mirror of
https://github.com/torvalds/linux.git
synced 2024-11-18 01:51:53 +00:00
35dfb43c24
POWER8 and POWER9 machines have a hardware deviation where generation of a hypervisor decrementer exception is suppressed if the HDICE bit in the LPCR register is 0 at the time when the HDEC register decrements from 0 to -1. When entering a guest, KVM first writes the HDEC register with the time until it wants the CPU to exit the guest, and then writes the LPCR with the guest value, which includes HDICE = 1. If HDEC decrements from 0 to -1 during the interval between those two events, it is possible that we can enter the guest with HDEC already negative but no HDEC exception pending, meaning that no HDEC interrupt will occur while the CPU is in the guest, or at least not until HDEC wraps around. Thus it is possible for the CPU to keep executing in the guest for a long time; up to about 4 seconds on POWER8, or about 4.46 years on POWER9 (except that the host kernel hard lockup detector will fire first). To fix this, we set the LPCR[HDICE] bit before writing HDEC on guest entry. Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
167 lines
4.0 KiB
ArmAsm
167 lines
4.0 KiB
ArmAsm
/* SPDX-License-Identifier: GPL-2.0-only */
|
|
/*
|
|
*
|
|
* Copyright 2011 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
|
|
*
|
|
* Derived from book3s_interrupts.S, which is:
|
|
* 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/page.h>
|
|
#include <asm/asm-offsets.h>
|
|
#include <asm/exception-64s.h>
|
|
#include <asm/ppc-opcode.h>
|
|
#include <asm/asm-compat.h>
|
|
#include <asm/feature-fixups.h>
|
|
|
|
/*****************************************************************************
|
|
* *
|
|
* Guest entry / exit code that is in kernel module memory (vmalloc) *
|
|
* *
|
|
****************************************************************************/
|
|
|
|
/* Registers:
|
|
* none
|
|
*/
|
|
_GLOBAL(__kvmppc_vcore_entry)
|
|
|
|
/* Write correct stack frame */
|
|
mflr r0
|
|
std r0,PPC_LR_STKOFF(r1)
|
|
|
|
/* Save host state to the stack */
|
|
stdu r1, -SWITCH_FRAME_SIZE(r1)
|
|
|
|
/* Save non-volatile registers (r14 - r31) and CR */
|
|
SAVE_NVGPRS(r1)
|
|
mfcr r3
|
|
std r3, _CCR(r1)
|
|
|
|
/* Save host DSCR */
|
|
mfspr r3, SPRN_DSCR
|
|
std r3, HSTATE_DSCR(r13)
|
|
|
|
BEGIN_FTR_SECTION
|
|
/* Save host DABR */
|
|
mfspr r3, SPRN_DABR
|
|
std r3, HSTATE_DABR(r13)
|
|
END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
|
|
|
|
/* Save host PMU registers */
|
|
bl kvmhv_save_host_pmu
|
|
|
|
/*
|
|
* Put whatever is in the decrementer into the
|
|
* hypervisor decrementer.
|
|
* Because of a hardware deviation in P8 and P9,
|
|
* we need to set LPCR[HDICE] before writing HDEC.
|
|
*/
|
|
ld r5, HSTATE_KVM_VCORE(r13)
|
|
ld r6, VCORE_KVM(r5)
|
|
ld r9, KVM_HOST_LPCR(r6)
|
|
ori r8, r9, LPCR_HDICE
|
|
mtspr SPRN_LPCR, r8
|
|
isync
|
|
andis. r0, r9, LPCR_LD@h
|
|
mfspr r8,SPRN_DEC
|
|
mftb r7
|
|
BEGIN_FTR_SECTION
|
|
/* On POWER9, don't sign-extend if host LPCR[LD] bit is set */
|
|
bne 32f
|
|
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
|
|
extsw r8,r8
|
|
32: mtspr SPRN_HDEC,r8
|
|
add r8,r8,r7
|
|
std r8,HSTATE_DECEXP(r13)
|
|
|
|
/* Jump to partition switch code */
|
|
bl kvmppc_hv_entry_trampoline
|
|
nop
|
|
|
|
/*
|
|
* We return here in virtual mode after the guest exits
|
|
* with something that we can't handle in real mode.
|
|
* Interrupts are still hard-disabled.
|
|
*/
|
|
|
|
/*
|
|
* Register usage at this point:
|
|
*
|
|
* R1 = host R1
|
|
* R2 = host R2
|
|
* R3 = trap number on this thread
|
|
* R12 = exit handler id
|
|
* R13 = PACA
|
|
*/
|
|
|
|
/* Restore non-volatile host registers (r14 - r31) and CR */
|
|
REST_NVGPRS(r1)
|
|
ld r4, _CCR(r1)
|
|
mtcr r4
|
|
|
|
addi r1, r1, SWITCH_FRAME_SIZE
|
|
ld r0, PPC_LR_STKOFF(r1)
|
|
mtlr r0
|
|
blr
|
|
|
|
_GLOBAL(kvmhv_save_host_pmu)
|
|
BEGIN_FTR_SECTION
|
|
/* Work around P8 PMAE bug */
|
|
li r3, -1
|
|
clrrdi r3, r3, 10
|
|
mfspr r8, SPRN_MMCR2
|
|
mtspr SPRN_MMCR2, r3 /* freeze all counters using MMCR2 */
|
|
isync
|
|
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
|
|
li r3, 1
|
|
sldi r3, r3, 31 /* MMCR0_FC (freeze counters) bit */
|
|
mfspr r7, SPRN_MMCR0 /* save MMCR0 */
|
|
mtspr SPRN_MMCR0, r3 /* freeze all counters, disable interrupts */
|
|
mfspr r6, SPRN_MMCRA
|
|
/* Clear MMCRA in order to disable SDAR updates */
|
|
li r5, 0
|
|
mtspr SPRN_MMCRA, r5
|
|
isync
|
|
lbz r5, PACA_PMCINUSE(r13) /* is the host using the PMU? */
|
|
cmpwi r5, 0
|
|
beq 31f /* skip if not */
|
|
mfspr r5, SPRN_MMCR1
|
|
mfspr r9, SPRN_SIAR
|
|
mfspr r10, SPRN_SDAR
|
|
std r7, HSTATE_MMCR0(r13)
|
|
std r5, HSTATE_MMCR1(r13)
|
|
std r6, HSTATE_MMCRA(r13)
|
|
std r9, HSTATE_SIAR(r13)
|
|
std r10, HSTATE_SDAR(r13)
|
|
BEGIN_FTR_SECTION
|
|
mfspr r9, SPRN_SIER
|
|
std r8, HSTATE_MMCR2(r13)
|
|
std r9, HSTATE_SIER(r13)
|
|
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
|
|
BEGIN_FTR_SECTION
|
|
mfspr r5, SPRN_MMCR3
|
|
mfspr r6, SPRN_SIER2
|
|
mfspr r7, SPRN_SIER3
|
|
std r5, HSTATE_MMCR3(r13)
|
|
std r6, HSTATE_SIER2(r13)
|
|
std r7, HSTATE_SIER3(r13)
|
|
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_31)
|
|
mfspr r3, SPRN_PMC1
|
|
mfspr r5, SPRN_PMC2
|
|
mfspr r6, SPRN_PMC3
|
|
mfspr r7, SPRN_PMC4
|
|
mfspr r8, SPRN_PMC5
|
|
mfspr r9, SPRN_PMC6
|
|
stw r3, HSTATE_PMC1(r13)
|
|
stw r5, HSTATE_PMC2(r13)
|
|
stw r6, HSTATE_PMC3(r13)
|
|
stw r7, HSTATE_PMC4(r13)
|
|
stw r8, HSTATE_PMC5(r13)
|
|
stw r9, HSTATE_PMC6(r13)
|
|
31: blr
|