booke.c 33.8 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15
/*
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License, version 2, as
 * published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write to the Free Software
 * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
 *
 * Copyright IBM Corp. 2007
16
 * Copyright 2010-2011 Freescale Semiconductor, Inc.
17 18 19
 *
 * Authors: Hollis Blanchard <hollisb@us.ibm.com>
 *          Christian Ehrhardt <ehrhardt@linux.vnet.ibm.com>
20 21
 *          Scott Wood <scottwood@freescale.com>
 *          Varun Sethi <varun.sethi@freescale.com>
22 23 24 25 26
 */

#include <linux/errno.h>
#include <linux/err.h>
#include <linux/kvm_host.h>
27
#include <linux/gfp.h>
28 29 30
#include <linux/module.h>
#include <linux/vmalloc.h>
#include <linux/fs.h>
31

32 33 34
#include <asm/cputable.h>
#include <asm/uaccess.h>
#include <asm/kvm_ppc.h>
35
#include <asm/cacheflush.h>
36 37 38
#include <asm/dbell.h>
#include <asm/hw_irq.h>
#include <asm/irq.h>
39

40
#include "timing.h"
41
#include "booke.h"
42

43 44
unsigned long kvmppc_booke_handlers;

45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61
#define VM_STAT(x) offsetof(struct kvm, stat.x), KVM_STAT_VM
#define VCPU_STAT(x) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU

struct kvm_stats_debugfs_item debugfs_entries[] = {
	{ "mmio",       VCPU_STAT(mmio_exits) },
	{ "dcr",        VCPU_STAT(dcr_exits) },
	{ "sig",        VCPU_STAT(signal_exits) },
	{ "itlb_r",     VCPU_STAT(itlb_real_miss_exits) },
	{ "itlb_v",     VCPU_STAT(itlb_virt_miss_exits) },
	{ "dtlb_r",     VCPU_STAT(dtlb_real_miss_exits) },
	{ "dtlb_v",     VCPU_STAT(dtlb_virt_miss_exits) },
	{ "sysc",       VCPU_STAT(syscall_exits) },
	{ "isi",        VCPU_STAT(isi_exits) },
	{ "dsi",        VCPU_STAT(dsi_exits) },
	{ "inst_emu",   VCPU_STAT(emulated_inst_exits) },
	{ "dec",        VCPU_STAT(dec_exits) },
	{ "ext_intr",   VCPU_STAT(ext_intr_exits) },
62
	{ "halt_wakeup", VCPU_STAT(halt_wakeup) },
63 64
	{ "doorbell", VCPU_STAT(dbell_exits) },
	{ "guest doorbell", VCPU_STAT(gdbell_exits) },
65 66 67 68 69 70 71 72
	{ NULL }
};

/* TODO: use vcpu_printf() */
void kvmppc_dump_vcpu(struct kvm_vcpu *vcpu)
{
	int i;

73
	printk("pc:   %08lx msr:  %08llx\n", vcpu->arch.pc, vcpu->arch.shared->msr);
74
	printk("lr:   %08lx ctr:  %08lx\n", vcpu->arch.lr, vcpu->arch.ctr);
75 76
	printk("srr0: %08llx srr1: %08llx\n", vcpu->arch.shared->srr0,
					    vcpu->arch.shared->srr1);
77 78 79 80

	printk("exceptions: %08lx\n", vcpu->arch.pending_exceptions);

	for (i = 0; i < 32; i += 4) {
81
		printk("gpr%02d: %08lx %08lx %08lx %08lx\n", i,
82 83 84 85
		       kvmppc_get_gpr(vcpu, i),
		       kvmppc_get_gpr(vcpu, i+1),
		       kvmppc_get_gpr(vcpu, i+2),
		       kvmppc_get_gpr(vcpu, i+3));
86 87 88
	}
}

89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122
#ifdef CONFIG_SPE
void kvmppc_vcpu_disable_spe(struct kvm_vcpu *vcpu)
{
	preempt_disable();
	enable_kernel_spe();
	kvmppc_save_guest_spe(vcpu);
	vcpu->arch.shadow_msr &= ~MSR_SPE;
	preempt_enable();
}

static void kvmppc_vcpu_enable_spe(struct kvm_vcpu *vcpu)
{
	preempt_disable();
	enable_kernel_spe();
	kvmppc_load_guest_spe(vcpu);
	vcpu->arch.shadow_msr |= MSR_SPE;
	preempt_enable();
}

static void kvmppc_vcpu_sync_spe(struct kvm_vcpu *vcpu)
{
	if (vcpu->arch.shared->msr & MSR_SPE) {
		if (!(vcpu->arch.shadow_msr & MSR_SPE))
			kvmppc_vcpu_enable_spe(vcpu);
	} else if (vcpu->arch.shadow_msr & MSR_SPE) {
		kvmppc_vcpu_disable_spe(vcpu);
	}
}
#else
static void kvmppc_vcpu_sync_spe(struct kvm_vcpu *vcpu)
{
}
#endif

L
Liu Yu 已提交
123 124 125 126
/*
 * Helper function for "full" MSR writes.  No need to call this if only
 * EE/CE/ME/DE/RI are changing.
 */
127 128
void kvmppc_set_msr(struct kvm_vcpu *vcpu, u32 new_msr)
{
L
Liu Yu 已提交
129
	u32 old_msr = vcpu->arch.shared->msr;
130

131 132 133 134
#ifdef CONFIG_KVM_BOOKE_HV
	new_msr |= MSR_GS;
#endif

135 136
	vcpu->arch.shared->msr = new_msr;

L
Liu Yu 已提交
137
	kvmppc_mmu_msr_notify(vcpu, old_msr);
138 139 140
	kvmppc_vcpu_sync_spe(vcpu);
}

141 142
static void kvmppc_booke_queue_irqprio(struct kvm_vcpu *vcpu,
                                       unsigned int priority)
143 144 145 146
{
	set_bit(priority, &vcpu->arch.pending_exceptions);
}

147 148
static void kvmppc_core_queue_dtlb_miss(struct kvm_vcpu *vcpu,
                                        ulong dear_flags, ulong esr_flags)
149
{
150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172
	vcpu->arch.queued_dear = dear_flags;
	vcpu->arch.queued_esr = esr_flags;
	kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_DTLB_MISS);
}

static void kvmppc_core_queue_data_storage(struct kvm_vcpu *vcpu,
                                           ulong dear_flags, ulong esr_flags)
{
	vcpu->arch.queued_dear = dear_flags;
	vcpu->arch.queued_esr = esr_flags;
	kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_DATA_STORAGE);
}

static void kvmppc_core_queue_inst_storage(struct kvm_vcpu *vcpu,
                                           ulong esr_flags)
{
	vcpu->arch.queued_esr = esr_flags;
	kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_INST_STORAGE);
}

void kvmppc_core_queue_program(struct kvm_vcpu *vcpu, ulong esr_flags)
{
	vcpu->arch.queued_esr = esr_flags;
173
	kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_PROGRAM);
174 175 176 177
}

void kvmppc_core_queue_dec(struct kvm_vcpu *vcpu)
{
178
	kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_DECREMENTER);
179 180 181 182
}

int kvmppc_core_pending_dec(struct kvm_vcpu *vcpu)
{
183
	return test_bit(BOOKE_IRQPRIO_DECREMENTER, &vcpu->arch.pending_exceptions);
184 185
}

186 187 188 189 190
void kvmppc_core_dequeue_dec(struct kvm_vcpu *vcpu)
{
	clear_bit(BOOKE_IRQPRIO_DECREMENTER, &vcpu->arch.pending_exceptions);
}

191 192 193
void kvmppc_core_queue_external(struct kvm_vcpu *vcpu,
                                struct kvm_interrupt *irq)
{
194 195 196 197 198 199
	unsigned int prio = BOOKE_IRQPRIO_EXTERNAL;

	if (irq->irq == KVM_INTERRUPT_SET_LEVEL)
		prio = BOOKE_IRQPRIO_EXTERNAL_LEVEL;

	kvmppc_booke_queue_irqprio(vcpu, prio);
200 201
}

202 203 204 205
void kvmppc_core_dequeue_external(struct kvm_vcpu *vcpu,
                                  struct kvm_interrupt *irq)
{
	clear_bit(BOOKE_IRQPRIO_EXTERNAL, &vcpu->arch.pending_exceptions);
206
	clear_bit(BOOKE_IRQPRIO_EXTERNAL_LEVEL, &vcpu->arch.pending_exceptions);
207 208
}

209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277
static void set_guest_srr(struct kvm_vcpu *vcpu, unsigned long srr0, u32 srr1)
{
#ifdef CONFIG_KVM_BOOKE_HV
	mtspr(SPRN_GSRR0, srr0);
	mtspr(SPRN_GSRR1, srr1);
#else
	vcpu->arch.shared->srr0 = srr0;
	vcpu->arch.shared->srr1 = srr1;
#endif
}

static void set_guest_csrr(struct kvm_vcpu *vcpu, unsigned long srr0, u32 srr1)
{
	vcpu->arch.csrr0 = srr0;
	vcpu->arch.csrr1 = srr1;
}

static void set_guest_dsrr(struct kvm_vcpu *vcpu, unsigned long srr0, u32 srr1)
{
	if (cpu_has_feature(CPU_FTR_DEBUG_LVL_EXC)) {
		vcpu->arch.dsrr0 = srr0;
		vcpu->arch.dsrr1 = srr1;
	} else {
		set_guest_csrr(vcpu, srr0, srr1);
	}
}

static void set_guest_mcsrr(struct kvm_vcpu *vcpu, unsigned long srr0, u32 srr1)
{
	vcpu->arch.mcsrr0 = srr0;
	vcpu->arch.mcsrr1 = srr1;
}

static unsigned long get_guest_dear(struct kvm_vcpu *vcpu)
{
#ifdef CONFIG_KVM_BOOKE_HV
	return mfspr(SPRN_GDEAR);
#else
	return vcpu->arch.shared->dar;
#endif
}

static void set_guest_dear(struct kvm_vcpu *vcpu, unsigned long dear)
{
#ifdef CONFIG_KVM_BOOKE_HV
	mtspr(SPRN_GDEAR, dear);
#else
	vcpu->arch.shared->dar = dear;
#endif
}

static unsigned long get_guest_esr(struct kvm_vcpu *vcpu)
{
#ifdef CONFIG_KVM_BOOKE_HV
	return mfspr(SPRN_GESR);
#else
	return vcpu->arch.shared->esr;
#endif
}

static void set_guest_esr(struct kvm_vcpu *vcpu, u32 esr)
{
#ifdef CONFIG_KVM_BOOKE_HV
	mtspr(SPRN_GESR, esr);
#else
	vcpu->arch.shared->esr = esr;
#endif
}

278 279 280
/* Deliver the interrupt of the corresponding priority, if possible. */
static int kvmppc_booke_irqprio_deliver(struct kvm_vcpu *vcpu,
                                        unsigned int priority)
281
{
282
	int allowed = 0;
283
	ulong msr_mask = 0;
284
	bool update_esr = false, update_dear = false;
285 286 287
	ulong crit_raw = vcpu->arch.shared->critical;
	ulong crit_r1 = kvmppc_get_gpr(vcpu, 1);
	bool crit;
288
	bool keep_irq = false;
289
	enum int_class int_class;
290 291 292 293 294 295 296 297 298 299 300

	/* Truncate crit indicators in 32 bit mode */
	if (!(vcpu->arch.shared->msr & MSR_SF)) {
		crit_raw &= 0xffffffff;
		crit_r1 &= 0xffffffff;
	}

	/* Critical section when crit == r1 */
	crit = (crit_raw == crit_r1);
	/* ... and we're in supervisor mode */
	crit = crit && !(vcpu->arch.shared->msr & MSR_PR);
301

302 303 304 305 306
	if (priority == BOOKE_IRQPRIO_EXTERNAL_LEVEL) {
		priority = BOOKE_IRQPRIO_EXTERNAL;
		keep_irq = true;
	}

307 308 309
	switch (priority) {
	case BOOKE_IRQPRIO_DTLB_MISS:
	case BOOKE_IRQPRIO_DATA_STORAGE:
310 311
		update_dear = true;
		/* fall through */
312
	case BOOKE_IRQPRIO_INST_STORAGE:
313 314 315 316 317
	case BOOKE_IRQPRIO_PROGRAM:
		update_esr = true;
		/* fall through */
	case BOOKE_IRQPRIO_ITLB_MISS:
	case BOOKE_IRQPRIO_SYSCALL:
318
	case BOOKE_IRQPRIO_FP_UNAVAIL:
319 320 321
	case BOOKE_IRQPRIO_SPE_UNAVAIL:
	case BOOKE_IRQPRIO_SPE_FP_DATA:
	case BOOKE_IRQPRIO_SPE_FP_ROUND:
322 323 324
	case BOOKE_IRQPRIO_AP_UNAVAIL:
	case BOOKE_IRQPRIO_ALIGNMENT:
		allowed = 1;
325
		msr_mask = MSR_CE | MSR_ME | MSR_DE;
326
		int_class = INT_CLASS_NONCRIT;
327
		break;
328
	case BOOKE_IRQPRIO_CRITICAL:
329
	case BOOKE_IRQPRIO_DBELL_CRIT:
330
		allowed = vcpu->arch.shared->msr & MSR_CE;
331
		allowed = allowed && !crit;
332
		msr_mask = MSR_ME;
333
		int_class = INT_CLASS_CRIT;
334
		break;
335
	case BOOKE_IRQPRIO_MACHINE_CHECK:
336
		allowed = vcpu->arch.shared->msr & MSR_ME;
337 338
		allowed = allowed && !crit;
		int_class = INT_CLASS_MC;
339
		break;
340 341
	case BOOKE_IRQPRIO_DECREMENTER:
	case BOOKE_IRQPRIO_FIT:
342 343 344
		keep_irq = true;
		/* fall through */
	case BOOKE_IRQPRIO_EXTERNAL:
345
	case BOOKE_IRQPRIO_DBELL:
346
		allowed = vcpu->arch.shared->msr & MSR_EE;
347
		allowed = allowed && !crit;
348
		msr_mask = MSR_CE | MSR_ME | MSR_DE;
349
		int_class = INT_CLASS_NONCRIT;
350
		break;
351
	case BOOKE_IRQPRIO_DEBUG:
352
		allowed = vcpu->arch.shared->msr & MSR_DE;
353
		allowed = allowed && !crit;
354
		msr_mask = MSR_ME;
355
		int_class = INT_CLASS_CRIT;
356 357 358
		break;
	}

359
	if (allowed) {
360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378
		switch (int_class) {
		case INT_CLASS_NONCRIT:
			set_guest_srr(vcpu, vcpu->arch.pc,
				      vcpu->arch.shared->msr);
			break;
		case INT_CLASS_CRIT:
			set_guest_csrr(vcpu, vcpu->arch.pc,
				       vcpu->arch.shared->msr);
			break;
		case INT_CLASS_DBG:
			set_guest_dsrr(vcpu, vcpu->arch.pc,
				       vcpu->arch.shared->msr);
			break;
		case INT_CLASS_MC:
			set_guest_mcsrr(vcpu, vcpu->arch.pc,
					vcpu->arch.shared->msr);
			break;
		}

379
		vcpu->arch.pc = vcpu->arch.ivpr | vcpu->arch.ivor[priority];
380
		if (update_esr == true)
381
			set_guest_esr(vcpu, vcpu->arch.queued_esr);
382
		if (update_dear == true)
383
			set_guest_dear(vcpu, vcpu->arch.queued_dear);
384
		kvmppc_set_msr(vcpu, vcpu->arch.shared->msr & msr_mask);
385

386 387
		if (!keep_irq)
			clear_bit(priority, &vcpu->arch.pending_exceptions);
388 389
	}

390 391 392 393 394 395 396 397 398 399 400 401 402 403
#ifdef CONFIG_KVM_BOOKE_HV
	/*
	 * If an interrupt is pending but masked, raise a guest doorbell
	 * so that we are notified when the guest enables the relevant
	 * MSR bit.
	 */
	if (vcpu->arch.pending_exceptions & BOOKE_IRQMASK_EE)
		kvmppc_set_pending_interrupt(vcpu, INT_CLASS_NONCRIT);
	if (vcpu->arch.pending_exceptions & BOOKE_IRQMASK_CE)
		kvmppc_set_pending_interrupt(vcpu, INT_CLASS_CRIT);
	if (vcpu->arch.pending_exceptions & BOOKE_IRQPRIO_MACHINE_CHECK)
		kvmppc_set_pending_interrupt(vcpu, INT_CLASS_MC);
#endif

404
	return allowed;
405 406
}

407 408 409 410 411 412 413 414
static void update_timer_ints(struct kvm_vcpu *vcpu)
{
	if ((vcpu->arch.tcr & TCR_DIE) && (vcpu->arch.tsr & TSR_DIS))
		kvmppc_core_queue_dec(vcpu);
	else
		kvmppc_core_dequeue_dec(vcpu);
}

415
static void kvmppc_core_check_exceptions(struct kvm_vcpu *vcpu)
416 417 418 419
{
	unsigned long *pending = &vcpu->arch.pending_exceptions;
	unsigned int priority;

420 421 422 423 424 425 426
	if (vcpu->requests) {
		if (kvm_check_request(KVM_REQ_PENDING_TIMER, vcpu)) {
			smp_mb();
			update_timer_ints(vcpu);
		}
	}

427
	priority = __ffs(*pending);
428
	while (priority < BOOKE_IRQPRIO_MAX) {
429
		if (kvmppc_booke_irqprio_deliver(vcpu, priority))
430 431 432 433 434 435
			break;

		priority = find_next_bit(pending,
		                         BITS_PER_BYTE * sizeof(*pending),
		                         priority + 1);
	}
436 437

	/* Tell the guest about our interrupt status */
438
	vcpu->arch.shared->int_pending = !!*pending;
439 440
}

441
/* Check pending exceptions and deliver one, if possible. */
442
int kvmppc_core_prepare_to_enter(struct kvm_vcpu *vcpu)
443
{
444
	int r = 0;
445 446 447 448 449 450 451 452 453 454
	WARN_ON_ONCE(!irqs_disabled());

	kvmppc_core_check_exceptions(vcpu);

	if (vcpu->arch.shared->msr & MSR_WE) {
		local_irq_enable();
		kvm_vcpu_block(vcpu);
		local_irq_disable();

		kvmppc_set_exit_type(vcpu, EMULATED_MTMSRWE_EXITS);
455
		r = 1;
456
	};
457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494

	return r;
}

/*
 * Common checks before entering the guest world.  Call with interrupts
 * disabled.
 *
 * returns !0 if a signal is pending and check_signal is true
 */
static int kvmppc_prepare_to_enter(struct kvm_vcpu *vcpu, bool check_signal)
{
	int r = 0;

	WARN_ON_ONCE(!irqs_disabled());
	while (true) {
		if (need_resched()) {
			local_irq_enable();
			cond_resched();
			local_irq_disable();
			continue;
		}

		if (check_signal && signal_pending(current)) {
			r = 1;
			break;
		}

		if (kvmppc_core_prepare_to_enter(vcpu)) {
			/* interrupts got enabled in between, so we
			   are back at square 1 */
			continue;
		}

		break;
	}

	return r;
495 496
}

497 498 499
int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
{
	int ret;
500 501 502 503 504
#ifdef CONFIG_PPC_FPU
	unsigned int fpscr;
	int fpexc_mode;
	u64 fpr[32];
#endif
505

506 507 508 509 510
	if (!vcpu->arch.sane) {
		kvm_run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
		return -EINVAL;
	}

511
	local_irq_disable();
512
	if (kvmppc_prepare_to_enter(vcpu, true)) {
513 514 515 516 517
		kvm_run->exit_reason = KVM_EXIT_INTR;
		ret = -EINTR;
		goto out;
	}

518
	kvm_guest_enter();
519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541

#ifdef CONFIG_PPC_FPU
	/* Save userspace FPU state in stack */
	enable_kernel_fp();
	memcpy(fpr, current->thread.fpr, sizeof(current->thread.fpr));
	fpscr = current->thread.fpscr.val;
	fpexc_mode = current->thread.fpexc_mode;

	/* Restore guest FPU state to thread */
	memcpy(current->thread.fpr, vcpu->arch.fpr, sizeof(vcpu->arch.fpr));
	current->thread.fpscr.val = vcpu->arch.fpscr;

	/*
	 * Since we can't trap on MSR_FP in GS-mode, we consider the guest
	 * as always using the FPU.  Kernel usage of FP (via
	 * enable_kernel_fp()) in this thread must not occur while
	 * vcpu->fpu_active is set.
	 */
	vcpu->fpu_active = 1;

	kvmppc_load_guest_fp(vcpu);
#endif

542
	ret = __kvmppc_vcpu_run(kvm_run, vcpu);
543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558

#ifdef CONFIG_PPC_FPU
	kvmppc_save_guest_fp(vcpu);

	vcpu->fpu_active = 0;

	/* Save guest FPU state from thread */
	memcpy(vcpu->arch.fpr, current->thread.fpr, sizeof(vcpu->arch.fpr));
	vcpu->arch.fpscr = current->thread.fpscr.val;

	/* Restore userspace FPU state from stack */
	memcpy(current->thread.fpr, fpr, sizeof(current->thread.fpr));
	current->thread.fpscr.val = fpscr;
	current->thread.fpexc_mode = fpexc_mode;
#endif

559 560
	kvm_guest_exit();

561 562
out:
	local_irq_enable();
563 564 565
	return ret;
}

566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589
static int emulation_exit(struct kvm_run *run, struct kvm_vcpu *vcpu)
{
	enum emulation_result er;

	er = kvmppc_emulate_instruction(run, vcpu);
	switch (er) {
	case EMULATE_DONE:
		/* don't overwrite subtypes, just account kvm_stats */
		kvmppc_account_exit_stat(vcpu, EMULATED_INST_EXITS);
		/* Future optimization: only reload non-volatiles if
		 * they were actually modified by emulation. */
		return RESUME_GUEST_NV;

	case EMULATE_DO_DCR:
		run->exit_reason = KVM_EXIT_DCR;
		return RESUME_HOST;

	case EMULATE_FAIL:
		printk(KERN_CRIT "%s: emulation at %lx failed (%08x)\n",
		       __func__, vcpu->arch.pc, vcpu->arch.last_inst);
		/* For debugging, encode the failing instruction and
		 * report it to userspace. */
		run->hw.hardware_exit_reason = ~0ULL << 32;
		run->hw.hardware_exit_reason |= vcpu->arch.last_inst;
590
		kvmppc_core_queue_program(vcpu, ESR_PIL);
591 592 593 594 595 596 597
		return RESUME_HOST;

	default:
		BUG();
	}
}

598 599 600 601 602 603 604 605 606 607
/**
 * kvmppc_handle_exit
 *
 * Return value is in the form (errcode<<2 | RESUME_FLAG_HOST | RESUME_FLAG_NV)
 */
int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
                       unsigned int exit_nr)
{
	int r = RESUME_HOST;

608 609 610
	/* update before a new last_exit_type is rewritten */
	kvmppc_update_timing_stats(vcpu);

611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629
	switch (exit_nr) {
	case BOOKE_INTERRUPT_EXTERNAL:
		do_IRQ(current->thread.regs);
		break;

	case BOOKE_INTERRUPT_DECREMENTER:
		timer_interrupt(current->thread.regs);
		break;

#if defined(CONFIG_PPC_FSL_BOOK3E) || defined(CONFIG_PPC_BOOK3E_64)
	case BOOKE_INTERRUPT_DOORBELL:
		doorbell_exception(current->thread.regs);
		break;
#endif
	case BOOKE_INTERRUPT_MACHINE_CHECK:
		/* FIXME */
		break;
	}

630 631 632 633 634 635 636
	local_irq_enable();

	run->exit_reason = KVM_EXIT_UNKNOWN;
	run->ready_for_interrupt_injection = 1;

	switch (exit_nr) {
	case BOOKE_INTERRUPT_MACHINE_CHECK:
637
		r = RESUME_GUEST;
638 639 640
		break;

	case BOOKE_INTERRUPT_EXTERNAL:
641
		kvmppc_account_exit(vcpu, EXT_INTR_EXITS);
642 643 644
		r = RESUME_GUEST;
		break;

645
	case BOOKE_INTERRUPT_DECREMENTER:
646
		kvmppc_account_exit(vcpu, DEC_EXITS);
647 648 649
		r = RESUME_GUEST;
		break;

650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680
	case BOOKE_INTERRUPT_DOORBELL:
		kvmppc_account_exit(vcpu, DBELL_EXITS);
		r = RESUME_GUEST;
		break;

	case BOOKE_INTERRUPT_GUEST_DBELL_CRIT:
		kvmppc_account_exit(vcpu, GDBELL_EXITS);

		/*
		 * We are here because there is a pending guest interrupt
		 * which could not be delivered as MSR_CE or MSR_ME was not
		 * set.  Once we break from here we will retry delivery.
		 */
		r = RESUME_GUEST;
		break;

	case BOOKE_INTERRUPT_GUEST_DBELL:
		kvmppc_account_exit(vcpu, GDBELL_EXITS);

		/*
		 * We are here because there is a pending guest interrupt
		 * which could not be delivered as MSR_EE was not set.  Once
		 * we break from here we will retry delivery.
		 */
		r = RESUME_GUEST;
		break;

	case BOOKE_INTERRUPT_HV_PRIV:
		r = emulation_exit(run, vcpu);
		break;

681
	case BOOKE_INTERRUPT_PROGRAM:
682
		if (vcpu->arch.shared->msr & (MSR_PR | MSR_GS)) {
683 684
			/* Program traps generated by user-level software must be handled
			 * by the guest kernel. */
685
			kvmppc_core_queue_program(vcpu, vcpu->arch.fault_esr);
686
			r = RESUME_GUEST;
687
			kvmppc_account_exit(vcpu, USR_PR_INST);
688 689 690
			break;
		}

691
		r = emulation_exit(run, vcpu);
692 693
		break;

694
	case BOOKE_INTERRUPT_FP_UNAVAIL:
695
		kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_FP_UNAVAIL);
696
		kvmppc_account_exit(vcpu, FP_UNAVAIL);
697 698 699
		r = RESUME_GUEST;
		break;

700 701 702 703 704 705 706
#ifdef CONFIG_SPE
	case BOOKE_INTERRUPT_SPE_UNAVAIL: {
		if (vcpu->arch.shared->msr & MSR_SPE)
			kvmppc_vcpu_enable_spe(vcpu);
		else
			kvmppc_booke_queue_irqprio(vcpu,
						   BOOKE_IRQPRIO_SPE_UNAVAIL);
707 708
		r = RESUME_GUEST;
		break;
709
	}
710 711 712 713 714 715 716 717 718 719

	case BOOKE_INTERRUPT_SPE_FP_DATA:
		kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_SPE_FP_DATA);
		r = RESUME_GUEST;
		break;

	case BOOKE_INTERRUPT_SPE_FP_ROUND:
		kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_SPE_FP_ROUND);
		r = RESUME_GUEST;
		break;
720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741
#else
	case BOOKE_INTERRUPT_SPE_UNAVAIL:
		/*
		 * Guest wants SPE, but host kernel doesn't support it.  Send
		 * an "unimplemented operation" program check to the guest.
		 */
		kvmppc_core_queue_program(vcpu, ESR_PUO | ESR_SPV);
		r = RESUME_GUEST;
		break;

	/*
	 * These really should never happen without CONFIG_SPE,
	 * as we should never enable the real MSR[SPE] in the guest.
	 */
	case BOOKE_INTERRUPT_SPE_FP_DATA:
	case BOOKE_INTERRUPT_SPE_FP_ROUND:
		printk(KERN_CRIT "%s: unexpected SPE interrupt %u at %08lx\n",
		       __func__, exit_nr, vcpu->arch.pc);
		run->hw.hardware_exit_reason = exit_nr;
		r = RESUME_HOST;
		break;
#endif
742

743
	case BOOKE_INTERRUPT_DATA_STORAGE:
744 745
		kvmppc_core_queue_data_storage(vcpu, vcpu->arch.fault_dear,
		                               vcpu->arch.fault_esr);
746
		kvmppc_account_exit(vcpu, DSI_EXITS);
747 748 749 750
		r = RESUME_GUEST;
		break;

	case BOOKE_INTERRUPT_INST_STORAGE:
751
		kvmppc_core_queue_inst_storage(vcpu, vcpu->arch.fault_esr);
752
		kvmppc_account_exit(vcpu, ISI_EXITS);
753 754 755
		r = RESUME_GUEST;
		break;

756 757 758 759 760 761 762 763 764 765 766 767 768 769 770
#ifdef CONFIG_KVM_BOOKE_HV
	case BOOKE_INTERRUPT_HV_SYSCALL:
		if (!(vcpu->arch.shared->msr & MSR_PR)) {
			kvmppc_set_gpr(vcpu, 3, kvmppc_kvm_pv(vcpu));
		} else {
			/*
			 * hcall from guest userspace -- send privileged
			 * instruction program check.
			 */
			kvmppc_core_queue_program(vcpu, ESR_PPR);
		}

		r = RESUME_GUEST;
		break;
#else
771
	case BOOKE_INTERRUPT_SYSCALL:
772 773 774 775 776 777 778 779 780
		if (!(vcpu->arch.shared->msr & MSR_PR) &&
		    (((u32)kvmppc_get_gpr(vcpu, 0)) == KVM_SC_MAGIC_R0)) {
			/* KVM PV hypercalls */
			kvmppc_set_gpr(vcpu, 3, kvmppc_kvm_pv(vcpu));
			r = RESUME_GUEST;
		} else {
			/* Guest syscalls */
			kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_SYSCALL);
		}
781
		kvmppc_account_exit(vcpu, SYSCALL_EXITS);
782 783
		r = RESUME_GUEST;
		break;
784
#endif
785 786 787

	case BOOKE_INTERRUPT_DTLB_MISS: {
		unsigned long eaddr = vcpu->arch.fault_dear;
788
		int gtlb_index;
789
		gpa_t gpaddr;
790 791
		gfn_t gfn;

792
#ifdef CONFIG_KVM_E500V2
S
Scott Wood 已提交
793 794 795 796 797 798 799 800 801 802
		if (!(vcpu->arch.shared->msr & MSR_PR) &&
		    (eaddr & PAGE_MASK) == vcpu->arch.magic_page_ea) {
			kvmppc_map_magic(vcpu);
			kvmppc_account_exit(vcpu, DTLB_VIRT_MISS_EXITS);
			r = RESUME_GUEST;

			break;
		}
#endif

803
		/* Check the guest TLB. */
804
		gtlb_index = kvmppc_mmu_dtlb_index(vcpu, eaddr);
805
		if (gtlb_index < 0) {
806
			/* The guest didn't have a mapping for it. */
807 808 809
			kvmppc_core_queue_dtlb_miss(vcpu,
			                            vcpu->arch.fault_dear,
			                            vcpu->arch.fault_esr);
810
			kvmppc_mmu_dtlb_miss(vcpu);
811
			kvmppc_account_exit(vcpu, DTLB_REAL_MISS_EXITS);
812 813 814 815
			r = RESUME_GUEST;
			break;
		}

816
		gpaddr = kvmppc_mmu_xlate(vcpu, gtlb_index, eaddr);
817
		gfn = gpaddr >> PAGE_SHIFT;
818 819 820 821 822 823 824 825

		if (kvm_is_visible_gfn(vcpu->kvm, gfn)) {
			/* The guest TLB had a mapping, but the shadow TLB
			 * didn't, and it is RAM. This could be because:
			 * a) the entry is mapping the host kernel, or
			 * b) the guest used a large mapping which we're faking
			 * Either way, we need to satisfy the fault without
			 * invoking the guest. */
826
			kvmppc_mmu_map(vcpu, eaddr, gpaddr, gtlb_index);
827
			kvmppc_account_exit(vcpu, DTLB_VIRT_MISS_EXITS);
828 829 830 831
			r = RESUME_GUEST;
		} else {
			/* Guest has mapped and accessed a page which is not
			 * actually RAM. */
832
			vcpu->arch.paddr_accessed = gpaddr;
833
			r = kvmppc_emulate_mmio(run, vcpu);
834
			kvmppc_account_exit(vcpu, MMIO_EXITS);
835 836 837 838 839 840 841
		}

		break;
	}

	case BOOKE_INTERRUPT_ITLB_MISS: {
		unsigned long eaddr = vcpu->arch.pc;
842
		gpa_t gpaddr;
843
		gfn_t gfn;
844
		int gtlb_index;
845 846 847 848

		r = RESUME_GUEST;

		/* Check the guest TLB. */
849
		gtlb_index = kvmppc_mmu_itlb_index(vcpu, eaddr);
850
		if (gtlb_index < 0) {
851
			/* The guest didn't have a mapping for it. */
852
			kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_ITLB_MISS);
853
			kvmppc_mmu_itlb_miss(vcpu);
854
			kvmppc_account_exit(vcpu, ITLB_REAL_MISS_EXITS);
855 856 857
			break;
		}

858
		kvmppc_account_exit(vcpu, ITLB_VIRT_MISS_EXITS);
859

860
		gpaddr = kvmppc_mmu_xlate(vcpu, gtlb_index, eaddr);
861
		gfn = gpaddr >> PAGE_SHIFT;
862 863 864 865 866 867 868 869

		if (kvm_is_visible_gfn(vcpu->kvm, gfn)) {
			/* The guest TLB had a mapping, but the shadow TLB
			 * didn't. This could be because:
			 * a) the entry is mapping the host kernel, or
			 * b) the guest used a large mapping which we're faking
			 * Either way, we need to satisfy the fault without
			 * invoking the guest. */
870
			kvmppc_mmu_map(vcpu, eaddr, gpaddr, gtlb_index);
871 872
		} else {
			/* Guest mapped and leaped at non-RAM! */
873
			kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_MACHINE_CHECK);
874 875 876 877 878
		}

		break;
	}

879 880 881 882 883 884 885 886 887 888 889
	case BOOKE_INTERRUPT_DEBUG: {
		u32 dbsr;

		vcpu->arch.pc = mfspr(SPRN_CSRR0);

		/* clear IAC events in DBSR register */
		dbsr = mfspr(SPRN_DBSR);
		dbsr &= DBSR_IAC1 | DBSR_IAC2 | DBSR_IAC3 | DBSR_IAC4;
		mtspr(SPRN_DBSR, dbsr);

		run->exit_reason = KVM_EXIT_DEBUG;
890
		kvmppc_account_exit(vcpu, DEBUG_EXITS);
891 892 893 894
		r = RESUME_HOST;
		break;
	}

895 896 897 898 899
	default:
		printk(KERN_EMERG "exit_nr %d\n", exit_nr);
		BUG();
	}

900 901 902 903
	/*
	 * To avoid clobbering exit_reason, only check for signals if we
	 * aren't already exiting to userspace for some other reason.
	 */
904
	local_irq_disable();
905 906 907 908
	if (kvmppc_prepare_to_enter(vcpu, !(r & RESUME_HOST))) {
		run->exit_reason = KVM_EXIT_INTR;
		r = (-EINTR << 2) | RESUME_HOST | (r & RESUME_FLAG_NV);
		kvmppc_account_exit(vcpu, SIGNAL_EXITS);
909 910 911 912 913 914 915 916
	}

	return r;
}

/* Initial guest state: 16MB mapping 0 -> 0, PC = 0, MSR = 0, R1 = 16MB */
int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
{
917
	int i;
918
	int r;
919

920
	vcpu->arch.pc = 0;
921
	vcpu->arch.shared->pir = vcpu->vcpu_id;
922
	kvmppc_set_gpr(vcpu, 1, (16<<20) - 8); /* -8 for the callee-save LR slot */
923
	kvmppc_set_msr(vcpu, 0);
924

925 926
#ifndef CONFIG_KVM_BOOKE_HV
	vcpu->arch.shadow_msr = MSR_USER | MSR_DE | MSR_IS | MSR_DS;
927
	vcpu->arch.shadow_pid = 1;
928 929
	vcpu->arch.shared->msr = 0;
#endif
930

931 932
	/* Eye-catching numbers so we know if the guest takes an interrupt
	 * before it's programmed its own IVPR/IVORs. */
933
	vcpu->arch.ivpr = 0x55550000;
934 935
	for (i = 0; i < BOOKE_IRQPRIO_MAX; i++)
		vcpu->arch.ivor[i] = 0x7700 | i * 4;
936

937 938
	kvmppc_init_timing_stats(vcpu);

939 940 941
	r = kvmppc_core_vcpu_setup(vcpu);
	kvmppc_sanity_check(vcpu);
	return r;
942 943 944 945 946 947 948
}

int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
{
	int i;

	regs->pc = vcpu->arch.pc;
949
	regs->cr = kvmppc_get_cr(vcpu);
950 951
	regs->ctr = vcpu->arch.ctr;
	regs->lr = vcpu->arch.lr;
952
	regs->xer = kvmppc_get_xer(vcpu);
953
	regs->msr = vcpu->arch.shared->msr;
954 955
	regs->srr0 = vcpu->arch.shared->srr0;
	regs->srr1 = vcpu->arch.shared->srr1;
956
	regs->pid = vcpu->arch.pid;
957 958 959 960
	regs->sprg0 = vcpu->arch.shared->sprg0;
	regs->sprg1 = vcpu->arch.shared->sprg1;
	regs->sprg2 = vcpu->arch.shared->sprg2;
	regs->sprg3 = vcpu->arch.shared->sprg3;
961 962 963 964
	regs->sprg4 = vcpu->arch.shared->sprg4;
	regs->sprg5 = vcpu->arch.shared->sprg5;
	regs->sprg6 = vcpu->arch.shared->sprg6;
	regs->sprg7 = vcpu->arch.shared->sprg7;
965 966

	for (i = 0; i < ARRAY_SIZE(regs->gpr); i++)
967
		regs->gpr[i] = kvmppc_get_gpr(vcpu, i);
968 969 970 971 972 973 974 975 976

	return 0;
}

int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
{
	int i;

	vcpu->arch.pc = regs->pc;
977
	kvmppc_set_cr(vcpu, regs->cr);
978 979
	vcpu->arch.ctr = regs->ctr;
	vcpu->arch.lr = regs->lr;
980
	kvmppc_set_xer(vcpu, regs->xer);
981
	kvmppc_set_msr(vcpu, regs->msr);
982 983
	vcpu->arch.shared->srr0 = regs->srr0;
	vcpu->arch.shared->srr1 = regs->srr1;
S
Scott Wood 已提交
984
	kvmppc_set_pid(vcpu, regs->pid);
985 986 987 988
	vcpu->arch.shared->sprg0 = regs->sprg0;
	vcpu->arch.shared->sprg1 = regs->sprg1;
	vcpu->arch.shared->sprg2 = regs->sprg2;
	vcpu->arch.shared->sprg3 = regs->sprg3;
989 990 991 992
	vcpu->arch.shared->sprg4 = regs->sprg4;
	vcpu->arch.shared->sprg5 = regs->sprg5;
	vcpu->arch.shared->sprg6 = regs->sprg6;
	vcpu->arch.shared->sprg7 = regs->sprg7;
993

994 995
	for (i = 0; i < ARRAY_SIZE(regs->gpr); i++)
		kvmppc_set_gpr(vcpu, i, regs->gpr[i]);
996 997 998 999

	return 0;
}

S
Scott Wood 已提交
1000 1001 1002 1003 1004 1005 1006 1007 1008 1009
static void get_sregs_base(struct kvm_vcpu *vcpu,
                           struct kvm_sregs *sregs)
{
	u64 tb = get_tb();

	sregs->u.e.features |= KVM_SREGS_E_BASE;

	sregs->u.e.csrr0 = vcpu->arch.csrr0;
	sregs->u.e.csrr1 = vcpu->arch.csrr1;
	sregs->u.e.mcsr = vcpu->arch.mcsr;
1010 1011
	sregs->u.e.esr = get_guest_esr(vcpu);
	sregs->u.e.dear = get_guest_dear(vcpu);
S
Scott Wood 已提交
1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027
	sregs->u.e.tsr = vcpu->arch.tsr;
	sregs->u.e.tcr = vcpu->arch.tcr;
	sregs->u.e.dec = kvmppc_get_dec(vcpu, tb);
	sregs->u.e.tb = tb;
	sregs->u.e.vrsave = vcpu->arch.vrsave;
}

static int set_sregs_base(struct kvm_vcpu *vcpu,
                          struct kvm_sregs *sregs)
{
	if (!(sregs->u.e.features & KVM_SREGS_E_BASE))
		return 0;

	vcpu->arch.csrr0 = sregs->u.e.csrr0;
	vcpu->arch.csrr1 = sregs->u.e.csrr1;
	vcpu->arch.mcsr = sregs->u.e.mcsr;
1028 1029
	set_guest_esr(vcpu, sregs->u.e.esr);
	set_guest_dear(vcpu, sregs->u.e.dear);
S
Scott Wood 已提交
1030
	vcpu->arch.vrsave = sregs->u.e.vrsave;
1031
	kvmppc_set_tcr(vcpu, sregs->u.e.tcr);
S
Scott Wood 已提交
1032

1033
	if (sregs->u.e.update_special & KVM_SREGS_E_UPDATE_DEC) {
S
Scott Wood 已提交
1034
		vcpu->arch.dec = sregs->u.e.dec;
1035 1036
		kvmppc_emulate_dec(vcpu);
	}
S
Scott Wood 已提交
1037 1038

	if (sregs->u.e.update_special & KVM_SREGS_E_UPDATE_TSR) {
1039 1040
		vcpu->arch.tsr = sregs->u.e.tsr;
		update_timer_ints(vcpu);
S
Scott Wood 已提交
1041 1042 1043 1044 1045 1046 1047 1048 1049 1050
	}

	return 0;
}

static void get_sregs_arch206(struct kvm_vcpu *vcpu,
                              struct kvm_sregs *sregs)
{
	sregs->u.e.features |= KVM_SREGS_E_ARCH206;

1051
	sregs->u.e.pir = vcpu->vcpu_id;
S
Scott Wood 已提交
1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063
	sregs->u.e.mcsrr0 = vcpu->arch.mcsrr0;
	sregs->u.e.mcsrr1 = vcpu->arch.mcsrr1;
	sregs->u.e.decar = vcpu->arch.decar;
	sregs->u.e.ivpr = vcpu->arch.ivpr;
}

static int set_sregs_arch206(struct kvm_vcpu *vcpu,
                             struct kvm_sregs *sregs)
{
	if (!(sregs->u.e.features & KVM_SREGS_E_ARCH206))
		return 0;

1064
	if (sregs->u.e.pir != vcpu->vcpu_id)
S
Scott Wood 已提交
1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121
		return -EINVAL;

	vcpu->arch.mcsrr0 = sregs->u.e.mcsrr0;
	vcpu->arch.mcsrr1 = sregs->u.e.mcsrr1;
	vcpu->arch.decar = sregs->u.e.decar;
	vcpu->arch.ivpr = sregs->u.e.ivpr;

	return 0;
}

void kvmppc_get_sregs_ivor(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
{
	sregs->u.e.features |= KVM_SREGS_E_IVOR;

	sregs->u.e.ivor_low[0] = vcpu->arch.ivor[BOOKE_IRQPRIO_CRITICAL];
	sregs->u.e.ivor_low[1] = vcpu->arch.ivor[BOOKE_IRQPRIO_MACHINE_CHECK];
	sregs->u.e.ivor_low[2] = vcpu->arch.ivor[BOOKE_IRQPRIO_DATA_STORAGE];
	sregs->u.e.ivor_low[3] = vcpu->arch.ivor[BOOKE_IRQPRIO_INST_STORAGE];
	sregs->u.e.ivor_low[4] = vcpu->arch.ivor[BOOKE_IRQPRIO_EXTERNAL];
	sregs->u.e.ivor_low[5] = vcpu->arch.ivor[BOOKE_IRQPRIO_ALIGNMENT];
	sregs->u.e.ivor_low[6] = vcpu->arch.ivor[BOOKE_IRQPRIO_PROGRAM];
	sregs->u.e.ivor_low[7] = vcpu->arch.ivor[BOOKE_IRQPRIO_FP_UNAVAIL];
	sregs->u.e.ivor_low[8] = vcpu->arch.ivor[BOOKE_IRQPRIO_SYSCALL];
	sregs->u.e.ivor_low[9] = vcpu->arch.ivor[BOOKE_IRQPRIO_AP_UNAVAIL];
	sregs->u.e.ivor_low[10] = vcpu->arch.ivor[BOOKE_IRQPRIO_DECREMENTER];
	sregs->u.e.ivor_low[11] = vcpu->arch.ivor[BOOKE_IRQPRIO_FIT];
	sregs->u.e.ivor_low[12] = vcpu->arch.ivor[BOOKE_IRQPRIO_WATCHDOG];
	sregs->u.e.ivor_low[13] = vcpu->arch.ivor[BOOKE_IRQPRIO_DTLB_MISS];
	sregs->u.e.ivor_low[14] = vcpu->arch.ivor[BOOKE_IRQPRIO_ITLB_MISS];
	sregs->u.e.ivor_low[15] = vcpu->arch.ivor[BOOKE_IRQPRIO_DEBUG];
}

int kvmppc_set_sregs_ivor(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
{
	if (!(sregs->u.e.features & KVM_SREGS_E_IVOR))
		return 0;

	vcpu->arch.ivor[BOOKE_IRQPRIO_CRITICAL] = sregs->u.e.ivor_low[0];
	vcpu->arch.ivor[BOOKE_IRQPRIO_MACHINE_CHECK] = sregs->u.e.ivor_low[1];
	vcpu->arch.ivor[BOOKE_IRQPRIO_DATA_STORAGE] = sregs->u.e.ivor_low[2];
	vcpu->arch.ivor[BOOKE_IRQPRIO_INST_STORAGE] = sregs->u.e.ivor_low[3];
	vcpu->arch.ivor[BOOKE_IRQPRIO_EXTERNAL] = sregs->u.e.ivor_low[4];
	vcpu->arch.ivor[BOOKE_IRQPRIO_ALIGNMENT] = sregs->u.e.ivor_low[5];
	vcpu->arch.ivor[BOOKE_IRQPRIO_PROGRAM] = sregs->u.e.ivor_low[6];
	vcpu->arch.ivor[BOOKE_IRQPRIO_FP_UNAVAIL] = sregs->u.e.ivor_low[7];
	vcpu->arch.ivor[BOOKE_IRQPRIO_SYSCALL] = sregs->u.e.ivor_low[8];
	vcpu->arch.ivor[BOOKE_IRQPRIO_AP_UNAVAIL] = sregs->u.e.ivor_low[9];
	vcpu->arch.ivor[BOOKE_IRQPRIO_DECREMENTER] = sregs->u.e.ivor_low[10];
	vcpu->arch.ivor[BOOKE_IRQPRIO_FIT] = sregs->u.e.ivor_low[11];
	vcpu->arch.ivor[BOOKE_IRQPRIO_WATCHDOG] = sregs->u.e.ivor_low[12];
	vcpu->arch.ivor[BOOKE_IRQPRIO_DTLB_MISS] = sregs->u.e.ivor_low[13];
	vcpu->arch.ivor[BOOKE_IRQPRIO_ITLB_MISS] = sregs->u.e.ivor_low[14];
	vcpu->arch.ivor[BOOKE_IRQPRIO_DEBUG] = sregs->u.e.ivor_low[15];

	return 0;
}

1122 1123 1124
int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
                                  struct kvm_sregs *sregs)
{
S
Scott Wood 已提交
1125 1126 1127 1128 1129 1130
	sregs->pvr = vcpu->arch.pvr;

	get_sregs_base(vcpu, sregs);
	get_sregs_arch206(vcpu, sregs);
	kvmppc_core_get_sregs(vcpu, sregs);
	return 0;
1131 1132 1133 1134 1135
}

int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
                                  struct kvm_sregs *sregs)
{
S
Scott Wood 已提交
1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149
	int ret;

	if (vcpu->arch.pvr != sregs->pvr)
		return -EINVAL;

	ret = set_sregs_base(vcpu, sregs);
	if (ret < 0)
		return ret;

	ret = set_sregs_arch206(vcpu, sregs);
	if (ret < 0)
		return ret;

	return kvmppc_core_set_sregs(vcpu, sregs);
1150 1151
}

1152 1153 1154 1155 1156 1157 1158 1159 1160 1161
int kvm_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
{
	return -EINVAL;
}

int kvm_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
{
	return -EINVAL;
}

1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174
int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
{
	return -ENOTSUPP;
}

int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
{
	return -ENOTSUPP;
}

int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu,
                                  struct kvm_translation *tr)
{
1175 1176 1177 1178
	int r;

	r = kvmppc_core_vcpu_translate(vcpu, tr);
	return r;
1179
}
1180

1181 1182 1183 1184 1185
int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log)
{
	return -ENOTSUPP;
}

1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196
int kvmppc_core_prepare_memory_region(struct kvm *kvm,
				      struct kvm_userspace_memory_region *mem)
{
	return 0;
}

void kvmppc_core_commit_memory_region(struct kvm *kvm,
				struct kvm_userspace_memory_region *mem)
{
}

1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223
void kvmppc_set_tcr(struct kvm_vcpu *vcpu, u32 new_tcr)
{
	vcpu->arch.tcr = new_tcr;
	update_timer_ints(vcpu);
}

void kvmppc_set_tsr_bits(struct kvm_vcpu *vcpu, u32 tsr_bits)
{
	set_bits(tsr_bits, &vcpu->arch.tsr);
	smp_wmb();
	kvm_make_request(KVM_REQ_PENDING_TIMER, vcpu);
	kvm_vcpu_kick(vcpu);
}

void kvmppc_clr_tsr_bits(struct kvm_vcpu *vcpu, u32 tsr_bits)
{
	clear_bits(tsr_bits, &vcpu->arch.tsr);
	update_timer_ints(vcpu);
}

void kvmppc_decrementer_func(unsigned long data)
{
	struct kvm_vcpu *vcpu = (struct kvm_vcpu *)data;

	kvmppc_set_tsr_bits(vcpu, TSR_DIS);
}

1224 1225
void kvmppc_booke_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
{
1226
	current->thread.kvm_vcpu = vcpu;
1227 1228 1229 1230
}

void kvmppc_booke_vcpu_put(struct kvm_vcpu *vcpu)
{
1231
	current->thread.kvm_vcpu = NULL;
1232 1233
}

1234
int __init kvmppc_booke_init(void)
1235
{
1236
#ifndef CONFIG_KVM_BOOKE_HV
1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278
	unsigned long ivor[16];
	unsigned long max_ivor = 0;
	int i;

	/* We install our own exception handlers by hijacking IVPR. IVPR must
	 * be 16-bit aligned, so we need a 64KB allocation. */
	kvmppc_booke_handlers = __get_free_pages(GFP_KERNEL | __GFP_ZERO,
	                                         VCPU_SIZE_ORDER);
	if (!kvmppc_booke_handlers)
		return -ENOMEM;

	/* XXX make sure our handlers are smaller than Linux's */

	/* Copy our interrupt handlers to match host IVORs. That way we don't
	 * have to swap the IVORs on every guest/host transition. */
	ivor[0] = mfspr(SPRN_IVOR0);
	ivor[1] = mfspr(SPRN_IVOR1);
	ivor[2] = mfspr(SPRN_IVOR2);
	ivor[3] = mfspr(SPRN_IVOR3);
	ivor[4] = mfspr(SPRN_IVOR4);
	ivor[5] = mfspr(SPRN_IVOR5);
	ivor[6] = mfspr(SPRN_IVOR6);
	ivor[7] = mfspr(SPRN_IVOR7);
	ivor[8] = mfspr(SPRN_IVOR8);
	ivor[9] = mfspr(SPRN_IVOR9);
	ivor[10] = mfspr(SPRN_IVOR10);
	ivor[11] = mfspr(SPRN_IVOR11);
	ivor[12] = mfspr(SPRN_IVOR12);
	ivor[13] = mfspr(SPRN_IVOR13);
	ivor[14] = mfspr(SPRN_IVOR14);
	ivor[15] = mfspr(SPRN_IVOR15);

	for (i = 0; i < 16; i++) {
		if (ivor[i] > max_ivor)
			max_ivor = ivor[i];

		memcpy((void *)kvmppc_booke_handlers + ivor[i],
		       kvmppc_handlers_start + i * kvmppc_handler_len,
		       kvmppc_handler_len);
	}
	flush_icache_range(kvmppc_booke_handlers,
	                   kvmppc_booke_handlers + max_ivor + kvmppc_handler_len);
1279
#endif /* !BOOKE_HV */
1280
	return 0;
1281 1282
}

1283
void __exit kvmppc_booke_exit(void)
1284 1285 1286 1287
{
	free_pages(kvmppc_booke_handlers, VCPU_SIZE_ORDER);
	kvm_exit();
}