[PATCH v6 0/3] x86/tdx: Fix port I/O handling bugs

[PATCH v6 0/3] x86/tdx: Fix port I/O handling bugs

[Kiryl Shutsemau]

From: "Kiryl Shutsemau (Meta)" <kas@kernel.org>

Three fixes for emulated port I/O in the TDX guest #VE handler.

Patch 1 fixes an off-by-one in the GENMASK() used by handle_in() and
handle_out(): the mask was one bit too wide for every I/O size.

Patch 3 fixes 32-bit port IN to zero-extend into RAX, per x86
semantics, instead of preserving the upper 32 bits. To avoid
open-coding the partial-register-write rules, patch 2 first moves KVM's
assign_register() into <asm/insn-eval.h> as insn_assign_reg() so both
KVM and the #VE handler can share it.

Changes since v5:
  - Patch 2: reword the shortlog and comment; no functional change
    (Sean, David Laight). Collect Acked-by from Sean.
  - Patches 1 and 3 unchanged.

v5: https://lore.kernel.org/all/20260701110547.764083-1-kirill@shutemov.name/
v4: https://lore.kernel.org/all/cover.1780584300.git.kas@kernel.org/

Kiryl Shutsemau (Meta) (3):
  x86/tdx: Fix off-by-one in port I/O handling
  x86/insn-eval: Move assign_register() out of KVM as insn_assign_reg()
  x86/tdx: Fix zero-extension for 32-bit port I/O

 arch/x86/coco/tdx/tdx.c          | 10 ++++-----
 arch/x86/include/asm/insn-eval.h | 36 ++++++++++++++++++++++++++++++++
 arch/x86/kvm/emulate.c           | 26 ++++-------------------
 3 files changed, 44 insertions(+), 28 deletions(-)


base-commit: dc59e4fea9d83f03bad6bddf3fa2e52491777482
-- 
2.54.0

[PATCH v6 1/3] x86/tdx: Fix off-by-one in port I/O handling

[Kiryl Shutsemau]

From: "Kiryl Shutsemau (Meta)" <kas@kernel.org>

handle_in() and handle_out() in arch/x86/coco/tdx/tdx.c use:

    u64 mask = GENMASK(BITS_PER_BYTE * size, 0);

GENMASK(h, l) includes bit h. For size=1 (INB), this produces
GENMASK(8, 0) = 0x1FF (9 bits) instead of GENMASK(7, 0) = 0xFF (8
bits). The mask is one bit too wide for all I/O sizes.

Fix the mask calculation.

Fixes: 03149948832a ("x86/tdx: Port I/O: Add runtime hypercalls")
Reported-by: Borys Tsyrulnikov <tsyrulnikov.borys@gmail.com>
Link: https://lore.kernel.org/all/CAKw_Dz96rfSQc6Rn+9QBcUFHhmkK+9zu+P=bxowfZwxrATCBRg@mail.gmail.com/
Signed-off-by: Kiryl Shutsemau (Meta) <kas@kernel.org>
Reviewed-by: Kai Huang <kai.huang@intel.com>
Reviewed-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>
Reviewed-by: Binbin Wu <binbin.wu@linux.intel.com>
Reviewed-by: Rick Edgecombe <rick.p.edgecombe@intel.com>
Cc: stable@vger.kernel.org
---
 arch/x86/coco/tdx/tdx.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/x86/coco/tdx/tdx.c b/arch/x86/coco/tdx/tdx.c
index 29b6f1ed59ec..b8bbd715fb62 100644
--- a/arch/x86/coco/tdx/tdx.c
+++ b/arch/x86/coco/tdx/tdx.c
@@ -694,7 +694,7 @@ static bool handle_in(struct pt_regs *regs, int size, int port)
 		.r13 = PORT_READ,
 		.r14 = port,
 	};
-	u64 mask = GENMASK(BITS_PER_BYTE * size, 0);
+	u64 mask = GENMASK(BITS_PER_BYTE * size - 1, 0);
 	bool success;
 
 	/*
@@ -714,7 +714,7 @@ static bool handle_in(struct pt_regs *regs, int size, int port)
 
 static bool handle_out(struct pt_regs *regs, int size, int port)
 {
-	u64 mask = GENMASK(BITS_PER_BYTE * size, 0);
+	u64 mask = GENMASK(BITS_PER_BYTE * size - 1, 0);
 
 	/*
 	 * Emulate the I/O write via hypercall. More info about ABI can be found
-- 
2.54.0

[PATCH v6 2/3] x86/insn-eval: Move assign_register() out of KVM as insn_assign_reg()

[Kiryl Shutsemau]

From: "Kiryl Shutsemau (Meta)" <kas@kernel.org>

KVM's instruction emulator has a small helper, assign_register(), that
writes a value into a register following the x86 rules for writes to
general-purpose registers: an 8- or 16-bit write leaves the rest of the
register untouched, a 32-bit write zero-extends the result to 64 bits,
and a 64-bit write replaces the whole register.

The TDX guest #VE handler needs the same logic for port I/O emulation
to get 32-bit zero-extension right.  Rather than add a third copy of
the same switch, move the helper verbatim to <asm/insn-eval.h>, rename
it to insn_assign_reg(), and route KVM's callers through it.

Add <asm/insn.h> to the header's includes so it builds standalone in
callers that have not pulled it in transitively.

No functional change.

Signed-off-by: Kiryl Shutsemau (Meta) <kas@kernel.org>
Acked-by: Sean Christopherson <seanjc@google.com>
Cc: stable@vger.kernel.org # prerequisite for the following 32-bit port I/O zero-extension fix
---
 arch/x86/include/asm/insn-eval.h | 36 ++++++++++++++++++++++++++++++++
 arch/x86/kvm/emulate.c           | 26 ++++-------------------
 2 files changed, 40 insertions(+), 22 deletions(-)

diff --git a/arch/x86/include/asm/insn-eval.h b/arch/x86/include/asm/insn-eval.h
index 4733e9064ee5..ae05647a0afb 100644
--- a/arch/x86/include/asm/insn-eval.h
+++ b/arch/x86/include/asm/insn-eval.h
@@ -9,6 +9,7 @@
 #include <linux/compiler.h>
 #include <linux/bug.h>
 #include <linux/err.h>
+#include <asm/insn.h>
 #include <asm/ptrace.h>
 
 #define INSN_CODE_SEG_ADDR_SZ(params) ((params >> 4) & 0xf)
@@ -46,4 +47,39 @@ enum insn_mmio_type insn_decode_mmio(struct insn *insn, int *bytes);
 
 bool insn_is_nop(struct insn *insn);
 
+/*
+ * Write @val into *@reg following the x86 rules for writes to
+ * general-purpose registers (Intel SDM Vol. 1, "General-Purpose
+ * Registers in 64-Bit Mode"): an 8- or 16-bit write leaves the rest of
+ * the register untouched, a 32-bit write zero-extends the result into
+ * the upper 32 bits, and a 64-bit write replaces the whole register.
+ *
+ * @bytes is the width of the write, not a property of the instruction:
+ * an instruction that, say, sign-extends a 32-bit immediate into a
+ * 64-bit register does a 64-bit write here.
+ *
+ * @reg need not be 8-byte aligned: KVM's instruction emulator offsets
+ * the pointer by one byte to address the high-byte registers (AH, CH,
+ * DH, BH).  Use narrow stores for the sub-word cases so the access
+ * width matches @bytes and the adjacent bytes are left alone.
+ */
+static inline void insn_assign_reg(unsigned long *reg, u64 val, int bytes)
+{
+	switch (bytes) {
+	case 1:
+		*(u8 *)reg = (u8)val;
+		break;
+	case 2:
+		*(u16 *)reg = (u16)val;
+		break;
+	case 4:
+		/* A 32-bit write zero-extends into the upper 32 bits. */
+		*reg = (u32)val;
+		break;
+	case 8:
+		*reg = val;
+		break;
+	}
+}
+
 #endif /* _ASM_X86_INSN_EVAL_H */
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index b566ab5c7515..c6dcb5ac48af 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -24,6 +24,7 @@
 #include "kvm_emulate.h"
 #include <linux/stringify.h>
 #include <asm/debugreg.h>
+#include <asm/insn-eval.h>
 #include <asm/nospec-branch.h>
 #include <asm/ibt.h>
 #include <asm/text-patching.h>
@@ -439,25 +440,6 @@ static void assign_masked(ulong *dest, ulong src, ulong mask)
 	*dest = (*dest & ~mask) | (src & mask);
 }
 
-static void assign_register(unsigned long *reg, u64 val, int bytes)
-{
-	/* The 4-byte case *is* correct: in 64-bit mode we zero-extend. */
-	switch (bytes) {
-	case 1:
-		*(u8 *)reg = (u8)val;
-		break;
-	case 2:
-		*(u16 *)reg = (u16)val;
-		break;
-	case 4:
-		*reg = (u32)val;
-		break;	/* 64b: zero-extend */
-	case 8:
-		*reg = val;
-		break;
-	}
-}
-
 static inline unsigned long ad_mask(struct x86_emulate_ctxt *ctxt)
 {
 	return (1UL << (ctxt->ad_bytes << 3)) - 1;
@@ -505,7 +487,7 @@ register_address_increment(struct x86_emulate_ctxt *ctxt, int reg, int inc)
 {
 	ulong *preg = reg_rmw(ctxt, reg);
 
-	assign_register(preg, *preg + inc, ctxt->ad_bytes);
+	insn_assign_reg(preg, *preg + inc, ctxt->ad_bytes);
 }
 
 static void rsp_increment(struct x86_emulate_ctxt *ctxt, int inc)
@@ -1767,7 +1749,7 @@ static int load_segment_descriptor(struct x86_emulate_ctxt *ctxt,
 
 static void write_register_operand(struct operand *op)
 {
-	return assign_register(op->addr.reg, op->val, op->bytes);
+	return insn_assign_reg(op->addr.reg, op->val, op->bytes);
 }
 
 static int writeback(struct x86_emulate_ctxt *ctxt, struct operand *op)
@@ -2008,7 +1990,7 @@ static int em_popa(struct x86_emulate_ctxt *ctxt)
 		rc = emulate_pop(ctxt, &val, ctxt->op_bytes);
 		if (rc != X86EMUL_CONTINUE)
 			break;
-		assign_register(reg_rmw(ctxt, reg), val, ctxt->op_bytes);
+		insn_assign_reg(reg_rmw(ctxt, reg), val, ctxt->op_bytes);
 		--reg;
 	}
 	return rc;
-- 
2.54.0

[PATCH v6 3/3] x86/tdx: Fix zero-extension for 32-bit port I/O

[Kiryl Shutsemau]

From: "Kiryl Shutsemau (Meta)" <kas@kernel.org>

According to x86 architecture rules, 32-bit operations zero-extend the
result to 64 bits. The current implementation of handle_in() only masks
the lower 32 bits, which preserves the upper 32 bits of RAX when a
32-bit port IN instruction is emulated.

Use insn_assign_reg() to write the result back into RAX with proper
partial-register-write semantics: 1- and 2-byte forms leave the upper
bits untouched, the 4-byte form zero-extends to the full register.

Fixes: 03149948832a ("x86/tdx: Port I/O: Add runtime hypercalls")
Reported-by: Borys Tsyrulnikov <tsyrulnikov.borys@gmail.com>
Link: https://lore.kernel.org/all/CAKw_Dz96rfSQc6Rn+9QBcUFHhmkK+9zu+P=bxowfZwxrATCBRg@mail.gmail.com/
Signed-off-by: Kiryl Shutsemau (Meta) <kas@kernel.org>
Reviewed-by: Binbin Wu <binbin.wu@linux.intel.com>
Cc: stable@vger.kernel.org
---
 arch/x86/coco/tdx/tdx.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/arch/x86/coco/tdx/tdx.c b/arch/x86/coco/tdx/tdx.c
index b8bbd715fb62..f904a636d449 100644
--- a/arch/x86/coco/tdx/tdx.c
+++ b/arch/x86/coco/tdx/tdx.c
@@ -694,8 +694,8 @@ static bool handle_in(struct pt_regs *regs, int size, int port)
 		.r13 = PORT_READ,
 		.r14 = port,
 	};
-	u64 mask = GENMASK(BITS_PER_BYTE * size - 1, 0);
 	bool success;
+	u64 val;
 
 	/*
 	 * Emulate the I/O read via hypercall. More info about ABI can be found
@@ -703,11 +703,9 @@ static bool handle_in(struct pt_regs *regs, int size, int port)
 	 * "TDG.VP.VMCALL<Instruction.IO>".
 	 */
 	success = !__tdx_hypercall(&args);
+	val = success ? args.r11 : 0;
 
-	/* Update part of the register affected by the emulated instruction */
-	regs->ax &= ~mask;
-	if (success)
-		regs->ax |= args.r11 & mask;
+	insn_assign_reg(&regs->ax, val, size);
 
 	return success;
 }
-- 
2.54.0

Re: [PATCH v6 1/3] x86/tdx: Fix off-by-one in port I/O handling

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 2 potential issue(s) to consider:

Pre-existing issues:
- [High] Emulated 32-bit I/O reads (inl) fail to zero-extend the result into the 64-bit RAX register, violating x86-64 semantics.
- [High] Guest register state is corrupted on the error/fault path of an I/O read.
--

--- Patch [1]: [PATCH v6 1/3] x86/tdx: Fix off-by-one in port I/O handling ---
commit 6a0c705281bac273b6793004a9d727acc5a4f92d
Author: Kiryl Shutsemau (Meta) <kas@kernel.org>

x86/tdx: Fix off-by-one in port I/O handling

handle_in() and handle_out() in arch/x86/coco/tdx/tdx.c use a mask that
is one bit too wide for all I/O sizes. For size=1 (INB), this produces
GENMASK(8, 0) = 0x1FF (9 bits) instead of GENMASK(7, 0) = 0xFF (8 bits).
This commit fixes the mask calculation.

Link: https://lore.kernel.org/all/CAKw_Dz96rfSQc6Rn+9QBcUFHhmkK+9zu+P=bxowfZwxrATCBRg@mail.gmail.com/

> diff --git a/arch/x86/coco/tdx/tdx.c b/arch/x86/coco/tdx/tdx.c
> index 29b6f1ed59ec5..b8bbd715fb624 100644
> --- a/arch/x86/coco/tdx/tdx.c
> +++ b/arch/x86/coco/tdx/tdx.c
> @@ -694,7 +694,7 @@ static bool handle_in(struct pt_regs *regs, int size, int port)
>  		.r13 = PORT_READ,
>  		.r14 = port,
>  	};
> -	u64 mask = GENMASK(BITS_PER_BYTE * size, 0);
> +	u64 mask = GENMASK(BITS_PER_BYTE * size - 1, 0);

[Severity: High]
This isn't a bug introduced by this patch, but does the bitwise operation in
arch/x86/coco/tdx/tdx.c:handle_in() properly zero-extend a 32-bit read?

When a guest executes a 32-bit in instruction (inl) triggering handle_in()
with size == 4, mask is evaluated to 32 bits (0xFFFFFFFF).

arch/x86/coco/tdx/tdx.c:handle_in() {
    ...
	success = !__tdx_hypercall(&args);

	/* Update part of the register affected by the emulated instruction */
	regs->ax &= ~mask;
	if (success)
		regs->ax |= args.r11 & mask;
    ...
}

The bitwise operation regs->ax &= ~mask will clear the lower 32 bits, but it
incorrectly preserves the upper 32 bits of the 64-bit register. x86-64
architectural semantics require any 32-bit write to a general-purpose
register to zero-extend to 64 bits.

Could this cause data corruption for guest software expecting RAX to be
zero-extended?

[Severity: High]
This is another pre-existing issue, but is it safe to unconditionally clear
the target bits in regs->ax on the error path?

If the VMM rejects the hypercall (__tdx_hypercall() returns a non-zero
error), handle_in() still performs regs->ax &= ~mask; and returns false.
The kernel then injects a #GP fault into the guest.

The guest exception handler will observe a partially modified RAX register
instead of the unmodified state from before the faulting instruction. 

Can this violate architectural guarantees for faults by exposing corrupted
register state?

>  	bool success;
>  
>  	/*
[ ... ]

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260713133753.223947-1-kirill@shutemov.name?part=1

Re: [PATCH v6 3/3] x86/tdx: Fix zero-extension for 32-bit port I/O

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 3 potential issue(s) to consider:

Pre-existing issues:
- [High] The TDX #VE handler for the CPUID instruction fails to zero the upper 32 bits of the destination registers, exposing the guest to potentially malicious or garbage data from the VMM.
- [High] The TDX #VE handler for MMIO reads fails to zero the upper 32 bits of the destination register for 32-bit MOVZX and MOVSX instructions.
- [High] The TDX #VE handler for MSR writes corrupts the MSR data sent to the VMM if the guest's RAX register contains non-zero upper 32 bits.
--

--- Patch [3]: [PATCH v6 3/3] x86/tdx: Fix zero-extension for 32-bit port I/O ---
commit 54fa9007fcfc0403e17720722b833050a2d55438
Author: Kiryl Shutsemau (Meta) <kas@kernel.org>

x86/tdx: Fix zero-extension for 32-bit port I/O

This commit updates handle_in() to use insn_assign_reg() for 32-bit port IN
instructions. This ensures proper partial-register-write semantics where
4-byte forms correctly zero-extend to the full 64-bit register.

Link: https://lore.kernel.org/all/CAKw_Dz96rfSQc6Rn+9QBcUFHhmkK+9zu+P=bxowfZwxrATCBRg@mail.gmail.com/

> diff --git a/arch/x86/coco/tdx/tdx.c b/arch/x86/coco/tdx/tdx.c
> index b8bbd715fb624..f904a636d449b 100644
> --- a/arch/x86/coco/tdx/tdx.c
> +++ b/arch/x86/coco/tdx/tdx.c
> @@ -703,11 +703,9 @@ static bool handle_in(struct pt_regs *regs, int size, int port)
>  	 * "TDG.VP.VMCALL<Instruction.IO>".
>  	 */
>  	success = !__tdx_hypercall(&args);
> +	val = success ? args.r11 : 0;
>  
> -	/* Update part of the register affected by the emulated instruction */
> -	regs->ax &= ~mask;
> -	if (success)
> -		regs->ax |= args.r11 & mask;
> +	insn_assign_reg(&regs->ax, val, size);
>  
>  	return success;
>  }

[Severity: High]
This is a pre-existing issue, but since you are fixing zero-extension issues
in this file, I noticed another zero-extension problem in handle_mmio() for
32-bit destination registers.

If a guest executes an instruction like MOVZX EAX, BYTE PTR [mem], the #VE
handler calculates extend_size:

arch/x86/coco/tdx/tdx.c:handle_mmio() {
	...
	case INSN_MMIO_READ_ZERO_EXTEND:
		/* Zero extend based on operand size */
		extend_size = insn.opnd_bytes;
		break;
	...
}

If insn.opnd_bytes is 4, doesn't this cause the subsequent memset to only
clear the lower 4 bytes of regs->ax, leaving the upper 32 bits containing
stale data and violating x86-64 architecture rules?


[Severity: High]
This isn't a bug introduced by this patch, but does handle_cpuid() have a
similar problem with zero-extending registers?

When a guest executes CPUID, it traps to the #VE handler. handle_cpuid()
copies the VMM hypercall results directly into the registers:

arch/x86/coco/tdx/tdx.c:handle_cpuid() {
	...
	regs->ax = args.r12;
	regs->bx = args.r13;
	regs->cx = args.r14;
	regs->dx = args.r15;
	...
}

Could an untrusted VMM inject non-zero data into the upper 32 bits of these
registers and violate x86-64 CPUID semantics since they are not being
zero-extended?


[Severity: High]
This is also a pre-existing issue, but could write_msr() corrupt the MSR
data sent to the VMM if the guest's RAX register contains non-zero upper
32 bits?

The payload for WRMSR is constructed like this:

arch/x86/coco/tdx/tdx.c:write_msr() {
	...
	struct tdx_module_args args = {
		...
		.r13 = (u64)regs->dx << 32 | regs->ax,
	};
	...
}

Since WRMSR ignores the upper 32 bits of RAX, the architecture permits
garbage in them. Because regs->ax is not cast to a 32-bit integer before
the bitwise-OR, won't any set bits in its upper 32 bits bleed into the
EDX portion of the payload?

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260713133753.223947-1-kirill@shutemov.name?part=3

[tip: x86/tdx] x86/tdx: Fix zero-extension for 32-bit port I/O

[tip-bot2 for Kiryl Shutsemau (Meta)]

The following commit has been merged into the x86/tdx branch of tip:

Commit-ID:     941370fc93cc3474e26811f4d3b062903eefe2cf
Gitweb:        https://git.kernel.org/tip/941370fc93cc3474e26811f4d3b062903eefe2cf
Author:        Kiryl Shutsemau (Meta) <kas@kernel.org>
AuthorDate:    Mon, 13 Jul 2026 14:37:53 +01:00
Committer:     Dave Hansen <dave.hansen@linux.intel.com>
CommitterDate: Mon, 13 Jul 2026 14:45:07 -07:00

x86/tdx: Fix zero-extension for 32-bit port I/O

According to x86 architecture rules, 32-bit operations zero-extend the
result to 64 bits. The current implementation of handle_in() only masks
the lower 32 bits, which preserves the upper 32 bits of RAX when a
32-bit port IN instruction is emulated.

Use insn_assign_reg() to write the result back into RAX with proper
partial-register-write semantics: 1- and 2-byte forms leave the upper
bits untouched, the 4-byte form zero-extends to the full register.

Fixes: 03149948832a ("x86/tdx: Port I/O: Add runtime hypercalls")
Reported-by: Borys Tsyrulnikov <tsyrulnikov.borys@gmail.com>
Signed-off-by: Kiryl Shutsemau (Meta) <kas@kernel.org>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Binbin Wu <binbin.wu@linux.intel.com>
Link: https://lore.kernel.org/all/CAKw_Dz96rfSQc6Rn+9QBcUFHhmkK+9zu+P=bxowfZwxrATCBRg@mail.gmail.com/
Cc:stable@vger.kernel.org
Link: https://patch.msgid.link/20260713133753.223947-4-kirill@shutemov.name
---
 arch/x86/coco/tdx/tdx.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/arch/x86/coco/tdx/tdx.c b/arch/x86/coco/tdx/tdx.c
index b8bbd71..f904a63 100644
--- a/arch/x86/coco/tdx/tdx.c
+++ b/arch/x86/coco/tdx/tdx.c
@@ -694,8 +694,8 @@ static bool handle_in(struct pt_regs *regs, int size, int port)
 		.r13 = PORT_READ,
 		.r14 = port,
 	};
-	u64 mask = GENMASK(BITS_PER_BYTE * size - 1, 0);
 	bool success;
+	u64 val;
 
 	/*
 	 * Emulate the I/O read via hypercall. More info about ABI can be found
@@ -703,11 +703,9 @@ static bool handle_in(struct pt_regs *regs, int size, int port)
 	 * "TDG.VP.VMCALL<Instruction.IO>".
 	 */
 	success = !__tdx_hypercall(&args);
+	val = success ? args.r11 : 0;
 
-	/* Update part of the register affected by the emulated instruction */
-	regs->ax &= ~mask;
-	if (success)
-		regs->ax |= args.r11 & mask;
+	insn_assign_reg(&regs->ax, val, size);
 
 	return success;
 }

[tip: x86/tdx] x86/insn-eval: Move assign_register() out of KVM as insn_assign_reg()

[tip-bot2 for Kiryl Shutsemau (Meta)]

The following commit has been merged into the x86/tdx branch of tip:

Commit-ID:     1fe104b048d77d6cb25bd938e6a67450fb50e61d
Gitweb:        https://git.kernel.org/tip/1fe104b048d77d6cb25bd938e6a67450fb50e61d
Author:        Kiryl Shutsemau (Meta) <kas@kernel.org>
AuthorDate:    Mon, 13 Jul 2026 14:37:52 +01:00
Committer:     Dave Hansen <dave.hansen@linux.intel.com>
CommitterDate: Mon, 13 Jul 2026 14:45:07 -07:00

x86/insn-eval: Move assign_register() out of KVM as insn_assign_reg()

KVM's instruction emulator has a small helper, assign_register(), that
writes a value into a register following the x86 rules for writes to
general-purpose registers: an 8- or 16-bit write leaves the rest of the
register untouched, a 32-bit write zero-extends the result to 64 bits,
and a 64-bit write replaces the whole register.

The TDX guest #VE handler needs the same logic for port I/O emulation
to get 32-bit zero-extension right.  Rather than add a third copy of
the same switch, move the helper verbatim to <asm/insn-eval.h>, rename
it to insn_assign_reg(), and route KVM's callers through it.

Add <asm/insn.h> to the header's includes so it builds standalone in
callers that have not pulled it in transitively.

No functional change.

Signed-off-by: Kiryl Shutsemau (Meta) <kas@kernel.org>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Acked-by: Sean Christopherson <seanjc@google.com>
Cc:stable@vger.kernel.org
Link: https://patch.msgid.link/20260713133753.223947-3-kirill@shutemov.name
---
 arch/x86/include/asm/insn-eval.h | 36 +++++++++++++++++++++++++++++++-
 arch/x86/kvm/emulate.c           | 26 +++-------------------
 2 files changed, 40 insertions(+), 22 deletions(-)

diff --git a/arch/x86/include/asm/insn-eval.h b/arch/x86/include/asm/insn-eval.h
index 4733e90..ae05647 100644
--- a/arch/x86/include/asm/insn-eval.h
+++ b/arch/x86/include/asm/insn-eval.h
@@ -9,6 +9,7 @@
 #include <linux/compiler.h>
 #include <linux/bug.h>
 #include <linux/err.h>
+#include <asm/insn.h>
 #include <asm/ptrace.h>
 
 #define INSN_CODE_SEG_ADDR_SZ(params) ((params >> 4) & 0xf)
@@ -46,4 +47,39 @@ enum insn_mmio_type insn_decode_mmio(struct insn *insn, int *bytes);
 
 bool insn_is_nop(struct insn *insn);
 
+/*
+ * Write @val into *@reg following the x86 rules for writes to
+ * general-purpose registers (Intel SDM Vol. 1, "General-Purpose
+ * Registers in 64-Bit Mode"): an 8- or 16-bit write leaves the rest of
+ * the register untouched, a 32-bit write zero-extends the result into
+ * the upper 32 bits, and a 64-bit write replaces the whole register.
+ *
+ * @bytes is the width of the write, not a property of the instruction:
+ * an instruction that, say, sign-extends a 32-bit immediate into a
+ * 64-bit register does a 64-bit write here.
+ *
+ * @reg need not be 8-byte aligned: KVM's instruction emulator offsets
+ * the pointer by one byte to address the high-byte registers (AH, CH,
+ * DH, BH).  Use narrow stores for the sub-word cases so the access
+ * width matches @bytes and the adjacent bytes are left alone.
+ */
+static inline void insn_assign_reg(unsigned long *reg, u64 val, int bytes)
+{
+	switch (bytes) {
+	case 1:
+		*(u8 *)reg = (u8)val;
+		break;
+	case 2:
+		*(u16 *)reg = (u16)val;
+		break;
+	case 4:
+		/* A 32-bit write zero-extends into the upper 32 bits. */
+		*reg = (u32)val;
+		break;
+	case 8:
+		*reg = val;
+		break;
+	}
+}
+
 #endif /* _ASM_X86_INSN_EVAL_H */
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index b566ab5..c6dcb5a 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -24,6 +24,7 @@
 #include "kvm_emulate.h"
 #include <linux/stringify.h>
 #include <asm/debugreg.h>
+#include <asm/insn-eval.h>
 #include <asm/nospec-branch.h>
 #include <asm/ibt.h>
 #include <asm/text-patching.h>
@@ -439,25 +440,6 @@ static void assign_masked(ulong *dest, ulong src, ulong mask)
 	*dest = (*dest & ~mask) | (src & mask);
 }
 
-static void assign_register(unsigned long *reg, u64 val, int bytes)
-{
-	/* The 4-byte case *is* correct: in 64-bit mode we zero-extend. */
-	switch (bytes) {
-	case 1:
-		*(u8 *)reg = (u8)val;
-		break;
-	case 2:
-		*(u16 *)reg = (u16)val;
-		break;
-	case 4:
-		*reg = (u32)val;
-		break;	/* 64b: zero-extend */
-	case 8:
-		*reg = val;
-		break;
-	}
-}
-
 static inline unsigned long ad_mask(struct x86_emulate_ctxt *ctxt)
 {
 	return (1UL << (ctxt->ad_bytes << 3)) - 1;
@@ -505,7 +487,7 @@ register_address_increment(struct x86_emulate_ctxt *ctxt, int reg, int inc)
 {
 	ulong *preg = reg_rmw(ctxt, reg);
 
-	assign_register(preg, *preg + inc, ctxt->ad_bytes);
+	insn_assign_reg(preg, *preg + inc, ctxt->ad_bytes);
 }
 
 static void rsp_increment(struct x86_emulate_ctxt *ctxt, int inc)
@@ -1767,7 +1749,7 @@ static int load_segment_descriptor(struct x86_emulate_ctxt *ctxt,
 
 static void write_register_operand(struct operand *op)
 {
-	return assign_register(op->addr.reg, op->val, op->bytes);
+	return insn_assign_reg(op->addr.reg, op->val, op->bytes);
 }
 
 static int writeback(struct x86_emulate_ctxt *ctxt, struct operand *op)
@@ -2008,7 +1990,7 @@ static int em_popa(struct x86_emulate_ctxt *ctxt)
 		rc = emulate_pop(ctxt, &val, ctxt->op_bytes);
 		if (rc != X86EMUL_CONTINUE)
 			break;
-		assign_register(reg_rmw(ctxt, reg), val, ctxt->op_bytes);
+		insn_assign_reg(reg_rmw(ctxt, reg), val, ctxt->op_bytes);
 		--reg;
 	}
 	return rc;

[tip: x86/tdx] x86/tdx: Fix off-by-one in port I/O handling

[tip-bot2 for Kiryl Shutsemau (Meta)]

The following commit has been merged into the x86/tdx branch of tip:

Commit-ID:     0f63e656b1c679d32ac595de29d10c03efca6a25
Gitweb:        https://git.kernel.org/tip/0f63e656b1c679d32ac595de29d10c03efca6a25
Author:        Kiryl Shutsemau (Meta) <kas@kernel.org>
AuthorDate:    Mon, 13 Jul 2026 14:37:51 +01:00
Committer:     Dave Hansen <dave.hansen@linux.intel.com>
CommitterDate: Mon, 13 Jul 2026 14:45:07 -07:00

x86/tdx: Fix off-by-one in port I/O handling

handle_in() and handle_out() in arch/x86/coco/tdx/tdx.c use:

    u64 mask = GENMASK(BITS_PER_BYTE * size, 0);

GENMASK(h, l) includes bit h. For size=1 (INB), this produces
GENMASK(8, 0) = 0x1FF (9 bits) instead of GENMASK(7, 0) = 0xFF (8
bits). The mask is one bit too wide for all I/O sizes.

Fix the mask calculation.

Fixes: 03149948832a ("x86/tdx: Port I/O: Add runtime hypercalls")
Reported-by: Borys Tsyrulnikov <tsyrulnikov.borys@gmail.com>
Signed-off-by: Kiryl Shutsemau (Meta) <kas@kernel.org>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Kai Huang <kai.huang@intel.com>
Reviewed-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>
Reviewed-by: Binbin Wu <binbin.wu@linux.intel.com>
Reviewed-by: Rick Edgecombe <rick.p.edgecombe@intel.com>
Link: https://lore.kernel.org/all/CAKw_Dz96rfSQc6Rn+9QBcUFHhmkK+9zu+P=bxowfZwxrATCBRg@mail.gmail.com/
Cc:stable@vger.kernel.org
Link: https://patch.msgid.link/20260713133753.223947-2-kirill@shutemov.name
---
 arch/x86/coco/tdx/tdx.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/x86/coco/tdx/tdx.c b/arch/x86/coco/tdx/tdx.c
index 29b6f1e..b8bbd71 100644
--- a/arch/x86/coco/tdx/tdx.c
+++ b/arch/x86/coco/tdx/tdx.c
@@ -694,7 +694,7 @@ static bool handle_in(struct pt_regs *regs, int size, int port)
 		.r13 = PORT_READ,
 		.r14 = port,
 	};
-	u64 mask = GENMASK(BITS_PER_BYTE * size, 0);
+	u64 mask = GENMASK(BITS_PER_BYTE * size - 1, 0);
 	bool success;
 
 	/*
@@ -714,7 +714,7 @@ static bool handle_in(struct pt_regs *regs, int size, int port)
 
 static bool handle_out(struct pt_regs *regs, int size, int port)
 {
-	u64 mask = GENMASK(BITS_PER_BYTE * size, 0);
+	u64 mask = GENMASK(BITS_PER_BYTE * size - 1, 0);
 
 	/*
 	 * Emulate the I/O write via hypercall. More info about ABI can be found