interrupt.c 60.1 KB
Newer Older
1
/*
2
 * handling kvm guest interrupts
3
 *
4
 * Copyright IBM Corp. 2008, 2015
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
#include <linux/vmalloc.h>
21
#include <asm/asm-offsets.h>
22
#include <asm/dis.h>
23
#include <asm/uaccess.h>
24
#include <asm/sclp.h>
25
#include <asm/isc.h>
26 27
#include "kvm-s390.h"
#include "gaccess.h"
28
#include "trace-s390.h"
29

30 31 32
#define IOINT_SCHID_MASK 0x0000ffff
#define IOINT_SSID_MASK 0x00030000
#define IOINT_CSSID_MASK 0x03fc0000
33
#define PFAULT_INIT 0x0600
34 35
#define PFAULT_DONE 0x0680
#define VIRTIO_PARAM 0x0d00
36

37
int psw_extint_disabled(struct kvm_vcpu *vcpu)
38 39 40 41
{
	return !(vcpu->arch.sie_block->gpsw.mask & PSW_MASK_EXT);
}

42 43 44 45 46
static int psw_ioint_disabled(struct kvm_vcpu *vcpu)
{
	return !(vcpu->arch.sie_block->gpsw.mask & PSW_MASK_IO);
}

47 48 49 50 51
static int psw_mchk_disabled(struct kvm_vcpu *vcpu)
{
	return !(vcpu->arch.sie_block->gpsw.mask & PSW_MASK_MCHECK);
}

52 53
static int psw_interrupts_disabled(struct kvm_vcpu *vcpu)
{
54 55 56
	return psw_extint_disabled(vcpu) &&
	       psw_ioint_disabled(vcpu) &&
	       psw_mchk_disabled(vcpu);
57 58
}

59 60 61 62 63
static int ckc_interrupts_enabled(struct kvm_vcpu *vcpu)
{
	if (psw_extint_disabled(vcpu) ||
	    !(vcpu->arch.sie_block->gcr[0] & 0x800ul))
		return 0;
64 65 66
	if (guestdbg_enabled(vcpu) && guestdbg_sstep_enabled(vcpu))
		/* No timer interrupts when single stepping */
		return 0;
67 68 69
	return 1;
}

70 71
static int ckc_irq_pending(struct kvm_vcpu *vcpu)
{
72
	preempt_disable();
73
	if (!(vcpu->arch.sie_block->ckc <
74 75
	      get_tod_clock_fast() + vcpu->arch.sie_block->epoch)) {
		preempt_enable();
76
		return 0;
77 78
	}
	preempt_enable();
79 80 81 82 83 84 85 86 87 88 89 90 91 92 93
	return ckc_interrupts_enabled(vcpu);
}

static int cpu_timer_interrupts_enabled(struct kvm_vcpu *vcpu)
{
	return !psw_extint_disabled(vcpu) &&
	       (vcpu->arch.sie_block->gcr[0] & 0x400ul);
}

static int cpu_timer_irq_pending(struct kvm_vcpu *vcpu)
{
	return (vcpu->arch.sie_block->cputm >> 63) &&
	       cpu_timer_interrupts_enabled(vcpu);
}

94
static inline int is_ioirq(unsigned long irq_type)
C
Cornelia Huck 已提交
95
{
96 97 98
	return ((irq_type >= IRQ_PEND_IO_ISC_0) &&
		(irq_type <= IRQ_PEND_IO_ISC_7));
}
C
Cornelia Huck 已提交
99

100 101
static uint64_t isc_to_isc_bits(int isc)
{
C
Cornelia Huck 已提交
102 103 104
	return (0x80 >> isc) << 24;
}

105
static inline u8 int_word_to_isc(u32 int_word)
106
{
107 108 109
	return (int_word & 0x38000000) >> 27;
}

110
static inline unsigned long pending_irqs(struct kvm_vcpu *vcpu)
111
{
112 113
	return vcpu->kvm->arch.float_int.pending_irqs |
	       vcpu->arch.local_int.pending_irqs;
114 115
}

116 117 118 119 120 121 122 123 124 125 126 127 128
static unsigned long disable_iscs(struct kvm_vcpu *vcpu,
				   unsigned long active_mask)
{
	int i;

	for (i = 0; i <= MAX_ISC; i++)
		if (!(vcpu->arch.sie_block->gcr[6] & isc_to_isc_bits(i)))
			active_mask &= ~(1UL << (IRQ_PEND_IO_ISC_0 + i));

	return active_mask;
}

static unsigned long deliverable_irqs(struct kvm_vcpu *vcpu)
129
{
130 131
	unsigned long active_mask;

132
	active_mask = pending_irqs(vcpu);
133 134
	if (!active_mask)
		return 0;
135 136 137

	if (psw_extint_disabled(vcpu))
		active_mask &= ~IRQ_PEND_EXT_MASK;
138 139 140 141
	if (psw_ioint_disabled(vcpu))
		active_mask &= ~IRQ_PEND_IO_MASK;
	else
		active_mask = disable_iscs(vcpu, active_mask);
142 143 144 145 146 147 148 149
	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);
150 151
	if (!(vcpu->arch.sie_block->gcr[0] & 0x200ul))
		__clear_bit(IRQ_PEND_EXT_SERVICE, &active_mask);
152 153
	if (psw_mchk_disabled(vcpu))
		active_mask &= ~IRQ_PEND_MCHK_MASK;
154 155 156
	if (!(vcpu->arch.sie_block->gcr[14] &
	      vcpu->kvm->arch.float_int.mchk.cr14))
		__clear_bit(IRQ_PEND_MCHK_REP, &active_mask);
157

158 159 160 161 162 163
	/*
	 * 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);

164 165 166
	return active_mask;
}

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

static void __unset_cpu_idle(struct kvm_vcpu *vcpu)
{
175
	atomic_andnot(CPUSTAT_WAIT, &vcpu->arch.sie_block->cpuflags);
176 177 178 179 180
	clear_bit(vcpu->vcpu_id, vcpu->arch.local_int.float_int->idle_mask);
}

static void __reset_intercept_indicators(struct kvm_vcpu *vcpu)
{
181 182
	atomic_andnot(CPUSTAT_IO_INT | CPUSTAT_EXT_INT | CPUSTAT_STOP_INT,
		    &vcpu->arch.sie_block->cpuflags);
183
	vcpu->arch.sie_block->lctl = 0x0000;
184 185 186 187 188 189 190
	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);
	}
191 192 193 194
}

static void __set_cpuflag(struct kvm_vcpu *vcpu, u32 flag)
{
195
	atomic_or(flag, &vcpu->arch.sie_block->cpuflags);
196 197
}

198 199
static void set_intercept_indicators_io(struct kvm_vcpu *vcpu)
{
200
	if (!(pending_irqs(vcpu) & IRQ_PEND_IO_MASK))
201 202 203 204 205 206 207
		return;
	else if (psw_ioint_disabled(vcpu))
		__set_cpuflag(vcpu, CPUSTAT_IO_INT);
	else
		vcpu->arch.sie_block->lctl |= LCTL_CR6;
}

208 209
static void set_intercept_indicators_ext(struct kvm_vcpu *vcpu)
{
210
	if (!(pending_irqs(vcpu) & IRQ_PEND_EXT_MASK))
211 212 213 214 215 216 217 218 219
		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)
{
220
	if (!(pending_irqs(vcpu) & IRQ_PEND_MCHK_MASK))
221 222 223 224 225 226 227
		return;
	if (psw_mchk_disabled(vcpu))
		vcpu->arch.sie_block->ictl |= ICTL_LPSW;
	else
		vcpu->arch.sie_block->lctl |= LCTL_CR14;
}

228 229 230 231 232 233
static void set_intercept_indicators_stop(struct kvm_vcpu *vcpu)
{
	if (kvm_s390_is_stop_irq_pending(vcpu))
		__set_cpuflag(vcpu, CPUSTAT_STOP_INT);
}

234 235
/* Set interception request for non-deliverable interrupts */
static void set_intercept_indicators(struct kvm_vcpu *vcpu)
236
{
237
	set_intercept_indicators_io(vcpu);
238 239
	set_intercept_indicators_ext(vcpu);
	set_intercept_indicators_mchk(vcpu);
240
	set_intercept_indicators_stop(vcpu);
241 242
}

243 244 245 246 247 248 249 250 251
static u16 get_ilc(struct kvm_vcpu *vcpu)
{
	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 */
252
		return insn_length(vcpu->arch.sie_block->ipa >> 8);
253 254 255 256 257 258 259
	case ICPT_PROGI:
		return vcpu->arch.sie_block->pgmilc;
	default:
		return 0;
	}
}

260 261
static int __must_check __deliver_cpu_timer(struct kvm_vcpu *vcpu)
{
262
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
263 264 265 266 267 268 269
	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);
270
	rc |= put_guest_lc(vcpu, 0, (u16 *)__LC_EXT_CPU_ADDR);
271 272 273 274
	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));
275
	clear_bit(IRQ_PEND_EXT_CPU_TIMER, &li->pending_irqs);
276
	return rc ? -EFAULT : 0;
277 278 279 280
}

static int __must_check __deliver_ckc(struct kvm_vcpu *vcpu)
{
281
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
282 283 284 285 286 287 288
	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);
289
	rc |= put_guest_lc(vcpu, 0, (u16 *)__LC_EXT_CPU_ADDR);
290 291 292 293
	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));
294
	clear_bit(IRQ_PEND_EXT_CLOCK_COMP, &li->pending_irqs);
295
	return rc ? -EFAULT : 0;
296 297
}

298
static int __must_check __deliver_pfault_init(struct kvm_vcpu *vcpu)
299
{
300 301
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
	struct kvm_s390_ext_info ext;
302 303
	int rc;

304 305 306 307 308 309
	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);

310 311
	VCPU_EVENT(vcpu, 4, "deliver: pfault init token 0x%llx",
		   ext.ext_params2);
312 313
	trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id,
					 KVM_S390_INT_PFAULT_INIT,
314
					 0, ext.ext_params2);
315 316 317 318 319 320 321

	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));
322
	rc |= put_guest_lc(vcpu, ext.ext_params2, (u64 *) __LC_EXT_PARAMS2);
323
	return rc ? -EFAULT : 0;
324 325
}

326
static int __must_check __deliver_machine_check(struct kvm_vcpu *vcpu)
327
{
328
	struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int;
329
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
330
	struct kvm_s390_mchk_info mchk = {};
E
Eric Farman 已提交
331
	unsigned long adtl_status_addr;
332 333
	int deliver = 0;
	int rc = 0;
334

335
	spin_lock(&fi->lock);
336
	spin_lock(&li->lock);
337 338 339 340 341 342 343 344 345 346 347 348 349 350
	if (test_bit(IRQ_PEND_MCHK_EX, &li->pending_irqs) ||
	    test_bit(IRQ_PEND_MCHK_REP, &li->pending_irqs)) {
		/*
		 * 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 bits for
		 * repressible and exigent interrupts
		 */
		mchk = li->irq.mchk;
		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));
		deliver = 1;
	}
351
	/*
352 353 354 355
	 * We indicate floating repressible conditions along with
	 * other pending conditions. Channel Report Pending and Channel
	 * Subsystem damage are the only two and and are indicated by
	 * bits in mcic and masked in cr14.
356
	 */
357 358 359 360 361 362
	if (test_and_clear_bit(IRQ_PEND_MCHK_REP, &fi->pending_irqs)) {
		mchk.mcic |= fi->mchk.mcic;
		mchk.cr14 |= fi->mchk.cr14;
		memset(&fi->mchk, 0, sizeof(mchk));
		deliver = 1;
	}
363
	spin_unlock(&li->lock);
364
	spin_unlock(&fi->lock);
365

366
	if (deliver) {
367
		VCPU_EVENT(vcpu, 3, "deliver: machine check mcic 0x%llx",
368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393
			   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 |= read_guest_lc(vcpu, __LC_VX_SAVE_AREA_ADDR,
				    &adtl_status_addr,
				    sizeof(unsigned long));
		rc |= kvm_s390_vcpu_store_adtl_status(vcpu,
						      adtl_status_addr);
		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));
	}
394
	return rc ? -EFAULT : 0;
395 396 397 398
}

static int __must_check __deliver_restart(struct kvm_vcpu *vcpu)
{
399
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
400 401
	int rc;

402
	VCPU_EVENT(vcpu, 3, "%s", "deliver: cpu restart");
403 404 405 406 407 408 409 410
	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));
411
	clear_bit(IRQ_PEND_RESTART, &li->pending_irqs);
412
	return rc ? -EFAULT : 0;
413 414
}

415
static int __must_check __deliver_set_prefix(struct kvm_vcpu *vcpu)
416
{
417 418 419 420 421 422 423 424
	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);
425 426 427 428

	vcpu->stat.deliver_prefix_signal++;
	trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id,
					 KVM_S390_SIGP_SET_PREFIX,
429
					 prefix.address, 0);
430

431
	kvm_s390_set_prefix(vcpu, prefix.address);
432 433 434
	return 0;
}

435
static int __must_check __deliver_emergency_signal(struct kvm_vcpu *vcpu)
436
{
437
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
438
	int rc;
439 440 441 442 443 444 445 446
	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);
447

448
	VCPU_EVENT(vcpu, 4, "%s", "deliver: sigp emerg");
449
	vcpu->stat.deliver_emergency_signal++;
450 451
	trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_INT_EMERGENCY,
					 cpu_addr, 0);
452 453 454

	rc  = put_guest_lc(vcpu, EXT_IRQ_EMERGENCY_SIG,
			   (u16 *)__LC_EXT_INT_CODE);
455
	rc |= put_guest_lc(vcpu, cpu_addr, (u16 *)__LC_EXT_CPU_ADDR);
456 457 458 459
	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));
460
	return rc ? -EFAULT : 0;
461 462
}

463
static int __must_check __deliver_external_call(struct kvm_vcpu *vcpu)
464
{
465 466
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
	struct kvm_s390_extcall_info extcall;
467 468
	int rc;

469 470 471 472 473 474
	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);

475
	VCPU_EVENT(vcpu, 4, "%s", "deliver: sigp ext call");
476 477 478
	vcpu->stat.deliver_external_call++;
	trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id,
					 KVM_S390_INT_EXTERNAL_CALL,
479
					 extcall.code, 0);
480 481 482

	rc  = put_guest_lc(vcpu, EXT_IRQ_EXTERNAL_CALL,
			   (u16 *)__LC_EXT_INT_CODE);
483
	rc |= put_guest_lc(vcpu, extcall.code, (u16 *)__LC_EXT_CPU_ADDR);
484 485 486 487
	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));
488
	return rc ? -EFAULT : 0;
489 490
}

491
static int __must_check __deliver_prog(struct kvm_vcpu *vcpu)
492
{
493 494
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
	struct kvm_s390_pgm_info pgm_info;
495
	int rc = 0, nullifying = false;
496
	u16 ilc = get_ilc(vcpu);
497

498 499 500 501 502 503
	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);

504
	VCPU_EVENT(vcpu, 3, "deliver: program irq code 0x%x, ilc:%d",
505
		   pgm_info.code, ilc);
506 507
	vcpu->stat.deliver_program_int++;
	trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_PROGRAM_INT,
508
					 pgm_info.code, 0);
509

510
	switch (pgm_info.code & ~PGM_PER) {
511 512 513 514 515 516 517 518 519
	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:
520 521
		nullifying = true;
		/* fall through */
522
	case PGM_SPACE_SWITCH:
523
		rc = put_guest_lc(vcpu, pgm_info.trans_exc_code,
524 525 526 527 528 529 530 531
				  (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:
532
		rc = put_guest_lc(vcpu, pgm_info.exc_access_id,
533
				  (u8 *)__LC_EXC_ACCESS_ID);
534
		nullifying = true;
535 536 537 538 539 540 541
		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:
542
		rc = put_guest_lc(vcpu, pgm_info.trans_exc_code,
543
				  (u64 *)__LC_TRANS_EXC_CODE);
544
		rc |= put_guest_lc(vcpu, pgm_info.exc_access_id,
545
				   (u8 *)__LC_EXC_ACCESS_ID);
546
		rc |= put_guest_lc(vcpu, pgm_info.op_access_id,
547
				   (u8 *)__LC_OP_ACCESS_ID);
548
		nullifying = true;
549 550
		break;
	case PGM_MONITOR:
551
		rc = put_guest_lc(vcpu, pgm_info.mon_class_nr,
552
				  (u16 *)__LC_MON_CLASS_NR);
553
		rc |= put_guest_lc(vcpu, pgm_info.mon_code,
554 555
				   (u64 *)__LC_MON_CODE);
		break;
E
Eric Farman 已提交
556
	case PGM_VECTOR_PROCESSING:
557
	case PGM_DATA:
558
		rc = put_guest_lc(vcpu, pgm_info.data_exc_code,
559 560 561
				  (u32 *)__LC_DATA_EXC_CODE);
		break;
	case PGM_PROTECTION:
562
		rc = put_guest_lc(vcpu, pgm_info.trans_exc_code,
563
				  (u64 *)__LC_TRANS_EXC_CODE);
564
		rc |= put_guest_lc(vcpu, pgm_info.exc_access_id,
565 566
				   (u8 *)__LC_EXC_ACCESS_ID);
		break;
567 568 569 570 571 572 573 574 575
	case PGM_STACK_FULL:
	case PGM_STACK_EMPTY:
	case PGM_STACK_SPECIFICATION:
	case PGM_STACK_TYPE:
	case PGM_STACK_OPERATION:
	case PGM_TRACE_TABEL:
	case PGM_CRYPTO_OPERATION:
		nullifying = true;
		break;
576 577
	}

578 579
	if (pgm_info.code & PGM_PER) {
		rc |= put_guest_lc(vcpu, pgm_info.per_code,
580
				   (u8 *) __LC_PER_CODE);
581
		rc |= put_guest_lc(vcpu, pgm_info.per_atmid,
582
				   (u8 *)__LC_PER_ATMID);
583
		rc |= put_guest_lc(vcpu, pgm_info.per_address,
584
				   (u64 *) __LC_PER_ADDRESS);
585
		rc |= put_guest_lc(vcpu, pgm_info.per_access_id,
586 587 588
				   (u8 *) __LC_PER_ACCESS_ID);
	}

589 590 591
	if (nullifying && vcpu->arch.sie_block->icptcode == ICPT_INST)
		kvm_s390_rewind_psw(vcpu, ilc);

592
	rc |= put_guest_lc(vcpu, ilc, (u16 *) __LC_PGM_ILC);
593 594
	rc |= put_guest_lc(vcpu, vcpu->arch.sie_block->gbea,
				 (u64 *) __LC_LAST_BREAK);
595
	rc |= put_guest_lc(vcpu, pgm_info.code,
596 597 598 599 600
			   (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));
601
	return rc ? -EFAULT : 0;
602 603
}

604
static int __must_check __deliver_service(struct kvm_vcpu *vcpu)
605
{
606 607 608 609 610 611 612 613 614 615 616 617 618
	struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int;
	struct kvm_s390_ext_info ext;
	int rc = 0;

	spin_lock(&fi->lock);
	if (!(test_bit(IRQ_PEND_EXT_SERVICE, &fi->pending_irqs))) {
		spin_unlock(&fi->lock);
		return 0;
	}
	ext = fi->srv_signal;
	memset(&fi->srv_signal, 0, sizeof(ext));
	clear_bit(IRQ_PEND_EXT_SERVICE, &fi->pending_irqs);
	spin_unlock(&fi->lock);
619

620
	VCPU_EVENT(vcpu, 4, "deliver: sclp parameter 0x%x",
621
		   ext.ext_params);
622
	vcpu->stat.deliver_service_signal++;
623 624
	trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_INT_SERVICE,
					 ext.ext_params, 0);
625 626

	rc  = put_guest_lc(vcpu, EXT_IRQ_SERVICE_SIG, (u16 *)__LC_EXT_INT_CODE);
627
	rc |= put_guest_lc(vcpu, 0, (u16 *)__LC_EXT_CPU_ADDR);
628 629 630 631
	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));
632
	rc |= put_guest_lc(vcpu, ext.ext_params,
633
			   (u32 *)__LC_EXT_PARAMS);
634

635
	return rc ? -EFAULT : 0;
636 637
}

638
static int __must_check __deliver_pfault_done(struct kvm_vcpu *vcpu)
639
{
640 641 642
	struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int;
	struct kvm_s390_interrupt_info *inti;
	int rc = 0;
643

644 645 646 647 648 649 650 651 652 653 654
	spin_lock(&fi->lock);
	inti = list_first_entry_or_null(&fi->lists[FIRQ_LIST_PFAULT],
					struct kvm_s390_interrupt_info,
					list);
	if (inti) {
		list_del(&inti->list);
		fi->counters[FIRQ_CNTR_PFAULT] -= 1;
	}
	if (list_empty(&fi->lists[FIRQ_LIST_PFAULT]))
		clear_bit(IRQ_PEND_PFAULT_DONE, &fi->pending_irqs);
	spin_unlock(&fi->lock);
655

656
	if (inti) {
657 658 659 660 661 662
		trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id,
						 KVM_S390_INT_PFAULT_DONE, 0,
						 inti->ext.ext_params2);
		VCPU_EVENT(vcpu, 4, "deliver: pfault done token 0x%llx",
			   inti->ext.ext_params2);

663 664 665 666 667 668 669 670 671 672 673 674 675 676
		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);
		kfree(inti);
	}
677
	return rc ? -EFAULT : 0;
678 679
}

680
static int __must_check __deliver_virtio(struct kvm_vcpu *vcpu)
681
{
682 683 684
	struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int;
	struct kvm_s390_interrupt_info *inti;
	int rc = 0;
685

686 687 688 689 690 691
	spin_lock(&fi->lock);
	inti = list_first_entry_or_null(&fi->lists[FIRQ_LIST_VIRTIO],
					struct kvm_s390_interrupt_info,
					list);
	if (inti) {
		VCPU_EVENT(vcpu, 4,
692
			   "deliver: virtio parm: 0x%x,parm64: 0x%llx",
693 694 695 696 697 698 699 700 701 702 703 704
			   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);
		list_del(&inti->list);
		fi->counters[FIRQ_CNTR_VIRTIO] -= 1;
	}
	if (list_empty(&fi->lists[FIRQ_LIST_VIRTIO]))
		clear_bit(IRQ_PEND_VIRTIO, &fi->pending_irqs);
	spin_unlock(&fi->lock);
705

706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722
	if (inti) {
		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);
		kfree(inti);
	}
723
	return rc ? -EFAULT : 0;
724 725 726
}

static int __must_check __deliver_io(struct kvm_vcpu *vcpu,
727
				     unsigned long irq_type)
728
{
729 730 731 732
	struct list_head *isc_list;
	struct kvm_s390_float_interrupt *fi;
	struct kvm_s390_interrupt_info *inti = NULL;
	int rc = 0;
733

734
	fi = &vcpu->kvm->arch.float_int;
735

736 737 738 739 740 741
	spin_lock(&fi->lock);
	isc_list = &fi->lists[irq_type - IRQ_PEND_IO_ISC_0];
	inti = list_first_entry_or_null(isc_list,
					struct kvm_s390_interrupt_info,
					list);
	if (inti) {
742
		VCPU_EVENT(vcpu, 4, "deliver: I/O 0x%llx", inti->type);
743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773
		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);
		list_del(&inti->list);
		fi->counters[FIRQ_CNTR_IO] -= 1;
	}
	if (list_empty(isc_list))
		clear_bit(irq_type, &fi->pending_irqs);
	spin_unlock(&fi->lock);

	if (inti) {
		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));
		kfree(inti);
	}
774

775
	return rc ? -EFAULT : 0;
776 777 778 779 780 781
}

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

static const deliver_irq_t deliver_irq_funcs[] = {
	[IRQ_PEND_MCHK_EX]        = __deliver_machine_check,
782
	[IRQ_PEND_MCHK_REP]       = __deliver_machine_check,
783 784 785 786 787 788 789 790
	[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,
791 792 793
	[IRQ_PEND_EXT_SERVICE]    = __deliver_service,
	[IRQ_PEND_PFAULT_DONE]    = __deliver_pfault_done,
	[IRQ_PEND_VIRTIO]         = __deliver_virtio,
794 795
};

796 797
/* Check whether an external call is pending (deliverable or not) */
int kvm_s390_ext_call_pending(struct kvm_vcpu *vcpu)
798
{
799 800
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
	uint8_t sigp_ctrl = vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sigp_ctrl;
801

802
	if (!sclp.has_sigpif)
803
		return test_bit(IRQ_PEND_EXT_EXTERNAL, &li->pending_irqs);
804

805 806
	return (sigp_ctrl & SIGP_CTRL_C) &&
	       (atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_ECALL_PEND);
807 808
}

809
int kvm_s390_vcpu_has_irq(struct kvm_vcpu *vcpu, int exclude_stop)
810
{
811
	int rc;
812

813
	rc = !!deliverable_irqs(vcpu);
814

815 816
	if (!rc && kvm_cpu_has_pending_timer(vcpu))
		rc = 1;
817

818 819 820 821
	/* external call pending and deliverable */
	if (!rc && kvm_s390_ext_call_pending(vcpu) &&
	    !psw_extint_disabled(vcpu) &&
	    (vcpu->arch.sie_block->gcr[0] & 0x2000ul))
822 823
		rc = 1;

824
	if (!rc && !exclude_stop && kvm_s390_is_stop_irq_pending(vcpu))
825 826
		rc = 1;

827 828 829
	return rc;
}

830 831
int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
{
832
	return ckc_irq_pending(vcpu) || cpu_timer_irq_pending(vcpu);
833 834
}

835 836 837 838 839 840
int kvm_s390_handle_wait(struct kvm_vcpu *vcpu)
{
	u64 now, sltime;

	vcpu->stat.exit_wait_state++;

841 842 843
	/* fast path */
	if (kvm_cpu_has_pending_timer(vcpu) || kvm_arch_vcpu_runnable(vcpu))
		return 0;
844

845 846
	if (psw_interrupts_disabled(vcpu)) {
		VCPU_EVENT(vcpu, 3, "%s", "disabled wait");
847
		return -EOPNOTSUPP; /* disabled wait */
848 849
	}

850
	if (!ckc_interrupts_enabled(vcpu)) {
851
		VCPU_EVENT(vcpu, 3, "%s", "enabled wait w/o timer");
852
		__set_cpu_idle(vcpu);
853 854 855
		goto no_timer;
	}

856
	preempt_disable();
857
	now = get_tod_clock_fast() + vcpu->arch.sie_block->epoch;
858
	preempt_enable();
859
	sltime = tod_to_ns(vcpu->arch.sie_block->ckc - now);
860 861 862 863 864 865

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

	__set_cpu_idle(vcpu);
866
	hrtimer_start(&vcpu->arch.ckc_timer, ktime_set (0, sltime) , HRTIMER_MODE_REL);
867
	VCPU_EVENT(vcpu, 4, "enabled wait via clock comparator: %llu ns", sltime);
868
no_timer:
869
	srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
870
	kvm_vcpu_block(vcpu);
871
	__unset_cpu_idle(vcpu);
872 873
	vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);

874
	hrtimer_cancel(&vcpu->arch.ckc_timer);
875 876 877
	return 0;
}

878 879 880 881 882 883 884 885 886
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);
887
		vcpu->stat.halt_wakeup++;
888 889 890
	}
}

891 892 893
enum hrtimer_restart kvm_s390_idle_wakeup(struct hrtimer *timer)
{
	struct kvm_vcpu *vcpu;
894
	u64 now, sltime;
895 896

	vcpu = container_of(timer, struct kvm_vcpu, arch.ckc_timer);
897
	preempt_disable();
898
	now = get_tod_clock_fast() + vcpu->arch.sie_block->epoch;
899
	preempt_enable();
900
	sltime = tod_to_ns(vcpu->arch.sie_block->ckc - now);
901

902 903 904 905 906 907 908 909
	/*
	 * 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);
910 911
	return HRTIMER_NORESTART;
}
912

913 914 915 916
void kvm_s390_clear_local_irqs(struct kvm_vcpu *vcpu)
{
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;

917
	spin_lock(&li->lock);
918 919 920
	li->pending_irqs = 0;
	bitmap_zero(li->sigp_emerg_pending, KVM_MAX_VCPUS);
	memset(&li->irq, 0, sizeof(li->irq));
921
	spin_unlock(&li->lock);
922 923

	/* clear pending external calls set by sigp interpretation facility */
924
	atomic_andnot(CPUSTAT_ECALL_PEND, li->cpuflags);
925
	vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sigp_ctrl = 0;
926 927
}

928
int __must_check kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu)
929
{
930
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
931
	deliver_irq_t func;
932
	int rc = 0;
933
	unsigned long irq_type;
934
	unsigned long irqs;
935 936 937

	__reset_intercept_indicators(vcpu);

938 939
	/* pending ckc conditions might have been invalidated */
	clear_bit(IRQ_PEND_EXT_CLOCK_COMP, &li->pending_irqs);
940
	if (ckc_irq_pending(vcpu))
941 942
		set_bit(IRQ_PEND_EXT_CLOCK_COMP, &li->pending_irqs);

943 944 945 946 947
	/* pending cpu timer conditions might have been invalidated */
	clear_bit(IRQ_PEND_EXT_CPU_TIMER, &li->pending_irqs);
	if (cpu_timer_irq_pending(vcpu))
		set_bit(IRQ_PEND_EXT_CPU_TIMER, &li->pending_irqs);

948
	while ((irqs = deliverable_irqs(vcpu)) && !rc) {
949
		/* bits are in the order of interrupt priority */
950 951 952 953 954 955 956 957 958 959 960
		irq_type = find_first_bit(&irqs, IRQ_PEND_COUNT);
		if (is_ioirq(irq_type)) {
			rc = __deliver_io(vcpu, irq_type);
		} else {
			func = deliver_irq_funcs[irq_type];
			if (!func) {
				WARN_ON_ONCE(func == NULL);
				clear_bit(irq_type, &li->pending_irqs);
				continue;
			}
			rc = func(vcpu);
961
		}
962
	}
963

964
	set_intercept_indicators(vcpu);
965 966

	return rc;
967 968
}

969
static int __inject_prog(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
970 971 972
{
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;

973 974 975 976
	VCPU_EVENT(vcpu, 3, "inject: program irq code 0x%x", irq->u.pgm.code);
	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_PROGRAM_INT,
				   irq->u.pgm.code, 0);

977
	li->irq.pgm = irq->u.pgm;
978
	set_bit(IRQ_PEND_PROG, &li->pending_irqs);
979 980 981
	return 0;
}

982 983
int kvm_s390_inject_program_int(struct kvm_vcpu *vcpu, u16 code)
{
984
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
985
	struct kvm_s390_irq irq;
986

987
	spin_lock(&li->lock);
988 989
	irq.u.pgm.code = code;
	__inject_prog(vcpu, &irq);
990
	BUG_ON(waitqueue_active(li->wq));
991
	spin_unlock(&li->lock);
992 993 994 995 996 997 998
	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;
999
	struct kvm_s390_irq irq;
1000
	int rc;
1001

1002
	spin_lock(&li->lock);
1003 1004
	irq.u.pgm = *pgm_info;
	rc = __inject_prog(vcpu, &irq);
1005
	BUG_ON(waitqueue_active(li->wq));
1006
	spin_unlock(&li->lock);
1007 1008 1009
	return rc;
}

1010
static int __inject_pfault_init(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
1011 1012 1013
{
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;

1014 1015
	VCPU_EVENT(vcpu, 4, "inject: pfault init parameter block at 0x%llx",
		   irq->u.ext.ext_params2);
1016 1017
	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_INT_PFAULT_INIT,
				   irq->u.ext.ext_params,
1018
				   irq->u.ext.ext_params2);
1019 1020 1021

	li->irq.ext = irq->u.ext;
	set_bit(IRQ_PEND_PFAULT_INIT, &li->pending_irqs);
1022
	atomic_or(CPUSTAT_EXT_INT, li->cpuflags);
1023 1024 1025
	return 0;
}

1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036
static int __inject_extcall_sigpif(struct kvm_vcpu *vcpu, uint16_t src_id)
{
	unsigned char new_val, old_val;
	uint8_t *sigp_ctrl = &vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sigp_ctrl;

	new_val = SIGP_CTRL_C | (src_id & SIGP_CTRL_SCN_MASK);
	old_val = *sigp_ctrl & ~SIGP_CTRL_C;
	if (cmpxchg(sigp_ctrl, old_val, new_val) != old_val) {
		/* another external call is pending */
		return -EBUSY;
	}
1037
	atomic_or(CPUSTAT_ECALL_PEND, &vcpu->arch.sie_block->cpuflags);
1038 1039 1040
	return 0;
}

1041
static int __inject_extcall(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
1042 1043
{
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
1044
	struct kvm_s390_extcall_info *extcall = &li->irq.extcall;
1045
	uint16_t src_id = irq->u.extcall.code;
1046

1047
	VCPU_EVENT(vcpu, 4, "inject: external call source-cpu:%u",
1048
		   src_id);
1049
	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_INT_EXTERNAL_CALL,
1050
				   src_id, 0);
1051 1052 1053 1054 1055 1056

	/* sending vcpu invalid */
	if (src_id >= KVM_MAX_VCPUS ||
	    kvm_get_vcpu(vcpu->kvm, src_id) == NULL)
		return -EINVAL;

1057
	if (sclp.has_sigpif)
1058
		return __inject_extcall_sigpif(vcpu, src_id);
1059

1060
	if (test_and_set_bit(IRQ_PEND_EXT_EXTERNAL, &li->pending_irqs))
1061
		return -EBUSY;
1062
	*extcall = irq->u.extcall;
1063
	atomic_or(CPUSTAT_EXT_INT, li->cpuflags);
1064 1065 1066
	return 0;
}

1067
static int __inject_set_prefix(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
1068 1069
{
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
1070
	struct kvm_s390_prefix_info *prefix = &li->irq.prefix;
1071

1072
	VCPU_EVENT(vcpu, 3, "inject: set prefix to %x",
1073
		   irq->u.prefix.address);
1074
	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_SIGP_SET_PREFIX,
1075
				   irq->u.prefix.address, 0);
1076

1077 1078 1079
	if (!is_vcpu_stopped(vcpu))
		return -EBUSY;

1080 1081
	*prefix = irq->u.prefix;
	set_bit(IRQ_PEND_SET_PREFIX, &li->pending_irqs);
1082 1083 1084
	return 0;
}

1085
#define KVM_S390_STOP_SUPP_FLAGS (KVM_S390_STOP_FLAG_STORE_STATUS)
1086
static int __inject_sigp_stop(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
1087 1088
{
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
1089
	struct kvm_s390_stop_info *stop = &li->irq.stop;
1090
	int rc = 0;
1091

1092
	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_SIGP_STOP, 0, 0);
1093

1094 1095 1096
	if (irq->u.stop.flags & ~KVM_S390_STOP_SUPP_FLAGS)
		return -EINVAL;

1097 1098 1099 1100 1101 1102 1103 1104 1105
	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;
1106
	stop->flags = irq->u.stop.flags;
1107
	__set_cpuflag(vcpu, CPUSTAT_STOP_INT);
1108 1109 1110 1111
	return 0;
}

static int __inject_sigp_restart(struct kvm_vcpu *vcpu,
1112
				 struct kvm_s390_irq *irq)
1113 1114 1115
{
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;

1116
	VCPU_EVENT(vcpu, 3, "%s", "inject: restart int");
1117
	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_RESTART, 0, 0);
1118 1119

	set_bit(IRQ_PEND_RESTART, &li->pending_irqs);
1120 1121 1122 1123
	return 0;
}

static int __inject_sigp_emergency(struct kvm_vcpu *vcpu,
1124
				   struct kvm_s390_irq *irq)
1125 1126 1127
{
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;

1128
	VCPU_EVENT(vcpu, 4, "inject: emergency from cpu %u",
1129 1130
		   irq->u.emerg.code);
	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_INT_EMERGENCY,
1131
				   irq->u.emerg.code, 0);
1132

1133
	set_bit(irq->u.emerg.code, li->sigp_emerg_pending);
1134
	set_bit(IRQ_PEND_EXT_EMERGENCY, &li->pending_irqs);
1135
	atomic_or(CPUSTAT_EXT_INT, li->cpuflags);
1136 1137 1138
	return 0;
}

1139
static int __inject_mchk(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
1140 1141
{
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
1142
	struct kvm_s390_mchk_info *mchk = &li->irq.mchk;
1143

1144
	VCPU_EVENT(vcpu, 3, "inject: machine check mcic 0x%llx",
1145
		   irq->u.mchk.mcic);
1146
	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_MCHK, 0,
1147
				   irq->u.mchk.mcic);
1148 1149

	/*
1150 1151 1152 1153 1154 1155
	 * 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
1156
	 */
1157
	mchk->cr14 |= irq->u.mchk.cr14;
1158
	mchk->mcic |= irq->u.mchk.mcic;
1159 1160 1161 1162
	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));
1163 1164 1165 1166
	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);
1167 1168 1169
	return 0;
}

1170
static int __inject_ckc(struct kvm_vcpu *vcpu)
1171 1172 1173
{
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;

1174
	VCPU_EVENT(vcpu, 3, "%s", "inject: clock comparator external");
1175
	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_INT_CLOCK_COMP,
1176
				   0, 0);
1177 1178

	set_bit(IRQ_PEND_EXT_CLOCK_COMP, &li->pending_irqs);
1179
	atomic_or(CPUSTAT_EXT_INT, li->cpuflags);
1180 1181 1182
	return 0;
}

1183
static int __inject_cpu_timer(struct kvm_vcpu *vcpu)
1184 1185 1186
{
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;

1187
	VCPU_EVENT(vcpu, 3, "%s", "inject: cpu timer external");
1188
	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_INT_CPU_TIMER,
1189
				   0, 0);
1190 1191

	set_bit(IRQ_PEND_EXT_CPU_TIMER, &li->pending_irqs);
1192
	atomic_or(CPUSTAT_EXT_INT, li->cpuflags);
1193 1194 1195
	return 0;
}

1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220
static struct kvm_s390_interrupt_info *get_io_int(struct kvm *kvm,
						  int isc, u32 schid)
{
	struct kvm_s390_float_interrupt *fi = &kvm->arch.float_int;
	struct list_head *isc_list = &fi->lists[FIRQ_LIST_IO_ISC_0 + isc];
	struct kvm_s390_interrupt_info *iter;
	u16 id = (schid & 0xffff0000U) >> 16;
	u16 nr = schid & 0x0000ffffU;

	spin_lock(&fi->lock);
	list_for_each_entry(iter, isc_list, list) {
		if (schid && (id != iter->io.subchannel_id ||
			      nr != iter->io.subchannel_nr))
			continue;
		/* found an appropriate entry */
		list_del_init(&iter->list);
		fi->counters[FIRQ_CNTR_IO] -= 1;
		if (list_empty(isc_list))
			clear_bit(IRQ_PEND_IO_ISC_0 + isc, &fi->pending_irqs);
		spin_unlock(&fi->lock);
		return iter;
	}
	spin_unlock(&fi->lock);
	return NULL;
}
1221

1222 1223 1224 1225
/*
 * Dequeue and return an I/O interrupt matching any of the interruption
 * subclasses as designated by the isc mask in cr6 and the schid (if != 0).
 */
1226
struct kvm_s390_interrupt_info *kvm_s390_get_io_int(struct kvm *kvm,
1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 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 1311 1312 1313 1314 1315 1316 1317
						    u64 isc_mask, u32 schid)
{
	struct kvm_s390_interrupt_info *inti = NULL;
	int isc;

	for (isc = 0; isc <= MAX_ISC && !inti; isc++) {
		if (isc_mask & isc_to_isc_bits(isc))
			inti = get_io_int(kvm, isc, schid);
	}
	return inti;
}

#define SCCB_MASK 0xFFFFFFF8
#define SCCB_EVENT_PENDING 0x3

static int __inject_service(struct kvm *kvm,
			     struct kvm_s390_interrupt_info *inti)
{
	struct kvm_s390_float_interrupt *fi = &kvm->arch.float_int;

	spin_lock(&fi->lock);
	fi->srv_signal.ext_params |= inti->ext.ext_params & SCCB_EVENT_PENDING;
	/*
	 * Early versions of the QEMU s390 bios will inject several
	 * service interrupts after another without handling a
	 * condition code indicating busy.
	 * We will silently ignore those superfluous sccb values.
	 * A future version of QEMU will take care of serialization
	 * of servc requests
	 */
	if (fi->srv_signal.ext_params & SCCB_MASK)
		goto out;
	fi->srv_signal.ext_params |= inti->ext.ext_params & SCCB_MASK;
	set_bit(IRQ_PEND_EXT_SERVICE, &fi->pending_irqs);
out:
	spin_unlock(&fi->lock);
	kfree(inti);
	return 0;
}

static int __inject_virtio(struct kvm *kvm,
			    struct kvm_s390_interrupt_info *inti)
{
	struct kvm_s390_float_interrupt *fi = &kvm->arch.float_int;

	spin_lock(&fi->lock);
	if (fi->counters[FIRQ_CNTR_VIRTIO] >= KVM_S390_MAX_VIRTIO_IRQS) {
		spin_unlock(&fi->lock);
		return -EBUSY;
	}
	fi->counters[FIRQ_CNTR_VIRTIO] += 1;
	list_add_tail(&inti->list, &fi->lists[FIRQ_LIST_VIRTIO]);
	set_bit(IRQ_PEND_VIRTIO, &fi->pending_irqs);
	spin_unlock(&fi->lock);
	return 0;
}

static int __inject_pfault_done(struct kvm *kvm,
				 struct kvm_s390_interrupt_info *inti)
{
	struct kvm_s390_float_interrupt *fi = &kvm->arch.float_int;

	spin_lock(&fi->lock);
	if (fi->counters[FIRQ_CNTR_PFAULT] >=
		(ASYNC_PF_PER_VCPU * KVM_MAX_VCPUS)) {
		spin_unlock(&fi->lock);
		return -EBUSY;
	}
	fi->counters[FIRQ_CNTR_PFAULT] += 1;
	list_add_tail(&inti->list, &fi->lists[FIRQ_LIST_PFAULT]);
	set_bit(IRQ_PEND_PFAULT_DONE, &fi->pending_irqs);
	spin_unlock(&fi->lock);
	return 0;
}

#define CR_PENDING_SUBCLASS 28
static int __inject_float_mchk(struct kvm *kvm,
				struct kvm_s390_interrupt_info *inti)
{
	struct kvm_s390_float_interrupt *fi = &kvm->arch.float_int;

	spin_lock(&fi->lock);
	fi->mchk.cr14 |= inti->mchk.cr14 & (1UL << CR_PENDING_SUBCLASS);
	fi->mchk.mcic |= inti->mchk.mcic;
	set_bit(IRQ_PEND_MCHK_REP, &fi->pending_irqs);
	spin_unlock(&fi->lock);
	kfree(inti);
	return 0;
}

static int __inject_io(struct kvm *kvm, struct kvm_s390_interrupt_info *inti)
1318 1319
{
	struct kvm_s390_float_interrupt *fi;
1320 1321
	struct list_head *list;
	int isc;
1322 1323 1324

	fi = &kvm->arch.float_int;
	spin_lock(&fi->lock);
1325 1326 1327
	if (fi->counters[FIRQ_CNTR_IO] >= KVM_S390_MAX_FLOAT_IRQS) {
		spin_unlock(&fi->lock);
		return -EBUSY;
J
Jens Freimann 已提交
1328
	}
1329 1330 1331 1332 1333 1334
	fi->counters[FIRQ_CNTR_IO] += 1;

	isc = int_word_to_isc(inti->io.io_int_word);
	list = &fi->lists[FIRQ_LIST_IO_ISC_0 + isc];
	list_add_tail(&inti->list, list);
	set_bit(IRQ_PEND_IO_ISC_0 + isc, &fi->pending_irqs);
1335
	spin_unlock(&fi->lock);
1336
	return 0;
1337
}
1338

1339 1340 1341 1342
/*
 * Find a destination VCPU for a floating irq and kick it.
 */
static void __floating_irq_kick(struct kvm *kvm, u64 type)
1343
{
1344
	struct kvm_s390_float_interrupt *fi = &kvm->arch.float_int;
1345
	struct kvm_s390_local_interrupt *li;
1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370
	struct kvm_vcpu *dst_vcpu;
	int sigcpu, online_vcpus, nr_tries = 0;

	online_vcpus = atomic_read(&kvm->online_vcpus);
	if (!online_vcpus)
		return;

	/* find idle VCPUs first, then round robin */
	sigcpu = find_first_bit(fi->idle_mask, online_vcpus);
	if (sigcpu == online_vcpus) {
		do {
			sigcpu = fi->next_rr_cpu;
			fi->next_rr_cpu = (fi->next_rr_cpu + 1) % online_vcpus;
			/* avoid endless loops if all vcpus are stopped */
			if (nr_tries++ >= online_vcpus)
				return;
		} while (is_vcpu_stopped(kvm_get_vcpu(kvm, sigcpu)));
	}
	dst_vcpu = kvm_get_vcpu(kvm, sigcpu);

	/* make the VCPU drop out of the SIE, or wake it up if sleeping */
	li = &dst_vcpu->arch.local_int;
	spin_lock(&li->lock);
	switch (type) {
	case KVM_S390_MCHK:
1371
		atomic_or(CPUSTAT_STOP_INT, li->cpuflags);
1372 1373
		break;
	case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
1374
		atomic_or(CPUSTAT_IO_INT, li->cpuflags);
1375 1376
		break;
	default:
1377
		atomic_or(CPUSTAT_EXT_INT, li->cpuflags);
1378 1379 1380 1381 1382 1383 1384 1385
		break;
	}
	spin_unlock(&li->lock);
	kvm_s390_vcpu_wakeup(dst_vcpu);
}

static int __inject_vm(struct kvm *kvm, struct kvm_s390_interrupt_info *inti)
{
1386 1387
	u64 type = READ_ONCE(inti->type);
	int rc;
1388

1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405
	switch (type) {
	case KVM_S390_MCHK:
		rc = __inject_float_mchk(kvm, inti);
		break;
	case KVM_S390_INT_VIRTIO:
		rc = __inject_virtio(kvm, inti);
		break;
	case KVM_S390_INT_SERVICE:
		rc = __inject_service(kvm, inti);
		break;
	case KVM_S390_INT_PFAULT_DONE:
		rc = __inject_pfault_done(kvm, inti);
		break;
	case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
		rc = __inject_io(kvm, inti);
		break;
	default:
J
Jens Freimann 已提交
1406
		rc = -EINVAL;
1407
	}
1408 1409 1410
	if (rc)
		return rc;

1411
	__floating_irq_kick(kvm, type);
1412
	return 0;
1413 1414 1415 1416 1417 1418
}

int kvm_s390_inject_vm(struct kvm *kvm,
		       struct kvm_s390_interrupt *s390int)
{
	struct kvm_s390_interrupt_info *inti;
1419
	int rc;
1420

1421 1422 1423 1424
	inti = kzalloc(sizeof(*inti), GFP_KERNEL);
	if (!inti)
		return -ENOMEM;

1425 1426
	inti->type = s390int->type;
	switch (inti->type) {
1427
	case KVM_S390_INT_VIRTIO:
1428
		VM_EVENT(kvm, 5, "inject: virtio parm:%x,parm64:%llx",
1429 1430 1431 1432 1433
			 s390int->parm, s390int->parm64);
		inti->ext.ext_params = s390int->parm;
		inti->ext.ext_params2 = s390int->parm64;
		break;
	case KVM_S390_INT_SERVICE:
1434
		VM_EVENT(kvm, 4, "inject: sclp parm:%x", s390int->parm);
1435 1436
		inti->ext.ext_params = s390int->parm;
		break;
1437 1438 1439
	case KVM_S390_INT_PFAULT_DONE:
		inti->ext.ext_params2 = s390int->parm64;
		break;
1440
	case KVM_S390_MCHK:
1441
		VM_EVENT(kvm, 3, "inject: machine check mcic 0x%llx",
1442 1443 1444 1445
			 s390int->parm64);
		inti->mchk.cr14 = s390int->parm; /* upper bits are not used */
		inti->mchk.mcic = s390int->parm64;
		break;
1446
	case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
1447
		if (inti->type & KVM_S390_INT_IO_AI_MASK)
1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458
			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;
1459 1460 1461 1462
	default:
		kfree(inti);
		return -EINVAL;
	}
1463 1464
	trace_kvm_s390_inject_vm(s390int->type, s390int->parm, s390int->parm64,
				 2);
1465

1466 1467 1468 1469
	rc = __inject_vm(kvm, inti);
	if (rc)
		kfree(inti);
	return rc;
1470 1471
}

1472
int kvm_s390_reinject_io_int(struct kvm *kvm,
1473 1474
			      struct kvm_s390_interrupt_info *inti)
{
1475
	return __inject_vm(kvm, inti);
1476 1477
}

1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490
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;
1491 1492 1493
	case KVM_S390_SIGP_STOP:
		irq->u.stop.flags = s390int->parm;
		break;
1494
	case KVM_S390_INT_EXTERNAL_CALL:
1495
		if (s390int->parm & 0xffff0000)
1496 1497 1498 1499
			return -EINVAL;
		irq->u.extcall.code = s390int->parm;
		break;
	case KVM_S390_INT_EMERGENCY:
1500
		if (s390int->parm & 0xffff0000)
1501 1502 1503 1504 1505 1506 1507 1508 1509 1510
			return -EINVAL;
		irq->u.emerg.code = s390int->parm;
		break;
	case KVM_S390_MCHK:
		irq->u.mchk.mcic = s390int->parm64;
		break;
	}
	return 0;
}

1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527
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);
}

1528
static int do_inject_vcpu(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
1529
{
1530
	int rc;
1531

1532
	switch (irq->type) {
1533
	case KVM_S390_PROGRAM_INT:
1534
		rc = __inject_prog(vcpu, irq);
1535
		break;
1536
	case KVM_S390_SIGP_SET_PREFIX:
1537
		rc = __inject_set_prefix(vcpu, irq);
1538
		break;
1539
	case KVM_S390_SIGP_STOP:
1540
		rc = __inject_sigp_stop(vcpu, irq);
1541
		break;
1542
	case KVM_S390_RESTART:
1543
		rc = __inject_sigp_restart(vcpu, irq);
1544
		break;
1545
	case KVM_S390_INT_CLOCK_COMP:
1546
		rc = __inject_ckc(vcpu);
1547
		break;
1548
	case KVM_S390_INT_CPU_TIMER:
1549
		rc = __inject_cpu_timer(vcpu);
1550
		break;
1551
	case KVM_S390_INT_EXTERNAL_CALL:
1552
		rc = __inject_extcall(vcpu, irq);
1553
		break;
1554
	case KVM_S390_INT_EMERGENCY:
1555
		rc = __inject_sigp_emergency(vcpu, irq);
1556
		break;
1557
	case KVM_S390_MCHK:
1558
		rc = __inject_mchk(vcpu, irq);
1559
		break;
1560
	case KVM_S390_INT_PFAULT_INIT:
1561
		rc = __inject_pfault_init(vcpu, irq);
1562
		break;
1563 1564
	case KVM_S390_INT_VIRTIO:
	case KVM_S390_INT_SERVICE:
1565
	case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
1566
	default:
1567
		rc = -EINVAL;
1568
	}
1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579

	return rc;
}

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

	spin_lock(&li->lock);
	rc = do_inject_vcpu(vcpu, irq);
1580
	spin_unlock(&li->lock);
1581 1582 1583
	if (!rc)
		kvm_s390_vcpu_wakeup(vcpu);
	return rc;
1584
}
1585

1586
static inline void clear_irq_list(struct list_head *_list)
1587
{
1588
	struct kvm_s390_interrupt_info *inti, *n;
1589

1590
	list_for_each_entry_safe(inti, n, _list, list) {
1591 1592 1593 1594 1595
		list_del(&inti->list);
		kfree(inti);
	}
}

1596 1597
static void inti_to_irq(struct kvm_s390_interrupt_info *inti,
		       struct kvm_s390_irq *irq)
1598
{
1599
	irq->type = inti->type;
1600
	switch (inti->type) {
1601 1602
	case KVM_S390_INT_PFAULT_INIT:
	case KVM_S390_INT_PFAULT_DONE:
1603
	case KVM_S390_INT_VIRTIO:
1604
		irq->u.ext = inti->ext;
1605 1606
		break;
	case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
1607
		irq->u.io = inti->io;
1608 1609 1610 1611
		break;
	}
}

1612 1613 1614 1615 1616 1617
void kvm_s390_clear_float_irqs(struct kvm *kvm)
{
	struct kvm_s390_float_interrupt *fi = &kvm->arch.float_int;
	int i;

	spin_lock(&fi->lock);
1618 1619 1620
	fi->pending_irqs = 0;
	memset(&fi->srv_signal, 0, sizeof(fi->srv_signal));
	memset(&fi->mchk, 0, sizeof(fi->mchk));
1621 1622 1623 1624 1625 1626 1627
	for (i = 0; i < FIRQ_LIST_COUNT; i++)
		clear_irq_list(&fi->lists[i]);
	for (i = 0; i < FIRQ_MAX_COUNT; i++)
		fi->counters[i] = 0;
	spin_unlock(&fi->lock);
};

1628
static int get_all_floating_irqs(struct kvm *kvm, u8 __user *usrbuf, u64 len)
1629 1630 1631
{
	struct kvm_s390_interrupt_info *inti;
	struct kvm_s390_float_interrupt *fi;
1632
	struct kvm_s390_irq *buf;
1633
	struct kvm_s390_irq *irq;
1634
	int max_irqs;
1635 1636
	int ret = 0;
	int n = 0;
1637
	int i;
1638

1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652
	if (len > KVM_S390_FLIC_MAX_BUFFER || len == 0)
		return -EINVAL;

	/*
	 * We are already using -ENOMEM to signal
	 * userspace it may retry with a bigger buffer,
	 * so we need to use something else for this case
	 */
	buf = vzalloc(len);
	if (!buf)
		return -ENOBUFS;

	max_irqs = len / sizeof(struct kvm_s390_irq);

1653 1654
	fi = &kvm->arch.float_int;
	spin_lock(&fi->lock);
1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666
	for (i = 0; i < FIRQ_LIST_COUNT; i++) {
		list_for_each_entry(inti, &fi->lists[i], list) {
			if (n == max_irqs) {
				/* signal userspace to try again */
				ret = -ENOMEM;
				goto out;
			}
			inti_to_irq(inti, &buf[n]);
			n++;
		}
	}
	if (test_bit(IRQ_PEND_EXT_SERVICE, &fi->pending_irqs)) {
1667
		if (n == max_irqs) {
1668 1669
			/* signal userspace to try again */
			ret = -ENOMEM;
1670
			goto out;
1671
		}
1672 1673 1674
		irq = (struct kvm_s390_irq *) &buf[n];
		irq->type = KVM_S390_INT_SERVICE;
		irq->u.ext = fi->srv_signal;
1675 1676
		n++;
	}
1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689
	if (test_bit(IRQ_PEND_MCHK_REP, &fi->pending_irqs)) {
		if (n == max_irqs) {
				/* signal userspace to try again */
				ret = -ENOMEM;
				goto out;
		}
		irq = (struct kvm_s390_irq *) &buf[n];
		irq->type = KVM_S390_MCHK;
		irq->u.mchk = fi->mchk;
		n++;
}

out:
1690
	spin_unlock(&fi->lock);
1691 1692 1693 1694 1695
	if (!ret && n > 0) {
		if (copy_to_user(usrbuf, buf, sizeof(struct kvm_s390_irq) * n))
			ret = -EFAULT;
	}
	vfree(buf);
1696 1697 1698 1699 1700 1701 1702 1703 1704 1705

	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:
1706
		r = get_all_floating_irqs(dev->kvm, (u8 __user *) attr->addr,
1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727
					  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) {
1728 1729
	case KVM_S390_INT_PFAULT_INIT:
	case KVM_S390_INT_PFAULT_DONE:
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 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777
	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
1778 1779 1780 1781 1782
		r = __inject_vm(dev->kvm, inti);
		if (r) {
			kfree(inti);
			return r;
		}
1783 1784 1785 1786 1787 1788 1789
		len -= sizeof(struct kvm_s390_irq);
		attr->addr += sizeof(struct kvm_s390_irq);
	}

	return r;
}

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 1851 1852 1853 1854 1855
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;
1856
	map->addr = gmap_translate(kvm->arch.gmap, addr);
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 1905 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 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954
	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;
}

1955 1956 1957
static int flic_set_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
{
	int r = 0;
1958 1959
	unsigned int i;
	struct kvm_vcpu *vcpu;
1960 1961 1962 1963 1964 1965

	switch (attr->group) {
	case KVM_DEV_FLIC_ENQUEUE:
		r = enqueue_floating_irq(dev, attr);
		break;
	case KVM_DEV_FLIC_CLEAR_IRQS:
1966
		kvm_s390_clear_float_irqs(dev->kvm);
1967
		break;
1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981
	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;
1982 1983 1984 1985 1986 1987
	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;
1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018
	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,
};
2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110

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;
}

2111
int kvm_set_routing_entry(struct kvm_kernel_irq_routing_entry *e,
2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137
			  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;
}
2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277

int kvm_s390_set_irq_state(struct kvm_vcpu *vcpu, void __user *irqstate, int len)
{
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
	struct kvm_s390_irq *buf;
	int r = 0;
	int n;

	buf = vmalloc(len);
	if (!buf)
		return -ENOMEM;

	if (copy_from_user((void *) buf, irqstate, len)) {
		r = -EFAULT;
		goto out_free;
	}

	/*
	 * Don't allow setting the interrupt state
	 * when there are already interrupts pending
	 */
	spin_lock(&li->lock);
	if (li->pending_irqs) {
		r = -EBUSY;
		goto out_unlock;
	}

	for (n = 0; n < len / sizeof(*buf); n++) {
		r = do_inject_vcpu(vcpu, &buf[n]);
		if (r)
			break;
	}

out_unlock:
	spin_unlock(&li->lock);
out_free:
	vfree(buf);

	return r;
}

static void store_local_irq(struct kvm_s390_local_interrupt *li,
			    struct kvm_s390_irq *irq,
			    unsigned long irq_type)
{
	switch (irq_type) {
	case IRQ_PEND_MCHK_EX:
	case IRQ_PEND_MCHK_REP:
		irq->type = KVM_S390_MCHK;
		irq->u.mchk = li->irq.mchk;
		break;
	case IRQ_PEND_PROG:
		irq->type = KVM_S390_PROGRAM_INT;
		irq->u.pgm = li->irq.pgm;
		break;
	case IRQ_PEND_PFAULT_INIT:
		irq->type = KVM_S390_INT_PFAULT_INIT;
		irq->u.ext = li->irq.ext;
		break;
	case IRQ_PEND_EXT_EXTERNAL:
		irq->type = KVM_S390_INT_EXTERNAL_CALL;
		irq->u.extcall = li->irq.extcall;
		break;
	case IRQ_PEND_EXT_CLOCK_COMP:
		irq->type = KVM_S390_INT_CLOCK_COMP;
		break;
	case IRQ_PEND_EXT_CPU_TIMER:
		irq->type = KVM_S390_INT_CPU_TIMER;
		break;
	case IRQ_PEND_SIGP_STOP:
		irq->type = KVM_S390_SIGP_STOP;
		irq->u.stop = li->irq.stop;
		break;
	case IRQ_PEND_RESTART:
		irq->type = KVM_S390_RESTART;
		break;
	case IRQ_PEND_SET_PREFIX:
		irq->type = KVM_S390_SIGP_SET_PREFIX;
		irq->u.prefix = li->irq.prefix;
		break;
	}
}

int kvm_s390_get_irq_state(struct kvm_vcpu *vcpu, __u8 __user *buf, int len)
{
	uint8_t sigp_ctrl = vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sigp_ctrl;
	unsigned long sigp_emerg_pending[BITS_TO_LONGS(KVM_MAX_VCPUS)];
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
	unsigned long pending_irqs;
	struct kvm_s390_irq irq;
	unsigned long irq_type;
	int cpuaddr;
	int n = 0;

	spin_lock(&li->lock);
	pending_irqs = li->pending_irqs;
	memcpy(&sigp_emerg_pending, &li->sigp_emerg_pending,
	       sizeof(sigp_emerg_pending));
	spin_unlock(&li->lock);

	for_each_set_bit(irq_type, &pending_irqs, IRQ_PEND_COUNT) {
		memset(&irq, 0, sizeof(irq));
		if (irq_type == IRQ_PEND_EXT_EMERGENCY)
			continue;
		if (n + sizeof(irq) > len)
			return -ENOBUFS;
		store_local_irq(&vcpu->arch.local_int, &irq, irq_type);
		if (copy_to_user(&buf[n], &irq, sizeof(irq)))
			return -EFAULT;
		n += sizeof(irq);
	}

	if (test_bit(IRQ_PEND_EXT_EMERGENCY, &pending_irqs)) {
		for_each_set_bit(cpuaddr, sigp_emerg_pending, KVM_MAX_VCPUS) {
			memset(&irq, 0, sizeof(irq));
			if (n + sizeof(irq) > len)
				return -ENOBUFS;
			irq.type = KVM_S390_INT_EMERGENCY;
			irq.u.emerg.code = cpuaddr;
			if (copy_to_user(&buf[n], &irq, sizeof(irq)))
				return -EFAULT;
			n += sizeof(irq);
		}
	}

	if ((sigp_ctrl & SIGP_CTRL_C) &&
	    (atomic_read(&vcpu->arch.sie_block->cpuflags) &
	     CPUSTAT_ECALL_PEND)) {
		if (n + sizeof(irq) > len)
			return -ENOBUFS;
		memset(&irq, 0, sizeof(irq));
		irq.type = KVM_S390_INT_EXTERNAL_CALL;
		irq.u.extcall.code = sigp_ctrl & SIGP_CTRL_SCN_MASK;
		if (copy_to_user(&buf[n], &irq, sizeof(irq)))
			return -EFAULT;
		n += sizeof(irq);
	}

	return n;
}