Merge commit 'b9a7985' into HEAD

Conflicts:
	kernel/time/timekeeping.c

6 files changed, 118 insertions, 69 deletions

diff --git a/kernel/async.c b/kernel/async.c
index cd9dbb9..04f66e3 100644
--- a/kernel/async.c
+++ b/kernel/async.c
@@ -87,6 +87,13 @@ static async_cookie_t  __lowest_in_progress(struct list_head *running)
 {
 	struct async_entry *entry;
 
+	if (!running) { /* just check the entry count */
+		if (atomic_read(&entry_count))
+			return 0; /* smaller than any cookie */
+		else
+			return next_cookie;
+	}
+
 	if (!list_empty(running)) {
 		entry = list_first_entry(running,
 			struct async_entry, list);
@@ -236,9 +243,7 @@ EXPORT_SYMBOL_GPL(async_schedule_domain);
  */
 void async_synchronize_full(void)
 {
-	do {
-		async_synchronize_cookie(next_cookie);
-	} while (!list_empty(&async_running) || !list_empty(&async_pending));
+	async_synchronize_cookie_domain(next_cookie, NULL);
 }
 EXPORT_SYMBOL_GPL(async_synchronize_full);
 
@@ -258,7 +263,7 @@ EXPORT_SYMBOL_GPL(async_synchronize_full_domain);
 /**
  * async_synchronize_cookie_domain - synchronize asynchronous function calls within a certain domain with cookie checkpointing
  * @cookie: async_cookie_t to use as checkpoint
- * @running: running list to synchronize on
+ * @running: running list to synchronize on, NULL indicates all lists
  *
  * This function waits until all asynchronous function calls for the
  * synchronization domain specified by the running list @list submitted
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 32a6151..7b344be 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -2969,12 +2969,12 @@ EXPORT_SYMBOL_GPL(perf_event_release_kernel);
 /*
  * Called when the last reference to the file is gone.
  */
-static int perf_release(struct inode *inode, struct file *file)
+static void put_event(struct perf_event *event)
 {
-	struct perf_event *event = file->private_data;
 	struct task_struct *owner;
 
-	file->private_data = NULL;
+	if (!atomic_long_dec_and_test(&event->refcount))
+		return;
 
 	rcu_read_lock();
 	owner = ACCESS_ONCE(event->owner);
@@ -3009,7 +3009,13 @@ static int perf_release(struct inode *inode, struct file *file)
 		put_task_struct(owner);
 	}
 
-	return perf_event_release_kernel(event);
+	perf_event_release_kernel(event);
+}
+
+static int perf_release(struct inode *inode, struct file *file)
+{
+	put_event(file->private_data);
+	return 0;
 }
 
 u64 perf_event_read_value(struct perf_event *event, u64 *enabled, u64 *running)
@@ -3241,7 +3247,7 @@ unlock:
 
 static const struct file_operations perf_fops;
 
-static struct perf_event *perf_fget_light(int fd, int *fput_needed)
+static struct file *perf_fget_light(int fd, int *fput_needed)
 {
 	struct file *file;
 
@@ -3255,7 +3261,7 @@ static struct perf_event *perf_fget_light(int fd, int *fput_needed)
 		return ERR_PTR(-EBADF);
 	}
 
-	return file->private_data;
+	return file;
 }
 
 static int perf_event_set_output(struct perf_event *event,
@@ -3287,19 +3293,21 @@ static long perf_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 
 	case PERF_EVENT_IOC_SET_OUTPUT:
 	{
+		struct file *output_file = NULL;
 		struct perf_event *output_event = NULL;
 		int fput_needed = 0;
 		int ret;
 
 		if (arg != -1) {
-			output_event = perf_fget_light(arg, &fput_needed);
-			if (IS_ERR(output_event))
-				return PTR_ERR(output_event);
+			output_file = perf_fget_light(arg, &fput_needed);
+			if (IS_ERR(output_file))
+				return PTR_ERR(output_file);
+			output_event = output_file->private_data;
 		}
 
 		ret = perf_event_set_output(event, output_event);
 		if (output_event)
-			fput_light(output_event->filp, fput_needed);
+			fput_light(output_file, fput_needed);
 
 		return ret;
 	}
@@ -6181,6 +6189,7 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 
 	mutex_init(&event->mmap_mutex);
 
+	atomic_long_set(&event->refcount, 1);
 	event->cpu		= cpu;
 	event->attr		= *attr;
 	event->group_leader	= group_leader;
@@ -6455,12 +6464,12 @@ SYSCALL_DEFINE5(perf_event_open,
 		return event_fd;
 
 	if (group_fd != -1) {
-		group_leader = perf_fget_light(group_fd, &fput_needed);
-		if (IS_ERR(group_leader)) {
-			err = PTR_ERR(group_leader);
+		group_file = perf_fget_light(group_fd, &fput_needed);
+		if (IS_ERR(group_file)) {
+			err = PTR_ERR(group_file);
 			goto err_fd;
 		}
-		group_file = group_leader->filp;
+		group_leader = group_file->private_data;
 		if (flags & PERF_FLAG_FD_OUTPUT)
 			output_event = group_leader;
 		if (flags & PERF_FLAG_FD_NO_GROUP)
@@ -6594,7 +6603,6 @@ SYSCALL_DEFINE5(perf_event_open,
 		put_ctx(gctx);
 	}
 
-	event->filp = event_file;
 	WARN_ON_ONCE(ctx->parent_ctx);
 	mutex_lock(&ctx->mutex);
 
@@ -6682,7 +6690,6 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu,
 		goto err_free;
 	}
 
-	event->filp = NULL;
 	WARN_ON_ONCE(ctx->parent_ctx);
 	mutex_lock(&ctx->mutex);
 	perf_install_in_context(ctx, event, cpu);
@@ -6731,7 +6738,7 @@ static void sync_child_event(struct perf_event *child_event,
 	 * Release the parent event, if this was the last
 	 * reference to it.
 	 */
-	fput(parent_event->filp);
+	put_event(parent_event);
 }
 
 static void
@@ -6807,9 +6814,8 @@ static void perf_event_exit_task_context(struct task_struct *child, int ctxn)
 	 *
 	 *   __perf_event_exit_task()
 	 *     sync_child_event()
-	 *       fput(parent_event->filp)
-	 *         perf_release()
-	 *           mutex_lock(&ctx->mutex)
+	 *       put_event()
+	 *         mutex_lock(&ctx->mutex)
 	 *
 	 * But since its the parent context it won't be the same instance.
 	 */
@@ -6877,7 +6883,7 @@ static void perf_free_event(struct perf_event *event,
 	list_del_init(&event->child_list);
 	mutex_unlock(&parent->child_mutex);
 
-	fput(parent->filp);
+	put_event(parent);
 
 	perf_group_detach(event);
 	list_del_event(event, ctx);
@@ -6957,6 +6963,12 @@ inherit_event(struct perf_event *parent_event,
 					   NULL);
 	if (IS_ERR(child_event))
 		return child_event;
+
+	if (!atomic_long_inc_not_zero(&parent_event->refcount)) {
+		free_event(child_event);
+		return NULL;
+	}
+
 	get_ctx(child_ctx);
 
 	/*
@@ -6996,14 +7008,6 @@ inherit_event(struct perf_event *parent_event,
 	raw_spin_unlock_irqrestore(&child_ctx->lock, flags);
 
 	/*
-	 * Get a reference to the parent filp - we will fput it
-	 * when the child event exits. This is safe to do because
-	 * we are in the parent and we know that the filp still
-	 * exists and has a nonzero count:
-	 */
-	atomic_long_inc(&parent_event->filp->f_count);
-
-	/*
 	 * Link this into the parent event's child list
 	 */
 	WARN_ON_ONCE(parent_event->ctx->parent_ctx);
diff --git a/kernel/exit.c b/kernel/exit.c
index 303bed2..97dd317 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -1049,6 +1049,22 @@ NORET_TYPE void do_exit(long code)
 
 	preempt_disable();
 	exit_rcu();
+
+	/*
+	 * The setting of TASK_RUNNING by try_to_wake_up() may be delayed
+	 * when the following two conditions become true.
+	 *   - There is race condition of mmap_sem (It is acquired by
+	 *     exit_mm()), and
+	 *   - SMI occurs before setting TASK_RUNINNG.
+	 *     (or hypervisor of virtual machine switches to other guest)
+	 *  As a result, we may become TASK_RUNNING after becoming TASK_DEAD
+	 *
+	 * To avoid it, we have to wait for releasing tsk->pi_lock which
+	 * is held by try_to_wake_up()
+	 */
+	smp_mb();
+	raw_spin_unlock_wait(&tsk->pi_lock);
+
 	/* causes final put_task_struct in finish_task_switch(). */
 	tsk->state = TASK_DEAD;
 	schedule();
diff --git a/kernel/sched.c b/kernel/sched.c
index e19782f..d759d33 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -606,22 +606,19 @@ static inline int cpu_of(struct rq *rq)
 /*
  * Return the group to which this tasks belongs.
  *
- * We use task_subsys_state_check() and extend the RCU verification with
- * pi->lock and rq->lock because cpu_cgroup_attach() holds those locks for each
- * task it moves into the cgroup. Therefore by holding either of those locks,
- * we pin the task to the current cgroup.
+ * We cannot use task_subsys_state() and friends because the cgroup
+ * subsystem changes that value before the cgroup_subsys::attach() method
+ * is called, therefore we cannot pin it and might observe the wrong value.
+ *
+ * The same is true for autogroup's p->signal->autogroup->tg, the autogroup
+ * core changes this before calling sched_move_task().
+ *
+ * Instead we use a 'copy' which is updated from sched_move_task() while
+ * holding both task_struct::pi_lock and rq::lock.
  */
 static inline struct task_group *task_group(struct task_struct *p)
 {
-	struct task_group *tg;
-	struct cgroup_subsys_state *css;
-
-	css = task_subsys_state_check(p, cpu_cgroup_subsys_id,
-			lockdep_is_held(&p->pi_lock) ||
-			lockdep_is_held(&task_rq(p)->lock));
-	tg = container_of(css, struct task_group, css);
-
-	return autogroup_task_group(p, tg);
+	return p->sched_task_group;
 }
 
 /* Change a task's cfs_rq and parent entity if it moves across CPUs/groups */
@@ -2207,7 +2204,7 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 	 * a task's CPU. ->pi_lock for waking tasks, rq->lock for runnable tasks.
 	 *
 	 * sched_move_task() holds both and thus holding either pins the cgroup,
-	 * see set_task_rq().
+	 * see task_group().
 	 *
 	 * Furthermore, all task_rq users should acquire both locks, see
 	 * task_rq_lock().
@@ -8557,6 +8554,7 @@ void sched_destroy_group(struct task_group *tg)
  */
 void sched_move_task(struct task_struct *tsk)
 {
+	struct task_group *tg;
 	int on_rq, running;
 	unsigned long flags;
 	struct rq *rq;
@@ -8571,6 +8569,12 @@ void sched_move_task(struct task_struct *tsk)
 	if (unlikely(running))
 		tsk->sched_class->put_prev_task(rq, tsk);
 
+	tg = container_of(task_subsys_state_check(tsk, cpu_cgroup_subsys_id,
+				lockdep_is_held(&tsk->sighand->siglock)),
+			  struct task_group, css);
+	tg = autogroup_task_group(tsk, tg);
+	tsk->sched_task_group = tg;
+
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	if (tsk->sched_class->task_move_group)
 		tsk->sched_class->task_move_group(tsk, on_rq);
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 5f00308..343ab2a 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -382,7 +382,7 @@ int do_settimeofday(const struct timespec *tv)
 	struct timespec ts_delta;
 	unsigned long flags;
 
-	if ((unsigned long)tv->tv_nsec >= NSEC_PER_SEC)
+	if (!timespec_valid_strict(tv))
 		return -EINVAL;
 
 	write_seqlock_irqsave(&xtime_lock, flags);
@@ -417,6 +417,8 @@ EXPORT_SYMBOL(do_settimeofday);
 int timekeeping_inject_offset(struct timespec *ts)
 {
 	unsigned long flags;
+	struct timespec tmp;
+	int ret = 0;
 
 	if ((unsigned long)ts->tv_nsec >= NSEC_PER_SEC)
 		return -EINVAL;
@@ -425,9 +427,16 @@ int timekeeping_inject_offset(struct timespec *ts)
 
 	timekeeping_forward_now();
 
+	tmp = timespec_add(xtime,  *ts);
+	if (!timespec_valid_strict(&tmp)) {
+		ret = -EINVAL;
+		goto error;
+	}
+
 	xtime = timespec_add(xtime, *ts);
 	wall_to_monotonic = timespec_sub(wall_to_monotonic, *ts);
 
+error: /* even if we error out, we forwarded the time, so call update */
 	timekeeping_update(true);
 
 	write_sequnlock_irqrestore(&xtime_lock, flags);
@@ -435,7 +444,7 @@ int timekeeping_inject_offset(struct timespec *ts)
 	/* signal hrtimers about time change */
 	clock_was_set();
 
-	return 0;
+	return ret;
 }
 EXPORT_SYMBOL(timekeeping_inject_offset);
 
@@ -582,7 +591,20 @@ void __init timekeeping_init(void)
 	struct timespec now, boot;
 
 	read_persistent_clock(&now);
+	if (!timespec_valid_strict(&now)) {
+		pr_warn("WARNING: Persistent clock returned invalid value!\n"
+			"         Check your CMOS/BIOS settings.\n");
+		now.tv_sec = 0;
+		now.tv_nsec = 0;
+	}
+
 	read_boot_clock(&boot);
+	if (!timespec_valid_strict(&boot)) {
+		pr_warn("WARNING: Boot clock returned invalid value!\n"
+			"         Check your CMOS/BIOS settings.\n");
+		boot.tv_sec = 0;
+		boot.tv_nsec = 0;
+	}
 
 	write_seqlock_irqsave(&xtime_lock, flags);
 
@@ -903,6 +925,10 @@ static void update_wall_time(void)
 #else
 	offset = (clock->read(clock) - clock->cycle_last) & clock->mask;
 #endif
+	/* Check if there's really nothing to do */
+	if (offset < timekeeper.cycle_interval)
+		return;
+
 	timekeeper.xtime_nsec = (s64)xtime.tv_nsec << timekeeper.shift;
 
 	/*
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index e88c924..00c0bad 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -3412,14 +3412,17 @@ static int __cpuinit trustee_thread(void *__gcwq)
 
 	for_each_busy_worker(worker, i, pos, gcwq) {
 		struct work_struct *rebind_work = &worker->rebind_work;
+		unsigned long worker_flags = worker->flags;
 
 		/*
 		 * Rebind_work may race with future cpu hotplug
 		 * operations.  Use a separate flag to mark that
-		 * rebinding is scheduled.
+		 * rebinding is scheduled.  The morphing should
+		 * be atomic.
 		 */
-		worker->flags |= WORKER_REBIND;
-		worker->flags &= ~WORKER_ROGUE;
+		worker_flags |= WORKER_REBIND;
+		worker_flags &= ~WORKER_ROGUE;
+		ACCESS_ONCE(worker->flags) = worker_flags;
 
 		/* queue rebind_work, wq doesn't matter, use the default one */
 		if (test_and_set_bit(WORK_STRUCT_PENDING_BIT,
@@ -3599,18 +3602,17 @@ static int __devinit workqueue_cpu_down_callback(struct notifier_block *nfb,
 #ifdef CONFIG_SMP
 
 struct work_for_cpu {
-	struct completion completion;
+	struct work_struct work;
 	long (*fn)(void *);
 	void *arg;
 	long ret;
 };
 
-static int do_work_for_cpu(void *_wfc)
+static void work_for_cpu_fn(struct work_struct *work)
 {
-	struct work_for_cpu *wfc = _wfc;
+	struct work_for_cpu *wfc = container_of(work, struct work_for_cpu, work);
+
 	wfc->ret = wfc->fn(wfc->arg);
-	complete(&wfc->completion);
-	return 0;
 }
 
 /**
@@ -3625,19 +3627,11 @@ static int do_work_for_cpu(void *_wfc)
  */
 long work_on_cpu(unsigned int cpu, long (*fn)(void *), void *arg)
 {
-	struct task_struct *sub_thread;
-	struct work_for_cpu wfc = {
-		.completion = COMPLETION_INITIALIZER_ONSTACK(wfc.completion),
-		.fn = fn,
-		.arg = arg,
-	};
+	struct work_for_cpu wfc = { .fn = fn, .arg = arg };
 
-	sub_thread = kthread_create(do_work_for_cpu, &wfc, "work_for_cpu");
-	if (IS_ERR(sub_thread))
-		return PTR_ERR(sub_thread);
-	kthread_bind(sub_thread, cpu);
-	wake_up_process(sub_thread);
-	wait_for_completion(&wfc.completion);
+	INIT_WORK_ONSTACK(&wfc.work, work_for_cpu_fn);
+	schedule_work_on(cpu, &wfc.work);
+	flush_work(&wfc.work);
 	return wfc.ret;
 }
 EXPORT_SYMBOL_GPL(work_on_cpu);