interrupt.c 64.0 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
#include <asm/gmap.h>
27 28
#include "kvm-s390.h"
#include "gaccess.h"
29
#include "trace-s390.h"
30

31
#define PFAULT_INIT 0x0600
32 33
#define PFAULT_DONE 0x0680
#define VIRTIO_PARAM 0x0d00
34

35 36 37
/* handle external calls via sigp interpretation facility */
static int sca_ext_call_pending(struct kvm_vcpu *vcpu, int *src_id)
{
38 39
	int c, scn;

40 41 42
	if (!(atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_ECALL_PEND))
		return 0;

43
	read_lock(&vcpu->kvm->arch.sca_lock);
44 45 46 47 48 49 50 51 52 53 54 55 56 57 58
	if (vcpu->kvm->arch.use_esca) {
		struct esca_block *sca = vcpu->kvm->arch.sca;
		union esca_sigp_ctrl sigp_ctrl =
			sca->cpu[vcpu->vcpu_id].sigp_ctrl;

		c = sigp_ctrl.c;
		scn = sigp_ctrl.scn;
	} else {
		struct bsca_block *sca = vcpu->kvm->arch.sca;
		union bsca_sigp_ctrl sigp_ctrl =
			sca->cpu[vcpu->vcpu_id].sigp_ctrl;

		c = sigp_ctrl.c;
		scn = sigp_ctrl.scn;
	}
59
	read_unlock(&vcpu->kvm->arch.sca_lock);
60 61

	if (src_id)
62
		*src_id = scn;
63

64
	return c;
65 66 67 68
}

static int sca_inject_ext_call(struct kvm_vcpu *vcpu, int src_id)
{
69
	int expect, rc;
70

71
	read_lock(&vcpu->kvm->arch.sca_lock);
72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88
	if (vcpu->kvm->arch.use_esca) {
		struct esca_block *sca = vcpu->kvm->arch.sca;
		union esca_sigp_ctrl *sigp_ctrl =
			&(sca->cpu[vcpu->vcpu_id].sigp_ctrl);
		union esca_sigp_ctrl new_val = {0}, old_val = *sigp_ctrl;

		new_val.scn = src_id;
		new_val.c = 1;
		old_val.c = 0;

		expect = old_val.value;
		rc = cmpxchg(&sigp_ctrl->value, old_val.value, new_val.value);
	} else {
		struct bsca_block *sca = vcpu->kvm->arch.sca;
		union bsca_sigp_ctrl *sigp_ctrl =
			&(sca->cpu[vcpu->vcpu_id].sigp_ctrl);
		union bsca_sigp_ctrl new_val = {0}, old_val = *sigp_ctrl;
89

90 91 92 93 94 95 96
		new_val.scn = src_id;
		new_val.c = 1;
		old_val.c = 0;

		expect = old_val.value;
		rc = cmpxchg(&sigp_ctrl->value, old_val.value, new_val.value);
	}
97
	read_unlock(&vcpu->kvm->arch.sca_lock);
98 99

	if (rc != expect) {
100 101 102 103 104 105 106 107 108 109
		/* another external call is pending */
		return -EBUSY;
	}
	atomic_or(CPUSTAT_ECALL_PEND, &vcpu->arch.sie_block->cpuflags);
	return 0;
}

static void sca_clear_ext_call(struct kvm_vcpu *vcpu)
{
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
110
	int rc, expect;
111 112

	atomic_andnot(CPUSTAT_ECALL_PEND, li->cpuflags);
113
	read_lock(&vcpu->kvm->arch.sca_lock);
114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130
	if (vcpu->kvm->arch.use_esca) {
		struct esca_block *sca = vcpu->kvm->arch.sca;
		union esca_sigp_ctrl *sigp_ctrl =
			&(sca->cpu[vcpu->vcpu_id].sigp_ctrl);
		union esca_sigp_ctrl old = *sigp_ctrl;

		expect = old.value;
		rc = cmpxchg(&sigp_ctrl->value, old.value, 0);
	} else {
		struct bsca_block *sca = vcpu->kvm->arch.sca;
		union bsca_sigp_ctrl *sigp_ctrl =
			&(sca->cpu[vcpu->vcpu_id].sigp_ctrl);
		union bsca_sigp_ctrl old = *sigp_ctrl;

		expect = old.value;
		rc = cmpxchg(&sigp_ctrl->value, old.value, 0);
	}
131
	read_unlock(&vcpu->kvm->arch.sca_lock);
132
	WARN_ON(rc != expect); /* cannot clear? */
133 134
}

135
int psw_extint_disabled(struct kvm_vcpu *vcpu)
136 137 138 139
{
	return !(vcpu->arch.sie_block->gpsw.mask & PSW_MASK_EXT);
}

140 141 142 143 144
static int psw_ioint_disabled(struct kvm_vcpu *vcpu)
{
	return !(vcpu->arch.sie_block->gpsw.mask & PSW_MASK_IO);
}

145 146 147 148 149
static int psw_mchk_disabled(struct kvm_vcpu *vcpu)
{
	return !(vcpu->arch.sie_block->gpsw.mask & PSW_MASK_MCHECK);
}

150 151
static int psw_interrupts_disabled(struct kvm_vcpu *vcpu)
{
152 153 154
	return psw_extint_disabled(vcpu) &&
	       psw_ioint_disabled(vcpu) &&
	       psw_mchk_disabled(vcpu);
155 156
}

157 158 159 160 161
static int ckc_interrupts_enabled(struct kvm_vcpu *vcpu)
{
	if (psw_extint_disabled(vcpu) ||
	    !(vcpu->arch.sie_block->gcr[0] & 0x800ul))
		return 0;
162 163 164
	if (guestdbg_enabled(vcpu) && guestdbg_sstep_enabled(vcpu))
		/* No timer interrupts when single stepping */
		return 0;
165 166 167
	return 1;
}

168 169
static int ckc_irq_pending(struct kvm_vcpu *vcpu)
{
170
	if (vcpu->arch.sie_block->ckc >= kvm_s390_get_tod_clock_fast(vcpu->kvm))
171 172 173 174 175 176 177 178 179 180 181 182
		return 0;
	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)
{
183 184 185
	if (!cpu_timer_interrupts_enabled(vcpu))
		return 0;
	return kvm_s390_get_cpu_timer(vcpu) >> 63;
186 187
}

188
static inline int is_ioirq(unsigned long irq_type)
C
Cornelia Huck 已提交
189
{
190 191 192
	return ((irq_type >= IRQ_PEND_IO_ISC_0) &&
		(irq_type <= IRQ_PEND_IO_ISC_7));
}
C
Cornelia Huck 已提交
193

194 195
static uint64_t isc_to_isc_bits(int isc)
{
C
Cornelia Huck 已提交
196 197 198
	return (0x80 >> isc) << 24;
}

199
static inline u8 int_word_to_isc(u32 int_word)
200
{
201 202 203
	return (int_word & 0x38000000) >> 27;
}

204
static inline unsigned long pending_irqs(struct kvm_vcpu *vcpu)
205
{
206 207
	return vcpu->kvm->arch.float_int.pending_irqs |
	       vcpu->arch.local_int.pending_irqs;
208 209
}

210 211 212 213 214 215 216 217 218 219 220 221 222
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)
223
{
224 225
	unsigned long active_mask;

226
	active_mask = pending_irqs(vcpu);
227 228
	if (!active_mask)
		return 0;
229 230 231

	if (psw_extint_disabled(vcpu))
		active_mask &= ~IRQ_PEND_EXT_MASK;
232 233 234 235
	if (psw_ioint_disabled(vcpu))
		active_mask &= ~IRQ_PEND_IO_MASK;
	else
		active_mask = disable_iscs(vcpu, active_mask);
236 237 238 239 240 241 242 243
	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);
244 245
	if (!(vcpu->arch.sie_block->gcr[0] & 0x200ul))
		__clear_bit(IRQ_PEND_EXT_SERVICE, &active_mask);
246 247
	if (psw_mchk_disabled(vcpu))
		active_mask &= ~IRQ_PEND_MCHK_MASK;
248 249 250
	if (!(vcpu->arch.sie_block->gcr[14] &
	      vcpu->kvm->arch.float_int.mchk.cr14))
		__clear_bit(IRQ_PEND_MCHK_REP, &active_mask);
251

252 253 254 255 256 257
	/*
	 * 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);

258 259 260
	return active_mask;
}

261 262
static void __set_cpu_idle(struct kvm_vcpu *vcpu)
{
263
	atomic_or(CPUSTAT_WAIT, &vcpu->arch.sie_block->cpuflags);
264 265 266 267 268
	set_bit(vcpu->vcpu_id, vcpu->arch.local_int.float_int->idle_mask);
}

static void __unset_cpu_idle(struct kvm_vcpu *vcpu)
{
269
	atomic_andnot(CPUSTAT_WAIT, &vcpu->arch.sie_block->cpuflags);
270 271 272 273 274
	clear_bit(vcpu->vcpu_id, vcpu->arch.local_int.float_int->idle_mask);
}

static void __reset_intercept_indicators(struct kvm_vcpu *vcpu)
{
275 276
	atomic_andnot(CPUSTAT_IO_INT | CPUSTAT_EXT_INT | CPUSTAT_STOP_INT,
		    &vcpu->arch.sie_block->cpuflags);
277
	vcpu->arch.sie_block->lctl = 0x0000;
278 279 280 281 282 283 284
	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);
	}
285 286 287 288
}

static void __set_cpuflag(struct kvm_vcpu *vcpu, u32 flag)
{
289
	atomic_or(flag, &vcpu->arch.sie_block->cpuflags);
290 291
}

292 293
static void set_intercept_indicators_io(struct kvm_vcpu *vcpu)
{
294
	if (!(pending_irqs(vcpu) & IRQ_PEND_IO_MASK))
295 296 297 298 299 300 301
		return;
	else if (psw_ioint_disabled(vcpu))
		__set_cpuflag(vcpu, CPUSTAT_IO_INT);
	else
		vcpu->arch.sie_block->lctl |= LCTL_CR6;
}

302 303
static void set_intercept_indicators_ext(struct kvm_vcpu *vcpu)
{
304
	if (!(pending_irqs(vcpu) & IRQ_PEND_EXT_MASK))
305 306 307 308 309 310 311 312 313
		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)
{
314
	if (!(pending_irqs(vcpu) & IRQ_PEND_MCHK_MASK))
315 316 317 318 319 320 321
		return;
	if (psw_mchk_disabled(vcpu))
		vcpu->arch.sie_block->ictl |= ICTL_LPSW;
	else
		vcpu->arch.sie_block->lctl |= LCTL_CR14;
}

322 323 324 325 326 327
static void set_intercept_indicators_stop(struct kvm_vcpu *vcpu)
{
	if (kvm_s390_is_stop_irq_pending(vcpu))
		__set_cpuflag(vcpu, CPUSTAT_STOP_INT);
}

328 329
/* Set interception request for non-deliverable interrupts */
static void set_intercept_indicators(struct kvm_vcpu *vcpu)
330
{
331
	set_intercept_indicators_io(vcpu);
332 333
	set_intercept_indicators_ext(vcpu);
	set_intercept_indicators_mchk(vcpu);
334
	set_intercept_indicators_stop(vcpu);
335 336
}

337 338
static int __must_check __deliver_cpu_timer(struct kvm_vcpu *vcpu)
{
339
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
340 341 342 343 344 345 346
	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);
347
	rc |= put_guest_lc(vcpu, 0, (u16 *)__LC_EXT_CPU_ADDR);
348 349 350 351
	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));
352
	clear_bit(IRQ_PEND_EXT_CPU_TIMER, &li->pending_irqs);
353
	return rc ? -EFAULT : 0;
354 355 356 357
}

static int __must_check __deliver_ckc(struct kvm_vcpu *vcpu)
{
358
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
359 360 361 362 363 364 365
	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);
366
	rc |= put_guest_lc(vcpu, 0, (u16 *)__LC_EXT_CPU_ADDR);
367 368 369 370
	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));
371
	clear_bit(IRQ_PEND_EXT_CLOCK_COMP, &li->pending_irqs);
372
	return rc ? -EFAULT : 0;
373 374
}

375
static int __must_check __deliver_pfault_init(struct kvm_vcpu *vcpu)
376
{
377 378
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
	struct kvm_s390_ext_info ext;
379 380
	int rc;

381 382 383 384 385 386
	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);

387 388
	VCPU_EVENT(vcpu, 4, "deliver: pfault init token 0x%llx",
		   ext.ext_params2);
389 390
	trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id,
					 KVM_S390_INT_PFAULT_INIT,
391
					 0, ext.ext_params2);
392 393 394 395 396 397 398

	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));
399
	rc |= put_guest_lc(vcpu, ext.ext_params2, (u64 *) __LC_EXT_PARAMS2);
400
	return rc ? -EFAULT : 0;
401 402
}

403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431
static int __write_machine_check(struct kvm_vcpu *vcpu,
				 struct kvm_s390_mchk_info *mchk)
{
	unsigned long ext_sa_addr;
	int rc;

	/* Extended save area */
	rc = read_guest_lc(vcpu, __LC_VX_SAVE_AREA_ADDR, &ext_sa_addr,
			    sizeof(unsigned long));
	rc |= kvm_s390_vcpu_store_adtl_status(vcpu, ext_sa_addr);

	/* General interruption information */
	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));
	rc |= put_guest_lc(vcpu, mchk->mcic, (u64 __user *) __LC_MCCK_CODE);

	/* Register-save areas */
	rc |= kvm_s390_vcpu_store_status(vcpu, KVM_S390_STORE_STATUS_PREFIXED);

	/* Extended interruption information */
	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));
	return rc ? -EFAULT : 0;
}

432
static int __must_check __deliver_machine_check(struct kvm_vcpu *vcpu)
433
{
434
	struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int;
435
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
436 437 438
	struct kvm_s390_mchk_info mchk = {};
	int deliver = 0;
	int rc = 0;
439

440
	spin_lock(&fi->lock);
441
	spin_lock(&li->lock);
442 443 444 445 446 447 448 449 450 451 452 453 454 455
	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;
	}
456
	/*
457 458 459 460
	 * 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.
461
	 */
462 463 464 465 466 467
	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;
	}
468
	spin_unlock(&li->lock);
469
	spin_unlock(&fi->lock);
470

471
	if (deliver) {
472
		VCPU_EVENT(vcpu, 3, "deliver: machine check mcic 0x%llx",
473 474 475 476
			   mchk.mcic);
		trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id,
						 KVM_S390_MCHK,
						 mchk.cr14, mchk.mcic);
477
		rc = __write_machine_check(vcpu, &mchk);
478
	}
479
	return rc;
480 481 482 483
}

static int __must_check __deliver_restart(struct kvm_vcpu *vcpu)
{
484
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
485 486
	int rc;

487
	VCPU_EVENT(vcpu, 3, "%s", "deliver: cpu restart");
488 489 490 491
	vcpu->stat.deliver_restart_signal++;
	trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_RESTART, 0, 0);

	rc  = write_guest_lc(vcpu,
492
			     offsetof(struct lowcore, restart_old_psw),
493
			     &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
494
	rc |= read_guest_lc(vcpu, offsetof(struct lowcore, restart_psw),
495
			    &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
496
	clear_bit(IRQ_PEND_RESTART, &li->pending_irqs);
497
	return rc ? -EFAULT : 0;
498 499
}

500
static int __must_check __deliver_set_prefix(struct kvm_vcpu *vcpu)
501
{
502 503 504 505 506 507 508 509
	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);
510 511 512 513

	vcpu->stat.deliver_prefix_signal++;
	trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id,
					 KVM_S390_SIGP_SET_PREFIX,
514
					 prefix.address, 0);
515

516
	kvm_s390_set_prefix(vcpu, prefix.address);
517 518 519
	return 0;
}

520
static int __must_check __deliver_emergency_signal(struct kvm_vcpu *vcpu)
521
{
522
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
523
	int rc;
524 525 526 527 528 529 530 531
	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);
532

533
	VCPU_EVENT(vcpu, 4, "%s", "deliver: sigp emerg");
534
	vcpu->stat.deliver_emergency_signal++;
535 536
	trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_INT_EMERGENCY,
					 cpu_addr, 0);
537 538 539

	rc  = put_guest_lc(vcpu, EXT_IRQ_EMERGENCY_SIG,
			   (u16 *)__LC_EXT_INT_CODE);
540
	rc |= put_guest_lc(vcpu, cpu_addr, (u16 *)__LC_EXT_CPU_ADDR);
541 542 543 544
	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));
545
	return rc ? -EFAULT : 0;
546 547
}

548
static int __must_check __deliver_external_call(struct kvm_vcpu *vcpu)
549
{
550 551
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
	struct kvm_s390_extcall_info extcall;
552 553
	int rc;

554 555 556 557 558 559
	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);

560
	VCPU_EVENT(vcpu, 4, "%s", "deliver: sigp ext call");
561 562 563
	vcpu->stat.deliver_external_call++;
	trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id,
					 KVM_S390_INT_EXTERNAL_CALL,
564
					 extcall.code, 0);
565 566 567

	rc  = put_guest_lc(vcpu, EXT_IRQ_EXTERNAL_CALL,
			   (u16 *)__LC_EXT_INT_CODE);
568
	rc |= put_guest_lc(vcpu, extcall.code, (u16 *)__LC_EXT_CPU_ADDR);
569 570 571 572
	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));
573
	return rc ? -EFAULT : 0;
574 575
}

576
static int __must_check __deliver_prog(struct kvm_vcpu *vcpu)
577
{
578 579
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
	struct kvm_s390_pgm_info pgm_info;
580
	int rc = 0, nullifying = false;
581
	u16 ilen;
582

583 584 585 586 587 588
	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);

589
	ilen = pgm_info.flags & KVM_S390_PGM_FLAGS_ILC_MASK;
590 591
	VCPU_EVENT(vcpu, 3, "deliver: program irq code 0x%x, ilen:%d",
		   pgm_info.code, ilen);
592 593
	vcpu->stat.deliver_program_int++;
	trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_PROGRAM_INT,
594
					 pgm_info.code, 0);
595

596
	switch (pgm_info.code & ~PGM_PER) {
597 598 599 600 601 602 603 604 605
	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:
606 607
		nullifying = true;
		/* fall through */
608
	case PGM_SPACE_SWITCH:
609
		rc = put_guest_lc(vcpu, pgm_info.trans_exc_code,
610 611 612 613 614 615 616 617
				  (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:
618
		rc = put_guest_lc(vcpu, pgm_info.exc_access_id,
619
				  (u8 *)__LC_EXC_ACCESS_ID);
620
		nullifying = true;
621 622 623 624 625 626 627
		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:
628
		rc = put_guest_lc(vcpu, pgm_info.trans_exc_code,
629
				  (u64 *)__LC_TRANS_EXC_CODE);
630
		rc |= put_guest_lc(vcpu, pgm_info.exc_access_id,
631
				   (u8 *)__LC_EXC_ACCESS_ID);
632
		rc |= put_guest_lc(vcpu, pgm_info.op_access_id,
633
				   (u8 *)__LC_OP_ACCESS_ID);
634
		nullifying = true;
635 636
		break;
	case PGM_MONITOR:
637
		rc = put_guest_lc(vcpu, pgm_info.mon_class_nr,
638
				  (u16 *)__LC_MON_CLASS_NR);
639
		rc |= put_guest_lc(vcpu, pgm_info.mon_code,
640 641
				   (u64 *)__LC_MON_CODE);
		break;
E
Eric Farman 已提交
642
	case PGM_VECTOR_PROCESSING:
643
	case PGM_DATA:
644
		rc = put_guest_lc(vcpu, pgm_info.data_exc_code,
645 646 647
				  (u32 *)__LC_DATA_EXC_CODE);
		break;
	case PGM_PROTECTION:
648
		rc = put_guest_lc(vcpu, pgm_info.trans_exc_code,
649
				  (u64 *)__LC_TRANS_EXC_CODE);
650
		rc |= put_guest_lc(vcpu, pgm_info.exc_access_id,
651 652
				   (u8 *)__LC_EXC_ACCESS_ID);
		break;
653 654 655 656 657 658 659 660 661
	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;
662 663
	}

664 665
	if (pgm_info.code & PGM_PER) {
		rc |= put_guest_lc(vcpu, pgm_info.per_code,
666
				   (u8 *) __LC_PER_CODE);
667
		rc |= put_guest_lc(vcpu, pgm_info.per_atmid,
668
				   (u8 *)__LC_PER_ATMID);
669
		rc |= put_guest_lc(vcpu, pgm_info.per_address,
670
				   (u64 *) __LC_PER_ADDRESS);
671
		rc |= put_guest_lc(vcpu, pgm_info.per_access_id,
672 673 674
				   (u8 *) __LC_PER_ACCESS_ID);
	}

675
	if (nullifying && !(pgm_info.flags & KVM_S390_PGM_FLAGS_NO_REWIND))
676
		kvm_s390_rewind_psw(vcpu, ilen);
677

678 679
	/* bit 1+2 of the target are the ilc, so we can directly use ilen */
	rc |= put_guest_lc(vcpu, ilen, (u16 *) __LC_PGM_ILC);
680 681
	rc |= put_guest_lc(vcpu, vcpu->arch.sie_block->gbea,
				 (u64 *) __LC_LAST_BREAK);
682
	rc |= put_guest_lc(vcpu, pgm_info.code,
683 684 685 686 687
			   (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));
688
	return rc ? -EFAULT : 0;
689 690
}

691
static int __must_check __deliver_service(struct kvm_vcpu *vcpu)
692
{
693 694 695 696 697 698 699 700 701 702 703 704 705
	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);
706

707
	VCPU_EVENT(vcpu, 4, "deliver: sclp parameter 0x%x",
708
		   ext.ext_params);
709
	vcpu->stat.deliver_service_signal++;
710 711
	trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_INT_SERVICE,
					 ext.ext_params, 0);
712 713

	rc  = put_guest_lc(vcpu, EXT_IRQ_SERVICE_SIG, (u16 *)__LC_EXT_INT_CODE);
714
	rc |= put_guest_lc(vcpu, 0, (u16 *)__LC_EXT_CPU_ADDR);
715 716 717 718
	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));
719
	rc |= put_guest_lc(vcpu, ext.ext_params,
720
			   (u32 *)__LC_EXT_PARAMS);
721

722
	return rc ? -EFAULT : 0;
723 724
}

725
static int __must_check __deliver_pfault_done(struct kvm_vcpu *vcpu)
726
{
727 728 729
	struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int;
	struct kvm_s390_interrupt_info *inti;
	int rc = 0;
730

731 732 733 734 735 736 737 738 739 740 741
	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);
742

743
	if (inti) {
744 745 746 747 748 749
		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);

750 751 752 753 754 755 756 757 758 759 760 761 762 763
		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);
	}
764
	return rc ? -EFAULT : 0;
765 766
}

767
static int __must_check __deliver_virtio(struct kvm_vcpu *vcpu)
768
{
769 770 771
	struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int;
	struct kvm_s390_interrupt_info *inti;
	int rc = 0;
772

773 774 775 776 777 778
	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,
779
			   "deliver: virtio parm: 0x%x,parm64: 0x%llx",
780 781 782 783 784 785 786 787 788 789 790 791
			   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);
792

793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809
	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);
	}
810
	return rc ? -EFAULT : 0;
811 812 813
}

static int __must_check __deliver_io(struct kvm_vcpu *vcpu,
814
				     unsigned long irq_type)
815
{
816 817 818 819
	struct list_head *isc_list;
	struct kvm_s390_float_interrupt *fi;
	struct kvm_s390_interrupt_info *inti = NULL;
	int rc = 0;
820

821
	fi = &vcpu->kvm->arch.float_int;
822

823 824 825 826 827 828
	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) {
829 830 831 832 833 834 835 836
		if (inti->type & KVM_S390_INT_IO_AI_MASK)
			VCPU_EVENT(vcpu, 4, "%s", "deliver: I/O (AI)");
		else
			VCPU_EVENT(vcpu, 4, "deliver: I/O %x ss %x schid %04x",
			inti->io.subchannel_id >> 8,
			inti->io.subchannel_id >> 1 & 0x3,
			inti->io.subchannel_nr);

837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867
		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);
	}
868

869
	return rc ? -EFAULT : 0;
870 871 872 873 874 875
}

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

static const deliver_irq_t deliver_irq_funcs[] = {
	[IRQ_PEND_MCHK_EX]        = __deliver_machine_check,
876
	[IRQ_PEND_MCHK_REP]       = __deliver_machine_check,
877 878 879 880 881 882 883 884
	[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,
885 886 887
	[IRQ_PEND_EXT_SERVICE]    = __deliver_service,
	[IRQ_PEND_PFAULT_DONE]    = __deliver_pfault_done,
	[IRQ_PEND_VIRTIO]         = __deliver_virtio,
888 889
};

890 891
/* Check whether an external call is pending (deliverable or not) */
int kvm_s390_ext_call_pending(struct kvm_vcpu *vcpu)
892
{
893
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
894

895
	if (!sclp.has_sigpif)
896
		return test_bit(IRQ_PEND_EXT_EXTERNAL, &li->pending_irqs);
897

898
	return sca_ext_call_pending(vcpu, NULL);
899 900
}

901
int kvm_s390_vcpu_has_irq(struct kvm_vcpu *vcpu, int exclude_stop)
902
{
903 904
	if (deliverable_irqs(vcpu))
		return 1;
905

906 907
	if (kvm_cpu_has_pending_timer(vcpu))
		return 1;
908

909
	/* external call pending and deliverable */
910
	if (kvm_s390_ext_call_pending(vcpu) &&
911 912
	    !psw_extint_disabled(vcpu) &&
	    (vcpu->arch.sie_block->gcr[0] & 0x2000ul))
913
		return 1;
914

915 916 917
	if (!exclude_stop && kvm_s390_is_stop_irq_pending(vcpu))
		return 1;
	return 0;
918 919
}

920 921
int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
{
922
	return ckc_irq_pending(vcpu) || cpu_timer_irq_pending(vcpu);
923 924
}

925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950
static u64 __calculate_sltime(struct kvm_vcpu *vcpu)
{
	u64 now, cputm, sltime = 0;

	if (ckc_interrupts_enabled(vcpu)) {
		now = kvm_s390_get_tod_clock_fast(vcpu->kvm);
		sltime = tod_to_ns(vcpu->arch.sie_block->ckc - now);
		/* already expired or overflow? */
		if (!sltime || vcpu->arch.sie_block->ckc <= now)
			return 0;
		if (cpu_timer_interrupts_enabled(vcpu)) {
			cputm = kvm_s390_get_cpu_timer(vcpu);
			/* already expired? */
			if (cputm >> 63)
				return 0;
			return min(sltime, tod_to_ns(cputm));
		}
	} else if (cpu_timer_interrupts_enabled(vcpu)) {
		sltime = kvm_s390_get_cpu_timer(vcpu);
		/* already expired? */
		if (sltime >> 63)
			return 0;
	}
	return sltime;
}

951 952
int kvm_s390_handle_wait(struct kvm_vcpu *vcpu)
{
953
	u64 sltime;
954 955 956

	vcpu->stat.exit_wait_state++;

957
	/* fast path */
958
	if (kvm_arch_vcpu_runnable(vcpu))
959
		return 0;
960

961 962
	if (psw_interrupts_disabled(vcpu)) {
		VCPU_EVENT(vcpu, 3, "%s", "disabled wait");
963
		return -EOPNOTSUPP; /* disabled wait */
964 965
	}

966 967
	if (!ckc_interrupts_enabled(vcpu) &&
	    !cpu_timer_interrupts_enabled(vcpu)) {
968
		VCPU_EVENT(vcpu, 3, "%s", "enabled wait w/o timer");
969
		__set_cpu_idle(vcpu);
970 971 972
		goto no_timer;
	}

973 974
	sltime = __calculate_sltime(vcpu);
	if (!sltime)
975 976 977
		return 0;

	__set_cpu_idle(vcpu);
978
	hrtimer_start(&vcpu->arch.ckc_timer, ktime_set (0, sltime) , HRTIMER_MODE_REL);
979
	VCPU_EVENT(vcpu, 4, "enabled wait: %llu ns", sltime);
980
no_timer:
981
	srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
982
	kvm_vcpu_block(vcpu);
983
	__unset_cpu_idle(vcpu);
984 985
	vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);

986
	hrtimer_cancel(&vcpu->arch.ckc_timer);
987 988 989
	return 0;
}

990 991
void kvm_s390_vcpu_wakeup(struct kvm_vcpu *vcpu)
{
992 993 994 995 996
	/*
	 * We cannot move this into the if, as the CPU might be already
	 * in kvm_vcpu_block without having the waitqueue set (polling)
	 */
	vcpu->valid_wakeup = true;
997
	if (swait_active(&vcpu->wq)) {
998 999 1000 1001 1002
		/*
		 * The vcpu gave up the cpu voluntarily, mark it as a good
		 * yield-candidate.
		 */
		vcpu->preempted = true;
1003
		swake_up(&vcpu->wq);
1004
		vcpu->stat.halt_wakeup++;
1005
	}
1006 1007 1008 1009 1010
	/*
	 * The VCPU might not be sleeping but is executing the VSIE. Let's
	 * kick it, so it leaves the SIE to process the request.
	 */
	kvm_s390_vsie_kick(vcpu);
1011 1012
}

1013 1014 1015
enum hrtimer_restart kvm_s390_idle_wakeup(struct hrtimer *timer)
{
	struct kvm_vcpu *vcpu;
1016
	u64 sltime;
1017 1018

	vcpu = container_of(timer, struct kvm_vcpu, arch.ckc_timer);
1019
	sltime = __calculate_sltime(vcpu);
1020

1021 1022 1023 1024
	/*
	 * 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.
	 */
1025
	if (sltime && hrtimer_forward_now(timer, ns_to_ktime(sltime)))
1026 1027
		return HRTIMER_RESTART;
	kvm_s390_vcpu_wakeup(vcpu);
1028 1029
	return HRTIMER_NORESTART;
}
1030

1031 1032 1033 1034
void kvm_s390_clear_local_irqs(struct kvm_vcpu *vcpu)
{
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;

1035
	spin_lock(&li->lock);
1036 1037 1038
	li->pending_irqs = 0;
	bitmap_zero(li->sigp_emerg_pending, KVM_MAX_VCPUS);
	memset(&li->irq, 0, sizeof(li->irq));
1039
	spin_unlock(&li->lock);
1040

1041
	sca_clear_ext_call(vcpu);
1042 1043
}

1044
int __must_check kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu)
1045
{
1046
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
1047
	deliver_irq_t func;
1048
	int rc = 0;
1049
	unsigned long irq_type;
1050
	unsigned long irqs;
1051 1052 1053

	__reset_intercept_indicators(vcpu);

1054 1055
	/* pending ckc conditions might have been invalidated */
	clear_bit(IRQ_PEND_EXT_CLOCK_COMP, &li->pending_irqs);
1056
	if (ckc_irq_pending(vcpu))
1057 1058
		set_bit(IRQ_PEND_EXT_CLOCK_COMP, &li->pending_irqs);

1059 1060 1061 1062 1063
	/* 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);

1064
	while ((irqs = deliverable_irqs(vcpu)) && !rc) {
1065
		/* bits are in the order of interrupt priority */
1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076
		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);
1077
		}
1078
	}
1079

1080
	set_intercept_indicators(vcpu);
1081 1082

	return rc;
1083 1084
}

1085
static int __inject_prog(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
1086 1087 1088
{
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;

1089 1090 1091 1092
	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);

1093 1094 1095 1096 1097 1098 1099
	if (!(irq->u.pgm.flags & KVM_S390_PGM_FLAGS_ILC_VALID)) {
		/* auto detection if no valid ILC was given */
		irq->u.pgm.flags &= ~KVM_S390_PGM_FLAGS_ILC_MASK;
		irq->u.pgm.flags |= kvm_s390_get_ilen(vcpu);
		irq->u.pgm.flags |= KVM_S390_PGM_FLAGS_ILC_VALID;
	}

1100 1101
	if (irq->u.pgm.code == PGM_PER) {
		li->irq.pgm.code |= PGM_PER;
1102
		li->irq.pgm.flags = irq->u.pgm.flags;
1103 1104 1105 1106 1107 1108 1109 1110
		/* only modify PER related information */
		li->irq.pgm.per_address = irq->u.pgm.per_address;
		li->irq.pgm.per_code = irq->u.pgm.per_code;
		li->irq.pgm.per_atmid = irq->u.pgm.per_atmid;
		li->irq.pgm.per_access_id = irq->u.pgm.per_access_id;
	} else if (!(irq->u.pgm.code & PGM_PER)) {
		li->irq.pgm.code = (li->irq.pgm.code & PGM_PER) |
				   irq->u.pgm.code;
1111
		li->irq.pgm.flags = irq->u.pgm.flags;
1112 1113 1114 1115 1116 1117 1118 1119 1120 1121
		/* only modify non-PER information */
		li->irq.pgm.trans_exc_code = irq->u.pgm.trans_exc_code;
		li->irq.pgm.mon_code = irq->u.pgm.mon_code;
		li->irq.pgm.data_exc_code = irq->u.pgm.data_exc_code;
		li->irq.pgm.mon_class_nr = irq->u.pgm.mon_class_nr;
		li->irq.pgm.exc_access_id = irq->u.pgm.exc_access_id;
		li->irq.pgm.op_access_id = irq->u.pgm.op_access_id;
	} else {
		li->irq.pgm = irq->u.pgm;
	}
1122
	set_bit(IRQ_PEND_PROG, &li->pending_irqs);
1123 1124 1125
	return 0;
}

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

1130 1131
	VCPU_EVENT(vcpu, 4, "inject: pfault init parameter block at 0x%llx",
		   irq->u.ext.ext_params2);
1132 1133
	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_INT_PFAULT_INIT,
				   irq->u.ext.ext_params,
1134
				   irq->u.ext.ext_params2);
1135 1136 1137

	li->irq.ext = irq->u.ext;
	set_bit(IRQ_PEND_PFAULT_INIT, &li->pending_irqs);
1138
	atomic_or(CPUSTAT_EXT_INT, li->cpuflags);
1139 1140 1141
	return 0;
}

1142
static int __inject_extcall(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
1143 1144
{
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
1145
	struct kvm_s390_extcall_info *extcall = &li->irq.extcall;
1146
	uint16_t src_id = irq->u.extcall.code;
1147

1148
	VCPU_EVENT(vcpu, 4, "inject: external call source-cpu:%u",
1149
		   src_id);
1150
	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_INT_EXTERNAL_CALL,
1151
				   src_id, 0);
1152 1153

	/* sending vcpu invalid */
1154
	if (kvm_get_vcpu_by_id(vcpu->kvm, src_id) == NULL)
1155 1156
		return -EINVAL;

1157
	if (sclp.has_sigpif)
1158
		return sca_inject_ext_call(vcpu, src_id);
1159

1160
	if (test_and_set_bit(IRQ_PEND_EXT_EXTERNAL, &li->pending_irqs))
1161
		return -EBUSY;
1162
	*extcall = irq->u.extcall;
1163
	atomic_or(CPUSTAT_EXT_INT, li->cpuflags);
1164 1165 1166
	return 0;
}

1167
static int __inject_set_prefix(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
1168 1169
{
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
1170
	struct kvm_s390_prefix_info *prefix = &li->irq.prefix;
1171

1172
	VCPU_EVENT(vcpu, 3, "inject: set prefix to %x",
1173
		   irq->u.prefix.address);
1174
	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_SIGP_SET_PREFIX,
1175
				   irq->u.prefix.address, 0);
1176

1177 1178 1179
	if (!is_vcpu_stopped(vcpu))
		return -EBUSY;

1180 1181
	*prefix = irq->u.prefix;
	set_bit(IRQ_PEND_SET_PREFIX, &li->pending_irqs);
1182 1183 1184
	return 0;
}

1185
#define KVM_S390_STOP_SUPP_FLAGS (KVM_S390_STOP_FLAG_STORE_STATUS)
1186
static int __inject_sigp_stop(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
1187 1188
{
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
1189
	struct kvm_s390_stop_info *stop = &li->irq.stop;
1190
	int rc = 0;
1191

1192
	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_SIGP_STOP, 0, 0);
1193

1194 1195 1196
	if (irq->u.stop.flags & ~KVM_S390_STOP_SUPP_FLAGS)
		return -EINVAL;

1197 1198 1199 1200 1201 1202 1203 1204 1205
	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;
1206
	stop->flags = irq->u.stop.flags;
1207
	__set_cpuflag(vcpu, CPUSTAT_STOP_INT);
1208 1209 1210 1211
	return 0;
}

static int __inject_sigp_restart(struct kvm_vcpu *vcpu,
1212
				 struct kvm_s390_irq *irq)
1213 1214 1215
{
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;

1216
	VCPU_EVENT(vcpu, 3, "%s", "inject: restart int");
1217
	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_RESTART, 0, 0);
1218 1219

	set_bit(IRQ_PEND_RESTART, &li->pending_irqs);
1220 1221 1222 1223
	return 0;
}

static int __inject_sigp_emergency(struct kvm_vcpu *vcpu,
1224
				   struct kvm_s390_irq *irq)
1225 1226 1227
{
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;

1228
	VCPU_EVENT(vcpu, 4, "inject: emergency from cpu %u",
1229 1230
		   irq->u.emerg.code);
	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_INT_EMERGENCY,
1231
				   irq->u.emerg.code, 0);
1232

1233 1234 1235 1236
	/* sending vcpu invalid */
	if (kvm_get_vcpu_by_id(vcpu->kvm, irq->u.emerg.code) == NULL)
		return -EINVAL;

1237
	set_bit(irq->u.emerg.code, li->sigp_emerg_pending);
1238
	set_bit(IRQ_PEND_EXT_EMERGENCY, &li->pending_irqs);
1239
	atomic_or(CPUSTAT_EXT_INT, li->cpuflags);
1240 1241 1242
	return 0;
}

1243
static int __inject_mchk(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
1244 1245
{
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
1246
	struct kvm_s390_mchk_info *mchk = &li->irq.mchk;
1247

1248
	VCPU_EVENT(vcpu, 3, "inject: machine check mcic 0x%llx",
1249
		   irq->u.mchk.mcic);
1250
	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_MCHK, 0,
1251
				   irq->u.mchk.mcic);
1252 1253

	/*
1254 1255 1256 1257 1258 1259
	 * 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
1260
	 */
1261
	mchk->cr14 |= irq->u.mchk.cr14;
1262
	mchk->mcic |= irq->u.mchk.mcic;
1263 1264 1265 1266
	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));
1267 1268 1269 1270
	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);
1271 1272 1273
	return 0;
}

1274
static int __inject_ckc(struct kvm_vcpu *vcpu)
1275 1276 1277
{
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;

1278
	VCPU_EVENT(vcpu, 3, "%s", "inject: clock comparator external");
1279
	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_INT_CLOCK_COMP,
1280
				   0, 0);
1281 1282

	set_bit(IRQ_PEND_EXT_CLOCK_COMP, &li->pending_irqs);
1283
	atomic_or(CPUSTAT_EXT_INT, li->cpuflags);
1284 1285 1286
	return 0;
}

1287
static int __inject_cpu_timer(struct kvm_vcpu *vcpu)
1288 1289 1290
{
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;

1291
	VCPU_EVENT(vcpu, 3, "%s", "inject: cpu timer external");
1292
	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_INT_CPU_TIMER,
1293
				   0, 0);
1294 1295

	set_bit(IRQ_PEND_EXT_CPU_TIMER, &li->pending_irqs);
1296
	atomic_or(CPUSTAT_EXT_INT, li->cpuflags);
1297 1298 1299
	return 0;
}

1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324
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;
}
1325

1326 1327 1328 1329
/*
 * 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).
 */
1330
struct kvm_s390_interrupt_info *kvm_s390_get_io_int(struct kvm *kvm,
1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 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 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421
						    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)
1422 1423
{
	struct kvm_s390_float_interrupt *fi;
1424 1425
	struct list_head *list;
	int isc;
1426 1427 1428

	fi = &kvm->arch.float_int;
	spin_lock(&fi->lock);
1429 1430 1431
	if (fi->counters[FIRQ_CNTR_IO] >= KVM_S390_MAX_FLOAT_IRQS) {
		spin_unlock(&fi->lock);
		return -EBUSY;
J
Jens Freimann 已提交
1432
	}
1433 1434
	fi->counters[FIRQ_CNTR_IO] += 1;

1435 1436 1437 1438 1439 1440 1441
	if (inti->type & KVM_S390_INT_IO_AI_MASK)
		VM_EVENT(kvm, 4, "%s", "inject: I/O (AI)");
	else
		VM_EVENT(kvm, 4, "inject: I/O %x ss %x schid %04x",
			inti->io.subchannel_id >> 8,
			inti->io.subchannel_id >> 1 & 0x3,
			inti->io.subchannel_nr);
1442 1443 1444 1445
	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);
1446
	spin_unlock(&fi->lock);
1447
	return 0;
1448
}
1449

1450 1451 1452 1453
/*
 * Find a destination VCPU for a floating irq and kick it.
 */
static void __floating_irq_kick(struct kvm *kvm, u64 type)
1454
{
1455
	struct kvm_s390_float_interrupt *fi = &kvm->arch.float_int;
1456
	struct kvm_s390_local_interrupt *li;
1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481
	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:
1482
		atomic_or(CPUSTAT_STOP_INT, li->cpuflags);
1483 1484
		break;
	case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
1485
		atomic_or(CPUSTAT_IO_INT, li->cpuflags);
1486 1487
		break;
	default:
1488
		atomic_or(CPUSTAT_EXT_INT, li->cpuflags);
1489 1490 1491 1492 1493 1494 1495 1496
		break;
	}
	spin_unlock(&li->lock);
	kvm_s390_vcpu_wakeup(dst_vcpu);
}

static int __inject_vm(struct kvm *kvm, struct kvm_s390_interrupt_info *inti)
{
1497 1498
	u64 type = READ_ONCE(inti->type);
	int rc;
1499

1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516
	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
1517
		rc = -EINVAL;
1518
	}
1519 1520 1521
	if (rc)
		return rc;

1522
	__floating_irq_kick(kvm, type);
1523
	return 0;
1524 1525 1526 1527 1528 1529
}

int kvm_s390_inject_vm(struct kvm *kvm,
		       struct kvm_s390_interrupt *s390int)
{
	struct kvm_s390_interrupt_info *inti;
1530
	int rc;
1531

1532 1533 1534 1535
	inti = kzalloc(sizeof(*inti), GFP_KERNEL);
	if (!inti)
		return -ENOMEM;

1536 1537
	inti->type = s390int->type;
	switch (inti->type) {
1538
	case KVM_S390_INT_VIRTIO:
1539
		VM_EVENT(kvm, 5, "inject: virtio parm:%x,parm64:%llx",
1540 1541 1542 1543 1544
			 s390int->parm, s390int->parm64);
		inti->ext.ext_params = s390int->parm;
		inti->ext.ext_params2 = s390int->parm64;
		break;
	case KVM_S390_INT_SERVICE:
1545
		VM_EVENT(kvm, 4, "inject: sclp parm:%x", s390int->parm);
1546 1547
		inti->ext.ext_params = s390int->parm;
		break;
1548 1549 1550
	case KVM_S390_INT_PFAULT_DONE:
		inti->ext.ext_params2 = s390int->parm64;
		break;
1551
	case KVM_S390_MCHK:
1552
		VM_EVENT(kvm, 3, "inject: machine check mcic 0x%llx",
1553 1554 1555 1556
			 s390int->parm64);
		inti->mchk.cr14 = s390int->parm; /* upper bits are not used */
		inti->mchk.mcic = s390int->parm64;
		break;
1557 1558 1559 1560 1561 1562
	case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
		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;
1563 1564 1565 1566
	default:
		kfree(inti);
		return -EINVAL;
	}
1567 1568
	trace_kvm_s390_inject_vm(s390int->type, s390int->parm, s390int->parm64,
				 2);
1569

1570 1571 1572 1573
	rc = __inject_vm(kvm, inti);
	if (rc)
		kfree(inti);
	return rc;
1574 1575
}

1576
int kvm_s390_reinject_io_int(struct kvm *kvm,
1577 1578
			      struct kvm_s390_interrupt_info *inti)
{
1579
	return __inject_vm(kvm, inti);
1580 1581
}

1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594
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;
1595 1596 1597
	case KVM_S390_SIGP_STOP:
		irq->u.stop.flags = s390int->parm;
		break;
1598
	case KVM_S390_INT_EXTERNAL_CALL:
1599
		if (s390int->parm & 0xffff0000)
1600 1601 1602 1603
			return -EINVAL;
		irq->u.extcall.code = s390int->parm;
		break;
	case KVM_S390_INT_EMERGENCY:
1604
		if (s390int->parm & 0xffff0000)
1605 1606 1607 1608 1609 1610 1611 1612 1613 1614
			return -EINVAL;
		irq->u.emerg.code = s390int->parm;
		break;
	case KVM_S390_MCHK:
		irq->u.mchk.mcic = s390int->parm64;
		break;
	}
	return 0;
}

1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631
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);
}

1632
static int do_inject_vcpu(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
1633
{
1634
	int rc;
1635

1636
	switch (irq->type) {
1637
	case KVM_S390_PROGRAM_INT:
1638
		rc = __inject_prog(vcpu, irq);
1639
		break;
1640
	case KVM_S390_SIGP_SET_PREFIX:
1641
		rc = __inject_set_prefix(vcpu, irq);
1642
		break;
1643
	case KVM_S390_SIGP_STOP:
1644
		rc = __inject_sigp_stop(vcpu, irq);
1645
		break;
1646
	case KVM_S390_RESTART:
1647
		rc = __inject_sigp_restart(vcpu, irq);
1648
		break;
1649
	case KVM_S390_INT_CLOCK_COMP:
1650
		rc = __inject_ckc(vcpu);
1651
		break;
1652
	case KVM_S390_INT_CPU_TIMER:
1653
		rc = __inject_cpu_timer(vcpu);
1654
		break;
1655
	case KVM_S390_INT_EXTERNAL_CALL:
1656
		rc = __inject_extcall(vcpu, irq);
1657
		break;
1658
	case KVM_S390_INT_EMERGENCY:
1659
		rc = __inject_sigp_emergency(vcpu, irq);
1660
		break;
1661
	case KVM_S390_MCHK:
1662
		rc = __inject_mchk(vcpu, irq);
1663
		break;
1664
	case KVM_S390_INT_PFAULT_INIT:
1665
		rc = __inject_pfault_init(vcpu, irq);
1666
		break;
1667 1668
	case KVM_S390_INT_VIRTIO:
	case KVM_S390_INT_SERVICE:
1669
	case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
1670
	default:
1671
		rc = -EINVAL;
1672
	}
1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683

	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);
1684
	spin_unlock(&li->lock);
1685 1686 1687
	if (!rc)
		kvm_s390_vcpu_wakeup(vcpu);
	return rc;
1688
}
1689

1690
static inline void clear_irq_list(struct list_head *_list)
1691
{
1692
	struct kvm_s390_interrupt_info *inti, *n;
1693

1694
	list_for_each_entry_safe(inti, n, _list, list) {
1695 1696 1697 1698 1699
		list_del(&inti->list);
		kfree(inti);
	}
}

1700 1701
static void inti_to_irq(struct kvm_s390_interrupt_info *inti,
		       struct kvm_s390_irq *irq)
1702
{
1703
	irq->type = inti->type;
1704
	switch (inti->type) {
1705 1706
	case KVM_S390_INT_PFAULT_INIT:
	case KVM_S390_INT_PFAULT_DONE:
1707
	case KVM_S390_INT_VIRTIO:
1708
		irq->u.ext = inti->ext;
1709 1710
		break;
	case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
1711
		irq->u.io = inti->io;
1712 1713 1714 1715
		break;
	}
}

1716 1717 1718 1719 1720 1721
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);
1722 1723 1724
	fi->pending_irqs = 0;
	memset(&fi->srv_signal, 0, sizeof(fi->srv_signal));
	memset(&fi->mchk, 0, sizeof(fi->mchk));
1725 1726 1727 1728 1729 1730 1731
	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);
};

1732
static int get_all_floating_irqs(struct kvm *kvm, u8 __user *usrbuf, u64 len)
1733 1734 1735
{
	struct kvm_s390_interrupt_info *inti;
	struct kvm_s390_float_interrupt *fi;
1736
	struct kvm_s390_irq *buf;
1737
	struct kvm_s390_irq *irq;
1738
	int max_irqs;
1739 1740
	int ret = 0;
	int n = 0;
1741
	int i;
1742

1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756
	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);

1757 1758
	fi = &kvm->arch.float_int;
	spin_lock(&fi->lock);
1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770
	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)) {
1771
		if (n == max_irqs) {
1772 1773
			/* signal userspace to try again */
			ret = -ENOMEM;
1774
			goto out;
1775
		}
1776 1777 1778
		irq = (struct kvm_s390_irq *) &buf[n];
		irq->type = KVM_S390_INT_SERVICE;
		irq->u.ext = fi->srv_signal;
1779 1780
		n++;
	}
1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793
	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:
1794
	spin_unlock(&fi->lock);
1795 1796 1797 1798 1799
	if (!ret && n > 0) {
		if (copy_to_user(usrbuf, buf, sizeof(struct kvm_s390_irq) * n))
			ret = -EFAULT;
	}
	vfree(buf);
1800 1801 1802 1803 1804 1805 1806 1807 1808 1809

	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:
1810
		r = get_all_floating_irqs(dev->kvm, (u8 __user *) attr->addr,
1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831
					  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) {
1832 1833
	case KVM_S390_INT_PFAULT_INIT:
	case KVM_S390_INT_PFAULT_DONE:
1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881
	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
1882 1883 1884 1885 1886
		r = __inject_vm(dev->kvm, inti);
		if (r) {
			kfree(inti);
			return r;
		}
1887 1888 1889 1890 1891 1892 1893
		len -= sizeof(struct kvm_s390_irq);
		attr->addr += sizeof(struct kvm_s390_irq);
	}

	return r;
}

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 1956 1957 1958 1959
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;
1960
	map->addr = gmap_translate(kvm->arch.gmap, addr);
1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 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 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
	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;
}

2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079
static int clear_io_irq(struct kvm *kvm, struct kvm_device_attr *attr)

{
	const u64 isc_mask = 0xffUL << 24; /* all iscs set */
	u32 schid;

	if (attr->flags)
		return -EINVAL;
	if (attr->attr != sizeof(schid))
		return -EINVAL;
	if (copy_from_user(&schid, (void __user *) attr->addr, sizeof(schid)))
		return -EFAULT;
	kfree(kvm_s390_get_io_int(kvm, isc_mask, schid));
	/*
	 * If userspace is conforming to the architecture, we can have at most
	 * one pending I/O interrupt per subchannel, so this is effectively a
	 * clear all.
	 */
	return 0;
}

2080 2081 2082
static int flic_set_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
{
	int r = 0;
2083 2084
	unsigned int i;
	struct kvm_vcpu *vcpu;
2085 2086 2087 2088 2089 2090

	switch (attr->group) {
	case KVM_DEV_FLIC_ENQUEUE:
		r = enqueue_floating_irq(dev, attr);
		break;
	case KVM_DEV_FLIC_CLEAR_IRQS:
2091
		kvm_s390_clear_float_irqs(dev->kvm);
2092
		break;
2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106
	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;
2107 2108 2109 2110 2111 2112
	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;
2113 2114 2115
	case KVM_DEV_FLIC_CLEAR_IO_IRQ:
		r = clear_io_irq(dev->kvm, attr);
		break;
2116 2117 2118 2119 2120 2121 2122
	default:
		r = -EINVAL;
	}

	return r;
}

2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133
static int flic_has_attr(struct kvm_device *dev,
			     struct kvm_device_attr *attr)
{
	switch (attr->group) {
	case KVM_DEV_FLIC_GET_ALL_IRQS:
	case KVM_DEV_FLIC_ENQUEUE:
	case KVM_DEV_FLIC_CLEAR_IRQS:
	case KVM_DEV_FLIC_APF_ENABLE:
	case KVM_DEV_FLIC_APF_DISABLE_WAIT:
	case KVM_DEV_FLIC_ADAPTER_REGISTER:
	case KVM_DEV_FLIC_ADAPTER_MODIFY:
2134
	case KVM_DEV_FLIC_CLEAR_IO_IRQ:
2135 2136 2137 2138 2139
		return 0;
	}
	return -ENXIO;
}

2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160
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,
2161
	.has_attr = flic_has_attr,
2162 2163 2164
	.create = flic_create,
	.destroy = flic_destroy,
};
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

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;
}

2257 2258
int kvm_set_routing_entry(struct kvm *kvm,
			  struct kvm_kernel_irq_routing_entry *e,
2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284
			  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;
}
2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369

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)
{
2370
	int scn;
2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409
	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);
		}
	}

2410
	if (sca_ext_call_pending(vcpu, &scn)) {
2411 2412 2413 2414
		if (n + sizeof(irq) > len)
			return -ENOBUFS;
		memset(&irq, 0, sizeof(irq));
		irq.type = KVM_S390_INT_EXTERNAL_CALL;
2415
		irq.u.extcall.code = scn;
2416 2417 2418 2419 2420 2421 2422
		if (copy_to_user(&buf[n], &irq, sizeof(irq)))
			return -EFAULT;
		n += sizeof(irq);
	}

	return n;
}