KVM: TDX: Handle TDX PV MMIO hypercall

Handle TDX PV MMIO hypercall when TDX guest calls TDVMCALL with the
leaf #VE.RequestMMIO (same value as EXIT_REASON_EPT_VIOLATION) according
to TDX Guest Host Communication Interface (GHCI) spec.

For TDX guests, VMM is not allowed to access vCPU registers and the private
memory, and the code instructions must be fetched from the private memory.
So MMIO emulation implemented for non-TDX VMs is not possible for TDX
guests.

In TDX the MMIO regions are instead configured by VMM to trigger a #VE
exception in the guest.  The #VE handling is supposed to emulate the MMIO
instruction inside the guest and convert it into a TDVMCALL with the
leaf #VE.RequestMMIO, which equals to EXIT_REASON_EPT_VIOLATION.

The requested MMIO address must be in shared GPA space.  The shared bit
is stripped after check because the existing code for MMIO emulation is
not aware of the shared bit.

The MMIO GPA shouldn't have a valid memslot, also the attribute of the GPA
should be shared.  KVM could do the checks before exiting to userspace,
however, even if KVM does the check, there still will be race conditions
between the check in KVM and the emulation of MMIO access in userspace due
to a memslot hotplug, or a memory attribute conversion.  If userspace
doesn't check the attribute of the GPA and the attribute happens to be
private, it will not pose a security risk or cause an MCE, but it can lead
to another issue. E.g., in QEMU, treating a GPA with private attribute as
shared when it falls within RAM's range can result in extra memory
consumption during the emulation to the access to the HVA of the GPA.
There are two options: 1) Do the check both in KVM and userspace.  2) Do
the check only in QEMU.  This patch chooses option 2, i.e. KVM omits the
memslot and attribute checks, and expects userspace to do the checks.

Similar to normal MMIO emulation, try to handle the MMIO in kernel first,
if kernel can't support it, forward the request to userspace.  Export
needed symbols used for MMIO handling.

Fragments handling is not needed for TDX PV MMIO because GPA is provided,
if a MMIO access crosses page boundary, it should be continuous in GPA.
Also, the size is limited to 1, 2, 4, 8 bytes.  No further split needed.
Allow cross page access because no extra handling needed after checking
both start and end GPA are shared GPAs.

Suggested-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Isaku Yamahata <isaku.yamahata@intel.com>
Co-developed-by: Binbin Wu <binbin.wu@linux.intel.com>
Signed-off-by: Binbin Wu <binbin.wu@linux.intel.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Message-ID: <20250222014225.897298-10-binbin.wu@linux.intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

Author: Sean Christopherson

arch/x86/kvm/vmx/tdx.c

@@ -810,6 +810,8 @@ static __always_inline u32 tdcall_to_vmx_exit_reason(struct kvm_vcpu *vcpu)
 	switch (tdvmcall_leaf(vcpu)) {
 	case EXIT_REASON_IO_INSTRUCTION:
 		return tdvmcall_leaf(vcpu);
+	case EXIT_REASON_EPT_VIOLATION:
+		return EXIT_REASON_EPT_MISCONFIG;
 	default:
 		break;
 	}
@@ -1190,6 +1192,107 @@ static int tdx_emulate_io(struct kvm_vcpu *vcpu)
 	return ret;
 }
 
+static int tdx_complete_mmio_read(struct kvm_vcpu *vcpu)
+{
+	unsigned long val = 0;
+	gpa_t gpa;
+	int size;
+
+	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_io_bus_write(vcpu, KVM_FAST_MMIO_BUS, gpa, 0, NULL)) {
+		trace_kvm_fast_mmio(gpa);
+		return 0;
+	}
+
+	trace_kvm_mmio(KVM_TRACE_MMIO_WRITE, size, gpa, &val);
+	if (kvm_io_bus_write(vcpu, KVM_MMIO_BUS, gpa, size, &val))
+		return -EOPNOTSUPP;
+
+	return 0;
+}
+
+static inline int tdx_mmio_read(struct kvm_vcpu *vcpu, gpa_t gpa, int size)
+{
+	unsigned long val;
+
+	if (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 vcpu_tdx *tdx = to_tdx(vcpu);
+	int size, write, r;
+	unsigned long val;
+	gpa_t gpa;
+
+	size = tdx->vp_enter_args.r12;
+	write = tdx->vp_enter_args.r13;
+	gpa = tdx->vp_enter_args.r14;
+	val = write ? tdx->vp_enter_args.r15 : 0;
+
+	if (size != 1 && size != 2 && size != 4 && size != 8)
+		goto error;
+	if (write != 0 && write != 1)
+		goto error;
+
+	/*
+	 * TDG.VP.VMCALL<MMIO> allows only shared GPA, it makes no sense to
+	 * do MMIO emulation for private GPA.
+	 */
+	if (vt_is_tdx_private_gpa(vcpu->kvm, gpa) ||
+	    vt_is_tdx_private_gpa(vcpu->kvm, gpa + size - 1))
+		goto error;
+
+	gpa = gpa & ~gfn_to_gpa(kvm_gfn_direct_bits(vcpu->kvm));
+
+	if (write)
+		r = tdx_mmio_write(vcpu, gpa, size, val);
+	else
+		r = tdx_mmio_read(vcpu, gpa, size);
+	if (!r)
+		/* Kernel completed device emulation. */
+		return 1;
+
+	/* Request the device emulation to userspace device model. */
+	vcpu->mmio_is_write = write;
+	if (!write)
+		vcpu->arch.complete_userspace_io = tdx_complete_mmio_read;
+
+	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, TDVMCALL_STATUS_INVALID_OPERAND);
+	return 1;
+}
+
 static int handle_tdvmcall(struct kvm_vcpu *vcpu)
 {
 	switch (tdvmcall_leaf(vcpu)) {
@@ -1569,6 +1672,8 @@ int tdx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t fastpath)
 		return tdx_emulate_vmcall(vcpu);
 	case EXIT_REASON_IO_INSTRUCTION:
 		return tdx_emulate_io(vcpu);
+	case EXIT_REASON_EPT_MISCONFIG:
+		return tdx_emulate_mmio(vcpu);
 	default:
 		break;
 	}

arch/x86/kvm/x86.c

@@ -14024,6 +14024,7 @@ EXPORT_SYMBOL_GPL(kvm_sev_es_string_io);
 
 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);

virt/kvm/kvm_main.c

@@ -5842,6 +5842,7 @@ 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);
 
 int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
 			    int len, struct kvm_io_device *dev)