Merge branch 'smp/threadalloc' into smp/hotplug

Reason: Pull in the separate branch which was created so arch/tile can
base further work on it.

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

12 files changed, 107 insertions, 70 deletions

diff --git a/kernel/events/core.c b/kernel/events/core.c
index a6a9ec4..fd126f8 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3183,7 +3183,7 @@ static void perf_event_for_each(struct perf_event *event,
 	perf_event_for_each_child(event, func);
 	func(event);
 	list_for_each_entry(sibling, &event->sibling_list, group_entry)
-		perf_event_for_each_child(event, func);
+		perf_event_for_each_child(sibling, func);
 	mutex_unlock(&ctx->mutex);
 }
 
diff --git a/kernel/fork.c b/kernel/fork.c
index b9372a0..2dfad02 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -112,29 +112,38 @@ int nr_processes(void)
 }
 
 #ifndef __HAVE_ARCH_TASK_STRUCT_ALLOCATOR
-# define alloc_task_struct_node(node)		\
-		kmem_cache_alloc_node(task_struct_cachep, GFP_KERNEL, node)
-# define free_task_struct(tsk)			\
-		kmem_cache_free(task_struct_cachep, (tsk))
 static struct kmem_cache *task_struct_cachep;
+
+static inline struct task_struct *alloc_task_struct_node(int node)
+{
+	return kmem_cache_alloc_node(task_struct_cachep, GFP_KERNEL, node);
+}
+
+void __weak arch_release_task_struct(struct task_struct *tsk) { }
+
+static inline void free_task_struct(struct task_struct *tsk)
+{
+	arch_release_task_struct(tsk);
+	kmem_cache_free(task_struct_cachep, tsk);
+}
 #endif
 
 #ifndef __HAVE_ARCH_THREAD_INFO_ALLOCATOR
+
+void __weak arch_release_thread_info(struct thread_info *ti) { }
+
 static struct thread_info *alloc_thread_info_node(struct task_struct *tsk,
 						  int node)
 {
-#ifdef CONFIG_DEBUG_STACK_USAGE
-	gfp_t mask = GFP_KERNEL | __GFP_ZERO;
-#else
-	gfp_t mask = GFP_KERNEL;
-#endif
-	struct page *page = alloc_pages_node(node, mask, THREAD_SIZE_ORDER);
+	struct page *page = alloc_pages_node(node, THREADINFO_GFP,
+					     THREAD_SIZE_ORDER);
 
 	return page ? page_address(page) : NULL;
 }
 
 static inline void free_thread_info(struct thread_info *ti)
 {
+	arch_release_thread_info(ti);
 	free_pages((unsigned long)ti, THREAD_SIZE_ORDER);
 }
 #endif
@@ -203,13 +212,7 @@ void __put_task_struct(struct task_struct *tsk)
 }
 EXPORT_SYMBOL_GPL(__put_task_struct);
 
-/*
- * macro override instead of weak attribute alias, to workaround
- * gcc 4.1.0 and 4.1.1 bugs with weak attribute and empty functions.
- */
-#ifndef arch_task_cache_init
-#define arch_task_cache_init()
-#endif
+void __init __weak arch_task_cache_init(void) { }
 
 void __init fork_init(unsigned long mempages)
 {
diff --git a/kernel/irq/debug.h b/kernel/irq/debug.h
index 97a8bfa..e75e29e 100644
--- a/kernel/irq/debug.h
+++ b/kernel/irq/debug.h
@@ -4,10 +4,10 @@
 
 #include <linux/kallsyms.h>
 
-#define P(f) if (desc->status_use_accessors & f) printk("%14s set\n", #f)
-#define PS(f) if (desc->istate & f) printk("%14s set\n", #f)
+#define ___P(f) if (desc->status_use_accessors & f) printk("%14s set\n", #f)
+#define ___PS(f) if (desc->istate & f) printk("%14s set\n", #f)
 /* FIXME */
-#define PD(f) do { } while (0)
+#define ___PD(f) do { } while (0)
 
 static inline void print_irq_desc(unsigned int irq, struct irq_desc *desc)
 {
@@ -23,23 +23,23 @@ static inline void print_irq_desc(unsigned int irq, struct irq_desc *desc)
 		print_symbol("%s\n", (unsigned long)desc->action->handler);
 	}
 
-	P(IRQ_LEVEL);
-	P(IRQ_PER_CPU);
-	P(IRQ_NOPROBE);
-	P(IRQ_NOREQUEST);
-	P(IRQ_NOTHREAD);
-	P(IRQ_NOAUTOEN);
+	___P(IRQ_LEVEL);
+	___P(IRQ_PER_CPU);
+	___P(IRQ_NOPROBE);
+	___P(IRQ_NOREQUEST);
+	___P(IRQ_NOTHREAD);
+	___P(IRQ_NOAUTOEN);
 
-	PS(IRQS_AUTODETECT);
-	PS(IRQS_REPLAY);
-	PS(IRQS_WAITING);
-	PS(IRQS_PENDING);
+	___PS(IRQS_AUTODETECT);
+	___PS(IRQS_REPLAY);
+	___PS(IRQS_WAITING);
+	___PS(IRQS_PENDING);
 
-	PD(IRQS_INPROGRESS);
-	PD(IRQS_DISABLED);
-	PD(IRQS_MASKED);
+	___PD(IRQS_INPROGRESS);
+	___PD(IRQS_DISABLED);
+	___PD(IRQS_MASKED);
 }
 
-#undef P
-#undef PS
-#undef PD
+#undef ___P
+#undef ___PS
+#undef ___PD
diff --git a/kernel/power/swap.c b/kernel/power/swap.c
index 8742fd0..eef311a 100644
--- a/kernel/power/swap.c
+++ b/kernel/power/swap.c
@@ -51,6 +51,23 @@
 
 #define MAP_PAGE_ENTRIES	(PAGE_SIZE / sizeof(sector_t) - 1)
 
+/*
+ * Number of free pages that are not high.
+ */
+static inline unsigned long low_free_pages(void)
+{
+	return nr_free_pages() - nr_free_highpages();
+}
+
+/*
+ * Number of pages required to be kept free while writing the image. Always
+ * half of all available low pages before the writing starts.
+ */
+static inline unsigned long reqd_free_pages(void)
+{
+	return low_free_pages() / 2;
+}
+
 struct swap_map_page {
 	sector_t entries[MAP_PAGE_ENTRIES];
 	sector_t next_swap;
@@ -72,7 +89,7 @@ struct swap_map_handle {
 	sector_t cur_swap;
 	sector_t first_sector;
 	unsigned int k;
-	unsigned long nr_free_pages, written;
+	unsigned long reqd_free_pages;
 	u32 crc32;
 };
 
@@ -316,8 +333,7 @@ static int get_swap_writer(struct swap_map_handle *handle)
 		goto err_rel;
 	}
 	handle->k = 0;
-	handle->nr_free_pages = nr_free_pages() >> 1;
-	handle->written = 0;
+	handle->reqd_free_pages = reqd_free_pages();
 	handle->first_sector = handle->cur_swap;
 	return 0;
 err_rel:
@@ -352,11 +368,11 @@ static int swap_write_page(struct swap_map_handle *handle, void *buf,
 		handle->cur_swap = offset;
 		handle->k = 0;
 	}
-	if (bio_chain && ++handle->written > handle->nr_free_pages) {
+	if (bio_chain && low_free_pages() <= handle->reqd_free_pages) {
 		error = hib_wait_on_bio_chain(bio_chain);
 		if (error)
 			goto out;
-		handle->written = 0;
+		handle->reqd_free_pages = reqd_free_pages();
 	}
  out:
 	return error;
@@ -618,7 +634,7 @@ static int save_image_lzo(struct swap_map_handle *handle,
 	 * Adjust number of free pages after all allocations have been done.
 	 * We don't want to run out of pages when writing.
 	 */
-	handle->nr_free_pages = nr_free_pages() >> 1;
+	handle->reqd_free_pages = reqd_free_pages();
 
 	/*
 	 * Start the CRC32 thread.
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index 1050d6d..d0c5baf 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -1820,7 +1820,6 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu),
 	 * a quiescent state betweentimes.
 	 */
 	local_irq_save(flags);
-	WARN_ON_ONCE(cpu_is_offline(smp_processor_id()));
 	rdp = this_cpu_ptr(rsp->rda);
 
 	/* Add the callback to our list. */
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 6a63cde..7b77e3b 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -6406,16 +6406,26 @@ static void __sdt_free(const struct cpumask *cpu_map)
 		struct sd_data *sdd = &tl->data;
 
 		for_each_cpu(j, cpu_map) {
-			struct sched_domain *sd = *per_cpu_ptr(sdd->sd, j);
-			if (sd && (sd->flags & SD_OVERLAP))
-				free_sched_groups(sd->groups, 0);
-			kfree(*per_cpu_ptr(sdd->sd, j));
-			kfree(*per_cpu_ptr(sdd->sg, j));
-			kfree(*per_cpu_ptr(sdd->sgp, j));
+			struct sched_domain *sd;
+
+			if (sdd->sd) {
+				sd = *per_cpu_ptr(sdd->sd, j);
+				if (sd && (sd->flags & SD_OVERLAP))
+					free_sched_groups(sd->groups, 0);
+				kfree(*per_cpu_ptr(sdd->sd, j));
+			}
+
+			if (sdd->sg)
+				kfree(*per_cpu_ptr(sdd->sg, j));
+			if (sdd->sgp)
+				kfree(*per_cpu_ptr(sdd->sgp, j));
 		}
 		free_percpu(sdd->sd);
+		sdd->sd = NULL;
 		free_percpu(sdd->sg);
+		sdd->sg = NULL;
 		free_percpu(sdd->sgp);
+		sdd->sgp = NULL;
 	}
 }
 
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 0d97ebd..e955364 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -784,7 +784,7 @@ account_entity_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se)
 		update_load_add(&rq_of(cfs_rq)->load, se->load.weight);
 #ifdef CONFIG_SMP
 	if (entity_is_task(se))
-		list_add_tail(&se->group_node, &rq_of(cfs_rq)->cfs_tasks);
+		list_add(&se->group_node, &rq_of(cfs_rq)->cfs_tasks);
 #endif
 	cfs_rq->nr_running++;
 }
@@ -3215,6 +3215,8 @@ static int move_one_task(struct lb_env *env)
 
 static unsigned long task_h_load(struct task_struct *p);
 
+static const unsigned int sched_nr_migrate_break = 32;
+
 /*
  * move_tasks tries to move up to load_move weighted load from busiest to
  * this_rq, as part of a balancing operation within domain "sd".
@@ -3242,7 +3244,7 @@ static int move_tasks(struct lb_env *env)
 
 		/* take a breather every nr_migrate tasks */
 		if (env->loop > env->loop_break) {
-			env->loop_break += sysctl_sched_nr_migrate;
+			env->loop_break += sched_nr_migrate_break;
 			env->flags |= LBF_NEED_BREAK;
 			break;
 		}
@@ -3252,7 +3254,7 @@ static int move_tasks(struct lb_env *env)
 
 		load = task_h_load(p);
 
-		if (load < 16 && !env->sd->nr_balance_failed)
+		if (sched_feat(LB_MIN) && load < 16 && !env->sd->nr_balance_failed)
 			goto next;
 
 		if ((load / 2) > env->load_move)
@@ -4407,7 +4409,7 @@ static int load_balance(int this_cpu, struct rq *this_rq,
 		.dst_cpu	= this_cpu,
 		.dst_rq		= this_rq,
 		.idle		= idle,
-		.loop_break	= sysctl_sched_nr_migrate,
+		.loop_break	= sched_nr_migrate_break,
 	};
 
 	cpumask_copy(cpus, cpu_active_mask);
@@ -4445,10 +4447,10 @@ redo:
 		 * correctly treated as an imbalance.
 		 */
 		env.flags |= LBF_ALL_PINNED;
-		env.load_move = imbalance;
-		env.src_cpu = busiest->cpu;
-		env.src_rq = busiest;
-		env.loop_max = busiest->nr_running;
+		env.load_move	= imbalance;
+		env.src_cpu	= busiest->cpu;
+		env.src_rq	= busiest;
+		env.loop_max	= min_t(unsigned long, sysctl_sched_nr_migrate, busiest->nr_running);
 
 more_balance:
 		local_irq_save(flags);
diff --git a/kernel/sched/features.h b/kernel/sched/features.h
index e61fd73..de00a48 100644
--- a/kernel/sched/features.h
+++ b/kernel/sched/features.h
@@ -68,3 +68,4 @@ SCHED_FEAT(TTWU_QUEUE, true)
 
 SCHED_FEAT(FORCE_SD_OVERLAP, false)
 SCHED_FEAT(RT_RUNTIME_SHARE, true)
+SCHED_FEAT(LB_MIN, false)
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index bf57abd..f113755 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -346,7 +346,8 @@ int tick_resume_broadcast(void)
 						     tick_get_broadcast_mask());
 			break;
 		case TICKDEV_MODE_ONESHOT:
-			broadcast = tick_resume_broadcast_oneshot(bc);
+			if (!cpumask_empty(tick_get_broadcast_mask()))
+				broadcast = tick_resume_broadcast_oneshot(bc);
 			break;
 		}
 	}
@@ -373,6 +374,9 @@ static int tick_broadcast_set_event(ktime_t expires, int force)
 {
 	struct clock_event_device *bc = tick_broadcast_device.evtdev;
 
+	if (bc->mode != CLOCK_EVT_MODE_ONESHOT)
+		clockevents_set_mode(bc, CLOCK_EVT_MODE_ONESHOT);
+
 	return clockevents_program_event(bc, expires, force);
 }
 
@@ -531,7 +535,6 @@ void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
 		int was_periodic = bc->mode == CLOCK_EVT_MODE_PERIODIC;
 
 		bc->event_handler = tick_handle_oneshot_broadcast;
-		clockevents_set_mode(bc, CLOCK_EVT_MODE_ONESHOT);
 
 		/* Take the do_timer update */
 		tick_do_timer_cpu = cpu;
@@ -549,6 +552,7 @@ void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
 			   to_cpumask(tmpmask));
 
 		if (was_periodic && !cpumask_empty(to_cpumask(tmpmask))) {
+			clockevents_set_mode(bc, CLOCK_EVT_MODE_ONESHOT);
 			tick_broadcast_init_next_event(to_cpumask(tmpmask),
 						       tick_next_period);
 			tick_broadcast_set_event(tick_next_period, 1);
@@ -577,15 +581,10 @@ void tick_broadcast_switch_to_oneshot(void)
 	raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
 
 	tick_broadcast_device.mode = TICKDEV_MODE_ONESHOT;
-
-	if (cpumask_empty(tick_get_broadcast_mask()))
-		goto end;
-
 	bc = tick_broadcast_device.evtdev;
 	if (bc)
 		tick_broadcast_setup_oneshot(bc);
 
-end:
 	raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
 }
 
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index ed7b5d1..2a22255 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -4629,7 +4629,8 @@ static ssize_t
 rb_simple_read(struct file *filp, char __user *ubuf,
 	       size_t cnt, loff_t *ppos)
 {
-	struct ring_buffer *buffer = filp->private_data;
+	struct trace_array *tr = filp->private_data;
+	struct ring_buffer *buffer = tr->buffer;
 	char buf[64];
 	int r;
 
@@ -4647,7 +4648,8 @@ static ssize_t
 rb_simple_write(struct file *filp, const char __user *ubuf,
 		size_t cnt, loff_t *ppos)
 {
-	struct ring_buffer *buffer = filp->private_data;
+	struct trace_array *tr = filp->private_data;
+	struct ring_buffer *buffer = tr->buffer;
 	unsigned long val;
 	int ret;
 
@@ -4734,7 +4736,7 @@ static __init int tracer_init_debugfs(void)
 			  &trace_clock_fops);
 
 	trace_create_file("tracing_on", 0644, d_tracer,
-			    global_trace.buffer, &rb_simple_fops);
+			    &global_trace, &rb_simple_fops);
 
 #ifdef CONFIG_DYNAMIC_FTRACE
 	trace_create_file("dyn_ftrace_total_info", 0444, d_tracer,
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 95059f0..f95d65d 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -836,11 +836,11 @@ extern const char *__stop___trace_bprintk_fmt[];
 		     filter)
 #include "trace_entries.h"
 
-#ifdef CONFIG_FUNCTION_TRACER
+#if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_FUNCTION_TRACER)
 int perf_ftrace_event_register(struct ftrace_event_call *call,
 			       enum trace_reg type, void *data);
 #else
 #define perf_ftrace_event_register NULL
-#endif /* CONFIG_FUNCTION_TRACER */
+#endif
 
 #endif /* _LINUX_KERNEL_TRACE_H */
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index 859fae6b..df611a0 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -652,6 +652,8 @@ int trace_print_lat_context(struct trace_iterator *iter)
 {
 	u64 next_ts;
 	int ret;
+	/* trace_find_next_entry will reset ent_size */
+	int ent_size = iter->ent_size;
 	struct trace_seq *s = &iter->seq;
 	struct trace_entry *entry = iter->ent,
 			   *next_entry = trace_find_next_entry(iter, NULL,
@@ -660,6 +662,9 @@ int trace_print_lat_context(struct trace_iterator *iter)
 	unsigned long abs_usecs = ns2usecs(iter->ts - iter->tr->time_start);
 	unsigned long rel_usecs;
 
+	/* Restore the original ent_size */
+	iter->ent_size = ent_size;
+
 	if (!next_entry)
 		next_ts = iter->ts;
 	rel_usecs = ns2usecs(next_ts - iter->ts);