arch/powerpc/kvm/book3s_hv_rmhandlers.S

/* SPDX-License-Identifier: GPL-2.0-only */
/*
 *
 * 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>
#include <asm/mmu.h>
#include <asm/page.h>
#include <asm/ptrace.h>
#include <asm/hvcall.h>
#include <asm/asm-offsets.h>
#include <asm/exception-64s.h>
#include <asm/kvm_book3s_asm.h>
#include <asm/book3s/64/mmu-hash.h>
#include <asm/export.h>
#include <asm/tm.h>
#include <asm/opal.h>
#include <asm/xive-regs.h>
#include <asm/thread_info.h>
#include <asm/asm-compat.h>
#include <asm/feature-fixups.h>
#include <asm/cpuidle.h>
#include <asm/ultravisor-api.h>

/* Sign-extend HDEC if not on POWER9 */
#define EXTEND_HDEC(reg)			\
BEGIN_FTR_SECTION;				\
	extsw	reg, reg;			\
END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)

/* Values in HSTATE_NAPPING(r13) */
#define NAPPING_CEDE	1
#define NAPPING_NOVCPU	2
#define NAPPING_UNSPLIT	3

/* Stack frame offsets for kvmppc_hv_entry */
#define SFS			208
#define STACK_SLOT_TRAP		(SFS-4)
#define STACK_SLOT_SHORT_PATH	(SFS-8)
#define STACK_SLOT_TID		(SFS-16)
#define STACK_SLOT_PSSCR	(SFS-24)
#define STACK_SLOT_PID		(SFS-32)
#define STACK_SLOT_IAMR		(SFS-40)
#define STACK_SLOT_CIABR	(SFS-48)
#define STACK_SLOT_DAWR		(SFS-56)
#define STACK_SLOT_DAWRX	(SFS-64)
#define STACK_SLOT_HFSCR	(SFS-72)
#define STACK_SLOT_AMR		(SFS-80)
#define STACK_SLOT_UAMOR	(SFS-88)
/* the following is used by the P9 short path */
#define STACK_SLOT_NVGPRS	(SFS-152)	/* 18 gprs */

/*
 * Call kvmppc_hv_entry in real mode.
 * Must be called with interrupts hard-disabled.
 *
 * Input Registers:
 *
 * LR = return address to continue at after eventually re-enabling MMU
 */
_GLOBAL_TOC(kvmppc_hv_entry_trampoline)
	mflr	r0
	std	r0, PPC_LR_STKOFF(r1)
	stdu	r1, -112(r1)
	mfmsr	r10
	std	r10, HSTATE_HOST_MSR(r13)
	LOAD_REG_ADDR(r5, kvmppc_call_hv_entry)
	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_TO_KERNEL

kvmppc_call_hv_entry:
BEGIN_FTR_SECTION
	/* On P9, do LPCR setting, if necessary */
	ld	r3, HSTATE_SPLIT_MODE(r13)
	cmpdi	r3, 0
	beq	46f
	lwz	r4, KVM_SPLIT_DO_SET(r3)
	cmpwi	r4, 0
	beq	46f
	bl	kvmhv_p9_set_lpcr
	nop
46:
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)

	ld	r4, HSTATE_KVM_VCPU(r13)
	bl	kvmppc_hv_entry

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

BEGIN_FTR_SECTION
	/* Restore host DABR and DABRX */
	ld	r5,HSTATE_DABR(r13)
	li	r6,7
	mtspr	SPRN_DABR,r5
	mtspr	SPRN_DABRX,r6
END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)

	/* Restore SPRG3 */
	ld	r3,PACA_SPRG_VDSO(r13)
	mtspr	SPRN_SPRG_VDSO_WRITE,r3

	/* Reload the host's PMU registers */
	bl	kvmhv_load_host_pmu

	/*
	 * 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

	/* hwthread_req may have got set by cede or no vcpu, so clear it */
	li	r0, 0
	stb	r0, HSTATE_HWTHREAD_REQ(r13)

	/*
	 * For external interrupts we need to call the Linux
	 * handler to process the interrupt. We do that by jumping
	 * to absolute address 0x500 for external interrupts.
	 * 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)

	/* Return the trap number on this thread as the return value */
	mr	r3, r12

	/*
	 * If we came back from the guest via a relocation-on interrupt,
	 * we will be in virtual mode at this point, which makes it a
	 * little easier to get back to the caller.
	 */
	mfmsr	r0
	andi.	r0, r0, MSR_IR		/* in real mode? */
	bne	.Lvirt_return

	/* RFI into the highmem handler */
	mfmsr	r6
	li	r0, MSR_RI
	andc	r6, r6, r0
	mtmsrd	r6, 1			/* Clear RI in MSR */
	mtsrr0	r8
	mtsrr1	r7
	RFI_TO_KERNEL

	/* Virtual-mode return */
.Lvirt_return:
	mtlr	r8
	blr

kvmppc_primary_no_guest:
	/* We handle this much like a ceded vcpu */
	/* put the HDEC into the DEC, since HDEC interrupts don't wake us */
	/* HDEC may be larger than DEC for arch >= v3.00, but since the */
	/* HDEC value came from DEC in the first place, it will fit */
	mfspr	r3, SPRN_HDEC
	mtspr	SPRN_DEC, r3
	/*
	 * Make sure the primary has finished the MMU switch.
	 * We should never get here on a secondary thread, but
	 * check it for robustness' sake.
	 */
	ld	r5, HSTATE_KVM_VCORE(r13)
65:	lbz	r0, VCORE_IN_GUEST(r5)
	cmpwi	r0, 0
	beq	65b
	/* Set LPCR. */
	ld	r8,VCORE_LPCR(r5)
	mtspr	SPRN_LPCR,r8
	isync
	/* set our bit in napping_threads */
	ld	r5, HSTATE_KVM_VCORE(r13)
	lbz	r7, HSTATE_PTID(r13)
	li	r0, 1
	sld	r0, r0, r7
	addi	r6, r5, VCORE_NAPPING_THREADS
1:	lwarx	r3, 0, r6
	or	r3, r3, r0
	stwcx.	r3, 0, r6
	bne	1b
	/* order napping_threads update vs testing entry_exit_map */
	isync
	li	r12, 0
	lwz	r7, VCORE_ENTRY_EXIT(r5)
	cmpwi	r7, 0x100
	bge	kvm_novcpu_exit	/* another thread already exiting */
	li	r3, NAPPING_NOVCPU
	stb	r3, HSTATE_NAPPING(r13)

	li	r3, 0		/* Don't wake on privileged (OS) doorbell */
	b	kvm_do_nap

/*
 * kvm_novcpu_wakeup
 *	Entered from kvm_start_guest if kvm_hstate.napping is set
 *	to NAPPING_NOVCPU
 *		r2 = kernel TOC
 *		r13 = paca
 */
kvm_novcpu_wakeup:
	ld	r1, HSTATE_HOST_R1(r13)
	ld	r5, HSTATE_KVM_VCORE(r13)
	li	r0, 0
	stb	r0, HSTATE_NAPPING(r13)

	/* check the wake reason */
	bl	kvmppc_check_wake_reason

	/*
	 * Restore volatile registers since we could have called
	 * a C routine in kvmppc_check_wake_reason.
	 *	r5 = VCORE
	 */
	ld	r5, HSTATE_KVM_VCORE(r13)

	/* see if any other thread is already exiting */
	lwz	r0, VCORE_ENTRY_EXIT(r5)
	cmpwi	r0, 0x100
	bge	kvm_novcpu_exit

	/* clear our bit in napping_threads */
	lbz	r7, HSTATE_PTID(r13)
	li	r0, 1
	sld	r0, r0, r7
	addi	r6, r5, VCORE_NAPPING_THREADS
4:	lwarx	r7, 0, r6
	andc	r7, r7, r0
	stwcx.	r7, 0, r6
	bne	4b

	/* See if the wake reason means we need to exit */
	cmpdi	r3, 0
	bge	kvm_novcpu_exit

	/* See if our timeslice has expired (HDEC is negative) */
	mfspr	r0, SPRN_HDEC
	EXTEND_HDEC(r0)
	li	r12, BOOK3S_INTERRUPT_HV_DECREMENTER
	cmpdi	r0, 0
	blt	kvm_novcpu_exit

	/* Got an IPI but other vcpus aren't yet exiting, must be a latecomer */
	ld	r4, HSTATE_KVM_VCPU(r13)
	cmpdi	r4, 0
	beq	kvmppc_primary_no_guest

#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
	addi	r3, r4, VCPU_TB_RMENTRY
	bl	kvmhv_start_timing
#endif
	b	kvmppc_got_guest

kvm_novcpu_exit:
#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
	ld	r4, HSTATE_KVM_VCPU(r13)
	cmpdi	r4, 0
	beq	13f
	addi	r3, r4, VCPU_TB_RMEXIT
	bl	kvmhv_accumulate_time
#endif
13:	mr	r3, r12
	stw	r12, STACK_SLOT_TRAP(r1)
	bl	kvmhv_commence_exit
	nop
	b	kvmhv_switch_to_host

/*
 * We come in here when wakened from Linux offline idle code.
 * Relocation is off
 * r3 contains the SRR1 wakeup value, SRR1 is trashed.
 */
_GLOBAL(idle_kvm_start_guest)
	ld	r4,PACAEMERGSP(r13)
	mfcr	r5
	mflr	r0
	std	r1,0(r4)
	std	r5,8(r4)
	std	r0,16(r4)
	subi	r1,r4,STACK_FRAME_OVERHEAD
	SAVE_NVGPRS(r1)

	/*
	 * Could avoid this and pass it through in r3. For now,
	 * code expects it to be in SRR1.
	 */
	mtspr	SPRN_SRR1,r3

	li	r0,0
	stb	r0,PACA_FTRACE_ENABLED(r13)

	li	r0,KVM_HWTHREAD_IN_KVM
	stb	r0,HSTATE_HWTHREAD_STATE(r13)

	/* kvm cede / napping does not come through here */
	lbz	r0,HSTATE_NAPPING(r13)
	twnei	r0,0

	b	1f

kvm_unsplit_wakeup:
	li	r0, 0
	stb	r0, HSTATE_NAPPING(r13)

1:

	/*
	 * 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.)
	 */

	/* Check the wake reason in SRR1 to see why we got here */
	bl	kvmppc_check_wake_reason
	/*
	 * kvmppc_check_wake_reason could invoke a C routine, but we
	 * have no volatile registers to restore when we return.
	 */

	cmpdi	r3, 0
	bge	kvm_no_guest

	/* get vcore pointer, NULL if we have nothing to run */
	ld	r5,HSTATE_KVM_VCORE(r13)
	cmpdi	r5,0
	/* if we have no vcore to run, go back to sleep */
	beq	kvm_no_guest

kvm_secondary_got_guest:

	/* Set HSTATE_DSCR(r13) to something sensible */
	ld	r6, PACA_DSCR_DEFAULT(r13)
	std	r6, HSTATE_DSCR(r13)

	/* On thread 0 of a subcore, set HDEC to max */
	lbz	r4, HSTATE_PTID(r13)
	cmpwi	r4, 0
	bne	63f
	LOAD_REG_ADDR(r6, decrementer_max)
	ld	r6, 0(r6)
	mtspr	SPRN_HDEC, r6
	/* and set per-LPAR registers, if doing dynamic micro-threading */
	ld	r6, HSTATE_SPLIT_MODE(r13)
	cmpdi	r6, 0
	beq	63f
BEGIN_FTR_SECTION
	ld	r0, KVM_SPLIT_RPR(r6)
	mtspr	SPRN_RPR, r0
	ld	r0, KVM_SPLIT_PMMAR(r6)
	mtspr	SPRN_PMMAR, r0
	ld	r0, KVM_SPLIT_LDBAR(r6)
	mtspr	SPRN_LDBAR, r0
	isync
FTR_SECTION_ELSE
	/* On P9 we use the split_info for coordinating LPCR changes */
	lwz	r4, KVM_SPLIT_DO_SET(r6)
	cmpwi	r4, 0
	beq	1f
	mr	r3, r6
	bl	kvmhv_p9_set_lpcr
	nop
1:
ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300)
63:
	/* Order load of vcpu after load of vcore */
	lwsync
	ld	r4, HSTATE_KVM_VCPU(r13)
	bl	kvmppc_hv_entry

	/* Back from the guest, go back to nap */
	/* Clear our vcpu and vcore pointers so we don't come back in early */
	li	r0, 0
	std	r0, HSTATE_KVM_VCPU(r13)
	/*
	 * Once we clear HSTATE_KVM_VCORE(r13), the code in
	 * kvmppc_run_core() is going to assume that all our vcpu
	 * state is visible in memory.  This lwsync makes sure
	 * that that is true.
	 */
	lwsync
	std	r0, HSTATE_KVM_VCORE(r13)

	/*
	 * All secondaries exiting guest will fall through this path.
	 * Before proceeding, just check for HMI interrupt and
	 * invoke opal hmi handler. By now we are sure that the
	 * primary thread on this core/subcore has already made partition
	 * switch/TB resync and we are good to call opal hmi handler.
	 */
	cmpwi	r12, BOOK3S_INTERRUPT_HMI
	bne	kvm_no_guest

	li	r3,0			/* NULL argument */
	bl	hmi_exception_realmode
/*
 * At this point we have finished executing in the guest.
 * We need to wait for hwthread_req to become zero, since
 * we may not turn on the MMU while hwthread_req is non-zero.
 * While waiting we also need to check if we get given a vcpu to run.
 */
kvm_no_guest:
	lbz	r3, HSTATE_HWTHREAD_REQ(r13)
	cmpwi	r3, 0
	bne	53f
	HMT_MEDIUM
	li	r0, KVM_HWTHREAD_IN_KERNEL
	stb	r0, HSTATE_HWTHREAD_STATE(r13)
	/* need to recheck hwthread_req after a barrier, to avoid race */
	sync
	lbz	r3, HSTATE_HWTHREAD_REQ(r13)
	cmpwi	r3, 0
	bne	54f

	/*
	 * Jump to idle_return_gpr_loss, which returns to the
	 * idle_kvm_start_guest caller.
	 */
	li	r3, LPCR_PECE0
	mfspr	r4, SPRN_LPCR
	rlwimi	r4, r3, 0, LPCR_PECE0 | LPCR_PECE1
	mtspr	SPRN_LPCR, r4
	/* set up r3 for return */
	mfspr	r3,SPRN_SRR1
	REST_NVGPRS(r1)
	addi	r1, r1, STACK_FRAME_OVERHEAD
	ld	r0, 16(r1)
	ld	r5, 8(r1)
	ld	r1, 0(r1)
	mtlr	r0
	mtcr	r5
	blr

53:	HMT_LOW
	ld	r5, HSTATE_KVM_VCORE(r13)
	cmpdi	r5, 0
	bne	60f
	ld	r3, HSTATE_SPLIT_MODE(r13)
	cmpdi	r3, 0
	beq	kvm_no_guest
	lwz	r0, KVM_SPLIT_DO_SET(r3)
	cmpwi	r0, 0
	bne	kvmhv_do_set
	lwz	r0, KVM_SPLIT_DO_RESTORE(r3)
	cmpwi	r0, 0
	bne	kvmhv_do_restore
	lbz	r0, KVM_SPLIT_DO_NAP(r3)
	cmpwi	r0, 0
	beq	kvm_no_guest
	HMT_MEDIUM
	b	kvm_unsplit_nap
60:	HMT_MEDIUM
	b	kvm_secondary_got_guest

54:	li	r0, KVM_HWTHREAD_IN_KVM
	stb	r0, HSTATE_HWTHREAD_STATE(r13)
	b	kvm_no_guest

kvmhv_do_set:
	/* Set LPCR, LPIDR etc. on P9 */
	HMT_MEDIUM
	bl	kvmhv_p9_set_lpcr
	nop
	b	kvm_no_guest

kvmhv_do_restore:
	HMT_MEDIUM
	bl	kvmhv_p9_restore_lpcr
	nop
	b	kvm_no_guest

/*
 * Here the primary thread is trying to return the core to
 * whole-core mode, so we need to nap.
 */
kvm_unsplit_nap:
	/*
	 * When secondaries are napping in kvm_unsplit_nap() with
	 * hwthread_req = 1, HMI goes ignored even though subcores are
	 * already exited the guest. Hence HMI keeps waking up secondaries
	 * from nap in a loop and secondaries always go back to nap since
	 * no vcore is assigned to them. This makes impossible for primary
	 * thread to get hold of secondary threads resulting into a soft
	 * lockup in KVM path.
	 *
	 * Let us check if HMI is pending and handle it before we go to nap.
	 */
	cmpwi	r12, BOOK3S_INTERRUPT_HMI
	bne	55f
	li	r3, 0			/* NULL argument */
	bl	hmi_exception_realmode
55:
	/*
	 * Ensure that secondary doesn't nap when it has
	 * its vcore pointer set.
	 */
	sync		/* matches smp_mb() before setting split_info.do_nap */
	ld	r0, HSTATE_KVM_VCORE(r13)
	cmpdi	r0, 0
	bne	kvm_no_guest
	/* clear any pending message */
BEGIN_FTR_SECTION
	lis	r6, (PPC_DBELL_SERVER << (63-36))@h
	PPC_MSGCLR(6)
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
	/* Set kvm_split_mode.napped[tid] = 1 */
	ld	r3, HSTATE_SPLIT_MODE(r13)
	li	r0, 1
	lbz	r4, HSTATE_TID(r13)
	addi	r4, r4, KVM_SPLIT_NAPPED
	stbx	r0, r3, r4
	/* Check the do_nap flag again after setting napped[] */
	sync
	lbz	r0, KVM_SPLIT_DO_NAP(r3)
	cmpwi	r0, 0
	beq	57f
	li	r3, NAPPING_UNSPLIT
	stb	r3, HSTATE_NAPPING(r13)
	li	r3, (LPCR_PECEDH | LPCR_PECE0) >> 4
	mfspr	r5, SPRN_LPCR
	rlwimi	r5, r3, 4, (LPCR_PECEDP | LPCR_PECEDH | LPCR_PECE0 | LPCR_PECE1)
	b	kvm_nap_sequence

57:	li	r0, 0
	stbx	r0, r3, r4
	b	kvm_no_guest

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

.global kvmppc_hv_entry
kvmppc_hv_entry:

	/* Required state:
	 *
	 * R4 = vcpu pointer (or NULL)
	 * MSR = ~IR|DR
	 * R13 = PACA
	 * R1 = host R1
	 * R2 = TOC
	 * all other volatile GPRS = free
	 * Does not preserve non-volatile GPRs or CR fields
	 */
	mflr	r0
	std	r0, PPC_LR_STKOFF(r1)
	stdu	r1, -SFS(r1)

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

	li	r6, KVM_GUEST_MODE_HOST_HV
	stb	r6, HSTATE_IN_GUEST(r13)

#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
	/* Store initial timestamp */
	cmpdi	r4, 0
	beq	1f
	addi	r3, r4, VCPU_TB_RMENTRY
	bl	kvmhv_start_timing
1:
#endif

	ld	r5, HSTATE_KVM_VCORE(r13)
	ld	r9, VCORE_KVM(r5)	/* pointer to struct kvm */

	/*
	 * POWER7/POWER8 host -> guest partition switch code.
	 * We don't have to lock against concurrent tlbies,
	 * but we do have to coordinate across hardware threads.
	 */
	/* Set bit in entry map iff exit map is zero. */
	li	r7, 1
	lbz	r6, HSTATE_PTID(r13)
	sld	r7, r7, r6
	addi	r8, r5, VCORE_ENTRY_EXIT
21:	lwarx	r3, 0, r8
	cmpwi	r3, 0x100		/* any threads starting to exit? */
	bge	secondary_too_late	/* if so we're too late to the party */
	or	r3, r3, r7
	stwcx.	r3, 0, r8
	bne	21b

	/* Primary thread switches to guest partition. */
	cmpwi	r6,0
	bne	10f

	lwz	r7,KVM_LPID(r9)
BEGIN_FTR_SECTION
	ld	r6,KVM_SDR1(r9)
	li	r0,LPID_RSVD		/* switch to reserved LPID */
	mtspr	SPRN_LPID,r0
	ptesync
	mtspr	SPRN_SDR1,r6		/* switch to partition page table */
END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
	mtspr	SPRN_LPID,r7
	isync

	/* See if we need to flush the TLB. */
	mr	r3, r9			/* kvm pointer */
	lhz	r4, PACAPACAINDEX(r13)	/* physical cpu number */
	li	r5, 0			/* nested vcpu pointer */
	bl	kvmppc_check_need_tlb_flush
	nop
	ld	r5, HSTATE_KVM_VCORE(r13)

	/* Add timebase offset onto timebase */
22:	ld	r8,VCORE_TB_OFFSET(r5)
	cmpdi	r8,0
	beq	37f
	std	r8, VCORE_TB_OFFSET_APPL(r5)
	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

	/* 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:

BEGIN_FTR_SECTION
	/* DPDES and VTB are shared between threads */
	ld	r8, VCORE_DPDES(r5)
	ld	r7, VCORE_VTB(r5)
	mtspr	SPRN_DPDES, r8
	mtspr	SPRN_VTB, r7
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)

	/* Mark the subcore state as inside guest */
	bl	kvmppc_subcore_enter_guest
	nop
	ld	r5, HSTATE_KVM_VCORE(r13)
	ld	r4, HSTATE_KVM_VCPU(r13)
	li	r0,1
	stb	r0,VCORE_IN_GUEST(r5)	/* signal secondaries to continue */

	/* Do we have a guest vcpu to run? */
10:	cmpdi	r4, 0
	beq	kvmppc_primary_no_guest
kvmppc_got_guest:
	/* Increment yield count if they have a VPA */
	ld	r3, VCPU_VPA(r4)
	cmpdi	r3, 0
	beq	25f
	li	r6, LPPACA_YIELDCOUNT
	LWZX_BE	r5, r3, r6
	addi	r5, r5, 1
	STWX_BE	r5, r3, r6
	li	r6, 1
	stb	r6, VCPU_VPA_DIRTY(r4)
25:

	/* 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

	/* Save host values of some registers */
BEGIN_FTR_SECTION
	mfspr	r5, SPRN_TIDR
	mfspr	r6, SPRN_PSSCR
	mfspr	r7, SPRN_PID
	std	r5, STACK_SLOT_TID(r1)
	std	r6, STACK_SLOT_PSSCR(r1)
	std	r7, STACK_SLOT_PID(r1)
	mfspr	r5, SPRN_HFSCR
	std	r5, STACK_SLOT_HFSCR(r1)
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
BEGIN_FTR_SECTION
	mfspr	r5, SPRN_CIABR
	mfspr	r6, SPRN_DAWR
	mfspr	r7, SPRN_DAWRX
	mfspr	r8, SPRN_IAMR
	std	r5, STACK_SLOT_CIABR(r1)
	std	r6, STACK_SLOT_DAWR(r1)
	std	r7, STACK_SLOT_DAWRX(r1)
	std	r8, STACK_SLOT_IAMR(r1)
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)

	mfspr	r5, SPRN_AMR
	std	r5, STACK_SLOT_AMR(r1)
	mfspr	r6, SPRN_UAMOR
	std	r6, STACK_SLOT_UAMOR(r1)

BEGIN_FTR_SECTION
	/* Set partition DABR */
	/* Do this before re-enabling PMU to avoid P7 DABR corruption bug */
	lwz	r5,VCPU_DABRX(r4)
	ld	r6,VCPU_DABR(r4)
	mtspr	SPRN_DABRX,r5
	mtspr	SPRN_DABR,r6
	isync
END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)

#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
/*
 * Branch around the call if both CPU_FTR_TM and
 * CPU_FTR_P9_TM_HV_ASSIST are off.
 */
BEGIN_FTR_SECTION
	b	91f
END_FTR_SECTION(CPU_FTR_TM | CPU_FTR_P9_TM_HV_ASSIST, 0)
	/*
	 * NOTE THAT THIS TRASHES ALL NON-VOLATILE REGISTERS (but not CR)
	 */
	mr      r3, r4
	ld      r4, VCPU_MSR(r3)
	li	r5, 0			/* don't preserve non-vol regs */
	bl	kvmppc_restore_tm_hv
	nop
	ld	r4, HSTATE_KVM_VCPU(r13)
91:
#endif

	/* Load guest PMU registers; r4 = vcpu pointer here */
	mr	r3, r4
	bl	kvmhv_load_guest_pmu

	/* Load up FP, VMX and VSX registers */
	ld	r4, HSTATE_KVM_VCPU(r13)
	bl	kvmppc_load_fp

	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)

	/* Switch DSCR to guest value */
	ld	r5, VCPU_DSCR(r4)
	mtspr	SPRN_DSCR, r5

BEGIN_FTR_SECTION
	/* Skip next section on POWER7 */
	b	8f
END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
	/* Load up POWER8-specific registers */
	ld	r5, VCPU_IAMR(r4)
	lwz	r6, VCPU_PSPB(r4)
	ld	r7, VCPU_FSCR(r4)
	mtspr	SPRN_IAMR, r5
	mtspr	SPRN_PSPB, r6
	mtspr	SPRN_FSCR, r7
	/*
	 * Handle broken DAWR case by not writing it. This means we
	 * can still store the DAWR register for migration.
	 */
	LOAD_REG_ADDR(r5, dawr_force_enable)
	lbz	r5, 0(r5)
	cmpdi	r5, 0
	beq	1f
	ld	r5, VCPU_DAWR(r4)
	ld	r6, VCPU_DAWRX(r4)
	mtspr	SPRN_DAWR, r5
	mtspr	SPRN_DAWRX, r6
1:
	ld	r7, VCPU_CIABR(r4)
	ld	r8, VCPU_TAR(r4)
	mtspr	SPRN_CIABR, r7
	mtspr	SPRN_TAR, r8
	ld	r5, VCPU_IC(r4)
	ld	r8, VCPU_EBBHR(r4)
	mtspr	SPRN_IC, r5
	mtspr	SPRN_EBBHR, r8
	ld	r5, VCPU_EBBRR(r4)
	ld	r6, VCPU_BESCR(r4)
	lwz	r7, VCPU_GUEST_PID(r4)
	ld	r8, VCPU_WORT(r4)
	mtspr	SPRN_EBBRR, r5
	mtspr	SPRN_BESCR, r6
	mtspr	SPRN_PID, r7
	mtspr	SPRN_WORT, r8
BEGIN_FTR_SECTION
	/* POWER8-only registers */
	ld	r5, VCPU_TCSCR(r4)
	ld	r6, VCPU_ACOP(r4)
	ld	r7, VCPU_CSIGR(r4)
	ld	r8, VCPU_TACR(r4)
	mtspr	SPRN_TCSCR, r5
	mtspr	SPRN_ACOP, r6
	mtspr	SPRN_CSIGR, r7
	mtspr	SPRN_TACR, r8
	nop
FTR_SECTION_ELSE
	/* POWER9-only registers */
	ld	r5, VCPU_TID(r4)
	ld	r6, VCPU_PSSCR(r4)
	lbz	r8, HSTATE_FAKE_SUSPEND(r13)
	oris	r6, r6, PSSCR_EC@h	/* This makes stop trap to HV */
	rldimi	r6, r8, PSSCR_FAKE_SUSPEND_LG, 63 - PSSCR_FAKE_SUSPEND_LG
	ld	r7, VCPU_HFSCR(r4)
	mtspr	SPRN_TIDR, r5
	mtspr	SPRN_PSSCR, r6
	mtspr	SPRN_HFSCR, r7
ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300)
8:

	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

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

	/* 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

	/* 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:
	/* Secondary threads wait for primary to have done partition switch */
	ld	r5, HSTATE_KVM_VCORE(r13)
	lbz	r6, HSTATE_PTID(r13)
	cmpwi	r6, 0
	beq	21f
	lbz	r0, VCORE_IN_GUEST(r5)
	cmpwi	r0, 0
	bne	21f
	HMT_LOW
20:	lwz	r3, VCORE_ENTRY_EXIT(r5)
	cmpwi	r3, 0x100
	bge	no_switch_exit
	lbz	r0, VCORE_IN_GUEST(r5)
	cmpwi	r0, 0
	beq	20b
	HMT_MEDIUM
21:
	/* Set LPCR. */
	ld	r8,VCORE_LPCR(r5)
	mtspr	SPRN_LPCR,r8
	isync

	/*
	 * Set the decrementer to the guest decrementer.
	 */
	ld	r8,VCPU_DEC_EXPIRES(r4)
	/* r8 is a host timebase value here, convert to guest TB */
	ld	r5,HSTATE_KVM_VCORE(r13)
	ld	r6,VCORE_TB_OFFSET_APPL(r5)
	add	r8,r8,r6
	mftb	r7
	subf	r3,r7,r8
	mtspr	SPRN_DEC,r3

	/* Check if HDEC expires soon */
	mfspr	r3, SPRN_HDEC
	EXTEND_HDEC(r3)
	cmpdi	r3, 512		/* 1 microsecond */
	blt	hdec_soon

	/* For hash guest, clear out and reload the SLB */
	ld	r6, VCPU_KVM(r4)
	lbz	r0, KVM_RADIX(r6)
	cmpwi	r0, 0
	bne	9f
	li	r6, 0
	slbmte	r6, r6
	slbia
	ptesync

	/* Load up guest SLB entries (N.B. slb_max will be 0 for radix) */
	lwz	r5,VCPU_SLB_MAX(r4)
	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:

#ifdef CONFIG_KVM_XICS
	/* We are entering the guest on that thread, push VCPU to XIVE */
	ld	r11, VCPU_XIVE_SAVED_STATE(r4)
	li	r9, TM_QW1_OS
	lwz	r8, VCPU_XIVE_CAM_WORD(r4)
	cmpwi	r8, 0
	beq	no_xive
	li	r7, TM_QW1_OS + TM_WORD2
	mfmsr	r0
	andi.	r0, r0, MSR_DR		/* in real mode? */
	beq	2f
	ld	r10, HSTATE_XIVE_TIMA_VIRT(r13)
	cmpldi	cr1, r10, 0
	beq     cr1, no_xive
	eieio
	stdx	r11,r9,r10
	stwx	r8,r7,r10
	b	3f
2:	ld	r10, HSTATE_XIVE_TIMA_PHYS(r13)
	cmpldi	cr1, r10, 0
	beq	cr1, no_xive
	eieio
	stdcix	r11,r9,r10
	stwcix	r8,r7,r10
3:	li	r9, 1
	stb	r9, VCPU_XIVE_PUSHED(r4)
	eieio

	/*
	 * We clear the irq_pending flag. There is a small chance of a
	 * race vs. the escalation interrupt happening on another
	 * processor setting it again, but the only consequence is to
	 * cause a spurrious wakeup on the next H_CEDE which is not an
	 * issue.
	 */
	li	r0,0
	stb	r0, VCPU_IRQ_PENDING(r4)

	/*
	 * In single escalation mode, if the escalation interrupt is
	 * on, we mask it.
	 */
	lbz	r0, VCPU_XIVE_ESC_ON(r4)
	cmpwi	cr1, r0,0
	beq	cr1, 1f
	li	r9, XIVE_ESB_SET_PQ_01
	beq	4f			/* in real mode? */
	ld	r10, VCPU_XIVE_ESC_VADDR(r4)
	ldx	r0, r10, r9
	b	5f
4:	ld	r10, VCPU_XIVE_ESC_RADDR(r4)
	ldcix	r0, r10, r9
5:	sync

	/* We have a possible subtle race here: The escalation interrupt might
	 * have fired and be on its way to the host queue while we mask it,
	 * and if we unmask it early enough (re-cede right away), there is
	 * a theorical possibility that it fires again, thus landing in the
	 * target queue more than once which is a big no-no.
	 *
	 * Fortunately, solving this is rather easy. If the above load setting
	 * PQ to 01 returns a previous value where P is set, then we know the
	 * escalation interrupt is somewhere on its way to the host. In that
	 * case we simply don't clear the xive_esc_on flag below. It will be
	 * eventually cleared by the handler for the escalation interrupt.
	 *
	 * Then, when doing a cede, we check that flag again before re-enabling
	 * the escalation interrupt, and if set, we abort the cede.
	 */
	andi.	r0, r0, XIVE_ESB_VAL_P
	bne-	1f

	/* Now P is 0, we can clear the flag */
	li	r0, 0
	stb	r0, VCPU_XIVE_ESC_ON(r4)
1:
no_xive:
#endif /* CONFIG_KVM_XICS */

	li	r0, 0
	stw	r0, STACK_SLOT_SHORT_PATH(r1)

deliver_guest_interrupt:	/* r4 = vcpu, r13 = paca */
	/* Check if we can deliver an external or decrementer interrupt now */
	ld	r0, VCPU_PENDING_EXC(r4)
BEGIN_FTR_SECTION
	/* On POWER9, also check for emulated doorbell interrupt */
	lbz	r3, VCPU_DBELL_REQ(r4)
	or	r0, r0, r3
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
	cmpdi	r0, 0
	beq	71f
	mr	r3, r4
	bl	kvmppc_guest_entry_inject_int
	ld	r4, HSTATE_KVM_VCPU(r13)
71:
	ld	r6, VCPU_SRR0(r4)
	ld	r7, VCPU_SRR1(r4)
	mtspr	SPRN_SRR0, r6
	mtspr	SPRN_SRR1, r7

fast_guest_entry_c:
	ld	r10, VCPU_PC(r4)
	ld	r11, VCPU_MSR(r4)
	/* r11 = vcpu->arch.msr & ~MSR_HV */
	rldicl	r11, r11, 63 - MSR_HV_LG, 1
	rotldi	r11, r11, 1 + MSR_HV_LG
	ori	r11, r11, MSR_ME

	ld	r6, VCPU_CTR(r4)
	ld	r7, VCPU_XER(r4)
	mtctr	r6
	mtxer	r7

/*
 * Required state:
 * R4 = vcpu
 * R10: value for HSRR0
 * R11: value for HSRR1
 * R13 = PACA
 */
fast_guest_return:
	li	r0,0
	stb	r0,VCPU_CEDED(r4)	/* cancel cede */
	mtspr	SPRN_HSRR0,r10
	mtspr	SPRN_HSRR1,r11

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

#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
	/* Accumulate timing */
	addi	r3, r4, VCPU_TB_GUEST
	bl	kvmhv_accumulate_time
#endif

	/* Enter guest */

BEGIN_FTR_SECTION
	ld	r5, VCPU_CFAR(r4)
	mtspr	SPRN_CFAR, r5
END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
BEGIN_FTR_SECTION
	ld	r0, VCPU_PPR(r4)
END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)

	ld	r5, VCPU_LR(r4)
	mtlr	r5

	ld	r1, VCPU_GPR(R1)(r4)
	ld	r5, VCPU_GPR(R5)(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)

BEGIN_FTR_SECTION
	mtspr	SPRN_PPR, r0
END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)

/* Move canary into DSISR to check for later */
BEGIN_FTR_SECTION
	li	r0, 0x7fff
	mtspr	SPRN_HDSISR, r0
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)

	ld	r6, VCPU_KVM(r4)
	lbz	r7, KVM_SECURE_GUEST(r6)
	cmpdi	r7, 0
	ld	r6, VCPU_GPR(R6)(r4)
	ld	r7, VCPU_GPR(R7)(r4)
	bne	ret_to_ultra

	lwz	r0, VCPU_CR(r4)
	mtcr	r0

	ld	r0, VCPU_GPR(R0)(r4)
	ld	r2, VCPU_GPR(R2)(r4)
	ld	r3, VCPU_GPR(R3)(r4)
	ld	r4, VCPU_GPR(R4)(r4)
	HRFI_TO_GUEST
	b	.
/*
 * Use UV_RETURN ultracall to return control back to the Ultravisor after
 * processing an hypercall or interrupt that was forwarded (a.k.a. reflected)
 * to the Hypervisor.
 *
 * All registers have already been loaded, except:
 *   R0 = hcall result
 *   R2 = SRR1, so UV can detect a synthesized interrupt (if any)
 *   R3 = UV_RETURN
 */
ret_to_ultra:
	lwz	r0, VCPU_CR(r4)
	mtcr	r0

	ld	r0, VCPU_GPR(R3)(r4)
	mfspr	r2, SPRN_SRR1
	li	r3, 0
	ori	r3, r3, UV_RETURN
	ld	r4, VCPU_GPR(R4)(r4)
	sc	2

/*
 * Enter the guest on a P9 or later system where we have exactly
 * one vcpu per vcore and we don't need to go to real mode
 * (which implies that host and guest are both using radix MMU mode).
 * r3 = vcpu pointer
 * Most SPRs and all the VSRs have been loaded already.
 */
_GLOBAL(__kvmhv_vcpu_entry_p9)
EXPORT_SYMBOL_GPL(__kvmhv_vcpu_entry_p9)
	mflr	r0
	std	r0, PPC_LR_STKOFF(r1)
	stdu	r1, -SFS(r1)

	li	r0, 1
	stw	r0, STACK_SLOT_SHORT_PATH(r1)

	std	r3, HSTATE_KVM_VCPU(r13)
	mfcr	r4
	stw	r4, SFS+8(r1)

	std	r1, HSTATE_HOST_R1(r13)

	reg = 14
	.rept	18
	std	reg, STACK_SLOT_NVGPRS + ((reg - 14) * 8)(r1)
	reg = reg + 1
	.endr

	reg = 14
	.rept	18
	ld	reg, __VCPU_GPR(reg)(r3)
	reg = reg + 1
	.endr

	mfmsr	r10
	std	r10, HSTATE_HOST_MSR(r13)

	mr	r4, r3
	b	fast_guest_entry_c
guest_exit_short_path:

	li	r0, KVM_GUEST_MODE_NONE
	stb	r0, HSTATE_IN_GUEST(r13)

	reg = 14
	.rept	18
	std	reg, __VCPU_GPR(reg)(r9)
	reg = reg + 1
	.endr

	reg = 14
	.rept	18
	ld	reg, STACK_SLOT_NVGPRS + ((reg - 14) * 8)(r1)
	reg = reg + 1
	.endr

	lwz	r4, SFS+8(r1)
	mtcr	r4

	mr	r3, r12		/* trap number */

	addi	r1, r1, SFS
	ld	r0, PPC_LR_STKOFF(r1)
	mtlr	r0

	/* If we are in real mode, do a rfid to get back to the caller */
	mfmsr	r4
	andi.	r5, r4, MSR_IR
	bnelr
	rldicl	r5, r4, 64 - MSR_TS_S_LG, 62	/* extract TS field */
	mtspr	SPRN_SRR0, r0
	ld	r10, HSTATE_HOST_MSR(r13)
	rldimi	r10, r5, MSR_TS_S_LG, 63 - MSR_TS_T_LG
	mtspr	SPRN_SRR1, r10
	RFI_TO_KERNEL
	b	.

secondary_too_late:
	li	r12, 0
	stw	r12, STACK_SLOT_TRAP(r1)
	cmpdi	r4, 0
	beq	11f
	stw	r12, VCPU_TRAP(r4)
#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
	addi	r3, r4, VCPU_TB_RMEXIT
	bl	kvmhv_accumulate_time
#endif
11:	b	kvmhv_switch_to_host

no_switch_exit:
	HMT_MEDIUM
	li	r12, 0
	b	12f
hdec_soon:
	li	r12, BOOK3S_INTERRUPT_HV_DECREMENTER
12:	stw	r12, VCPU_TRAP(r4)
	mr	r9, r4
#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
	addi	r3, r4, VCPU_TB_RMEXIT
	bl	kvmhv_accumulate_time
#endif
	b	guest_bypass

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

/*
 * We come here from the first-level interrupt handlers.
 */
	.globl	kvmppc_interrupt_hv
kvmppc_interrupt_hv:
	/*
	 * Register contents:
	 * R12		= (guest CR << 32) | interrupt vector
	 * R13		= PACA
	 * guest R12 saved in shadow VCPU SCRATCH0
	 * guest CTR saved in shadow VCPU SCRATCH1 if RELOCATABLE
	 * guest R13 saved in SPRN_SCRATCH0
	 */
	std	r9, HSTATE_SCRATCH2(r13)
	lbz	r9, HSTATE_IN_GUEST(r13)
	cmpwi	r9, KVM_GUEST_MODE_HOST_HV
	beq	kvmppc_bad_host_intr
#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
	cmpwi	r9, KVM_GUEST_MODE_GUEST
	ld	r9, HSTATE_SCRATCH2(r13)
	beq	kvmppc_interrupt_pr
#endif
	/* 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)

	ld	r9, HSTATE_KVM_VCPU(r13)

	/* Save registers */

	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)
	ld	r0, HSTATE_SCRATCH2(r13)
	std	r0, VCPU_GPR(R9)(r9)
	std	r10, VCPU_GPR(R10)(r9)
	std	r11, VCPU_GPR(R11)(r9)
	ld	r3, HSTATE_SCRATCH0(r13)
	std	r3, VCPU_GPR(R12)(r9)
	/* CR is in the high half of r12 */
	srdi	r4, r12, 32
	std	r4, VCPU_CR(r9)
BEGIN_FTR_SECTION
	ld	r3, HSTATE_CFAR(r13)
	std	r3, VCPU_CFAR(r9)
END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
BEGIN_FTR_SECTION
	ld	r4, HSTATE_PPR(r13)
	std	r4, VCPU_PPR(r9)
END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)

	/* 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)
	/* trap is in the low half of r12, clear CR from the high half */
	clrldi	r12, r12, 32
	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
	std	r3, VCPU_GPR(R13)(r9)
	std	r4, VCPU_LR(r9)

	stw	r12,VCPU_TRAP(r9)

	/*
	 * Now that we have saved away SRR0/1 and HSRR0/1,
	 * interrupts are recoverable in principle, so set MSR_RI.
	 * This becomes important for relocation-on interrupts from
	 * the guest, which we can get in radix mode on POWER9.
	 */
	li	r0, MSR_RI
	mtmsrd	r0, 1

#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
	addi	r3, r9, VCPU_TB_RMINTR
	mr	r4, r9
	bl	kvmhv_accumulate_time
	ld	r5, VCPU_GPR(R5)(r9)
	ld	r6, VCPU_GPR(R6)(r9)
	ld	r7, VCPU_GPR(R7)(r9)
	ld	r8, VCPU_GPR(R8)(r9)
#endif

	/* Save HEIR (HV emulation assist reg) in emul_inst
	   if this is an HEI (HV emulation interrupt, e40) */
	li	r3,KVM_INST_FETCH_FAILED
	stw	r3,VCPU_LAST_INST(r9)
	cmpwi	r12,BOOK3S_INTERRUPT_H_EMUL_ASSIST
	bne	11f
	mfspr	r3,SPRN_HEIR
11:	stw	r3,VCPU_HEIR(r9)

	/* these are volatile across C function calls */
#ifdef CONFIG_RELOCATABLE
	ld	r3, HSTATE_SCRATCH1(r13)
	mtctr	r3
#else
	mfctr	r3
#endif
	mfxer	r4
	std	r3, VCPU_CTR(r9)
	std	r4, VCPU_XER(r9)

	/* Save more register state  */
	mfdar	r3
	mfdsisr	r4
	std	r3, VCPU_DAR(r9)
	stw	r4, VCPU_DSISR(r9)

	/* 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
	std	r3, VCPU_FAULT_DAR(r9)
	stw	r4, VCPU_FAULT_DSISR(r9)
	cmpwi	r12, BOOK3S_INTERRUPT_H_INST_STORAGE
	beq	kvmppc_hisi

#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
	/* For softpatch interrupt, go off and do TM instruction emulation */
	cmpwi	r12, BOOK3S_INTERRUPT_HV_SOFTPATCH
	beq	kvmppc_tm_emul
#endif

	/* See if this is a leftover HDEC interrupt */
	cmpwi	r12,BOOK3S_INTERRUPT_HV_DECREMENTER
	bne	2f
	mfspr	r3,SPRN_HDEC
	EXTEND_HDEC(r3)
	cmpdi	r3,0
	mr	r4,r9
	bge	fast_guest_return
2:
	/* See if this is an hcall we can handle in real mode */
	cmpwi	r12,BOOK3S_INTERRUPT_SYSCALL
	beq	hcall_try_real_mode

	/* Hypervisor doorbell - exit only if host IPI flag set */
	cmpwi	r12, BOOK3S_INTERRUPT_H_DOORBELL
	bne	3f
BEGIN_FTR_SECTION
	PPC_MSGSYNC
	lwsync
	/* always exit if we're running a nested guest */
	ld	r0, VCPU_NESTED(r9)
	cmpdi	r0, 0
	bne	guest_exit_cont
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
	lbz	r0, HSTATE_HOST_IPI(r13)
	cmpwi	r0, 0
	beq	maybe_reenter_guest
	b	guest_exit_cont
3:
	/* If it's a hypervisor facility unavailable interrupt, save HFSCR */
	cmpwi	r12, BOOK3S_INTERRUPT_H_FAC_UNAVAIL
	bne	14f
	mfspr	r3, SPRN_HFSCR
	std	r3, VCPU_HFSCR(r9)
	b	guest_exit_cont
14:
	/* External interrupt ? */
	cmpwi	r12, BOOK3S_INTERRUPT_EXTERNAL
	beq	kvmppc_guest_external
	/* See if it is a machine check */
	cmpwi	r12, BOOK3S_INTERRUPT_MACHINE_CHECK
	beq	machine_check_realmode
	/* Or a hypervisor maintenance interrupt */
	cmpwi	r12, BOOK3S_INTERRUPT_HMI
	beq	hmi_realmode

guest_exit_cont:		/* r9 = vcpu, r12 = trap, r13 = paca */

#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
	addi	r3, r9, VCPU_TB_RMEXIT
	mr	r4, r9
	bl	kvmhv_accumulate_time
#endif
#ifdef CONFIG_KVM_XICS
	/* We are exiting, pull the VP from the XIVE */
	lbz	r0, VCPU_XIVE_PUSHED(r9)
	cmpwi	cr0, r0, 0
	beq	1f
	li	r7, TM_SPC_PULL_OS_CTX
	li	r6, TM_QW1_OS
	mfmsr	r0
	andi.	r0, r0, MSR_DR		/* in real mode? */
	beq	2f
	ld	r10, HSTATE_XIVE_TIMA_VIRT(r13)
	cmpldi	cr0, r10, 0
	beq	1f
	/* First load to pull the context, we ignore the value */
	eieio
	lwzx	r11, r7, r10
	/* Second load to recover the context state (Words 0 and 1) */
	ldx	r11, r6, r10
	b	3f
2:	ld	r10, HSTATE_XIVE_TIMA_PHYS(r13)
	cmpldi	cr0, r10, 0
	beq	1f
	/* First load to pull the context, we ignore the value */
	eieio
	lwzcix	r11, r7, r10
	/* Second load to recover the context state (Words 0 and 1) */
	ldcix	r11, r6, r10
3:	std	r11, VCPU_XIVE_SAVED_STATE(r9)
	/* Fixup some of the state for the next load */
	li	r10, 0
	li	r0, 0xff
	stb	r10, VCPU_XIVE_PUSHED(r9)
	stb	r10, (VCPU_XIVE_SAVED_STATE+3)(r9)
	stb	r0, (VCPU_XIVE_SAVED_STATE+4)(r9)
	eieio
1:
#endif /* CONFIG_KVM_XICS */

	/* If we came in through the P9 short path, go back out to C now */
	lwz	r0, STACK_SLOT_SHORT_PATH(r1)
	cmpwi	r0, 0
	bne	guest_exit_short_path

	/* For hash guest, read the guest SLB and save it away */
	ld	r5, VCPU_KVM(r9)
	lbz	r0, KVM_RADIX(r5)
	li	r5, 0
	cmpwi	r0, 0
	bne	3f			/* for radix, save 0 entries */
	lwz	r0,VCPU_SLB_NR(r9)	/* number of entries in SLB */
	mtctr	r0
	li	r6,0
	addi	r7,r9,VCPU_SLB
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
	/* Finally clear out the SLB */
	li	r0,0
	slbmte	r0,r0
	slbia
	ptesync
3:	stw	r5,VCPU_SLB_MAX(r9)

	/* load host SLB entries */
BEGIN_MMU_FTR_SECTION
	b	0f
END_MMU_FTR_SECTION_IFSET(MMU_FTR_TYPE_RADIX)
	ld	r8,PACA_SLBSHADOWPTR(r13)

	.rept	SLB_NUM_BOLTED
	li	r3, SLBSHADOW_SAVEAREA
	LDX_BE	r5, r8, r3
	addi	r3, r3, 8
	LDX_BE	r6, r8, r3
	andis.	r7,r5,SLB_ESID_V@h
	beq	1f
	slbmte	r6,r5
1:	addi	r8,r8,16
	.endr
0:

guest_bypass:
	stw	r12, STACK_SLOT_TRAP(r1)

	/* Save DEC */
	/* Do this before kvmhv_commence_exit so we know TB is guest TB */
	ld	r3, HSTATE_KVM_VCORE(r13)
	mfspr	r5,SPRN_DEC
	mftb	r6
	/* On P9, if the guest has large decr enabled, don't sign extend */
BEGIN_FTR_SECTION
	ld	r4, VCORE_LPCR(r3)
	andis.	r4, r4, LPCR_LD@h
	bne	16f
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
	extsw	r5,r5
16:	add	r5,r5,r6
	/* r5 is a guest timebase value here, convert to host TB */
	ld	r4,VCORE_TB_OFFSET_APPL(r3)
	subf	r5,r4,r5
	std	r5,VCPU_DEC_EXPIRES(r9)

	/* Increment exit count, poke other threads to exit */
	mr 	r3, r12
	bl	kvmhv_commence_exit
	nop
	ld	r9, HSTATE_KVM_VCPU(r13)

	/* Stop others sending VCPU interrupts to this physical CPU */
	li	r0, -1
	stw	r0, VCPU_CPU(r9)
	stw	r0, VCPU_THREAD_CPU(r9)

	/* Save guest CTRL register, set runlatch to 1 */
	mfspr	r6,SPRN_CTRLF
	stw	r6,VCPU_CTRL(r9)
	andi.	r0,r6,1
	bne	4f
	ori	r6,r6,1
	mtspr	SPRN_CTRLT,r6
4:
	/*
	 * Save the guest PURR/SPURR
	 */
	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

BEGIN_FTR_SECTION
	b	8f
END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
	/* Save POWER8-specific registers */
	mfspr	r5, SPRN_IAMR
	mfspr	r6, SPRN_PSPB
	mfspr	r7, SPRN_FSCR
	std	r5, VCPU_IAMR(r9)
	stw	r6, VCPU_PSPB(r9)
	std	r7, VCPU_FSCR(r9)
	mfspr	r5, SPRN_IC
	mfspr	r7, SPRN_TAR
	std	r5, VCPU_IC(r9)
	std	r7, VCPU_TAR(r9)
	mfspr	r8, SPRN_EBBHR
	std	r8, VCPU_EBBHR(r9)
	mfspr	r5, SPRN_EBBRR
	mfspr	r6, SPRN_BESCR
	mfspr	r7, SPRN_PID
	mfspr	r8, SPRN_WORT
	std	r5, VCPU_EBBRR(r9)
	std	r6, VCPU_BESCR(r9)
	stw	r7, VCPU_GUEST_PID(r9)
	std	r8, VCPU_WORT(r9)
BEGIN_FTR_SECTION
	mfspr	r5, SPRN_TCSCR
	mfspr	r6, SPRN_ACOP
	mfspr	r7, SPRN_CSIGR
	mfspr	r8, SPRN_TACR
	std	r5, VCPU_TCSCR(r9)
	std	r6, VCPU_ACOP(r9)
	std	r7, VCPU_CSIGR(r9)
	std	r8, VCPU_TACR(r9)
FTR_SECTION_ELSE
	mfspr	r5, SPRN_TIDR
	mfspr	r6, SPRN_PSSCR
	std	r5, VCPU_TID(r9)
	rldicl	r6, r6, 4, 50		/* r6 &= PSSCR_GUEST_VIS */
	rotldi	r6, r6, 60
	std	r6, VCPU_PSSCR(r9)
	/* Restore host HFSCR value */
	ld	r7, STACK_SLOT_HFSCR(r1)
	mtspr	SPRN_HFSCR, r7
ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300)
	/*
	 * Restore various registers to 0, where non-zero values
	 * set by the guest could disrupt the host.
	 */
	li	r0, 0
	mtspr	SPRN_PSPB, r0
	mtspr	SPRN_WORT, r0
BEGIN_FTR_SECTION
	mtspr	SPRN_TCSCR, r0
	/* Set MMCRS to 1<<31 to freeze and disable the SPMC counters */
	li	r0, 1
	sldi	r0, r0, 31
	mtspr	SPRN_MMCRS, r0
END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)

	/* Save and restore AMR, IAMR and UAMOR before turning on the MMU */
	ld	r8, STACK_SLOT_IAMR(r1)
	mtspr	SPRN_IAMR, r8

8:	/* Power7 jumps back in here */
	mfspr	r5,SPRN_AMR
	mfspr	r6,SPRN_UAMOR
	std	r5,VCPU_AMR(r9)
	std	r6,VCPU_UAMOR(r9)
	ld	r5,STACK_SLOT_AMR(r1)
	ld	r6,STACK_SLOT_UAMOR(r1)
	mtspr	SPRN_AMR, r5
	mtspr	SPRN_UAMOR, r6

	/* Switch DSCR back to host value */
	mfspr	r8, SPRN_DSCR
	ld	r7, HSTATE_DSCR(r13)
	std	r8, VCPU_DSCR(r9)
	mtspr	SPRN_DSCR, r7

	/* Save non-volatile GPRs */
	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)

	/* 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)

	/* save FP state */
	mr	r3, r9
	bl	kvmppc_save_fp

#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
/*
 * Branch around the call if both CPU_FTR_TM and
 * CPU_FTR_P9_TM_HV_ASSIST are off.
 */
BEGIN_FTR_SECTION
	b	91f
END_FTR_SECTION(CPU_FTR_TM | CPU_FTR_P9_TM_HV_ASSIST, 0)
	/*
	 * NOTE THAT THIS TRASHES ALL NON-VOLATILE REGISTERS (but not CR)
	 */
	mr      r3, r9
	ld      r4, VCPU_MSR(r3)
	li	r5, 0			/* don't preserve non-vol regs */
	bl	kvmppc_save_tm_hv
	nop
	ld	r9, HSTATE_KVM_VCPU(r13)
91:
#endif

	/* Increment yield count if they have a VPA */
	ld	r8, VCPU_VPA(r9)	/* do they have a VPA? */
	cmpdi	r8, 0
	beq	25f
	li	r4, LPPACA_YIELDCOUNT
	LWZX_BE	r3, r8, r4
	addi	r3, r3, 1
	STWX_BE	r3, r8, r4
	li	r3, 1
	stb	r3, VCPU_VPA_DIRTY(r9)
25:
	/* Save PMU registers if requested */
	/* r8 and cr0.eq are live here */
	mr	r3, r9
	li	r4, 1
	beq	21f			/* if no VPA, save PMU stuff anyway */
	lbz	r4, LPPACA_PMCINUSE(r8)
21:	bl	kvmhv_save_guest_pmu
	ld	r9, HSTATE_KVM_VCPU(r13)

	/* Restore host values of some registers */
BEGIN_FTR_SECTION
	ld	r5, STACK_SLOT_CIABR(r1)
	ld	r6, STACK_SLOT_DAWR(r1)
	ld	r7, STACK_SLOT_DAWRX(r1)
	mtspr	SPRN_CIABR, r5
	/*
	 * If the DAWR doesn't work, it's ok to write these here as
	 * this value should always be zero
	*/
	mtspr	SPRN_DAWR, r6
	mtspr	SPRN_DAWRX, r7
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
BEGIN_FTR_SECTION
	ld	r5, STACK_SLOT_TID(r1)
	ld	r6, STACK_SLOT_PSSCR(r1)
	ld	r7, STACK_SLOT_PID(r1)
	mtspr	SPRN_TIDR, r5
	mtspr	SPRN_PSSCR, r6
	mtspr	SPRN_PID, r7
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)

#ifdef CONFIG_PPC_RADIX_MMU
	/*
	 * Are we running hash or radix ?
	 */
	ld	r5, VCPU_KVM(r9)
	lbz	r0, KVM_RADIX(r5)
	cmpwi	cr2, r0, 0
	beq	cr2, 2f

	/*
	 * Radix: do eieio; tlbsync; ptesync sequence in case we
	 * interrupted the guest between a tlbie and a ptesync.
	 */
	eieio
	tlbsync
	ptesync

	/* Radix: Handle the case where the guest used an illegal PID */
	LOAD_REG_ADDR(r4, mmu_base_pid)
	lwz	r3, VCPU_GUEST_PID(r9)
	lwz	r5, 0(r4)
	cmpw	cr0,r3,r5
	blt	2f

	/*
	 * Illegal PID, the HW might have prefetched and cached in the TLB
	 * some translations for the  LPID 0 / guest PID combination which
	 * Linux doesn't know about, so we need to flush that PID out of
	 * the TLB. First we need to set LPIDR to 0 so tlbiel applies to
	 * the right context.
	*/
	li	r0,0
	mtspr	SPRN_LPID,r0
	isync

	/* Then do a congruence class local flush */
	ld	r6,VCPU_KVM(r9)
	lwz	r0,KVM_TLB_SETS(r6)
	mtctr	r0
	li	r7,0x400		/* IS field = 0b01 */
	ptesync
	sldi	r0,r3,32		/* RS has PID */
1:	PPC_TLBIEL(7,0,2,1,1)		/* RIC=2, PRS=1, R=1 */
	addi	r7,r7,0x1000
	bdnz	1b
	ptesync

2:
#endif /* CONFIG_PPC_RADIX_MMU */

	/*
	 * POWER7/POWER8 guest -> host partition switch code.
	 * We don't have to lock against tlbies but we do
	 * have to coordinate the hardware threads.
	 * Here STACK_SLOT_TRAP(r1) contains the trap number.
	 */
kvmhv_switch_to_host:
	/* Secondary threads wait for primary to do partition switch */
	ld	r5,HSTATE_KVM_VCORE(r13)
	ld	r4,VCORE_KVM(r5)	/* pointer to struct kvm */
	lbz	r3,HSTATE_PTID(r13)
	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)
	rlwinm	r0,r3,32-8,0xff
	clrldi	r3,r3,56
	cmpw	r3,r0
	bne	15b
	isync

	/* Did we actually switch to the guest at all? */
	lbz	r6, VCORE_IN_GUEST(r5)
	cmpwi	r6, 0
	beq	19f

	/* Primary thread switches back to host partition */
	lwz	r7,KVM_HOST_LPID(r4)
BEGIN_FTR_SECTION
	ld	r6,KVM_HOST_SDR1(r4)
	li	r8,LPID_RSVD		/* switch to reserved LPID */
	mtspr	SPRN_LPID,r8
	ptesync
	mtspr	SPRN_SDR1,r6		/* switch to host page table */
END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
	mtspr	SPRN_LPID,r7
	isync

BEGIN_FTR_SECTION
	/* DPDES and VTB are shared between threads */
	mfspr	r7, SPRN_DPDES
	mfspr	r8, SPRN_VTB
	std	r7, VCORE_DPDES(r5)
	std	r8, VCORE_VTB(r5)
	/* clear DPDES so we don't get guest doorbells in the host */
	li	r8, 0
	mtspr	SPRN_DPDES, r8
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)

	/* Subtract timebase offset from timebase */
	ld	r8, VCORE_TB_OFFSET_APPL(r5)
	cmpdi	r8,0
	beq	17f
	li	r0, 0
	std	r0, VCORE_TB_OFFSET_APPL(r5)
	mftb	r6			/* current guest 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

17:
	/*
	 * If this is an HMI, we called kvmppc_realmode_hmi_handler
	 * above, which may or may not have already called
	 * kvmppc_subcore_exit_guest.  Fortunately, all that
	 * kvmppc_subcore_exit_guest does is clear a flag, so calling
	 * it again here is benign even if kvmppc_realmode_hmi_handler
	 * has already called it.
	 */
	bl	kvmppc_subcore_exit_guest
	nop
30:	ld	r5,HSTATE_KVM_VCORE(r13)
	ld	r4,VCORE_KVM(r5)	/* pointer to struct kvm */

	/* Reset PCR */
	ld	r0, VCORE_PCR(r5)
	cmpdi	r0, 0
	beq	18f
	li	r0, 0
	mtspr	SPRN_PCR, r0
18:
	/* Signal secondary CPUs to continue */
	stb	r0,VCORE_IN_GUEST(r5)
19:	lis	r8,0x7fff		/* MAX_INT@h */
	mtspr	SPRN_HDEC,r8

16:
BEGIN_FTR_SECTION
	/* On POWER9 with HPT-on-radix we need to wait for all other threads */
	ld	r3, HSTATE_SPLIT_MODE(r13)
	cmpdi	r3, 0
	beq	47f
	lwz	r8, KVM_SPLIT_DO_RESTORE(r3)
	cmpwi	r8, 0
	beq	47f
	bl	kvmhv_p9_restore_lpcr
	nop
	b	48f
47:
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
	ld	r8,KVM_HOST_LPCR(r4)
	mtspr	SPRN_LPCR,r8
	isync
48:
#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
	/* Finish timing, if we have a vcpu */
	ld	r4, HSTATE_KVM_VCPU(r13)
	cmpdi	r4, 0
	li	r3, 0
	beq	2f
	bl	kvmhv_accumulate_time
2:
#endif
	/* Unset guest mode */
	li	r0, KVM_GUEST_MODE_NONE
	stb	r0, HSTATE_IN_GUEST(r13)

	lwz	r12, STACK_SLOT_TRAP(r1)	/* return trap # in r12 */
	ld	r0, SFS+PPC_LR_STKOFF(r1)
	addi	r1, r1, SFS
	mtlr	r0
	blr

kvmppc_guest_external:
	/* External interrupt, first check for host_ipi. If this is
	 * set, we know the host wants us out so let's do it now
	 */
	bl	kvmppc_read_intr

	/*
	 * Restore the active volatile registers after returning from
	 * a C function.
	 */
	ld	r9, HSTATE_KVM_VCPU(r13)
	li	r12, BOOK3S_INTERRUPT_EXTERNAL

	/*
	 * kvmppc_read_intr return codes:
	 *
	 * Exit to host (r3 > 0)
	 *   1 An interrupt is pending that needs to be handled by the host
	 *     Exit guest and return to host by branching to guest_exit_cont
	 *
	 *   2 Passthrough that needs completion in the host
	 *     Exit guest and return to host by branching to guest_exit_cont
	 *     However, we also set r12 to BOOK3S_INTERRUPT_HV_RM_HARD
	 *     to indicate to the host to complete handling the interrupt
	 *
	 * Before returning to guest, we check if any CPU is heading out
	 * to the host and if so, we head out also. If no CPUs are heading
	 * check return values <= 0.
	 *
	 * Return to guest (r3 <= 0)
	 *  0 No external interrupt is pending
	 * -1 A guest wakeup IPI (which has now been cleared)
	 *    In either case, we return to guest to deliver any pending
	 *    guest interrupts.
	 *
	 * -2 A PCI passthrough external interrupt was handled
	 *    (interrupt was delivered directly to guest)
	 *    Return to guest to deliver any pending guest interrupts.
	 */

	cmpdi	r3, 1
	ble	1f

	/* Return code = 2 */
	li	r12, BOOK3S_INTERRUPT_HV_RM_HARD
	stw	r12, VCPU_TRAP(r9)
	b	guest_exit_cont

1:	/* Return code <= 1 */
	cmpdi	r3, 0
	bgt	guest_exit_cont

	/* Return code <= 0 */
maybe_reenter_guest:
	ld	r5, HSTATE_KVM_VCORE(r13)
	lwz	r0, VCORE_ENTRY_EXIT(r5)
	cmpwi	r0, 0x100
	mr	r4, r9
	blt	deliver_guest_interrupt
	b	guest_exit_cont

#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
/*
 * Softpatch interrupt for transactional memory emulation cases
 * on POWER9 DD2.2.  This is early in the guest exit path - we
 * haven't saved registers or done a treclaim yet.
 */
kvmppc_tm_emul:
	/* Save instruction image in HEIR */
	mfspr	r3, SPRN_HEIR
	stw	r3, VCPU_HEIR(r9)

	/*
	 * The cases we want to handle here are those where the guest
	 * is in real suspend mode and is trying to transition to
	 * transactional mode.
	 */
	lbz	r0, HSTATE_FAKE_SUSPEND(r13)
	cmpwi	r0, 0		/* keep exiting guest if in fake suspend */
	bne	guest_exit_cont
	rldicl	r3, r11, 64 - MSR_TS_S_LG, 62
	cmpwi	r3, 1		/* or if not in suspend state */
	bne	guest_exit_cont

	/* Call C code to do the emulation */
	mr	r3, r9
	bl	kvmhv_p9_tm_emulation_early
	nop
	ld	r9, HSTATE_KVM_VCPU(r13)
	li	r12, BOOK3S_INTERRUPT_HV_SOFTPATCH
	cmpwi	r3, 0
	beq	guest_exit_cont		/* continue exiting if not handled */
	ld	r10, VCPU_PC(r9)
	ld	r11, VCPU_MSR(r9)
	b	fast_interrupt_c_return	/* go back to guest if handled */
#endif /* CONFIG_PPC_TRANSACTIONAL_MEM */

/*
 * 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:
	ld	r3, VCPU_KVM(r9)
	lbz	r0, KVM_RADIX(r3)
	mfspr	r4, SPRN_HDAR
	mfspr	r6, SPRN_HDSISR
BEGIN_FTR_SECTION
	/* Look for DSISR canary. If we find it, retry instruction */
	cmpdi	r6, 0x7fff
	beq	6f
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
	cmpwi	r0, 0
	bne	.Lradix_hdsi		/* on radix, just save DAR/DSISR/ASDR */
	/* HPTE not found fault or protection fault? */
	andis.	r0, r6, (DSISR_NOHPTE | DSISR_PROTFAULT)@h
	beq	1f			/* if not, send it to the guest */
	andi.	r0, r11, MSR_DR		/* data relocation enabled? */
	beq	3f
BEGIN_FTR_SECTION
	mfspr	r5, SPRN_ASDR		/* on POWER9, use ASDR to get VSID */
	b	4f
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
	clrrdi	r0, r4, 28
	PPC_SLBFEE_DOT(R5, R0)		/* if so, look up SLB */
	li	r0, BOOK3S_INTERRUPT_DATA_SEGMENT
	bne	7f			/* 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 */
	li	r7, 1			/* data 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_DATA_STORAGE
	cmpdi	r3, 0			/* retry the instruction */
	beq	6f
	cmpdi	r3, -1			/* handle in kernel mode */
	beq	guest_exit_cont
	cmpdi	r3, -2			/* MMIO emulation; need instr word */
	beq	2f

	/* Synthesize a DSI (or DSegI) for the guest */
	ld	r4, VCPU_FAULT_DAR(r9)
	mr	r6, r3
1:	li	r0, BOOK3S_INTERRUPT_DATA_STORAGE
	mtspr	SPRN_DSISR, r6
7:	mtspr	SPRN_DAR, r4
	mtspr	SPRN_SRR0, r10
	mtspr	SPRN_SRR1, r11
	mr	r10, r0
	bl	kvmppc_msr_interrupt
fast_interrupt_c_return:
6:	ld	r7, VCPU_CTR(r9)
	ld	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. */
	li	r0, KVM_GUEST_MODE_HOST_HV
	stb	r0, HSTATE_IN_GUEST(r13)
	b	guest_exit_cont

.Lradix_hdsi:
	std	r4, VCPU_FAULT_DAR(r9)
	stw	r6, VCPU_FAULT_DSISR(r9)
.Lradix_hisi:
	mfspr	r5, SPRN_ASDR
	std	r5, VCPU_FAULT_GPA(r9)
	b	guest_exit_cont

/*
 * 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:
	ld	r3, VCPU_KVM(r9)
	lbz	r0, KVM_RADIX(r3)
	cmpwi	r0, 0
	bne	.Lradix_hisi		/* for radix, just save ASDR */
	andis.	r0, r11, SRR1_ISI_NOPT@h
	beq	1f
	andi.	r0, r11, MSR_IR		/* instruction relocation enabled? */
	beq	3f
BEGIN_FTR_SECTION
	mfspr	r5, SPRN_ASDR		/* on POWER9, use ASDR to get VSID */
	b	4f
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
	clrrdi	r0, r10, 28
	PPC_SLBFEE_DOT(R5, R0)		/* if so, look up SLB */
	li	r0, BOOK3S_INTERRUPT_INST_SEGMENT
	bne	7f			/* 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 */
	beq	fast_interrupt_c_return
	cmpdi	r3, -1			/* handle in kernel mode */
	beq	guest_exit_cont

	/* Synthesize an ISI (or ISegI) for the guest */
	mr	r11, r3
1:	li	r0, BOOK3S_INTERRUPT_INST_STORAGE
7:	mtspr	SPRN_SRR0, r10
	mtspr	SPRN_SRR1, r11
	mr	r10, r0
	bl	kvmppc_msr_interrupt
	b	fast_interrupt_c_return

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

/*
 * 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).
 *
 * r5 - r8 contain hcall args,
 * r9 = vcpu, r10 = pc, r11 = msr, r12 = trap, r13 = paca
 */
hcall_try_real_mode:
	ld	r3,VCPU_GPR(R3)(r9)
	andi.	r0,r11,MSR_PR
	/* sc 1 from userspace - reflect to guest syscall */
	bne	sc_1_fast_return
	/* sc 1 from nested guest - give it to L1 to handle */
	ld	r0, VCPU_NESTED(r9)
	cmpdi	r0, 0
	bne	guest_exit_cont
	clrrdi	r3,r3,2
	cmpldi	r3,hcall_real_table_end - hcall_real_table
	bge	guest_exit_cont
	/* See if this hcall is enabled for in-kernel handling */
	ld	r4, VCPU_KVM(r9)
	srdi	r0, r3, 8	/* r0 = (r3 / 4) >> 6 */
	sldi	r0, r0, 3	/* index into kvm->arch.enabled_hcalls[] */
	add	r4, r4, r0
	ld	r0, KVM_ENABLED_HCALLS(r4)
	rlwinm	r4, r3, 32-2, 0x3f	/* r4 = (r3 / 4) & 0x3f */
	srd	r0, r0, r4
	andi.	r0, r0, 1
	beq	guest_exit_cont
	/* Get pointer to handler, if any, and call it */
	LOAD_REG_ADDR(r4, hcall_real_table)
	lwax	r3,r3,r4
	cmpwi	r3,0
	beq	guest_exit_cont
	add	r12,r3,r4
	mtctr	r12
	mr	r3,r9		/* get vcpu pointer */
	ld	r4,VCPU_GPR(R4)(r9)
	bctrl
	cmpdi	r3,H_TOO_HARD
	beq	hcall_real_fallback
	ld	r4,HSTATE_KVM_VCPU(r13)
	std	r3,VCPU_GPR(R3)(r4)
	ld	r10,VCPU_PC(r4)
	ld	r11,VCPU_MSR(r4)
	b	fast_guest_return

sc_1_fast_return:
	mtspr	SPRN_SRR0,r10
	mtspr	SPRN_SRR1,r11
	li	r10, BOOK3S_INTERRUPT_SYSCALL
	bl	kvmppc_msr_interrupt
	mr	r4,r9
	b	fast_guest_return

	/* 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)

	b	guest_exit_cont

	.globl	hcall_real_table
hcall_real_table:
	.long	0		/* 0 - unused */
	.long	DOTSYM(kvmppc_h_remove) - hcall_real_table
	.long	DOTSYM(kvmppc_h_enter) - hcall_real_table
	.long	DOTSYM(kvmppc_h_read) - hcall_real_table
	.long	DOTSYM(kvmppc_h_clear_mod) - hcall_real_table
	.long	DOTSYM(kvmppc_h_clear_ref) - hcall_real_table
	.long	DOTSYM(kvmppc_h_protect) - hcall_real_table
#ifdef CONFIG_SPAPR_TCE_IOMMU
	.long	DOTSYM(kvmppc_h_get_tce) - hcall_real_table
	.long	DOTSYM(kvmppc_rm_h_put_tce) - hcall_real_table
#else
	.long	0		/* 0x1c */
	.long	0		/* 0x20 */
#endif
	.long	0		/* 0x24 - H_SET_SPRG0 */
	.long	DOTSYM(kvmppc_h_set_dabr) - hcall_real_table
	.long	DOTSYM(kvmppc_rm_h_page_init) - hcall_real_table
	.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 */
#ifdef CONFIG_KVM_XICS
	.long	DOTSYM(kvmppc_rm_h_eoi) - hcall_real_table
	.long	DOTSYM(kvmppc_rm_h_cppr) - hcall_real_table
	.long	DOTSYM(kvmppc_rm_h_ipi) - hcall_real_table
	.long	DOTSYM(kvmppc_rm_h_ipoll) - hcall_real_table
	.long	DOTSYM(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
	.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 */
	.long	DOTSYM(kvmppc_h_cede) - hcall_real_table
	.long	DOTSYM(kvmppc_rm_h_confer) - hcall_real_table
	.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	DOTSYM(kvmppc_h_bulk_remove) - hcall_real_table
	.long	0		/* 0x128 */
	.long	0		/* 0x12c */
	.long	0		/* 0x130 */
	.long	DOTSYM(kvmppc_h_set_xdabr) - hcall_real_table
#ifdef CONFIG_SPAPR_TCE_IOMMU
	.long	DOTSYM(kvmppc_rm_h_stuff_tce) - hcall_real_table
	.long	DOTSYM(kvmppc_rm_h_put_tce_indirect) - hcall_real_table
#else
	.long	0		/* 0x138 */
	.long	0		/* 0x13c */
#endif
	.long	0		/* 0x140 */
	.long	0		/* 0x144 */
	.long	0		/* 0x148 */
	.long	0		/* 0x14c */
	.long	0		/* 0x150 */
	.long	0		/* 0x154 */
	.long	0		/* 0x158 */
	.long	0		/* 0x15c */
	.long	0		/* 0x160 */
	.long	0		/* 0x164 */
	.long	0		/* 0x168 */
	.long	0		/* 0x16c */
	.long	0		/* 0x170 */
	.long	0		/* 0x174 */
	.long	0		/* 0x178 */
	.long	0		/* 0x17c */
	.long	0		/* 0x180 */
	.long	0		/* 0x184 */
	.long	0		/* 0x188 */
	.long	0		/* 0x18c */
	.long	0		/* 0x190 */
	.long	0		/* 0x194 */
	.long	0		/* 0x198 */
	.long	0		/* 0x19c */
	.long	0		/* 0x1a0 */
	.long	0		/* 0x1a4 */
	.long	0		/* 0x1a8 */
	.long	0		/* 0x1ac */
	.long	0		/* 0x1b0 */
	.long	0		/* 0x1b4 */
	.long	0		/* 0x1b8 */
	.long	0		/* 0x1bc */
	.long	0		/* 0x1c0 */
	.long	0		/* 0x1c4 */
	.long	0		/* 0x1c8 */
	.long	0		/* 0x1cc */
	.long	0		/* 0x1d0 */
	.long	0		/* 0x1d4 */
	.long	0		/* 0x1d8 */
	.long	0		/* 0x1dc */
	.long	0		/* 0x1e0 */
	.long	0		/* 0x1e4 */
	.long	0		/* 0x1e8 */
	.long	0		/* 0x1ec */
	.long	0		/* 0x1f0 */
	.long	0		/* 0x1f4 */
	.long	0		/* 0x1f8 */
	.long	0		/* 0x1fc */
	.long	0		/* 0x200 */
	.long	0		/* 0x204 */
	.long	0		/* 0x208 */
	.long	0		/* 0x20c */
	.long	0		/* 0x210 */
	.long	0		/* 0x214 */
	.long	0		/* 0x218 */
	.long	0		/* 0x21c */
	.long	0		/* 0x220 */
	.long	0		/* 0x224 */
	.long	0		/* 0x228 */
	.long	0		/* 0x22c */
	.long	0		/* 0x230 */
	.long	0		/* 0x234 */
	.long	0		/* 0x238 */
	.long	0		/* 0x23c */
	.long	0		/* 0x240 */
	.long	0		/* 0x244 */
	.long	0		/* 0x248 */
	.long	0		/* 0x24c */
	.long	0		/* 0x250 */
	.long	0		/* 0x254 */
	.long	0		/* 0x258 */
	.long	0		/* 0x25c */
	.long	0		/* 0x260 */
	.long	0		/* 0x264 */
	.long	0		/* 0x268 */
	.long	0		/* 0x26c */
	.long	0		/* 0x270 */
	.long	0		/* 0x274 */
	.long	0		/* 0x278 */
	.long	0		/* 0x27c */
	.long	0		/* 0x280 */
	.long	0		/* 0x284 */
	.long	0		/* 0x288 */
	.long	0		/* 0x28c */
	.long	0		/* 0x290 */
	.long	0		/* 0x294 */
	.long	0		/* 0x298 */
	.long	0		/* 0x29c */
	.long	0		/* 0x2a0 */
	.long	0		/* 0x2a4 */
	.long	0		/* 0x2a8 */
	.long	0		/* 0x2ac */
	.long	0		/* 0x2b0 */
	.long	0		/* 0x2b4 */
	.long	0		/* 0x2b8 */
	.long	0		/* 0x2bc */
	.long	0		/* 0x2c0 */
	.long	0		/* 0x2c4 */
	.long	0		/* 0x2c8 */
	.long	0		/* 0x2cc */
	.long	0		/* 0x2d0 */
	.long	0		/* 0x2d4 */
	.long	0		/* 0x2d8 */
	.long	0		/* 0x2dc */
	.long	0		/* 0x2e0 */
	.long	0		/* 0x2e4 */
	.long	0		/* 0x2e8 */
	.long	0		/* 0x2ec */
	.long	0		/* 0x2f0 */
	.long	0		/* 0x2f4 */
	.long	0		/* 0x2f8 */
#ifdef CONFIG_KVM_XICS
	.long	DOTSYM(kvmppc_rm_h_xirr_x) - hcall_real_table
#else
	.long	0		/* 0x2fc - H_XIRR_X*/
#endif
	.long	DOTSYM(kvmppc_h_random) - hcall_real_table
	.globl	hcall_real_table_end
hcall_real_table_end:

_GLOBAL(kvmppc_h_set_xdabr)
EXPORT_SYMBOL_GPL(kvmppc_h_set_xdabr)
	andi.	r0, r5, DABRX_USER | DABRX_KERNEL
	beq	6f
	li	r0, DABRX_USER | DABRX_KERNEL | DABRX_BTI
	andc.	r0, r5, r0
	beq	3f
6:	li	r3, H_PARAMETER
	blr

_GLOBAL(kvmppc_h_set_dabr)
EXPORT_SYMBOL_GPL(kvmppc_h_set_dabr)
	li	r5, DABRX_USER | DABRX_KERNEL
3:
BEGIN_FTR_SECTION
	b	2f
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
	std	r4,VCPU_DABR(r3)
	stw	r5, VCPU_DABRX(r3)
	mtspr	SPRN_DABRX, r5
	/* 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
	li	r3,0
	blr

2:
	LOAD_REG_ADDR(r11, dawr_force_enable)
	lbz	r11, 0(r11)
	cmpdi	r11, 0
	bne	3f
	li	r3, H_HARDWARE
	blr
3:
	/* Emulate H_SET_DABR/X on P8 for the sake of compat mode guests */
	rlwimi	r5, r4, 5, DAWRX_DR | DAWRX_DW
	rlwimi	r5, r4, 2, DAWRX_WT
	clrrdi	r4, r4, 3
	std	r4, VCPU_DAWR(r3)
	std	r5, VCPU_DAWRX(r3)
	/*
	 * If came in through the real mode hcall handler then it is necessary
	 * to write the registers since the return path won't. Otherwise it is
	 * sufficient to store then in the vcpu struct as they will be loaded
	 * next time the vcpu is run.
	 */
	mfmsr	r6
	andi.	r6, r6, MSR_DR		/* in real mode? */
	bne	4f
	mtspr	SPRN_DAWR, r4
	mtspr	SPRN_DAWRX, r5
4:	li	r3, 0
	blr

_GLOBAL(kvmppc_h_cede)		/* r3 = vcpu pointer, r11 = msr, r13 = paca */
	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
	bne	kvm_cede_prodded
	li	r12,0		/* set trap to 0 to say hcall is handled */
	stw	r12,VCPU_TRAP(r3)
	li	r0,H_SUCCESS
	std	r0,VCPU_GPR(R3)(r3)

	/*
	 * 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)
	lbz	r6,HSTATE_PTID(r13)
	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
	cmpw	r4,r8
	beq	kvm_cede_exit
	stwcx.	r4,0,r6
	bne	31b
	/* order napping_threads update vs testing entry_exit_map */
	isync
	li	r0,NAPPING_CEDE
	stb	r0,HSTATE_NAPPING(r13)
	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 */
	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)

	/* save FP state */
	bl	kvmppc_save_fp

#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
/*
 * Branch around the call if both CPU_FTR_TM and
 * CPU_FTR_P9_TM_HV_ASSIST are off.
 */
BEGIN_FTR_SECTION
	b	91f
END_FTR_SECTION(CPU_FTR_TM | CPU_FTR_P9_TM_HV_ASSIST, 0)
	/*
	 * NOTE THAT THIS TRASHES ALL NON-VOLATILE REGISTERS (but not CR)
	 */
	ld	r3, HSTATE_KVM_VCPU(r13)
	ld      r4, VCPU_MSR(r3)
	li	r5, 0			/* don't preserve non-vol regs */
	bl	kvmppc_save_tm_hv
	nop
91:
#endif

	/*
	 * Set DEC to the smaller of DEC and HDEC, so that we wake
	 * no later than the end of our timeslice (HDEC interrupts
	 * don't wake us from nap).
	 */
	mfspr	r3, SPRN_DEC
	mfspr	r4, SPRN_HDEC
	mftb	r5
BEGIN_FTR_SECTION
	/* On P9 check whether the guest has large decrementer mode enabled */
	ld	r6, HSTATE_KVM_VCORE(r13)
	ld	r6, VCORE_LPCR(r6)
	andis.	r6, r6, LPCR_LD@h
	bne	68f
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
	extsw	r3, r3
68:	EXTEND_HDEC(r4)
	cmpd	r3, r4
	ble	67f
	mtspr	SPRN_DEC, r4
67:
	/* save expiry time of guest decrementer */
	add	r3, r3, r5
	ld	r4, HSTATE_KVM_VCPU(r13)
	ld	r5, HSTATE_KVM_VCORE(r13)
	ld	r6, VCORE_TB_OFFSET_APPL(r5)
	subf	r3, r6, r3	/* convert to host TB value */
	std	r3, VCPU_DEC_EXPIRES(r4)

#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
	ld	r4, HSTATE_KVM_VCPU(r13)
	addi	r3, r4, VCPU_TB_CEDE
	bl	kvmhv_accumulate_time
#endif

	lis	r3, LPCR_PECEDP@h	/* Do wake on privileged doorbell */

	/* Go back to host stack */
	ld	r1, HSTATE_HOST_R1(r13)

	/*
	 * Take a nap until a decrementer or external or doobell interrupt
	 * occurs, with PECE1 and PECE0 set in LPCR.
	 * On POWER8, set PECEDH, and if we are ceding, also set PECEDP.
	 * Also clear the runlatch bit before napping.
	 */
kvm_do_nap:
	mfspr	r0, SPRN_CTRLF
	clrrdi	r0, r0, 1
	mtspr	SPRN_CTRLT, r0

	li	r0,1
	stb	r0,HSTATE_HWTHREAD_REQ(r13)
	mfspr	r5,SPRN_LPCR
	ori	r5,r5,LPCR_PECE0 | LPCR_PECE1
BEGIN_FTR_SECTION
	ori	r5, r5, LPCR_PECEDH
	rlwimi	r5, r3, 0, LPCR_PECEDP
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)

kvm_nap_sequence:		/* desired LPCR value in r5 */
BEGIN_FTR_SECTION
	/*
	 * PSSCR bits:	exit criterion = 1 (wakeup based on LPCR at sreset)
	 *		enable state loss = 1 (allow SMT mode switch)
	 *		requested level = 0 (just stop dispatching)
	 */
	lis	r3, (PSSCR_EC | PSSCR_ESL)@h
	/* Set LPCR_PECE_HVEE bit to enable wakeup by HV interrupts */
	li	r4, LPCR_PECE_HVEE@higher
	sldi	r4, r4, 32
	or	r5, r5, r4
FTR_SECTION_ELSE
	li	r3, PNV_THREAD_NAP
ALT_FTR_SECTION_END_IFSET(CPU_FTR_ARCH_300)
	mtspr	SPRN_LPCR,r5
	isync

BEGIN_FTR_SECTION
	bl	isa300_idle_stop_mayloss
FTR_SECTION_ELSE
	bl	isa206_idle_insn_mayloss
ALT_FTR_SECTION_END_IFSET(CPU_FTR_ARCH_300)

	mfspr	r0, SPRN_CTRLF
	ori	r0, r0, 1
	mtspr	SPRN_CTRLT, r0

	mtspr	SPRN_SRR1, r3

	li	r0, 0
	stb	r0, PACA_FTRACE_ENABLED(r13)

	li	r0, KVM_HWTHREAD_IN_KVM
	stb	r0, HSTATE_HWTHREAD_STATE(r13)

	lbz	r0, HSTATE_NAPPING(r13)
	cmpwi	r0, NAPPING_CEDE
	beq	kvm_end_cede
	cmpwi	r0, NAPPING_NOVCPU
	beq	kvm_novcpu_wakeup
	cmpwi	r0, NAPPING_UNSPLIT
	beq	kvm_unsplit_wakeup
	twi	31,0,0 /* Nap state must not be zero */

33:	mr	r4, r3
	li	r3, 0
	li	r12, 0
	b	34f

kvm_end_cede:
	/* Woken by external or decrementer interrupt */

	/* get vcpu pointer */
	ld	r4, HSTATE_KVM_VCPU(r13)

#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
	addi	r3, r4, VCPU_TB_RMINTR
	bl	kvmhv_accumulate_time
#endif

#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
/*
 * Branch around the call if both CPU_FTR_TM and
 * CPU_FTR_P9_TM_HV_ASSIST are off.
 */
BEGIN_FTR_SECTION
	b	91f
END_FTR_SECTION(CPU_FTR_TM | CPU_FTR_P9_TM_HV_ASSIST, 0)
	/*
	 * NOTE THAT THIS TRASHES ALL NON-VOLATILE REGISTERS (but not CR)
	 */
	mr      r3, r4
	ld      r4, VCPU_MSR(r3)
	li	r5, 0			/* don't preserve non-vol regs */
	bl	kvmppc_restore_tm_hv
	nop
	ld	r4, HSTATE_KVM_VCPU(r13)
91:
#endif

	/* load up FP state */
	bl	kvmppc_load_fp

	/* Restore guest decrementer */
	ld	r3, VCPU_DEC_EXPIRES(r4)
	ld	r5, HSTATE_KVM_VCORE(r13)
	ld	r6, VCORE_TB_OFFSET_APPL(r5)
	add	r3, r3, r6	/* convert host TB to guest TB value */
	mftb	r7
	subf	r3, r7, r3
	mtspr	SPRN_DEC, r3

	/* Load NV GPRS */
	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)

	/* Check the wake reason in SRR1 to see why we got here */
	bl	kvmppc_check_wake_reason

	/*
	 * Restore volatile registers since we could have called a
	 * C routine in kvmppc_check_wake_reason
	 *	r4 = VCPU
	 * r3 tells us whether we need to return to host or not
	 * WARNING: it gets checked further down:
	 * should not modify r3 until this check is done.
	 */
	ld	r4, HSTATE_KVM_VCPU(r13)

	/* clear our bit in vcore->napping_threads */
34:	ld	r5,HSTATE_KVM_VCORE(r13)
	lbz	r7,HSTATE_PTID(r13)
	li	r0,1
	sld	r0,r0,r7
	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)

	/* See if the wake reason saved in r3 means we need to exit */
	stw	r12, VCPU_TRAP(r4)
	mr	r9, r4
	cmpdi	r3, 0
	bgt	guest_exit_cont
	b	maybe_reenter_guest

	/* cede when already previously prodded case */
kvm_cede_prodded:
	li	r0,0
	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 */
kvm_cede_exit:
	ld	r9, HSTATE_KVM_VCPU(r13)
#ifdef CONFIG_KVM_XICS
	/* are we using XIVE with single escalation? */
	ld	r10, VCPU_XIVE_ESC_VADDR(r9)
	cmpdi	r10, 0
	beq	3f
	li	r6, XIVE_ESB_SET_PQ_00
	/*
	 * If we still have a pending escalation, abort the cede,
	 * and we must set PQ to 10 rather than 00 so that we don't
	 * potentially end up with two entries for the escalation
	 * interrupt in the XIVE interrupt queue.  In that case
	 * we also don't want to set xive_esc_on to 1 here in
	 * case we race with xive_esc_irq().
	 */
	lbz	r5, VCPU_XIVE_ESC_ON(r9)
	cmpwi	r5, 0
	beq	4f
	li	r0, 0
	stb	r0, VCPU_CEDED(r9)
	li	r6, XIVE_ESB_SET_PQ_10
	b	5f
4:	li	r0, 1
	stb	r0, VCPU_XIVE_ESC_ON(r9)
	/* make sure store to xive_esc_on is seen before xive_esc_irq runs */
	sync
5:	/* Enable XIVE escalation */
	mfmsr	r0
	andi.	r0, r0, MSR_DR		/* in real mode? */
	beq	1f
	ldx	r0, r10, r6
	b	2f
1:	ld	r10, VCPU_XIVE_ESC_RADDR(r9)
	ldcix	r0, r10, r6
2:	sync
#endif /* CONFIG_KVM_XICS */
3:	b	guest_exit_cont

	/* Try to do machine check recovery in real mode */
machine_check_realmode:
	mr	r3, r9		/* get vcpu pointer */
	bl	kvmppc_realmode_machine_check
	nop
	/* all machine checks go to virtual mode for further handling */
	ld	r9, HSTATE_KVM_VCPU(r13)
	li	r12, BOOK3S_INTERRUPT_MACHINE_CHECK
	b	guest_exit_cont

/*
 * Call C code to handle a HMI in real mode.
 * Only the primary thread does the call, secondary threads are handled
 * by calling hmi_exception_realmode() after kvmppc_hv_entry returns.
 * r9 points to the vcpu on entry
 */
hmi_realmode:
	lbz	r0, HSTATE_PTID(r13)
	cmpwi	r0, 0
	bne	guest_exit_cont
	bl	kvmppc_realmode_hmi_handler
	ld	r9, HSTATE_KVM_VCPU(r13)
	li	r12, BOOK3S_INTERRUPT_HMI
	b	guest_exit_cont

/*
 * Check the reason we woke from nap, and take appropriate action.
 * Returns (in r3):
 *	0 if nothing needs to be done
 *	1 if something happened that needs to be handled by the host
 *	-1 if there was a guest wakeup (IPI or msgsnd)
 *	-2 if we handled a PCI passthrough interrupt (returned by
 *		kvmppc_read_intr only)
 *
 * Also sets r12 to the interrupt vector for any interrupt that needs
 * to be handled now by the host (0x500 for external interrupt), or zero.
 * Modifies all volatile registers (since it may call a C function).
 * This routine calls kvmppc_read_intr, a C function, if an external
 * interrupt is pending.
 */
kvmppc_check_wake_reason:
	mfspr	r6, SPRN_SRR1
BEGIN_FTR_SECTION
	rlwinm	r6, r6, 45-31, 0xf	/* extract wake reason field (P8) */
FTR_SECTION_ELSE
	rlwinm	r6, r6, 45-31, 0xe	/* P7 wake reason field is 3 bits */
ALT_FTR_SECTION_END_IFSET(CPU_FTR_ARCH_207S)
	cmpwi	r6, 8			/* was it an external interrupt? */
	beq	7f			/* if so, see what it was */
	li	r3, 0
	li	r12, 0
	cmpwi	r6, 6			/* was it the decrementer? */
	beq	0f
BEGIN_FTR_SECTION
	cmpwi	r6, 5			/* privileged doorbell? */
	beq	0f
	cmpwi	r6, 3			/* hypervisor doorbell? */
	beq	3f
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
	cmpwi	r6, 0xa			/* Hypervisor maintenance ? */
	beq	4f
	li	r3, 1			/* anything else, return 1 */
0:	blr

	/* hypervisor doorbell */
3:	li	r12, BOOK3S_INTERRUPT_H_DOORBELL

	/*
	 * Clear the doorbell as we will invoke the handler
	 * explicitly in the guest exit path.
	 */
	lis	r6, (PPC_DBELL_SERVER << (63-36))@h
	PPC_MSGCLR(6)
	/* see if it's a host IPI */
	li	r3, 1
BEGIN_FTR_SECTION
	PPC_MSGSYNC
	lwsync
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
	lbz	r0, HSTATE_HOST_IPI(r13)
	cmpwi	r0, 0
	bnelr
	/* if not, return -1 */
	li	r3, -1
	blr

	/* Woken up due to Hypervisor maintenance interrupt */
4:	li	r12, BOOK3S_INTERRUPT_HMI
	li	r3, 1
	blr

	/* external interrupt - create a stack frame so we can call C */
7:	mflr	r0
	std	r0, PPC_LR_STKOFF(r1)
	stdu	r1, -PPC_MIN_STKFRM(r1)
	bl	kvmppc_read_intr
	nop
	li	r12, BOOK3S_INTERRUPT_EXTERNAL
	cmpdi	r3, 1
	ble	1f

	/*
	 * Return code of 2 means PCI passthrough interrupt, but
	 * we need to return back to host to complete handling the
	 * interrupt. Trap reason is expected in r12 by guest
	 * exit code.
	 */
	li	r12, BOOK3S_INTERRUPT_HV_RM_HARD
1:
	ld	r0, PPC_MIN_STKFRM+PPC_LR_STKOFF(r1)
	addi	r1, r1, PPC_MIN_STKFRM
	mtlr	r0
	blr

/*
 * Save away FP, VMX and VSX registers.
 * r3 = vcpu pointer
 * N.B. r30 and r31 are volatile across this function,
 * thus it is not callable from C.
 */
kvmppc_save_fp:
	mflr	r30
	mr	r31,r3
	mfmsr	r5
	ori	r8,r5,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
	addi	r3,r3,VCPU_FPRS
	bl	store_fp_state
#ifdef CONFIG_ALTIVEC
BEGIN_FTR_SECTION
	addi	r3,r31,VCPU_VRS
	bl	store_vr_state
END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
#endif
	mfspr	r6,SPRN_VRSAVE
	stw	r6,VCPU_VRSAVE(r31)
	mtlr	r30
	blr

/*
 * Load up FP, VMX and VSX registers
 * r4 = vcpu pointer
 * N.B. r30 and r31 are volatile across this function,
 * thus it is not callable from C.
 */
kvmppc_load_fp:
	mflr	r30
	mr	r31,r4
	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
	addi	r3,r4,VCPU_FPRS
	bl	load_fp_state
#ifdef CONFIG_ALTIVEC
BEGIN_FTR_SECTION
	addi	r3,r31,VCPU_VRS
	bl	load_vr_state
END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
#endif
	lwz	r7,VCPU_VRSAVE(r31)
	mtspr	SPRN_VRSAVE,r7
	mtlr	r30
	mr	r4,r31
	blr

#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
/*
 * Save transactional state and TM-related registers.
 * Called with r3 pointing to the vcpu struct and r4 containing
 * the guest MSR value.
 * r5 is non-zero iff non-volatile register state needs to be maintained.
 * If r5 == 0, this can modify all checkpointed registers, but
 * restores r1 and r2 before exit.
 */
_GLOBAL_TOC(kvmppc_save_tm_hv)
EXPORT_SYMBOL_GPL(kvmppc_save_tm_hv)
	/* See if we need to handle fake suspend mode */
BEGIN_FTR_SECTION
	b	__kvmppc_save_tm
END_FTR_SECTION_IFCLR(CPU_FTR_P9_TM_HV_ASSIST)

	lbz	r0, HSTATE_FAKE_SUSPEND(r13) /* Were we fake suspended? */
	cmpwi	r0, 0
	beq	__kvmppc_save_tm

	/* The following code handles the fake_suspend = 1 case */
	mflr	r0
	std	r0, PPC_LR_STKOFF(r1)
	stdu	r1, -PPC_MIN_STKFRM(r1)

	/* Turn on TM. */
	mfmsr	r8
	li	r0, 1
	rldimi	r8, r0, MSR_TM_LG, 63-MSR_TM_LG
	mtmsrd	r8

	rldicl. r8, r8, 64 - MSR_TS_S_LG, 62 /* Did we actually hrfid? */
	beq	4f
BEGIN_FTR_SECTION
	bl	pnv_power9_force_smt4_catch
END_FTR_SECTION_IFSET(CPU_FTR_P9_TM_XER_SO_BUG)
	nop

	/* We have to treclaim here because that's the only way to do S->N */
	li	r3, TM_CAUSE_KVM_RESCHED
	TRECLAIM(R3)

	/*
	 * We were in fake suspend, so we are not going to save the
	 * register state as the guest checkpointed state (since
	 * we already have it), therefore we can now use any volatile GPR.
	 * In fact treclaim in fake suspend state doesn't modify
	 * any registers.
	 */

BEGIN_FTR_SECTION
	bl	pnv_power9_force_smt4_release
END_FTR_SECTION_IFSET(CPU_FTR_P9_TM_XER_SO_BUG)
	nop

4:
	mfspr	r3, SPRN_PSSCR
	/* PSSCR_FAKE_SUSPEND is a write-only bit, but clear it anyway */
	li	r0, PSSCR_FAKE_SUSPEND
	andc	r3, r3, r0
	mtspr	SPRN_PSSCR, r3

	/* Don't save TEXASR, use value from last exit in real suspend state */
	ld	r9, HSTATE_KVM_VCPU(r13)
	mfspr	r5, SPRN_TFHAR
	mfspr	r6, SPRN_TFIAR
	std	r5, VCPU_TFHAR(r9)
	std	r6, VCPU_TFIAR(r9)

	addi	r1, r1, PPC_MIN_STKFRM
	ld	r0, PPC_LR_STKOFF(r1)
	mtlr	r0
	blr

/*
 * Restore transactional state and TM-related registers.
 * Called with r3 pointing to the vcpu struct
 * and r4 containing the guest MSR value.
 * r5 is non-zero iff non-volatile register state needs to be maintained.
 * This potentially modifies all checkpointed registers.
 * It restores r1 and r2 from the PACA.
 */
_GLOBAL_TOC(kvmppc_restore_tm_hv)
EXPORT_SYMBOL_GPL(kvmppc_restore_tm_hv)
	/*
	 * If we are doing TM emulation for the guest on a POWER9 DD2,
	 * then we don't actually do a trechkpt -- we either set up
	 * fake-suspend mode, or emulate a TM rollback.
	 */
BEGIN_FTR_SECTION
	b	__kvmppc_restore_tm
END_FTR_SECTION_IFCLR(CPU_FTR_P9_TM_HV_ASSIST)
	mflr	r0
	std	r0, PPC_LR_STKOFF(r1)

	li	r0, 0
	stb	r0, HSTATE_FAKE_SUSPEND(r13)

	/* Turn on TM so we can restore TM SPRs */
	mfmsr	r5
	li	r0, 1
	rldimi	r5, r0, MSR_TM_LG, 63-MSR_TM_LG
	mtmsrd	r5

	/*
	 * The user may change these outside of a transaction, so they must
	 * always be context switched.
	 */
	ld	r5, VCPU_TFHAR(r3)
	ld	r6, VCPU_TFIAR(r3)
	ld	r7, VCPU_TEXASR(r3)
	mtspr	SPRN_TFHAR, r5
	mtspr	SPRN_TFIAR, r6
	mtspr	SPRN_TEXASR, r7

	rldicl. r5, r4, 64 - MSR_TS_S_LG, 62
	beqlr		/* TM not active in guest */

	/* Make sure the failure summary is set */
	oris	r7, r7, (TEXASR_FS)@h
	mtspr	SPRN_TEXASR, r7

	cmpwi	r5, 1		/* check for suspended state */
	bgt	10f
	stb	r5, HSTATE_FAKE_SUSPEND(r13)
	b	9f		/* and return */
10:	stdu	r1, -PPC_MIN_STKFRM(r1)
	/* guest is in transactional state, so simulate rollback */
	bl	kvmhv_emulate_tm_rollback
	nop
	addi	r1, r1, PPC_MIN_STKFRM
9:	ld	r0, PPC_LR_STKOFF(r1)
	mtlr	r0
	blr
#endif /* CONFIG_PPC_TRANSACTIONAL_MEM */

/*
 * We come here if we get any exception or interrupt while we are
 * executing host real mode code while in guest MMU context.
 * r12 is (CR << 32) | vector
 * r13 points to our PACA
 * r12 is saved in HSTATE_SCRATCH0(r13)
 * ctr is saved in HSTATE_SCRATCH1(r13) if RELOCATABLE
 * r9 is saved in HSTATE_SCRATCH2(r13)
 * r13 is saved in HSPRG1
 * cfar is saved in HSTATE_CFAR(r13)
 * ppr is saved in HSTATE_PPR(r13)
 */
kvmppc_bad_host_intr:
	/*
	 * Switch to the emergency stack, but start half-way down in
	 * case we were already on it.
	 */
	mr	r9, r1
	std	r1, PACAR1(r13)
	ld	r1, PACAEMERGSP(r13)
	subi	r1, r1, THREAD_SIZE/2 + INT_FRAME_SIZE
	std	r9, 0(r1)
	std	r0, GPR0(r1)
	std	r9, GPR1(r1)
	std	r2, GPR2(r1)
	SAVE_4GPRS(3, r1)
	SAVE_2GPRS(7, r1)
	srdi	r0, r12, 32
	clrldi	r12, r12, 32
	std	r0, _CCR(r1)
	std	r12, _TRAP(r1)
	andi.	r0, r12, 2
	beq	1f
	mfspr	r3, SPRN_HSRR0
	mfspr	r4, SPRN_HSRR1
	mfspr	r5, SPRN_HDAR
	mfspr	r6, SPRN_HDSISR
	b	2f
1:	mfspr	r3, SPRN_SRR0
	mfspr	r4, SPRN_SRR1
	mfspr	r5, SPRN_DAR
	mfspr	r6, SPRN_DSISR
2:	std	r3, _NIP(r1)
	std	r4, _MSR(r1)
	std	r5, _DAR(r1)
	std	r6, _DSISR(r1)
	ld	r9, HSTATE_SCRATCH2(r13)
	ld	r12, HSTATE_SCRATCH0(r13)
	GET_SCRATCH0(r0)
	SAVE_4GPRS(9, r1)
	std	r0, GPR13(r1)
	SAVE_NVGPRS(r1)
	ld	r5, HSTATE_CFAR(r13)
	std	r5, ORIG_GPR3(r1)
	mflr	r3
#ifdef CONFIG_RELOCATABLE
	ld	r4, HSTATE_SCRATCH1(r13)
#else
	mfctr	r4
#endif
	mfxer	r5
	lbz	r6, PACAIRQSOFTMASK(r13)
	std	r3, _LINK(r1)
	std	r4, _CTR(r1)
	std	r5, _XER(r1)
	std	r6, SOFTE(r1)
	ld	r2, PACATOC(r13)
	LOAD_REG_IMMEDIATE(3, 0x7265677368657265)
	std	r3, STACK_FRAME_OVERHEAD-16(r1)

	/*
	 * On POWER9 do a minimal restore of the MMU and call C code,
	 * which will print a message and panic.
	 * XXX On POWER7 and POWER8, we just spin here since we don't
	 * know what the other threads are doing (and we don't want to
	 * coordinate with them) - but at least we now have register state
	 * in memory that we might be able to look at from another CPU.
	 */
BEGIN_FTR_SECTION
	b	.
END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
	ld	r9, HSTATE_KVM_VCPU(r13)
	ld	r10, VCPU_KVM(r9)

	li	r0, 0
	mtspr	SPRN_AMR, r0
	mtspr	SPRN_IAMR, r0
	mtspr	SPRN_CIABR, r0
	mtspr	SPRN_DAWRX, r0

BEGIN_MMU_FTR_SECTION
	b	4f
END_MMU_FTR_SECTION_IFSET(MMU_FTR_TYPE_RADIX)

	slbmte	r0, r0
	slbia
	ptesync
	ld	r8, PACA_SLBSHADOWPTR(r13)
	.rept	SLB_NUM_BOLTED
	li	r3, SLBSHADOW_SAVEAREA
	LDX_BE	r5, r8, r3
	addi	r3, r3, 8
	LDX_BE	r6, r8, r3
	andis.	r7, r5, SLB_ESID_V@h
	beq	3f
	slbmte	r6, r5
3:	addi	r8, r8, 16
	.endr

4:	lwz	r7, KVM_HOST_LPID(r10)
	mtspr	SPRN_LPID, r7
	mtspr	SPRN_PID, r0
	ld	r8, KVM_HOST_LPCR(r10)
	mtspr	SPRN_LPCR, r8
	isync
	li	r0, KVM_GUEST_MODE_NONE
	stb	r0, HSTATE_IN_GUEST(r13)

	/*
	 * Turn on the MMU and jump to C code
	 */
	bcl	20, 31, .+4
5:	mflr	r3
	addi	r3, r3, 9f - 5b
	li	r4, -1
	rldimi	r3, r4, 62, 0	/* ensure 0xc000000000000000 bits are set */
	ld	r4, PACAKMSR(r13)
	mtspr	SPRN_SRR0, r3
	mtspr	SPRN_SRR1, r4
	RFI_TO_KERNEL
9:	addi	r3, r1, STACK_FRAME_OVERHEAD
	bl	kvmppc_bad_interrupt
	b	9b

/*
 * This mimics the MSR transition on IRQ delivery.  The new guest MSR is taken
 * from VCPU_INTR_MSR and is modified based on the required TM state changes.
 *   r11 has the guest MSR value (in/out)
 *   r9 has a vcpu pointer (in)
 *   r0 is used as a scratch register
 */
kvmppc_msr_interrupt:
	rldicl	r0, r11, 64 - MSR_TS_S_LG, 62
	cmpwi	r0, 2 /* Check if we are in transactional state..  */
	ld	r11, VCPU_INTR_MSR(r9)
	bne	1f
	/* ... if transactional, change to suspended */
	li	r0, 1
1:	rldimi	r11, r0, MSR_TS_S_LG, 63 - MSR_TS_T_LG
	blr

/*
 * Load up guest PMU state.  R3 points to the vcpu struct.
 */
_GLOBAL(kvmhv_load_guest_pmu)
EXPORT_SYMBOL_GPL(kvmhv_load_guest_pmu)
	mr	r4, r3
	mflr	r0
	li	r3, 1
	sldi	r3, r3, 31		/* MMCR0_FC (freeze counters) bit */
	mtspr	SPRN_MMCR0, r3		/* freeze all counters, disable ints */
	isync
BEGIN_FTR_SECTION
	ld	r3, VCPU_MMCR(r4)
	andi.	r5, r3, MMCR0_PMAO_SYNC | MMCR0_PMAO
	cmpwi	r5, MMCR0_PMAO
	beql	kvmppc_fix_pmao
END_FTR_SECTION_IFSET(CPU_FTR_PMAO_BUG)
	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)
	mtspr	SPRN_PMC1, r3
	mtspr	SPRN_PMC2, r5
	mtspr	SPRN_PMC3, r6
	mtspr	SPRN_PMC4, r7
	mtspr	SPRN_PMC5, r8
	mtspr	SPRN_PMC6, r9
	ld	r3, VCPU_MMCR(r4)
	ld	r5, VCPU_MMCR + 8(r4)
	ld	r6, VCPU_MMCR + 16(r4)
	ld	r7, VCPU_SIAR(r4)
	ld	r8, VCPU_SDAR(r4)
	mtspr	SPRN_MMCR1, r5
	mtspr	SPRN_MMCRA, r6
	mtspr	SPRN_SIAR, r7
	mtspr	SPRN_SDAR, r8
BEGIN_FTR_SECTION
	ld	r5, VCPU_MMCR + 24(r4)
	ld	r6, VCPU_SIER(r4)
	mtspr	SPRN_MMCR2, r5
	mtspr	SPRN_SIER, r6
BEGIN_FTR_SECTION_NESTED(96)
	lwz	r7, VCPU_PMC + 24(r4)
	lwz	r8, VCPU_PMC + 28(r4)
	ld	r9, VCPU_MMCR + 32(r4)
	mtspr	SPRN_SPMC1, r7
	mtspr	SPRN_SPMC2, r8
	mtspr	SPRN_MMCRS, r9
END_FTR_SECTION_NESTED(CPU_FTR_ARCH_300, 0, 96)
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
	mtspr	SPRN_MMCR0, r3
	isync
	mtlr	r0
	blr

/*
 * Reload host PMU state saved in the PACA by kvmhv_save_host_pmu.
 */
_GLOBAL(kvmhv_load_host_pmu)
EXPORT_SYMBOL_GPL(kvmhv_load_host_pmu)
	mflr	r0
	lbz	r4, PACA_PMCINUSE(r13) /* is the host using the PMU? */
	cmpwi	r4, 0
	beq	23f			/* skip if not */
BEGIN_FTR_SECTION
	ld	r3, HSTATE_MMCR0(r13)
	andi.	r4, r3, MMCR0_PMAO_SYNC | MMCR0_PMAO
	cmpwi	r4, MMCR0_PMAO
	beql	kvmppc_fix_pmao
END_FTR_SECTION_IFSET(CPU_FTR_PMAO_BUG)
	lwz	r3, HSTATE_PMC1(r13)
	lwz	r4, HSTATE_PMC2(r13)
	lwz	r5, HSTATE_PMC3(r13)
	lwz	r6, HSTATE_PMC4(r13)
	lwz	r8, HSTATE_PMC5(r13)
	lwz	r9, HSTATE_PMC6(r13)
	mtspr	SPRN_PMC1, r3
	mtspr	SPRN_PMC2, r4
	mtspr	SPRN_PMC3, r5
	mtspr	SPRN_PMC4, r6
	mtspr	SPRN_PMC5, r8
	mtspr	SPRN_PMC6, r9
	ld	r3, HSTATE_MMCR0(r13)
	ld	r4, HSTATE_MMCR1(r13)
	ld	r5, HSTATE_MMCRA(r13)
	ld	r6, HSTATE_SIAR(r13)
	ld	r7, HSTATE_SDAR(r13)
	mtspr	SPRN_MMCR1, r4
	mtspr	SPRN_MMCRA, r5
	mtspr	SPRN_SIAR, r6
	mtspr	SPRN_SDAR, r7
BEGIN_FTR_SECTION
	ld	r8, HSTATE_MMCR2(r13)
	ld	r9, HSTATE_SIER(r13)
	mtspr	SPRN_MMCR2, r8
	mtspr	SPRN_SIER, r9
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
	mtspr	SPRN_MMCR0, r3
	isync
	mtlr	r0
23:	blr

/*
 * Save guest PMU state into the vcpu struct.
 * r3 = vcpu, r4 = full save flag (PMU in use flag set in VPA)
 */
_GLOBAL(kvmhv_save_guest_pmu)
EXPORT_SYMBOL_GPL(kvmhv_save_guest_pmu)
	mr	r9, r3
	mr	r8, r4
BEGIN_FTR_SECTION
	/*
	 * POWER8 seems to have a hardware bug where setting
	 * MMCR0[PMAE] along with MMCR0[PMC1CE] and/or MMCR0[PMCjCE]
	 * when some counters are already negative doesn't seem
	 * to cause a performance monitor alert (and hence interrupt).
	 * The effect of this is that when saving the PMU state,
	 * if there is no PMU alert pending when we read MMCR0
	 * before freezing the counters, but one becomes pending
	 * before we read the counters, we lose it.
	 * To work around this, we need a way to freeze the counters
	 * before reading MMCR0.  Normally, freezing the counters
	 * is done by writing MMCR0 (to set MMCR0[FC]) which
	 * unavoidably writes MMCR0[PMA0] as well.  On POWER8,
	 * we can also freeze the counters using MMCR2, by writing
	 * 1s to all the counter freeze condition bits (there are
	 * 9 bits each for 6 counters).
	 */
	li	r3, -1			/* set all freeze bits */
	clrrdi	r3, r3, 10
	mfspr	r10, SPRN_MMCR2
	mtspr	SPRN_MMCR2, r3
	isync
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
	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 */
	mfspr	r6, SPRN_MMCRA
	/* Clear MMCRA in order to disable SDAR updates */
	li	r7, 0
	mtspr	SPRN_MMCRA, r7
	isync
	cmpwi	r8, 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
	mfspr	r7, SPRN_SIAR
	mfspr	r8, SPRN_SDAR
	std	r4, VCPU_MMCR(r9)
	std	r5, VCPU_MMCR + 8(r9)
	std	r6, VCPU_MMCR + 16(r9)
BEGIN_FTR_SECTION
	std	r10, VCPU_MMCR + 24(r9)
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
	std	r7, VCPU_SIAR(r9)
	std	r8, VCPU_SDAR(r9)
	mfspr	r3, SPRN_PMC1
	mfspr	r4, SPRN_PMC2
	mfspr	r5, SPRN_PMC3
	mfspr	r6, SPRN_PMC4
	mfspr	r7, SPRN_PMC5
	mfspr	r8, SPRN_PMC6
	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)
BEGIN_FTR_SECTION
	mfspr	r5, SPRN_SIER
	std	r5, VCPU_SIER(r9)
BEGIN_FTR_SECTION_NESTED(96)
	mfspr	r6, SPRN_SPMC1
	mfspr	r7, SPRN_SPMC2
	mfspr	r8, SPRN_MMCRS
	stw	r6, VCPU_PMC + 24(r9)
	stw	r7, VCPU_PMC + 28(r9)
	std	r8, VCPU_MMCR + 32(r9)
	lis	r4, 0x8000
	mtspr	SPRN_MMCRS, r4
END_FTR_SECTION_NESTED(CPU_FTR_ARCH_300, 0, 96)
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
22:	blr

/*
 * This works around a hardware bug on POWER8E processors, where
 * writing a 1 to the MMCR0[PMAO] bit doesn't generate a
 * performance monitor interrupt.  Instead, when we need to have
 * an interrupt pending, we have to arrange for a counter to overflow.
 */
kvmppc_fix_pmao:
	li	r3, 0
	mtspr	SPRN_MMCR2, r3
	lis	r3, (MMCR0_PMXE | MMCR0_FCECE)@h
	ori	r3, r3, MMCR0_PMCjCE | MMCR0_C56RUN
	mtspr	SPRN_MMCR0, r3
	lis	r3, 0x7fff
	ori	r3, r3, 0xffff
	mtspr	SPRN_PMC6, r3
	isync
	blr

#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
/*
 * Start timing an activity
 * r3 = pointer to time accumulation struct, r4 = vcpu
 */
kvmhv_start_timing:
	ld	r5, HSTATE_KVM_VCORE(r13)
	ld	r6, VCORE_TB_OFFSET_APPL(r5)
	mftb	r5
	subf	r5, r6, r5	/* subtract current timebase offset */
	std	r3, VCPU_CUR_ACTIVITY(r4)
	std	r5, VCPU_ACTIVITY_START(r4)
	blr

/*
 * Accumulate time to one activity and start another.
 * r3 = pointer to new time accumulation struct, r4 = vcpu
 */
kvmhv_accumulate_time:
	ld	r5, HSTATE_KVM_VCORE(r13)
	ld	r8, VCORE_TB_OFFSET_APPL(r5)
	ld	r5, VCPU_CUR_ACTIVITY(r4)
	ld	r6, VCPU_ACTIVITY_START(r4)
	std	r3, VCPU_CUR_ACTIVITY(r4)
	mftb	r7
	subf	r7, r8, r7	/* subtract current timebase offset */
	std	r7, VCPU_ACTIVITY_START(r4)
	cmpdi	r5, 0
	beqlr
	subf	r3, r6, r7
	ld	r8, TAS_SEQCOUNT(r5)
	cmpdi	r8, 0
	addi	r8, r8, 1
	std	r8, TAS_SEQCOUNT(r5)
	lwsync
	ld	r7, TAS_TOTAL(r5)
	add	r7, r7, r3
	std	r7, TAS_TOTAL(r5)
	ld	r6, TAS_MIN(r5)
	ld	r7, TAS_MAX(r5)
	beq	3f
	cmpd	r3, r6
	bge	1f
3:	std	r3, TAS_MIN(r5)
1:	cmpd	r3, r7
	ble	2f
	std	r3, TAS_MAX(r5)
2:	lwsync
	addi	r8, r8, 1
	std	r8, TAS_SEQCOUNT(r5)
	blr
#endif