X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=kernel%2Fmodule.c;h=f82386bd9ee9cf01b6399ee750fc481269c63c89;hb=5dab600e6a153ceb64832f608069e6c08185411a;hp=2f0fddf3c114e19d73ca890f71e43f112693b4c8;hpb=414fd31b2553aaf160ca9b9afe45aa0372b01b92;p=safe%2Fjmp%2Flinux-2.6 diff --git a/kernel/module.c b/kernel/module.c index 2f0fddf..f82386b 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -18,6 +18,7 @@ */ #include #include +#include #include #include #include @@ -46,12 +47,19 @@ #include #include #include +#include #include #include #include #include #include #include +#include + +#define CREATE_TRACE_POINTS +#include + +EXPORT_TRACEPOINT_SYMBOL(module_get); #if 0 #define DEBUGP printk @@ -68,15 +76,19 @@ /* List of modules, protected by module_mutex or preempt_disable * (delete uses stop_machine/add uses RCU list operations). */ -static DEFINE_MUTEX(module_mutex); +DEFINE_MUTEX(module_mutex); +EXPORT_SYMBOL_GPL(module_mutex); static LIST_HEAD(modules); +/* Block module loading/unloading? */ +int modules_disabled = 0; + /* Waiting for a module to finish initializing? */ static DECLARE_WAIT_QUEUE_HEAD(module_wq); static BLOCKING_NOTIFIER_HEAD(module_notify_list); -/* Bounds of module allocation, for speeding __module_text_address */ +/* Bounds of module allocation, for speeding __module_address */ static unsigned long module_addr_min = -1UL, module_addr_max = 0; int register_module_notifier(struct notifier_block * nb) @@ -186,17 +198,6 @@ extern const unsigned long __start___kcrctab_unused_gpl[]; #define symversion(base, idx) ((base != NULL) ? ((base) + (idx)) : NULL) #endif -struct symsearch { - const struct kernel_symbol *start, *stop; - const unsigned long *crcs; - enum { - NOT_GPL_ONLY, - GPL_ONLY, - WILL_BE_GPL_ONLY, - } licence; - bool unused; -}; - static bool each_symbol_in_section(const struct symsearch *arr, unsigned int arrsize, struct module *owner, @@ -217,10 +218,8 @@ static bool each_symbol_in_section(const struct symsearch *arr, } /* Returns true as soon as fn returns true, otherwise false. */ -static bool each_symbol(bool (*fn)(const struct symsearch *arr, - struct module *owner, - unsigned int symnum, void *data), - void *data) +bool each_symbol(bool (*fn)(const struct symsearch *arr, struct module *owner, + unsigned int symnum, void *data), void *data) { struct module *mod; const struct symsearch arr[] = { @@ -273,6 +272,7 @@ static bool each_symbol(bool (*fn)(const struct symsearch *arr, } return false; } +EXPORT_SYMBOL_GPL(each_symbol); struct find_symbol_arg { /* Input */ @@ -330,11 +330,11 @@ static bool find_symbol_in_section(const struct symsearch *syms, /* Find a symbol and return it, along with, (optional) crc and * (optional) module which owns it */ -static const struct kernel_symbol *find_symbol(const char *name, - struct module **owner, - const unsigned long **crc, - bool gplok, - bool warn) +const struct kernel_symbol *find_symbol(const char *name, + struct module **owner, + const unsigned long **crc, + bool gplok, + bool warn) { struct find_symbol_arg fsa; @@ -353,9 +353,10 @@ static const struct kernel_symbol *find_symbol(const char *name, DEBUGP("Failed to find symbol %s\n", name); return NULL; } +EXPORT_SYMBOL_GPL(find_symbol); /* Search for module by name: must hold module_mutex. */ -static struct module *find_module(const char *name) +struct module *find_module(const char *name) { struct module *mod; @@ -365,11 +366,10 @@ static struct module *find_module(const char *name) } return NULL; } +EXPORT_SYMBOL_GPL(find_module); #ifdef CONFIG_SMP -#ifdef CONFIG_HAVE_DYNAMIC_PER_CPU_AREA - static void *percpu_modalloc(unsigned long size, unsigned long align, const char *name) { @@ -393,143 +393,6 @@ static void percpu_modfree(void *freeme) free_percpu(freeme); } -#else /* ... !CONFIG_HAVE_DYNAMIC_PER_CPU_AREA */ - -/* Number of blocks used and allocated. */ -static unsigned int pcpu_num_used, pcpu_num_allocated; -/* Size of each block. -ve means used. */ -static int *pcpu_size; - -static int split_block(unsigned int i, unsigned short size) -{ - /* Reallocation required? */ - if (pcpu_num_used + 1 > pcpu_num_allocated) { - int *new; - - new = krealloc(pcpu_size, sizeof(new[0])*pcpu_num_allocated*2, - GFP_KERNEL); - if (!new) - return 0; - - pcpu_num_allocated *= 2; - pcpu_size = new; - } - - /* Insert a new subblock */ - memmove(&pcpu_size[i+1], &pcpu_size[i], - sizeof(pcpu_size[0]) * (pcpu_num_used - i)); - pcpu_num_used++; - - pcpu_size[i+1] -= size; - pcpu_size[i] = size; - return 1; -} - -static inline unsigned int block_size(int val) -{ - if (val < 0) - return -val; - return val; -} - -static void *percpu_modalloc(unsigned long size, unsigned long align, - const char *name) -{ - unsigned long extra; - unsigned int i; - void *ptr; - - if (align > PAGE_SIZE) { - printk(KERN_WARNING "%s: per-cpu alignment %li > %li\n", - name, align, PAGE_SIZE); - align = PAGE_SIZE; - } - - ptr = __per_cpu_start; - for (i = 0; i < pcpu_num_used; ptr += block_size(pcpu_size[i]), i++) { - /* Extra for alignment requirement. */ - extra = ALIGN((unsigned long)ptr, align) - (unsigned long)ptr; - BUG_ON(i == 0 && extra != 0); - - if (pcpu_size[i] < 0 || pcpu_size[i] < extra + size) - continue; - - /* Transfer extra to previous block. */ - if (pcpu_size[i-1] < 0) - pcpu_size[i-1] -= extra; - else - pcpu_size[i-1] += extra; - pcpu_size[i] -= extra; - ptr += extra; - - /* Split block if warranted */ - if (pcpu_size[i] - size > sizeof(unsigned long)) - if (!split_block(i, size)) - return NULL; - - /* Mark allocated */ - pcpu_size[i] = -pcpu_size[i]; - return ptr; - } - - printk(KERN_WARNING "Could not allocate %lu bytes percpu data\n", - size); - return NULL; -} - -static void percpu_modfree(void *freeme) -{ - unsigned int i; - void *ptr = __per_cpu_start + block_size(pcpu_size[0]); - - /* First entry is core kernel percpu data. */ - for (i = 1; i < pcpu_num_used; ptr += block_size(pcpu_size[i]), i++) { - if (ptr == freeme) { - pcpu_size[i] = -pcpu_size[i]; - goto free; - } - } - BUG(); - - free: - /* Merge with previous? */ - if (pcpu_size[i-1] >= 0) { - pcpu_size[i-1] += pcpu_size[i]; - pcpu_num_used--; - memmove(&pcpu_size[i], &pcpu_size[i+1], - (pcpu_num_used - i) * sizeof(pcpu_size[0])); - i--; - } - /* Merge with next? */ - if (i+1 < pcpu_num_used && pcpu_size[i+1] >= 0) { - pcpu_size[i] += pcpu_size[i+1]; - pcpu_num_used--; - memmove(&pcpu_size[i+1], &pcpu_size[i+2], - (pcpu_num_used - (i+1)) * sizeof(pcpu_size[0])); - } -} - -static int percpu_modinit(void) -{ - pcpu_num_used = 2; - pcpu_num_allocated = 2; - pcpu_size = kmalloc(sizeof(pcpu_size[0]) * pcpu_num_allocated, - GFP_KERNEL); - /* Static in-kernel percpu data (used). */ - pcpu_size[0] = -(__per_cpu_end-__per_cpu_start); - /* Free room. */ - pcpu_size[1] = PERCPU_ENOUGH_ROOM + pcpu_size[0]; - if (pcpu_size[1] < 0) { - printk(KERN_ERR "No per-cpu room for modules.\n"); - pcpu_num_used = 1; - } - - return 0; -} -__initcall(percpu_modinit); - -#endif /* CONFIG_HAVE_DYNAMIC_PER_CPU_AREA */ - static unsigned int find_pcpusec(Elf_Ehdr *hdr, Elf_Shdr *sechdrs, const char *secstrings) @@ -641,7 +504,7 @@ static int already_uses(struct module *a, struct module *b) } /* Module a uses b */ -static int use_module(struct module *a, struct module *b) +int use_module(struct module *a, struct module *b) { struct module_use *use; int no_warn, err; @@ -674,6 +537,7 @@ static int use_module(struct module *a, struct module *b) no_warn = sysfs_create_link(b->holders_dir, &a->mkobj.kobj, a->name); return 1; } +EXPORT_SYMBOL_GPL(use_module); /* Clear the unload stuff of the module. */ static void module_unload_free(struct module *mod) @@ -785,7 +649,7 @@ SYSCALL_DEFINE2(delete_module, const char __user *, name_user, char name[MODULE_NAME_LEN]; int ret, forced = 0; - if (!capable(CAP_SYS_MODULE)) + if (!capable(CAP_SYS_MODULE) || modules_disabled) return -EPERM; if (strncpy_from_user(name, name_user, MODULE_NAME_LEN-1) < 0) @@ -901,15 +765,19 @@ void __symbol_put(const char *symbol) } EXPORT_SYMBOL(__symbol_put); +/* Note this assumes addr is a function, which it currently always is. */ void symbol_put_addr(void *addr) { struct module *modaddr; + unsigned long a = (unsigned long)dereference_function_descriptor(addr); - if (core_kernel_text((unsigned long)addr)) + if (core_kernel_text(a)) return; - if (!(modaddr = module_text_address((unsigned long)addr))) - BUG(); + /* module_text_address is safe here: we're supposed to have reference + * to module from symbol_get, so it can't go away. */ + modaddr = __module_text_address(a); + BUG_ON(!modaddr); module_put(modaddr); } EXPORT_SYMBOL_GPL(symbol_put_addr); @@ -930,6 +798,8 @@ void module_put(struct module *module) if (module) { unsigned int cpu = get_cpu(); local_dec(__module_ref_addr(module, cpu)); + trace_module_put(module, _RET_IP_, + local_read(__module_ref_addr(module, cpu))); /* Maybe they're waiting for us to drop reference? */ if (unlikely(!module_is_live(module))) wake_up_process(module->waiter); @@ -949,10 +819,11 @@ static inline void module_unload_free(struct module *mod) { } -static inline int use_module(struct module *a, struct module *b) +int use_module(struct module *a, struct module *b) { return strong_try_module_get(b) == 0; } +EXPORT_SYMBOL_GPL(use_module); static inline void module_unload_init(struct module *mod) { @@ -995,12 +866,12 @@ static struct module_attribute *modinfo_attrs[] = { static const char vermagic[] = VERMAGIC_STRING; -static int try_to_force_load(struct module *mod, const char *symname) +static int try_to_force_load(struct module *mod, const char *reason) { #ifdef CONFIG_MODULE_FORCE_LOAD if (!test_taint(TAINT_FORCED_MODULE)) - printk("%s: no version for \"%s\" found: kernel tainted.\n", - mod->name, symname); + printk(KERN_WARNING "%s: %s: kernel tainted.\n", + mod->name, reason); add_taint_module(mod, TAINT_FORCED_MODULE); return 0; #else @@ -1009,11 +880,23 @@ static int try_to_force_load(struct module *mod, const char *symname) } #ifdef CONFIG_MODVERSIONS +/* If the arch applies (non-zero) relocations to kernel kcrctab, unapply it. */ +static unsigned long maybe_relocated(unsigned long crc, + const struct module *crc_owner) +{ +#ifdef ARCH_RELOCATES_KCRCTAB + if (crc_owner == NULL) + return crc - (unsigned long)reloc_start; +#endif + return crc; +} + static int check_version(Elf_Shdr *sechdrs, unsigned int versindex, const char *symname, struct module *mod, - const unsigned long *crc) + const unsigned long *crc, + const struct module *crc_owner) { unsigned int i, num_versions; struct modversion_info *versions; @@ -1034,10 +917,10 @@ static int check_version(Elf_Shdr *sechdrs, if (strcmp(versions[i].name, symname) != 0) continue; - if (versions[i].crc == *crc) + if (versions[i].crc == maybe_relocated(*crc, crc_owner)) return 1; DEBUGP("Found checksum %lX vs module %lX\n", - *crc, versions[i].crc); + maybe_relocated(*crc, crc_owner), versions[i].crc); goto bad_version; } @@ -1057,9 +940,11 @@ static inline int check_modstruct_version(Elf_Shdr *sechdrs, { const unsigned long *crc; - if (!find_symbol("struct_module", NULL, &crc, true, false)) + if (!find_symbol(MODULE_SYMBOL_PREFIX "module_layout", NULL, + &crc, true, false)) BUG(); - return check_version(sechdrs, versindex, "struct_module", mod, crc); + return check_version(sechdrs, versindex, "module_layout", mod, crc, + NULL); } /* First part is kernel version, which we ignore if module has crcs. */ @@ -1077,7 +962,8 @@ static inline int check_version(Elf_Shdr *sechdrs, unsigned int versindex, const char *symname, struct module *mod, - const unsigned long *crc) + const unsigned long *crc, + const struct module *crc_owner) { return 1; } @@ -1112,8 +998,8 @@ static const struct kernel_symbol *resolve_symbol(Elf_Shdr *sechdrs, /* use_module can fail due to OOM, or module initialization or unloading */ if (sym) { - if (!check_version(sechdrs, versindex, name, mod, crc) || - !use_module(mod, owner)) + if (!check_version(sechdrs, versindex, name, mod, crc, owner) + || !use_module(mod, owner)) sym = NULL; } return sym; @@ -1124,6 +1010,12 @@ static const struct kernel_symbol *resolve_symbol(Elf_Shdr *sechdrs, * J. Corbet */ #if defined(CONFIG_KALLSYMS) && defined(CONFIG_SYSFS) + +static inline bool sect_empty(const Elf_Shdr *sect) +{ + return !(sect->sh_flags & SHF_ALLOC) || sect->sh_size == 0; +} + struct module_sect_attr { struct module_attribute mattr; @@ -1165,7 +1057,7 @@ static void add_sect_attrs(struct module *mod, unsigned int nsect, /* Count loaded sections and allocate structures */ for (i = 0; i < nsect; i++) - if (sechdrs[i].sh_flags & SHF_ALLOC) + if (!sect_empty(&sechdrs[i])) nloaded++; size[0] = ALIGN(sizeof(*sect_attrs) + nloaded * sizeof(sect_attrs->attrs[0]), @@ -1183,7 +1075,7 @@ static void add_sect_attrs(struct module *mod, unsigned int nsect, sattr = §_attrs->attrs[0]; gattr = §_attrs->grp.attrs[0]; for (i = 0; i < nsect; i++) { - if (! (sechdrs[i].sh_flags & SHF_ALLOC)) + if (sect_empty(&sechdrs[i])) continue; sattr->address = sechdrs[i].sh_addr; sattr->name = kstrdup(secstrings + sechdrs[i].sh_name, @@ -1260,10 +1152,14 @@ static void add_notes_attrs(struct module *mod, unsigned int nsect, struct module_notes_attrs *notes_attrs; struct bin_attribute *nattr; + /* failed to create section attributes, so can't create notes */ + if (!mod->sect_attrs) + return; + /* Count notes sections and allocate structures. */ notes = 0; for (i = 0; i < nsect; i++) - if ((sechdrs[i].sh_flags & SHF_ALLOC) && + if (!sect_empty(&sechdrs[i]) && (sechdrs[i].sh_type == SHT_NOTE)) ++notes; @@ -1279,7 +1175,7 @@ static void add_notes_attrs(struct module *mod, unsigned int nsect, notes_attrs->notes = notes; nattr = ¬es_attrs->attrs[0]; for (loaded = i = 0; i < nsect; ++i) { - if (!(sechdrs[i].sh_flags & SHF_ALLOC)) + if (sect_empty(&sechdrs[i])) continue; if (sechdrs[i].sh_type == SHT_NOTE) { nattr->attr.name = mod->sect_attrs->attrs[loaded].name; @@ -1479,6 +1375,8 @@ static int __unlink_module(void *_mod) /* Free a module, remove from lists, etc (must hold module_mutex). */ static void free_module(struct module *mod) { + trace_module_free(mod); + /* Delete from various lists */ stop_machine(__unlink_module, mod, NULL); remove_notes_attrs(mod); @@ -1494,9 +1392,6 @@ static void free_module(struct module *mod) /* Free any allocated parameters. */ destroy_params(mod->kp, mod->num_kp); - /* release any pointers to mcount in this module */ - ftrace_release(mod->module_core, mod->core_size); - /* This may be NULL, but that's OK */ module_free(mod, mod->module_init); kfree(mod->args); @@ -1511,6 +1406,10 @@ static void free_module(struct module *mod) /* Finally, free the core (containing the module structure) */ module_free(mod, mod->module_core); + +#ifdef CONFIG_MPU + update_protections(current->mm); +#endif } void *__symbol_get(const char *symbol) @@ -1678,8 +1577,7 @@ static void layout_sections(struct module *mod, if ((s->sh_flags & masks[m][0]) != masks[m][0] || (s->sh_flags & masks[m][1]) || s->sh_entsize != ~0UL - || strncmp(secstrings + s->sh_name, - ".init", 5) == 0) + || strstarts(secstrings + s->sh_name, ".init")) continue; s->sh_entsize = get_offset(mod, &mod->core_size, s, i); DEBUGP("\t%s\n", secstrings + s->sh_name); @@ -1696,8 +1594,7 @@ static void layout_sections(struct module *mod, if ((s->sh_flags & masks[m][0]) != masks[m][0] || (s->sh_flags & masks[m][1]) || s->sh_entsize != ~0UL - || strncmp(secstrings + s->sh_name, - ".init", 5) != 0) + || !strstarts(secstrings + s->sh_name, ".init")) continue; s->sh_entsize = (get_offset(mod, &mod->init_size, s, i) | INIT_OFFSET_MASK); @@ -1770,6 +1667,17 @@ static void setup_modinfo(struct module *mod, Elf_Shdr *sechdrs, } } +static void free_modinfo(struct module *mod) +{ + struct module_attribute *attr; + int i; + + for (i = 0; (attr = modinfo_attrs[i]); i++) { + if (attr->free) + attr->free(mod); + } +} + #ifdef CONFIG_KALLSYMS /* lookup symbol in given range of kernel_symbols */ @@ -1830,19 +1738,98 @@ static char elf_type(const Elf_Sym *sym, else return 'b'; } - if (strncmp(secstrings + sechdrs[sym->st_shndx].sh_name, - ".debug", strlen(".debug")) == 0) + if (strstarts(secstrings + sechdrs[sym->st_shndx].sh_name, ".debug")) return 'n'; return '?'; } +static bool is_core_symbol(const Elf_Sym *src, const Elf_Shdr *sechdrs, + unsigned int shnum) +{ + const Elf_Shdr *sec; + + if (src->st_shndx == SHN_UNDEF + || src->st_shndx >= shnum + || !src->st_name) + return false; + + sec = sechdrs + src->st_shndx; + if (!(sec->sh_flags & SHF_ALLOC) +#ifndef CONFIG_KALLSYMS_ALL + || !(sec->sh_flags & SHF_EXECINSTR) +#endif + || (sec->sh_entsize & INIT_OFFSET_MASK)) + return false; + + return true; +} + +static unsigned long layout_symtab(struct module *mod, + Elf_Shdr *sechdrs, + unsigned int symindex, + unsigned int strindex, + const Elf_Ehdr *hdr, + const char *secstrings, + unsigned long *pstroffs, + unsigned long *strmap) +{ + unsigned long symoffs; + Elf_Shdr *symsect = sechdrs + symindex; + Elf_Shdr *strsect = sechdrs + strindex; + const Elf_Sym *src; + const char *strtab; + unsigned int i, nsrc, ndst; + + /* Put symbol section at end of init part of module. */ + symsect->sh_flags |= SHF_ALLOC; + symsect->sh_entsize = get_offset(mod, &mod->init_size, symsect, + symindex) | INIT_OFFSET_MASK; + DEBUGP("\t%s\n", secstrings + symsect->sh_name); + + src = (void *)hdr + symsect->sh_offset; + nsrc = symsect->sh_size / sizeof(*src); + strtab = (void *)hdr + strsect->sh_offset; + for (ndst = i = 1; i < nsrc; ++i, ++src) + if (is_core_symbol(src, sechdrs, hdr->e_shnum)) { + unsigned int j = src->st_name; + + while(!__test_and_set_bit(j, strmap) && strtab[j]) + ++j; + ++ndst; + } + + /* Append room for core symbols at end of core part. */ + symoffs = ALIGN(mod->core_size, symsect->sh_addralign ?: 1); + mod->core_size = symoffs + ndst * sizeof(Elf_Sym); + + /* Put string table section at end of init part of module. */ + strsect->sh_flags |= SHF_ALLOC; + strsect->sh_entsize = get_offset(mod, &mod->init_size, strsect, + strindex) | INIT_OFFSET_MASK; + DEBUGP("\t%s\n", secstrings + strsect->sh_name); + + /* Append room for core symbols' strings at end of core part. */ + *pstroffs = mod->core_size; + __set_bit(0, strmap); + mod->core_size += bitmap_weight(strmap, strsect->sh_size); + + return symoffs; +} + static void add_kallsyms(struct module *mod, Elf_Shdr *sechdrs, + unsigned int shnum, unsigned int symindex, unsigned int strindex, - const char *secstrings) + unsigned long symoffs, + unsigned long stroffs, + const char *secstrings, + unsigned long *strmap) { - unsigned int i; + unsigned int i, ndst; + const Elf_Sym *src; + Elf_Sym *dst; + char *s; mod->symtab = (void *)sechdrs[symindex].sh_addr; mod->num_symtab = sechdrs[symindex].sh_size / sizeof(Elf_Sym); @@ -1852,13 +1839,46 @@ static void add_kallsyms(struct module *mod, for (i = 0; i < mod->num_symtab; i++) mod->symtab[i].st_info = elf_type(&mod->symtab[i], sechdrs, secstrings, mod); + + mod->core_symtab = dst = mod->module_core + symoffs; + src = mod->symtab; + *dst = *src; + for (ndst = i = 1; i < mod->num_symtab; ++i, ++src) { + if (!is_core_symbol(src, sechdrs, shnum)) + continue; + dst[ndst] = *src; + dst[ndst].st_name = bitmap_weight(strmap, dst[ndst].st_name); + ++ndst; + } + mod->core_num_syms = ndst; + + mod->core_strtab = s = mod->module_core + stroffs; + for (*s = 0, i = 1; i < sechdrs[strindex].sh_size; ++i) + if (test_bit(i, strmap)) + *++s = mod->strtab[i]; } #else +static inline unsigned long layout_symtab(struct module *mod, + Elf_Shdr *sechdrs, + unsigned int symindex, + unsigned int strindex, + const Elf_Ehdr *hdr, + const char *secstrings, + unsigned long *pstroffs, + unsigned long *strmap) +{ + return 0; +} + static inline void add_kallsyms(struct module *mod, Elf_Shdr *sechdrs, + unsigned int shnum, unsigned int symindex, unsigned int strindex, - const char *secstrings) + unsigned long symoffs, + unsigned long stroffs, + const char *secstrings, + const unsigned long *strmap) { } #endif /* CONFIG_KALLSYMS */ @@ -1886,6 +1906,33 @@ static void *module_alloc_update_bounds(unsigned long size) return ret; } +#ifdef CONFIG_DEBUG_KMEMLEAK +static void kmemleak_load_module(struct module *mod, Elf_Ehdr *hdr, + Elf_Shdr *sechdrs, char *secstrings) +{ + unsigned int i; + + /* only scan the sections containing data */ + kmemleak_scan_area(mod, sizeof(struct module), GFP_KERNEL); + + for (i = 1; i < hdr->e_shnum; i++) { + if (!(sechdrs[i].sh_flags & SHF_ALLOC)) + continue; + if (strncmp(secstrings + sechdrs[i].sh_name, ".data", 5) != 0 + && strncmp(secstrings + sechdrs[i].sh_name, ".bss", 4) != 0) + continue; + + kmemleak_scan_area((void *)sechdrs[i].sh_addr, + sechdrs[i].sh_size, GFP_KERNEL); + } +} +#else +static inline void kmemleak_load_module(struct module *mod, Elf_Ehdr *hdr, + Elf_Shdr *sechdrs, char *secstrings) +{ +} +#endif + /* Allocate and load the module: note that size of section 0 is always zero, and we rely on this for optional sections. */ static noinline struct module *load_module(void __user *umod, @@ -1900,11 +1947,11 @@ static noinline struct module *load_module(void __user *umod, unsigned int symindex = 0; unsigned int strindex = 0; unsigned int modindex, versindex, infoindex, pcpuindex; - unsigned int num_mcount; struct module *mod; long err = 0; void *percpu = NULL, *ptr = NULL; /* Stops spurious gcc warning */ - unsigned long *mseg; + unsigned long symoffs, stroffs, *strmap; + mm_segment_t old_fs; DEBUGP("load_module: umod=%p, len=%lu, uargs=%p\n", @@ -1917,12 +1964,6 @@ static noinline struct module *load_module(void __user *umod, if (len > 64 * 1024 * 1024 || (hdr = vmalloc(len)) == NULL) return ERR_PTR(-ENOMEM); - /* Create stop_machine threads since the error path relies on - * a non-failing stop_machine call. */ - err = stop_machine_create(); - if (err) - goto free_hdr; - if (copy_from_user(hdr, umod, len) != 0) { err = -EFAULT; goto free_hdr; @@ -1963,7 +2004,7 @@ static noinline struct module *load_module(void __user *umod, } #ifndef CONFIG_MODULE_UNLOAD /* Don't load .exit sections */ - if (strncmp(secstrings+sechdrs[i].sh_name, ".exit", 5) == 0) + if (strstarts(secstrings+sechdrs[i].sh_name, ".exit")) sechdrs[i].sh_flags &= ~(unsigned long)SHF_ALLOC; #endif } @@ -1992,11 +2033,6 @@ static noinline struct module *load_module(void __user *umod, /* Don't keep modinfo and version sections. */ sechdrs[infoindex].sh_flags &= ~(unsigned long)SHF_ALLOC; sechdrs[versindex].sh_flags &= ~(unsigned long)SHF_ALLOC; -#ifdef CONFIG_KALLSYMS - /* Keep symbol and string tables for decoding later. */ - sechdrs[symindex].sh_flags |= SHF_ALLOC; - sechdrs[strindex].sh_flags |= SHF_ALLOC; -#endif /* Check module struct version now, before we try to use module. */ if (!check_modstruct_version(sechdrs, versindex, mod)) { @@ -2007,7 +2043,7 @@ static noinline struct module *load_module(void __user *umod, modmagic = get_modinfo(sechdrs, infoindex, "vermagic"); /* This is allowed: modprobe --force will invalidate it. */ if (!modmagic) { - err = try_to_force_load(mod, "magic"); + err = try_to_force_load(mod, "bad vermagic"); if (err) goto free_hdr; } else if (!same_magic(modmagic, vermagic, versindex)) { @@ -2032,6 +2068,13 @@ static noinline struct module *load_module(void __user *umod, goto free_hdr; } + strmap = kzalloc(BITS_TO_LONGS(sechdrs[strindex].sh_size) + * sizeof(long), GFP_KERNEL); + if (!strmap) { + err = -ENOMEM; + goto free_mod; + } + if (find_module(mod->name)) { err = -EEXIST; goto free_mod; @@ -2061,9 +2104,17 @@ static noinline struct module *load_module(void __user *umod, this is done generically; there doesn't appear to be any special cases for the architectures. */ layout_sections(mod, hdr, sechdrs, secstrings); + symoffs = layout_symtab(mod, sechdrs, symindex, strindex, hdr, + secstrings, &stroffs, strmap); /* Do the allocs. */ ptr = module_alloc_update_bounds(mod->core_size); + /* + * The pointer to this block is stored in the module structure + * which is inside the block. Just mark it as not being a + * leak. + */ + kmemleak_not_leak(ptr); if (!ptr) { err = -ENOMEM; goto free_percpu; @@ -2072,6 +2123,13 @@ static noinline struct module *load_module(void __user *umod, mod->module_core = ptr; ptr = module_alloc_update_bounds(mod->init_size); + /* + * The pointer to this block is stored in the module structure + * which is inside the block. This block doesn't need to be + * scanned as it contains data and code that will be freed + * after the module is initialized. + */ + kmemleak_ignore(ptr); if (!ptr && mod->init_size) { err = -ENOMEM; goto free_core; @@ -2102,6 +2160,7 @@ static noinline struct module *load_module(void __user *umod, } /* Module has been moved. */ mod = (void *)sechdrs[modindex].sh_addr; + kmemleak_load_module(mod, hdr, sechdrs, secstrings); #if defined(CONFIG_MODULE_UNLOAD) && defined(CONFIG_SMP) mod->refptr = percpu_modalloc(sizeof(local_t), __alignof__(local_t), @@ -2175,18 +2234,36 @@ static noinline struct module *load_module(void __user *umod, mod->unused_gpl_crcs = section_addr(hdr, sechdrs, secstrings, "__kcrctab_unused_gpl"); #endif - -#ifdef CONFIG_MARKERS - mod->markers = section_objs(hdr, sechdrs, secstrings, "__markers", - sizeof(*mod->markers), &mod->num_markers); +#ifdef CONFIG_CONSTRUCTORS + mod->ctors = section_objs(hdr, sechdrs, secstrings, ".ctors", + sizeof(*mod->ctors), &mod->num_ctors); #endif + #ifdef CONFIG_TRACEPOINTS mod->tracepoints = section_objs(hdr, sechdrs, secstrings, "__tracepoints", sizeof(*mod->tracepoints), &mod->num_tracepoints); #endif - +#ifdef CONFIG_EVENT_TRACING + mod->trace_events = section_objs(hdr, sechdrs, secstrings, + "_ftrace_events", + sizeof(*mod->trace_events), + &mod->num_trace_events); + /* + * This section contains pointers to allocated objects in the trace + * code and not scanning it leads to false positives. + */ + kmemleak_scan_area(mod->trace_events, sizeof(*mod->trace_events) * + mod->num_trace_events, GFP_KERNEL); +#endif +#ifdef CONFIG_FTRACE_MCOUNT_RECORD + /* sechdrs[0].sh_size is always zero */ + mod->ftrace_callsites = section_objs(hdr, sechdrs, secstrings, + "__mcount_loc", + sizeof(*mod->ftrace_callsites), + &mod->num_ftrace_callsites); +#endif #ifdef CONFIG_MODVERSIONS if ((mod->num_syms && !mod->crcs) || (mod->num_gpl_syms && !mod->gpl_crcs) @@ -2196,8 +2273,8 @@ static noinline struct module *load_module(void __user *umod, || (mod->num_unused_gpl_syms && !mod->unused_gpl_crcs) #endif ) { - printk(KERN_WARNING "%s: No versions for exported symbols.\n", mod->name); - err = try_to_force_load(mod, "nocrc"); + err = try_to_force_load(mod, + "no versions for exported symbols"); if (err) goto cleanup; } @@ -2239,7 +2316,10 @@ static noinline struct module *load_module(void __user *umod, percpu_modcopy(mod->percpu, (void *)sechdrs[pcpuindex].sh_addr, sechdrs[pcpuindex].sh_size); - add_kallsyms(mod, sechdrs, symindex, strindex, secstrings); + add_kallsyms(mod, sechdrs, hdr->e_shnum, symindex, strindex, + symoffs, stroffs, secstrings, strmap); + kfree(strmap); + strmap = NULL; if (!mod->taints) { struct _ddebug *debug; @@ -2251,11 +2331,6 @@ static noinline struct module *load_module(void __user *umod, dynamic_debug_setup(debug, num_debug); } - /* sechdrs[0].sh_size is always zero */ - mseg = section_objs(hdr, sechdrs, secstrings, "__mcount_loc", - sizeof(*mseg), &num_mcount); - ftrace_init_module(mod, mseg, mseg + num_mcount); - err = module_finalize(hdr, sechdrs, mod); if (err < 0) goto cleanup; @@ -2305,22 +2380,25 @@ static noinline struct module *load_module(void __user *umod, /* Get rid of temporary copy */ vfree(hdr); - stop_machine_destroy(); + trace_module_load(mod); + /* Done! */ return mod; unlink: - stop_machine(__unlink_module, mod, NULL); + /* Unlink carefully: kallsyms could be walking list. */ + list_del_rcu(&mod->list); + synchronize_sched(); module_arch_cleanup(mod); cleanup: + free_modinfo(mod); kobject_del(&mod->mkobj.kobj); kobject_put(&mod->mkobj.kobj); - ftrace_release(mod->module_core, mod->core_size); free_unload: module_unload_free(mod); #if defined(CONFIG_MODULE_UNLOAD) && defined(CONFIG_SMP) - free_init: percpu_modfree(mod->refptr); + free_init: #endif module_free(mod, mod->module_init); free_core: @@ -2331,9 +2409,9 @@ static noinline struct module *load_module(void __user *umod, percpu_modfree(percpu); free_mod: kfree(args); + kfree(strmap); free_hdr: vfree(hdr); - stop_machine_destroy(); return ERR_PTR(err); truncated: @@ -2342,6 +2420,17 @@ static noinline struct module *load_module(void __user *umod, goto free_hdr; } +/* Call module constructors. */ +static void do_mod_ctors(struct module *mod) +{ +#ifdef CONFIG_CONSTRUCTORS + unsigned long i; + + for (i = 0; i < mod->num_ctors; i++) + mod->ctors[i](); +#endif +} + /* This is where the real work happens */ SYSCALL_DEFINE3(init_module, void __user *, umod, unsigned long, len, const char __user *, uargs) @@ -2350,7 +2439,7 @@ SYSCALL_DEFINE3(init_module, void __user *, umod, int ret = 0; /* Must have permission */ - if (!capable(CAP_SYS_MODULE)) + if (!capable(CAP_SYS_MODULE) || modules_disabled) return -EPERM; /* Only one module load at a time, please */ @@ -2370,6 +2459,7 @@ SYSCALL_DEFINE3(init_module, void __user *, umod, blocking_notifier_call_chain(&module_notify_list, MODULE_STATE_COMING, mod); + do_mod_ctors(mod); /* Start the module */ if (mod->init != NULL) ret = do_one_initcall(mod->init); @@ -2388,9 +2478,9 @@ SYSCALL_DEFINE3(init_module, void __user *, umod, return ret; } if (ret > 0) { - printk(KERN_WARNING "%s: '%s'->init suspiciously returned %d, " - "it should follow 0/-E convention\n" - KERN_WARNING "%s: loading module anyway...\n", + printk(KERN_WARNING +"%s: '%s'->init suspiciously returned %d, it should follow 0/-E convention\n" +"%s: loading module anyway...\n", __func__, mod->name, ret, __func__); dump_stack(); @@ -2402,9 +2492,18 @@ SYSCALL_DEFINE3(init_module, void __user *, umod, blocking_notifier_call_chain(&module_notify_list, MODULE_STATE_LIVE, mod); + /* We need to finish all async code before the module init sequence is done */ + async_synchronize_full(); + mutex_lock(&module_mutex); /* Drop initial reference. */ module_put(mod); + trim_init_extable(mod); +#ifdef CONFIG_KALLSYMS + mod->num_symtab = mod->core_num_syms; + mod->symtab = mod->core_symtab; + mod->strtab = mod->core_strtab; +#endif module_free(mod, mod->module_init); mod->module_init = NULL; mod->init_size = 0; @@ -2610,6 +2709,25 @@ unsigned long module_kallsyms_lookup_name(const char *name) preempt_enable(); return ret; } + +int module_kallsyms_on_each_symbol(int (*fn)(void *, const char *, + struct module *, unsigned long), + void *data) +{ + struct module *mod; + unsigned int i; + int ret; + + list_for_each_entry(mod, &modules, list) { + for (i = 0; i < mod->num_symtab; i++) { + ret = fn(data, mod->strtab + mod->symtab[i].st_name, + mod, mod->symtab[i].st_value); + if (ret != 0) + return ret; + } + } + return 0; +} #endif /* CONFIG_KALLSYMS */ static char *module_flags(struct module *mod, char *buf) @@ -2745,29 +2863,31 @@ const struct exception_table_entry *search_module_extables(unsigned long addr) } /* - * Is this a valid module address? + * is_module_address - is this address inside a module? + * @addr: the address to check. + * + * See is_module_text_address() if you simply want to see if the address + * is code (not data). */ -int is_module_address(unsigned long addr) +bool is_module_address(unsigned long addr) { - struct module *mod; + bool ret; preempt_disable(); - - list_for_each_entry_rcu(mod, &modules, list) { - if (within_module_core(addr, mod)) { - preempt_enable(); - return 1; - } - } - + ret = __module_address(addr) != NULL; preempt_enable(); - return 0; + return ret; } - -/* Is this a valid kernel address? */ -__notrace_funcgraph struct module *__module_text_address(unsigned long addr) +/* + * __module_address - get the module which contains an address. + * @addr: the address. + * + * Must be called with preempt disabled or module mutex held so that + * module doesn't get freed during this. + */ +struct module *__module_address(unsigned long addr) { struct module *mod; @@ -2775,22 +2895,51 @@ __notrace_funcgraph struct module *__module_text_address(unsigned long addr) return NULL; list_for_each_entry_rcu(mod, &modules, list) - if (within(addr, mod->module_init, mod->init_text_size) - || within(addr, mod->module_core, mod->core_text_size)) + if (within_module_core(addr, mod) + || within_module_init(addr, mod)) return mod; return NULL; } +EXPORT_SYMBOL_GPL(__module_address); -struct module *module_text_address(unsigned long addr) +/* + * is_module_text_address - is this address inside module code? + * @addr: the address to check. + * + * See is_module_address() if you simply want to see if the address is + * anywhere in a module. See kernel_text_address() for testing if an + * address corresponds to kernel or module code. + */ +bool is_module_text_address(unsigned long addr) { - struct module *mod; + bool ret; preempt_disable(); - mod = __module_text_address(addr); + ret = __module_text_address(addr) != NULL; preempt_enable(); + return ret; +} + +/* + * __module_text_address - get the module whose code contains an address. + * @addr: the address. + * + * Must be called with preempt disabled or module mutex held so that + * module doesn't get freed during this. + */ +struct module *__module_text_address(unsigned long addr) +{ + struct module *mod = __module_address(addr); + if (mod) { + /* Make sure it's within the text section. */ + if (!within(addr, mod->module_init, mod->init_text_size) + && !within(addr, mod->module_core, mod->core_text_size)) + mod = NULL; + } return mod; } +EXPORT_SYMBOL_GPL(__module_text_address); /* Don't grab lock, we're oopsing. */ void print_modules(void) @@ -2798,7 +2947,7 @@ void print_modules(void) struct module *mod; char buf[8]; - printk("Modules linked in:"); + printk(KERN_DEFAULT "Modules linked in:"); /* Most callers should already have preempt disabled, but make sure */ preempt_disable(); list_for_each_entry_rcu(mod, &modules, list) @@ -2810,23 +2959,16 @@ void print_modules(void) } #ifdef CONFIG_MODVERSIONS -/* Generate the signature for struct module here, too, for modversions. */ -void struct_module(struct module *mod) { return; } -EXPORT_SYMBOL(struct_module); -#endif - -#ifdef CONFIG_MARKERS -void module_update_markers(void) +/* Generate the signature for all relevant module structures here. + * If these change, we don't want to try to parse the module. */ +void module_layout(struct module *mod, + struct modversion_info *ver, + struct kernel_param *kp, + struct kernel_symbol *ks, + struct tracepoint *tp) { - struct module *mod; - - mutex_lock(&module_mutex); - list_for_each_entry(mod, &modules, list) - if (!mod->taints) - marker_update_probe_range(mod->markers, - mod->markers + mod->num_markers); - mutex_unlock(&module_mutex); } +EXPORT_SYMBOL(module_layout); #endif #ifdef CONFIG_TRACEPOINTS