Merge branch 'x86/boot' into x86/core, to merge dependent commits

Prepare to resolve conflicts with an upstream series of fixes that conflict
with pending x86 changes:

  6f5bf947bab0 Merge tag 'its-for-linus-20250509' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Signed-off-by: Ingo Molnar <mingo@kernel.org>

54 files changed, 3070 insertions, 2848 deletions

diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 594723005d95..53daf4654f6c 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -281,6 +281,7 @@ archprepare: $(cpufeaturemasks.hdr)
 ###
 # Kernel objects
 
+core-y  += arch/x86/boot/startup/
 libs-y  += arch/x86/lib/
 
 # drivers-y are linked after core-y
diff --git a/arch/x86/boot/bioscall.S b/arch/x86/boot/bioscall.S
index aa9b96457584..cf4a6155714e 100644
--- a/arch/x86/boot/bioscall.S
+++ b/arch/x86/boot/bioscall.S
@@ -32,7 +32,7 @@ intcall:
 	movw	%dx, %si
 	movw	%sp, %di
 	movw	$11, %cx
-	rep; movsl
+	rep movsl
 
 	/* Pop full state from the stack */
 	popal
@@ -67,7 +67,7 @@ intcall:
 	jz	4f
 	movw	%sp, %si
 	movw	$11, %cx
-	rep; movsl
+	rep movsl
 4:	addw	$44, %sp
 
 	/* Restore state and return */
diff --git a/arch/x86/boot/boot.h b/arch/x86/boot/boot.h
index f899717f9e48..60580836daf7 100644
--- a/arch/x86/boot/boot.h
+++ b/arch/x86/boot/boot.h
@@ -155,14 +155,14 @@ static inline void wrgs32(u32 v, addr_t addr)
 static inline bool memcmp_fs(const void *s1, addr_t s2, size_t len)
 {
 	bool diff;
-	asm volatile("fs; repe; cmpsb" CC_SET(nz)
+	asm volatile("fs repe cmpsb" CC_SET(nz)
 		     : CC_OUT(nz) (diff), "+D" (s1), "+S" (s2), "+c" (len));
 	return diff;
 }
 static inline bool memcmp_gs(const void *s1, addr_t s2, size_t len)
 {
 	bool diff;
-	asm volatile("gs; repe; cmpsb" CC_SET(nz)
+	asm volatile("gs repe cmpsb" CC_SET(nz)
 		     : CC_OUT(nz) (diff), "+D" (s1), "+S" (s2), "+c" (len));
 	return diff;
 }
diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index fdbce022db55..f4f7b22d8113 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -44,10 +44,10 @@ KBUILD_CFLAGS += -D__DISABLE_EXPORTS
 KBUILD_CFLAGS += $(call cc-option,-Wa$(comma)-mrelax-relocations=no)
 KBUILD_CFLAGS += -include $(srctree)/include/linux/hidden.h
 
-# sev.c indirectly includes inat-table.h which is generated during
+# sev-decode-insn.c indirectly includes inat-table.c which is generated during
 # compilation and stored in $(objtree). Add the directory to the includes so
 # that the compiler finds it even with out-of-tree builds (make O=/some/path).
-CFLAGS_sev.o += -I$(objtree)/arch/x86/lib/
+CFLAGS_sev-handle-vc.o += -I$(objtree)/arch/x86/lib/
 
 KBUILD_AFLAGS  := $(KBUILD_CFLAGS) -D__ASSEMBLY__
 
@@ -73,7 +73,7 @@ LDFLAGS_vmlinux += -T
 hostprogs	:= mkpiggy
 HOST_EXTRACFLAGS += -I$(srctree)/tools/include
 
-sed-voffset := -e 's/^\([0-9a-fA-F]*\) [ABCDGRSTVW] \(_text\|__start_rodata\|__bss_start\|_end\)$$/\#define VO_\2 _AC(0x\1,UL)/p'
+sed-voffset := -e 's/^\([0-9a-fA-F]*\) [ABbCDGRSTtVW] \(_text\|__start_rodata\|__bss_start\|_end\)$$/\#define VO_\2 _AC(0x\1,UL)/p'
 
 quiet_cmd_voffset = VOFFSET $@
       cmd_voffset = $(NM) $< | sed -n $(sed-voffset) > $@
@@ -96,8 +96,7 @@ ifdef CONFIG_X86_64
 	vmlinux-objs-y += $(obj)/idt_64.o $(obj)/idt_handlers_64.o
 	vmlinux-objs-$(CONFIG_AMD_MEM_ENCRYPT) += $(obj)/mem_encrypt.o
 	vmlinux-objs-y += $(obj)/pgtable_64.o
-	vmlinux-objs-$(CONFIG_AMD_MEM_ENCRYPT) += $(obj)/sev.o
-	vmlinux-objs-y += $(obj)/la57toggle.o
+	vmlinux-objs-$(CONFIG_AMD_MEM_ENCRYPT) += $(obj)/sev.o $(obj)/sev-handle-vc.o
 endif
 
 vmlinux-objs-$(CONFIG_ACPI) += $(obj)/acpi.o
@@ -106,6 +105,7 @@ vmlinux-objs-$(CONFIG_UNACCEPTED_MEMORY) += $(obj)/mem.o
 
 vmlinux-objs-$(CONFIG_EFI) += $(obj)/efi.o
 vmlinux-libs-$(CONFIG_EFI_STUB) += $(objtree)/drivers/firmware/efi/libstub/lib.a
+vmlinux-libs-$(CONFIG_X86_64)	+= $(objtree)/arch/x86/boot/startup/lib.a
 
 $(obj)/vmlinux: $(vmlinux-objs-y) $(vmlinux-libs-y) FORCE
 	$(call if_changed,ld)
diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S
index eafd4f185e77..d9dab940ff62 100644
--- a/arch/x86/boot/compressed/head_64.S
+++ b/arch/x86/boot/compressed/head_64.S
@@ -35,7 +35,6 @@
 #include <asm/bootparam.h>
 #include <asm/desc_defs.h>
 #include <asm/trapnr.h>
-#include "pgtable.h"
 
 /*
  * Fix alignment at 16 bytes. Following CONFIG_FUNCTION_ALIGNMENT will result
diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c
index 1cdcd4aaf395..94b5991da001 100644
--- a/arch/x86/boot/compressed/misc.c
+++ b/arch/x86/boot/compressed/misc.c
@@ -14,7 +14,6 @@
 
 #include "misc.h"
 #include "error.h"
-#include "pgtable.h"
 #include "../string.h"
 #include "../voffset.h"
 #include <asm/bootparam_utils.h>
diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h
index dd8d1a85f671..db1048621ea2 100644
--- a/arch/x86/boot/compressed/misc.h
+++ b/arch/x86/boot/compressed/misc.h
@@ -136,6 +136,9 @@ static inline void console_init(void)
 #endif
 
 #ifdef CONFIG_AMD_MEM_ENCRYPT
+struct es_em_ctxt;
+struct insn;
+
 void sev_enable(struct boot_params *bp);
 void snp_check_features(void);
 void sev_es_shutdown_ghcb(void);
@@ -143,6 +146,11 @@ extern bool sev_es_check_ghcb_fault(unsigned long address);
 void snp_set_page_private(unsigned long paddr);
 void snp_set_page_shared(unsigned long paddr);
 void sev_prep_identity_maps(unsigned long top_level_pgt);
+
+enum es_result vc_decode_insn(struct es_em_ctxt *ctxt);
+bool insn_has_rep_prefix(struct insn *insn);
+void sev_insn_decode_init(void);
+bool early_setup_ghcb(void);
 #else
 static inline void sev_enable(struct boot_params *bp)
 {
diff --git a/arch/x86/boot/compressed/pgtable.h b/arch/x86/boot/compressed/pgtable.h
deleted file mode 100644
index 6d595abe06b3..000000000000
--- a/arch/x86/boot/compressed/pgtable.h
+++ /dev/null
@@ -1,18 +0,0 @@
-#ifndef BOOT_COMPRESSED_PAGETABLE_H
-#define BOOT_COMPRESSED_PAGETABLE_H
-
-#define TRAMPOLINE_32BIT_SIZE		(2 * PAGE_SIZE)
-
-#define TRAMPOLINE_32BIT_CODE_OFFSET	PAGE_SIZE
-#define TRAMPOLINE_32BIT_CODE_SIZE	0xA0
-
-#ifndef __ASSEMBLER__
-
-extern unsigned long *trampoline_32bit;
-
-extern void trampoline_32bit_src(void *trampoline, bool enable_5lvl);
-
-extern const u16 trampoline_ljmp_imm_offset;
-
-#endif /* __ASSEMBLER__ */
-#endif /* BOOT_COMPRESSED_PAGETABLE_H */
diff --git a/arch/x86/boot/compressed/pgtable_64.c b/arch/x86/boot/compressed/pgtable_64.c
index d8c5de40669d..5a6c7a190e5b 100644
--- a/arch/x86/boot/compressed/pgtable_64.c
+++ b/arch/x86/boot/compressed/pgtable_64.c
@@ -4,7 +4,6 @@
 #include <asm/bootparam_utils.h>
 #include <asm/e820/types.h>
 #include <asm/processor.h>
-#include "pgtable.h"
 #include "../string.h"
 #include "efi.h"
 
diff --git a/arch/x86/boot/compressed/sev-handle-vc.c b/arch/x86/boot/compressed/sev-handle-vc.c
new file mode 100644
index 000000000000..89dd02de2a0f
--- /dev/null
+++ b/arch/x86/boot/compressed/sev-handle-vc.c
@@ -0,0 +1,134 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include "misc.h"
+#include "sev.h"
+
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <asm/insn.h>
+#include <asm/pgtable_types.h>
+#include <asm/ptrace.h>
+#include <asm/sev.h>
+#include <asm/trapnr.h>
+#include <asm/trap_pf.h>
+#include <asm/fpu/xcr.h>
+
+#define __BOOT_COMPRESSED
+
+/* Basic instruction decoding support needed */
+#include "../../lib/inat.c"
+#include "../../lib/insn.c"
+
+/*
+ * Copy a version of this function here - insn-eval.c can't be used in
+ * pre-decompression code.
+ */
+bool insn_has_rep_prefix(struct insn *insn)
+{
+	insn_byte_t p;
+	int i;
+
+	insn_get_prefixes(insn);
+
+	for_each_insn_prefix(insn, i, p) {
+		if (p == 0xf2 || p == 0xf3)
+			return true;
+	}
+
+	return false;
+}
+
+enum es_result vc_decode_insn(struct es_em_ctxt *ctxt)
+{
+	char buffer[MAX_INSN_SIZE];
+	int ret;
+
+	memcpy(buffer, (unsigned char *)ctxt->regs->ip, MAX_INSN_SIZE);
+
+	ret = insn_decode(&ctxt->insn, buffer, MAX_INSN_SIZE, INSN_MODE_64);
+	if (ret < 0)
+		return ES_DECODE_FAILED;
+
+	return ES_OK;
+}
+
+extern void sev_insn_decode_init(void) __alias(inat_init_tables);
+
+/*
+ * Only a dummy for insn_get_seg_base() - Early boot-code is 64bit only and
+ * doesn't use segments.
+ */
+static unsigned long insn_get_seg_base(struct pt_regs *regs, int seg_reg_idx)
+{
+	return 0UL;
+}
+
+static enum es_result vc_write_mem(struct es_em_ctxt *ctxt,
+				   void *dst, char *buf, size_t size)
+{
+	memcpy(dst, buf, size);
+
+	return ES_OK;
+}
+
+static enum es_result vc_read_mem(struct es_em_ctxt *ctxt,
+				  void *src, char *buf, size_t size)
+{
+	memcpy(buf, src, size);
+
+	return ES_OK;
+}
+
+static enum es_result vc_ioio_check(struct es_em_ctxt *ctxt, u16 port, size_t size)
+{
+	return ES_OK;
+}
+
+static bool fault_in_kernel_space(unsigned long address)
+{
+	return false;
+}
+
+#define sev_printk(fmt, ...)
+
+#include "../../coco/sev/vc-shared.c"
+
+void do_boot_stage2_vc(struct pt_regs *regs, unsigned long exit_code)
+{
+	struct es_em_ctxt ctxt;
+	enum es_result result;
+
+	if (!boot_ghcb && !early_setup_ghcb())
+		sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_GEN_REQ);
+
+	vc_ghcb_invalidate(boot_ghcb);
+	result = vc_init_em_ctxt(&ctxt, regs, exit_code);
+	if (result != ES_OK)
+		goto finish;
+
+	result = vc_check_opcode_bytes(&ctxt, exit_code);
+	if (result != ES_OK)
+		goto finish;
+
+	switch (exit_code) {
+	case SVM_EXIT_RDTSC:
+	case SVM_EXIT_RDTSCP:
+		result = vc_handle_rdtsc(boot_ghcb, &ctxt, exit_code);
+		break;
+	case SVM_EXIT_IOIO:
+		result = vc_handle_ioio(boot_ghcb, &ctxt);
+		break;
+	case SVM_EXIT_CPUID:
+		result = vc_handle_cpuid(boot_ghcb, &ctxt);
+		break;
+	default:
+		result = ES_UNSUPPORTED;
+		break;
+	}
+
+finish:
+	if (result == ES_OK)
+		vc_finish_insn(&ctxt);
+	else if (result != ES_RETRY)
+		sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_GEN_REQ);
+}
diff --git a/arch/x86/boot/compressed/sev.c b/arch/x86/boot/compressed/sev.c
index 0003e4416efd..612b443296d3 100644
--- a/arch/x86/boot/compressed/sev.c
+++ b/arch/x86/boot/compressed/sev.c
@@ -24,96 +24,11 @@
 #include <asm/cpuid.h>
 
 #include "error.h"
-#include "../msr.h"
+#include "sev.h"
 
 static struct ghcb boot_ghcb_page __aligned(PAGE_SIZE);
 struct ghcb *boot_ghcb;
 
-/*
- * Copy a version of this function here - insn-eval.c can't be used in
- * pre-decompression code.
- */
-static bool insn_has_rep_prefix(struct insn *insn)
-{
-	insn_byte_t p;
-	int i;
-
-	insn_get_prefixes(insn);
-
-	for_each_insn_prefix(insn, i, p) {
-		if (p == 0xf2 || p == 0xf3)
-			return true;
-	}
-
-	return false;
-}
-
-/*
- * Only a dummy for insn_get_seg_base() - Early boot-code is 64bit only and
- * doesn't use segments.
- */
-static unsigned long insn_get_seg_base(struct pt_regs *regs, int seg_reg_idx)
-{
-	return 0UL;
-}
-
-static inline u64 sev_es_rd_ghcb_msr(void)
-{
-	struct msr m;
-
-	boot_rdmsr(MSR_AMD64_SEV_ES_GHCB, &m);
-
-	return m.q;
-}
-
-static inline void sev_es_wr_ghcb_msr(u64 val)
-{
-	struct msr m;
-
-	m.q = val;
-	boot_wrmsr(MSR_AMD64_SEV_ES_GHCB, &m);
-}
-
-static enum es_result vc_decode_insn(struct es_em_ctxt *ctxt)
-{
-	char buffer[MAX_INSN_SIZE];
-	int ret;
-
-	memcpy(buffer, (unsigned char *)ctxt->regs->ip, MAX_INSN_SIZE);
-
-	ret = insn_decode(&ctxt->insn, buffer, MAX_INSN_SIZE, INSN_MODE_64);
-	if (ret < 0)
-		return ES_DECODE_FAILED;
-
-	return ES_OK;
-}
-
-static enum es_result vc_write_mem(struct es_em_ctxt *ctxt,
-				   void *dst, char *buf, size_t size)
-{
-	memcpy(dst, buf, size);
-
-	return ES_OK;
-}
-
-static enum es_result vc_read_mem(struct es_em_ctxt *ctxt,
-				  void *src, char *buf, size_t size)
-{
-	memcpy(buf, src, size);
-
-	return ES_OK;
-}
-
-static enum es_result vc_ioio_check(struct es_em_ctxt *ctxt, u16 port, size_t size)
-{
-	return ES_OK;
-}
-
-static bool fault_in_kernel_space(unsigned long address)
-{
-	return false;
-}
-
 #undef __init
 #define __init
 
@@ -122,24 +37,27 @@ static bool fault_in_kernel_space(unsigned long address)
 
 #define __BOOT_COMPRESSED
 
-/* Basic instruction decoding support needed */
-#include "../../lib/inat.c"
-#include "../../lib/insn.c"
+extern struct svsm_ca *boot_svsm_caa;
+extern u64 boot_svsm_caa_pa;
 
-/* Include code for early handlers */
-#include "../../coco/sev/shared.c"
-
-static struct svsm_ca *svsm_get_caa(void)
+struct svsm_ca *svsm_get_caa(void)
 {
 	return boot_svsm_caa;
 }
 
-static u64 svsm_get_caa_pa(void)
+u64 svsm_get_caa_pa(void)
 {
 	return boot_svsm_caa_pa;
 }
 
-static int svsm_perform_call_protocol(struct svsm_call *call)
+int svsm_perform_call_protocol(struct svsm_call *call);
+
+u8 snp_vmpl;
+
+/* Include code for early handlers */
+#include "../../boot/startup/sev-shared.c"
+
+int svsm_perform_call_protocol(struct svsm_call *call)
 {
 	struct ghcb *ghcb;
 	int ret;
@@ -157,7 +75,7 @@ static int svsm_perform_call_protocol(struct svsm_call *call)
 	return ret;
 }
 
-bool sev_snp_enabled(void)
+static bool sev_snp_enabled(void)
 {
 	return sev_status & MSR_AMD64_SEV_SNP_ENABLED;
 }
@@ -212,7 +130,7 @@ void snp_set_page_shared(unsigned long paddr)
 	__page_state_change(paddr, SNP_PAGE_STATE_SHARED);
 }
 
-static bool early_setup_ghcb(void)
+bool early_setup_ghcb(void)
 {
 	if (set_page_decrypted((unsigned long)&boot_ghcb_page))
 		return false;
@@ -223,7 +141,7 @@ static bool early_setup_ghcb(void)
 	boot_ghcb = &boot_ghcb_page;
 
 	/* Initialize lookup tables for the instruction decoder */
-	inat_init_tables();
+	sev_insn_decode_init();
 
 	/* SNP guest requires the GHCB GPA must be registered */
 	if (sev_snp_enabled())
@@ -296,46 +214,6 @@ bool sev_es_check_ghcb_fault(unsigned long address)
 	return ((address & PAGE_MASK) == (unsigned long)&boot_ghcb_page);
 }
 
-void do_boot_stage2_vc(struct pt_regs *regs, unsigned long exit_code)
-{
-	struct es_em_ctxt ctxt;
-	enum es_result result;
-
-	if (!boot_ghcb && !early_setup_ghcb())
-		sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_GEN_REQ);
-
-	vc_ghcb_invalidate(boot_ghcb);
-	result = vc_init_em_ctxt(&ctxt, regs, exit_code);
-	if (result != ES_OK)
-		goto finish;
-
-	result = vc_check_opcode_bytes(&ctxt, exit_code);
-	if (result != ES_OK)
-		goto finish;
-
-	switch (exit_code) {
-	case SVM_EXIT_RDTSC:
-	case SVM_EXIT_RDTSCP:
-		result = vc_handle_rdtsc(boot_ghcb, &ctxt, exit_code);
-		break;
-	case SVM_EXIT_IOIO:
-		result = vc_handle_ioio(boot_ghcb, &ctxt);
-		break;
-	case SVM_EXIT_CPUID:
-		result = vc_handle_cpuid(boot_ghcb, &ctxt);
-		break;
-	default:
-		result = ES_UNSUPPORTED;
-		break;
-	}
-
-finish:
-	if (result == ES_OK)
-		vc_finish_insn(&ctxt);
-	else if (result != ES_RETRY)
-		sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_GEN_REQ);
-}
-
 /*
  * SNP_FEATURES_IMPL_REQ is the mask of SNP features that will need
  * guest side implementation for proper functioning of the guest. If any
diff --git a/arch/x86/boot/compressed/sev.h b/arch/x86/boot/compressed/sev.h
index d3900384b8ab..92f79c21939c 100644
--- a/arch/x86/boot/compressed/sev.h
+++ b/arch/x86/boot/compressed/sev.h
@@ -10,14 +10,31 @@
 
 #ifdef CONFIG_AMD_MEM_ENCRYPT
 
-bool sev_snp_enabled(void);
+#include "../msr.h"
+
 void snp_accept_memory(phys_addr_t start, phys_addr_t end);
 u64 sev_get_status(void);
 bool early_is_sevsnp_guest(void);
 
+static inline u64 sev_es_rd_ghcb_msr(void)
+{
+	struct msr m;
+
+	boot_rdmsr(MSR_AMD64_SEV_ES_GHCB, &m);
+
+	return m.q;
+}
+
+static inline void sev_es_wr_ghcb_msr(u64 val)
+{
+	struct msr m;
+
+	m.q = val;
+	boot_wrmsr(MSR_AMD64_SEV_ES_GHCB, &m);
+}
+
 #else
 
-static inline bool sev_snp_enabled(void) { return false; }
 static inline void snp_accept_memory(phys_addr_t start, phys_addr_t end) { }
 static inline u64 sev_get_status(void) { return 0; }
 static inline bool early_is_sevsnp_guest(void) { return false; }
diff --git a/arch/x86/boot/compressed/string.c b/arch/x86/boot/compressed/string.c
index 81fc1eaa3229..9af19d9614cb 100644
--- a/arch/x86/boot/compressed/string.c
+++ b/arch/x86/boot/compressed/string.c
@@ -15,9 +15,9 @@ static void *____memcpy(void *dest, const void *src, size_t n)
 {
 	int d0, d1, d2;
 	asm volatile(
-		"rep ; movsl\n\t"
+		"rep movsl\n\t"
 		"movl %4,%%ecx\n\t"
-		"rep ; movsb\n\t"
+		"rep movsb"
 		: "=&c" (d0), "=&D" (d1), "=&S" (d2)
 		: "0" (n >> 2), "g" (n & 3), "1" (dest), "2" (src)
 		: "memory");
@@ -29,9 +29,9 @@ static void *____memcpy(void *dest, const void *src, size_t n)
 {
 	long d0, d1, d2;
 	asm volatile(
-		"rep ; movsq\n\t"
+		"rep movsq\n\t"
 		"movq %4,%%rcx\n\t"
-		"rep ; movsb\n\t"
+		"rep movsb"
 		: "=&c" (d0), "=&D" (d1), "=&S" (d2)
 		: "0" (n >> 3), "g" (n & 7), "1" (dest), "2" (src)
 		: "memory");
diff --git a/arch/x86/boot/copy.S b/arch/x86/boot/copy.S
index 6afd05e819d2..3973a67cd04e 100644
--- a/arch/x86/boot/copy.S
+++ b/arch/x86/boot/copy.S
@@ -22,10 +22,10 @@ SYM_FUNC_START_NOALIGN(memcpy)
 	movw	%dx, %si
 	pushw	%cx
 	shrw	$2, %cx
-	rep; movsl
+	rep movsl
 	popw	%cx
 	andw	$3, %cx
-	rep; movsb
+	rep movsb
 	popw	%di
 	popw	%si
 	retl
@@ -38,10 +38,10 @@ SYM_FUNC_START_NOALIGN(memset)
 	imull	$0x01010101,%eax
 	pushw	%cx
 	shrw	$2, %cx
-	rep; stosl
+	rep stosl
 	popw	%cx
 	andw	$3, %cx
-	rep; stosb
+	rep stosb
 	popw	%di
 	retl
 SYM_FUNC_END(memset)
diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S
index b5c79f43359b..9cb91421b4e4 100644
--- a/arch/x86/boot/header.S
+++ b/arch/x86/boot/header.S
@@ -585,7 +585,7 @@ start_of_setup:
 	xorl	%eax, %eax
 	subw	%di, %cx
 	shrw	$2, %cx
-	rep; stosl
+	rep stosl
 
 # Jump to C code (should not return)
 	calll	main
diff --git a/arch/x86/boot/startup/Makefile b/arch/x86/boot/startup/Makefile
new file mode 100644
index 000000000000..b514f7e81332
--- /dev/null
+++ b/arch/x86/boot/startup/Makefile
@@ -0,0 +1,30 @@
+# SPDX-License-Identifier: GPL-2.0
+
+KBUILD_AFLAGS		+= -D__DISABLE_EXPORTS
+KBUILD_CFLAGS		+= -D__DISABLE_EXPORTS -mcmodel=small -fPIC \
+			   -Os -DDISABLE_BRANCH_PROFILING \
+			   $(DISABLE_STACKLEAK_PLUGIN) \
+			   -fno-stack-protector -D__NO_FORTIFY \
+			   -fno-jump-tables \
+			   -include $(srctree)/include/linux/hidden.h
+
+# disable ftrace hooks and LTO
+KBUILD_CFLAGS	:= $(subst $(CC_FLAGS_FTRACE),,$(KBUILD_CFLAGS))
+KBUILD_CFLAGS	:= $(filter-out $(CC_FLAGS_LTO),$(KBUILD_CFLAGS))
+KASAN_SANITIZE	:= n
+KCSAN_SANITIZE	:= n
+KMSAN_SANITIZE	:= n
+UBSAN_SANITIZE	:= n
+KCOV_INSTRUMENT	:= n
+
+obj-$(CONFIG_X86_64)		+= gdt_idt.o map_kernel.o
+obj-$(CONFIG_AMD_MEM_ENCRYPT)	+= sme.o sev-startup.o
+
+lib-$(CONFIG_X86_64)		+= la57toggle.o
+lib-$(CONFIG_EFI_MIXED)		+= efi-mixed.o
+
+#
+# Disable objtool validation for all library code, which is intended
+# to be linked into the decompressor or the EFI stub but not vmlinux
+#
+$(patsubst %.o,$(obj)/%.o,$(lib-y)): OBJECT_FILES_NON_STANDARD := y
diff --git a/drivers/firmware/efi/libstub/x86-mixed.S b/arch/x86/boot/startup/efi-mixed.S
index e04ed99bc449..e04ed99bc449 100644
--- a/drivers/firmware/efi/libstub/x86-mixed.S
+++ b/arch/x86/boot/startup/efi-mixed.S
diff --git a/arch/x86/boot/startup/gdt_idt.c b/arch/x86/boot/startup/gdt_idt.c
new file mode 100644
index 000000000000..a3112a69b06a
--- /dev/null
+++ b/arch/x86/boot/startup/gdt_idt.c
@@ -0,0 +1,71 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/linkage.h>
+#include <linux/types.h>
+
+#include <asm/desc.h>
+#include <asm/init.h>
+#include <asm/setup.h>
+#include <asm/sev.h>
+#include <asm/trapnr.h>
+
+/*
+ * Data structures and code used for IDT setup in head_64.S. The bringup-IDT is
+ * used until the idt_table takes over. On the boot CPU this happens in
+ * x86_64_start_kernel(), on secondary CPUs in start_secondary(). In both cases
+ * this happens in the functions called from head_64.S.
+ *
+ * The idt_table can't be used that early because all the code modifying it is
+ * in idt.c and can be instrumented by tracing or KASAN, which both don't work
+ * during early CPU bringup. Also the idt_table has the runtime vectors
+ * configured which require certain CPU state to be setup already (like TSS),
+ * which also hasn't happened yet in early CPU bringup.
+ */
+static gate_desc bringup_idt_table[NUM_EXCEPTION_VECTORS] __page_aligned_data;
+
+/* This may run while still in the direct mapping */
+void __head startup_64_load_idt(void *vc_handler)
+{
+	struct desc_ptr desc = {
+		.address = (unsigned long)rip_rel_ptr(bringup_idt_table),
+		.size    = sizeof(bringup_idt_table) - 1,
+	};
+	struct idt_data data;
+	gate_desc idt_desc;
+
+	/* @vc_handler is set only for a VMM Communication Exception */
+	if (vc_handler) {
+		init_idt_data(&data, X86_TRAP_VC, vc_handler);
+		idt_init_desc(&idt_desc, &data);
+		native_write_idt_entry((gate_desc *)desc.address, X86_TRAP_VC, &idt_desc);
+	}
+
+	native_load_idt(&desc);
+}
+
+/*
+ * Setup boot CPU state needed before kernel switches to virtual addresses.
+ */
+void __head startup_64_setup_gdt_idt(void)
+{
+	struct gdt_page *gp = rip_rel_ptr((void *)(__force unsigned long)&gdt_page);
+	void *handler = NULL;
+
+	struct desc_ptr startup_gdt_descr = {
+		.address = (unsigned long)gp->gdt,
+		.size    = GDT_SIZE - 1,
+	};
+
+	/* Load GDT */
+	native_load_gdt(&startup_gdt_descr);
+
+	/* New GDT is live - reload data segment registers */
+	asm volatile("movl %%eax, %%ds\n"
+		     "movl %%eax, %%ss\n"
+		     "movl %%eax, %%es\n" : : "a"(__KERNEL_DS) : "memory");
+
+	if (IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT))
+		handler = rip_rel_ptr(vc_no_ghcb);
+
+	startup_64_load_idt(handler);
+}
diff --git a/arch/x86/boot/compressed/la57toggle.S b/arch/x86/boot/startup/la57toggle.S
index 9ee002387eb1..370075b4d95b 100644
--- a/arch/x86/boot/compressed/la57toggle.S
+++ b/arch/x86/boot/startup/la57toggle.S
@@ -5,7 +5,6 @@
 #include <asm/boot.h>
 #include <asm/msr.h>
 #include <asm/processor-flags.h>
-#include "pgtable.h"
 
 /*
  * This is the 32-bit trampoline that will be copied over to low memory. It
diff --git a/arch/x86/boot/startup/map_kernel.c b/arch/x86/boot/startup/map_kernel.c
new file mode 100644
index 000000000000..099ae2559336
--- /dev/null
+++ b/arch/x86/boot/startup/map_kernel.c
@@ -0,0 +1,223 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/init.h>
+#include <linux/linkage.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/pgtable.h>
+
+#include <asm/init.h>
+#include <asm/sections.h>
+#include <asm/setup.h>
+#include <asm/sev.h>
+
+extern pmd_t early_dynamic_pgts[EARLY_DYNAMIC_PAGE_TABLES][PTRS_PER_PMD];
+extern unsigned int next_early_pgt;
+
+static inline bool check_la57_support(void)
+{
+	if (!IS_ENABLED(CONFIG_X86_5LEVEL))
+		return false;
+
+	/*
+	 * 5-level paging is detected and enabled at kernel decompression
+	 * stage. Only check if it has been enabled there.
+	 */
+	if (!(native_read_cr4() & X86_CR4_LA57))
+		return false;
+
+	__pgtable_l5_enabled	= 1;
+	pgdir_shift		= 48;
+	ptrs_per_p4d		= 512;
+	page_offset_base	= __PAGE_OFFSET_BASE_L5;
+	vmalloc_base		= __VMALLOC_BASE_L5;
+	vmemmap_base		= __VMEMMAP_BASE_L5;
+
+	return true;
+}
+
+static unsigned long __head sme_postprocess_startup(struct boot_params *bp,
+						    pmdval_t *pmd,
+						    unsigned long p2v_offset)
+{
+	unsigned long paddr, paddr_end;
+	int i;
+
+	/* Encrypt the kernel and related (if SME is active) */
+	sme_encrypt_kernel(bp);
+
+	/*
+	 * Clear the memory encryption mask from the .bss..decrypted section.
+	 * The bss section will be memset to zero later in the initialization so
+	 * there is no need to zero it after changing the memory encryption
+	 * attribute.
+	 */
+	if (sme_get_me_mask()) {
+		paddr = (unsigned long)rip_rel_ptr(__start_bss_decrypted);
+		paddr_end = (unsigned long)rip_rel_ptr(__end_bss_decrypted);
+
+		for (; paddr < paddr_end; paddr += PMD_SIZE) {
+			/*
+			 * On SNP, transition the page to shared in the RMP table so that
+			 * it is consistent with the page table attribute change.
+			 *
+			 * __start_bss_decrypted has a virtual address in the high range
+			 * mapping (kernel .text). PVALIDATE, by way of
+			 * early_snp_set_memory_shared(), requires a valid virtual
+			 * address but the kernel is currently running off of the identity
+			 * mapping so use the PA to get a *currently* valid virtual address.
+			 */
+			early_snp_set_memory_shared(paddr, paddr, PTRS_PER_PMD);
+
+			i = pmd_index(paddr - p2v_offset);
+			pmd[i] -= sme_get_me_mask();
+		}
+	}
+
+	/*
+	 * Return the SME encryption mask (if SME is active) to be used as a
+	 * modifier for the initial pgdir entry programmed into CR3.
+	 */
+	return sme_get_me_mask();
+}
+
+/*
+ * This code is compiled using PIC codegen because it will execute from the
+ * early 1:1 mapping of memory, which deviates from the mapping expected by the
+ * linker. Due to this deviation, taking the address of a global variable will
+ * produce an ambiguous result when using the plain & operator.  Instead,
+ * rip_rel_ptr() must be used, which will return the RIP-relative address in
+ * the 1:1 mapping of memory. Kernel virtual addresses can be determined by
+ * subtracting p2v_offset from the RIP-relative address.
+ */
+unsigned long __head __startup_64(unsigned long p2v_offset,
+				  struct boot_params *bp)
+{
+	pmd_t (*early_pgts)[PTRS_PER_PMD] = rip_rel_ptr(early_dynamic_pgts);
+	unsigned long physaddr = (unsigned long)rip_rel_ptr(_text);
+	unsigned long va_text, va_end;
+	unsigned long pgtable_flags;
+	unsigned long load_delta;
+	pgdval_t *pgd;
+	p4dval_t *p4d;
+	pudval_t *pud;
+	pmdval_t *pmd, pmd_entry;
+	bool la57;
+	int i;
+
+	la57 = check_la57_support();
+
+	/* Is the address too large? */
+	if (physaddr >> MAX_PHYSMEM_BITS)
+		for (;;);
+
+	/*
+	 * Compute the delta between the address I am compiled to run at
+	 * and the address I am actually running at.
+	 */
+	phys_base = load_delta = __START_KERNEL_map + p2v_offset;
+
+	/* Is the address not 2M aligned? */
+	if (load_delta & ~PMD_MASK)
+		for (;;);
+
+	va_text = physaddr - p2v_offset;
+	va_end  = (unsigned long)rip_rel_ptr(_end) - p2v_offset;
+
+	/* Include the SME encryption mask in the fixup value */
+	load_delta += sme_get_me_mask();
+
+	/* Fixup the physical addresses in the page table */
+
+	pgd = rip_rel_ptr(early_top_pgt);
+	pgd[pgd_index(__START_KERNEL_map)] += load_delta;
+
+	if (IS_ENABLED(CONFIG_X86_5LEVEL) && la57) {
+		p4d = (p4dval_t *)rip_rel_ptr(level4_kernel_pgt);
+		p4d[MAX_PTRS_PER_P4D - 1] += load_delta;
+
+		pgd[pgd_index(__START_KERNEL_map)] = (pgdval_t)p4d | _PAGE_TABLE;
+	}
+
+	level3_kernel_pgt[PTRS_PER_PUD - 2].pud += load_delta;
+	level3_kernel_pgt[PTRS_PER_PUD - 1].pud += load_delta;
+
+	for (i = FIXMAP_PMD_TOP; i > FIXMAP_PMD_TOP - FIXMAP_PMD_NUM; i--)
+		level2_fixmap_pgt[i].pmd += load_delta;
+
+	/*
+	 * Set up the identity mapping for the switchover.  These
+	 * entries should *NOT* have the global bit set!  This also
+	 * creates a bunch of nonsense entries but that is fine --
+	 * it avoids problems around wraparound.
+	 */
+
+	pud = &early_pgts[0]->pmd;
+	pmd = &early_pgts[1]->pmd;
+	next_early_pgt = 2;
+
+	pgtable_flags = _KERNPG_TABLE_NOENC + sme_get_me_mask();
+
+	if (la57) {
+		p4d = &early_pgts[next_early_pgt++]->pmd;
+
+		i = (physaddr >> PGDIR_SHIFT) % PTRS_PER_PGD;
+		pgd[i + 0] = (pgdval_t)p4d + pgtable_flags;
+		pgd[i + 1] = (pgdval_t)p4d + pgtable_flags;
+
+		i = physaddr >> P4D_SHIFT;
+		p4d[(i + 0) % PTRS_PER_P4D] = (pgdval_t)pud + pgtable_flags;
+		p4d[(i + 1) % PTRS_PER_P4D] = (pgdval_t)pud + pgtable_flags;
+	} else {
+		i = (physaddr >> PGDIR_SHIFT) % PTRS_PER_PGD;
+		pgd[i + 0] = (pgdval_t)pud + pgtable_flags;
+		pgd[i + 1] = (pgdval_t)pud + pgtable_flags;
+	}
+
+	i = physaddr >> PUD_SHIFT;
+	pud[(i + 0) % PTRS_PER_PUD] = (pudval_t)pmd + pgtable_flags;
+	pud[(i + 1) % PTRS_PER_PUD] = (pudval_t)pmd + pgtable_flags;
+
+	pmd_entry = __PAGE_KERNEL_LARGE_EXEC & ~_PAGE_GLOBAL;
+	pmd_entry += sme_get_me_mask();
+	pmd_entry +=  physaddr;
+
+	for (i = 0; i < DIV_ROUND_UP(va_end - va_text, PMD_SIZE); i++) {
+		int idx = i + (physaddr >> PMD_SHIFT);
+
+		pmd[idx % PTRS_PER_PMD] = pmd_entry + i * PMD_SIZE;
+	}
+
+	/*
+	 * Fixup the kernel text+data virtual addresses. Note that
+	 * we might write invalid pmds, when the kernel is relocated
+	 * cleanup_highmap() fixes this up along with the mappings
+	 * beyond _end.
+	 *
+	 * Only the region occupied by the kernel image has so far
+	 * been checked against the table of usable memory regions
+	 * provided by the firmware, so invalidate pages outside that
+	 * region. A page table entry that maps to a reserved area of
+	 * memory would allow processor speculation into that area,
+	 * and on some hardware (particularly the UV platform) even
+	 * speculative access to some reserved areas is caught as an
+	 * error, causing the BIOS to halt the system.
+	 */
+
+	pmd = rip_rel_ptr(level2_kernel_pgt);
+
+	/* invalidate pages before the kernel image */
+	for (i = 0; i < pmd_index(va_text); i++)
+		pmd[i] &= ~_PAGE_PRESENT;
+
+	/* fixup pages that are part of the kernel image */
+	for (; i <= pmd_index(va_end); i++)
+		if (pmd[i] & _PAGE_PRESENT)
+			pmd[i] += load_delta;
+
+	/* invalidate pages after the kernel image */
+	for (; i < PTRS_PER_PMD; i++)
+		pmd[i] &= ~_PAGE_PRESENT;
+
+	return sme_postprocess_startup(bp, pmd, p2v_offset);
+}
diff --git a/arch/x86/coco/sev/shared.c b/arch/x86/boot/startup/sev-shared.c
index 2e4122f8aa6b..7a706db87b93 100644
--- a/arch/x86/coco/sev/shared.c
+++ b/arch/x86/boot/startup/sev-shared.c
@@ -14,76 +14,23 @@
 #ifndef __BOOT_COMPRESSED
 #define error(v)			pr_err(v)
 #define has_cpuflag(f)			boot_cpu_has(f)
-#define sev_printk(fmt, ...)		printk(fmt, ##__VA_ARGS__)
-#define sev_printk_rtl(fmt, ...)	printk_ratelimited(fmt, ##__VA_ARGS__)
 #else
 #undef WARN
 #define WARN(condition, format...) (!!(condition))
-#define sev_printk(fmt, ...)
-#define sev_printk_rtl(fmt, ...)
 #undef vc_forward_exception
 #define vc_forward_exception(c)		panic("SNP: Hypervisor requested exception\n")
 #endif
 
 /*
  * SVSM related information:
- *   When running under an SVSM, the VMPL that Linux is executing at must be
- *   non-zero. The VMPL is therefore used to indicate the presence of an SVSM.
- *
  *   During boot, the page tables are set up as identity mapped and later
  *   changed to use kernel virtual addresses. Maintain separate virtual and
  *   physical addresses for the CAA to allow SVSM functions to be used during
  *   early boot, both with identity mapped virtual addresses and proper kernel
  *   virtual addresses.
  */
-u8 snp_vmpl __ro_after_init;
-EXPORT_SYMBOL_GPL(snp_vmpl);
-static struct svsm_ca *boot_svsm_caa __ro_after_init;
-static u64 boot_svsm_caa_pa __ro_after_init;
-
-static struct svsm_ca *svsm_get_caa(void);
-static u64 svsm_get_caa_pa(void);
-static int svsm_perform_call_protocol(struct svsm_call *call);
-
-/* I/O parameters for CPUID-related helpers */
-struct cpuid_leaf {
-	u32 fn;
-	u32 subfn;
-	u32 eax;
-	u32 ebx;
-	u32 ecx;
-	u32 edx;
-};
-
-/*
- * Individual entries of the SNP CPUID table, as defined by the SNP
- * Firmware ABI, Revision 0.9, Section 7.1, Table 14.
- */
-struct snp_cpuid_fn {
-	u32 eax_in;
-	u32 ecx_in;
-	u64 xcr0_in;
-	u64 xss_in;
-	u32 eax;
-	u32 ebx;
-	u32 ecx;
-	u32 edx;
-	u64 __reserved;
-} __packed;
-
-/*
- * SNP CPUID table, as defined by the SNP Firmware ABI, Revision 0.9,
- * Section 8.14.2.6. Also noted there is the SNP firmware-enforced limit
- * of 64 entries per CPUID table.
- */
-#define SNP_CPUID_COUNT_MAX 64
-
-struct snp_cpuid_table {
-	u32 count;
-	u32 __reserved1;
-	u64 __reserved2;
-	struct snp_cpuid_fn fn[SNP_CPUID_COUNT_MAX];
-} __packed;
+struct svsm_ca *boot_svsm_caa __ro_after_init;
+u64 boot_svsm_caa_pa __ro_after_init;
 
 /*
  * Since feature negotiation related variables are set early in the boot
@@ -107,7 +54,7 @@ static u32 cpuid_std_range_max __ro_after_init;
 static u32 cpuid_hyp_range_max __ro_after_init;
 static u32 cpuid_ext_range_max __ro_after_init;
 
-static bool __init sev_es_check_cpu_features(void)
+bool __init sev_es_check_cpu_features(void)
 {
 	if (!has_cpuflag(X86_FEATURE_RDRAND)) {
 		error("RDRAND instruction not supported - no trusted source of randomness available\n");
@@ -117,7 +64,7 @@ static bool __init sev_es_check_cpu_features(void)
 	return true;
 }
 
-static void __head __noreturn
+void __head __noreturn
 sev_es_terminate(unsigned int set, unsigned int reason)
 {
 	u64 val = GHCB_MSR_TERM_REQ;
@@ -136,7 +83,7 @@ sev_es_terminate(unsigned int set, unsigned int reason)
 /*
  * The hypervisor features are available from GHCB version 2 onward.
  */
-static u64 get_hv_features(void)
+u64 get_hv_features(void)
 {
 	u64 val;
 
@@ -153,7 +100,7 @@ static u64 get_hv_features(void)
 	return GHCB_MSR_HV_FT_RESP_VAL(val);
 }
 
-static void snp_register_ghcb_early(unsigned long paddr)
+void snp_register_ghcb_early(unsigned long paddr)
 {
 	unsigned long pfn = paddr >> PAGE_SHIFT;
 	u64 val;
@@ -169,7 +116,7 @@ static void snp_register_ghcb_early(unsigned long paddr)
 		sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_REGISTER);
 }
 
-static bool sev_es_negotiate_protocol(void)
+bool sev_es_negotiate_protocol(void)
 {
 	u64 val;
 
@@ -190,39 +137,6 @@ static bool sev_es_negotiate_protocol(void)
 	return true;
 }
 
-static __always_inline void vc_ghcb_invalidate(struct ghcb *ghcb)
-{
-	ghcb->save.sw_exit_code = 0;
-	__builtin_memset(ghcb->save.valid_bitmap, 0, sizeof(ghcb->save.valid_bitmap));
-}
-
-static bool vc_decoding_needed(unsigned long exit_code)
-{
-	/* Exceptions don't require to decode the instruction */
-	return !(exit_code >= SVM_EXIT_EXCP_BASE &&
-		 exit_code <= SVM_EXIT_LAST_EXCP);
-}
-
-static enum es_result vc_init_em_ctxt(struct es_em_ctxt *ctxt,
-				      struct pt_regs *regs,
-				      unsigned long exit_code)
-{
-	enum es_result ret = ES_OK;
-
-	memset(ctxt, 0, sizeof(*ctxt));
-	ctxt->regs = regs;
-
-	if (vc_decoding_needed(exit_code))
-		ret = vc_decode_insn(ctxt);
-
-	return ret;
-}
-
-static void vc_finish_insn(struct es_em_ctxt *ctxt)
-{
-	ctxt->regs->ip += ctxt->insn.length;
-}
-
 static enum es_result verify_exception_info(struct ghcb *ghcb, struct es_em_ctxt *ctxt)
 {
 	u32 ret;
@@ -344,7 +258,7 @@ static int svsm_perform_ghcb_protocol(struct ghcb *ghcb, struct svsm_call *call)
 	 * Fill in protocol and format specifiers. This can be called very early
 	 * in the boot, so use rip-relative references as needed.
 	 */
-	ghcb->protocol_version = RIP_REL_REF(ghcb_version);
+	ghcb->protocol_version = ghcb_version;
 	ghcb->ghcb_usage       = GHCB_DEFAULT_USAGE;
 
 	ghcb_set_sw_exit_code(ghcb, SVM_VMGEXIT_SNP_RUN_VMPL);
@@ -371,10 +285,10 @@ static int svsm_perform_ghcb_protocol(struct ghcb *ghcb, struct svsm_call *call)
 	return svsm_process_result_codes(call);
 }
 
-static enum es_result sev_es_ghcb_hv_call(struct ghcb *ghcb,
-					  struct es_em_ctxt *ctxt,
-					  u64 exit_code, u64 exit_info_1,
-					  u64 exit_info_2)
+enum es_result sev_es_ghcb_hv_call(struct ghcb *ghcb,
+				   struct es_em_ctxt *ctxt,
+				   u64 exit_code, u64 exit_info_1,
+				   u64 exit_info_2)
 {
 	/* Fill in protocol and format specifiers */
 	ghcb->protocol_version = ghcb_version;
@@ -473,9 +387,9 @@ static int sev_cpuid_hv(struct ghcb *ghcb, struct es_em_ctxt *ctxt, struct cpuid
  * while running with the initial identity mapping as well as the
  * switch-over to kernel virtual addresses later.
  */
-static const struct snp_cpuid_table *snp_cpuid_get_table(void)
+const struct snp_cpuid_table *snp_cpuid_get_table(void)
 {
-	return &RIP_REL_REF(cpuid_table_copy);
+	return rip_rel_ptr(&cpuid_table_copy);
 }
 
 /*
@@ -672,7 +586,7 @@ snp_cpuid_postprocess(struct ghcb *ghcb, struct es_em_ctxt *ctxt,
  * Returns -EOPNOTSUPP if feature not enabled. Any other non-zero return value
  * should be treated as fatal by caller.
  */
-static int __head
+int __head
 snp_cpuid(struct ghcb *ghcb, struct es_em_ctxt *ctxt, struct cpuid_leaf *leaf)
 {
 	const struct snp_cpuid_table *cpuid_table = snp_cpuid_get_table();
@@ -701,9 +615,9 @@ snp_cpuid(struct ghcb *ghcb, struct es_em_ctxt *ctxt, struct cpuid_leaf *leaf)
 		leaf->eax = leaf->ebx = leaf->ecx = leaf->edx = 0;
 
 		/* Skip post-processing for out-of-range zero leafs. */
-		if (!(leaf->fn <= RIP_REL_REF(cpuid_std_range_max) ||
-		      (leaf->fn >= 0x40000000 && leaf->fn <= RIP_REL_REF(cpuid_hyp_range_max)) ||
-		      (leaf->fn >= 0x80000000 && leaf->fn <= RIP_REL_REF(cpuid_ext_range_max))))
+		if (!(leaf->fn <= cpuid_std_range_max ||
+		      (leaf->fn >= 0x40000000 && leaf->fn <= cpuid_hyp_range_max) ||
+		      (leaf->fn >= 0x80000000 && leaf->fn <= cpuid_ext_range_max)))
 			return 0;
 	}
 
@@ -782,391 +696,6 @@ fail:
 	sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_GEN_REQ);
 }
 
-static enum es_result vc_insn_string_check(struct es_em_ctxt *ctxt,
-					   unsigned long address,
-					   bool write)
-{
-	if (user_mode(ctxt->regs) && fault_in_kernel_space(address)) {
-		ctxt->fi.vector     = X86_TRAP_PF;
-		ctxt->fi.error_code = X86_PF_USER;
-		ctxt->fi.cr2        = address;
-		if (write)
-			ctxt->fi.error_code |= X86_PF_WRITE;
-
-		return ES_EXCEPTION;
-	}
-
-	return ES_OK;
-}
-
-static enum es_result vc_insn_string_read(struct es_em_ctxt *ctxt,
-					  void *src, char *buf,
-					  unsigned int data_size,
-					  unsigned int count,
-					  bool backwards)
-{
-	int i, b = backwards ? -1 : 1;
-	unsigned long address = (unsigned long)src;
-	enum es_result ret;
-
-	ret = vc_insn_string_check(ctxt, address, false);
-	if (ret != ES_OK)
-		return ret;
-
-	for (i = 0; i < count; i++) {
-		void *s = src + (i * data_size * b);
-		char *d = buf + (i * data_size);
-
-		ret = vc_read_mem(ctxt, s, d, data_size);
-		if (ret != ES_OK)
-			break;
-	}
-
-	return ret;
-}
-
-static enum es_result vc_insn_string_write(struct es_em_ctxt *ctxt,
-					   void *dst, char *buf,
-					   unsigned int data_size,
-					   unsigned int count,
-					   bool backwards)
-{
-	int i, s = backwards ? -1 : 1;
-	unsigned long address = (unsigned long)dst;
-	enum es_result ret;
-
-	ret = vc_insn_string_check(ctxt, address, true);
-	if (ret != ES_OK)
-		return ret;
-
-	for (i = 0; i < count; i++) {
-		void *d = dst + (i * data_size * s);
-		char *b = buf + (i * data_size);
-
-		ret = vc_write_mem(ctxt, d, b, data_size);
-		if (ret != ES_OK)
-			break;
-	}
-
-	return ret;
-}
-
-#define IOIO_TYPE_STR  BIT(2)
-#define IOIO_TYPE_IN   1
-#define IOIO_TYPE_INS  (IOIO_TYPE_IN | IOIO_TYPE_STR)
-#define IOIO_TYPE_OUT  0
-#define IOIO_TYPE_OUTS (IOIO_TYPE_OUT | IOIO_TYPE_STR)
-
-#define IOIO_REP       BIT(3)
-
-#define IOIO_ADDR_64   BIT(9)
-#define IOIO_ADDR_32   BIT(8)
-#define IOIO_ADDR_16   BIT(7)
-
-#define IOIO_DATA_32   BIT(6)
-#define IOIO_DATA_16   BIT(5)
-#define IOIO_DATA_8    BIT(4)
-
-#define IOIO_SEG_ES    (0 << 10)
-#define IOIO_SEG_DS    (3 << 10)
-
-static enum es_result vc_ioio_exitinfo(struct es_em_ctxt *ctxt, u64 *exitinfo)
-{
-	struct insn *insn = &ctxt->insn;
-	size_t size;
-	u64 port;
-
-	*exitinfo = 0;
-
-	switch (insn->opcode.bytes[0]) {
-	/* INS opcodes */
-	case 0x6c:
-	case 0x6d:
-		*exitinfo |= IOIO_TYPE_INS;
-		*exitinfo |= IOIO_SEG_ES;
-		port	   = ctxt->regs->dx & 0xffff;
-		break;
-
-	/* OUTS opcodes */
-	case 0x6e:
-	case 0x6f:
-		*exitinfo |= IOIO_TYPE_OUTS;
-		*exitinfo |= IOIO_SEG_DS;
-		port	   = ctxt->regs->dx & 0xffff;
-		break;
-
-	/* IN immediate opcodes */
-	case 0xe4:
-	case 0xe5:
-		*exitinfo |= IOIO_TYPE_IN;
-		port	   = (u8)insn->immediate.value & 0xffff;
-		break;
-
-	/* OUT immediate opcodes */
-	case 0xe6:
-	case 0xe7:
-		*exitinfo |= IOIO_TYPE_OUT;
-		port	   = (u8)insn->immediate.value & 0xffff;
-		break;
-
-	/* IN register opcodes */
-	case 0xec:
-	case 0xed:
-		*exitinfo |= IOIO_TYPE_IN;
-		port	   = ctxt->regs->dx & 0xffff;
-		break;
-
-	/* OUT register opcodes */
-	case 0xee:
-	case 0xef:
-		*exitinfo |= IOIO_TYPE_OUT;
-		port	   = ctxt->regs->dx & 0xffff;
-		break;
-
-	default:
-		return ES_DECODE_FAILED;
-	}
-
-	*exitinfo |= port << 16;
-
-	switch (insn->opcode.bytes[0]) {
-	case 0x6c:
-	case 0x6e:
-	case 0xe4:
-	case 0xe6:
-	case 0xec:
-	case 0xee:
-		/* Single byte opcodes */
-		*exitinfo |= IOIO_DATA_8;
-		size       = 1;
-		break;
-	default:
-		/* Length determined by instruction parsing */
-		*exitinfo |= (insn->opnd_bytes == 2) ? IOIO_DATA_16
-						     : IOIO_DATA_32;
-		size       = (insn->opnd_bytes == 2) ? 2 : 4;
-	}
-
-	switch (insn->addr_bytes) {
-	case 2:
-		*exitinfo |= IOIO_ADDR_16;
-		break;
-	case 4:
-		*exitinfo |= IOIO_ADDR_32;
-		break;
-	case 8:
-		*exitinfo |= IOIO_ADDR_64;
-		break;
-	}
-
-	if (insn_has_rep_prefix(insn))
-		*exitinfo |= IOIO_REP;
-
-	return vc_ioio_check(ctxt, (u16)port, size);
-}
-
-static enum es_result vc_handle_ioio(struct ghcb *ghcb, struct es_em_ctxt *ctxt)
-{
-	struct pt_regs *regs = ctxt->regs;
-	u64 exit_info_1, exit_info_2;
-	enum es_result ret;
-
-	ret = vc_ioio_exitinfo(ctxt, &exit_info_1);
-	if (ret != ES_OK)
-		return ret;
-
-	if (exit_info_1 & IOIO_TYPE_STR) {
-
-		/* (REP) INS/OUTS */
-
-		bool df = ((regs->flags & X86_EFLAGS_DF) == X86_EFLAGS_DF);
-		unsigned int io_bytes, exit_bytes;
-		unsigned int ghcb_count, op_count;
-		unsigned long es_base;
-		u64 sw_scratch;
-
-		/*
-		 * For the string variants with rep prefix the amount of in/out
-		 * operations per #VC exception is limited so that the kernel
-		 * has a chance to take interrupts and re-schedule while the
-		 * instruction is emulated.
-		 */
-		io_bytes   = (exit_info_1 >> 4) & 0x7;
-		ghcb_count = sizeof(ghcb->shared_buffer) / io_bytes;
-
-		op_count    = (exit_info_1 & IOIO_REP) ? regs->cx : 1;
-		exit_info_2 = min(op_count, ghcb_count);
-		exit_bytes  = exit_info_2 * io_bytes;
-
-		es_base = insn_get_seg_base(ctxt->regs, INAT_SEG_REG_ES);
-
-		/* Read bytes of OUTS into the shared buffer */
-		if (!(exit_info_1 & IOIO_TYPE_IN)) {
-			ret = vc_insn_string_read(ctxt,
-					       (void *)(es_base + regs->si),
-					       ghcb->shared_buffer, io_bytes,
-					       exit_info_2, df);
-			if (ret)
-				return ret;
-		}
-
-		/*
-		 * Issue an VMGEXIT to the HV to consume the bytes from the
-		 * shared buffer or to have it write them into the shared buffer
-		 * depending on the instruction: OUTS or INS.
-		 */
-		sw_scratch = __pa(ghcb) + offsetof(struct ghcb, shared_buffer);
-		ghcb_set_sw_scratch(ghcb, sw_scratch);
-		ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_IOIO,
-					  exit_info_1, exit_info_2);
-		if (ret != ES_OK)
-			return ret;
-
-		/* Read bytes from shared buffer into the guest's destination. */
-		if (exit_info_1 & IOIO_TYPE_IN) {
-			ret = vc_insn_string_write(ctxt,
-						   (void *)(es_base + regs->di),
-						   ghcb->shared_buffer, io_bytes,
-						   exit_info_2, df);
-			if (ret)
-				return ret;
-
-			if (df)
-				regs->di -= exit_bytes;
-			else
-				regs->di += exit_bytes;
-		} else {
-			if (df)
-				regs->si -= exit_bytes;
-			else
-				regs->si += exit_bytes;
-		}
-
-		if (exit_info_1 & IOIO_REP)
-			regs->cx -= exit_info_2;
-
-		ret = regs->cx ? ES_RETRY : ES_OK;
-
-	} else {
-
-		/* IN/OUT into/from rAX */
-
-		int bits = (exit_info_1 & 0x70) >> 1;
-		u64 rax = 0;
-
-		if (!(exit_info_1 & IOIO_TYPE_IN))
-			rax = lower_bits(regs->ax, bits);
-
-		ghcb_set_rax(ghcb, rax);
-
-		ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_IOIO, exit_info_1, 0);
-		if (ret != ES_OK)
-			return ret;
-
-		if (exit_info_1 & IOIO_TYPE_IN) {
-			if (!ghcb_rax_is_valid(ghcb))
-				return ES_VMM_ERROR;
-			regs->ax = lower_bits(ghcb->save.rax, bits);
-		}
-	}
-
-	return ret;
-}
-
-static int vc_handle_cpuid_snp(struct ghcb *ghcb, struct es_em_ctxt *ctxt)
-{
-	struct pt_regs *regs = ctxt->regs;
-	struct cpuid_leaf leaf;
-	int ret;
-
-	leaf.fn = regs->ax;
-	leaf.subfn = regs->cx;
-	ret = snp_cpuid(ghcb, ctxt, &leaf);
-	if (!ret) {
-		regs->ax = leaf.eax;
-		regs->bx = leaf.ebx;
-		regs->cx = leaf.ecx;
-		regs->dx = leaf.edx;
-	}
-
-	return ret;
-}
-
-static enum es_result vc_handle_cpuid(struct ghcb *ghcb,
-				      struct es_em_ctxt *ctxt)
-{
-	struct pt_regs *regs = ctxt->regs;
-	u32 cr4 = native_read_cr4();
-	enum es_result ret;
-	int snp_cpuid_ret;
-
-	snp_cpuid_ret = vc_handle_cpuid_snp(ghcb, ctxt);
-	if (!snp_cpuid_ret)
-		return ES_OK;
-	if (snp_cpuid_ret != -EOPNOTSUPP)
-		return ES_VMM_ERROR;
-
-	ghcb_set_rax(ghcb, regs->ax);
-	ghcb_set_rcx(ghcb, regs->cx);
-
-	if (cr4 & X86_CR4_OSXSAVE)
-		/* Safe to read xcr0 */
-		ghcb_set_xcr0(ghcb, xgetbv(XCR_XFEATURE_ENABLED_MASK));
-	else
-		/* xgetbv will cause #GP - use reset value for xcr0 */
-		ghcb_set_xcr0(ghcb, 1);
-
-	ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_CPUID, 0, 0);
-	if (ret != ES_OK)
-		return ret;
-
-	if (!(ghcb_rax_is_valid(ghcb) &&
-	      ghcb_rbx_is_valid(ghcb) &&
-	      ghcb_rcx_is_valid(ghcb) &&
-	      ghcb_rdx_is_valid(ghcb)))
-		return ES_VMM_ERROR;
-
-	regs->ax = ghcb->save.rax;
-	regs->bx = ghcb->save.rbx;
-	regs->cx = ghcb->save.rcx;
-	regs->dx = ghcb->save.rdx;
-
-	return ES_OK;
-}
-
-static enum es_result vc_handle_rdtsc(struct ghcb *ghcb,
-				      struct es_em_ctxt *ctxt,
-				      unsigned long exit_code)
-{
-	bool rdtscp = (exit_code == SVM_EXIT_RDTSCP);
-	enum es_result ret;
-
-	/*
-	 * The hypervisor should not be intercepting RDTSC/RDTSCP when Secure
-	 * TSC is enabled. A #VC exception will be generated if the RDTSC/RDTSCP
-	 * instructions are being intercepted. If this should occur and Secure
-	 * TSC is enabled, guest execution should be terminated as the guest
-	 * cannot rely on the TSC value provided by the hypervisor.
-	 */
-	if (sev_status & MSR_AMD64_SNP_SECURE_TSC)
-		return ES_VMM_ERROR;
-
-	ret = sev_es_ghcb_hv_call(ghcb, ctxt, exit_code, 0, 0);
-	if (ret != ES_OK)
-		return ret;
-
-	if (!(ghcb_rax_is_valid(ghcb) && ghcb_rdx_is_valid(ghcb) &&
-	     (!rdtscp || ghcb_rcx_is_valid(ghcb))))
-		return ES_VMM_ERROR;
-
-	ctxt->regs->ax = ghcb->save.rax;
-	ctxt->regs->dx = ghcb->save.rdx;
-	if (rdtscp)
-		ctxt->regs->cx = ghcb->save.rcx;
-
-	return ES_OK;
-}
-
 struct cc_setup_data {
 	struct setup_data header;
 	u32 cc_blob_address;
@@ -1224,36 +753,14 @@ static void __head setup_cpuid_table(const struct cc_blob_sev_info *cc_info)
 		const struct snp_cpuid_fn *fn = &cpuid_table->fn[i];
 
 		if (fn->eax_in == 0x0)
-			RIP_REL_REF(cpuid_std_range_max) = fn->eax;
+			cpuid_std_range_max = fn->eax;
 		else if (fn->eax_in == 0x40000000)
-			RIP_REL_REF(cpuid_hyp_range_max) = fn->eax;
+			cpuid_hyp_range_max = fn->eax;
 		else if (fn->eax_in == 0x80000000)
-			RIP_REL_REF(cpuid_ext_range_max) = fn->eax;
+			cpuid_ext_range_max = fn->eax;
 	}
 }
 
-static inline void __pval_terminate(u64 pfn, bool action, unsigned int page_size,
-				    int ret, u64 svsm_ret)
-{
-	WARN(1, "PVALIDATE failure: pfn: 0x%llx, action: %u, size: %u, ret: %d, svsm_ret: 0x%llx\n",
-	     pfn, action, page_size, ret, svsm_ret);
-
-	sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PVALIDATE);
-}
-
-static void svsm_pval_terminate(struct svsm_pvalidate_call *pc, int ret, u64 svsm_ret)
-{
-	unsigned int page_size;
-	bool action;
-	u64 pfn;
-
-	pfn = pc->entry[pc->cur_index].pfn;
-	action = pc->entry[pc->cur_index].action;
-	page_size = pc->entry[pc->cur_index].page_size;
-
-	__pval_terminate(pfn, action, page_size, ret, svsm_ret);
-}
-
 static void __head svsm_pval_4k_page(unsigned long paddr, bool validate)
 {
 	struct svsm_pvalidate_call *pc;
@@ -1296,11 +803,7 @@ static void __head pvalidate_4k_page(unsigned long vaddr, unsigned long paddr,
 {
 	int ret;
 
-	/*
-	 * This can be called very early during boot, so use rIP-relative
-	 * references as needed.
-	 */
-	if (RIP_REL_REF(snp_vmpl)) {
+	if (snp_vmpl) {
 		svsm_pval_4k_page(paddr, validate);
 	} else {
 		ret = pvalidate(vaddr, RMP_PG_SIZE_4K, validate);
@@ -1309,351 +812,6 @@ static void __head pvalidate_4k_page(unsigned long vaddr, unsigned long paddr,
 	}
 }
 
-static void pval_pages(struct snp_psc_desc *desc)
-{
-	struct psc_entry *e;
-	unsigned long vaddr;
-	unsigned int size;
-	unsigned int i;
-	bool validate;
-	u64 pfn;
-	int rc;
-
-	for (i = 0; i <= desc->hdr.end_entry; i++) {
-		e = &desc->entries[i];
-
-		pfn = e->gfn;
-		vaddr = (unsigned long)pfn_to_kaddr(pfn);
-		size = e->pagesize ? RMP_PG_SIZE_2M : RMP_PG_SIZE_4K;
-		validate = e->operation == SNP_PAGE_STATE_PRIVATE;
-
-		rc = pvalidate(vaddr, size, validate);
-		if (!rc)
-			continue;
-
-		if (rc == PVALIDATE_FAIL_SIZEMISMATCH && size == RMP_PG_SIZE_2M) {
-			unsigned long vaddr_end = vaddr + PMD_SIZE;
-
-			for (; vaddr < vaddr_end; vaddr += PAGE_SIZE, pfn++) {
-				rc = pvalidate(vaddr, RMP_PG_SIZE_4K, validate);
-				if (rc)
-					__pval_terminate(pfn, validate, RMP_PG_SIZE_4K, rc, 0);
-			}
-		} else {
-			__pval_terminate(pfn, validate, size, rc, 0);
-		}
-	}
-}
-
-static u64 svsm_build_ca_from_pfn_range(u64 pfn, u64 pfn_end, bool action,
-					struct svsm_pvalidate_call *pc)
-{
-	struct svsm_pvalidate_entry *pe;
-
-	/* Nothing in the CA yet */
-	pc->num_entries = 0;
-	pc->cur_index   = 0;
-
-	pe = &pc->entry[0];
-
-	while (pfn < pfn_end) {
-		pe->page_size = RMP_PG_SIZE_4K;
-		pe->action    = action;
-		pe->ignore_cf = 0;
-		pe->pfn       = pfn;
-
-		pe++;
-		pfn++;
-
-		pc->num_entries++;
-		if (pc->num_entries == SVSM_PVALIDATE_MAX_COUNT)
-			break;
-	}
-
-	return pfn;
-}
-
-static int svsm_build_ca_from_psc_desc(struct snp_psc_desc *desc, unsigned int desc_entry,
-				       struct svsm_pvalidate_call *pc)
-{
-	struct svsm_pvalidate_entry *pe;
-	struct psc_entry *e;
-
-	/* Nothing in the CA yet */
-	pc->num_entries = 0;
-	pc->cur_index   = 0;
-
-	pe = &pc->entry[0];
-	e  = &desc->entries[desc_entry];
-
-	while (desc_entry <= desc->hdr.end_entry) {
-		pe->page_size = e->pagesize ? RMP_PG_SIZE_2M : RMP_PG_SIZE_4K;
-		pe->action    = e->operation == SNP_PAGE_STATE_PRIVATE;
-		pe->ignore_cf = 0;
-		pe->pfn       = e->gfn;
-
-		pe++;
-		e++;
-
-		desc_entry++;
-		pc->num_entries++;
-		if (pc->num_entries == SVSM_PVALIDATE_MAX_COUNT)
-			break;
-	}
-
-	return desc_entry;
-}
-
-static void svsm_pval_pages(struct snp_psc_desc *desc)
-{
-	struct svsm_pvalidate_entry pv_4k[VMGEXIT_PSC_MAX_ENTRY];
-	unsigned int i, pv_4k_count = 0;
-	struct svsm_pvalidate_call *pc;
-	struct svsm_call call = {};
-	unsigned long flags;
-	bool action;
-	u64 pc_pa;
-	int ret;
-
-	/*
-	 * This can be called very early in the boot, use native functions in
-	 * order to avoid paravirt issues.
-	 */
-	flags = native_local_irq_save();
-
-	/*
-	 * The SVSM calling area (CA) can support processing 510 entries at a
-	 * time. Loop through the Page State Change descriptor until the CA is
-	 * full or the last entry in the descriptor is reached, at which time
-	 * the SVSM is invoked. This repeats until all entries in the descriptor
-	 * are processed.
-	 */
-	call.caa = svsm_get_caa();
-
-	pc = (struct svsm_pvalidate_call *)call.caa->svsm_buffer;
-	pc_pa = svsm_get_caa_pa() + offsetof(struct svsm_ca, svsm_buffer);
-
-	/* Protocol 0, Call ID 1 */
-	call.rax = SVSM_CORE_CALL(SVSM_CORE_PVALIDATE);
-	call.rcx = pc_pa;
-
-	for (i = 0; i <= desc->hdr.end_entry;) {
-		i = svsm_build_ca_from_psc_desc(desc, i, pc);
-
-		do {
-			ret = svsm_perform_call_protocol(&call);
-			if (!ret)
-				continue;
-
-			/*
-			 * Check if the entry failed because of an RMP mismatch (a
-			 * PVALIDATE at 2M was requested, but the page is mapped in
-			 * the RMP as 4K).
-			 */
-
-			if (call.rax_out == SVSM_PVALIDATE_FAIL_SIZEMISMATCH &&
-			    pc->entry[pc->cur_index].page_size == RMP_PG_SIZE_2M) {
-				/* Save this entry for post-processing at 4K */
-				pv_4k[pv_4k_count++] = pc->entry[pc->cur_index];
-
-				/* Skip to the next one unless at the end of the list */
-				pc->cur_index++;
-				if (pc->cur_index < pc->num_entries)
-					ret = -EAGAIN;
-				else
-					ret = 0;
-			}
-		} while (ret == -EAGAIN);
-
-		if (ret)
-			svsm_pval_terminate(pc, ret, call.rax_out);
-	}
-
-	/* Process any entries that failed to be validated at 2M and validate them at 4K */
-	for (i = 0; i < pv_4k_count; i++) {
-		u64 pfn, pfn_end;
-
-		action  = pv_4k[i].action;
-		pfn     = pv_4k[i].pfn;
-		pfn_end = pfn + 512;
-
-		while (pfn < pfn_end) {
-			pfn = svsm_build_ca_from_pfn_range(pfn, pfn_end, action, pc);
-
-			ret = svsm_perform_call_protocol(&call);
-			if (ret)
-				svsm_pval_terminate(pc, ret, call.rax_out);
-		}
-	}
-
-	native_local_irq_restore(flags);
-}
-
-static void pvalidate_pages(struct snp_psc_desc *desc)
-{
-	if (snp_vmpl)
-		svsm_pval_pages(desc);
-	else
-		pval_pages(desc);
-}
-
-static int vmgexit_psc(struct ghcb *ghcb, struct snp_psc_desc *desc)
-{
-	int cur_entry, end_entry, ret = 0;
-	struct snp_psc_desc *data;
-	struct es_em_ctxt ctxt;
-
-	vc_ghcb_invalidate(ghcb);
-
-	/* Copy the input desc into GHCB shared buffer */
-	data = (struct snp_psc_desc *)ghcb->shared_buffer;
-	memcpy(ghcb->shared_buffer, desc, min_t(int, GHCB_SHARED_BUF_SIZE, sizeof(*desc)));
-
-	/*
-	 * As per the GHCB specification, the hypervisor can resume the guest
-	 * before processing all the entries. Check whether all the entries
-	 * are processed. If not, then keep retrying. Note, the hypervisor
-	 * will update the data memory directly to indicate the status, so
-	 * reference the data->hdr everywhere.
-	 *
-	 * The strategy here is to wait for the hypervisor to change the page
-	 * state in the RMP table before guest accesses the memory pages. If the
-	 * page state change was not successful, then later memory access will
-	 * result in a crash.
-	 */
-	cur_entry = data->hdr.cur_entry;
-	end_entry = data->hdr.end_entry;
-
-	while (data->hdr.cur_entry <= data->hdr.end_entry) {
-		ghcb_set_sw_scratch(ghcb, (u64)__pa(data));
-
-		/* This will advance the shared buffer data points to. */
-		ret = sev_es_ghcb_hv_call(ghcb, &ctxt, SVM_VMGEXIT_PSC, 0, 0);
-
-		/*
-		 * Page State Change VMGEXIT can pass error code through
-		 * exit_info_2.
-		 */
-		if (WARN(ret || ghcb->save.sw_exit_info_2,
-			 "SNP: PSC failed ret=%d exit_info_2=%llx\n",
-			 ret, ghcb->save.sw_exit_info_2)) {
-			ret = 1;
-			goto out;
-		}
-
-		/* Verify that reserved bit is not set */
-		if (WARN(data->hdr.reserved, "Reserved bit is set in the PSC header\n")) {
-			ret = 1;
-			goto out;
-		}
-
-		/*
-		 * Sanity check that entry processing is not going backwards.
-		 * This will happen only if hypervisor is tricking us.
-		 */
-		if (WARN(data->hdr.end_entry > end_entry || cur_entry > data->hdr.cur_entry,
-"SNP: PSC processing going backward, end_entry %d (got %d) cur_entry %d (got %d)\n",
-			 end_entry, data->hdr.end_entry, cur_entry, data->hdr.cur_entry)) {
-			ret = 1;
-			goto out;
-		}
-	}
-
-out:
-	return ret;
-}
-
-static enum es_result vc_check_opcode_bytes(struct es_em_ctxt *ctxt,
-					    unsigned long exit_code)
-{
-	unsigned int opcode = (unsigned int)ctxt->insn.opcode.value;
-	u8 modrm = ctxt->insn.modrm.value;
-
-	switch (exit_code) {
-
-	case SVM_EXIT_IOIO:
-	case SVM_EXIT_NPF:
-		/* handled separately */
-		return ES_OK;
-
-	case SVM_EXIT_CPUID:
-		if (opcode == 0xa20f)
-			return ES_OK;
-		break;
-
-	case SVM_EXIT_INVD:
-		if (opcode == 0x080f)
-			return ES_OK;
-		break;
-
-	case SVM_EXIT_MONITOR:
-		/* MONITOR and MONITORX instructions generate the same error code */
-		if (opcode == 0x010f && (modrm == 0xc8 || modrm == 0xfa))
-			return ES_OK;
-		break;
-
-	case SVM_EXIT_MWAIT:
-		/* MWAIT and MWAITX instructions generate the same error code */
-		if (opcode == 0x010f && (modrm == 0xc9 || modrm == 0xfb))
-			return ES_OK;
-		break;
-
-	case SVM_EXIT_MSR:
-		/* RDMSR */
-		if (opcode == 0x320f ||
-		/* WRMSR */
-		    opcode == 0x300f)
-			return ES_OK;
-		break;
-
-	case SVM_EXIT_RDPMC:
-		if (opcode == 0x330f)
-			return ES_OK;
-		break;
-
-	case SVM_EXIT_RDTSC:
-		if (opcode == 0x310f)
-			return ES_OK;
-		break;
-
-	case SVM_EXIT_RDTSCP:
-		if (opcode == 0x010f && modrm == 0xf9)
-			return ES_OK;
-		break;
-
-	case SVM_EXIT_READ_DR7:
-		if (opcode == 0x210f &&
-		    X86_MODRM_REG(ctxt->insn.modrm.value) == 7)
-			return ES_OK;
-		break;
-
-	case SVM_EXIT_VMMCALL:
-		if (opcode == 0x010f && modrm == 0xd9)
-			return ES_OK;
-
-		break;
-
-	case SVM_EXIT_WRITE_DR7:
-		if (opcode == 0x230f &&
-		    X86_MODRM_REG(ctxt->insn.modrm.value) == 7)
-			return ES_OK;
-		break;
-
-	case SVM_EXIT_WBINVD:
-		if (opcode == 0x90f)
-			return ES_OK;
-		break;
-
-	default:
-		break;
-	}
-
-	sev_printk(KERN_ERR "Wrong/unhandled opcode bytes: 0x%x, exit_code: 0x%lx, rIP: 0x%lx\n",
-		   opcode, exit_code, ctxt->regs->ip);
-
-	return ES_UNSUPPORTED;
-}
-
 /*
  * Maintain the GPA of the SVSM Calling Area (CA) in order to utilize the SVSM
  * services needed when not running in VMPL0.
@@ -1681,7 +839,7 @@ static bool __head svsm_setup_ca(const struct cc_blob_sev_info *cc_info)
 	 * routine is running identity mapped when called, both by the decompressor
 	 * code and the early kernel code.
 	 */
-	if (!rmpadjust((unsigned long)&RIP_REL_REF(boot_ghcb_page), RMP_PG_SIZE_4K, 1))
+	if (!rmpadjust((unsigned long)rip_rel_ptr(&boot_ghcb_page), RMP_PG_SIZE_4K, 1))
 		return false;
 
 	/*
@@ -1698,7 +856,7 @@ static bool __head svsm_setup_ca(const struct cc_blob_sev_info *cc_info)
 	if (!secrets_page->svsm_guest_vmpl)
 		sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_SVSM_VMPL0);
 
-	RIP_REL_REF(snp_vmpl) = secrets_page->svsm_guest_vmpl;
+	snp_vmpl = secrets_page->svsm_guest_vmpl;
 
 	caa = secrets_page->svsm_caa;
 
@@ -1713,8 +871,8 @@ static bool __head svsm_setup_ca(const struct cc_blob_sev_info *cc_info)
 	 * The CA is identity mapped when this routine is called, both by the
 	 * decompressor code and the early kernel code.
 	 */
-	RIP_REL_REF(boot_svsm_caa) = (struct svsm_ca *)caa;
-	RIP_REL_REF(boot_svsm_caa_pa) = caa;
+	boot_svsm_caa = (struct svsm_ca *)caa;
+	boot_svsm_caa_pa = caa;
 
 	/* Advertise the SVSM presence via CPUID. */
 	cpuid_table = (struct snp_cpuid_table *)snp_cpuid_get_table();
diff --git a/arch/x86/boot/startup/sev-startup.c b/arch/x86/boot/startup/sev-startup.c
new file mode 100644
index 000000000000..435853a55768
--- /dev/null
+++ b/arch/x86/boot/startup/sev-startup.c
@@ -0,0 +1,368 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * AMD Memory Encryption Support
+ *
+ * Copyright (C) 2019 SUSE
+ *
+ * Author: Joerg Roedel <jroedel@suse.de>
+ */
+
+#define pr_fmt(fmt)	"SEV: " fmt
+
+#include <linux/percpu-defs.h>
+#include <linux/cc_platform.h>
+#include <linux/printk.h>
+#include <linux/mm_types.h>
+#include <linux/set_memory.h>
+#include <linux/memblock.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/cpumask.h>
+#include <linux/efi.h>
+#include <linux/io.h>
+#include <linux/psp-sev.h>
+#include <uapi/linux/sev-guest.h>
+
+#include <asm/init.h>
+#include <asm/cpu_entry_area.h>
+#include <asm/stacktrace.h>
+#include <asm/sev.h>
+#include <asm/sev-internal.h>
+#include <asm/insn-eval.h>
+#include <asm/fpu/xcr.h>
+#include <asm/processor.h>
+#include <asm/realmode.h>
+#include <asm/setup.h>
+#include <asm/traps.h>
+#include <asm/svm.h>
+#include <asm/smp.h>
+#include <asm/cpu.h>
+#include <asm/apic.h>
+#include <asm/cpuid.h>
+#include <asm/cmdline.h>
+
+/* For early boot hypervisor communication in SEV-ES enabled guests */
+struct ghcb boot_ghcb_page __bss_decrypted __aligned(PAGE_SIZE);
+
+/*
+ * Needs to be in the .data section because we need it NULL before bss is
+ * cleared
+ */
+struct ghcb *boot_ghcb __section(".data");
+
+/* Bitmap of SEV features supported by the hypervisor */
+u64 sev_hv_features __ro_after_init;
+
+/* Secrets page physical address from the CC blob */
+u64 sev_secrets_pa __ro_after_init;
+
+/* For early boot SVSM communication */
+struct svsm_ca boot_svsm_ca_page __aligned(PAGE_SIZE);
+
+DEFINE_PER_CPU(struct svsm_ca *, svsm_caa);
+DEFINE_PER_CPU(u64, svsm_caa_pa);
+
+/*
+ * Nothing shall interrupt this code path while holding the per-CPU
+ * GHCB. The backup GHCB is only for NMIs interrupting this path.
+ *
+ * Callers must disable local interrupts around it.
+ */
+noinstr struct ghcb *__sev_get_ghcb(struct ghcb_state *state)
+{
+	struct sev_es_runtime_data *data;
+	struct ghcb *ghcb;
+
+	WARN_ON(!irqs_disabled());
+
+	data = this_cpu_read(runtime_data);
+	ghcb = &data->ghcb_page;
+
+	if (unlikely(data->ghcb_active)) {
+		/* GHCB is already in use - save its contents */
+
+		if (unlikely(data->backup_ghcb_active)) {
+			/*
+			 * Backup-GHCB is also already in use. There is no way
+			 * to continue here so just kill the machine. To make
+			 * panic() work, mark GHCBs inactive so that messages
+			 * can be printed out.
+			 */
+			data->ghcb_active        = false;
+			data->backup_ghcb_active = false;
+
+			instrumentation_begin();
+			panic("Unable to handle #VC exception! GHCB and Backup GHCB are already in use");
+			instrumentation_end();
+		}
+
+		/* Mark backup_ghcb active before writing to it */
+		data->backup_ghcb_active = true;
+
+		state->ghcb = &data->backup_ghcb;
+
+		/* Backup GHCB content */
+		*state->ghcb = *ghcb;
+	} else {
+		state->ghcb = NULL;
+		data->ghcb_active = true;
+	}
+
+	return ghcb;
+}
+
+/* Include code shared with pre-decompression boot stage */
+#include "sev-shared.c"
+
+noinstr void __sev_put_ghcb(struct ghcb_state *state)
+{
+	struct sev_es_runtime_data *data;
+	struct ghcb *ghcb;
+
+	WARN_ON(!irqs_disabled());
+
+	data = this_cpu_read(runtime_data);
+	ghcb = &data->ghcb_page;
+
+	if (state->ghcb) {
+		/* Restore GHCB from Backup */
+		*ghcb = *state->ghcb;
+		data->backup_ghcb_active = false;
+		state->ghcb = NULL;
+	} else {
+		/*
+		 * Invalidate the GHCB so a VMGEXIT instruction issued
+		 * from userspace won't appear to be valid.
+		 */
+		vc_ghcb_invalidate(ghcb);
+		data->ghcb_active = false;
+	}
+}
+
+int svsm_perform_call_protocol(struct svsm_call *call)
+{
+	struct ghcb_state state;
+	unsigned long flags;
+	struct ghcb *ghcb;
+	int ret;
+
+	/*
+	 * This can be called very early in the boot, use native functions in
+	 * order to avoid paravirt issues.
+	 */
+	flags = native_local_irq_save();
+
+	if (sev_cfg.ghcbs_initialized)
+		ghcb = __sev_get_ghcb(&state);
+	else if (boot_ghcb)
+		ghcb = boot_ghcb;
+	else
+		ghcb = NULL;
+
+	do {
+		ret = ghcb ? svsm_perform_ghcb_protocol(ghcb, call)
+			   : svsm_perform_msr_protocol(call);
+	} while (ret == -EAGAIN);
+
+	if (sev_cfg.ghcbs_initialized)
+		__sev_put_ghcb(&state);
+
+	native_local_irq_restore(flags);
+
+	return ret;
+}
+
+void __head
+early_set_pages_state(unsigned long vaddr, unsigned long paddr,
+		      unsigned long npages, enum psc_op op)
+{
+	unsigned long paddr_end;
+	u64 val;
+
+	vaddr = vaddr & PAGE_MASK;
+
+	paddr = paddr & PAGE_MASK;
+	paddr_end = paddr + (npages << PAGE_SHIFT);
+
+	while (paddr < paddr_end) {
+		/* Page validation must be rescinded before changing to shared */
+		if (op == SNP_PAGE_STATE_SHARED)
+			pvalidate_4k_page(vaddr, paddr, false);
+
+		/*
+		 * Use the MSR protocol because this function can be called before
+		 * the GHCB is established.
+		 */
+		sev_es_wr_ghcb_msr(GHCB_MSR_PSC_REQ_GFN(paddr >> PAGE_SHIFT, op));
+		VMGEXIT();
+
+		val = sev_es_rd_ghcb_msr();
+
+		if (GHCB_RESP_CODE(val) != GHCB_MSR_PSC_RESP)
+			goto e_term;
+
+		if (GHCB_MSR_PSC_RESP_VAL(val))
+			goto e_term;
+
+		/* Page validation must be performed after changing to private */
+		if (op == SNP_PAGE_STATE_PRIVATE)
+			pvalidate_4k_page(vaddr, paddr, true);
+
+		vaddr += PAGE_SIZE;
+		paddr += PAGE_SIZE;
+	}
+
+	return;
+
+e_term:
+	sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PSC);
+}
+
+void __head early_snp_set_memory_private(unsigned long vaddr, unsigned long paddr,
+					 unsigned long npages)
+{
+	/*
+	 * This can be invoked in early boot while running identity mapped, so
+	 * use an open coded check for SNP instead of using cc_platform_has().
+	 * This eliminates worries about jump tables or checking boot_cpu_data
+	 * in the cc_platform_has() function.
+	 */
+	if (!(sev_status & MSR_AMD64_SEV_SNP_ENABLED))
+		return;
+
+	 /*
+	  * Ask the hypervisor to mark the memory pages as private in the RMP
+	  * table.
+	  */
+	early_set_pages_state(vaddr, paddr, npages, SNP_PAGE_STATE_PRIVATE);
+}
+
+void __head early_snp_set_memory_shared(unsigned long vaddr, unsigned long paddr,
+					unsigned long npages)
+{
+	/*
+	 * This can be invoked in early boot while running identity mapped, so
+	 * use an open coded check for SNP instead of using cc_platform_has().
+	 * This eliminates worries about jump tables or checking boot_cpu_data
+	 * in the cc_platform_has() function.
+	 */
+	if (!(sev_status & MSR_AMD64_SEV_SNP_ENABLED))
+		return;
+
+	 /* Ask hypervisor to mark the memory pages shared in the RMP table. */
+	early_set_pages_state(vaddr, paddr, npages, SNP_PAGE_STATE_SHARED);
+}
+
+/*
+ * Initial set up of SNP relies on information provided by the
+ * Confidential Computing blob, which can be passed to the kernel
+ * in the following ways, depending on how it is booted:
+ *
+ * - when booted via the boot/decompress kernel:
+ *   - via boot_params
+ *
+ * - when booted directly by firmware/bootloader (e.g. CONFIG_PVH):
+ *   - via a setup_data entry, as defined by the Linux Boot Protocol
+ *
+ * Scan for the blob in that order.
+ */
+static __head struct cc_blob_sev_info *find_cc_blob(struct boot_params *bp)
+{
+	struct cc_blob_sev_info *cc_info;
+
+	/* Boot kernel would have passed the CC blob via boot_params. */
+	if (bp->cc_blob_address) {
+		cc_info = (struct cc_blob_sev_info *)(unsigned long)bp->cc_blob_address;
+		goto found_cc_info;
+	}
+
+	/*
+	 * If kernel was booted directly, without the use of the
+	 * boot/decompression kernel, the CC blob may have been passed via
+	 * setup_data instead.
+	 */
+	cc_info = find_cc_blob_setup_data(bp);
+	if (!cc_info)
+		return NULL;
+
+found_cc_info:
+	if (cc_info->magic != CC_BLOB_SEV_HDR_MAGIC)
+		snp_abort();
+
+	return cc_info;
+}
+
+static __head void svsm_setup(struct cc_blob_sev_info *cc_info)
+{
+	struct svsm_call call = {};
+	int ret;
+	u64 pa;
+
+	/*
+	 * Record the SVSM Calling Area address (CAA) if the guest is not
+	 * running at VMPL0. The CA will be used to communicate with the
+	 * SVSM to perform the SVSM services.
+	 */
+	if (!svsm_setup_ca(cc_info))
+		return;
+
+	/*
+	 * It is very early in the boot and the kernel is running identity
+	 * mapped but without having adjusted the pagetables to where the
+	 * kernel was loaded (physbase), so the get the CA address using
+	 * RIP-relative addressing.
+	 */
+	pa = (u64)rip_rel_ptr(&boot_svsm_ca_page);
+
+	/*
+	 * Switch over to the boot SVSM CA while the current CA is still
+	 * addressable. There is no GHCB at this point so use the MSR protocol.
+	 *
+	 * SVSM_CORE_REMAP_CA call:
+	 *   RAX = 0 (Protocol=0, CallID=0)
+	 *   RCX = New CA GPA
+	 */
+	call.caa = svsm_get_caa();
+	call.rax = SVSM_CORE_CALL(SVSM_CORE_REMAP_CA);
+	call.rcx = pa;
+	ret = svsm_perform_call_protocol(&call);
+	if (ret)
+		sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_SVSM_CA_REMAP_FAIL);
+
+	boot_svsm_caa = (struct svsm_ca *)pa;
+	boot_svsm_caa_pa = pa;
+}
+
+bool __head snp_init(struct boot_params *bp)
+{
+	struct cc_blob_sev_info *cc_info;
+
+	if (!bp)
+		return false;
+
+	cc_info = find_cc_blob(bp);
+	if (!cc_info)
+		return false;
+
+	if (cc_info->secrets_phys && cc_info->secrets_len == PAGE_SIZE)
+		sev_secrets_pa = cc_info->secrets_phys;
+	else
+		return false;
+
+	setup_cpuid_table(cc_info);
+
+	svsm_setup(cc_info);
+
+	/*
+	 * The CC blob will be used later to access the secrets page. Cache
+	 * it here like the boot kernel does.
+	 */
+	bp->cc_blob_address = (u32)(unsigned long)cc_info;
+
+	return true;
+}
+
+void __head __noreturn snp_abort(void)
+{
+	sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SNP_UNSUPPORTED);
+}
diff --git a/arch/x86/mm/mem_encrypt_identity.c b/arch/x86/boot/startup/sme.c
index 5eecdd92da10..753cd2094080 100644
--- a/arch/x86/mm/mem_encrypt_identity.c
+++ b/arch/x86/boot/startup/sme.c
@@ -45,8 +45,6 @@
 #include <asm/coco.h>
 #include <asm/sev.h>
 
-#include "mm_internal.h"
-
 #define PGD_FLAGS		_KERNPG_TABLE_NOENC
 #define P4D_FLAGS		_KERNPG_TABLE_NOENC
 #define PUD_FLAGS		_KERNPG_TABLE_NOENC
@@ -299,8 +297,7 @@ void __head sme_encrypt_kernel(struct boot_params *bp)
 	 * instrumentation or checking boot_cpu_data in the cc_platform_has()
 	 * function.
 	 */
-	if (!sme_get_me_mask() ||
-	    RIP_REL_REF(sev_status) & MSR_AMD64_SEV_ENABLED)
+	if (!sme_get_me_mask() || sev_status & MSR_AMD64_SEV_ENABLED)
 		return;
 
 	/*
@@ -318,8 +315,8 @@ void __head sme_encrypt_kernel(struct boot_params *bp)
 	 *     memory from being cached.
 	 */
 
-	kernel_start = (unsigned long)RIP_REL_REF(_text);
-	kernel_end = ALIGN((unsigned long)RIP_REL_REF(_end), PMD_SIZE);
+	kernel_start = (unsigned long)rip_rel_ptr(_text);
+	kernel_end = ALIGN((unsigned long)rip_rel_ptr(_end), PMD_SIZE);
 	kernel_len = kernel_end - kernel_start;
 
 	initrd_start = 0;
@@ -345,7 +342,7 @@ void __head sme_encrypt_kernel(struct boot_params *bp)
 	 *   pagetable structures for the encryption of the kernel
 	 *   pagetable structures for workarea (in case not currently mapped)
 	 */
-	execute_start = workarea_start = (unsigned long)RIP_REL_REF(sme_workarea);
+	execute_start = workarea_start = (unsigned long)rip_rel_ptr(sme_workarea);
 	execute_end = execute_start + (PAGE_SIZE * 2) + PMD_SIZE;
 	execute_len = execute_end - execute_start;
 
@@ -526,7 +523,7 @@ void __head sme_enable(struct boot_params *bp)
 	me_mask = 1UL << (ebx & 0x3f);
 
 	/* Check the SEV MSR whether SEV or SME is enabled */
-	RIP_REL_REF(sev_status) = msr = __rdmsr(MSR_AMD64_SEV);
+	sev_status = msr = __rdmsr(MSR_AMD64_SEV);
 	feature_mask = (msr & MSR_AMD64_SEV_ENABLED) ? AMD_SEV_BIT : AMD_SME_BIT;
 
 	/*
@@ -562,8 +559,17 @@ void __head sme_enable(struct boot_params *bp)
 			return;
 	}
 
-	RIP_REL_REF(sme_me_mask) = me_mask;
-	RIP_REL_REF(physical_mask) &= ~me_mask;
-	RIP_REL_REF(cc_vendor) = CC_VENDOR_AMD;
+	sme_me_mask	= me_mask;
+	physical_mask	&= ~me_mask;
+	cc_vendor	= CC_VENDOR_AMD;
 	cc_set_mask(me_mask);
 }
+
+#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION
+/* Local version for startup code, which never operates on user page tables */
+__weak
+pgd_t __pti_set_user_pgtbl(pgd_t *pgdp, pgd_t pgd)
+{
+	return pgd;
+}
+#endif
diff --git a/arch/x86/boot/string.c b/arch/x86/boot/string.c
index 84f7a883ce1e..f35369bb14c5 100644
--- a/arch/x86/boot/string.c
+++ b/arch/x86/boot/string.c
@@ -32,7 +32,7 @@
 int memcmp(const void *s1, const void *s2, size_t len)
 {
 	bool diff;
-	asm("repe; cmpsb" CC_SET(nz)
+	asm("repe cmpsb" CC_SET(nz)
 	    : CC_OUT(nz) (diff), "+D" (s1), "+S" (s2), "+c" (len));
 	return diff;
 }
diff --git a/arch/x86/boot/video.c b/arch/x86/boot/video.c
index f2e96905b3fe..0641c8c46aee 100644
--- a/arch/x86/boot/video.c
+++ b/arch/x86/boot/video.c
@@ -292,7 +292,7 @@ static void restore_screen(void)
 			     "shrw %%cx ; "
 			     "jnc 1f ; "
 			     "stosw \n\t"
-			     "1: rep;stosl ; "
+			     "1: rep stosl ; "
 			     "popw %%es"
 			     : "+D" (dst), "+c" (npad)
 			     : "bdS" (video_segment),
diff --git a/arch/x86/coco/core.c b/arch/x86/coco/core.c
index 9a0ddda3aa69..d4610af68114 100644
--- a/arch/x86/coco/core.c
+++ b/arch/x86/coco/core.c
@@ -18,7 +18,9 @@
 #include <asm/processor.h>
 
 enum cc_vendor cc_vendor __ro_after_init = CC_VENDOR_NONE;
+SYM_PIC_ALIAS(cc_vendor);
 u64 cc_mask __ro_after_init;
+SYM_PIC_ALIAS(cc_mask);
 
 static struct cc_attr_flags {
 	__u64 host_sev_snp	: 1,
diff --git a/arch/x86/coco/sev/Makefile b/arch/x86/coco/sev/Makefile
index dcb06dc8b5ae..db3255b979bd 100644
--- a/arch/x86/coco/sev/Makefile
+++ b/arch/x86/coco/sev/Makefile
@@ -1,22 +1,9 @@
 # SPDX-License-Identifier: GPL-2.0
 
-obj-y += core.o
-
-# jump tables are emitted using absolute references in non-PIC code
-# so they cannot be used in the early SEV startup code
-CFLAGS_core.o += -fno-jump-tables
-
-ifdef CONFIG_FUNCTION_TRACER
-CFLAGS_REMOVE_core.o = -pg
-endif
-
-KASAN_SANITIZE_core.o	:= n
-KMSAN_SANITIZE_core.o	:= n
-KCOV_INSTRUMENT_core.o	:= n
-
-# With some compiler versions the generated code results in boot hangs, caused
-# by several compilation units. To be safe, disable all instrumentation.
-KCSAN_SANITIZE		:= n
+obj-y += core.o sev-nmi.o vc-handle.o
 
 # Clang 14 and older may fail to respect __no_sanitize_undefined when inlining
-UBSAN_SANITIZE		:= n
+UBSAN_SANITIZE_sev-nmi.o	:= n
+
+# GCC may fail to respect __no_sanitize_address when inlining
+KASAN_SANITIZE_sev-nmi.o	:= n
diff --git a/arch/x86/coco/sev/core.c b/arch/x86/coco/sev/core.c
index b0c1a7a57497..ac400525de73 100644
--- a/arch/x86/coco/sev/core.c
+++ b/arch/x86/coco/sev/core.c
@@ -31,6 +31,7 @@
 #include <asm/cpu_entry_area.h>
 #include <asm/stacktrace.h>
 #include <asm/sev.h>
+#include <asm/sev-internal.h>
 #include <asm/insn-eval.h>
 #include <asm/fpu/xcr.h>
 #include <asm/processor.h>
@@ -44,8 +45,6 @@
 #include <asm/cpuid.h>
 #include <asm/cmdline.h>
 
-#define DR7_RESET_VALUE        0x400
-
 /* AP INIT values as documented in the APM2  section "Processor Initialization State" */
 #define AP_INIT_CS_LIMIT		0xffff
 #define AP_INIT_DS_LIMIT		0xffff
@@ -81,21 +80,6 @@ static const char * const sev_status_feat_names[] = {
 	[MSR_AMD64_SNP_SMT_PROT_BIT]		= "SMTProt",
 };
 
-/* For early boot hypervisor communication in SEV-ES enabled guests */
-static struct ghcb boot_ghcb_page __bss_decrypted __aligned(PAGE_SIZE);
-
-/*
- * Needs to be in the .data section because we need it NULL before bss is
- * cleared
- */
-static struct ghcb *boot_ghcb __section(".data");
-
-/* Bitmap of SEV features supported by the hypervisor */
-static u64 sev_hv_features __ro_after_init;
-
-/* Secrets page physical address from the CC blob */
-static u64 secrets_pa __ro_after_init;
-
 /*
  * For Secure TSC guests, the BSP fetches TSC_INFO using SNP guest messaging and
  * initializes snp_tsc_scale and snp_tsc_offset. These values are replicated
@@ -105,558 +89,196 @@ static u64 snp_tsc_scale __ro_after_init;
 static u64 snp_tsc_offset __ro_after_init;
 static u64 snp_tsc_freq_khz __ro_after_init;
 
-/* #VC handler runtime per-CPU data */
-struct sev_es_runtime_data {
-	struct ghcb ghcb_page;
-
-	/*
-	 * Reserve one page per CPU as backup storage for the unencrypted GHCB.
-	 * It is needed when an NMI happens while the #VC handler uses the real
-	 * GHCB, and the NMI handler itself is causing another #VC exception. In
-	 * that case the GHCB content of the first handler needs to be backed up
-	 * and restored.
-	 */
-	struct ghcb backup_ghcb;
-
-	/*
-	 * Mark the per-cpu GHCBs as in-use to detect nested #VC exceptions.
-	 * There is no need for it to be atomic, because nothing is written to
-	 * the GHCB between the read and the write of ghcb_active. So it is safe
-	 * to use it when a nested #VC exception happens before the write.
-	 *
-	 * This is necessary for example in the #VC->NMI->#VC case when the NMI
-	 * happens while the first #VC handler uses the GHCB. When the NMI code
-	 * raises a second #VC handler it might overwrite the contents of the
-	 * GHCB written by the first handler. To avoid this the content of the
-	 * GHCB is saved and restored when the GHCB is detected to be in use
-	 * already.
-	 */
-	bool ghcb_active;
-	bool backup_ghcb_active;
-
-	/*
-	 * Cached DR7 value - write it on DR7 writes and return it on reads.
-	 * That value will never make it to the real hardware DR7 as debugging
-	 * is currently unsupported in SEV-ES guests.
-	 */
-	unsigned long dr7;
-};
-
-struct ghcb_state {
-	struct ghcb *ghcb;
-};
-
-/* For early boot SVSM communication */
-static struct svsm_ca boot_svsm_ca_page __aligned(PAGE_SIZE);
-
-static DEFINE_PER_CPU(struct sev_es_runtime_data*, runtime_data);
-static DEFINE_PER_CPU(struct sev_es_save_area *, sev_vmsa);
-static DEFINE_PER_CPU(struct svsm_ca *, svsm_caa);
-static DEFINE_PER_CPU(u64, svsm_caa_pa);
-
-static __always_inline bool on_vc_stack(struct pt_regs *regs)
-{
-	unsigned long sp = regs->sp;
-
-	/* User-mode RSP is not trusted */
-	if (user_mode(regs))
-		return false;
-
-	/* SYSCALL gap still has user-mode RSP */
-	if (ip_within_syscall_gap(regs))
-		return false;
-
-	return ((sp >= __this_cpu_ist_bottom_va(VC)) && (sp < __this_cpu_ist_top_va(VC)));
-}
+DEFINE_PER_CPU(struct sev_es_runtime_data*, runtime_data);
+DEFINE_PER_CPU(struct sev_es_save_area *, sev_vmsa);
 
 /*
- * This function handles the case when an NMI is raised in the #VC
- * exception handler entry code, before the #VC handler has switched off
- * its IST stack. In this case, the IST entry for #VC must be adjusted,
- * so that any nested #VC exception will not overwrite the stack
- * contents of the interrupted #VC handler.
- *
- * The IST entry is adjusted unconditionally so that it can be also be
- * unconditionally adjusted back in __sev_es_ist_exit(). Otherwise a
- * nested sev_es_ist_exit() call may adjust back the IST entry too
- * early.
- *
- * The __sev_es_ist_enter() and __sev_es_ist_exit() functions always run
- * on the NMI IST stack, as they are only called from NMI handling code
- * right now.
+ * SVSM related information:
+ *   When running under an SVSM, the VMPL that Linux is executing at must be
+ *   non-zero. The VMPL is therefore used to indicate the presence of an SVSM.
  */
-void noinstr __sev_es_ist_enter(struct pt_regs *regs)
-{
-	unsigned long old_ist, new_ist;
-
-	/* Read old IST entry */
-	new_ist = old_ist = __this_cpu_read(cpu_tss_rw.x86_tss.ist[IST_INDEX_VC]);
-
-	/*
-	 * If NMI happened while on the #VC IST stack, set the new IST
-	 * value below regs->sp, so that the interrupted stack frame is
-	 * not overwritten by subsequent #VC exceptions.
-	 */
-	if (on_vc_stack(regs))
-		new_ist = regs->sp;
-
-	/*
-	 * Reserve additional 8 bytes and store old IST value so this
-	 * adjustment can be unrolled in __sev_es_ist_exit().
-	 */
-	new_ist -= sizeof(old_ist);
-	*(unsigned long *)new_ist = old_ist;
-
-	/* Set new IST entry */
-	this_cpu_write(cpu_tss_rw.x86_tss.ist[IST_INDEX_VC], new_ist);
-}
+u8 snp_vmpl __ro_after_init;
+EXPORT_SYMBOL_GPL(snp_vmpl);
 
-void noinstr __sev_es_ist_exit(void)
+static u64 __init get_snp_jump_table_addr(void)
 {
-	unsigned long ist;
+	struct snp_secrets_page *secrets;
+	void __iomem *mem;
+	u64 addr;
 
-	/* Read IST entry */
-	ist = __this_cpu_read(cpu_tss_rw.x86_tss.ist[IST_INDEX_VC]);
+	mem = ioremap_encrypted(sev_secrets_pa, PAGE_SIZE);
+	if (!mem) {
+		pr_err("Unable to locate AP jump table address: failed to map the SNP secrets page.\n");
+		return 0;
+	}
 
-	if (WARN_ON(ist == __this_cpu_ist_top_va(VC)))
-		return;
+	secrets = (__force struct snp_secrets_page *)mem;
 
-	/* Read back old IST entry and write it to the TSS */
-	this_cpu_write(cpu_tss_rw.x86_tss.ist[IST_INDEX_VC], *(unsigned long *)ist);
+	addr = secrets->os_area.ap_jump_table_pa;
+	iounmap(mem);
+
+	return addr;
 }
 
-/*
- * Nothing shall interrupt this code path while holding the per-CPU
- * GHCB. The backup GHCB is only for NMIs interrupting this path.
- *
- * Callers must disable local interrupts around it.
- */
-static noinstr struct ghcb *__sev_get_ghcb(struct ghcb_state *state)
+static u64 __init get_jump_table_addr(void)
 {
-	struct sev_es_runtime_data *data;
+	struct ghcb_state state;
+	unsigned long flags;
 	struct ghcb *ghcb;
+	u64 ret = 0;
 
-	WARN_ON(!irqs_disabled());
-
-	data = this_cpu_read(runtime_data);
-	ghcb = &data->ghcb_page;
-
-	if (unlikely(data->ghcb_active)) {
-		/* GHCB is already in use - save its contents */
-
-		if (unlikely(data->backup_ghcb_active)) {
-			/*
-			 * Backup-GHCB is also already in use. There is no way
-			 * to continue here so just kill the machine. To make
-			 * panic() work, mark GHCBs inactive so that messages
-			 * can be printed out.
-			 */
-			data->ghcb_active        = false;
-			data->backup_ghcb_active = false;
-
-			instrumentation_begin();
-			panic("Unable to handle #VC exception! GHCB and Backup GHCB are already in use");
-			instrumentation_end();
-		}
-
-		/* Mark backup_ghcb active before writing to it */
-		data->backup_ghcb_active = true;
+	if (cc_platform_has(CC_ATTR_GUEST_SEV_SNP))
+		return get_snp_jump_table_addr();
 
-		state->ghcb = &data->backup_ghcb;
+	local_irq_save(flags);
 
-		/* Backup GHCB content */
-		*state->ghcb = *ghcb;
-	} else {
-		state->ghcb = NULL;
-		data->ghcb_active = true;
-	}
+	ghcb = __sev_get_ghcb(&state);
 
-	return ghcb;
-}
+	vc_ghcb_invalidate(ghcb);
+	ghcb_set_sw_exit_code(ghcb, SVM_VMGEXIT_AP_JUMP_TABLE);
+	ghcb_set_sw_exit_info_1(ghcb, SVM_VMGEXIT_GET_AP_JUMP_TABLE);
+	ghcb_set_sw_exit_info_2(ghcb, 0);
 
-static inline u64 sev_es_rd_ghcb_msr(void)
-{
-	return __rdmsr(MSR_AMD64_SEV_ES_GHCB);
-}
+	sev_es_wr_ghcb_msr(__pa(ghcb));
+	VMGEXIT();
 
-static __always_inline void sev_es_wr_ghcb_msr(u64 val)
-{
-	u32 low, high;
+	if (ghcb_sw_exit_info_1_is_valid(ghcb) &&
+	    ghcb_sw_exit_info_2_is_valid(ghcb))
+		ret = ghcb->save.sw_exit_info_2;
 
-	low  = (u32)(val);
-	high = (u32)(val >> 32);
+	__sev_put_ghcb(&state);
 
-	native_wrmsr(MSR_AMD64_SEV_ES_GHCB, low, high);
-}
+	local_irq_restore(flags);
 
-static int vc_fetch_insn_kernel(struct es_em_ctxt *ctxt,
-				unsigned char *buffer)
-{
-	return copy_from_kernel_nofault(buffer, (unsigned char *)ctxt->regs->ip, MAX_INSN_SIZE);
+	return ret;
 }
 
-static enum es_result __vc_decode_user_insn(struct es_em_ctxt *ctxt)
+static inline void __pval_terminate(u64 pfn, bool action, unsigned int page_size,
+				    int ret, u64 svsm_ret)
 {
-	char buffer[MAX_INSN_SIZE];
-	int insn_bytes;
-
-	insn_bytes = insn_fetch_from_user_inatomic(ctxt->regs, buffer);
-	if (insn_bytes == 0) {
-		/* Nothing could be copied */
-		ctxt->fi.vector     = X86_TRAP_PF;
-		ctxt->fi.error_code = X86_PF_INSTR | X86_PF_USER;
-		ctxt->fi.cr2        = ctxt->regs->ip;
-		return ES_EXCEPTION;
-	} else if (insn_bytes == -EINVAL) {
-		/* Effective RIP could not be calculated */
-		ctxt->fi.vector     = X86_TRAP_GP;
-		ctxt->fi.error_code = 0;
-		ctxt->fi.cr2        = 0;
-		return ES_EXCEPTION;
-	}
-
-	if (!insn_decode_from_regs(&ctxt->insn, ctxt->regs, buffer, insn_bytes))
-		return ES_DECODE_FAILED;
+	WARN(1, "PVALIDATE failure: pfn: 0x%llx, action: %u, size: %u, ret: %d, svsm_ret: 0x%llx\n",
+	     pfn, action, page_size, ret, svsm_ret);
 
-	if (ctxt->insn.immediate.got)
-		return ES_OK;
-	else
-		return ES_DECODE_FAILED;
+	sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PVALIDATE);
 }
 
-static enum es_result __vc_decode_kern_insn(struct es_em_ctxt *ctxt)
+static void svsm_pval_terminate(struct svsm_pvalidate_call *pc, int ret, u64 svsm_ret)
 {
-	char buffer[MAX_INSN_SIZE];
-	int res, ret;
+	unsigned int page_size;
+	bool action;
+	u64 pfn;
 
-	res = vc_fetch_insn_kernel(ctxt, buffer);
-	if (res) {
-		ctxt->fi.vector     = X86_TRAP_PF;
-		ctxt->fi.error_code = X86_PF_INSTR;
-		ctxt->fi.cr2        = ctxt->regs->ip;
-		return ES_EXCEPTION;
-	}
+	pfn = pc->entry[pc->cur_index].pfn;
+	action = pc->entry[pc->cur_index].action;
+	page_size = pc->entry[pc->cur_index].page_size;
 
-	ret = insn_decode(&ctxt->insn, buffer, MAX_INSN_SIZE, INSN_MODE_64);
-	if (ret < 0)
-		return ES_DECODE_FAILED;
-	else
-		return ES_OK;
+	__pval_terminate(pfn, action, page_size, ret, svsm_ret);
 }
 
-static enum es_result vc_decode_insn(struct es_em_ctxt *ctxt)
+static void pval_pages(struct snp_psc_desc *desc)
 {
-	if (user_mode(ctxt->regs))
-		return __vc_decode_user_insn(ctxt);
-	else
-		return __vc_decode_kern_insn(ctxt);
-}
+	struct psc_entry *e;
+	unsigned long vaddr;
+	unsigned int size;
+	unsigned int i;
+	bool validate;
+	u64 pfn;
+	int rc;
 
-static enum es_result vc_write_mem(struct es_em_ctxt *ctxt,
-				   char *dst, char *buf, size_t size)
-{
-	unsigned long error_code = X86_PF_PROT | X86_PF_WRITE;
+	for (i = 0; i <= desc->hdr.end_entry; i++) {
+		e = &desc->entries[i];
 
-	/*
-	 * This function uses __put_user() independent of whether kernel or user
-	 * memory is accessed. This works fine because __put_user() does no
-	 * sanity checks of the pointer being accessed. All that it does is
-	 * to report when the access failed.
-	 *
-	 * Also, this function runs in atomic context, so __put_user() is not
-	 * allowed to sleep. The page-fault handler detects that it is running
-	 * in atomic context and will not try to take mmap_sem and handle the
-	 * fault, so additional pagefault_enable()/disable() calls are not
-	 * needed.
-	 *
-	 * The access can't be done via copy_to_user() here because
-	 * vc_write_mem() must not use string instructions to access unsafe
-	 * memory. The reason is that MOVS is emulated by the #VC handler by
-	 * splitting the move up into a read and a write and taking a nested #VC
-	 * exception on whatever of them is the MMIO access. Using string
-	 * instructions here would cause infinite nesting.
-	 */
-	switch (size) {
-	case 1: {
-		u8 d1;
-		u8 __user *target = (u8 __user *)dst;
-
-		memcpy(&d1, buf, 1);
-		if (__put_user(d1, target))
-			goto fault;
-		break;
-	}
-	case 2: {
-		u16 d2;
-		u16 __user *target = (u16 __user *)dst;
+		pfn = e->gfn;
+		vaddr = (unsigned long)pfn_to_kaddr(pfn);
+		size = e->pagesize ? RMP_PG_SIZE_2M : RMP_PG_SIZE_4K;
+		validate = e->operation == SNP_PAGE_STATE_PRIVATE;
 
-		memcpy(&d2, buf, 2);
-		if (__put_user(d2, target))
-			goto fault;
-		break;
-	}
-	case 4: {
-		u32 d4;
-		u32 __user *target = (u32 __user *)dst;
+		rc = pvalidate(vaddr, size, validate);
+		if (!rc)
+			continue;
 
-		memcpy(&d4, buf, 4);
-		if (__put_user(d4, target))
-			goto fault;
-		break;
-	}
-	case 8: {
-		u64 d8;
-		u64 __user *target = (u64 __user *)dst;
+		if (rc == PVALIDATE_FAIL_SIZEMISMATCH && size == RMP_PG_SIZE_2M) {
+			unsigned long vaddr_end = vaddr + PMD_SIZE;
 
-		memcpy(&d8, buf, 8);
-		if (__put_user(d8, target))
-			goto fault;
-		break;
-	}
-	default:
-		WARN_ONCE(1, "%s: Invalid size: %zu\n", __func__, size);
-		return ES_UNSUPPORTED;
+			for (; vaddr < vaddr_end; vaddr += PAGE_SIZE, pfn++) {
+				rc = pvalidate(vaddr, RMP_PG_SIZE_4K, validate);
+				if (rc)
+					__pval_terminate(pfn, validate, RMP_PG_SIZE_4K, rc, 0);
+			}
+		} else {
+			__pval_terminate(pfn, validate, size, rc, 0);
+		}
 	}
-
-	return ES_OK;
-
-fault:
-	if (user_mode(ctxt->regs))
-		error_code |= X86_PF_USER;
-
-	ctxt->fi.vector = X86_TRAP_PF;
-	ctxt->fi.error_code = error_code;
-	ctxt->fi.cr2 = (unsigned long)dst;
-
-	return ES_EXCEPTION;
 }
 
-static enum es_result vc_read_mem(struct es_em_ctxt *ctxt,
-				  char *src, char *buf, size_t size)
+static u64 svsm_build_ca_from_pfn_range(u64 pfn, u64 pfn_end, bool action,
+					struct svsm_pvalidate_call *pc)
 {
-	unsigned long error_code = X86_PF_PROT;
-
-	/*
-	 * This function uses __get_user() independent of whether kernel or user
-	 * memory is accessed. This works fine because __get_user() does no
-	 * sanity checks of the pointer being accessed. All that it does is
-	 * to report when the access failed.
-	 *
-	 * Also, this function runs in atomic context, so __get_user() is not
-	 * allowed to sleep. The page-fault handler detects that it is running
-	 * in atomic context and will not try to take mmap_sem and handle the
-	 * fault, so additional pagefault_enable()/disable() calls are not
-	 * needed.
-	 *
-	 * The access can't be done via copy_from_user() here because
-	 * vc_read_mem() must not use string instructions to access unsafe
-	 * memory. The reason is that MOVS is emulated by the #VC handler by
-	 * splitting the move up into a read and a write and taking a nested #VC
-	 * exception on whatever of them is the MMIO access. Using string
-	 * instructions here would cause infinite nesting.
-	 */
-	switch (size) {
-	case 1: {
-		u8 d1;
-		u8 __user *s = (u8 __user *)src;
-
-		if (__get_user(d1, s))
-			goto fault;
-		memcpy(buf, &d1, 1);
-		break;
-	}
-	case 2: {
-		u16 d2;
-		u16 __user *s = (u16 __user *)src;
-
-		if (__get_user(d2, s))
-			goto fault;
-		memcpy(buf, &d2, 2);
-		break;
-	}
-	case 4: {
-		u32 d4;
-		u32 __user *s = (u32 __user *)src;
-
-		if (__get_user(d4, s))
-			goto fault;
-		memcpy(buf, &d4, 4);
-		break;
-	}
-	case 8: {
-		u64 d8;
-		u64 __user *s = (u64 __user *)src;
-		if (__get_user(d8, s))
-			goto fault;
-		memcpy(buf, &d8, 8);
-		break;
-	}
-	default:
-		WARN_ONCE(1, "%s: Invalid size: %zu\n", __func__, size);
-		return ES_UNSUPPORTED;
-	}
-
-	return ES_OK;
-
-fault:
-	if (user_mode(ctxt->regs))
-		error_code |= X86_PF_USER;
+	struct svsm_pvalidate_entry *pe;
 
-	ctxt->fi.vector = X86_TRAP_PF;
-	ctxt->fi.error_code = error_code;
-	ctxt->fi.cr2 = (unsigned long)src;
+	/* Nothing in the CA yet */
+	pc->num_entries = 0;
+	pc->cur_index   = 0;
 
-	return ES_EXCEPTION;
-}
+	pe = &pc->entry[0];
 
-static enum es_result vc_slow_virt_to_phys(struct ghcb *ghcb, struct es_em_ctxt *ctxt,
-					   unsigned long vaddr, phys_addr_t *paddr)
-{
-	unsigned long va = (unsigned long)vaddr;
-	unsigned int level;
-	phys_addr_t pa;
-	pgd_t *pgd;
-	pte_t *pte;
+	while (pfn < pfn_end) {
+		pe->page_size = RMP_PG_SIZE_4K;
+		pe->action    = action;
+		pe->ignore_cf = 0;
+		pe->pfn       = pfn;
 
-	pgd = __va(read_cr3_pa());
-	pgd = &pgd[pgd_index(va)];
-	pte = lookup_address_in_pgd(pgd, va, &level);
-	if (!pte) {
-		ctxt->fi.vector     = X86_TRAP_PF;
-		ctxt->fi.cr2        = vaddr;
-		ctxt->fi.error_code = 0;
+		pe++;
+		pfn++;
 
-		if (user_mode(ctxt->regs))
-			ctxt->fi.error_code |= X86_PF_USER;
-
-		return ES_EXCEPTION;
+		pc->num_entries++;
+		if (pc->num_entries == SVSM_PVALIDATE_MAX_COUNT)
+			break;
 	}
 
-	if (WARN_ON_ONCE(pte_val(*pte) & _PAGE_ENC))
-		/* Emulated MMIO to/from encrypted memory not supported */
-		return ES_UNSUPPORTED;
-
-	pa = (phys_addr_t)pte_pfn(*pte) << PAGE_SHIFT;
-	pa |= va & ~page_level_mask(level);
-
-	*paddr = pa;
-
-	return ES_OK;
+	return pfn;
 }
 
-static enum es_result vc_ioio_check(struct es_em_ctxt *ctxt, u16 port, size_t size)
+static int svsm_build_ca_from_psc_desc(struct snp_psc_desc *desc, unsigned int desc_entry,
+				       struct svsm_pvalidate_call *pc)
 {
-	BUG_ON(size > 4);
-
-	if (user_mode(ctxt->regs)) {
-		struct thread_struct *t = &current->thread;
-		struct io_bitmap *iobm = t->io_bitmap;
-		size_t idx;
-
-		if (!iobm)
-			goto fault;
-
-		for (idx = port; idx < port + size; ++idx) {
-			if (test_bit(idx, iobm->bitmap))
-				goto fault;
-		}
-	}
-
-	return ES_OK;
+	struct svsm_pvalidate_entry *pe;
+	struct psc_entry *e;
 
-fault:
-	ctxt->fi.vector = X86_TRAP_GP;
-	ctxt->fi.error_code = 0;
+	/* Nothing in the CA yet */
+	pc->num_entries = 0;
+	pc->cur_index   = 0;
 
-	return ES_EXCEPTION;
-}
+	pe = &pc->entry[0];
+	e  = &desc->entries[desc_entry];
 
-static __always_inline void vc_forward_exception(struct es_em_ctxt *ctxt)
-{
-	long error_code = ctxt->fi.error_code;
-	int trapnr = ctxt->fi.vector;
+	while (desc_entry <= desc->hdr.end_entry) {
+		pe->page_size = e->pagesize ? RMP_PG_SIZE_2M : RMP_PG_SIZE_4K;
+		pe->action    = e->operation == SNP_PAGE_STATE_PRIVATE;
+		pe->ignore_cf = 0;
+		pe->pfn       = e->gfn;
 
-	ctxt->regs->orig_ax = ctxt->fi.error_code;
+		pe++;
+		e++;
 
-	switch (trapnr) {
-	case X86_TRAP_GP:
-		exc_general_protection(ctxt->regs, error_code);
-		break;
-	case X86_TRAP_UD:
-		exc_invalid_op(ctxt->regs);
-		break;
-	case X86_TRAP_PF:
-		write_cr2(ctxt->fi.cr2);
-		exc_page_fault(ctxt->regs, error_code);
-		break;
-	case X86_TRAP_AC:
-		exc_alignment_check(ctxt->regs, error_code);
-		break;
-	default:
-		pr_emerg("Unsupported exception in #VC instruction emulation - can't continue\n");
-		BUG();
+		desc_entry++;
+		pc->num_entries++;
+		if (pc->num_entries == SVSM_PVALIDATE_MAX_COUNT)
+			break;
 	}
-}
-
-/* Include code shared with pre-decompression boot stage */
-#include "shared.c"
-
-static inline struct svsm_ca *svsm_get_caa(void)
-{
-	/*
-	 * Use rIP-relative references when called early in the boot. If
-	 * ->use_cas is set, then it is late in the boot and no need
-	 * to worry about rIP-relative references.
-	 */
-	if (RIP_REL_REF(sev_cfg).use_cas)
-		return this_cpu_read(svsm_caa);
-	else
-		return RIP_REL_REF(boot_svsm_caa);
-}
-
-static u64 svsm_get_caa_pa(void)
-{
-	/*
-	 * Use rIP-relative references when called early in the boot. If
-	 * ->use_cas is set, then it is late in the boot and no need
-	 * to worry about rIP-relative references.
-	 */
-	if (RIP_REL_REF(sev_cfg).use_cas)
-		return this_cpu_read(svsm_caa_pa);
-	else
-		return RIP_REL_REF(boot_svsm_caa_pa);
-}
-
-static noinstr void __sev_put_ghcb(struct ghcb_state *state)
-{
-	struct sev_es_runtime_data *data;
-	struct ghcb *ghcb;
-
-	WARN_ON(!irqs_disabled());
-
-	data = this_cpu_read(runtime_data);
-	ghcb = &data->ghcb_page;
 
-	if (state->ghcb) {
-		/* Restore GHCB from Backup */
-		*ghcb = *state->ghcb;
-		data->backup_ghcb_active = false;
-		state->ghcb = NULL;
-	} else {
-		/*
-		 * Invalidate the GHCB so a VMGEXIT instruction issued
-		 * from userspace won't appear to be valid.
-		 */
-		vc_ghcb_invalidate(ghcb);
-		data->ghcb_active = false;
-	}
+	return desc_entry;
 }
 
-static int svsm_perform_call_protocol(struct svsm_call *call)
+static void svsm_pval_pages(struct snp_psc_desc *desc)
 {
-	struct ghcb_state state;
+	struct svsm_pvalidate_entry pv_4k[VMGEXIT_PSC_MAX_ENTRY];
+	unsigned int i, pv_4k_count = 0;
+	struct svsm_pvalidate_call *pc;
+	struct svsm_call call = {};
 	unsigned long flags;
-	struct ghcb *ghcb;
+	bool action;
+	u64 pc_pa;
 	int ret;
 
 	/*
@@ -666,180 +288,145 @@ static int svsm_perform_call_protocol(struct svsm_call *call)
 	flags = native_local_irq_save();
 
 	/*
-	 * Use rip-relative references when called early in the boot. If
-	 * ghcbs_initialized is set, then it is late in the boot and no need
-	 * to worry about rip-relative references in called functions.
+	 * The SVSM calling area (CA) can support processing 510 entries at a
+	 * time. Loop through the Page State Change descriptor until the CA is
+	 * full or the last entry in the descriptor is reached, at which time
+	 * the SVSM is invoked. This repeats until all entries in the descriptor
+	 * are processed.
 	 */
-	if (RIP_REL_REF(sev_cfg).ghcbs_initialized)
-		ghcb = __sev_get_ghcb(&state);
-	else if (RIP_REL_REF(boot_ghcb))
-		ghcb = RIP_REL_REF(boot_ghcb);
-	else
-		ghcb = NULL;
+	call.caa = svsm_get_caa();
 
-	do {
-		ret = ghcb ? svsm_perform_ghcb_protocol(ghcb, call)
-			   : svsm_perform_msr_protocol(call);
-	} while (ret == -EAGAIN);
+	pc = (struct svsm_pvalidate_call *)call.caa->svsm_buffer;
+	pc_pa = svsm_get_caa_pa() + offsetof(struct svsm_ca, svsm_buffer);
 
-	if (RIP_REL_REF(sev_cfg).ghcbs_initialized)
-		__sev_put_ghcb(&state);
+	/* Protocol 0, Call ID 1 */
+	call.rax = SVSM_CORE_CALL(SVSM_CORE_PVALIDATE);
+	call.rcx = pc_pa;
 
-	native_local_irq_restore(flags);
+	for (i = 0; i <= desc->hdr.end_entry;) {
+		i = svsm_build_ca_from_psc_desc(desc, i, pc);
 
-	return ret;
-}
+		do {
+			ret = svsm_perform_call_protocol(&call);
+			if (!ret)
+				continue;
 
-void noinstr __sev_es_nmi_complete(void)
-{
-	struct ghcb_state state;
-	struct ghcb *ghcb;
+			/*
+			 * Check if the entry failed because of an RMP mismatch (a
+			 * PVALIDATE at 2M was requested, but the page is mapped in
+			 * the RMP as 4K).
+			 */
 
-	ghcb = __sev_get_ghcb(&state);
+			if (call.rax_out == SVSM_PVALIDATE_FAIL_SIZEMISMATCH &&
+			    pc->entry[pc->cur_index].page_size == RMP_PG_SIZE_2M) {
+				/* Save this entry for post-processing at 4K */
+				pv_4k[pv_4k_count++] = pc->entry[pc->cur_index];
+
+				/* Skip to the next one unless at the end of the list */
+				pc->cur_index++;
+				if (pc->cur_index < pc->num_entries)
+					ret = -EAGAIN;
+				else
+					ret = 0;
+			}
+		} while (ret == -EAGAIN);
 
-	vc_ghcb_invalidate(ghcb);
-	ghcb_set_sw_exit_code(ghcb, SVM_VMGEXIT_NMI_COMPLETE);
-	ghcb_set_sw_exit_info_1(ghcb, 0);
-	ghcb_set_sw_exit_info_2(ghcb, 0);
+		if (ret)
+			svsm_pval_terminate(pc, ret, call.rax_out);
+	}
 
-	sev_es_wr_ghcb_msr(__pa_nodebug(ghcb));
-	VMGEXIT();
+	/* Process any entries that failed to be validated at 2M and validate them at 4K */
+	for (i = 0; i < pv_4k_count; i++) {
+		u64 pfn, pfn_end;
 
-	__sev_put_ghcb(&state);
-}
+		action  = pv_4k[i].action;
+		pfn     = pv_4k[i].pfn;
+		pfn_end = pfn + 512;
 
-static u64 __init get_snp_jump_table_addr(void)
-{
-	struct snp_secrets_page *secrets;
-	void __iomem *mem;
-	u64 addr;
+		while (pfn < pfn_end) {
+			pfn = svsm_build_ca_from_pfn_range(pfn, pfn_end, action, pc);
 
-	mem = ioremap_encrypted(secrets_pa, PAGE_SIZE);
-	if (!mem) {
-		pr_err("Unable to locate AP jump table address: failed to map the SNP secrets page.\n");
-		return 0;
+			ret = svsm_perform_call_protocol(&call);
+			if (ret)
+				svsm_pval_terminate(pc, ret, call.rax_out);
+		}
 	}
 
-	secrets = (__force struct snp_secrets_page *)mem;
-
-	addr = secrets->os_area.ap_jump_table_pa;
-	iounmap(mem);
-
-	return addr;
+	native_local_irq_restore(flags);
 }
 
-static u64 __init get_jump_table_addr(void)
+static void pvalidate_pages(struct snp_psc_desc *desc)
 {
-	struct ghcb_state state;
-	unsigned long flags;
-	struct ghcb *ghcb;
-	u64 ret = 0;
-
-	if (cc_platform_has(CC_ATTR_GUEST_SEV_SNP))
-		return get_snp_jump_table_addr();
-
-	local_irq_save(flags);
+	if (snp_vmpl)
+		svsm_pval_pages(desc);
+	else
+		pval_pages(desc);
+}
 
-	ghcb = __sev_get_ghcb(&state);
+static int vmgexit_psc(struct ghcb *ghcb, struct snp_psc_desc *desc)
+{
+	int cur_entry, end_entry, ret = 0;
+	struct snp_psc_desc *data;
+	struct es_em_ctxt ctxt;
 
 	vc_ghcb_invalidate(ghcb);
-	ghcb_set_sw_exit_code(ghcb, SVM_VMGEXIT_AP_JUMP_TABLE);
-	ghcb_set_sw_exit_info_1(ghcb, SVM_VMGEXIT_GET_AP_JUMP_TABLE);
-	ghcb_set_sw_exit_info_2(ghcb, 0);
 
-	sev_es_wr_ghcb_msr(__pa(ghcb));
-	VMGEXIT();
-
-	if (ghcb_sw_exit_info_1_is_valid(ghcb) &&
-	    ghcb_sw_exit_info_2_is_valid(ghcb))
-		ret = ghcb->save.sw_exit_info_2;
-
-	__sev_put_ghcb(&state);
-
-	local_irq_restore(flags);
+	/* Copy the input desc into GHCB shared buffer */
+	data = (struct snp_psc_desc *)ghcb->shared_buffer;
+	memcpy(ghcb->shared_buffer, desc, min_t(int, GHCB_SHARED_BUF_SIZE, sizeof(*desc)));
 
-	return ret;
-}
-
-static void __head
-early_set_pages_state(unsigned long vaddr, unsigned long paddr,
-		      unsigned long npages, enum psc_op op)
-{
-	unsigned long paddr_end;
-	u64 val;
-
-	vaddr = vaddr & PAGE_MASK;
+	/*
+	 * As per the GHCB specification, the hypervisor can resume the guest
+	 * before processing all the entries. Check whether all the entries
+	 * are processed. If not, then keep retrying. Note, the hypervisor
+	 * will update the data memory directly to indicate the status, so
+	 * reference the data->hdr everywhere.
+	 *
+	 * The strategy here is to wait for the hypervisor to change the page
+	 * state in the RMP table before guest accesses the memory pages. If the
+	 * page state change was not successful, then later memory access will
+	 * result in a crash.
+	 */
+	cur_entry = data->hdr.cur_entry;
+	end_entry = data->hdr.end_entry;
 
-	paddr = paddr & PAGE_MASK;
-	paddr_end = paddr + (npages << PAGE_SHIFT);
+	while (data->hdr.cur_entry <= data->hdr.end_entry) {
+		ghcb_set_sw_scratch(ghcb, (u64)__pa(data));
 
-	while (paddr < paddr_end) {
-		/* Page validation must be rescinded before changing to shared */
-		if (op == SNP_PAGE_STATE_SHARED)
-			pvalidate_4k_page(vaddr, paddr, false);
+		/* This will advance the shared buffer data points to. */
+		ret = sev_es_ghcb_hv_call(ghcb, &ctxt, SVM_VMGEXIT_PSC, 0, 0);
 
 		/*
-		 * Use the MSR protocol because this function can be called before
-		 * the GHCB is established.
+		 * Page State Change VMGEXIT can pass error code through
+		 * exit_info_2.
 		 */
-		sev_es_wr_ghcb_msr(GHCB_MSR_PSC_REQ_GFN(paddr >> PAGE_SHIFT, op));
-		VMGEXIT();
-
-		val = sev_es_rd_ghcb_msr();
-
-		if (GHCB_RESP_CODE(val) != GHCB_MSR_PSC_RESP)
-			goto e_term;
-
-		if (GHCB_MSR_PSC_RESP_VAL(val))
-			goto e_term;
+		if (WARN(ret || ghcb->save.sw_exit_info_2,
+			 "SNP: PSC failed ret=%d exit_info_2=%llx\n",
+			 ret, ghcb->save.sw_exit_info_2)) {
+			ret = 1;
+			goto out;
+		}
 
-		/* Page validation must be performed after changing to private */
-		if (op == SNP_PAGE_STATE_PRIVATE)
-			pvalidate_4k_page(vaddr, paddr, true);
+		/* Verify that reserved bit is not set */
+		if (WARN(data->hdr.reserved, "Reserved bit is set in the PSC header\n")) {
+			ret = 1;
+			goto out;
+		}
 
-		vaddr += PAGE_SIZE;
-		paddr += PAGE_SIZE;
+		/*
+		 * Sanity check that entry processing is not going backwards.
+		 * This will happen only if hypervisor is tricking us.
+		 */
+		if (WARN(data->hdr.end_entry > end_entry || cur_entry > data->hdr.cur_entry,
+"SNP: PSC processing going backward, end_entry %d (got %d) cur_entry %d (got %d)\n",
+			 end_entry, data->hdr.end_entry, cur_entry, data->hdr.cur_entry)) {
+			ret = 1;
+			goto out;
+		}
 	}
 
-	return;
-
-e_term:
-	sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PSC);
-}
-
-void __head early_snp_set_memory_private(unsigned long vaddr, unsigned long paddr,
-					 unsigned long npages)
-{
-	/*
-	 * This can be invoked in early boot while running identity mapped, so
-	 * use an open coded check for SNP instead of using cc_platform_has().
-	 * This eliminates worries about jump tables or checking boot_cpu_data
-	 * in the cc_platform_has() function.
-	 */
-	if (!(RIP_REL_REF(sev_status) & MSR_AMD64_SEV_SNP_ENABLED))
-		return;
-
-	 /*
-	  * Ask the hypervisor to mark the memory pages as private in the RMP
-	  * table.
-	  */
-	early_set_pages_state(vaddr, paddr, npages, SNP_PAGE_STATE_PRIVATE);
-}
-
-void __head early_snp_set_memory_shared(unsigned long vaddr, unsigned long paddr,
-					unsigned long npages)
-{
-	/*
-	 * This can be invoked in early boot while running identity mapped, so
-	 * use an open coded check for SNP instead of using cc_platform_has().
-	 * This eliminates worries about jump tables or checking boot_cpu_data
-	 * in the cc_platform_has() function.
-	 */
-	if (!(RIP_REL_REF(sev_status) & MSR_AMD64_SEV_SNP_ENABLED))
-		return;
-
-	 /* Ask hypervisor to mark the memory pages shared in the RMP table. */
-	early_set_pages_state(vaddr, paddr, npages, SNP_PAGE_STATE_SHARED);
+out:
+	return ret;
 }
 
 static unsigned long __set_pages_state(struct snp_psc_desc *data, unsigned long vaddr,
@@ -1417,90 +1004,6 @@ int __init sev_es_efi_map_ghcbs(pgd_t *pgd)
 	return 0;
 }
 
-/* Writes to the SVSM CAA MSR are ignored */
-static enum es_result __vc_handle_msr_caa(struct pt_regs *regs, bool write)
-{
-	if (write)
-		return ES_OK;
-
-	regs->ax = lower_32_bits(this_cpu_read(svsm_caa_pa));
-	regs->dx = upper_32_bits(this_cpu_read(svsm_caa_pa));
-
-	return ES_OK;
-}
-
-/*
- * TSC related accesses should not exit to the hypervisor when a guest is
- * executing with Secure TSC enabled, so special handling is required for
- * accesses of MSR_IA32_TSC and MSR_AMD64_GUEST_TSC_FREQ.
- */
-static enum es_result __vc_handle_secure_tsc_msrs(struct pt_regs *regs, bool write)
-{
-	u64 tsc;
-
-	/*
-	 * GUEST_TSC_FREQ should not be intercepted when Secure TSC is enabled.
-	 * Terminate the SNP guest when the interception is enabled.
-	 */
-	if (regs->cx == MSR_AMD64_GUEST_TSC_FREQ)
-		return ES_VMM_ERROR;
-
-	/*
-	 * Writes: Writing to MSR_IA32_TSC can cause subsequent reads of the TSC
-	 *         to return undefined values, so ignore all writes.
-	 *
-	 * Reads: Reads of MSR_IA32_TSC should return the current TSC value, use
-	 *        the value returned by rdtsc_ordered().
-	 */
-	if (write) {
-		WARN_ONCE(1, "TSC MSR writes are verboten!\n");
-		return ES_OK;
-	}
-
-	tsc = rdtsc_ordered();
-	regs->ax = lower_32_bits(tsc);
-	regs->dx = upper_32_bits(tsc);
-
-	return ES_OK;
-}
-
-static enum es_result vc_handle_msr(struct ghcb *ghcb, struct es_em_ctxt *ctxt)
-{
-	struct pt_regs *regs = ctxt->regs;
-	enum es_result ret;
-	bool write;
-
-	/* Is it a WRMSR? */
-	write = ctxt->insn.opcode.bytes[1] == 0x30;
-
-	switch (regs->cx) {
-	case MSR_SVSM_CAA:
-		return __vc_handle_msr_caa(regs, write);
-	case MSR_IA32_TSC:
-	case MSR_AMD64_GUEST_TSC_FREQ:
-		if (sev_status & MSR_AMD64_SNP_SECURE_TSC)
-			return __vc_handle_secure_tsc_msrs(regs, write);
-		break;
-	default:
-		break;
-	}
-
-	ghcb_set_rcx(ghcb, regs->cx);
-	if (write) {
-		ghcb_set_rax(ghcb, regs->ax);
-		ghcb_set_rdx(ghcb, regs->dx);
-	}
-
-	ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_MSR, write, 0);
-
-	if ((ret == ES_OK) && !write) {
-		regs->ax = ghcb->save.rax;
-		regs->dx = ghcb->save.rdx;
-	}
-
-	return ret;
-}
-
 static void snp_register_per_cpu_ghcb(void)
 {
 	struct sev_es_runtime_data *data;
@@ -1713,748 +1216,6 @@ void __init sev_es_init_vc_handling(void)
 	initial_vc_handler = (unsigned long)kernel_exc_vmm_communication;
 }
 
-static void __init vc_early_forward_exception(struct es_em_ctxt *ctxt)
-{
-	int trapnr = ctxt->fi.vector;
-
-	if (trapnr == X86_TRAP_PF)
-		native_write_cr2(ctxt->fi.cr2);
-
-	ctxt->regs->orig_ax = ctxt->fi.error_code;
-	do_early_exception(ctxt->regs, trapnr);
-}
-
-static long *vc_insn_get_rm(struct es_em_ctxt *ctxt)
-{
-	long *reg_array;
-	int offset;
-
-	reg_array = (long *)ctxt->regs;
-	offset    = insn_get_modrm_rm_off(&ctxt->insn, ctxt->regs);
-
-	if (offset < 0)
-		return NULL;
-
-	offset /= sizeof(long);
-
-	return reg_array + offset;
-}
-static enum es_result vc_do_mmio(struct ghcb *ghcb, struct es_em_ctxt *ctxt,
-				 unsigned int bytes, bool read)
-{
-	u64 exit_code, exit_info_1, exit_info_2;
-	unsigned long ghcb_pa = __pa(ghcb);
-	enum es_result res;
-	phys_addr_t paddr;
-	void __user *ref;
-
-	ref = insn_get_addr_ref(&ctxt->insn, ctxt->regs);
-	if (ref == (void __user *)-1L)
-		return ES_UNSUPPORTED;
-
-	exit_code = read ? SVM_VMGEXIT_MMIO_READ : SVM_VMGEXIT_MMIO_WRITE;
-
-	res = vc_slow_virt_to_phys(ghcb, ctxt, (unsigned long)ref, &paddr);
-	if (res != ES_OK) {
-		if (res == ES_EXCEPTION && !read)
-			ctxt->fi.error_code |= X86_PF_WRITE;
-
-		return res;
-	}
-
-	exit_info_1 = paddr;
-	/* Can never be greater than 8 */
-	exit_info_2 = bytes;
-
-	ghcb_set_sw_scratch(ghcb, ghcb_pa + offsetof(struct ghcb, shared_buffer));
-
-	return sev_es_ghcb_hv_call(ghcb, ctxt, exit_code, exit_info_1, exit_info_2);
-}
-
-/*
- * The MOVS instruction has two memory operands, which raises the
- * problem that it is not known whether the access to the source or the
- * destination caused the #VC exception (and hence whether an MMIO read
- * or write operation needs to be emulated).
- *
- * Instead of playing games with walking page-tables and trying to guess
- * whether the source or destination is an MMIO range, split the move
- * into two operations, a read and a write with only one memory operand.
- * This will cause a nested #VC exception on the MMIO address which can
- * then be handled.
- *
- * This implementation has the benefit that it also supports MOVS where
- * source _and_ destination are MMIO regions.
- *
- * It will slow MOVS on MMIO down a lot, but in SEV-ES guests it is a
- * rare operation. If it turns out to be a performance problem the split
- * operations can be moved to memcpy_fromio() and memcpy_toio().
- */
-static enum es_result vc_handle_mmio_movs(struct es_em_ctxt *ctxt,
-					  unsigned int bytes)
-{
-	unsigned long ds_base, es_base;
-	unsigned char *src, *dst;
-	unsigned char buffer[8];
-	enum es_result ret;
-	bool rep;
-	int off;
-
-	ds_base = insn_get_seg_base(ctxt->regs, INAT_SEG_REG_DS);
-	es_base = insn_get_seg_base(ctxt->regs, INAT_SEG_REG_ES);
-
-	if (ds_base == -1L || es_base == -1L) {
-		ctxt->fi.vector = X86_TRAP_GP;
-		ctxt->fi.error_code = 0;
-		return ES_EXCEPTION;
-	}
-
-	src = ds_base + (unsigned char *)ctxt->regs->si;
-	dst = es_base + (unsigned char *)ctxt->regs->di;
-
-	ret = vc_read_mem(ctxt, src, buffer, bytes);
-	if (ret != ES_OK)
-		return ret;
-
-	ret = vc_write_mem(ctxt, dst, buffer, bytes);
-	if (ret != ES_OK)
-		return ret;
-
-	if (ctxt->regs->flags & X86_EFLAGS_DF)
-		off = -bytes;
-	else
-		off =  bytes;
-
-	ctxt->regs->si += off;
-	ctxt->regs->di += off;
-
-	rep = insn_has_rep_prefix(&ctxt->insn);
-	if (rep)
-		ctxt->regs->cx -= 1;
-
-	if (!rep || ctxt->regs->cx == 0)
-		return ES_OK;
-	else
-		return ES_RETRY;
-}
-
-static enum es_result vc_handle_mmio(struct ghcb *ghcb, struct es_em_ctxt *ctxt)
-{
-	struct insn *insn = &ctxt->insn;
-	enum insn_mmio_type mmio;
-	unsigned int bytes = 0;
-	enum es_result ret;
-	u8 sign_byte;
-	long *reg_data;
-
-	mmio = insn_decode_mmio(insn, &bytes);
-	if (mmio == INSN_MMIO_DECODE_FAILED)
-		return ES_DECODE_FAILED;
-
-	if (mmio != INSN_MMIO_WRITE_IMM && mmio != INSN_MMIO_MOVS) {
-		reg_data = insn_get_modrm_reg_ptr(insn, ctxt->regs);
-		if (!reg_data)
-			return ES_DECODE_FAILED;
-	}
-
-	if (user_mode(ctxt->regs))
-		return ES_UNSUPPORTED;
-
-	switch (mmio) {
-	case INSN_MMIO_WRITE:
-		memcpy(ghcb->shared_buffer, reg_data, bytes);
-		ret = vc_do_mmio(ghcb, ctxt, bytes, false);
-		break;
-	case INSN_MMIO_WRITE_IMM:
-		memcpy(ghcb->shared_buffer, insn->immediate1.bytes, bytes);
-		ret = vc_do_mmio(ghcb, ctxt, bytes, false);
-		break;
-	case INSN_MMIO_READ:
-		ret = vc_do_mmio(ghcb, ctxt, bytes, true);
-		if (ret)
-			break;
-
-		/* Zero-extend for 32-bit operation */
-		if (bytes == 4)
-			*reg_data = 0;
-
-		memcpy(reg_data, ghcb->shared_buffer, bytes);
-		break;
-	case INSN_MMIO_READ_ZERO_EXTEND:
-		ret = vc_do_mmio(ghcb, ctxt, bytes, true);
-		if (ret)
-			break;
-
-		/* Zero extend based on operand size */
-		memset(reg_data, 0, insn->opnd_bytes);
-		memcpy(reg_data, ghcb->shared_buffer, bytes);
-		break;
-	case INSN_MMIO_READ_SIGN_EXTEND:
-		ret = vc_do_mmio(ghcb, ctxt, bytes, true);
-		if (ret)
-			break;
-
-		if (bytes == 1) {
-			u8 *val = (u8 *)ghcb->shared_buffer;
-
-			sign_byte = (*val & 0x80) ? 0xff : 0x00;
-		} else {
-			u16 *val = (u16 *)ghcb->shared_buffer;
-
-			sign_byte = (*val & 0x8000) ? 0xff : 0x00;
-		}
-
-		/* Sign extend based on operand size */
-		memset(reg_data, sign_byte, insn->opnd_bytes);
-		memcpy(reg_data, ghcb->shared_buffer, bytes);
-		break;
-	case INSN_MMIO_MOVS:
-		ret = vc_handle_mmio_movs(ctxt, bytes);
-		break;
-	default:
-		ret = ES_UNSUPPORTED;
-		break;
-	}
-
-	return ret;
-}
-
-static enum es_result vc_handle_dr7_write(struct ghcb *ghcb,
-					  struct es_em_ctxt *ctxt)
-{
-	struct sev_es_runtime_data *data = this_cpu_read(runtime_data);
-	long val, *reg = vc_insn_get_rm(ctxt);
-	enum es_result ret;
-
-	if (sev_status & MSR_AMD64_SNP_DEBUG_SWAP)
-		return ES_VMM_ERROR;
-
-	if (!reg)
-		return ES_DECODE_FAILED;
-
-	val = *reg;
-
-	/* Upper 32 bits must be written as zeroes */
-	if (val >> 32) {
-		ctxt->fi.vector = X86_TRAP_GP;
-		ctxt->fi.error_code = 0;
-		return ES_EXCEPTION;
-	}
-
-	/* Clear out other reserved bits and set bit 10 */
-	val = (val & 0xffff23ffL) | BIT(10);
-
-	/* Early non-zero writes to DR7 are not supported */
-	if (!data && (val & ~DR7_RESET_VALUE))
-		return ES_UNSUPPORTED;
-
-	/* Using a value of 0 for ExitInfo1 means RAX holds the value */
-	ghcb_set_rax(ghcb, val);
-	ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_WRITE_DR7, 0, 0);
-	if (ret != ES_OK)
-		return ret;
-
-	if (data)
-		data->dr7 = val;
-
-	return ES_OK;
-}
-
-static enum es_result vc_handle_dr7_read(struct ghcb *ghcb,
-					 struct es_em_ctxt *ctxt)
-{
-	struct sev_es_runtime_data *data = this_cpu_read(runtime_data);
-	long *reg = vc_insn_get_rm(ctxt);
-
-	if (sev_status & MSR_AMD64_SNP_DEBUG_SWAP)
-		return ES_VMM_ERROR;
-
-	if (!reg)
-		return ES_DECODE_FAILED;
-
-	if (data)
-		*reg = data->dr7;
-	else
-		*reg = DR7_RESET_VALUE;
-
-	return ES_OK;
-}
-
-static enum es_result vc_handle_wbinvd(struct ghcb *ghcb,
-				       struct es_em_ctxt *ctxt)
-{
-	return sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_WBINVD, 0, 0);
-}
-
-static enum es_result vc_handle_rdpmc(struct ghcb *ghcb, struct es_em_ctxt *ctxt)
-{
-	enum es_result ret;
-
-	ghcb_set_rcx(ghcb, ctxt->regs->cx);
-
-	ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_RDPMC, 0, 0);
-	if (ret != ES_OK)
-		return ret;
-
-	if (!(ghcb_rax_is_valid(ghcb) && ghcb_rdx_is_valid(ghcb)))
-		return ES_VMM_ERROR;
-
-	ctxt->regs->ax = ghcb->save.rax;
-	ctxt->regs->dx = ghcb->save.rdx;
-
-	return ES_OK;
-}
-
-static enum es_result vc_handle_monitor(struct ghcb *ghcb,
-					struct es_em_ctxt *ctxt)
-{
-	/*
-	 * Treat it as a NOP and do not leak a physical address to the
-	 * hypervisor.
-	 */
-	return ES_OK;
-}
-
-static enum es_result vc_handle_mwait(struct ghcb *ghcb,
-				      struct es_em_ctxt *ctxt)
-{
-	/* Treat the same as MONITOR/MONITORX */
-	return ES_OK;
-}
-
-static enum es_result vc_handle_vmmcall(struct ghcb *ghcb,
-					struct es_em_ctxt *ctxt)
-{
-	enum es_result ret;
-
-	ghcb_set_rax(ghcb, ctxt->regs->ax);
-	ghcb_set_cpl(ghcb, user_mode(ctxt->regs) ? 3 : 0);
-
-	if (x86_platform.hyper.sev_es_hcall_prepare)
-		x86_platform.hyper.sev_es_hcall_prepare(ghcb, ctxt->regs);
-
-	ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_VMMCALL, 0, 0);
-	if (ret != ES_OK)
-		return ret;
-
-	if (!ghcb_rax_is_valid(ghcb))
-		return ES_VMM_ERROR;
-
-	ctxt->regs->ax = ghcb->save.rax;
-
-	/*
-	 * Call sev_es_hcall_finish() after regs->ax is already set.
-	 * This allows the hypervisor handler to overwrite it again if
-	 * necessary.
-	 */
-	if (x86_platform.hyper.sev_es_hcall_finish &&
-	    !x86_platform.hyper.sev_es_hcall_finish(ghcb, ctxt->regs))
-		return ES_VMM_ERROR;
-
-	return ES_OK;
-}
-
-static enum es_result vc_handle_trap_ac(struct ghcb *ghcb,
-					struct es_em_ctxt *ctxt)
-{
-	/*
-	 * Calling ecx_alignment_check() directly does not work, because it
-	 * enables IRQs and the GHCB is active. Forward the exception and call
-	 * it later from vc_forward_exception().
-	 */
-	ctxt->fi.vector = X86_TRAP_AC;
-	ctxt->fi.error_code = 0;
-	return ES_EXCEPTION;
-}
-
-static enum es_result vc_handle_exitcode(struct es_em_ctxt *ctxt,
-					 struct ghcb *ghcb,
-					 unsigned long exit_code)
-{
-	enum es_result result = vc_check_opcode_bytes(ctxt, exit_code);
-
-	if (result != ES_OK)
-		return result;
-
-	switch (exit_code) {
-	case SVM_EXIT_READ_DR7:
-		result = vc_handle_dr7_read(ghcb, ctxt);
-		break;
-	case SVM_EXIT_WRITE_DR7:
-		result = vc_handle_dr7_write(ghcb, ctxt);
-		break;
-	case SVM_EXIT_EXCP_BASE + X86_TRAP_AC:
-		result = vc_handle_trap_ac(ghcb, ctxt);
-		break;
-	case SVM_EXIT_RDTSC:
-	case SVM_EXIT_RDTSCP:
-		result = vc_handle_rdtsc(ghcb, ctxt, exit_code);
-		break;
-	case SVM_EXIT_RDPMC:
-		result = vc_handle_rdpmc(ghcb, ctxt);
-		break;
-	case SVM_EXIT_INVD:
-		pr_err_ratelimited("#VC exception for INVD??? Seriously???\n");
-		result = ES_UNSUPPORTED;
-		break;
-	case SVM_EXIT_CPUID:
-		result = vc_handle_cpuid(ghcb, ctxt);
-		break;
-	case SVM_EXIT_IOIO:
-		result = vc_handle_ioio(ghcb, ctxt);
-		break;
-	case SVM_EXIT_MSR:
-		result = vc_handle_msr(ghcb, ctxt);
-		break;
-	case SVM_EXIT_VMMCALL:
-		result = vc_handle_vmmcall(ghcb, ctxt);
-		break;
-	case SVM_EXIT_WBINVD:
-		result = vc_handle_wbinvd(ghcb, ctxt);
-		break;
-	case SVM_EXIT_MONITOR:
-		result = vc_handle_monitor(ghcb, ctxt);
-		break;
-	case SVM_EXIT_MWAIT:
-		result = vc_handle_mwait(ghcb, ctxt);
-		break;
-	case SVM_EXIT_NPF:
-		result = vc_handle_mmio(ghcb, ctxt);
-		break;
-	default:
-		/*
-		 * Unexpected #VC exception
-		 */
-		result = ES_UNSUPPORTED;
-	}
-
-	return result;
-}
-
-static __always_inline bool is_vc2_stack(unsigned long sp)
-{
-	return (sp >= __this_cpu_ist_bottom_va(VC2) && sp < __this_cpu_ist_top_va(VC2));
-}
-
-static __always_inline bool vc_from_invalid_context(struct pt_regs *regs)
-{
-	unsigned long sp, prev_sp;
-
-	sp      = (unsigned long)regs;
-	prev_sp = regs->sp;
-
-	/*
-	 * If the code was already executing on the VC2 stack when the #VC
-	 * happened, let it proceed to the normal handling routine. This way the
-	 * code executing on the VC2 stack can cause #VC exceptions to get handled.
-	 */
-	return is_vc2_stack(sp) && !is_vc2_stack(prev_sp);
-}
-
-static bool vc_raw_handle_exception(struct pt_regs *regs, unsigned long error_code)
-{
-	struct ghcb_state state;
-	struct es_em_ctxt ctxt;
-	enum es_result result;
-	struct ghcb *ghcb;
-	bool ret = true;
-
-	ghcb = __sev_get_ghcb(&state);
-
-	vc_ghcb_invalidate(ghcb);
-	result = vc_init_em_ctxt(&ctxt, regs, error_code);
-
-	if (result == ES_OK)
-		result = vc_handle_exitcode(&ctxt, ghcb, error_code);
-
-	__sev_put_ghcb(&state);
-
-	/* Done - now check the result */
-	switch (result) {
-	case ES_OK:
-		vc_finish_insn(&ctxt);
-		break;
-	case ES_UNSUPPORTED:
-		pr_err_ratelimited("Unsupported exit-code 0x%02lx in #VC exception (IP: 0x%lx)\n",
-				   error_code, regs->ip);
-		ret = false;
-		break;
-	case ES_VMM_ERROR:
-		pr_err_ratelimited("Failure in communication with VMM (exit-code 0x%02lx IP: 0x%lx)\n",
-				   error_code, regs->ip);
-		ret = false;
-		break;
-	case ES_DECODE_FAILED:
-		pr_err_ratelimited("Failed to decode instruction (exit-code 0x%02lx IP: 0x%lx)\n",
-				   error_code, regs->ip);
-		ret = false;
-		break;
-	case ES_EXCEPTION:
-		vc_forward_exception(&ctxt);
-		break;
-	case ES_RETRY:
-		/* Nothing to do */
-		break;
-	default:
-		pr_emerg("Unknown result in %s():%d\n", __func__, result);
-		/*
-		 * Emulating the instruction which caused the #VC exception
-		 * failed - can't continue so print debug information
-		 */
-		BUG();
-	}
-
-	return ret;
-}
-
-static __always_inline bool vc_is_db(unsigned long error_code)
-{
-	return error_code == SVM_EXIT_EXCP_BASE + X86_TRAP_DB;
-}
-
-/*
- * Runtime #VC exception handler when raised from kernel mode. Runs in NMI mode
- * and will panic when an error happens.
- */
-DEFINE_IDTENTRY_VC_KERNEL(exc_vmm_communication)
-{
-	irqentry_state_t irq_state;
-
-	/*
-	 * With the current implementation it is always possible to switch to a
-	 * safe stack because #VC exceptions only happen at known places, like
-	 * intercepted instructions or accesses to MMIO areas/IO ports. They can
-	 * also happen with code instrumentation when the hypervisor intercepts
-	 * #DB, but the critical paths are forbidden to be instrumented, so #DB
-	 * exceptions currently also only happen in safe places.
-	 *
-	 * But keep this here in case the noinstr annotations are violated due
-	 * to bug elsewhere.
-	 */
-	if (unlikely(vc_from_invalid_context(regs))) {
-		instrumentation_begin();
-		panic("Can't handle #VC exception from unsupported context\n");
-		instrumentation_end();
-	}
-
-	/*
-	 * Handle #DB before calling into !noinstr code to avoid recursive #DB.
-	 */
-	if (vc_is_db(error_code)) {
-		exc_debug(regs);
-		return;
-	}
-
-	irq_state = irqentry_nmi_enter(regs);
-
-	instrumentation_begin();
-
-	if (!vc_raw_handle_exception(regs, error_code)) {
-		/* Show some debug info */
-		show_regs(regs);
-
-		/* Ask hypervisor to sev_es_terminate */
-		sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_GEN_REQ);
-
-		/* If that fails and we get here - just panic */
-		panic("Returned from Terminate-Request to Hypervisor\n");
-	}
-
-	instrumentation_end();
-	irqentry_nmi_exit(regs, irq_state);
-}
-
-/*
- * Runtime #VC exception handler when raised from user mode. Runs in IRQ mode
- * and will kill the current task with SIGBUS when an error happens.
- */
-DEFINE_IDTENTRY_VC_USER(exc_vmm_communication)
-{
-	/*
-	 * Handle #DB before calling into !noinstr code to avoid recursive #DB.
-	 */
-	if (vc_is_db(error_code)) {
-		noist_exc_debug(regs);
-		return;
-	}
-
-	irqentry_enter_from_user_mode(regs);
-	instrumentation_begin();
-
-	if (!vc_raw_handle_exception(regs, error_code)) {
-		/*
-		 * Do not kill the machine if user-space triggered the
-		 * exception. Send SIGBUS instead and let user-space deal with
-		 * it.
-		 */
-		force_sig_fault(SIGBUS, BUS_OBJERR, (void __user *)0);
-	}
-
-	instrumentation_end();
-	irqentry_exit_to_user_mode(regs);
-}
-
-bool __init handle_vc_boot_ghcb(struct pt_regs *regs)
-{
-	unsigned long exit_code = regs->orig_ax;
-	struct es_em_ctxt ctxt;
-	enum es_result result;
-
-	vc_ghcb_invalidate(boot_ghcb);
-
-	result = vc_init_em_ctxt(&ctxt, regs, exit_code);
-	if (result == ES_OK)
-		result = vc_handle_exitcode(&ctxt, boot_ghcb, exit_code);
-
-	/* Done - now check the result */
-	switch (result) {
-	case ES_OK:
-		vc_finish_insn(&ctxt);
-		break;
-	case ES_UNSUPPORTED:
-		early_printk("PANIC: Unsupported exit-code 0x%02lx in early #VC exception (IP: 0x%lx)\n",
-				exit_code, regs->ip);
-		goto fail;
-	case ES_VMM_ERROR:
-		early_printk("PANIC: Failure in communication with VMM (exit-code 0x%02lx IP: 0x%lx)\n",
-				exit_code, regs->ip);
-		goto fail;
-	case ES_DECODE_FAILED:
-		early_printk("PANIC: Failed to decode instruction (exit-code 0x%02lx IP: 0x%lx)\n",
-				exit_code, regs->ip);
-		goto fail;
-	case ES_EXCEPTION:
-		vc_early_forward_exception(&ctxt);
-		break;
-	case ES_RETRY:
-		/* Nothing to do */
-		break;
-	default:
-		BUG();
-	}
-
-	return true;
-
-fail:
-	show_regs(regs);
-
-	sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_GEN_REQ);
-}
-
-/*
- * Initial set up of SNP relies on information provided by the
- * Confidential Computing blob, which can be passed to the kernel
- * in the following ways, depending on how it is booted:
- *
- * - when booted via the boot/decompress kernel:
- *   - via boot_params
- *
- * - when booted directly by firmware/bootloader (e.g. CONFIG_PVH):
- *   - via a setup_data entry, as defined by the Linux Boot Protocol
- *
- * Scan for the blob in that order.
- */
-static __head struct cc_blob_sev_info *find_cc_blob(struct boot_params *bp)
-{
-	struct cc_blob_sev_info *cc_info;
-
-	/* Boot kernel would have passed the CC blob via boot_params. */
-	if (bp->cc_blob_address) {
-		cc_info = (struct cc_blob_sev_info *)(unsigned long)bp->cc_blob_address;
-		goto found_cc_info;
-	}
-
-	/*
-	 * If kernel was booted directly, without the use of the
-	 * boot/decompression kernel, the CC blob may have been passed via
-	 * setup_data instead.
-	 */
-	cc_info = find_cc_blob_setup_data(bp);
-	if (!cc_info)
-		return NULL;
-
-found_cc_info:
-	if (cc_info->magic != CC_BLOB_SEV_HDR_MAGIC)
-		snp_abort();
-
-	return cc_info;
-}
-
-static __head void svsm_setup(struct cc_blob_sev_info *cc_info)
-{
-	struct svsm_call call = {};
-	int ret;
-	u64 pa;
-
-	/*
-	 * Record the SVSM Calling Area address (CAA) if the guest is not
-	 * running at VMPL0. The CA will be used to communicate with the
-	 * SVSM to perform the SVSM services.
-	 */
-	if (!svsm_setup_ca(cc_info))
-		return;
-
-	/*
-	 * It is very early in the boot and the kernel is running identity
-	 * mapped but without having adjusted the pagetables to where the
-	 * kernel was loaded (physbase), so the get the CA address using
-	 * RIP-relative addressing.
-	 */
-	pa = (u64)&RIP_REL_REF(boot_svsm_ca_page);
-
-	/*
-	 * Switch over to the boot SVSM CA while the current CA is still
-	 * addressable. There is no GHCB at this point so use the MSR protocol.
-	 *
-	 * SVSM_CORE_REMAP_CA call:
-	 *   RAX = 0 (Protocol=0, CallID=0)
-	 *   RCX = New CA GPA
-	 */
-	call.caa = svsm_get_caa();
-	call.rax = SVSM_CORE_CALL(SVSM_CORE_REMAP_CA);
-	call.rcx = pa;
-	ret = svsm_perform_call_protocol(&call);
-	if (ret)
-		sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_SVSM_CA_REMAP_FAIL);
-
-	RIP_REL_REF(boot_svsm_caa) = (struct svsm_ca *)pa;
-	RIP_REL_REF(boot_svsm_caa_pa) = pa;
-}
-
-bool __head snp_init(struct boot_params *bp)
-{
-	struct cc_blob_sev_info *cc_info;
-
-	if (!bp)
-		return false;
-
-	cc_info = find_cc_blob(bp);
-	if (!cc_info)
-		return false;
-
-	if (cc_info->secrets_phys && cc_info->secrets_len == PAGE_SIZE)
-		secrets_pa = cc_info->secrets_phys;
-	else
-		return false;
-
-	setup_cpuid_table(cc_info);
-
-	svsm_setup(cc_info);
-
-	/*
-	 * The CC blob will be used later to access the secrets page. Cache
-	 * it here like the boot kernel does.
-	 */
-	bp->cc_blob_address = (u32)(unsigned long)cc_info;
-
-	return true;
-}
-
-void __head __noreturn snp_abort(void)
-{
-	sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SNP_UNSUPPORTED);
-}
-
 /*
  * SEV-SNP guests should only execute dmi_setup() if EFI_CONFIG_TABLES are
  * enabled, as the alternative (fallback) logic for DMI probing in the legacy
@@ -2835,7 +1596,7 @@ struct snp_msg_desc *snp_msg_alloc(void)
 	if (!mdesc)
 		return ERR_PTR(-ENOMEM);
 
-	mem = ioremap_encrypted(secrets_pa, PAGE_SIZE);
+	mem = ioremap_encrypted(sev_secrets_pa, PAGE_SIZE);
 	if (!mem)
 		goto e_free_mdesc;
 
diff --git a/arch/x86/coco/sev/sev-nmi.c b/arch/x86/coco/sev/sev-nmi.c
new file mode 100644
index 000000000000..d8dfaddfb367
--- /dev/null
+++ b/arch/x86/coco/sev/sev-nmi.c
@@ -0,0 +1,108 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * AMD Memory Encryption Support
+ *
+ * Copyright (C) 2019 SUSE
+ *
+ * Author: Joerg Roedel <jroedel@suse.de>
+ */
+
+#define pr_fmt(fmt)	"SEV: " fmt
+
+#include <linux/bug.h>
+#include <linux/kernel.h>
+
+#include <asm/cpu_entry_area.h>
+#include <asm/msr.h>
+#include <asm/ptrace.h>
+#include <asm/sev.h>
+#include <asm/sev-internal.h>
+
+static __always_inline bool on_vc_stack(struct pt_regs *regs)
+{
+	unsigned long sp = regs->sp;
+
+	/* User-mode RSP is not trusted */
+	if (user_mode(regs))
+		return false;
+
+	/* SYSCALL gap still has user-mode RSP */
+	if (ip_within_syscall_gap(regs))
+		return false;
+
+	return ((sp >= __this_cpu_ist_bottom_va(VC)) && (sp < __this_cpu_ist_top_va(VC)));
+}
+
+/*
+ * This function handles the case when an NMI is raised in the #VC
+ * exception handler entry code, before the #VC handler has switched off
+ * its IST stack. In this case, the IST entry for #VC must be adjusted,
+ * so that any nested #VC exception will not overwrite the stack
+ * contents of the interrupted #VC handler.
+ *
+ * The IST entry is adjusted unconditionally so that it can be also be
+ * unconditionally adjusted back in __sev_es_ist_exit(). Otherwise a
+ * nested sev_es_ist_exit() call may adjust back the IST entry too
+ * early.
+ *
+ * The __sev_es_ist_enter() and __sev_es_ist_exit() functions always run
+ * on the NMI IST stack, as they are only called from NMI handling code
+ * right now.
+ */
+void noinstr __sev_es_ist_enter(struct pt_regs *regs)
+{
+	unsigned long old_ist, new_ist;
+
+	/* Read old IST entry */
+	new_ist = old_ist = __this_cpu_read(cpu_tss_rw.x86_tss.ist[IST_INDEX_VC]);
+
+	/*
+	 * If NMI happened while on the #VC IST stack, set the new IST
+	 * value below regs->sp, so that the interrupted stack frame is
+	 * not overwritten by subsequent #VC exceptions.
+	 */
+	if (on_vc_stack(regs))
+		new_ist = regs->sp;
+
+	/*
+	 * Reserve additional 8 bytes and store old IST value so this
+	 * adjustment can be unrolled in __sev_es_ist_exit().
+	 */
+	new_ist -= sizeof(old_ist);
+	*(unsigned long *)new_ist = old_ist;
+
+	/* Set new IST entry */
+	this_cpu_write(cpu_tss_rw.x86_tss.ist[IST_INDEX_VC], new_ist);
+}
+
+void noinstr __sev_es_ist_exit(void)
+{
+	unsigned long ist;
+
+	/* Read IST entry */
+	ist = __this_cpu_read(cpu_tss_rw.x86_tss.ist[IST_INDEX_VC]);
+
+	if (WARN_ON(ist == __this_cpu_ist_top_va(VC)))
+		return;
+
+	/* Read back old IST entry and write it to the TSS */
+	this_cpu_write(cpu_tss_rw.x86_tss.ist[IST_INDEX_VC], *(unsigned long *)ist);
+}
+
+void noinstr __sev_es_nmi_complete(void)
+{
+	struct ghcb_state state;
+	struct ghcb *ghcb;
+
+	ghcb = __sev_get_ghcb(&state);
+
+	vc_ghcb_invalidate(ghcb);
+	ghcb_set_sw_exit_code(ghcb, SVM_VMGEXIT_NMI_COMPLETE);
+	ghcb_set_sw_exit_info_1(ghcb, 0);
+	ghcb_set_sw_exit_info_2(ghcb, 0);
+
+	sev_es_wr_ghcb_msr(__pa_nodebug(ghcb));
+	VMGEXIT();
+
+	__sev_put_ghcb(&state);
+}
diff --git a/arch/x86/coco/sev/vc-handle.c b/arch/x86/coco/sev/vc-handle.c
new file mode 100644
index 000000000000..b4895c648024
--- /dev/null
+++ b/arch/x86/coco/sev/vc-handle.c
@@ -0,0 +1,1061 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * AMD Memory Encryption Support
+ *
+ * Copyright (C) 2019 SUSE
+ *
+ * Author: Joerg Roedel <jroedel@suse.de>
+ */
+
+#define pr_fmt(fmt)	"SEV: " fmt
+
+#include <linux/sched/debug.h>	/* For show_regs() */
+#include <linux/cc_platform.h>
+#include <linux/printk.h>
+#include <linux/mm_types.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/io.h>
+#include <linux/psp-sev.h>
+#include <uapi/linux/sev-guest.h>
+
+#include <asm/init.h>
+#include <asm/stacktrace.h>
+#include <asm/sev.h>
+#include <asm/sev-internal.h>
+#include <asm/insn-eval.h>
+#include <asm/fpu/xcr.h>
+#include <asm/processor.h>
+#include <asm/setup.h>
+#include <asm/traps.h>
+#include <asm/svm.h>
+#include <asm/smp.h>
+#include <asm/cpu.h>
+#include <asm/apic.h>
+#include <asm/cpuid.h>
+
+static enum es_result vc_slow_virt_to_phys(struct ghcb *ghcb, struct es_em_ctxt *ctxt,
+					   unsigned long vaddr, phys_addr_t *paddr)
+{
+	unsigned long va = (unsigned long)vaddr;
+	unsigned int level;
+	phys_addr_t pa;
+	pgd_t *pgd;
+	pte_t *pte;
+
+	pgd = __va(read_cr3_pa());
+	pgd = &pgd[pgd_index(va)];
+	pte = lookup_address_in_pgd(pgd, va, &level);
+	if (!pte) {
+		ctxt->fi.vector     = X86_TRAP_PF;
+		ctxt->fi.cr2        = vaddr;
+		ctxt->fi.error_code = 0;
+
+		if (user_mode(ctxt->regs))
+			ctxt->fi.error_code |= X86_PF_USER;
+
+		return ES_EXCEPTION;
+	}
+
+	if (WARN_ON_ONCE(pte_val(*pte) & _PAGE_ENC))
+		/* Emulated MMIO to/from encrypted memory not supported */
+		return ES_UNSUPPORTED;
+
+	pa = (phys_addr_t)pte_pfn(*pte) << PAGE_SHIFT;
+	pa |= va & ~page_level_mask(level);
+
+	*paddr = pa;
+
+	return ES_OK;
+}
+
+static enum es_result vc_ioio_check(struct es_em_ctxt *ctxt, u16 port, size_t size)
+{
+	BUG_ON(size > 4);
+
+	if (user_mode(ctxt->regs)) {
+		struct thread_struct *t = &current->thread;
+		struct io_bitmap *iobm = t->io_bitmap;
+		size_t idx;
+
+		if (!iobm)
+			goto fault;
+
+		for (idx = port; idx < port + size; ++idx) {
+			if (test_bit(idx, iobm->bitmap))
+				goto fault;
+		}
+	}
+
+	return ES_OK;
+
+fault:
+	ctxt->fi.vector = X86_TRAP_GP;
+	ctxt->fi.error_code = 0;
+
+	return ES_EXCEPTION;
+}
+
+void vc_forward_exception(struct es_em_ctxt *ctxt)
+{
+	long error_code = ctxt->fi.error_code;
+	int trapnr = ctxt->fi.vector;
+
+	ctxt->regs->orig_ax = ctxt->fi.error_code;
+
+	switch (trapnr) {
+	case X86_TRAP_GP:
+		exc_general_protection(ctxt->regs, error_code);
+		break;
+	case X86_TRAP_UD:
+		exc_invalid_op(ctxt->regs);
+		break;
+	case X86_TRAP_PF:
+		write_cr2(ctxt->fi.cr2);
+		exc_page_fault(ctxt->regs, error_code);
+		break;
+	case X86_TRAP_AC:
+		exc_alignment_check(ctxt->regs, error_code);
+		break;
+	default:
+		pr_emerg("Unsupported exception in #VC instruction emulation - can't continue\n");
+		BUG();
+	}
+}
+
+static int vc_fetch_insn_kernel(struct es_em_ctxt *ctxt,
+				unsigned char *buffer)
+{
+	return copy_from_kernel_nofault(buffer, (unsigned char *)ctxt->regs->ip, MAX_INSN_SIZE);
+}
+
+static enum es_result __vc_decode_user_insn(struct es_em_ctxt *ctxt)
+{
+	char buffer[MAX_INSN_SIZE];
+	int insn_bytes;
+
+	insn_bytes = insn_fetch_from_user_inatomic(ctxt->regs, buffer);
+	if (insn_bytes == 0) {
+		/* Nothing could be copied */
+		ctxt->fi.vector     = X86_TRAP_PF;
+		ctxt->fi.error_code = X86_PF_INSTR | X86_PF_USER;
+		ctxt->fi.cr2        = ctxt->regs->ip;
+		return ES_EXCEPTION;
+	} else if (insn_bytes == -EINVAL) {
+		/* Effective RIP could not be calculated */
+		ctxt->fi.vector     = X86_TRAP_GP;
+		ctxt->fi.error_code = 0;
+		ctxt->fi.cr2        = 0;
+		return ES_EXCEPTION;
+	}
+
+	if (!insn_decode_from_regs(&ctxt->insn, ctxt->regs, buffer, insn_bytes))
+		return ES_DECODE_FAILED;
+
+	if (ctxt->insn.immediate.got)
+		return ES_OK;
+	else
+		return ES_DECODE_FAILED;
+}
+
+static enum es_result __vc_decode_kern_insn(struct es_em_ctxt *ctxt)
+{
+	char buffer[MAX_INSN_SIZE];
+	int res, ret;
+
+	res = vc_fetch_insn_kernel(ctxt, buffer);
+	if (res) {
+		ctxt->fi.vector     = X86_TRAP_PF;
+		ctxt->fi.error_code = X86_PF_INSTR;
+		ctxt->fi.cr2        = ctxt->regs->ip;
+		return ES_EXCEPTION;
+	}
+
+	ret = insn_decode(&ctxt->insn, buffer, MAX_INSN_SIZE, INSN_MODE_64);
+	if (ret < 0)
+		return ES_DECODE_FAILED;
+	else
+		return ES_OK;
+}
+
+static enum es_result vc_decode_insn(struct es_em_ctxt *ctxt)
+{
+	if (user_mode(ctxt->regs))
+		return __vc_decode_user_insn(ctxt);
+	else
+		return __vc_decode_kern_insn(ctxt);
+}
+
+static enum es_result vc_write_mem(struct es_em_ctxt *ctxt,
+				   char *dst, char *buf, size_t size)
+{
+	unsigned long error_code = X86_PF_PROT | X86_PF_WRITE;
+
+	/*
+	 * This function uses __put_user() independent of whether kernel or user
+	 * memory is accessed. This works fine because __put_user() does no
+	 * sanity checks of the pointer being accessed. All that it does is
+	 * to report when the access failed.
+	 *
+	 * Also, this function runs in atomic context, so __put_user() is not
+	 * allowed to sleep. The page-fault handler detects that it is running
+	 * in atomic context and will not try to take mmap_sem and handle the
+	 * fault, so additional pagefault_enable()/disable() calls are not
+	 * needed.
+	 *
+	 * The access can't be done via copy_to_user() here because
+	 * vc_write_mem() must not use string instructions to access unsafe
+	 * memory. The reason is that MOVS is emulated by the #VC handler by
+	 * splitting the move up into a read and a write and taking a nested #VC
+	 * exception on whatever of them is the MMIO access. Using string
+	 * instructions here would cause infinite nesting.
+	 */
+	switch (size) {
+	case 1: {
+		u8 d1;
+		u8 __user *target = (u8 __user *)dst;
+
+		memcpy(&d1, buf, 1);
+		if (__put_user(d1, target))
+			goto fault;
+		break;
+	}
+	case 2: {
+		u16 d2;
+		u16 __user *target = (u16 __user *)dst;
+
+		memcpy(&d2, buf, 2);
+		if (__put_user(d2, target))
+			goto fault;
+		break;
+	}
+	case 4: {
+		u32 d4;
+		u32 __user *target = (u32 __user *)dst;
+
+		memcpy(&d4, buf, 4);
+		if (__put_user(d4, target))
+			goto fault;
+		break;
+	}
+	case 8: {
+		u64 d8;
+		u64 __user *target = (u64 __user *)dst;
+
+		memcpy(&d8, buf, 8);
+		if (__put_user(d8, target))
+			goto fault;
+		break;
+	}
+	default:
+		WARN_ONCE(1, "%s: Invalid size: %zu\n", __func__, size);
+		return ES_UNSUPPORTED;
+	}
+
+	return ES_OK;
+
+fault:
+	if (user_mode(ctxt->regs))
+		error_code |= X86_PF_USER;
+
+	ctxt->fi.vector = X86_TRAP_PF;
+	ctxt->fi.error_code = error_code;
+	ctxt->fi.cr2 = (unsigned long)dst;
+
+	return ES_EXCEPTION;
+}
+
+static enum es_result vc_read_mem(struct es_em_ctxt *ctxt,
+				  char *src, char *buf, size_t size)
+{
+	unsigned long error_code = X86_PF_PROT;
+
+	/*
+	 * This function uses __get_user() independent of whether kernel or user
+	 * memory is accessed. This works fine because __get_user() does no
+	 * sanity checks of the pointer being accessed. All that it does is
+	 * to report when the access failed.
+	 *
+	 * Also, this function runs in atomic context, so __get_user() is not
+	 * allowed to sleep. The page-fault handler detects that it is running
+	 * in atomic context and will not try to take mmap_sem and handle the
+	 * fault, so additional pagefault_enable()/disable() calls are not
+	 * needed.
+	 *
+	 * The access can't be done via copy_from_user() here because
+	 * vc_read_mem() must not use string instructions to access unsafe
+	 * memory. The reason is that MOVS is emulated by the #VC handler by
+	 * splitting the move up into a read and a write and taking a nested #VC
+	 * exception on whatever of them is the MMIO access. Using string
+	 * instructions here would cause infinite nesting.
+	 */
+	switch (size) {
+	case 1: {
+		u8 d1;
+		u8 __user *s = (u8 __user *)src;
+
+		if (__get_user(d1, s))
+			goto fault;
+		memcpy(buf, &d1, 1);
+		break;
+	}
+	case 2: {
+		u16 d2;
+		u16 __user *s = (u16 __user *)src;
+
+		if (__get_user(d2, s))
+			goto fault;
+		memcpy(buf, &d2, 2);
+		break;
+	}
+	case 4: {
+		u32 d4;
+		u32 __user *s = (u32 __user *)src;
+
+		if (__get_user(d4, s))
+			goto fault;
+		memcpy(buf, &d4, 4);
+		break;
+	}
+	case 8: {
+		u64 d8;
+		u64 __user *s = (u64 __user *)src;
+		if (__get_user(d8, s))
+			goto fault;
+		memcpy(buf, &d8, 8);
+		break;
+	}
+	default:
+		WARN_ONCE(1, "%s: Invalid size: %zu\n", __func__, size);
+		return ES_UNSUPPORTED;
+	}
+
+	return ES_OK;
+
+fault:
+	if (user_mode(ctxt->regs))
+		error_code |= X86_PF_USER;
+
+	ctxt->fi.vector = X86_TRAP_PF;
+	ctxt->fi.error_code = error_code;
+	ctxt->fi.cr2 = (unsigned long)src;
+
+	return ES_EXCEPTION;
+}
+
+#define sev_printk(fmt, ...)		printk(fmt, ##__VA_ARGS__)
+
+#include "vc-shared.c"
+
+/* Writes to the SVSM CAA MSR are ignored */
+static enum es_result __vc_handle_msr_caa(struct pt_regs *regs, bool write)
+{
+	if (write)
+		return ES_OK;
+
+	regs->ax = lower_32_bits(this_cpu_read(svsm_caa_pa));
+	regs->dx = upper_32_bits(this_cpu_read(svsm_caa_pa));
+
+	return ES_OK;
+}
+
+/*
+ * TSC related accesses should not exit to the hypervisor when a guest is
+ * executing with Secure TSC enabled, so special handling is required for
+ * accesses of MSR_IA32_TSC and MSR_AMD64_GUEST_TSC_FREQ.
+ */
+static enum es_result __vc_handle_secure_tsc_msrs(struct pt_regs *regs, bool write)
+{
+	u64 tsc;
+
+	/*
+	 * GUEST_TSC_FREQ should not be intercepted when Secure TSC is enabled.
+	 * Terminate the SNP guest when the interception is enabled.
+	 */
+	if (regs->cx == MSR_AMD64_GUEST_TSC_FREQ)
+		return ES_VMM_ERROR;
+
+	/*
+	 * Writes: Writing to MSR_IA32_TSC can cause subsequent reads of the TSC
+	 *         to return undefined values, so ignore all writes.
+	 *
+	 * Reads: Reads of MSR_IA32_TSC should return the current TSC value, use
+	 *        the value returned by rdtsc_ordered().
+	 */
+	if (write) {
+		WARN_ONCE(1, "TSC MSR writes are verboten!\n");
+		return ES_OK;
+	}
+
+	tsc = rdtsc_ordered();
+	regs->ax = lower_32_bits(tsc);
+	regs->dx = upper_32_bits(tsc);
+
+	return ES_OK;
+}
+
+static enum es_result vc_handle_msr(struct ghcb *ghcb, struct es_em_ctxt *ctxt)
+{
+	struct pt_regs *regs = ctxt->regs;
+	enum es_result ret;
+	bool write;
+
+	/* Is it a WRMSR? */
+	write = ctxt->insn.opcode.bytes[1] == 0x30;
+
+	switch (regs->cx) {
+	case MSR_SVSM_CAA:
+		return __vc_handle_msr_caa(regs, write);
+	case MSR_IA32_TSC:
+	case MSR_AMD64_GUEST_TSC_FREQ:
+		if (sev_status & MSR_AMD64_SNP_SECURE_TSC)
+			return __vc_handle_secure_tsc_msrs(regs, write);
+		break;
+	default:
+		break;
+	}
+
+	ghcb_set_rcx(ghcb, regs->cx);
+	if (write) {
+		ghcb_set_rax(ghcb, regs->ax);
+		ghcb_set_rdx(ghcb, regs->dx);
+	}
+
+	ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_MSR, write, 0);
+
+	if ((ret == ES_OK) && !write) {
+		regs->ax = ghcb->save.rax;
+		regs->dx = ghcb->save.rdx;
+	}
+
+	return ret;
+}
+
+static void __init vc_early_forward_exception(struct es_em_ctxt *ctxt)
+{
+	int trapnr = ctxt->fi.vector;
+
+	if (trapnr == X86_TRAP_PF)
+		native_write_cr2(ctxt->fi.cr2);
+
+	ctxt->regs->orig_ax = ctxt->fi.error_code;
+	do_early_exception(ctxt->regs, trapnr);
+}
+
+static long *vc_insn_get_rm(struct es_em_ctxt *ctxt)
+{
+	long *reg_array;
+	int offset;
+
+	reg_array = (long *)ctxt->regs;
+	offset    = insn_get_modrm_rm_off(&ctxt->insn, ctxt->regs);
+
+	if (offset < 0)
+		return NULL;
+
+	offset /= sizeof(long);
+
+	return reg_array + offset;
+}
+static enum es_result vc_do_mmio(struct ghcb *ghcb, struct es_em_ctxt *ctxt,
+				 unsigned int bytes, bool read)
+{
+	u64 exit_code, exit_info_1, exit_info_2;
+	unsigned long ghcb_pa = __pa(ghcb);
+	enum es_result res;
+	phys_addr_t paddr;
+	void __user *ref;
+
+	ref = insn_get_addr_ref(&ctxt->insn, ctxt->regs);
+	if (ref == (void __user *)-1L)
+		return ES_UNSUPPORTED;
+
+	exit_code = read ? SVM_VMGEXIT_MMIO_READ : SVM_VMGEXIT_MMIO_WRITE;
+
+	res = vc_slow_virt_to_phys(ghcb, ctxt, (unsigned long)ref, &paddr);
+	if (res != ES_OK) {
+		if (res == ES_EXCEPTION && !read)
+			ctxt->fi.error_code |= X86_PF_WRITE;
+
+		return res;
+	}
+
+	exit_info_1 = paddr;
+	/* Can never be greater than 8 */
+	exit_info_2 = bytes;
+
+	ghcb_set_sw_scratch(ghcb, ghcb_pa + offsetof(struct ghcb, shared_buffer));
+
+	return sev_es_ghcb_hv_call(ghcb, ctxt, exit_code, exit_info_1, exit_info_2);
+}
+
+/*
+ * The MOVS instruction has two memory operands, which raises the
+ * problem that it is not known whether the access to the source or the
+ * destination caused the #VC exception (and hence whether an MMIO read
+ * or write operation needs to be emulated).
+ *
+ * Instead of playing games with walking page-tables and trying to guess
+ * whether the source or destination is an MMIO range, split the move
+ * into two operations, a read and a write with only one memory operand.
+ * This will cause a nested #VC exception on the MMIO address which can
+ * then be handled.
+ *
+ * This implementation has the benefit that it also supports MOVS where
+ * source _and_ destination are MMIO regions.
+ *
+ * It will slow MOVS on MMIO down a lot, but in SEV-ES guests it is a
+ * rare operation. If it turns out to be a performance problem the split
+ * operations can be moved to memcpy_fromio() and memcpy_toio().
+ */
+static enum es_result vc_handle_mmio_movs(struct es_em_ctxt *ctxt,
+					  unsigned int bytes)
+{
+	unsigned long ds_base, es_base;
+	unsigned char *src, *dst;
+	unsigned char buffer[8];
+	enum es_result ret;
+	bool rep;
+	int off;
+
+	ds_base = insn_get_seg_base(ctxt->regs, INAT_SEG_REG_DS);
+	es_base = insn_get_seg_base(ctxt->regs, INAT_SEG_REG_ES);
+
+	if (ds_base == -1L || es_base == -1L) {
+		ctxt->fi.vector = X86_TRAP_GP;
+		ctxt->fi.error_code = 0;
+		return ES_EXCEPTION;
+	}
+
+	src = ds_base + (unsigned char *)ctxt->regs->si;
+	dst = es_base + (unsigned char *)ctxt->regs->di;
+
+	ret = vc_read_mem(ctxt, src, buffer, bytes);
+	if (ret != ES_OK)
+		return ret;
+
+	ret = vc_write_mem(ctxt, dst, buffer, bytes);
+	if (ret != ES_OK)
+		return ret;
+
+	if (ctxt->regs->flags & X86_EFLAGS_DF)
+		off = -bytes;
+	else
+		off =  bytes;
+
+	ctxt->regs->si += off;
+	ctxt->regs->di += off;
+
+	rep = insn_has_rep_prefix(&ctxt->insn);
+	if (rep)
+		ctxt->regs->cx -= 1;
+
+	if (!rep || ctxt->regs->cx == 0)
+		return ES_OK;
+	else
+		return ES_RETRY;
+}
+
+static enum es_result vc_handle_mmio(struct ghcb *ghcb, struct es_em_ctxt *ctxt)
+{
+	struct insn *insn = &ctxt->insn;
+	enum insn_mmio_type mmio;
+	unsigned int bytes = 0;
+	enum es_result ret;
+	u8 sign_byte;
+	long *reg_data;
+
+	mmio = insn_decode_mmio(insn, &bytes);
+	if (mmio == INSN_MMIO_DECODE_FAILED)
+		return ES_DECODE_FAILED;
+
+	if (mmio != INSN_MMIO_WRITE_IMM && mmio != INSN_MMIO_MOVS) {
+		reg_data = insn_get_modrm_reg_ptr(insn, ctxt->regs);
+		if (!reg_data)
+			return ES_DECODE_FAILED;
+	}
+
+	if (user_mode(ctxt->regs))
+		return ES_UNSUPPORTED;
+
+	switch (mmio) {
+	case INSN_MMIO_WRITE:
+		memcpy(ghcb->shared_buffer, reg_data, bytes);
+		ret = vc_do_mmio(ghcb, ctxt, bytes, false);
+		break;
+	case INSN_MMIO_WRITE_IMM:
+		memcpy(ghcb->shared_buffer, insn->immediate1.bytes, bytes);
+		ret = vc_do_mmio(ghcb, ctxt, bytes, false);
+		break;
+	case INSN_MMIO_READ:
+		ret = vc_do_mmio(ghcb, ctxt, bytes, true);
+		if (ret)
+			break;
+
+		/* Zero-extend for 32-bit operation */
+		if (bytes == 4)
+			*reg_data = 0;
+
+		memcpy(reg_data, ghcb->shared_buffer, bytes);
+		break;
+	case INSN_MMIO_READ_ZERO_EXTEND:
+		ret = vc_do_mmio(ghcb, ctxt, bytes, true);
+		if (ret)
+			break;
+
+		/* Zero extend based on operand size */
+		memset(reg_data, 0, insn->opnd_bytes);
+		memcpy(reg_data, ghcb->shared_buffer, bytes);
+		break;
+	case INSN_MMIO_READ_SIGN_EXTEND:
+		ret = vc_do_mmio(ghcb, ctxt, bytes, true);
+		if (ret)
+			break;
+
+		if (bytes == 1) {
+			u8 *val = (u8 *)ghcb->shared_buffer;
+
+			sign_byte = (*val & 0x80) ? 0xff : 0x00;
+		} else {
+			u16 *val = (u16 *)ghcb->shared_buffer;
+
+			sign_byte = (*val & 0x8000) ? 0xff : 0x00;
+		}
+
+		/* Sign extend based on operand size */
+		memset(reg_data, sign_byte, insn->opnd_bytes);
+		memcpy(reg_data, ghcb->shared_buffer, bytes);
+		break;
+	case INSN_MMIO_MOVS:
+		ret = vc_handle_mmio_movs(ctxt, bytes);
+		break;
+	default:
+		ret = ES_UNSUPPORTED;
+		break;
+	}
+
+	return ret;
+}
+
+static enum es_result vc_handle_dr7_write(struct ghcb *ghcb,
+					  struct es_em_ctxt *ctxt)
+{
+	struct sev_es_runtime_data *data = this_cpu_read(runtime_data);
+	long val, *reg = vc_insn_get_rm(ctxt);
+	enum es_result ret;
+
+	if (sev_status & MSR_AMD64_SNP_DEBUG_SWAP)
+		return ES_VMM_ERROR;
+
+	if (!reg)
+		return ES_DECODE_FAILED;
+
+	val = *reg;
+
+	/* Upper 32 bits must be written as zeroes */
+	if (val >> 32) {
+		ctxt->fi.vector = X86_TRAP_GP;
+		ctxt->fi.error_code = 0;
+		return ES_EXCEPTION;
+	}
+
+	/* Clear out other reserved bits and set bit 10 */
+	val = (val & 0xffff23ffL) | BIT(10);
+
+	/* Early non-zero writes to DR7 are not supported */
+	if (!data && (val & ~DR7_RESET_VALUE))
+		return ES_UNSUPPORTED;
+
+	/* Using a value of 0 for ExitInfo1 means RAX holds the value */
+	ghcb_set_rax(ghcb, val);
+	ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_WRITE_DR7, 0, 0);
+	if (ret != ES_OK)
+		return ret;
+
+	if (data)
+		data->dr7 = val;
+
+	return ES_OK;
+}
+
+static enum es_result vc_handle_dr7_read(struct ghcb *ghcb,
+					 struct es_em_ctxt *ctxt)
+{
+	struct sev_es_runtime_data *data = this_cpu_read(runtime_data);
+	long *reg = vc_insn_get_rm(ctxt);
+
+	if (sev_status & MSR_AMD64_SNP_DEBUG_SWAP)
+		return ES_VMM_ERROR;
+
+	if (!reg)
+		return ES_DECODE_FAILED;
+
+	if (data)
+		*reg = data->dr7;
+	else
+		*reg = DR7_RESET_VALUE;
+
+	return ES_OK;
+}
+
+static enum es_result vc_handle_wbinvd(struct ghcb *ghcb,
+				       struct es_em_ctxt *ctxt)
+{
+	return sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_WBINVD, 0, 0);
+}
+
+static enum es_result vc_handle_rdpmc(struct ghcb *ghcb, struct es_em_ctxt *ctxt)
+{
+	enum es_result ret;
+
+	ghcb_set_rcx(ghcb, ctxt->regs->cx);
+
+	ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_RDPMC, 0, 0);
+	if (ret != ES_OK)
+		return ret;
+
+	if (!(ghcb_rax_is_valid(ghcb) && ghcb_rdx_is_valid(ghcb)))
+		return ES_VMM_ERROR;
+
+	ctxt->regs->ax = ghcb->save.rax;
+	ctxt->regs->dx = ghcb->save.rdx;
+
+	return ES_OK;
+}
+
+static enum es_result vc_handle_monitor(struct ghcb *ghcb,
+					struct es_em_ctxt *ctxt)
+{
+	/*
+	 * Treat it as a NOP and do not leak a physical address to the
+	 * hypervisor.
+	 */
+	return ES_OK;
+}
+
+static enum es_result vc_handle_mwait(struct ghcb *ghcb,
+				      struct es_em_ctxt *ctxt)
+{
+	/* Treat the same as MONITOR/MONITORX */
+	return ES_OK;
+}
+
+static enum es_result vc_handle_vmmcall(struct ghcb *ghcb,
+					struct es_em_ctxt *ctxt)
+{
+	enum es_result ret;
+
+	ghcb_set_rax(ghcb, ctxt->regs->ax);
+	ghcb_set_cpl(ghcb, user_mode(ctxt->regs) ? 3 : 0);
+
+	if (x86_platform.hyper.sev_es_hcall_prepare)
+		x86_platform.hyper.sev_es_hcall_prepare(ghcb, ctxt->regs);
+
+	ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_VMMCALL, 0, 0);
+	if (ret != ES_OK)
+		return ret;
+
+	if (!ghcb_rax_is_valid(ghcb))
+		return ES_VMM_ERROR;
+
+	ctxt->regs->ax = ghcb->save.rax;
+
+	/*
+	 * Call sev_es_hcall_finish() after regs->ax is already set.
+	 * This allows the hypervisor handler to overwrite it again if
+	 * necessary.
+	 */
+	if (x86_platform.hyper.sev_es_hcall_finish &&
+	    !x86_platform.hyper.sev_es_hcall_finish(ghcb, ctxt->regs))
+		return ES_VMM_ERROR;
+
+	return ES_OK;
+}
+
+static enum es_result vc_handle_trap_ac(struct ghcb *ghcb,
+					struct es_em_ctxt *ctxt)
+{
+	/*
+	 * Calling ecx_alignment_check() directly does not work, because it
+	 * enables IRQs and the GHCB is active. Forward the exception and call
+	 * it later from vc_forward_exception().
+	 */
+	ctxt->fi.vector = X86_TRAP_AC;
+	ctxt->fi.error_code = 0;
+	return ES_EXCEPTION;
+}
+
+static enum es_result vc_handle_exitcode(struct es_em_ctxt *ctxt,
+					 struct ghcb *ghcb,
+					 unsigned long exit_code)
+{
+	enum es_result result = vc_check_opcode_bytes(ctxt, exit_code);
+
+	if (result != ES_OK)
+		return result;
+
+	switch (exit_code) {
+	case SVM_EXIT_READ_DR7:
+		result = vc_handle_dr7_read(ghcb, ctxt);
+		break;
+	case SVM_EXIT_WRITE_DR7:
+		result = vc_handle_dr7_write(ghcb, ctxt);
+		break;
+	case SVM_EXIT_EXCP_BASE + X86_TRAP_AC:
+		result = vc_handle_trap_ac(ghcb, ctxt);
+		break;
+	case SVM_EXIT_RDTSC:
+	case SVM_EXIT_RDTSCP:
+		result = vc_handle_rdtsc(ghcb, ctxt, exit_code);
+		break;
+	case SVM_EXIT_RDPMC:
+		result = vc_handle_rdpmc(ghcb, ctxt);
+		break;
+	case SVM_EXIT_INVD:
+		pr_err_ratelimited("#VC exception for INVD??? Seriously???\n");
+		result = ES_UNSUPPORTED;
+		break;
+	case SVM_EXIT_CPUID:
+		result = vc_handle_cpuid(ghcb, ctxt);
+		break;
+	case SVM_EXIT_IOIO:
+		result = vc_handle_ioio(ghcb, ctxt);
+		break;
+	case SVM_EXIT_MSR:
+		result = vc_handle_msr(ghcb, ctxt);
+		break;
+	case SVM_EXIT_VMMCALL:
+		result = vc_handle_vmmcall(ghcb, ctxt);
+		break;
+	case SVM_EXIT_WBINVD:
+		result = vc_handle_wbinvd(ghcb, ctxt);
+		break;
+	case SVM_EXIT_MONITOR:
+		result = vc_handle_monitor(ghcb, ctxt);
+		break;
+	case SVM_EXIT_MWAIT:
+		result = vc_handle_mwait(ghcb, ctxt);
+		break;
+	case SVM_EXIT_NPF:
+		result = vc_handle_mmio(ghcb, ctxt);
+		break;
+	default:
+		/*
+		 * Unexpected #VC exception
+		 */
+		result = ES_UNSUPPORTED;
+	}
+
+	return result;
+}
+
+static __always_inline bool is_vc2_stack(unsigned long sp)
+{
+	return (sp >= __this_cpu_ist_bottom_va(VC2) && sp < __this_cpu_ist_top_va(VC2));
+}
+
+static __always_inline bool vc_from_invalid_context(struct pt_regs *regs)
+{
+	unsigned long sp, prev_sp;
+
+	sp      = (unsigned long)regs;
+	prev_sp = regs->sp;
+
+	/*
+	 * If the code was already executing on the VC2 stack when the #VC
+	 * happened, let it proceed to the normal handling routine. This way the
+	 * code executing on the VC2 stack can cause #VC exceptions to get handled.
+	 */
+	return is_vc2_stack(sp) && !is_vc2_stack(prev_sp);
+}
+
+static bool vc_raw_handle_exception(struct pt_regs *regs, unsigned long error_code)
+{
+	struct ghcb_state state;
+	struct es_em_ctxt ctxt;
+	enum es_result result;
+	struct ghcb *ghcb;
+	bool ret = true;
+
+	ghcb = __sev_get_ghcb(&state);
+
+	vc_ghcb_invalidate(ghcb);
+	result = vc_init_em_ctxt(&ctxt, regs, error_code);
+
+	if (result == ES_OK)
+		result = vc_handle_exitcode(&ctxt, ghcb, error_code);
+
+	__sev_put_ghcb(&state);
+
+	/* Done - now check the result */
+	switch (result) {
+	case ES_OK:
+		vc_finish_insn(&ctxt);
+		break;
+	case ES_UNSUPPORTED:
+		pr_err_ratelimited("Unsupported exit-code 0x%02lx in #VC exception (IP: 0x%lx)\n",
+				   error_code, regs->ip);
+		ret = false;
+		break;
+	case ES_VMM_ERROR:
+		pr_err_ratelimited("Failure in communication with VMM (exit-code 0x%02lx IP: 0x%lx)\n",
+				   error_code, regs->ip);
+		ret = false;
+		break;
+	case ES_DECODE_FAILED:
+		pr_err_ratelimited("Failed to decode instruction (exit-code 0x%02lx IP: 0x%lx)\n",
+				   error_code, regs->ip);
+		ret = false;
+		break;
+	case ES_EXCEPTION:
+		vc_forward_exception(&ctxt);
+		break;
+	case ES_RETRY:
+		/* Nothing to do */
+		break;
+	default:
+		pr_emerg("Unknown result in %s():%d\n", __func__, result);
+		/*
+		 * Emulating the instruction which caused the #VC exception
+		 * failed - can't continue so print debug information
+		 */
+		BUG();
+	}
+
+	return ret;
+}
+
+static __always_inline bool vc_is_db(unsigned long error_code)
+{
+	return error_code == SVM_EXIT_EXCP_BASE + X86_TRAP_DB;
+}
+
+/*
+ * Runtime #VC exception handler when raised from kernel mode. Runs in NMI mode
+ * and will panic when an error happens.
+ */
+DEFINE_IDTENTRY_VC_KERNEL(exc_vmm_communication)
+{
+	irqentry_state_t irq_state;
+
+	/*
+	 * With the current implementation it is always possible to switch to a
+	 * safe stack because #VC exceptions only happen at known places, like
+	 * intercepted instructions or accesses to MMIO areas/IO ports. They can
+	 * also happen with code instrumentation when the hypervisor intercepts
+	 * #DB, but the critical paths are forbidden to be instrumented, so #DB
+	 * exceptions currently also only happen in safe places.
+	 *
+	 * But keep this here in case the noinstr annotations are violated due
+	 * to bug elsewhere.
+	 */
+	if (unlikely(vc_from_invalid_context(regs))) {
+		instrumentation_begin();
+		panic("Can't handle #VC exception from unsupported context\n");
+		instrumentation_end();
+	}
+
+	/*
+	 * Handle #DB before calling into !noinstr code to avoid recursive #DB.
+	 */
+	if (vc_is_db(error_code)) {
+		exc_debug(regs);
+		return;
+	}
+
+	irq_state = irqentry_nmi_enter(regs);
+
+	instrumentation_begin();
+
+	if (!vc_raw_handle_exception(regs, error_code)) {
+		/* Show some debug info */
+		show_regs(regs);
+
+		/* Ask hypervisor to sev_es_terminate */
+		sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_GEN_REQ);
+
+		/* If that fails and we get here - just panic */
+		panic("Returned from Terminate-Request to Hypervisor\n");
+	}
+
+	instrumentation_end();
+	irqentry_nmi_exit(regs, irq_state);
+}
+
+/*
+ * Runtime #VC exception handler when raised from user mode. Runs in IRQ mode
+ * and will kill the current task with SIGBUS when an error happens.
+ */
+DEFINE_IDTENTRY_VC_USER(exc_vmm_communication)
+{
+	/*
+	 * Handle #DB before calling into !noinstr code to avoid recursive #DB.
+	 */
+	if (vc_is_db(error_code)) {
+		noist_exc_debug(regs);
+		return;
+	}
+
+	irqentry_enter_from_user_mode(regs);
+	instrumentation_begin();
+
+	if (!vc_raw_handle_exception(regs, error_code)) {
+		/*
+		 * Do not kill the machine if user-space triggered the
+		 * exception. Send SIGBUS instead and let user-space deal with
+		 * it.
+		 */
+		force_sig_fault(SIGBUS, BUS_OBJERR, (void __user *)0);
+	}
+
+	instrumentation_end();
+	irqentry_exit_to_user_mode(regs);
+}
+
+bool __init handle_vc_boot_ghcb(struct pt_regs *regs)
+{
+	unsigned long exit_code = regs->orig_ax;
+	struct es_em_ctxt ctxt;
+	enum es_result result;
+
+	vc_ghcb_invalidate(boot_ghcb);
+
+	result = vc_init_em_ctxt(&ctxt, regs, exit_code);
+	if (result == ES_OK)
+		result = vc_handle_exitcode(&ctxt, boot_ghcb, exit_code);
+
+	/* Done - now check the result */
+	switch (result) {
+	case ES_OK:
+		vc_finish_insn(&ctxt);
+		break;
+	case ES_UNSUPPORTED:
+		early_printk("PANIC: Unsupported exit-code 0x%02lx in early #VC exception (IP: 0x%lx)\n",
+				exit_code, regs->ip);
+		goto fail;
+	case ES_VMM_ERROR:
+		early_printk("PANIC: Failure in communication with VMM (exit-code 0x%02lx IP: 0x%lx)\n",
+				exit_code, regs->ip);
+		goto fail;
+	case ES_DECODE_FAILED:
+		early_printk("PANIC: Failed to decode instruction (exit-code 0x%02lx IP: 0x%lx)\n",
+				exit_code, regs->ip);
+		goto fail;
+	case ES_EXCEPTION:
+		vc_early_forward_exception(&ctxt);
+		break;
+	case ES_RETRY:
+		/* Nothing to do */
+		break;
+	default:
+		BUG();
+	}
+
+	return true;
+
+fail:
+	show_regs(regs);
+
+	sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_GEN_REQ);
+}
+
diff --git a/arch/x86/coco/sev/vc-shared.c b/arch/x86/coco/sev/vc-shared.c
new file mode 100644
index 000000000000..2c0ab0fdc060
--- /dev/null
+++ b/arch/x86/coco/sev/vc-shared.c
@@ -0,0 +1,504 @@
+// SPDX-License-Identifier: GPL-2.0
+
+static enum es_result vc_check_opcode_bytes(struct es_em_ctxt *ctxt,
+					    unsigned long exit_code)
+{
+	unsigned int opcode = (unsigned int)ctxt->insn.opcode.value;
+	u8 modrm = ctxt->insn.modrm.value;
+
+	switch (exit_code) {
+
+	case SVM_EXIT_IOIO:
+	case SVM_EXIT_NPF:
+		/* handled separately */
+		return ES_OK;
+
+	case SVM_EXIT_CPUID:
+		if (opcode == 0xa20f)
+			return ES_OK;
+		break;
+
+	case SVM_EXIT_INVD:
+		if (opcode == 0x080f)
+			return ES_OK;
+		break;
+
+	case SVM_EXIT_MONITOR:
+		/* MONITOR and MONITORX instructions generate the same error code */
+		if (opcode == 0x010f && (modrm == 0xc8 || modrm == 0xfa))
+			return ES_OK;
+		break;
+
+	case SVM_EXIT_MWAIT:
+		/* MWAIT and MWAITX instructions generate the same error code */
+		if (opcode == 0x010f && (modrm == 0xc9 || modrm == 0xfb))
+			return ES_OK;
+		break;
+
+	case SVM_EXIT_MSR:
+		/* RDMSR */
+		if (opcode == 0x320f ||
+		/* WRMSR */
+		    opcode == 0x300f)
+			return ES_OK;
+		break;
+
+	case SVM_EXIT_RDPMC:
+		if (opcode == 0x330f)
+			return ES_OK;
+		break;
+
+	case SVM_EXIT_RDTSC:
+		if (opcode == 0x310f)
+			return ES_OK;
+		break;
+
+	case SVM_EXIT_RDTSCP:
+		if (opcode == 0x010f && modrm == 0xf9)
+			return ES_OK;
+		break;
+
+	case SVM_EXIT_READ_DR7:
+		if (opcode == 0x210f &&
+		    X86_MODRM_REG(ctxt->insn.modrm.value) == 7)
+			return ES_OK;
+		break;
+
+	case SVM_EXIT_VMMCALL:
+		if (opcode == 0x010f && modrm == 0xd9)
+			return ES_OK;
+
+		break;
+
+	case SVM_EXIT_WRITE_DR7:
+		if (opcode == 0x230f &&
+		    X86_MODRM_REG(ctxt->insn.modrm.value) == 7)
+			return ES_OK;
+		break;
+
+	case SVM_EXIT_WBINVD:
+		if (opcode == 0x90f)
+			return ES_OK;
+		break;
+
+	default:
+		break;
+	}
+
+	sev_printk(KERN_ERR "Wrong/unhandled opcode bytes: 0x%x, exit_code: 0x%lx, rIP: 0x%lx\n",
+		   opcode, exit_code, ctxt->regs->ip);
+
+	return ES_UNSUPPORTED;
+}
+
+static bool vc_decoding_needed(unsigned long exit_code)
+{
+	/* Exceptions don't require to decode the instruction */
+	return !(exit_code >= SVM_EXIT_EXCP_BASE &&
+		 exit_code <= SVM_EXIT_LAST_EXCP);
+}
+
+static enum es_result vc_init_em_ctxt(struct es_em_ctxt *ctxt,
+				      struct pt_regs *regs,
+				      unsigned long exit_code)
+{
+	enum es_result ret = ES_OK;
+
+	memset(ctxt, 0, sizeof(*ctxt));
+	ctxt->regs = regs;
+
+	if (vc_decoding_needed(exit_code))
+		ret = vc_decode_insn(ctxt);
+
+	return ret;
+}
+
+static void vc_finish_insn(struct es_em_ctxt *ctxt)
+{
+	ctxt->regs->ip += ctxt->insn.length;
+}
+
+static enum es_result vc_insn_string_check(struct es_em_ctxt *ctxt,
+					   unsigned long address,
+					   bool write)
+{
+	if (user_mode(ctxt->regs) && fault_in_kernel_space(address)) {
+		ctxt->fi.vector     = X86_TRAP_PF;
+		ctxt->fi.error_code = X86_PF_USER;
+		ctxt->fi.cr2        = address;
+		if (write)
+			ctxt->fi.error_code |= X86_PF_WRITE;
+
+		return ES_EXCEPTION;
+	}
+
+	return ES_OK;
+}
+
+static enum es_result vc_insn_string_read(struct es_em_ctxt *ctxt,
+					  void *src, char *buf,
+					  unsigned int data_size,
+					  unsigned int count,
+					  bool backwards)
+{
+	int i, b = backwards ? -1 : 1;
+	unsigned long address = (unsigned long)src;
+	enum es_result ret;
+
+	ret = vc_insn_string_check(ctxt, address, false);
+	if (ret != ES_OK)
+		return ret;
+
+	for (i = 0; i < count; i++) {
+		void *s = src + (i * data_size * b);
+		char *d = buf + (i * data_size);
+
+		ret = vc_read_mem(ctxt, s, d, data_size);
+		if (ret != ES_OK)
+			break;
+	}
+
+	return ret;
+}
+
+static enum es_result vc_insn_string_write(struct es_em_ctxt *ctxt,
+					   void *dst, char *buf,
+					   unsigned int data_size,
+					   unsigned int count,
+					   bool backwards)
+{
+	int i, s = backwards ? -1 : 1;
+	unsigned long address = (unsigned long)dst;
+	enum es_result ret;
+
+	ret = vc_insn_string_check(ctxt, address, true);
+	if (ret != ES_OK)
+		return ret;
+
+	for (i = 0; i < count; i++) {
+		void *d = dst + (i * data_size * s);
+		char *b = buf + (i * data_size);
+
+		ret = vc_write_mem(ctxt, d, b, data_size);
+		if (ret != ES_OK)
+			break;
+	}
+
+	return ret;
+}
+
+#define IOIO_TYPE_STR  BIT(2)
+#define IOIO_TYPE_IN   1
+#define IOIO_TYPE_INS  (IOIO_TYPE_IN | IOIO_TYPE_STR)
+#define IOIO_TYPE_OUT  0
+#define IOIO_TYPE_OUTS (IOIO_TYPE_OUT | IOIO_TYPE_STR)
+
+#define IOIO_REP       BIT(3)
+
+#define IOIO_ADDR_64   BIT(9)
+#define IOIO_ADDR_32   BIT(8)
+#define IOIO_ADDR_16   BIT(7)
+
+#define IOIO_DATA_32   BIT(6)
+#define IOIO_DATA_16   BIT(5)
+#define IOIO_DATA_8    BIT(4)
+
+#define IOIO_SEG_ES    (0 << 10)
+#define IOIO_SEG_DS    (3 << 10)
+
+static enum es_result vc_ioio_exitinfo(struct es_em_ctxt *ctxt, u64 *exitinfo)
+{
+	struct insn *insn = &ctxt->insn;
+	size_t size;
+	u64 port;
+
+	*exitinfo = 0;
+
+	switch (insn->opcode.bytes[0]) {
+	/* INS opcodes */
+	case 0x6c:
+	case 0x6d:
+		*exitinfo |= IOIO_TYPE_INS;
+		*exitinfo |= IOIO_SEG_ES;
+		port	   = ctxt->regs->dx & 0xffff;
+		break;
+
+	/* OUTS opcodes */
+	case 0x6e:
+	case 0x6f:
+		*exitinfo |= IOIO_TYPE_OUTS;
+		*exitinfo |= IOIO_SEG_DS;
+		port	   = ctxt->regs->dx & 0xffff;
+		break;
+
+	/* IN immediate opcodes */
+	case 0xe4:
+	case 0xe5:
+		*exitinfo |= IOIO_TYPE_IN;
+		port	   = (u8)insn->immediate.value & 0xffff;
+		break;
+
+	/* OUT immediate opcodes */
+	case 0xe6:
+	case 0xe7:
+		*exitinfo |= IOIO_TYPE_OUT;
+		port	   = (u8)insn->immediate.value & 0xffff;
+		break;
+
+	/* IN register opcodes */
+	case 0xec:
+	case 0xed:
+		*exitinfo |= IOIO_TYPE_IN;
+		port	   = ctxt->regs->dx & 0xffff;
+		break;
+
+	/* OUT register opcodes */
+	case 0xee:
+	case 0xef:
+		*exitinfo |= IOIO_TYPE_OUT;
+		port	   = ctxt->regs->dx & 0xffff;
+		break;
+
+	default:
+		return ES_DECODE_FAILED;
+	}
+
+	*exitinfo |= port << 16;
+
+	switch (insn->opcode.bytes[0]) {
+	case 0x6c:
+	case 0x6e:
+	case 0xe4:
+	case 0xe6:
+	case 0xec:
+	case 0xee:
+		/* Single byte opcodes */
+		*exitinfo |= IOIO_DATA_8;
+		size       = 1;
+		break;
+	default:
+		/* Length determined by instruction parsing */
+		*exitinfo |= (insn->opnd_bytes == 2) ? IOIO_DATA_16
+						     : IOIO_DATA_32;
+		size       = (insn->opnd_bytes == 2) ? 2 : 4;
+	}
+
+	switch (insn->addr_bytes) {
+	case 2:
+		*exitinfo |= IOIO_ADDR_16;
+		break;
+	case 4:
+		*exitinfo |= IOIO_ADDR_32;
+		break;
+	case 8:
+		*exitinfo |= IOIO_ADDR_64;
+		break;
+	}
+
+	if (insn_has_rep_prefix(insn))
+		*exitinfo |= IOIO_REP;
+
+	return vc_ioio_check(ctxt, (u16)port, size);
+}
+
+static enum es_result vc_handle_ioio(struct ghcb *ghcb, struct es_em_ctxt *ctxt)
+{
+	struct pt_regs *regs = ctxt->regs;
+	u64 exit_info_1, exit_info_2;
+	enum es_result ret;
+
+	ret = vc_ioio_exitinfo(ctxt, &exit_info_1);
+	if (ret != ES_OK)
+		return ret;
+
+	if (exit_info_1 & IOIO_TYPE_STR) {
+
+		/* (REP) INS/OUTS */
+
+		bool df = ((regs->flags & X86_EFLAGS_DF) == X86_EFLAGS_DF);
+		unsigned int io_bytes, exit_bytes;
+		unsigned int ghcb_count, op_count;
+		unsigned long es_base;
+		u64 sw_scratch;
+
+		/*
+		 * For the string variants with rep prefix the amount of in/out
+		 * operations per #VC exception is limited so that the kernel
+		 * has a chance to take interrupts and re-schedule while the
+		 * instruction is emulated.
+		 */
+		io_bytes   = (exit_info_1 >> 4) & 0x7;
+		ghcb_count = sizeof(ghcb->shared_buffer) / io_bytes;
+
+		op_count    = (exit_info_1 & IOIO_REP) ? regs->cx : 1;
+		exit_info_2 = min(op_count, ghcb_count);
+		exit_bytes  = exit_info_2 * io_bytes;
+
+		es_base = insn_get_seg_base(ctxt->regs, INAT_SEG_REG_ES);
+
+		/* Read bytes of OUTS into the shared buffer */
+		if (!(exit_info_1 & IOIO_TYPE_IN)) {
+			ret = vc_insn_string_read(ctxt,
+					       (void *)(es_base + regs->si),
+					       ghcb->shared_buffer, io_bytes,
+					       exit_info_2, df);
+			if (ret)
+				return ret;
+		}
+
+		/*
+		 * Issue an VMGEXIT to the HV to consume the bytes from the
+		 * shared buffer or to have it write them into the shared buffer
+		 * depending on the instruction: OUTS or INS.
+		 */
+		sw_scratch = __pa(ghcb) + offsetof(struct ghcb, shared_buffer);
+		ghcb_set_sw_scratch(ghcb, sw_scratch);
+		ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_IOIO,
+					  exit_info_1, exit_info_2);
+		if (ret != ES_OK)
+			return ret;
+
+		/* Read bytes from shared buffer into the guest's destination. */
+		if (exit_info_1 & IOIO_TYPE_IN) {
+			ret = vc_insn_string_write(ctxt,
+						   (void *)(es_base + regs->di),
+						   ghcb->shared_buffer, io_bytes,
+						   exit_info_2, df);
+			if (ret)
+				return ret;
+
+			if (df)
+				regs->di -= exit_bytes;
+			else
+				regs->di += exit_bytes;
+		} else {
+			if (df)
+				regs->si -= exit_bytes;
+			else
+				regs->si += exit_bytes;
+		}
+
+		if (exit_info_1 & IOIO_REP)
+			regs->cx -= exit_info_2;
+
+		ret = regs->cx ? ES_RETRY : ES_OK;
+
+	} else {
+
+		/* IN/OUT into/from rAX */
+
+		int bits = (exit_info_1 & 0x70) >> 1;
+		u64 rax = 0;
+
+		if (!(exit_info_1 & IOIO_TYPE_IN))
+			rax = lower_bits(regs->ax, bits);
+
+		ghcb_set_rax(ghcb, rax);
+
+		ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_IOIO, exit_info_1, 0);
+		if (ret != ES_OK)
+			return ret;
+
+		if (exit_info_1 & IOIO_TYPE_IN) {
+			if (!ghcb_rax_is_valid(ghcb))
+				return ES_VMM_ERROR;
+			regs->ax = lower_bits(ghcb->save.rax, bits);
+		}
+	}
+
+	return ret;
+}
+
+static int vc_handle_cpuid_snp(struct ghcb *ghcb, struct es_em_ctxt *ctxt)
+{
+	struct pt_regs *regs = ctxt->regs;
+	struct cpuid_leaf leaf;
+	int ret;
+
+	leaf.fn = regs->ax;
+	leaf.subfn = regs->cx;
+	ret = snp_cpuid(ghcb, ctxt, &leaf);
+	if (!ret) {
+		regs->ax = leaf.eax;
+		regs->bx = leaf.ebx;
+		regs->cx = leaf.ecx;
+		regs->dx = leaf.edx;
+	}
+
+	return ret;
+}
+
+static enum es_result vc_handle_cpuid(struct ghcb *ghcb,
+				      struct es_em_ctxt *ctxt)
+{
+	struct pt_regs *regs = ctxt->regs;
+	u32 cr4 = native_read_cr4();
+	enum es_result ret;
+	int snp_cpuid_ret;
+
+	snp_cpuid_ret = vc_handle_cpuid_snp(ghcb, ctxt);
+	if (!snp_cpuid_ret)
+		return ES_OK;
+	if (snp_cpuid_ret != -EOPNOTSUPP)
+		return ES_VMM_ERROR;
+
+	ghcb_set_rax(ghcb, regs->ax);
+	ghcb_set_rcx(ghcb, regs->cx);
+
+	if (cr4 & X86_CR4_OSXSAVE)
+		/* Safe to read xcr0 */
+		ghcb_set_xcr0(ghcb, xgetbv(XCR_XFEATURE_ENABLED_MASK));
+	else
+		/* xgetbv will cause #GP - use reset value for xcr0 */
+		ghcb_set_xcr0(ghcb, 1);
+
+	ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_CPUID, 0, 0);
+	if (ret != ES_OK)
+		return ret;
+
+	if (!(ghcb_rax_is_valid(ghcb) &&
+	      ghcb_rbx_is_valid(ghcb) &&
+	      ghcb_rcx_is_valid(ghcb) &&
+	      ghcb_rdx_is_valid(ghcb)))
+		return ES_VMM_ERROR;
+
+	regs->ax = ghcb->save.rax;
+	regs->bx = ghcb->save.rbx;
+	regs->cx = ghcb->save.rcx;
+	regs->dx = ghcb->save.rdx;
+
+	return ES_OK;
+}
+
+static enum es_result vc_handle_rdtsc(struct ghcb *ghcb,
+				      struct es_em_ctxt *ctxt,
+				      unsigned long exit_code)
+{
+	bool rdtscp = (exit_code == SVM_EXIT_RDTSCP);
+	enum es_result ret;
+
+	/*
+	 * The hypervisor should not be intercepting RDTSC/RDTSCP when Secure
+	 * TSC is enabled. A #VC exception will be generated if the RDTSC/RDTSCP
+	 * instructions are being intercepted. If this should occur and Secure
+	 * TSC is enabled, guest execution should be terminated as the guest
+	 * cannot rely on the TSC value provided by the hypervisor.
+	 */
+	if (sev_status & MSR_AMD64_SNP_SECURE_TSC)
+		return ES_VMM_ERROR;
+
+	ret = sev_es_ghcb_hv_call(ghcb, ctxt, exit_code, 0, 0);
+	if (ret != ES_OK)
+		return ret;
+
+	if (!(ghcb_rax_is_valid(ghcb) && ghcb_rdx_is_valid(ghcb) &&
+	     (!rdtscp || ghcb_rcx_is_valid(ghcb))))
+		return ES_VMM_ERROR;
+
+	ctxt->regs->ax = ghcb->save.rax;
+	ctxt->regs->dx = ghcb->save.rdx;
+	if (rdtscp)
+		ctxt->regs->cx = ghcb->save.rcx;
+
+	return ES_OK;
+}
diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h
index cc2881576c2c..eef0771512de 100644
--- a/arch/x86/include/asm/asm.h
+++ b/arch/x86/include/asm/asm.h
@@ -114,17 +114,12 @@
 #endif
 
 #ifndef __ASSEMBLER__
-#ifndef __pic__
 static __always_inline __pure void *rip_rel_ptr(void *p)
 {
 	asm("leaq %c1(%%rip), %0" : "=r"(p) : "i"(p));
 
 	return p;
 }
-#define RIP_REL_REF(var)	(*(typeof(&(var)))rip_rel_ptr(&(var)))
-#else
-#define RIP_REL_REF(var)	(var)
-#endif
 #endif
 
 /*
diff --git a/arch/x86/include/asm/boot.h b/arch/x86/include/asm/boot.h
index 3f02ff6d333d..02b23aa78955 100644
--- a/arch/x86/include/asm/boot.h
+++ b/arch/x86/include/asm/boot.h
@@ -74,6 +74,11 @@
 # define BOOT_STACK_SIZE	0x1000
 #endif
 
+#define TRAMPOLINE_32BIT_SIZE		(2 * PAGE_SIZE)
+
+#define TRAMPOLINE_32BIT_CODE_OFFSET	PAGE_SIZE
+#define TRAMPOLINE_32BIT_CODE_SIZE	0xA0
+
 #ifndef __ASSEMBLER__
 extern unsigned int output_len;
 extern const unsigned long kernel_text_size;
@@ -83,6 +88,11 @@ unsigned long decompress_kernel(unsigned char *outbuf, unsigned long virt_addr,
 				void (*error)(char *x));
 
 extern struct boot_params *boot_params_ptr;
+extern unsigned long *trampoline_32bit;
+extern const u16 trampoline_ljmp_imm_offset;
+
+void trampoline_32bit_src(void *trampoline, bool enable_5lvl);
+
 #endif
 
 #endif /* _ASM_X86_BOOT_H */
diff --git a/arch/x86/include/asm/coco.h b/arch/x86/include/asm/coco.h
index e7225452963f..e1dbf8df1b69 100644
--- a/arch/x86/include/asm/coco.h
+++ b/arch/x86/include/asm/coco.h
@@ -22,7 +22,7 @@ static inline u64 cc_get_mask(void)
 
 static inline void cc_set_mask(u64 mask)
 {
-	RIP_REL_REF(cc_mask) = mask;
+	cc_mask = mask;
 }
 
 u64 cc_mkenc(u64 val);
diff --git a/arch/x86/include/asm/linkage.h b/arch/x86/include/asm/linkage.h
index b51d8a4673f5..9d38ae744a2e 100644
--- a/arch/x86/include/asm/linkage.h
+++ b/arch/x86/include/asm/linkage.h
@@ -141,5 +141,15 @@
 #define SYM_FUNC_START_WEAK_NOALIGN(name)		\
 	SYM_START(name, SYM_L_WEAK, SYM_A_NONE)
 
+/*
+ * Expose 'sym' to the startup code in arch/x86/boot/startup/, by emitting an
+ * alias prefixed with __pi_
+ */
+#ifdef __ASSEMBLER__
+#define SYM_PIC_ALIAS(sym)	SYM_ALIAS(__pi_ ## sym, sym, SYM_L_GLOBAL)
+#else
+#define SYM_PIC_ALIAS(sym)	extern typeof(sym) __PASTE(__pi_, sym) __alias(sym)
+#endif
+
 #endif /* _ASM_X86_LINKAGE_H */
 
diff --git a/arch/x86/include/asm/mem_encrypt.h b/arch/x86/include/asm/mem_encrypt.h
index 1530ee301dfe..ea6494628cb0 100644
--- a/arch/x86/include/asm/mem_encrypt.h
+++ b/arch/x86/include/asm/mem_encrypt.h
@@ -61,7 +61,7 @@ void __init sev_es_init_vc_handling(void);
 
 static inline u64 sme_get_me_mask(void)
 {
-	return RIP_REL_REF(sme_me_mask);
+	return sme_me_mask;
 }
 
 #define __bss_decrypted __section(".bss..decrypted")
diff --git a/arch/x86/include/asm/page_types.h b/arch/x86/include/asm/page_types.h
index 9f77bf03d747..018a8d906ca3 100644
--- a/arch/x86/include/asm/page_types.h
+++ b/arch/x86/include/asm/page_types.h
@@ -29,9 +29,7 @@
 #define VM_DATA_DEFAULT_FLAGS	VM_DATA_FLAGS_TSK_EXEC
 
 /* Physical address where kernel should be loaded. */
-#define LOAD_PHYSICAL_ADDR ((CONFIG_PHYSICAL_START \
-				+ (CONFIG_PHYSICAL_ALIGN - 1)) \
-				& ~(CONFIG_PHYSICAL_ALIGN - 1))
+#define LOAD_PHYSICAL_ADDR	__ALIGN_KERNEL_MASK(CONFIG_PHYSICAL_START, CONFIG_PHYSICAL_ALIGN - 1)
 
 #define __START_KERNEL		(__START_KERNEL_map + LOAD_PHYSICAL_ADDR)
 
diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h
index ad9212df0ec0..6324f4c6c545 100644
--- a/arch/x86/include/asm/setup.h
+++ b/arch/x86/include/asm/setup.h
@@ -52,6 +52,7 @@ extern void reserve_standard_io_resources(void);
 extern void i386_reserve_resources(void);
 extern unsigned long __startup_64(unsigned long p2v_offset, struct boot_params *bp);
 extern void startup_64_setup_gdt_idt(void);
+extern void startup_64_load_idt(void *vc_handler);
 extern void early_setup_idt(void);
 extern void __init do_early_exception(struct pt_regs *regs, int trapnr);
 
diff --git a/arch/x86/include/asm/sev-internal.h b/arch/x86/include/asm/sev-internal.h
new file mode 100644
index 000000000000..b7232081f8f7
--- /dev/null
+++ b/arch/x86/include/asm/sev-internal.h
@@ -0,0 +1,105 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#define DR7_RESET_VALUE        0x400
+
+extern struct ghcb boot_ghcb_page;
+extern u64 sev_hv_features;
+extern u64 sev_secrets_pa;
+
+/* #VC handler runtime per-CPU data */
+struct sev_es_runtime_data {
+	struct ghcb ghcb_page;
+
+	/*
+	 * Reserve one page per CPU as backup storage for the unencrypted GHCB.
+	 * It is needed when an NMI happens while the #VC handler uses the real
+	 * GHCB, and the NMI handler itself is causing another #VC exception. In
+	 * that case the GHCB content of the first handler needs to be backed up
+	 * and restored.
+	 */
+	struct ghcb backup_ghcb;
+
+	/*
+	 * Mark the per-cpu GHCBs as in-use to detect nested #VC exceptions.
+	 * There is no need for it to be atomic, because nothing is written to
+	 * the GHCB between the read and the write of ghcb_active. So it is safe
+	 * to use it when a nested #VC exception happens before the write.
+	 *
+	 * This is necessary for example in the #VC->NMI->#VC case when the NMI
+	 * happens while the first #VC handler uses the GHCB. When the NMI code
+	 * raises a second #VC handler it might overwrite the contents of the
+	 * GHCB written by the first handler. To avoid this the content of the
+	 * GHCB is saved and restored when the GHCB is detected to be in use
+	 * already.
+	 */
+	bool ghcb_active;
+	bool backup_ghcb_active;
+
+	/*
+	 * Cached DR7 value - write it on DR7 writes and return it on reads.
+	 * That value will never make it to the real hardware DR7 as debugging
+	 * is currently unsupported in SEV-ES guests.
+	 */
+	unsigned long dr7;
+};
+
+struct ghcb_state {
+	struct ghcb *ghcb;
+};
+
+extern struct svsm_ca boot_svsm_ca_page;
+
+struct ghcb *__sev_get_ghcb(struct ghcb_state *state);
+void __sev_put_ghcb(struct ghcb_state *state);
+
+DECLARE_PER_CPU(struct sev_es_runtime_data*, runtime_data);
+DECLARE_PER_CPU(struct sev_es_save_area *, sev_vmsa);
+
+void early_set_pages_state(unsigned long vaddr, unsigned long paddr,
+			   unsigned long npages, enum psc_op op);
+
+DECLARE_PER_CPU(struct svsm_ca *, svsm_caa);
+DECLARE_PER_CPU(u64, svsm_caa_pa);
+
+extern struct svsm_ca *boot_svsm_caa;
+extern u64 boot_svsm_caa_pa;
+
+static __always_inline struct svsm_ca *svsm_get_caa(void)
+{
+	if (sev_cfg.use_cas)
+		return this_cpu_read(svsm_caa);
+	else
+		return boot_svsm_caa;
+}
+
+static __always_inline u64 svsm_get_caa_pa(void)
+{
+	if (sev_cfg.use_cas)
+		return this_cpu_read(svsm_caa_pa);
+	else
+		return boot_svsm_caa_pa;
+}
+
+int svsm_perform_call_protocol(struct svsm_call *call);
+
+static inline u64 sev_es_rd_ghcb_msr(void)
+{
+	return __rdmsr(MSR_AMD64_SEV_ES_GHCB);
+}
+
+static __always_inline void sev_es_wr_ghcb_msr(u64 val)
+{
+	u32 low, high;
+
+	low  = (u32)(val);
+	high = (u32)(val >> 32);
+
+	native_wrmsr(MSR_AMD64_SEV_ES_GHCB, low, high);
+}
+
+void snp_register_ghcb_early(unsigned long paddr);
+bool sev_es_negotiate_protocol(void);
+bool sev_es_check_cpu_features(void);
+u64 get_hv_features(void);
+
+const struct snp_cpuid_table *snp_cpuid_get_table(void);
diff --git a/arch/x86/include/asm/sev.h b/arch/x86/include/asm/sev.h
index ba7999f66abe..6158893786d6 100644
--- a/arch/x86/include/asm/sev.h
+++ b/arch/x86/include/asm/sev.h
@@ -15,6 +15,7 @@
 #include <asm/sev-common.h>
 #include <asm/coco.h>
 #include <asm/set_memory.h>
+#include <asm/svm.h>
 
 #define GHCB_PROTOCOL_MIN	1ULL
 #define GHCB_PROTOCOL_MAX	2ULL
@@ -83,6 +84,36 @@ extern void vc_no_ghcb(void);
 extern void vc_boot_ghcb(void);
 extern bool handle_vc_boot_ghcb(struct pt_regs *regs);
 
+/*
+ * Individual entries of the SNP CPUID table, as defined by the SNP
+ * Firmware ABI, Revision 0.9, Section 7.1, Table 14.
+ */
+struct snp_cpuid_fn {
+	u32 eax_in;
+	u32 ecx_in;
+	u64 xcr0_in;
+	u64 xss_in;
+	u32 eax;
+	u32 ebx;
+	u32 ecx;
+	u32 edx;
+	u64 __reserved;
+} __packed;
+
+/*
+ * SNP CPUID table, as defined by the SNP Firmware ABI, Revision 0.9,
+ * Section 8.14.2.6. Also noted there is the SNP firmware-enforced limit
+ * of 64 entries per CPUID table.
+ */
+#define SNP_CPUID_COUNT_MAX 64
+
+struct snp_cpuid_table {
+	u32 count;
+	u32 __reserved1;
+	u64 __reserved2;
+	struct snp_cpuid_fn fn[SNP_CPUID_COUNT_MAX];
+} __packed;
+
 /* PVALIDATE return codes */
 #define PVALIDATE_FAIL_SIZEMISMATCH	6
 
@@ -484,6 +515,34 @@ int snp_send_guest_request(struct snp_msg_desc *mdesc, struct snp_guest_req *req
 void __init snp_secure_tsc_prepare(void);
 void __init snp_secure_tsc_init(void);
 
+static __always_inline void vc_ghcb_invalidate(struct ghcb *ghcb)
+{
+	ghcb->save.sw_exit_code = 0;
+	__builtin_memset(ghcb->save.valid_bitmap, 0, sizeof(ghcb->save.valid_bitmap));
+}
+
+void vc_forward_exception(struct es_em_ctxt *ctxt);
+
+/* I/O parameters for CPUID-related helpers */
+struct cpuid_leaf {
+	u32 fn;
+	u32 subfn;
+	u32 eax;
+	u32 ebx;
+	u32 ecx;
+	u32 edx;
+};
+
+int snp_cpuid(struct ghcb *ghcb, struct es_em_ctxt *ctxt, struct cpuid_leaf *leaf);
+
+void __noreturn sev_es_terminate(unsigned int set, unsigned int reason);
+enum es_result sev_es_ghcb_hv_call(struct ghcb *ghcb,
+				   struct es_em_ctxt *ctxt,
+				   u64 exit_code, u64 exit_info_1,
+				   u64 exit_info_2);
+
+extern struct ghcb *boot_ghcb;
+
 #else	/* !CONFIG_AMD_MEM_ENCRYPT */
 
 #define snp_vmpl 0
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 12126adbc3a9..f0f85482a73b 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -242,6 +242,7 @@ DEFINE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page) = { .gdt = {
 #endif
 } };
 EXPORT_PER_CPU_SYMBOL_GPL(gdt_page);
+SYM_PIC_ALIAS(gdt_page);
 
 #ifdef CONFIG_X86_64
 static int __init x86_nopcid_setup(char *s)
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index fa9b6339975f..510fb41f55fc 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -47,7 +47,8 @@
  * Manage page tables very early on.
  */
 extern pmd_t early_dynamic_pgts[EARLY_DYNAMIC_PAGE_TABLES][PTRS_PER_PMD];
-static unsigned int __initdata next_early_pgt;
+unsigned int __initdata next_early_pgt;
+SYM_PIC_ALIAS(next_early_pgt);
 pmdval_t early_pmd_flags = __PAGE_KERNEL_LARGE & ~(_PAGE_GLOBAL | _PAGE_NX);
 
 #ifdef CONFIG_X86_5LEVEL
@@ -61,221 +62,15 @@ EXPORT_SYMBOL(ptrs_per_p4d);
 #ifdef CONFIG_DYNAMIC_MEMORY_LAYOUT
 unsigned long page_offset_base __ro_after_init = __PAGE_OFFSET_BASE_L4;
 EXPORT_SYMBOL(page_offset_base);
+SYM_PIC_ALIAS(page_offset_base);
 unsigned long vmalloc_base __ro_after_init = __VMALLOC_BASE_L4;
 EXPORT_SYMBOL(vmalloc_base);
+SYM_PIC_ALIAS(vmalloc_base);
 unsigned long vmemmap_base __ro_after_init = __VMEMMAP_BASE_L4;
 EXPORT_SYMBOL(vmemmap_base);
+SYM_PIC_ALIAS(vmemmap_base);
 #endif
 
-static inline bool check_la57_support(void)
-{
-	if (!IS_ENABLED(CONFIG_X86_5LEVEL))
-		return false;
-
-	/*
-	 * 5-level paging is detected and enabled at kernel decompression
-	 * stage. Only check if it has been enabled there.
-	 */
-	if (!(native_read_cr4() & X86_CR4_LA57))
-		return false;
-
-	RIP_REL_REF(__pgtable_l5_enabled)	= 1;
-	RIP_REL_REF(pgdir_shift)		= 48;
-	RIP_REL_REF(ptrs_per_p4d)		= 512;
-	RIP_REL_REF(page_offset_base)		= __PAGE_OFFSET_BASE_L5;
-	RIP_REL_REF(vmalloc_base)		= __VMALLOC_BASE_L5;
-	RIP_REL_REF(vmemmap_base)		= __VMEMMAP_BASE_L5;
-
-	return true;
-}
-
-static unsigned long __head sme_postprocess_startup(struct boot_params *bp,
-						    pmdval_t *pmd,
-						    unsigned long p2v_offset)
-{
-	unsigned long paddr, paddr_end;
-	int i;
-
-	/* Encrypt the kernel and related (if SME is active) */
-	sme_encrypt_kernel(bp);
-
-	/*
-	 * Clear the memory encryption mask from the .bss..decrypted section.
-	 * The bss section will be memset to zero later in the initialization so
-	 * there is no need to zero it after changing the memory encryption
-	 * attribute.
-	 */
-	if (sme_get_me_mask()) {
-		paddr = (unsigned long)&RIP_REL_REF(__start_bss_decrypted);
-		paddr_end = (unsigned long)&RIP_REL_REF(__end_bss_decrypted);
-
-		for (; paddr < paddr_end; paddr += PMD_SIZE) {
-			/*
-			 * On SNP, transition the page to shared in the RMP table so that
-			 * it is consistent with the page table attribute change.
-			 *
-			 * __start_bss_decrypted has a virtual address in the high range
-			 * mapping (kernel .text). PVALIDATE, by way of
-			 * early_snp_set_memory_shared(), requires a valid virtual
-			 * address but the kernel is currently running off of the identity
-			 * mapping so use the PA to get a *currently* valid virtual address.
-			 */
-			early_snp_set_memory_shared(paddr, paddr, PTRS_PER_PMD);
-
-			i = pmd_index(paddr - p2v_offset);
-			pmd[i] -= sme_get_me_mask();
-		}
-	}
-
-	/*
-	 * Return the SME encryption mask (if SME is active) to be used as a
-	 * modifier for the initial pgdir entry programmed into CR3.
-	 */
-	return sme_get_me_mask();
-}
-
-/* Code in __startup_64() can be relocated during execution, but the compiler
- * doesn't have to generate PC-relative relocations when accessing globals from
- * that function. Clang actually does not generate them, which leads to
- * boot-time crashes. To work around this problem, every global pointer must
- * be accessed using RIP_REL_REF(). Kernel virtual addresses can be determined
- * by subtracting p2v_offset from the RIP-relative address.
- */
-unsigned long __head __startup_64(unsigned long p2v_offset,
-				  struct boot_params *bp)
-{
-	pmd_t (*early_pgts)[PTRS_PER_PMD] = RIP_REL_REF(early_dynamic_pgts);
-	unsigned long physaddr = (unsigned long)&RIP_REL_REF(_text);
-	unsigned long va_text, va_end;
-	unsigned long pgtable_flags;
-	unsigned long load_delta;
-	pgdval_t *pgd;
-	p4dval_t *p4d;
-	pudval_t *pud;
-	pmdval_t *pmd, pmd_entry;
-	bool la57;
-	int i;
-
-	la57 = check_la57_support();
-
-	/* Is the address too large? */
-	if (physaddr >> MAX_PHYSMEM_BITS)
-		for (;;);
-
-	/*
-	 * Compute the delta between the address I am compiled to run at
-	 * and the address I am actually running at.
-	 */
-	load_delta = __START_KERNEL_map + p2v_offset;
-	RIP_REL_REF(phys_base) = load_delta;
-
-	/* Is the address not 2M aligned? */
-	if (load_delta & ~PMD_MASK)
-		for (;;);
-
-	va_text = physaddr - p2v_offset;
-	va_end  = (unsigned long)&RIP_REL_REF(_end) - p2v_offset;
-
-	/* Include the SME encryption mask in the fixup value */
-	load_delta += sme_get_me_mask();
-
-	/* Fixup the physical addresses in the page table */
-
-	pgd = &RIP_REL_REF(early_top_pgt)->pgd;
-	pgd[pgd_index(__START_KERNEL_map)] += load_delta;
-
-	if (IS_ENABLED(CONFIG_X86_5LEVEL) && la57) {
-		p4d = (p4dval_t *)&RIP_REL_REF(level4_kernel_pgt);
-		p4d[MAX_PTRS_PER_P4D - 1] += load_delta;
-
-		pgd[pgd_index(__START_KERNEL_map)] = (pgdval_t)p4d | _PAGE_TABLE;
-	}
-
-	RIP_REL_REF(level3_kernel_pgt)[PTRS_PER_PUD - 2].pud += load_delta;
-	RIP_REL_REF(level3_kernel_pgt)[PTRS_PER_PUD - 1].pud += load_delta;
-
-	for (i = FIXMAP_PMD_TOP; i > FIXMAP_PMD_TOP - FIXMAP_PMD_NUM; i--)
-		RIP_REL_REF(level2_fixmap_pgt)[i].pmd += load_delta;
-
-	/*
-	 * Set up the identity mapping for the switchover.  These
-	 * entries should *NOT* have the global bit set!  This also
-	 * creates a bunch of nonsense entries but that is fine --
-	 * it avoids problems around wraparound.
-	 */
-
-	pud = &early_pgts[0]->pmd;
-	pmd = &early_pgts[1]->pmd;
-	RIP_REL_REF(next_early_pgt) = 2;
-
-	pgtable_flags = _KERNPG_TABLE_NOENC + sme_get_me_mask();
-
-	if (la57) {
-		p4d = &early_pgts[RIP_REL_REF(next_early_pgt)++]->pmd;
-
-		i = (physaddr >> PGDIR_SHIFT) % PTRS_PER_PGD;
-		pgd[i + 0] = (pgdval_t)p4d + pgtable_flags;
-		pgd[i + 1] = (pgdval_t)p4d + pgtable_flags;
-
-		i = physaddr >> P4D_SHIFT;
-		p4d[(i + 0) % PTRS_PER_P4D] = (pgdval_t)pud + pgtable_flags;
-		p4d[(i + 1) % PTRS_PER_P4D] = (pgdval_t)pud + pgtable_flags;
-	} else {
-		i = (physaddr >> PGDIR_SHIFT) % PTRS_PER_PGD;
-		pgd[i + 0] = (pgdval_t)pud + pgtable_flags;
-		pgd[i + 1] = (pgdval_t)pud + pgtable_flags;
-	}
-
-	i = physaddr >> PUD_SHIFT;
-	pud[(i + 0) % PTRS_PER_PUD] = (pudval_t)pmd + pgtable_flags;
-	pud[(i + 1) % PTRS_PER_PUD] = (pudval_t)pmd + pgtable_flags;
-
-	pmd_entry = __PAGE_KERNEL_LARGE_EXEC & ~_PAGE_GLOBAL;
-	/* Filter out unsupported __PAGE_KERNEL_* bits: */
-	pmd_entry &= RIP_REL_REF(__supported_pte_mask);
-	pmd_entry += sme_get_me_mask();
-	pmd_entry +=  physaddr;
-
-	for (i = 0; i < DIV_ROUND_UP(va_end - va_text, PMD_SIZE); i++) {
-		int idx = i + (physaddr >> PMD_SHIFT);
-
-		pmd[idx % PTRS_PER_PMD] = pmd_entry + i * PMD_SIZE;
-	}
-
-	/*
-	 * Fixup the kernel text+data virtual addresses. Note that
-	 * we might write invalid pmds, when the kernel is relocated
-	 * cleanup_highmap() fixes this up along with the mappings
-	 * beyond _end.
-	 *
-	 * Only the region occupied by the kernel image has so far
-	 * been checked against the table of usable memory regions
-	 * provided by the firmware, so invalidate pages outside that
-	 * region. A page table entry that maps to a reserved area of
-	 * memory would allow processor speculation into that area,
-	 * and on some hardware (particularly the UV platform) even
-	 * speculative access to some reserved areas is caught as an
-	 * error, causing the BIOS to halt the system.
-	 */
-
-	pmd = &RIP_REL_REF(level2_kernel_pgt)->pmd;
-
-	/* invalidate pages before the kernel image */
-	for (i = 0; i < pmd_index(va_text); i++)
-		pmd[i] &= ~_PAGE_PRESENT;
-
-	/* fixup pages that are part of the kernel image */
-	for (; i <= pmd_index(va_end); i++)
-		if (pmd[i] & _PAGE_PRESENT)
-			pmd[i] += load_delta;
-
-	/* invalidate pages after the kernel image */
-	for (; i < PTRS_PER_PMD; i++)
-		pmd[i] &= ~_PAGE_PRESENT;
-
-	return sme_postprocess_startup(bp, pmd, p2v_offset);
-}
-
 /* Wipe all early page tables except for the kernel symbol map */
 static void __init reset_early_page_tables(void)
 {
@@ -513,41 +308,6 @@ void __init __noreturn x86_64_start_reservations(char *real_mode_data)
 	start_kernel();
 }
 
-/*
- * Data structures and code used for IDT setup in head_64.S. The bringup-IDT is
- * used until the idt_table takes over. On the boot CPU this happens in
- * x86_64_start_kernel(), on secondary CPUs in start_secondary(). In both cases
- * this happens in the functions called from head_64.S.
- *
- * The idt_table can't be used that early because all the code modifying it is
- * in idt.c and can be instrumented by tracing or KASAN, which both don't work
- * during early CPU bringup. Also the idt_table has the runtime vectors
- * configured which require certain CPU state to be setup already (like TSS),
- * which also hasn't happened yet in early CPU bringup.
- */
-static gate_desc bringup_idt_table[NUM_EXCEPTION_VECTORS] __page_aligned_data;
-
-/* This may run while still in the direct mapping */
-static void __head startup_64_load_idt(void *vc_handler)
-{
-	struct desc_ptr desc = {
-		.address = (unsigned long)&RIP_REL_REF(bringup_idt_table),
-		.size    = sizeof(bringup_idt_table) - 1,
-	};
-	struct idt_data data;
-	gate_desc idt_desc;
-
-	/* @vc_handler is set only for a VMM Communication Exception */
-	if (vc_handler) {
-		init_idt_data(&data, X86_TRAP_VC, vc_handler);
-		idt_init_desc(&idt_desc, &data);
-		native_write_idt_entry((gate_desc *)desc.address, X86_TRAP_VC, &idt_desc);
-	}
-
-	native_load_idt(&desc);
-}
-
-/* This is used when running on kernel addresses */
 void early_setup_idt(void)
 {
 	void *handler = NULL;
@@ -559,30 +319,3 @@ void early_setup_idt(void)
 
 	startup_64_load_idt(handler);
 }
-
-/*
- * Setup boot CPU state needed before kernel switches to virtual addresses.
- */
-void __head startup_64_setup_gdt_idt(void)
-{
-	struct desc_struct *gdt = (void *)(__force unsigned long)gdt_page.gdt;
-	void *handler = NULL;
-
-	struct desc_ptr startup_gdt_descr = {
-		.address = (unsigned long)&RIP_REL_REF(*gdt),
-		.size    = GDT_SIZE - 1,
-	};
-
-	/* Load GDT */
-	native_load_gdt(&startup_gdt_descr);
-
-	/* New GDT is live - reload data segment registers */
-	asm volatile("movl %%eax, %%ds\n"
-		     "movl %%eax, %%ss\n"
-		     "movl %%eax, %%es\n" : : "a"(__KERNEL_DS) : "memory");
-
-	if (IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT))
-		handler = &RIP_REL_REF(vc_no_ghcb);
-
-	startup_64_load_idt(handler);
-}
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index fefe2a25cf02..069420853304 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -573,6 +573,7 @@ SYM_CODE_START_NOALIGN(vc_no_ghcb)
 	/* Pure iret required here - don't use INTERRUPT_RETURN */
 	iretq
 SYM_CODE_END(vc_no_ghcb)
+SYM_PIC_ALIAS(vc_no_ghcb);
 #endif
 
 #ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION
@@ -604,10 +605,12 @@ SYM_DATA_START_PTI_ALIGNED(early_top_pgt)
 	.quad	level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC
 	.fill	PTI_USER_PGD_FILL,8,0
 SYM_DATA_END(early_top_pgt)
+SYM_PIC_ALIAS(early_top_pgt)
 
 SYM_DATA_START_PAGE_ALIGNED(early_dynamic_pgts)
 	.fill	512*EARLY_DYNAMIC_PAGE_TABLES,8,0
 SYM_DATA_END(early_dynamic_pgts)
+SYM_PIC_ALIAS(early_dynamic_pgts);
 
 SYM_DATA(early_recursion_flag, .long 0)
 
@@ -651,6 +654,7 @@ SYM_DATA_START_PAGE_ALIGNED(level4_kernel_pgt)
 	.fill	511,8,0
 	.quad	level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC
 SYM_DATA_END(level4_kernel_pgt)
+SYM_PIC_ALIAS(level4_kernel_pgt)
 #endif
 
 SYM_DATA_START_PAGE_ALIGNED(level3_kernel_pgt)
@@ -659,6 +663,7 @@ SYM_DATA_START_PAGE_ALIGNED(level3_kernel_pgt)
 	.quad	level2_kernel_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC
 	.quad	level2_fixmap_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC
 SYM_DATA_END(level3_kernel_pgt)
+SYM_PIC_ALIAS(level3_kernel_pgt)
 
 SYM_DATA_START_PAGE_ALIGNED(level2_kernel_pgt)
 	/*
@@ -676,6 +681,7 @@ SYM_DATA_START_PAGE_ALIGNED(level2_kernel_pgt)
 	 */
 	PMDS(0, __PAGE_KERNEL_LARGE_EXEC, KERNEL_IMAGE_SIZE/PMD_SIZE)
 SYM_DATA_END(level2_kernel_pgt)
+SYM_PIC_ALIAS(level2_kernel_pgt)
 
 SYM_DATA_START_PAGE_ALIGNED(level2_fixmap_pgt)
 	.fill	(512 - 4 - FIXMAP_PMD_NUM),8,0
@@ -688,6 +694,7 @@ SYM_DATA_START_PAGE_ALIGNED(level2_fixmap_pgt)
 	/* 6 MB reserved space + a 2MB hole */
 	.fill	4,8,0
 SYM_DATA_END(level2_fixmap_pgt)
+SYM_PIC_ALIAS(level2_fixmap_pgt)
 
 SYM_DATA_START_PAGE_ALIGNED(level1_fixmap_pgt)
 	.rept (FIXMAP_PMD_NUM)
@@ -703,6 +710,7 @@ SYM_DATA(smpboot_control,		.long 0)
 	.align 16
 /* This must match the first entry in level2_kernel_pgt */
 SYM_DATA(phys_base, .quad 0x0)
+SYM_PIC_ALIAS(phys_base);
 EXPORT_SYMBOL(phys_base)
 
 #include "../xen/xen-head.S"
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 9d2a13b37833..e0cf1595a0ab 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -134,6 +134,7 @@ struct ist_info ist_info;
 
 struct cpuinfo_x86 boot_cpu_data __read_mostly;
 EXPORT_SYMBOL(boot_cpu_data);
+SYM_PIC_ALIAS(boot_cpu_data);
 
 #if !defined(CONFIG_X86_PAE) || defined(CONFIG_X86_64)
 __visible unsigned long mmu_cr4_features __ro_after_init;
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index aa4d0221583c..d813f64a89d6 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -79,11 +79,13 @@ const_cpu_current_top_of_stack = cpu_current_top_of_stack;
 #define BSS_DECRYPTED						\
 	. = ALIGN(PMD_SIZE);					\
 	__start_bss_decrypted = .;				\
+	__pi___start_bss_decrypted = .;				\
 	*(.bss..decrypted);					\
 	. = ALIGN(PAGE_SIZE);					\
 	__start_bss_decrypted_unused = .;			\
 	. = ALIGN(PMD_SIZE);					\
 	__end_bss_decrypted = .;				\
+	__pi___end_bss_decrypted = .;				\
 
 #else
 
@@ -128,6 +130,7 @@ SECTIONS
 	/* Text and read-only data */
 	.text :  AT(ADDR(.text) - LOAD_OFFSET) {
 		_text = .;
+		__pi__text = .;
 		_stext = .;
 		ALIGN_ENTRY_TEXT_BEGIN
 		*(.text..__x86.rethunk_untrain)
@@ -391,6 +394,7 @@ SECTIONS
 
 	. = ALIGN(PAGE_SIZE);		/* keep VO_INIT_SIZE page aligned */
 	_end = .;
+	__pi__end = .;
 
 #ifdef CONFIG_AMD_MEM_ENCRYPT
 	/*
diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S
index 0ae2e1712e2e..12a23fa7c44c 100644
--- a/arch/x86/lib/memcpy_64.S
+++ b/arch/x86/lib/memcpy_64.S
@@ -41,6 +41,7 @@ SYM_FUNC_END(__memcpy)
 EXPORT_SYMBOL(__memcpy)
 
 SYM_FUNC_ALIAS_MEMFUNC(memcpy, __memcpy)
+SYM_PIC_ALIAS(memcpy)
 EXPORT_SYMBOL(memcpy)
 
 SYM_FUNC_START_LOCAL(memcpy_orig)
diff --git a/arch/x86/lib/memset_64.S b/arch/x86/lib/memset_64.S
index d66b710d628f..fb5a03cf5ab7 100644
--- a/arch/x86/lib/memset_64.S
+++ b/arch/x86/lib/memset_64.S
@@ -42,6 +42,7 @@ SYM_FUNC_END(__memset)
 EXPORT_SYMBOL(__memset)
 
 SYM_FUNC_ALIAS_MEMFUNC(memset, __memset)
+SYM_PIC_ALIAS(memset)
 EXPORT_SYMBOL(memset)
 
 SYM_FUNC_START_LOCAL(memset_orig)
diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S
index a26c43abd47d..9f3116609c8c 100644
--- a/arch/x86/lib/retpoline.S
+++ b/arch/x86/lib/retpoline.S
@@ -40,6 +40,7 @@ SYM_INNER_LABEL(__x86_indirect_thunk_\reg, SYM_L_GLOBAL)
 	ALTERNATIVE_2 __stringify(RETPOLINE \reg), \
 		      __stringify(lfence; ANNOTATE_RETPOLINE_SAFE; jmp *%\reg; int3), X86_FEATURE_RETPOLINE_LFENCE, \
 		      __stringify(ANNOTATE_RETPOLINE_SAFE; jmp *%\reg), ALT_NOT(X86_FEATURE_RETPOLINE)
+SYM_PIC_ALIAS(__x86_indirect_thunk_\reg)
 
 .endm
 
@@ -394,6 +395,7 @@ SYM_CODE_START(__x86_return_thunk)
 #endif
 	int3
 SYM_CODE_END(__x86_return_thunk)
+SYM_PIC_ALIAS(__x86_return_thunk)
 EXPORT_SYMBOL(__x86_return_thunk)
 
 #endif /* CONFIG_MITIGATION_RETHUNK */
diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile
index 32035d5be5a0..3faa60f13a61 100644
--- a/arch/x86/mm/Makefile
+++ b/arch/x86/mm/Makefile
@@ -3,12 +3,10 @@
 KCOV_INSTRUMENT_tlb.o			:= n
 KCOV_INSTRUMENT_mem_encrypt.o		:= n
 KCOV_INSTRUMENT_mem_encrypt_amd.o	:= n
-KCOV_INSTRUMENT_mem_encrypt_identity.o	:= n
 KCOV_INSTRUMENT_pgprot.o		:= n
 
 KASAN_SANITIZE_mem_encrypt.o		:= n
 KASAN_SANITIZE_mem_encrypt_amd.o	:= n
-KASAN_SANITIZE_mem_encrypt_identity.o	:= n
 KASAN_SANITIZE_pgprot.o		:= n
 
 # Disable KCSAN entirely, because otherwise we get warnings that some functions
@@ -16,12 +14,10 @@ KASAN_SANITIZE_pgprot.o		:= n
 KCSAN_SANITIZE := n
 # Avoid recursion by not calling KMSAN hooks for CEA code.
 KMSAN_SANITIZE_cpu_entry_area.o := n
-KMSAN_SANITIZE_mem_encrypt_identity.o := n
 
 ifdef CONFIG_FUNCTION_TRACER
 CFLAGS_REMOVE_mem_encrypt.o		= -pg
 CFLAGS_REMOVE_mem_encrypt_amd.o		= -pg
-CFLAGS_REMOVE_mem_encrypt_identity.o	= -pg
 CFLAGS_REMOVE_pgprot.o			= -pg
 endif
 
@@ -32,7 +28,6 @@ obj-y				+= pat/
 
 # Make sure __phys_addr has no stackprotector
 CFLAGS_physaddr.o		:= -fno-stack-protector
-CFLAGS_mem_encrypt_identity.o	:= -fno-stack-protector
 
 CFLAGS_fault.o := -I $(src)/../include/asm/trace
 
@@ -63,5 +58,4 @@ obj-$(CONFIG_MITIGATION_PAGE_TABLE_ISOLATION)	+= pti.o
 obj-$(CONFIG_X86_MEM_ENCRYPT)	+= mem_encrypt.o
 obj-$(CONFIG_AMD_MEM_ENCRYPT)	+= mem_encrypt_amd.o
 
-obj-$(CONFIG_AMD_MEM_ENCRYPT)	+= mem_encrypt_identity.o
 obj-$(CONFIG_AMD_MEM_ENCRYPT)	+= mem_encrypt_boot.o
diff --git a/arch/x86/mm/mem_encrypt_amd.c b/arch/x86/mm/mem_encrypt_amd.c
index 7490ff6d83b1..faf3a13fb6ba 100644
--- a/arch/x86/mm/mem_encrypt_amd.c
+++ b/arch/x86/mm/mem_encrypt_amd.c
@@ -40,7 +40,9 @@
  * section is later cleared.
  */
 u64 sme_me_mask __section(".data") = 0;
+SYM_PIC_ALIAS(sme_me_mask);
 u64 sev_status __section(".data") = 0;
+SYM_PIC_ALIAS(sev_status);
 u64 sev_check_data __section(".data") = 0;
 EXPORT_SYMBOL(sme_me_mask);
 
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index f7ae44d3dd9e..e62af72923e8 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -10,6 +10,7 @@
 #ifdef CONFIG_DYNAMIC_PHYSICAL_MASK
 phys_addr_t physical_mask __ro_after_init = (1ULL << __PHYSICAL_MASK_SHIFT) - 1;
 EXPORT_SYMBOL(physical_mask);
+SYM_PIC_ALIAS(physical_mask);
 #endif
 
 pgtable_t pte_alloc_one(struct mm_struct *mm)
diff --git a/drivers/firmware/efi/libstub/Makefile b/drivers/firmware/efi/libstub/Makefile
index d23a1b9fed75..2f173391b63d 100644
--- a/drivers/firmware/efi/libstub/Makefile
+++ b/drivers/firmware/efi/libstub/Makefile
@@ -85,7 +85,6 @@ lib-$(CONFIG_EFI_GENERIC_STUB)	+= efi-stub.o string.o intrinsics.o systable.o \
 lib-$(CONFIG_ARM)		+= arm32-stub.o
 lib-$(CONFIG_ARM64)		+= kaslr.o arm64.o arm64-stub.o smbios.o
 lib-$(CONFIG_X86)		+= x86-stub.o smbios.o
-lib-$(CONFIG_EFI_MIXED)		+= x86-mixed.o
 lib-$(CONFIG_X86_64)		+= x86-5lvl.o
 lib-$(CONFIG_RISCV)		+= kaslr.o riscv.o riscv-stub.o
 lib-$(CONFIG_LOONGARCH)		+= loongarch.o loongarch-stub.o
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 58a635a6d5bd..66409bc3a4e0 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -108,13 +108,13 @@ defined(CONFIG_AUTOFDO_CLANG) || defined(CONFIG_PROPELLER_CLANG)
 #define TEXT_MAIN .text
 #endif
 #if defined(CONFIG_LD_DEAD_CODE_DATA_ELIMINATION) || defined(CONFIG_LTO_CLANG)
-#define DATA_MAIN .data .data.[0-9a-zA-Z_]* .data..L* .data..compoundliteral* .data.$__unnamed_* .data.$L*
+#define DATA_MAIN .data .data.[0-9a-zA-Z_]* .data.rel.* .data..L* .data..compoundliteral* .data.$__unnamed_* .data.$L*
 #define SDATA_MAIN .sdata .sdata.[0-9a-zA-Z_]*
 #define RODATA_MAIN .rodata .rodata.[0-9a-zA-Z_]* .rodata..L*
 #define BSS_MAIN .bss .bss.[0-9a-zA-Z_]* .bss..L* .bss..compoundliteral*
 #define SBSS_MAIN .sbss .sbss.[0-9a-zA-Z_]*
 #else
-#define DATA_MAIN .data
+#define DATA_MAIN .data .data.rel .data.rel.local
 #define SDATA_MAIN .sdata
 #define RODATA_MAIN .rodata
 #define BSS_MAIN .bss
diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c
index 3ce7b54003c2..331b9a744410 100644
--- a/tools/objtool/arch/x86/decode.c
+++ b/tools/objtool/arch/x86/decode.c
@@ -842,12 +842,14 @@ int arch_decode_hint_reg(u8 sp_reg, int *base)
 
 bool arch_is_retpoline(struct symbol *sym)
 {
-	return !strncmp(sym->name, "__x86_indirect_", 15);
+	return !strncmp(sym->name, "__x86_indirect_", 15) ||
+	       !strncmp(sym->name, "__pi___x86_indirect_", 20);
 }
 
 bool arch_is_rethunk(struct symbol *sym)
 {
-	return !strcmp(sym->name, "__x86_return_thunk");
+	return !strcmp(sym->name, "__x86_return_thunk") ||
+	       !strcmp(sym->name, "__pi___x86_return_thunk");
 }
 
 bool arch_is_embedded_insn(struct symbol *sym)