Merge branch 'master' into pm-sleep

* master: (848 commits)
  SELinux: Fix RCU deref check warning in sel_netport_insert()
  binary_sysctl(): fix memory leak
  mm/vmalloc.c: remove static declaration of va from __get_vm_area_node
  ipmi_watchdog: restore settings when BMC reset
  oom: fix integer overflow of points in oom_badness
  memcg: keep root group unchanged if creation fails
  nilfs2: potential integer overflow in nilfs_ioctl_clean_segments()
  nilfs2: unbreak compat ioctl
  cpusets: stall when updating mems_allowed for mempolicy or disjoint nodemask
  evm: prevent racing during tfm allocation
  evm: key must be set once during initialization
  mmc: vub300: fix type of firmware_rom_wait_states module parameter
  Revert "mmc: enable runtime PM by default"
  mmc: sdhci: remove "state" argument from sdhci_suspend_host
  x86, dumpstack: Fix code bytes breakage due to missing KERN_CONT
  IB/qib: Correct sense on freectxts increment and decrement
  RDMA/cma: Verify private data length
  cgroups: fix a css_set not found bug in cgroup_attach_proc
  oprofile: Fix uninitialized memory access when writing to writing to oprofilefs
  Revert "xen/pv-on-hvm kexec: add xs_reset_watches to shutdown watches from old kernel"
  ...

Conflicts:
	kernel/cgroup_freezer.c

kernel/cgroup.c

@@ -2098,11 +2098,6 @@ int cgroup_attach_proc(struct cgroup *cgrp, struct task_struct *leader)
 			continue;
 		/* get old css_set pointer */
 		task_lock(tsk);
-		if (tsk->flags & PF_EXITING) {
-			/* ignore this task if it's going away */
-			task_unlock(tsk);
-			continue;
-		}
 		oldcg = tsk->cgroups;
 		get_css_set(oldcg);
 		task_unlock(tsk);

kernel/cgroup_freezer.c

@@ -152,6 +152,13 @@ static void freezer_destroy(struct cgroup_subsys *ss,
 	kfree(freezer);
 }
 
+/* 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
@@ -224,7 +231,7 @@ static void update_if_frozen(struct cgroup *cgroup,
 	cgroup_iter_start(cgroup, &it);
 	while ((task = cgroup_iter_next(cgroup, &it))) {
 		ntotal++;
-		if (freezing(task) && frozen(task))
+		if (freezing(task) && is_task_frozen_enough(task))
 			nfrozen++;
 	}
 
@@ -276,7 +283,7 @@ static int try_to_freeze_cgroup(struct cgroup *cgroup, struct freezer *freezer)
 	while ((task = cgroup_iter_next(cgroup, &it))) {
 		if (!freeze_task(task))
 			continue;
-		if (frozen(task))
+		if (is_task_frozen_enough(task))
 			continue;
 		if (!freezing(task) && !freezer_should_skip(task))
 			num_cant_freeze_now++;

kernel/cpuset.c

@@ -123,6 +123,19 @@ static inline struct cpuset *task_cs(struct task_struct *task)
 			    struct cpuset, css);
 }
 
+#ifdef CONFIG_NUMA
+static inline bool task_has_mempolicy(struct task_struct *task)
+{
+	return task->mempolicy;
+}
+#else
+static inline bool task_has_mempolicy(struct task_struct *task)
+{
+	return false;
+}
+#endif
+
+
 /* bits in struct cpuset flags field */
 typedef enum {
 	CS_CPU_EXCLUSIVE,
@@ -949,7 +962,7 @@ static void cpuset_migrate_mm(struct mm_struct *mm, const nodemask_t *from,
 static void cpuset_change_task_nodemask(struct task_struct *tsk,
 					nodemask_t *newmems)
 {
-	bool masks_disjoint = !nodes_intersects(*newmems, tsk->mems_allowed);
+	bool need_loop;
 
 repeat:
 	/*
@@ -962,6 +975,14 @@ repeat:
 		return;
 
 	task_lock(tsk);
+	/*
+	 * Determine if a loop is necessary if another thread is doing
+	 * get_mems_allowed().  If at least one node remains unchanged and
+	 * tsk does not have a mempolicy, then an empty nodemask will not be
+	 * possible when mems_allowed is larger than a word.
+	 */
+	need_loop = task_has_mempolicy(tsk) ||
+			!nodes_intersects(*newmems, tsk->mems_allowed);
 	nodes_or(tsk->mems_allowed, tsk->mems_allowed, *newmems);
 	mpol_rebind_task(tsk, newmems, MPOL_REBIND_STEP1);
 
@@ -981,11 +1002,9 @@ repeat:
 
 	/*
 	 * Allocation of memory is very fast, we needn't sleep when waiting
-	 * for the read-side.  No wait is necessary, however, if at least one
-	 * node remains unchanged.
+	 * for the read-side.
 	 */
-	while (masks_disjoint &&
-			ACCESS_ONCE(tsk->mems_allowed_change_disable)) {
+	while (need_loop && ACCESS_ONCE(tsk->mems_allowed_change_disable)) {
 		task_unlock(tsk);
 		if (!task_curr(tsk))
 			yield();

kernel/events/core.c

@@ -185,6 +185,9 @@ static void cpu_ctx_sched_in(struct perf_cpu_context *cpuctx,
 static void update_context_time(struct perf_event_context *ctx);
 static u64 perf_event_time(struct perf_event *event);
 
+static void ring_buffer_attach(struct perf_event *event,
+			       struct ring_buffer *rb);
+
 void __weak perf_event_print_debug(void)	{ }
 
 extern __weak const char *perf_pmu_name(void)
@@ -2171,9 +2174,10 @@ static void perf_event_context_sched_in(struct perf_event_context *ctx,
 	 */
 	cpu_ctx_sched_out(cpuctx, EVENT_FLEXIBLE);
 
-	perf_event_sched_in(cpuctx, ctx, task);
+	if (ctx->nr_events)
+		cpuctx->task_ctx = ctx;
 
-	cpuctx->task_ctx = ctx;
+	perf_event_sched_in(cpuctx, cpuctx->task_ctx, task);
 
 	perf_pmu_enable(ctx->pmu);
 	perf_ctx_unlock(cpuctx, ctx);
@@ -3190,12 +3194,33 @@ static unsigned int perf_poll(struct file *file, poll_table *wait)
 	struct ring_buffer *rb;
 	unsigned int events = POLL_HUP;
 
+	/*
+	 * Race between perf_event_set_output() and perf_poll(): perf_poll()
+	 * grabs the rb reference but perf_event_set_output() overrides it.
+	 * Here is the timeline for two threads T1, T2:
+	 * t0: T1, rb = rcu_dereference(event->rb)
+	 * t1: T2, old_rb = event->rb
+	 * t2: T2, event->rb = new rb
+	 * t3: T2, ring_buffer_detach(old_rb)
+	 * t4: T1, ring_buffer_attach(rb1)
+	 * t5: T1, poll_wait(event->waitq)
+	 *
+	 * To avoid this problem, we grab mmap_mutex in perf_poll()
+	 * thereby ensuring that the assignment of the new ring buffer
+	 * and the detachment of the old buffer appear atomic to perf_poll()
+	 */
+	mutex_lock(&event->mmap_mutex);
+
 	rcu_read_lock();
 	rb = rcu_dereference(event->rb);
-	if (rb)
+	if (rb) {
+		ring_buffer_attach(event, rb);
 		events = atomic_xchg(&rb->poll, 0);
+	}
 	rcu_read_unlock();
 
+	mutex_unlock(&event->mmap_mutex);
+
 	poll_wait(file, &event->waitq, wait);
 
 	return events;
@@ -3496,6 +3521,53 @@ unlock:
 	return ret;
 }
 
+static void ring_buffer_attach(struct perf_event *event,
+			       struct ring_buffer *rb)
+{
+	unsigned long flags;
+
+	if (!list_empty(&event->rb_entry))
+		return;
+
+	spin_lock_irqsave(&rb->event_lock, flags);
+	if (!list_empty(&event->rb_entry))
+		goto unlock;
+
+	list_add(&event->rb_entry, &rb->event_list);
+unlock:
+	spin_unlock_irqrestore(&rb->event_lock, flags);
+}
+
+static void ring_buffer_detach(struct perf_event *event,
+			       struct ring_buffer *rb)
+{
+	unsigned long flags;
+
+	if (list_empty(&event->rb_entry))
+		return;
+
+	spin_lock_irqsave(&rb->event_lock, flags);
+	list_del_init(&event->rb_entry);
+	wake_up_all(&event->waitq);
+	spin_unlock_irqrestore(&rb->event_lock, flags);
+}
+
+static void ring_buffer_wakeup(struct perf_event *event)
+{
+	struct ring_buffer *rb;
+
+	rcu_read_lock();
+	rb = rcu_dereference(event->rb);
+	if (!rb)
+		goto unlock;
+
+	list_for_each_entry_rcu(event, &rb->event_list, rb_entry)
+		wake_up_all(&event->waitq);
+
+unlock:
+	rcu_read_unlock();
+}
+
 static void rb_free_rcu(struct rcu_head *rcu_head)
 {
 	struct ring_buffer *rb;
@@ -3521,9 +3593,19 @@ static struct ring_buffer *ring_buffer_get(struct perf_event *event)
 
 static void ring_buffer_put(struct ring_buffer *rb)
 {
+	struct perf_event *event, *n;
+	unsigned long flags;
+
 	if (!atomic_dec_and_test(&rb->refcount))
 		return;
 
+	spin_lock_irqsave(&rb->event_lock, flags);
+	list_for_each_entry_safe(event, n, &rb->event_list, rb_entry) {
+		list_del_init(&event->rb_entry);
+		wake_up_all(&event->waitq);
+	}
+	spin_unlock_irqrestore(&rb->event_lock, flags);
+
 	call_rcu(&rb->rcu_head, rb_free_rcu);
 }
 
@@ -3546,6 +3628,7 @@ static void perf_mmap_close(struct vm_area_struct *vma)
 		atomic_long_sub((size >> PAGE_SHIFT) + 1, &user->locked_vm);
 		vma->vm_mm->pinned_vm -= event->mmap_locked;
 		rcu_assign_pointer(event->rb, NULL);
+		ring_buffer_detach(event, rb);
 		mutex_unlock(&event->mmap_mutex);
 
 		ring_buffer_put(rb);
@@ -3700,7 +3783,7 @@ static const struct file_operations perf_fops = {
 
 void perf_event_wakeup(struct perf_event *event)
 {
-	wake_up_all(&event->waitq);
+	ring_buffer_wakeup(event);
 
 	if (event->pending_kill) {
 		kill_fasync(&event->fasync, SIGIO, event->pending_kill);
@@ -5822,6 +5905,8 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 	INIT_LIST_HEAD(&event->group_entry);
 	INIT_LIST_HEAD(&event->event_entry);
 	INIT_LIST_HEAD(&event->sibling_list);
+	INIT_LIST_HEAD(&event->rb_entry);
+
 	init_waitqueue_head(&event->waitq);
 	init_irq_work(&event->pending, perf_pending_event);
 
@@ -6028,6 +6113,8 @@ set:
 
 	old_rb = event->rb;
 	rcu_assign_pointer(event->rb, rb);
+	if (old_rb)
+		ring_buffer_detach(event, old_rb);
 	ret = 0;
 unlock:
 	mutex_unlock(&event->mmap_mutex);

kernel/events/internal.h

@@ -22,6 +22,9 @@ struct ring_buffer {
 	local_t				lost;		/* nr records lost   */
 
 	long				watermark;	/* wakeup watermark  */
+	/* poll crap */
+	spinlock_t			event_lock;
+	struct list_head		event_list;
 
 	struct perf_event_mmap_page	*user_page;
 	void				*data_pages[0];

kernel/events/ring_buffer.c

@@ -209,6 +209,9 @@ ring_buffer_init(struct ring_buffer *rb, long watermark, int flags)
 		rb->writable = 1;
 
 	atomic_set(&rb->refcount, 1);
+
+	INIT_LIST_HEAD(&rb->event_list);
+	spin_lock_init(&rb->event_lock);
 }
 
 #ifndef CONFIG_PERF_USE_VMALLOC

kernel/hrtimer.c

@@ -885,10 +885,13 @@ static void __remove_hrtimer(struct hrtimer *timer,
 			     struct hrtimer_clock_base *base,
 			     unsigned long newstate, int reprogram)
 {
+	struct timerqueue_node *next_timer;
 	if (!(timer->state & HRTIMER_STATE_ENQUEUED))
 		goto out;
 
-	if (&timer->node == timerqueue_getnext(&base->active)) {
+	next_timer = timerqueue_getnext(&base->active);
+	timerqueue_del(&base->active, &timer->node);
+	if (&timer->node == next_timer) {
 #ifdef CONFIG_HIGH_RES_TIMERS
 		/* Reprogram the clock event device. if enabled */
 		if (reprogram && hrtimer_hres_active()) {
@@ -901,7 +904,6 @@ static void __remove_hrtimer(struct hrtimer *timer,
 		}
 #endif
 	}
-	timerqueue_del(&base->active, &timer->node);
 	if (!timerqueue_getnext(&base->active))
 		base->cpu_base->active_bases &= ~(1 << base->index);
 out:

kernel/irq/manage.c

@@ -623,8 +623,9 @@ static irqreturn_t irq_nested_primary_handler(int irq, void *dev_id)
 
 static int irq_wait_for_interrupt(struct irqaction *action)
 {
+	set_current_state(TASK_INTERRUPTIBLE);
+
 	while (!kthread_should_stop()) {
-		set_current_state(TASK_INTERRUPTIBLE);
 
 		if (test_and_clear_bit(IRQTF_RUNTHREAD,
 				       &action->thread_flags)) {
@@ -632,7 +633,9 @@ static int irq_wait_for_interrupt(struct irqaction *action)
 			return 0;
 		}
 		schedule();
+		set_current_state(TASK_INTERRUPTIBLE);
 	}
+	__set_current_state(TASK_RUNNING);
 	return -1;
 }
 
@@ -1596,7 +1599,7 @@ int request_percpu_irq(unsigned int irq, irq_handler_t handler,
 		return -ENOMEM;
 
 	action->handler = handler;
-	action->flags = IRQF_PERCPU;
+	action->flags = IRQF_PERCPU | IRQF_NO_SUSPEND;
 	action->name = devname;
 	action->percpu_dev_id = dev_id;
 

kernel/irq/spurious.c

@@ -84,7 +84,9 @@ static int try_one_irq(int irq, struct irq_desc *desc, bool force)
 	 */
 	action = desc->action;
 	if (!action || !(action->flags & IRQF_SHARED) ||
-	    (action->flags & __IRQF_TIMER) || !action->next)
+	    (action->flags & __IRQF_TIMER) ||
+	    (action->handler(irq, action->dev_id) == IRQ_HANDLED) ||
+	    !action->next)
 		goto out;
 
 	/* Already running on another processor */

kernel/jump_label.c

@@ -66,8 +66,9 @@ void jump_label_inc(struct jump_label_key *key)
 		return;
 
 	jump_label_lock();
-	if (atomic_add_return(1, &key->enabled) == 1)
+	if (atomic_read(&key->enabled) == 0)
 		jump_label_update(key, JUMP_LABEL_ENABLE);
+	atomic_inc(&key->enabled);
 	jump_label_unlock();
 }
 

kernel/lockdep.c

@@ -44,6 +44,7 @@
 #include <linux/stringify.h>
 #include <linux/bitops.h>
 #include <linux/gfp.h>
+#include <linux/kmemcheck.h>
 
 #include <asm/sections.h>
 
@@ -2948,7 +2949,12 @@ static int mark_lock(struct task_struct *curr, struct held_lock *this,
 void lockdep_init_map(struct lockdep_map *lock, const char *name,
 		      struct lock_class_key *key, int subclass)
 {
-	memset(lock, 0, sizeof(*lock));
+	int i;
+
+	kmemcheck_mark_initialized(lock, sizeof(*lock));
+
+	for (i = 0; i < NR_LOCKDEP_CACHING_CLASSES; i++)
+		lock->class_cache[i] = NULL;
 
 #ifdef CONFIG_LOCK_STAT
 	lock->cpu = raw_smp_processor_id();

kernel/printk.c

@@ -1293,10 +1293,11 @@ again:
 	raw_spin_lock(&logbuf_lock);
 	if (con_start != log_end)
 		retry = 1;
+	raw_spin_unlock_irqrestore(&logbuf_lock, flags);
+
 	if (retry && console_trylock())
 		goto again;
 
-	raw_spin_unlock_irqrestore(&logbuf_lock, flags);
 	if (wake_klogd)
 		wake_up_klogd();
 }

kernel/sched.c

@@ -71,6 +71,7 @@
 #include <linux/ctype.h>
 #include <linux/ftrace.h>
 #include <linux/slab.h>
+#include <linux/init_task.h>
 
 #include <asm/tlb.h>
 #include <asm/irq_regs.h>
@@ -4810,6 +4811,9 @@ EXPORT_SYMBOL(wait_for_completion);
  * This waits for either a completion of a specific task to be signaled or for a
  * specified timeout to expire. The timeout is in jiffies. It is not
  * interruptible.
+ *
+ * The return value is 0 if timed out, and positive (at least 1, or number of
+ * jiffies left till timeout) if completed.
  */
 unsigned long __sched
 wait_for_completion_timeout(struct completion *x, unsigned long timeout)
@@ -4824,6 +4828,8 @@ EXPORT_SYMBOL(wait_for_completion_timeout);
  *
  * This waits for completion of a specific task to be signaled. It is
  * interruptible.
+ *
+ * The return value is -ERESTARTSYS if interrupted, 0 if completed.
  */
 int __sched wait_for_completion_interruptible(struct completion *x)
 {
@@ -4841,6 +4847,9 @@ EXPORT_SYMBOL(wait_for_completion_interruptible);
  *
  * This waits for either a completion of a specific task to be signaled or for a
  * specified timeout to expire. It is interruptible. The timeout is in jiffies.
+ *
+ * The return value is -ERESTARTSYS if interrupted, 0 if timed out,
+ * positive (at least 1, or number of jiffies left till timeout) if completed.
  */
 long __sched
 wait_for_completion_interruptible_timeout(struct completion *x,
@@ -4856,6 +4865,8 @@ EXPORT_SYMBOL(wait_for_completion_interruptible_timeout);
  *
  * This waits to be signaled for completion of a specific task. It can be
  * interrupted by a kill signal.
+ *
+ * The return value is -ERESTARTSYS if interrupted, 0 if completed.
  */
 int __sched wait_for_completion_killable(struct completion *x)
 {
@@ -4874,6 +4885,9 @@ EXPORT_SYMBOL(wait_for_completion_killable);
  * This waits for either a completion of a specific task to be
  * signaled or for a specified timeout to expire. It can be
  * interrupted by a kill signal. The timeout is in jiffies.
+ *
+ * The return value is -ERESTARTSYS if interrupted, 0 if timed out,
+ * positive (at least 1, or number of jiffies left till timeout) if completed.
  */
 long __sched
 wait_for_completion_killable_timeout(struct completion *x,
@@ -6099,6 +6113,9 @@ void __cpuinit init_idle(struct task_struct *idle, int cpu)
 	 */
 	idle->sched_class = &idle_sched_class;
 	ftrace_graph_init_idle_task(idle, cpu);
+#if defined(CONFIG_SMP)
+	sprintf(idle->comm, "%s/%d", INIT_TASK_COMM, cpu);
+#endif
 }
 
 /*

kernel/sched_fair.c

@@ -772,19 +772,32 @@ static void update_cfs_load(struct cfs_rq *cfs_rq, int global_update)
 		list_del_leaf_cfs_rq(cfs_rq);
 }
 
+static inline long calc_tg_weight(struct task_group *tg, struct cfs_rq *cfs_rq)
+{
+	long tg_weight;
+
+	/*
+	 * Use this CPU's actual weight instead of the last load_contribution
+	 * to gain a more accurate current total weight. See
+	 * update_cfs_rq_load_contribution().
+	 */
+	tg_weight = atomic_read(&tg->load_weight);
+	tg_weight -= cfs_rq->load_contribution;
+	tg_weight += cfs_rq->load.weight;
+
+	return tg_weight;
+}
+
 static long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg)
 {
-	long load_weight, load, shares;
+	long tg_weight, load, shares;
 
+	tg_weight = calc_tg_weight(tg, cfs_rq);
 	load = cfs_rq->load.weight;
 
-	load_weight = atomic_read(&tg->load_weight);
-	load_weight += load;
-	load_weight -= cfs_rq->load_contribution;
-
 	shares = (tg->shares * load);
-	if (load_weight)
-		shares /= load_weight;
+	if (tg_weight)
+		shares /= tg_weight;
 
 	if (shares < MIN_SHARES)
 		shares = MIN_SHARES;
@@ -1743,7 +1756,7 @@ static void __return_cfs_rq_runtime(struct cfs_rq *cfs_rq)
 
 static __always_inline void return_cfs_rq_runtime(struct cfs_rq *cfs_rq)
 {
-	if (!cfs_rq->runtime_enabled || !cfs_rq->nr_running)
+	if (!cfs_rq->runtime_enabled || cfs_rq->nr_running)
 		return;
 
 	__return_cfs_rq_runtime(cfs_rq);
@@ -2036,36 +2049,100 @@ static void task_waking_fair(struct task_struct *p)
  * Adding load to a group doesn't make a group heavier, but can cause movement
  * of group shares between cpus. Assuming the shares were perfectly aligned one
  * can calculate the shift in shares.
+ *
+ * Calculate the effective load difference if @wl is added (subtracted) to @tg
+ * on this @cpu and results in a total addition (subtraction) of @wg to the
+ * total group weight.
+ *
+ * Given a runqueue weight distribution (rw_i) we can compute a shares
+ * distribution (s_i) using:
+ *
+ *   s_i = rw_i / \Sum rw_j						(1)
+ *
+ * Suppose we have 4 CPUs and our @tg is a direct child of the root group and
+ * has 7 equal weight tasks, distributed as below (rw_i), with the resulting
+ * shares distribution (s_i):
+ *
+ *   rw_i = {   2,   4,   1,   0 }
+ *   s_i  = { 2/7, 4/7, 1/7,   0 }
+ *
+ * As per wake_affine() we're interested in the load of two CPUs (the CPU the
+ * task used to run on and the CPU the waker is running on), we need to
+ * compute the effect of waking a task on either CPU and, in case of a sync
+ * wakeup, compute the effect of the current task going to sleep.
+ *
+ * So for a change of @wl to the local @cpu with an overall group weight change
+ * of @wl we can compute the new shares distribution (s'_i) using:
+ *
+ *   s'_i = (rw_i + @wl) / (@wg + \Sum rw_j)				(2)
+ *
+ * Suppose we're interested in CPUs 0 and 1, and want to compute the load
+ * differences in waking a task to CPU 0. The additional task changes the
+ * weight and shares distributions like:
+ *
+ *   rw'_i = {   3,   4,   1,   0 }
+ *   s'_i  = { 3/8, 4/8, 1/8,   0 }
+ *
+ * We can then compute the difference in effective weight by using:
+ *
+ *   dw_i = S * (s'_i - s_i)						(3)
+ *
+ * Where 'S' is the group weight as seen by its parent.
+ *
+ * Therefore the effective change in loads on CPU 0 would be 5/56 (3/8 - 2/7)
+ * times the weight of the group. The effect on CPU 1 would be -4/56 (4/8 -
+ * 4/7) times the weight of the group.
  */
 static long effective_load(struct task_group *tg, int cpu, long wl, long wg)
 {
 	struct sched_entity *se = tg->se[cpu];
 
-	if (!tg->parent)
+	if (!tg->parent)	/* the trivial, non-cgroup case */
 		return wl;
 
 	for_each_sched_entity(se) {
-		long lw, w;
+		long w, W;
 
 		tg = se->my_q->tg;
-		w = se->my_q->load.weight;
 
-		/* use this cpu's instantaneous contribution */
-		lw = atomic_read(&tg->load_weight);
-		lw -= se->my_q->load_contribution;
-		lw += w + wg;
+		/*
+		 * W = @wg + \Sum rw_j
+		 */
+		W = wg + calc_tg_weight(tg, se->my_q);
 
-		wl += w;
+		/*
+		 * w = rw_i + @wl
+		 */
+		w = se->my_q->load.weight + wl;
 
-		if (lw > 0 && wl < lw)
-			wl = (wl * tg->shares) / lw;
+		/*
+		 * wl = S * s'_i; see (2)
+		 */
+		if (W > 0 && w < W)
+			wl = (w * tg->shares) / W;
 		else
 			wl = tg->shares;
 
-		/* zero point is MIN_SHARES */
+		/*
+		 * Per the above, wl is the new se->load.weight value; since
+		 * those are clipped to [MIN_SHARES, ...) do so now. See
+		 * calc_cfs_shares().
+		 */
 		if (wl < MIN_SHARES)
 			wl = MIN_SHARES;
+
+		/*
+		 * wl = dw_i = S * (s'_i - s_i); see (3)
+		 */
 		wl -= se->load.weight;
+
+		/*
+		 * Recursively apply this logic to all parent groups to compute
+		 * the final effective load change on the root group. Since
+		 * only the @tg group gets extra weight, all parent groups can
+		 * only redistribute existing shares. @wl is the shift in shares
+		 * resulting from this level per the above.
+		 */
 		wg = 0;
 	}
 
@@ -2249,7 +2326,8 @@ static int select_idle_sibling(struct task_struct *p, int target)
 	int cpu = smp_processor_id();
 	int prev_cpu = task_cpu(p);
 	struct sched_domain *sd;
-	int i;
+	struct sched_group *sg;
+	int i, smt = 0;
 
 	/*
 	 * If the task is going to be woken-up on this cpu and if it is
@@ -2269,25 +2347,40 @@ static int select_idle_sibling(struct task_struct *p, int target)
 	 * Otherwise, iterate the domains and find an elegible idle cpu.
 	 */
 	rcu_read_lock();
+again:
 	for_each_domain(target, sd) {
+		if (!smt && (sd->flags & SD_SHARE_CPUPOWER))
+			continue;
+
+		if (smt && !(sd->flags & SD_SHARE_CPUPOWER))
+			break;
+
 		if (!(sd->flags & SD_SHARE_PKG_RESOURCES))
 			break;
 
-		for_each_cpu_and(i, sched_domain_span(sd), tsk_cpus_allowed(p)) {
-			if (idle_cpu(i)) {
-				target = i;
-				break;
-			}
-		}
+		sg = sd->groups;
+		do {
+			if (!cpumask_intersects(sched_group_cpus(sg),
+						tsk_cpus_allowed(p)))
+				goto next;
 
-		/*
-		 * Lets stop looking for an idle sibling when we reached
-		 * the domain that spans the current cpu and prev_cpu.
-		 */
-		if (cpumask_test_cpu(cpu, sched_domain_span(sd)) &&
-		    cpumask_test_cpu(prev_cpu, sched_domain_span(sd)))
-			break;
+			for_each_cpu(i, sched_group_cpus(sg)) {
+				if (!idle_cpu(i))
+					goto next;
+			}
+
+			target = cpumask_first_and(sched_group_cpus(sg),
+					tsk_cpus_allowed(p));
+			goto done;
+next:
+			sg = sg->next;
+		} while (sg != sd->groups);
 	}
+	if (!smt) {
+		smt = 1;
+		goto again;
+	}
+done:
 	rcu_read_unlock();
 
 	return target;
@@ -3511,7 +3604,7 @@ static bool update_sd_pick_busiest(struct sched_domain *sd,
 }
 
 /**
- * update_sd_lb_stats - Update sched_group's statistics for load balancing.
+ * update_sd_lb_stats - Update sched_domain's statistics for load balancing.
  * @sd: sched_domain whose statistics are to be updated.
  * @this_cpu: Cpu for which load balance is currently performed.
  * @idle: Idle status of this_cpu

kernel/sched_features.h

@@ -67,3 +67,4 @@ SCHED_FEAT(NONTASK_POWER, 1)
 SCHED_FEAT(TTWU_QUEUE, 1)
 
 SCHED_FEAT(FORCE_SD_OVERLAP, 0)
+SCHED_FEAT(RT_RUNTIME_SHARE, 1)

kernel/sched_rt.c

@@ -560,6 +560,9 @@ static int balance_runtime(struct rt_rq *rt_rq)
 {
 	int more = 0;
 
+	if (!sched_feat(RT_RUNTIME_SHARE))
+		return more;
+
 	if (rt_rq->rt_time > rt_rq->rt_runtime) {
 		raw_spin_unlock(&rt_rq->rt_runtime_lock);
 		more = do_balance_runtime(rt_rq);

kernel/sysctl_binary.c

@@ -1354,7 +1354,7 @@ static ssize_t binary_sysctl(const int *name, int nlen,
 
 	fput(file);
 out_putname:
-	putname(pathname);
+	__putname(pathname);
 out:
 	return result;
 }

kernel/time/alarmtimer.c

@@ -195,7 +195,7 @@ static enum hrtimer_restart alarmtimer_fired(struct hrtimer *timer)
 		struct alarm *alarm;
 		ktime_t expired = next->expires;
 
-		if (expired.tv64 >= now.tv64)
+		if (expired.tv64 > now.tv64)
 			break;
 
 		alarm = container_of(next, struct alarm, node);

kernel/time/clockevents.c

@@ -387,6 +387,7 @@ void clockevents_exchange_device(struct clock_event_device *old,
 	 * released list and do a notify add later.
 	 */
 	if (old) {
+		old->event_handler = clockevents_handle_noop;
 		clockevents_set_mode(old, CLOCK_EVT_MODE_UNUSED);
 		list_del(&old->list);
 		list_add(&old->list, &clockevents_released);

kernel/time/clocksource.c

@@ -491,6 +491,22 @@ void clocksource_touch_watchdog(void)
 	clocksource_resume_watchdog();
 }
 
+/**
+ * clocksource_max_adjustment- Returns max adjustment amount
+ * @cs:         Pointer to clocksource
+ *
+ */
+static u32 clocksource_max_adjustment(struct clocksource *cs)
+{
+	u64 ret;
+	/*
+	 * We won't try to correct for more then 11% adjustments (110,000 ppm),
+	 */
+	ret = (u64)cs->mult * 11;
+	do_div(ret,100);
+	return (u32)ret;
+}
+
 /**
  * clocksource_max_deferment - Returns max time the clocksource can be deferred
  * @cs:         Pointer to clocksource
@@ -503,25 +519,28 @@ static u64 clocksource_max_deferment(struct clocksource *cs)
 	/*
 	 * Calculate the maximum number of cycles that we can pass to the
 	 * cyc2ns function without overflowing a 64-bit signed result. The
-	 * maximum number of cycles is equal to ULLONG_MAX/cs->mult which
-	 * is equivalent to the below.
-	 * max_cycles < (2^63)/cs->mult
-	 * max_cycles < 2^(log2((2^63)/cs->mult))
-	 * max_cycles < 2^(log2(2^63) - log2(cs->mult))
-	 * max_cycles < 2^(63 - log2(cs->mult))
-	 * max_cycles < 1 << (63 - log2(cs->mult))
+	 * maximum number of cycles is equal to ULLONG_MAX/(cs->mult+cs->maxadj)
+	 * which is equivalent to the below.
+	 * max_cycles < (2^63)/(cs->mult + cs->maxadj)
+	 * max_cycles < 2^(log2((2^63)/(cs->mult + cs->maxadj)))
+	 * max_cycles < 2^(log2(2^63) - log2(cs->mult + cs->maxadj))
+	 * max_cycles < 2^(63 - log2(cs->mult + cs->maxadj))
+	 * max_cycles < 1 << (63 - log2(cs->mult + cs->maxadj))
 	 * Please note that we add 1 to the result of the log2 to account for
 	 * any rounding errors, ensure the above inequality is satisfied and
 	 * no overflow will occur.
 	 */
-	max_cycles = 1ULL << (63 - (ilog2(cs->mult) + 1));
+	max_cycles = 1ULL << (63 - (ilog2(cs->mult + cs->maxadj) + 1));
 
 	/*
 	 * The actual maximum number of cycles we can defer the clocksource is
 	 * determined by the minimum of max_cycles and cs->mask.
+	 * Note: Here we subtract the maxadj to make sure we don't sleep for
+	 * too long if there's a large negative adjustment.
 	 */
 	max_cycles = min_t(u64, max_cycles, (u64) cs->mask);
-	max_nsecs = clocksource_cyc2ns(max_cycles, cs->mult, cs->shift);
+	max_nsecs = clocksource_cyc2ns(max_cycles, cs->mult - cs->maxadj,
+					cs->shift);
 
 	/*
 	 * To ensure that the clocksource does not wrap whilst we are idle,
@@ -529,7 +548,7 @@ static u64 clocksource_max_deferment(struct clocksource *cs)
 	 * note a margin of 12.5% is used because this can be computed with
 	 * a shift, versus say 10% which would require division.
 	 */
-	return max_nsecs - (max_nsecs >> 5);
+	return max_nsecs - (max_nsecs >> 3);
 }
 
 #ifndef CONFIG_ARCH_USES_GETTIMEOFFSET
@@ -628,7 +647,7 @@ static void clocksource_enqueue(struct clocksource *cs)
 
 /**
  * __clocksource_updatefreq_scale - Used update clocksource with new freq
- * @t:		clocksource to be registered
+ * @cs:		clocksource to be registered
  * @scale:	Scale factor multiplied against freq to get clocksource hz
  * @freq:	clocksource frequency (cycles per second) divided by scale
  *
@@ -640,7 +659,6 @@ static void clocksource_enqueue(struct clocksource *cs)
 void __clocksource_updatefreq_scale(struct clocksource *cs, u32 scale, u32 freq)
 {
 	u64 sec;
-
 	/*
 	 * Calc the maximum number of seconds which we can run before
 	 * wrapping around. For clocksources which have a mask > 32bit
@@ -651,7 +669,7 @@ void __clocksource_updatefreq_scale(struct clocksource *cs, u32 scale, u32 freq)
 	 * ~ 0.06ppm granularity for NTP. We apply the same 12.5%
 	 * margin as we do in clocksource_max_deferment()
 	 */
-	sec = (cs->mask - (cs->mask >> 5));
+	sec = (cs->mask - (cs->mask >> 3));
 	do_div(sec, freq);
 	do_div(sec, scale);
 	if (!sec)
@@ -661,13 +679,27 @@ void __clocksource_updatefreq_scale(struct clocksource *cs, u32 scale, u32 freq)
 
 	clocks_calc_mult_shift(&cs->mult, &cs->shift, freq,
 			       NSEC_PER_SEC / scale, sec * scale);
+
+	/*
+	 * for clocksources that have large mults, to avoid overflow.
+	 * Since mult may be adjusted by ntp, add an safety extra margin
+	 *
+	 */
+	cs->maxadj = clocksource_max_adjustment(cs);
+	while ((cs->mult + cs->maxadj < cs->mult)
+		|| (cs->mult - cs->maxadj > cs->mult)) {
+		cs->mult >>= 1;
+		cs->shift--;
+		cs->maxadj = clocksource_max_adjustment(cs);
+	}
+
 	cs->max_idle_ns = clocksource_max_deferment(cs);
 }
 EXPORT_SYMBOL_GPL(__clocksource_updatefreq_scale);
 
 /**
  * __clocksource_register_scale - Used to install new clocksources
- * @t:		clocksource to be registered
+ * @cs:		clocksource to be registered
  * @scale:	Scale factor multiplied against freq to get clocksource hz
  * @freq:	clocksource frequency (cycles per second) divided by scale
  *
@@ -695,12 +727,18 @@ EXPORT_SYMBOL_GPL(__clocksource_register_scale);
 
 /**
  * clocksource_register - Used to install new clocksources
- * @t:		clocksource to be registered
+ * @cs:		clocksource to be registered
  *
  * Returns -EBUSY if registration fails, zero otherwise.
  */
 int clocksource_register(struct clocksource *cs)
 {
+	/* calculate max adjustment for given mult/shift */
+	cs->maxadj = clocksource_max_adjustment(cs);
+	WARN_ONCE(cs->mult + cs->maxadj < cs->mult,
+		"Clocksource %s might overflow on 11%% adjustment\n",
+		cs->name);
+
 	/* calculate max idle time permitted for this clocksource */
 	cs->max_idle_ns = clocksource_max_deferment(cs);
 
@@ -723,6 +761,8 @@ static void __clocksource_change_rating(struct clocksource *cs, int rating)
 
 /**
  * clocksource_change_rating - Change the rating of a registered clocksource
+ * @cs:		clocksource to be changed
+ * @rating:	new rating
  */
 void clocksource_change_rating(struct clocksource *cs, int rating)
 {
@@ -734,6 +774,7 @@ EXPORT_SYMBOL(clocksource_change_rating);
 
 /**
  * clocksource_unregister - remove a registered clocksource
+ * @cs:	clocksource to be unregistered
  */
 void clocksource_unregister(struct clocksource *cs)
 {
@@ -749,6 +790,7 @@ EXPORT_SYMBOL(clocksource_unregister);
 /**
  * sysfs_show_current_clocksources - sysfs interface for current clocksource
  * @dev:	unused
+ * @attr:	unused
  * @buf:	char buffer to be filled with clocksource list
  *
  * Provides sysfs interface for listing current clocksource.
@@ -769,6 +811,7 @@ sysfs_show_current_clocksources(struct sys_device *dev,
 /**
  * sysfs_override_clocksource - interface for manually overriding clocksource
  * @dev:	unused
+ * @attr:	unused
  * @buf:	name of override clocksource
  * @count:	length of buffer
  *
@@ -804,6 +847,7 @@ static ssize_t sysfs_override_clocksource(struct sys_device *dev,
 /**
  * sysfs_show_available_clocksources - sysfs interface for listing clocksource
  * @dev:	unused
+ * @attr:	unused
  * @buf:	char buffer to be filled with clocksource list
  *
  * Provides sysfs interface for listing registered clocksources

kernel/time/tick-broadcast.c

@@ -71,7 +71,7 @@ int tick_check_broadcast_device(struct clock_event_device *dev)
 	     (dev->features & CLOCK_EVT_FEAT_C3STOP))
 		return 0;
 
-	clockevents_exchange_device(NULL, dev);
+	clockevents_exchange_device(tick_broadcast_device.evtdev, dev);
 	tick_broadcast_device.evtdev = dev;
 	if (!cpumask_empty(tick_get_broadcast_mask()))
 		tick_broadcast_start_periodic(dev);

kernel/time/timekeeping.c

@@ -249,6 +249,8 @@ ktime_t ktime_get(void)
 		secs = xtime.tv_sec + wall_to_monotonic.tv_sec;
 		nsecs = xtime.tv_nsec + wall_to_monotonic.tv_nsec;
 		nsecs += timekeeping_get_ns();
+		/* If arch requires, add in gettimeoffset() */
+		nsecs += arch_gettimeoffset();
 
 	} while (read_seqretry(&xtime_lock, seq));
 	/*
@@ -280,6 +282,8 @@ void ktime_get_ts(struct timespec *ts)
 		*ts = xtime;
 		tomono = wall_to_monotonic;
 		nsecs = timekeeping_get_ns();
+		/* If arch requires, add in gettimeoffset() */
+		nsecs += arch_gettimeoffset();
 
 	} while (read_seqretry(&xtime_lock, seq));
 
@@ -802,14 +806,44 @@ static void timekeeping_adjust(s64 offset)
 	s64 error, interval = timekeeper.cycle_interval;
 	int adj;
 
+	/*
+	 * The point of this is to check if the error is greater then half
+	 * an interval.
+	 *
+	 * First we shift it down from NTP_SHIFT to clocksource->shifted nsecs.
+	 *
+	 * Note we subtract one in the shift, so that error is really error*2.
+	 * This "saves" dividing(shifting) intererval twice, but keeps the
+	 * (error > interval) comparision as still measuring if error is
+	 * larger then half an interval.
+	 *
+	 * Note: It does not "save" on aggrivation when reading the code.
+	 */
 	error = timekeeper.ntp_error >> (timekeeper.ntp_error_shift - 1);
 	if (error > interval) {
+		/*
+		 * We now divide error by 4(via shift), which checks if
+		 * the error is greater then twice the interval.
+		 * If it is greater, we need a bigadjust, if its smaller,
+		 * we can adjust by 1.
+		 */
 		error >>= 2;
+		/*
+		 * XXX - In update_wall_time, we round up to the next
+		 * nanosecond, and store the amount rounded up into
+		 * the error. This causes the likely below to be unlikely.
+		 *
+		 * The properfix is to avoid rounding up by using
+		 * the high precision timekeeper.xtime_nsec instead of
+		 * xtime.tv_nsec everywhere. Fixing this will take some
+		 * time.
+		 */
 		if (likely(error <= interval))
 			adj = 1;
 		else
 			adj = timekeeping_bigadjust(error, &interval, &offset);
 	} else if (error < -interval) {
+		/* See comment above, this is just switched for the negative */
 		error >>= 2;
 		if (likely(error >= -interval)) {
 			adj = -1;
@@ -817,9 +851,65 @@ static void timekeeping_adjust(s64 offset)
 			offset = -offset;
 		} else
 			adj = timekeeping_bigadjust(error, &interval, &offset);
-	} else
+	} else /* No adjustment needed */
 		return;
 
+	WARN_ONCE(timekeeper.clock->maxadj &&
+			(timekeeper.mult + adj > timekeeper.clock->mult +
+						timekeeper.clock->maxadj),
+			"Adjusting %s more then 11%% (%ld vs %ld)\n",
+			timekeeper.clock->name, (long)timekeeper.mult + adj,
+			(long)timekeeper.clock->mult +
+				timekeeper.clock->maxadj);
+	/*
+	 * So the following can be confusing.
+	 *
+	 * To keep things simple, lets assume adj == 1 for now.
+	 *
+	 * When adj != 1, remember that the interval and offset values
+	 * have been appropriately scaled so the math is the same.
+	 *
+	 * The basic idea here is that we're increasing the multiplier
+	 * by one, this causes the xtime_interval to be incremented by
+	 * one cycle_interval. This is because:
+	 *	xtime_interval = cycle_interval * mult
+	 * So if mult is being incremented by one:
+	 *	xtime_interval = cycle_interval * (mult + 1)
+	 * Its the same as:
+	 *	xtime_interval = (cycle_interval * mult) + cycle_interval
+	 * Which can be shortened to:
+	 *	xtime_interval += cycle_interval
+	 *
+	 * So offset stores the non-accumulated cycles. Thus the current
+	 * time (in shifted nanoseconds) is:
+	 *	now = (offset * adj) + xtime_nsec
+	 * Now, even though we're adjusting the clock frequency, we have
+	 * to keep time consistent. In other words, we can't jump back
+	 * in time, and we also want to avoid jumping forward in time.
+	 *
+	 * So given the same offset value, we need the time to be the same
+	 * both before and after the freq adjustment.
+	 *	now = (offset * adj_1) + xtime_nsec_1
+	 *	now = (offset * adj_2) + xtime_nsec_2
+	 * So:
+	 *	(offset * adj_1) + xtime_nsec_1 =
+	 *		(offset * adj_2) + xtime_nsec_2
+	 * And we know:
+	 *	adj_2 = adj_1 + 1
+	 * So:
+	 *	(offset * adj_1) + xtime_nsec_1 =
+	 *		(offset * (adj_1+1)) + xtime_nsec_2
+	 *	(offset * adj_1) + xtime_nsec_1 =
+	 *		(offset * adj_1) + offset + xtime_nsec_2
+	 * Canceling the sides:
+	 *	xtime_nsec_1 = offset + xtime_nsec_2
+	 * Which gives us:
+	 *	xtime_nsec_2 = xtime_nsec_1 - offset
+	 * Which simplfies to:
+	 *	xtime_nsec -= offset
+	 *
+	 * XXX - TODO: Doc ntp_error calculation.
+	 */
 	timekeeper.mult += adj;
 	timekeeper.xtime_interval += interval;
 	timekeeper.xtime_nsec -= offset;

kernel/timer.c

@@ -1368,7 +1368,7 @@ SYSCALL_DEFINE0(getppid)
 	int pid;
 
 	rcu_read_lock();
-	pid = task_tgid_vnr(current->real_parent);
+	pid = task_tgid_vnr(rcu_dereference(current->real_parent));
 	rcu_read_unlock();
 
 	return pid;

kernel/trace/ftrace.c

@@ -152,7 +152,6 @@ void clear_ftrace_function(void)
 	ftrace_pid_function = ftrace_stub;
 }
 
-#undef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST
 #ifndef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST
 /*
  * For those archs that do not test ftrace_trace_stop in their
@@ -1212,7 +1211,9 @@ ftrace_hash_move(struct ftrace_ops *ops, int enable,
 	if (!src->count) {
 		free_ftrace_hash_rcu(*dst);
 		rcu_assign_pointer(*dst, EMPTY_HASH);
-		return 0;
+		/* still need to update the function records */
+		ret = 0;
+		goto out;
 	}
 
 	/*

kernel/trace/trace_events.c

@@ -1078,7 +1078,6 @@ event_subsystem_dir(const char *name, struct dentry *d_events)
 	/* First see if we did not already create this dir */
 	list_for_each_entry(system, &event_subsystems, list) {
 		if (strcmp(system->name, name) == 0) {
-			__get_system(system);
 			system->nr_events++;
 			return system->entry;
 		}

kernel/trace/trace_events_filter.c

@@ -1649,7 +1649,9 @@ static int replace_system_preds(struct event_subsystem *system,
 		 */
 		err = replace_preds(call, NULL, ps, filter_string, true);
 		if (err)
-			goto fail;
+			call->flags |= TRACE_EVENT_FL_NO_SET_FILTER;
+		else
+			call->flags &= ~TRACE_EVENT_FL_NO_SET_FILTER;
 	}
 
 	list_for_each_entry(call, &ftrace_events, list) {
@@ -1658,6 +1660,9 @@ static int replace_system_preds(struct event_subsystem *system,
 		if (strcmp(call->class->system, system->name) != 0)
 			continue;
 
+		if (call->flags & TRACE_EVENT_FL_NO_SET_FILTER)
+			continue;
+
 		filter_item = kzalloc(sizeof(*filter_item), GFP_KERNEL);
 		if (!filter_item)
 			goto fail_mem;
@@ -1686,7 +1691,7 @@ static int replace_system_preds(struct event_subsystem *system,
 		 * replace the filter for the call.
 		 */
 		filter = call->filter;
-		call->filter = filter_item->filter;
+		rcu_assign_pointer(call->filter, filter_item->filter);
 		filter_item->filter = filter;
 
 		fail = false;
@@ -1741,7 +1746,7 @@ int apply_event_filter(struct ftrace_event_call *call, char *filter_string)
 		filter = call->filter;
 		if (!filter)
 			goto out_unlock;
-		call->filter = NULL;
+		RCU_INIT_POINTER(call->filter, NULL);
 		/* Make sure the filter is not being used */
 		synchronize_sched();
 		__free_filter(filter);
@@ -1782,7 +1787,7 @@ out:
 	 * string
 	 */
 	tmp = call->filter;
-	call->filter = filter;
+	rcu_assign_pointer(call->filter, filter);
 	if (tmp) {
 		/* Make sure the call is done with the filter */
 		synchronize_sched();