20 files changed, 300 insertions, 291 deletions

diff --git a/kernel/Makefile b/kernel/Makefile
index 1408b3353a3c..0f8f8b0bc1bf 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -9,7 +9,9 @@ obj-y     = fork.o exec_domain.o panic.o \
 	    extable.o params.o \
 	    kthread.o sys_ni.o nsproxy.o \
 	    notifier.o ksysfs.o cred.o reboot.o \
-	    async.o range.o groups.o smpboot.o
+	    async.o range.o smpboot.o
+
+obj-$(CONFIG_MULTIUSER) += groups.o
 
 ifdef CONFIG_FUNCTION_TRACER
 # Do not trace debug files and internal ftrace files
diff --git a/kernel/acct.c b/kernel/acct.c
index e6c10d1a4058..74963d192c5d 100644
--- a/kernel/acct.c
+++ b/kernel/acct.c
@@ -213,7 +213,7 @@ static int acct_on(struct filename *pathname)
 		return -EACCES;
 	}
 
-	if (!file->f_op->write) {
+	if (!(file->f_mode & FMODE_CAN_WRITE)) {
 		kfree(acct);
 		filp_close(file, NULL);
 		return -EIO;
diff --git a/kernel/capability.c b/kernel/capability.c
index 989f5bfc57dc..45432b54d5c6 100644
--- a/kernel/capability.c
+++ b/kernel/capability.c
@@ -35,6 +35,7 @@ static int __init file_caps_disable(char *str)
 }
 __setup("no_file_caps", file_caps_disable);
 
+#ifdef CONFIG_MULTIUSER
 /*
  * More recent versions of libcap are available from:
  *
@@ -386,6 +387,24 @@ bool ns_capable(struct user_namespace *ns, int cap)
 }
 EXPORT_SYMBOL(ns_capable);
 
+
+/**
+ * capable - Determine if the current task has a superior capability in effect
+ * @cap: The capability to be tested for
+ *
+ * Return true if the current task has the given superior capability currently
+ * available for use, false if not.
+ *
+ * This sets PF_SUPERPRIV on the task if the capability is available on the
+ * assumption that it's about to be used.
+ */
+bool capable(int cap)
+{
+	return ns_capable(&init_user_ns, cap);
+}
+EXPORT_SYMBOL(capable);
+#endif /* CONFIG_MULTIUSER */
+
 /**
  * file_ns_capable - Determine if the file's opener had a capability in effect
  * @file:  The file we want to check
@@ -412,22 +431,6 @@ bool file_ns_capable(const struct file *file, struct user_namespace *ns,
 EXPORT_SYMBOL(file_ns_capable);
 
 /**
- * capable - Determine if the current task has a superior capability in effect
- * @cap: The capability to be tested for
- *
- * Return true if the current task has the given superior capability currently
- * available for use, false if not.
- *
- * This sets PF_SUPERPRIV on the task if the capability is available on the
- * assumption that it's about to be used.
- */
-bool capable(int cap)
-{
-	return ns_capable(&init_user_ns, cap);
-}
-EXPORT_SYMBOL(capable);
-
-/**
  * capable_wrt_inode_uidgid - Check nsown_capable and uid and gid mapped
  * @inode: The inode in question
  * @cap: The capability in question
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index a220fdb66568..469dd547770c 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -4196,7 +4196,9 @@ static void *cgroup_pidlist_next(struct seq_file *s, void *v, loff_t *pos)
 
 static int cgroup_pidlist_show(struct seq_file *s, void *v)
 {
-	return seq_printf(s, "%d\n", *(int *)v);
+	seq_printf(s, "%d\n", *(int *)v);
+
+	return 0;
 }
 
 static u64 cgroup_read_notify_on_release(struct cgroup_subsys_state *css,
@@ -5451,7 +5453,7 @@ struct cgroup_subsys_state *css_tryget_online_from_dir(struct dentry *dentry,
 struct cgroup_subsys_state *css_from_id(int id, struct cgroup_subsys *ss)
 {
 	WARN_ON_ONCE(!rcu_read_lock_held());
-	return idr_find(&ss->css_idr, id);
+	return id > 0 ? idr_find(&ss->css_idr, id) : NULL;
 }
 
 #ifdef CONFIG_CGROUP_DEBUG
diff --git a/kernel/cred.c b/kernel/cred.c
index e0573a43c7df..ec1c07667ec1 100644
--- a/kernel/cred.c
+++ b/kernel/cred.c
@@ -29,6 +29,9 @@
 
 static struct kmem_cache *cred_jar;
 
+/* init to 2 - one for init_task, one to ensure it is never freed */
+struct group_info init_groups = { .usage = ATOMIC_INIT(2) };
+
 /*
  * The initial credentials for the initial task
  */
diff --git a/kernel/exec_domain.c b/kernel/exec_domain.c
index 83d4382f5699..6873bb3e6b7e 100644
--- a/kernel/exec_domain.c
+++ b/kernel/exec_domain.c
@@ -20,145 +20,10 @@
 #include <linux/types.h>
 #include <linux/fs_struct.h>
 
-
-static void default_handler(int, struct pt_regs *);
-
-static struct exec_domain *exec_domains = &default_exec_domain;
-static DEFINE_RWLOCK(exec_domains_lock);
-
-
-static unsigned long ident_map[32] = {
-	0,	1,	2,	3,	4,	5,	6,	7,
-	8,	9,	10,	11,	12,	13,	14,	15,
-	16,	17,	18,	19,	20,	21,	22,	23,
-	24,	25,	26,	27,	28,	29,	30,	31
-};
-
-struct exec_domain default_exec_domain = {
-	.name		= "Linux",		/* name */
-	.handler	= default_handler,	/* lcall7 causes a seg fault. */
-	.pers_low	= 0,			/* PER_LINUX personality. */
-	.pers_high	= 0,			/* PER_LINUX personality. */
-	.signal_map	= ident_map,		/* Identity map signals. */
-	.signal_invmap	= ident_map,		/*  - both ways. */
-};
-
-
-static void
-default_handler(int segment, struct pt_regs *regp)
-{
-	set_personality(0);
-
-	if (current_thread_info()->exec_domain->handler != default_handler)
-		current_thread_info()->exec_domain->handler(segment, regp);
-	else
-		send_sig(SIGSEGV, current, 1);
-}
-
-static struct exec_domain *
-lookup_exec_domain(unsigned int personality)
-{
-	unsigned int pers = personality(personality);
-	struct exec_domain *ep;
-
-	read_lock(&exec_domains_lock);
-	for (ep = exec_domains; ep; ep = ep->next) {
-		if (pers >= ep->pers_low && pers <= ep->pers_high)
-			if (try_module_get(ep->module))
-				goto out;
-	}
-
-#ifdef CONFIG_MODULES
-	read_unlock(&exec_domains_lock);
-	request_module("personality-%d", pers);
-	read_lock(&exec_domains_lock);
-
-	for (ep = exec_domains; ep; ep = ep->next) {
-		if (pers >= ep->pers_low && pers <= ep->pers_high)
-			if (try_module_get(ep->module))
-				goto out;
-	}
-#endif
-
-	ep = &default_exec_domain;
-out:
-	read_unlock(&exec_domains_lock);
-	return ep;
-}
-
-int
-register_exec_domain(struct exec_domain *ep)
-{
-	struct exec_domain	*tmp;
-	int			err = -EBUSY;
-
-	if (ep == NULL)
-		return -EINVAL;
-
-	if (ep->next != NULL)
-		return -EBUSY;
-
-	write_lock(&exec_domains_lock);
-	for (tmp = exec_domains; tmp; tmp = tmp->next) {
-		if (tmp == ep)
-			goto out;
-	}
-
-	ep->next = exec_domains;
-	exec_domains = ep;
-	err = 0;
-
-out:
-	write_unlock(&exec_domains_lock);
-	return err;
-}
-EXPORT_SYMBOL(register_exec_domain);
-
-int
-unregister_exec_domain(struct exec_domain *ep)
-{
-	struct exec_domain	**epp;
-
-	epp = &exec_domains;
-	write_lock(&exec_domains_lock);
-	for (epp = &exec_domains; *epp; epp = &(*epp)->next) {
-		if (ep == *epp)
-			goto unregister;
-	}
-	write_unlock(&exec_domains_lock);
-	return -EINVAL;
-
-unregister:
-	*epp = ep->next;
-	ep->next = NULL;
-	write_unlock(&exec_domains_lock);
-	return 0;
-}
-EXPORT_SYMBOL(unregister_exec_domain);
-
-int __set_personality(unsigned int personality)
-{
-	struct exec_domain *oep = current_thread_info()->exec_domain;
-
-	current_thread_info()->exec_domain = lookup_exec_domain(personality);
-	current->personality = personality;
-	module_put(oep->module);
-
-	return 0;
-}
-EXPORT_SYMBOL(__set_personality);
-
 #ifdef CONFIG_PROC_FS
 static int execdomains_proc_show(struct seq_file *m, void *v)
 {
-	struct exec_domain	*ep;
-
-	read_lock(&exec_domains_lock);
-	for (ep = exec_domains; ep; ep = ep->next)
-		seq_printf(m, "%d-%d\t%-16s\t[%s]\n",
-			       ep->pers_low, ep->pers_high, ep->name,
-			       module_name(ep->module));
-	read_unlock(&exec_domains_lock);
+	seq_puts(m, "0-0\tLinux           \t[kernel]\n");
 	return 0;
 }
 
diff --git a/kernel/exit.c b/kernel/exit.c
index feff10bbb307..22fcc05dec40 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -756,8 +756,6 @@ void do_exit(long code)
 
 	cgroup_exit(tsk);
 
-	module_put(task_thread_info(tsk)->exec_domain->module);
-
 	/*
 	 * FIXME: do that only when needed, using sched_exit tracepoint
 	 */
diff --git a/kernel/fork.c b/kernel/fork.c
index cf65139615a0..03c1eaaa6ef5 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -74,6 +74,7 @@
 #include <linux/uprobes.h>
 #include <linux/aio.h>
 #include <linux/compiler.h>
+#include <linux/sysctl.h>
 
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
@@ -88,6 +89,16 @@
 #include <trace/events/task.h>
 
 /*
+ * Minimum number of threads to boot the kernel
+ */
+#define MIN_THREADS 20
+
+/*
+ * Maximum number of threads
+ */
+#define MAX_THREADS FUTEX_TID_MASK
+
+/*
  * Protected counters by write_lock_irq(&tasklist_lock)
  */
 unsigned long total_forks;	/* Handle normal Linux uptimes. */
@@ -253,7 +264,30 @@ EXPORT_SYMBOL_GPL(__put_task_struct);
 
 void __init __weak arch_task_cache_init(void) { }
 
-void __init fork_init(unsigned long mempages)
+/*
+ * set_max_threads
+ */
+static void set_max_threads(unsigned int max_threads_suggested)
+{
+	u64 threads;
+
+	/*
+	 * The number of threads shall be limited such that the thread
+	 * structures may only consume a small part of the available memory.
+	 */
+	if (fls64(totalram_pages) + fls64(PAGE_SIZE) > 64)
+		threads = MAX_THREADS;
+	else
+		threads = div64_u64((u64) totalram_pages * (u64) PAGE_SIZE,
+				    (u64) THREAD_SIZE * 8UL);
+
+	if (threads > max_threads_suggested)
+		threads = max_threads_suggested;
+
+	max_threads = clamp_t(u64, threads, MIN_THREADS, MAX_THREADS);
+}
+
+void __init fork_init(void)
 {
 #ifndef CONFIG_ARCH_TASK_STRUCT_ALLOCATOR
 #ifndef ARCH_MIN_TASKALIGN
@@ -268,18 +302,7 @@ void __init fork_init(unsigned long mempages)
 	/* do the arch specific task caches init */
 	arch_task_cache_init();
 
-	/*
-	 * The default maximum number of threads is set to a safe
-	 * value: the thread structures can take up at most half
-	 * of memory.
-	 */
-	max_threads = mempages / (8 * THREAD_SIZE / PAGE_SIZE);
-
-	/*
-	 * we need to allow at least 20 threads to boot a system
-	 */
-	if (max_threads < 20)
-		max_threads = 20;
+	set_max_threads(MAX_THREADS);
 
 	init_task.signal->rlim[RLIMIT_NPROC].rlim_cur = max_threads/2;
 	init_task.signal->rlim[RLIMIT_NPROC].rlim_max = max_threads/2;
@@ -380,6 +403,9 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
 	 */
 	down_write_nested(&mm->mmap_sem, SINGLE_DEPTH_NESTING);
 
+	/* No ordering required: file already has been exposed. */
+	RCU_INIT_POINTER(mm->exe_file, get_mm_exe_file(oldmm));
+
 	mm->total_vm = oldmm->total_vm;
 	mm->shared_vm = oldmm->shared_vm;
 	mm->exec_vm = oldmm->exec_vm;
@@ -505,7 +531,13 @@ static inline void mm_free_pgd(struct mm_struct *mm)
 	pgd_free(mm, mm->pgd);
 }
 #else
-#define dup_mmap(mm, oldmm)	(0)
+static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
+{
+	down_write(&oldmm->mmap_sem);
+	RCU_INIT_POINTER(mm->exe_file, get_mm_exe_file(oldmm));
+	up_write(&oldmm->mmap_sem);
+	return 0;
+}
 #define mm_alloc_pgd(mm)	(0)
 #define mm_free_pgd(mm)
 #endif /* CONFIG_MMU */
@@ -674,34 +706,53 @@ void mmput(struct mm_struct *mm)
 }
 EXPORT_SYMBOL_GPL(mmput);
 
+/**
+ * set_mm_exe_file - change a reference to the mm's executable file
+ *
+ * This changes mm's executable file (shown as symlink /proc/[pid]/exe).
+ *
+ * Main users are mmput() and sys_execve(). Callers prevent concurrent
+ * invocations: in mmput() nobody alive left, in execve task is single
+ * threaded. sys_prctl(PR_SET_MM_MAP/EXE_FILE) also needs to set the
+ * mm->exe_file, but does so without using set_mm_exe_file() in order
+ * to do avoid the need for any locks.
+ */
 void set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file)
 {
+	struct file *old_exe_file;
+
+	/*
+	 * It is safe to dereference the exe_file without RCU as
+	 * this function is only called if nobody else can access
+	 * this mm -- see comment above for justification.
+	 */
+	old_exe_file = rcu_dereference_raw(mm->exe_file);
+
 	if (new_exe_file)
 		get_file(new_exe_file);
-	if (mm->exe_file)
-		fput(mm->exe_file);
-	mm->exe_file = new_exe_file;
+	rcu_assign_pointer(mm->exe_file, new_exe_file);
+	if (old_exe_file)
+		fput(old_exe_file);
 }
 
+/**
+ * get_mm_exe_file - acquire a reference to the mm's executable file
+ *
+ * Returns %NULL if mm has no associated executable file.
+ * User must release file via fput().
+ */
 struct file *get_mm_exe_file(struct mm_struct *mm)
 {
 	struct file *exe_file;
 
-	/* We need mmap_sem to protect against races with removal of exe_file */
-	down_read(&mm->mmap_sem);
-	exe_file = mm->exe_file;
-	if (exe_file)
-		get_file(exe_file);
-	up_read(&mm->mmap_sem);
+	rcu_read_lock();
+	exe_file = rcu_dereference(mm->exe_file);
+	if (exe_file && !get_file_rcu(exe_file))
+		exe_file = NULL;
+	rcu_read_unlock();
 	return exe_file;
 }
-
-static void dup_mm_exe_file(struct mm_struct *oldmm, struct mm_struct *newmm)
-{
-	/* It's safe to write the exe_file pointer without exe_file_lock because
-	 * this is called during fork when the task is not yet in /proc */
-	newmm->exe_file = get_mm_exe_file(oldmm);
-}
+EXPORT_SYMBOL(get_mm_exe_file);
 
 /**
  * get_task_mm - acquire a reference to the task's mm
@@ -864,8 +915,6 @@ static struct mm_struct *dup_mm(struct task_struct *tsk)
 	if (!mm_init(mm, tsk))
 		goto fail_nomem;
 
-	dup_mm_exe_file(oldmm, mm);
-
 	err = dup_mmap(mm, oldmm);
 	if (err)
 		goto free_pt;
@@ -1279,9 +1328,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	if (nr_threads >= max_threads)
 		goto bad_fork_cleanup_count;
 
-	if (!try_module_get(task_thread_info(p)->exec_domain->module))
-		goto bad_fork_cleanup_count;
-
 	delayacct_tsk_init(p);	/* Must remain after dup_task_struct() */
 	p->flags &= ~(PF_SUPERPRIV | PF_WQ_WORKER);
 	p->flags |= PF_FORKNOEXEC;
@@ -1406,10 +1452,11 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 		goto bad_fork_cleanup_io;
 
 	if (pid != &init_struct_pid) {
-		retval = -ENOMEM;
 		pid = alloc_pid(p->nsproxy->pid_ns_for_children);
-		if (!pid)
+		if (IS_ERR(pid)) {
+			retval = PTR_ERR(pid);
 			goto bad_fork_cleanup_io;
+		}
 	}
 
 	p->set_child_tid = (clone_flags & CLONE_CHILD_SETTID) ? child_tidptr : NULL;
@@ -1590,7 +1637,6 @@ bad_fork_cleanup_threadgroup_lock:
 	if (clone_flags & CLONE_THREAD)
 		threadgroup_change_end(current);
 	delayacct_tsk_free(p);
-	module_put(task_thread_info(p)->exec_domain->module);
 bad_fork_cleanup_count:
 	atomic_dec(&p->cred->user->processes);
 	exit_creds(p);
@@ -2004,3 +2050,26 @@ int unshare_files(struct files_struct **displaced)
 	task_unlock(task);
 	return 0;
 }
+
+int sysctl_max_threads(struct ctl_table *table, int write,
+		       void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+	struct ctl_table t;
+	int ret;
+	int threads = max_threads;
+	int min = MIN_THREADS;
+	int max = MAX_THREADS;
+
+	t = *table;
+	t.data = &threads;
+	t.extra1 = &min;
+	t.extra2 = &max;
+
+	ret = proc_dointvec_minmax(&t, write, buffer, lenp, ppos);
+	if (ret || !write)
+		return ret;
+
+	set_max_threads(threads);
+
+	return 0;
+}
diff --git a/kernel/gcov/base.c b/kernel/gcov/base.c
index b358a802fd18..a744098e4eb7 100644
--- a/kernel/gcov/base.c
+++ b/kernel/gcov/base.c
@@ -18,6 +18,7 @@
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
+#include <linux/sched.h>
 #include "gcov.h"
 
 static int gcov_events_enabled;
@@ -107,8 +108,10 @@ void gcov_enable_events(void)
 	gcov_events_enabled = 1;
 
 	/* Perform event callback for previously registered entries. */
-	while ((info = gcov_info_next(info)))
+	while ((info = gcov_info_next(info))) {
 		gcov_event(GCOV_ADD, info);
+		cond_resched();
+	}
 
 	mutex_unlock(&gcov_lock);
 }
diff --git a/kernel/groups.c b/kernel/groups.c
index 664411f171b5..74d431d25251 100644
--- a/kernel/groups.c
+++ b/kernel/groups.c
@@ -9,9 +9,6 @@
 #include <linux/user_namespace.h>
 #include <asm/uaccess.h>
 
-/* init to 2 - one for init_task, one to ensure it is never freed */
-struct group_info init_groups = { .usage = ATOMIC_INIT(2) };
-
 struct group_info *groups_alloc(int gidsetsize)
 {
 	struct group_info *group_info;
diff --git a/kernel/hung_task.c b/kernel/hung_task.c
index 06db12434d72..e0f90c2b57aa 100644
--- a/kernel/hung_task.c
+++ b/kernel/hung_task.c
@@ -169,7 +169,7 @@ static void check_hung_uninterruptible_tasks(unsigned long timeout)
 		return;
 
 	rcu_read_lock();
-	do_each_thread(g, t) {
+	for_each_process_thread(g, t) {
 		if (!max_count--)
 			goto unlock;
 		if (!--batch_count) {
@@ -180,7 +180,7 @@ static void check_hung_uninterruptible_tasks(unsigned long timeout)
 		/* use "==" to skip the TASK_KILLABLE tasks waiting on NFS */
 		if (t->state == TASK_UNINTERRUPTIBLE)
 			check_hung_task(t, timeout);
-	} while_each_thread(g, t);
+	}
  unlock:
 	rcu_read_unlock();
 }
diff --git a/kernel/pid.c b/kernel/pid.c
index cd36a5e0d173..4fd07d5b7baf 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -182,7 +182,7 @@ static int alloc_pidmap(struct pid_namespace *pid_ns)
 			spin_unlock_irq(&pidmap_lock);
 			kfree(page);
 			if (unlikely(!map->page))
-				break;
+				return -ENOMEM;
 		}
 		if (likely(atomic_read(&map->nr_free))) {
 			for ( ; ; ) {
@@ -210,7 +210,7 @@ static int alloc_pidmap(struct pid_namespace *pid_ns)
 		}
 		pid = mk_pid(pid_ns, map, offset);
 	}
-	return -1;
+	return -EAGAIN;
 }
 
 int next_pidmap(struct pid_namespace *pid_ns, unsigned int last)
@@ -301,17 +301,20 @@ struct pid *alloc_pid(struct pid_namespace *ns)
 	int i, nr;
 	struct pid_namespace *tmp;
 	struct upid *upid;
+	int retval = -ENOMEM;
 
 	pid = kmem_cache_alloc(ns->pid_cachep, GFP_KERNEL);
 	if (!pid)
-		goto out;
+		return ERR_PTR(retval);
 
 	tmp = ns;
 	pid->level = ns->level;
 	for (i = ns->level; i >= 0; i--) {
 		nr = alloc_pidmap(tmp);
-		if (nr < 0)
+		if (IS_ERR_VALUE(nr)) {
+			retval = nr;
 			goto out_free;
+		}
 
 		pid->numbers[i].nr = nr;
 		pid->numbers[i].ns = tmp;
@@ -339,7 +342,6 @@ struct pid *alloc_pid(struct pid_namespace *ns)
 	}
 	spin_unlock_irq(&pidmap_lock);
 
-out:
 	return pid;
 
 out_unlock:
@@ -351,8 +353,7 @@ out_free:
 		free_pidmap(pid->numbers + i);
 
 	kmem_cache_free(ns->pid_cachep, pid);
-	pid = NULL;
-	goto out;
+	return ERR_PTR(retval);
 }
 
 void disable_pid_allocation(struct pid_namespace *ns)
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 227fec36b12a..c8e0e050a36a 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -456,8 +456,6 @@ static bool __ptrace_detach(struct task_struct *tracer, struct task_struct *p)
 
 static int ptrace_detach(struct task_struct *child, unsigned int data)
 {
-	bool dead = false;
-
 	if (!valid_signal(data))
 		return -EIO;
 
@@ -467,18 +465,19 @@ static int ptrace_detach(struct task_struct *child, unsigned int data)
 
 	write_lock_irq(&tasklist_lock);
 	/*
-	 * This child can be already killed. Make sure de_thread() or
-	 * our sub-thread doing do_wait() didn't do release_task() yet.
+	 * We rely on ptrace_freeze_traced(). It can't be killed and
+	 * untraced by another thread, it can't be a zombie.
 	 */
-	if (child->ptrace) {
-		child->exit_code = data;
-		dead = __ptrace_detach(current, child);
-	}
+	WARN_ON(!child->ptrace || child->exit_state);
+	/*
+	 * tasklist_lock avoids the race with wait_task_stopped(), see
+	 * the comment in ptrace_resume().
+	 */
+	child->exit_code = data;
+	__ptrace_detach(current, child);
 	write_unlock_irq(&tasklist_lock);
 
 	proc_ptrace_connector(child, PTRACE_DETACH);
-	if (unlikely(dead))
-		release_task(child);
 
 	return 0;
 }
@@ -697,6 +696,8 @@ static int ptrace_peek_siginfo(struct task_struct *child,
 static int ptrace_resume(struct task_struct *child, long request,
 			 unsigned long data)
 {
+	bool need_siglock;
+
 	if (!valid_signal(data))
 		return -EIO;
 
@@ -724,8 +725,26 @@ static int ptrace_resume(struct task_struct *child, long request,
 		user_disable_single_step(child);
 	}
 
+	/*
+	 * Change ->exit_code and ->state under siglock to avoid the race
+	 * with wait_task_stopped() in between; a non-zero ->exit_code will
+	 * wrongly look like another report from tracee.
+	 *
+	 * Note that we need siglock even if ->exit_code == data and/or this
+	 * status was not reported yet, the new status must not be cleared by
+	 * wait_task_stopped() after resume.
+	 *
+	 * If data == 0 we do not care if wait_task_stopped() reports the old
+	 * status and clears the code too; this can't race with the tracee, it
+	 * takes siglock after resume.
+	 */
+	need_siglock = data && !thread_group_empty(current);
+	if (need_siglock)
+		spin_lock_irq(&child->sighand->siglock);
 	child->exit_code = data;
 	wake_up_state(child, __TASK_TRACED);
+	if (need_siglock)
+		spin_unlock_irq(&child->sighand->siglock);
 
 	return 0;
 }
diff --git a/kernel/reboot.c b/kernel/reboot.c
index 5925f5ae8dff..d20c85d9f8c0 100644
--- a/kernel/reboot.c
+++ b/kernel/reboot.c
@@ -387,8 +387,9 @@ void ctrl_alt_del(void)
 }
 
 char poweroff_cmd[POWEROFF_CMD_PATH_LEN] = "/sbin/poweroff";
+static const char reboot_cmd[] = "/sbin/reboot";
 
-static int __orderly_poweroff(bool force)
+static int run_cmd(const char *cmd)
 {
 	char **argv;
 	static char *envp[] = {
@@ -397,8 +398,7 @@ static int __orderly_poweroff(bool force)
 		NULL
 	};
 	int ret;
-
-	argv = argv_split(GFP_KERNEL, poweroff_cmd, NULL);
+	argv = argv_split(GFP_KERNEL, cmd, NULL);
 	if (argv) {
 		ret = call_usermodehelper(argv[0], argv, envp, UMH_WAIT_EXEC);
 		argv_free(argv);
@@ -406,8 +406,33 @@ static int __orderly_poweroff(bool force)
 		ret = -ENOMEM;
 	}
 
+	return ret;
+}
+
+static int __orderly_reboot(void)
+{
+	int ret;
+
+	ret = run_cmd(reboot_cmd);
+
+	if (ret) {
+		pr_warn("Failed to start orderly reboot: forcing the issue\n");
+		emergency_sync();
+		kernel_restart(NULL);
+	}
+
+	return ret;
+}
+
+static int __orderly_poweroff(bool force)
+{
+	int ret;
+
+	ret = run_cmd(poweroff_cmd);
+
 	if (ret && force) {
 		pr_warn("Failed to start orderly shutdown: forcing the issue\n");
+
 		/*
 		 * I guess this should try to kick off some daemon to sync and
 		 * poweroff asap.  Or not even bother syncing if we're doing an
@@ -436,15 +461,33 @@ static DECLARE_WORK(poweroff_work, poweroff_work_func);
  * This may be called from any context to trigger a system shutdown.
  * If the orderly shutdown fails, it will force an immediate shutdown.
  */
-int orderly_poweroff(bool force)
+void orderly_poweroff(bool force)
 {
 	if (force) /* do not override the pending "true" */
 		poweroff_force = true;
 	schedule_work(&poweroff_work);
-	return 0;
 }
 EXPORT_SYMBOL_GPL(orderly_poweroff);
 
+static void reboot_work_func(struct work_struct *work)
+{
+	__orderly_reboot();
+}
+
+static DECLARE_WORK(reboot_work, reboot_work_func);
+
+/**
+ * orderly_reboot - Trigger an orderly system reboot
+ *
+ * This may be called from any context to trigger a system reboot.
+ * If the orderly reboot fails, it will force an immediate reboot.
+ */
+void orderly_reboot(void)
+{
+	schedule_work(&reboot_work);
+}
+EXPORT_SYMBOL_GPL(orderly_reboot);
+
 static int __init reboot_setup(char *str)
 {
 	for (;;) {
diff --git a/kernel/resource.c b/kernel/resource.c
index 19f2357dfda3..90552aab5f2d 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -1034,8 +1034,6 @@ resource_size_t resource_alignment(struct resource *res)
  *
  * request_region creates a new busy region.
  *
- * check_region returns non-zero if the area is already busy.
- *
  * release_region releases a matching busy region.
  */
 
@@ -1098,36 +1096,6 @@ struct resource * __request_region(struct resource *parent,
 EXPORT_SYMBOL(__request_region);
 
 /**
- * __check_region - check if a resource region is busy or free
- * @parent: parent resource descriptor
- * @start: resource start address
- * @n: resource region size
- *
- * Returns 0 if the region is free at the moment it is checked,
- * returns %-EBUSY if the region is busy.
- *
- * NOTE:
- * This function is deprecated because its use is racy.
- * Even if it returns 0, a subsequent call to request_region()
- * may fail because another driver etc. just allocated the region.
- * Do NOT use it.  It will be removed from the kernel.
- */
-int __check_region(struct resource *parent, resource_size_t start,
-			resource_size_t n)
-{
-	struct resource * res;
-
-	res = __request_region(parent, start, n, "check-region", 0);
-	if (!res)
-		return -EBUSY;
-
-	release_resource(res);
-	free_resource(res);
-	return 0;
-}
-EXPORT_SYMBOL(__check_region);
-
-/**
  * __release_region - release a previously reserved resource region
  * @parent: parent resource descriptor
  * @start: resource start address
diff --git a/kernel/signal.c b/kernel/signal.c
index a390499943e4..d51c5ddd855c 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -2992,11 +2992,9 @@ static int do_rt_sigqueueinfo(pid_t pid, int sig, siginfo_t *info)
 	 * Nor can they impersonate a kill()/tgkill(), which adds source info.
 	 */
 	if ((info->si_code >= 0 || info->si_code == SI_TKILL) &&
-	    (task_pid_vnr(current) != pid)) {
-		/* We used to allow any < 0 si_code */
-		WARN_ON_ONCE(info->si_code < 0);
+	    (task_pid_vnr(current) != pid))
 		return -EPERM;
-	}
+
 	info->si_signo = sig;
 
 	/* POSIX.1b doesn't mention process groups.  */
@@ -3041,12 +3039,10 @@ static int do_rt_tgsigqueueinfo(pid_t tgid, pid_t pid, int sig, siginfo_t *info)
 	/* Not even root can pretend to send signals from the kernel.
 	 * Nor can they impersonate a kill()/tgkill(), which adds source info.
 	 */
-	if (((info->si_code >= 0 || info->si_code == SI_TKILL)) &&
-	    (task_pid_vnr(current) != pid)) {
-		/* We used to allow any < 0 si_code */
-		WARN_ON_ONCE(info->si_code < 0);
+	if ((info->si_code >= 0 || info->si_code == SI_TKILL) &&
+	    (task_pid_vnr(current) != pid))
 		return -EPERM;
-	}
+
 	info->si_signo = sig;
 
 	return do_send_specific(tgid, pid, sig, info);
diff --git a/kernel/sys.c b/kernel/sys.c
index a03d9cd23ed7..a4e372b798a5 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -325,6 +325,7 @@ out_unlock:
  * SMP: There are not races, the GIDs are checked only by filesystem
  *      operations (as far as semantic preservation is concerned).
  */
+#ifdef CONFIG_MULTIUSER
 SYSCALL_DEFINE2(setregid, gid_t, rgid, gid_t, egid)
 {
 	struct user_namespace *ns = current_user_ns();
@@ -815,6 +816,7 @@ change_okay:
 	commit_creds(new);
 	return old_fsgid;
 }
+#endif /* CONFIG_MULTIUSER */
 
 /**
  * sys_getpid - return the thread group id of the current process
@@ -1647,14 +1649,13 @@ SYSCALL_DEFINE1(umask, int, mask)
 	return mask;
 }
 
-static int prctl_set_mm_exe_file_locked(struct mm_struct *mm, unsigned int fd)
+static int prctl_set_mm_exe_file(struct mm_struct *mm, unsigned int fd)
 {
 	struct fd exe;
+	struct file *old_exe, *exe_file;
 	struct inode *inode;
 	int err;
 
-	VM_BUG_ON_MM(!rwsem_is_locked(&mm->mmap_sem), mm);
-
 	exe = fdget(fd);
 	if (!exe.file)
 		return -EBADF;
@@ -1678,15 +1679,22 @@ static int prctl_set_mm_exe_file_locked(struct mm_struct *mm, unsigned int fd)
 	/*
 	 * Forbid mm->exe_file change if old file still mapped.
 	 */
+	exe_file = get_mm_exe_file(mm);
 	err = -EBUSY;
-	if (mm->exe_file) {
+	if (exe_file) {
 		struct vm_area_struct *vma;
 
-		for (vma = mm->mmap; vma; vma = vma->vm_next)
-			if (vma->vm_file &&
-			    path_equal(&vma->vm_file->f_path,
-				       &mm->exe_file->f_path))
-				goto exit;
+		down_read(&mm->mmap_sem);
+		for (vma = mm->mmap; vma; vma = vma->vm_next) {
+			if (!vma->vm_file)
+				continue;
+			if (path_equal(&vma->vm_file->f_path,
+				       &exe_file->f_path))
+				goto exit_err;
+		}
+
+		up_read(&mm->mmap_sem);
+		fput(exe_file);
 	}
 
 	/*
@@ -1700,10 +1708,18 @@ static int prctl_set_mm_exe_file_locked(struct mm_struct *mm, unsigned int fd)
 		goto exit;
 
 	err = 0;
-	set_mm_exe_file(mm, exe.file);	/* this grabs a reference to exe.file */
+	/* set the new file, lockless */
+	get_file(exe.file);
+	old_exe = xchg(&mm->exe_file, exe.file);
+	if (old_exe)
+		fput(old_exe);
 exit:
 	fdput(exe);
 	return err;
+exit_err:
+	up_read(&mm->mmap_sem);
+	fput(exe_file);
+	goto exit;
 }
 
 #ifdef CONFIG_CHECKPOINT_RESTORE
@@ -1838,10 +1854,9 @@ static int prctl_set_mm_map(int opt, const void __user *addr, unsigned long data
 		user_auxv[AT_VECTOR_SIZE - 1] = AT_NULL;
 	}
 
-	down_write(&mm->mmap_sem);
 	if (prctl_map.exe_fd != (u32)-1)
-		error = prctl_set_mm_exe_file_locked(mm, prctl_map.exe_fd);
-	downgrade_write(&mm->mmap_sem);
+		error = prctl_set_mm_exe_file(mm, prctl_map.exe_fd);
+	down_read(&mm->mmap_sem);
 	if (error)
 		goto out;
 
@@ -1907,12 +1922,8 @@ static int prctl_set_mm(int opt, unsigned long addr,
 	if (!capable(CAP_SYS_RESOURCE))
 		return -EPERM;
 
-	if (opt == PR_SET_MM_EXE_FILE) {
-		down_write(&mm->mmap_sem);
-		error = prctl_set_mm_exe_file_locked(mm, (unsigned int)addr);
-		up_write(&mm->mmap_sem);
-		return error;
-	}
+	if (opt == PR_SET_MM_EXE_FILE)
+		return prctl_set_mm_exe_file(mm, (unsigned int)addr);
 
 	if (addr >= TASK_SIZE || addr < mmap_min_addr)
 		return -EINVAL;
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index 5adcb0ae3a58..7995ef5868d8 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -159,6 +159,20 @@ cond_syscall(sys_uselib);
 cond_syscall(sys_fadvise64);
 cond_syscall(sys_fadvise64_64);
 cond_syscall(sys_madvise);
+cond_syscall(sys_setuid);
+cond_syscall(sys_setregid);
+cond_syscall(sys_setgid);
+cond_syscall(sys_setreuid);
+cond_syscall(sys_setresuid);
+cond_syscall(sys_getresuid);
+cond_syscall(sys_setresgid);
+cond_syscall(sys_getresgid);
+cond_syscall(sys_setgroups);
+cond_syscall(sys_getgroups);
+cond_syscall(sys_setfsuid);
+cond_syscall(sys_setfsgid);
+cond_syscall(sys_capget);
+cond_syscall(sys_capset);
 
 /* arch-specific weak syscall entries */
 cond_syscall(sys_pciconfig_read);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 8c0eabd41886..2082b1a88fb9 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -93,11 +93,9 @@
 #include <linux/nmi.h>
 #endif
 
-
 #if defined(CONFIG_SYSCTL)
 
 /* External variables not in a header file. */
-extern int max_threads;
 extern int suid_dumpable;
 #ifdef CONFIG_COREDUMP
 extern int core_uses_pid;
@@ -710,10 +708,10 @@ static struct ctl_table kern_table[] = {
 #endif
 	{
 		.procname	= "threads-max",
-		.data		= &max_threads,
+		.data		= NULL,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
+		.proc_handler	= sysctl_max_threads,
 	},
 	{
 		.procname	= "random",
@@ -1335,6 +1333,15 @@ static struct ctl_table vm_table[] = {
 		.extra1		= &min_extfrag_threshold,
 		.extra2		= &max_extfrag_threshold,
 	},
+	{
+		.procname	= "compact_unevictable_allowed",
+		.data		= &sysctl_compact_unevictable_allowed,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+		.extra1		= &zero,
+		.extra2		= &one,
+	},
 
 #endif /* CONFIG_COMPACTION */
 	{
@@ -1974,7 +1981,15 @@ static int do_proc_dointvec_conv(bool *negp, unsigned long *lvalp,
 				 int write, void *data)
 {
 	if (write) {
-		*valp = *negp ? -*lvalp : *lvalp;
+		if (*negp) {
+			if (*lvalp > (unsigned long) INT_MAX + 1)
+				return -EINVAL;
+			*valp = -*lvalp;
+		} else {
+			if (*lvalp > (unsigned long) INT_MAX)
+				return -EINVAL;
+			*valp = *lvalp;
+		}
 	} else {
 		int val = *valp;
 		if (val < 0) {
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index c3e4fcfddd45..3f34496244e9 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -327,11 +327,11 @@ static void t_stop(struct seq_file *m, void *p)
 	local_irq_enable();
 }
 
-static int trace_lookup_stack(struct seq_file *m, long i)
+static void trace_lookup_stack(struct seq_file *m, long i)
 {
 	unsigned long addr = stack_dump_trace[i];
 
-	return seq_printf(m, "%pS\n", (void *)addr);
+	seq_printf(m, "%pS\n", (void *)addr);
 }
 
 static void print_disabled(struct seq_file *m)