summaryrefslogtreecommitdiff
path: root/arch/powerpc/kvm/book3s_hv_rmhandlers.S
diff options
context:
space:
mode:
Diffstat (limited to 'arch/powerpc/kvm/book3s_hv_rmhandlers.S')
-rw-r--r--arch/powerpc/kvm/book3s_hv_rmhandlers.S1577
1 files changed, 1577 insertions, 0 deletions
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
new file mode 100644
index 000000000000..44d8829334ab
--- /dev/null
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -0,0 +1,1577 @@
+/*
+ * 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>
+#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>
+
+/*****************************************************************************
+ * *
+ * Real Mode handlers that need to be in the linear mapping *
+ * *
+ ****************************************************************************/
+
+ .globl kvmppc_skip_interrupt
+kvmppc_skip_interrupt:
+ mfspr r13,SPRN_SRR0
+ addi r13,r13,4
+ mtspr SPRN_SRR0,r13
+ GET_SCRATCH0(r13)
+ rfid
+ b .
+
+ .globl kvmppc_skip_Hinterrupt
+kvmppc_skip_Hinterrupt:
+ mfspr r13,SPRN_HSRR0
+ addi r13,r13,4
+ mtspr SPRN_HSRR0,r13
+ GET_SCRATCH0(r13)
+ hrfid
+ b .
+
+/*
+ * 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(kvmppc_hv_entry_trampoline)
+ mfmsr r10
+ LOAD_REG_ADDR(r5, kvmppc_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
+
+#define ULONG_SIZE 8
+#define VCPU_GPR(n) (VCPU_GPRS + (n * ULONG_SIZE))
+
+/******************************************************************************
+ * *
+ * Entry code *
+ * *
+ *****************************************************************************/
+
+#define XICS_XIRR 4
+#define XICS_QIRR 0xc
+
+/*
+ * 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
+ ld r2,PACATOC(r13)
+
+ /* were we napping due to cede? */
+ lbz r0,HSTATE_NAPPING(r13)
+ cmpwi r0,0
+ bne kvm_end_cede
+
+ /* get vcpu pointer */
+ ld r4, HSTATE_KVM_VCPU(r13)
+
+ /* We got here with an IPI; clear it */
+ ld r5, HSTATE_XICS_PHYS(r13)
+ li r0, 0xff
+ li r6, XICS_QIRR
+ li r7, XICS_XIRR
+ lwzcix r8, r5, r7 /* ack the interrupt */
+ sync
+ stbcix r0, r5, r6 /* clear it */
+ stwcix r8, r5, r7 /* EOI it */
+
+.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
+ std r0, HSTATE_VMHANDLER(r13)
+
+ 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)
+
+ /* 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)
+BEGIN_FTR_SECTION
+ lwz r10, VCPU_PMC + 24(r4)
+ lwz r11, VCPU_PMC + 28(r4)
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
+ mtspr SPRN_PMC1, r3
+ mtspr SPRN_PMC2, r5
+ mtspr SPRN_PMC3, r6
+ mtspr SPRN_PMC4, r7
+ 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, VCPU_MMCR(r4)
+ ld r5, VCPU_MMCR + 8(r4)
+ ld r6, VCPU_MMCR + 16(r4)
+ mtspr SPRN_MMCR1, r5
+ mtspr SPRN_MMCRA, r6
+ mtspr SPRN_MMCR0, r3
+ isync
+
+ /* Load up FP, VMX and VSX registers */
+ bl kvmppc_load_fp
+
+BEGIN_FTR_SECTION
+ /* Switch DSCR to guest value */
+ ld r5, VCPU_DSCR(r4)
+ mtspr SPRN_DSCR, r5
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
+
+ /*
+ * 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)
+
+ /* 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)
+25:
+ /* Load up DAR and DSISR */
+ ld r5, VCPU_DAR(r4)
+ lwz r6, VCPU_DSISR(r4)
+ mtspr SPRN_DAR, r5
+ mtspr SPRN_DSISR, r6
+
+ /* Set partition DABR */
+ li r5,3
+ ld r6,VCPU_DABR(r4)
+ mtspr SPRN_DABRX,r5
+ mtspr SPRN_DABR,r6
+
+BEGIN_FTR_SECTION
+ /* 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
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
+
+ /* Clear out SLB */
+ li r6,0
+ slbmte r6,r6
+ slbia
+ ptesync
+
+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.
+ */
+ /* 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. */
+ ld r9,VCPU_KVM(r4) /* pointer to struct kvm */
+ lwz r6,VCPU_PTID(r4)
+ cmpwi r6,0
+ bne 20f
+ 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
+ li r0,1
+ 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
+
+ /* Set LPCR and RMOR. */
+10: ld r8,KVM_LPCR(r9)
+ mtspr SPRN_LPCR,r8
+ ld r8,KVM_RMOR(r9)
+ mtspr SPRN_RMOR,r8
+ isync
+
+ /* Check if HDEC expires soon */
+ mfspr r3,SPRN_HDEC
+ cmpwi r3,10
+ li r12,BOOK3S_INTERRUPT_HV_DECREMENTER
+ mr r9,r4
+ blt hdec_soon
+
+ /*
+ * Invalidate the TLB if we could possibly have stale TLB
+ * entries for this partition on this core due to the use
+ * of tlbiel.
+ * XXX maybe only need this on primary thread?
+ */
+ ld r9,VCPU_KVM(r4) /* pointer to struct kvm */
+ lwz r5,VCPU_VCPUID(r4)
+ lhz r6,PACAPACAINDEX(r13)
+ rldimi r6,r5,0,62 /* XXX map as if threads 1:1 p:v */
+ lhz r8,VCPU_LAST_CPU(r4)
+ sldi r7,r6,1 /* see if this is the same vcpu */
+ add r7,r7,r9 /* as last ran on this pcpu */
+ lhz r0,KVM_LAST_VCPU(r7)
+ cmpw r6,r8 /* on the same cpu core as last time? */
+ bne 3f
+ cmpw r0,r5 /* same vcpu as this core last ran? */
+ beq 1f
+3: sth r6,VCPU_LAST_CPU(r4) /* if not, invalidate partition TLB */
+ sth r5,KVM_LAST_VCPU(r7)
+ li r6,128
+ mtctr r6
+ li r7,0x800 /* IS field = 0b10 */
+ ptesync
+2: tlbiel r7
+ addi r7,r7,0x1000
+ bdnz 2b
+ ptesync
+1:
+
+ /* 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
+ 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)
+ lwz r8,PACA_LOCK_TOKEN(r13)
+24: lwarx r0,0,r3
+ cmpwi r0,0
+ bne 24b
+ stwcx. r8,0,r3
+ bne 24b
+ isync
+
+ ld r7,KVM_LPCR(r9) /* use kvm->arch.lpcr to store 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 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
+
+ /* Load up guest SLB entries */
+31: 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:
+
+ /* 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
+
+kvmppc_cede_reentry: /* r4 = vcpu, r13 = paca */
+ ld r6, VCPU_SRR0(r4)
+ ld r7, VCPU_SRR1(r4)
+ 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
+
+ /* Check if we can deliver an external or decrementer interrupt now */
+ ld r0,VCPU_PENDING_EXC(r4)
+ li r8,(1 << BOOK3S_IRQPRIO_EXTERNAL)
+ oris r8,r8,(1 << BOOK3S_IRQPRIO_EXTERNAL_LEVEL)@h
+ 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
+ li r0,0
+ stb r0,VCPU_CEDED(r4) /* cancel cede */
+
+fast_guest_return:
+ mtspr SPRN_HSRR0,r10
+ mtspr SPRN_HSRR1,r11
+
+ /* Activate guest mode, so faults get handled by KVM */
+ li r9, KVM_GUEST_MODE_GUEST
+ stb r9, HSTATE_IN_GUEST(r13)
+
+ /* Enter guest */
+
+ ld r5, VCPU_LR(r4)
+ lwz r6, VCPU_CR(r4)
+ mtlr r5
+ mtcr r6
+
+ ld r0, VCPU_GPR(r0)(r4)
+ 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)
+
+ ld r4, VCPU_GPR(r4)(r4)
+
+ hrfid
+ b .
+
+/******************************************************************************
+ * *
+ * Exit code *
+ * *
+ *****************************************************************************/
+
+/*
+ * We come here from the first-level interrupt handlers.
+ */
+ .globl kvmppc_interrupt
+kvmppc_interrupt:
+ /*
+ * 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)
+ 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_HOST_R2(r13)
+ std r0, VCPU_GPR(r9)(r9)
+ std r10, VCPU_GPR(r10)(r9)
+ std r11, VCPU_GPR(r11)(r9)
+ ld r3, HSTATE_SCRATCH0(r13)
+ lwz r4, HSTATE_SCRATCH1(r13)
+ std r3, VCPU_GPR(r12)(r9)
+ stw r4, VCPU_CR(r9)
+
+ /* 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
+ std r3, VCPU_GPR(r13)(r9)
+ std r4, VCPU_LR(r9)
+
+ /* Unset guest mode */
+ li r0, KVM_GUEST_MODE_NONE
+ stb r0, HSTATE_IN_GUEST(r13)
+
+ stw r12,VCPU_TRAP(r9)
+
+ /* 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:
+ /* See if this is something we can handle in real mode */
+ cmpwi r12,BOOK3S_INTERRUPT_SYSCALL
+ beq hcall_try_real_mode
+
+ /* Check for mediated interrupts (could be done earlier really ...) */
+BEGIN_FTR_SECTION
+ cmpwi r12,BOOK3S_INTERRUPT_EXTERNAL
+ bne+ 1f
+ andi. r0,r11,MSR_EE
+ beq 1f
+ mfspr r5,SPRN_LPCR
+ andi. r0,r5,LPCR_MER
+ bne bounce_ext_interrupt
+1:
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
+
+hcall_real_cont: /* r9 = vcpu, r12 = trap, r13 = paca */
+ /* Save DEC */
+ mfspr r5,SPRN_DEC
+ mftb r6
+ extsw r5,r5
+ add r5,r5,r6
+ std r5,VCPU_DEC_EXPIRES(r9)
+
+ /* Save HEIR (HV emulation assist reg) in last_inst
+ if this is an HEI (HV emulation interrupt, e40) */
+ li r3,-1
+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)
+
+ /* Save more register state */
+ mfxer r5
+ mfdar r6
+ mfdsisr r7
+ mfctr r8
+
+ stw r5, VCPU_XER(r9)
+ std r6, VCPU_DAR(r9)
+ stw r7, VCPU_DSISR(r9)
+ std r8, VCPU_CTR(r9)
+ /* grab HDAR & HDSISR if HV data storage interrupt (HDSI) */
+BEGIN_FTR_SECTION
+ cmpwi r12,BOOK3S_INTERRUPT_H_DATA_STORAGE
+ beq 6f
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
+7: std r6, VCPU_FAULT_DAR(r9)
+ stw r7, VCPU_FAULT_DSISR(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:
+ /* 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
+ */
+BEGIN_FTR_SECTION
+ 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
+END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_201)
+
+ /* Clear out SLB */
+ li r5,0
+ slbmte r5,r5
+ slbia
+ ptesync
+
+hdec_soon: /* r9 = vcpu, r12 = trap, r13 = paca */
+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.
+ */
+ /* 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
+ lwsync
+
+ /*
+ * 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.
+ */
+ cmpwi r3,0x100 /* Are we the first here? */
+ bge 43f
+ cmpwi r3,1 /* Are any other threads in the guest? */
+ ble 43f
+ cmpwi r12,BOOK3S_INTERRUPT_HV_DECREMENTER
+ beq 40f
+ li r0,0
+ mtspr SPRN_HDEC,r0
+40:
+ /*
+ * 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
+ sldi r0,r0,r4
+ 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
+ li r7,XICS_QIRR
+ stbcix r0,r7,r8 /* trigger the IPI */
+44: srdi. r3,r3,1
+ addi r6,r6,PACA_SIZE
+ bne 42b
+
+ /* Secondary threads wait for primary to do partition switch */
+43: ld r4,VCPU_KVM(r9) /* pointer to struct kvm */
+ 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 */
+ 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
+ li r0,0
+ stb r0,VCORE_IN_GUEST(r5)
+ lis r8,0x7fff /* MAX_INT@h */
+ mtspr SPRN_HDEC,r8
+
+16: ld r8,KVM_HOST_LPCR(r4)
+ mtspr SPRN_LPCR,r8
+ isync
+ 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 */
+ lwz r8,PACA_LOCK_TOKEN(r13)
+ 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
+
+ /* load host SLB entries */
+33: ld r8,PACA_SLBSHADOWPTR(r13)
+
+ .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
+
+ /* Save and reset AMR and UAMOR before turning on the MMU */
+BEGIN_FTR_SECTION
+ 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
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
+
+ /* Restore host DABR and DABRX */
+ ld r5,HSTATE_DABR(r13)
+ li r6,7
+ mtspr SPRN_DABR,r5
+ mtspr SPRN_DABRX,r6
+
+ /* Switch DSCR back to host value */
+BEGIN_FTR_SECTION
+ mfspr r8, SPRN_DSCR
+ ld r7, HSTATE_DSCR(r13)
+ std r8, VCPU_DSCR(r7)
+ mtspr SPRN_DSCR, r7
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
+
+ /* 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)
+
+ /* 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)
+25:
+ /* Save PMU registers if requested */
+ /* r8 and cr0.eq are live here */
+ 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 */
+ isync
+ 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
+ mfspr r6, SPRN_MMCRA
+ std r4, VCPU_MMCR(r9)
+ std r5, VCPU_MMCR + 8(r9)
+ std r6, VCPU_MMCR + 16(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
+BEGIN_FTR_SECTION
+ mfspr r10, SPRN_PMC7
+ mfspr r11, SPRN_PMC8
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
+ 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
+ stw r10, VCPU_PMC + 24(r9)
+ stw r11, VCPU_PMC + 28(r9)
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
+22:
+ /* save FP state */
+ mr r3, r9
+ bl .kvmppc_save_fp
+
+ /* Secondary threads go off to take a nap on POWER7 */
+BEGIN_FTR_SECTION
+ lwz r0,VCPU_PTID(r3)
+ cmpwi r0,0
+ bne secondary_nap
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
+
+ /*
+ * 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 the interrupt vector address
+ * which we have in r12. 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_interrupts.S code here.
+ */
+ ld r8, HSTATE_VMHANDLER(r13)
+ ld r7, HSTATE_HOST_MSR(r13)
+
+ cmpwi r12, BOOK3S_INTERRUPT_EXTERNAL
+ beq 11f
+ cmpwi r12, BOOK3S_INTERRUPT_MACHINE_CHECK
+
+ /* RFI into the highmem handler, or branch to interrupt handler */
+12: mfmsr r6
+ mtctr r12
+ li r0, MSR_RI
+ andc r6, r6, r0
+ mtmsrd r6, 1 /* Clear RI in MSR */
+ mtsrr0 r8
+ mtsrr1 r7
+ beqctr
+ RFI
+
+11:
+BEGIN_FTR_SECTION
+ b 12b
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
+ mtspr SPRN_HSRR0, r8
+ mtspr SPRN_HSRR1, r7
+ ba 0x500
+
+6: mfspr r6,SPRN_HDAR
+ mfspr r7,SPRN_HDSISR
+ b 7b
+
+/*
+ * 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:
+ ld r3,VCPU_GPR(r3)(r9)
+ andi. r0,r11,MSR_PR
+ bne hcall_real_cont
+ clrrdi r3,r3,2
+ cmpldi r3,hcall_real_table_end - hcall_real_table
+ bge hcall_real_cont
+ LOAD_REG_ADDR(r4, hcall_real_table)
+ lwzx r3,r3,r4
+ cmpwi r3,0
+ beq hcall_real_cont
+ add r3,r3,r4
+ mtctr r3
+ 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
+
+ /* 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 hcall_real_cont
+
+ .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 */
+ .long .kvmppc_h_put_tce - hcall_real_table
+ .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 */
+ .long 0 /* 0x64 */
+ .long 0 /* 0x68 */
+ .long 0 /* 0x6c */
+ .long 0 /* 0x70 */
+ .long 0 /* 0x74 */
+ .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 .kvmppc_h_cede - hcall_real_table
+ .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:
+
+ignore_hdec:
+ mr r4,r9
+ b fast_guest_return
+
+bounce_ext_interrupt:
+ mr r4,r9
+ 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
+ b fast_guest_return
+
+_GLOBAL(kvmppc_h_set_dabr)
+ std r4,VCPU_DABR(r3)
+ mtspr SPRN_DABR,r4
+ li r3,0
+ blr
+
+_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
+ bne 1f
+ li r0,0 /* set trap to 0 to say hcall is handled */
+ stw r0,VCPU_TRAP(r3)
+ li r0,H_SUCCESS
+ std r0,VCPU_GPR(r3)(r3)
+BEGIN_FTR_SECTION
+ b 2f /* just send it up to host on 970 */
+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
+ PPC_POPCNTW(r7,r4)
+ cmpw r7,r8
+ bge 2f
+ 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 */
+ 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
+
+ /*
+ * Take a nap until a decrementer or external interrupt occurs,
+ * with PECE1 (wake on decr) and PECE0 (wake on external) set in LPCR
+ */
+ li r0,0x80
+ stb r0,PACAPROCSTART(r13)
+ 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:
+ /* Woken by external or decrementer interrupt */
+ ld r1, HSTATE_HOST_R1(r13)
+ ld r2, PACATOC(r13)
+
+ /* If we're a secondary thread and we got here by an IPI, ack it */
+ ld r4,HSTATE_KVM_VCPU(r13)
+ lwz r3,VCPU_PTID(r4)
+ cmpwi r3,0
+ beq 27f
+ mfspr r3,SPRN_SRR1
+ rlwinm r3,r3,44-31,0x7 /* extract wake reason field */
+ cmpwi r3,4 /* was it an external interrupt? */
+ bne 27f
+ ld r5, HSTATE_XICS_PHYS(r13)
+ li r0,0xff
+ li r6,XICS_QIRR
+ li r7,XICS_XIRR
+ lwzcix r8,r5,r7 /* ack the interrupt */
+ sync
+ stbcix r0,r5,r6 /* clear it */
+ stwcix r8,r5,r7 /* EOI it */
+27:
+ /* load up FP state */
+ bl kvmppc_load_fp
+
+ /* 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)
+
+ /* 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)
+
+ /* 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 */
+1: 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 */
+2: li r3,H_TOO_HARD
+ 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
+ ld r11,PACA_SLBSHADOWPTR(r13)
+
+ .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
+
+secondary_nap:
+ /* Clear any pending IPI - assume we're a secondary 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_QIRR
+ 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
+
+ li r3, LPCR_PECE0
+ mfspr r4, SPRN_LPCR
+ rlwimi r4, r3, 0, LPCR_PECE0 | LPCR_PECE1
+ mtspr SPRN_LPCR, r4
+ isync
+ li r0, 0
+ std r0, HSTATE_SCRATCH0(r13)
+ ptesync
+ ld r0, HSTATE_SCRATCH0(r13)
+1: cmpd r0, r0
+ bne 1b
+ nap
+ b .
+
+/*
+ * Save away FP, VMX and VSX registers.
+ * r3 = vcpu pointer
+ */
+_GLOBAL(kvmppc_save_fp)
+ 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
+#ifdef CONFIG_VSX
+BEGIN_FTR_SECTION
+ reg = 0
+ .rept 32
+ li r6,reg*16+VCPU_VSRS
+ STXVD2X(reg,r6,r3)
+ reg = reg + 1
+ .endr
+FTR_SECTION_ELSE
+#endif
+ reg = 0
+ .rept 32
+ stfd reg,reg*8+VCPU_FPRS(r3)
+ reg = reg + 1
+ .endr
+#ifdef CONFIG_VSX
+ALT_FTR_SECTION_END_IFSET(CPU_FTR_VSX)
+#endif
+ mffs fr0
+ stfd fr0,VCPU_FPSCR(r3)
+
+#ifdef CONFIG_ALTIVEC
+BEGIN_FTR_SECTION
+ reg = 0
+ .rept 32
+ li r6,reg*16+VCPU_VRS
+ stvx reg,r6,r3
+ reg = reg + 1
+ .endr
+ mfvscr vr0
+ li r6,VCPU_VSCR
+ stvx vr0,r6,r3
+END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
+#endif
+ mfspr r6,SPRN_VRSAVE
+ stw r6,VCPU_VRSAVE(r3)
+ mtmsrd r9
+ isync
+ blr
+
+/*
+ * Load up FP, VMX and VSX registers
+ * r4 = vcpu pointer
+ */
+ .globl kvmppc_load_fp
+kvmppc_load_fp:
+ 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
+ lfd fr0,VCPU_FPSCR(r4)
+ MTFSF_L(fr0)
+#ifdef CONFIG_VSX
+BEGIN_FTR_SECTION
+ reg = 0
+ .rept 32
+ li r7,reg*16+VCPU_VSRS
+ LXVD2X(reg,r7,r4)
+ reg = reg + 1
+ .endr
+FTR_SECTION_ELSE
+#endif
+ reg = 0
+ .rept 32
+ lfd reg,reg*8+VCPU_FPRS(r4)
+ reg = reg + 1
+ .endr
+#ifdef CONFIG_VSX
+ALT_FTR_SECTION_END_IFSET(CPU_FTR_VSX)
+#endif
+
+#ifdef CONFIG_ALTIVEC
+BEGIN_FTR_SECTION
+ li r7,VCPU_VSCR
+ lvx vr0,r7,r4
+ mtvscr vr0
+ reg = 0
+ .rept 32
+ li r7,reg*16+VCPU_VRS
+ lvx reg,r7,r4
+ reg = reg + 1
+ .endr
+END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
+#endif
+ lwz r7,VCPU_VRSAVE(r4)
+ mtspr SPRN_VRSAVE,r7
+ blr