diff options
61 files changed, 1429 insertions, 942 deletions
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 363e348bff9..da0e0773ca9 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -594,6 +594,9 @@ bytes respectively. Such letter suffixes can also be entirely omitted. is selected automatically. Check Documentation/kdump/kdump.txt for further details. + crashkernel_low=size[KMG] + [KNL, x86] parts under 4G. + crashkernel=range1:size1[,range2:size2,...][@offset] [KNL] Same as above, but depends on the memory in the running system. The syntax of range is diff --git a/Documentation/x86/boot.txt b/Documentation/x86/boot.txt index 406d82d5d2b..0e383169839 100644 --- a/Documentation/x86/boot.txt +++ b/Documentation/x86/boot.txt @@ -57,6 +57,10 @@ Protocol 2.10: (Kernel 2.6.31) Added a protocol for relaxed alignment 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 @@ -182,7 +186,7 @@ Offset Proto Name Meaning 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 @@ -582,6 +586,27 @@ Protocol: 2.10+ 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 Offset/size: 0x238/4 @@ -1029,6 +1054,44 @@ must have read/write permission; CS must be __BOOT_CS and DS, ES, SS must be __BOOT_DS; interrupt must be disabled; %esi must hold the base address of the struct boot_params; %ebp, %edi and %ebx must be zero. +**** 64-bit BOOT PROTOCOL + +For machine with 64bit cpus and 64bit kernel, we could use 64bit bootloader +and we need a 64-bit boot protocol. + +In 64-bit boot protocol, the first step in loading a Linux kernel +should be to setup the boot parameters (struct boot_params, +traditionally known as "zero page"). The memory for struct boot_params +could be allocated anywhere (even above 4G) and initialized to all zero. +Then, the setup header at offset 0x01f1 of kernel image on should be +loaded into struct boot_params and examined. The end of setup header +can be calculated as follows: + + 0x0202 + byte value at offset 0x0201 + +In addition to read/modify/write the setup header of the struct +boot_params as that of 16-bit boot protocol, the boot loader should +also fill the additional fields of the struct boot_params as described +in zero-page.txt. + +After setting up the struct boot_params, the boot loader can load +64-bit kernel in the same way as that of 16-bit boot protocol, but +kernel could be loaded above 4G. + +In 64-bit boot protocol, the kernel is started by jumping to the +64-bit kernel entry point, which is the start address of loaded +64-bit kernel plus 0x200. + +At entry, the CPU must be in 64-bit mode with paging enabled. +The range with setup_header.init_size from start address of loaded +kernel and zero page and command line buffer get ident mapping; +a GDT must be loaded with the descriptors for selectors +__BOOT_CS(0x10) and __BOOT_DS(0x18); both descriptors must be 4G flat +segment; __BOOT_CS must have execute/read permission, and __BOOT_DS +must have read/write permission; CS must be __BOOT_CS and DS, ES, SS +must be __BOOT_DS; interrupt must be disabled; %rsi must hold the base +address of the struct boot_params. + **** EFI HANDOVER PROTOCOL This protocol allows boot loaders to defer initialisation to the EFI diff --git a/Documentation/x86/zero-page.txt b/Documentation/x86/zero-page.txt index cf5437deda8..199f453cb4d 100644 --- a/Documentation/x86/zero-page.txt +++ b/Documentation/x86/zero-page.txt @@ -19,6 +19,9 @@ Offset Proto Name Meaning 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 @@ -27,6 +30,7 @@ Offset Proto Name Meaning 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) diff --git a/arch/mips/cavium-octeon/dma-octeon.c b/arch/mips/cavium-octeon/dma-octeon.c index 41dd0088497..02f24447520 100644 --- a/arch/mips/cavium-octeon/dma-octeon.c +++ b/arch/mips/cavium-octeon/dma-octeon.c @@ -317,7 +317,8 @@ void __init plat_swiotlb_setup(void) octeon_swiotlb = alloc_bootmem_low_pages(swiotlbsize); - swiotlb_init_with_tbl(octeon_swiotlb, swiotlb_nslabs, 1); + if (swiotlb_init_with_tbl(octeon_swiotlb, swiotlb_nslabs, 1) == -ENOMEM) + panic("Cannot allocate SWIOTLB buffer"); mips_dma_map_ops = &octeon_linear_dma_map_ops.dma_map_ops; } diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c index c3b72423c84..fc5a7c4bd9e 100644 --- a/arch/sparc/mm/init_64.c +++ b/arch/sparc/mm/init_64.c @@ -2021,6 +2021,16 @@ static void __init patch_tlb_miss_handler_bitmap(void) flushi(&valid_addr_bitmap_insn[0]); } +static void __init register_page_bootmem_info(void) +{ +#ifdef CONFIG_NEED_MULTIPLE_NODES + int i; + + for_each_online_node(i) + if (NODE_DATA(i)->node_spanned_pages) + register_page_bootmem_info_node(NODE_DATA(i)); +#endif +} void __init mem_init(void) { unsigned long codepages, datapages, initpages; @@ -2038,20 +2048,8 @@ void __init mem_init(void) high_memory = __va(last_valid_pfn << PAGE_SHIFT); -#ifdef CONFIG_NEED_MULTIPLE_NODES - { - int i; - for_each_online_node(i) { - if (NODE_DATA(i)->node_spanned_pages != 0) { - totalram_pages += - free_all_bootmem_node(NODE_DATA(i)); - } - } - totalram_pages += free_low_memory_core_early(MAX_NUMNODES); - } -#else + register_page_bootmem_info(); totalram_pages = free_all_bootmem(); -#endif /* We subtract one to account for the mem_map_zero page * allocated below. diff --git a/arch/x86/boot/boot.h b/arch/x86/boot/boot.h index 18997e5a105..5b7531966b8 100644 --- a/arch/x86/boot/boot.h +++ b/arch/x86/boot/boot.h @@ -285,16 +285,26 @@ struct biosregs { void intcall(u8 int_no, const struct biosregs *ireg, struct biosregs *oreg); /* cmdline.c */ -int __cmdline_find_option(u32 cmdline_ptr, const char *option, char *buffer, int bufsize); -int __cmdline_find_option_bool(u32 cmdline_ptr, const char *option); +int __cmdline_find_option(unsigned long cmdline_ptr, const char *option, char *buffer, int bufsize); +int __cmdline_find_option_bool(unsigned long cmdline_ptr, const char *option); static inline int cmdline_find_option(const char *option, char *buffer, int bufsize) { - return __cmdline_find_option(boot_params.hdr.cmd_line_ptr, option, buffer, bufsize); + unsigned long cmd_line_ptr = boot_params.hdr.cmd_line_ptr; + + if (cmd_line_ptr >= 0x100000) + return -1; /* inaccessible */ + + return __cmdline_find_option(cmd_line_ptr, option, buffer, bufsize); } static inline int cmdline_find_option_bool(const char *option) { - return __cmdline_find_option_bool(boot_params.hdr.cmd_line_ptr, option); + unsigned long cmd_line_ptr = boot_params.hdr.cmd_line_ptr; + + if (cmd_line_ptr >= 0x100000) + return -1; /* inaccessible */ + + return __cmdline_find_option_bool(cmd_line_ptr, option); } diff --git a/arch/x86/boot/cmdline.c b/arch/x86/boot/cmdline.c index 6b3b6f708c0..625d21b0cd3 100644 --- a/arch/x86/boot/cmdline.c +++ b/arch/x86/boot/cmdline.c @@ -27,7 +27,7 @@ static inline int myisspace(u8 c) * Returns the length of the argument (regardless of if it was * truncated to fit in the buffer), or -1 on not found. */ -int __cmdline_find_option(u32 cmdline_ptr, const char *option, char *buffer, int bufsize) +int __cmdline_find_option(unsigned long cmdline_ptr, const char *option, char *buffer, int bufsize) { addr_t cptr; char c; @@ -41,8 +41,8 @@ int __cmdline_find_option(u32 cmdline_ptr, const char *option, char *buffer, int st_bufcpy /* Copying this to buffer */ } state = st_wordstart; - if (!cmdline_ptr || cmdline_ptr >= 0x100000) - return -1; /* No command line, or inaccessible */ + if (!cmdline_ptr) + return -1; /* No command line */ cptr = cmdline_ptr & 0xf; set_fs(cmdline_ptr >> 4); @@ -99,7 +99,7 @@ int __cmdline_find_option(u32 cmdline_ptr, const char *option, char *buffer, int * Returns the position of that option (starts counting with 1) * or 0 on not found */ -int __cmdline_find_option_bool(u32 cmdline_ptr, const char *option) +int __cmdline_find_option_bool(unsigned long cmdline_ptr, const char *option) { addr_t cptr; char c; @@ -111,8 +111,8 @@ int __cmdline_find_option_bool(u32 cmdline_ptr, const char *option) st_wordskip, /* Miscompare, skip */ } state = st_wordstart; - if (!cmdline_ptr || cmdline_ptr >= 0x100000) - return -1; /* No command line, or inaccessible */ + if (!cmdline_ptr) + return -1; /* No command line */ cptr = cmdline_ptr & 0xf; set_fs(cmdline_ptr >> 4); diff --git a/arch/x86/boot/compressed/cmdline.c b/arch/x86/boot/compressed/cmdline.c index 10f6b1178c6..bffd73b45b1 100644 --- a/arch/x86/boot/compressed/cmdline.c +++ b/arch/x86/boot/compressed/cmdline.c @@ -13,13 +13,21 @@ static inline char rdfs8(addr_t addr) return *((char *)(fs + addr)); } #include "../cmdline.c" +static unsigned long get_cmd_line_ptr(void) +{ + unsigned long cmd_line_ptr = real_mode->hdr.cmd_line_ptr; + + cmd_line_ptr |= (u64)real_mode->ext_cmd_line_ptr << 32; + + return cmd_line_ptr; +} int cmdline_find_option(const char *option, char *buffer, int bufsize) { - return __cmdline_find_option(real_mode->hdr.cmd_line_ptr, option, buffer, bufsize); + return __cmdline_find_option(get_cmd_line_ptr(), option, buffer, bufsize); } int cmdline_find_option_bool(const char *option) { - return __cmdline_find_option_bool(real_mode->hdr.cmd_line_ptr, option); + return __cmdline_find_option_bool(get_cmd_line_ptr(), option); } #endif diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S index 2c4b171eec3..d9ae9a4ffcb 100644 --- a/arch/x86/boot/compressed/head_64.S +++ b/arch/x86/boot/compressed/head_64.S @@ -37,6 +37,12 @@ __HEAD .code32 ENTRY(startup_32) + /* + * 32bit entry is 0 and it is ABI so immutable! + * If we come here directly from a bootloader, + * kernel(text+data+bss+brk) ramdisk, zero_page, command line + * all need to be under the 4G limit. + */ cld /* * Test KEEP_SEGMENTS flag to see if the bootloader is asking @@ -154,6 +160,12 @@ ENTRY(startup_32) btsl $_EFER_LME, %eax wrmsr + /* After gdt is loaded */ + xorl %eax, %eax + lldt %ax + movl $0x20, %eax + ltr %ax + /* * Setup for the jump to 64bit mode * @@ -176,28 +188,18 @@ ENTRY(startup_32) lret ENDPROC(startup_32) -no_longmode: - /* This isn't an x86-64 CPU so hang */ -1: - hlt - jmp 1b - -#include "../../kernel/verify_cpu.S" - - /* - * Be careful here startup_64 needs to be at a predictable - * address so I can export it in an ELF header. Bootloaders - * should look at the ELF header to find this address, as - * it may change in the future. - */ .code64 .org 0x200 ENTRY(startup_64) /* + * 64bit entry is 0x200 and it is ABI so immutable! * We come here either from startup_32 or directly from a - * 64bit bootloader. If we come here from a bootloader we depend on - * an identity mapped page table being provied that maps our - * entire text+data+bss and hopefully all of memory. + * 64bit bootloader. + * If we come here from a bootloader, kernel(text+data+bss+brk), + * ramdisk, zero_page, command line could be above 4G. + * We depend on an identity mapped page table being provided + * that maps our entire kernel(text+data+bss+brk), zero page + * and command line. */ #ifdef CONFIG_EFI_STUB /* @@ -247,9 +249,6 @@ preferred_addr: movl %eax, %ss movl %eax, %fs movl %eax, %gs - lldt %ax - movl $0x20, %eax - ltr %ax /* * Compute the decompressed kernel start address. It is where @@ -349,6 +348,15 @@ relocated: */ jmp *%rbp + .code32 +no_longmode: + /* This isn't an x86-64 CPU so hang */ +1: + hlt + jmp 1b + +#include "../../kernel/verify_cpu.S" + .data gdt: .word gdt_end - gdt diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c index 88f7ff6da40..7cb56c6ca35 100644 --- a/arch/x86/boot/compressed/misc.c +++ b/arch/x86/boot/compressed/misc.c @@ -325,6 +325,8 @@ asmlinkage void decompress_kernel(void *rmode, memptr heap, { real_mode = rmode; + sanitize_boot_params(real_mode); + if (real_mode->screen_info.orig_video_mode == 7) { vidmem = (char *) 0xb0000; vidport = 0x3b4; diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h index 0e6dc0ee0ee..674019d8e23 100644 --- a/arch/x86/boot/compressed/misc.h +++ b/arch/x86/boot/compressed/misc.h @@ -18,6 +18,7 @@ #include <asm/page.h> #include <asm/boot.h> #include <asm/bootparam.h> +#include <asm/bootparam_utils.h> #define BOOT_BOOT_H #include "../ctype.h" diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S index 8c132a625b9..9ec06a1f6d6 100644 --- a/arch/x86/boot/header.S +++ b/arch/x86/boot/header.S @@ -21,6 +21,7 @@ #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" @@ -255,6 +256,9 @@ section_table: # 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 */ @@ -279,7 +283,7 @@ _start: # 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 @@ -297,13 +301,7 @@ type_of_loader: .byte 0 # 0 means ancient bootloader, newer # 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 @@ -369,7 +367,31 @@ relocatable_kernel: .byte 1 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 + +#if defined(CONFIG_RELOCATABLE) && defined(CONFIG_X86_64) + /* kernel/boot_param/ramdisk could be loaded above 4g */ +# define XLF1 XLF_CAN_BE_LOADED_ABOVE_4G +#else +# define XLF1 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 | XLF1 | XLF23 cmdline_size: .long COMMAND_LINE_SIZE-1 #length of the command line, #added with boot protocol @@ -397,8 +419,13 @@ pref_address: .quad LOAD_PHYSICAL_ADDR # preferred load addr #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 ##################################################### diff --git a/arch/x86/boot/setup.ld b/arch/x86/boot/setup.ld index 03c0683636b..96a6c756353 100644 --- a/arch/x86/boot/setup.ld +++ b/arch/x86/boot/setup.ld @@ -13,7 +13,7 @@ SECTIONS .bstext : { *(.bstext) } .bsdata : { *(.bsdata) } - . = 497; + . = 495; .header : { *(.header) } .entrytext : { *(.entrytext) } .inittext : { *(.inittext) } diff --git a/arch/x86/include/asm/bootparam_utils.h b/arch/x86/include/asm/bootparam_utils.h new file mode 100644 index 00000000000..5b5e9cb774b --- /dev/null +++ b/arch/x86/include/asm/bootparam_utils.h @@ -0,0 +1,38 @@ +#ifndef _ASM_X86_BOOTPARAM_UTILS_H +#define _ASM_X86_BOOTPARAM_UTILS_H + +#include <asm/bootparam.h> + +/* + * This file is included from multiple environments. Do not + * add completing #includes to make it standalone. + */ + +/* + * Deal with bootloaders which fail to initialize unknown fields in + * boot_params to zero. The list fields in this list are taken from + * analysis of kexec-tools; if other broken bootloaders initialize a + * different set of fields we will need to figure out how to disambiguate. + * + */ +static void sanitize_boot_params(struct boot_params *boot_params) +{ + if (boot_params->sentinel) { + /*fields in boot_params are not valid, clear them */ + memset(&boot_params->olpc_ofw_header, 0, + (char *)&boot_params->alt_mem_k - + (char *)&boot_params->olpc_ofw_header); + memset(&boot_params->kbd_status, 0, + (char *)&boot_params->hdr - + (char *)&boot_params->kbd_status); + memset(&boot_params->_pad7[0], 0, + (char *)&boot_params->edd_mbr_sig_buffer[0] - + (char *)&boot_params->_pad7[0]); + memset(&boot_params->_pad8[0], 0, + (char *)&boot_params->eddbuf[0] - + (char *)&boot_params->_pad8[0]); + memset(&boot_params->_pad9[0], 0, sizeof(boot_params->_pad9)); + } +} + +#endif /* _ASM_X86_BOOTPARAM_UTILS_H */ diff --git a/arch/x86/include/asm/init.h b/arch/x86/include/asm/init.h index adcc0ae73d0..223042086f4 100644 --- a/arch/x86/include/asm/init.h +++ b/arch/x86/include/asm/init.h @@ -1,20 +1,14 @@ -#ifndef _ASM_X86_INIT_32_H -#define _ASM_X86_INIT_32_H +#ifndef _ASM_X86_INIT_H +#define _ASM_X86_INIT_H -#ifdef CONFIG_X86_32 -extern void __init early_ioremap_page_table_range_init(void); -#endif +struct x86_mapping_info { + void *(*alloc_pgt_page)(void *); /* allocate buf for page table */ + void *cont |