[PATCH v7 10/12] x86/tdx: Add MSR support for TDX guest

[Kuppuswamy Sathyanarayanan]

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

Operations on context-switched MSRs can be run natively. The rest of
MSRs should be handled through TDVMCALLs.

TDVMCALL[Instruction.RDMSR] and TDVMCALL[Instruction.WRMSR] provide
MSR oprations.

RDMSR and WRMSR specification details can be found in
Guest-Host-Communication Interface (GHCI) for Intel Trust Domain
Extensions (Intel TDX) specification, sec 3.10, 3.11.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx>
Reviewed-by: Andi Kleen <ak@xxxxxxxxxxxxxxx>
Reviewed-by: Tony Luck <tony.luck@xxxxxxxxx>
Signed-off-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@xxxxxxxxxxxxxxx>
---

Changes since v6:
 * None

Changes since v5:
 * Renamed "tdg" prefix with "tdx".
 * Added comments for _tdx_hypercall() usage in MSR read/write functions.

Change since v4:
 * Removed You usage from commit log.

Changes since v3:
 * None

 arch/x86/kernel/tdx.c | 77 +++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 75 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kernel/tdx.c b/arch/x86/kernel/tdx.c
index ec1008cc42d9..5c52dde4a5fd 100644
--- a/arch/x86/kernel/tdx.c
+++ b/arch/x86/kernel/tdx.c
@@ -91,6 +91,65 @@ static __cpuidle void tdx_safe_halt(void)
 	_tdx_halt(irq_disabled, do_sti);
 }
 
+static bool tdx_is_context_switched_msr(unsigned int msr)
+{
+	switch (msr) {
+	case MSR_EFER:
+	case MSR_IA32_CR_PAT:
+	case MSR_FS_BASE:
+	case MSR_GS_BASE:
+	case MSR_KERNEL_GS_BASE:
+	case MSR_IA32_SYSENTER_CS:
+	case MSR_IA32_SYSENTER_EIP:
+	case MSR_IA32_SYSENTER_ESP:
+	case MSR_STAR:
+	case MSR_LSTAR:
+	case MSR_SYSCALL_MASK:
+	case MSR_IA32_XSS:
+	case MSR_TSC_AUX:
+	case MSR_IA32_BNDCFGS:
+		return true;
+	}
+	return false;
+}
+
+static u64 tdx_read_msr_safe(unsigned int msr, int *err)
+{
+	struct tdx_hypercall_output out = {0};
+	u64 ret;
+
+	WARN_ON_ONCE(tdx_is_context_switched_msr(msr));
+
+	/*
+	 * Emulate the MSR read via hypercall. More info about ABI
+	 * can be found in TDX Guest-Host-Communication Interface
+	 * (GHCI), sec 3.10.
+	 */
+	ret = _tdx_hypercall(EXIT_REASON_MSR_READ, msr, 0, 0, 0, &out);
+
+	*err = ret ? -EIO : 0;
+
+	return out.r11;
+}
+
+static int tdx_write_msr_safe(unsigned int msr, unsigned int low,
+			      unsigned int high)
+{
+	u64 ret;
+
+	WARN_ON_ONCE(tdx_is_context_switched_msr(msr));
+
+	/*
+	 * Emulate the MSR write via hypercall. More info about ABI
+	 * can be found in TDX Guest-Host-Communication Interface
+	 * (GHCI) sec 3.11.
+	 */
+	ret = _tdx_hypercall(EXIT_REASON_MSR_WRITE, msr, (u64)high << 32 | low,
+			     0, 0, NULL);
+
+	return ret ? -EIO : 0;
+}
+
 unsigned long tdx_get_ve_info(struct ve_info *ve)
 {
 	struct tdx_module_output out = {0};
@@ -117,19 +176,33 @@ unsigned long tdx_get_ve_info(struct ve_info *ve)
 int tdx_handle_virtualization_exception(struct pt_regs *regs,
 					struct ve_info *ve)
 {
+	unsigned long val;
+	int ret = 0;
+
 	switch (ve->exit_reason) {
 	case EXIT_REASON_HLT:
 		tdx_halt();
 		break;
+	case EXIT_REASON_MSR_READ:
+		val = tdx_read_msr_safe(regs->cx, (unsigned int *)&ret);
+		if (!ret) {
+			regs->ax = (u32)val;
+			regs->dx = val >> 32;
+		}
+		break;
+	case EXIT_REASON_MSR_WRITE:
+		ret = tdx_write_msr_safe(regs->cx, regs->ax, regs->dx);
+		break;
 	default:
 		pr_warn("Unexpected #VE: %lld\n", ve->exit_reason);
 		return -EFAULT;
 	}
 
 	/* After successful #VE handling, move the IP */
-	regs->ip += ve->instr_len;
+	if (!ret)
+		regs->ip += ve->instr_len;
 
-	return 0;
+	return ret;
 }
 
 void __init tdx_early_init(void)
-- 
2.25.1