kvm-s390.c 39.4 KB
Newer Older
1
/*
2
 * hosting zSeries kernel virtual machines
3
 *
4
 * Copyright IBM Corp. 2008, 2009
5 6 7 8 9 10 11 12
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License (version 2 only)
 * as published by the Free Software Foundation.
 *
 *    Author(s): Carsten Otte <cotte@de.ibm.com>
 *               Christian Borntraeger <borntraeger@de.ibm.com>
 *               Heiko Carstens <heiko.carstens@de.ibm.com>
13
 *               Christian Ehrhardt <ehrhardt@de.ibm.com>
14
 *               Jason J. Herne <jjherne@us.ibm.com>
15 16 17 18 19
 */

#include <linux/compiler.h>
#include <linux/err.h>
#include <linux/fs.h>
20
#include <linux/hrtimer.h>
21 22 23 24 25
#include <linux/init.h>
#include <linux/kvm.h>
#include <linux/kvm_host.h>
#include <linux/module.h>
#include <linux/slab.h>
26
#include <linux/timer.h>
27
#include <asm/asm-offsets.h>
28 29
#include <asm/lowcore.h>
#include <asm/pgtable.h>
30
#include <asm/nmi.h>
31
#include <asm/switch_to.h>
32
#include <asm/facility.h>
33
#include <asm/sclp.h>
34
#include "kvm-s390.h"
35 36
#include "gaccess.h"

37 38
#define CREATE_TRACE_POINTS
#include "trace.h"
39
#include "trace-s390.h"
40

41 42 43 44
#define VCPU_STAT(x) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU

struct kvm_stats_debugfs_item debugfs_entries[] = {
	{ "userspace_handled", VCPU_STAT(exit_userspace) },
45
	{ "exit_null", VCPU_STAT(exit_null) },
46 47 48 49
	{ "exit_validity", VCPU_STAT(exit_validity) },
	{ "exit_stop_request", VCPU_STAT(exit_stop_request) },
	{ "exit_external_request", VCPU_STAT(exit_external_request) },
	{ "exit_external_interrupt", VCPU_STAT(exit_external_interrupt) },
50 51 52
	{ "exit_instruction", VCPU_STAT(exit_instruction) },
	{ "exit_program_interruption", VCPU_STAT(exit_program_interruption) },
	{ "exit_instr_and_program_int", VCPU_STAT(exit_instr_and_program) },
53
	{ "instruction_lctlg", VCPU_STAT(instruction_lctlg) },
54 55
	{ "instruction_lctl", VCPU_STAT(instruction_lctl) },
	{ "deliver_emergency_signal", VCPU_STAT(deliver_emergency_signal) },
56
	{ "deliver_external_call", VCPU_STAT(deliver_external_call) },
57 58 59 60 61 62 63
	{ "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) },
64
	{ "instruction_pfmf", VCPU_STAT(instruction_pfmf) },
65 66 67 68 69
	{ "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) },
70
	{ "instruction_ipte_interlock", VCPU_STAT(instruction_ipte_interlock) },
71 72
	{ "instruction_stsch", VCPU_STAT(instruction_stsch) },
	{ "instruction_chsc", VCPU_STAT(instruction_chsc) },
73
	{ "instruction_essa", VCPU_STAT(instruction_essa) },
74 75
	{ "instruction_stsi", VCPU_STAT(instruction_stsi) },
	{ "instruction_stfl", VCPU_STAT(instruction_stfl) },
76
	{ "instruction_tprot", VCPU_STAT(instruction_tprot) },
77
	{ "instruction_sigp_sense", VCPU_STAT(instruction_sigp_sense) },
78
	{ "instruction_sigp_sense_running", VCPU_STAT(instruction_sigp_sense_running) },
79
	{ "instruction_sigp_external_call", VCPU_STAT(instruction_sigp_external_call) },
80 81 82 83 84
	{ "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) },
85
	{ "diagnose_10", VCPU_STAT(diagnose_10) },
86
	{ "diagnose_44", VCPU_STAT(diagnose_44) },
87
	{ "diagnose_9c", VCPU_STAT(diagnose_9c) },
88 89 90
	{ NULL }
};

91
unsigned long *vfacilities;
92
static struct gmap_notifier gmap_notifier;
93

94
/* test availability of vfacility */
95
int test_vfacility(unsigned long nr)
96 97 98 99
{
	return __test_facility(nr, (void *) vfacilities);
}

100
/* Section: not file related */
101
int kvm_arch_hardware_enable(void *garbage)
102 103
{
	/* every s390 is virtualization enabled ;-) */
104
	return 0;
105 106 107 108 109 110
}

void kvm_arch_hardware_disable(void *garbage)
{
}

111 112
static void kvm_gmap_notifier(struct gmap *gmap, unsigned long address);

113 114
int kvm_arch_hardware_setup(void)
{
115 116
	gmap_notifier.notifier_call = kvm_gmap_notifier;
	gmap_register_ipte_notifier(&gmap_notifier);
117 118 119 120 121
	return 0;
}

void kvm_arch_hardware_unsetup(void)
{
122
	gmap_unregister_ipte_notifier(&gmap_notifier);
123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148
}

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)
{
149 150
	int r;

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

185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203
static void kvm_s390_sync_dirty_log(struct kvm *kvm,
					struct kvm_memory_slot *memslot)
{
	gfn_t cur_gfn, last_gfn;
	unsigned long address;
	struct gmap *gmap = kvm->arch.gmap;

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

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

204 205 206 207 208 209 210
/* 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)
{
211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240
	int r;
	unsigned long n;
	struct kvm_memory_slot *memslot;
	int is_dirty = 0;

	mutex_lock(&kvm->slots_lock);

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

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

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

	/* Clear the dirty log */
	if (is_dirty) {
		n = kvm_dirty_bitmap_bytes(memslot);
		memset(memslot->dirty_bitmap, 0, n);
	}
	r = 0;
out:
	mutex_unlock(&kvm->slots_lock);
	return r;
241 242
}

243 244 245 246 247 248 249 250
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) {
251 252 253 254
	case KVM_CAP_S390_IRQCHIP:
		kvm->arch.use_irqchip = 1;
		r = 0;
		break;
255 256 257 258 259 260 261
	default:
		r = -EINVAL;
		break;
	}
	return r;
}

262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290
static int kvm_s390_mem_control(struct kvm *kvm, struct kvm_device_attr *attr)
{
	int ret;
	unsigned int idx;
	switch (attr->attr) {
	case KVM_S390_VM_MEM_ENABLE_CMMA:
		ret = -EBUSY;
		mutex_lock(&kvm->lock);
		if (atomic_read(&kvm->online_vcpus) == 0) {
			kvm->arch.use_cmma = 1;
			ret = 0;
		}
		mutex_unlock(&kvm->lock);
		break;
	case KVM_S390_VM_MEM_CLR_CMMA:
		mutex_lock(&kvm->lock);
		idx = srcu_read_lock(&kvm->srcu);
		page_table_reset_pgste(kvm->arch.gmap->mm, 0, TASK_SIZE, false);
		srcu_read_unlock(&kvm->srcu, idx);
		mutex_unlock(&kvm->lock);
		ret = 0;
		break;
	default:
		ret = -ENXIO;
		break;
	}
	return ret;
}

291 292 293 294 295
static int kvm_s390_vm_set_attr(struct kvm *kvm, struct kvm_device_attr *attr)
{
	int ret;

	switch (attr->group) {
296 297 298
	case KVM_S390_VM_MEM_CTRL:
		ret = kvm_s390_mem_control(kvm, attr);
		break;
299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316
	default:
		ret = -ENXIO;
		break;
	}

	return ret;
}

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

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

	switch (attr->group) {
317 318 319 320 321 322 323 324 325 326 327
	case KVM_S390_VM_MEM_CTRL:
		switch (attr->attr) {
		case KVM_S390_VM_MEM_ENABLE_CMMA:
		case KVM_S390_VM_MEM_CLR_CMMA:
			ret = 0;
			break;
		default:
			ret = -ENXIO;
			break;
		}
		break;
328 329 330 331 332 333 334 335
	default:
		ret = -ENXIO;
		break;
	}

	return ret;
}

336 337 338 339 340
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;
341
	struct kvm_device_attr attr;
342 343 344
	int r;

	switch (ioctl) {
345 346 347 348 349 350 351 352 353
	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;
	}
354 355 356 357 358 359 360 361
	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;
	}
362 363 364 365 366 367 368 369 370 371 372 373
	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;
	}
374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394
	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;
	}
395
	default:
396
		r = -ENOTTY;
397 398 399 400 401
	}

	return r;
}

402
int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
403 404 405
{
	int rc;
	char debug_name[16];
406
	static unsigned long sca_offset;
407

408 409 410 411 412 413 414 415 416 417 418
	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

419 420
	rc = s390_enable_sie();
	if (rc)
421
		goto out_err;
422

423 424
	rc = -ENOMEM;

425 426
	kvm->arch.sca = (struct sca_block *) get_zeroed_page(GFP_KERNEL);
	if (!kvm->arch.sca)
427
		goto out_err;
428 429 430 431
	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);
432 433 434 435 436 437 438

	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;

439 440
	spin_lock_init(&kvm->arch.float_int.lock);
	INIT_LIST_HEAD(&kvm->arch.float_int.list);
441
	init_waitqueue_head(&kvm->arch.ipte_wq);
442

443 444 445
	debug_register_view(kvm->arch.dbf, &debug_sprintf_view);
	VM_EVENT(kvm, 3, "%s", "vm created");

446 447 448 449 450 451
	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;
452
		kvm->arch.gmap->private = kvm;
453
		kvm->arch.gmap->pfault_enabled = 0;
454
	}
455 456

	kvm->arch.css_support = 0;
457
	kvm->arch.use_irqchip = 0;
458

459
	return 0;
460 461
out_nogmap:
	debug_unregister(kvm->arch.dbf);
462 463
out_nodbf:
	free_page((unsigned long)(kvm->arch.sca));
464 465
out_err:
	return rc;
466 467
}

468 469 470
void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
{
	VCPU_EVENT(vcpu, 3, "%s", "free cpu");
471
	trace_kvm_s390_destroy_vcpu(vcpu->vcpu_id);
472
	kvm_clear_async_pf_completion_queue(vcpu);
C
Carsten Otte 已提交
473 474 475 476 477 478 479
	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;
	}
480
	smp_mb();
481 482 483 484

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

485 486
	if (kvm_s390_cmma_enabled(vcpu->kvm))
		kvm_s390_vcpu_unsetup_cmma(vcpu);
487
	free_page((unsigned long)(vcpu->arch.sie_block));
488

489
	kvm_vcpu_uninit(vcpu);
490
	kmem_cache_free(kvm_vcpu_cache, vcpu);
491 492 493 494 495
}

static void kvm_free_vcpus(struct kvm *kvm)
{
	unsigned int i;
496
	struct kvm_vcpu *vcpu;
497

498 499 500 501 502 503 504 505 506
	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);
507 508
}

509 510 511 512
void kvm_arch_sync_events(struct kvm *kvm)
{
}

513 514
void kvm_arch_destroy_vm(struct kvm *kvm)
{
515
	kvm_free_vcpus(kvm);
516
	free_page((unsigned long)(kvm->arch.sca));
517
	debug_unregister(kvm->arch.dbf);
518 519
	if (!kvm_is_ucontrol(kvm))
		gmap_free(kvm->arch.gmap);
520
	kvm_s390_destroy_adapters(kvm);
521 522 523 524 525
}

/* Section: vcpu related */
int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
{
526 527
	vcpu->arch.pfault_token = KVM_S390_PFAULT_TOKEN_INVALID;
	kvm_clear_async_pf_completion_queue(vcpu);
528 529 530 531
	if (kvm_is_ucontrol(vcpu->kvm)) {
		vcpu->arch.gmap = gmap_alloc(current->mm);
		if (!vcpu->arch.gmap)
			return -ENOMEM;
532
		vcpu->arch.gmap->private = vcpu->kvm;
533 534 535
		return 0;
	}

536
	vcpu->arch.gmap = vcpu->kvm->arch.gmap;
537 538
	vcpu->run->kvm_valid_regs = KVM_SYNC_PREFIX |
				    KVM_SYNC_GPRS |
539 540
				    KVM_SYNC_ACRS |
				    KVM_SYNC_CRS;
541 542 543 544 545
	return 0;
}

void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu)
{
546
	/* Nothing todo */
547 548 549 550
}

void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
{
551 552
	save_fp_ctl(&vcpu->arch.host_fpregs.fpc);
	save_fp_regs(vcpu->arch.host_fpregs.fprs);
553
	save_access_regs(vcpu->arch.host_acrs);
554 555
	restore_fp_ctl(&vcpu->arch.guest_fpregs.fpc);
	restore_fp_regs(vcpu->arch.guest_fpregs.fprs);
556
	restore_access_regs(vcpu->run->s.regs.acrs);
557
	gmap_enable(vcpu->arch.gmap);
558
	atomic_set_mask(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
559 560 561 562
}

void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
{
563
	atomic_clear_mask(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
564
	gmap_disable(vcpu->arch.gmap);
565 566
	save_fp_ctl(&vcpu->arch.guest_fpregs.fpc);
	save_fp_regs(vcpu->arch.guest_fpregs.fprs);
567
	save_access_regs(vcpu->run->s.regs.acrs);
568 569
	restore_fp_ctl(&vcpu->arch.host_fpregs.fpc);
	restore_fp_regs(vcpu->arch.host_fpregs.fprs);
570 571 572 573 574 575 576 577
	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;
578
	kvm_s390_set_prefix(vcpu, 0);
579 580 581 582 583 584 585 586 587
	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;
588
	vcpu->arch.sie_block->pp = 0;
589 590
	vcpu->arch.pfault_token = KVM_S390_PFAULT_TOKEN_INVALID;
	kvm_clear_async_pf_completion_queue(vcpu);
591
	atomic_set_mask(CPUSTAT_STOPPED, &vcpu->arch.sie_block->cpuflags);
592
	kvm_s390_clear_local_irqs(vcpu);
593 594
}

595 596 597 598 599
int kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
{
	return 0;
}

600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616
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;
}

617 618
int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
{
619
	int rc = 0;
620

621 622
	atomic_set(&vcpu->arch.sie_block->cpuflags, CPUSTAT_ZARCH |
						    CPUSTAT_SM |
623 624
						    CPUSTAT_STOPPED |
						    CPUSTAT_GED);
625
	vcpu->arch.sie_block->ecb   = 6;
626 627 628
	if (test_vfacility(50) && test_vfacility(73))
		vcpu->arch.sie_block->ecb |= 0x10;

629
	vcpu->arch.sie_block->ecb2  = 8;
630 631 632
	vcpu->arch.sie_block->eca   = 0xC1002000U;
	if (sclp_has_siif())
		vcpu->arch.sie_block->eca |= 1;
633
	vcpu->arch.sie_block->fac   = (int) (long) vfacilities;
634
	vcpu->arch.sie_block->ictl |= ICTL_ISKE | ICTL_SSKE | ICTL_RRBE;
635 636 637 638
	if (kvm_s390_cmma_enabled(vcpu->kvm)) {
		rc = kvm_s390_vcpu_setup_cmma(vcpu);
		if (rc)
			return rc;
639
	}
640 641 642 643
	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;
644
	get_cpu_id(&vcpu->arch.cpu_id);
645
	vcpu->arch.cpu_id.version = 0xff;
646
	return rc;
647 648 649 650 651
}

struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
				      unsigned int id)
{
652
	struct kvm_vcpu *vcpu;
653
	struct sie_page *sie_page;
654 655 656 657 658 659
	int rc = -EINVAL;

	if (id >= KVM_MAX_VCPUS)
		goto out;

	rc = -ENOMEM;
660

661
	vcpu = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL);
662
	if (!vcpu)
663
		goto out;
664

665 666
	sie_page = (struct sie_page *) get_zeroed_page(GFP_KERNEL);
	if (!sie_page)
667 668
		goto out_free_cpu;

669 670 671
	vcpu->arch.sie_block = &sie_page->sie_block;
	vcpu->arch.sie_block->itdba = (unsigned long) &sie_page->itdb;

672
	vcpu->arch.sie_block->icpua = id;
C
Carsten Otte 已提交
673 674 675 676 677 678 679 680 681 682 683 684 685
	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);
	}
686

687 688 689
	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;
690
	vcpu->arch.local_int.wq = &vcpu->wq;
691
	vcpu->arch.local_int.cpuflags = &vcpu->arch.sie_block->cpuflags;
692

693 694
	rc = kvm_vcpu_init(vcpu, kvm, id);
	if (rc)
695
		goto out_free_sie_block;
696 697
	VM_EVENT(kvm, 3, "create cpu %d at %p, sie block at %p", id, vcpu,
		 vcpu->arch.sie_block);
698
	trace_kvm_s390_create_vcpu(id, vcpu, vcpu->arch.sie_block);
699 700

	return vcpu;
701 702
out_free_sie_block:
	free_page((unsigned long)(vcpu->arch.sie_block));
703
out_free_cpu:
704
	kmem_cache_free(kvm_vcpu_cache, vcpu);
705
out:
706 707 708 709 710
	return ERR_PTR(rc);
}

int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
{
711
	return kvm_cpu_has_interrupt(vcpu);
712 713
}

714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741
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);
}

742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757
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);
		}
	}
}

758 759 760 761 762 763 764
int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu)
{
	/* kvm common code refers to this, but never calls it */
	BUG();
	return 0;
}

765 766 767 768 769 770
static int kvm_arch_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu,
					   struct kvm_one_reg *reg)
{
	int r = -EINVAL;

	switch (reg->id) {
771 772 773 774 775 776 777 778
	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;
779 780 781 782 783 784 785 786
	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;
787 788 789 790 791 792 793 794 795 796 797 798
	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;
799 800 801 802
	case KVM_REG_S390_PP:
		r = put_user(vcpu->arch.sie_block->pp,
			     (u64 __user *)reg->addr);
		break;
803 804 805 806
	case KVM_REG_S390_GBEA:
		r = put_user(vcpu->arch.sie_block->gbea,
			     (u64 __user *)reg->addr);
		break;
807 808 809 810 811 812 813 814 815 816 817 818 819
	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) {
820 821 822 823 824 825 826 827
	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;
828 829 830 831 832 833 834 835
	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;
836 837 838 839 840 841 842 843 844 845 846 847
	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;
848 849 850 851
	case KVM_REG_S390_PP:
		r = get_user(vcpu->arch.sie_block->pp,
			     (u64 __user *)reg->addr);
		break;
852 853 854 855
	case KVM_REG_S390_GBEA:
		r = get_user(vcpu->arch.sie_block->gbea,
			     (u64 __user *)reg->addr);
		break;
856 857 858 859 860 861
	default:
		break;
	}

	return r;
}
862

863 864 865 866 867 868 869 870
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)
{
871
	memcpy(&vcpu->run->s.regs.gprs, &regs->gprs, sizeof(regs->gprs));
872 873 874 875 876
	return 0;
}

int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
{
877
	memcpy(&regs->gprs, &vcpu->run->s.regs.gprs, sizeof(regs->gprs));
878 879 880 881 882 883
	return 0;
}

int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
				  struct kvm_sregs *sregs)
{
884
	memcpy(&vcpu->run->s.regs.acrs, &sregs->acrs, sizeof(sregs->acrs));
885
	memcpy(&vcpu->arch.sie_block->gcr, &sregs->crs, sizeof(sregs->crs));
886
	restore_access_regs(vcpu->run->s.regs.acrs);
887 888 889 890 891 892
	return 0;
}

int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
				  struct kvm_sregs *sregs)
{
893
	memcpy(&sregs->acrs, &vcpu->run->s.regs.acrs, sizeof(sregs->acrs));
894 895 896 897 898 899
	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)
{
900 901
	if (test_fp_ctl(fpu->fpc))
		return -EINVAL;
902
	memcpy(&vcpu->arch.guest_fpregs.fprs, &fpu->fprs, sizeof(fpu->fprs));
903 904 905
	vcpu->arch.guest_fpregs.fpc = fpu->fpc;
	restore_fp_ctl(&vcpu->arch.guest_fpregs.fpc);
	restore_fp_regs(vcpu->arch.guest_fpregs.fprs);
906 907 908 909 910 911 912 913 914 915 916 917 918 919
	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;

920
	if (!(atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_STOPPED))
921
		rc = -EBUSY;
922 923 924 925
	else {
		vcpu->run->psw_mask = psw.mask;
		vcpu->run->psw_addr = psw.addr;
	}
926 927 928 929 930 931 932 933 934
	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
935 936
int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
					struct kvm_guest_debug *dbg)
937 938 939 940
{
	return -EINVAL; /* not implemented yet */
}

941 942 943 944 945 946 947 948 949 950 951 952
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 */
}

953 954 955 956 957 958 959 960 961 962 963 964
bool kvm_s390_cmma_enabled(struct kvm *kvm)
{
	if (!MACHINE_IS_LPAR)
		return false;
	/* only enable for z10 and later */
	if (!MACHINE_HAS_EDAT1)
		return false;
	if (!kvm->arch.use_cmma)
		return false;
	return true;
}

965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985
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;
}

986 987 988 989 990 991 992 993 994 995 996
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;
}

997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060
static void __kvm_inject_pfault_token(struct kvm_vcpu *vcpu, bool start_token,
				      unsigned long token)
{
	struct kvm_s390_interrupt inti;
	inti.parm64 = token;

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

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

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

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

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

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

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

H
Heiko Carstens 已提交
1061 1062 1063
	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))
1064 1065 1066 1067 1068 1069
		return 0;

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

1070
static int vcpu_pre_run(struct kvm_vcpu *vcpu)
1071
{
1072
	int rc, cpuflags;
1073

1074 1075 1076 1077 1078 1079 1080
	/*
	 * 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);

1081
	memcpy(&vcpu->arch.sie_block->gg14, &vcpu->run->s.regs.gprs[14], 16);
1082 1083 1084 1085

	if (need_resched())
		schedule();

1086 1087 1088
	if (test_thread_flag(TIF_MCCK_PENDING))
		s390_handle_mcck();

1089 1090
	if (!kvm_is_ucontrol(vcpu->kvm))
		kvm_s390_deliver_pending_interrupts(vcpu);
C
Carsten Otte 已提交
1091

1092 1093 1094 1095
	rc = kvm_s390_handle_requests(vcpu);
	if (rc)
		return rc;

1096
	vcpu->arch.sie_block->icptcode = 0;
1097 1098 1099
	cpuflags = atomic_read(&vcpu->arch.sie_block->cpuflags);
	VCPU_EVENT(vcpu, 6, "entering sie flags %x", cpuflags);
	trace_kvm_s390_sie_enter(vcpu, cpuflags);
1100

1101 1102 1103 1104 1105
	return 0;
}

static int vcpu_post_run(struct kvm_vcpu *vcpu, int exit_reason)
{
1106
	int rc = -1;
1107 1108 1109 1110 1111

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

1112
	if (exit_reason >= 0) {
1113
		rc = 0;
1114 1115 1116 1117 1118 1119
	} 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;
1120 1121

	} else if (current->thread.gmap_pfault) {
1122
		trace_kvm_s390_major_guest_pfault(vcpu);
1123
		current->thread.gmap_pfault = 0;
1124 1125
		if (kvm_arch_setup_async_pf(vcpu) ||
		    (kvm_arch_fault_in_sync(vcpu) >= 0))
1126 1127 1128 1129
			rc = 0;
	}

	if (rc == -1) {
1130 1131 1132
		VCPU_EVENT(vcpu, 3, "%s", "fault in sie instruction");
		trace_kvm_s390_sie_fault(vcpu);
		rc = kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
1133
	}
1134

1135
	memcpy(&vcpu->run->s.regs.gprs[14], &vcpu->arch.sie_block->gg14, 16);
1136

1137 1138
	if (rc == 0) {
		if (kvm_is_ucontrol(vcpu->kvm))
1139 1140
			/* Don't exit for host interrupts. */
			rc = vcpu->arch.sie_block->icptcode ? -EOPNOTSUPP : 0;
1141 1142 1143 1144
		else
			rc = kvm_handle_sie_intercept(vcpu);
	}

1145 1146 1147 1148 1149 1150 1151
	return rc;
}

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

1152 1153 1154 1155 1156 1157
	/*
	 * 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);

1158 1159 1160 1161
	do {
		rc = vcpu_pre_run(vcpu);
		if (rc)
			break;
1162

1163
		srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
1164 1165 1166 1167 1168 1169 1170 1171 1172 1173
		/*
		 * 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();
1174
		vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
1175 1176 1177

		rc = vcpu_post_run(vcpu, exit_reason);
	} while (!signal_pending(current) && !rc);
1178

1179
	srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
1180
	return rc;
1181 1182 1183 1184
}

int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
{
1185
	int rc;
1186 1187 1188 1189 1190
	sigset_t sigsaved;

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

1191
	atomic_clear_mask(CPUSTAT_STOPPED, &vcpu->arch.sie_block->cpuflags);
1192

1193 1194 1195
	switch (kvm_run->exit_reason) {
	case KVM_EXIT_S390_SIEIC:
	case KVM_EXIT_UNKNOWN:
1196
	case KVM_EXIT_INTR:
1197
	case KVM_EXIT_S390_RESET:
1198
	case KVM_EXIT_S390_UCONTROL:
1199
	case KVM_EXIT_S390_TSCH:
1200 1201 1202 1203 1204
		break;
	default:
		BUG();
	}

1205 1206
	vcpu->arch.sie_block->gpsw.mask = kvm_run->psw_mask;
	vcpu->arch.sie_block->gpsw.addr = kvm_run->psw_addr;
1207 1208 1209 1210
	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);
	}
1211 1212 1213 1214 1215
	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);
	}
1216

1217
	might_fault();
1218
	rc = __vcpu_run(vcpu);
1219

1220 1221
	if (signal_pending(current) && !rc) {
		kvm_run->exit_reason = KVM_EXIT_INTR;
1222
		rc = -EINTR;
1223
	}
1224

1225
	if (rc == -EOPNOTSUPP) {
1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238
		/* 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;
	}
1239

1240 1241
	kvm_run->psw_mask     = vcpu->arch.sie_block->gpsw.mask;
	kvm_run->psw_addr     = vcpu->arch.sie_block->gpsw.addr;
1242
	kvm_run->s.regs.prefix = vcpu->arch.sie_block->prefix;
1243
	memcpy(&kvm_run->s.regs.crs, &vcpu->arch.sie_block->gcr, 128);
1244

1245 1246 1247 1248
	if (vcpu->sigset_active)
		sigprocmask(SIG_SETMASK, &sigsaved, NULL);

	vcpu->stat.exit_userspace++;
1249
	return rc;
1250 1251 1252 1253 1254 1255 1256 1257
}

/*
 * 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
 */
1258
int kvm_s390_store_status_unloaded(struct kvm_vcpu *vcpu, unsigned long gpa)
1259
{
1260
	unsigned char archmode = 1;
1261
	u64 clkcomp;
1262
	int rc;
1263

1264 1265
	if (gpa == KVM_S390_STORE_STATUS_NOADDR) {
		if (write_guest_abs(vcpu, 163, &archmode, 1))
1266
			return -EFAULT;
1267 1268 1269
		gpa = SAVE_AREA_BASE;
	} else if (gpa == KVM_S390_STORE_STATUS_PREFIXED) {
		if (write_guest_real(vcpu, 163, &archmode, 1))
1270
			return -EFAULT;
1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287
		gpa = kvm_s390_real_to_abs(vcpu, SAVE_AREA_BASE);
	}
	rc = write_guest_abs(vcpu, gpa + offsetof(struct save_area, fp_regs),
			     vcpu->arch.guest_fpregs.fprs, 128);
	rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, gp_regs),
			      vcpu->run->s.regs.gprs, 128);
	rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, psw),
			      &vcpu->arch.sie_block->gpsw, 16);
	rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, pref_reg),
			      &vcpu->arch.sie_block->prefix, 4);
	rc |= write_guest_abs(vcpu,
			      gpa + offsetof(struct save_area, fp_ctrl_reg),
			      &vcpu->arch.guest_fpregs.fpc, 4);
	rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, tod_reg),
			      &vcpu->arch.sie_block->todpr, 4);
	rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, timer),
			      &vcpu->arch.sie_block->cputm, 8);
1288
	clkcomp = vcpu->arch.sie_block->ckc >> 8;
1289 1290 1291 1292 1293 1294 1295
	rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, clk_cmp),
			      &clkcomp, 8);
	rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, acc_regs),
			      &vcpu->run->s.regs.acrs, 64);
	rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, ctrl_regs),
			      &vcpu->arch.sie_block->gcr, 128);
	return rc ? -EFAULT : 0;
1296 1297
}

1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311
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);
}

1312 1313 1314 1315 1316 1317 1318 1319 1320
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) {
1321 1322 1323 1324 1325 1326 1327
	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;
1328 1329 1330 1331 1332 1333 1334
	default:
		r = -EINVAL;
		break;
	}
	return r;
}

1335 1336 1337 1338 1339
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;
1340
	int idx;
1341
	long r;
1342

1343 1344
	switch (ioctl) {
	case KVM_S390_INTERRUPT: {
1345 1346
		struct kvm_s390_interrupt s390int;

1347
		r = -EFAULT;
1348
		if (copy_from_user(&s390int, argp, sizeof(s390int)))
1349 1350 1351
			break;
		r = kvm_s390_inject_vcpu(vcpu, &s390int);
		break;
1352
	}
1353
	case KVM_S390_STORE_STATUS:
1354
		idx = srcu_read_lock(&vcpu->kvm->srcu);
1355
		r = kvm_s390_vcpu_store_status(vcpu, arg);
1356
		srcu_read_unlock(&vcpu->kvm->srcu, idx);
1357
		break;
1358 1359 1360
	case KVM_S390_SET_INITIAL_PSW: {
		psw_t psw;

1361
		r = -EFAULT;
1362
		if (copy_from_user(&psw, argp, sizeof(psw)))
1363 1364 1365
			break;
		r = kvm_arch_vcpu_ioctl_set_initial_psw(vcpu, psw);
		break;
1366 1367
	}
	case KVM_S390_INITIAL_RESET:
1368 1369
		r = kvm_arch_vcpu_ioctl_initial_reset(vcpu);
		break;
1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381
	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;
	}
1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417
#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
1418 1419 1420 1421 1422 1423
	case KVM_S390_VCPU_FAULT: {
		r = gmap_fault(arg, vcpu->arch.gmap);
		if (!IS_ERR_VALUE(r))
			r = 0;
		break;
	}
1424 1425 1426 1427 1428 1429 1430 1431 1432
	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;
	}
1433
	default:
1434
		r = -ENOTTY;
1435
	}
1436
	return r;
1437 1438
}

1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451
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;
}

1452
void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free,
1453 1454 1455 1456
			   struct kvm_memory_slot *dont)
{
}

1457 1458
int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
			    unsigned long npages)
1459 1460 1461 1462
{
	return 0;
}

1463 1464 1465 1466
void kvm_arch_memslots_updated(struct kvm *kvm)
{
}

1467
/* Section: memory related */
1468 1469
int kvm_arch_prepare_memory_region(struct kvm *kvm,
				   struct kvm_memory_slot *memslot,
1470 1471
				   struct kvm_userspace_memory_region *mem,
				   enum kvm_mr_change change)
1472
{
1473 1474 1475 1476
	/* 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 */
1477

1478
	if (mem->userspace_addr & 0xffffful)
1479 1480
		return -EINVAL;

1481
	if (mem->memory_size & 0xffffful)
1482 1483
		return -EINVAL;

1484 1485 1486 1487 1488
	return 0;
}

void kvm_arch_commit_memory_region(struct kvm *kvm,
				struct kvm_userspace_memory_region *mem,
1489 1490
				const struct kvm_memory_slot *old,
				enum kvm_mr_change change)
1491
{
1492
	int rc;
1493

1494 1495 1496 1497 1498 1499 1500 1501 1502 1503
	/* 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;
1504 1505 1506 1507

	rc = gmap_map_segment(kvm->arch.gmap, mem->userspace_addr,
		mem->guest_phys_addr, mem->memory_size);
	if (rc)
1508
		printk(KERN_WARNING "kvm-s390: failed to commit memory region\n");
1509
	return;
1510 1511
}

1512 1513 1514 1515 1516 1517
void kvm_arch_flush_shadow_all(struct kvm *kvm)
{
}

void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
				   struct kvm_memory_slot *slot)
1518 1519 1520
{
}

1521 1522
static int __init kvm_s390_init(void)
{
1523
	int ret;
1524
	ret = kvm_init(NULL, sizeof(struct kvm_vcpu), 0, THIS_MODULE);
1525 1526 1527 1528 1529
	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
1530
	 * to hold the maximum amount of facilities. On the other hand, we
1531 1532
	 * only set facilities that are known to work in KVM.
	 */
1533 1534
	vfacilities = (unsigned long *) get_zeroed_page(GFP_KERNEL|GFP_DMA);
	if (!vfacilities) {
1535 1536 1537
		kvm_exit();
		return -ENOMEM;
	}
1538
	memcpy(vfacilities, S390_lowcore.stfle_fac_list, 16);
1539
	vfacilities[0] &= 0xff82fff3f4fc2000UL;
1540
	vfacilities[1] &= 0x005c000000000000UL;
1541
	return 0;
1542 1543 1544 1545
}

static void __exit kvm_s390_exit(void)
{
1546
	free_page((unsigned long) vfacilities);
1547 1548 1549 1550 1551
	kvm_exit();
}

module_init(kvm_s390_init);
module_exit(kvm_s390_exit);
1552 1553 1554 1555 1556 1557 1558 1559 1560

/*
 * 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");