hyperv.c 26.3 KB
Newer Older
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
/*
 * KVM Microsoft Hyper-V emulation
 *
 * derived from arch/x86/kvm/x86.c
 *
 * Copyright (C) 2006 Qumranet, Inc.
 * Copyright (C) 2008 Qumranet, Inc.
 * Copyright IBM Corporation, 2008
 * Copyright 2010 Red Hat, Inc. and/or its affiliates.
 * Copyright (C) 2015 Andrey Smetanin <asmetanin@virtuozzo.com>
 *
 * Authors:
 *   Avi Kivity   <avi@qumranet.com>
 *   Yaniv Kamay  <yaniv@qumranet.com>
 *   Amit Shah    <amit.shah@qumranet.com>
 *   Ben-Ami Yassour <benami@il.ibm.com>
 *   Andrey Smetanin <asmetanin@virtuozzo.com>
 *
 * This work is licensed under the terms of the GNU GPL, version 2.  See
 * the COPYING file in the top-level directory.
 *
 */

#include "x86.h"
#include "lapic.h"
26
#include "ioapic.h"
27 28 29
#include "hyperv.h"

#include <linux/kvm_host.h>
30
#include <linux/highmem.h>
31
#include <asm/apicdef.h>
32 33 34 35
#include <trace/events/kvm.h>

#include "trace.h"

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
static inline u64 synic_read_sint(struct kvm_vcpu_hv_synic *synic, int sint)
{
	return atomic64_read(&synic->sint[sint]);
}

static inline int synic_get_sint_vector(u64 sint_value)
{
	if (sint_value & HV_SYNIC_SINT_MASKED)
		return -1;
	return sint_value & HV_SYNIC_SINT_VECTOR_MASK;
}

static bool synic_has_vector_connected(struct kvm_vcpu_hv_synic *synic,
				      int vector)
{
	int i;

	for (i = 0; i < ARRAY_SIZE(synic->sint); i++) {
		if (synic_get_sint_vector(synic_read_sint(synic, i)) == vector)
			return true;
	}
	return false;
}

static bool synic_has_vector_auto_eoi(struct kvm_vcpu_hv_synic *synic,
				     int vector)
{
	int i;
	u64 sint_value;

	for (i = 0; i < ARRAY_SIZE(synic->sint); i++) {
		sint_value = synic_read_sint(synic, i);
		if (synic_get_sint_vector(sint_value) == vector &&
		    sint_value & HV_SYNIC_SINT_AUTO_EOI)
			return true;
	}
	return false;
}

static int synic_set_sint(struct kvm_vcpu_hv_synic *synic, int sint, u64 data)
{
	int vector;

	vector = data & HV_SYNIC_SINT_VECTOR_MASK;
	if (vector < 16)
		return 1;
	/*
	 * Guest may configure multiple SINTs to use the same vector, so
	 * we maintain a bitmap of vectors handled by synic, and a
	 * bitmap of vectors with auto-eoi behavior.  The bitmaps are
	 * updated here, and atomically queried on fast paths.
	 */

	atomic64_set(&synic->sint[sint], data);

	if (synic_has_vector_connected(synic, vector))
		__set_bit(vector, synic->vec_bitmap);
	else
		__clear_bit(vector, synic->vec_bitmap);

	if (synic_has_vector_auto_eoi(synic, vector))
		__set_bit(vector, synic->auto_eoi_bitmap);
	else
		__clear_bit(vector, synic->auto_eoi_bitmap);

	/* Load SynIC vectors into EOI exit bitmap */
	kvm_make_request(KVM_REQ_SCAN_IOAPIC, synic_to_vcpu(synic));
	return 0;
}

static struct kvm_vcpu_hv_synic *synic_get(struct kvm *kvm, u32 vcpu_id)
{
	struct kvm_vcpu *vcpu;
	struct kvm_vcpu_hv_synic *synic;

	if (vcpu_id >= atomic_read(&kvm->online_vcpus))
		return NULL;
	vcpu = kvm_get_vcpu(kvm, vcpu_id);
	if (!vcpu)
		return NULL;
	synic = vcpu_to_synic(vcpu);
	return (synic->active) ? synic : NULL;
}

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
static void synic_clear_sint_msg_pending(struct kvm_vcpu_hv_synic *synic,
					u32 sint)
{
	struct kvm_vcpu *vcpu = synic_to_vcpu(synic);
	struct page *page;
	gpa_t gpa;
	struct hv_message *msg;
	struct hv_message_page *msg_page;

	gpa = synic->msg_page & PAGE_MASK;
	page = kvm_vcpu_gfn_to_page(vcpu, gpa >> PAGE_SHIFT);
	if (is_error_page(page)) {
		vcpu_err(vcpu, "Hyper-V SynIC can't get msg page, gpa 0x%llx\n",
			 gpa);
		return;
	}
	msg_page = kmap_atomic(page);

	msg = &msg_page->sint_message[sint];
	msg->header.message_flags.msg_pending = 0;

	kunmap_atomic(msg_page);
	kvm_release_page_dirty(page);
	kvm_vcpu_mark_page_dirty(vcpu, gpa >> PAGE_SHIFT);
}

146 147 148
static void kvm_hv_notify_acked_sint(struct kvm_vcpu *vcpu, u32 sint)
{
	struct kvm *kvm = vcpu->kvm;
149
	struct kvm_vcpu_hv_synic *synic = vcpu_to_synic(vcpu);
A
Andrey Smetanin 已提交
150 151 152
	struct kvm_vcpu_hv *hv_vcpu = vcpu_to_hv_vcpu(vcpu);
	struct kvm_vcpu_hv_stimer *stimer;
	int gsi, idx, stimers_pending;
153 154 155

	vcpu_debug(vcpu, "Hyper-V SynIC acked sint %d\n", sint);

156 157 158
	if (synic->msg_page & HV_SYNIC_SIMP_ENABLE)
		synic_clear_sint_msg_pending(synic, sint);

A
Andrey Smetanin 已提交
159 160 161 162 163 164 165 166 167 168 169 170 171 172 173
	/* Try to deliver pending Hyper-V SynIC timers messages */
	stimers_pending = 0;
	for (idx = 0; idx < ARRAY_SIZE(hv_vcpu->stimer); idx++) {
		stimer = &hv_vcpu->stimer[idx];
		if (stimer->msg_pending &&
		    (stimer->config & HV_STIMER_ENABLE) &&
		    HV_STIMER_SINT(stimer->config) == sint) {
			set_bit(stimer->index,
				hv_vcpu->stimer_pending_bitmap);
			stimers_pending++;
		}
	}
	if (stimers_pending)
		kvm_make_request(KVM_REQ_HV_STIMER, vcpu);

174
	idx = srcu_read_lock(&kvm->irq_srcu);
A
Andrey Smetanin 已提交
175
	gsi = atomic_read(&synic->sint_to_gsi[sint]);
176 177 178 179 180
	if (gsi != -1)
		kvm_notify_acked_gsi(kvm, gsi);
	srcu_read_unlock(&kvm->irq_srcu, idx);
}

A
Andrey Smetanin 已提交
181 182 183 184 185 186 187 188 189 190 191 192 193 194
static void synic_exit(struct kvm_vcpu_hv_synic *synic, u32 msr)
{
	struct kvm_vcpu *vcpu = synic_to_vcpu(synic);
	struct kvm_vcpu_hv *hv_vcpu = &vcpu->arch.hyperv;

	hv_vcpu->exit.type = KVM_EXIT_HYPERV_SYNIC;
	hv_vcpu->exit.u.synic.msr = msr;
	hv_vcpu->exit.u.synic.control = synic->control;
	hv_vcpu->exit.u.synic.evt_page = synic->evt_page;
	hv_vcpu->exit.u.synic.msg_page = synic->msg_page;

	kvm_make_request(KVM_REQ_HV_EXIT, vcpu);
}

195 196 197 198 199 200 201 202 203 204 205 206 207 208 209
static int synic_set_msr(struct kvm_vcpu_hv_synic *synic,
			 u32 msr, u64 data, bool host)
{
	struct kvm_vcpu *vcpu = synic_to_vcpu(synic);
	int ret;

	if (!synic->active)
		return 1;

	vcpu_debug(vcpu, "Hyper-V SynIC set msr 0x%x 0x%llx host %d\n",
		   msr, data, host);
	ret = 0;
	switch (msr) {
	case HV_X64_MSR_SCONTROL:
		synic->control = data;
A
Andrey Smetanin 已提交
210 211
		if (!host)
			synic_exit(synic, msr);
212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227
		break;
	case HV_X64_MSR_SVERSION:
		if (!host) {
			ret = 1;
			break;
		}
		synic->version = data;
		break;
	case HV_X64_MSR_SIEFP:
		if (data & HV_SYNIC_SIEFP_ENABLE)
			if (kvm_clear_guest(vcpu->kvm,
					    data & PAGE_MASK, PAGE_SIZE)) {
				ret = 1;
				break;
			}
		synic->evt_page = data;
A
Andrey Smetanin 已提交
228 229
		if (!host)
			synic_exit(synic, msr);
230 231 232 233 234 235 236 237 238
		break;
	case HV_X64_MSR_SIMP:
		if (data & HV_SYNIC_SIMP_ENABLE)
			if (kvm_clear_guest(vcpu->kvm,
					    data & PAGE_MASK, PAGE_SIZE)) {
				ret = 1;
				break;
			}
		synic->msg_page = data;
A
Andrey Smetanin 已提交
239 240
		if (!host)
			synic_exit(synic, msr);
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
		break;
	case HV_X64_MSR_EOM: {
		int i;

		for (i = 0; i < ARRAY_SIZE(synic->sint); i++)
			kvm_hv_notify_acked_sint(vcpu, i);
		break;
	}
	case HV_X64_MSR_SINT0 ... HV_X64_MSR_SINT15:
		ret = synic_set_sint(synic, msr - HV_X64_MSR_SINT0, data);
		break;
	default:
		ret = 1;
		break;
	}
	return ret;
}

static int synic_get_msr(struct kvm_vcpu_hv_synic *synic, u32 msr, u64 *pdata)
{
	int ret;

	if (!synic->active)
		return 1;

	ret = 0;
	switch (msr) {
	case HV_X64_MSR_SCONTROL:
		*pdata = synic->control;
		break;
	case HV_X64_MSR_SVERSION:
		*pdata = synic->version;
		break;
	case HV_X64_MSR_SIEFP:
		*pdata = synic->evt_page;
		break;
	case HV_X64_MSR_SIMP:
		*pdata = synic->msg_page;
		break;
	case HV_X64_MSR_EOM:
		*pdata = 0;
		break;
	case HV_X64_MSR_SINT0 ... HV_X64_MSR_SINT15:
		*pdata = atomic64_read(&synic->sint[msr - HV_X64_MSR_SINT0]);
		break;
	default:
		ret = 1;
		break;
	}
	return ret;
}

int synic_set_irq(struct kvm_vcpu_hv_synic *synic, u32 sint)
{
	struct kvm_vcpu *vcpu = synic_to_vcpu(synic);
	struct kvm_lapic_irq irq;
	int ret, vector;

	if (sint >= ARRAY_SIZE(synic->sint))
		return -EINVAL;

	vector = synic_get_sint_vector(synic_read_sint(synic, sint));
	if (vector < 0)
		return -ENOENT;

	memset(&irq, 0, sizeof(irq));
	irq.dest_id = kvm_apic_id(vcpu->arch.apic);
	irq.dest_mode = APIC_DEST_PHYSICAL;
	irq.delivery_mode = APIC_DM_FIXED;
	irq.vector = vector;
	irq.level = 1;

	ret = kvm_irq_delivery_to_apic(vcpu->kvm, NULL, &irq, NULL);
	vcpu_debug(vcpu, "Hyper-V SynIC set irq ret %d\n", ret);
	return ret;
}

int kvm_hv_synic_set_irq(struct kvm *kvm, u32 vcpu_id, u32 sint)
{
	struct kvm_vcpu_hv_synic *synic;

	synic = synic_get(kvm, vcpu_id);
	if (!synic)
		return -EINVAL;

	return synic_set_irq(synic, sint);
}

void kvm_hv_synic_send_eoi(struct kvm_vcpu *vcpu, int vector)
{
	struct kvm_vcpu_hv_synic *synic = vcpu_to_synic(vcpu);
	int i;

	vcpu_debug(vcpu, "Hyper-V SynIC send eoi vec %d\n", vector);

	for (i = 0; i < ARRAY_SIZE(synic->sint); i++)
		if (synic_get_sint_vector(synic_read_sint(synic, i)) == vector)
			kvm_hv_notify_acked_sint(vcpu, i);
}

static int kvm_hv_set_sint_gsi(struct kvm *kvm, u32 vcpu_id, u32 sint, int gsi)
{
	struct kvm_vcpu_hv_synic *synic;

	synic = synic_get(kvm, vcpu_id);
	if (!synic)
		return -EINVAL;

	if (sint >= ARRAY_SIZE(synic->sint_to_gsi))
		return -EINVAL;

	atomic_set(&synic->sint_to_gsi[sint], gsi);
	return 0;
}

void kvm_hv_irq_routing_update(struct kvm *kvm)
{
	struct kvm_irq_routing_table *irq_rt;
	struct kvm_kernel_irq_routing_entry *e;
	u32 gsi;

	irq_rt = srcu_dereference_check(kvm->irq_routing, &kvm->irq_srcu,
					lockdep_is_held(&kvm->irq_lock));

	for (gsi = 0; gsi < irq_rt->nr_rt_entries; gsi++) {
		hlist_for_each_entry(e, &irq_rt->map[gsi], link) {
			if (e->type == KVM_IRQ_ROUTING_HV_SINT)
				kvm_hv_set_sint_gsi(kvm, e->hv_sint.vcpu,
						    e->hv_sint.sint, gsi);
		}
	}
}

static void synic_init(struct kvm_vcpu_hv_synic *synic)
{
	int i;

	memset(synic, 0, sizeof(*synic));
	synic->version = HV_SYNIC_VERSION_1;
	for (i = 0; i < ARRAY_SIZE(synic->sint); i++) {
		atomic64_set(&synic->sint[i], HV_SYNIC_SINT_MASKED);
		atomic_set(&synic->sint_to_gsi[i], -1);
	}
}

386 387 388 389 390
static u64 get_time_ref_counter(struct kvm *kvm)
{
	return div_u64(get_kernel_ns() + kvm->arch.kvmclock_offset, 100);
}

A
Andrey Smetanin 已提交
391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406
static void stimer_mark_expired(struct kvm_vcpu_hv_stimer *stimer,
				bool vcpu_kick)
{
	struct kvm_vcpu *vcpu = stimer_to_vcpu(stimer);

	set_bit(stimer->index,
		vcpu_to_hv_vcpu(vcpu)->stimer_pending_bitmap);
	kvm_make_request(KVM_REQ_HV_STIMER, vcpu);
	if (vcpu_kick)
		kvm_vcpu_kick(vcpu);
}

static void stimer_cleanup(struct kvm_vcpu_hv_stimer *stimer)
{
	struct kvm_vcpu *vcpu = stimer_to_vcpu(stimer);

407
	hrtimer_cancel(&stimer->timer);
A
Andrey Smetanin 已提交
408 409 410
	clear_bit(stimer->index,
		  vcpu_to_hv_vcpu(vcpu)->stimer_pending_bitmap);
	stimer->msg_pending = false;
411
	stimer->exp_time = 0;
A
Andrey Smetanin 已提交
412 413 414 415 416 417 418 419 420 421 422 423
}

static enum hrtimer_restart stimer_timer_callback(struct hrtimer *timer)
{
	struct kvm_vcpu_hv_stimer *stimer;

	stimer = container_of(timer, struct kvm_vcpu_hv_stimer, timer);
	stimer_mark_expired(stimer, true);

	return HRTIMER_NORESTART;
}

424 425 426 427 428
/*
 * stimer_start() assumptions:
 * a) stimer->count is not equal to 0
 * b) stimer->config has HV_STIMER_ENABLE flag
 */
A
Andrey Smetanin 已提交
429 430 431 432 433 434 435 436 437
static int stimer_start(struct kvm_vcpu_hv_stimer *stimer)
{
	u64 time_now;
	ktime_t ktime_now;

	time_now = get_time_ref_counter(stimer_to_vcpu(stimer)->kvm);
	ktime_now = ktime_get();

	if (stimer->config & HV_STIMER_PERIODIC) {
438 439 440 441 442 443 444 445 446 447 448
		if (stimer->exp_time) {
			if (time_now >= stimer->exp_time) {
				u64 remainder;

				div64_u64_rem(time_now - stimer->exp_time,
					      stimer->count, &remainder);
				stimer->exp_time =
					time_now + (stimer->count - remainder);
			}
		} else
			stimer->exp_time = time_now + stimer->count;
A
Andrey Smetanin 已提交
449 450

		hrtimer_start(&stimer->timer,
451 452
			      ktime_add_ns(ktime_now,
					   100 * (stimer->exp_time - time_now)),
A
Andrey Smetanin 已提交
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
			      HRTIMER_MODE_ABS);
		return 0;
	}
	stimer->exp_time = stimer->count;
	if (time_now >= stimer->count) {
		/*
		 * Expire timer according to Hypervisor Top-Level Functional
		 * specification v4(15.3.1):
		 * "If a one shot is enabled and the specified count is in
		 * the past, it will expire immediately."
		 */
		stimer_mark_expired(stimer, false);
		return 0;
	}

	hrtimer_start(&stimer->timer,
		      ktime_add_ns(ktime_now, 100 * (stimer->count - time_now)),
		      HRTIMER_MODE_ABS);
	return 0;
}

static int stimer_set_config(struct kvm_vcpu_hv_stimer *stimer, u64 config,
			     bool host)
{
	if (stimer->count == 0 || HV_STIMER_SINT(config) == 0)
		config &= ~HV_STIMER_ENABLE;
	stimer->config = config;
	stimer_cleanup(stimer);
	if (stimer->config & HV_STIMER_ENABLE)
		if (stimer_start(stimer))
			return 1;
	return 0;
}

static int stimer_set_count(struct kvm_vcpu_hv_stimer *stimer, u64 count,
			    bool host)
{
	stimer->count = count;

	stimer_cleanup(stimer);
	if (stimer->count == 0)
		stimer->config &= ~HV_STIMER_ENABLE;
	else if (stimer->config & HV_STIMER_AUTOENABLE) {
		stimer->config |= HV_STIMER_ENABLE;
		if (stimer_start(stimer))
			return 1;
	}

	return 0;
}

static int stimer_get_config(struct kvm_vcpu_hv_stimer *stimer, u64 *pconfig)
{
	*pconfig = stimer->config;
	return 0;
}

static int stimer_get_count(struct kvm_vcpu_hv_stimer *stimer, u64 *pcount)
{
	*pcount = stimer->count;
	return 0;
}

static int synic_deliver_msg(struct kvm_vcpu_hv_synic *synic, u32 sint,
			     struct hv_message *src_msg)
{
	struct kvm_vcpu *vcpu = synic_to_vcpu(synic);
	struct page *page;
	gpa_t gpa;
	struct hv_message *dst_msg;
	int r;
	struct hv_message_page *msg_page;

	if (!(synic->msg_page & HV_SYNIC_SIMP_ENABLE))
		return -ENOENT;

	gpa = synic->msg_page & PAGE_MASK;
	page = kvm_vcpu_gfn_to_page(vcpu, gpa >> PAGE_SHIFT);
	if (is_error_page(page))
		return -EFAULT;

	msg_page = kmap_atomic(page);
	dst_msg = &msg_page->sint_message[sint];
	if (sync_cmpxchg(&dst_msg->header.message_type, HVMSG_NONE,
			 src_msg->header.message_type) != HVMSG_NONE) {
		dst_msg->header.message_flags.msg_pending = 1;
		r = -EAGAIN;
	} else {
		memcpy(&dst_msg->u.payload, &src_msg->u.payload,
		       src_msg->header.payload_size);
		dst_msg->header.message_type = src_msg->header.message_type;
		dst_msg->header.payload_size = src_msg->header.payload_size;
		r = synic_set_irq(synic, sint);
		if (r >= 1)
			r = 0;
		else if (r == 0)
			r = -EFAULT;
	}
	kunmap_atomic(msg_page);
	kvm_release_page_dirty(page);
	kvm_vcpu_mark_page_dirty(vcpu, gpa >> PAGE_SHIFT);
	return r;
}

static void stimer_send_msg(struct kvm_vcpu_hv_stimer *stimer)
{
	struct kvm_vcpu *vcpu = stimer_to_vcpu(stimer);
	struct hv_message *msg = &stimer->msg;
	struct hv_timer_message_payload *payload =
			(struct hv_timer_message_payload *)&msg->u.payload;
	int r;

	stimer->msg_pending = true;
	payload->expiration_time = stimer->exp_time;
	payload->delivery_time = get_time_ref_counter(vcpu->kvm);
	r = synic_deliver_msg(vcpu_to_synic(vcpu),
			      HV_STIMER_SINT(stimer->config), msg);
	if (!r)
		stimer->msg_pending = false;
}

static void stimer_expiration(struct kvm_vcpu_hv_stimer *stimer)
{
	stimer_send_msg(stimer);
	if (!(stimer->config & HV_STIMER_PERIODIC))
578
		stimer->config &= ~HV_STIMER_ENABLE;
A
Andrey Smetanin 已提交
579
	else
580
		stimer_start(stimer);
A
Andrey Smetanin 已提交
581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633
}

void kvm_hv_process_stimers(struct kvm_vcpu *vcpu)
{
	struct kvm_vcpu_hv *hv_vcpu = vcpu_to_hv_vcpu(vcpu);
	struct kvm_vcpu_hv_stimer *stimer;
	u64 time_now;
	int i;

	for (i = 0; i < ARRAY_SIZE(hv_vcpu->stimer); i++)
		if (test_and_clear_bit(i, hv_vcpu->stimer_pending_bitmap)) {
			stimer = &hv_vcpu->stimer[i];
			if (stimer->config & HV_STIMER_ENABLE) {
				time_now = get_time_ref_counter(vcpu->kvm);
				if (time_now >= stimer->exp_time)
					stimer_expiration(stimer);
			}
		}
}

void kvm_hv_vcpu_uninit(struct kvm_vcpu *vcpu)
{
	struct kvm_vcpu_hv *hv_vcpu = vcpu_to_hv_vcpu(vcpu);
	int i;

	for (i = 0; i < ARRAY_SIZE(hv_vcpu->stimer); i++)
		stimer_cleanup(&hv_vcpu->stimer[i]);
}

static void stimer_prepare_msg(struct kvm_vcpu_hv_stimer *stimer)
{
	struct hv_message *msg = &stimer->msg;
	struct hv_timer_message_payload *payload =
			(struct hv_timer_message_payload *)&msg->u.payload;

	memset(&msg->header, 0, sizeof(msg->header));
	msg->header.message_type = HVMSG_TIMER_EXPIRED;
	msg->header.payload_size = sizeof(*payload);

	payload->timer_index = stimer->index;
	payload->expiration_time = 0;
	payload->delivery_time = 0;
}

static void stimer_init(struct kvm_vcpu_hv_stimer *stimer, int timer_index)
{
	memset(stimer, 0, sizeof(*stimer));
	stimer->index = timer_index;
	hrtimer_init(&stimer->timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
	stimer->timer.function = stimer_timer_callback;
	stimer_prepare_msg(stimer);
}

634 635
void kvm_hv_vcpu_init(struct kvm_vcpu *vcpu)
{
A
Andrey Smetanin 已提交
636 637 638 639 640 641 642 643
	struct kvm_vcpu_hv *hv_vcpu = vcpu_to_hv_vcpu(vcpu);
	int i;

	synic_init(&hv_vcpu->synic);

	bitmap_zero(hv_vcpu->stimer_pending_bitmap, HV_SYNIC_STIMER_COUNT);
	for (i = 0; i < ARRAY_SIZE(hv_vcpu->stimer); i++)
		stimer_init(&hv_vcpu->stimer[i], i);
644 645 646 647 648 649 650 651 652 653 654 655 656
}

int kvm_hv_activate_synic(struct kvm_vcpu *vcpu)
{
	/*
	 * Hyper-V SynIC auto EOI SINT's are
	 * not compatible with APICV, so deactivate APICV
	 */
	kvm_vcpu_deactivate_apicv(vcpu);
	vcpu_to_synic(vcpu)->active = true;
	return 0;
}

657 658 659 660 661 662 663 664 665
static bool kvm_hv_msr_partition_wide(u32 msr)
{
	bool r = false;

	switch (msr) {
	case HV_X64_MSR_GUEST_OS_ID:
	case HV_X64_MSR_HYPERCALL:
	case HV_X64_MSR_REFERENCE_TSC:
	case HV_X64_MSR_TIME_REF_COUNT:
666 667
	case HV_X64_MSR_CRASH_CTL:
	case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4:
668
	case HV_X64_MSR_RESET:
669 670 671 672 673 674 675
		r = true;
		break;
	}

	return r;
}

676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732
static int kvm_hv_msr_get_crash_data(struct kvm_vcpu *vcpu,
				     u32 index, u64 *pdata)
{
	struct kvm_hv *hv = &vcpu->kvm->arch.hyperv;

	if (WARN_ON_ONCE(index >= ARRAY_SIZE(hv->hv_crash_param)))
		return -EINVAL;

	*pdata = hv->hv_crash_param[index];
	return 0;
}

static int kvm_hv_msr_get_crash_ctl(struct kvm_vcpu *vcpu, u64 *pdata)
{
	struct kvm_hv *hv = &vcpu->kvm->arch.hyperv;

	*pdata = hv->hv_crash_ctl;
	return 0;
}

static int kvm_hv_msr_set_crash_ctl(struct kvm_vcpu *vcpu, u64 data, bool host)
{
	struct kvm_hv *hv = &vcpu->kvm->arch.hyperv;

	if (host)
		hv->hv_crash_ctl = data & HV_X64_MSR_CRASH_CTL_NOTIFY;

	if (!host && (data & HV_X64_MSR_CRASH_CTL_NOTIFY)) {

		vcpu_debug(vcpu, "hv crash (0x%llx 0x%llx 0x%llx 0x%llx 0x%llx)\n",
			  hv->hv_crash_param[0],
			  hv->hv_crash_param[1],
			  hv->hv_crash_param[2],
			  hv->hv_crash_param[3],
			  hv->hv_crash_param[4]);

		/* Send notification about crash to user space */
		kvm_make_request(KVM_REQ_HV_CRASH, vcpu);
	}

	return 0;
}

static int kvm_hv_msr_set_crash_data(struct kvm_vcpu *vcpu,
				     u32 index, u64 data)
{
	struct kvm_hv *hv = &vcpu->kvm->arch.hyperv;

	if (WARN_ON_ONCE(index >= ARRAY_SIZE(hv->hv_crash_param)))
		return -EINVAL;

	hv->hv_crash_param[index] = data;
	return 0;
}

static int kvm_hv_set_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data,
			     bool host)
733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784
{
	struct kvm *kvm = vcpu->kvm;
	struct kvm_hv *hv = &kvm->arch.hyperv;

	switch (msr) {
	case HV_X64_MSR_GUEST_OS_ID:
		hv->hv_guest_os_id = data;
		/* setting guest os id to zero disables hypercall page */
		if (!hv->hv_guest_os_id)
			hv->hv_hypercall &= ~HV_X64_MSR_HYPERCALL_ENABLE;
		break;
	case HV_X64_MSR_HYPERCALL: {
		u64 gfn;
		unsigned long addr;
		u8 instructions[4];

		/* if guest os id is not set hypercall should remain disabled */
		if (!hv->hv_guest_os_id)
			break;
		if (!(data & HV_X64_MSR_HYPERCALL_ENABLE)) {
			hv->hv_hypercall = data;
			break;
		}
		gfn = data >> HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_SHIFT;
		addr = gfn_to_hva(kvm, gfn);
		if (kvm_is_error_hva(addr))
			return 1;
		kvm_x86_ops->patch_hypercall(vcpu, instructions);
		((unsigned char *)instructions)[3] = 0xc3; /* ret */
		if (__copy_to_user((void __user *)addr, instructions, 4))
			return 1;
		hv->hv_hypercall = data;
		mark_page_dirty(kvm, gfn);
		break;
	}
	case HV_X64_MSR_REFERENCE_TSC: {
		u64 gfn;
		HV_REFERENCE_TSC_PAGE tsc_ref;

		memset(&tsc_ref, 0, sizeof(tsc_ref));
		hv->hv_tsc_page = data;
		if (!(data & HV_X64_MSR_TSC_REFERENCE_ENABLE))
			break;
		gfn = data >> HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT;
		if (kvm_write_guest(
				kvm,
				gfn << HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT,
				&tsc_ref, sizeof(tsc_ref)))
			return 1;
		mark_page_dirty(kvm, gfn);
		break;
	}
785 786 787 788 789 790
	case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4:
		return kvm_hv_msr_set_crash_data(vcpu,
						 msr - HV_X64_MSR_CRASH_P0,
						 data);
	case HV_X64_MSR_CRASH_CTL:
		return kvm_hv_msr_set_crash_ctl(vcpu, data, host);
791 792 793 794 795 796
	case HV_X64_MSR_RESET:
		if (data == 1) {
			vcpu_debug(vcpu, "hyper-v reset requested\n");
			kvm_make_request(KVM_REQ_HV_RESET, vcpu);
		}
		break;
797 798 799 800 801 802 803 804
	default:
		vcpu_unimpl(vcpu, "Hyper-V uhandled wrmsr: 0x%x data 0x%llx\n",
			    msr, data);
		return 1;
	}
	return 0;
}

805 806 807 808 809 810 811 812 813 814
/* Calculate cpu time spent by current task in 100ns units */
static u64 current_task_runtime_100ns(void)
{
	cputime_t utime, stime;

	task_cputime_adjusted(current, &utime, &stime);
	return div_u64(cputime_to_nsecs(utime + stime), 100);
}

static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host)
815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847
{
	struct kvm_vcpu_hv *hv = &vcpu->arch.hyperv;

	switch (msr) {
	case HV_X64_MSR_APIC_ASSIST_PAGE: {
		u64 gfn;
		unsigned long addr;

		if (!(data & HV_X64_MSR_APIC_ASSIST_PAGE_ENABLE)) {
			hv->hv_vapic = data;
			if (kvm_lapic_enable_pv_eoi(vcpu, 0))
				return 1;
			break;
		}
		gfn = data >> HV_X64_MSR_APIC_ASSIST_PAGE_ADDRESS_SHIFT;
		addr = kvm_vcpu_gfn_to_hva(vcpu, gfn);
		if (kvm_is_error_hva(addr))
			return 1;
		if (__clear_user((void __user *)addr, PAGE_SIZE))
			return 1;
		hv->hv_vapic = data;
		kvm_vcpu_mark_page_dirty(vcpu, gfn);
		if (kvm_lapic_enable_pv_eoi(vcpu,
					    gfn_to_gpa(gfn) | KVM_MSR_ENABLED))
			return 1;
		break;
	}
	case HV_X64_MSR_EOI:
		return kvm_hv_vapic_msr_write(vcpu, APIC_EOI, data);
	case HV_X64_MSR_ICR:
		return kvm_hv_vapic_msr_write(vcpu, APIC_ICR, data);
	case HV_X64_MSR_TPR:
		return kvm_hv_vapic_msr_write(vcpu, APIC_TASKPRI, data);
848 849 850 851 852
	case HV_X64_MSR_VP_RUNTIME:
		if (!host)
			return 1;
		hv->runtime_offset = data - current_task_runtime_100ns();
		break;
853 854 855 856 857 858 859
	case HV_X64_MSR_SCONTROL:
	case HV_X64_MSR_SVERSION:
	case HV_X64_MSR_SIEFP:
	case HV_X64_MSR_SIMP:
	case HV_X64_MSR_EOM:
	case HV_X64_MSR_SINT0 ... HV_X64_MSR_SINT15:
		return synic_set_msr(vcpu_to_synic(vcpu), msr, data, host);
A
Andrey Smetanin 已提交
860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877
	case HV_X64_MSR_STIMER0_CONFIG:
	case HV_X64_MSR_STIMER1_CONFIG:
	case HV_X64_MSR_STIMER2_CONFIG:
	case HV_X64_MSR_STIMER3_CONFIG: {
		int timer_index = (msr - HV_X64_MSR_STIMER0_CONFIG)/2;

		return stimer_set_config(vcpu_to_stimer(vcpu, timer_index),
					 data, host);
	}
	case HV_X64_MSR_STIMER0_COUNT:
	case HV_X64_MSR_STIMER1_COUNT:
	case HV_X64_MSR_STIMER2_COUNT:
	case HV_X64_MSR_STIMER3_COUNT: {
		int timer_index = (msr - HV_X64_MSR_STIMER0_COUNT)/2;

		return stimer_set_count(vcpu_to_stimer(vcpu, timer_index),
					data, host);
	}
878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899
	default:
		vcpu_unimpl(vcpu, "Hyper-V uhandled wrmsr: 0x%x data 0x%llx\n",
			    msr, data);
		return 1;
	}

	return 0;
}

static int kvm_hv_get_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
{
	u64 data = 0;
	struct kvm *kvm = vcpu->kvm;
	struct kvm_hv *hv = &kvm->arch.hyperv;

	switch (msr) {
	case HV_X64_MSR_GUEST_OS_ID:
		data = hv->hv_guest_os_id;
		break;
	case HV_X64_MSR_HYPERCALL:
		data = hv->hv_hypercall;
		break;
900 901
	case HV_X64_MSR_TIME_REF_COUNT:
		data = get_time_ref_counter(kvm);
902 903 904 905
		break;
	case HV_X64_MSR_REFERENCE_TSC:
		data = hv->hv_tsc_page;
		break;
906 907 908 909 910 911
	case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4:
		return kvm_hv_msr_get_crash_data(vcpu,
						 msr - HV_X64_MSR_CRASH_P0,
						 pdata);
	case HV_X64_MSR_CRASH_CTL:
		return kvm_hv_msr_get_crash_ctl(vcpu, pdata);
912 913 914
	case HV_X64_MSR_RESET:
		data = 0;
		break;
915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950
	default:
		vcpu_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr);
		return 1;
	}

	*pdata = data;
	return 0;
}

static int kvm_hv_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
{
	u64 data = 0;
	struct kvm_vcpu_hv *hv = &vcpu->arch.hyperv;

	switch (msr) {
	case HV_X64_MSR_VP_INDEX: {
		int r;
		struct kvm_vcpu *v;

		kvm_for_each_vcpu(r, v, vcpu->kvm) {
			if (v == vcpu) {
				data = r;
				break;
			}
		}
		break;
	}
	case HV_X64_MSR_EOI:
		return kvm_hv_vapic_msr_read(vcpu, APIC_EOI, pdata);
	case HV_X64_MSR_ICR:
		return kvm_hv_vapic_msr_read(vcpu, APIC_ICR, pdata);
	case HV_X64_MSR_TPR:
		return kvm_hv_vapic_msr_read(vcpu, APIC_TASKPRI, pdata);
	case HV_X64_MSR_APIC_ASSIST_PAGE:
		data = hv->hv_vapic;
		break;
951 952 953
	case HV_X64_MSR_VP_RUNTIME:
		data = current_task_runtime_100ns() + hv->runtime_offset;
		break;
954 955 956 957 958 959 960
	case HV_X64_MSR_SCONTROL:
	case HV_X64_MSR_SVERSION:
	case HV_X64_MSR_SIEFP:
	case HV_X64_MSR_SIMP:
	case HV_X64_MSR_EOM:
	case HV_X64_MSR_SINT0 ... HV_X64_MSR_SINT15:
		return synic_get_msr(vcpu_to_synic(vcpu), msr, pdata);
A
Andrey Smetanin 已提交
961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978
	case HV_X64_MSR_STIMER0_CONFIG:
	case HV_X64_MSR_STIMER1_CONFIG:
	case HV_X64_MSR_STIMER2_CONFIG:
	case HV_X64_MSR_STIMER3_CONFIG: {
		int timer_index = (msr - HV_X64_MSR_STIMER0_CONFIG)/2;

		return stimer_get_config(vcpu_to_stimer(vcpu, timer_index),
					 pdata);
	}
	case HV_X64_MSR_STIMER0_COUNT:
	case HV_X64_MSR_STIMER1_COUNT:
	case HV_X64_MSR_STIMER2_COUNT:
	case HV_X64_MSR_STIMER3_COUNT: {
		int timer_index = (msr - HV_X64_MSR_STIMER0_COUNT)/2;

		return stimer_get_count(vcpu_to_stimer(vcpu, timer_index),
					pdata);
	}
979 980 981 982 983 984 985 986
	default:
		vcpu_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr);
		return 1;
	}
	*pdata = data;
	return 0;
}

987
int kvm_hv_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host)
988 989 990 991 992
{
	if (kvm_hv_msr_partition_wide(msr)) {
		int r;

		mutex_lock(&vcpu->kvm->lock);
993
		r = kvm_hv_set_msr_pw(vcpu, msr, data, host);
994 995 996
		mutex_unlock(&vcpu->kvm->lock);
		return r;
	} else
997
		return kvm_hv_set_msr(vcpu, msr, data, host);
998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 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 1044 1045 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
}

int kvm_hv_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
{
	if (kvm_hv_msr_partition_wide(msr)) {
		int r;

		mutex_lock(&vcpu->kvm->lock);
		r = kvm_hv_get_msr_pw(vcpu, msr, pdata);
		mutex_unlock(&vcpu->kvm->lock);
		return r;
	} else
		return kvm_hv_get_msr(vcpu, msr, pdata);
}

bool kvm_hv_hypercall_enabled(struct kvm *kvm)
{
	return kvm->arch.hyperv.hv_hypercall & HV_X64_MSR_HYPERCALL_ENABLE;
}

int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
{
	u64 param, ingpa, outgpa, ret;
	uint16_t code, rep_idx, rep_cnt, res = HV_STATUS_SUCCESS, rep_done = 0;
	bool fast, longmode;

	/*
	 * hypercall generates UD from non zero cpl and real mode
	 * per HYPER-V spec
	 */
	if (kvm_x86_ops->get_cpl(vcpu) != 0 || !is_protmode(vcpu)) {
		kvm_queue_exception(vcpu, UD_VECTOR);
		return 0;
	}

	longmode = is_64_bit_mode(vcpu);

	if (!longmode) {
		param = ((u64)kvm_register_read(vcpu, VCPU_REGS_RDX) << 32) |
			(kvm_register_read(vcpu, VCPU_REGS_RAX) & 0xffffffff);
		ingpa = ((u64)kvm_register_read(vcpu, VCPU_REGS_RBX) << 32) |
			(kvm_register_read(vcpu, VCPU_REGS_RCX) & 0xffffffff);
		outgpa = ((u64)kvm_register_read(vcpu, VCPU_REGS_RDI) << 32) |
			(kvm_register_read(vcpu, VCPU_REGS_RSI) & 0xffffffff);
	}
#ifdef CONFIG_X86_64
	else {
		param = kvm_register_read(vcpu, VCPU_REGS_RCX);
		ingpa = kvm_register_read(vcpu, VCPU_REGS_RDX);
		outgpa = kvm_register_read(vcpu, VCPU_REGS_R8);
	}
#endif

	code = param & 0xffff;
	fast = (param >> 16) & 0x1;
	rep_cnt = (param >> 32) & 0xfff;
	rep_idx = (param >> 48) & 0xfff;

	trace_kvm_hv_hypercall(code, fast, rep_cnt, rep_idx, ingpa, outgpa);

	switch (code) {
	case HV_X64_HV_NOTIFY_LONG_SPIN_WAIT:
		kvm_vcpu_on_spin(vcpu);
		break;
	default:
		res = HV_STATUS_INVALID_HYPERCALL_CODE;
		break;
	}

	ret = res | (((u64)rep_done & 0xfff) << 32);
	if (longmode) {
		kvm_register_write(vcpu, VCPU_REGS_RAX, ret);
	} else {
		kvm_register_write(vcpu, VCPU_REGS_RDX, ret >> 32);
		kvm_register_write(vcpu, VCPU_REGS_RAX, ret & 0xffffffff);
	}

	return 1;
}