x86/tdx: Skip saving output regs when SEAMCALL fails with VMFailInvalid

If SEAMCALL fails with VMFailInvalid, the SEAM software (e.g., the TDX
module) won't have chance to set any output register.  Skip saving the
output registers to the structure in this case.

Also, as '.Lno_output_struct' is the very last symbol before RET, rename
it to '.Lout' to make it short.

Opportunistically make the asm directives unindented.
Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Kai Huang <kai.huang@intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/all/704088f5b4d72c7e24084f7f15bd1ac5005b7213.1692096753.git.kai.huang%40intel.com

arch/x86/coco/tdx/tdcall.S

@@ -78,10 +78,7 @@
  * Return status of TDCALL via RAX.
  */
 SYM_FUNC_START(__tdx_module_call)
-	FRAME_BEGIN
 	TDX_MODULE_CALL host=0
-	FRAME_END
-	RET
 SYM_FUNC_END(__tdx_module_call)
 
 /*

arch/x86/virt/vmx/tdx/tdxcall.S

 /* SPDX-License-Identifier: GPL-2.0 */
 #include <asm/asm-offsets.h>
+#include <asm/frame.h>
 #include <asm/tdx.h>
 
 /*
@@ -18,6 +19,7 @@
  *            TDX module.
  */
 .macro TDX_MODULE_CALL host:req
+	FRAME_BEGIN
 	/*
 	 * R12 will be used as temporary storage for struct tdx_module_output
 	 * pointer. Since R12-R15 registers are not used by TDCALL/SEAMCALL
@@ -44,7 +46,7 @@
 	mov %rsi, %rcx
 	/* Leave input param 2 in RDX */
 
-	.if \host
+.if \host
 	seamcall
 	/*
 	 * SEAMCALL instruction is essentially a VMExit from VMX root
@@ -57,13 +59,10 @@
 	 * This value will never be used as actual SEAMCALL error code as
 	 * it is from the Reserved status code class.
 	 */
-	jnc .Lno_vmfailinvalid
-	mov $TDX_SEAMCALL_VMFAILINVALID, %rax
-.Lno_vmfailinvalid:
-
-	.else
+	jc .Lseamcall_vmfailinvalid
+.else
 	tdcall
-	.endif
+.endif
 
 	/*
 	 * Fetch output pointer from stack to R12 (It is used
@@ -80,7 +79,7 @@
 	 * Other registers may contain details of the failure.
 	 */
 	test %r12, %r12
-	jz .Lno_output_struct
+	jz .Lout
 
 	/* Copy result registers to output struct: */
 	movq %rcx, TDX_MODULE_rcx(%r12)
@@ -90,7 +89,19 @@
 	movq %r10, TDX_MODULE_r10(%r12)
 	movq %r11, TDX_MODULE_r11(%r12)
 
-.Lno_output_struct:
+.Lout:
 	/* Restore the state of R12 register */
 	pop %r12
+
+	FRAME_END
+	RET
+
+.if \host
+.Lseamcall_vmfailinvalid:
+	mov $TDX_SEAMCALL_VMFAILINVALID, %rax
+	/* pop the unused output pointer back to %r9 */
+	pop %r9
+	jmp .Lout
+.endif	/* \host */
+
 .endm