Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1759306Ab3D3IJa (ORCPT ); Tue, 30 Apr 2013 04:09:30 -0400 Received: from mail-bk0-f51.google.com ([209.85.214.51]:48786 "EHLO mail-bk0-f51.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1759171Ab3D3IJZ (ORCPT ); Tue, 30 Apr 2013 04:09:25 -0400 Date: Tue, 30 Apr 2013 10:09:20 +0200 From: Ingo Molnar To: Linus Torvalds Cc: linux-kernel@vger.kernel.org, "H. Peter Anvin" , Thomas Gleixner , Andrew Morton Subject: [GIT PULL] x86 KASLR changes for v3.10 Message-ID: <20130430080920.GA21638@gmail.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline User-Agent: Mutt/1.5.21 (2010-09-15) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 38612 Lines: 1396 Linus, Please pull the latest x86-kaslr-for-linus git tree from: git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86-kaslr-for-linus HEAD: c889ba801dc3b3a0155fa77d567f2c3a6097de1c x86, relocs: Refactor the relocs tool to merge 32- and 64-bit ELF This merge contains changes from the ongoing KASLR work, by Kees Cook. The main changes are the use of a read-only IDT on x86 (which decouples the userspace visible virtual IDT address from the physical address), and a rework of ELF relocation support, in preparation of random, boot-time kernel image relocation. Thanks, Ingo ------------------> H. Peter Anvin (1): x86, relocs: Refactor the relocs tool to merge 32- and 64-bit ELF Kees Cook (5): x86: Use a read-only IDT alias on all CPUs x86, relocs: Generalize ELF structure names x86, relocs: Consolidate processing logic x86, relocs: Add 64-bit ELF support to relocs tool x86, relocs: Build separate 32/64-bit tools arch/x86/include/asm/fixmap.h | 4 +- arch/x86/kernel/cpu/intel.c | 18 +- arch/x86/kernel/traps.c | 9 + arch/x86/tools/Makefile | 1 + arch/x86/tools/relocs.c | 783 ++++++++++++++++++++++++++--------------- arch/x86/tools/relocs.h | 36 ++ arch/x86/tools/relocs_32.c | 17 + arch/x86/tools/relocs_64.c | 17 + arch/x86/tools/relocs_common.c | 76 ++++ arch/x86/xen/mmu.c | 4 +- 10 files changed, 660 insertions(+), 305 deletions(-) create mode 100644 arch/x86/tools/relocs.h create mode 100644 arch/x86/tools/relocs_32.c create mode 100644 arch/x86/tools/relocs_64.c create mode 100644 arch/x86/tools/relocs_common.c diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h index a09c285..51b9e32 100644 --- a/arch/x86/include/asm/fixmap.h +++ b/arch/x86/include/asm/fixmap.h @@ -104,9 +104,7 @@ enum fixed_addresses { FIX_LI_PCIA, /* Lithium PCI Bridge A */ FIX_LI_PCIB, /* Lithium PCI Bridge B */ #endif -#ifdef CONFIG_X86_F00F_BUG - FIX_F00F_IDT, /* Virtual mapping for IDT */ -#endif + FIX_RO_IDT, /* Virtual mapping for read-only IDT */ #ifdef CONFIG_X86_CYCLONE_TIMER FIX_CYCLONE_TIMER, /*cyclone timer register*/ #endif diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 1905ce9..7170024 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -164,20 +164,6 @@ int __cpuinit ppro_with_ram_bug(void) return 0; } -#ifdef CONFIG_X86_F00F_BUG -static void __cpuinit trap_init_f00f_bug(void) -{ - __set_fixmap(FIX_F00F_IDT, __pa_symbol(idt_table), PAGE_KERNEL_RO); - - /* - * Update the IDT descriptor and reload the IDT so that - * it uses the read-only mapped virtual address. - */ - idt_descr.address = fix_to_virt(FIX_F00F_IDT); - load_idt(&idt_descr); -} -#endif - static void __cpuinit intel_smp_check(struct cpuinfo_x86 *c) { /* calling is from identify_secondary_cpu() ? */ @@ -206,8 +192,7 @@ static void __cpuinit intel_workarounds(struct cpuinfo_x86 *c) /* * All current models of Pentium and Pentium with MMX technology CPUs * have the F0 0F bug, which lets nonprivileged users lock up the - * system. - * Note that the workaround only should be initialized once... + * system. Announce that the fault handler will be checking for it. */ c->f00f_bug = 0; if (!paravirt_enabled() && c->x86 == 5) { @@ -215,7 +200,6 @@ static void __cpuinit intel_workarounds(struct cpuinfo_x86 *c) c->f00f_bug = 1; if (!f00f_workaround_enabled) { - trap_init_f00f_bug(); printk(KERN_NOTICE "Intel Pentium with F0 0F bug - workaround enabled.\n"); f00f_workaround_enabled = 1; } diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 68bda7a..10e2446 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -56,6 +56,7 @@ #include #include #include +#include #include @@ -753,6 +754,14 @@ void __init trap_init(void) #endif /* + * Set the IDT descriptor to a fixed read-only location, so that the + * "sidt" instruction will not leak the location of the kernel, and + * to defend the IDT against arbitrary memory write vulnerabilities. + * It will be reloaded in cpu_init() */ + __set_fixmap(FIX_RO_IDT, __pa_symbol(idt_table), PAGE_KERNEL_RO); + idt_descr.address = fix_to_virt(FIX_RO_IDT); + + /* * Should be a barrier for any external CPU state: */ cpu_init(); diff --git a/arch/x86/tools/Makefile b/arch/x86/tools/Makefile index bae601f..e812034 100644 --- a/arch/x86/tools/Makefile +++ b/arch/x86/tools/Makefile @@ -39,4 +39,5 @@ $(obj)/insn_sanity.o: $(srctree)/arch/x86/lib/insn.c $(srctree)/arch/x86/lib/ina HOST_EXTRACFLAGS += -I$(srctree)/tools/include hostprogs-y += relocs +relocs-objs := relocs_32.o relocs_64.o relocs_common.o relocs: $(obj)/relocs diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c index 79d67bd..590be10 100644 --- a/arch/x86/tools/relocs.c +++ b/arch/x86/tools/relocs.c @@ -1,43 +1,36 @@ -#include -#include -#include -#include -#include -#include -#include -#include -#include -#define USE_BSD -#include -#include -#include - -static void die(char *fmt, ...); - -#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) -static Elf32_Ehdr ehdr; -static unsigned long reloc_count, reloc_idx; -static unsigned long *relocs; -static unsigned long reloc16_count, reloc16_idx; -static unsigned long *relocs16; +/* This is included from relocs_32/64.c */ + +#define ElfW(type) _ElfW(ELF_BITS, type) +#define _ElfW(bits, type) __ElfW(bits, type) +#define __ElfW(bits, type) Elf##bits##_##type + +#define Elf_Addr ElfW(Addr) +#define Elf_Ehdr ElfW(Ehdr) +#define Elf_Phdr ElfW(Phdr) +#define Elf_Shdr ElfW(Shdr) +#define Elf_Sym ElfW(Sym) + +static Elf_Ehdr ehdr; + +struct relocs { + uint32_t *offset; + unsigned long count; + unsigned long size; +}; + +static struct relocs relocs16; +static struct relocs relocs32; +static struct relocs relocs64; struct section { - Elf32_Shdr shdr; + Elf_Shdr shdr; struct section *link; - Elf32_Sym *symtab; - Elf32_Rel *reltab; + Elf_Sym *symtab; + Elf_Rel *reltab; char *strtab; }; static struct section *secs; -enum symtype { - S_ABS, - S_REL, - S_SEG, - S_LIN, - S_NSYMTYPES -}; - static const char * const sym_regex_kernel[S_NSYMTYPES] = { /* * Following symbols have been audited. There values are constant and do @@ -49,6 +42,9 @@ static const char * const sym_regex_kernel[S_NSYMTYPES] = { "^(xen_irq_disable_direct_reloc$|" "xen_save_fl_direct_reloc$|" "VDSO|" +#if ELF_BITS == 64 + "__vvar_page|" +#endif "__crc_)", /* @@ -72,6 +68,11 @@ static const char * const sym_regex_kernel[S_NSYMTYPES] = { "__end_rodata|" "__initramfs_start|" "(jiffies|jiffies_64)|" +#if ELF_BITS == 64 + "__per_cpu_load|" + "init_per_cpu__.*|" + "__end_rodata_hpage_align|" +#endif "_end)$" }; @@ -132,15 +133,6 @@ static void regex_init(int use_real_mode) } } -static void die(char *fmt, ...) -{ - va_list ap; - va_start(ap, fmt); - vfprintf(stderr, fmt, ap); - va_end(ap); - exit(1); -} - static const char *sym_type(unsigned type) { static const char *type_name[] = { @@ -198,6 +190,24 @@ static const char *rel_type(unsigned type) { static const char *type_name[] = { #define REL_TYPE(X) [X] = #X +#if ELF_BITS == 64 + REL_TYPE(R_X86_64_NONE), + REL_TYPE(R_X86_64_64), + REL_TYPE(R_X86_64_PC32), + REL_TYPE(R_X86_64_GOT32), + REL_TYPE(R_X86_64_PLT32), + REL_TYPE(R_X86_64_COPY), + REL_TYPE(R_X86_64_GLOB_DAT), + REL_TYPE(R_X86_64_JUMP_SLOT), + REL_TYPE(R_X86_64_RELATIVE), + REL_TYPE(R_X86_64_GOTPCREL), + REL_TYPE(R_X86_64_32), + REL_TYPE(R_X86_64_32S), + REL_TYPE(R_X86_64_16), + REL_TYPE(R_X86_64_PC16), + REL_TYPE(R_X86_64_8), + REL_TYPE(R_X86_64_PC8), +#else REL_TYPE(R_386_NONE), REL_TYPE(R_386_32), REL_TYPE(R_386_PC32), @@ -213,6 +223,7 @@ static const char *rel_type(unsigned type) REL_TYPE(R_386_PC8), REL_TYPE(R_386_16), REL_TYPE(R_386_PC16), +#endif #undef REL_TYPE }; const char *name = "unknown type rel type name"; @@ -240,7 +251,7 @@ static const char *sec_name(unsigned shndx) return name; } -static const char *sym_name(const char *sym_strtab, Elf32_Sym *sym) +static const char *sym_name(const char *sym_strtab, Elf_Sym *sym) { const char *name; name = ""; @@ -253,15 +264,42 @@ static const char *sym_name(const char *sym_strtab, Elf32_Sym *sym) return name; } +static Elf_Sym *sym_lookup(const char *symname) +{ + int i; + for (i = 0; i < ehdr.e_shnum; i++) { + struct section *sec = &secs[i]; + long nsyms; + char *strtab; + Elf_Sym *symtab; + Elf_Sym *sym; + + if (sec->shdr.sh_type != SHT_SYMTAB) + continue; + nsyms = sec->shdr.sh_size/sizeof(Elf_Sym); + symtab = sec->symtab; + strtab = sec->link->strtab; + + for (sym = symtab; --nsyms >= 0; sym++) { + if (!sym->st_name) + continue; + if (strcmp(symname, strtab + sym->st_name) == 0) + return sym; + } + } + return 0; +} #if BYTE_ORDER == LITTLE_ENDIAN #define le16_to_cpu(val) (val) #define le32_to_cpu(val) (val) +#define le64_to_cpu(val) (val) #endif #if BYTE_ORDER == BIG_ENDIAN #define le16_to_cpu(val) bswap_16(val) #define le32_to_cpu(val) bswap_32(val) +#define le64_to_cpu(val) bswap_64(val) #endif static uint16_t elf16_to_cpu(uint16_t val) @@ -274,6 +312,23 @@ static uint32_t elf32_to_cpu(uint32_t val) return le32_to_cpu(val); } +#define elf_half_to_cpu(x) elf16_to_cpu(x) +#define elf_word_to_cpu(x) elf32_to_cpu(x) + +#if ELF_BITS == 64 +static uint64_t elf64_to_cpu(uint64_t val) +{ + return le64_to_cpu(val); +} +#define elf_addr_to_cpu(x) elf64_to_cpu(x) +#define elf_off_to_cpu(x) elf64_to_cpu(x) +#define elf_xword_to_cpu(x) elf64_to_cpu(x) +#else +#define elf_addr_to_cpu(x) elf32_to_cpu(x) +#define elf_off_to_cpu(x) elf32_to_cpu(x) +#define elf_xword_to_cpu(x) elf32_to_cpu(x) +#endif + static void read_ehdr(FILE *fp) { if (fread(&ehdr, sizeof(ehdr), 1, fp) != 1) { @@ -283,8 +338,8 @@ static void read_ehdr(FILE *fp) if (memcmp(ehdr.e_ident, ELFMAG, SELFMAG) != 0) { die("No ELF magic\n"); } - if (ehdr.e_ident[EI_CLASS] != ELFCLASS32) { - die("Not a 32 bit executable\n"); + if (ehdr.e_ident[EI_CLASS] != ELF_CLASS) { + die("Not a %d bit executable\n", ELF_BITS); } if (ehdr.e_ident[EI_DATA] != ELFDATA2LSB) { die("Not a LSB ELF executable\n"); @@ -293,36 +348,36 @@ static void read_ehdr(FILE *fp) die("Unknown ELF version\n"); } /* Convert the fields to native endian */ - ehdr.e_type = elf16_to_cpu(ehdr.e_type); - ehdr.e_machine = elf16_to_cpu(ehdr.e_machine); - ehdr.e_version = elf32_to_cpu(ehdr.e_version); - ehdr.e_entry = elf32_to_cpu(ehdr.e_entry); - ehdr.e_phoff = elf32_to_cpu(ehdr.e_phoff); - ehdr.e_shoff = elf32_to_cpu(ehdr.e_shoff); - ehdr.e_flags = elf32_to_cpu(ehdr.e_flags); - ehdr.e_ehsize = elf16_to_cpu(ehdr.e_ehsize); - ehdr.e_phentsize = elf16_to_cpu(ehdr.e_phentsize); - ehdr.e_phnum = elf16_to_cpu(ehdr.e_phnum); - ehdr.e_shentsize = elf16_to_cpu(ehdr.e_shentsize); - ehdr.e_shnum = elf16_to_cpu(ehdr.e_shnum); - ehdr.e_shstrndx = elf16_to_cpu(ehdr.e_shstrndx); + ehdr.e_type = elf_half_to_cpu(ehdr.e_type); + ehdr.e_machine = elf_half_to_cpu(ehdr.e_machine); + ehdr.e_version = elf_word_to_cpu(ehdr.e_version); + ehdr.e_entry = elf_addr_to_cpu(ehdr.e_entry); + ehdr.e_phoff = elf_off_to_cpu(ehdr.e_phoff); + ehdr.e_shoff = elf_off_to_cpu(ehdr.e_shoff); + ehdr.e_flags = elf_word_to_cpu(ehdr.e_flags); + ehdr.e_ehsize = elf_half_to_cpu(ehdr.e_ehsize); + ehdr.e_phentsize = elf_half_to_cpu(ehdr.e_phentsize); + ehdr.e_phnum = elf_half_to_cpu(ehdr.e_phnum); + ehdr.e_shentsize = elf_half_to_cpu(ehdr.e_shentsize); + ehdr.e_shnum = elf_half_to_cpu(ehdr.e_shnum); + ehdr.e_shstrndx = elf_half_to_cpu(ehdr.e_shstrndx); if ((ehdr.e_type != ET_EXEC) && (ehdr.e_type != ET_DYN)) { die("Unsupported ELF header type\n"); } - if (ehdr.e_machine != EM_386) { - die("Not for x86\n"); + if (ehdr.e_machine != ELF_MACHINE) { + die("Not for %s\n", ELF_MACHINE_NAME); } if (ehdr.e_version != EV_CURRENT) { die("Unknown ELF version\n"); } - if (ehdr.e_ehsize != sizeof(Elf32_Ehdr)) { + if (ehdr.e_ehsize != sizeof(Elf_Ehdr)) { die("Bad Elf header size\n"); } - if (ehdr.e_phentsize != sizeof(Elf32_Phdr)) { + if (ehdr.e_phentsize != sizeof(Elf_Phdr)) { die("Bad program header entry\n"); } - if (ehdr.e_shentsize != sizeof(Elf32_Shdr)) { + if (ehdr.e_shentsize != sizeof(Elf_Shdr)) { die("Bad section header entry\n"); } if (ehdr.e_shstrndx >= ehdr.e_shnum) { @@ -333,7 +388,7 @@ static void read_ehdr(FILE *fp) static void read_shdrs(FILE *fp) { int i; - Elf32_Shdr shdr; + Elf_Shdr shdr; secs = calloc(ehdr.e_shnum, sizeof(struct section)); if (!secs) { @@ -349,16 +404,16 @@ static void read_shdrs(FILE *fp) if (fread(&shdr, sizeof shdr, 1, fp) != 1) die("Cannot read ELF section headers %d/%d: %s\n", i, ehdr.e_shnum, strerror(errno)); - sec->shdr.sh_name = elf32_to_cpu(shdr.sh_name); - sec->shdr.sh_type = elf32_to_cpu(shdr.sh_type); - sec->shdr.sh_flags = elf32_to_cpu(shdr.sh_flags); - sec->shdr.sh_addr = elf32_to_cpu(shdr.sh_addr); - sec->shdr.sh_offset = elf32_to_cpu(shdr.sh_offset); - sec->shdr.sh_size = elf32_to_cpu(shdr.sh_size); - sec->shdr.sh_link = elf32_to_cpu(shdr.sh_link); - sec->shdr.sh_info = elf32_to_cpu(shdr.sh_info); - sec->shdr.sh_addralign = elf32_to_cpu(shdr.sh_addralign); - sec->shdr.sh_entsize = elf32_to_cpu(shdr.sh_entsize); + sec->shdr.sh_name = elf_word_to_cpu(shdr.sh_name); + sec->shdr.sh_type = elf_word_to_cpu(shdr.sh_type); + sec->shdr.sh_flags = elf_xword_to_cpu(shdr.sh_flags); + sec->shdr.sh_addr = elf_addr_to_cpu(shdr.sh_addr); + sec->shdr.sh_offset = elf_off_to_cpu(shdr.sh_offset); + sec->shdr.sh_size = elf_xword_to_cpu(shdr.sh_size); + sec->shdr.sh_link = elf_word_to_cpu(shdr.sh_link); + sec->shdr.sh_info = elf_word_to_cpu(shdr.sh_info); + sec->shdr.sh_addralign = elf_xword_to_cpu(shdr.sh_addralign); + sec->shdr.sh_entsize = elf_xword_to_cpu(shdr.sh_entsize); if (sec->shdr.sh_link < ehdr.e_shnum) sec->link = &secs[sec->shdr.sh_link]; } @@ -412,12 +467,12 @@ static void read_symtabs(FILE *fp) die("Cannot read symbol table: %s\n", strerror(errno)); } - for (j = 0; j < sec->shdr.sh_size/sizeof(Elf32_Sym); j++) { - Elf32_Sym *sym = &sec->symtab[j]; - sym->st_name = elf32_to_cpu(sym->st_name); - sym->st_value = elf32_to_cpu(sym->st_value); - sym->st_size = elf32_to_cpu(sym->st_size); - sym->st_shndx = elf16_to_cpu(sym->st_shndx); + for (j = 0; j < sec->shdr.sh_size/sizeof(Elf_Sym); j++) { + Elf_Sym *sym = &sec->symtab[j]; + sym->st_name = elf_word_to_cpu(sym->st_name); + sym->st_value = elf_addr_to_cpu(sym->st_value); + sym->st_size = elf_xword_to_cpu(sym->st_size); + sym->st_shndx = elf_half_to_cpu(sym->st_shndx); } } } @@ -428,7 +483,7 @@ static void read_relocs(FILE *fp) int i,j; for (i = 0; i < ehdr.e_shnum; i++) { struct section *sec = &secs[i]; - if (sec->shdr.sh_type != SHT_REL) { + if (sec->shdr.sh_type != SHT_REL_TYPE) { continue; } sec->reltab = malloc(sec->shdr.sh_size); @@ -445,10 +500,13 @@ static void read_relocs(FILE *fp) die("Cannot read symbol table: %s\n", strerror(errno)); } - for (j = 0; j < sec->shdr.sh_size/sizeof(Elf32_Rel); j++) { - Elf32_Rel *rel = &sec->reltab[j]; - rel->r_offset = elf32_to_cpu(rel->r_offset); - rel->r_info = elf32_to_cpu(rel->r_info); + for (j = 0; j < sec->shdr.sh_size/sizeof(Elf_Rel); j++) { + Elf_Rel *rel = &sec->reltab[j]; + rel->r_offset = elf_addr_to_cpu(rel->r_offset); + rel->r_info = elf_xword_to_cpu(rel->r_info); +#if (SHT_REL_TYPE == SHT_RELA) + rel->r_addend = elf_xword_to_cpu(rel->r_addend); +#endif } } } @@ -457,6 +515,13 @@ static void read_relocs(FILE *fp) static void print_absolute_symbols(void) { int i; + const char *format; + + if (ELF_BITS == 64) + format = "%5d %016"PRIx64" %5"PRId64" %10s %10s %12s %s\n"; + else + format = "%5d %08"PRIx32" %5"PRId32" %10s %10s %12s %s\n"; + printf("Absolute symbols\n"); printf(" Num: Value Size Type Bind Visibility Name\n"); for (i = 0; i < ehdr.e_shnum; i++) { @@ -468,19 +533,19 @@ static void print_absolute_symbols(void) continue; } sym_strtab = sec->link->strtab; - for (j = 0; j < sec->shdr.sh_size/sizeof(Elf32_Sym); j++) { - Elf32_Sym *sym; + for (j = 0; j < sec->shdr.sh_size/sizeof(Elf_Sym); j++) { + Elf_Sym *sym; const char *name; sym = &sec->symtab[j]; name = sym_name(sym_strtab, sym); if (sym->st_shndx != SHN_ABS) { continue; } - printf("%5d %08x %5d %10s %10s %12s %s\n", + printf(format, j, sym->st_value, sym->st_size, - sym_type(ELF32_ST_TYPE(sym->st_info)), - sym_bind(ELF32_ST_BIND(sym->st_info)), - sym_visibility(ELF32_ST_VISIBILITY(sym->st_other)), + sym_type(ELF_ST_TYPE(sym->st_info)), + sym_bind(ELF_ST_BIND(sym->st_info)), + sym_visibility(ELF_ST_VISIBILITY(sym->st_other)), name); } } @@ -490,14 +555,20 @@ static void print_absolute_symbols(void) static void print_absolute_relocs(void) { int i, printed = 0; + const char *format; + + if (ELF_BITS == 64) + format = "%016"PRIx64" %016"PRIx64" %10s %016"PRIx64" %s\n"; + else + format = "%08"PRIx32" %08"PRIx32" %10s %08"PRIx32" %s\n"; for (i = 0; i < ehdr.e_shnum; i++) { struct section *sec = &secs[i]; struct section *sec_applies, *sec_symtab; char *sym_strtab; - Elf32_Sym *sh_symtab; + Elf_Sym *sh_symtab; int j; - if (sec->shdr.sh_type != SHT_REL) { + if (sec->shdr.sh_type != SHT_REL_TYPE) { continue; } sec_symtab = sec->link; @@ -507,12 +578,12 @@ static void print_absolute_relocs(void) } sh_symtab = sec_symtab->symtab; sym_strtab = sec_symtab->link->strtab; - for (j = 0; j < sec->shdr.sh_size/sizeof(Elf32_Rel); j++) { - Elf32_Rel *rel; - Elf32_Sym *sym; + for (j = 0; j < sec->shdr.sh_size/sizeof(Elf_Rel); j++) { + Elf_Rel *rel; + Elf_Sym *sym; const char *name; rel = &sec->reltab[j]; - sym = &sh_symtab[ELF32_R_SYM(rel->r_info)]; + sym = &sh_symtab[ELF_R_SYM(rel->r_info)]; name = sym_name(sym_strtab, sym); if (sym->st_shndx != SHN_ABS) { continue; @@ -542,10 +613,10 @@ static void print_absolute_relocs(void) printed = 1; } - printf("%08x %08x %10s %08x %s\n", + printf(format, rel->r_offset, rel->r_info, - rel_type(ELF32_R_TYPE(rel->r_info)), + rel_type(ELF_R_TYPE(rel->r_info)), sym->st_value, name); } @@ -555,19 +626,34 @@ static void print_absolute_relocs(void) printf("\n"); } -static void walk_relocs(void (*visit)(Elf32_Rel *rel, Elf32_Sym *sym), - int use_real_mode) +static void add_reloc(struct relocs *r, uint32_t offset) +{ + if (r->count == r->size) { + unsigned long newsize = r->size + 50000; + void *mem = realloc(r->offset, newsize * sizeof(r->offset[0])); + + if (!mem) + die("realloc of %ld entries for relocs failed\n", + newsize); + r->offset = mem; + r->size = newsize; + } + r->offset[r->count++] = offset; +} + +static void walk_relocs(int (*process)(struct section *sec, Elf_Rel *rel, + Elf_Sym *sym, const char *symname)) { int i; /* Walk through the relocations */ for (i = 0; i < ehdr.e_shnum; i++) { char *sym_strtab; - Elf32_Sym *sh_symtab; + Elf_Sym *sh_symtab; struct section *sec_applies, *sec_symtab; int j; struct section *sec = &secs[i]; - if (sec->shdr.sh_type != SHT_REL) { + if (sec->shdr.sh_type != SHT_REL_TYPE) { continue; } sec_symtab = sec->link; @@ -577,101 +663,281 @@ static void walk_relocs(void (*visit)(Elf32_Rel *rel, Elf32_Sym *sym), } sh_symtab = sec_symtab->symtab; sym_strtab = sec_symtab->link->strtab; - for (j = 0; j < sec->shdr.sh_size/sizeof(Elf32_Rel); j++) { - Elf32_Rel *rel; - Elf32_Sym *sym; - unsigned r_type; - const char *symname; - int shn_abs; + for (j = 0; j < sec->shdr.sh_size/sizeof(Elf_Rel); j++) { + Elf_Rel *rel = &sec->reltab[j]; + Elf_Sym *sym = &sh_symtab[ELF_R_SYM(rel->r_info)]; + const char *symname = sym_name(sym_strtab, sym); - rel = &sec->reltab[j]; - sym = &sh_symtab[ELF32_R_SYM(rel->r_info)]; - r_type = ELF32_R_TYPE(rel->r_info); - - shn_abs = sym->st_shndx == SHN_ABS; - - switch (r_type) { - case R_386_NONE: - case R_386_PC32: - case R_386_PC16: - case R_386_PC8: - /* - * NONE can be ignored and and PC relative - * relocations don't need to be adjusted. - */ - break; + process(sec, rel, sym, symname); + } + } +} - case R_386_16: - symname = sym_name(sym_strtab, sym); - if (!use_real_mode) - goto bad; - if (shn_abs) { - if (is_reloc(S_ABS, symname)) - break; - else if (!is_reloc(S_SEG, symname)) - goto bad; - } else { - if (is_reloc(S_LIN, symname)) - goto bad; - else - break; - } - visit(rel, sym); - break; +/* + * The .data..percpu section is a special case for x86_64 SMP kernels. + * It is used to initialize the actual per_cpu areas and to provide + * definitions for the per_cpu variables that correspond to their offsets + * within the percpu area. Since the values of all of the symbols need + * to be offsets from the start of the per_cpu area the virtual address + * (sh_addr) of .data..percpu is 0 in SMP kernels. + * + * This means that: + * + * Relocations that reference symbols in the per_cpu area do not + * need further relocation (since the value is an offset relative + * to the start of the per_cpu area that does not change). + * + * Relocations that apply to the per_cpu area need to have their + * offset adjusted by by the value of __per_cpu_load to make them + * point to the correct place in the loaded image (because the + * virtual address of .data..percpu is 0). + * + * For non SMP kernels .data..percpu is linked as part of the normal + * kernel data and does not require special treatment. + * + */ +static int per_cpu_shndx = -1; +Elf_Addr per_cpu_load_addr; - case R_386_32: - symname = sym_name(sym_strtab, sym); - if (shn_abs) { - if (is_reloc(S_ABS, symname)) - break; - else if (!is_reloc(S_REL, symname)) - goto bad; - } else { - if (use_real_mode && - !is_reloc(S_LIN, symname)) - break; - } - visit(rel, sym); - break; - default: - die("Unsupported relocation type: %s (%d)\n", - rel_type(r_type), r_type); +static void percpu_init(void) +{ + int i; + for (i = 0; i < ehdr.e_shnum; i++) { + ElfW(Sym) *sym; + if (strcmp(sec_name(i), ".data..percpu")) + continue; + + if (secs[i].shdr.sh_addr != 0) /* non SMP kernel */ + return; + + sym = sym_lookup("__per_cpu_load"); + if (!sym) + die("can't find __per_cpu_load\n"); + + per_cpu_shndx = i; + per_cpu_load_addr = sym->st_value; + return; + } +} + +#if ELF_BITS == 64 + +/* + * Check to see if a symbol lies in the .data..percpu section. + * For some as yet not understood reason the "__init_begin" + * symbol which immediately preceeds the .data..percpu section + * also shows up as it it were part of it so we do an explict + * check for that symbol name and ignore it. + */ +static int is_percpu_sym(ElfW(Sym) *sym, const char *symname) +{ + return (sym->st_shndx == per_cpu_shndx) && + strcmp(symname, "__init_begin"); +} + + +static int do_reloc64(struct section *sec, Elf_Rel *rel, ElfW(Sym) *sym, + const char *symname) +{ + unsigned r_type = ELF64_R_TYPE(rel->r_info); + ElfW(Addr) offset = rel->r_offset; + int shn_abs = (sym->st_shndx == SHN_ABS) && !is_reloc(S_REL, symname); + + if (sym->st_shndx == SHN_UNDEF) + return 0; + + /* + * Adjust the offset if this reloc applies to the percpu section. + */ + if (sec->shdr.sh_info == per_cpu_shndx) + offset += per_cpu_load_addr; + + switch (r_type) { + case R_X86_64_NONE: + case R_X86_64_PC32: + /* + * NONE can be ignored and PC relative relocations don't + * need to be adjusted. + */ + break; + + case R_X86_64_32: + case R_X86_64_32S: + case R_X86_64_64: + /* + * References to the percpu area don't need to be adjusted. + */ + if (is_percpu_sym(sym, symname)) + break; + + if (shn_abs) { + /* + * Whitelisted absolute symbols do not require + * relocation. + */ + if (is_reloc(S_ABS, symname)) break; - bad: - symname = sym_name(sym_strtab, sym); - die("Invalid %s %s relocation: %s\n", - shn_abs ? "absolute" : "relative", - rel_type(r_type), symname); - } + + die("Invalid absolute %s relocation: %s\n", + rel_type(r_type), symname); + break; } + + /* + * Relocation offsets for 64 bit kernels are output + * as 32 bits and sign extended back to 64 bits when + * the relocations are processed. + * Make sure that the offset will fit. + */ + if ((int32_t)offset != (int64_t)offset) + die("Relocation offset doesn't fit in 32 bits\n"); + + if (r_type == R_X86_64_64) + add_reloc(&relocs64, offset); + else + add_reloc(&relocs32, offset); + break; + + default: + die("Unsupported relocation type: %s (%d)\n", + rel_type(r_type), r_type); + break; } + + return 0; } -static void count_reloc(Elf32_Rel *rel, Elf32_Sym *sym) +#else + +static int do_reloc32(struct section *sec, Elf_Rel *rel, Elf_Sym *sym, + const char *symname) { - if (ELF32_R_TYPE(rel->r_info) == R_386_16) - reloc16_count++; - else - reloc_count++; + unsigned r_type = ELF32_R_TYPE(rel->r_info); + int shn_abs = (sym->st_shndx == SHN_ABS) && !is_reloc(S_REL, symname); + + switch (r_type) { + case R_386_NONE: + case R_386_PC32: + case R_386_PC16: + case R_386_PC8: + /* + * NONE can be ignored and PC relative relocations don't + * need to be adjusted. + */ + break; + + case R_386_32: + if (shn_abs) { + /* + * Whitelisted absolute symbols do not require + * relocation. + */ + if (is_reloc(S_ABS, symname)) + break; + + die("Invalid absolute %s relocation: %s\n", + rel_type(r_type), symname); + break; + } + + add_reloc(&relocs32, rel->r_offset); + break; + + default: + die("Unsupported relocation type: %s (%d)\n", + rel_type(r_type), r_type); + break; + } + + return 0; } -static void collect_reloc(Elf32_Rel *rel, Elf32_Sym *sym) +static int do_reloc_real(struct section *sec, Elf_Rel *rel, Elf_Sym *sym, + const char *symname) { - /* Remember the address that needs to be adjusted. */ - if (ELF32_R_TYPE(rel->r_info) == R_386_16) - relocs16[reloc16_idx++] = rel->r_offset; - else - relocs[reloc_idx++] = rel->r_offset; + unsigned r_type = ELF32_R_TYPE(rel->r_info); + int shn_abs = (sym->st_shndx == SHN_ABS) && !is_reloc(S_REL, symname); + + switch (r_type) { + case R_386_NONE: + case R_386_PC32: + case R_386_PC16: + case R_386_PC8: + /* + * NONE can be ignored and PC relative relocations don't + * need to be adjusted. + */ + break; + + case R_386_16: + if (shn_abs) { + /* + * Whitelisted absolute symbols do not require + * relocation. + */ + if (is_reloc(S_ABS, symname)) + break; + + if (is_reloc(S_SEG, symname)) { + add_reloc(&relocs16, rel->r_offset); + break; + } + } else { + if (!is_reloc(S_LIN, symname)) + break; + } + die("Invalid %s %s relocation: %s\n", + shn_abs ? "absolute" : "relative", + rel_type(r_type), symname); + break; + + case R_386_32: + if (shn_abs) { + /* + * Whitelisted absolute symbols do not require + * relocation. + */ + if (is_reloc(S_ABS, symname)) + break; + + if (is_reloc(S_REL, symname)) { + add_reloc(&relocs32, rel->r_offset); + break; + } + } else { + if (is_reloc(S_LIN, symname)) + add_reloc(&relocs32, rel->r_offset); + break; + } + die("Invalid %s %s relocation: %s\n", + shn_abs ? "absolute" : "relative", + rel_type(r_type), symname); + break; + + default: + die("Unsupported relocation type: %s (%d)\n", + rel_type(r_type), r_type); + break; + } + + return 0; } +#endif + static int cmp_relocs(const void *va, const void *vb) { - const unsigned long *a, *b; + const uint32_t *a, *b; a = va; b = vb; return (*a == *b)? 0 : (*a > *b)? 1 : -1; } -static int write32(unsigned int v, FILE *f) +static void sort_relocs(struct relocs *r) +{ + qsort(r->offset, r->count, sizeof(r->offset[0]), cmp_relocs); +} + +static int write32(uint32_t v, FILE *f) { unsigned char buf[4]; @@ -679,33 +945,40 @@ static int write32(unsigned int v, FILE *f) return fwrite(buf, 1, 4, f) == 4 ? 0 : -1; } +static int write32_as_text(uint32_t v, FILE *f) +{ + return fprintf(f, "\t.long 0x%08"PRIx32"\n", v) > 0 ? 0 : -1; +} + static void emit_relocs(int as_text, int use_real_mode) { int i; - /* Count how many relocations I have and allocate space for them. */ - reloc_count = 0; - walk_relocs(count_reloc, use_real_mode); - relocs = malloc(reloc_count * sizeof(relocs[0])); - if (!relocs) { - die("malloc of %d entries for relocs failed\n", - reloc_count); - } + int (*write_reloc)(uint32_t, FILE *) = write32; + int (*do_reloc)(struct section *sec, Elf_Rel *rel, Elf_Sym *sym, + const char *symname); + +#if ELF_BITS == 64 + if (!use_real_mode) + do_reloc = do_reloc64; + else + die("--realmode not valid for a 64-bit ELF file"); +#else + if (!use_real_mode) + do_reloc = do_reloc32; + else + do_reloc = do_reloc_real; +#endif - relocs16 = malloc(reloc16_count * sizeof(relocs[0])); - if (!relocs16) { - die("malloc of %d entries for relocs16 failed\n", - reloc16_count); - } /* Collect up the relocations */ - reloc_idx = 0; - walk_relocs(collect_reloc, use_real_mode); + walk_relocs(do_reloc); - if (reloc16_count && !use_real_mode) + if (relocs16.count && !use_real_mode) die("Segment relocations found but --realmode not specified\n"); /* Order the relocations for more efficient processing */ - qsort(relocs, reloc_count, sizeof(relocs[0]), cmp_relocs); - qsort(relocs16, reloc16_count, sizeof(relocs16[0]), cmp_relocs); + sort_relocs(&relocs16); + sort_relocs(&relocs32); + sort_relocs(&relocs64); /* Print the relocations */ if (as_text) { @@ -714,114 +987,60 @@ static void emit_relocs(int as_text, int use_real_mode) */ printf(".section \".data.reloc\",\"a\"\n"); printf(".balign 4\n"); - if (use_real_mode) { - printf("\t.long %lu\n", reloc16_count); - for (i = 0; i < reloc16_count; i++) - printf("\t.long 0x%08lx\n", relocs16[i]); - printf("\t.long %lu\n", reloc_count); - for (i = 0; i < reloc_count; i++) { - printf("\t.long 0x%08lx\n", relocs[i]); - } - } else { - /* Print a stop */ - printf("\t.long 0x%08lx\n", (unsigned long)0); - for (i = 0; i < reloc_count; i++) { - printf("\t.long 0x%08lx\n", relocs[i]); - } - } - - printf("\n"); + write_reloc = write32_as_text; } - else { - if (use_real_mode) { - write32(reloc16_count, stdout); - for (i = 0; i < reloc16_count; i++) - write32(relocs16[i], stdout); - write32(reloc_count, stdout); - /* Now print each relocation */ - for (i = 0; i < reloc_count; i++) - write32(relocs[i], stdout); - } else { + if (use_real_mode) { + write_reloc(relocs16.count, stdout); + for (i = 0; i < relocs16.count; i++) + write_reloc(relocs16.offset[i], stdout); + + write_reloc(relocs32.count, stdout); + for (i = 0; i < relocs32.count; i++) + write_reloc(relocs32.offset[i], stdout); + } else { + if (ELF_BITS == 64) { /* Print a stop */ - write32(0, stdout); + write_reloc(0, stdout); /* Now print each relocation */ - for (i = 0; i < reloc_count; i++) { - write32(relocs[i], stdout); - } + for (i = 0; i < relocs64.count; i++) + write_reloc(relocs64.offset[i], stdout); } + + /* Print a stop */ + write_reloc(0, stdout); + + /* Now print each relocation */ + for (i = 0; i < relocs32.count; i++) + write_reloc(relocs32.offset[i], stdout); } } -static void usage(void) -{ - die("relocs [--abs-syms|--abs-relocs|--text|--realmode] vmlinux\n"); -} +#if ELF_BITS == 64 +# define process process_64 +#else +# define process process_32 +#endif -int main(int argc, char **argv) +void process(FILE *fp, int use_real_mode, int as_text, + int show_absolute_syms, int show_absolute_relocs) { - int show_absolute_syms, show_absolute_relocs; - int as_text, use_real_mode; - const char *fname; - FILE *fp; - int i; - - show_absolute_syms = 0; - show_absolute_relocs = 0; - as_text = 0; - use_real_mode = 0; - fname = NULL; - for (i = 1; i < argc; i++) { - char *arg = argv[i]; - if (*arg == '-') { - if (strcmp(arg, "--abs-syms") == 0) { - show_absolute_syms = 1; - continue; - } - if (strcmp(arg, "--abs-relocs") == 0) { - show_absolute_relocs = 1; - continue; - } - if (strcmp(arg, "--text") == 0) { - as_text = 1; - continue; - } - if (strcmp(arg, "--realmode") == 0) { - use_real_mode = 1; - continue; - } - } - else if (!fname) { - fname = arg; - continue; - } - usage(); - } - if (!fname) { - usage(); - } regex_init(use_real_mode); - fp = fopen(fname, "r"); - if (!fp) { - die("Cannot open %s: %s\n", - fname, strerror(errno)); - } read_ehdr(fp); read_shdrs(fp); read_strtabs(fp); read_symtabs(fp); read_relocs(fp); + if (ELF_BITS == 64) + percpu_init(); if (show_absolute_syms) { print_absolute_symbols(); - goto out; + return; } if (show_absolute_relocs) { print_absolute_relocs(); - goto out; + return; } emit_relocs(as_text, use_real_mode); -out: - fclose(fp); - return 0; } diff --git a/arch/x86/tools/relocs.h b/arch/x86/tools/relocs.h new file mode 100644 index 0000000..07cdb1e --- /dev/null +++ b/arch/x86/tools/relocs.h @@ -0,0 +1,36 @@ +#ifndef RELOCS_H +#define RELOCS_H + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#define USE_BSD +#include +#include +#include + +void die(char *fmt, ...); + +#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) + +enum symtype { + S_ABS, + S_REL, + S_SEG, + S_LIN, + S_NSYMTYPES +}; + +void process_32(FILE *fp, int use_real_mode, int as_text, + int show_absolute_syms, int show_absolute_relocs); +void process_64(FILE *fp, int use_real_mode, int as_text, + int show_absolute_syms, int show_absolute_relocs); + +#endif /* RELOCS_H */ diff --git a/arch/x86/tools/relocs_32.c b/arch/x86/tools/relocs_32.c new file mode 100644 index 0000000..b2ade2b --- /dev/null +++ b/arch/x86/tools/relocs_32.c @@ -0,0 +1,17 @@ +#include "relocs.h" + +#define ELF_BITS 32 + +#define ELF_MACHINE EM_386 +#define ELF_MACHINE_NAME "i386" +#define SHT_REL_TYPE SHT_REL +#define Elf_Rel ElfW(Rel) + +#define ELF_CLASS ELFCLASS32 +#define ELF_R_SYM(val) ELF32_R_SYM(val) +#define ELF_R_TYPE(val) ELF32_R_TYPE(val) +#define ELF_ST_TYPE(o) ELF32_ST_TYPE(o) +#define ELF_ST_BIND(o) ELF32_ST_BIND(o) +#define ELF_ST_VISIBILITY(o) ELF32_ST_VISIBILITY(o) + +#include "relocs.c" diff --git a/arch/x86/tools/relocs_64.c b/arch/x86/tools/relocs_64.c new file mode 100644 index 0000000..56b61b7 --- /dev/null +++ b/arch/x86/tools/relocs_64.c @@ -0,0 +1,17 @@ +#include "relocs.h" + +#define ELF_BITS 64 + +#define ELF_MACHINE EM_X86_64 +#define ELF_MACHINE_NAME "x86_64" +#define SHT_REL_TYPE SHT_RELA +#define Elf_Rel Elf64_Rela + +#define ELF_CLASS ELFCLASS64 +#define ELF_R_SYM(val) ELF64_R_SYM(val) +#define ELF_R_TYPE(val) ELF64_R_TYPE(val) +#define ELF_ST_TYPE(o) ELF64_ST_TYPE(o) +#define ELF_ST_BIND(o) ELF64_ST_BIND(o) +#define ELF_ST_VISIBILITY(o) ELF64_ST_VISIBILITY(o) + +#include "relocs.c" diff --git a/arch/x86/tools/relocs_common.c b/arch/x86/tools/relocs_common.c new file mode 100644 index 0000000..44d3968 --- /dev/null +++ b/arch/x86/tools/relocs_common.c @@ -0,0 +1,76 @@ +#include "relocs.h" + +void die(char *fmt, ...) +{ + va_list ap; + va_start(ap, fmt); + vfprintf(stderr, fmt, ap); + va_end(ap); + exit(1); +} + +static void usage(void) +{ + die("relocs [--abs-syms|--abs-relocs|--text|--realmode] vmlinux\n"); +} + +int main(int argc, char **argv) +{ + int show_absolute_syms, show_absolute_relocs; + int as_text, use_real_mode; + const char *fname; + FILE *fp; + int i; + unsigned char e_ident[EI_NIDENT]; + + show_absolute_syms = 0; + show_absolute_relocs = 0; + as_text = 0; + use_real_mode = 0; + fname = NULL; + for (i = 1; i < argc; i++) { + char *arg = argv[i]; + if (*arg == '-') { + if (strcmp(arg, "--abs-syms") == 0) { + show_absolute_syms = 1; + continue; + } + if (strcmp(arg, "--abs-relocs") == 0) { + show_absolute_relocs = 1; + continue; + } + if (strcmp(arg, "--text") == 0) { + as_text = 1; + continue; + } + if (strcmp(arg, "--realmode") == 0) { + use_real_mode = 1; + continue; + } + } + else if (!fname) { + fname = arg; + continue; + } + usage(); + } + if (!fname) { + usage(); + } + fp = fopen(fname, "r"); + if (!fp) { + die("Cannot open %s: %s\n", fname, strerror(errno)); + } + if (fread(&e_ident, 1, EI_NIDENT, fp) != EI_NIDENT) { + die("Cannot read %s: %s", fname, strerror(errno)); + } + rewind(fp); + if (e_ident[EI_CLASS] == ELFCLASS64) + process_64(fp, use_real_mode, as_text, + show_absolute_syms, show_absolute_relocs); + else + process_32(fp, use_real_mode, as_text, + show_absolute_syms, show_absolute_relocs); + fclose(fp); + return 0; +} diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index 6afbb2c..8bc4dec 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -2039,9 +2039,7 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot) switch (idx) { case FIX_BTMAP_END ... FIX_BTMAP_BEGIN: -#ifdef CONFIG_X86_F00F_BUG - case FIX_F00F_IDT: -#endif + case FIX_RO_IDT: #ifdef CONFIG_X86_32 case FIX_WP_TEST: case FIX_VDSO: -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/