kvm-s390.c 47.1 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
	{ "halt_wakeup", VCPU_STAT(halt_wakeup) },
54
	{ "instruction_lctlg", VCPU_STAT(instruction_lctlg) },
55
	{ "instruction_lctl", VCPU_STAT(instruction_lctl) },
56 57
	{ "instruction_stctl", VCPU_STAT(instruction_stctl) },
	{ "instruction_stctg", VCPU_STAT(instruction_stctg) },
58
	{ "deliver_emergency_signal", VCPU_STAT(deliver_emergency_signal) },
59
	{ "deliver_external_call", VCPU_STAT(deliver_external_call) },
60 61 62 63 64 65 66
	{ "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) },
67
	{ "instruction_pfmf", VCPU_STAT(instruction_pfmf) },
68 69 70 71 72
	{ "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) },
73
	{ "instruction_ipte_interlock", VCPU_STAT(instruction_ipte_interlock) },
74 75
	{ "instruction_stsch", VCPU_STAT(instruction_stsch) },
	{ "instruction_chsc", VCPU_STAT(instruction_chsc) },
76
	{ "instruction_essa", VCPU_STAT(instruction_essa) },
77 78
	{ "instruction_stsi", VCPU_STAT(instruction_stsi) },
	{ "instruction_stfl", VCPU_STAT(instruction_stfl) },
79
	{ "instruction_tprot", VCPU_STAT(instruction_tprot) },
80
	{ "instruction_sigp_sense", VCPU_STAT(instruction_sigp_sense) },
81
	{ "instruction_sigp_sense_running", VCPU_STAT(instruction_sigp_sense_running) },
82
	{ "instruction_sigp_external_call", VCPU_STAT(instruction_sigp_external_call) },
83
	{ "instruction_sigp_emergency", VCPU_STAT(instruction_sigp_emergency) },
84 85
	{ "instruction_sigp_cond_emergency", VCPU_STAT(instruction_sigp_cond_emergency) },
	{ "instruction_sigp_start", VCPU_STAT(instruction_sigp_start) },
86
	{ "instruction_sigp_stop", VCPU_STAT(instruction_sigp_stop) },
87 88
	{ "instruction_sigp_stop_store_status", VCPU_STAT(instruction_sigp_stop_store_status) },
	{ "instruction_sigp_store_status", VCPU_STAT(instruction_sigp_store_status) },
89 90 91
	{ "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) },
92 93 94
	{ "instruction_sigp_cpu_reset", VCPU_STAT(instruction_sigp_cpu_reset) },
	{ "instruction_sigp_init_cpu_reset", VCPU_STAT(instruction_sigp_init_cpu_reset) },
	{ "instruction_sigp_unknown", VCPU_STAT(instruction_sigp_unknown) },
95
	{ "diagnose_10", VCPU_STAT(diagnose_10) },
96
	{ "diagnose_44", VCPU_STAT(diagnose_44) },
97
	{ "diagnose_9c", VCPU_STAT(diagnose_9c) },
98 99 100
	{ NULL }
};

101
unsigned long *vfacilities;
102
static struct gmap_notifier gmap_notifier;
103

104
/* test availability of vfacility */
105
int test_vfacility(unsigned long nr)
106 107 108 109
{
	return __test_facility(nr, (void *) vfacilities);
}

110
/* Section: not file related */
111
int kvm_arch_hardware_enable(void)
112 113
{
	/* every s390 is virtualization enabled ;-) */
114
	return 0;
115 116
}

117 118
static void kvm_gmap_notifier(struct gmap *gmap, unsigned long address);

119 120
int kvm_arch_hardware_setup(void)
{
121 122
	gmap_notifier.notifier_call = kvm_gmap_notifier;
	gmap_register_ipte_notifier(&gmap_notifier);
123 124 125 126 127
	return 0;
}

void kvm_arch_hardware_unsetup(void)
{
128
	gmap_unregister_ipte_notifier(&gmap_notifier);
129 130 131 132
}

int kvm_arch_init(void *opaque)
{
133 134
	/* Register floating interrupt controller interface. */
	return kvm_register_device_ops(&kvm_flic_ops, KVM_DEV_TYPE_FLIC);
135 136 137 138 139 140 141 142 143 144 145
}

/* 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;
}

146
int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
147
{
148 149
	int r;

150
	switch (ext) {
151
	case KVM_CAP_S390_PSW:
152
	case KVM_CAP_S390_GMAP:
153
	case KVM_CAP_SYNC_MMU:
154 155 156
#ifdef CONFIG_KVM_S390_UCONTROL
	case KVM_CAP_S390_UCONTROL:
#endif
157
	case KVM_CAP_ASYNC_PF:
158
	case KVM_CAP_SYNC_REGS:
159
	case KVM_CAP_ONE_REG:
160
	case KVM_CAP_ENABLE_CAP:
161
	case KVM_CAP_S390_CSS_SUPPORT:
162
	case KVM_CAP_IRQFD:
C
Cornelia Huck 已提交
163
	case KVM_CAP_IOEVENTFD:
164
	case KVM_CAP_DEVICE_CTRL:
165
	case KVM_CAP_ENABLE_CAP_VM:
166
	case KVM_CAP_S390_IRQCHIP:
167
	case KVM_CAP_VM_ATTRIBUTES:
168
	case KVM_CAP_MP_STATE:
169 170
		r = 1;
		break;
171 172 173 174
	case KVM_CAP_NR_VCPUS:
	case KVM_CAP_MAX_VCPUS:
		r = KVM_MAX_VCPUS;
		break;
175 176 177
	case KVM_CAP_NR_MEMSLOTS:
		r = KVM_USER_MEM_SLOTS;
		break;
178
	case KVM_CAP_S390_COW:
179
		r = MACHINE_HAS_ESOP;
180
		break;
181
	default:
182
		r = 0;
183
	}
184
	return r;
185 186
}

187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205
static void kvm_s390_sync_dirty_log(struct kvm *kvm,
					struct kvm_memory_slot *memslot)
{
	gfn_t cur_gfn, last_gfn;
	unsigned long address;
	struct gmap *gmap = kvm->arch.gmap;

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

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

206 207 208 209 210 211 212
/* Section: vm related */
/*
 * Get (and clear) the dirty memory log for a memory slot.
 */
int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
			       struct kvm_dirty_log *log)
{
213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242
	int r;
	unsigned long n;
	struct kvm_memory_slot *memslot;
	int is_dirty = 0;

	mutex_lock(&kvm->slots_lock);

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

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

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

	/* Clear the dirty log */
	if (is_dirty) {
		n = kvm_dirty_bitmap_bytes(memslot);
		memset(memslot->dirty_bitmap, 0, n);
	}
	r = 0;
out:
	mutex_unlock(&kvm->slots_lock);
	return r;
243 244
}

245 246 247 248 249 250 251 252
static int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap)
{
	int r;

	if (cap->flags)
		return -EINVAL;

	switch (cap->cap) {
253 254 255 256
	case KVM_CAP_S390_IRQCHIP:
		kvm->arch.use_irqchip = 1;
		r = 0;
		break;
257 258 259 260 261 262 263
	default:
		r = -EINVAL;
		break;
	}
	return r;
}

264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280
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);
281
		s390_reset_cmma(kvm->arch.gmap->mm);
282 283 284 285 286 287 288 289 290 291 292
		srcu_read_unlock(&kvm->srcu, idx);
		mutex_unlock(&kvm->lock);
		ret = 0;
		break;
	default:
		ret = -ENXIO;
		break;
	}
	return ret;
}

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

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

	return ret;
}

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

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

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

	return ret;
}

338 339 340 341 342
long kvm_arch_vm_ioctl(struct file *filp,
		       unsigned int ioctl, unsigned long arg)
{
	struct kvm *kvm = filp->private_data;
	void __user *argp = (void __user *)arg;
343
	struct kvm_device_attr attr;
344 345 346
	int r;

	switch (ioctl) {
347 348 349 350 351 352 353 354 355
	case KVM_S390_INTERRUPT: {
		struct kvm_s390_interrupt s390int;

		r = -EFAULT;
		if (copy_from_user(&s390int, argp, sizeof(s390int)))
			break;
		r = kvm_s390_inject_vm(kvm, &s390int);
		break;
	}
356 357 358 359 360 361 362 363
	case KVM_ENABLE_CAP: {
		struct kvm_enable_cap cap;
		r = -EFAULT;
		if (copy_from_user(&cap, argp, sizeof(cap)))
			break;
		r = kvm_vm_ioctl_enable_cap(kvm, &cap);
		break;
	}
364 365 366 367 368 369 370 371 372 373 374 375
	case KVM_CREATE_IRQCHIP: {
		struct kvm_irq_routing_entry routing;

		r = -EINVAL;
		if (kvm->arch.use_irqchip) {
			/* Set up dummy routing. */
			memset(&routing, 0, sizeof(routing));
			kvm_set_irq_routing(kvm, &routing, 0, 0);
			r = 0;
		}
		break;
	}
376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396
	case KVM_SET_DEVICE_ATTR: {
		r = -EFAULT;
		if (copy_from_user(&attr, (void __user *)arg, sizeof(attr)))
			break;
		r = kvm_s390_vm_set_attr(kvm, &attr);
		break;
	}
	case KVM_GET_DEVICE_ATTR: {
		r = -EFAULT;
		if (copy_from_user(&attr, (void __user *)arg, sizeof(attr)))
			break;
		r = kvm_s390_vm_get_attr(kvm, &attr);
		break;
	}
	case KVM_HAS_DEVICE_ATTR: {
		r = -EFAULT;
		if (copy_from_user(&attr, (void __user *)arg, sizeof(attr)))
			break;
		r = kvm_s390_vm_has_attr(kvm, &attr);
		break;
	}
397
	default:
398
		r = -ENOTTY;
399 400 401 402 403
	}

	return r;
}

404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419
static int kvm_s390_crypto_init(struct kvm *kvm)
{
	if (!test_vfacility(76))
		return 0;

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

	kvm->arch.crypto.crycbd = (__u32) (unsigned long) kvm->arch.crypto.crycb |
				  CRYCB_FORMAT1;

	return 0;
}

420
int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
421 422 423
{
	int rc;
	char debug_name[16];
424
	static unsigned long sca_offset;
425

426 427 428 429 430 431 432 433 434 435 436
	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

437 438
	rc = s390_enable_sie();
	if (rc)
439
		goto out_err;
440

441 442
	rc = -ENOMEM;

443 444
	kvm->arch.sca = (struct sca_block *) get_zeroed_page(GFP_KERNEL);
	if (!kvm->arch.sca)
445
		goto out_err;
446 447 448 449
	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);
450 451 452 453 454 455 456

	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;

457 458 459
	if (kvm_s390_crypto_init(kvm) < 0)
		goto out_crypto;

460 461
	spin_lock_init(&kvm->arch.float_int.lock);
	INIT_LIST_HEAD(&kvm->arch.float_int.list);
462
	init_waitqueue_head(&kvm->arch.ipte_wq);
463
	mutex_init(&kvm->arch.ipte_mutex);
464

465 466 467
	debug_register_view(kvm->arch.dbf, &debug_sprintf_view);
	VM_EVENT(kvm, 3, "%s", "vm created");

468 469 470
	if (type & KVM_VM_S390_UCONTROL) {
		kvm->arch.gmap = NULL;
	} else {
471
		kvm->arch.gmap = gmap_alloc(current->mm, (1UL << 44) - 1);
472 473
		if (!kvm->arch.gmap)
			goto out_nogmap;
474
		kvm->arch.gmap->private = kvm;
475
		kvm->arch.gmap->pfault_enabled = 0;
476
	}
477 478

	kvm->arch.css_support = 0;
479
	kvm->arch.use_irqchip = 0;
480

481 482
	spin_lock_init(&kvm->arch.start_stop_lock);

483
	return 0;
484
out_nogmap:
485 486
	kfree(kvm->arch.crypto.crycb);
out_crypto:
487
	debug_unregister(kvm->arch.dbf);
488 489
out_nodbf:
	free_page((unsigned long)(kvm->arch.sca));
490 491
out_err:
	return rc;
492 493
}

494 495 496
void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
{
	VCPU_EVENT(vcpu, 3, "%s", "free cpu");
497
	trace_kvm_s390_destroy_vcpu(vcpu->vcpu_id);
498
	kvm_s390_clear_local_irqs(vcpu);
499
	kvm_clear_async_pf_completion_queue(vcpu);
C
Carsten Otte 已提交
500 501 502 503 504 505 506
	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;
	}
507
	smp_mb();
508 509 510 511

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

512 513
	if (kvm_s390_cmma_enabled(vcpu->kvm))
		kvm_s390_vcpu_unsetup_cmma(vcpu);
514
	free_page((unsigned long)(vcpu->arch.sie_block));
515

516
	kvm_vcpu_uninit(vcpu);
517
	kmem_cache_free(kvm_vcpu_cache, vcpu);
518 519 520 521 522
}

static void kvm_free_vcpus(struct kvm *kvm)
{
	unsigned int i;
523
	struct kvm_vcpu *vcpu;
524

525 526 527 528 529 530 531 532 533
	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);
534 535
}

536 537
void kvm_arch_destroy_vm(struct kvm *kvm)
{
538
	kvm_free_vcpus(kvm);
539
	free_page((unsigned long)(kvm->arch.sca));
540
	debug_unregister(kvm->arch.dbf);
541
	kfree(kvm->arch.crypto.crycb);
542 543
	if (!kvm_is_ucontrol(kvm))
		gmap_free(kvm->arch.gmap);
544
	kvm_s390_destroy_adapters(kvm);
545
	kvm_s390_clear_float_irqs(kvm);
546 547 548
}

/* Section: vcpu related */
549 550 551 552 553 554 555 556 557 558
static int __kvm_ucontrol_vcpu_init(struct kvm_vcpu *vcpu)
{
	vcpu->arch.gmap = gmap_alloc(current->mm, -1UL);
	if (!vcpu->arch.gmap)
		return -ENOMEM;
	vcpu->arch.gmap->private = vcpu->kvm;

	return 0;
}

559 560
int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
{
561 562
	vcpu->arch.pfault_token = KVM_S390_PFAULT_TOKEN_INVALID;
	kvm_clear_async_pf_completion_queue(vcpu);
563 564
	vcpu->run->kvm_valid_regs = KVM_SYNC_PREFIX |
				    KVM_SYNC_GPRS |
565
				    KVM_SYNC_ACRS |
566 567 568
				    KVM_SYNC_CRS |
				    KVM_SYNC_ARCH0 |
				    KVM_SYNC_PFAULT;
569 570 571 572

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

573 574 575 576 577
	return 0;
}

void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
{
578 579
	save_fp_ctl(&vcpu->arch.host_fpregs.fpc);
	save_fp_regs(vcpu->arch.host_fpregs.fprs);
580
	save_access_regs(vcpu->arch.host_acrs);
581 582
	restore_fp_ctl(&vcpu->arch.guest_fpregs.fpc);
	restore_fp_regs(vcpu->arch.guest_fpregs.fprs);
583
	restore_access_regs(vcpu->run->s.regs.acrs);
584
	gmap_enable(vcpu->arch.gmap);
585
	atomic_set_mask(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
586 587 588 589
}

void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
{
590
	atomic_clear_mask(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
591
	gmap_disable(vcpu->arch.gmap);
592 593
	save_fp_ctl(&vcpu->arch.guest_fpregs.fpc);
	save_fp_regs(vcpu->arch.guest_fpregs.fprs);
594
	save_access_regs(vcpu->run->s.regs.acrs);
595 596
	restore_fp_ctl(&vcpu->arch.host_fpregs.fpc);
	restore_fp_regs(vcpu->arch.host_fpregs.fprs);
597 598 599 600 601 602 603 604
	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;
605
	kvm_s390_set_prefix(vcpu, 0);
606 607 608 609 610 611 612 613 614
	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;
615
	vcpu->arch.sie_block->pp = 0;
616 617
	vcpu->arch.pfault_token = KVM_S390_PFAULT_TOKEN_INVALID;
	kvm_clear_async_pf_completion_queue(vcpu);
618 619
	if (!kvm_s390_user_cpu_state_ctrl(vcpu->kvm))
		kvm_s390_vcpu_stop(vcpu);
620
	kvm_s390_clear_local_irqs(vcpu);
621 622
}

623
void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
624
{
625 626
	if (!kvm_is_ucontrol(vcpu->kvm))
		vcpu->arch.gmap = vcpu->kvm->arch.gmap;
627 628
}

629 630 631 632 633 634 635 636
static void kvm_s390_vcpu_crypto_setup(struct kvm_vcpu *vcpu)
{
	if (!test_vfacility(76))
		return;

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

637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653
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;
}

654 655
int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
{
656
	int rc = 0;
657

658 659
	atomic_set(&vcpu->arch.sie_block->cpuflags, CPUSTAT_ZARCH |
						    CPUSTAT_SM |
660 661
						    CPUSTAT_STOPPED |
						    CPUSTAT_GED);
662
	vcpu->arch.sie_block->ecb   = 6;
663 664 665
	if (test_vfacility(50) && test_vfacility(73))
		vcpu->arch.sie_block->ecb |= 0x10;

666
	vcpu->arch.sie_block->ecb2  = 8;
667
	vcpu->arch.sie_block->eca   = 0xD1002000U;
668 669
	if (sclp_has_siif())
		vcpu->arch.sie_block->eca |= 1;
670
	vcpu->arch.sie_block->fac   = (int) (long) vfacilities;
671 672 673
	vcpu->arch.sie_block->ictl |= ICTL_ISKE | ICTL_SSKE | ICTL_RRBE |
				      ICTL_TPROT;

674 675 676 677
	if (kvm_s390_cmma_enabled(vcpu->kvm)) {
		rc = kvm_s390_vcpu_setup_cmma(vcpu);
		if (rc)
			return rc;
678
	}
679 680
	hrtimer_init(&vcpu->arch.ckc_timer, CLOCK_REALTIME, HRTIMER_MODE_ABS);
	vcpu->arch.ckc_timer.function = kvm_s390_idle_wakeup;
681
	get_cpu_id(&vcpu->arch.cpu_id);
682
	vcpu->arch.cpu_id.version = 0xff;
683 684 685

	kvm_s390_vcpu_crypto_setup(vcpu);

686
	return rc;
687 688 689 690 691
}

struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
				      unsigned int id)
{
692
	struct kvm_vcpu *vcpu;
693
	struct sie_page *sie_page;
694 695 696 697 698 699
	int rc = -EINVAL;

	if (id >= KVM_MAX_VCPUS)
		goto out;

	rc = -ENOMEM;
700

701
	vcpu = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL);
702
	if (!vcpu)
703
		goto out;
704

705 706
	sie_page = (struct sie_page *) get_zeroed_page(GFP_KERNEL);
	if (!sie_page)
707 708
		goto out_free_cpu;

709 710 711
	vcpu->arch.sie_block = &sie_page->sie_block;
	vcpu->arch.sie_block->itdba = (unsigned long) &sie_page->itdb;

712
	vcpu->arch.sie_block->icpua = id;
C
Carsten Otte 已提交
713 714 715 716 717 718 719 720 721 722 723 724 725
	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);
	}
726

727 728
	spin_lock_init(&vcpu->arch.local_int.lock);
	vcpu->arch.local_int.float_int = &kvm->arch.float_int;
729
	vcpu->arch.local_int.wq = &vcpu->wq;
730
	vcpu->arch.local_int.cpuflags = &vcpu->arch.sie_block->cpuflags;
731

732 733
	rc = kvm_vcpu_init(vcpu, kvm, id);
	if (rc)
734
		goto out_free_sie_block;
735 736
	VM_EVENT(kvm, 3, "create cpu %d at %p, sie block at %p", id, vcpu,
		 vcpu->arch.sie_block);
737
	trace_kvm_s390_create_vcpu(id, vcpu, vcpu->arch.sie_block);
738 739

	return vcpu;
740 741
out_free_sie_block:
	free_page((unsigned long)(vcpu->arch.sie_block));
742
out_free_cpu:
743
	kmem_cache_free(kvm_vcpu_cache, vcpu);
744
out:
745 746 747 748 749
	return ERR_PTR(rc);
}

int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
{
750
	return kvm_cpu_has_interrupt(vcpu);
751 752
}

753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780
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);
}

781 782 783 784 785 786 787 788
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 */
789
		if (kvm_s390_get_prefix(vcpu) == (address & ~0x1000UL)) {
790 791 792 793 794 795 796
			VCPU_EVENT(vcpu, 2, "gmap notifier for %lx", address);
			kvm_make_request(KVM_REQ_MMU_RELOAD, vcpu);
			exit_sie_sync(vcpu);
		}
	}
}

797 798 799 800 801 802 803
int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu)
{
	/* kvm common code refers to this, but never calls it */
	BUG();
	return 0;
}

804 805 806 807 808 809
static int kvm_arch_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu,
					   struct kvm_one_reg *reg)
{
	int r = -EINVAL;

	switch (reg->id) {
810 811 812 813 814 815 816 817
	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;
818 819 820 821 822 823 824 825
	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;
826 827 828 829 830 831 832 833 834 835 836 837
	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;
838 839 840 841
	case KVM_REG_S390_PP:
		r = put_user(vcpu->arch.sie_block->pp,
			     (u64 __user *)reg->addr);
		break;
842 843 844 845
	case KVM_REG_S390_GBEA:
		r = put_user(vcpu->arch.sie_block->gbea,
			     (u64 __user *)reg->addr);
		break;
846 847 848 849 850 851 852 853 854 855 856 857 858
	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) {
859 860 861 862 863 864 865 866
	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;
867 868 869 870 871 872 873 874
	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;
875 876 877 878 879 880 881 882 883 884 885 886
	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;
887 888 889 890
	case KVM_REG_S390_PP:
		r = get_user(vcpu->arch.sie_block->pp,
			     (u64 __user *)reg->addr);
		break;
891 892 893 894
	case KVM_REG_S390_GBEA:
		r = get_user(vcpu->arch.sie_block->gbea,
			     (u64 __user *)reg->addr);
		break;
895 896 897 898 899 900
	default:
		break;
	}

	return r;
}
901

902 903 904 905 906 907 908 909
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)
{
910
	memcpy(&vcpu->run->s.regs.gprs, &regs->gprs, sizeof(regs->gprs));
911 912 913 914 915
	return 0;
}

int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
{
916
	memcpy(&regs->gprs, &vcpu->run->s.regs.gprs, sizeof(regs->gprs));
917 918 919 920 921 922
	return 0;
}

int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
				  struct kvm_sregs *sregs)
{
923
	memcpy(&vcpu->run->s.regs.acrs, &sregs->acrs, sizeof(sregs->acrs));
924
	memcpy(&vcpu->arch.sie_block->gcr, &sregs->crs, sizeof(sregs->crs));
925
	restore_access_regs(vcpu->run->s.regs.acrs);
926 927 928 929 930 931
	return 0;
}

int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
				  struct kvm_sregs *sregs)
{
932
	memcpy(&sregs->acrs, &vcpu->run->s.regs.acrs, sizeof(sregs->acrs));
933 934 935 936 937 938
	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)
{
939 940
	if (test_fp_ctl(fpu->fpc))
		return -EINVAL;
941
	memcpy(&vcpu->arch.guest_fpregs.fprs, &fpu->fprs, sizeof(fpu->fprs));
942 943 944
	vcpu->arch.guest_fpregs.fpc = fpu->fpc;
	restore_fp_ctl(&vcpu->arch.guest_fpregs.fpc);
	restore_fp_regs(vcpu->arch.guest_fpregs.fprs);
945 946 947 948 949 950 951 952 953 954 955 956 957 958
	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;

959
	if (!is_vcpu_stopped(vcpu))
960
		rc = -EBUSY;
961 962 963 964
	else {
		vcpu->run->psw_mask = psw.mask;
		vcpu->run->psw_addr = psw.addr;
	}
965 966 967 968 969 970 971 972 973
	return rc;
}

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

974 975 976 977
#define VALID_GUESTDBG_FLAGS (KVM_GUESTDBG_SINGLESTEP | \
			      KVM_GUESTDBG_USE_HW_BP | \
			      KVM_GUESTDBG_ENABLE)

J
Jan Kiszka 已提交
978 979
int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
					struct kvm_guest_debug *dbg)
980
{
981 982 983 984 985
	int rc = 0;

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

986
	if (dbg->control & ~VALID_GUESTDBG_FLAGS)
987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007
		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;
1008 1009
}

1010 1011 1012
int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
				    struct kvm_mp_state *mp_state)
{
1013 1014 1015
	/* CHECK_STOP and LOAD are not supported yet */
	return is_vcpu_stopped(vcpu) ? KVM_MP_STATE_STOPPED :
				       KVM_MP_STATE_OPERATING;
1016 1017 1018 1019 1020
}

int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
				    struct kvm_mp_state *mp_state)
{
1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040
	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;
1041 1042
}

1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054
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;
}

1055 1056 1057 1058 1059
static bool ibs_enabled(struct kvm_vcpu *vcpu)
{
	return atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_IBS;
}

1060 1061
static int kvm_s390_handle_requests(struct kvm_vcpu *vcpu)
{
1062 1063
retry:
	s390_vcpu_unblock(vcpu);
1064 1065 1066 1067 1068 1069 1070
	/*
	 * 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.
	 */
1071
	if (kvm_check_request(KVM_REQ_MMU_RELOAD, vcpu)) {
1072 1073
		int rc;
		rc = gmap_ipte_notify(vcpu->arch.gmap,
1074
				      kvm_s390_get_prefix(vcpu),
1075 1076 1077
				      PAGE_SIZE * 2);
		if (rc)
			return rc;
1078
		goto retry;
1079
	}
1080

1081 1082 1083 1084 1085
	if (kvm_check_request(KVM_REQ_TLB_FLUSH, vcpu)) {
		vcpu->arch.sie_block->ihcpu = 0xffff;
		goto retry;
	}

1086 1087 1088 1089 1090 1091 1092
	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;
1093
	}
1094 1095 1096 1097 1098 1099 1100 1101 1102 1103

	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;
	}

1104 1105 1106
	/* nothing to do, just clear the request */
	clear_bit(KVM_REQ_UNHALT, &vcpu->requests);

1107 1108 1109
	return 0;
}

1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120
/**
 * 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)
1121
{
1122 1123
	return gmap_fault(vcpu->arch.gmap, gpa,
			  writable ? FAULT_FLAG_WRITE : 0);
1124 1125
}

1126 1127 1128 1129
static void __kvm_inject_pfault_token(struct kvm_vcpu *vcpu, bool start_token,
				      unsigned long token)
{
	struct kvm_s390_interrupt inti;
1130
	struct kvm_s390_irq irq;
1131 1132

	if (start_token) {
1133 1134 1135
		irq.u.ext.ext_params2 = token;
		irq.type = KVM_S390_INT_PFAULT_INIT;
		WARN_ON_ONCE(kvm_s390_inject_vcpu(vcpu, &irq));
1136 1137
	} else {
		inti.type = KVM_S390_INT_PFAULT_DONE;
1138
		inti.parm64 = token;
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 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191
		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
1192 1193 1194
	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))
1195 1196 1197 1198 1199 1200
		return 0;

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

1201
static int vcpu_pre_run(struct kvm_vcpu *vcpu)
1202
{
1203
	int rc, cpuflags;
1204

1205 1206 1207 1208 1209 1210 1211
	/*
	 * 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);

1212
	memcpy(&vcpu->arch.sie_block->gg14, &vcpu->run->s.regs.gprs[14], 16);
1213 1214 1215 1216

	if (need_resched())
		schedule();

1217
	if (test_cpu_flag(CIF_MCCK_PENDING))
1218 1219
		s390_handle_mcck();

1220 1221 1222 1223 1224
	if (!kvm_is_ucontrol(vcpu->kvm)) {
		rc = kvm_s390_deliver_pending_interrupts(vcpu);
		if (rc)
			return rc;
	}
C
Carsten Otte 已提交
1225

1226 1227 1228 1229
	rc = kvm_s390_handle_requests(vcpu);
	if (rc)
		return rc;

1230 1231 1232 1233 1234
	if (guestdbg_enabled(vcpu)) {
		kvm_s390_backup_guest_per_regs(vcpu);
		kvm_s390_patch_guest_per_regs(vcpu);
	}

1235
	vcpu->arch.sie_block->icptcode = 0;
1236 1237 1238
	cpuflags = atomic_read(&vcpu->arch.sie_block->cpuflags);
	VCPU_EVENT(vcpu, 6, "entering sie flags %x", cpuflags);
	trace_kvm_s390_sie_enter(vcpu, cpuflags);
1239

1240 1241 1242 1243 1244
	return 0;
}

static int vcpu_post_run(struct kvm_vcpu *vcpu, int exit_reason)
{
1245
	int rc = -1;
1246 1247 1248 1249 1250

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

1251 1252 1253
	if (guestdbg_enabled(vcpu))
		kvm_s390_restore_guest_per_regs(vcpu);

1254
	if (exit_reason >= 0) {
1255
		rc = 0;
1256 1257 1258 1259 1260 1261
	} 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;
1262 1263

	} else if (current->thread.gmap_pfault) {
1264
		trace_kvm_s390_major_guest_pfault(vcpu);
1265
		current->thread.gmap_pfault = 0;
1266
		if (kvm_arch_setup_async_pf(vcpu)) {
1267
			rc = 0;
1268 1269 1270 1271
		} else {
			gpa_t gpa = current->thread.gmap_addr;
			rc = kvm_arch_fault_in_page(vcpu, gpa, 1);
		}
1272 1273 1274
	}

	if (rc == -1) {
1275 1276 1277
		VCPU_EVENT(vcpu, 3, "%s", "fault in sie instruction");
		trace_kvm_s390_sie_fault(vcpu);
		rc = kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
1278
	}
1279

1280
	memcpy(&vcpu->run->s.regs.gprs[14], &vcpu->arch.sie_block->gg14, 16);
1281

1282 1283
	if (rc == 0) {
		if (kvm_is_ucontrol(vcpu->kvm))
1284 1285
			/* Don't exit for host interrupts. */
			rc = vcpu->arch.sie_block->icptcode ? -EOPNOTSUPP : 0;
1286 1287 1288 1289
		else
			rc = kvm_handle_sie_intercept(vcpu);
	}

1290 1291 1292 1293 1294 1295 1296
	return rc;
}

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

1297 1298 1299 1300 1301 1302
	/*
	 * 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);

1303 1304 1305 1306
	do {
		rc = vcpu_pre_run(vcpu);
		if (rc)
			break;
1307

1308
		srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
1309 1310 1311 1312 1313 1314 1315 1316 1317 1318
		/*
		 * 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();
1319
		vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
1320 1321

		rc = vcpu_post_run(vcpu, exit_reason);
1322
	} while (!signal_pending(current) && !guestdbg_exit_pending(vcpu) && !rc);
1323

1324
	srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
1325
	return rc;
1326 1327
}

1328 1329 1330 1331 1332 1333 1334 1335
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);
1336 1337
		/* some control register changes require a tlb flush */
		kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369
	}
	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;
}

1370 1371
int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
{
1372
	int rc;
1373 1374
	sigset_t sigsaved;

1375 1376 1377 1378 1379
	if (guestdbg_exit_pending(vcpu)) {
		kvm_s390_prepare_debug_exit(vcpu);
		return 0;
	}

1380 1381 1382
	if (vcpu->sigset_active)
		sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved);

1383 1384 1385 1386 1387 1388 1389
	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;
	}
1390

1391
	sync_regs(vcpu, kvm_run);
1392

1393
	might_fault();
1394
	rc = __vcpu_run(vcpu);
1395

1396 1397
	if (signal_pending(current) && !rc) {
		kvm_run->exit_reason = KVM_EXIT_INTR;
1398
		rc = -EINTR;
1399
	}
1400

1401 1402 1403 1404 1405
	if (guestdbg_exit_pending(vcpu) && !rc)  {
		kvm_s390_prepare_debug_exit(vcpu);
		rc = 0;
	}

1406
	if (rc == -EOPNOTSUPP) {
1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419
		/* 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;
	}
1420

1421
	store_regs(vcpu, kvm_run);
1422

1423 1424 1425 1426
	if (vcpu->sigset_active)
		sigprocmask(SIG_SETMASK, &sigsaved, NULL);

	vcpu->stat.exit_userspace++;
1427
	return rc;
1428 1429 1430 1431 1432 1433 1434 1435
}

/*
 * 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
 */
1436
int kvm_s390_store_status_unloaded(struct kvm_vcpu *vcpu, unsigned long gpa)
1437
{
1438
	unsigned char archmode = 1;
1439
	unsigned int px;
1440
	u64 clkcomp;
1441
	int rc;
1442

1443 1444
	if (gpa == KVM_S390_STORE_STATUS_NOADDR) {
		if (write_guest_abs(vcpu, 163, &archmode, 1))
1445
			return -EFAULT;
1446 1447 1448
		gpa = SAVE_AREA_BASE;
	} else if (gpa == KVM_S390_STORE_STATUS_PREFIXED) {
		if (write_guest_real(vcpu, 163, &archmode, 1))
1449
			return -EFAULT;
1450 1451 1452 1453 1454 1455 1456 1457
		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);
1458
	px = kvm_s390_get_prefix(vcpu);
1459
	rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, pref_reg),
1460
			      &px, 4);
1461 1462 1463 1464 1465 1466 1467
	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);
1468
	clkcomp = vcpu->arch.sie_block->ckc >> 8;
1469 1470 1471 1472 1473 1474 1475
	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;
1476 1477
}

1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491
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);
}

1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515
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);
}

1516 1517
void kvm_s390_vcpu_start(struct kvm_vcpu *vcpu)
{
1518 1519 1520 1521 1522
	int i, online_vcpus, started_vcpus = 0;

	if (!is_vcpu_stopped(vcpu))
		return;

1523
	trace_kvm_s390_vcpu_start_stop(vcpu->vcpu_id, 1);
1524
	/* Only one cpu at a time may enter/leave the STOPPED state. */
1525
	spin_lock(&vcpu->kvm->arch.start_stop_lock);
1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544
	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);
	}

1545
	atomic_clear_mask(CPUSTAT_STOPPED, &vcpu->arch.sie_block->cpuflags);
1546 1547 1548 1549
	/*
	 * Another VCPU might have used IBS while we were offline.
	 * Let's play safe and flush the VCPU at startup.
	 */
1550
	kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
1551
	spin_unlock(&vcpu->kvm->arch.start_stop_lock);
1552
	return;
1553 1554 1555 1556
}

void kvm_s390_vcpu_stop(struct kvm_vcpu *vcpu)
{
1557 1558 1559 1560 1561 1562
	int i, online_vcpus, started_vcpus = 0;
	struct kvm_vcpu *started_vcpu = NULL;

	if (is_vcpu_stopped(vcpu))
		return;

1563
	trace_kvm_s390_vcpu_start_stop(vcpu->vcpu_id, 0);
1564
	/* Only one cpu at a time may enter/leave the STOPPED state. */
1565
	spin_lock(&vcpu->kvm->arch.start_stop_lock);
1566 1567
	online_vcpus = atomic_read(&vcpu->kvm->online_vcpus);

1568
	/* Need to lock access to action_bits to avoid a SIGP race condition */
1569
	spin_lock(&vcpu->arch.local_int.lock);
1570
	atomic_set_mask(CPUSTAT_STOPPED, &vcpu->arch.sie_block->cpuflags);
1571 1572 1573 1574

	/* 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);
1575
	spin_unlock(&vcpu->arch.local_int.lock);
1576

1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593
	__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);
	}

1594
	spin_unlock(&vcpu->kvm->arch.start_stop_lock);
1595
	return;
1596 1597
}

1598 1599 1600 1601 1602 1603 1604 1605 1606
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) {
1607 1608 1609 1610 1611 1612 1613
	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;
1614 1615 1616 1617 1618 1619 1620
	default:
		r = -EINVAL;
		break;
	}
	return r;
}

1621 1622 1623 1624 1625
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;
1626
	int idx;
1627
	long r;
1628

1629 1630
	switch (ioctl) {
	case KVM_S390_INTERRUPT: {
1631
		struct kvm_s390_interrupt s390int;
1632
		struct kvm_s390_irq s390irq;
1633

1634
		r = -EFAULT;
1635
		if (copy_from_user(&s390int, argp, sizeof(s390int)))
1636
			break;
1637 1638 1639
		if (s390int_to_s390irq(&s390int, &s390irq))
			return -EINVAL;
		r = kvm_s390_inject_vcpu(vcpu, &s390irq);
1640
		break;
1641
	}
1642
	case KVM_S390_STORE_STATUS:
1643
		idx = srcu_read_lock(&vcpu->kvm->srcu);
1644
		r = kvm_s390_vcpu_store_status(vcpu, arg);
1645
		srcu_read_unlock(&vcpu->kvm->srcu, idx);
1646
		break;
1647 1648 1649
	case KVM_S390_SET_INITIAL_PSW: {
		psw_t psw;

1650
		r = -EFAULT;
1651
		if (copy_from_user(&psw, argp, sizeof(psw)))
1652 1653 1654
			break;
		r = kvm_arch_vcpu_ioctl_set_initial_psw(vcpu, psw);
		break;
1655 1656
	}
	case KVM_S390_INITIAL_RESET:
1657 1658
		r = kvm_arch_vcpu_ioctl_initial_reset(vcpu);
		break;
1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670
	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;
	}
1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706
#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
1707
	case KVM_S390_VCPU_FAULT: {
1708
		r = gmap_fault(vcpu->arch.gmap, arg, 0);
1709 1710
		break;
	}
1711 1712 1713 1714 1715 1716 1717 1718 1719
	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;
	}
1720
	default:
1721
		r = -ENOTTY;
1722
	}
1723
	return r;
1724 1725
}

1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738
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;
}

1739 1740
int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
			    unsigned long npages)
1741 1742 1743 1744
{
	return 0;
}

1745
/* Section: memory related */
1746 1747
int kvm_arch_prepare_memory_region(struct kvm *kvm,
				   struct kvm_memory_slot *memslot,
1748 1749
				   struct kvm_userspace_memory_region *mem,
				   enum kvm_mr_change change)
1750
{
1751 1752 1753 1754
	/* 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 */
1755

1756
	if (mem->userspace_addr & 0xffffful)
1757 1758
		return -EINVAL;

1759
	if (mem->memory_size & 0xffffful)
1760 1761
		return -EINVAL;

1762 1763 1764 1765 1766
	return 0;
}

void kvm_arch_commit_memory_region(struct kvm *kvm,
				struct kvm_userspace_memory_region *mem,
1767 1768
				const struct kvm_memory_slot *old,
				enum kvm_mr_change change)
1769
{
1770
	int rc;
1771

1772 1773 1774 1775 1776 1777 1778 1779 1780 1781
	/* 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;
1782 1783 1784 1785

	rc = gmap_map_segment(kvm->arch.gmap, mem->userspace_addr,
		mem->guest_phys_addr, mem->memory_size);
	if (rc)
1786
		printk(KERN_WARNING "kvm-s390: failed to commit memory region\n");
1787
	return;
1788 1789 1790 1791
}

static int __init kvm_s390_init(void)
{
1792
	int ret;
1793
	ret = kvm_init(NULL, sizeof(struct kvm_vcpu), 0, THIS_MODULE);
1794 1795 1796 1797 1798
	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
1799
	 * to hold the maximum amount of facilities. On the other hand, we
1800 1801
	 * only set facilities that are known to work in KVM.
	 */
1802 1803
	vfacilities = (unsigned long *) get_zeroed_page(GFP_KERNEL|GFP_DMA);
	if (!vfacilities) {
1804 1805 1806
		kvm_exit();
		return -ENOMEM;
	}
1807
	memcpy(vfacilities, S390_lowcore.stfle_fac_list, 16);
1808
	vfacilities[0] &= 0xff82fffbf47c2000UL;
1809
	vfacilities[1] &= 0x005c000000000000UL;
1810
	return 0;
1811 1812 1813 1814
}

static void __exit kvm_s390_exit(void)
{
1815
	free_page((unsigned long) vfacilities);
1816 1817 1818 1819 1820
	kvm_exit();
}

module_init(kvm_s390_init);
module_exit(kvm_s390_exit);
1821 1822 1823 1824 1825 1826 1827 1828 1829

/*
 * 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");