kvm-s390.c 45.2 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:
165
	case KVM_CAP_IRQFD:
C
Cornelia Huck 已提交
166
	case KVM_CAP_IOEVENTFD:
167
	case KVM_CAP_DEVICE_CTRL:
168
	case KVM_CAP_ENABLE_CAP_VM:
169
	case KVM_CAP_VM_ATTRIBUTES:
170
	case KVM_CAP_MP_STATE:
171 172
		r = 1;
		break;
173 174 175 176
	case KVM_CAP_NR_VCPUS:
	case KVM_CAP_MAX_VCPUS:
		r = KVM_MAX_VCPUS;
		break;
177 178 179
	case KVM_CAP_NR_MEMSLOTS:
		r = KVM_USER_MEM_SLOTS;
		break;
180
	case KVM_CAP_S390_COW:
181
		r = MACHINE_HAS_ESOP;
182
		break;
183
	default:
184
		r = 0;
185
	}
186
	return r;
187 188
}

189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207
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);
}

208 209 210 211 212 213 214
/* 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)
{
215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244
	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;
245 246
}

247 248 249 250 251 252 253 254
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) {
255 256 257 258
	case KVM_CAP_S390_IRQCHIP:
		kvm->arch.use_irqchip = 1;
		r = 0;
		break;
259 260 261 262 263 264 265
	default:
		r = -EINVAL;
		break;
	}
	return r;
}

266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294
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;
}

295 296 297 298 299
static int kvm_s390_vm_set_attr(struct kvm *kvm, struct kvm_device_attr *attr)
{
	int ret;

	switch (attr->group) {
300 301 302
	case KVM_S390_VM_MEM_CTRL:
		ret = kvm_s390_mem_control(kvm, attr);
		break;
303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320
	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) {
321 322 323 324 325 326 327 328 329 330 331
	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;
332 333 334 335 336 337 338 339
	default:
		ret = -ENXIO;
		break;
	}

	return ret;
}

340 341 342 343 344
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;
345
	struct kvm_device_attr attr;
346 347 348
	int r;

	switch (ioctl) {
349 350 351 352 353 354 355 356 357
	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;
	}
358 359 360 361 362 363 364 365
	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;
	}
366 367 368 369 370 371 372 373 374 375 376 377
	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;
	}
378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398
	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;
	}
399
	default:
400
		r = -ENOTTY;
401 402 403 404 405
	}

	return r;
}

406
int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
407 408 409
{
	int rc;
	char debug_name[16];
410
	static unsigned long sca_offset;
411

412 413 414 415 416 417 418 419 420 421 422
	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

423 424
	rc = s390_enable_sie();
	if (rc)
425
		goto out_err;
426

427 428
	rc = -ENOMEM;

429 430
	kvm->arch.sca = (struct sca_block *) get_zeroed_page(GFP_KERNEL);
	if (!kvm->arch.sca)
431
		goto out_err;
432 433 434 435
	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);
436 437 438 439 440 441 442

	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;

443 444
	spin_lock_init(&kvm->arch.float_int.lock);
	INIT_LIST_HEAD(&kvm->arch.float_int.list);
445
	init_waitqueue_head(&kvm->arch.ipte_wq);
446

447 448 449
	debug_register_view(kvm->arch.dbf, &debug_sprintf_view);
	VM_EVENT(kvm, 3, "%s", "vm created");

450 451 452 453 454 455
	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;
456
		kvm->arch.gmap->private = kvm;
457
		kvm->arch.gmap->pfault_enabled = 0;
458
	}
459 460

	kvm->arch.css_support = 0;
461
	kvm->arch.use_irqchip = 0;
462

463 464
	spin_lock_init(&kvm->arch.start_stop_lock);

465
	return 0;
466 467
out_nogmap:
	debug_unregister(kvm->arch.dbf);
468 469
out_nodbf:
	free_page((unsigned long)(kvm->arch.sca));
470 471
out_err:
	return rc;
472 473
}

474 475 476
void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
{
	VCPU_EVENT(vcpu, 3, "%s", "free cpu");
477
	trace_kvm_s390_destroy_vcpu(vcpu->vcpu_id);
478
	kvm_s390_clear_local_irqs(vcpu);
479
	kvm_clear_async_pf_completion_queue(vcpu);
C
Carsten Otte 已提交
480 481 482 483 484 485 486
	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;
	}
487
	smp_mb();
488 489 490 491

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

492 493
	if (kvm_s390_cmma_enabled(vcpu->kvm))
		kvm_s390_vcpu_unsetup_cmma(vcpu);
494
	free_page((unsigned long)(vcpu->arch.sie_block));
495

496
	kvm_vcpu_uninit(vcpu);
497
	kmem_cache_free(kvm_vcpu_cache, vcpu);
498 499 500 501 502
}

static void kvm_free_vcpus(struct kvm *kvm)
{
	unsigned int i;
503
	struct kvm_vcpu *vcpu;
504

505 506 507 508 509 510 511 512 513
	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);
514 515
}

516 517 518 519
void kvm_arch_sync_events(struct kvm *kvm)
{
}

520 521
void kvm_arch_destroy_vm(struct kvm *kvm)
{
522
	kvm_free_vcpus(kvm);
523
	free_page((unsigned long)(kvm->arch.sca));
524
	debug_unregister(kvm->arch.dbf);
525 526
	if (!kvm_is_ucontrol(kvm))
		gmap_free(kvm->arch.gmap);
527
	kvm_s390_destroy_adapters(kvm);
528
	kvm_s390_clear_float_irqs(kvm);
529 530 531 532 533
}

/* Section: vcpu related */
int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
{
534 535
	vcpu->arch.pfault_token = KVM_S390_PFAULT_TOKEN_INVALID;
	kvm_clear_async_pf_completion_queue(vcpu);
536 537 538 539
	if (kvm_is_ucontrol(vcpu->kvm)) {
		vcpu->arch.gmap = gmap_alloc(current->mm);
		if (!vcpu->arch.gmap)
			return -ENOMEM;
540
		vcpu->arch.gmap->private = vcpu->kvm;
541 542 543
		return 0;
	}

544
	vcpu->arch.gmap = vcpu->kvm->arch.gmap;
545 546
	vcpu->run->kvm_valid_regs = KVM_SYNC_PREFIX |
				    KVM_SYNC_GPRS |
547 548
				    KVM_SYNC_ACRS |
				    KVM_SYNC_CRS;
549 550 551 552 553
	return 0;
}

void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu)
{
554
	/* Nothing todo */
555 556 557 558
}

void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
{
559 560
	save_fp_ctl(&vcpu->arch.host_fpregs.fpc);
	save_fp_regs(vcpu->arch.host_fpregs.fprs);
561
	save_access_regs(vcpu->arch.host_acrs);
562 563
	restore_fp_ctl(&vcpu->arch.guest_fpregs.fpc);
	restore_fp_regs(vcpu->arch.guest_fpregs.fprs);
564
	restore_access_regs(vcpu->run->s.regs.acrs);
565
	gmap_enable(vcpu->arch.gmap);
566
	atomic_set_mask(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
567 568 569 570
}

void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
{
571
	atomic_clear_mask(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
572
	gmap_disable(vcpu->arch.gmap);
573 574
	save_fp_ctl(&vcpu->arch.guest_fpregs.fpc);
	save_fp_regs(vcpu->arch.guest_fpregs.fprs);
575
	save_access_regs(vcpu->run->s.regs.acrs);
576 577
	restore_fp_ctl(&vcpu->arch.host_fpregs.fpc);
	restore_fp_regs(vcpu->arch.host_fpregs.fprs);
578 579 580 581 582 583 584 585
	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;
586
	kvm_s390_set_prefix(vcpu, 0);
587 588 589 590 591 592 593 594 595
	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;
596
	vcpu->arch.sie_block->pp = 0;
597 598
	vcpu->arch.pfault_token = KVM_S390_PFAULT_TOKEN_INVALID;
	kvm_clear_async_pf_completion_queue(vcpu);
599 600
	if (!kvm_s390_user_cpu_state_ctrl(vcpu->kvm))
		kvm_s390_vcpu_stop(vcpu);
601
	kvm_s390_clear_local_irqs(vcpu);
602 603
}

604 605 606 607 608
int kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
{
	return 0;
}

609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625
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;
}

626 627
int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
{
628
	int rc = 0;
629

630 631
	atomic_set(&vcpu->arch.sie_block->cpuflags, CPUSTAT_ZARCH |
						    CPUSTAT_SM |
632 633
						    CPUSTAT_STOPPED |
						    CPUSTAT_GED);
634
	vcpu->arch.sie_block->ecb   = 6;
635 636 637
	if (test_vfacility(50) && test_vfacility(73))
		vcpu->arch.sie_block->ecb |= 0x10;

638
	vcpu->arch.sie_block->ecb2  = 8;
639
	vcpu->arch.sie_block->eca   = 0xD1002000U;
640 641
	if (sclp_has_siif())
		vcpu->arch.sie_block->eca |= 1;
642
	vcpu->arch.sie_block->fac   = (int) (long) vfacilities;
643 644 645
	vcpu->arch.sie_block->ictl |= ICTL_ISKE | ICTL_SSKE | ICTL_RRBE |
				      ICTL_TPROT;

646 647 648 649
	if (kvm_s390_cmma_enabled(vcpu->kvm)) {
		rc = kvm_s390_vcpu_setup_cmma(vcpu);
		if (rc)
			return rc;
650
	}
651 652
	hrtimer_init(&vcpu->arch.ckc_timer, CLOCK_REALTIME, HRTIMER_MODE_ABS);
	vcpu->arch.ckc_timer.function = kvm_s390_idle_wakeup;
653
	get_cpu_id(&vcpu->arch.cpu_id);
654
	vcpu->arch.cpu_id.version = 0xff;
655
	return rc;
656 657 658 659 660
}

struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
				      unsigned int id)
{
661
	struct kvm_vcpu *vcpu;
662
	struct sie_page *sie_page;
663 664 665 666 667 668
	int rc = -EINVAL;

	if (id >= KVM_MAX_VCPUS)
		goto out;

	rc = -ENOMEM;
669

670
	vcpu = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL);
671
	if (!vcpu)
672
		goto out;
673

674 675
	sie_page = (struct sie_page *) get_zeroed_page(GFP_KERNEL);
	if (!sie_page)
676 677
		goto out_free_cpu;

678 679 680
	vcpu->arch.sie_block = &sie_page->sie_block;
	vcpu->arch.sie_block->itdba = (unsigned long) &sie_page->itdb;

681
	vcpu->arch.sie_block->icpua = id;
C
Carsten Otte 已提交
682 683 684 685 686 687 688 689 690 691 692 693 694
	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);
	}
695

696 697 698
	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;
699
	vcpu->arch.local_int.wq = &vcpu->wq;
700
	vcpu->arch.local_int.cpuflags = &vcpu->arch.sie_block->cpuflags;
701

702 703
	rc = kvm_vcpu_init(vcpu, kvm, id);
	if (rc)
704
		goto out_free_sie_block;
705 706
	VM_EVENT(kvm, 3, "create cpu %d at %p, sie block at %p", id, vcpu,
		 vcpu->arch.sie_block);
707
	trace_kvm_s390_create_vcpu(id, vcpu, vcpu->arch.sie_block);
708 709

	return vcpu;
710 711
out_free_sie_block:
	free_page((unsigned long)(vcpu->arch.sie_block));
712
out_free_cpu:
713
	kmem_cache_free(kvm_vcpu_cache, vcpu);
714
out:
715 716 717 718 719
	return ERR_PTR(rc);
}

int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
{
720
	return kvm_cpu_has_interrupt(vcpu);
721 722
}

723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750
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);
}

751 752 753 754 755 756 757 758
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 */
759
		if (kvm_s390_get_prefix(vcpu) == (address & ~0x1000UL)) {
760 761 762 763 764 765 766
			VCPU_EVENT(vcpu, 2, "gmap notifier for %lx", address);
			kvm_make_request(KVM_REQ_MMU_RELOAD, vcpu);
			exit_sie_sync(vcpu);
		}
	}
}

767 768 769 770 771 772 773
int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu)
{
	/* kvm common code refers to this, but never calls it */
	BUG();
	return 0;
}

774 775 776 777 778 779
static int kvm_arch_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu,
					   struct kvm_one_reg *reg)
{
	int r = -EINVAL;

	switch (reg->id) {
780 781 782 783 784 785 786 787
	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;
788 789 790 791 792 793 794 795
	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;
796 797 798 799 800 801 802 803 804 805 806 807
	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;
808 809 810 811
	case KVM_REG_S390_PP:
		r = put_user(vcpu->arch.sie_block->pp,
			     (u64 __user *)reg->addr);
		break;
812 813 814 815
	case KVM_REG_S390_GBEA:
		r = put_user(vcpu->arch.sie_block->gbea,
			     (u64 __user *)reg->addr);
		break;
816 817 818 819 820 821 822 823 824 825 826 827 828
	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) {
829 830 831 832 833 834 835 836
	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;
837 838 839 840 841 842 843 844
	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;
845 846 847 848 849 850 851 852 853 854 855 856
	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;
857 858 859 860
	case KVM_REG_S390_PP:
		r = get_user(vcpu->arch.sie_block->pp,
			     (u64 __user *)reg->addr);
		break;
861 862 863 864
	case KVM_REG_S390_GBEA:
		r = get_user(vcpu->arch.sie_block->gbea,
			     (u64 __user *)reg->addr);
		break;
865 866 867 868 869 870
	default:
		break;
	}

	return r;
}
871

872 873 874 875 876 877 878 879
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)
{
880
	memcpy(&vcpu->run->s.regs.gprs, &regs->gprs, sizeof(regs->gprs));
881 882 883 884 885
	return 0;
}

int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
{
886
	memcpy(&regs->gprs, &vcpu->run->s.regs.gprs, sizeof(regs->gprs));
887 888 889 890 891 892
	return 0;
}

int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
				  struct kvm_sregs *sregs)
{
893
	memcpy(&vcpu->run->s.regs.acrs, &sregs->acrs, sizeof(sregs->acrs));
894
	memcpy(&vcpu->arch.sie_block->gcr, &sregs->crs, sizeof(sregs->crs));
895
	restore_access_regs(vcpu->run->s.regs.acrs);
896 897 898 899 900 901
	return 0;
}

int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
				  struct kvm_sregs *sregs)
{
902
	memcpy(&sregs->acrs, &vcpu->run->s.regs.acrs, sizeof(sregs->acrs));
903 904 905 906 907 908
	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)
{
909 910
	if (test_fp_ctl(fpu->fpc))
		return -EINVAL;
911
	memcpy(&vcpu->arch.guest_fpregs.fprs, &fpu->fprs, sizeof(fpu->fprs));
912 913 914
	vcpu->arch.guest_fpregs.fpc = fpu->fpc;
	restore_fp_ctl(&vcpu->arch.guest_fpregs.fpc);
	restore_fp_regs(vcpu->arch.guest_fpregs.fprs);
915 916 917 918 919 920 921 922 923 924 925 926 927 928
	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;

929
	if (!is_vcpu_stopped(vcpu))
930
		rc = -EBUSY;
931 932 933 934
	else {
		vcpu->run->psw_mask = psw.mask;
		vcpu->run->psw_addr = psw.addr;
	}
935 936 937 938 939 940 941 942 943
	return rc;
}

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

944 945 946 947
#define VALID_GUESTDBG_FLAGS (KVM_GUESTDBG_SINGLESTEP | \
			      KVM_GUESTDBG_USE_HW_BP | \
			      KVM_GUESTDBG_ENABLE)

J
Jan Kiszka 已提交
948 949
int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
					struct kvm_guest_debug *dbg)
950
{
951 952 953 954 955
	int rc = 0;

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

956
	if (dbg->control & ~VALID_GUESTDBG_FLAGS)
957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977
		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;
978 979
}

980 981 982
int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
				    struct kvm_mp_state *mp_state)
{
983 984 985
	/* CHECK_STOP and LOAD are not supported yet */
	return is_vcpu_stopped(vcpu) ? KVM_MP_STATE_STOPPED :
				       KVM_MP_STATE_OPERATING;
986 987 988 989 990
}

int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
				    struct kvm_mp_state *mp_state)
{
991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010
	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;
1011 1012
}

1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024
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;
}

1025 1026 1027 1028 1029
static bool ibs_enabled(struct kvm_vcpu *vcpu)
{
	return atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_IBS;
}

1030 1031
static int kvm_s390_handle_requests(struct kvm_vcpu *vcpu)
{
1032 1033
retry:
	s390_vcpu_unblock(vcpu);
1034 1035 1036 1037 1038 1039 1040
	/*
	 * 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.
	 */
1041
	if (kvm_check_request(KVM_REQ_MMU_RELOAD, vcpu)) {
1042 1043
		int rc;
		rc = gmap_ipte_notify(vcpu->arch.gmap,
1044
				      kvm_s390_get_prefix(vcpu),
1045 1046 1047
				      PAGE_SIZE * 2);
		if (rc)
			return rc;
1048
		goto retry;
1049
	}
1050 1051 1052 1053 1054 1055 1056 1057

	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;
1058
	}
1059 1060 1061 1062 1063 1064 1065 1066 1067 1068

	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;
	}

1069 1070 1071
	/* nothing to do, just clear the request */
	clear_bit(KVM_REQ_UNHALT, &vcpu->requests);

1072 1073 1074
	return 0;
}

1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085
/**
 * 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)
1086 1087
{
	struct mm_struct *mm = current->mm;
1088 1089 1090 1091 1092 1093
	hva_t hva;
	long rc;

	hva = gmap_fault(gpa, vcpu->arch.gmap);
	if (IS_ERR_VALUE(hva))
		return (long)hva;
1094
	down_read(&mm->mmap_sem);
1095
	rc = get_user_pages(current, mm, hva, 1, writable, 0, NULL, NULL);
1096
	up_read(&mm->mmap_sem);
1097 1098

	return rc < 0 ? rc : 0;
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 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164
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
1165 1166 1167
	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))
1168 1169 1170 1171 1172 1173
		return 0;

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

1174
static int vcpu_pre_run(struct kvm_vcpu *vcpu)
1175
{
1176
	int rc, cpuflags;
1177

1178 1179 1180 1181 1182 1183 1184
	/*
	 * 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);

1185
	memcpy(&vcpu->arch.sie_block->gg14, &vcpu->run->s.regs.gprs[14], 16);
1186 1187 1188 1189

	if (need_resched())
		schedule();

1190
	if (test_cpu_flag(CIF_MCCK_PENDING))
1191 1192
		s390_handle_mcck();

1193 1194
	if (!kvm_is_ucontrol(vcpu->kvm))
		kvm_s390_deliver_pending_interrupts(vcpu);
C
Carsten Otte 已提交
1195

1196 1197 1198 1199
	rc = kvm_s390_handle_requests(vcpu);
	if (rc)
		return rc;

1200 1201 1202 1203 1204
	if (guestdbg_enabled(vcpu)) {
		kvm_s390_backup_guest_per_regs(vcpu);
		kvm_s390_patch_guest_per_regs(vcpu);
	}

1205
	vcpu->arch.sie_block->icptcode = 0;
1206 1207 1208
	cpuflags = atomic_read(&vcpu->arch.sie_block->cpuflags);
	VCPU_EVENT(vcpu, 6, "entering sie flags %x", cpuflags);
	trace_kvm_s390_sie_enter(vcpu, cpuflags);
1209

1210 1211 1212 1213 1214
	return 0;
}

static int vcpu_post_run(struct kvm_vcpu *vcpu, int exit_reason)
{
1215
	int rc = -1;
1216 1217 1218 1219 1220

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

1221 1222 1223
	if (guestdbg_enabled(vcpu))
		kvm_s390_restore_guest_per_regs(vcpu);

1224
	if (exit_reason >= 0) {
1225
		rc = 0;
1226 1227 1228 1229 1230 1231
	} 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;
1232 1233

	} else if (current->thread.gmap_pfault) {
1234
		trace_kvm_s390_major_guest_pfault(vcpu);
1235
		current->thread.gmap_pfault = 0;
1236
		if (kvm_arch_setup_async_pf(vcpu)) {
1237
			rc = 0;
1238 1239 1240 1241
		} else {
			gpa_t gpa = current->thread.gmap_addr;
			rc = kvm_arch_fault_in_page(vcpu, gpa, 1);
		}
1242 1243 1244
	}

	if (rc == -1) {
1245 1246 1247
		VCPU_EVENT(vcpu, 3, "%s", "fault in sie instruction");
		trace_kvm_s390_sie_fault(vcpu);
		rc = kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
1248
	}
1249

1250
	memcpy(&vcpu->run->s.regs.gprs[14], &vcpu->arch.sie_block->gg14, 16);
1251

1252 1253
	if (rc == 0) {
		if (kvm_is_ucontrol(vcpu->kvm))
1254 1255
			/* Don't exit for host interrupts. */
			rc = vcpu->arch.sie_block->icptcode ? -EOPNOTSUPP : 0;
1256 1257 1258 1259
		else
			rc = kvm_handle_sie_intercept(vcpu);
	}

1260 1261 1262 1263 1264 1265 1266
	return rc;
}

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

1267 1268 1269 1270 1271 1272
	/*
	 * 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);

1273 1274 1275 1276
	do {
		rc = vcpu_pre_run(vcpu);
		if (rc)
			break;
1277

1278
		srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
1279 1280 1281 1282 1283 1284 1285 1286 1287 1288
		/*
		 * 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();
1289
		vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
1290 1291

		rc = vcpu_post_run(vcpu, exit_reason);
1292
	} while (!signal_pending(current) && !guestdbg_exit_pending(vcpu) && !rc);
1293

1294
	srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
1295
	return rc;
1296 1297 1298 1299
}

int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
{
1300
	int rc;
1301 1302
	sigset_t sigsaved;

1303 1304 1305 1306 1307
	if (guestdbg_exit_pending(vcpu)) {
		kvm_s390_prepare_debug_exit(vcpu);
		return 0;
	}

1308 1309 1310
	if (vcpu->sigset_active)
		sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved);

1311 1312 1313 1314 1315 1316 1317
	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;
	}
1318

1319 1320 1321
	switch (kvm_run->exit_reason) {
	case KVM_EXIT_S390_SIEIC:
	case KVM_EXIT_UNKNOWN:
1322
	case KVM_EXIT_INTR:
1323
	case KVM_EXIT_S390_RESET:
1324
	case KVM_EXIT_S390_UCONTROL:
1325
	case KVM_EXIT_S390_TSCH:
1326
	case KVM_EXIT_DEBUG:
1327 1328 1329 1330 1331
		break;
	default:
		BUG();
	}

1332 1333
	vcpu->arch.sie_block->gpsw.mask = kvm_run->psw_mask;
	vcpu->arch.sie_block->gpsw.addr = kvm_run->psw_addr;
1334 1335 1336 1337
	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);
	}
1338 1339 1340 1341 1342
	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);
	}
1343

1344
	might_fault();
1345
	rc = __vcpu_run(vcpu);
1346

1347 1348
	if (signal_pending(current) && !rc) {
		kvm_run->exit_reason = KVM_EXIT_INTR;
1349
		rc = -EINTR;
1350
	}
1351

1352 1353 1354 1355 1356
	if (guestdbg_exit_pending(vcpu) && !rc)  {
		kvm_s390_prepare_debug_exit(vcpu);
		rc = 0;
	}

1357
	if (rc == -EOPNOTSUPP) {
1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370
		/* 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;
	}
1371

1372 1373
	kvm_run->psw_mask     = vcpu->arch.sie_block->gpsw.mask;
	kvm_run->psw_addr     = vcpu->arch.sie_block->gpsw.addr;
1374
	kvm_run->s.regs.prefix = kvm_s390_get_prefix(vcpu);
1375
	memcpy(&kvm_run->s.regs.crs, &vcpu->arch.sie_block->gcr, 128);
1376

1377 1378 1379 1380
	if (vcpu->sigset_active)
		sigprocmask(SIG_SETMASK, &sigsaved, NULL);

	vcpu->stat.exit_userspace++;
1381
	return rc;
1382 1383 1384 1385 1386 1387 1388 1389
}

/*
 * 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
 */
1390
int kvm_s390_store_status_unloaded(struct kvm_vcpu *vcpu, unsigned long gpa)
1391
{
1392
	unsigned char archmode = 1;
1393
	unsigned int px;
1394
	u64 clkcomp;
1395
	int rc;
1396

1397 1398
	if (gpa == KVM_S390_STORE_STATUS_NOADDR) {
		if (write_guest_abs(vcpu, 163, &archmode, 1))
1399
			return -EFAULT;
1400 1401 1402
		gpa = SAVE_AREA_BASE;
	} else if (gpa == KVM_S390_STORE_STATUS_PREFIXED) {
		if (write_guest_real(vcpu, 163, &archmode, 1))
1403
			return -EFAULT;
1404 1405 1406 1407 1408 1409 1410 1411
		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);
1412
	px = kvm_s390_get_prefix(vcpu);
1413
	rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, pref_reg),
1414
			      &px, 4);
1415 1416 1417 1418 1419 1420 1421
	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);
1422
	clkcomp = vcpu->arch.sie_block->ckc >> 8;
1423 1424 1425 1426 1427 1428 1429
	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;
1430 1431
}

1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445
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);
}

1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469
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);
}

1470 1471
void kvm_s390_vcpu_start(struct kvm_vcpu *vcpu)
{
1472 1473 1474 1475 1476
	int i, online_vcpus, started_vcpus = 0;

	if (!is_vcpu_stopped(vcpu))
		return;

1477
	trace_kvm_s390_vcpu_start_stop(vcpu->vcpu_id, 1);
1478
	/* Only one cpu at a time may enter/leave the STOPPED state. */
1479
	spin_lock(&vcpu->kvm->arch.start_stop_lock);
1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498
	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);
	}

1499
	atomic_clear_mask(CPUSTAT_STOPPED, &vcpu->arch.sie_block->cpuflags);
1500 1501 1502 1503 1504
	/*
	 * 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;
1505
	spin_unlock(&vcpu->kvm->arch.start_stop_lock);
1506
	return;
1507 1508 1509 1510
}

void kvm_s390_vcpu_stop(struct kvm_vcpu *vcpu)
{
1511 1512 1513 1514 1515 1516
	int i, online_vcpus, started_vcpus = 0;
	struct kvm_vcpu *started_vcpu = NULL;

	if (is_vcpu_stopped(vcpu))
		return;

1517
	trace_kvm_s390_vcpu_start_stop(vcpu->vcpu_id, 0);
1518
	/* Only one cpu at a time may enter/leave the STOPPED state. */
1519
	spin_lock(&vcpu->kvm->arch.start_stop_lock);
1520 1521
	online_vcpus = atomic_read(&vcpu->kvm->online_vcpus);

1522
	/* Need to lock access to action_bits to avoid a SIGP race condition */
1523
	spin_lock(&vcpu->arch.local_int.lock);
1524
	atomic_set_mask(CPUSTAT_STOPPED, &vcpu->arch.sie_block->cpuflags);
1525 1526 1527 1528

	/* SIGP STOP and SIGP STOP AND STORE STATUS has been fully processed */
	vcpu->arch.local_int.action_bits &=
				 ~(ACTION_STOP_ON_STOP | ACTION_STORE_ON_STOP);
1529
	spin_unlock(&vcpu->arch.local_int.lock);
1530

1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547
	__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);
	}

1548
	spin_unlock(&vcpu->kvm->arch.start_stop_lock);
1549
	return;
1550 1551
}

1552 1553 1554 1555 1556 1557 1558 1559 1560
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) {
1561 1562 1563 1564 1565 1566 1567
	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;
1568 1569 1570 1571 1572 1573 1574
	default:
		r = -EINVAL;
		break;
	}
	return r;
}

1575 1576 1577 1578 1579
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;
1580
	int idx;
1581
	long r;
1582

1583 1584
	switch (ioctl) {
	case KVM_S390_INTERRUPT: {
1585 1586
		struct kvm_s390_interrupt s390int;

1587
		r = -EFAULT;
1588
		if (copy_from_user(&s390int, argp, sizeof(s390int)))
1589 1590 1591
			break;
		r = kvm_s390_inject_vcpu(vcpu, &s390int);
		break;
1592
	}
1593
	case KVM_S390_STORE_STATUS:
1594
		idx = srcu_read_lock(&vcpu->kvm->srcu);
1595
		r = kvm_s390_vcpu_store_status(vcpu, arg);
1596
		srcu_read_unlock(&vcpu->kvm->srcu, idx);
1597
		break;
1598 1599 1600
	case KVM_S390_SET_INITIAL_PSW: {
		psw_t psw;

1601
		r = -EFAULT;
1602
		if (copy_from_user(&psw, argp, sizeof(psw)))
1603 1604 1605
			break;
		r = kvm_arch_vcpu_ioctl_set_initial_psw(vcpu, psw);
		break;
1606 1607
	}
	case KVM_S390_INITIAL_RESET:
1608 1609
		r = kvm_arch_vcpu_ioctl_initial_reset(vcpu);
		break;
1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621
	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;
	}
1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657
#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
1658 1659 1660 1661 1662 1663
	case KVM_S390_VCPU_FAULT: {
		r = gmap_fault(arg, vcpu->arch.gmap);
		if (!IS_ERR_VALUE(r))
			r = 0;
		break;
	}
1664 1665 1666 1667 1668 1669 1670 1671 1672
	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;
	}
1673
	default:
1674
		r = -ENOTTY;
1675
	}
1676
	return r;
1677 1678
}

1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691
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;
}

1692
void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free,
1693 1694 1695 1696
			   struct kvm_memory_slot *dont)
{
}

1697 1698
int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
			    unsigned long npages)
1699 1700 1701 1702
{
	return 0;
}

1703 1704 1705 1706
void kvm_arch_memslots_updated(struct kvm *kvm)
{
}

1707
/* Section: memory related */
1708 1709
int kvm_arch_prepare_memory_region(struct kvm *kvm,
				   struct kvm_memory_slot *memslot,
1710 1711
				   struct kvm_userspace_memory_region *mem,
				   enum kvm_mr_change change)
1712
{
1713 1714 1715 1716
	/* 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 */
1717

1718
	if (mem->userspace_addr & 0xffffful)
1719 1720
		return -EINVAL;

1721
	if (mem->memory_size & 0xffffful)
1722 1723
		return -EINVAL;

1724 1725 1726 1727 1728
	return 0;
}

void kvm_arch_commit_memory_region(struct kvm *kvm,
				struct kvm_userspace_memory_region *mem,
1729 1730
				const struct kvm_memory_slot *old,
				enum kvm_mr_change change)
1731
{
1732
	int rc;
1733

1734 1735 1736 1737 1738 1739 1740 1741 1742 1743
	/* 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;
1744 1745 1746 1747

	rc = gmap_map_segment(kvm->arch.gmap, mem->userspace_addr,
		mem->guest_phys_addr, mem->memory_size);
	if (rc)
1748
		printk(KERN_WARNING "kvm-s390: failed to commit memory region\n");
1749
	return;
1750 1751
}

1752 1753 1754 1755 1756 1757
void kvm_arch_flush_shadow_all(struct kvm *kvm)
{
}

void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
				   struct kvm_memory_slot *slot)
1758 1759 1760
{
}

1761 1762
static int __init kvm_s390_init(void)
{
1763
	int ret;
1764
	ret = kvm_init(NULL, sizeof(struct kvm_vcpu), 0, THIS_MODULE);
1765 1766 1767 1768 1769
	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
1770
	 * to hold the maximum amount of facilities. On the other hand, we
1771 1772
	 * only set facilities that are known to work in KVM.
	 */
1773 1774
	vfacilities = (unsigned long *) get_zeroed_page(GFP_KERNEL|GFP_DMA);
	if (!vfacilities) {
1775 1776 1777
		kvm_exit();
		return -ENOMEM;
	}
1778
	memcpy(vfacilities, S390_lowcore.stfle_fac_list, 16);
1779
	vfacilities[0] &= 0xff82fff3f4fc2000UL;
1780
	vfacilities[1] &= 0x005c000000000000UL;
1781
	return 0;
1782 1783 1784 1785
}

static void __exit kvm_s390_exit(void)
{
1786
	free_page((unsigned long) vfacilities);
1787 1788 1789 1790 1791
	kvm_exit();
}

module_init(kvm_s390_init);
module_exit(kvm_s390_exit);
1792 1793 1794 1795 1796 1797 1798 1799 1800

/*
 * 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");