From 5f51c5d0e905608ba7be126737f7c84a793ae1aa Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Tue, 12 Sep 2023 09:00:52 +0000 Subject: [PATCH 01/23] x86/efi: Drop EFI stub .bss from .data section Now that the EFI stub always zero inits its BSS section upon entry, there is no longer a need to place the BSS symbols carried by the stub into the .data section. Signed-off-by: Ard Biesheuvel Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20230912090051.4014114-18-ardb@google.com --- arch/x86/boot/compressed/vmlinux.lds.S | 1 - drivers/firmware/efi/libstub/Makefile | 7 ------- 2 files changed, 8 deletions(-) diff --git a/arch/x86/boot/compressed/vmlinux.lds.S b/arch/x86/boot/compressed/vmlinux.lds.S index b22f34b8684a..4ff6ab1b67d9 100644 --- a/arch/x86/boot/compressed/vmlinux.lds.S +++ b/arch/x86/boot/compressed/vmlinux.lds.S @@ -47,7 +47,6 @@ SECTIONS _data = . ; *(.data) *(.data.*) - *(.bss.efistub) _edata = . ; } . = ALIGN(L1_CACHE_BYTES); diff --git a/drivers/firmware/efi/libstub/Makefile b/drivers/firmware/efi/libstub/Makefile index a1157c2a7170..ef4c12f0877b 100644 --- a/drivers/firmware/efi/libstub/Makefile +++ b/drivers/firmware/efi/libstub/Makefile @@ -108,13 +108,6 @@ lib-y := $(patsubst %.o,%.stub.o,$(lib-y)) # https://bugs.llvm.org/show_bug.cgi?id=46480 STUBCOPY_FLAGS-y += --remove-section=.note.gnu.property -# -# For x86, bootloaders like systemd-boot or grub-efi do not zero-initialize the -# .bss section, so the .bss section of the EFI stub needs to be included in the -# .data section of the compressed kernel to ensure initialization. Rename the -# .bss section here so it's easy to pick out in the linker script. -# -STUBCOPY_FLAGS-$(CONFIG_X86) += --rename-section .bss=.bss.efistub,load,alloc STUBCOPY_RELOC-$(CONFIG_X86_32) := R_386_32 STUBCOPY_RELOC-$(CONFIG_X86_64) := R_X86_64_64 From 7e50262229faad0c7b8c54477cd1c883f31cc4a7 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Tue, 12 Sep 2023 09:00:53 +0000 Subject: [PATCH 02/23] x86/efi: Disregard setup header of loaded image The native EFI entrypoint does not take a struct boot_params from the loader, but instead, it constructs one from scratch, using the setup header data placed at the start of the image. This setup header is placed in a way that permits legacy loaders to manipulate the contents (i.e., to pass the kernel command line or the address and size of an initial ramdisk), but EFI boot does not use it in that way - it only copies the contents that were placed there at build time, but EFI loaders will not (and should not) manipulate the setup header to configure the boot. (Commit 63bf28ceb3ebbe76 "efi: x86: Wipe setup_data on pure EFI boot" deals with some of the fallout of using setup_data in a way that breaks EFI boot.) Given that none of the non-zero values that are copied from the setup header into the EFI stub's struct boot_params are relevant to the boot now that the EFI stub no longer enters via the legacy decompressor, the copy can be omitted altogether. Signed-off-by: Ard Biesheuvel Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20230912090051.4014114-19-ardb@google.com --- drivers/firmware/efi/libstub/x86-stub.c | 46 ++++--------------------- 1 file changed, 6 insertions(+), 40 deletions(-) diff --git a/drivers/firmware/efi/libstub/x86-stub.c b/drivers/firmware/efi/libstub/x86-stub.c index 2fee52ed335d..3bfc59637dd1 100644 --- a/drivers/firmware/efi/libstub/x86-stub.c +++ b/drivers/firmware/efi/libstub/x86-stub.c @@ -449,9 +449,8 @@ void __noreturn efi_stub_entry(efi_handle_t handle, efi_status_t __efiapi efi_pe_entry(efi_handle_t handle, efi_system_table_t *sys_table_arg) { - struct boot_params *boot_params; - struct setup_header *hdr; - void *image_base; + static struct boot_params boot_params __page_aligned_bss; + struct setup_header *hdr = &boot_params.hdr; efi_guid_t proto = LOADED_IMAGE_PROTOCOL_GUID; int options_size = 0; efi_status_t status; @@ -469,30 +468,9 @@ efi_status_t __efiapi efi_pe_entry(efi_handle_t handle, efi_exit(handle, status); } - image_base = efi_table_attr(image, image_base); - - status = efi_allocate_pages(sizeof(struct boot_params), - (unsigned long *)&boot_params, ULONG_MAX); - if (status != EFI_SUCCESS) { - efi_err("Failed to allocate lowmem for boot params\n"); - efi_exit(handle, status); - } - - memset(boot_params, 0x0, sizeof(struct boot_params)); - - hdr = &boot_params->hdr; - - /* Copy the setup header from the second sector to boot_params */ - memcpy(&hdr->jump, image_base + 512, - sizeof(struct setup_header) - offsetof(struct setup_header, jump)); - - /* - * Fill out some of the header fields ourselves because the - * EFI firmware loader doesn't load the first sector. - */ + /* Assign the setup_header fields that the kernel actually cares about */ hdr->root_flags = 1; hdr->vid_mode = 0xffff; - hdr->boot_flag = 0xAA55; hdr->type_of_loader = 0x21; @@ -501,25 +479,13 @@ efi_status_t __efiapi efi_pe_entry(efi_handle_t handle, if (!cmdline_ptr) goto fail; - efi_set_u64_split((unsigned long)cmdline_ptr, - &hdr->cmd_line_ptr, &boot_params->ext_cmd_line_ptr); + efi_set_u64_split((unsigned long)cmdline_ptr, &hdr->cmd_line_ptr, + &boot_params.ext_cmd_line_ptr); - hdr->ramdisk_image = 0; - hdr->ramdisk_size = 0; - - /* - * Disregard any setup data that was provided by the bootloader: - * setup_data could be pointing anywhere, and we have no way of - * authenticating or validating the payload. - */ - hdr->setup_data = 0; - - efi_stub_entry(handle, sys_table_arg, boot_params); + efi_stub_entry(handle, sys_table_arg, &boot_params); /* not reached */ fail: - efi_free(sizeof(struct boot_params), (unsigned long)boot_params); - efi_exit(handle, status); } From bfab35f552ab3dd6d017165bf9de1d1d20f198cc Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Tue, 12 Sep 2023 09:00:54 +0000 Subject: [PATCH 03/23] x86/efi: Drop alignment flags from PE section headers The section header flags for alignment are documented in the PE/COFF spec as being applicable to PE object files only, not to PE executables such as the Linux bzImage, so let's drop them from the PE header. Signed-off-by: Ard Biesheuvel Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20230912090051.4014114-20-ardb@google.com --- arch/x86/boot/header.S | 12 ++++-------- 1 file changed, 4 insertions(+), 8 deletions(-) diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S index b04ca8e2b213..8c8148d751c6 100644 --- a/arch/x86/boot/header.S +++ b/arch/x86/boot/header.S @@ -209,8 +209,7 @@ section_table: .word 0 # NumberOfLineNumbers .long IMAGE_SCN_CNT_CODE | \ IMAGE_SCN_MEM_READ | \ - IMAGE_SCN_MEM_EXECUTE | \ - IMAGE_SCN_ALIGN_16BYTES # Characteristics + IMAGE_SCN_MEM_EXECUTE # Characteristics # # The EFI application loader requires a relocation section @@ -230,8 +229,7 @@ section_table: .word 0 # NumberOfLineNumbers .long IMAGE_SCN_CNT_INITIALIZED_DATA | \ IMAGE_SCN_MEM_READ | \ - IMAGE_SCN_MEM_DISCARDABLE | \ - IMAGE_SCN_ALIGN_1BYTES # Characteristics + IMAGE_SCN_MEM_DISCARDABLE # Characteristics #ifdef CONFIG_EFI_MIXED # @@ -249,8 +247,7 @@ section_table: .word 0 # NumberOfLineNumbers .long IMAGE_SCN_CNT_INITIALIZED_DATA | \ IMAGE_SCN_MEM_READ | \ - IMAGE_SCN_MEM_DISCARDABLE | \ - IMAGE_SCN_ALIGN_1BYTES # Characteristics + IMAGE_SCN_MEM_DISCARDABLE # Characteristics #endif # @@ -271,8 +268,7 @@ section_table: .word 0 # NumberOfLineNumbers .long IMAGE_SCN_CNT_CODE | \ IMAGE_SCN_MEM_READ | \ - IMAGE_SCN_MEM_EXECUTE | \ - IMAGE_SCN_ALIGN_16BYTES # Characteristics + IMAGE_SCN_MEM_EXECUTE # Characteristics .set section_count, (. - section_table) / 40 #endif /* CONFIG_EFI_STUB */ From 768171d7ebbce005210e1cf8456f043304805c15 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Tue, 12 Sep 2023 09:00:55 +0000 Subject: [PATCH 04/23] x86/boot: Remove the 'bugger off' message Ancient (pre-2003) x86 kernels could boot from a floppy disk straight from the BIOS, using a small real mode boot stub at the start of the image where the BIOS would expect the boot record (or boot block) to appear. Due to its limitations (kernel size < 1 MiB, no support for IDE, USB or El Torito floppy emulation), this support was dropped, and a Linux aware bootloader is now always required to boot the kernel from a legacy BIOS. To smoothen this transition, the boot stub was not removed entirely, but replaced with one that just prints an error message telling the user to install a bootloader. As it is unlikely that anyone doing direct floppy boot with such an ancient kernel is going to upgrade to v6.5+ and expect that this boot method still works, printing this message is kind of pointless, and so it should be possible to remove the logic that emits it. Let's free up this space so it can be used to expand the PE header in a subsequent patch. Signed-off-by: Ard Biesheuvel Signed-off-by: Ingo Molnar Acked-by: H. Peter Anvin (Intel) Link: https://lore.kernel.org/r/20230912090051.4014114-21-ardb@google.com --- arch/x86/boot/header.S | 49 ------------------------------------------ arch/x86/boot/setup.ld | 7 +++--- 2 files changed, 4 insertions(+), 52 deletions(-) diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S index 8c8148d751c6..b24fa50a9898 100644 --- a/arch/x86/boot/header.S +++ b/arch/x86/boot/header.S @@ -38,64 +38,15 @@ SYSSEG = 0x1000 /* historical load address >> 4 */ .code16 .section ".bstext", "ax" - - .global bootsect_start -bootsect_start: #ifdef CONFIG_EFI_STUB # "MZ", MS-DOS header .word MZ_MAGIC -#endif - - # Normalize the start address - ljmp $BOOTSEG, $start2 - -start2: - movw %cs, %ax - movw %ax, %ds - movw %ax, %es - movw %ax, %ss - xorw %sp, %sp - sti - cld - - movw $bugger_off_msg, %si - -msg_loop: - lodsb - andb %al, %al - jz bs_die - movb $0xe, %ah - movw $7, %bx - int $0x10 - jmp msg_loop - -bs_die: - # Allow the user to press a key, then reboot - xorw %ax, %ax - int $0x16 - int $0x19 - - # int 0x19 should never return. In case it does anyway, - # invoke the BIOS reset code... - ljmp $0xf000,$0xfff0 - -#ifdef CONFIG_EFI_STUB .org 0x38 # # Offset to the PE header. # .long LINUX_PE_MAGIC .long pe_header -#endif /* CONFIG_EFI_STUB */ - - .section ".bsdata", "a" -bugger_off_msg: - .ascii "Use a boot loader.\r\n" - .ascii "\n" - .ascii "Remove disk and press any key to reboot...\r\n" - .byte 0 - -#ifdef CONFIG_EFI_STUB pe_header: .long PE_MAGIC diff --git a/arch/x86/boot/setup.ld b/arch/x86/boot/setup.ld index 49546c247ae2..b11c45b9e51e 100644 --- a/arch/x86/boot/setup.ld +++ b/arch/x86/boot/setup.ld @@ -10,10 +10,11 @@ ENTRY(_start) SECTIONS { . = 0; - .bstext : { *(.bstext) } - .bsdata : { *(.bsdata) } + .bstext : { + *(.bstext) + . = 495; + } =0xffffffff - . = 495; .header : { *(.header) } .entrytext : { *(.entrytext) } .inittext : { *(.inittext) } From 8eace5b3555606e684739bef5bcdfcfe68235257 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Tue, 12 Sep 2023 09:00:56 +0000 Subject: [PATCH 05/23] x86/boot: Omit compression buffer from PE/COFF image memory footprint Now that the EFI stub decompresses the kernel and hands over to the decompressed image directly, there is no longer a need to provide a decompression buffer as part of the .BSS allocation of the PE/COFF image. It also means the PE/COFF image can be loaded anywhere in memory, and setting the preferred image base is unnecessary. So drop the handling of this from the header and from the build tool. Signed-off-by: Ard Biesheuvel Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20230912090051.4014114-22-ardb@google.com --- arch/x86/boot/header.S | 6 ++--- arch/x86/boot/tools/build.c | 50 +++++-------------------------------- 2 files changed, 8 insertions(+), 48 deletions(-) diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S index b24fa50a9898..a87d9133384b 100644 --- a/arch/x86/boot/header.S +++ b/arch/x86/boot/header.S @@ -90,12 +90,10 @@ optional_header: #endif extra_header_fields: - # PE specification requires ImageBase to be 64k aligned - .set image_base, (LOAD_PHYSICAL_ADDR + 0xffff) & ~0xffff #ifdef CONFIG_X86_32 - .long image_base # ImageBase + .long 0 # ImageBase #else - .quad image_base # ImageBase + .quad 0 # ImageBase #endif .long 0x20 # SectionAlignment .long 0x20 # FileAlignment diff --git a/arch/x86/boot/tools/build.c b/arch/x86/boot/tools/build.c index bd247692b701..0354c223e354 100644 --- a/arch/x86/boot/tools/build.c +++ b/arch/x86/boot/tools/build.c @@ -65,7 +65,6 @@ static unsigned long efi_pe_entry; static unsigned long efi32_pe_entry; static unsigned long kernel_info; static unsigned long startup_64; -static unsigned long _ehead; static unsigned long _end; /*----------------------------------------------------------------------*/ @@ -229,27 +228,14 @@ static void update_pecoff_setup_and_reloc(unsigned int size) #endif } -static void update_pecoff_text(unsigned int text_start, unsigned int file_sz, - unsigned int init_sz) +static void update_pecoff_text(unsigned int text_start, unsigned int file_sz) { unsigned int pe_header; unsigned int text_sz = file_sz - text_start; - unsigned int bss_sz = init_sz - file_sz; + unsigned int bss_sz = _end - text_sz; pe_header = get_unaligned_le32(&buf[0x3c]); - /* - * The PE/COFF loader may load the image at an address which is - * misaligned with respect to the kernel_alignment field in the setup - * header. - * - * In order to avoid relocating the kernel to correct the misalignment, - * add slack to allow the buffer to be aligned within the declared size - * of the image. - */ - bss_sz += CONFIG_PHYSICAL_ALIGN; - init_sz += CONFIG_PHYSICAL_ALIGN; - /* * Size of code: Subtract the size of the first sector (512 bytes) * which includes the header. @@ -257,7 +243,7 @@ static void update_pecoff_text(unsigned int text_start, unsigned int file_sz, put_unaligned_le32(file_sz - 512 + bss_sz, &buf[pe_header + 0x1c]); /* Size of image */ - put_unaligned_le32(init_sz, &buf[pe_header + 0x50]); + put_unaligned_le32(file_sz + bss_sz, &buf[pe_header + 0x50]); /* * Address of entry point for PE/COFF executable @@ -308,8 +294,7 @@ static void efi_stub_entry_update(void) static inline void update_pecoff_setup_and_reloc(unsigned int size) {} static inline void update_pecoff_text(unsigned int text_start, - unsigned int file_sz, - unsigned int init_sz) {} + unsigned int file_sz) {} static inline void efi_stub_defaults(void) {} static inline void efi_stub_entry_update(void) {} @@ -360,7 +345,6 @@ static void parse_zoffset(char *fname) PARSE_ZOFS(p, efi32_pe_entry); PARSE_ZOFS(p, kernel_info); PARSE_ZOFS(p, startup_64); - PARSE_ZOFS(p, _ehead); PARSE_ZOFS(p, _end); p = strchr(p, '\n'); @@ -371,7 +355,7 @@ static void parse_zoffset(char *fname) int main(int argc, char ** argv) { - unsigned int i, sz, setup_sectors, init_sz; + unsigned int i, sz, setup_sectors; int c; u32 sys_size; struct stat sb; @@ -442,31 +426,9 @@ int main(int argc, char ** argv) buf[0x1f1] = setup_sectors-1; put_unaligned_le32(sys_size, &buf[0x1f4]); - init_sz = get_unaligned_le32(&buf[0x260]); -#ifdef CONFIG_EFI_STUB - /* - * The decompression buffer will start at ImageBase. When relocating - * the compressed kernel to its end, we must ensure that the head - * section does not get overwritten. The head section occupies - * [i, i + _ehead), and the destination is [init_sz - _end, init_sz). - * - * At present these should never overlap, because 'i' is at most 32k - * because of SETUP_SECT_MAX, '_ehead' is less than 1k, and the - * calculation of INIT_SIZE in boot/header.S ensures that - * 'init_sz - _end' is at least 64k. - * - * For future-proofing, increase init_sz if necessary. - */ - - if (init_sz - _end < i + _ehead) { - init_sz = (i + _ehead + _end + 4095) & ~4095; - put_unaligned_le32(init_sz, &buf[0x260]); - } -#endif - update_pecoff_text(setup_sectors * 512, i + (sys_size * 16), init_sz); + update_pecoff_text(setup_sectors * 512, i + (sys_size * 16)); efi_stub_entry_update(); - /* Update kernel_info offset. */ put_unaligned_le32(kernel_info, &buf[0x268]); From 7448e8e5d15a3c4df649bf6d6d460f78396f7e1e Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Tue, 12 Sep 2023 09:00:57 +0000 Subject: [PATCH 06/23] x86/boot: Drop redundant code setting the root device The root device defaults to 0,0 and is no longer configurable at build time [0], so there is no need for the build tool to ever write to this field. [0] 079f85e624189292 ("x86, build: Do not set the root_dev field in bzImage") This change has no impact on the resulting bzImage binary. Signed-off-by: Ard Biesheuvel Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20230912090051.4014114-23-ardb@google.com --- arch/x86/boot/header.S | 2 +- arch/x86/boot/tools/build.c | 7 ------- 2 files changed, 1 insertion(+), 8 deletions(-) diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S index a87d9133384b..6059f87b159d 100644 --- a/arch/x86/boot/header.S +++ b/arch/x86/boot/header.S @@ -236,7 +236,7 @@ root_flags: .word ROOT_RDONLY syssize: .long 0 /* Filled in by build.c */ ram_size: .word 0 /* Obsolete */ vid_mode: .word SVGA_MODE -root_dev: .word 0 /* Filled in by build.c */ +root_dev: .word 0 /* Default to major/minor 0/0 */ boot_flag: .word 0xAA55 # offset 512, entry point diff --git a/arch/x86/boot/tools/build.c b/arch/x86/boot/tools/build.c index 0354c223e354..efa4e9c7d713 100644 --- a/arch/x86/boot/tools/build.c +++ b/arch/x86/boot/tools/build.c @@ -40,10 +40,6 @@ typedef unsigned char u8; typedef unsigned short u16; typedef unsigned int u32; -#define DEFAULT_MAJOR_ROOT 0 -#define DEFAULT_MINOR_ROOT 0 -#define DEFAULT_ROOT_DEV (DEFAULT_MAJOR_ROOT << 8 | DEFAULT_MINOR_ROOT) - /* Minimal number of setup sectors */ #define SETUP_SECT_MIN 5 #define SETUP_SECT_MAX 64 @@ -399,9 +395,6 @@ int main(int argc, char ** argv) update_pecoff_setup_and_reloc(i); - /* Set the default root device */ - put_unaligned_le16(DEFAULT_ROOT_DEV, &buf[508]); - /* Open and stat the kernel file */ fd = open(argv[2], O_RDONLY); if (fd < 0) From b618d31f112bea3d2daea19190d63e567f32a4db Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Tue, 12 Sep 2023 09:00:59 +0000 Subject: [PATCH 07/23] x86/boot: Drop references to startup_64 The x86 boot image generation tool assign a default value to startup_64 and subsequently parses the actual value from zoffset.h but it never actually uses the value anywhere. So remove this code. This change has no impact on the resulting bzImage binary. Signed-off-by: Ard Biesheuvel Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20230912090051.4014114-25-ardb@google.com --- arch/x86/boot/Makefile | 2 +- arch/x86/boot/tools/build.c | 3 --- 2 files changed, 1 insertion(+), 4 deletions(-) diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile index f33e45ed1437..0e98bc503699 100644 --- a/arch/x86/boot/Makefile +++ b/arch/x86/boot/Makefile @@ -89,7 +89,7 @@ $(obj)/vmlinux.bin: $(obj)/compressed/vmlinux FORCE SETUP_OBJS = $(addprefix $(obj)/,$(setup-y)) -sed-zoffset := -e 's/^\([0-9a-fA-F]*\) [a-zA-Z] \(startup_32\|startup_64\|efi32_stub_entry\|efi64_stub_entry\|efi_pe_entry\|efi32_pe_entry\|input_data\|kernel_info\|_end\|_ehead\|_text\|z_.*\)$$/\#define ZO_\2 0x\1/p' +sed-zoffset := -e 's/^\([0-9a-fA-F]*\) [a-zA-Z] \(startup_32\|efi32_stub_entry\|efi64_stub_entry\|efi_pe_entry\|efi32_pe_entry\|input_data\|kernel_info\|_end\|_ehead\|_text\|z_.*\)$$/\#define ZO_\2 0x\1/p' quiet_cmd_zoffset = ZOFFSET $@ cmd_zoffset = $(NM) $< | sed -n $(sed-zoffset) > $@ diff --git a/arch/x86/boot/tools/build.c b/arch/x86/boot/tools/build.c index efa4e9c7d713..10b0207a6b18 100644 --- a/arch/x86/boot/tools/build.c +++ b/arch/x86/boot/tools/build.c @@ -60,7 +60,6 @@ static unsigned long efi64_stub_entry; static unsigned long efi_pe_entry; static unsigned long efi32_pe_entry; static unsigned long kernel_info; -static unsigned long startup_64; static unsigned long _end; /*----------------------------------------------------------------------*/ @@ -264,7 +263,6 @@ static void efi_stub_defaults(void) efi_pe_entry = 0x10; #else efi_pe_entry = 0x210; - startup_64 = 0x200; #endif } @@ -340,7 +338,6 @@ static void parse_zoffset(char *fname) PARSE_ZOFS(p, efi_pe_entry); PARSE_ZOFS(p, efi32_pe_entry); PARSE_ZOFS(p, kernel_info); - PARSE_ZOFS(p, startup_64); PARSE_ZOFS(p, _end); p = strchr(p, '\n'); From 2e765c02dcbfc2a8a4527c621a84b9502f6b9bd2 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Fri, 15 Sep 2023 17:16:25 +0000 Subject: [PATCH 08/23] x86/boot: Grab kernel_info offset from zoffset header directly Instead of parsing zoffset.h and poking the kernel_info offset value into the header from the build tool, just grab the value directly in the asm file that describes this header. This change has no impact on the resulting bzImage binary. Signed-off-by: Ard Biesheuvel Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20230915171623.655440-11-ardb@google.com --- arch/x86/boot/header.S | 2 +- arch/x86/boot/tools/build.c | 4 ---- 2 files changed, 1 insertion(+), 5 deletions(-) diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S index 6059f87b159d..5575d0f06bab 100644 --- a/arch/x86/boot/header.S +++ b/arch/x86/boot/header.S @@ -526,7 +526,7 @@ pref_address: .quad LOAD_PHYSICAL_ADDR # preferred load addr init_size: .long INIT_SIZE # kernel initialization size handover_offset: .long 0 # Filled in by build.c -kernel_info_offset: .long 0 # Filled in by build.c +kernel_info_offset: .long ZO_kernel_info # End of setup header ##################################################### diff --git a/arch/x86/boot/tools/build.c b/arch/x86/boot/tools/build.c index 10b0207a6b18..14ef13fe7ab0 100644 --- a/arch/x86/boot/tools/build.c +++ b/arch/x86/boot/tools/build.c @@ -59,7 +59,6 @@ static unsigned long efi32_stub_entry; static unsigned long efi64_stub_entry; static unsigned long efi_pe_entry; static unsigned long efi32_pe_entry; -static unsigned long kernel_info; static unsigned long _end; /*----------------------------------------------------------------------*/ @@ -337,7 +336,6 @@ static void parse_zoffset(char *fname) PARSE_ZOFS(p, efi64_stub_entry); PARSE_ZOFS(p, efi_pe_entry); PARSE_ZOFS(p, efi32_pe_entry); - PARSE_ZOFS(p, kernel_info); PARSE_ZOFS(p, _end); p = strchr(p, '\n'); @@ -419,8 +417,6 @@ int main(int argc, char ** argv) update_pecoff_text(setup_sectors * 512, i + (sys_size * 16)); efi_stub_entry_update(); - /* Update kernel_info offset. */ - put_unaligned_le32(kernel_info, &buf[0x268]); crc = partial_crc32(buf, i, crc); if (fwrite(buf, 1, i, dest) != i) From eac956345f99dda3d68f4ae6cf7b494105e54780 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Fri, 15 Sep 2023 17:16:26 +0000 Subject: [PATCH 09/23] x86/boot: Set EFI handover offset directly in header asm The offsets of the EFI handover entrypoints are available to the assembler when constructing the header, so there is no need to set them from the build tool afterwards. This change has no impact on the resulting bzImage binary. Signed-off-by: Ard Biesheuvel Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20230915171623.655440-12-ardb@google.com --- arch/x86/boot/header.S | 18 +++++++++++++++++- arch/x86/boot/tools/build.c | 24 ------------------------ 2 files changed, 17 insertions(+), 25 deletions(-) diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S index 5575d0f06bab..72744ba440f6 100644 --- a/arch/x86/boot/header.S +++ b/arch/x86/boot/header.S @@ -524,8 +524,24 @@ pref_address: .quad LOAD_PHYSICAL_ADDR # preferred load addr # define INIT_SIZE VO_INIT_SIZE #endif + .macro __handover_offset +#ifndef CONFIG_EFI_HANDOVER_PROTOCOL + .long 0 +#elif !defined(CONFIG_X86_64) + .long ZO_efi32_stub_entry +#else + /* Yes, this is really how we defined it :( */ + .long ZO_efi64_stub_entry - 0x200 +#ifdef CONFIG_EFI_MIXED + .if ZO_efi32_stub_entry != ZO_efi64_stub_entry - 0x200 + .error "32-bit and 64-bit EFI entry points do not match" + .endif +#endif +#endif + .endm + init_size: .long INIT_SIZE # kernel initialization size -handover_offset: .long 0 # Filled in by build.c +handover_offset: __handover_offset kernel_info_offset: .long ZO_kernel_info # End of setup header ##################################################### diff --git a/arch/x86/boot/tools/build.c b/arch/x86/boot/tools/build.c index 14ef13fe7ab0..069497543164 100644 --- a/arch/x86/boot/tools/build.c +++ b/arch/x86/boot/tools/build.c @@ -55,8 +55,6 @@ u8 buf[SETUP_SECT_MAX*512]; #define PECOFF_COMPAT_RESERVE 0x0 #endif -static unsigned long efi32_stub_entry; -static unsigned long efi64_stub_entry; static unsigned long efi_pe_entry; static unsigned long efi32_pe_entry; static unsigned long _end; @@ -265,31 +263,12 @@ static void efi_stub_defaults(void) #endif } -static void efi_stub_entry_update(void) -{ - unsigned long addr = efi32_stub_entry; - -#ifdef CONFIG_EFI_HANDOVER_PROTOCOL -#ifdef CONFIG_X86_64 - /* Yes, this is really how we defined it :( */ - addr = efi64_stub_entry - 0x200; -#endif - -#ifdef CONFIG_EFI_MIXED - if (efi32_stub_entry != addr) - die("32-bit and 64-bit EFI entry points do not match\n"); -#endif -#endif - put_unaligned_le32(addr, &buf[0x264]); -} - #else static inline void update_pecoff_setup_and_reloc(unsigned int size) {} static inline void update_pecoff_text(unsigned int text_start, unsigned int file_sz) {} static inline void efi_stub_defaults(void) {} -static inline void efi_stub_entry_update(void) {} static inline int reserve_pecoff_reloc_section(int c) { @@ -332,8 +311,6 @@ static void parse_zoffset(char *fname) p = (char *)buf; while (p && *p) { - PARSE_ZOFS(p, efi32_stub_entry); - PARSE_ZOFS(p, efi64_stub_entry); PARSE_ZOFS(p, efi_pe_entry); PARSE_ZOFS(p, efi32_pe_entry); PARSE_ZOFS(p, _end); @@ -416,7 +393,6 @@ int main(int argc, char ** argv) update_pecoff_text(setup_sectors * 512, i + (sys_size * 16)); - efi_stub_entry_update(); crc = partial_crc32(buf, i, crc); if (fwrite(buf, 1, i, dest) != i) From 093ab258e3fb1d1d3afdfd4a69403d44ce90e360 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Fri, 15 Sep 2023 17:16:27 +0000 Subject: [PATCH 10/23] x86/boot: Define setup size in linker script The setup block contains the real mode startup code that is used when booting from a legacy BIOS, along with the boot_params/setup_data that is used by legacy x86 bootloaders to pass the command line and initial ramdisk parameters, among other things. The setup block also contains the PE/COFF header of the entire combined image, which includes the compressed kernel image, the decompressor and the EFI stub. This PE header describes the layout of the executable image in memory, and currently, the fact that the setup block precedes it makes it rather fiddly to get the right values into the right place in the final image. Let's make things a bit easier by defining the setup_size in the linker script so it can be referenced from the asm code directly, rather than having to rely on the build tool to calculate it. For the time being, add 64 bytes of fixed padding for the .reloc and .compat sections - this will be removed in a subsequent patch after the PE/COFF header has been reorganized. This change has no impact on the resulting bzImage binary when configured with CONFIG_EFI_MIXED=y. Signed-off-by: Ard Biesheuvel Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20230915171623.655440-13-ardb@google.com --- arch/x86/boot/header.S | 2 +- arch/x86/boot/setup.ld | 4 ++++ arch/x86/boot/tools/build.c | 6 ------ 3 files changed, 5 insertions(+), 7 deletions(-) diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S index 72744ba440f6..06bd72a324c1 100644 --- a/arch/x86/boot/header.S +++ b/arch/x86/boot/header.S @@ -231,7 +231,7 @@ sentinel: .byte 0xff, 0xff /* Used to detect broken loaders */ .globl hdr hdr: -setup_sects: .byte 0 /* Filled in by build.c */ + .byte setup_sects - 1 root_flags: .word ROOT_RDONLY syssize: .long 0 /* Filled in by build.c */ ram_size: .word 0 /* Obsolete */ diff --git a/arch/x86/boot/setup.ld b/arch/x86/boot/setup.ld index b11c45b9e51e..9bd5c1ada599 100644 --- a/arch/x86/boot/setup.ld +++ b/arch/x86/boot/setup.ld @@ -39,6 +39,10 @@ SECTIONS .signature : { setup_sig = .; LONG(0x5a5aaa55) + + /* Reserve some extra space for the reloc and compat sections */ + setup_size = ALIGN(ABSOLUTE(.) + 64, 512); + setup_sects = ABSOLUTE(setup_size / 512); } diff --git a/arch/x86/boot/tools/build.c b/arch/x86/boot/tools/build.c index 069497543164..745d64b6d930 100644 --- a/arch/x86/boot/tools/build.c +++ b/arch/x86/boot/tools/build.c @@ -48,12 +48,7 @@ typedef unsigned int u32; u8 buf[SETUP_SECT_MAX*512]; #define PECOFF_RELOC_RESERVE 0x20 - -#ifdef CONFIG_EFI_MIXED #define PECOFF_COMPAT_RESERVE 0x20 -#else -#define PECOFF_COMPAT_RESERVE 0x0 -#endif static unsigned long efi_pe_entry; static unsigned long efi32_pe_entry; @@ -388,7 +383,6 @@ int main(int argc, char ** argv) #endif /* Patch the setup code with the appropriate size parameters */ - buf[0x1f1] = setup_sectors-1; put_unaligned_le32(sys_size, &buf[0x1f4]); update_pecoff_text(setup_sectors * 512, i + (sys_size * 16)); From aeb92067f6ae994b541d7f9752fe54ed3d108bcc Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Fri, 15 Sep 2023 17:16:28 +0000 Subject: [PATCH 11/23] x86/boot: Derive file size from _edata symbol Tweak the linker script so that the value of _edata represents the decompressor binary's file size rounded up to the appropriate alignment. This removes the need to calculate it in the build tool, and will make it easier to refer to the file size from the header directly in subsequent changes to the PE header layout. While adding _edata to the sed regex that parses the compressed vmlinux's symbol list, tweak the regex a bit for conciseness. This change has no impact on the resulting bzImage binary when configured with CONFIG_EFI_STUB=y. Signed-off-by: Ard Biesheuvel Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20230915171623.655440-14-ardb@google.com --- arch/x86/boot/Makefile | 2 +- arch/x86/boot/compressed/vmlinux.lds.S | 3 +++ arch/x86/boot/header.S | 2 +- arch/x86/boot/tools/build.c | 30 ++++++-------------------- 4 files changed, 12 insertions(+), 25 deletions(-) diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile index 0e98bc503699..cc04917b1ac6 100644 --- a/arch/x86/boot/Makefile +++ b/arch/x86/boot/Makefile @@ -89,7 +89,7 @@ $(obj)/vmlinux.bin: $(obj)/compressed/vmlinux FORCE SETUP_OBJS = $(addprefix $(obj)/,$(setup-y)) -sed-zoffset := -e 's/^\([0-9a-fA-F]*\) [a-zA-Z] \(startup_32\|efi32_stub_entry\|efi64_stub_entry\|efi_pe_entry\|efi32_pe_entry\|input_data\|kernel_info\|_end\|_ehead\|_text\|z_.*\)$$/\#define ZO_\2 0x\1/p' +sed-zoffset := -e 's/^\([0-9a-fA-F]*\) [a-zA-Z] \(startup_32\|efi.._stub_entry\|efi\(32\)\?_pe_entry\|input_data\|kernel_info\|_end\|_ehead\|_text\|_edata\|z_.*\)$$/\#define ZO_\2 0x\1/p' quiet_cmd_zoffset = ZOFFSET $@ cmd_zoffset = $(NM) $< | sed -n $(sed-zoffset) > $@ diff --git a/arch/x86/boot/compressed/vmlinux.lds.S b/arch/x86/boot/compressed/vmlinux.lds.S index 4ff6ab1b67d9..b688598db28e 100644 --- a/arch/x86/boot/compressed/vmlinux.lds.S +++ b/arch/x86/boot/compressed/vmlinux.lds.S @@ -47,6 +47,9 @@ SECTIONS _data = . ; *(.data) *(.data.*) + + /* Add 4 bytes of extra space for a CRC-32 checksum */ + . = ALIGN(. + 4, 0x20); _edata = . ; } . = ALIGN(L1_CACHE_BYTES); diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S index 06bd72a324c1..34e9b35b827c 100644 --- a/arch/x86/boot/header.S +++ b/arch/x86/boot/header.S @@ -233,7 +233,7 @@ sentinel: .byte 0xff, 0xff /* Used to detect broken loaders */ hdr: .byte setup_sects - 1 root_flags: .word ROOT_RDONLY -syssize: .long 0 /* Filled in by build.c */ +syssize: .long ZO__edata / 16 ram_size: .word 0 /* Obsolete */ vid_mode: .word SVGA_MODE root_dev: .word 0 /* Default to major/minor 0/0 */ diff --git a/arch/x86/boot/tools/build.c b/arch/x86/boot/tools/build.c index 745d64b6d930..e792c6c5a634 100644 --- a/arch/x86/boot/tools/build.c +++ b/arch/x86/boot/tools/build.c @@ -52,6 +52,7 @@ u8 buf[SETUP_SECT_MAX*512]; static unsigned long efi_pe_entry; static unsigned long efi32_pe_entry; +static unsigned long _edata; static unsigned long _end; /*----------------------------------------------------------------------*/ @@ -308,6 +309,7 @@ static void parse_zoffset(char *fname) while (p && *p) { PARSE_ZOFS(p, efi_pe_entry); PARSE_ZOFS(p, efi32_pe_entry); + PARSE_ZOFS(p, _edata); PARSE_ZOFS(p, _end); p = strchr(p, '\n'); @@ -320,7 +322,6 @@ int main(int argc, char ** argv) { unsigned int i, sz, setup_sectors; int c; - u32 sys_size; struct stat sb; FILE *file, *dest; int fd; @@ -368,24 +369,14 @@ int main(int argc, char ** argv) die("Unable to open `%s': %m", argv[2]); if (fstat(fd, &sb)) die("Unable to stat `%s': %m", argv[2]); - sz = sb.st_size; + if (_edata != sb.st_size) + die("Unexpected file size `%s': %u != %u", argv[2], _edata, + sb.st_size); + sz = _edata - 4; kernel = mmap(NULL, sz, PROT_READ, MAP_SHARED, fd, 0); if (kernel == MAP_FAILED) die("Unable to mmap '%s': %m", argv[2]); - /* Number of 16-byte paragraphs, including space for a 4-byte CRC */ - sys_size = (sz + 15 + 4) / 16; -#ifdef CONFIG_EFI_STUB - /* - * COFF requires minimum 32-byte alignment of sections, and - * adding a signature is problematic without that alignment. - */ - sys_size = (sys_size + 1) & ~1; -#endif - - /* Patch the setup code with the appropriate size parameters */ - put_unaligned_le32(sys_size, &buf[0x1f4]); - - update_pecoff_text(setup_sectors * 512, i + (sys_size * 16)); + update_pecoff_text(setup_sectors * 512, i + _edata); crc = partial_crc32(buf, i, crc); @@ -397,13 +388,6 @@ int main(int argc, char ** argv) if (fwrite(kernel, 1, sz, dest) != sz) die("Writing kernel failed"); - /* Add padding leaving 4 bytes for the checksum */ - while (sz++ < (sys_size*16) - 4) { - crc = partial_crc32_one('\0', crc); - if (fwrite("\0", 1, 1, dest) != 1) - die("Writing padding failed"); - } - /* Write the CRC */ put_unaligned_le32(crc, buf); if (fwrite(buf, 1, 4, dest) != 4) From efa089e63b56bdc5eca754b995cb039dd7a5457e Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Fri, 15 Sep 2023 17:16:29 +0000 Subject: [PATCH 12/23] x86/boot: Construct PE/COFF .text section from assembler Now that the size of the setup block is visible to the assembler, it is possible to populate the PE/COFF header fields from the asm code directly, instead of poking the values into the binary using the build tool. This will make it easier to reorganize the section layout without having to tweak the build tool in lockstep. This change has no impact on the resulting bzImage binary. Signed-off-by: Ard Biesheuvel Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20230915171623.655440-15-ardb@google.com --- arch/x86/boot/header.S | 22 ++++++----------- arch/x86/boot/tools/build.c | 47 ------------------------------------- 2 files changed, 7 insertions(+), 62 deletions(-) diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S index 34e9b35b827c..2b07bc596c39 100644 --- a/arch/x86/boot/header.S +++ b/arch/x86/boot/header.S @@ -75,14 +75,12 @@ optional_header: .byte 0x02 # MajorLinkerVersion .byte 0x14 # MinorLinkerVersion - # Filled in by build.c - .long 0 # SizeOfCode + .long setup_size + ZO__end - 0x200 # SizeOfCode .long 0 # SizeOfInitializedData .long 0 # SizeOfUninitializedData - # Filled in by build.c - .long 0x0000 # AddressOfEntryPoint + .long setup_size + ZO_efi_pe_entry # AddressOfEntryPoint .long 0x0200 # BaseOfCode #ifdef CONFIG_X86_32 @@ -105,10 +103,7 @@ extra_header_fields: .word 0 # MinorSubsystemVersion .long 0 # Win32VersionValue - # - # The size of the bzImage is written in tools/build.c - # - .long 0 # SizeOfImage + .long setup_size + ZO__end # SizeOfImage .long 0x200 # SizeOfHeaders .long 0 # CheckSum @@ -199,18 +194,15 @@ section_table: IMAGE_SCN_MEM_DISCARDABLE # Characteristics #endif - # - # The offset & size fields are filled in by build.c. - # .ascii ".text" .byte 0 .byte 0 .byte 0 - .long 0 - .long 0x0 # startup_{32,64} - .long 0 # Size of initialized data + .long ZO__end + .long setup_size + .long ZO__edata # Size of initialized data # on disk - .long 0x0 # startup_{32,64} + .long setup_size .long 0 # PointerToRelocations .long 0 # PointerToLineNumbers .word 0 # NumberOfRelocations diff --git a/arch/x86/boot/tools/build.c b/arch/x86/boot/tools/build.c index e792c6c5a634..9712f27e32c1 100644 --- a/arch/x86/boot/tools/build.c +++ b/arch/x86/boot/tools/build.c @@ -50,10 +50,8 @@ u8 buf[SETUP_SECT_MAX*512]; #define PECOFF_RELOC_RESERVE 0x20 #define PECOFF_COMPAT_RESERVE 0x20 -static unsigned long efi_pe_entry; static unsigned long efi32_pe_entry; static unsigned long _edata; -static unsigned long _end; /*----------------------------------------------------------------------*/ @@ -216,32 +214,6 @@ static void update_pecoff_setup_and_reloc(unsigned int size) #endif } -static void update_pecoff_text(unsigned int text_start, unsigned int file_sz) -{ - unsigned int pe_header; - unsigned int text_sz = file_sz - text_start; - unsigned int bss_sz = _end - text_sz; - - pe_header = get_unaligned_le32(&buf[0x3c]); - - /* - * Size of code: Subtract the size of the first sector (512 bytes) - * which includes the header. - */ - put_unaligned_le32(file_sz - 512 + bss_sz, &buf[pe_header + 0x1c]); - - /* Size of image */ - put_unaligned_le32(file_sz + bss_sz, &buf[pe_header + 0x50]); - - /* - * Address of entry point for PE/COFF executable - */ - put_unaligned_le32(text_start + efi_pe_entry, &buf[pe_header + 0x28]); - - update_pecoff_section_header_fields(".text", text_start, text_sz + bss_sz, - text_sz, text_start); -} - static int reserve_pecoff_reloc_section(int c) { /* Reserve 0x20 bytes for .reloc section */ @@ -249,22 +221,9 @@ static int reserve_pecoff_reloc_section(int c) return PECOFF_RELOC_RESERVE; } -static void efi_stub_defaults(void) -{ - /* Defaults for old kernel */ -#ifdef CONFIG_X86_32 - efi_pe_entry = 0x10; -#else - efi_pe_entry = 0x210; -#endif -} - #else static inline void update_pecoff_setup_and_reloc(unsigned int size) {} -static inline void update_pecoff_text(unsigned int text_start, - unsigned int file_sz) {} -static inline void efi_stub_defaults(void) {} static inline int reserve_pecoff_reloc_section(int c) { @@ -307,10 +266,8 @@ static void parse_zoffset(char *fname) p = (char *)buf; while (p && *p) { - PARSE_ZOFS(p, efi_pe_entry); PARSE_ZOFS(p, efi32_pe_entry); PARSE_ZOFS(p, _edata); - PARSE_ZOFS(p, _end); p = strchr(p, '\n'); while (p && (*p == '\r' || *p == '\n')) @@ -328,8 +285,6 @@ int main(int argc, char ** argv) void *kernel; u32 crc = 0xffffffffUL; - efi_stub_defaults(); - if (argc != 5) usage(); parse_zoffset(argv[3]); @@ -376,8 +331,6 @@ int main(int argc, char ** argv) kernel = mmap(NULL, sz, PROT_READ, MAP_SHARED, fd, 0); if (kernel == MAP_FAILED) die("Unable to mmap '%s': %m", argv[2]); - update_pecoff_text(setup_sectors * 512, i + _edata); - crc = partial_crc32(buf, i, crc); if (fwrite(buf, 1, i, dest) != i) From fa5750521e0a4efbc1af05223da9c4bbd6c21c83 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Fri, 15 Sep 2023 17:16:30 +0000 Subject: [PATCH 13/23] x86/boot: Drop PE/COFF .reloc section Ancient buggy EFI loaders may have required a .reloc section to be present at some point in time, but this has not been true for a long time so the .reloc section can just be dropped. Signed-off-by: Ard Biesheuvel Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20230915171623.655440-16-ardb@google.com --- arch/x86/boot/header.S | 20 -------------------- arch/x86/boot/setup.ld | 4 ++-- arch/x86/boot/tools/build.c | 34 +++++----------------------------- 3 files changed, 7 insertions(+), 51 deletions(-) diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S index 2b07bc596c39..9e9641e220a7 100644 --- a/arch/x86/boot/header.S +++ b/arch/x86/boot/header.S @@ -155,26 +155,6 @@ section_table: IMAGE_SCN_MEM_READ | \ IMAGE_SCN_MEM_EXECUTE # Characteristics - # - # The EFI application loader requires a relocation section - # because EFI applications must be relocatable. The .reloc - # offset & size fields are filled in by build.c. - # - .ascii ".reloc" - .byte 0 - .byte 0 - .long 0 - .long 0 - .long 0 # SizeOfRawData - .long 0 # PointerToRawData - .long 0 # PointerToRelocations - .long 0 # PointerToLineNumbers - .word 0 # NumberOfRelocations - .word 0 # NumberOfLineNumbers - .long IMAGE_SCN_CNT_INITIALIZED_DATA | \ - IMAGE_SCN_MEM_READ | \ - IMAGE_SCN_MEM_DISCARDABLE # Characteristics - #ifdef CONFIG_EFI_MIXED # # The offset & size fields are filled in by build.c. diff --git a/arch/x86/boot/setup.ld b/arch/x86/boot/setup.ld index 9bd5c1ada599..6d389499565c 100644 --- a/arch/x86/boot/setup.ld +++ b/arch/x86/boot/setup.ld @@ -40,8 +40,8 @@ SECTIONS setup_sig = .; LONG(0x5a5aaa55) - /* Reserve some extra space for the reloc and compat sections */ - setup_size = ALIGN(ABSOLUTE(.) + 64, 512); + /* Reserve some extra space for the compat section */ + setup_size = ALIGN(ABSOLUTE(.) + 32, 512); setup_sects = ABSOLUTE(setup_size / 512); } diff --git a/arch/x86/boot/tools/build.c b/arch/x86/boot/tools/build.c index 9712f27e32c1..faccff9743a3 100644 --- a/arch/x86/boot/tools/build.c +++ b/arch/x86/boot/tools/build.c @@ -47,7 +47,6 @@ typedef unsigned int u32; /* This must be large enough to hold the entire setup */ u8 buf[SETUP_SECT_MAX*512]; -#define PECOFF_RELOC_RESERVE 0x20 #define PECOFF_COMPAT_RESERVE 0x20 static unsigned long efi32_pe_entry; @@ -180,24 +179,13 @@ static void update_pecoff_section_header(char *section_name, u32 offset, u32 siz update_pecoff_section_header_fields(section_name, offset, size, size, offset); } -static void update_pecoff_setup_and_reloc(unsigned int size) +static void update_pecoff_setup(unsigned int size) { u32 setup_offset = 0x200; - u32 reloc_offset = size - PECOFF_RELOC_RESERVE - PECOFF_COMPAT_RESERVE; -#ifdef CONFIG_EFI_MIXED - u32 compat_offset = reloc_offset + PECOFF_RELOC_RESERVE; -#endif - u32 setup_size = reloc_offset - setup_offset; + u32 compat_offset = size - PECOFF_COMPAT_RESERVE; + u32 setup_size = compat_offset - setup_offset; update_pecoff_section_header(".setup", setup_offset, setup_size); - update_pecoff_section_header(".reloc", reloc_offset, PECOFF_RELOC_RESERVE); - - /* - * Modify .reloc section contents with a single entry. The - * relocation is applied to offset 10 of the relocation section. - */ - put_unaligned_le32(reloc_offset + 10, &buf[reloc_offset]); - put_unaligned_le32(10, &buf[reloc_offset + 4]); #ifdef CONFIG_EFI_MIXED update_pecoff_section_header(".compat", compat_offset, PECOFF_COMPAT_RESERVE); @@ -214,21 +202,10 @@ static void update_pecoff_setup_and_reloc(unsigned int size) #endif } -static int reserve_pecoff_reloc_section(int c) -{ - /* Reserve 0x20 bytes for .reloc section */ - memset(buf+c, 0, PECOFF_RELOC_RESERVE); - return PECOFF_RELOC_RESERVE; -} - #else -static inline void update_pecoff_setup_and_reloc(unsigned int size) {} +static inline void update_pecoff_setup(unsigned int size) {} -static inline int reserve_pecoff_reloc_section(int c) -{ - return 0; -} #endif /* CONFIG_EFI_STUB */ static int reserve_pecoff_compat_section(int c) @@ -307,7 +284,6 @@ int main(int argc, char ** argv) fclose(file); c += reserve_pecoff_compat_section(c); - c += reserve_pecoff_reloc_section(c); /* Pad unused space with zeros */ setup_sectors = (c + 511) / 512; @@ -316,7 +292,7 @@ int main(int argc, char ** argv) i = setup_sectors*512; memset(buf+c, 0, i-c); - update_pecoff_setup_and_reloc(i); + update_pecoff_setup(i); /* Open and stat the kernel file */ fd = open(argv[2], O_RDONLY); From 34951f3c28bdf6481d949a20413b2ce7693687b2 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Fri, 15 Sep 2023 17:16:31 +0000 Subject: [PATCH 14/23] x86/boot: Split off PE/COFF .data section Describe the code and data of the decompressor binary using separate .text and .data PE/COFF sections, so that we will be able to map them using restricted permissions once we increase the section and file alignment sufficiently. This avoids the need for memory mappings that are writable and executable at the same time, which is something that is best avoided for security reasons. Signed-off-by: Ard Biesheuvel Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20230915171623.655440-17-ardb@google.com --- arch/x86/boot/Makefile | 2 +- arch/x86/boot/header.S | 19 +++++++++++++++---- 2 files changed, 16 insertions(+), 5 deletions(-) diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile index cc04917b1ac6..3cece19b7473 100644 --- a/arch/x86/boot/Makefile +++ b/arch/x86/boot/Makefile @@ -89,7 +89,7 @@ $(obj)/vmlinux.bin: $(obj)/compressed/vmlinux FORCE SETUP_OBJS = $(addprefix $(obj)/,$(setup-y)) -sed-zoffset := -e 's/^\([0-9a-fA-F]*\) [a-zA-Z] \(startup_32\|efi.._stub_entry\|efi\(32\)\?_pe_entry\|input_data\|kernel_info\|_end\|_ehead\|_text\|_edata\|z_.*\)$$/\#define ZO_\2 0x\1/p' +sed-zoffset := -e 's/^\([0-9a-fA-F]*\) [a-zA-Z] \(startup_32\|efi.._stub_entry\|efi\(32\)\?_pe_entry\|input_data\|kernel_info\|_end\|_ehead\|_text\|_e\?data\|z_.*\)$$/\#define ZO_\2 0x\1/p' quiet_cmd_zoffset = ZOFFSET $@ cmd_zoffset = $(NM) $< | sed -n $(sed-zoffset) > $@ diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S index 9e9641e220a7..a1f986105f00 100644 --- a/arch/x86/boot/header.S +++ b/arch/x86/boot/header.S @@ -75,9 +75,9 @@ optional_header: .byte 0x02 # MajorLinkerVersion .byte 0x14 # MinorLinkerVersion - .long setup_size + ZO__end - 0x200 # SizeOfCode + .long ZO__data # SizeOfCode - .long 0 # SizeOfInitializedData + .long ZO__end - ZO__data # SizeOfInitializedData .long 0 # SizeOfUninitializedData .long setup_size + ZO_efi_pe_entry # AddressOfEntryPoint @@ -178,9 +178,9 @@ section_table: .byte 0 .byte 0 .byte 0 - .long ZO__end + .long ZO__data .long setup_size - .long ZO__edata # Size of initialized data + .long ZO__data # Size of initialized data # on disk .long setup_size .long 0 # PointerToRelocations @@ -191,6 +191,17 @@ section_table: IMAGE_SCN_MEM_READ | \ IMAGE_SCN_MEM_EXECUTE # Characteristics + .ascii ".data\0\0\0" + .long ZO__end - ZO__data # VirtualSize + .long setup_size + ZO__data # VirtualAddress + .long ZO__edata - ZO__data # SizeOfRawData + .long setup_size + ZO__data # PointerToRawData + + .long 0, 0, 0 + .long IMAGE_SCN_CNT_INITIALIZED_DATA | \ + IMAGE_SCN_MEM_READ | \ + IMAGE_SCN_MEM_WRITE # Characteristics + .set section_count, (. - section_table) / 40 #endif /* CONFIG_EFI_STUB */ From 3e3eabe26dc88692d34cf76ca0e0dd331481cc15 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Fri, 15 Sep 2023 17:16:32 +0000 Subject: [PATCH 15/23] x86/boot: Increase section and file alignment to 4k/512 Align x86 with other EFI architectures, and increase the section alignment to the EFI page size (4k), so that firmware is able to honour the section permission attributes and map code read-only and data non-executable. There are a number of requirements that have to be taken into account: - the sign tools get cranky when there are gaps between sections in the file view of the image - the virtual offset of each section must be aligned to the image's section alignment - the file offset *and size* of each section must be aligned to the image's file alignment - the image size must be aligned to the section alignment - each section's virtual offset must be greater than or equal to the size of the headers. In order to meet all these requirements, while avoiding the need for lots of padding to accommodate the .compat section, the latter is placed at an arbitrary offset towards the end of the image, but aligned to the minimum file alignment (512 bytes). The space before the .text section is therefore distributed between the PE header, the .setup section and the .compat section, leaving no gaps in the file coverage, making the signing tools happy. Signed-off-by: Ard Biesheuvel Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20230915171623.655440-18-ardb@google.com --- arch/x86/boot/compressed/vmlinux.lds.S | 4 +- arch/x86/boot/header.S | 81 +++++++++++++---------- arch/x86/boot/setup.ld | 7 +- arch/x86/boot/tools/build.c | 90 +------------------------- 4 files changed, 54 insertions(+), 128 deletions(-) diff --git a/arch/x86/boot/compressed/vmlinux.lds.S b/arch/x86/boot/compressed/vmlinux.lds.S index b688598db28e..083ec6d7722a 100644 --- a/arch/x86/boot/compressed/vmlinux.lds.S +++ b/arch/x86/boot/compressed/vmlinux.lds.S @@ -43,13 +43,13 @@ SECTIONS *(.rodata.*) _erodata = . ; } - .data : { + .data : ALIGN(0x1000) { _data = . ; *(.data) *(.data.*) /* Add 4 bytes of extra space for a CRC-32 checksum */ - . = ALIGN(. + 4, 0x20); + . = ALIGN(. + 4, 0x200); _edata = . ; } . = ALIGN(L1_CACHE_BYTES); diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S index a1f986105f00..b2771710ed98 100644 --- a/arch/x86/boot/header.S +++ b/arch/x86/boot/header.S @@ -36,6 +36,9 @@ SYSSEG = 0x1000 /* historical load address >> 4 */ #define ROOT_RDONLY 1 #endif + .set salign, 0x1000 + .set falign, 0x200 + .code16 .section ".bstext", "ax" #ifdef CONFIG_EFI_STUB @@ -82,7 +85,7 @@ optional_header: .long setup_size + ZO_efi_pe_entry # AddressOfEntryPoint - .long 0x0200 # BaseOfCode + .long setup_size # BaseOfCode #ifdef CONFIG_X86_32 .long 0 # data #endif @@ -93,8 +96,8 @@ extra_header_fields: #else .quad 0 # ImageBase #endif - .long 0x20 # SectionAlignment - .long 0x20 # FileAlignment + .long salign # SectionAlignment + .long falign # FileAlignment .word 0 # MajorOperatingSystemVersion .word 0 # MinorOperatingSystemVersion .word LINUX_EFISTUB_MAJOR_VERSION # MajorImageVersion @@ -103,9 +106,10 @@ extra_header_fields: .word 0 # MinorSubsystemVersion .long 0 # Win32VersionValue - .long setup_size + ZO__end # SizeOfImage + .long setup_size + ZO__end + pecompat_vsize + # SizeOfImage - .long 0x200 # SizeOfHeaders + .long salign # SizeOfHeaders .long 0 # CheckSum .word IMAGE_SUBSYSTEM_EFI_APPLICATION # Subsystem (EFI application) #ifdef CONFIG_EFI_DXE_MEM_ATTRIBUTES @@ -136,44 +140,51 @@ extra_header_fields: # Section table section_table: - # - # The offset & size fields are filled in by build.c. - # .ascii ".setup" .byte 0 .byte 0 - .long 0 - .long 0x0 # startup_{32,64} - .long 0 # Size of initialized data - # on disk - .long 0x0 # startup_{32,64} - .long 0 # PointerToRelocations - .long 0 # PointerToLineNumbers - .word 0 # NumberOfRelocations - .word 0 # NumberOfLineNumbers - .long IMAGE_SCN_CNT_CODE | \ - IMAGE_SCN_MEM_READ | \ - IMAGE_SCN_MEM_EXECUTE # Characteristics + .long setup_size - salign # VirtualSize + .long salign # VirtualAddress + .long pecompat_fstart - salign # SizeOfRawData + .long salign # PointerToRawData -#ifdef CONFIG_EFI_MIXED - # - # The offset & size fields are filled in by build.c. - # - .asciz ".compat" - .long 0 - .long 0x0 - .long 0 # Size of initialized data - # on disk - .long 0x0 - .long 0 # PointerToRelocations - .long 0 # PointerToLineNumbers - .word 0 # NumberOfRelocations - .word 0 # NumberOfLineNumbers + .long 0, 0, 0 .long IMAGE_SCN_CNT_INITIALIZED_DATA | \ IMAGE_SCN_MEM_READ | \ IMAGE_SCN_MEM_DISCARDABLE # Characteristics -#endif +#ifdef CONFIG_EFI_MIXED + .asciz ".compat" + + .long 8 # VirtualSize + .long setup_size + ZO__end # VirtualAddress + .long pecompat_fsize # SizeOfRawData + .long pecompat_fstart # PointerToRawData + + .long 0, 0, 0 + .long IMAGE_SCN_CNT_INITIALIZED_DATA | \ + IMAGE_SCN_MEM_READ | \ + IMAGE_SCN_MEM_DISCARDABLE # Characteristics + + /* + * Put the IA-32 machine type and the associated entry point address in + * the .compat section, so loaders can figure out which other execution + * modes this image supports. + */ + .pushsection ".pecompat", "a", @progbits + .balign falign + .set pecompat_vsize, salign + .globl pecompat_fstart +pecompat_fstart: + .byte 0x1 # Version + .byte 8 # Size + .word IMAGE_FILE_MACHINE_I386 # PE machine type + .long setup_size + ZO_efi32_pe_entry # Entrypoint + .popsection +#else + .set pecompat_vsize, 0 + .set pecompat_fstart, setup_size +#endif .ascii ".text" .byte 0 .byte 0 diff --git a/arch/x86/boot/setup.ld b/arch/x86/boot/setup.ld index 6d389499565c..83bb7efad8ae 100644 --- a/arch/x86/boot/setup.ld +++ b/arch/x86/boot/setup.ld @@ -36,16 +36,17 @@ SECTIONS . = ALIGN(16); .data : { *(.data*) } + .pecompat : { *(.pecompat) } + PROVIDE(pecompat_fsize = setup_size - pecompat_fstart); + .signature : { setup_sig = .; LONG(0x5a5aaa55) - /* Reserve some extra space for the compat section */ - setup_size = ALIGN(ABSOLUTE(.) + 32, 512); + setup_size = ALIGN(ABSOLUTE(.), 4096); setup_sects = ABSOLUTE(setup_size / 512); } - . = ALIGN(16); .bss : { diff --git a/arch/x86/boot/tools/build.c b/arch/x86/boot/tools/build.c index faccff9743a3..10311d77c67f 100644 --- a/arch/x86/boot/tools/build.c +++ b/arch/x86/boot/tools/build.c @@ -47,9 +47,6 @@ typedef unsigned int u32; /* This must be large enough to hold the entire setup */ u8 buf[SETUP_SECT_MAX*512]; -#define PECOFF_COMPAT_RESERVE 0x20 - -static unsigned long efi32_pe_entry; static unsigned long _edata; /*----------------------------------------------------------------------*/ @@ -136,85 +133,6 @@ static void usage(void) die("Usage: build setup system zoffset.h image"); } -#ifdef CONFIG_EFI_STUB - -static void update_pecoff_section_header_fields(char *section_name, u32 vma, u32 size, u32 datasz, u32 offset) -{ - unsigned int pe_header; - unsigned short num_sections; - u8 *section; - - pe_header = get_unaligned_le32(&buf[0x3c]); - num_sections = get_unaligned_le16(&buf[pe_header + 6]); - -#ifdef CONFIG_X86_32 - section = &buf[pe_header + 0xa8]; -#else - section = &buf[pe_header + 0xb8]; -#endif - - while (num_sections > 0) { - if (strncmp((char*)section, section_name, 8) == 0) { - /* section header size field */ - put_unaligned_le32(size, section + 0x8); - - /* section header vma field */ - put_unaligned_le32(vma, section + 0xc); - - /* section header 'size of initialised data' field */ - put_unaligned_le32(datasz, section + 0x10); - - /* section header 'file offset' field */ - put_unaligned_le32(offset, section + 0x14); - - break; - } - section += 0x28; - num_sections--; - } -} - -static void update_pecoff_section_header(char *section_name, u32 offset, u32 size) -{ - update_pecoff_section_header_fields(section_name, offset, size, size, offset); -} - -static void update_pecoff_setup(unsigned int size) -{ - u32 setup_offset = 0x200; - u32 compat_offset = size - PECOFF_COMPAT_RESERVE; - u32 setup_size = compat_offset - setup_offset; - - update_pecoff_section_header(".setup", setup_offset, setup_size); - -#ifdef CONFIG_EFI_MIXED - update_pecoff_section_header(".compat", compat_offset, PECOFF_COMPAT_RESERVE); - - /* - * Put the IA-32 machine type (0x14c) and the associated entry point - * address in the .compat section, so loaders can figure out which other - * execution modes this image supports. - */ - buf[compat_offset] = 0x1; - buf[compat_offset + 1] = 0x8; - put_unaligned_le16(0x14c, &buf[compat_offset + 2]); - put_unaligned_le32(efi32_pe_entry + size, &buf[compat_offset + 4]); -#endif -} - -#else - -static inline void update_pecoff_setup(unsigned int size) {} - -#endif /* CONFIG_EFI_STUB */ - -static int reserve_pecoff_compat_section(int c) -{ - /* Reserve 0x20 bytes for .compat section */ - memset(buf+c, 0, PECOFF_COMPAT_RESERVE); - return PECOFF_COMPAT_RESERVE; -} - /* * 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 @@ -243,7 +161,6 @@ static void parse_zoffset(char *fname) p = (char *)buf; while (p && *p) { - PARSE_ZOFS(p, efi32_pe_entry); PARSE_ZOFS(p, _edata); p = strchr(p, '\n'); @@ -283,17 +200,14 @@ int main(int argc, char ** argv) die("Boot block hasn't got boot flag (0xAA55)"); fclose(file); - c += reserve_pecoff_compat_section(c); - /* Pad unused space with zeros */ - setup_sectors = (c + 511) / 512; + setup_sectors = (c + 4095) / 4096; + setup_sectors *= 8; if (setup_sectors < SETUP_SECT_MIN) setup_sectors = SETUP_SECT_MIN; i = setup_sectors*512; memset(buf+c, 0, i-c); - update_pecoff_setup(i); - /* Open and stat the kernel file */ fd = open(argv[2], O_RDONLY); if (fd < 0) From b3bee1e7c3f2b1b77182302c7b2131c804175870 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Wed, 27 Sep 2023 18:42:11 +0300 Subject: [PATCH 16/23] x86/boot: Compile boot code with -std=gnu11 too Use -std=gnu11 for consistency with main kernel code. It doesn't seem to change anything in vmlinux. Signed-off-by: Alexey Dobriyan Signed-off-by: Ingo Molnar Acked-by: H. Peter Anvin (Intel) Link: https://lore.kernel.org/r/2058761e-12a4-4b2f-9690-3c3c1c9902a5@p183 --- arch/x86/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 5bfe5caaa444..776331f3f9c3 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -43,7 +43,7 @@ endif # How to compile the 16-bit code. Note we always compile for -march=i386; # that way we can complain to the user if the CPU is insufficient. -REALMODE_CFLAGS := -m16 -g -Os -DDISABLE_BRANCH_PROFILING -D__DISABLE_EXPORTS \ +REALMODE_CFLAGS := -std=gnu11 -m16 -g -Os -DDISABLE_BRANCH_PROFILING -D__DISABLE_EXPORTS \ -Wall -Wstrict-prototypes -march=i386 -mregparm=3 \ -fno-strict-aliasing -fomit-frame-pointer -fno-pic \ -mno-mmx -mno-sse $(call cc-option,-fcf-protection=none) From 001470fed5959d01faecbd57fcf2f60294da0de1 Mon Sep 17 00:00:00 2001 From: Yuntao Wang Date: Mon, 7 Aug 2023 16:45:47 +0800 Subject: [PATCH 17/23] x86/boot: Fix incorrect startup_gdt_descr.size Since the size value is added to the base address to yield the last valid byte address of the GDT, the current size value of startup_gdt_descr is incorrect (too large by one), fix it. [ mingo: This probably never mattered, because startup_gdt[] is only used in a very controlled fashion - but make it consistent nevertheless. ] Fixes: 866b556efa12 ("x86/head/64: Install startup GDT") Signed-off-by: Yuntao Wang Signed-off-by: Ingo Molnar Cc: "H. Peter Anvin" Link: https://lore.kernel.org/r/20230807084547.217390-1-ytcoode@gmail.com --- arch/x86/kernel/head64.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 49f7629b17f7..bbc21798df10 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -80,7 +80,7 @@ static struct desc_struct startup_gdt[GDT_ENTRIES] = { * while the kernel still uses a direct mapping. */ static struct desc_ptr startup_gdt_descr = { - .size = sizeof(startup_gdt), + .size = sizeof(startup_gdt)-1, .address = 0, }; From 9f76d606269be7bd1ee5942b7c9c21bb0b43825f Mon Sep 17 00:00:00 2001 From: Wang Jinchao Date: Thu, 3 Aug 2023 17:44:00 +0800 Subject: [PATCH 18/23] x86/boot: Harmonize the style of array-type parameter for fixup_pointer() calls The usage of '&' before the array parameter is redundant because '&array' is equivalent to 'array'. Therefore, there is no need to include '&' before the array parameter. In fact, using '&' can cause more confusion, especially for individuals who are not familiar with the address-of operation for arrays. They might mistakenly believe that one is different from the other and spend additional time realizing that they are actually the same. Harmonizing the style by removing the unnecessary '&' would save time for those individuals. Signed-off-by: Wang Jinchao Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/ZMt24BGEX9IhPSY6@fedora --- arch/x86/kernel/head64.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index bbc21798df10..d6ca9c5c3da4 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -211,7 +211,7 @@ unsigned long __head __startup_64(unsigned long physaddr, /* Fixup the physical addresses in the page table */ - pgd = fixup_pointer(&early_top_pgt, physaddr); + pgd = fixup_pointer(early_top_pgt, physaddr); p = pgd + pgd_index(__START_KERNEL_map); if (la57) *p = (unsigned long)level4_kernel_pgt; @@ -220,11 +220,11 @@ unsigned long __head __startup_64(unsigned long physaddr, *p += _PAGE_TABLE_NOENC - __START_KERNEL_map + load_delta; if (la57) { - p4d = fixup_pointer(&level4_kernel_pgt, physaddr); + p4d = fixup_pointer(level4_kernel_pgt, physaddr); p4d[511] += load_delta; } - pud = fixup_pointer(&level3_kernel_pgt, physaddr); + pud = fixup_pointer(level3_kernel_pgt, physaddr); pud[510] += load_delta; pud[511] += load_delta; From dc6283009016acd5a8c6a6c073506d82bbc55529 Mon Sep 17 00:00:00 2001 From: Hou Wenlong Date: Wed, 12 Jul 2023 11:30:05 +0800 Subject: [PATCH 19/23] x86/head/64: Mark 'startup_gdt[]' and 'startup_gdt_descr' as __initdata As 'startup_gdt[]' and 'startup_gdt_descr' are only used in booting, mark them as __initdata to allow them to be freed after boot. Signed-off-by: Hou Wenlong Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/c85903a7cfad37d14a7e5a4df9fc7119a3669fb3.1689130310.git.houwenlong.hwl@antgroup.com --- arch/x86/kernel/head64.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index d6ca9c5c3da4..f41625de9442 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -69,7 +69,7 @@ EXPORT_SYMBOL(vmemmap_base); /* * GDT used on the boot CPU before switching to virtual addresses. */ -static struct desc_struct startup_gdt[GDT_ENTRIES] = { +static struct desc_struct startup_gdt[GDT_ENTRIES] __initdata = { [GDT_ENTRY_KERNEL32_CS] = GDT_ENTRY_INIT(0xc09b, 0, 0xfffff), [GDT_ENTRY_KERNEL_CS] = GDT_ENTRY_INIT(0xa09b, 0, 0xfffff), [GDT_ENTRY_KERNEL_DS] = GDT_ENTRY_INIT(0xc093, 0, 0xfffff), @@ -79,7 +79,7 @@ static struct desc_struct startup_gdt[GDT_ENTRIES] = { * Address needs to be set at runtime because it references the startup_gdt * while the kernel still uses a direct mapping. */ -static struct desc_ptr startup_gdt_descr = { +static struct desc_ptr startup_gdt_descr __initdata = { .size = sizeof(startup_gdt)-1, .address = 0, }; From 7f6874eddd81cb2ed784642a7a4321671e158ffe Mon Sep 17 00:00:00 2001 From: Hou Wenlong Date: Wed, 12 Jul 2023 11:30:06 +0800 Subject: [PATCH 20/23] x86/head/64: Add missing __head annotation to startup_64_load_idt() This function is currently only used in the head code and is only called from startup_64_setup_env(). Although it would be inlined by the compiler, it would be better to mark it as __head too in case it doesn't. Signed-off-by: Hou Wenlong Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/efcc5b5e18af880e415d884e072bf651c1fa7c34.1689130310.git.houwenlong.hwl@antgroup.com --- arch/x86/kernel/head64.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index f41625de9442..f0efc22fe759 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -588,7 +588,7 @@ static void set_bringup_idt_handler(gate_desc *idt, int n, void *handler) } /* This runs while still in the direct mapping */ -static void startup_64_load_idt(unsigned long physbase) +static void __head startup_64_load_idt(unsigned long physbase) { struct desc_ptr *desc = fixup_pointer(&bringup_idt_descr, physbase); gate_desc *idt = fixup_pointer(bringup_idt_table, physbase); From d2a285d65bfde3218fd0c3b88794d0135ced680b Mon Sep 17 00:00:00 2001 From: Hou Wenlong Date: Tue, 17 Oct 2023 15:08:06 +0800 Subject: [PATCH 21/23] x86/head/64: Move the __head definition to Move the __head section definition to a header to widen its use. An upcoming patch will mark the code as __head in mem_encrypt_identity.c too. Signed-off-by: Hou Wenlong Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/0583f57977be184689c373fe540cbd7d85ca2047.1697525407.git.houwenlong.hwl@antgroup.com --- arch/x86/include/asm/init.h | 2 ++ arch/x86/kernel/head64.c | 3 +-- 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/arch/x86/include/asm/init.h b/arch/x86/include/asm/init.h index 5f1d3c421f68..cc9ccf61b6bd 100644 --- a/arch/x86/include/asm/init.h +++ b/arch/x86/include/asm/init.h @@ -2,6 +2,8 @@ #ifndef _ASM_X86_INIT_H #define _ASM_X86_INIT_H +#define __head __section(".head.text") + struct x86_mapping_info { void *(*alloc_pgt_page)(void *); /* allocate buf for page table */ void *context; /* context for alloc_pgt_page */ diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index f0efc22fe759..05a110c97111 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -41,6 +41,7 @@ #include #include #include +#include /* * Manage page tables very early on. @@ -84,8 +85,6 @@ static struct desc_ptr startup_gdt_descr __initdata = { .address = 0, }; -#define __head __section(".head.text") - static void __head *fixup_pointer(void *ptr, unsigned long physaddr) { return ptr - (void *)_text + (void *)physaddr; From d55d5bc5d937743aa8ebb7ca3af25111053b5d8c Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Tue, 17 Oct 2023 15:25:12 +0200 Subject: [PATCH 22/23] x86/boot: Rename conflicting 'boot_params' pointer to 'boot_params_ptr' The x86 decompressor is built and linked as a separate executable, but it shares components with the kernel proper, which are either #include'd as C files, or linked into the decompresor as a static library (e.g, the EFI stub) Both the kernel itself and the decompressor define a global symbol 'boot_params' to refer to the boot_params struct, but in the former case, it refers to the struct directly, whereas in the decompressor, it refers to a global pointer variable referring to the struct boot_params passed by the bootloader or constructed from scratch. This ambiguity is unfortunate, and makes it impossible to assign this decompressor variable from the x86 EFI stub, given that declaring it as extern results in a clash. So rename the decompressor version (whose scope is limited) to boot_params_ptr. [ mingo: Renamed 'boot_params_p' to 'boot_params_ptr' for clarity ] Signed-off-by: Ard Biesheuvel Signed-off-by: Ingo Molnar Cc: linux-kernel@vger.kernel.org --- arch/x86/boot/compressed/acpi.c | 14 ++++++------- arch/x86/boot/compressed/cmdline.c | 4 ++-- arch/x86/boot/compressed/ident_map_64.c | 7 ++++--- arch/x86/boot/compressed/kaslr.c | 26 ++++++++++++------------- arch/x86/boot/compressed/mem.c | 6 +++--- arch/x86/boot/compressed/misc.c | 24 +++++++++++------------ arch/x86/boot/compressed/misc.h | 1 - arch/x86/boot/compressed/pgtable_64.c | 9 ++++----- arch/x86/boot/compressed/sev.c | 2 +- arch/x86/include/asm/boot.h | 2 ++ 10 files changed, 48 insertions(+), 47 deletions(-) diff --git a/arch/x86/boot/compressed/acpi.c b/arch/x86/boot/compressed/acpi.c index 9caf89063e77..55c98fdd67d2 100644 --- a/arch/x86/boot/compressed/acpi.c +++ b/arch/x86/boot/compressed/acpi.c @@ -30,13 +30,13 @@ __efi_get_rsdp_addr(unsigned long cfg_tbl_pa, unsigned int cfg_tbl_len) * Search EFI system tables for RSDP. Preferred is ACPI_20_TABLE_GUID to * ACPI_TABLE_GUID because it has more features. */ - rsdp_addr = efi_find_vendor_table(boot_params, cfg_tbl_pa, cfg_tbl_len, + rsdp_addr = efi_find_vendor_table(boot_params_ptr, cfg_tbl_pa, cfg_tbl_len, ACPI_20_TABLE_GUID); if (rsdp_addr) return (acpi_physical_address)rsdp_addr; /* No ACPI_20_TABLE_GUID found, fallback to ACPI_TABLE_GUID. */ - rsdp_addr = efi_find_vendor_table(boot_params, cfg_tbl_pa, cfg_tbl_len, + rsdp_addr = efi_find_vendor_table(boot_params_ptr, cfg_tbl_pa, cfg_tbl_len, ACPI_TABLE_GUID); if (rsdp_addr) return (acpi_physical_address)rsdp_addr; @@ -56,15 +56,15 @@ static acpi_physical_address efi_get_rsdp_addr(void) enum efi_type et; int ret; - et = efi_get_type(boot_params); + et = efi_get_type(boot_params_ptr); if (et == EFI_TYPE_NONE) return 0; - systab_pa = efi_get_system_table(boot_params); + systab_pa = efi_get_system_table(boot_params_ptr); if (!systab_pa) error("EFI support advertised, but unable to locate system table."); - ret = efi_get_conf_table(boot_params, &cfg_tbl_pa, &cfg_tbl_len); + ret = efi_get_conf_table(boot_params_ptr, &cfg_tbl_pa, &cfg_tbl_len); if (ret || !cfg_tbl_pa) error("EFI config table not found."); @@ -156,7 +156,7 @@ acpi_physical_address get_rsdp_addr(void) { acpi_physical_address pa; - pa = boot_params->acpi_rsdp_addr; + pa = boot_params_ptr->acpi_rsdp_addr; if (!pa) pa = efi_get_rsdp_addr(); @@ -210,7 +210,7 @@ static unsigned long get_acpi_srat_table(void) rsdp = (struct acpi_table_rsdp *)get_cmdline_acpi_rsdp(); if (!rsdp) rsdp = (struct acpi_table_rsdp *)(long) - boot_params->acpi_rsdp_addr; + boot_params_ptr->acpi_rsdp_addr; if (!rsdp) return 0; diff --git a/arch/x86/boot/compressed/cmdline.c b/arch/x86/boot/compressed/cmdline.c index f1add5d85da9..c1bb180973ea 100644 --- a/arch/x86/boot/compressed/cmdline.c +++ b/arch/x86/boot/compressed/cmdline.c @@ -14,9 +14,9 @@ static inline char rdfs8(addr_t addr) #include "../cmdline.c" unsigned long get_cmd_line_ptr(void) { - unsigned long cmd_line_ptr = boot_params->hdr.cmd_line_ptr; + unsigned long cmd_line_ptr = boot_params_ptr->hdr.cmd_line_ptr; - cmd_line_ptr |= (u64)boot_params->ext_cmd_line_ptr << 32; + cmd_line_ptr |= (u64)boot_params_ptr->ext_cmd_line_ptr << 32; return cmd_line_ptr; } diff --git a/arch/x86/boot/compressed/ident_map_64.c b/arch/x86/boot/compressed/ident_map_64.c index bcc956c17872..3c8593de8ccb 100644 --- a/arch/x86/boot/compressed/ident_map_64.c +++ b/arch/x86/boot/compressed/ident_map_64.c @@ -151,8 +151,9 @@ void initialize_identity_maps(void *rmode) * or does not touch all the pages covering them. */ kernel_add_identity_map((unsigned long)_head, (unsigned long)_end); - boot_params = rmode; - kernel_add_identity_map((unsigned long)boot_params, (unsigned long)(boot_params + 1)); + boot_params_ptr = rmode; + kernel_add_identity_map((unsigned long)boot_params_ptr, + (unsigned long)(boot_params_ptr + 1)); cmdline = get_cmd_line_ptr(); kernel_add_identity_map(cmdline, cmdline + COMMAND_LINE_SIZE); @@ -160,7 +161,7 @@ void initialize_identity_maps(void *rmode) * Also map the setup_data entries passed via boot_params in case they * need to be accessed by uncompressed kernel via the identity mapping. */ - sd = (struct setup_data *)boot_params->hdr.setup_data; + sd = (struct setup_data *)boot_params_ptr->hdr.setup_data; while (sd) { unsigned long sd_addr = (unsigned long)sd; diff --git a/arch/x86/boot/compressed/kaslr.c b/arch/x86/boot/compressed/kaslr.c index 9193acf0e9cd..dec961c6d16a 100644 --- a/arch/x86/boot/compressed/kaslr.c +++ b/arch/x86/boot/compressed/kaslr.c @@ -63,7 +63,7 @@ static unsigned long get_boot_seed(void) unsigned long hash = 0; hash = rotate_xor(hash, build_str, sizeof(build_str)); - hash = rotate_xor(hash, boot_params, sizeof(*boot_params)); + hash = rotate_xor(hash, boot_params_ptr, sizeof(*boot_params_ptr)); return hash; } @@ -383,7 +383,7 @@ static void handle_mem_options(void) static void mem_avoid_init(unsigned long input, unsigned long input_size, unsigned long output) { - unsigned long init_size = boot_params->hdr.init_size; + unsigned long init_size = boot_params_ptr->hdr.init_size; u64 initrd_start, initrd_size; unsigned long cmd_line, cmd_line_size; @@ -395,10 +395,10 @@ static void mem_avoid_init(unsigned long input, unsigned long input_size, mem_avoid[MEM_AVOID_ZO_RANGE].size = (output + init_size) - input; /* Avoid initrd. */ - initrd_start = (u64)boot_params->ext_ramdisk_image << 32; - initrd_start |= boot_params->hdr.ramdisk_image; - initrd_size = (u64)boot_params->ext_ramdisk_size << 32; - initrd_size |= boot_params->hdr.ramdisk_size; + initrd_start = (u64)boot_params_ptr->ext_ramdisk_image << 32; + initrd_start |= boot_params_ptr->hdr.ramdisk_image; + initrd_size = (u64)boot_params_ptr->ext_ramdisk_size << 32; + initrd_size |= boot_params_ptr->hdr.ramdisk_size; mem_avoid[MEM_AVOID_INITRD].start = initrd_start; mem_avoid[MEM_AVOID_INITRD].size = initrd_size; /* No need to set mapping for initrd, it will be handled in VO. */ @@ -413,8 +413,8 @@ static void mem_avoid_init(unsigned long input, unsigned long input_size, } /* Avoid boot parameters. */ - mem_avoid[MEM_AVOID_BOOTPARAMS].start = (unsigned long)boot_params; - mem_avoid[MEM_AVOID_BOOTPARAMS].size = sizeof(*boot_params); + mem_avoid[MEM_AVOID_BOOTPARAMS].start = (unsigned long)boot_params_ptr; + mem_avoid[MEM_AVOID_BOOTPARAMS].size = sizeof(*boot_params_ptr); /* We don't need to set a mapping for setup_data. */ @@ -447,7 +447,7 @@ static bool mem_avoid_overlap(struct mem_vector *img, } /* Avoid all entries in the setup_data linked list. */ - ptr = (struct setup_data *)(unsigned long)boot_params->hdr.setup_data; + ptr = (struct setup_data *)(unsigned long)boot_params_ptr->hdr.setup_data; while (ptr) { struct mem_vector avoid; @@ -706,7 +706,7 @@ static inline bool memory_type_is_free(efi_memory_desc_t *md) static bool process_efi_entries(unsigned long minimum, unsigned long image_size) { - struct efi_info *e = &boot_params->efi_info; + struct efi_info *e = &boot_params_ptr->efi_info; bool efi_mirror_found = false; struct mem_vector region; efi_memory_desc_t *md; @@ -777,8 +777,8 @@ static void process_e820_entries(unsigned long minimum, struct boot_e820_entry *entry; /* Verify potential e820 positions, appending to slots list. */ - for (i = 0; i < boot_params->e820_entries; i++) { - entry = &boot_params->e820_table[i]; + for (i = 0; i < boot_params_ptr->e820_entries; i++) { + entry = &boot_params_ptr->e820_table[i]; /* Skip non-RAM entries. */ if (entry->type != E820_TYPE_RAM) continue; @@ -852,7 +852,7 @@ void choose_random_location(unsigned long input, return; } - boot_params->hdr.loadflags |= KASLR_FLAG; + boot_params_ptr->hdr.loadflags |= KASLR_FLAG; if (IS_ENABLED(CONFIG_X86_32)) mem_limit = KERNEL_IMAGE_SIZE; diff --git a/arch/x86/boot/compressed/mem.c b/arch/x86/boot/compressed/mem.c index 3c1609245f2a..b3c3a4be7471 100644 --- a/arch/x86/boot/compressed/mem.c +++ b/arch/x86/boot/compressed/mem.c @@ -54,17 +54,17 @@ bool init_unaccepted_memory(void) enum efi_type et; int ret; - et = efi_get_type(boot_params); + et = efi_get_type(boot_params_ptr); if (et == EFI_TYPE_NONE) return false; - ret = efi_get_conf_table(boot_params, &cfg_table_pa, &cfg_table_len); + ret = efi_get_conf_table(boot_params_ptr, &cfg_table_pa, &cfg_table_len); if (ret) { warn("EFI config table not found."); return false; } - table = (void *)efi_find_vendor_table(boot_params, cfg_table_pa, + table = (void *)efi_find_vendor_table(boot_params_ptr, cfg_table_pa, cfg_table_len, guid); if (!table) return false; diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c index f711f2a85862..b99e08e6815b 100644 --- a/arch/x86/boot/compressed/misc.c +++ b/arch/x86/boot/compressed/misc.c @@ -46,7 +46,7 @@ void *memmove(void *dest, const void *src, size_t n); /* * This is set up by the setup-routine at boot-time */ -struct boot_params *boot_params; +struct boot_params *boot_params_ptr; struct port_io_ops pio_ops; @@ -132,8 +132,8 @@ void __putstr(const char *s) if (lines == 0 || cols == 0) return; - x = boot_params->screen_info.orig_x; - y = boot_params->screen_info.orig_y; + x = boot_params_ptr->screen_info.orig_x; + y = boot_params_ptr->screen_info.orig_y; while ((c = *s++) != '\0') { if (c == '\n') { @@ -154,8 +154,8 @@ void __putstr(const char *s) } } - boot_params->screen_info.orig_x = x; - boot_params->screen_info.orig_y = y; + boot_params_ptr->screen_info.orig_x = x; + boot_params_ptr->screen_info.orig_y = y; pos = (x + cols * y) * 2; /* Update cursor position */ outb(14, vidport); @@ -382,14 +382,14 @@ asmlinkage __visible void *extract_kernel(void *rmode, unsigned char *output) size_t entry_offset; /* Retain x86 boot parameters pointer passed from startup_32/64. */ - boot_params = rmode; + boot_params_ptr = rmode; /* Clear flags intended for solely in-kernel use. */ - boot_params->hdr.loadflags &= ~KASLR_FLAG; + boot_params_ptr->hdr.loadflags &= ~KASLR_FLAG; - sanitize_boot_params(boot_params); + sanitize_boot_params(boot_params_ptr); - if (boot_params->screen_info.orig_video_mode == 7) { + if (boot_params_ptr->screen_info.orig_video_mode == 7) { vidmem = (char *) 0xb0000; vidport = 0x3b4; } else { @@ -397,8 +397,8 @@ asmlinkage __visible void *extract_kernel(void *rmode, unsigned char *output) vidport = 0x3d4; } - lines = boot_params->screen_info.orig_video_lines; - cols = boot_params->screen_info.orig_video_cols; + lines = boot_params_ptr->screen_info.orig_video_lines; + cols = boot_params_ptr->screen_info.orig_video_cols; init_default_io_ops(); @@ -417,7 +417,7 @@ asmlinkage __visible void *extract_kernel(void *rmode, unsigned char *output) * so that early debugging output from the RSDP parsing code can be * collected. */ - boot_params->acpi_rsdp_addr = get_rsdp_addr(); + boot_params_ptr->acpi_rsdp_addr = get_rsdp_addr(); debug_putstr("early console in extract_kernel\n"); diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h index cc70d3fb9049..c0d502bd8716 100644 --- a/arch/x86/boot/compressed/misc.h +++ b/arch/x86/boot/compressed/misc.h @@ -61,7 +61,6 @@ extern memptr free_mem_ptr; extern memptr free_mem_end_ptr; void *malloc(int size); void free(void *where); -extern struct boot_params *boot_params; void __putstr(const char *s); void __puthex(unsigned long value); #define error_putstr(__x) __putstr(__x) diff --git a/arch/x86/boot/compressed/pgtable_64.c b/arch/x86/boot/compressed/pgtable_64.c index 7939eb6e6ce9..51f957b24ba7 100644 --- a/arch/x86/boot/compressed/pgtable_64.c +++ b/arch/x86/boot/compressed/pgtable_64.c @@ -28,7 +28,6 @@ static char trampoline_save[TRAMPOLINE_32BIT_SIZE]; */ unsigned long *trampoline_32bit __section(".data"); -extern struct boot_params *boot_params; int cmdline_find_option_bool(const char *option); static unsigned long find_trampoline_placement(void) @@ -49,7 +48,7 @@ static unsigned long find_trampoline_placement(void) * * Only look for values in the legacy ROM for non-EFI system. */ - signature = (char *)&boot_params->efi_info.efi_loader_signature; + signature = (char *)&boot_params_ptr->efi_info.efi_loader_signature; if (strncmp(signature, EFI32_LOADER_SIGNATURE, 4) && strncmp(signature, EFI64_LOADER_SIGNATURE, 4)) { ebda_start = *(unsigned short *)0x40e << 4; @@ -65,10 +64,10 @@ static unsigned long find_trampoline_placement(void) bios_start = round_down(bios_start, PAGE_SIZE); /* Find the first usable memory region under bios_start. */ - for (i = boot_params->e820_entries - 1; i >= 0; i--) { + for (i = boot_params_ptr->e820_entries - 1; i >= 0; i--) { unsigned long new = bios_start; - entry = &boot_params->e820_table[i]; + entry = &boot_params_ptr->e820_table[i]; /* Skip all entries above bios_start. */ if (bios_start <= entry->addr) @@ -107,7 +106,7 @@ asmlinkage void configure_5level_paging(struct boot_params *bp, void *pgtable) bool l5_required = false; /* Initialize boot_params. Required for cmdline_find_option_bool(). */ - boot_params = bp; + boot_params_ptr = bp; /* * Check if LA57 is desired and supported. diff --git a/arch/x86/boot/compressed/sev.c b/arch/x86/boot/compressed/sev.c index dc8c876fbd8f..9c075b526de4 100644 --- a/arch/x86/boot/compressed/sev.c +++ b/arch/x86/boot/compressed/sev.c @@ -605,7 +605,7 @@ void sev_prep_identity_maps(unsigned long top_level_pgt) * accessed after switchover. */ if (sev_snp_enabled()) { - unsigned long cc_info_pa = boot_params->cc_blob_address; + unsigned long cc_info_pa = boot_params_ptr->cc_blob_address; struct cc_blob_sev_info *cc_info; kernel_add_identity_map(cc_info_pa, cc_info_pa + sizeof(*cc_info)); diff --git a/arch/x86/include/asm/boot.h b/arch/x86/include/asm/boot.h index 4ae14339cb8c..74d5a1723d2d 100644 --- a/arch/x86/include/asm/boot.h +++ b/arch/x86/include/asm/boot.h @@ -68,6 +68,8 @@ extern const unsigned long kernel_total_size; unsigned long decompress_kernel(unsigned char *outbuf, unsigned long virt_addr, void (*error)(char *x)); + +extern struct boot_params *boot_params_ptr; #endif #endif /* _ASM_X86_BOOT_H */ From 50dcc2e0d62e3c4a54f39673c4dc3dcde7c74d52 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Tue, 17 Oct 2023 15:25:13 +0200 Subject: [PATCH 23/23] x86/boot: efistub: Assign global boot_params variable Now that the x86 EFI stub calls into some APIs exposed by the decompressor (e.g., kaslr_get_random_long()), it is necessary to ensure that the global boot_params variable is set correctly before doing so. Signed-off-by: Ard Biesheuvel Signed-off-by: Ingo Molnar Cc: linux-kernel@vger.kernel.org --- drivers/firmware/efi/libstub/x86-stub.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/firmware/efi/libstub/x86-stub.c b/drivers/firmware/efi/libstub/x86-stub.c index 3bfc59637dd1..76cc0d08e68a 100644 --- a/drivers/firmware/efi/libstub/x86-stub.c +++ b/drivers/firmware/efi/libstub/x86-stub.c @@ -818,6 +818,8 @@ void __noreturn efi_stub_entry(efi_handle_t handle, unsigned long kernel_entry; efi_status_t status; + boot_params_ptr = boot_params; + efi_system_table = sys_table_arg; /* Check if we were booted by the EFI firmware */ if (efi_system_table->hdr.signature != EFI_SYSTEM_TABLE_SIGNATURE)