interrupt.c 53.3 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 26
#include "kvm-s390.h"
#include "gaccess.h"
27
#include "trace-s390.h"
28

29 30 31 32
#define IOINT_SCHID_MASK 0x0000ffff
#define IOINT_SSID_MASK 0x00030000
#define IOINT_CSSID_MASK 0x03fc0000
#define IOINT_AI_MASK 0x04000000
33
#define PFAULT_INIT 0x0600
34 35
#define PFAULT_DONE 0x0680
#define VIRTIO_PARAM 0x0d00
36 37 38 39 40 41

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

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

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

52 53 54 55 56
static int psw_mchk_disabled(struct kvm_vcpu *vcpu)
{
	return !(vcpu->arch.sie_block->gpsw.mask & PSW_MASK_MCHECK);
}

57 58 59 60 61 62 63 64 65
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;
}

66 67 68 69 70
static int ckc_interrupts_enabled(struct kvm_vcpu *vcpu)
{
	if (psw_extint_disabled(vcpu) ||
	    !(vcpu->arch.sie_block->gcr[0] & 0x800ul))
		return 0;
71 72 73
	if (guestdbg_enabled(vcpu) && guestdbg_sstep_enabled(vcpu))
		/* No timer interrupts when single stepping */
		return 0;
74 75 76
	return 1;
}

C
Cornelia Huck 已提交
77 78 79 80 81 82 83
static u64 int_word_to_isc_bits(u32 int_word)
{
	u8 isc = (int_word & 0x38000000) >> 27;

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

84
static int __must_check __interrupt_is_deliverable(struct kvm_vcpu *vcpu,
85
				      struct kvm_s390_interrupt_info *inti)
86 87
{
	switch (inti->type) {
88 89 90 91 92
	case KVM_S390_INT_EXTERNAL_CALL:
		if (psw_extint_disabled(vcpu))
			return 0;
		if (vcpu->arch.sie_block->gcr[0] & 0x2000ul)
			return 1;
93
		return 0;
94 95 96 97 98 99
	case KVM_S390_INT_EMERGENCY:
		if (psw_extint_disabled(vcpu))
			return 0;
		if (vcpu->arch.sie_block->gcr[0] & 0x4000ul)
			return 1;
		return 0;
100 101 102 103 104 105 106 107
	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;
108
	case KVM_S390_INT_SERVICE:
109 110
	case KVM_S390_INT_PFAULT_INIT:
	case KVM_S390_INT_PFAULT_DONE:
111 112 113 114 115 116 117 118 119 120 121
	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;
122 123 124 125 126 127
	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;
128 129 130
	case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
		if (psw_ioint_disabled(vcpu))
			return 0;
C
Cornelia Huck 已提交
131 132
		if (vcpu->arch.sie_block->gcr[6] &
		    int_word_to_isc_bits(inti->io.io_int_word))
133 134
			return 1;
		return 0;
135
	default:
136 137
		printk(KERN_WARNING "illegal interrupt type %llx\n",
		       inti->type);
138 139 140 141 142
		BUG();
	}
	return 0;
}

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

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

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

165 166 167 168 169 170
	/*
	 * 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);

171 172 173
	return active_mask;
}

174 175 176 177 178 179 180 181 182 183 184 185 186 187
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)
{
188 189
	atomic_clear_mask(CPUSTAT_IO_INT | CPUSTAT_EXT_INT | CPUSTAT_STOP_INT,
			  &vcpu->arch.sie_block->cpuflags);
190
	vcpu->arch.sie_block->lctl = 0x0000;
191 192 193 194 195 196 197
	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);
	}
198 199 200 201 202 203 204
}

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

205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224
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;
}

225 226 227 228 229 230
static void set_intercept_indicators_stop(struct kvm_vcpu *vcpu)
{
	if (kvm_s390_is_stop_irq_pending(vcpu))
		__set_cpuflag(vcpu, CPUSTAT_STOP_INT);
}

231 232 233 234 235
/* 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);
236
	set_intercept_indicators_stop(vcpu);
237 238
}

239
static void __set_intercept_indicator(struct kvm_vcpu *vcpu,
240
				      struct kvm_s390_interrupt_info *inti)
241 242 243
{
	switch (inti->type) {
	case KVM_S390_INT_SERVICE:
244
	case KVM_S390_INT_PFAULT_DONE:
245 246 247 248 249 250
	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;
251 252 253 254 255 256
	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;
257 258 259 260 261 262
	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;
263 264 265 266 267
	default:
		BUG();
	}
}

268 269 270 271 272 273 274 275 276
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 */
277
		return insn_length(vcpu->arch.sie_block->ipa >> 8);
278 279 280 281 282 283 284
	case ICPT_PROGI:
		return vcpu->arch.sie_block->pgmilc;
	default:
		return 0;
	}
}

285 286
static int __must_check __deliver_cpu_timer(struct kvm_vcpu *vcpu)
{
287
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
288 289 290 291 292 293 294
	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);
295
	rc |= put_guest_lc(vcpu, 0, (u16 *)__LC_EXT_CPU_ADDR);
296 297 298 299
	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));
300
	clear_bit(IRQ_PEND_EXT_CPU_TIMER, &li->pending_irqs);
301
	return rc ? -EFAULT : 0;
302 303 304 305
}

static int __must_check __deliver_ckc(struct kvm_vcpu *vcpu)
{
306
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
307 308 309 310 311 312 313
	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);
314
	rc |= put_guest_lc(vcpu, 0, (u16 *)__LC_EXT_CPU_ADDR);
315 316 317 318
	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));
319
	clear_bit(IRQ_PEND_EXT_CLOCK_COMP, &li->pending_irqs);
320
	return rc ? -EFAULT : 0;
321 322
}

323
static int __must_check __deliver_pfault_init(struct kvm_vcpu *vcpu)
324
{
325 326
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
	struct kvm_s390_ext_info ext;
327 328
	int rc;

329 330 331 332 333 334
	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);

335
	VCPU_EVENT(vcpu, 4, "interrupt: pfault init parm:%x,parm64:%llx",
336
		   0, ext.ext_params2);
337 338
	trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id,
					 KVM_S390_INT_PFAULT_INIT,
339
					 0, ext.ext_params2);
340 341 342 343 344 345 346

	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));
347
	rc |= put_guest_lc(vcpu, ext.ext_params2, (u64 *) __LC_EXT_PARAMS2);
348
	return rc ? -EFAULT : 0;
349 350
}

351
static int __must_check __deliver_machine_check(struct kvm_vcpu *vcpu)
352
{
353 354
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
	struct kvm_s390_mchk_info mchk;
E
Eric Farman 已提交
355
	unsigned long adtl_status_addr;
356 357
	int rc;

358 359 360 361 362 363 364 365 366 367 368 369
	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);

370
	VCPU_EVENT(vcpu, 4, "interrupt: machine check mcic=%llx",
371
		   mchk.mcic);
372
	trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_MCHK,
373
					 mchk.cr14, mchk.mcic);
374 375

	rc  = kvm_s390_vcpu_store_status(vcpu, KVM_S390_STORE_STATUS_PREFIXED);
E
Eric Farman 已提交
376 377 378
	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);
379
	rc |= put_guest_lc(vcpu, mchk.mcic,
380
			   (u64 __user *) __LC_MCCK_CODE);
381
	rc |= put_guest_lc(vcpu, mchk.failing_storage_address,
382 383
			   (u64 __user *) __LC_MCCK_FAIL_STOR_ADDR);
	rc |= write_guest_lc(vcpu, __LC_PSW_SAVE_AREA,
384
			     &mchk.fixed_logout, sizeof(mchk.fixed_logout));
385 386 387 388
	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));
389
	return rc ? -EFAULT : 0;
390 391 392 393
}

static int __must_check __deliver_restart(struct kvm_vcpu *vcpu)
{
394
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
395 396 397 398 399 400 401 402 403 404 405
	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));
406
	clear_bit(IRQ_PEND_RESTART, &li->pending_irqs);
407
	return rc ? -EFAULT : 0;
408 409
}

410
static int __must_check __deliver_set_prefix(struct kvm_vcpu *vcpu)
411
{
412 413 414 415 416 417 418 419
	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);
420

421
	VCPU_EVENT(vcpu, 4, "interrupt: set prefix to %x", prefix.address);
422 423 424
	vcpu->stat.deliver_prefix_signal++;
	trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id,
					 KVM_S390_SIGP_SET_PREFIX,
425
					 prefix.address, 0);
426

427
	kvm_s390_set_prefix(vcpu, prefix.address);
428 429 430
	return 0;
}

431
static int __must_check __deliver_emergency_signal(struct kvm_vcpu *vcpu)
432
{
433
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
434
	int rc;
435 436 437 438 439 440 441 442
	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);
443 444 445

	VCPU_EVENT(vcpu, 4, "%s", "interrupt: sigp emerg");
	vcpu->stat.deliver_emergency_signal++;
446 447
	trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_INT_EMERGENCY,
					 cpu_addr, 0);
448 449 450

	rc  = put_guest_lc(vcpu, EXT_IRQ_EMERGENCY_SIG,
			   (u16 *)__LC_EXT_INT_CODE);
451
	rc |= put_guest_lc(vcpu, cpu_addr, (u16 *)__LC_EXT_CPU_ADDR);
452 453 454 455
	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));
456
	return rc ? -EFAULT : 0;
457 458
}

459
static int __must_check __deliver_external_call(struct kvm_vcpu *vcpu)
460
{
461 462
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
	struct kvm_s390_extcall_info extcall;
463 464
	int rc;

465 466 467 468 469 470
	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);

471 472 473 474
	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,
475
					 extcall.code, 0);
476 477 478

	rc  = put_guest_lc(vcpu, EXT_IRQ_EXTERNAL_CALL,
			   (u16 *)__LC_EXT_INT_CODE);
479
	rc |= put_guest_lc(vcpu, extcall.code, (u16 *)__LC_EXT_CPU_ADDR);
480 481 482 483
	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));
484
	return rc ? -EFAULT : 0;
485 486
}

487
static int __must_check __deliver_prog(struct kvm_vcpu *vcpu)
488
{
489 490
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
	struct kvm_s390_pgm_info pgm_info;
491
	int rc = 0, nullifying = false;
492
	u16 ilc = get_ilc(vcpu);
493

494 495 496 497 498 499
	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);

500
	VCPU_EVENT(vcpu, 4, "interrupt: pgm check code:%x, ilc:%x",
501
		   pgm_info.code, ilc);
502 503
	vcpu->stat.deliver_program_int++;
	trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_PROGRAM_INT,
504
					 pgm_info.code, 0);
505

506
	switch (pgm_info.code & ~PGM_PER) {
507 508 509 510 511 512 513 514 515
	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:
516 517
		nullifying = true;
		/* fall through */
518
	case PGM_SPACE_SWITCH:
519
		rc = put_guest_lc(vcpu, pgm_info.trans_exc_code,
520 521 522 523 524 525 526 527
				  (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:
528
		rc = put_guest_lc(vcpu, pgm_info.exc_access_id,
529
				  (u8 *)__LC_EXC_ACCESS_ID);
530
		nullifying = true;
531 532 533 534 535 536 537
		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:
538
		rc = put_guest_lc(vcpu, pgm_info.trans_exc_code,
539
				  (u64 *)__LC_TRANS_EXC_CODE);
540
		rc |= put_guest_lc(vcpu, pgm_info.exc_access_id,
541
				   (u8 *)__LC_EXC_ACCESS_ID);
542
		rc |= put_guest_lc(vcpu, pgm_info.op_access_id,
543
				   (u8 *)__LC_OP_ACCESS_ID);
544
		nullifying = true;
545 546
		break;
	case PGM_MONITOR:
547
		rc = put_guest_lc(vcpu, pgm_info.mon_class_nr,
548
				  (u16 *)__LC_MON_CLASS_NR);
549
		rc |= put_guest_lc(vcpu, pgm_info.mon_code,
550 551
				   (u64 *)__LC_MON_CODE);
		break;
E
Eric Farman 已提交
552
	case PGM_VECTOR_PROCESSING:
553
	case PGM_DATA:
554
		rc = put_guest_lc(vcpu, pgm_info.data_exc_code,
555 556 557
				  (u32 *)__LC_DATA_EXC_CODE);
		break;
	case PGM_PROTECTION:
558
		rc = put_guest_lc(vcpu, pgm_info.trans_exc_code,
559
				  (u64 *)__LC_TRANS_EXC_CODE);
560
		rc |= put_guest_lc(vcpu, pgm_info.exc_access_id,
561 562
				   (u8 *)__LC_EXC_ACCESS_ID);
		break;
563 564 565 566 567 568 569 570 571
	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;
572 573
	}

574 575
	if (pgm_info.code & PGM_PER) {
		rc |= put_guest_lc(vcpu, pgm_info.per_code,
576
				   (u8 *) __LC_PER_CODE);
577
		rc |= put_guest_lc(vcpu, pgm_info.per_atmid,
578
				   (u8 *)__LC_PER_ATMID);
579
		rc |= put_guest_lc(vcpu, pgm_info.per_address,
580
				   (u64 *) __LC_PER_ADDRESS);
581
		rc |= put_guest_lc(vcpu, pgm_info.per_access_id,
582 583 584
				   (u8 *) __LC_PER_ACCESS_ID);
	}

585 586 587
	if (nullifying && vcpu->arch.sie_block->icptcode == ICPT_INST)
		kvm_s390_rewind_psw(vcpu, ilc);

588
	rc |= put_guest_lc(vcpu, ilc, (u16 *) __LC_PGM_ILC);
589 590
	rc |= put_guest_lc(vcpu, vcpu->arch.sie_block->gbea,
				 (u64 *) __LC_LAST_BREAK);
591
	rc |= put_guest_lc(vcpu, pgm_info.code,
592 593 594 595 596
			   (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));
597
	return rc ? -EFAULT : 0;
598 599 600 601 602 603 604 605 606 607 608 609 610 611
}

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);
612
	rc |= put_guest_lc(vcpu, 0, (u16 *)__LC_EXT_CPU_ADDR);
613 614 615 616 617 618
	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);
619
	return rc ? -EFAULT : 0;
620 621 622 623 624 625 626 627 628 629
}

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);
630

631 632 633 634 635 636 637 638
	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);
639
	return rc ? -EFAULT : 0;
640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663
}

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);
664
	return rc ? -EFAULT : 0;
665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691
}

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));
692
	return rc ? -EFAULT : 0;
693 694
}

695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716
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));
717
	return rc ? -EFAULT : 0;
718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735
}

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)
736
{
737
	int rc;
738 739 740

	switch (inti->type) {
	case KVM_S390_INT_SERVICE:
741
		rc = __deliver_service(vcpu, inti);
742
		break;
743
	case KVM_S390_INT_PFAULT_DONE:
744
		rc = __deliver_pfault_done(vcpu, inti);
745
		break;
746
	case KVM_S390_INT_VIRTIO:
747
		rc = __deliver_virtio(vcpu, inti);
748
		break;
749
	case KVM_S390_MCHK:
750
		rc = __deliver_mchk_floating(vcpu, inti);
751
		break;
752
	case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
753
		rc = __deliver_io(vcpu, inti);
754
		break;
755 756 757
	default:
		BUG();
	}
758 759

	return rc;
760 761
}

762 763
/* Check whether an external call is pending (deliverable or not) */
int kvm_s390_ext_call_pending(struct kvm_vcpu *vcpu)
764
{
765 766
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
	uint8_t sigp_ctrl = vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sigp_ctrl;
767

768 769
	if (!sclp_has_sigpif())
		return test_bit(IRQ_PEND_EXT_EXTERNAL, &li->pending_irqs);
770

771 772
	return (sigp_ctrl & SIGP_CTRL_C) &&
	       (atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_ECALL_PEND);
773 774
}

775
int kvm_s390_vcpu_has_irq(struct kvm_vcpu *vcpu, int exclude_stop)
776
{
777 778
	struct kvm_s390_float_interrupt *fi = vcpu->arch.local_int.float_int;
	struct kvm_s390_interrupt_info  *inti;
779
	int rc;
780

781
	rc = !!deliverable_local_irqs(vcpu);
782 783

	if ((!rc) && atomic_read(&fi->active)) {
784
		spin_lock(&fi->lock);
785 786 787 788 789
		list_for_each_entry(inti, &fi->list, list)
			if (__interrupt_is_deliverable(vcpu, inti)) {
				rc = 1;
				break;
			}
790
		spin_unlock(&fi->lock);
791 792
	}

793 794
	if (!rc && kvm_cpu_has_pending_timer(vcpu))
		rc = 1;
795

796 797 798 799
	/* external call pending and deliverable */
	if (!rc && kvm_s390_ext_call_pending(vcpu) &&
	    !psw_extint_disabled(vcpu) &&
	    (vcpu->arch.sie_block->gcr[0] & 0x2000ul))
800 801
		rc = 1;

802
	if (!rc && !exclude_stop && kvm_s390_is_stop_irq_pending(vcpu))
803 804
		rc = 1;

805 806 807
	return rc;
}

808 809
int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
{
810 811 812 813 814 815
	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;
816 817
}

818 819 820 821 822 823
int kvm_s390_handle_wait(struct kvm_vcpu *vcpu)
{
	u64 now, sltime;

	vcpu->stat.exit_wait_state++;

824 825 826
	/* fast path */
	if (kvm_cpu_has_pending_timer(vcpu) || kvm_arch_vcpu_runnable(vcpu))
		return 0;
827

828 829
	if (psw_interrupts_disabled(vcpu)) {
		VCPU_EVENT(vcpu, 3, "%s", "disabled wait");
830
		return -EOPNOTSUPP; /* disabled wait */
831 832
	}

833
	if (!ckc_interrupts_enabled(vcpu)) {
834
		VCPU_EVENT(vcpu, 3, "%s", "enabled wait w/o timer");
835
		__set_cpu_idle(vcpu);
836 837 838
		goto no_timer;
	}

839
	now = get_tod_clock_fast() + vcpu->arch.sie_block->epoch;
840
	sltime = tod_to_ns(vcpu->arch.sie_block->ckc - now);
841 842 843 844 845 846

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

	__set_cpu_idle(vcpu);
847 848
	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);
849
no_timer:
850
	srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
851
	kvm_vcpu_block(vcpu);
852
	__unset_cpu_idle(vcpu);
853 854
	vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);

855
	hrtimer_cancel(&vcpu->arch.ckc_timer);
856 857 858
	return 0;
}

859 860 861 862 863 864 865 866 867
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);
868
		vcpu->stat.halt_wakeup++;
869 870 871
	}
}

872 873 874
enum hrtimer_restart kvm_s390_idle_wakeup(struct hrtimer *timer)
{
	struct kvm_vcpu *vcpu;
875
	u64 now, sltime;
876 877

	vcpu = container_of(timer, struct kvm_vcpu, arch.ckc_timer);
878 879
	now = get_tod_clock_fast() + vcpu->arch.sie_block->epoch;
	sltime = tod_to_ns(vcpu->arch.sie_block->ckc - now);
880

881 882 883 884 885 886 887 888
	/*
	 * 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);
889 890
	return HRTIMER_NORESTART;
}
891

892 893 894 895
void kvm_s390_clear_local_irqs(struct kvm_vcpu *vcpu)
{
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;

896
	spin_lock(&li->lock);
897 898 899
	li->pending_irqs = 0;
	bitmap_zero(li->sigp_emerg_pending, KVM_MAX_VCPUS);
	memset(&li->irq, 0, sizeof(li->irq));
900
	spin_unlock(&li->lock);
901 902

	/* clear pending external calls set by sigp interpretation facility */
903
	atomic_clear_mask(CPUSTAT_ECALL_PEND, li->cpuflags);
904
	vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sigp_ctrl = 0;
905 906
}

907
int __must_check kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu)
908
{
909 910 911
	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;
912
	deliver_irq_t func;
913
	int deliver;
914
	int rc = 0;
915 916
	unsigned long irq_type;
	unsigned long deliverable_irqs;
917 918 919

	__reset_intercept_indicators(vcpu);

920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940
	/* 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);
941

942
	if (!rc && atomic_read(&fi->active)) {
943 944
		do {
			deliver = 0;
945
			spin_lock(&fi->lock);
946 947 948
			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
949
					fi->irq_count--;
950 951 952 953 954 955 956
					deliver = 1;
					break;
				}
				__set_intercept_indicator(vcpu, inti);
			}
			if (list_empty(&fi->list))
				atomic_set(&fi->active, 0);
957
			spin_unlock(&fi->lock);
958
			if (deliver) {
959
				rc = __deliver_floating_interrupt(vcpu, inti);
960 961
				kfree(inti);
			}
962
		} while (!rc && deliver);
963
	}
964 965

	return rc;
966 967
}

968
static int __inject_prog(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
969 970 971
{
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;

972
	li->irq.pgm = irq->u.pgm;
973
	set_bit(IRQ_PEND_PROG, &li->pending_irqs);
974 975 976
	return 0;
}

977 978
int kvm_s390_inject_program_int(struct kvm_vcpu *vcpu, u16 code)
{
979
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
980
	struct kvm_s390_irq irq;
981 982

	VCPU_EVENT(vcpu, 3, "inject: program check %d (from kernel)", code);
983 984
	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_PROGRAM_INT, code,
				   0, 1);
985
	spin_lock(&li->lock);
986 987
	irq.u.pgm.code = code;
	__inject_prog(vcpu, &irq);
988
	BUG_ON(waitqueue_active(li->wq));
989
	spin_unlock(&li->lock);
990 991 992 993 994 995 996
	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;
997
	struct kvm_s390_irq irq;
998
	int rc;
999 1000 1001 1002 1003

	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);
1004
	spin_lock(&li->lock);
1005 1006
	irq.u.pgm = *pgm_info;
	rc = __inject_prog(vcpu, &irq);
1007
	BUG_ON(waitqueue_active(li->wq));
1008
	spin_unlock(&li->lock);
1009 1010 1011
	return rc;
}

1012
static int __inject_pfault_init(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
1013 1014 1015
{
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;

1016 1017 1018 1019 1020 1021 1022 1023
	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);
1024 1025 1026 1027
	atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags);
	return 0;
}

1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042
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;
	}
	atomic_set_mask(CPUSTAT_ECALL_PEND, &vcpu->arch.sie_block->cpuflags);
	return 0;
}

1043
static int __inject_extcall(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
1044 1045
{
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
1046
	struct kvm_s390_extcall_info *extcall = &li->irq.extcall;
1047
	uint16_t src_id = irq->u.extcall.code;
1048 1049

	VCPU_EVENT(vcpu, 3, "inject: external call source-cpu:%u",
1050
		   src_id);
1051
	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_INT_EXTERNAL_CALL,
1052 1053 1054 1055 1056 1057 1058 1059 1060
				   src_id, 0, 2);

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

	if (sclp_has_sigpif())
		return __inject_extcall_sigpif(vcpu, src_id);
1061

1062 1063
	if (!test_and_set_bit(IRQ_PEND_EXT_EXTERNAL, &li->pending_irqs))
		return -EBUSY;
1064
	*extcall = irq->u.extcall;
1065 1066 1067 1068
	atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags);
	return 0;
}

1069
static int __inject_set_prefix(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
1070 1071
{
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
1072
	struct kvm_s390_prefix_info *prefix = &li->irq.prefix;
1073 1074

	VCPU_EVENT(vcpu, 3, "inject: set prefix to %x (from user)",
1075
		   irq->u.prefix.address);
1076
	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_SIGP_SET_PREFIX,
1077
				   irq->u.prefix.address, 0, 2);
1078

1079 1080 1081
	if (!is_vcpu_stopped(vcpu))
		return -EBUSY;

1082 1083
	*prefix = irq->u.prefix;
	set_bit(IRQ_PEND_SET_PREFIX, &li->pending_irqs);
1084 1085 1086
	return 0;
}

1087
#define KVM_S390_STOP_SUPP_FLAGS (KVM_S390_STOP_FLAG_STORE_STATUS)
1088
static int __inject_sigp_stop(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
1089 1090
{
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
1091
	struct kvm_s390_stop_info *stop = &li->irq.stop;
1092
	int rc = 0;
1093

1094 1095
	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_SIGP_STOP, 0, 0, 2);

1096 1097 1098
	if (irq->u.stop.flags & ~KVM_S390_STOP_SUPP_FLAGS)
		return -EINVAL;

1099 1100 1101 1102 1103 1104 1105 1106 1107
	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;
1108
	stop->flags = irq->u.stop.flags;
1109
	__set_cpuflag(vcpu, CPUSTAT_STOP_INT);
1110 1111 1112 1113
	return 0;
}

static int __inject_sigp_restart(struct kvm_vcpu *vcpu,
1114
				 struct kvm_s390_irq *irq)
1115 1116 1117
{
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;

1118 1119 1120 1121
	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);
1122 1123 1124 1125
	return 0;
}

static int __inject_sigp_emergency(struct kvm_vcpu *vcpu,
1126
				   struct kvm_s390_irq *irq)
1127 1128 1129
{
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;

1130 1131 1132
	VCPU_EVENT(vcpu, 3, "inject: emergency %u\n",
		   irq->u.emerg.code);
	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_INT_EMERGENCY,
1133
				   irq->u.emerg.code, 0, 2);
1134

1135
	set_bit(irq->u.emerg.code, li->sigp_emerg_pending);
1136
	set_bit(IRQ_PEND_EXT_EMERGENCY, &li->pending_irqs);
1137 1138 1139 1140
	atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags);
	return 0;
}

1141
static int __inject_mchk(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
1142 1143
{
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
1144
	struct kvm_s390_mchk_info *mchk = &li->irq.mchk;
1145 1146

	VCPU_EVENT(vcpu, 5, "inject: machine check parm64:%llx",
1147
		   irq->u.mchk.mcic);
1148
	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_MCHK, 0,
1149
				   irq->u.mchk.mcic, 2);
1150 1151

	/*
1152 1153 1154 1155 1156 1157
	 * 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
1158
	 */
1159
	mchk->cr14 |= irq->u.mchk.cr14;
1160
	mchk->mcic |= irq->u.mchk.mcic;
1161 1162 1163 1164
	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));
1165 1166 1167 1168
	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);
1169 1170 1171
	return 0;
}

1172
static int __inject_ckc(struct kvm_vcpu *vcpu)
1173 1174 1175
{
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;

1176 1177 1178 1179 1180
	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);
1181 1182 1183 1184
	atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags);
	return 0;
}

1185
static int __inject_cpu_timer(struct kvm_vcpu *vcpu)
1186 1187 1188
{
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;

1189 1190 1191 1192 1193
	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);
1194
	atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags);
1195 1196 1197
	return 0;
}

1198

1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212
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;
	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
1213 1214
		if (cr6 &&
		    ((cr6 & int_word_to_isc_bits(iter->io.io_int_word)) == 0))
1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226
			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
1227
	if (inti) {
1228
		list_del_init(&inti->list);
J
Jens Freimann 已提交
1229 1230
		fi->irq_count--;
	}
1231 1232 1233 1234 1235
	if (list_empty(&fi->list))
		atomic_set(&fi->active, 0);
	spin_unlock(&fi->lock);
	return inti;
}
1236

J
Jens Freimann 已提交
1237
static int __inject_vm(struct kvm *kvm, struct kvm_s390_interrupt_info *inti)
1238
{
1239 1240
	struct kvm_s390_local_interrupt *li;
	struct kvm_s390_float_interrupt *fi;
1241
	struct kvm_s390_interrupt_info *iter;
1242
	struct kvm_vcpu *dst_vcpu = NULL;
1243
	int sigcpu;
J
Jens Freimann 已提交
1244
	int rc = 0;
1245

1246 1247
	fi = &kvm->arch.float_int;
	spin_lock(&fi->lock);
J
Jens Freimann 已提交
1248 1249 1250 1251 1252
	if (fi->irq_count >= KVM_S390_MAX_FLOAT_IRQS) {
		rc = -EINVAL;
		goto unlock_fi;
	}
	fi->irq_count++;
1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269
	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);
1270 1271
	if (atomic_read(&kvm->online_vcpus) == 0)
		goto unlock_fi;
1272 1273 1274 1275 1276 1277
	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;
1278
		} while (kvm_get_vcpu(kvm, sigcpu) == NULL);
1279
	}
1280 1281
	dst_vcpu = kvm_get_vcpu(kvm, sigcpu);
	li = &dst_vcpu->arch.local_int;
1282
	spin_lock(&li->lock);
1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293
	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;
	}
1294
	spin_unlock(&li->lock);
1295
	kvm_s390_vcpu_wakeup(kvm_get_vcpu(kvm, sigcpu));
J
Jens Freimann 已提交
1296
unlock_fi:
1297
	spin_unlock(&fi->lock);
J
Jens Freimann 已提交
1298
	return rc;
1299 1300 1301 1302 1303 1304
}

int kvm_s390_inject_vm(struct kvm *kvm,
		       struct kvm_s390_interrupt *s390int)
{
	struct kvm_s390_interrupt_info *inti;
1305
	int rc;
1306

1307 1308 1309 1310
	inti = kzalloc(sizeof(*inti), GFP_KERNEL);
	if (!inti)
		return -ENOMEM;

1311 1312
	inti->type = s390int->type;
	switch (inti->type) {
1313
	case KVM_S390_INT_VIRTIO:
1314
		VM_EVENT(kvm, 5, "inject: virtio parm:%x,parm64:%llx",
1315 1316 1317 1318 1319 1320 1321 1322
			 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;
1323 1324 1325
	case KVM_S390_INT_PFAULT_DONE:
		inti->ext.ext_params2 = s390int->parm64;
		break;
1326 1327 1328 1329 1330 1331
	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;
1332
	case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
1333
		if (inti->type & IOINT_AI_MASK)
1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344
			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;
1345 1346 1347 1348
	default:
		kfree(inti);
		return -EINVAL;
	}
1349 1350
	trace_kvm_s390_inject_vm(s390int->type, s390int->parm, s390int->parm64,
				 2);
1351

1352 1353 1354 1355
	rc = __inject_vm(kvm, inti);
	if (rc)
		kfree(inti);
	return rc;
1356 1357
}

1358
int kvm_s390_reinject_io_int(struct kvm *kvm,
1359 1360
			      struct kvm_s390_interrupt_info *inti)
{
1361
	return __inject_vm(kvm, inti);
1362 1363
}

1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376
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;
1377 1378 1379
	case KVM_S390_SIGP_STOP:
		irq->u.stop.flags = s390int->parm;
		break;
1380
	case KVM_S390_INT_EXTERNAL_CALL:
1381
		if (s390int->parm & 0xffff0000)
1382 1383 1384 1385
			return -EINVAL;
		irq->u.extcall.code = s390int->parm;
		break;
	case KVM_S390_INT_EMERGENCY:
1386
		if (s390int->parm & 0xffff0000)
1387 1388 1389 1390 1391 1392 1393 1394 1395 1396
			return -EINVAL;
		irq->u.emerg.code = s390int->parm;
		break;
	case KVM_S390_MCHK:
		irq->u.mchk.mcic = s390int->parm64;
		break;
	}
	return 0;
}

1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413
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);
}

1414
int kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
1415
{
1416 1417
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
	int rc;
1418

1419
	spin_lock(&li->lock);
1420
	switch (irq->type) {
1421 1422
	case KVM_S390_PROGRAM_INT:
		VCPU_EVENT(vcpu, 3, "inject: program check %d (from user)",
1423 1424
			   irq->u.pgm.code);
		rc = __inject_prog(vcpu, irq);
1425
		break;
1426
	case KVM_S390_SIGP_SET_PREFIX:
1427
		rc = __inject_set_prefix(vcpu, irq);
1428
		break;
1429
	case KVM_S390_SIGP_STOP:
1430
		rc = __inject_sigp_stop(vcpu, irq);
1431
		break;
1432
	case KVM_S390_RESTART:
1433
		rc = __inject_sigp_restart(vcpu, irq);
1434
		break;
1435
	case KVM_S390_INT_CLOCK_COMP:
1436
		rc = __inject_ckc(vcpu);
1437
		break;
1438
	case KVM_S390_INT_CPU_TIMER:
1439
		rc = __inject_cpu_timer(vcpu);
1440
		break;
1441
	case KVM_S390_INT_EXTERNAL_CALL:
1442
		rc = __inject_extcall(vcpu, irq);
1443
		break;
1444
	case KVM_S390_INT_EMERGENCY:
1445
		rc = __inject_sigp_emergency(vcpu, irq);
1446
		break;
1447
	case KVM_S390_MCHK:
1448
		rc = __inject_mchk(vcpu, irq);
1449
		break;
1450
	case KVM_S390_INT_PFAULT_INIT:
1451
		rc = __inject_pfault_init(vcpu, irq);
1452
		break;
1453 1454
	case KVM_S390_INT_VIRTIO:
	case KVM_S390_INT_SERVICE:
1455
	case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
1456
	default:
1457
		rc = -EINVAL;
1458
	}
1459
	spin_unlock(&li->lock);
1460 1461 1462
	if (!rc)
		kvm_s390_vcpu_wakeup(vcpu);
	return rc;
1463
}
1464

1465
void kvm_s390_clear_float_irqs(struct kvm *kvm)
1466 1467 1468 1469 1470 1471 1472 1473 1474 1475
{
	struct kvm_s390_float_interrupt *fi;
	struct kvm_s390_interrupt_info	*n, *inti = NULL;

	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
1476
	fi->irq_count = 0;
1477 1478 1479 1480
	atomic_set(&fi->active, 0);
	spin_unlock(&fi->lock);
}

1481 1482
static void inti_to_irq(struct kvm_s390_interrupt_info *inti,
		       struct kvm_s390_irq *irq)
1483
{
1484
	irq->type = inti->type;
1485
	switch (inti->type) {
1486 1487
	case KVM_S390_INT_PFAULT_INIT:
	case KVM_S390_INT_PFAULT_DONE:
1488 1489
	case KVM_S390_INT_VIRTIO:
	case KVM_S390_INT_SERVICE:
1490
		irq->u.ext = inti->ext;
1491 1492
		break;
	case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
1493
		irq->u.io = inti->io;
1494 1495
		break;
	case KVM_S390_MCHK:
1496
		irq->u.mchk = inti->mchk;
1497 1498 1499 1500
		break;
	}
}

1501
static int get_all_floating_irqs(struct kvm *kvm, u8 __user *usrbuf, u64 len)
1502 1503 1504
{
	struct kvm_s390_interrupt_info *inti;
	struct kvm_s390_float_interrupt *fi;
1505 1506
	struct kvm_s390_irq *buf;
	int max_irqs;
1507 1508 1509
	int ret = 0;
	int n = 0;

1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523
	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);

1524 1525 1526
	fi = &kvm->arch.float_int;
	spin_lock(&fi->lock);
	list_for_each_entry(inti, &fi->list, list) {
1527
		if (n == max_irqs) {
1528 1529 1530 1531
			/* signal userspace to try again */
			ret = -ENOMEM;
			break;
		}
1532
		inti_to_irq(inti, &buf[n]);
1533 1534 1535
		n++;
	}
	spin_unlock(&fi->lock);
1536 1537 1538 1539 1540
	if (!ret && n > 0) {
		if (copy_to_user(usrbuf, buf, sizeof(struct kvm_s390_irq) * n))
			ret = -EFAULT;
	}
	vfree(buf);
1541 1542 1543 1544 1545 1546 1547 1548 1549 1550

	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:
1551
		r = get_all_floating_irqs(dev->kvm, (u8 __user *) attr->addr,
1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572
					  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) {
1573 1574
	case KVM_S390_INT_PFAULT_INIT:
	case KVM_S390_INT_PFAULT_DONE:
1575 1576 1577 1578 1579 1580 1581 1582 1583 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
	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
1623 1624 1625 1626 1627
		r = __inject_vm(dev->kvm, inti);
		if (r) {
			kfree(inti);
			return r;
		}
1628 1629 1630 1631 1632 1633 1634
		len -= sizeof(struct kvm_s390_irq);
		attr->addr += sizeof(struct kvm_s390_irq);
	}

	return r;
}

1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700
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;
1701
	map->addr = gmap_translate(kvm->arch.gmap, addr);
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 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 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799
	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;
}

1800 1801 1802
static int flic_set_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
{
	int r = 0;
1803 1804
	unsigned int i;
	struct kvm_vcpu *vcpu;
1805 1806 1807 1808 1809 1810

	switch (attr->group) {
	case KVM_DEV_FLIC_ENQUEUE:
		r = enqueue_floating_irq(dev, attr);
		break;
	case KVM_DEV_FLIC_CLEAR_IRQS:
1811
		kvm_s390_clear_float_irqs(dev->kvm);
1812
		break;
1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826
	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;
1827 1828 1829 1830 1831 1832
	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;
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
	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,
};
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 1955

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;
}

1956
int kvm_set_routing_entry(struct kvm_kernel_irq_routing_entry *e,
1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982
			  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;
}