Merge tag 'x86_tdx_for_v5.19_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull Intel TDX support from Borislav Petkov:
 "Intel Trust Domain Extensions (TDX) support.

  This is the Intel version of a confidential computing solution called
  Trust Domain Extensions (TDX). This series adds support to run the
  kernel as part of a TDX guest. It provides similar guest protections
  to AMD's SEV-SNP like guest memory and register state encryption,
  memory integrity protection and a lot more.

  Design-wise, it differs from AMD's solution considerably: it uses a
  software module which runs in a special CPU mode called (Secure
  Arbitration Mode) SEAM. As the name suggests, this module serves as
  sort of an arbiter which the confidential guest calls for services it
  needs during its lifetime.

  Just like AMD's SNP set, this series reworks and streamlines certain
  parts of x86 arch code so that this feature can be properly
  accomodated"

* tag 'x86_tdx_for_v5.19_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (34 commits)
  x86/tdx: Fix RETs in TDX asm
  x86/tdx: Annotate a noreturn function
  x86/mm: Fix spacing within memory encryption features message
  x86/kaslr: Fix build warning in KASLR code in boot stub
  Documentation/x86: Document TDX kernel architecture
  ACPICA: Avoid cache flush inside virtual machines
  x86/tdx/ioapic: Add shared bit for IOAPIC base address
  x86/mm: Make DMA memory shared for TD guest
  x86/mm/cpa: Add support for TDX shared memory
  x86/tdx: Make pages shared in ioremap()
  x86/topology: Disable CPU online/offline control for TDX guests
  x86/boot: Avoid #VE during boot for TDX platforms
  x86/boot: Set CR0.NE early and keep it set during the boot
  x86/acpi/x86/boot: Add multiprocessor wake-up support
  x86/boot: Add a trampoline for booting APs via firmware handoff
  x86/tdx: Wire up KVM hypercalls
  x86/tdx: Port I/O: Add early boot support
  x86/tdx: Port I/O: Add runtime hypercalls
  x86/boot: Port I/O: Add decompression-time support for TDX
  x86/boot: Port I/O: Allow to hook up alternative helpers
  ...

49 files changed, 1835 insertions, 120 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 4bed3abf444d..d90a33e96517 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -878,6 +878,21 @@ config ACRN_GUEST
 	  IOT with small footprint and real-time features. More details can be
 	  found in https://projectacrn.org/.
 
+config INTEL_TDX_GUEST
+	bool "Intel TDX (Trust Domain Extensions) - Guest Support"
+	depends on X86_64 && CPU_SUP_INTEL
+	depends on X86_X2APIC
+	select ARCH_HAS_CC_PLATFORM
+	select X86_MEM_ENCRYPT
+	select X86_MCE
+	help
+	  Support running as a guest under Intel TDX.  Without this support,
+	  the guest kernel can not boot or run under TDX.
+	  TDX includes memory encryption and integrity capabilities
+	  which protect the confidentiality and integrity of guest
+	  memory contents and CPU state. TDX guests are protected from
+	  some attacks from the VMM.
+
 endif #HYPERVISOR_GUEST
 
 source "arch/x86/Kconfig.cpu"
diff --git a/arch/x86/boot/boot.h b/arch/x86/boot/boot.h
index 34c9dbb6a47d..b42b91606ca8 100644
--- a/arch/x86/boot/boot.h
+++ b/arch/x86/boot/boot.h
@@ -26,6 +26,7 @@
 #include "bitops.h"
 #include "ctype.h"
 #include "cpuflags.h"
+#include "io.h"
 
 /* Useful macros */
 #define ARRAY_SIZE(x) (sizeof(x) / sizeof(*(x)))
@@ -35,44 +36,10 @@ extern struct boot_params boot_params;
 
 #define cpu_relax()	asm volatile("rep; nop")
 
-/* Basic port I/O */
-static inline void outb(u8 v, u16 port)
-{
-	asm volatile("outb %0,%1" : : "a" (v), "dN" (port));
-}
-static inline u8 inb(u16 port)
-{
-	u8 v;
-	asm volatile("inb %1,%0" : "=a" (v) : "dN" (port));
-	return v;
-}
-
-static inline void outw(u16 v, u16 port)
-{
-	asm volatile("outw %0,%1" : : "a" (v), "dN" (port));
-}
-static inline u16 inw(u16 port)
-{
-	u16 v;
-	asm volatile("inw %1,%0" : "=a" (v) : "dN" (port));
-	return v;
-}
-
-static inline void outl(u32 v, u16 port)
-{
-	asm volatile("outl %0,%1" : : "a" (v), "dN" (port));
-}
-static inline u32 inl(u16 port)
-{
-	u32 v;
-	asm volatile("inl %1,%0" : "=a" (v) : "dN" (port));
-	return v;
-}
-
 static inline void io_delay(void)
 {
 	const u16 DELAY_PORT = 0x80;
-	asm volatile("outb %%al,%0" : : "dN" (DELAY_PORT));
+	outb(0, DELAY_PORT);
 }
 
 /* These functions are used to reference data in other segments. */
diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index e69c3d2e0628..19e1905dcbf6 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -101,6 +101,7 @@ ifdef CONFIG_X86_64
 endif
 
 vmlinux-objs-$(CONFIG_ACPI) += $(obj)/acpi.o
+vmlinux-objs-$(CONFIG_INTEL_TDX_GUEST) += $(obj)/tdx.o $(obj)/tdcall.o
 
 vmlinux-objs-$(CONFIG_EFI_MIXED) += $(obj)/efi_thunk_$(BITS).o
 vmlinux-objs-$(CONFIG_EFI) += $(obj)/efi.o
diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S
index 4cd661165d4a..d33f060900d2 100644
--- a/arch/x86/boot/compressed/head_64.S
+++ b/arch/x86/boot/compressed/head_64.S
@@ -289,7 +289,7 @@ SYM_FUNC_START(startup_32)
 	pushl	%eax
 
 	/* Enter paged protected Mode, activating Long Mode */
-	movl	$(X86_CR0_PG | X86_CR0_PE), %eax /* Enable Paging and Protected mode */
+	movl	$CR0_STATE, %eax
 	movl	%eax, %cr0
 
 	/* Jump from 32bit compatibility mode into 64bit mode. */
@@ -649,12 +649,28 @@ SYM_CODE_START(trampoline_32bit_src)
 	movl	$MSR_EFER, %ecx
 	rdmsr
 	btsl	$_EFER_LME, %eax
+	/* Avoid writing EFER if no change was made (for TDX guest) */
+	jc	1f
 	wrmsr
-	popl	%edx
+1:	popl	%edx
 	popl	%ecx
 
+#ifdef CONFIG_X86_MCE
+	/*
+	 * Preserve CR4.MCE if the kernel will enable #MC support.
+	 * Clearing MCE may fault in some environments (that also force #MC
+	 * support). Any machine check that occurs before #MC support is fully
+	 * configured will crash the system regardless of the CR4.MCE value set
+	 * here.
+	 */
+	movl	%cr4, %eax
+	andl	$X86_CR4_MCE, %eax
+#else
+	movl	$0, %eax
+#endif
+
 	/* Enable PAE and LA57 (if required) paging modes */
-	movl	$X86_CR4_PAE, %eax
+	orl	$X86_CR4_PAE, %eax
 	testl	%edx, %edx
 	jz	1f
 	orl	$X86_CR4_LA57, %eax
@@ -668,8 +684,9 @@ SYM_CODE_START(trampoline_32bit_src)
 	pushl	$__KERNEL_CS
 	pushl	%eax
 
-	/* Enable paging again */
-	movl	$(X86_CR0_PG | X86_CR0_PE), %eax
+	/* Enable paging again. */
+	movl	%cr0, %eax
+	btsl	$X86_CR0_PG_BIT, %eax
 	movl	%eax, %cr0
 
 	lret
diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c
index ca6820f99b40..cf690d8712f4 100644
--- a/arch/x86/boot/compressed/misc.c
+++ b/arch/x86/boot/compressed/misc.c
@@ -48,6 +48,8 @@ void *memmove(void *dest, const void *src, size_t n);
  */
 struct boot_params *boot_params;
 
+struct port_io_ops pio_ops;
+
 memptr free_mem_ptr;
 memptr free_mem_end_ptr;
 
@@ -374,6 +376,16 @@ asmlinkage __visible void *extract_kernel(void *rmode, memptr heap,
 	lines = boot_params->screen_info.orig_video_lines;
 	cols = boot_params->screen_info.orig_video_cols;
 
+	init_default_io_ops();
+
+	/*
+	 * Detect TDX guest environment.
+	 *
+	 * It has to be done before console_init() in order to use
+	 * paravirtualized port I/O operations if needed.
+	 */
+	early_tdx_detect();
+
 	console_init();
 
 	/*
diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h
index 4ca2857ea041..4910bf230d7b 100644
--- a/arch/x86/boot/compressed/misc.h
+++ b/arch/x86/boot/compressed/misc.h
@@ -22,17 +22,19 @@
 #include <linux/linkage.h>
 #include <linux/screen_info.h>
 #include <linux/elf.h>
-#include <linux/io.h>
 #include <asm/page.h>
 #include <asm/boot.h>
 #include <asm/bootparam.h>
 #include <asm/desc_defs.h>
 
+#include "tdx.h"
+
 #define BOOT_CTYPE_H
 #include <linux/acpi.h>
 
 #define BOOT_BOOT_H
 #include "../ctype.h"
+#include "../io.h"
 
 #include "efi.h"
 
diff --git a/arch/x86/boot/compressed/pgtable.h b/arch/x86/boot/compressed/pgtable.h
index 6ff7e81b5628..cc9b2529a086 100644
--- a/arch/x86/boot/compressed/pgtable.h
+++ b/arch/x86/boot/compressed/pgtable.h
@@ -6,7 +6,7 @@
 #define TRAMPOLINE_32BIT_PGTABLE_OFFSET	0
 
 #define TRAMPOLINE_32BIT_CODE_OFFSET	PAGE_SIZE
-#define TRAMPOLINE_32BIT_CODE_SIZE	0x70
+#define TRAMPOLINE_32BIT_CODE_SIZE	0x80
 
 #define TRAMPOLINE_32BIT_STACK_END	TRAMPOLINE_32BIT_SIZE
 
diff --git a/arch/x86/boot/compressed/tdcall.S b/arch/x86/boot/compressed/tdcall.S
new file mode 100644
index 000000000000..46d0495e0d3a
--- /dev/null
+++ b/arch/x86/boot/compressed/tdcall.S
@@ -0,0 +1,3 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#include "../../coco/tdx/tdcall.S"
diff --git a/arch/x86/boot/compressed/tdx.c b/arch/x86/boot/compressed/tdx.c
new file mode 100644
index 000000000000..918a7606f53c
--- /dev/null
+++ b/arch/x86/boot/compressed/tdx.c
@@ -0,0 +1,77 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include "../cpuflags.h"
+#include "../string.h"
+#include "../io.h"
+#include "error.h"
+
+#include <vdso/limits.h>
+#include <uapi/asm/vmx.h>
+
+#include <asm/shared/tdx.h>
+
+/* Called from __tdx_hypercall() for unrecoverable failure */
+void __tdx_hypercall_failed(void)
+{
+	error("TDVMCALL failed. TDX module bug?");
+}
+
+static inline unsigned int tdx_io_in(int size, u16 port)
+{
+	struct tdx_hypercall_args args = {
+		.r10 = TDX_HYPERCALL_STANDARD,
+		.r11 = EXIT_REASON_IO_INSTRUCTION,
+		.r12 = size,
+		.r13 = 0,
+		.r14 = port,
+	};
+
+	if (__tdx_hypercall(&args, TDX_HCALL_HAS_OUTPUT))
+		return UINT_MAX;
+
+	return args.r11;
+}
+
+static inline void tdx_io_out(int size, u16 port, u32 value)
+{
+	struct tdx_hypercall_args args = {
+		.r10 = TDX_HYPERCALL_STANDARD,
+		.r11 = EXIT_REASON_IO_INSTRUCTION,
+		.r12 = size,
+		.r13 = 1,
+		.r14 = port,
+		.r15 = value,
+	};
+
+	__tdx_hypercall(&args, 0);
+}
+
+static inline u8 tdx_inb(u16 port)
+{
+	return tdx_io_in(1, port);
+}
+
+static inline void tdx_outb(u8 value, u16 port)
+{
+	tdx_io_out(1, port, value);
+}
+
+static inline void tdx_outw(u16 value, u16 port)
+{
+	tdx_io_out(2, port, value);
+}
+
+void early_tdx_detect(void)
+{
+	u32 eax, sig[3];
+
+	cpuid_count(TDX_CPUID_LEAF_ID, 0, &eax, &sig[0], &sig[2],  &sig[1]);
+
+	if (memcmp(TDX_IDENT, sig, sizeof(sig)))
+		return;
+
+	/* Use hypercalls instead of I/O instructions */
+	pio_ops.f_inb  = tdx_inb;
+	pio_ops.f_outb = tdx_outb;
+	pio_ops.f_outw = tdx_outw;
+}
diff --git a/arch/x86/boot/compressed/tdx.h b/arch/x86/boot/compressed/tdx.h
new file mode 100644
index 000000000000..9055482cd35c
--- /dev/null
+++ b/arch/x86/boot/compressed/tdx.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef BOOT_COMPRESSED_TDX_H
+#define BOOT_COMPRESSED_TDX_H
+
+#include <linux/types.h>
+
+#ifdef CONFIG_INTEL_TDX_GUEST
+void early_tdx_detect(void);
+#else
+static inline void early_tdx_detect(void) { };
+#endif
+
+#endif /* BOOT_COMPRESSED_TDX_H */
diff --git a/arch/x86/boot/cpuflags.c b/arch/x86/boot/cpuflags.c
index a0b75f73dc63..a83d67ec627d 100644
--- a/arch/x86/boot/cpuflags.c
+++ b/arch/x86/boot/cpuflags.c
@@ -71,8 +71,7 @@ int has_eflag(unsigned long mask)
 # define EBX_REG "=b"
 #endif
 
-static inline void cpuid_count(u32 id, u32 count,
-		u32 *a, u32 *b, u32 *c, u32 *d)
+void cpuid_count(u32 id, u32 count, u32 *a, u32 *b, u32 *c, u32 *d)
 {
 	asm volatile(".ifnc %%ebx,%3 ; movl  %%ebx,%3 ; .endif	\n\t"
 		     "cpuid					\n\t"
diff --git a/arch/x86/boot/cpuflags.h b/arch/x86/boot/cpuflags.h
index 2e20814d3ce3..475b8fde90f7 100644
--- a/arch/x86/boot/cpuflags.h
+++ b/arch/x86/boot/cpuflags.h
@@ -17,5 +17,6 @@ extern u32 cpu_vendor[3];
 
 int has_eflag(unsigned long mask);
 void get_cpuflags(void);
+void cpuid_count(u32 id, u32 count, u32 *a, u32 *b, u32 *c, u32 *d);
 
 #endif
diff --git a/arch/x86/boot/io.h b/arch/x86/boot/io.h
new file mode 100644
index 000000000000..110880907f87
--- /dev/null
+++ b/arch/x86/boot/io.h
@@ -0,0 +1,41 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef BOOT_IO_H
+#define BOOT_IO_H
+
+#include <asm/shared/io.h>
+
+#undef inb
+#undef inw
+#undef inl
+#undef outb
+#undef outw
+#undef outl
+
+struct port_io_ops {
+	u8	(*f_inb)(u16 port);
+	void	(*f_outb)(u8 v, u16 port);
+	void	(*f_outw)(u16 v, u16 port);
+};
+
+extern struct port_io_ops pio_ops;
+
+/*
+ * Use the normal I/O instructions by default.
+ * TDX guests override these to use hypercalls.
+ */
+static inline void init_default_io_ops(void)
+{
+	pio_ops.f_inb  = __inb;
+	pio_ops.f_outb = __outb;
+	pio_ops.f_outw = __outw;
+}
+
+/*
+ * Redirect port I/O operations via pio_ops callbacks.
+ * TDX guests override these callbacks with TDX-specific helpers.
+ */
+#define inb  pio_ops.f_inb
+#define outb pio_ops.f_outb
+#define outw pio_ops.f_outw
+
+#endif
diff --git a/arch/x86/boot/main.c b/arch/x86/boot/main.c
index e3add857c2c9..1202d4f8a390 100644
--- a/arch/x86/boot/main.c
+++ b/arch/x86/boot/main.c
@@ -17,6 +17,8 @@
 
 struct boot_params boot_params __attribute__((aligned(16)));
 
+struct port_io_ops pio_ops;
+
 char *HEAP = _end;
 char *heap_end = _end;		/* Default end of heap = no heap */
 
@@ -133,6 +135,8 @@ static void init_heap(void)
 
 void main(void)
 {
+	init_default_io_ops();
+
 	/* First, copy the boot header into the "zeropage" */
 	copy_boot_params();
 
diff --git a/arch/x86/coco/Makefile b/arch/x86/coco/Makefile
index c1ead00017a7..c816acf78b6a 100644
--- a/arch/x86/coco/Makefile
+++ b/arch/x86/coco/Makefile
@@ -4,3 +4,5 @@ KASAN_SANITIZE_core.o	:= n
 CFLAGS_core.o		+= -fno-stack-protector
 
 obj-y += core.o
+
+obj-$(CONFIG_INTEL_TDX_GUEST)	+= tdx/
diff --git a/arch/x86/coco/core.c b/arch/x86/coco/core.c
index dafd4881ce29..49b44f881484 100644
--- a/arch/x86/coco/core.c
+++ b/arch/x86/coco/core.c
@@ -18,7 +18,15 @@ static u64 cc_mask __ro_after_init;
 
 static bool intel_cc_platform_has(enum cc_attr attr)
 {
-	return false;
+	switch (attr) {
+	case CC_ATTR_GUEST_UNROLL_STRING_IO:
+	case CC_ATTR_HOTPLUG_DISABLED:
+	case CC_ATTR_GUEST_MEM_ENCRYPT:
+	case CC_ATTR_MEM_ENCRYPT:
+		return true;
+	default:
+		return false;
+	}
 }
 
 /*
@@ -90,9 +98,18 @@ EXPORT_SYMBOL_GPL(cc_platform_has);
 
 u64 cc_mkenc(u64 val)
 {
+	/*
+	 * Both AMD and Intel use a bit in the page table to indicate
+	 * encryption status of the page.
+	 *
+	 * - for AMD, bit *set* means the page is encrypted
+	 * - for Intel *clear* means encrypted.
+	 */
 	switch (vendor) {
 	case CC_VENDOR_AMD:
 		return val | cc_mask;
+	case CC_VENDOR_INTEL:
+		return val & ~cc_mask;
 	default:
 		return val;
 	}
@@ -100,9 +117,12 @@ u64 cc_mkenc(u64 val)
 
 u64 cc_mkdec(u64 val)
 {
+	/* See comment in cc_mkenc() */
 	switch (vendor) {
 	case CC_VENDOR_AMD:
 		return val & ~cc_mask;
+	case CC_VENDOR_INTEL:
+		return val | cc_mask;
 	default:
 		return val;
 	}
diff --git a/arch/x86/coco/tdx/Makefile b/arch/x86/coco/tdx/Makefile
new file mode 100644
index 000000000000..46c55998557d
--- /dev/null
+++ b/arch/x86/coco/tdx/Makefile
@@ -0,0 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0
+
+obj-y += tdx.o tdcall.o
diff --git a/arch/x86/coco/tdx/tdcall.S b/arch/x86/coco/tdx/tdcall.S
new file mode 100644
index 000000000000..f9eb1134f22d
--- /dev/null
+++ b/arch/x86/coco/tdx/tdcall.S
@@ -0,0 +1,205 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <asm/asm-offsets.h>
+#include <asm/asm.h>
+#include <asm/frame.h>
+#include <asm/unwind_hints.h>
+
+#include <linux/linkage.h>
+#include <linux/bits.h>
+#include <linux/errno.h>
+
+#include "../../virt/vmx/tdx/tdxcall.S"
+
+/*
+ * Bitmasks of exposed registers (with VMM).
+ */
+#define TDX_R10		BIT(10)
+#define TDX_R11		BIT(11)
+#define TDX_R12		BIT(12)
+#define TDX_R13		BIT(13)
+#define TDX_R14		BIT(14)
+#define TDX_R15		BIT(15)
+
+/*
+ * These registers are clobbered to hold arguments for each
+ * TDVMCALL. They are safe to expose to the VMM.
+ * Each bit in this mask represents a register ID. Bit field
+ * details can be found in TDX GHCI specification, section
+ * titled "TDCALL [TDG.VP.VMCALL] leaf".
+ */
+#define TDVMCALL_EXPOSE_REGS_MASK	( TDX_R10 | TDX_R11 | \
+					  TDX_R12 | TDX_R13 | \
+					  TDX_R14 | TDX_R15 )
+
+/*
+ * __tdx_module_call()  - Used by TDX guests to request services from
+ * the TDX module (does not include VMM services) using TDCALL instruction.
+ *
+ * Transforms function call register arguments into the TDCALL register ABI.
+ * After TDCALL operation, TDX module output is saved in @out (if it is
+ * provided by the user).
+ *
+ *-------------------------------------------------------------------------
+ * TDCALL ABI:
+ *-------------------------------------------------------------------------
+ * Input Registers:
+ *
+ * RAX                 - TDCALL Leaf number.
+ * RCX,RDX,R8-R9       - TDCALL Leaf specific input registers.
+ *
+ * Output Registers:
+ *
+ * RAX                 - TDCALL instruction error code.
+ * RCX,RDX,R8-R11      - TDCALL Leaf specific output registers.
+ *
+ *-------------------------------------------------------------------------
+ *
+ * __tdx_module_call() function ABI:
+ *
+ * @fn  (RDI)          - TDCALL Leaf ID,    moved to RAX
+ * @rcx (RSI)          - Input parameter 1, moved to RCX
+ * @rdx (RDX)          - Input parameter 2, moved to RDX
+ * @r8  (RCX)          - Input parameter 3, moved to R8
+ * @r9  (R8)           - Input parameter 4, moved to R9
+ *
+ * @out (R9)           - struct tdx_module_output pointer
+ *                       stored temporarily in R12 (not
+ *                       shared with the TDX module). It
+ *                       can be NULL.
+ *
+ * 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)
+
+/*
+ * __tdx_hypercall() - Make hypercalls to a TDX VMM using TDVMCALL leaf
+ * of TDCALL instruction
+ *
+ * Transforms values in  function call argument struct tdx_hypercall_args @args
+ * into the TDCALL register ABI. After TDCALL operation, VMM output is saved
+ * back in @args.
+ *
+ *-------------------------------------------------------------------------
+ * TD VMCALL ABI:
+ *-------------------------------------------------------------------------
+ *
+ * Input Registers:
+ *
+ * RAX                 - TDCALL instruction leaf number (0 - TDG.VP.VMCALL)
+ * RCX                 - BITMAP which controls which part of TD Guest GPR
+ *                       is passed as-is to the VMM and back.
+ * R10                 - Set 0 to indicate TDCALL follows standard TDX ABI
+ *                       specification. Non zero value indicates vendor
+ *                       specific ABI.
+ * R11                 - VMCALL sub function number
+ * RBX, RBP, RDI, RSI  - Used to pass VMCALL sub function specific arguments.
+ * R8-R9, R12-R15      - Same as above.
+ *
+ * Output Registers:
+ *
+ * RAX                 - TDCALL instruction status (Not related to hypercall
+ *                        output).
+ * R10                 - Hypercall output error code.
+ * R11-R15             - Hypercall sub function specific output values.
+ *
+ *-------------------------------------------------------------------------
+ *
+ * __tdx_hypercall() function ABI:
+ *
+ * @args  (RDI)        - struct tdx_hypercall_args for input and output
+ * @flags (RSI)        - TDX_HCALL_* flags
+ *
+ * On successful completion, return the hypercall error code.
+ */
+SYM_FUNC_START(__tdx_hypercall)
+	FRAME_BEGIN
+
+	/* Save callee-saved GPRs as mandated by the x86_64 ABI */
+	push %r15
+	push %r14
+	push %r13
+	push %r12
+
+	/* Mangle function call ABI into TDCALL ABI: */
+	/* Set TDCALL leaf ID (TDVMCALL (0)) in RAX */
+	xor %eax, %eax
+
+	/* Copy hypercall registers from arg struct: */
+	movq TDX_HYPERCALL_r10(%rdi), %r10
+	movq TDX_HYPERCALL_r11(%rdi), %r11
+	movq TDX_HYPERCALL_r12(%rdi), %r12
+	movq TDX_HYPERCALL_r13(%rdi), %r13
+	movq TDX_HYPERCALL_r14(%rdi), %r14
+	movq TDX_HYPERCALL_r15(%rdi), %r15
+
+	movl $TDVMCALL_EXPOSE_REGS_MASK, %ecx
+
+	/*
+	 * For the idle loop STI needs to be called directly before the TDCALL
+	 * that enters idle (EXIT_REASON_HLT case). STI instruction enables
+	 * interrupts only one instruction later. If there is a window between
+	 * STI and the instruction that emulates the HALT state, there is a
+	 * chance for interrupts to happen in this window, which can delay the
+	 * HLT operation indefinitely. Since this is the not the desired
+	 * result, conditionally call STI before TDCALL.
+	 */
+	testq $TDX_HCALL_ISSUE_STI, %rsi
+	jz .Lskip_sti
+	sti
+.Lskip_sti:
+	tdcall
+
+	/*
+	 * RAX==0 indicates a failure of the TDVMCALL mechanism itself and that
+	 * something has gone horribly wrong with the TDX module.
+	 *
+	 * The return status of the hypercall operation is in a separate
+	 * register (in R10). Hypercall errors are a part of normal operation
+	 * and are handled by callers.
+	 */
+	testq %rax, %rax