kvm-s390.c 77.5 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
#include <linux/init.h>
#include <linux/kvm.h>
#include <linux/kvm_host.h>
#include <linux/module.h>
25
#include <linux/random.h>
26
#include <linux/slab.h>
27
#include <linux/timer.h>
28
#include <linux/vmalloc.h>
29
#include <asm/asm-offsets.h>
30
#include <asm/lowcore.h>
31
#include <asm/etr.h>
32
#include <asm/pgtable.h>
33
#include <asm/gmap.h>
34
#include <asm/nmi.h>
35
#include <asm/switch_to.h>
36
#include <asm/isc.h>
37
#include <asm/sclp.h>
38
#include "kvm-s390.h"
39 40
#include "gaccess.h"

41 42 43 44
#define KMSG_COMPONENT "kvm-s390"
#undef pr_fmt
#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt

45 46
#define CREATE_TRACE_POINTS
#include "trace.h"
47
#include "trace-s390.h"
48

49
#define MEM_OP_MAX_SIZE 65536	/* Maximum transfer size for KVM_S390_MEM_OP */
50 51 52
#define LOCAL_IRQS 32
#define VCPU_IRQS_MAX_BUF (sizeof(struct kvm_s390_irq) * \
			   (KVM_MAX_VCPUS + LOCAL_IRQS))
53

54 55 56 57
#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) },
58
	{ "exit_null", VCPU_STAT(exit_null) },
59 60 61 62
	{ "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) },
63 64 65
	{ "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) },
66
	{ "exit_operation_exception", VCPU_STAT(exit_operation_exception) },
67
	{ "halt_successful_poll", VCPU_STAT(halt_successful_poll) },
68
	{ "halt_attempted_poll", VCPU_STAT(halt_attempted_poll) },
69
	{ "halt_poll_invalid", VCPU_STAT(halt_poll_invalid) },
70
	{ "halt_wakeup", VCPU_STAT(halt_wakeup) },
71
	{ "instruction_lctlg", VCPU_STAT(instruction_lctlg) },
72
	{ "instruction_lctl", VCPU_STAT(instruction_lctl) },
73 74
	{ "instruction_stctl", VCPU_STAT(instruction_stctl) },
	{ "instruction_stctg", VCPU_STAT(instruction_stctg) },
75
	{ "deliver_emergency_signal", VCPU_STAT(deliver_emergency_signal) },
76
	{ "deliver_external_call", VCPU_STAT(deliver_external_call) },
77 78 79 80 81 82 83
	{ "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) },
84
	{ "instruction_pfmf", VCPU_STAT(instruction_pfmf) },
85 86 87 88 89
	{ "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) },
90
	{ "instruction_ipte_interlock", VCPU_STAT(instruction_ipte_interlock) },
91 92
	{ "instruction_stsch", VCPU_STAT(instruction_stsch) },
	{ "instruction_chsc", VCPU_STAT(instruction_chsc) },
93
	{ "instruction_essa", VCPU_STAT(instruction_essa) },
94 95
	{ "instruction_stsi", VCPU_STAT(instruction_stsi) },
	{ "instruction_stfl", VCPU_STAT(instruction_stfl) },
96
	{ "instruction_tprot", VCPU_STAT(instruction_tprot) },
J
Janosch Frank 已提交
97
	{ "instruction_sthyi", VCPU_STAT(instruction_sthyi) },
98
	{ "instruction_sigp_sense", VCPU_STAT(instruction_sigp_sense) },
99
	{ "instruction_sigp_sense_running", VCPU_STAT(instruction_sigp_sense_running) },
100
	{ "instruction_sigp_external_call", VCPU_STAT(instruction_sigp_external_call) },
101
	{ "instruction_sigp_emergency", VCPU_STAT(instruction_sigp_emergency) },
102 103
	{ "instruction_sigp_cond_emergency", VCPU_STAT(instruction_sigp_cond_emergency) },
	{ "instruction_sigp_start", VCPU_STAT(instruction_sigp_start) },
104
	{ "instruction_sigp_stop", VCPU_STAT(instruction_sigp_stop) },
105 106
	{ "instruction_sigp_stop_store_status", VCPU_STAT(instruction_sigp_stop_store_status) },
	{ "instruction_sigp_store_status", VCPU_STAT(instruction_sigp_store_status) },
107
	{ "instruction_sigp_store_adtl_status", VCPU_STAT(instruction_sigp_store_adtl_status) },
108 109 110
	{ "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) },
111 112 113
	{ "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) },
114
	{ "diagnose_10", VCPU_STAT(diagnose_10) },
115
	{ "diagnose_44", VCPU_STAT(diagnose_44) },
116
	{ "diagnose_9c", VCPU_STAT(diagnose_9c) },
117 118 119
	{ "diagnose_258", VCPU_STAT(diagnose_258) },
	{ "diagnose_308", VCPU_STAT(diagnose_308) },
	{ "diagnose_500", VCPU_STAT(diagnose_500) },
120 121 122
	{ NULL }
};

123
/* upper facilities limit for kvm */
124 125 126
unsigned long kvm_s390_fac_list_mask[16] = {
	0xffe6000000000000UL,
	0x005e000000000000UL,
127
};
128

129
unsigned long kvm_s390_fac_list_mask_size(void)
130
{
131 132
	BUILD_BUG_ON(ARRAY_SIZE(kvm_s390_fac_list_mask) > S390_ARCH_FAC_MASK_SIZE_U64);
	return ARRAY_SIZE(kvm_s390_fac_list_mask);
133 134
}

135
static struct gmap_notifier gmap_notifier;
136
debug_info_t *kvm_s390_dbf;
137

138
/* Section: not file related */
139
int kvm_arch_hardware_enable(void)
140 141
{
	/* every s390 is virtualization enabled ;-) */
142
	return 0;
143 144
}

145 146
static void kvm_gmap_notifier(struct gmap *gmap, unsigned long address);

147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164
/*
 * This callback is executed during stop_machine(). All CPUs are therefore
 * temporarily stopped. In order not to change guest behavior, we have to
 * disable preemption whenever we touch the epoch of kvm and the VCPUs,
 * so a CPU won't be stopped while calculating with the epoch.
 */
static int kvm_clock_sync(struct notifier_block *notifier, unsigned long val,
			  void *v)
{
	struct kvm *kvm;
	struct kvm_vcpu *vcpu;
	int i;
	unsigned long long *delta = v;

	list_for_each_entry(kvm, &vm_list, vm_list) {
		kvm->arch.epoch -= *delta;
		kvm_for_each_vcpu(i, vcpu, kvm) {
			vcpu->arch.sie_block->epoch -= *delta;
165 166
			if (vcpu->arch.cputm_enabled)
				vcpu->arch.cputm_start += *delta;
167 168 169 170 171 172 173 174 175
		}
	}
	return NOTIFY_OK;
}

static struct notifier_block kvm_clock_notifier = {
	.notifier_call = kvm_clock_sync,
};

176 177
int kvm_arch_hardware_setup(void)
{
178 179
	gmap_notifier.notifier_call = kvm_gmap_notifier;
	gmap_register_ipte_notifier(&gmap_notifier);
180 181
	atomic_notifier_chain_register(&s390_epoch_delta_notifier,
				       &kvm_clock_notifier);
182 183 184 185 186
	return 0;
}

void kvm_arch_hardware_unsetup(void)
{
187
	gmap_unregister_ipte_notifier(&gmap_notifier);
188 189
	atomic_notifier_chain_unregister(&s390_epoch_delta_notifier,
					 &kvm_clock_notifier);
190 191 192 193
}

int kvm_arch_init(void *opaque)
{
194 195 196 197 198 199 200 201 202
	kvm_s390_dbf = debug_register("kvm-trace", 32, 1, 7 * sizeof(long));
	if (!kvm_s390_dbf)
		return -ENOMEM;

	if (debug_register_view(kvm_s390_dbf, &debug_sprintf_view)) {
		debug_unregister(kvm_s390_dbf);
		return -ENOMEM;
	}

203 204
	/* Register floating interrupt controller interface. */
	return kvm_register_device_ops(&kvm_flic_ops, KVM_DEV_TYPE_FLIC);
205 206
}

207 208 209 210 211
void kvm_arch_exit(void)
{
	debug_unregister(kvm_s390_dbf);
}

212 213 214 215 216 217 218 219 220
/* 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;
}

221
int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
222
{
223 224
	int r;

225
	switch (ext) {
226
	case KVM_CAP_S390_PSW:
227
	case KVM_CAP_S390_GMAP:
228
	case KVM_CAP_SYNC_MMU:
229 230 231
#ifdef CONFIG_KVM_S390_UCONTROL
	case KVM_CAP_S390_UCONTROL:
#endif
232
	case KVM_CAP_ASYNC_PF:
233
	case KVM_CAP_SYNC_REGS:
234
	case KVM_CAP_ONE_REG:
235
	case KVM_CAP_ENABLE_CAP:
236
	case KVM_CAP_S390_CSS_SUPPORT:
C
Cornelia Huck 已提交
237
	case KVM_CAP_IOEVENTFD:
238
	case KVM_CAP_DEVICE_CTRL:
239
	case KVM_CAP_ENABLE_CAP_VM:
240
	case KVM_CAP_S390_IRQCHIP:
241
	case KVM_CAP_VM_ATTRIBUTES:
242
	case KVM_CAP_MP_STATE:
243
	case KVM_CAP_S390_INJECT_IRQ:
244
	case KVM_CAP_S390_USER_SIGP:
245
	case KVM_CAP_S390_USER_STSI:
246
	case KVM_CAP_S390_SKEYS:
247
	case KVM_CAP_S390_IRQ_STATE:
248 249
		r = 1;
		break;
250 251 252
	case KVM_CAP_S390_MEM_OP:
		r = MEM_OP_MAX_SIZE;
		break;
253 254
	case KVM_CAP_NR_VCPUS:
	case KVM_CAP_MAX_VCPUS:
255 256
		r = sclp.has_esca ? KVM_S390_ESCA_CPU_SLOTS
				  : KVM_S390_BSCA_CPU_SLOTS;
257
		break;
258 259 260
	case KVM_CAP_NR_MEMSLOTS:
		r = KVM_USER_MEM_SLOTS;
		break;
261
	case KVM_CAP_S390_COW:
262
		r = MACHINE_HAS_ESOP;
263
		break;
264 265 266
	case KVM_CAP_S390_VECTOR_REGISTERS:
		r = MACHINE_HAS_VX;
		break;
267 268 269
	case KVM_CAP_S390_RI:
		r = test_facility(64);
		break;
270
	default:
271
		r = 0;
272
	}
273
	return r;
274 275
}

276 277 278 279 280 281 282 283 284 285 286 287
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;

	/* 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);

288
		if (test_and_clear_guest_dirty(gmap->mm, address))
289
			mark_page_dirty(kvm, cur_gfn);
290 291
		if (fatal_signal_pending(current))
			return;
292
		cond_resched();
293 294 295
	}
}

296
/* Section: vm related */
297 298
static void sca_del_vcpu(struct kvm_vcpu *vcpu);

299 300 301 302 303 304
/*
 * 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)
{
305 306
	int r;
	unsigned long n;
307
	struct kvm_memslots *slots;
308 309 310 311 312 313 314 315 316
	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;

317 318
	slots = kvm_memslots(kvm);
	memslot = id_to_memslot(slots, log->slot);
319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336
	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;
337 338
}

339 340 341 342 343 344 345 346
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) {
347
	case KVM_CAP_S390_IRQCHIP:
348
		VM_EVENT(kvm, 3, "%s", "ENABLE: CAP_S390_IRQCHIP");
349 350 351
		kvm->arch.use_irqchip = 1;
		r = 0;
		break;
352
	case KVM_CAP_S390_USER_SIGP:
353
		VM_EVENT(kvm, 3, "%s", "ENABLE: CAP_S390_USER_SIGP");
354 355 356
		kvm->arch.user_sigp = 1;
		r = 0;
		break;
357
	case KVM_CAP_S390_VECTOR_REGISTERS:
358 359 360 361
		mutex_lock(&kvm->lock);
		if (atomic_read(&kvm->online_vcpus)) {
			r = -EBUSY;
		} else if (MACHINE_HAS_VX) {
362 363
			set_kvm_facility(kvm->arch.model.fac_mask, 129);
			set_kvm_facility(kvm->arch.model.fac_list, 129);
364 365 366
			r = 0;
		} else
			r = -EINVAL;
367
		mutex_unlock(&kvm->lock);
368 369
		VM_EVENT(kvm, 3, "ENABLE: CAP_S390_VECTOR_REGISTERS %s",
			 r ? "(not available)" : "(success)");
370
		break;
371 372 373 374 375 376
	case KVM_CAP_S390_RI:
		r = -EINVAL;
		mutex_lock(&kvm->lock);
		if (atomic_read(&kvm->online_vcpus)) {
			r = -EBUSY;
		} else if (test_facility(64)) {
377 378
			set_kvm_facility(kvm->arch.model.fac_mask, 64);
			set_kvm_facility(kvm->arch.model.fac_list, 64);
379 380 381 382 383 384
			r = 0;
		}
		mutex_unlock(&kvm->lock);
		VM_EVENT(kvm, 3, "ENABLE: CAP_S390_RI %s",
			 r ? "(not available)" : "(success)");
		break;
385
	case KVM_CAP_S390_USER_STSI:
386
		VM_EVENT(kvm, 3, "%s", "ENABLE: CAP_S390_USER_STSI");
387 388 389
		kvm->arch.user_stsi = 1;
		r = 0;
		break;
390 391 392 393 394 395 396
	default:
		r = -EINVAL;
		break;
	}
	return r;
}

397 398 399 400 401 402 403
static int kvm_s390_get_mem_control(struct kvm *kvm, struct kvm_device_attr *attr)
{
	int ret;

	switch (attr->attr) {
	case KVM_S390_VM_MEM_LIMIT_SIZE:
		ret = 0;
404
		VM_EVENT(kvm, 3, "QUERY: max guest memory: %lu bytes",
405 406
			 kvm->arch.mem_limit);
		if (put_user(kvm->arch.mem_limit, (u64 __user *)attr->addr))
407 408 409 410 411 412 413 414 415 416
			ret = -EFAULT;
		break;
	default:
		ret = -ENXIO;
		break;
	}
	return ret;
}

static int kvm_s390_set_mem_control(struct kvm *kvm, struct kvm_device_attr *attr)
417 418 419 420 421
{
	int ret;
	unsigned int idx;
	switch (attr->attr) {
	case KVM_S390_VM_MEM_ENABLE_CMMA:
422 423 424 425 426
		/* enable CMMA only for z10 and later (EDAT_1) */
		ret = -EINVAL;
		if (!MACHINE_IS_LPAR || !MACHINE_HAS_EDAT1)
			break;

427
		ret = -EBUSY;
428
		VM_EVENT(kvm, 3, "%s", "ENABLE: CMMA support");
429 430 431 432 433 434 435 436
		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:
437 438 439 440
		ret = -EINVAL;
		if (!kvm->arch.use_cmma)
			break;

441
		VM_EVENT(kvm, 3, "%s", "RESET: CMMA states");
442 443
		mutex_lock(&kvm->lock);
		idx = srcu_read_lock(&kvm->srcu);
444
		s390_reset_cmma(kvm->arch.gmap->mm);
445 446 447 448
		srcu_read_unlock(&kvm->srcu, idx);
		mutex_unlock(&kvm->lock);
		ret = 0;
		break;
449 450 451 452 453 454 455 456 457
	case KVM_S390_VM_MEM_LIMIT_SIZE: {
		unsigned long new_limit;

		if (kvm_is_ucontrol(kvm))
			return -EINVAL;

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

458 459
		if (kvm->arch.mem_limit != KVM_S390_NO_MEM_LIMIT &&
		    new_limit > kvm->arch.mem_limit)
460 461
			return -E2BIG;

462 463 464 465 466 467 468
		if (!new_limit)
			return -EINVAL;

		/* gmap_alloc takes last usable address */
		if (new_limit != KVM_S390_NO_MEM_LIMIT)
			new_limit -= 1;

469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484
		ret = -EBUSY;
		mutex_lock(&kvm->lock);
		if (atomic_read(&kvm->online_vcpus) == 0) {
			/* gmap_alloc will round the limit up */
			struct gmap *new = gmap_alloc(current->mm, new_limit);

			if (!new) {
				ret = -ENOMEM;
			} else {
				gmap_free(kvm->arch.gmap);
				new->private = kvm;
				kvm->arch.gmap = new;
				ret = 0;
			}
		}
		mutex_unlock(&kvm->lock);
485 486 487
		VM_EVENT(kvm, 3, "SET: max guest address: %lu", new_limit);
		VM_EVENT(kvm, 3, "New guest asce: 0x%pK",
			 (void *) kvm->arch.gmap->asce);
488 489
		break;
	}
490 491 492 493 494 495 496
	default:
		ret = -ENXIO;
		break;
	}
	return ret;
}

497 498 499 500 501 502 503
static void kvm_s390_vcpu_crypto_setup(struct kvm_vcpu *vcpu);

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

504
	if (!test_kvm_facility(kvm, 76))
505 506 507 508 509 510 511 512 513
		return -EINVAL;

	mutex_lock(&kvm->lock);
	switch (attr->attr) {
	case KVM_S390_VM_CRYPTO_ENABLE_AES_KW:
		get_random_bytes(
			kvm->arch.crypto.crycb->aes_wrapping_key_mask,
			sizeof(kvm->arch.crypto.crycb->aes_wrapping_key_mask));
		kvm->arch.crypto.aes_kw = 1;
514
		VM_EVENT(kvm, 3, "%s", "ENABLE: AES keywrapping support");
515 516 517 518 519 520
		break;
	case KVM_S390_VM_CRYPTO_ENABLE_DEA_KW:
		get_random_bytes(
			kvm->arch.crypto.crycb->dea_wrapping_key_mask,
			sizeof(kvm->arch.crypto.crycb->dea_wrapping_key_mask));
		kvm->arch.crypto.dea_kw = 1;
521
		VM_EVENT(kvm, 3, "%s", "ENABLE: DEA keywrapping support");
522 523 524 525 526
		break;
	case KVM_S390_VM_CRYPTO_DISABLE_AES_KW:
		kvm->arch.crypto.aes_kw = 0;
		memset(kvm->arch.crypto.crycb->aes_wrapping_key_mask, 0,
			sizeof(kvm->arch.crypto.crycb->aes_wrapping_key_mask));
527
		VM_EVENT(kvm, 3, "%s", "DISABLE: AES keywrapping support");
528 529 530 531 532
		break;
	case KVM_S390_VM_CRYPTO_DISABLE_DEA_KW:
		kvm->arch.crypto.dea_kw = 0;
		memset(kvm->arch.crypto.crycb->dea_wrapping_key_mask, 0,
			sizeof(kvm->arch.crypto.crycb->dea_wrapping_key_mask));
533
		VM_EVENT(kvm, 3, "%s", "DISABLE: DEA keywrapping support");
534 535 536 537 538 539 540 541 542 543 544 545 546 547
		break;
	default:
		mutex_unlock(&kvm->lock);
		return -ENXIO;
	}

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

548 549 550 551 552 553 554 555 556 557
static int kvm_s390_set_tod_high(struct kvm *kvm, struct kvm_device_attr *attr)
{
	u8 gtod_high;

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

	if (gtod_high != 0)
		return -EINVAL;
558
	VM_EVENT(kvm, 3, "SET: TOD extension: 0x%x", gtod_high);
559 560 561 562 563 564

	return 0;
}

static int kvm_s390_set_tod_low(struct kvm *kvm, struct kvm_device_attr *attr)
{
565
	u64 gtod;
566 567 568 569

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

570
	kvm_s390_set_tod_clock(kvm, gtod);
571
	VM_EVENT(kvm, 3, "SET: TOD base: 0x%llx", gtod);
572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602
	return 0;
}

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

	if (attr->flags)
		return -EINVAL;

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

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

	if (copy_to_user((void __user *)attr->addr, &gtod_high,
					 sizeof(gtod_high)))
		return -EFAULT;
603
	VM_EVENT(kvm, 3, "QUERY: TOD extension: 0x%x", gtod_high);
604 605 606 607 608 609

	return 0;
}

static int kvm_s390_get_tod_low(struct kvm *kvm, struct kvm_device_attr *attr)
{
610
	u64 gtod;
611

612
	gtod = kvm_s390_get_tod_clock_fast(kvm);
613 614
	if (copy_to_user((void __user *)attr->addr, &gtod, sizeof(gtod)))
		return -EFAULT;
615
	VM_EVENT(kvm, 3, "QUERY: TOD base: 0x%llx", gtod);
616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640

	return 0;
}

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

	if (attr->flags)
		return -EINVAL;

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

641 642 643
static int kvm_s390_set_processor(struct kvm *kvm, struct kvm_device_attr *attr)
{
	struct kvm_s390_vm_cpu_processor *proc;
644
	u16 lowest_ibc, unblocked_ibc;
645 646 647 648 649 650 651 652 653 654 655 656 657 658
	int ret = 0;

	mutex_lock(&kvm->lock);
	if (atomic_read(&kvm->online_vcpus)) {
		ret = -EBUSY;
		goto out;
	}
	proc = kzalloc(sizeof(*proc), GFP_KERNEL);
	if (!proc) {
		ret = -ENOMEM;
		goto out;
	}
	if (!copy_from_user(proc, (void __user *)attr->addr,
			    sizeof(*proc))) {
659
		kvm->arch.model.cpuid = proc->cpuid;
660 661 662 663 664 665 666 667 668 669
		lowest_ibc = sclp.ibc >> 16 & 0xfff;
		unblocked_ibc = sclp.ibc & 0xfff;
		if (lowest_ibc) {
			if (proc->ibc > unblocked_ibc)
				kvm->arch.model.ibc = unblocked_ibc;
			else if (proc->ibc < lowest_ibc)
				kvm->arch.model.ibc = lowest_ibc;
			else
				kvm->arch.model.ibc = proc->ibc;
		}
670
		memcpy(kvm->arch.model.fac_list, proc->fac_list,
671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701
		       S390_ARCH_FAC_LIST_SIZE_BYTE);
	} else
		ret = -EFAULT;
	kfree(proc);
out:
	mutex_unlock(&kvm->lock);
	return ret;
}

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

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

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

	proc = kzalloc(sizeof(*proc), GFP_KERNEL);
	if (!proc) {
		ret = -ENOMEM;
		goto out;
	}
702
	proc->cpuid = kvm->arch.model.cpuid;
703
	proc->ibc = kvm->arch.model.ibc;
704 705
	memcpy(&proc->fac_list, kvm->arch.model.fac_list,
	       S390_ARCH_FAC_LIST_SIZE_BYTE);
706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723
	if (copy_to_user((void __user *)attr->addr, proc, sizeof(*proc)))
		ret = -EFAULT;
	kfree(proc);
out:
	return ret;
}

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

	mach = kzalloc(sizeof(*mach), GFP_KERNEL);
	if (!mach) {
		ret = -ENOMEM;
		goto out;
	}
	get_cpu_id((struct cpuid *) &mach->cpuid);
724
	mach->ibc = sclp.ibc;
725
	memcpy(&mach->fac_mask, kvm->arch.model.fac_mask,
726
	       S390_ARCH_FAC_LIST_SIZE_BYTE);
727
	memcpy((unsigned long *)&mach->fac_list, S390_lowcore.stfle_fac_list,
728
	       S390_ARCH_FAC_LIST_SIZE_BYTE);
729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750
	if (copy_to_user((void __user *)attr->addr, mach, sizeof(*mach)))
		ret = -EFAULT;
	kfree(mach);
out:
	return ret;
}

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

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

751 752 753 754 755
static int kvm_s390_vm_set_attr(struct kvm *kvm, struct kvm_device_attr *attr)
{
	int ret;

	switch (attr->group) {
756
	case KVM_S390_VM_MEM_CTRL:
757
		ret = kvm_s390_set_mem_control(kvm, attr);
758
		break;
759 760 761
	case KVM_S390_VM_TOD:
		ret = kvm_s390_set_tod(kvm, attr);
		break;
762 763 764
	case KVM_S390_VM_CPU_MODEL:
		ret = kvm_s390_set_cpu_model(kvm, attr);
		break;
765 766 767
	case KVM_S390_VM_CRYPTO:
		ret = kvm_s390_vm_set_crypto(kvm, attr);
		break;
768 769 770 771 772 773 774 775 776 777
	default:
		ret = -ENXIO;
		break;
	}

	return ret;
}

static int kvm_s390_vm_get_attr(struct kvm *kvm, struct kvm_device_attr *attr)
{
778 779 780 781 782 783
	int ret;

	switch (attr->group) {
	case KVM_S390_VM_MEM_CTRL:
		ret = kvm_s390_get_mem_control(kvm, attr);
		break;
784 785 786
	case KVM_S390_VM_TOD:
		ret = kvm_s390_get_tod(kvm, attr);
		break;
787 788 789
	case KVM_S390_VM_CPU_MODEL:
		ret = kvm_s390_get_cpu_model(kvm, attr);
		break;
790 791 792 793 794 795
	default:
		ret = -ENXIO;
		break;
	}

	return ret;
796 797 798 799 800 801 802
}

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

	switch (attr->group) {
803 804 805 806
	case KVM_S390_VM_MEM_CTRL:
		switch (attr->attr) {
		case KVM_S390_VM_MEM_ENABLE_CMMA:
		case KVM_S390_VM_MEM_CLR_CMMA:
807
		case KVM_S390_VM_MEM_LIMIT_SIZE:
808 809 810 811 812 813 814
			ret = 0;
			break;
		default:
			ret = -ENXIO;
			break;
		}
		break;
815 816 817 818 819 820 821 822 823 824 825
	case KVM_S390_VM_TOD:
		switch (attr->attr) {
		case KVM_S390_VM_TOD_LOW:
		case KVM_S390_VM_TOD_HIGH:
			ret = 0;
			break;
		default:
			ret = -ENXIO;
			break;
		}
		break;
826 827 828 829 830 831 832 833 834 835 836
	case KVM_S390_VM_CPU_MODEL:
		switch (attr->attr) {
		case KVM_S390_VM_CPU_PROCESSOR:
		case KVM_S390_VM_CPU_MACHINE:
			ret = 0;
			break;
		default:
			ret = -ENXIO;
			break;
		}
		break;
837 838 839 840 841 842 843 844 845 846 847 848 849
	case KVM_S390_VM_CRYPTO:
		switch (attr->attr) {
		case KVM_S390_VM_CRYPTO_ENABLE_AES_KW:
		case KVM_S390_VM_CRYPTO_ENABLE_DEA_KW:
		case KVM_S390_VM_CRYPTO_DISABLE_AES_KW:
		case KVM_S390_VM_CRYPTO_DISABLE_DEA_KW:
			ret = 0;
			break;
		default:
			ret = -ENXIO;
			break;
		}
		break;
850 851 852 853 854 855 856 857
	default:
		ret = -ENXIO;
		break;
	}

	return ret;
}

858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934
static long kvm_s390_get_skeys(struct kvm *kvm, struct kvm_s390_skeys *args)
{
	uint8_t *keys;
	uint64_t hva;
	unsigned long curkey;
	int i, r = 0;

	if (args->flags != 0)
		return -EINVAL;

	/* Is this guest using storage keys? */
	if (!mm_use_skey(current->mm))
		return KVM_S390_GET_SKEYS_NONE;

	/* Enforce sane limit on memory allocation */
	if (args->count < 1 || args->count > KVM_S390_SKEYS_MAX)
		return -EINVAL;

	keys = kmalloc_array(args->count, sizeof(uint8_t),
			     GFP_KERNEL | __GFP_NOWARN);
	if (!keys)
		keys = vmalloc(sizeof(uint8_t) * args->count);
	if (!keys)
		return -ENOMEM;

	for (i = 0; i < args->count; i++) {
		hva = gfn_to_hva(kvm, args->start_gfn + i);
		if (kvm_is_error_hva(hva)) {
			r = -EFAULT;
			goto out;
		}

		curkey = get_guest_storage_key(current->mm, hva);
		if (IS_ERR_VALUE(curkey)) {
			r = curkey;
			goto out;
		}
		keys[i] = curkey;
	}

	r = copy_to_user((uint8_t __user *)args->skeydata_addr, keys,
			 sizeof(uint8_t) * args->count);
	if (r)
		r = -EFAULT;
out:
	kvfree(keys);
	return r;
}

static long kvm_s390_set_skeys(struct kvm *kvm, struct kvm_s390_skeys *args)
{
	uint8_t *keys;
	uint64_t hva;
	int i, r = 0;

	if (args->flags != 0)
		return -EINVAL;

	/* Enforce sane limit on memory allocation */
	if (args->count < 1 || args->count > KVM_S390_SKEYS_MAX)
		return -EINVAL;

	keys = kmalloc_array(args->count, sizeof(uint8_t),
			     GFP_KERNEL | __GFP_NOWARN);
	if (!keys)
		keys = vmalloc(sizeof(uint8_t) * args->count);
	if (!keys)
		return -ENOMEM;

	r = copy_from_user(keys, (uint8_t __user *)args->skeydata_addr,
			   sizeof(uint8_t) * args->count);
	if (r) {
		r = -EFAULT;
		goto out;
	}

	/* Enable storage key handling for the guest */
935 936 937
	r = s390_enable_skey();
	if (r)
		goto out;
938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961

	for (i = 0; i < args->count; i++) {
		hva = gfn_to_hva(kvm, args->start_gfn + i);
		if (kvm_is_error_hva(hva)) {
			r = -EFAULT;
			goto out;
		}

		/* Lowest order bit is reserved */
		if (keys[i] & 0x01) {
			r = -EINVAL;
			goto out;
		}

		r = set_guest_storage_key(current->mm, hva,
					  (unsigned long)keys[i], 0);
		if (r)
			goto out;
	}
out:
	kvfree(keys);
	return r;
}

962 963 964 965 966
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;
967
	struct kvm_device_attr attr;
968 969 970
	int r;

	switch (ioctl) {
971 972 973 974 975 976 977 978 979
	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;
	}
980 981 982 983 984 985 986 987
	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;
	}
988 989 990 991 992 993 994
	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));
995
			r = kvm_set_irq_routing(kvm, &routing, 0, 0);
996 997 998
		}
		break;
	}
999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019
	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;
	}
1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039
	case KVM_S390_GET_SKEYS: {
		struct kvm_s390_skeys args;

		r = -EFAULT;
		if (copy_from_user(&args, argp,
				   sizeof(struct kvm_s390_skeys)))
			break;
		r = kvm_s390_get_skeys(kvm, &args);
		break;
	}
	case KVM_S390_SET_SKEYS: {
		struct kvm_s390_skeys args;

		r = -EFAULT;
		if (copy_from_user(&args, argp,
				   sizeof(struct kvm_s390_skeys)))
			break;
		r = kvm_s390_set_skeys(kvm, &args);
		break;
	}
1040
	default:
1041
		r = -ENOTTY;
1042 1043 1044 1045 1046
	}

	return r;
}

1047 1048 1049
static int kvm_s390_query_ap_config(u8 *config)
{
	u32 fcn_code = 0x04000000UL;
1050
	u32 cc = 0;
1051

1052
	memset(config, 0, 128);
1053 1054 1055 1056
	asm volatile(
		"lgr 0,%1\n"
		"lgr 2,%2\n"
		".long 0xb2af0000\n"		/* PQAP(QCI) */
1057
		"0: ipm %0\n"
1058
		"srl %0,28\n"
1059 1060 1061
		"1:\n"
		EX_TABLE(0b, 1b)
		: "+r" (cc)
1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073
		: "r" (fcn_code), "r" (config)
		: "cc", "0", "2", "memory"
	);

	return cc;
}

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

1074
	if (test_facility(12)) {
1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095
		cc = kvm_s390_query_ap_config(config);

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

	return 0;
}

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

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

1096
static u64 kvm_s390_get_initial_cpuid(void)
1097
{
1098 1099 1100 1101 1102
	struct cpuid cpuid;

	get_cpu_id(&cpuid);
	cpuid.version = 0xff;
	return *((u64 *) &cpuid);
1103 1104
}

1105
static void kvm_s390_crypto_init(struct kvm *kvm)
1106
{
1107
	if (!test_kvm_facility(kvm, 76))
1108
		return;
1109

1110
	kvm->arch.crypto.crycb = &kvm->arch.sie_page2->crycb;
1111
	kvm_s390_set_crycb_format(kvm);
1112

1113 1114 1115 1116 1117 1118 1119
	/* Enable AES/DEA protected key functions by default */
	kvm->arch.crypto.aes_kw = 1;
	kvm->arch.crypto.dea_kw = 1;
	get_random_bytes(kvm->arch.crypto.crycb->aes_wrapping_key_mask,
			 sizeof(kvm->arch.crypto.crycb->aes_wrapping_key_mask));
	get_random_bytes(kvm->arch.crypto.crycb->dea_wrapping_key_mask,
			 sizeof(kvm->arch.crypto.crycb->dea_wrapping_key_mask));
1120 1121
}

1122 1123 1124
static void sca_dispose(struct kvm *kvm)
{
	if (kvm->arch.use_esca)
1125
		free_pages_exact(kvm->arch.sca, sizeof(struct esca_block));
1126 1127 1128 1129 1130
	else
		free_page((unsigned long)(kvm->arch.sca));
	kvm->arch.sca = NULL;
}

1131
int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
1132
{
1133
	int i, rc;
1134
	char debug_name[16];
1135
	static unsigned long sca_offset;
1136

1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147
	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

1148 1149
	rc = s390_enable_sie();
	if (rc)
1150
		goto out_err;
1151

1152 1153
	rc = -ENOMEM;

1154
	kvm->arch.use_esca = 0; /* start with basic SCA */
1155
	rwlock_init(&kvm->arch.sca_lock);
1156
	kvm->arch.sca = (struct bsca_block *) get_zeroed_page(GFP_KERNEL);
1157
	if (!kvm->arch.sca)
1158
		goto out_err;
1159
	spin_lock(&kvm_lock);
1160
	sca_offset += 16;
1161
	if (sca_offset + sizeof(struct bsca_block) > PAGE_SIZE)
1162
		sca_offset = 0;
1163 1164
	kvm->arch.sca = (struct bsca_block *)
			((char *) kvm->arch.sca + sca_offset);
1165
	spin_unlock(&kvm_lock);
1166 1167 1168

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

1169
	kvm->arch.dbf = debug_register(debug_name, 32, 1, 7 * sizeof(long));
1170
	if (!kvm->arch.dbf)
1171
		goto out_err;
1172

1173 1174 1175
	kvm->arch.sie_page2 =
	     (struct sie_page2 *) get_zeroed_page(GFP_KERNEL | GFP_DMA);
	if (!kvm->arch.sie_page2)
1176
		goto out_err;
1177

1178
	/* Populate the facility mask initially. */
1179
	memcpy(kvm->arch.model.fac_mask, S390_lowcore.stfle_fac_list,
1180
	       S390_ARCH_FAC_LIST_SIZE_BYTE);
1181 1182
	for (i = 0; i < S390_ARCH_FAC_LIST_SIZE_U64; i++) {
		if (i < kvm_s390_fac_list_mask_size())
1183
			kvm->arch.model.fac_mask[i] &= kvm_s390_fac_list_mask[i];
1184
		else
1185
			kvm->arch.model.fac_mask[i] = 0UL;
1186 1187
	}

1188
	/* Populate the facility list initially. */
1189 1190
	kvm->arch.model.fac_list = kvm->arch.sie_page2->fac_list;
	memcpy(kvm->arch.model.fac_list, kvm->arch.model.fac_mask,
1191 1192
	       S390_ARCH_FAC_LIST_SIZE_BYTE);

J
Janosch Frank 已提交
1193 1194 1195
	set_kvm_facility(kvm->arch.model.fac_mask, 74);
	set_kvm_facility(kvm->arch.model.fac_list, 74);

1196
	kvm->arch.model.cpuid = kvm_s390_get_initial_cpuid();
1197
	kvm->arch.model.ibc = sclp.ibc & 0x0fff;
1198

1199
	kvm_s390_crypto_init(kvm);
1200

1201
	spin_lock_init(&kvm->arch.float_int.lock);
1202 1203
	for (i = 0; i < FIRQ_LIST_COUNT; i++)
		INIT_LIST_HEAD(&kvm->arch.float_int.lists[i]);
1204
	init_waitqueue_head(&kvm->arch.ipte_wq);
1205
	mutex_init(&kvm->arch.ipte_mutex);
1206

1207
	debug_register_view(kvm->arch.dbf, &debug_sprintf_view);
1208
	VM_EVENT(kvm, 3, "vm created with type %lu", type);
1209

1210 1211
	if (type & KVM_VM_S390_UCONTROL) {
		kvm->arch.gmap = NULL;
1212
		kvm->arch.mem_limit = KVM_S390_NO_MEM_LIMIT;
1213
	} else {
1214 1215 1216 1217 1218
		if (sclp.hamax == U64_MAX)
			kvm->arch.mem_limit = TASK_MAX_SIZE;
		else
			kvm->arch.mem_limit = min_t(unsigned long, TASK_MAX_SIZE,
						    sclp.hamax + 1);
1219
		kvm->arch.gmap = gmap_alloc(current->mm, kvm->arch.mem_limit - 1);
1220
		if (!kvm->arch.gmap)
1221
			goto out_err;
1222
		kvm->arch.gmap->private = kvm;
1223
		kvm->arch.gmap->pfault_enabled = 0;
1224
	}
1225 1226

	kvm->arch.css_support = 0;
1227
	kvm->arch.use_irqchip = 0;
1228
	kvm->arch.epoch = 0;
1229

1230
	spin_lock_init(&kvm->arch.start_stop_lock);
1231
	KVM_EVENT(3, "vm 0x%pK created by pid %u", kvm, current->pid);
1232

1233
	return 0;
1234
out_err:
1235
	free_page((unsigned long)kvm->arch.sie_page2);
1236
	debug_unregister(kvm->arch.dbf);
1237
	sca_dispose(kvm);
1238
	KVM_EVENT(3, "creation of vm failed: %d", rc);
1239
	return rc;
1240 1241
}

1242 1243 1244
void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
{
	VCPU_EVENT(vcpu, 3, "%s", "free cpu");
1245
	trace_kvm_s390_destroy_vcpu(vcpu->vcpu_id);
1246
	kvm_s390_clear_local_irqs(vcpu);
1247
	kvm_clear_async_pf_completion_queue(vcpu);
1248
	if (!kvm_is_ucontrol(vcpu->kvm))
1249
		sca_del_vcpu(vcpu);
1250 1251 1252 1253

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

1254
	if (vcpu->kvm->arch.use_cmma)
1255
		kvm_s390_vcpu_unsetup_cmma(vcpu);
1256
	free_page((unsigned long)(vcpu->arch.sie_block));
1257

1258
	kvm_vcpu_uninit(vcpu);
1259
	kmem_cache_free(kvm_vcpu_cache, vcpu);
1260 1261 1262 1263 1264
}

static void kvm_free_vcpus(struct kvm *kvm)
{
	unsigned int i;
1265
	struct kvm_vcpu *vcpu;
1266

1267 1268 1269 1270 1271 1272 1273 1274 1275
	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);
1276 1277
}

1278 1279
void kvm_arch_destroy_vm(struct kvm *kvm)
{
1280
	kvm_free_vcpus(kvm);
1281
	sca_dispose(kvm);
1282
	debug_unregister(kvm->arch.dbf);
1283
	free_page((unsigned long)kvm->arch.sie_page2);
1284 1285
	if (!kvm_is_ucontrol(kvm))
		gmap_free(kvm->arch.gmap);
1286
	kvm_s390_destroy_adapters(kvm);
1287
	kvm_s390_clear_float_irqs(kvm);
1288
	KVM_EVENT(3, "vm 0x%pK destroyed", kvm);
1289 1290 1291
}

/* Section: vcpu related */
1292 1293 1294 1295 1296 1297 1298 1299 1300 1301
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;
}

1302 1303
static void sca_del_vcpu(struct kvm_vcpu *vcpu)
{
1304
	read_lock(&vcpu->kvm->arch.sca_lock);
1305 1306
	if (vcpu->kvm->arch.use_esca) {
		struct esca_block *sca = vcpu->kvm->arch.sca;
1307

1308
		clear_bit_inv(vcpu->vcpu_id, (unsigned long *) sca->mcn);
1309
		sca->cpu[vcpu->vcpu_id].sda = 0;
1310 1311 1312 1313
	} else {
		struct bsca_block *sca = vcpu->kvm->arch.sca;

		clear_bit_inv(vcpu->vcpu_id, (unsigned long *) &sca->mcn);
1314
		sca->cpu[vcpu->vcpu_id].sda = 0;
1315
	}
1316
	read_unlock(&vcpu->kvm->arch.sca_lock);
1317 1318
}

1319
static void sca_add_vcpu(struct kvm_vcpu *vcpu)
1320
{
1321 1322 1323
	read_lock(&vcpu->kvm->arch.sca_lock);
	if (vcpu->kvm->arch.use_esca) {
		struct esca_block *sca = vcpu->kvm->arch.sca;
1324

1325
		sca->cpu[vcpu->vcpu_id].sda = (__u64) vcpu->arch.sie_block;
1326 1327
		vcpu->arch.sie_block->scaoh = (__u32)(((__u64)sca) >> 32);
		vcpu->arch.sie_block->scaol = (__u32)(__u64)sca & ~0x3fU;
1328
		vcpu->arch.sie_block->ecb2 |= 0x04U;
1329
		set_bit_inv(vcpu->vcpu_id, (unsigned long *) sca->mcn);
1330
	} else {
1331
		struct bsca_block *sca = vcpu->kvm->arch.sca;
1332

1333
		sca->cpu[vcpu->vcpu_id].sda = (__u64) vcpu->arch.sie_block;
1334 1335
		vcpu->arch.sie_block->scaoh = (__u32)(((__u64)sca) >> 32);
		vcpu->arch.sie_block->scaol = (__u32)(__u64)sca;
1336
		set_bit_inv(vcpu->vcpu_id, (unsigned long *) &sca->mcn);
1337
	}
1338
	read_unlock(&vcpu->kvm->arch.sca_lock);
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 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391
}

/* Basic SCA to Extended SCA data copy routines */
static inline void sca_copy_entry(struct esca_entry *d, struct bsca_entry *s)
{
	d->sda = s->sda;
	d->sigp_ctrl.c = s->sigp_ctrl.c;
	d->sigp_ctrl.scn = s->sigp_ctrl.scn;
}

static void sca_copy_b_to_e(struct esca_block *d, struct bsca_block *s)
{
	int i;

	d->ipte_control = s->ipte_control;
	d->mcn[0] = s->mcn;
	for (i = 0; i < KVM_S390_BSCA_CPU_SLOTS; i++)
		sca_copy_entry(&d->cpu[i], &s->cpu[i]);
}

static int sca_switch_to_extended(struct kvm *kvm)
{
	struct bsca_block *old_sca = kvm->arch.sca;
	struct esca_block *new_sca;
	struct kvm_vcpu *vcpu;
	unsigned int vcpu_idx;
	u32 scaol, scaoh;

	new_sca = alloc_pages_exact(sizeof(*new_sca), GFP_KERNEL|__GFP_ZERO);
	if (!new_sca)
		return -ENOMEM;

	scaoh = (u32)((u64)(new_sca) >> 32);
	scaol = (u32)(u64)(new_sca) & ~0x3fU;

	kvm_s390_vcpu_block_all(kvm);
	write_lock(&kvm->arch.sca_lock);

	sca_copy_b_to_e(new_sca, old_sca);

	kvm_for_each_vcpu(vcpu_idx, vcpu, kvm) {
		vcpu->arch.sie_block->scaoh = scaoh;
		vcpu->arch.sie_block->scaol = scaol;
		vcpu->arch.sie_block->ecb2 |= 0x04U;
	}
	kvm->arch.sca = new_sca;
	kvm->arch.use_esca = 1;

	write_unlock(&kvm->arch.sca_lock);
	kvm_s390_vcpu_unblock_all(kvm);

	free_page((unsigned long)old_sca);

1392 1393
	VM_EVENT(kvm, 2, "Switched to ESCA (0x%pK -> 0x%pK)",
		 old_sca, kvm->arch.sca);
1394
	return 0;
1395 1396 1397 1398
}

static int sca_can_add_vcpu(struct kvm *kvm, unsigned int id)
{
1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410
	int rc;

	if (id < KVM_S390_BSCA_CPU_SLOTS)
		return true;
	if (!sclp.has_esca)
		return false;

	mutex_lock(&kvm->lock);
	rc = kvm->arch.use_esca ? 0 : sca_switch_to_extended(kvm);
	mutex_unlock(&kvm->lock);

	return rc == 0 && id < KVM_S390_ESCA_CPU_SLOTS;
1411 1412
}

1413 1414
int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
{
1415 1416
	vcpu->arch.pfault_token = KVM_S390_PFAULT_TOKEN_INVALID;
	kvm_clear_async_pf_completion_queue(vcpu);
1417 1418
	vcpu->run->kvm_valid_regs = KVM_SYNC_PREFIX |
				    KVM_SYNC_GPRS |
1419
				    KVM_SYNC_ACRS |
1420 1421 1422
				    KVM_SYNC_CRS |
				    KVM_SYNC_ARCH0 |
				    KVM_SYNC_PFAULT;
1423 1424
	if (test_kvm_facility(vcpu->kvm, 64))
		vcpu->run->kvm_valid_regs |= KVM_SYNC_RICCB;
1425 1426 1427 1428
	/* fprs can be synchronized via vrs, even if the guest has no vx. With
	 * MACHINE_HAS_VX, (load|store)_fpu_regs() will work with vrs format.
	 */
	if (MACHINE_HAS_VX)
1429
		vcpu->run->kvm_valid_regs |= KVM_SYNC_VRS;
1430 1431
	else
		vcpu->run->kvm_valid_regs |= KVM_SYNC_FPRS;
1432 1433 1434 1435

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

1436 1437 1438
	return 0;
}

1439 1440 1441 1442
/* needs disabled preemption to protect from TOD sync and vcpu_load/put */
static void __start_cpu_timer_accounting(struct kvm_vcpu *vcpu)
{
	WARN_ON_ONCE(vcpu->arch.cputm_start != 0);
1443
	raw_write_seqcount_begin(&vcpu->arch.cputm_seqcount);
1444
	vcpu->arch.cputm_start = get_tod_clock_fast();
1445
	raw_write_seqcount_end(&vcpu->arch.cputm_seqcount);
1446 1447 1448 1449 1450 1451
}

/* needs disabled preemption to protect from TOD sync and vcpu_load/put */
static void __stop_cpu_timer_accounting(struct kvm_vcpu *vcpu)
{
	WARN_ON_ONCE(vcpu->arch.cputm_start == 0);
1452
	raw_write_seqcount_begin(&vcpu->arch.cputm_seqcount);
1453 1454
	vcpu->arch.sie_block->cputm -= get_tod_clock_fast() - vcpu->arch.cputm_start;
	vcpu->arch.cputm_start = 0;
1455
	raw_write_seqcount_end(&vcpu->arch.cputm_seqcount);
1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487
}

/* needs disabled preemption to protect from TOD sync and vcpu_load/put */
static void __enable_cpu_timer_accounting(struct kvm_vcpu *vcpu)
{
	WARN_ON_ONCE(vcpu->arch.cputm_enabled);
	vcpu->arch.cputm_enabled = true;
	__start_cpu_timer_accounting(vcpu);
}

/* needs disabled preemption to protect from TOD sync and vcpu_load/put */
static void __disable_cpu_timer_accounting(struct kvm_vcpu *vcpu)
{
	WARN_ON_ONCE(!vcpu->arch.cputm_enabled);
	__stop_cpu_timer_accounting(vcpu);
	vcpu->arch.cputm_enabled = false;
}

static void enable_cpu_timer_accounting(struct kvm_vcpu *vcpu)
{
	preempt_disable(); /* protect from TOD sync and vcpu_load/put */
	__enable_cpu_timer_accounting(vcpu);
	preempt_enable();
}

static void disable_cpu_timer_accounting(struct kvm_vcpu *vcpu)
{
	preempt_disable(); /* protect from TOD sync and vcpu_load/put */
	__disable_cpu_timer_accounting(vcpu);
	preempt_enable();
}

1488 1489 1490
/* set the cpu timer - may only be called from the VCPU thread itself */
void kvm_s390_set_cpu_timer(struct kvm_vcpu *vcpu, __u64 cputm)
{
1491
	preempt_disable(); /* protect from TOD sync and vcpu_load/put */
1492
	raw_write_seqcount_begin(&vcpu->arch.cputm_seqcount);
1493 1494
	if (vcpu->arch.cputm_enabled)
		vcpu->arch.cputm_start = get_tod_clock_fast();
1495
	vcpu->arch.sie_block->cputm = cputm;
1496
	raw_write_seqcount_end(&vcpu->arch.cputm_seqcount);
1497
	preempt_enable();
1498 1499
}

1500
/* update and get the cpu timer - can also be called from other VCPU threads */
1501 1502
__u64 kvm_s390_get_cpu_timer(struct kvm_vcpu *vcpu)
{
1503
	unsigned int seq;
1504 1505 1506 1507 1508
	__u64 value;

	if (unlikely(!vcpu->arch.cputm_enabled))
		return vcpu->arch.sie_block->cputm;

1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522
	preempt_disable(); /* protect from TOD sync and vcpu_load/put */
	do {
		seq = raw_read_seqcount(&vcpu->arch.cputm_seqcount);
		/*
		 * If the writer would ever execute a read in the critical
		 * section, e.g. in irq context, we have a deadlock.
		 */
		WARN_ON_ONCE((seq & 1) && smp_processor_id() == vcpu->cpu);
		value = vcpu->arch.sie_block->cputm;
		/* if cputm_start is 0, accounting is being started/stopped */
		if (likely(vcpu->arch.cputm_start))
			value -= get_tod_clock_fast() - vcpu->arch.cputm_start;
	} while (read_seqcount_retry(&vcpu->arch.cputm_seqcount, seq & ~1));
	preempt_enable();
1523
	return value;
1524 1525
}

1526 1527
void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
{
1528
	/* Save host register state */
1529
	save_fpu_regs();
1530 1531
	vcpu->arch.host_fpregs.fpc = current->thread.fpu.fpc;
	vcpu->arch.host_fpregs.regs = current->thread.fpu.regs;
1532

1533 1534 1535 1536
	if (MACHINE_HAS_VX)
		current->thread.fpu.regs = vcpu->run->s.regs.vrs;
	else
		current->thread.fpu.regs = vcpu->run->s.regs.fprs;
1537
	current->thread.fpu.fpc = vcpu->run->s.regs.fpc;
1538
	if (test_fp_ctl(current->thread.fpu.fpc))
1539
		/* User space provided an invalid FPC, let's clear it */
1540 1541 1542
		current->thread.fpu.fpc = 0;

	save_access_regs(vcpu->arch.host_acrs);
1543
	restore_access_regs(vcpu->run->s.regs.acrs);
1544
	gmap_enable(vcpu->arch.gmap);
1545
	atomic_or(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
1546
	if (vcpu->arch.cputm_enabled && !is_vcpu_idle(vcpu))
1547
		__start_cpu_timer_accounting(vcpu);
1548
	vcpu->cpu = cpu;
1549 1550 1551 1552
}

void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
{
1553
	vcpu->cpu = -1;
1554
	if (vcpu->arch.cputm_enabled && !is_vcpu_idle(vcpu))
1555
		__stop_cpu_timer_accounting(vcpu);
1556
	atomic_andnot(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
1557
	gmap_disable(vcpu->arch.gmap);
1558

1559
	/* Save guest register state */
1560
	save_fpu_regs();
1561
	vcpu->run->s.regs.fpc = current->thread.fpu.fpc;
1562

1563 1564 1565
	/* Restore host register state */
	current->thread.fpu.fpc = vcpu->arch.host_fpregs.fpc;
	current->thread.fpu.regs = vcpu->arch.host_fpregs.regs;
1566 1567

	save_access_regs(vcpu->run->s.regs.acrs);
1568 1569 1570 1571 1572 1573 1574 1575
	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;
1576
	kvm_s390_set_prefix(vcpu, 0);
1577
	kvm_s390_set_cpu_timer(vcpu, 0);
1578 1579 1580 1581 1582
	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;
1583 1584 1585
	/* make sure the new fpc will be lazily loaded */
	save_fpu_regs();
	current->thread.fpu.fpc = 0;
1586
	vcpu->arch.sie_block->gbea = 1;
1587
	vcpu->arch.sie_block->pp = 0;
1588 1589
	vcpu->arch.pfault_token = KVM_S390_PFAULT_TOKEN_INVALID;
	kvm_clear_async_pf_completion_queue(vcpu);
1590 1591
	if (!kvm_s390_user_cpu_state_ctrl(vcpu->kvm))
		kvm_s390_vcpu_stop(vcpu);
1592
	kvm_s390_clear_local_irqs(vcpu);
1593 1594
}

1595
void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
1596
{
1597
	mutex_lock(&vcpu->kvm->lock);
1598
	preempt_disable();
1599
	vcpu->arch.sie_block->epoch = vcpu->kvm->arch.epoch;
1600
	preempt_enable();
1601
	mutex_unlock(&vcpu->kvm->lock);
1602
	if (!kvm_is_ucontrol(vcpu->kvm)) {
1603
		vcpu->arch.gmap = vcpu->kvm->arch.gmap;
1604
		sca_add_vcpu(vcpu);
1605 1606
	}

1607 1608
}

1609 1610
static void kvm_s390_vcpu_crypto_setup(struct kvm_vcpu *vcpu)
{
1611
	if (!test_kvm_facility(vcpu->kvm, 76))
1612 1613
		return;

1614 1615 1616 1617 1618 1619 1620
	vcpu->arch.sie_block->ecb3 &= ~(ECB3_AES | ECB3_DEA);

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

1621 1622 1623
	vcpu->arch.sie_block->crycbd = vcpu->kvm->arch.crypto.crycbd;
}

1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640
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;
}

1641 1642 1643 1644 1645
static void kvm_s390_vcpu_setup_model(struct kvm_vcpu *vcpu)
{
	struct kvm_s390_cpu_model *model = &vcpu->kvm->arch.model;

	vcpu->arch.sie_block->ibc = model->ibc;
1646
	if (test_kvm_facility(vcpu->kvm, 7))
1647
		vcpu->arch.sie_block->fac = (u32)(u64) model->fac_list;
1648 1649
}

1650 1651
int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
{
1652
	int rc = 0;
1653

1654 1655
	atomic_set(&vcpu->arch.sie_block->cpuflags, CPUSTAT_ZARCH |
						    CPUSTAT_SM |
1656 1657
						    CPUSTAT_STOPPED);

1658
	if (test_kvm_facility(vcpu->kvm, 78))
1659
		atomic_or(CPUSTAT_GED2, &vcpu->arch.sie_block->cpuflags);
1660
	else if (test_kvm_facility(vcpu->kvm, 8))
1661
		atomic_or(CPUSTAT_GED, &vcpu->arch.sie_block->cpuflags);
1662

1663 1664
	kvm_s390_vcpu_setup_model(vcpu);

1665 1666 1667
	vcpu->arch.sie_block->ecb = 0x02;
	if (test_kvm_facility(vcpu->kvm, 9))
		vcpu->arch.sie_block->ecb |= 0x04;
1668
	if (test_kvm_facility(vcpu->kvm, 50) && test_kvm_facility(vcpu->kvm, 73))
1669 1670
		vcpu->arch.sie_block->ecb |= 0x10;

1671 1672
	if (test_kvm_facility(vcpu->kvm, 8))
		vcpu->arch.sie_block->ecb2 |= 0x08;
1673
	vcpu->arch.sie_block->eca   = 0xC1002000U;
1674
	if (sclp.has_siif)
1675
		vcpu->arch.sie_block->eca |= 1;
1676
	if (sclp.has_sigpif)
1677
		vcpu->arch.sie_block->eca |= 0x10000000U;
1678 1679
	if (test_kvm_facility(vcpu->kvm, 64))
		vcpu->arch.sie_block->ecb3 |= 0x01;
1680
	if (test_kvm_facility(vcpu->kvm, 129)) {
1681 1682 1683
		vcpu->arch.sie_block->eca |= 0x00020000;
		vcpu->arch.sie_block->ecd |= 0x20000000;
	}
1684
	vcpu->arch.sie_block->riccbd = (unsigned long) &vcpu->run->s.regs.riccb;
1685
	vcpu->arch.sie_block->ictl |= ICTL_ISKE | ICTL_SSKE | ICTL_RRBE;
J
Janosch Frank 已提交
1686 1687
	if (test_kvm_facility(vcpu->kvm, 74))
		vcpu->arch.sie_block->ictl |= ICTL_OPEREXC;
1688

1689
	if (vcpu->kvm->arch.use_cmma) {
1690 1691 1692
		rc = kvm_s390_vcpu_setup_cmma(vcpu);
		if (rc)
			return rc;
1693
	}
1694
	hrtimer_init(&vcpu->arch.ckc_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
1695
	vcpu->arch.ckc_timer.function = kvm_s390_idle_wakeup;
1696

1697 1698
	kvm_s390_vcpu_crypto_setup(vcpu);

1699
	return rc;
1700 1701 1702 1703 1704
}

struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
				      unsigned int id)
{
1705
	struct kvm_vcpu *vcpu;
1706
	struct sie_page *sie_page;
1707 1708
	int rc = -EINVAL;

1709
	if (!kvm_is_ucontrol(kvm) && !sca_can_add_vcpu(kvm, id))
1710 1711 1712
		goto out;

	rc = -ENOMEM;
1713

1714
	vcpu = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL);
1715
	if (!vcpu)
1716
		goto out;
1717

1718 1719
	sie_page = (struct sie_page *) get_zeroed_page(GFP_KERNEL);
	if (!sie_page)
1720 1721
		goto out_free_cpu;

1722 1723 1724
	vcpu->arch.sie_block = &sie_page->sie_block;
	vcpu->arch.sie_block->itdba = (unsigned long) &sie_page->itdb;

1725
	vcpu->arch.sie_block->icpua = id;
1726 1727
	spin_lock_init(&vcpu->arch.local_int.lock);
	vcpu->arch.local_int.float_int = &kvm->arch.float_int;
1728
	vcpu->arch.local_int.wq = &vcpu->wq;
1729
	vcpu->arch.local_int.cpuflags = &vcpu->arch.sie_block->cpuflags;
1730
	seqcount_init(&vcpu->arch.cputm_seqcount);
1731

1732 1733
	rc = kvm_vcpu_init(vcpu, kvm, id);
	if (rc)
1734
		goto out_free_sie_block;
1735
	VM_EVENT(kvm, 3, "create cpu %d at 0x%pK, sie block at 0x%pK", id, vcpu,
1736
		 vcpu->arch.sie_block);
1737
	trace_kvm_s390_create_vcpu(id, vcpu, vcpu->arch.sie_block);
1738 1739

	return vcpu;
1740 1741
out_free_sie_block:
	free_page((unsigned long)(vcpu->arch.sie_block));
1742
out_free_cpu:
1743
	kmem_cache_free(kvm_vcpu_cache, vcpu);
1744
out:
1745 1746 1747 1748 1749
	return ERR_PTR(rc);
}

int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
{
1750
	return kvm_s390_vcpu_has_irq(vcpu, 0);
1751 1752
}

1753
void kvm_s390_vcpu_block(struct kvm_vcpu *vcpu)
1754
{
1755
	atomic_or(PROG_BLOCK_SIE, &vcpu->arch.sie_block->prog20);
1756
	exit_sie(vcpu);
1757 1758
}

1759
void kvm_s390_vcpu_unblock(struct kvm_vcpu *vcpu)
1760
{
1761
	atomic_andnot(PROG_BLOCK_SIE, &vcpu->arch.sie_block->prog20);
1762 1763
}

1764 1765
static void kvm_s390_vcpu_request(struct kvm_vcpu *vcpu)
{
1766
	atomic_or(PROG_REQUEST, &vcpu->arch.sie_block->prog20);
1767
	exit_sie(vcpu);
1768 1769 1770 1771
}

static void kvm_s390_vcpu_request_handled(struct kvm_vcpu *vcpu)
{
1772
	atomic_andnot(PROG_REQUEST, &vcpu->arch.sie_block->prog20);
1773 1774
}

1775 1776 1777 1778 1779 1780
/*
 * 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)
{
1781
	atomic_or(CPUSTAT_STOP_INT, &vcpu->arch.sie_block->cpuflags);
1782 1783 1784 1785
	while (vcpu->arch.sie_block->prog0c & PROG_IN_SIE)
		cpu_relax();
}

1786 1787
/* Kick a guest cpu out of SIE to process a request synchronously */
void kvm_s390_sync_request(int req, struct kvm_vcpu *vcpu)
1788
{
1789 1790
	kvm_make_request(req, vcpu);
	kvm_s390_vcpu_request(vcpu);
1791 1792
}

1793 1794 1795 1796 1797 1798 1799 1800
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 */
1801
		if (kvm_s390_get_prefix(vcpu) == (address & ~0x1000UL)) {
1802
			VCPU_EVENT(vcpu, 2, "gmap notifier for %lx", address);
1803
			kvm_s390_sync_request(KVM_REQ_MMU_RELOAD, vcpu);
1804 1805 1806 1807
		}
	}
}

1808 1809 1810 1811 1812 1813 1814
int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu)
{
	/* kvm common code refers to this, but never calls it */
	BUG();
	return 0;
}

1815 1816 1817 1818 1819 1820
static int kvm_arch_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu,
					   struct kvm_one_reg *reg)
{
	int r = -EINVAL;

	switch (reg->id) {
1821 1822 1823 1824 1825 1826 1827 1828
	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;
1829
	case KVM_REG_S390_CPU_TIMER:
1830
		r = put_user(kvm_s390_get_cpu_timer(vcpu),
1831 1832 1833 1834 1835 1836
			     (u64 __user *)reg->addr);
		break;
	case KVM_REG_S390_CLOCK_COMP:
		r = put_user(vcpu->arch.sie_block->ckc,
			     (u64 __user *)reg->addr);
		break;
1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848
	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;
1849 1850 1851 1852
	case KVM_REG_S390_PP:
		r = put_user(vcpu->arch.sie_block->pp,
			     (u64 __user *)reg->addr);
		break;
1853 1854 1855 1856
	case KVM_REG_S390_GBEA:
		r = put_user(vcpu->arch.sie_block->gbea,
			     (u64 __user *)reg->addr);
		break;
1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867
	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;
1868
	__u64 val;
1869 1870

	switch (reg->id) {
1871 1872 1873 1874 1875 1876 1877 1878
	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;
1879
	case KVM_REG_S390_CPU_TIMER:
1880 1881 1882
		r = get_user(val, (u64 __user *)reg->addr);
		if (!r)
			kvm_s390_set_cpu_timer(vcpu, val);
1883 1884 1885 1886 1887
		break;
	case KVM_REG_S390_CLOCK_COMP:
		r = get_user(vcpu->arch.sie_block->ckc,
			     (u64 __user *)reg->addr);
		break;
1888 1889 1890
	case KVM_REG_S390_PFTOKEN:
		r = get_user(vcpu->arch.pfault_token,
			     (u64 __user *)reg->addr);
1891 1892
		if (vcpu->arch.pfault_token == KVM_S390_PFAULT_TOKEN_INVALID)
			kvm_clear_async_pf_completion_queue(vcpu);
1893 1894 1895 1896 1897 1898 1899 1900 1901
		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;
1902 1903 1904 1905
	case KVM_REG_S390_PP:
		r = get_user(vcpu->arch.sie_block->pp,
			     (u64 __user *)reg->addr);
		break;
1906 1907 1908 1909
	case KVM_REG_S390_GBEA:
		r = get_user(vcpu->arch.sie_block->gbea,
			     (u64 __user *)reg->addr);
		break;
1910 1911 1912 1913 1914 1915
	default:
		break;
	}

	return r;
}
1916

1917 1918 1919 1920 1921 1922 1923 1924
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)
{
1925
	memcpy(&vcpu->run->s.regs.gprs, &regs->gprs, sizeof(regs->gprs));
1926 1927 1928 1929 1930
	return 0;
}

int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
{
1931
	memcpy(&regs->gprs, &vcpu->run->s.regs.gprs, sizeof(regs->gprs));
1932 1933 1934 1935 1936 1937
	return 0;
}

int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
				  struct kvm_sregs *sregs)
{
1938
	memcpy(&vcpu->run->s.regs.acrs, &sregs->acrs, sizeof(sregs->acrs));
1939
	memcpy(&vcpu->arch.sie_block->gcr, &sregs->crs, sizeof(sregs->crs));
1940
	restore_access_regs(vcpu->run->s.regs.acrs);
1941 1942 1943 1944 1945 1946
	return 0;
}

int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
				  struct kvm_sregs *sregs)
{
1947
	memcpy(&sregs->acrs, &vcpu->run->s.regs.acrs, sizeof(sregs->acrs));
1948 1949 1950 1951 1952 1953
	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)
{
1954 1955
	/* make sure the new values will be lazily loaded */
	save_fpu_regs();
1956 1957
	if (test_fp_ctl(fpu->fpc))
		return -EINVAL;
1958 1959 1960 1961 1962
	current->thread.fpu.fpc = fpu->fpc;
	if (MACHINE_HAS_VX)
		convert_fp_to_vx(current->thread.fpu.vxrs, (freg_t *)fpu->fprs);
	else
		memcpy(current->thread.fpu.fprs, &fpu->fprs, sizeof(fpu->fprs));
1963 1964 1965 1966 1967
	return 0;
}

int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
{
1968 1969 1970 1971 1972 1973 1974
	/* make sure we have the latest values */
	save_fpu_regs();
	if (MACHINE_HAS_VX)
		convert_vx_to_fp((freg_t *)fpu->fprs, current->thread.fpu.vxrs);
	else
		memcpy(fpu->fprs, current->thread.fpu.fprs, sizeof(fpu->fprs));
	fpu->fpc = current->thread.fpu.fpc;
1975 1976 1977 1978 1979 1980 1981
	return 0;
}

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

1982
	if (!is_vcpu_stopped(vcpu))
1983
		rc = -EBUSY;
1984 1985 1986 1987
	else {
		vcpu->run->psw_mask = psw.mask;
		vcpu->run->psw_addr = psw.addr;
	}
1988 1989 1990 1991 1992 1993 1994 1995 1996
	return rc;
}

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

1997 1998 1999 2000
#define VALID_GUESTDBG_FLAGS (KVM_GUESTDBG_SINGLESTEP | \
			      KVM_GUESTDBG_USE_HW_BP | \
			      KVM_GUESTDBG_ENABLE)

J
Jan Kiszka 已提交
2001 2002
int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
					struct kvm_guest_debug *dbg)
2003
{
2004 2005 2006 2007 2008
	int rc = 0;

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

2009
	if (dbg->control & ~VALID_GUESTDBG_FLAGS)
2010 2011 2012 2013 2014
		return -EINVAL;

	if (dbg->control & KVM_GUESTDBG_ENABLE) {
		vcpu->guest_debug = dbg->control;
		/* enforce guest PER */
2015
		atomic_or(CPUSTAT_P, &vcpu->arch.sie_block->cpuflags);
2016 2017 2018 2019

		if (dbg->control & KVM_GUESTDBG_USE_HW_BP)
			rc = kvm_s390_import_bp_data(vcpu, dbg);
	} else {
2020
		atomic_andnot(CPUSTAT_P, &vcpu->arch.sie_block->cpuflags);
2021 2022 2023 2024 2025 2026
		vcpu->arch.guestdbg.last_bp = 0;
	}

	if (rc) {
		vcpu->guest_debug = 0;
		kvm_s390_clear_bp_data(vcpu);
2027
		atomic_andnot(CPUSTAT_P, &vcpu->arch.sie_block->cpuflags);
2028 2029 2030
	}

	return rc;
2031 2032
}

2033 2034 2035
int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
				    struct kvm_mp_state *mp_state)
{
2036 2037 2038
	/* CHECK_STOP and LOAD are not supported yet */
	return is_vcpu_stopped(vcpu) ? KVM_MP_STATE_STOPPED :
				       KVM_MP_STATE_OPERATING;
2039 2040 2041 2042 2043
}

int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
				    struct kvm_mp_state *mp_state)
{
2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063
	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;
2064 2065
}

2066 2067 2068 2069 2070
static bool ibs_enabled(struct kvm_vcpu *vcpu)
{
	return atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_IBS;
}

2071 2072
static int kvm_s390_handle_requests(struct kvm_vcpu *vcpu)
{
2073
retry:
2074
	kvm_s390_vcpu_request_handled(vcpu);
2075 2076
	if (!vcpu->requests)
		return 0;
2077 2078 2079 2080 2081 2082 2083
	/*
	 * 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.
	 */
2084
	if (kvm_check_request(KVM_REQ_MMU_RELOAD, vcpu)) {
2085 2086
		int rc;
		rc = gmap_ipte_notify(vcpu->arch.gmap,
2087
				      kvm_s390_get_prefix(vcpu),
2088 2089 2090
				      PAGE_SIZE * 2);
		if (rc)
			return rc;
2091
		goto retry;
2092
	}
2093

2094 2095 2096 2097 2098
	if (kvm_check_request(KVM_REQ_TLB_FLUSH, vcpu)) {
		vcpu->arch.sie_block->ihcpu = 0xffff;
		goto retry;
	}

2099 2100 2101
	if (kvm_check_request(KVM_REQ_ENABLE_IBS, vcpu)) {
		if (!ibs_enabled(vcpu)) {
			trace_kvm_s390_enable_disable_ibs(vcpu->vcpu_id, 1);
2102
			atomic_or(CPUSTAT_IBS,
2103 2104 2105
					&vcpu->arch.sie_block->cpuflags);
		}
		goto retry;
2106
	}
2107 2108 2109 2110

	if (kvm_check_request(KVM_REQ_DISABLE_IBS, vcpu)) {
		if (ibs_enabled(vcpu)) {
			trace_kvm_s390_enable_disable_ibs(vcpu->vcpu_id, 0);
2111
			atomic_andnot(CPUSTAT_IBS,
2112 2113 2114 2115 2116
					  &vcpu->arch.sie_block->cpuflags);
		}
		goto retry;
	}

2117 2118 2119
	/* nothing to do, just clear the request */
	clear_bit(KVM_REQ_UNHALT, &vcpu->requests);

2120 2121 2122
	return 0;
}

2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138
void kvm_s390_set_tod_clock(struct kvm *kvm, u64 tod)
{
	struct kvm_vcpu *vcpu;
	int i;

	mutex_lock(&kvm->lock);
	preempt_disable();
	kvm->arch.epoch = tod - get_tod_clock();
	kvm_s390_vcpu_block_all(kvm);
	kvm_for_each_vcpu(i, vcpu, kvm)
		vcpu->arch.sie_block->epoch = kvm->arch.epoch;
	kvm_s390_vcpu_unblock_all(kvm);
	preempt_enable();
	mutex_unlock(&kvm->lock);
}

2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149
/**
 * 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)
2150
{
2151 2152
	return gmap_fault(vcpu->arch.gmap, gpa,
			  writable ? FAULT_FLAG_WRITE : 0);
2153 2154
}

2155 2156 2157 2158
static void __kvm_inject_pfault_token(struct kvm_vcpu *vcpu, bool start_token,
				      unsigned long token)
{
	struct kvm_s390_interrupt inti;
2159
	struct kvm_s390_irq irq;
2160 2161

	if (start_token) {
2162 2163 2164
		irq.u.ext.ext_params2 = token;
		irq.type = KVM_S390_INT_PFAULT_INIT;
		WARN_ON_ONCE(kvm_s390_inject_vcpu(vcpu, &irq));
2165 2166
	} else {
		inti.type = KVM_S390_INT_PFAULT_DONE;
2167
		inti.parm64 = token;
2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213
		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;
2214
	if (kvm_s390_vcpu_has_irq(vcpu, 0))
2215 2216 2217 2218 2219 2220
		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
2221 2222 2223
	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))
2224 2225 2226 2227 2228 2229
		return 0;

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

2230
static int vcpu_pre_run(struct kvm_vcpu *vcpu)
2231
{
2232
	int rc, cpuflags;
2233

2234 2235 2236 2237 2238 2239 2240
	/*
	 * 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);

2241 2242
	vcpu->arch.sie_block->gg14 = vcpu->run->s.regs.gprs[14];
	vcpu->arch.sie_block->gg15 = vcpu->run->s.regs.gprs[15];
2243 2244 2245 2246

	if (need_resched())
		schedule();

2247
	if (test_cpu_flag(CIF_MCCK_PENDING))
2248 2249
		s390_handle_mcck();

2250 2251 2252 2253 2254
	if (!kvm_is_ucontrol(vcpu->kvm)) {
		rc = kvm_s390_deliver_pending_interrupts(vcpu);
		if (rc)
			return rc;
	}
C
Carsten Otte 已提交
2255

2256 2257 2258 2259
	rc = kvm_s390_handle_requests(vcpu);
	if (rc)
		return rc;

2260 2261 2262 2263 2264
	if (guestdbg_enabled(vcpu)) {
		kvm_s390_backup_guest_per_regs(vcpu);
		kvm_s390_patch_guest_per_regs(vcpu);
	}

2265
	vcpu->arch.sie_block->icptcode = 0;
2266 2267 2268
	cpuflags = atomic_read(&vcpu->arch.sie_block->cpuflags);
	VCPU_EVENT(vcpu, 6, "entering sie flags %x", cpuflags);
	trace_kvm_s390_sie_enter(vcpu, cpuflags);
2269

2270 2271 2272
	return 0;
}

2273 2274
static int vcpu_post_run_fault_in_sie(struct kvm_vcpu *vcpu)
{
2275 2276 2277 2278
	struct kvm_s390_pgm_info pgm_info = {
		.code = PGM_ADDRESSING,
	};
	u8 opcode, ilen;
2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291
	int rc;

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

	/*
	 * We want to inject an addressing exception, which is defined as a
	 * suppressing or terminating exception. However, since we came here
	 * by a DAT access exception, the PSW still points to the faulting
	 * instruction since DAT exceptions are nullifying. So we've got
	 * to look up the current opcode to get the length of the instruction
	 * to be able to forward the PSW.
	 */
2292
	rc = read_guest_instr(vcpu, &opcode, 1);
2293
	ilen = insn_length(opcode);
2294 2295 2296 2297 2298 2299 2300 2301 2302 2303
	if (rc < 0) {
		return rc;
	} else if (rc) {
		/* Instruction-Fetching Exceptions - we can't detect the ilen.
		 * Forward by arbitrary ilc, injection will take care of
		 * nullification if necessary.
		 */
		pgm_info = vcpu->arch.pgm;
		ilen = 4;
	}
2304 2305 2306
	pgm_info.flags = ilen | KVM_S390_PGM_FLAGS_ILC_VALID;
	kvm_s390_forward_psw(vcpu, ilen);
	return kvm_s390_inject_prog_irq(vcpu, &pgm_info);
2307 2308
}

2309 2310
static int vcpu_post_run(struct kvm_vcpu *vcpu, int exit_reason)
{
2311 2312 2313 2314
	VCPU_EVENT(vcpu, 6, "exit sie icptcode %d",
		   vcpu->arch.sie_block->icptcode);
	trace_kvm_s390_sie_exit(vcpu, vcpu->arch.sie_block->icptcode);

2315 2316 2317
	if (guestdbg_enabled(vcpu))
		kvm_s390_restore_guest_per_regs(vcpu);

2318 2319
	vcpu->run->s.regs.gprs[14] = vcpu->arch.sie_block->gg14;
	vcpu->run->s.regs.gprs[15] = vcpu->arch.sie_block->gg15;
2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333

	if (vcpu->arch.sie_block->icptcode > 0) {
		int rc = kvm_handle_sie_intercept(vcpu);

		if (rc != -EOPNOTSUPP)
			return rc;
		vcpu->run->exit_reason = KVM_EXIT_S390_SIEIC;
		vcpu->run->s390_sieic.icptcode = vcpu->arch.sie_block->icptcode;
		vcpu->run->s390_sieic.ipa = vcpu->arch.sie_block->ipa;
		vcpu->run->s390_sieic.ipb = vcpu->arch.sie_block->ipb;
		return -EREMOTE;
	} else if (exit_reason != -EFAULT) {
		vcpu->stat.exit_null++;
		return 0;
2334 2335 2336 2337 2338
	} 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;
2339
		return -EREMOTE;
2340
	} else if (current->thread.gmap_pfault) {
2341
		trace_kvm_s390_major_guest_pfault(vcpu);
2342
		current->thread.gmap_pfault = 0;
2343 2344 2345
		if (kvm_arch_setup_async_pf(vcpu))
			return 0;
		return kvm_arch_fault_in_page(vcpu, current->thread.gmap_addr, 1);
2346
	}
2347
	return vcpu_post_run_fault_in_sie(vcpu);
2348 2349 2350 2351 2352 2353
}

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

2354 2355 2356 2357 2358 2359
	/*
	 * 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);

2360 2361 2362 2363
	do {
		rc = vcpu_pre_run(vcpu);
		if (rc)
			break;
2364

2365
		srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
2366 2367 2368 2369
		/*
		 * As PF_VCPU will be used in fault handler, between
		 * guest_enter and guest_exit should be no uaccess.
		 */
2370 2371
		local_irq_disable();
		__kvm_guest_enter();
2372
		__disable_cpu_timer_accounting(vcpu);
2373
		local_irq_enable();
2374 2375
		exit_reason = sie64a(vcpu->arch.sie_block,
				     vcpu->run->s.regs.gprs);
2376
		local_irq_disable();
2377
		__enable_cpu_timer_accounting(vcpu);
2378 2379
		__kvm_guest_exit();
		local_irq_enable();
2380
		vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
2381 2382

		rc = vcpu_post_run(vcpu, exit_reason);
2383
	} while (!signal_pending(current) && !guestdbg_exit_pending(vcpu) && !rc);
2384

2385
	srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
2386
	return rc;
2387 2388
}

2389 2390 2391 2392 2393 2394 2395 2396
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);
2397 2398
		/* some control register changes require a tlb flush */
		kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
2399 2400
	}
	if (kvm_run->kvm_dirty_regs & KVM_SYNC_ARCH0) {
2401
		kvm_s390_set_cpu_timer(vcpu, kvm_run->s.regs.cputm);
2402 2403 2404 2405 2406 2407 2408 2409 2410
		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;
2411 2412
		if (vcpu->arch.pfault_token == KVM_S390_PFAULT_TOKEN_INVALID)
			kvm_clear_async_pf_completion_queue(vcpu);
2413 2414 2415 2416 2417 2418 2419 2420 2421 2422
	}
	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);
2423
	kvm_run->s.regs.cputm = kvm_s390_get_cpu_timer(vcpu);
2424 2425 2426 2427 2428 2429 2430 2431 2432
	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;
}

2433 2434
int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
{
2435
	int rc;
2436 2437
	sigset_t sigsaved;

2438 2439 2440 2441 2442
	if (guestdbg_exit_pending(vcpu)) {
		kvm_s390_prepare_debug_exit(vcpu);
		return 0;
	}

2443 2444 2445
	if (vcpu->sigset_active)
		sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved);

2446 2447 2448
	if (!kvm_s390_user_cpu_state_ctrl(vcpu->kvm)) {
		kvm_s390_vcpu_start(vcpu);
	} else if (is_vcpu_stopped(vcpu)) {
2449
		pr_err_ratelimited("can't run stopped vcpu %d\n",
2450 2451 2452
				   vcpu->vcpu_id);
		return -EINVAL;
	}
2453

2454
	sync_regs(vcpu, kvm_run);
2455
	enable_cpu_timer_accounting(vcpu);
2456

2457
	might_fault();
2458
	rc = __vcpu_run(vcpu);
2459

2460 2461
	if (signal_pending(current) && !rc) {
		kvm_run->exit_reason = KVM_EXIT_INTR;
2462
		rc = -EINTR;
2463
	}
2464

2465 2466 2467 2468 2469
	if (guestdbg_exit_pending(vcpu) && !rc)  {
		kvm_s390_prepare_debug_exit(vcpu);
		rc = 0;
	}

2470
	if (rc == -EREMOTE) {
2471
		/* userspace support is needed, kvm_run has been prepared */
2472 2473
		rc = 0;
	}
2474

2475
	disable_cpu_timer_accounting(vcpu);
2476
	store_regs(vcpu, kvm_run);
2477

2478 2479 2480 2481
	if (vcpu->sigset_active)
		sigprocmask(SIG_SETMASK, &sigsaved, NULL);

	vcpu->stat.exit_userspace++;
2482
	return rc;
2483 2484 2485 2486 2487 2488 2489 2490
}

/*
 * 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
 */
2491
int kvm_s390_store_status_unloaded(struct kvm_vcpu *vcpu, unsigned long gpa)
2492
{
2493
	unsigned char archmode = 1;
2494
	freg_t fprs[NUM_FPRS];
2495
	unsigned int px;
2496
	u64 clkcomp, cputm;
2497
	int rc;
2498

2499
	px = kvm_s390_get_prefix(vcpu);
2500 2501
	if (gpa == KVM_S390_STORE_STATUS_NOADDR) {
		if (write_guest_abs(vcpu, 163, &archmode, 1))
2502
			return -EFAULT;
2503
		gpa = 0;
2504 2505
	} else if (gpa == KVM_S390_STORE_STATUS_PREFIXED) {
		if (write_guest_real(vcpu, 163, &archmode, 1))
2506
			return -EFAULT;
2507 2508 2509
		gpa = px;
	} else
		gpa -= __LC_FPREGS_SAVE_AREA;
2510 2511 2512

	/* manually convert vector registers if necessary */
	if (MACHINE_HAS_VX) {
2513
		convert_vx_to_fp(fprs, (__vector128 *) vcpu->run->s.regs.vrs);
2514 2515 2516 2517
		rc = write_guest_abs(vcpu, gpa + __LC_FPREGS_SAVE_AREA,
				     fprs, 128);
	} else {
		rc = write_guest_abs(vcpu, gpa + __LC_FPREGS_SAVE_AREA,
2518
				     vcpu->run->s.regs.fprs, 128);
2519
	}
2520
	rc |= write_guest_abs(vcpu, gpa + __LC_GPREGS_SAVE_AREA,
2521
			      vcpu->run->s.regs.gprs, 128);
2522
	rc |= write_guest_abs(vcpu, gpa + __LC_PSW_SAVE_AREA,
2523
			      &vcpu->arch.sie_block->gpsw, 16);
2524
	rc |= write_guest_abs(vcpu, gpa + __LC_PREFIX_SAVE_AREA,
2525
			      &px, 4);
2526
	rc |= write_guest_abs(vcpu, gpa + __LC_FP_CREG_SAVE_AREA,
2527
			      &vcpu->run->s.regs.fpc, 4);
2528
	rc |= write_guest_abs(vcpu, gpa + __LC_TOD_PROGREG_SAVE_AREA,
2529
			      &vcpu->arch.sie_block->todpr, 4);
2530
	cputm = kvm_s390_get_cpu_timer(vcpu);
2531
	rc |= write_guest_abs(vcpu, gpa + __LC_CPU_TIMER_SAVE_AREA,
2532
			      &cputm, 8);
2533
	clkcomp = vcpu->arch.sie_block->ckc >> 8;
2534
	rc |= write_guest_abs(vcpu, gpa + __LC_CLOCK_COMP_SAVE_AREA,
2535
			      &clkcomp, 8);
2536
	rc |= write_guest_abs(vcpu, gpa + __LC_AREGS_SAVE_AREA,
2537
			      &vcpu->run->s.regs.acrs, 64);
2538
	rc |= write_guest_abs(vcpu, gpa + __LC_CREGS_SAVE_AREA,
2539 2540
			      &vcpu->arch.sie_block->gcr, 128);
	return rc ? -EFAULT : 0;
2541 2542
}

2543 2544 2545 2546 2547 2548 2549
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
	 */
2550
	save_fpu_regs();
2551
	vcpu->run->s.regs.fpc = current->thread.fpu.fpc;
2552 2553 2554 2555 2556
	save_access_regs(vcpu->run->s.regs.acrs);

	return kvm_s390_store_status_unloaded(vcpu, addr);
}

E
Eric Farman 已提交
2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577
/*
 * store additional status at address
 */
int kvm_s390_store_adtl_status_unloaded(struct kvm_vcpu *vcpu,
					unsigned long gpa)
{
	/* Only bits 0-53 are used for address formation */
	if (!(gpa & ~0x3ff))
		return 0;

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

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

	/*
	 * The guest VXRS are in the host VXRs due to the lazy
2578 2579 2580 2581 2582
	 * copying in vcpu load/put. We can simply call save_fpu_regs()
	 * to save the current register state because we are in the
	 * middle of a load/put cycle.
	 *
	 * Let's update our copies before we save it into the save area.
E
Eric Farman 已提交
2583
	 */
2584
	save_fpu_regs();
E
Eric Farman 已提交
2585 2586 2587 2588

	return kvm_s390_store_adtl_status_unloaded(vcpu, addr);
}

2589 2590 2591
static void __disable_ibs_on_vcpu(struct kvm_vcpu *vcpu)
{
	kvm_check_request(KVM_REQ_ENABLE_IBS, vcpu);
2592
	kvm_s390_sync_request(KVM_REQ_DISABLE_IBS, vcpu);
2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607
}

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);
2608
	kvm_s390_sync_request(KVM_REQ_ENABLE_IBS, vcpu);
2609 2610
}

2611 2612
void kvm_s390_vcpu_start(struct kvm_vcpu *vcpu)
{
2613 2614 2615 2616 2617
	int i, online_vcpus, started_vcpus = 0;

	if (!is_vcpu_stopped(vcpu))
		return;

2618
	trace_kvm_s390_vcpu_start_stop(vcpu->vcpu_id, 1);
2619
	/* Only one cpu at a time may enter/leave the STOPPED state. */
2620
	spin_lock(&vcpu->kvm->arch.start_stop_lock);
2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639
	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);
	}

2640
	atomic_andnot(CPUSTAT_STOPPED, &vcpu->arch.sie_block->cpuflags);
2641 2642 2643 2644
	/*
	 * Another VCPU might have used IBS while we were offline.
	 * Let's play safe and flush the VCPU at startup.
	 */
2645
	kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
2646
	spin_unlock(&vcpu->kvm->arch.start_stop_lock);
2647
	return;
2648 2649 2650 2651
}

void kvm_s390_vcpu_stop(struct kvm_vcpu *vcpu)
{
2652 2653 2654 2655 2656 2657
	int i, online_vcpus, started_vcpus = 0;
	struct kvm_vcpu *started_vcpu = NULL;

	if (is_vcpu_stopped(vcpu))
		return;

2658
	trace_kvm_s390_vcpu_start_stop(vcpu->vcpu_id, 0);
2659
	/* Only one cpu at a time may enter/leave the STOPPED state. */
2660
	spin_lock(&vcpu->kvm->arch.start_stop_lock);
2661 2662
	online_vcpus = atomic_read(&vcpu->kvm->online_vcpus);

2663
	/* SIGP STOP and SIGP STOP AND STORE STATUS has been fully processed */
2664
	kvm_s390_clear_stop_irq(vcpu);
2665

2666
	atomic_or(CPUSTAT_STOPPED, &vcpu->arch.sie_block->cpuflags);
2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683
	__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);
	}

2684
	spin_unlock(&vcpu->kvm->arch.start_stop_lock);
2685
	return;
2686 2687
}

2688 2689 2690 2691 2692 2693 2694 2695 2696
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) {
2697 2698 2699
	case KVM_CAP_S390_CSS_SUPPORT:
		if (!vcpu->kvm->arch.css_support) {
			vcpu->kvm->arch.css_support = 1;
2700
			VM_EVENT(vcpu->kvm, 3, "%s", "ENABLE: CSS support");
2701 2702 2703 2704
			trace_kvm_s390_enable_css(vcpu->kvm);
		}
		r = 0;
		break;
2705 2706 2707 2708 2709 2710 2711
	default:
		r = -EINVAL;
		break;
	}
	return r;
}

2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737
static long kvm_s390_guest_mem_op(struct kvm_vcpu *vcpu,
				  struct kvm_s390_mem_op *mop)
{
	void __user *uaddr = (void __user *)mop->buf;
	void *tmpbuf = NULL;
	int r, srcu_idx;
	const u64 supported_flags = KVM_S390_MEMOP_F_INJECT_EXCEPTION
				    | KVM_S390_MEMOP_F_CHECK_ONLY;

	if (mop->flags & ~supported_flags)
		return -EINVAL;

	if (mop->size > MEM_OP_MAX_SIZE)
		return -E2BIG;

	if (!(mop->flags & KVM_S390_MEMOP_F_CHECK_ONLY)) {
		tmpbuf = vmalloc(mop->size);
		if (!tmpbuf)
			return -ENOMEM;
	}

	srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);

	switch (mop->op) {
	case KVM_S390_MEMOP_LOGICAL_READ:
		if (mop->flags & KVM_S390_MEMOP_F_CHECK_ONLY) {
2738 2739
			r = check_gva_range(vcpu, mop->gaddr, mop->ar,
					    mop->size, GACC_FETCH);
2740 2741 2742 2743 2744 2745 2746 2747 2748 2749
			break;
		}
		r = read_guest(vcpu, mop->gaddr, mop->ar, tmpbuf, mop->size);
		if (r == 0) {
			if (copy_to_user(uaddr, tmpbuf, mop->size))
				r = -EFAULT;
		}
		break;
	case KVM_S390_MEMOP_LOGICAL_WRITE:
		if (mop->flags & KVM_S390_MEMOP_F_CHECK_ONLY) {
2750 2751
			r = check_gva_range(vcpu, mop->gaddr, mop->ar,
					    mop->size, GACC_STORE);
2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772
			break;
		}
		if (copy_from_user(tmpbuf, uaddr, mop->size)) {
			r = -EFAULT;
			break;
		}
		r = write_guest(vcpu, mop->gaddr, mop->ar, tmpbuf, mop->size);
		break;
	default:
		r = -EINVAL;
	}

	srcu_read_unlock(&vcpu->kvm->srcu, srcu_idx);

	if (r > 0 && (mop->flags & KVM_S390_MEMOP_F_INJECT_EXCEPTION) != 0)
		kvm_s390_inject_prog_irq(vcpu, &vcpu->arch.pgm);

	vfree(tmpbuf);
	return r;
}

2773 2774 2775 2776 2777
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;
2778
	int idx;
2779
	long r;
2780

2781
	switch (ioctl) {
2782 2783 2784 2785 2786 2787 2788 2789 2790
	case KVM_S390_IRQ: {
		struct kvm_s390_irq s390irq;

		r = -EFAULT;
		if (copy_from_user(&s390irq, argp, sizeof(s390irq)))
			break;
		r = kvm_s390_inject_vcpu(vcpu, &s390irq);
		break;
	}
2791
	case KVM_S390_INTERRUPT: {
2792
		struct kvm_s390_interrupt s390int;
2793
		struct kvm_s390_irq s390irq;
2794

2795
		r = -EFAULT;
2796
		if (copy_from_user(&s390int, argp, sizeof(s390int)))
2797
			break;
2798 2799 2800
		if (s390int_to_s390irq(&s390int, &s390irq))
			return -EINVAL;
		r = kvm_s390_inject_vcpu(vcpu, &s390irq);
2801
		break;
2802
	}
2803
	case KVM_S390_STORE_STATUS:
2804
		idx = srcu_read_lock(&vcpu->kvm->srcu);
2805
		r = kvm_s390_vcpu_store_status(vcpu, arg);
2806
		srcu_read_unlock(&vcpu->kvm->srcu, idx);
2807
		break;
2808 2809 2810
	case KVM_S390_SET_INITIAL_PSW: {
		psw_t psw;

2811
		r = -EFAULT;
2812
		if (copy_from_user(&psw, argp, sizeof(psw)))
2813 2814 2815
			break;
		r = kvm_arch_vcpu_ioctl_set_initial_psw(vcpu, psw);
		break;
2816 2817
	}
	case KVM_S390_INITIAL_RESET:
2818 2819
		r = kvm_arch_vcpu_ioctl_initial_reset(vcpu);
		break;
2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831
	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;
	}
2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867
#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
2868
	case KVM_S390_VCPU_FAULT: {
2869
		r = gmap_fault(vcpu->arch.gmap, arg, 0);
2870 2871
		break;
	}
2872 2873 2874 2875 2876 2877 2878 2879 2880
	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;
	}
2881 2882 2883 2884 2885 2886 2887 2888 2889
	case KVM_S390_MEM_OP: {
		struct kvm_s390_mem_op mem_op;

		if (copy_from_user(&mem_op, argp, sizeof(mem_op)) == 0)
			r = kvm_s390_guest_mem_op(vcpu, &mem_op);
		else
			r = -EFAULT;
		break;
	}
2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921
	case KVM_S390_SET_IRQ_STATE: {
		struct kvm_s390_irq_state irq_state;

		r = -EFAULT;
		if (copy_from_user(&irq_state, argp, sizeof(irq_state)))
			break;
		if (irq_state.len > VCPU_IRQS_MAX_BUF ||
		    irq_state.len == 0 ||
		    irq_state.len % sizeof(struct kvm_s390_irq) > 0) {
			r = -EINVAL;
			break;
		}
		r = kvm_s390_set_irq_state(vcpu,
					   (void __user *) irq_state.buf,
					   irq_state.len);
		break;
	}
	case KVM_S390_GET_IRQ_STATE: {
		struct kvm_s390_irq_state irq_state;

		r = -EFAULT;
		if (copy_from_user(&irq_state, argp, sizeof(irq_state)))
			break;
		if (irq_state.len == 0) {
			r = -EINVAL;
			break;
		}
		r = kvm_s390_get_irq_state(vcpu,
					   (__u8 __user *)  irq_state.buf,
					   irq_state.len);
		break;
	}
2922
	default:
2923
		r = -ENOTTY;
2924
	}
2925
	return r;
2926 2927
}

2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940
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;
}

2941 2942
int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
			    unsigned long npages)
2943 2944 2945 2946
{
	return 0;
}

2947
/* Section: memory related */
2948 2949
int kvm_arch_prepare_memory_region(struct kvm *kvm,
				   struct kvm_memory_slot *memslot,
2950
				   const struct kvm_userspace_memory_region *mem,
2951
				   enum kvm_mr_change change)
2952
{
2953 2954 2955 2956
	/* 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 */
2957

2958
	if (mem->userspace_addr & 0xffffful)
2959 2960
		return -EINVAL;

2961
	if (mem->memory_size & 0xffffful)
2962 2963
		return -EINVAL;

2964 2965 2966
	if (mem->guest_phys_addr + mem->memory_size > kvm->arch.mem_limit)
		return -EINVAL;

2967 2968 2969 2970
	return 0;
}

void kvm_arch_commit_memory_region(struct kvm *kvm,
2971
				const struct kvm_userspace_memory_region *mem,
2972
				const struct kvm_memory_slot *old,
2973
				const struct kvm_memory_slot *new,
2974
				enum kvm_mr_change change)
2975
{
2976
	int rc;
2977

2978 2979 2980 2981 2982 2983 2984 2985 2986 2987
	/* 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;
2988 2989 2990 2991

	rc = gmap_map_segment(kvm->arch.gmap, mem->userspace_addr,
		mem->guest_phys_addr, mem->memory_size);
	if (rc)
2992
		pr_warn("failed to commit memory region\n");
2993
	return;
2994 2995
}

2996 2997 2998 2999 3000 3001 3002
static inline unsigned long nonhyp_mask(int i)
{
	unsigned int nonhyp_fai = (sclp.hmfai << i * 2) >> 30;

	return 0x0000ffffffffffffUL >> (nonhyp_fai << 4);
}

3003 3004 3005 3006 3007
void kvm_arch_vcpu_block_finish(struct kvm_vcpu *vcpu)
{
	vcpu->valid_wakeup = false;
}

3008 3009
static int __init kvm_s390_init(void)
{
3010 3011
	int i;

3012 3013 3014 3015 3016
	if (!sclp.has_sief2) {
		pr_info("SIE not available\n");
		return -ENODEV;
	}

3017 3018 3019 3020
	for (i = 0; i < 16; i++)
		kvm_s390_fac_list_mask[i] |=
			S390_lowcore.stfle_fac_list[i] & nonhyp_mask(i);

3021
	return kvm_init(NULL, sizeof(struct kvm_vcpu), 0, THIS_MODULE);
3022 3023 3024 3025 3026 3027 3028 3029 3030
}

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

module_init(kvm_s390_init);
module_exit(kvm_s390_exit);
3031 3032 3033 3034 3035 3036 3037 3038 3039

/*
 * 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");