Merge tag 'x86_tdx_for_v5.19_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull Intel TDX support from Borislav Petkov:
 "Intel Trust Domain Extensions (TDX) support.

  This is the Intel version of a confidential computing solution called
  Trust Domain Extensions (TDX). This series adds support to run the
  kernel as part of a TDX guest. It provides similar guest protections
  to AMD's SEV-SNP like guest memory and register state encryption,
  memory integrity protection and a lot more.

  Design-wise, it differs from AMD's solution considerably: it uses a
  software module which runs in a special CPU mode called (Secure
  Arbitration Mode) SEAM. As the name suggests, this module serves as
  sort of an arbiter which the confidential guest calls for services it
  needs during its lifetime.

  Just like AMD's SNP set, this series reworks and streamlines certain
  parts of x86 arch code so that this feature can be properly
  accomodated"

* tag 'x86_tdx_for_v5.19_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (34 commits)
  x86/tdx: Fix RETs in TDX asm
  x86/tdx: Annotate a noreturn function
  x86/mm: Fix spacing within memory encryption features message
  x86/kaslr: Fix build warning in KASLR code in boot stub
  Documentation/x86: Document TDX kernel architecture
  ACPICA: Avoid cache flush inside virtual machines
  x86/tdx/ioapic: Add shared bit for IOAPIC base address
  x86/mm: Make DMA memory shared for TD guest
  x86/mm/cpa: Add support for TDX shared memory
  x86/tdx: Make pages shared in ioremap()
  x86/topology: Disable CPU online/offline control for TDX guests
  x86/boot: Avoid #VE during boot for TDX platforms
  x86/boot: Set CR0.NE early and keep it set during the boot
  x86/acpi/x86/boot: Add multiprocessor wake-up support
  x86/boot: Add a trampoline for booting APs via firmware handoff
  x86/tdx: Wire up KVM hypercalls
  x86/tdx: Port I/O: Add early boot support
  x86/tdx: Port I/O: Add runtime hypercalls
  x86/boot: Port I/O: Add decompression-time support for TDX
  x86/boot: Port I/O: Allow to hook up alternative helpers
  ...

12 files changed, 235 insertions, 35 deletions

diff --git a/arch/x86/include/asm/acenv.h b/arch/x86/include/asm/acenv.h
index 9aff97f0de7f..d937c55e717e 100644
--- a/arch/x86/include/asm/acenv.h
+++ b/arch/x86/include/asm/acenv.h
@@ -13,7 +13,19 @@
 
 /* Asm macros */
 
-#define ACPI_FLUSH_CPU_CACHE()	wbinvd()
+/*
+ * ACPI_FLUSH_CPU_CACHE() flushes caches on entering sleep states.
+ * It is required to prevent data loss.
+ *
+ * While running inside virtual machine, the kernel can bypass cache flushing.
+ * Changing sleep state in a virtual machine doesn't affect the host system
+ * sleep state and cannot lead to data loss.
+ */
+#define ACPI_FLUSH_CPU_CACHE()					\
+do {								\
+	if (!cpu_feature_enabled(X86_FEATURE_HYPERVISOR))	\
+		wbinvd();					\
+} while (0)
 
 int __acpi_acquire_global_lock(unsigned int *lock);
 int __acpi_release_global_lock(unsigned int *lock);
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index 48067af94678..bd8ae0a7010a 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -328,6 +328,8 @@ struct apic {
 
 	/* wakeup_secondary_cpu */
 	int	(*wakeup_secondary_cpu)(int apicid, unsigned long start_eip);
+	/* wakeup secondary CPU using 64-bit wakeup point */
+	int	(*wakeup_secondary_cpu_64)(int apicid, unsigned long start_eip);
 
 	void	(*inquire_remote_apic)(int apicid);
 
@@ -488,6 +490,11 @@ static inline unsigned int read_apic_id(void)
 	return apic->get_apic_id(reg);
 }
 
+#ifdef CONFIG_X86_64
+typedef int (*wakeup_cpu_handler)(int apicid, unsigned long start_eip);
+extern void acpi_wake_cpu_handler_update(wakeup_cpu_handler handler);
+#endif
+
 extern int default_apic_id_valid(u32 apicid);
 extern int default_acpi_madt_oem_check(char *, char *);
 extern void default_setup_apic_routing(void);
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 73e643ae94b6..20df73b51025 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -238,6 +238,7 @@
 #define X86_FEATURE_VMW_VMMCALL		( 8*32+19) /* "" VMware prefers VMMCALL hypercall instruction */
 #define X86_FEATURE_PVUNLOCK		( 8*32+20) /* "" PV unlock function */
 #define X86_FEATURE_VCPUPREEMPT		( 8*32+21) /* "" PV vcpu_is_preempted function */
+#define X86_FEATURE_TDX_GUEST		( 8*32+22) /* Intel Trust Domain Extensions Guest */
 
 /* Intel-defined CPU features, CPUID level 0x00000007:0 (EBX), word 9 */
 #define X86_FEATURE_FSGSBASE		( 9*32+ 0) /* RDFSBASE, WRFSBASE, RDGSBASE, WRGSBASE instructions*/
diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h
index 1231d63f836d..b37de8268c9a 100644
--- a/arch/x86/include/asm/disabled-features.h
+++ b/arch/x86/include/asm/disabled-features.h
@@ -68,6 +68,12 @@
 # define DISABLE_SGX	(1 << (X86_FEATURE_SGX & 31))
 #endif
 
+#ifdef CONFIG_INTEL_TDX_GUEST
+# define DISABLE_TDX_GUEST	0
+#else
+# define DISABLE_TDX_GUEST	(1 << (X86_FEATURE_TDX_GUEST & 31))
+#endif
+
 /*
  * Make sure to add features to the correct mask
  */
@@ -79,7 +85,7 @@
 #define DISABLED_MASK5	0
 #define DISABLED_MASK6	0
 #define DISABLED_MASK7	(DISABLE_PTI)
-#define DISABLED_MASK8	0
+#define DISABLED_MASK8	(DISABLE_TDX_GUEST)
 #define DISABLED_MASK9	(DISABLE_SMAP|DISABLE_SGX)
 #define DISABLED_MASK10	0
 #define DISABLED_MASK11	0
diff --git a/arch/x86/include/asm/idtentry.h b/arch/x86/include/asm/idtentry.h
index 7924f27f5c8b..72184b0b2219 100644
--- a/arch/x86/include/asm/idtentry.h
+++ b/arch/x86/include/asm/idtentry.h
@@ -632,6 +632,10 @@ DECLARE_IDTENTRY_XENCB(X86_TRAP_OTHER,	exc_xen_hypervisor_callback);
 DECLARE_IDTENTRY_RAW(X86_TRAP_OTHER,	exc_xen_unknown_trap);
 #endif
 
+#ifdef CONFIG_INTEL_TDX_GUEST
+DECLARE_IDTENTRY(X86_TRAP_VE,		exc_virtualization_exception);
+#endif
+
 /* Device interrupts common/spurious */
 DECLARE_IDTENTRY_IRQ(X86_TRAP_OTHER,	common_interrupt);
 #ifdef CONFIG_X86_LOCAL_APIC
diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h
index e9736af126b2..1870b99c3356 100644
--- a/arch/x86/include/asm/io.h
+++ b/arch/x86/include/asm/io.h
@@ -44,6 +44,7 @@
 #include <asm/page.h>
 #include <asm/early_ioremap.h>
 #include <asm/pgtable_types.h>
+#include <asm/shared/io.h>
 
 #define build_mmio_read(name, size, type, reg, barrier) \
 static inline type name(const volatile void __iomem *addr) \
@@ -256,37 +257,23 @@ static inline void slow_down_io(void)
 #endif
 
 #define BUILDIO(bwl, bw, type)						\
-static inline void out##bwl(unsigned type value, int port)		\
-{									\
-	asm volatile("out" #bwl " %" #bw "0, %w1"			\
-		     : : "a"(value), "Nd"(port));			\
-}									\
-									\
-static inline unsigned type in##bwl(int port)				\
-{									\
-	unsigned type value;						\
-	asm volatile("in" #bwl " %w1, %" #bw "0"			\
-		     : "=a"(value) : "Nd"(port));			\
-	return value;							\
-}									\
-									\
-static inline void out##bwl##_p(unsigned type value, int port)		\
+static inline void out##bwl##_p(type value, u16 port)			\
 {									\
 	out##bwl(value, port);						\
 	slow_down_io();							\
 }									\
 									\
-static inline unsigned type in##bwl##_p(int port)			\
+static inline type in##bwl##_p(u16 port)				\
 {									\
-	unsigned type value = in##bwl(port);				\
+	type value = in##bwl(port);					\
 	slow_down_io();							\
 	return value;							\
 }									\
 									\
-static inline void outs##bwl(int port, const void *addr, unsigned long count) \
+static inline void outs##bwl(u16 port, const void *addr, unsigned long count) \
 {									\
 	if (cc_platform_has(CC_ATTR_GUEST_UNROLL_STRING_IO)) {		\
-		unsigned type *value = (unsigned type *)addr;		\
+		type *value = (type *)addr;				\
 		while (count) {						\
 			out##bwl(*value, port);				\
 			value++;					\
@@ -299,10 +286,10 @@ 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)	\
+static inline void ins##bwl(u16 port, void *addr, unsigned long count)	\
 {									\
 	if (cc_platform_has(CC_ATTR_GUEST_UNROLL_STRING_IO)) {		\
-		unsigned type *value = (unsigned type *)addr;		\
+		type *value = (type *)addr;				\
 		while (count) {						\
 			*value = in##bwl(port);				\
 			value++;					\
@@ -315,13 +302,11 @@ static inline void ins##bwl(int port, void *addr, unsigned long count)	\
 	}								\
 }
 
-BUILDIO(b, b, char)
-BUILDIO(w, w, short)
-BUILDIO(l, , int)
+BUILDIO(b, b, u8)
+BUILDIO(w, w, u16)
+BUILDIO(l,  , u32)
+#undef BUILDIO
 
-#define inb inb
-#define inw inw
-#define inl inl
 #define inb_p inb_p
 #define inw_p inw_p
 #define inl_p inl_p
@@ -329,9 +314,6 @@ BUILDIO(l, , int)
 #define insw insw
 #define insl insl
 
-#define outb outb
-#define outw outw
-#define outl outl
 #define outb_p outb_p
 #define outw_p outw_p
 #define outl_p outl_p
diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h
index 56935ebb1dfe..57bc74e112f2 100644
--- a/arch/x86/include/asm/kvm_para.h
+++ b/arch/x86/include/asm/kvm_para.h
@@ -7,6 +7,8 @@
 #include <linux/interrupt.h>
 #include <uapi/asm/kvm_para.h>
 
+#include <asm/tdx.h>
+
 #ifdef CONFIG_KVM_GUEST
 bool kvm_check_and_clear_guest_paused(void);
 #else
@@ -32,6 +34,10 @@ static inline bool kvm_check_and_clear_guest_paused(void)
 static inline long kvm_hypercall0(unsigned int nr)
 {
 	long ret;
+
+	if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST))
+		return tdx_kvm_hypercall(nr, 0, 0, 0, 0);
+
 	asm volatile(KVM_HYPERCALL
 		     : "=a"(ret)
 		     : "a"(nr)
@@ -42,6 +48,10 @@ static inline long kvm_hypercall0(unsigned int nr)
 static inline long kvm_hypercall1(unsigned int nr, unsigned long p1)
 {
 	long ret;
+
+	if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST))
+		return tdx_kvm_hypercall(nr, p1, 0, 0, 0);
+
 	asm volatile(KVM_HYPERCALL
 		     : "=a"(ret)
 		     : "a"(nr), "b"(p1)
@@ -53,6 +63,10 @@ static inline long kvm_hypercall2(unsigned int nr, unsigned long p1,
 				  unsigned long p2)
 {
 	long ret;
+
+	if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST))
+		return tdx_kvm_hypercall(nr, p1, p2, 0, 0);
+
 	asm volatile(KVM_HYPERCALL
 		     : "=a"(ret)
 		     : "a"(nr), "b"(p1), "c"(p2)
@@ -64,6 +78,10 @@ static inline long kvm_hypercall3(unsigned int nr, unsigned long p1,
 				  unsigned long p2, unsigned long p3)
 {
 	long ret;
+
+	if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST))
+		return tdx_kvm_hypercall(nr, p1, p2, p3, 0);
+
 	asm volatile(KVM_HYPERCALL
 		     : "=a"(ret)
 		     : "a"(nr), "b"(p1), "c"(p2), "d"(p3)
@@ -76,6 +94,10 @@ static inline long kvm_hypercall4(unsigned int nr, unsigned long p1,
 				  unsigned long p4)
 {
 	long ret;
+
+	if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST))
+		return tdx_kvm_hypercall(nr, p1, p2, p3, p4);
+
 	asm volatile(KVM_HYPERCALL
 		     : "=a"(ret)
 		     : "a"(nr), "b"(p1), "c"(p2), "d"(p3), "S"(p4)
diff --git a/arch/x86/include/asm/mem_encrypt.h b/arch/x86/include/asm/mem_encrypt.h
index e2c6f433ed10..88ceaf3648b3 100644
--- a/arch/x86/include/asm/mem_encrypt.h
+++ b/arch/x86/include/asm/mem_encrypt.h
@@ -49,9 +49,6 @@ void __init early_set_mem_enc_dec_hypercall(unsigned long vaddr, int npages,
 
 void __init mem_encrypt_free_decrypted_mem(void);
 
-/* Architecture __weak replacement functions */
-void __init mem_encrypt_init(void);
-
 void __init sev_es_init_vc_handling(void);
 
 #define __bss_decrypted __section(".bss..decrypted")
@@ -89,6 +86,9 @@ static inline void mem_encrypt_free_decrypted_mem(void) { }
 
 #endif	/* CONFIG_AMD_MEM_ENCRYPT */
 
+/* Architecture __weak replacement functions */
+void __init mem_encrypt_init(void);
+
 /*
  * The __sme_pa() and __sme_pa_nodebug() macros are meant for use when
  * writing to or comparing values from the cr3 register.  Having the
diff --git a/arch/x86/include/asm/realmode.h b/arch/x86/include/asm/realmode.h
index 331474b150f1..fd6f6e5b755a 100644
--- a/arch/x86/include/asm/realmode.h
+++ b/arch/x86/include/asm/realmode.h
@@ -25,6 +25,7 @@ struct real_mode_header {
 	u32	sev_es_trampoline_start;
 #endif
 #ifdef CONFIG_X86_64
+	u32	trampoline_start64;
 	u32	trampoline_pgd;
 #endif
 	/* ACPI S3 wakeup */
diff --git a/arch/x86/include/asm/shared/io.h b/arch/x86/include/asm/shared/io.h
new file mode 100644
index 000000000000..c0ef921c0586
--- /dev/null
+++ b/arch/x86/include/asm/shared/io.h
@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_X86_SHARED_IO_H
+#define _ASM_X86_SHARED_IO_H
+
+#include <linux/types.h>
+
+#define BUILDIO(bwl, bw, type)						\
+static inline void __out##bwl(type value, u16 port)			\
+{									\
+	asm volatile("out" #bwl " %" #bw "0, %w1"			\
+		     : : "a"(value), "Nd"(port));			\
+}									\
+									\
+static inline type __in##bwl(u16 port)					\
+{									\
+	type value;							\
+	asm volatile("in" #bwl " %w1, %" #bw "0"			\
+		     : "=a"(value) : "Nd"(port));			\
+	return value;							\
+}
+
+BUILDIO(b, b, u8)
+BUILDIO(w, w, u16)
+BUILDIO(l,  , u32)
+#undef BUILDIO
+
+#define inb __inb
+#define inw __inw
+#define inl __inl
+#define outb __outb
+#define outw __outw
+#define outl __outl
+
+#endif
diff --git a/arch/x86/include/asm/shared/tdx.h b/arch/x86/include/asm/shared/tdx.h
new file mode 100644
index 000000000000..e53f26228fbb
--- /dev/null
+++ b/arch/x86/include/asm/shared/tdx.h
@@ -0,0 +1,40 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_X86_SHARED_TDX_H
+#define _ASM_X86_SHARED_TDX_H
+
+#include <linux/bits.h>
+#include <linux/types.h>
+
+#define TDX_HYPERCALL_STANDARD  0
+
+#define TDX_HCALL_HAS_OUTPUT	BIT(0)
+#define TDX_HCALL_ISSUE_STI	BIT(1)
+
+#define TDX_CPUID_LEAF_ID	0x21
+#define TDX_IDENT		"IntelTDX    "
+
+#ifndef __ASSEMBLY__
+
+/*
+ * Used in __tdx_hypercall() to pass down and get back registers' values of
+ * the TDCALL instruction when requesting services from the VMM.
+ *
+ * This is a software only structure and not part of the TDX module/VMM ABI.
+ */
+struct tdx_hypercall_args {
+	u64 r10;
+	u64 r11;
+	u64 r12;
+	u64 r13;
+	u64 r14;
+	u64 r15;
+};
+
+/* Used to request services from the VMM */
+u64 __tdx_hypercall(struct tdx_hypercall_args *args, unsigned long flags);
+
+/* Called from __tdx_hypercall() for unrecoverable failure */
+void __tdx_hypercall_failed(void);
+
+#endif /* !__ASSEMBLY__ */
+#endif /* _ASM_X86_SHARED_TDX_H */
diff --git a/arch/x86/include/asm/tdx.h b/arch/x86/include/asm/tdx.h
new file mode 100644
index 000000000000..020c81a7c729
--- /dev/null
+++ b/arch/x86/include/asm/tdx.h
@@ -0,0 +1,91 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2021-2022 Intel Corporation */
+#ifndef _ASM_X86_TDX_H
+#define _ASM_X86_TDX_H
+
+#include <linux/init.h>
+#include <linux/bits.h>
+#include <asm/ptrace.h>
+#include <asm/shared/tdx.h>
+
+/*
+ * SW-defined error codes.
+ *
+ * Bits 47:40 == 0xFF indicate Reserved status code class that never used by
+ * TDX module.
+ */
+#define TDX_ERROR			_BITUL(63)
+#define TDX_SW_ERROR			(TDX_ERROR | GENMASK_ULL(47, 40))
+#define TDX_SEAMCALL_VMFAILINVALID	(TDX_SW_ERROR | _UL(0xFFFF0000))
+
+#ifndef __ASSEMBLY__
+
+/*
+ * Used to gather the output registers values of the TDCALL and SEAMCALL
+ * instructions when requesting services from the TDX module.
+ *
+ * This is a software only structure and not part of the TDX module/VMM ABI.
+ */
+struct tdx_module_output {
+	u64 rcx;
+	u64 rdx;
+	u64 r8;
+	u64 r9;
+	u64 r10;
+	u64 r11;
+};
+
+/*
+ * Used by the #VE exception handler to gather the #VE exception
+ * info from the TDX module. This is a software only structure
+ * and not part of the TDX module/VMM ABI.
+ */
+struct ve_info {
+	u64 exit_reason;
+	u64 exit_qual;
+	/* Guest Linear (virtual) Address */
+	u64 gla;
+	/* Guest Physical Address */
+	u64 gpa;
+	u32 instr_len;
+	u32 instr_info;
+};
+
+#ifdef CONFIG_INTEL_TDX_GUEST
+
+void __init tdx_early_init(void);
+
+/* Used to communicate with the TDX module */
+u64 __tdx_module_call(u64 fn, u64 rcx, u64 rdx, u64 r8, u64 r9,
+		      struct tdx_module_output *out);
+
+void tdx_get_ve_info(struct ve_info *ve);
+
+bool tdx_handle_virt_exception(struct pt_regs *regs, struct ve_info *ve);
+
+void tdx_safe_halt(void);
+
+bool tdx_early_handle_ve(struct pt_regs *regs);
+
+#else
+
+static inline void tdx_early_init(void) { };
+static inline void tdx_safe_halt(void) { };
+
+static inline bool tdx_early_handle_ve(struct pt_regs *regs) { return false; }
+
+#endif /* CONFIG_INTEL_TDX_GUEST */
+
+#if defined(CONFIG_KVM_GUEST) && defined(CONFIG_INTEL_TDX_GUEST)
+long tdx_kvm_hypercall(unsigned int nr, unsigned long p1, unsigned long p2,
+		       unsigned long p3, unsigned long p4);
+#else
+static inline long tdx_kvm_hypercall(unsigned int nr, unsigned long p1,
+				     unsigned long p2, unsigned long p3,
+				     unsigned long p4)
+{
+	return -ENODEV;
+}
+#endif /* CONFIG_INTEL_TDX_GUEST && CONFIG_KVM_GUEST */
+#endif /* !__ASSEMBLY__ */
+#endif /* _ASM_X86_TDX_H */