Merge commit 'tip/auto-latest'

Conflicts:
	arch/x86/include/asm/termios.h

11 files changed, 164 insertions, 110 deletions

diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 50da67672901..aeb4ee0f6883 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -935,7 +935,7 @@ int request_threaded_irq(unsigned int irq, irq_handler_t handler,
 		kfree(action);
 
 #ifdef CONFIG_DEBUG_SHIRQ
-	if (irqflags & IRQF_SHARED) {
+	if (!retval && (irqflags & IRQF_SHARED)) {
 		/*
 		 * It's a shared IRQ -- the driver ought to be prepared for it
 		 * to happen immediately, so let's make sure....
diff --git a/kernel/perf_counter.c b/kernel/perf_counter.c
index 1a933a221ea4..c2b19c111718 100644
--- a/kernel/perf_counter.c
+++ b/kernel/perf_counter.c
@@ -1508,11 +1508,13 @@ static void free_counter(struct perf_counter *counter)
 {
 	perf_pending_sync(counter);
 
-	atomic_dec(&nr_counters);
-	if (counter->attr.mmap)
-		atomic_dec(&nr_mmap_counters);
-	if (counter->attr.comm)
-		atomic_dec(&nr_comm_counters);
+	if (!counter->parent) {
+		atomic_dec(&nr_counters);
+		if (counter->attr.mmap)
+			atomic_dec(&nr_mmap_counters);
+		if (counter->attr.comm)
+			atomic_dec(&nr_comm_counters);
+	}
 
 	if (counter->destroy)
 		counter->destroy(counter);
@@ -3317,8 +3319,8 @@ out:
 	put_cpu_var(perf_cpu_context);
 }
 
-void
-perf_swcounter_event(u32 event, u64 nr, int nmi, struct pt_regs *regs, u64 addr)
+void __perf_swcounter_event(u32 event, u64 nr, int nmi,
+			    struct pt_regs *regs, u64 addr)
 {
 	struct perf_sample_data data = {
 		.regs = regs,
@@ -3509,9 +3511,21 @@ static const struct pmu *tp_perf_counter_init(struct perf_counter *counter)
 }
 #endif
 
+atomic_t perf_swcounter_enabled[PERF_COUNT_SW_MAX];
+
+static void sw_perf_counter_destroy(struct perf_counter *counter)
+{
+	u64 event = counter->attr.config;
+
+	WARN_ON(counter->parent);
+
+	atomic_dec(&perf_swcounter_enabled[event]);
+}
+
 static const struct pmu *sw_perf_counter_init(struct perf_counter *counter)
 {
 	const struct pmu *pmu = NULL;
+	u64 event = counter->attr.config;
 
 	/*
 	 * Software counters (currently) can't in general distinguish
@@ -3520,7 +3534,7 @@ static const struct pmu *sw_perf_counter_init(struct perf_counter *counter)
 	 * to be kernel events, and page faults are never hypervisor
 	 * events.
 	 */
-	switch (counter->attr.config) {
+	switch (event) {
 	case PERF_COUNT_SW_CPU_CLOCK:
 		pmu = &perf_ops_cpu_clock;
 
@@ -3541,6 +3555,10 @@ static const struct pmu *sw_perf_counter_init(struct perf_counter *counter)
 	case PERF_COUNT_SW_PAGE_FAULTS_MAJ:
 	case PERF_COUNT_SW_CONTEXT_SWITCHES:
 	case PERF_COUNT_SW_CPU_MIGRATIONS:
+		if (!counter->parent) {
+			atomic_inc(&perf_swcounter_enabled[event]);
+			counter->destroy = sw_perf_counter_destroy;
+		}
 		pmu = &perf_ops_generic;
 		break;
 	}
@@ -3556,6 +3574,7 @@ perf_counter_alloc(struct perf_counter_attr *attr,
 		   int cpu,
 		   struct perf_counter_context *ctx,
 		   struct perf_counter *group_leader,
+		   struct perf_counter *parent_counter,
 		   gfp_t gfpflags)
 {
 	const struct pmu *pmu;
@@ -3591,6 +3610,8 @@ perf_counter_alloc(struct perf_counter_attr *attr,
 	counter->ctx		= ctx;
 	counter->oncpu		= -1;
 
+	counter->parent		= parent_counter;
+
 	counter->ns		= get_pid_ns(current->nsproxy->pid_ns);
 	counter->id		= atomic64_inc_return(&perf_counter_id);
 
@@ -3648,11 +3669,13 @@ done:
 
 	counter->pmu = pmu;
 
-	atomic_inc(&nr_counters);
-	if (counter->attr.mmap)
-		atomic_inc(&nr_mmap_counters);
-	if (counter->attr.comm)
-		atomic_inc(&nr_comm_counters);
+	if (!counter->parent) {
+		atomic_inc(&nr_counters);
+		if (counter->attr.mmap)
+			atomic_inc(&nr_mmap_counters);
+		if (counter->attr.comm)
+			atomic_inc(&nr_comm_counters);
+	}
 
 	return counter;
 }
@@ -3815,7 +3838,7 @@ SYSCALL_DEFINE5(perf_counter_open,
 	}
 
 	counter = perf_counter_alloc(&attr, cpu, ctx, group_leader,
-				     GFP_KERNEL);
+				     NULL, GFP_KERNEL);
 	ret = PTR_ERR(counter);
 	if (IS_ERR(counter))
 		goto err_put_context;
@@ -3881,7 +3904,8 @@ inherit_counter(struct perf_counter *parent_counter,
 
 	child_counter = perf_counter_alloc(&parent_counter->attr,
 					   parent_counter->cpu, child_ctx,
-					   group_leader, GFP_KERNEL);
+					   group_leader, parent_counter,
+					   GFP_KERNEL);
 	if (IS_ERR(child_counter))
 		return child_counter;
 	get_ctx(child_ctx);
@@ -3904,12 +3928,6 @@ inherit_counter(struct perf_counter *parent_counter,
 	 */
 	add_counter_to_ctx(child_counter, child_ctx);
 
-	child_counter->parent = parent_counter;
-	/*
-	 * inherit into child's child as well:
-	 */
-	child_counter->attr.inherit = 1;
-
 	/*
 	 * Get a reference to the parent filp - we will fput it
 	 * when the child counter exits. This is safe to do because
diff --git a/kernel/sched.c b/kernel/sched.c
index 7c9098d186e6..168b2680ae27 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -2614,9 +2614,32 @@ void sched_fork(struct task_struct *p, int clone_flags)
 	set_task_cpu(p, cpu);
 
 	/*
-	 * Make sure we do not leak PI boosting priority to the child:
+	 * Make sure we do not leak PI boosting priority to the child.
 	 */
 	p->prio = current->normal_prio;
+
+	/*
+	 * Revert to default priority/policy on fork if requested.
+	 */
+	if (unlikely(p->sched_reset_on_fork)) {
+		if (p->policy == SCHED_FIFO || p->policy == SCHED_RR)
+			p->policy = SCHED_NORMAL;
+
+		if (p->normal_prio < DEFAULT_PRIO)
+			p->prio = DEFAULT_PRIO;
+
+		if (PRIO_TO_NICE(p->static_prio) < 0) {
+			p->static_prio = NICE_TO_PRIO(0);
+			set_load_weight(p);
+		}
+
+		/*
+		 * We don't need the reset flag anymore after the fork. It has
+		 * fulfilled its duty:
+		 */
+		p->sched_reset_on_fork = 0;
+	}
+
 	if (!rt_prio(p->prio))
 		p->sched_class = &fair_sched_class;
 
@@ -6100,17 +6123,25 @@ static int __sched_setscheduler(struct task_struct *p, int policy,
 	unsigned long flags;
 	const struct sched_class *prev_class = p->sched_class;
 	struct rq *rq;
+	int reset_on_fork;
 
 	/* may grab non-irq protected spin_locks */
 	BUG_ON(in_interrupt());
 recheck:
 	/* double check policy once rq lock held */
-	if (policy < 0)
+	if (policy < 0) {
+		reset_on_fork = p->sched_reset_on_fork;
 		policy = oldpolicy = p->policy;
-	else if (policy != SCHED_FIFO && policy != SCHED_RR &&
-			policy != SCHED_NORMAL && policy != SCHED_BATCH &&
-			policy != SCHED_IDLE)
-		return -EINVAL;
+	} else {
+		reset_on_fork = !!(policy & SCHED_RESET_ON_FORK);
+		policy &= ~SCHED_RESET_ON_FORK;
+
+		if (policy != SCHED_FIFO && policy != SCHED_RR &&
+				policy != SCHED_NORMAL && policy != SCHED_BATCH &&
+				policy != SCHED_IDLE)
+			return -EINVAL;
+	}
+
 	/*
 	 * Valid priorities for SCHED_FIFO and SCHED_RR are
 	 * 1..MAX_USER_RT_PRIO-1, valid priority for SCHED_NORMAL,
@@ -6154,6 +6185,10 @@ recheck:
 		/* can't change other user's priorities */
 		if (!check_same_owner(p))
 			return -EPERM;
+
+		/* Normal users shall not reset the sched_reset_on_fork flag */
+		if (p->sched_reset_on_fork && !reset_on_fork)
+			return -EPERM;
 	}
 
 	if (user) {
@@ -6197,6 +6232,8 @@ recheck:
 	if (running)
 		p->sched_class->put_prev_task(rq, p);
 
+	p->sched_reset_on_fork = reset_on_fork;
+
 	oldprio = p->prio;
 	__setscheduler(rq, p, policy, param->sched_priority);
 
@@ -6313,14 +6350,15 @@ SYSCALL_DEFINE1(sched_getscheduler, pid_t, pid)
 	if (p) {
 		retval = security_task_getscheduler(p);
 		if (!retval)
-			retval = p->policy;
+			retval = p->policy
+				| (p->sched_reset_on_fork ? SCHED_RESET_ON_FORK : 0);
 	}
 	read_unlock(&tasklist_lock);
 	return retval;
 }
 
 /**
- * sys_sched_getscheduler - get the RT priority of a thread
+ * sys_sched_getparam - get the RT priority of a thread
  * @pid: the pid in question.
  * @param: structure containing the RT priority.
  */
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 62e4ff9968b5..c428ba161db1 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -335,7 +335,10 @@ static struct ctl_table kern_table[] = {
 		.data		= &sysctl_timer_migration,
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
-		.proc_handler	= &proc_dointvec,
+		.proc_handler	= &proc_dointvec_minmax,
+		.strategy	= &sysctl_intvec,
+		.extra1		= &zero,
+		.extra2		= &one,
 	},
 #endif
 	{
diff --git a/kernel/time/timer_stats.c b/kernel/time/timer_stats.c
index c994530d166d..4cde8b9c716f 100644
--- a/kernel/time/timer_stats.c
+++ b/kernel/time/timer_stats.c
@@ -96,7 +96,7 @@ static DEFINE_MUTEX(show_mutex);
 /*
  * Collection status, active/inactive:
  */
-static int __read_mostly active;
+int __read_mostly timer_stats_active;
 
 /*
  * Beginning/end timestamps of measurement:
@@ -242,7 +242,7 @@ void timer_stats_update_stats(void *timer, pid_t pid, void *startf,
 	struct entry *entry, input;
 	unsigned long flags;
 
-	if (likely(!active))
+	if (likely(!timer_stats_active))
 		return;
 
 	lock = &per_cpu(lookup_lock, raw_smp_processor_id());
@@ -254,7 +254,7 @@ void timer_stats_update_stats(void *timer, pid_t pid, void *startf,
 	input.timer_flag = timer_flag;
 
 	spin_lock_irqsave(lock, flags);
-	if (!active)
+	if (!timer_stats_active)
 		goto out_unlock;
 
 	entry = tstat_lookup(&input, comm);
@@ -290,7 +290,7 @@ static int tstats_show(struct seq_file *m, void *v)
 	/*
 	 * If still active then calculate up to now:
 	 */
-	if (active)
+	if (timer_stats_active)
 		time_stop = ktime_get();
 
 	time = ktime_sub(time_stop, time_start);
@@ -368,18 +368,18 @@ static ssize_t tstats_write(struct file *file, const char __user *buf,
 	mutex_lock(&show_mutex);
 	switch (ctl[0]) {
 	case '0':
-		if (active) {
-			active = 0;
+		if (timer_stats_active) {
+			timer_stats_active = 0;
 			time_stop = ktime_get();
 			sync_access();
 		}
 		break;
 	case '1':
-		if (!active) {
+		if (!timer_stats_active) {
 			reset_entries();
 			time_start = ktime_get();
 			smp_mb();
-			active = 1;
+			timer_stats_active = 1;
 		}
 		break;
 	default:
diff --git a/kernel/timer.c b/kernel/timer.c
index 54d3912f8cad..0b36b9e5cc8b 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -380,6 +380,8 @@ static void timer_stats_account_timer(struct timer_list *timer)
 {
 	unsigned int flag = 0;
 
+	if (likely(!timer->start_site))
+		return;
 	if (unlikely(tbase_get_deferrable(timer->base)))
 		flag |= TIMER_STATS_FLAG_DEFERRABLE;
 
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 3718d55fb4c3..71a52c172140 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -1417,10 +1417,20 @@ static void *t_hash_start(struct seq_file *m, loff_t *pos)
 {
 	struct ftrace_iterator *iter = m->private;
 	void *p = NULL;
+	loff_t l;
+
+	if (!(iter->flags & FTRACE_ITER_HASH))
+		*pos = 0;
 
 	iter->flags |= FTRACE_ITER_HASH;
 
-	return t_hash_next(m, p, pos);
+	iter->hidx = 0;
+	for (l = 0; l <= *pos; ) {
+		p = t_hash_next(m, p, &l);
+		if (!p)
+			break;
+	}
+	return p;
 }
 
 static int t_hash_show(struct seq_file *m, void *v)
@@ -1467,8 +1477,6 @@ t_next(struct seq_file *m, void *v, loff_t *pos)
 			iter->pg = iter->pg->next;
 			iter->idx = 0;
 			goto retry;
-		} else {
-			iter->idx = -1;
 		}
 	} else {
 		rec = &iter->pg->records[iter->idx++];
@@ -1497,6 +1505,7 @@ static void *t_start(struct seq_file *m, loff_t *pos)
 {
 	struct ftrace_iterator *iter = m->private;
 	void *p = NULL;
+	loff_t l;
 
 	mutex_lock(&ftrace_lock);
 	/*
@@ -1508,23 +1517,21 @@ static void *t_start(struct seq_file *m, loff_t *pos)
 		if (*pos > 0)
 			return t_hash_start(m, pos);
 		iter->flags |= FTRACE_ITER_PRINTALL;
-		(*pos)++;
 		return iter;
 	}
 
 	if (iter->flags & FTRACE_ITER_HASH)
 		return t_hash_start(m, pos);
 
-	if (*pos > 0) {
-		if (iter->idx < 0)
-			return p;
-		(*pos)--;
-		iter->idx--;
+	iter->pg = ftrace_pages_start;
+	iter->idx = 0;
+	for (l = 0; l <= *pos; ) {
+		p = t_next(m, p, &l);
+		if (!p)
+			break;
 	}
 
-	p = t_next(m, p, pos);
-
-	if (!p)
+	if (!p && iter->flags & FTRACE_ITER_FILTER)
 		return t_hash_start(m, pos);
 
 	return p;
@@ -2500,32 +2507,31 @@ int ftrace_graph_count;
 unsigned long ftrace_graph_funcs[FTRACE_GRAPH_MAX_FUNCS] __read_mostly;
 
 static void *
-g_next(struct seq_file *m, void *v, loff_t *pos)
+__g_next(struct seq_file *m, loff_t *pos)
 {
 	unsigned long *array = m->private;
-	int index = *pos;
-
-	(*pos)++;
 
-	if (index >= ftrace_graph_count)
+	if (*pos >= ftrace_graph_count)
 		return NULL;
+	return &array[*pos];
+}
 
-	return &array[index];
+static void *
+g_next(struct seq_file *m, void *v, loff_t *pos)
+{
+	(*pos)++;
+	return __g_next(m, pos);
 }
 
 static void *g_start(struct seq_file *m, loff_t *pos)
 {
-	void *p = NULL;
-
 	mutex_lock(&graph_lock);
 
 	/* Nothing, tell g_show to print all functions are enabled */
 	if (!ftrace_graph_count && !*pos)
 		return (void *)1;
 
-	p = g_next(m, p, pos);
-
-	return p;
+	return __g_next(m, pos);
 }
 
 static void g_stop(struct seq_file *m, void *p)
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 18038cb431f7..ffe3a951bb32 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -284,13 +284,12 @@ void trace_wake_up(void)
 static int __init set_buf_size(char *str)
 {
 	unsigned long buf_size;
-	int ret;
 
 	if (!str)
 		return 0;
-	ret = strict_strtoul(str, 0, &buf_size);
+	buf_size = memparse(str, &str);
 	/* nr_entries can not be zero */
-	if (ret < 0 || buf_size == 0)
+	if (buf_size == 0)
 		return 0;
 	trace_buf_size = buf_size;
 	return 1;
@@ -2051,25 +2050,23 @@ static int tracing_open(struct inode *inode, struct file *file)
 static void *
 t_next(struct seq_file *m, void *v, loff_t *pos)
 {
-	struct tracer *t = m->private;
+	struct tracer *t = v;
 
 	(*pos)++;
 
 	if (t)
 		t = t->next;
 
-	m->private = t;
-
 	return t;
 }
 
 static void *t_start(struct seq_file *m, loff_t *pos)
 {
-	struct tracer *t = m->private;
+	struct tracer *t;
 	loff_t l = 0;
 
 	mutex_lock(&trace_types_lock);
-	for (; t && l < *pos; t = t_next(m, t, &l))
+	for (t = trace_types; t && l < *pos; t = t_next(m, t, &l))
 		;
 
 	return t;
@@ -2105,18 +2102,10 @@ static struct seq_operations show_traces_seq_ops = {
 
 static int show_traces_open(struct inode *inode, struct file *file)
 {
-	int ret;
-
 	if (tracing_disabled)
 		return -ENODEV;
 
-	ret = seq_open(file, &show_traces_seq_ops);
-	if (!ret) {
-		struct seq_file *m = file->private_data;
-		m->private = trace_types;
-	}
-
-	return ret;
+	return seq_open(file, &show_traces_seq_ops);
 }
 
 static ssize_t
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index aa08be69a1b6..53c8fd376a88 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -300,10 +300,18 @@ t_next(struct seq_file *m, void *v, loff_t *pos)
 
 static void *t_start(struct seq_file *m, loff_t *pos)
 {
+	struct ftrace_event_call *call = NULL;
+	loff_t l;
+
 	mutex_lock(&event_mutex);
-	if (*pos == 0)
-		m->private = ftrace_events.next;
-	return t_next(m, NULL, pos);
+
+	m->private = ftrace_events.next;
+	for (l = 0; l <= *pos; ) {
+		call = t_next(m, NULL, &l);
+		if (!call)
+			break;
+	}
+	return call;
 }
 
 static void *
@@ -332,10 +340,18 @@ s_next(struct seq_file *m, void *v, loff_t *pos)
 
 static void *s_start(struct seq_file *m, loff_t *pos)
 {
+	struct ftrace_event_call *call = NULL;
+	loff_t l;
+
 	mutex_lock(&event_mutex);
-	if (*pos == 0)
-		m->private = ftrace_events.next;
-	return s_next(m, NULL, pos);
+
+	m->private = ftrace_events.next;
+	for (l = 0; l <= *pos; ) {
+		call = s_next(m, NULL, &l);
+		if (!call)
+			break;
+	}
+	return call;
 }
 
 static int t_show(struct seq_file *m, void *v)
diff --git a/kernel/trace/trace_printk.c b/kernel/trace/trace_printk.c
index 9bece9687b62..7b6278110827 100644
--- a/kernel/trace/trace_printk.c
+++ b/kernel/trace/trace_printk.c
@@ -155,25 +155,19 @@ int __ftrace_vprintk(unsigned long ip, const char *fmt, va_list ap)
 EXPORT_SYMBOL_GPL(__ftrace_vprintk);
 
 static void *
-t_next(struct seq_file *m, void *v, loff_t *pos)
+t_start(struct seq_file *m, loff_t *pos)
 {
-	const char **fmt = m->private;
-	const char **next = fmt;
-
-	(*pos)++;
+	const char **fmt = __start___trace_bprintk_fmt + *pos;
 
 	if ((unsigned long)fmt >= (unsigned long)__stop___trace_bprintk_fmt)
 		return NULL;
-
-	next = fmt;
-	m->private = ++next;
-
 	return fmt;
 }
 
-static void *t_start(struct seq_file *m, loff_t *pos)
+static void *t_next(struct seq_file *m, void * v, loff_t *pos)
 {
-	return t_next(m, NULL, pos);
+	(*pos)++;
+	return t_start(m, pos);
 }
 
 static int t_show(struct seq_file *m, void *v)
@@ -224,15 +218,7 @@ static const struct seq_operations show_format_seq_ops = {
 static int
 ftrace_formats_open(struct inode *inode, struct file *file)
 {
-	int ret;
-
-	ret = seq_open(file, &show_format_seq_ops);
-	if (!ret) {
-		struct seq_file *m = file->private_data;
-
-		m->private = __start___trace_bprintk_fmt;
-	}
-	return ret;
+	return seq_open(file, &show_format_seq_ops);
 }
 
 static const struct file_operations ftrace_formats_fops = {
diff --git a/kernel/trace/trace_stat.c b/kernel/trace/trace_stat.c
index c00643733f4c..e66f5e493342 100644
--- a/kernel/trace/trace_stat.c
+++ b/kernel/trace/trace_stat.c
@@ -199,17 +199,13 @@ static void *stat_seq_start(struct seq_file *s, loff_t *pos)
 	mutex_lock(&session->stat_mutex);
 
 	/* If we are in the beginning of the file, print the headers */
-	if (!*pos && session->ts->stat_headers) {
-		(*pos)++;
+	if (!*pos && session->ts->stat_headers)
 		return SEQ_START_TOKEN;
-	}
 
 	node = rb_first(&session->stat_root);
 	for (i = 0; node && i < *pos; i++)
 		node = rb_next(node);
 
-	(*pos)++;
-
 	return node;
 }