[PATCH v3 0/2] x86/tdx: Use TDVMCALLs directly for earlyprintk

[PATCH v3 0/2] x86/tdx: Use TDVMCALLs directly for earlyprintk

[Vishal Verma]

Background
==========

TDX guests have early_printk support, but it is through a roundabout way
using a #VE exception as a functional mechanism. The exception handler
has to use TDG.VP.VEINFO.GET to find out what faulted, and then issue
the TDVMCALL. Simplify this by using a TDVMCALL from the guest which can
directly perform the port I/O.

Patch details
=============

Patch 1 is a prep patch that moves the port I/O direction constants to
arch/x86/include/asm/shared/tdx.h.

Patch 2: Add a new earlyprintk=tdx option, which calls the new tdx_inb()
/ tdx_outb() helpers to perform the port I/O directly using TDVMCALLs.

The serial earlyprintk path is left as is - TD guests using this will
still take a #VE exception, and the exception handler will perform the
I/O.

Testing
=======

Added a counter for the number of COM1 port I/O #VEs handled:

  no earlyprintk     -  ~63000
  earlyprintk=ttyS0  -  ~61000
  earlyprintk=tdx    -  ~35000

The new tdx option nearly halves the number of #VEs handled.

Additionally, ran the usual suite of CI testing, which covers KVM self
tests, KVM unit tests, and Avocado KVM tests without any regressions.

Signed-off-by: Vishal Verma <vishal.l.verma@intel.com>
---
Changes in v3:
- Drop the ttySN and baudrate option parsing for earlyprintk=tdx (Dave Hansen)
- Link to v2: https://patch.msgid.link/20260921-b4-tdx_earlyprintk_tdcalls-v2-0-ad1fde3f25fd@intel.com

Changes in v2:
- Rebase to v7.3-rc4
- Move the TDX hypercall helpers into coco/tdx/tdx.c (Kiryl)
- Add a new earlyprintk=tdx option that implements the direct TDVMCALL
  path (Dave Hansen)
- Link to v1: https://patch.msgid.link/20260910-b4-tdx_earlyprintk_tdcalls-v1-0-4b2b1bf9001b@intel.com

---
Vishal Verma (2):
      x86/tdx: Move port I/O definitions to a shared header
      x86/early_printk: Add earlyprintk=tdx to drive the UART with TDVMCALLs

 Documentation/admin-guide/kernel-parameters.txt |  9 +++++
 arch/x86/include/asm/shared/tdx.h               |  6 ++++
 arch/x86/include/asm/tdx.h                      |  3 ++
 arch/x86/boot/compressed/tdx.c                  |  4 +--
 arch/x86/coco/tdx/tdx.c                         | 47 +++++++++++++++++++++----
 arch/x86/kernel/early_printk.c                  | 41 +++++++++++++++++++++
 6 files changed, 102 insertions(+), 8 deletions(-)
---
base-commit: 93f51579e7df248780214094418f205253383cc5
change-id: 20260903-b4-tdx_earlyprintk_tdcalls-40d1b21a8ba2

Best regards,
--  
Vishal Verma <vishal.l.verma@intel.com>

[PATCH v3 1/2] x86/tdx: Move port I/O definitions to a shared header

[Vishal Verma]

In preparation for adding a 'tdx' option for early_printk which uses
direct TDVMCALLs for I/O, factor out the PORT_READ and PORT_WRITE
definitions from arch/x86/coco/tdx/tdx.c into
arch/x86/include/asm/shared/tdx.h, and namespace them with 'TDVMCALL_'.

The decompressor also used 0/1 literals in its tdx_io_{in,out} helpers -
switch those to use the new definitions.

Signed-off-by: Vishal Verma <vishal.l.verma@intel.com>
Reviewed-by: Kiryl Shutsemau (Meta) <kas@kernel.org>
Cc: Rick Edgecombe <rick.p.edgecombe@intel.com>
---
 arch/x86/include/asm/shared/tdx.h | 6 ++++++
 arch/x86/boot/compressed/tdx.c    | 4 ++--
 arch/x86/coco/tdx/tdx.c           | 8 ++------
 3 files changed, 10 insertions(+), 8 deletions(-)

diff --git a/arch/x86/include/asm/shared/tdx.h b/arch/x86/include/asm/shared/tdx.h
index f20e91d7ac35..ecaf965f059b 100644
--- a/arch/x86/include/asm/shared/tdx.h
+++ b/arch/x86/include/asm/shared/tdx.h
@@ -84,6 +84,12 @@
 #define TDVMCALL_STATUS_ALIGN_ERROR	0x8000000000000002ULL
 #define TDVMCALL_STATUS_SUBFUNC_UNSUPPORTED	0x8000000000000003ULL
 
+/*
+ * TDG.VP.VMCALL<Instruction.IO> direction (passed in R13)
+ */
+#define TDVMCALL_PORT_READ		0
+#define TDVMCALL_PORT_WRITE		1
+
 /*
  * Bitmasks of exposed registers (with VMM).
  */
diff --git a/arch/x86/boot/compressed/tdx.c b/arch/x86/boot/compressed/tdx.c
index 8451d6a1030c..ed278bac3c93 100644
--- a/arch/x86/boot/compressed/tdx.c
+++ b/arch/x86/boot/compressed/tdx.c
@@ -22,7 +22,7 @@ static inline unsigned int tdx_io_in(int size, u16 port)
 		.r10 = TDX_HYPERCALL_STANDARD,
 		.r11 = hcall_func(EXIT_REASON_IO_INSTRUCTION),
 		.r12 = size,
-		.r13 = 0,
+		.r13 = TDVMCALL_PORT_READ,
 		.r14 = port,
 	};
 
@@ -38,7 +38,7 @@ static inline void tdx_io_out(int size, u16 port, u32 value)
 		.r10 = TDX_HYPERCALL_STANDARD,
 		.r11 = hcall_func(EXIT_REASON_IO_INSTRUCTION),
 		.r12 = size,
-		.r13 = 1,
+		.r13 = TDVMCALL_PORT_WRITE,
 		.r14 = port,
 		.r15 = value,
 	};
diff --git a/arch/x86/coco/tdx/tdx.c b/arch/x86/coco/tdx/tdx.c
index f904a636d449..7d1a93ee2534 100644
--- a/arch/x86/coco/tdx/tdx.c
+++ b/arch/x86/coco/tdx/tdx.c
@@ -24,10 +24,6 @@
 #define EPT_READ	0
 #define EPT_WRITE	1
 
-/* Port I/O direction */
-#define PORT_READ	0
-#define PORT_WRITE	1
-
 /* See Exit Qualification for I/O Instructions in VMX documentation */
 #define VE_IS_IO_IN(e)		((e) & BIT(3))
 #define VE_GET_IO_SIZE(e)	(((e) & GENMASK(2, 0)) + 1)
@@ -691,7 +687,7 @@ static bool handle_in(struct pt_regs *regs, int size, int port)
 		.r10 = TDX_HYPERCALL_STANDARD,
 		.r11 = hcall_func(EXIT_REASON_IO_INSTRUCTION),
 		.r12 = size,
-		.r13 = PORT_READ,
+		.r13 = TDVMCALL_PORT_READ,
 		.r14 = port,
 	};
 	bool success;
@@ -720,7 +716,7 @@ static bool handle_out(struct pt_regs *regs, int size, int port)
 	 * "TDG.VP.VMCALL<Instruction.IO>".
 	 */
 	return !_tdx_hypercall(hcall_func(EXIT_REASON_IO_INSTRUCTION), size,
-			       PORT_WRITE, port, regs->ax & mask);
+			       TDVMCALL_PORT_WRITE, port, regs->ax & mask);
 }
 
 /*

-- 
2.55.0

[PATCH v3 2/2] x86/early_printk: Add earlyprintk=tdx to drive the UART with TDVMCALLs

[Vishal Verma]

A TDX guest cannot execute port I/O instructions directly, but
earlyprintk's serial console still issues plain inb()/outb() and lets
each one fault into the #VE handler to be emulated as a TDVMCALL.

While that works, it is a roundabout way to get a character out.
early_serial_putc() polls the LSR, and then writes a byte, but since the
TDX guest can't directly do port I/O, a #VE exception is raised. The #VE
handler must call TDG.VP.VEINFO.GET to find out what faulted, and then
it can issue the TDVMCALL that does the actual work.

This makes #VE a functional mechanism for doing I/O, which is not
desirable, is unnecessarily complicated and fragile, and results in
twice the number of calls into the TDX module.

Instead, add an earlyprintk=tdx option, which can issue the TDVMCALLs
directly. Add a pair of tdx_serial_in() and tdx_serial_out() accessors
and set them up in this case.

Note that the output does not appear any earlier - "earlyprintk=" is an
early_param(), so the console is still registered from
parse_early_param(). This only changes how the bytes leave the guest
once it is up.

LLMs were used under supervision to create this patch, to help
understand the scope and mechanisms, create testing instrumentation
(throwaway) to count #VEs in the serial vs tdx earlyprintk setups,
and to drive lab machines to do this testing.

Signed-off-by: Vishal Verma <vishal.l.verma@intel.com>
---
 Documentation/admin-guide/kernel-parameters.txt |  9 ++++++
 arch/x86/include/asm/tdx.h                      |  3 ++
 arch/x86/coco/tdx/tdx.c                         | 39 +++++++++++++++++++++++
 arch/x86/kernel/early_printk.c                  | 41 +++++++++++++++++++++++++
 4 files changed, 92 insertions(+)

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 33cd30996e47..f8dac4a58327 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -1543,6 +1543,7 @@ Kernel parameters
 			earlyprintk=serial[,ttySn[,baudrate]]
 			earlyprintk=serial[,0x...[,baudrate]]
 			earlyprintk=ttySn[,baudrate]
+			earlyprintk=tdx
 			earlyprintk=dbgp[debugController#]
 			earlyprintk=mmio32,membase[,{nocfg|baudrate}]
 			earlyprintk=pciserial[,force],bus:device.function[,{nocfg|baudrate}]
@@ -1556,6 +1557,14 @@ Kernel parameters
 			Use "nocfg" to skip UART configuration, assume
 			BIOS/firmware has configured UART correctly.
 
+			On x86, "tdx" is a fixed COM1 console, and takes no
+			options. In a TDX guest the port is driven with
+			TDVMCALLs rather than port I/O instructions, avoiding
+			the #VE exception that would otherwise be taken to
+			emulate every access. Outside a TDX guest it falls back
+			to port I/O, behaving like "earlyprintk=serial". If
+			CONFIG_INTEL_TDX_GUEST is not set, it is ignored.
+
 			Append ",keep" to not disable it when the real console
 			takes over.
 
diff --git a/arch/x86/include/asm/tdx.h b/arch/x86/include/asm/tdx.h
index 89e97d5761d8..325dd7c5929f 100644
--- a/arch/x86/include/asm/tdx.h
+++ b/arch/x86/include/asm/tdx.h
@@ -83,6 +83,9 @@ int tdx_mcall_extend_rtmr(u8 index, u8 *data);
 
 u64 tdx_hcall_get_quote(u8 *buf, size_t size);
 
+u8 tdx_inb(u16 port);
+void tdx_outb(u8 value, u16 port);
+
 void __init tdx_dump_attributes(u64 td_attr);
 void __init tdx_dump_td_ctls(u64 td_ctls);
 
diff --git a/arch/x86/coco/tdx/tdx.c b/arch/x86/coco/tdx/tdx.c
index 7d1a93ee2534..d8887a2a524b 100644
--- a/arch/x86/coco/tdx/tdx.c
+++ b/arch/x86/coco/tdx/tdx.c
@@ -194,6 +194,45 @@ u64 tdx_hcall_get_quote(u8 *buf, size_t size)
 }
 EXPORT_SYMBOL_GPL(tdx_hcall_get_quote);
 
+/**
+ * tdx_inb() - Read a byte from an I/O port without a #VE
+ * @port: I/O port to read from
+ *
+ * Ask the VMM to perform the read with TDG.VP.VMCALL<Instruction.IO>, rather
+ * than executing an IN instruction and having the resulting #VE emulate it.
+ *
+ * Return: the byte read, or 0xFF if the hypercall failed.
+ */
+u8 tdx_inb(u16 port)
+{
+	struct tdx_module_args args = {
+		.r10 = TDX_HYPERCALL_STANDARD,
+		.r11 = hcall_func(EXIT_REASON_IO_INSTRUCTION),
+		.r12 = 1,
+		.r13 = TDVMCALL_PORT_READ,
+		.r14 = port,
+	};
+
+	if (__tdx_hypercall(&args))
+		return 0xFF;
+
+	return args.r11;
+}
+
+/**
+ * tdx_outb() - Write a byte to an I/O port without a #VE
+ * @value: byte to write
+ * @port: I/O port to write to
+ *
+ * Ask the VMM to perform the write with TDG.VP.VMCALL<Instruction.IO>, rather
+ * than executing an OUT instruction and having the resulting #VE emulate it.
+ */
+void tdx_outb(u8 value, u16 port)
+{
+	_tdx_hypercall(hcall_func(EXIT_REASON_IO_INSTRUCTION), 1,
+		       TDVMCALL_PORT_WRITE, port, value);
+}
+
 static void __noreturn tdx_panic(const char *msg)
 {
 	struct tdx_module_args args = {
diff --git a/arch/x86/kernel/early_printk.c b/arch/x86/kernel/early_printk.c
index cba75306e5b6..194737a3e9a0 100644
--- a/arch/x86/kernel/early_printk.c
+++ b/arch/x86/kernel/early_printk.c
@@ -21,6 +21,7 @@
 #include <linux/usb/xhci-dbgp.h>
 #include <asm/pci_x86.h>
 #include <linux/static_call.h>
+#include <asm/tdx.h>
 
 /* Simple VGA output */
 #define VGABASE		(__ISA_IO_base + 0xb8000)
@@ -111,6 +112,23 @@ ANNOTATE_NOENDBR_SYM(io_serial_out);
 DEFINE_STATIC_CALL(serial_in, io_serial_in);
 DEFINE_STATIC_CALL(serial_out, io_serial_out);
 
+#ifdef CONFIG_INTEL_TDX_GUEST
+/*
+ * A TDX guest cannot execute port I/O instructions, so ask the VMM to do it.
+ */
+static __noendbr unsigned int tdx_serial_in(unsigned long addr, int offset)
+{
+	return tdx_inb(addr + offset);
+}
+ANNOTATE_NOENDBR_SYM(tdx_serial_in);
+
+static __noendbr void tdx_serial_out(unsigned long addr, int offset, int value)
+{
+	tdx_outb(value, addr + offset);
+}
+ANNOTATE_NOENDBR_SYM(tdx_serial_out);
+#endif /* CONFIG_INTEL_TDX_GUEST */
+
 static int early_serial_putc(unsigned char ch)
 {
 	unsigned timeout = 0xffff;
@@ -196,6 +214,22 @@ static __init void early_serial_init(char *s)
 	early_serial_hw_init(divisor);
 }
 
+#ifdef CONFIG_INTEL_TDX_GUEST
+/*
+ * Use early_serial_base (COM1) and same default baud rate as
+ * "earlyprintk=serial"
+ */
+static __init void early_serial_tdx_init(void)
+{
+	if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST)) {
+		static_call_update(serial_in, tdx_serial_in);
+		static_call_update(serial_out, tdx_serial_out);
+	}
+
+	early_serial_hw_init(115200 / DEFAULT_BAUD);
+}
+#endif /* CONFIG_INTEL_TDX_GUEST */
+
 static __noendbr void mem32_serial_out(unsigned long addr, int offset, int value)
 {
 	u32 __iomem *vaddr = (u32 __iomem *)addr;
@@ -414,6 +448,13 @@ static int __init setup_early_printk(char *buf)
 			early_serial_init(buf + 4);
 			early_console_register(&early_serial_console, keep);
 		}
+#ifdef CONFIG_INTEL_TDX_GUEST
+		if (!strncmp(buf, "tdx", 3)) {
+			early_serial_tdx_init();
+			early_console_register(&early_serial_console, keep);
+			break;
+		}
+#endif
 #ifdef CONFIG_PCI
 		if (!strncmp(buf, "pciserial", 9)) {
 			buf += 9; /* Keep from match the above "pciserial" */

-- 
2.55.0

Re: [PATCH v3 2/2] x86/early_printk: Add earlyprintk=tdx to drive the UART with TDVMCALLs

[Kiryl Shutsemau]

On Tue, Sep 22, 2026 at 02:20:07PM -0600, Vishal Verma wrote:
> @@ -111,6 +112,23 @@ ANNOTATE_NOENDBR_SYM(io_serial_out);
>  DEFINE_STATIC_CALL(serial_in, io_serial_in);
>  DEFINE_STATIC_CALL(serial_out, io_serial_out);
>  
> +#ifdef CONFIG_INTEL_TDX_GUEST
> +/*
> + * A TDX guest cannot execute port I/O instructions, so ask the VMM to do it.
> + */
> +static __noendbr unsigned int tdx_serial_in(unsigned long addr, int offset)
> +{
> +	return tdx_inb(addr + offset);
> +}
> +ANNOTATE_NOENDBR_SYM(tdx_serial_in);
> +
> +static __noendbr void tdx_serial_out(unsigned long addr, int offset, int value)
> +{
> +	tdx_outb(value, addr + offset);
> +}
> +ANNOTATE_NOENDBR_SYM(tdx_serial_out);
> +#endif /* CONFIG_INTEL_TDX_GUEST */
> +
>  static int early_serial_putc(unsigned char ch)
>  {
>  	unsigned timeout = 0xffff;
> @@ -196,6 +214,22 @@ static __init void early_serial_init(char *s)
>  	early_serial_hw_init(divisor);
>  }
>  
> +#ifdef CONFIG_INTEL_TDX_GUEST
> +/*
> + * Use early_serial_base (COM1) and same default baud rate as
> + * "earlyprintk=serial"
> + */
> +static __init void early_serial_tdx_init(void)
> +{
> +	if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST)) {
> +		static_call_update(serial_in, tdx_serial_in);
> +		static_call_update(serial_out, tdx_serial_out);
> +	}
> +
> +	early_serial_hw_init(115200 / DEFAULT_BAUD);
> +}
> +#endif /* CONFIG_INTEL_TDX_GUEST */
> +
>  static __noendbr void mem32_serial_out(unsigned long addr, int offset, int value)
>  {
>  	u32 __iomem *vaddr = (u32 __iomem *)addr;
> @@ -414,6 +448,13 @@ static int __init setup_early_printk(char *buf)
>  			early_serial_init(buf + 4);
>  			early_console_register(&early_serial_console, keep);
>  		}
> +#ifdef CONFIG_INTEL_TDX_GUEST
> +		if (!strncmp(buf, "tdx", 3)) {
> +			early_serial_tdx_init();
> +			early_console_register(&early_serial_console, keep);
> +			break;
> +		}
> +#endif

All these #ifdefs in early_printk.c can go. X86_FEATURE_TDX_GUEST is a
disabled feature without CONFIG_INTEL_TDX_GUEST, so
cpu_feature_enabled() folds to zero and the compiler drops the
static_call_update() calls and the wrappers with them.

Add stubs for tdx_inb() and tdx_outb() to the #else branch in
<asm/tdx.h> and make the "tdx" case unconditional.

-- 
  Kiryl Shutsemau / Kirill A. Shutemov