[RFC v2-fix-v2 3/3] x86/tdx: Handle port I/O

[Kuppuswamy Sathyanarayanan]

From: "Kirill A. Shutemov" <kirill.shutemov@xxxxxxxxxxxxxxx>

TDX hypervisors cannot emulate instructions directly. This
includes port IO which is normally emulated in the hypervisor.
All port IO instructions inside TDX trigger the #VE exception
in the guest and would be normally emulated there.

Also string I/O is not supported in TDX guest. So, unroll the
string I/O operation into a loop operating on one element at
a time. This method is similar to AMD SEV, so just extend the
support for TDX guest platform.

Co-developed-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@xxxxxxxxxxxxxxx>
Signed-off-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@xxxxxxxxxxxxxxx>
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx>
Reviewed-by: Andi Kleen <ak@xxxxxxxxxxxxxxx>
---
Changes since RFC v2-fix-v1:
 * Fixed commit log to adapt to decompression support code split.

 arch/x86/include/asm/io.h |  6 ++++--
 arch/x86/kernel/tdx.c     | 28 ++++++++++++++++++++++++++++
 2 files changed, 32 insertions(+), 2 deletions(-)

diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h
index 391205dace98..e01d8bf2b37a 100644
--- a/arch/x86/include/asm/io.h
+++ b/arch/x86/include/asm/io.h
@@ -310,7 +310,8 @@ static inline unsigned type in##bwl##_p(int port)			\
 									\
 static inline void outs##bwl(int port, const void *addr, unsigned long count) \
 {									\
-	if (sev_key_active()) {						\
+	if (sev_key_active() ||						\
+	    protected_guest_has(VM_UNROLL_STRING_IO)) {			\
 		unsigned type *value = (unsigned type *)addr;		\
 		while (count) {						\
 			out##bwl(*value, port);				\
@@ -326,7 +327,8 @@ static inline void outs##bwl(int port, const void *addr, unsigned long count) \
 									\
 static inline void ins##bwl(int port, void *addr, unsigned long count)	\
 {									\
-	if (sev_key_active()) {						\
+	if (sev_key_active() ||						\
+	    protected_guest_has(VM_UNROLL_STRING_IO)) {			\
 		unsigned type *value = (unsigned type *)addr;		\
 		while (count) {						\
 			*value = in##bwl(port);				\
diff --git a/arch/x86/kernel/tdx.c b/arch/x86/kernel/tdx.c
index 3410cfc8a988..48a0cc2663ea 100644
--- a/arch/x86/kernel/tdx.c
+++ b/arch/x86/kernel/tdx.c
@@ -201,6 +201,31 @@ static void tdg_handle_cpuid(struct pt_regs *regs)
 	regs->dx = out.r15;
 }
 
+/*
+ * Since the way we fail for string case is different we cannot
+ * reuse tdx_handle_early_io().
+ */
+static void tdg_handle_io(struct pt_regs *regs, u32 exit_qual)
+{
+	struct tdx_hypercall_output outh;
+	int out = VE_IS_IO_OUT(exit_qual);
+	int size = VE_GET_IO_SIZE(exit_qual);
+	int port = VE_GET_PORT_NUM(exit_qual);
+	u64 mask = GENMASK(8 * size, 0);
+	bool string = VE_IS_IO_STRING(exit_qual);
+	int ret;
+
+	/* I/O strings ops are unrolled at build time. */
+	BUG_ON(string);
+
+	ret = __tdx_hypercall(EXIT_REASON_IO_INSTRUCTION, size, out, port,
+			      regs->ax, &outh);
+	if (!out) {
+		regs->ax &= ~mask;
+		regs->ax |= (ret ? UINT_MAX : outh.r11) & mask;
+	}
+}
+
 unsigned long tdg_get_ve_info(struct ve_info *ve)
 {
 	u64 ret;
@@ -247,6 +272,9 @@ int tdg_handle_virtualization_exception(struct pt_regs *regs,
 	case EXIT_REASON_CPUID:
 		tdg_handle_cpuid(regs);
 		break;
+	case EXIT_REASON_IO_INSTRUCTION:
+		tdg_handle_io(regs, ve->exit_qual);
+		break;
 	default:
 		pr_warn("Unexpected #VE: %lld\n", ve->exit_reason);
 		return -EFAULT;
-- 
2.25.1