Merge branch 'x86-efi-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 EFI fixes from Peter Anvin:
"This is a collection of fixes for the EFI support. The controversial
bit here is a set of patches which bumps the boot protocol version as
part of fixing some serious problems with the EFI handover protocol,
used when booting under EFI using a bootloader as opposed to directly
from EFI. These changes should also make it a lot saner to support
cross-mode 32/64-bit EFI booting in the future. Getting these changes
into 3.8 means we avoid presenting an inconsistent ABI to bootloaders.

Other changes are display detection and fixing efivarfs."

* 'x86-efi-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86, efi: remove attribute check from setup_efi_pci
x86, build: Dynamically find entry points in compressed startup code
x86, efi: Fix PCI ROM handing in EFI boot stub, in 32-bit mode
x86, efi: Fix 32-bit EFI handover protocol entry point
x86, efi: Fix display detection in EFI boot stub
x86, boot: Define the 2.12 bzImage boot protocol
x86/boot: Fix minor fd leakage in tools/relocs.c
x86, efi: Set runtime_version to the EFI spec revision
x86, efi: fix 32-bit warnings in setup_efi_pci()
efivarfs: Delete dentry from dcache in efivarfs_file_write()
efivarfs: Never return ENOENT from firmware
efi, x86: Pass a proper identity mapping in efi_call_phys_prelog
efivarfs: Drop link count of the right inode

Documentation/x86/boot.txt

···
 Protocol 2.11:	(Kernel 3.6) Added a field for offset of EFI handover
 		protocol entry point.
 
+Protocol 2.12:	(Kernel 3.9) Added the xloadflags field and extension fields
+	 	to struct boot_params for for loading bzImage and ramdisk
+		above 4G in 64bit.
+
 **** MEMORY LAYOUT
 
 The traditional memory map for the kernel loader, used for Image or
···
 0230/4	2.05+	kernel_alignment Physical addr alignment required for kernel
 0234/1	2.05+	relocatable_kernel Whether kernel is relocatable or not
 0235/1	2.10+	min_alignment	Minimum alignment, as a power of two
-0236/2	N/A	pad3		Unused
+0236/2	2.12+	xloadflags	Boot protocol option flags
 0238/4	2.06+	cmdline_size	Maximum size of the kernel command line
 023C/4	2.07+	hardware_subarch Hardware subarchitecture
 0240/8	2.07+	hardware_subarch_data Subarchitecture-specific data
···
   There may be a considerable performance cost with an excessively
   misaligned kernel.  Therefore, a loader should typically try each
   power-of-two alignment from kernel_alignment down to this alignment.
+
+Field name:     xloadflags
+Type:           read
+Offset/size:    0x236/2
+Protocol:       2.12+
+
+  This field is a bitmask.
+
+  Bit 0 (read):	XLF_KERNEL_64
+	- If 1, this kernel has the legacy 64-bit entry point at 0x200.
+
+  Bit 1 (read): XLF_CAN_BE_LOADED_ABOVE_4G
+        - If 1, kernel/boot_params/cmdline/ramdisk can be above 4G.
+
+  Bit 2 (read):	XLF_EFI_HANDOVER_32
+	- If 1, the kernel supports the 32-bit EFI handoff entry point
+          given at handover_offset.
+
+  Bit 3 (read): XLF_EFI_HANDOVER_64
+	- If 1, the kernel supports the 64-bit EFI handoff entry point
+          given at handover_offset + 0x200.
 
 Field name:	cmdline_size
 Type:		read

Documentation/x86/zero-page.txt

···
 090/010	ALL	hd1_info	hd1 disk parameter, OBSOLETE!!
 0A0/010	ALL	sys_desc_table	System description table (struct sys_desc_table)
 0B0/010	ALL	olpc_ofw_header	OLPC's OpenFirmware CIF and friends
+0C0/004	ALL	ext_ramdisk_image ramdisk_image high 32bits
+0C4/004	ALL	ext_ramdisk_size  ramdisk_size high 32bits
+0C8/004	ALL	ext_cmd_line_ptr  cmd_line_ptr high 32bits
 140/080	ALL	edid_info	Video mode setup (struct edid_info)
 1C0/020	ALL	efi_info	EFI 32 information (struct efi_info)
 1E0/004	ALL	alk_mem_k	Alternative mem check, in KB
···
 1E9/001	ALL	eddbuf_entries	Number of entries in eddbuf (below)
 1EA/001	ALL	edd_mbr_sig_buf_entries	Number of entries in edd_mbr_sig_buffer
 				(below)
+1EF/001	ALL	sentinel	Used to detect broken bootloaders
 290/040	ALL	edd_mbr_sig_buffer EDD MBR signatures
 2D0/A00	ALL	e820_map	E820 memory map table
 				(array of struct e820entry)

arch/x86/boot/Makefile

···
 $(obj)/bzImage: asflags-y  := $(SVGA_MODE)
 
 quiet_cmd_image = BUILD   $@
-cmd_image = $(obj)/tools/build $(obj)/setup.bin $(obj)/vmlinux.bin > $@
+cmd_image = $(obj)/tools/build $(obj)/setup.bin $(obj)/vmlinux.bin $(obj)/zoffset.h > $@
 
 $(obj)/bzImage: $(obj)/setup.bin $(obj)/vmlinux.bin $(obj)/tools/build FORCE
 	$(call if_changed,image)
···
 $(obj)/voffset.h: vmlinux FORCE
 	$(call if_changed,voffset)
 
-sed-zoffset := -e 's/^\([0-9a-fA-F]*\) . \(startup_32\|input_data\|_end\|z_.*\)$$/\#define ZO_\2 0x\1/p'
+sed-zoffset := -e 's/^\([0-9a-fA-F]*\) . \(startup_32\|startup_64\|efi_pe_entry\|efi_stub_entry\|input_data\|_end\|z_.*\)$$/\#define ZO_\2 0x\1/p'
 
 quiet_cmd_zoffset = ZOFFSET $@
       cmd_zoffset = $(NM) $< | sed -n $(sed-zoffset) > $@

arch/x86/boot/compressed/eboot.c

···
 	int i;
 	struct setup_data *data;
 
-	data = (struct setup_data *)params->hdr.setup_data;
+	data = (struct setup_data *)(unsigned long)params->hdr.setup_data;
 
 	while (data && data->next)
-		data = (struct setup_data *)data->next;
+		data = (struct setup_data *)(unsigned long)data->next;
 
 	status = efi_call_phys5(sys_table->boottime->locate_handle,
 				EFI_LOCATE_BY_PROTOCOL, &pci_proto,
···
 		if (!pci)
 			continue;
 
+#ifdef CONFIG_X86_64
 		status = efi_call_phys4(pci->attributes, pci,
 					EfiPciIoAttributeOperationGet, 0,
 					&attributes);
-
+#else
+		status = efi_call_phys5(pci->attributes, pci,
+					EfiPciIoAttributeOperationGet, 0, 0,
+					&attributes);
+#endif
 		if (status != EFI_SUCCESS)
-			continue;
-
-		if (!(attributes & EFI_PCI_IO_ATTRIBUTE_EMBEDDED_ROM))
 			continue;
 
 		if (!pci->romimage || !pci->romsize)
···
 		memcpy(rom->romdata, pci->romimage, pci->romsize);
 
 		if (data)
-			data->next = (uint64_t)rom;
+			data->next = (unsigned long)rom;
 		else
-			params->hdr.setup_data = (uint64_t)rom;
+			params->hdr.setup_data = (unsigned long)rom;
 
 		data = (struct setup_data *)rom;
 
···
 			 * Once we've found a GOP supporting ConOut,
 			 * don't bother looking any further.
 			 */
+			first_gop = gop;
 			if (conout_found)
 				break;
-
-			first_gop = gop;
 		}
 	}
 

arch/x86/boot/compressed/head_32.S

···
 #ifdef CONFIG_EFI_STUB
 	jmp	preferred_addr
 
-	.balign	0x10
 	/*
 	 * We don't need the return address, so set up the stack so
-	 * efi_main() can find its arugments.
+	 * efi_main() can find its arguments.
 	 */
+ENTRY(efi_pe_entry)
 	add	$0x4, %esp
 
 	call	make_boot_params
···
 	pushl	%eax
 	pushl	%esi
 	pushl	%ecx
+	sub	$0x4, %esp
 
-	.org 0x30,0x90
+ENTRY(efi_stub_entry)
+	add	$0x4, %esp
 	call	efi_main
 	cmpl	$0, %eax
 	movl	%eax, %esi

arch/x86/boot/compressed/head_64.S

···
 	 */
 #ifdef CONFIG_EFI_STUB
 	/*
-	 * The entry point for the PE/COFF executable is 0x210, so only
-	 * legacy boot loaders will execute this jmp.
+	 * The entry point for the PE/COFF executable is efi_pe_entry, so
+	 * only legacy boot loaders will execute this jmp.
 	 */
 	jmp	preferred_addr
 
-	.org 0x210
+ENTRY(efi_pe_entry)
 	mov	%rcx, %rdi
 	mov	%rdx, %rsi
 	pushq	%rdi
···
 	popq	%rsi
 	popq	%rdi
 
-	.org 0x230,0x90
+ENTRY(efi_stub_entry)
 	call	efi_main
 	movq	%rax,%rsi
 	cmpq	$0,%rax

arch/x86/boot/header.S

···
 #include <asm/e820.h>
 #include <asm/page_types.h>
 #include <asm/setup.h>
+#include <asm/bootparam.h>
 #include "boot.h"
 #include "voffset.h"
 #include "zoffset.h"
···
 	# header, from the old boot sector.
 
 	.section ".header", "a"
+	.globl	sentinel
+sentinel:	.byte 0xff, 0xff        /* Used to detect broken loaders */
+
 	.globl	hdr
 hdr:
 setup_sects:	.byte 0			/* Filled in by build.c */
···
 	# Part 2 of the header, from the old setup.S
 
 		.ascii	"HdrS"		# header signature
-		.word	0x020b		# header version number (>= 0x0105)
+		.word	0x020c		# header version number (>= 0x0105)
 					# or else old loadlin-1.5 will fail)
 		.globl realmode_swtch
 realmode_swtch:	.word	0, 0		# default_switch, SETUPSEG
···
 
 # flags, unused bits must be zero (RFU) bit within loadflags
 loadflags:
-LOADED_HIGH	= 1			# If set, the kernel is loaded high
-CAN_USE_HEAP	= 0x80			# If set, the loader also has set
-					# heap_end_ptr to tell how much
-					# space behind setup.S can be used for
-					# heap purposes.
-					# Only the loader knows what is free
-		.byte	LOADED_HIGH
+		.byte	LOADED_HIGH	# The kernel is to be loaded high
 
 setup_move_size: .word  0x8000		# size to move, when setup is not
 					# loaded at 0x90000. We will move setup
···
 relocatable_kernel:    .byte 0
 #endif
 min_alignment:		.byte MIN_KERNEL_ALIGN_LG2	# minimum alignment
-pad3:			.word 0
+
+xloadflags:
+#ifdef CONFIG_X86_64
+# define XLF0 XLF_KERNEL_64			/* 64-bit kernel */
+#else
+# define XLF0 0
+#endif
+#ifdef CONFIG_EFI_STUB
+# ifdef CONFIG_X86_64
+#  define XLF23 XLF_EFI_HANDOVER_64		/* 64-bit EFI handover ok */
+# else
+#  define XLF23 XLF_EFI_HANDOVER_32		/* 32-bit EFI handover ok */
+# endif
+#else
+# define XLF23 0
+#endif
+			.word XLF0 | XLF23
 
 cmdline_size:   .long   COMMAND_LINE_SIZE-1     #length of the command line,
                                                 #added with boot protocol
···
 #define INIT_SIZE VO_INIT_SIZE
 #endif
 init_size:		.long INIT_SIZE		# kernel initialization size
-handover_offset:	.long 0x30		# offset to the handover
+handover_offset:
+#ifdef CONFIG_EFI_STUB
+  			.long 0x30		# offset to the handover
 						# protocol entry point
+#else
+			.long 0
+#endif
 
 # End of setup header #####################################################
 

arch/x86/boot/setup.ld

···
 	.bstext		: { *(.bstext) }
 	.bsdata		: { *(.bsdata) }
 
-	. = 497;
+	. = 495;
 	.header		: { *(.header) }
 	.entrytext	: { *(.entrytext) }
 	.inittext	: { *(.inittext) }

arch/x86/boot/tools/build.c

···
 
 #define PECOFF_RELOC_RESERVE 0x20
 
+unsigned long efi_stub_entry;
+unsigned long efi_pe_entry;
+unsigned long startup_64;
+
 /*----------------------------------------------------------------------*/
 
 static const u32 crctab32[] = {
···
 
 static void usage(void)
 {
-	die("Usage: build setup system [> image]");
+	die("Usage: build setup system [zoffset.h] [> image]");
 }
 
 #ifdef CONFIG_EFI_STUB
···
 	 */
 	put_unaligned_le32(file_sz - 512, &buf[pe_header + 0x1c]);
 
-#ifdef CONFIG_X86_32
 	/*
-	 * Address of entry point.
-	 *
-	 * The EFI stub entry point is +16 bytes from the start of
-	 * the .text section.
+	 * Address of entry point for PE/COFF executable
 	 */
-	put_unaligned_le32(text_start + 16, &buf[pe_header + 0x28]);
-#else
-	/*
-	 * Address of entry point. startup_32 is at the beginning and
-	 * the 64-bit entry point (startup_64) is always 512 bytes
-	 * after. The EFI stub entry point is 16 bytes after that, as
-	 * the first instruction allows legacy loaders to jump over
-	 * the EFI stub initialisation
-	 */
-	put_unaligned_le32(text_start + 528, &buf[pe_header + 0x28]);
-#endif /* CONFIG_X86_32 */
+	put_unaligned_le32(text_start + efi_pe_entry, &buf[pe_header + 0x28]);
 
 	update_pecoff_section_header(".text", text_start, text_sz);
 }
 
 #endif /* CONFIG_EFI_STUB */
+
+
+/*
+ * Parse zoffset.h and find the entry points. We could just #include zoffset.h
+ * but that would mean tools/build would have to be rebuilt every time. It's
+ * not as if parsing it is hard...
+ */
+#define PARSE_ZOFS(p, sym) do { \
+	if (!strncmp(p, "#define ZO_" #sym " ", 11+sizeof(#sym)))	\
+		sym = strtoul(p + 11 + sizeof(#sym), NULL, 16);		\
+} while (0)
+
+static void parse_zoffset(char *fname)
+{
+	FILE *file;
+	char *p;
+	int c;
+
+	file = fopen(fname, "r");
+	if (!file)
+		die("Unable to open `%s': %m", fname);
+	c = fread(buf, 1, sizeof(buf) - 1, file);
+	if (ferror(file))
+		die("read-error on `zoffset.h'");
+	buf[c] = 0;
+
+	p = (char *)buf;
+
+	while (p && *p) {
+		PARSE_ZOFS(p, efi_stub_entry);
+		PARSE_ZOFS(p, efi_pe_entry);
+		PARSE_ZOFS(p, startup_64);
+
+		p = strchr(p, '\n');
+		while (p && (*p == '\r' || *p == '\n'))
+			p++;
+	}
+}
 
 int main(int argc, char ** argv)
 {
···
 	void *kernel;
 	u32 crc = 0xffffffffUL;
 
-	if (argc != 3)
+	/* Defaults for old kernel */
+#ifdef CONFIG_X86_32
+	efi_pe_entry = 0x10;
+	efi_stub_entry = 0x30;
+#else
+	efi_pe_entry = 0x210;
+	efi_stub_entry = 0x230;
+	startup_64 = 0x200;
+#endif
+
+	if (argc == 4)
+		parse_zoffset(argv[3]);
+	else if (argc != 3)
 		usage();
 
 	/* Copy the setup code */
···
 
 #ifdef CONFIG_EFI_STUB
 	update_pecoff_text(setup_sectors * 512, sz + i + ((sys_size * 16) - sz));
+
+#ifdef CONFIG_X86_64 /* Yes, this is really how we defined it :( */
+	efi_stub_entry -= 0x200;
+#endif
+	put_unaligned_le32(efi_stub_entry, &buf[0x264]);
 #endif
 
 	crc = partial_crc32(buf, i, crc);

arch/x86/include/uapi/asm/bootparam.h

···
 #ifndef _ASM_X86_BOOTPARAM_H
 #define _ASM_X86_BOOTPARAM_H
 
+/* setup_data types */
+#define SETUP_NONE			0
+#define SETUP_E820_EXT			1
+#define SETUP_DTB			2
+#define SETUP_PCI			3
+
+/* ram_size flags */
+#define RAMDISK_IMAGE_START_MASK	0x07FF
+#define RAMDISK_PROMPT_FLAG		0x8000
+#define RAMDISK_LOAD_FLAG		0x4000
+
+/* loadflags */
+#define LOADED_HIGH	(1<<0)
+#define QUIET_FLAG	(1<<5)
+#define KEEP_SEGMENTS	(1<<6)
+#define CAN_USE_HEAP	(1<<7)
+
+/* xloadflags */
+#define XLF_KERNEL_64			(1<<0)
+#define XLF_CAN_BE_LOADED_ABOVE_4G	(1<<1)
+#define XLF_EFI_HANDOVER_32		(1<<2)
+#define XLF_EFI_HANDOVER_64		(1<<3)
+
+#ifndef __ASSEMBLY__
+
 #include <linux/types.h>
 #include <linux/screen_info.h>
 #include <linux/apm_bios.h>
···
 #include <asm/e820.h>
 #include <asm/ist.h>
 #include <video/edid.h>
-
-/* setup data types */
-#define SETUP_NONE			0
-#define SETUP_E820_EXT			1
-#define SETUP_DTB			2
-#define SETUP_PCI			3
 
 /* extensible setup data list node */
 struct setup_data {
···
 	__u16	root_flags;
 	__u32	syssize;
 	__u16	ram_size;
-#define RAMDISK_IMAGE_START_MASK	0x07FF
-#define RAMDISK_PROMPT_FLAG		0x8000
-#define RAMDISK_LOAD_FLAG		0x4000
 	__u16	vid_mode;
 	__u16	root_dev;
 	__u16	boot_flag;
···
 	__u16	kernel_version;
 	__u8	type_of_loader;
 	__u8	loadflags;
-#define LOADED_HIGH	(1<<0)
-#define QUIET_FLAG	(1<<5)
-#define KEEP_SEGMENTS	(1<<6)
-#define CAN_USE_HEAP	(1<<7)
 	__u16	setup_move_size;
 	__u32	code32_start;
 	__u32	ramdisk_image;
···
 	__u32	initrd_addr_max;
 	__u32	kernel_alignment;
 	__u8	relocatable_kernel;
-	__u8	_pad2[3];
+	__u8	min_alignment;
+	__u16	xloadflags;
 	__u32	cmdline_size;
 	__u32	hardware_subarch;
 	__u64	hardware_subarch_data;
···
 	__u8  hd1_info[16];	/* obsolete! */		/* 0x090 */
 	struct sys_desc_table sys_desc_table;		/* 0x0a0 */
 	struct olpc_ofw_header olpc_ofw_header;		/* 0x0b0 */
-	__u8  _pad4[128];				/* 0x0c0 */
+	__u32 ext_ramdisk_image;			/* 0x0c0 */
+	__u32 ext_ramdisk_size;				/* 0x0c4 */
+	__u32 ext_cmd_line_ptr;				/* 0x0c8 */
+	__u8  _pad4[116];				/* 0x0cc */
 	struct edid_info edid_info;			/* 0x140 */
 	struct efi_info efi_info;			/* 0x1c0 */
 	__u32 alt_mem_k;				/* 0x1e0 */
···
 	__u8  eddbuf_entries;				/* 0x1e9 */
 	__u8  edd_mbr_sig_buf_entries;			/* 0x1ea */
 	__u8  kbd_status;				/* 0x1eb */
-	__u8  _pad6[5];					/* 0x1ec */
+	__u8  _pad5[3];					/* 0x1ec */
+	/*
+	 * The sentinel is set to a nonzero value (0xff) in header.S.
+	 *
+	 * A bootloader is supposed to only take setup_header and put
+	 * it into a clean boot_params buffer. If it turns out that
+	 * it is clumsy or too generous with the buffer, it most
+	 * probably will pick up the sentinel variable too. The fact
+	 * that this variable then is still 0xff will let kernel
+	 * know that some variables in boot_params are invalid and
+	 * kernel should zero out certain portions of boot_params.
+	 */
+	__u8  sentinel;					/* 0x1ef */
+	__u8  _pad6[1];					/* 0x1f0 */
 	struct setup_header hdr;    /* setup header */	/* 0x1f1 */
 	__u8  _pad7[0x290-0x1f1-sizeof(struct setup_header)];
 	__u32 edd_mbr_sig_buffer[EDD_MBR_SIG_MAX];	/* 0x290 */
···
 	X86_NR_SUBARCHS,
 };
 
-
+#endif /* __ASSEMBLY__ */
 
 #endif /* _ASM_X86_BOOTPARAM_H */

arch/x86/platform/efi/efi.c

···
 	 *
 	 * Call EFI services through wrapper functions.
 	 */
-	efi.runtime_version = efi_systab.fw_revision;
+	efi.runtime_version = efi_systab.hdr.revision;
 	efi.get_time = virt_efi_get_time;
 	efi.set_time = virt_efi_set_time;
 	efi.get_wakeup_time = virt_efi_get_wakeup_time;

arch/x86/platform/efi/efi_64.c

···
 #include <asm/cacheflush.h>
 #include <asm/fixmap.h>
 
-static pgd_t save_pgd __initdata;
+static pgd_t *save_pgd __initdata;
 static unsigned long efi_flags __initdata;
 
 static void __init early_code_mapping_set_exec(int executable)
···
 void __init efi_call_phys_prelog(void)
 {
 	unsigned long vaddress;
+	int pgd;
+	int n_pgds;
 
 	early_code_mapping_set_exec(1);
 	local_irq_save(efi_flags);
-	vaddress = (unsigned long)__va(0x0UL);
-	save_pgd = *pgd_offset_k(0x0UL);
-	set_pgd(pgd_offset_k(0x0UL), *pgd_offset_k(vaddress));
+
+	n_pgds = DIV_ROUND_UP((max_pfn << PAGE_SHIFT), PGDIR_SIZE);
+	save_pgd = kmalloc(n_pgds * sizeof(pgd_t), GFP_KERNEL);
+
+	for (pgd = 0; pgd < n_pgds; pgd++) {
+		save_pgd[pgd] = *pgd_offset_k(pgd * PGDIR_SIZE);
+		vaddress = (unsigned long)__va(pgd * PGDIR_SIZE);
+		set_pgd(pgd_offset_k(pgd * PGDIR_SIZE), *pgd_offset_k(vaddress));
+	}
 	__flush_tlb_all();
 }
 
···
 	/*
 	 * After the lock is released, the original page table is restored.
 	 */
-	set_pgd(pgd_offset_k(0x0UL), save_pgd);
+	int pgd;
+	int n_pgds = DIV_ROUND_UP((max_pfn << PAGE_SHIFT) , PGDIR_SIZE);
+	for (pgd = 0; pgd < n_pgds; pgd++)
+		set_pgd(pgd_offset_k(pgd * PGDIR_SIZE), save_pgd[pgd]);
+	kfree(save_pgd);
 	__flush_tlb_all();
 	local_irq_restore(efi_flags);
 	early_code_mapping_set_exec(0);

arch/x86/tools/relocs.c

···
 	read_relocs(fp);
 	if (show_absolute_syms) {
 		print_absolute_symbols();
-		return 0;
+		goto out;
 	}
 	if (show_absolute_relocs) {
 		print_absolute_relocs();
-		return 0;
+		goto out;
 	}
 	emit_relocs(as_text, use_real_mode);
+out:
+	fclose(fp);
 	return 0;
 }

drivers/firmware/efivars.c

···
 		err = -EACCES;
 		break;
 	case EFI_NOT_FOUND:
-		err = -ENOENT;
+		err = -EIO;
 		break;
 	default:
 		err = -EINVAL;
···
 		spin_unlock(&efivars->lock);
 		efivar_unregister(var);
 		drop_nlink(inode);
+		d_delete(file->f_dentry);
 		dput(file->f_dentry);
 
 	} else {
···
 		list_del(&var->list);
 		spin_unlock(&efivars->lock);
 		efivar_unregister(var);
-		drop_nlink(dir);
+		drop_nlink(dentry->d_inode);
 		dput(dentry);
 		return 0;
 	}