diff options
Diffstat (limited to 'kernel')
34 files changed, 832 insertions, 389 deletions
diff --git a/kernel/Makefile b/kernel/Makefile index ac0d533eb7de..6c072b6da239 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -54,7 +54,7 @@ obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock.o obj-$(CONFIG_PROVE_LOCKING) += spinlock.o obj-$(CONFIG_UID16) += uid16.o obj-$(CONFIG_MODULES) += module.o -obj-$(CONFIG_MODULE_SIG) += module_signing.o modsign_pubkey.o +obj-$(CONFIG_MODULE_SIG) += module_signing.o modsign_pubkey.o modsign_certificate.o obj-$(CONFIG_KALLSYMS) += kallsyms.o obj-$(CONFIG_BSD_PROCESS_ACCT) += acct.o obj-$(CONFIG_KEXEC) += kexec.o @@ -137,10 +137,14 @@ ifeq ($(CONFIG_MODULE_SIG),y) # # Pull the signing certificate and any extra certificates into the kernel # + +quiet_cmd_touch = TOUCH $@ + cmd_touch = touch $@ + extra_certificates: - touch $@ + $(call cmd,touch) -kernel/modsign_pubkey.o: signing_key.x509 extra_certificates +kernel/modsign_certificate.o: signing_key.x509 extra_certificates ############################################################################### # diff --git a/kernel/async.c b/kernel/async.c index d9bf2a9b5cee..6c68fc3fae7b 100644 --- a/kernel/async.c +++ b/kernel/async.c @@ -88,18 +88,27 @@ static atomic_t entry_count; */ static async_cookie_t __lowest_in_progress(struct async_domain *running) { + async_cookie_t first_running = next_cookie; /* infinity value */ + async_cookie_t first_pending = next_cookie; /* ditto */ struct async_entry *entry; + /* + * Both running and pending lists are sorted but not disjoint. + * Take the first cookies from both and return the min. + */ if (!list_empty(&running->domain)) { entry = list_first_entry(&running->domain, typeof(*entry), list); - return entry->cookie; + first_running = entry->cookie; } - list_for_each_entry(entry, &async_pending, list) - if (entry->running == running) - return entry->cookie; + list_for_each_entry(entry, &async_pending, list) { + if (entry->running == running) { + first_pending = entry->cookie; + break; + } + } - return next_cookie; /* "infinity" value */ + return min(first_running, first_pending); } static async_cookie_t lowest_in_progress(struct async_domain *running) @@ -120,13 +129,17 @@ static void async_run_entry_fn(struct work_struct *work) { struct async_entry *entry = container_of(work, struct async_entry, work); + struct async_entry *pos; unsigned long flags; ktime_t uninitialized_var(calltime), delta, rettime; struct async_domain *running = entry->running; - /* 1) move self to the running queue */ + /* 1) move self to the running queue, make sure it stays sorted */ spin_lock_irqsave(&async_lock, flags); - list_move_tail(&entry->list, &running->domain); + list_for_each_entry_reverse(pos, &running->domain, list) + if (entry->cookie < pos->cookie) + break; + list_move_tail(&entry->list, &pos->list); spin_unlock_irqrestore(&async_lock, flags); /* 2) run (and print duration) */ @@ -198,6 +211,9 @@ static async_cookie_t __async_schedule(async_func_ptr *ptr, void *data, struct a atomic_inc(&entry_count); spin_unlock_irqrestore(&async_lock, flags); + /* mark that this task has queued an async job, used by module init */ + current->flags |= PF_USED_ASYNC; + /* schedule for execution */ queue_work(system_unbound_wq, &entry->work); diff --git a/kernel/audit.c b/kernel/audit.c index 40414e9143db..d596e5355f15 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -272,6 +272,8 @@ static int audit_log_config_change(char *function_name, int new, int old, int rc = 0; ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_CONFIG_CHANGE); + if (unlikely(!ab)) + return rc; audit_log_format(ab, "%s=%d old=%d auid=%u ses=%u", function_name, new, old, from_kuid(&init_user_ns, loginuid), sessionid); if (sid) { @@ -619,6 +621,8 @@ static int audit_log_common_recv_msg(struct audit_buffer **ab, u16 msg_type, } *ab = audit_log_start(NULL, GFP_KERNEL, msg_type); + if (unlikely(!*ab)) + return rc; audit_log_format(*ab, "pid=%d uid=%u auid=%u ses=%u", task_tgid_vnr(current), from_kuid(&init_user_ns, current_uid()), @@ -1097,6 +1101,23 @@ static inline void audit_get_stamp(struct audit_context *ctx, } } +/* + * Wait for auditd to drain the queue a little + */ +static void wait_for_auditd(unsigned long sleep_time) +{ + DECLARE_WAITQUEUE(wait, current); + set_current_state(TASK_INTERRUPTIBLE); + add_wait_queue(&audit_backlog_wait, &wait); + + if (audit_backlog_limit && + skb_queue_len(&audit_skb_queue) > audit_backlog_limit) + schedule_timeout(sleep_time); + + __set_current_state(TASK_RUNNING); + remove_wait_queue(&audit_backlog_wait, &wait); +} + /* Obtain an audit buffer. This routine does locking to obtain the * audit buffer, but then no locking is required for calls to * audit_log_*format. If the tsk is a task that is currently in a @@ -1142,20 +1163,13 @@ struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask, while (audit_backlog_limit && skb_queue_len(&audit_skb_queue) > audit_backlog_limit + reserve) { - if (gfp_mask & __GFP_WAIT && audit_backlog_wait_time - && time_before(jiffies, timeout_start + audit_backlog_wait_time)) { + if (gfp_mask & __GFP_WAIT && audit_backlog_wait_time) { + unsigned long sleep_time; - /* Wait for auditd to drain the queue a little */ - DECLARE_WAITQUEUE(wait, current); - set_current_state(TASK_INTERRUPTIBLE); - add_wait_queue(&audit_backlog_wait, &wait); - - if (audit_backlog_limit && - skb_queue_len(&audit_skb_queue) > audit_backlog_limit) - schedule_timeout(timeout_start + audit_backlog_wait_time - jiffies); - - __set_current_state(TASK_RUNNING); - remove_wait_queue(&audit_backlog_wait, &wait); + sleep_time = timeout_start + audit_backlog_wait_time - + jiffies; + if ((long)sleep_time > 0) + wait_for_auditd(sleep_time); continue; } if (audit_rate_check() && printk_ratelimit()) diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c index ed206fd88cca..642a89c4f3d6 100644 --- a/kernel/audit_tree.c +++ b/kernel/audit_tree.c @@ -249,7 +249,7 @@ static void untag_chunk(struct node *p) list_del_rcu(&chunk->hash); spin_unlock(&hash_lock); spin_unlock(&entry->lock); - fsnotify_destroy_mark(entry); + fsnotify_destroy_mark(entry, audit_tree_group); goto out; } @@ -291,7 +291,7 @@ static void untag_chunk(struct node *p) owner->root = new; spin_unlock(&hash_lock); spin_unlock(&entry->lock); - fsnotify_destroy_mark(entry); + fsnotify_destroy_mark(entry, audit_tree_group); fsnotify_put_mark(&new->mark); /* drop initial reference */ goto out; @@ -331,7 +331,7 @@ static int create_chunk(struct inode *inode, struct audit_tree *tree) spin_unlock(&hash_lock); chunk->dead = 1; spin_unlock(&entry->lock); - fsnotify_destroy_mark(entry); + fsnotify_destroy_mark(entry, audit_tree_group); fsnotify_put_mark(entry); return 0; } @@ -412,7 +412,7 @@ static int tag_chunk(struct inode *inode, struct audit_tree *tree) spin_unlock(&chunk_entry->lock); spin_unlock(&old_entry->lock); - fsnotify_destroy_mark(chunk_entry); + fsnotify_destroy_mark(chunk_entry, audit_tree_group); fsnotify_put_mark(chunk_entry); fsnotify_put_mark(old_entry); @@ -443,17 +443,32 @@ static int tag_chunk(struct inode *inode, struct audit_tree *tree) spin_unlock(&hash_lock); spin_unlock(&chunk_entry->lock); spin_unlock(&old_entry->lock); - fsnotify_destroy_mark(old_entry); + fsnotify_destroy_mark(old_entry, audit_tree_group); fsnotify_put_mark(chunk_entry); /* drop initial reference */ fsnotify_put_mark(old_entry); /* pair to fsnotify_find mark_entry */ return 0; } +static void audit_log_remove_rule(struct audit_krule *rule) +{ + struct audit_buffer *ab; + + ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_CONFIG_CHANGE); + if (unlikely(!ab)) + return; + audit_log_format(ab, "op="); + audit_log_string(ab, "remove rule"); + audit_log_format(ab, " dir="); + audit_log_untrustedstring(ab, rule->tree->pathname); + audit_log_key(ab, rule->filterkey); + audit_log_format(ab, " list=%d res=1", rule->listnr); + audit_log_end(ab); +} + static void kill_rules(struct audit_tree *tree) { struct audit_krule *rule, *next; struct audit_entry *entry; - struct audit_buffer *ab; list_for_each_entry_safe(rule, next, &tree->rules, rlist) { entry = container_of(rule, struct audit_entry, rule); @@ -461,14 +476,7 @@ static void kill_rules(struct audit_tree *tree) list_del_init(&rule->rlist); if (rule->tree) { /* not a half-baked one */ - ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_CONFIG_CHANGE); - audit_log_format(ab, "op="); - audit_log_string(ab, "remove rule"); - audit_log_format(ab, " dir="); - audit_log_untrustedstring(ab, rule->tree->pathname); - audit_log_key(ab, rule->filterkey); - audit_log_format(ab, " list=%d res=1", rule->listnr); - audit_log_end(ab); + audit_log_remove_rule(rule); rule->tree = NULL; list_del_rcu(&entry->list); list_del(&entry->rule.list); diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c index 9a9ae6e3d290..22831c4d369c 100644 --- a/kernel/audit_watch.c +++ b/kernel/audit_watch.c @@ -240,6 +240,8 @@ static void audit_watch_log_rule_change(struct audit_krule *r, struct audit_watc if (audit_enabled) { struct audit_buffer *ab; ab = audit_log_start(NULL, GFP_NOFS, AUDIT_CONFIG_CHANGE); + if (unlikely(!ab)) + return; audit_log_format(ab, "auid=%u ses=%u op=", from_kuid(&init_user_ns, audit_get_loginuid(current)), audit_get_sessionid(current)); @@ -350,7 +352,7 @@ static void audit_remove_parent_watches(struct audit_parent *parent) } mutex_unlock(&audit_filter_mutex); - fsnotify_destroy_mark(&parent->mark); + fsnotify_destroy_mark(&parent->mark, audit_watch_group); } /* Get path information necessary for adding watches. */ @@ -457,7 +459,7 @@ void audit_remove_watch_rule(struct audit_krule *krule) if (list_empty(&parent->watches)) { audit_get_parent(parent); - fsnotify_destroy_mark(&parent->mark); + fsnotify_destroy_mark(&parent->mark, audit_watch_group); audit_put_parent(parent); } } diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c index 7f19f23d38a3..f9fc54bbe06f 100644 --- a/kernel/auditfilter.c +++ b/kernel/auditfilter.c @@ -1144,7 +1144,6 @@ static void audit_log_rule_change(kuid_t loginuid, u32 sessionid, u32 sid, * audit_receive_filter - apply all rules to the specified message type * @type: audit message type * @pid: target pid for netlink audit messages - * @uid: target uid for netlink audit messages * @seq: netlink audit message sequence (serial) number * @data: payload data * @datasz: size of payload data diff --git a/kernel/auditsc.c b/kernel/auditsc.c index e37e6a12c5e3..a371f857a0a9 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -1464,14 +1464,14 @@ static void show_special(struct audit_context *context, int *call_panic) audit_log_end(ab); ab = audit_log_start(context, GFP_KERNEL, AUDIT_IPC_SET_PERM); + if (unlikely(!ab)) + return; audit_log_format(ab, "qbytes=%lx ouid=%u ogid=%u mode=%#ho", context->ipc.qbytes, context->ipc.perm_uid, context->ipc.perm_gid, context->ipc.perm_mode); - if (!ab) - return; } break; } case AUDIT_MQ_OPEN: { @@ -2675,7 +2675,7 @@ void __audit_mmap_fd(int fd, int flags) context->type = AUDIT_MMAP; } -static void audit_log_abend(struct audit_buffer *ab, char *reason, long signr) +static void audit_log_task(struct audit_buffer *ab) { kuid_t auid, uid; kgid_t gid; @@ -2693,6 +2693,11 @@ static void audit_log_abend(struct audit_buffer *ab, char *reason, long signr) audit_log_task_context(ab); audit_log_format(ab, " pid=%d comm=", current->pid); audit_log_untrustedstring(ab, current->comm); +} + +static void audit_log_abend(struct audit_buffer *ab, char *reason, long signr) +{ + audit_log_task(ab); audit_log_format(ab, " reason="); audit_log_string(ab, reason); audit_log_format(ab, " sig=%ld", signr); @@ -2715,6 +2720,8 @@ void audit_core_dumps(long signr) return; ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_ANOM_ABEND); + if (unlikely(!ab)) + return; audit_log_abend(ab, "memory violation", signr); audit_log_end(ab); } @@ -2723,8 +2730,11 @@ void __audit_seccomp(unsigned long syscall, long signr, int code) { struct audit_buffer *ab; - ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_ANOM_ABEND); - audit_log_abend(ab, "seccomp", signr); + ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_SECCOMP); + if (unlikely(!ab)) + return; + audit_log_task(ab); + audit_log_format(ab, " sig=%ld", signr); audit_log_format(ab, " syscall=%ld", syscall); audit_log_format(ab, " compat=%d", is_compat_task()); audit_log_format(ab, " ip=0x%lx", KSTK_EIP(current)); diff --git a/kernel/compat.c b/kernel/compat.c index f6150e92dfc9..36700e9e2be9 100644 --- a/kernel/compat.c +++ b/kernel/compat.c @@ -535,9 +535,11 @@ asmlinkage long compat_sys_getrusage(int who, struct compat_rusage __user *ru) return 0; } -asmlinkage long -compat_sys_wait4(compat_pid_t pid, compat_uint_t __user *stat_addr, int options, - struct compat_rusage __user *ru) +COMPAT_SYSCALL_DEFINE4(wait4, + compat_pid_t, pid, + compat_uint_t __user *, stat_addr, + int, options, + struct compat_rusage __user *, ru) { if (!ru) { return sys_wait4(pid, stat_addr, options, NULL); @@ -564,9 +566,10 @@ compat_sys_wait4(compat_pid_t pid, compat_uint_t __user *stat_addr, int options, } } -asmlinkage long compat_sys_waitid(int which, compat_pid_t pid, - struct compat_siginfo __user *uinfo, int options, - struct compat_rusage __user *uru) +COMPAT_SYSCALL_DEFINE5(waitid, + int, which, compat_pid_t, pid, + struct compat_siginfo __user *, uinfo, int, options, + struct compat_rusage __user *, uru) { siginfo_t info; struct rusage ru; @@ -584,7 +587,11 @@ asmlinkage long compat_sys_waitid(int which, compat_pid_t pid, return ret; if (uru) { - ret = put_compat_rusage(&ru, uru); + /* sys_waitid() overwrites everything in ru */ + if (COMPAT_USE_64BIT_TIME) + ret = copy_to_user(uru, &ru, sizeof(ru)); + else + ret = put_compat_rusage(&ru, uru); if (ret) return ret; } @@ -994,7 +1001,7 @@ compat_sys_rt_sigtimedwait (compat_sigset_t __user *uthese, sigset_from_compat(&s, &s32); if (uts) { - if (get_compat_timespec(&t, uts)) + if (compat_get_timespec(&t, uts)) return -EFAULT; } diff --git a/kernel/cred.c b/kernel/cred.c index 8888afb846e9..e0573a43c7df 100644 --- a/kernel/cred.c +++ b/kernel/cred.c @@ -372,6 +372,31 @@ error_put: return ret; } +static bool cred_cap_issubset(const struct cred *set, const struct cred *subset) +{ + const struct user_namespace *set_ns = set->user_ns; + const struct user_namespace *subset_ns = subset->user_ns; + + /* If the two credentials are in the same user namespace see if + * the capabilities of subset are a subset of set. + */ + if (set_ns == subset_ns) + return cap_issubset(subset->cap_permitted, set->cap_permitted); + + /* The credentials are in a different user namespaces + * therefore one is a subset of the other only if a set is an + * ancestor of subset and set->euid is owner of subset or one + * of subsets ancestors. + */ + for (;subset_ns != &init_user_ns; subset_ns = subset_ns->parent) { + if ((set_ns == subset_ns->parent) && + uid_eq(subset_ns->owner, set->euid)) + return true; + } + + return false; +} + /** * commit_creds - Install new credentials upon the current task * @new: The credentials to be assigned @@ -410,7 +435,7 @@ int commit_creds(struct cred *new) !gid_eq(old->egid, new->egid) || !uid_eq(old->fsuid, new->fsuid) || !gid_eq(old->fsgid, new->fsgid) || - !cap_issubset(new->cap_permitted, old->cap_permitted)) { + !cred_cap_issubset(old, new)) { if (task->mm) set_dumpable(task->mm, suid_dumpable); task->pdeath_signal = 0; diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c index 4d5f8d5612f3..8875254120b6 100644 --- a/kernel/debug/kdb/kdb_main.c +++ b/kernel/debug/kdb/kdb_main.c @@ -1970,6 +1970,8 @@ static int kdb_lsmod(int argc, const char **argv) kdb_printf("Module Size modstruct Used by\n"); list_for_each_entry(mod, kdb_modules, list) { + if (mod->state == MODULE_STATE_UNFORMED) + continue; kdb_printf("%-20s%8u 0x%p ", mod->name, mod->core_size, (void *)mod); diff --git a/kernel/fork.c b/kernel/fork.c index c36c4e301efe..c535f33bbb9c 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -146,7 +146,7 @@ void __weak arch_release_thread_info(struct thread_info *ti) static struct thread_info *alloc_thread_info_node(struct task_struct *tsk, int node) { - struct page *page = alloc_pages_node(node, THREADINFO_GFP, + struct page *page = alloc_pages_node(node, THREADINFO_GFP_ACCOUNTED, THREAD_SIZE_ORDER); return page ? page_address(page) : NULL; @@ -154,7 +154,7 @@ static struct thread_info *alloc_thread_info_node(struct task_struct *tsk, static inline void free_thread_info(struct thread_info *ti) { - free_pages((unsigned long)ti, THREAD_SIZE_ORDER); + free_memcg_kmem_pages((unsigned long)ti, THREAD_SIZE_ORDER); } # else static struct kmem_cache *thread_info_cache; @@ -1166,6 +1166,14 @@ static struct task_struct *copy_process(unsigned long clone_flags, current->signal->flags & SIGNAL_UNKILLABLE) return ERR_PTR(-EINVAL); + /* + * If the new process will be in a different pid namespace + * don't allow the creation of threads. + */ + if ((clone_flags & (CLONE_VM|CLONE_NEWPID)) && + (task_active_pid_ns(current) != current->nsproxy->pid_ns)) + return ERR_PTR(-EINVAL); + retval = security_task_create(clone_flags); if (retval) goto fork_out; @@ -1613,7 +1621,6 @@ long do_fork(unsigned long clone_flags, return nr; } -#ifdef CONFIG_GENERIC_KERNEL_THREAD /* * Create a kernel thread. */ @@ -1622,7 +1629,6 @@ pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags) return do_fork(flags|CLONE_VM|CLONE_UNTRACED, (unsigned long)fn, (unsigned long)arg, NULL, NULL); } -#endif #ifdef __ARCH_WANT_SYS_FORK SYSCALL_DEFINE0(fork) @@ -1662,8 +1668,10 @@ SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp, int, tls_val) #endif { - return do_fork(clone_flags, newsp, 0, - parent_tidptr, child_tidptr); + long ret = do_fork(clone_flags, newsp, 0, parent_tidptr, child_tidptr); + asmlinkage_protect(5, ret, clone_flags, newsp, + parent_tidptr, child_tidptr, tls_val); + return ret; } #endif diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 35c70c9e24d8..e49a288fa479 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -818,7 +818,7 @@ static void irq_thread_dtor(struct callback_head *unused) action = kthread_data(tsk); pr_err("exiting task \"%s\" (%d) is an active IRQ thread (irq %d)\n", - tsk->comm ? tsk->comm : "", tsk->pid, action->irq); + tsk->comm, tsk->pid, action->irq); desc = irq_to_desc(action->irq); diff --git a/kernel/kcmp.c b/kernel/kcmp.c index 30b7b225306c..e30ac0fe61c3 100644 --- a/kernel/kcmp.c +++ b/kernel/kcmp.c @@ -4,6 +4,7 @@ #include <linux/string.h> #include <linux/random.h> #include <linux/module.h> +#include <linux/ptrace.h> #include <linux/init.h> #include <linux/errno.h> #include <linux/cache.h> diff --git a/kernel/kmod.c b/kernel/kmod.c index ecd42b484db8..56dd34976d7b 100644 --- a/kernel/kmod.c +++ b/kernel/kmod.c @@ -228,9 +228,9 @@ static int ____call_usermodehelper(void *data) commit_creds(new); - retval = kernel_execve(sub_info->path, - (const char *const *)sub_info->argv, - (const char *const *)sub_info->envp); + retval = do_execve(sub_info->path, + (const char __user *const __user *)sub_info->argv, + (const char __user *const __user *)sub_info->envp); if (!retval) return 0; diff --git a/kernel/modsign_certificate.S b/kernel/modsign_certificate.S new file mode 100644 index 000000000000..246b4c6e6135 --- /dev/null +++ b/kernel/modsign_certificate.S @@ -0,0 +1,19 @@ +/* SYMBOL_PREFIX defined on commandline from CONFIG_SYMBOL_PREFIX */ +#ifndef SYMBOL_PREFIX +#define ASM_SYMBOL(sym) sym +#else +#define PASTE2(x,y) x##y +#define PASTE(x,y) PASTE2(x,y) +#define ASM_SYMBOL(sym) PASTE(SYMBOL_PREFIX, sym) +#endif + +#define GLOBAL(name) \ + .globl ASM_SYMBOL(name); \ + ASM_SYMBOL(name): + + .section ".init.data","aw" + +GLOBAL(modsign_certificate_list) + .incbin "signing_key.x509" + .incbin "extra_certificates" +GLOBAL(modsign_certificate_list_end) diff --git a/kernel/modsign_pubkey.c b/kernel/modsign_pubkey.c index 767e559dfb10..2b6e69909c39 100644 --- a/kernel/modsign_pubkey.c +++ b/kernel/modsign_pubkey.c @@ -20,12 +20,6 @@ struct key *modsign_keyring; extern __initdata const u8 modsign_certificate_list[]; extern __initdata const u8 modsign_certificate_list_end[]; -asm(".section .init.data,\"aw\"\n" - SYMBOL_PREFIX "modsign_certificate_list:\n" - ".incbin \"signing_key.x509\"\n" - ".incbin \"extra_certificates\"\n" - SYMBOL_PREFIX "modsign_certificate_list_end:" - ); /* * We need to make sure ccache doesn't cache the .o file as it doesn't notice @@ -40,18 +34,15 @@ static __init int module_verify_init(void) { pr_notice("Initialise module verification\n"); - modsign_keyring = key_alloc(&key_type_keyring, ".module_sign", - KUIDT_INIT(0), KGIDT_INIT(0), - current_cred(), - (KEY_POS_ALL & ~KEY_POS_SETATTR) | - KEY_USR_VIEW | KEY_USR_READ, - KEY_ALLOC_NOT_IN_QUOTA); + modsign_keyring = keyring_alloc(".module_sign", + KUIDT_INIT(0), KGIDT_INIT(0), + current_cred(), + ((KEY_POS_ALL & ~KEY_POS_SETATTR) | + KEY_USR_VIEW | KEY_USR_READ), + KEY_ALLOC_NOT_IN_QUOTA, NULL); if (IS_ERR(modsign_keyring)) panic("Can't allocate module signing keyring\n"); - if (key_instantiate_and_link(modsign_keyring, NULL, 0, NULL, NULL) < 0) - panic("Can't instantiate module signing keyring\n"); - return 0; } diff --git a/kernel/module.c b/kernel/module.c index 808bd62e1723..eab08274ec9b 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -21,6 +21,7 @@ #include <linux/ftrace_event.h> #include <linux/init.h> #include <linux/kallsyms.h> +#include <linux/file.h> #include <linux/fs.h> #include <linux/sysfs.h> #include <linux/kernel.h> @@ -28,6 +29,7 @@ #include <linux/vmalloc.h> #include <linux/elf.h> #include <linux/proc_fs.h> +#include <linux/security.h> #include <linux/seq_file.h> #include <linux/syscalls.h> #include <linux/fcntl.h> @@ -59,6 +61,7 @@ #include <linux/pfn.h> #include <linux/bsearch.h> #include <linux/fips.h> +#include <uapi/linux/module.h> #include "module-internal.h" #define CREATE_TRACE_POINTS @@ -185,6 +188,7 @@ struct load_info { ongoing or failed initialization etc. */ static inline int strong_try_module_get(struct module *mod) { + BUG_ON(mod && mod->state == MODULE_STATE_UNFORMED); if (mod && mod->state == MODULE_STATE_COMING) return -EBUSY; if (try_module_get(mod)) @@ -340,6 +344,9 @@ bool each_symbol_section(bool (*fn)(const struct symsearch *arr, #endif }; + if (mod->state == MODULE_STATE_UNFORMED) + continue; + if (each_symbol_in_section(arr, ARRAY_SIZE(arr), mod, fn, data)) return true; } @@ -447,16 +454,24 @@ const struct kernel_symbol *find_symbol(const char *name, EXPORT_SYMBOL_GPL(find_symbol); /* Search for module by name: must hold module_mutex. */ -struct module *find_module(const char *name) +static struct module *find_module_all(const char *name, + bool even_unformed) { struct module *mod; list_for_each_entry(mod, &modules, list) { + if (!even_unformed && mod->state == MODULE_STATE_UNFORMED) + continue; if (strcmp(mod->name, name) == 0) return mod; } return NULL; } + +struct module *find_module(const char *name) +{ + return find_module_all(name, false); +} EXPORT_SYMBOL_GPL(find_module); #ifdef CONFIG_SMP @@ -522,6 +537,8 @@ bool is_module_percpu_address(unsigned long addr) preempt_disable(); list_for_each_entry_rcu(mod, &modules, list) { + if (mod->state == MODULE_STATE_UNFORMED) + continue; if (!mod->percpu_size) continue; for_each_possible_cpu(cpu) { @@ -1045,6 +1062,8 @@ static ssize_t show_initstate(struct module_attribute *mattr, case MODULE_STATE_GOING: state = "going"; break; + default: + BUG(); } return sprintf(buffer, "%s\n", state); } @@ -1783,6 +1802,8 @@ void set_all_modules_text_rw(void) mutex_lock(&module_mutex); list_for_each_entry_rcu(mod, &modules, list) { + if (mod->state == MODULE_STATE_UNFORMED) + continue; if ((mod->module_core) && (mod->core_text_size)) { set_page_attributes(mod->module_core, mod->module_core + mod->core_text_size, @@ -1804,6 +1825,8 @@ void set_all_modules_text_ro(void) mutex_lock(&module_mutex); list_for_each_entry_rcu(mod, &modules, list) { + if (mod->state == MODULE_STATE_UNFORMED) + continue; if ((mod->module_core) && (mod->core_text_size)) { set_page_attributes(mod->module_core, mod->module_core + mod->core_text_size, @@ -2279,7 +2302,7 @@ static void layout_symtab(struct module *mod, struct load_info *info) Elf_Shdr *symsect = info->sechdrs + info->index.sym; Elf_Shdr *strsect = info->sechdrs + info->index.str; const Elf_Sym *src; - unsigned int i, nsrc, ndst, strtab_size; + unsigned int i, nsrc, ndst, strtab_size = 0; /* Put symbol section at end of init part of module. */ symsect->sh_flags |= SHF_ALLOC; @@ -2290,9 +2313,6 @@ static void layout_symtab(struct module *mod, struct load_info *info) src = (void *)info->hdr + symsect->sh_offset; nsrc = symsect->sh_size / sizeof(*src); - /* strtab always starts with a nul, so offset 0 is the empty string. */ - strtab_size = 1; - /* Compute total space required for the core symbols' strtab. */ for (ndst = i = 0; i < nsrc; i++) { if (i == 0 || @@ -2334,7 +2354,6 @@ static void add_kallsyms(struct module *mod, const struct load_info *info) mod->core_symtab = dst = mod->module_core + info->symoffs; mod->core_strtab = s = mod->module_core + info->stroffs; src = mod->symtab; - *s++ = 0; for (ndst = i = 0; i < mod->num_symtab; i++) { if (i == 0 || is_core_symbol(src+i, info->sechdrs, info->hdr->e_shnum)) { @@ -2375,7 +2394,7 @@ static void dynamic_debug_remove(struct _ddebug *debug) void * __weak module_alloc(unsigned long size) { - return size == 0 ? NULL : vmalloc_exec(size); + return vmalloc_exec(size); } static void *module_alloc_update_bounds(unsigned long size) @@ -2422,18 +2441,17 @@ static inline void kmemleak_load_module(const struct module *mod, #endif #ifdef CONFIG_MODULE_SIG -static int module_sig_check(struct load_info *info, - const void *mod, unsigned long *_len) +static int module_sig_check(struct load_info *info) { int err = -ENOKEY; - unsigned long markerlen = sizeof(MODULE_SIG_STRING) - 1; - unsigned long len = *_len; + const unsigned long markerlen = sizeof(MODULE_SIG_STRING) - 1; + const void *mod = info->hdr; - if (len > markerlen && - memcmp(mod + len - markerlen, MODULE_SIG_STRING, markerlen) == 0) { + if (info->len > markerlen && + memcmp(mod + info->len - markerlen, MODULE_SIG_STRING, markerlen) == 0) { /* We truncate the module to discard the signature */ - *_len -= markerlen; - err = mod_verify_sig(mod, _len); + info->len -= markerlen; + err = mod_verify_sig(mod, &info->len); } if (!err) { @@ -2451,59 +2469,114 @@ static int module_sig_check(struct load_info *info, return err; } #else /* !CONFIG_MODULE_SIG */ -static int module_sig_check(struct load_info *info, - void *mod, unsigned long *len) +static int module_sig_check(struct load_info *info) { return 0; } #endif /* !CONFIG_MODULE_SIG */ -/* Sets info->hdr, info->len and info->sig_ok. */ -static int copy_and_check(struct load_info *info, - const void __user *umod, unsigned long len, - const char __user *uargs) +/* Sanity checks against invalid binaries, wrong arch, weird elf version. */ +static int elf_header_check(struct load_info *info) +{ + if (info->len < sizeof(*(info->hdr))) + return -ENOEXEC; + + if (memcmp(info->hdr->e_ident, ELFMAG, SELFMAG) != 0 + || info->hdr->e_type != ET_REL + || !elf_check_arch(info->hdr) + || info->hdr->e_shentsize != sizeof(Elf_Shdr)) + return -ENOEXEC; + + if (info->hdr->e_shoff >= info->len + || (info->hdr->e_shnum * sizeof(Elf_Shdr) > + info->len - info->hdr->e_shoff)) + return -ENOEXEC; + + return 0; +} + +/* Sets info->hdr and info->len. */ +static int copy_module_from_user(const void __user *umod, unsigned long len, + struct load_info *info) { int err; - Elf_Ehdr *hdr; - if (len < sizeof(*hdr)) + info->len = len; + if (info->len < sizeof(*(info->hdr))) return -ENOEXEC; + err = security_kernel_module_from_file(NULL); + if (err) + return err; + /* Suck in entire file: we'll want most of it. */ - if ((hdr = vmalloc(len)) == NULL) + info->hdr = vmalloc(info->len); + if (!info->hdr) return -ENOMEM; - if (copy_from_user(hdr, umod, len) != 0) { - err = -EFAULT; - goto free_hdr; + if (copy_from_user(info->hdr, umod, info->len) != 0) { + vfree(info->hdr); + return -EFAULT; } - err = module_sig_check(info, hdr, &len); + return 0; +} + +/* Sets info->hdr and info->len. */ +static int copy_module_from_fd(int fd, struct load_info *info) +{ + struct file *file; + int err; + struct kstat stat; + loff_t pos; + ssize_t bytes = 0; + + file = fget(fd); + if (!file) + return -ENOEXEC; + + err = security_kernel_module_from_file(file); + if (err) + goto out; + + err = vfs_getattr(file->f_vfsmnt, file->f_dentry, &stat); if (err) - goto free_hdr; + goto out; - /* Sanity checks against insmoding binaries or wrong arch, - weird elf version */ - if (memcmp(hdr->e_ident, ELFMAG, SELFMAG) != 0 - || hdr->e_type != ET_REL - || !elf_check_arch(hdr) - || hdr->e_shentsize != sizeof(Elf_Shdr)) { - err = -ENOEXEC; - goto free_hdr; + if (stat.size > INT_MAX) { + err = -EFBIG; + goto out; } - if (hdr->e_shoff >= len || - hdr->e_shnum * sizeof(Elf_Shdr) > len - hdr->e_shoff) { - err = -ENOEXEC; - goto free_hdr; + /* Don't hand 0 to vmalloc, it whines. */ + if (stat.size == 0) { + err = -EINVAL; + goto out; } - info->hdr = hdr; - info->len = len; - return 0; + info->hdr = vmalloc(stat.size); + if (!info->hdr) { + err = -ENOMEM; + goto out; + } + + pos = 0; + while (pos < stat.size) { + bytes = kernel_read(file, pos, (char *)(info->hdr) + pos, + stat.size - pos); + if (bytes < 0) { + vfree(info->hdr); + err = bytes; + goto out; + } + if (bytes == 0) + break; + pos += bytes; + } + info->len = pos; -free_hdr: - vfree(hdr); +out: + fput(file); return err; } @@ -2512,7 +2585,7 @@ static void free_copy(struct load_info *info) vfree(info->hdr); } -static int rewrite_section_headers(struct load_info *info) +static int rewrite_section_headers(struct load_info *info, int flags) { unsigned int i; @@ -2540,7 +2613,10 @@ static int rewrite_section_headers(struct load_info *info) } /* Track but don't keep modinfo and version sections. */ - info->index.vers = find_sec(info, "__versions"); + if (flags & MODULE_INIT_IGNORE_MODVERSIONS) + info->index.vers = 0; /* Pretend no __versions section! */ + else + info->index.vers = find_sec(info, "__versions"); info->index.info = find_sec(info, ".modinfo"); info->sechdrs[info->index.info].sh_flags &= ~(unsigned long)SHF_ALLOC; info->sechdrs[info->index.vers].sh_flags &= ~(unsigned long)SHF_ALLOC; @@ -2555,7 +2631,7 @@ static int rewrite_section_headers(struct load_info *info) * Return the temporary module pointer (we'll replace it with the final * one when we move the module sections around). */ -static struct module *setup_load_info(struct load_info *info) +static struct module *setup_load_info(struct load_info *info, int flags) { unsigned int i; int err; @@ -2566,7 +2642,7 @@ static struct module *setup_load_info(struct load_info *info) info->secstrings = (void *)info->hdr + info->sechdrs[info->hdr->e_shstrndx].sh_offset; - err = rewrite_section_headers(info); + err = rewrite_section_headers(info, flags); if (err) return ERR_PTR(err); @@ -2604,11 +2680,14 @@ static struct module *setup_load_info(struct load_info *info) return mod; } -static int check_modinfo(struct module *mod, struct load_info *info) +static int check_modinfo(struct module *mod, struct load_info *info, int flags) { const char *modmagic = get_modinfo(info, "vermagic"); int err; + if (flags & MODULE_INIT_IGNORE_VERMAGIC) + modmagic = NULL; + /* This is allowed: modprobe --force will invalidate it. */ if (!modmagic) { err = try_to_force_load(mod, "bad vermagic"); @@ -2738,20 +2817,23 @@ static int move_module(struct module *mod, struct load_info *info) memset(ptr, 0, mod->core_size); 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) { - module_free(mod, mod->module_core); - return -ENOMEM; - } - memset(ptr, 0, mod->init_size); - mod->module_init = ptr; + if (mod->init_size) { + 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) { + module_free(mod, mod->module_core); + return -ENOMEM; + } + memset(ptr, 0, mod->init_size); + mod->module_init = ptr; + } else + mod->module_init = NULL; /* Transfer each section which specifies SHF_ALLOC */ pr_debug("final section addresses:\n"); @@ -2844,18 +2926,18 @@ int __weak module_frob_arch_sections(Elf_Ehdr *hdr, return 0; } -static struct module *layout_and_allocate(struct load_info *info) +static struct module *layout_and_allocate(struct load_info *info, int flags) { /* Module within temporary copy. */ struct module *mod; Elf_Shdr *pcpusec; int err; - mod = setup_load_info(info); + mod = setup_load_info(info, flags); if (IS_ERR(mod)) return mod; - err = check_modinfo(mod, info); + err = check_modinfo(mod, info, flags); if (err) return ERR_PTR(err); @@ -2935,40 +3017,181 @@ static bool finished_loading(const char *name) bool ret; mutex_lock(&module_mutex); - mod = find_module(name); - ret = !mod || mod->state != MODULE_STATE_COMING; + mod = find_module_all(name, true); + ret = !mod || mod->state == MODULE_STATE_LIVE + || mod->state == MODULE_STATE_GOING; mutex_unlock(&module_mutex); return ret; } +/* 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 */ +static int do_init_module(struct module *mod) +{ + int ret = 0; + + /* + * We want to find out whether @mod uses async during init. Clear + * PF_USED_ASYNC. async_schedule*() will set it. + */ + current->flags &= ~PF_USED_ASYNC; + + blocking_notifier_call_chain(&module_notify_list, + MODULE_STATE_COMING, mod); + + /* Set RO and NX regions for core */ + set_section_ro_nx(mod->module_core, + mod->core_text_size, + mod->core_ro_size, + mod->core_size); + + /* Set RO and NX regions for init */ + set_section_ro_nx(mod->module_init, + mod->init_text_size, + mod->init_ro_size, + mod->init_size); + + do_mod_ctors(mod); + /* Start the module */ + if (mod->init != NULL) + 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); + free_module(mod); + wake_up_all(&module_wq); + return ret; + } + if (ret > 0) { + 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(); + } + + /* Now it's a first class citizen! */ + mod->state = MODULE_STATE_LIVE; + 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. This has potential to deadlock. For example, a newly + * detected block device can trigger request_module() of the + * default iosched from async probing task. Once userland helper + * reaches here, async_synchronize_full() will wait on the async + * task waiting on request_module() and deadlock. + * + * This deadlock is avoided by perfomring async_synchronize_full() + * iff module init queued any async jobs. This isn't a full + * solution as it will deadlock the same if module loading from + * async jobs nests more than once; however, due to the various + * constraints, this hack seems to be the best option for now. + * Please refer to the following thread for details. + * + * http://thread.gmane.org/gmane.linux.kernel/1420814 + */ + if (current->flags & PF_USED_ASYNC) + 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 + unset_module_init_ro_nx(mod); + module_free(mod, mod->module_init); + mod->module_init = NULL; + mod->init_size = 0; + mod->init_ro_size = 0; + mod->init_text_size = 0; + mutex_unlock(&module_mutex); + wake_up_all(&module_wq); + + return 0; +} + +static int may_init_module(void) +{ + if (!capable(CAP_SYS_MODULE) || modules_disabled) + return -EPERM; + + return 0; +} + /* 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, - unsigned long len, - const char __user *uargs) +static int load_module(struct load_info *info, const char __user *uargs, + int flags) { - struct load_info info = { NULL, }; struct module *mod, *old; long err; - pr_debug("load_module: umod=%p, len=%lu, uargs=%p\n", - umod, len, uargs); + err = module_sig_check(info); + if (err) + goto free_copy; - /* Copy in the blobs from userspace, check they are vaguely sane. */ - err = copy_and_check(&info, umod, len, uargs); + err = elf_header_check(info); if (err) - return ERR_PTR(err); + goto free_copy; /* Figure out module layout, and allocate all the memory. */ - mod = layout_and_allocate(&info); + mod = layout_and_allocate(info, flags); if (IS_ERR(mod)) { err = PTR_ERR(mod); goto free_copy; } + /* + * We try to place it in the list now to make sure it's unique + * before we dedicate too many resources. In particular, + * temporary percpu memory exhaustion. + */ + mod->state = MODULE_STATE_UNFORMED; +again: + mutex_lock(&module_mutex); + if ((old = find_module_all(mod->name, true)) != NULL) { + if (old->state == MODULE_STATE_COMING + || old->state == MODULE_STATE_UNFORMED) { + /* Wait in case it fails to load. */ + mutex_unlock(&module_mutex); + err = wait_event_interruptible(module_wq, + finished_loading(mod->name)); + if (err) + goto free_module; + goto again; + } + err = -EEXIST; + mutex_unlock(&module_mutex); + goto free_module; + } + list_add_rcu(&mod->list, &modules); + mutex_unlock(&module_mutex); + #ifdef CONFIG_MODULE_SIG - mod->sig_ok = info.sig_ok; + mod->sig_ok = info->sig_ok; if (!mod->sig_ok) add_taint_module(mod, TAINT_FORCED_MODULE); #endif @@ -2976,29 +3199,29 @@ static struct module *load_module(void __user *umod, /* Now module is in final location, initialize linked lists, etc. */ err = module_unload_init(mod); if (err) - goto free_module; + goto unlink_mod; /* Now we've got everything in the final locations, we can * find optional sections. */ - find_module_sections(mod, &info); + find_module_sections(mod, info); err = check_module_license_and_versions(mod); if (err) goto free_unload; /* Set up MODINFO_ATTR fields */ - setup_modinfo(mod, &info); + setup_modinfo(mod, info); /* Fix up syms, so that st_value is a pointer to location. */ - err = simplify_symbols(mod, &info); + err = simplify_symbols(mod, info); if (err < 0) goto free_modinfo; - err = apply_relocations(mod, &info); + err = apply_relocations(mod, info); if (err < 0) goto free_modinfo; - err = post_relocation(mod, &info); + err = post_relocation(mod, info); if (err < 0) goto free_modinfo; @@ -3011,72 +3234,49 @@ static struct module *load_module(void __user *umod, goto free_arch_cleanup; } - /* Mark state as coming so strong_try_module_get() ignores us. */ - mod->state = MODULE_STATE_COMING; + dynamic_debug_setup(info->debug, info->num_debug); - /* Now sew it into the lists so we can get lockdep and oops - * info during argument parsing. No one 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. - */ -again: mutex_lock(&module_mutex); - if ((old = find_module(mod->name)) != NULL) { - if (old->state == MODULE_STATE_COMING) { - /* Wait in case it fails to load. */ - mutex_unlock(&module_mutex); - err = wait_event_interruptible(module_wq, - finished_loading(mod->name)); - if (err) - goto free_arch_cleanup; - goto again; - } - err = -EEXIST; - goto unlock; - } - - /* This has to be done once we're sure module name is unique. */ - dynamic_debug_setup(info.debug, info.num_debug); - - /* Find duplicate symbols */ + /* Find duplicate symbols (must be called under lock). */ err = verify_export_symbols(mod); if (err < 0) - goto ddebug; + goto ddebug_cleanup; + + /* This relies on module_mutex for list integrity. */ + module_bug_finalize(info->hdr, info->sechdrs, mod); + + /* Mark state as coming so strong_try_module_get() ignores us, + * but kallsyms etc. can see us. */ + mod->state = MODULE_STATE_COMING; - module_bug_finalize(info.hdr, info.sechdrs, mod); - list_add_rcu(&mod->list, &modules); mutex_unlock(&module_mutex); /* Module is ready to execute: parsing args may do that. */ err = parse_args(mod->name, mod->args, mod->kp, mod->num_kp, -32768, 32767, &ddebug_dyndbg_module_param_cb); if (err < 0) - goto unlink; + goto bug_cleanup; /* Link in to syfs. */ - err = mod_sysfs_setup(mod, &info, mod->kp, mod->num_kp); + err = mod_sysfs_setup(mod, info, mod->kp, mod->num_kp); if (err < 0) - goto unlink; + goto bug_cleanup; /* Get rid of temporary copy. */ - free_copy(&info); + free_copy(info); /* Done! */ trace_module_load(mod); - return mod; - unlink: + return do_init_module(mod); + + bug_cleanup: + /* module_bug_cleanup needs module_mutex protection */ mutex_lock(&module_mutex); - /* Unlink carefully: kallsyms could be walking list. */ - list_del_rcu(&mod->list); module_bug_cleanup(mod); - wake_up_all(&module_wq); - ddebug: - dynamic_debug_remove(info.debug); - unlock: + ddebug_cleanup: mutex_unlock(&module_mutex); + dynamic_debug_remove(info->debug); synchronize_sched(); kfree(mod->args); free_arch_cleanup: @@ -3085,107 +3285,59 @@ again: free_modinfo(mod); free_unload: module_unload_free(mod); + unlink_mod: + mutex_lock(&module_mutex); + /* Unlink carefully: kallsyms could be walking list. */ + list_del_rcu(&mod->list); + wake_up_all(&module_wq); + mutex_unlock(&module_mutex); free_module: - module_deallocate(mod, &info); + module_deallocate(mod, info); free_copy: - free_copy(&info); - return ERR_PTR(err); -} - -/* 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 + free_copy(info); + return err; } -/* This is where the real work happens */ SYSCALL_DEFINE3(init_module, void __user *, umod, unsigned long, len, const char __user *, uargs) { - struct module *mod; - int ret = 0; + int err; + struct load_info info = { }; - /* Must have permission */ - if (!capable(CAP_SYS_MODULE) || modules_disabled) - return -EPERM; + err = may_init_module(); + if (err) + return err; - /* Do all the hard work */ - mod = load_module(umod, len, uargs); - if (IS_ERR(mod)) - return PTR_ERR(mod); + pr_debug("init_module: umod=%p, len=%lu, uargs=%p\n", + umod, len, uargs); - blocking_notifier_call_chain(&module_notify_list, - MODULE_STATE_COMING, mod); + err = copy_module_from_user(umod, len, &info); + if (err) + return err; - /* Set RO and NX regions for core */ - set_section_ro_nx(mod->module_core, - mod->core_text_size, - mod->core_ro_size, - mod->core_size); + return load_module(&info, uargs, 0); +} - /* Set RO and NX regions for init */ - set_section_ro_nx(mod->module_init, - mod->init_text_size, - mod->init_ro_size, - mod->init_size); +SYSCALL_DEFINE3(finit_module, int, fd, const char __user *, uargs, int, flags) +{ + int err; + struct load_info info = { }; - do_mod_ctors(mod); - /* Start the module */ - if (mod->init != NULL) - 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); - free_module(mod); - wake_up_all(&module_wq); - return ret; - } - if (ret > 0) { - 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(); - } + err = may_init_module(); + if (err) + return err; - /* Now it's a first class citizen! */ - mod->state = MODULE_STATE_LIVE; - blocking_notifier_call_chain(&module_notify_list, - MODULE_STATE_LIVE, mod); + pr_debug("finit_module: fd=%d, uargs=%p, flags=%i\n", fd, uargs, flags); - /* We need to finish all async code before the module init sequence is done */ - async_synchronize_full(); + if (flags & ~(MODULE_INIT_IGNORE_MODVERSIONS + |MODULE_INIT_IGNORE_VERMAGIC)) + return -EINVAL; - 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 - unset_module_init_ro_nx(mod); - module_free(mod, mod->module_init); - mod->module_init = NULL; - mod->init_size = 0; - mod->init_ro_size = 0; - mod->init_text_size = 0; - mutex_unlock(&module_mutex); - wake_up_all(&module_wq); + err = copy_module_from_fd(fd, &info); + if (err) + return err; - return 0; + return load_module(&info, uargs, flags); } static inline int within(unsigned long addr, void *start, unsigned long size) @@ -3261,6 +3413,8 @@ const char *module_address_lookup(unsigned long addr, preempt_disable(); list_for_each_entry_rcu(mod, &modules, list) { + if (mod->state == MODULE_STATE_UNFORMED) + continue; if (within_module_init(addr, mod) || within_module_core(addr, mod)) { if (modname) @@ -3284,6 +3438,8 @@ int lookup_module_symbol_name(unsigned long addr, char *symname) preempt_disable(); list_for_each_entry_rcu(mod, &modules, list) { + if (mod->state == MODULE_STATE_UNFORMED) + continue; if (within_module_init(addr, mod) || within_module_core(addr, mod)) { const char *sym; @@ -3308,6 +3464,8 @@ int lookup_module_symbol_attrs(unsigned long addr, unsigned long *size, preempt_disable(); list_for_each_entry_rcu(mod, &modules, list) { + if (mod->state == MODULE_STATE_UNFORMED) + continue; if (within_module_init(addr, mod) || within_module_core(addr, mod)) { const char *sym; @@ -3335,6 +3493,8 @@ int module_get_kallsym(unsigned int symnum, unsigned long *value, char *type, preempt_disable(); list_for_each_entry_rcu(mod, &modules, list) { + if (mod->state == MODULE_STATE_UNFORMED) + continue; if (symnum < mod->num_symtab) { *value = mod->symtab[symnum].st_value; *type = mod->symtab[symnum].st_info; @@ -3377,9 +3537,12 @@ unsigned long module_kallsyms_lookup_name(const char *name) ret = mod_find_symname(mod, colon+1); *colon = ':'; } else { - list_for_each_entry_rcu(mod, &modules, list) + list_for_each_entry_rcu(mod, &modules, list) { + if (mod->state == MODULE_STATE_UNFORMED) + continue; if ((ret = mod_find_symname(mod, name)) != 0) break; + } } preempt_enable(); return ret; @@ -3394,6 +3557,8 @@ int module_kallsyms_on_each_symbol(int (*fn)(void *, const char *, int ret; list_for_each_entry(mod, &modules, list) { + if (mod->state == MODULE_STATE_UNFORMED) + continue; for (i = 0; i < mod->num_symtab; i++) { ret = fn(data, mod->strtab + mod->symtab[i].st_name, mod, mod->symtab[i].st_value); @@ -3409,6 +3574,7 @@ static char *module_flags(struct module *mod, char *buf) { int bx = 0; + BUG_ON(mod->state == MODULE_STATE_UNFORMED); if (mod->taints || mod->state == MODULE_STATE_GOING || mod->state == MODULE_STATE_COMING) { @@ -3450,6 +3616,10 @@ static int m_show(struct seq_file *m, void *p) struct module *mod = list_entry(p, struct module, list); char buf[8]; + /* We always ignore unformed modules. */ + if (mod->state == MODULE_STATE_UNFORMED) + return 0; + seq_printf(m, "%s %u", mod->name, mod->init_size + mod->core_size); print_unload_info(m, mod); @@ -3510,6 +3680,8 @@ const struct exception_table_entry *search_module_extables(unsigned long addr) preempt_disable(); list_for_each_entry_rcu(mod, &modules, list) { + if (mod->state == MODULE_STATE_UNFORMED) + continue; if (mod->num_exentries == 0) continue; @@ -3558,10 +3730,13 @@ struct module *__module_address(unsigned long addr) if (addr < module_addr_min || addr > module_addr_max) return NULL; - list_for_each_entry_rcu(mod, &modules, list) + list_for_each_entry_rcu(mod, &modules, list) { + if (mod->state == MODULE_STATE_UNFORMED) + continue; if (within_module_core(addr, mod) || within_module_init(addr, mod)) return mod; + } return NULL; } EXPORT_SYMBOL_GPL(__module_address); @@ -3614,8 +3789,11 @@ void print_modules(void) 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) + list_for_each_entry_rcu(mod, &modules, list) { + if (mod->state == MODULE_STATE_UNFORMED) + continue; printk(" %s%s", mod->name, module_flags(mod, buf)); + } preempt_enable(); if (last_unloaded_module[0]) printk(" [last unloaded: %s]", last_unloaded_module); diff --git a/kernel/pid.c b/kernel/pid.c index 36aa02ff17d6..de9af600006f 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -270,7 +270,6 @@ void free_pid(struct pid *pid) wake_up_process(ns->child_reaper); break; case 0: - ns->nr_hashed = -1; schedule_work(&ns->proc_work); break; } @@ -319,7 +318,7 @@ struct pid *alloc_pid(struct pid_namespace *ns) upid = pid->numbers + ns->level; spin_lock_irq(&pidmap_lock); - if (ns->nr_hashed < 0) + if (!(ns->nr_hashed & PIDNS_HASH_ADDING)) goto out_unlock; for ( ; upid >= pid->numbers; --upid) { hlist_add_head_rcu(&upid->pid_chain, @@ -342,6 +341,13 @@ out_free: goto out; } +void disable_pid_allocation(struct pid_namespace *ns) +{ + spin_lock_irq(&pidmap_lock); + ns->nr_hashed &= ~PIDNS_HASH_ADDING; + spin_unlock_irq(&pidmap_lock); +} + struct pid *find_pid_ns(int nr, struct pid_namespace *ns) { struct hlist_node *elem; @@ -573,6 +579,9 @@ void __init pidhash_init(void) void __init pidmap_init(void) { + /* Veryify no one has done anything silly */ + BUILD_BUG_ON(PID_MAX_LIMIT >= PIDNS_HASH_ADDING); + /* bump default and minimum pid_max based on number of cpus */ pid_max = min(pid_max_max, max_t(int, pid_max, PIDS_PER_CPU_DEFAULT * num_possible_cpus())); @@ -584,7 +593,7 @@ void __init pidmap_init(void) /* Reserve PID 0. We never call free_pidmap(0) */ set_bit(0, init_pid_ns.pidmap[0].page); atomic_dec(&init_pid_ns.pidmap[0].nr_free); - init_pid_ns.nr_hashed = 1; + init_pid_ns.nr_hashed = PIDNS_HASH_ADDING; init_pid_ns.pid_cachep = KMEM_CACHE(pid, SLAB_HWCACHE_ALIGN | SLAB_PANIC); diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c index 560da0dab230..c1c3dc1c6023 100644 --- a/kernel/pid_namespace.c +++ b/kernel/pid_namespace.c @@ -115,6 +115,7 @@ static struct pid_namespace *create_pid_namespace(struct user_namespace *user_ns ns->level = level; ns->parent = get_pid_ns(parent_pid_ns); ns->user_ns = get_user_ns(user_ns); + ns->nr_hashed = PIDNS_HASH_ADDING; INIT_WORK(&ns->proc_work, proc_cleanup_work); set_bit(0, ns->pidmap[0].page); @@ -181,6 +182,9 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns) int rc; struct task_struct *task, *me = current; + /* Don't allow any more processes into the pid namespace */ + disable_pid_allocation(pid_ns); + /* Ignore SIGCHLD causing any terminated children to autoreap */ spin_lock_irq(&me->sighand->siglock); me->sighand->action[SIGCHLD - 1].sa.sa_handler = SIG_IGN; @@ -325,7 +329,8 @@ static int pidns_install(struct nsproxy *nsproxy, void *ns) struct pid_namespace *active = task_active_pid_ns(current); struct pid_namespace *ancestor, *new = ns; - if (!ns_capable(new->user_ns, CAP_SYS_ADMIN)) + if (!ns_capable(new->user_ns, CAP_SYS_ADMIN) || + !nsown_capable(CAP_SYS_ADMIN)) return -EPERM; /* diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c index d73840271dce..a278cad1d5d6 100644 --- a/kernel/posix-cpu-timers.c +++ b/kernel/posix-cpu-timers.c @@ -9,6 +9,7 @@ #include <asm/uaccess.h> #include <linux/kernel_stat.h> #include <trace/events/timer.h> +#include <linux/random.h> /* * Called after updating RLIMIT_CPU to run cpu timer and update @@ -470,6 +471,8 @@ static void cleanup_timers(struct list_head *head, */ void posix_cpu_timers_exit(struct task_struct *tsk) { + add_device_randomness((const void*) &tsk->se.sum_exec_runtime, + sizeof(unsigned long long)); cleanup_timers(tsk->cpu_timers, tsk->utime, tsk->stime, tsk->se.sum_exec_runtime); diff --git a/kernel/printk.c b/kernel/printk.c index 19c0d7bcf24a..357f714ddd49 100644 --- a/kernel/printk.c +++ b/kernel/printk.c @@ -870,10 +870,11 @@ static size_t print_time(u64 ts, char *buf) if (!printk_time) return 0; + rem_nsec = do_div(ts, 1000000000); + if (!buf) - return 15; + return snprintf(NULL, 0, "[%5lu.000000] ", (unsigned long)ts); - rem_nsec = do_div(ts, 1000000000); return sprintf(buf, "[%5lu.%06lu] ", (unsigned long)ts, rem_nsec / 1000); } diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 1599157336a6..6cbeaae4406d 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -117,11 +117,45 @@ void __ptrace_unlink(struct task_struct *child) * TASK_KILLABLE sleeps. */ if (child->jobctl & JOBCTL_STOP_PENDING || task_is_traced(child)) - signal_wake_up(child, task_is_traced(child)); + ptrace_signal_wake_up(child, true); spin_unlock(&child->sighand->siglock); } +/* Ensure that nothing can wake it up, even SIGKILL */ +static bool ptrace_freeze_traced(struct task_struct *task) +{ + bool ret = false; + + /* Lockless, nobody but us can set this flag */ + if (task->jobctl & JOBCTL_LISTENING) + return ret; + + spin_lock_irq(&task->sighand->siglock); + if (task_is_traced(task) && !__fatal_signal_pending(task)) { + task->state = __TASK_TRACED; + ret = true; + } + spin_unlock_irq(&task->sighand->siglock); + + return ret; +} + +static void ptrace_unfreeze_traced(struct task_struct *task) +{ + if (task->state != __TASK_TRACED) + return; + + WARN_ON(!task->ptrace || task->parent != current); + + spin_lock_irq(&task->sighand->siglock); + if (__fatal_signal_pending(task)) + wake_up_state(task, __TASK_TRACED); + else + task->state = TASK_TRACED; + spin_unlock_irq(&task->sighand->siglock); +} + /** * ptrace_check_attach - check whether ptracee is ready for ptrace operation * @child: ptracee to check for @@ -139,7 +173,7 @@ void __ptrace_unlink(struct task_struct *child) * RETURNS: * 0 on success, -ESRCH if %child is not ready. */ -int ptrace_check_attach(struct task_struct *child, bool ignore_state) +static int ptrace_check_attach(struct task_struct *child, bool ignore_state) { int ret = -ESRCH; @@ -151,24 +185,29 @@ int ptrace_check_attach(struct task_struct *child, bool ignore_state) * be changed by us so it's not changing right after this. */ read_lock(&tasklist_lock); - if ((child->ptrace & PT_PTRACED) && child->parent == current) { + if (child->ptrace && child->parent == current) { + WARN_ON(child->state == __TASK_TRACED); /* * child->sighand can't be NULL, release_task() * does ptrace_unlink() before __exit_signal(). */ - spin_lock_irq(&child->sighand->siglock); - WARN_ON_ONCE(task_is_stopped(child)); - if (ignore_state || (task_is_traced(child) && - !(child->jobctl & JOBCTL_LISTENING))) + if (ignore_state || ptrace_freeze_traced(child)) ret = 0; - spin_unlock_irq(&child->sighand->siglock); } read_unlock(&tasklist_lock); - if (!ret && !ignore_state) - ret = wait_task_inactive(child, TASK_TRACED) ? 0 : -ESRCH; + if (!ret && !ignore_state) { + if (!wait_task_inactive(child, __TASK_TRACED)) { + /* + * This can only happen if may_ptrace_stop() fails and + * ptrace_stop() changes ->state back to TASK_RUNNING, + * so we should not worry about leaking __TASK_TRACED. + */ + WARN_ON(child->state == __TASK_TRACED); + ret = -ESRCH; + } + } - /* All systems go.. */ return ret; } @@ -317,7 +356,7 @@ static int ptrace_attach(struct task_struct *task, long request, */ if (task_is_stopped(task) && task_set_jobctl_pending(task, JOBCTL_TRAP_STOP | JOBCTL_TRAPPING)) - signal_wake_up(task, 1); + signal_wake_up_state(task, __TASK_STOPPED); spin_unlock(&task->sighand->siglock); @@ -737,7 +776,7 @@ int ptrace_request(struct task_struct *child, long request, * tracee into STOP. */ if (likely(task_set_jobctl_pending(child, JOBCTL_TRAP_STOP))) - signal_wake_up(child, child->jobctl & JOBCTL_LISTENING); + ptrace_signal_wake_up(child, child->jobctl & JOBCTL_LISTENING); unlock_task_sighand(child, &flags); ret = 0; @@ -763,7 +802,7 @@ int ptrace_request(struct task_struct *child, long request, * start of this trap and now. Trigger re-trap. */ if (child->jobctl & JOBCTL_TRAP_NOTIFY) - signal_wake_up(child, true); + ptrace_signal_wake_up(child, true); ret = 0; } unlock_task_sighand(child, &flags); @@ -900,6 +939,8 @@ SYSCALL_DEFINE4(ptrace, long, request, long, pid, unsigned long, addr, goto out_put_task_struct; ret = arch_ptrace(child, request, addr, data); + if (ret || request != PTRACE_DETACH) + ptrace_unfreeze_traced(child); out_put_task_struct: put_task_struct(child); @@ -1039,8 +1080,11 @@ asmlinkage long compat_sys_ptrace(compat_long_t request, compat_long_t pid, ret = ptrace_check_attach(child, request == PTRACE_KILL || request == PTRACE_INTERRUPT); - if (!ret) + if (!ret) { ret = compat_arch_ptrace(child, request, addr, data); + if (ret || request != PTRACE_DETACH) + ptrace_unfreeze_traced(child); + } out_put_task_struct: put_task_struct(child); diff --git a/kernel/res_counter.c b/kernel/res_counter.c index 3920d593e63c..ff55247e7049 100644 --- a/kernel/res_counter.c +++ b/kernel/res_counter.c @@ -86,33 +86,39 @@ int res_counter_charge_nofail(struct res_counter *counter, unsigned long val, return __res_counter_charge(counter, val, limit_fail_at, true); } -void res_counter_uncharge_locked(struct res_counter *counter, unsigned long val) +u64 res_counter_uncharge_locked(struct res_counter *counter, unsigned long val) { if (WARN_ON(counter->usage < val)) val = counter->usage; counter->usage -= val; + return counter->usage; } -void res_counter_uncharge_until(struct res_counter *counter, - struct res_counter *top, - unsigned long val) +u64 res_counter_uncharge_until(struct res_counter *counter, + struct res_counter *top, + unsigned long val) { unsigned long flags; struct res_counter *c; + u64 ret = 0; local_irq_save(flags); for (c = counter; c != top; c = c->parent) { + u64 r; spin_lock(&c->lock); - res_counter_uncharge_locked(c, val); + r = res_counter_uncharge_locked(c, val); + if (c == counter) + ret = r; spin_unlock(&c->lock); } local_irq_restore(flags); + return ret; } -void res_counter_uncharge(struct res_counter *counter, unsigned long val) +u64 res_counter_uncharge(struct res_counter *counter, unsigned long val) { - res_counter_uncharge_until(counter, NULL, val); + return res_counter_uncharge_until(counter, NULL, val); } static inline unsigned long long * diff --git a/kernel/rwsem.c b/kernel/rwsem.c index 6850f53e02d8..b3c6c3fcd847 100644 --- a/kernel/rwsem.c +++ b/kernel/rwsem.c @@ -116,6 +116,16 @@ void down_read_nested(struct rw_semaphore *sem, int subclass) EXPORT_SYMBOL(down_read_nested); +void _down_write_nest_lock(struct rw_semaphore *sem, struct lockdep_map *nest) +{ + might_sleep(); + rwsem_acquire_nest(&sem->dep_map, 0, 0, nest, _RET_IP_); + + LOCK_CONTENDED(sem, __down_write_trylock, __down_write); +} + +EXPORT_SYMBOL(_down_write_nest_lock); + void down_write_nested(struct rw_semaphore *sem, int subclass) { might_sleep(); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index c6737f4fb63b..bfe8ae22f710 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1523,7 +1523,8 @@ out: */ int wake_up_process(struct task_struct *p) { - return try_to_wake_up(p, TASK_ALL, 0); + WARN_ON(task_is_stopped_or_traced(p)); + return try_to_wake_up(p, TASK_NORMAL, 0); } EXPORT_SYMBOL(wake_up_process); diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 4603d6cb9e25..5eea8707234a 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -793,8 +793,11 @@ unsigned int sysctl_numa_balancing_scan_delay = 1000; static void task_numa_placement(struct task_struct *p) { - int seq = ACCESS_ONCE(p->mm->numa_scan_seq); + int seq; + if (!p->mm) /* for example, ksmd faulting in a user's mm */ + return; + seq = ACCESS_ONCE(p->mm->numa_scan_seq); if (p->numa_scan_seq == seq) return; p->numa_scan_seq = seq; diff --git a/kernel/signal.c b/kernel/signal.c index 580a91e63471..3d09cf6cde75 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -31,6 +31,7 @@ #include <linux/nsproxy.h> #include <linux/user_namespace.h> #include <linux/uprobes.h> +#include <linux/compat.h> #define CREATE_TRACE_POINTS #include <trace/events/signal.h> @@ -679,23 +680,17 @@ int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info) * No need to set need_resched since signal event passing * goes through ->blocked */ -void signal_wake_up(struct task_struct *t, int resume) +void signal_wake_up_state(struct task_struct *t, unsigned int state) { - unsigned int mask; - set_tsk_thread_flag(t, TIF_SIGPENDING); - /* - * For SIGKILL, we want to wake it up in the stopped/traced/killable + * TASK_WAKEKILL also means wake it up in the stopped/traced/killable * case. We don't check t->state here because there is a race with it * executing another processor and just now entering stopped state. * By using wake_up_state, we ensure the process will wake up and * handle its death signal. */ - mask = TASK_INTERRUPTIBLE; - if (resume) - mask |= TASK_WAKEKILL; - if (!wake_up_state(t, mask)) + if (!wake_up_state(t, state | TASK_INTERRUPTIBLE)) kick_process(t); } @@ -843,7 +838,7 @@ static void ptrace_trap_notify(struct task_struct *t) assert_spin_locked(&t->sighand->siglock); task_set_jobctl_pending(t, JOBCTL_TRAP_NOTIFY); - signal_wake_up(t, t->jobctl & JOBCTL_LISTENING); + ptrace_signal_wake_up(t, t->jobctl & JOBCTL_LISTENING); } /* @@ -1799,6 +1794,10 @@ static inline int may_ptrace_stop(void) * If SIGKILL was already sent before the caller unlocked * ->siglock we must see ->core_state != NULL. Otherwise it * is safe to enter schedule(). + * + * This is almost outdated, a task with the pending SIGKILL can't + * block in TASK_TRACED. But PTRACE_EVENT_EXIT can be reported + * after SIGKILL was already dequeued. */ if (unlikely(current->mm->core_state) && unlikely(current->mm == current->parent->mm)) @@ -1924,6 +1923,7 @@ static void ptrace_stop(int exit_code, int why, int clear_code, siginfo_t *info) if (gstop_done) do_notify_parent_cldstop(current, false, why); + /* tasklist protects us from ptrace_freeze_traced() */ __set_current_state(TASK_RUNNING); if (clear_code) current->exit_code = 0; @@ -2527,11 +2527,8 @@ static void __set_task_blocked(struct task_struct *tsk, const sigset_t *newset) */ void set_current_blocked(sigset_t *newset) { - struct task_struct *tsk = current; sigdelsetmask(newset, sigmask(SIGKILL) | sigmask(SIGSTOP)); - spin_lock_irq(&tsk->sighand->siglock); - __set_task_blocked(tsk, newset); - spin_unlock_irq(&tsk->sighand->siglock); + __set_current_blocked(newset); } void __set_current_blocked(const sigset_t *newset) @@ -3094,6 +3091,80 @@ do_sigaltstack (const stack_t __user *uss, stack_t __user *uoss, unsigned long s out: return error; } +#ifdef CONFIG_GENERIC_SIGALTSTACK +SYSCALL_DEFINE2(sigaltstack,const stack_t __user *,uss, stack_t __user *,uoss) +{ + return do_sigaltstack(uss, uoss, current_user_stack_pointer()); +} +#endif + +int restore_altstack(const stack_t __user *uss) +{ + int err = do_sigaltstack(uss, NULL, current_user_stack_pointer()); + /* squash all but EFAULT for now */ + return err == -EFAULT ? err : 0; +} + +int __save_altstack(stack_t __user *uss, unsigned long sp) +{ + struct task_struct *t = current; + return __put_user((void __user *)t->sas_ss_sp, &uss->ss_sp) | + __put_user(sas_ss_flags(sp), &uss->ss_flags) | + __put_user(t->sas_ss_size, &uss->ss_size); +} + +#ifdef CONFIG_COMPAT +#ifdef CONFIG_GENERIC_SIGALTSTACK +COMPAT_SYSCALL_DEFINE2(sigaltstack, + const compat_stack_t __user *, uss_ptr, + compat_stack_t __user *, uoss_ptr) +{ + stack_t uss, uoss; + int ret; + mm_segment_t seg; + + if (uss_ptr) { + compat_stack_t uss32; + + memset(&uss, 0, sizeof(stack_t)); + if (copy_from_user(&uss32, uss_ptr, sizeof(compat_stack_t))) + return -EFAULT; + uss.ss_sp = compat_ptr(uss32.ss_sp); + uss.ss_flags = uss32.ss_flags; + uss.ss_size = uss32.ss_size; + } + seg = get_fs(); + set_fs(KERNEL_DS); + ret = do_sigaltstack((stack_t __force __user *) (uss_ptr ? &uss : NULL), + (stack_t __force __user *) &uoss, + compat_user_stack_pointer()); + set_fs(seg); + if (ret >= 0 && uoss_ptr) { + if (!access_ok(VERIFY_WRITE, uoss_ptr, sizeof(compat_stack_t)) || + __put_user(ptr_to_compat(uoss.ss_sp), &uoss_ptr->ss_sp) || + __put_user(uoss.ss_flags, &uoss_ptr->ss_flags) || + __put_user(uoss.ss_size, &uoss_ptr->ss_size)) + ret = -EFAULT; + } + return ret; +} + +int compat_restore_altstack(const compat_stack_t __user *uss) +{ + int err = compat_sys_sigaltstack(uss, NULL); + /* squash all but -EFAULT for now */ + return err == -EFAULT ? err : 0; +} + +int __compat_save_altstack(compat_stack_t __user *uss, unsigned long sp) +{ + struct task_struct *t = current; + return __put_user(ptr_to_compat((void __user *)t->sas_ss_sp), &uss->ss_sp) | + __put_user(sas_ss_flags(sp), &uss->ss_flags) | + __put_user(t->sas_ss_size, &uss->ss_size); +} +#endif +#endif #ifdef __ARCH_WANT_SYS_SIGPENDING @@ -3130,7 +3201,6 @@ SYSCALL_DEFINE3(sigprocmask, int, how, old_sigset_t __user *, nset, if (nset) { if (copy_from_user(&new_set, nset, sizeof(*nset))) return -EFAULT; - new_set &= ~(sigmask(SIGKILL) | sigmask(SIGSTOP)); new_blocked = current->blocked; @@ -3148,7 +3218,7 @@ SYSCALL_DEFINE3(sigprocmask, int, how, old_sigset_t __user *, nset, return -EINVAL; } - __set_current_blocked(&new_blocked); + set_current_blocked(&new_blocked); } if (oset) { @@ -3212,6 +3282,7 @@ SYSCALL_DEFINE1(ssetmask, int, newmask) int old = current->blocked.sig[0]; sigset_t newset; + siginitset(&newset, newmask); set_current_blocked(&newset); return old; diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index dbff751e4086..395084d4ce16 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -25,6 +25,7 @@ cond_syscall(sys_swapoff); cond_syscall(sys_kexec_load); cond_syscall(compat_sys_kexec_load); cond_syscall(sys_init_module); +cond_syscall(sys_finit_module); cond_syscall(sys_delete_module); cond_syscall(sys_socketpair); cond_syscall(sys_bind); diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 3ffe4c5ad3f3..41473b4ad7a4 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -3998,7 +3998,7 @@ static int ftrace_module_notify(struct notifier_block *self, struct notifier_block ftrace_module_nb = { .notifier_call = ftrace_module_notify, - .priority = 0, + .priority = INT_MAX, /* Run before anything that can use kprobes */ }; extern unsigned long __start_mcount_loc[]; diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 61e081b4ba11..3c13e46d7d24 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -2899,6 +2899,8 @@ tracing_trace_options_write(struct file *filp, const char __user *ubuf, if (copy_from_user(&buf, ubuf, cnt)) return -EFAULT; + buf[cnt] = 0; + trace_set_options(buf); *ppos += cnt; @@ -3034,6 +3036,31 @@ static void set_buffer_entries(struct trace_array *tr, unsigned long val) tr->data[cpu]->entries = val; } +/* resize @tr's buffer to the size of @size_tr's entries */ +static int resize_buffer_duplicate_size(struct trace_array *tr, + struct trace_array *size_tr, int cpu_id) +{ + int cpu, ret = 0; + + if (cpu_id == RING_BUFFER_ALL_CPUS) { + for_each_tracing_cpu(cpu) { + ret = ring_buffer_resize(tr->buffer, + size_tr->data[cpu]->entries, cpu); + if (ret < 0) + break; + tr->data[cpu]->entries = size_tr->data[cpu]->entries; + } + } else { + ret = ring_buffer_resize(tr->buffer, + size_tr->data[cpu_id]->entries, cpu_id); + if (ret == 0) + tr->data[cpu_id]->entries = + size_tr->data[cpu_id]->entries; + } + + return ret; +} + static int __tracing_resize_ring_buffer(unsigned long size, int cpu) { int ret; @@ -3058,23 +3085,8 @@ static int __tracing_resize_ring_buffer(unsigned long size, int cpu) ret = ring_buffer_resize(max_tr.buffer, size, cpu); if (ret < 0) { - int r = 0; - - if (cpu == RING_BUFFER_ALL_CPUS) { - int i; - for_each_tracing_cpu(i) { - r = ring_buffer_resize(global_trace.buffer, - global_trace.data[i]->entries, - i); - if (r < 0) - break; - } - } else { - r = ring_buffer_resize(global_trace.buffer, - global_trace.data[cpu]->entries, - cpu); - } - + int r = resize_buffer_duplicate_size(&global_trace, + &global_trace, cpu); if (r < 0) { /* * AARGH! We are left with different @@ -3212,17 +3224,11 @@ static int tracing_set_tracer(const char *buf) topts = create_trace_option_files(t); if (t->use_max_tr) { - int cpu; /* we need to make per cpu buffer sizes equivalent */ - for_each_tracing_cpu(cpu) { - ret = ring_buffer_resize(max_tr.buffer, - global_trace.data[cpu]->entries, - cpu); - if (ret < 0) - goto out; - max_tr.data[cpu]->entries = - global_trace.data[cpu]->entries; - } + ret = resize_buffer_duplicate_size(&max_tr, &global_trace, + RING_BUFFER_ALL_CPUS); + if (ret < 0) + goto out; } if (t->init) { @@ -3448,7 +3454,7 @@ static int tracing_wait_pipe(struct file *filp) return -EINTR; /* - * We block until we read something and tracing is enabled. + * We block until we read something and tracing is disabled. * We still block if tracing is disabled, but we have never * read anything. This allows a user to cat this file, and * then enable tracing. But after we have read something, @@ -3456,7 +3462,7 @@ static int tracing_wait_pipe(struct file *filp) * * iter->pos will be 0 if we haven't read anything. */ - if (tracing_is_enabled() && iter->pos) + if (!tracing_is_enabled() && iter->pos) break; } @@ -4271,13 +4277,11 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, return -ENOMEM; if (*ppos & (PAGE_SIZE - 1)) { - WARN_ONCE(1, "Ftrace: previous read must page-align\n"); ret = -EINVAL; goto out; } if (len & (PAGE_SIZE - 1)) { - WARN_ONCE(1, "Ftrace: splice_read should page-align\n"); if (len < PAGE_SIZE) { ret = -EINVAL; goto out; @@ -4813,10 +4817,17 @@ rb_simple_write(struct file *filp, const char __user *ubuf, return ret; if (buffer) { - if (val) + mutex_lock(&trace_types_lock); + if (val) { ring_buffer_record_on(buffer); - else + if (current_trace->start) + current_trace->start(tr); + } else { ring_buffer_record_off(buffer); + if (current_trace->stop) + current_trace->stop(tr); + } + mutex_unlock(&trace_types_lock); } (*ppos)++; diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c index 0c1b165778e5..42ca822fc701 100644 --- a/kernel/trace/trace_stack.c +++ b/kernel/trace/trace_stack.c @@ -33,7 +33,6 @@ static unsigned long max_stack_size; static arch_spinlock_t max_stack_lock = (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED; -static int stack_trace_disabled __read_mostly; static DEFINE_PER_CPU(int, trace_active); static DEFINE_MUTEX(stack_sysctl_mutex); @@ -116,9 +115,6 @@ stack_trace_call(unsigned long ip, unsigned long parent_ip, { int cpu; - if (unlikely(!ftrace_enabled || stack_trace_disabled)) - return; - preempt_disable_notrace(); cpu = raw_smp_processor_id(); diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c index f5975ccf9348..2b042c42fbc4 100644 --- a/kernel/user_namespace.c +++ b/kernel/user_namespace.c @@ -799,7 +799,7 @@ static int userns_install(struct nsproxy *nsproxy, void *ns) if (user_ns == current_user_ns()) return -EINVAL; - /* Threaded many not enter a different user namespace */ + /* Threaded processes may not enter a different user namespace */ if (atomic_read(¤t->mm->mm_users) > 1) return -EINVAL; diff --git a/kernel/utsname.c b/kernel/utsname.c index f6336d51d64c..08b197e8c485 100644 --- a/kernel/utsname.c +++ b/kernel/utsname.c @@ -113,7 +113,8 @@ static int utsns_install(struct nsproxy *nsproxy, void *new) { struct uts_namespace *ns = new; - if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN)) + if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN) || + !nsown_capable(CAP_SYS_ADMIN)) return -EPERM; get_uts_ns(ns); diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 997c6a16ec22..75a2ab3d0b02 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -344,6 +344,10 @@ static void watchdog_enable(unsigned int cpu) { struct hrtimer *hrtimer = &__raw_get_cpu_var(watchdog_hrtimer); + /* kick off the timer for the hardlockup detector */ + hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + hrtimer->function = watchdog_timer_fn; + if (!watchdog_enabled) { kthread_park(current); return; @@ -352,10 +356,6 @@ static void watchdog_enable(unsigned int cpu) /* Enable the perf event */ watchdog_nmi_enable(cpu); - /* kick off the timer for the hardlockup detector */ - hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); - hrtimer->function = watchdog_timer_fn; - /* done here because hrtimer_start can only pin to smp_processor_id() */ hrtimer_start(hrtimer, ns_to_ktime(sample_period), HRTIMER_MODE_REL_PINNED); @@ -369,9 +369,6 @@ static void watchdog_disable(unsigned int cpu) { struct hrtimer *hrtimer = &__raw_get_cpu_var(watchdog_hrtimer); - if (!watchdog_enabled) - return; - watchdog_set_prio(SCHED_NORMAL, 0); hrtimer_cancel(hrtimer); /* disable the perf event */ |