Merge branch 'master' into next

kernel/fork.c

@@ -568,18 +568,18 @@ void mm_release(struct task_struct *tsk, struct mm_struct *mm)
 	 * the value intact in a core dump, and to save the unnecessary
 	 * trouble otherwise.  Userland only wants this done for a sys_exit.
 	 */
-	if (tsk->clear_child_tid
-	    && !(tsk->flags & PF_SIGNALED)
-	    && atomic_read(&mm->mm_users) > 1) {
-		u32 __user * tidptr = tsk->clear_child_tid;
+	if (tsk->clear_child_tid) {
+		if (!(tsk->flags & PF_SIGNALED) &&
+		    atomic_read(&mm->mm_users) > 1) {
+			/*
+			 * We don't check the error code - if userspace has
+			 * not set up a proper pointer then tough luck.
+			 */
+			put_user(0, tsk->clear_child_tid);
+			sys_futex(tsk->clear_child_tid, FUTEX_WAKE,
+					1, NULL, NULL, 0);
+		}
 		tsk->clear_child_tid = NULL;
-
-		/*
-		 * We don't check the error code - if userspace has
-		 * not set up a proper pointer then tough luck.
-		 */
-		put_user(0, tidptr);
-		sys_futex(tidptr, FUTEX_WAKE, 1, NULL, NULL, 0);
 	}
 }
 

kernel/irq/numa_migrate.c

@@ -107,8 +107,8 @@ out_unlock:
 
 struct irq_desc *move_irq_desc(struct irq_desc *desc, int node)
 {
-	/* those all static, do move them */
-	if (desc->irq < NR_IRQS_LEGACY)
+	/* those static or target node is -1, do not move them */
+	if (desc->irq < NR_IRQS_LEGACY || node == -1)
 		return desc;
 
 	if (desc->node != node)

kernel/lockdep_proc.c

@@ -758,7 +758,8 @@ static int __init lockdep_proc_init(void)
 		    &proc_lockdep_stats_operations);
 
 #ifdef CONFIG_LOCK_STAT
-	proc_create("lock_stat", S_IRUSR, NULL, &proc_lock_stat_operations);
+	proc_create("lock_stat", S_IRUSR | S_IWUSR, NULL,
+		    &proc_lock_stat_operations);
 #endif
 
 	return 0;

kernel/perf_counter.c

@@ -1104,7 +1104,7 @@ static void perf_counter_sync_stat(struct perf_counter_context *ctx,
 		__perf_counter_sync_stat(counter, next_counter);
 
 		counter = list_next_entry(counter, event_entry);
-		next_counter = list_next_entry(counter, event_entry);
+		next_counter = list_next_entry(next_counter, event_entry);
 	}
 }
 
@@ -2714,6 +2714,18 @@ static void perf_counter_output(struct perf_counter *counter, int nmi,
 			header.size += sizeof(u64);
 	}
 
+	if (sample_type & PERF_SAMPLE_RAW) {
+		int size = sizeof(u32);
+
+		if (data->raw)
+			size += data->raw->size;
+		else
+			size += sizeof(u32);
+
+		WARN_ON_ONCE(size & (sizeof(u64)-1));
+		header.size += size;
+	}
+
 	ret = perf_output_begin(&handle, counter, header.size, nmi, 1);
 	if (ret)
 		return;
@@ -2777,6 +2789,22 @@ static void perf_counter_output(struct perf_counter *counter, int nmi,
 		}
 	}
 
+	if (sample_type & PERF_SAMPLE_RAW) {
+		if (data->raw) {
+			perf_output_put(&handle, data->raw->size);
+			perf_output_copy(&handle, data->raw->data, data->raw->size);
+		} else {
+			struct {
+				u32	size;
+				u32	data;
+			} raw = {
+				.size = sizeof(u32),
+				.data = 0,
+			};
+			perf_output_put(&handle, raw);
+		}
+	}
+
 	perf_output_end(&handle);
 }
 
@@ -2840,7 +2868,8 @@ perf_counter_read_event(struct perf_counter *counter,
  */
 
 struct perf_task_event {
-	struct task_struct	*task;
+	struct task_struct		*task;
+	struct perf_counter_context	*task_ctx;
 
 	struct {
 		struct perf_event_header	header;
@@ -2900,24 +2929,23 @@ static void perf_counter_task_ctx(struct perf_counter_context *ctx,
 static void perf_counter_task_event(struct perf_task_event *task_event)
 {
 	struct perf_cpu_context *cpuctx;
-	struct perf_counter_context *ctx;
+	struct perf_counter_context *ctx = task_event->task_ctx;
 
 	cpuctx = &get_cpu_var(perf_cpu_context);
 	perf_counter_task_ctx(&cpuctx->ctx, task_event);
 	put_cpu_var(perf_cpu_context);
 
 	rcu_read_lock();
-	/*
-	 * doesn't really matter which of the child contexts the
-	 * events ends up in.
-	 */
-	ctx = rcu_dereference(current->perf_counter_ctxp);
+	if (!ctx)
+		ctx = rcu_dereference(task_event->task->perf_counter_ctxp);
 	if (ctx)
 		perf_counter_task_ctx(ctx, task_event);
 	rcu_read_unlock();
 }
 
-static void perf_counter_task(struct task_struct *task, int new)
+static void perf_counter_task(struct task_struct *task,
+			      struct perf_counter_context *task_ctx,
+			      int new)
 {
 	struct perf_task_event task_event;
 
@@ -2927,8 +2955,9 @@ static void perf_counter_task(struct task_struct *task, int new)
 		return;
 
 	task_event = (struct perf_task_event){
-		.task	= task,
-		.event  = {
+		.task	  = task,
+		.task_ctx = task_ctx,
+		.event    = {
 			.header = {
 				.type = new ? PERF_EVENT_FORK : PERF_EVENT_EXIT,
 				.misc = 0,
@@ -2946,7 +2975,7 @@ static void perf_counter_task(struct task_struct *task, int new)
 
 void perf_counter_fork(struct task_struct *task)
 {
-	perf_counter_task(task, 1);
+	perf_counter_task(task, NULL, 1);
 }
 
 /*
@@ -3335,87 +3364,81 @@ int perf_counter_overflow(struct perf_counter *counter, int nmi,
  * Generic software counter infrastructure
  */
 
-static void perf_swcounter_update(struct perf_counter *counter)
+/*
+ * We directly increment counter->count and keep a second value in
+ * counter->hw.period_left to count intervals. This period counter
+ * is kept in the range [-sample_period, 0] so that we can use the
+ * sign as trigger.
+ */
+
+static u64 perf_swcounter_set_period(struct perf_counter *counter)
 {
 	struct hw_perf_counter *hwc = &counter->hw;
-	u64 prev, now;
-	s64 delta;
+	u64 period = hwc->last_period;
+	u64 nr, offset;
+	s64 old, val;
+
+	hwc->last_period = hwc->sample_period;
 
 again:
-	prev = atomic64_read(&hwc->prev_count);
-	now = atomic64_read(&hwc->count);
-	if (atomic64_cmpxchg(&hwc->prev_count, prev, now) != prev)
+	old = val = atomic64_read(&hwc->period_left);
+	if (val < 0)
+		return 0;
+
+	nr = div64_u64(period + val, period);
+	offset = nr * period;
+	val -= offset;
+	if (atomic64_cmpxchg(&hwc->period_left, old, val) != old)
 		goto again;
 
-	delta = now - prev;
-
-	atomic64_add(delta, &counter->count);
-	atomic64_sub(delta, &hwc->period_left);
-}
-
-static void perf_swcounter_set_period(struct perf_counter *counter)
-{
-	struct hw_perf_counter *hwc = &counter->hw;
-	s64 left = atomic64_read(&hwc->period_left);
-	s64 period = hwc->sample_period;
-
-	if (unlikely(left <= -period)) {
-		left = period;
-		atomic64_set(&hwc->period_left, left);
-		hwc->last_period = period;
-	}
-
-	if (unlikely(left <= 0)) {
-		left += period;
-		atomic64_add(period, &hwc->period_left);
-		hwc->last_period = period;
-	}
-
-	atomic64_set(&hwc->prev_count, -left);
-	atomic64_set(&hwc->count, -left);
-}
-
-static enum hrtimer_restart perf_swcounter_hrtimer(struct hrtimer *hrtimer)
-{
-	enum hrtimer_restart ret = HRTIMER_RESTART;
-	struct perf_sample_data data;
-	struct perf_counter *counter;
-	u64 period;
-
-	counter	= container_of(hrtimer, struct perf_counter, hw.hrtimer);
-	counter->pmu->read(counter);
-
-	data.addr = 0;
-	data.regs = get_irq_regs();
-	/*
-	 * In case we exclude kernel IPs or are somehow not in interrupt
-	 * context, provide the next best thing, the user IP.
-	 */
-	if ((counter->attr.exclude_kernel || !data.regs) &&
-			!counter->attr.exclude_user)
-		data.regs = task_pt_regs(current);
-
-	if (data.regs) {
-		if (perf_counter_overflow(counter, 0, &data))
-			ret = HRTIMER_NORESTART;
-	}
-
-	period = max_t(u64, 10000, counter->hw.sample_period);
-	hrtimer_forward_now(hrtimer, ns_to_ktime(period));
-
-	return ret;
+	return nr;
 }
 
 static void perf_swcounter_overflow(struct perf_counter *counter,
 				    int nmi, struct perf_sample_data *data)
 {
-	data->period = counter->hw.last_period;
+	struct hw_perf_counter *hwc = &counter->hw;
+	u64 overflow;
 
-	perf_swcounter_update(counter);
-	perf_swcounter_set_period(counter);
-	if (perf_counter_overflow(counter, nmi, data))
-		/* soft-disable the counter */
-		;
+	data->period = counter->hw.last_period;
+	overflow = perf_swcounter_set_period(counter);
+
+	if (hwc->interrupts == MAX_INTERRUPTS)
+		return;
+
+	for (; overflow; overflow--) {
+		if (perf_counter_overflow(counter, nmi, data)) {
+			/*
+			 * We inhibit the overflow from happening when
+			 * hwc->interrupts == MAX_INTERRUPTS.
+			 */
+			break;
+		}
+	}
+}
+
+static void perf_swcounter_unthrottle(struct perf_counter *counter)
+{
+	/*
+	 * Nothing to do, we already reset hwc->interrupts.
+	 */
+}
+
+static void perf_swcounter_add(struct perf_counter *counter, u64 nr,
+			       int nmi, struct perf_sample_data *data)
+{
+	struct hw_perf_counter *hwc = &counter->hw;
+
+	atomic64_add(nr, &counter->count);
+
+	if (!hwc->sample_period)
+		return;
+
+	if (!data->regs)
+		return;
+
+	if (!atomic64_add_negative(nr, &hwc->period_left))
+		perf_swcounter_overflow(counter, nmi, data);
 }
 
 static int perf_swcounter_is_counting(struct perf_counter *counter)
@@ -3479,15 +3502,6 @@ static int perf_swcounter_match(struct perf_counter *counter,
 	return 1;
 }
 
-static void perf_swcounter_add(struct perf_counter *counter, u64 nr,
-			       int nmi, struct perf_sample_data *data)
-{
-	int neg = atomic64_add_negative(nr, &counter->hw.count);
-
-	if (counter->hw.sample_period && !neg && data->regs)
-		perf_swcounter_overflow(counter, nmi, data);
-}
-
 static void perf_swcounter_ctx_event(struct perf_counter_context *ctx,
 				     enum perf_type_id type,
 				     u32 event, u64 nr, int nmi,
@@ -3566,26 +3580,65 @@ void __perf_swcounter_event(u32 event, u64 nr, int nmi,
 
 static void perf_swcounter_read(struct perf_counter *counter)
 {
-	perf_swcounter_update(counter);
 }
 
 static int perf_swcounter_enable(struct perf_counter *counter)
 {
-	perf_swcounter_set_period(counter);
+	struct hw_perf_counter *hwc = &counter->hw;
+
+	if (hwc->sample_period) {
+		hwc->last_period = hwc->sample_period;
+		perf_swcounter_set_period(counter);
+	}
 	return 0;
 }
 
 static void perf_swcounter_disable(struct perf_counter *counter)
 {
-	perf_swcounter_update(counter);
 }
 
 static const struct pmu perf_ops_generic = {
 	.enable		= perf_swcounter_enable,
 	.disable	= perf_swcounter_disable,
 	.read		= perf_swcounter_read,
+	.unthrottle	= perf_swcounter_unthrottle,
 };
 
+/*
+ * hrtimer based swcounter callback
+ */
+
+static enum hrtimer_restart perf_swcounter_hrtimer(struct hrtimer *hrtimer)
+{
+	enum hrtimer_restart ret = HRTIMER_RESTART;
+	struct perf_sample_data data;
+	struct perf_counter *counter;
+	u64 period;
+
+	counter	= container_of(hrtimer, struct perf_counter, hw.hrtimer);
+	counter->pmu->read(counter);
+
+	data.addr = 0;
+	data.regs = get_irq_regs();
+	/*
+	 * In case we exclude kernel IPs or are somehow not in interrupt
+	 * context, provide the next best thing, the user IP.
+	 */
+	if ((counter->attr.exclude_kernel || !data.regs) &&
+			!counter->attr.exclude_user)
+		data.regs = task_pt_regs(current);
+
+	if (data.regs) {
+		if (perf_counter_overflow(counter, 0, &data))
+			ret = HRTIMER_NORESTART;
+	}
+
+	period = max_t(u64, 10000, counter->hw.sample_period);
+	hrtimer_forward_now(hrtimer, ns_to_ktime(period));
+
+	return ret;
+}
+
 /*
  * Software counter: cpu wall time clock
  */
@@ -3703,17 +3756,24 @@ static const struct pmu perf_ops_task_clock = {
 };
 
 #ifdef CONFIG_EVENT_PROFILE
-void perf_tpcounter_event(int event_id)
+void perf_tpcounter_event(int event_id, u64 addr, u64 count, void *record,
+			  int entry_size)
 {
+	struct perf_raw_record raw = {
+		.size = entry_size,
+		.data = record,
+	};
+
 	struct perf_sample_data data = {
 		.regs = get_irq_regs(),
-		.addr = 0,
+		.addr = addr,
+		.raw = &raw,
 	};
 
 	if (!data.regs)
 		data.regs = task_pt_regs(current);
 
-	do_perf_swcounter_event(PERF_TYPE_TRACEPOINT, event_id, 1, 1, &data);
+	do_perf_swcounter_event(PERF_TYPE_TRACEPOINT, event_id, count, 1, &data);
 }
 EXPORT_SYMBOL_GPL(perf_tpcounter_event);
 
@@ -3727,6 +3787,14 @@ static void tp_perf_counter_destroy(struct perf_counter *counter)
 
 static const struct pmu *tp_perf_counter_init(struct perf_counter *counter)
 {
+	/*
+	 * Raw tracepoint data is a severe data leak, only allow root to
+	 * have these.
+	 */
+	if ((counter->attr.sample_type & PERF_SAMPLE_RAW) &&
+			!capable(CAP_SYS_ADMIN))
+		return ERR_PTR(-EPERM);
+
 	if (ftrace_profile_enable(counter->attr.config))
 		return NULL;
 
@@ -4269,7 +4337,7 @@ void perf_counter_exit_task(struct task_struct *child)
 	unsigned long flags;
 
 	if (likely(!child->perf_counter_ctxp)) {
-		perf_counter_task(child, 0);
+		perf_counter_task(child, NULL, 0);
 		return;
 	}
 
@@ -4289,6 +4357,7 @@ void perf_counter_exit_task(struct task_struct *child)
 	 * incremented the context's refcount before we do put_ctx below.
 	 */
 	spin_lock(&child_ctx->lock);
+	child->perf_counter_ctxp = NULL;
 	/*
 	 * If this context is a clone; unclone it so it can't get
 	 * swapped to another process while we're removing all
@@ -4302,9 +4371,7 @@ void perf_counter_exit_task(struct task_struct *child)
 	 * won't get any samples after PERF_EVENT_EXIT. We can however still
 	 * get a few PERF_EVENT_READ events.
 	 */
-	perf_counter_task(child, 0);
-
-	child->perf_counter_ctxp = NULL;
+	perf_counter_task(child, child_ctx, 0);
 
 	/*
 	 * We can recurse on the same lock type through:

kernel/posix-cpu-timers.c

@@ -521,11 +521,12 @@ void posix_cpu_timers_exit(struct task_struct *tsk)
 }
 void posix_cpu_timers_exit_group(struct task_struct *tsk)
 {
-	struct task_cputime cputime;
+	struct signal_struct *const sig = tsk->signal;
 
-	thread_group_cputimer(tsk, &cputime);
 	cleanup_timers(tsk->signal->cpu_timers,
-		       cputime.utime, cputime.stime, cputime.sum_exec_runtime);
+		       cputime_add(tsk->utime, sig->utime),
+		       cputime_add(tsk->stime, sig->stime),
+		       tsk->se.sum_exec_runtime + sig->sum_sched_runtime);
 }
 
 static void clear_dead_task(struct k_itimer *timer, union cpu_time_count now)

kernel/rtmutex.c

@@ -1039,16 +1039,14 @@ int rt_mutex_start_proxy_lock(struct rt_mutex *lock,
 	if (!rt_mutex_owner(lock) || try_to_steal_lock(lock, task)) {
 		/* We got the lock for task. */
 		debug_rt_mutex_lock(lock);
-
 		rt_mutex_set_owner(lock, task, 0);
-
+		spin_unlock(&lock->wait_lock);
 		rt_mutex_deadlock_account_lock(lock, task);
 		return 1;
 	}
 
 	ret = task_blocks_on_rt_mutex(lock, waiter, task, detect_deadlock);
 
-
 	if (ret && !waiter->task) {
 		/*
 		 * Reset the return value. We might have

kernel/smp.c

@@ -57,7 +57,7 @@ hotplug_cfd(struct notifier_block *nfb, unsigned long action, void *hcpu)
 			return NOTIFY_BAD;
 		break;
 
-#ifdef CONFIG_CPU_HOTPLUG
+#ifdef CONFIG_HOTPLUG_CPU
 	case CPU_UP_CANCELED:
 	case CPU_UP_CANCELED_FROZEN:
 

kernel/trace/ring_buffer.c

@@ -735,6 +735,7 @@ ring_buffer_free(struct ring_buffer *buffer)
 
 	put_online_cpus();
 
+	kfree(buffer->buffers);
 	free_cpumask_var(buffer->cpumask);
 
 	kfree(buffer);
@@ -1785,7 +1786,7 @@ void ring_buffer_discard_commit(struct ring_buffer *buffer,
 	 */
 	RB_WARN_ON(buffer, !local_read(&cpu_buffer->committing));
 
-	if (!rb_try_to_discard(cpu_buffer, event))
+	if (rb_try_to_discard(cpu_buffer, event))
 		goto out;
 
 	/*
@@ -2383,7 +2384,6 @@ rb_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts)
 		 * the box. Return the padding, and we will release
 		 * the current locks, and try again.
 		 */
-		rb_advance_reader(cpu_buffer);
 		return event;
 
 	case RINGBUF_TYPE_TIME_EXTEND:
@@ -2486,7 +2486,7 @@ static inline int rb_ok_to_lock(void)
 	 * buffer too. A one time deal is all you get from reading
 	 * the ring buffer from an NMI.
 	 */
-	if (likely(!in_nmi() && !oops_in_progress))
+	if (likely(!in_nmi()))
 		return 1;
 
 	tracing_off_permanent();
@@ -2519,6 +2519,8 @@ ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts)
 	if (dolock)
 		spin_lock(&cpu_buffer->reader_lock);
 	event = rb_buffer_peek(buffer, cpu, ts);
+	if (event && event->type_len == RINGBUF_TYPE_PADDING)
+		rb_advance_reader(cpu_buffer);
 	if (dolock)
 		spin_unlock(&cpu_buffer->reader_lock);
 	local_irq_restore(flags);
@@ -2590,12 +2592,9 @@ ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts)
 		spin_lock(&cpu_buffer->reader_lock);
 
 	event = rb_buffer_peek(buffer, cpu, ts);
-	if (!event)
-		goto out_unlock;
+	if (event)
+		rb_advance_reader(cpu_buffer);
 
-	rb_advance_reader(cpu_buffer);
-
- out_unlock:
 	if (dolock)
 		spin_unlock(&cpu_buffer->reader_lock);
 	local_irq_restore(flags);

kernel/trace/trace.c

@@ -848,6 +848,7 @@ tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags,
 		((pc & SOFTIRQ_MASK) ? TRACE_FLAG_SOFTIRQ : 0) |
 		(need_resched() ? TRACE_FLAG_NEED_RESCHED : 0);
 }
+EXPORT_SYMBOL_GPL(tracing_generic_entry_update);
 
 struct ring_buffer_event *trace_buffer_lock_reserve(struct trace_array *tr,
 						    int type,

kernel/trace/trace.h

@@ -438,10 +438,6 @@ struct trace_entry *tracing_get_trace_entry(struct trace_array *tr,
 struct trace_entry *trace_find_next_entry(struct trace_iterator *iter,
 					  int *ent_cpu, u64 *ent_ts);
 
-void tracing_generic_entry_update(struct trace_entry *entry,
-				  unsigned long flags,
-				  int pc);
-
 void default_wait_pipe(struct trace_iterator *iter);
 void poll_wait_pipe(struct trace_iterator *iter);
 

kernel/trace/trace_event_profile.c

@@ -14,7 +14,7 @@ int ftrace_profile_enable(int event_id)
 
 	mutex_lock(&event_mutex);
 	list_for_each_entry(event, &ftrace_events, list) {
-		if (event->id == event_id) {
+		if (event->id == event_id && event->profile_enable) {
 			ret = event->profile_enable(event);
 			break;
 		}

kernel/trace/trace_events.c

@@ -940,7 +940,7 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events,
 		entry = trace_create_file("enable", 0644, call->dir, call,
 					  enable);
 
-	if (call->id)
+	if (call->id && call->profile_enable)
 		entry = trace_create_file("id", 0444, call->dir, call,
 					  id);
 

kernel/trace/trace_events_filter.c

@@ -624,9 +624,6 @@ static int filter_add_subsystem_pred(struct filter_parse_state *ps,
 		return -ENOSPC;
 	}
 
-	filter->preds[filter->n_preds] = pred;
-	filter->n_preds++;
-
 	list_for_each_entry(call, &ftrace_events, list) {
 
 		if (!call->define_fields)
@@ -643,6 +640,9 @@ static int filter_add_subsystem_pred(struct filter_parse_state *ps,
 		}
 		replace_filter_string(call->filter, filter_string);
 	}
+
+	filter->preds[filter->n_preds] = pred;
+	filter->n_preds++;
 out:
 	return err;
 }
@@ -1029,12 +1029,17 @@ static int replace_preds(struct event_subsystem *system,
 
 		if (elt->op == OP_AND || elt->op == OP_OR) {
 			pred = create_logical_pred(elt->op);
+			if (!pred)
+				return -ENOMEM;
 			if (call) {
 				err = filter_add_pred(ps, call, pred);
 				filter_free_pred(pred);
-			} else
+			} else {
 				err = filter_add_subsystem_pred(ps, system,
 							pred, filter_string);
+				if (err)
+					filter_free_pred(pred);
+			}
 			if (err)
 				return err;
 
@@ -1048,12 +1053,17 @@ static int replace_preds(struct event_subsystem *system,
 		}
 
 		pred = create_pred(elt->op, operand1, operand2);
+		if (!pred)
+			return -ENOMEM;
 		if (call) {
 			err = filter_add_pred(ps, call, pred);
 			filter_free_pred(pred);
-		} else
+		} else {
 			err = filter_add_subsystem_pred(ps, system, pred,
 							filter_string);
+			if (err)
+				filter_free_pred(pred);
+		}
 		if (err)
 			return err;