[PATCH v14 090/113] KVM: TDX: Add KVM Exit for TDX TDG.VP.VMCALL

[isaku . yamahata]

From: Isaku Yamahata <isaku.yamahata@xxxxxxxxx>

Some of TDG.VP.VMCALL require device model, for example, qemu, to handle
them on behalf of kvm kernel module. TDG_VP_VMCALL_REPORT_FATAL_ERROR,
TDG_VP_VMCALL_MAP_GPA, TDG_VP_VMCALL_SETUP_EVENT_NOTIFY_INTERRUPT, and
TDG_VP_VMCALL_GET_QUOTE requires user space VMM handling.

Introduce new kvm exit, KVM_EXIT_TDX, and functions to setup it.
TDG_VP_VMCALL_INVALID_OPERAND is set as default return value to avoid
random value.  Device model should update R10 if necessary.

Signed-off-by: Isaku Yamahata <isaku.yamahata@xxxxxxxxx>
---
 arch/x86/kvm/vmx/tdx.c   | 98 +++++++++++++++++++++++++++++++++++++++-
 include/uapi/linux/kvm.h | 57 +++++++++++++++++++++++
 2 files changed, 153 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c
index 8d3a5f9d208a..d53e263794b4 100644
--- a/arch/x86/kvm/vmx/tdx.c
+++ b/arch/x86/kvm/vmx/tdx.c
@@ -123,6 +123,18 @@ BUILD_TDVMCALL_ACCESSORS(a1, r13);
 BUILD_TDVMCALL_ACCESSORS(a2, r14);
 BUILD_TDVMCALL_ACCESSORS(a3, r15);
 
+#define TDX_VMCALL_REG_MASK_RBX	BIT_ULL(2)
+#define TDX_VMCALL_REG_MASK_RDX	BIT_ULL(3)
+#define TDX_VMCALL_REG_MASK_RBP	BIT_ULL(5)
+#define TDX_VMCALL_REG_MASK_RSI	BIT_ULL(6)
+#define TDX_VMCALL_REG_MASK_RDI	BIT_ULL(7)
+#define TDX_VMCALL_REG_MASK_R8	BIT_ULL(8)
+#define TDX_VMCALL_REG_MASK_R9	BIT_ULL(9)
+#define TDX_VMCALL_REG_MASK_R12	BIT_ULL(12)
+#define TDX_VMCALL_REG_MASK_R13	BIT_ULL(13)
+#define TDX_VMCALL_REG_MASK_R14	BIT_ULL(14)
+#define TDX_VMCALL_REG_MASK_R15	BIT_ULL(15)
+
 static __always_inline unsigned long tdvmcall_exit_type(struct kvm_vcpu *vcpu)
 {
 	return kvm_r10_read(vcpu);
@@ -896,6 +908,80 @@ static int tdx_emulate_vmcall(struct kvm_vcpu *vcpu)
 	return 1;
 }
 
+static int tdx_complete_vp_vmcall(struct kvm_vcpu *vcpu)
+{
+	struct kvm_tdx_vmcall *tdx_vmcall = &vcpu->run->tdx.u.vmcall;
+	__u64 reg_mask;
+
+	tdvmcall_set_return_code(vcpu, tdx_vmcall->status_code);
+	tdvmcall_set_return_val(vcpu, tdx_vmcall->out_r11);
+
+	reg_mask = kvm_rcx_read(vcpu);
+	if (reg_mask & TDX_VMCALL_REG_MASK_R12)
+		kvm_r12_write(vcpu, tdx_vmcall->out_r12);
+	if (reg_mask & TDX_VMCALL_REG_MASK_R13)
+		kvm_r13_write(vcpu, tdx_vmcall->out_r13);
+	if (reg_mask & TDX_VMCALL_REG_MASK_R14)
+		kvm_r14_write(vcpu, tdx_vmcall->out_r14);
+	if (reg_mask & TDX_VMCALL_REG_MASK_R15)
+		kvm_r15_write(vcpu, tdx_vmcall->out_r15);
+	if (reg_mask & TDX_VMCALL_REG_MASK_RBX)
+		kvm_rbx_write(vcpu, tdx_vmcall->out_rbx);
+	if (reg_mask & TDX_VMCALL_REG_MASK_RDI)
+		kvm_rdi_write(vcpu, tdx_vmcall->out_rdi);
+	if (reg_mask & TDX_VMCALL_REG_MASK_RSI)
+		kvm_rsi_write(vcpu, tdx_vmcall->out_rsi);
+	if (reg_mask & TDX_VMCALL_REG_MASK_R8)
+		kvm_r8_write(vcpu, tdx_vmcall->out_r8);
+	if (reg_mask & TDX_VMCALL_REG_MASK_R9)
+		kvm_r9_write(vcpu, tdx_vmcall->out_r9);
+	if (reg_mask & TDX_VMCALL_REG_MASK_RDX)
+		kvm_rdx_write(vcpu, tdx_vmcall->out_rdx);
+
+	return 1;
+}
+
+static int tdx_vp_vmcall_to_user(struct kvm_vcpu *vcpu)
+{
+	struct kvm_tdx_vmcall *tdx_vmcall = &vcpu->run->tdx.u.vmcall;
+	__u64 reg_mask;
+
+	vcpu->arch.complete_userspace_io = tdx_complete_vp_vmcall;
+	memset(tdx_vmcall, 0, sizeof(*tdx_vmcall));
+
+	vcpu->run->exit_reason = KVM_EXIT_TDX;
+	vcpu->run->tdx.type = KVM_EXIT_TDX_VMCALL;
+	tdx_vmcall->type = tdvmcall_exit_type(vcpu);
+	tdx_vmcall->subfunction = tdvmcall_leaf(vcpu);
+	tdx_vmcall->status_code = TDG_VP_VMCALL_INVALID_OPERAND;
+
+	reg_mask = kvm_rcx_read(vcpu);
+	tdx_vmcall->reg_mask = reg_mask;
+	if (reg_mask & TDX_VMCALL_REG_MASK_R12)
+		tdx_vmcall->in_r12 = kvm_r12_read(vcpu);
+	if (reg_mask & TDX_VMCALL_REG_MASK_R13)
+		tdx_vmcall->in_r13 = kvm_r13_read(vcpu);
+	if (reg_mask & TDX_VMCALL_REG_MASK_R14)
+		tdx_vmcall->in_r14 = kvm_r14_read(vcpu);
+	if (reg_mask & TDX_VMCALL_REG_MASK_R15)
+		tdx_vmcall->in_r15 = kvm_r15_read(vcpu);
+	if (reg_mask & TDX_VMCALL_REG_MASK_RBX)
+		tdx_vmcall->in_rbx = kvm_rbx_read(vcpu);
+	if (reg_mask & TDX_VMCALL_REG_MASK_RDI)
+		tdx_vmcall->in_rdi = kvm_rdi_read(vcpu);
+	if (reg_mask & TDX_VMCALL_REG_MASK_RSI)
+		tdx_vmcall->in_rsi = kvm_rsi_read(vcpu);
+	if (reg_mask & TDX_VMCALL_REG_MASK_R8)
+		tdx_vmcall->in_r8 = kvm_r8_read(vcpu);
+	if (reg_mask & TDX_VMCALL_REG_MASK_R9)
+		tdx_vmcall->in_r9 = kvm_r9_read(vcpu);
+	if (reg_mask & TDX_VMCALL_REG_MASK_RDX)
+		tdx_vmcall->in_rdx = kvm_rdx_read(vcpu);
+
+	/* notify userspace to handle the request */
+	return 0;
+}
+
 static int handle_tdvmcall(struct kvm_vcpu *vcpu)
 {
 	if (tdvmcall_exit_type(vcpu))
@@ -906,8 +992,16 @@ static int handle_tdvmcall(struct kvm_vcpu *vcpu)
 		break;
 	}
 
-	tdvmcall_set_return_code(vcpu, TDG_VP_VMCALL_INVALID_OPERAND);
-	return 1;
+	/*
+	 * Unknown VMCALL.  Toss the request to the user space VMM, e.g. qemu,
+	 * as it may know how to handle.
+	 *
+	 * Those VMCALLs require user space VMM:
+	 * TDG_VP_VMCALL_REPORT_FATAL_ERROR, TDG_VP_VMCALL_MAP_GPA,
+	 * TDG_VP_VMCALL_SETUP_EVENT_NOTIFY_INTERRUPT, and
+	 * TDG_VP_VMCALL_GET_QUOTE.
+	 */
+	return tdx_vp_vmcall_to_user(vcpu);
 }
 
 void tdx_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa, int pgd_level)
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 18705e661c9e..7edcbef7626b 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -237,6 +237,60 @@ struct kvm_xen_exit {
 	} u;
 };
 
+struct kvm_tdx_exit {
+#define KVM_EXIT_TDX_VMCALL	1
+	__u32 type;
+	__u32 pad;
+
+	union {
+		struct kvm_tdx_vmcall {
+			/*
+			 * Guest-Host-Communication Interface for TDX spec
+			 * defines the ABI for TDG.VP.VMCALL.
+			 */
+
+			/* Input parameters: guest -> VMM */
+			__u64 type;		/* r10 */
+			__u64 subfunction;	/* r11 */
+			__u64 reg_mask;		/* rcx */
+			/*
+			 * Subfunction specific.
+			 * Registers are used in this order to pass input
+			 * arguments.  r12=arg0, r13=arg1, etc.
+			 */
+			__u64 in_r12;
+			__u64 in_r13;
+			__u64 in_r14;
+			__u64 in_r15;
+			__u64 in_rbx;
+			__u64 in_rdi;
+			__u64 in_rsi;
+			__u64 in_r8;
+			__u64 in_r9;
+			__u64 in_rdx;
+
+			/* Output parameters: VMM -> guest */
+			__u64 status_code;	/* r10 */
+			/*
+			 * Subfunction specific.
+			 * Registers are used in this order to output return
+			 * values.  r11=ret0, r12=ret1, etc.
+			 */
+			__u64 out_r11;
+			__u64 out_r12;
+			__u64 out_r13;
+			__u64 out_r14;
+			__u64 out_r15;
+			__u64 out_rbx;
+			__u64 out_rdi;
+			__u64 out_rsi;
+			__u64 out_r8;
+			__u64 out_r9;
+			__u64 out_rdx;
+		} vmcall;
+	} u;
+};
+
 #define KVM_S390_GET_SKEYS_NONE   1
 #define KVM_S390_SKEYS_MAX        1048576
 
@@ -279,6 +333,7 @@ struct kvm_xen_exit {
 #define KVM_EXIT_RISCV_CSR        36
 #define KVM_EXIT_NOTIFY           37
 #define KVM_EXIT_MEMORY_FAULT     38
+#define KVM_EXIT_TDX              39
 
 /* For KVM_EXIT_INTERNAL_ERROR */
 /* Emulate instruction failed. */
@@ -532,6 +587,8 @@ struct kvm_run {
 			__u64 gpa;
 			__u64 size;
 		} memory;
+		/* KVM_EXIT_TDX_VMCALL */
+		struct kvm_tdx_exit tdx;
 		/* Fix the size of the union. */
 		char padding[256];
 	};
-- 
2.25.1