book3s_hv_rmhandlers.S 45.6 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22
/*
 * 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.
 *
 * Copyright 2011 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
 *
 * Derived from book3s_rmhandlers.S and other files, which are:
 *
 * Copyright SUSE Linux Products GmbH 2009
 *
 * Authors: Alexander Graf <agraf@suse.de>
 */

#include <asm/ppc_asm.h>
#include <asm/kvm_asm.h>
#include <asm/reg.h>
23
#include <asm/mmu.h>
24
#include <asm/page.h>
25 26
#include <asm/ptrace.h>
#include <asm/hvcall.h>
27 28
#include <asm/asm-offsets.h>
#include <asm/exception-64s.h>
29
#include <asm/kvm_book3s_asm.h>
30
#include <asm/mmu-hash64.h>
31

32 33 34 35
#ifdef __LITTLE_ENDIAN__
#error Need to fix lppaca and SLB shadow accesses in little endian mode
#endif

36
/*
37
 * Call kvmppc_hv_entry in real mode.
38 39 40 41 42 43 44
 * Must be called with interrupts hard-disabled.
 *
 * Input Registers:
 *
 * LR = return address to continue at after eventually re-enabling MMU
 */
_GLOBAL(kvmppc_hv_entry_trampoline)
45 46 47
	mflr	r0
	std	r0, PPC_LR_STKOFF(r1)
	stdu	r1, -112(r1)
48
	mfmsr	r10
49
	LOAD_REG_ADDR(r5, kvmppc_call_hv_entry)
50 51 52 53 54 55 56 57 58
	li	r0,MSR_RI
	andc	r0,r10,r0
	li	r6,MSR_IR | MSR_DR
	andc	r6,r10,r6
	mtmsrd	r0,1		/* clear RI in MSR */
	mtsrr0	r5
	mtsrr1	r6
	RFI

59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155
kvmppc_call_hv_entry:
	bl	kvmppc_hv_entry

	/* Back from guest - restore host state and return to caller */

	/* Restore host DABR and DABRX */
	ld	r5,HSTATE_DABR(r13)
	li	r6,7
	mtspr	SPRN_DABR,r5
	mtspr	SPRN_DABRX,r6

	/* Restore SPRG3 */
	ld	r3,PACA_SPRG3(r13)
	mtspr	SPRN_SPRG3,r3

	/*
	 * Reload DEC.  HDEC interrupts were disabled when
	 * we reloaded the host's LPCR value.
	 */
	ld	r3, HSTATE_DECEXP(r13)
	mftb	r4
	subf	r4, r4, r3
	mtspr	SPRN_DEC, r4

	/* Reload the host's PMU registers */
	ld	r3, PACALPPACAPTR(r13)	/* is the host using the PMU? */
	lbz	r4, LPPACA_PMCINUSE(r3)
	cmpwi	r4, 0
	beq	23f			/* skip if not */
	lwz	r3, HSTATE_PMC(r13)
	lwz	r4, HSTATE_PMC + 4(r13)
	lwz	r5, HSTATE_PMC + 8(r13)
	lwz	r6, HSTATE_PMC + 12(r13)
	lwz	r8, HSTATE_PMC + 16(r13)
	lwz	r9, HSTATE_PMC + 20(r13)
BEGIN_FTR_SECTION
	lwz	r10, HSTATE_PMC + 24(r13)
	lwz	r11, HSTATE_PMC + 28(r13)
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
	mtspr	SPRN_PMC1, r3
	mtspr	SPRN_PMC2, r4
	mtspr	SPRN_PMC3, r5
	mtspr	SPRN_PMC4, r6
	mtspr	SPRN_PMC5, r8
	mtspr	SPRN_PMC6, r9
BEGIN_FTR_SECTION
	mtspr	SPRN_PMC7, r10
	mtspr	SPRN_PMC8, r11
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
	ld	r3, HSTATE_MMCR(r13)
	ld	r4, HSTATE_MMCR + 8(r13)
	ld	r5, HSTATE_MMCR + 16(r13)
	mtspr	SPRN_MMCR1, r4
	mtspr	SPRN_MMCRA, r5
	mtspr	SPRN_MMCR0, r3
	isync
23:

	/*
	 * For external and machine check interrupts, we need
	 * to call the Linux handler to process the interrupt.
	 * We do that by jumping to absolute address 0x500 for
	 * external interrupts, or the machine_check_fwnmi label
	 * for machine checks (since firmware might have patched
	 * the vector area at 0x200).  The [h]rfid at the end of the
	 * handler will return to the book3s_hv_interrupts.S code.
	 * For other interrupts we do the rfid to get back
	 * to the book3s_hv_interrupts.S code here.
	 */
	ld	r8, 112+PPC_LR_STKOFF(r1)
	addi	r1, r1, 112
	ld	r7, HSTATE_HOST_MSR(r13)

	cmpwi	cr1, r12, BOOK3S_INTERRUPT_MACHINE_CHECK
	cmpwi	r12, BOOK3S_INTERRUPT_EXTERNAL
BEGIN_FTR_SECTION
	beq	11f
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)

	/* RFI into the highmem handler, or branch to interrupt handler */
	mfmsr	r6
	li	r0, MSR_RI
	andc	r6, r6, r0
	mtmsrd	r6, 1			/* Clear RI in MSR */
	mtsrr0	r8
	mtsrr1	r7
	beqa	0x500			/* external interrupt (PPC970) */
	beq	cr1, 13f		/* machine check */
	RFI

	/* On POWER7, we have external interrupts set to use HSRR0/1 */
11:	mtspr	SPRN_HSRR0, r8
	mtspr	SPRN_HSRR1, r7
	ba	0x500

13:	b	machine_check_fwnmi

156

157 158 159 160 161 162 163 164 165
/*
 * We come in here when wakened from nap mode on a secondary hw thread.
 * Relocation is off and most register values are lost.
 * r13 points to the PACA.
 */
	.globl	kvm_start_guest
kvm_start_guest:
	ld	r1,PACAEMERGSP(r13)
	subi	r1,r1,STACK_FRAME_OVERHEAD
166 167
	ld	r2,PACATOC(r13)

168 169
	li	r0,KVM_HWTHREAD_IN_KVM
	stb	r0,HSTATE_HWTHREAD_STATE(r13)
170

171 172 173
	/* NV GPR values from power7_idle() will no longer be valid */
	li	r0,1
	stb	r0,PACA_NAPSTATELOST(r13)
174

175 176 177 178 179 180 181 182 183 184 185
	/* were we napping due to cede? */
	lbz	r0,HSTATE_NAPPING(r13)
	cmpwi	r0,0
	bne	kvm_end_cede

	/*
	 * We weren't napping due to cede, so this must be a secondary
	 * thread being woken up to run a guest, or being woken up due
	 * to a stray IPI.  (Or due to some machine check or hypervisor
	 * maintenance interrupt while the core is in KVM.)
	 */
186 187 188 189 190

	/* Check the wake reason in SRR1 to see why we got here */
	mfspr	r3,SPRN_SRR1
	rlwinm	r3,r3,44-31,0x7		/* extract wake reason field */
	cmpwi	r3,4			/* was it an external interrupt? */
191 192 193
	bne	27f			/* if not */
	ld	r5,HSTATE_XICS_PHYS(r13)
	li	r7,XICS_XIRR		/* if it was an external interrupt, */
194
	lwzcix	r8,r5,r7		/* get and ack the interrupt */
195
	sync
196
	clrldi.	r9,r8,40		/* get interrupt source ID. */
197 198 199 200 201
	beq	28f			/* none there? */
	cmpwi	r9,XICS_IPI		/* was it an IPI? */
	bne	29f
	li	r0,0xff
	li	r6,XICS_MFRR
202
	stbcix	r0,r5,r6		/* clear IPI */
203 204
	stwcix	r8,r5,r7		/* EOI the interrupt */
	sync				/* order loading of vcpu after that */
205

206
	/* get vcpu pointer, NULL if we have no vcpu to run */
207 208
	ld	r4,HSTATE_KVM_VCPU(r13)
	cmpdi	r4,0
209
	/* if we have no vcpu to run, go back to sleep */
210
	beq	kvm_no_guest
211
	b	30f
212

213 214 215 216 217 218 219
27:	/* XXX should handle hypervisor maintenance interrupts etc. here */
	b	kvm_no_guest
28:	/* SRR1 said external but ICP said nope?? */
	b	kvm_no_guest
29:	/* External non-IPI interrupt to offline secondary thread? help?? */
	stw	r8,HSTATE_SAVED_XIRR(r13)
	b	kvm_no_guest
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
30:	bl	kvmppc_hv_entry

	/* Back from the guest, go back to nap */
	/* Clear our vcpu pointer so we don't come back in early */
	li	r0, 0
	std	r0, HSTATE_KVM_VCPU(r13)
	lwsync
	/* Clear any pending IPI - we're an offline thread */
	ld	r5, HSTATE_XICS_PHYS(r13)
	li	r7, XICS_XIRR
	lwzcix	r3, r5, r7		/* ack any pending interrupt */
	rlwinm.	r0, r3, 0, 0xffffff	/* any pending? */
	beq	37f
	sync
	li	r0, 0xff
	li	r6, XICS_MFRR
	stbcix	r0, r5, r6		/* clear the IPI */
	stwcix	r3, r5, r7		/* EOI it */
37:	sync

	/* increment the nap count and then go to nap mode */
	ld	r4, HSTATE_KVM_VCORE(r13)
	addi	r4, r4, VCORE_NAP_COUNT
	lwsync				/* make previous updates visible */
51:	lwarx	r3, 0, r4
	addi	r3, r3, 1
	stwcx.	r3, 0, r4
	bne	51b

kvm_no_guest:
	li	r0, KVM_HWTHREAD_IN_NAP
	stb	r0, HSTATE_HWTHREAD_STATE(r13)
	li	r3, LPCR_PECE0
	mfspr	r4, SPRN_LPCR
	rlwimi	r4, r3, 0, LPCR_PECE0 | LPCR_PECE1
	mtspr	SPRN_LPCR, r4
	isync
	std	r0, HSTATE_SCRATCH0(r13)
	ptesync
	ld	r0, HSTATE_SCRATCH0(r13)
1:	cmpd	r0, r0
	bne	1b
	nap
	b	.

/******************************************************************************
 *                                                                            *
 *                               Entry code                                   *
 *                                                                            *
 *****************************************************************************/

272 273 274 275 276 277 278 279 280 281 282 283
.global kvmppc_hv_entry
kvmppc_hv_entry:

	/* Required state:
	 *
	 * R4 = vcpu pointer
	 * MSR = ~IR|DR
	 * R13 = PACA
	 * R1 = host R1
	 * all other volatile GPRS = free
	 */
	mflr	r0
284 285
	std	r0, PPC_LR_STKOFF(r1)
	stdu	r1, -112(r1)
286

287 288 289 290 291 292 293 294 295
	/* Set partition DABR */
	/* Do this before re-enabling PMU to avoid P7 DABR corruption bug */
	li	r5,3
	ld	r6,VCPU_DABR(r4)
	mtspr	SPRN_DABRX,r5
	mtspr	SPRN_DABR,r6
BEGIN_FTR_SECTION
	isync
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
296 297 298 299 300 301 302 303 304 305 306 307 308

	/* Load guest PMU registers */
	/* R4 is live here (vcpu pointer) */
	li	r3, 1
	sldi	r3, r3, 31		/* MMCR0_FC (freeze counters) bit */
	mtspr	SPRN_MMCR0, r3		/* freeze all counters, disable ints */
	isync
	lwz	r3, VCPU_PMC(r4)	/* always load up guest PMU registers */
	lwz	r5, VCPU_PMC + 4(r4)	/* to prevent information leak */
	lwz	r6, VCPU_PMC + 8(r4)
	lwz	r7, VCPU_PMC + 12(r4)
	lwz	r8, VCPU_PMC + 16(r4)
	lwz	r9, VCPU_PMC + 20(r4)
309 310 311 312
BEGIN_FTR_SECTION
	lwz	r10, VCPU_PMC + 24(r4)
	lwz	r11, VCPU_PMC + 28(r4)
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
313 314 315 316 317 318
	mtspr	SPRN_PMC1, r3
	mtspr	SPRN_PMC2, r5
	mtspr	SPRN_PMC3, r6
	mtspr	SPRN_PMC4, r7
	mtspr	SPRN_PMC5, r8
	mtspr	SPRN_PMC6, r9
319 320 321 322
BEGIN_FTR_SECTION
	mtspr	SPRN_PMC7, r10
	mtspr	SPRN_PMC8, r11
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
323 324 325
	ld	r3, VCPU_MMCR(r4)
	ld	r5, VCPU_MMCR + 8(r4)
	ld	r6, VCPU_MMCR + 16(r4)
326 327
	ld	r7, VCPU_SIAR(r4)
	ld	r8, VCPU_SDAR(r4)
328 329
	mtspr	SPRN_MMCR1, r5
	mtspr	SPRN_MMCRA, r6
330 331
	mtspr	SPRN_SIAR, r7
	mtspr	SPRN_SDAR, r8
332 333 334 335 336 337
	mtspr	SPRN_MMCR0, r3
	isync

	/* Load up FP, VMX and VSX registers */
	bl	kvmppc_load_fp

338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355
	ld	r14, VCPU_GPR(R14)(r4)
	ld	r15, VCPU_GPR(R15)(r4)
	ld	r16, VCPU_GPR(R16)(r4)
	ld	r17, VCPU_GPR(R17)(r4)
	ld	r18, VCPU_GPR(R18)(r4)
	ld	r19, VCPU_GPR(R19)(r4)
	ld	r20, VCPU_GPR(R20)(r4)
	ld	r21, VCPU_GPR(R21)(r4)
	ld	r22, VCPU_GPR(R22)(r4)
	ld	r23, VCPU_GPR(R23)(r4)
	ld	r24, VCPU_GPR(R24)(r4)
	ld	r25, VCPU_GPR(R25)(r4)
	ld	r26, VCPU_GPR(R26)(r4)
	ld	r27, VCPU_GPR(R27)(r4)
	ld	r28, VCPU_GPR(R28)(r4)
	ld	r29, VCPU_GPR(R29)(r4)
	ld	r30, VCPU_GPR(R30)(r4)
	ld	r31, VCPU_GPR(R31)(r4)
356

357
BEGIN_FTR_SECTION
358 359 360
	/* Switch DSCR to guest value */
	ld	r5, VCPU_DSCR(r4)
	mtspr	SPRN_DSCR, r5
361
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
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

	/*
	 * Set the decrementer to the guest decrementer.
	 */
	ld	r8,VCPU_DEC_EXPIRES(r4)
	mftb	r7
	subf	r3,r7,r8
	mtspr	SPRN_DEC,r3
	stw	r3,VCPU_DEC(r4)

	ld	r5, VCPU_SPRG0(r4)
	ld	r6, VCPU_SPRG1(r4)
	ld	r7, VCPU_SPRG2(r4)
	ld	r8, VCPU_SPRG3(r4)
	mtspr	SPRN_SPRG0, r5
	mtspr	SPRN_SPRG1, r6
	mtspr	SPRN_SPRG2, r7
	mtspr	SPRN_SPRG3, r8

	/* Save R1 in the PACA */
	std	r1, HSTATE_HOST_R1(r13)

	/* Load up DAR and DSISR */
	ld	r5, VCPU_DAR(r4)
	lwz	r6, VCPU_DSISR(r4)
	mtspr	SPRN_DAR, r5
	mtspr	SPRN_DSISR, r6

390 391 392
	li	r6, KVM_GUEST_MODE_HOST_HV
	stb	r6, HSTATE_IN_GUEST(r13)

393
BEGIN_FTR_SECTION
394 395 396 397 398 399 400
	/* Restore AMR and UAMOR, set AMOR to all 1s */
	ld	r5,VCPU_AMR(r4)
	ld	r6,VCPU_UAMOR(r4)
	li	r7,-1
	mtspr	SPRN_AMR,r5
	mtspr	SPRN_UAMOR,r6
	mtspr	SPRN_AMOR,r7
401
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
402 403 404 405 406 407 408

	/* Clear out SLB */
	li	r6,0
	slbmte	r6,r6
	slbia
	ptesync

409 410 411 412 413 414 415 416
BEGIN_FTR_SECTION
	b	30f
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
	/*
	 * POWER7 host -> guest partition switch code.
	 * We don't have to lock against concurrent tlbies,
	 * but we do have to coordinate across hardware threads.
	 */
417 418 419 420 421 422 423 424 425 426 427
	/* Increment entry count iff exit count is zero. */
	ld	r5,HSTATE_KVM_VCORE(r13)
	addi	r9,r5,VCORE_ENTRY_EXIT
21:	lwarx	r3,0,r9
	cmpwi	r3,0x100		/* any threads starting to exit? */
	bge	secondary_too_late	/* if so we're too late to the party */
	addi	r3,r3,1
	stwcx.	r3,0,r9
	bne	21b

	/* Primary thread switches to guest partition. */
428
	ld	r9,VCPU_KVM(r4)		/* pointer to struct kvm */
429 430 431
	lwz	r6,VCPU_PTID(r4)
	cmpwi	r6,0
	bne	20f
432 433 434 435 436 437 438 439
	ld	r6,KVM_SDR1(r9)
	lwz	r7,KVM_LPID(r9)
	li	r0,LPID_RSVD		/* switch to reserved LPID */
	mtspr	SPRN_LPID,r0
	ptesync
	mtspr	SPRN_SDR1,r6		/* switch to partition page table */
	mtspr	SPRN_LPID,r7
	isync
440 441 442 443 444 445 446 447

	/* See if we need to flush the TLB */
	lhz	r6,PACAPACAINDEX(r13)	/* test_bit(cpu, need_tlb_flush) */
	clrldi	r7,r6,64-6		/* extract bit number (6 bits) */
	srdi	r6,r6,6			/* doubleword number */
	sldi	r6,r6,3			/* address offset */
	add	r6,r6,r9
	addi	r6,r6,KVM_NEED_FLUSH	/* dword in kvm->arch.need_tlb_flush */
448
	li	r0,1
449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465
	sld	r0,r0,r7
	ld	r7,0(r6)
	and.	r7,r7,r0
	beq	22f
23:	ldarx	r7,0,r6			/* if set, clear the bit */
	andc	r7,r7,r0
	stdcx.	r7,0,r6
	bne	23b
	li	r6,128			/* and flush the TLB */
	mtctr	r6
	li	r7,0x800		/* IS field = 0b10 */
	ptesync
28:	tlbiel	r7
	addi	r7,r7,0x1000
	bdnz	28b
	ptesync

466 467 468 469 470 471 472 473 474 475 476 477 478 479 480
	/* Add timebase offset onto timebase */
22:	ld	r8,VCORE_TB_OFFSET(r5)
	cmpdi	r8,0
	beq	37f
	mftb	r6		/* current host timebase */
	add	r8,r8,r6
	mtspr	SPRN_TBU40,r8	/* update upper 40 bits */
	mftb	r7		/* check if lower 24 bits overflowed */
	clrldi	r6,r6,40
	clrldi	r7,r7,40
	cmpld	r7,r6
	bge	37f
	addis	r8,r8,0x100	/* if so, increment upper 40 bits */
	mtspr	SPRN_TBU40,r8

481 482 483 484 485 486 487
	/* Load guest PCR value to select appropriate compat mode */
37:	ld	r7, VCORE_PCR(r5)
	cmpdi	r7, 0
	beq	38f
	mtspr	SPRN_PCR, r7
38:
	li	r0,1
488 489 490 491 492 493 494
	stb	r0,VCORE_IN_GUEST(r5)	/* signal secondaries to continue */
	b	10f

	/* Secondary threads wait for primary to have done partition switch */
20:	lbz	r0,VCORE_IN_GUEST(r5)
	cmpwi	r0,0
	beq	20b
495

496
	/* Set LPCR and RMOR. */
497
10:	ld	r8,VCORE_LPCR(r5)
498
	mtspr	SPRN_LPCR,r8
499 500
	ld	r8,KVM_RMOR(r9)
	mtspr	SPRN_RMOR,r8
501 502
	isync

503 504 505 506 507 508 509 510 511 512
	/* Increment yield count if they have a VPA */
	ld	r3, VCPU_VPA(r4)
	cmpdi	r3, 0
	beq	25f
	lwz	r5, LPPACA_YIELDCOUNT(r3)
	addi	r5, r5, 1
	stw	r5, LPPACA_YIELDCOUNT(r3)
	li	r6, 1
	stb	r6, VCPU_VPA_DIRTY(r4)
25:
513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528
	/* Check if HDEC expires soon */
	mfspr	r3,SPRN_HDEC
	cmpwi	r3,10
	li	r12,BOOK3S_INTERRUPT_HV_DECREMENTER
	mr	r9,r4
	blt	hdec_soon

	/* Save purr/spurr */
	mfspr	r5,SPRN_PURR
	mfspr	r6,SPRN_SPURR
	std	r5,HSTATE_PURR(r13)
	std	r6,HSTATE_SPURR(r13)
	ld	r7,VCPU_PURR(r4)
	ld	r8,VCPU_SPURR(r4)
	mtspr	SPRN_PURR,r7
	mtspr	SPRN_SPURR,r8
529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546
	b	31f

	/*
	 * PPC970 host -> guest partition switch code.
	 * We have to lock against concurrent tlbies,
	 * using native_tlbie_lock to lock against host tlbies
	 * and kvm->arch.tlbie_lock to lock against guest tlbies.
	 * We also have to invalidate the TLB since its
	 * entries aren't tagged with the LPID.
	 */
30:	ld	r9,VCPU_KVM(r4)		/* pointer to struct kvm */

	/* first take native_tlbie_lock */
	.section ".toc","aw"
toc_tlbie_lock:
	.tc	native_tlbie_lock[TC],native_tlbie_lock
	.previous
	ld	r3,toc_tlbie_lock@toc(2)
547
#ifdef __BIG_ENDIAN__
548
	lwz	r8,PACA_LOCK_TOKEN(r13)
549 550 551
#else
	lwz	r8,PACAPACAINDEX(r13)
#endif
552 553 554 555 556 557 558
24:	lwarx	r0,0,r3
	cmpwi	r0,0
	bne	24b
	stwcx.	r8,0,r3
	bne	24b
	isync

559 560
	ld	r5,HSTATE_KVM_VCORE(r13)
	ld	r7,VCORE_LPCR(r5)	/* use vcore->lpcr to store HID4 */
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
	li	r0,0x18f
	rotldi	r0,r0,HID4_LPID5_SH	/* all lpid bits in HID4 = 1 */
	or	r0,r7,r0
	ptesync
	sync
	mtspr	SPRN_HID4,r0		/* switch to reserved LPID */
	isync
	li	r0,0
	stw	r0,0(r3)		/* drop native_tlbie_lock */

	/* invalidate the whole TLB */
	li	r0,256
	mtctr	r0
	li	r6,0
25:	tlbiel	r6
	addi	r6,r6,0x1000
	bdnz	25b
	ptesync

	/* Take the guest's tlbie_lock */
	addi	r3,r9,KVM_TLBIE_LOCK
24:	lwarx	r0,0,r3
	cmpwi	r0,0
	bne	24b
	stwcx.	r8,0,r3
	bne	24b
	isync
	ld	r6,KVM_SDR1(r9)
	mtspr	SPRN_SDR1,r6		/* switch to partition page table */

	/* Set up HID4 with the guest's LPID etc. */
	sync
	mtspr	SPRN_HID4,r7
	isync

	/* drop the guest's tlbie_lock */
	li	r0,0
	stw	r0,0(r3)

	/* Check if HDEC expires soon */
	mfspr	r3,SPRN_HDEC
	cmpwi	r3,10
	li	r12,BOOK3S_INTERRUPT_HV_DECREMENTER
	mr	r9,r4
	blt	hdec_soon

	/* Enable HDEC interrupts */
	mfspr	r0,SPRN_HID0
	li	r3,1
	rldimi	r0,r3, HID0_HDICE_SH, 64-HID0_HDICE_SH-1
	sync
	mtspr	SPRN_HID0,r0
	mfspr	r0,SPRN_HID0
	mfspr	r0,SPRN_HID0
	mfspr	r0,SPRN_HID0
	mfspr	r0,SPRN_HID0
	mfspr	r0,SPRN_HID0
	mfspr	r0,SPRN_HID0
619 620

	/* Load up guest SLB entries */
621
31:	lwz	r5,VCPU_SLB_MAX(r4)
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
	cmpwi	r5,0
	beq	9f
	mtctr	r5
	addi	r6,r4,VCPU_SLB
1:	ld	r8,VCPU_SLB_E(r6)
	ld	r9,VCPU_SLB_V(r6)
	slbmte	r9,r8
	addi	r6,r6,VCPU_SLB_SIZE
	bdnz	1b
9:

	/* Restore state of CTRL run bit; assume 1 on entry */
	lwz	r5,VCPU_CTRL(r4)
	andi.	r5,r5,1
	bne	4f
	mfspr	r6,SPRN_CTRLF
	clrrdi	r6,r6,1
	mtspr	SPRN_CTRLT,r6
4:
	ld	r6, VCPU_CTR(r4)
	lwz	r7, VCPU_XER(r4)

	mtctr	r6
	mtxer	r7

647 648
	ld	r10, VCPU_PC(r4)
	ld	r11, VCPU_MSR(r4)
649
kvmppc_cede_reentry:		/* r4 = vcpu, r13 = paca */
650 651 652
	ld	r6, VCPU_SRR0(r4)
	ld	r7, VCPU_SRR1(r4)

653
	/* r11 = vcpu->arch.msr & ~MSR_HV */
654 655 656 657
	rldicl	r11, r11, 63 - MSR_HV_LG, 1
	rotldi	r11, r11, 1 + MSR_HV_LG
	ori	r11, r11, MSR_ME

658 659
	/* Check if we can deliver an external or decrementer interrupt now */
	ld	r0,VCPU_PENDING_EXC(r4)
660
	lis	r8,(1 << BOOK3S_IRQPRIO_EXTERNAL_LEVEL)@h
661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688
	and	r0,r0,r8
	cmpdi	cr1,r0,0
	andi.	r0,r11,MSR_EE
	beq	cr1,11f
BEGIN_FTR_SECTION
	mfspr	r8,SPRN_LPCR
	ori	r8,r8,LPCR_MER
	mtspr	SPRN_LPCR,r8
	isync
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
	beq	5f
	li	r0,BOOK3S_INTERRUPT_EXTERNAL
12:	mr	r6,r10
	mr	r10,r0
	mr	r7,r11
	li	r11,(MSR_ME << 1) | 1	/* synthesize MSR_SF | MSR_ME */
	rotldi	r11,r11,63
	b	5f
11:	beq	5f
	mfspr	r0,SPRN_DEC
	cmpwi	r0,0
	li	r0,BOOK3S_INTERRUPT_DECREMENTER
	blt	12b

	/* Move SRR0 and SRR1 into the respective regs */
5:	mtspr	SPRN_SRR0, r6
	mtspr	SPRN_SRR1, r7

689 690 691 692 693 694 695
/*
 * Required state:
 * R4 = vcpu
 * R10: value for HSRR0
 * R11: value for HSRR1
 * R13 = PACA
 */
696
fast_guest_return:
697 698
	li	r0,0
	stb	r0,VCPU_CEDED(r4)	/* cancel cede */
699 700 701 702
	mtspr	SPRN_HSRR0,r10
	mtspr	SPRN_HSRR1,r11

	/* Activate guest mode, so faults get handled by KVM */
703
	li	r9, KVM_GUEST_MODE_GUEST_HV
704 705 706 707
	stb	r9, HSTATE_IN_GUEST(r13)

	/* Enter guest */

708 709 710 711
BEGIN_FTR_SECTION
	ld	r5, VCPU_CFAR(r4)
	mtspr	SPRN_CFAR, r5
END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
712 713 714
BEGIN_FTR_SECTION
	ld	r0, VCPU_PPR(r4)
END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
715

716 717 718 719 720
	ld	r5, VCPU_LR(r4)
	lwz	r6, VCPU_CR(r4)
	mtlr	r5
	mtcr	r6

721 722 723 724 725 726 727 728 729 730 731 732 733
	ld	r1, VCPU_GPR(R1)(r4)
	ld	r2, VCPU_GPR(R2)(r4)
	ld	r3, VCPU_GPR(R3)(r4)
	ld	r5, VCPU_GPR(R5)(r4)
	ld	r6, VCPU_GPR(R6)(r4)
	ld	r7, VCPU_GPR(R7)(r4)
	ld	r8, VCPU_GPR(R8)(r4)
	ld	r9, VCPU_GPR(R9)(r4)
	ld	r10, VCPU_GPR(R10)(r4)
	ld	r11, VCPU_GPR(R11)(r4)
	ld	r12, VCPU_GPR(R12)(r4)
	ld	r13, VCPU_GPR(R13)(r4)

734 735 736 737
BEGIN_FTR_SECTION
	mtspr	SPRN_PPR, r0
END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
	ld	r0, VCPU_GPR(R0)(r4)
738
	ld	r4, VCPU_GPR(R4)(r4)
739 740 741 742 743 744 745 746 747 748 749 750 751

	hrfid
	b	.

/******************************************************************************
 *                                                                            *
 *                               Exit code                                    *
 *                                                                            *
 *****************************************************************************/

/*
 * We come here from the first-level interrupt handlers.
 */
752 753
	.globl	kvmppc_interrupt_hv
kvmppc_interrupt_hv:
754 755 756 757 758 759 760 761 762
	/*
	 * Register contents:
	 * R12		= interrupt vector
	 * R13		= PACA
	 * guest CR, R12 saved in shadow VCPU SCRATCH1/0
	 * guest R13 saved in SPRN_SCRATCH0
	 */
	/* abuse host_r2 as third scratch area; we get r2 from PACATOC(r13) */
	std	r9, HSTATE_HOST_R2(r13)
763 764 765 766

	lbz	r9, HSTATE_IN_GUEST(r13)
	cmpwi	r9, KVM_GUEST_MODE_HOST_HV
	beq	kvmppc_bad_host_intr
767 768 769 770 771
#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
	cmpwi	r9, KVM_GUEST_MODE_GUEST
	ld	r9, HSTATE_HOST_R2(r13)
	beq	kvmppc_interrupt_pr
#endif
772 773 774 775
	/* We're now back in the host but in guest MMU context */
	li	r9, KVM_GUEST_MODE_HOST_HV
	stb	r9, HSTATE_IN_GUEST(r13)

776 777 778 779
	ld	r9, HSTATE_KVM_VCPU(r13)

	/* Save registers */

780 781 782 783 784 785 786 787 788
	std	r0, VCPU_GPR(R0)(r9)
	std	r1, VCPU_GPR(R1)(r9)
	std	r2, VCPU_GPR(R2)(r9)
	std	r3, VCPU_GPR(R3)(r9)
	std	r4, VCPU_GPR(R4)(r9)
	std	r5, VCPU_GPR(R5)(r9)
	std	r6, VCPU_GPR(R6)(r9)
	std	r7, VCPU_GPR(R7)(r9)
	std	r8, VCPU_GPR(R8)(r9)
789
	ld	r0, HSTATE_HOST_R2(r13)
790 791 792
	std	r0, VCPU_GPR(R9)(r9)
	std	r10, VCPU_GPR(R10)(r9)
	std	r11, VCPU_GPR(R11)(r9)
793 794
	ld	r3, HSTATE_SCRATCH0(r13)
	lwz	r4, HSTATE_SCRATCH1(r13)
795
	std	r3, VCPU_GPR(R12)(r9)
796
	stw	r4, VCPU_CR(r9)
797 798 799 800
BEGIN_FTR_SECTION
	ld	r3, HSTATE_CFAR(r13)
	std	r3, VCPU_CFAR(r9)
END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
801 802 803 804
BEGIN_FTR_SECTION
	ld	r4, HSTATE_PPR(r13)
	std	r4, VCPU_PPR(r9)
END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823

	/* Restore R1/R2 so we can handle faults */
	ld	r1, HSTATE_HOST_R1(r13)
	ld	r2, PACATOC(r13)

	mfspr	r10, SPRN_SRR0
	mfspr	r11, SPRN_SRR1
	std	r10, VCPU_SRR0(r9)
	std	r11, VCPU_SRR1(r9)
	andi.	r0, r12, 2		/* need to read HSRR0/1? */
	beq	1f
	mfspr	r10, SPRN_HSRR0
	mfspr	r11, SPRN_HSRR1
	clrrdi	r12, r12, 2
1:	std	r10, VCPU_PC(r9)
	std	r11, VCPU_MSR(r9)

	GET_SCRATCH0(r3)
	mflr	r4
824
	std	r3, VCPU_GPR(R13)(r9)
825 826 827 828
	std	r4, VCPU_LR(r9)

	stw	r12,VCPU_TRAP(r9)

829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848
	/* Save HEIR (HV emulation assist reg) in last_inst
	   if this is an HEI (HV emulation interrupt, e40) */
	li	r3,KVM_INST_FETCH_FAILED
BEGIN_FTR_SECTION
	cmpwi	r12,BOOK3S_INTERRUPT_H_EMUL_ASSIST
	bne	11f
	mfspr	r3,SPRN_HEIR
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
11:	stw	r3,VCPU_LAST_INST(r9)

	/* these are volatile across C function calls */
	mfctr	r3
	mfxer	r4
	std	r3, VCPU_CTR(r9)
	stw	r4, VCPU_XER(r9)

BEGIN_FTR_SECTION
	/* If this is a page table miss then see if it's theirs or ours */
	cmpwi	r12, BOOK3S_INTERRUPT_H_DATA_STORAGE
	beq	kvmppc_hdsi
849 850
	cmpwi	r12, BOOK3S_INTERRUPT_H_INST_STORAGE
	beq	kvmppc_hisi
851 852
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)

853 854 855 856 857 858 859
	/* See if this is a leftover HDEC interrupt */
	cmpwi	r12,BOOK3S_INTERRUPT_HV_DECREMENTER
	bne	2f
	mfspr	r3,SPRN_HDEC
	cmpwi	r3,0
	bge	ignore_hdec
2:
860
	/* See if this is an hcall we can handle in real mode */
861 862
	cmpwi	r12,BOOK3S_INTERRUPT_SYSCALL
	beq	hcall_try_real_mode
863

864
	/* Only handle external interrupts here on arch 206 and later */
865
BEGIN_FTR_SECTION
866 867 868 869 870 871 872 873 874 875
	b	ext_interrupt_to_host
END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_206)

	/* External interrupt ? */
	cmpwi	r12, BOOK3S_INTERRUPT_EXTERNAL
	bne+	ext_interrupt_to_host

	/* External interrupt, first check for host_ipi. If this is
	 * set, we know the host wants us out so let's do it now
	 */
876
do_ext_interrupt:
877 878 879
	bl	kvmppc_read_intr
	cmpdi	r3, 0
	bgt	ext_interrupt_to_host
880 881

	/* Allright, looks like an IPI for the guest, we need to set MER */
882 883 884 885 886 887 888 889 890 891 892 893 894
	/* Check if any CPU is heading out to the host, if so head out too */
	ld	r5, HSTATE_KVM_VCORE(r13)
	lwz	r0, VCORE_ENTRY_EXIT(r5)
	cmpwi	r0, 0x100
	bge	ext_interrupt_to_host

	/* See if there is a pending interrupt for the guest */
	mfspr	r8, SPRN_LPCR
	ld	r0, VCPU_PENDING_EXC(r9)
	/* Insert EXTERNAL_LEVEL bit into LPCR at the MER bit position */
	rldicl.	r0, r0, 64 - BOOK3S_IRQPRIO_EXTERNAL_LEVEL, 63
	rldimi	r8, r0, LPCR_MER_SH, 63 - LPCR_MER_SH
	beq	2f
895 896 897 898 899

	/* And if the guest EE is set, we can deliver immediately, else
	 * we return to the guest with MER set
	 */
	andi.	r0, r11, MSR_EE
900 901 902 903 904 905 906 907
	beq	2f
	mtspr	SPRN_SRR0, r10
	mtspr	SPRN_SRR1, r11
	li	r10, BOOK3S_INTERRUPT_EXTERNAL
	li	r11, (MSR_ME << 1) | 1	/* synthesize MSR_SF | MSR_ME */
	rotldi	r11, r11, 63
2:	mr	r4, r9
	mtspr	SPRN_LPCR, r8
908 909 910
	b	fast_guest_return

ext_interrupt_to_host:
911

912
guest_exit_cont:		/* r9 = vcpu, r12 = trap, r13 = paca */
913 914 915 916 917
	/* Save more register state  */
	mfdar	r6
	mfdsisr	r7
	std	r6, VCPU_DAR(r9)
	stw	r7, VCPU_DSISR(r9)
918
BEGIN_FTR_SECTION
919
	/* don't overwrite fault_dar/fault_dsisr if HDSI */
920 921
	cmpwi	r12,BOOK3S_INTERRUPT_H_DATA_STORAGE
	beq	6f
922
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
923
	std	r6, VCPU_FAULT_DAR(r9)
924 925
	stw	r7, VCPU_FAULT_DSISR(r9)

926 927 928 929 930
	/* See if it is a machine check */
	cmpwi	r12, BOOK3S_INTERRUPT_MACHINE_CHECK
	beq	machine_check_realmode
mc_cont:

931
	/* Save guest CTRL register, set runlatch to 1 */
932
6:	mfspr	r6,SPRN_CTRLF
933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960
	stw	r6,VCPU_CTRL(r9)
	andi.	r0,r6,1
	bne	4f
	ori	r6,r6,1
	mtspr	SPRN_CTRLT,r6
4:
	/* Read the guest SLB and save it away */
	lwz	r0,VCPU_SLB_NR(r9)	/* number of entries in SLB */
	mtctr	r0
	li	r6,0
	addi	r7,r9,VCPU_SLB
	li	r5,0
1:	slbmfee	r8,r6
	andis.	r0,r8,SLB_ESID_V@h
	beq	2f
	add	r8,r8,r6		/* put index in */
	slbmfev	r3,r6
	std	r8,VCPU_SLB_E(r7)
	std	r3,VCPU_SLB_V(r7)
	addi	r7,r7,VCPU_SLB_SIZE
	addi	r5,r5,1
2:	addi	r6,r6,1
	bdnz	1b
	stw	r5,VCPU_SLB_MAX(r9)

	/*
	 * Save the guest PURR/SPURR
	 */
961
BEGIN_FTR_SECTION
962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980
	mfspr	r5,SPRN_PURR
	mfspr	r6,SPRN_SPURR
	ld	r7,VCPU_PURR(r9)
	ld	r8,VCPU_SPURR(r9)
	std	r5,VCPU_PURR(r9)
	std	r6,VCPU_SPURR(r9)
	subf	r5,r7,r5
	subf	r6,r8,r6

	/*
	 * Restore host PURR/SPURR and add guest times
	 * so that the time in the guest gets accounted.
	 */
	ld	r3,HSTATE_PURR(r13)
	ld	r4,HSTATE_SPURR(r13)
	add	r3,r3,r5
	add	r4,r4,r6
	mtspr	SPRN_PURR,r3
	mtspr	SPRN_SPURR,r4
981
END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_201)
982 983 984 985 986 987 988

	/* Clear out SLB */
	li	r5,0
	slbmte	r5,r5
	slbia
	ptesync

989
hdec_soon:			/* r9 = vcpu, r12 = trap, r13 = paca */
990 991 992 993 994 995 996 997
BEGIN_FTR_SECTION
	b	32f
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
	/*
	 * POWER7 guest -> host partition switch code.
	 * We don't have to lock against tlbies but we do
	 * have to coordinate the hardware threads.
	 */
998 999 1000 1001 1002 1003 1004 1005 1006
	/* Increment the threads-exiting-guest count in the 0xff00
	   bits of vcore->entry_exit_count */
	lwsync
	ld	r5,HSTATE_KVM_VCORE(r13)
	addi	r6,r5,VCORE_ENTRY_EXIT
41:	lwarx	r3,0,r6
	addi	r0,r3,0x100
	stwcx.	r0,0,r6
	bne	41b
1007
	lwsync
1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020

	/*
	 * At this point we have an interrupt that we have to pass
	 * up to the kernel or qemu; we can't handle it in real mode.
	 * Thus we have to do a partition switch, so we have to
	 * collect the other threads, if we are the first thread
	 * to take an interrupt.  To do this, we set the HDEC to 0,
	 * which causes an HDEC interrupt in all threads within 2ns
	 * because the HDEC register is shared between all 4 threads.
	 * However, we don't need to bother if this is an HDEC
	 * interrupt, since the other threads will already be on their
	 * way here in that case.
	 */
1021 1022 1023 1024
	cmpwi	r3,0x100	/* Are we the first here? */
	bge	43f
	cmpwi	r3,1		/* Are any other threads in the guest? */
	ble	43f
1025 1026 1027 1028 1029
	cmpwi	r12,BOOK3S_INTERRUPT_HV_DECREMENTER
	beq	40f
	li	r0,0
	mtspr	SPRN_HDEC,r0
40:
1030 1031 1032 1033 1034 1035 1036
	/*
	 * Send an IPI to any napping threads, since an HDEC interrupt
	 * doesn't wake CPUs up from nap.
	 */
	lwz	r3,VCORE_NAPPING_THREADS(r5)
	lwz	r4,VCPU_PTID(r9)
	li	r0,1
1037
	sld	r0,r0,r4
1038 1039 1040 1041 1042 1043 1044 1045
	andc.	r3,r3,r0		/* no sense IPI'ing ourselves */
	beq	43f
	mulli	r4,r4,PACA_SIZE		/* get paca for thread 0 */
	subf	r6,r4,r13
42:	andi.	r0,r3,1
	beq	44f
	ld	r8,HSTATE_XICS_PHYS(r6)	/* get thread's XICS reg addr */
	li	r0,IPI_PRIORITY
1046
	li	r7,XICS_MFRR
1047 1048 1049 1050
	stbcix	r0,r7,r8		/* trigger the IPI */
44:	srdi.	r3,r3,1
	addi	r6,r6,PACA_SIZE
	bne	42b
1051 1052

	/* Secondary threads wait for primary to do partition switch */
1053
43:	ld	r4,VCPU_KVM(r9)		/* pointer to struct kvm */
1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073
	ld	r5,HSTATE_KVM_VCORE(r13)
	lwz	r3,VCPU_PTID(r9)
	cmpwi	r3,0
	beq	15f
	HMT_LOW
13:	lbz	r3,VCORE_IN_GUEST(r5)
	cmpwi	r3,0
	bne	13b
	HMT_MEDIUM
	b	16f

	/* Primary thread waits for all the secondaries to exit guest */
15:	lwz	r3,VCORE_ENTRY_EXIT(r5)
	srwi	r0,r3,8
	clrldi	r3,r3,56
	cmpw	r3,r0
	bne	15b
	isync

	/* Primary thread switches back to host partition */
1074 1075 1076 1077 1078 1079 1080 1081
	ld	r6,KVM_HOST_SDR1(r4)
	lwz	r7,KVM_HOST_LPID(r4)
	li	r8,LPID_RSVD		/* switch to reserved LPID */
	mtspr	SPRN_LPID,r8
	ptesync
	mtspr	SPRN_SDR1,r6		/* switch to partition page table */
	mtspr	SPRN_LPID,r7
	isync
1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097

	/* Subtract timebase offset from timebase */
	ld	r8,VCORE_TB_OFFSET(r5)
	cmpdi	r8,0
	beq	17f
	mftb	r6			/* current host timebase */
	subf	r8,r8,r6
	mtspr	SPRN_TBU40,r8		/* update upper 40 bits */
	mftb	r7			/* check if lower 24 bits overflowed */
	clrldi	r6,r6,40
	clrldi	r7,r7,40
	cmpld	r7,r6
	bge	17f
	addis	r8,r8,0x100		/* if so, increment upper 40 bits */
	mtspr	SPRN_TBU40,r8

1098 1099 1100 1101 1102 1103 1104
	/* Reset PCR */
17:	ld	r0, VCORE_PCR(r5)
	cmpdi	r0, 0
	beq	18f
	li	r0, 0
	mtspr	SPRN_PCR, r0
18:
1105
	/* Signal secondary CPUs to continue */
1106
	stb	r0,VCORE_IN_GUEST(r5)
1107 1108 1109
	lis	r8,0x7fff		/* MAX_INT@h */
	mtspr	SPRN_HDEC,r8

1110
16:	ld	r8,KVM_HOST_LPCR(r4)
1111 1112
	mtspr	SPRN_LPCR,r8
	isync
1113 1114 1115 1116 1117 1118 1119 1120 1121 1122
	b	33f

	/*
	 * PPC970 guest -> host partition switch code.
	 * We have to lock against concurrent tlbies, and
	 * we have to flush the whole TLB.
	 */
32:	ld	r4,VCPU_KVM(r9)		/* pointer to struct kvm */

	/* Take the guest's tlbie_lock */
1123
#ifdef __BIG_ENDIAN__
1124
	lwz	r8,PACA_LOCK_TOKEN(r13)
1125 1126 1127
#else
	lwz	r8,PACAPACAINDEX(r13)
#endif
1128 1129 1130 1131 1132 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 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189
	addi	r3,r4,KVM_TLBIE_LOCK
24:	lwarx	r0,0,r3
	cmpwi	r0,0
	bne	24b
	stwcx.	r8,0,r3
	bne	24b
	isync

	ld	r7,KVM_HOST_LPCR(r4)	/* use kvm->arch.host_lpcr for HID4 */
	li	r0,0x18f
	rotldi	r0,r0,HID4_LPID5_SH	/* all lpid bits in HID4 = 1 */
	or	r0,r7,r0
	ptesync
	sync
	mtspr	SPRN_HID4,r0		/* switch to reserved LPID */
	isync
	li	r0,0
	stw	r0,0(r3)		/* drop guest tlbie_lock */

	/* invalidate the whole TLB */
	li	r0,256
	mtctr	r0
	li	r6,0
25:	tlbiel	r6
	addi	r6,r6,0x1000
	bdnz	25b
	ptesync

	/* take native_tlbie_lock */
	ld	r3,toc_tlbie_lock@toc(2)
24:	lwarx	r0,0,r3
	cmpwi	r0,0
	bne	24b
	stwcx.	r8,0,r3
	bne	24b
	isync

	ld	r6,KVM_HOST_SDR1(r4)
	mtspr	SPRN_SDR1,r6		/* switch to host page table */

	/* Set up host HID4 value */
	sync
	mtspr	SPRN_HID4,r7
	isync
	li	r0,0
	stw	r0,0(r3)		/* drop native_tlbie_lock */

	lis	r8,0x7fff		/* MAX_INT@h */
	mtspr	SPRN_HDEC,r8

	/* Disable HDEC interrupts */
	mfspr	r0,SPRN_HID0
	li	r3,0
	rldimi	r0,r3, HID0_HDICE_SH, 64-HID0_HDICE_SH-1
	sync
	mtspr	SPRN_HID0,r0
	mfspr	r0,SPRN_HID0
	mfspr	r0,SPRN_HID0
	mfspr	r0,SPRN_HID0
	mfspr	r0,SPRN_HID0
	mfspr	r0,SPRN_HID0
	mfspr	r0,SPRN_HID0
1190 1191

	/* load host SLB entries */
1192
33:	ld	r8,PACA_SLBSHADOWPTR(r13)
1193 1194 1195 1196 1197 1198 1199 1200 1201 1202

	.rept	SLB_NUM_BOLTED
	ld	r5,SLBSHADOW_SAVEAREA(r8)
	ld	r6,SLBSHADOW_SAVEAREA+8(r8)
	andis.	r7,r5,SLB_ESID_V@h
	beq	1f
	slbmte	r6,r5
1:	addi	r8,r8,16
	.endr

1203 1204 1205 1206 1207 1208 1209
	/* Save DEC */
	mfspr	r5,SPRN_DEC
	mftb	r6
	extsw	r5,r5
	add	r5,r5,r6
	std	r5,VCPU_DEC_EXPIRES(r9)

1210
	/* Save and reset AMR and UAMOR before turning on the MMU */
1211
BEGIN_FTR_SECTION
1212 1213 1214 1215 1216 1217
	mfspr	r5,SPRN_AMR
	mfspr	r6,SPRN_UAMOR
	std	r5,VCPU_AMR(r9)
	std	r6,VCPU_UAMOR(r9)
	li	r6,0
	mtspr	SPRN_AMR,r6
1218
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
1219

1220 1221 1222 1223
	/* Unset guest mode */
	li	r0, KVM_GUEST_MODE_NONE
	stb	r0, HSTATE_IN_GUEST(r13)

1224
	/* Switch DSCR back to host value */
1225
BEGIN_FTR_SECTION
1226 1227
	mfspr	r8, SPRN_DSCR
	ld	r7, HSTATE_DSCR(r13)
1228
	std	r8, VCPU_DSCR(r9)
1229
	mtspr	SPRN_DSCR, r7
1230
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
1231 1232

	/* Save non-volatile GPRs */
1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250
	std	r14, VCPU_GPR(R14)(r9)
	std	r15, VCPU_GPR(R15)(r9)
	std	r16, VCPU_GPR(R16)(r9)
	std	r17, VCPU_GPR(R17)(r9)
	std	r18, VCPU_GPR(R18)(r9)
	std	r19, VCPU_GPR(R19)(r9)
	std	r20, VCPU_GPR(R20)(r9)
	std	r21, VCPU_GPR(R21)(r9)
	std	r22, VCPU_GPR(R22)(r9)
	std	r23, VCPU_GPR(R23)(r9)
	std	r24, VCPU_GPR(R24)(r9)
	std	r25, VCPU_GPR(R25)(r9)
	std	r26, VCPU_GPR(R26)(r9)
	std	r27, VCPU_GPR(R27)(r9)
	std	r28, VCPU_GPR(R28)(r9)
	std	r29, VCPU_GPR(R29)(r9)
	std	r30, VCPU_GPR(R30)(r9)
	std	r31, VCPU_GPR(R31)(r9)
1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261

	/* Save SPRGs */
	mfspr	r3, SPRN_SPRG0
	mfspr	r4, SPRN_SPRG1
	mfspr	r5, SPRN_SPRG2
	mfspr	r6, SPRN_SPRG3
	std	r3, VCPU_SPRG0(r9)
	std	r4, VCPU_SPRG1(r9)
	std	r5, VCPU_SPRG2(r9)
	std	r6, VCPU_SPRG3(r9)

1262 1263
	/* save FP state */
	mr	r3, r9
1264
	bl	kvmppc_save_fp
1265

1266 1267 1268 1269 1270 1271 1272
	/* Increment yield count if they have a VPA */
	ld	r8, VCPU_VPA(r9)	/* do they have a VPA? */
	cmpdi	r8, 0
	beq	25f
	lwz	r3, LPPACA_YIELDCOUNT(r8)
	addi	r3, r3, 1
	stw	r3, LPPACA_YIELDCOUNT(r8)
1273 1274
	li	r3, 1
	stb	r3, VCPU_VPA_DIRTY(r9)
1275 1276 1277
25:
	/* Save PMU registers if requested */
	/* r8 and cr0.eq are live here */
1278 1279 1280 1281
	li	r3, 1
	sldi	r3, r3, 31		/* MMCR0_FC (freeze counters) bit */
	mfspr	r4, SPRN_MMCR0		/* save MMCR0 */
	mtspr	SPRN_MMCR0, r3		/* freeze all counters, disable ints */
1282 1283 1284 1285 1286 1287
	mfspr	r6, SPRN_MMCRA
BEGIN_FTR_SECTION
	/* On P7, clear MMCRA in order to disable SDAR updates */
	li	r7, 0
	mtspr	SPRN_MMCRA, r7
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
1288
	isync
1289 1290 1291 1292 1293 1294 1295
	beq	21f			/* if no VPA, save PMU stuff anyway */
	lbz	r7, LPPACA_PMCINUSE(r8)
	cmpwi	r7, 0			/* did they ask for PMU stuff to be saved? */
	bne	21f
	std	r3, VCPU_MMCR(r9)	/* if not, set saved MMCR0 to FC */
	b	22f
21:	mfspr	r5, SPRN_MMCR1
1296 1297
	mfspr	r7, SPRN_SIAR
	mfspr	r8, SPRN_SDAR
1298 1299 1300
	std	r4, VCPU_MMCR(r9)
	std	r5, VCPU_MMCR + 8(r9)
	std	r6, VCPU_MMCR + 16(r9)
1301 1302
	std	r7, VCPU_SIAR(r9)
	std	r8, VCPU_SDAR(r9)
1303 1304 1305 1306 1307 1308
	mfspr	r3, SPRN_PMC1
	mfspr	r4, SPRN_PMC2
	mfspr	r5, SPRN_PMC3
	mfspr	r6, SPRN_PMC4
	mfspr	r7, SPRN_PMC5
	mfspr	r8, SPRN_PMC6
1309 1310 1311 1312
BEGIN_FTR_SECTION
	mfspr	r10, SPRN_PMC7
	mfspr	r11, SPRN_PMC8
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
1313 1314 1315 1316 1317 1318
	stw	r3, VCPU_PMC(r9)
	stw	r4, VCPU_PMC + 4(r9)
	stw	r5, VCPU_PMC + 8(r9)
	stw	r6, VCPU_PMC + 12(r9)
	stw	r7, VCPU_PMC + 16(r9)
	stw	r8, VCPU_PMC + 20(r9)
1319 1320 1321 1322
BEGIN_FTR_SECTION
	stw	r10, VCPU_PMC + 24(r9)
	stw	r11, VCPU_PMC + 28(r9)
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
1323
22:
1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337
	ld	r0, 112+PPC_LR_STKOFF(r1)
	addi	r1, r1, 112
	mtlr	r0
	blr
secondary_too_late:
	ld	r5,HSTATE_KVM_VCORE(r13)
	HMT_LOW
13:	lbz	r3,VCORE_IN_GUEST(r5)
	cmpwi	r3,0
	bne	13b
	HMT_MEDIUM
	li	r0, KVM_GUEST_MODE_NONE
	stb	r0, HSTATE_IN_GUEST(r13)
	ld	r11,PACA_SLBSHADOWPTR(r13)
1338

1339 1340 1341 1342 1343 1344 1345 1346 1347
	.rept	SLB_NUM_BOLTED
	ld	r5,SLBSHADOW_SAVEAREA(r11)
	ld	r6,SLBSHADOW_SAVEAREA+8(r11)
	andis.	r7,r5,SLB_ESID_V@h
	beq	1f
	slbmte	r6,r5
1:	addi	r11,r11,16
	.endr
	b	22b
1348

1349 1350 1351 1352 1353 1354 1355 1356 1357 1358
/*
 * Check whether an HDSI is an HPTE not found fault or something else.
 * If it is an HPTE not found fault that is due to the guest accessing
 * a page that they have mapped but which we have paged out, then
 * we continue on with the guest exit path.  In all other cases,
 * reflect the HDSI to the guest as a DSI.
 */
kvmppc_hdsi:
	mfspr	r4, SPRN_HDAR
	mfspr	r6, SPRN_HDSISR
1359 1360
	/* HPTE not found fault or protection fault? */
	andis.	r0, r6, (DSISR_NOHPTE | DSISR_PROTFAULT)@h
1361 1362 1363 1364
	beq	1f			/* if not, send it to the guest */
	andi.	r0, r11, MSR_DR		/* data relocation enabled? */
	beq	3f
	clrrdi	r0, r4, 28
1365
	PPC_SLBFEE_DOT(R5, R0)		/* if so, look up SLB */
1366 1367 1368 1369 1370 1371
	bne	1f			/* if no SLB entry found */
4:	std	r4, VCPU_FAULT_DAR(r9)
	stw	r6, VCPU_FAULT_DSISR(r9)

	/* Search the hash table. */
	mr	r3, r9			/* vcpu pointer */
1372
	li	r7, 1			/* data fault */
1373 1374 1375 1376 1377 1378 1379 1380
	bl	.kvmppc_hpte_hv_fault
	ld	r9, HSTATE_KVM_VCPU(r13)
	ld	r10, VCPU_PC(r9)
	ld	r11, VCPU_MSR(r9)
	li	r12, BOOK3S_INTERRUPT_H_DATA_STORAGE
	cmpdi	r3, 0			/* retry the instruction */
	beq	6f
	cmpdi	r3, -1			/* handle in kernel mode */
1381
	beq	guest_exit_cont
1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394
	cmpdi	r3, -2			/* MMIO emulation; need instr word */
	beq	2f

	/* Synthesize a DSI for the guest */
	ld	r4, VCPU_FAULT_DAR(r9)
	mr	r6, r3
1:	mtspr	SPRN_DAR, r4
	mtspr	SPRN_DSISR, r6
	mtspr	SPRN_SRR0, r10
	mtspr	SPRN_SRR1, r11
	li	r10, BOOK3S_INTERRUPT_DATA_STORAGE
	li	r11, (MSR_ME << 1) | 1	/* synthesize MSR_SF | MSR_ME */
	rotldi	r11, r11, 63
1395
fast_interrupt_c_return:
1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425
6:	ld	r7, VCPU_CTR(r9)
	lwz	r8, VCPU_XER(r9)
	mtctr	r7
	mtxer	r8
	mr	r4, r9
	b	fast_guest_return

3:	ld	r5, VCPU_KVM(r9)	/* not relocated, use VRMA */
	ld	r5, KVM_VRMA_SLB_V(r5)
	b	4b

	/* If this is for emulated MMIO, load the instruction word */
2:	li	r8, KVM_INST_FETCH_FAILED	/* In case lwz faults */

	/* Set guest mode to 'jump over instruction' so if lwz faults
	 * we'll just continue at the next IP. */
	li	r0, KVM_GUEST_MODE_SKIP
	stb	r0, HSTATE_IN_GUEST(r13)

	/* Do the access with MSR:DR enabled */
	mfmsr	r3
	ori	r4, r3, MSR_DR		/* Enable paging for data */
	mtmsrd	r4
	lwz	r8, 0(r10)
	mtmsrd	r3

	/* Store the result */
	stw	r8, VCPU_LAST_INST(r9)

	/* Unset guest mode. */
1426
	li	r0, KVM_GUEST_MODE_HOST_HV
1427
	stb	r0, HSTATE_IN_GUEST(r13)
1428
	b	guest_exit_cont
1429

1430 1431 1432 1433 1434 1435 1436 1437 1438 1439
/*
 * Similarly for an HISI, reflect it to the guest as an ISI unless
 * it is an HPTE not found fault for a page that we have paged out.
 */
kvmppc_hisi:
	andis.	r0, r11, SRR1_ISI_NOPT@h
	beq	1f
	andi.	r0, r11, MSR_IR		/* instruction relocation enabled? */
	beq	3f
	clrrdi	r0, r10, 28
1440
	PPC_SLBFEE_DOT(R5, R0)		/* if so, look up SLB */
1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453
	bne	1f			/* if no SLB entry found */
4:
	/* Search the hash table. */
	mr	r3, r9			/* vcpu pointer */
	mr	r4, r10
	mr	r6, r11
	li	r7, 0			/* instruction fault */
	bl	.kvmppc_hpte_hv_fault
	ld	r9, HSTATE_KVM_VCPU(r13)
	ld	r10, VCPU_PC(r9)
	ld	r11, VCPU_MSR(r9)
	li	r12, BOOK3S_INTERRUPT_H_INST_STORAGE
	cmpdi	r3, 0			/* retry the instruction */
1454
	beq	fast_interrupt_c_return
1455
	cmpdi	r3, -1			/* handle in kernel mode */
1456
	beq	guest_exit_cont
1457 1458 1459 1460 1461 1462 1463 1464

	/* Synthesize an ISI for the guest */
	mr	r11, r3
1:	mtspr	SPRN_SRR0, r10
	mtspr	SPRN_SRR1, r11
	li	r10, BOOK3S_INTERRUPT_INST_STORAGE
	li	r11, (MSR_ME << 1) | 1	/* synthesize MSR_SF | MSR_ME */
	rotldi	r11, r11, 63
1465
	b	fast_interrupt_c_return
1466 1467 1468 1469 1470

3:	ld	r6, VCPU_KVM(r9)	/* not relocated, use VRMA */
	ld	r5, KVM_VRMA_SLB_V(r6)
	b	4b

1471 1472 1473 1474 1475 1476 1477 1478
/*
 * Try to handle an hcall in real mode.
 * Returns to the guest if we handle it, or continues on up to
 * the kernel if we can't (i.e. if we don't have a handler for
 * it, or if the handler returns H_TOO_HARD).
 */
	.globl	hcall_try_real_mode
hcall_try_real_mode:
1479
	ld	r3,VCPU_GPR(R3)(r9)
1480
	andi.	r0,r11,MSR_PR
1481 1482
	/* sc 1 from userspace - reflect to guest syscall */
	bne	sc_1_fast_return
1483 1484
	clrrdi	r3,r3,2
	cmpldi	r3,hcall_real_table_end - hcall_real_table
1485
	bge	guest_exit_cont
1486
	LOAD_REG_ADDR(r4, hcall_real_table)
1487
	lwax	r3,r3,r4
1488
	cmpwi	r3,0
1489
	beq	guest_exit_cont
1490 1491 1492
	add	r3,r3,r4
	mtctr	r3
	mr	r3,r9		/* get vcpu pointer */
1493
	ld	r4,VCPU_GPR(R4)(r9)
1494 1495 1496 1497
	bctrl
	cmpdi	r3,H_TOO_HARD
	beq	hcall_real_fallback
	ld	r4,HSTATE_KVM_VCPU(r13)
1498
	std	r3,VCPU_GPR(R3)(r4)
1499 1500 1501 1502
	ld	r10,VCPU_PC(r4)
	ld	r11,VCPU_MSR(r4)
	b	fast_guest_return

1503 1504 1505 1506 1507 1508 1509 1510 1511
sc_1_fast_return:
	mtspr	SPRN_SRR0,r10
	mtspr	SPRN_SRR1,r11
	li	r10, BOOK3S_INTERRUPT_SYSCALL
	li	r11, (MSR_ME << 1) | 1  /* synthesize MSR_SF | MSR_ME */
	rotldi	r11, r11, 63
	mr	r4,r9
	b	fast_guest_return

1512 1513 1514 1515 1516 1517 1518
	/* We've attempted a real mode hcall, but it's punted it back
	 * to userspace.  We need to restore some clobbered volatiles
	 * before resuming the pass-it-to-qemu path */
hcall_real_fallback:
	li	r12,BOOK3S_INTERRUPT_SYSCALL
	ld	r9, HSTATE_KVM_VCPU(r13)

1519
	b	guest_exit_cont
1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530

	.globl	hcall_real_table
hcall_real_table:
	.long	0		/* 0 - unused */
	.long	.kvmppc_h_remove - hcall_real_table
	.long	.kvmppc_h_enter - hcall_real_table
	.long	.kvmppc_h_read - hcall_real_table
	.long	0		/* 0x10 - H_CLEAR_MOD */
	.long	0		/* 0x14 - H_CLEAR_REF */
	.long	.kvmppc_h_protect - hcall_real_table
	.long	0		/* 0x1c - H_GET_TCE */
1531
	.long	.kvmppc_h_put_tce - hcall_real_table
1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547
	.long	0		/* 0x24 - H_SET_SPRG0 */
	.long	.kvmppc_h_set_dabr - hcall_real_table
	.long	0		/* 0x2c */
	.long	0		/* 0x30 */
	.long	0		/* 0x34 */
	.long	0		/* 0x38 */
	.long	0		/* 0x3c */
	.long	0		/* 0x40 */
	.long	0		/* 0x44 */
	.long	0		/* 0x48 */
	.long	0		/* 0x4c */
	.long	0		/* 0x50 */
	.long	0		/* 0x54 */
	.long	0		/* 0x58 */
	.long	0		/* 0x5c */
	.long	0		/* 0x60 */
1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560
#ifdef CONFIG_KVM_XICS
	.long	.kvmppc_rm_h_eoi - hcall_real_table
	.long	.kvmppc_rm_h_cppr - hcall_real_table
	.long	.kvmppc_rm_h_ipi - hcall_real_table
	.long	0		/* 0x70 - H_IPOLL */
	.long	.kvmppc_rm_h_xirr - hcall_real_table
#else
	.long	0		/* 0x64 - H_EOI */
	.long	0		/* 0x68 - H_CPPR */
	.long	0		/* 0x6c - H_IPI */
	.long	0		/* 0x70 - H_IPOLL */
	.long	0		/* 0x74 - H_XIRR */
#endif
1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586
	.long	0		/* 0x78 */
	.long	0		/* 0x7c */
	.long	0		/* 0x80 */
	.long	0		/* 0x84 */
	.long	0		/* 0x88 */
	.long	0		/* 0x8c */
	.long	0		/* 0x90 */
	.long	0		/* 0x94 */
	.long	0		/* 0x98 */
	.long	0		/* 0x9c */
	.long	0		/* 0xa0 */
	.long	0		/* 0xa4 */
	.long	0		/* 0xa8 */
	.long	0		/* 0xac */
	.long	0		/* 0xb0 */
	.long	0		/* 0xb4 */
	.long	0		/* 0xb8 */
	.long	0		/* 0xbc */
	.long	0		/* 0xc0 */
	.long	0		/* 0xc4 */
	.long	0		/* 0xc8 */
	.long	0		/* 0xcc */
	.long	0		/* 0xd0 */
	.long	0		/* 0xd4 */
	.long	0		/* 0xd8 */
	.long	0		/* 0xdc */
1587
	.long	.kvmppc_h_cede - hcall_real_table
1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606
	.long	0		/* 0xe4 */
	.long	0		/* 0xe8 */
	.long	0		/* 0xec */
	.long	0		/* 0xf0 */
	.long	0		/* 0xf4 */
	.long	0		/* 0xf8 */
	.long	0		/* 0xfc */
	.long	0		/* 0x100 */
	.long	0		/* 0x104 */
	.long	0		/* 0x108 */
	.long	0		/* 0x10c */
	.long	0		/* 0x110 */
	.long	0		/* 0x114 */
	.long	0		/* 0x118 */
	.long	0		/* 0x11c */
	.long	0		/* 0x120 */
	.long	.kvmppc_h_bulk_remove - hcall_real_table
hcall_real_table_end:

1607 1608 1609 1610
ignore_hdec:
	mr	r4,r9
	b	fast_guest_return

1611 1612
_GLOBAL(kvmppc_h_set_dabr)
	std	r4,VCPU_DABR(r3)
1613 1614 1615 1616 1617 1618
	/* Work around P7 bug where DABR can get corrupted on mtspr */
1:	mtspr	SPRN_DABR,r4
	mfspr	r5, SPRN_DABR
	cmpd	r4, r5
	bne	1b
	isync
1619 1620 1621
	li	r3,0
	blr

1622 1623 1624 1625 1626 1627 1628 1629
_GLOBAL(kvmppc_h_cede)
	ori	r11,r11,MSR_EE
	std	r11,VCPU_MSR(r3)
	li	r0,1
	stb	r0,VCPU_CEDED(r3)
	sync			/* order setting ceded vs. testing prodded */
	lbz	r5,VCPU_PRODDED(r3)
	cmpwi	r5,0
1630
	bne	kvm_cede_prodded
1631 1632 1633
	li	r0,0		/* set trap to 0 to say hcall is handled */
	stw	r0,VCPU_TRAP(r3)
	li	r0,H_SUCCESS
1634
	std	r0,VCPU_GPR(R3)(r3)
1635
BEGIN_FTR_SECTION
1636
	b	kvm_cede_exit	/* just send it up to host on 970 */
1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652
END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_206)

	/*
	 * Set our bit in the bitmask of napping threads unless all the
	 * other threads are already napping, in which case we send this
	 * up to the host.
	 */
	ld	r5,HSTATE_KVM_VCORE(r13)
	lwz	r6,VCPU_PTID(r3)
	lwz	r8,VCORE_ENTRY_EXIT(r5)
	clrldi	r8,r8,56
	li	r0,1
	sld	r0,r0,r6
	addi	r6,r5,VCORE_NAPPING_THREADS
31:	lwarx	r4,0,r6
	or	r4,r4,r0
1653
	PPC_POPCNTW(R7,R4)
1654
	cmpw	r7,r8
1655
	bge	kvm_cede_exit
1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673
	stwcx.	r4,0,r6
	bne	31b
	li	r0,1
	stb	r0,HSTATE_NAPPING(r13)
	/* order napping_threads update vs testing entry_exit_count */
	lwsync
	mr	r4,r3
	lwz	r7,VCORE_ENTRY_EXIT(r5)
	cmpwi	r7,0x100
	bge	33f		/* another thread already exiting */

/*
 * Although not specifically required by the architecture, POWER7
 * preserves the following registers in nap mode, even if an SMT mode
 * switch occurs: SLB entries, PURR, SPURR, AMOR, UAMOR, AMR, SPRG0-3,
 * DAR, DSISR, DABR, DABRX, DSCR, PMCx, MMCRx, SIAR, SDAR.
 */
	/* Save non-volatile GPRs */
1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691
	std	r14, VCPU_GPR(R14)(r3)
	std	r15, VCPU_GPR(R15)(r3)
	std	r16, VCPU_GPR(R16)(r3)
	std	r17, VCPU_GPR(R17)(r3)
	std	r18, VCPU_GPR(R18)(r3)
	std	r19, VCPU_GPR(R19)(r3)
	std	r20, VCPU_GPR(R20)(r3)
	std	r21, VCPU_GPR(R21)(r3)
	std	r22, VCPU_GPR(R22)(r3)
	std	r23, VCPU_GPR(R23)(r3)
	std	r24, VCPU_GPR(R24)(r3)
	std	r25, VCPU_GPR(R25)(r3)
	std	r26, VCPU_GPR(R26)(r3)
	std	r27, VCPU_GPR(R27)(r3)
	std	r28, VCPU_GPR(R28)(r3)
	std	r29, VCPU_GPR(R29)(r3)
	std	r30, VCPU_GPR(R30)(r3)
	std	r31, VCPU_GPR(R31)(r3)
1692 1693

	/* save FP state */
1694
	bl	kvmppc_save_fp
1695 1696 1697 1698 1699

	/*
	 * Take a nap until a decrementer or external interrupt occurs,
	 * with PECE1 (wake on decr) and PECE0 (wake on external) set in LPCR
	 */
1700 1701
	li	r0,1
	stb	r0,HSTATE_HWTHREAD_REQ(r13)
1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715
	mfspr	r5,SPRN_LPCR
	ori	r5,r5,LPCR_PECE0 | LPCR_PECE1
	mtspr	SPRN_LPCR,r5
	isync
	li	r0, 0
	std	r0, HSTATE_SCRATCH0(r13)
	ptesync
	ld	r0, HSTATE_SCRATCH0(r13)
1:	cmpd	r0, r0
	bne	1b
	nap
	b	.

kvm_end_cede:
1716 1717 1718
	/* get vcpu pointer */
	ld	r4, HSTATE_KVM_VCPU(r13)

1719 1720 1721 1722 1723 1724 1725
	/* Woken by external or decrementer interrupt */
	ld	r1, HSTATE_HOST_R1(r13)

	/* load up FP state */
	bl	kvmppc_load_fp

	/* Load NV GPRS */
1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743
	ld	r14, VCPU_GPR(R14)(r4)
	ld	r15, VCPU_GPR(R15)(r4)
	ld	r16, VCPU_GPR(R16)(r4)
	ld	r17, VCPU_GPR(R17)(r4)
	ld	r18, VCPU_GPR(R18)(r4)
	ld	r19, VCPU_GPR(R19)(r4)
	ld	r20, VCPU_GPR(R20)(r4)
	ld	r21, VCPU_GPR(R21)(r4)
	ld	r22, VCPU_GPR(R22)(r4)
	ld	r23, VCPU_GPR(R23)(r4)
	ld	r24, VCPU_GPR(R24)(r4)
	ld	r25, VCPU_GPR(R25)(r4)
	ld	r26, VCPU_GPR(R26)(r4)
	ld	r27, VCPU_GPR(R27)(r4)
	ld	r28, VCPU_GPR(R28)(r4)
	ld	r29, VCPU_GPR(R29)(r4)
	ld	r30, VCPU_GPR(R30)(r4)
	ld	r31, VCPU_GPR(R31)(r4)
1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757

	/* clear our bit in vcore->napping_threads */
33:	ld	r5,HSTATE_KVM_VCORE(r13)
	lwz	r3,VCPU_PTID(r4)
	li	r0,1
	sld	r0,r0,r3
	addi	r6,r5,VCORE_NAPPING_THREADS
32:	lwarx	r7,0,r6
	andc	r7,r7,r0
	stwcx.	r7,0,r6
	bne	32b
	li	r0,0
	stb	r0,HSTATE_NAPPING(r13)

1758 1759 1760 1761 1762 1763 1764 1765 1766 1767
	/* Check the wake reason in SRR1 to see why we got here */
	mfspr	r3, SPRN_SRR1
	rlwinm	r3, r3, 44-31, 0x7	/* extract wake reason field */
	cmpwi	r3, 4			/* was it an external interrupt? */
	li	r12, BOOK3S_INTERRUPT_EXTERNAL
	mr	r9, r4
	ld	r10, VCPU_PC(r9)
	ld	r11, VCPU_MSR(r9)
	beq	do_ext_interrupt	/* if so */

1768 1769 1770 1771 1772 1773 1774 1775 1776
	/* see if any other thread is already exiting */
	lwz	r0,VCORE_ENTRY_EXIT(r5)
	cmpwi	r0,0x100
	blt	kvmppc_cede_reentry	/* if not go back to guest */

	/* some threads are exiting, so go to the guest exit path */
	b	hcall_real_fallback

	/* cede when already previously prodded case */
1777 1778
kvm_cede_prodded:
	li	r0,0
1779 1780 1781 1782 1783 1784 1785
	stb	r0,VCPU_PRODDED(r3)
	sync			/* order testing prodded vs. clearing ceded */
	stb	r0,VCPU_CEDED(r3)
	li	r3,H_SUCCESS
	blr

	/* we've ceded but we want to give control to the host */
1786
kvm_cede_exit:
1787
	b	hcall_real_fallback
1788

1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803
	/* Try to handle a machine check in real mode */
machine_check_realmode:
	mr	r3, r9		/* get vcpu pointer */
	bl	.kvmppc_realmode_machine_check
	nop
	cmpdi	r3, 0		/* continue exiting from guest? */
	ld	r9, HSTATE_KVM_VCPU(r13)
	li	r12, BOOK3S_INTERRUPT_MACHINE_CHECK
	beq	mc_cont
	/* If not, deliver a machine check.  SRR0/1 are already set */
	li	r10, BOOK3S_INTERRUPT_MACHINE_CHECK
	li	r11, (MSR_ME << 1) | 1	/* synthesize MSR_SF | MSR_ME */
	rotldi	r11, r11, 63
	b	fast_interrupt_c_return

1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816
/*
 * Determine what sort of external interrupt is pending (if any).
 * Returns:
 *	0 if no interrupt is pending
 *	1 if an interrupt is pending that needs to be handled by the host
 *	-1 if there was a guest wakeup IPI (which has now been cleared)
 */
kvmppc_read_intr:
	/* see if a host IPI is pending */
	li	r3, 1
	lbz	r0, HSTATE_HOST_IPI(r13)
	cmpwi	r0, 0
	bne	1f
1817

1818 1819
	/* Now read the interrupt from the ICP */
	ld	r6, HSTATE_XICS_PHYS(r13)
1820
	li	r7, XICS_XIRR
1821 1822 1823 1824
	cmpdi	r6, 0
	beq-	1f
	lwzcix	r0, r6, r7
	rlwinm.	r3, r0, 0, 0xffffff
1825
	sync
1826
	beq	1f			/* if nothing pending in the ICP */
1827

1828 1829 1830 1831 1832 1833 1834 1835 1836
	/* We found something in the ICP...
	 *
	 * If it's not an IPI, stash it in the PACA and return to
	 * the host, we don't (yet) handle directing real external
	 * interrupts directly to the guest
	 */
	cmpwi	r3, XICS_IPI		/* if there is, is it an IPI? */
	li	r3, 1
	bne	42f
1837

1838 1839 1840 1841 1842 1843
	/* It's an IPI, clear the MFRR and EOI it */
	li	r3, 0xff
	li	r8, XICS_MFRR
	stbcix	r3, r6, r8		/* clear the IPI */
	stwcix	r0, r6, r7		/* EOI it */
	sync
1844

1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867
	/* We need to re-check host IPI now in case it got set in the
	 * meantime. If it's clear, we bounce the interrupt to the
	 * guest
	 */
	lbz	r0, HSTATE_HOST_IPI(r13)
	cmpwi	r0, 0
	bne-	43f

	/* OK, it's an IPI for us */
	li	r3, -1
1:	blr

42:	/* It's not an IPI and it's for the host, stash it in the PACA
	 * before exit, it will be picked up by the host ICP driver
	 */
	stw	r0, HSTATE_SAVED_XIRR(r13)
	b	1b

43:	/* We raced with the host, we need to resend that IPI, bummer */
	li	r0, IPI_PRIORITY
	stbcix	r0, r6, r8		/* set the IPI */
	sync
	b	1b
1868

1869 1870 1871
/*
 * Save away FP, VMX and VSX registers.
 * r3 = vcpu pointer
1872 1873
 * N.B. r30 and r31 are volatile across this function,
 * thus it is not callable from C.
1874
 */
1875 1876 1877
kvmppc_save_fp:
	mflr	r30
	mr	r31,r3
1878 1879
	mfmsr	r5
	ori	r8,r5,MSR_FP
1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891
#ifdef CONFIG_ALTIVEC
BEGIN_FTR_SECTION
	oris	r8,r8,MSR_VEC@h
END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
#endif
#ifdef CONFIG_VSX
BEGIN_FTR_SECTION
	oris	r8,r8,MSR_VSX@h
END_FTR_SECTION_IFSET(CPU_FTR_VSX)
#endif
	mtmsrd	r8
	isync
1892 1893
	addi	r3,r3,VCPU_FPRS
	bl	.store_fp_state
1894 1895
#ifdef CONFIG_ALTIVEC
BEGIN_FTR_SECTION
1896 1897
	addi	r3,r31,VCPU_VRS
	bl	.store_vr_state
1898 1899 1900 1901
END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
#endif
	mfspr	r6,SPRN_VRSAVE
	stw	r6,VCPU_VRSAVE(r3)
1902
	mtlr	r30
1903
	mtmsrd	r5
1904 1905 1906 1907 1908 1909
	isync
	blr

/*
 * Load up FP, VMX and VSX registers
 * r4 = vcpu pointer
1910 1911
 * N.B. r30 and r31 are volatile across this function,
 * thus it is not callable from C.
1912 1913
 */
kvmppc_load_fp:
1914 1915
	mflr	r30
	mr	r31,r4
1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929
	mfmsr	r9
	ori	r8,r9,MSR_FP
#ifdef CONFIG_ALTIVEC
BEGIN_FTR_SECTION
	oris	r8,r8,MSR_VEC@h
END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
#endif
#ifdef CONFIG_VSX
BEGIN_FTR_SECTION
	oris	r8,r8,MSR_VSX@h
END_FTR_SECTION_IFSET(CPU_FTR_VSX)
#endif
	mtmsrd	r8
	isync
1930 1931
	addi	r3,r4,VCPU_FPRS
	bl	.load_fp_state
1932 1933
#ifdef CONFIG_ALTIVEC
BEGIN_FTR_SECTION
1934 1935
	addi	r3,r31,VCPU_VRS
	bl	.load_vr_state
1936 1937 1938 1939
END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
#endif
	lwz	r7,VCPU_VRSAVE(r4)
	mtspr	SPRN_VRSAVE,r7
1940 1941
	mtlr	r30
	mr	r4,r31
1942
	blr
1943 1944 1945 1946 1947 1948 1949 1950

/*
 * We come here if we get any exception or interrupt while we are
 * executing host real mode code while in guest MMU context.
 * For now just spin, but we should do something better.
 */
kvmppc_bad_host_intr:
	b	.