kvm-s390.c 102.6 KB
Newer Older
1
/*
2
 * hosting zSeries kernel virtual machines
3
 *
4
 * Copyright IBM Corp. 2008, 2009
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>
 *               Christian Borntraeger <borntraeger@de.ibm.com>
 *               Heiko Carstens <heiko.carstens@de.ibm.com>
13
 *               Christian Ehrhardt <ehrhardt@de.ibm.com>
14
 *               Jason J. Herne <jjherne@us.ibm.com>
15 16 17 18 19
 */

#include <linux/compiler.h>
#include <linux/err.h>
#include <linux/fs.h>
20
#include <linux/hrtimer.h>
21 22 23
#include <linux/init.h>
#include <linux/kvm.h>
#include <linux/kvm_host.h>
24
#include <linux/mman.h>
25
#include <linux/module.h>
26
#include <linux/moduleparam.h>
27
#include <linux/random.h>
28
#include <linux/slab.h>
29
#include <linux/timer.h>
30
#include <linux/vmalloc.h>
31
#include <linux/bitmap.h>
32
#include <linux/sched/signal.h>
33
#include <linux/string.h>
34

35
#include <asm/asm-offsets.h>
36
#include <asm/lowcore.h>
37
#include <asm/stp.h>
38
#include <asm/pgtable.h>
39
#include <asm/gmap.h>
40
#include <asm/nmi.h>
41
#include <asm/switch_to.h>
42
#include <asm/isc.h>
43
#include <asm/sclp.h>
44
#include <asm/cpacf.h>
45
#include <asm/timex.h>
46
#include "kvm-s390.h"
47 48
#include "gaccess.h"

49 50 51 52
#define KMSG_COMPONENT "kvm-s390"
#undef pr_fmt
#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt

53 54
#define CREATE_TRACE_POINTS
#include "trace.h"
55
#include "trace-s390.h"
56

57
#define MEM_OP_MAX_SIZE 65536	/* Maximum transfer size for KVM_S390_MEM_OP */
58 59 60
#define LOCAL_IRQS 32
#define VCPU_IRQS_MAX_BUF (sizeof(struct kvm_s390_irq) * \
			   (KVM_MAX_VCPUS + LOCAL_IRQS))
61

62 63 64 65
#define VCPU_STAT(x) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU

struct kvm_stats_debugfs_item debugfs_entries[] = {
	{ "userspace_handled", VCPU_STAT(exit_userspace) },
66
	{ "exit_null", VCPU_STAT(exit_null) },
67 68 69 70
	{ "exit_validity", VCPU_STAT(exit_validity) },
	{ "exit_stop_request", VCPU_STAT(exit_stop_request) },
	{ "exit_external_request", VCPU_STAT(exit_external_request) },
	{ "exit_external_interrupt", VCPU_STAT(exit_external_interrupt) },
71
	{ "exit_instruction", VCPU_STAT(exit_instruction) },
72
	{ "exit_pei", VCPU_STAT(exit_pei) },
73 74
	{ "exit_program_interruption", VCPU_STAT(exit_program_interruption) },
	{ "exit_instr_and_program_int", VCPU_STAT(exit_instr_and_program) },
75
	{ "exit_operation_exception", VCPU_STAT(exit_operation_exception) },
76
	{ "halt_successful_poll", VCPU_STAT(halt_successful_poll) },
77
	{ "halt_attempted_poll", VCPU_STAT(halt_attempted_poll) },
78
	{ "halt_poll_invalid", VCPU_STAT(halt_poll_invalid) },
79
	{ "halt_wakeup", VCPU_STAT(halt_wakeup) },
80
	{ "instruction_lctlg", VCPU_STAT(instruction_lctlg) },
81
	{ "instruction_lctl", VCPU_STAT(instruction_lctl) },
82 83
	{ "instruction_stctl", VCPU_STAT(instruction_stctl) },
	{ "instruction_stctg", VCPU_STAT(instruction_stctg) },
84
	{ "deliver_emergency_signal", VCPU_STAT(deliver_emergency_signal) },
85
	{ "deliver_external_call", VCPU_STAT(deliver_external_call) },
86 87 88 89 90 91 92
	{ "deliver_service_signal", VCPU_STAT(deliver_service_signal) },
	{ "deliver_virtio_interrupt", VCPU_STAT(deliver_virtio_interrupt) },
	{ "deliver_stop_signal", VCPU_STAT(deliver_stop_signal) },
	{ "deliver_prefix_signal", VCPU_STAT(deliver_prefix_signal) },
	{ "deliver_restart_signal", VCPU_STAT(deliver_restart_signal) },
	{ "deliver_program_interruption", VCPU_STAT(deliver_program_int) },
	{ "exit_wait_state", VCPU_STAT(exit_wait_state) },
93
	{ "instruction_pfmf", VCPU_STAT(instruction_pfmf) },
94 95 96 97 98
	{ "instruction_stidp", VCPU_STAT(instruction_stidp) },
	{ "instruction_spx", VCPU_STAT(instruction_spx) },
	{ "instruction_stpx", VCPU_STAT(instruction_stpx) },
	{ "instruction_stap", VCPU_STAT(instruction_stap) },
	{ "instruction_storage_key", VCPU_STAT(instruction_storage_key) },
99
	{ "instruction_ipte_interlock", VCPU_STAT(instruction_ipte_interlock) },
100 101
	{ "instruction_stsch", VCPU_STAT(instruction_stsch) },
	{ "instruction_chsc", VCPU_STAT(instruction_chsc) },
102
	{ "instruction_essa", VCPU_STAT(instruction_essa) },
103 104
	{ "instruction_stsi", VCPU_STAT(instruction_stsi) },
	{ "instruction_stfl", VCPU_STAT(instruction_stfl) },
105
	{ "instruction_tprot", VCPU_STAT(instruction_tprot) },
J
Janosch Frank 已提交
106
	{ "instruction_sthyi", VCPU_STAT(instruction_sthyi) },
107
	{ "instruction_sie", VCPU_STAT(instruction_sie) },
108
	{ "instruction_sigp_sense", VCPU_STAT(instruction_sigp_sense) },
109
	{ "instruction_sigp_sense_running", VCPU_STAT(instruction_sigp_sense_running) },
110
	{ "instruction_sigp_external_call", VCPU_STAT(instruction_sigp_external_call) },
111
	{ "instruction_sigp_emergency", VCPU_STAT(instruction_sigp_emergency) },
112 113
	{ "instruction_sigp_cond_emergency", VCPU_STAT(instruction_sigp_cond_emergency) },
	{ "instruction_sigp_start", VCPU_STAT(instruction_sigp_start) },
114
	{ "instruction_sigp_stop", VCPU_STAT(instruction_sigp_stop) },
115 116
	{ "instruction_sigp_stop_store_status", VCPU_STAT(instruction_sigp_stop_store_status) },
	{ "instruction_sigp_store_status", VCPU_STAT(instruction_sigp_store_status) },
117
	{ "instruction_sigp_store_adtl_status", VCPU_STAT(instruction_sigp_store_adtl_status) },
118 119 120
	{ "instruction_sigp_set_arch", VCPU_STAT(instruction_sigp_arch) },
	{ "instruction_sigp_set_prefix", VCPU_STAT(instruction_sigp_prefix) },
	{ "instruction_sigp_restart", VCPU_STAT(instruction_sigp_restart) },
121 122 123
	{ "instruction_sigp_cpu_reset", VCPU_STAT(instruction_sigp_cpu_reset) },
	{ "instruction_sigp_init_cpu_reset", VCPU_STAT(instruction_sigp_init_cpu_reset) },
	{ "instruction_sigp_unknown", VCPU_STAT(instruction_sigp_unknown) },
124
	{ "diagnose_10", VCPU_STAT(diagnose_10) },
125
	{ "diagnose_44", VCPU_STAT(diagnose_44) },
126
	{ "diagnose_9c", VCPU_STAT(diagnose_9c) },
127 128 129
	{ "diagnose_258", VCPU_STAT(diagnose_258) },
	{ "diagnose_308", VCPU_STAT(diagnose_308) },
	{ "diagnose_500", VCPU_STAT(diagnose_500) },
130 131 132
	{ NULL }
};

133 134 135 136 137 138
struct kvm_s390_tod_clock_ext {
	__u8 epoch_idx;
	__u64 tod;
	__u8 reserved[7];
} __packed;

139 140 141 142 143
/* allow nested virtualization in KVM (if enabled by user space) */
static int nested;
module_param(nested, int, S_IRUGO);
MODULE_PARM_DESC(nested, "Nested virtualization support");

144
/* upper facilities limit for kvm */
145
unsigned long kvm_s390_fac_list_mask[16] = { FACILITIES_KVM };
146

147
unsigned long kvm_s390_fac_list_mask_size(void)
148
{
149 150
	BUILD_BUG_ON(ARRAY_SIZE(kvm_s390_fac_list_mask) > S390_ARCH_FAC_MASK_SIZE_U64);
	return ARRAY_SIZE(kvm_s390_fac_list_mask);
151 152
}

153 154
/* available cpu features supported by kvm */
static DECLARE_BITMAP(kvm_s390_available_cpu_feat, KVM_S390_VM_CPU_FEAT_NR_BITS);
155 156
/* available subfunctions indicated via query / "test bit" */
static struct kvm_s390_vm_cpu_subfunc kvm_s390_available_subfunc;
157

158
static struct gmap_notifier gmap_notifier;
159
static struct gmap_notifier vsie_gmap_notifier;
160
debug_info_t *kvm_s390_dbf;
161

162
/* Section: not file related */
163
int kvm_arch_hardware_enable(void)
164 165
{
	/* every s390 is virtualization enabled ;-) */
166
	return 0;
167 168
}

169 170
static void kvm_gmap_notifier(struct gmap *gmap, unsigned long start,
			      unsigned long end);
171

172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189
/*
 * This callback is executed during stop_machine(). All CPUs are therefore
 * temporarily stopped. In order not to change guest behavior, we have to
 * disable preemption whenever we touch the epoch of kvm and the VCPUs,
 * so a CPU won't be stopped while calculating with the epoch.
 */
static int kvm_clock_sync(struct notifier_block *notifier, unsigned long val,
			  void *v)
{
	struct kvm *kvm;
	struct kvm_vcpu *vcpu;
	int i;
	unsigned long long *delta = v;

	list_for_each_entry(kvm, &vm_list, vm_list) {
		kvm->arch.epoch -= *delta;
		kvm_for_each_vcpu(i, vcpu, kvm) {
			vcpu->arch.sie_block->epoch -= *delta;
190 191
			if (vcpu->arch.cputm_enabled)
				vcpu->arch.cputm_start += *delta;
192 193
			if (vcpu->arch.vsie_block)
				vcpu->arch.vsie_block->epoch -= *delta;
194 195 196 197 198 199 200 201 202
		}
	}
	return NOTIFY_OK;
}

static struct notifier_block kvm_clock_notifier = {
	.notifier_call = kvm_clock_sync,
};

203 204
int kvm_arch_hardware_setup(void)
{
205
	gmap_notifier.notifier_call = kvm_gmap_notifier;
206
	gmap_register_pte_notifier(&gmap_notifier);
207 208
	vsie_gmap_notifier.notifier_call = kvm_s390_vsie_gmap_notifier;
	gmap_register_pte_notifier(&vsie_gmap_notifier);
209 210
	atomic_notifier_chain_register(&s390_epoch_delta_notifier,
				       &kvm_clock_notifier);
211 212 213 214 215
	return 0;
}

void kvm_arch_hardware_unsetup(void)
{
216
	gmap_unregister_pte_notifier(&gmap_notifier);
217
	gmap_unregister_pte_notifier(&vsie_gmap_notifier);
218 219
	atomic_notifier_chain_unregister(&s390_epoch_delta_notifier,
					 &kvm_clock_notifier);
220 221
}

222 223 224 225 226
static void allow_cpu_feat(unsigned long nr)
{
	set_bit_inv(nr, kvm_s390_available_cpu_feat);
}

227 228 229
static inline int plo_test_bit(unsigned char nr)
{
	register unsigned long r0 asm("0") = (unsigned long) nr | 0x100;
230
	int cc;
231 232 233 234 235 236 237 238 239 240 241 242

	asm volatile(
		/* Parameter registers are ignored for "test bit" */
		"	plo	0,0,0,0(0)\n"
		"	ipm	%0\n"
		"	srl	%0,28\n"
		: "=d" (cc)
		: "d" (r0)
		: "cc");
	return cc == 0;
}

243 244
static void kvm_s390_cpu_feat_init(void)
{
245 246 247 248 249 250 251 252
	int i;

	for (i = 0; i < 256; ++i) {
		if (plo_test_bit(i))
			kvm_s390_available_subfunc.plo[i >> 3] |= 0x80 >> (i & 7);
	}

	if (test_facility(28)) /* TOD-clock steering */
253 254 255
		ptff(kvm_s390_available_subfunc.ptff,
		     sizeof(kvm_s390_available_subfunc.ptff),
		     PTFF_QAF);
256 257

	if (test_facility(17)) { /* MSA */
258 259 260 261 262 263 264 265 266 267
		__cpacf_query(CPACF_KMAC, (cpacf_mask_t *)
			      kvm_s390_available_subfunc.kmac);
		__cpacf_query(CPACF_KMC, (cpacf_mask_t *)
			      kvm_s390_available_subfunc.kmc);
		__cpacf_query(CPACF_KM, (cpacf_mask_t *)
			      kvm_s390_available_subfunc.km);
		__cpacf_query(CPACF_KIMD, (cpacf_mask_t *)
			      kvm_s390_available_subfunc.kimd);
		__cpacf_query(CPACF_KLMD, (cpacf_mask_t *)
			      kvm_s390_available_subfunc.klmd);
268 269
	}
	if (test_facility(76)) /* MSA3 */
270 271
		__cpacf_query(CPACF_PCKMO, (cpacf_mask_t *)
			      kvm_s390_available_subfunc.pckmo);
272
	if (test_facility(77)) { /* MSA4 */
273 274 275 276 277 278 279 280
		__cpacf_query(CPACF_KMCTR, (cpacf_mask_t *)
			      kvm_s390_available_subfunc.kmctr);
		__cpacf_query(CPACF_KMF, (cpacf_mask_t *)
			      kvm_s390_available_subfunc.kmf);
		__cpacf_query(CPACF_KMO, (cpacf_mask_t *)
			      kvm_s390_available_subfunc.kmo);
		__cpacf_query(CPACF_PCC, (cpacf_mask_t *)
			      kvm_s390_available_subfunc.pcc);
281 282
	}
	if (test_facility(57)) /* MSA5 */
283
		__cpacf_query(CPACF_PRNO, (cpacf_mask_t *)
284
			      kvm_s390_available_subfunc.ppno);
285

286 287 288 289
	if (test_facility(146)) /* MSA8 */
		__cpacf_query(CPACF_KMA, (cpacf_mask_t *)
			      kvm_s390_available_subfunc.kma);

290 291
	if (MACHINE_HAS_ESOP)
		allow_cpu_feat(KVM_S390_VM_CPU_FEAT_ESOP);
292 293 294 295 296
	/*
	 * We need SIE support, ESOP (PROT_READ protection for gmap_shadow),
	 * 64bit SCAO (SCA passthrough) and IDTE (for gmap_shadow unshadowing).
	 */
	if (!sclp.has_sief2 || !MACHINE_HAS_ESOP || !sclp.has_64bscao ||
297
	    !test_facility(3) || !nested)
298 299
		return;
	allow_cpu_feat(KVM_S390_VM_CPU_FEAT_SIEF2);
300 301
	if (sclp.has_64bscao)
		allow_cpu_feat(KVM_S390_VM_CPU_FEAT_64BSCAO);
302 303
	if (sclp.has_siif)
		allow_cpu_feat(KVM_S390_VM_CPU_FEAT_SIIF);
304 305
	if (sclp.has_gpere)
		allow_cpu_feat(KVM_S390_VM_CPU_FEAT_GPERE);
306 307
	if (sclp.has_gsls)
		allow_cpu_feat(KVM_S390_VM_CPU_FEAT_GSLS);
308 309
	if (sclp.has_ib)
		allow_cpu_feat(KVM_S390_VM_CPU_FEAT_IB);
310 311
	if (sclp.has_cei)
		allow_cpu_feat(KVM_S390_VM_CPU_FEAT_CEI);
312 313
	if (sclp.has_ibs)
		allow_cpu_feat(KVM_S390_VM_CPU_FEAT_IBS);
314 315
	if (sclp.has_kss)
		allow_cpu_feat(KVM_S390_VM_CPU_FEAT_KSS);
316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333
	/*
	 * KVM_S390_VM_CPU_FEAT_SKEY: Wrong shadow of PTE.I bits will make
	 * all skey handling functions read/set the skey from the PGSTE
	 * instead of the real storage key.
	 *
	 * KVM_S390_VM_CPU_FEAT_CMMA: Wrong shadow of PTE.I bits will make
	 * pages being detected as preserved although they are resident.
	 *
	 * KVM_S390_VM_CPU_FEAT_PFMFI: Wrong shadow of PTE.I bits will
	 * have the same effect as for KVM_S390_VM_CPU_FEAT_SKEY.
	 *
	 * For KVM_S390_VM_CPU_FEAT_SKEY, KVM_S390_VM_CPU_FEAT_CMMA and
	 * KVM_S390_VM_CPU_FEAT_PFMFI, all PTE.I and PGSTE bits have to be
	 * correctly shadowed. We can do that for the PGSTE but not for PTE.I.
	 *
	 * KVM_S390_VM_CPU_FEAT_SIGPIF: Wrong SCB addresses in the SCA. We
	 * cannot easily shadow the SCA because of the ipte lock.
	 */
334 335
}

336 337
int kvm_arch_init(void *opaque)
{
338 339 340 341 342 343 344 345 346
	kvm_s390_dbf = debug_register("kvm-trace", 32, 1, 7 * sizeof(long));
	if (!kvm_s390_dbf)
		return -ENOMEM;

	if (debug_register_view(kvm_s390_dbf, &debug_sprintf_view)) {
		debug_unregister(kvm_s390_dbf);
		return -ENOMEM;
	}

347 348
	kvm_s390_cpu_feat_init();

349 350
	/* Register floating interrupt controller interface. */
	return kvm_register_device_ops(&kvm_flic_ops, KVM_DEV_TYPE_FLIC);
351 352
}

353 354 355 356 357
void kvm_arch_exit(void)
{
	debug_unregister(kvm_s390_dbf);
}

358 359 360 361 362 363 364 365 366
/* Section: device related */
long kvm_arch_dev_ioctl(struct file *filp,
			unsigned int ioctl, unsigned long arg)
{
	if (ioctl == KVM_S390_ENABLE_SIE)
		return s390_enable_sie();
	return -EINVAL;
}

367
int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
368
{
369 370
	int r;

371
	switch (ext) {
372
	case KVM_CAP_S390_PSW:
373
	case KVM_CAP_S390_GMAP:
374
	case KVM_CAP_SYNC_MMU:
375 376 377
#ifdef CONFIG_KVM_S390_UCONTROL
	case KVM_CAP_S390_UCONTROL:
#endif
378
	case KVM_CAP_ASYNC_PF:
379
	case KVM_CAP_SYNC_REGS:
380
	case KVM_CAP_ONE_REG:
381
	case KVM_CAP_ENABLE_CAP:
382
	case KVM_CAP_S390_CSS_SUPPORT:
C
Cornelia Huck 已提交
383
	case KVM_CAP_IOEVENTFD:
384
	case KVM_CAP_DEVICE_CTRL:
385
	case KVM_CAP_ENABLE_CAP_VM:
386
	case KVM_CAP_S390_IRQCHIP:
387
	case KVM_CAP_VM_ATTRIBUTES:
388
	case KVM_CAP_MP_STATE:
389
	case KVM_CAP_IMMEDIATE_EXIT:
390
	case KVM_CAP_S390_INJECT_IRQ:
391
	case KVM_CAP_S390_USER_SIGP:
392
	case KVM_CAP_S390_USER_STSI:
393
	case KVM_CAP_S390_SKEYS:
394
	case KVM_CAP_S390_IRQ_STATE:
395
	case KVM_CAP_S390_USER_INSTR0:
396
	case KVM_CAP_S390_CMMA_MIGRATION:
397
	case KVM_CAP_S390_AIS:
398 399
		r = 1;
		break;
400 401 402
	case KVM_CAP_S390_MEM_OP:
		r = MEM_OP_MAX_SIZE;
		break;
403 404
	case KVM_CAP_NR_VCPUS:
	case KVM_CAP_MAX_VCPUS:
405
		r = KVM_S390_BSCA_CPU_SLOTS;
406 407 408
		if (!kvm_s390_use_sca_entries())
			r = KVM_MAX_VCPUS;
		else if (sclp.has_esca && sclp.has_64bscao)
409
			r = KVM_S390_ESCA_CPU_SLOTS;
410
		break;
411 412 413
	case KVM_CAP_NR_MEMSLOTS:
		r = KVM_USER_MEM_SLOTS;
		break;
414
	case KVM_CAP_S390_COW:
415
		r = MACHINE_HAS_ESOP;
416
		break;
417 418 419
	case KVM_CAP_S390_VECTOR_REGISTERS:
		r = MACHINE_HAS_VX;
		break;
420 421 422
	case KVM_CAP_S390_RI:
		r = test_facility(64);
		break;
F
Fan Zhang 已提交
423 424 425
	case KVM_CAP_S390_GS:
		r = test_facility(133);
		break;
426
	default:
427
		r = 0;
428
	}
429
	return r;
430 431
}

432 433 434 435 436 437 438 439 440 441 442 443
static void kvm_s390_sync_dirty_log(struct kvm *kvm,
					struct kvm_memory_slot *memslot)
{
	gfn_t cur_gfn, last_gfn;
	unsigned long address;
	struct gmap *gmap = kvm->arch.gmap;

	/* Loop over all guest pages */
	last_gfn = memslot->base_gfn + memslot->npages;
	for (cur_gfn = memslot->base_gfn; cur_gfn <= last_gfn; cur_gfn++) {
		address = gfn_to_hva_memslot(memslot, cur_gfn);

444
		if (test_and_clear_guest_dirty(gmap->mm, address))
445
			mark_page_dirty(kvm, cur_gfn);
446 447
		if (fatal_signal_pending(current))
			return;
448
		cond_resched();
449 450 451
	}
}

452
/* Section: vm related */
453 454
static void sca_del_vcpu(struct kvm_vcpu *vcpu);

455 456 457 458 459 460
/*
 * Get (and clear) the dirty memory log for a memory slot.
 */
int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
			       struct kvm_dirty_log *log)
{
461 462
	int r;
	unsigned long n;
463
	struct kvm_memslots *slots;
464 465 466
	struct kvm_memory_slot *memslot;
	int is_dirty = 0;

467 468 469
	if (kvm_is_ucontrol(kvm))
		return -EINVAL;

470 471 472 473 474 475
	mutex_lock(&kvm->slots_lock);

	r = -EINVAL;
	if (log->slot >= KVM_USER_MEM_SLOTS)
		goto out;

476 477
	slots = kvm_memslots(kvm);
	memslot = id_to_memslot(slots, log->slot);
478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495
	r = -ENOENT;
	if (!memslot->dirty_bitmap)
		goto out;

	kvm_s390_sync_dirty_log(kvm, memslot);
	r = kvm_get_dirty_log(kvm, log, &is_dirty);
	if (r)
		goto out;

	/* Clear the dirty log */
	if (is_dirty) {
		n = kvm_dirty_bitmap_bytes(memslot);
		memset(memslot->dirty_bitmap, 0, n);
	}
	r = 0;
out:
	mutex_unlock(&kvm->slots_lock);
	return r;
496 497
}

498 499 500 501 502 503 504 505 506 507
static void icpt_operexc_on_all_vcpus(struct kvm *kvm)
{
	unsigned int i;
	struct kvm_vcpu *vcpu;

	kvm_for_each_vcpu(i, vcpu, kvm) {
		kvm_s390_sync_request(KVM_REQ_ICPT_OPEREXC, vcpu);
	}
}

508 509 510 511 512 513 514 515
static int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap)
{
	int r;

	if (cap->flags)
		return -EINVAL;

	switch (cap->cap) {
516
	case KVM_CAP_S390_IRQCHIP:
517
		VM_EVENT(kvm, 3, "%s", "ENABLE: CAP_S390_IRQCHIP");
518 519 520
		kvm->arch.use_irqchip = 1;
		r = 0;
		break;
521
	case KVM_CAP_S390_USER_SIGP:
522
		VM_EVENT(kvm, 3, "%s", "ENABLE: CAP_S390_USER_SIGP");
523 524 525
		kvm->arch.user_sigp = 1;
		r = 0;
		break;
526
	case KVM_CAP_S390_VECTOR_REGISTERS:
527
		mutex_lock(&kvm->lock);
528
		if (kvm->created_vcpus) {
529 530
			r = -EBUSY;
		} else if (MACHINE_HAS_VX) {
531 532
			set_kvm_facility(kvm->arch.model.fac_mask, 129);
			set_kvm_facility(kvm->arch.model.fac_list, 129);
533 534 535 536
			if (test_facility(134)) {
				set_kvm_facility(kvm->arch.model.fac_mask, 134);
				set_kvm_facility(kvm->arch.model.fac_list, 134);
			}
537 538 539 540
			if (test_facility(135)) {
				set_kvm_facility(kvm->arch.model.fac_mask, 135);
				set_kvm_facility(kvm->arch.model.fac_list, 135);
			}
541 542 543
			r = 0;
		} else
			r = -EINVAL;
544
		mutex_unlock(&kvm->lock);
545 546
		VM_EVENT(kvm, 3, "ENABLE: CAP_S390_VECTOR_REGISTERS %s",
			 r ? "(not available)" : "(success)");
547
		break;
548 549 550
	case KVM_CAP_S390_RI:
		r = -EINVAL;
		mutex_lock(&kvm->lock);
551
		if (kvm->created_vcpus) {
552 553
			r = -EBUSY;
		} else if (test_facility(64)) {
554 555
			set_kvm_facility(kvm->arch.model.fac_mask, 64);
			set_kvm_facility(kvm->arch.model.fac_list, 64);
556 557 558 559 560 561
			r = 0;
		}
		mutex_unlock(&kvm->lock);
		VM_EVENT(kvm, 3, "ENABLE: CAP_S390_RI %s",
			 r ? "(not available)" : "(success)");
		break;
562 563 564 565 566 567 568 569 570 571 572 573 574
	case KVM_CAP_S390_AIS:
		mutex_lock(&kvm->lock);
		if (kvm->created_vcpus) {
			r = -EBUSY;
		} else {
			set_kvm_facility(kvm->arch.model.fac_mask, 72);
			set_kvm_facility(kvm->arch.model.fac_list, 72);
			r = 0;
		}
		mutex_unlock(&kvm->lock);
		VM_EVENT(kvm, 3, "ENABLE: AIS %s",
			 r ? "(not available)" : "(success)");
		break;
F
Fan Zhang 已提交
575 576 577 578 579 580 581 582 583 584 585 586 587 588
	case KVM_CAP_S390_GS:
		r = -EINVAL;
		mutex_lock(&kvm->lock);
		if (atomic_read(&kvm->online_vcpus)) {
			r = -EBUSY;
		} else if (test_facility(133)) {
			set_kvm_facility(kvm->arch.model.fac_mask, 133);
			set_kvm_facility(kvm->arch.model.fac_list, 133);
			r = 0;
		}
		mutex_unlock(&kvm->lock);
		VM_EVENT(kvm, 3, "ENABLE: CAP_S390_GS %s",
			 r ? "(not available)" : "(success)");
		break;
589
	case KVM_CAP_S390_USER_STSI:
590
		VM_EVENT(kvm, 3, "%s", "ENABLE: CAP_S390_USER_STSI");
591 592 593
		kvm->arch.user_stsi = 1;
		r = 0;
		break;
594 595 596 597 598 599
	case KVM_CAP_S390_USER_INSTR0:
		VM_EVENT(kvm, 3, "%s", "ENABLE: CAP_S390_USER_INSTR0");
		kvm->arch.user_instr0 = 1;
		icpt_operexc_on_all_vcpus(kvm);
		r = 0;
		break;
600 601 602 603 604 605 606
	default:
		r = -EINVAL;
		break;
	}
	return r;
}

607 608 609 610 611 612 613
static int kvm_s390_get_mem_control(struct kvm *kvm, struct kvm_device_attr *attr)
{
	int ret;

	switch (attr->attr) {
	case KVM_S390_VM_MEM_LIMIT_SIZE:
		ret = 0;
614
		VM_EVENT(kvm, 3, "QUERY: max guest memory: %lu bytes",
615 616
			 kvm->arch.mem_limit);
		if (put_user(kvm->arch.mem_limit, (u64 __user *)attr->addr))
617 618 619 620 621 622 623 624 625 626
			ret = -EFAULT;
		break;
	default:
		ret = -ENXIO;
		break;
	}
	return ret;
}

static int kvm_s390_set_mem_control(struct kvm *kvm, struct kvm_device_attr *attr)
627 628 629 630 631
{
	int ret;
	unsigned int idx;
	switch (attr->attr) {
	case KVM_S390_VM_MEM_ENABLE_CMMA:
632
		ret = -ENXIO;
633
		if (!sclp.has_cmma)
634 635
			break;

636
		ret = -EBUSY;
637
		VM_EVENT(kvm, 3, "%s", "ENABLE: CMMA support");
638
		mutex_lock(&kvm->lock);
639
		if (!kvm->created_vcpus) {
640 641 642 643 644 645
			kvm->arch.use_cmma = 1;
			ret = 0;
		}
		mutex_unlock(&kvm->lock);
		break;
	case KVM_S390_VM_MEM_CLR_CMMA:
646 647 648
		ret = -ENXIO;
		if (!sclp.has_cmma)
			break;
649 650 651 652
		ret = -EINVAL;
		if (!kvm->arch.use_cmma)
			break;

653
		VM_EVENT(kvm, 3, "%s", "RESET: CMMA states");
654 655
		mutex_lock(&kvm->lock);
		idx = srcu_read_lock(&kvm->srcu);
656
		s390_reset_cmma(kvm->arch.gmap->mm);
657 658 659 660
		srcu_read_unlock(&kvm->srcu, idx);
		mutex_unlock(&kvm->lock);
		ret = 0;
		break;
661 662 663 664 665 666 667 668 669
	case KVM_S390_VM_MEM_LIMIT_SIZE: {
		unsigned long new_limit;

		if (kvm_is_ucontrol(kvm))
			return -EINVAL;

		if (get_user(new_limit, (u64 __user *)attr->addr))
			return -EFAULT;

670 671
		if (kvm->arch.mem_limit != KVM_S390_NO_MEM_LIMIT &&
		    new_limit > kvm->arch.mem_limit)
672 673
			return -E2BIG;

674 675 676
		if (!new_limit)
			return -EINVAL;

677
		/* gmap_create takes last usable address */
678 679 680
		if (new_limit != KVM_S390_NO_MEM_LIMIT)
			new_limit -= 1;

681 682
		ret = -EBUSY;
		mutex_lock(&kvm->lock);
683
		if (!kvm->created_vcpus) {
684 685
			/* gmap_create will round the limit up */
			struct gmap *new = gmap_create(current->mm, new_limit);
686 687 688 689

			if (!new) {
				ret = -ENOMEM;
			} else {
690
				gmap_remove(kvm->arch.gmap);
691 692 693 694 695 696
				new->private = kvm;
				kvm->arch.gmap = new;
				ret = 0;
			}
		}
		mutex_unlock(&kvm->lock);
697 698 699
		VM_EVENT(kvm, 3, "SET: max guest address: %lu", new_limit);
		VM_EVENT(kvm, 3, "New guest asce: 0x%pK",
			 (void *) kvm->arch.gmap->asce);
700 701
		break;
	}
702 703 704 705 706 707 708
	default:
		ret = -ENXIO;
		break;
	}
	return ret;
}

709 710 711 712 713 714 715
static void kvm_s390_vcpu_crypto_setup(struct kvm_vcpu *vcpu);

static int kvm_s390_vm_set_crypto(struct kvm *kvm, struct kvm_device_attr *attr)
{
	struct kvm_vcpu *vcpu;
	int i;

716
	if (!test_kvm_facility(kvm, 76))
717 718 719 720 721 722 723 724 725
		return -EINVAL;

	mutex_lock(&kvm->lock);
	switch (attr->attr) {
	case KVM_S390_VM_CRYPTO_ENABLE_AES_KW:
		get_random_bytes(
			kvm->arch.crypto.crycb->aes_wrapping_key_mask,
			sizeof(kvm->arch.crypto.crycb->aes_wrapping_key_mask));
		kvm->arch.crypto.aes_kw = 1;
726
		VM_EVENT(kvm, 3, "%s", "ENABLE: AES keywrapping support");
727 728 729 730 731 732
		break;
	case KVM_S390_VM_CRYPTO_ENABLE_DEA_KW:
		get_random_bytes(
			kvm->arch.crypto.crycb->dea_wrapping_key_mask,
			sizeof(kvm->arch.crypto.crycb->dea_wrapping_key_mask));
		kvm->arch.crypto.dea_kw = 1;
733
		VM_EVENT(kvm, 3, "%s", "ENABLE: DEA keywrapping support");
734 735 736 737 738
		break;
	case KVM_S390_VM_CRYPTO_DISABLE_AES_KW:
		kvm->arch.crypto.aes_kw = 0;
		memset(kvm->arch.crypto.crycb->aes_wrapping_key_mask, 0,
			sizeof(kvm->arch.crypto.crycb->aes_wrapping_key_mask));
739
		VM_EVENT(kvm, 3, "%s", "DISABLE: AES keywrapping support");
740 741 742 743 744
		break;
	case KVM_S390_VM_CRYPTO_DISABLE_DEA_KW:
		kvm->arch.crypto.dea_kw = 0;
		memset(kvm->arch.crypto.crycb->dea_wrapping_key_mask, 0,
			sizeof(kvm->arch.crypto.crycb->dea_wrapping_key_mask));
745
		VM_EVENT(kvm, 3, "%s", "DISABLE: DEA keywrapping support");
746 747 748 749 750 751 752 753 754 755 756 757 758 759
		break;
	default:
		mutex_unlock(&kvm->lock);
		return -ENXIO;
	}

	kvm_for_each_vcpu(i, vcpu, kvm) {
		kvm_s390_vcpu_crypto_setup(vcpu);
		exit_sie(vcpu);
	}
	mutex_unlock(&kvm->lock);
	return 0;
}

760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882
static void kvm_s390_sync_request_broadcast(struct kvm *kvm, int req)
{
	int cx;
	struct kvm_vcpu *vcpu;

	kvm_for_each_vcpu(cx, vcpu, kvm)
		kvm_s390_sync_request(req, vcpu);
}

/*
 * Must be called with kvm->srcu held to avoid races on memslots, and with
 * kvm->lock to avoid races with ourselves and kvm_s390_vm_stop_migration.
 */
static int kvm_s390_vm_start_migration(struct kvm *kvm)
{
	struct kvm_s390_migration_state *mgs;
	struct kvm_memory_slot *ms;
	/* should be the only one */
	struct kvm_memslots *slots;
	unsigned long ram_pages;
	int slotnr;

	/* migration mode already enabled */
	if (kvm->arch.migration_state)
		return 0;

	slots = kvm_memslots(kvm);
	if (!slots || !slots->used_slots)
		return -EINVAL;

	mgs = kzalloc(sizeof(*mgs), GFP_KERNEL);
	if (!mgs)
		return -ENOMEM;
	kvm->arch.migration_state = mgs;

	if (kvm->arch.use_cmma) {
		/*
		 * Get the last slot. They should be sorted by base_gfn, so the
		 * last slot is also the one at the end of the address space.
		 * We have verified above that at least one slot is present.
		 */
		ms = slots->memslots + slots->used_slots - 1;
		/* round up so we only use full longs */
		ram_pages = roundup(ms->base_gfn + ms->npages, BITS_PER_LONG);
		/* allocate enough bytes to store all the bits */
		mgs->pgste_bitmap = vmalloc(ram_pages / 8);
		if (!mgs->pgste_bitmap) {
			kfree(mgs);
			kvm->arch.migration_state = NULL;
			return -ENOMEM;
		}

		mgs->bitmap_size = ram_pages;
		atomic64_set(&mgs->dirty_pages, ram_pages);
		/* mark all the pages in active slots as dirty */
		for (slotnr = 0; slotnr < slots->used_slots; slotnr++) {
			ms = slots->memslots + slotnr;
			bitmap_set(mgs->pgste_bitmap, ms->base_gfn, ms->npages);
		}

		kvm_s390_sync_request_broadcast(kvm, KVM_REQ_START_MIGRATION);
	}
	return 0;
}

/*
 * Must be called with kvm->lock to avoid races with ourselves and
 * kvm_s390_vm_start_migration.
 */
static int kvm_s390_vm_stop_migration(struct kvm *kvm)
{
	struct kvm_s390_migration_state *mgs;

	/* migration mode already disabled */
	if (!kvm->arch.migration_state)
		return 0;
	mgs = kvm->arch.migration_state;
	kvm->arch.migration_state = NULL;

	if (kvm->arch.use_cmma) {
		kvm_s390_sync_request_broadcast(kvm, KVM_REQ_STOP_MIGRATION);
		vfree(mgs->pgste_bitmap);
	}
	kfree(mgs);
	return 0;
}

static int kvm_s390_vm_set_migration(struct kvm *kvm,
				     struct kvm_device_attr *attr)
{
	int idx, res = -ENXIO;

	mutex_lock(&kvm->lock);
	switch (attr->attr) {
	case KVM_S390_VM_MIGRATION_START:
		idx = srcu_read_lock(&kvm->srcu);
		res = kvm_s390_vm_start_migration(kvm);
		srcu_read_unlock(&kvm->srcu, idx);
		break;
	case KVM_S390_VM_MIGRATION_STOP:
		res = kvm_s390_vm_stop_migration(kvm);
		break;
	default:
		break;
	}
	mutex_unlock(&kvm->lock);

	return res;
}

static int kvm_s390_vm_get_migration(struct kvm *kvm,
				     struct kvm_device_attr *attr)
{
	u64 mig = (kvm->arch.migration_state != NULL);

	if (attr->attr != KVM_S390_VM_MIGRATION_STATUS)
		return -ENXIO;

	if (copy_to_user((void __user *)attr->addr, &mig, sizeof(mig)))
		return -EFAULT;
	return 0;
}

883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902
static int kvm_s390_set_tod_ext(struct kvm *kvm, struct kvm_device_attr *attr)
{
	struct kvm_s390_vm_tod_clock gtod;

	if (copy_from_user(&gtod, (void __user *)attr->addr, sizeof(gtod)))
		return -EFAULT;

	if (test_kvm_facility(kvm, 139))
		kvm_s390_set_tod_clock_ext(kvm, &gtod);
	else if (gtod.epoch_idx == 0)
		kvm_s390_set_tod_clock(kvm, gtod.tod);
	else
		return -EINVAL;

	VM_EVENT(kvm, 3, "SET: TOD extension: 0x%x, TOD base: 0x%llx",
		gtod.epoch_idx, gtod.tod);

	return 0;
}

903 904 905 906 907 908 909 910 911 912
static int kvm_s390_set_tod_high(struct kvm *kvm, struct kvm_device_attr *attr)
{
	u8 gtod_high;

	if (copy_from_user(&gtod_high, (void __user *)attr->addr,
					   sizeof(gtod_high)))
		return -EFAULT;

	if (gtod_high != 0)
		return -EINVAL;
913
	VM_EVENT(kvm, 3, "SET: TOD extension: 0x%x", gtod_high);
914 915 916 917 918 919

	return 0;
}

static int kvm_s390_set_tod_low(struct kvm *kvm, struct kvm_device_attr *attr)
{
920
	u64 gtod;
921 922 923 924

	if (copy_from_user(&gtod, (void __user *)attr->addr, sizeof(gtod)))
		return -EFAULT;

925
	kvm_s390_set_tod_clock(kvm, gtod);
926
	VM_EVENT(kvm, 3, "SET: TOD base: 0x%llx", gtod);
927 928 929 930 931 932 933 934 935 936 937
	return 0;
}

static int kvm_s390_set_tod(struct kvm *kvm, struct kvm_device_attr *attr)
{
	int ret;

	if (attr->flags)
		return -EINVAL;

	switch (attr->attr) {
938 939 940
	case KVM_S390_VM_TOD_EXT:
		ret = kvm_s390_set_tod_ext(kvm, attr);
		break;
941 942 943 944 945 946 947 948 949 950 951 952 953
	case KVM_S390_VM_TOD_HIGH:
		ret = kvm_s390_set_tod_high(kvm, attr);
		break;
	case KVM_S390_VM_TOD_LOW:
		ret = kvm_s390_set_tod_low(kvm, attr);
		break;
	default:
		ret = -ENXIO;
		break;
	}
	return ret;
}

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
static void kvm_s390_get_tod_clock_ext(struct kvm *kvm,
					struct kvm_s390_vm_tod_clock *gtod)
{
	struct kvm_s390_tod_clock_ext htod;

	preempt_disable();

	get_tod_clock_ext((char *)&htod);

	gtod->tod = htod.tod + kvm->arch.epoch;
	gtod->epoch_idx = htod.epoch_idx + kvm->arch.epdx;

	if (gtod->tod < htod.tod)
		gtod->epoch_idx += 1;

	preempt_enable();
}

static int kvm_s390_get_tod_ext(struct kvm *kvm, struct kvm_device_attr *attr)
{
	struct kvm_s390_vm_tod_clock gtod;

	memset(&gtod, 0, sizeof(gtod));

	if (test_kvm_facility(kvm, 139))
		kvm_s390_get_tod_clock_ext(kvm, &gtod);
	else
		gtod.tod = kvm_s390_get_tod_clock_fast(kvm);

	if (copy_to_user((void __user *)attr->addr, &gtod, sizeof(gtod)))
		return -EFAULT;

	VM_EVENT(kvm, 3, "QUERY: TOD extension: 0x%x, TOD base: 0x%llx",
		gtod.epoch_idx, gtod.tod);
	return 0;
}

991 992 993 994 995 996 997
static int kvm_s390_get_tod_high(struct kvm *kvm, struct kvm_device_attr *attr)
{
	u8 gtod_high = 0;

	if (copy_to_user((void __user *)attr->addr, &gtod_high,
					 sizeof(gtod_high)))
		return -EFAULT;
998
	VM_EVENT(kvm, 3, "QUERY: TOD extension: 0x%x", gtod_high);
999 1000 1001 1002 1003 1004

	return 0;
}

static int kvm_s390_get_tod_low(struct kvm *kvm, struct kvm_device_attr *attr)
{
1005
	u64 gtod;
1006

1007
	gtod = kvm_s390_get_tod_clock_fast(kvm);
1008 1009
	if (copy_to_user((void __user *)attr->addr, &gtod, sizeof(gtod)))
		return -EFAULT;
1010
	VM_EVENT(kvm, 3, "QUERY: TOD base: 0x%llx", gtod);
1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022

	return 0;
}

static int kvm_s390_get_tod(struct kvm *kvm, struct kvm_device_attr *attr)
{
	int ret;

	if (attr->flags)
		return -EINVAL;

	switch (attr->attr) {
1023 1024 1025
	case KVM_S390_VM_TOD_EXT:
		ret = kvm_s390_get_tod_ext(kvm, attr);
		break;
1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038
	case KVM_S390_VM_TOD_HIGH:
		ret = kvm_s390_get_tod_high(kvm, attr);
		break;
	case KVM_S390_VM_TOD_LOW:
		ret = kvm_s390_get_tod_low(kvm, attr);
		break;
	default:
		ret = -ENXIO;
		break;
	}
	return ret;
}

1039 1040 1041
static int kvm_s390_set_processor(struct kvm *kvm, struct kvm_device_attr *attr)
{
	struct kvm_s390_vm_cpu_processor *proc;
1042
	u16 lowest_ibc, unblocked_ibc;
1043 1044 1045
	int ret = 0;

	mutex_lock(&kvm->lock);
1046
	if (kvm->created_vcpus) {
1047 1048 1049 1050 1051 1052 1053 1054 1055 1056
		ret = -EBUSY;
		goto out;
	}
	proc = kzalloc(sizeof(*proc), GFP_KERNEL);
	if (!proc) {
		ret = -ENOMEM;
		goto out;
	}
	if (!copy_from_user(proc, (void __user *)attr->addr,
			    sizeof(*proc))) {
1057
		kvm->arch.model.cpuid = proc->cpuid;
1058 1059
		lowest_ibc = sclp.ibc >> 16 & 0xfff;
		unblocked_ibc = sclp.ibc & 0xfff;
1060
		if (lowest_ibc && proc->ibc) {
1061 1062 1063 1064 1065 1066 1067
			if (proc->ibc > unblocked_ibc)
				kvm->arch.model.ibc = unblocked_ibc;
			else if (proc->ibc < lowest_ibc)
				kvm->arch.model.ibc = lowest_ibc;
			else
				kvm->arch.model.ibc = proc->ibc;
		}
1068
		memcpy(kvm->arch.model.fac_list, proc->fac_list,
1069
		       S390_ARCH_FAC_LIST_SIZE_BYTE);
1070 1071 1072 1073 1074 1075 1076
		VM_EVENT(kvm, 3, "SET: guest ibc: 0x%4.4x, guest cpuid: 0x%16.16llx",
			 kvm->arch.model.ibc,
			 kvm->arch.model.cpuid);
		VM_EVENT(kvm, 3, "SET: guest faclist: 0x%16.16llx.%16.16llx.%16.16llx",
			 kvm->arch.model.fac_list[0],
			 kvm->arch.model.fac_list[1],
			 kvm->arch.model.fac_list[2]);
1077 1078 1079 1080 1081 1082 1083 1084
	} else
		ret = -EFAULT;
	kfree(proc);
out:
	mutex_unlock(&kvm->lock);
	return ret;
}

1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107
static int kvm_s390_set_processor_feat(struct kvm *kvm,
				       struct kvm_device_attr *attr)
{
	struct kvm_s390_vm_cpu_feat data;
	int ret = -EBUSY;

	if (copy_from_user(&data, (void __user *)attr->addr, sizeof(data)))
		return -EFAULT;
	if (!bitmap_subset((unsigned long *) data.feat,
			   kvm_s390_available_cpu_feat,
			   KVM_S390_VM_CPU_FEAT_NR_BITS))
		return -EINVAL;

	mutex_lock(&kvm->lock);
	if (!atomic_read(&kvm->online_vcpus)) {
		bitmap_copy(kvm->arch.cpu_feat, (unsigned long *) data.feat,
			    KVM_S390_VM_CPU_FEAT_NR_BITS);
		ret = 0;
	}
	mutex_unlock(&kvm->lock);
	return ret;
}

1108 1109 1110 1111 1112 1113 1114 1115 1116 1117
static int kvm_s390_set_processor_subfunc(struct kvm *kvm,
					  struct kvm_device_attr *attr)
{
	/*
	 * Once supported by kernel + hw, we have to store the subfunctions
	 * in kvm->arch and remember that user space configured them.
	 */
	return -ENXIO;
}

1118 1119 1120 1121 1122 1123 1124 1125
static int kvm_s390_set_cpu_model(struct kvm *kvm, struct kvm_device_attr *attr)
{
	int ret = -ENXIO;

	switch (attr->attr) {
	case KVM_S390_VM_CPU_PROCESSOR:
		ret = kvm_s390_set_processor(kvm, attr);
		break;
1126 1127 1128
	case KVM_S390_VM_CPU_PROCESSOR_FEAT:
		ret = kvm_s390_set_processor_feat(kvm, attr);
		break;
1129 1130 1131
	case KVM_S390_VM_CPU_PROCESSOR_SUBFUNC:
		ret = kvm_s390_set_processor_subfunc(kvm, attr);
		break;
1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145
	}
	return ret;
}

static int kvm_s390_get_processor(struct kvm *kvm, struct kvm_device_attr *attr)
{
	struct kvm_s390_vm_cpu_processor *proc;
	int ret = 0;

	proc = kzalloc(sizeof(*proc), GFP_KERNEL);
	if (!proc) {
		ret = -ENOMEM;
		goto out;
	}
1146
	proc->cpuid = kvm->arch.model.cpuid;
1147
	proc->ibc = kvm->arch.model.ibc;
1148 1149
	memcpy(&proc->fac_list, kvm->arch.model.fac_list,
	       S390_ARCH_FAC_LIST_SIZE_BYTE);
1150 1151 1152 1153 1154 1155 1156
	VM_EVENT(kvm, 3, "GET: guest ibc: 0x%4.4x, guest cpuid: 0x%16.16llx",
		 kvm->arch.model.ibc,
		 kvm->arch.model.cpuid);
	VM_EVENT(kvm, 3, "GET: guest faclist: 0x%16.16llx.%16.16llx.%16.16llx",
		 kvm->arch.model.fac_list[0],
		 kvm->arch.model.fac_list[1],
		 kvm->arch.model.fac_list[2]);
1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174
	if (copy_to_user((void __user *)attr->addr, proc, sizeof(*proc)))
		ret = -EFAULT;
	kfree(proc);
out:
	return ret;
}

static int kvm_s390_get_machine(struct kvm *kvm, struct kvm_device_attr *attr)
{
	struct kvm_s390_vm_cpu_machine *mach;
	int ret = 0;

	mach = kzalloc(sizeof(*mach), GFP_KERNEL);
	if (!mach) {
		ret = -ENOMEM;
		goto out;
	}
	get_cpu_id((struct cpuid *) &mach->cpuid);
1175
	mach->ibc = sclp.ibc;
1176
	memcpy(&mach->fac_mask, kvm->arch.model.fac_mask,
1177
	       S390_ARCH_FAC_LIST_SIZE_BYTE);
1178
	memcpy((unsigned long *)&mach->fac_list, S390_lowcore.stfle_fac_list,
1179
	       sizeof(S390_lowcore.stfle_fac_list));
1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190
	VM_EVENT(kvm, 3, "GET: host ibc:  0x%4.4x, host cpuid:  0x%16.16llx",
		 kvm->arch.model.ibc,
		 kvm->arch.model.cpuid);
	VM_EVENT(kvm, 3, "GET: host facmask:  0x%16.16llx.%16.16llx.%16.16llx",
		 mach->fac_mask[0],
		 mach->fac_mask[1],
		 mach->fac_mask[2]);
	VM_EVENT(kvm, 3, "GET: host faclist:  0x%16.16llx.%16.16llx.%16.16llx",
		 mach->fac_list[0],
		 mach->fac_list[1],
		 mach->fac_list[2]);
1191 1192 1193 1194 1195 1196 1197
	if (copy_to_user((void __user *)attr->addr, mach, sizeof(*mach)))
		ret = -EFAULT;
	kfree(mach);
out:
	return ret;
}

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
static int kvm_s390_get_processor_feat(struct kvm *kvm,
				       struct kvm_device_attr *attr)
{
	struct kvm_s390_vm_cpu_feat data;

	bitmap_copy((unsigned long *) data.feat, kvm->arch.cpu_feat,
		    KVM_S390_VM_CPU_FEAT_NR_BITS);
	if (copy_to_user((void __user *)attr->addr, &data, sizeof(data)))
		return -EFAULT;
	return 0;
}

static int kvm_s390_get_machine_feat(struct kvm *kvm,
				     struct kvm_device_attr *attr)
{
	struct kvm_s390_vm_cpu_feat data;

	bitmap_copy((unsigned long *) data.feat,
		    kvm_s390_available_cpu_feat,
		    KVM_S390_VM_CPU_FEAT_NR_BITS);
	if (copy_to_user((void __user *)attr->addr, &data, sizeof(data)))
		return -EFAULT;
	return 0;
}

1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241
static int kvm_s390_get_processor_subfunc(struct kvm *kvm,
					  struct kvm_device_attr *attr)
{
	/*
	 * Once we can actually configure subfunctions (kernel + hw support),
	 * we have to check if they were already set by user space, if so copy
	 * them from kvm->arch.
	 */
	return -ENXIO;
}

static int kvm_s390_get_machine_subfunc(struct kvm *kvm,
					struct kvm_device_attr *attr)
{
	if (copy_to_user((void __user *)attr->addr, &kvm_s390_available_subfunc,
	    sizeof(struct kvm_s390_vm_cpu_subfunc)))
		return -EFAULT;
	return 0;
}
1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252
static int kvm_s390_get_cpu_model(struct kvm *kvm, struct kvm_device_attr *attr)
{
	int ret = -ENXIO;

	switch (attr->attr) {
	case KVM_S390_VM_CPU_PROCESSOR:
		ret = kvm_s390_get_processor(kvm, attr);
		break;
	case KVM_S390_VM_CPU_MACHINE:
		ret = kvm_s390_get_machine(kvm, attr);
		break;
1253 1254 1255 1256 1257 1258
	case KVM_S390_VM_CPU_PROCESSOR_FEAT:
		ret = kvm_s390_get_processor_feat(kvm, attr);
		break;
	case KVM_S390_VM_CPU_MACHINE_FEAT:
		ret = kvm_s390_get_machine_feat(kvm, attr);
		break;
1259 1260 1261 1262 1263 1264
	case KVM_S390_VM_CPU_PROCESSOR_SUBFUNC:
		ret = kvm_s390_get_processor_subfunc(kvm, attr);
		break;
	case KVM_S390_VM_CPU_MACHINE_SUBFUNC:
		ret = kvm_s390_get_machine_subfunc(kvm, attr);
		break;
1265 1266 1267 1268
	}
	return ret;
}

1269 1270 1271 1272 1273
static int kvm_s390_vm_set_attr(struct kvm *kvm, struct kvm_device_attr *attr)
{
	int ret;

	switch (attr->group) {
1274
	case KVM_S390_VM_MEM_CTRL:
1275
		ret = kvm_s390_set_mem_control(kvm, attr);
1276
		break;
1277 1278 1279
	case KVM_S390_VM_TOD:
		ret = kvm_s390_set_tod(kvm, attr);
		break;
1280 1281 1282
	case KVM_S390_VM_CPU_MODEL:
		ret = kvm_s390_set_cpu_model(kvm, attr);
		break;
1283 1284 1285
	case KVM_S390_VM_CRYPTO:
		ret = kvm_s390_vm_set_crypto(kvm, attr);
		break;
1286 1287 1288
	case KVM_S390_VM_MIGRATION:
		ret = kvm_s390_vm_set_migration(kvm, attr);
		break;
1289 1290 1291 1292 1293 1294 1295 1296 1297 1298
	default:
		ret = -ENXIO;
		break;
	}

	return ret;
}

static int kvm_s390_vm_get_attr(struct kvm *kvm, struct kvm_device_attr *attr)
{
1299 1300 1301 1302 1303 1304
	int ret;

	switch (attr->group) {
	case KVM_S390_VM_MEM_CTRL:
		ret = kvm_s390_get_mem_control(kvm, attr);
		break;
1305 1306 1307
	case KVM_S390_VM_TOD:
		ret = kvm_s390_get_tod(kvm, attr);
		break;
1308 1309 1310
	case KVM_S390_VM_CPU_MODEL:
		ret = kvm_s390_get_cpu_model(kvm, attr);
		break;
1311 1312 1313
	case KVM_S390_VM_MIGRATION:
		ret = kvm_s390_vm_get_migration(kvm, attr);
		break;
1314 1315 1316 1317 1318 1319
	default:
		ret = -ENXIO;
		break;
	}

	return ret;
1320 1321 1322 1323 1324 1325 1326
}

static int kvm_s390_vm_has_attr(struct kvm *kvm, struct kvm_device_attr *attr)
{
	int ret;

	switch (attr->group) {
1327 1328 1329 1330
	case KVM_S390_VM_MEM_CTRL:
		switch (attr->attr) {
		case KVM_S390_VM_MEM_ENABLE_CMMA:
		case KVM_S390_VM_MEM_CLR_CMMA:
1331 1332
			ret = sclp.has_cmma ? 0 : -ENXIO;
			break;
1333
		case KVM_S390_VM_MEM_LIMIT_SIZE:
1334 1335 1336 1337 1338 1339 1340
			ret = 0;
			break;
		default:
			ret = -ENXIO;
			break;
		}
		break;
1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351
	case KVM_S390_VM_TOD:
		switch (attr->attr) {
		case KVM_S390_VM_TOD_LOW:
		case KVM_S390_VM_TOD_HIGH:
			ret = 0;
			break;
		default:
			ret = -ENXIO;
			break;
		}
		break;
1352 1353 1354 1355
	case KVM_S390_VM_CPU_MODEL:
		switch (attr->attr) {
		case KVM_S390_VM_CPU_PROCESSOR:
		case KVM_S390_VM_CPU_MACHINE:
1356 1357
		case KVM_S390_VM_CPU_PROCESSOR_FEAT:
		case KVM_S390_VM_CPU_MACHINE_FEAT:
1358
		case KVM_S390_VM_CPU_MACHINE_SUBFUNC:
1359 1360
			ret = 0;
			break;
1361 1362
		/* configuring subfunctions is not supported yet */
		case KVM_S390_VM_CPU_PROCESSOR_SUBFUNC:
1363 1364 1365 1366 1367
		default:
			ret = -ENXIO;
			break;
		}
		break;
1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380
	case KVM_S390_VM_CRYPTO:
		switch (attr->attr) {
		case KVM_S390_VM_CRYPTO_ENABLE_AES_KW:
		case KVM_S390_VM_CRYPTO_ENABLE_DEA_KW:
		case KVM_S390_VM_CRYPTO_DISABLE_AES_KW:
		case KVM_S390_VM_CRYPTO_DISABLE_DEA_KW:
			ret = 0;
			break;
		default:
			ret = -ENXIO;
			break;
		}
		break;
1381 1382 1383
	case KVM_S390_VM_MIGRATION:
		ret = 0;
		break;
1384 1385 1386 1387 1388 1389 1390 1391
	default:
		ret = -ENXIO;
		break;
	}

	return ret;
}

1392 1393 1394 1395
static long kvm_s390_get_skeys(struct kvm *kvm, struct kvm_s390_skeys *args)
{
	uint8_t *keys;
	uint64_t hva;
1396
	int srcu_idx, i, r = 0;
1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408

	if (args->flags != 0)
		return -EINVAL;

	/* Is this guest using storage keys? */
	if (!mm_use_skey(current->mm))
		return KVM_S390_GET_SKEYS_NONE;

	/* Enforce sane limit on memory allocation */
	if (args->count < 1 || args->count > KVM_S390_SKEYS_MAX)
		return -EINVAL;

1409
	keys = kvmalloc_array(args->count, sizeof(uint8_t), GFP_KERNEL);
1410 1411 1412
	if (!keys)
		return -ENOMEM;

1413
	down_read(&current->mm->mmap_sem);
1414
	srcu_idx = srcu_read_lock(&kvm->srcu);
1415 1416 1417 1418
	for (i = 0; i < args->count; i++) {
		hva = gfn_to_hva(kvm, args->start_gfn + i);
		if (kvm_is_error_hva(hva)) {
			r = -EFAULT;
1419
			break;
1420 1421
		}

1422 1423
		r = get_guest_storage_key(current->mm, hva, &keys[i]);
		if (r)
1424
			break;
1425
	}
1426
	srcu_read_unlock(&kvm->srcu, srcu_idx);
1427 1428 1429 1430 1431 1432 1433
	up_read(&current->mm->mmap_sem);

	if (!r) {
		r = copy_to_user((uint8_t __user *)args->skeydata_addr, keys,
				 sizeof(uint8_t) * args->count);
		if (r)
			r = -EFAULT;
1434 1435 1436 1437 1438 1439 1440 1441 1442 1443
	}

	kvfree(keys);
	return r;
}

static long kvm_s390_set_skeys(struct kvm *kvm, struct kvm_s390_skeys *args)
{
	uint8_t *keys;
	uint64_t hva;
1444
	int srcu_idx, i, r = 0;
1445 1446 1447 1448 1449 1450 1451 1452

	if (args->flags != 0)
		return -EINVAL;

	/* Enforce sane limit on memory allocation */
	if (args->count < 1 || args->count > KVM_S390_SKEYS_MAX)
		return -EINVAL;

1453
	keys = kvmalloc_array(args->count, sizeof(uint8_t), GFP_KERNEL);
1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464
	if (!keys)
		return -ENOMEM;

	r = copy_from_user(keys, (uint8_t __user *)args->skeydata_addr,
			   sizeof(uint8_t) * args->count);
	if (r) {
		r = -EFAULT;
		goto out;
	}

	/* Enable storage key handling for the guest */
1465 1466 1467
	r = s390_enable_skey();
	if (r)
		goto out;
1468

1469
	down_read(&current->mm->mmap_sem);
1470
	srcu_idx = srcu_read_lock(&kvm->srcu);
1471 1472 1473 1474
	for (i = 0; i < args->count; i++) {
		hva = gfn_to_hva(kvm, args->start_gfn + i);
		if (kvm_is_error_hva(hva)) {
			r = -EFAULT;
1475
			break;
1476 1477 1478 1479 1480
		}

		/* Lowest order bit is reserved */
		if (keys[i] & 0x01) {
			r = -EINVAL;
1481
			break;
1482 1483
		}

1484
		r = set_guest_storage_key(current->mm, hva, keys[i], 0);
1485
		if (r)
1486
			break;
1487
	}
1488
	srcu_read_unlock(&kvm->srcu, srcu_idx);
1489
	up_read(&current->mm->mmap_sem);
1490 1491 1492 1493 1494
out:
	kvfree(keys);
	return r;
}

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 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576
/*
 * Base address and length must be sent at the start of each block, therefore
 * it's cheaper to send some clean data, as long as it's less than the size of
 * two longs.
 */
#define KVM_S390_MAX_BIT_DISTANCE (2 * sizeof(void *))
/* for consistency */
#define KVM_S390_CMMA_SIZE_MAX ((u32)KVM_S390_SKEYS_MAX)

/*
 * This function searches for the next page with dirty CMMA attributes, and
 * saves the attributes in the buffer up to either the end of the buffer or
 * until a block of at least KVM_S390_MAX_BIT_DISTANCE clean bits is found;
 * no trailing clean bytes are saved.
 * In case no dirty bits were found, or if CMMA was not enabled or used, the
 * output buffer will indicate 0 as length.
 */
static int kvm_s390_get_cmma_bits(struct kvm *kvm,
				  struct kvm_s390_cmma_log *args)
{
	struct kvm_s390_migration_state *s = kvm->arch.migration_state;
	unsigned long bufsize, hva, pgstev, i, next, cur;
	int srcu_idx, peek, r = 0, rr;
	u8 *res;

	cur = args->start_gfn;
	i = next = pgstev = 0;

	if (unlikely(!kvm->arch.use_cmma))
		return -ENXIO;
	/* Invalid/unsupported flags were specified */
	if (args->flags & ~KVM_S390_CMMA_PEEK)
		return -EINVAL;
	/* Migration mode query, and we are not doing a migration */
	peek = !!(args->flags & KVM_S390_CMMA_PEEK);
	if (!peek && !s)
		return -EINVAL;
	/* CMMA is disabled or was not used, or the buffer has length zero */
	bufsize = min(args->count, KVM_S390_CMMA_SIZE_MAX);
	if (!bufsize || !kvm->mm->context.use_cmma) {
		memset(args, 0, sizeof(*args));
		return 0;
	}

	if (!peek) {
		/* We are not peeking, and there are no dirty pages */
		if (!atomic64_read(&s->dirty_pages)) {
			memset(args, 0, sizeof(*args));
			return 0;
		}
		cur = find_next_bit(s->pgste_bitmap, s->bitmap_size,
				    args->start_gfn);
		if (cur >= s->bitmap_size)	/* nothing found, loop back */
			cur = find_next_bit(s->pgste_bitmap, s->bitmap_size, 0);
		if (cur >= s->bitmap_size) {	/* again! (very unlikely) */
			memset(args, 0, sizeof(*args));
			return 0;
		}
		next = find_next_bit(s->pgste_bitmap, s->bitmap_size, cur + 1);
	}

	res = vmalloc(bufsize);
	if (!res)
		return -ENOMEM;

	args->start_gfn = cur;

	down_read(&kvm->mm->mmap_sem);
	srcu_idx = srcu_read_lock(&kvm->srcu);
	while (i < bufsize) {
		hva = gfn_to_hva(kvm, cur);
		if (kvm_is_error_hva(hva)) {
			r = -EFAULT;
			break;
		}
		/* decrement only if we actually flipped the bit to 0 */
		if (!peek && test_and_clear_bit(cur, s->pgste_bitmap))
			atomic64_dec(&s->dirty_pages);
		r = get_pgste(kvm->mm, hva, &pgstev);
		if (r < 0)
			pgstev = 0;
		/* save the value */
1577
		res[i++] = (pgstev >> 24) & 0x43;
1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654
		/*
		 * if the next bit is too far away, stop.
		 * if we reached the previous "next", find the next one
		 */
		if (!peek) {
			if (next > cur + KVM_S390_MAX_BIT_DISTANCE)
				break;
			if (cur == next)
				next = find_next_bit(s->pgste_bitmap,
						     s->bitmap_size, cur + 1);
		/* reached the end of the bitmap or of the buffer, stop */
			if ((next >= s->bitmap_size) ||
			    (next >= args->start_gfn + bufsize))
				break;
		}
		cur++;
	}
	srcu_read_unlock(&kvm->srcu, srcu_idx);
	up_read(&kvm->mm->mmap_sem);
	args->count = i;
	args->remaining = s ? atomic64_read(&s->dirty_pages) : 0;

	rr = copy_to_user((void __user *)args->values, res, args->count);
	if (rr)
		r = -EFAULT;

	vfree(res);
	return r;
}

/*
 * This function sets the CMMA attributes for the given pages. If the input
 * buffer has zero length, no action is taken, otherwise the attributes are
 * set and the mm->context.use_cmma flag is set.
 */
static int kvm_s390_set_cmma_bits(struct kvm *kvm,
				  const struct kvm_s390_cmma_log *args)
{
	unsigned long hva, mask, pgstev, i;
	uint8_t *bits;
	int srcu_idx, r = 0;

	mask = args->mask;

	if (!kvm->arch.use_cmma)
		return -ENXIO;
	/* invalid/unsupported flags */
	if (args->flags != 0)
		return -EINVAL;
	/* Enforce sane limit on memory allocation */
	if (args->count > KVM_S390_CMMA_SIZE_MAX)
		return -EINVAL;
	/* Nothing to do */
	if (args->count == 0)
		return 0;

	bits = vmalloc(sizeof(*bits) * args->count);
	if (!bits)
		return -ENOMEM;

	r = copy_from_user(bits, (void __user *)args->values, args->count);
	if (r) {
		r = -EFAULT;
		goto out;
	}

	down_read(&kvm->mm->mmap_sem);
	srcu_idx = srcu_read_lock(&kvm->srcu);
	for (i = 0; i < args->count; i++) {
		hva = gfn_to_hva(kvm, args->start_gfn + i);
		if (kvm_is_error_hva(hva)) {
			r = -EFAULT;
			break;
		}

		pgstev = bits[i];
		pgstev = pgstev << 24;
1655
		mask &= _PGSTE_GPS_USAGE_MASK | _PGSTE_GPS_NODAT;
1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670
		set_pgste_bits(kvm->mm, hva, mask, pgstev);
	}
	srcu_read_unlock(&kvm->srcu, srcu_idx);
	up_read(&kvm->mm->mmap_sem);

	if (!kvm->mm->context.use_cmma) {
		down_write(&kvm->mm->mmap_sem);
		kvm->mm->context.use_cmma = 1;
		up_write(&kvm->mm->mmap_sem);
	}
out:
	vfree(bits);
	return r;
}

1671 1672 1673 1674 1675
long kvm_arch_vm_ioctl(struct file *filp,
		       unsigned int ioctl, unsigned long arg)
{
	struct kvm *kvm = filp->private_data;
	void __user *argp = (void __user *)arg;
1676
	struct kvm_device_attr attr;
1677 1678 1679
	int r;

	switch (ioctl) {
1680 1681 1682 1683 1684 1685 1686 1687 1688
	case KVM_S390_INTERRUPT: {
		struct kvm_s390_interrupt s390int;

		r = -EFAULT;
		if (copy_from_user(&s390int, argp, sizeof(s390int)))
			break;
		r = kvm_s390_inject_vm(kvm, &s390int);
		break;
	}
1689 1690 1691 1692 1693 1694 1695 1696
	case KVM_ENABLE_CAP: {
		struct kvm_enable_cap cap;
		r = -EFAULT;
		if (copy_from_user(&cap, argp, sizeof(cap)))
			break;
		r = kvm_vm_ioctl_enable_cap(kvm, &cap);
		break;
	}
1697 1698 1699 1700 1701 1702 1703
	case KVM_CREATE_IRQCHIP: {
		struct kvm_irq_routing_entry routing;

		r = -EINVAL;
		if (kvm->arch.use_irqchip) {
			/* Set up dummy routing. */
			memset(&routing, 0, sizeof(routing));
1704
			r = kvm_set_irq_routing(kvm, &routing, 0, 0);
1705 1706 1707
		}
		break;
	}
1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728
	case KVM_SET_DEVICE_ATTR: {
		r = -EFAULT;
		if (copy_from_user(&attr, (void __user *)arg, sizeof(attr)))
			break;
		r = kvm_s390_vm_set_attr(kvm, &attr);
		break;
	}
	case KVM_GET_DEVICE_ATTR: {
		r = -EFAULT;
		if (copy_from_user(&attr, (void __user *)arg, sizeof(attr)))
			break;
		r = kvm_s390_vm_get_attr(kvm, &attr);
		break;
	}
	case KVM_HAS_DEVICE_ATTR: {
		r = -EFAULT;
		if (copy_from_user(&attr, (void __user *)arg, sizeof(attr)))
			break;
		r = kvm_s390_vm_has_attr(kvm, &attr);
		break;
	}
1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748
	case KVM_S390_GET_SKEYS: {
		struct kvm_s390_skeys args;

		r = -EFAULT;
		if (copy_from_user(&args, argp,
				   sizeof(struct kvm_s390_skeys)))
			break;
		r = kvm_s390_get_skeys(kvm, &args);
		break;
	}
	case KVM_S390_SET_SKEYS: {
		struct kvm_s390_skeys args;

		r = -EFAULT;
		if (copy_from_user(&args, argp,
				   sizeof(struct kvm_s390_skeys)))
			break;
		r = kvm_s390_set_skeys(kvm, &args);
		break;
	}
1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771
	case KVM_S390_GET_CMMA_BITS: {
		struct kvm_s390_cmma_log args;

		r = -EFAULT;
		if (copy_from_user(&args, argp, sizeof(args)))
			break;
		r = kvm_s390_get_cmma_bits(kvm, &args);
		if (!r) {
			r = copy_to_user(argp, &args, sizeof(args));
			if (r)
				r = -EFAULT;
		}
		break;
	}
	case KVM_S390_SET_CMMA_BITS: {
		struct kvm_s390_cmma_log args;

		r = -EFAULT;
		if (copy_from_user(&args, argp, sizeof(args)))
			break;
		r = kvm_s390_set_cmma_bits(kvm, &args);
		break;
	}
1772
	default:
1773
		r = -ENOTTY;
1774 1775 1776 1777 1778
	}

	return r;
}

1779 1780 1781
static int kvm_s390_query_ap_config(u8 *config)
{
	u32 fcn_code = 0x04000000UL;
1782
	u32 cc = 0;
1783

1784
	memset(config, 0, 128);
1785 1786 1787 1788
	asm volatile(
		"lgr 0,%1\n"
		"lgr 2,%2\n"
		".long 0xb2af0000\n"		/* PQAP(QCI) */
1789
		"0: ipm %0\n"
1790
		"srl %0,28\n"
1791 1792 1793
		"1:\n"
		EX_TABLE(0b, 1b)
		: "+r" (cc)
1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805
		: "r" (fcn_code), "r" (config)
		: "cc", "0", "2", "memory"
	);

	return cc;
}

static int kvm_s390_apxa_installed(void)
{
	u8 config[128];
	int cc;

1806
	if (test_facility(12)) {
1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827
		cc = kvm_s390_query_ap_config(config);

		if (cc)
			pr_err("PQAP(QCI) failed with cc=%d", cc);
		else
			return config[0] & 0x40;
	}

	return 0;
}

static void kvm_s390_set_crycb_format(struct kvm *kvm)
{
	kvm->arch.crypto.crycbd = (__u32)(unsigned long) kvm->arch.crypto.crycb;

	if (kvm_s390_apxa_installed())
		kvm->arch.crypto.crycbd |= CRYCB_FORMAT2;
	else
		kvm->arch.crypto.crycbd |= CRYCB_FORMAT1;
}

1828
static u64 kvm_s390_get_initial_cpuid(void)
1829
{
1830 1831 1832 1833 1834
	struct cpuid cpuid;

	get_cpu_id(&cpuid);
	cpuid.version = 0xff;
	return *((u64 *) &cpuid);
1835 1836
}

1837
static void kvm_s390_crypto_init(struct kvm *kvm)
1838
{
1839
	if (!test_kvm_facility(kvm, 76))
1840
		return;
1841

1842
	kvm->arch.crypto.crycb = &kvm->arch.sie_page2->crycb;
1843
	kvm_s390_set_crycb_format(kvm);
1844

1845 1846 1847 1848 1849 1850 1851
	/* Enable AES/DEA protected key functions by default */
	kvm->arch.crypto.aes_kw = 1;
	kvm->arch.crypto.dea_kw = 1;
	get_random_bytes(kvm->arch.crypto.crycb->aes_wrapping_key_mask,
			 sizeof(kvm->arch.crypto.crycb->aes_wrapping_key_mask));
	get_random_bytes(kvm->arch.crypto.crycb->dea_wrapping_key_mask,
			 sizeof(kvm->arch.crypto.crycb->dea_wrapping_key_mask));
1852 1853
}

1854 1855 1856
static void sca_dispose(struct kvm *kvm)
{
	if (kvm->arch.use_esca)
1857
		free_pages_exact(kvm->arch.sca, sizeof(struct esca_block));
1858 1859 1860 1861 1862
	else
		free_page((unsigned long)(kvm->arch.sca));
	kvm->arch.sca = NULL;
}

1863
int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
1864
{
1865
	gfp_t alloc_flags = GFP_KERNEL;
1866
	int i, rc;
1867
	char debug_name[16];
1868
	static unsigned long sca_offset;
1869

1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880
	rc = -EINVAL;
#ifdef CONFIG_KVM_S390_UCONTROL
	if (type & ~KVM_VM_S390_UCONTROL)
		goto out_err;
	if ((type & KVM_VM_S390_UCONTROL) && (!capable(CAP_SYS_ADMIN)))
		goto out_err;
#else
	if (type)
		goto out_err;
#endif

1881 1882
	rc = s390_enable_sie();
	if (rc)
1883
		goto out_err;
1884

1885 1886
	rc = -ENOMEM;

1887
	kvm->arch.use_esca = 0; /* start with basic SCA */
1888 1889
	if (!sclp.has_64bscao)
		alloc_flags |= GFP_DMA;
1890
	rwlock_init(&kvm->arch.sca_lock);
1891
	kvm->arch.sca = (struct bsca_block *) get_zeroed_page(alloc_flags);
1892
	if (!kvm->arch.sca)
1893
		goto out_err;
1894
	spin_lock(&kvm_lock);
1895
	sca_offset += 16;
1896
	if (sca_offset + sizeof(struct bsca_block) > PAGE_SIZE)
1897
		sca_offset = 0;
1898 1899
	kvm->arch.sca = (struct bsca_block *)
			((char *) kvm->arch.sca + sca_offset);
1900
	spin_unlock(&kvm_lock);
1901 1902 1903

	sprintf(debug_name, "kvm-%u", current->pid);

1904
	kvm->arch.dbf = debug_register(debug_name, 32, 1, 7 * sizeof(long));
1905
	if (!kvm->arch.dbf)
1906
		goto out_err;
1907

1908 1909 1910
	kvm->arch.sie_page2 =
	     (struct sie_page2 *) get_zeroed_page(GFP_KERNEL | GFP_DMA);
	if (!kvm->arch.sie_page2)
1911
		goto out_err;
1912

1913
	/* Populate the facility mask initially. */
1914
	memcpy(kvm->arch.model.fac_mask, S390_lowcore.stfle_fac_list,
1915
	       sizeof(S390_lowcore.stfle_fac_list));
1916 1917
	for (i = 0; i < S390_ARCH_FAC_LIST_SIZE_U64; i++) {
		if (i < kvm_s390_fac_list_mask_size())
1918
			kvm->arch.model.fac_mask[i] &= kvm_s390_fac_list_mask[i];
1919
		else
1920
			kvm->arch.model.fac_mask[i] = 0UL;
1921 1922
	}

1923
	/* Populate the facility list initially. */
1924 1925
	kvm->arch.model.fac_list = kvm->arch.sie_page2->fac_list;
	memcpy(kvm->arch.model.fac_list, kvm->arch.model.fac_mask,
1926 1927
	       S390_ARCH_FAC_LIST_SIZE_BYTE);

1928 1929 1930 1931
	/* we are always in czam mode - even on pre z14 machines */
	set_kvm_facility(kvm->arch.model.fac_mask, 138);
	set_kvm_facility(kvm->arch.model.fac_list, 138);
	/* we emulate STHYI in kvm */
J
Janosch Frank 已提交
1932 1933
	set_kvm_facility(kvm->arch.model.fac_mask, 74);
	set_kvm_facility(kvm->arch.model.fac_list, 74);
1934 1935 1936 1937
	if (MACHINE_HAS_TLB_GUEST) {
		set_kvm_facility(kvm->arch.model.fac_mask, 147);
		set_kvm_facility(kvm->arch.model.fac_list, 147);
	}
J
Janosch Frank 已提交
1938

1939
	kvm->arch.model.cpuid = kvm_s390_get_initial_cpuid();
1940
	kvm->arch.model.ibc = sclp.ibc & 0x0fff;
1941

1942
	kvm_s390_crypto_init(kvm);
1943

1944 1945 1946
	mutex_init(&kvm->arch.float_int.ais_lock);
	kvm->arch.float_int.simm = 0;
	kvm->arch.float_int.nimm = 0;
1947
	spin_lock_init(&kvm->arch.float_int.lock);
1948 1949
	for (i = 0; i < FIRQ_LIST_COUNT; i++)
		INIT_LIST_HEAD(&kvm->arch.float_int.lists[i]);
1950
	init_waitqueue_head(&kvm->arch.ipte_wq);
1951
	mutex_init(&kvm->arch.ipte_mutex);
1952

1953
	debug_register_view(kvm->arch.dbf, &debug_sprintf_view);
1954
	VM_EVENT(kvm, 3, "vm created with type %lu", type);
1955

1956 1957
	if (type & KVM_VM_S390_UCONTROL) {
		kvm->arch.gmap = NULL;
1958
		kvm->arch.mem_limit = KVM_S390_NO_MEM_LIMIT;
1959
	} else {
1960
		if (sclp.hamax == U64_MAX)
1961
			kvm->arch.mem_limit = TASK_SIZE_MAX;
1962
		else
1963
			kvm->arch.mem_limit = min_t(unsigned long, TASK_SIZE_MAX,
1964
						    sclp.hamax + 1);
1965
		kvm->arch.gmap = gmap_create(current->mm, kvm->arch.mem_limit - 1);
1966
		if (!kvm->arch.gmap)
1967
			goto out_err;
1968
		kvm->arch.gmap->private = kvm;
1969
		kvm->arch.gmap->pfault_enabled = 0;
1970
	}
1971 1972

	kvm->arch.css_support = 0;
1973
	kvm->arch.use_irqchip = 0;
1974
	kvm->arch.epoch = 0;
1975

1976
	spin_lock_init(&kvm->arch.start_stop_lock);
1977
	kvm_s390_vsie_init(kvm);
1978
	KVM_EVENT(3, "vm 0x%pK created by pid %u", kvm, current->pid);
1979

1980
	return 0;
1981
out_err:
1982
	free_page((unsigned long)kvm->arch.sie_page2);
1983
	debug_unregister(kvm->arch.dbf);
1984
	sca_dispose(kvm);
1985
	KVM_EVENT(3, "creation of vm failed: %d", rc);
1986
	return rc;
1987 1988
}

1989 1990 1991 1992 1993 1994 1995 1996 1997 1998
bool kvm_arch_has_vcpu_debugfs(void)
{
	return false;
}

int kvm_arch_create_vcpu_debugfs(struct kvm_vcpu *vcpu)
{
	return 0;
}

1999 2000 2001
void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
{
	VCPU_EVENT(vcpu, 3, "%s", "free cpu");
2002
	trace_kvm_s390_destroy_vcpu(vcpu->vcpu_id);
2003
	kvm_s390_clear_local_irqs(vcpu);
2004
	kvm_clear_async_pf_completion_queue(vcpu);
2005
	if (!kvm_is_ucontrol(vcpu->kvm))
2006
		sca_del_vcpu(vcpu);
2007 2008

	if (kvm_is_ucontrol(vcpu->kvm))
2009
		gmap_remove(vcpu->arch.gmap);
2010

2011
	if (vcpu->kvm->arch.use_cmma)
2012
		kvm_s390_vcpu_unsetup_cmma(vcpu);
2013
	free_page((unsigned long)(vcpu->arch.sie_block));
2014

2015
	kvm_vcpu_uninit(vcpu);
2016
	kmem_cache_free(kvm_vcpu_cache, vcpu);
2017 2018 2019 2020 2021
}

static void kvm_free_vcpus(struct kvm *kvm)
{
	unsigned int i;
2022
	struct kvm_vcpu *vcpu;
2023

2024 2025 2026 2027 2028 2029 2030 2031 2032
	kvm_for_each_vcpu(i, vcpu, kvm)
		kvm_arch_vcpu_destroy(vcpu);

	mutex_lock(&kvm->lock);
	for (i = 0; i < atomic_read(&kvm->online_vcpus); i++)
		kvm->vcpus[i] = NULL;

	atomic_set(&kvm->online_vcpus, 0);
	mutex_unlock(&kvm->lock);
2033 2034
}

2035 2036
void kvm_arch_destroy_vm(struct kvm *kvm)
{
2037
	kvm_free_vcpus(kvm);
2038
	sca_dispose(kvm);
2039
	debug_unregister(kvm->arch.dbf);
2040
	free_page((unsigned long)kvm->arch.sie_page2);
2041
	if (!kvm_is_ucontrol(kvm))
2042
		gmap_remove(kvm->arch.gmap);
2043
	kvm_s390_destroy_adapters(kvm);
2044
	kvm_s390_clear_float_irqs(kvm);
2045
	kvm_s390_vsie_destroy(kvm);
2046 2047 2048 2049
	if (kvm->arch.migration_state) {
		vfree(kvm->arch.migration_state->pgste_bitmap);
		kfree(kvm->arch.migration_state);
	}
2050
	KVM_EVENT(3, "vm 0x%pK destroyed", kvm);
2051 2052 2053
}

/* Section: vcpu related */
2054 2055
static int __kvm_ucontrol_vcpu_init(struct kvm_vcpu *vcpu)
{
2056
	vcpu->arch.gmap = gmap_create(current->mm, -1UL);
2057 2058 2059 2060 2061 2062 2063
	if (!vcpu->arch.gmap)
		return -ENOMEM;
	vcpu->arch.gmap->private = vcpu->kvm;

	return 0;
}

2064 2065
static void sca_del_vcpu(struct kvm_vcpu *vcpu)
{
2066 2067
	if (!kvm_s390_use_sca_entries())
		return;
2068
	read_lock(&vcpu->kvm->arch.sca_lock);
2069 2070
	if (vcpu->kvm->arch.use_esca) {
		struct esca_block *sca = vcpu->kvm->arch.sca;
2071

2072
		clear_bit_inv(vcpu->vcpu_id, (unsigned long *) sca->mcn);
2073
		sca->cpu[vcpu->vcpu_id].sda = 0;
2074 2075 2076 2077
	} else {
		struct bsca_block *sca = vcpu->kvm->arch.sca;

		clear_bit_inv(vcpu->vcpu_id, (unsigned long *) &sca->mcn);
2078
		sca->cpu[vcpu->vcpu_id].sda = 0;
2079
	}
2080
	read_unlock(&vcpu->kvm->arch.sca_lock);
2081 2082
}

2083
static void sca_add_vcpu(struct kvm_vcpu *vcpu)
2084
{
2085 2086 2087 2088 2089 2090 2091
	if (!kvm_s390_use_sca_entries()) {
		struct bsca_block *sca = vcpu->kvm->arch.sca;

		/* we still need the basic sca for the ipte control */
		vcpu->arch.sie_block->scaoh = (__u32)(((__u64)sca) >> 32);
		vcpu->arch.sie_block->scaol = (__u32)(__u64)sca;
	}
2092 2093 2094
	read_lock(&vcpu->kvm->arch.sca_lock);
	if (vcpu->kvm->arch.use_esca) {
		struct esca_block *sca = vcpu->kvm->arch.sca;
2095

2096
		sca->cpu[vcpu->vcpu_id].sda = (__u64) vcpu->arch.sie_block;
2097 2098
		vcpu->arch.sie_block->scaoh = (__u32)(((__u64)sca) >> 32);
		vcpu->arch.sie_block->scaol = (__u32)(__u64)sca & ~0x3fU;
2099
		vcpu->arch.sie_block->ecb2 |= ECB2_ESCA;
2100
		set_bit_inv(vcpu->vcpu_id, (unsigned long *) sca->mcn);
2101
	} else {
2102
		struct bsca_block *sca = vcpu->kvm->arch.sca;
2103

2104
		sca->cpu[vcpu->vcpu_id].sda = (__u64) vcpu->arch.sie_block;
2105 2106
		vcpu->arch.sie_block->scaoh = (__u32)(((__u64)sca) >> 32);
		vcpu->arch.sie_block->scaol = (__u32)(__u64)sca;
2107
		set_bit_inv(vcpu->vcpu_id, (unsigned long *) &sca->mcn);
2108
	}
2109
	read_unlock(&vcpu->kvm->arch.sca_lock);
2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152
}

/* Basic SCA to Extended SCA data copy routines */
static inline void sca_copy_entry(struct esca_entry *d, struct bsca_entry *s)
{
	d->sda = s->sda;
	d->sigp_ctrl.c = s->sigp_ctrl.c;
	d->sigp_ctrl.scn = s->sigp_ctrl.scn;
}

static void sca_copy_b_to_e(struct esca_block *d, struct bsca_block *s)
{
	int i;

	d->ipte_control = s->ipte_control;
	d->mcn[0] = s->mcn;
	for (i = 0; i < KVM_S390_BSCA_CPU_SLOTS; i++)
		sca_copy_entry(&d->cpu[i], &s->cpu[i]);
}

static int sca_switch_to_extended(struct kvm *kvm)
{
	struct bsca_block *old_sca = kvm->arch.sca;
	struct esca_block *new_sca;
	struct kvm_vcpu *vcpu;
	unsigned int vcpu_idx;
	u32 scaol, scaoh;

	new_sca = alloc_pages_exact(sizeof(*new_sca), GFP_KERNEL|__GFP_ZERO);
	if (!new_sca)
		return -ENOMEM;

	scaoh = (u32)((u64)(new_sca) >> 32);
	scaol = (u32)(u64)(new_sca) & ~0x3fU;

	kvm_s390_vcpu_block_all(kvm);
	write_lock(&kvm->arch.sca_lock);

	sca_copy_b_to_e(new_sca, old_sca);

	kvm_for_each_vcpu(vcpu_idx, vcpu, kvm) {
		vcpu->arch.sie_block->scaoh = scaoh;
		vcpu->arch.sie_block->scaol = scaol;
2153
		vcpu->arch.sie_block->ecb2 |= ECB2_ESCA;
2154 2155 2156 2157 2158 2159 2160 2161 2162
	}
	kvm->arch.sca = new_sca;
	kvm->arch.use_esca = 1;

	write_unlock(&kvm->arch.sca_lock);
	kvm_s390_vcpu_unblock_all(kvm);

	free_page((unsigned long)old_sca);

2163 2164
	VM_EVENT(kvm, 2, "Switched to ESCA (0x%pK -> 0x%pK)",
		 old_sca, kvm->arch.sca);
2165
	return 0;
2166 2167 2168 2169
}

static int sca_can_add_vcpu(struct kvm *kvm, unsigned int id)
{
2170 2171
	int rc;

2172 2173 2174 2175 2176
	if (!kvm_s390_use_sca_entries()) {
		if (id < KVM_MAX_VCPUS)
			return true;
		return false;
	}
2177 2178
	if (id < KVM_S390_BSCA_CPU_SLOTS)
		return true;
2179
	if (!sclp.has_esca || !sclp.has_64bscao)
2180 2181 2182 2183 2184 2185 2186
		return false;

	mutex_lock(&kvm->lock);
	rc = kvm->arch.use_esca ? 0 : sca_switch_to_extended(kvm);
	mutex_unlock(&kvm->lock);

	return rc == 0 && id < KVM_S390_ESCA_CPU_SLOTS;
2187 2188
}

2189 2190
int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
{
2191 2192
	vcpu->arch.pfault_token = KVM_S390_PFAULT_TOKEN_INVALID;
	kvm_clear_async_pf_completion_queue(vcpu);
2193 2194
	vcpu->run->kvm_valid_regs = KVM_SYNC_PREFIX |
				    KVM_SYNC_GPRS |
2195
				    KVM_SYNC_ACRS |
2196 2197 2198
				    KVM_SYNC_CRS |
				    KVM_SYNC_ARCH0 |
				    KVM_SYNC_PFAULT;
2199
	kvm_s390_set_prefix(vcpu, 0);
2200 2201
	if (test_kvm_facility(vcpu->kvm, 64))
		vcpu->run->kvm_valid_regs |= KVM_SYNC_RICCB;
F
Fan Zhang 已提交
2202 2203
	if (test_kvm_facility(vcpu->kvm, 133))
		vcpu->run->kvm_valid_regs |= KVM_SYNC_GSCB;
2204 2205 2206 2207
	/* fprs can be synchronized via vrs, even if the guest has no vx. With
	 * MACHINE_HAS_VX, (load|store)_fpu_regs() will work with vrs format.
	 */
	if (MACHINE_HAS_VX)
2208
		vcpu->run->kvm_valid_regs |= KVM_SYNC_VRS;
2209 2210
	else
		vcpu->run->kvm_valid_regs |= KVM_SYNC_FPRS;
2211 2212 2213 2214

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

2215 2216 2217
	return 0;
}

2218 2219 2220 2221
/* needs disabled preemption to protect from TOD sync and vcpu_load/put */
static void __start_cpu_timer_accounting(struct kvm_vcpu *vcpu)
{
	WARN_ON_ONCE(vcpu->arch.cputm_start != 0);
2222
	raw_write_seqcount_begin(&vcpu->arch.cputm_seqcount);
2223
	vcpu->arch.cputm_start = get_tod_clock_fast();
2224
	raw_write_seqcount_end(&vcpu->arch.cputm_seqcount);
2225 2226 2227 2228 2229 2230
}

/* needs disabled preemption to protect from TOD sync and vcpu_load/put */
static void __stop_cpu_timer_accounting(struct kvm_vcpu *vcpu)
{
	WARN_ON_ONCE(vcpu->arch.cputm_start == 0);
2231
	raw_write_seqcount_begin(&vcpu->arch.cputm_seqcount);
2232 2233
	vcpu->arch.sie_block->cputm -= get_tod_clock_fast() - vcpu->arch.cputm_start;
	vcpu->arch.cputm_start = 0;
2234
	raw_write_seqcount_end(&vcpu->arch.cputm_seqcount);
2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266
}

/* needs disabled preemption to protect from TOD sync and vcpu_load/put */
static void __enable_cpu_timer_accounting(struct kvm_vcpu *vcpu)
{
	WARN_ON_ONCE(vcpu->arch.cputm_enabled);
	vcpu->arch.cputm_enabled = true;
	__start_cpu_timer_accounting(vcpu);
}

/* needs disabled preemption to protect from TOD sync and vcpu_load/put */
static void __disable_cpu_timer_accounting(struct kvm_vcpu *vcpu)
{
	WARN_ON_ONCE(!vcpu->arch.cputm_enabled);
	__stop_cpu_timer_accounting(vcpu);
	vcpu->arch.cputm_enabled = false;
}

static void enable_cpu_timer_accounting(struct kvm_vcpu *vcpu)
{
	preempt_disable(); /* protect from TOD sync and vcpu_load/put */
	__enable_cpu_timer_accounting(vcpu);
	preempt_enable();
}

static void disable_cpu_timer_accounting(struct kvm_vcpu *vcpu)
{
	preempt_disable(); /* protect from TOD sync and vcpu_load/put */
	__disable_cpu_timer_accounting(vcpu);
	preempt_enable();
}

2267 2268 2269
/* set the cpu timer - may only be called from the VCPU thread itself */
void kvm_s390_set_cpu_timer(struct kvm_vcpu *vcpu, __u64 cputm)
{
2270
	preempt_disable(); /* protect from TOD sync and vcpu_load/put */
2271
	raw_write_seqcount_begin(&vcpu->arch.cputm_seqcount);
2272 2273
	if (vcpu->arch.cputm_enabled)
		vcpu->arch.cputm_start = get_tod_clock_fast();
2274
	vcpu->arch.sie_block->cputm = cputm;
2275
	raw_write_seqcount_end(&vcpu->arch.cputm_seqcount);
2276
	preempt_enable();
2277 2278
}

2279
/* update and get the cpu timer - can also be called from other VCPU threads */
2280 2281
__u64 kvm_s390_get_cpu_timer(struct kvm_vcpu *vcpu)
{
2282
	unsigned int seq;
2283 2284 2285 2286 2287
	__u64 value;

	if (unlikely(!vcpu->arch.cputm_enabled))
		return vcpu->arch.sie_block->cputm;

2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301
	preempt_disable(); /* protect from TOD sync and vcpu_load/put */
	do {
		seq = raw_read_seqcount(&vcpu->arch.cputm_seqcount);
		/*
		 * If the writer would ever execute a read in the critical
		 * section, e.g. in irq context, we have a deadlock.
		 */
		WARN_ON_ONCE((seq & 1) && smp_processor_id() == vcpu->cpu);
		value = vcpu->arch.sie_block->cputm;
		/* if cputm_start is 0, accounting is being started/stopped */
		if (likely(vcpu->arch.cputm_start))
			value -= get_tod_clock_fast() - vcpu->arch.cputm_start;
	} while (read_seqcount_retry(&vcpu->arch.cputm_seqcount, seq & ~1));
	preempt_enable();
2302
	return value;
2303 2304
}

2305 2306
void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
{
2307

2308
	gmap_enable(vcpu->arch.enabled_gmap);
2309
	atomic_or(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
2310
	if (vcpu->arch.cputm_enabled && !is_vcpu_idle(vcpu))
2311
		__start_cpu_timer_accounting(vcpu);
2312
	vcpu->cpu = cpu;
2313 2314 2315 2316
}

void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
{
2317
	vcpu->cpu = -1;
2318
	if (vcpu->arch.cputm_enabled && !is_vcpu_idle(vcpu))
2319
		__stop_cpu_timer_accounting(vcpu);
2320
	atomic_andnot(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
2321 2322
	vcpu->arch.enabled_gmap = gmap_get_enabled();
	gmap_disable(vcpu->arch.enabled_gmap);
2323

2324 2325 2326 2327 2328 2329 2330
}

static void kvm_s390_vcpu_initial_reset(struct kvm_vcpu *vcpu)
{
	/* this equals initial cpu reset in pop, but we don't switch to ESA */
	vcpu->arch.sie_block->gpsw.mask = 0UL;
	vcpu->arch.sie_block->gpsw.addr = 0UL;
2331
	kvm_s390_set_prefix(vcpu, 0);
2332
	kvm_s390_set_cpu_timer(vcpu, 0);
2333 2334 2335 2336 2337
	vcpu->arch.sie_block->ckc       = 0UL;
	vcpu->arch.sie_block->todpr     = 0;
	memset(vcpu->arch.sie_block->gcr, 0, 16 * sizeof(__u64));
	vcpu->arch.sie_block->gcr[0]  = 0xE0UL;
	vcpu->arch.sie_block->gcr[14] = 0xC2000000UL;
2338 2339 2340
	/* make sure the new fpc will be lazily loaded */
	save_fpu_regs();
	current->thread.fpu.fpc = 0;
2341
	vcpu->arch.sie_block->gbea = 1;
2342
	vcpu->arch.sie_block->pp = 0;
2343 2344
	vcpu->arch.pfault_token = KVM_S390_PFAULT_TOKEN_INVALID;
	kvm_clear_async_pf_completion_queue(vcpu);
2345 2346
	if (!kvm_s390_user_cpu_state_ctrl(vcpu->kvm))
		kvm_s390_vcpu_stop(vcpu);
2347
	kvm_s390_clear_local_irqs(vcpu);
2348 2349
}

2350
void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
2351
{
2352
	mutex_lock(&vcpu->kvm->lock);
2353
	preempt_disable();
2354
	vcpu->arch.sie_block->epoch = vcpu->kvm->arch.epoch;
2355
	preempt_enable();
2356
	mutex_unlock(&vcpu->kvm->lock);
2357
	if (!kvm_is_ucontrol(vcpu->kvm)) {
2358
		vcpu->arch.gmap = vcpu->kvm->arch.gmap;
2359
		sca_add_vcpu(vcpu);
2360
	}
2361 2362
	if (test_kvm_facility(vcpu->kvm, 74) || vcpu->kvm->arch.user_instr0)
		vcpu->arch.sie_block->ictl |= ICTL_OPEREXC;
2363 2364
	/* make vcpu_load load the right gmap on the first trigger */
	vcpu->arch.enabled_gmap = vcpu->arch.gmap;
2365 2366
}

2367 2368
static void kvm_s390_vcpu_crypto_setup(struct kvm_vcpu *vcpu)
{
2369
	if (!test_kvm_facility(vcpu->kvm, 76))
2370 2371
		return;

2372 2373 2374 2375 2376 2377 2378
	vcpu->arch.sie_block->ecb3 &= ~(ECB3_AES | ECB3_DEA);

	if (vcpu->kvm->arch.crypto.aes_kw)
		vcpu->arch.sie_block->ecb3 |= ECB3_AES;
	if (vcpu->kvm->arch.crypto.dea_kw)
		vcpu->arch.sie_block->ecb3 |= ECB3_DEA;

2379 2380 2381
	vcpu->arch.sie_block->crycbd = vcpu->kvm->arch.crypto.crycbd;
}

2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393
void kvm_s390_vcpu_unsetup_cmma(struct kvm_vcpu *vcpu)
{
	free_page(vcpu->arch.sie_block->cbrlo);
	vcpu->arch.sie_block->cbrlo = 0;
}

int kvm_s390_vcpu_setup_cmma(struct kvm_vcpu *vcpu)
{
	vcpu->arch.sie_block->cbrlo = get_zeroed_page(GFP_KERNEL);
	if (!vcpu->arch.sie_block->cbrlo)
		return -ENOMEM;

2394
	vcpu->arch.sie_block->ecb2 &= ~ECB2_PFMFI;
2395 2396 2397
	return 0;
}

2398 2399 2400 2401 2402
static void kvm_s390_vcpu_setup_model(struct kvm_vcpu *vcpu)
{
	struct kvm_s390_cpu_model *model = &vcpu->kvm->arch.model;

	vcpu->arch.sie_block->ibc = model->ibc;
2403
	if (test_kvm_facility(vcpu->kvm, 7))
2404
		vcpu->arch.sie_block->fac = (u32)(u64) model->fac_list;
2405 2406
}

2407 2408
int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
{
2409
	int rc = 0;
2410

2411 2412
	atomic_set(&vcpu->arch.sie_block->cpuflags, CPUSTAT_ZARCH |
						    CPUSTAT_SM |
2413 2414
						    CPUSTAT_STOPPED);

2415
	if (test_kvm_facility(vcpu->kvm, 78))
2416
		atomic_or(CPUSTAT_GED2, &vcpu->arch.sie_block->cpuflags);
2417
	else if (test_kvm_facility(vcpu->kvm, 8))
2418
		atomic_or(CPUSTAT_GED, &vcpu->arch.sie_block->cpuflags);
2419

2420 2421
	kvm_s390_vcpu_setup_model(vcpu);

2422 2423
	/* pgste_set_pte has special handling for !MACHINE_HAS_ESOP */
	if (MACHINE_HAS_ESOP)
2424
		vcpu->arch.sie_block->ecb |= ECB_HOSTPROTINT;
2425
	if (test_kvm_facility(vcpu->kvm, 9))
2426
		vcpu->arch.sie_block->ecb |= ECB_SRSI;
2427
	if (test_kvm_facility(vcpu->kvm, 73))
2428
		vcpu->arch.sie_block->ecb |= ECB_TE;
2429

2430
	if (test_kvm_facility(vcpu->kvm, 8) && sclp.has_pfmfi)
2431
		vcpu->arch.sie_block->ecb2 |= ECB2_PFMFI;
2432
	if (test_kvm_facility(vcpu->kvm, 130))
2433 2434
		vcpu->arch.sie_block->ecb2 |= ECB2_IEP;
	vcpu->arch.sie_block->eca = ECA_MVPGI | ECA_PROTEXCI;
2435
	if (sclp.has_cei)
2436
		vcpu->arch.sie_block->eca |= ECA_CEI;
2437
	if (sclp.has_ib)
2438
		vcpu->arch.sie_block->eca |= ECA_IB;
2439
	if (sclp.has_siif)
2440
		vcpu->arch.sie_block->eca |= ECA_SII;
2441
	if (sclp.has_sigpif)
2442
		vcpu->arch.sie_block->eca |= ECA_SIGPI;
2443
	if (test_kvm_facility(vcpu->kvm, 129)) {
2444 2445
		vcpu->arch.sie_block->eca |= ECA_VX;
		vcpu->arch.sie_block->ecd |= ECD_HOSTREGMGMT;
2446
	}
2447 2448 2449
	if (test_kvm_facility(vcpu->kvm, 139))
		vcpu->arch.sie_block->ecd |= ECD_MEF;

F
Fan Zhang 已提交
2450 2451
	vcpu->arch.sie_block->sdnxo = ((unsigned long) &vcpu->run->s.regs.sdnx)
					| SDNXC;
2452
	vcpu->arch.sie_block->riccbd = (unsigned long) &vcpu->run->s.regs.riccb;
2453 2454 2455 2456 2457

	if (sclp.has_kss)
		atomic_or(CPUSTAT_KSS, &vcpu->arch.sie_block->cpuflags);
	else
		vcpu->arch.sie_block->ictl |= ICTL_ISKE | ICTL_SSKE | ICTL_RRBE;
2458

2459
	if (vcpu->kvm->arch.use_cmma) {
2460 2461 2462
		rc = kvm_s390_vcpu_setup_cmma(vcpu);
		if (rc)
			return rc;
2463
	}
2464
	hrtimer_init(&vcpu->arch.ckc_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
2465
	vcpu->arch.ckc_timer.function = kvm_s390_idle_wakeup;
2466

2467 2468
	kvm_s390_vcpu_crypto_setup(vcpu);

2469
	return rc;
2470 2471 2472 2473 2474
}

struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
				      unsigned int id)
{
2475
	struct kvm_vcpu *vcpu;
2476
	struct sie_page *sie_page;
2477 2478
	int rc = -EINVAL;

2479
	if (!kvm_is_ucontrol(kvm) && !sca_can_add_vcpu(kvm, id))
2480 2481 2482
		goto out;

	rc = -ENOMEM;
2483

2484
	vcpu = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL);
2485
	if (!vcpu)
2486
		goto out;
2487

2488
	BUILD_BUG_ON(sizeof(struct sie_page) != 4096);
2489 2490
	sie_page = (struct sie_page *) get_zeroed_page(GFP_KERNEL);
	if (!sie_page)
2491 2492
		goto out_free_cpu;

2493 2494 2495
	vcpu->arch.sie_block = &sie_page->sie_block;
	vcpu->arch.sie_block->itdba = (unsigned long) &sie_page->itdb;

2496 2497 2498 2499
	/* the real guest size will always be smaller than msl */
	vcpu->arch.sie_block->mso = 0;
	vcpu->arch.sie_block->msl = sclp.hamax;

2500
	vcpu->arch.sie_block->icpua = id;
2501 2502
	spin_lock_init(&vcpu->arch.local_int.lock);
	vcpu->arch.local_int.float_int = &kvm->arch.float_int;
2503
	vcpu->arch.local_int.wq = &vcpu->wq;
2504
	vcpu->arch.local_int.cpuflags = &vcpu->arch.sie_block->cpuflags;
2505
	seqcount_init(&vcpu->arch.cputm_seqcount);
2506

2507 2508
	rc = kvm_vcpu_init(vcpu, kvm, id);
	if (rc)
2509
		goto out_free_sie_block;
2510
	VM_EVENT(kvm, 3, "create cpu %d at 0x%pK, sie block at 0x%pK", id, vcpu,
2511
		 vcpu->arch.sie_block);
2512
	trace_kvm_s390_create_vcpu(id, vcpu, vcpu->arch.sie_block);
2513 2514

	return vcpu;
2515 2516
out_free_sie_block:
	free_page((unsigned long)(vcpu->arch.sie_block));
2517
out_free_cpu:
2518
	kmem_cache_free(kvm_vcpu_cache, vcpu);
2519
out:
2520 2521 2522 2523 2524
	return ERR_PTR(rc);
}

int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
{
2525
	return kvm_s390_vcpu_has_irq(vcpu, 0);
2526 2527
}

2528 2529
bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu)
{
2530
	return !(vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE);
2531 2532
}

2533
void kvm_s390_vcpu_block(struct kvm_vcpu *vcpu)
2534
{
2535
	atomic_or(PROG_BLOCK_SIE, &vcpu->arch.sie_block->prog20);
2536
	exit_sie(vcpu);
2537 2538
}

2539
void kvm_s390_vcpu_unblock(struct kvm_vcpu *vcpu)
2540
{
2541
	atomic_andnot(PROG_BLOCK_SIE, &vcpu->arch.sie_block->prog20);
2542 2543
}

2544 2545
static void kvm_s390_vcpu_request(struct kvm_vcpu *vcpu)
{
2546
	atomic_or(PROG_REQUEST, &vcpu->arch.sie_block->prog20);
2547
	exit_sie(vcpu);
2548 2549 2550 2551
}

static void kvm_s390_vcpu_request_handled(struct kvm_vcpu *vcpu)
{
2552
	atomic_andnot(PROG_REQUEST, &vcpu->arch.sie_block->prog20);
2553 2554
}

2555 2556 2557 2558 2559 2560
/*
 * Kick a guest cpu out of SIE and wait until SIE is not running.
 * If the CPU is not running (e.g. waiting as idle) the function will
 * return immediately. */
void exit_sie(struct kvm_vcpu *vcpu)
{
2561
	atomic_or(CPUSTAT_STOP_INT, &vcpu->arch.sie_block->cpuflags);
2562 2563 2564 2565
	while (vcpu->arch.sie_block->prog0c & PROG_IN_SIE)
		cpu_relax();
}

2566 2567
/* Kick a guest cpu out of SIE to process a request synchronously */
void kvm_s390_sync_request(int req, struct kvm_vcpu *vcpu)
2568
{
2569 2570
	kvm_make_request(req, vcpu);
	kvm_s390_vcpu_request(vcpu);
2571 2572
}

2573 2574
static void kvm_gmap_notifier(struct gmap *gmap, unsigned long start,
			      unsigned long end)
2575 2576 2577
{
	struct kvm *kvm = gmap->private;
	struct kvm_vcpu *vcpu;
2578 2579
	unsigned long prefix;
	int i;
2580

2581 2582
	if (gmap_is_shadow(gmap))
		return;
2583 2584 2585
	if (start >= 1UL << 31)
		/* We are only interested in prefix pages */
		return;
2586 2587
	kvm_for_each_vcpu(i, vcpu, kvm) {
		/* match against both prefix pages */
2588 2589 2590 2591
		prefix = kvm_s390_get_prefix(vcpu);
		if (prefix <= end && start <= prefix + 2*PAGE_SIZE - 1) {
			VCPU_EVENT(vcpu, 2, "gmap notifier for %lx-%lx",
				   start, end);
2592
			kvm_s390_sync_request(KVM_REQ_MMU_RELOAD, vcpu);
2593 2594 2595 2596
		}
	}
}

2597 2598 2599 2600 2601 2602 2603
int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu)
{
	/* kvm common code refers to this, but never calls it */
	BUG();
	return 0;
}

2604 2605 2606 2607 2608 2609
static int kvm_arch_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu,
					   struct kvm_one_reg *reg)
{
	int r = -EINVAL;

	switch (reg->id) {
2610 2611 2612 2613 2614 2615 2616 2617
	case KVM_REG_S390_TODPR:
		r = put_user(vcpu->arch.sie_block->todpr,
			     (u32 __user *)reg->addr);
		break;
	case KVM_REG_S390_EPOCHDIFF:
		r = put_user(vcpu->arch.sie_block->epoch,
			     (u64 __user *)reg->addr);
		break;
2618
	case KVM_REG_S390_CPU_TIMER:
2619
		r = put_user(kvm_s390_get_cpu_timer(vcpu),
2620 2621 2622 2623 2624 2625
			     (u64 __user *)reg->addr);
		break;
	case KVM_REG_S390_CLOCK_COMP:
		r = put_user(vcpu->arch.sie_block->ckc,
			     (u64 __user *)reg->addr);
		break;
2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637
	case KVM_REG_S390_PFTOKEN:
		r = put_user(vcpu->arch.pfault_token,
			     (u64 __user *)reg->addr);
		break;
	case KVM_REG_S390_PFCOMPARE:
		r = put_user(vcpu->arch.pfault_compare,
			     (u64 __user *)reg->addr);
		break;
	case KVM_REG_S390_PFSELECT:
		r = put_user(vcpu->arch.pfault_select,
			     (u64 __user *)reg->addr);
		break;
2638 2639 2640 2641
	case KVM_REG_S390_PP:
		r = put_user(vcpu->arch.sie_block->pp,
			     (u64 __user *)reg->addr);
		break;
2642 2643 2644 2645
	case KVM_REG_S390_GBEA:
		r = put_user(vcpu->arch.sie_block->gbea,
			     (u64 __user *)reg->addr);
		break;
2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656
	default:
		break;
	}

	return r;
}

static int kvm_arch_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu,
					   struct kvm_one_reg *reg)
{
	int r = -EINVAL;
2657
	__u64 val;
2658 2659

	switch (reg->id) {
2660 2661 2662 2663 2664 2665 2666 2667
	case KVM_REG_S390_TODPR:
		r = get_user(vcpu->arch.sie_block->todpr,
			     (u32 __user *)reg->addr);
		break;
	case KVM_REG_S390_EPOCHDIFF:
		r = get_user(vcpu->arch.sie_block->epoch,
			     (u64 __user *)reg->addr);
		break;
2668
	case KVM_REG_S390_CPU_TIMER:
2669 2670 2671
		r = get_user(val, (u64 __user *)reg->addr);
		if (!r)
			kvm_s390_set_cpu_timer(vcpu, val);
2672 2673 2674 2675 2676
		break;
	case KVM_REG_S390_CLOCK_COMP:
		r = get_user(vcpu->arch.sie_block->ckc,
			     (u64 __user *)reg->addr);
		break;
2677 2678 2679
	case KVM_REG_S390_PFTOKEN:
		r = get_user(vcpu->arch.pfault_token,
			     (u64 __user *)reg->addr);
2680 2681
		if (vcpu->arch.pfault_token == KVM_S390_PFAULT_TOKEN_INVALID)
			kvm_clear_async_pf_completion_queue(vcpu);
2682 2683 2684 2685 2686 2687 2688 2689 2690
		break;
	case KVM_REG_S390_PFCOMPARE:
		r = get_user(vcpu->arch.pfault_compare,
			     (u64 __user *)reg->addr);
		break;
	case KVM_REG_S390_PFSELECT:
		r = get_user(vcpu->arch.pfault_select,
			     (u64 __user *)reg->addr);
		break;
2691 2692 2693 2694
	case KVM_REG_S390_PP:
		r = get_user(vcpu->arch.sie_block->pp,
			     (u64 __user *)reg->addr);
		break;
2695 2696 2697 2698
	case KVM_REG_S390_GBEA:
		r = get_user(vcpu->arch.sie_block->gbea,
			     (u64 __user *)reg->addr);
		break;
2699 2700 2701 2702 2703 2704
	default:
		break;
	}

	return r;
}
2705

2706 2707 2708 2709 2710 2711 2712 2713
static int kvm_arch_vcpu_ioctl_initial_reset(struct kvm_vcpu *vcpu)
{
	kvm_s390_vcpu_initial_reset(vcpu);
	return 0;
}

int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
{
2714
	memcpy(&vcpu->run->s.regs.gprs, &regs->gprs, sizeof(regs->gprs));
2715 2716 2717 2718 2719
	return 0;
}

int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
{
2720
	memcpy(&regs->gprs, &vcpu->run->s.regs.gprs, sizeof(regs->gprs));
2721 2722 2723 2724 2725 2726
	return 0;
}

int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
				  struct kvm_sregs *sregs)
{
2727
	memcpy(&vcpu->run->s.regs.acrs, &sregs->acrs, sizeof(sregs->acrs));
2728 2729 2730 2731 2732 2733 2734
	memcpy(&vcpu->arch.sie_block->gcr, &sregs->crs, sizeof(sregs->crs));
	return 0;
}

int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
				  struct kvm_sregs *sregs)
{
2735
	memcpy(&sregs->acrs, &vcpu->run->s.regs.acrs, sizeof(sregs->acrs));
2736 2737 2738 2739 2740 2741
	memcpy(&sregs->crs, &vcpu->arch.sie_block->gcr, sizeof(sregs->crs));
	return 0;
}

int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
{
2742 2743
	if (test_fp_ctl(fpu->fpc))
		return -EINVAL;
2744
	vcpu->run->s.regs.fpc = fpu->fpc;
2745
	if (MACHINE_HAS_VX)
2746 2747
		convert_fp_to_vx((__vector128 *) vcpu->run->s.regs.vrs,
				 (freg_t *) fpu->fprs);
2748
	else
2749
		memcpy(vcpu->run->s.regs.fprs, &fpu->fprs, sizeof(fpu->fprs));
2750 2751 2752 2753 2754
	return 0;
}

int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
{
2755 2756 2757
	/* make sure we have the latest values */
	save_fpu_regs();
	if (MACHINE_HAS_VX)
2758 2759
		convert_vx_to_fp((freg_t *) fpu->fprs,
				 (__vector128 *) vcpu->run->s.regs.vrs);
2760
	else
2761
		memcpy(fpu->fprs, vcpu->run->s.regs.fprs, sizeof(fpu->fprs));
2762
	fpu->fpc = vcpu->run->s.regs.fpc;
2763 2764 2765 2766 2767 2768 2769
	return 0;
}

static int kvm_arch_vcpu_ioctl_set_initial_psw(struct kvm_vcpu *vcpu, psw_t psw)
{
	int rc = 0;

2770
	if (!is_vcpu_stopped(vcpu))
2771
		rc = -EBUSY;
2772 2773 2774 2775
	else {
		vcpu->run->psw_mask = psw.mask;
		vcpu->run->psw_addr = psw.addr;
	}
2776 2777 2778 2779 2780 2781 2782 2783 2784
	return rc;
}

int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu,
				  struct kvm_translation *tr)
{
	return -EINVAL; /* not implemented yet */
}

2785 2786 2787 2788
#define VALID_GUESTDBG_FLAGS (KVM_GUESTDBG_SINGLESTEP | \
			      KVM_GUESTDBG_USE_HW_BP | \
			      KVM_GUESTDBG_ENABLE)

J
Jan Kiszka 已提交
2789 2790
int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
					struct kvm_guest_debug *dbg)
2791
{
2792 2793 2794 2795 2796
	int rc = 0;

	vcpu->guest_debug = 0;
	kvm_s390_clear_bp_data(vcpu);

2797
	if (dbg->control & ~VALID_GUESTDBG_FLAGS)
2798
		return -EINVAL;
2799 2800
	if (!sclp.has_gpere)
		return -EINVAL;
2801 2802 2803 2804

	if (dbg->control & KVM_GUESTDBG_ENABLE) {
		vcpu->guest_debug = dbg->control;
		/* enforce guest PER */
2805
		atomic_or(CPUSTAT_P, &vcpu->arch.sie_block->cpuflags);
2806 2807 2808 2809

		if (dbg->control & KVM_GUESTDBG_USE_HW_BP)
			rc = kvm_s390_import_bp_data(vcpu, dbg);
	} else {
2810
		atomic_andnot(CPUSTAT_P, &vcpu->arch.sie_block->cpuflags);
2811 2812 2813 2814 2815 2816
		vcpu->arch.guestdbg.last_bp = 0;
	}

	if (rc) {
		vcpu->guest_debug = 0;
		kvm_s390_clear_bp_data(vcpu);
2817
		atomic_andnot(CPUSTAT_P, &vcpu->arch.sie_block->cpuflags);
2818 2819 2820
	}

	return rc;
2821 2822
}

2823 2824 2825
int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
				    struct kvm_mp_state *mp_state)
{
2826 2827 2828
	/* CHECK_STOP and LOAD are not supported yet */
	return is_vcpu_stopped(vcpu) ? KVM_MP_STATE_STOPPED :
				       KVM_MP_STATE_OPERATING;
2829 2830 2831 2832 2833
}

int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
				    struct kvm_mp_state *mp_state)
{
2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853
	int rc = 0;

	/* user space knows about this interface - let it control the state */
	vcpu->kvm->arch.user_cpu_state_ctrl = 1;

	switch (mp_state->mp_state) {
	case KVM_MP_STATE_STOPPED:
		kvm_s390_vcpu_stop(vcpu);
		break;
	case KVM_MP_STATE_OPERATING:
		kvm_s390_vcpu_start(vcpu);
		break;
	case KVM_MP_STATE_LOAD:
	case KVM_MP_STATE_CHECK_STOP:
		/* fall through - CHECK_STOP and LOAD are not supported yet */
	default:
		rc = -ENXIO;
	}

	return rc;
2854 2855
}

2856 2857 2858 2859 2860
static bool ibs_enabled(struct kvm_vcpu *vcpu)
{
	return atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_IBS;
}

2861 2862
static int kvm_s390_handle_requests(struct kvm_vcpu *vcpu)
{
2863
retry:
2864
	kvm_s390_vcpu_request_handled(vcpu);
R
Radim Krčmář 已提交
2865
	if (!kvm_request_pending(vcpu))
2866
		return 0;
2867 2868
	/*
	 * We use MMU_RELOAD just to re-arm the ipte notifier for the
2869
	 * guest prefix page. gmap_mprotect_notify will wait on the ptl lock.
2870 2871 2872 2873
	 * This ensures that the ipte instruction for this request has
	 * already finished. We might race against a second unmapper that
	 * wants to set the blocking bit. Lets just retry the request loop.
	 */
2874
	if (kvm_check_request(KVM_REQ_MMU_RELOAD, vcpu)) {
2875
		int rc;
2876 2877 2878
		rc = gmap_mprotect_notify(vcpu->arch.gmap,
					  kvm_s390_get_prefix(vcpu),
					  PAGE_SIZE * 2, PROT_WRITE);
2879 2880
		if (rc) {
			kvm_make_request(KVM_REQ_MMU_RELOAD, vcpu);
2881
			return rc;
2882
		}
2883
		goto retry;
2884
	}
2885

2886 2887 2888 2889 2890
	if (kvm_check_request(KVM_REQ_TLB_FLUSH, vcpu)) {
		vcpu->arch.sie_block->ihcpu = 0xffff;
		goto retry;
	}

2891 2892 2893
	if (kvm_check_request(KVM_REQ_ENABLE_IBS, vcpu)) {
		if (!ibs_enabled(vcpu)) {
			trace_kvm_s390_enable_disable_ibs(vcpu->vcpu_id, 1);
2894
			atomic_or(CPUSTAT_IBS,
2895 2896 2897
					&vcpu->arch.sie_block->cpuflags);
		}
		goto retry;
2898
	}
2899 2900 2901 2902

	if (kvm_check_request(KVM_REQ_DISABLE_IBS, vcpu)) {
		if (ibs_enabled(vcpu)) {
			trace_kvm_s390_enable_disable_ibs(vcpu->vcpu_id, 0);
2903
			atomic_andnot(CPUSTAT_IBS,
2904 2905 2906 2907 2908
					  &vcpu->arch.sie_block->cpuflags);
		}
		goto retry;
	}

2909 2910 2911 2912 2913
	if (kvm_check_request(KVM_REQ_ICPT_OPEREXC, vcpu)) {
		vcpu->arch.sie_block->ictl |= ICTL_OPEREXC;
		goto retry;
	}

2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934
	if (kvm_check_request(KVM_REQ_START_MIGRATION, vcpu)) {
		/*
		 * Disable CMMA virtualization; we will emulate the ESSA
		 * instruction manually, in order to provide additional
		 * functionalities needed for live migration.
		 */
		vcpu->arch.sie_block->ecb2 &= ~ECB2_CMMA;
		goto retry;
	}

	if (kvm_check_request(KVM_REQ_STOP_MIGRATION, vcpu)) {
		/*
		 * Re-enable CMMA virtualization if CMMA is available and
		 * was used.
		 */
		if ((vcpu->kvm->arch.use_cmma) &&
		    (vcpu->kvm->mm->context.use_cmma))
			vcpu->arch.sie_block->ecb2 |= ECB2_CMMA;
		goto retry;
	}

2935
	/* nothing to do, just clear the request */
2936
	kvm_clear_request(KVM_REQ_UNHALT, vcpu);
2937

2938 2939 2940
	return 0;
}

2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969
void kvm_s390_set_tod_clock_ext(struct kvm *kvm,
				 const struct kvm_s390_vm_tod_clock *gtod)
{
	struct kvm_vcpu *vcpu;
	struct kvm_s390_tod_clock_ext htod;
	int i;

	mutex_lock(&kvm->lock);
	preempt_disable();

	get_tod_clock_ext((char *)&htod);

	kvm->arch.epoch = gtod->tod - htod.tod;
	kvm->arch.epdx = gtod->epoch_idx - htod.epoch_idx;

	if (kvm->arch.epoch > gtod->tod)
		kvm->arch.epdx -= 1;

	kvm_s390_vcpu_block_all(kvm);
	kvm_for_each_vcpu(i, vcpu, kvm) {
		vcpu->arch.sie_block->epoch = kvm->arch.epoch;
		vcpu->arch.sie_block->epdx  = kvm->arch.epdx;
	}

	kvm_s390_vcpu_unblock_all(kvm);
	preempt_enable();
	mutex_unlock(&kvm->lock);
}

2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985
void kvm_s390_set_tod_clock(struct kvm *kvm, u64 tod)
{
	struct kvm_vcpu *vcpu;
	int i;

	mutex_lock(&kvm->lock);
	preempt_disable();
	kvm->arch.epoch = tod - get_tod_clock();
	kvm_s390_vcpu_block_all(kvm);
	kvm_for_each_vcpu(i, vcpu, kvm)
		vcpu->arch.sie_block->epoch = kvm->arch.epoch;
	kvm_s390_vcpu_unblock_all(kvm);
	preempt_enable();
	mutex_unlock(&kvm->lock);
}

2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996
/**
 * kvm_arch_fault_in_page - fault-in guest page if necessary
 * @vcpu: The corresponding virtual cpu
 * @gpa: Guest physical address
 * @writable: Whether the page should be writable or not
 *
 * Make sure that a guest page has been faulted-in on the host.
 *
 * Return: Zero on success, negative error code otherwise.
 */
long kvm_arch_fault_in_page(struct kvm_vcpu *vcpu, gpa_t gpa, int writable)
2997
{
2998 2999
	return gmap_fault(vcpu->arch.gmap, gpa,
			  writable ? FAULT_FLAG_WRITE : 0);
3000 3001
}

3002 3003 3004 3005
static void __kvm_inject_pfault_token(struct kvm_vcpu *vcpu, bool start_token,
				      unsigned long token)
{
	struct kvm_s390_interrupt inti;
3006
	struct kvm_s390_irq irq;
3007 3008

	if (start_token) {
3009 3010 3011
		irq.u.ext.ext_params2 = token;
		irq.type = KVM_S390_INT_PFAULT_INIT;
		WARN_ON_ONCE(kvm_s390_inject_vcpu(vcpu, &irq));
3012 3013
	} else {
		inti.type = KVM_S390_INT_PFAULT_DONE;
3014
		inti.parm64 = token;
3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060
		WARN_ON_ONCE(kvm_s390_inject_vm(vcpu->kvm, &inti));
	}
}

void kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu,
				     struct kvm_async_pf *work)
{
	trace_kvm_s390_pfault_init(vcpu, work->arch.pfault_token);
	__kvm_inject_pfault_token(vcpu, true, work->arch.pfault_token);
}

void kvm_arch_async_page_present(struct kvm_vcpu *vcpu,
				 struct kvm_async_pf *work)
{
	trace_kvm_s390_pfault_done(vcpu, work->arch.pfault_token);
	__kvm_inject_pfault_token(vcpu, false, work->arch.pfault_token);
}

void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu,
			       struct kvm_async_pf *work)
{
	/* s390 will always inject the page directly */
}

bool kvm_arch_can_inject_async_page_present(struct kvm_vcpu *vcpu)
{
	/*
	 * s390 will always inject the page directly,
	 * but we still want check_async_completion to cleanup
	 */
	return true;
}

static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu)
{
	hva_t hva;
	struct kvm_arch_async_pf arch;
	int rc;

	if (vcpu->arch.pfault_token == KVM_S390_PFAULT_TOKEN_INVALID)
		return 0;
	if ((vcpu->arch.sie_block->gpsw.mask & vcpu->arch.pfault_select) !=
	    vcpu->arch.pfault_compare)
		return 0;
	if (psw_extint_disabled(vcpu))
		return 0;
3061
	if (kvm_s390_vcpu_has_irq(vcpu, 0))
3062 3063 3064 3065 3066 3067
		return 0;
	if (!(vcpu->arch.sie_block->gcr[0] & 0x200ul))
		return 0;
	if (!vcpu->arch.gmap->pfault_enabled)
		return 0;

H
Heiko Carstens 已提交
3068 3069 3070
	hva = gfn_to_hva(vcpu->kvm, gpa_to_gfn(current->thread.gmap_addr));
	hva += current->thread.gmap_addr & ~PAGE_MASK;
	if (read_guest_real(vcpu, vcpu->arch.pfault_token, &arch.pfault_token, 8))
3071 3072 3073 3074 3075 3076
		return 0;

	rc = kvm_setup_async_pf(vcpu, current->thread.gmap_addr, hva, &arch);
	return rc;
}

3077
static int vcpu_pre_run(struct kvm_vcpu *vcpu)
3078
{
3079
	int rc, cpuflags;
3080

3081 3082 3083 3084 3085 3086 3087
	/*
	 * On s390 notifications for arriving pages will be delivered directly
	 * to the guest but the house keeping for completed pfaults is
	 * handled outside the worker.
	 */
	kvm_check_async_pf_completion(vcpu);

3088 3089
	vcpu->arch.sie_block->gg14 = vcpu->run->s.regs.gprs[14];
	vcpu->arch.sie_block->gg15 = vcpu->run->s.regs.gprs[15];
3090 3091 3092 3093

	if (need_resched())
		schedule();

3094
	if (test_cpu_flag(CIF_MCCK_PENDING))
3095 3096
		s390_handle_mcck();

3097 3098 3099 3100 3101
	if (!kvm_is_ucontrol(vcpu->kvm)) {
		rc = kvm_s390_deliver_pending_interrupts(vcpu);
		if (rc)
			return rc;
	}
C
Carsten Otte 已提交
3102

3103 3104 3105 3106
	rc = kvm_s390_handle_requests(vcpu);
	if (rc)
		return rc;

3107 3108 3109 3110 3111
	if (guestdbg_enabled(vcpu)) {
		kvm_s390_backup_guest_per_regs(vcpu);
		kvm_s390_patch_guest_per_regs(vcpu);
	}

3112
	vcpu->arch.sie_block->icptcode = 0;
3113 3114 3115
	cpuflags = atomic_read(&vcpu->arch.sie_block->cpuflags);
	VCPU_EVENT(vcpu, 6, "entering sie flags %x", cpuflags);
	trace_kvm_s390_sie_enter(vcpu, cpuflags);
3116

3117 3118 3119
	return 0;
}

3120 3121
static int vcpu_post_run_fault_in_sie(struct kvm_vcpu *vcpu)
{
3122 3123 3124 3125
	struct kvm_s390_pgm_info pgm_info = {
		.code = PGM_ADDRESSING,
	};
	u8 opcode, ilen;
3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138
	int rc;

	VCPU_EVENT(vcpu, 3, "%s", "fault in sie instruction");
	trace_kvm_s390_sie_fault(vcpu);

	/*
	 * We want to inject an addressing exception, which is defined as a
	 * suppressing or terminating exception. However, since we came here
	 * by a DAT access exception, the PSW still points to the faulting
	 * instruction since DAT exceptions are nullifying. So we've got
	 * to look up the current opcode to get the length of the instruction
	 * to be able to forward the PSW.
	 */
3139
	rc = read_guest_instr(vcpu, vcpu->arch.sie_block->gpsw.addr, &opcode, 1);
3140
	ilen = insn_length(opcode);
3141 3142 3143 3144 3145 3146 3147 3148 3149 3150
	if (rc < 0) {
		return rc;
	} else if (rc) {
		/* Instruction-Fetching Exceptions - we can't detect the ilen.
		 * Forward by arbitrary ilc, injection will take care of
		 * nullification if necessary.
		 */
		pgm_info = vcpu->arch.pgm;
		ilen = 4;
	}
3151 3152 3153
	pgm_info.flags = ilen | KVM_S390_PGM_FLAGS_ILC_VALID;
	kvm_s390_forward_psw(vcpu, ilen);
	return kvm_s390_inject_prog_irq(vcpu, &pgm_info);
3154 3155
}

3156 3157
static int vcpu_post_run(struct kvm_vcpu *vcpu, int exit_reason)
{
3158 3159 3160
	struct mcck_volatile_info *mcck_info;
	struct sie_page *sie_page;

3161 3162 3163 3164
	VCPU_EVENT(vcpu, 6, "exit sie icptcode %d",
		   vcpu->arch.sie_block->icptcode);
	trace_kvm_s390_sie_exit(vcpu, vcpu->arch.sie_block->icptcode);

3165 3166 3167
	if (guestdbg_enabled(vcpu))
		kvm_s390_restore_guest_per_regs(vcpu);

3168 3169
	vcpu->run->s.regs.gprs[14] = vcpu->arch.sie_block->gg14;
	vcpu->run->s.regs.gprs[15] = vcpu->arch.sie_block->gg15;
3170

3171 3172 3173 3174 3175 3176 3177 3178 3179
	if (exit_reason == -EINTR) {
		VCPU_EVENT(vcpu, 3, "%s", "machine check");
		sie_page = container_of(vcpu->arch.sie_block,
					struct sie_page, sie_block);
		mcck_info = &sie_page->mcck_info;
		kvm_s390_reinject_machine_check(vcpu, mcck_info);
		return 0;
	}

3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192
	if (vcpu->arch.sie_block->icptcode > 0) {
		int rc = kvm_handle_sie_intercept(vcpu);

		if (rc != -EOPNOTSUPP)
			return rc;
		vcpu->run->exit_reason = KVM_EXIT_S390_SIEIC;
		vcpu->run->s390_sieic.icptcode = vcpu->arch.sie_block->icptcode;
		vcpu->run->s390_sieic.ipa = vcpu->arch.sie_block->ipa;
		vcpu->run->s390_sieic.ipb = vcpu->arch.sie_block->ipb;
		return -EREMOTE;
	} else if (exit_reason != -EFAULT) {
		vcpu->stat.exit_null++;
		return 0;
3193 3194 3195 3196 3197
	} else if (kvm_is_ucontrol(vcpu->kvm)) {
		vcpu->run->exit_reason = KVM_EXIT_S390_UCONTROL;
		vcpu->run->s390_ucontrol.trans_exc_code =
						current->thread.gmap_addr;
		vcpu->run->s390_ucontrol.pgm_code = 0x10;
3198
		return -EREMOTE;
3199
	} else if (current->thread.gmap_pfault) {
3200
		trace_kvm_s390_major_guest_pfault(vcpu);
3201
		current->thread.gmap_pfault = 0;
3202 3203 3204
		if (kvm_arch_setup_async_pf(vcpu))
			return 0;
		return kvm_arch_fault_in_page(vcpu, current->thread.gmap_addr, 1);
3205
	}
3206
	return vcpu_post_run_fault_in_sie(vcpu);
3207 3208 3209 3210 3211 3212
}

static int __vcpu_run(struct kvm_vcpu *vcpu)
{
	int rc, exit_reason;

3213 3214 3215 3216 3217 3218
	/*
	 * We try to hold kvm->srcu during most of vcpu_run (except when run-
	 * ning the guest), so that memslots (and other stuff) are protected
	 */
	vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);

3219 3220 3221 3222
	do {
		rc = vcpu_pre_run(vcpu);
		if (rc)
			break;
3223

3224
		srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
3225 3226 3227 3228
		/*
		 * As PF_VCPU will be used in fault handler, between
		 * guest_enter and guest_exit should be no uaccess.
		 */
3229
		local_irq_disable();
3230
		guest_enter_irqoff();
3231
		__disable_cpu_timer_accounting(vcpu);
3232
		local_irq_enable();
3233 3234
		exit_reason = sie64a(vcpu->arch.sie_block,
				     vcpu->run->s.regs.gprs);
3235
		local_irq_disable();
3236
		__enable_cpu_timer_accounting(vcpu);
3237
		guest_exit_irqoff();
3238
		local_irq_enable();
3239
		vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
3240 3241

		rc = vcpu_post_run(vcpu, exit_reason);
3242
	} while (!signal_pending(current) && !guestdbg_exit_pending(vcpu) && !rc);
3243

3244
	srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
3245
	return rc;
3246 3247
}

3248 3249
static void sync_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
{
3250
	struct runtime_instr_cb *riccb;
F
Fan Zhang 已提交
3251
	struct gs_cb *gscb;
3252 3253

	riccb = (struct runtime_instr_cb *) &kvm_run->s.regs.riccb;
F
Fan Zhang 已提交
3254
	gscb = (struct gs_cb *) &kvm_run->s.regs.gscb;
3255 3256 3257 3258 3259 3260
	vcpu->arch.sie_block->gpsw.mask = kvm_run->psw_mask;
	vcpu->arch.sie_block->gpsw.addr = kvm_run->psw_addr;
	if (kvm_run->kvm_dirty_regs & KVM_SYNC_PREFIX)
		kvm_s390_set_prefix(vcpu, kvm_run->s.regs.prefix);
	if (kvm_run->kvm_dirty_regs & KVM_SYNC_CRS) {
		memcpy(&vcpu->arch.sie_block->gcr, &kvm_run->s.regs.crs, 128);
3261 3262
		/* some control register changes require a tlb flush */
		kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
3263 3264
	}
	if (kvm_run->kvm_dirty_regs & KVM_SYNC_ARCH0) {
3265
		kvm_s390_set_cpu_timer(vcpu, kvm_run->s.regs.cputm);
3266 3267 3268 3269 3270 3271 3272 3273 3274
		vcpu->arch.sie_block->ckc = kvm_run->s.regs.ckc;
		vcpu->arch.sie_block->todpr = kvm_run->s.regs.todpr;
		vcpu->arch.sie_block->pp = kvm_run->s.regs.pp;
		vcpu->arch.sie_block->gbea = kvm_run->s.regs.gbea;
	}
	if (kvm_run->kvm_dirty_regs & KVM_SYNC_PFAULT) {
		vcpu->arch.pfault_token = kvm_run->s.regs.pft;
		vcpu->arch.pfault_select = kvm_run->s.regs.pfs;
		vcpu->arch.pfault_compare = kvm_run->s.regs.pfc;
3275 3276
		if (vcpu->arch.pfault_token == KVM_S390_PFAULT_TOKEN_INVALID)
			kvm_clear_async_pf_completion_queue(vcpu);
3277
	}
F
Fan Zhang 已提交
3278 3279 3280 3281 3282
	/*
	 * If userspace sets the riccb (e.g. after migration) to a valid state,
	 * we should enable RI here instead of doing the lazy enablement.
	 */
	if ((kvm_run->kvm_dirty_regs & KVM_SYNC_RICCB) &&
3283 3284
	    test_kvm_facility(vcpu->kvm, 64) &&
	    riccb->valid &&
3285
	    !(vcpu->arch.sie_block->ecb3 & ECB3_RI)) {
3286
		VCPU_EVENT(vcpu, 3, "%s", "ENABLE: RI (sync_regs)");
3287
		vcpu->arch.sie_block->ecb3 |= ECB3_RI;
F
Fan Zhang 已提交
3288
	}
F
Fan Zhang 已提交
3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300
	/*
	 * If userspace sets the gscb (e.g. after migration) to non-zero,
	 * we should enable GS here instead of doing the lazy enablement.
	 */
	if ((kvm_run->kvm_dirty_regs & KVM_SYNC_GSCB) &&
	    test_kvm_facility(vcpu->kvm, 133) &&
	    gscb->gssm &&
	    !vcpu->arch.gs_enabled) {
		VCPU_EVENT(vcpu, 3, "%s", "ENABLE: GS (sync_regs)");
		vcpu->arch.sie_block->ecb |= ECB_GS;
		vcpu->arch.sie_block->ecd |= ECD_HOSTREGMGMT;
		vcpu->arch.gs_enabled = 1;
F
Fan Zhang 已提交
3301
	}
3302 3303
	save_access_regs(vcpu->arch.host_acrs);
	restore_access_regs(vcpu->run->s.regs.acrs);
3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315
	/* save host (userspace) fprs/vrs */
	save_fpu_regs();
	vcpu->arch.host_fpregs.fpc = current->thread.fpu.fpc;
	vcpu->arch.host_fpregs.regs = current->thread.fpu.regs;
	if (MACHINE_HAS_VX)
		current->thread.fpu.regs = vcpu->run->s.regs.vrs;
	else
		current->thread.fpu.regs = vcpu->run->s.regs.fprs;
	current->thread.fpu.fpc = vcpu->run->s.regs.fpc;
	if (test_fp_ctl(current->thread.fpu.fpc))
		/* User space provided an invalid FPC, let's clear it */
		current->thread.fpu.fpc = 0;
F
Fan Zhang 已提交
3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329
	if (MACHINE_HAS_GS) {
		preempt_disable();
		__ctl_set_bit(2, 4);
		if (current->thread.gs_cb) {
			vcpu->arch.host_gscb = current->thread.gs_cb;
			save_gs_cb(vcpu->arch.host_gscb);
		}
		if (vcpu->arch.gs_enabled) {
			current->thread.gs_cb = (struct gs_cb *)
						&vcpu->run->s.regs.gscb;
			restore_gs_cb(current->thread.gs_cb);
		}
		preempt_enable();
	}
F
Fan Zhang 已提交
3330

3331 3332 3333 3334 3335 3336 3337 3338 3339
	kvm_run->kvm_dirty_regs = 0;
}

static void store_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
{
	kvm_run->psw_mask = vcpu->arch.sie_block->gpsw.mask;
	kvm_run->psw_addr = vcpu->arch.sie_block->gpsw.addr;
	kvm_run->s.regs.prefix = kvm_s390_get_prefix(vcpu);
	memcpy(&kvm_run->s.regs.crs, &vcpu->arch.sie_block->gcr, 128);
3340
	kvm_run->s.regs.cputm = kvm_s390_get_cpu_timer(vcpu);
3341 3342 3343 3344 3345 3346 3347
	kvm_run->s.regs.ckc = vcpu->arch.sie_block->ckc;
	kvm_run->s.regs.todpr = vcpu->arch.sie_block->todpr;
	kvm_run->s.regs.pp = vcpu->arch.sie_block->pp;
	kvm_run->s.regs.gbea = vcpu->arch.sie_block->gbea;
	kvm_run->s.regs.pft = vcpu->arch.pfault_token;
	kvm_run->s.regs.pfs = vcpu->arch.pfault_select;
	kvm_run->s.regs.pfc = vcpu->arch.pfault_compare;
3348 3349
	save_access_regs(vcpu->run->s.regs.acrs);
	restore_access_regs(vcpu->arch.host_acrs);
3350 3351 3352 3353 3354 3355
	/* Save guest register state */
	save_fpu_regs();
	vcpu->run->s.regs.fpc = current->thread.fpu.fpc;
	/* Restore will be done lazily at return */
	current->thread.fpu.fpc = vcpu->arch.host_fpregs.fpc;
	current->thread.fpu.regs = vcpu->arch.host_fpregs.regs;
F
Fan Zhang 已提交
3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367
	if (MACHINE_HAS_GS) {
		__ctl_set_bit(2, 4);
		if (vcpu->arch.gs_enabled)
			save_gs_cb(current->thread.gs_cb);
		preempt_disable();
		current->thread.gs_cb = vcpu->arch.host_gscb;
		restore_gs_cb(vcpu->arch.host_gscb);
		preempt_enable();
		if (!vcpu->arch.host_gscb)
			__ctl_clear_bit(2, 4);
		vcpu->arch.host_gscb = NULL;
	}
3368

3369 3370
}

3371 3372
int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
{
3373
	int rc;
3374 3375
	sigset_t sigsaved;

3376 3377 3378
	if (kvm_run->immediate_exit)
		return -EINTR;

3379 3380 3381 3382 3383
	if (guestdbg_exit_pending(vcpu)) {
		kvm_s390_prepare_debug_exit(vcpu);
		return 0;
	}

3384 3385 3386
	if (vcpu->sigset_active)
		sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved);

3387 3388 3389
	if (!kvm_s390_user_cpu_state_ctrl(vcpu->kvm)) {
		kvm_s390_vcpu_start(vcpu);
	} else if (is_vcpu_stopped(vcpu)) {
3390
		pr_err_ratelimited("can't run stopped vcpu %d\n",
3391 3392 3393
				   vcpu->vcpu_id);
		return -EINVAL;
	}
3394

3395
	sync_regs(vcpu, kvm_run);
3396
	enable_cpu_timer_accounting(vcpu);
3397

3398
	might_fault();
3399
	rc = __vcpu_run(vcpu);
3400

3401 3402
	if (signal_pending(current) && !rc) {
		kvm_run->exit_reason = KVM_EXIT_INTR;
3403
		rc = -EINTR;
3404
	}
3405

3406 3407 3408 3409 3410
	if (guestdbg_exit_pending(vcpu) && !rc)  {
		kvm_s390_prepare_debug_exit(vcpu);
		rc = 0;
	}

3411
	if (rc == -EREMOTE) {
3412
		/* userspace support is needed, kvm_run has been prepared */
3413 3414
		rc = 0;
	}
3415

3416
	disable_cpu_timer_accounting(vcpu);
3417
	store_regs(vcpu, kvm_run);
3418

3419 3420 3421 3422
	if (vcpu->sigset_active)
		sigprocmask(SIG_SETMASK, &sigsaved, NULL);

	vcpu->stat.exit_userspace++;
3423
	return rc;
3424 3425 3426 3427 3428 3429 3430 3431
}

/*
 * store status at address
 * we use have two special cases:
 * KVM_S390_STORE_STATUS_NOADDR: -> 0x1200 on 64 bit
 * KVM_S390_STORE_STATUS_PREFIXED: -> prefix
 */
3432
int kvm_s390_store_status_unloaded(struct kvm_vcpu *vcpu, unsigned long gpa)
3433
{
3434
	unsigned char archmode = 1;
3435
	freg_t fprs[NUM_FPRS];
3436
	unsigned int px;
3437
	u64 clkcomp, cputm;
3438
	int rc;
3439

3440
	px = kvm_s390_get_prefix(vcpu);
3441 3442
	if (gpa == KVM_S390_STORE_STATUS_NOADDR) {
		if (write_guest_abs(vcpu, 163, &archmode, 1))
3443
			return -EFAULT;
3444
		gpa = 0;
3445 3446
	} else if (gpa == KVM_S390_STORE_STATUS_PREFIXED) {
		if (write_guest_real(vcpu, 163, &archmode, 1))
3447
			return -EFAULT;
3448 3449 3450
		gpa = px;
	} else
		gpa -= __LC_FPREGS_SAVE_AREA;
3451 3452 3453

	/* manually convert vector registers if necessary */
	if (MACHINE_HAS_VX) {
3454
		convert_vx_to_fp(fprs, (__vector128 *) vcpu->run->s.regs.vrs);
3455 3456 3457 3458
		rc = write_guest_abs(vcpu, gpa + __LC_FPREGS_SAVE_AREA,
				     fprs, 128);
	} else {
		rc = write_guest_abs(vcpu, gpa + __LC_FPREGS_SAVE_AREA,
3459
				     vcpu->run->s.regs.fprs, 128);
3460
	}
3461
	rc |= write_guest_abs(vcpu, gpa + __LC_GPREGS_SAVE_AREA,
3462
			      vcpu->run->s.regs.gprs, 128);
3463
	rc |= write_guest_abs(vcpu, gpa + __LC_PSW_SAVE_AREA,
3464
			      &vcpu->arch.sie_block->gpsw, 16);
3465
	rc |= write_guest_abs(vcpu, gpa + __LC_PREFIX_SAVE_AREA,
3466
			      &px, 4);
3467
	rc |= write_guest_abs(vcpu, gpa + __LC_FP_CREG_SAVE_AREA,
3468
			      &vcpu->run->s.regs.fpc, 4);
3469
	rc |= write_guest_abs(vcpu, gpa + __LC_TOD_PROGREG_SAVE_AREA,
3470
			      &vcpu->arch.sie_block->todpr, 4);
3471
	cputm = kvm_s390_get_cpu_timer(vcpu);
3472
	rc |= write_guest_abs(vcpu, gpa + __LC_CPU_TIMER_SAVE_AREA,
3473
			      &cputm, 8);
3474
	clkcomp = vcpu->arch.sie_block->ckc >> 8;
3475
	rc |= write_guest_abs(vcpu, gpa + __LC_CLOCK_COMP_SAVE_AREA,
3476
			      &clkcomp, 8);
3477
	rc |= write_guest_abs(vcpu, gpa + __LC_AREGS_SAVE_AREA,
3478
			      &vcpu->run->s.regs.acrs, 64);
3479
	rc |= write_guest_abs(vcpu, gpa + __LC_CREGS_SAVE_AREA,
3480 3481
			      &vcpu->arch.sie_block->gcr, 128);
	return rc ? -EFAULT : 0;
3482 3483
}

3484 3485 3486 3487
int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr)
{
	/*
	 * The guest FPRS and ACRS are in the host FPRS/ACRS due to the lazy
3488
	 * switch in the run ioctl. Let's update our copies before we save
3489 3490
	 * it into the save area
	 */
3491
	save_fpu_regs();
3492
	vcpu->run->s.regs.fpc = current->thread.fpu.fpc;
3493 3494 3495 3496 3497
	save_access_regs(vcpu->run->s.regs.acrs);

	return kvm_s390_store_status_unloaded(vcpu, addr);
}

3498 3499 3500
static void __disable_ibs_on_vcpu(struct kvm_vcpu *vcpu)
{
	kvm_check_request(KVM_REQ_ENABLE_IBS, vcpu);
3501
	kvm_s390_sync_request(KVM_REQ_DISABLE_IBS, vcpu);
3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515
}

static void __disable_ibs_on_all_vcpus(struct kvm *kvm)
{
	unsigned int i;
	struct kvm_vcpu *vcpu;

	kvm_for_each_vcpu(i, vcpu, kvm) {
		__disable_ibs_on_vcpu(vcpu);
	}
}

static void __enable_ibs_on_vcpu(struct kvm_vcpu *vcpu)
{
3516 3517
	if (!sclp.has_ibs)
		return;
3518
	kvm_check_request(KVM_REQ_DISABLE_IBS, vcpu);
3519
	kvm_s390_sync_request(KVM_REQ_ENABLE_IBS, vcpu);
3520 3521
}

3522 3523
void kvm_s390_vcpu_start(struct kvm_vcpu *vcpu)
{
3524 3525 3526 3527 3528
	int i, online_vcpus, started_vcpus = 0;

	if (!is_vcpu_stopped(vcpu))
		return;

3529
	trace_kvm_s390_vcpu_start_stop(vcpu->vcpu_id, 1);
3530
	/* Only one cpu at a time may enter/leave the STOPPED state. */
3531
	spin_lock(&vcpu->kvm->arch.start_stop_lock);
3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550
	online_vcpus = atomic_read(&vcpu->kvm->online_vcpus);

	for (i = 0; i < online_vcpus; i++) {
		if (!is_vcpu_stopped(vcpu->kvm->vcpus[i]))
			started_vcpus++;
	}

	if (started_vcpus == 0) {
		/* we're the only active VCPU -> speed it up */
		__enable_ibs_on_vcpu(vcpu);
	} else if (started_vcpus == 1) {
		/*
		 * As we are starting a second VCPU, we have to disable
		 * the IBS facility on all VCPUs to remove potentially
		 * oustanding ENABLE requests.
		 */
		__disable_ibs_on_all_vcpus(vcpu->kvm);
	}

3551
	atomic_andnot(CPUSTAT_STOPPED, &vcpu->arch.sie_block->cpuflags);
3552 3553 3554 3555
	/*
	 * Another VCPU might have used IBS while we were offline.
	 * Let's play safe and flush the VCPU at startup.
	 */
3556
	kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
3557
	spin_unlock(&vcpu->kvm->arch.start_stop_lock);
3558
	return;
3559 3560 3561 3562
}

void kvm_s390_vcpu_stop(struct kvm_vcpu *vcpu)
{
3563 3564 3565 3566 3567 3568
	int i, online_vcpus, started_vcpus = 0;
	struct kvm_vcpu *started_vcpu = NULL;

	if (is_vcpu_stopped(vcpu))
		return;

3569
	trace_kvm_s390_vcpu_start_stop(vcpu->vcpu_id, 0);
3570
	/* Only one cpu at a time may enter/leave the STOPPED state. */
3571
	spin_lock(&vcpu->kvm->arch.start_stop_lock);
3572 3573
	online_vcpus = atomic_read(&vcpu->kvm->online_vcpus);

3574
	/* SIGP STOP and SIGP STOP AND STORE STATUS has been fully processed */
3575
	kvm_s390_clear_stop_irq(vcpu);
3576

3577
	atomic_or(CPUSTAT_STOPPED, &vcpu->arch.sie_block->cpuflags);
3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594
	__disable_ibs_on_vcpu(vcpu);

	for (i = 0; i < online_vcpus; i++) {
		if (!is_vcpu_stopped(vcpu->kvm->vcpus[i])) {
			started_vcpus++;
			started_vcpu = vcpu->kvm->vcpus[i];
		}
	}

	if (started_vcpus == 1) {
		/*
		 * As we only have one VCPU left, we want to enable the
		 * IBS facility for that VCPU to speed it up.
		 */
		__enable_ibs_on_vcpu(started_vcpu);
	}

3595
	spin_unlock(&vcpu->kvm->arch.start_stop_lock);
3596
	return;
3597 3598
}

3599 3600 3601 3602 3603 3604 3605 3606 3607
static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
				     struct kvm_enable_cap *cap)
{
	int r;

	if (cap->flags)
		return -EINVAL;

	switch (cap->cap) {
3608 3609 3610
	case KVM_CAP_S390_CSS_SUPPORT:
		if (!vcpu->kvm->arch.css_support) {
			vcpu->kvm->arch.css_support = 1;
3611
			VM_EVENT(vcpu->kvm, 3, "%s", "ENABLE: CSS support");
3612 3613 3614 3615
			trace_kvm_s390_enable_css(vcpu->kvm);
		}
		r = 0;
		break;
3616 3617 3618 3619 3620 3621 3622
	default:
		r = -EINVAL;
		break;
	}
	return r;
}

3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648
static long kvm_s390_guest_mem_op(struct kvm_vcpu *vcpu,
				  struct kvm_s390_mem_op *mop)
{
	void __user *uaddr = (void __user *)mop->buf;
	void *tmpbuf = NULL;
	int r, srcu_idx;
	const u64 supported_flags = KVM_S390_MEMOP_F_INJECT_EXCEPTION
				    | KVM_S390_MEMOP_F_CHECK_ONLY;

	if (mop->flags & ~supported_flags)
		return -EINVAL;

	if (mop->size > MEM_OP_MAX_SIZE)
		return -E2BIG;

	if (!(mop->flags & KVM_S390_MEMOP_F_CHECK_ONLY)) {
		tmpbuf = vmalloc(mop->size);
		if (!tmpbuf)
			return -ENOMEM;
	}

	srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);

	switch (mop->op) {
	case KVM_S390_MEMOP_LOGICAL_READ:
		if (mop->flags & KVM_S390_MEMOP_F_CHECK_ONLY) {
3649 3650
			r = check_gva_range(vcpu, mop->gaddr, mop->ar,
					    mop->size, GACC_FETCH);
3651 3652 3653 3654 3655 3656 3657 3658 3659 3660
			break;
		}
		r = read_guest(vcpu, mop->gaddr, mop->ar, tmpbuf, mop->size);
		if (r == 0) {
			if (copy_to_user(uaddr, tmpbuf, mop->size))
				r = -EFAULT;
		}
		break;
	case KVM_S390_MEMOP_LOGICAL_WRITE:
		if (mop->flags & KVM_S390_MEMOP_F_CHECK_ONLY) {
3661 3662
			r = check_gva_range(vcpu, mop->gaddr, mop->ar,
					    mop->size, GACC_STORE);
3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683
			break;
		}
		if (copy_from_user(tmpbuf, uaddr, mop->size)) {
			r = -EFAULT;
			break;
		}
		r = write_guest(vcpu, mop->gaddr, mop->ar, tmpbuf, mop->size);
		break;
	default:
		r = -EINVAL;
	}

	srcu_read_unlock(&vcpu->kvm->srcu, srcu_idx);

	if (r > 0 && (mop->flags & KVM_S390_MEMOP_F_INJECT_EXCEPTION) != 0)
		kvm_s390_inject_prog_irq(vcpu, &vcpu->arch.pgm);

	vfree(tmpbuf);
	return r;
}

3684 3685 3686 3687 3688
long kvm_arch_vcpu_ioctl(struct file *filp,
			 unsigned int ioctl, unsigned long arg)
{
	struct kvm_vcpu *vcpu = filp->private_data;
	void __user *argp = (void __user *)arg;
3689
	int idx;
3690
	long r;
3691

3692
	switch (ioctl) {
3693 3694 3695 3696 3697 3698 3699 3700 3701
	case KVM_S390_IRQ: {
		struct kvm_s390_irq s390irq;

		r = -EFAULT;
		if (copy_from_user(&s390irq, argp, sizeof(s390irq)))
			break;
		r = kvm_s390_inject_vcpu(vcpu, &s390irq);
		break;
	}
3702
	case KVM_S390_INTERRUPT: {
3703
		struct kvm_s390_interrupt s390int;
3704
		struct kvm_s390_irq s390irq;
3705

3706
		r = -EFAULT;
3707
		if (copy_from_user(&s390int, argp, sizeof(s390int)))
3708
			break;
3709 3710 3711
		if (s390int_to_s390irq(&s390int, &s390irq))
			return -EINVAL;
		r = kvm_s390_inject_vcpu(vcpu, &s390irq);
3712
		break;
3713
	}
3714
	case KVM_S390_STORE_STATUS:
3715
		idx = srcu_read_lock(&vcpu->kvm->srcu);
3716
		r = kvm_s390_vcpu_store_status(vcpu, arg);
3717
		srcu_read_unlock(&vcpu->kvm->srcu, idx);
3718
		break;
3719 3720 3721
	case KVM_S390_SET_INITIAL_PSW: {
		psw_t psw;

3722
		r = -EFAULT;
3723
		if (copy_from_user(&psw, argp, sizeof(psw)))
3724 3725 3726
			break;
		r = kvm_arch_vcpu_ioctl_set_initial_psw(vcpu, psw);
		break;
3727 3728
	}
	case KVM_S390_INITIAL_RESET:
3729 3730
		r = kvm_arch_vcpu_ioctl_initial_reset(vcpu);
		break;
3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742
	case KVM_SET_ONE_REG:
	case KVM_GET_ONE_REG: {
		struct kvm_one_reg reg;
		r = -EFAULT;
		if (copy_from_user(&reg, argp, sizeof(reg)))
			break;
		if (ioctl == KVM_SET_ONE_REG)
			r = kvm_arch_vcpu_ioctl_set_one_reg(vcpu, &reg);
		else
			r = kvm_arch_vcpu_ioctl_get_one_reg(vcpu, &reg);
		break;
	}
3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778
#ifdef CONFIG_KVM_S390_UCONTROL
	case KVM_S390_UCAS_MAP: {
		struct kvm_s390_ucas_mapping ucasmap;

		if (copy_from_user(&ucasmap, argp, sizeof(ucasmap))) {
			r = -EFAULT;
			break;
		}

		if (!kvm_is_ucontrol(vcpu->kvm)) {
			r = -EINVAL;
			break;
		}

		r = gmap_map_segment(vcpu->arch.gmap, ucasmap.user_addr,
				     ucasmap.vcpu_addr, ucasmap.length);
		break;
	}
	case KVM_S390_UCAS_UNMAP: {
		struct kvm_s390_ucas_mapping ucasmap;

		if (copy_from_user(&ucasmap, argp, sizeof(ucasmap))) {
			r = -EFAULT;
			break;
		}

		if (!kvm_is_ucontrol(vcpu->kvm)) {
			r = -EINVAL;
			break;
		}

		r = gmap_unmap_segment(vcpu->arch.gmap, ucasmap.vcpu_addr,
			ucasmap.length);
		break;
	}
#endif
3779
	case KVM_S390_VCPU_FAULT: {
3780
		r = gmap_fault(vcpu->arch.gmap, arg, 0);
3781 3782
		break;
	}
3783 3784 3785 3786 3787 3788 3789 3790 3791
	case KVM_ENABLE_CAP:
	{
		struct kvm_enable_cap cap;
		r = -EFAULT;
		if (copy_from_user(&cap, argp, sizeof(cap)))
			break;
		r = kvm_vcpu_ioctl_enable_cap(vcpu, &cap);
		break;
	}
3792 3793 3794 3795 3796 3797 3798 3799 3800
	case KVM_S390_MEM_OP: {
		struct kvm_s390_mem_op mem_op;

		if (copy_from_user(&mem_op, argp, sizeof(mem_op)) == 0)
			r = kvm_s390_guest_mem_op(vcpu, &mem_op);
		else
			r = -EFAULT;
		break;
	}
3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832
	case KVM_S390_SET_IRQ_STATE: {
		struct kvm_s390_irq_state irq_state;

		r = -EFAULT;
		if (copy_from_user(&irq_state, argp, sizeof(irq_state)))
			break;
		if (irq_state.len > VCPU_IRQS_MAX_BUF ||
		    irq_state.len == 0 ||
		    irq_state.len % sizeof(struct kvm_s390_irq) > 0) {
			r = -EINVAL;
			break;
		}
		r = kvm_s390_set_irq_state(vcpu,
					   (void __user *) irq_state.buf,
					   irq_state.len);
		break;
	}
	case KVM_S390_GET_IRQ_STATE: {
		struct kvm_s390_irq_state irq_state;

		r = -EFAULT;
		if (copy_from_user(&irq_state, argp, sizeof(irq_state)))
			break;
		if (irq_state.len == 0) {
			r = -EINVAL;
			break;
		}
		r = kvm_s390_get_irq_state(vcpu,
					   (__u8 __user *)  irq_state.buf,
					   irq_state.len);
		break;
	}
3833
	default:
3834
		r = -ENOTTY;
3835
	}
3836
	return r;
3837 3838
}

3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851
int kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf)
{
#ifdef CONFIG_KVM_S390_UCONTROL
	if ((vmf->pgoff == KVM_S390_SIE_PAGE_OFFSET)
		 && (kvm_is_ucontrol(vcpu->kvm))) {
		vmf->page = virt_to_page(vcpu->arch.sie_block);
		get_page(vmf->page);
		return 0;
	}
#endif
	return VM_FAULT_SIGBUS;
}

3852 3853
int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
			    unsigned long npages)
3854 3855 3856 3857
{
	return 0;
}

3858
/* Section: memory related */
3859 3860
int kvm_arch_prepare_memory_region(struct kvm *kvm,
				   struct kvm_memory_slot *memslot,
3861
				   const struct kvm_userspace_memory_region *mem,
3862
				   enum kvm_mr_change change)
3863
{
3864 3865 3866 3867
	/* A few sanity checks. We can have memory slots which have to be
	   located/ended at a segment boundary (1MB). The memory in userland is
	   ok to be fragmented into various different vmas. It is okay to mmap()
	   and munmap() stuff in this slot after doing this call at any time */
3868

3869
	if (mem->userspace_addr & 0xffffful)
3870 3871
		return -EINVAL;

3872
	if (mem->memory_size & 0xffffful)
3873 3874
		return -EINVAL;

3875 3876 3877
	if (mem->guest_phys_addr + mem->memory_size > kvm->arch.mem_limit)
		return -EINVAL;

3878 3879 3880 3881
	return 0;
}

void kvm_arch_commit_memory_region(struct kvm *kvm,
3882
				const struct kvm_userspace_memory_region *mem,
3883
				const struct kvm_memory_slot *old,
3884
				const struct kvm_memory_slot *new,
3885
				enum kvm_mr_change change)
3886
{
3887
	int rc;
3888

3889 3890 3891 3892 3893 3894 3895 3896 3897 3898
	/* If the basics of the memslot do not change, we do not want
	 * to update the gmap. Every update causes several unnecessary
	 * segment translation exceptions. This is usually handled just
	 * fine by the normal fault handler + gmap, but it will also
	 * cause faults on the prefix page of running guest CPUs.
	 */
	if (old->userspace_addr == mem->userspace_addr &&
	    old->base_gfn * PAGE_SIZE == mem->guest_phys_addr &&
	    old->npages * PAGE_SIZE == mem->memory_size)
		return;
3899 3900 3901 3902

	rc = gmap_map_segment(kvm->arch.gmap, mem->userspace_addr,
		mem->guest_phys_addr, mem->memory_size);
	if (rc)
3903
		pr_warn("failed to commit memory region\n");
3904
	return;
3905 3906
}

3907 3908 3909 3910 3911 3912 3913
static inline unsigned long nonhyp_mask(int i)
{
	unsigned int nonhyp_fai = (sclp.hmfai << i * 2) >> 30;

	return 0x0000ffffffffffffUL >> (nonhyp_fai << 4);
}

3914 3915 3916 3917 3918
void kvm_arch_vcpu_block_finish(struct kvm_vcpu *vcpu)
{
	vcpu->valid_wakeup = false;
}

3919 3920
static int __init kvm_s390_init(void)
{
3921 3922
	int i;

3923 3924 3925 3926 3927
	if (!sclp.has_sief2) {
		pr_info("SIE not available\n");
		return -ENODEV;
	}

3928 3929 3930 3931
	for (i = 0; i < 16; i++)
		kvm_s390_fac_list_mask[i] |=
			S390_lowcore.stfle_fac_list[i] & nonhyp_mask(i);

3932
	return kvm_init(NULL, sizeof(struct kvm_vcpu), 0, THIS_MODULE);
3933 3934 3935 3936 3937 3938 3939 3940 3941
}

static void __exit kvm_s390_exit(void)
{
	kvm_exit();
}

module_init(kvm_s390_init);
module_exit(kvm_s390_exit);
3942 3943 3944 3945 3946 3947 3948 3949 3950

/*
 * Enable autoloading of the kvm module.
 * Note that we add the module alias here instead of virt/kvm/kvm_main.c
 * since x86 takes a different approach.
 */
#include <linux/miscdevice.h>
MODULE_ALIAS_MISCDEV(KVM_MINOR);
MODULE_ALIAS("devname:kvm");