x86/tdx: Pass TDCALL/SEAMCALL input/output registers via a structure

Currently, the TDX_MODULE_CALL asm macro, which handles both TDCALL and
SEAMCALL, takes one parameter for each input register and an optional
'struct tdx_module_output' (a collection of output registers) as output.
This is different from the TDX_HYPERCALL macro which uses a single
'struct tdx_hypercall_args' to carry all input/output registers.

The newer TDX versions introduce more TDCALLs/SEAMCALLs which use more
input/output registers.  Also, the TDH.VP.ENTER (which isn't covered
by the current TDX_MODULE_CALL macro) basically can use all registers
that the TDX_HYPERCALL does.  The current TDX_MODULE_CALL macro isn't
extendible to cover those cases.

Similar to the TDX_HYPERCALL macro, simplify the TDX_MODULE_CALL macro
to use a single structure 'struct tdx_module_args' to carry all the
input/output registers.  Currently, R10/R11 are only used as output
register but not as input by any TDCALL/SEAMCALL.  Change to also use
R10/R11 as input register to make input/output registers symmetric.

Currently, the TDX_MODULE_CALL macro depends on the caller to pass a
non-NULL 'struct tdx_module_output' to get additional output registers.
Similar to the TDX_HYPERCALL macro, change the TDX_MODULE_CALL macro to
take a new 'ret' macro argument to indicate whether to save the output
registers to the 'struct tdx_module_args'.  Also introduce a new
__tdcall_ret() for that purpose, similar to the __tdx_hypercall_ret().

Note the tdcall(), which is a wrapper of __tdcall(), is called by three
callers: tdx_parse_tdinfo(), tdx_get_ve_info() and tdx_early_init().
The former two need the additional output but the last one doesn't.  For
simplicity, make tdcall() always call __tdcall_ret() to avoid another
"_ret()" wrapper.  The last caller tdx_early_init() isn't performance
critical anyway.

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/483616c1762d85eb3a3c3035a7de061cfacf2f14.1692096753.git.kai.huang%40intel.com

1 files changed, 25 insertions, 19 deletions

diff --git a/arch/x86/coco/tdx/tdx.c b/arch/x86/coco/tdx/tdx.c
index 9833c8140fca..0741a9dbf61f 100644
--- a/arch/x86/coco/tdx/tdx.c
+++ b/arch/x86/coco/tdx/tdx.c
@@ -66,10 +66,9 @@ EXPORT_SYMBOL_GPL(tdx_kvm_hypercall);
  * should only be used for calls that have no legitimate reason to fail
  * or where the kernel can not survive the call failing.
  */
-static inline void tdcall(u64 fn, u64 rcx, u64 rdx, u64 r8, u64 r9,
-			  struct tdx_module_output *out)
+static inline void tdcall(u64 fn, struct tdx_module_args *args)
 {
-	if (__tdcall(fn, rcx, rdx, r8, r9, out))
+	if (__tdcall_ret(fn, args))
 		panic("TDCALL %lld failed (Buggy TDX module!)\n", fn);
 }
 
@@ -89,11 +88,14 @@ static inline void tdcall(u64 fn, u64 rcx, u64 rdx, u64 r8, u64 r9,
  */
 int tdx_mcall_get_report0(u8 *reportdata, u8 *tdreport)
 {
+	struct tdx_module_args args = {
+		.rcx = virt_to_phys(tdreport),
+		.rdx = virt_to_phys(reportdata),
+		.r8 = TDREPORT_SUBTYPE_0,
+	};
 	u64 ret;
 
-	ret = __tdcall(TDG_MR_REPORT, virt_to_phys(tdreport),
-			virt_to_phys(reportdata), TDREPORT_SUBTYPE_0,
-			0, NULL);
+	ret = __tdcall(TDG_MR_REPORT, &args);
 	if (ret) {
 		if (TDCALL_RETURN_CODE(ret) == TDCALL_INVALID_OPERAND)
 			return -EINVAL;
@@ -141,7 +143,7 @@ static void __noreturn tdx_panic(const char *msg)
 
 static void tdx_parse_tdinfo(u64 *cc_mask)
 {
-	struct tdx_module_output out;
+	struct tdx_module_args args = {};
 	unsigned int gpa_width;
 	u64 td_attr;
 
@@ -152,7 +154,7 @@ static void tdx_parse_tdinfo(u64 *cc_mask)
 	 * Guest-Host-Communication Interface (GHCI), section 2.4.2 TDCALL
 	 * [TDG.VP.INFO].
 	 */
-	tdcall(TDG_VP_INFO, 0, 0, 0, 0, &out);
+	tdcall(TDG_VP_INFO, &args);
 
 	/*
 	 * The highest bit of a guest physical address is the "sharing" bit.
@@ -161,7 +163,7 @@ static void tdx_parse_tdinfo(u64 *cc_mask)
 	 * The GPA width that comes out of this call is critical. TDX guests
 	 * can not meaningfully run without it.
 	 */
-	gpa_width = out.rcx & GENMASK(5, 0);
+	gpa_width = args.rcx & GENMASK(5, 0);
 	*cc_mask = BIT_ULL(gpa_width - 1);
 
 	/*
@@ -169,7 +171,7 @@ static void tdx_parse_tdinfo(u64 *cc_mask)
 	 * memory.  Ensure that no #VE will be delivered for accesses to
 	 * TD-private memory.  Only VMM-shared memory (MMIO) will #VE.
 	 */
-	td_attr = out.rdx;
+	td_attr = args.rdx;
 	if (!(td_attr & ATTR_SEPT_VE_DISABLE)) {
 		const char *msg = "TD misconfiguration: SEPT_VE_DISABLE attribute must be set.";
 
@@ -577,7 +579,7 @@ __init bool tdx_early_handle_ve(struct pt_regs *regs)
 
 void tdx_get_ve_info(struct ve_info *ve)
 {
-	struct tdx_module_output out;
+	struct tdx_module_args args = {};
 
 	/*
 	 * Called during #VE handling to retrieve the #VE info from the
@@ -594,15 +596,15 @@ void tdx_get_ve_info(struct ve_info *ve)
 	 * Note, the TDX module treats virtual NMIs as inhibited if the #VE
 	 * valid flag is set. It means that NMI=>#VE will not result in a #DF.
 	 */
-	tdcall(TDG_VP_VEINFO_GET, 0, 0, 0, 0, &out);
+	tdcall(TDG_VP_VEINFO_GET, &args);
 
 	/* Transfer the output parameters */
-	ve->exit_reason = out.rcx;
-	ve->exit_qual   = out.rdx;
-	ve->gla         = out.r8;
-	ve->gpa         = out.r9;
-	ve->instr_len   = lower_32_bits(out.r10);
-	ve->instr_info  = upper_32_bits(out.r10);
+	ve->exit_reason = args.rcx;
+	ve->exit_qual   = args.rdx;
+	ve->gla         = args.r8;
+	ve->gpa         = args.r9;
+	ve->instr_len   = lower_32_bits(args.r10);
+	ve->instr_info  = upper_32_bits(args.r10);
 }
 
 /*
@@ -799,6 +801,10 @@ static bool tdx_enc_status_change_finish(unsigned long vaddr, int numpages,
 
 void __init tdx_early_init(void)
 {
+	struct tdx_module_args args = {
+		.rdx = TDCS_NOTIFY_ENABLES,
+		.r9 = -1ULL,
+	};
 	u64 cc_mask;
 	u32 eax, sig[3];
 
@@ -814,7 +820,7 @@ void __init tdx_early_init(void)
 	cc_set_mask(cc_mask);
 
 	/* Kernel does not use NOTIFY_ENABLES and does not need random #VEs */
-	tdcall(TDG_VM_WR, 0, TDCS_NOTIFY_ENABLES, 0, -1ULL, NULL);
+	tdcall(TDG_VM_WR, &args);
 
 	/*
 	 * All bits above GPA width are reserved and kernel treats shared bit