Merge git://git.kernel.org/pub/scm/linux/kernel/git/mingo/linux-2.6-sched

* git://git.kernel.org/pub/scm/linux/kernel/git/mingo/linux-2.6-sched:
  sched: mark CONFIG_FAIR_GROUP_SCHED as !EXPERIMENTAL
  sched: isolate SMP balancing code a bit more
  sched: reduce balance-tasks overhead
  sched: make cpu_shares_{show,store}() static
  sched: clean up some control group code
  sched: constify sched.h
  sched: document profile=sleep requiring CONFIG_SCHEDSTATS
  sched: use show_regs() to improve __schedule_bug() output
  sched: clean up sched_domain_debug()
  sched: fix fastcall mismatch in completion APIs
  sched: fix sched_domain sysctl registration again

Documentation/kernel-parameters.txt

@@ -1444,7 +1444,8 @@ and is between 256 and 4096 characters. It is defined in the file
 			Param: "schedule" - profile schedule points.
 			Param: <number> - step/bucket size as a power of 2 for
 				statistical time based profiling.
-			Param: "sleep" - profile D-state sleeping (millisecs)
+			Param: "sleep" - profile D-state sleeping (millisecs).
+				Requires CONFIG_SCHEDSTATS
 			Param: "kvm" - profile VM exits.
 
 	processor.max_cstate=	[HW,ACPI]

include/linux/completion.h

@@ -42,15 +42,15 @@ static inline void init_completion(struct completion *x)
 	init_waitqueue_head(&x->wait);
 }
 
-extern void FASTCALL(wait_for_completion(struct completion *));
-extern int FASTCALL(wait_for_completion_interruptible(struct completion *x));
-extern unsigned long FASTCALL(wait_for_completion_timeout(struct completion *x,
-						   unsigned long timeout));
-extern unsigned long FASTCALL(wait_for_completion_interruptible_timeout(
-			struct completion *x, unsigned long timeout));
-
-extern void FASTCALL(complete(struct completion *));
-extern void FASTCALL(complete_all(struct completion *));
+extern void wait_for_completion(struct completion *);
+extern int wait_for_completion_interruptible(struct completion *x);
+extern unsigned long wait_for_completion_timeout(struct completion *x,
+						   unsigned long timeout);
+extern unsigned long wait_for_completion_interruptible_timeout(
+			struct completion *x, unsigned long timeout);
+
+extern void complete(struct completion *);
+extern void complete_all(struct completion *);
 
 #define INIT_COMPLETION(x)	((x).done = 0)
 

include/linux/sched.h

@@ -828,12 +828,17 @@ struct sched_class {
 	struct task_struct * (*pick_next_task) (struct rq *rq);
 	void (*put_prev_task) (struct rq *rq, struct task_struct *p);
 
+#ifdef CONFIG_SMP
 	unsigned long (*load_balance) (struct rq *this_rq, int this_cpu,
-			struct rq *busiest,
-			unsigned long max_nr_move, unsigned long max_load_move,
+			struct rq *busiest, unsigned long max_load_move,
 			struct sched_domain *sd, enum cpu_idle_type idle,
 			int *all_pinned, int *this_best_prio);
 
+	int (*move_one_task) (struct rq *this_rq, int this_cpu,
+			      struct rq *busiest, struct sched_domain *sd,
+			      enum cpu_idle_type idle);
+#endif
+
 	void (*set_curr_task) (struct rq *rq);
 	void (*task_tick) (struct rq *rq, struct task_struct *p);
 	void (*task_new) (struct rq *rq, struct task_struct *p);
@@ -1196,7 +1201,7 @@ static inline int rt_prio(int prio)
 	return 0;
 }
 
-static inline int rt_task(struct task_struct *p)
+static inline int rt_task(const struct task_struct *p)
 {
 	return rt_prio(p->prio);
 }
@@ -1211,22 +1216,22 @@ static inline void set_task_pgrp(struct task_struct *tsk, pid_t pgrp)
 	tsk->signal->__pgrp = pgrp;
 }
 
-static inline struct pid *task_pid(struct task_struct *task)
+static inline struct pid *task_pid(const struct task_struct *task)
 {
 	return task->pids[PIDTYPE_PID].pid;
 }
 
-static inline struct pid *task_tgid(struct task_struct *task)
+static inline struct pid *task_tgid(const struct task_struct *task)
 {
 	return task->group_leader->pids[PIDTYPE_PID].pid;
 }
 
-static inline struct pid *task_pgrp(struct task_struct *task)
+static inline struct pid *task_pgrp(const struct task_struct *task)
 {
 	return task->group_leader->pids[PIDTYPE_PGID].pid;
 }
 
-static inline struct pid *task_session(struct task_struct *task)
+static inline struct pid *task_session(const struct task_struct *task)
 {
 	return task->group_leader->pids[PIDTYPE_SID].pid;
 }
@@ -1255,7 +1260,7 @@ struct pid_namespace;
  * see also pid_nr() etc in include/linux/pid.h
  */
 
-static inline pid_t task_pid_nr(struct task_struct *tsk)
+static inline pid_t task_pid_nr(const struct task_struct *tsk)
 {
 	return tsk->pid;
 }
@@ -1268,7 +1273,7 @@ static inline pid_t task_pid_vnr(struct task_struct *tsk)
 }
 
 
-static inline pid_t task_tgid_nr(struct task_struct *tsk)
+static inline pid_t task_tgid_nr(const struct task_struct *tsk)
 {
 	return tsk->tgid;
 }
@@ -1281,7 +1286,7 @@ static inline pid_t task_tgid_vnr(struct task_struct *tsk)
 }
 
 
-static inline pid_t task_pgrp_nr(struct task_struct *tsk)
+static inline pid_t task_pgrp_nr(const struct task_struct *tsk)
 {
 	return tsk->signal->__pgrp;
 }
@@ -1294,7 +1299,7 @@ static inline pid_t task_pgrp_vnr(struct task_struct *tsk)
 }
 
 
-static inline pid_t task_session_nr(struct task_struct *tsk)
+static inline pid_t task_session_nr(const struct task_struct *tsk)
 {
 	return tsk->signal->__session;
 }
@@ -1321,7 +1326,7 @@ static inline pid_t task_ppid_nr_ns(struct task_struct *tsk,
  * If pid_alive fails, then pointers within the task structure
  * can be stale and must not be dereferenced.
  */
-static inline int pid_alive(struct task_struct *p)
+static inline int pid_alive(const struct task_struct *p)
 {
 	return p->pids[PIDTYPE_PID].pid != NULL;
 }
@@ -1332,7 +1337,7 @@ static inline int pid_alive(struct task_struct *p)
  *
  * Check if a task structure is the first user space task the kernel created.
  */
-static inline int is_global_init(struct task_struct *tsk)
+static inline int is_global_init(const struct task_struct *tsk)
 {
 	return tsk->pid == 1;
 }
@@ -1469,7 +1474,7 @@ extern int rt_mutex_getprio(struct task_struct *p);
 extern void rt_mutex_setprio(struct task_struct *p, int prio);
 extern void rt_mutex_adjust_pi(struct task_struct *p);
 #else
-static inline int rt_mutex_getprio(struct task_struct *p)
+static inline int rt_mutex_getprio(const struct task_struct *p)
 {
 	return p->normal_prio;
 }
@@ -1721,7 +1726,7 @@ extern void wait_task_inactive(struct task_struct * p);
  * all we care about is that we have a task with the appropriate
  * pid, we don't actually care if we have the right task.
  */
-static inline int has_group_leader_pid(struct task_struct *p)
+static inline int has_group_leader_pid(const struct task_struct *p)
 {
 	return p->pid == p->tgid;
 }
@@ -1738,7 +1743,7 @@ static inline struct task_struct *next_thread(const struct task_struct *p)
 			  struct task_struct, thread_group);
 }
 
-static inline int thread_group_empty(struct task_struct *p)
+static inline int thread_group_empty(const struct task_struct *p)
 {
 	return list_empty(&p->thread_group);
 }

init/Kconfig

@@ -322,7 +322,6 @@ config CPUSETS
 config FAIR_GROUP_SCHED
 	bool "Fair group CPU scheduler"
 	default y
-	depends on EXPERIMENTAL
 	help
 	  This feature lets CPU scheduler recognize task groups and control CPU
 	  bandwidth allocation to such task groups.

kernel/profile.c

@@ -60,6 +60,7 @@ static int __init profile_setup(char * str)
 	int par;
 
 	if (!strncmp(str, sleepstr, strlen(sleepstr))) {
+#ifdef CONFIG_SCHEDSTATS
 		prof_on = SLEEP_PROFILING;
 		if (str[strlen(sleepstr)] == ',')
 			str += strlen(sleepstr) + 1;
@@ -68,6 +69,10 @@ static int __init profile_setup(char * str)
 		printk(KERN_INFO
 			"kernel sleep profiling enabled (shift: %ld)\n",
 			prof_shift);
+#else
+		printk(KERN_WARNING
+			"kernel sleep profiling requires CONFIG_SCHEDSTATS\n");
+#endif /* CONFIG_SCHEDSTATS */
 	} else if (!strncmp(str, schedstr, strlen(schedstr))) {
 		prof_on = SCHED_PROFILING;
 		if (str[strlen(schedstr)] == ',')

kernel/sched_fair.c

@@ -876,6 +876,7 @@ static void put_prev_task_fair(struct rq *rq, struct task_struct *prev)
 	}
 }
 
+#ifdef CONFIG_SMP
 /**************************************************
  * Fair scheduling class load-balancing methods:
  */
@@ -936,12 +937,11 @@ static int cfs_rq_best_prio(struct cfs_rq *cfs_rq)
 
 static unsigned long
 load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
-		  unsigned long max_nr_move, unsigned long max_load_move,
+		  unsigned long max_load_move,
 		  struct sched_domain *sd, enum cpu_idle_type idle,
 		  int *all_pinned, int *this_best_prio)
 {
 	struct cfs_rq *busy_cfs_rq;
-	unsigned long load_moved, total_nr_moved = 0, nr_moved;
 	long rem_load_move = max_load_move;
 	struct rq_iterator cfs_rq_iterator;
 
@@ -969,25 +969,48 @@ load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
 #else
 # define maxload rem_load_move
 #endif
-		/* pass busy_cfs_rq argument into
+		/*
+		 * pass busy_cfs_rq argument into
 		 * load_balance_[start|next]_fair iterators
 		 */
 		cfs_rq_iterator.arg = busy_cfs_rq;
-		nr_moved = balance_tasks(this_rq, this_cpu, busiest,
-				max_nr_move, maxload, sd, idle, all_pinned,
-				&load_moved, this_best_prio, &cfs_rq_iterator);
-
-		total_nr_moved += nr_moved;
-		max_nr_move -= nr_moved;
-		rem_load_move -= load_moved;
+		rem_load_move -= balance_tasks(this_rq, this_cpu, busiest,
+					       maxload, sd, idle, all_pinned,
+					       this_best_prio,
+					       &cfs_rq_iterator);
 
-		if (max_nr_move <= 0 || rem_load_move <= 0)
+		if (rem_load_move <= 0)
 			break;
 	}
 
 	return max_load_move - rem_load_move;
 }
 
+static int
+move_one_task_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
+		   struct sched_domain *sd, enum cpu_idle_type idle)
+{
+	struct cfs_rq *busy_cfs_rq;
+	struct rq_iterator cfs_rq_iterator;
+
+	cfs_rq_iterator.start = load_balance_start_fair;
+	cfs_rq_iterator.next = load_balance_next_fair;
+
+	for_each_leaf_cfs_rq(busiest, busy_cfs_rq) {
+		/*
+		 * pass busy_cfs_rq argument into
+		 * load_balance_[start|next]_fair iterators
+		 */
+		cfs_rq_iterator.arg = busy_cfs_rq;
+		if (iter_move_one_task(this_rq, this_cpu, busiest, sd, idle,
+				       &cfs_rq_iterator))
+		    return 1;
+	}
+
+	return 0;
+}
+#endif
+
 /*
  * scheduler tick hitting a task of our scheduling class:
  */
@@ -1063,7 +1086,10 @@ static const struct sched_class fair_sched_class = {
 	.pick_next_task		= pick_next_task_fair,
 	.put_prev_task		= put_prev_task_fair,
 
+#ifdef CONFIG_SMP
 	.load_balance		= load_balance_fair,
+	.move_one_task		= move_one_task_fair,
+#endif
 
 	.set_curr_task          = set_curr_task_fair,
 	.task_tick		= task_tick_fair,

kernel/sched_idletask.c

@@ -37,15 +37,24 @@ static void put_prev_task_idle(struct rq *rq, struct task_struct *prev)
 {
 }
 
+#ifdef CONFIG_SMP
 static unsigned long
 load_balance_idle(struct rq *this_rq, int this_cpu, struct rq *busiest,
-			unsigned long max_nr_move, unsigned long max_load_move,
+		  unsigned long max_load_move,
 		  struct sched_domain *sd, enum cpu_idle_type idle,
 		  int *all_pinned, int *this_best_prio)
 {
 	return 0;
 }
 
+static int
+move_one_task_idle(struct rq *this_rq, int this_cpu, struct rq *busiest,
+		   struct sched_domain *sd, enum cpu_idle_type idle)
+{
+	return 0;
+}
+#endif
+
 static void task_tick_idle(struct rq *rq, struct task_struct *curr)
 {
 }
@@ -69,7 +78,10 @@ const struct sched_class idle_sched_class = {
 	.pick_next_task		= pick_next_task_idle,
 	.put_prev_task		= put_prev_task_idle,
 
+#ifdef CONFIG_SMP
 	.load_balance		= load_balance_idle,
+	.move_one_task		= move_one_task_idle,
+#endif
 
 	.set_curr_task          = set_curr_task_idle,
 	.task_tick		= task_tick_idle,

kernel/sched_rt.c

@@ -98,6 +98,7 @@ static void put_prev_task_rt(struct rq *rq, struct task_struct *p)
 	p->se.exec_start = 0;
 }
 
+#ifdef CONFIG_SMP
 /*
  * Load-balancing iterator. Note: while the runqueue stays locked
  * during the whole iteration, the current task might be
@@ -172,13 +173,11 @@ static struct task_struct *load_balance_next_rt(void *arg)
 
 static unsigned long
 load_balance_rt(struct rq *this_rq, int this_cpu, struct rq *busiest,
-			unsigned long max_nr_move, unsigned long max_load_move,
+		unsigned long max_load_move,
 		struct sched_domain *sd, enum cpu_idle_type idle,
 		int *all_pinned, int *this_best_prio)
 {
-	int nr_moved;
 	struct rq_iterator rt_rq_iterator;
-	unsigned long load_moved;
 
 	rt_rq_iterator.start = load_balance_start_rt;
 	rt_rq_iterator.next = load_balance_next_rt;
@@ -187,12 +186,24 @@ load_balance_rt(struct rq *this_rq, int this_cpu, struct rq *busiest,
 	 */
 	rt_rq_iterator.arg = busiest;
 
-	nr_moved = balance_tasks(this_rq, this_cpu, busiest, max_nr_move,
-			max_load_move, sd, idle, all_pinned, &load_moved,
-			this_best_prio, &rt_rq_iterator);
+	return balance_tasks(this_rq, this_cpu, busiest, max_load_move, sd,
+			     idle, all_pinned, this_best_prio, &rt_rq_iterator);
+}
+
+static int
+move_one_task_rt(struct rq *this_rq, int this_cpu, struct rq *busiest,
+		 struct sched_domain *sd, enum cpu_idle_type idle)
+{
+	struct rq_iterator rt_rq_iterator;
+
+	rt_rq_iterator.start = load_balance_start_rt;
+	rt_rq_iterator.next = load_balance_next_rt;
+	rt_rq_iterator.arg = busiest;
 
-	return load_moved;
+	return iter_move_one_task(this_rq, this_cpu, busiest, sd, idle,
+				  &rt_rq_iterator);
 }
+#endif
 
 static void task_tick_rt(struct rq *rq, struct task_struct *p)
 {
@@ -236,7 +247,10 @@ const struct sched_class rt_sched_class = {
 	.pick_next_task		= pick_next_task_rt,
 	.put_prev_task		= put_prev_task_rt,
 
+#ifdef CONFIG_SMP
 	.load_balance		= load_balance_rt,
+	.move_one_task		= move_one_task_rt,
+#endif
 
 	.set_curr_task          = set_curr_task_rt,
 	.task_tick		= task_tick_rt,

kernel/user.c

@@ -129,7 +129,7 @@ static inline void uids_mutex_unlock(void)
 }
 
 /* return cpu shares held by the user */
-ssize_t cpu_shares_show(struct kset *kset, char *buffer)
+static ssize_t cpu_shares_show(struct kset *kset, char *buffer)
 {
 	struct user_struct *up = container_of(kset, struct user_struct, kset);
 
@@ -137,7 +137,8 @@ ssize_t cpu_shares_show(struct kset *kset, char *buffer)
 }
 
 /* modify cpu shares held by the user */
-ssize_t cpu_shares_store(struct kset *kset, const char *buffer, size_t size)
+static ssize_t cpu_shares_store(struct kset *kset, const char *buffer,
+				size_t size)
 {
 	struct user_struct *up = container_of(kset, struct user_struct, kset);
 	unsigned long shares;