Merge tag 'efi-next' of git://git.kernel.org/pub/scm/linux/kernel/git…

…/efi/efi into efi/core

Pull EFI updates for v5.7 from Ard Biesheuvel:

This time, the set of changes for the EFI subsystem is much larger than
usual. The main reasons are:

 - Get things cleaned up before EFI support for RISC-V arrives, which will
   increase the size of the validation matrix, and therefore the threshold to
   making drastic changes,

 - After years of defunct maintainership, the GRUB project has finally started
   to consider changes from the distros regarding UEFI boot, some of which are
   highly specific to the way x86 does UEFI secure boot and measured boot,
   based on knowledge of both shim internals and the layout of bootparams and
   the x86 setup header. Having this maintenance burden on other architectures
   (which don't need shim in the first place) is hard to justify, so instead,
   we are introducing a generic Linux/UEFI boot protocol.

Summary of changes:

 - Boot time GDT handling changes (Arvind)

 - Simplify handling of EFI properties table on arm64

 - Generic EFI stub cleanups, to improve command line handling, file I/O,
   memory allocation, etc.

 - Introduce a generic initrd loading method based on calling back into
   the firmware, instead of relying on the x86 EFI handover protocol or
   device tree.

 - Introduce a mixed mode boot method that does not rely on the x86 EFI
   handover protocol either, and could potentially be adopted by other
   architectures (if another one ever surfaces where one execution mode
   is a superset of another)

 - Clean up the contents of struct efi, and move out everything that
   doesn't need to be stored there.

 - Incorporate support for UEFI spec v2.8A changes that permit firmware
   implementations to return EFI_UNSUPPORTED from UEFI runtime services at
   OS runtime, and expose a mask of which ones are supported or unsupported
   via a configuration table.

 - Various documentation updates and minor code cleanups (Heinrich)

 - Partial fix for the lack of by-VA cache maintenance in the decompressor
   on 32-bit ARM. Note that these patches were deliberately put at the
   beginning so they can be used as a stable branch that will be shared with
   a PR containing the complete fix, which I will send to the ARM tree.

Signed-off-by: Ingo Molnar <[email protected]>

Documentation/x86/boot.rst

@@ -490,15 +490,11 @@ Protocol:	2.00+
 		kernel) to not write early messages that require
 		accessing the display hardware directly.
 
-  Bit 6 (write): KEEP_SEGMENTS
+  Bit 6 (obsolete): KEEP_SEGMENTS
 
 	Protocol: 2.07+
 
-	- If 0, reload the segment registers in the 32bit entry point.
-	- If 1, do not reload the segment registers in the 32bit entry point.
-
-		Assume that %cs %ds %ss %es are all set to flat segments with
-		a base of 0 (or the equivalent for their environment).
+        - This flag is obsolete.
 
   Bit 7 (write): CAN_USE_HEAP
 

arch/arm/boot/compressed/efi-header.S

@@ -60,7 +60,7 @@ optional_header:
 		.long	__pecoff_code_size		@ SizeOfCode
 		.long	__pecoff_data_size		@ SizeOfInitializedData
 		.long	0				@ SizeOfUninitializedData
-		.long	efi_stub_entry - start		@ AddressOfEntryPoint
+		.long	efi_entry - start		@ AddressOfEntryPoint
 		.long	start_offset			@ BaseOfCode
 		.long	__pecoff_data_start - start	@ BaseOfData
 
@@ -70,8 +70,8 @@ extra_header_fields:
 		.long	SZ_512				@ FileAlignment
 		.short	0				@ MajorOsVersion
 		.short	0				@ MinorOsVersion
-		.short	0				@ MajorImageVersion
-		.short	0				@ MinorImageVersion
+		.short	LINUX_EFISTUB_MAJOR_VERSION	@ MajorImageVersion
+		.short	LINUX_EFISTUB_MINOR_VERSION	@ MinorImageVersion
 		.short	0				@ MajorSubsystemVersion
 		.short	0				@ MinorSubsystemVersion
 		.long	0				@ Win32VersionValue

arch/arm/boot/compressed/head.S

@@ -1437,30 +1437,28 @@ __enter_kernel:
 reloc_code_end:
 
 #ifdef CONFIG_EFI_STUB
-		.align	2
-_start:		.long	start - .
-
-ENTRY(efi_stub_entry)
-		@ allocate space on stack for passing current zImage address
-		@ and for the EFI stub to return of new entry point of
-		@ zImage, as EFI stub may copy the kernel. Pointer address
-		@ is passed in r2. r0 and r1 are passed through from the
-		@ EFI firmware to efi_entry
-		adr	ip, _start
-		ldr	r3, [ip]
-		add	r3, r3, ip
-		stmfd	sp!, {r3, lr}
-		mov	r2, sp			@ pass zImage address in r2
-		bl	efi_entry
-
-		@ Check for error return from EFI stub. r0 has FDT address
-		@ or error code.
-		cmn	r0, #1
-		beq	efi_load_fail
-
-		@ Preserve return value of efi_entry() in r4
-		mov	r4, r0
+ENTRY(efi_enter_kernel)
+		mov	r7, r0				@ preserve image base
+		mov	r4, r1				@ preserve DT pointer
+
+		mov	r0, r4				@ DT start
+		add	r1, r4, r2			@ DT end
+		bl	cache_clean_flush
+
+		mov	r0, r7				@ relocated zImage
+		ldr	r1, =_edata			@ size of zImage
+		add	r1, r1, r0			@ end of zImage
 		bl	cache_clean_flush
+
+		@ The PE/COFF loader might not have cleaned the code we are
+		@ running beyond the PoU, and so calling cache_off below from
+		@ inside the PE/COFF loader allocated region is unsafe. Let's
+		@ assume our own zImage relocation code did a better job, and
+		@ jump into its version of this routine before proceeding.
+		ldr	r1, .Ljmp
+		sub	r1, r7, r1
+		mov	pc, r1				@ no mode switch
+0:
 		bl	cache_off
 
 		@ Set parameters for booting zImage according to boot protocol
@@ -1469,18 +1467,10 @@ ENTRY(efi_stub_entry)
 		mov	r0, #0
 		mov	r1, #0xFFFFFFFF
 		mov	r2, r4
-
-		@ Branch to (possibly) relocated zImage that is in [sp]
-		ldr	lr, [sp]
-		ldr	ip, =start_offset
-		add	lr, lr, ip
-		mov	pc, lr				@ no mode switch
-
-efi_load_fail:
-		@ Return EFI_LOAD_ERROR to EFI firmware on error.
-		ldr	r0, =0x80000001
-		ldmfd	sp!, {ip, pc}
-ENDPROC(efi_stub_entry)
+		b	__efi_start
+ENDPROC(efi_enter_kernel)
+		.align	2
+.Ljmp:		.long	start - 0b
 #endif
 
 		.align

arch/arm64/include/asm/efi.h

@@ -57,13 +57,6 @@ efi_status_t __efi_rt_asm_wrapper(void *, const char *, ...);
 
 /* arch specific definitions used by the stub code */
 
-/*
- * AArch64 requires the DTB to be 8-byte aligned in the first 512MiB from
- * start of kernel and may not cross a 2MiB boundary. We set alignment to
- * 2MiB so we know it won't cross a 2MiB boundary.
- */
-#define EFI_FDT_ALIGN	SZ_2M   /* used by allocate_new_fdt_and_exit_boot() */
-
 /*
  * In some configurations (e.g. VMAP_STACK && 64K pages), stacks built into the
  * kernel need greater alignment than we require the segments to be padded to.
@@ -107,9 +100,6 @@ static inline void free_screen_info(struct screen_info *si)
 {
 }
 
-/* redeclare as 'hidden' so the compiler will generate relative references */
-extern struct screen_info screen_info __attribute__((__visibility__("hidden")));
-
 static inline void efifb_setup_from_dmi(struct screen_info *si, const char *opt)
 {
 }

arch/arm64/kernel/efi-entry.S

@@ -10,81 +10,35 @@
 
 #include <asm/assembler.h>
 
-#define EFI_LOAD_ERROR 0x8000000000000001
-
 	__INIT
 
-	/*
-	 * We arrive here from the EFI boot manager with:
-	 *
-	 *    * CPU in little-endian mode
-	 *    * MMU on with identity-mapped RAM
-	 *    * Icache and Dcache on
-	 *
-	 * We will most likely be running from some place other than where
-	 * we want to be. The kernel image wants to be placed at TEXT_OFFSET
-	 * from start of RAM.
-	 */
-ENTRY(entry)
-	/*
-	 * Create a stack frame to save FP/LR with extra space
-	 * for image_addr variable passed to efi_entry().
-	 */
-	stp	x29, x30, [sp, #-32]!
-	mov	x29, sp
-
-	/*
-	 * Call efi_entry to do the real work.
-	 * x0 and x1 are already set up by firmware. Current runtime
-	 * address of image is calculated and passed via *image_addr.
-	 *
-	 * unsigned long efi_entry(void *handle,
-	 *                         efi_system_table_t *sys_table,
-	 *                         unsigned long *image_addr) ;
-	 */
-	adr_l	x8, _text
-	add	x2, sp, 16
-	str	x8, [x2]
-	bl	efi_entry
-	cmn	x0, #1
-	b.eq	efi_load_fail
-
+ENTRY(efi_enter_kernel)
 	/*
 	 * efi_entry() will have copied the kernel image if necessary and we
-	 * return here with device tree address in x0 and the kernel entry
-	 * point stored at *image_addr. Save those values in registers which
-	 * are callee preserved.
-	 */
-	mov	x20, x0		// DTB address
-	ldr	x0, [sp, #16]	// relocated _text address
-	ldr	w21, =stext_offset
-	add	x21, x0, x21
-
-	/*
-	 * Calculate size of the kernel Image (same for original and copy).
+	 * end up here with device tree address in x1 and the kernel entry
+	 * point stored in x0. Save those values in registers which are
+	 * callee preserved.
 	 */
-	adr_l	x1, _text
-	adr_l	x2, _edata
-	sub	x1, x2, x1
+	mov	x19, x0			// relocated Image address
+	mov	x20, x1			// DTB address
 
 	/*
 	 * Flush the copied Image to the PoC, and ensure it is not shadowed by
 	 * stale icache entries from before relocation.
 	 */
+	ldr	w1, =kernel_size
 	bl	__flush_dcache_area
 	ic	ialluis
+	dsb	sy
 
 	/*
-	 * Ensure that the rest of this function (in the original Image) is
-	 * visible when the caches are disabled. The I-cache can't have stale
-	 * entries for the VA range of the current image, so no maintenance is
-	 * necessary.
+	 * Jump across, into the copy of the image that we just cleaned
+	 * to the PoC, so that we can safely disable the MMU and caches.
 	 */
-	adr	x0, entry
-	adr	x1, entry_end
-	sub	x1, x1, x0
-	bl	__flush_dcache_area
-
+	ldr	w0, .Ljmp
+	sub	x0, x19, w0, sxtw
+	br	x0
+0:
 	/* Turn off Dcache and MMU */
 	mrs	x0, CurrentEL
 	cmp	x0, #CurrentEL_EL2
@@ -109,12 +63,6 @@ ENTRY(entry)
 	mov	x1, xzr
 	mov	x2, xzr
 	mov	x3, xzr
-	br	x21
-
-efi_load_fail:
-	mov	x0, #EFI_LOAD_ERROR
-	ldp	x29, x30, [sp], #32
-	ret
-
-entry_end:
-ENDPROC(entry)
+	b	stext
+ENDPROC(efi_enter_kernel)
+.Ljmp:	.long	_text - 0b

arch/arm64/kernel/efi-header.S

@@ -27,7 +27,7 @@ optional_header:
 	.long	__initdata_begin - efi_header_end	// SizeOfCode
 	.long	__pecoff_data_size			// SizeOfInitializedData
 	.long	0					// SizeOfUninitializedData
-	.long	__efistub_entry - _head			// AddressOfEntryPoint
+	.long	__efistub_efi_entry - _head		// AddressOfEntryPoint
 	.long	efi_header_end - _head			// BaseOfCode
 
 extra_header_fields:
@@ -36,8 +36,8 @@ extra_header_fields:
 	.long	PECOFF_FILE_ALIGNMENT			// FileAlignment
 	.short	0					// MajorOperatingSystemVersion
 	.short	0					// MinorOperatingSystemVersion
-	.short	0					// MajorImageVersion
-	.short	0					// MinorImageVersion
+	.short	LINUX_EFISTUB_MAJOR_VERSION		// MajorImageVersion
+	.short	LINUX_EFISTUB_MINOR_VERSION		// MinorImageVersion
 	.short	0					// MajorSubsystemVersion
 	.short	0					// MinorSubsystemVersion
 	.long	0					// Win32VersionValue

arch/arm64/kernel/image-vars.h

@@ -12,7 +12,8 @@
 
 #ifdef CONFIG_EFI
 
-__efistub_stext_offset = stext - _text;
+__efistub_kernel_size		= _edata - _text;
+
 
 /*
  * The EFI stub has its own symbol namespace prefixed by __efistub_, to
@@ -42,9 +43,11 @@ __efistub___memset		= __pi_memset;
 #endif
 
 __efistub__text			= _text;
+__efistub_stext			= stext;
 __efistub__end			= _end;
 __efistub__edata		= _edata;
 __efistub_screen_info		= screen_info;
+__efistub__ctype		= _ctype;
 
 #endif
 

arch/ia64/kernel/efi.c

@@ -45,11 +45,21 @@
 
 #define EFI_DEBUG	0
 
+#define ESI_TABLE_GUID					\
+    EFI_GUID(0x43EA58DC, 0xCF28, 0x4b06, 0xB3,		\
+	     0x91, 0xB7, 0x50, 0x59, 0x34, 0x2B, 0xD4)
+
+static unsigned long mps_phys = EFI_INVALID_TABLE_ADDR;
 static __initdata unsigned long palo_phys;
 
+unsigned long __initdata esi_phys = EFI_INVALID_TABLE_ADDR;
+unsigned long hcdp_phys = EFI_INVALID_TABLE_ADDR;
 unsigned long sal_systab_phys = EFI_INVALID_TABLE_ADDR;
 
-static __initdata efi_config_table_type_t arch_tables[] = {
+static const efi_config_table_type_t arch_tables[] __initconst = {
+	{ESI_TABLE_GUID, "ESI", &esi_phys},
+	{HCDP_TABLE_GUID, "HCDP", &hcdp_phys},
+	{MPS_TABLE_GUID, "MPS", &mps_phys},
 	{PROCESSOR_ABSTRACTION_LAYER_OVERWRITE_GUID, "PALO", &palo_phys},
 	{SAL_SYSTEM_TABLE_GUID, "SALsystab", &sal_systab_phys},
 	{NULL_GUID, NULL, 0},
@@ -474,11 +484,10 @@ efi_map_pal_code (void)
 void __init
 efi_init (void)
 {
+	const efi_system_table_t *efi_systab;
 	void *efi_map_start, *efi_map_end;
-	efi_char16_t *c16;
 	u64 efi_desc_size;
-	char *cp, vendor[100] = "unknown";
-	int i;
+	char *cp;
 
 	set_bit(EFI_BOOT, &efi.flags);
 	set_bit(EFI_64BIT, &efi.flags);
@@ -508,42 +517,29 @@ efi_init (void)
 		printk(KERN_INFO "Ignoring memory above %lluMB\n",
 		       max_addr >> 20);
 
-	efi.systab = __va(ia64_boot_param->efi_systab);
+	efi_systab = __va(ia64_boot_param->efi_systab);
 
 	/*
 	 * Verify the EFI Table
 	 */
-	if (efi.systab == NULL)
+	if (efi_systab == NULL)
 		panic("Whoa! Can't find EFI system table.\n");
-	if (efi.systab->hdr.signature != EFI_SYSTEM_TABLE_SIGNATURE)
+	if (efi_systab_check_header(&efi_systab->hdr, 1))
 		panic("Whoa! EFI system table signature incorrect\n");
-	if ((efi.systab->hdr.revision >> 16) == 0)
-		printk(KERN_WARNING "Warning: EFI system table version "
-		       "%d.%02d, expected 1.00 or greater\n",
-		       efi.systab->hdr.revision >> 16,
-		       efi.systab->hdr.revision & 0xffff);
-
-	/* Show what we know for posterity */
-	c16 = __va(efi.systab->fw_vendor);
-	if (c16) {
-		for (i = 0;i < (int) sizeof(vendor) - 1 && *c16; ++i)
-			vendor[i] = *c16++;
-		vendor[i] = '\0';
-	}
 
-	printk(KERN_INFO "EFI v%u.%.02u by %s:",
-	       efi.systab->hdr.revision >> 16,
-	       efi.systab->hdr.revision & 0xffff, vendor);
+	efi_systab_report_header(&efi_systab->hdr, efi_systab->fw_vendor);
 
 	palo_phys      = EFI_INVALID_TABLE_ADDR;
 
-	if (efi_config_init(arch_tables) != 0)
+	if (efi_config_parse_tables(__va(efi_systab->tables),
+				    efi_systab->nr_tables,
+				    arch_tables) != 0)
 		return;
 
 	if (palo_phys != EFI_INVALID_TABLE_ADDR)
 		handle_palo(palo_phys);
 
-	runtime = __va(efi.systab->runtime);
+	runtime = __va(efi_systab->runtime);
 	efi.get_time = phys_get_time;
 	efi.set_time = phys_set_time;
 	efi.get_wakeup_time = phys_get_wakeup_time;
@@ -1351,3 +1347,12 @@ vmcore_find_descriptor_size (unsigned long address)
 	return ret;
 }
 #endif
+
+char *efi_systab_show_arch(char *str)
+{
+	if (mps_phys != EFI_INVALID_TABLE_ADDR)
+		str += sprintf(str, "MPS=0x%lx\n", mps_phys);
+	if (hcdp_phys != EFI_INVALID_TABLE_ADDR)
+		str += sprintf(str, "HCDP=0x%lx\n", hcdp_phys);
+	return str;
+}