Implement HvFlushVirtualAddress{List,Space} hypercalls in a simplistic way: do full TLB flush with KVM_REQ_TLB_FLUSH and kick vCPUs which are currently IN_GUEST_MODE. Signed-off-by: Vitaly Kuznetsov <vkuznets@xxxxxxxxxx> --- arch/x86/include/asm/kvm_host.h | 1 + arch/x86/kvm/hyperv.c | 74 ++++++++++++++++++++++++++++++++++++++++- arch/x86/kvm/trace.h | 24 +++++++++++++ 3 files changed, 98 insertions(+), 1 deletion(-) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index c25775fad4ed..9ce1fb2b6af3 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -476,6 +476,7 @@ struct kvm_vcpu_hv { struct kvm_hyperv_exit exit; struct kvm_vcpu_hv_stimer stimer[HV_SYNIC_STIMER_COUNT]; DECLARE_BITMAP(stimer_pending_bitmap, HV_SYNIC_STIMER_COUNT); + cpumask_t tlb_lush; }; struct kvm_vcpu_arch { diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 67788d358200..fa26af1e8b7c 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -1242,6 +1242,65 @@ int kvm_hv_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) return kvm_hv_get_msr(vcpu, msr, pdata); } +static void ack_flush(void *_completed) +{ +} + +static u64 kvm_hv_flush_tlb(struct kvm_vcpu *current_vcpu, u64 ingpa, + u16 rep_cnt) +{ + struct kvm *kvm = current_vcpu->kvm; + struct kvm_vcpu_hv *hv_current = ¤t_vcpu->arch.hyperv; + struct hv_tlb_flush flush; + struct kvm_vcpu *vcpu; + int i, cpu, me; + + if (unlikely(kvm_read_guest(kvm, ingpa, &flush, sizeof(flush)))) + return HV_STATUS_INVALID_HYPERCALL_INPUT; + + trace_kvm_hv_flush_tlb(flush.processor_mask, flush.address_space, + flush.flags); + + cpumask_clear(&hv_current->tlb_lush); + + me = get_cpu(); + + kvm_for_each_vcpu(i, vcpu, kvm) { + struct kvm_vcpu_hv *hv = &vcpu->arch.hyperv; + + if (!(flush.flags & HV_FLUSH_ALL_PROCESSORS) && + !(flush.processor_mask & BIT_ULL(hv->vp_index))) + continue; + + /* + * vcpu->arch.cr3 may not be up-to-date for running vCPUs so we + * can't analyze it here, flush TLB regardless of the specified + * address space. + */ + kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu); + + /* + * It is possible that vCPU will migrate and we will kick wrong + * CPU but vCPU's TLB will anyway be flushed upon migration as + * we already made KVM_REQ_TLB_FLUSH request. + */ + cpu = vcpu->cpu; + if (cpu != -1 && cpu != me && cpu_online(cpu) && + kvm_arch_vcpu_should_kick(vcpu)) + cpumask_set_cpu(cpu, &hv_current->tlb_lush); + } + + if (!cpumask_empty(&hv_current->tlb_lush)) + smp_call_function_many(&hv_current->tlb_lush, ack_flush, + NULL, true); + + put_cpu(); + + /* We always do full TLB flush, set rep_done = rep_cnt. */ + return (u64)HV_STATUS_SUCCESS | + ((u64)rep_cnt << HV_HYPERCALL_REP_COMP_OFFSET); +} + bool kvm_hv_hypercall_enabled(struct kvm *kvm) { return READ_ONCE(kvm->arch.hyperv.hv_hypercall) & HV_X64_MSR_HYPERCALL_ENABLE; @@ -1377,12 +1436,25 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu) vcpu->arch.complete_userspace_io = kvm_hv_hypercall_complete_userspace; return 0; + case HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST: + if (unlikely(fast || !rep_cnt || rep_idx)) { + ret = HV_STATUS_INVALID_HYPERCALL_INPUT; + break; + } + ret = kvm_hv_flush_tlb(vcpu, ingpa, rep_cnt); + break; + case HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE: + if (unlikely(fast || rep)) { + ret = HV_STATUS_INVALID_HYPERCALL_INPUT; + break; + } + ret = kvm_hv_flush_tlb(vcpu, ingpa, rep_cnt); + break; default: ret = HV_STATUS_INVALID_HYPERCALL_CODE; break; } -set_result: kvm_hv_hypercall_set_result(vcpu, ret); return 1; } diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index 9807c314c478..47a4fd758743 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -1367,6 +1367,30 @@ TRACE_EVENT(kvm_hv_timer_state, __entry->vcpu_id, __entry->hv_timer_in_use) ); + +/* + * Tracepoint for kvm_hv_flush_tlb. + */ +TRACE_EVENT(kvm_hv_flush_tlb, + TP_PROTO(u64 processor_mask, u64 address_space, u64 flags), + TP_ARGS(processor_mask, address_space, flags), + + TP_STRUCT__entry( + __field(u64, processor_mask) + __field(u64, address_space) + __field(u64, flags) + ), + + TP_fast_assign( + __entry->processor_mask = processor_mask; + __entry->address_space = address_space; + __entry->flags = flags; + ), + + TP_printk("processor_mask 0x%llx address_space 0x%llx flags 0x%llx", + __entry->processor_mask, __entry->address_space, + __entry->flags) +); #endif /* _TRACE_KVM_H */ #undef TRACE_INCLUDE_PATH -- 2.14.3