X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=kernel%2Fmodule.c;h=ba22484a987eb96a9d2bff0cdeede4b62a1d7156;hb=06eb23b1ba39c61ee5d5faeb42a097635693e370;hp=91fe6958b6e1b253f98c2ab08518693df00a1497;hpb=9a4b9708f1f2eaf5edd619df578cf3afec36eb82;p=safe%2Fjmp%2Flinux-2.6 diff --git a/kernel/module.c b/kernel/module.c index 91fe695..ba22484 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -20,11 +20,13 @@ #include #include #include +#include #include #include #include #include #include +#include #include #include #include @@ -41,13 +43,14 @@ #include #include #include -#include +#include #include -#include #include #include - -extern int module_sysfs_initialized; +#include +#include +#include +#include #if 0 #define DEBUGP printk @@ -63,12 +66,18 @@ extern int module_sysfs_initialized; #define INIT_OFFSET_MASK (1UL << (BITS_PER_LONG-1)) /* List of modules, protected by module_mutex or preempt_disable - * (add/delete uses stop_machine). */ + * (delete uses stop_machine/add uses RCU list operations). */ static DEFINE_MUTEX(module_mutex); static LIST_HEAD(modules); +/* 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 */ +static unsigned long module_addr_min = -1UL, module_addr_max = 0; + int register_module_notifier(struct notifier_block * nb) { return blocking_notifier_chain_register(&module_notify_list, nb); @@ -86,14 +95,17 @@ EXPORT_SYMBOL(unregister_module_notifier); static inline int strong_try_module_get(struct module *mod) { if (mod && mod->state == MODULE_STATE_COMING) + return -EBUSY; + if (try_module_get(mod)) return 0; - return try_module_get(mod); + else + return -ENOENT; } static inline void add_taint_module(struct module *mod, unsigned flag) { add_taint(flag); - mod->taints |= flag; + mod->taints |= (1U << flag); } /* @@ -123,6 +135,29 @@ static unsigned int find_sec(Elf_Ehdr *hdr, return 0; } +/* Find a module section, or NULL. */ +static void *section_addr(Elf_Ehdr *hdr, Elf_Shdr *shdrs, + const char *secstrings, const char *name) +{ + /* Section 0 has sh_addr 0. */ + return (void *)shdrs[find_sec(hdr, shdrs, secstrings, name)].sh_addr; +} + +/* Find a module section, or NULL. Fill in number of "objects" in section. */ +static void *section_objs(Elf_Ehdr *hdr, + Elf_Shdr *sechdrs, + const char *secstrings, + const char *name, + size_t object_size, + unsigned int *num) +{ + unsigned int sec = find_sec(hdr, sechdrs, secstrings, name); + + /* Section 0 has sh_addr 0 and sh_size 0. */ + *num = sechdrs[sec].sh_size / object_size; + return (void *)sechdrs[sec].sh_addr; +} + /* Provided by the linker */ extern const struct kernel_symbol __start___ksymtab[]; extern const struct kernel_symbol __stop___ksymtab[]; @@ -130,17 +165,19 @@ extern const struct kernel_symbol __start___ksymtab_gpl[]; extern const struct kernel_symbol __stop___ksymtab_gpl[]; extern const struct kernel_symbol __start___ksymtab_gpl_future[]; extern const struct kernel_symbol __stop___ksymtab_gpl_future[]; -extern const struct kernel_symbol __start___ksymtab_unused[]; -extern const struct kernel_symbol __stop___ksymtab_unused[]; -extern const struct kernel_symbol __start___ksymtab_unused_gpl[]; -extern const struct kernel_symbol __stop___ksymtab_unused_gpl[]; extern const struct kernel_symbol __start___ksymtab_gpl_future[]; extern const struct kernel_symbol __stop___ksymtab_gpl_future[]; extern const unsigned long __start___kcrctab[]; extern const unsigned long __start___kcrctab_gpl[]; extern const unsigned long __start___kcrctab_gpl_future[]; +#ifdef CONFIG_UNUSED_SYMBOLS +extern const struct kernel_symbol __start___ksymtab_unused[]; +extern const struct kernel_symbol __stop___ksymtab_unused[]; +extern const struct kernel_symbol __start___ksymtab_unused_gpl[]; +extern const struct kernel_symbol __stop___ksymtab_unused_gpl[]; extern const unsigned long __start___kcrctab_unused[]; extern const unsigned long __start___kcrctab_unused_gpl[]; +#endif #ifndef CONFIG_MODVERSIONS #define symversion(base, idx) NULL @@ -148,145 +185,172 @@ extern const unsigned long __start___kcrctab_unused_gpl[]; #define symversion(base, idx) ((base != NULL) ? ((base) + (idx)) : NULL) #endif -/* lookup symbol in given range of kernel_symbols */ -static const struct kernel_symbol *lookup_symbol(const char *name, - const struct kernel_symbol *start, - const struct kernel_symbol *stop) -{ - const struct kernel_symbol *ks = start; - for (; ks < stop; ks++) - if (strcmp(ks->name, name) == 0) - return ks; - return NULL; -} +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 void printk_unused_warning(const char *name) +static bool each_symbol_in_section(const struct symsearch *arr, + unsigned int arrsize, + struct module *owner, + bool (*fn)(const struct symsearch *syms, + struct module *owner, + unsigned int symnum, void *data), + void *data) { - printk(KERN_WARNING "Symbol %s is marked as UNUSED, " - "however this module is using it.\n", name); - printk(KERN_WARNING "This symbol will go away in the future.\n"); - printk(KERN_WARNING "Please evalute if this is the right api to use, " - "and if it really is, submit a report the linux kernel " - "mailinglist together with submitting your code for " - "inclusion.\n"); + unsigned int i, j; + + for (j = 0; j < arrsize; j++) { + for (i = 0; i < arr[j].stop - arr[j].start; i++) + if (fn(&arr[j], owner, i, data)) + return true; + } + + return false; } -/* Find a symbol, return value, crc and module which owns it */ -static unsigned long __find_symbol(const char *name, - struct module **owner, - const unsigned long **crc, - int gplok) +/* 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) { struct module *mod; - const struct kernel_symbol *ks; + const struct symsearch arr[] = { + { __start___ksymtab, __stop___ksymtab, __start___kcrctab, + NOT_GPL_ONLY, false }, + { __start___ksymtab_gpl, __stop___ksymtab_gpl, + __start___kcrctab_gpl, + GPL_ONLY, false }, + { __start___ksymtab_gpl_future, __stop___ksymtab_gpl_future, + __start___kcrctab_gpl_future, + WILL_BE_GPL_ONLY, false }, +#ifdef CONFIG_UNUSED_SYMBOLS + { __start___ksymtab_unused, __stop___ksymtab_unused, + __start___kcrctab_unused, + NOT_GPL_ONLY, true }, + { __start___ksymtab_unused_gpl, __stop___ksymtab_unused_gpl, + __start___kcrctab_unused_gpl, + GPL_ONLY, true }, +#endif + }; - /* Core kernel first. */ - *owner = NULL; - ks = lookup_symbol(name, __start___ksymtab, __stop___ksymtab); - if (ks) { - *crc = symversion(__start___kcrctab, (ks - __start___ksymtab)); - return ks->value; - } - if (gplok) { - ks = lookup_symbol(name, __start___ksymtab_gpl, - __stop___ksymtab_gpl); - if (ks) { - *crc = symversion(__start___kcrctab_gpl, - (ks - __start___ksymtab_gpl)); - return ks->value; - } + if (each_symbol_in_section(arr, ARRAY_SIZE(arr), NULL, fn, data)) + return true; + + list_for_each_entry_rcu(mod, &modules, list) { + struct symsearch arr[] = { + { mod->syms, mod->syms + mod->num_syms, mod->crcs, + NOT_GPL_ONLY, false }, + { mod->gpl_syms, mod->gpl_syms + mod->num_gpl_syms, + mod->gpl_crcs, + GPL_ONLY, false }, + { mod->gpl_future_syms, + mod->gpl_future_syms + mod->num_gpl_future_syms, + mod->gpl_future_crcs, + WILL_BE_GPL_ONLY, false }, +#ifdef CONFIG_UNUSED_SYMBOLS + { mod->unused_syms, + mod->unused_syms + mod->num_unused_syms, + mod->unused_crcs, + NOT_GPL_ONLY, true }, + { mod->unused_gpl_syms, + mod->unused_gpl_syms + mod->num_unused_gpl_syms, + mod->unused_gpl_crcs, + GPL_ONLY, true }, +#endif + }; + + if (each_symbol_in_section(arr, ARRAY_SIZE(arr), mod, fn, data)) + return true; } - ks = lookup_symbol(name, __start___ksymtab_gpl_future, - __stop___ksymtab_gpl_future); - if (ks) { - if (!gplok) { + return false; +} + +struct find_symbol_arg { + /* Input */ + const char *name; + bool gplok; + bool warn; + + /* Output */ + struct module *owner; + const unsigned long *crc; + unsigned long value; +}; + +static bool find_symbol_in_section(const struct symsearch *syms, + struct module *owner, + unsigned int symnum, void *data) +{ + struct find_symbol_arg *fsa = data; + + if (strcmp(syms->start[symnum].name, fsa->name) != 0) + return false; + + if (!fsa->gplok) { + if (syms->licence == GPL_ONLY) + return false; + if (syms->licence == WILL_BE_GPL_ONLY && fsa->warn) { printk(KERN_WARNING "Symbol %s is being used " "by a non-GPL module, which will not " - "be allowed in the future\n", name); + "be allowed in the future\n", fsa->name); printk(KERN_WARNING "Please see the file " "Documentation/feature-removal-schedule.txt " - "in the kernel source tree for more " - "details.\n"); + "in the kernel source tree for more details.\n"); } - *crc = symversion(__start___kcrctab_gpl_future, - (ks - __start___ksymtab_gpl_future)); - return ks->value; } - ks = lookup_symbol(name, __start___ksymtab_unused, - __stop___ksymtab_unused); - if (ks) { - printk_unused_warning(name); - *crc = symversion(__start___kcrctab_unused, - (ks - __start___ksymtab_unused)); - return ks->value; +#ifdef CONFIG_UNUSED_SYMBOLS + if (syms->unused && fsa->warn) { + printk(KERN_WARNING "Symbol %s is marked as UNUSED, " + "however this module is using it.\n", fsa->name); + printk(KERN_WARNING + "This symbol will go away in the future.\n"); + printk(KERN_WARNING + "Please evalute if this is the right api to use and if " + "it really is, submit a report the linux kernel " + "mailinglist together with submitting your code for " + "inclusion.\n"); } +#endif - if (gplok) - ks = lookup_symbol(name, __start___ksymtab_unused_gpl, - __stop___ksymtab_unused_gpl); - if (ks) { - printk_unused_warning(name); - *crc = symversion(__start___kcrctab_unused_gpl, - (ks - __start___ksymtab_unused_gpl)); - return ks->value; - } + fsa->owner = owner; + fsa->crc = symversion(syms->crcs, symnum); + fsa->value = syms->start[symnum].value; + return true; +} - /* Now try modules. */ - list_for_each_entry(mod, &modules, list) { - *owner = mod; - ks = lookup_symbol(name, mod->syms, mod->syms + mod->num_syms); - if (ks) { - *crc = symversion(mod->crcs, (ks - mod->syms)); - return ks->value; - } +/* Find a symbol, return value, (optional) crc and (optional) module + * which owns it */ +static unsigned long find_symbol(const char *name, + struct module **owner, + const unsigned long **crc, + bool gplok, + bool warn) +{ + struct find_symbol_arg fsa; - if (gplok) { - ks = lookup_symbol(name, mod->gpl_syms, - mod->gpl_syms + mod->num_gpl_syms); - if (ks) { - *crc = symversion(mod->gpl_crcs, - (ks - mod->gpl_syms)); - return ks->value; - } - } - ks = lookup_symbol(name, mod->unused_syms, mod->unused_syms + mod->num_unused_syms); - if (ks) { - printk_unused_warning(name); - *crc = symversion(mod->unused_crcs, (ks - mod->unused_syms)); - return ks->value; - } + fsa.name = name; + fsa.gplok = gplok; + fsa.warn = warn; - if (gplok) { - ks = lookup_symbol(name, mod->unused_gpl_syms, - mod->unused_gpl_syms + mod->num_unused_gpl_syms); - if (ks) { - printk_unused_warning(name); - *crc = symversion(mod->unused_gpl_crcs, - (ks - mod->unused_gpl_syms)); - return ks->value; - } - } - ks = lookup_symbol(name, mod->gpl_future_syms, - (mod->gpl_future_syms + - mod->num_gpl_future_syms)); - if (ks) { - if (!gplok) { - printk(KERN_WARNING "Symbol %s is being used " - "by a non-GPL module, which will not " - "be allowed in the future\n", name); - printk(KERN_WARNING "Please see the file " - "Documentation/feature-removal-schedule.txt " - "in the kernel source tree for more " - "details.\n"); - } - *crc = symversion(mod->gpl_future_crcs, - (ks - mod->gpl_future_syms)); - return ks->value; - } + if (each_symbol(find_symbol_in_section, &fsa)) { + if (owner) + *owner = fsa.owner; + if (crc) + *crc = fsa.crc; + return fsa.value; } + DEBUGP("Failed to find symbol %s\n", name); - return 0; + return -ENOENT; } /* Search for module by name: must hold module_mutex. */ @@ -339,9 +403,6 @@ static inline unsigned int block_size(int val) return val; } -/* Created by linker magic */ -extern char __per_cpu_start[], __per_cpu_end[]; - static void *percpu_modalloc(unsigned long size, unsigned long align, const char *name) { @@ -426,6 +487,14 @@ static unsigned int find_pcpusec(Elf_Ehdr *hdr, return find_sec(hdr, sechdrs, secstrings, ".data.percpu"); } +static void percpu_modcopy(void *pcpudest, const void *from, unsigned long size) +{ + int cpu; + + for_each_possible_cpu(cpu) + memcpy(pcpudest + per_cpu_offset(cpu), from, size); +} + static int percpu_modinit(void) { pcpu_num_used = 2; @@ -498,17 +567,19 @@ static struct module_attribute modinfo_##field = { \ MODINFO_ATTR(version); MODINFO_ATTR(srcversion); +static char last_unloaded_module[MODULE_NAME_LEN+1]; + #ifdef CONFIG_MODULE_UNLOAD /* Init the unload section of the module. */ static void module_unload_init(struct module *mod) { - unsigned int i; + int cpu; INIT_LIST_HEAD(&mod->modules_which_use_me); - for (i = 0; i < NR_CPUS; i++) - local_set(&mod->ref[i].count, 0); + for_each_possible_cpu(cpu) + local_set(__module_ref_addr(mod, cpu), 0); /* Hold reference count during initialization. */ - local_set(&mod->ref[raw_smp_processor_id()].count, 1); + local_set(__module_ref_addr(mod, raw_smp_processor_id()), 1); /* Backwards compatibility macros put refcount during init. */ mod->waiter = current; } @@ -539,11 +610,21 @@ static int already_uses(struct module *a, struct module *b) static int use_module(struct module *a, struct module *b) { struct module_use *use; - int no_warn; + int no_warn, err; if (b == NULL || already_uses(a, b)) return 1; - if (!strong_try_module_get(b)) + /* If we're interrupted or time out, we fail. */ + if (wait_event_interruptible_timeout( + module_wq, (err = strong_try_module_get(b)) != -EBUSY, + 30 * HZ) <= 0) { + printk("%s: gave up waiting for init of module %s.\n", + a->name, b->name); + return 0; + } + + /* If strong_try_module_get() returned a different error, we fail. */ + if (err) return 0; DEBUGP("Allocating new usage for %s.\n", a->name); @@ -609,8 +690,8 @@ static int __try_stop_module(void *_sref) { struct stopref *sref = _sref; - /* If it's not unused, quit unless we are told to block. */ - if ((sref->flags & O_NONBLOCK) && module_refcount(sref->mod) != 0) { + /* If it's not unused, quit unless we're forcing. */ + if (module_refcount(sref->mod) != 0) { if (!(*sref->forced = try_force_unload(sref->flags))) return -EWOULDBLOCK; } @@ -622,17 +703,25 @@ static int __try_stop_module(void *_sref) static int try_stop_module(struct module *mod, int flags, int *forced) { - struct stopref sref = { mod, flags, forced }; + if (flags & O_NONBLOCK) { + struct stopref sref = { mod, flags, forced }; - return stop_machine_run(__try_stop_module, &sref, NR_CPUS); + return stop_machine(__try_stop_module, &sref, NULL); + } else { + /* We don't need to stop the machine for this. */ + mod->state = MODULE_STATE_GOING; + synchronize_sched(); + return 0; + } } unsigned int module_refcount(struct module *mod) { - unsigned int i, total = 0; + unsigned int total = 0; + int cpu; - for (i = 0; i < NR_CPUS; i++) - total += local_read(&mod->ref[i].count); + for_each_possible_cpu(cpu) + total += local_read(__module_ref_addr(mod, cpu)); return total; } EXPORT_SYMBOL(module_refcount); @@ -642,7 +731,7 @@ static void free_module(struct module *mod); static void wait_for_zero_refcount(struct module *mod) { - /* Since we might sleep for some time, drop the semaphore first */ + /* Since we might sleep for some time, release the mutex first */ mutex_unlock(&module_mutex); for (;;) { DEBUGP("Looking at refcount...\n"); @@ -655,8 +744,8 @@ static void wait_for_zero_refcount(struct module *mod) mutex_lock(&module_mutex); } -asmlinkage long -sys_delete_module(const char __user *name_user, unsigned int flags) +SYSCALL_DEFINE2(delete_module, const char __user *, name_user, + unsigned int, flags) { struct module *mod; char name[MODULE_NAME_LEN]; @@ -669,8 +758,16 @@ sys_delete_module(const char __user *name_user, unsigned int flags) return -EFAULT; name[MODULE_NAME_LEN-1] = '\0'; - if (mutex_lock_interruptible(&module_mutex) != 0) - return -EINTR; + /* Create stop_machine threads since free_module relies on + * a non-failing stop_machine call. */ + ret = stop_machine_create(); + if (ret) + return ret; + + if (mutex_lock_interruptible(&module_mutex) != 0) { + ret = -EINTR; + goto out_stop; + } mod = find_module(name); if (!mod) { @@ -715,20 +812,27 @@ sys_delete_module(const char __user *name_user, unsigned int flags) if (!forced && module_refcount(mod) != 0) wait_for_zero_refcount(mod); + mutex_unlock(&module_mutex); /* Final destruction now noone is using it. */ - if (mod->exit != NULL) { - mutex_unlock(&module_mutex); + if (mod->exit != NULL) mod->exit(); - mutex_lock(&module_mutex); - } + blocking_notifier_call_chain(&module_notify_list, + MODULE_STATE_GOING, mod); + async_synchronize_full(); + mutex_lock(&module_mutex); + /* Store the name of the last unloaded module for diagnostic purposes */ + strlcpy(last_unloaded_module, mod->name, sizeof(last_unloaded_module)); + unregister_dynamic_debug_module(mod->name); free_module(mod); out: mutex_unlock(&module_mutex); +out_stop: + stop_machine_destroy(); return ret; } -static void print_unload_info(struct seq_file *m, struct module *mod) +static inline void print_unload_info(struct seq_file *m, struct module *mod) { struct module_use *use; int printed_something = 0; @@ -754,10 +858,9 @@ static void print_unload_info(struct seq_file *m, struct module *mod) void __symbol_put(const char *symbol) { struct module *owner; - const unsigned long *crc; preempt_disable(); - if (!__find_symbol(symbol, &owner, &crc, 1)) + if (IS_ERR_VALUE(find_symbol(symbol, &owner, NULL, true, false))) BUG(); module_put(owner); preempt_enable(); @@ -792,7 +895,7 @@ void module_put(struct module *module) { if (module) { unsigned int cpu = get_cpu(); - local_dec(&module->ref[cpu].count); + local_dec(__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); @@ -802,7 +905,7 @@ void module_put(struct module *module) EXPORT_SYMBOL(module_put); #else /* !CONFIG_MODULE_UNLOAD */ -static void print_unload_info(struct seq_file *m, struct module *mod) +static inline void print_unload_info(struct seq_file *m, struct module *mod) { /* We don't know the usage count, or what modules are using. */ seq_printf(m, " - -"); @@ -814,7 +917,7 @@ static inline void module_unload_free(struct module *mod) static inline int use_module(struct module *a, struct module *b) { - return strong_try_module_get(b); + return strong_try_module_get(b) == 0; } static inline void module_unload_init(struct module *mod) @@ -858,6 +961,19 @@ static struct module_attribute *modinfo_attrs[] = { static const char vermagic[] = VERMAGIC_STRING; +static int try_to_force_load(struct module *mod, const char *symname) +{ +#ifdef CONFIG_MODULE_FORCE_LOAD + if (!test_taint(TAINT_FORCED_MODULE)) + printk("%s: no version for \"%s\" found: kernel tainted.\n", + mod->name, symname); + add_taint_module(mod, TAINT_FORCED_MODULE); + return 0; +#else + return -ENOEXEC; +#endif +} + #ifdef CONFIG_MODVERSIONS static int check_version(Elf_Shdr *sechdrs, unsigned int versindex, @@ -872,6 +988,10 @@ static int check_version(Elf_Shdr *sechdrs, if (!crc) return 1; + /* No versions at all? modprobe --force does this. */ + if (versindex == 0) + return try_to_force_load(mod, symname) == 0; + versions = (void *) sechdrs[versindex].sh_addr; num_versions = sechdrs[versindex].sh_size / sizeof(struct modversion_info); @@ -882,18 +1002,19 @@ static int check_version(Elf_Shdr *sechdrs, if (versions[i].crc == *crc) return 1; - printk("%s: disagrees about version of symbol %s\n", - mod->name, symname); DEBUGP("Found checksum %lX vs module %lX\n", *crc, versions[i].crc); - return 0; + goto bad_version; } - /* Not in module's version table. OK, but that taints the kernel. */ - if (!(tainted & TAINT_FORCED_MODULE)) - printk("%s: no version for \"%s\" found: kernel tainted.\n", - mod->name, symname); - add_taint_module(mod, TAINT_FORCED_MODULE); - return 1; + + printk(KERN_WARNING "%s: no symbol version for %s\n", + mod->name, symname); + return 0; + +bad_version: + printk("%s: disagrees about version of symbol %s\n", + mod->name, symname); + return 0; } static inline int check_modstruct_version(Elf_Shdr *sechdrs, @@ -901,19 +1022,20 @@ static inline int check_modstruct_version(Elf_Shdr *sechdrs, struct module *mod) { const unsigned long *crc; - struct module *owner; - if (!__find_symbol("struct_module", &owner, &crc, 1)) + if (IS_ERR_VALUE(find_symbol("struct_module", NULL, &crc, true, false))) BUG(); - return check_version(sechdrs, versindex, "struct_module", mod, - crc); + return check_version(sechdrs, versindex, "struct_module", mod, crc); } -/* First part is kernel version, which we ignore. */ -static inline int same_magic(const char *amagic, const char *bmagic) +/* First part is kernel version, which we ignore if module has crcs. */ +static inline int same_magic(const char *amagic, const char *bmagic, + bool has_crcs) { - amagic += strcspn(amagic, " "); - bmagic += strcspn(bmagic, " "); + if (has_crcs) { + amagic += strcspn(amagic, " "); + bmagic += strcspn(bmagic, " "); + } return strcmp(amagic, bmagic) == 0; } #else @@ -933,7 +1055,8 @@ static inline int check_modstruct_version(Elf_Shdr *sechdrs, return 1; } -static inline int same_magic(const char *amagic, const char *bmagic) +static inline int same_magic(const char *amagic, const char *bmagic, + bool has_crcs) { return strcmp(amagic, bmagic) == 0; } @@ -950,24 +1073,37 @@ static unsigned long resolve_symbol(Elf_Shdr *sechdrs, unsigned long ret; const unsigned long *crc; - ret = __find_symbol(name, &owner, &crc, - !(mod->taints & TAINT_PROPRIETARY_MODULE)); - if (ret) { + ret = find_symbol(name, &owner, &crc, + !(mod->taints & (1 << TAINT_PROPRIETARY_MODULE)), true); + if (!IS_ERR_VALUE(ret)) { /* use_module can fail due to OOM, or module initialization or unloading */ if (!check_version(sechdrs, versindex, name, mod, crc) || !use_module(mod, owner)) - ret = 0; + ret = -EINVAL; } return ret; } - /* * /sys/module/foo/sections stuff * J. Corbet */ -#ifdef CONFIG_KALLSYMS +#if defined(CONFIG_KALLSYMS) && defined(CONFIG_SYSFS) +struct module_sect_attr +{ + struct module_attribute mattr; + char *name; + unsigned long address; +}; + +struct module_sect_attrs +{ + struct attribute_group grp; + unsigned int nsections; + struct module_sect_attr attrs[0]; +}; + static ssize_t module_sect_show(struct module_attribute *mattr, struct module *mod, char *buf) { @@ -978,7 +1114,7 @@ static ssize_t module_sect_show(struct module_attribute *mattr, static void free_sect_attrs(struct module_sect_attrs *sect_attrs) { - int section; + unsigned int section; for (section = 0; section < sect_attrs->nsections; section++) kfree(sect_attrs->attrs[section].name); @@ -1078,7 +1214,7 @@ static void free_notes_attrs(struct module_notes_attrs *notes_attrs, while (i-- > 0) sysfs_remove_bin_file(notes_attrs->dir, ¬es_attrs->attrs[i]); - kobject_del(notes_attrs->dir); + kobject_put(notes_attrs->dir); } kfree(notes_attrs); } @@ -1122,7 +1258,7 @@ static void add_notes_attrs(struct module *mod, unsigned int nsect, ++loaded; } - notes_attrs->dir = kobject_add_dir(&mod->mkobj.kobj, "notes"); + notes_attrs->dir = kobject_create_and_add("notes", &mod->mkobj.kobj); if (!notes_attrs->dir) goto out; @@ -1163,7 +1299,7 @@ static inline void add_notes_attrs(struct module *mod, unsigned int nsect, static inline void remove_notes_attrs(struct module *mod) { } -#endif /* CONFIG_KALLSYMS */ +#endif #ifdef CONFIG_SYSFS int module_add_modinfo_attrs(struct module *mod) @@ -1206,12 +1342,11 @@ void module_remove_modinfo_attrs(struct module *mod) } kfree(mod->modinfo_attrs); } -#endif -#ifdef CONFIG_SYSFS int mod_sysfs_init(struct module *mod) { int err; + struct kobject *kobj; if (!module_sysfs_initialized) { printk(KERN_ERR "%s: module sysfs not initialized\n", @@ -1219,15 +1354,25 @@ int mod_sysfs_init(struct module *mod) err = -EINVAL; goto out; } - memset(&mod->mkobj.kobj, 0, sizeof(mod->mkobj.kobj)); - err = kobject_set_name(&mod->mkobj.kobj, "%s", mod->name); - if (err) + + kobj = kset_find_obj(module_kset, mod->name); + if (kobj) { + printk(KERN_ERR "%s: module is already loaded\n", mod->name); + kobject_put(kobj); + err = -EINVAL; goto out; - kobj_set_kset_s(&mod->mkobj, module_subsys); + } + mod->mkobj.mod = mod; - kobject_init(&mod->mkobj.kobj); + memset(&mod->mkobj.kobj, 0, sizeof(mod->mkobj.kobj)); + mod->mkobj.kobj.kset = module_kset; + err = kobject_init_and_add(&mod->mkobj.kobj, &module_ktype, NULL, + "%s", mod->name); + if (err) + kobject_put(&mod->mkobj.kobj); + /* delay uevent until full sysfs population */ out: return err; } @@ -1238,12 +1383,7 @@ int mod_sysfs_setup(struct module *mod, { int err; - /* delay uevent until full sysfs population */ - err = kobject_add(&mod->mkobj.kobj); - if (err) - goto out; - - mod->holders_dir = kobject_add_dir(&mod->mkobj.kobj, "holders"); + mod->holders_dir = kobject_create_and_add("holders", &mod->mkobj.kobj); if (!mod->holders_dir) { err = -ENOMEM; goto out_unreg; @@ -1263,22 +1403,32 @@ int mod_sysfs_setup(struct module *mod, out_unreg_param: module_param_sysfs_remove(mod); out_unreg_holders: - kobject_unregister(mod->holders_dir); + kobject_put(mod->holders_dir); out_unreg: - kobject_del(&mod->mkobj.kobj); kobject_put(&mod->mkobj.kobj); -out: return err; } -#endif + +static void mod_sysfs_fini(struct module *mod) +{ + kobject_put(&mod->mkobj.kobj); +} + +#else /* CONFIG_SYSFS */ + +static void mod_sysfs_fini(struct module *mod) +{ +} + +#endif /* CONFIG_SYSFS */ static void mod_kobject_remove(struct module *mod) { module_remove_modinfo_attrs(mod); module_param_sysfs_remove(mod); - kobject_unregister(mod->mkobj.drivers_dir); - kobject_unregister(mod->holders_dir); - kobject_unregister(&mod->mkobj.kobj); + kobject_put(mod->mkobj.drivers_dir); + kobject_put(mod->holders_dir); + mod_sysfs_fini(mod); } /* @@ -1296,25 +1446,29 @@ static int __unlink_module(void *_mod) static void free_module(struct module *mod) { /* Delete from various lists */ - stop_machine_run(__unlink_module, mod, NR_CPUS); + stop_machine(__unlink_module, mod, NULL); remove_notes_attrs(mod); remove_sect_attrs(mod); mod_kobject_remove(mod); - unwind_remove_table(mod->unwind_info, 0); - /* Arch-specific cleanup. */ module_arch_cleanup(mod); /* Module unload stuff */ module_unload_free(mod); + /* 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); if (mod->percpu) percpu_modfree(mod->percpu); - +#if defined(CONFIG_MODULE_UNLOAD) && defined(CONFIG_SMP) + if (mod->refptr) + percpu_modfree(mod->refptr); +#endif /* Free lock-classes: */ lockdep_free_key_range(mod->module_core, mod->core_size); @@ -1326,11 +1480,12 @@ void *__symbol_get(const char *symbol) { struct module *owner; unsigned long value; - const unsigned long *crc; preempt_disable(); - value = __find_symbol(symbol, &owner, &crc, 1); - if (value && !strong_try_module_get(owner)) + value = find_symbol(symbol, &owner, NULL, true, true); + if (IS_ERR_VALUE(value)) + value = 0; + else if (strong_try_module_get(owner)) value = 0; preempt_enable(); @@ -1344,31 +1499,35 @@ EXPORT_SYMBOL_GPL(__symbol_get); */ static int verify_export_symbols(struct module *mod) { - const char *name = NULL; - unsigned long i, ret = 0; + unsigned int i; struct module *owner; - const unsigned long *crc; - - for (i = 0; i < mod->num_syms; i++) - if (__find_symbol(mod->syms[i].name, &owner, &crc, 1)) { - name = mod->syms[i].name; - ret = -ENOEXEC; - goto dup; - } + const struct kernel_symbol *s; + struct { + const struct kernel_symbol *sym; + unsigned int num; + } arr[] = { + { mod->syms, mod->num_syms }, + { mod->gpl_syms, mod->num_gpl_syms }, + { mod->gpl_future_syms, mod->num_gpl_future_syms }, +#ifdef CONFIG_UNUSED_SYMBOLS + { mod->unused_syms, mod->num_unused_syms }, + { mod->unused_gpl_syms, mod->num_unused_gpl_syms }, +#endif + }; - for (i = 0; i < mod->num_gpl_syms; i++) - if (__find_symbol(mod->gpl_syms[i].name, &owner, &crc, 1)) { - name = mod->gpl_syms[i].name; - ret = -ENOEXEC; - goto dup; + for (i = 0; i < ARRAY_SIZE(arr); i++) { + for (s = arr[i].sym; s < arr[i].sym + arr[i].num; s++) { + if (!IS_ERR_VALUE(find_symbol(s->name, &owner, + NULL, true, false))) { + printk(KERN_ERR + "%s: exports duplicate symbol %s" + " (owned by %s)\n", + mod->name, s->name, module_name(owner)); + return -ENOEXEC; + } } - -dup: - if (ret) - printk(KERN_ERR "%s: exports duplicate symbol %s (owned by %s)\n", - mod->name, name, module_name(owner)); - - return ret; + } + return 0; } /* Change all symbols so that st_value encodes the pointer directly. */ @@ -1407,7 +1566,7 @@ static int simplify_symbols(Elf_Shdr *sechdrs, strtab + sym[i].st_name, mod); /* Ok if resolved. */ - if (sym[i].st_value != 0) + if (!IS_ERR_VALUE(sym[i].st_value)) break; /* Ok if weak. */ if (ELF_ST_BIND(sym[i].st_info) == STB_WEAK) @@ -1432,11 +1591,21 @@ static int simplify_symbols(Elf_Shdr *sechdrs, return ret; } +/* Additional bytes needed by arch in front of individual sections */ +unsigned int __weak arch_mod_section_prepend(struct module *mod, + unsigned int section) +{ + /* default implementation just returns zero */ + return 0; +} + /* Update size with this section: return offset. */ -static long get_offset(unsigned long *size, Elf_Shdr *sechdr) +static long get_offset(struct module *mod, unsigned int *size, + Elf_Shdr *sechdr, unsigned int section) { long ret; + *size += arch_mod_section_prepend(mod, section); ret = ALIGN(*size, sechdr->sh_addralign ?: 1); *size = ret + sechdr->sh_size; return ret; @@ -1476,7 +1645,7 @@ static void layout_sections(struct module *mod, || strncmp(secstrings + s->sh_name, ".init", 5) == 0) continue; - s->sh_entsize = get_offset(&mod->core_size, s); + s->sh_entsize = get_offset(mod, &mod->core_size, s, i); DEBUGP("\t%s\n", secstrings + s->sh_name); } if (m == 0) @@ -1494,7 +1663,7 @@ static void layout_sections(struct module *mod, || strncmp(secstrings + s->sh_name, ".init", 5) != 0) continue; - s->sh_entsize = (get_offset(&mod->init_size, s) + s->sh_entsize = (get_offset(mod, &mod->init_size, s, i) | INIT_OFFSET_MASK); DEBUGP("\t%s\n", secstrings + s->sh_name); } @@ -1509,7 +1678,7 @@ static void set_license(struct module *mod, const char *license) license = "unspecified"; if (!license_is_gpl_compatible(license)) { - if (!(tainted & TAINT_PROPRIETARY_MODULE)) + if (!test_taint(TAINT_PROPRIETARY_MODULE)) printk(KERN_WARNING "%s: module license '%s' taints " "kernel.\n", mod->name, license); add_taint_module(mod, TAINT_PROPRIETARY_MODULE); @@ -1566,15 +1735,28 @@ static void setup_modinfo(struct module *mod, Elf_Shdr *sechdrs, } #ifdef CONFIG_KALLSYMS -static int is_exported(const char *name, const struct module *mod) + +/* lookup symbol in given range of kernel_symbols */ +static const struct kernel_symbol *lookup_symbol(const char *name, + const struct kernel_symbol *start, + const struct kernel_symbol *stop) { - if (!mod && lookup_symbol(name, __start___ksymtab, __stop___ksymtab)) - return 1; + const struct kernel_symbol *ks = start; + for (; ks < stop; ks++) + if (strcmp(ks->name, name) == 0) + return ks; + return NULL; +} + +static int is_exported(const char *name, unsigned long value, + const struct module *mod) +{ + const struct kernel_symbol *ks; + if (!mod) + ks = lookup_symbol(name, __start___ksymtab, __stop___ksymtab); else - if (mod && lookup_symbol(name, mod->syms, mod->syms + mod->num_syms)) - return 1; - else - return 0; + ks = lookup_symbol(name, mod->syms, mod->syms + mod->num_syms); + return ks != NULL && ks->value == value; } /* As per nm */ @@ -1645,42 +1827,55 @@ static inline void add_kallsyms(struct module *mod, } #endif /* CONFIG_KALLSYMS */ +static void dynamic_printk_setup(struct mod_debug *debug, unsigned int num) +{ +#ifdef CONFIG_DYNAMIC_PRINTK_DEBUG + unsigned int i; + + for (i = 0; i < num; i++) { + register_dynamic_debug_module(debug[i].modname, + debug[i].type, + debug[i].logical_modname, + debug[i].flag_names, + debug[i].hash, debug[i].hash2); + } +#endif /* CONFIG_DYNAMIC_PRINTK_DEBUG */ +} + +static void *module_alloc_update_bounds(unsigned long size) +{ + void *ret = module_alloc(size); + + if (ret) { + /* Update module bounds. */ + if ((unsigned long)ret < module_addr_min) + module_addr_min = (unsigned long)ret; + if ((unsigned long)ret + size > module_addr_max) + module_addr_max = (unsigned long)ret + size; + } + return ret; +} + /* Allocate and load the module: note that size of section 0 is always zero, and we rely on this for optional sections. */ -static struct module *load_module(void __user *umod, +static noinline struct module *load_module(void __user *umod, unsigned long len, const char __user *uargs) { Elf_Ehdr *hdr; Elf_Shdr *sechdrs; char *secstrings, *args, *modmagic, *strtab = NULL; + char *staging; unsigned int i; unsigned int symindex = 0; unsigned int strindex = 0; - unsigned int setupindex; - unsigned int exindex; - unsigned int exportindex; - unsigned int modindex; - unsigned int obsparmindex; - unsigned int infoindex; - unsigned int gplindex; - unsigned int crcindex; - unsigned int gplcrcindex; - unsigned int versindex; - unsigned int pcpuindex; - unsigned int gplfutureindex; - unsigned int gplfuturecrcindex; - unsigned int unwindex = 0; - unsigned int unusedindex; - unsigned int unusedcrcindex; - unsigned int unusedgplindex; - unsigned int unusedgplcrcindex; - unsigned int markersindex; - unsigned int markersstringsindex; + unsigned int modindex, versindex, infoindex, pcpuindex; + unsigned int num_kp, num_mcount; + struct kernel_param *kp; struct module *mod; long err = 0; void *percpu = NULL, *ptr = NULL; /* Stops spurious gcc warning */ - struct exception_table_entry *extable; + unsigned long *mseg; mm_segment_t old_fs; DEBUGP("load_module: umod=%p, len=%lu, uargs=%p\n", @@ -1692,6 +1887,13 @@ static struct module *load_module(void __user *umod, /* vmalloc barfs on "unusual" numbers. Check here */ 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; @@ -1699,7 +1901,7 @@ static struct module *load_module(void __user *umod, /* Sanity checks against insmoding binaries or wrong arch, weird elf version */ - if (memcmp(hdr->e_ident, ELFMAG, 4) != 0 + if (memcmp(hdr->e_ident, ELFMAG, SELFMAG) != 0 || hdr->e_type != ET_REL || !elf_check_arch(hdr) || hdr->e_shentsize != sizeof(*sechdrs)) { @@ -1744,6 +1946,7 @@ static struct module *load_module(void __user *umod, err = -ENOEXEC; goto free_hdr; } + /* This is temporary: point mod into copy of data. */ mod = (void *)sechdrs[modindex].sh_addr; if (symindex == 0) { @@ -1753,36 +1956,18 @@ static struct module *load_module(void __user *umod, goto free_hdr; } - /* Optional sections */ - exportindex = find_sec(hdr, sechdrs, secstrings, "__ksymtab"); - gplindex = find_sec(hdr, sechdrs, secstrings, "__ksymtab_gpl"); - gplfutureindex = find_sec(hdr, sechdrs, secstrings, "__ksymtab_gpl_future"); - unusedindex = find_sec(hdr, sechdrs, secstrings, "__ksymtab_unused"); - unusedgplindex = find_sec(hdr, sechdrs, secstrings, "__ksymtab_unused_gpl"); - crcindex = find_sec(hdr, sechdrs, secstrings, "__kcrctab"); - gplcrcindex = find_sec(hdr, sechdrs, secstrings, "__kcrctab_gpl"); - gplfuturecrcindex = find_sec(hdr, sechdrs, secstrings, "__kcrctab_gpl_future"); - unusedcrcindex = find_sec(hdr, sechdrs, secstrings, "__kcrctab_unused"); - unusedgplcrcindex = find_sec(hdr, sechdrs, secstrings, "__kcrctab_unused_gpl"); - setupindex = find_sec(hdr, sechdrs, secstrings, "__param"); - exindex = find_sec(hdr, sechdrs, secstrings, "__ex_table"); - obsparmindex = find_sec(hdr, sechdrs, secstrings, "__obsparm"); versindex = find_sec(hdr, sechdrs, secstrings, "__versions"); infoindex = find_sec(hdr, sechdrs, secstrings, ".modinfo"); pcpuindex = find_pcpusec(hdr, sechdrs, secstrings); -#ifdef ARCH_UNWIND_SECTION_NAME - unwindex = find_sec(hdr, sechdrs, secstrings, ARCH_UNWIND_SECTION_NAME); -#endif - /* Don't keep modinfo section */ + /* 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 - if (unwindex) - sechdrs[unwindex].sh_flags |= SHF_ALLOC; /* Check module struct version now, before we try to use module. */ if (!check_modstruct_version(sechdrs, versindex, mod)) { @@ -1793,16 +1978,24 @@ static struct module *load_module(void __user *umod, modmagic = get_modinfo(sechdrs, infoindex, "vermagic"); /* This is allowed: modprobe --force will invalidate it. */ if (!modmagic) { - add_taint_module(mod, TAINT_FORCED_MODULE); - printk(KERN_WARNING "%s: no version magic, tainting kernel.\n", - mod->name); - } else if (!same_magic(modmagic, vermagic)) { + err = try_to_force_load(mod, "magic"); + if (err) + goto free_hdr; + } else if (!same_magic(modmagic, vermagic, versindex)) { printk(KERN_ERR "%s: version magic '%s' should be '%s'\n", mod->name, modmagic, vermagic); err = -ENOEXEC; goto free_hdr; } + staging = get_modinfo(sechdrs, infoindex, "staging"); + if (staging) { + add_taint_module(mod, TAINT_CRAP); + printk(KERN_WARNING "%s: module is from the staging directory," + " the quality is unknown, you have been warned.\n", + mod->name); + } + /* Now copy in args */ args = strndup_user(uargs, ~0UL >> 1); if (IS_ERR(args)) { @@ -1822,6 +2015,14 @@ static struct module *load_module(void __user *umod, if (err < 0) goto free_mod; +#if defined(CONFIG_MODULE_UNLOAD) && defined(CONFIG_SMP) + mod->refptr = percpu_modalloc(sizeof(local_t), __alignof__(local_t), + mod->name); + if (!mod->refptr) { + err = -ENOMEM; + goto free_mod; + } +#endif if (pcpuindex) { /* We have a special allocation for this section. */ percpu = percpu_modalloc(sechdrs[pcpuindex].sh_size, @@ -1829,7 +2030,7 @@ static struct module *load_module(void __user *umod, mod->name); if (!percpu) { err = -ENOMEM; - goto free_mod; + goto free_percpu; } sechdrs[pcpuindex].sh_flags &= ~(unsigned long)SHF_ALLOC; mod->percpu = percpu; @@ -1841,7 +2042,7 @@ static struct module *load_module(void __user *umod, layout_sections(mod, hdr, sechdrs, secstrings); /* Do the allocs. */ - ptr = module_alloc(mod->core_size); + ptr = module_alloc_update_bounds(mod->core_size); if (!ptr) { err = -ENOMEM; goto free_percpu; @@ -1849,7 +2050,7 @@ static struct module *load_module(void __user *umod, memset(ptr, 0, mod->core_size); mod->module_core = ptr; - ptr = module_alloc(mod->init_size); + ptr = module_alloc_update_bounds(mod->init_size); if (!ptr && mod->init_size) { err = -ENOMEM; goto free_core; @@ -1884,16 +2085,23 @@ static struct module *load_module(void __user *umod, /* Now we've moved module, initialize linked lists, etc. */ module_unload_init(mod); - /* Initialize kobject, so we can reference it. */ + /* add kobject, so we can reference it. */ err = mod_sysfs_init(mod); if (err) - goto cleanup; + goto free_unload; /* Set up license info based on the info section */ set_license(mod, get_modinfo(sechdrs, infoindex, "license")); + /* + * ndiswrapper is under GPL by itself, but loads proprietary modules. + * Don't use add_taint_module(), as it would prevent ndiswrapper from + * using GPL-only symbols it needs. + */ if (strcmp(mod->name, "ndiswrapper") == 0) add_taint(TAINT_PROPRIETARY_MODULE); + + /* driverloader was caught wrongly pretending to be under GPL */ if (strcmp(mod->name, "driverloader") == 0) add_taint_module(mod, TAINT_PROPRIETARY_MODULE); @@ -1906,46 +2114,65 @@ static struct module *load_module(void __user *umod, if (err < 0) goto cleanup; - /* Set up EXPORTed & EXPORT_GPLed symbols (section 0 is 0 length) */ - mod->num_syms = sechdrs[exportindex].sh_size / sizeof(*mod->syms); - mod->syms = (void *)sechdrs[exportindex].sh_addr; - if (crcindex) - mod->crcs = (void *)sechdrs[crcindex].sh_addr; - mod->num_gpl_syms = sechdrs[gplindex].sh_size / sizeof(*mod->gpl_syms); - mod->gpl_syms = (void *)sechdrs[gplindex].sh_addr; - if (gplcrcindex) - mod->gpl_crcs = (void *)sechdrs[gplcrcindex].sh_addr; - mod->num_gpl_future_syms = sechdrs[gplfutureindex].sh_size / - sizeof(*mod->gpl_future_syms); - mod->num_unused_syms = sechdrs[unusedindex].sh_size / - sizeof(*mod->unused_syms); - mod->num_unused_gpl_syms = sechdrs[unusedgplindex].sh_size / - sizeof(*mod->unused_gpl_syms); - mod->gpl_future_syms = (void *)sechdrs[gplfutureindex].sh_addr; - if (gplfuturecrcindex) - mod->gpl_future_crcs = (void *)sechdrs[gplfuturecrcindex].sh_addr; - - mod->unused_syms = (void *)sechdrs[unusedindex].sh_addr; - if (unusedcrcindex) - mod->unused_crcs = (void *)sechdrs[unusedcrcindex].sh_addr; - mod->unused_gpl_syms = (void *)sechdrs[unusedgplindex].sh_addr; - if (unusedgplcrcindex) - mod->unused_crcs = (void *)sechdrs[unusedgplcrcindex].sh_addr; + /* Now we've got everything in the final locations, we can + * find optional sections. */ + kp = section_objs(hdr, sechdrs, secstrings, "__param", sizeof(*kp), + &num_kp); + mod->syms = section_objs(hdr, sechdrs, secstrings, "__ksymtab", + sizeof(*mod->syms), &mod->num_syms); + mod->crcs = section_addr(hdr, sechdrs, secstrings, "__kcrctab"); + mod->gpl_syms = section_objs(hdr, sechdrs, secstrings, "__ksymtab_gpl", + sizeof(*mod->gpl_syms), + &mod->num_gpl_syms); + mod->gpl_crcs = section_addr(hdr, sechdrs, secstrings, "__kcrctab_gpl"); + mod->gpl_future_syms = section_objs(hdr, sechdrs, secstrings, + "__ksymtab_gpl_future", + sizeof(*mod->gpl_future_syms), + &mod->num_gpl_future_syms); + mod->gpl_future_crcs = section_addr(hdr, sechdrs, secstrings, + "__kcrctab_gpl_future"); + +#ifdef CONFIG_UNUSED_SYMBOLS + mod->unused_syms = section_objs(hdr, sechdrs, secstrings, + "__ksymtab_unused", + sizeof(*mod->unused_syms), + &mod->num_unused_syms); + mod->unused_crcs = section_addr(hdr, sechdrs, secstrings, + "__kcrctab_unused"); + mod->unused_gpl_syms = section_objs(hdr, sechdrs, secstrings, + "__ksymtab_unused_gpl", + sizeof(*mod->unused_gpl_syms), + &mod->num_unused_gpl_syms); + 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); +#endif +#ifdef CONFIG_TRACEPOINTS + mod->tracepoints = section_objs(hdr, sechdrs, secstrings, + "__tracepoints", + sizeof(*mod->tracepoints), + &mod->num_tracepoints); +#endif #ifdef CONFIG_MODVERSIONS - if ((mod->num_syms && !crcindex) || - (mod->num_gpl_syms && !gplcrcindex) || - (mod->num_gpl_future_syms && !gplfuturecrcindex) || - (mod->num_unused_syms && !unusedcrcindex) || - (mod->num_unused_gpl_syms && !unusedgplcrcindex)) { - printk(KERN_WARNING "%s: No versions for exported symbols." - " Tainting kernel.\n", mod->name); - add_taint_module(mod, TAINT_FORCED_MODULE); + if ((mod->num_syms && !mod->crcs) + || (mod->num_gpl_syms && !mod->gpl_crcs) + || (mod->num_gpl_future_syms && !mod->gpl_future_crcs) +#ifdef CONFIG_UNUSED_SYMBOLS + || (mod->num_unused_syms && !mod->unused_crcs) + || (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"); + if (err) + goto cleanup; } #endif - markersindex = find_sec(hdr, sechdrs, secstrings, "__markers"); - markersstringsindex = find_sec(hdr, sechdrs, secstrings, - "__markers_strings"); /* Now do relocations. */ for (i = 1; i < hdr->e_shnum; i++) { @@ -1968,22 +2195,16 @@ static struct module *load_module(void __user *umod, if (err < 0) goto cleanup; } -#ifdef CONFIG_MARKERS - mod->markers = (void *)sechdrs[markersindex].sh_addr; - mod->num_markers = - sechdrs[markersindex].sh_size / sizeof(*mod->markers); -#endif /* Find duplicate symbols */ err = verify_export_symbols(mod); - if (err < 0) goto cleanup; /* Set up and sort exception table */ - mod->num_exentries = sechdrs[exindex].sh_size / sizeof(*mod->extable); - mod->extable = extable = (void *)sechdrs[exindex].sh_addr; - sort_extable(extable, extable + mod->num_exentries); + mod->extable = section_objs(hdr, sechdrs, secstrings, "__ex_table", + sizeof(*mod->extable), &mod->num_exentries); + sort_extable(mod->extable, mod->extable + mod->num_exentries); /* Finally, copy percpu area over. */ percpu_modcopy(mod->percpu, (void *)sechdrs[pcpuindex].sh_addr, @@ -1991,11 +2212,20 @@ static struct module *load_module(void __user *umod, add_kallsyms(mod, sechdrs, symindex, strindex, secstrings); -#ifdef CONFIG_MARKERS - if (!mod->taints) - marker_update_probe_range(mod->markers, - mod->markers + mod->num_markers, NULL, NULL); -#endif + if (!mod->taints) { + struct mod_debug *debug; + unsigned int num_debug; + + debug = section_objs(hdr, sechdrs, secstrings, "__verbose", + sizeof(*debug), &num_debug); + dynamic_printk_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; @@ -2019,44 +2249,44 @@ static struct module *load_module(void __user *umod, set_fs(old_fs); mod->args = args; - if (obsparmindex) + if (section_addr(hdr, sechdrs, secstrings, "__obsparm")) printk(KERN_WARNING "%s: Ignoring obsolete parameters\n", mod->name); - /* Size of section 0 is 0, so this works well if no params */ - err = parse_args(mod->name, mod->args, - (struct kernel_param *) - sechdrs[setupindex].sh_addr, - sechdrs[setupindex].sh_size - / sizeof(struct kernel_param), - NULL); + /* Now sew it into the lists so we can get lockdep and oops + * info during argument parsing. Noone should access us, since + * strong_try_module_get() will fail. + * lockdep/oops can run asynchronous, so use the RCU list insertion + * function to insert in a way safe to concurrent readers. + * The mutex protects against concurrent writers. + */ + list_add_rcu(&mod->list, &modules); + + err = parse_args(mod->name, mod->args, kp, num_kp, NULL); if (err < 0) - goto arch_cleanup; + goto unlink; - err = mod_sysfs_setup(mod, - (struct kernel_param *) - sechdrs[setupindex].sh_addr, - sechdrs[setupindex].sh_size - / sizeof(struct kernel_param)); + err = mod_sysfs_setup(mod, kp, num_kp); if (err < 0) - goto arch_cleanup; + goto unlink; add_sect_attrs(mod, hdr->e_shnum, secstrings, sechdrs); add_notes_attrs(mod, hdr->e_shnum, secstrings, sechdrs); - /* Size of section 0 is 0, so this works well if no unwind info. */ - mod->unwind_info = unwind_add_table(mod, - (void *)sechdrs[unwindex].sh_addr, - sechdrs[unwindex].sh_size); - /* Get rid of temporary copy */ vfree(hdr); + stop_machine_destroy(); /* Done! */ return mod; - arch_cleanup: + unlink: + stop_machine(__unlink_module, mod, NULL); module_arch_cleanup(mod); cleanup: + kobject_del(&mod->mkobj.kobj); + kobject_put(&mod->mkobj.kobj); + ftrace_release(mod->module_core, mod->core_size); + free_unload: module_unload_free(mod); module_free(mod, mod->module_init); free_core: @@ -2064,10 +2294,14 @@ static struct module *load_module(void __user *umod, free_percpu: if (percpu) percpu_modfree(percpu); +#if defined(CONFIG_MODULE_UNLOAD) && defined(CONFIG_SMP) + percpu_modfree(mod->refptr); +#endif free_mod: kfree(args); free_hdr: vfree(hdr); + stop_machine_destroy(); return ERR_PTR(err); truncated: @@ -2076,22 +2310,9 @@ static struct module *load_module(void __user *umod, goto free_hdr; } -/* - * link the module with the whole machine is stopped with interrupts off - * - this defends against kallsyms not taking locks - */ -static int __link_module(void *_mod) -{ - struct module *mod = _mod; - list_add(&mod->list, &modules); - return 0; -} - /* This is where the real work happens */ -asmlinkage long -sys_init_module(void __user *umod, - unsigned long len, - const char __user *uargs) +SYSCALL_DEFINE3(init_module, void __user *, umod, + unsigned long, len, const char __user *, uargs) { struct module *mod; int ret = 0; @@ -2111,10 +2332,6 @@ sys_init_module(void __user *umod, return PTR_ERR(mod); } - /* Now sew it into the lists. They won't access us, since - strong_try_module_get() will fail. */ - stop_machine_run(__link_module, mod, NR_CPUS); - /* Drop lock so they can recurse */ mutex_unlock(&module_mutex); @@ -2123,25 +2340,39 @@ sys_init_module(void __user *umod, /* Start the module */ if (mod->init != NULL) - ret = mod->init(); + ret = do_one_initcall(mod->init); if (ret < 0) { /* Init routine failed: abort. Try to protect us from buggy refcounters. */ mod->state = MODULE_STATE_GOING; synchronize_sched(); module_put(mod); + blocking_notifier_call_chain(&module_notify_list, + MODULE_STATE_GOING, mod); mutex_lock(&module_mutex); free_module(mod); mutex_unlock(&module_mutex); + wake_up(&module_wq); 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", + __func__, mod->name, ret, + __func__); + dump_stack(); + } - /* Now it's a first class citizen! */ - mutex_lock(&module_mutex); + /* Now it's a first class citizen! Wake up anyone waiting for it. */ mod->state = MODULE_STATE_LIVE; + wake_up(&module_wq); + blocking_notifier_call_chain(&module_notify_list, + MODULE_STATE_LIVE, mod); + + mutex_lock(&module_mutex); /* Drop initial reference. */ module_put(mod); - unwind_remove_table(mod->unwind_info, 1); module_free(mod, mod->module_init); mod->module_init = NULL; mod->init_size = 0; @@ -2176,7 +2407,7 @@ static const char *get_ksymbol(struct module *mod, unsigned long nextval; /* At worse, next value is at end of module */ - if (within(addr, mod->module_init, mod->init_size)) + if (within_module_init(addr, mod)) nextval = (unsigned long)mod->module_init+mod->init_text_size; else nextval = (unsigned long)mod->module_core+mod->core_text_size; @@ -2211,47 +2442,56 @@ static const char *get_ksymbol(struct module *mod, return mod->strtab + mod->symtab[best].st_name; } -/* For kallsyms to ask for address resolution. NULL means not found. - We don't lock, as this is used for oops resolution and races are a - lesser concern. */ +/* For kallsyms to ask for address resolution. NULL means not found. Careful + * not to lock to avoid deadlock on oopses, simply disable preemption. */ const char *module_address_lookup(unsigned long addr, - unsigned long *size, - unsigned long *offset, - char **modname) + unsigned long *size, + unsigned long *offset, + char **modname, + char *namebuf) { struct module *mod; + const char *ret = NULL; - list_for_each_entry(mod, &modules, list) { - if (within(addr, mod->module_init, mod->init_size) - || within(addr, mod->module_core, mod->core_size)) { + preempt_disable(); + list_for_each_entry_rcu(mod, &modules, list) { + if (within_module_init(addr, mod) || + within_module_core(addr, mod)) { if (modname) *modname = mod->name; - return get_ksymbol(mod, addr, size, offset); + ret = get_ksymbol(mod, addr, size, offset); + break; } } - return NULL; + /* Make a copy in here where it's safe */ + if (ret) { + strncpy(namebuf, ret, KSYM_NAME_LEN - 1); + ret = namebuf; + } + preempt_enable(); + return ret; } int lookup_module_symbol_name(unsigned long addr, char *symname) { struct module *mod; - mutex_lock(&module_mutex); - list_for_each_entry(mod, &modules, list) { - if (within(addr, mod->module_init, mod->init_size) || - within(addr, mod->module_core, mod->core_size)) { + preempt_disable(); + list_for_each_entry_rcu(mod, &modules, list) { + if (within_module_init(addr, mod) || + within_module_core(addr, mod)) { const char *sym; sym = get_ksymbol(mod, addr, NULL, NULL); if (!sym) goto out; strlcpy(symname, sym, KSYM_NAME_LEN); - mutex_unlock(&module_mutex); + preempt_enable(); return 0; } } out: - mutex_unlock(&module_mutex); + preempt_enable(); return -ERANGE; } @@ -2260,10 +2500,10 @@ int lookup_module_symbol_attrs(unsigned long addr, unsigned long *size, { struct module *mod; - mutex_lock(&module_mutex); - list_for_each_entry(mod, &modules, list) { - if (within(addr, mod->module_init, mod->init_size) || - within(addr, mod->module_core, mod->core_size)) { + preempt_disable(); + list_for_each_entry_rcu(mod, &modules, list) { + if (within_module_init(addr, mod) || + within_module_core(addr, mod)) { const char *sym; sym = get_ksymbol(mod, addr, size, offset); @@ -2273,12 +2513,12 @@ int lookup_module_symbol_attrs(unsigned long addr, unsigned long *size, strlcpy(modname, mod->name, MODULE_NAME_LEN); if (name) strlcpy(name, sym, KSYM_NAME_LEN); - mutex_unlock(&module_mutex); + preempt_enable(); return 0; } } out: - mutex_unlock(&module_mutex); + preempt_enable(); return -ERANGE; } @@ -2287,21 +2527,21 @@ int module_get_kallsym(unsigned int symnum, unsigned long *value, char *type, { struct module *mod; - mutex_lock(&module_mutex); - list_for_each_entry(mod, &modules, list) { + preempt_disable(); + list_for_each_entry_rcu(mod, &modules, list) { if (symnum < mod->num_symtab) { *value = mod->symtab[symnum].st_value; *type = mod->symtab[symnum].st_info; strlcpy(name, mod->strtab + mod->symtab[symnum].st_name, KSYM_NAME_LEN); strlcpy(module_name, mod->name, MODULE_NAME_LEN); - *exported = is_exported(name, mod); - mutex_unlock(&module_mutex); + *exported = is_exported(name, *value, mod); + preempt_enable(); return 0; } symnum -= mod->num_symtab; } - mutex_unlock(&module_mutex); + preempt_enable(); return -ERANGE; } @@ -2324,52 +2564,48 @@ unsigned long module_kallsyms_lookup_name(const char *name) unsigned long ret = 0; /* Don't lock: we're in enough trouble already. */ + preempt_disable(); if ((colon = strchr(name, ':')) != NULL) { *colon = '\0'; if ((mod = find_module(name)) != NULL) ret = mod_find_symname(mod, colon+1); *colon = ':'; } else { - list_for_each_entry(mod, &modules, list) + list_for_each_entry_rcu(mod, &modules, list) if ((ret = mod_find_symname(mod, name)) != 0) break; } + preempt_enable(); return ret; } #endif /* CONFIG_KALLSYMS */ -/* Called by the /proc file system to return a list of modules. */ -static void *m_start(struct seq_file *m, loff_t *pos) -{ - mutex_lock(&module_mutex); - return seq_list_start(&modules, *pos); -} - -static void *m_next(struct seq_file *m, void *p, loff_t *pos) -{ - return seq_list_next(p, &modules, pos); -} - -static void m_stop(struct seq_file *m, void *p) -{ - mutex_unlock(&module_mutex); -} - -static char *taint_flags(unsigned int taints, char *buf) +static char *module_flags(struct module *mod, char *buf) { int bx = 0; - if (taints) { + if (mod->taints || + mod->state == MODULE_STATE_GOING || + mod->state == MODULE_STATE_COMING) { buf[bx++] = '('; - if (taints & TAINT_PROPRIETARY_MODULE) + if (mod->taints & (1 << TAINT_PROPRIETARY_MODULE)) buf[bx++] = 'P'; - if (taints & TAINT_FORCED_MODULE) + if (mod->taints & (1 << TAINT_FORCED_MODULE)) buf[bx++] = 'F'; + if (mod->taints & (1 << TAINT_CRAP)) + buf[bx++] = 'C'; /* * TAINT_FORCED_RMMOD: could be added. * TAINT_UNSAFE_SMP, TAINT_MACHINE_CHECK, TAINT_BAD_PAGE don't * apply to modules. */ + + /* Show a - for module-is-being-unloaded */ + if (mod->state == MODULE_STATE_GOING) + buf[bx++] = '-'; + /* Show a + for module-is-being-loaded */ + if (mod->state == MODULE_STATE_COMING) + buf[bx++] = '+'; buf[bx++] = ')'; } buf[bx] = '\0'; @@ -2377,12 +2613,30 @@ static char *taint_flags(unsigned int taints, char *buf) return buf; } +#ifdef CONFIG_PROC_FS +/* Called by the /proc file system to return a list of modules. */ +static void *m_start(struct seq_file *m, loff_t *pos) +{ + mutex_lock(&module_mutex); + return seq_list_start(&modules, *pos); +} + +static void *m_next(struct seq_file *m, void *p, loff_t *pos) +{ + return seq_list_next(p, &modules, pos); +} + +static void m_stop(struct seq_file *m, void *p) +{ + mutex_unlock(&module_mutex); +} + static int m_show(struct seq_file *m, void *p) { struct module *mod = list_entry(p, struct module, list); char buf[8]; - seq_printf(m, "%s %lu", + seq_printf(m, "%s %u", mod->name, mod->init_size + mod->core_size); print_unload_info(m, mod); @@ -2396,7 +2650,7 @@ static int m_show(struct seq_file *m, void *p) /* Taints info */ if (mod->taints) - seq_printf(m, " %s", taint_flags(mod->taints, buf)); + seq_printf(m, " %s", module_flags(mod, buf)); seq_printf(m, "\n"); return 0; @@ -2407,13 +2661,33 @@ static int m_show(struct seq_file *m, void *p) Where refcount is a number or -, and deps is a comma-separated list of depends or -. */ -const struct seq_operations modules_op = { +static const struct seq_operations modules_op = { .start = m_start, .next = m_next, .stop = m_stop, .show = m_show }; +static int modules_open(struct inode *inode, struct file *file) +{ + return seq_open(file, &modules_op); +} + +static const struct file_operations proc_modules_operations = { + .open = modules_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; + +static int __init proc_modules_init(void) +{ + proc_create("modules", 0, NULL, &proc_modules_operations); + return 0; +} +module_init(proc_modules_init); +#endif + /* Given an address, look for it in the module exception tables. */ const struct exception_table_entry *search_module_extables(unsigned long addr) { @@ -2421,7 +2695,7 @@ const struct exception_table_entry *search_module_extables(unsigned long addr) struct module *mod; preempt_disable(); - list_for_each_entry(mod, &modules, list) { + list_for_each_entry_rcu(mod, &modules, list) { if (mod->num_exentries == 0) continue; @@ -2447,8 +2721,8 @@ int is_module_address(unsigned long addr) preempt_disable(); - list_for_each_entry(mod, &modules, list) { - if (within(addr, mod->module_core, mod->core_size)) { + list_for_each_entry_rcu(mod, &modules, list) { + if (within_module_core(addr, mod)) { preempt_enable(); return 1; } @@ -2461,11 +2735,14 @@ int is_module_address(unsigned long addr) /* Is this a valid kernel address? */ -struct module *__module_text_address(unsigned long addr) +__notrace_funcgraph struct module *__module_text_address(unsigned long addr) { struct module *mod; - list_for_each_entry(mod, &modules, list) + if (addr < module_addr_min || addr > module_addr_max) + 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)) return mod; @@ -2490,98 +2767,16 @@ void print_modules(void) char buf[8]; printk("Modules linked in:"); - list_for_each_entry(mod, &modules, list) - printk(" %s%s", mod->name, taint_flags(mod->taints, buf)); + /* Most callers should already have preempt disabled, but make sure */ + preempt_disable(); + list_for_each_entry_rcu(mod, &modules, list) + printk(" %s%s", mod->name, module_flags(mod, buf)); + preempt_enable(); + if (last_unloaded_module[0]) + printk(" [last unloaded: %s]", last_unloaded_module); printk("\n"); } -#ifdef CONFIG_SYSFS -static char *make_driver_name(struct device_driver *drv) -{ - char *driver_name; - - driver_name = kmalloc(strlen(drv->name) + strlen(drv->bus->name) + 2, - GFP_KERNEL); - if (!driver_name) - return NULL; - - sprintf(driver_name, "%s:%s", drv->bus->name, drv->name); - return driver_name; -} - -static void module_create_drivers_dir(struct module_kobject *mk) -{ - if (!mk || mk->drivers_dir) - return; - - mk->drivers_dir = kobject_add_dir(&mk->kobj, "drivers"); -} - -void module_add_driver(struct module *mod, struct device_driver *drv) -{ - char *driver_name; - int no_warn; - struct module_kobject *mk = NULL; - - if (!drv) - return; - - if (mod) - mk = &mod->mkobj; - else if (drv->mod_name) { - struct kobject *mkobj; - - /* Lookup built-in module entry in /sys/modules */ - mkobj = kset_find_obj(&module_subsys, drv->mod_name); - if (mkobj) { - mk = container_of(mkobj, struct module_kobject, kobj); - /* remember our module structure */ - drv->mkobj = mk; - /* kset_find_obj took a reference */ - kobject_put(mkobj); - } - } - - if (!mk) - return; - - /* Don't check return codes; these calls are idempotent */ - no_warn = sysfs_create_link(&drv->kobj, &mk->kobj, "module"); - driver_name = make_driver_name(drv); - if (driver_name) { - module_create_drivers_dir(mk); - no_warn = sysfs_create_link(mk->drivers_dir, &drv->kobj, - driver_name); - kfree(driver_name); - } -} -EXPORT_SYMBOL(module_add_driver); - -void module_remove_driver(struct device_driver *drv) -{ - struct module_kobject *mk = NULL; - char *driver_name; - - if (!drv) - return; - - sysfs_remove_link(&drv->kobj, "module"); - - if (drv->owner) - mk = &drv->owner->mkobj; - else if (drv->mkobj) - mk = drv->mkobj; - if (mk && mk->drivers_dir) { - driver_name = make_driver_name(drv); - if (driver_name) { - sysfs_remove_link(mk->drivers_dir, driver_name); - kfree(driver_name); - } - } -} -EXPORT_SYMBOL(module_remove_driver); -#endif - #ifdef CONFIG_MODVERSIONS /* Generate the signature for struct module here, too, for modversions. */ void struct_module(struct module *mod) { return; } @@ -2589,7 +2784,7 @@ EXPORT_SYMBOL(struct_module); #endif #ifdef CONFIG_MARKERS -void module_update_markers(struct module *probe_module, int *refcount) +void module_update_markers(void) { struct module *mod; @@ -2597,8 +2792,54 @@ void module_update_markers(struct module *probe_module, int *refcount) list_for_each_entry(mod, &modules, list) if (!mod->taints) marker_update_probe_range(mod->markers, - mod->markers + mod->num_markers, - probe_module, refcount); + mod->markers + mod->num_markers); + mutex_unlock(&module_mutex); +} +#endif + +#ifdef CONFIG_TRACEPOINTS +void module_update_tracepoints(void) +{ + struct module *mod; + + mutex_lock(&module_mutex); + list_for_each_entry(mod, &modules, list) + if (!mod->taints) + tracepoint_update_probe_range(mod->tracepoints, + mod->tracepoints + mod->num_tracepoints); + mutex_unlock(&module_mutex); +} + +/* + * Returns 0 if current not found. + * Returns 1 if current found. + */ +int module_get_iter_tracepoints(struct tracepoint_iter *iter) +{ + struct module *iter_mod; + int found = 0; + + mutex_lock(&module_mutex); + list_for_each_entry(iter_mod, &modules, list) { + if (!iter_mod->taints) { + /* + * Sorted module list + */ + if (iter_mod < iter->module) + continue; + else if (iter_mod > iter->module) + iter->tracepoint = NULL; + found = tracepoint_get_iter_range(&iter->tracepoint, + iter_mod->tracepoints, + iter_mod->tracepoints + + iter_mod->num_tracepoints); + if (found) { + iter->module = iter_mod; + break; + } + } + } mutex_unlock(&module_mutex); + return found; } #endif