interrupt.c 37.3 KB
Newer Older
1
/*
2
 * handling kvm guest interrupts
3
 *
4
 * Copyright IBM Corp. 2008,2014
5 6 7 8 9 10 11 12
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License (version 2 only)
 * as published by the Free Software Foundation.
 *
 *    Author(s): Carsten Otte <cotte@de.ibm.com>
 */

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

25 26 27 28 29 30 31 32 33 34
#define IOINT_SCHID_MASK 0x0000ffff
#define IOINT_SSID_MASK 0x00030000
#define IOINT_CSSID_MASK 0x03fc0000
#define IOINT_AI_MASK 0x04000000

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

35
int psw_extint_disabled(struct kvm_vcpu *vcpu)
36 37 38 39
{
	return !(vcpu->arch.sie_block->gpsw.mask & PSW_MASK_EXT);
}

40 41 42 43 44
static int psw_ioint_disabled(struct kvm_vcpu *vcpu)
{
	return !(vcpu->arch.sie_block->gpsw.mask & PSW_MASK_IO);
}

45 46 47 48 49
static int psw_mchk_disabled(struct kvm_vcpu *vcpu)
{
	return !(vcpu->arch.sie_block->gpsw.mask & PSW_MASK_MCHECK);
}

50 51 52 53 54 55 56 57 58
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;
}

C
Cornelia Huck 已提交
59 60 61 62 63 64 65
static u64 int_word_to_isc_bits(u32 int_word)
{
	u8 isc = (int_word & 0x38000000) >> 27;

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

66
static int __interrupt_is_deliverable(struct kvm_vcpu *vcpu,
67
				      struct kvm_s390_interrupt_info *inti)
68 69
{
	switch (inti->type) {
70 71 72 73 74
	case KVM_S390_INT_EXTERNAL_CALL:
		if (psw_extint_disabled(vcpu))
			return 0;
		if (vcpu->arch.sie_block->gcr[0] & 0x2000ul)
			return 1;
75 76 77 78 79 80 81
	case KVM_S390_INT_EMERGENCY:
		if (psw_extint_disabled(vcpu))
			return 0;
		if (vcpu->arch.sie_block->gcr[0] & 0x4000ul)
			return 1;
		return 0;
	case KVM_S390_INT_SERVICE:
82 83
	case KVM_S390_INT_PFAULT_INIT:
	case KVM_S390_INT_PFAULT_DONE:
84 85 86 87 88 89 90 91 92 93 94
	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;
95 96 97 98 99 100
	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;
101 102 103
	case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
		if (psw_ioint_disabled(vcpu))
			return 0;
C
Cornelia Huck 已提交
104 105
		if (vcpu->arch.sie_block->gcr[6] &
		    int_word_to_isc_bits(inti->io.io_int_word))
106 107
			return 1;
		return 0;
108
	default:
109 110
		printk(KERN_WARNING "illegal interrupt type %llx\n",
		       inti->type);
111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133
		BUG();
	}
	return 0;
}

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)
{
	atomic_clear_mask(CPUSTAT_ECALL_PEND |
		CPUSTAT_IO_INT | CPUSTAT_EXT_INT | CPUSTAT_STOP_INT,
		&vcpu->arch.sie_block->cpuflags);
	vcpu->arch.sie_block->lctl = 0x0000;
134
	vcpu->arch.sie_block->ictl &= ~ICTL_LPSW;
135 136 137 138 139 140 141 142
}

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

static void __set_intercept_indicator(struct kvm_vcpu *vcpu,
143
				      struct kvm_s390_interrupt_info *inti)
144 145
{
	switch (inti->type) {
146
	case KVM_S390_INT_EXTERNAL_CALL:
147 148
	case KVM_S390_INT_EMERGENCY:
	case KVM_S390_INT_SERVICE:
149 150
	case KVM_S390_INT_PFAULT_INIT:
	case KVM_S390_INT_PFAULT_DONE:
151 152 153 154 155 156 157 158 159
	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;
	case KVM_S390_SIGP_STOP:
		__set_cpuflag(vcpu, CPUSTAT_STOP_INT);
		break;
160 161 162 163 164 165
	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;
166 167 168 169 170 171
	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;
172 173 174 175 176 177
	default:
		BUG();
	}
}

static void __do_deliver_interrupt(struct kvm_vcpu *vcpu,
178
				   struct kvm_s390_interrupt_info *inti)
179 180
{
	const unsigned short table[] = { 2, 4, 4, 6 };
181
	int rc = 0;
182 183 184 185 186

	switch (inti->type) {
	case KVM_S390_INT_EMERGENCY:
		VCPU_EVENT(vcpu, 4, "%s", "interrupt: sigp emerg");
		vcpu->stat.deliver_emergency_signal++;
187 188
		trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type,
						 inti->emerg.code, 0);
189
		rc  = put_guest(vcpu, 0x1201, (u16 __user *)__LC_EXT_INT_CODE);
190
		rc |= put_guest(vcpu, inti->emerg.code,
191
				(u16 __user *)__LC_EXT_CPU_ADDR);
192 193 194 195
		rc |= copy_to_guest(vcpu, __LC_EXT_OLD_PSW,
				    &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
		rc |= copy_from_guest(vcpu, &vcpu->arch.sie_block->gpsw,
				      __LC_EXT_NEW_PSW, sizeof(psw_t));
196
		break;
197 198 199
	case KVM_S390_INT_EXTERNAL_CALL:
		VCPU_EVENT(vcpu, 4, "%s", "interrupt: sigp ext call");
		vcpu->stat.deliver_external_call++;
200 201
		trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type,
						 inti->extcall.code, 0);
202
		rc  = put_guest(vcpu, 0x1202, (u16 __user *)__LC_EXT_INT_CODE);
203
		rc |= put_guest(vcpu, inti->extcall.code,
204
				(u16 __user *)__LC_EXT_CPU_ADDR);
205 206 207 208
		rc |= copy_to_guest(vcpu, __LC_EXT_OLD_PSW,
				    &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
		rc |= copy_from_guest(vcpu, &vcpu->arch.sie_block->gpsw,
				      __LC_EXT_NEW_PSW, sizeof(psw_t));
209
		break;
210 211 212 213
	case KVM_S390_INT_SERVICE:
		VCPU_EVENT(vcpu, 4, "interrupt: sclp parm:%x",
			   inti->ext.ext_params);
		vcpu->stat.deliver_service_signal++;
214 215
		trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type,
						 inti->ext.ext_params, 0);
216
		rc  = put_guest(vcpu, 0x2401, (u16 __user *)__LC_EXT_INT_CODE);
217 218 219 220
		rc |= copy_to_guest(vcpu, __LC_EXT_OLD_PSW,
				    &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
		rc |= copy_from_guest(vcpu, &vcpu->arch.sie_block->gpsw,
				      __LC_EXT_NEW_PSW, sizeof(psw_t));
221
		rc |= put_guest(vcpu, inti->ext.ext_params,
222
				(u32 __user *)__LC_EXT_PARAMS);
223
		break;
224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247
	case KVM_S390_INT_PFAULT_INIT:
		trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type, 0,
						 inti->ext.ext_params2);
		rc  = put_guest(vcpu, 0x2603, (u16 __user *) __LC_EXT_INT_CODE);
		rc |= put_guest(vcpu, 0x0600, (u16 __user *) __LC_EXT_CPU_ADDR);
		rc |= copy_to_guest(vcpu, __LC_EXT_OLD_PSW,
				    &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
		rc |= copy_from_guest(vcpu, &vcpu->arch.sie_block->gpsw,
				      __LC_EXT_NEW_PSW, sizeof(psw_t));
		rc |= put_guest(vcpu, inti->ext.ext_params2,
				(u64 __user *) __LC_EXT_PARAMS2);
		break;
	case KVM_S390_INT_PFAULT_DONE:
		trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type, 0,
						 inti->ext.ext_params2);
		rc  = put_guest(vcpu, 0x2603, (u16 __user *) __LC_EXT_INT_CODE);
		rc |= put_guest(vcpu, 0x0680, (u16 __user *) __LC_EXT_CPU_ADDR);
		rc |= copy_to_guest(vcpu, __LC_EXT_OLD_PSW,
				    &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
		rc |= copy_from_guest(vcpu, &vcpu->arch.sie_block->gpsw,
				      __LC_EXT_NEW_PSW, sizeof(psw_t));
		rc |= put_guest(vcpu, inti->ext.ext_params2,
				(u64 __user *) __LC_EXT_PARAMS2);
		break;
248
	case KVM_S390_INT_VIRTIO:
249
		VCPU_EVENT(vcpu, 4, "interrupt: virtio parm:%x,parm64:%llx",
250 251
			   inti->ext.ext_params, inti->ext.ext_params2);
		vcpu->stat.deliver_virtio_interrupt++;
252 253 254
		trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type,
						 inti->ext.ext_params,
						 inti->ext.ext_params2);
255 256
		rc  = put_guest(vcpu, 0x2603, (u16 __user *)__LC_EXT_INT_CODE);
		rc |= put_guest(vcpu, 0x0d00, (u16 __user *)__LC_EXT_CPU_ADDR);
257 258 259 260
		rc |= copy_to_guest(vcpu, __LC_EXT_OLD_PSW,
				    &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
		rc |= copy_from_guest(vcpu, &vcpu->arch.sie_block->gpsw,
				      __LC_EXT_NEW_PSW, sizeof(psw_t));
261
		rc |= put_guest(vcpu, inti->ext.ext_params,
262
				(u32 __user *)__LC_EXT_PARAMS);
263
		rc |= put_guest(vcpu, inti->ext.ext_params2,
264
				(u64 __user *)__LC_EXT_PARAMS2);
265 266 267 268
		break;
	case KVM_S390_SIGP_STOP:
		VCPU_EVENT(vcpu, 4, "%s", "interrupt: cpu stop");
		vcpu->stat.deliver_stop_signal++;
269 270
		trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type,
						 0, 0);
271 272 273 274 275 276 277
		__set_intercept_indicator(vcpu, inti);
		break;

	case KVM_S390_SIGP_SET_PREFIX:
		VCPU_EVENT(vcpu, 4, "interrupt: set prefix to %x",
			   inti->prefix.address);
		vcpu->stat.deliver_prefix_signal++;
278 279
		trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type,
						 inti->prefix.address, 0);
280
		kvm_s390_set_prefix(vcpu, inti->prefix.address);
281 282 283 284 285
		break;

	case KVM_S390_RESTART:
		VCPU_EVENT(vcpu, 4, "%s", "interrupt: cpu restart");
		vcpu->stat.deliver_restart_signal++;
286 287
		trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type,
						 0, 0);
288 289 290 291 292 293
		rc  = copy_to_guest(vcpu,
				    offsetof(struct _lowcore, restart_old_psw),
				    &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
		rc |= copy_from_guest(vcpu, &vcpu->arch.sie_block->gpsw,
				      offsetof(struct _lowcore, restart_psw),
				      sizeof(psw_t));
294
		atomic_clear_mask(CPUSTAT_STOPPED, &vcpu->arch.sie_block->cpuflags);
295 296 297 298 299 300
		break;
	case KVM_S390_PROGRAM_INT:
		VCPU_EVENT(vcpu, 4, "interrupt: pgm check code:%x, ilc:%x",
			   inti->pgm.code,
			   table[vcpu->arch.sie_block->ipa >> 14]);
		vcpu->stat.deliver_program_int++;
301 302
		trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type,
						 inti->pgm.code, 0);
303
		rc  = put_guest(vcpu, inti->pgm.code, (u16 __user *)__LC_PGM_INT_CODE);
304
		rc |= put_guest(vcpu, table[vcpu->arch.sie_block->ipa >> 14],
305
				(u16 __user *)__LC_PGM_ILC);
306 307 308 309
		rc |= copy_to_guest(vcpu, __LC_PGM_OLD_PSW,
				    &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
		rc |= copy_from_guest(vcpu, &vcpu->arch.sie_block->gpsw,
				      __LC_PGM_NEW_PSW, sizeof(psw_t));
310 311
		break;

312 313 314 315 316 317
	case KVM_S390_MCHK:
		VCPU_EVENT(vcpu, 4, "interrupt: machine check mcic=%llx",
			   inti->mchk.mcic);
		trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type,
						 inti->mchk.cr14,
						 inti->mchk.mcic);
318 319
		rc  = kvm_s390_vcpu_store_status(vcpu,
						 KVM_S390_STORE_STATUS_PREFIXED);
320
		rc |= put_guest(vcpu, inti->mchk.mcic, (u64 __user *) __LC_MCCK_CODE);
321 322 323 324
		rc |= copy_to_guest(vcpu, __LC_MCK_OLD_PSW,
				    &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
		rc |= copy_from_guest(vcpu, &vcpu->arch.sie_block->gpsw,
				      __LC_MCK_NEW_PSW, sizeof(psw_t));
325 326
		break;

327 328 329 330 331 332 333 334 335 336
	case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
	{
		__u32 param0 = ((__u32)inti->io.subchannel_id << 16) |
			inti->io.subchannel_nr;
		__u64 param1 = ((__u64)inti->io.io_int_parm << 32) |
			inti->io.io_int_word;
		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,
						 param0, param1);
337
		rc  = put_guest(vcpu, inti->io.subchannel_id,
338
				(u16 __user *) __LC_SUBCHANNEL_ID);
339
		rc |= put_guest(vcpu, inti->io.subchannel_nr,
340
				(u16 __user *) __LC_SUBCHANNEL_NR);
341
		rc |= put_guest(vcpu, inti->io.io_int_parm,
342
				(u32 __user *) __LC_IO_INT_PARM);
343
		rc |= put_guest(vcpu, inti->io.io_int_word,
344
				(u32 __user *) __LC_IO_INT_WORD);
345 346 347 348
		rc |= copy_to_guest(vcpu, __LC_IO_OLD_PSW,
				    &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
		rc |= copy_from_guest(vcpu, &vcpu->arch.sie_block->gpsw,
				      __LC_IO_NEW_PSW, sizeof(psw_t));
349 350
		break;
	}
351 352 353
	default:
		BUG();
	}
354
	if (rc) {
355
		printk("kvm: The guest lowcore is not mapped during interrupt "
356
		       "delivery, killing userspace\n");
357
		do_exit(SIGKILL);
358 359 360 361 362
	}
}

static int __try_deliver_ckc_interrupt(struct kvm_vcpu *vcpu)
{
363
	int rc;
364 365 366 367 368

	if (psw_extint_disabled(vcpu))
		return 0;
	if (!(vcpu->arch.sie_block->gcr[0] & 0x800ul))
		return 0;
369
	rc  = put_guest(vcpu, 0x1004, (u16 __user *)__LC_EXT_INT_CODE);
370 371 372 373 374
	rc |= copy_to_guest(vcpu, __LC_EXT_OLD_PSW,
			    &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
	rc |= copy_from_guest(vcpu, &vcpu->arch.sie_block->gpsw,
			      __LC_EXT_NEW_PSW, sizeof(psw_t));
	if (rc) {
375 376 377
		printk("kvm: The guest lowcore is not mapped during interrupt "
			"delivery, killing userspace\n");
		do_exit(SIGKILL);
378 379 380 381
	}
	return 1;
}

382
int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu)
383
{
384 385 386
	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  *inti;
387 388 389 390 391 392 393 394 395 396 397 398 399
	int rc = 0;

	if (atomic_read(&li->active)) {
		spin_lock_bh(&li->lock);
		list_for_each_entry(inti, &li->list, list)
			if (__interrupt_is_deliverable(vcpu, inti)) {
				rc = 1;
				break;
			}
		spin_unlock_bh(&li->lock);
	}

	if ((!rc) && atomic_read(&fi->active)) {
400
		spin_lock(&fi->lock);
401 402 403 404 405
		list_for_each_entry(inti, &fi->list, list)
			if (__interrupt_is_deliverable(vcpu, inti)) {
				rc = 1;
				break;
			}
406
		spin_unlock(&fi->lock);
407 408 409
	}

	if ((!rc) && (vcpu->arch.sie_block->ckc <
410
		get_tod_clock_fast() + vcpu->arch.sie_block->epoch)) {
411 412 413 414 415 416 417 418
		if ((!psw_extint_disabled(vcpu)) &&
			(vcpu->arch.sie_block->gcr[0] & 0x800ul))
			rc = 1;
	}

	return rc;
}

419 420 421 422 423
int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
{
	return 0;
}

424 425 426 427 428 429 430 431 432
int kvm_s390_handle_wait(struct kvm_vcpu *vcpu)
{
	u64 now, sltime;
	DECLARE_WAITQUEUE(wait, current);

	vcpu->stat.exit_wait_state++;
	if (kvm_cpu_has_interrupt(vcpu))
		return 0;

433 434 435 436 437
	__set_cpu_idle(vcpu);
	spin_lock_bh(&vcpu->arch.local_int.lock);
	vcpu->arch.local_int.timer_due = 0;
	spin_unlock_bh(&vcpu->arch.local_int.lock);

438 439 440
	if (psw_interrupts_disabled(vcpu)) {
		VCPU_EVENT(vcpu, 3, "%s", "disabled wait");
		__unset_cpu_idle(vcpu);
441
		return -EOPNOTSUPP; /* disabled wait */
442 443 444 445 446 447 448 449
	}

	if (psw_extint_disabled(vcpu) ||
	    (!(vcpu->arch.sie_block->gcr[0] & 0x800ul))) {
		VCPU_EVENT(vcpu, 3, "%s", "enabled wait w/o timer");
		goto no_timer;
	}

450
	now = get_tod_clock_fast() + vcpu->arch.sie_block->epoch;
451 452 453 454 455
	if (vcpu->arch.sie_block->ckc < now) {
		__unset_cpu_idle(vcpu);
		return 0;
	}

456
	sltime = tod_to_ns(vcpu->arch.sie_block->ckc - now);
457

458 459
	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);
460
no_timer:
461
	srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
462
	spin_lock(&vcpu->arch.local_int.float_int->lock);
463
	spin_lock_bh(&vcpu->arch.local_int.lock);
464
	add_wait_queue(&vcpu->wq, &wait);
465 466 467 468 469 470
	while (list_empty(&vcpu->arch.local_int.list) &&
		list_empty(&vcpu->arch.local_int.float_int->list) &&
		(!vcpu->arch.local_int.timer_due) &&
		!signal_pending(current)) {
		set_current_state(TASK_INTERRUPTIBLE);
		spin_unlock_bh(&vcpu->arch.local_int.lock);
471
		spin_unlock(&vcpu->arch.local_int.float_int->lock);
472
		schedule();
473
		spin_lock(&vcpu->arch.local_int.float_int->lock);
474 475 476 477
		spin_lock_bh(&vcpu->arch.local_int.lock);
	}
	__unset_cpu_idle(vcpu);
	__set_current_state(TASK_RUNNING);
478
	remove_wait_queue(&vcpu->wq, &wait);
479
	spin_unlock_bh(&vcpu->arch.local_int.lock);
480
	spin_unlock(&vcpu->arch.local_int.float_int->lock);
481 482
	vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);

483
	hrtimer_try_to_cancel(&vcpu->arch.ckc_timer);
484 485 486
	return 0;
}

487
void kvm_s390_tasklet(unsigned long parm)
488
{
489
	struct kvm_vcpu *vcpu = (struct kvm_vcpu *) parm;
490

491
	spin_lock(&vcpu->arch.local_int.lock);
492
	vcpu->arch.local_int.timer_due = 1;
493 494
	if (waitqueue_active(&vcpu->wq))
		wake_up_interruptible(&vcpu->wq);
495
	spin_unlock(&vcpu->arch.local_int.lock);
496 497
}

498 499 500 501 502 503 504 505 506
/*
 * low level hrtimer wake routine. Because this runs in hardirq context
 * we schedule a tasklet to do the real work.
 */
enum hrtimer_restart kvm_s390_idle_wakeup(struct hrtimer *timer)
{
	struct kvm_vcpu *vcpu;

	vcpu = container_of(timer, struct kvm_vcpu, arch.ckc_timer);
507
	vcpu->preempted = true;
508 509 510 511
	tasklet_schedule(&vcpu->arch.tasklet);

	return HRTIMER_NORESTART;
}
512

513 514 515 516 517 518 519 520 521 522 523 524 525 526
void kvm_s390_clear_local_irqs(struct kvm_vcpu *vcpu)
{
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
	struct kvm_s390_interrupt_info  *n, *inti = NULL;

	spin_lock_bh(&li->lock);
	list_for_each_entry_safe(inti, n, &li->list, list) {
		list_del(&inti->list);
		kfree(inti);
	}
	atomic_set(&li->active, 0);
	spin_unlock_bh(&li->lock);
}

527 528
void kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu)
{
529 530 531
	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;
532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557
	int deliver;

	__reset_intercept_indicators(vcpu);
	if (atomic_read(&li->active)) {
		do {
			deliver = 0;
			spin_lock_bh(&li->lock);
			list_for_each_entry_safe(inti, n, &li->list, list) {
				if (__interrupt_is_deliverable(vcpu, inti)) {
					list_del(&inti->list);
					deliver = 1;
					break;
				}
				__set_intercept_indicator(vcpu, inti);
			}
			if (list_empty(&li->list))
				atomic_set(&li->active, 0);
			spin_unlock_bh(&li->lock);
			if (deliver) {
				__do_deliver_interrupt(vcpu, inti);
				kfree(inti);
			}
		} while (deliver);
	}

	if ((vcpu->arch.sie_block->ckc <
558
		get_tod_clock_fast() + vcpu->arch.sie_block->epoch))
559 560 561 562 563
		__try_deliver_ckc_interrupt(vcpu);

	if (atomic_read(&fi->active)) {
		do {
			deliver = 0;
564
			spin_lock(&fi->lock);
565 566 567
			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
568
					fi->irq_count--;
569 570 571 572 573 574 575
					deliver = 1;
					break;
				}
				__set_intercept_indicator(vcpu, inti);
			}
			if (list_empty(&fi->list))
				atomic_set(&fi->active, 0);
576
			spin_unlock(&fi->lock);
577 578 579 580 581 582 583 584
			if (deliver) {
				__do_deliver_interrupt(vcpu, inti);
				kfree(inti);
			}
		} while (deliver);
	}
}

585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623
void kvm_s390_deliver_pending_machine_checks(struct kvm_vcpu *vcpu)
{
	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;
	int deliver;

	__reset_intercept_indicators(vcpu);
	if (atomic_read(&li->active)) {
		do {
			deliver = 0;
			spin_lock_bh(&li->lock);
			list_for_each_entry_safe(inti, n, &li->list, list) {
				if ((inti->type == KVM_S390_MCHK) &&
				    __interrupt_is_deliverable(vcpu, inti)) {
					list_del(&inti->list);
					deliver = 1;
					break;
				}
				__set_intercept_indicator(vcpu, inti);
			}
			if (list_empty(&li->list))
				atomic_set(&li->active, 0);
			spin_unlock_bh(&li->lock);
			if (deliver) {
				__do_deliver_interrupt(vcpu, inti);
				kfree(inti);
			}
		} while (deliver);
	}

	if (atomic_read(&fi->active)) {
		do {
			deliver = 0;
			spin_lock(&fi->lock);
			list_for_each_entry_safe(inti, n, &fi->list, list) {
				if ((inti->type == KVM_S390_MCHK) &&
				    __interrupt_is_deliverable(vcpu, inti)) {
					list_del(&inti->list);
J
Jens Freimann 已提交
624
					fi->irq_count--;
625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640
					deliver = 1;
					break;
				}
				__set_intercept_indicator(vcpu, inti);
			}
			if (list_empty(&fi->list))
				atomic_set(&fi->active, 0);
			spin_unlock(&fi->lock);
			if (deliver) {
				__do_deliver_interrupt(vcpu, inti);
				kfree(inti);
			}
		} while (deliver);
	}
}

641 642
int kvm_s390_inject_program_int(struct kvm_vcpu *vcpu, u16 code)
{
643 644
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
	struct kvm_s390_interrupt_info *inti;
645 646 647 648 649

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

650
	inti->type = KVM_S390_PROGRAM_INT;
651 652 653
	inti->pgm.code = code;

	VCPU_EVENT(vcpu, 3, "inject: program check %d (from kernel)", code);
654
	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, inti->type, code, 0, 1);
655 656 657
	spin_lock_bh(&li->lock);
	list_add(&inti->list, &li->list);
	atomic_set(&li->active, 1);
658
	BUG_ON(waitqueue_active(li->wq));
659 660 661 662
	spin_unlock_bh(&li->lock);
	return 0;
}

663 664 665 666 667 668 669 670 671 672 673 674 675 676 677
struct kvm_s390_interrupt_info *kvm_s390_get_io_int(struct kvm *kvm,
						    u64 cr6, u64 schid)
{
	struct kvm_s390_float_interrupt *fi;
	struct kvm_s390_interrupt_info *inti, *iter;

	if ((!schid && !cr6) || (schid && cr6))
		return NULL;
	mutex_lock(&kvm->lock);
	fi = &kvm->arch.float_int;
	spin_lock(&fi->lock);
	inti = NULL;
	list_for_each_entry(iter, &fi->list, list) {
		if (!is_ioint(iter->type))
			continue;
C
Cornelia Huck 已提交
678 679
		if (cr6 &&
		    ((cr6 & int_word_to_isc_bits(iter->io.io_int_word)) == 0))
680 681 682 683 684 685 686 687 688 689 690 691
			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
692
	if (inti) {
693
		list_del_init(&inti->list);
J
Jens Freimann 已提交
694 695
		fi->irq_count--;
	}
696 697 698 699 700 701
	if (list_empty(&fi->list))
		atomic_set(&fi->active, 0);
	spin_unlock(&fi->lock);
	mutex_unlock(&kvm->lock);
	return inti;
}
702

J
Jens Freimann 已提交
703
static int __inject_vm(struct kvm *kvm, struct kvm_s390_interrupt_info *inti)
704
{
705 706
	struct kvm_s390_local_interrupt *li;
	struct kvm_s390_float_interrupt *fi;
707
	struct kvm_s390_interrupt_info *iter;
708
	struct kvm_vcpu *dst_vcpu = NULL;
709
	int sigcpu;
J
Jens Freimann 已提交
710
	int rc = 0;
711

712 713 714
	mutex_lock(&kvm->lock);
	fi = &kvm->arch.float_int;
	spin_lock(&fi->lock);
J
Jens Freimann 已提交
715 716 717 718 719
	if (fi->irq_count >= KVM_S390_MAX_FLOAT_IRQS) {
		rc = -EINVAL;
		goto unlock_fi;
	}
	fi->irq_count++;
720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742
	if (!is_ioint(inti->type)) {
		list_add_tail(&inti->list, &fi->list);
	} else {
		u64 isc_bits = int_word_to_isc_bits(inti->io.io_int_word);

		/* Keep I/O interrupts sorted in isc order. */
		list_for_each_entry(iter, &fi->list, list) {
			if (!is_ioint(iter->type))
				continue;
			if (int_word_to_isc_bits(iter->io.io_int_word)
			    <= isc_bits)
				continue;
			break;
		}
		list_add_tail(&inti->list, &iter->list);
	}
	atomic_set(&fi->active, 1);
	sigcpu = find_first_bit(fi->idle_mask, KVM_MAX_VCPUS);
	if (sigcpu == KVM_MAX_VCPUS) {
		do {
			sigcpu = fi->next_rr_cpu++;
			if (sigcpu == KVM_MAX_VCPUS)
				sigcpu = fi->next_rr_cpu = 0;
743
		} while (kvm_get_vcpu(kvm, sigcpu) == NULL);
744
	}
745 746
	dst_vcpu = kvm_get_vcpu(kvm, sigcpu);
	li = &dst_vcpu->arch.local_int;
747 748 749 750
	spin_lock_bh(&li->lock);
	atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags);
	if (waitqueue_active(li->wq))
		wake_up_interruptible(li->wq);
751
	kvm_get_vcpu(kvm, sigcpu)->preempted = true;
752
	spin_unlock_bh(&li->lock);
J
Jens Freimann 已提交
753
unlock_fi:
754 755
	spin_unlock(&fi->lock);
	mutex_unlock(&kvm->lock);
J
Jens Freimann 已提交
756
	return rc;
757 758 759 760 761 762 763
}

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

764 765 766 767
	inti = kzalloc(sizeof(*inti), GFP_KERNEL);
	if (!inti)
		return -ENOMEM;

768 769
	inti->type = s390int->type;
	switch (inti->type) {
770
	case KVM_S390_INT_VIRTIO:
771
		VM_EVENT(kvm, 5, "inject: virtio parm:%x,parm64:%llx",
772 773 774 775 776 777 778 779
			 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;
780 781 782 783
	case KVM_S390_INT_PFAULT_DONE:
		inti->type = s390int->type;
		inti->ext.ext_params2 = s390int->parm64;
		break;
784 785 786 787 788 789
	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;
790
	case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
791
		if (inti->type & IOINT_AI_MASK)
792 793 794 795 796 797 798 799 800 801 802
			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;
803 804 805 806
	default:
		kfree(inti);
		return -EINVAL;
	}
807 808
	trace_kvm_s390_inject_vm(s390int->type, s390int->parm, s390int->parm64,
				 2);
809

J
Jens Freimann 已提交
810
	return __inject_vm(kvm, inti);
811 812 813 814 815
}

int kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu,
			 struct kvm_s390_interrupt *s390int)
{
816 817
	struct kvm_s390_local_interrupt *li;
	struct kvm_s390_interrupt_info *inti;
818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833

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

	switch (s390int->type) {
	case KVM_S390_PROGRAM_INT:
		if (s390int->parm & 0xffff0000) {
			kfree(inti);
			return -EINVAL;
		}
		inti->type = s390int->type;
		inti->pgm.code = s390int->parm;
		VCPU_EVENT(vcpu, 3, "inject: program check %d (from user)",
			   s390int->parm);
		break;
834 835 836 837 838 839
	case KVM_S390_SIGP_SET_PREFIX:
		inti->prefix.address = s390int->parm;
		inti->type = s390int->type;
		VCPU_EVENT(vcpu, 3, "inject: set prefix to %x (from user)",
			   s390int->parm);
		break;
840 841
	case KVM_S390_SIGP_STOP:
	case KVM_S390_RESTART:
842 843 844
		VCPU_EVENT(vcpu, 3, "inject: type %x", s390int->type);
		inti->type = s390int->type;
		break;
845
	case KVM_S390_INT_EXTERNAL_CALL:
846 847 848 849 850 851 852 853 854
		if (s390int->parm & 0xffff0000) {
			kfree(inti);
			return -EINVAL;
		}
		VCPU_EVENT(vcpu, 3, "inject: external call source-cpu:%u",
			   s390int->parm);
		inti->type = s390int->type;
		inti->extcall.code = s390int->parm;
		break;
855
	case KVM_S390_INT_EMERGENCY:
856 857 858 859 860
		if (s390int->parm & 0xffff0000) {
			kfree(inti);
			return -EINVAL;
		}
		VCPU_EVENT(vcpu, 3, "inject: emergency %u\n", s390int->parm);
861
		inti->type = s390int->type;
862
		inti->emerg.code = s390int->parm;
863
		break;
864 865 866 867 868 869
	case KVM_S390_MCHK:
		VCPU_EVENT(vcpu, 5, "inject: machine check parm64:%llx",
			   s390int->parm64);
		inti->type = s390int->type;
		inti->mchk.mcic = s390int->parm64;
		break;
870 871 872 873
	case KVM_S390_INT_PFAULT_INIT:
		inti->type = s390int->type;
		inti->ext.ext_params2 = s390int->parm64;
		break;
874 875
	case KVM_S390_INT_VIRTIO:
	case KVM_S390_INT_SERVICE:
876
	case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
877 878 879 880
	default:
		kfree(inti);
		return -EINVAL;
	}
881 882
	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, s390int->type, s390int->parm,
				   s390int->parm64, 2);
883 884 885 886 887 888 889 890 891 892 893 894

	mutex_lock(&vcpu->kvm->lock);
	li = &vcpu->arch.local_int;
	spin_lock_bh(&li->lock);
	if (inti->type == KVM_S390_PROGRAM_INT)
		list_add(&inti->list, &li->list);
	else
		list_add_tail(&inti->list, &li->list);
	atomic_set(&li->active, 1);
	if (inti->type == KVM_S390_SIGP_STOP)
		li->action_bits |= ACTION_STOP_ON_STOP;
	atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags);
895 896
	if (waitqueue_active(&vcpu->wq))
		wake_up_interruptible(&vcpu->wq);
897
	vcpu->preempted = true;
898 899 900 901
	spin_unlock_bh(&li->lock);
	mutex_unlock(&vcpu->kvm->lock);
	return 0;
}
902 903 904 905 906 907 908 909 910 911 912 913 914

static void clear_floating_interrupts(struct kvm *kvm)
{
	struct kvm_s390_float_interrupt *fi;
	struct kvm_s390_interrupt_info	*n, *inti = NULL;

	mutex_lock(&kvm->lock);
	fi = &kvm->arch.float_int;
	spin_lock(&fi->lock);
	list_for_each_entry_safe(inti, n, &fi->list, list) {
		list_del(&inti->list);
		kfree(inti);
	}
J
Jens Freimann 已提交
915
	fi->irq_count = 0;
916 917 918 919 920 921 922 923 924 925 926 927 928
	atomic_set(&fi->active, 0);
	spin_unlock(&fi->lock);
	mutex_unlock(&kvm->lock);
}

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

	irq.type = inti->type;
	switch (inti->type) {
929 930
	case KVM_S390_INT_PFAULT_INIT:
	case KVM_S390_INT_PFAULT_DONE:
931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009
	case KVM_S390_INT_VIRTIO:
	case KVM_S390_INT_SERVICE:
		irq.u.ext = inti->ext;
		break;
	case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
		irq.u.io = inti->io;
		break;
	case KVM_S390_MCHK:
		irq.u.mchk = inti->mchk;
		break;
	default:
		return -EINVAL;
	}

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

	return 0;
}

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

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

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

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

	return ret < 0 ? ret : n;
}

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

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

	return r;
}

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

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

	switch (inti->type) {
1010 1011
	case KVM_S390_INT_PFAULT_INIT:
	case KVM_S390_INT_PFAULT_DONE:
1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059
	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
1060 1061 1062 1063 1064
		r = __inject_vm(dev->kvm, inti);
		if (r) {
			kfree(inti);
			return r;
		}
1065 1066 1067 1068 1069 1070 1071
		len -= sizeof(struct kvm_s390_irq);
		attr->addr += sizeof(struct kvm_s390_irq);
	}

	return r;
}

1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236
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;
	map->addr = gmap_translate(addr, kvm->arch.gmap);
	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;
}

1237 1238 1239
static int flic_set_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
{
	int r = 0;
1240 1241
	unsigned int i;
	struct kvm_vcpu *vcpu;
1242 1243 1244 1245 1246 1247 1248 1249 1250

	switch (attr->group) {
	case KVM_DEV_FLIC_ENQUEUE:
		r = enqueue_floating_irq(dev, attr);
		break;
	case KVM_DEV_FLIC_CLEAR_IRQS:
		r = 0;
		clear_floating_interrupts(dev->kvm);
		break;
1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264
	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;
1265 1266 1267 1268 1269 1270
	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;
1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301
	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,
};
1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 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

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;
}

int kvm_set_routing_entry(struct kvm_irq_routing_table *rt,
			  struct kvm_kernel_irq_routing_entry *e,
			  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;
}