summaryrefslogtreecommitdiff
path: root/arch/s390/kvm/intercept.c
blob: 9966c43c6035b740dff7279af9901af6757f979e (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
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
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
// SPDX-License-Identifier: GPL-2.0
/*
 * in-kernel handling for sie intercepts
 *
 * Copyright IBM Corp. 2008, 2020
 *
 *    Author(s): Carsten Otte <cotte@de.ibm.com>
 *               Christian Borntraeger <borntraeger@de.ibm.com>
 */

#include <linux/kvm_host.h>
#include <linux/errno.h>
#include <linux/pagemap.h>

#include <asm/kvm_host.h>
#include <asm/asm-offsets.h>
#include <asm/irq.h>
#include <asm/sysinfo.h>

#include "kvm-s390.h"
#include "gaccess.h"
#include "trace.h"
#include "trace-s390.h"

u8 kvm_s390_get_ilen(struct kvm_vcpu *vcpu)
{
	struct kvm_s390_sie_block *sie_block = vcpu->arch.sie_block;
	u8 ilen = 0;

	switch (vcpu->arch.sie_block->icptcode) {
	case ICPT_INST:
	case ICPT_INSTPROGI:
	case ICPT_OPEREXC:
	case ICPT_PARTEXEC:
	case ICPT_IOINST:
		/* instruction only stored for these icptcodes */
		ilen = insn_length(vcpu->arch.sie_block->ipa >> 8);
		/* Use the length of the EXECUTE instruction if necessary */
		if (sie_block->icptstatus & 1) {
			ilen = (sie_block->icptstatus >> 4) & 0x6;
			if (!ilen)
				ilen = 4;
		}
		break;
	case ICPT_PROGI:
		/* bit 1+2 of pgmilc are the ilc, so we directly get ilen */
		ilen = vcpu->arch.sie_block->pgmilc & 0x6;
		break;
	}
	return ilen;
}

static int handle_stop(struct kvm_vcpu *vcpu)
{
	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
	int rc = 0;
	uint8_t flags, stop_pending;

	vcpu->stat.exit_stop_request++;

	/* delay the stop if any non-stop irq is pending */
	if (kvm_s390_vcpu_has_irq(vcpu, 1))
		return 0;

	/* avoid races with the injection/SIGP STOP code */
	spin_lock(&li->lock);
	flags = li->irq.stop.flags;
	stop_pending = kvm_s390_is_stop_irq_pending(vcpu);
	spin_unlock(&li->lock);

	trace_kvm_s390_stop_request(stop_pending, flags);
	if (!stop_pending)
		return 0;

	if (flags & KVM_S390_STOP_FLAG_STORE_STATUS) {
		rc = kvm_s390_vcpu_store_status(vcpu,
						KVM_S390_STORE_STATUS_NOADDR);
		if (rc)
			return rc;
	}

	if (!kvm_s390_user_cpu_state_ctrl(vcpu->kvm))
		kvm_s390_vcpu_stop(vcpu);
	return -EOPNOTSUPP;
}

static int handle_validity(struct kvm_vcpu *vcpu)
{
	int viwhy = vcpu->arch.sie_block->ipb >> 16;

	vcpu->stat.exit_validity++;
	trace_kvm_s390_intercept_validity(vcpu, viwhy);
	KVM_EVENT(3, "validity intercept 0x%x for pid %u (kvm 0x%pK)", viwhy,
		  current->pid, vcpu->kvm);

	/* do not warn on invalid runtime instrumentation mode */
	WARN_ONCE(viwhy != 0x44, "kvm: unhandled validity intercept 0x%x\n",
		  viwhy);
	return -EINVAL;
}

static int handle_instruction(struct kvm_vcpu *vcpu)
{
	vcpu->stat.exit_instruction++;
	trace_kvm_s390_intercept_instruction(vcpu,
					     vcpu->arch.sie_block->ipa,
					     vcpu->arch.sie_block->ipb);

	switch (vcpu->arch.sie_block->ipa >> 8) {
	case 0x01:
		return kvm_s390_handle_01(vcpu);
	case 0x82:
		return kvm_s390_handle_lpsw(vcpu);
	case 0x83:
		return kvm_s390_handle_diag(vcpu);
	case 0xaa:
		return kvm_s390_handle_aa(vcpu);
	case 0xae:
		return kvm_s390_handle_sigp(vcpu);
	case 0xb2:
		return kvm_s390_handle_b2(vcpu);
	case 0xb6:
		return kvm_s390_handle_stctl(vcpu);
	case 0xb7:
		return kvm_s390_handle_lctl(vcpu);
	case 0xb9:
		return kvm_s390_handle_b9(vcpu);
	case 0xe3:
		return kvm_s390_handle_e3(vcpu);
	case 0xe5:
		return kvm_s390_handle_e5(vcpu);
	case 0xeb:
		return kvm_s390_handle_eb(vcpu);
	default:
		return -EOPNOTSUPP;
	}
}

static int inject_prog_on_prog_intercept(struct kvm_vcpu *vcpu)
{
	struct kvm_s390_pgm_info pgm_info = {
		.code = vcpu->arch.sie_block->iprcc,
		/* the PSW has already been rewound */
		.flags = KVM_S390_PGM_FLAGS_NO_REWIND,
	};

	switch (vcpu->arch.sie_block->iprcc & ~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:
		pgm_info.trans_exc_code = vcpu->arch.sie_block->tecmc;
		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:
		pgm_info.exc_access_id = vcpu->arch.sie_block->eai;
		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:
		pgm_info.trans_exc_code = vcpu->arch.sie_block->tecmc;
		pgm_info.exc_access_id  = vcpu->arch.sie_block->eai;
		pgm_info.op_access_id  = vcpu->arch.sie_block->oai;
		break;
	case PGM_MONITOR:
		pgm_info.mon_class_nr = vcpu->arch.sie_block->mcn;
		pgm_info.mon_code = vcpu->arch.sie_block->tecmc;
		break;
	case PGM_VECTOR_PROCESSING:
	case PGM_DATA:
		pgm_info.data_exc_code = vcpu->arch.sie_block->dxc;
		break;
	case PGM_PROTECTION:
		pgm_info.trans_exc_code = vcpu->arch.sie_block->tecmc;
		pgm_info.exc_access_id  = vcpu->arch.sie_block->eai;
		break;
	default:
		break;
	}

	if (vcpu->arch.sie_block->iprcc & PGM_PER) {
		pgm_info.per_code = vcpu->arch.sie_block->perc;
		pgm_info.per_atmid = vcpu->arch.sie_block->peratmid;
		pgm_info.per_address = vcpu->arch.sie_block->peraddr;
		pgm_info.per_access_id = vcpu->arch.sie_block->peraid;
	}
	return kvm_s390_inject_prog_irq(vcpu, &pgm_info);
}

/*
 * restore ITDB to program-interruption TDB in guest lowcore
 * and set TX abort indication if required
*/
static int handle_itdb(struct kvm_vcpu *vcpu)
{
	struct kvm_s390_itdb *itdb;
	int rc;

	if (!IS_TE_ENABLED(vcpu) || !IS_ITDB_VALID(vcpu))
		return 0;
	if (current->thread.per_flags & PER_FLAG_NO_TE)
		return 0;
	itdb = (struct kvm_s390_itdb *)vcpu->arch.sie_block->itdba;
	rc = write_guest_lc(vcpu, __LC_PGM_TDB, itdb, sizeof(*itdb));
	if (rc)
		return rc;
	memset(itdb, 0, sizeof(*itdb));

	return 0;
}

#define per_event(vcpu) (vcpu->arch.sie_block->iprcc & PGM_PER)

static int handle_prog(struct kvm_vcpu *vcpu)
{
	psw_t psw;
	int rc;

	vcpu->stat.exit_program_interruption++;

	if (guestdbg_enabled(vcpu) && per_event(vcpu)) {
		rc = kvm_s390_handle_per_event(vcpu);
		if (rc)
			return rc;
		/* the interrupt might have been filtered out completely */
		if (vcpu->arch.sie_block->iprcc == 0)
			return 0;
	}

	trace_kvm_s390_intercept_prog(vcpu, vcpu->arch.sie_block->iprcc);
	if (vcpu->arch.sie_block->iprcc == PGM_SPECIFICATION) {
		rc = read_guest_lc(vcpu, __LC_PGM_NEW_PSW, &psw, sizeof(psw_t));
		if (rc)
			return rc;
		/* Avoid endless loops of specification exceptions */
		if (!is_valid_psw(&psw))
			return -EOPNOTSUPP;
	}
	rc = handle_itdb(vcpu);
	if (rc)
		return rc;

	return inject_prog_on_prog_intercept(vcpu);
}

/**
 * handle_external_interrupt - used for external interruption interceptions
 *
 * This interception only occurs if the CPUSTAT_EXT_INT bit was set, or if
 * the new PSW does not have external interrupts disabled. In the first case,
 * we've got to deliver the interrupt manually, and in the second case, we
 * drop to userspace to handle the situation there.
 */
static int handle_external_interrupt(struct kvm_vcpu *vcpu)
{
	u16 eic = vcpu->arch.sie_block->eic;
	struct kvm_s390_irq irq;
	psw_t newpsw;
	int rc;

	vcpu->stat.exit_external_interrupt++;

	rc = read_guest_lc(vcpu, __LC_EXT_NEW_PSW, &newpsw, sizeof(psw_t));
	if (rc)
		return rc;
	/* We can not handle clock comparator or timer interrupt with bad PSW */
	if ((eic == EXT_IRQ_CLK_COMP || eic == EXT_IRQ_CPU_TIMER) &&
	    (newpsw.mask & PSW_MASK_EXT))
		return -EOPNOTSUPP;

	switch (eic) {
	case EXT_IRQ_CLK_COMP:
		irq.type = KVM_S390_INT_CLOCK_COMP;
		break;
	case EXT_IRQ_CPU_TIMER:
		irq.type = KVM_S390_INT_CPU_TIMER;
		break;
	case EXT_IRQ_EXTERNAL_CALL:
		irq.type = KVM_S390_INT_EXTERNAL_CALL;
		irq.u.extcall.code = vcpu->arch.sie_block->extcpuaddr;
		rc = kvm_s390_inject_vcpu(vcpu, &irq);
		/* ignore if another external call is already pending */
		if (rc == -EBUSY)
			return 0;
		return rc;
	default:
		return -EOPNOTSUPP;
	}

	return kvm_s390_inject_vcpu(vcpu, &irq);
}

/**
 * Handle MOVE PAGE partial execution interception.
 *
 * This interception can only happen for guests with DAT disabled and
 * addresses that are currently not mapped in the host. Thus we try to
 * set up the mappings for the corresponding user pages here (or throw
 * addressing exceptions in case of illegal guest addresses).
 */
static int handle_mvpg_pei(struct kvm_vcpu *vcpu)
{
	unsigned long srcaddr, dstaddr;
	int reg1, reg2, rc;

	kvm_s390_get_regs_rre(vcpu, &reg1, &reg2);

	/* Make sure that the source is paged-in */
	rc = guest_translate_address(vcpu, vcpu->run->s.regs.gprs[reg2],
				     reg2, &srcaddr, GACC_FETCH);
	if (rc)
		return kvm_s390_inject_prog_cond(vcpu, rc);
	rc = kvm_arch_fault_in_page(vcpu, srcaddr, 0);
	if (rc != 0)
		return rc;

	/* Make sure that the destination is paged-in */
	rc = guest_translate_address(vcpu, vcpu->run->s.regs.gprs[reg1],
				     reg1, &dstaddr, GACC_STORE);
	if (rc)
		return kvm_s390_inject_prog_cond(vcpu, rc);
	rc = kvm_arch_fault_in_page(vcpu, dstaddr, 1);
	if (rc != 0)
		return rc;

	kvm_s390_retry_instr(vcpu);

	return 0;
}

static int handle_partial_execution(struct kvm_vcpu *vcpu)
{
	vcpu->stat.exit_pei++;

	if (vcpu->arch.sie_block->ipa == 0xb254)	/* MVPG */
		return handle_mvpg_pei(vcpu);
	if (vcpu->arch.sie_block->ipa >> 8 == 0xae)	/* SIGP */
		return kvm_s390_handle_sigp_pei(vcpu);

	return -EOPNOTSUPP;
}

/*
 * Handle the sthyi instruction that provides the guest with system
 * information, like current CPU resources available at each level of
 * the machine.
 */
int handle_sthyi(struct kvm_vcpu *vcpu)
{
	int reg1, reg2, r = 0;
	u64 code, addr, cc = 0, rc = 0;
	struct sthyi_sctns *sctns = NULL;

	if (!test_kvm_facility(vcpu->kvm, 74))
		return kvm_s390_inject_program_int(vcpu, PGM_OPERATION);

	kvm_s390_get_regs_rre(vcpu, &reg1, &reg2);
	code = vcpu->run->s.regs.gprs[reg1];
	addr = vcpu->run->s.regs.gprs[reg2];

	vcpu->stat.instruction_sthyi++;
	VCPU_EVENT(vcpu, 3, "STHYI: fc: %llu addr: 0x%016llx", code, addr);
	trace_kvm_s390_handle_sthyi(vcpu, code, addr);

	if (reg1 == reg2 || reg1 & 1 || reg2 & 1)
		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);

	if (code & 0xffff) {
		cc = 3;
		rc = 4;
		goto out;
	}

	if (addr & ~PAGE_MASK)
		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);

	sctns = (void *)get_zeroed_page(GFP_KERNEL);
	if (!sctns)
		return -ENOMEM;

	cc = sthyi_fill(sctns, &rc);

out:
	if (!cc) {
		r = write_guest(vcpu, addr, reg2, sctns, PAGE_SIZE);
		if (r) {
			free_page((unsigned long)sctns);
			return kvm_s390_inject_prog_cond(vcpu, r);
		}
	}

	free_page((unsigned long)sctns);
	vcpu->run->s.regs.gprs[reg2 + 1] = rc;
	kvm_s390_set_psw_cc(vcpu, cc);
	return r;
}

static int handle_operexc(struct kvm_vcpu *vcpu)
{
	psw_t oldpsw, newpsw;
	int rc;

	vcpu->stat.exit_operation_exception++;
	trace_kvm_s390_handle_operexc(vcpu, vcpu->arch.sie_block->ipa,
				      vcpu->arch.sie_block->ipb);

	if (vcpu->arch.sie_block->ipa == 0xb256)
		return handle_sthyi(vcpu);

	if (vcpu->arch.sie_block->ipa == 0 && vcpu->kvm->arch.user_instr0)
		return -EOPNOTSUPP;
	rc = read_guest_lc(vcpu, __LC_PGM_NEW_PSW, &newpsw, sizeof(psw_t));
	if (rc)
		return rc;
	/*
	 * Avoid endless loops of operation exceptions, if the pgm new
	 * PSW will cause a new operation exception.
	 * The heuristic checks if the pgm new psw is within 6 bytes before
	 * the faulting psw address (with same DAT, AS settings) and the
	 * new psw is not a wait psw and the fault was not triggered by
	 * problem state.
	 */
	oldpsw = vcpu->arch.sie_block->gpsw;
	if (oldpsw.addr - newpsw.addr <= 6 &&
	    !(newpsw.mask & PSW_MASK_WAIT) &&
	    !(oldpsw.mask & PSW_MASK_PSTATE) &&
	    (newpsw.mask & PSW_MASK_ASC) == (oldpsw.mask & PSW_MASK_ASC) &&
	    (newpsw.mask & PSW_MASK_DAT) == (oldpsw.mask & PSW_MASK_DAT))
		return -EOPNOTSUPP;

	return kvm_s390_inject_program_int(vcpu, PGM_OPERATION);
}

static int handle_pv_notification(struct kvm_vcpu *vcpu)
{
	return handle_instruction(vcpu);
}

int kvm_handle_sie_intercept(struct kvm_vcpu *vcpu)
{
	int rc, per_rc = 0;

	if (kvm_is_ucontrol(vcpu->kvm))
		return -EOPNOTSUPP;

	switch (vcpu->arch.sie_block->icptcode) {
	case ICPT_EXTREQ:
		vcpu->stat.exit_external_request++;
		return 0;
	case ICPT_IOREQ:
		vcpu->stat.exit_io_request++;
		return 0;
	case ICPT_INST:
		rc = handle_instruction(vcpu);
		break;
	case ICPT_PROGI:
		return handle_prog(vcpu);
	case ICPT_EXTINT:
		return handle_external_interrupt(vcpu);
	case ICPT_WAIT:
		return kvm_s390_handle_wait(vcpu);
	case ICPT_VALIDITY:
		return handle_validity(vcpu);
	case ICPT_STOP:
		return handle_stop(vcpu);
	case ICPT_OPEREXC:
		rc = handle_operexc(vcpu);
		break;
	case ICPT_PARTEXEC:
		rc = handle_partial_execution(vcpu);
		break;
	case ICPT_KSS:
		rc = kvm_s390_skey_check_enable(vcpu);
		break;
	case ICPT_MCHKREQ:
	case ICPT_INT_ENABLE:
		/*
		 * PSW bit 13 or a CR (0, 6, 14) changed and we might
		 * now be able to deliver interrupts. The pre-run code
		 * will take care of this.
		 */
		rc = 0;
		break;
	case ICPT_PV_INSTR:
		rc = handle_instruction(vcpu);
		break;
	case ICPT_PV_NOTIFY:
		rc = handle_pv_notification(vcpu);
		break;
	default:
		return -EOPNOTSUPP;
	}

	/* process PER, also if the instrution is processed in user space */
	if (vcpu->arch.sie_block->icptstatus & 0x02 &&
	    (!rc || rc == -EOPNOTSUPP))
		per_rc = kvm_s390_handle_per_ifetch_icpt(vcpu);
	return per_rc ? per_rc : rc;
}