kvm-s390.c 36.3 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 15 16 17 18
 */

#include <linux/compiler.h>
#include <linux/err.h>
#include <linux/fs.h>
19
#include <linux/hrtimer.h>
20 21 22 23 24
#include <linux/init.h>
#include <linux/kvm.h>
#include <linux/kvm_host.h>
#include <linux/module.h>
#include <linux/slab.h>
25
#include <linux/timer.h>
26
#include <asm/asm-offsets.h>
27 28
#include <asm/lowcore.h>
#include <asm/pgtable.h>
29
#include <asm/nmi.h>
30
#include <asm/switch_to.h>
31
#include <asm/facility.h>
32
#include <asm/sclp.h>
33
#include "kvm-s390.h"
34 35
#include "gaccess.h"

36 37
#define CREATE_TRACE_POINTS
#include "trace.h"
38
#include "trace-s390.h"
39

40 41 42 43
#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) },
44
	{ "exit_null", VCPU_STAT(exit_null) },
45 46 47 48
	{ "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) },
49 50 51
	{ "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) },
52
	{ "instruction_lctlg", VCPU_STAT(instruction_lctlg) },
53 54
	{ "instruction_lctl", VCPU_STAT(instruction_lctl) },
	{ "deliver_emergency_signal", VCPU_STAT(deliver_emergency_signal) },
55
	{ "deliver_external_call", VCPU_STAT(deliver_external_call) },
56 57 58 59 60 61 62
	{ "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) },
63
	{ "instruction_pfmf", VCPU_STAT(instruction_pfmf) },
64 65 66 67 68 69 70
	{ "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) },
	{ "instruction_stsch", VCPU_STAT(instruction_stsch) },
	{ "instruction_chsc", VCPU_STAT(instruction_chsc) },
71
	{ "instruction_essa", VCPU_STAT(instruction_essa) },
72 73
	{ "instruction_stsi", VCPU_STAT(instruction_stsi) },
	{ "instruction_stfl", VCPU_STAT(instruction_stfl) },
74
	{ "instruction_tprot", VCPU_STAT(instruction_tprot) },
75
	{ "instruction_sigp_sense", VCPU_STAT(instruction_sigp_sense) },
76
	{ "instruction_sigp_sense_running", VCPU_STAT(instruction_sigp_sense_running) },
77
	{ "instruction_sigp_external_call", VCPU_STAT(instruction_sigp_external_call) },
78 79 80 81 82
	{ "instruction_sigp_emergency", VCPU_STAT(instruction_sigp_emergency) },
	{ "instruction_sigp_stop", VCPU_STAT(instruction_sigp_stop) },
	{ "instruction_sigp_set_arch", VCPU_STAT(instruction_sigp_arch) },
	{ "instruction_sigp_set_prefix", VCPU_STAT(instruction_sigp_prefix) },
	{ "instruction_sigp_restart", VCPU_STAT(instruction_sigp_restart) },
83
	{ "diagnose_10", VCPU_STAT(diagnose_10) },
84
	{ "diagnose_44", VCPU_STAT(diagnose_44) },
85
	{ "diagnose_9c", VCPU_STAT(diagnose_9c) },
86 87 88
	{ NULL }
};

89
unsigned long *vfacilities;
90
static struct gmap_notifier gmap_notifier;
91

92 93 94 95 96 97
/* test availability of vfacility */
static inline int test_vfacility(unsigned long nr)
{
	return __test_facility(nr, (void *) vfacilities);
}

98
/* Section: not file related */
99
int kvm_arch_hardware_enable(void *garbage)
100 101
{
	/* every s390 is virtualization enabled ;-) */
102
	return 0;
103 104 105 106 107 108
}

void kvm_arch_hardware_disable(void *garbage)
{
}

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

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

void kvm_arch_hardware_unsetup(void)
{
120
	gmap_unregister_ipte_notifier(&gmap_notifier);
121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146
}

void kvm_arch_check_processor_compat(void *rtn)
{
}

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

void kvm_arch_exit(void)
{
}

/* Section: device related */
long kvm_arch_dev_ioctl(struct file *filp,
			unsigned int ioctl, unsigned long arg)
{
	if (ioctl == KVM_S390_ENABLE_SIE)
		return s390_enable_sie();
	return -EINVAL;
}

int kvm_dev_ioctl_check_extension(long ext)
{
147 148
	int r;

149
	switch (ext) {
150
	case KVM_CAP_S390_PSW:
151
	case KVM_CAP_S390_GMAP:
152
	case KVM_CAP_SYNC_MMU:
153 154 155
#ifdef CONFIG_KVM_S390_UCONTROL
	case KVM_CAP_S390_UCONTROL:
#endif
156
	case KVM_CAP_ASYNC_PF:
157
	case KVM_CAP_SYNC_REGS:
158
	case KVM_CAP_ONE_REG:
159
	case KVM_CAP_ENABLE_CAP:
160
	case KVM_CAP_S390_CSS_SUPPORT:
C
Cornelia Huck 已提交
161
	case KVM_CAP_IOEVENTFD:
162
	case KVM_CAP_DEVICE_CTRL:
163
	case KVM_CAP_ENABLE_CAP_VM:
164 165
		r = 1;
		break;
166 167 168 169
	case KVM_CAP_NR_VCPUS:
	case KVM_CAP_MAX_VCPUS:
		r = KVM_MAX_VCPUS;
		break;
170 171 172
	case KVM_CAP_NR_MEMSLOTS:
		r = KVM_USER_MEM_SLOTS;
		break;
173
	case KVM_CAP_S390_COW:
174
		r = MACHINE_HAS_ESOP;
175
		break;
176
	default:
177
		r = 0;
178
	}
179
	return r;
180 181 182 183 184 185 186 187 188 189 190 191
}

/* Section: vm related */
/*
 * Get (and clear) the dirty memory log for a memory slot.
 */
int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
			       struct kvm_dirty_log *log)
{
	return 0;
}

192 193 194 195 196 197 198 199
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) {
200 201 202 203
	case KVM_CAP_S390_IRQCHIP:
		kvm->arch.use_irqchip = 1;
		r = 0;
		break;
204 205 206 207 208 209 210
	default:
		r = -EINVAL;
		break;
	}
	return r;
}

211 212 213 214 215 216 217 218
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;
	int r;

	switch (ioctl) {
219 220 221 222 223 224 225 226 227
	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;
	}
228 229 230 231 232 233 234 235
	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;
	}
236 237 238 239 240 241 242 243 244 245 246 247
	case KVM_CREATE_IRQCHIP: {
		struct kvm_irq_routing_entry routing;

		r = -EINVAL;
		if (kvm->arch.use_irqchip) {
			/* Set up dummy routing. */
			memset(&routing, 0, sizeof(routing));
			kvm_set_irq_routing(kvm, &routing, 0, 0);
			r = 0;
		}
		break;
	}
248
	default:
249
		r = -ENOTTY;
250 251 252 253 254
	}

	return r;
}

255
int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
256 257 258
{
	int rc;
	char debug_name[16];
259
	static unsigned long sca_offset;
260

261 262 263 264 265 266 267 268 269 270 271
	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

272 273
	rc = s390_enable_sie();
	if (rc)
274
		goto out_err;
275

276 277
	rc = -ENOMEM;

278 279
	kvm->arch.sca = (struct sca_block *) get_zeroed_page(GFP_KERNEL);
	if (!kvm->arch.sca)
280
		goto out_err;
281 282 283 284
	spin_lock(&kvm_lock);
	sca_offset = (sca_offset + 16) & 0x7f0;
	kvm->arch.sca = (struct sca_block *) ((char *) kvm->arch.sca + sca_offset);
	spin_unlock(&kvm_lock);
285 286 287 288 289 290 291

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

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

292 293 294
	spin_lock_init(&kvm->arch.float_int.lock);
	INIT_LIST_HEAD(&kvm->arch.float_int.list);

295 296 297
	debug_register_view(kvm->arch.dbf, &debug_sprintf_view);
	VM_EVENT(kvm, 3, "%s", "vm created");

298 299 300 301 302 303
	if (type & KVM_VM_S390_UCONTROL) {
		kvm->arch.gmap = NULL;
	} else {
		kvm->arch.gmap = gmap_alloc(current->mm);
		if (!kvm->arch.gmap)
			goto out_nogmap;
304
		kvm->arch.gmap->private = kvm;
305
		kvm->arch.gmap->pfault_enabled = 0;
306
	}
307 308

	kvm->arch.css_support = 0;
309
	kvm->arch.use_irqchip = 0;
310

311
	return 0;
312 313
out_nogmap:
	debug_unregister(kvm->arch.dbf);
314 315
out_nodbf:
	free_page((unsigned long)(kvm->arch.sca));
316 317
out_err:
	return rc;
318 319
}

320 321 322
void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
{
	VCPU_EVENT(vcpu, 3, "%s", "free cpu");
323
	trace_kvm_s390_destroy_vcpu(vcpu->vcpu_id);
324
	kvm_clear_async_pf_completion_queue(vcpu);
C
Carsten Otte 已提交
325 326 327 328 329 330 331
	if (!kvm_is_ucontrol(vcpu->kvm)) {
		clear_bit(63 - vcpu->vcpu_id,
			  (unsigned long *) &vcpu->kvm->arch.sca->mcn);
		if (vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sda ==
		    (__u64) vcpu->arch.sie_block)
			vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sda = 0;
	}
332
	smp_mb();
333 334 335 336

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

337 338 339
	if (vcpu->arch.sie_block->cbrlo)
		__free_page(__pfn_to_page(
				vcpu->arch.sie_block->cbrlo >> PAGE_SHIFT));
340
	free_page((unsigned long)(vcpu->arch.sie_block));
341

342
	kvm_vcpu_uninit(vcpu);
343
	kmem_cache_free(kvm_vcpu_cache, vcpu);
344 345 346 347 348
}

static void kvm_free_vcpus(struct kvm *kvm)
{
	unsigned int i;
349
	struct kvm_vcpu *vcpu;
350

351 352 353 354 355 356 357 358 359
	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);
360 361
}

362 363 364 365
void kvm_arch_sync_events(struct kvm *kvm)
{
}

366 367
void kvm_arch_destroy_vm(struct kvm *kvm)
{
368
	kvm_free_vcpus(kvm);
369
	free_page((unsigned long)(kvm->arch.sca));
370
	debug_unregister(kvm->arch.dbf);
371 372
	if (!kvm_is_ucontrol(kvm))
		gmap_free(kvm->arch.gmap);
373
	kvm_s390_destroy_adapters(kvm);
374 375 376 377 378
}

/* Section: vcpu related */
int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
{
379 380
	vcpu->arch.pfault_token = KVM_S390_PFAULT_TOKEN_INVALID;
	kvm_clear_async_pf_completion_queue(vcpu);
381 382 383 384
	if (kvm_is_ucontrol(vcpu->kvm)) {
		vcpu->arch.gmap = gmap_alloc(current->mm);
		if (!vcpu->arch.gmap)
			return -ENOMEM;
385
		vcpu->arch.gmap->private = vcpu->kvm;
386 387 388
		return 0;
	}

389
	vcpu->arch.gmap = vcpu->kvm->arch.gmap;
390 391
	vcpu->run->kvm_valid_regs = KVM_SYNC_PREFIX |
				    KVM_SYNC_GPRS |
392 393
				    KVM_SYNC_ACRS |
				    KVM_SYNC_CRS;
394 395 396 397 398
	return 0;
}

void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu)
{
399
	/* Nothing todo */
400 401 402 403
}

void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
{
404 405
	save_fp_ctl(&vcpu->arch.host_fpregs.fpc);
	save_fp_regs(vcpu->arch.host_fpregs.fprs);
406
	save_access_regs(vcpu->arch.host_acrs);
407 408
	restore_fp_ctl(&vcpu->arch.guest_fpregs.fpc);
	restore_fp_regs(vcpu->arch.guest_fpregs.fprs);
409
	restore_access_regs(vcpu->run->s.regs.acrs);
410
	gmap_enable(vcpu->arch.gmap);
411
	atomic_set_mask(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
412 413 414 415
}

void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
{
416
	atomic_clear_mask(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
417
	gmap_disable(vcpu->arch.gmap);
418 419
	save_fp_ctl(&vcpu->arch.guest_fpregs.fpc);
	save_fp_regs(vcpu->arch.guest_fpregs.fprs);
420
	save_access_regs(vcpu->run->s.regs.acrs);
421 422
	restore_fp_ctl(&vcpu->arch.host_fpregs.fpc);
	restore_fp_regs(vcpu->arch.host_fpregs.fprs);
423 424 425 426 427 428 429 430
	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;
431
	kvm_s390_set_prefix(vcpu, 0);
432 433 434 435 436 437 438 439 440
	vcpu->arch.sie_block->cputm     = 0UL;
	vcpu->arch.sie_block->ckc       = 0UL;
	vcpu->arch.sie_block->todpr     = 0;
	memset(vcpu->arch.sie_block->gcr, 0, 16 * sizeof(__u64));
	vcpu->arch.sie_block->gcr[0]  = 0xE0UL;
	vcpu->arch.sie_block->gcr[14] = 0xC2000000UL;
	vcpu->arch.guest_fpregs.fpc = 0;
	asm volatile("lfpc %0" : : "Q" (vcpu->arch.guest_fpregs.fpc));
	vcpu->arch.sie_block->gbea = 1;
441
	vcpu->arch.sie_block->pp = 0;
442 443
	vcpu->arch.pfault_token = KVM_S390_PFAULT_TOKEN_INVALID;
	kvm_clear_async_pf_completion_queue(vcpu);
444
	atomic_set_mask(CPUSTAT_STOPPED, &vcpu->arch.sie_block->cpuflags);
445
	kvm_s390_clear_local_irqs(vcpu);
446 447
}

448 449 450 451 452
int kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
{
	return 0;
}

453 454
int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
{
455 456
	struct page *cbrl;

457 458
	atomic_set(&vcpu->arch.sie_block->cpuflags, CPUSTAT_ZARCH |
						    CPUSTAT_SM |
459 460
						    CPUSTAT_STOPPED |
						    CPUSTAT_GED);
461
	vcpu->arch.sie_block->ecb   = 6;
462 463 464
	if (test_vfacility(50) && test_vfacility(73))
		vcpu->arch.sie_block->ecb |= 0x10;

465
	vcpu->arch.sie_block->ecb2  = 8;
466
	vcpu->arch.sie_block->eca   = 0xC1002001U;
467
	vcpu->arch.sie_block->fac   = (int) (long) vfacilities;
468
	vcpu->arch.sie_block->ictl |= ICTL_ISKE | ICTL_SSKE | ICTL_RRBE;
469 470 471 472 473 474 475 476
	if (kvm_enabled_cmma()) {
		cbrl = alloc_page(GFP_KERNEL | __GFP_ZERO);
		if (cbrl) {
			vcpu->arch.sie_block->ecb2 |= 0x80;
			vcpu->arch.sie_block->ecb2 &= ~0x08;
			vcpu->arch.sie_block->cbrlo = page_to_phys(cbrl);
		}
	}
477 478 479 480
	hrtimer_init(&vcpu->arch.ckc_timer, CLOCK_REALTIME, HRTIMER_MODE_ABS);
	tasklet_init(&vcpu->arch.tasklet, kvm_s390_tasklet,
		     (unsigned long) vcpu);
	vcpu->arch.ckc_timer.function = kvm_s390_idle_wakeup;
481
	get_cpu_id(&vcpu->arch.cpu_id);
482
	vcpu->arch.cpu_id.version = 0xff;
483 484 485 486 487 488
	return 0;
}

struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
				      unsigned int id)
{
489
	struct kvm_vcpu *vcpu;
490
	struct sie_page *sie_page;
491 492 493 494 495 496
	int rc = -EINVAL;

	if (id >= KVM_MAX_VCPUS)
		goto out;

	rc = -ENOMEM;
497

498
	vcpu = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL);
499
	if (!vcpu)
500
		goto out;
501

502 503
	sie_page = (struct sie_page *) get_zeroed_page(GFP_KERNEL);
	if (!sie_page)
504 505
		goto out_free_cpu;

506 507 508
	vcpu->arch.sie_block = &sie_page->sie_block;
	vcpu->arch.sie_block->itdba = (unsigned long) &sie_page->itdb;

509
	vcpu->arch.sie_block->icpua = id;
C
Carsten Otte 已提交
510 511 512 513 514 515 516 517 518 519 520 521 522
	if (!kvm_is_ucontrol(kvm)) {
		if (!kvm->arch.sca) {
			WARN_ON_ONCE(1);
			goto out_free_cpu;
		}
		if (!kvm->arch.sca->cpu[id].sda)
			kvm->arch.sca->cpu[id].sda =
				(__u64) vcpu->arch.sie_block;
		vcpu->arch.sie_block->scaoh =
			(__u32)(((__u64)kvm->arch.sca) >> 32);
		vcpu->arch.sie_block->scaol = (__u32)(__u64)kvm->arch.sca;
		set_bit(63 - id, (unsigned long *) &kvm->arch.sca->mcn);
	}
523

524 525 526
	spin_lock_init(&vcpu->arch.local_int.lock);
	INIT_LIST_HEAD(&vcpu->arch.local_int.list);
	vcpu->arch.local_int.float_int = &kvm->arch.float_int;
527
	vcpu->arch.local_int.wq = &vcpu->wq;
528
	vcpu->arch.local_int.cpuflags = &vcpu->arch.sie_block->cpuflags;
529

530 531
	rc = kvm_vcpu_init(vcpu, kvm, id);
	if (rc)
532
		goto out_free_sie_block;
533 534
	VM_EVENT(kvm, 3, "create cpu %d at %p, sie block at %p", id, vcpu,
		 vcpu->arch.sie_block);
535
	trace_kvm_s390_create_vcpu(id, vcpu, vcpu->arch.sie_block);
536 537

	return vcpu;
538 539
out_free_sie_block:
	free_page((unsigned long)(vcpu->arch.sie_block));
540
out_free_cpu:
541
	kmem_cache_free(kvm_vcpu_cache, vcpu);
542
out:
543 544 545 546 547
	return ERR_PTR(rc);
}

int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
{
548
	return kvm_cpu_has_interrupt(vcpu);
549 550
}

551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578
void s390_vcpu_block(struct kvm_vcpu *vcpu)
{
	atomic_set_mask(PROG_BLOCK_SIE, &vcpu->arch.sie_block->prog20);
}

void s390_vcpu_unblock(struct kvm_vcpu *vcpu)
{
	atomic_clear_mask(PROG_BLOCK_SIE, &vcpu->arch.sie_block->prog20);
}

/*
 * Kick a guest cpu out of SIE and wait until SIE is not running.
 * If the CPU is not running (e.g. waiting as idle) the function will
 * return immediately. */
void exit_sie(struct kvm_vcpu *vcpu)
{
	atomic_set_mask(CPUSTAT_STOP_INT, &vcpu->arch.sie_block->cpuflags);
	while (vcpu->arch.sie_block->prog0c & PROG_IN_SIE)
		cpu_relax();
}

/* Kick a guest cpu out of SIE and prevent SIE-reentry */
void exit_sie_sync(struct kvm_vcpu *vcpu)
{
	s390_vcpu_block(vcpu);
	exit_sie(vcpu);
}

579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594
static void kvm_gmap_notifier(struct gmap *gmap, unsigned long address)
{
	int i;
	struct kvm *kvm = gmap->private;
	struct kvm_vcpu *vcpu;

	kvm_for_each_vcpu(i, vcpu, kvm) {
		/* match against both prefix pages */
		if (vcpu->arch.sie_block->prefix == (address & ~0x1000UL)) {
			VCPU_EVENT(vcpu, 2, "gmap notifier for %lx", address);
			kvm_make_request(KVM_REQ_MMU_RELOAD, vcpu);
			exit_sie_sync(vcpu);
		}
	}
}

595 596 597 598 599 600 601
int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu)
{
	/* kvm common code refers to this, but never calls it */
	BUG();
	return 0;
}

602 603 604 605 606 607
static int kvm_arch_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu,
					   struct kvm_one_reg *reg)
{
	int r = -EINVAL;

	switch (reg->id) {
608 609 610 611 612 613 614 615
	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;
616 617 618 619 620 621 622 623
	case KVM_REG_S390_CPU_TIMER:
		r = put_user(vcpu->arch.sie_block->cputm,
			     (u64 __user *)reg->addr);
		break;
	case KVM_REG_S390_CLOCK_COMP:
		r = put_user(vcpu->arch.sie_block->ckc,
			     (u64 __user *)reg->addr);
		break;
624 625 626 627 628 629 630 631 632 633 634 635
	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;
636 637 638 639
	case KVM_REG_S390_PP:
		r = put_user(vcpu->arch.sie_block->pp,
			     (u64 __user *)reg->addr);
		break;
640 641 642 643
	case KVM_REG_S390_GBEA:
		r = put_user(vcpu->arch.sie_block->gbea,
			     (u64 __user *)reg->addr);
		break;
644 645 646 647 648 649 650 651 652 653 654 655 656
	default:
		break;
	}

	return r;
}

static int kvm_arch_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu,
					   struct kvm_one_reg *reg)
{
	int r = -EINVAL;

	switch (reg->id) {
657 658 659 660 661 662 663 664
	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;
665 666 667 668 669 670 671 672
	case KVM_REG_S390_CPU_TIMER:
		r = get_user(vcpu->arch.sie_block->cputm,
			     (u64 __user *)reg->addr);
		break;
	case KVM_REG_S390_CLOCK_COMP:
		r = get_user(vcpu->arch.sie_block->ckc,
			     (u64 __user *)reg->addr);
		break;
673 674 675 676 677 678 679 680 681 682 683 684
	case KVM_REG_S390_PFTOKEN:
		r = get_user(vcpu->arch.pfault_token,
			     (u64 __user *)reg->addr);
		break;
	case KVM_REG_S390_PFCOMPARE:
		r = get_user(vcpu->arch.pfault_compare,
			     (u64 __user *)reg->addr);
		break;
	case KVM_REG_S390_PFSELECT:
		r = get_user(vcpu->arch.pfault_select,
			     (u64 __user *)reg->addr);
		break;
685 686 687 688
	case KVM_REG_S390_PP:
		r = get_user(vcpu->arch.sie_block->pp,
			     (u64 __user *)reg->addr);
		break;
689 690 691 692
	case KVM_REG_S390_GBEA:
		r = get_user(vcpu->arch.sie_block->gbea,
			     (u64 __user *)reg->addr);
		break;
693 694 695 696 697 698
	default:
		break;
	}

	return r;
}
699

700 701 702 703 704 705 706 707
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)
{
708
	memcpy(&vcpu->run->s.regs.gprs, &regs->gprs, sizeof(regs->gprs));
709 710 711 712 713
	return 0;
}

int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
{
714
	memcpy(&regs->gprs, &vcpu->run->s.regs.gprs, sizeof(regs->gprs));
715 716 717 718 719 720
	return 0;
}

int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
				  struct kvm_sregs *sregs)
{
721
	memcpy(&vcpu->run->s.regs.acrs, &sregs->acrs, sizeof(sregs->acrs));
722
	memcpy(&vcpu->arch.sie_block->gcr, &sregs->crs, sizeof(sregs->crs));
723
	restore_access_regs(vcpu->run->s.regs.acrs);
724 725 726 727 728 729
	return 0;
}

int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
				  struct kvm_sregs *sregs)
{
730
	memcpy(&sregs->acrs, &vcpu->run->s.regs.acrs, sizeof(sregs->acrs));
731 732 733 734 735 736
	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)
{
737 738
	if (test_fp_ctl(fpu->fpc))
		return -EINVAL;
739
	memcpy(&vcpu->arch.guest_fpregs.fprs, &fpu->fprs, sizeof(fpu->fprs));
740 741 742
	vcpu->arch.guest_fpregs.fpc = fpu->fpc;
	restore_fp_ctl(&vcpu->arch.guest_fpregs.fpc);
	restore_fp_regs(vcpu->arch.guest_fpregs.fprs);
743 744 745 746 747 748 749 750 751 752 753 754 755 756
	return 0;
}

int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
{
	memcpy(&fpu->fprs, &vcpu->arch.guest_fpregs.fprs, sizeof(fpu->fprs));
	fpu->fpc = vcpu->arch.guest_fpregs.fpc;
	return 0;
}

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

757
	if (!(atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_STOPPED))
758
		rc = -EBUSY;
759 760 761 762
	else {
		vcpu->run->psw_mask = psw.mask;
		vcpu->run->psw_addr = psw.addr;
	}
763 764 765 766 767 768 769 770 771
	return rc;
}

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

J
Jan Kiszka 已提交
772 773
int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
					struct kvm_guest_debug *dbg)
774 775 776 777
{
	return -EINVAL; /* not implemented yet */
}

778 779 780 781 782 783 784 785 786 787 788 789
int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
				    struct kvm_mp_state *mp_state)
{
	return -EINVAL; /* not implemented yet */
}

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

790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810
static int kvm_s390_handle_requests(struct kvm_vcpu *vcpu)
{
	/*
	 * 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.
	 */
	while (kvm_check_request(KVM_REQ_MMU_RELOAD, vcpu)) {
		int rc;
		rc = gmap_ipte_notify(vcpu->arch.gmap,
				      vcpu->arch.sie_block->prefix,
				      PAGE_SIZE * 2);
		if (rc)
			return rc;
		s390_vcpu_unblock(vcpu);
	}
	return 0;
}

811 812 813 814 815 816 817 818 819 820 821
static long kvm_arch_fault_in_sync(struct kvm_vcpu *vcpu)
{
	long rc;
	hva_t fault = gmap_fault(current->thread.gmap_addr, vcpu->arch.gmap);
	struct mm_struct *mm = current->mm;
	down_read(&mm->mmap_sem);
	rc = get_user_pages(current, mm, fault, 1, 1, 0, NULL, NULL);
	up_read(&mm->mmap_sem);
	return rc;
}

822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893
static void __kvm_inject_pfault_token(struct kvm_vcpu *vcpu, bool start_token,
				      unsigned long token)
{
	struct kvm_s390_interrupt inti;
	inti.parm64 = token;

	if (start_token) {
		inti.type = KVM_S390_INT_PFAULT_INIT;
		WARN_ON_ONCE(kvm_s390_inject_vcpu(vcpu, &inti));
	} else {
		inti.type = KVM_S390_INT_PFAULT_DONE;
		WARN_ON_ONCE(kvm_s390_inject_vm(vcpu->kvm, &inti));
	}
}

void kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu,
				     struct kvm_async_pf *work)
{
	trace_kvm_s390_pfault_init(vcpu, work->arch.pfault_token);
	__kvm_inject_pfault_token(vcpu, true, work->arch.pfault_token);
}

void kvm_arch_async_page_present(struct kvm_vcpu *vcpu,
				 struct kvm_async_pf *work)
{
	trace_kvm_s390_pfault_done(vcpu, work->arch.pfault_token);
	__kvm_inject_pfault_token(vcpu, false, work->arch.pfault_token);
}

void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu,
			       struct kvm_async_pf *work)
{
	/* s390 will always inject the page directly */
}

bool kvm_arch_can_inject_async_page_present(struct kvm_vcpu *vcpu)
{
	/*
	 * s390 will always inject the page directly,
	 * but we still want check_async_completion to cleanup
	 */
	return true;
}

static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu)
{
	hva_t hva;
	struct kvm_arch_async_pf arch;
	int rc;

	if (vcpu->arch.pfault_token == KVM_S390_PFAULT_TOKEN_INVALID)
		return 0;
	if ((vcpu->arch.sie_block->gpsw.mask & vcpu->arch.pfault_select) !=
	    vcpu->arch.pfault_compare)
		return 0;
	if (psw_extint_disabled(vcpu))
		return 0;
	if (kvm_cpu_has_interrupt(vcpu))
		return 0;
	if (!(vcpu->arch.sie_block->gcr[0] & 0x200ul))
		return 0;
	if (!vcpu->arch.gmap->pfault_enabled)
		return 0;

	hva = gmap_fault(current->thread.gmap_addr, vcpu->arch.gmap);
	if (copy_from_guest(vcpu, &arch.pfault_token, vcpu->arch.pfault_token, 8))
		return 0;

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

894
static int vcpu_pre_run(struct kvm_vcpu *vcpu)
895
{
896
	int rc, cpuflags;
897

898 899 900 901 902 903 904
	/*
	 * 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);

905
	memcpy(&vcpu->arch.sie_block->gg14, &vcpu->run->s.regs.gprs[14], 16);
906 907 908 909

	if (need_resched())
		schedule();

910 911 912
	if (test_thread_flag(TIF_MCCK_PENDING))
		s390_handle_mcck();

913 914
	if (!kvm_is_ucontrol(vcpu->kvm))
		kvm_s390_deliver_pending_interrupts(vcpu);
C
Carsten Otte 已提交
915

916 917 918 919
	rc = kvm_s390_handle_requests(vcpu);
	if (rc)
		return rc;

920
	vcpu->arch.sie_block->icptcode = 0;
921 922 923
	cpuflags = atomic_read(&vcpu->arch.sie_block->cpuflags);
	VCPU_EVENT(vcpu, 6, "entering sie flags %x", cpuflags);
	trace_kvm_s390_sie_enter(vcpu, cpuflags);
924

925 926 927 928 929
	return 0;
}

static int vcpu_post_run(struct kvm_vcpu *vcpu, int exit_reason)
{
930
	int rc = -1;
931 932 933 934 935

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

936
	if (exit_reason >= 0) {
937
		rc = 0;
938 939 940 941 942 943
	} else if (kvm_is_ucontrol(vcpu->kvm)) {
		vcpu->run->exit_reason = KVM_EXIT_S390_UCONTROL;
		vcpu->run->s390_ucontrol.trans_exc_code =
						current->thread.gmap_addr;
		vcpu->run->s390_ucontrol.pgm_code = 0x10;
		rc = -EREMOTE;
944 945

	} else if (current->thread.gmap_pfault) {
946
		trace_kvm_s390_major_guest_pfault(vcpu);
947
		current->thread.gmap_pfault = 0;
948 949
		if (kvm_arch_setup_async_pf(vcpu) ||
		    (kvm_arch_fault_in_sync(vcpu) >= 0))
950 951 952 953
			rc = 0;
	}

	if (rc == -1) {
954 955 956
		VCPU_EVENT(vcpu, 3, "%s", "fault in sie instruction");
		trace_kvm_s390_sie_fault(vcpu);
		rc = kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
957
	}
958

959
	memcpy(&vcpu->run->s.regs.gprs[14], &vcpu->arch.sie_block->gg14, 16);
960

961 962
	if (rc == 0) {
		if (kvm_is_ucontrol(vcpu->kvm))
963 964
			/* Don't exit for host interrupts. */
			rc = vcpu->arch.sie_block->icptcode ? -EOPNOTSUPP : 0;
965 966 967 968
		else
			rc = kvm_handle_sie_intercept(vcpu);
	}

969 970 971
	return rc;
}

972 973 974 975 976 977 978 979 980 981
bool kvm_enabled_cmma(void)
{
	if (!MACHINE_IS_LPAR)
		return false;
	/* only enable for z10 and later */
	if (!MACHINE_HAS_EDAT1)
		return false;
	return true;
}

982 983 984 985
static int __vcpu_run(struct kvm_vcpu *vcpu)
{
	int rc, exit_reason;

986 987 988 989 990 991
	/*
	 * 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);

992 993 994 995
	do {
		rc = vcpu_pre_run(vcpu);
		if (rc)
			break;
996

997
		srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
998 999 1000 1001 1002 1003 1004 1005 1006 1007
		/*
		 * As PF_VCPU will be used in fault handler, between
		 * guest_enter and guest_exit should be no uaccess.
		 */
		preempt_disable();
		kvm_guest_enter();
		preempt_enable();
		exit_reason = sie64a(vcpu->arch.sie_block,
				     vcpu->run->s.regs.gprs);
		kvm_guest_exit();
1008
		vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
1009 1010 1011

		rc = vcpu_post_run(vcpu, exit_reason);
	} while (!signal_pending(current) && !rc);
1012

1013
	srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
1014
	return rc;
1015 1016 1017 1018
}

int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
{
1019
	int rc;
1020 1021 1022 1023 1024
	sigset_t sigsaved;

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

1025
	atomic_clear_mask(CPUSTAT_STOPPED, &vcpu->arch.sie_block->cpuflags);
1026

1027 1028 1029
	switch (kvm_run->exit_reason) {
	case KVM_EXIT_S390_SIEIC:
	case KVM_EXIT_UNKNOWN:
1030
	case KVM_EXIT_INTR:
1031
	case KVM_EXIT_S390_RESET:
1032
	case KVM_EXIT_S390_UCONTROL:
1033
	case KVM_EXIT_S390_TSCH:
1034 1035 1036 1037 1038
		break;
	default:
		BUG();
	}

1039 1040
	vcpu->arch.sie_block->gpsw.mask = kvm_run->psw_mask;
	vcpu->arch.sie_block->gpsw.addr = kvm_run->psw_addr;
1041 1042 1043 1044
	if (kvm_run->kvm_dirty_regs & KVM_SYNC_PREFIX) {
		kvm_run->kvm_dirty_regs &= ~KVM_SYNC_PREFIX;
		kvm_s390_set_prefix(vcpu, kvm_run->s.regs.prefix);
	}
1045 1046 1047 1048 1049
	if (kvm_run->kvm_dirty_regs & KVM_SYNC_CRS) {
		kvm_run->kvm_dirty_regs &= ~KVM_SYNC_CRS;
		memcpy(&vcpu->arch.sie_block->gcr, &kvm_run->s.regs.crs, 128);
		kvm_s390_set_prefix(vcpu, kvm_run->s.regs.prefix);
	}
1050

1051
	might_fault();
1052
	rc = __vcpu_run(vcpu);
1053

1054 1055
	if (signal_pending(current) && !rc) {
		kvm_run->exit_reason = KVM_EXIT_INTR;
1056
		rc = -EINTR;
1057
	}
1058

1059
	if (rc == -EOPNOTSUPP) {
1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072
		/* intercept cannot be handled in-kernel, prepare kvm-run */
		kvm_run->exit_reason         = KVM_EXIT_S390_SIEIC;
		kvm_run->s390_sieic.icptcode = vcpu->arch.sie_block->icptcode;
		kvm_run->s390_sieic.ipa      = vcpu->arch.sie_block->ipa;
		kvm_run->s390_sieic.ipb      = vcpu->arch.sie_block->ipb;
		rc = 0;
	}

	if (rc == -EREMOTE) {
		/* intercept was handled, but userspace support is needed
		 * kvm_run has been prepared by the handler */
		rc = 0;
	}
1073

1074 1075
	kvm_run->psw_mask     = vcpu->arch.sie_block->gpsw.mask;
	kvm_run->psw_addr     = vcpu->arch.sie_block->gpsw.addr;
1076
	kvm_run->s.regs.prefix = vcpu->arch.sie_block->prefix;
1077
	memcpy(&kvm_run->s.regs.crs, &vcpu->arch.sie_block->gcr, 128);
1078

1079 1080 1081 1082
	if (vcpu->sigset_active)
		sigprocmask(SIG_SETMASK, &sigsaved, NULL);

	vcpu->stat.exit_userspace++;
1083
	return rc;
1084 1085
}

1086
static int __guestcopy(struct kvm_vcpu *vcpu, u64 guestdest, void *from,
1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100
		       unsigned long n, int prefix)
{
	if (prefix)
		return copy_to_guest(vcpu, guestdest, from, n);
	else
		return copy_to_guest_absolute(vcpu, guestdest, from, n);
}

/*
 * 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
 */
1101
int kvm_s390_store_status_unloaded(struct kvm_vcpu *vcpu, unsigned long addr)
1102
{
1103
	unsigned char archmode = 1;
1104
	int prefix;
1105
	u64 clkcomp;
1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119

	if (addr == KVM_S390_STORE_STATUS_NOADDR) {
		if (copy_to_guest_absolute(vcpu, 163ul, &archmode, 1))
			return -EFAULT;
		addr = SAVE_AREA_BASE;
		prefix = 0;
	} else if (addr == KVM_S390_STORE_STATUS_PREFIXED) {
		if (copy_to_guest(vcpu, 163ul, &archmode, 1))
			return -EFAULT;
		addr = SAVE_AREA_BASE;
		prefix = 1;
	} else
		prefix = 0;

1120
	if (__guestcopy(vcpu, addr + offsetof(struct save_area, fp_regs),
1121 1122 1123
			vcpu->arch.guest_fpregs.fprs, 128, prefix))
		return -EFAULT;

1124
	if (__guestcopy(vcpu, addr + offsetof(struct save_area, gp_regs),
1125
			vcpu->run->s.regs.gprs, 128, prefix))
1126 1127
		return -EFAULT;

1128
	if (__guestcopy(vcpu, addr + offsetof(struct save_area, psw),
1129 1130 1131
			&vcpu->arch.sie_block->gpsw, 16, prefix))
		return -EFAULT;

1132
	if (__guestcopy(vcpu, addr + offsetof(struct save_area, pref_reg),
1133 1134 1135 1136
			&vcpu->arch.sie_block->prefix, 4, prefix))
		return -EFAULT;

	if (__guestcopy(vcpu,
1137
			addr + offsetof(struct save_area, fp_ctrl_reg),
1138 1139 1140
			&vcpu->arch.guest_fpregs.fpc, 4, prefix))
		return -EFAULT;

1141
	if (__guestcopy(vcpu, addr + offsetof(struct save_area, tod_reg),
1142 1143 1144
			&vcpu->arch.sie_block->todpr, 4, prefix))
		return -EFAULT;

1145
	if (__guestcopy(vcpu, addr + offsetof(struct save_area, timer),
1146 1147 1148
			&vcpu->arch.sie_block->cputm, 8, prefix))
		return -EFAULT;

1149
	clkcomp = vcpu->arch.sie_block->ckc >> 8;
1150
	if (__guestcopy(vcpu, addr + offsetof(struct save_area, clk_cmp),
1151
			&clkcomp, 8, prefix))
1152 1153
		return -EFAULT;

1154
	if (__guestcopy(vcpu, addr + offsetof(struct save_area, acc_regs),
1155
			&vcpu->run->s.regs.acrs, 64, prefix))
1156 1157 1158
		return -EFAULT;

	if (__guestcopy(vcpu,
1159
			addr + offsetof(struct save_area, ctrl_regs),
1160 1161 1162 1163 1164
			&vcpu->arch.sie_block->gcr, 128, prefix))
		return -EFAULT;
	return 0;
}

1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178
int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr)
{
	/*
	 * The guest FPRS and ACRS are in the host FPRS/ACRS due to the lazy
	 * copying in vcpu load/put. Lets update our copies before we save
	 * it into the save area
	 */
	save_fp_ctl(&vcpu->arch.guest_fpregs.fpc);
	save_fp_regs(vcpu->arch.guest_fpregs.fprs);
	save_access_regs(vcpu->run->s.regs.acrs);

	return kvm_s390_store_status_unloaded(vcpu, addr);
}

1179 1180 1181 1182 1183 1184 1185 1186 1187
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) {
1188 1189 1190 1191 1192 1193 1194
	case KVM_CAP_S390_CSS_SUPPORT:
		if (!vcpu->kvm->arch.css_support) {
			vcpu->kvm->arch.css_support = 1;
			trace_kvm_s390_enable_css(vcpu->kvm);
		}
		r = 0;
		break;
1195 1196 1197 1198 1199 1200 1201
	default:
		r = -EINVAL;
		break;
	}
	return r;
}

1202 1203 1204 1205 1206
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;
1207
	int idx;
1208
	long r;
1209

1210 1211
	switch (ioctl) {
	case KVM_S390_INTERRUPT: {
1212 1213
		struct kvm_s390_interrupt s390int;

1214
		r = -EFAULT;
1215
		if (copy_from_user(&s390int, argp, sizeof(s390int)))
1216 1217 1218
			break;
		r = kvm_s390_inject_vcpu(vcpu, &s390int);
		break;
1219
	}
1220
	case KVM_S390_STORE_STATUS:
1221
		idx = srcu_read_lock(&vcpu->kvm->srcu);
1222
		r = kvm_s390_vcpu_store_status(vcpu, arg);
1223
		srcu_read_unlock(&vcpu->kvm->srcu, idx);
1224
		break;
1225 1226 1227
	case KVM_S390_SET_INITIAL_PSW: {
		psw_t psw;

1228
		r = -EFAULT;
1229
		if (copy_from_user(&psw, argp, sizeof(psw)))
1230 1231 1232
			break;
		r = kvm_arch_vcpu_ioctl_set_initial_psw(vcpu, psw);
		break;
1233 1234
	}
	case KVM_S390_INITIAL_RESET:
1235 1236
		r = kvm_arch_vcpu_ioctl_initial_reset(vcpu);
		break;
1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248
	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;
	}
1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284
#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
1285 1286 1287 1288 1289 1290
	case KVM_S390_VCPU_FAULT: {
		r = gmap_fault(arg, vcpu->arch.gmap);
		if (!IS_ERR_VALUE(r))
			r = 0;
		break;
	}
1291 1292 1293 1294 1295 1296 1297 1298 1299
	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;
	}
1300
	default:
1301
		r = -ENOTTY;
1302
	}
1303
	return r;
1304 1305
}

1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318
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;
}

1319
void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free,
1320 1321 1322 1323
			   struct kvm_memory_slot *dont)
{
}

1324 1325
int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
			    unsigned long npages)
1326 1327 1328 1329
{
	return 0;
}

1330 1331 1332 1333
void kvm_arch_memslots_updated(struct kvm *kvm)
{
}

1334
/* Section: memory related */
1335 1336
int kvm_arch_prepare_memory_region(struct kvm *kvm,
				   struct kvm_memory_slot *memslot,
1337 1338
				   struct kvm_userspace_memory_region *mem,
				   enum kvm_mr_change change)
1339
{
1340 1341 1342 1343
	/* 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 */
1344

1345
	if (mem->userspace_addr & 0xffffful)
1346 1347
		return -EINVAL;

1348
	if (mem->memory_size & 0xffffful)
1349 1350
		return -EINVAL;

1351 1352 1353 1354 1355
	return 0;
}

void kvm_arch_commit_memory_region(struct kvm *kvm,
				struct kvm_userspace_memory_region *mem,
1356 1357
				const struct kvm_memory_slot *old,
				enum kvm_mr_change change)
1358
{
1359
	int rc;
1360

1361 1362 1363 1364 1365 1366 1367 1368 1369 1370
	/* 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;
1371 1372 1373 1374

	rc = gmap_map_segment(kvm->arch.gmap, mem->userspace_addr,
		mem->guest_phys_addr, mem->memory_size);
	if (rc)
1375
		printk(KERN_WARNING "kvm-s390: failed to commit memory region\n");
1376
	return;
1377 1378
}

1379 1380 1381 1382 1383 1384
void kvm_arch_flush_shadow_all(struct kvm *kvm)
{
}

void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
				   struct kvm_memory_slot *slot)
1385 1386 1387
{
}

1388 1389
static int __init kvm_s390_init(void)
{
1390
	int ret;
1391
	ret = kvm_init(NULL, sizeof(struct kvm_vcpu), 0, THIS_MODULE);
1392 1393 1394 1395 1396
	if (ret)
		return ret;

	/*
	 * guests can ask for up to 255+1 double words, we need a full page
L
Lucas De Marchi 已提交
1397
	 * to hold the maximum amount of facilities. On the other hand, we
1398 1399
	 * only set facilities that are known to work in KVM.
	 */
1400 1401
	vfacilities = (unsigned long *) get_zeroed_page(GFP_KERNEL|GFP_DMA);
	if (!vfacilities) {
1402 1403 1404
		kvm_exit();
		return -ENOMEM;
	}
1405
	memcpy(vfacilities, S390_lowcore.stfle_fac_list, 16);
1406
	vfacilities[0] &= 0xff82fff3f4fc2000UL;
1407
	vfacilities[1] &= 0x005c000000000000UL;
1408
	return 0;
1409 1410 1411 1412
}

static void __exit kvm_s390_exit(void)
{
1413
	free_page((unsigned long) vfacilities);
1414 1415 1416 1417 1418
	kvm_exit();
}

module_init(kvm_s390_init);
module_exit(kvm_s390_exit);
1419 1420 1421 1422 1423 1424 1425 1426 1427

/*
 * 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");