interrupt.c 51.7 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
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;

162 163 164 165 166 167
	/*
	 * STOP irqs will never be actively delivered. They are triggered via
	 * intercept requests and cleared when the stop intercept is performed.
	 */
	__clear_bit(IRQ_PEND_SIGP_STOP, &active_mask);

168 169 170
	return active_mask;
}

171 172 173 174 175 176 177 178 179 180 181 182 183 184
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)
{
185 186
	atomic_clear_mask(CPUSTAT_IO_INT | CPUSTAT_EXT_INT | CPUSTAT_STOP_INT,
			  &vcpu->arch.sie_block->cpuflags);
187
	vcpu->arch.sie_block->lctl = 0x0000;
188 189 190 191 192 193 194
	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);
	}
195 196 197 198 199 200 201
}

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

202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221
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;
}

222 223 224 225 226 227
static void set_intercept_indicators_stop(struct kvm_vcpu *vcpu)
{
	if (kvm_s390_is_stop_irq_pending(vcpu))
		__set_cpuflag(vcpu, CPUSTAT_STOP_INT);
}

228 229 230 231 232
/* 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);
233
	set_intercept_indicators_stop(vcpu);
234 235
}

236
static void __set_intercept_indicator(struct kvm_vcpu *vcpu,
237
				      struct kvm_s390_interrupt_info *inti)
238 239 240
{
	switch (inti->type) {
	case KVM_S390_INT_SERVICE:
241
	case KVM_S390_INT_PFAULT_DONE:
242 243 244 245 246 247
	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;
248 249 250 251 252 253
	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;
254 255 256 257 258 259
	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;
260 261 262 263 264
	default:
		BUG();
	}
}

265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283
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;
	}
}

284 285
static int __must_check __deliver_cpu_timer(struct kvm_vcpu *vcpu)
{
286
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
287 288 289 290 291 292 293
	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);
294
	rc |= put_guest_lc(vcpu, 0, (u16 *)__LC_EXT_CPU_ADDR);
295 296 297 298
	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));
299
	clear_bit(IRQ_PEND_EXT_CPU_TIMER, &li->pending_irqs);
300
	return rc ? -EFAULT : 0;
301 302 303 304
}

static int __must_check __deliver_ckc(struct kvm_vcpu *vcpu)
{
305
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
306 307 308 309 310 311 312
	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);
313
	rc |= put_guest_lc(vcpu, 0, (u16 *)__LC_EXT_CPU_ADDR);
314 315 316 317
	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));
318
	clear_bit(IRQ_PEND_EXT_CLOCK_COMP, &li->pending_irqs);
319
	return rc ? -EFAULT : 0;
320 321
}

322
static int __must_check __deliver_pfault_init(struct kvm_vcpu *vcpu)
323
{
324 325
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
	struct kvm_s390_ext_info ext;
326 327
	int rc;

328 329 330 331 332 333
	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);

334
	VCPU_EVENT(vcpu, 4, "interrupt: pfault init parm:%x,parm64:%llx",
335
		   0, ext.ext_params2);
336 337
	trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id,
					 KVM_S390_INT_PFAULT_INIT,
338
					 0, ext.ext_params2);
339 340 341 342 343 344 345

	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));
346
	rc |= put_guest_lc(vcpu, ext.ext_params2, (u64 *) __LC_EXT_PARAMS2);
347
	return rc ? -EFAULT : 0;
348 349
}

350
static int __must_check __deliver_machine_check(struct kvm_vcpu *vcpu)
351
{
352 353
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
	struct kvm_s390_mchk_info mchk;
354 355
	int rc;

356 357 358 359 360 361 362 363 364 365 366 367
	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);

368
	VCPU_EVENT(vcpu, 4, "interrupt: machine check mcic=%llx",
369
		   mchk.mcic);
370
	trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_MCHK,
371
					 mchk.cr14, mchk.mcic);
372 373

	rc  = kvm_s390_vcpu_store_status(vcpu, KVM_S390_STORE_STATUS_PREFIXED);
374
	rc |= put_guest_lc(vcpu, mchk.mcic,
375
			   (u64 __user *) __LC_MCCK_CODE);
376
	rc |= put_guest_lc(vcpu, mchk.failing_storage_address,
377 378
			   (u64 __user *) __LC_MCCK_FAIL_STOR_ADDR);
	rc |= write_guest_lc(vcpu, __LC_PSW_SAVE_AREA,
379
			     &mchk.fixed_logout, sizeof(mchk.fixed_logout));
380 381 382 383
	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));
384
	return rc ? -EFAULT : 0;
385 386 387 388
}

static int __must_check __deliver_restart(struct kvm_vcpu *vcpu)
{
389
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
390 391 392 393 394 395 396 397 398 399 400
	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));
401
	clear_bit(IRQ_PEND_RESTART, &li->pending_irqs);
402
	return rc ? -EFAULT : 0;
403 404
}

405
static int __must_check __deliver_set_prefix(struct kvm_vcpu *vcpu)
406
{
407 408 409 410 411 412 413 414
	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);
415

416
	VCPU_EVENT(vcpu, 4, "interrupt: set prefix to %x", prefix.address);
417 418 419
	vcpu->stat.deliver_prefix_signal++;
	trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id,
					 KVM_S390_SIGP_SET_PREFIX,
420
					 prefix.address, 0);
421

422
	kvm_s390_set_prefix(vcpu, prefix.address);
423 424 425
	return 0;
}

426
static int __must_check __deliver_emergency_signal(struct kvm_vcpu *vcpu)
427
{
428
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
429
	int rc;
430 431 432 433 434 435 436 437
	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);
438 439 440

	VCPU_EVENT(vcpu, 4, "%s", "interrupt: sigp emerg");
	vcpu->stat.deliver_emergency_signal++;
441 442
	trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_INT_EMERGENCY,
					 cpu_addr, 0);
443 444 445

	rc  = put_guest_lc(vcpu, EXT_IRQ_EMERGENCY_SIG,
			   (u16 *)__LC_EXT_INT_CODE);
446
	rc |= put_guest_lc(vcpu, cpu_addr, (u16 *)__LC_EXT_CPU_ADDR);
447 448 449 450
	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));
451
	return rc ? -EFAULT : 0;
452 453
}

454
static int __must_check __deliver_external_call(struct kvm_vcpu *vcpu)
455
{
456 457
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
	struct kvm_s390_extcall_info extcall;
458 459
	int rc;

460 461 462 463 464 465
	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);

466 467 468 469
	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,
470
					 extcall.code, 0);
471 472 473

	rc  = put_guest_lc(vcpu, EXT_IRQ_EXTERNAL_CALL,
			   (u16 *)__LC_EXT_INT_CODE);
474
	rc |= put_guest_lc(vcpu, extcall.code, (u16 *)__LC_EXT_CPU_ADDR);
475 476 477 478
	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));
479
	return rc ? -EFAULT : 0;
480 481
}

482
static int __must_check __deliver_prog(struct kvm_vcpu *vcpu)
483
{
484 485
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
	struct kvm_s390_pgm_info pgm_info;
486
	int rc = 0;
487
	u16 ilc = get_ilc(vcpu);
488

489 490 491 492 493 494
	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);

495
	VCPU_EVENT(vcpu, 4, "interrupt: pgm check code:%x, ilc:%x",
496
		   pgm_info.code, ilc);
497 498
	vcpu->stat.deliver_program_int++;
	trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_PROGRAM_INT,
499
					 pgm_info.code, 0);
500

501
	switch (pgm_info.code & ~PGM_PER) {
502 503 504 505 506 507 508 509 510 511
	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:
512
		rc = put_guest_lc(vcpu, pgm_info.trans_exc_code,
513 514 515 516 517 518 519 520
				  (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:
521
		rc = put_guest_lc(vcpu, pgm_info.exc_access_id,
522 523 524 525 526 527 528 529
				  (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:
530
		rc = put_guest_lc(vcpu, pgm_info.trans_exc_code,
531
				  (u64 *)__LC_TRANS_EXC_CODE);
532
		rc |= put_guest_lc(vcpu, pgm_info.exc_access_id,
533
				   (u8 *)__LC_EXC_ACCESS_ID);
534
		rc |= put_guest_lc(vcpu, pgm_info.op_access_id,
535 536 537
				   (u8 *)__LC_OP_ACCESS_ID);
		break;
	case PGM_MONITOR:
538
		rc = put_guest_lc(vcpu, pgm_info.mon_class_nr,
539
				  (u16 *)__LC_MON_CLASS_NR);
540
		rc |= put_guest_lc(vcpu, pgm_info.mon_code,
541 542 543
				   (u64 *)__LC_MON_CODE);
		break;
	case PGM_DATA:
544
		rc = put_guest_lc(vcpu, pgm_info.data_exc_code,
545 546 547
				  (u32 *)__LC_DATA_EXC_CODE);
		break;
	case PGM_PROTECTION:
548
		rc = put_guest_lc(vcpu, pgm_info.trans_exc_code,
549
				  (u64 *)__LC_TRANS_EXC_CODE);
550
		rc |= put_guest_lc(vcpu, pgm_info.exc_access_id,
551 552 553 554
				   (u8 *)__LC_EXC_ACCESS_ID);
		break;
	}

555 556
	if (pgm_info.code & PGM_PER) {
		rc |= put_guest_lc(vcpu, pgm_info.per_code,
557
				   (u8 *) __LC_PER_CODE);
558
		rc |= put_guest_lc(vcpu, pgm_info.per_atmid,
559
				   (u8 *)__LC_PER_ATMID);
560
		rc |= put_guest_lc(vcpu, pgm_info.per_address,
561
				   (u64 *) __LC_PER_ADDRESS);
562
		rc |= put_guest_lc(vcpu, pgm_info.per_access_id,
563 564 565
				   (u8 *) __LC_PER_ACCESS_ID);
	}

566
	rc |= put_guest_lc(vcpu, ilc, (u16 *) __LC_PGM_ILC);
567
	rc |= put_guest_lc(vcpu, pgm_info.code,
568 569 570 571 572
			   (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));
573
	return rc ? -EFAULT : 0;
574 575 576 577 578 579 580 581 582 583 584 585 586 587
}

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);
588
	rc |= put_guest_lc(vcpu, 0, (u16 *)__LC_EXT_CPU_ADDR);
589 590 591 592 593 594
	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);
595
	return rc ? -EFAULT : 0;
596 597 598 599 600 601 602 603 604 605
}

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);
606

607 608 609 610 611 612 613 614
	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);
615
	return rc ? -EFAULT : 0;
616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639
}

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);
640
	return rc ? -EFAULT : 0;
641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667
}

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));
668
	return rc ? -EFAULT : 0;
669 670
}

671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692
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));
693
	return rc ? -EFAULT : 0;
694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711
}

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_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)
712
{
713
	int rc;
714 715 716

	switch (inti->type) {
	case KVM_S390_INT_SERVICE:
717
		rc = __deliver_service(vcpu, inti);
718
		break;
719
	case KVM_S390_INT_PFAULT_DONE:
720
		rc = __deliver_pfault_done(vcpu, inti);
721
		break;
722
	case KVM_S390_INT_VIRTIO:
723
		rc = __deliver_virtio(vcpu, inti);
724
		break;
725
	case KVM_S390_MCHK:
726
		rc = __deliver_mchk_floating(vcpu, inti);
727
		break;
728
	case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
729
		rc = __deliver_io(vcpu, inti);
730
		break;
731 732 733
	default:
		BUG();
	}
734 735

	return rc;
736 737
}

738 739 740 741 742 743 744 745 746 747 748 749 750 751
/* 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;
}

752
int kvm_s390_vcpu_has_irq(struct kvm_vcpu *vcpu, int exclude_stop)
753
{
754 755
	struct kvm_s390_float_interrupt *fi = vcpu->arch.local_int.float_int;
	struct kvm_s390_interrupt_info  *inti;
756
	int rc;
757

758
	rc = !!deliverable_local_irqs(vcpu);
759 760

	if ((!rc) && atomic_read(&fi->active)) {
761
		spin_lock(&fi->lock);
762 763 764 765 766
		list_for_each_entry(inti, &fi->list, list)
			if (__interrupt_is_deliverable(vcpu, inti)) {
				rc = 1;
				break;
			}
767
		spin_unlock(&fi->lock);
768 769
	}

770 771
	if (!rc && kvm_cpu_has_pending_timer(vcpu))
		rc = 1;
772

773 774 775
	if (!rc && kvm_s390_si_ext_call_pending(vcpu))
		rc = 1;

776
	if (!rc && !exclude_stop && kvm_s390_is_stop_irq_pending(vcpu))
777 778
		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
	if (!ckc_interrupts_enabled(vcpu)) {
808
		VCPU_EVENT(vcpu, 3, "%s", "enabled wait w/o timer");
809
		__set_cpu_idle(vcpu);
810 811 812
		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);
815 816 817 818 819 820

	/* underflow */
	if (vcpu->arch.sie_block->ckc < now)
		return 0;

	__set_cpu_idle(vcpu);
821 822
	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);
823
no_timer:
824
	srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
825
	kvm_vcpu_block(vcpu);
826
	__unset_cpu_idle(vcpu);
827 828
	vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);

829
	hrtimer_cancel(&vcpu->arch.ckc_timer);
830 831 832
	return 0;
}

833 834 835 836 837 838 839 840 841
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);
842
		vcpu->stat.halt_wakeup++;
843 844 845
	}
}

846 847 848
enum hrtimer_restart kvm_s390_idle_wakeup(struct hrtimer *timer)
{
	struct kvm_vcpu *vcpu;
849
	u64 now, sltime;
850 851

	vcpu = container_of(timer, struct kvm_vcpu, arch.ckc_timer);
852 853
	now = get_tod_clock_fast() + vcpu->arch.sie_block->epoch;
	sltime = tod_to_ns(vcpu->arch.sie_block->ckc - now);
854

855 856 857 858 859 860 861 862
	/*
	 * If the monotonic clock runs faster than the tod clock we might be
	 * woken up too early and have to go back to sleep to avoid deadlocks.
	 */
	if (vcpu->arch.sie_block->ckc > now &&
	    hrtimer_forward_now(timer, ns_to_ktime(sltime)))
		return HRTIMER_RESTART;
	kvm_s390_vcpu_wakeup(vcpu);
863 864
	return HRTIMER_NORESTART;
}
865

866 867 868 869
void kvm_s390_clear_local_irqs(struct kvm_vcpu *vcpu)
{
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;

870
	spin_lock(&li->lock);
871 872 873
	li->pending_irqs = 0;
	bitmap_zero(li->sigp_emerg_pending, KVM_MAX_VCPUS);
	memset(&li->irq, 0, sizeof(li->irq));
874
	spin_unlock(&li->lock);
875 876

	/* clear pending external calls set by sigp interpretation facility */
877
	atomic_clear_mask(CPUSTAT_ECALL_PEND, li->cpuflags);
878 879
	atomic_clear_mask(SIGP_CTRL_C,
			  &vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].ctrl);
880 881
}

882
int __must_check kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu)
883
{
884 885 886
	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;
887
	deliver_irq_t func;
888
	int deliver;
889
	int rc = 0;
890 891
	unsigned long irq_type;
	unsigned long deliverable_irqs;
892 893 894

	__reset_intercept_indicators(vcpu);

895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915
	/* 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);
916

917
	if (!rc && atomic_read(&fi->active)) {
918 919
		do {
			deliver = 0;
920
			spin_lock(&fi->lock);
921 922 923
			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
924
					fi->irq_count--;
925 926 927 928 929 930 931
					deliver = 1;
					break;
				}
				__set_intercept_indicator(vcpu, inti);
			}
			if (list_empty(&fi->list))
				atomic_set(&fi->active, 0);
932
			spin_unlock(&fi->lock);
933
			if (deliver) {
934
				rc = __deliver_floating_interrupt(vcpu, inti);
935 936
				kfree(inti);
			}
937
		} while (!rc && deliver);
938
	}
939 940

	return rc;
941 942
}

943
static int __inject_prog(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
944 945 946
{
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;

947
	li->irq.pgm = irq->u.pgm;
948
	set_bit(IRQ_PEND_PROG, &li->pending_irqs);
949 950 951
	return 0;
}

952 953
int kvm_s390_inject_program_int(struct kvm_vcpu *vcpu, u16 code)
{
954
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
955
	struct kvm_s390_irq irq;
956 957

	VCPU_EVENT(vcpu, 3, "inject: program check %d (from kernel)", code);
958 959
	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_PROGRAM_INT, code,
				   0, 1);
960
	spin_lock(&li->lock);
961 962
	irq.u.pgm.code = code;
	__inject_prog(vcpu, &irq);
963
	BUG_ON(waitqueue_active(li->wq));
964
	spin_unlock(&li->lock);
965 966 967 968 969 970 971
	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;
972
	struct kvm_s390_irq irq;
973
	int rc;
974 975 976 977 978

	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);
979
	spin_lock(&li->lock);
980 981
	irq.u.pgm = *pgm_info;
	rc = __inject_prog(vcpu, &irq);
982
	BUG_ON(waitqueue_active(li->wq));
983
	spin_unlock(&li->lock);
984 985 986
	return rc;
}

987
static int __inject_pfault_init(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
988 989 990
{
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;

991 992 993 994 995 996 997 998
	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);
999 1000 1001 1002
	atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags);
	return 0;
}

1003
static int __inject_extcall(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_extcall_info *extcall = &li->irq.extcall;
1007 1008

	VCPU_EVENT(vcpu, 3, "inject: external call source-cpu:%u",
1009 1010 1011 1012 1013
		   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;
1014
	set_bit(IRQ_PEND_EXT_EXTERNAL, &li->pending_irqs);
1015 1016 1017 1018
	atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags);
	return 0;
}

1019
static int __inject_set_prefix(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
1020 1021
{
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
1022
	struct kvm_s390_prefix_info *prefix = &li->irq.prefix;
1023 1024

	VCPU_EVENT(vcpu, 3, "inject: set prefix to %x (from user)",
1025 1026 1027 1028
		   prefix->address);
	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_SIGP_SET_PREFIX,
				   prefix->address, 0, 2);

1029 1030 1031
	if (!is_vcpu_stopped(vcpu))
		return -EBUSY;

1032 1033
	*prefix = irq->u.prefix;
	set_bit(IRQ_PEND_SET_PREFIX, &li->pending_irqs);
1034 1035 1036
	return 0;
}

1037
#define KVM_S390_STOP_SUPP_FLAGS (KVM_S390_STOP_FLAG_STORE_STATUS)
1038
static int __inject_sigp_stop(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
1039 1040
{
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
1041
	struct kvm_s390_stop_info *stop = &li->irq.stop;
1042
	int rc = 0;
1043

1044 1045
	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_SIGP_STOP, 0, 0, 2);

1046 1047 1048
	if (irq->u.stop.flags & ~KVM_S390_STOP_SUPP_FLAGS)
		return -EINVAL;

1049 1050 1051 1052 1053 1054 1055 1056 1057
	if (is_vcpu_stopped(vcpu)) {
		if (irq->u.stop.flags & KVM_S390_STOP_FLAG_STORE_STATUS)
			rc = kvm_s390_store_status_unloaded(vcpu,
						KVM_S390_STORE_STATUS_NOADDR);
		return rc;
	}

	if (test_and_set_bit(IRQ_PEND_SIGP_STOP, &li->pending_irqs))
		return -EBUSY;
1058
	stop->flags = irq->u.stop.flags;
1059
	__set_cpuflag(vcpu, CPUSTAT_STOP_INT);
1060 1061 1062 1063
	return 0;
}

static int __inject_sigp_restart(struct kvm_vcpu *vcpu,
1064
				 struct kvm_s390_irq *irq)
1065 1066 1067
{
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;

1068 1069 1070 1071
	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);
1072 1073 1074 1075
	return 0;
}

static int __inject_sigp_emergency(struct kvm_vcpu *vcpu,
1076
				   struct kvm_s390_irq *irq)
1077 1078
{
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
1079
	struct kvm_s390_emerg_info *emerg = &li->irq.emerg;
1080

1081 1082 1083 1084 1085 1086 1087
	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);
1088 1089 1090 1091
	atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags);
	return 0;
}

1092
static int __inject_mchk(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
1093 1094
{
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
1095
	struct kvm_s390_mchk_info *mchk = &li->irq.mchk;
1096 1097

	VCPU_EVENT(vcpu, 5, "inject: machine check parm64:%llx",
1098 1099 1100 1101 1102
		   mchk->mcic);
	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_MCHK, 0,
				   mchk->mcic, 2);

	/*
1103 1104 1105 1106 1107 1108
	 * 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
1109
	 */
1110
	mchk->cr14 |= irq->u.mchk.cr14;
1111
	mchk->mcic |= irq->u.mchk.mcic;
1112 1113 1114 1115
	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));
1116 1117 1118 1119
	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);
1120 1121 1122
	return 0;
}

1123
static int __inject_ckc(struct kvm_vcpu *vcpu)
1124 1125 1126
{
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;

1127 1128 1129 1130 1131
	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);
1132 1133 1134 1135
	atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags);
	return 0;
}

1136
static int __inject_cpu_timer(struct kvm_vcpu *vcpu)
1137 1138 1139
{
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;

1140 1141 1142 1143 1144
	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);
1145
	atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags);
1146 1147 1148
	return 0;
}

1149

1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164
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
1165 1166
		if (cr6 &&
		    ((cr6 & int_word_to_isc_bits(iter->io.io_int_word)) == 0))
1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178
			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
1179
	if (inti) {
1180
		list_del_init(&inti->list);
J
Jens Freimann 已提交
1181 1182
		fi->irq_count--;
	}
1183 1184 1185 1186 1187 1188
	if (list_empty(&fi->list))
		atomic_set(&fi->active, 0);
	spin_unlock(&fi->lock);
	mutex_unlock(&kvm->lock);
	return inti;
}
1189

J
Jens Freimann 已提交
1190
static int __inject_vm(struct kvm *kvm, struct kvm_s390_interrupt_info *inti)
1191
{
1192 1193
	struct kvm_s390_local_interrupt *li;
	struct kvm_s390_float_interrupt *fi;
1194
	struct kvm_s390_interrupt_info *iter;
1195
	struct kvm_vcpu *dst_vcpu = NULL;
1196
	int sigcpu;
J
Jens Freimann 已提交
1197
	int rc = 0;
1198

1199 1200 1201
	mutex_lock(&kvm->lock);
	fi = &kvm->arch.float_int;
	spin_lock(&fi->lock);
J
Jens Freimann 已提交
1202 1203 1204 1205 1206
	if (fi->irq_count >= KVM_S390_MAX_FLOAT_IRQS) {
		rc = -EINVAL;
		goto unlock_fi;
	}
	fi->irq_count++;
1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229
	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;
1230
		} while (kvm_get_vcpu(kvm, sigcpu) == NULL);
1231
	}
1232 1233
	dst_vcpu = kvm_get_vcpu(kvm, sigcpu);
	li = &dst_vcpu->arch.local_int;
1234
	spin_lock(&li->lock);
1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245
	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;
	}
1246
	spin_unlock(&li->lock);
1247
	kvm_s390_vcpu_wakeup(kvm_get_vcpu(kvm, sigcpu));
J
Jens Freimann 已提交
1248
unlock_fi:
1249 1250
	spin_unlock(&fi->lock);
	mutex_unlock(&kvm->lock);
J
Jens Freimann 已提交
1251
	return rc;
1252 1253 1254 1255 1256 1257 1258
}

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

1259 1260 1261 1262
	inti = kzalloc(sizeof(*inti), GFP_KERNEL);
	if (!inti)
		return -ENOMEM;

1263 1264
	inti->type = s390int->type;
	switch (inti->type) {
1265
	case KVM_S390_INT_VIRTIO:
1266
		VM_EVENT(kvm, 5, "inject: virtio parm:%x,parm64:%llx",
1267 1268 1269 1270 1271 1272 1273 1274
			 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;
1275 1276 1277 1278
	case KVM_S390_INT_PFAULT_DONE:
		inti->type = s390int->type;
		inti->ext.ext_params2 = s390int->parm64;
		break;
1279 1280 1281 1282 1283 1284
	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;
1285
	case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
1286
		if (inti->type & IOINT_AI_MASK)
1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297
			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;
1298 1299 1300 1301
	default:
		kfree(inti);
		return -EINVAL;
	}
1302 1303
	trace_kvm_s390_inject_vm(s390int->type, s390int->parm, s390int->parm64,
				 2);
1304

J
Jens Freimann 已提交
1305
	return __inject_vm(kvm, inti);
1306 1307
}

1308 1309 1310 1311 1312 1313
void kvm_s390_reinject_io_int(struct kvm *kvm,
			      struct kvm_s390_interrupt_info *inti)
{
	__inject_vm(kvm, inti);
}

1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326
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;
1327 1328 1329
	case KVM_S390_SIGP_STOP:
		irq->u.stop.flags = s390int->parm;
		break;
1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346
	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;
}

1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363
int kvm_s390_is_stop_irq_pending(struct kvm_vcpu *vcpu)
{
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;

	return test_bit(IRQ_PEND_SIGP_STOP, &li->pending_irqs);
}

void kvm_s390_clear_stop_irq(struct kvm_vcpu *vcpu)
{
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;

	spin_lock(&li->lock);
	li->irq.stop.flags = 0;
	clear_bit(IRQ_PEND_SIGP_STOP, &li->pending_irqs);
	spin_unlock(&li->lock);
}

1364
int kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
1365
{
1366 1367
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
	int rc;
1368

1369
	spin_lock(&li->lock);
1370
	switch (irq->type) {
1371 1372
	case KVM_S390_PROGRAM_INT:
		VCPU_EVENT(vcpu, 3, "inject: program check %d (from user)",
1373 1374
			   irq->u.pgm.code);
		rc = __inject_prog(vcpu, irq);
1375
		break;
1376
	case KVM_S390_SIGP_SET_PREFIX:
1377
		rc = __inject_set_prefix(vcpu, irq);
1378
		break;
1379
	case KVM_S390_SIGP_STOP:
1380
		rc = __inject_sigp_stop(vcpu, irq);
1381
		break;
1382
	case KVM_S390_RESTART:
1383
		rc = __inject_sigp_restart(vcpu, irq);
1384
		break;
1385
	case KVM_S390_INT_CLOCK_COMP:
1386
		rc = __inject_ckc(vcpu);
1387
		break;
1388
	case KVM_S390_INT_CPU_TIMER:
1389
		rc = __inject_cpu_timer(vcpu);
1390
		break;
1391
	case KVM_S390_INT_EXTERNAL_CALL:
1392
		rc = __inject_extcall(vcpu, irq);
1393
		break;
1394
	case KVM_S390_INT_EMERGENCY:
1395
		rc = __inject_sigp_emergency(vcpu, irq);
1396
		break;
1397
	case KVM_S390_MCHK:
1398
		rc = __inject_mchk(vcpu, irq);
1399
		break;
1400
	case KVM_S390_INT_PFAULT_INIT:
1401
		rc = __inject_pfault_init(vcpu, irq);
1402
		break;
1403 1404
	case KVM_S390_INT_VIRTIO:
	case KVM_S390_INT_SERVICE:
1405
	case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
1406
	default:
1407
		rc = -EINVAL;
1408
	}
1409
	spin_unlock(&li->lock);
1410 1411 1412
	if (!rc)
		kvm_s390_vcpu_wakeup(vcpu);
	return rc;
1413
}
1414

1415
void kvm_s390_clear_float_irqs(struct kvm *kvm)
1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426
{
	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
1427
	fi->irq_count = 0;
1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440
	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) {
1441 1442
	case KVM_S390_INT_PFAULT_INIT:
	case KVM_S390_INT_PFAULT_DONE:
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 1468 1469 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 1518 1519 1520 1521
	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) {
1522 1523
	case KVM_S390_INT_PFAULT_INIT:
	case KVM_S390_INT_PFAULT_DONE:
1524 1525 1526 1527 1528 1529 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
	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
1572 1573 1574 1575 1576
		r = __inject_vm(dev->kvm, inti);
		if (r) {
			kfree(inti);
			return r;
		}
1577 1578 1579 1580 1581 1582 1583
		len -= sizeof(struct kvm_s390_irq);
		attr->addr += sizeof(struct kvm_s390_irq);
	}

	return r;
}

1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 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
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;
1650
	map->addr = gmap_translate(kvm->arch.gmap, addr);
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 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748
	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;
}

1749 1750 1751
static int flic_set_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
{
	int r = 0;
1752 1753
	unsigned int i;
	struct kvm_vcpu *vcpu;
1754 1755 1756 1757 1758 1759

	switch (attr->group) {
	case KVM_DEV_FLIC_ENQUEUE:
		r = enqueue_floating_irq(dev, attr);
		break;
	case KVM_DEV_FLIC_CLEAR_IRQS:
1760
		kvm_s390_clear_float_irqs(dev->kvm);
1761
		break;
1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775
	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;
1776 1777 1778 1779 1780 1781
	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;
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
	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,
};
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 1851 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 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904

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;
}

1905
int kvm_set_routing_entry(struct kvm_kernel_irq_routing_entry *e,
1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931
			  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;
}