Merge commit 'v2.6.37' into sched/core

Merge reason: Merge the final .37 tree.

Signed-off-by: Ingo Molnar <mingo@elte.hu>

kernel/fork.c

@@ -275,6 +275,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig)
 
 	setup_thread_stack(tsk, orig);
 	clear_user_return_notifier(tsk);
+	clear_tsk_need_resched(tsk);
 	stackend = end_of_stack(tsk);
 	*stackend = STACK_END_MAGIC;	/* for overflow detection */
 

kernel/kthread.c

@@ -265,6 +265,17 @@ int kthreadd(void *unused)
 	return 0;
 }
 
+void __init_kthread_worker(struct kthread_worker *worker,
+				const char *name,
+				struct lock_class_key *key)
+{
+	spin_lock_init(&worker->lock);
+	lockdep_set_class_and_name(&worker->lock, key, name);
+	INIT_LIST_HEAD(&worker->work_list);
+	worker->task = NULL;
+}
+EXPORT_SYMBOL_GPL(__init_kthread_worker);
+
 /**
  * kthread_worker_fn - kthread function to process kthread_worker
  * @worker_ptr: pointer to initialized kthread_worker

kernel/perf_event.c

@@ -3824,6 +3824,8 @@ static void perf_event_task_event(struct perf_task_event *task_event)
 	rcu_read_lock();
 	list_for_each_entry_rcu(pmu, &pmus, entry) {
 		cpuctx = get_cpu_ptr(pmu->pmu_cpu_context);
+		if (cpuctx->active_pmu != pmu)
+			goto next;
 		perf_event_task_ctx(&cpuctx->ctx, task_event);
 
 		ctx = task_event->task_ctx;
@@ -3959,6 +3961,8 @@ static void perf_event_comm_event(struct perf_comm_event *comm_event)
 	rcu_read_lock();
 	list_for_each_entry_rcu(pmu, &pmus, entry) {
 		cpuctx = get_cpu_ptr(pmu->pmu_cpu_context);
+		if (cpuctx->active_pmu != pmu)
+			goto next;
 		perf_event_comm_ctx(&cpuctx->ctx, comm_event);
 
 		ctxn = pmu->task_ctx_nr;
@@ -4144,6 +4148,8 @@ got_name:
 	rcu_read_lock();
 	list_for_each_entry_rcu(pmu, &pmus, entry) {
 		cpuctx = get_cpu_ptr(pmu->pmu_cpu_context);
+		if (cpuctx->active_pmu != pmu)
+			goto next;
 		perf_event_mmap_ctx(&cpuctx->ctx, mmap_event,
 					vma->vm_flags & VM_EXEC);
 
@@ -4713,7 +4719,7 @@ static int perf_swevent_init(struct perf_event *event)
 		break;
 	}
 
-	if (event_id > PERF_COUNT_SW_MAX)
+	if (event_id >= PERF_COUNT_SW_MAX)
 		return -ENOENT;
 
 	if (!event->parent) {
@@ -5145,20 +5151,36 @@ static void *find_pmu_context(int ctxn)
 	return NULL;
 }
 
-static void free_pmu_context(void * __percpu cpu_context)
+static void update_pmu_context(struct pmu *pmu, struct pmu *old_pmu)
 {
-	struct pmu *pmu;
+	int cpu;
+
+	for_each_possible_cpu(cpu) {
+		struct perf_cpu_context *cpuctx;
+
+		cpuctx = per_cpu_ptr(pmu->pmu_cpu_context, cpu);
+
+		if (cpuctx->active_pmu == old_pmu)
+			cpuctx->active_pmu = pmu;
+	}
+}
+
+static void free_pmu_context(struct pmu *pmu)
+{
+	struct pmu *i;
 
 	mutex_lock(&pmus_lock);
 	/*
 	 * Like a real lame refcount.
 	 */
-	list_for_each_entry(pmu, &pmus, entry) {
-		if (pmu->pmu_cpu_context == cpu_context)
+	list_for_each_entry(i, &pmus, entry) {
+		if (i->pmu_cpu_context == pmu->pmu_cpu_context) {
+			update_pmu_context(i, pmu);
 			goto out;
+		}
 	}
 
-	free_percpu(cpu_context);
+	free_percpu(pmu->pmu_cpu_context);
 out:
 	mutex_unlock(&pmus_lock);
 }
@@ -5190,6 +5212,7 @@ int perf_pmu_register(struct pmu *pmu)
 		cpuctx->ctx.pmu = pmu;
 		cpuctx->jiffies_interval = 1;
 		INIT_LIST_HEAD(&cpuctx->rotation_list);
+		cpuctx->active_pmu = pmu;
 	}
 
 got_cpu_context:
@@ -5241,7 +5264,7 @@ void perf_pmu_unregister(struct pmu *pmu)
 	synchronize_rcu();
 
 	free_percpu(pmu->pmu_disable_count);
-	free_pmu_context(pmu->pmu_cpu_context);
+	free_pmu_context(pmu);
 }
 
 struct pmu *perf_init_event(struct perf_event *event)

kernel/power/swap.c

@@ -30,7 +30,7 @@
 
 #include "power.h"
 
-#define HIBERNATE_SIG	"LINHIB0001"
+#define HIBERNATE_SIG	"S1SUSPEND"
 
 /*
  *	The swap map is a data structure used for keeping track of each page

kernel/power/user.c

@@ -137,7 +137,7 @@ static int snapshot_release(struct inode *inode, struct file *filp)
 	free_all_swap_pages(data->swap);
 	if (data->frozen)
 		thaw_processes();
-	pm_notifier_call_chain(data->mode == O_WRONLY ?
+	pm_notifier_call_chain(data->mode == O_RDONLY ?
 			PM_POST_HIBERNATION : PM_POST_RESTORE);
 	atomic_inc(&snapshot_device_available);
 

kernel/resource.c

@@ -40,23 +40,6 @@ EXPORT_SYMBOL(iomem_resource);
 
 static DEFINE_RWLOCK(resource_lock);
 
-/*
- * By default, we allocate free space bottom-up.  The architecture can request
- * top-down by clearing this flag.  The user can override the architecture's
- * choice with the "resource_alloc_from_bottom" kernel boot option, but that
- * should only be a debugging tool.
- */
-int resource_alloc_from_bottom = 1;
-
-static __init int setup_alloc_from_bottom(char *s)
-{
-	printk(KERN_INFO
-	       "resource: allocating from bottom-up; please report a bug\n");
-	resource_alloc_from_bottom = 1;
-	return 0;
-}
-early_param("resource_alloc_from_bottom", setup_alloc_from_bottom);
-
 static void *r_next(struct seq_file *m, void *v, loff_t *pos)
 {
 	struct resource *p = v;
@@ -374,6 +357,10 @@ int __weak page_is_ram(unsigned long pfn)
 	return walk_system_ram_range(pfn, 1, NULL, __is_ram) == 1;
 }
 
+void __weak arch_remove_reservations(struct resource *avail)
+{
+}
+
 static resource_size_t simple_align_resource(void *data,
 					     const struct resource *avail,
 					     resource_size_t size,
@@ -396,75 +383,8 @@ static bool resource_contains(struct resource *res1, struct resource *res2)
 	return res1->start <= res2->start && res1->end >= res2->end;
 }
 
-/*
- * Find the resource before "child" in the sibling list of "root" children.
- */
-static struct resource *find_sibling_prev(struct resource *root, struct resource *child)
-{
-	struct resource *this;
-
-	for (this = root->child; this; this = this->sibling)
-		if (this->sibling == child)
-			return this;
-
-	return NULL;
-}
-
 /*
  * Find empty slot in the resource tree given range and alignment.
- * This version allocates from the end of the root resource first.
- */
-static int find_resource_from_top(struct resource *root, struct resource *new,
-				  resource_size_t size, resource_size_t min,
-				  resource_size_t max, resource_size_t align,
-				  resource_size_t (*alignf)(void *,
-						   const struct resource *,
-						   resource_size_t,
-						   resource_size_t),
-				  void *alignf_data)
-{
-	struct resource *this;
-	struct resource tmp, avail, alloc;
-
-	tmp.start = root->end;
-	tmp.end = root->end;
-
-	this = find_sibling_prev(root, NULL);
-	for (;;) {
-		if (this) {
-			if (this->end < root->end)
-				tmp.start = this->end + 1;
-		} else
-			tmp.start = root->start;
-
-		resource_clip(&tmp, min, max);
-
-		/* Check for overflow after ALIGN() */
-		avail = *new;
-		avail.start = ALIGN(tmp.start, align);
-		avail.end = tmp.end;
-		if (avail.start >= tmp.start) {
-			alloc.start = alignf(alignf_data, &avail, size, align);
-			alloc.end = alloc.start + size - 1;
-			if (resource_contains(&avail, &alloc)) {
-				new->start = alloc.start;
-				new->end = alloc.end;
-				return 0;
-			}
-		}
-
-		if (!this || this->start == root->start)
-			break;
-
-		tmp.end = this->start - 1;
-		this = find_sibling_prev(root, this);
-	}
-	return -EBUSY;
-}
-
-/*
- * Find empty slot in the resource tree given range and alignment.
- * This version allocates from the beginning of the root resource first.
  */
 static int find_resource(struct resource *root, struct resource *new,
 			 resource_size_t size, resource_size_t min,
@@ -478,23 +398,24 @@ static int find_resource(struct resource *root, struct resource *new,
 	struct resource *this = root->child;
 	struct resource tmp = *new, avail, alloc;
 
+	tmp.flags = new->flags;
 	tmp.start = root->start;
 	/*
-	 * Skip past an allocated resource that starts at 0, since the
-	 * assignment of this->start - 1 to tmp->end below would cause an
-	 * underflow.
+	 * Skip past an allocated resource that starts at 0, since the assignment
+	 * of this->start - 1 to tmp->end below would cause an underflow.
 	 */
 	if (this && this->start == 0) {
 		tmp.start = this->end + 1;
 		this = this->sibling;
 	}
-	for (;;) {
+	for(;;) {
 		if (this)
 			tmp.end = this->start - 1;
 		else
 			tmp.end = root->end;
 
 		resource_clip(&tmp, min, max);
+		arch_remove_reservations(&tmp);
 
 		/* Check for overflow after ALIGN() */
 		avail = *new;
@@ -509,10 +430,8 @@ static int find_resource(struct resource *root, struct resource *new,
 				return 0;
 			}
 		}
-
 		if (!this)
 			break;
-
 		tmp.start = this->end + 1;
 		this = this->sibling;
 	}
@@ -545,10 +464,7 @@ int allocate_resource(struct resource *root, struct resource *new,
 		alignf = simple_align_resource;
 
 	write_lock(&resource_lock);
-	if (resource_alloc_from_bottom)
-		err = find_resource(root, new, size, min, max, align, alignf, alignf_data);
-	else
-		err = find_resource_from_top(root, new, size, min, max, align, alignf, alignf_data);
+	err = find_resource(root, new, size, min, max, align, alignf, alignf_data);
 	if (err >= 0 && __request_resource(root, new))
 		err = -EBUSY;
 	write_unlock(&resource_lock);

kernel/sched.c

@@ -642,22 +642,18 @@ static inline struct task_group *task_group(struct task_struct *p)
 
 #endif /* CONFIG_CGROUP_SCHED */
 
-static u64 irq_time_cpu(int cpu);
-static void sched_irq_time_avg_update(struct rq *rq, u64 irq_time);
+static void update_rq_clock_task(struct rq *rq, s64 delta);
 
-inline void update_rq_clock(struct rq *rq)
+static void update_rq_clock(struct rq *rq)
 {
-	if (!rq->skip_clock_update) {
-		int cpu = cpu_of(rq);
-		u64 irq_time;
+	s64 delta;
 
-		rq->clock = sched_clock_cpu(cpu);
-		irq_time = irq_time_cpu(cpu);
-		if (rq->clock - irq_time > rq->clock_task)
-			rq->clock_task = rq->clock - irq_time;
+	if (rq->skip_clock_update)
+		return;
 
-		sched_irq_time_avg_update(rq, irq_time);
-	}
+	delta = sched_clock_cpu(cpu_of(rq)) - rq->clock;
+	rq->clock += delta;
+	update_rq_clock_task(rq, delta);
 }
 
 /*
@@ -1795,10 +1791,9 @@ static void deactivate_task(struct rq *rq, struct task_struct *p, int flags)
  * They are read and saved off onto struct rq in update_rq_clock().
  * This may result in other CPU reading this CPU's irq time and can
  * race with irq/account_system_vtime on this CPU. We would either get old
- * or new value (or semi updated value on 32 bit) with a side effect of
- * accounting a slice of irq time to wrong task when irq is in progress
- * while we read rq->clock. That is a worthy compromise in place of having
- * locks on each irq in account_system_time.
+ * or new value with a side effect of accounting a slice of irq time to wrong
+ * task when irq is in progress while we read rq->clock. That is a worthy
+ * compromise in place of having locks on each irq in account_system_time.
  */
 static DEFINE_PER_CPU(u64, cpu_hardirq_time);
 static DEFINE_PER_CPU(u64, cpu_softirq_time);
@@ -1816,19 +1811,58 @@ void disable_sched_clock_irqtime(void)
 	sched_clock_irqtime = 0;
 }
 
-static u64 irq_time_cpu(int cpu)
-{
-	if (!sched_clock_irqtime)
-		return 0;
+#ifndef CONFIG_64BIT
+static DEFINE_PER_CPU(seqcount_t, irq_time_seq);
 
-	return per_cpu(cpu_softirq_time, cpu) + per_cpu(cpu_hardirq_time, cpu);
+static inline void irq_time_write_begin(void)
+{
+	__this_cpu_inc(irq_time_seq.sequence);
+	smp_wmb();
 }
 
+static inline void irq_time_write_end(void)
+{
+	smp_wmb();
+	__this_cpu_inc(irq_time_seq.sequence);
+}
+
+static inline u64 irq_time_read(int cpu)
+{
+	u64 irq_time;
+	unsigned seq;
+
+	do {
+		seq = read_seqcount_begin(&per_cpu(irq_time_seq, cpu));
+		irq_time = per_cpu(cpu_softirq_time, cpu) +
+			   per_cpu(cpu_hardirq_time, cpu);
+	} while (read_seqcount_retry(&per_cpu(irq_time_seq, cpu), seq));
+
+	return irq_time;
+}
+#else /* CONFIG_64BIT */
+static inline void irq_time_write_begin(void)
+{
+}
+
+static inline void irq_time_write_end(void)
+{
+}
+
+static inline u64 irq_time_read(int cpu)
+{
+	return per_cpu(cpu_softirq_time, cpu) + per_cpu(cpu_hardirq_time, cpu);
+}
+#endif /* CONFIG_64BIT */
+
+/*
+ * Called before incrementing preempt_count on {soft,}irq_enter
+ * and before decrementing preempt_count on {soft,}irq_exit.
+ */
 void account_system_vtime(struct task_struct *curr)
 {
 	unsigned long flags;
+	s64 delta;
 	int cpu;
-	u64 now, delta;
 
 	if (!sched_clock_irqtime)
 		return;
@@ -1836,9 +1870,10 @@ void account_system_vtime(struct task_struct *curr)
 	local_irq_save(flags);
 
 	cpu = smp_processor_id();
-	now = sched_clock_cpu(cpu);
-	delta = now - per_cpu(irq_start_time, cpu);
-	per_cpu(irq_start_time, cpu) = now;
+	delta = sched_clock_cpu(cpu) - __this_cpu_read(irq_start_time);
+	__this_cpu_add(irq_start_time, delta);
+
+	irq_time_write_begin();
 	/*
 	 * We do not account for softirq time from ksoftirqd here.
 	 * We want to continue accounting softirq time to ksoftirqd thread
@@ -1846,33 +1881,55 @@ void account_system_vtime(struct task_struct *curr)
 	 * that do not consume any time, but still wants to run.
 	 */
 	if (hardirq_count())
-		per_cpu(cpu_hardirq_time, cpu) += delta;
+		__this_cpu_add(cpu_hardirq_time, delta);
 	else if (in_serving_softirq() && !(curr->flags & PF_KSOFTIRQD))
-		per_cpu(cpu_softirq_time, cpu) += delta;
+		__this_cpu_add(cpu_softirq_time, delta);
 
+	irq_time_write_end();
 	local_irq_restore(flags);
 }
 EXPORT_SYMBOL_GPL(account_system_vtime);
 
-static void sched_irq_time_avg_update(struct rq *rq, u64 curr_irq_time)
+static void update_rq_clock_task(struct rq *rq, s64 delta)
 {
-	if (sched_clock_irqtime && sched_feat(NONIRQ_POWER)) {
-		u64 delta_irq = curr_irq_time - rq->prev_irq_time;
-		rq->prev_irq_time = curr_irq_time;
-		sched_rt_avg_update(rq, delta_irq);
-	}
+	s64 irq_delta;
+
+	irq_delta = irq_time_read(cpu_of(rq)) - rq->prev_irq_time;
+
+	/*
+	 * Since irq_time is only updated on {soft,}irq_exit, we might run into
+	 * this case when a previous update_rq_clock() happened inside a
+	 * {soft,}irq region.
+	 *
+	 * When this happens, we stop ->clock_task and only update the
+	 * prev_irq_time stamp to account for the part that fit, so that a next
+	 * update will consume the rest. This ensures ->clock_task is
+	 * monotonic.
+	 *
+	 * It does however cause some slight miss-attribution of {soft,}irq
+	 * time, a more accurate solution would be to update the irq_time using
+	 * the current rq->clock timestamp, except that would require using
+	 * atomic ops.
+	 */
+	if (irq_delta > delta)
+		irq_delta = delta;
+
+	rq->prev_irq_time += irq_delta;
+	delta -= irq_delta;
+	rq->clock_task += delta;
+
+	if (irq_delta && sched_feat(NONIRQ_POWER))
+		sched_rt_avg_update(rq, irq_delta);
 }
 
-#else
+#else /* CONFIG_IRQ_TIME_ACCOUNTING */
 
-static u64 irq_time_cpu(int cpu)
+static void update_rq_clock_task(struct rq *rq, s64 delta)
 {
-	return 0;
+	rq->clock_task += delta;
 }
 
-static void sched_irq_time_avg_update(struct rq *rq, u64 curr_irq_time) { }
-
-#endif
+#endif /* CONFIG_IRQ_TIME_ACCOUNTING */
 
 #include "sched_idletask.c"
 #include "sched_fair.c"
@@ -2001,7 +2058,7 @@ static void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags)
 	 * A queue event has occurred, and we're going to schedule.  In
 	 * this case, we can save a useless back to back clock update.
 	 */
-	if (test_tsk_need_resched(rq->curr))
+	if (rq->curr->se.on_rq && test_tsk_need_resched(rq->curr))
 		rq->skip_clock_update = 1;
 }
 
@@ -2988,6 +3045,15 @@ static long calc_load_fold_active(struct rq *this_rq)
 	return delta;
 }
 
+static unsigned long
+calc_load(unsigned long load, unsigned long exp, unsigned long active)
+{
+	load *= exp;
+	load += active * (FIXED_1 - exp);
+	load += 1UL << (FSHIFT - 1);
+	return load >> FSHIFT;
+}
+
 #ifdef CONFIG_NO_HZ
 /*
  * For NO_HZ we delay the active fold to the next LOAD_FREQ update.
@@ -3017,6 +3083,128 @@ static long calc_load_fold_idle(void)
 
 	return delta;
 }
+
+/**
+ * fixed_power_int - compute: x^n, in O(log n) time
+ *
+ * @x:         base of the power
+ * @frac_bits: fractional bits of @x
+ * @n:         power to raise @x to.
+ *
+ * By exploiting the relation between the definition of the natural power
+ * function: x^n := x*x*...*x (x multiplied by itself for n times), and
+ * the binary encoding of numbers used by computers: n := \Sum n_i * 2^i,
+ * (where: n_i \elem {0, 1}, the binary vector representing n),
+ * we find: x^n := x^(\Sum n_i * 2^i) := \Prod x^(n_i * 2^i), which is
+ * of course trivially computable in O(log_2 n), the length of our binary
+ * vector.
+ */
+static unsigned long
+fixed_power_int(unsigned long x, unsigned int frac_bits, unsigned int n)
+{
+	unsigned long result = 1UL << frac_bits;
+
+	if (n) for (;;) {
+		if (n & 1) {
+			result *= x;
+			result += 1UL << (frac_bits - 1);
+			result >>= frac_bits;
+		}
+		n >>= 1;
+		if (!n)
+			break;
+		x *= x;
+		x += 1UL << (frac_bits - 1);
+		x >>= frac_bits;
+	}
+
+	return result;
+}
+
+/*
+ * a1 = a0 * e + a * (1 - e)
+ *
+ * a2 = a1 * e + a * (1 - e)
+ *    = (a0 * e + a * (1 - e)) * e + a * (1 - e)
+ *    = a0 * e^2 + a * (1 - e) * (1 + e)
+ *
+ * a3 = a2 * e + a * (1 - e)
+ *    = (a0 * e^2 + a * (1 - e) * (1 + e)) * e + a * (1 - e)
+ *    = a0 * e^3 + a * (1 - e) * (1 + e + e^2)
+ *
+ *  ...
+ *
+ * an = a0 * e^n + a * (1 - e) * (1 + e + ... + e^n-1) [1]
+ *    = a0 * e^n + a * (1 - e) * (1 - e^n)/(1 - e)
+ *    = a0 * e^n + a * (1 - e^n)
+ *
+ * [1] application of the geometric series:
+ *
+ *              n         1 - x^(n+1)
+ *     S_n := \Sum x^i = -------------
+ *             i=0          1 - x
+ */
+static unsigned long
+calc_load_n(unsigned long load, unsigned long exp,
+	    unsigned long active, unsigned int n)
+{
+
+	return calc_load(load, fixed_power_int(exp, FSHIFT, n), active);
+}
+
+/*
+ * NO_HZ can leave us missing all per-cpu ticks calling
+ * calc_load_account_active(), but since an idle CPU folds its delta into
+ * calc_load_tasks_idle per calc_load_account_idle(), all we need to do is fold
+ * in the pending idle delta if our idle period crossed a load cycle boundary.
+ *
+ * Once we've updated the global active value, we need to apply the exponential
+ * weights adjusted to the number of cycles missed.
+ */
+static void calc_global_nohz(unsigned long ticks)
+{
+	long delta, active, n;
+
+	if (time_before(jiffies, calc_load_update))
+		return;
+
+	/*
+	 * If we crossed a calc_load_update boundary, make sure to fold
+	 * any pending idle changes, the respective CPUs might have
+	 * missed the tick driven calc_load_account_active() update
+	 * due to NO_HZ.
+	 */
+	delta = calc_load_fold_idle();
+	if (delta)
+		atomic_long_add(delta, &calc_load_tasks);
+
+	/*
+	 * If we were idle for multiple load cycles, apply them.
+	 */
+	if (ticks >= LOAD_FREQ) {
+		n = ticks / LOAD_FREQ;
+
+		active = atomic_long_read(&calc_load_tasks);
+		active = active > 0 ? active * FIXED_1 : 0;
+
+		avenrun[0] = calc_load_n(avenrun[0], EXP_1, active, n);
+		avenrun[1] = calc_load_n(avenrun[1], EXP_5, active, n);
+		avenrun[2] = calc_load_n(avenrun[2], EXP_15, active, n);
+
+		calc_load_update += n * LOAD_FREQ;
+	}
+
+	/*
+	 * Its possible the remainder of the above division also crosses
+	 * a LOAD_FREQ period, the regular check in calc_global_load()
+	 * which comes after this will take care of that.
+	 *
+	 * Consider us being 11 ticks before a cycle completion, and us
+	 * sleeping for 4*LOAD_FREQ + 22 ticks, then the above code will
+	 * age us 4 cycles, and the test in calc_global_load() will
+	 * pick up the final one.
+	 */
+}
 #else
 static void calc_load_account_idle(struct rq *this_rq)
 {
@@ -3026,6 +3214,10 @@ static inline long calc_load_fold_idle(void)
 {
 	return 0;
 }
+
+static void calc_global_nohz(unsigned long ticks)
+{
+}
 #endif
 
 /**
@@ -3043,24 +3235,17 @@ void get_avenrun(unsigned long *loads, unsigned long offset, int shift)
 	loads[2] = (avenrun[2] + offset) << shift;
 }
 
-static unsigned long
-calc_load(unsigned long load, unsigned long exp, unsigned long active)
-{
-	load *= exp;
-	load += active * (FIXED_1 - exp);
-	return load >> FSHIFT;
-}
-
 /*
  * calc_load - update the avenrun load estimates 10 ticks after the
  * CPUs have updated calc_load_tasks.
  */
-void calc_global_load(void)
+void calc_global_load(unsigned long ticks)
 {
-	unsigned long upd = calc_load_update + 10;
 	long active;
 
-	if (time_before(jiffies, upd))
+	calc_global_nohz(ticks);
+
+	if (time_before(jiffies, calc_load_update + 10))
 		return;
 
 	active = atomic_long_read(&calc_load_tasks);
@@ -3714,7 +3899,6 @@ static void put_prev_task(struct rq *rq, struct task_struct *prev)
 {
 	if (prev->se.on_rq)
 		update_rq_clock(rq);
-	rq->skip_clock_update = 0;
 	prev->sched_class->put_prev_task(rq, prev);
 }
 
@@ -3772,7 +3956,6 @@ need_resched_nonpreemptible:
 		hrtick_clear(rq);
 
 	raw_spin_lock_irq(&rq->lock);
-	clear_tsk_need_resched(prev);
 
 	switch_count = &prev->nivcsw;
 	if (prev->state && !(preempt_count() & PREEMPT_ACTIVE)) {
@@ -3804,6 +3987,8 @@ need_resched_nonpreemptible:
 
 	put_prev_task(rq, prev);
 	next = pick_next_task(rq);
+	clear_tsk_need_resched(prev);
+	rq->skip_clock_update = 0;
 
 	if (likely(prev != next)) {
 		sched_info_switch(prev, next);

kernel/taskstats.c

@@ -349,25 +349,47 @@ static int parse(struct nlattr *na, struct cpumask *mask)
 	return ret;
 }
 
+#ifdef CONFIG_IA64
+#define TASKSTATS_NEEDS_PADDING 1
+#endif
+
 static struct taskstats *mk_reply(struct sk_buff *skb, int type, u32 pid)
 {
 	struct nlattr *na, *ret;
 	int aggr;
 
-	/* If we don't pad, we end up with alignment on a 4 byte boundary.
-	 * This causes lots of runtime warnings on systems requiring 8 byte
-	 * alignment */
-	u32 pids[2] = { pid, 0 };
-	int pid_size = ALIGN(sizeof(pid), sizeof(long));
-
 	aggr = (type == TASKSTATS_TYPE_PID)
 			? TASKSTATS_TYPE_AGGR_PID
 			: TASKSTATS_TYPE_AGGR_TGID;
 
+	/*
+	 * The taskstats structure is internally aligned on 8 byte
+	 * boundaries but the layout of the aggregrate reply, with
+	 * two NLA headers and the pid (each 4 bytes), actually
+	 * force the entire structure to be unaligned. This causes
+	 * the kernel to issue unaligned access warnings on some
+	 * architectures like ia64. Unfortunately, some software out there
+	 * doesn't properly unroll the NLA packet and assumes that the start
+	 * of the taskstats structure will always be 20 bytes from the start
+	 * of the netlink payload. Aligning the start of the taskstats
+	 * structure breaks this software, which we don't want. So, for now
+	 * the alignment only happens on architectures that require it
+	 * and those users will have to update to fixed versions of those
+	 * packages. Space is reserved in the packet only when needed.
+	 * This ifdef should be removed in several years e.g. 2012 once
+	 * we can be confident that fixed versions are installed on most
+	 * systems. We add the padding before the aggregate since the
+	 * aggregate is already a defined type.
+	 */
+#ifdef TASKSTATS_NEEDS_PADDING
+	if (nla_put(skb, TASKSTATS_TYPE_NULL, 0, NULL) < 0)
+		goto err;
+#endif
 	na = nla_nest_start(skb, aggr);
 	if (!na)
 		goto err;
-	if (nla_put(skb, type, pid_size, pids) < 0)
+
+	if (nla_put(skb, type, sizeof(pid), &pid) < 0)
 		goto err;
 	ret = nla_reserve(skb, TASKSTATS_TYPE_STATS, sizeof(struct taskstats));
 	if (!ret)
@@ -456,6 +478,18 @@ out:
 	return rc;
 }
 
+static size_t taskstats_packet_size(void)
+{
+	size_t size;
+
+	size = nla_total_size(sizeof(u32)) +
+		nla_total_size(sizeof(struct taskstats)) + nla_total_size(0);
+#ifdef TASKSTATS_NEEDS_PADDING
+	size += nla_total_size(0); /* Padding for alignment */
+#endif
+	return size;
+}
+
 static int cmd_attr_pid(struct genl_info *info)
 {
 	struct taskstats *stats;
@@ -464,8 +498,7 @@ static int cmd_attr_pid(struct genl_info *info)
 	u32 pid;
 	int rc;
 
-	size = nla_total_size(sizeof(u32)) +
-		nla_total_size(sizeof(struct taskstats)) + nla_total_size(0);
+	size = taskstats_packet_size();
 
 	rc = prepare_reply(info, TASKSTATS_CMD_NEW, &rep_skb, size);
 	if (rc < 0)
@@ -494,8 +527,7 @@ static int cmd_attr_tgid(struct genl_info *info)
 	u32 tgid;
 	int rc;
 
-	size = nla_total_size(sizeof(u32)) +
-		nla_total_size(sizeof(struct taskstats)) + nla_total_size(0);
+	size = taskstats_packet_size();
 
 	rc = prepare_reply(info, TASKSTATS_CMD_NEW, &rep_skb, size);
 	if (rc < 0)
@@ -570,8 +602,7 @@ void taskstats_exit(struct task_struct *tsk, int group_dead)
 	/*
 	 * Size includes space for nested attributes
 	 */
-	size = nla_total_size(sizeof(u32)) +
-		nla_total_size(sizeof(struct taskstats)) + nla_total_size(0);
+	size = taskstats_packet_size();
 
 	is_thread_group = !!taskstats_tgid_alloc(tsk);
 	if (is_thread_group) {

kernel/timer.c

@@ -1252,6 +1252,12 @@ unsigned long get_next_timer_interrupt(unsigned long now)
 	struct tvec_base *base = __get_cpu_var(tvec_bases);
 	unsigned long expires;
 
+	/*
+	 * Pretend that there is no timer pending if the cpu is offline.
+	 * Possible pending timers will be migrated later to an active cpu.
+	 */
+	if (cpu_is_offline(smp_processor_id()))
+		return now + NEXT_TIMER_MAX_DELTA;
 	spin_lock(&base->lock);
 	if (time_before_eq(base->next_timer, base->timer_jiffies))
 		base->next_timer = __next_timer_interrupt(base);
@@ -1319,7 +1325,7 @@ void do_timer(unsigned long ticks)
 {
 	jiffies_64 += ticks;
 	update_wall_time();
-	calc_global_load();
+	calc_global_load(ticks);
 }
 
 #ifdef __ARCH_WANT_SYS_ALARM

kernel/trace/ring_buffer.c

@@ -3853,6 +3853,13 @@ int ring_buffer_read_page(struct ring_buffer *buffer,
 
 		/* Need to copy one event at a time */
 		do {
+			/* We need the size of one event, because
+			 * rb_advance_reader only advances by one event,
+			 * whereas rb_event_ts_length may include the size of
+			 * one or two events.
+			 * We have already ensured there's enough space if this
+			 * is a time extend. */
+			size = rb_event_length(event);
 			memcpy(bpage->data + pos, rpage->data + rpos, size);
 
 			len -= size;
@@ -3867,7 +3874,7 @@ int ring_buffer_read_page(struct ring_buffer *buffer,
 			event = rb_reader_event(cpu_buffer);
 			/* Always keep the time extend and data together */
 			size = rb_event_ts_length(event);
-		} while (len > size);
+		} while (len >= size);
 
 		/* update bpage */
 		local_set(&bpage->commit, pos);

kernel/trace/trace.c

@@ -2338,11 +2338,19 @@ tracing_write_stub(struct file *filp, const char __user *ubuf,
 	return count;
 }
 
+static loff_t tracing_seek(struct file *file, loff_t offset, int origin)
+{
+	if (file->f_mode & FMODE_READ)
+		return seq_lseek(file, offset, origin);
+	else
+		return 0;
+}
+
 static const struct file_operations tracing_fops = {
 	.open		= tracing_open,
 	.read		= seq_read,
 	.write		= tracing_write_stub,
-	.llseek		= seq_lseek,
+	.llseek		= tracing_seek,
 	.release	= tracing_release,
 };
 

kernel/user.c

@@ -158,6 +158,7 @@ struct user_struct *alloc_uid(struct user_namespace *ns, uid_t uid)
 		spin_lock_irq(&uidhash_lock);
 		up = uid_hash_find(uid, hashent);
 		if (up) {
+			put_user_ns(ns);
 			key_put(new->uid_keyring);
 			key_put(new->session_keyring);
 			kmem_cache_free(uid_cachep, new);

kernel/watchdog.c

@@ -364,7 +364,8 @@ static int watchdog_nmi_enable(int cpu)
 		goto out_save;
 	}
 
-	printk(KERN_ERR "NMI watchdog failed to create perf event on cpu%i: %p\n", cpu, event);
+	printk(KERN_ERR "NMI watchdog disabled for cpu%i: unable to create perf event: %ld\n",
+	       cpu, PTR_ERR(event));
 	return PTR_ERR(event);
 
 	/* success path */