Merge branch 'linus' into irq/core

Bring in upstream updates for patches which depend on them

8 files changed, 129 insertions, 52 deletions

diff --git a/kernel/events/core.c b/kernel/events/core.c
index f548f69..b11756f 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1243,11 +1243,7 @@ static inline void perf_event__state_init(struct perf_event *event)
 					      PERF_EVENT_STATE_INACTIVE;
 }
 
-/*
- * Called at perf_event creation and when events are attached/detached from a
- * group.
- */
-static void perf_event__read_size(struct perf_event *event)
+static void __perf_event_read_size(struct perf_event *event, int nr_siblings)
 {
 	int entry = sizeof(u64); /* value */
 	int size = 0;
@@ -1263,7 +1259,7 @@ static void perf_event__read_size(struct perf_event *event)
 		entry += sizeof(u64);
 
 	if (event->attr.read_format & PERF_FORMAT_GROUP) {
-		nr += event->group_leader->nr_siblings;
+		nr += nr_siblings;
 		size += sizeof(u64);
 	}
 
@@ -1271,14 +1267,11 @@ static void perf_event__read_size(struct perf_event *event)
 	event->read_size = size;
 }
 
-static void perf_event__header_size(struct perf_event *event)
+static void __perf_event_header_size(struct perf_event *event, u64 sample_type)
 {
 	struct perf_sample_data *data;
-	u64 sample_type = event->attr.sample_type;
 	u16 size = 0;
 
-	perf_event__read_size(event);
-
 	if (sample_type & PERF_SAMPLE_IP)
 		size += sizeof(data->ip);
 
@@ -1303,6 +1296,17 @@ static void perf_event__header_size(struct perf_event *event)
 	event->header_size = size;
 }
 
+/*
+ * Called at perf_event creation and when events are attached/detached from a
+ * group.
+ */
+static void perf_event__header_size(struct perf_event *event)
+{
+	__perf_event_read_size(event,
+			       event->group_leader->nr_siblings);
+	__perf_event_header_size(event, event->attr.sample_type);
+}
+
 static void perf_event__id_header_size(struct perf_event *event)
 {
 	struct perf_sample_data *data;
@@ -1330,6 +1334,27 @@ static void perf_event__id_header_size(struct perf_event *event)
 	event->id_header_size = size;
 }
 
+static bool perf_event_validate_size(struct perf_event *event)
+{
+	/*
+	 * The values computed here will be over-written when we actually
+	 * attach the event.
+	 */
+	__perf_event_read_size(event, event->group_leader->nr_siblings + 1);
+	__perf_event_header_size(event, event->attr.sample_type & ~PERF_SAMPLE_READ);
+	perf_event__id_header_size(event);
+
+	/*
+	 * Sum the lot; should not exceed the 64k limit we have on records.
+	 * Conservative limit to allow for callchains and other variable fields.
+	 */
+	if (event->read_size + event->header_size +
+	    event->id_header_size + sizeof(struct perf_event_header) >= 16*1024)
+		return false;
+
+	return true;
+}
+
 static void perf_group_attach(struct perf_event *event)
 {
 	struct perf_event *group_leader = event->group_leader, *pos;
@@ -8297,13 +8322,35 @@ SYSCALL_DEFINE5(perf_event_open,
 
 	if (move_group) {
 		gctx = group_leader->ctx;
+		mutex_lock_double(&gctx->mutex, &ctx->mutex);
+	} else {
+		mutex_lock(&ctx->mutex);
+	}
 
+	if (!perf_event_validate_size(event)) {
+		err = -E2BIG;
+		goto err_locked;
+	}
+
+	/*
+	 * Must be under the same ctx::mutex as perf_install_in_context(),
+	 * because we need to serialize with concurrent event creation.
+	 */
+	if (!exclusive_event_installable(event, ctx)) {
+		/* exclusive and group stuff are assumed mutually exclusive */
+		WARN_ON_ONCE(move_group);
+
+		err = -EBUSY;
+		goto err_locked;
+	}
+
+	WARN_ON_ONCE(ctx->parent_ctx);
+
+	if (move_group) {
 		/*
 		 * See perf_event_ctx_lock() for comments on the details
 		 * of swizzling perf_event::ctx.
 		 */
-		mutex_lock_double(&gctx->mutex, &ctx->mutex);
-
 		perf_remove_from_context(group_leader, false);
 
 		list_for_each_entry(sibling, &group_leader->sibling_list,
@@ -8311,13 +8358,7 @@ SYSCALL_DEFINE5(perf_event_open,
 			perf_remove_from_context(sibling, false);
 			put_ctx(gctx);
 		}
-	} else {
-		mutex_lock(&ctx->mutex);
-	}
 
-	WARN_ON_ONCE(ctx->parent_ctx);
-
-	if (move_group) {
 		/*
 		 * Wait for everybody to stop referencing the events through
 		 * the old lists, before installing it on new lists.
@@ -8349,22 +8390,29 @@ SYSCALL_DEFINE5(perf_event_open,
 		perf_event__state_init(group_leader);
 		perf_install_in_context(ctx, group_leader, group_leader->cpu);
 		get_ctx(ctx);
-	}
 
-	if (!exclusive_event_installable(event, ctx)) {
-		err = -EBUSY;
-		mutex_unlock(&ctx->mutex);
-		fput(event_file);
-		goto err_context;
+		/*
+		 * Now that all events are installed in @ctx, nothing
+		 * references @gctx anymore, so drop the last reference we have
+		 * on it.
+		 */
+		put_ctx(gctx);
 	}
 
+	/*
+	 * Precalculate sample_data sizes; do while holding ctx::mutex such
+	 * that we're serialized against further additions and before
+	 * perf_install_in_context() which is the point the event is active and
+	 * can use these values.
+	 */
+	perf_event__header_size(event);
+	perf_event__id_header_size(event);
+
 	perf_install_in_context(ctx, event, event->cpu);
 	perf_unpin_context(ctx);
 
-	if (move_group) {
+	if (move_group)
 		mutex_unlock(&gctx->mutex);
-		put_ctx(gctx);
-	}
 	mutex_unlock(&ctx->mutex);
 
 	put_online_cpus();
@@ -8376,12 +8424,6 @@ SYSCALL_DEFINE5(perf_event_open,
 	mutex_unlock(&current->perf_event_mutex);
 
 	/*
-	 * Precalculate sample_data sizes
-	 */
-	perf_event__header_size(event);
-	perf_event__id_header_size(event);
-
-	/*
 	 * Drop the reference on the group_event after placing the
 	 * new event on the sibling_list. This ensures destruction
 	 * of the group leader will find the pointer to itself in
@@ -8391,6 +8433,12 @@ SYSCALL_DEFINE5(perf_event_open,
 	fd_install(event_fd, event_file);
 	return event_fd;
 
+err_locked:
+	if (move_group)
+		mutex_unlock(&gctx->mutex);
+	mutex_unlock(&ctx->mutex);
+/* err_file: */
+	fput(event_file);
 err_context:
 	perf_unpin_context(ctx);
 	put_ctx(ctx);
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index ea7b5fd..a302cf9 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -22,7 +22,6 @@
 
 /**
  * handle_bad_irq - handle spurious and unhandled irqs
- * @irq:       the interrupt number
  * @desc:      description of the interrupt
  *
  * Handles spurious and unhandled IRQ's. It also prints a debugmessage.
@@ -35,6 +34,7 @@ void handle_bad_irq(struct irq_desc *desc)
 	kstat_incr_irqs_this_cpu(desc);
 	ack_bad_irq(irq);
 }
+EXPORT_SYMBOL_GPL(handle_bad_irq);
 
 /*
  * Special, empty irq handler:
diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c
index 7d60905..a916cf1 100644
--- a/kernel/irq/proc.c
+++ b/kernel/irq/proc.c
@@ -12,6 +12,7 @@
 #include <linux/seq_file.h>
 #include <linux/interrupt.h>
 #include <linux/kernel_stat.h>
+#include <linux/mutex.h>
 
 #include "internals.h"
 
@@ -323,18 +324,29 @@ void register_handler_proc(unsigned int irq, struct irqaction *action)
 
 void register_irq_proc(unsigned int irq, struct irq_desc *desc)
 {
+	static DEFINE_MUTEX(register_lock);
 	char name [MAX_NAMELEN];
 
-	if (!root_irq_dir || (desc->irq_data.chip == &no_irq_chip) || desc->dir)
+	if (!root_irq_dir || (desc->irq_data.chip == &no_irq_chip))
 		return;
 
+	/*
+	 * irq directories are registered only when a handler is
+	 * added, not when the descriptor is created, so multiple
+	 * tasks might try to register at the same time.
+	 */
+	mutex_lock(&register_lock);
+
+	if (desc->dir)
+		goto out_unlock;
+
 	memset(name, 0, MAX_NAMELEN);
 	sprintf(name, "%d", irq);
 
 	/* create /proc/irq/1234 */
 	desc->dir = proc_mkdir(name, root_irq_dir);
 	if (!desc->dir)
-		return;
+		goto out_unlock;
 
 #ifdef CONFIG_SMP
 	/* create /proc/irq/<irq>/smp_affinity */
@@ -355,6 +367,9 @@ void register_irq_proc(unsigned int irq, struct irq_desc *desc)
 
 	proc_create_data("spurious", 0444, desc->dir,
 			 &irq_spurious_proc_fops, (void *)(long)irq);
+
+out_unlock:
+	mutex_unlock(&register_lock);
 }
 
 void unregister_irq_proc(unsigned int irq, struct irq_desc *desc)
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 8acfbf7..4e49cc4 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -3068,7 +3068,7 @@ static int __lock_is_held(struct lockdep_map *lock);
 static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 			  int trylock, int read, int check, int hardirqs_off,
 			  struct lockdep_map *nest_lock, unsigned long ip,
-			  int references)
+			  int references, int pin_count)
 {
 	struct task_struct *curr = current;
 	struct lock_class *class = NULL;
@@ -3157,7 +3157,7 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 	hlock->waittime_stamp = 0;
 	hlock->holdtime_stamp = lockstat_clock();
 #endif
-	hlock->pin_count = 0;
+	hlock->pin_count = pin_count;
 
 	if (check && !mark_irqflags(curr, hlock))
 		return 0;
@@ -3343,7 +3343,7 @@ found_it:
 			hlock_class(hlock)->subclass, hlock->trylock,
 				hlock->read, hlock->check, hlock->hardirqs_off,
 				hlock->nest_lock, hlock->acquire_ip,
-				hlock->references))
+				hlock->references, hlock->pin_count))
 			return 0;
 	}
 
@@ -3433,7 +3433,7 @@ found_it:
 			hlock_class(hlock)->subclass, hlock->trylock,
 				hlock->read, hlock->check, hlock->hardirqs_off,
 				hlock->nest_lock, hlock->acquire_ip,
-				hlock->references))
+				hlock->references, hlock->pin_count))
 			return 0;
 	}
 
@@ -3583,7 +3583,7 @@ void lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 	current->lockdep_recursion = 1;
 	trace_lock_acquire(lock, subclass, trylock, read, check, nest_lock, ip);
 	__lock_acquire(lock, subclass, trylock, read, check,
-		       irqs_disabled_flags(flags), nest_lock, ip, 0);
+		       irqs_disabled_flags(flags), nest_lock, ip, 0, 0);
 	current->lockdep_recursion = 0;
 	raw_local_irq_restore(flags);
 }
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 9f75f25..775d36c 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -3868,6 +3868,7 @@ static void rcu_init_new_rnp(struct rcu_node *rnp_leaf)
 static void __init
 rcu_boot_init_percpu_data(int cpu, struct rcu_state *rsp)
 {
+	static struct lock_class_key rcu_exp_sched_rdp_class;
 	unsigned long flags;
 	struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
 	struct rcu_node *rnp = rcu_get_root(rsp);
@@ -3883,6 +3884,10 @@ rcu_boot_init_percpu_data(int cpu, struct rcu_state *rsp)
 	mutex_init(&rdp->exp_funnel_mutex);
 	rcu_boot_init_nocb_percpu_data(rdp);
 	raw_spin_unlock_irqrestore(&rnp->lock, flags);
+	if (rsp == &rcu_sched_state)
+		lockdep_set_class_and_name(&rdp->exp_funnel_mutex,
+					   &rcu_exp_sched_rdp_class,
+					   "rcu_data_exp_sched");
 }
 
 /*
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 2f9c928..10a8faa 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2517,11 +2517,11 @@ static struct rq *finish_task_switch(struct task_struct *prev)
 	 * If a task dies, then it sets TASK_DEAD in tsk->state and calls
 	 * schedule one last time. The schedule call will never return, and
 	 * the scheduled task must drop that reference.
-	 * The test for TASK_DEAD must occur while the runqueue locks are
-	 * still held, otherwise prev could be scheduled on another cpu, die
-	 * there before we look at prev->state, and then the reference would
-	 * be dropped twice.
-	 *		Manfred Spraul <manfred@colorfullife.com>
+	 *
+	 * We must observe prev->state before clearing prev->on_cpu (in
+	 * finish_lock_switch), otherwise a concurrent wakeup can get prev
+	 * running on another CPU and we could rave with its RUNNING -> DEAD
+	 * transition, resulting in a double drop.
 	 */
 	prev_state = prev->state;
 	vtime_task_switch(prev);
@@ -4934,7 +4934,15 @@ void init_idle(struct task_struct *idle, int cpu)
 	idle->state = TASK_RUNNING;
 	idle->se.exec_start = sched_clock();
 
-	do_set_cpus_allowed(idle, cpumask_of(cpu));
+#ifdef CONFIG_SMP
+	/*
+	 * Its possible that init_idle() gets called multiple times on a task,
+	 * in that case do_set_cpus_allowed() will not do the right thing.
+	 *
+	 * And since this is boot we can forgo the serialization.
+	 */
+	set_cpus_allowed_common(idle, cpumask_of(cpu));
+#endif
 	/*
 	 * We're having a chicken and egg problem, even though we are
 	 * holding rq->lock, the cpu isn't yet set to this cpu so the
@@ -4951,7 +4959,7 @@ void init_idle(struct task_struct *idle, int cpu)
 
 	rq->curr = rq->idle = idle;
 	idle->on_rq = TASK_ON_RQ_QUEUED;
-#if defined(CONFIG_SMP)
+#ifdef CONFIG_SMP
 	idle->on_cpu = 1;
 #endif
 	raw_spin_unlock(&rq->lock);
@@ -4966,7 +4974,7 @@ void init_idle(struct task_struct *idle, int cpu)
 	idle->sched_class = &idle_sched_class;
 	ftrace_graph_init_idle_task(idle, cpu);
 	vtime_init_idle(idle, cpu);
-#if defined(CONFIG_SMP)
+#ifdef CONFIG_SMP
 	sprintf(idle->comm, "%s/%d", INIT_TASK_COMM, cpu);
 #endif
 }
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 68cda11..6d2a119 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1078,9 +1078,10 @@ static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev)
 	 * After ->on_cpu is cleared, the task can be moved to a different CPU.
 	 * We must ensure this doesn't happen until the switch is completely
 	 * finished.
+	 *
+	 * Pairs with the control dependency and rmb in try_to_wake_up().
 	 */
-	smp_wmb();
-	prev->on_cpu = 0;
+	smp_store_release(&prev->on_cpu, 0);
 #endif
 #ifdef CONFIG_DEBUG_SPINLOCK
 	/* this is a valid case when another task releases the spinlock */
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index 841b72f..3a38775 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -217,7 +217,7 @@ static void clocksource_watchdog(unsigned long data)
 			continue;
 
 		/* Check the deviation from the watchdog clocksource. */
-		if ((abs(cs_nsec - wd_nsec) > WATCHDOG_THRESHOLD)) {
+		if (abs64(cs_nsec - wd_nsec) > WATCHDOG_THRESHOLD) {
 			pr_warn("timekeeping watchdog: Marking clocksource '%s' as unstable because the skew is too large:\n",
 				cs->name);
 			pr_warn("                      '%s' wd_now: %llx wd_last: %llx mask: %llx\n",