Re: [RFC PATCH v5 094/104] KVM: TDX: Handle TDX PV MMIO hypercall

[Paolo Bonzini]

On 3/4/22 20:49, isaku.yamahata@xxxxxxxxx wrote:
> From: Sean Christopherson <sean.j.christopherson@xxxxxxxxx>
>
> Export kvm_io_bus_read and kvm_mmio tracepoint and wire up TDX PV MMIO
> hypercall to the KVM backend functions.
>
> kvm_io_bus_read/write() searches KVM device emulated in kernel of the given
> MMIO address and emulates the MMIO.  As TDX PV MMIO also needs it, export
> kvm_io_bus_read().  kvm_io_bus_write() is already exported.  TDX PV MMIO
> emulates some of MMIO itself.  To add trace point consistently with x86
> kvm, export kvm_mmio tracepoint.
>
> Signed-off-by: Sean Christopherson <sean.j.christopherson@xxxxxxxxx>
> Signed-off-by: Isaku Yamahata <isaku.yamahata@xxxxxxxxx>
> ---
>   arch/x86/kvm/vmx/tdx.c | 114 +++++++++++++++++++++++++++++++++++++++++
>   arch/x86/kvm/x86.c     |   1 +
>   virt/kvm/kvm_main.c    |   2 +
>   3 files changed, 117 insertions(+)
>
> diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c
> index c900347d0bc7..914af5da4805 100644
> --- a/arch/x86/kvm/vmx/tdx.c
> +++ b/arch/x86/kvm/vmx/tdx.c
> @@ -1012,6 +1012,118 @@ static int tdx_emulate_io(struct kvm_vcpu *vcpu)
>   	return ret;
>   }
>   
> +static int tdx_complete_mmio(struct kvm_vcpu *vcpu)
> +{
> +	unsigned long val = 0;
> +	gpa_t gpa;
> +	int size;
> +
> +	WARN_ON(vcpu->mmio_needed != 1);
> +	vcpu->mmio_needed = 0;
> +
> +	if (!vcpu->mmio_is_write) {
> +		gpa = vcpu->mmio_fragments[0].gpa;
> +		size = vcpu->mmio_fragments[0].len;
> +
> +		memcpy(&val, vcpu->run->mmio.data, size);
> +		tdvmcall_set_return_val(vcpu, val);
> +		trace_kvm_mmio(KVM_TRACE_MMIO_READ, size, gpa, &val);
> +	}
> +	return 1;
> +}
> +
> +static inline int tdx_mmio_write(struct kvm_vcpu *vcpu, gpa_t gpa, int size,
> +				 unsigned long val)
> +{
> +	if (kvm_iodevice_write(vcpu, &vcpu->arch.apic->dev, gpa, size, &val) &&
> +	    kvm_io_bus_write(vcpu, KVM_MMIO_BUS, gpa, size, &val))
> +		return -EOPNOTSUPP;
> +
> +	trace_kvm_mmio(KVM_TRACE_MMIO_WRITE, size, gpa, &val);
> +	return 0;
> +}
> +
> +static inline int tdx_mmio_read(struct kvm_vcpu *vcpu, gpa_t gpa, int size)
> +{
> +	unsigned long val;
> +
> +	if (kvm_iodevice_read(vcpu, &vcpu->arch.apic->dev, gpa, size, &val) &&
> +	    kvm_io_bus_read(vcpu, KVM_MMIO_BUS, gpa, size, &val))
> +		return -EOPNOTSUPP;
> +
> +	tdvmcall_set_return_val(vcpu, val);
> +	trace_kvm_mmio(KVM_TRACE_MMIO_READ, size, gpa, &val);
> +	return 0;
> +}
> +
> +static int tdx_emulate_mmio(struct kvm_vcpu *vcpu)
> +{
> +	struct kvm_memory_slot *slot;
> +	int size, write, r;
> +	unsigned long val;
> +	gpa_t gpa;
> +
> +	WARN_ON(vcpu->mmio_needed);
> +
> +	size = tdvmcall_p1_read(vcpu);
> +	write = tdvmcall_p2_read(vcpu);
> +	gpa = tdvmcall_p3_read(vcpu);
> +	val = write ? tdvmcall_p4_read(vcpu) : 0;
> +
> +	if (size != 1 && size != 2 && size != 4 && size != 8)
> +		goto error;
> +	if (write != 0 && write != 1)
> +		goto error;
> +
> +	/* Strip the shared bit, allow MMIO with and without it set. */
> +	gpa = kvm_gpa_unalias(vcpu->kvm, gpa);
> +
> +	if (size > 8u || ((gpa + size - 1) ^ gpa) & PAGE_MASK)
> +		goto error;
> +
> +	slot = kvm_vcpu_gfn_to_memslot(vcpu, gpa_to_gfn(gpa));
> +	if (slot && !(slot->flags & KVM_MEMSLOT_INVALID))
> +		goto error;
> +
> +	if (!kvm_io_bus_write(vcpu, KVM_FAST_MMIO_BUS, gpa, 0, NULL)) {
> +		trace_kvm_fast_mmio(gpa);
> +		return 1;
> +	}
> +
> +	if (write)
> +		r = tdx_mmio_write(vcpu, gpa, size, val);
> +	else
> +		r = tdx_mmio_read(vcpu, gpa, size);
> +	if (!r) {
> +		/* Kernel completed device emulation. */
> +		tdvmcall_set_return_code(vcpu, TDG_VP_VMCALL_SUCCESS);
> +		return 1;
> +	}
> +
> +	/* Request the device emulation to userspace device model. */
> +	vcpu->mmio_needed = 1;
> +	vcpu->mmio_is_write = write;
> +	vcpu->arch.complete_userspace_io = tdx_complete_mmio;
> +
> +	vcpu->run->mmio.phys_addr = gpa;
> +	vcpu->run->mmio.len = size;
> +	vcpu->run->mmio.is_write = write;
> +	vcpu->run->exit_reason = KVM_EXIT_MMIO;
> +
> +	if (write) {
> +		memcpy(vcpu->run->mmio.data, &val, size);
> +	} else {
> +		vcpu->mmio_fragments[0].gpa = gpa;
> +		vcpu->mmio_fragments[0].len = size;
> +		trace_kvm_mmio(KVM_TRACE_MMIO_READ_UNSATISFIED, size, gpa, NULL);
> +	}
> +	return 0;
> +
> +error:
> +	tdvmcall_set_return_code(vcpu, TDG_VP_VMCALL_SUCCESS);
> +	return 1;
> +}
> +
>   static int handle_tdvmcall(struct kvm_vcpu *vcpu)
>   {
>   	struct vcpu_tdx *tdx = to_tdx(vcpu);
> @@ -1029,6 +1141,8 @@ static int handle_tdvmcall(struct kvm_vcpu *vcpu)
>   		return tdx_emulate_hlt(vcpu);
>   	case EXIT_REASON_IO_INSTRUCTION:
>   		return tdx_emulate_io(vcpu);
> +	case EXIT_REASON_EPT_VIOLATION:
> +		return tdx_emulate_mmio(vcpu);
>   	default:
>   		break;
>   	}
> diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
> index 9acb33a17445..483fa46b1be7 100644
> --- a/arch/x86/kvm/x86.c
> +++ b/arch/x86/kvm/x86.c
> @@ -12915,6 +12915,7 @@ bool kvm_arch_dirty_log_supported(struct kvm *kvm)
>   
>   EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_entry);
>   EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_exit);
> +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_mmio);
>   EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_fast_mmio);
>   EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_inj_virq);
>   EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_page_fault);
> diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
> index d4e117f5b5b9..6db075db6098 100644
> --- a/virt/kvm/kvm_main.c
> +++ b/virt/kvm/kvm_main.c
> @@ -2259,6 +2259,7 @@ struct kvm_memory_slot *kvm_vcpu_gfn_to_memslot(struct kvm_vcpu *vcpu, gfn_t gfn
>   
>   	return NULL;
>   }
> +EXPORT_SYMBOL_GPL(kvm_vcpu_gfn_to_memslot);
>   
>   bool kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn)
>   {
> @@ -5126,6 +5127,7 @@ int kvm_io_bus_read(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, gpa_t addr,
>   	r = __kvm_io_bus_read(vcpu, bus, &range, val);
>   	return r < 0 ? r : 0;
>   }
> +EXPORT_SYMBOL_GPL(kvm_io_bus_read);
>   
>   /* Caller must hold slots_lock. */
>   int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,

Reviewed-by: Paolo Bonzini <pbonzini@xxxxxxxxxx>