book3s.c 30.2 KB
Newer Older
A
Alexander Graf 已提交
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35
/*
 * Copyright (C) 2009. SUSE Linux Products GmbH. All rights reserved.
 *
 * Authors:
 *    Alexander Graf <agraf@suse.de>
 *    Kevin Wolf <mail@kevin-wolf.de>
 *
 * Description:
 * This file is derived from arch/powerpc/kvm/44x.c,
 * by Hollis Blanchard <hollisb@us.ibm.com>.
 *
 * 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.
 */

#include <linux/kvm_host.h>
#include <linux/err.h>

#include <asm/reg.h>
#include <asm/cputable.h>
#include <asm/cacheflush.h>
#include <asm/tlbflush.h>
#include <asm/uaccess.h>
#include <asm/io.h>
#include <asm/kvm_ppc.h>
#include <asm/kvm_book3s.h>
#include <asm/mmu_context.h>
#include <linux/sched.h>
#include <linux/vmalloc.h>

#define VCPU_STAT(x) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU

/* #define EXIT_DEBUG */
/* #define EXIT_DEBUG_SIMPLE */
36 37 38
/* #define DEBUG_EXT */

static void kvmppc_giveup_ext(struct kvm_vcpu *vcpu, ulong msr);
A
Alexander Graf 已提交
39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71

struct kvm_stats_debugfs_item debugfs_entries[] = {
	{ "exits",       VCPU_STAT(sum_exits) },
	{ "mmio",        VCPU_STAT(mmio_exits) },
	{ "sig",         VCPU_STAT(signal_exits) },
	{ "sysc",        VCPU_STAT(syscall_exits) },
	{ "inst_emu",    VCPU_STAT(emulated_inst_exits) },
	{ "dec",         VCPU_STAT(dec_exits) },
	{ "ext_intr",    VCPU_STAT(ext_intr_exits) },
	{ "queue_intr",  VCPU_STAT(queue_intr) },
	{ "halt_wakeup", VCPU_STAT(halt_wakeup) },
	{ "pf_storage",  VCPU_STAT(pf_storage) },
	{ "sp_storage",  VCPU_STAT(sp_storage) },
	{ "pf_instruc",  VCPU_STAT(pf_instruc) },
	{ "sp_instruc",  VCPU_STAT(sp_instruc) },
	{ "ld",          VCPU_STAT(ld) },
	{ "ld_slow",     VCPU_STAT(ld_slow) },
	{ "st",          VCPU_STAT(st) },
	{ "st_slow",     VCPU_STAT(st_slow) },
	{ NULL }
};

void kvmppc_core_load_host_debugstate(struct kvm_vcpu *vcpu)
{
}

void kvmppc_core_load_guest_debugstate(struct kvm_vcpu *vcpu)
{
}

void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
{
	memcpy(get_paca()->kvm_slb, to_book3s(vcpu)->slb_shadow, sizeof(get_paca()->kvm_slb));
72 73
	memcpy(&get_paca()->shadow_vcpu, &to_book3s(vcpu)->shadow_vcpu,
	       sizeof(get_paca()->shadow_vcpu));
A
Alexander Graf 已提交
74 75 76 77 78 79
	get_paca()->kvm_slb_max = to_book3s(vcpu)->slb_shadow_max;
}

void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu)
{
	memcpy(to_book3s(vcpu)->slb_shadow, get_paca()->kvm_slb, sizeof(get_paca()->kvm_slb));
80 81
	memcpy(&to_book3s(vcpu)->shadow_vcpu, &get_paca()->shadow_vcpu,
	       sizeof(get_paca()->shadow_vcpu));
A
Alexander Graf 已提交
82
	to_book3s(vcpu)->slb_shadow_max = get_paca()->kvm_slb_max;
83 84 85 86

	kvmppc_giveup_ext(vcpu, MSR_FP);
	kvmppc_giveup_ext(vcpu, MSR_VEC);
	kvmppc_giveup_ext(vcpu, MSR_VSX);
A
Alexander Graf 已提交
87 88
}

89
#if defined(EXIT_DEBUG)
A
Alexander Graf 已提交
90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106
static u32 kvmppc_get_dec(struct kvm_vcpu *vcpu)
{
	u64 jd = mftb() - vcpu->arch.dec_jiffies;
	return vcpu->arch.dec - jd;
}
#endif

void kvmppc_set_msr(struct kvm_vcpu *vcpu, u64 msr)
{
	ulong old_msr = vcpu->arch.msr;

#ifdef EXIT_DEBUG
	printk(KERN_INFO "KVM: Set MSR to 0x%llx\n", msr);
#endif
	msr &= to_book3s(vcpu)->msr_mask;
	vcpu->arch.msr = msr;
	vcpu->arch.shadow_msr = msr | MSR_USER32;
107 108 109
	vcpu->arch.shadow_msr &= (MSR_FE0 | MSR_USER64 | MSR_SE | MSR_BE |
				  MSR_DE | MSR_FE1);
	vcpu->arch.shadow_msr |= (msr & vcpu->arch.guest_owned_ext);
A
Alexander Graf 已提交
110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132

	if (msr & (MSR_WE|MSR_POW)) {
		if (!vcpu->arch.pending_exceptions) {
			kvm_vcpu_block(vcpu);
			vcpu->stat.halt_wakeup++;
		}
	}

	if (((vcpu->arch.msr & (MSR_IR|MSR_DR)) != (old_msr & (MSR_IR|MSR_DR))) ||
	    (vcpu->arch.msr & MSR_PR) != (old_msr & MSR_PR)) {
		kvmppc_mmu_flush_segments(vcpu);
		kvmppc_mmu_map_segment(vcpu, vcpu->arch.pc);
	}
}

void kvmppc_inject_interrupt(struct kvm_vcpu *vcpu, int vec, u64 flags)
{
	vcpu->arch.srr0 = vcpu->arch.pc;
	vcpu->arch.srr1 = vcpu->arch.msr | flags;
	vcpu->arch.pc = to_book3s(vcpu)->hior + vec;
	vcpu->arch.mmu.reset_msr(vcpu);
}

133
static int kvmppc_book3s_vec2irqprio(unsigned int vec)
A
Alexander Graf 已提交
134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155
{
	unsigned int prio;

	switch (vec) {
	case 0x100: prio = BOOK3S_IRQPRIO_SYSTEM_RESET;		break;
	case 0x200: prio = BOOK3S_IRQPRIO_MACHINE_CHECK;	break;
	case 0x300: prio = BOOK3S_IRQPRIO_DATA_STORAGE;		break;
	case 0x380: prio = BOOK3S_IRQPRIO_DATA_SEGMENT;		break;
	case 0x400: prio = BOOK3S_IRQPRIO_INST_STORAGE;		break;
	case 0x480: prio = BOOK3S_IRQPRIO_INST_SEGMENT;		break;
	case 0x500: prio = BOOK3S_IRQPRIO_EXTERNAL;		break;
	case 0x600: prio = BOOK3S_IRQPRIO_ALIGNMENT;		break;
	case 0x700: prio = BOOK3S_IRQPRIO_PROGRAM;		break;
	case 0x800: prio = BOOK3S_IRQPRIO_FP_UNAVAIL;		break;
	case 0x900: prio = BOOK3S_IRQPRIO_DECREMENTER;		break;
	case 0xc00: prio = BOOK3S_IRQPRIO_SYSCALL;		break;
	case 0xd00: prio = BOOK3S_IRQPRIO_DEBUG;		break;
	case 0xf20: prio = BOOK3S_IRQPRIO_ALTIVEC;		break;
	case 0xf40: prio = BOOK3S_IRQPRIO_VSX;			break;
	default:    prio = BOOK3S_IRQPRIO_MAX;			break;
	}

156 157 158
	return prio;
}

159 160 161 162 163 164 165
static void kvmppc_book3s_dequeue_irqprio(struct kvm_vcpu *vcpu,
					  unsigned int vec)
{
	clear_bit(kvmppc_book3s_vec2irqprio(vec),
		  &vcpu->arch.pending_exceptions);
}

166 167 168 169 170 171
void kvmppc_book3s_queue_irqprio(struct kvm_vcpu *vcpu, unsigned int vec)
{
	vcpu->stat.queue_intr++;

	set_bit(kvmppc_book3s_vec2irqprio(vec),
		&vcpu->arch.pending_exceptions);
A
Alexander Graf 已提交
172 173 174 175 176 177
#ifdef EXIT_DEBUG
	printk(KERN_INFO "Queueing interrupt %x\n", vec);
#endif
}


178
void kvmppc_core_queue_program(struct kvm_vcpu *vcpu, ulong flags)
A
Alexander Graf 已提交
179
{
180
	to_book3s(vcpu)->prog_flags = flags;
A
Alexander Graf 已提交
181 182 183 184 185 186 187 188 189 190 191 192 193
	kvmppc_book3s_queue_irqprio(vcpu, BOOK3S_INTERRUPT_PROGRAM);
}

void kvmppc_core_queue_dec(struct kvm_vcpu *vcpu)
{
	kvmppc_book3s_queue_irqprio(vcpu, BOOK3S_INTERRUPT_DECREMENTER);
}

int kvmppc_core_pending_dec(struct kvm_vcpu *vcpu)
{
	return test_bit(BOOK3S_INTERRUPT_DECREMENTER >> 7, &vcpu->arch.pending_exceptions);
}

194 195 196 197 198
void kvmppc_core_dequeue_dec(struct kvm_vcpu *vcpu)
{
	kvmppc_book3s_dequeue_irqprio(vcpu, BOOK3S_INTERRUPT_DECREMENTER);
}

A
Alexander Graf 已提交
199 200 201 202 203 204 205 206 207 208
void kvmppc_core_queue_external(struct kvm_vcpu *vcpu,
                                struct kvm_interrupt *irq)
{
	kvmppc_book3s_queue_irqprio(vcpu, BOOK3S_INTERRUPT_EXTERNAL);
}

int kvmppc_book3s_irqprio_deliver(struct kvm_vcpu *vcpu, unsigned int priority)
{
	int deliver = 1;
	int vec = 0;
209
	ulong flags = 0ULL;
A
Alexander Graf 已提交
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

	switch (priority) {
	case BOOK3S_IRQPRIO_DECREMENTER:
		deliver = vcpu->arch.msr & MSR_EE;
		vec = BOOK3S_INTERRUPT_DECREMENTER;
		break;
	case BOOK3S_IRQPRIO_EXTERNAL:
		deliver = vcpu->arch.msr & MSR_EE;
		vec = BOOK3S_INTERRUPT_EXTERNAL;
		break;
	case BOOK3S_IRQPRIO_SYSTEM_RESET:
		vec = BOOK3S_INTERRUPT_SYSTEM_RESET;
		break;
	case BOOK3S_IRQPRIO_MACHINE_CHECK:
		vec = BOOK3S_INTERRUPT_MACHINE_CHECK;
		break;
	case BOOK3S_IRQPRIO_DATA_STORAGE:
		vec = BOOK3S_INTERRUPT_DATA_STORAGE;
		break;
	case BOOK3S_IRQPRIO_INST_STORAGE:
		vec = BOOK3S_INTERRUPT_INST_STORAGE;
		break;
	case BOOK3S_IRQPRIO_DATA_SEGMENT:
		vec = BOOK3S_INTERRUPT_DATA_SEGMENT;
		break;
	case BOOK3S_IRQPRIO_INST_SEGMENT:
		vec = BOOK3S_INTERRUPT_INST_SEGMENT;
		break;
	case BOOK3S_IRQPRIO_ALIGNMENT:
		vec = BOOK3S_INTERRUPT_ALIGNMENT;
		break;
	case BOOK3S_IRQPRIO_PROGRAM:
		vec = BOOK3S_INTERRUPT_PROGRAM;
243
		flags = to_book3s(vcpu)->prog_flags;
A
Alexander Graf 已提交
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
		break;
	case BOOK3S_IRQPRIO_VSX:
		vec = BOOK3S_INTERRUPT_VSX;
		break;
	case BOOK3S_IRQPRIO_ALTIVEC:
		vec = BOOK3S_INTERRUPT_ALTIVEC;
		break;
	case BOOK3S_IRQPRIO_FP_UNAVAIL:
		vec = BOOK3S_INTERRUPT_FP_UNAVAIL;
		break;
	case BOOK3S_IRQPRIO_SYSCALL:
		vec = BOOK3S_INTERRUPT_SYSCALL;
		break;
	case BOOK3S_IRQPRIO_DEBUG:
		vec = BOOK3S_INTERRUPT_TRACE;
		break;
	case BOOK3S_IRQPRIO_PERFORMANCE_MONITOR:
		vec = BOOK3S_INTERRUPT_PERFMON;
		break;
	default:
		deliver = 0;
		printk(KERN_ERR "KVM: Unknown interrupt: 0x%x\n", priority);
		break;
	}

#if 0
	printk(KERN_INFO "Deliver interrupt 0x%x? %x\n", vec, deliver);
#endif

	if (deliver)
274
		kvmppc_inject_interrupt(vcpu, vec, flags);
A
Alexander Graf 已提交
275 276 277 278 279 280 281 282 283 284 285 286 287 288 289

	return deliver;
}

void kvmppc_core_deliver_interrupts(struct kvm_vcpu *vcpu)
{
	unsigned long *pending = &vcpu->arch.pending_exceptions;
	unsigned int priority;

#ifdef EXIT_DEBUG
	if (vcpu->arch.pending_exceptions)
		printk(KERN_EMERG "KVM: Check pending: %lx\n", vcpu->arch.pending_exceptions);
#endif
	priority = __ffs(*pending);
	while (priority <= (sizeof(unsigned int) * 8)) {
290 291 292
		if (kvmppc_book3s_irqprio_deliver(vcpu, priority) &&
		    (priority != BOOK3S_IRQPRIO_DECREMENTER)) {
			/* DEC interrupts get cleared by mtdec */
A
Alexander Graf 已提交
293 294 295 296 297 298 299 300 301 302 303 304
			clear_bit(priority, &vcpu->arch.pending_exceptions);
			break;
		}

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

void kvmppc_set_pvr(struct kvm_vcpu *vcpu, u32 pvr)
{
305
	vcpu->arch.hflags &= ~BOOK3S_HFLAG_SLB;
A
Alexander Graf 已提交
306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560
	vcpu->arch.pvr = pvr;
	if ((pvr >= 0x330000) && (pvr < 0x70330000)) {
		kvmppc_mmu_book3s_64_init(vcpu);
		to_book3s(vcpu)->hior = 0xfff00000;
		to_book3s(vcpu)->msr_mask = 0xffffffffffffffffULL;
	} else {
		kvmppc_mmu_book3s_32_init(vcpu);
		to_book3s(vcpu)->hior = 0;
		to_book3s(vcpu)->msr_mask = 0xffffffffULL;
	}

	/* If we are in hypervisor level on 970, we can tell the CPU to
	 * treat DCBZ as 32 bytes store */
	vcpu->arch.hflags &= ~BOOK3S_HFLAG_DCBZ32;
	if (vcpu->arch.mmu.is_dcbz32(vcpu) && (mfmsr() & MSR_HV) &&
	    !strcmp(cur_cpu_spec->platform, "ppc970"))
		vcpu->arch.hflags |= BOOK3S_HFLAG_DCBZ32;

}

/* Book3s_32 CPUs always have 32 bytes cache line size, which Linux assumes. To
 * make Book3s_32 Linux work on Book3s_64, we have to make sure we trap dcbz to
 * emulate 32 bytes dcbz length.
 *
 * The Book3s_64 inventors also realized this case and implemented a special bit
 * in the HID5 register, which is a hypervisor ressource. Thus we can't use it.
 *
 * My approach here is to patch the dcbz instruction on executing pages.
 */
static void kvmppc_patch_dcbz(struct kvm_vcpu *vcpu, struct kvmppc_pte *pte)
{
	bool touched = false;
	hva_t hpage;
	u32 *page;
	int i;

	hpage = gfn_to_hva(vcpu->kvm, pte->raddr >> PAGE_SHIFT);
	if (kvm_is_error_hva(hpage))
		return;

	hpage |= pte->raddr & ~PAGE_MASK;
	hpage &= ~0xFFFULL;

	page = vmalloc(HW_PAGE_SIZE);

	if (copy_from_user(page, (void __user *)hpage, HW_PAGE_SIZE))
		goto out;

	for (i=0; i < HW_PAGE_SIZE / 4; i++)
		if ((page[i] & 0xff0007ff) == INS_DCBZ) {
			page[i] &= 0xfffffff7; // reserved instruction, so we trap
			touched = true;
		}

	if (touched)
		copy_to_user((void __user *)hpage, page, HW_PAGE_SIZE);

out:
	vfree(page);
}

static int kvmppc_xlate(struct kvm_vcpu *vcpu, ulong eaddr, bool data,
			 struct kvmppc_pte *pte)
{
	int relocated = (vcpu->arch.msr & (data ? MSR_DR : MSR_IR));
	int r;

	if (relocated) {
		r = vcpu->arch.mmu.xlate(vcpu, eaddr, pte, data);
	} else {
		pte->eaddr = eaddr;
		pte->raddr = eaddr & 0xffffffff;
		pte->vpage = eaddr >> 12;
		switch (vcpu->arch.msr & (MSR_DR|MSR_IR)) {
		case 0:
			pte->vpage |= VSID_REAL;
		case MSR_DR:
			pte->vpage |= VSID_REAL_DR;
		case MSR_IR:
			pte->vpage |= VSID_REAL_IR;
		}
		pte->may_read = true;
		pte->may_write = true;
		pte->may_execute = true;
		r = 0;
	}

	return r;
}

static hva_t kvmppc_bad_hva(void)
{
	return PAGE_OFFSET;
}

static hva_t kvmppc_pte_to_hva(struct kvm_vcpu *vcpu, struct kvmppc_pte *pte,
			       bool read)
{
	hva_t hpage;

	if (read && !pte->may_read)
		goto err;

	if (!read && !pte->may_write)
		goto err;

	hpage = gfn_to_hva(vcpu->kvm, pte->raddr >> PAGE_SHIFT);
	if (kvm_is_error_hva(hpage))
		goto err;

	return hpage | (pte->raddr & ~PAGE_MASK);
err:
	return kvmppc_bad_hva();
}

int kvmppc_st(struct kvm_vcpu *vcpu, ulong eaddr, int size, void *ptr)
{
	struct kvmppc_pte pte;
	hva_t hva = eaddr;

	vcpu->stat.st++;

	if (kvmppc_xlate(vcpu, eaddr, false, &pte))
		goto err;

	hva = kvmppc_pte_to_hva(vcpu, &pte, false);
	if (kvm_is_error_hva(hva))
		goto err;

	if (copy_to_user((void __user *)hva, ptr, size)) {
		printk(KERN_INFO "kvmppc_st at 0x%lx failed\n", hva);
		goto err;
	}

	return 0;

err:
	return -ENOENT;
}

int kvmppc_ld(struct kvm_vcpu *vcpu, ulong eaddr, int size, void *ptr,
		      bool data)
{
	struct kvmppc_pte pte;
	hva_t hva = eaddr;

	vcpu->stat.ld++;

	if (kvmppc_xlate(vcpu, eaddr, data, &pte))
		goto err;

	hva = kvmppc_pte_to_hva(vcpu, &pte, true);
	if (kvm_is_error_hva(hva))
		goto err;

	if (copy_from_user(ptr, (void __user *)hva, size)) {
		printk(KERN_INFO "kvmppc_ld at 0x%lx failed\n", hva);
		goto err;
	}

	return 0;

err:
	return -ENOENT;
}

static int kvmppc_visible_gfn(struct kvm_vcpu *vcpu, gfn_t gfn)
{
	return kvm_is_visible_gfn(vcpu->kvm, gfn);
}

int kvmppc_handle_pagefault(struct kvm_run *run, struct kvm_vcpu *vcpu,
			    ulong eaddr, int vec)
{
	bool data = (vec == BOOK3S_INTERRUPT_DATA_STORAGE);
	int r = RESUME_GUEST;
	int relocated;
	int page_found = 0;
	struct kvmppc_pte pte;
	bool is_mmio = false;

	if ( vec == BOOK3S_INTERRUPT_DATA_STORAGE ) {
		relocated = (vcpu->arch.msr & MSR_DR);
	} else {
		relocated = (vcpu->arch.msr & MSR_IR);
	}

	/* Resolve real address if translation turned on */
	if (relocated) {
		page_found = vcpu->arch.mmu.xlate(vcpu, eaddr, &pte, data);
	} else {
		pte.may_execute = true;
		pte.may_read = true;
		pte.may_write = true;
		pte.raddr = eaddr & 0xffffffff;
		pte.eaddr = eaddr;
		pte.vpage = eaddr >> 12;
		switch (vcpu->arch.msr & (MSR_DR|MSR_IR)) {
		case 0:
			pte.vpage |= VSID_REAL;
		case MSR_DR:
			pte.vpage |= VSID_REAL_DR;
		case MSR_IR:
			pte.vpage |= VSID_REAL_IR;
		}
	}

	if (vcpu->arch.mmu.is_dcbz32(vcpu) &&
	   (!(vcpu->arch.hflags & BOOK3S_HFLAG_DCBZ32))) {
		/*
		 * If we do the dcbz hack, we have to NX on every execution,
		 * so we can patch the executing code. This renders our guest
		 * NX-less.
		 */
		pte.may_execute = !data;
	}

	if (page_found == -ENOENT) {
		/* Page not found in guest PTE entries */
		vcpu->arch.dear = vcpu->arch.fault_dear;
		to_book3s(vcpu)->dsisr = vcpu->arch.fault_dsisr;
		vcpu->arch.msr |= (vcpu->arch.shadow_msr & 0x00000000f8000000ULL);
		kvmppc_book3s_queue_irqprio(vcpu, vec);
	} else if (page_found == -EPERM) {
		/* Storage protection */
		vcpu->arch.dear = vcpu->arch.fault_dear;
		to_book3s(vcpu)->dsisr = vcpu->arch.fault_dsisr & ~DSISR_NOHPTE;
		to_book3s(vcpu)->dsisr |= DSISR_PROTFAULT;
		vcpu->arch.msr |= (vcpu->arch.shadow_msr & 0x00000000f8000000ULL);
		kvmppc_book3s_queue_irqprio(vcpu, vec);
	} else if (page_found == -EINVAL) {
		/* Page not found in guest SLB */
		vcpu->arch.dear = vcpu->arch.fault_dear;
		kvmppc_book3s_queue_irqprio(vcpu, vec + 0x80);
	} else if (!is_mmio &&
		   kvmppc_visible_gfn(vcpu, pte.raddr >> PAGE_SHIFT)) {
		/* The guest's PTE is not mapped yet. Map on the host */
		kvmppc_mmu_map_page(vcpu, &pte);
		if (data)
			vcpu->stat.sp_storage++;
		else if (vcpu->arch.mmu.is_dcbz32(vcpu) &&
			(!(vcpu->arch.hflags & BOOK3S_HFLAG_DCBZ32)))
			kvmppc_patch_dcbz(vcpu, &pte);
	} else {
		/* MMIO */
		vcpu->stat.mmio_exits++;
		vcpu->arch.paddr_accessed = pte.raddr;
		r = kvmppc_emulate_mmio(run, vcpu);
		if ( r == RESUME_HOST_NV )
			r = RESUME_HOST;
	}

	return r;
}

561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671
static inline int get_fpr_index(int i)
{
#ifdef CONFIG_VSX
	i *= 2;
#endif
	return i;
}

/* Give up external provider (FPU, Altivec, VSX) */
static void kvmppc_giveup_ext(struct kvm_vcpu *vcpu, ulong msr)
{
	struct thread_struct *t = &current->thread;
	u64 *vcpu_fpr = vcpu->arch.fpr;
	u64 *vcpu_vsx = vcpu->arch.vsr;
	u64 *thread_fpr = (u64*)t->fpr;
	int i;

	if (!(vcpu->arch.guest_owned_ext & msr))
		return;

#ifdef DEBUG_EXT
	printk(KERN_INFO "Giving up ext 0x%lx\n", msr);
#endif

	switch (msr) {
	case MSR_FP:
		giveup_fpu(current);
		for (i = 0; i < ARRAY_SIZE(vcpu->arch.fpr); i++)
			vcpu_fpr[i] = thread_fpr[get_fpr_index(i)];

		vcpu->arch.fpscr = t->fpscr.val;
		break;
	case MSR_VEC:
#ifdef CONFIG_ALTIVEC
		giveup_altivec(current);
		memcpy(vcpu->arch.vr, t->vr, sizeof(vcpu->arch.vr));
		vcpu->arch.vscr = t->vscr;
#endif
		break;
	case MSR_VSX:
#ifdef CONFIG_VSX
		__giveup_vsx(current);
		for (i = 0; i < ARRAY_SIZE(vcpu->arch.vsr); i++)
			vcpu_vsx[i] = thread_fpr[get_fpr_index(i) + 1];
#endif
		break;
	default:
		BUG();
	}

	vcpu->arch.guest_owned_ext &= ~msr;
	current->thread.regs->msr &= ~msr;
	kvmppc_set_msr(vcpu, vcpu->arch.msr);
}

/* Handle external providers (FPU, Altivec, VSX) */
static int kvmppc_handle_ext(struct kvm_vcpu *vcpu, unsigned int exit_nr,
			     ulong msr)
{
	struct thread_struct *t = &current->thread;
	u64 *vcpu_fpr = vcpu->arch.fpr;
	u64 *vcpu_vsx = vcpu->arch.vsr;
	u64 *thread_fpr = (u64*)t->fpr;
	int i;

	if (!(vcpu->arch.msr & msr)) {
		kvmppc_book3s_queue_irqprio(vcpu, exit_nr);
		return RESUME_GUEST;
	}

#ifdef DEBUG_EXT
	printk(KERN_INFO "Loading up ext 0x%lx\n", msr);
#endif

	current->thread.regs->msr |= msr;

	switch (msr) {
	case MSR_FP:
		for (i = 0; i < ARRAY_SIZE(vcpu->arch.fpr); i++)
			thread_fpr[get_fpr_index(i)] = vcpu_fpr[i];

		t->fpscr.val = vcpu->arch.fpscr;
		t->fpexc_mode = 0;
		kvmppc_load_up_fpu();
		break;
	case MSR_VEC:
#ifdef CONFIG_ALTIVEC
		memcpy(t->vr, vcpu->arch.vr, sizeof(vcpu->arch.vr));
		t->vscr = vcpu->arch.vscr;
		t->vrsave = -1;
		kvmppc_load_up_altivec();
#endif
		break;
	case MSR_VSX:
#ifdef CONFIG_VSX
		for (i = 0; i < ARRAY_SIZE(vcpu->arch.vsr); i++)
			thread_fpr[get_fpr_index(i) + 1] = vcpu_vsx[i];
		kvmppc_load_up_vsx();
#endif
		break;
	default:
		BUG();
	}

	vcpu->arch.guest_owned_ext |= msr;

	kvmppc_set_msr(vcpu, vcpu->arch.msr);

	return RESUME_GUEST;
}

A
Alexander Graf 已提交
672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753
int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
                       unsigned int exit_nr)
{
	int r = RESUME_HOST;

	vcpu->stat.sum_exits++;

	run->exit_reason = KVM_EXIT_UNKNOWN;
	run->ready_for_interrupt_injection = 1;
#ifdef EXIT_DEBUG
	printk(KERN_EMERG "exit_nr=0x%x | pc=0x%lx | dar=0x%lx | dec=0x%x | msr=0x%lx\n",
		exit_nr, vcpu->arch.pc, vcpu->arch.fault_dear,
		kvmppc_get_dec(vcpu), vcpu->arch.msr);
#elif defined (EXIT_DEBUG_SIMPLE)
	if ((exit_nr != 0x900) && (exit_nr != 0x500))
		printk(KERN_EMERG "exit_nr=0x%x | pc=0x%lx | dar=0x%lx | msr=0x%lx\n",
			exit_nr, vcpu->arch.pc, vcpu->arch.fault_dear,
			vcpu->arch.msr);
#endif
	kvm_resched(vcpu);
	switch (exit_nr) {
	case BOOK3S_INTERRUPT_INST_STORAGE:
		vcpu->stat.pf_instruc++;
		/* only care about PTEG not found errors, but leave NX alone */
		if (vcpu->arch.shadow_msr & 0x40000000) {
			r = kvmppc_handle_pagefault(run, vcpu, vcpu->arch.pc, exit_nr);
			vcpu->stat.sp_instruc++;
		} else if (vcpu->arch.mmu.is_dcbz32(vcpu) &&
			  (!(vcpu->arch.hflags & BOOK3S_HFLAG_DCBZ32))) {
			/*
			 * XXX If we do the dcbz hack we use the NX bit to flush&patch the page,
			 *     so we can't use the NX bit inside the guest. Let's cross our fingers,
			 *     that no guest that needs the dcbz hack does NX.
			 */
			kvmppc_mmu_pte_flush(vcpu, vcpu->arch.pc, ~0xFFFULL);
		} else {
			vcpu->arch.msr |= (vcpu->arch.shadow_msr & 0x58000000);
			kvmppc_book3s_queue_irqprio(vcpu, exit_nr);
			kvmppc_mmu_pte_flush(vcpu, vcpu->arch.pc, ~0xFFFULL);
			r = RESUME_GUEST;
		}
		break;
	case BOOK3S_INTERRUPT_DATA_STORAGE:
		vcpu->stat.pf_storage++;
		/* The only case we need to handle is missing shadow PTEs */
		if (vcpu->arch.fault_dsisr & DSISR_NOHPTE) {
			r = kvmppc_handle_pagefault(run, vcpu, vcpu->arch.fault_dear, exit_nr);
		} else {
			vcpu->arch.dear = vcpu->arch.fault_dear;
			to_book3s(vcpu)->dsisr = vcpu->arch.fault_dsisr;
			kvmppc_book3s_queue_irqprio(vcpu, exit_nr);
			kvmppc_mmu_pte_flush(vcpu, vcpu->arch.dear, ~0xFFFULL);
			r = RESUME_GUEST;
		}
		break;
	case BOOK3S_INTERRUPT_DATA_SEGMENT:
		if (kvmppc_mmu_map_segment(vcpu, vcpu->arch.fault_dear) < 0) {
			vcpu->arch.dear = vcpu->arch.fault_dear;
			kvmppc_book3s_queue_irqprio(vcpu,
				BOOK3S_INTERRUPT_DATA_SEGMENT);
		}
		r = RESUME_GUEST;
		break;
	case BOOK3S_INTERRUPT_INST_SEGMENT:
		if (kvmppc_mmu_map_segment(vcpu, vcpu->arch.pc) < 0) {
			kvmppc_book3s_queue_irqprio(vcpu,
				BOOK3S_INTERRUPT_INST_SEGMENT);
		}
		r = RESUME_GUEST;
		break;
	/* We're good on these - the host merely wanted to get our attention */
	case BOOK3S_INTERRUPT_DECREMENTER:
		vcpu->stat.dec_exits++;
		r = RESUME_GUEST;
		break;
	case BOOK3S_INTERRUPT_EXTERNAL:
		vcpu->stat.ext_intr_exits++;
		r = RESUME_GUEST;
		break;
	case BOOK3S_INTERRUPT_PROGRAM:
	{
		enum emulation_result er;
754 755 756
		ulong flags;

		flags = (vcpu->arch.shadow_msr & 0x1f0000ull);
A
Alexander Graf 已提交
757 758 759 760 761 762 763

		if (vcpu->arch.msr & MSR_PR) {
#ifdef EXIT_DEBUG
			printk(KERN_INFO "Userspace triggered 0x700 exception at 0x%lx (0x%x)\n", vcpu->arch.pc, vcpu->arch.last_inst);
#endif
			if ((vcpu->arch.last_inst & 0xff0007ff) !=
			    (INS_DCBZ & 0xfffffff7)) {
764
				kvmppc_core_queue_program(vcpu, flags);
A
Alexander Graf 已提交
765 766 767 768 769 770 771 772 773
				r = RESUME_GUEST;
				break;
			}
		}

		vcpu->stat.emulated_inst_exits++;
		er = kvmppc_emulate_instruction(run, vcpu);
		switch (er) {
		case EMULATE_DONE:
774
			r = RESUME_GUEST_NV;
A
Alexander Graf 已提交
775 776 777 778
			break;
		case EMULATE_FAIL:
			printk(KERN_CRIT "%s: emulation at %lx failed (%08x)\n",
			       __func__, vcpu->arch.pc, vcpu->arch.last_inst);
779
			kvmppc_core_queue_program(vcpu, flags);
A
Alexander Graf 已提交
780 781 782 783 784 785 786 787 788
			r = RESUME_GUEST;
			break;
		default:
			BUG();
		}
		break;
	}
	case BOOK3S_INTERRUPT_SYSCALL:
#ifdef EXIT_DEBUG
789
		printk(KERN_INFO "Syscall Nr %d\n", (int)kvmppc_get_gpr(vcpu, 0));
A
Alexander Graf 已提交
790 791 792 793 794 795
#endif
		vcpu->stat.syscall_exits++;
		kvmppc_book3s_queue_irqprio(vcpu, exit_nr);
		r = RESUME_GUEST;
		break;
	case BOOK3S_INTERRUPT_FP_UNAVAIL:
796 797
		r = kvmppc_handle_ext(vcpu, exit_nr, MSR_FP);
		break;
A
Alexander Graf 已提交
798
	case BOOK3S_INTERRUPT_ALTIVEC:
799 800
		r = kvmppc_handle_ext(vcpu, exit_nr, MSR_VEC);
		break;
A
Alexander Graf 已提交
801
	case BOOK3S_INTERRUPT_VSX:
802 803 804 805
		r = kvmppc_handle_ext(vcpu, exit_nr, MSR_VSX);
		break;
	case BOOK3S_INTERRUPT_MACHINE_CHECK:
	case BOOK3S_INTERRUPT_TRACE:
A
Alexander Graf 已提交
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
		kvmppc_book3s_queue_irqprio(vcpu, exit_nr);
		r = RESUME_GUEST;
		break;
	default:
		/* Ugh - bork here! What did we get? */
		printk(KERN_EMERG "exit_nr=0x%x | pc=0x%lx | msr=0x%lx\n", exit_nr, vcpu->arch.pc, vcpu->arch.shadow_msr);
		r = RESUME_HOST;
		BUG();
		break;
	}


	if (!(r & RESUME_HOST)) {
		/* To avoid clobbering exit_reason, only check for signals if
		 * we aren't already exiting to userspace for some other
		 * reason. */
		if (signal_pending(current)) {
#ifdef EXIT_DEBUG
			printk(KERN_EMERG "KVM: Going back to host\n");
#endif
			vcpu->stat.signal_exits++;
			run->exit_reason = KVM_EXIT_INTR;
			r = -EINTR;
		} else {
			/* In case an interrupt came in that was triggered
			 * from userspace (like DEC), we need to check what
			 * to inject now! */
			kvmppc_core_deliver_interrupts(vcpu);
		}
	}

#ifdef EXIT_DEBUG
	printk(KERN_EMERG "KVM exit: vcpu=0x%p pc=0x%lx r=0x%x\n", vcpu, vcpu->arch.pc, r);
#endif

	return r;
}

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

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

	regs->pc = vcpu->arch.pc;
854
	regs->cr = kvmppc_get_cr(vcpu);
A
Alexander Graf 已提交
855 856
	regs->ctr = vcpu->arch.ctr;
	regs->lr = vcpu->arch.lr;
857
	regs->xer = kvmppc_get_xer(vcpu);
A
Alexander Graf 已提交
858 859 860 861 862 863 864 865 866 867 868 869 870
	regs->msr = vcpu->arch.msr;
	regs->srr0 = vcpu->arch.srr0;
	regs->srr1 = vcpu->arch.srr1;
	regs->pid = vcpu->arch.pid;
	regs->sprg0 = vcpu->arch.sprg0;
	regs->sprg1 = vcpu->arch.sprg1;
	regs->sprg2 = vcpu->arch.sprg2;
	regs->sprg3 = vcpu->arch.sprg3;
	regs->sprg5 = vcpu->arch.sprg4;
	regs->sprg6 = vcpu->arch.sprg5;
	regs->sprg7 = vcpu->arch.sprg6;

	for (i = 0; i < ARRAY_SIZE(regs->gpr); i++)
871
		regs->gpr[i] = kvmppc_get_gpr(vcpu, i);
A
Alexander Graf 已提交
872 873 874 875 876 877 878 879 880

	return 0;
}

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

	vcpu->arch.pc = regs->pc;
881
	kvmppc_set_cr(vcpu, regs->cr);
A
Alexander Graf 已提交
882 883
	vcpu->arch.ctr = regs->ctr;
	vcpu->arch.lr = regs->lr;
884
	kvmppc_set_xer(vcpu, regs->xer);
A
Alexander Graf 已提交
885 886 887 888 889 890 891 892 893 894 895
	kvmppc_set_msr(vcpu, regs->msr);
	vcpu->arch.srr0 = regs->srr0;
	vcpu->arch.srr1 = regs->srr1;
	vcpu->arch.sprg0 = regs->sprg0;
	vcpu->arch.sprg1 = regs->sprg1;
	vcpu->arch.sprg2 = regs->sprg2;
	vcpu->arch.sprg3 = regs->sprg3;
	vcpu->arch.sprg5 = regs->sprg4;
	vcpu->arch.sprg6 = regs->sprg5;
	vcpu->arch.sprg7 = regs->sprg6;

896 897
	for (i = 0; i < ARRAY_SIZE(regs->gpr); i++)
		kvmppc_set_gpr(vcpu, i, regs->gpr[i]);
A
Alexander Graf 已提交
898 899 900 901 902 903 904

	return 0;
}

int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
                                  struct kvm_sregs *sregs)
{
905 906 907
	struct kvmppc_vcpu_book3s *vcpu3s = to_book3s(vcpu);
	int i;

A
Alexander Graf 已提交
908
	sregs->pvr = vcpu->arch.pvr;
909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925

	sregs->u.s.sdr1 = to_book3s(vcpu)->sdr1;
	if (vcpu->arch.hflags & BOOK3S_HFLAG_SLB) {
		for (i = 0; i < 64; i++) {
			sregs->u.s.ppc64.slb[i].slbe = vcpu3s->slb[i].orige | i;
			sregs->u.s.ppc64.slb[i].slbv = vcpu3s->slb[i].origv;
		}
	} else {
		for (i = 0; i < 16; i++) {
			sregs->u.s.ppc32.sr[i] = vcpu3s->sr[i].raw;
			sregs->u.s.ppc32.sr[i] = vcpu3s->sr[i].raw;
		}
		for (i = 0; i < 8; i++) {
			sregs->u.s.ppc32.ibat[i] = vcpu3s->ibat[i].raw;
			sregs->u.s.ppc32.dbat[i] = vcpu3s->dbat[i].raw;
		}
	}
A
Alexander Graf 已提交
926 927 928 929 930 931
	return 0;
}

int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
                                  struct kvm_sregs *sregs)
{
932 933 934
	struct kvmppc_vcpu_book3s *vcpu3s = to_book3s(vcpu);
	int i;

A
Alexander Graf 已提交
935
	kvmppc_set_pvr(vcpu, sregs->pvr);
936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960

	vcpu3s->sdr1 = sregs->u.s.sdr1;
	if (vcpu->arch.hflags & BOOK3S_HFLAG_SLB) {
		for (i = 0; i < 64; i++) {
			vcpu->arch.mmu.slbmte(vcpu, sregs->u.s.ppc64.slb[i].slbv,
						    sregs->u.s.ppc64.slb[i].slbe);
		}
	} else {
		for (i = 0; i < 16; i++) {
			vcpu->arch.mmu.mtsrin(vcpu, i, sregs->u.s.ppc32.sr[i]);
		}
		for (i = 0; i < 8; i++) {
			kvmppc_set_bat(vcpu, &(vcpu3s->ibat[i]), false,
				       (u32)sregs->u.s.ppc32.ibat[i]);
			kvmppc_set_bat(vcpu, &(vcpu3s->ibat[i]), true,
				       (u32)(sregs->u.s.ppc32.ibat[i] >> 32));
			kvmppc_set_bat(vcpu, &(vcpu3s->dbat[i]), false,
				       (u32)sregs->u.s.ppc32.dbat[i]);
			kvmppc_set_bat(vcpu, &(vcpu3s->dbat[i]), true,
				       (u32)(sregs->u.s.ppc32.dbat[i] >> 32));
		}
	}

	/* Flush the MMU after messing with the segments */
	kvmppc_mmu_pte_flush(vcpu, 0, 0);
A
Alexander Graf 已提交
961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991
	return 0;
}

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)
{
	return 0;
}

/*
 * 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)
{
	struct kvm_memory_slot *memslot;
	struct kvm_vcpu *vcpu;
	ulong ga, ga_end;
	int is_dirty = 0;
	int r, n;

992
	mutex_lock(&kvm->slots_lock);
A
Alexander Graf 已提交
993 994 995 996 997 998 999

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

	/* If nothing is dirty, don't bother messing with page tables. */
	if (is_dirty) {
1000
		memslot = &kvm->memslots->memslots[log->slot];
A
Alexander Graf 已提交
1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013

		ga = memslot->base_gfn << PAGE_SHIFT;
		ga_end = ga + (memslot->npages << PAGE_SHIFT);

		kvm_for_each_vcpu(n, vcpu, kvm)
			kvmppc_mmu_pte_pflush(vcpu, ga, ga_end);

		n = ALIGN(memslot->npages, BITS_PER_LONG) / 8;
		memset(memslot->dirty_bitmap, 0, n);
	}

	r = 0;
out:
1014
	mutex_unlock(&kvm->slots_lock);
A
Alexander Graf 已提交
1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051
	return r;
}

int kvmppc_core_check_processor_compat(void)
{
	return 0;
}

struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
{
	struct kvmppc_vcpu_book3s *vcpu_book3s;
	struct kvm_vcpu *vcpu;
	int err;

	vcpu_book3s = (struct kvmppc_vcpu_book3s *)__get_free_pages( GFP_KERNEL | __GFP_ZERO,
			get_order(sizeof(struct kvmppc_vcpu_book3s)));
	if (!vcpu_book3s) {
		err = -ENOMEM;
		goto out;
	}

	vcpu = &vcpu_book3s->vcpu;
	err = kvm_vcpu_init(vcpu, kvm, id);
	if (err)
		goto free_vcpu;

	vcpu->arch.host_retip = kvm_return_point;
	vcpu->arch.host_msr = mfmsr();
	/* default to book3s_64 (970fx) */
	vcpu->arch.pvr = 0x3C0301;
	kvmppc_set_pvr(vcpu, vcpu->arch.pvr);
	vcpu_book3s->slb_nr = 64;

	/* remember where some real-mode handlers are */
	vcpu->arch.trampoline_lowmem = kvmppc_trampoline_lowmem;
	vcpu->arch.trampoline_enter = kvmppc_trampoline_enter;
	vcpu->arch.highmem_handler = (ulong)kvmppc_handler_highmem;
1052
	vcpu->arch.rmcall = *(ulong*)kvmppc_rmcall;
A
Alexander Graf 已提交
1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085

	vcpu->arch.shadow_msr = MSR_USER64;

	err = __init_new_context();
	if (err < 0)
		goto free_vcpu;
	vcpu_book3s->context_id = err;

	vcpu_book3s->vsid_max = ((vcpu_book3s->context_id + 1) << USER_ESID_BITS) - 1;
	vcpu_book3s->vsid_first = vcpu_book3s->context_id << USER_ESID_BITS;
	vcpu_book3s->vsid_next = vcpu_book3s->vsid_first;

	return vcpu;

free_vcpu:
	free_pages((long)vcpu_book3s, get_order(sizeof(struct kvmppc_vcpu_book3s)));
out:
	return ERR_PTR(err);
}

void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu)
{
	struct kvmppc_vcpu_book3s *vcpu_book3s = to_book3s(vcpu);

	__destroy_context(vcpu_book3s->context_id);
	kvm_vcpu_uninit(vcpu);
	free_pages((long)vcpu_book3s, get_order(sizeof(struct kvmppc_vcpu_book3s)));
}

extern int __kvmppc_vcpu_entry(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu);
int __kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
{
	int ret;
1086 1087 1088 1089
	struct thread_struct ext_bkp;
	bool save_vec = current->thread.used_vr;
	bool save_vsx = current->thread.used_vsr;
	ulong ext_msr;
A
Alexander Graf 已提交
1090 1091 1092 1093 1094 1095 1096

	/* No need to go into the guest when all we do is going out */
	if (signal_pending(current)) {
		kvm_run->exit_reason = KVM_EXIT_INTR;
		return -EINTR;
	}

1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125
	/* Save FPU state in stack */
	if (current->thread.regs->msr & MSR_FP)
		giveup_fpu(current);
	memcpy(ext_bkp.fpr, current->thread.fpr, sizeof(current->thread.fpr));
	ext_bkp.fpscr = current->thread.fpscr;
	ext_bkp.fpexc_mode = current->thread.fpexc_mode;

#ifdef CONFIG_ALTIVEC
	/* Save Altivec state in stack */
	if (save_vec) {
		if (current->thread.regs->msr & MSR_VEC)
			giveup_altivec(current);
		memcpy(ext_bkp.vr, current->thread.vr, sizeof(ext_bkp.vr));
		ext_bkp.vscr = current->thread.vscr;
		ext_bkp.vrsave = current->thread.vrsave;
	}
	ext_bkp.used_vr = current->thread.used_vr;
#endif

#ifdef CONFIG_VSX
	/* Save VSX state in stack */
	if (save_vsx && (current->thread.regs->msr & MSR_VSX))
			__giveup_vsx(current);
	ext_bkp.used_vsr = current->thread.used_vsr;
#endif

	/* Remember the MSR with disabled extensions */
	ext_msr = current->thread.regs->msr;

A
Alexander Graf 已提交
1126 1127 1128 1129 1130 1131 1132
	/* XXX we get called with irq disabled - change that! */
	local_irq_enable();

	ret = __kvmppc_vcpu_entry(kvm_run, vcpu);

	local_irq_disable();

1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158
	current->thread.regs->msr = ext_msr;

	/* Make sure we save the guest FPU/Altivec/VSX state */
	kvmppc_giveup_ext(vcpu, MSR_FP);
	kvmppc_giveup_ext(vcpu, MSR_VEC);
	kvmppc_giveup_ext(vcpu, MSR_VSX);

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

#ifdef CONFIG_ALTIVEC
	/* Restore Altivec state from stack */
	if (save_vec && current->thread.used_vr) {
		memcpy(current->thread.vr, ext_bkp.vr, sizeof(ext_bkp.vr));
		current->thread.vscr = ext_bkp.vscr;
		current->thread.vrsave= ext_bkp.vrsave;
	}
	current->thread.used_vr = ext_bkp.used_vr;
#endif

#ifdef CONFIG_VSX
	current->thread.used_vsr = ext_bkp.used_vsr;
#endif

A
Alexander Graf 已提交
1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173
	return ret;
}

static int kvmppc_book3s_init(void)
{
	return kvm_init(NULL, sizeof(struct kvmppc_vcpu_book3s), THIS_MODULE);
}

static void kvmppc_book3s_exit(void)
{
	kvm_exit();
}

module_init(kvmppc_book3s_init);
module_exit(kvmppc_book3s_exit);