kvm-s390.c 22.0 KB
Newer Older
1 2 3
/*
 * s390host.c --  hosting zSeries kernel virtual machines
 *
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/system.h>
31
#include "kvm-s390.h"
32 33 34 35 36 37
#include "gaccess.h"

#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) },
38
	{ "exit_null", VCPU_STAT(exit_null) },
39 40 41 42
	{ "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) },
43 44 45
	{ "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) },
46
	{ "instruction_lctlg", VCPU_STAT(instruction_lctlg) },
47 48
	{ "instruction_lctl", VCPU_STAT(instruction_lctl) },
	{ "deliver_emergency_signal", VCPU_STAT(deliver_emergency_signal) },
49
	{ "deliver_external_call", VCPU_STAT(deliver_external_call) },
50 51 52 53 54 55 56
	{ "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) },
57 58 59 60 61 62 63 64 65
	{ "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) },
	{ "instruction_stsi", VCPU_STAT(instruction_stsi) },
	{ "instruction_stfl", VCPU_STAT(instruction_stfl) },
66
	{ "instruction_tprot", VCPU_STAT(instruction_tprot) },
67
	{ "instruction_sigp_sense", VCPU_STAT(instruction_sigp_sense) },
68
	{ "instruction_sigp_sense_running", VCPU_STAT(instruction_sigp_sense_running) },
69
	{ "instruction_sigp_external_call", VCPU_STAT(instruction_sigp_external_call) },
70 71 72 73 74
	{ "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) },
75
	{ "diagnose_10", VCPU_STAT(diagnose_10) },
76
	{ "diagnose_44", VCPU_STAT(diagnose_44) },
77 78 79
	{ NULL }
};

80
static unsigned long long *facilities;
81 82

/* Section: not file related */
83
int kvm_arch_hardware_enable(void *garbage)
84 85
{
	/* every s390 is virtualization enabled ;-) */
86
	return 0;
87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125
}

void kvm_arch_hardware_disable(void *garbage)
{
}

int kvm_arch_hardware_setup(void)
{
	return 0;
}

void kvm_arch_hardware_unsetup(void)
{
}

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)
{
126 127
	int r;

128
	switch (ext) {
129
	case KVM_CAP_S390_PSW:
130
	case KVM_CAP_S390_GMAP:
131
	case KVM_CAP_SYNC_MMU:
132 133
		r = 1;
		break;
134
	default:
135
		r = 0;
136
	}
137
	return r;
138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157
}

/* 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;
}

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) {
158 159 160 161 162 163 164 165 166
	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;
	}
167
	default:
168
		r = -ENOTTY;
169 170 171 172 173
	}

	return r;
}

174
int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
175 176 177 178
{
	int rc;
	char debug_name[16];

179 180 181 182 183 184 185 186 187 188 189
	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

190 191
	rc = s390_enable_sie();
	if (rc)
192
		goto out_err;
193

194 195
	rc = -ENOMEM;

196 197
	kvm->arch.sca = (struct sca_block *) get_zeroed_page(GFP_KERNEL);
	if (!kvm->arch.sca)
198
		goto out_err;
199 200 201 202 203 204 205

	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;

206 207 208
	spin_lock_init(&kvm->arch.float_int.lock);
	INIT_LIST_HEAD(&kvm->arch.float_int.list);

209 210 211
	debug_register_view(kvm->arch.dbf, &debug_sprintf_view);
	VM_EVENT(kvm, 3, "%s", "vm created");

212 213 214 215 216 217 218
	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;
	}
219
	return 0;
220 221
out_nogmap:
	debug_unregister(kvm->arch.dbf);
222 223
out_nodbf:
	free_page((unsigned long)(kvm->arch.sca));
224 225
out_err:
	return rc;
226 227
}

228 229 230
void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
{
	VCPU_EVENT(vcpu, 3, "%s", "free cpu");
231
	clear_bit(63 - vcpu->vcpu_id, (unsigned long *) &vcpu->kvm->arch.sca->mcn);
232 233 234 235
	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;
	smp_mb();
236 237 238 239

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

240
	free_page((unsigned long)(vcpu->arch.sie_block));
241
	kvm_vcpu_uninit(vcpu);
242 243 244 245 246 247
	kfree(vcpu);
}

static void kvm_free_vcpus(struct kvm *kvm)
{
	unsigned int i;
248
	struct kvm_vcpu *vcpu;
249

250 251 252 253 254 255 256 257 258
	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);
259 260
}

261 262 263 264
void kvm_arch_sync_events(struct kvm *kvm)
{
}

265 266
void kvm_arch_destroy_vm(struct kvm *kvm)
{
267
	kvm_free_vcpus(kvm);
268
	free_page((unsigned long)(kvm->arch.sca));
269
	debug_unregister(kvm->arch.dbf);
270 271
	if (!kvm_is_ucontrol(kvm))
		gmap_free(kvm->arch.gmap);
272 273 274 275 276
}

/* Section: vcpu related */
int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
{
277 278 279 280 281 282 283
	if (kvm_is_ucontrol(vcpu->kvm)) {
		vcpu->arch.gmap = gmap_alloc(current->mm);
		if (!vcpu->arch.gmap)
			return -ENOMEM;
		return 0;
	}

284
	vcpu->arch.gmap = vcpu->kvm->arch.gmap;
285 286 287 288 289
	return 0;
}

void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu)
{
290
	/* Nothing todo */
291 292 293 294 295 296 297 298 299
}

void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
{
	save_fp_regs(&vcpu->arch.host_fpregs);
	save_access_regs(vcpu->arch.host_acrs);
	vcpu->arch.guest_fpregs.fpc &= FPC_VALID_MASK;
	restore_fp_regs(&vcpu->arch.guest_fpregs);
	restore_access_regs(vcpu->arch.guest_acrs);
300
	gmap_enable(vcpu->arch.gmap);
301
	atomic_set_mask(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
302 303 304 305
}

void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
{
306
	atomic_clear_mask(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
307
	gmap_disable(vcpu->arch.gmap);
308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333
	save_fp_regs(&vcpu->arch.guest_fpregs);
	save_access_regs(vcpu->arch.guest_acrs);
	restore_fp_regs(&vcpu->arch.host_fpregs);
	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;
	vcpu->arch.sie_block->prefix    = 0UL;
	vcpu->arch.sie_block->ihcpu     = 0xffff;
	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;
}

int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
{
334 335 336
	atomic_set(&vcpu->arch.sie_block->cpuflags, CPUSTAT_ZARCH |
						    CPUSTAT_SM |
						    CPUSTAT_STOPPED);
337
	vcpu->arch.sie_block->ecb   = 6;
338
	vcpu->arch.sie_block->eca   = 0xC1002001U;
339
	vcpu->arch.sie_block->fac   = (int) (long) facilities;
340 341 342 343
	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;
344
	get_cpu_id(&vcpu->arch.cpu_id);
345
	vcpu->arch.cpu_id.version = 0xff;
346 347 348 349 350 351
	return 0;
}

struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
				      unsigned int id)
{
352 353 354 355 356 357 358
	struct kvm_vcpu *vcpu;
	int rc = -EINVAL;

	if (id >= KVM_MAX_VCPUS)
		goto out;

	rc = -ENOMEM;
359

360
	vcpu = kzalloc(sizeof(struct kvm_vcpu), GFP_KERNEL);
361
	if (!vcpu)
362
		goto out;
363

364 365
	vcpu->arch.sie_block = (struct kvm_s390_sie_block *)
					get_zeroed_page(GFP_KERNEL);
366 367 368 369 370 371

	if (!vcpu->arch.sie_block)
		goto out_free_cpu;

	vcpu->arch.sie_block->icpua = id;
	BUG_ON(!kvm->arch.sca);
372 373
	if (!kvm->arch.sca->cpu[id].sda)
		kvm->arch.sca->cpu[id].sda = (__u64) vcpu->arch.sie_block;
374 375
	vcpu->arch.sie_block->scaoh = (__u32)(((__u64)kvm->arch.sca) >> 32);
	vcpu->arch.sie_block->scaol = (__u32)(__u64)kvm->arch.sca;
376
	set_bit(63 - id, (unsigned long *) &kvm->arch.sca->mcn);
377

378 379 380
	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;
381
	spin_lock(&kvm->arch.float_int.lock);
382 383
	kvm->arch.float_int.local_int[id] = &vcpu->arch.local_int;
	init_waitqueue_head(&vcpu->arch.local_int.wq);
384
	vcpu->arch.local_int.cpuflags = &vcpu->arch.sie_block->cpuflags;
385
	spin_unlock(&kvm->arch.float_int.lock);
386

387 388
	rc = kvm_vcpu_init(vcpu, kvm, id);
	if (rc)
389
		goto out_free_sie_block;
390 391 392 393
	VM_EVENT(kvm, 3, "create cpu %d at %p, sie block at %p", id, vcpu,
		 vcpu->arch.sie_block);

	return vcpu;
394 395
out_free_sie_block:
	free_page((unsigned long)(vcpu->arch.sie_block));
396 397
out_free_cpu:
	kfree(vcpu);
398
out:
399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431
	return ERR_PTR(rc);
}

int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
{
	/* kvm common code refers to this, but never calls it */
	BUG();
	return 0;
}

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)
{
	memcpy(&vcpu->arch.guest_gprs, &regs->gprs, sizeof(regs->gprs));
	return 0;
}

int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
{
	memcpy(&regs->gprs, &vcpu->arch.guest_gprs, sizeof(regs->gprs));
	return 0;
}

int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
				  struct kvm_sregs *sregs)
{
	memcpy(&vcpu->arch.guest_acrs, &sregs->acrs, sizeof(sregs->acrs));
	memcpy(&vcpu->arch.sie_block->gcr, &sregs->crs, sizeof(sregs->crs));
C
Carsten Otte 已提交
432
	restore_access_regs(vcpu->arch.guest_acrs);
433 434 435 436 437 438 439 440 441 442 443 444 445 446 447
	return 0;
}

int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
				  struct kvm_sregs *sregs)
{
	memcpy(&sregs->acrs, &vcpu->arch.guest_acrs, sizeof(sregs->acrs));
	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)
{
	memcpy(&vcpu->arch.guest_fpregs.fprs, &fpu->fprs, sizeof(fpu->fprs));
	vcpu->arch.guest_fpregs.fpc = fpu->fpc;
C
Carsten Otte 已提交
448
	restore_fp_regs(&vcpu->arch.guest_fpregs);
449 450 451 452 453 454 455 456 457 458 459 460 461 462
	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;

463
	if (!(atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_STOPPED))
464
		rc = -EBUSY;
465 466 467 468
	else {
		vcpu->run->psw_mask = psw.mask;
		vcpu->run->psw_addr = psw.addr;
	}
469 470 471 472 473 474 475 476 477
	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
478 479
int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
					struct kvm_guest_debug *dbg)
480 481 482 483
{
	return -EINVAL; /* not implemented yet */
}

484 485 486 487 488 489 490 491 492 493 494 495
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 */
}

496
static int __vcpu_run(struct kvm_vcpu *vcpu)
497
{
498 499
	int rc;

500 501 502 503 504
	memcpy(&vcpu->arch.sie_block->gg14, &vcpu->arch.guest_gprs[14], 16);

	if (need_resched())
		schedule();

505 506 507
	if (test_thread_flag(TIF_MCCK_PENDING))
		s390_handle_mcck();

508 509
	if (!kvm_is_ucontrol(vcpu->kvm))
		kvm_s390_deliver_pending_interrupts(vcpu);
C
Carsten Otte 已提交
510

511 512 513 514 515 516
	vcpu->arch.sie_block->icptcode = 0;
	local_irq_disable();
	kvm_guest_enter();
	local_irq_enable();
	VCPU_EVENT(vcpu, 6, "entering sie flags %x",
		   atomic_read(&vcpu->arch.sie_block->cpuflags));
517 518 519 520 521 522 523 524 525
	rc = sie64a(vcpu->arch.sie_block, vcpu->arch.guest_gprs);
	if (rc) {
		if (kvm_is_ucontrol(vcpu->kvm)) {
			rc = SIE_INTERCEPT_UCONTROL;
		} else {
			VCPU_EVENT(vcpu, 3, "%s", "fault in sie instruction");
			kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
			rc = 0;
		}
526
	}
527 528 529 530 531 532 533
	VCPU_EVENT(vcpu, 6, "exit sie icptcode %d",
		   vcpu->arch.sie_block->icptcode);
	local_irq_disable();
	kvm_guest_exit();
	local_irq_enable();

	memcpy(&vcpu->arch.guest_gprs[14], &vcpu->arch.sie_block->gg14, 16);
534
	return rc;
535 536 537 538
}

int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
{
539
	int rc;
540 541
	sigset_t sigsaved;

542
rerun_vcpu:
543 544 545
	if (vcpu->sigset_active)
		sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved);

546
	atomic_clear_mask(CPUSTAT_STOPPED, &vcpu->arch.sie_block->cpuflags);
547

548 549
	BUG_ON(vcpu->kvm->arch.float_int.local_int[vcpu->vcpu_id] == NULL);

550 551 552
	switch (kvm_run->exit_reason) {
	case KVM_EXIT_S390_SIEIC:
	case KVM_EXIT_UNKNOWN:
553
	case KVM_EXIT_INTR:
554
	case KVM_EXIT_S390_RESET:
555
	case KVM_EXIT_S390_UCONTROL:
556 557 558 559 560
		break;
	default:
		BUG();
	}

561 562 563
	vcpu->arch.sie_block->gpsw.mask = kvm_run->psw_mask;
	vcpu->arch.sie_block->gpsw.addr = kvm_run->psw_addr;

564
	might_fault();
565 566

	do {
567 568 569
		rc = __vcpu_run(vcpu);
		if (rc)
			break;
570 571 572 573
		if (kvm_is_ucontrol(vcpu->kvm))
			rc = -EOPNOTSUPP;
		else
			rc = kvm_handle_sie_intercept(vcpu);
574 575
	} while (!signal_pending(current) && !rc);

576 577 578
	if (rc == SIE_INTERCEPT_RERUNVCPU)
		goto rerun_vcpu;

579 580
	if (signal_pending(current) && !rc) {
		kvm_run->exit_reason = KVM_EXIT_INTR;
581
		rc = -EINTR;
582
	}
583

584 585 586 587 588 589 590 591 592 593
#ifdef CONFIG_KVM_S390_UCONTROL
	if (rc == SIE_INTERCEPT_UCONTROL) {
		kvm_run->exit_reason = KVM_EXIT_S390_UCONTROL;
		kvm_run->s390_ucontrol.trans_exc_code =
			current->thread.gmap_addr;
		kvm_run->s390_ucontrol.pgm_code = 0x10;
		rc = 0;
	}
#endif

594
	if (rc == -EOPNOTSUPP) {
595 596 597 598 599 600 601 602 603 604 605 606 607
		/* 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;
	}
608

609 610 611
	kvm_run->psw_mask     = vcpu->arch.sie_block->gpsw.mask;
	kvm_run->psw_addr     = vcpu->arch.sie_block->gpsw.addr;

612 613 614 615
	if (vcpu->sigset_active)
		sigprocmask(SIG_SETMASK, &sigsaved, NULL);

	vcpu->stat.exit_userspace++;
616
	return rc;
617 618
}

619
static int __guestcopy(struct kvm_vcpu *vcpu, u64 guestdest, void *from,
620 621 622 623 624 625 626 627 628 629 630 631 632 633
		       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
 */
634
int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr)
635
{
636
	unsigned char archmode = 1;
637 638 639 640 641 642 643 644 645 646 647 648 649 650 651
	int prefix;

	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;

652
	if (__guestcopy(vcpu, addr + offsetof(struct save_area, fp_regs),
653 654 655
			vcpu->arch.guest_fpregs.fprs, 128, prefix))
		return -EFAULT;

656
	if (__guestcopy(vcpu, addr + offsetof(struct save_area, gp_regs),
657 658 659
			vcpu->arch.guest_gprs, 128, prefix))
		return -EFAULT;

660
	if (__guestcopy(vcpu, addr + offsetof(struct save_area, psw),
661 662 663
			&vcpu->arch.sie_block->gpsw, 16, prefix))
		return -EFAULT;

664
	if (__guestcopy(vcpu, addr + offsetof(struct save_area, pref_reg),
665 666 667 668
			&vcpu->arch.sie_block->prefix, 4, prefix))
		return -EFAULT;

	if (__guestcopy(vcpu,
669
			addr + offsetof(struct save_area, fp_ctrl_reg),
670 671 672
			&vcpu->arch.guest_fpregs.fpc, 4, prefix))
		return -EFAULT;

673
	if (__guestcopy(vcpu, addr + offsetof(struct save_area, tod_reg),
674 675 676
			&vcpu->arch.sie_block->todpr, 4, prefix))
		return -EFAULT;

677
	if (__guestcopy(vcpu, addr + offsetof(struct save_area, timer),
678 679 680
			&vcpu->arch.sie_block->cputm, 8, prefix))
		return -EFAULT;

681
	if (__guestcopy(vcpu, addr + offsetof(struct save_area, clk_cmp),
682 683 684
			&vcpu->arch.sie_block->ckc, 8, prefix))
		return -EFAULT;

685
	if (__guestcopy(vcpu, addr + offsetof(struct save_area, acc_regs),
686 687 688 689
			&vcpu->arch.guest_acrs, 64, prefix))
		return -EFAULT;

	if (__guestcopy(vcpu,
690
			addr + offsetof(struct save_area, ctrl_regs),
691 692 693 694 695 696 697 698 699 700
			&vcpu->arch.sie_block->gcr, 128, prefix))
		return -EFAULT;
	return 0;
}

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;
701
	long r;
702

703 704
	switch (ioctl) {
	case KVM_S390_INTERRUPT: {
705 706
		struct kvm_s390_interrupt s390int;

707
		r = -EFAULT;
708
		if (copy_from_user(&s390int, argp, sizeof(s390int)))
709 710 711
			break;
		r = kvm_s390_inject_vcpu(vcpu, &s390int);
		break;
712
	}
713
	case KVM_S390_STORE_STATUS:
714 715
		r = kvm_s390_vcpu_store_status(vcpu, arg);
		break;
716 717 718
	case KVM_S390_SET_INITIAL_PSW: {
		psw_t psw;

719
		r = -EFAULT;
720
		if (copy_from_user(&psw, argp, sizeof(psw)))
721 722 723
			break;
		r = kvm_arch_vcpu_ioctl_set_initial_psw(vcpu, psw);
		break;
724 725
	}
	case KVM_S390_INITIAL_RESET:
726 727
		r = kvm_arch_vcpu_ioctl_initial_reset(vcpu);
		break;
728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763
#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
764 765 766 767 768 769
	case KVM_S390_VCPU_FAULT: {
		r = gmap_fault(arg, vcpu->arch.gmap);
		if (!IS_ERR_VALUE(r))
			r = 0;
		break;
	}
770
	default:
771
		r = -EINVAL;
772
	}
773
	return r;
774 775
}

776 777 778 779 780 781 782 783 784 785 786 787 788
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;
}

789
/* Section: memory related */
790 791 792 793 794
int kvm_arch_prepare_memory_region(struct kvm *kvm,
				   struct kvm_memory_slot *memslot,
				   struct kvm_memory_slot old,
				   struct kvm_userspace_memory_region *mem,
				   int user_alloc)
795 796 797 798 799 800 801 802
{
	/* A few sanity checks. We can have exactly one memory slot which has
	   to start at guest virtual zero and which has to be located at a
	   page boundary in userland and which has to end at a page boundary.
	   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 */

803
	if (mem->slot)
804 805 806 807 808
		return -EINVAL;

	if (mem->guest_phys_addr)
		return -EINVAL;

809
	if (mem->userspace_addr & 0xffffful)
810 811
		return -EINVAL;

812
	if (mem->memory_size & 0xffffful)
813 814
		return -EINVAL;

815 816 817
	if (!user_alloc)
		return -EINVAL;

818 819 820 821 822 823 824 825
	return 0;
}

void kvm_arch_commit_memory_region(struct kvm *kvm,
				struct kvm_userspace_memory_region *mem,
				struct kvm_memory_slot old,
				int user_alloc)
{
826
	int rc;
827

828 829 830 831

	rc = gmap_map_segment(kvm->arch.gmap, mem->userspace_addr,
		mem->guest_phys_addr, mem->memory_size);
	if (rc)
832
		printk(KERN_WARNING "kvm-s390: failed to commit memory region\n");
833
	return;
834 835
}

836 837 838 839
void kvm_arch_flush_shadow(struct kvm *kvm)
{
}

840 841
static int __init kvm_s390_init(void)
{
842
	int ret;
843
	ret = kvm_init(NULL, sizeof(struct kvm_vcpu), 0, THIS_MODULE);
844 845 846 847 848
	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
849
	 * to hold the maximum amount of facilities. On the other hand, we
850 851
	 * only set facilities that are known to work in KVM.
	 */
852
	facilities = (unsigned long long *) get_zeroed_page(GFP_KERNEL|GFP_DMA);
853 854 855 856
	if (!facilities) {
		kvm_exit();
		return -ENOMEM;
	}
857
	memcpy(facilities, S390_lowcore.stfle_fac_list, 16);
858
	facilities[0] &= 0xff00fff3f47c0000ULL;
859
	facilities[1] &= 0x201c000000000000ULL;
860
	return 0;
861 862 863 864
}

static void __exit kvm_s390_exit(void)
{
865
	free_page((unsigned long) facilities);
866 867 868 869 870
	kvm_exit();
}

module_init(kvm_s390_init);
module_exit(kvm_s390_exit);