kvm-s390.c 45.5 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)
104 105
{
	/* every s390 is virtualization enabled ;-) */
106
	return 0;
107 108
}

109 110
static void kvm_gmap_notifier(struct gmap *gmap, unsigned long address);

111 112
int kvm_arch_hardware_setup(void)
{
113 114
	gmap_notifier.notifier_call = kvm_gmap_notifier;
	gmap_register_ipte_notifier(&gmap_notifier);
115 116 117 118 119
	return 0;
}

void kvm_arch_hardware_unsetup(void)
{
120
	gmap_unregister_ipte_notifier(&gmap_notifier);
121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136
}

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

/* 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;
}

137
int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
138
{
139 140
	int r;

141
	switch (ext) {
142
	case KVM_CAP_S390_PSW:
143
	case KVM_CAP_S390_GMAP:
144
	case KVM_CAP_SYNC_MMU:
145 146 147
#ifdef CONFIG_KVM_S390_UCONTROL
	case KVM_CAP_S390_UCONTROL:
#endif
148
	case KVM_CAP_ASYNC_PF:
149
	case KVM_CAP_SYNC_REGS:
150
	case KVM_CAP_ONE_REG:
151
	case KVM_CAP_ENABLE_CAP:
152
	case KVM_CAP_S390_CSS_SUPPORT:
153
	case KVM_CAP_IRQFD:
C
Cornelia Huck 已提交
154
	case KVM_CAP_IOEVENTFD:
155
	case KVM_CAP_DEVICE_CTRL:
156
	case KVM_CAP_ENABLE_CAP_VM:
157
	case KVM_CAP_S390_IRQCHIP:
158
	case KVM_CAP_VM_ATTRIBUTES:
159
	case KVM_CAP_MP_STATE:
160 161
		r = 1;
		break;
162 163 164 165
	case KVM_CAP_NR_VCPUS:
	case KVM_CAP_MAX_VCPUS:
		r = KVM_MAX_VCPUS;
		break;
166 167 168
	case KVM_CAP_NR_MEMSLOTS:
		r = KVM_USER_MEM_SLOTS;
		break;
169
	case KVM_CAP_S390_COW:
170
		r = MACHINE_HAS_ESOP;
171
		break;
172
	default:
173
		r = 0;
174
	}
175
	return r;
176 177
}

178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196
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);
}

197 198 199 200 201 202 203
/* 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)
{
204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233
	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;
234 235
}

236 237 238 239 240 241 242 243
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) {
244 245 246 247
	case KVM_CAP_S390_IRQCHIP:
		kvm->arch.use_irqchip = 1;
		r = 0;
		break;
248 249 250 251 252 253 254
	default:
		r = -EINVAL;
		break;
	}
	return r;
}

255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283
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;
}

284 285 286 287 288
static int kvm_s390_vm_set_attr(struct kvm *kvm, struct kvm_device_attr *attr)
{
	int ret;

	switch (attr->group) {
289 290 291
	case KVM_S390_VM_MEM_CTRL:
		ret = kvm_s390_mem_control(kvm, attr);
		break;
292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309
	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) {
310 311 312 313 314 315 316 317 318 319 320
	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;
321 322 323 324 325 326 327 328
	default:
		ret = -ENXIO;
		break;
	}

	return ret;
}

329 330 331 332 333
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;
334
	struct kvm_device_attr attr;
335 336 337
	int r;

	switch (ioctl) {
338 339 340 341 342 343 344 345 346
	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;
	}
347 348 349 350 351 352 353 354
	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;
	}
355 356 357 358 359 360 361 362 363 364 365 366
	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;
	}
367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387
	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;
	}
388
	default:
389
		r = -ENOTTY;
390 391 392 393 394
	}

	return r;
}

395
int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
396 397 398
{
	int rc;
	char debug_name[16];
399
	static unsigned long sca_offset;
400

401 402 403 404 405 406 407 408 409 410 411
	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

412 413
	rc = s390_enable_sie();
	if (rc)
414
		goto out_err;
415

416 417
	rc = -ENOMEM;

418 419
	kvm->arch.sca = (struct sca_block *) get_zeroed_page(GFP_KERNEL);
	if (!kvm->arch.sca)
420
		goto out_err;
421 422 423 424
	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);
425 426 427 428 429 430 431

	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;

432 433
	spin_lock_init(&kvm->arch.float_int.lock);
	INIT_LIST_HEAD(&kvm->arch.float_int.list);
434
	init_waitqueue_head(&kvm->arch.ipte_wq);
435

436 437 438
	debug_register_view(kvm->arch.dbf, &debug_sprintf_view);
	VM_EVENT(kvm, 3, "%s", "vm created");

439 440 441
	if (type & KVM_VM_S390_UCONTROL) {
		kvm->arch.gmap = NULL;
	} else {
442
		kvm->arch.gmap = gmap_alloc(current->mm, -1UL);
443 444
		if (!kvm->arch.gmap)
			goto out_nogmap;
445
		kvm->arch.gmap->private = kvm;
446
		kvm->arch.gmap->pfault_enabled = 0;
447
	}
448 449

	kvm->arch.css_support = 0;
450
	kvm->arch.use_irqchip = 0;
451

452 453
	spin_lock_init(&kvm->arch.start_stop_lock);

454
	return 0;
455 456
out_nogmap:
	debug_unregister(kvm->arch.dbf);
457 458
out_nodbf:
	free_page((unsigned long)(kvm->arch.sca));
459 460
out_err:
	return rc;
461 462
}

463 464 465
void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
{
	VCPU_EVENT(vcpu, 3, "%s", "free cpu");
466
	trace_kvm_s390_destroy_vcpu(vcpu->vcpu_id);
467
	kvm_s390_clear_local_irqs(vcpu);
468
	kvm_clear_async_pf_completion_queue(vcpu);
C
Carsten Otte 已提交
469 470 471 472 473 474 475
	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;
	}
476
	smp_mb();
477 478 479 480

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

481 482
	if (kvm_s390_cmma_enabled(vcpu->kvm))
		kvm_s390_vcpu_unsetup_cmma(vcpu);
483
	free_page((unsigned long)(vcpu->arch.sie_block));
484

485
	kvm_vcpu_uninit(vcpu);
486
	kmem_cache_free(kvm_vcpu_cache, vcpu);
487 488 489 490 491
}

static void kvm_free_vcpus(struct kvm *kvm)
{
	unsigned int i;
492
	struct kvm_vcpu *vcpu;
493

494 495 496 497 498 499 500 501 502
	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);
503 504
}

505 506
void kvm_arch_destroy_vm(struct kvm *kvm)
{
507
	kvm_free_vcpus(kvm);
508
	free_page((unsigned long)(kvm->arch.sca));
509
	debug_unregister(kvm->arch.dbf);
510 511
	if (!kvm_is_ucontrol(kvm))
		gmap_free(kvm->arch.gmap);
512
	kvm_s390_destroy_adapters(kvm);
513
	kvm_s390_clear_float_irqs(kvm);
514 515 516 517 518
}

/* Section: vcpu related */
int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
{
519 520
	vcpu->arch.pfault_token = KVM_S390_PFAULT_TOKEN_INVALID;
	kvm_clear_async_pf_completion_queue(vcpu);
521
	if (kvm_is_ucontrol(vcpu->kvm)) {
522
		vcpu->arch.gmap = gmap_alloc(current->mm, -1UL);
523 524
		if (!vcpu->arch.gmap)
			return -ENOMEM;
525
		vcpu->arch.gmap->private = vcpu->kvm;
526 527 528
		return 0;
	}

529
	vcpu->arch.gmap = vcpu->kvm->arch.gmap;
530 531
	vcpu->run->kvm_valid_regs = KVM_SYNC_PREFIX |
				    KVM_SYNC_GPRS |
532
				    KVM_SYNC_ACRS |
533 534 535
				    KVM_SYNC_CRS |
				    KVM_SYNC_ARCH0 |
				    KVM_SYNC_PFAULT;
536 537 538 539 540
	return 0;
}

void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
{
541 542
	save_fp_ctl(&vcpu->arch.host_fpregs.fpc);
	save_fp_regs(vcpu->arch.host_fpregs.fprs);
543
	save_access_regs(vcpu->arch.host_acrs);
544 545
	restore_fp_ctl(&vcpu->arch.guest_fpregs.fpc);
	restore_fp_regs(vcpu->arch.guest_fpregs.fprs);
546
	restore_access_regs(vcpu->run->s.regs.acrs);
547
	gmap_enable(vcpu->arch.gmap);
548
	atomic_set_mask(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
549 550 551 552
}

void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
{
553
	atomic_clear_mask(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
554
	gmap_disable(vcpu->arch.gmap);
555 556
	save_fp_ctl(&vcpu->arch.guest_fpregs.fpc);
	save_fp_regs(vcpu->arch.guest_fpregs.fprs);
557
	save_access_regs(vcpu->run->s.regs.acrs);
558 559
	restore_fp_ctl(&vcpu->arch.host_fpregs.fpc);
	restore_fp_regs(vcpu->arch.host_fpregs.fprs);
560 561 562 563 564 565 566 567
	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;
568
	kvm_s390_set_prefix(vcpu, 0);
569 570 571 572 573 574 575 576 577
	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;
578
	vcpu->arch.sie_block->pp = 0;
579 580
	vcpu->arch.pfault_token = KVM_S390_PFAULT_TOKEN_INVALID;
	kvm_clear_async_pf_completion_queue(vcpu);
581 582
	if (!kvm_s390_user_cpu_state_ctrl(vcpu->kvm))
		kvm_s390_vcpu_stop(vcpu);
583
	kvm_s390_clear_local_irqs(vcpu);
584 585
}

586 587 588 589 590
int kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
{
	return 0;
}

591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607
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;
}

608 609
int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
{
610
	int rc = 0;
611

612 613
	atomic_set(&vcpu->arch.sie_block->cpuflags, CPUSTAT_ZARCH |
						    CPUSTAT_SM |
614 615
						    CPUSTAT_STOPPED |
						    CPUSTAT_GED);
616
	vcpu->arch.sie_block->ecb   = 6;
617 618 619
	if (test_vfacility(50) && test_vfacility(73))
		vcpu->arch.sie_block->ecb |= 0x10;

620
	vcpu->arch.sie_block->ecb2  = 8;
621
	vcpu->arch.sie_block->eca   = 0xD1002000U;
622 623
	if (sclp_has_siif())
		vcpu->arch.sie_block->eca |= 1;
624
	vcpu->arch.sie_block->fac   = (int) (long) vfacilities;
625 626 627
	vcpu->arch.sie_block->ictl |= ICTL_ISKE | ICTL_SSKE | ICTL_RRBE |
				      ICTL_TPROT;

628 629 630 631
	if (kvm_s390_cmma_enabled(vcpu->kvm)) {
		rc = kvm_s390_vcpu_setup_cmma(vcpu);
		if (rc)
			return rc;
632
	}
633 634
	hrtimer_init(&vcpu->arch.ckc_timer, CLOCK_REALTIME, HRTIMER_MODE_ABS);
	vcpu->arch.ckc_timer.function = kvm_s390_idle_wakeup;
635
	get_cpu_id(&vcpu->arch.cpu_id);
636
	vcpu->arch.cpu_id.version = 0xff;
637
	return rc;
638 639 640 641 642
}

struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
				      unsigned int id)
{
643
	struct kvm_vcpu *vcpu;
644
	struct sie_page *sie_page;
645 646 647 648 649 650
	int rc = -EINVAL;

	if (id >= KVM_MAX_VCPUS)
		goto out;

	rc = -ENOMEM;
651

652
	vcpu = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL);
653
	if (!vcpu)
654
		goto out;
655

656 657
	sie_page = (struct sie_page *) get_zeroed_page(GFP_KERNEL);
	if (!sie_page)
658 659
		goto out_free_cpu;

660 661 662
	vcpu->arch.sie_block = &sie_page->sie_block;
	vcpu->arch.sie_block->itdba = (unsigned long) &sie_page->itdb;

663
	vcpu->arch.sie_block->icpua = id;
C
Carsten Otte 已提交
664 665 666 667 668 669 670 671 672 673 674 675 676
	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);
	}
677

678 679 680
	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;
681
	vcpu->arch.local_int.wq = &vcpu->wq;
682
	vcpu->arch.local_int.cpuflags = &vcpu->arch.sie_block->cpuflags;
683

684 685
	rc = kvm_vcpu_init(vcpu, kvm, id);
	if (rc)
686
		goto out_free_sie_block;
687 688
	VM_EVENT(kvm, 3, "create cpu %d at %p, sie block at %p", id, vcpu,
		 vcpu->arch.sie_block);
689
	trace_kvm_s390_create_vcpu(id, vcpu, vcpu->arch.sie_block);
690 691

	return vcpu;
692 693
out_free_sie_block:
	free_page((unsigned long)(vcpu->arch.sie_block));
694
out_free_cpu:
695
	kmem_cache_free(kvm_vcpu_cache, vcpu);
696
out:
697 698 699 700 701
	return ERR_PTR(rc);
}

int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
{
702
	return kvm_cpu_has_interrupt(vcpu);
703 704
}

705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732
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);
}

733 734 735 736 737 738 739 740
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 */
741
		if (kvm_s390_get_prefix(vcpu) == (address & ~0x1000UL)) {
742 743 744 745 746 747 748
			VCPU_EVENT(vcpu, 2, "gmap notifier for %lx", address);
			kvm_make_request(KVM_REQ_MMU_RELOAD, vcpu);
			exit_sie_sync(vcpu);
		}
	}
}

749 750 751 752 753 754 755
int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu)
{
	/* kvm common code refers to this, but never calls it */
	BUG();
	return 0;
}

756 757 758 759 760 761
static int kvm_arch_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu,
					   struct kvm_one_reg *reg)
{
	int r = -EINVAL;

	switch (reg->id) {
762 763 764 765 766 767 768 769
	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;
770 771 772 773 774 775 776 777
	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;
778 779 780 781 782 783 784 785 786 787 788 789
	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;
790 791 792 793
	case KVM_REG_S390_PP:
		r = put_user(vcpu->arch.sie_block->pp,
			     (u64 __user *)reg->addr);
		break;
794 795 796 797
	case KVM_REG_S390_GBEA:
		r = put_user(vcpu->arch.sie_block->gbea,
			     (u64 __user *)reg->addr);
		break;
798 799 800 801 802 803 804 805 806 807 808 809 810
	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) {
811 812 813 814 815 816 817 818
	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;
819 820 821 822 823 824 825 826
	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;
827 828 829 830 831 832 833 834 835 836 837 838
	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;
839 840 841 842
	case KVM_REG_S390_PP:
		r = get_user(vcpu->arch.sie_block->pp,
			     (u64 __user *)reg->addr);
		break;
843 844 845 846
	case KVM_REG_S390_GBEA:
		r = get_user(vcpu->arch.sie_block->gbea,
			     (u64 __user *)reg->addr);
		break;
847 848 849 850 851 852
	default:
		break;
	}

	return r;
}
853

854 855 856 857 858 859 860 861
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)
{
862
	memcpy(&vcpu->run->s.regs.gprs, &regs->gprs, sizeof(regs->gprs));
863 864 865 866 867
	return 0;
}

int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
{
868
	memcpy(&regs->gprs, &vcpu->run->s.regs.gprs, sizeof(regs->gprs));
869 870 871 872 873 874
	return 0;
}

int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
				  struct kvm_sregs *sregs)
{
875
	memcpy(&vcpu->run->s.regs.acrs, &sregs->acrs, sizeof(sregs->acrs));
876
	memcpy(&vcpu->arch.sie_block->gcr, &sregs->crs, sizeof(sregs->crs));
877
	restore_access_regs(vcpu->run->s.regs.acrs);
878 879 880 881 882 883
	return 0;
}

int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
				  struct kvm_sregs *sregs)
{
884
	memcpy(&sregs->acrs, &vcpu->run->s.regs.acrs, sizeof(sregs->acrs));
885 886 887 888 889 890
	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)
{
891 892
	if (test_fp_ctl(fpu->fpc))
		return -EINVAL;
893
	memcpy(&vcpu->arch.guest_fpregs.fprs, &fpu->fprs, sizeof(fpu->fprs));
894 895 896
	vcpu->arch.guest_fpregs.fpc = fpu->fpc;
	restore_fp_ctl(&vcpu->arch.guest_fpregs.fpc);
	restore_fp_regs(vcpu->arch.guest_fpregs.fprs);
897 898 899 900 901 902 903 904 905 906 907 908 909 910
	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;

911
	if (!is_vcpu_stopped(vcpu))
912
		rc = -EBUSY;
913 914 915 916
	else {
		vcpu->run->psw_mask = psw.mask;
		vcpu->run->psw_addr = psw.addr;
	}
917 918 919 920 921 922 923 924 925
	return rc;
}

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

926 927 928 929
#define VALID_GUESTDBG_FLAGS (KVM_GUESTDBG_SINGLESTEP | \
			      KVM_GUESTDBG_USE_HW_BP | \
			      KVM_GUESTDBG_ENABLE)

J
Jan Kiszka 已提交
930 931
int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
					struct kvm_guest_debug *dbg)
932
{
933 934 935 936 937
	int rc = 0;

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

938
	if (dbg->control & ~VALID_GUESTDBG_FLAGS)
939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959
		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;
960 961
}

962 963 964
int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
				    struct kvm_mp_state *mp_state)
{
965 966 967
	/* CHECK_STOP and LOAD are not supported yet */
	return is_vcpu_stopped(vcpu) ? KVM_MP_STATE_STOPPED :
				       KVM_MP_STATE_OPERATING;
968 969 970 971 972
}

int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
				    struct kvm_mp_state *mp_state)
{
973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992
	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;
993 994
}

995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006
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;
}

1007 1008 1009 1010 1011
static bool ibs_enabled(struct kvm_vcpu *vcpu)
{
	return atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_IBS;
}

1012 1013
static int kvm_s390_handle_requests(struct kvm_vcpu *vcpu)
{
1014 1015
retry:
	s390_vcpu_unblock(vcpu);
1016 1017 1018 1019 1020 1021 1022
	/*
	 * 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.
	 */
1023
	if (kvm_check_request(KVM_REQ_MMU_RELOAD, vcpu)) {
1024 1025
		int rc;
		rc = gmap_ipte_notify(vcpu->arch.gmap,
1026
				      kvm_s390_get_prefix(vcpu),
1027 1028 1029
				      PAGE_SIZE * 2);
		if (rc)
			return rc;
1030
		goto retry;
1031
	}
1032

1033 1034 1035 1036 1037
	if (kvm_check_request(KVM_REQ_TLB_FLUSH, vcpu)) {
		vcpu->arch.sie_block->ihcpu = 0xffff;
		goto retry;
	}

1038 1039 1040 1041 1042 1043 1044
	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;
1045
	}
1046 1047 1048 1049 1050 1051 1052 1053 1054 1055

	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;
	}

1056 1057 1058
	/* nothing to do, just clear the request */
	clear_bit(KVM_REQ_UNHALT, &vcpu->requests);

1059 1060 1061
	return 0;
}

1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072
/**
 * 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)
1073
{
1074 1075
	return gmap_fault(vcpu->arch.gmap, gpa,
			  writable ? FAULT_FLAG_WRITE : 0);
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 1138 1139 1140 1141
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
1142 1143 1144
	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))
1145 1146 1147 1148 1149 1150
		return 0;

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

1151
static int vcpu_pre_run(struct kvm_vcpu *vcpu)
1152
{
1153
	int rc, cpuflags;
1154

1155 1156 1157 1158 1159 1160 1161
	/*
	 * 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);

1162
	memcpy(&vcpu->arch.sie_block->gg14, &vcpu->run->s.regs.gprs[14], 16);
1163 1164 1165 1166

	if (need_resched())
		schedule();

1167
	if (test_cpu_flag(CIF_MCCK_PENDING))
1168 1169
		s390_handle_mcck();

1170 1171 1172 1173 1174
	if (!kvm_is_ucontrol(vcpu->kvm)) {
		rc = kvm_s390_deliver_pending_interrupts(vcpu);
		if (rc)
			return rc;
	}
C
Carsten Otte 已提交
1175

1176 1177 1178 1179
	rc = kvm_s390_handle_requests(vcpu);
	if (rc)
		return rc;

1180 1181 1182 1183 1184
	if (guestdbg_enabled(vcpu)) {
		kvm_s390_backup_guest_per_regs(vcpu);
		kvm_s390_patch_guest_per_regs(vcpu);
	}

1185
	vcpu->arch.sie_block->icptcode = 0;
1186 1187 1188
	cpuflags = atomic_read(&vcpu->arch.sie_block->cpuflags);
	VCPU_EVENT(vcpu, 6, "entering sie flags %x", cpuflags);
	trace_kvm_s390_sie_enter(vcpu, cpuflags);
1189

1190 1191 1192 1193 1194
	return 0;
}

static int vcpu_post_run(struct kvm_vcpu *vcpu, int exit_reason)
{
1195
	int rc = -1;
1196 1197 1198 1199 1200

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

1201 1202 1203
	if (guestdbg_enabled(vcpu))
		kvm_s390_restore_guest_per_regs(vcpu);

1204
	if (exit_reason >= 0) {
1205
		rc = 0;
1206 1207 1208 1209 1210 1211
	} 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;
1212 1213

	} else if (current->thread.gmap_pfault) {
1214
		trace_kvm_s390_major_guest_pfault(vcpu);
1215
		current->thread.gmap_pfault = 0;
1216
		if (kvm_arch_setup_async_pf(vcpu)) {
1217
			rc = 0;
1218 1219 1220 1221
		} else {
			gpa_t gpa = current->thread.gmap_addr;
			rc = kvm_arch_fault_in_page(vcpu, gpa, 1);
		}
1222 1223 1224
	}

	if (rc == -1) {
1225 1226 1227
		VCPU_EVENT(vcpu, 3, "%s", "fault in sie instruction");
		trace_kvm_s390_sie_fault(vcpu);
		rc = kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
1228
	}
1229

1230
	memcpy(&vcpu->run->s.regs.gprs[14], &vcpu->arch.sie_block->gg14, 16);
1231

1232 1233
	if (rc == 0) {
		if (kvm_is_ucontrol(vcpu->kvm))
1234 1235
			/* Don't exit for host interrupts. */
			rc = vcpu->arch.sie_block->icptcode ? -EOPNOTSUPP : 0;
1236 1237 1238 1239
		else
			rc = kvm_handle_sie_intercept(vcpu);
	}

1240 1241 1242 1243 1244 1245 1246
	return rc;
}

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

1247 1248 1249 1250 1251 1252
	/*
	 * 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);

1253 1254 1255 1256
	do {
		rc = vcpu_pre_run(vcpu);
		if (rc)
			break;
1257

1258
		srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
1259 1260 1261 1262 1263 1264 1265 1266 1267 1268
		/*
		 * 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();
1269
		vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
1270 1271

		rc = vcpu_post_run(vcpu, exit_reason);
1272
	} while (!signal_pending(current) && !guestdbg_exit_pending(vcpu) && !rc);
1273

1274
	srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
1275
	return rc;
1276 1277
}

1278 1279 1280 1281 1282 1283 1284 1285
static void sync_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
{
	vcpu->arch.sie_block->gpsw.mask = kvm_run->psw_mask;
	vcpu->arch.sie_block->gpsw.addr = kvm_run->psw_addr;
	if (kvm_run->kvm_dirty_regs & KVM_SYNC_PREFIX)
		kvm_s390_set_prefix(vcpu, kvm_run->s.regs.prefix);
	if (kvm_run->kvm_dirty_regs & KVM_SYNC_CRS) {
		memcpy(&vcpu->arch.sie_block->gcr, &kvm_run->s.regs.crs, 128);
1286 1287
		/* some control register changes require a tlb flush */
		kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319
	}
	if (kvm_run->kvm_dirty_regs & KVM_SYNC_ARCH0) {
		vcpu->arch.sie_block->cputm = kvm_run->s.regs.cputm;
		vcpu->arch.sie_block->ckc = kvm_run->s.regs.ckc;
		vcpu->arch.sie_block->todpr = kvm_run->s.regs.todpr;
		vcpu->arch.sie_block->pp = kvm_run->s.regs.pp;
		vcpu->arch.sie_block->gbea = kvm_run->s.regs.gbea;
	}
	if (kvm_run->kvm_dirty_regs & KVM_SYNC_PFAULT) {
		vcpu->arch.pfault_token = kvm_run->s.regs.pft;
		vcpu->arch.pfault_select = kvm_run->s.regs.pfs;
		vcpu->arch.pfault_compare = kvm_run->s.regs.pfc;
	}
	kvm_run->kvm_dirty_regs = 0;
}

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

1320 1321
int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
{
1322
	int rc;
1323 1324
	sigset_t sigsaved;

1325 1326 1327 1328 1329
	if (guestdbg_exit_pending(vcpu)) {
		kvm_s390_prepare_debug_exit(vcpu);
		return 0;
	}

1330 1331 1332
	if (vcpu->sigset_active)
		sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved);

1333 1334 1335 1336 1337 1338 1339
	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;
	}
1340

1341
	sync_regs(vcpu, kvm_run);
1342

1343
	might_fault();
1344
	rc = __vcpu_run(vcpu);
1345

1346 1347
	if (signal_pending(current) && !rc) {
		kvm_run->exit_reason = KVM_EXIT_INTR;
1348
		rc = -EINTR;
1349
	}
1350

1351 1352 1353 1354 1355
	if (guestdbg_exit_pending(vcpu) && !rc)  {
		kvm_s390_prepare_debug_exit(vcpu);
		rc = 0;
	}

1356
	if (rc == -EOPNOTSUPP) {
1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369
		/* 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;
	}
1370

1371
	store_regs(vcpu, kvm_run);
1372

1373 1374 1375 1376
	if (vcpu->sigset_active)
		sigprocmask(SIG_SETMASK, &sigsaved, NULL);

	vcpu->stat.exit_userspace++;
1377
	return rc;
1378 1379 1380 1381 1382 1383 1384 1385
}

/*
 * 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
 */
1386
int kvm_s390_store_status_unloaded(struct kvm_vcpu *vcpu, unsigned long gpa)
1387
{
1388
	unsigned char archmode = 1;
1389
	unsigned int px;
1390
	u64 clkcomp;
1391
	int rc;
1392

1393 1394
	if (gpa == KVM_S390_STORE_STATUS_NOADDR) {
		if (write_guest_abs(vcpu, 163, &archmode, 1))
1395
			return -EFAULT;
1396 1397 1398
		gpa = SAVE_AREA_BASE;
	} else if (gpa == KVM_S390_STORE_STATUS_PREFIXED) {
		if (write_guest_real(vcpu, 163, &archmode, 1))
1399
			return -EFAULT;
1400 1401 1402 1403 1404 1405 1406 1407
		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);
1408
	px = kvm_s390_get_prefix(vcpu);
1409
	rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, pref_reg),
1410
			      &px, 4);
1411 1412 1413 1414 1415 1416 1417
	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);
1418
	clkcomp = vcpu->arch.sie_block->ckc >> 8;
1419 1420 1421 1422 1423 1424 1425
	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;
1426 1427
}

1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441
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);
}

1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465
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);
}

1466 1467
void kvm_s390_vcpu_start(struct kvm_vcpu *vcpu)
{
1468 1469 1470 1471 1472
	int i, online_vcpus, started_vcpus = 0;

	if (!is_vcpu_stopped(vcpu))
		return;

1473
	trace_kvm_s390_vcpu_start_stop(vcpu->vcpu_id, 1);
1474
	/* Only one cpu at a time may enter/leave the STOPPED state. */
1475
	spin_lock(&vcpu->kvm->arch.start_stop_lock);
1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494
	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);
	}

1495
	atomic_clear_mask(CPUSTAT_STOPPED, &vcpu->arch.sie_block->cpuflags);
1496 1497 1498 1499
	/*
	 * Another VCPU might have used IBS while we were offline.
	 * Let's play safe and flush the VCPU at startup.
	 */
1500
	kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
1501
	spin_unlock(&vcpu->kvm->arch.start_stop_lock);
1502
	return;
1503 1504 1505 1506
}

void kvm_s390_vcpu_stop(struct kvm_vcpu *vcpu)
{
1507 1508 1509 1510 1511 1512
	int i, online_vcpus, started_vcpus = 0;
	struct kvm_vcpu *started_vcpu = NULL;

	if (is_vcpu_stopped(vcpu))
		return;

1513
	trace_kvm_s390_vcpu_start_stop(vcpu->vcpu_id, 0);
1514
	/* Only one cpu at a time may enter/leave the STOPPED state. */
1515
	spin_lock(&vcpu->kvm->arch.start_stop_lock);
1516 1517
	online_vcpus = atomic_read(&vcpu->kvm->online_vcpus);

1518
	/* Need to lock access to action_bits to avoid a SIGP race condition */
1519
	spin_lock(&vcpu->arch.local_int.lock);
1520
	atomic_set_mask(CPUSTAT_STOPPED, &vcpu->arch.sie_block->cpuflags);
1521 1522 1523 1524

	/* 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);
1525
	spin_unlock(&vcpu->arch.local_int.lock);
1526

1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543
	__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);
	}

1544
	spin_unlock(&vcpu->kvm->arch.start_stop_lock);
1545
	return;
1546 1547
}

1548 1549 1550 1551 1552 1553 1554 1555 1556
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) {
1557 1558 1559 1560 1561 1562 1563
	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;
1564 1565 1566 1567 1568 1569 1570
	default:
		r = -EINVAL;
		break;
	}
	return r;
}

1571 1572 1573 1574 1575
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;
1576
	int idx;
1577
	long r;
1578

1579 1580
	switch (ioctl) {
	case KVM_S390_INTERRUPT: {
1581 1582
		struct kvm_s390_interrupt s390int;

1583
		r = -EFAULT;
1584
		if (copy_from_user(&s390int, argp, sizeof(s390int)))
1585 1586 1587
			break;
		r = kvm_s390_inject_vcpu(vcpu, &s390int);
		break;
1588
	}
1589
	case KVM_S390_STORE_STATUS:
1590
		idx = srcu_read_lock(&vcpu->kvm->srcu);
1591
		r = kvm_s390_vcpu_store_status(vcpu, arg);
1592
		srcu_read_unlock(&vcpu->kvm->srcu, idx);
1593
		break;
1594 1595 1596
	case KVM_S390_SET_INITIAL_PSW: {
		psw_t psw;

1597
		r = -EFAULT;
1598
		if (copy_from_user(&psw, argp, sizeof(psw)))
1599 1600 1601
			break;
		r = kvm_arch_vcpu_ioctl_set_initial_psw(vcpu, psw);
		break;
1602 1603
	}
	case KVM_S390_INITIAL_RESET:
1604 1605
		r = kvm_arch_vcpu_ioctl_initial_reset(vcpu);
		break;
1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617
	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;
	}
1618 1619 1620 1621 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
#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
1654
	case KVM_S390_VCPU_FAULT: {
1655
		r = gmap_fault(vcpu->arch.gmap, arg, 0);
1656 1657
		break;
	}
1658 1659 1660 1661 1662 1663 1664 1665 1666
	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;
	}
1667
	default:
1668
		r = -ENOTTY;
1669
	}
1670
	return r;
1671 1672
}

1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685
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;
}

1686 1687
int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
			    unsigned long npages)
1688 1689 1690 1691
{
	return 0;
}

1692
/* Section: memory related */
1693 1694
int kvm_arch_prepare_memory_region(struct kvm *kvm,
				   struct kvm_memory_slot *memslot,
1695 1696
				   struct kvm_userspace_memory_region *mem,
				   enum kvm_mr_change change)
1697
{
1698 1699 1700 1701
	/* 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 */
1702

1703
	if (mem->userspace_addr & 0xffffful)
1704 1705
		return -EINVAL;

1706
	if (mem->memory_size & 0xffffful)
1707 1708
		return -EINVAL;

1709 1710 1711 1712 1713
	return 0;
}

void kvm_arch_commit_memory_region(struct kvm *kvm,
				struct kvm_userspace_memory_region *mem,
1714 1715
				const struct kvm_memory_slot *old,
				enum kvm_mr_change change)
1716
{
1717
	int rc;
1718

1719 1720 1721 1722 1723 1724 1725 1726 1727 1728
	/* 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;
1729 1730 1731 1732

	rc = gmap_map_segment(kvm->arch.gmap, mem->userspace_addr,
		mem->guest_phys_addr, mem->memory_size);
	if (rc)
1733
		printk(KERN_WARNING "kvm-s390: failed to commit memory region\n");
1734
	return;
1735 1736 1737 1738
}

static int __init kvm_s390_init(void)
{
1739
	int ret;
1740
	ret = kvm_init(NULL, sizeof(struct kvm_vcpu), 0, THIS_MODULE);
1741 1742 1743 1744 1745
	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
1746
	 * to hold the maximum amount of facilities. On the other hand, we
1747 1748
	 * only set facilities that are known to work in KVM.
	 */
1749 1750
	vfacilities = (unsigned long *) get_zeroed_page(GFP_KERNEL|GFP_DMA);
	if (!vfacilities) {
1751 1752 1753
		kvm_exit();
		return -ENOMEM;
	}
1754
	memcpy(vfacilities, S390_lowcore.stfle_fac_list, 16);
1755
	vfacilities[0] &= 0xff82fff3f4fc2000UL;
1756
	vfacilities[1] &= 0x005c000000000000UL;
1757
	return 0;
1758 1759 1760 1761
}

static void __exit kvm_s390_exit(void)
{
1762
	free_page((unsigned long) vfacilities);
1763 1764 1765 1766 1767
	kvm_exit();
}

module_init(kvm_s390_init);
module_exit(kvm_s390_exit);
1768 1769 1770 1771 1772 1773 1774 1775 1776

/*
 * 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");