kvm-s390.c 60.0 KB
Newer Older
1
/*
2
 * hosting zSeries kernel virtual machines
3
 *
4
 * Copyright IBM Corp. 2008, 2009
5 6 7 8 9 10 11 12
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License (version 2 only)
 * as published by the Free Software Foundation.
 *
 *    Author(s): Carsten Otte <cotte@de.ibm.com>
 *               Christian Borntraeger <borntraeger@de.ibm.com>
 *               Heiko Carstens <heiko.carstens@de.ibm.com>
13
 *               Christian Ehrhardt <ehrhardt@de.ibm.com>
14
 *               Jason J. Herne <jjherne@us.ibm.com>
15 16 17 18 19
 */

#include <linux/compiler.h>
#include <linux/err.h>
#include <linux/fs.h>
20
#include <linux/hrtimer.h>
21 22 23 24
#include <linux/init.h>
#include <linux/kvm.h>
#include <linux/kvm_host.h>
#include <linux/module.h>
25
#include <linux/random.h>
26
#include <linux/slab.h>
27
#include <linux/timer.h>
28
#include <asm/asm-offsets.h>
29 30
#include <asm/lowcore.h>
#include <asm/pgtable.h>
31
#include <asm/nmi.h>
32
#include <asm/switch_to.h>
33
#include <asm/sclp.h>
34
#include "kvm-s390.h"
35 36
#include "gaccess.h"

37 38
#define CREATE_TRACE_POINTS
#include "trace.h"
39
#include "trace-s390.h"
40

41 42 43 44
#define VCPU_STAT(x) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU

struct kvm_stats_debugfs_item debugfs_entries[] = {
	{ "userspace_handled", VCPU_STAT(exit_userspace) },
45
	{ "exit_null", VCPU_STAT(exit_null) },
46 47 48 49
	{ "exit_validity", VCPU_STAT(exit_validity) },
	{ "exit_stop_request", VCPU_STAT(exit_stop_request) },
	{ "exit_external_request", VCPU_STAT(exit_external_request) },
	{ "exit_external_interrupt", VCPU_STAT(exit_external_interrupt) },
50 51 52
	{ "exit_instruction", VCPU_STAT(exit_instruction) },
	{ "exit_program_interruption", VCPU_STAT(exit_program_interruption) },
	{ "exit_instr_and_program_int", VCPU_STAT(exit_instr_and_program) },
53
	{ "halt_successful_poll", VCPU_STAT(halt_successful_poll) },
54
	{ "halt_wakeup", VCPU_STAT(halt_wakeup) },
55
	{ "instruction_lctlg", VCPU_STAT(instruction_lctlg) },
56
	{ "instruction_lctl", VCPU_STAT(instruction_lctl) },
57 58
	{ "instruction_stctl", VCPU_STAT(instruction_stctl) },
	{ "instruction_stctg", VCPU_STAT(instruction_stctg) },
59
	{ "deliver_emergency_signal", VCPU_STAT(deliver_emergency_signal) },
60
	{ "deliver_external_call", VCPU_STAT(deliver_external_call) },
61 62 63 64 65 66 67
	{ "deliver_service_signal", VCPU_STAT(deliver_service_signal) },
	{ "deliver_virtio_interrupt", VCPU_STAT(deliver_virtio_interrupt) },
	{ "deliver_stop_signal", VCPU_STAT(deliver_stop_signal) },
	{ "deliver_prefix_signal", VCPU_STAT(deliver_prefix_signal) },
	{ "deliver_restart_signal", VCPU_STAT(deliver_restart_signal) },
	{ "deliver_program_interruption", VCPU_STAT(deliver_program_int) },
	{ "exit_wait_state", VCPU_STAT(exit_wait_state) },
68
	{ "instruction_pfmf", VCPU_STAT(instruction_pfmf) },
69 70 71 72 73
	{ "instruction_stidp", VCPU_STAT(instruction_stidp) },
	{ "instruction_spx", VCPU_STAT(instruction_spx) },
	{ "instruction_stpx", VCPU_STAT(instruction_stpx) },
	{ "instruction_stap", VCPU_STAT(instruction_stap) },
	{ "instruction_storage_key", VCPU_STAT(instruction_storage_key) },
74
	{ "instruction_ipte_interlock", VCPU_STAT(instruction_ipte_interlock) },
75 76
	{ "instruction_stsch", VCPU_STAT(instruction_stsch) },
	{ "instruction_chsc", VCPU_STAT(instruction_chsc) },
77
	{ "instruction_essa", VCPU_STAT(instruction_essa) },
78 79
	{ "instruction_stsi", VCPU_STAT(instruction_stsi) },
	{ "instruction_stfl", VCPU_STAT(instruction_stfl) },
80
	{ "instruction_tprot", VCPU_STAT(instruction_tprot) },
81
	{ "instruction_sigp_sense", VCPU_STAT(instruction_sigp_sense) },
82
	{ "instruction_sigp_sense_running", VCPU_STAT(instruction_sigp_sense_running) },
83
	{ "instruction_sigp_external_call", VCPU_STAT(instruction_sigp_external_call) },
84
	{ "instruction_sigp_emergency", VCPU_STAT(instruction_sigp_emergency) },
85 86
	{ "instruction_sigp_cond_emergency", VCPU_STAT(instruction_sigp_cond_emergency) },
	{ "instruction_sigp_start", VCPU_STAT(instruction_sigp_start) },
87
	{ "instruction_sigp_stop", VCPU_STAT(instruction_sigp_stop) },
88 89
	{ "instruction_sigp_stop_store_status", VCPU_STAT(instruction_sigp_stop_store_status) },
	{ "instruction_sigp_store_status", VCPU_STAT(instruction_sigp_store_status) },
90
	{ "instruction_sigp_store_adtl_status", VCPU_STAT(instruction_sigp_store_adtl_status) },
91 92 93
	{ "instruction_sigp_set_arch", VCPU_STAT(instruction_sigp_arch) },
	{ "instruction_sigp_set_prefix", VCPU_STAT(instruction_sigp_prefix) },
	{ "instruction_sigp_restart", VCPU_STAT(instruction_sigp_restart) },
94 95 96
	{ "instruction_sigp_cpu_reset", VCPU_STAT(instruction_sigp_cpu_reset) },
	{ "instruction_sigp_init_cpu_reset", VCPU_STAT(instruction_sigp_init_cpu_reset) },
	{ "instruction_sigp_unknown", VCPU_STAT(instruction_sigp_unknown) },
97
	{ "diagnose_10", VCPU_STAT(diagnose_10) },
98
	{ "diagnose_44", VCPU_STAT(diagnose_44) },
99
	{ "diagnose_9c", VCPU_STAT(diagnose_9c) },
100 101 102
	{ NULL }
};

103 104 105 106
/* upper facilities limit for kvm */
unsigned long kvm_s390_fac_list_mask[] = {
	0xff82fffbf4fc2000UL,
	0x005c000000000000UL,
107
	0x4000000000000000UL,
108
};
109

110
unsigned long kvm_s390_fac_list_mask_size(void)
111
{
112 113
	BUILD_BUG_ON(ARRAY_SIZE(kvm_s390_fac_list_mask) > S390_ARCH_FAC_MASK_SIZE_U64);
	return ARRAY_SIZE(kvm_s390_fac_list_mask);
114 115
}

116 117
static struct gmap_notifier gmap_notifier;

118
/* Section: not file related */
119
int kvm_arch_hardware_enable(void)
120 121
{
	/* every s390 is virtualization enabled ;-) */
122
	return 0;
123 124
}

125 126
static void kvm_gmap_notifier(struct gmap *gmap, unsigned long address);

127 128
int kvm_arch_hardware_setup(void)
{
129 130
	gmap_notifier.notifier_call = kvm_gmap_notifier;
	gmap_register_ipte_notifier(&gmap_notifier);
131 132 133 134 135
	return 0;
}

void kvm_arch_hardware_unsetup(void)
{
136
	gmap_unregister_ipte_notifier(&gmap_notifier);
137 138 139 140
}

int kvm_arch_init(void *opaque)
{
141 142
	/* Register floating interrupt controller interface. */
	return kvm_register_device_ops(&kvm_flic_ops, KVM_DEV_TYPE_FLIC);
143 144 145 146 147 148 149 150 151 152 153
}

/* Section: device related */
long kvm_arch_dev_ioctl(struct file *filp,
			unsigned int ioctl, unsigned long arg)
{
	if (ioctl == KVM_S390_ENABLE_SIE)
		return s390_enable_sie();
	return -EINVAL;
}

154
int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
155
{
156 157
	int r;

158
	switch (ext) {
159
	case KVM_CAP_S390_PSW:
160
	case KVM_CAP_S390_GMAP:
161
	case KVM_CAP_SYNC_MMU:
162 163 164
#ifdef CONFIG_KVM_S390_UCONTROL
	case KVM_CAP_S390_UCONTROL:
#endif
165
	case KVM_CAP_ASYNC_PF:
166
	case KVM_CAP_SYNC_REGS:
167
	case KVM_CAP_ONE_REG:
168
	case KVM_CAP_ENABLE_CAP:
169
	case KVM_CAP_S390_CSS_SUPPORT:
170
	case KVM_CAP_IRQFD:
C
Cornelia Huck 已提交
171
	case KVM_CAP_IOEVENTFD:
172
	case KVM_CAP_DEVICE_CTRL:
173
	case KVM_CAP_ENABLE_CAP_VM:
174
	case KVM_CAP_S390_IRQCHIP:
175
	case KVM_CAP_VM_ATTRIBUTES:
176
	case KVM_CAP_MP_STATE:
177
	case KVM_CAP_S390_USER_SIGP:
178 179
		r = 1;
		break;
180 181 182 183
	case KVM_CAP_NR_VCPUS:
	case KVM_CAP_MAX_VCPUS:
		r = KVM_MAX_VCPUS;
		break;
184 185 186
	case KVM_CAP_NR_MEMSLOTS:
		r = KVM_USER_MEM_SLOTS;
		break;
187
	case KVM_CAP_S390_COW:
188
		r = MACHINE_HAS_ESOP;
189
		break;
190 191 192
	case KVM_CAP_S390_VECTOR_REGISTERS:
		r = MACHINE_HAS_VX;
		break;
193
	default:
194
		r = 0;
195
	}
196
	return r;
197 198
}

199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217
static void kvm_s390_sync_dirty_log(struct kvm *kvm,
					struct kvm_memory_slot *memslot)
{
	gfn_t cur_gfn, last_gfn;
	unsigned long address;
	struct gmap *gmap = kvm->arch.gmap;

	down_read(&gmap->mm->mmap_sem);
	/* Loop over all guest pages */
	last_gfn = memslot->base_gfn + memslot->npages;
	for (cur_gfn = memslot->base_gfn; cur_gfn <= last_gfn; cur_gfn++) {
		address = gfn_to_hva_memslot(memslot, cur_gfn);

		if (gmap_test_and_clear_dirty(address, gmap))
			mark_page_dirty(kvm, cur_gfn);
	}
	up_read(&gmap->mm->mmap_sem);
}

218 219 220 221 222 223 224
/* Section: vm related */
/*
 * Get (and clear) the dirty memory log for a memory slot.
 */
int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
			       struct kvm_dirty_log *log)
{
225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254
	int r;
	unsigned long n;
	struct kvm_memory_slot *memslot;
	int is_dirty = 0;

	mutex_lock(&kvm->slots_lock);

	r = -EINVAL;
	if (log->slot >= KVM_USER_MEM_SLOTS)
		goto out;

	memslot = id_to_memslot(kvm->memslots, log->slot);
	r = -ENOENT;
	if (!memslot->dirty_bitmap)
		goto out;

	kvm_s390_sync_dirty_log(kvm, memslot);
	r = kvm_get_dirty_log(kvm, log, &is_dirty);
	if (r)
		goto out;

	/* Clear the dirty log */
	if (is_dirty) {
		n = kvm_dirty_bitmap_bytes(memslot);
		memset(memslot->dirty_bitmap, 0, n);
	}
	r = 0;
out:
	mutex_unlock(&kvm->slots_lock);
	return r;
255 256
}

257 258 259 260 261 262 263 264
static int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap)
{
	int r;

	if (cap->flags)
		return -EINVAL;

	switch (cap->cap) {
265 266 267 268
	case KVM_CAP_S390_IRQCHIP:
		kvm->arch.use_irqchip = 1;
		r = 0;
		break;
269 270 271 272
	case KVM_CAP_S390_USER_SIGP:
		kvm->arch.user_sigp = 1;
		r = 0;
		break;
273 274 275 276
	case KVM_CAP_S390_VECTOR_REGISTERS:
		kvm->arch.use_vectors = MACHINE_HAS_VX;
		r = MACHINE_HAS_VX ? 0 : -EINVAL;
		break;
277 278 279 280 281 282 283
	default:
		r = -EINVAL;
		break;
	}
	return r;
}

284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301
static int kvm_s390_get_mem_control(struct kvm *kvm, struct kvm_device_attr *attr)
{
	int ret;

	switch (attr->attr) {
	case KVM_S390_VM_MEM_LIMIT_SIZE:
		ret = 0;
		if (put_user(kvm->arch.gmap->asce_end, (u64 __user *)attr->addr))
			ret = -EFAULT;
		break;
	default:
		ret = -ENXIO;
		break;
	}
	return ret;
}

static int kvm_s390_set_mem_control(struct kvm *kvm, struct kvm_device_attr *attr)
302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317
{
	int ret;
	unsigned int idx;
	switch (attr->attr) {
	case KVM_S390_VM_MEM_ENABLE_CMMA:
		ret = -EBUSY;
		mutex_lock(&kvm->lock);
		if (atomic_read(&kvm->online_vcpus) == 0) {
			kvm->arch.use_cmma = 1;
			ret = 0;
		}
		mutex_unlock(&kvm->lock);
		break;
	case KVM_S390_VM_MEM_CLR_CMMA:
		mutex_lock(&kvm->lock);
		idx = srcu_read_lock(&kvm->srcu);
318
		s390_reset_cmma(kvm->arch.gmap->mm);
319 320 321 322
		srcu_read_unlock(&kvm->srcu, idx);
		mutex_unlock(&kvm->lock);
		ret = 0;
		break;
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
	case KVM_S390_VM_MEM_LIMIT_SIZE: {
		unsigned long new_limit;

		if (kvm_is_ucontrol(kvm))
			return -EINVAL;

		if (get_user(new_limit, (u64 __user *)attr->addr))
			return -EFAULT;

		if (new_limit > kvm->arch.gmap->asce_end)
			return -E2BIG;

		ret = -EBUSY;
		mutex_lock(&kvm->lock);
		if (atomic_read(&kvm->online_vcpus) == 0) {
			/* gmap_alloc will round the limit up */
			struct gmap *new = gmap_alloc(current->mm, new_limit);

			if (!new) {
				ret = -ENOMEM;
			} else {
				gmap_free(kvm->arch.gmap);
				new->private = kvm;
				kvm->arch.gmap = new;
				ret = 0;
			}
		}
		mutex_unlock(&kvm->lock);
		break;
	}
353 354 355 356 357 358 359
	default:
		ret = -ENXIO;
		break;
	}
	return ret;
}

360 361 362 363 364 365 366
static void kvm_s390_vcpu_crypto_setup(struct kvm_vcpu *vcpu);

static int kvm_s390_vm_set_crypto(struct kvm *kvm, struct kvm_device_attr *attr)
{
	struct kvm_vcpu *vcpu;
	int i;

367
	if (!test_kvm_facility(kvm, 76))
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
		return -EINVAL;

	mutex_lock(&kvm->lock);
	switch (attr->attr) {
	case KVM_S390_VM_CRYPTO_ENABLE_AES_KW:
		get_random_bytes(
			kvm->arch.crypto.crycb->aes_wrapping_key_mask,
			sizeof(kvm->arch.crypto.crycb->aes_wrapping_key_mask));
		kvm->arch.crypto.aes_kw = 1;
		break;
	case KVM_S390_VM_CRYPTO_ENABLE_DEA_KW:
		get_random_bytes(
			kvm->arch.crypto.crycb->dea_wrapping_key_mask,
			sizeof(kvm->arch.crypto.crycb->dea_wrapping_key_mask));
		kvm->arch.crypto.dea_kw = 1;
		break;
	case KVM_S390_VM_CRYPTO_DISABLE_AES_KW:
		kvm->arch.crypto.aes_kw = 0;
		memset(kvm->arch.crypto.crycb->aes_wrapping_key_mask, 0,
			sizeof(kvm->arch.crypto.crycb->aes_wrapping_key_mask));
		break;
	case KVM_S390_VM_CRYPTO_DISABLE_DEA_KW:
		kvm->arch.crypto.dea_kw = 0;
		memset(kvm->arch.crypto.crycb->dea_wrapping_key_mask, 0,
			sizeof(kvm->arch.crypto.crycb->dea_wrapping_key_mask));
		break;
	default:
		mutex_unlock(&kvm->lock);
		return -ENXIO;
	}

	kvm_for_each_vcpu(i, vcpu, kvm) {
		kvm_s390_vcpu_crypto_setup(vcpu);
		exit_sie(vcpu);
	}
	mutex_unlock(&kvm->lock);
	return 0;
}

407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513
static int kvm_s390_set_tod_high(struct kvm *kvm, struct kvm_device_attr *attr)
{
	u8 gtod_high;

	if (copy_from_user(&gtod_high, (void __user *)attr->addr,
					   sizeof(gtod_high)))
		return -EFAULT;

	if (gtod_high != 0)
		return -EINVAL;

	return 0;
}

static int kvm_s390_set_tod_low(struct kvm *kvm, struct kvm_device_attr *attr)
{
	struct kvm_vcpu *cur_vcpu;
	unsigned int vcpu_idx;
	u64 host_tod, gtod;
	int r;

	if (copy_from_user(&gtod, (void __user *)attr->addr, sizeof(gtod)))
		return -EFAULT;

	r = store_tod_clock(&host_tod);
	if (r)
		return r;

	mutex_lock(&kvm->lock);
	kvm->arch.epoch = gtod - host_tod;
	kvm_for_each_vcpu(vcpu_idx, cur_vcpu, kvm) {
		cur_vcpu->arch.sie_block->epoch = kvm->arch.epoch;
		exit_sie(cur_vcpu);
	}
	mutex_unlock(&kvm->lock);
	return 0;
}

static int kvm_s390_set_tod(struct kvm *kvm, struct kvm_device_attr *attr)
{
	int ret;

	if (attr->flags)
		return -EINVAL;

	switch (attr->attr) {
	case KVM_S390_VM_TOD_HIGH:
		ret = kvm_s390_set_tod_high(kvm, attr);
		break;
	case KVM_S390_VM_TOD_LOW:
		ret = kvm_s390_set_tod_low(kvm, attr);
		break;
	default:
		ret = -ENXIO;
		break;
	}
	return ret;
}

static int kvm_s390_get_tod_high(struct kvm *kvm, struct kvm_device_attr *attr)
{
	u8 gtod_high = 0;

	if (copy_to_user((void __user *)attr->addr, &gtod_high,
					 sizeof(gtod_high)))
		return -EFAULT;

	return 0;
}

static int kvm_s390_get_tod_low(struct kvm *kvm, struct kvm_device_attr *attr)
{
	u64 host_tod, gtod;
	int r;

	r = store_tod_clock(&host_tod);
	if (r)
		return r;

	gtod = host_tod + kvm->arch.epoch;
	if (copy_to_user((void __user *)attr->addr, &gtod, sizeof(gtod)))
		return -EFAULT;

	return 0;
}

static int kvm_s390_get_tod(struct kvm *kvm, struct kvm_device_attr *attr)
{
	int ret;

	if (attr->flags)
		return -EINVAL;

	switch (attr->attr) {
	case KVM_S390_VM_TOD_HIGH:
		ret = kvm_s390_get_tod_high(kvm, attr);
		break;
	case KVM_S390_VM_TOD_LOW:
		ret = kvm_s390_get_tod_low(kvm, attr);
		break;
	default:
		ret = -ENXIO;
		break;
	}
	return ret;
}

514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533
static int kvm_s390_set_processor(struct kvm *kvm, struct kvm_device_attr *attr)
{
	struct kvm_s390_vm_cpu_processor *proc;
	int ret = 0;

	mutex_lock(&kvm->lock);
	if (atomic_read(&kvm->online_vcpus)) {
		ret = -EBUSY;
		goto out;
	}
	proc = kzalloc(sizeof(*proc), GFP_KERNEL);
	if (!proc) {
		ret = -ENOMEM;
		goto out;
	}
	if (!copy_from_user(proc, (void __user *)attr->addr,
			    sizeof(*proc))) {
		memcpy(&kvm->arch.model.cpu_id, &proc->cpuid,
		       sizeof(struct cpuid));
		kvm->arch.model.ibc = proc->ibc;
534
		memcpy(kvm->arch.model.fac->list, proc->fac_list,
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
		       S390_ARCH_FAC_LIST_SIZE_BYTE);
	} else
		ret = -EFAULT;
	kfree(proc);
out:
	mutex_unlock(&kvm->lock);
	return ret;
}

static int kvm_s390_set_cpu_model(struct kvm *kvm, struct kvm_device_attr *attr)
{
	int ret = -ENXIO;

	switch (attr->attr) {
	case KVM_S390_VM_CPU_PROCESSOR:
		ret = kvm_s390_set_processor(kvm, attr);
		break;
	}
	return ret;
}

static int kvm_s390_get_processor(struct kvm *kvm, struct kvm_device_attr *attr)
{
	struct kvm_s390_vm_cpu_processor *proc;
	int ret = 0;

	proc = kzalloc(sizeof(*proc), GFP_KERNEL);
	if (!proc) {
		ret = -ENOMEM;
		goto out;
	}
	memcpy(&proc->cpuid, &kvm->arch.model.cpu_id, sizeof(struct cpuid));
	proc->ibc = kvm->arch.model.ibc;
568
	memcpy(&proc->fac_list, kvm->arch.model.fac->list, S390_ARCH_FAC_LIST_SIZE_BYTE);
569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587
	if (copy_to_user((void __user *)attr->addr, proc, sizeof(*proc)))
		ret = -EFAULT;
	kfree(proc);
out:
	return ret;
}

static int kvm_s390_get_machine(struct kvm *kvm, struct kvm_device_attr *attr)
{
	struct kvm_s390_vm_cpu_machine *mach;
	int ret = 0;

	mach = kzalloc(sizeof(*mach), GFP_KERNEL);
	if (!mach) {
		ret = -ENOMEM;
		goto out;
	}
	get_cpu_id((struct cpuid *) &mach->cpuid);
	mach->ibc = sclp_get_ibc();
588 589
	memcpy(&mach->fac_mask, kvm->arch.model.fac->mask,
	       S390_ARCH_FAC_LIST_SIZE_BYTE);
590
	memcpy((unsigned long *)&mach->fac_list, S390_lowcore.stfle_fac_list,
591
	       S390_ARCH_FAC_LIST_SIZE_BYTE);
592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613
	if (copy_to_user((void __user *)attr->addr, mach, sizeof(*mach)))
		ret = -EFAULT;
	kfree(mach);
out:
	return ret;
}

static int kvm_s390_get_cpu_model(struct kvm *kvm, struct kvm_device_attr *attr)
{
	int ret = -ENXIO;

	switch (attr->attr) {
	case KVM_S390_VM_CPU_PROCESSOR:
		ret = kvm_s390_get_processor(kvm, attr);
		break;
	case KVM_S390_VM_CPU_MACHINE:
		ret = kvm_s390_get_machine(kvm, attr);
		break;
	}
	return ret;
}

614 615 616 617 618
static int kvm_s390_vm_set_attr(struct kvm *kvm, struct kvm_device_attr *attr)
{
	int ret;

	switch (attr->group) {
619
	case KVM_S390_VM_MEM_CTRL:
620
		ret = kvm_s390_set_mem_control(kvm, attr);
621
		break;
622 623 624
	case KVM_S390_VM_TOD:
		ret = kvm_s390_set_tod(kvm, attr);
		break;
625 626 627
	case KVM_S390_VM_CPU_MODEL:
		ret = kvm_s390_set_cpu_model(kvm, attr);
		break;
628 629 630
	case KVM_S390_VM_CRYPTO:
		ret = kvm_s390_vm_set_crypto(kvm, attr);
		break;
631 632 633 634 635 636 637 638 639 640
	default:
		ret = -ENXIO;
		break;
	}

	return ret;
}

static int kvm_s390_vm_get_attr(struct kvm *kvm, struct kvm_device_attr *attr)
{
641 642 643 644 645 646
	int ret;

	switch (attr->group) {
	case KVM_S390_VM_MEM_CTRL:
		ret = kvm_s390_get_mem_control(kvm, attr);
		break;
647 648 649
	case KVM_S390_VM_TOD:
		ret = kvm_s390_get_tod(kvm, attr);
		break;
650 651 652
	case KVM_S390_VM_CPU_MODEL:
		ret = kvm_s390_get_cpu_model(kvm, attr);
		break;
653 654 655 656 657 658
	default:
		ret = -ENXIO;
		break;
	}

	return ret;
659 660 661 662 663 664 665
}

static int kvm_s390_vm_has_attr(struct kvm *kvm, struct kvm_device_attr *attr)
{
	int ret;

	switch (attr->group) {
666 667 668 669
	case KVM_S390_VM_MEM_CTRL:
		switch (attr->attr) {
		case KVM_S390_VM_MEM_ENABLE_CMMA:
		case KVM_S390_VM_MEM_CLR_CMMA:
670
		case KVM_S390_VM_MEM_LIMIT_SIZE:
671 672 673 674 675 676 677
			ret = 0;
			break;
		default:
			ret = -ENXIO;
			break;
		}
		break;
678 679 680 681 682 683 684 685 686 687 688
	case KVM_S390_VM_TOD:
		switch (attr->attr) {
		case KVM_S390_VM_TOD_LOW:
		case KVM_S390_VM_TOD_HIGH:
			ret = 0;
			break;
		default:
			ret = -ENXIO;
			break;
		}
		break;
689 690 691 692 693 694 695 696 697 698 699
	case KVM_S390_VM_CPU_MODEL:
		switch (attr->attr) {
		case KVM_S390_VM_CPU_PROCESSOR:
		case KVM_S390_VM_CPU_MACHINE:
			ret = 0;
			break;
		default:
			ret = -ENXIO;
			break;
		}
		break;
700 701 702 703 704 705 706 707 708 709 710 711 712
	case KVM_S390_VM_CRYPTO:
		switch (attr->attr) {
		case KVM_S390_VM_CRYPTO_ENABLE_AES_KW:
		case KVM_S390_VM_CRYPTO_ENABLE_DEA_KW:
		case KVM_S390_VM_CRYPTO_DISABLE_AES_KW:
		case KVM_S390_VM_CRYPTO_DISABLE_DEA_KW:
			ret = 0;
			break;
		default:
			ret = -ENXIO;
			break;
		}
		break;
713 714 715 716 717 718 719 720
	default:
		ret = -ENXIO;
		break;
	}

	return ret;
}

721 722 723 724 725
long kvm_arch_vm_ioctl(struct file *filp,
		       unsigned int ioctl, unsigned long arg)
{
	struct kvm *kvm = filp->private_data;
	void __user *argp = (void __user *)arg;
726
	struct kvm_device_attr attr;
727 728 729
	int r;

	switch (ioctl) {
730 731 732 733 734 735 736 737 738
	case KVM_S390_INTERRUPT: {
		struct kvm_s390_interrupt s390int;

		r = -EFAULT;
		if (copy_from_user(&s390int, argp, sizeof(s390int)))
			break;
		r = kvm_s390_inject_vm(kvm, &s390int);
		break;
	}
739 740 741 742 743 744 745 746
	case KVM_ENABLE_CAP: {
		struct kvm_enable_cap cap;
		r = -EFAULT;
		if (copy_from_user(&cap, argp, sizeof(cap)))
			break;
		r = kvm_vm_ioctl_enable_cap(kvm, &cap);
		break;
	}
747 748 749 750 751 752 753 754 755 756 757 758
	case KVM_CREATE_IRQCHIP: {
		struct kvm_irq_routing_entry routing;

		r = -EINVAL;
		if (kvm->arch.use_irqchip) {
			/* Set up dummy routing. */
			memset(&routing, 0, sizeof(routing));
			kvm_set_irq_routing(kvm, &routing, 0, 0);
			r = 0;
		}
		break;
	}
759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779
	case KVM_SET_DEVICE_ATTR: {
		r = -EFAULT;
		if (copy_from_user(&attr, (void __user *)arg, sizeof(attr)))
			break;
		r = kvm_s390_vm_set_attr(kvm, &attr);
		break;
	}
	case KVM_GET_DEVICE_ATTR: {
		r = -EFAULT;
		if (copy_from_user(&attr, (void __user *)arg, sizeof(attr)))
			break;
		r = kvm_s390_vm_get_attr(kvm, &attr);
		break;
	}
	case KVM_HAS_DEVICE_ATTR: {
		r = -EFAULT;
		if (copy_from_user(&attr, (void __user *)arg, sizeof(attr)))
			break;
		r = kvm_s390_vm_has_attr(kvm, &attr);
		break;
	}
780
	default:
781
		r = -ENOTTY;
782 783 784 785 786
	}

	return r;
}

787 788 789
static int kvm_s390_query_ap_config(u8 *config)
{
	u32 fcn_code = 0x04000000UL;
790
	u32 cc = 0;
791

792
	memset(config, 0, 128);
793 794 795 796
	asm volatile(
		"lgr 0,%1\n"
		"lgr 2,%2\n"
		".long 0xb2af0000\n"		/* PQAP(QCI) */
797
		"0: ipm %0\n"
798
		"srl %0,28\n"
799 800 801
		"1:\n"
		EX_TABLE(0b, 1b)
		: "+r" (cc)
802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835
		: "r" (fcn_code), "r" (config)
		: "cc", "0", "2", "memory"
	);

	return cc;
}

static int kvm_s390_apxa_installed(void)
{
	u8 config[128];
	int cc;

	if (test_facility(2) && test_facility(12)) {
		cc = kvm_s390_query_ap_config(config);

		if (cc)
			pr_err("PQAP(QCI) failed with cc=%d", cc);
		else
			return config[0] & 0x40;
	}

	return 0;
}

static void kvm_s390_set_crycb_format(struct kvm *kvm)
{
	kvm->arch.crypto.crycbd = (__u32)(unsigned long) kvm->arch.crypto.crycb;

	if (kvm_s390_apxa_installed())
		kvm->arch.crypto.crycbd |= CRYCB_FORMAT2;
	else
		kvm->arch.crypto.crycbd |= CRYCB_FORMAT1;
}

836 837 838 839 840 841
static void kvm_s390_get_cpu_id(struct cpuid *cpu_id)
{
	get_cpu_id(cpu_id);
	cpu_id->version = 0xff;
}

842 843
static int kvm_s390_crypto_init(struct kvm *kvm)
{
844
	if (!test_kvm_facility(kvm, 76))
845 846 847 848 849 850 851
		return 0;

	kvm->arch.crypto.crycb = kzalloc(sizeof(*kvm->arch.crypto.crycb),
					 GFP_KERNEL | GFP_DMA);
	if (!kvm->arch.crypto.crycb)
		return -ENOMEM;

852
	kvm_s390_set_crycb_format(kvm);
853

854 855 856 857 858 859 860
	/* Enable AES/DEA protected key functions by default */
	kvm->arch.crypto.aes_kw = 1;
	kvm->arch.crypto.dea_kw = 1;
	get_random_bytes(kvm->arch.crypto.crycb->aes_wrapping_key_mask,
			 sizeof(kvm->arch.crypto.crycb->aes_wrapping_key_mask));
	get_random_bytes(kvm->arch.crypto.crycb->dea_wrapping_key_mask,
			 sizeof(kvm->arch.crypto.crycb->dea_wrapping_key_mask));
861

862 863 864
	return 0;
}

865
int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
866
{
867
	int i, rc;
868
	char debug_name[16];
869
	static unsigned long sca_offset;
870

871 872 873 874 875 876 877 878 879 880 881
	rc = -EINVAL;
#ifdef CONFIG_KVM_S390_UCONTROL
	if (type & ~KVM_VM_S390_UCONTROL)
		goto out_err;
	if ((type & KVM_VM_S390_UCONTROL) && (!capable(CAP_SYS_ADMIN)))
		goto out_err;
#else
	if (type)
		goto out_err;
#endif

882 883
	rc = s390_enable_sie();
	if (rc)
884
		goto out_err;
885

886 887
	rc = -ENOMEM;

888 889
	kvm->arch.sca = (struct sca_block *) get_zeroed_page(GFP_KERNEL);
	if (!kvm->arch.sca)
890
		goto out_err;
891 892 893 894
	spin_lock(&kvm_lock);
	sca_offset = (sca_offset + 16) & 0x7f0;
	kvm->arch.sca = (struct sca_block *) ((char *) kvm->arch.sca + sca_offset);
	spin_unlock(&kvm_lock);
895 896 897 898 899

	sprintf(debug_name, "kvm-%u", current->pid);

	kvm->arch.dbf = debug_register(debug_name, 8, 2, 8 * sizeof(long));
	if (!kvm->arch.dbf)
900
		goto out_err;
901

902 903 904
	/*
	 * The architectural maximum amount of facilities is 16 kbit. To store
	 * this amount, 2 kbyte of memory is required. Thus we need a full
905 906
	 * page to hold the guest facility list (arch.model.fac->list) and the
	 * facility mask (arch.model.fac->mask). Its address size has to be
907 908 909
	 * 31 bits and word aligned.
	 */
	kvm->arch.model.fac =
910
		(struct kvm_s390_fac *) get_zeroed_page(GFP_KERNEL | GFP_DMA);
911
	if (!kvm->arch.model.fac)
912
		goto out_err;
913

914
	/* Populate the facility mask initially. */
915
	memcpy(kvm->arch.model.fac->mask, S390_lowcore.stfle_fac_list,
916
	       S390_ARCH_FAC_LIST_SIZE_BYTE);
917 918
	for (i = 0; i < S390_ARCH_FAC_LIST_SIZE_U64; i++) {
		if (i < kvm_s390_fac_list_mask_size())
919
			kvm->arch.model.fac->mask[i] &= kvm_s390_fac_list_mask[i];
920
		else
921
			kvm->arch.model.fac->mask[i] = 0UL;
922 923
	}

924 925 926 927
	/* Populate the facility list initially. */
	memcpy(kvm->arch.model.fac->list, kvm->arch.model.fac->mask,
	       S390_ARCH_FAC_LIST_SIZE_BYTE);

928
	kvm_s390_get_cpu_id(&kvm->arch.model.cpu_id);
929
	kvm->arch.model.ibc = sclp_get_ibc() & 0x0fff;
930

931
	if (kvm_s390_crypto_init(kvm) < 0)
932
		goto out_err;
933

934 935
	spin_lock_init(&kvm->arch.float_int.lock);
	INIT_LIST_HEAD(&kvm->arch.float_int.list);
936
	init_waitqueue_head(&kvm->arch.ipte_wq);
937
	mutex_init(&kvm->arch.ipte_mutex);
938

939 940 941
	debug_register_view(kvm->arch.dbf, &debug_sprintf_view);
	VM_EVENT(kvm, 3, "%s", "vm created");

942 943 944
	if (type & KVM_VM_S390_UCONTROL) {
		kvm->arch.gmap = NULL;
	} else {
945
		kvm->arch.gmap = gmap_alloc(current->mm, (1UL << 44) - 1);
946
		if (!kvm->arch.gmap)
947
			goto out_err;
948
		kvm->arch.gmap->private = kvm;
949
		kvm->arch.gmap->pfault_enabled = 0;
950
	}
951 952

	kvm->arch.css_support = 0;
953
	kvm->arch.use_irqchip = 0;
954
	kvm->arch.use_vectors = 0;
955
	kvm->arch.epoch = 0;
956

957 958
	spin_lock_init(&kvm->arch.start_stop_lock);

959
	return 0;
960
out_err:
961
	kfree(kvm->arch.crypto.crycb);
962
	free_page((unsigned long)kvm->arch.model.fac);
963
	debug_unregister(kvm->arch.dbf);
964
	free_page((unsigned long)(kvm->arch.sca));
965
	return rc;
966 967
}

968 969 970
void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
{
	VCPU_EVENT(vcpu, 3, "%s", "free cpu");
971
	trace_kvm_s390_destroy_vcpu(vcpu->vcpu_id);
972
	kvm_s390_clear_local_irqs(vcpu);
973
	kvm_clear_async_pf_completion_queue(vcpu);
C
Carsten Otte 已提交
974 975 976 977 978 979 980
	if (!kvm_is_ucontrol(vcpu->kvm)) {
		clear_bit(63 - vcpu->vcpu_id,
			  (unsigned long *) &vcpu->kvm->arch.sca->mcn);
		if (vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sda ==
		    (__u64) vcpu->arch.sie_block)
			vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sda = 0;
	}
981
	smp_mb();
982 983 984 985

	if (kvm_is_ucontrol(vcpu->kvm))
		gmap_free(vcpu->arch.gmap);

986 987
	if (kvm_s390_cmma_enabled(vcpu->kvm))
		kvm_s390_vcpu_unsetup_cmma(vcpu);
988
	free_page((unsigned long)(vcpu->arch.sie_block));
989

990
	kvm_vcpu_uninit(vcpu);
991
	kmem_cache_free(kvm_vcpu_cache, vcpu);
992 993 994 995 996
}

static void kvm_free_vcpus(struct kvm *kvm)
{
	unsigned int i;
997
	struct kvm_vcpu *vcpu;
998

999 1000 1001 1002 1003 1004 1005 1006 1007
	kvm_for_each_vcpu(i, vcpu, kvm)
		kvm_arch_vcpu_destroy(vcpu);

	mutex_lock(&kvm->lock);
	for (i = 0; i < atomic_read(&kvm->online_vcpus); i++)
		kvm->vcpus[i] = NULL;

	atomic_set(&kvm->online_vcpus, 0);
	mutex_unlock(&kvm->lock);
1008 1009
}

1010 1011
void kvm_arch_destroy_vm(struct kvm *kvm)
{
1012
	kvm_free_vcpus(kvm);
1013
	free_page((unsigned long)kvm->arch.model.fac);
1014
	free_page((unsigned long)(kvm->arch.sca));
1015
	debug_unregister(kvm->arch.dbf);
1016
	kfree(kvm->arch.crypto.crycb);
1017 1018
	if (!kvm_is_ucontrol(kvm))
		gmap_free(kvm->arch.gmap);
1019
	kvm_s390_destroy_adapters(kvm);
1020
	kvm_s390_clear_float_irqs(kvm);
1021 1022 1023
}

/* Section: vcpu related */
1024 1025 1026 1027 1028 1029 1030 1031 1032 1033
static int __kvm_ucontrol_vcpu_init(struct kvm_vcpu *vcpu)
{
	vcpu->arch.gmap = gmap_alloc(current->mm, -1UL);
	if (!vcpu->arch.gmap)
		return -ENOMEM;
	vcpu->arch.gmap->private = vcpu->kvm;

	return 0;
}

1034 1035
int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
{
1036 1037
	vcpu->arch.pfault_token = KVM_S390_PFAULT_TOKEN_INVALID;
	kvm_clear_async_pf_completion_queue(vcpu);
1038 1039
	vcpu->run->kvm_valid_regs = KVM_SYNC_PREFIX |
				    KVM_SYNC_GPRS |
1040
				    KVM_SYNC_ACRS |
1041 1042 1043
				    KVM_SYNC_CRS |
				    KVM_SYNC_ARCH0 |
				    KVM_SYNC_PFAULT;
1044 1045
	if (test_kvm_facility(vcpu->kvm, 129))
		vcpu->run->kvm_valid_regs |= KVM_SYNC_VRS;
1046 1047 1048 1049

	if (kvm_is_ucontrol(vcpu->kvm))
		return __kvm_ucontrol_vcpu_init(vcpu);

1050 1051 1052 1053 1054
	return 0;
}

void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
{
1055
	save_fp_ctl(&vcpu->arch.host_fpregs.fpc);
1056 1057 1058 1059
	if (vcpu->kvm->arch.use_vectors)
		save_vx_regs((__vector128 *)&vcpu->arch.host_vregs->vrs);
	else
		save_fp_regs(vcpu->arch.host_fpregs.fprs);
1060
	save_access_regs(vcpu->arch.host_acrs);
1061 1062 1063 1064 1065 1066 1067
	if (vcpu->kvm->arch.use_vectors) {
		restore_fp_ctl(&vcpu->run->s.regs.fpc);
		restore_vx_regs((__vector128 *)&vcpu->run->s.regs.vrs);
	} else {
		restore_fp_ctl(&vcpu->arch.guest_fpregs.fpc);
		restore_fp_regs(vcpu->arch.guest_fpregs.fprs);
	}
1068
	restore_access_regs(vcpu->run->s.regs.acrs);
1069
	gmap_enable(vcpu->arch.gmap);
1070
	atomic_set_mask(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
1071 1072 1073 1074
}

void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
{
1075
	atomic_clear_mask(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
1076
	gmap_disable(vcpu->arch.gmap);
1077 1078 1079 1080 1081 1082 1083
	if (vcpu->kvm->arch.use_vectors) {
		save_fp_ctl(&vcpu->run->s.regs.fpc);
		save_vx_regs((__vector128 *)&vcpu->run->s.regs.vrs);
	} else {
		save_fp_ctl(&vcpu->arch.guest_fpregs.fpc);
		save_fp_regs(vcpu->arch.guest_fpregs.fprs);
	}
1084
	save_access_regs(vcpu->run->s.regs.acrs);
1085
	restore_fp_ctl(&vcpu->arch.host_fpregs.fpc);
1086 1087 1088 1089
	if (vcpu->kvm->arch.use_vectors)
		restore_vx_regs((__vector128 *)&vcpu->arch.host_vregs->vrs);
	else
		restore_fp_regs(vcpu->arch.host_fpregs.fprs);
1090 1091 1092 1093 1094 1095 1096 1097
	restore_access_regs(vcpu->arch.host_acrs);
}

static void kvm_s390_vcpu_initial_reset(struct kvm_vcpu *vcpu)
{
	/* this equals initial cpu reset in pop, but we don't switch to ESA */
	vcpu->arch.sie_block->gpsw.mask = 0UL;
	vcpu->arch.sie_block->gpsw.addr = 0UL;
1098
	kvm_s390_set_prefix(vcpu, 0);
1099 1100 1101 1102 1103 1104 1105 1106 1107
	vcpu->arch.sie_block->cputm     = 0UL;
	vcpu->arch.sie_block->ckc       = 0UL;
	vcpu->arch.sie_block->todpr     = 0;
	memset(vcpu->arch.sie_block->gcr, 0, 16 * sizeof(__u64));
	vcpu->arch.sie_block->gcr[0]  = 0xE0UL;
	vcpu->arch.sie_block->gcr[14] = 0xC2000000UL;
	vcpu->arch.guest_fpregs.fpc = 0;
	asm volatile("lfpc %0" : : "Q" (vcpu->arch.guest_fpregs.fpc));
	vcpu->arch.sie_block->gbea = 1;
1108
	vcpu->arch.sie_block->pp = 0;
1109 1110
	vcpu->arch.pfault_token = KVM_S390_PFAULT_TOKEN_INVALID;
	kvm_clear_async_pf_completion_queue(vcpu);
1111 1112
	if (!kvm_s390_user_cpu_state_ctrl(vcpu->kvm))
		kvm_s390_vcpu_stop(vcpu);
1113
	kvm_s390_clear_local_irqs(vcpu);
1114 1115
}

1116
void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
1117
{
1118 1119 1120
	mutex_lock(&vcpu->kvm->lock);
	vcpu->arch.sie_block->epoch = vcpu->kvm->arch.epoch;
	mutex_unlock(&vcpu->kvm->lock);
1121 1122
	if (!kvm_is_ucontrol(vcpu->kvm))
		vcpu->arch.gmap = vcpu->kvm->arch.gmap;
1123 1124
}

1125 1126
static void kvm_s390_vcpu_crypto_setup(struct kvm_vcpu *vcpu)
{
1127
	if (!test_kvm_facility(vcpu->kvm, 76))
1128 1129
		return;

1130 1131 1132 1133 1134 1135 1136
	vcpu->arch.sie_block->ecb3 &= ~(ECB3_AES | ECB3_DEA);

	if (vcpu->kvm->arch.crypto.aes_kw)
		vcpu->arch.sie_block->ecb3 |= ECB3_AES;
	if (vcpu->kvm->arch.crypto.dea_kw)
		vcpu->arch.sie_block->ecb3 |= ECB3_DEA;

1137 1138 1139
	vcpu->arch.sie_block->crycbd = vcpu->kvm->arch.crypto.crycbd;
}

1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156
void kvm_s390_vcpu_unsetup_cmma(struct kvm_vcpu *vcpu)
{
	free_page(vcpu->arch.sie_block->cbrlo);
	vcpu->arch.sie_block->cbrlo = 0;
}

int kvm_s390_vcpu_setup_cmma(struct kvm_vcpu *vcpu)
{
	vcpu->arch.sie_block->cbrlo = get_zeroed_page(GFP_KERNEL);
	if (!vcpu->arch.sie_block->cbrlo)
		return -ENOMEM;

	vcpu->arch.sie_block->ecb2 |= 0x80;
	vcpu->arch.sie_block->ecb2 &= ~0x08;
	return 0;
}

1157 1158 1159 1160 1161 1162 1163 1164 1165
static void kvm_s390_vcpu_setup_model(struct kvm_vcpu *vcpu)
{
	struct kvm_s390_cpu_model *model = &vcpu->kvm->arch.model;

	vcpu->arch.cpu_id = model->cpu_id;
	vcpu->arch.sie_block->ibc = model->ibc;
	vcpu->arch.sie_block->fac = (int) (long) model->fac->list;
}

1166 1167
int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
{
1168
	int rc = 0;
1169

1170 1171
	atomic_set(&vcpu->arch.sie_block->cpuflags, CPUSTAT_ZARCH |
						    CPUSTAT_SM |
1172 1173
						    CPUSTAT_STOPPED |
						    CPUSTAT_GED);
1174 1175
	kvm_s390_vcpu_setup_model(vcpu);

1176
	vcpu->arch.sie_block->ecb   = 6;
1177
	if (test_kvm_facility(vcpu->kvm, 50) && test_kvm_facility(vcpu->kvm, 73))
1178 1179
		vcpu->arch.sie_block->ecb |= 0x10;

1180
	vcpu->arch.sie_block->ecb2  = 8;
1181
	vcpu->arch.sie_block->eca   = 0xC1002000U;
1182 1183
	if (sclp_has_siif())
		vcpu->arch.sie_block->eca |= 1;
1184 1185
	if (sclp_has_sigpif())
		vcpu->arch.sie_block->eca |= 0x10000000U;
1186 1187 1188 1189
	if (vcpu->kvm->arch.use_vectors) {
		vcpu->arch.sie_block->eca |= 0x00020000;
		vcpu->arch.sie_block->ecd |= 0x20000000;
	}
1190
	vcpu->arch.sie_block->ictl |= ICTL_ISKE | ICTL_SSKE | ICTL_RRBE;
1191

1192 1193 1194 1195
	if (kvm_s390_cmma_enabled(vcpu->kvm)) {
		rc = kvm_s390_vcpu_setup_cmma(vcpu);
		if (rc)
			return rc;
1196
	}
1197
	hrtimer_init(&vcpu->arch.ckc_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
1198
	vcpu->arch.ckc_timer.function = kvm_s390_idle_wakeup;
1199

1200 1201
	kvm_s390_vcpu_crypto_setup(vcpu);

1202
	return rc;
1203 1204 1205 1206 1207
}

struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
				      unsigned int id)
{
1208
	struct kvm_vcpu *vcpu;
1209
	struct sie_page *sie_page;
1210 1211 1212 1213 1214 1215
	int rc = -EINVAL;

	if (id >= KVM_MAX_VCPUS)
		goto out;

	rc = -ENOMEM;
1216

1217
	vcpu = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL);
1218
	if (!vcpu)
1219
		goto out;
1220

1221 1222
	sie_page = (struct sie_page *) get_zeroed_page(GFP_KERNEL);
	if (!sie_page)
1223 1224
		goto out_free_cpu;

1225 1226
	vcpu->arch.sie_block = &sie_page->sie_block;
	vcpu->arch.sie_block->itdba = (unsigned long) &sie_page->itdb;
1227
	vcpu->arch.host_vregs = &sie_page->vregs;
1228

1229
	vcpu->arch.sie_block->icpua = id;
C
Carsten Otte 已提交
1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242
	if (!kvm_is_ucontrol(kvm)) {
		if (!kvm->arch.sca) {
			WARN_ON_ONCE(1);
			goto out_free_cpu;
		}
		if (!kvm->arch.sca->cpu[id].sda)
			kvm->arch.sca->cpu[id].sda =
				(__u64) vcpu->arch.sie_block;
		vcpu->arch.sie_block->scaoh =
			(__u32)(((__u64)kvm->arch.sca) >> 32);
		vcpu->arch.sie_block->scaol = (__u32)(__u64)kvm->arch.sca;
		set_bit(63 - id, (unsigned long *) &kvm->arch.sca->mcn);
	}
1243

1244 1245
	spin_lock_init(&vcpu->arch.local_int.lock);
	vcpu->arch.local_int.float_int = &kvm->arch.float_int;
1246
	vcpu->arch.local_int.wq = &vcpu->wq;
1247
	vcpu->arch.local_int.cpuflags = &vcpu->arch.sie_block->cpuflags;
1248

1249 1250
	rc = kvm_vcpu_init(vcpu, kvm, id);
	if (rc)
1251
		goto out_free_sie_block;
1252 1253
	VM_EVENT(kvm, 3, "create cpu %d at %p, sie block at %p", id, vcpu,
		 vcpu->arch.sie_block);
1254
	trace_kvm_s390_create_vcpu(id, vcpu, vcpu->arch.sie_block);
1255 1256

	return vcpu;
1257 1258
out_free_sie_block:
	free_page((unsigned long)(vcpu->arch.sie_block));
1259
out_free_cpu:
1260
	kmem_cache_free(kvm_vcpu_cache, vcpu);
1261
out:
1262 1263 1264 1265 1266
	return ERR_PTR(rc);
}

int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
{
1267
	return kvm_s390_vcpu_has_irq(vcpu, 0);
1268 1269
}

1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297
void s390_vcpu_block(struct kvm_vcpu *vcpu)
{
	atomic_set_mask(PROG_BLOCK_SIE, &vcpu->arch.sie_block->prog20);
}

void s390_vcpu_unblock(struct kvm_vcpu *vcpu)
{
	atomic_clear_mask(PROG_BLOCK_SIE, &vcpu->arch.sie_block->prog20);
}

/*
 * Kick a guest cpu out of SIE and wait until SIE is not running.
 * If the CPU is not running (e.g. waiting as idle) the function will
 * return immediately. */
void exit_sie(struct kvm_vcpu *vcpu)
{
	atomic_set_mask(CPUSTAT_STOP_INT, &vcpu->arch.sie_block->cpuflags);
	while (vcpu->arch.sie_block->prog0c & PROG_IN_SIE)
		cpu_relax();
}

/* Kick a guest cpu out of SIE and prevent SIE-reentry */
void exit_sie_sync(struct kvm_vcpu *vcpu)
{
	s390_vcpu_block(vcpu);
	exit_sie(vcpu);
}

1298 1299 1300 1301 1302 1303 1304 1305
static void kvm_gmap_notifier(struct gmap *gmap, unsigned long address)
{
	int i;
	struct kvm *kvm = gmap->private;
	struct kvm_vcpu *vcpu;

	kvm_for_each_vcpu(i, vcpu, kvm) {
		/* match against both prefix pages */
1306
		if (kvm_s390_get_prefix(vcpu) == (address & ~0x1000UL)) {
1307 1308 1309 1310 1311 1312 1313
			VCPU_EVENT(vcpu, 2, "gmap notifier for %lx", address);
			kvm_make_request(KVM_REQ_MMU_RELOAD, vcpu);
			exit_sie_sync(vcpu);
		}
	}
}

1314 1315 1316 1317 1318 1319 1320
int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu)
{
	/* kvm common code refers to this, but never calls it */
	BUG();
	return 0;
}

1321 1322 1323 1324 1325 1326
static int kvm_arch_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu,
					   struct kvm_one_reg *reg)
{
	int r = -EINVAL;

	switch (reg->id) {
1327 1328 1329 1330 1331 1332 1333 1334
	case KVM_REG_S390_TODPR:
		r = put_user(vcpu->arch.sie_block->todpr,
			     (u32 __user *)reg->addr);
		break;
	case KVM_REG_S390_EPOCHDIFF:
		r = put_user(vcpu->arch.sie_block->epoch,
			     (u64 __user *)reg->addr);
		break;
1335 1336 1337 1338 1339 1340 1341 1342
	case KVM_REG_S390_CPU_TIMER:
		r = put_user(vcpu->arch.sie_block->cputm,
			     (u64 __user *)reg->addr);
		break;
	case KVM_REG_S390_CLOCK_COMP:
		r = put_user(vcpu->arch.sie_block->ckc,
			     (u64 __user *)reg->addr);
		break;
1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354
	case KVM_REG_S390_PFTOKEN:
		r = put_user(vcpu->arch.pfault_token,
			     (u64 __user *)reg->addr);
		break;
	case KVM_REG_S390_PFCOMPARE:
		r = put_user(vcpu->arch.pfault_compare,
			     (u64 __user *)reg->addr);
		break;
	case KVM_REG_S390_PFSELECT:
		r = put_user(vcpu->arch.pfault_select,
			     (u64 __user *)reg->addr);
		break;
1355 1356 1357 1358
	case KVM_REG_S390_PP:
		r = put_user(vcpu->arch.sie_block->pp,
			     (u64 __user *)reg->addr);
		break;
1359 1360 1361 1362
	case KVM_REG_S390_GBEA:
		r = put_user(vcpu->arch.sie_block->gbea,
			     (u64 __user *)reg->addr);
		break;
1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375
	default:
		break;
	}

	return r;
}

static int kvm_arch_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu,
					   struct kvm_one_reg *reg)
{
	int r = -EINVAL;

	switch (reg->id) {
1376 1377 1378 1379 1380 1381 1382 1383
	case KVM_REG_S390_TODPR:
		r = get_user(vcpu->arch.sie_block->todpr,
			     (u32 __user *)reg->addr);
		break;
	case KVM_REG_S390_EPOCHDIFF:
		r = get_user(vcpu->arch.sie_block->epoch,
			     (u64 __user *)reg->addr);
		break;
1384 1385 1386 1387 1388 1389 1390 1391
	case KVM_REG_S390_CPU_TIMER:
		r = get_user(vcpu->arch.sie_block->cputm,
			     (u64 __user *)reg->addr);
		break;
	case KVM_REG_S390_CLOCK_COMP:
		r = get_user(vcpu->arch.sie_block->ckc,
			     (u64 __user *)reg->addr);
		break;
1392 1393 1394
	case KVM_REG_S390_PFTOKEN:
		r = get_user(vcpu->arch.pfault_token,
			     (u64 __user *)reg->addr);
1395 1396
		if (vcpu->arch.pfault_token == KVM_S390_PFAULT_TOKEN_INVALID)
			kvm_clear_async_pf_completion_queue(vcpu);
1397 1398 1399 1400 1401 1402 1403 1404 1405
		break;
	case KVM_REG_S390_PFCOMPARE:
		r = get_user(vcpu->arch.pfault_compare,
			     (u64 __user *)reg->addr);
		break;
	case KVM_REG_S390_PFSELECT:
		r = get_user(vcpu->arch.pfault_select,
			     (u64 __user *)reg->addr);
		break;
1406 1407 1408 1409
	case KVM_REG_S390_PP:
		r = get_user(vcpu->arch.sie_block->pp,
			     (u64 __user *)reg->addr);
		break;
1410 1411 1412 1413
	case KVM_REG_S390_GBEA:
		r = get_user(vcpu->arch.sie_block->gbea,
			     (u64 __user *)reg->addr);
		break;
1414 1415 1416 1417 1418 1419
	default:
		break;
	}

	return r;
}
1420

1421 1422 1423 1424 1425 1426 1427 1428
static int kvm_arch_vcpu_ioctl_initial_reset(struct kvm_vcpu *vcpu)
{
	kvm_s390_vcpu_initial_reset(vcpu);
	return 0;
}

int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
{
1429
	memcpy(&vcpu->run->s.regs.gprs, &regs->gprs, sizeof(regs->gprs));
1430 1431 1432 1433 1434
	return 0;
}

int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
{
1435
	memcpy(&regs->gprs, &vcpu->run->s.regs.gprs, sizeof(regs->gprs));
1436 1437 1438 1439 1440 1441
	return 0;
}

int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
				  struct kvm_sregs *sregs)
{
1442
	memcpy(&vcpu->run->s.regs.acrs, &sregs->acrs, sizeof(sregs->acrs));
1443
	memcpy(&vcpu->arch.sie_block->gcr, &sregs->crs, sizeof(sregs->crs));
1444
	restore_access_regs(vcpu->run->s.regs.acrs);
1445 1446 1447 1448 1449 1450
	return 0;
}

int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
				  struct kvm_sregs *sregs)
{
1451
	memcpy(&sregs->acrs, &vcpu->run->s.regs.acrs, sizeof(sregs->acrs));
1452 1453 1454 1455 1456 1457
	memcpy(&sregs->crs, &vcpu->arch.sie_block->gcr, sizeof(sregs->crs));
	return 0;
}

int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
{
1458 1459
	if (test_fp_ctl(fpu->fpc))
		return -EINVAL;
1460
	memcpy(&vcpu->arch.guest_fpregs.fprs, &fpu->fprs, sizeof(fpu->fprs));
1461 1462 1463
	vcpu->arch.guest_fpregs.fpc = fpu->fpc;
	restore_fp_ctl(&vcpu->arch.guest_fpregs.fpc);
	restore_fp_regs(vcpu->arch.guest_fpregs.fprs);
1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477
	return 0;
}

int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
{
	memcpy(&fpu->fprs, &vcpu->arch.guest_fpregs.fprs, sizeof(fpu->fprs));
	fpu->fpc = vcpu->arch.guest_fpregs.fpc;
	return 0;
}

static int kvm_arch_vcpu_ioctl_set_initial_psw(struct kvm_vcpu *vcpu, psw_t psw)
{
	int rc = 0;

1478
	if (!is_vcpu_stopped(vcpu))
1479
		rc = -EBUSY;
1480 1481 1482 1483
	else {
		vcpu->run->psw_mask = psw.mask;
		vcpu->run->psw_addr = psw.addr;
	}
1484 1485 1486 1487 1488 1489 1490 1491 1492
	return rc;
}

int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu,
				  struct kvm_translation *tr)
{
	return -EINVAL; /* not implemented yet */
}

1493 1494 1495 1496
#define VALID_GUESTDBG_FLAGS (KVM_GUESTDBG_SINGLESTEP | \
			      KVM_GUESTDBG_USE_HW_BP | \
			      KVM_GUESTDBG_ENABLE)

J
Jan Kiszka 已提交
1497 1498
int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
					struct kvm_guest_debug *dbg)
1499
{
1500 1501 1502 1503 1504
	int rc = 0;

	vcpu->guest_debug = 0;
	kvm_s390_clear_bp_data(vcpu);

1505
	if (dbg->control & ~VALID_GUESTDBG_FLAGS)
1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526
		return -EINVAL;

	if (dbg->control & KVM_GUESTDBG_ENABLE) {
		vcpu->guest_debug = dbg->control;
		/* enforce guest PER */
		atomic_set_mask(CPUSTAT_P, &vcpu->arch.sie_block->cpuflags);

		if (dbg->control & KVM_GUESTDBG_USE_HW_BP)
			rc = kvm_s390_import_bp_data(vcpu, dbg);
	} else {
		atomic_clear_mask(CPUSTAT_P, &vcpu->arch.sie_block->cpuflags);
		vcpu->arch.guestdbg.last_bp = 0;
	}

	if (rc) {
		vcpu->guest_debug = 0;
		kvm_s390_clear_bp_data(vcpu);
		atomic_clear_mask(CPUSTAT_P, &vcpu->arch.sie_block->cpuflags);
	}

	return rc;
1527 1528
}

1529 1530 1531
int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
				    struct kvm_mp_state *mp_state)
{
1532 1533 1534
	/* CHECK_STOP and LOAD are not supported yet */
	return is_vcpu_stopped(vcpu) ? KVM_MP_STATE_STOPPED :
				       KVM_MP_STATE_OPERATING;
1535 1536 1537 1538 1539
}

int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
				    struct kvm_mp_state *mp_state)
{
1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559
	int rc = 0;

	/* user space knows about this interface - let it control the state */
	vcpu->kvm->arch.user_cpu_state_ctrl = 1;

	switch (mp_state->mp_state) {
	case KVM_MP_STATE_STOPPED:
		kvm_s390_vcpu_stop(vcpu);
		break;
	case KVM_MP_STATE_OPERATING:
		kvm_s390_vcpu_start(vcpu);
		break;
	case KVM_MP_STATE_LOAD:
	case KVM_MP_STATE_CHECK_STOP:
		/* fall through - CHECK_STOP and LOAD are not supported yet */
	default:
		rc = -ENXIO;
	}

	return rc;
1560 1561
}

1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573
bool kvm_s390_cmma_enabled(struct kvm *kvm)
{
	if (!MACHINE_IS_LPAR)
		return false;
	/* only enable for z10 and later */
	if (!MACHINE_HAS_EDAT1)
		return false;
	if (!kvm->arch.use_cmma)
		return false;
	return true;
}

1574 1575 1576 1577 1578
static bool ibs_enabled(struct kvm_vcpu *vcpu)
{
	return atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_IBS;
}

1579 1580
static int kvm_s390_handle_requests(struct kvm_vcpu *vcpu)
{
1581 1582
retry:
	s390_vcpu_unblock(vcpu);
1583 1584 1585 1586 1587 1588 1589
	/*
	 * We use MMU_RELOAD just to re-arm the ipte notifier for the
	 * guest prefix page. gmap_ipte_notify will wait on the ptl lock.
	 * This ensures that the ipte instruction for this request has
	 * already finished. We might race against a second unmapper that
	 * wants to set the blocking bit. Lets just retry the request loop.
	 */
1590
	if (kvm_check_request(KVM_REQ_MMU_RELOAD, vcpu)) {
1591 1592
		int rc;
		rc = gmap_ipte_notify(vcpu->arch.gmap,
1593
				      kvm_s390_get_prefix(vcpu),
1594 1595 1596
				      PAGE_SIZE * 2);
		if (rc)
			return rc;
1597
		goto retry;
1598
	}
1599

1600 1601 1602 1603 1604
	if (kvm_check_request(KVM_REQ_TLB_FLUSH, vcpu)) {
		vcpu->arch.sie_block->ihcpu = 0xffff;
		goto retry;
	}

1605 1606 1607 1608 1609 1610 1611
	if (kvm_check_request(KVM_REQ_ENABLE_IBS, vcpu)) {
		if (!ibs_enabled(vcpu)) {
			trace_kvm_s390_enable_disable_ibs(vcpu->vcpu_id, 1);
			atomic_set_mask(CPUSTAT_IBS,
					&vcpu->arch.sie_block->cpuflags);
		}
		goto retry;
1612
	}
1613 1614 1615 1616 1617 1618 1619 1620 1621 1622

	if (kvm_check_request(KVM_REQ_DISABLE_IBS, vcpu)) {
		if (ibs_enabled(vcpu)) {
			trace_kvm_s390_enable_disable_ibs(vcpu->vcpu_id, 0);
			atomic_clear_mask(CPUSTAT_IBS,
					  &vcpu->arch.sie_block->cpuflags);
		}
		goto retry;
	}

1623 1624 1625
	/* nothing to do, just clear the request */
	clear_bit(KVM_REQ_UNHALT, &vcpu->requests);

1626 1627 1628
	return 0;
}

1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639
/**
 * kvm_arch_fault_in_page - fault-in guest page if necessary
 * @vcpu: The corresponding virtual cpu
 * @gpa: Guest physical address
 * @writable: Whether the page should be writable or not
 *
 * Make sure that a guest page has been faulted-in on the host.
 *
 * Return: Zero on success, negative error code otherwise.
 */
long kvm_arch_fault_in_page(struct kvm_vcpu *vcpu, gpa_t gpa, int writable)
1640
{
1641 1642
	return gmap_fault(vcpu->arch.gmap, gpa,
			  writable ? FAULT_FLAG_WRITE : 0);
1643 1644
}

1645 1646 1647 1648
static void __kvm_inject_pfault_token(struct kvm_vcpu *vcpu, bool start_token,
				      unsigned long token)
{
	struct kvm_s390_interrupt inti;
1649
	struct kvm_s390_irq irq;
1650 1651

	if (start_token) {
1652 1653 1654
		irq.u.ext.ext_params2 = token;
		irq.type = KVM_S390_INT_PFAULT_INIT;
		WARN_ON_ONCE(kvm_s390_inject_vcpu(vcpu, &irq));
1655 1656
	} else {
		inti.type = KVM_S390_INT_PFAULT_DONE;
1657
		inti.parm64 = token;
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 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703
		WARN_ON_ONCE(kvm_s390_inject_vm(vcpu->kvm, &inti));
	}
}

void kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu,
				     struct kvm_async_pf *work)
{
	trace_kvm_s390_pfault_init(vcpu, work->arch.pfault_token);
	__kvm_inject_pfault_token(vcpu, true, work->arch.pfault_token);
}

void kvm_arch_async_page_present(struct kvm_vcpu *vcpu,
				 struct kvm_async_pf *work)
{
	trace_kvm_s390_pfault_done(vcpu, work->arch.pfault_token);
	__kvm_inject_pfault_token(vcpu, false, work->arch.pfault_token);
}

void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu,
			       struct kvm_async_pf *work)
{
	/* s390 will always inject the page directly */
}

bool kvm_arch_can_inject_async_page_present(struct kvm_vcpu *vcpu)
{
	/*
	 * s390 will always inject the page directly,
	 * but we still want check_async_completion to cleanup
	 */
	return true;
}

static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu)
{
	hva_t hva;
	struct kvm_arch_async_pf arch;
	int rc;

	if (vcpu->arch.pfault_token == KVM_S390_PFAULT_TOKEN_INVALID)
		return 0;
	if ((vcpu->arch.sie_block->gpsw.mask & vcpu->arch.pfault_select) !=
	    vcpu->arch.pfault_compare)
		return 0;
	if (psw_extint_disabled(vcpu))
		return 0;
1704
	if (kvm_s390_vcpu_has_irq(vcpu, 0))
1705 1706 1707 1708 1709 1710
		return 0;
	if (!(vcpu->arch.sie_block->gcr[0] & 0x200ul))
		return 0;
	if (!vcpu->arch.gmap->pfault_enabled)
		return 0;

H
Heiko Carstens 已提交
1711 1712 1713
	hva = gfn_to_hva(vcpu->kvm, gpa_to_gfn(current->thread.gmap_addr));
	hva += current->thread.gmap_addr & ~PAGE_MASK;
	if (read_guest_real(vcpu, vcpu->arch.pfault_token, &arch.pfault_token, 8))
1714 1715 1716 1717 1718 1719
		return 0;

	rc = kvm_setup_async_pf(vcpu, current->thread.gmap_addr, hva, &arch);
	return rc;
}

1720
static int vcpu_pre_run(struct kvm_vcpu *vcpu)
1721
{
1722
	int rc, cpuflags;
1723

1724 1725 1726 1727 1728 1729 1730
	/*
	 * On s390 notifications for arriving pages will be delivered directly
	 * to the guest but the house keeping for completed pfaults is
	 * handled outside the worker.
	 */
	kvm_check_async_pf_completion(vcpu);

1731
	memcpy(&vcpu->arch.sie_block->gg14, &vcpu->run->s.regs.gprs[14], 16);
1732 1733 1734 1735

	if (need_resched())
		schedule();

1736
	if (test_cpu_flag(CIF_MCCK_PENDING))
1737 1738
		s390_handle_mcck();

1739 1740 1741 1742 1743
	if (!kvm_is_ucontrol(vcpu->kvm)) {
		rc = kvm_s390_deliver_pending_interrupts(vcpu);
		if (rc)
			return rc;
	}
C
Carsten Otte 已提交
1744

1745 1746 1747 1748
	rc = kvm_s390_handle_requests(vcpu);
	if (rc)
		return rc;

1749 1750 1751 1752 1753
	if (guestdbg_enabled(vcpu)) {
		kvm_s390_backup_guest_per_regs(vcpu);
		kvm_s390_patch_guest_per_regs(vcpu);
	}

1754
	vcpu->arch.sie_block->icptcode = 0;
1755 1756 1757
	cpuflags = atomic_read(&vcpu->arch.sie_block->cpuflags);
	VCPU_EVENT(vcpu, 6, "entering sie flags %x", cpuflags);
	trace_kvm_s390_sie_enter(vcpu, cpuflags);
1758

1759 1760 1761
	return 0;
}

1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786
static int vcpu_post_run_fault_in_sie(struct kvm_vcpu *vcpu)
{
	psw_t *psw = &vcpu->arch.sie_block->gpsw;
	u8 opcode;
	int rc;

	VCPU_EVENT(vcpu, 3, "%s", "fault in sie instruction");
	trace_kvm_s390_sie_fault(vcpu);

	/*
	 * We want to inject an addressing exception, which is defined as a
	 * suppressing or terminating exception. However, since we came here
	 * by a DAT access exception, the PSW still points to the faulting
	 * instruction since DAT exceptions are nullifying. So we've got
	 * to look up the current opcode to get the length of the instruction
	 * to be able to forward the PSW.
	 */
	rc = read_guest(vcpu, psw->addr, &opcode, 1);
	if (rc)
		return kvm_s390_inject_prog_cond(vcpu, rc);
	psw->addr = __rewind_psw(*psw, -insn_length(opcode));

	return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
}

1787 1788
static int vcpu_post_run(struct kvm_vcpu *vcpu, int exit_reason)
{
1789
	int rc = -1;
1790 1791 1792 1793 1794

	VCPU_EVENT(vcpu, 6, "exit sie icptcode %d",
		   vcpu->arch.sie_block->icptcode);
	trace_kvm_s390_sie_exit(vcpu, vcpu->arch.sie_block->icptcode);

1795 1796 1797
	if (guestdbg_enabled(vcpu))
		kvm_s390_restore_guest_per_regs(vcpu);

1798
	if (exit_reason >= 0) {
1799
		rc = 0;
1800 1801 1802 1803 1804 1805
	} else if (kvm_is_ucontrol(vcpu->kvm)) {
		vcpu->run->exit_reason = KVM_EXIT_S390_UCONTROL;
		vcpu->run->s390_ucontrol.trans_exc_code =
						current->thread.gmap_addr;
		vcpu->run->s390_ucontrol.pgm_code = 0x10;
		rc = -EREMOTE;
1806 1807

	} else if (current->thread.gmap_pfault) {
1808
		trace_kvm_s390_major_guest_pfault(vcpu);
1809
		current->thread.gmap_pfault = 0;
1810
		if (kvm_arch_setup_async_pf(vcpu)) {
1811
			rc = 0;
1812 1813 1814 1815
		} else {
			gpa_t gpa = current->thread.gmap_addr;
			rc = kvm_arch_fault_in_page(vcpu, gpa, 1);
		}
1816 1817
	}

1818 1819
	if (rc == -1)
		rc = vcpu_post_run_fault_in_sie(vcpu);
1820

1821
	memcpy(&vcpu->run->s.regs.gprs[14], &vcpu->arch.sie_block->gg14, 16);
1822

1823 1824
	if (rc == 0) {
		if (kvm_is_ucontrol(vcpu->kvm))
1825 1826
			/* Don't exit for host interrupts. */
			rc = vcpu->arch.sie_block->icptcode ? -EOPNOTSUPP : 0;
1827 1828 1829 1830
		else
			rc = kvm_handle_sie_intercept(vcpu);
	}

1831 1832 1833 1834 1835 1836 1837
	return rc;
}

static int __vcpu_run(struct kvm_vcpu *vcpu)
{
	int rc, exit_reason;

1838 1839 1840 1841 1842 1843
	/*
	 * We try to hold kvm->srcu during most of vcpu_run (except when run-
	 * ning the guest), so that memslots (and other stuff) are protected
	 */
	vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);

1844 1845 1846 1847
	do {
		rc = vcpu_pre_run(vcpu);
		if (rc)
			break;
1848

1849
		srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
1850 1851 1852 1853 1854 1855 1856 1857 1858 1859
		/*
		 * As PF_VCPU will be used in fault handler, between
		 * guest_enter and guest_exit should be no uaccess.
		 */
		preempt_disable();
		kvm_guest_enter();
		preempt_enable();
		exit_reason = sie64a(vcpu->arch.sie_block,
				     vcpu->run->s.regs.gprs);
		kvm_guest_exit();
1860
		vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
1861 1862

		rc = vcpu_post_run(vcpu, exit_reason);
1863
	} while (!signal_pending(current) && !guestdbg_exit_pending(vcpu) && !rc);
1864

1865
	srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
1866
	return rc;
1867 1868
}

1869 1870 1871 1872 1873 1874 1875 1876
static void sync_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
{
	vcpu->arch.sie_block->gpsw.mask = kvm_run->psw_mask;
	vcpu->arch.sie_block->gpsw.addr = kvm_run->psw_addr;
	if (kvm_run->kvm_dirty_regs & KVM_SYNC_PREFIX)
		kvm_s390_set_prefix(vcpu, kvm_run->s.regs.prefix);
	if (kvm_run->kvm_dirty_regs & KVM_SYNC_CRS) {
		memcpy(&vcpu->arch.sie_block->gcr, &kvm_run->s.regs.crs, 128);
1877 1878
		/* some control register changes require a tlb flush */
		kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890
	}
	if (kvm_run->kvm_dirty_regs & KVM_SYNC_ARCH0) {
		vcpu->arch.sie_block->cputm = kvm_run->s.regs.cputm;
		vcpu->arch.sie_block->ckc = kvm_run->s.regs.ckc;
		vcpu->arch.sie_block->todpr = kvm_run->s.regs.todpr;
		vcpu->arch.sie_block->pp = kvm_run->s.regs.pp;
		vcpu->arch.sie_block->gbea = kvm_run->s.regs.gbea;
	}
	if (kvm_run->kvm_dirty_regs & KVM_SYNC_PFAULT) {
		vcpu->arch.pfault_token = kvm_run->s.regs.pft;
		vcpu->arch.pfault_select = kvm_run->s.regs.pfs;
		vcpu->arch.pfault_compare = kvm_run->s.regs.pfc;
1891 1892
		if (vcpu->arch.pfault_token == KVM_S390_PFAULT_TOKEN_INVALID)
			kvm_clear_async_pf_completion_queue(vcpu);
1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912
	}
	kvm_run->kvm_dirty_regs = 0;
}

static void store_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
{
	kvm_run->psw_mask = vcpu->arch.sie_block->gpsw.mask;
	kvm_run->psw_addr = vcpu->arch.sie_block->gpsw.addr;
	kvm_run->s.regs.prefix = kvm_s390_get_prefix(vcpu);
	memcpy(&kvm_run->s.regs.crs, &vcpu->arch.sie_block->gcr, 128);
	kvm_run->s.regs.cputm = vcpu->arch.sie_block->cputm;
	kvm_run->s.regs.ckc = vcpu->arch.sie_block->ckc;
	kvm_run->s.regs.todpr = vcpu->arch.sie_block->todpr;
	kvm_run->s.regs.pp = vcpu->arch.sie_block->pp;
	kvm_run->s.regs.gbea = vcpu->arch.sie_block->gbea;
	kvm_run->s.regs.pft = vcpu->arch.pfault_token;
	kvm_run->s.regs.pfs = vcpu->arch.pfault_select;
	kvm_run->s.regs.pfc = vcpu->arch.pfault_compare;
}

1913 1914
int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
{
1915
	int rc;
1916 1917
	sigset_t sigsaved;

1918 1919 1920 1921 1922
	if (guestdbg_exit_pending(vcpu)) {
		kvm_s390_prepare_debug_exit(vcpu);
		return 0;
	}

1923 1924 1925
	if (vcpu->sigset_active)
		sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved);

1926 1927 1928 1929 1930 1931 1932
	if (!kvm_s390_user_cpu_state_ctrl(vcpu->kvm)) {
		kvm_s390_vcpu_start(vcpu);
	} else if (is_vcpu_stopped(vcpu)) {
		pr_err_ratelimited("kvm-s390: can't run stopped vcpu %d\n",
				   vcpu->vcpu_id);
		return -EINVAL;
	}
1933

1934
	sync_regs(vcpu, kvm_run);
1935

1936
	might_fault();
1937
	rc = __vcpu_run(vcpu);
1938

1939 1940
	if (signal_pending(current) && !rc) {
		kvm_run->exit_reason = KVM_EXIT_INTR;
1941
		rc = -EINTR;
1942
	}
1943

1944 1945 1946 1947 1948
	if (guestdbg_exit_pending(vcpu) && !rc)  {
		kvm_s390_prepare_debug_exit(vcpu);
		rc = 0;
	}

1949
	if (rc == -EOPNOTSUPP) {
1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962
		/* intercept cannot be handled in-kernel, prepare kvm-run */
		kvm_run->exit_reason         = KVM_EXIT_S390_SIEIC;
		kvm_run->s390_sieic.icptcode = vcpu->arch.sie_block->icptcode;
		kvm_run->s390_sieic.ipa      = vcpu->arch.sie_block->ipa;
		kvm_run->s390_sieic.ipb      = vcpu->arch.sie_block->ipb;
		rc = 0;
	}

	if (rc == -EREMOTE) {
		/* intercept was handled, but userspace support is needed
		 * kvm_run has been prepared by the handler */
		rc = 0;
	}
1963

1964
	store_regs(vcpu, kvm_run);
1965

1966 1967 1968 1969
	if (vcpu->sigset_active)
		sigprocmask(SIG_SETMASK, &sigsaved, NULL);

	vcpu->stat.exit_userspace++;
1970
	return rc;
1971 1972 1973 1974 1975 1976 1977 1978
}

/*
 * store status at address
 * we use have two special cases:
 * KVM_S390_STORE_STATUS_NOADDR: -> 0x1200 on 64 bit
 * KVM_S390_STORE_STATUS_PREFIXED: -> prefix
 */
1979
int kvm_s390_store_status_unloaded(struct kvm_vcpu *vcpu, unsigned long gpa)
1980
{
1981
	unsigned char archmode = 1;
1982
	unsigned int px;
1983
	u64 clkcomp;
1984
	int rc;
1985

1986 1987
	if (gpa == KVM_S390_STORE_STATUS_NOADDR) {
		if (write_guest_abs(vcpu, 163, &archmode, 1))
1988
			return -EFAULT;
1989 1990 1991
		gpa = SAVE_AREA_BASE;
	} else if (gpa == KVM_S390_STORE_STATUS_PREFIXED) {
		if (write_guest_real(vcpu, 163, &archmode, 1))
1992
			return -EFAULT;
1993 1994 1995 1996 1997 1998 1999 2000
		gpa = kvm_s390_real_to_abs(vcpu, SAVE_AREA_BASE);
	}
	rc = write_guest_abs(vcpu, gpa + offsetof(struct save_area, fp_regs),
			     vcpu->arch.guest_fpregs.fprs, 128);
	rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, gp_regs),
			      vcpu->run->s.regs.gprs, 128);
	rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, psw),
			      &vcpu->arch.sie_block->gpsw, 16);
2001
	px = kvm_s390_get_prefix(vcpu);
2002
	rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, pref_reg),
2003
			      &px, 4);
2004 2005 2006 2007 2008 2009 2010
	rc |= write_guest_abs(vcpu,
			      gpa + offsetof(struct save_area, fp_ctrl_reg),
			      &vcpu->arch.guest_fpregs.fpc, 4);
	rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, tod_reg),
			      &vcpu->arch.sie_block->todpr, 4);
	rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, timer),
			      &vcpu->arch.sie_block->cputm, 8);
2011
	clkcomp = vcpu->arch.sie_block->ckc >> 8;
2012 2013 2014 2015 2016 2017 2018
	rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, clk_cmp),
			      &clkcomp, 8);
	rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, acc_regs),
			      &vcpu->run->s.regs.acrs, 64);
	rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, ctrl_regs),
			      &vcpu->arch.sie_block->gcr, 128);
	return rc ? -EFAULT : 0;
2019 2020
}

2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034
int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr)
{
	/*
	 * The guest FPRS and ACRS are in the host FPRS/ACRS due to the lazy
	 * copying in vcpu load/put. Lets update our copies before we save
	 * it into the save area
	 */
	save_fp_ctl(&vcpu->arch.guest_fpregs.fpc);
	save_fp_regs(vcpu->arch.guest_fpregs.fprs);
	save_access_regs(vcpu->run->s.regs.acrs);

	return kvm_s390_store_status_unloaded(vcpu, addr);
}

E
Eric Farman 已提交
2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063
/*
 * store additional status at address
 */
int kvm_s390_store_adtl_status_unloaded(struct kvm_vcpu *vcpu,
					unsigned long gpa)
{
	/* Only bits 0-53 are used for address formation */
	if (!(gpa & ~0x3ff))
		return 0;

	return write_guest_abs(vcpu, gpa & ~0x3ff,
			       (void *)&vcpu->run->s.regs.vrs, 512);
}

int kvm_s390_vcpu_store_adtl_status(struct kvm_vcpu *vcpu, unsigned long addr)
{
	if (!test_kvm_facility(vcpu->kvm, 129))
		return 0;

	/*
	 * The guest VXRS are in the host VXRs due to the lazy
	 * copying in vcpu load/put. Let's update our copies before we save
	 * it into the save area.
	 */
	save_vx_regs((__vector128 *)&vcpu->run->s.regs.vrs);

	return kvm_s390_store_adtl_status_unloaded(vcpu, addr);
}

2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087
static void __disable_ibs_on_vcpu(struct kvm_vcpu *vcpu)
{
	kvm_check_request(KVM_REQ_ENABLE_IBS, vcpu);
	kvm_make_request(KVM_REQ_DISABLE_IBS, vcpu);
	exit_sie_sync(vcpu);
}

static void __disable_ibs_on_all_vcpus(struct kvm *kvm)
{
	unsigned int i;
	struct kvm_vcpu *vcpu;

	kvm_for_each_vcpu(i, vcpu, kvm) {
		__disable_ibs_on_vcpu(vcpu);
	}
}

static void __enable_ibs_on_vcpu(struct kvm_vcpu *vcpu)
{
	kvm_check_request(KVM_REQ_DISABLE_IBS, vcpu);
	kvm_make_request(KVM_REQ_ENABLE_IBS, vcpu);
	exit_sie_sync(vcpu);
}

2088 2089
void kvm_s390_vcpu_start(struct kvm_vcpu *vcpu)
{
2090 2091 2092 2093 2094
	int i, online_vcpus, started_vcpus = 0;

	if (!is_vcpu_stopped(vcpu))
		return;

2095
	trace_kvm_s390_vcpu_start_stop(vcpu->vcpu_id, 1);
2096
	/* Only one cpu at a time may enter/leave the STOPPED state. */
2097
	spin_lock(&vcpu->kvm->arch.start_stop_lock);
2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116
	online_vcpus = atomic_read(&vcpu->kvm->online_vcpus);

	for (i = 0; i < online_vcpus; i++) {
		if (!is_vcpu_stopped(vcpu->kvm->vcpus[i]))
			started_vcpus++;
	}

	if (started_vcpus == 0) {
		/* we're the only active VCPU -> speed it up */
		__enable_ibs_on_vcpu(vcpu);
	} else if (started_vcpus == 1) {
		/*
		 * As we are starting a second VCPU, we have to disable
		 * the IBS facility on all VCPUs to remove potentially
		 * oustanding ENABLE requests.
		 */
		__disable_ibs_on_all_vcpus(vcpu->kvm);
	}

2117
	atomic_clear_mask(CPUSTAT_STOPPED, &vcpu->arch.sie_block->cpuflags);
2118 2119 2120 2121
	/*
	 * Another VCPU might have used IBS while we were offline.
	 * Let's play safe and flush the VCPU at startup.
	 */
2122
	kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
2123
	spin_unlock(&vcpu->kvm->arch.start_stop_lock);
2124
	return;
2125 2126 2127 2128
}

void kvm_s390_vcpu_stop(struct kvm_vcpu *vcpu)
{
2129 2130 2131 2132 2133 2134
	int i, online_vcpus, started_vcpus = 0;
	struct kvm_vcpu *started_vcpu = NULL;

	if (is_vcpu_stopped(vcpu))
		return;

2135
	trace_kvm_s390_vcpu_start_stop(vcpu->vcpu_id, 0);
2136
	/* Only one cpu at a time may enter/leave the STOPPED state. */
2137
	spin_lock(&vcpu->kvm->arch.start_stop_lock);
2138 2139
	online_vcpus = atomic_read(&vcpu->kvm->online_vcpus);

2140
	/* SIGP STOP and SIGP STOP AND STORE STATUS has been fully processed */
2141
	kvm_s390_clear_stop_irq(vcpu);
2142

2143
	atomic_set_mask(CPUSTAT_STOPPED, &vcpu->arch.sie_block->cpuflags);
2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160
	__disable_ibs_on_vcpu(vcpu);

	for (i = 0; i < online_vcpus; i++) {
		if (!is_vcpu_stopped(vcpu->kvm->vcpus[i])) {
			started_vcpus++;
			started_vcpu = vcpu->kvm->vcpus[i];
		}
	}

	if (started_vcpus == 1) {
		/*
		 * As we only have one VCPU left, we want to enable the
		 * IBS facility for that VCPU to speed it up.
		 */
		__enable_ibs_on_vcpu(started_vcpu);
	}

2161
	spin_unlock(&vcpu->kvm->arch.start_stop_lock);
2162
	return;
2163 2164
}

2165 2166 2167 2168 2169 2170 2171 2172 2173
static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
				     struct kvm_enable_cap *cap)
{
	int r;

	if (cap->flags)
		return -EINVAL;

	switch (cap->cap) {
2174 2175 2176 2177 2178 2179 2180
	case KVM_CAP_S390_CSS_SUPPORT:
		if (!vcpu->kvm->arch.css_support) {
			vcpu->kvm->arch.css_support = 1;
			trace_kvm_s390_enable_css(vcpu->kvm);
		}
		r = 0;
		break;
2181 2182 2183 2184 2185 2186 2187
	default:
		r = -EINVAL;
		break;
	}
	return r;
}

2188 2189 2190 2191 2192
long kvm_arch_vcpu_ioctl(struct file *filp,
			 unsigned int ioctl, unsigned long arg)
{
	struct kvm_vcpu *vcpu = filp->private_data;
	void __user *argp = (void __user *)arg;
2193
	int idx;
2194
	long r;
2195

2196 2197
	switch (ioctl) {
	case KVM_S390_INTERRUPT: {
2198
		struct kvm_s390_interrupt s390int;
2199
		struct kvm_s390_irq s390irq;
2200

2201
		r = -EFAULT;
2202
		if (copy_from_user(&s390int, argp, sizeof(s390int)))
2203
			break;
2204 2205 2206
		if (s390int_to_s390irq(&s390int, &s390irq))
			return -EINVAL;
		r = kvm_s390_inject_vcpu(vcpu, &s390irq);
2207
		break;
2208
	}
2209
	case KVM_S390_STORE_STATUS:
2210
		idx = srcu_read_lock(&vcpu->kvm->srcu);
2211
		r = kvm_s390_vcpu_store_status(vcpu, arg);
2212
		srcu_read_unlock(&vcpu->kvm->srcu, idx);
2213
		break;
2214 2215 2216
	case KVM_S390_SET_INITIAL_PSW: {
		psw_t psw;

2217
		r = -EFAULT;
2218
		if (copy_from_user(&psw, argp, sizeof(psw)))
2219 2220 2221
			break;
		r = kvm_arch_vcpu_ioctl_set_initial_psw(vcpu, psw);
		break;
2222 2223
	}
	case KVM_S390_INITIAL_RESET:
2224 2225
		r = kvm_arch_vcpu_ioctl_initial_reset(vcpu);
		break;
2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237
	case KVM_SET_ONE_REG:
	case KVM_GET_ONE_REG: {
		struct kvm_one_reg reg;
		r = -EFAULT;
		if (copy_from_user(&reg, argp, sizeof(reg)))
			break;
		if (ioctl == KVM_SET_ONE_REG)
			r = kvm_arch_vcpu_ioctl_set_one_reg(vcpu, &reg);
		else
			r = kvm_arch_vcpu_ioctl_get_one_reg(vcpu, &reg);
		break;
	}
2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273
#ifdef CONFIG_KVM_S390_UCONTROL
	case KVM_S390_UCAS_MAP: {
		struct kvm_s390_ucas_mapping ucasmap;

		if (copy_from_user(&ucasmap, argp, sizeof(ucasmap))) {
			r = -EFAULT;
			break;
		}

		if (!kvm_is_ucontrol(vcpu->kvm)) {
			r = -EINVAL;
			break;
		}

		r = gmap_map_segment(vcpu->arch.gmap, ucasmap.user_addr,
				     ucasmap.vcpu_addr, ucasmap.length);
		break;
	}
	case KVM_S390_UCAS_UNMAP: {
		struct kvm_s390_ucas_mapping ucasmap;

		if (copy_from_user(&ucasmap, argp, sizeof(ucasmap))) {
			r = -EFAULT;
			break;
		}

		if (!kvm_is_ucontrol(vcpu->kvm)) {
			r = -EINVAL;
			break;
		}

		r = gmap_unmap_segment(vcpu->arch.gmap, ucasmap.vcpu_addr,
			ucasmap.length);
		break;
	}
#endif
2274
	case KVM_S390_VCPU_FAULT: {
2275
		r = gmap_fault(vcpu->arch.gmap, arg, 0);
2276 2277
		break;
	}
2278 2279 2280 2281 2282 2283 2284 2285 2286
	case KVM_ENABLE_CAP:
	{
		struct kvm_enable_cap cap;
		r = -EFAULT;
		if (copy_from_user(&cap, argp, sizeof(cap)))
			break;
		r = kvm_vcpu_ioctl_enable_cap(vcpu, &cap);
		break;
	}
2287
	default:
2288
		r = -ENOTTY;
2289
	}
2290
	return r;
2291 2292
}

2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305
int kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf)
{
#ifdef CONFIG_KVM_S390_UCONTROL
	if ((vmf->pgoff == KVM_S390_SIE_PAGE_OFFSET)
		 && (kvm_is_ucontrol(vcpu->kvm))) {
		vmf->page = virt_to_page(vcpu->arch.sie_block);
		get_page(vmf->page);
		return 0;
	}
#endif
	return VM_FAULT_SIGBUS;
}

2306 2307
int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
			    unsigned long npages)
2308 2309 2310 2311
{
	return 0;
}

2312
/* Section: memory related */
2313 2314
int kvm_arch_prepare_memory_region(struct kvm *kvm,
				   struct kvm_memory_slot *memslot,
2315 2316
				   struct kvm_userspace_memory_region *mem,
				   enum kvm_mr_change change)
2317
{
2318 2319 2320 2321
	/* A few sanity checks. We can have memory slots which have to be
	   located/ended at a segment boundary (1MB). The memory in userland is
	   ok to be fragmented into various different vmas. It is okay to mmap()
	   and munmap() stuff in this slot after doing this call at any time */
2322

2323
	if (mem->userspace_addr & 0xffffful)
2324 2325
		return -EINVAL;

2326
	if (mem->memory_size & 0xffffful)
2327 2328
		return -EINVAL;

2329 2330 2331 2332 2333
	return 0;
}

void kvm_arch_commit_memory_region(struct kvm *kvm,
				struct kvm_userspace_memory_region *mem,
2334 2335
				const struct kvm_memory_slot *old,
				enum kvm_mr_change change)
2336
{
2337
	int rc;
2338

2339 2340 2341 2342 2343 2344 2345 2346 2347 2348
	/* If the basics of the memslot do not change, we do not want
	 * to update the gmap. Every update causes several unnecessary
	 * segment translation exceptions. This is usually handled just
	 * fine by the normal fault handler + gmap, but it will also
	 * cause faults on the prefix page of running guest CPUs.
	 */
	if (old->userspace_addr == mem->userspace_addr &&
	    old->base_gfn * PAGE_SIZE == mem->guest_phys_addr &&
	    old->npages * PAGE_SIZE == mem->memory_size)
		return;
2349 2350 2351 2352

	rc = gmap_map_segment(kvm->arch.gmap, mem->userspace_addr,
		mem->guest_phys_addr, mem->memory_size);
	if (rc)
2353
		printk(KERN_WARNING "kvm-s390: failed to commit memory region\n");
2354
	return;
2355 2356 2357 2358
}

static int __init kvm_s390_init(void)
{
2359
	return kvm_init(NULL, sizeof(struct kvm_vcpu), 0, THIS_MODULE);
2360 2361 2362 2363 2364 2365 2366 2367 2368
}

static void __exit kvm_s390_exit(void)
{
	kvm_exit();
}

module_init(kvm_s390_init);
module_exit(kvm_s390_exit);
2369 2370 2371 2372 2373 2374 2375 2376 2377

/*
 * Enable autoloading of the kvm module.
 * Note that we add the module alias here instead of virt/kvm/kvm_main.c
 * since x86 takes a different approach.
 */
#include <linux/miscdevice.h>
MODULE_ALIAS_MISCDEV(KVM_MINOR);
MODULE_ALIAS("devname:kvm");