Merge tag 'x86_seves_for_v5.10' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 SEV-ES support from Borislav Petkov:
 "SEV-ES enhances the current guest memory encryption support called SEV
  by also encrypting the guest register state, making the registers
  inaccessible to the hypervisor by en-/decrypting them on world
  switches. Thus, it adds additional protection to Linux guests against
  exfiltration, control flow and rollback attacks.

  With SEV-ES, the guest is in full control of what registers the
  hypervisor can access. This is provided by a guest-host exchange
  mechanism based on a new exception vector called VMM Communication
  Exception (#VC), a new instruction called VMGEXIT and a shared
  Guest-Host Communication Block which is a decrypted page shared
  between the guest and the hypervisor.

  Intercepts to the hypervisor become #VC exceptions in an SEV-ES guest
  so in order for that exception mechanism to work, the early x86 init
  code needed to be made able to handle exceptions, which, in itself,
  brings a bunch of very nice cleanups and improvements to the early
  boot code like an early page fault handler, allowing for on-demand
  building of the identity mapping. With that, !KASLR configurations do
  not use the EFI page table anymore but switch to a kernel-controlled
  one.

  The main part of this series adds the support for that new exchange
  mechanism. The goal has been to keep this as much as possibly separate
  from the core x86 code by concentrating the machinery in two
  SEV-ES-specific files:

    arch/x86/kernel/sev-es-shared.c
    arch/x86/kernel/sev-es.c

  Other interaction with core x86 code has been kept at minimum and
  behind static keys to minimize the performance impact on !SEV-ES
  setups.

  Work by Joerg Roedel and Thomas Lendacky and others"

* tag 'x86_seves_for_v5.10' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (73 commits)
  x86/sev-es: Use GHCB accessor for setting the MMIO scratch buffer
  x86/sev-es: Check required CPU features for SEV-ES
  x86/efi: Add GHCB mappings when SEV-ES is active
  x86/sev-es: Handle NMI State
  x86/sev-es: Support CPU offline/online
  x86/head/64: Don't call verify_cpu() on starting APs
  x86/smpboot: Load TSS and getcpu GDT entry before loading IDT
  x86/realmode: Setup AP jump table
  x86/realmode: Add SEV-ES specific trampoline entry point
  x86/vmware: Add VMware-specific handling for VMMCALL under SEV-ES
  x86/kvm: Add KVM-specific VMMCALL handling under SEV-ES
  x86/paravirt: Allow hypervisor-specific VMMCALL handling under SEV-ES
  x86/sev-es: Handle #DB Events
  x86/sev-es: Handle #AC Events
  x86/sev-es: Handle VMMCALL Events
  x86/sev-es: Handle MWAIT/MWAITX Events
  x86/sev-es: Handle MONITOR/MONITORX Events
  x86/sev-es: Handle INVD Events
  x86/sev-es: Handle RDPMC Events
  x86/sev-es: Handle RDTSC(P) Events
  ...

24 files changed, 431 insertions, 71 deletions

diff --git a/arch/x86/include/asm/cpu_entry_area.h b/arch/x86/include/asm/cpu_entry_area.h
index 8902fdb7de13..3d52b094850a 100644
--- a/arch/x86/include/asm/cpu_entry_area.h
+++ b/arch/x86/include/asm/cpu_entry_area.h
@@ -11,25 +11,29 @@
 #ifdef CONFIG_X86_64
 
 /* Macro to enforce the same ordering and stack sizes */
-#define ESTACKS_MEMBERS(guardsize)		\
-	char	DF_stack_guard[guardsize];	\
-	char	DF_stack[EXCEPTION_STKSZ];	\
-	char	NMI_stack_guard[guardsize];	\
-	char	NMI_stack[EXCEPTION_STKSZ];	\
-	char	DB_stack_guard[guardsize];	\
-	char	DB_stack[EXCEPTION_STKSZ];	\
-	char	MCE_stack_guard[guardsize];	\
-	char	MCE_stack[EXCEPTION_STKSZ];	\
-	char	IST_top_guard[guardsize];	\
+#define ESTACKS_MEMBERS(guardsize, optional_stack_size)		\
+	char	DF_stack_guard[guardsize];			\
+	char	DF_stack[EXCEPTION_STKSZ];			\
+	char	NMI_stack_guard[guardsize];			\
+	char	NMI_stack[EXCEPTION_STKSZ];			\
+	char	DB_stack_guard[guardsize];			\
+	char	DB_stack[EXCEPTION_STKSZ];			\
+	char	MCE_stack_guard[guardsize];			\
+	char	MCE_stack[EXCEPTION_STKSZ];			\
+	char	VC_stack_guard[guardsize];			\
+	char	VC_stack[optional_stack_size];			\
+	char	VC2_stack_guard[guardsize];			\
+	char	VC2_stack[optional_stack_size];			\
+	char	IST_top_guard[guardsize];			\
 
 /* The exception stacks' physical storage. No guard pages required */
 struct exception_stacks {
-	ESTACKS_MEMBERS(0)
+	ESTACKS_MEMBERS(0, 0)
 };
 
 /* The effective cpu entry area mapping with guard pages. */
 struct cea_exception_stacks {
-	ESTACKS_MEMBERS(PAGE_SIZE)
+	ESTACKS_MEMBERS(PAGE_SIZE, EXCEPTION_STKSZ)
 };
 
 /*
@@ -40,6 +44,8 @@ enum exception_stack_ordering {
 	ESTACK_NMI,
 	ESTACK_DB,
 	ESTACK_MCE,
+	ESTACK_VC,
+	ESTACK_VC2,
 	N_EXCEPTION_STACKS
 };
 
@@ -139,4 +145,7 @@ static inline struct entry_stack *cpu_entry_stack(int cpu)
 #define __this_cpu_ist_top_va(name)					\
 	CEA_ESTACK_TOP(__this_cpu_read(cea_exception_stacks), name)
 
+#define __this_cpu_ist_bottom_va(name)					\
+	CEA_ESTACK_BOT(__this_cpu_read(cea_exception_stacks), name)
+
 #endif
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 7b0afd5e6c57..dad350d42ecf 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -236,6 +236,7 @@
 #define X86_FEATURE_EPT_AD		( 8*32+17) /* Intel Extended Page Table access-dirty bit */
 #define X86_FEATURE_VMCALL		( 8*32+18) /* "" Hypervisor supports the VMCALL instruction */
 #define X86_FEATURE_VMW_VMMCALL		( 8*32+19) /* "" VMware prefers VMMCALL hypercall instruction */
+#define X86_FEATURE_SEV_ES		( 8*32+20) /* AMD Secure Encrypted Virtualization - Encrypted State */
 
 /* 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/desc.h b/arch/x86/include/asm/desc.h
index 1ced11d31932..476082a83d1c 100644
--- a/arch/x86/include/asm/desc.h
+++ b/arch/x86/include/asm/desc.h
@@ -383,6 +383,33 @@ static inline void set_desc_limit(struct desc_struct *desc, unsigned long limit)
 
 void alloc_intr_gate(unsigned int n, const void *addr);
 
+static inline void init_idt_data(struct idt_data *data, unsigned int n,
+				 const void *addr)
+{
+	BUG_ON(n > 0xFF);
+
+	memset(data, 0, sizeof(*data));
+	data->vector	= n;
+	data->addr	= addr;
+	data->segment	= __KERNEL_CS;
+	data->bits.type	= GATE_INTERRUPT;
+	data->bits.p	= 1;
+}
+
+static inline void idt_init_desc(gate_desc *gate, const struct idt_data *d)
+{
+	unsigned long addr = (unsigned long) d->addr;
+
+	gate->offset_low	= (u16) addr;
+	gate->segment		= (u16) d->segment;
+	gate->bits		= d->bits;
+	gate->offset_middle	= (u16) (addr >> 16);
+#ifdef CONFIG_X86_64
+	gate->offset_high	= (u32) (addr >> 32);
+	gate->reserved		= 0;
+#endif
+}
+
 extern unsigned long system_vectors[];
 
 extern void load_current_idt(void);
diff --git a/arch/x86/include/asm/desc_defs.h b/arch/x86/include/asm/desc_defs.h
index a91f3b6e4f2a..f7e7099af595 100644
--- a/arch/x86/include/asm/desc_defs.h
+++ b/arch/x86/include/asm/desc_defs.h
@@ -74,6 +74,13 @@ struct idt_bits {
 			p	: 1;
 } __attribute__((packed));
 
+struct idt_data {
+	unsigned int	vector;
+	unsigned int	segment;
+	struct idt_bits	bits;
+	const void	*addr;
+};
+
 struct gate_struct {
 	u16		offset_low;
 	u16		segment;
@@ -109,6 +116,9 @@ struct desc_ptr {
 
 #endif /* !__ASSEMBLY__ */
 
+/* Boot IDT definitions */
+#define	BOOT_IDT_ENTRIES	32
+
 /* Access rights as returned by LAR */
 #define AR_TYPE_RODATA		(0 * (1 << 9))
 #define AR_TYPE_RWDATA		(1 * (1 << 9))
diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h
index eb1ed3bd8d96..8d33ad80704f 100644
--- a/arch/x86/include/asm/fpu/internal.h
+++ b/arch/x86/include/asm/fpu/internal.h
@@ -19,6 +19,7 @@
 #include <asm/user.h>
 #include <asm/fpu/api.h>
 #include <asm/fpu/xstate.h>
+#include <asm/fpu/xcr.h>
 #include <asm/cpufeature.h>
 #include <asm/trace/fpu.h>
 
@@ -592,33 +593,4 @@ static inline void switch_fpu_finish(struct fpu *new_fpu)
 	update_pasid();
 }
 
-/*
- * MXCSR and XCR definitions:
- */
-
-static inline void ldmxcsr(u32 mxcsr)
-{
-	asm volatile("ldmxcsr %0" :: "m" (mxcsr));
-}
-
-extern unsigned int mxcsr_feature_mask;
-
-#define XCR_XFEATURE_ENABLED_MASK	0x00000000
-
-static inline u64 xgetbv(u32 index)
-{
-	u32 eax, edx;
-
-	asm volatile("xgetbv" : "=a" (eax), "=d" (edx) : "c" (index));
-	return eax + ((u64)edx << 32);
-}
-
-static inline void xsetbv(u32 index, u64 value)
-{
-	u32 eax = value;
-	u32 edx = value >> 32;
-
-	asm volatile("xsetbv" :: "a" (eax), "d" (edx), "c" (index));
-}
-
 #endif /* _ASM_X86_FPU_INTERNAL_H */
diff --git a/arch/x86/include/asm/fpu/xcr.h b/arch/x86/include/asm/fpu/xcr.h
new file mode 100644
index 000000000000..1c7ab8d95da5
--- /dev/null
+++ b/arch/x86/include/asm/fpu/xcr.h
@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_X86_FPU_XCR_H
+#define _ASM_X86_FPU_XCR_H
+
+/*
+ * MXCSR and XCR definitions:
+ */
+
+static inline void ldmxcsr(u32 mxcsr)
+{
+	asm volatile("ldmxcsr %0" :: "m" (mxcsr));
+}
+
+extern unsigned int mxcsr_feature_mask;
+
+#define XCR_XFEATURE_ENABLED_MASK	0x00000000
+
+static inline u64 xgetbv(u32 index)
+{
+	u32 eax, edx;
+
+	asm volatile("xgetbv" : "=a" (eax), "=d" (edx) : "c" (index));
+	return eax + ((u64)edx << 32);
+}
+
+static inline void xsetbv(u32 index, u64 value)
+{
+	u32 eax = value;
+	u32 edx = value >> 32;
+
+	asm volatile("xsetbv" :: "a" (eax), "d" (edx), "c" (index));
+}
+
+#endif /* _ASM_X86_FPU_XCR_H */
diff --git a/arch/x86/include/asm/idtentry.h b/arch/x86/include/asm/idtentry.h
index cdd41d039cd1..b2442eb0ac2f 100644
--- a/arch/x86/include/asm/idtentry.h
+++ b/arch/x86/include/asm/idtentry.h
@@ -309,6 +309,19 @@ static __always_inline void __##func(struct pt_regs *regs)
 	__visible void noist_##func(struct pt_regs *regs)
 
 /**
+ * DECLARE_IDTENTRY_VC - Declare functions for the VC entry point
+ * @vector:	Vector number (ignored for C)
+ * @func:	Function name of the entry point
+ *
+ * Maps to DECLARE_IDTENTRY_RAW_ERRORCODE, but declares also the
+ * safe_stack C handler.
+ */
+#define DECLARE_IDTENTRY_VC(vector, func)				\
+	DECLARE_IDTENTRY_RAW_ERRORCODE(vector, func);			\
+	__visible noinstr void ist_##func(struct pt_regs *regs, unsigned long error_code);	\
+	__visible noinstr void safe_stack_##func(struct pt_regs *regs, unsigned long error_code)
+
+/**
  * DEFINE_IDTENTRY_IST - Emit code for IST entry points
  * @func:	Function name of the entry point
  *
@@ -347,6 +360,35 @@ static __always_inline void __##func(struct pt_regs *regs)
 #define DEFINE_IDTENTRY_DF(func)					\
 	DEFINE_IDTENTRY_RAW_ERRORCODE(func)
 
+/**
+ * DEFINE_IDTENTRY_VC_SAFE_STACK - Emit code for VMM communication handler
+				   which runs on a safe stack.
+ * @func:	Function name of the entry point
+ *
+ * Maps to DEFINE_IDTENTRY_RAW_ERRORCODE
+ */
+#define DEFINE_IDTENTRY_VC_SAFE_STACK(func)				\
+	DEFINE_IDTENTRY_RAW_ERRORCODE(safe_stack_##func)
+
+/**
+ * DEFINE_IDTENTRY_VC_IST - Emit code for VMM communication handler
+			    which runs on the VC fall-back stack
+ * @func:	Function name of the entry point
+ *
+ * Maps to DEFINE_IDTENTRY_RAW_ERRORCODE
+ */
+#define DEFINE_IDTENTRY_VC_IST(func)				\
+	DEFINE_IDTENTRY_RAW_ERRORCODE(ist_##func)
+
+/**
+ * DEFINE_IDTENTRY_VC - Emit code for VMM communication handler
+ * @func:	Function name of the entry point
+ *
+ * Maps to DEFINE_IDTENTRY_RAW_ERRORCODE
+ */
+#define DEFINE_IDTENTRY_VC(func)					\
+	DEFINE_IDTENTRY_RAW_ERRORCODE(func)
+
 #else	/* CONFIG_X86_64 */
 
 /**
@@ -433,6 +475,9 @@ __visible noinstr void func(struct pt_regs *regs,			\
 # define DECLARE_IDTENTRY_XENCB(vector, func)				\
 	DECLARE_IDTENTRY(vector, func)
 
+# define DECLARE_IDTENTRY_VC(vector, func)				\
+	idtentry_vc vector asm_##func func
+
 #else
 # define DECLARE_IDTENTRY_MCE(vector, func)				\
 	DECLARE_IDTENTRY(vector, func)
@@ -564,6 +609,11 @@ DECLARE_IDTENTRY_RAW(X86_TRAP_DB,	xenpv_exc_debug);
 /* #DF */
 DECLARE_IDTENTRY_DF(X86_TRAP_DF,	exc_double_fault);
 
+/* #VC */
+#ifdef CONFIG_AMD_MEM_ENCRYPT
+DECLARE_IDTENTRY_VC(X86_TRAP_VC,	exc_vmm_communication);
+#endif
+
 #ifdef CONFIG_XEN_PV
 DECLARE_IDTENTRY_XENCB(X86_TRAP_OTHER,	exc_xen_hypervisor_callback);
 #endif
diff --git a/arch/x86/include/asm/insn-eval.h b/arch/x86/include/asm/insn-eval.h
index 2b6ccf2c49f1..a0f839aa144d 100644
--- a/arch/x86/include/asm/insn-eval.h
+++ b/arch/x86/include/asm/insn-eval.h
@@ -15,9 +15,15 @@
 #define INSN_CODE_SEG_OPND_SZ(params) (params & 0xf)
 #define INSN_CODE_SEG_PARAMS(oper_sz, addr_sz) (oper_sz | (addr_sz << 4))
 
+bool insn_has_rep_prefix(struct insn *insn);
 void __user *insn_get_addr_ref(struct insn *insn, struct pt_regs *regs);
 int insn_get_modrm_rm_off(struct insn *insn, struct pt_regs *regs);
+int insn_get_modrm_reg_off(struct insn *insn, struct pt_regs *regs);
 unsigned long insn_get_seg_base(struct pt_regs *regs, int seg_reg_idx);
 int insn_get_code_seg_params(struct pt_regs *regs);
+int insn_fetch_from_user(struct pt_regs *regs,
+			 unsigned char buf[MAX_INSN_SIZE]);
+bool insn_decode(struct insn *insn, struct pt_regs *regs,
+		 unsigned char buf[MAX_INSN_SIZE], int buf_size);
 
 #endif /* _ASM_X86_INSN_EVAL_H */
diff --git a/arch/x86/include/asm/mem_encrypt.h b/arch/x86/include/asm/mem_encrypt.h
index 5049f6c22683..c9f5df0a1c10 100644
--- a/arch/x86/include/asm/mem_encrypt.h
+++ b/arch/x86/include/asm/mem_encrypt.h
@@ -19,6 +19,7 @@
 #ifdef CONFIG_AMD_MEM_ENCRYPT
 
 extern u64 sme_me_mask;
+extern u64 sev_status;
 extern bool sev_enabled;
 
 void sme_encrypt_execute(unsigned long encrypted_kernel_vaddr,
@@ -48,8 +49,10 @@ 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);
 bool sme_active(void);
 bool sev_active(void);
+bool sev_es_active(void);
 
 #define __bss_decrypted __attribute__((__section__(".bss..decrypted")))
 
@@ -70,8 +73,10 @@ static inline void __init sme_early_init(void) { }
 static inline void __init sme_encrypt_kernel(struct boot_params *bp) { }
 static inline void __init sme_enable(struct boot_params *bp) { }
 
+static inline void sev_es_init_vc_handling(void) { }
 static inline bool sme_active(void) { return false; }
 static inline bool sev_active(void) { return false; }
+static inline bool sev_es_active(void) { return false; }
 
 static inline int __init
 early_set_memory_decrypted(unsigned long vaddr, unsigned long size) { return 0; }
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index c07a70ce7ffd..972a34d93505 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -470,9 +470,12 @@
 #define MSR_AMD64_ICIBSEXTDCTL		0xc001103c
 #define MSR_AMD64_IBSOPDATA4		0xc001103d
 #define MSR_AMD64_IBS_REG_COUNT_MAX	8 /* includes MSR_AMD64_IBSBRTARGET */
+#define MSR_AMD64_SEV_ES_GHCB		0xc0010130
 #define MSR_AMD64_SEV			0xc0010131
 #define MSR_AMD64_SEV_ENABLED_BIT	0
+#define MSR_AMD64_SEV_ES_ENABLED_BIT	1
 #define MSR_AMD64_SEV_ENABLED		BIT_ULL(MSR_AMD64_SEV_ENABLED_BIT)
+#define MSR_AMD64_SEV_ES_ENABLED	BIT_ULL(MSR_AMD64_SEV_ES_ENABLED_BIT)
 
 #define MSR_AMD64_VIRT_SPEC_CTRL	0xc001011f
 
diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h
index 288b065955b7..d0c6c10c18a0 100644
--- a/arch/x86/include/asm/page_64_types.h
+++ b/arch/x86/include/asm/page_64_types.h
@@ -28,6 +28,7 @@
 #define	IST_INDEX_NMI		1
 #define	IST_INDEX_DB		2
 #define	IST_INDEX_MCE		3
+#define	IST_INDEX_VC		4
 
 /*
  * Set __PAGE_OFFSET to the most negative possible address +
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 5e0dcc20614d..a02c67291cfc 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -28,7 +28,7 @@
 #include <asm-generic/pgtable_uffd.h>
 
 extern pgd_t early_top_pgt[PTRS_PER_PGD];
-int __init __early_make_pgtable(unsigned long address, pmdval_t pmd);
+bool __init __early_make_pgtable(unsigned long address, pmdval_t pmd);
 
 void ptdump_walk_pgd_level(struct seq_file *m, struct mm_struct *mm);
 void ptdump_walk_pgd_level_debugfs(struct seq_file *m, struct mm_struct *mm,
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index d8a82e650810..5ac507586769 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -696,6 +696,7 @@ extern void load_direct_gdt(int);
 extern void load_fixmap_gdt(int);
 extern void load_percpu_segment(int);
 extern void cpu_init(void);
+extern void cpu_init_exception_handling(void);
 extern void cr4_init(void);
 
 static inline unsigned long get_debugctlmsr(void)
diff --git a/arch/x86/include/asm/proto.h b/arch/x86/include/asm/proto.h
index 28996fe19301..2c35f1c01a2d 100644
--- a/arch/x86/include/asm/proto.h
+++ b/arch/x86/include/asm/proto.h
@@ -10,6 +10,7 @@ void syscall_init(void);
 
 #ifdef CONFIG_X86_64
 void entry_SYSCALL_64(void);
+void entry_SYSCALL_64_safe_stack(void);
 long do_arch_prctl_64(struct task_struct *task, int option, unsigned long arg2);
 #endif
 
diff --git a/arch/x86/include/asm/realmode.h b/arch/x86/include/asm/realmode.h
index b35030eeec36..5db5d083c873 100644
--- a/arch/x86/include/asm/realmode.h
+++ b/arch/x86/include/asm/realmode.h
@@ -21,6 +21,9 @@ struct real_mode_header {
 	/* SMP trampoline */
 	u32	trampoline_start;
 	u32	trampoline_header;
+#ifdef CONFIG_AMD_MEM_ENCRYPT
+	u32	sev_es_trampoline_start;
+#endif
 #ifdef CONFIG_X86_64
 	u32	trampoline_pgd;
 #endif
@@ -57,6 +60,9 @@ extern unsigned char real_mode_blob_end[];
 extern unsigned long initial_code;
 extern unsigned long initial_gs;
 extern unsigned long initial_stack;
+#ifdef CONFIG_AMD_MEM_ENCRYPT
+extern unsigned long initial_vc_handler;
+#endif
 
 extern unsigned char real_mode_blob[];
 extern unsigned char real_mode_relocs[];
@@ -66,6 +72,7 @@ extern unsigned char startup_32_smp[];
 extern unsigned char boot_gdt[];
 #else
 extern unsigned char secondary_startup_64[];
+extern unsigned char secondary_startup_64_no_verify[];
 #endif
 
 static inline size_t real_mode_size_needed(void)
diff --git a/arch/x86/include/asm/segment.h b/arch/x86/include/asm/segment.h
index 517920928989..7fdd4facfce7 100644
--- a/arch/x86/include/asm/segment.h
+++ b/arch/x86/include/asm/segment.h
@@ -226,7 +226,7 @@
 #define NUM_EXCEPTION_VECTORS		32
 
 /* Bitmask of exception vectors which push an error code on the stack: */
-#define EXCEPTION_ERRCODE_MASK		0x00027d00
+#define EXCEPTION_ERRCODE_MASK		0x20027d00
 
 #define GDT_SIZE			(GDT_ENTRIES*8)
 #define GDT_ENTRY_TLS_ENTRIES		3
diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h
index 84b645cc8bc9..7d7a064af6ff 100644
--- a/arch/x86/include/asm/setup.h
+++ b/arch/x86/include/asm/setup.h
@@ -39,6 +39,8 @@ void vsmp_init(void);
 static inline void vsmp_init(void) { }
 #endif
 
+struct pt_regs;
+
 void setup_bios_corruption_check(void);
 void early_platform_quirks(void);
 
@@ -48,7 +50,9 @@ extern void reserve_standard_io_resources(void);
 extern void i386_reserve_resources(void);
 extern unsigned long __startup_64(unsigned long physaddr, struct boot_params *bp);
 extern unsigned long __startup_secondary_64(void);
-extern int early_make_pgtable(unsigned long address);
+extern void startup_64_setup_env(unsigned long physbase);
+extern void early_setup_idt(void);
+extern void __init do_early_exception(struct pt_regs *regs, int trapnr);
 
 #ifdef CONFIG_X86_INTEL_MID
 extern void x86_intel_mid_early_setup(void);
diff --git a/arch/x86/include/asm/sev-es.h b/arch/x86/include/asm/sev-es.h
new file mode 100644
index 000000000000..cf1d957c7091
--- /dev/null
+++ b/arch/x86/include/asm/sev-es.h
@@ -0,0 +1,114 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * AMD Encrypted Register State Support
+ *
+ * Author: Joerg Roedel <jroedel@suse.de>
+ */
+
+#ifndef __ASM_ENCRYPTED_STATE_H
+#define __ASM_ENCRYPTED_STATE_H
+
+#include <linux/types.h>
+#include <asm/insn.h>
+
+#define GHCB_SEV_INFO		0x001UL
+#define GHCB_SEV_INFO_REQ	0x002UL
+#define		GHCB_INFO(v)		((v) & 0xfffUL)
+#define		GHCB_PROTO_MAX(v)	(((v) >> 48) & 0xffffUL)
+#define		GHCB_PROTO_MIN(v)	(((v) >> 32) & 0xffffUL)
+#define		GHCB_PROTO_OUR		0x0001UL
+#define GHCB_SEV_CPUID_REQ	0x004UL
+#define		GHCB_CPUID_REQ_EAX	0
+#define		GHCB_CPUID_REQ_EBX	1
+#define		GHCB_CPUID_REQ_ECX	2
+#define		GHCB_CPUID_REQ_EDX	3
+#define		GHCB_CPUID_REQ(fn, reg) (GHCB_SEV_CPUID_REQ | \
+					(((unsigned long)reg & 3) << 30) | \
+					(((unsigned long)fn) << 32))
+
+#define	GHCB_PROTOCOL_MAX	0x0001UL
+#define GHCB_DEFAULT_USAGE	0x0000UL
+
+#define GHCB_SEV_CPUID_RESP	0x005UL
+#define GHCB_SEV_TERMINATE	0x100UL
+#define		GHCB_SEV_TERMINATE_REASON(reason_set, reason_val)	\
+			(((((u64)reason_set) &  0x7) << 12) |		\
+			 ((((u64)reason_val) & 0xff) << 16))
+#define		GHCB_SEV_ES_REASON_GENERAL_REQUEST	0
+#define		GHCB_SEV_ES_REASON_PROTOCOL_UNSUPPORTED	1
+
+#define	GHCB_SEV_GHCB_RESP_CODE(v)	((v) & 0xfff)
+#define	VMGEXIT()			{ asm volatile("rep; vmmcall\n\r"); }
+
+enum es_result {
+	ES_OK,			/* All good */
+	ES_UNSUPPORTED,		/* Requested operation not supported */
+	ES_VMM_ERROR,		/* Unexpected state from the VMM */
+	ES_DECODE_FAILED,	/* Instruction decoding failed */
+	ES_EXCEPTION,		/* Instruction caused exception */
+	ES_RETRY,		/* Retry instruction emulation */
+};
+
+struct es_fault_info {
+	unsigned long vector;
+	unsigned long error_code;
+	unsigned long cr2;
+};
+
+struct pt_regs;
+
+/* ES instruction emulation context */
+struct es_em_ctxt {
+	struct pt_regs *regs;
+	struct insn insn;
+	struct es_fault_info fi;
+};
+
+void do_vc_no_ghcb(struct pt_regs *regs, unsigned long exit_code);
+
+static inline u64 lower_bits(u64 val, unsigned int bits)
+{
+	u64 mask = (1ULL << bits) - 1;
+
+	return (val & mask);
+}
+
+struct real_mode_header;
+enum stack_type;
+
+/* Early IDT entry points for #VC handler */
+extern void vc_no_ghcb(void);
+extern void vc_boot_ghcb(void);
+extern bool handle_vc_boot_ghcb(struct pt_regs *regs);
+
+#ifdef CONFIG_AMD_MEM_ENCRYPT
+extern struct static_key_false sev_es_enable_key;
+extern void __sev_es_ist_enter(struct pt_regs *regs);
+extern void __sev_es_ist_exit(void);
+static __always_inline void sev_es_ist_enter(struct pt_regs *regs)
+{
+	if (static_branch_unlikely(&sev_es_enable_key))
+		__sev_es_ist_enter(regs);
+}
+static __always_inline void sev_es_ist_exit(void)
+{
+	if (static_branch_unlikely(&sev_es_enable_key))
+		__sev_es_ist_exit();
+}
+extern int sev_es_setup_ap_jump_table(struct real_mode_header *rmh);
+extern void __sev_es_nmi_complete(void);
+static __always_inline void sev_es_nmi_complete(void)
+{
+	if (static_branch_unlikely(&sev_es_enable_key))
+		__sev_es_nmi_complete();
+}
+extern int __init sev_es_efi_map_ghcbs(pgd_t *pgd);
+#else
+static inline void sev_es_ist_enter(struct pt_regs *regs) { }
+static inline void sev_es_ist_exit(void) { }
+static inline int sev_es_setup_ap_jump_table(struct real_mode_header *rmh) { return 0; }
+static inline void sev_es_nmi_complete(void) { }
+static inline int sev_es_efi_map_ghcbs(pgd_t *pgd) { return 0; }
+#endif
+
+#endif
diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h
index 5ae5a68e469d..49600643faba 100644
--- a/arch/x86/include/asm/stacktrace.h
+++ b/arch/x86/include/asm/stacktrace.h
@@ -35,6 +35,8 @@ bool in_entry_stack(unsigned long *stack, struct stack_info *info);
 
 int get_stack_info(unsigned long *stack, struct task_struct *task,
 		   struct stack_info *info, unsigned long *visit_mask);
+bool get_stack_info_noinstr(unsigned long *stack, struct task_struct *task,
+			    struct stack_info *info);
 
 const char *stack_type_name(enum stack_type type);
 
diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h
index 8a1f5382a4ea..cf13f9e78585 100644
--- a/arch/x86/include/asm/svm.h
+++ b/arch/x86/include/asm/svm.h
@@ -150,14 +150,14 @@ struct __attribute__ ((__packed__)) vmcb_control_area {
 #define SVM_NESTED_CTL_NP_ENABLE	BIT(0)
 #define SVM_NESTED_CTL_SEV_ENABLE	BIT(1)
 
-struct __attribute__ ((__packed__)) vmcb_seg {
+struct vmcb_seg {
 	u16 selector;
 	u16 attrib;
 	u32 limit;
 	u64 base;
-};
+} __packed;
 
-struct __attribute__ ((__packed__)) vmcb_save_area {
+struct vmcb_save_area {
 	struct vmcb_seg es;
 	struct vmcb_seg cs;
 	struct vmcb_seg ss;
@@ -200,20 +200,67 @@ struct __attribute__ ((__packed__)) vmcb_save_area {
 	u64 br_to;
 	u64 last_excp_from;
 	u64 last_excp_to;
-};
 
+	/*
+	 * The following part of the save area is valid only for
+	 * SEV-ES guests when referenced through the GHCB.
+	 */
+	u8 reserved_7[104];
+	u64 reserved_8;		/* rax already available at 0x01f8 */
+	u64 rcx;
+	u64 rdx;
+	u64 rbx;
+	u64 reserved_9;		/* rsp already available at 0x01d8 */
+	u64 rbp;
+	u64 rsi;
+	u64 rdi;
+	u64 r8;
+	u64 r9;
+	u64 r10;
+	u64 r11;
+	u64 r12;
+	u64 r13;
+	u64 r14;
+	u64 r15;
+	u8 reserved_10[16];
+	u64 sw_exit_code;
+	u64 sw_exit_info_1;
+	u64 sw_exit_info_2;
+	u64 sw_scratch;
+	u8 reserved_11[56];
+	u64 xcr0;
+	u8 valid_bitmap[16];
+	u64 x87_state_gpa;
+} __packed;
+
+struct ghcb {
+	struct vmcb_save_area save;
+	u8 reserved_save[2048 - sizeof(struct vmcb_save_area)];
+
+	u8 shared_buffer[2032];
+
+	u8 reserved_1[10];
+	u16 protocol_version;	/* negotiated SEV-ES/GHCB protocol version */
+	u32 ghcb_usage;
+} __packed;
+
+
+#define EXPECTED_VMCB_SAVE_AREA_SIZE		1032
+#define EXPECTED_VMCB_CONTROL_AREA_SIZE		256
+#define EXPECTED_GHCB_SIZE			PAGE_SIZE
 
 static inline void __unused_size_checks(void)
 {
-	BUILD_BUG_ON(sizeof(struct vmcb_save_area) != 0x298);
-	BUILD_BUG_ON(sizeof(struct vmcb_control_area) != 256);
+	BUILD_BUG_ON(sizeof(struct vmcb_save_area)	!= EXPECTED_VMCB_SAVE_AREA_SIZE);
+	BUILD_BUG_ON(sizeof(struct vmcb_control_area)	!= EXPECTED_VMCB_CONTROL_AREA_SIZE);
+	BUILD_BUG_ON(sizeof(struct ghcb)		!= EXPECTED_GHCB_SIZE);
 }
 
-struct __attribute__ ((__packed__)) vmcb {
+struct vmcb {
 	struct vmcb_control_area control;
 	u8 reserved_control[1024 - sizeof(struct vmcb_control_area)];
 	struct vmcb_save_area save;
-};
+} __packed;
 
 #define SVM_CPUID_FUNC 0x8000000a
 
@@ -298,4 +345,47 @@ struct __attribute__ ((__packed__)) vmcb {
 
 #define SVM_CR0_SELECTIVE_MASK (X86_CR0_TS | X86_CR0_MP)
 
+/* GHCB Accessor functions */
+
+#define GHCB_BITMAP_IDX(field)							\
+	(offsetof(struct vmcb_save_area, field) / sizeof(u64))
+
+#define DEFINE_GHCB_ACCESSORS(field)						\
+	static inline bool ghcb_##field##_is_valid(const struct ghcb *ghcb)	\
+	{									\
+		return test_bit(GHCB_BITMAP_IDX(field),				\
+				(unsigned long *)&ghcb->save.valid_bitmap);	\
+	}									\
+										\
+	static inline void ghcb_set_##field(struct ghcb *ghcb, u64 value)	\
+	{									\
+		__set_bit(GHCB_BITMAP_IDX(field),				\
+			  (unsigned long *)&ghcb->save.valid_bitmap);		\
+		ghcb->save.field = value;					\
+	}
+
+DEFINE_GHCB_ACCESSORS(cpl)
+DEFINE_GHCB_ACCESSORS(rip)
+DEFINE_GHCB_ACCESSORS(rsp)
+DEFINE_GHCB_ACCESSORS(rax)
+DEFINE_GHCB_ACCESSORS(rcx)
+DEFINE_GHCB_ACCESSORS(rdx)
+DEFINE_GHCB_ACCESSORS(rbx)
+DEFINE_GHCB_ACCESSORS(rbp)
+DEFINE_GHCB_ACCESSORS(rsi)
+DEFINE_GHCB_ACCESSORS(rdi)
+DEFINE_GHCB_ACCESSORS(r8)
+DEFINE_GHCB_ACCESSORS(r9)
+DEFINE_GHCB_ACCESSORS(r10)
+DEFINE_GHCB_ACCESSORS(r11)
+DEFINE_GHCB_ACCESSORS(r12)
+DEFINE_GHCB_ACCESSORS(r13)
+DEFINE_GHCB_ACCESSORS(r14)
+DEFINE_GHCB_ACCESSORS(r15)
+DEFINE_GHCB_ACCESSORS(sw_exit_code)
+DEFINE_GHCB_ACCESSORS(sw_exit_info_1)
+DEFINE_GHCB_ACCESSORS(sw_exit_info_2)
+DEFINE_GHCB_ACCESSORS(sw_scratch)
+DEFINE_GHCB_ACCESSORS(xcr0)
+
 #endif
diff --git a/arch/x86/include/asm/trap_pf.h b/arch/x86/include/asm/trap_pf.h
new file mode 100644
index 000000000000..305bc1214aef
--- /dev/null
+++ b/arch/x86/include/asm/trap_pf.h
@@ -0,0 +1,24 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_X86_TRAP_PF_H
+#define _ASM_X86_TRAP_PF_H
+
+/*
+ * Page fault error code bits:
+ *
+ *   bit 0 ==	 0: no page found	1: protection fault
+ *   bit 1 ==	 0: read access		1: write access
+ *   bit 2 ==	 0: kernel-mode access	1: user-mode access
+ *   bit 3 ==				1: use of reserved bit detected
+ *   bit 4 ==				1: fault was an instruction fetch
+ *   bit 5 ==				1: protection keys block access
+ */
+enum x86_pf_error_code {
+	X86_PF_PROT	=		1 << 0,
+	X86_PF_WRITE	=		1 << 1,
+	X86_PF_USER	=		1 << 2,
+	X86_PF_RSVD	=		1 << 3,
+	X86_PF_INSTR	=		1 << 4,
+	X86_PF_PK	=		1 << 5,
+};
+
+#endif /* _ASM_X86_TRAP_PF_H */
diff --git a/arch/x86/include/asm/trapnr.h b/arch/x86/include/asm/trapnr.h
index 082f45631fa9..f5d2325aa0b7 100644
--- a/arch/x86/include/asm/trapnr.h
+++ b/arch/x86/include/asm/trapnr.h
@@ -26,6 +26,7 @@
 #define X86_TRAP_XF		19	/* SIMD Floating-Point Exception */
 #define X86_TRAP_VE		20	/* Virtualization Exception */
 #define X86_TRAP_CP		21	/* Control Protection Exception */
+#define X86_TRAP_VC		29	/* VMM Communication Exception */
 #define X86_TRAP_IRET		32	/* IRET Exception */
 
 #endif
diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h
index df0b7bfc1234..7f7200021bd1 100644
--- a/arch/x86/include/asm/traps.h
+++ b/arch/x86/include/asm/traps.h
@@ -8,12 +8,14 @@
 #include <asm/debugreg.h>
 #include <asm/idtentry.h>
 #include <asm/siginfo.h>			/* TRAP_TRACE, ... */
+#include <asm/trap_pf.h>
 
 #ifdef CONFIG_X86_64
 asmlinkage __visible notrace struct pt_regs *sync_regs(struct pt_regs *eregs);
 asmlinkage __visible notrace
 struct bad_iret_stack *fixup_bad_iret(struct bad_iret_stack *s);
 void __init trap_init(void);
+asmlinkage __visible noinstr struct pt_regs *vc_switch_off_ist(struct pt_regs *eregs);
 #endif
 
 #ifdef CONFIG_X86_F00F_BUG
@@ -43,22 +45,4 @@ void __noreturn handle_stack_overflow(const char *message,
 				      unsigned long fault_address);
 #endif
 
-/*
- * Page fault error code bits:
- *
- *   bit 0 ==	 0: no page found	1: protection fault
- *   bit 1 ==	 0: read access		1: write access
- *   bit 2 ==	 0: kernel-mode access	1: user-mode access
- *   bit 3 ==				1: use of reserved bit detected
- *   bit 4 ==				1: fault was an instruction fetch
- *   bit 5 ==				1: protection keys block access
- */
-enum x86_pf_error_code {
-	X86_PF_PROT	=		1 << 0,
-	X86_PF_WRITE	=		1 << 1,
-	X86_PF_USER	=		1 << 2,
-	X86_PF_RSVD	=		1 << 3,
-	X86_PF_INSTR	=		1 << 4,
-	X86_PF_PK	=		1 << 5,
-};
 #endif /* _ASM_X86_TRAPS_H */
diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h
index 397196fae24d..dde5b3f1e7cd 100644
--- a/arch/x86/include/asm/x86_init.h
+++ b/arch/x86/include/asm/x86_init.h
@@ -4,8 +4,10 @@
 
 #include <asm/bootparam.h>
 
+struct ghcb;
 struct mpc_bus;
 struct mpc_cpu;
+struct pt_regs;
 struct mpc_table;
 struct cpuinfo_x86;
 struct irq_domain;
@@ -229,10 +231,22 @@ struct x86_legacy_features {
 /**
  * struct x86_hyper_runtime - x86 hypervisor specific runtime callbacks
  *
- * @pin_vcpu:		pin current vcpu to specified physical cpu (run rarely)
+ * @pin_vcpu:			pin current vcpu to specified physical
+ *				cpu (run rarely)
+ * @sev_es_hcall_prepare:	Load additional hypervisor-specific
+ *				state into the GHCB when doing a VMMCALL under
+ *				SEV-ES. Called from the #VC exception handler.
+ * @sev_es_hcall_finish:	Copies state from the GHCB back into the
+ *				processor (or pt_regs). Also runs checks on the
+ *				state returned from the hypervisor after a
+ *				VMMCALL under SEV-ES.  Needs to return 'false'
+ *				if the checks fail.  Called from the #VC
+ *				exception handler.
  */
 struct x86_hyper_runtime {
 	void (*pin_vcpu)(int cpu);
+	void (*sev_es_hcall_prepare)(struct ghcb *ghcb, struct pt_regs *regs);
+	bool (*sev_es_hcall_finish)(struct ghcb *ghcb, struct pt_regs *regs);
 };
 
 /**