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

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

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

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

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

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

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

  Work by Joerg Roedel and Thomas Lendacky and others"

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

11 files changed, 781 insertions, 207 deletions

diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index 4fb989ef5665..ee249088cbfe 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -32,7 +32,7 @@ KBUILD_CFLAGS := -m$(BITS) -O2
 KBUILD_CFLAGS += -fno-strict-aliasing -fPIE
 KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING
 cflags-$(CONFIG_X86_32) := -march=i386
-cflags-$(CONFIG_X86_64) := -mcmodel=small
+cflags-$(CONFIG_X86_64) := -mcmodel=small -mno-red-zone
 KBUILD_CFLAGS += $(cflags-y)
 KBUILD_CFLAGS += -mno-mmx -mno-sse
 KBUILD_CFLAGS += -ffreestanding
@@ -47,6 +47,11 @@ KBUILD_CFLAGS += -D__DISABLE_EXPORTS
 KBUILD_CFLAGS += $(call as-option,-Wa$(comma)-mrelax-relocations=no)
 KBUILD_CFLAGS += -include $(srctree)/include/linux/hidden.h
 
+# sev-es.c indirectly inludes inat-table.h which is generated during
+# compilation and stored in $(objtree). Add the directory to the includes so
+# that the compiler finds it even with out-of-tree builds (make O=/some/path).
+CFLAGS_sev-es.o += -I$(objtree)/arch/x86/lib/
+
 KBUILD_AFLAGS  := $(KBUILD_CFLAGS) -D__ASSEMBLY__
 GCOV_PROFILE := n
 UBSAN_SANITIZE :=n
@@ -81,9 +86,11 @@ vmlinux-objs-y := $(obj)/vmlinux.lds $(obj)/kernel_info.o $(obj)/head_$(BITS).o
 vmlinux-objs-$(CONFIG_EARLY_PRINTK) += $(obj)/early_serial_console.o
 vmlinux-objs-$(CONFIG_RANDOMIZE_BASE) += $(obj)/kaslr.o
 ifdef CONFIG_X86_64
-	vmlinux-objs-$(CONFIG_RANDOMIZE_BASE) += $(obj)/kaslr_64.o
+	vmlinux-objs-y += $(obj)/ident_map_64.o
+	vmlinux-objs-y += $(obj)/idt_64.o $(obj)/idt_handlers_64.o
 	vmlinux-objs-y += $(obj)/mem_encrypt.o
 	vmlinux-objs-y += $(obj)/pgtable_64.o
+	vmlinux-objs-$(CONFIG_AMD_MEM_ENCRYPT) += $(obj)/sev-es.o
 endif
 
 vmlinux-objs-$(CONFIG_ACPI) += $(obj)/acpi.o
diff --git a/arch/x86/boot/compressed/cpuflags.c b/arch/x86/boot/compressed/cpuflags.c
index 6448a8196d32..0cc1323896d1 100644
--- a/arch/x86/boot/compressed/cpuflags.c
+++ b/arch/x86/boot/compressed/cpuflags.c
@@ -1,6 +1,4 @@
 // SPDX-License-Identifier: GPL-2.0
-#ifdef CONFIG_RANDOMIZE_BASE
-
 #include "../cpuflags.c"
 
 bool has_cpuflag(int flag)
@@ -9,5 +7,3 @@ bool has_cpuflag(int flag)
 
 	return test_bit(flag, cpu.flags);
 }
-
-#endif
diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S
index 9e46729cf162..1c80f1738fd9 100644
--- a/arch/x86/boot/compressed/head_64.S
+++ b/arch/x86/boot/compressed/head_64.S
@@ -33,6 +33,7 @@
 #include <asm/processor-flags.h>
 #include <asm/asm-offsets.h>
 #include <asm/bootparam.h>
+#include <asm/desc_defs.h>
 #include "pgtable.h"
 
 /*
@@ -415,6 +416,10 @@ SYM_CODE_START(startup_64)
 
 .Lon_kernel_cs:
 
+	pushq	%rsi
+	call	load_stage1_idt
+	popq	%rsi
+
 	/*
 	 * paging_prepare() sets up the trampoline and checks if we need to
 	 * enable 5-level paging.
@@ -528,6 +533,21 @@ SYM_FUNC_START_LOCAL_NOALIGN(.Lrelocated)
 	rep	stosq
 
 /*
+ * If running as an SEV guest, the encryption mask is required in the
+ * page-table setup code below. When the guest also has SEV-ES enabled
+ * set_sev_encryption_mask() will cause #VC exceptions, but the stage2
+ * handler can't map its GHCB because the page-table is not set up yet.
+ * So set up the encryption mask here while still on the stage1 #VC
+ * handler. Then load stage2 IDT and switch to the kernel's own
+ * page-table.
+ */
+	pushq	%rsi
+	call	set_sev_encryption_mask
+	call	load_stage2_idt
+	call	initialize_identity_maps
+	popq	%rsi
+
+/*
  * Do the extraction, and jump to the new kernel..
  */
 	pushq	%rsi			/* Save the real mode argument */
@@ -659,10 +679,21 @@ SYM_DATA_START_LOCAL(gdt)
 	.quad   0x0000000000000000	/* TS continued */
 SYM_DATA_END_LABEL(gdt, SYM_L_LOCAL, gdt_end)
 
+SYM_DATA_START(boot_idt_desc)
+	.word	boot_idt_end - boot_idt - 1
+	.quad	0
+SYM_DATA_END(boot_idt_desc)
+	.balign 8
+SYM_DATA_START(boot_idt)
+	.rept	BOOT_IDT_ENTRIES
+	.quad	0
+	.quad	0
+	.endr
+SYM_DATA_END_LABEL(boot_idt, SYM_L_GLOBAL, boot_idt_end)
+
 #ifdef CONFIG_EFI_STUB
 SYM_DATA(image_offset, .long 0)
 #endif
-
 #ifdef CONFIG_EFI_MIXED
 SYM_DATA_LOCAL(efi32_boot_args, .long 0, 0, 0)
 SYM_DATA(efi_is64, .byte 1)
diff --git a/arch/x86/boot/compressed/ident_map_64.c b/arch/x86/boot/compressed/ident_map_64.c
new file mode 100644
index 000000000000..063a60edcf99
--- /dev/null
+++ b/arch/x86/boot/compressed/ident_map_64.c
@@ -0,0 +1,349 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * This code is used on x86_64 to create page table identity mappings on
+ * demand by building up a new set of page tables (or appending to the
+ * existing ones), and then switching over to them when ready.
+ *
+ * Copyright (C) 2015-2016  Yinghai Lu
+ * Copyright (C)      2016  Kees Cook
+ */
+
+/*
+ * Since we're dealing with identity mappings, physical and virtual
+ * addresses are the same, so override these defines which are ultimately
+ * used by the headers in misc.h.
+ */
+#define __pa(x)  ((unsigned long)(x))
+#define __va(x)  ((void *)((unsigned long)(x)))
+
+/* No PAGE_TABLE_ISOLATION support needed either: */
+#undef CONFIG_PAGE_TABLE_ISOLATION
+
+#include "error.h"
+#include "misc.h"
+
+/* These actually do the work of building the kernel identity maps. */
+#include <linux/pgtable.h>
+#include <asm/cmpxchg.h>
+#include <asm/trap_pf.h>
+#include <asm/trapnr.h>
+#include <asm/init.h>
+/* Use the static base for this part of the boot process */
+#undef __PAGE_OFFSET
+#define __PAGE_OFFSET __PAGE_OFFSET_BASE
+#include "../../mm/ident_map.c"
+
+#ifdef CONFIG_X86_5LEVEL
+unsigned int __pgtable_l5_enabled;
+unsigned int pgdir_shift = 39;
+unsigned int ptrs_per_p4d = 1;
+#endif
+
+/* Used by PAGE_KERN* macros: */
+pteval_t __default_kernel_pte_mask __read_mostly = ~0;
+
+/* Used to track our page table allocation area. */
+struct alloc_pgt_data {
+	unsigned char *pgt_buf;
+	unsigned long pgt_buf_size;
+	unsigned long pgt_buf_offset;
+};
+
+/*
+ * Allocates space for a page table entry, using struct alloc_pgt_data
+ * above. Besides the local callers, this is used as the allocation
+ * callback in mapping_info below.
+ */
+static void *alloc_pgt_page(void *context)
+{
+	struct alloc_pgt_data *pages = (struct alloc_pgt_data *)context;
+	unsigned char *entry;
+
+	/* Validate there is space available for a new page. */
+	if (pages->pgt_buf_offset >= pages->pgt_buf_size) {
+		debug_putstr("out of pgt_buf in " __FILE__ "!?\n");
+		debug_putaddr(pages->pgt_buf_offset);
+		debug_putaddr(pages->pgt_buf_size);
+		return NULL;
+	}
+
+	entry = pages->pgt_buf + pages->pgt_buf_offset;
+	pages->pgt_buf_offset += PAGE_SIZE;
+
+	return entry;
+}
+
+/* Used to track our allocated page tables. */
+static struct alloc_pgt_data pgt_data;
+
+/* The top level page table entry pointer. */
+static unsigned long top_level_pgt;
+
+phys_addr_t physical_mask = (1ULL << __PHYSICAL_MASK_SHIFT) - 1;
+
+/*
+ * Mapping information structure passed to kernel_ident_mapping_init().
+ * Due to relocation, pointers must be assigned at run time not build time.
+ */
+static struct x86_mapping_info mapping_info;
+
+/*
+ * Adds the specified range to the identity mappings.
+ */
+static void add_identity_map(unsigned long start, unsigned long end)
+{
+	int ret;
+
+	/* Align boundary to 2M. */
+	start = round_down(start, PMD_SIZE);
+	end = round_up(end, PMD_SIZE);
+	if (start >= end)
+		return;
+
+	/* Build the mapping. */
+	ret = kernel_ident_mapping_init(&mapping_info, (pgd_t *)top_level_pgt, start, end);
+	if (ret)
+		error("Error: kernel_ident_mapping_init() failed\n");
+}
+
+/* Locates and clears a region for a new top level page table. */
+void initialize_identity_maps(void)
+{
+	/* Exclude the encryption mask from __PHYSICAL_MASK */
+	physical_mask &= ~sme_me_mask;
+
+	/* Init mapping_info with run-time function/buffer pointers. */
+	mapping_info.alloc_pgt_page = alloc_pgt_page;
+	mapping_info.context = &pgt_data;
+	mapping_info.page_flag = __PAGE_KERNEL_LARGE_EXEC | sme_me_mask;
+	mapping_info.kernpg_flag = _KERNPG_TABLE;
+
+	/*
+	 * It should be impossible for this not to already be true,
+	 * but since calling this a second time would rewind the other
+	 * counters, let's just make sure this is reset too.
+	 */
+	pgt_data.pgt_buf_offset = 0;
+
+	/*
+	 * If we came here via startup_32(), cr3 will be _pgtable already
+	 * and we must append to the existing area instead of entirely
+	 * overwriting it.
+	 *
+	 * With 5-level paging, we use '_pgtable' to allocate the p4d page table,
+	 * the top-level page table is allocated separately.
+	 *
+	 * p4d_offset(top_level_pgt, 0) would cover both the 4- and 5-level
+	 * cases. On 4-level paging it's equal to 'top_level_pgt'.
+	 */
+	top_level_pgt = read_cr3_pa();
+	if (p4d_offset((pgd_t *)top_level_pgt, 0) == (p4d_t *)_pgtable) {
+		pgt_data.pgt_buf = _pgtable + BOOT_INIT_PGT_SIZE;
+		pgt_data.pgt_buf_size = BOOT_PGT_SIZE - BOOT_INIT_PGT_SIZE;
+		memset(pgt_data.pgt_buf, 0, pgt_data.pgt_buf_size);
+	} else {
+		pgt_data.pgt_buf = _pgtable;
+		pgt_data.pgt_buf_size = BOOT_PGT_SIZE;
+		memset(pgt_data.pgt_buf, 0, pgt_data.pgt_buf_size);
+		top_level_pgt = (unsigned long)alloc_pgt_page(&pgt_data);
+	}
+
+	/*
+	 * New page-table is set up - map the kernel image and load it
+	 * into cr3.
+	 */
+	add_identity_map((unsigned long)_head, (unsigned long)_end);
+	write_cr3(top_level_pgt);
+}
+
+/*
+ * This switches the page tables to the new level4 that has been built
+ * via calls to add_identity_map() above. If booted via startup_32(),
+ * this is effectively a no-op.
+ */
+void finalize_identity_maps(void)
+{
+	write_cr3(top_level_pgt);
+}
+
+static pte_t *split_large_pmd(struct x86_mapping_info *info,
+			      pmd_t *pmdp, unsigned long __address)
+{
+	unsigned long page_flags;
+	unsigned long address;
+	pte_t *pte;
+	pmd_t pmd;
+	int i;
+
+	pte = (pte_t *)info->alloc_pgt_page(info->context);
+	if (!pte)
+		return NULL;
+
+	address     = __address & PMD_MASK;
+	/* No large page - clear PSE flag */
+	page_flags  = info->page_flag & ~_PAGE_PSE;
+
+	/* Populate the PTEs */
+	for (i = 0; i < PTRS_PER_PMD; i++) {
+		set_pte(&pte[i], __pte(address | page_flags));
+		address += PAGE_SIZE;
+	}
+
+	/*
+	 * Ideally we need to clear the large PMD first and do a TLB
+	 * flush before we write the new PMD. But the 2M range of the
+	 * PMD might contain the code we execute and/or the stack
+	 * we are on, so we can't do that. But that should be safe here
+	 * because we are going from large to small mappings and we are
+	 * also the only user of the page-table, so there is no chance
+	 * of a TLB multihit.
+	 */
+	pmd = __pmd((unsigned long)pte | info->kernpg_flag);
+	set_pmd(pmdp, pmd);
+	/* Flush TLB to establish the new PMD */
+	write_cr3(top_level_pgt);
+
+	return pte + pte_index(__address);
+}
+
+static void clflush_page(unsigned long address)
+{
+	unsigned int flush_size;
+	char *cl, *start, *end;
+
+	/*
+	 * Hardcode cl-size to 64 - CPUID can't be used here because that might
+	 * cause another #VC exception and the GHCB is not ready to use yet.
+	 */
+	flush_size = 64;
+	start      = (char *)(address & PAGE_MASK);
+	end        = start + PAGE_SIZE;
+
+	/*
+	 * First make sure there are no pending writes on the cache-lines to
+	 * flush.
+	 */
+	asm volatile("mfence" : : : "memory");
+
+	for (cl = start; cl != end; cl += flush_size)
+		clflush(cl);
+}
+
+static int set_clr_page_flags(struct x86_mapping_info *info,
+			      unsigned long address,
+			      pteval_t set, pteval_t clr)
+{
+	pgd_t *pgdp = (pgd_t *)top_level_pgt;
+	p4d_t *p4dp;
+	pud_t *pudp;
+	pmd_t *pmdp;
+	pte_t *ptep, pte;
+
+	/*
+	 * First make sure there is a PMD mapping for 'address'.
+	 * It should already exist, but keep things generic.
+	 *
+	 * To map the page just read from it and fault it in if there is no
+	 * mapping yet. add_identity_map() can't be called here because that
+	 * would unconditionally map the address on PMD level, destroying any
+	 * PTE-level mappings that might already exist. Use assembly here so
+	 * the access won't be optimized away.
+	 */
+	asm volatile("mov %[address], %%r9"
+		     :: [address] "g" (*(unsigned long *)address)
+		     : "r9", "memory");
+
+	/*
+	 * The page is mapped at least with PMD size - so skip checks and walk
+	 * directly to the PMD.
+	 */
+	p4dp = p4d_offset(pgdp, address);
+	pudp = pud_offset(p4dp, address);
+	pmdp = pmd_offset(pudp, address);
+
+	if (pmd_large(*pmdp))
+		ptep = split_large_pmd(info, pmdp, address);
+	else
+		ptep = pte_offset_kernel(pmdp, address);
+
+	if (!ptep)
+		return -ENOMEM;
+
+	/*
+	 * Changing encryption attributes of a page requires to flush it from
+	 * the caches.
+	 */
+	if ((set | clr) & _PAGE_ENC)
+		clflush_page(address);
+
+	/* Update PTE */
+	pte = *ptep;
+	pte = pte_set_flags(pte, set);
+	pte = pte_clear_flags(pte, clr);
+	set_pte(ptep, pte);
+
+	/* Flush TLB after changing encryption attribute */
+	write_cr3(top_level_pgt);
+
+	return 0;
+}
+
+int set_page_decrypted(unsigned long address)
+{
+	return set_clr_page_flags(&mapping_info, address, 0, _PAGE_ENC);
+}
+
+int set_page_encrypted(unsigned long address)
+{
+	return set_clr_page_flags(&mapping_info, address, _PAGE_ENC, 0);
+}
+
+int set_page_non_present(unsigned long address)
+{
+	return set_clr_page_flags(&mapping_info, address, 0, _PAGE_PRESENT);
+}
+
+static void do_pf_error(const char *msg, unsigned long error_code,
+			unsigned long address, unsigned long ip)
+{
+	error_putstr(msg);
+
+	error_putstr("\nError Code: ");
+	error_puthex(error_code);
+	error_putstr("\nCR2: 0x");
+	error_puthex(address);
+	error_putstr("\nRIP relative to _head: 0x");
+	error_puthex(ip - (unsigned long)_head);
+	error_putstr("\n");
+
+	error("Stopping.\n");
+}
+
+void do_boot_page_fault(struct pt_regs *regs, unsigned long error_code)
+{
+	unsigned long address = native_read_cr2();
+	unsigned long end;
+	bool ghcb_fault;
+
+	ghcb_fault = sev_es_check_ghcb_fault(address);
+
+	address   &= PMD_MASK;
+	end        = address + PMD_SIZE;
+
+	/*
+	 * Check for unexpected error codes. Unexpected are:
+	 *	- Faults on present pages
+	 *	- User faults
+	 *	- Reserved bits set
+	 */
+	if (error_code & (X86_PF_PROT | X86_PF_USER | X86_PF_RSVD))
+		do_pf_error("Unexpected page-fault:", error_code, address, regs->ip);
+	else if (ghcb_fault)
+		do_pf_error("Page-fault on GHCB page:", error_code, address, regs->ip);
+
+	/*
+	 * Error code is sane - now identity map the 2M region around
+	 * the faulting address.
+	 */
+	add_identity_map(address, end);
+}
diff --git a/arch/x86/boot/compressed/idt_64.c b/arch/x86/boot/compressed/idt_64.c
new file mode 100644
index 000000000000..804a502ee0d2
--- /dev/null
+++ b/arch/x86/boot/compressed/idt_64.c
@@ -0,0 +1,54 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <asm/trap_pf.h>
+#include <asm/segment.h>
+#include <asm/trapnr.h>
+#include "misc.h"
+
+static void set_idt_entry(int vector, void (*handler)(void))
+{
+	unsigned long address = (unsigned long)handler;
+	gate_desc entry;
+
+	memset(&entry, 0, sizeof(entry));
+
+	entry.offset_low    = (u16)(address & 0xffff);
+	entry.segment       = __KERNEL_CS;
+	entry.bits.type     = GATE_TRAP;
+	entry.bits.p        = 1;
+	entry.offset_middle = (u16)((address >> 16) & 0xffff);
+	entry.offset_high   = (u32)(address >> 32);
+
+	memcpy(&boot_idt[vector], &entry, sizeof(entry));
+}
+
+/* Have this here so we don't need to include <asm/desc.h> */
+static void load_boot_idt(const struct desc_ptr *dtr)
+{
+	asm volatile("lidt %0"::"m" (*dtr));
+}
+
+/* Setup IDT before kernel jumping to  .Lrelocated */
+void load_stage1_idt(void)
+{
+	boot_idt_desc.address = (unsigned long)boot_idt;
+
+
+	if (IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT))
+		set_idt_entry(X86_TRAP_VC, boot_stage1_vc);
+
+	load_boot_idt(&boot_idt_desc);
+}
+
+/* Setup IDT after kernel jumping to  .Lrelocated */
+void load_stage2_idt(void)
+{
+	boot_idt_desc.address = (unsigned long)boot_idt;
+
+	set_idt_entry(X86_TRAP_PF, boot_page_fault);
+
+#ifdef CONFIG_AMD_MEM_ENCRYPT
+	set_idt_entry(X86_TRAP_VC, boot_stage2_vc);
+#endif
+
+	load_boot_idt(&boot_idt_desc);
+}
diff --git a/arch/x86/boot/compressed/idt_handlers_64.S b/arch/x86/boot/compressed/idt_handlers_64.S
new file mode 100644
index 000000000000..22890e199f5b
--- /dev/null
+++ b/arch/x86/boot/compressed/idt_handlers_64.S
@@ -0,0 +1,77 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Early IDT handler entry points
+ *
+ * Copyright (C) 2019 SUSE
+ *
+ * Author: Joerg Roedel <jroedel@suse.de>
+ */
+
+#include <asm/segment.h>
+
+/* For ORIG_RAX */
+#include "../../entry/calling.h"
+
+.macro EXCEPTION_HANDLER name function error_code=0
+SYM_FUNC_START(\name)
+
+	/* Build pt_regs */
+	.if \error_code == 0
+	pushq   $0
+	.endif
+
+	pushq   %rdi
+	pushq   %rsi
+	pushq   %rdx
+	pushq   %rcx
+	pushq   %rax
+	pushq   %r8
+	pushq   %r9
+	pushq   %r10
+	pushq   %r11
+	pushq   %rbx
+	pushq   %rbp
+	pushq   %r12
+	pushq   %r13
+	pushq   %r14
+	pushq   %r15
+
+	/* Call handler with pt_regs */
+	movq    %rsp, %rdi
+	/* Error code is second parameter */
+	movq	ORIG_RAX(%rsp), %rsi
+	call    \function
+
+	/* Restore regs */
+	popq    %r15
+	popq    %r14
+	popq    %r13
+	popq    %r12
+	popq    %rbp
+	popq    %rbx
+	popq    %r11
+	popq    %r10
+	popq    %r9
+	popq    %r8
+	popq    %rax
+	popq    %rcx
+	popq    %rdx
+	popq    %rsi
+	popq    %rdi
+
+	/* Remove error code and return */
+	addq    $8, %rsp
+
+	iretq
+SYM_FUNC_END(\name)
+	.endm
+
+	.text
+	.code64
+
+EXCEPTION_HANDLER	boot_page_fault do_boot_page_fault error_code=1
+
+#ifdef CONFIG_AMD_MEM_ENCRYPT
+EXCEPTION_HANDLER	boot_stage1_vc do_vc_no_ghcb		error_code=1
+EXCEPTION_HANDLER	boot_stage2_vc do_boot_stage2_vc	error_code=1
+#endif
diff --git a/arch/x86/boot/compressed/kaslr.c b/arch/x86/boot/compressed/kaslr.c
index 877970d76249..b59547ce5b19 100644
--- a/arch/x86/boot/compressed/kaslr.c
+++ b/arch/x86/boot/compressed/kaslr.c
@@ -40,17 +40,8 @@
 #include <asm/setup.h>	/* For COMMAND_LINE_SIZE */
 #undef _SETUP
 
-#ifdef CONFIG_X86_5LEVEL
-unsigned int __pgtable_l5_enabled;
-unsigned int pgdir_shift __ro_after_init = 39;
-unsigned int ptrs_per_p4d __ro_after_init = 1;
-#endif
-
 extern unsigned long get_cmd_line_ptr(void);
 
-/* Used by PAGE_KERN* macros: */
-pteval_t __default_kernel_pte_mask __read_mostly = ~0;
-
 /* Simplified build-specific string for starting entropy. */
 static const char build_str[] = UTS_RELEASE " (" LINUX_COMPILE_BY "@"
 		LINUX_COMPILE_HOST ") (" LINUX_COMPILER ") " UTS_VERSION;
@@ -406,8 +397,6 @@ static void mem_avoid_init(unsigned long input, unsigned long input_size,
 	 */
 	mem_avoid[MEM_AVOID_ZO_RANGE].start = input;
 	mem_avoid[MEM_AVOID_ZO_RANGE].size = (output + init_size) - input;
-	add_identity_map(mem_avoid[MEM_AVOID_ZO_RANGE].start,
-			 mem_avoid[MEM_AVOID_ZO_RANGE].size);
 
 	/* Avoid initrd. */
 	initrd_start  = (u64)boot_params->ext_ramdisk_image << 32;
@@ -425,15 +414,11 @@ static void mem_avoid_init(unsigned long input, unsigned long input_size,
 		cmd_line_size = strnlen((char *)cmd_line, COMMAND_LINE_SIZE-1) + 1;
 		mem_avoid[MEM_AVOID_CMDLINE].start = cmd_line;
 		mem_avoid[MEM_AVOID_CMDLINE].size = cmd_line_size;
-		add_identity_map(mem_avoid[MEM_AVOID_CMDLINE].start,
-				 mem_avoid[MEM_AVOID_CMDLINE].size);
 	}
 
 	/* Avoid boot parameters. */
 	mem_avoid[MEM_AVOID_BOOTPARAMS].start = (unsigned long)boot_params;
 	mem_avoid[MEM_AVOID_BOOTPARAMS].size = sizeof(*boot_params);
-	add_identity_map(mem_avoid[MEM_AVOID_BOOTPARAMS].start,
-			 mem_avoid[MEM_AVOID_BOOTPARAMS].size);
 
 	/* We don't need to set a mapping for setup_data. */
 
@@ -442,11 +427,6 @@ static void mem_avoid_init(unsigned long input, unsigned long input_size,
 
 	/* Enumerate the immovable memory regions */
 	num_immovable_mem = count_immovable_mem_regions();
-
-#ifdef CONFIG_X86_VERBOSE_BOOTUP
-	/* Make sure video RAM can be used. */
-	add_identity_map(0, PMD_SIZE);
-#endif
 }
 
 /*
@@ -870,9 +850,6 @@ void choose_random_location(unsigned long input,
 
 	boot_params->hdr.loadflags |= KASLR_FLAG;
 
-	/* Prepare to add new identity pagetables on demand. */
-	initialize_identity_maps();
-
 	if (IS_ENABLED(CONFIG_X86_32))
 		mem_limit = KERNEL_IMAGE_SIZE;
 	else
@@ -896,19 +873,8 @@ void choose_random_location(unsigned long input,
 		warn("Physical KASLR disabled: no suitable memory region!");
 	} else {
 		/* Update the new physical address location. */
-		if (*output != random_addr) {
-			add_identity_map(random_addr, output_size);
+		if (*output != random_addr)
 			*output = random_addr;
-		}
-
-		/*
-		 * This loads the identity mapping page table.
-		 * This should only be done if a new physical address
-		 * is found for the kernel, otherwise we should keep
-		 * the old page table to make it be like the "nokaslr"
-		 * case.
-		 */
-		finalize_identity_maps();
 	}
 
 
diff --git a/arch/x86/boot/compressed/kaslr_64.c b/arch/x86/boot/compressed/kaslr_64.c
deleted file mode 100644
index f9c5c13d979b..000000000000
--- a/arch/x86/boot/compressed/kaslr_64.c
+++ /dev/null
@@ -1,153 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * This code is used on x86_64 to create page table identity mappings on
- * demand by building up a new set of page tables (or appending to the
- * existing ones), and then switching over to them when ready.
- *
- * Copyright (C) 2015-2016  Yinghai Lu
- * Copyright (C)      2016  Kees Cook
- */
-
-/*
- * Since we're dealing with identity mappings, physical and virtual
- * addresses are the same, so override these defines which are ultimately
- * used by the headers in misc.h.
- */
-#define __pa(x)  ((unsigned long)(x))
-#define __va(x)  ((void *)((unsigned long)(x)))
-
-/* No PAGE_TABLE_ISOLATION support needed either: */
-#undef CONFIG_PAGE_TABLE_ISOLATION
-
-#include "misc.h"
-
-/* These actually do the work of building the kernel identity maps. */
-#include <linux/pgtable.h>
-#include <asm/init.h>
-/* Use the static base for this part of the boot process */
-#undef __PAGE_OFFSET
-#define __PAGE_OFFSET __PAGE_OFFSET_BASE
-#include "../../mm/ident_map.c"
-
-/* Used to track our page table allocation area. */
-struct alloc_pgt_data {
-	unsigned char *pgt_buf;
-	unsigned long pgt_buf_size;
-	unsigned long pgt_buf_offset;
-};
-
-/*
- * Allocates space for a page table entry, using struct alloc_pgt_data
- * above. Besides the local callers, this is used as the allocation
- * callback in mapping_info below.
- */
-static void *alloc_pgt_page(void *context)
-{
-	struct alloc_pgt_data *pages = (struct alloc_pgt_data *)context;
-	unsigned char *entry;
-
-	/* Validate there is space available for a new page. */
-	if (pages->pgt_buf_offset >= pages->pgt_buf_size) {
-		debug_putstr("out of pgt_buf in " __FILE__ "!?\n");
-		debug_putaddr(pages->pgt_buf_offset);
-		debug_putaddr(pages->pgt_buf_size);
-		return NULL;
-	}
-
-	entry = pages->pgt_buf + pages->pgt_buf_offset;
-	pages->pgt_buf_offset += PAGE_SIZE;
-
-	return entry;
-}
-
-/* Used to track our allocated page tables. */
-static struct alloc_pgt_data pgt_data;
-
-/* The top level page table entry pointer. */
-static unsigned long top_level_pgt;
-
-phys_addr_t physical_mask = (1ULL << __PHYSICAL_MASK_SHIFT) - 1;
-
-/*
- * Mapping information structure passed to kernel_ident_mapping_init().
- * Due to relocation, pointers must be assigned at run time not build time.
- */
-static struct x86_mapping_info mapping_info;
-
-/* Locates and clears a region for a new top level page table. */
-void initialize_identity_maps(void)
-{
-	/* If running as an SEV guest, the encryption mask is required. */
-	set_sev_encryption_mask();
-
-	/* Exclude the encryption mask from __PHYSICAL_MASK */
-	physical_mask &= ~sme_me_mask;
-
-	/* Init mapping_info with run-time function/buffer pointers. */
-	mapping_info.alloc_pgt_page = alloc_pgt_page;
-	mapping_info.context = &pgt_data;
-	mapping_info.page_flag = __PAGE_KERNEL_LARGE_EXEC | sme_me_mask;
-	mapping_info.kernpg_flag = _KERNPG_TABLE;
-
-	/*
-	 * It should be impossible for this not to already be true,
-	 * but since calling this a second time would rewind the other
-	 * counters, let's just make sure this is reset too.
-	 */
-	pgt_data.pgt_buf_offset = 0;
-
-	/*
-	 * If we came here via startup_32(), cr3 will be _pgtable already
-	 * and we must append to the existing area instead of entirely
-	 * overwriting it.
-	 *
-	 * With 5-level paging, we use '_pgtable' to allocate the p4d page table,
-	 * the top-level page table is allocated separately.
-	 *
-	 * p4d_offset(top_level_pgt, 0) would cover both the 4- and 5-level
-	 * cases. On 4-level paging it's equal to 'top_level_pgt'.
-	 */
-	top_level_pgt = read_cr3_pa();
-	if (p4d_offset((pgd_t *)top_level_pgt, 0) == (p4d_t *)_pgtable) {
-		debug_putstr("booted via startup_32()\n");
-		pgt_data.pgt_buf = _pgtable + BOOT_INIT_PGT_SIZE;
-		pgt_data.pgt_buf_size = BOOT_PGT_SIZE - BOOT_INIT_PGT_SIZE;
-		memset(pgt_data.pgt_buf, 0, pgt_data.pgt_buf_size);
-	} else {
-		debug_putstr("booted via startup_64()\n");
-		pgt_data.pgt_buf = _pgtable;
-		pgt_data.pgt_buf_size = BOOT_PGT_SIZE;
-		memset(pgt_data.pgt_buf, 0, pgt_data.pgt_buf_size);
-		top_level_pgt = (unsigned long)alloc_pgt_page(&pgt_data);
-	}
-}
-
-/*
- * Adds the specified range to what will become the new identity mappings.
- * Once all ranges have been added, the new mapping is activated by calling
- * finalize_identity_maps() below.
- */
-void add_identity_map(unsigned long start, unsigned long size)
-{
-	unsigned long end = start + size;
-
-	/* Align boundary to 2M. */
-	start = round_down(start, PMD_SIZE);
-	end = round_up(end, PMD_SIZE);
-	if (start >= end)
-		return;
-
-	/* Build the mapping. */
-	kernel_ident_mapping_init(&mapping_info, (pgd_t *)top_level_pgt,
-				  start, end);
-}
-
-/*
- * This switches the page tables to the new level4 that has been built
- * via calls to add_identity_map() above. If booted via startup_32(),
- * this is effectively a no-op.
- */
-void finalize_identity_maps(void)
-{
-	write_cr3(top_level_pgt);
-}
diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c
index e478e40fbe5a..267e7f93050e 100644
--- a/arch/x86/boot/compressed/misc.c
+++ b/arch/x86/boot/compressed/misc.c
@@ -442,6 +442,13 @@ asmlinkage __visible void *extract_kernel(void *rmode, memptr heap,
 	parse_elf(output);
 	handle_relocations(output, output_len, virt_addr);
 	debug_putstr("done.\nBooting the kernel.\n");
+
+	/*
+	 * Flush GHCB from cache and map it encrypted again when running as
+	 * SEV-ES guest.
+	 */
+	sev_es_shutdown_ghcb();
+
 	return output;
 }
 
diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h
index 3efce27ba35c..6d31f1b4c4d1 100644
--- a/arch/x86/boot/compressed/misc.h
+++ b/arch/x86/boot/compressed/misc.h
@@ -23,6 +23,7 @@
 #include <asm/page.h>
 #include <asm/boot.h>
 #include <asm/bootparam.h>
+#include <asm/desc_defs.h>
 
 #define BOOT_CTYPE_H
 #include <linux/acpi.h>
@@ -36,6 +37,9 @@
 #define memptr unsigned
 #endif
 
+/* boot/compressed/vmlinux start and end markers */
+extern char _head[], _end[];
+
 /* misc.c */
 extern memptr free_mem_ptr;
 extern memptr free_mem_end_ptr;
@@ -81,8 +85,6 @@ void choose_random_location(unsigned long input,
 			    unsigned long *output,
 			    unsigned long output_size,
 			    unsigned long *virt_addr);
-/* cpuflags.c */
-bool has_cpuflag(int flag);
 #else
 static inline void choose_random_location(unsigned long input,
 					  unsigned long input_size,
@@ -93,18 +95,14 @@ static inline void choose_random_location(unsigned long input,
 }
 #endif
 
+/* cpuflags.c */
+bool has_cpuflag(int flag);
+
 #ifdef CONFIG_X86_64
-void initialize_identity_maps(void);
-void add_identity_map(unsigned long start, unsigned long size);
-void finalize_identity_maps(void);
+extern int set_page_decrypted(unsigned long address);
+extern int set_page_encrypted(unsigned long address);
+extern int set_page_non_present(unsigned long address);
 extern unsigned char _pgtable[];
-#else
-static inline void initialize_identity_maps(void)
-{ }
-static inline void add_identity_map(unsigned long start, unsigned long size)
-{ }
-static inline void finalize_identity_maps(void)
-{ }
 #endif
 
 #ifdef CONFIG_EARLY_PRINTK
@@ -119,6 +117,17 @@ static inline void console_init(void)
 
 void set_sev_encryption_mask(void);
 
+#ifdef CONFIG_AMD_MEM_ENCRYPT
+void sev_es_shutdown_ghcb(void);
+extern bool sev_es_check_ghcb_fault(unsigned long address);
+#else
+static inline void sev_es_shutdown_ghcb(void) { }
+static inline bool sev_es_check_ghcb_fault(unsigned long address)
+{
+	return false;
+}
+#endif
+
 /* acpi.c */
 #ifdef CONFIG_ACPI
 acpi_physical_address get_rsdp_addr(void);
@@ -133,4 +142,21 @@ int count_immovable_mem_regions(void);
 static inline int count_immovable_mem_regions(void) { return 0; }
 #endif
 
+/* ident_map_64.c */
+#ifdef CONFIG_X86_5LEVEL
+extern unsigned int __pgtable_l5_enabled, pgdir_shift, ptrs_per_p4d;
+#endif
+
+/* Used by PAGE_KERN* macros: */
+extern pteval_t __default_kernel_pte_mask;
+
+/* idt_64.c */
+extern gate_desc boot_idt[BOOT_IDT_ENTRIES];
+extern struct desc_ptr boot_idt_desc;
+
+/* IDT Entry Points */
+void boot_page_fault(void);
+void boot_stage1_vc(void);
+void boot_stage2_vc(void);
+
 #endif /* BOOT_COMPRESSED_MISC_H */
diff --git a/arch/x86/boot/compressed/sev-es.c b/arch/x86/boot/compressed/sev-es.c
new file mode 100644
index 000000000000..954cb2702e23
--- /dev/null
+++ b/arch/x86/boot/compressed/sev-es.c
@@ -0,0 +1,214 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * AMD Encrypted Register State Support
+ *
+ * Author: Joerg Roedel <jroedel@suse.de>
+ */
+
+/*
+ * misc.h needs to be first because it knows how to include the other kernel
+ * headers in the pre-decompression code in a way that does not break
+ * compilation.
+ */
+#include "misc.h"
+
+#include <asm/pgtable_types.h>
+#include <asm/sev-es.h>
+#include <asm/trapnr.h>
+#include <asm/trap_pf.h>
+#include <asm/msr-index.h>
+#include <asm/fpu/xcr.h>
+#include <asm/ptrace.h>
+#include <asm/svm.h>
+
+#include "error.h"
+
+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)
+{
+	int i;
+
+	insn_get_prefixes(insn);
+
+	for (i = 0; i < insn->prefixes.nbytes; i++) {
+		insn_byte_t p = insn->prefixes.bytes[i];
+
+		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)
+{
+	unsigned long low, high;
+
+	asm volatile("rdmsr" : "=a" (low), "=d" (high) :
+			"c" (MSR_AMD64_SEV_ES_GHCB));
+
+	return ((high << 32) | low);
+}
+
+static inline void sev_es_wr_ghcb_msr(u64 val)
+{
+	u32 low, high;
+
+	low  = val & 0xffffffffUL;
+	high = val >> 32;
+
+	asm volatile("wrmsr" : : "c" (MSR_AMD64_SEV_ES_GHCB),
+			"a"(low), "d" (high) : "memory");
+}
+
+static enum es_result vc_decode_insn(struct es_em_ctxt *ctxt)
+{
+	char buffer[MAX_INSN_SIZE];
+	enum es_result ret;
+
+	memcpy(buffer, (unsigned char *)ctxt->regs->ip, MAX_INSN_SIZE);
+
+	insn_init(&ctxt->insn, buffer, MAX_INSN_SIZE, 1);
+	insn_get_length(&ctxt->insn);
+
+	ret = ctxt->insn.immediate.got ? ES_OK : ES_DECODE_FAILED;
+
+	return ret;
+}
+
+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;
+}
+
+#undef __init
+#undef __pa
+#define __init
+#define __pa(x)	((unsigned long)(x))
+
+#define __BOOT_COMPRESSED
+
+/* Basic instruction decoding support needed */
+#include "../../lib/inat.c"
+#include "../../lib/insn.c"
+
+/* Include code for early handlers */
+#include "../../kernel/sev-es-shared.c"
+
+static bool early_setup_sev_es(void)
+{
+	if (!sev_es_negotiate_protocol())
+		sev_es_terminate(GHCB_SEV_ES_REASON_PROTOCOL_UNSUPPORTED);
+
+	if (set_page_decrypted((unsigned long)&boot_ghcb_page))
+		return false;
+
+	/* Page is now mapped decrypted, clear it */
+	memset(&boot_ghcb_page, 0, sizeof(boot_ghcb_page));
+
+	boot_ghcb = &boot_ghcb_page;
+
+	/* Initialize lookup tables for the instruction decoder */
+	inat_init_tables();
+
+	return true;
+}
+
+void sev_es_shutdown_ghcb(void)
+{
+	if (!boot_ghcb)
+		return;
+
+	if (!sev_es_check_cpu_features())
+		error("SEV-ES CPU Features missing.");
+
+	/*
+	 * GHCB Page must be flushed from the cache and mapped encrypted again.
+	 * Otherwise the running kernel will see strange cache effects when
+	 * trying to use that page.
+	 */
+	if (set_page_encrypted((unsigned long)&boot_ghcb_page))
+		error("Can't map GHCB page encrypted");
+
+	/*
+	 * GHCB page is mapped encrypted again and flushed from the cache.
+	 * Mark it non-present now to catch bugs when #VC exceptions trigger
+	 * after this point.
+	 */
+	if (set_page_non_present((unsigned long)&boot_ghcb_page))
+		error("Can't unmap GHCB page");
+}
+
+bool sev_es_check_ghcb_fault(unsigned long address)
+{
+	/* Check whether the fault was on the GHCB page */
+	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_sev_es())
+		sev_es_terminate(GHCB_SEV_ES_REASON_GENERAL_REQUEST);
+
+	vc_ghcb_invalidate(boot_ghcb);
+	result = vc_init_em_ctxt(&ctxt, regs, 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) {
+		/*
+		 * For now, just halt the machine. That makes debugging easier,
+		 * later we just call sev_es_terminate() here.
+		 */
+		while (true)
+			asm volatile("hlt\n");
+	}
+}