Merge commit 'origin/master' into for-linus/xen/master

* commit 'origin/master': (4825 commits)
  Fix build errors due to CONFIG_BRANCH_TRACER=y
  parport: Use the PCI IRQ if offered
  tty: jsm cleanups
  Adjust path to gpio headers
  KGDB_SERIAL_CONSOLE check for module
  Change KCONFIG name
  tty: Blackin CTS/RTS
  Change hardware flow control from poll to interrupt driven
  Add support for the MAX3100 SPI UART.
  lanana: assign a device name and numbering for MAX3100
  serqt: initial clean up pass for tty side
  tty: Use the generic RS485 ioctl on CRIS
  tty: Correct inline types for tty_driver_kref_get()
  splice: fix deadlock in splicing to file
  nilfs2: support nanosecond timestamp
  nilfs2: introduce secondary super block
  nilfs2: simplify handling of active state of segments
  nilfs2: mark minor flag for checkpoint created by internal operation
  nilfs2: clean up sketch file
  nilfs2: super block operations fix endian bug
  ...

Conflicts:
	arch/x86/include/asm/thread_info.h
	arch/x86/lguest/boot.c
	drivers/xen/manage.c

1 files changed, 125 insertions, 36 deletions

diff --git a/kernel/sched.c b/kernel/sched.c
index 133762aece5..b38bd96098f 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -231,13 +231,20 @@ static void start_rt_bandwidth(struct rt_bandwidth *rt_b)
 
 	spin_lock(&rt_b->rt_runtime_lock);
 	for (;;) {
+		unsigned long delta;
+		ktime_t soft, hard;
+
 		if (hrtimer_active(&rt_b->rt_period_timer))
 			break;
 
 		now = hrtimer_cb_get_time(&rt_b->rt_period_timer);
 		hrtimer_forward(&rt_b->rt_period_timer, now, rt_b->rt_period);
-		hrtimer_start_expires(&rt_b->rt_period_timer,
-				HRTIMER_MODE_ABS);
+
+		soft = hrtimer_get_softexpires(&rt_b->rt_period_timer);
+		hard = hrtimer_get_expires(&rt_b->rt_period_timer);
+		delta = ktime_to_ns(ktime_sub(hard, soft));
+		__hrtimer_start_range_ns(&rt_b->rt_period_timer, soft, delta,
+				HRTIMER_MODE_ABS, 0);
 	}
 	spin_unlock(&rt_b->rt_runtime_lock);
 }
@@ -1110,7 +1117,7 @@ static void hrtick_start(struct rq *rq, u64 delay)
 	if (rq == this_rq()) {
 		hrtimer_restart(timer);
 	} else if (!rq->hrtick_csd_pending) {
-		__smp_call_function_single(cpu_of(rq), &rq->hrtick_csd);
+		__smp_call_function_single(cpu_of(rq), &rq->hrtick_csd, 0);
 		rq->hrtick_csd_pending = 1;
 	}
 }
@@ -1146,7 +1153,8 @@ static __init void init_hrtick(void)
  */
 static void hrtick_start(struct rq *rq, u64 delay)
 {
-	hrtimer_start(&rq->hrtick_timer, ns_to_ktime(delay), HRTIMER_MODE_REL);
+	__hrtimer_start_range_ns(&rq->hrtick_timer, ns_to_ktime(delay), 0,
+			HRTIMER_MODE_REL, 0);
 }
 
 static inline void init_hrtick(void)
@@ -3818,19 +3826,23 @@ find_busiest_queue(struct sched_group *group, enum cpu_idle_type idle,
  */
 #define MAX_PINNED_INTERVAL	512
 
+/* Working cpumask for load_balance and load_balance_newidle. */
+static DEFINE_PER_CPU(cpumask_var_t, load_balance_tmpmask);
+
 /*
  * Check this_cpu to ensure it is balanced within domain. Attempt to move
  * tasks if there is an imbalance.
  */
 static int load_balance(int this_cpu, struct rq *this_rq,
 			struct sched_domain *sd, enum cpu_idle_type idle,
-			int *balance, struct cpumask *cpus)
+			int *balance)
 {
 	int ld_moved, all_pinned = 0, active_balance = 0, sd_idle = 0;
 	struct sched_group *group;
 	unsigned long imbalance;
 	struct rq *busiest;
 	unsigned long flags;
+	struct cpumask *cpus = __get_cpu_var(load_balance_tmpmask);
 
 	cpumask_setall(cpus);
 
@@ -3985,8 +3997,7 @@ out:
  * this_rq is locked.
  */
 static int
-load_balance_newidle(int this_cpu, struct rq *this_rq, struct sched_domain *sd,
-			struct cpumask *cpus)
+load_balance_newidle(int this_cpu, struct rq *this_rq, struct sched_domain *sd)
 {
 	struct sched_group *group;
 	struct rq *busiest = NULL;
@@ -3994,6 +4005,7 @@ load_balance_newidle(int this_cpu, struct rq *this_rq, struct sched_domain *sd,
 	int ld_moved = 0;
 	int sd_idle = 0;
 	int all_pinned = 0;
+	struct cpumask *cpus = __get_cpu_var(load_balance_tmpmask);
 
 	cpumask_setall(cpus);
 
@@ -4134,10 +4146,6 @@ static void idle_balance(int this_cpu, struct rq *this_rq)
 	struct sched_domain *sd;
 	int pulled_task = 0;
 	unsigned long next_balance = jiffies + HZ;
-	cpumask_var_t tmpmask;
-
-	if (!alloc_cpumask_var(&tmpmask, GFP_ATOMIC))
-		return;
 
 	for_each_domain(this_cpu, sd) {
 		unsigned long interval;
@@ -4148,7 +4156,7 @@ static void idle_balance(int this_cpu, struct rq *this_rq)
 		if (sd->flags & SD_BALANCE_NEWIDLE)
 			/* If we've pulled tasks over stop searching: */
 			pulled_task = load_balance_newidle(this_cpu, this_rq,
-							   sd, tmpmask);
+							   sd);
 
 		interval = msecs_to_jiffies(sd->balance_interval);
 		if (time_after(next_balance, sd->last_balance + interval))
@@ -4163,7 +4171,6 @@ static void idle_balance(int this_cpu, struct rq *this_rq)
 		 */
 		this_rq->next_balance = next_balance;
 	}
-	free_cpumask_var(tmpmask);
 }
 
 /*
@@ -4313,11 +4320,6 @@ static void rebalance_domains(int cpu, enum cpu_idle_type idle)
 	unsigned long next_balance = jiffies + 60*HZ;
 	int update_next_balance = 0;
 	int need_serialize;
-	cpumask_var_t tmp;
-
-	/* Fails alloc?  Rebalancing probably not a priority right now. */
-	if (!alloc_cpumask_var(&tmp, GFP_ATOMIC))
-		return;
 
 	for_each_domain(cpu, sd) {
 		if (!(sd->flags & SD_LOAD_BALANCE))
@@ -4342,7 +4344,7 @@ static void rebalance_domains(int cpu, enum cpu_idle_type idle)
 		}
 
 		if (time_after_eq(jiffies, sd->last_balance + interval)) {
-			if (load_balance(cpu, rq, sd, idle, &balance, tmp)) {
+			if (load_balance(cpu, rq, sd, idle, &balance)) {
 				/*
 				 * We've pulled tasks over so either we're no
 				 * longer idle, or one of our SMT siblings is
@@ -4376,8 +4378,6 @@ out:
 	 */
 	if (likely(update_next_balance))
 		rq->next_balance = next_balance;
-
-	free_cpumask_var(tmp);
 }
 
 /*
@@ -4781,10 +4781,7 @@ void scheduler_tick(void)
 #endif
 }
 
-#if defined(CONFIG_PREEMPT) && (defined(CONFIG_DEBUG_PREEMPT) || \
-				defined(CONFIG_PREEMPT_TRACER))
-
-static inline unsigned long get_parent_ip(unsigned long addr)
+unsigned long get_parent_ip(unsigned long addr)
 {
 	if (in_lock_functions(addr)) {
 		addr = CALLER_ADDR2;
@@ -4794,6 +4791,9 @@ static inline unsigned long get_parent_ip(unsigned long addr)
 	return addr;
 }
 
+#if defined(CONFIG_PREEMPT) && (defined(CONFIG_DEBUG_PREEMPT) || \
+				defined(CONFIG_PREEMPT_TRACER))
+
 void __kprobes add_preempt_count(int val)
 {
 #ifdef CONFIG_DEBUG_PREEMPT
@@ -4942,15 +4942,13 @@ pick_next_task(struct rq *rq)
 /*
  * schedule() is the main scheduler function.
  */
-asmlinkage void __sched schedule(void)
+asmlinkage void __sched __schedule(void)
 {
 	struct task_struct *prev, *next;
 	unsigned long *switch_count;
 	struct rq *rq;
 	int cpu;
 
-need_resched:
-	preempt_disable();
 	cpu = smp_processor_id();
 	rq = cpu_rq(cpu);
 	rcu_qsctr_inc(cpu);
@@ -5007,13 +5005,80 @@ need_resched_nonpreemptible:
 
 	if (unlikely(reacquire_kernel_lock(current) < 0))
 		goto need_resched_nonpreemptible;
+}
 
+asmlinkage void __sched schedule(void)
+{
+need_resched:
+	preempt_disable();
+	__schedule();
 	preempt_enable_no_resched();
 	if (unlikely(test_thread_flag(TIF_NEED_RESCHED)))
 		goto need_resched;
 }
 EXPORT_SYMBOL(schedule);
 
+#ifdef CONFIG_SMP
+/*
+ * Look out! "owner" is an entirely speculative pointer
+ * access and not reliable.
+ */
+int mutex_spin_on_owner(struct mutex *lock, struct thread_info *owner)
+{
+	unsigned int cpu;
+	struct rq *rq;
+
+	if (!sched_feat(OWNER_SPIN))
+		return 0;
+
+#ifdef CONFIG_DEBUG_PAGEALLOC
+	/*
+	 * Need to access the cpu field knowing that
+	 * DEBUG_PAGEALLOC could have unmapped it if
+	 * the mutex owner just released it and exited.
+	 */
+	if (probe_kernel_address(&owner->cpu, cpu))
+		goto out;
+#else
+	cpu = owner->cpu;
+#endif
+
+	/*
+	 * Even if the access succeeded (likely case),
+	 * the cpu field may no longer be valid.
+	 */
+	if (cpu >= nr_cpumask_bits)
+		goto out;
+
+	/*
+	 * We need to validate that we can do a
+	 * get_cpu() and that we have the percpu area.
+	 */
+	if (!cpu_online(cpu))
+		goto out;
+
+	rq = cpu_rq(cpu);
+
+	for (;;) {
+		/*
+		 * Owner changed, break to re-assess state.
+		 */
+		if (lock->owner != owner)
+			break;
+
+		/*
+		 * Is that owner really running on that cpu?
+		 */
+		if (task_thread_info(rq->curr) != owner || need_resched())
+			return 0;
+
+		cpu_relax();
+	}
+out:
+	return 1;
+}
+#endif
+
 #ifdef CONFIG_PREEMPT
 /*
  * this is the entry point to schedule() from in-kernel preemption
@@ -5131,11 +5196,17 @@ void __wake_up_locked(wait_queue_head_t *q, unsigned int mode)
 	__wake_up_common(q, mode, 1, 0, NULL);
 }
 
+void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key)
+{
+	__wake_up_common(q, mode, 1, 0, key);
+}
+
 /**
- * __wake_up_sync - wake up threads blocked on a waitqueue.
+ * __wake_up_sync_key - wake up threads blocked on a waitqueue.
  * @q: the waitqueue
  * @mode: which threads
  * @nr_exclusive: how many wake-one or wake-many threads to wake up
+ * @key: opaque value to be passed to wakeup targets
  *
  * The sync wakeup differs that the waker knows that it will schedule
  * away soon, so while the target thread will be woken up, it will not
@@ -5144,8 +5215,8 @@ void __wake_up_locked(wait_queue_head_t *q, unsigned int mode)
  *
  * On UP it can prevent extra preemption.
  */
-void
-__wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr_exclusive)
+void __wake_up_sync_key(wait_queue_head_t *q, unsigned int mode,
+			int nr_exclusive, void *key)
 {
 	unsigned long flags;
 	int sync = 1;
@@ -5157,9 +5228,18 @@ __wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr_exclusive)
 		sync = 0;
 
 	spin_lock_irqsave(&q->lock, flags);
-	__wake_up_common(q, mode, nr_exclusive, sync, NULL);
+	__wake_up_common(q, mode, nr_exclusive, sync, key);
 	spin_unlock_irqrestore(&q->lock, flags);
 }
+EXPORT_SYMBOL_GPL(__wake_up_sync_key);
+
+/*
+ * __wake_up_sync - see __wake_up_sync_key()
+ */
+void __wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr_exclusive)
+{
+	__wake_up_sync_key(q, mode, nr_exclusive, NULL);
+}
 EXPORT_SYMBOL_GPL(__wake_up_sync);	/* For internal use only */
 
 /**
@@ -7648,7 +7728,7 @@ cpu_to_core_group(int cpu, const struct cpumask *cpu_map,
 {
 	int group;
 
-	cpumask_and(mask, &per_cpu(cpu_sibling_map, cpu), cpu_map);
+	cpumask_and(mask, topology_thread_cpumask(cpu), cpu_map);
 	group = cpumask_first(mask);
 	if (sg)
 		*sg = &per_cpu(sched_group_core, group).sg;
@@ -7677,7 +7757,7 @@ cpu_to_phys_group(int cpu, const struct cpumask *cpu_map,
 	cpumask_and(mask, cpu_coregroup_mask(cpu), cpu_map);
 	group = cpumask_first(mask);
 #elif defined(CONFIG_SCHED_SMT)
-	cpumask_and(mask, &per_cpu(cpu_sibling_map, cpu), cpu_map);
+	cpumask_and(mask, topology_thread_cpumask(cpu), cpu_map);
 	group = cpumask_first(mask);
 #else
 	group = cpu;
@@ -8020,7 +8100,7 @@ static int __build_sched_domains(const struct cpumask *cpu_map,
 		SD_INIT(sd, SIBLING);
 		set_domain_attribute(sd, attr);
 		cpumask_and(sched_domain_span(sd),
-			    &per_cpu(cpu_sibling_map, i), cpu_map);
+			    topology_thread_cpumask(i), cpu_map);
 		sd->parent = p;
 		p->child = sd;
 		cpu_to_cpu_group(i, cpu_map, &sd->groups, tmpmask);
@@ -8031,7 +8111,7 @@ static int __build_sched_domains(const struct cpumask *cpu_map,
 	/* Set up CPU (sibling) groups */
 	for_each_cpu(i, cpu_map) {
 		cpumask_and(this_sibling_map,
-			    &per_cpu(cpu_sibling_map, i), cpu_map);
+			    topology_thread_cpumask(i), cpu_map);
 		if (i != cpumask_first(this_sibling_map))
 			continue;
 
@@ -8707,6 +8787,9 @@ void __init sched_init(void)
 #ifdef CONFIG_USER_SCHED
 	alloc_size *= 2;
 #endif
+#ifdef CONFIG_CPUMASK_OFFSTACK
+	alloc_size += num_possible_cpus() * cpumask_size();
+#endif
 	/*
 	 * As sched_init() is called before page_alloc is setup,
 	 * we use alloc_bootmem().
@@ -8744,6 +8827,12 @@ void __init sched_init(void)
 		ptr += nr_cpu_ids * sizeof(void **);
 #endif /* CONFIG_USER_SCHED */
 #endif /* CONFIG_RT_GROUP_SCHED */
+#ifdef CONFIG_CPUMASK_OFFSTACK
+		for_each_possible_cpu(i) {
+			per_cpu(load_balance_tmpmask, i) = (void *)ptr;
+			ptr += cpumask_size();
+		}
+#endif /* CONFIG_CPUMASK_OFFSTACK */
 	}
 
 #ifdef CONFIG_SMP