interrupt.c 50.3 KB
Newer Older
1
/*
2
 * handling kvm guest interrupts
3
 *
4
 * Copyright IBM Corp. 2008,2014
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>
 */

13
#include <linux/interrupt.h>
14
#include <linux/kvm_host.h>
15
#include <linux/hrtimer.h>
16
#include <linux/mmu_context.h>
17
#include <linux/signal.h>
18
#include <linux/slab.h>
19
#include <linux/bitmap.h>
20 21
#include <asm/asm-offsets.h>
#include <asm/uaccess.h>
22 23
#include "kvm-s390.h"
#include "gaccess.h"
24
#include "trace-s390.h"
25

26 27 28 29
#define IOINT_SCHID_MASK 0x0000ffff
#define IOINT_SSID_MASK 0x00030000
#define IOINT_CSSID_MASK 0x03fc0000
#define IOINT_AI_MASK 0x04000000
30
#define PFAULT_INIT 0x0600
31 32
#define PFAULT_DONE 0x0680
#define VIRTIO_PARAM 0x0d00
33 34 35 36 37 38

static int is_ioint(u64 type)
{
	return ((type & 0xfffe0000u) != 0xfffe0000u);
}

39
int psw_extint_disabled(struct kvm_vcpu *vcpu)
40 41 42 43
{
	return !(vcpu->arch.sie_block->gpsw.mask & PSW_MASK_EXT);
}

44 45 46 47 48
static int psw_ioint_disabled(struct kvm_vcpu *vcpu)
{
	return !(vcpu->arch.sie_block->gpsw.mask & PSW_MASK_IO);
}

49 50 51 52 53
static int psw_mchk_disabled(struct kvm_vcpu *vcpu)
{
	return !(vcpu->arch.sie_block->gpsw.mask & PSW_MASK_MCHECK);
}

54 55 56 57 58 59 60 61 62
static int psw_interrupts_disabled(struct kvm_vcpu *vcpu)
{
	if ((vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PER) ||
	    (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_IO) ||
	    (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_EXT))
		return 0;
	return 1;
}

63 64 65 66 67
static int ckc_interrupts_enabled(struct kvm_vcpu *vcpu)
{
	if (psw_extint_disabled(vcpu) ||
	    !(vcpu->arch.sie_block->gcr[0] & 0x800ul))
		return 0;
68 69 70
	if (guestdbg_enabled(vcpu) && guestdbg_sstep_enabled(vcpu))
		/* No timer interrupts when single stepping */
		return 0;
71 72 73
	return 1;
}

C
Cornelia Huck 已提交
74 75 76 77 78 79 80
static u64 int_word_to_isc_bits(u32 int_word)
{
	u8 isc = (int_word & 0x38000000) >> 27;

	return (0x80 >> isc) << 24;
}

81
static int __must_check __interrupt_is_deliverable(struct kvm_vcpu *vcpu,
82
				      struct kvm_s390_interrupt_info *inti)
83 84
{
	switch (inti->type) {
85 86 87 88 89
	case KVM_S390_INT_EXTERNAL_CALL:
		if (psw_extint_disabled(vcpu))
			return 0;
		if (vcpu->arch.sie_block->gcr[0] & 0x2000ul)
			return 1;
90
		return 0;
91 92 93 94 95 96
	case KVM_S390_INT_EMERGENCY:
		if (psw_extint_disabled(vcpu))
			return 0;
		if (vcpu->arch.sie_block->gcr[0] & 0x4000ul)
			return 1;
		return 0;
97 98 99 100 101 102 103 104
	case KVM_S390_INT_CLOCK_COMP:
		return ckc_interrupts_enabled(vcpu);
	case KVM_S390_INT_CPU_TIMER:
		if (psw_extint_disabled(vcpu))
			return 0;
		if (vcpu->arch.sie_block->gcr[0] & 0x400ul)
			return 1;
		return 0;
105
	case KVM_S390_INT_SERVICE:
106 107
	case KVM_S390_INT_PFAULT_INIT:
	case KVM_S390_INT_PFAULT_DONE:
108 109 110 111 112 113 114 115 116 117 118
	case KVM_S390_INT_VIRTIO:
		if (psw_extint_disabled(vcpu))
			return 0;
		if (vcpu->arch.sie_block->gcr[0] & 0x200ul)
			return 1;
		return 0;
	case KVM_S390_PROGRAM_INT:
	case KVM_S390_SIGP_STOP:
	case KVM_S390_SIGP_SET_PREFIX:
	case KVM_S390_RESTART:
		return 1;
119 120 121 122 123 124
	case KVM_S390_MCHK:
		if (psw_mchk_disabled(vcpu))
			return 0;
		if (vcpu->arch.sie_block->gcr[14] & inti->mchk.cr14)
			return 1;
		return 0;
125 126 127
	case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
		if (psw_ioint_disabled(vcpu))
			return 0;
C
Cornelia Huck 已提交
128 129
		if (vcpu->arch.sie_block->gcr[6] &
		    int_word_to_isc_bits(inti->io.io_int_word))
130 131
			return 1;
		return 0;
132
	default:
133 134
		printk(KERN_WARNING "illegal interrupt type %llx\n",
		       inti->type);
135 136 137 138 139
		BUG();
	}
	return 0;
}

140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164
static inline unsigned long pending_local_irqs(struct kvm_vcpu *vcpu)
{
	return vcpu->arch.local_int.pending_irqs;
}

static unsigned long deliverable_local_irqs(struct kvm_vcpu *vcpu)
{
	unsigned long active_mask = pending_local_irqs(vcpu);

	if (psw_extint_disabled(vcpu))
		active_mask &= ~IRQ_PEND_EXT_MASK;
	if (!(vcpu->arch.sie_block->gcr[0] & 0x2000ul))
		__clear_bit(IRQ_PEND_EXT_EXTERNAL, &active_mask);
	if (!(vcpu->arch.sie_block->gcr[0] & 0x4000ul))
		__clear_bit(IRQ_PEND_EXT_EMERGENCY, &active_mask);
	if (!(vcpu->arch.sie_block->gcr[0] & 0x800ul))
		__clear_bit(IRQ_PEND_EXT_CLOCK_COMP, &active_mask);
	if (!(vcpu->arch.sie_block->gcr[0] & 0x400ul))
		__clear_bit(IRQ_PEND_EXT_CPU_TIMER, &active_mask);
	if (psw_mchk_disabled(vcpu))
		active_mask &= ~IRQ_PEND_MCHK_MASK;

	return active_mask;
}

165 166 167 168 169 170 171 172 173 174 175 176 177 178
static void __set_cpu_idle(struct kvm_vcpu *vcpu)
{
	atomic_set_mask(CPUSTAT_WAIT, &vcpu->arch.sie_block->cpuflags);
	set_bit(vcpu->vcpu_id, vcpu->arch.local_int.float_int->idle_mask);
}

static void __unset_cpu_idle(struct kvm_vcpu *vcpu)
{
	atomic_clear_mask(CPUSTAT_WAIT, &vcpu->arch.sie_block->cpuflags);
	clear_bit(vcpu->vcpu_id, vcpu->arch.local_int.float_int->idle_mask);
}

static void __reset_intercept_indicators(struct kvm_vcpu *vcpu)
{
179 180
	atomic_clear_mask(CPUSTAT_IO_INT | CPUSTAT_EXT_INT | CPUSTAT_STOP_INT,
			  &vcpu->arch.sie_block->cpuflags);
181
	vcpu->arch.sie_block->lctl = 0x0000;
182 183 184 185 186 187 188
	vcpu->arch.sie_block->ictl &= ~(ICTL_LPSW | ICTL_STCTL | ICTL_PINT);

	if (guestdbg_enabled(vcpu)) {
		vcpu->arch.sie_block->lctl |= (LCTL_CR0 | LCTL_CR9 |
					       LCTL_CR10 | LCTL_CR11);
		vcpu->arch.sie_block->ictl |= (ICTL_STCTL | ICTL_PINT);
	}
189 190 191

	if (vcpu->arch.local_int.action_bits & ACTION_STOP_ON_STOP)
		atomic_set_mask(CPUSTAT_STOP_INT, &vcpu->arch.sie_block->cpuflags);
192 193 194 195 196 197 198
}

static void __set_cpuflag(struct kvm_vcpu *vcpu, u32 flag)
{
	atomic_set_mask(flag, &vcpu->arch.sie_block->cpuflags);
}

199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225
static void set_intercept_indicators_ext(struct kvm_vcpu *vcpu)
{
	if (!(pending_local_irqs(vcpu) & IRQ_PEND_EXT_MASK))
		return;
	if (psw_extint_disabled(vcpu))
		__set_cpuflag(vcpu, CPUSTAT_EXT_INT);
	else
		vcpu->arch.sie_block->lctl |= LCTL_CR0;
}

static void set_intercept_indicators_mchk(struct kvm_vcpu *vcpu)
{
	if (!(pending_local_irqs(vcpu) & IRQ_PEND_MCHK_MASK))
		return;
	if (psw_mchk_disabled(vcpu))
		vcpu->arch.sie_block->ictl |= ICTL_LPSW;
	else
		vcpu->arch.sie_block->lctl |= LCTL_CR14;
}

/* Set interception request for non-deliverable local interrupts */
static void set_intercept_indicators_local(struct kvm_vcpu *vcpu)
{
	set_intercept_indicators_ext(vcpu);
	set_intercept_indicators_mchk(vcpu);
}

226
static void __set_intercept_indicator(struct kvm_vcpu *vcpu,
227
				      struct kvm_s390_interrupt_info *inti)
228 229 230
{
	switch (inti->type) {
	case KVM_S390_INT_SERVICE:
231
	case KVM_S390_INT_PFAULT_DONE:
232 233 234 235 236 237
	case KVM_S390_INT_VIRTIO:
		if (psw_extint_disabled(vcpu))
			__set_cpuflag(vcpu, CPUSTAT_EXT_INT);
		else
			vcpu->arch.sie_block->lctl |= LCTL_CR0;
		break;
238 239 240 241 242 243
	case KVM_S390_MCHK:
		if (psw_mchk_disabled(vcpu))
			vcpu->arch.sie_block->ictl |= ICTL_LPSW;
		else
			vcpu->arch.sie_block->lctl |= LCTL_CR14;
		break;
244 245 246 247 248 249
	case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
		if (psw_ioint_disabled(vcpu))
			__set_cpuflag(vcpu, CPUSTAT_IO_INT);
		else
			vcpu->arch.sie_block->lctl |= LCTL_CR6;
		break;
250 251 252 253 254
	default:
		BUG();
	}
}

255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273
static u16 get_ilc(struct kvm_vcpu *vcpu)
{
	const unsigned short table[] = { 2, 4, 4, 6 };

	switch (vcpu->arch.sie_block->icptcode) {
	case ICPT_INST:
	case ICPT_INSTPROGI:
	case ICPT_OPEREXC:
	case ICPT_PARTEXEC:
	case ICPT_IOINST:
		/* last instruction only stored for these icptcodes */
		return table[vcpu->arch.sie_block->ipa >> 14];
	case ICPT_PROGI:
		return vcpu->arch.sie_block->pgmilc;
	default:
		return 0;
	}
}

274 275
static int __must_check __deliver_cpu_timer(struct kvm_vcpu *vcpu)
{
276
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
277 278 279 280 281 282 283
	int rc;

	trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_INT_CPU_TIMER,
					 0, 0);

	rc  = put_guest_lc(vcpu, EXT_IRQ_CPU_TIMER,
			   (u16 *)__LC_EXT_INT_CODE);
284
	rc |= put_guest_lc(vcpu, 0, (u16 *)__LC_EXT_CPU_ADDR);
285 286 287 288
	rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW,
			     &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
	rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW,
			    &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
289
	clear_bit(IRQ_PEND_EXT_CPU_TIMER, &li->pending_irqs);
290
	return rc ? -EFAULT : 0;
291 292 293 294
}

static int __must_check __deliver_ckc(struct kvm_vcpu *vcpu)
{
295
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
296 297 298 299 300 301 302
	int rc;

	trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_INT_CLOCK_COMP,
					 0, 0);

	rc  = put_guest_lc(vcpu, EXT_IRQ_CLK_COMP,
			   (u16 __user *)__LC_EXT_INT_CODE);
303
	rc |= put_guest_lc(vcpu, 0, (u16 *)__LC_EXT_CPU_ADDR);
304 305 306 307
	rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW,
			     &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
	rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW,
			    &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
308
	clear_bit(IRQ_PEND_EXT_CLOCK_COMP, &li->pending_irqs);
309
	return rc ? -EFAULT : 0;
310 311
}

312
static int __must_check __deliver_pfault_init(struct kvm_vcpu *vcpu)
313
{
314 315
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
	struct kvm_s390_ext_info ext;
316 317
	int rc;

318 319 320 321 322 323
	spin_lock(&li->lock);
	ext = li->irq.ext;
	clear_bit(IRQ_PEND_PFAULT_INIT, &li->pending_irqs);
	li->irq.ext.ext_params2 = 0;
	spin_unlock(&li->lock);

324
	VCPU_EVENT(vcpu, 4, "interrupt: pfault init parm:%x,parm64:%llx",
325
		   0, ext.ext_params2);
326 327
	trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id,
					 KVM_S390_INT_PFAULT_INIT,
328
					 0, ext.ext_params2);
329 330 331 332 333 334 335

	rc  = put_guest_lc(vcpu, EXT_IRQ_CP_SERVICE, (u16 *) __LC_EXT_INT_CODE);
	rc |= put_guest_lc(vcpu, PFAULT_INIT, (u16 *) __LC_EXT_CPU_ADDR);
	rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW,
			     &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
	rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW,
			    &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
336
	rc |= put_guest_lc(vcpu, ext.ext_params2, (u64 *) __LC_EXT_PARAMS2);
337
	return rc ? -EFAULT : 0;
338 339
}

340
static int __must_check __deliver_machine_check(struct kvm_vcpu *vcpu)
341
{
342 343
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
	struct kvm_s390_mchk_info mchk;
344 345
	int rc;

346 347 348 349 350 351 352 353 354 355 356 357
	spin_lock(&li->lock);
	mchk = li->irq.mchk;
	/*
	 * If there was an exigent machine check pending, then any repressible
	 * machine checks that might have been pending are indicated along
	 * with it, so always clear both bits
	 */
	clear_bit(IRQ_PEND_MCHK_EX, &li->pending_irqs);
	clear_bit(IRQ_PEND_MCHK_REP, &li->pending_irqs);
	memset(&li->irq.mchk, 0, sizeof(mchk));
	spin_unlock(&li->lock);

358
	VCPU_EVENT(vcpu, 4, "interrupt: machine check mcic=%llx",
359
		   mchk.mcic);
360
	trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_MCHK,
361
					 mchk.cr14, mchk.mcic);
362 363

	rc  = kvm_s390_vcpu_store_status(vcpu, KVM_S390_STORE_STATUS_PREFIXED);
364
	rc |= put_guest_lc(vcpu, mchk.mcic,
365
			   (u64 __user *) __LC_MCCK_CODE);
366
	rc |= put_guest_lc(vcpu, mchk.failing_storage_address,
367 368
			   (u64 __user *) __LC_MCCK_FAIL_STOR_ADDR);
	rc |= write_guest_lc(vcpu, __LC_PSW_SAVE_AREA,
369
			     &mchk.fixed_logout, sizeof(mchk.fixed_logout));
370 371 372 373
	rc |= write_guest_lc(vcpu, __LC_MCK_OLD_PSW,
			     &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
	rc |= read_guest_lc(vcpu, __LC_MCK_NEW_PSW,
			    &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
374
	return rc ? -EFAULT : 0;
375 376 377 378
}

static int __must_check __deliver_restart(struct kvm_vcpu *vcpu)
{
379
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
380 381 382 383 384 385 386 387 388 389 390
	int rc;

	VCPU_EVENT(vcpu, 4, "%s", "interrupt: cpu restart");
	vcpu->stat.deliver_restart_signal++;
	trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_RESTART, 0, 0);

	rc  = write_guest_lc(vcpu,
			     offsetof(struct _lowcore, restart_old_psw),
			     &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
	rc |= read_guest_lc(vcpu, offsetof(struct _lowcore, restart_psw),
			    &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
391
	clear_bit(IRQ_PEND_RESTART, &li->pending_irqs);
392
	return rc ? -EFAULT : 0;
393 394 395 396 397 398 399 400 401 402
}

static int __must_check __deliver_stop(struct kvm_vcpu *vcpu)
{
	VCPU_EVENT(vcpu, 4, "%s", "interrupt: cpu stop");
	vcpu->stat.deliver_stop_signal++;
	trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_SIGP_STOP,
					 0, 0);

	__set_cpuflag(vcpu, CPUSTAT_STOP_INT);
403
	clear_bit(IRQ_PEND_SIGP_STOP, &vcpu->arch.local_int.pending_irqs);
404 405 406
	return 0;
}

407
static int __must_check __deliver_set_prefix(struct kvm_vcpu *vcpu)
408
{
409 410 411 412 413 414 415 416
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
	struct kvm_s390_prefix_info prefix;

	spin_lock(&li->lock);
	prefix = li->irq.prefix;
	li->irq.prefix.address = 0;
	clear_bit(IRQ_PEND_SET_PREFIX, &li->pending_irqs);
	spin_unlock(&li->lock);
417

418
	VCPU_EVENT(vcpu, 4, "interrupt: set prefix to %x", prefix.address);
419 420 421
	vcpu->stat.deliver_prefix_signal++;
	trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id,
					 KVM_S390_SIGP_SET_PREFIX,
422
					 prefix.address, 0);
423

424
	kvm_s390_set_prefix(vcpu, prefix.address);
425 426 427
	return 0;
}

428
static int __must_check __deliver_emergency_signal(struct kvm_vcpu *vcpu)
429
{
430
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
431
	int rc;
432 433 434 435 436 437 438 439
	int cpu_addr;

	spin_lock(&li->lock);
	cpu_addr = find_first_bit(li->sigp_emerg_pending, KVM_MAX_VCPUS);
	clear_bit(cpu_addr, li->sigp_emerg_pending);
	if (bitmap_empty(li->sigp_emerg_pending, KVM_MAX_VCPUS))
		clear_bit(IRQ_PEND_EXT_EMERGENCY, &li->pending_irqs);
	spin_unlock(&li->lock);
440 441 442

	VCPU_EVENT(vcpu, 4, "%s", "interrupt: sigp emerg");
	vcpu->stat.deliver_emergency_signal++;
443 444
	trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_INT_EMERGENCY,
					 cpu_addr, 0);
445 446 447

	rc  = put_guest_lc(vcpu, EXT_IRQ_EMERGENCY_SIG,
			   (u16 *)__LC_EXT_INT_CODE);
448
	rc |= put_guest_lc(vcpu, cpu_addr, (u16 *)__LC_EXT_CPU_ADDR);
449 450 451 452
	rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW,
			     &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
	rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW,
			    &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
453
	return rc ? -EFAULT : 0;
454 455
}

456
static int __must_check __deliver_external_call(struct kvm_vcpu *vcpu)
457
{
458 459
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
	struct kvm_s390_extcall_info extcall;
460 461
	int rc;

462 463 464 465 466 467
	spin_lock(&li->lock);
	extcall = li->irq.extcall;
	li->irq.extcall.code = 0;
	clear_bit(IRQ_PEND_EXT_EXTERNAL, &li->pending_irqs);
	spin_unlock(&li->lock);

468 469 470 471
	VCPU_EVENT(vcpu, 4, "%s", "interrupt: sigp ext call");
	vcpu->stat.deliver_external_call++;
	trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id,
					 KVM_S390_INT_EXTERNAL_CALL,
472
					 extcall.code, 0);
473 474 475

	rc  = put_guest_lc(vcpu, EXT_IRQ_EXTERNAL_CALL,
			   (u16 *)__LC_EXT_INT_CODE);
476
	rc |= put_guest_lc(vcpu, extcall.code, (u16 *)__LC_EXT_CPU_ADDR);
477 478 479 480
	rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW,
			     &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
	rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW, &vcpu->arch.sie_block->gpsw,
			    sizeof(psw_t));
481
	return rc ? -EFAULT : 0;
482 483
}

484
static int __must_check __deliver_prog(struct kvm_vcpu *vcpu)
485
{
486 487
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
	struct kvm_s390_pgm_info pgm_info;
488
	int rc = 0;
489
	u16 ilc = get_ilc(vcpu);
490

491 492 493 494 495 496
	spin_lock(&li->lock);
	pgm_info = li->irq.pgm;
	clear_bit(IRQ_PEND_PROG, &li->pending_irqs);
	memset(&li->irq.pgm, 0, sizeof(pgm_info));
	spin_unlock(&li->lock);

497
	VCPU_EVENT(vcpu, 4, "interrupt: pgm check code:%x, ilc:%x",
498
		   pgm_info.code, ilc);
499 500
	vcpu->stat.deliver_program_int++;
	trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_PROGRAM_INT,
501
					 pgm_info.code, 0);
502

503
	switch (pgm_info.code & ~PGM_PER) {
504 505 506 507 508 509 510 511 512 513
	case PGM_AFX_TRANSLATION:
	case PGM_ASX_TRANSLATION:
	case PGM_EX_TRANSLATION:
	case PGM_LFX_TRANSLATION:
	case PGM_LSTE_SEQUENCE:
	case PGM_LSX_TRANSLATION:
	case PGM_LX_TRANSLATION:
	case PGM_PRIMARY_AUTHORITY:
	case PGM_SECONDARY_AUTHORITY:
	case PGM_SPACE_SWITCH:
514
		rc = put_guest_lc(vcpu, pgm_info.trans_exc_code,
515 516 517 518 519 520 521 522
				  (u64 *)__LC_TRANS_EXC_CODE);
		break;
	case PGM_ALEN_TRANSLATION:
	case PGM_ALE_SEQUENCE:
	case PGM_ASTE_INSTANCE:
	case PGM_ASTE_SEQUENCE:
	case PGM_ASTE_VALIDITY:
	case PGM_EXTENDED_AUTHORITY:
523
		rc = put_guest_lc(vcpu, pgm_info.exc_access_id,
524 525 526 527 528 529 530 531
				  (u8 *)__LC_EXC_ACCESS_ID);
		break;
	case PGM_ASCE_TYPE:
	case PGM_PAGE_TRANSLATION:
	case PGM_REGION_FIRST_TRANS:
	case PGM_REGION_SECOND_TRANS:
	case PGM_REGION_THIRD_TRANS:
	case PGM_SEGMENT_TRANSLATION:
532
		rc = put_guest_lc(vcpu, pgm_info.trans_exc_code,
533
				  (u64 *)__LC_TRANS_EXC_CODE);
534
		rc |= put_guest_lc(vcpu, pgm_info.exc_access_id,
535
				   (u8 *)__LC_EXC_ACCESS_ID);
536
		rc |= put_guest_lc(vcpu, pgm_info.op_access_id,
537 538 539
				   (u8 *)__LC_OP_ACCESS_ID);
		break;
	case PGM_MONITOR:
540
		rc = put_guest_lc(vcpu, pgm_info.mon_class_nr,
541
				  (u16 *)__LC_MON_CLASS_NR);
542
		rc |= put_guest_lc(vcpu, pgm_info.mon_code,
543 544 545
				   (u64 *)__LC_MON_CODE);
		break;
	case PGM_DATA:
546
		rc = put_guest_lc(vcpu, pgm_info.data_exc_code,
547 548 549
				  (u32 *)__LC_DATA_EXC_CODE);
		break;
	case PGM_PROTECTION:
550
		rc = put_guest_lc(vcpu, pgm_info.trans_exc_code,
551
				  (u64 *)__LC_TRANS_EXC_CODE);
552
		rc |= put_guest_lc(vcpu, pgm_info.exc_access_id,
553 554 555 556
				   (u8 *)__LC_EXC_ACCESS_ID);
		break;
	}

557 558
	if (pgm_info.code & PGM_PER) {
		rc |= put_guest_lc(vcpu, pgm_info.per_code,
559
				   (u8 *) __LC_PER_CODE);
560
		rc |= put_guest_lc(vcpu, pgm_info.per_atmid,
561
				   (u8 *)__LC_PER_ATMID);
562
		rc |= put_guest_lc(vcpu, pgm_info.per_address,
563
				   (u64 *) __LC_PER_ADDRESS);
564
		rc |= put_guest_lc(vcpu, pgm_info.per_access_id,
565 566 567
				   (u8 *) __LC_PER_ACCESS_ID);
	}

568
	rc |= put_guest_lc(vcpu, ilc, (u16 *) __LC_PGM_ILC);
569
	rc |= put_guest_lc(vcpu, pgm_info.code,
570 571 572 573 574
			   (u16 *)__LC_PGM_INT_CODE);
	rc |= write_guest_lc(vcpu, __LC_PGM_OLD_PSW,
			     &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
	rc |= read_guest_lc(vcpu, __LC_PGM_NEW_PSW,
			    &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
575
	return rc ? -EFAULT : 0;
576 577 578 579 580 581 582 583 584 585 586 587 588 589
}

static int __must_check __deliver_service(struct kvm_vcpu *vcpu,
					  struct kvm_s390_interrupt_info *inti)
{
	int rc;

	VCPU_EVENT(vcpu, 4, "interrupt: sclp parm:%x",
		   inti->ext.ext_params);
	vcpu->stat.deliver_service_signal++;
	trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type,
					 inti->ext.ext_params, 0);

	rc  = put_guest_lc(vcpu, EXT_IRQ_SERVICE_SIG, (u16 *)__LC_EXT_INT_CODE);
590
	rc |= put_guest_lc(vcpu, 0, (u16 *)__LC_EXT_CPU_ADDR);
591 592 593 594 595 596
	rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW,
			     &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
	rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW,
			    &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
	rc |= put_guest_lc(vcpu, inti->ext.ext_params,
			   (u32 *)__LC_EXT_PARAMS);
597
	return rc ? -EFAULT : 0;
598 599 600 601 602 603 604 605 606 607
}

static int __must_check __deliver_pfault_done(struct kvm_vcpu *vcpu,
					   struct kvm_s390_interrupt_info *inti)
{
	int rc;

	trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id,
					 KVM_S390_INT_PFAULT_DONE, 0,
					 inti->ext.ext_params2);
608

609 610 611 612 613 614 615 616
	rc  = put_guest_lc(vcpu, EXT_IRQ_CP_SERVICE, (u16 *)__LC_EXT_INT_CODE);
	rc |= put_guest_lc(vcpu, PFAULT_DONE, (u16 *)__LC_EXT_CPU_ADDR);
	rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW,
			     &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
	rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW,
			    &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
	rc |= put_guest_lc(vcpu, inti->ext.ext_params2,
			   (u64 *)__LC_EXT_PARAMS2);
617
	return rc ? -EFAULT : 0;
618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641
}

static int __must_check __deliver_virtio(struct kvm_vcpu *vcpu,
					 struct kvm_s390_interrupt_info *inti)
{
	int rc;

	VCPU_EVENT(vcpu, 4, "interrupt: virtio parm:%x,parm64:%llx",
		   inti->ext.ext_params, inti->ext.ext_params2);
	vcpu->stat.deliver_virtio_interrupt++;
	trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type,
					 inti->ext.ext_params,
					 inti->ext.ext_params2);

	rc  = put_guest_lc(vcpu, EXT_IRQ_CP_SERVICE, (u16 *)__LC_EXT_INT_CODE);
	rc |= put_guest_lc(vcpu, VIRTIO_PARAM, (u16 *)__LC_EXT_CPU_ADDR);
	rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW,
			     &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
	rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW,
			    &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
	rc |= put_guest_lc(vcpu, inti->ext.ext_params,
			   (u32 *)__LC_EXT_PARAMS);
	rc |= put_guest_lc(vcpu, inti->ext.ext_params2,
			   (u64 *)__LC_EXT_PARAMS2);
642
	return rc ? -EFAULT : 0;
643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669
}

static int __must_check __deliver_io(struct kvm_vcpu *vcpu,
				     struct kvm_s390_interrupt_info *inti)
{
	int rc;

	VCPU_EVENT(vcpu, 4, "interrupt: I/O %llx", inti->type);
	vcpu->stat.deliver_io_int++;
	trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type,
					 ((__u32)inti->io.subchannel_id << 16) |
						inti->io.subchannel_nr,
					 ((__u64)inti->io.io_int_parm << 32) |
						inti->io.io_int_word);

	rc  = put_guest_lc(vcpu, inti->io.subchannel_id,
			   (u16 *)__LC_SUBCHANNEL_ID);
	rc |= put_guest_lc(vcpu, inti->io.subchannel_nr,
			   (u16 *)__LC_SUBCHANNEL_NR);
	rc |= put_guest_lc(vcpu, inti->io.io_int_parm,
			   (u32 *)__LC_IO_INT_PARM);
	rc |= put_guest_lc(vcpu, inti->io.io_int_word,
			   (u32 *)__LC_IO_INT_WORD);
	rc |= write_guest_lc(vcpu, __LC_IO_OLD_PSW,
			     &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
	rc |= read_guest_lc(vcpu, __LC_IO_NEW_PSW,
			    &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
670
	return rc ? -EFAULT : 0;
671 672
}

673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694
static int __must_check __deliver_mchk_floating(struct kvm_vcpu *vcpu,
					   struct kvm_s390_interrupt_info *inti)
{
	struct kvm_s390_mchk_info *mchk = &inti->mchk;
	int rc;

	VCPU_EVENT(vcpu, 4, "interrupt: machine check mcic=%llx",
		   mchk->mcic);
	trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_MCHK,
					 mchk->cr14, mchk->mcic);

	rc  = kvm_s390_vcpu_store_status(vcpu, KVM_S390_STORE_STATUS_PREFIXED);
	rc |= put_guest_lc(vcpu, mchk->mcic,
			(u64 __user *) __LC_MCCK_CODE);
	rc |= put_guest_lc(vcpu, mchk->failing_storage_address,
			(u64 __user *) __LC_MCCK_FAIL_STOR_ADDR);
	rc |= write_guest_lc(vcpu, __LC_PSW_SAVE_AREA,
			     &mchk->fixed_logout, sizeof(mchk->fixed_logout));
	rc |= write_guest_lc(vcpu, __LC_MCK_OLD_PSW,
			     &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
	rc |= read_guest_lc(vcpu, __LC_MCK_NEW_PSW,
			    &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
695
	return rc ? -EFAULT : 0;
696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714
}

typedef int (*deliver_irq_t)(struct kvm_vcpu *vcpu);

static const deliver_irq_t deliver_irq_funcs[] = {
	[IRQ_PEND_MCHK_EX]        = __deliver_machine_check,
	[IRQ_PEND_PROG]           = __deliver_prog,
	[IRQ_PEND_EXT_EMERGENCY]  = __deliver_emergency_signal,
	[IRQ_PEND_EXT_EXTERNAL]   = __deliver_external_call,
	[IRQ_PEND_EXT_CLOCK_COMP] = __deliver_ckc,
	[IRQ_PEND_EXT_CPU_TIMER]  = __deliver_cpu_timer,
	[IRQ_PEND_RESTART]        = __deliver_restart,
	[IRQ_PEND_SIGP_STOP]      = __deliver_stop,
	[IRQ_PEND_SET_PREFIX]     = __deliver_set_prefix,
	[IRQ_PEND_PFAULT_INIT]    = __deliver_pfault_init,
};

static int __must_check __deliver_floating_interrupt(struct kvm_vcpu *vcpu,
					   struct kvm_s390_interrupt_info *inti)
715
{
716
	int rc;
717 718 719

	switch (inti->type) {
	case KVM_S390_INT_SERVICE:
720
		rc = __deliver_service(vcpu, inti);
721
		break;
722
	case KVM_S390_INT_PFAULT_DONE:
723
		rc = __deliver_pfault_done(vcpu, inti);
724
		break;
725
	case KVM_S390_INT_VIRTIO:
726
		rc = __deliver_virtio(vcpu, inti);
727
		break;
728
	case KVM_S390_MCHK:
729
		rc = __deliver_mchk_floating(vcpu, inti);
730
		break;
731
	case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
732
		rc = __deliver_io(vcpu, inti);
733
		break;
734 735 736
	default:
		BUG();
	}
737 738

	return rc;
739 740
}

741 742 743 744 745 746 747 748 749 750 751 752 753 754
/* Check whether SIGP interpretation facility has an external call pending */
int kvm_s390_si_ext_call_pending(struct kvm_vcpu *vcpu)
{
	atomic_t *sigp_ctrl = &vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].ctrl;

	if (!psw_extint_disabled(vcpu) &&
	    (vcpu->arch.sie_block->gcr[0] & 0x2000ul) &&
	    (atomic_read(sigp_ctrl) & SIGP_CTRL_C) &&
	    (atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_ECALL_PEND))
		return 1;

	return 0;
}

755
int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu)
756
{
757 758
	struct kvm_s390_float_interrupt *fi = vcpu->arch.local_int.float_int;
	struct kvm_s390_interrupt_info  *inti;
759
	int rc;
760

761
	rc = !!deliverable_local_irqs(vcpu);
762 763

	if ((!rc) && atomic_read(&fi->active)) {
764
		spin_lock(&fi->lock);
765 766 767 768 769
		list_for_each_entry(inti, &fi->list, list)
			if (__interrupt_is_deliverable(vcpu, inti)) {
				rc = 1;
				break;
			}
770
		spin_unlock(&fi->lock);
771 772
	}

773 774
	if (!rc && kvm_cpu_has_pending_timer(vcpu))
		rc = 1;
775

776 777 778
	if (!rc && kvm_s390_si_ext_call_pending(vcpu))
		rc = 1;

779 780 781
	return rc;
}

782 783
int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
{
784 785 786 787 788 789
	if (!(vcpu->arch.sie_block->ckc <
	      get_tod_clock_fast() + vcpu->arch.sie_block->epoch))
		return 0;
	if (!ckc_interrupts_enabled(vcpu))
		return 0;
	return 1;
790 791
}

792 793 794 795 796 797
int kvm_s390_handle_wait(struct kvm_vcpu *vcpu)
{
	u64 now, sltime;

	vcpu->stat.exit_wait_state++;

798 799 800
	/* fast path */
	if (kvm_cpu_has_pending_timer(vcpu) || kvm_arch_vcpu_runnable(vcpu))
		return 0;
801

802 803
	if (psw_interrupts_disabled(vcpu)) {
		VCPU_EVENT(vcpu, 3, "%s", "disabled wait");
804
		return -EOPNOTSUPP; /* disabled wait */
805 806
	}

807
	__set_cpu_idle(vcpu);
808
	if (!ckc_interrupts_enabled(vcpu)) {
809 810 811 812
		VCPU_EVENT(vcpu, 3, "%s", "enabled wait w/o timer");
		goto no_timer;
	}

813
	now = get_tod_clock_fast() + vcpu->arch.sie_block->epoch;
814
	sltime = tod_to_ns(vcpu->arch.sie_block->ckc - now);
815 816
	hrtimer_start(&vcpu->arch.ckc_timer, ktime_set (0, sltime) , HRTIMER_MODE_REL);
	VCPU_EVENT(vcpu, 5, "enabled wait via clock comparator: %llx ns", sltime);
817
no_timer:
818
	srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
819
	kvm_vcpu_block(vcpu);
820
	__unset_cpu_idle(vcpu);
821 822
	vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);

823
	hrtimer_try_to_cancel(&vcpu->arch.ckc_timer);
824 825 826
	return 0;
}

827 828 829 830 831 832 833 834 835
void kvm_s390_vcpu_wakeup(struct kvm_vcpu *vcpu)
{
	if (waitqueue_active(&vcpu->wq)) {
		/*
		 * The vcpu gave up the cpu voluntarily, mark it as a good
		 * yield-candidate.
		 */
		vcpu->preempted = true;
		wake_up_interruptible(&vcpu->wq);
836
		vcpu->stat.halt_wakeup++;
837 838 839
	}
}

840 841 842 843 844
enum hrtimer_restart kvm_s390_idle_wakeup(struct hrtimer *timer)
{
	struct kvm_vcpu *vcpu;

	vcpu = container_of(timer, struct kvm_vcpu, arch.ckc_timer);
845
	kvm_s390_vcpu_wakeup(vcpu);
846 847 848

	return HRTIMER_NORESTART;
}
849

850 851 852 853
void kvm_s390_clear_local_irqs(struct kvm_vcpu *vcpu)
{
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;

854
	spin_lock(&li->lock);
855 856 857
	li->pending_irqs = 0;
	bitmap_zero(li->sigp_emerg_pending, KVM_MAX_VCPUS);
	memset(&li->irq, 0, sizeof(li->irq));
858
	spin_unlock(&li->lock);
859 860

	/* clear pending external calls set by sigp interpretation facility */
861
	atomic_clear_mask(CPUSTAT_ECALL_PEND, li->cpuflags);
862 863
	atomic_clear_mask(SIGP_CTRL_C,
			  &vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].ctrl);
864 865
}

866
int __must_check kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu)
867
{
868 869 870
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
	struct kvm_s390_float_interrupt *fi = vcpu->arch.local_int.float_int;
	struct kvm_s390_interrupt_info  *n, *inti = NULL;
871
	deliver_irq_t func;
872
	int deliver;
873
	int rc = 0;
874 875
	unsigned long irq_type;
	unsigned long deliverable_irqs;
876 877 878

	__reset_intercept_indicators(vcpu);

879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899
	/* pending ckc conditions might have been invalidated */
	clear_bit(IRQ_PEND_EXT_CLOCK_COMP, &li->pending_irqs);
	if (kvm_cpu_has_pending_timer(vcpu))
		set_bit(IRQ_PEND_EXT_CLOCK_COMP, &li->pending_irqs);

	do {
		deliverable_irqs = deliverable_local_irqs(vcpu);
		/* bits are in the order of interrupt priority */
		irq_type = find_first_bit(&deliverable_irqs, IRQ_PEND_COUNT);
		if (irq_type == IRQ_PEND_COUNT)
			break;
		func = deliver_irq_funcs[irq_type];
		if (!func) {
			WARN_ON_ONCE(func == NULL);
			clear_bit(irq_type, &li->pending_irqs);
			continue;
		}
		rc = func(vcpu);
	} while (!rc && irq_type != IRQ_PEND_COUNT);

	set_intercept_indicators_local(vcpu);
900

901
	if (!rc && atomic_read(&fi->active)) {
902 903
		do {
			deliver = 0;
904
			spin_lock(&fi->lock);
905 906 907
			list_for_each_entry_safe(inti, n, &fi->list, list) {
				if (__interrupt_is_deliverable(vcpu, inti)) {
					list_del(&inti->list);
J
Jens Freimann 已提交
908
					fi->irq_count--;
909 910 911 912 913 914 915
					deliver = 1;
					break;
				}
				__set_intercept_indicator(vcpu, inti);
			}
			if (list_empty(&fi->list))
				atomic_set(&fi->active, 0);
916
			spin_unlock(&fi->lock);
917
			if (deliver) {
918
				rc = __deliver_floating_interrupt(vcpu, inti);
919 920
				kfree(inti);
			}
921
		} while (!rc && deliver);
922
	}
923 924

	return rc;
925 926
}

927
static int __inject_prog(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
928 929 930
{
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;

931
	li->irq.pgm = irq->u.pgm;
932
	set_bit(IRQ_PEND_PROG, &li->pending_irqs);
933 934 935
	return 0;
}

936 937
int kvm_s390_inject_program_int(struct kvm_vcpu *vcpu, u16 code)
{
938
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
939
	struct kvm_s390_irq irq;
940 941

	VCPU_EVENT(vcpu, 3, "inject: program check %d (from kernel)", code);
942 943
	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_PROGRAM_INT, code,
				   0, 1);
944
	spin_lock(&li->lock);
945 946
	irq.u.pgm.code = code;
	__inject_prog(vcpu, &irq);
947
	BUG_ON(waitqueue_active(li->wq));
948
	spin_unlock(&li->lock);
949 950 951 952 953 954 955
	return 0;
}

int kvm_s390_inject_prog_irq(struct kvm_vcpu *vcpu,
			     struct kvm_s390_pgm_info *pgm_info)
{
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
956
	struct kvm_s390_irq irq;
957
	int rc;
958 959 960 961 962

	VCPU_EVENT(vcpu, 3, "inject: prog irq %d (from kernel)",
		   pgm_info->code);
	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_PROGRAM_INT,
				   pgm_info->code, 0, 1);
963
	spin_lock(&li->lock);
964 965
	irq.u.pgm = *pgm_info;
	rc = __inject_prog(vcpu, &irq);
966
	BUG_ON(waitqueue_active(li->wq));
967
	spin_unlock(&li->lock);
968 969 970
	return rc;
}

971
static int __inject_pfault_init(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
972 973 974
{
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;

975 976 977 978 979 980 981 982
	VCPU_EVENT(vcpu, 3, "inject: external irq params:%x, params2:%llx",
		   irq->u.ext.ext_params, irq->u.ext.ext_params2);
	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_INT_PFAULT_INIT,
				   irq->u.ext.ext_params,
				   irq->u.ext.ext_params2, 2);

	li->irq.ext = irq->u.ext;
	set_bit(IRQ_PEND_PFAULT_INIT, &li->pending_irqs);
983 984 985 986
	atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags);
	return 0;
}

987
int __inject_extcall(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
988 989
{
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
990
	struct kvm_s390_extcall_info *extcall = &li->irq.extcall;
991 992

	VCPU_EVENT(vcpu, 3, "inject: external call source-cpu:%u",
993 994 995 996 997
		   irq->u.extcall.code);
	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_INT_EXTERNAL_CALL,
				   irq->u.extcall.code, 0, 2);

	*extcall = irq->u.extcall;
998
	set_bit(IRQ_PEND_EXT_EXTERNAL, &li->pending_irqs);
999 1000 1001 1002
	atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags);
	return 0;
}

1003
static int __inject_set_prefix(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
1004 1005
{
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
1006
	struct kvm_s390_prefix_info *prefix = &li->irq.prefix;
1007 1008

	VCPU_EVENT(vcpu, 3, "inject: set prefix to %x (from user)",
1009 1010 1011 1012 1013 1014
		   prefix->address);
	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_SIGP_SET_PREFIX,
				   prefix->address, 0, 2);

	*prefix = irq->u.prefix;
	set_bit(IRQ_PEND_SET_PREFIX, &li->pending_irqs);
1015 1016 1017
	return 0;
}

1018
static int __inject_sigp_stop(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
1019 1020 1021
{
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;

1022 1023
	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_SIGP_STOP, 0, 0, 2);

1024
	li->action_bits |= ACTION_STOP_ON_STOP;
1025
	set_bit(IRQ_PEND_SIGP_STOP, &li->pending_irqs);
1026 1027 1028 1029
	return 0;
}

static int __inject_sigp_restart(struct kvm_vcpu *vcpu,
1030
				 struct kvm_s390_irq *irq)
1031 1032 1033
{
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;

1034 1035 1036 1037
	VCPU_EVENT(vcpu, 3, "inject: restart type %llx", irq->type);
	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_RESTART, 0, 0, 2);

	set_bit(IRQ_PEND_RESTART, &li->pending_irqs);
1038 1039 1040 1041
	return 0;
}

static int __inject_sigp_emergency(struct kvm_vcpu *vcpu,
1042
				   struct kvm_s390_irq *irq)
1043 1044
{
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
1045
	struct kvm_s390_emerg_info *emerg = &li->irq.emerg;
1046

1047 1048 1049 1050 1051 1052 1053
	VCPU_EVENT(vcpu, 3, "inject: emergency %u\n",
		   irq->u.emerg.code);
	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_INT_EMERGENCY,
				   emerg->code, 0, 2);

	set_bit(emerg->code, li->sigp_emerg_pending);
	set_bit(IRQ_PEND_EXT_EMERGENCY, &li->pending_irqs);
1054 1055 1056 1057
	atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags);
	return 0;
}

1058
static int __inject_mchk(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
1059 1060
{
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
1061
	struct kvm_s390_mchk_info *mchk = &li->irq.mchk;
1062 1063

	VCPU_EVENT(vcpu, 5, "inject: machine check parm64:%llx",
1064 1065 1066 1067 1068
		   mchk->mcic);
	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_MCHK, 0,
				   mchk->mcic, 2);

	/*
1069 1070 1071 1072 1073 1074
	 * Because repressible machine checks can be indicated along with
	 * exigent machine checks (PoP, Chapter 11, Interruption action)
	 * we need to combine cr14, mcic and external damage code.
	 * Failing storage address and the logout area should not be or'ed
	 * together, we just indicate the last occurrence of the corresponding
	 * machine check
1075
	 */
1076
	mchk->cr14 |= irq->u.mchk.cr14;
1077
	mchk->mcic |= irq->u.mchk.mcic;
1078 1079 1080 1081
	mchk->ext_damage_code |= irq->u.mchk.ext_damage_code;
	mchk->failing_storage_address = irq->u.mchk.failing_storage_address;
	memcpy(&mchk->fixed_logout, &irq->u.mchk.fixed_logout,
	       sizeof(mchk->fixed_logout));
1082 1083 1084 1085
	if (mchk->mcic & MCHK_EX_MASK)
		set_bit(IRQ_PEND_MCHK_EX, &li->pending_irqs);
	else if (mchk->mcic & MCHK_REP_MASK)
		set_bit(IRQ_PEND_MCHK_REP,  &li->pending_irqs);
1086 1087 1088
	return 0;
}

1089
static int __inject_ckc(struct kvm_vcpu *vcpu)
1090 1091 1092
{
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;

1093 1094 1095 1096 1097
	VCPU_EVENT(vcpu, 3, "inject: type %x", KVM_S390_INT_CLOCK_COMP);
	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_INT_CLOCK_COMP,
				   0, 0, 2);

	set_bit(IRQ_PEND_EXT_CLOCK_COMP, &li->pending_irqs);
1098 1099 1100 1101
	atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags);
	return 0;
}

1102
static int __inject_cpu_timer(struct kvm_vcpu *vcpu)
1103 1104 1105
{
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;

1106 1107 1108 1109 1110
	VCPU_EVENT(vcpu, 3, "inject: type %x", KVM_S390_INT_CPU_TIMER);
	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_INT_CPU_TIMER,
				   0, 0, 2);

	set_bit(IRQ_PEND_EXT_CPU_TIMER, &li->pending_irqs);
1111
	atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags);
1112 1113 1114
	return 0;
}

1115

1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130
struct kvm_s390_interrupt_info *kvm_s390_get_io_int(struct kvm *kvm,
						    u64 cr6, u64 schid)
{
	struct kvm_s390_float_interrupt *fi;
	struct kvm_s390_interrupt_info *inti, *iter;

	if ((!schid && !cr6) || (schid && cr6))
		return NULL;
	mutex_lock(&kvm->lock);
	fi = &kvm->arch.float_int;
	spin_lock(&fi->lock);
	inti = NULL;
	list_for_each_entry(iter, &fi->list, list) {
		if (!is_ioint(iter->type))
			continue;
C
Cornelia Huck 已提交
1131 1132
		if (cr6 &&
		    ((cr6 & int_word_to_isc_bits(iter->io.io_int_word)) == 0))
1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144
			continue;
		if (schid) {
			if (((schid & 0x00000000ffff0000) >> 16) !=
			    iter->io.subchannel_id)
				continue;
			if ((schid & 0x000000000000ffff) !=
			    iter->io.subchannel_nr)
				continue;
		}
		inti = iter;
		break;
	}
J
Jens Freimann 已提交
1145
	if (inti) {
1146
		list_del_init(&inti->list);
J
Jens Freimann 已提交
1147 1148
		fi->irq_count--;
	}
1149 1150 1151 1152 1153 1154
	if (list_empty(&fi->list))
		atomic_set(&fi->active, 0);
	spin_unlock(&fi->lock);
	mutex_unlock(&kvm->lock);
	return inti;
}
1155

J
Jens Freimann 已提交
1156
static int __inject_vm(struct kvm *kvm, struct kvm_s390_interrupt_info *inti)
1157
{
1158 1159
	struct kvm_s390_local_interrupt *li;
	struct kvm_s390_float_interrupt *fi;
1160
	struct kvm_s390_interrupt_info *iter;
1161
	struct kvm_vcpu *dst_vcpu = NULL;
1162
	int sigcpu;
J
Jens Freimann 已提交
1163
	int rc = 0;
1164

1165 1166 1167
	mutex_lock(&kvm->lock);
	fi = &kvm->arch.float_int;
	spin_lock(&fi->lock);
J
Jens Freimann 已提交
1168 1169 1170 1171 1172
	if (fi->irq_count >= KVM_S390_MAX_FLOAT_IRQS) {
		rc = -EINVAL;
		goto unlock_fi;
	}
	fi->irq_count++;
1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195
	if (!is_ioint(inti->type)) {
		list_add_tail(&inti->list, &fi->list);
	} else {
		u64 isc_bits = int_word_to_isc_bits(inti->io.io_int_word);

		/* Keep I/O interrupts sorted in isc order. */
		list_for_each_entry(iter, &fi->list, list) {
			if (!is_ioint(iter->type))
				continue;
			if (int_word_to_isc_bits(iter->io.io_int_word)
			    <= isc_bits)
				continue;
			break;
		}
		list_add_tail(&inti->list, &iter->list);
	}
	atomic_set(&fi->active, 1);
	sigcpu = find_first_bit(fi->idle_mask, KVM_MAX_VCPUS);
	if (sigcpu == KVM_MAX_VCPUS) {
		do {
			sigcpu = fi->next_rr_cpu++;
			if (sigcpu == KVM_MAX_VCPUS)
				sigcpu = fi->next_rr_cpu = 0;
1196
		} while (kvm_get_vcpu(kvm, sigcpu) == NULL);
1197
	}
1198 1199
	dst_vcpu = kvm_get_vcpu(kvm, sigcpu);
	li = &dst_vcpu->arch.local_int;
1200
	spin_lock(&li->lock);
1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211
	switch (inti->type) {
	case KVM_S390_MCHK:
		atomic_set_mask(CPUSTAT_STOP_INT, li->cpuflags);
		break;
	case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
		atomic_set_mask(CPUSTAT_IO_INT, li->cpuflags);
		break;
	default:
		atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags);
		break;
	}
1212
	spin_unlock(&li->lock);
1213
	kvm_s390_vcpu_wakeup(kvm_get_vcpu(kvm, sigcpu));
J
Jens Freimann 已提交
1214
unlock_fi:
1215 1216
	spin_unlock(&fi->lock);
	mutex_unlock(&kvm->lock);
J
Jens Freimann 已提交
1217
	return rc;
1218 1219 1220 1221 1222 1223 1224
}

int kvm_s390_inject_vm(struct kvm *kvm,
		       struct kvm_s390_interrupt *s390int)
{
	struct kvm_s390_interrupt_info *inti;

1225 1226 1227 1228
	inti = kzalloc(sizeof(*inti), GFP_KERNEL);
	if (!inti)
		return -ENOMEM;

1229 1230
	inti->type = s390int->type;
	switch (inti->type) {
1231
	case KVM_S390_INT_VIRTIO:
1232
		VM_EVENT(kvm, 5, "inject: virtio parm:%x,parm64:%llx",
1233 1234 1235 1236 1237 1238 1239 1240
			 s390int->parm, s390int->parm64);
		inti->ext.ext_params = s390int->parm;
		inti->ext.ext_params2 = s390int->parm64;
		break;
	case KVM_S390_INT_SERVICE:
		VM_EVENT(kvm, 5, "inject: sclp parm:%x", s390int->parm);
		inti->ext.ext_params = s390int->parm;
		break;
1241 1242 1243 1244
	case KVM_S390_INT_PFAULT_DONE:
		inti->type = s390int->type;
		inti->ext.ext_params2 = s390int->parm64;
		break;
1245 1246 1247 1248 1249 1250
	case KVM_S390_MCHK:
		VM_EVENT(kvm, 5, "inject: machine check parm64:%llx",
			 s390int->parm64);
		inti->mchk.cr14 = s390int->parm; /* upper bits are not used */
		inti->mchk.mcic = s390int->parm64;
		break;
1251
	case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
1252
		if (inti->type & IOINT_AI_MASK)
1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263
			VM_EVENT(kvm, 5, "%s", "inject: I/O (AI)");
		else
			VM_EVENT(kvm, 5, "inject: I/O css %x ss %x schid %04x",
				 s390int->type & IOINT_CSSID_MASK,
				 s390int->type & IOINT_SSID_MASK,
				 s390int->type & IOINT_SCHID_MASK);
		inti->io.subchannel_id = s390int->parm >> 16;
		inti->io.subchannel_nr = s390int->parm & 0x0000ffffu;
		inti->io.io_int_parm = s390int->parm64 >> 32;
		inti->io.io_int_word = s390int->parm64 & 0x00000000ffffffffull;
		break;
1264 1265 1266 1267
	default:
		kfree(inti);
		return -EINVAL;
	}
1268 1269
	trace_kvm_s390_inject_vm(s390int->type, s390int->parm, s390int->parm64,
				 2);
1270

J
Jens Freimann 已提交
1271
	return __inject_vm(kvm, inti);
1272 1273
}

1274 1275 1276 1277 1278 1279
void kvm_s390_reinject_io_int(struct kvm *kvm,
			      struct kvm_s390_interrupt_info *inti)
{
	__inject_vm(kvm, inti);
}

1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310
int s390int_to_s390irq(struct kvm_s390_interrupt *s390int,
		       struct kvm_s390_irq *irq)
{
	irq->type = s390int->type;
	switch (irq->type) {
	case KVM_S390_PROGRAM_INT:
		if (s390int->parm & 0xffff0000)
			return -EINVAL;
		irq->u.pgm.code = s390int->parm;
		break;
	case KVM_S390_SIGP_SET_PREFIX:
		irq->u.prefix.address = s390int->parm;
		break;
	case KVM_S390_INT_EXTERNAL_CALL:
		if (irq->u.extcall.code & 0xffff0000)
			return -EINVAL;
		irq->u.extcall.code = s390int->parm;
		break;
	case KVM_S390_INT_EMERGENCY:
		if (irq->u.emerg.code & 0xffff0000)
			return -EINVAL;
		irq->u.emerg.code = s390int->parm;
		break;
	case KVM_S390_MCHK:
		irq->u.mchk.mcic = s390int->parm64;
		break;
	}
	return 0;
}

int kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
1311
{
1312 1313
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
	int rc;
1314

1315
	spin_lock(&li->lock);
1316
	switch (irq->type) {
1317 1318
	case KVM_S390_PROGRAM_INT:
		VCPU_EVENT(vcpu, 3, "inject: program check %d (from user)",
1319 1320
			   irq->u.pgm.code);
		rc = __inject_prog(vcpu, irq);
1321
		break;
1322
	case KVM_S390_SIGP_SET_PREFIX:
1323
		rc = __inject_set_prefix(vcpu, irq);
1324
		break;
1325
	case KVM_S390_SIGP_STOP:
1326
		rc = __inject_sigp_stop(vcpu, irq);
1327
		break;
1328
	case KVM_S390_RESTART:
1329
		rc = __inject_sigp_restart(vcpu, irq);
1330
		break;
1331
	case KVM_S390_INT_CLOCK_COMP:
1332
		rc = __inject_ckc(vcpu);
1333
		break;
1334
	case KVM_S390_INT_CPU_TIMER:
1335
		rc = __inject_cpu_timer(vcpu);
1336
		break;
1337
	case KVM_S390_INT_EXTERNAL_CALL:
1338
		rc = __inject_extcall(vcpu, irq);
1339
		break;
1340
	case KVM_S390_INT_EMERGENCY:
1341
		rc = __inject_sigp_emergency(vcpu, irq);
1342
		break;
1343
	case KVM_S390_MCHK:
1344
		rc = __inject_mchk(vcpu, irq);
1345
		break;
1346
	case KVM_S390_INT_PFAULT_INIT:
1347
		rc = __inject_pfault_init(vcpu, irq);
1348
		break;
1349 1350
	case KVM_S390_INT_VIRTIO:
	case KVM_S390_INT_SERVICE:
1351
	case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
1352
	default:
1353
		rc = -EINVAL;
1354
	}
1355
	spin_unlock(&li->lock);
1356 1357 1358
	if (!rc)
		kvm_s390_vcpu_wakeup(vcpu);
	return rc;
1359
}
1360

1361
void kvm_s390_clear_float_irqs(struct kvm *kvm)
1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372
{
	struct kvm_s390_float_interrupt *fi;
	struct kvm_s390_interrupt_info	*n, *inti = NULL;

	mutex_lock(&kvm->lock);
	fi = &kvm->arch.float_int;
	spin_lock(&fi->lock);
	list_for_each_entry_safe(inti, n, &fi->list, list) {
		list_del(&inti->list);
		kfree(inti);
	}
J
Jens Freimann 已提交
1373
	fi->irq_count = 0;
1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386
	atomic_set(&fi->active, 0);
	spin_unlock(&fi->lock);
	mutex_unlock(&kvm->lock);
}

static inline int copy_irq_to_user(struct kvm_s390_interrupt_info *inti,
				   u8 *addr)
{
	struct kvm_s390_irq __user *uptr = (struct kvm_s390_irq __user *) addr;
	struct kvm_s390_irq irq = {0};

	irq.type = inti->type;
	switch (inti->type) {
1387 1388
	case KVM_S390_INT_PFAULT_INIT:
	case KVM_S390_INT_PFAULT_DONE:
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 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467
	case KVM_S390_INT_VIRTIO:
	case KVM_S390_INT_SERVICE:
		irq.u.ext = inti->ext;
		break;
	case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
		irq.u.io = inti->io;
		break;
	case KVM_S390_MCHK:
		irq.u.mchk = inti->mchk;
		break;
	default:
		return -EINVAL;
	}

	if (copy_to_user(uptr, &irq, sizeof(irq)))
		return -EFAULT;

	return 0;
}

static int get_all_floating_irqs(struct kvm *kvm, __u8 *buf, __u64 len)
{
	struct kvm_s390_interrupt_info *inti;
	struct kvm_s390_float_interrupt *fi;
	int ret = 0;
	int n = 0;

	mutex_lock(&kvm->lock);
	fi = &kvm->arch.float_int;
	spin_lock(&fi->lock);

	list_for_each_entry(inti, &fi->list, list) {
		if (len < sizeof(struct kvm_s390_irq)) {
			/* signal userspace to try again */
			ret = -ENOMEM;
			break;
		}
		ret = copy_irq_to_user(inti, buf);
		if (ret)
			break;
		buf += sizeof(struct kvm_s390_irq);
		len -= sizeof(struct kvm_s390_irq);
		n++;
	}

	spin_unlock(&fi->lock);
	mutex_unlock(&kvm->lock);

	return ret < 0 ? ret : n;
}

static int flic_get_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
{
	int r;

	switch (attr->group) {
	case KVM_DEV_FLIC_GET_ALL_IRQS:
		r = get_all_floating_irqs(dev->kvm, (u8 *) attr->addr,
					  attr->attr);
		break;
	default:
		r = -EINVAL;
	}

	return r;
}

static inline int copy_irq_from_user(struct kvm_s390_interrupt_info *inti,
				     u64 addr)
{
	struct kvm_s390_irq __user *uptr = (struct kvm_s390_irq __user *) addr;
	void *target = NULL;
	void __user *source;
	u64 size;

	if (get_user(inti->type, (u64 __user *)addr))
		return -EFAULT;

	switch (inti->type) {
1468 1469
	case KVM_S390_INT_PFAULT_INIT:
	case KVM_S390_INT_PFAULT_DONE:
1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517
	case KVM_S390_INT_VIRTIO:
	case KVM_S390_INT_SERVICE:
		target = (void *) &inti->ext;
		source = &uptr->u.ext;
		size = sizeof(inti->ext);
		break;
	case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
		target = (void *) &inti->io;
		source = &uptr->u.io;
		size = sizeof(inti->io);
		break;
	case KVM_S390_MCHK:
		target = (void *) &inti->mchk;
		source = &uptr->u.mchk;
		size = sizeof(inti->mchk);
		break;
	default:
		return -EINVAL;
	}

	if (copy_from_user(target, source, size))
		return -EFAULT;

	return 0;
}

static int enqueue_floating_irq(struct kvm_device *dev,
				struct kvm_device_attr *attr)
{
	struct kvm_s390_interrupt_info *inti = NULL;
	int r = 0;
	int len = attr->attr;

	if (len % sizeof(struct kvm_s390_irq) != 0)
		return -EINVAL;
	else if (len > KVM_S390_FLIC_MAX_BUFFER)
		return -EINVAL;

	while (len >= sizeof(struct kvm_s390_irq)) {
		inti = kzalloc(sizeof(*inti), GFP_KERNEL);
		if (!inti)
			return -ENOMEM;

		r = copy_irq_from_user(inti, attr->addr);
		if (r) {
			kfree(inti);
			return r;
		}
J
Jens Freimann 已提交
1518 1519 1520 1521 1522
		r = __inject_vm(dev->kvm, inti);
		if (r) {
			kfree(inti);
			return r;
		}
1523 1524 1525 1526 1527 1528 1529
		len -= sizeof(struct kvm_s390_irq);
		attr->addr += sizeof(struct kvm_s390_irq);
	}

	return r;
}

1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595
static struct s390_io_adapter *get_io_adapter(struct kvm *kvm, unsigned int id)
{
	if (id >= MAX_S390_IO_ADAPTERS)
		return NULL;
	return kvm->arch.adapters[id];
}

static int register_io_adapter(struct kvm_device *dev,
			       struct kvm_device_attr *attr)
{
	struct s390_io_adapter *adapter;
	struct kvm_s390_io_adapter adapter_info;

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

	if ((adapter_info.id >= MAX_S390_IO_ADAPTERS) ||
	    (dev->kvm->arch.adapters[adapter_info.id] != NULL))
		return -EINVAL;

	adapter = kzalloc(sizeof(*adapter), GFP_KERNEL);
	if (!adapter)
		return -ENOMEM;

	INIT_LIST_HEAD(&adapter->maps);
	init_rwsem(&adapter->maps_lock);
	atomic_set(&adapter->nr_maps, 0);
	adapter->id = adapter_info.id;
	adapter->isc = adapter_info.isc;
	adapter->maskable = adapter_info.maskable;
	adapter->masked = false;
	adapter->swap = adapter_info.swap;
	dev->kvm->arch.adapters[adapter->id] = adapter;

	return 0;
}

int kvm_s390_mask_adapter(struct kvm *kvm, unsigned int id, bool masked)
{
	int ret;
	struct s390_io_adapter *adapter = get_io_adapter(kvm, id);

	if (!adapter || !adapter->maskable)
		return -EINVAL;
	ret = adapter->masked;
	adapter->masked = masked;
	return ret;
}

static int kvm_s390_adapter_map(struct kvm *kvm, unsigned int id, __u64 addr)
{
	struct s390_io_adapter *adapter = get_io_adapter(kvm, id);
	struct s390_map_info *map;
	int ret;

	if (!adapter || !addr)
		return -EINVAL;

	map = kzalloc(sizeof(*map), GFP_KERNEL);
	if (!map) {
		ret = -ENOMEM;
		goto out;
	}
	INIT_LIST_HEAD(&map->list);
	map->guest_addr = addr;
1596
	map->addr = gmap_translate(kvm->arch.gmap, addr);
1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694
	if (map->addr == -EFAULT) {
		ret = -EFAULT;
		goto out;
	}
	ret = get_user_pages_fast(map->addr, 1, 1, &map->page);
	if (ret < 0)
		goto out;
	BUG_ON(ret != 1);
	down_write(&adapter->maps_lock);
	if (atomic_inc_return(&adapter->nr_maps) < MAX_S390_ADAPTER_MAPS) {
		list_add_tail(&map->list, &adapter->maps);
		ret = 0;
	} else {
		put_page(map->page);
		ret = -EINVAL;
	}
	up_write(&adapter->maps_lock);
out:
	if (ret)
		kfree(map);
	return ret;
}

static int kvm_s390_adapter_unmap(struct kvm *kvm, unsigned int id, __u64 addr)
{
	struct s390_io_adapter *adapter = get_io_adapter(kvm, id);
	struct s390_map_info *map, *tmp;
	int found = 0;

	if (!adapter || !addr)
		return -EINVAL;

	down_write(&adapter->maps_lock);
	list_for_each_entry_safe(map, tmp, &adapter->maps, list) {
		if (map->guest_addr == addr) {
			found = 1;
			atomic_dec(&adapter->nr_maps);
			list_del(&map->list);
			put_page(map->page);
			kfree(map);
			break;
		}
	}
	up_write(&adapter->maps_lock);

	return found ? 0 : -EINVAL;
}

void kvm_s390_destroy_adapters(struct kvm *kvm)
{
	int i;
	struct s390_map_info *map, *tmp;

	for (i = 0; i < MAX_S390_IO_ADAPTERS; i++) {
		if (!kvm->arch.adapters[i])
			continue;
		list_for_each_entry_safe(map, tmp,
					 &kvm->arch.adapters[i]->maps, list) {
			list_del(&map->list);
			put_page(map->page);
			kfree(map);
		}
		kfree(kvm->arch.adapters[i]);
	}
}

static int modify_io_adapter(struct kvm_device *dev,
			     struct kvm_device_attr *attr)
{
	struct kvm_s390_io_adapter_req req;
	struct s390_io_adapter *adapter;
	int ret;

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

	adapter = get_io_adapter(dev->kvm, req.id);
	if (!adapter)
		return -EINVAL;
	switch (req.type) {
	case KVM_S390_IO_ADAPTER_MASK:
		ret = kvm_s390_mask_adapter(dev->kvm, req.id, req.mask);
		if (ret > 0)
			ret = 0;
		break;
	case KVM_S390_IO_ADAPTER_MAP:
		ret = kvm_s390_adapter_map(dev->kvm, req.id, req.addr);
		break;
	case KVM_S390_IO_ADAPTER_UNMAP:
		ret = kvm_s390_adapter_unmap(dev->kvm, req.id, req.addr);
		break;
	default:
		ret = -EINVAL;
	}

	return ret;
}

1695 1696 1697
static int flic_set_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
{
	int r = 0;
1698 1699
	unsigned int i;
	struct kvm_vcpu *vcpu;
1700 1701 1702 1703 1704 1705

	switch (attr->group) {
	case KVM_DEV_FLIC_ENQUEUE:
		r = enqueue_floating_irq(dev, attr);
		break;
	case KVM_DEV_FLIC_CLEAR_IRQS:
1706
		kvm_s390_clear_float_irqs(dev->kvm);
1707
		break;
1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721
	case KVM_DEV_FLIC_APF_ENABLE:
		dev->kvm->arch.gmap->pfault_enabled = 1;
		break;
	case KVM_DEV_FLIC_APF_DISABLE_WAIT:
		dev->kvm->arch.gmap->pfault_enabled = 0;
		/*
		 * Make sure no async faults are in transition when
		 * clearing the queues. So we don't need to worry
		 * about late coming workers.
		 */
		synchronize_srcu(&dev->kvm->srcu);
		kvm_for_each_vcpu(i, vcpu, dev->kvm)
			kvm_clear_async_pf_completion_queue(vcpu);
		break;
1722 1723 1724 1725 1726 1727
	case KVM_DEV_FLIC_ADAPTER_REGISTER:
		r = register_io_adapter(dev, attr);
		break;
	case KVM_DEV_FLIC_ADAPTER_MODIFY:
		r = modify_io_adapter(dev, attr);
		break;
1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758
	default:
		r = -EINVAL;
	}

	return r;
}

static int flic_create(struct kvm_device *dev, u32 type)
{
	if (!dev)
		return -EINVAL;
	if (dev->kvm->arch.flic)
		return -EINVAL;
	dev->kvm->arch.flic = dev;
	return 0;
}

static void flic_destroy(struct kvm_device *dev)
{
	dev->kvm->arch.flic = NULL;
	kfree(dev);
}

/* s390 floating irq controller (flic) */
struct kvm_device_ops kvm_flic_ops = {
	.name = "kvm-flic",
	.get_attr = flic_get_attr,
	.set_attr = flic_set_attr,
	.create = flic_create,
	.destroy = flic_destroy,
};
1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850

static unsigned long get_ind_bit(__u64 addr, unsigned long bit_nr, bool swap)
{
	unsigned long bit;

	bit = bit_nr + (addr % PAGE_SIZE) * 8;

	return swap ? (bit ^ (BITS_PER_LONG - 1)) : bit;
}

static struct s390_map_info *get_map_info(struct s390_io_adapter *adapter,
					  u64 addr)
{
	struct s390_map_info *map;

	if (!adapter)
		return NULL;

	list_for_each_entry(map, &adapter->maps, list) {
		if (map->guest_addr == addr)
			return map;
	}
	return NULL;
}

static int adapter_indicators_set(struct kvm *kvm,
				  struct s390_io_adapter *adapter,
				  struct kvm_s390_adapter_int *adapter_int)
{
	unsigned long bit;
	int summary_set, idx;
	struct s390_map_info *info;
	void *map;

	info = get_map_info(adapter, adapter_int->ind_addr);
	if (!info)
		return -1;
	map = page_address(info->page);
	bit = get_ind_bit(info->addr, adapter_int->ind_offset, adapter->swap);
	set_bit(bit, map);
	idx = srcu_read_lock(&kvm->srcu);
	mark_page_dirty(kvm, info->guest_addr >> PAGE_SHIFT);
	set_page_dirty_lock(info->page);
	info = get_map_info(adapter, adapter_int->summary_addr);
	if (!info) {
		srcu_read_unlock(&kvm->srcu, idx);
		return -1;
	}
	map = page_address(info->page);
	bit = get_ind_bit(info->addr, adapter_int->summary_offset,
			  adapter->swap);
	summary_set = test_and_set_bit(bit, map);
	mark_page_dirty(kvm, info->guest_addr >> PAGE_SHIFT);
	set_page_dirty_lock(info->page);
	srcu_read_unlock(&kvm->srcu, idx);
	return summary_set ? 0 : 1;
}

/*
 * < 0 - not injected due to error
 * = 0 - coalesced, summary indicator already active
 * > 0 - injected interrupt
 */
static int set_adapter_int(struct kvm_kernel_irq_routing_entry *e,
			   struct kvm *kvm, int irq_source_id, int level,
			   bool line_status)
{
	int ret;
	struct s390_io_adapter *adapter;

	/* We're only interested in the 0->1 transition. */
	if (!level)
		return 0;
	adapter = get_io_adapter(kvm, e->adapter.adapter_id);
	if (!adapter)
		return -1;
	down_read(&adapter->maps_lock);
	ret = adapter_indicators_set(kvm, adapter, &e->adapter);
	up_read(&adapter->maps_lock);
	if ((ret > 0) && !adapter->masked) {
		struct kvm_s390_interrupt s390int = {
			.type = KVM_S390_INT_IO(1, 0, 0, 0),
			.parm = 0,
			.parm64 = (adapter->isc << 27) | 0x80000000,
		};
		ret = kvm_s390_inject_vm(kvm, &s390int);
		if (ret == 0)
			ret = 1;
	}
	return ret;
}

1851
int kvm_set_routing_entry(struct kvm_kernel_irq_routing_entry *e,
1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877
			  const struct kvm_irq_routing_entry *ue)
{
	int ret;

	switch (ue->type) {
	case KVM_IRQ_ROUTING_S390_ADAPTER:
		e->set = set_adapter_int;
		e->adapter.summary_addr = ue->u.adapter.summary_addr;
		e->adapter.ind_addr = ue->u.adapter.ind_addr;
		e->adapter.summary_offset = ue->u.adapter.summary_offset;
		e->adapter.ind_offset = ue->u.adapter.ind_offset;
		e->adapter.adapter_id = ue->u.adapter.adapter_id;
		ret = 0;
		break;
	default:
		ret = -EINVAL;
	}

	return ret;
}

int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm,
		int irq_source_id, int level, bool line_status)
{
	return -EINVAL;
}