diff --git a/include/linux/kallsyms.h b/include/linux/kallsyms.h index fe3c9993b5bf..c3f075e8f60c 100644 --- a/include/linux/kallsyms.h +++ b/include/linux/kallsyms.h @@ -65,6 +65,9 @@ static inline void *dereference_symbol_descriptor(void *ptr) return ptr; } +/* How and when do we show kallsyms values? */ +extern bool kallsyms_show_value(const struct cred *cred); + #ifdef CONFIG_KALLSYMS unsigned long kallsyms_sym_address(int idx); int kallsyms_on_each_symbol(int (*fn)(void *, const char *, unsigned long), @@ -93,10 +96,6 @@ extern int sprint_backtrace(char *buffer, unsigned long address); extern int sprint_backtrace_build_id(char *buffer, unsigned long address); int lookup_symbol_name(unsigned long addr, char *symname); -int lookup_symbol_attrs(unsigned long addr, unsigned long *size, unsigned long *offset, char *modname, char *name); - -/* How and when do we show kallsyms values? */ -extern bool kallsyms_show_value(const struct cred *cred); #else /* !CONFIG_KALLSYMS */ @@ -155,16 +154,6 @@ static inline int lookup_symbol_name(unsigned long addr, char *symname) return -ERANGE; } -static inline int lookup_symbol_attrs(unsigned long addr, unsigned long *size, unsigned long *offset, char *modname, char *name) -{ - return -ERANGE; -} - -static inline bool kallsyms_show_value(const struct cred *cred) -{ - return false; -} - static inline int kallsyms_on_each_symbol(int (*fn)(void *, const char *, unsigned long), void *data) { diff --git a/include/linux/module.h b/include/linux/module.h index 2902761e14a0..be2d36838259 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -971,15 +971,6 @@ static inline int lookup_module_symbol_name(unsigned long addr, char *symname) return -ERANGE; } -static inline int lookup_module_symbol_attrs(unsigned long addr, - unsigned long *size, - unsigned long *offset, - char *modname, - char *name) -{ - return -ERANGE; -} - static inline int module_get_kallsym(unsigned int symnum, unsigned long *value, char *type, char *name, char *module_name, int *exported) diff --git a/kernel/Makefile b/kernel/Makefile index f9e3fd9195d9..3947122d618b 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -10,7 +10,7 @@ obj-y = fork.o exec_domain.o panic.o \ extable.o params.o \ kthread.o sys_ni.o nsproxy.o \ notifier.o ksysfs.o cred.o reboot.o \ - async.o range.o smpboot.o ucount.o regset.o + async.o range.o smpboot.o ucount.o regset.o ksyms_common.o obj-$(CONFIG_USERMODE_DRIVER) += usermode_driver.o obj-$(CONFIG_MULTIUSER) += groups.o diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c index ddb91d8edaae..7982cc9d497c 100644 --- a/kernel/kallsyms.c +++ b/kernel/kallsyms.c @@ -484,34 +484,6 @@ found: return 0; } -int lookup_symbol_attrs(unsigned long addr, unsigned long *size, - unsigned long *offset, char *modname, char *name) -{ - int res; - - name[0] = '\0'; - name[KSYM_NAME_LEN - 1] = '\0'; - - if (is_ksym_addr(addr)) { - unsigned long pos; - - pos = get_symbol_pos(addr, size, offset); - /* Grab name */ - kallsyms_expand_symbol(get_symbol_offset(pos), - name, KSYM_NAME_LEN); - modname[0] = '\0'; - goto found; - } - /* See if it's in a module. */ - res = lookup_module_symbol_attrs(addr, size, offset, modname, name); - if (res) - return res; - -found: - cleanup_symbol_name(name); - return 0; -} - /* Look up a kernel symbol and return it in a text buffer. */ static int __sprint_symbol(char *buffer, unsigned long address, int symbol_offset, int add_offset, int add_buildid) @@ -646,7 +618,6 @@ int sprint_backtrace_build_id(char *buffer, unsigned long address) /* To avoid using get_symbol_offset for every symbol, we carry prefix along. */ struct kallsym_iter { loff_t pos; - loff_t pos_arch_end; loff_t pos_mod_end; loff_t pos_ftrace_mod_end; loff_t pos_bpf_end; @@ -659,29 +630,9 @@ struct kallsym_iter { int show_value; }; -int __weak arch_get_kallsym(unsigned int symnum, unsigned long *value, - char *type, char *name) -{ - return -EINVAL; -} - -static int get_ksymbol_arch(struct kallsym_iter *iter) -{ - int ret = arch_get_kallsym(iter->pos - kallsyms_num_syms, - &iter->value, &iter->type, - iter->name); - - if (ret < 0) { - iter->pos_arch_end = iter->pos; - return 0; - } - - return 1; -} - static int get_ksymbol_mod(struct kallsym_iter *iter) { - int ret = module_get_kallsym(iter->pos - iter->pos_arch_end, + int ret = module_get_kallsym(iter->pos - kallsyms_num_syms, &iter->value, &iter->type, iter->name, iter->module_name, &iter->exported); @@ -764,7 +715,6 @@ static void reset_iter(struct kallsym_iter *iter, loff_t new_pos) iter->nameoff = get_symbol_offset(new_pos); iter->pos = new_pos; if (new_pos == 0) { - iter->pos_arch_end = 0; iter->pos_mod_end = 0; iter->pos_ftrace_mod_end = 0; iter->pos_bpf_end = 0; @@ -780,10 +730,6 @@ static int update_iter_mod(struct kallsym_iter *iter, loff_t pos) { iter->pos = pos; - if ((!iter->pos_arch_end || iter->pos_arch_end > pos) && - get_ksymbol_arch(iter)) - return 1; - if ((!iter->pos_mod_end || iter->pos_mod_end > pos) && get_ksymbol_mod(iter)) return 1; @@ -961,41 +907,6 @@ late_initcall(bpf_ksym_iter_register); #endif /* CONFIG_BPF_SYSCALL */ -static inline int kallsyms_for_perf(void) -{ -#ifdef CONFIG_PERF_EVENTS - extern int sysctl_perf_event_paranoid; - if (sysctl_perf_event_paranoid <= 1) - return 1; -#endif - return 0; -} - -/* - * We show kallsyms information even to normal users if we've enabled - * kernel profiling and are explicitly not paranoid (so kptr_restrict - * is clear, and sysctl_perf_event_paranoid isn't set). - * - * Otherwise, require CAP_SYSLOG (assuming kptr_restrict isn't set to - * block even that). - */ -bool kallsyms_show_value(const struct cred *cred) -{ - switch (kptr_restrict) { - case 0: - if (kallsyms_for_perf()) - return true; - fallthrough; - case 1: - if (security_capable(cred, &init_user_ns, CAP_SYSLOG, - CAP_OPT_NOAUDIT) == 0) - return true; - fallthrough; - default: - return false; - } -} - static int kallsyms_open(struct inode *inode, struct file *file) { /* diff --git a/kernel/ksyms_common.c b/kernel/ksyms_common.c new file mode 100644 index 000000000000..cf1a73cbf2f6 --- /dev/null +++ b/kernel/ksyms_common.c @@ -0,0 +1,43 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * ksyms_common.c: A split of kernel/kallsyms.c + * Contains a few generic function definations independent of config KALLSYMS. + */ +#include +#include + +static inline int kallsyms_for_perf(void) +{ +#ifdef CONFIG_PERF_EVENTS + extern int sysctl_perf_event_paranoid; + + if (sysctl_perf_event_paranoid <= 1) + return 1; +#endif + return 0; +} + +/* + * We show kallsyms information even to normal users if we've enabled + * kernel profiling and are explicitly not paranoid (so kptr_restrict + * is clear, and sysctl_perf_event_paranoid isn't set). + * + * Otherwise, require CAP_SYSLOG (assuming kptr_restrict isn't set to + * block even that). + */ +bool kallsyms_show_value(const struct cred *cred) +{ + switch (kptr_restrict) { + case 0: + if (kallsyms_for_perf()) + return true; + fallthrough; + case 1: + if (security_capable(cred, &init_user_ns, CAP_SYSLOG, + CAP_OPT_NOAUDIT) == 0) + return true; + fallthrough; + default: + return false; + } +} diff --git a/kernel/module/kallsyms.c b/kernel/module/kallsyms.c index c550d7d45f2f..ef73ae7c8909 100644 --- a/kernel/module/kallsyms.c +++ b/kernel/module/kallsyms.c @@ -381,34 +381,6 @@ out: return -ERANGE; } -int lookup_module_symbol_attrs(unsigned long addr, unsigned long *size, - unsigned long *offset, char *modname, char *name) -{ - struct module *mod; - - preempt_disable(); - list_for_each_entry_rcu(mod, &modules, list) { - if (mod->state == MODULE_STATE_UNFORMED) - continue; - if (within_module(addr, mod)) { - const char *sym; - - sym = find_kallsyms_symbol(mod, addr, size, offset); - if (!sym) - goto out; - if (modname) - strscpy(modname, mod->name, MODULE_NAME_LEN); - if (name) - strscpy(name, sym, KSYM_NAME_LEN); - preempt_enable(); - return 0; - } - } -out: - preempt_enable(); - return -ERANGE; -} - int module_get_kallsym(unsigned int symnum, unsigned long *value, char *type, char *name, char *module_name, int *exported) { diff --git a/kernel/module/main.c b/kernel/module/main.c index 25e17cdac0e6..5e120ebdd3d7 100644 --- a/kernel/module/main.c +++ b/kernel/module/main.c @@ -821,10 +821,8 @@ static struct module_attribute modinfo_refcnt = void __module_get(struct module *module) { if (module) { - preempt_disable(); atomic_inc(&module->refcnt); trace_module_get(module, _RET_IP_); - preempt_enable(); } } EXPORT_SYMBOL(__module_get); @@ -834,15 +832,12 @@ bool try_module_get(struct module *module) bool ret = true; if (module) { - preempt_disable(); /* Note: here, we can fail to get a reference */ if (likely(module_is_live(module) && atomic_inc_not_zero(&module->refcnt) != 0)) trace_module_get(module, _RET_IP_); else ret = false; - - preempt_enable(); } return ret; } @@ -853,11 +848,9 @@ void module_put(struct module *module) int ret; if (module) { - preempt_disable(); ret = atomic_dec_if_positive(&module->refcnt); WARN_ON(ret < 0); /* Failed to put refcount */ trace_module_put(module, _RET_IP_); - preempt_enable(); } } EXPORT_SYMBOL(module_put); @@ -3090,12 +3083,111 @@ SYSCALL_DEFINE3(init_module, void __user *, umod, return load_module(&info, uargs, 0); } -SYSCALL_DEFINE3(finit_module, int, fd, const char __user *, uargs, int, flags) +struct idempotent { + const void *cookie; + struct hlist_node entry; + struct completion complete; + int ret; +}; + +#define IDEM_HASH_BITS 8 +static struct hlist_head idem_hash[1 << IDEM_HASH_BITS]; +static DEFINE_SPINLOCK(idem_lock); + +static bool idempotent(struct idempotent *u, const void *cookie) { + int hash = hash_ptr(cookie, IDEM_HASH_BITS); + struct hlist_head *head = idem_hash + hash; + struct idempotent *existing; + bool first; + + u->ret = 0; + u->cookie = cookie; + init_completion(&u->complete); + + spin_lock(&idem_lock); + first = true; + hlist_for_each_entry(existing, head, entry) { + if (existing->cookie != cookie) + continue; + first = false; + break; + } + hlist_add_head(&u->entry, idem_hash + hash); + spin_unlock(&idem_lock); + + return !first; +} + +/* + * We were the first one with 'cookie' on the list, and we ended + * up completing the operation. We now need to walk the list, + * remove everybody - which includes ourselves - fill in the return + * value, and then complete the operation. + */ +static void idempotent_complete(struct idempotent *u, int ret) +{ + const void *cookie = u->cookie; + int hash = hash_ptr(cookie, IDEM_HASH_BITS); + struct hlist_head *head = idem_hash + hash; + struct hlist_node *next; + struct idempotent *pos; + + spin_lock(&idem_lock); + hlist_for_each_entry_safe(pos, next, head, entry) { + if (pos->cookie != cookie) + continue; + hlist_del(&pos->entry); + pos->ret = ret; + complete(&pos->complete); + } + spin_unlock(&idem_lock); +} + +static int init_module_from_file(struct file *f, const char __user * uargs, int flags) +{ + struct idempotent idem; struct load_info info = { }; void *buf = NULL; - int len; + int len, ret; + + if (!f || !(f->f_mode & FMODE_READ)) + return -EBADF; + + if (idempotent(&idem, file_inode(f))) { + wait_for_completion(&idem.complete); + return idem.ret; + } + + len = kernel_read_file(f, 0, &buf, INT_MAX, NULL, READING_MODULE); + if (len < 0) { + mod_stat_inc(&failed_kreads); + mod_stat_add_long(len, &invalid_kread_bytes); + return len; + } + + if (flags & MODULE_INIT_COMPRESSED_FILE) { + int err = module_decompress(&info, buf, len); + vfree(buf); /* compressed data is no longer needed */ + if (err) { + mod_stat_inc(&failed_decompress); + mod_stat_add_long(len, &invalid_decompress_bytes); + return err; + } + } else { + info.hdr = buf; + info.len = len; + } + + ret = load_module(&info, uargs, flags); + idempotent_complete(&idem, ret); + return ret; +} + +SYSCALL_DEFINE3(finit_module, int, fd, const char __user *, uargs, int, flags) +{ int err; + struct fd f; err = may_init_module(); if (err) @@ -3108,28 +3200,10 @@ SYSCALL_DEFINE3(finit_module, int, fd, const char __user *, uargs, int, flags) |MODULE_INIT_COMPRESSED_FILE)) return -EINVAL; - len = kernel_read_file_from_fd(fd, 0, &buf, INT_MAX, NULL, - READING_MODULE); - if (len < 0) { - mod_stat_inc(&failed_kreads); - mod_stat_add_long(len, &invalid_kread_bytes); - return len; - } - - if (flags & MODULE_INIT_COMPRESSED_FILE) { - err = module_decompress(&info, buf, len); - vfree(buf); /* compressed data is no longer needed */ - if (err) { - mod_stat_inc(&failed_decompress); - mod_stat_add_long(len, &invalid_decompress_bytes); - return err; - } - } else { - info.hdr = buf; - info.len = len; - } - - return load_module(&info, uargs, flags); + f = fdget(fd); + err = init_module_from_file(f.file, uargs, flags); + fdput(f); + return err; } /* Keep in sync with MODULE_FLAGS_BUF_SIZE !!! */ diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_ksym.c b/tools/testing/selftests/bpf/progs/bpf_iter_ksym.c index 5ddcc46fd886..521267818f4d 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_ksym.c +++ b/tools/testing/selftests/bpf/progs/bpf_iter_ksym.c @@ -59,9 +59,7 @@ int dump_ksym(struct bpf_iter__ksym *ctx) } else { BPF_SEQ_PRINTF(seq, "0x%llx %c %s ", value, type, iter->name); } - if (!iter->pos_arch_end || iter->pos_arch_end > iter->pos) - BPF_SEQ_PRINTF(seq, "CORE "); - else if (!iter->pos_mod_end || iter->pos_mod_end > iter->pos) + if (!iter->pos_mod_end || iter->pos_mod_end > iter->pos) BPF_SEQ_PRINTF(seq, "MOD "); else if (!iter->pos_ftrace_mod_end || iter->pos_ftrace_mod_end > iter->pos) BPF_SEQ_PRINTF(seq, "FTRACE_MOD ");