3494 lines
85 KiB
ArmAsm
3494 lines
85 KiB
ArmAsm
/*
|
|
* 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>
|
|
#include <asm/kvm_book3s_asm.h>
|
|
#include <asm/book3s/64/mmu-hash.h>
|
|
#include <asm/tm.h>
|
|
#include <asm/opal.h>
|
|
#include <asm/xive-regs.h>
|
|
#include <asm/thread_info.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
|
|
|
|
/* Stack frame offsets for kvmppc_hv_entry */
|
|
#define SFS 160
|
|
#define STACK_SLOT_TRAP (SFS-4)
|
|
#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)
|
|
|
|
/*
|
|
* 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 */
|
|
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
|
|
23:
|
|
|
|
/*
|
|
* 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 nap mode.
|
|
* Relocation is off and most register values are lost.
|
|
* r13 points to the PACA.
|
|
* r3 contains the SRR1 wakeup value, SRR1 is trashed.
|
|
*/
|
|
.globl kvm_start_guest
|
|
kvm_start_guest:
|
|
/* Set runlatch bit the minute you wake up from nap */
|
|
mfspr r0, SPRN_CTRLF
|
|
ori r0, r0, 1
|
|
mtspr SPRN_CTRLT, r0
|
|
|
|
/*
|
|
* Could avoid this and pass it through in r3. For now,
|
|
* code expects it to be in SRR1.
|
|
*/
|
|
mtspr SPRN_SRR1,r3
|
|
|
|
ld r2,PACATOC(r13)
|
|
|
|
li r0,0
|
|
stb r0,PACA_FTRACE_ENABLED(r13)
|
|
|
|
li r0,KVM_HWTHREAD_IN_KVM
|
|
stb r0,HSTATE_HWTHREAD_STATE(r13)
|
|
|
|
/* NV GPR values from power7_idle() will no longer be valid */
|
|
li r0,1
|
|
stb r0,PACA_NAPSTATELOST(r13)
|
|
|
|
/* were we napping due to cede? */
|
|
lbz r0,HSTATE_NAPPING(r13)
|
|
cmpwi r0,NAPPING_CEDE
|
|
beq kvm_end_cede
|
|
cmpwi r0,NAPPING_NOVCPU
|
|
beq kvm_novcpu_wakeup
|
|
|
|
ld r1,PACAEMERGSP(r13)
|
|
subi r1,r1,STACK_FRAME_OVERHEAD
|
|
|
|
/*
|
|
* 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
|
|
/*
|
|
* We jump to pnv_wakeup_loss, which will return to the caller
|
|
* of power7_nap in the powernv cpu offline loop. The value we
|
|
* put in r3 becomes the return value for power7_nap. pnv_wakeup_loss
|
|
* requires SRR1 in r12.
|
|
*/
|
|
li r3, LPCR_PECE0
|
|
mfspr r4, SPRN_LPCR
|
|
rlwimi r4, r3, 0, LPCR_PECE0 | LPCR_PECE1
|
|
mtspr SPRN_LPCR, r4
|
|
li r3, 0
|
|
mfspr r12,SPRN_SRR1
|
|
b pnv_wakeup_loss
|
|
|
|
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, (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
|
|
|
|
/* Use cr7 as an indication of radix mode */
|
|
ld r5, HSTATE_KVM_VCORE(r13)
|
|
ld r9, VCORE_KVM(r5) /* pointer to struct kvm */
|
|
lbz r0, KVM_RADIX(r9)
|
|
cmpwi cr7, r0, 0
|
|
|
|
/*
|
|
* 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
|
|
|
|
/* Radix has already switched LPID and flushed core TLB */
|
|
bne cr7, 22f
|
|
|
|
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. Hash has to be done in RM */
|
|
lhz r6,PACAPACAINDEX(r13) /* test_bit(cpu, need_tlb_flush) */
|
|
BEGIN_FTR_SECTION
|
|
/*
|
|
* On POWER9, individual threads can come in here, but the
|
|
* TLB is shared between the 4 threads in a core, hence
|
|
* invalidating on one thread invalidates for all.
|
|
* Thus we make all 4 threads use the same bit here.
|
|
*/
|
|
clrrdi r6,r6,2
|
|
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
|
|
clrldi r7,r6,64-6 /* extract bit number (6 bits) */
|
|
srdi r6,r6,6 /* doubleword number */
|
|
sldi r6,r6,3 /* address offset */
|
|
add r6,r6,r9
|
|
addi r6,r6,KVM_NEED_FLUSH /* dword in kvm->arch.need_tlb_flush */
|
|
li r8,1
|
|
sld r8,r8,r7
|
|
ld r7,0(r6)
|
|
and. r7,r7,r8
|
|
beq 22f
|
|
/* Flush the TLB of any entries for this LPID */
|
|
lwz r0,KVM_TLB_SETS(r9)
|
|
mtctr r0
|
|
li r7,0x800 /* IS field = 0b10 */
|
|
ptesync
|
|
li r0,0 /* RS for P9 version of tlbiel */
|
|
28: tlbiel r7 /* On P9, rs=0, RIC=0, PRS=0, R=0 */
|
|
addi r7,r7,0x1000
|
|
bdnz 28b
|
|
ptesync
|
|
23: ldarx r7,0,r6 /* clear the bit after TLB flushed */
|
|
andc r7,r7,r8
|
|
stdcx. r7,0,r6
|
|
bne 23b
|
|
|
|
/* 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
|
|
mfspr r8, SPRN_IAMR
|
|
std r5, STACK_SLOT_TID(r1)
|
|
std r6, STACK_SLOT_PSSCR(r1)
|
|
std r7, STACK_SLOT_PID(r1)
|
|
std r8, STACK_SLOT_IAMR(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
|
|
std r5, STACK_SLOT_CIABR(r1)
|
|
std r6, STACK_SLOT_DAWR(r1)
|
|
std r7, STACK_SLOT_DAWRX(r1)
|
|
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
|
|
|
|
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 INCLUDING CR
|
|
*/
|
|
mr r3, r4
|
|
ld r4, VCPU_MSR(r3)
|
|
bl kvmppc_restore_tm_hv
|
|
ld r4, HSTATE_KVM_VCPU(r13)
|
|
91:
|
|
#endif
|
|
|
|
/* 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
|
|
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
|
|
|
|
/* Load up FP, VMX and VSX registers */
|
|
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
|
|
ld r5, VCPU_DAWR(r4)
|
|
ld r6, VCPU_DAWRX(r4)
|
|
ld r7, VCPU_CIABR(r4)
|
|
ld r8, VCPU_TAR(r4)
|
|
/*
|
|
* Handle broken DAWR case by not writing it. This means we
|
|
* can still store the DAWR register for migration.
|
|
*/
|
|
BEGIN_FTR_SECTION
|
|
mtspr SPRN_DAWR, r5
|
|
mtspr SPRN_DAWRX, r6
|
|
END_FTR_SECTION_IFSET(CPU_FTR_DAWR)
|
|
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 r10, HSTATE_XIVE_TIMA_PHYS(r13)
|
|
cmpldi cr0, r10, 0
|
|
beq no_xive
|
|
ld r11, VCPU_XIVE_SAVED_STATE(r4)
|
|
li r9, TM_QW1_OS
|
|
eieio
|
|
stdcix r11,r9,r10
|
|
lwz r11, VCPU_XIVE_CAM_WORD(r4)
|
|
li r9, TM_QW1_OS + TM_WORD2
|
|
stwcix r11,r9,r10
|
|
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 r0,0
|
|
beq 1f
|
|
ld r10, VCPU_XIVE_ESC_RADDR(r4)
|
|
li r9, XIVE_ESB_SET_PQ_01
|
|
ldcix r0, r10, r9
|
|
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 */
|
|
|
|
deliver_guest_interrupt:
|
|
ld r6, VCPU_CTR(r4)
|
|
ld r7, VCPU_XER(r4)
|
|
|
|
mtctr r6
|
|
mtxer r7
|
|
|
|
kvmppc_cede_reentry: /* r4 = vcpu, r13 = paca */
|
|
ld r10, VCPU_PC(r4)
|
|
ld r11, VCPU_MSR(r4)
|
|
ld r6, VCPU_SRR0(r4)
|
|
ld r7, VCPU_SRR1(r4)
|
|
mtspr SPRN_SRR0, r6
|
|
mtspr SPRN_SRR1, r7
|
|
|
|
/* 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)
|
|
rldicl r0, r0, 64 - BOOK3S_IRQPRIO_EXTERNAL_LEVEL, 63
|
|
cmpdi cr1, r0, 0
|
|
andi. r8, r11, MSR_EE
|
|
mfspr r8, SPRN_LPCR
|
|
/* Insert EXTERNAL_LEVEL bit into LPCR at the MER bit position */
|
|
rldimi r8, r0, LPCR_MER_SH, 63 - LPCR_MER_SH
|
|
mtspr SPRN_LPCR, r8
|
|
isync
|
|
beq 5f
|
|
li r0, BOOK3S_INTERRUPT_EXTERNAL
|
|
bne cr1, 12f
|
|
mfspr r0, SPRN_DEC
|
|
BEGIN_FTR_SECTION
|
|
/* On POWER9 check whether the guest has large decrementer enabled */
|
|
andis. r8, r8, LPCR_LD@h
|
|
bne 15f
|
|
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
|
|
extsw r0, r0
|
|
15: cmpdi r0, 0
|
|
li r0, BOOK3S_INTERRUPT_DECREMENTER
|
|
bge 5f
|
|
|
|
12: mtspr SPRN_SRR0, r10
|
|
mr r10,r0
|
|
mtspr SPRN_SRR1, r11
|
|
mr r9, r4
|
|
bl kvmppc_msr_interrupt
|
|
5:
|
|
BEGIN_FTR_SECTION
|
|
b fast_guest_return
|
|
END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
|
|
/* On POWER9, check for pending doorbell requests */
|
|
lbz r0, VCPU_DBELL_REQ(r4)
|
|
cmpwi r0, 0
|
|
beq fast_guest_return
|
|
ld r5, HSTATE_KVM_VCORE(r13)
|
|
/* Set DPDES register so the CPU will take a doorbell interrupt */
|
|
li r0, 1
|
|
mtspr SPRN_DPDES, r0
|
|
std r0, VCORE_DPDES(r5)
|
|
/* Make sure other cpus see vcore->dpdes set before dbell req clear */
|
|
lwsync
|
|
/* Clear the pending doorbell request */
|
|
li r0, 0
|
|
stb r0, VCPU_DBELL_REQ(r4)
|
|
|
|
/*
|
|
* 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)
|
|
lwz r6, VCPU_CR(r4)
|
|
mtlr r5
|
|
mtcr r6
|
|
|
|
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)
|
|
|
|
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 r0, VCPU_GPR(R0)(r4)
|
|
ld r4, VCPU_GPR(R4)(r4)
|
|
HRFI_TO_GUEST
|
|
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
|
|
stw 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)
|
|
|
|
#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
|
|
|
|
/* 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
|
|
cmpwi r12, BOOK3S_INTERRUPT_H_INST_STORAGE
|
|
beq kvmppc_hisi
|
|
|
|
/* 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
|
|
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
|
|
lbz r0, HSTATE_HOST_IPI(r13)
|
|
cmpwi r0, 0
|
|
beq 4f
|
|
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
|
|
bne+ guest_exit_cont
|
|
|
|
/* 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 */
|
|
4: ld r5, HSTATE_KVM_VCORE(r13)
|
|
lwz r0, VCORE_ENTRY_EXIT(r5)
|
|
cmpwi r0, 0x100
|
|
mr r4, r9
|
|
blt deliver_guest_interrupt
|
|
|
|
guest_exit_cont: /* r9 = vcpu, r12 = trap, r13 = paca */
|
|
/* Save more register state */
|
|
mfdar r6
|
|
mfdsisr r7
|
|
std r6, VCPU_DAR(r9)
|
|
stw r7, VCPU_DSISR(r9)
|
|
/* don't overwrite fault_dar/fault_dsisr if HDSI */
|
|
cmpwi r12,BOOK3S_INTERRUPT_H_DATA_STORAGE
|
|
beq mc_cont
|
|
std r6, VCPU_FAULT_DAR(r9)
|
|
stw r7, VCPU_FAULT_DSISR(r9)
|
|
|
|
/* See if it is a machine check */
|
|
cmpwi r12, BOOK3S_INTERRUPT_MACHINE_CHECK
|
|
beq machine_check_realmode
|
|
mc_cont:
|
|
#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 */
|
|
|
|
/* 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_IAMR, r0
|
|
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)
|
|
8:
|
|
|
|
/* Save and reset AMR and UAMOR before turning on the MMU */
|
|
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
|
|
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 INCLUDING CR
|
|
*/
|
|
mr r3, r9
|
|
ld r4, VCPU_MSR(r3)
|
|
bl kvmppc_save_tm_hv
|
|
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 */
|
|
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
|
|
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 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:
|
|
|
|
/* 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)
|
|
ld r8, STACK_SLOT_IAMR(r1)
|
|
mtspr SPRN_TIDR, r5
|
|
mtspr SPRN_PSSCR, r6
|
|
mtspr SPRN_PID, r7
|
|
mtspr SPRN_IAMR, r8
|
|
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)
|
|
|
|
/* If HMI, call kvmppc_realmode_hmi_handler() */
|
|
lwz r12, STACK_SLOT_TRAP(r1)
|
|
cmpwi r12, BOOK3S_INTERRUPT_HMI
|
|
bne 27f
|
|
bl kvmppc_realmode_hmi_handler
|
|
nop
|
|
cmpdi r3, 0
|
|
/*
|
|
* At this point kvmppc_realmode_hmi_handler may have resync-ed
|
|
* the TB, and if it has, we must not subtract the guest timebase
|
|
* offset from the timebase. So, skip it.
|
|
*
|
|
* Also, do not call kvmppc_subcore_exit_guest() because it has
|
|
* been invoked as part of kvmppc_realmode_hmi_handler().
|
|
*/
|
|
beq 30f
|
|
|
|
27:
|
|
/* 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: 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
|
|
|
|
#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
|
|
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
|
|
.long DOTSYM(kvmppc_h_get_tce) - hcall_real_table
|
|
.long DOTSYM(kvmppc_rm_h_put_tce) - hcall_real_table
|
|
.long 0 /* 0x24 - H_SET_SPRG0 */
|
|
.long DOTSYM(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 */
|
|
#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
|
|
.long DOTSYM(kvmppc_rm_h_stuff_tce) - hcall_real_table
|
|
.long DOTSYM(kvmppc_rm_h_put_tce_indirect) - hcall_real_table
|
|
.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)
|
|
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)
|
|
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:
|
|
BEGIN_FTR_SECTION
|
|
/* POWER9 with disabled DAWR */
|
|
li r3, H_HARDWARE
|
|
blr
|
|
END_FTR_SECTION_IFCLR(CPU_FTR_DAWR)
|
|
/* 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)
|
|
mtspr SPRN_DAWR, r4
|
|
mtspr SPRN_DAWRX, r5
|
|
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 INCLUDING CR
|
|
*/
|
|
ld r3, HSTATE_KVM_VCPU(r13)
|
|
ld r4, VCPU_MSR(r3)
|
|
bl kvmppc_save_tm_hv
|
|
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 */
|
|
|
|
/*
|
|
* 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
|
|
mtspr SPRN_PSSCR, r3
|
|
/* 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
|
|
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
|
|
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
|
|
BEGIN_FTR_SECTION
|
|
nap
|
|
FTR_SECTION_ELSE
|
|
PPC_STOP
|
|
ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300)
|
|
b .
|
|
|
|
33: mr r4, r3
|
|
li r3, 0
|
|
li r12, 0
|
|
b 34f
|
|
|
|
kvm_end_cede:
|
|
/* get vcpu pointer */
|
|
ld r4, HSTATE_KVM_VCPU(r13)
|
|
|
|
/* Woken by external or decrementer interrupt */
|
|
ld r1, HSTATE_HOST_R1(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 INCLUDING CR
|
|
*/
|
|
mr r3, r4
|
|
ld r4, VCPU_MSR(r3)
|
|
bl kvmppc_restore_tm_hv
|
|
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
|
|
|
|
/* see if any other thread is already exiting */
|
|
lwz r0,VCORE_ENTRY_EXIT(r5)
|
|
cmpwi r0,0x100
|
|
bge guest_exit_cont
|
|
|
|
b kvmppc_cede_reentry /* if not go back to 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
|
|
/* Abort if we still have a pending escalation */
|
|
lbz r5, VCPU_XIVE_ESC_ON(r9)
|
|
cmpwi r5, 0
|
|
beq 1f
|
|
li r0, 0
|
|
stb r0, VCPU_CEDED(r9)
|
|
1: /* Enable XIVE escalation */
|
|
li r5, XIVE_ESB_SET_PQ_00
|
|
mfmsr r0
|
|
andi. r0, r0, MSR_DR /* in real mode? */
|
|
beq 1f
|
|
ld r10, VCPU_XIVE_ESC_VADDR(r9)
|
|
cmpdi r10, 0
|
|
beq 3f
|
|
ldx r0, r10, r5
|
|
b 2f
|
|
1: ld r10, VCPU_XIVE_ESC_RADDR(r9)
|
|
cmpdi r10, 0
|
|
beq 3f
|
|
ldcix r0, r10, r5
|
|
2: sync
|
|
li r0, 1
|
|
stb r0, VCPU_XIVE_ESC_ON(r9)
|
|
#endif /* CONFIG_KVM_XICS */
|
|
3: b guest_exit_cont
|
|
|
|
/* Try to handle a machine check in real mode */
|
|
machine_check_realmode:
|
|
mr r3, r9 /* get vcpu pointer */
|
|
bl kvmppc_realmode_machine_check
|
|
nop
|
|
ld r9, HSTATE_KVM_VCPU(r13)
|
|
li r12, BOOK3S_INTERRUPT_MACHINE_CHECK
|
|
/*
|
|
* For the guest that is FWNMI capable, deliver all the MCE errors
|
|
* (handled/unhandled) by exiting the guest with KVM_EXIT_NMI exit
|
|
* reason. This new approach injects machine check errors in guest
|
|
* address space to guest with additional information in the form
|
|
* of RTAS event, thus enabling guest kernel to suitably handle
|
|
* such errors.
|
|
*
|
|
* For the guest that is not FWNMI capable (old QEMU) fallback
|
|
* to old behaviour for backward compatibility:
|
|
* Deliver unhandled/fatal (e.g. UE) MCE errors to guest either
|
|
* through machine check interrupt (set HSRR0 to 0x200).
|
|
* For handled errors (no-fatal), just go back to guest execution
|
|
* with current HSRR0.
|
|
* if we receive machine check with MSR(RI=0) then deliver it to
|
|
* guest as machine check causing guest to crash.
|
|
*/
|
|
ld r11, VCPU_MSR(r9)
|
|
rldicl. r0, r11, 64-MSR_HV_LG, 63 /* check if it happened in HV mode */
|
|
bne mc_cont /* if so, exit to host */
|
|
/* Check if guest is capable of handling NMI exit */
|
|
ld r10, VCPU_KVM(r9)
|
|
lbz r10, KVM_FWNMI(r10)
|
|
cmpdi r10, 1 /* FWNMI capable? */
|
|
beq mc_cont /* if so, exit with KVM_EXIT_NMI. */
|
|
|
|
/* if not, fall through for backward compatibility. */
|
|
andi. r10, r11, MSR_RI /* check for unrecoverable exception */
|
|
beq 1f /* Deliver a machine check to guest */
|
|
ld r10, VCPU_PC(r9)
|
|
cmpdi r3, 0 /* Did we handle MCE ? */
|
|
bne 2f /* Continue guest execution. */
|
|
/* If not, deliver a machine check. SRR0/1 are already set */
|
|
1: li r10, BOOK3S_INTERRUPT_MACHINE_CHECK
|
|
bl kvmppc_msr_interrupt
|
|
2: b fast_interrupt_c_return
|
|
|
|
/*
|
|
* 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.
|
|
* This can modify all checkpointed registers, but
|
|
* restores r1 and r2 before exit.
|
|
*/
|
|
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
|
|
|
|
std r1, HSTATE_HOST_R1(r13)
|
|
|
|
/* Clear the MSR RI since r1, r13 may be foobar. */
|
|
li r5, 0
|
|
mtmsrd r5, 1
|
|
|
|
/* 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.
|
|
*/
|
|
/* Reload PACA pointer, stack pointer and TOC. */
|
|
GET_PACA(r13)
|
|
ld r1, HSTATE_HOST_R1(r13)
|
|
ld r2, PACATOC(r13)
|
|
|
|
/* Set MSR RI now we have r1 and r13 back. */
|
|
li r5, MSR_RI
|
|
mtmsrd r5, 1
|
|
|
|
HMT_MEDIUM
|
|
ld r6, HSTATE_DSCR(r13)
|
|
mtspr SPRN_DSCR, r6
|
|
BEGIN_FTR_SECTION_NESTED(96)
|
|
bl pnv_power9_force_smt4_release
|
|
END_FTR_SECTION_NESTED(CPU_FTR_P9_TM_XER_SO_BUG, CPU_FTR_P9_TM_XER_SO_BUG, 96)
|
|
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.
|
|
* This potentially modifies all checkpointed registers.
|
|
* It restores r1 and r2 from the PACA.
|
|
*/
|
|
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
|
|
|
|
/*
|
|
* 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
|