Merge tag 'v3.8-rc5' into next/cleanup

Linux 3.8-rc5

Signed-off-by: Olof Johansson <olof@lixom.net>

16 files changed, 335 insertions, 126 deletions

diff --git a/kernel/async.c b/kernel/async.c
index 9d3118384858..6f34904a0b53 100644
--- a/kernel/async.c
+++ b/kernel/async.c
@@ -86,18 +86,27 @@ 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)
@@ -118,13 +127,17 @@ 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) */
@@ -196,6 +209,9 @@ 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 e81175ef25f8..642a89c4f3d6 100644
--- a/kernel/audit_tree.c
+++ b/kernel/audit_tree.c
@@ -449,11 +449,26 @@ static int tag_chunk(struct inode *inode, struct audit_tree *tree)
 	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 4a599f699adc..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));
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/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 65ca6d27f24e..c535f33bbb9c 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1668,8 +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/module.c b/kernel/module.c
index 250092c1d57d..eab08274ec9b 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -188,6 +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))
@@ -343,6 +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;
 	}
@@ -450,16 +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
@@ -525,6 +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) {
@@ -1048,6 +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);
 }
@@ -1786,6 +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,
@@ -1807,6 +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,
@@ -2527,6 +2547,13 @@ static int copy_module_from_fd(int fd, struct load_info *info)
 		err = -EFBIG;
 		goto out;
 	}
+
+	/* Don't hand 0 to vmalloc, it whines. */
+	if (stat.size == 0) {
+		err = -EINVAL;
+		goto out;
+	}
+
 	info->hdr = vmalloc(stat.size);
 	if (!info->hdr) {
 		err = -ENOMEM;
@@ -2990,8 +3017,9 @@ 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;
@@ -3013,6 +3041,12 @@ 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);
 
@@ -3058,8 +3092,25 @@ static int do_init_module(struct module *mod)
 	blocking_notifier_call_chain(&module_notify_list,
 				     MODULE_STATE_LIVE, mod);
 
-	/* We need to finish all async code before the module init sequence is done */
-	async_synchronize_full();
+	/*
+	 * 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. */
@@ -3113,6 +3164,32 @@ static int load_module(struct load_info *info, const char __user *uargs,
 		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;
 	if (!mod->sig_ok)
@@ -3122,7 +3199,7 @@ static int load_module(struct load_info *info, const char __user *uargs,
 	/* 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. */
@@ -3157,54 +3234,33 @@ static int load_module(struct load_info *info, const char __user *uargs,
 		goto free_arch_cleanup;
 	}
 
-	/* Mark state as coming so strong_try_module_get() ignores us. */
-	mod->state = MODULE_STATE_COMING;
-
-	/* 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 */
+	mutex_lock(&module_mutex);
+	/* 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);
-	list_add_rcu(&mod->list, &modules);
+
+	/* Mark state as coming so strong_try_module_get() ignores us,
+	 * but kallsyms etc. can see us. */
+	mod->state = MODULE_STATE_COMING;
+
 	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);
 	if (err < 0)
-		goto unlink;
+		goto bug_cleanup;
 
 	/* Get rid of temporary copy. */
 	free_copy(info);
@@ -3214,16 +3270,13 @@ again:
 
 	return do_init_module(mod);
 
- unlink:
+ 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:
@@ -3232,6 +3285,12 @@ 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);
  free_copy:
@@ -3354,6 +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)
@@ -3377,6 +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;
@@ -3401,6 +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;
@@ -3428,6 +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;
@@ -3470,9 +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;
@@ -3487,6 +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);
@@ -3502,6 +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) {
@@ -3543,6 +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);
@@ -3603,6 +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;
 
@@ -3651,10 +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);
@@ -3707,8 +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/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/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 257002c13bb0..26058d0bebba 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/signal.c b/kernel/signal.c
index 372771e948c2..3d09cf6cde75 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -680,23 +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);
 }
 
@@ -844,7 +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);
 }
 
 /*
@@ -1800,6 +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))
@@ -1925,6 +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;
@@ -3116,8 +3115,9 @@ int __save_altstack(stack_t __user *uss, unsigned long sp)
 
 #ifdef CONFIG_COMPAT
 #ifdef CONFIG_GENERIC_SIGALTSTACK
-asmlinkage long compat_sys_sigaltstack(const compat_stack_t __user *uss_ptr,
-				       compat_stack_t __user *uoss_ptr)
+COMPAT_SYSCALL_DEFINE2(sigaltstack,
+			const compat_stack_t __user *, uss_ptr,
+			compat_stack_t __user *, uoss_ptr)
 {
 	stack_t uss, uoss;
 	int ret;
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 e5125677efa0..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;
@@ -3452,7 +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,
@@ -3460,7 +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;
 	}
 
@@ -4815,10 +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)++;