Merge tag 'x86_boot_for_v6.6_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 boot updates from Borislav Petkov:
 "Avoid the baremetal decompressor code when booting on an EFI machine.

  This is mandated by the current tightening of EFI executables
  requirements when used in a secure boot scenario. More specifically,
  an EFI executable cannot have a single section with RWX permissions,
  which conflicts with the in-place kernel decompression that is done
  today.

  Instead, the things required by the booting kernel image are done in
  the EFI stub now.

  Work by Ard Biesheuvel"

* tag 'x86_boot_for_v6.6_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (23 commits)
  x86/efistub: Avoid legacy decompressor when doing EFI boot
  x86/efistub: Perform SNP feature test while running in the firmware
  efi/libstub: Add limit argument to efi_random_alloc()
  x86/decompressor: Factor out kernel decompression and relocation
  x86/decompressor: Move global symbol references to C code
  decompress: Use 8 byte alignment
  x86/efistub: Prefer EFI memory attributes protocol over DXE services
  x86/efistub: Perform 4/5 level paging switch from the stub
  x86/decompressor: Merge trampoline cleanup with switching code
  x86/decompressor: Pass pgtable address to trampoline directly
  x86/decompressor: Only call the trampoline when changing paging levels
  x86/decompressor: Call trampoline directly from C code
  x86/decompressor: Avoid the need for a stack in the 32-bit trampoline
  x86/decompressor: Use standard calling convention for trampoline
  x86/decompressor: Call trampoline as a normal function
  x86/decompressor: Assign paging related global variables earlier
  x86/decompressor: Store boot_params pointer in callee save register
  x86/efistub: Clear BSS in EFI handover protocol entrypoint
  x86/decompressor: Avoid magic offsets for EFI handover entrypoint
  x86/efistub: Simplify and clean up handover entry code
  ...

9 files changed, 280 insertions, 133 deletions

diff --git a/drivers/firmware/efi/libstub/Makefile b/drivers/firmware/efi/libstub/Makefile
index 16d64a34d1e1..ae8874401a9f 100644
--- a/drivers/firmware/efi/libstub/Makefile
+++ b/drivers/firmware/efi/libstub/Makefile
@@ -88,6 +88,7 @@ lib-$(CONFIG_EFI_GENERIC_STUB)	+= efi-stub.o string.o intrinsics.o systable.o \
 lib-$(CONFIG_ARM)		+= arm32-stub.o
 lib-$(CONFIG_ARM64)		+= arm64.o arm64-stub.o smbios.o
 lib-$(CONFIG_X86)		+= x86-stub.o
+lib-$(CONFIG_X86_64)		+= x86-5lvl.o
 lib-$(CONFIG_RISCV)		+= riscv.o riscv-stub.o
 lib-$(CONFIG_LOONGARCH)		+= loongarch.o loongarch-stub.o
 
diff --git a/drivers/firmware/efi/libstub/arm64-stub.c b/drivers/firmware/efi/libstub/arm64-stub.c
index 770b8ecb7398..8c40fc89f5f9 100644
--- a/drivers/firmware/efi/libstub/arm64-stub.c
+++ b/drivers/firmware/efi/libstub/arm64-stub.c
@@ -106,7 +106,7 @@ efi_status_t handle_kernel_image(unsigned long *image_addr,
 		 */
 		status = efi_random_alloc(*reserve_size, min_kimg_align,
 					  reserve_addr, phys_seed,
-					  EFI_LOADER_CODE);
+					  EFI_LOADER_CODE, EFI_ALLOC_LIMIT);
 		if (status != EFI_SUCCESS)
 			efi_warn("efi_random_alloc() failed: 0x%lx\n", status);
 	} else {
diff --git a/drivers/firmware/efi/libstub/efi-stub-helper.c b/drivers/firmware/efi/libstub/efi-stub-helper.c
index 732984295295..bfa30625f5d0 100644
--- a/drivers/firmware/efi/libstub/efi-stub-helper.c
+++ b/drivers/firmware/efi/libstub/efi-stub-helper.c
@@ -73,6 +73,8 @@ efi_status_t efi_parse_options(char const *cmdline)
 			efi_loglevel = CONSOLE_LOGLEVEL_QUIET;
 		} else if (!strcmp(param, "noinitrd")) {
 			efi_noinitrd = true;
+		} else if (IS_ENABLED(CONFIG_X86_64) && !strcmp(param, "no5lvl")) {
+			efi_no5lvl = true;
 		} else if (!strcmp(param, "efi") && val) {
 			efi_nochunk = parse_option_str(val, "nochunk");
 			efi_novamap |= parse_option_str(val, "novamap");
diff --git a/drivers/firmware/efi/libstub/efistub.h b/drivers/firmware/efi/libstub/efistub.h
index 6aa38a1bf126..9823f6fb3e01 100644
--- a/drivers/firmware/efi/libstub/efistub.h
+++ b/drivers/firmware/efi/libstub/efistub.h
@@ -33,6 +33,7 @@
 #define EFI_ALLOC_LIMIT		ULONG_MAX
 #endif
 
+extern bool efi_no5lvl;
 extern bool efi_nochunk;
 extern bool efi_nokaslr;
 extern int efi_loglevel;
@@ -955,7 +956,7 @@ efi_status_t efi_get_random_bytes(unsigned long size, u8 *out);
 
 efi_status_t efi_random_alloc(unsigned long size, unsigned long align,
 			      unsigned long *addr, unsigned long random_seed,
-			      int memory_type);
+			      int memory_type, unsigned long alloc_limit);
 
 efi_status_t efi_random_get_seed(void);
 
diff --git a/drivers/firmware/efi/libstub/randomalloc.c b/drivers/firmware/efi/libstub/randomalloc.c
index 32c7a54923b4..674a064b8f7a 100644
--- a/drivers/firmware/efi/libstub/randomalloc.c
+++ b/drivers/firmware/efi/libstub/randomalloc.c
@@ -16,7 +16,8 @@
  */
 static unsigned long get_entry_num_slots(efi_memory_desc_t *md,
 					 unsigned long size,
-					 unsigned long align_shift)
+					 unsigned long align_shift,
+					 u64 alloc_limit)
 {
 	unsigned long align = 1UL << align_shift;
 	u64 first_slot, last_slot, region_end;
@@ -29,7 +30,7 @@ static unsigned long get_entry_num_slots(efi_memory_desc_t *md,
 		return 0;
 
 	region_end = min(md->phys_addr + md->num_pages * EFI_PAGE_SIZE - 1,
-			 (u64)EFI_ALLOC_LIMIT);
+			 alloc_limit);
 	if (region_end < size)
 		return 0;
 
@@ -54,7 +55,8 @@ efi_status_t efi_random_alloc(unsigned long size,
 			      unsigned long align,
 			      unsigned long *addr,
 			      unsigned long random_seed,
-			      int memory_type)
+			      int memory_type,
+			      unsigned long alloc_limit)
 {
 	unsigned long total_slots = 0, target_slot;
 	unsigned long total_mirrored_slots = 0;
@@ -76,7 +78,7 @@ efi_status_t efi_random_alloc(unsigned long size,
 		efi_memory_desc_t *md = (void *)map->map + map_offset;
 		unsigned long slots;
 
-		slots = get_entry_num_slots(md, size, ilog2(align));
+		slots = get_entry_num_slots(md, size, ilog2(align), alloc_limit);
 		MD_NUM_SLOTS(md) = slots;
 		total_slots += slots;
 		if (md->attribute & EFI_MEMORY_MORE_RELIABLE)
diff --git a/drivers/firmware/efi/libstub/x86-5lvl.c b/drivers/firmware/efi/libstub/x86-5lvl.c
new file mode 100644
index 000000000000..479dd445acdc
--- /dev/null
+++ b/drivers/firmware/efi/libstub/x86-5lvl.c
@@ -0,0 +1,95 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <linux/efi.h>
+
+#include <asm/boot.h>
+#include <asm/desc.h>
+#include <asm/efi.h>
+
+#include "efistub.h"
+#include "x86-stub.h"
+
+bool efi_no5lvl;
+
+static void (*la57_toggle)(void *cr3);
+
+static const struct desc_struct gdt[] = {
+	[GDT_ENTRY_KERNEL32_CS] = GDT_ENTRY_INIT(0xc09b, 0, 0xfffff),
+	[GDT_ENTRY_KERNEL_CS]   = GDT_ENTRY_INIT(0xa09b, 0, 0xfffff),
+};
+
+/*
+ * Enabling (or disabling) 5 level paging is tricky, because it can only be
+ * done from 32-bit mode with paging disabled. This means not only that the
+ * code itself must be running from 32-bit addressable physical memory, but
+ * also that the root page table must be 32-bit addressable, as programming
+ * a 64-bit value into CR3 when running in 32-bit mode is not supported.
+ */
+efi_status_t efi_setup_5level_paging(void)
+{
+	u8 tmpl_size = (u8 *)&trampoline_ljmp_imm_offset - (u8 *)&trampoline_32bit_src;
+	efi_status_t status;
+	u8 *la57_code;
+
+	if (!efi_is_64bit())
+		return EFI_SUCCESS;
+
+	/* check for 5 level paging support */
+	if (native_cpuid_eax(0) < 7 ||
+	    !(native_cpuid_ecx(7) & (1 << (X86_FEATURE_LA57 & 31))))
+		return EFI_SUCCESS;
+
+	/* allocate some 32-bit addressable memory for code and a page table */
+	status = efi_allocate_pages(2 * PAGE_SIZE, (unsigned long *)&la57_code,
+				    U32_MAX);
+	if (status != EFI_SUCCESS)
+		return status;
+
+	la57_toggle = memcpy(la57_code, trampoline_32bit_src, tmpl_size);
+	memset(la57_code + tmpl_size, 0x90, PAGE_SIZE - tmpl_size);
+
+	/*
+	 * To avoid the need to allocate a 32-bit addressable stack, the
+	 * trampoline uses a LJMP instruction to switch back to long mode.
+	 * LJMP takes an absolute destination address, which needs to be
+	 * fixed up at runtime.
+	 */
+	*(u32 *)&la57_code[trampoline_ljmp_imm_offset] += (unsigned long)la57_code;
+
+	efi_adjust_memory_range_protection((unsigned long)la57_toggle, PAGE_SIZE);
+
+	return EFI_SUCCESS;
+}
+
+void efi_5level_switch(void)
+{
+	bool want_la57 = IS_ENABLED(CONFIG_X86_5LEVEL) && !efi_no5lvl;
+	bool have_la57 = native_read_cr4() & X86_CR4_LA57;
+	bool need_toggle = want_la57 ^ have_la57;
+	u64 *pgt = (void *)la57_toggle + PAGE_SIZE;
+	u64 *cr3 = (u64 *)__native_read_cr3();
+	u64 *new_cr3;
+
+	if (!la57_toggle || !need_toggle)
+		return;
+
+	if (!have_la57) {
+		/*
+		 * 5 level paging will be enabled, so a root level page needs
+		 * to be allocated from the 32-bit addressable physical region,
+		 * with its first entry referring to the existing hierarchy.
+		 */
+		new_cr3 = memset(pgt, 0, PAGE_SIZE);
+		new_cr3[0] = (u64)cr3 | _PAGE_TABLE_NOENC;
+	} else {
+		/* take the new root table pointer from the current entry #0 */
+		new_cr3 = (u64 *)(cr3[0] & PAGE_MASK);
+
+		/* copy the new root table if it is not 32-bit addressable */
+		if ((u64)new_cr3 > U32_MAX)
+			new_cr3 = memcpy(pgt, new_cr3, PAGE_SIZE);
+	}
+
+	native_load_gdt(&(struct desc_ptr){ sizeof(gdt) - 1, (u64)gdt });
+
+	la57_toggle(new_cr3);
+}
diff --git a/drivers/firmware/efi/libstub/x86-stub.c b/drivers/firmware/efi/libstub/x86-stub.c
index 220be75a5cdc..e976288728e9 100644
--- a/drivers/firmware/efi/libstub/x86-stub.c
+++ b/drivers/firmware/efi/libstub/x86-stub.c
@@ -15,16 +15,16 @@
 #include <asm/setup.h>
 #include <asm/desc.h>
 #include <asm/boot.h>
+#include <asm/kaslr.h>
+#include <asm/sev.h>
 
 #include "efistub.h"
-
-/* Maximum physical address for 64-bit kernel with 4-level paging */
-#define MAXMEM_X86_64_4LEVEL (1ull << 46)
+#include "x86-stub.h"
 
 const efi_system_table_t *efi_system_table;
 const efi_dxe_services_table_t *efi_dxe_table;
-u32 image_offset __section(".data");
 static efi_loaded_image_t *image = NULL;
+static efi_memory_attribute_protocol_t *memattr;
 
 typedef union sev_memory_acceptance_protocol sev_memory_acceptance_protocol_t;
 union sev_memory_acceptance_protocol {
@@ -223,8 +223,8 @@ static void retrieve_apple_device_properties(struct boot_params *boot_params)
 	}
 }
 
-static void
-adjust_memory_range_protection(unsigned long start, unsigned long size)
+void efi_adjust_memory_range_protection(unsigned long start,
+					unsigned long size)
 {
 	efi_status_t status;
 	efi_gcd_memory_space_desc_t desc;
@@ -232,12 +232,18 @@ adjust_memory_range_protection(unsigned long start, unsigned long size)
 	unsigned long rounded_start, rounded_end;
 	unsigned long unprotect_start, unprotect_size;
 
-	if (efi_dxe_table == NULL)
-		return;
-
 	rounded_start = rounddown(start, EFI_PAGE_SIZE);
 	rounded_end = roundup(start + size, EFI_PAGE_SIZE);
 
+	if (memattr != NULL) {
+		efi_call_proto(memattr, clear_memory_attributes, rounded_start,
+			       rounded_end - rounded_start, EFI_MEMORY_XP);
+		return;
+	}
+
+	if (efi_dxe_table == NULL)
+		return;
+
 	/*
 	 * Don't modify memory region attributes, they are
 	 * already suitable, to lower the possibility to
@@ -278,49 +284,6 @@ adjust_memory_range_protection(unsigned long start, unsigned long size)
 	}
 }
 
-/*
- * Trampoline takes 2 pages and can be loaded in first megabyte of memory
- * with its end placed between 128k and 640k where BIOS might start.
- * (see arch/x86/boot/compressed/pgtable_64.c)
- *
- * We cannot find exact trampoline placement since memory map
- * can be modified by UEFI, and it can alter the computed address.
- */
-
-#define TRAMPOLINE_PLACEMENT_BASE ((128 - 8)*1024)
-#define TRAMPOLINE_PLACEMENT_SIZE (640*1024 - (128 - 8)*1024)
-
-void startup_32(struct boot_params *boot_params);
-
-static void
-setup_memory_protection(unsigned long image_base, unsigned long image_size)
-{
-	/*
-	 * Allow execution of possible trampoline used
-	 * for switching between 4- and 5-level page tables
-	 * and relocated kernel image.
-	 */
-
-	adjust_memory_range_protection(TRAMPOLINE_PLACEMENT_BASE,
-				       TRAMPOLINE_PLACEMENT_SIZE);
-
-#ifdef CONFIG_64BIT
-	if (image_base != (unsigned long)startup_32)
-		adjust_memory_range_protection(image_base, image_size);
-#else
-	/*
-	 * Clear protection flags on a whole range of possible
-	 * addresses used for KASLR. We don't need to do that
-	 * on x86_64, since KASLR/extraction is performed after
-	 * dedicated identity page tables are built and we only
-	 * need to remove possible protection on relocated image
-	 * itself disregarding further relocations.
-	 */
-	adjust_memory_range_protection(LOAD_PHYSICAL_ADDR,
-				       KERNEL_IMAGE_SIZE - LOAD_PHYSICAL_ADDR);
-#endif
-}
-
 static void setup_unaccepted_memory(void)
 {
 	efi_guid_t mem_acceptance_proto = OVMF_SEV_MEMORY_ACCEPTANCE_PROTOCOL_GUID;
@@ -346,9 +309,7 @@ static void setup_unaccepted_memory(void)
 
 static const efi_char16_t apple[] = L"Apple";
 
-static void setup_quirks(struct boot_params *boot_params,
-			 unsigned long image_base,
-			 unsigned long image_size)
+static void setup_quirks(struct boot_params *boot_params)
 {
 	efi_char16_t *fw_vendor = (efi_char16_t *)(unsigned long)
 		efi_table_attr(efi_system_table, fw_vendor);
@@ -357,9 +318,6 @@ static void setup_quirks(struct boot_params *boot_params,
 		if (IS_ENABLED(CONFIG_APPLE_PROPERTIES))
 			retrieve_apple_device_properties(boot_params);
 	}
-
-	if (IS_ENABLED(CONFIG_EFI_DXE_MEM_ATTRIBUTES))
-		setup_memory_protection(image_base, image_size);
 }
 
 /*
@@ -512,7 +470,6 @@ efi_status_t __efiapi efi_pe_entry(efi_handle_t handle,
 	}
 
 	image_base = efi_table_attr(image, image_base);
-	image_offset = (void *)startup_32 - image_base;
 
 	status = efi_allocate_pages(sizeof(struct boot_params),
 				    (unsigned long *)&boot_params, ULONG_MAX);
@@ -803,19 +760,96 @@ static efi_status_t exit_boot(struct boot_params *boot_params, void *handle)
 	return EFI_SUCCESS;
 }
 
+static bool have_unsupported_snp_features(void)
+{
+	u64 unsupported;
+
+	unsupported = snp_get_unsupported_features(sev_get_status());
+	if (unsupported) {
+		efi_err("Unsupported SEV-SNP features detected: 0x%llx\n",
+			unsupported);
+		return true;
+	}
+	return false;
+}
+
+static void efi_get_seed(void *seed, int size)
+{
+	efi_get_random_bytes(size, seed);
+
+	/*
+	 * This only updates seed[0] when running on 32-bit, but in that case,
+	 * seed[1] is not used anyway, as there is no virtual KASLR on 32-bit.
+	 */
+	*(unsigned long *)seed ^= kaslr_get_random_long("EFI");
+}
+
+static void error(char *str)
+{
+	efi_warn("Decompression failed: %s\n", str);
+}
+
+static efi_status_t efi_decompress_kernel(unsigned long *kernel_entry)
+{
+	unsigned long virt_addr = LOAD_PHYSICAL_ADDR;
+	unsigned long addr, alloc_size, entry;
+	efi_status_t status;
+	u32 seed[2] = {};
+
+	/* determine the required size of the allocation */
+	alloc_size = ALIGN(max_t(unsigned long, output_len, kernel_total_size),
+			   MIN_KERNEL_ALIGN);
+
+	if (IS_ENABLED(CONFIG_RANDOMIZE_BASE) && !efi_nokaslr) {
+		u64 range = KERNEL_IMAGE_SIZE - LOAD_PHYSICAL_ADDR - kernel_total_size;
+
+		efi_get_seed(seed, sizeof(seed));
+
+		virt_addr += (range * seed[1]) >> 32;
+		virt_addr &= ~(CONFIG_PHYSICAL_ALIGN - 1);
+	}
+
+	status = efi_random_alloc(alloc_size, CONFIG_PHYSICAL_ALIGN, &addr,
+				  seed[0], EFI_LOADER_CODE,
+				  EFI_X86_KERNEL_ALLOC_LIMIT);
+	if (status != EFI_SUCCESS)
+		return status;
+
+	entry = decompress_kernel((void *)addr, virt_addr, error);
+	if (entry == ULONG_MAX) {
+		efi_free(alloc_size, addr);
+		return EFI_LOAD_ERROR;
+	}
+
+	*kernel_entry = addr + entry;
+
+	efi_adjust_memory_range_protection(addr, kernel_total_size);
+
+	return EFI_SUCCESS;
+}
+
+static void __noreturn enter_kernel(unsigned long kernel_addr,
+				    struct boot_params *boot_params)
+{
+	/* enter decompressed kernel with boot_params pointer in RSI/ESI */
+	asm("jmp *%0"::"r"(kernel_addr), "S"(boot_params));
+
+	unreachable();
+}
+
 /*
- * On success, we return the address of startup_32, which has potentially been
- * relocated by efi_relocate_kernel.
- * On failure, we exit to the firmware via efi_exit instead of returning.
+ * On success, this routine will jump to the relocated image directly and never
+ * return.  On failure, it will exit to the firmware via efi_exit() instead of
+ * returning.
  */
-asmlinkage unsigned long efi_main(efi_handle_t handle,
-				  efi_system_table_t *sys_table_arg,
-				  struct boot_params *boot_params)
+void __noreturn efi_stub_entry(efi_handle_t handle,
+			       efi_system_table_t *sys_table_arg,
+			       struct boot_params *boot_params)
 {
-	unsigned long bzimage_addr = (unsigned long)startup_32;
-	unsigned long buffer_start, buffer_end;
+	efi_guid_t guid = EFI_MEMORY_ATTRIBUTE_PROTOCOL_GUID;
 	struct setup_header *hdr = &boot_params->hdr;
 	const struct linux_efi_initrd *initrd = NULL;
+	unsigned long kernel_entry;
 	efi_status_t status;
 
 	efi_system_table = sys_table_arg;
@@ -823,65 +857,25 @@ asmlinkage unsigned long efi_main(efi_handle_t handle,
 	if (efi_system_table->hdr.signature != EFI_SYSTEM_TABLE_SIGNATURE)
 		efi_exit(handle, EFI_INVALID_PARAMETER);
 
-	efi_dxe_table = get_efi_config_table(EFI_DXE_SERVICES_TABLE_GUID);
-	if (efi_dxe_table &&
-	    efi_dxe_table->hdr.signature != EFI_DXE_SERVICES_TABLE_SIGNATURE) {
-		efi_warn("Ignoring DXE services table: invalid signature\n");
-		efi_dxe_table = NULL;
+	if (have_unsupported_snp_features())
+		efi_exit(handle, EFI_UNSUPPORTED);
+
+	if (IS_ENABLED(CONFIG_EFI_DXE_MEM_ATTRIBUTES)) {
+		efi_dxe_table = get_efi_config_table(EFI_DXE_SERVICES_TABLE_GUID);
+		if (efi_dxe_table &&
+		    efi_dxe_table->hdr.signature != EFI_DXE_SERVICES_TABLE_SIGNATURE) {
+			efi_warn("Ignoring DXE services table: invalid signature\n");
+			efi_dxe_table = NULL;
+		}
 	}
 
-	/*
-	 * If the kernel isn't already loaded at a suitable address,
-	 * relocate it.
-	 *
-	 * It must be loaded above LOAD_PHYSICAL_ADDR.
-	 *
-	 * The maximum address for 64-bit is 1 << 46 for 4-level paging. This
-	 * is defined as the macro MAXMEM, but unfortunately that is not a
-	 * compile-time constant if 5-level paging is configured, so we instead
-	 * define our own macro for use here.
-	 *
-	 * For 32-bit, the maximum address is complicated to figure out, for
-	 * now use KERNEL_IMAGE_SIZE, which will be 512MiB, the same as what
-	 * KASLR uses.
-	 *
-	 * Also relocate it if image_offset is zero, i.e. the kernel wasn't
-	 * loaded by LoadImage, but rather by a bootloader that called the
-	 * handover entry. The reason we must always relocate in this case is
-	 * to handle the case of systemd-boot booting a unified kernel image,
-	 * which is a PE executable that contains the bzImage and an initrd as
-	 * COFF sections. The initrd section is placed after the bzImage
-	 * without ensuring that there are at least init_size bytes available
-	 * for the bzImage, and thus the compressed kernel's startup code may
-	 * overwrite the initrd unless it is moved out of the way.
-	 */
+	/* grab the memory attributes protocol if it exists */
+	efi_bs_call(locate_protocol, &guid, NULL, (void **)&memattr);
 
-	buffer_start = ALIGN(bzimage_addr - image_offset,
-			     hdr->kernel_alignment);
-	buffer_end = buffer_start + hdr->init_size;
-
-	if ((buffer_start < LOAD_PHYSICAL_ADDR)				     ||
-	    (IS_ENABLED(CONFIG_X86_32) && buffer_end > KERNEL_IMAGE_SIZE)    ||
-	    (IS_ENABLED(CONFIG_X86_64) && buffer_end > MAXMEM_X86_64_4LEVEL) ||
-	    (image_offset == 0)) {
-		extern char _bss[];
-
-		status = efi_relocate_kernel(&bzimage_addr,
-					     (unsigned long)_bss - bzimage_addr,
-					     hdr->init_size,
-					     hdr->pref_address,
-					     hdr->kernel_alignment,
-					     LOAD_PHYSICAL_ADDR);
-		if (status != EFI_SUCCESS) {
-			efi_err("efi_relocate_kernel() failed!\n");
-			goto fail;
-		}
-		/*
-		 * Now that we've copied the kernel elsewhere, we no longer
-		 * have a set up block before startup_32(), so reset image_offset
-		 * to zero in case it was set earlier.
-		 */
-		image_offset = 0;
+	status = efi_setup_5level_paging();
+	if (status != EFI_SUCCESS) {
+		efi_err("efi_setup_5level_paging() failed!\n");
+		goto fail;
 	}
 
 #ifdef CONFIG_CMDLINE_BOOL
@@ -901,6 +895,12 @@ asmlinkage unsigned long efi_main(efi_handle_t handle,
 		}
 	}
 
+	status = efi_decompress_kernel(&kernel_entry);
+	if (status != EFI_SUCCESS) {
+		efi_err("Failed to decompress kernel\n");
+		goto fail;
+	}
+
 	/*
 	 * At this point, an initrd may already have been loaded by the
 	 * bootloader and passed via bootparams. We permit an initrd loaded
@@ -940,7 +940,7 @@ asmlinkage unsigned long efi_main(efi_handle_t handle,
 
 	setup_efi_pci(boot_params);
 
-	setup_quirks(boot_params, bzimage_addr, buffer_end - buffer_start);
+	setup_quirks(boot_params);
 
 	setup_unaccepted_memory();
 
@@ -950,9 +950,38 @@ asmlinkage unsigned long efi_main(efi_handle_t handle,
 		goto fail;
 	}
 
-	return bzimage_addr;
+	/*
+	 * Call the SEV init code while still running with the firmware's
+	 * GDT/IDT, so #VC exceptions will be handled by EFI.
+	 */
+	sev_enable(boot_params);
+
+	efi_5level_switch();
+
+	enter_kernel(kernel_entry, boot_params);
 fail:
-	efi_err("efi_main() failed!\n");
+	efi_err("efi_stub_entry() failed!\n");
 
 	efi_exit(handle, status);
 }
+
+#ifdef CONFIG_EFI_HANDOVER_PROTOCOL
+void efi_handover_entry(efi_handle_t handle, efi_system_table_t *sys_table_arg,
+			struct boot_params *boot_params)
+{
+	extern char _bss[], _ebss[];
+
+	memset(_bss, 0, _ebss - _bss);
+	efi_stub_entry(handle, sys_table_arg, boot_params);
+}
+
+#ifndef CONFIG_EFI_MIXED
+extern __alias(efi_handover_entry)
+void efi32_stub_entry(efi_handle_t handle, efi_system_table_t *sys_table_arg,
+		      struct boot_params *boot_params);
+
+extern __alias(efi_handover_entry)
+void efi64_stub_entry(efi_handle_t handle, efi_system_table_t *sys_table_arg,
+		      struct boot_params *boot_params);
+#endif
+#endif
diff --git a/drivers/firmware/efi/libstub/x86-stub.h b/drivers/firmware/efi/libstub/x86-stub.h
new file mode 100644
index 000000000000..37c5a36b9d8c
--- /dev/null
+++ b/drivers/firmware/efi/libstub/x86-stub.h
@@ -0,0 +1,17 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#include <linux/efi.h>
+
+extern void trampoline_32bit_src(void *, bool);
+extern const u16 trampoline_ljmp_imm_offset;
+
+void efi_adjust_memory_range_protection(unsigned long start,
+					unsigned long size);
+
+#ifdef CONFIG_X86_64
+efi_status_t efi_setup_5level_paging(void);
+void efi_5level_switch(void);
+#else
+static inline efi_status_t efi_setup_5level_paging(void) { return EFI_SUCCESS; }
+static inline void efi_5level_switch(void) {}
+#endif
diff --git a/drivers/firmware/efi/libstub/zboot.c b/drivers/firmware/efi/libstub/zboot.c
index e5d7fa1f1d8f..bdb17eac0cb4 100644
--- a/drivers/firmware/efi/libstub/zboot.c
+++ b/drivers/firmware/efi/libstub/zboot.c
@@ -119,7 +119,7 @@ efi_zboot_entry(efi_handle_t handle, efi_system_table_t *systab)
 		}
 
 		status = efi_random_alloc(alloc_size, min_kimg_align, &image_base,
-					  seed, EFI_LOADER_CODE);
+					  seed, EFI_LOADER_CODE, EFI_ALLOC_LIMIT);
 		if (status != EFI_SUCCESS) {
 			efi_err("Failed to allocate memory\n");
 			goto free_cmdline;