Adding upstream version 6.1.76.upstream/6.1.76

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

5 files changed, 1190 insertions, 0 deletions

diff --git a/arch/x86/coco/Makefile b/arch/x86/coco/Makefile
new file mode 100644
index 000000000..c816acf78
--- /dev/null
+++ b/arch/x86/coco/Makefile
@@ -0,0 +1,8 @@
+# SPDX-License-Identifier: GPL-2.0
+CFLAGS_REMOVE_core.o	= -pg
+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
new file mode 100644
index 000000000..49b44f881
--- /dev/null
+++ b/arch/x86/coco/core.c
@@ -0,0 +1,140 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Confidential Computing Platform Capability checks
+ *
+ * Copyright (C) 2021 Advanced Micro Devices, Inc.
+ *
+ * Author: Tom Lendacky <thomas.lendacky@amd.com>
+ */
+
+#include <linux/export.h>
+#include <linux/cc_platform.h>
+
+#include <asm/coco.h>
+#include <asm/processor.h>
+
+static enum cc_vendor vendor __ro_after_init;
+static u64 cc_mask __ro_after_init;
+
+static bool intel_cc_platform_has(enum cc_attr attr)
+{
+	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;
+	}
+}
+
+/*
+ * SME and SEV are very similar but they are not the same, so there are
+ * times that the kernel will need to distinguish between SME and SEV. The
+ * cc_platform_has() function is used for this.  When a distinction isn't
+ * needed, the CC_ATTR_MEM_ENCRYPT attribute can be used.
+ *
+ * The trampoline code is a good example for this requirement.  Before
+ * paging is activated, SME will access all memory as decrypted, but SEV
+ * will access all memory as encrypted.  So, when APs are being brought
+ * up under SME the trampoline area cannot be encrypted, whereas under SEV
+ * the trampoline area must be encrypted.
+ */
+static bool amd_cc_platform_has(enum cc_attr attr)
+{
+#ifdef CONFIG_AMD_MEM_ENCRYPT
+	switch (attr) {
+	case CC_ATTR_MEM_ENCRYPT:
+		return sme_me_mask;
+
+	case CC_ATTR_HOST_MEM_ENCRYPT:
+		return sme_me_mask && !(sev_status & MSR_AMD64_SEV_ENABLED);
+
+	case CC_ATTR_GUEST_MEM_ENCRYPT:
+		return sev_status & MSR_AMD64_SEV_ENABLED;
+
+	case CC_ATTR_GUEST_STATE_ENCRYPT:
+		return sev_status & MSR_AMD64_SEV_ES_ENABLED;
+
+	/*
+	 * With SEV, the rep string I/O instructions need to be unrolled
+	 * but SEV-ES supports them through the #VC handler.
+	 */
+	case CC_ATTR_GUEST_UNROLL_STRING_IO:
+		return (sev_status & MSR_AMD64_SEV_ENABLED) &&
+			!(sev_status & MSR_AMD64_SEV_ES_ENABLED);
+
+	case CC_ATTR_GUEST_SEV_SNP:
+		return sev_status & MSR_AMD64_SEV_SNP_ENABLED;
+
+	default:
+		return false;
+	}
+#else
+	return false;
+#endif
+}
+
+static bool hyperv_cc_platform_has(enum cc_attr attr)
+{
+	return attr == CC_ATTR_GUEST_MEM_ENCRYPT;
+}
+
+bool cc_platform_has(enum cc_attr attr)
+{
+	switch (vendor) {
+	case CC_VENDOR_AMD:
+		return amd_cc_platform_has(attr);
+	case CC_VENDOR_INTEL:
+		return intel_cc_platform_has(attr);
+	case CC_VENDOR_HYPERV:
+		return hyperv_cc_platform_has(attr);
+	default:
+		return false;
+	}
+}
+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;
+	}
+}
+
+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;
+	}
+}
+EXPORT_SYMBOL_GPL(cc_mkdec);
+
+__init void cc_set_vendor(enum cc_vendor v)
+{
+	vendor = v;
+}
+
+__init void cc_set_mask(u64 mask)
+{
+	cc_mask = mask;
+}
diff --git a/arch/x86/coco/tdx/Makefile b/arch/x86/coco/tdx/Makefile
new file mode 100644
index 000000000..46c559985
--- /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 000000000..f9eb1134f
--- /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
+	jne .Lpanic
+
+	/* TDVMCALL leaf return code is in R10 */
+	movq %r10, %rax
+
+	/* Copy hypercall result registers to arg struct if needed */
+	testq $TDX_HCALL_HAS_OUTPUT, %rsi
+	jz .Lout
+
+	movq %r10, TDX_HYPERCALL_r10(%rdi)
+	movq %r11, TDX_HYPERCALL_r11(%rdi)
+	movq %r12, TDX_HYPERCALL_r12(%rdi)
+	movq %r13, TDX_HYPERCALL_r13(%rdi)
+	movq %r14, TDX_HYPERCALL_r14(%rdi)
+	movq %r15, TDX_HYPERCALL_r15(%rdi)
+.Lout:
+	/*
+	 * Zero out registers exposed to the VMM to avoid speculative execution
+	 * with VMM-controlled values. This needs to include all registers
+	 * present in TDVMCALL_EXPOSE_REGS_MASK (except R12-R15). R12-R15
+	 * context will be restored.
+	 */
+	xor %r10d, %r10d
+	xor %r11d, %r11d
+
+	/* Restore callee-saved GPRs as mandated by the x86_64 ABI */
+	pop %r12
+	pop %r13
+	pop %r14
+	pop %r15
+
+	FRAME_END
+
+	RET
+.Lpanic:
+	call __tdx_hypercall_failed
+	/* __tdx_hypercall_failed never returns */
+	REACHABLE
+	jmp .Lpanic
+SYM_FUNC_END(__tdx_hypercall)
diff --git a/arch/x86/coco/tdx/tdx.c b/arch/x86/coco/tdx/tdx.c
new file mode 100644
index 000000000..d0565a9e7
--- /dev/null
+++ b/arch/x86/coco/tdx/tdx.c
@@ -0,0 +1,834 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2021-2022 Intel Corporation */
+
+#undef pr_fmt
+#define pr_fmt(fmt)     "tdx: " fmt
+
+#include <linux/cpufeature.h>
+#include <asm/coco.h>
+#include <asm/tdx.h>
+#include <asm/vmx.h>
+#include <asm/ia32.h>
+#include <asm/insn.h>
+#include <asm/insn-eval.h>
+#include <asm/pgtable.h>
+
+/* TDX module Call Leaf IDs */
+#define TDX_GET_INFO			1
+#define TDX_GET_VEINFO			3
+#define TDX_ACCEPT_PAGE			6
+
+/* TDX hypercall Leaf IDs */
+#define TDVMCALL_MAP_GPA		0x10001
+
+/* MMIO direction */
+#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)
+#define VE_GET_PORT_NUM(e)	((e) >> 16)
+#define VE_IS_IO_STRING(e)	((e) & BIT(4))
+
+#define ATTR_SEPT_VE_DISABLE	BIT(28)
+
+/*
+ * Wrapper for standard use of __tdx_hypercall with no output aside from
+ * return code.
+ */
+static inline u64 _tdx_hypercall(u64 fn, u64 r12, u64 r13, u64 r14, u64 r15)
+{
+	struct tdx_hypercall_args args = {
+		.r10 = TDX_HYPERCALL_STANDARD,
+		.r11 = fn,
+		.r12 = r12,
+		.r13 = r13,
+		.r14 = r14,
+		.r15 = r15,
+	};
+
+	return __tdx_hypercall(&args, 0);
+}
+
+/* Called from __tdx_hypercall() for unrecoverable failure */
+void __tdx_hypercall_failed(void)
+{
+	panic("TDVMCALL failed. TDX module bug?");
+}
+
+/*
+ * The TDG.VP.VMCALL-Instruction-execution sub-functions are defined
+ * independently from but are currently matched 1:1 with VMX EXIT_REASONs.
+ * Reusing the KVM EXIT_REASON macros makes it easier to connect the host and
+ * guest sides of these calls.
+ */
+static u64 hcall_func(u64 exit_reason)
+{
+	return exit_reason;
+}
+
+#ifdef CONFIG_KVM_GUEST
+long tdx_kvm_hypercall(unsigned int nr, unsigned long p1, unsigned long p2,
+		       unsigned long p3, unsigned long p4)
+{
+	struct tdx_hypercall_args args = {
+		.r10 = nr,
+		.r11 = p1,
+		.r12 = p2,
+		.r13 = p3,
+		.r14 = p4,
+	};
+
+	return __tdx_hypercall(&args, 0);
+}
+EXPORT_SYMBOL_GPL(tdx_kvm_hypercall);
+#endif
+
+/*
+ * Used for TDX guests to make calls directly to the TD module.  This
+ * should only be used for calls that have no legitimate reason to fail
+ * or where the kernel can not survive the call failing.
+ */
+static inline void tdx_module_call(u64 fn, u64 rcx, u64 rdx, u64 r8, u64 r9,
+				   struct tdx_module_output *out)
+{
+	if (__tdx_module_call(fn, rcx, rdx, r8, r9, out))
+		panic("TDCALL %lld failed (Buggy TDX module!)\n", fn);
+}
+
+static void tdx_parse_tdinfo(u64 *cc_mask)
+{
+	struct tdx_module_output out;
+	unsigned int gpa_width;
+	u64 td_attr;
+
+	/*
+	 * TDINFO TDX module call is used to get the TD execution environment
+	 * information like GPA width, number of available vcpus, debug mode
+	 * information, etc. More details about the ABI can be found in TDX
+	 * Guest-Host-Communication Interface (GHCI), section 2.4.2 TDCALL
+	 * [TDG.VP.INFO].
+	 */
+	tdx_module_call(TDX_GET_INFO, 0, 0, 0, 0, &out);
+
+	/*
+	 * The highest bit of a guest physical address is the "sharing" bit.
+	 * Set it for shared pages and clear it for private pages.
+	 *
+	 * The GPA width that comes out of this call is critical. TDX guests
+	 * can not meaningfully run without it.
+	 */
+	gpa_width = out.rcx & GENMASK(5, 0);
+	*cc_mask = BIT_ULL(gpa_width - 1);
+
+	/*
+	 * The kernel can not handle #VE's when accessing normal kernel
+	 * memory.  Ensure that no #VE will be delivered for accesses to
+	 * TD-private memory.  Only VMM-shared memory (MMIO) will #VE.
+	 */
+	td_attr = out.rdx;
+	if (!(td_attr & ATTR_SEPT_VE_DISABLE))
+		panic("TD misconfiguration: SEPT_VE_DISABLE attibute must be set.\n");
+}
+
+/*
+ * The TDX module spec states that #VE may be injected for a limited set of
+ * reasons:
+ *
+ *  - Emulation of the architectural #VE injection on EPT violation;
+ *
+ *  - As a result of guest TD execution of a disallowed instruction,
+ *    a disallowed MSR access, or CPUID virtualization;
+ *
+ *  - A notification to the guest TD about anomalous behavior;
+ *
+ * The last one is opt-in and is not used by the kernel.
+ *
+ * The Intel Software Developer's Manual describes cases when instruction
+ * length field can be used in section "Information for VM Exits Due to
+ * Instruction Execution".
+ *
+ * For TDX, it ultimately means GET_VEINFO provides reliable instruction length
+ * information if #VE occurred due to instruction execution, but not for EPT
+ * violations.
+ */
+static int ve_instr_len(struct ve_info *ve)
+{
+	switch (ve->exit_reason) {
+	case EXIT_REASON_HLT:
+	case EXIT_REASON_MSR_READ:
+	case EXIT_REASON_MSR_WRITE:
+	case EXIT_REASON_CPUID:
+	case EXIT_REASON_IO_INSTRUCTION:
+		/* It is safe to use ve->instr_len for #VE due instructions */
+		return ve->instr_len;
+	case EXIT_REASON_EPT_VIOLATION:
+		/*
+		 * For EPT violations, ve->insn_len is not defined. For those,
+		 * the kernel must decode instructions manually and should not
+		 * be using this function.
+		 */
+		WARN_ONCE(1, "ve->instr_len is not defined for EPT violations");
+		return 0;
+	default:
+		WARN_ONCE(1, "Unexpected #VE-type: %lld\n", ve->exit_reason);
+		return ve->instr_len;
+	}
+}
+
+static u64 __cpuidle __halt(const bool irq_disabled, const bool do_sti)
+{
+	struct tdx_hypercall_args args = {
+		.r10 = TDX_HYPERCALL_STANDARD,
+		.r11 = hcall_func(EXIT_REASON_HLT),
+		.r12 = irq_disabled,
+	};
+
+	/*
+	 * Emulate HLT operation via hypercall. More info about ABI
+	 * can be found in TDX Guest-Host-Communication Interface
+	 * (GHCI), section 3.8 TDG.VP.VMCALL<Instruction.HLT>.
+	 *
+	 * The VMM uses the "IRQ disabled" param to understand IRQ
+	 * enabled status (RFLAGS.IF) of the TD guest and to determine
+	 * whether or not it should schedule the halted vCPU if an
+	 * IRQ becomes pending. E.g. if IRQs are disabled, the VMM
+	 * can keep the vCPU in virtual HLT, even if an IRQ is
+	 * pending, without hanging/breaking the guest.
+	 */
+	return __tdx_hypercall(&args, do_sti ? TDX_HCALL_ISSUE_STI : 0);
+}
+
+static int handle_halt(struct ve_info *ve)
+{
+	/*
+	 * Since non safe halt is mainly used in CPU offlining
+	 * and the guest will always stay in the halt state, don't
+	 * call the STI instruction (set do_sti as false).
+	 */
+	const bool irq_disabled = irqs_disabled();
+	const bool do_sti = false;
+
+	if (__halt(irq_disabled, do_sti))
+		return -EIO;
+
+	return ve_instr_len(ve);
+}
+
+void __cpuidle tdx_safe_halt(void)
+{
+	 /*
+	  * For do_sti=true case, __tdx_hypercall() function enables
+	  * interrupts using the STI instruction before the TDCALL. So
+	  * set irq_disabled as false.
+	  */
+	const bool irq_disabled = false;
+	const bool do_sti = true;
+
+	/*
+	 * Use WARN_ONCE() to report the failure.
+	 */
+	if (__halt(irq_disabled, do_sti))
+		WARN_ONCE(1, "HLT instruction emulation failed\n");
+}
+
+static int read_msr(struct pt_regs *regs, struct ve_info *ve)
+{
+	struct tdx_hypercall_args args = {
+		.r10 = TDX_HYPERCALL_STANDARD,
+		.r11 = hcall_func(EXIT_REASON_MSR_READ),
+		.r12 = regs->cx,
+	};
+
+	/*
+	 * Emulate the MSR read via hypercall. More info about ABI
+	 * can be found in TDX Guest-Host-Communication Interface
+	 * (GHCI), section titled "TDG.VP.VMCALL<Instruction.RDMSR>".
+	 */
+	if (__tdx_hypercall(&args, TDX_HCALL_HAS_OUTPUT))
+		return -EIO;
+
+	regs->ax = lower_32_bits(args.r11);
+	regs->dx = upper_32_bits(args.r11);
+	return ve_instr_len(ve);
+}
+
+static int write_msr(struct pt_regs *regs, struct ve_info *ve)
+{
+	struct tdx_hypercall_args args = {
+		.r10 = TDX_HYPERCALL_STANDARD,
+		.r11 = hcall_func(EXIT_REASON_MSR_WRITE),
+		.r12 = regs->cx,
+		.r13 = (u64)regs->dx << 32 | regs->ax,
+	};
+
+	/*
+	 * Emulate the MSR write via hypercall. More info about ABI
+	 * can be found in TDX Guest-Host-Communication Interface
+	 * (GHCI) section titled "TDG.VP.VMCALL<Instruction.WRMSR>".
+	 */
+	if (__tdx_hypercall(&args, 0))
+		return -EIO;
+
+	return ve_instr_len(ve);
+}
+
+static int handle_cpuid(struct pt_regs *regs, struct ve_info *ve)
+{
+	struct tdx_hypercall_args args = {
+		.r10 = TDX_HYPERCALL_STANDARD,
+		.r11 = hcall_func(EXIT_REASON_CPUID),
+		.r12 = regs->ax,
+		.r13 = regs->cx,
+	};
+
+	/*
+	 * Only allow VMM to control range reserved for hypervisor
+	 * communication.
+	 *
+	 * Return all-zeros for any CPUID outside the range. It matches CPU
+	 * behaviour for non-supported leaf.
+	 */
+	if (regs->ax < 0x40000000 || regs->ax > 0x4FFFFFFF) {
+		regs->ax = regs->bx = regs->cx = regs->dx = 0;
+		return ve_instr_len(ve);
+	}
+
+	/*
+	 * Emulate the CPUID instruction via a hypercall. More info about
+	 * ABI can be found in TDX Guest-Host-Communication Interface
+	 * (GHCI), section titled "VP.VMCALL<Instruction.CPUID>".
+	 */
+	if (__tdx_hypercall(&args, TDX_HCALL_HAS_OUTPUT))
+		return -EIO;
+
+	/*
+	 * As per TDX GHCI CPUID ABI, r12-r15 registers contain contents of
+	 * EAX, EBX, ECX, EDX registers after the CPUID instruction execution.
+	 * So copy the register contents back to pt_regs.
+	 */
+	regs->ax = args.r12;
+	regs->bx = args.r13;
+	regs->cx = args.r14;
+	regs->dx = args.r15;
+
+	return ve_instr_len(ve);
+}
+
+static bool mmio_read(int size, unsigned long addr, unsigned long *val)
+{
+	struct tdx_hypercall_args args = {
+		.r10 = TDX_HYPERCALL_STANDARD,
+		.r11 = hcall_func(EXIT_REASON_EPT_VIOLATION),
+		.r12 = size,
+		.r13 = EPT_READ,
+		.r14 = addr,
+		.r15 = *val,
+	};
+
+	if (__tdx_hypercall(&args, TDX_HCALL_HAS_OUTPUT))
+		return false;
+	*val = args.r11;
+	return true;
+}
+
+static bool mmio_write(int size, unsigned long addr, unsigned long val)
+{
+	return !_tdx_hypercall(hcall_func(EXIT_REASON_EPT_VIOLATION), size,
+			       EPT_WRITE, addr, val);
+}
+
+static int handle_mmio(struct pt_regs *regs, struct ve_info *ve)
+{
+	unsigned long *reg, val, vaddr;
+	char buffer[MAX_INSN_SIZE];
+	struct insn insn = {};
+	enum mmio_type mmio;
+	int size, extend_size;
+	u8 extend_val = 0;
+
+	/* Only in-kernel MMIO is supported */
+	if (WARN_ON_ONCE(user_mode(regs)))
+		return -EFAULT;
+
+	if (copy_from_kernel_nofault(buffer, (void *)regs->ip, MAX_INSN_SIZE))
+		return -EFAULT;
+
+	if (insn_decode(&insn, buffer, MAX_INSN_SIZE, INSN_MODE_64))
+		return -EINVAL;
+
+	mmio = insn_decode_mmio(&insn, &size);
+	if (WARN_ON_ONCE(mmio == MMIO_DECODE_FAILED))
+		return -EINVAL;
+
+	if (mmio != MMIO_WRITE_IMM && mmio != MMIO_MOVS) {
+		reg = insn_get_modrm_reg_ptr(&insn, regs);
+		if (!reg)
+			return -EINVAL;
+	}
+
+	/*
+	 * Reject EPT violation #VEs that split pages.
+	 *
+	 * MMIO accesses are supposed to be naturally aligned and therefore
+	 * never cross page boundaries. Seeing split page accesses indicates
+	 * a bug or a load_unaligned_zeropad() that stepped into an MMIO page.
+	 *
+	 * load_unaligned_zeropad() will recover using exception fixups.
+	 */
+	vaddr = (unsigned long)insn_get_addr_ref(&insn, regs);
+	if (vaddr / PAGE_SIZE != (vaddr + size - 1) / PAGE_SIZE)
+		return -EFAULT;
+
+	/* Handle writes first */
+	switch (mmio) {
+	case MMIO_WRITE:
+		memcpy(&val, reg, size);
+		if (!mmio_write(size, ve->gpa, val))
+			return -EIO;
+		return insn.length;
+	case MMIO_WRITE_IMM:
+		val = insn.immediate.value;
+		if (!mmio_write(size, ve->gpa, val))
+			return -EIO;
+		return insn.length;
+	case MMIO_READ:
+	case MMIO_READ_ZERO_EXTEND:
+	case MMIO_READ_SIGN_EXTEND:
+		/* Reads are handled below */
+		break;
+	case MMIO_MOVS:
+	case MMIO_DECODE_FAILED:
+		/*
+		 * MMIO was accessed with an instruction that could not be
+		 * decoded or handled properly. It was likely not using io.h
+		 * helpers or accessed MMIO accidentally.
+		 */
+		return -EINVAL;
+	default:
+		WARN_ONCE(1, "Unknown insn_decode_mmio() decode value?");
+		return -EINVAL;
+	}
+
+	/* Handle reads */
+	if (!mmio_read(size, ve->gpa, &val))
+		return -EIO;
+
+	switch (mmio) {
+	case MMIO_READ:
+		/* Zero-extend for 32-bit operation */
+		extend_size = size == 4 ? sizeof(*reg) : 0;
+		break;
+	case MMIO_READ_ZERO_EXTEND:
+		/* Zero extend based on operand size */
+		extend_size = insn.opnd_bytes;
+		break;
+	case MMIO_READ_SIGN_EXTEND:
+		/* Sign extend based on operand size */
+		extend_size = insn.opnd_bytes;
+		if (size == 1 && val & BIT(7))
+			extend_val = 0xFF;
+		else if (size > 1 && val & BIT(15))
+			extend_val = 0xFF;
+		break;
+	default:
+		/* All other cases has to be covered with the first switch() */
+		WARN_ON_ONCE(1);
+		return -EINVAL;
+	}
+
+	if (extend_size)
+		memset(reg, extend_val, extend_size);
+	memcpy(reg, &val, size);
+	return insn.length;
+}
+
+static bool handle_in(struct pt_regs *regs, int size, int port)
+{
+	struct tdx_hypercall_args args = {
+		.r10 = TDX_HYPERCALL_STANDARD,
+		.r11 = hcall_func(EXIT_REASON_IO_INSTRUCTION),
+		.r12 = size,
+		.r13 = PORT_READ,
+		.r14 = port,
+	};
+	u64 mask = GENMASK(BITS_PER_BYTE * size, 0);
+	bool success;
+
+	/*
+	 * Emulate the I/O read via hypercall. More info about ABI can be found
+	 * in TDX Guest-Host-Communication Interface (GHCI) section titled
+	 * "TDG.VP.VMCALL<Instruction.IO>".
+	 */
+	success = !__tdx_hypercall(&args, TDX_HCALL_HAS_OUTPUT);
+
+	/* Update part of the register affected by the emulated instruction */
+	regs->ax &= ~mask;
+	if (success)
+		regs->ax |= args.r11 & mask;
+
+	return success;
+}
+
+static bool handle_out(struct pt_regs *regs, int size, int port)
+{
+	u64 mask = GENMASK(BITS_PER_BYTE * size, 0);
+
+	/*
+	 * Emulate the I/O write via hypercall. More info about ABI can be found
+	 * in TDX Guest-Host-Communication Interface (GHCI) section titled
+	 * "TDG.VP.VMCALL<Instruction.IO>".
+	 */
+	return !_tdx_hypercall(hcall_func(EXIT_REASON_IO_INSTRUCTION), size,
+			       PORT_WRITE, port, regs->ax & mask);
+}
+
+/*
+ * Emulate I/O using hypercall.
+ *
+ * Assumes the IO instruction was using ax, which is enforced
+ * by the standard io.h macros.
+ *
+ * Return True on success or False on failure.
+ */
+static int handle_io(struct pt_regs *regs, struct ve_info *ve)
+{
+	u32 exit_qual = ve->exit_qual;
+	int size, port;
+	bool in, ret;
+
+	if (VE_IS_IO_STRING(exit_qual))
+		return -EIO;
+
+	in   = VE_IS_IO_IN(exit_qual);
+	size = VE_GET_IO_SIZE(exit_qual);
+	port = VE_GET_PORT_NUM(exit_qual);
+
+
+	if (in)
+		ret = handle_in(regs, size, port);
+	else
+		ret = handle_out(regs, size, port);
+	if (!ret)
+		return -EIO;
+
+	return ve_instr_len(ve);
+}
+
+/*
+ * Early #VE exception handler. Only handles a subset of port I/O.
+ * Intended only for earlyprintk. If failed, return false.
+ */
+__init bool tdx_early_handle_ve(struct pt_regs *regs)
+{
+	struct ve_info ve;
+	int insn_len;
+
+	tdx_get_ve_info(&ve);
+
+	if (ve.exit_reason != EXIT_REASON_IO_INSTRUCTION)
+		return false;
+
+	insn_len = handle_io(regs, &ve);
+	if (insn_len < 0)
+		return false;
+
+	regs->ip += insn_len;
+	return true;
+}
+
+void tdx_get_ve_info(struct ve_info *ve)
+{
+	struct tdx_module_output out;
+
+	/*
+	 * Called during #VE handling to retrieve the #VE info from the
+	 * TDX module.
+	 *
+	 * This has to be called early in #VE handling.  A "nested" #VE which
+	 * occurs before this will raise a #DF and is not recoverable.
+	 *
+	 * The call retrieves the #VE info from the TDX module, which also
+	 * clears the "#VE valid" flag. This must be done before anything else
+	 * because any #VE that occurs while the valid flag is set will lead to
+	 * #DF.
+	 *
+	 * Note, the TDX module treats virtual NMIs as inhibited if the #VE
+	 * valid flag is set. It means that NMI=>#VE will not result in a #DF.
+	 */
+	tdx_module_call(TDX_GET_VEINFO, 0, 0, 0, 0, &out);
+
+	/* Transfer the output parameters */
+	ve->exit_reason = out.rcx;
+	ve->exit_qual   = out.rdx;
+	ve->gla         = out.r8;
+	ve->gpa         = out.r9;
+	ve->instr_len   = lower_32_bits(out.r10);
+	ve->instr_info  = upper_32_bits(out.r10);
+}
+
+/*
+ * Handle the user initiated #VE.
+ *
+ * On success, returns the number of bytes RIP should be incremented (>=0)
+ * or -errno on error.
+ */
+static int virt_exception_user(struct pt_regs *regs, struct ve_info *ve)
+{
+	switch (ve->exit_reason) {
+	case EXIT_REASON_CPUID:
+		return handle_cpuid(regs, ve);
+	default:
+		pr_warn("Unexpected #VE: %lld\n", ve->exit_reason);
+		return -EIO;
+	}
+}
+
+/*
+ * Handle the kernel #VE.
+ *
+ * On success, returns the number of bytes RIP should be incremented (>=0)
+ * or -errno on error.
+ */
+static int virt_exception_kernel(struct pt_regs *regs, struct ve_info *ve)
+{
+	switch (ve->exit_reason) {
+	case EXIT_REASON_HLT:
+		return handle_halt(ve);
+	case EXIT_REASON_MSR_READ:
+		return read_msr(regs, ve);
+	case EXIT_REASON_MSR_WRITE:
+		return write_msr(regs, ve);
+	case EXIT_REASON_CPUID:
+		return handle_cpuid(regs, ve);
+	case EXIT_REASON_EPT_VIOLATION:
+		return handle_mmio(regs, ve);
+	case EXIT_REASON_IO_INSTRUCTION:
+		return handle_io(regs, ve);
+	default:
+		pr_warn("Unexpected #VE: %lld\n", ve->exit_reason);
+		return -EIO;
+	}
+}
+
+bool tdx_handle_virt_exception(struct pt_regs *regs, struct ve_info *ve)
+{
+	int insn_len;
+
+	if (user_mode(regs))
+		insn_len = virt_exception_user(regs, ve);
+	else
+		insn_len = virt_exception_kernel(regs, ve);
+	if (insn_len < 0)
+		return false;
+
+	/* After successful #VE handling, move the IP */
+	regs->ip += insn_len;
+
+	return true;
+}
+
+static bool tdx_tlb_flush_required(bool private)
+{
+	/*
+	 * TDX guest is responsible for flushing TLB on private->shared
+	 * transition. VMM is responsible for flushing on shared->private.
+	 *
+	 * The VMM _can't_ flush private addresses as it can't generate PAs
+	 * with the guest's HKID.  Shared memory isn't subject to integrity
+	 * checking, i.e. the VMM doesn't need to flush for its own protection.
+	 *
+	 * There's no need to flush when converting from shared to private,
+	 * as flushing is the VMM's responsibility in this case, e.g. it must
+	 * flush to avoid integrity failures in the face of a buggy or
+	 * malicious guest.
+	 */
+	return !private;
+}
+
+static bool tdx_cache_flush_required(void)
+{
+	/*
+	 * AMD SME/SEV can avoid cache flushing if HW enforces cache coherence.
+	 * TDX doesn't have such capability.
+	 *
+	 * Flush cache unconditionally.
+	 */
+	return true;
+}
+
+static bool try_accept_one(phys_addr_t *start, unsigned long len,
+			  enum pg_level pg_level)
+{
+	unsigned long accept_size = page_level_size(pg_level);
+	u64 tdcall_rcx;
+	u8 page_size;
+
+	if (!IS_ALIGNED(*start, accept_size))
+		return false;
+
+	if (len < accept_size)
+		return false;
+
+	/*
+	 * Pass the page physical address to the TDX module to accept the
+	 * pending, private page.
+	 *
+	 * Bits 2:0 of RCX encode page size: 0 - 4K, 1 - 2M, 2 - 1G.
+	 */
+	switch (pg_level) {
+	case PG_LEVEL_4K:
+		page_size = 0;
+		break;
+	case PG_LEVEL_2M:
+		page_size = 1;
+		break;
+	case PG_LEVEL_1G:
+		page_size = 2;
+		break;
+	default:
+		return false;
+	}
+
+	tdcall_rcx = *start | page_size;
+	if (__tdx_module_call(TDX_ACCEPT_PAGE, tdcall_rcx, 0, 0, 0, NULL))
+		return false;
+
+	*start += accept_size;
+	return true;
+}
+
+/*
+ * Inform the VMM of the guest's intent for this physical page: shared with
+ * the VMM or private to the guest.  The VMM is expected to change its mapping
+ * of the page in response.
+ */
+static bool tdx_enc_status_changed(unsigned long vaddr, int numpages, bool enc)
+{
+	phys_addr_t start = __pa(vaddr);
+	phys_addr_t end   = __pa(vaddr + numpages * PAGE_SIZE);
+
+	if (!enc) {
+		/* Set the shared (decrypted) bits: */
+		start |= cc_mkdec(0);
+		end   |= cc_mkdec(0);
+	}
+
+	/*
+	 * Notify the VMM about page mapping conversion. More info about ABI
+	 * can be found in TDX Guest-Host-Communication Interface (GHCI),
+	 * section "TDG.VP.VMCALL<MapGPA>"
+	 */
+	if (_tdx_hypercall(TDVMCALL_MAP_GPA, start, end - start, 0, 0))
+		return false;
+
+	/* private->shared conversion  requires only MapGPA call */
+	if (!enc)
+		return true;
+
+	/*
+	 * For shared->private conversion, accept the page using
+	 * TDX_ACCEPT_PAGE TDX module call.
+	 */
+	while (start < end) {
+		unsigned long len = end - start;
+
+		/*
+		 * Try larger accepts first. It gives chance to VMM to keep
+		 * 1G/2M SEPT entries where possible and speeds up process by
+		 * cutting number of hypercalls (if successful).
+		 */
+
+		if (try_accept_one(&start, len, PG_LEVEL_1G))
+			continue;
+
+		if (try_accept_one(&start, len, PG_LEVEL_2M))
+			continue;
+
+		if (!try_accept_one(&start, len, PG_LEVEL_4K))
+			return false;
+	}
+
+	return true;
+}
+
+static bool tdx_enc_status_change_prepare(unsigned long vaddr, int numpages,
+					  bool enc)
+{
+	/*
+	 * Only handle shared->private conversion here.
+	 * See the comment in tdx_early_init().
+	 */
+	if (enc)
+		return tdx_enc_status_changed(vaddr, numpages, enc);
+	return true;
+}
+
+static bool tdx_enc_status_change_finish(unsigned long vaddr, int numpages,
+					 bool enc)
+{
+	/*
+	 * Only handle private->shared conversion here.
+	 * See the comment in tdx_early_init().
+	 */
+	if (!enc)
+		return tdx_enc_status_changed(vaddr, numpages, enc);
+	return true;
+}
+
+void __init tdx_early_init(void)
+{
+	u64 cc_mask;
+	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;
+
+	setup_force_cpu_cap(X86_FEATURE_TDX_GUEST);
+
+	cc_set_vendor(CC_VENDOR_INTEL);
+	tdx_parse_tdinfo(&cc_mask);
+	cc_set_mask(cc_mask);
+
+	/*
+	 * All bits above GPA width are reserved and kernel treats shared bit
+	 * as flag, not as part of physical address.
+	 *
+	 * Adjust physical mask to only cover valid GPA bits.
+	 */
+	physical_mask &= cc_mask - 1;
+
+	/*
+	 * The kernel mapping should match the TDX metadata for the page.
+	 * load_unaligned_zeropad() can touch memory *adjacent* to that which is
+	 * owned by the caller and can catch even _momentary_ mismatches.  Bad
+	 * things happen on mismatch:
+	 *
+	 *   - Private mapping => Shared Page  == Guest shutdown
+         *   - Shared mapping  => Private Page == Recoverable #VE
+	 *
+	 * guest.enc_status_change_prepare() converts the page from
+	 * shared=>private before the mapping becomes private.
+	 *
+	 * guest.enc_status_change_finish() converts the page from
+	 * private=>shared after the mapping becomes private.
+	 *
+	 * In both cases there is a temporary shared mapping to a private page,
+	 * which can result in a #VE.  But, there is never a private mapping to
+	 * a shared page.
+	 */
+	x86_platform.guest.enc_status_change_prepare = tdx_enc_status_change_prepare;
+	x86_platform.guest.enc_status_change_finish  = tdx_enc_status_change_finish;
+
+	x86_platform.guest.enc_cache_flush_required  = tdx_cache_flush_required;
+	x86_platform.guest.enc_tlb_flush_required    = tdx_tlb_flush_required;
+
+	pr_info("Guest detected\n");
+}