Merge branch 'akpm-incoming-2'

* akpm-incoming-2: (139 commits)
  epoll: make epoll_wait() use the hrtimer range feature
  select: rename estimate_accuracy() to select_estimate_accuracy()
  Remove duplicate includes from many files
  ramoops: use the platform data structure instead of module params
  kernel/resource.c: handle reinsertion of an already-inserted resource
  kfifo: fix kfifo_alloc() to return a signed int value
  w1: don't allow arbitrary users to remove w1 devices
  alpha: remove dma64_addr_t usage
  mips: remove dma64_addr_t usage
  sparc: remove dma64_addr_t usage
  fuse: use release_pages()
  taskstats: use real microsecond granularity for CPU times
  taskstats: split fill_pid function
  taskstats: separate taskstats commands
  delayacct: align to 8 byte boundary on 64-bit systems
  delay-accounting: reimplement -c for getdelays.c to report information on a target command
  namespaces Kconfig: move namespace menu location after the cgroup
  namespaces Kconfig: remove the cgroup device whitelist experimental tag
  namespaces Kconfig: remove pointless cgroup dependency
  namespaces Kconfig: make namespace a submenu
  ...

13 files changed, 295 insertions, 163 deletions

diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 9270d532ec3..5cf366965d0 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -243,6 +243,11 @@ static int notify_on_release(const struct cgroup *cgrp)
 	return test_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags);
 }
 
+static int clone_children(const struct cgroup *cgrp)
+{
+	return test_bit(CGRP_CLONE_CHILDREN, &cgrp->flags);
+}
+
 /*
  * for_each_subsys() allows you to iterate on each subsystem attached to
  * an active hierarchy
@@ -1040,6 +1045,8 @@ static int cgroup_show_options(struct seq_file *seq, struct vfsmount *vfs)
 		seq_puts(seq, ",noprefix");
 	if (strlen(root->release_agent_path))
 		seq_printf(seq, ",release_agent=%s", root->release_agent_path);
+	if (clone_children(&root->top_cgroup))
+		seq_puts(seq, ",clone_children");
 	if (strlen(root->name))
 		seq_printf(seq, ",name=%s", root->name);
 	mutex_unlock(&cgroup_mutex);
@@ -1050,6 +1057,7 @@ struct cgroup_sb_opts {
 	unsigned long subsys_bits;
 	unsigned long flags;
 	char *release_agent;
+	bool clone_children;
 	char *name;
 	/* User explicitly requested empty subsystem */
 	bool none;
@@ -1066,7 +1074,8 @@ struct cgroup_sb_opts {
  */
 static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts)
 {
-	char *token, *o = data ?: "all";
+	char *token, *o = data;
+	bool all_ss = false, one_ss = false;
 	unsigned long mask = (unsigned long)-1;
 	int i;
 	bool module_pin_failed = false;
@@ -1082,22 +1091,27 @@ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts)
 	while ((token = strsep(&o, ",")) != NULL) {
 		if (!*token)
 			return -EINVAL;
-		if (!strcmp(token, "all")) {
-			/* Add all non-disabled subsystems */
-			opts->subsys_bits = 0;
-			for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
-				struct cgroup_subsys *ss = subsys[i];
-				if (ss == NULL)
-					continue;
-				if (!ss->disabled)
-					opts->subsys_bits |= 1ul << i;
-			}
-		} else if (!strcmp(token, "none")) {
+		if (!strcmp(token, "none")) {
 			/* Explicitly have no subsystems */
 			opts->none = true;
-		} else if (!strcmp(token, "noprefix")) {
+			continue;
+		}
+		if (!strcmp(token, "all")) {
+			/* Mutually exclusive option 'all' + subsystem name */
+			if (one_ss)
+				return -EINVAL;
+			all_ss = true;
+			continue;
+		}
+		if (!strcmp(token, "noprefix")) {
 			set_bit(ROOT_NOPREFIX, &opts->flags);
-		} else if (!strncmp(token, "release_agent=", 14)) {
+			continue;
+		}
+		if (!strcmp(token, "clone_children")) {
+			opts->clone_children = true;
+			continue;
+		}
+		if (!strncmp(token, "release_agent=", 14)) {
 			/* Specifying two release agents is forbidden */
 			if (opts->release_agent)
 				return -EINVAL;
@@ -1105,7 +1119,9 @@ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts)
 				kstrndup(token + 14, PATH_MAX - 1, GFP_KERNEL);
 			if (!opts->release_agent)
 				return -ENOMEM;
-		} else if (!strncmp(token, "name=", 5)) {
+			continue;
+		}
+		if (!strncmp(token, "name=", 5)) {
 			const char *name = token + 5;
 			/* Can't specify an empty name */
 			if (!strlen(name))
@@ -1127,20 +1143,44 @@ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts)
 					      GFP_KERNEL);
 			if (!opts->name)
 				return -ENOMEM;
-		} else {
-			struct cgroup_subsys *ss;
-			for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
-				ss = subsys[i];
-				if (ss == NULL)
-					continue;
-				if (!strcmp(token, ss->name)) {
-					if (!ss->disabled)
-						set_bit(i, &opts->subsys_bits);
-					break;
-				}
-			}
-			if (i == CGROUP_SUBSYS_COUNT)
-				return -ENOENT;
+
+			continue;
+		}
+
+		for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
+			struct cgroup_subsys *ss = subsys[i];
+			if (ss == NULL)
+				continue;
+			if (strcmp(token, ss->name))
+				continue;
+			if (ss->disabled)
+				continue;
+
+			/* Mutually exclusive option 'all' + subsystem name */
+			if (all_ss)
+				return -EINVAL;
+			set_bit(i, &opts->subsys_bits);
+			one_ss = true;
+
+			break;
+		}
+		if (i == CGROUP_SUBSYS_COUNT)
+			return -ENOENT;
+	}
+
+	/*
+	 * If the 'all' option was specified select all the subsystems,
+	 * otherwise 'all, 'none' and a subsystem name options were not
+	 * specified, let's default to 'all'
+	 */
+	if (all_ss || (!all_ss && !one_ss && !opts->none)) {
+		for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
+			struct cgroup_subsys *ss = subsys[i];
+			if (ss == NULL)
+				continue;
+			if (ss->disabled)
+				continue;
+			set_bit(i, &opts->subsys_bits);
 		}
 	}
 
@@ -1355,6 +1395,8 @@ static struct cgroupfs_root *cgroup_root_from_opts(struct cgroup_sb_opts *opts)
 		strcpy(root->release_agent_path, opts->release_agent);
 	if (opts->name)
 		strcpy(root->name, opts->name);
+	if (opts->clone_children)
+		set_bit(CGRP_CLONE_CHILDREN, &root->top_cgroup.flags);
 	return root;
 }
 
@@ -1880,6 +1922,8 @@ static int cgroup_release_agent_write(struct cgroup *cgrp, struct cftype *cft,
 				      const char *buffer)
 {
 	BUILD_BUG_ON(sizeof(cgrp->root->release_agent_path) < PATH_MAX);
+	if (strlen(buffer) >= PATH_MAX)
+		return -EINVAL;
 	if (!cgroup_lock_live_group(cgrp))
 		return -ENODEV;
 	strcpy(cgrp->root->release_agent_path, buffer);
@@ -3173,6 +3217,23 @@ fail:
 	return ret;
 }
 
+static u64 cgroup_clone_children_read(struct cgroup *cgrp,
+				    struct cftype *cft)
+{
+	return clone_children(cgrp);
+}
+
+static int cgroup_clone_children_write(struct cgroup *cgrp,
+				     struct cftype *cft,
+				     u64 val)
+{
+	if (val)
+		set_bit(CGRP_CLONE_CHILDREN, &cgrp->flags);
+	else
+		clear_bit(CGRP_CLONE_CHILDREN, &cgrp->flags);
+	return 0;
+}
+
 /*
  * for the common functions, 'private' gives the type of file
  */
@@ -3203,6 +3264,11 @@ static struct cftype files[] = {
 		.write_string = cgroup_write_event_control,
 		.mode = S_IWUGO,
 	},
+	{
+		.name = "cgroup.clone_children",
+		.read_u64 = cgroup_clone_children_read,
+		.write_u64 = cgroup_clone_children_write,
+	},
 };
 
 static struct cftype cft_release_agent = {
@@ -3332,6 +3398,9 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
 	if (notify_on_release(parent))
 		set_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags);
 
+	if (clone_children(parent))
+		set_bit(CGRP_CLONE_CHILDREN, &cgrp->flags);
+
 	for_each_subsys(root, ss) {
 		struct cgroup_subsys_state *css = ss->create(ss, cgrp);
 
@@ -3346,6 +3415,8 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
 				goto err_destroy;
 		}
 		/* At error, ->destroy() callback has to free assigned ID. */
+		if (clone_children(parent) && ss->post_clone)
+			ss->post_clone(ss, cgrp);
 	}
 
 	cgroup_lock_hierarchy(root);
diff --git a/kernel/cgroup_freezer.c b/kernel/cgroup_freezer.c
index ce71ed53e88..e7bebb7c6c3 100644
--- a/kernel/cgroup_freezer.c
+++ b/kernel/cgroup_freezer.c
@@ -48,20 +48,19 @@ static inline struct freezer *task_freezer(struct task_struct *task)
 			    struct freezer, css);
 }
 
-int cgroup_freezing_or_frozen(struct task_struct *task)
+static inline int __cgroup_freezing_or_frozen(struct task_struct *task)
 {
-	struct freezer *freezer;
-	enum freezer_state state;
+	enum freezer_state state = task_freezer(task)->state;
+	return (state == CGROUP_FREEZING) || (state == CGROUP_FROZEN);
+}
 
+int cgroup_freezing_or_frozen(struct task_struct *task)
+{
+	int result;
 	task_lock(task);
-	freezer = task_freezer(task);
-	if (!freezer->css.cgroup->parent)
-		state = CGROUP_THAWED; /* root cgroup can't be frozen */
-	else
-		state = freezer->state;
+	result = __cgroup_freezing_or_frozen(task);
 	task_unlock(task);
-
-	return (state == CGROUP_FREEZING) || (state == CGROUP_FROZEN);
+	return result;
 }
 
 /*
@@ -154,13 +153,6 @@ static void freezer_destroy(struct cgroup_subsys *ss,
 	kfree(cgroup_freezer(cgroup));
 }
 
-/* Task is frozen or will freeze immediately when next it gets woken */
-static bool is_task_frozen_enough(struct task_struct *task)
-{
-	return frozen(task) ||
-		(task_is_stopped_or_traced(task) && freezing(task));
-}
-
 /*
  * The call to cgroup_lock() in the freezer.state write method prevents
  * a write to that file racing against an attach, and hence the
@@ -174,24 +166,25 @@ static int freezer_can_attach(struct cgroup_subsys *ss,
 
 	/*
 	 * Anything frozen can't move or be moved to/from.
-	 *
-	 * Since orig_freezer->state == FROZEN means that @task has been
-	 * frozen, so it's sufficient to check the latter condition.
 	 */
 
-	if (is_task_frozen_enough(task))
+	freezer = cgroup_freezer(new_cgroup);
+	if (freezer->state != CGROUP_THAWED)
 		return -EBUSY;
 
-	freezer = cgroup_freezer(new_cgroup);
-	if (freezer->state == CGROUP_FROZEN)
+	rcu_read_lock();
+	if (__cgroup_freezing_or_frozen(task)) {
+		rcu_read_unlock();
 		return -EBUSY;
+	}
+	rcu_read_unlock();
 
 	if (threadgroup) {
 		struct task_struct *c;
 
 		rcu_read_lock();
 		list_for_each_entry_rcu(c, &task->thread_group, thread_group) {
-			if (is_task_frozen_enough(c)) {
+			if (__cgroup_freezing_or_frozen(c)) {
 				rcu_read_unlock();
 				return -EBUSY;
 			}
@@ -236,31 +229,30 @@ static void freezer_fork(struct cgroup_subsys *ss, struct task_struct *task)
 /*
  * caller must hold freezer->lock
  */
-static void update_freezer_state(struct cgroup *cgroup,
+static void update_if_frozen(struct cgroup *cgroup,
 				 struct freezer *freezer)
 {
 	struct cgroup_iter it;
 	struct task_struct *task;
 	unsigned int nfrozen = 0, ntotal = 0;
+	enum freezer_state old_state = freezer->state;
 
 	cgroup_iter_start(cgroup, &it);
 	while ((task = cgroup_iter_next(cgroup, &it))) {
 		ntotal++;
-		if (is_task_frozen_enough(task))
+		if (frozen(task))
 			nfrozen++;
 	}
 
-	/*
-	 * Transition to FROZEN when no new tasks can be added ensures
-	 * that we never exist in the FROZEN state while there are unfrozen
-	 * tasks.
-	 */
-	if (nfrozen == ntotal)
-		freezer->state = CGROUP_FROZEN;
-	else if (nfrozen > 0)
-		freezer->state = CGROUP_FREEZING;
-	else
-		freezer->state = CGROUP_THAWED;
+	if (old_state == CGROUP_THAWED) {
+		BUG_ON(nfrozen > 0);
+	} else if (old_state == CGROUP_FREEZING) {
+		if (nfrozen == ntotal)
+			freezer->state = CGROUP_FROZEN;
+	} else { /* old_state == CGROUP_FROZEN */
+		BUG_ON(nfrozen != ntotal);
+	}
+
 	cgroup_iter_end(cgroup, &it);
 }
 
@@ -279,7 +271,7 @@ static int freezer_read(struct cgroup *cgroup, struct cftype *cft,
 	if (state == CGROUP_FREEZING) {
 		/* We change from FREEZING to FROZEN lazily if the cgroup was
 		 * only partially frozen when we exitted write. */
-		update_freezer_state(cgroup, freezer);
+		update_if_frozen(cgroup, freezer);
 		state = freezer->state;
 	}
 	spin_unlock_irq(&freezer->lock);
@@ -301,7 +293,7 @@ static int try_to_freeze_cgroup(struct cgroup *cgroup, struct freezer *freezer)
 	while ((task = cgroup_iter_next(cgroup, &it))) {
 		if (!freeze_task(task, true))
 			continue;
-		if (is_task_frozen_enough(task))
+		if (frozen(task))
 			continue;
 		if (!freezing(task) && !freezer_should_skip(task))
 			num_cant_freeze_now++;
@@ -335,7 +327,7 @@ static int freezer_change_state(struct cgroup *cgroup,
 
 	spin_lock_irq(&freezer->lock);
 
-	update_freezer_state(cgroup, freezer);
+	update_if_frozen(cgroup, freezer);
 	if (goal_state == freezer->state)
 		goto out;
 
diff --git a/kernel/cred.c b/kernel/cred.c
index 9a3e22641fe..6a1aa004e37 100644
--- a/kernel/cred.c
+++ b/kernel/cred.c
@@ -325,7 +325,7 @@ EXPORT_SYMBOL(prepare_creds);
 
 /*
  * Prepare credentials for current to perform an execve()
- * - The caller must hold current->cred_guard_mutex
+ * - The caller must hold ->cred_guard_mutex
  */
 struct cred *prepare_exec_creds(void)
 {
@@ -384,8 +384,6 @@ int copy_creds(struct task_struct *p, unsigned long clone_flags)
 	struct cred *new;
 	int ret;
 
-	mutex_init(&p->cred_guard_mutex);
-
 	if (
 #ifdef CONFIG_KEYS
 		!p->cred->thread_keyring &&
diff --git a/kernel/exit.c b/kernel/exit.c
index 894179a32ec..b194febf579 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -703,6 +703,8 @@ static void exit_mm(struct task_struct * tsk)
  * space.
  */
 static struct task_struct *find_new_reaper(struct task_struct *father)
+	__releases(&tasklist_lock)
+	__acquires(&tasklist_lock)
 {
 	struct pid_namespace *pid_ns = task_active_pid_ns(father);
 	struct task_struct *thread;
diff --git a/kernel/fork.c b/kernel/fork.c
index e87aaaaf513..3b159c5991b 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -908,6 +908,8 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 	sig->oom_adj = current->signal->oom_adj;
 	sig->oom_score_adj = current->signal->oom_score_adj;
 
+	mutex_init(&sig->cred_guard_mutex);
+
 	return 0;
 }
 
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index 9d917ff7267..9988d03797f 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -393,3 +393,18 @@ unsigned int kstat_irqs_cpu(unsigned int irq, int cpu)
 	struct irq_desc *desc = irq_to_desc(irq);
 	return desc ? desc->kstat_irqs[cpu] : 0;
 }
+
+#ifdef CONFIG_GENERIC_HARDIRQS
+unsigned int kstat_irqs(unsigned int irq)
+{
+	struct irq_desc *desc = irq_to_desc(irq);
+	int cpu;
+	int sum = 0;
+
+	if (!desc)
+		return 0;
+	for_each_possible_cpu(cpu)
+		sum += desc->kstat_irqs[cpu];
+	return sum;
+}
+#endif /* CONFIG_GENERIC_HARDIRQS */
diff --git a/kernel/ns_cgroup.c b/kernel/ns_cgroup.c
index 2a5dfec8efe..2c98ad94ba0 100644
--- a/kernel/ns_cgroup.c
+++ b/kernel/ns_cgroup.c
@@ -85,6 +85,14 @@ static struct cgroup_subsys_state *ns_create(struct cgroup_subsys *ss,
 		return ERR_PTR(-EPERM);
 	if (!cgroup_is_descendant(cgroup, current))
 		return ERR_PTR(-EPERM);
+	if (test_bit(CGRP_CLONE_CHILDREN, &cgroup->flags)) {
+		printk("ns_cgroup can't be created with parent "
+		       "'clone_children' set.\n");
+		return ERR_PTR(-EINVAL);
+	}
+
+	printk_once("ns_cgroup deprecated: consider using the "
+		    "'clone_children' flag without the ns_cgroup.\n");
 
 	ns_cgroup = kzalloc(sizeof(*ns_cgroup), GFP_KERNEL);
 	if (!ns_cgroup)
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index f34d798ef4a..99bbaa3e5b0 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -181,7 +181,7 @@ int ptrace_attach(struct task_struct *task)
 	 * under ptrace.
 	 */
 	retval = -ERESTARTNOINTR;
-	if (mutex_lock_interruptible(&task->cred_guard_mutex))
+	if (mutex_lock_interruptible(&task->signal->cred_guard_mutex))
 		goto out;
 
 	task_lock(task);
@@ -208,7 +208,7 @@ int ptrace_attach(struct task_struct *task)
 unlock_tasklist:
 	write_unlock_irq(&tasklist_lock);
 unlock_creds:
-	mutex_unlock(&task->cred_guard_mutex);
+	mutex_unlock(&task->signal->cred_guard_mutex);
 out:
 	return retval;
 }
@@ -329,6 +329,8 @@ int ptrace_detach(struct task_struct *child, unsigned int data)
  * and reacquire the lock.
  */
 void exit_ptrace(struct task_struct *tracer)
+	__releases(&tasklist_lock)
+	__acquires(&tasklist_lock)
 {
 	struct task_struct *p, *n;
 	LIST_HEAD(ptrace_dead);
@@ -402,7 +404,7 @@ int ptrace_writedata(struct task_struct *tsk, char __user *src, unsigned long ds
 	return copied;
 }
 
-static int ptrace_setoptions(struct task_struct *child, long data)
+static int ptrace_setoptions(struct task_struct *child, unsigned long data)
 {
 	child->ptrace &= ~PT_TRACE_MASK;
 
@@ -481,7 +483,8 @@ static int ptrace_setsiginfo(struct task_struct *child, const siginfo_t *info)
 #define is_sysemu_singlestep(request)	0
 #endif
 
-static int ptrace_resume(struct task_struct *child, long request, long data)
+static int ptrace_resume(struct task_struct *child, long request,
+			 unsigned long data)
 {
 	if (!valid_signal(data))
 		return -EIO;
@@ -558,10 +561,12 @@ static int ptrace_regset(struct task_struct *task, int req, unsigned int type,
 #endif
 
 int ptrace_request(struct task_struct *child, long request,
-		   long addr, long data)
+		   unsigned long addr, unsigned long data)
 {
 	int ret = -EIO;
 	siginfo_t siginfo;
+	void __user *datavp = (void __user *) data;
+	unsigned long __user *datalp = datavp;
 
 	switch (request) {
 	case PTRACE_PEEKTEXT:
@@ -578,19 +583,17 @@ int ptrace_request(struct task_struct *child, long request,
 		ret = ptrace_setoptions(child, data);
 		break;
 	case PTRACE_GETEVENTMSG:
-		ret = put_user(child->ptrace_message, (unsigned long __user *) data);
+		ret = put_user(child->ptrace_message, datalp);
 		break;
 
 	case PTRACE_GETSIGINFO:
 		ret = ptrace_getsiginfo(child, &siginfo);
 		if (!ret)
-			ret = copy_siginfo_to_user((siginfo_t __user *) data,
-						   &siginfo);
+			ret = copy_siginfo_to_user(datavp, &siginfo);
 		break;
 
 	case PTRACE_SETSIGINFO:
-		if (copy_from_user(&siginfo, (siginfo_t __user *) data,
-				   sizeof siginfo))
+		if (copy_from_user(&siginfo, datavp, sizeof siginfo))
 			ret = -EFAULT;
 		else
 			ret = ptrace_setsiginfo(child, &siginfo);
@@ -621,7 +624,7 @@ int ptrace_request(struct task_struct *child, long request,
 		}
 		mmput(mm);
 
-		ret = put_user(tmp, (unsigned long __user *) data);
+		ret = put_user(tmp, datalp);
 		break;
 	}
 #endif
@@ -650,7 +653,7 @@ int ptrace_request(struct task_struct *child, long request,
 	case PTRACE_SETREGSET:
 	{
 		struct iovec kiov;
-		struct iovec __user *uiov = (struct iovec __user *) data;
+		struct iovec __user *uiov = datavp;
 
 		if (!access_ok(VERIFY_WRITE, uiov, sizeof(*uiov)))
 			return -EFAULT;
@@ -691,7 +694,8 @@ static struct task_struct *ptrace_get_task_struct(pid_t pid)
 #define arch_ptrace_attach(child)	do { } while (0)
 #endif
 
-SYSCALL_DEFINE4(ptrace, long, request, long, pid, long, addr, long, data)
+SYSCALL_DEFINE4(ptrace, long, request, long, pid, unsigned long, addr,
+		unsigned long, data)
 {
 	struct task_struct *child;
 	long ret;
@@ -732,7 +736,8 @@ SYSCALL_DEFINE4(ptrace, long, request, long, pid, long, addr, long, data)
 	return ret;
 }
 
-int generic_ptrace_peekdata(struct task_struct *tsk, long addr, long data)
+int generic_ptrace_peekdata(struct task_struct *tsk, unsigned long addr,
+			    unsigned long data)
 {
 	unsigned long tmp;
 	int copied;
@@ -743,7 +748,8 @@ int generic_ptrace_peekdata(struct task_struct *tsk, long addr, long data)
 	return put_user(tmp, (unsigned long __user *)data);
 }
 
-int generic_ptrace_pokedata(struct task_struct *tsk, long addr, long data)
+int generic_ptrace_pokedata(struct task_struct *tsk, unsigned long addr,
+			    unsigned long data)
 {
 	int copied;
 
diff --git a/kernel/resource.c b/kernel/resource.c
index 7b36976e5de..9c9841cb690 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -453,6 +453,8 @@ static struct resource * __insert_resource(struct resource *parent, struct resou
 
 		if (first == parent)
 			return first;
+		if (WARN_ON(first == new))	/* duplicated insertion */
+			return first;
 
 		if ((first->start > new->start) || (first->end < new->end))
 			break;
diff --git a/kernel/signal.c b/kernel/signal.c
index 919562c3d6b..4e3cff10fdc 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -1105,7 +1105,8 @@ int zap_other_threads(struct task_struct *p)
 	return count;
 }
 
-struct sighand_struct *lock_task_sighand(struct task_struct *tsk, unsigned long *flags)
+struct sighand_struct *__lock_task_sighand(struct task_struct *tsk,
+					   unsigned long *flags)
 {
 	struct sighand_struct *sighand;
 
@@ -1617,6 +1618,8 @@ static int sigkill_pending(struct task_struct *tsk)
  * is gone, we keep current->exit_code unless clear_code.
  */
 static void ptrace_stop(int exit_code, int clear_code, siginfo_t *info)
+	__releases(&current->sighand->siglock)
+	__acquires(&current->sighand->siglock)
 {
 	if (arch_ptrace_stop_needed(exit_code, info)) {
 		/*
diff --git a/kernel/taskstats.c b/kernel/taskstats.c
index 11281d5792b..c8231fb1570 100644
--- a/kernel/taskstats.c
+++ b/kernel/taskstats.c
@@ -175,22 +175,8 @@ static void send_cpu_listeners(struct sk_buff *skb,
 	up_write(&listeners->sem);
 }
 
-static int fill_pid(pid_t pid, struct task_struct *tsk,
-		struct taskstats *stats)
+static void fill_stats(struct task_struct *tsk, struct taskstats *stats)
 {
-	int rc = 0;
-
-	if (!tsk) {
-		rcu_read_lock();
-		tsk = find_task_by_vpid(pid);
-		if (tsk)
-			get_task_struct(tsk);
-		rcu_read_unlock();
-		if (!tsk)
-			return -ESRCH;
-	} else
-		get_task_struct(tsk);
-
 	memset(stats, 0, sizeof(*stats));
 	/*
 	 * Each accounting subsystem adds calls to its functions to
@@ -209,17 +195,27 @@ static int fill_pid(pid_t pid, struct task_struct *tsk,
 
 	/* fill in extended acct fields */
 	xacct_add_tsk(stats, tsk);
+}
 
-	/* Define err: label here if needed */
-	put_task_struct(tsk);
-	return rc;
+static int fill_stats_for_pid(pid_t pid, struct taskstats *stats)
+{
+	struct task_struct *tsk;
 
+	rcu_read_lock();
+	tsk = find_task_by_vpid(pid);
+	if (tsk)
+		get_task_struct(tsk);
+	rcu_read_unlock();
+	if (!tsk)
+		return -ESRCH;
+	fill_stats(tsk, stats);
+	put_task_struct(tsk);
+	return 0;
 }
 
-static int fill_tgid(pid_t tgid, struct task_struct *first,
-		struct taskstats *stats)
+static int fill_stats_for_tgid(pid_t tgid, struct taskstats *stats)
 {
-	struct task_struct *tsk;
+	struct task_struct *tsk, *first;
 	unsigned long flags;
 	int rc = -ESRCH;
 
@@ -228,8 +224,7 @@ static int fill_tgid(pid_t tgid, struct task_struct *first,
 	 * leaders who are already counted with the dead tasks
 	 */
 	rcu_read_lock();
-	if (!first)
-		first = find_task_by_vpid(tgid);
+	first = find_task_by_vpid(tgid);
 
 	if (!first || !lock_task_sighand(first, &flags))
 		goto out;
@@ -268,7 +263,6 @@ out:
 	return rc;
 }
 
-
 static void fill_tgid_exit(struct task_struct *tsk)
 {
 	unsigned long flags;
@@ -360,6 +354,12 @@ static struct taskstats *mk_reply(struct sk_buff *skb, int type, u32 pid)
 	struct nlattr *na, *ret;
 	int aggr;
 
+	/* If we don't pad, we end up with alignment on a 4 byte boundary.
+	 * This causes lots of runtime warnings on systems requiring 8 byte
+	 * alignment */
+	u32 pids[2] = { pid, 0 };
+	int pid_size = ALIGN(sizeof(pid), sizeof(long));
+
 	aggr = (type == TASKSTATS_TYPE_PID)
 			? TASKSTATS_TYPE_AGGR_PID
 			: TASKSTATS_TYPE_AGGR_TGID;
@@ -367,7 +367,7 @@ static struct taskstats *mk_reply(struct sk_buff *skb, int type, u32 pid)
 	na = nla_nest_start(skb, aggr);
 	if (!na)
 		goto err;
-	if (nla_put(skb, type, sizeof(pid), &pid) < 0)
+	if (nla_put(skb, type, pid_size, pids) < 0)
 		goto err;
 	ret = nla_reserve(skb, TASKSTATS_TYPE_STATS, sizeof(struct taskstats));
 	if (!ret)
@@ -424,39 +424,46 @@ err:
 	return rc;
 }
 
-static int taskstats_user_cmd(struct sk_buff *skb, struct genl_info *info)
+static int cmd_attr_register_cpumask(struct genl_info *info)
 {
-	int rc;
-	struct sk_buff *rep_skb;
-	struct taskstats *stats;
-	size_t size;
 	cpumask_var_t mask;
+	int rc;
 
 	if (!alloc_cpumask_var(&mask, GFP_KERNEL))
 		return -ENOMEM;
-
 	rc = parse(info->attrs[TASKSTATS_CMD_ATTR_REGISTER_CPUMASK], mask);
 	if (rc < 0)
-		goto free_return_rc;
-	if (rc == 0) {
-		rc = add_del_listener(info->snd_pid, mask, REGISTER);
-		goto free_return_rc;
-	}
+		goto out;
+	rc = add_del_listener(info->snd_pid, mask, REGISTER);
+out:
+	free_cpumask_var(mask);
+	return rc;
+}
+
+static int cmd_attr_deregister_cpumask(struct genl_info *info)
+{
+	cpumask_var_t mask;
+	int rc;
 
+	if (!alloc_cpumask_var(&mask, GFP_KERNEL))
+		return -ENOMEM;
 	rc = parse(info->attrs[TASKSTATS_CMD_ATTR_DEREGISTER_CPUMASK], mask);
 	if (rc < 0)
-		goto free_return_rc;
-	if (rc == 0) {
-		rc = add_del_listener(info->snd_pid, mask, DEREGISTER);
-free_return_rc:
-		free_cpumask_var(mask);
-		return rc;
-	}
+		goto out;
+	rc = add_del_listener(info->snd_pid, mask, DEREGISTER);
+out:
 	free_cpumask_var(mask);
+	return rc;
+}
+
+static int cmd_attr_pid(struct genl_info *info)
+{
+	struct taskstats *stats;
+	struct sk_buff *rep_skb;
+	size_t size;
+	u32 pid;
+	int rc;
 
-	/*
-	 * Size includes space for nested attributes
-	 */
 	size = nla_total_size(sizeof(u32)) +
 		nla_total_size(sizeof(struct taskstats)) + nla_total_size(0);
 
@@ -465,33 +472,64 @@ free_return_rc:
 		return rc;
 
 	rc = -EINVAL;
-	if (info->attrs[TASKSTATS_CMD_ATTR_PID]) {
-		u32 pid = nla_get_u32(info->attrs[TASKSTATS_CMD_ATTR_PID]);
-		stats = mk_reply(rep_skb, TASKSTATS_TYPE_PID, pid);
-		if (!stats)
-			goto err;
-
-		rc = fill_pid(pid, NULL, stats);
-		if (rc < 0)
-			goto err;
-	} else if (info->attrs[TASKSTATS_CMD_ATTR_TGID]) {
-		u32 tgid = nla_get_u32(info->attrs[TASKSTATS_CMD_ATTR_TGID]);
-		stats = mk_reply(rep_skb, TASKSTATS_TYPE_TGID, tgid);
-		if (!stats)
-			goto err;
-
-		rc = fill_tgid(tgid, NULL, stats);
-		if (rc < 0)
-			goto err;
-	} else
+	pid = nla_get_u32(info->attrs[TASKSTATS_CMD_ATTR_PID]);
+	stats = mk_reply(rep_skb, TASKSTATS_TYPE_PID, pid);
+	if (!stats)
+		goto err;
+
+	rc = fill_stats_for_pid(pid, stats);
+	if (rc < 0)
+		goto err;
+	return send_reply(rep_skb, info);
+err:
+	nlmsg_free(rep_skb);
+	return rc;
+}
+
+static int cmd_attr_tgid(struct genl_info *info)
+{
+	struct taskstats *stats;
+	struct sk_buff *rep_skb;
+	size_t size;
+	u32 tgid;
+	int rc;
+
+	size = nla_total_size(sizeof(u32)) +
+		nla_total_size(sizeof(struct taskstats)) + nla_total_size(0);
+
+	rc = prepare_reply(info, TASKSTATS_CMD_NEW, &rep_skb, size);
+	if (rc < 0)
+		return rc;
+
+	rc = -EINVAL;
+	tgid = nla_get_u32(info->attrs[TASKSTATS_CMD_ATTR_TGID]);
+	stats = mk_reply(rep_skb, TASKSTATS_TYPE_TGID, tgid);
+	if (!stats)
 		goto err;
 
+	rc = fill_stats_for_tgid(tgid, stats);
+	if (rc < 0)
+		goto err;
 	return send_reply(rep_skb, info);
 err:
 	nlmsg_free(rep_skb);
 	return rc;
 }
 
+static int taskstats_user_cmd(struct sk_buff *skb, struct genl_info *info)
+{
+	if (info->attrs[TASKSTATS_CMD_ATTR_REGISTER_CPUMASK])
+		return cmd_attr_register_cpumask(info);
+	else if (info->attrs[TASKSTATS_CMD_ATTR_DEREGISTER_CPUMASK])
+		return cmd_attr_deregister_cpumask(info);
+	else if (info->attrs[TASKSTATS_CMD_ATTR_PID])
+		return cmd_attr_pid(info);
+	else if (info->attrs[TASKSTATS_CMD_ATTR_TGID])
+		return cmd_attr_tgid(info);
+	else
+		return -EINVAL;
+}
+
 static struct taskstats *taskstats_tgid_alloc(struct task_struct *tsk)
 {
 	struct signal_struct *sig = tsk->signal;
@@ -555,9 +593,7 @@ void taskstats_exit(struct task_struct *tsk, int group_dead)
 	if (!stats)
 		goto err;
 
-	rc = fill_pid(-1, tsk, stats);
-	if (rc < 0)
-		goto err;
+	fill_stats(tsk, stats);
 
 	/*
 	 * Doesn't matter if tsk is the leader or the last group member leaving
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index b8d2852baa4..2dec9bcde8b 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -31,7 +31,6 @@
 #include <linux/perf_event.h>
 #include <linux/stringify.h>
 #include <linux/limits.h>
-#include <linux/uaccess.h>
 #include <asm/bitsperlong.h>
 
 #include "trace.h"
diff --git a/kernel/tsacct.c b/kernel/tsacct.c
index 0a67e041edf..24dc60d9fa1 100644
--- a/kernel/tsacct.c
+++ b/kernel/tsacct.c
@@ -63,12 +63,10 @@ void bacct_add_tsk(struct taskstats *stats, struct task_struct *tsk)
 	stats->ac_ppid	 = pid_alive(tsk) ?
 				rcu_dereference(tsk->real_parent)->tgid : 0;
 	rcu_read_unlock();
-	stats->ac_utime	 = cputime_to_msecs(tsk->utime) * USEC_PER_MSEC;
-	stats->ac_stime	 = cputime_to_msecs(tsk->stime) * USEC_PER_MSEC;
-	stats->ac_utimescaled =
-		cputime_to_msecs(tsk->utimescaled) * USEC_PER_MSEC;
-	stats->ac_stimescaled =
-		cputime_to_msecs(tsk->stimescaled) * USEC_PER_MSEC;
+	stats->ac_utime = cputime_to_usecs(tsk->utime);
+	stats->ac_stime = cputime_to_usecs(tsk->stime);
+	stats->ac_utimescaled = cputime_to_usecs(tsk->utimescaled);
+	stats->ac_stimescaled = cputime_to_usecs(tsk->stimescaled);
 	stats->ac_minflt = tsk->min_flt;
 	stats->ac_majflt = tsk->maj_flt;