openkylin
/
linux
mirror of https://gitee.com/openkylin/linux.git
9
0
Fork 0
Code Issues Projects Releases Wiki Activity
linux/arch/powerpc/kvm/book3s_hv_tm_builtin.c

110 lines
3.3 KiB
C
Raw Normal View History

KVM: PPC: Book3S HV: Work around transactional memory bugs in POWER9 POWER9 has hardware bugs relating to transactional memory and thread reconfiguration (changes to hardware SMT mode). Specifically, the core does not have enough storage to store a complete checkpoint of all the architected state for all four threads. The DD2.2 version of POWER9 includes hardware modifications designed to allow hypervisor software to implement workarounds for these problems. This patch implements those workarounds in KVM code so that KVM guests see a full, working transactional memory implementation. The problems center around the use of TM suspended state, where the CPU has a checkpointed state but execution is not transactional. The workaround is to implement a "fake suspend" state, which looks to the guest like suspended state but the CPU does not store a checkpoint. In this state, any instruction that would cause a transition to transactional state (rfid, rfebb, mtmsrd, tresume) or would use the checkpointed state (treclaim) causes a "soft patch" interrupt (vector 0x1500) to the hypervisor so that it can be emulated. The trechkpt instruction also causes a soft patch interrupt. On POWER9 DD2.2, we avoid returning to the guest in any state which would require a checkpoint to be present. The trechkpt in the guest entry path which would normally create that checkpoint is replaced by either a transition to fake suspend state, if the guest is in suspend state, or a rollback to the pre-transactional state if the guest is in transactional state. Fake suspend state is indicated by a flag in the PACA plus a new bit in the PSSCR. The new PSSCR bit is write-only and reads back as 0. On exit from the guest, if the guest is in fake suspend state, we still do the treclaim instruction as we would in real suspend state, in order to get into non-transactional state, but we do not save the resulting register state since there was no checkpoint. Emulation of the instructions that cause a softpatch interrupt is handled in two paths. If the guest is in real suspend mode, we call kvmhv_p9_tm_emulation_early() to handle the cases where the guest is transitioning to transactional state. This is called before we do the treclaim in the guest exit path; because we haven't done treclaim, we can get back to the guest with the transaction still active. If the instruction is a case that kvmhv_p9_tm_emulation_early() doesn't handle, or if the guest is in fake suspend state, then we proceed to do the complete guest exit path and subsequently call kvmhv_p9_tm_emulation() in host context with the MMU on. This handles all the cases including the cases that generate program interrupts (illegal instruction or TM Bad Thing) and facility unavailable interrupts. The emulation is reasonably straightforward and is mostly concerned with checking for exception conditions and updating the state of registers such as MSR and CR0. The treclaim emulation takes care to ensure that the TEXASR register gets updated as if it were the guest treclaim instruction that had done failure recording, not the treclaim done in hypervisor state in the guest exit path. With this, the KVM_CAP_PPC_HTM capability returns true (1) even if transactional memory is not available to host userspace. Signed-off-by: Paul Mackerras <paulus@ozlabs.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-03-21 18:32:01 +08:00
/*
* Copyright 2017 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
*
* 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.
*/
#include <linux/kvm_host.h>
#include <asm/kvm_ppc.h>
#include <asm/kvm_book3s.h>
#include <asm/kvm_book3s_64.h>
#include <asm/reg.h>
#include <asm/ppc-opcode.h>
/*
* This handles the cases where the guest is in real suspend mode
* and we want to get back to the guest without dooming the transaction.
* The caller has checked that the guest is in real-suspend mode
* (MSR[TS] = S and the fake-suspend flag is not set).
*/
int kvmhv_p9_tm_emulation_early(struct kvm_vcpu *vcpu)
{
u32 instr = vcpu->arch.emul_inst;
u64 newmsr, msr, bescr;
int rs;
switch (instr & 0xfc0007ff) {
case PPC_INST_RFID:
/* XXX do we need to check for PR=0 here? */
newmsr = vcpu->arch.shregs.srr1;
/* should only get here for Sx -> T1 transition */
if (!(MSR_TM_TRANSACTIONAL(newmsr) && (newmsr & MSR_TM)))
return 0;
newmsr = sanitize_msr(newmsr);
vcpu->arch.shregs.msr = newmsr;
vcpu->arch.cfar = vcpu->arch.pc - 4;
vcpu->arch.pc = vcpu->arch.shregs.srr0;
return 1;
case PPC_INST_RFEBB:
/* check for PR=1 and arch 2.06 bit set in PCR */
msr = vcpu->arch.shregs.msr;
if ((msr & MSR_PR) && (vcpu->arch.vcore->pcr & PCR_ARCH_206))
return 0;
/* check EBB facility is available */
if (!(vcpu->arch.hfscr & HFSCR_EBB) ||
((msr & MSR_PR) && !(mfspr(SPRN_FSCR) & FSCR_EBB)))
return 0;
bescr = mfspr(SPRN_BESCR);
/* expect to see a S->T transition requested */
if (((bescr >> 30) & 3) != 2)
return 0;
bescr &= ~BESCR_GE;
if (instr & (1 << 11))
bescr |= BESCR_GE;
mtspr(SPRN_BESCR, bescr);
msr = (msr & ~MSR_TS_MASK) | MSR_TS_T;
vcpu->arch.shregs.msr = msr;
vcpu->arch.cfar = vcpu->arch.pc - 4;
vcpu->arch.pc = mfspr(SPRN_EBBRR);
return 1;
case PPC_INST_MTMSRD:
/* XXX do we need to check for PR=0 here? */
rs = (instr >> 21) & 0x1f;
newmsr = kvmppc_get_gpr(vcpu, rs);
msr = vcpu->arch.shregs.msr;
/* check this is a Sx -> T1 transition */
if (!(MSR_TM_TRANSACTIONAL(newmsr) && (newmsr & MSR_TM)))
return 0;
/* mtmsrd doesn't change LE */
newmsr = (newmsr & ~MSR_LE) | (msr & MSR_LE);
newmsr = sanitize_msr(newmsr);
vcpu->arch.shregs.msr = newmsr;
return 1;
case PPC_INST_TSR:
/* we know the MSR has the TS field = S (0b01) here */
msr = vcpu->arch.shregs.msr;
/* check for PR=1 and arch 2.06 bit set in PCR */
if ((msr & MSR_PR) && (vcpu->arch.vcore->pcr & PCR_ARCH_206))
return 0;
/* check for TM disabled in the HFSCR or MSR */
if (!(vcpu->arch.hfscr & HFSCR_TM) || !(msr & MSR_TM))
return 0;
/* L=1 => tresume => set TS to T (0b10) */
if (instr & (1 << 21))
vcpu->arch.shregs.msr = (msr & ~MSR_TS_MASK) | MSR_TS_T;
/* Set CR0 to 0b0010 */
vcpu->arch.cr = (vcpu->arch.cr & 0x0fffffff) | 0x20000000;
return 1;
}
return 0;
}
/*
* This is called when we are returning to a guest in TM transactional
* state. We roll the guest state back to the checkpointed state.
*/
void kvmhv_emulate_tm_rollback(struct kvm_vcpu *vcpu)
{
vcpu->arch.shregs.msr &= ~MSR_TS_MASK; /* go to N state */
vcpu->arch.pc = vcpu->arch.tfhar;
copy_from_checkpoint(vcpu);
vcpu->arch.cr = (vcpu->arch.cr & 0x0fffffff) | 0xa0000000;
}