[6/7] KVM: TDX: Handle TDX PV port I/O hypercall

Commit Message

Binbin Wu Dec. 1, 2024, 3:53 a.m. UTC

From: Isaku Yamahata <[e-mail]>

Emulate port I/O requested by TDX guest via TDVMCALL with leaf
Instruction.IO (same value as EXIT_REASON_IO_INSTRUCTION) according to
TDX Guest Host Communication Interface (GHCI).

All port I/O instructions inside the TDX guest trigger the #VE exception.
On #VE triggered by I/O instructions, TDX guest can call TDVMCALL with
leaf Instruction.IO to request VMM to emulate I/O instructions.

Similar to normal port I/O emulation, try to handle the port I/O in kernel
first, if kernel can't support it, forward the request to userspace.

Note string I/O operations are not supported in TDX.  Guest should unroll them
before calling the TDVMCALL.

Signed-off-by: Isaku Yamahata <[e-mail]>
Co-developed-by: Binbin Wu <[e-mail]>
Signed-off-by: Binbin Wu <[e-mail]>
Reviewed-by: Paolo Bonzini <[e-mail]>
---
Hypercalls exit to userspace breakout:
- Renamed from "KVM: TDX: Handle TDX PV port io hypercall" to
  "KVM: TDX: Handle TDX PV port I/O hypercall".
- Update changelog.
- Add missing curly brackets.
- Move reset of pio.count to tdx_complete_pio_out() and remove the stale
  comment. (binbin)
- Use TDVMCALL_STATUS prefix for TDX call status codes (Binbin)
- Set status code to TDVMCALL_STATUS_SUCCESS when PIO is handled in kernel.
- Don't write to R11 when it is a write operation for output.

v18:
- Fix out case to set R10 and R11 correctly when user space handled port
  out.
---
 arch/x86/kvm/vmx/tdx.c | 66 ++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 66 insertions(+)

Patch

diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c
index a79f9ca962d1..495991407a95 100644
--- a/arch/x86/kvm/vmx/tdx.c
+++ b/arch/x86/kvm/vmx/tdx.c
@@ -1141,6 +1141,70 @@  static int tdx_report_fatal_error(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
+static int tdx_complete_pio_out(struct kvm_vcpu *vcpu)
+{
+	vcpu->arch.pio.count = 0;
+	tdvmcall_set_return_code(vcpu, TDVMCALL_STATUS_SUCCESS);
+	return 1;
+}
+
+static int tdx_complete_pio_in(struct kvm_vcpu *vcpu)
+{
+	struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt;
+	unsigned long val = 0;
+	int ret;
+
+	ret = ctxt->ops->pio_in_emulated(ctxt, vcpu->arch.pio.size,
+					 vcpu->arch.pio.port, &val, 1);
+
+	WARN_ON_ONCE(!ret);
+
+	tdvmcall_set_return_code(vcpu, TDVMCALL_STATUS_SUCCESS);
+	tdvmcall_set_return_val(vcpu, val);
+
+	return 1;
+}
+
+static int tdx_emulate_io(struct kvm_vcpu *vcpu)
+{
+	struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt;
+	unsigned long val = 0;
+	unsigned int port;
+	int size, ret;
+	bool write;
+
+	++vcpu->stat.io_exits;
+
+	size = tdvmcall_a0_read(vcpu);
+	write = tdvmcall_a1_read(vcpu);
+	port = tdvmcall_a2_read(vcpu);
+
+	if (size != 1 && size != 2 && size != 4) {
+		tdvmcall_set_return_code(vcpu, TDVMCALL_STATUS_INVALID_OPERAND);
+		return 1;
+	}
+
+	if (write) {
+		val = tdvmcall_a3_read(vcpu);
+		ret = ctxt->ops->pio_out_emulated(ctxt, size, port, &val, 1);
+	} else {
+		ret = ctxt->ops->pio_in_emulated(ctxt, size, port, &val, 1);
+	}
+
+	if (ret) {
+		if (!write)
+			tdvmcall_set_return_val(vcpu, val);
+		tdvmcall_set_return_code(vcpu, TDVMCALL_STATUS_SUCCESS);
+	} else {
+		if (write)
+			vcpu->arch.complete_userspace_io = tdx_complete_pio_out;
+		else
+			vcpu->arch.complete_userspace_io = tdx_complete_pio_in;
+	}
+
+	return ret;
+}
+
 static int handle_tdvmcall(struct kvm_vcpu *vcpu)
 {
 	if (tdvmcall_exit_type(vcpu))
@@ -1151,6 +1215,8 @@  static int handle_tdvmcall(struct kvm_vcpu *vcpu)
 		return tdx_map_gpa(vcpu);
 	case TDVMCALL_REPORT_FATAL_ERROR:
 		return tdx_report_fatal_error(vcpu);
+	case EXIT_REASON_IO_INSTRUCTION:
+		return tdx_emulate_io(vcpu);
 	default:
 		break;
 	}