kvm-s390.c 44.2 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 25
#include <linux/init.h>
#include <linux/kvm.h>
#include <linux/kvm_host.h>
#include <linux/module.h>
#include <linux/slab.h>
26
#include <linux/timer.h>
27
#include <asm/asm-offsets.h>
28 29
#include <asm/lowcore.h>
#include <asm/pgtable.h>
30
#include <asm/nmi.h>
31
#include <asm/switch_to.h>
32
#include <asm/facility.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
	{ "instruction_lctlg", VCPU_STAT(instruction_lctlg) },
54
	{ "instruction_lctl", VCPU_STAT(instruction_lctl) },
55 56
	{ "instruction_stctl", VCPU_STAT(instruction_stctl) },
	{ "instruction_stctg", VCPU_STAT(instruction_stctg) },
57
	{ "deliver_emergency_signal", VCPU_STAT(deliver_emergency_signal) },
58
	{ "deliver_external_call", VCPU_STAT(deliver_external_call) },
59 60 61 62 63 64 65
	{ "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) },
66
	{ "instruction_pfmf", VCPU_STAT(instruction_pfmf) },
67 68 69 70 71
	{ "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) },
72
	{ "instruction_ipte_interlock", VCPU_STAT(instruction_ipte_interlock) },
73 74
	{ "instruction_stsch", VCPU_STAT(instruction_stsch) },
	{ "instruction_chsc", VCPU_STAT(instruction_chsc) },
75
	{ "instruction_essa", VCPU_STAT(instruction_essa) },
76 77
	{ "instruction_stsi", VCPU_STAT(instruction_stsi) },
	{ "instruction_stfl", VCPU_STAT(instruction_stfl) },
78
	{ "instruction_tprot", VCPU_STAT(instruction_tprot) },
79
	{ "instruction_sigp_sense", VCPU_STAT(instruction_sigp_sense) },
80
	{ "instruction_sigp_sense_running", VCPU_STAT(instruction_sigp_sense_running) },
81
	{ "instruction_sigp_external_call", VCPU_STAT(instruction_sigp_external_call) },
82 83 84 85 86
	{ "instruction_sigp_emergency", VCPU_STAT(instruction_sigp_emergency) },
	{ "instruction_sigp_stop", VCPU_STAT(instruction_sigp_stop) },
	{ "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) },
87
	{ "diagnose_10", VCPU_STAT(diagnose_10) },
88
	{ "diagnose_44", VCPU_STAT(diagnose_44) },
89
	{ "diagnose_9c", VCPU_STAT(diagnose_9c) },
90 91 92
	{ NULL }
};

93
unsigned long *vfacilities;
94
static struct gmap_notifier gmap_notifier;
95

96
/* test availability of vfacility */
97
int test_vfacility(unsigned long nr)
98 99 100 101
{
	return __test_facility(nr, (void *) vfacilities);
}

102
/* Section: not file related */
103
int kvm_arch_hardware_enable(void *garbage)
104 105
{
	/* every s390 is virtualization enabled ;-) */
106
	return 0;
107 108 109 110 111 112
}

void kvm_arch_hardware_disable(void *garbage)
{
}

113 114
static void kvm_gmap_notifier(struct gmap *gmap, unsigned long address);

115 116
int kvm_arch_hardware_setup(void)
{
117 118
	gmap_notifier.notifier_call = kvm_gmap_notifier;
	gmap_register_ipte_notifier(&gmap_notifier);
119 120 121 122 123
	return 0;
}

void kvm_arch_hardware_unsetup(void)
{
124
	gmap_unregister_ipte_notifier(&gmap_notifier);
125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150
}

void kvm_arch_check_processor_compat(void *rtn)
{
}

int kvm_arch_init(void *opaque)
{
	return 0;
}

void kvm_arch_exit(void)
{
}

/* 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;
}

int kvm_dev_ioctl_check_extension(long ext)
{
151 152
	int r;

153
	switch (ext) {
154
	case KVM_CAP_S390_PSW:
155
	case KVM_CAP_S390_GMAP:
156
	case KVM_CAP_SYNC_MMU:
157 158 159
#ifdef CONFIG_KVM_S390_UCONTROL
	case KVM_CAP_S390_UCONTROL:
#endif
160
	case KVM_CAP_ASYNC_PF:
161
	case KVM_CAP_SYNC_REGS:
162
	case KVM_CAP_ONE_REG:
163
	case KVM_CAP_ENABLE_CAP:
164
	case KVM_CAP_S390_CSS_SUPPORT:
C
Cornelia Huck 已提交
165
	case KVM_CAP_IOEVENTFD:
166
	case KVM_CAP_DEVICE_CTRL:
167
	case KVM_CAP_ENABLE_CAP_VM:
168
	case KVM_CAP_VM_ATTRIBUTES:
169 170
		r = 1;
		break;
171 172 173 174
	case KVM_CAP_NR_VCPUS:
	case KVM_CAP_MAX_VCPUS:
		r = KVM_MAX_VCPUS;
		break;
175 176 177
	case KVM_CAP_NR_MEMSLOTS:
		r = KVM_USER_MEM_SLOTS;
		break;
178
	case KVM_CAP_S390_COW:
179
		r = MACHINE_HAS_ESOP;
180
		break;
181
	default:
182
		r = 0;
183
	}
184
	return r;
185 186
}

187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205
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);
}

206 207 208 209 210 211 212
/* 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)
{
213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242
	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;
243 244
}

245 246 247 248 249 250 251 252
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) {
253 254 255 256
	case KVM_CAP_S390_IRQCHIP:
		kvm->arch.use_irqchip = 1;
		r = 0;
		break;
257 258 259 260 261 262 263
	default:
		r = -EINVAL;
		break;
	}
	return r;
}

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
static int kvm_s390_mem_control(struct kvm *kvm, struct kvm_device_attr *attr)
{
	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);
		page_table_reset_pgste(kvm->arch.gmap->mm, 0, TASK_SIZE, false);
		srcu_read_unlock(&kvm->srcu, idx);
		mutex_unlock(&kvm->lock);
		ret = 0;
		break;
	default:
		ret = -ENXIO;
		break;
	}
	return ret;
}

293 294 295 296 297
static int kvm_s390_vm_set_attr(struct kvm *kvm, struct kvm_device_attr *attr)
{
	int ret;

	switch (attr->group) {
298 299 300
	case KVM_S390_VM_MEM_CTRL:
		ret = kvm_s390_mem_control(kvm, attr);
		break;
301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318
	default:
		ret = -ENXIO;
		break;
	}

	return ret;
}

static int kvm_s390_vm_get_attr(struct kvm *kvm, struct kvm_device_attr *attr)
{
	return -ENXIO;
}

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

	switch (attr->group) {
319 320 321 322 323 324 325 326 327 328 329
	case KVM_S390_VM_MEM_CTRL:
		switch (attr->attr) {
		case KVM_S390_VM_MEM_ENABLE_CMMA:
		case KVM_S390_VM_MEM_CLR_CMMA:
			ret = 0;
			break;
		default:
			ret = -ENXIO;
			break;
		}
		break;
330 331 332 333 334 335 336 337
	default:
		ret = -ENXIO;
		break;
	}

	return ret;
}

338 339 340 341 342
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;
343
	struct kvm_device_attr attr;
344 345 346
	int r;

	switch (ioctl) {
347 348 349 350 351 352 353 354 355
	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;
	}
356 357 358 359 360 361 362 363
	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;
	}
364 365 366 367 368 369 370 371 372 373 374 375
	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;
	}
376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396
	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;
	}
397
	default:
398
		r = -ENOTTY;
399 400 401 402 403
	}

	return r;
}

404
int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
405 406 407
{
	int rc;
	char debug_name[16];
408
	static unsigned long sca_offset;
409

410 411 412 413 414 415 416 417 418 419 420
	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

421 422
	rc = s390_enable_sie();
	if (rc)
423
		goto out_err;
424

425 426
	rc = -ENOMEM;

427 428
	kvm->arch.sca = (struct sca_block *) get_zeroed_page(GFP_KERNEL);
	if (!kvm->arch.sca)
429
		goto out_err;
430 431 432 433
	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);
434 435 436 437 438 439 440

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

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

441 442
	spin_lock_init(&kvm->arch.float_int.lock);
	INIT_LIST_HEAD(&kvm->arch.float_int.list);
443
	init_waitqueue_head(&kvm->arch.ipte_wq);
444

445 446 447
	debug_register_view(kvm->arch.dbf, &debug_sprintf_view);
	VM_EVENT(kvm, 3, "%s", "vm created");

448 449 450 451 452 453
	if (type & KVM_VM_S390_UCONTROL) {
		kvm->arch.gmap = NULL;
	} else {
		kvm->arch.gmap = gmap_alloc(current->mm);
		if (!kvm->arch.gmap)
			goto out_nogmap;
454
		kvm->arch.gmap->private = kvm;
455
		kvm->arch.gmap->pfault_enabled = 0;
456
	}
457 458

	kvm->arch.css_support = 0;
459
	kvm->arch.use_irqchip = 0;
460

461 462
	spin_lock_init(&kvm->arch.start_stop_lock);

463
	return 0;
464 465
out_nogmap:
	debug_unregister(kvm->arch.dbf);
466 467
out_nodbf:
	free_page((unsigned long)(kvm->arch.sca));
468 469
out_err:
	return rc;
470 471
}

472 473 474
void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
{
	VCPU_EVENT(vcpu, 3, "%s", "free cpu");
475
	trace_kvm_s390_destroy_vcpu(vcpu->vcpu_id);
476
	kvm_s390_clear_local_irqs(vcpu);
477
	kvm_clear_async_pf_completion_queue(vcpu);
C
Carsten Otte 已提交
478 479 480 481 482 483 484
	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;
	}
485
	smp_mb();
486 487 488 489

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

490 491
	if (kvm_s390_cmma_enabled(vcpu->kvm))
		kvm_s390_vcpu_unsetup_cmma(vcpu);
492
	free_page((unsigned long)(vcpu->arch.sie_block));
493

494
	kvm_vcpu_uninit(vcpu);
495
	kmem_cache_free(kvm_vcpu_cache, vcpu);
496 497 498 499 500
}

static void kvm_free_vcpus(struct kvm *kvm)
{
	unsigned int i;
501
	struct kvm_vcpu *vcpu;
502

503 504 505 506 507 508 509 510 511
	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);
512 513
}

514 515 516 517
void kvm_arch_sync_events(struct kvm *kvm)
{
}

518 519
void kvm_arch_destroy_vm(struct kvm *kvm)
{
520
	kvm_free_vcpus(kvm);
521
	free_page((unsigned long)(kvm->arch.sca));
522
	debug_unregister(kvm->arch.dbf);
523 524
	if (!kvm_is_ucontrol(kvm))
		gmap_free(kvm->arch.gmap);
525
	kvm_s390_destroy_adapters(kvm);
526
	kvm_s390_clear_float_irqs(kvm);
527 528 529 530 531
}

/* Section: vcpu related */
int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
{
532 533
	vcpu->arch.pfault_token = KVM_S390_PFAULT_TOKEN_INVALID;
	kvm_clear_async_pf_completion_queue(vcpu);
534 535 536 537
	if (kvm_is_ucontrol(vcpu->kvm)) {
		vcpu->arch.gmap = gmap_alloc(current->mm);
		if (!vcpu->arch.gmap)
			return -ENOMEM;
538
		vcpu->arch.gmap->private = vcpu->kvm;
539 540 541
		return 0;
	}

542
	vcpu->arch.gmap = vcpu->kvm->arch.gmap;
543 544
	vcpu->run->kvm_valid_regs = KVM_SYNC_PREFIX |
				    KVM_SYNC_GPRS |
545 546
				    KVM_SYNC_ACRS |
				    KVM_SYNC_CRS;
547 548 549 550 551
	return 0;
}

void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu)
{
552
	/* Nothing todo */
553 554 555 556
}

void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
{
557 558
	save_fp_ctl(&vcpu->arch.host_fpregs.fpc);
	save_fp_regs(vcpu->arch.host_fpregs.fprs);
559
	save_access_regs(vcpu->arch.host_acrs);
560 561
	restore_fp_ctl(&vcpu->arch.guest_fpregs.fpc);
	restore_fp_regs(vcpu->arch.guest_fpregs.fprs);
562
	restore_access_regs(vcpu->run->s.regs.acrs);
563
	gmap_enable(vcpu->arch.gmap);
564
	atomic_set_mask(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
565 566 567 568
}

void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
{
569
	atomic_clear_mask(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
570
	gmap_disable(vcpu->arch.gmap);
571 572
	save_fp_ctl(&vcpu->arch.guest_fpregs.fpc);
	save_fp_regs(vcpu->arch.guest_fpregs.fprs);
573
	save_access_regs(vcpu->run->s.regs.acrs);
574 575
	restore_fp_ctl(&vcpu->arch.host_fpregs.fpc);
	restore_fp_regs(vcpu->arch.host_fpregs.fprs);
576 577 578 579 580 581 582 583
	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;
584
	kvm_s390_set_prefix(vcpu, 0);
585 586 587 588 589 590 591 592 593
	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;
594
	vcpu->arch.sie_block->pp = 0;
595 596
	vcpu->arch.pfault_token = KVM_S390_PFAULT_TOKEN_INVALID;
	kvm_clear_async_pf_completion_queue(vcpu);
597
	kvm_s390_vcpu_stop(vcpu);
598
	kvm_s390_clear_local_irqs(vcpu);
599 600
}

601 602 603 604 605
int kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
{
	return 0;
}

606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622
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;
}

623 624
int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
{
625
	int rc = 0;
626

627 628
	atomic_set(&vcpu->arch.sie_block->cpuflags, CPUSTAT_ZARCH |
						    CPUSTAT_SM |
629 630
						    CPUSTAT_STOPPED |
						    CPUSTAT_GED);
631
	vcpu->arch.sie_block->ecb   = 6;
632 633 634
	if (test_vfacility(50) && test_vfacility(73))
		vcpu->arch.sie_block->ecb |= 0x10;

635
	vcpu->arch.sie_block->ecb2  = 8;
636
	vcpu->arch.sie_block->eca   = 0xD1002000U;
637 638
	if (sclp_has_siif())
		vcpu->arch.sie_block->eca |= 1;
639
	vcpu->arch.sie_block->fac   = (int) (long) vfacilities;
640
	vcpu->arch.sie_block->ictl |= ICTL_ISKE | ICTL_SSKE | ICTL_RRBE;
641 642 643 644
	if (kvm_s390_cmma_enabled(vcpu->kvm)) {
		rc = kvm_s390_vcpu_setup_cmma(vcpu);
		if (rc)
			return rc;
645
	}
646 647 648 649
	hrtimer_init(&vcpu->arch.ckc_timer, CLOCK_REALTIME, HRTIMER_MODE_ABS);
	tasklet_init(&vcpu->arch.tasklet, kvm_s390_tasklet,
		     (unsigned long) vcpu);
	vcpu->arch.ckc_timer.function = kvm_s390_idle_wakeup;
650
	get_cpu_id(&vcpu->arch.cpu_id);
651
	vcpu->arch.cpu_id.version = 0xff;
652
	return rc;
653 654 655 656 657
}

struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
				      unsigned int id)
{
658
	struct kvm_vcpu *vcpu;
659
	struct sie_page *sie_page;
660 661 662 663 664 665
	int rc = -EINVAL;

	if (id >= KVM_MAX_VCPUS)
		goto out;

	rc = -ENOMEM;
666

667
	vcpu = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL);
668
	if (!vcpu)
669
		goto out;
670

671 672
	sie_page = (struct sie_page *) get_zeroed_page(GFP_KERNEL);
	if (!sie_page)
673 674
		goto out_free_cpu;

675 676 677
	vcpu->arch.sie_block = &sie_page->sie_block;
	vcpu->arch.sie_block->itdba = (unsigned long) &sie_page->itdb;

678
	vcpu->arch.sie_block->icpua = id;
C
Carsten Otte 已提交
679 680 681 682 683 684 685 686 687 688 689 690 691
	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);
	}
692

693 694 695
	spin_lock_init(&vcpu->arch.local_int.lock);
	INIT_LIST_HEAD(&vcpu->arch.local_int.list);
	vcpu->arch.local_int.float_int = &kvm->arch.float_int;
696
	vcpu->arch.local_int.wq = &vcpu->wq;
697
	vcpu->arch.local_int.cpuflags = &vcpu->arch.sie_block->cpuflags;
698

699 700
	rc = kvm_vcpu_init(vcpu, kvm, id);
	if (rc)
701
		goto out_free_sie_block;
702 703
	VM_EVENT(kvm, 3, "create cpu %d at %p, sie block at %p", id, vcpu,
		 vcpu->arch.sie_block);
704
	trace_kvm_s390_create_vcpu(id, vcpu, vcpu->arch.sie_block);
705 706

	return vcpu;
707 708
out_free_sie_block:
	free_page((unsigned long)(vcpu->arch.sie_block));
709
out_free_cpu:
710
	kmem_cache_free(kvm_vcpu_cache, vcpu);
711
out:
712 713 714 715 716
	return ERR_PTR(rc);
}

int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
{
717
	return kvm_cpu_has_interrupt(vcpu);
718 719
}

720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747
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);
}

748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763
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 */
		if (vcpu->arch.sie_block->prefix == (address & ~0x1000UL)) {
			VCPU_EVENT(vcpu, 2, "gmap notifier for %lx", address);
			kvm_make_request(KVM_REQ_MMU_RELOAD, vcpu);
			exit_sie_sync(vcpu);
		}
	}
}

764 765 766 767 768 769 770
int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu)
{
	/* kvm common code refers to this, but never calls it */
	BUG();
	return 0;
}

771 772 773 774 775 776
static int kvm_arch_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu,
					   struct kvm_one_reg *reg)
{
	int r = -EINVAL;

	switch (reg->id) {
777 778 779 780 781 782 783 784
	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;
785 786 787 788 789 790 791 792
	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;
793 794 795 796 797 798 799 800 801 802 803 804
	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;
805 806 807 808
	case KVM_REG_S390_PP:
		r = put_user(vcpu->arch.sie_block->pp,
			     (u64 __user *)reg->addr);
		break;
809 810 811 812
	case KVM_REG_S390_GBEA:
		r = put_user(vcpu->arch.sie_block->gbea,
			     (u64 __user *)reg->addr);
		break;
813 814 815 816 817 818 819 820 821 822 823 824 825
	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) {
826 827 828 829 830 831 832 833
	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;
834 835 836 837 838 839 840 841
	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;
842 843 844 845 846 847 848 849 850 851 852 853
	case KVM_REG_S390_PFTOKEN:
		r = get_user(vcpu->arch.pfault_token,
			     (u64 __user *)reg->addr);
		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;
854 855 856 857
	case KVM_REG_S390_PP:
		r = get_user(vcpu->arch.sie_block->pp,
			     (u64 __user *)reg->addr);
		break;
858 859 860 861
	case KVM_REG_S390_GBEA:
		r = get_user(vcpu->arch.sie_block->gbea,
			     (u64 __user *)reg->addr);
		break;
862 863 864 865 866 867
	default:
		break;
	}

	return r;
}
868

869 870 871 872 873 874 875 876
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)
{
877
	memcpy(&vcpu->run->s.regs.gprs, &regs->gprs, sizeof(regs->gprs));
878 879 880 881 882
	return 0;
}

int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
{
883
	memcpy(&regs->gprs, &vcpu->run->s.regs.gprs, sizeof(regs->gprs));
884 885 886 887 888 889
	return 0;
}

int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
				  struct kvm_sregs *sregs)
{
890
	memcpy(&vcpu->run->s.regs.acrs, &sregs->acrs, sizeof(sregs->acrs));
891
	memcpy(&vcpu->arch.sie_block->gcr, &sregs->crs, sizeof(sregs->crs));
892
	restore_access_regs(vcpu->run->s.regs.acrs);
893 894 895 896 897 898
	return 0;
}

int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
				  struct kvm_sregs *sregs)
{
899
	memcpy(&sregs->acrs, &vcpu->run->s.regs.acrs, sizeof(sregs->acrs));
900 901 902 903 904 905
	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)
{
906 907
	if (test_fp_ctl(fpu->fpc))
		return -EINVAL;
908
	memcpy(&vcpu->arch.guest_fpregs.fprs, &fpu->fprs, sizeof(fpu->fprs));
909 910 911
	vcpu->arch.guest_fpregs.fpc = fpu->fpc;
	restore_fp_ctl(&vcpu->arch.guest_fpregs.fpc);
	restore_fp_regs(vcpu->arch.guest_fpregs.fprs);
912 913 914 915 916 917 918 919 920 921 922 923 924 925
	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;

926
	if (!(atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_STOPPED))
927
		rc = -EBUSY;
928 929 930 931
	else {
		vcpu->run->psw_mask = psw.mask;
		vcpu->run->psw_addr = psw.addr;
	}
932 933 934 935 936 937 938 939 940
	return rc;
}

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

941 942 943 944
#define VALID_GUESTDBG_FLAGS (KVM_GUESTDBG_SINGLESTEP | \
			      KVM_GUESTDBG_USE_HW_BP | \
			      KVM_GUESTDBG_ENABLE)

J
Jan Kiszka 已提交
945 946
int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
					struct kvm_guest_debug *dbg)
947
{
948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974
	int rc = 0;

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

	if (vcpu->guest_debug & ~VALID_GUESTDBG_FLAGS)
		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;
975 976
}

977 978 979 980 981 982 983 984 985 986 987 988
int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
				    struct kvm_mp_state *mp_state)
{
	return -EINVAL; /* not implemented yet */
}

int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
				    struct kvm_mp_state *mp_state)
{
	return -EINVAL; /* not implemented yet */
}

989 990 991 992 993 994 995 996 997 998 999 1000
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;
}

1001 1002 1003 1004 1005
static bool ibs_enabled(struct kvm_vcpu *vcpu)
{
	return atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_IBS;
}

1006 1007
static int kvm_s390_handle_requests(struct kvm_vcpu *vcpu)
{
1008 1009
retry:
	s390_vcpu_unblock(vcpu);
1010 1011 1012 1013 1014 1015 1016
	/*
	 * 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.
	 */
1017
	if (kvm_check_request(KVM_REQ_MMU_RELOAD, vcpu)) {
1018 1019 1020 1021 1022 1023
		int rc;
		rc = gmap_ipte_notify(vcpu->arch.gmap,
				      vcpu->arch.sie_block->prefix,
				      PAGE_SIZE * 2);
		if (rc)
			return rc;
1024 1025 1026 1027 1028 1029 1030 1031 1032 1033
		goto retry;
	}

	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;
1034
	}
1035 1036 1037 1038 1039 1040 1041 1042 1043 1044

	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;
	}

1045 1046 1047
	return 0;
}

1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058
/**
 * 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)
1059 1060
{
	struct mm_struct *mm = current->mm;
1061 1062 1063 1064 1065 1066
	hva_t hva;
	long rc;

	hva = gmap_fault(gpa, vcpu->arch.gmap);
	if (IS_ERR_VALUE(hva))
		return (long)hva;
1067
	down_read(&mm->mmap_sem);
1068
	rc = get_user_pages(current, mm, hva, 1, writable, 0, NULL, NULL);
1069
	up_read(&mm->mmap_sem);
1070 1071

	return rc < 0 ? rc : 0;
1072 1073
}

1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137
static void __kvm_inject_pfault_token(struct kvm_vcpu *vcpu, bool start_token,
				      unsigned long token)
{
	struct kvm_s390_interrupt inti;
	inti.parm64 = token;

	if (start_token) {
		inti.type = KVM_S390_INT_PFAULT_INIT;
		WARN_ON_ONCE(kvm_s390_inject_vcpu(vcpu, &inti));
	} else {
		inti.type = KVM_S390_INT_PFAULT_DONE;
		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;
	if (kvm_cpu_has_interrupt(vcpu))
		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
1138 1139 1140
	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))
1141 1142 1143 1144 1145 1146
		return 0;

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

1147
static int vcpu_pre_run(struct kvm_vcpu *vcpu)
1148
{
1149
	int rc, cpuflags;
1150

1151 1152 1153 1154 1155 1156 1157
	/*
	 * 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);

1158
	memcpy(&vcpu->arch.sie_block->gg14, &vcpu->run->s.regs.gprs[14], 16);
1159 1160 1161 1162

	if (need_resched())
		schedule();

1163 1164 1165
	if (test_thread_flag(TIF_MCCK_PENDING))
		s390_handle_mcck();

1166 1167
	if (!kvm_is_ucontrol(vcpu->kvm))
		kvm_s390_deliver_pending_interrupts(vcpu);
C
Carsten Otte 已提交
1168

1169 1170 1171 1172
	rc = kvm_s390_handle_requests(vcpu);
	if (rc)
		return rc;

1173 1174 1175 1176 1177
	if (guestdbg_enabled(vcpu)) {
		kvm_s390_backup_guest_per_regs(vcpu);
		kvm_s390_patch_guest_per_regs(vcpu);
	}

1178
	vcpu->arch.sie_block->icptcode = 0;
1179 1180 1181
	cpuflags = atomic_read(&vcpu->arch.sie_block->cpuflags);
	VCPU_EVENT(vcpu, 6, "entering sie flags %x", cpuflags);
	trace_kvm_s390_sie_enter(vcpu, cpuflags);
1182

1183 1184 1185 1186 1187
	return 0;
}

static int vcpu_post_run(struct kvm_vcpu *vcpu, int exit_reason)
{
1188
	int rc = -1;
1189 1190 1191 1192 1193

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

1194 1195 1196
	if (guestdbg_enabled(vcpu))
		kvm_s390_restore_guest_per_regs(vcpu);

1197
	if (exit_reason >= 0) {
1198
		rc = 0;
1199 1200 1201 1202 1203 1204
	} 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;
1205 1206

	} else if (current->thread.gmap_pfault) {
1207
		trace_kvm_s390_major_guest_pfault(vcpu);
1208
		current->thread.gmap_pfault = 0;
1209
		if (kvm_arch_setup_async_pf(vcpu)) {
1210
			rc = 0;
1211 1212 1213 1214
		} else {
			gpa_t gpa = current->thread.gmap_addr;
			rc = kvm_arch_fault_in_page(vcpu, gpa, 1);
		}
1215 1216 1217
	}

	if (rc == -1) {
1218 1219 1220
		VCPU_EVENT(vcpu, 3, "%s", "fault in sie instruction");
		trace_kvm_s390_sie_fault(vcpu);
		rc = kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
1221
	}
1222

1223
	memcpy(&vcpu->run->s.regs.gprs[14], &vcpu->arch.sie_block->gg14, 16);
1224

1225 1226
	if (rc == 0) {
		if (kvm_is_ucontrol(vcpu->kvm))
1227 1228
			/* Don't exit for host interrupts. */
			rc = vcpu->arch.sie_block->icptcode ? -EOPNOTSUPP : 0;
1229 1230 1231 1232
		else
			rc = kvm_handle_sie_intercept(vcpu);
	}

1233 1234 1235 1236 1237 1238 1239
	return rc;
}

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

1240 1241 1242 1243 1244 1245
	/*
	 * 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);

1246 1247 1248 1249
	do {
		rc = vcpu_pre_run(vcpu);
		if (rc)
			break;
1250

1251
		srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
1252 1253 1254 1255 1256 1257 1258 1259 1260 1261
		/*
		 * 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();
1262
		vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
1263 1264

		rc = vcpu_post_run(vcpu, exit_reason);
1265
	} while (!signal_pending(current) && !guestdbg_exit_pending(vcpu) && !rc);
1266

1267
	srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
1268
	return rc;
1269 1270 1271 1272
}

int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
{
1273
	int rc;
1274 1275
	sigset_t sigsaved;

1276 1277 1278 1279 1280
	if (guestdbg_exit_pending(vcpu)) {
		kvm_s390_prepare_debug_exit(vcpu);
		return 0;
	}

1281 1282 1283
	if (vcpu->sigset_active)
		sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved);

1284
	kvm_s390_vcpu_start(vcpu);
1285

1286 1287 1288
	switch (kvm_run->exit_reason) {
	case KVM_EXIT_S390_SIEIC:
	case KVM_EXIT_UNKNOWN:
1289
	case KVM_EXIT_INTR:
1290
	case KVM_EXIT_S390_RESET:
1291
	case KVM_EXIT_S390_UCONTROL:
1292
	case KVM_EXIT_S390_TSCH:
1293
	case KVM_EXIT_DEBUG:
1294 1295 1296 1297 1298
		break;
	default:
		BUG();
	}

1299 1300
	vcpu->arch.sie_block->gpsw.mask = kvm_run->psw_mask;
	vcpu->arch.sie_block->gpsw.addr = kvm_run->psw_addr;
1301 1302 1303 1304
	if (kvm_run->kvm_dirty_regs & KVM_SYNC_PREFIX) {
		kvm_run->kvm_dirty_regs &= ~KVM_SYNC_PREFIX;
		kvm_s390_set_prefix(vcpu, kvm_run->s.regs.prefix);
	}
1305 1306 1307 1308 1309
	if (kvm_run->kvm_dirty_regs & KVM_SYNC_CRS) {
		kvm_run->kvm_dirty_regs &= ~KVM_SYNC_CRS;
		memcpy(&vcpu->arch.sie_block->gcr, &kvm_run->s.regs.crs, 128);
		kvm_s390_set_prefix(vcpu, kvm_run->s.regs.prefix);
	}
1310

1311
	might_fault();
1312
	rc = __vcpu_run(vcpu);
1313

1314 1315
	if (signal_pending(current) && !rc) {
		kvm_run->exit_reason = KVM_EXIT_INTR;
1316
		rc = -EINTR;
1317
	}
1318

1319 1320 1321 1322 1323
	if (guestdbg_exit_pending(vcpu) && !rc)  {
		kvm_s390_prepare_debug_exit(vcpu);
		rc = 0;
	}

1324
	if (rc == -EOPNOTSUPP) {
1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337
		/* 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;
	}
1338

1339 1340
	kvm_run->psw_mask     = vcpu->arch.sie_block->gpsw.mask;
	kvm_run->psw_addr     = vcpu->arch.sie_block->gpsw.addr;
1341
	kvm_run->s.regs.prefix = vcpu->arch.sie_block->prefix;
1342
	memcpy(&kvm_run->s.regs.crs, &vcpu->arch.sie_block->gcr, 128);
1343

1344 1345 1346 1347
	if (vcpu->sigset_active)
		sigprocmask(SIG_SETMASK, &sigsaved, NULL);

	vcpu->stat.exit_userspace++;
1348
	return rc;
1349 1350 1351 1352 1353 1354 1355 1356
}

/*
 * 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
 */
1357
int kvm_s390_store_status_unloaded(struct kvm_vcpu *vcpu, unsigned long gpa)
1358
{
1359
	unsigned char archmode = 1;
1360
	u64 clkcomp;
1361
	int rc;
1362

1363 1364
	if (gpa == KVM_S390_STORE_STATUS_NOADDR) {
		if (write_guest_abs(vcpu, 163, &archmode, 1))
1365
			return -EFAULT;
1366 1367 1368
		gpa = SAVE_AREA_BASE;
	} else if (gpa == KVM_S390_STORE_STATUS_PREFIXED) {
		if (write_guest_real(vcpu, 163, &archmode, 1))
1369
			return -EFAULT;
1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386
		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);
	rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, pref_reg),
			      &vcpu->arch.sie_block->prefix, 4);
	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);
1387
	clkcomp = vcpu->arch.sie_block->ckc >> 8;
1388 1389 1390 1391 1392 1393 1394
	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;
1395 1396
}

1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410
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);
}

1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439
static inline int is_vcpu_stopped(struct kvm_vcpu *vcpu)
{
	return atomic_read(&(vcpu)->arch.sie_block->cpuflags) & CPUSTAT_STOPPED;
}

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);
}

1440 1441
void kvm_s390_vcpu_start(struct kvm_vcpu *vcpu)
{
1442 1443 1444 1445 1446
	int i, online_vcpus, started_vcpus = 0;

	if (!is_vcpu_stopped(vcpu))
		return;

1447
	trace_kvm_s390_vcpu_start_stop(vcpu->vcpu_id, 1);
1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468
	/* Only one cpu at a time may enter/leave the STOPPED state. */
	spin_lock_bh(&vcpu->kvm->arch.start_stop_lock);
	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);
	}

1469
	atomic_clear_mask(CPUSTAT_STOPPED, &vcpu->arch.sie_block->cpuflags);
1470 1471 1472 1473 1474 1475 1476
	/*
	 * Another VCPU might have used IBS while we were offline.
	 * Let's play safe and flush the VCPU at startup.
	 */
	vcpu->arch.sie_block->ihcpu  = 0xffff;
	spin_unlock_bh(&vcpu->kvm->arch.start_stop_lock);
	return;
1477 1478 1479 1480
}

void kvm_s390_vcpu_stop(struct kvm_vcpu *vcpu)
{
1481 1482 1483 1484 1485 1486
	int i, online_vcpus, started_vcpus = 0;
	struct kvm_vcpu *started_vcpu = NULL;

	if (is_vcpu_stopped(vcpu))
		return;

1487
	trace_kvm_s390_vcpu_start_stop(vcpu->vcpu_id, 0);
1488 1489 1490 1491
	/* Only one cpu at a time may enter/leave the STOPPED state. */
	spin_lock_bh(&vcpu->kvm->arch.start_stop_lock);
	online_vcpus = atomic_read(&vcpu->kvm->online_vcpus);

1492
	atomic_set_mask(CPUSTAT_STOPPED, &vcpu->arch.sie_block->cpuflags);
1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511
	__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);
	}

	spin_unlock_bh(&vcpu->kvm->arch.start_stop_lock);
	return;
1512 1513
}

1514 1515 1516 1517 1518 1519 1520 1521 1522
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) {
1523 1524 1525 1526 1527 1528 1529
	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;
1530 1531 1532 1533 1534 1535 1536
	default:
		r = -EINVAL;
		break;
	}
	return r;
}

1537 1538 1539 1540 1541
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;
1542
	int idx;
1543
	long r;
1544

1545 1546
	switch (ioctl) {
	case KVM_S390_INTERRUPT: {
1547 1548
		struct kvm_s390_interrupt s390int;

1549
		r = -EFAULT;
1550
		if (copy_from_user(&s390int, argp, sizeof(s390int)))
1551 1552 1553
			break;
		r = kvm_s390_inject_vcpu(vcpu, &s390int);
		break;
1554
	}
1555
	case KVM_S390_STORE_STATUS:
1556
		idx = srcu_read_lock(&vcpu->kvm->srcu);
1557
		r = kvm_s390_vcpu_store_status(vcpu, arg);
1558
		srcu_read_unlock(&vcpu->kvm->srcu, idx);
1559
		break;
1560 1561 1562
	case KVM_S390_SET_INITIAL_PSW: {
		psw_t psw;

1563
		r = -EFAULT;
1564
		if (copy_from_user(&psw, argp, sizeof(psw)))
1565 1566 1567
			break;
		r = kvm_arch_vcpu_ioctl_set_initial_psw(vcpu, psw);
		break;
1568 1569
	}
	case KVM_S390_INITIAL_RESET:
1570 1571
		r = kvm_arch_vcpu_ioctl_initial_reset(vcpu);
		break;
1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583
	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;
	}
1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619
#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
1620 1621 1622 1623 1624 1625
	case KVM_S390_VCPU_FAULT: {
		r = gmap_fault(arg, vcpu->arch.gmap);
		if (!IS_ERR_VALUE(r))
			r = 0;
		break;
	}
1626 1627 1628 1629 1630 1631 1632 1633 1634
	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;
	}
1635
	default:
1636
		r = -ENOTTY;
1637
	}
1638
	return r;
1639 1640
}

1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653
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;
}

1654
void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free,
1655 1656 1657 1658
			   struct kvm_memory_slot *dont)
{
}

1659 1660
int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
			    unsigned long npages)
1661 1662 1663 1664
{
	return 0;
}

1665 1666 1667 1668
void kvm_arch_memslots_updated(struct kvm *kvm)
{
}

1669
/* Section: memory related */
1670 1671
int kvm_arch_prepare_memory_region(struct kvm *kvm,
				   struct kvm_memory_slot *memslot,
1672 1673
				   struct kvm_userspace_memory_region *mem,
				   enum kvm_mr_change change)
1674
{
1675 1676 1677 1678
	/* 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 */
1679

1680
	if (mem->userspace_addr & 0xffffful)
1681 1682
		return -EINVAL;

1683
	if (mem->memory_size & 0xffffful)
1684 1685
		return -EINVAL;

1686 1687 1688 1689 1690
	return 0;
}

void kvm_arch_commit_memory_region(struct kvm *kvm,
				struct kvm_userspace_memory_region *mem,
1691 1692
				const struct kvm_memory_slot *old,
				enum kvm_mr_change change)
1693
{
1694
	int rc;
1695

1696 1697 1698 1699 1700 1701 1702 1703 1704 1705
	/* 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;
1706 1707 1708 1709

	rc = gmap_map_segment(kvm->arch.gmap, mem->userspace_addr,
		mem->guest_phys_addr, mem->memory_size);
	if (rc)
1710
		printk(KERN_WARNING "kvm-s390: failed to commit memory region\n");
1711
	return;
1712 1713
}

1714 1715 1716 1717 1718 1719
void kvm_arch_flush_shadow_all(struct kvm *kvm)
{
}

void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
				   struct kvm_memory_slot *slot)
1720 1721 1722
{
}

1723 1724
static int __init kvm_s390_init(void)
{
1725
	int ret;
1726
	ret = kvm_init(NULL, sizeof(struct kvm_vcpu), 0, THIS_MODULE);
1727 1728 1729 1730 1731
	if (ret)
		return ret;

	/*
	 * guests can ask for up to 255+1 double words, we need a full page
L
Lucas De Marchi 已提交
1732
	 * to hold the maximum amount of facilities. On the other hand, we
1733 1734
	 * only set facilities that are known to work in KVM.
	 */
1735 1736
	vfacilities = (unsigned long *) get_zeroed_page(GFP_KERNEL|GFP_DMA);
	if (!vfacilities) {
1737 1738 1739
		kvm_exit();
		return -ENOMEM;
	}
1740
	memcpy(vfacilities, S390_lowcore.stfle_fac_list, 16);
1741
	vfacilities[0] &= 0xff82fff3f4fc2000UL;
1742
	vfacilities[1] &= 0x005c000000000000UL;
1743
	return 0;
1744 1745 1746 1747
}

static void __exit kvm_s390_exit(void)
{
1748
	free_page((unsigned long) vfacilities);
1749 1750 1751 1752 1753
	kvm_exit();
}

module_init(kvm_s390_init);
module_exit(kvm_s390_exit);
1754 1755 1756 1757 1758 1759 1760 1761 1762

/*
 * 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");