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
  ...

24 files changed, 587 insertions, 562 deletions

diff --git a/Documentation/arch/x86/boot.rst b/Documentation/arch/x86/boot.rst
index 33520ecdb37a..cdbca15a4fc2 100644
--- a/Documentation/arch/x86/boot.rst
+++ b/Documentation/arch/x86/boot.rst
@@ -1417,7 +1417,7 @@ execution context provided by the EFI firmware.
 
 The function prototype for the handover entry point looks like this::
 
-    efi_main(void *handle, efi_system_table_t *table, struct boot_params *bp)
+    efi_stub_entry(void *handle, efi_system_table_t *table, struct boot_params *bp)
 
 'handle' is the EFI image handle passed to the boot loader by the EFI
 firmware, 'table' is the EFI system table - these are the first two
diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index 40d2ff503079..71fc531b95b4 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -74,6 +74,11 @@ LDFLAGS_vmlinux += -z noexecstack
 ifeq ($(CONFIG_LD_IS_BFD),y)
 LDFLAGS_vmlinux += $(call ld-option,--no-warn-rwx-segments)
 endif
+ifeq ($(CONFIG_EFI_STUB),y)
+# ensure that the static EFI stub library will be pulled in, even if it is
+# never referenced explicitly from the startup code
+LDFLAGS_vmlinux += -u efi_pe_entry
+endif
 LDFLAGS_vmlinux += -T
 
 hostprogs	:= mkpiggy
diff --git a/arch/x86/boot/compressed/efi_mixed.S b/arch/x86/boot/compressed/efi_mixed.S
index 4ca70bf93dc0..f4e22ef774ab 100644
--- a/arch/x86/boot/compressed/efi_mixed.S
+++ b/arch/x86/boot/compressed/efi_mixed.S
@@ -26,8 +26,8 @@
  * When booting in 64-bit mode on 32-bit EFI firmware, startup_64_mixed_mode()
  * is the first thing that runs after switching to long mode. Depending on
  * whether the EFI handover protocol or the compat entry point was used to
- * enter the kernel, it will either branch to the 64-bit EFI handover
- * entrypoint at offset 0x390 in the image, or to the 64-bit EFI PE/COFF
+ * enter the kernel, it will either branch to the common 64-bit EFI stub
+ * entrypoint efi_stub_entry() directly, or via the 64-bit EFI PE/COFF
  * entrypoint efi_pe_entry(). In the former case, the bootloader must provide a
  * struct bootparams pointer as the third argument, so the presence of such a
  * pointer is used to disambiguate.
@@ -37,21 +37,23 @@
  *  | efi32_pe_entry   |---->|            |            |       +-----------+--+
  *  +------------------+     |            |     +------+----------------+  |
  *                           | startup_32 |---->| startup_64_mixed_mode |  |
- *  +------------------+     |            |     +------+----------------+  V
- *  | efi32_stub_entry |---->|            |            |     +------------------+
- *  +------------------+     +------------+            +---->| efi64_stub_entry |
- *                                                           +-------------+----+
- *                           +------------+     +----------+               |
- *                           | startup_64 |<----| efi_main |<--------------+
- *                           +------------+     +----------+
+ *  +------------------+     |            |     +------+----------------+  |
+ *  | efi32_stub_entry |---->|            |            |                   |
+ *  +------------------+     +------------+            |                   |
+ *                                                     V                   |
+ *                           +------------+     +----------------+         |
+ *                           | startup_64 |<----| efi_stub_entry |<--------+
+ *                           +------------+     +----------------+
  */
 SYM_FUNC_START(startup_64_mixed_mode)
 	lea	efi32_boot_args(%rip), %rdx
 	mov	0(%rdx), %edi
 	mov	4(%rdx), %esi
+#ifdef CONFIG_EFI_HANDOVER_PROTOCOL
 	mov	8(%rdx), %edx		// saved bootparams pointer
 	test	%edx, %edx
-	jnz	efi64_stub_entry
+	jnz	efi_stub_entry
+#endif
 	/*
 	 * efi_pe_entry uses MS calling convention, which requires 32 bytes of
 	 * shadow space on the stack even if all arguments are passed in
@@ -138,6 +140,28 @@ SYM_FUNC_START(__efi64_thunk)
 SYM_FUNC_END(__efi64_thunk)
 
 	.code32
+#ifdef CONFIG_EFI_HANDOVER_PROTOCOL
+SYM_FUNC_START(efi32_stub_entry)
+	call	1f
+1:	popl	%ecx
+
+	/* Clear BSS */
+	xorl	%eax, %eax
+	leal	(_bss - 1b)(%ecx), %edi
+	leal	(_ebss - 1b)(%ecx), %ecx
+	subl	%edi, %ecx
+	shrl	$2, %ecx
+	cld
+	rep	stosl
+
+	add	$0x4, %esp		/* Discard return address */
+	popl	%ecx
+	popl	%edx
+	popl	%esi
+	jmp	efi32_entry
+SYM_FUNC_END(efi32_stub_entry)
+#endif
+
 /*
  * EFI service pointer must be in %edi.
  *
@@ -218,7 +242,7 @@ SYM_FUNC_END(efi_enter32)
  * stub may still exit and return to the firmware using the Exit() EFI boot
  * service.]
  */
-SYM_FUNC_START(efi32_entry)
+SYM_FUNC_START_LOCAL(efi32_entry)
 	call	1f
 1:	pop	%ebx
 
@@ -245,10 +269,6 @@ SYM_FUNC_START(efi32_entry)
 	jmp	startup_32
 SYM_FUNC_END(efi32_entry)
 
-#define ST32_boottime		60 // offsetof(efi_system_table_32_t, boottime)
-#define BS32_handle_protocol	88 // offsetof(efi_boot_services_32_t, handle_protocol)
-#define LI32_image_base		32 // offsetof(efi_loaded_image_32_t, image_base)
-
 /*
  * efi_status_t efi32_pe_entry(efi_handle_t image_handle,
  *			       efi_system_table_32_t *sys_table)
@@ -256,8 +276,6 @@ SYM_FUNC_END(efi32_entry)
 SYM_FUNC_START(efi32_pe_entry)
 	pushl	%ebp
 	movl	%esp, %ebp
-	pushl	%eax				// dummy push to allocate loaded_image
-
 	pushl	%ebx				// save callee-save registers
 	pushl	%edi
 
@@ -266,48 +284,8 @@ SYM_FUNC_START(efi32_pe_entry)
 	movl	$0x80000003, %eax		// EFI_UNSUPPORTED
 	jnz	2f
 
-	call	1f
-1:	pop	%ebx
-
-	/* Get the loaded image protocol pointer from the image handle */
-	leal	-4(%ebp), %eax
-	pushl	%eax				// &loaded_image
-	leal	(loaded_image_proto - 1b)(%ebx), %eax
-	pushl	%eax				// pass the GUID address
-	pushl	8(%ebp)				// pass the image handle
-
-	/*
-	 * Note the alignment of the stack frame.
-	 *   sys_table
-	 *   handle             <-- 16-byte aligned on entry by ABI
-	 *   return address
-	 *   frame pointer
-	 *   loaded_image       <-- local variable
-	 *   saved %ebx		<-- 16-byte aligned here
-	 *   saved %edi
-	 *   &loaded_image
-	 *   &loaded_image_proto
-	 *   handle             <-- 16-byte aligned for call to handle_protocol
-	 */
-
-	movl	12(%ebp), %eax			// sys_table
-	movl	ST32_boottime(%eax), %eax	// sys_table->boottime
-	call	*BS32_handle_protocol(%eax)	// sys_table->boottime->handle_protocol
-	addl	$12, %esp			// restore argument space
-	testl	%eax, %eax
-	jnz	2f
-
 	movl	8(%ebp), %ecx			// image_handle
 	movl	12(%ebp), %edx			// sys_table
-	movl	-4(%ebp), %esi			// loaded_image
-	movl	LI32_image_base(%esi), %esi	// loaded_image->image_base
-	leal	(startup_32 - 1b)(%ebx), %ebp	// runtime address of startup_32
-	/*
-	 * We need to set the image_offset variable here since startup_32() will
-	 * use it before we get to the 64-bit efi_pe_entry() in C code.
-	 */
-	subl	%esi, %ebp			// calculate image_offset
-	movl	%ebp, (image_offset - 1b)(%ebx)	// save image_offset
 	xorl	%esi, %esi
 	jmp	efi32_entry			// pass %ecx, %edx, %esi
 						// no other registers remain live
@@ -318,14 +296,13 @@ SYM_FUNC_START(efi32_pe_entry)
 	RET
 SYM_FUNC_END(efi32_pe_entry)
 
-	.section ".rodata"
-	/* EFI loaded image protocol GUID */
-	.balign 4
-SYM_DATA_START_LOCAL(loaded_image_proto)
-	.long	0x5b1b31a1
-	.word	0x9562, 0x11d2
-	.byte	0x8e, 0x3f, 0x00, 0xa0, 0xc9, 0x69, 0x72, 0x3b
-SYM_DATA_END(loaded_image_proto)
+#ifdef CONFIG_EFI_HANDOVER_PROTOCOL
+	.org	efi32_stub_entry + 0x200
+	.code64
+SYM_FUNC_START_NOALIGN(efi64_stub_entry)
+	jmp	efi_handover_entry
+SYM_FUNC_END(efi64_stub_entry)
+#endif
 
 	.data
 	.balign	8
diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S
index 987ae727cf9f..1cfe9802a42f 100644
--- a/arch/x86/boot/compressed/head_32.S
+++ b/arch/x86/boot/compressed/head_32.S
@@ -84,19 +84,6 @@ SYM_FUNC_START(startup_32)
 
 #ifdef CONFIG_RELOCATABLE
 	leal	startup_32@GOTOFF(%edx), %ebx
-
-#ifdef CONFIG_EFI_STUB
-/*
- * If we were loaded via the EFI LoadImage service, startup_32() will be at an
- * offset to the start of the space allocated for the image. efi_pe_entry() will
- * set up image_offset to tell us where the image actually starts, so that we
- * can use the full available buffer.
- *	image_offset = startup_32 - image_base
- * Otherwise image_offset will be zero and has no effect on the calculations.
- */
-	subl    image_offset@GOTOFF(%edx), %ebx
-#endif
-
 	movl	BP_kernel_alignment(%esi), %eax
 	decl	%eax
 	addl    %eax, %ebx
@@ -150,17 +137,6 @@ SYM_FUNC_START(startup_32)
 	jmp	*%eax
 SYM_FUNC_END(startup_32)
 
-#ifdef CONFIG_EFI_STUB
-SYM_FUNC_START(efi32_stub_entry)
-	add	$0x4, %esp
-	movl	8(%esp), %esi	/* save boot_params pointer */
-	call	efi_main
-	/* efi_main returns the possibly relocated address of startup_32 */
-	jmp	*%eax
-SYM_FUNC_END(efi32_stub_entry)
-SYM_FUNC_ALIAS(efi_stub_entry, efi32_stub_entry)
-#endif
-
 	.text
 SYM_FUNC_START_LOCAL_NOALIGN(.Lrelocated)
 
@@ -179,13 +155,7 @@ SYM_FUNC_START_LOCAL_NOALIGN(.Lrelocated)
  */
 	/* push arguments for extract_kernel: */
 
-	pushl	output_len@GOTOFF(%ebx)	/* decompressed length, end of relocs */
 	pushl	%ebp			/* output address */
-	pushl	input_len@GOTOFF(%ebx)	/* input_len */
-	leal	input_data@GOTOFF(%ebx), %eax
-	pushl	%eax			/* input_data */
-	leal	boot_heap@GOTOFF(%ebx), %eax
-	pushl	%eax			/* heap area */
 	pushl	%esi			/* real mode pointer */
 	call	extract_kernel		/* returns kernel entry point in %eax */
 	addl	$24, %esp
@@ -213,8 +183,6 @@ SYM_DATA_END_LABEL(gdt, SYM_L_LOCAL, gdt_end)
  */
 	.bss
 	.balign 4
-boot_heap:
-	.fill BOOT_HEAP_SIZE, 1, 0
 boot_stack:
 	.fill BOOT_STACK_SIZE, 1, 0
 boot_stack_end:
diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S
index 03c4328a88cb..bf4a10a5794f 100644
--- a/arch/x86/boot/compressed/head_64.S
+++ b/arch/x86/boot/compressed/head_64.S
@@ -146,19 +146,6 @@ SYM_FUNC_START(startup_32)
 
 #ifdef CONFIG_RELOCATABLE
 	movl	%ebp, %ebx
-
-#ifdef CONFIG_EFI_STUB
-/*
- * If we were loaded via the EFI LoadImage service, startup_32 will be at an
- * offset to the start of the space allocated for the image. efi_pe_entry will
- * set up image_offset to tell us where the image actually starts, so that we
- * can use the full available buffer.
- *	image_offset = startup_32 - image_base
- * Otherwise image_offset will be zero and has no effect on the calculations.
- */
-	subl    rva(image_offset)(%ebp), %ebx
-#endif
-
 	movl	BP_kernel_alignment(%esi), %eax
 	decl	%eax
 	addl	%eax, %ebx
@@ -294,17 +281,6 @@ SYM_FUNC_START(startup_32)
 	lret
 SYM_FUNC_END(startup_32)
 
-#if IS_ENABLED(CONFIG_EFI_MIXED) && IS_ENABLED(CONFIG_EFI_HANDOVER_PROTOCOL)
-	.org 0x190
-SYM_FUNC_START(efi32_stub_entry)
-	add	$0x4, %esp		/* Discard return address */
-	popl	%ecx
-	popl	%edx
-	popl	%esi
-	jmp	efi32_entry
-SYM_FUNC_END(efi32_stub_entry)
-#endif
-
 	.code64
 	.org 0x200
 SYM_CODE_START(startup_64)
@@ -346,20 +322,6 @@ SYM_CODE_START(startup_64)
 	/* Start with the delta to where the kernel will run at. */
 #ifdef CONFIG_RELOCATABLE
 	leaq	startup_32(%rip) /* - $startup_32 */, %rbp
-
-#ifdef CONFIG_EFI_STUB
-/*
- * If we were loaded via the EFI LoadImage service, startup_32 will be at an
- * offset to the start of the space allocated for the image. efi_pe_entry will
- * set up image_offset to tell us where the image actually starts, so that we
- * can use the full available buffer.
- *	image_offset = startup_32 - image_base
- * Otherwise image_offset will be zero and has no effect on the calculations.
- */
-	movl    image_offset(%rip), %eax
-	subq	%rax, %rbp
-#endif
-
 	movl	BP_kernel_alignment(%rsi), %eax
 	decl	%eax
 	addq	%rax, %rbp
@@ -398,10 +360,6 @@ SYM_CODE_START(startup_64)
 	 * For the trampoline, we need the top page table to reside in lower
 	 * memory as we don't have a way to load 64-bit values into CR3 in
 	 * 32-bit mode.
-	 *
-	 * We go though the trampoline even if we don't have to: if we're
-	 * already in a desired paging mode. This way the trampoline code gets
-	 * tested on every boot.
 	 */
 
 	/* Make sure we have GDT with 32-bit code segment */
@@ -416,10 +374,14 @@ SYM_CODE_START(startup_64)
 	lretq
 
 .Lon_kernel_cs:
+	/*
+	 * RSI holds a pointer to a boot_params structure provided by the
+	 * loader, and this needs to be preserved across C function calls. So
+	 * move it into a callee saved register.
+	 */
+	movq	%rsi, %r15
 
-	pushq	%rsi
 	call	load_stage1_idt
-	popq	%rsi
 
 #ifdef CONFIG_AMD_MEM_ENCRYPT
 	/*
@@ -430,63 +392,24 @@ SYM_CODE_START(startup_64)
 	 * CPUID instructions being issued, so go ahead and do that now via
 	 * sev_enable(), which will also handle the rest of the SEV-related
 	 * detection/setup to ensure that has been done in advance of any dependent
-	 * code.
+	 * code. Pass the boot_params pointer as the first argument.
 	 */
-	pushq	%rsi
-	movq	%rsi, %rdi		/* real mode address */
+	movq	%r15, %rdi
 	call	sev_enable
-	popq	%rsi
 #endif
 
 	/*
-	 * paging_prepare() sets up the trampoline and checks if we need to
-	 * enable 5-level paging.
+	 * configure_5level_paging() updates the number of paging levels using
+	 * a trampoline in 32-bit addressable memory if the current number does
+	 * not match the desired number.
 	 *
-	 * paging_prepare() returns a two-quadword structure which lands
-	 * into RDX:RAX:
-	 *   - Address of the trampoline is returned in RAX.
-	 *   - Non zero RDX means trampoline needs to enable 5-level
-	 *     paging.
-	 *
-	 * RSI holds real mode data and needs to be preserved across
-	 * this function call.
-	 */
-	pushq	%rsi
-	movq	%rsi, %rdi		/* real mode address */
-	call	paging_prepare
-	popq	%rsi
-
-	/* Save the trampoline address in RCX */
-	movq	%rax, %rcx
-
-	/*
-	 * Load the address of trampoline_return() into RDI.
-	 * It will be used by the trampoline to return to the main code.
+	 * Pass the boot_params pointer as the first argument. The second
+	 * argument is the relocated address of the page table to use instead
+	 * of the page table in trampoline memory (if required).
 	 */
-	leaq	trampoline_return(%rip), %rdi
-
-	/* Switch to compatibility mode (CS.L = 0 CS.D = 1) via far return */
-	pushq	$__KERNEL32_CS
-	leaq	TRAMPOLINE_32BIT_CODE_OFFSET(%rax), %rax
-	pushq	%rax
-	lretq
-trampoline_return:
-	/* Restore the stack, the 32-bit trampoline uses its own stack */
-	leaq	rva(boot_stack_end)(%rbx), %rsp
-
-	/*
-	 * cleanup_trampoline() would restore trampoline memory.
-	 *
-	 * RDI is address of the page table to use instead of page table
-	 * in trampoline memory (if required).
-	 *
-	 * RSI holds real mode data and needs to be preserved across
-	 * this function call.
-	 */
-	pushq	%rsi
-	leaq	rva(top_pgtable)(%rbx), %rdi
-	call	cleanup_trampoline
-	popq	%rsi
+	movq	%r15, %rdi
+	leaq	rva(top_pgtable)(%rbx), %rsi
+	call	configure_5level_paging
 
 	/* Zero EFLAGS */
 	pushq	$0
@@ -496,7 +419,6 @@ trampoline_return:
  * Copy the compressed kernel to the end of our buffer
  * where decompression in place becomes safe.
  */
-	pushq	%rsi
 	leaq	(_bss-8)(%rip), %rsi
 	leaq	rva(_bss-8)(%rbx), %rdi
 	movl	$(_bss - startup_32), %ecx
@@ -504,7 +426,6 @@ trampoline_return:
 	std
 	rep	movsq
 	cld
-	popq	%rsi
 
 	/*
 	 * The GDT may get overwritten either during the copy we just did or
@@ -523,21 +444,6 @@ trampoline_return:
 	jmp	*%rax
 SYM_CODE_END(startup_64)
 
-#ifdef CONFIG_EFI_STUB
-#ifdef CONFIG_EFI_HANDOVER_PROTOCOL
-	.org 0x390
-#endif
-SYM_FUNC_START(efi64_stub_entry)
-	and	$~0xf, %rsp			/* realign the stack */
-	movq	%rdx, %rbx			/* save boot_params pointer */
-	call	efi_main
-	movq	%rbx,%rsi
-	leaq	rva(startup_64)(%rax), %rax
-	jmp	*%rax
-SYM_FUNC_END(efi64_stub_entry)
-SYM_FUNC_ALIAS(efi_stub_entry, efi64_stub_entry)
-#endif
-
 	.text
 SYM_FUNC_START_LOCAL_NOALIGN(.Lrelocated)
 
@@ -551,128 +457,122 @@ SYM_FUNC_START_LOCAL_NOALIGN(.Lrelocated)
 	shrq	$3, %rcx
 	rep	stosq
 
-	pushq	%rsi
 	call	load_stage2_idt
 
 	/* Pass boot_params to initialize_identity_maps() */
-	movq	(%rsp), %rdi
+	movq	%r15, %rdi
 	call	initialize_identity_maps
-	popq	%rsi
 
 /*
  * Do the extraction, and jump to the new kernel..
  */
-	pushq	%rsi			/* Save the real mode argument */
-	movq	%rsi, %rdi		/* real mode address */
-	leaq	boot_heap(%rip), %rsi	/* malloc area for uncompression */
-	leaq	input_data(%rip), %rdx  /* input_data */
-	movl	input_len(%rip), %ecx	/* input_len */
-	movq	%rbp, %r8		/* output target address */
-	movl	output_len(%rip), %r9d	/* decompressed length, end of relocs */
+	/* pass struct boot_params pointer and output target address */
+	movq	%r15, %rdi
+	movq	%rbp, %rsi
 	call	extract_kernel		/* returns kernel entry point in %rax */
-	popq	%rsi
 
 /*
  * Jump to the decompressed kernel.
  */
+	movq	%r15, %rsi
 	jmp	*%rax
 SYM_FUNC_END(.Lrelocated)
 
-	.code32
 /*
- * This is the 32-bit trampoline that will be copied over to low memory.
+ * This is the 32-bit trampoline that will be copied over to low memory. It
+ * will be called using the ordinary 64-bit calling convention from code
+ * running in 64-bit mode.
  *
- * RDI contains the return address (might be above 4G).
- * ECX contains the base address of the trampoline memory.
- * Non zero RDX means trampoline needs to enable 5-level paging.
+ * Return address is at the top of the stack (might be above 4G).
+ * The first argument (EDI) contains the address of the temporary PGD level
+ * page table in 32-bit addressable memory which will be programmed into
+ * register CR3.
  */
+	.section ".rodata", "a", @progbits
 SYM_CODE_START(trampoline_32bit_src)
-	/* Set up data and stack segments */
-	movl	$__KERNEL_DS, %eax
-	movl	%eax, %ds
-	movl	%eax, %ss
+	/*
+	 * Preserve callee save 64-bit registers on the stack: this is
+	 * necessary because the architecture does not guarantee that GPRs will
+	 * retain their full 64-bit values across a 32-bit mode switch.
+	 */
+	pushq	%r15
+	pushq	%r14
+	pushq	%r13
+	pushq	%r12
+	pushq	%rbp
+	pushq	%rbx
+
+	/* Preserve top half of RSP in a legacy mode GPR to avoid truncation */
+	movq	%rsp, %rbx
+	shrq	$32, %rbx
+
+	/* Switch to compatibility mode (CS.L = 0 CS.D = 1) via far return */
+	pushq	$__KERNEL32_CS
+	leaq	0f(%rip), %rax
+	pushq	%rax
+	lretq
 
-	/* Set up new stack */
-	leal	TRAMPOLINE_32BIT_STACK_END(%ecx), %esp
+	/*
+	 * The 32-bit code below will do a far jump back to long mode and end
+	 * up here after reconfiguring the number of paging levels. First, the
+	 * stack pointer needs to be restored to its full 64-bit value before
+	 * the callee save register contents can be popped from the stack.
+	 */
+.Lret:
+	shlq	$32, %rbx
+	orq	%rbx, %rsp
+
+	/* Restore the preserved 64-bit registers */
+	popq	%rbx
+	popq	%rbp
+	popq	%r12
+	popq	%r13
+	popq	%r14
+	popq	%r15
+	retq
 
+	.code32
+0:
 	/* Disable paging */
 	movl	%cr0, %eax
 	btrl	$X86_CR0_PG_BIT, %eax
 	movl	%eax, %cr0
 
-	/* Check what paging mode we want to be in after the trampoline */
-	testl	%edx, %edx
-	jz	1f
-
-	/* We want 5-level paging: don't touch CR3 if it already points to 5-level page tables */
-	movl	%cr4, %eax
-	testl	$X86_CR4_LA57, %eax
-	jnz	3f
-	jmp	2f
-1:
-	/* We want 4-level paging: don't touch CR3 if it already points to 4-level page tables */
-	movl	%cr4, %eax
-	testl	$X86_CR4_LA57, %eax
-	jz	3f
-2:
 	/* Point CR3 to the trampoline's new top level page table */
-	leal	TRAMPOLINE_32BIT_PGTABLE_OFFSET(%ecx), %eax
-	movl	%eax, %cr3
-3:
+	movl	%edi, %cr3
+
 	/* Set EFER.LME=1 as a precaution in case hypervsior pulls the rug */
-	pushl	%ecx
-	pushl	%edx
 	movl	$MSR_EFER, %ecx
 	rdmsr
 	btsl	$_EFER_LME, %eax
 	/* Avoid writing EFER if no change was made (for TDX guest) */
 	jc	1f
 	wrmsr
-1:	popl	%edx
-	popl	%ecx
-
-#ifdef CONFIG_X86_MCE
-	/*
-	 * Preserve CR4.MCE if the kernel will enable #MC support.
-	 * Clearing MCE may fault in some environments (that also force #MC
-	 * support). Any machine check that occurs before #MC support is fully
-	 * configured will crash the system regardless of the CR4.MCE value set
-	 * here.
-	 */
-	movl	%cr4, %eax
-	andl	$X86_CR4_MCE, %eax
-#else
-	movl	$0, %eax
-#endif
-
-	/* Enable PAE and LA57 (if required) paging modes */
-	orl	$X86_CR4_PAE, %eax
-	testl	%edx, %edx
-	jz	1f
-	orl	$X86_CR4_LA57, %eax
 1:
+	/* Toggle CR4.LA57 */
+	movl	%cr4, %eax
+	btcl	$X86_CR4_LA57_BIT, %eax
 	movl	%eax, %cr4
 
-	/* Calculate address of paging_enabled() once we are executing in the trampoline */
-	leal	.Lpaging_enabled - trampoline_32bit_src + TRAMPOLINE_32BIT_CODE_OFFSET(%ecx), %eax
-
-	/* Prepare the stack for far return to Long Mode */
-	pushl	$__KERNEL_CS
-	pushl	%eax
-
 	/* Enable paging again. */
 	movl	%cr0, %eax
 	btsl	$X86_CR0_PG_BIT, %eax
 	movl	%eax, %cr0
 
-	lret
+	/*
+	 * Return to the 64-bit calling code using LJMP rather than LRET, to
+	 * avoid the need for a 32-bit addressable stack. The destination
+	 * address will be adjusted after the template code is copied into a
+	 * 32-bit addressable buffer.
+	 */
+.Ljmp:	ljmpl	$__KERNEL_CS, $(.Lret - trampoline_32bit_src)
 SYM_CODE_END(trampoline_32bit_src)
 
-	.code64
-SYM_FUNC_START_LOCAL_NOALIGN(.Lpaging_enabled)
-	/* Return from the trampoline */
-	jmp	*%rdi
-SYM_FUNC_END(.Lpaging_enabled)
+/*
+ * This symbol is placed right after trampoline_32bit_src() so its address can
+ * be used to infer the size of the trampoline code.
+ */
+SYM_DATA(trampoline_ljmp_imm_offset, .word  .Ljmp + 1 - trampoline_32bit_src)
 
 	/*
          * The trampoline code has a size limit.
@@ -681,7 +581,7 @@ SYM_FUNC_END(.Lpaging_enabled)
 	 */
 	.org	trampoline_32bit_src + TRAMPOLINE_32BIT_CODE_SIZE
 
-	.code32
+	.text
 SYM_FUNC_START_LOCAL_NOALIGN(.Lno_longmode)
 	/* This isn't an x86-64 CPU, so hang intentionally, we cannot continue */
 1:
@@ -726,8 +626,6 @@ SYM_DATA_END_LABEL(boot_idt, SYM_L_GLOBAL, boot_idt_end)
  */
 	.bss
 	.balign 4
-SYM_DATA_LOCAL(boot_heap,	.fill BOOT_HEAP_SIZE, 1, 0)
-
 SYM_DATA_START_LOCAL(boot_stack)
 	.fill BOOT_STACK_SIZE, 1, 0
 	.balign 16
diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c
index 94b7abcf624b..f711f2a85862 100644
--- a/arch/x86/boot/compressed/misc.c
+++ b/arch/x86/boot/compressed/misc.c
@@ -330,6 +330,33 @@ static size_t parse_elf(void *output)
 	return ehdr.e_entry - LOAD_PHYSICAL_ADDR;
 }
 
+const unsigned long kernel_total_size = VO__end - VO__text;
+
+static u8 boot_heap[BOOT_HEAP_SIZE] __aligned(4);
+
+extern unsigned char input_data[];
+extern unsigned int input_len, output_len;
+
+unsigned long decompress_kernel(unsigned char *outbuf, unsigned long virt_addr,
+				void (*error)(char *x))
+{
+	unsigned long entry;
+
+	if (!free_mem_ptr) {
+		free_mem_ptr     = (unsigned long)boot_heap;
+		free_mem_end_ptr = (unsigned long)boot_heap + sizeof(boot_heap);
+	}
+
+	if (__decompress(input_data, input_len, NULL, NULL, outbuf, output_len,
+			 NULL, error) < 0)
+		return ULONG_MAX;
+
+	entry = parse_elf(outbuf);
+	handle_relocations(outbuf, output_len, virt_addr);
+
+	return entry;
+}
+
 /*
  * The compressed kernel image (ZO), has been moved so that its position
  * is against the end of the buffer used to hold the uncompressed kernel
@@ -347,14 +374,10 @@ static size_t parse_elf(void *output)
  *             |-------uncompressed kernel image---------|
  *
  */
-asmlinkage __visible void *extract_kernel(void *rmode, memptr heap,
-				  unsigned char *input_data,
-				  unsigned long input_len,
-				  unsigned char *output,
-				  unsigned long output_len)
+asmlinkage __visible void *extract_kernel(void *rmode, unsigned char *output)
 {
-	const unsigned long kernel_total_size = VO__end - VO__text;
 	unsigned long virt_addr = LOAD_PHYSICAL_ADDR;
+	memptr heap = (memptr)boot_heap;
 	unsigned long needed_size;
 	size_t entry_offset;
 
@@ -412,7 +435,7 @@ asmlinkage __visible void *extract_kernel(void *rmode, memptr heap,
 	 * entries. This ensures the full mapped area is usable RAM
 	 * and doesn't include any reserved areas.
 	 */
-	needed_size = max(output_len, kernel_total_size);
+	needed_size = max_t(unsigned long, output_len, kernel_total_size);
 #ifdef CONFIG_X86_64
 	needed_size = ALIGN(needed_size, MIN_KERNEL_ALIGN);
 #endif
@@ -443,7 +466,7 @@ asmlinkage __visible void *extract_kernel(void *rmode, memptr heap,
 #ifdef CONFIG_X86_64
 	if (heap > 0x3fffffffffffUL)
 		error("Destination address too large");
-	if (virt_addr + max(output_len, kernel_total_size) > KERNEL_IMAGE_SIZE)
+	if (virt_addr + needed_size > KERNEL_IMAGE_SIZE)
 		error("Destination virtual address is beyond the kernel mapping area");
 #else
 	if (heap > ((-__PAGE_OFFSET-(128<<20)-1) & 0x7fffffff))
@@ -461,10 +484,7 @@ asmlinkage __visible void *extract_kernel(void *rmode, memptr heap,
 		accept_memory(__pa(output), __pa(output) + needed_size);
 	}
 
-	__decompress(input_data, input_len, NULL, NULL, output, output_len,
-			NULL, error);
-	entry_offset = parse_elf(output);
-	handle_relocations(output, output_len, virt_addr);
+	entry_offset = decompress_kernel(output, virt_addr, error);
 
 	debug_putstr("done.\nBooting the kernel (entry_offset: 0x");
 	debug_puthex(entry_offset);
diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h
index 964fe903a1cd..cc70d3fb9049 100644
--- a/arch/x86/boot/compressed/misc.h
+++ b/arch/x86/boot/compressed/misc.h
@@ -179,9 +179,7 @@ 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
 extern void kernel_add_identity_map(unsigned long start, unsigned long end);
 
 /* Used by PAGE_KERN* macros: */
diff --git a/arch/x86/boot/compressed/pgtable.h b/arch/x86/boot/compressed/pgtable.h
index cc9b2529a086..6d595abe06b3 100644
--- a/arch/x86/boot/compressed/pgtable.h
+++ b/arch/x86/boot/compressed/pgtable.h
@@ -3,18 +3,16 @@
 
 #define TRAMPOLINE_32BIT_SIZE		(2 * PAGE_SIZE)
 
-#define TRAMPOLINE_32BIT_PGTABLE_OFFSET	0
-
 #define TRAMPOLINE_32BIT_CODE_OFFSET	PAGE_SIZE
-#define TRAMPOLINE_32BIT_CODE_SIZE	0x80
-
-#define TRAMPOLINE_32BIT_STACK_END	TRAMPOLINE_32BIT_SIZE
+#define TRAMPOLINE_32BIT_CODE_SIZE	0xA0
 
 #ifndef __ASSEMBLER__
 
 extern unsigned long *trampoline_32bit;
 
-extern void trampoline_32bit_src(void *return_ptr);
+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/x