Merge branch 'linus' into perf/core

Reason: Further changes conflict with upstream fixes

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

9 files changed, 107 insertions, 81 deletions

diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 3164ba7ce151..e1497481fe8a 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -456,6 +456,9 @@ int __irq_set_trigger(struct irq_desc *desc, unsigned int irq,
 		/* note that IRQF_TRIGGER_MASK == IRQ_TYPE_SENSE_MASK */
 		desc->status &= ~(IRQ_LEVEL | IRQ_TYPE_SENSE_MASK);
 		desc->status |= flags;
+
+		if (chip != desc->chip)
+			irq_chip_set_defaults(desc->chip);
 	}
 
 	return ret;
diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig
index 5c36ea9d55d2..ca6066a6952e 100644
--- a/kernel/power/Kconfig
+++ b/kernel/power/Kconfig
@@ -99,9 +99,13 @@ config PM_SLEEP_ADVANCED_DEBUG
 	depends on PM_ADVANCED_DEBUG
 	default n
 
+config SUSPEND_NVS
+       bool
+
 config SUSPEND
 	bool "Suspend to RAM and standby"
 	depends on PM && ARCH_SUSPEND_POSSIBLE
+	select SUSPEND_NVS if HAS_IOMEM
 	default y
 	---help---
 	  Allow the system to enter sleep states in which main memory is
@@ -130,13 +134,10 @@ config SUSPEND_FREEZER
 
 	  Turning OFF this setting is NOT recommended! If in doubt, say Y.
 
-config HIBERNATION_NVS
-	bool
-
 config HIBERNATION
 	bool "Hibernation (aka 'suspend to disk')"
 	depends on PM && SWAP && ARCH_HIBERNATION_POSSIBLE
-	select HIBERNATION_NVS if HAS_IOMEM
+	select SUSPEND_NVS if HAS_IOMEM
 	---help---
 	  Enable the suspend to disk (STD) functionality, which is usually
 	  called "hibernation" in user interfaces.  STD checkpoints the
diff --git a/kernel/power/Makefile b/kernel/power/Makefile
index 524e058dcf06..f9063c6b185d 100644
--- a/kernel/power/Makefile
+++ b/kernel/power/Makefile
@@ -10,6 +10,6 @@ obj-$(CONFIG_SUSPEND)		+= suspend.o
 obj-$(CONFIG_PM_TEST_SUSPEND)	+= suspend_test.o
 obj-$(CONFIG_HIBERNATION)	+= hibernate.o snapshot.o swap.o user.o \
 				   block_io.o
-obj-$(CONFIG_HIBERNATION_NVS)	+= hibernate_nvs.o
+obj-$(CONFIG_SUSPEND_NVS)	+= nvs.o
 
 obj-$(CONFIG_MAGIC_SYSRQ)	+= poweroff.o
diff --git a/kernel/power/hibernate_nvs.c b/kernel/power/nvs.c
index fdcad9ed5a7b..1836db60bbb6 100644
--- a/kernel/power/hibernate_nvs.c
+++ b/kernel/power/nvs.c
@@ -15,7 +15,7 @@
 
 /*
  * Platforms, like ACPI, may want us to save some memory used by them during
- * hibernation and to restore the contents of this memory during the subsequent
+ * suspend and to restore the contents of this memory during the subsequent
  * resume.  The code below implements a mechanism allowing us to do that.
  */
 
@@ -30,7 +30,7 @@ struct nvs_page {
 static LIST_HEAD(nvs_list);
 
 /**
- *	hibernate_nvs_register - register platform NVS memory region to save
+ *	suspend_nvs_register - register platform NVS memory region to save
  *	@start - physical address of the region
  *	@size - size of the region
  *
@@ -38,7 +38,7 @@ static LIST_HEAD(nvs_list);
  *	things so that the data from page-aligned addresses in this region will
  *	be copied into separate RAM pages.
  */
-int hibernate_nvs_register(unsigned long start, unsigned long size)
+int suspend_nvs_register(unsigned long start, unsigned long size)
 {
 	struct nvs_page *entry, *next;
 
@@ -68,9 +68,9 @@ int hibernate_nvs_register(unsigned long start, unsigned long size)
 }
 
 /**
- *	hibernate_nvs_free - free data pages allocated for saving NVS regions
+ *	suspend_nvs_free - free data pages allocated for saving NVS regions
  */
-void hibernate_nvs_free(void)
+void suspend_nvs_free(void)
 {
 	struct nvs_page *entry;
 
@@ -86,16 +86,16 @@ void hibernate_nvs_free(void)
 }
 
 /**
- *	hibernate_nvs_alloc - allocate memory necessary for saving NVS regions
+ *	suspend_nvs_alloc - allocate memory necessary for saving NVS regions
  */
-int hibernate_nvs_alloc(void)
+int suspend_nvs_alloc(void)
 {
 	struct nvs_page *entry;
 
 	list_for_each_entry(entry, &nvs_list, node) {
 		entry->data = (void *)__get_free_page(GFP_KERNEL);
 		if (!entry->data) {
-			hibernate_nvs_free();
+			suspend_nvs_free();
 			return -ENOMEM;
 		}
 	}
@@ -103,9 +103,9 @@ int hibernate_nvs_alloc(void)
 }
 
 /**
- *	hibernate_nvs_save - save NVS memory regions
+ *	suspend_nvs_save - save NVS memory regions
  */
-void hibernate_nvs_save(void)
+void suspend_nvs_save(void)
 {
 	struct nvs_page *entry;
 
@@ -119,12 +119,12 @@ void hibernate_nvs_save(void)
 }
 
 /**
- *	hibernate_nvs_restore - restore NVS memory regions
+ *	suspend_nvs_restore - restore NVS memory regions
  *
  *	This function is going to be called with interrupts disabled, so it
  *	cannot iounmap the virtual addresses used to access the NVS region.
  */
-void hibernate_nvs_restore(void)
+void suspend_nvs_restore(void)
 {
 	struct nvs_page *entry;
 
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index 56e7dbb8b996..f37cb7dd4402 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -16,6 +16,12 @@
 #include <linux/cpu.h>
 #include <linux/syscalls.h>
 #include <linux/gfp.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <linux/suspend.h>
 
 #include "power.h"
 
diff --git a/kernel/sched.c b/kernel/sched.c
index 3c5d34a4e932..8c473adbf223 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -306,52 +306,6 @@ static int init_task_group_load = INIT_TASK_GROUP_LOAD;
  */
 struct task_group init_task_group;
 
-/* return group to which a task belongs */
-static inline struct task_group *task_group(struct task_struct *p)
-{
-	struct task_group *tg;
-
-#ifdef CONFIG_CGROUP_SCHED
-	tg = container_of(task_subsys_state(p, cpu_cgroup_subsys_id),
-				struct task_group, css);
-#else
-	tg = &init_task_group;
-#endif
-	return tg;
-}
-
-/* Change a task's cfs_rq and parent entity if it moves across CPUs/groups */
-static inline void set_task_rq(struct task_struct *p, unsigned int cpu)
-{
-	/*
-	 * Strictly speaking this rcu_read_lock() is not needed since the
-	 * task_group is tied to the cgroup, which in turn can never go away
-	 * as long as there are tasks attached to it.
-	 *
-	 * However since task_group() uses task_subsys_state() which is an
-	 * rcu_dereference() user, this quiets CONFIG_PROVE_RCU.
-	 */
-	rcu_read_lock();
-#ifdef CONFIG_FAIR_GROUP_SCHED
-	p->se.cfs_rq = task_group(p)->cfs_rq[cpu];
-	p->se.parent = task_group(p)->se[cpu];
-#endif
-
-#ifdef CONFIG_RT_GROUP_SCHED
-	p->rt.rt_rq  = task_group(p)->rt_rq[cpu];
-	p->rt.parent = task_group(p)->rt_se[cpu];
-#endif
-	rcu_read_unlock();
-}
-
-#else
-
-static inline void set_task_rq(struct task_struct *p, unsigned int cpu) { }
-static inline struct task_group *task_group(struct task_struct *p)
-{
-	return NULL;
-}
-
 #endif	/* CONFIG_CGROUP_SCHED */
 
 /* CFS-related fields in a runqueue */
@@ -644,6 +598,49 @@ static inline int cpu_of(struct rq *rq)
 #define cpu_curr(cpu)		(cpu_rq(cpu)->curr)
 #define raw_rq()		(&__raw_get_cpu_var(runqueues))
 
+#ifdef CONFIG_CGROUP_SCHED
+
+/*
+ * Return the group to which this tasks belongs.
+ *
+ * We use task_subsys_state_check() and extend the RCU verification
+ * with lockdep_is_held(&task_rq(p)->lock) because cpu_cgroup_attach()
+ * holds that lock for each task it moves into the cgroup. Therefore
+ * by holding that lock, we pin the task to the current cgroup.
+ */
+static inline struct task_group *task_group(struct task_struct *p)
+{
+	struct cgroup_subsys_state *css;
+
+	css = task_subsys_state_check(p, cpu_cgroup_subsys_id,
+			lockdep_is_held(&task_rq(p)->lock));
+	return container_of(css, struct task_group, css);
+}
+
+/* Change a task's cfs_rq and parent entity if it moves across CPUs/groups */
+static inline void set_task_rq(struct task_struct *p, unsigned int cpu)
+{
+#ifdef CONFIG_FAIR_GROUP_SCHED
+	p->se.cfs_rq = task_group(p)->cfs_rq[cpu];
+	p->se.parent = task_group(p)->se[cpu];
+#endif
+
+#ifdef CONFIG_RT_GROUP_SCHED
+	p->rt.rt_rq  = task_group(p)->rt_rq[cpu];
+	p->rt.parent = task_group(p)->rt_se[cpu];
+#endif
+}
+
+#else /* CONFIG_CGROUP_SCHED */
+
+static inline void set_task_rq(struct task_struct *p, unsigned int cpu) { }
+static inline struct task_group *task_group(struct task_struct *p)
+{
+	return NULL;
+}
+
+#endif /* CONFIG_CGROUP_SCHED */
+
 inline void update_rq_clock(struct rq *rq)
 {
 	if (!rq->skip_clock_update)
@@ -1257,6 +1254,12 @@ static void sched_avg_update(struct rq *rq)
 	s64 period = sched_avg_period();
 
 	while ((s64)(rq->clock - rq->age_stamp) > period) {
+		/*
+		 * Inline assembly required to prevent the compiler
+		 * optimising this loop into a divmod call.
+		 * See __iter_div_u64_rem() for another example of this.
+		 */
+		asm("" : "+rm" (rq->age_stamp));
 		rq->age_stamp += period;
 		rq->rt_avg /= 2;
 	}
@@ -1660,9 +1663,6 @@ static void update_shares(struct sched_domain *sd)
 
 static void update_h_load(long cpu)
 {
-	if (root_task_group_empty())
-		return;
-
 	walk_tg_tree(tg_load_down, tg_nop, (void *)cpu);
 }
 
@@ -2494,7 +2494,16 @@ void sched_fork(struct task_struct *p, int clone_flags)
 	if (p->sched_class->task_fork)
 		p->sched_class->task_fork(p);
 
+	/*
+	 * The child is not yet in the pid-hash so no cgroup attach races,
+	 * and the cgroup is pinned to this child due to cgroup_fork()
+	 * is ran before sched_fork().
+	 *
+	 * Silence PROVE_RCU.
+	 */
+	rcu_read_lock();
 	set_task_cpu(p, cpu);
+	rcu_read_unlock();
 
 #if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
 	if (likely(sched_info_on()))
@@ -4465,16 +4474,6 @@ recheck:
 	}
 
 	if (user) {
-#ifdef CONFIG_RT_GROUP_SCHED
-		/*
-		 * Do not allow realtime tasks into groups that have no runtime
-		 * assigned.
-		 */
-		if (rt_bandwidth_enabled() && rt_policy(policy) &&
-				task_group(p)->rt_bandwidth.rt_runtime == 0)
-			return -EPERM;
-#endif
-
 		retval = security_task_setscheduler(p, policy, param);
 		if (retval)
 			return retval;
@@ -4490,6 +4489,22 @@ recheck:
 	 * runqueue lock must be held.
 	 */
 	rq = __task_rq_lock(p);
+
+#ifdef CONFIG_RT_GROUP_SCHED
+	if (user) {
+		/*
+		 * Do not allow realtime tasks into groups that have no runtime
+		 * assigned.
+		 */
+		if (rt_bandwidth_enabled() && rt_policy(policy) &&
+				task_group(p)->rt_bandwidth.rt_runtime == 0) {
+			__task_rq_unlock(rq);
+			raw_spin_unlock_irqrestore(&p->pi_lock, flags);
+			return -EPERM;
+		}
+	}
+#endif
+
 	/* recheck policy now with rq lock held */
 	if (unlikely(oldpolicy != -1 && oldpolicy != p->policy)) {
 		policy = oldpolicy = -1;
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index eed35eded602..a878b5332daa 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -1240,6 +1240,7 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync)
 	 * effect of the currently running task from the load
 	 * of the current CPU:
 	 */
+	rcu_read_lock();
 	if (sync) {
 		tg = task_group(current);
 		weight = current->se.load.weight;
@@ -1275,6 +1276,7 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync)
 		balanced = this_eff_load <= prev_eff_load;
 	} else
 		balanced = true;
+	rcu_read_unlock();
 
 	/*
 	 * If the currently running task will sleep within
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 1d7b9bc1c034..783fbadf2202 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -315,9 +315,6 @@ void tick_nohz_stop_sched_tick(int inidle)
 		goto end;
 	}
 
-	if (nohz_ratelimit(cpu))
-		goto end;
-
 	ts->idle_calls++;
 	/* Read jiffies and the time when jiffies were updated last */
 	do {
@@ -328,7 +325,7 @@ void tick_nohz_stop_sched_tick(int inidle)
 	} while (read_seqretry(&xtime_lock, seq));
 
 	if (rcu_needs_cpu(cpu) || printk_needs_cpu(cpu) ||
-	    arch_needs_cpu(cpu)) {
+	    arch_needs_cpu(cpu) || nohz_ratelimit(cpu)) {
 		next_jiffies = last_jiffies + 1;
 		delta_jiffies = 1;
 	} else {
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index 4799d7047eb0..6053982dc302 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -94,7 +94,9 @@ int perf_trace_init(struct perf_event *p_event)
 	mutex_lock(&event_mutex);
 	list_for_each_entry(tp_event, &ftrace_events, list) {
 		if (tp_event->event.type == event_id &&
-		    tp_event->class && tp_event->class->perf_probe &&
+		    tp_event->class &&
+		    (tp_event->class->perf_probe ||
+		     tp_event->class->reg) &&
 		    try_module_get(tp_event->mod)) {
 			ret = perf_trace_event_init(tp_event, p_event);
 			break;