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
  ...

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

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

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

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:

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);

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: */

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 */

arch/x86/boot/compressed/pgtable_64.c

@@ -16,11 +16,6 @@ unsigned int __section(".data") pgdir_shift = 39;
 unsigned int __section(".data") ptrs_per_p4d = 1;
 #endif
 
-struct paging_config {
-	unsigned long trampoline_start;
-	unsigned long l5_required;
-};
-
 /* Buffer to preserve trampoline memory */
 static char trampoline_save[TRAMPOLINE_32BIT_SIZE];
 
@@ -29,7 +24,7 @@ static char trampoline_save[TRAMPOLINE_32BIT_SIZE];
  * purposes.
  *
  * Avoid putting the pointer into .bss as it will be cleared between
- * paging_prepare() and extract_kernel().
+ * configure_5level_paging() and extract_kernel().
  */
 unsigned long *trampoline_32bit __section(".data");
 
@@ -106,12 +101,13 @@ static unsigned long find_trampoline_placement(void)
 	return bios_start - TRAMPOLINE_32BIT_SIZE;
 }
 
-struct paging_config paging_prepare(void *rmode)
+asmlinkage void configure_5level_paging(struct boot_params *bp, void *pgtable)
 {
-	struct paging_config paging_config = {};
+	void (*toggle_la57)(void *cr3);
+	bool l5_required = false;
 
 	/* Initialize boot_params. Required for cmdline_find_option_bool(). */
-	boot_params = rmode;
+	boot_params = bp;
 
 	/*
 	 * Check if LA57 is desired and supported.
@@ -129,12 +125,22 @@ struct paging_config paging_prepare(void *rmode)
 			!cmdline_find_option_bool("no5lvl") &&
 			native_cpuid_eax(0) >= 7 &&
 			(native_cpuid_ecx(7) & (1 << (X86_FEATURE_LA57 & 31)))) {
-		paging_config.l5_required = 1;
+		l5_required = true;
+
+		/* Initialize variables for 5-level paging */
+		__pgtable_l5_enabled = 1;
+		pgdir_shift = 48;
+		ptrs_per_p4d = 512;
 	}
 
-	paging_config.trampoline_start = find_trampoline_placement();
+	/*
+	 * The trampoline will not be used if the paging mode is already set to
+	 * the desired one.
+	 */
+	if (l5_required == !!(native_read_cr4() & X86_CR4_LA57))
+		return;
 
-	trampoline_32bit = (unsigned long *)paging_config.trampoline_start;
+	trampoline_32bit = (unsigned long *)find_trampoline_placement();
 
 	/* Preserve trampoline memory */
 	memcpy(trampoline_save, trampoline_32bit, TRAMPOLINE_32BIT_SIZE);
@@ -143,32 +149,32 @@ struct paging_config paging_prepare(void *rmode)
 	memset(trampoline_32bit, 0, TRAMPOLINE_32BIT_SIZE);
 
 	/* Copy trampoline code in place */
-	memcpy(trampoline_32bit + TRAMPOLINE_32BIT_CODE_OFFSET / sizeof(unsigned long),
+	toggle_la57 = memcpy(trampoline_32bit +
+			TRAMPOLINE_32BIT_CODE_OFFSET / sizeof(unsigned long),
 			&trampoline_32bit_src, TRAMPOLINE_32BIT_CODE_SIZE);
 
+	/*
+	 * Avoid the need for a stack in the 32-bit trampoline code, by using
+	 * LJMP rather than LRET to return back to long mode. LJMP takes an
+	 * immediate absolute address, which needs to be adjusted based on the
+	 * placement of the trampoline.
+	 */
+	*(u32 *)((u8 *)toggle_la57 + trampoline_ljmp_imm_offset) +=
+						(unsigned long)toggle_la57;
+
 	/*
 	 * The code below prepares page table in trampoline memory.
 	 *
 	 * The new page table will be used by trampoline code for switching
 	 * from 4- to 5-level paging or vice versa.
-	 *
-	 * If switching is not required, the page table is unused: trampoline
-	 * code wouldn't touch CR3.
-	 */
-
-	/*
-	 * We are not going to use the page table in trampoline memory if we
-	 * are already in the desired paging mode.
 	 */
-	if (paging_config.l5_required == !!(native_read_cr4() & X86_CR4_LA57))
-		goto out;
 
-	if (paging_config.l5_required) {
+	if (l5_required) {
 		/*
 		 * For 4- to 5-level paging transition, set up current CR3 as
 		 * the first and the only entry in a new top-level page table.
 		 */
-		trampoline_32bit[TRAMPOLINE_32BIT_PGTABLE_OFFSET] = __native_read_cr3() | _PAGE_TABLE_NOENC;
+		*trampoline_32bit = __native_read_cr3() | _PAGE_TABLE_NOENC;
 	} else {
 		unsigned long src;
 
@@ -181,38 +187,17 @@ struct paging_config paging_prepare(void *rmode)
 		 * may be above 4G.
 		 */
 		src = *(unsigned long *)__native_read_cr3() & PAGE_MASK;
-		memcpy(trampoline_32bit + TRAMPOLINE_32BIT_PGTABLE_OFFSET / sizeof(unsigned long),
-		       (void *)src, PAGE_SIZE);
+		memcpy(trampoline_32bit, (void *)src, PAGE_SIZE);
 	}
 
-out:
-	return paging_config;
-}
-
-void cleanup_trampoline(void *pgtable)
-{
-	void *trampoline_pgtable;
-
-	trampoline_pgtable = trampoline_32bit + TRAMPOLINE_32BIT_PGTABLE_OFFSET / sizeof(unsigned long);
+	toggle_la57(trampoline_32bit);
 
 	/*
-	 * Move the top level page table out of trampoline memory,
-	 * if it's there.
+	 * Move the top level page table out of trampoline memory.
 	 */
-	if ((void *)__native_read_cr3() == trampoline_pgtable) {
-		memcpy(pgtable, trampoline_pgtable, PAGE_SIZE);
-		native_write_cr3((unsigned long)pgtable);
-	}
+	memcpy(pgtable, trampoline_32bit, PAGE_SIZE);
+	native_write_cr3((unsigned long)pgtable);
 
 	/* Restore trampoline memory */
 	memcpy(trampoline_32bit, trampoline_save, TRAMPOLINE_32BIT_SIZE);
-
-	/* Initialize variables for 5-level paging */
-#ifdef CONFIG_X86_5LEVEL
-	if (__read_cr4() & X86_CR4_LA57) {
-		__pgtable_l5_enabled = 1;
-		pgdir_shift = 48;
-		ptrs_per_p4d = 512;
-	}
-#endif
 }

arch/x86/boot/compressed/sev.c

@@ -367,20 +367,25 @@ static void enforce_vmpl0(void)
  */
 #define SNP_FEATURES_PRESENT (0)
 
+u64 snp_get_unsupported_features(u64 status)
+{
+	if (!(status & MSR_AMD64_SEV_SNP_ENABLED))
+		return 0;
+
+	return status & SNP_FEATURES_IMPL_REQ & ~SNP_FEATURES_PRESENT;
+}
+
 void snp_check_features(void)
 {
 	u64 unsupported;
 
-	if (!(sev_status & MSR_AMD64_SEV_SNP_ENABLED))
-		return;
-
 	/*
 	 * Terminate the boot if hypervisor has enabled any feature lacking
 	 * guest side implementation. Pass on the unsupported features mask through
 	 * EXIT_INFO_2 of the GHCB protocol so that those features can be reported
 	 * as part of the guest boot failure.
 	 */
-	unsupported = sev_status & SNP_FEATURES_IMPL_REQ & ~SNP_FEATURES_PRESENT;
+	unsupported = snp_get_unsupported_features(sev_status);
 	if (unsupported) {
 		if (ghcb_version < 2 || (!boot_ghcb && !early_setup_ghcb()))
 			sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SNP_UNSUPPORTED);
@@ -390,35 +395,22 @@ void snp_check_features(void)
 	}
 }
 
-void sev_enable(struct boot_params *bp)
+/*
+ * sev_check_cpu_support - Check for SEV support in the CPU capabilities
+ *
+ * Returns < 0 if SEV is not supported, otherwise the position of the
+ * encryption bit in the page table descriptors.
+ */
+static int sev_check_cpu_support(void)
 {
 	unsigned int eax, ebx, ecx, edx;
-	struct msr m;
-	bool snp;
-
-	/*
-	 * bp->cc_blob_address should only be set by boot/compressed kernel.
-	 * Initialize it to 0 to ensure that uninitialized values from
-	 * buggy bootloaders aren't propagated.
-	 */
-	if (bp)
-		bp->cc_blob_address = 0;
-
-	/*
-	 * Do an initial SEV capability check before snp_init() which
-	 * loads the CPUID page and the same checks afterwards are done
-	 * without the hypervisor and are trustworthy.
-	 *
-	 * If the HV fakes SEV support, the guest will crash'n'burn
-	 * which is good enough.
-	 */
 
 	/* Check for the SME/SEV support leaf */
 	eax = 0x80000000;
 	ecx = 0;
 	native_cpuid(&eax, &ebx, &ecx, &edx);
 	if (eax < 0x8000001f)
-		return;
+		return -ENODEV;
 
 	/*
 	 * Check for the SME/SEV feature:
@@ -433,6 +425,35 @@ void sev_enable(struct boot_params *bp)
 	native_cpuid(&eax, &ebx, &ecx, &edx);
 	/* Check whether SEV is supported */
 	if (!(eax & BIT(1)))
+		return -ENODEV;
+
+	return ebx & 0x3f;
+}
+
+void sev_enable(struct boot_params *bp)
+{
+	struct msr m;
+	int bitpos;
+	bool snp;
+
+	/*
+	 * bp->cc_blob_address should only be set by boot/compressed kernel.
+	 * Initialize it to 0 to ensure that uninitialized values from
+	 * buggy bootloaders aren't propagated.
+	 */
+	if (bp)
+		bp->cc_blob_address = 0;
+
+	/*
+	 * Do an initial SEV capability check before snp_init() which
+	 * loads the CPUID page and the same checks afterwards are done
+	 * without the hypervisor and are trustworthy.
+	 *
+	 * If the HV fakes SEV support, the guest will crash'n'burn
+	 * which is good enough.
+	 */
+
+	if (sev_check_cpu_support() < 0)
 		return;
 
 	/*
@@ -443,26 +464,8 @@ void sev_enable(struct boot_params *bp)
 
 	/* Now repeat the checks with the SNP CPUID table. */
 
-	/* Recheck the SME/SEV support leaf */
-	eax = 0x80000000;
-	ecx = 0;
-	native_cpuid(&eax, &ebx, &ecx, &edx);
-	if (eax < 0x8000001f)
-		return;
-
-	/*
-	 * Recheck for the SME/SEV feature:
-	 *   CPUID Fn8000_001F[EAX]
-	 *   - Bit 0 - Secure Memory Encryption support
-	 *   - Bit 1 - Secure Encrypted Virtualization support
-	 *   CPUID Fn8000_001F[EBX]
-	 *   - Bits 5:0 - Pagetable bit position used to indicate encryption
-	 */
-	eax = 0x8000001f;
-	ecx = 0;
-	native_cpuid(&eax, &ebx, &ecx, &edx);
-	/* Check whether SEV is supported */
-	if (!(eax & BIT(1))) {
+	bitpos = sev_check_cpu_support();
+	if (bitpos < 0) {
 		if (snp)
 			error("SEV-SNP support indicated by CC blob, but not CPUID.");
 		return;
@@ -494,7 +497,24 @@ void sev_enable(struct boot_params *bp)
 	if (snp && !(sev_status & MSR_AMD64_SEV_SNP_ENABLED))
 		error("SEV-SNP supported indicated by CC blob, but not SEV status MSR.");
 
-	sme_me_mask = BIT_ULL(ebx & 0x3f);
+	sme_me_mask = BIT_ULL(bitpos);
+}
+
+/*
+ * sev_get_status - Retrieve the SEV status mask
+ *
+ * Returns 0 if the CPU is not SEV capable, otherwise the value of the
+ * AMD64_SEV MSR.
+ */
+u64 sev_get_status(void)
+{
+	struct msr m;
+
+	if (sev_check_cpu_support() < 0)
+		return 0;
+
+	boot_rdmsr(MSR_AMD64_SEV, &m);
+	return m.q;
 }
 
 /* Search for Confidential Computing blob in the EFI config table. */

arch/x86/include/asm/boot.h

@@ -62,4 +62,12 @@
 # define BOOT_STACK_SIZE	0x1000
 #endif
 
+#ifndef __ASSEMBLY__
+extern unsigned int output_len;
+extern const unsigned long kernel_total_size;
+
+unsigned long decompress_kernel(unsigned char *outbuf, unsigned long virt_addr,
+				void (*error)(char *x));
+#endif
+
 #endif /* _ASM_X86_BOOT_H */

arch/x86/include/asm/efi.h

@@ -90,6 +90,8 @@ static inline void efi_fpu_end(void)
 }
 
 #ifdef CONFIG_X86_32
+#define EFI_X86_KERNEL_ALLOC_LIMIT		(SZ_512M - 1)
+
 #define arch_efi_call_virt_setup()					\
 ({									\
 	efi_fpu_begin();						\
@@ -103,8 +105,7 @@ static inline void efi_fpu_end(void)
 })
 
 #else /* !CONFIG_X86_32 */
-
-#define EFI_LOADER_SIGNATURE	"EL64"
+#define EFI_X86_KERNEL_ALLOC_LIMIT		EFI_ALLOC_LIMIT
 
 extern asmlinkage u64 __efi_call(void *fp, ...);
 
@@ -218,6 +219,8 @@ efi_status_t efi_set_virtual_address_map(unsigned long memory_map_size,
 
 #ifdef CONFIG_EFI_MIXED
 
+#define EFI_ALLOC_LIMIT		(efi_is_64bit() ? ULONG_MAX : U32_MAX)
+
 #define ARCH_HAS_EFISTUB_WRAPPERS
 
 static inline bool efi_is_64bit(void)

arch/x86/include/asm/sev.h

@@ -164,6 +164,7 @@ static __always_inline void sev_es_nmi_complete(void)
 		__sev_es_nmi_complete();
 }
 extern int __init sev_es_efi_map_ghcbs(pgd_t *pgd);
+extern void sev_enable(struct boot_params *bp);
 
 static inline int rmpadjust(unsigned long vaddr, bool rmp_psize, unsigned long attrs)
 {
@@ -210,12 +211,15 @@ bool snp_init(struct boot_params *bp);
 void __init __noreturn snp_abort(void);
 int snp_issue_guest_request(u64 exit_code, struct snp_req_data *input, struct snp_guest_request_ioctl *rio);
 void snp_accept_memory(phys_addr_t start, phys_addr_t end);
+u64 snp_get_unsupported_features(u64 status);
+u64 sev_get_status(void);
 #else
 static inline void sev_es_ist_enter(struct pt_regs *regs) { }
 static inline void sev_es_ist_exit(void) { }
 static inline int sev_es_setup_ap_jump_table(struct real_mode_header *rmh) { return 0; }
 static inline void sev_es_nmi_complete(void) { }
 static inline int sev_es_efi_map_ghcbs(pgd_t *pgd) { return 0; }
+static inline void sev_enable(struct boot_params *bp) { }
 static inline int pvalidate(unsigned long vaddr, bool rmp_psize, bool validate) { return 0; }
 static inline int rmpadjust(unsigned long vaddr, bool rmp_psize, unsigned long attrs) { return 0; }
 static inline void setup_ghcb(void) { }
@@ -235,6 +239,8 @@ static inline int snp_issue_guest_request(u64 exit_code, struct snp_req_data *in
 }
 
 static inline void snp_accept_memory(phys_addr_t start, phys_addr_t end) { }
+static inline u64 snp_get_unsupported_features(u64 status) { return 0; }
+static inline u64 sev_get_status(void) { return 0; }
 #endif
 
 #endif

arch/x86/kernel/head_64.S

@@ -51,7 +51,9 @@ SYM_CODE_START_NOALIGN(startup_64)
 	 * for us.  These identity mapped page tables map all of the
 	 * kernel pages and possibly all of memory.
 	 *
-	 * %rsi holds a physical pointer to real_mode_data.
+	 * %RSI holds the physical address of the boot_params structure
+	 * provided by the bootloader. Preserve it in %R15 so C function calls
+	 * will not clobber it.
 	 *
 	 * We come here either directly from a 64bit bootloader, or from
 	 * arch/x86/boot/compressed/head_64.S.
@@ -62,6 +64,7 @@ SYM_CODE_START_NOALIGN(startup_64)
 	 * compiled to run at we first fixup the physical addresses in our page
 	 * tables and then reload them.
 	 */
+	mov	%rsi, %r15
 
 	/* Set up the stack for verify_cpu() */
 	leaq	(__end_init_task - PTREGS_SIZE)(%rip), %rsp
@@ -75,9 +78,7 @@ SYM_CODE_START_NOALIGN(startup_64)
 	shrq	$32,  %rdx
 	wrmsr
 
-	pushq	%rsi
 	call	startup_64_setup_env
-	popq	%rsi
 
 	/* Now switch to __KERNEL_CS so IRET works reliably */
 	pushq	$__KERNEL_CS
@@ -93,12 +94,10 @@ SYM_CODE_START_NOALIGN(startup_64)
 	 * Activate SEV/SME memory encryption if supported/enabled. This needs to
 	 * be done now, since this also includes setup of the SEV-SNP CPUID table,
 	 * which needs to be done before any CPUID instructions are executed in
-	 * subsequent code.
+	 * subsequent code. Pass the boot_params pointer as the first argument.
 	 */
-	movq	%rsi, %rdi
-	pushq	%rsi
+	movq	%r15, %rdi
 	call	sme_enable
-	popq	%rsi
 #endif
 
 	/* Sanitize CPU configuration */
@@ -111,9 +110,8 @@ SYM_CODE_START_NOALIGN(startup_64)
 	 * programmed into CR3.
 	 */
 	leaq	_text(%rip), %rdi
-	pushq	%rsi
+	movq	%r15, %rsi
 	call	__startup_64
-	popq	%rsi
 
 	/* Form the CR3 value being sure to include the CR3 modifier */
 	addq	$(early_top_pgt - __START_KERNEL_map), %rax
@@ -127,8 +125,6 @@ SYM_CODE_START(secondary_startup_64)
 	 * At this point the CPU runs in 64bit mode CS.L = 1 CS.D = 0,
 	 * and someone has loaded a mapped page table.
 	 *
-	 * %rsi holds a physical pointer to real_mode_data.
-	 *
 	 * We come here either from startup_64 (using physical addresses)
 	 * or from trampoline.S (using virtual addresses).
 	 *
@@ -153,6 +149,9 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL)
 	UNWIND_HINT_END_OF_STACK
 	ANNOTATE_NOENDBR
 
+	/* Clear %R15 which holds the boot_params pointer on the boot CPU */
+	xorq	%r15, %r15
+
 	/*
 	 * Retrieve the modifier (SME encryption mask if SME is active) to be
 	 * added to the initial pgdir entry that will be programmed into CR3.
@@ -199,13 +198,9 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL)
 	 * hypervisor could lie about the C-bit position to perform a ROP
 	 * attack on the guest by writing to the unencrypted stack and wait for
 	 * the next RET instruction.
-	 * %rsi carries pointer to realmode data and is callee-clobbered. Save
-	 * and restore it.
 	 */
-	pushq	%rsi
 	movq	%rax, %rdi
 	call	sev_verify_cbit
-	popq	%rsi
 
 	/*
 	 * Switch to new page-table
@@ -365,9 +360,7 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL)
 	wrmsr
 
 	/* Setup and Load IDT */
-	pushq	%rsi
 	call	early_setup_idt
-	popq	%rsi
 
 	/* Check if nx is implemented */
 	movl	$0x80000001, %eax
@@ -403,9 +396,8 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL)
 	pushq $0
 	popfq
 
-	/* rsi is pointer to real mode structure with interesting info.
-	   pass it to C */
-	movq	%rsi, %rdi
+	/* Pass the boot_params pointer as first argument */
+	movq	%r15, %rdi
 
 .Ljump_to_C_code:
 	/*

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
 

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 {

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");

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);
 

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)

drivers/firmware/efi/libstub/x86-5lvl.c

+// 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);
+}

drivers/firmware/efi/libstub/x86-stub.h

+/* 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

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;

include/linux/decompress/mm.h

@@ -48,7 +48,7 @@ MALLOC_VISIBLE void *malloc(int size)
 	if (!malloc_ptr)
 		malloc_ptr = free_mem_ptr;
 
-	malloc_ptr = (malloc_ptr + 3) & ~3;     /* Align */
+	malloc_ptr = (malloc_ptr + 7) & ~7;     /* Align */
 
 	p = (void *)malloc_ptr;
 	malloc_ptr += size;