu_info) !=
			     sizeof(struct compat_vcpu_info));
314 315
		BUILD_BUG_ON(offsetof(struct vcpu_info, time) !=
			     offsetof(struct compat_vcpu_info, time));
J
Joao Martins 已提交
316

317 318
		if (data->u.gpa == GPA_INVALID) {
			vcpu->arch.xen.vcpu_info_set = false;
319
			r = 0;
320 321 322
			break;
		}

J
Joao Martins 已提交
323 324 325 326
		r = kvm_gfn_to_hva_cache_init(vcpu->kvm,
					      &vcpu->arch.xen.vcpu_info_cache,
					      data->u.gpa,
					      sizeof(struct vcpu_info));
327
		if (!r) {
J
Joao Martins 已提交
328
			vcpu->arch.xen.vcpu_info_set = true;
329 330
			kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
		}
J
Joao Martins 已提交
331 332
		break;

333
	case KVM_XEN_VCPU_ATTR_TYPE_VCPU_TIME_INFO:
334 335
		if (data->u.gpa == GPA_INVALID) {
			vcpu->arch.xen.vcpu_time_info_set = false;
336
			r = 0;
337 338 339
			break;
		}

340 341 342 343 344 345 346 347 348 349
		r = kvm_gfn_to_hva_cache_init(vcpu->kvm,
					      &vcpu->arch.xen.vcpu_time_info_cache,
					      data->u.gpa,
					      sizeof(struct pvclock_vcpu_time_info));
		if (!r) {
			vcpu->arch.xen.vcpu_time_info_set = true;
			kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
		}
		break;

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
	case KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADDR:
		if (!sched_info_on()) {
			r = -EOPNOTSUPP;
			break;
		}
		if (data->u.gpa == GPA_INVALID) {
			vcpu->arch.xen.runstate_set = false;
			r = 0;
			break;
		}

		r = kvm_gfn_to_hva_cache_init(vcpu->kvm,
					      &vcpu->arch.xen.runstate_cache,
					      data->u.gpa,
					      sizeof(struct vcpu_runstate_info));
		if (!r) {
			vcpu->arch.xen.runstate_set = true;
		}
		break;

	case KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_CURRENT:
		if (!sched_info_on()) {
			r = -EOPNOTSUPP;
			break;
		}
		if (data->u.runstate.state > RUNSTATE_offline) {
			r = -EINVAL;
			break;
		}

		kvm_xen_update_runstate(vcpu, data->u.runstate.state);
		r = 0;
		break;

	case KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_DATA:
		if (!sched_info_on()) {
			r = -EOPNOTSUPP;
			break;
		}
		if (data->u.runstate.state > RUNSTATE_offline) {
			r = -EINVAL;
			break;
		}
		if (data->u.runstate.state_entry_time !=
		    (data->u.runstate.time_running +
		     data->u.runstate.time_runnable +
		     data->u.runstate.time_blocked +
		     data->u.runstate.time_offline)) {
			r = -EINVAL;
			break;
		}
		if (get_kvmclock_ns(vcpu->kvm) <
		    data->u.runstate.state_entry_time) {
			r = -EINVAL;
			break;
		}

		vcpu->arch.xen.current_runstate = data->u.runstate.state;
		vcpu->arch.xen.runstate_entry_time =
			data->u.runstate.state_entry_time;
		vcpu->arch.xen.runstate_times[RUNSTATE_running] =
			data->u.runstate.time_running;
		vcpu->arch.xen.runstate_times[RUNSTATE_runnable] =
			data->u.runstate.time_runnable;
		vcpu->arch.xen.runstate_times[RUNSTATE_blocked] =
			data->u.runstate.time_blocked;
		vcpu->arch.xen.runstate_times[RUNSTATE_offline] =
			data->u.runstate.time_offline;
		vcpu->arch.xen.last_steal = current->sched_info.run_delay;
		r = 0;
		break;

	case KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADJUST:
		if (!sched_info_on()) {
			r = -EOPNOTSUPP;
			break;
		}
		if (data->u.runstate.state > RUNSTATE_offline &&
		    data->u.runstate.state != (u64)-1) {
			r = -EINVAL;
			break;
		}
		/* The adjustment must add up */
		if (data->u.runstate.state_entry_time !=
		    (data->u.runstate.time_running +
		     data->u.runstate.time_runnable +
		     data->u.runstate.time_blocked +
		     data->u.runstate.time_offline)) {
			r = -EINVAL;
			break;
		}

		if (get_kvmclock_ns(vcpu->kvm) <
		    (vcpu->arch.xen.runstate_entry_time +
		     data->u.runstate.state_entry_time)) {
			r = -EINVAL;
			break;
		}

		vcpu->arch.xen.runstate_entry_time +=
			data->u.runstate.state_entry_time;
		vcpu->arch.xen.runstate_times[RUNSTATE_running] +=
			data->u.runstate.time_running;
		vcpu->arch.xen.runstate_times[RUNSTATE_runnable] +=
			data->u.runstate.time_runnable;
		vcpu->arch.xen.runstate_times[RUNSTATE_blocked] +=
			data->u.runstate.time_blocked;
		vcpu->arch.xen.runstate_times[RUNSTATE_offline] +=
			data->u.runstate.time_offline;

		if (data->u.runstate.state <= RUNSTATE_offline)
			kvm_xen_update_runstate(vcpu, data->u.runstate.state);
		r = 0;
		break;

465 466 467 468
	default:
		break;
	}

J
Joao Martins 已提交
469
	srcu_read_unlock(&vcpu->kvm->srcu, idx);
470 471 472 473 474 475 476 477 478 479 480
	mutex_unlock(&vcpu->kvm->lock);
	return r;
}

int kvm_xen_vcpu_get_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data)
{
	int r = -ENOENT;

	mutex_lock(&vcpu->kvm->lock);

	switch (data->type) {
J
Joao Martins 已提交
481
	case KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO:
482
		if (vcpu->arch.xen.vcpu_info_set)
J
Joao Martins 已提交
483
			data->u.gpa = vcpu->arch.xen.vcpu_info_cache.gpa;
484 485 486
		else
			data->u.gpa = GPA_INVALID;
		r = 0;
J
Joao Martins 已提交
487 488
		break;

489
	case KVM_XEN_VCPU_ATTR_TYPE_VCPU_TIME_INFO:
490
		if (vcpu->arch.xen.vcpu_time_info_set)
491
			data->u.gpa = vcpu->arch.xen.vcpu_time_info_cache.gpa;
492 493 494
		else
			data->u.gpa = GPA_INVALID;
		r = 0;
495 496
		break;

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
	case KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADDR:
		if (!sched_info_on()) {
			r = -EOPNOTSUPP;
			break;
		}
		if (vcpu->arch.xen.runstate_set) {
			data->u.gpa = vcpu->arch.xen.runstate_cache.gpa;
			r = 0;
		}
		break;

	case KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_CURRENT:
		if (!sched_info_on()) {
			r = -EOPNOTSUPP;
			break;
		}
		data->u.runstate.state = vcpu->arch.xen.current_runstate;
		r = 0;
		break;

	case KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_DATA:
		if (!sched_info_on()) {
			r = -EOPNOTSUPP;
			break;
		}
		data->u.runstate.state = vcpu->arch.xen.current_runstate;
		data->u.runstate.state_entry_time =
			vcpu->arch.xen.runstate_entry_time;
		data->u.runstate.time_running =
			vcpu->arch.xen.runstate_times[RUNSTATE_running];
		data->u.runstate.time_runnable =
			vcpu->arch.xen.runstate_times[RUNSTATE_runnable];
		data->u.runstate.time_blocked =
			vcpu->arch.xen.runstate_times[RUNSTATE_blocked];
		data->u.runstate.time_offline =
			vcpu->arch.xen.runstate_times[RUNSTATE_offline];
		r = 0;
		break;

	case KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADJUST:
		r = -EINVAL;
		break;

540 541 542 543 544 545 546 547
	default:
		break;
	}

	mutex_unlock(&vcpu->kvm->lock);
	return r;
}

548 549 550 551 552
int kvm_xen_write_hypercall_page(struct kvm_vcpu *vcpu, u64 data)
{
	struct kvm *kvm = vcpu->kvm;
	u32 page_num = data & ~PAGE_MASK;
	u64 page_addr = data & PAGE_MASK;
553 554 555 556
	bool lm = is_long_mode(vcpu);

	/* Latch long_mode for shared_info pages etc. */
	vcpu->kvm->arch.xen.long_mode = lm;
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

	/*
	 * If Xen hypercall intercept is enabled, fill the hypercall
	 * page with VMCALL/VMMCALL instructions since that's what
	 * we catch. Else the VMM has provided the hypercall pages
	 * with instructions of its own choosing, so use those.
	 */
	if (kvm_xen_hypercall_enabled(kvm)) {
		u8 instructions[32];
		int i;

		if (page_num)
			return 1;

		/* mov imm32, %eax */
		instructions[0] = 0xb8;

		/* vmcall / vmmcall */
		kvm_x86_ops.patch_hypercall(vcpu, instructions + 5);

		/* ret */
		instructions[8] = 0xc3;

		/* int3 to pad */
		memset(instructions + 9, 0xcc, sizeof(instructions) - 9);

		for (i = 0; i < PAGE_SIZE / sizeof(instructions); i++) {
			*(u32 *)&instructions[1] = i;
			if (kvm_vcpu_write_guest(vcpu,
						 page_addr + (i * sizeof(instructions)),
						 instructions, sizeof(instructions)))
				return 1;
		}
	} else {
591 592 593 594 595 596
		/*
		 * Note, truncation is a non-issue as 'lm' is guaranteed to be
		 * false for a 32-bit kernel, i.e. when hva_t is only 4 bytes.
		 */
		hva_t blob_addr = lm ? kvm->arch.xen_hvm_config.blob_addr_64
				     : kvm->arch.xen_hvm_config.blob_addr_32;
597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617
		u8 blob_size = lm ? kvm->arch.xen_hvm_config.blob_size_64
				  : kvm->arch.xen_hvm_config.blob_size_32;
		u8 *page;

		if (page_num >= blob_size)
			return 1;

		blob_addr += page_num * PAGE_SIZE;

		page = memdup_user((u8 __user *)blob_addr, PAGE_SIZE);
		if (IS_ERR(page))
			return PTR_ERR(page);

		if (kvm_vcpu_write_guest(vcpu, page_addr, page, PAGE_SIZE)) {
			kfree(page);
			return 1;
		}
	}
	return 0;
}

618 619 620 621 622 623 624 625 626 627 628 629 630 631
int kvm_xen_hvm_config(struct kvm *kvm, struct kvm_xen_hvm_config *xhc)
{
	if (xhc->flags & ~KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL)
		return -EINVAL;

	/*
	 * With hypercall interception the kernel generates its own
	 * hypercall page so it must not be provided.
	 */
	if ((xhc->flags & KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL) &&
	    (xhc->blob_addr_32 || xhc->blob_addr_64 ||
	     xhc->blob_size_32 || xhc->blob_size_64))
		return -EINVAL;

632 633 634 635 636 637 638
	mutex_lock(&kvm->lock);

	if (xhc->msr && !kvm->arch.xen_hvm_config.msr)
		static_branch_inc(&kvm_xen_enabled.key);
	else if (!xhc->msr && kvm->arch.xen_hvm_config.msr)
		static_branch_slow_dec_deferred(&kvm_xen_enabled);

639
	memcpy(&kvm->arch.xen_hvm_config, xhc, sizeof(*xhc));
640 641

	mutex_unlock(&kvm->lock);
642 643 644
	return 0;
}

645 646 647 648 649
void kvm_xen_init_vm(struct kvm *kvm)
{
	kvm->arch.xen.shinfo_gfn = GPA_INVALID;
}

650 651 652 653 654 655
void kvm_xen_destroy_vm(struct kvm *kvm)
{
	if (kvm->arch.xen_hvm_config.msr)
		static_branch_slow_dec_deferred(&kvm_xen_enabled);
}

656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678
static int kvm_xen_hypercall_set_result(struct kvm_vcpu *vcpu, u64 result)
{
	kvm_rax_write(vcpu, result);
	return kvm_skip_emulated_instruction(vcpu);
}

static int kvm_xen_hypercall_complete_userspace(struct kvm_vcpu *vcpu)
{
	struct kvm_run *run = vcpu->run;

	if (unlikely(!kvm_is_linear_rip(vcpu, vcpu->arch.xen.hypercall_rip)))
		return 1;

	return kvm_xen_hypercall_set_result(vcpu, run->xen.u.hcall.result);
}

int kvm_xen_hypercall(struct kvm_vcpu *vcpu)
{
	bool longmode;
	u64 input, params[6];

	input = (u64)kvm_register_read(vcpu, VCPU_REGS_RAX);

679 680
	/* Hyper-V hypercalls get bit 31 set in EAX */
	if ((input & 0x80000000) &&
681
	    kvm_hv_hypercall_enabled(vcpu))
682 683
		return kvm_hv_hypercall(vcpu);

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
	longmode = is_64_bit_mode(vcpu);
	if (!longmode) {
		params[0] = (u32)kvm_rbx_read(vcpu);
		params[1] = (u32)kvm_rcx_read(vcpu);
		params[2] = (u32)kvm_rdx_read(vcpu);
		params[3] = (u32)kvm_rsi_read(vcpu);
		params[4] = (u32)kvm_rdi_read(vcpu);
		params[5] = (u32)kvm_rbp_read(vcpu);
	}
#ifdef CONFIG_X86_64
	else {
		params[0] = (u64)kvm_rdi_read(vcpu);
		params[1] = (u64)kvm_rsi_read(vcpu);
		params[2] = (u64)kvm_rdx_read(vcpu);
		params[3] = (u64)kvm_r10_read(vcpu);
		params[4] = (u64)kvm_r8_read(vcpu);
		params[5] = (u64)kvm_r9_read(vcpu);
	}
#endif
	trace_kvm_xen_hypercall(input, params[0], params[1], params[2],
				params[3], params[4], params[5]);

	vcpu->run->exit_reason = KVM_EXIT_XEN;
	vcpu->run->xen.type = KVM_EXIT_XEN_HCALL;
	vcpu->run->xen.u.hcall.longmode = longmode;
	vcpu->run->xen.u.hcall.cpl = kvm_x86_ops.get_cpl(vcpu);
	vcpu->run->xen.u.hcall.input = input;
	vcpu->run->xen.u.hcall.params[0] = params[0];
	vcpu->run->xen.u.hcall.params[1] = params[1];
	vcpu->run->xen.u.hcall.params[2] = params[2];
	vcpu->run->xen.u.hcall.params[3] = params[3];
	vcpu->run->xen.u.hcall.params[4] = params[4];
	vcpu->run->xen.u.hcall.params[5] = params[5];
	vcpu->arch.xen.hypercall_rip = kvm_get_linear_rip(vcpu);
	vcpu->arch.complete_userspace_io =
		kvm_xen_hypercall_complete_userspace;

	return 0;
}