Re: [RFC v2 PATCH 6/7] arm64: KVM: Handle trappable TLB instructions

From: Christoffer Dall
Date: Tue Sep 06 2016 - 06:19:40 EST


On Mon, Sep 05, 2016 at 05:31:36PM +0100, Punit Agrawal wrote:
> The ARMv8 architecture allows trapping of TLB maintenane instructions
> from EL0/EL1 to higher exception levels. On encountering a trappable TLB
> instruction in a guest, an exception is taken to EL2.
>
> Add functionality to handle emulating the TLB instructions.
>
> Signed-off-by: Punit Agrawal <punit.agrawal@xxxxxxx>
> Cc: Christoffer Dall <christoffer.dall@xxxxxxxxxx>
> Cc: Marc Zyngier <marc.zyngier@xxxxxxx>
> ---
> arch/arm64/include/asm/kvm_asm.h | 1 +
> arch/arm64/kvm/hyp/tlb.c | 69 ++++++++++++++++++++++++++++++++++
> arch/arm64/kvm/sys_regs.c | 81 ++++++++++++++++++++++++++++++++++++++++
> arch/arm64/kvm/trace.h | 16 ++++++++
> 4 files changed, 167 insertions(+)
>
> diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
> index 7561f63..1ac1cc3 100644
> --- a/arch/arm64/include/asm/kvm_asm.h
> +++ b/arch/arm64/include/asm/kvm_asm.h
> @@ -49,6 +49,7 @@ extern char __kvm_hyp_vector[];
> extern void __kvm_flush_vm_context(void);
> extern void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa);
> extern void __kvm_tlb_flush_vmid(struct kvm *kvm);
> +extern void __kvm_emulate_tlb_invalidate(struct kvm *kvm, u32 sysreg, u64 regval);
>
> extern int __kvm_vcpu_run(struct kvm_vcpu *vcpu);
>
> diff --git a/arch/arm64/kvm/hyp/tlb.c b/arch/arm64/kvm/hyp/tlb.c
> index 4cda100..1210f58 100644
> --- a/arch/arm64/kvm/hyp/tlb.c
> +++ b/arch/arm64/kvm/hyp/tlb.c
> @@ -78,3 +78,72 @@ static void __hyp_text __tlb_flush_vm_context(void)
> }
>
> __alias(__tlb_flush_vm_context) void __kvm_flush_vm_context(void);
> +
> +/* Intentionally empty functions */
> +static void __hyp_text __switch_to_hyp_role_nvhe(void) { }
> +static void __hyp_text __switch_to_host_role_nvhe(void) { }
> +
> +static void __hyp_text __switch_to_hyp_role_vhe(void)
> +{
> + u64 hcr = read_sysreg(hcr_el2);
> +
> + hcr &= ~HCR_TGE;
> + write_sysreg(hcr, hcr_el2);

why do we need to clear TGE for the TLB maintenance instructions to
work?

Perhaps this is worth explaining in a comment.

Otherwise this looks ok to me.

-Christoffer

> +}
> +
> +static void __hyp_text __switch_to_host_role_vhe(void)
> +{
> + u64 hcr = read_sysreg(hcr_el2);
> +
> + hcr |= HCR_TGE;
> + write_sysreg(hcr, hcr_el2);
> +}
> +
> +static hyp_alternate_select(__switch_to_hyp_role,
> + __switch_to_hyp_role_nvhe,
> + __switch_to_hyp_role_vhe,
> + ARM64_HAS_VIRT_HOST_EXTN);
> +
> +static hyp_alternate_select(__switch_to_host_role,
> + __switch_to_host_role_nvhe,
> + __switch_to_host_role_vhe,
> + ARM64_HAS_VIRT_HOST_EXTN);
> +
> +static void __hyp_text __switch_to_guest_regime(struct kvm *kvm)
> +{
> + write_sysreg(kvm->arch.vttbr, vttbr_el2);
> + __switch_to_hyp_role();
> + isb();
> +}
> +
> +static void __hyp_text __switch_to_host_regime(void)
> +{
> + __switch_to_host_role();
> + write_sysreg(0, vttbr_el2);
> +}
> +
> +void __hyp_text
> +__kvm_emulate_tlb_invalidate(struct kvm *kvm, u32 sys_op, u64 regval)
> +{
> + kvm = kern_hyp_va(kvm);
> +
> + /*
> + * Switch to the guest before performing any TLB operations to
> + * target the appropriate VMID
> + */
> + __switch_to_guest_regime(kvm);
> +
> + /*
> + * TLB maintenance operations are broadcast to
> + * inner-shareable domain when HCR_FB is set (default for
> + * KVM).
> + *
> + * Nuke all Stage 1 TLB entries for the VM. This will kill
> + * performance but it's always safe to do as we don't leave
> + * behind any strays in the TLB
> + */
> + __tlbi(vmalle1is);
> + isb();
> +
> + __switch_to_host_regime();
> +}
> diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
> index e51367d..0e70da9 100644
> --- a/arch/arm64/kvm/sys_regs.c
> +++ b/arch/arm64/kvm/sys_regs.c
> @@ -790,6 +790,18 @@ static bool access_pmuserenr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
> return true;
> }
>
> +static bool emulate_tlb_invalidate(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
> + const struct sys_reg_desc *r)
> +{
> + u32 opcode = sys_reg(p->Op0, p->Op1, p->CRn, p->CRm, p->Op2);
> +
> + kvm_call_hyp(__kvm_emulate_tlb_invalidate,
> + vcpu->kvm, opcode, p->regval);
> + trace_kvm_tlb_invalidate(*vcpu_pc(vcpu), opcode);
> +
> + return true;
> +}
> +
> /* Silly macro to expand the DBG{BCR,BVR,WVR,WCR}n_EL1 registers in one go */
> #define DBG_BCR_BVR_WCR_WVR_EL1(n) \
> /* DBGBVRn_EL1 */ \
> @@ -841,6 +853,35 @@ static const struct sys_reg_desc sys_reg_descs[] = {
> { Op0(0b01), Op1(0b000), CRn(0b0111), CRm(0b1110), Op2(0b010),
> access_dcsw },
>
> + /*
> + * ARMv8 ARM: Table C5-4 TLB maintenance instructions
> + * (Ref: ARMv8 ARM C5.1 version: ARM DDI 0487A.j)
> + */
> + /* TLBI VMALLE1IS */
> + { Op0(1), Op1(0), CRn(8), CRm(3), Op2(0), emulate_tlb_invalidate },
> + /* TLBI VAE1IS */
> + { Op0(1), Op1(0), CRn(8), CRm(3), Op2(1), emulate_tlb_invalidate },
> + /* TLBI ASIDE1IS */
> + { Op0(1), Op1(0), CRn(8), CRm(3), Op2(2), emulate_tlb_invalidate },
> + /* TLBI VAAE1IS */
> + { Op0(1), Op1(0), CRn(8), CRm(3), Op2(3), emulate_tlb_invalidate },
> + /* TLBI VALE1IS */
> + { Op0(1), Op1(0), CRn(8), CRm(3), Op2(5), emulate_tlb_invalidate },
> + /* TLBI VAALE1IS */
> + { Op0(1), Op1(0), CRn(8), CRm(3), Op2(7), emulate_tlb_invalidate },
> + /* TLBI VMALLE1 */
> + { Op0(1), Op1(0), CRn(8), CRm(7), Op2(0), emulate_tlb_invalidate },
> + /* TLBI VAE1 */
> + { Op0(1), Op1(0), CRn(8), CRm(7), Op2(1), emulate_tlb_invalidate },
> + /* TLBI ASIDE1 */
> + { Op0(1), Op1(0), CRn(8), CRm(7), Op2(2), emulate_tlb_invalidate },
> + /* TLBI VAAE1 */
> + { Op0(1), Op1(0), CRn(8), CRm(7), Op2(3), emulate_tlb_invalidate },
> + /* TLBI VALE1 */
> + { Op0(1), Op1(0), CRn(8), CRm(7), Op2(5), emulate_tlb_invalidate },
> + /* TLBI VAALE1 */
> + { Op0(1), Op1(0), CRn(8), CRm(7), Op2(7), emulate_tlb_invalidate },
> +
> DBG_BCR_BVR_WCR_WVR_EL1(0),
> DBG_BCR_BVR_WCR_WVR_EL1(1),
> /* MDCCINT_EL1 */
> @@ -1329,6 +1370,46 @@ static const struct sys_reg_desc cp15_regs[] = {
> { Op1( 0), CRn( 7), CRm(10), Op2( 2), access_dcsw },
> { Op1( 0), CRn( 7), CRm(14), Op2( 2), access_dcsw },
>
> + /*
> + * TLB operations
> + */
> + /* TLBIALLIS */
> + { Op1( 0), CRn( 8), CRm( 3), Op2( 0), emulate_tlb_invalidate},
> + /* TLBIMVAIS */
> + { Op1( 0), CRn( 8), CRm( 3), Op2( 1), emulate_tlb_invalidate},
> + /* TLBIASIDIS */
> + { Op1( 0), CRn( 8), CRm( 3), Op2( 2), emulate_tlb_invalidate},
> + /* TLBIMVAAIS */
> + { Op1( 0), CRn( 8), CRm( 3), Op2( 3), emulate_tlb_invalidate},
> + /* TLBIMVALIS */
> + { Op1( 0), CRn( 8), CRm( 3), Op2( 5), emulate_tlb_invalidate},
> + /* TLBIMVAALIS */
> + { Op1( 0), CRn( 8), CRm( 3), Op2( 7), emulate_tlb_invalidate},
> + /* ITLBIALL */
> + { Op1( 0), CRn( 8), CRm( 5), Op2( 0), emulate_tlb_invalidate},
> + /* ITLBIMVA */
> + { Op1( 0), CRn( 8), CRm( 5), Op2( 1), emulate_tlb_invalidate},
> + /* ITLBIASID */
> + { Op1( 0), CRn( 8), CRm( 5), Op2( 2), emulate_tlb_invalidate},
> + /* DTLBIALL */
> + { Op1( 0), CRn( 8), CRm( 6), Op2( 0), emulate_tlb_invalidate},
> + /* DTLBIMVA */
> + { Op1( 0), CRn( 8), CRm( 6), Op2( 1), emulate_tlb_invalidate},
> + /* DTLBIASID */
> + { Op1( 0), CRn( 8), CRm( 6), Op2( 2), emulate_tlb_invalidate},
> + /* TLBIALL */
> + { Op1( 0), CRn( 8), CRm( 7), Op2( 0), emulate_tlb_invalidate},
> + /* TLBIMVA */
> + { Op1( 0), CRn( 8), CRm( 7), Op2( 1), emulate_tlb_invalidate},
> + /* TLBIASID */
> + { Op1( 0), CRn( 8), CRm( 7), Op2( 2), emulate_tlb_invalidate},
> + /* TLBIMVAA */
> + { Op1( 0), CRn( 8), CRm( 7), Op2( 3), emulate_tlb_invalidate},
> + /* TLBIMVAL */
> + { Op1( 0), CRn( 8), CRm( 7), Op2( 5), emulate_tlb_invalidate},
> + /* TLBIMVAAL */
> + { Op1( 0), CRn( 8), CRm( 7), Op2( 7), emulate_tlb_invalidate},
> +
> /* PMU */
> { Op1( 0), CRn( 9), CRm(12), Op2( 0), access_pmcr },
> { Op1( 0), CRn( 9), CRm(12), Op2( 1), access_pmcnten },
> diff --git a/arch/arm64/kvm/trace.h b/arch/arm64/kvm/trace.h
> index 7fb0008..c4d577f 100644
> --- a/arch/arm64/kvm/trace.h
> +++ b/arch/arm64/kvm/trace.h
> @@ -166,6 +166,22 @@ TRACE_EVENT(kvm_set_guest_debug,
> TP_printk("vcpu: %p, flags: 0x%08x", __entry->vcpu, __entry->guest_debug)
> );
>
> +TRACE_EVENT(kvm_tlb_invalidate,
> + TP_PROTO(unsigned long vcpu_pc, u32 opcode),
> + TP_ARGS(vcpu_pc, opcode),
> +
> + TP_STRUCT__entry(
> + __field(unsigned long, vcpu_pc)
> + __field(u32, opcode)
> + ),
> +
> + TP_fast_assign(
> + __entry->vcpu_pc = vcpu_pc;
> + __entry->opcode = opcode;
> + ),
> +
> + TP_printk("vcpu_pc=0x%16lx opcode=%08x", __entry->vcpu_pc, __entry->opcode)
> +);
>
> #endif /* _TRACE_ARM64_KVM_H */
>
> --
> 2.8.1
>