interrupt.c 40.7 KB
Newer Older
1
/*
2
 * handling kvm guest interrupts
3
 *
4
 * Copyright IBM Corp. 2008,2014
5 6 7 8 9 10 11 12
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License (version 2 only)
 * as published by the Free Software Foundation.
 *
 *    Author(s): Carsten Otte <cotte@de.ibm.com>
 */

13
#include <linux/interrupt.h>
14
#include <linux/kvm_host.h>
15
#include <linux/hrtimer.h>
16
#include <linux/mmu_context.h>
17
#include <linux/signal.h>
18
#include <linux/slab.h>
19 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;
}

59 60 61 62 63 64 65 66
static int ckc_interrupts_enabled(struct kvm_vcpu *vcpu)
{
	if (psw_extint_disabled(vcpu) ||
	    !(vcpu->arch.sie_block->gcr[0] & 0x800ul))
		return 0;
	return 1;
}

C
Cornelia Huck 已提交
67 68 69 70 71 72 73
static u64 int_word_to_isc_bits(u32 int_word)
{
	u8 isc = (int_word & 0x38000000) >> 27;

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

74
static int __interrupt_is_deliverable(struct kvm_vcpu *vcpu,
75
				      struct kvm_s390_interrupt_info *inti)
76 77
{
	switch (inti->type) {
78 79 80 81 82
	case KVM_S390_INT_EXTERNAL_CALL:
		if (psw_extint_disabled(vcpu))
			return 0;
		if (vcpu->arch.sie_block->gcr[0] & 0x2000ul)
			return 1;
83 84 85 86 87 88 89
	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:
90 91
	case KVM_S390_INT_PFAULT_INIT:
	case KVM_S390_INT_PFAULT_DONE:
92 93 94 95 96 97 98 99 100 101 102
	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;
103 104 105 106 107 108
	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;
109 110 111
	case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
		if (psw_ioint_disabled(vcpu))
			return 0;
C
Cornelia Huck 已提交
112 113
		if (vcpu->arch.sie_block->gcr[6] &
		    int_word_to_isc_bits(inti->io.io_int_word))
114 115
			return 1;
		return 0;
116
	default:
117 118
		printk(KERN_WARNING "illegal interrupt type %llx\n",
		       inti->type);
119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141
		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;
142 143 144 145 146 147 148
	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);
	}
149 150 151 152 153 154 155 156
}

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,
157
				      struct kvm_s390_interrupt_info *inti)
158 159
{
	switch (inti->type) {
160
	case KVM_S390_INT_EXTERNAL_CALL:
161 162
	case KVM_S390_INT_EMERGENCY:
	case KVM_S390_INT_SERVICE:
163 164
	case KVM_S390_INT_PFAULT_INIT:
	case KVM_S390_INT_PFAULT_DONE:
165 166 167 168 169 170 171 172 173
	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;
174 175 176 177 178 179
	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;
180 181 182 183 184 185
	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;
186 187 188 189 190
	default:
		BUG();
	}
}

191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290
static int __deliver_prog_irq(struct kvm_vcpu *vcpu,
			      struct kvm_s390_pgm_info *pgm_info)
{
	const unsigned short table[] = { 2, 4, 4, 6 };
	int rc = 0;

	switch (pgm_info->code & ~PGM_PER) {
	case PGM_AFX_TRANSLATION:
	case PGM_ASX_TRANSLATION:
	case PGM_EX_TRANSLATION:
	case PGM_LFX_TRANSLATION:
	case PGM_LSTE_SEQUENCE:
	case PGM_LSX_TRANSLATION:
	case PGM_LX_TRANSLATION:
	case PGM_PRIMARY_AUTHORITY:
	case PGM_SECONDARY_AUTHORITY:
	case PGM_SPACE_SWITCH:
		rc = put_guest_lc(vcpu, pgm_info->trans_exc_code,
				  (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:
		rc = put_guest_lc(vcpu, pgm_info->exc_access_id,
				  (u8 *)__LC_EXC_ACCESS_ID);
		break;
	case PGM_ASCE_TYPE:
	case PGM_PAGE_TRANSLATION:
	case PGM_REGION_FIRST_TRANS:
	case PGM_REGION_SECOND_TRANS:
	case PGM_REGION_THIRD_TRANS:
	case PGM_SEGMENT_TRANSLATION:
		rc = put_guest_lc(vcpu, pgm_info->trans_exc_code,
				  (u64 *)__LC_TRANS_EXC_CODE);
		rc |= put_guest_lc(vcpu, pgm_info->exc_access_id,
				   (u8 *)__LC_EXC_ACCESS_ID);
		rc |= put_guest_lc(vcpu, pgm_info->op_access_id,
				   (u8 *)__LC_OP_ACCESS_ID);
		break;
	case PGM_MONITOR:
		rc = put_guest_lc(vcpu, pgm_info->mon_class_nr,
				  (u64 *)__LC_MON_CLASS_NR);
		rc |= put_guest_lc(vcpu, pgm_info->mon_code,
				   (u64 *)__LC_MON_CODE);
		break;
	case PGM_DATA:
		rc = put_guest_lc(vcpu, pgm_info->data_exc_code,
				  (u32 *)__LC_DATA_EXC_CODE);
		break;
	case PGM_PROTECTION:
		rc = put_guest_lc(vcpu, pgm_info->trans_exc_code,
				  (u64 *)__LC_TRANS_EXC_CODE);
		rc |= put_guest_lc(vcpu, pgm_info->exc_access_id,
				   (u8 *)__LC_EXC_ACCESS_ID);
		break;
	}

	if (pgm_info->code & PGM_PER) {
		rc |= put_guest_lc(vcpu, pgm_info->per_code,
				   (u8 *) __LC_PER_CODE);
		rc |= put_guest_lc(vcpu, pgm_info->per_atmid,
				   (u8 *)__LC_PER_ATMID);
		rc |= put_guest_lc(vcpu, pgm_info->per_address,
				   (u64 *) __LC_PER_ADDRESS);
		rc |= put_guest_lc(vcpu, pgm_info->per_access_id,
				   (u8 *) __LC_PER_ACCESS_ID);
	}

	switch (vcpu->arch.sie_block->icptcode) {
	case ICPT_INST:
	case ICPT_INSTPROGI:
	case ICPT_OPEREXC:
	case ICPT_PARTEXEC:
	case ICPT_IOINST:
		/* last instruction only stored for these icptcodes */
		rc |= put_guest_lc(vcpu, table[vcpu->arch.sie_block->ipa >> 14],
				   (u16 *) __LC_PGM_ILC);
		break;
	case ICPT_PROGI:
		rc |= put_guest_lc(vcpu, vcpu->arch.sie_block->pgmilc,
				   (u16 *) __LC_PGM_ILC);
		break;
	default:
		rc |= put_guest_lc(vcpu, 0,
				   (u16 *) __LC_PGM_ILC);
	}

	rc |= put_guest_lc(vcpu, pgm_info->code,
			   (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));

	return rc;
}

291
static void __do_deliver_interrupt(struct kvm_vcpu *vcpu,
292
				   struct kvm_s390_interrupt_info *inti)
293 294
{
	const unsigned short table[] = { 2, 4, 4, 6 };
295
	int rc = 0;
296 297 298 299 300

	switch (inti->type) {
	case KVM_S390_INT_EMERGENCY:
		VCPU_EVENT(vcpu, 4, "%s", "interrupt: sigp emerg");
		vcpu->stat.deliver_emergency_signal++;
301 302
		trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type,
						 inti->emerg.code, 0);
303 304 305 306 307 308
		rc  = put_guest_lc(vcpu, 0x1201, (u16 *)__LC_EXT_INT_CODE);
		rc |= put_guest_lc(vcpu, inti->emerg.code,
				   (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,
309
				    &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
310
		break;
311 312 313
	case KVM_S390_INT_EXTERNAL_CALL:
		VCPU_EVENT(vcpu, 4, "%s", "interrupt: sigp ext call");
		vcpu->stat.deliver_external_call++;
314 315
		trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type,
						 inti->extcall.code, 0);
316 317 318 319 320 321 322 323 324
		rc  = put_guest_lc(vcpu, 0x1202, (u16 *)__LC_EXT_INT_CODE);
		rc |= put_guest_lc(vcpu, inti->extcall.code,
				   (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));
325
		break;
326 327 328 329
	case KVM_S390_INT_SERVICE:
		VCPU_EVENT(vcpu, 4, "interrupt: sclp parm:%x",
			   inti->ext.ext_params);
		vcpu->stat.deliver_service_signal++;
330 331
		trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type,
						 inti->ext.ext_params, 0);
332 333 334 335 336
		rc  = put_guest_lc(vcpu, 0x2401, (u16 *)__LC_EXT_INT_CODE);
		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,
337
				    &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
338 339
		rc |= put_guest_lc(vcpu, inti->ext.ext_params,
				   (u32 *)__LC_EXT_PARAMS);
340
		break;
341 342 343
	case KVM_S390_INT_PFAULT_INIT:
		trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type, 0,
						 inti->ext.ext_params2);
344 345 346 347 348
		rc  = put_guest_lc(vcpu, 0x2603, (u16 *) __LC_EXT_INT_CODE);
		rc |= put_guest_lc(vcpu, 0x0600, (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,
349
				    &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
350 351
		rc |= put_guest_lc(vcpu, inti->ext.ext_params2,
				   (u64 *) __LC_EXT_PARAMS2);
352 353 354 355
		break;
	case KVM_S390_INT_PFAULT_DONE:
		trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type, 0,
						 inti->ext.ext_params2);
356 357 358 359 360 361
		rc  = put_guest_lc(vcpu, 0x2603, (u16 *)__LC_EXT_INT_CODE);
		rc |= put_guest_lc(vcpu, 0x0680, (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,
362
				    &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
363 364
		rc |= put_guest_lc(vcpu, inti->ext.ext_params2,
				   (u64 *)__LC_EXT_PARAMS2);
365
		break;
366
	case KVM_S390_INT_VIRTIO:
367
		VCPU_EVENT(vcpu, 4, "interrupt: virtio parm:%x,parm64:%llx",
368 369
			   inti->ext.ext_params, inti->ext.ext_params2);
		vcpu->stat.deliver_virtio_interrupt++;
370 371 372
		trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type,
						 inti->ext.ext_params,
						 inti->ext.ext_params2);
373 374 375 376 377 378
		rc  = put_guest_lc(vcpu, 0x2603, (u16 *)__LC_EXT_INT_CODE);
		rc |= put_guest_lc(vcpu, 0x0d00, (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,
379
				    &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
380 381 382 383
		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);
384 385 386 387
		break;
	case KVM_S390_SIGP_STOP:
		VCPU_EVENT(vcpu, 4, "%s", "interrupt: cpu stop");
		vcpu->stat.deliver_stop_signal++;
388 389
		trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type,
						 0, 0);
390 391 392 393 394 395 396
		__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++;
397 398
		trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type,
						 inti->prefix.address, 0);
399
		kvm_s390_set_prefix(vcpu, inti->prefix.address);
400 401 402 403 404
		break;

	case KVM_S390_RESTART:
		VCPU_EVENT(vcpu, 4, "%s", "interrupt: cpu restart");
		vcpu->stat.deliver_restart_signal++;
405 406
		trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type,
						 0, 0);
407 408 409 410 411 412
		rc  = write_guest_lc(vcpu,
				     offsetof(struct _lowcore, restart_old_psw),
				     &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
		rc |= read_guest_lc(vcpu, offsetof(struct _lowcore, restart_psw),
				    &vcpu->arch.sie_block->gpsw,
				    sizeof(psw_t));
413
		atomic_clear_mask(CPUSTAT_STOPPED, &vcpu->arch.sie_block->cpuflags);
414 415 416 417 418 419
		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++;
420 421
		trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type,
						 inti->pgm.code, 0);
422
		rc = __deliver_prog_irq(vcpu, &inti->pgm);
423 424
		break;

425 426 427 428 429 430
	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);
431 432
		rc  = kvm_s390_vcpu_store_status(vcpu,
						 KVM_S390_STORE_STATUS_PREFIXED);
433 434 435 436 437
		rc |= put_guest_lc(vcpu, inti->mchk.mcic, (u64 *)__LC_MCCK_CODE);
		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,
438
				    &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
439 440
		break;

441 442 443 444 445 446 447 448 449 450
	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);
451 452 453 454 455 456 457 458 459 460 461 462 463 464
		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));
465 466
		break;
	}
467 468 469
	default:
		BUG();
	}
470
	if (rc) {
471
		printk("kvm: The guest lowcore is not mapped during interrupt "
472
		       "delivery, killing userspace\n");
473
		do_exit(SIGKILL);
474 475 476
	}
}

477
static void deliver_ckc_interrupt(struct kvm_vcpu *vcpu)
478
{
479
	int rc;
480

481 482 483 484 485 486
	rc  = put_guest_lc(vcpu, 0x1004, (u16 __user *)__LC_EXT_INT_CODE);
	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));
487
	if (rc) {
488 489 490
		printk("kvm: The guest lowcore is not mapped during interrupt "
			"delivery, killing userspace\n");
		do_exit(SIGKILL);
491 492 493
	}
}

494
int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu)
495
{
496 497 498
	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;
499 500 501 502 503 504 505 506 507 508 509 510 511
	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)) {
512
		spin_lock(&fi->lock);
513 514 515 516 517
		list_for_each_entry(inti, &fi->list, list)
			if (__interrupt_is_deliverable(vcpu, inti)) {
				rc = 1;
				break;
			}
518
		spin_unlock(&fi->lock);
519 520
	}

521 522
	if (!rc && kvm_cpu_has_pending_timer(vcpu))
		rc = 1;
523 524 525 526

	return rc;
}

527 528
int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
{
529 530 531 532 533 534
	if (!(vcpu->arch.sie_block->ckc <
	      get_tod_clock_fast() + vcpu->arch.sie_block->epoch))
		return 0;
	if (!ckc_interrupts_enabled(vcpu))
		return 0;
	return 1;
535 536
}

537 538 539 540 541 542 543 544 545
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;

546 547 548 549 550
	__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);

551 552 553
	if (psw_interrupts_disabled(vcpu)) {
		VCPU_EVENT(vcpu, 3, "%s", "disabled wait");
		__unset_cpu_idle(vcpu);
554
		return -EOPNOTSUPP; /* disabled wait */
555 556
	}

557
	if (!ckc_interrupts_enabled(vcpu)) {
558 559 560 561
		VCPU_EVENT(vcpu, 3, "%s", "enabled wait w/o timer");
		goto no_timer;
	}

562
	now = get_tod_clock_fast() + vcpu->arch.sie_block->epoch;
563 564 565 566 567
	if (vcpu->arch.sie_block->ckc < now) {
		__unset_cpu_idle(vcpu);
		return 0;
	}

568
	sltime = tod_to_ns(vcpu->arch.sie_block->ckc - now);
569

570 571
	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);
572
no_timer:
573
	srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
574
	spin_lock(&vcpu->arch.local_int.float_int->lock);
575
	spin_lock_bh(&vcpu->arch.local_int.lock);
576
	add_wait_queue(&vcpu->wq, &wait);
577 578 579 580 581 582
	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);
583
		spin_unlock(&vcpu->arch.local_int.float_int->lock);
584
		schedule();
585
		spin_lock(&vcpu->arch.local_int.float_int->lock);
586 587 588 589
		spin_lock_bh(&vcpu->arch.local_int.lock);
	}
	__unset_cpu_idle(vcpu);
	__set_current_state(TASK_RUNNING);
590
	remove_wait_queue(&vcpu->wq, &wait);
591
	spin_unlock_bh(&vcpu->arch.local_int.lock);
592
	spin_unlock(&vcpu->arch.local_int.float_int->lock);
593 594
	vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);

595
	hrtimer_try_to_cancel(&vcpu->arch.ckc_timer);
596 597 598
	return 0;
}

599
void kvm_s390_tasklet(unsigned long parm)
600
{
601
	struct kvm_vcpu *vcpu = (struct kvm_vcpu *) parm;
602

603
	spin_lock(&vcpu->arch.local_int.lock);
604
	vcpu->arch.local_int.timer_due = 1;
605 606
	if (waitqueue_active(&vcpu->wq))
		wake_up_interruptible(&vcpu->wq);
607
	spin_unlock(&vcpu->arch.local_int.lock);
608 609
}

610 611 612 613 614 615 616 617 618
/*
 * 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);
619
	vcpu->preempted = true;
620 621 622 623
	tasklet_schedule(&vcpu->arch.tasklet);

	return HRTIMER_NORESTART;
}
624

625 626 627 628 629 630 631 632 633 634 635 636 637 638
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);
}

639 640
void kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu)
{
641 642 643
	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;
644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668
	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);
	}

669 670
	if (kvm_cpu_has_pending_timer(vcpu))
		deliver_ckc_interrupt(vcpu);
671 672 673 674

	if (atomic_read(&fi->active)) {
		do {
			deliver = 0;
675
			spin_lock(&fi->lock);
676 677 678
			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
679
					fi->irq_count--;
680 681 682 683 684 685 686
					deliver = 1;
					break;
				}
				__set_intercept_indicator(vcpu, inti);
			}
			if (list_empty(&fi->list))
				atomic_set(&fi->active, 0);
687
			spin_unlock(&fi->lock);
688 689 690 691 692 693 694 695
			if (deliver) {
				__do_deliver_interrupt(vcpu, inti);
				kfree(inti);
			}
		} while (deliver);
	}
}

696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734
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
735
					fi->irq_count--;
736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751
					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);
	}
}

752 753
int kvm_s390_inject_program_int(struct kvm_vcpu *vcpu, u16 code)
{
754 755
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
	struct kvm_s390_interrupt_info *inti;
756 757 758 759 760

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

761
	inti->type = KVM_S390_PROGRAM_INT;
762 763 764
	inti->pgm.code = code;

	VCPU_EVENT(vcpu, 3, "inject: program check %d (from kernel)", code);
765
	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, inti->type, code, 0, 1);
766 767 768
	spin_lock_bh(&li->lock);
	list_add(&inti->list, &li->list);
	atomic_set(&li->active, 1);
769
	BUG_ON(waitqueue_active(li->wq));
770
	spin_unlock_bh(&li->lock);
771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795
	return 0;
}

int kvm_s390_inject_prog_irq(struct kvm_vcpu *vcpu,
			     struct kvm_s390_pgm_info *pgm_info)
{
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
	struct kvm_s390_interrupt_info *inti;

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

	VCPU_EVENT(vcpu, 3, "inject: prog irq %d (from kernel)",
		   pgm_info->code);
	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_PROGRAM_INT,
				   pgm_info->code, 0, 1);

	inti->type = KVM_S390_PROGRAM_INT;
	memcpy(&inti->pgm, pgm_info, sizeof(inti->pgm));
	spin_lock_bh(&li->lock);
	list_add(&inti->list, &li->list);
	atomic_set(&li->active, 1);
	BUG_ON(waitqueue_active(li->wq));
	spin_unlock_bh(&li->lock);
796 797 798
	return 0;
}

799 800 801 802 803 804 805 806 807 808 809 810 811 812 813
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
814 815
		if (cr6 &&
		    ((cr6 & int_word_to_isc_bits(iter->io.io_int_word)) == 0))
816 817 818 819 820 821 822 823 824 825 826 827
			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
828
	if (inti) {
829
		list_del_init(&inti->list);
J
Jens Freimann 已提交
830 831
		fi->irq_count--;
	}
832 833 834 835 836 837
	if (list_empty(&fi->list))
		atomic_set(&fi->active, 0);
	spin_unlock(&fi->lock);
	mutex_unlock(&kvm->lock);
	return inti;
}
838

J
Jens Freimann 已提交
839
static int __inject_vm(struct kvm *kvm, struct kvm_s390_interrupt_info *inti)
840
{
841 842
	struct kvm_s390_local_interrupt *li;
	struct kvm_s390_float_interrupt *fi;
843
	struct kvm_s390_interrupt_info *iter;
844
	struct kvm_vcpu *dst_vcpu = NULL;
845
	int sigcpu;
J
Jens Freimann 已提交
846
	int rc = 0;
847

848 849 850
	mutex_lock(&kvm->lock);
	fi = &kvm->arch.float_int;
	spin_lock(&fi->lock);
J
Jens Freimann 已提交
851 852 853 854 855
	if (fi->irq_count >= KVM_S390_MAX_FLOAT_IRQS) {
		rc = -EINVAL;
		goto unlock_fi;
	}
	fi->irq_count++;
856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878
	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;
879
		} while (kvm_get_vcpu(kvm, sigcpu) == NULL);
880
	}
881 882
	dst_vcpu = kvm_get_vcpu(kvm, sigcpu);
	li = &dst_vcpu->arch.local_int;
883 884 885 886
	spin_lock_bh(&li->lock);
	atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags);
	if (waitqueue_active(li->wq))
		wake_up_interruptible(li->wq);
887
	kvm_get_vcpu(kvm, sigcpu)->preempted = true;
888
	spin_unlock_bh(&li->lock);
J
Jens Freimann 已提交
889
unlock_fi:
890 891
	spin_unlock(&fi->lock);
	mutex_unlock(&kvm->lock);
J
Jens Freimann 已提交
892
	return rc;
893 894 895 896 897 898 899
}

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

900 901 902 903
	inti = kzalloc(sizeof(*inti), GFP_KERNEL);
	if (!inti)
		return -ENOMEM;

904 905
	inti->type = s390int->type;
	switch (inti->type) {
906
	case KVM_S390_INT_VIRTIO:
907
		VM_EVENT(kvm, 5, "inject: virtio parm:%x,parm64:%llx",
908 909 910 911 912 913 914 915
			 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;
916 917 918 919
	case KVM_S390_INT_PFAULT_DONE:
		inti->type = s390int->type;
		inti->ext.ext_params2 = s390int->parm64;
		break;
920 921 922 923 924 925
	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;
926
	case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
927
		if (inti->type & IOINT_AI_MASK)
928 929 930 931 932 933 934 935 936 937 938
			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;
939 940 941 942
	default:
		kfree(inti);
		return -EINVAL;
	}
943 944
	trace_kvm_s390_inject_vm(s390int->type, s390int->parm, s390int->parm64,
				 2);
945

J
Jens Freimann 已提交
946
	return __inject_vm(kvm, inti);
947 948
}

949 950 951 952 953 954
void kvm_s390_reinject_io_int(struct kvm *kvm,
			      struct kvm_s390_interrupt_info *inti)
{
	__inject_vm(kvm, inti);
}

955 956 957
int kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu,
			 struct kvm_s390_interrupt *s390int)
{
958 959
	struct kvm_s390_local_interrupt *li;
	struct kvm_s390_interrupt_info *inti;
960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975

	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;
976 977 978 979 980 981
	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;
982 983
	case KVM_S390_SIGP_STOP:
	case KVM_S390_RESTART:
984 985 986
		VCPU_EVENT(vcpu, 3, "inject: type %x", s390int->type);
		inti->type = s390int->type;
		break;
987
	case KVM_S390_INT_EXTERNAL_CALL:
988 989 990 991 992 993 994 995 996
		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;
997
	case KVM_S390_INT_EMERGENCY:
998 999 1000 1001 1002
		if (s390int->parm & 0xffff0000) {
			kfree(inti);
			return -EINVAL;
		}
		VCPU_EVENT(vcpu, 3, "inject: emergency %u\n", s390int->parm);
1003
		inti->type = s390int->type;
1004
		inti->emerg.code = s390int->parm;
1005
		break;
1006 1007 1008 1009 1010 1011
	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;
1012 1013 1014 1015
	case KVM_S390_INT_PFAULT_INIT:
		inti->type = s390int->type;
		inti->ext.ext_params2 = s390int->parm64;
		break;
1016 1017
	case KVM_S390_INT_VIRTIO:
	case KVM_S390_INT_SERVICE:
1018
	case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
1019 1020 1021 1022
	default:
		kfree(inti);
		return -EINVAL;
	}
1023 1024
	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, s390int->type, s390int->parm,
				   s390int->parm64, 2);
1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036

	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);
1037 1038
	if (waitqueue_active(&vcpu->wq))
		wake_up_interruptible(&vcpu->wq);
1039
	vcpu->preempted = true;
1040 1041 1042 1043
	spin_unlock_bh(&li->lock);
	mutex_unlock(&vcpu->kvm->lock);
	return 0;
}
1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056

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
1057
	fi->irq_count = 0;
1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070
	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) {
1071 1072
	case KVM_S390_INT_PFAULT_INIT:
	case KVM_S390_INT_PFAULT_DONE:
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
	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) {
1152 1153
	case KVM_S390_INT_PFAULT_INIT:
	case KVM_S390_INT_PFAULT_DONE:
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
	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
1202 1203 1204 1205 1206
		r = __inject_vm(dev->kvm, inti);
		if (r) {
			kfree(inti);
			return r;
		}
1207 1208 1209 1210 1211 1212 1213
		len -= sizeof(struct kvm_s390_irq);
		attr->addr += sizeof(struct kvm_s390_irq);
	}

	return r;
}

1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 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
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;
}

1379 1380 1381
static int flic_set_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
{
	int r = 0;
1382 1383
	unsigned int i;
	struct kvm_vcpu *vcpu;
1384 1385 1386 1387 1388 1389 1390 1391 1392

	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;
1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406
	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;
1407 1408 1409 1410 1411 1412
	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;
1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443
	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,
};
1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563

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;
}