Merge branch 'sched-core-for-linus' of...

Merge branch 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (25 commits)
  sched: Fix SCHED_MC regression caused by change in sched cpu_power
  sched: Don't use possibly stale sched_class
  kthread, sched: Remove reference to kthread_create_on_cpu
  sched: cpuacct: Use bigger percpu counter batch values for stats counters
  percpu_counter: Make __percpu_counter_add an inline function on UP
  sched: Remove member rt_se from struct rt_rq
  sched: Change usage of rt_rq->rt_se to rt_rq->tg->rt_se[cpu]
  sched: Remove unused update_shares_locked()
  sched: Use for_each_bit
  sched: Queue a deboosted task to the head of the RT prio queue
  sched: Implement head queueing for sched_rt
  sched: Extend enqueue_task to allow head queueing
  sched: Remove USER_SCHED
  sched: Fix the place where group powers are updated
  sched: Assume *balance is valid
  sched: Remove load_balance_newidle()
  sched: Unify load_balance{,_newidle}()
  sched: Add a lock break for PREEMPT=y
  sched: Remove from fwd decls
  sched: Remove rq_iterator from move_one_task
  ...

Fix up trivial conflicts in kernel/sched.c

Documentation/feature-removal-schedule.txt

@@ -6,21 +6,6 @@ be removed from this file.
 
 ---------------------------
 
-What:	USER_SCHED
-When:	2.6.34
-
-Why:	USER_SCHED was implemented as a proof of concept for group scheduling.
-	The effect of USER_SCHED can already be achieved from userspace with
-	the help of libcgroup. The removal of USER_SCHED will also simplify
-	the scheduler code with the removal of one major ifdef. There are also
-	issues USER_SCHED has with USER_NS. A decision was taken not to fix
-	those and instead remove USER_SCHED. Also new group scheduling
-	features will not be implemented for USER_SCHED.
-
-Who:	Dhaval Giani <dhaval@linux.vnet.ibm.com>
-
----------------------------
-
 What:	PRISM54
 When:	2.6.34
 

include/linux/kernel.h

@@ -124,7 +124,7 @@ extern int _cond_resched(void);
 #endif
 
 #ifdef CONFIG_DEBUG_SPINLOCK_SLEEP
-  void __might_sleep(char *file, int line, int preempt_offset);
+  void __might_sleep(const char *file, int line, int preempt_offset);
 /**
  * might_sleep - annotation for functions that can sleep
  *
@@ -138,7 +138,8 @@ extern int _cond_resched(void);
 # define might_sleep() \
 	do { __might_sleep(__FILE__, __LINE__, 0); might_resched(); } while (0)
 #else
-  static inline void __might_sleep(char *file, int line, int preempt_offset) { }
+  static inline void __might_sleep(const char *file, int line,
+				   int preempt_offset) { }
 # define might_sleep() do { might_resched(); } while (0)
 #endif
 

include/linux/percpu_counter.h

@@ -98,9 +98,6 @@ static inline void percpu_counter_set(struct percpu_counter *fbc, s64 amount)
 	fbc->count = amount;
 }
 
-#define __percpu_counter_add(fbc, amount, batch) \
-	percpu_counter_add(fbc, amount)
-
 static inline void
 percpu_counter_add(struct percpu_counter *fbc, s64 amount)
 {
@@ -109,6 +106,12 @@ percpu_counter_add(struct percpu_counter *fbc, s64 amount)
 	preempt_enable();
 }
 
+static inline void
+__percpu_counter_add(struct percpu_counter *fbc, s64 amount, s32 batch)
+{
+	percpu_counter_add(fbc, amount);
+}
+
 static inline s64 percpu_counter_read(struct percpu_counter *fbc)
 {
 	return fbc->count;

include/linux/sched.h

@@ -740,14 +740,6 @@ struct user_struct {
 	uid_t uid;
 	struct user_namespace *user_ns;
 
-#ifdef CONFIG_USER_SCHED
-	struct task_group *tg;
-#ifdef CONFIG_SYSFS
-	struct kobject kobj;
-	struct delayed_work work;
-#endif
-#endif
-
 #ifdef CONFIG_PERF_EVENTS
 	atomic_long_t locked_vm;
 #endif
@@ -1087,7 +1079,8 @@ struct sched_domain;
 struct sched_class {
 	const struct sched_class *next;
 
-	void (*enqueue_task) (struct rq *rq, struct task_struct *p, int wakeup);
+	void (*enqueue_task) (struct rq *rq, struct task_struct *p, int wakeup,
+			      bool head);
 	void (*dequeue_task) (struct rq *rq, struct task_struct *p, int sleep);
 	void (*yield_task) (struct rq *rq);
 
@@ -1099,14 +1092,6 @@ struct sched_class {
 #ifdef CONFIG_SMP
 	int  (*select_task_rq)(struct task_struct *p, int sd_flag, int flags);
 
-	unsigned long (*load_balance) (struct rq *this_rq, int this_cpu,
-			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);
 	void (*pre_schedule) (struct rq *this_rq, struct task_struct *task);
 	void (*post_schedule) (struct rq *this_rq);
 	void (*task_waking) (struct rq *this_rq, struct task_struct *task);
@@ -2520,13 +2505,9 @@ extern long sched_getaffinity(pid_t pid, struct cpumask *mask);
 
 extern void normalize_rt_tasks(void);
 
-#ifdef CONFIG_GROUP_SCHED
+#ifdef CONFIG_CGROUP_SCHED
 
 extern struct task_group init_task_group;
-#ifdef CONFIG_USER_SCHED
-extern struct task_group root_task_group;
-extern void set_tg_uid(struct user_struct *user);
-#endif
 
 extern struct task_group *sched_create_group(struct task_group *parent);
 extern void sched_destroy_group(struct task_group *tg);

init/Kconfig

@@ -461,57 +461,6 @@ config LOG_BUF_SHIFT
 config HAVE_UNSTABLE_SCHED_CLOCK
 	bool
 
-config GROUP_SCHED
-	bool "Group CPU scheduler"
-	depends on EXPERIMENTAL
-	default n
-	help
-	  This feature lets CPU scheduler recognize task groups and control CPU
-	  bandwidth allocation to such task groups.
-	  In order to create a group from arbitrary set of processes, use
-	  CONFIG_CGROUPS. (See Control Group support.)
-
-config FAIR_GROUP_SCHED
-	bool "Group scheduling for SCHED_OTHER"
-	depends on GROUP_SCHED
-	default GROUP_SCHED
-
-config RT_GROUP_SCHED
-	bool "Group scheduling for SCHED_RR/FIFO"
-	depends on EXPERIMENTAL
-	depends on GROUP_SCHED
-	default n
-	help
-	  This feature lets you explicitly allocate real CPU bandwidth
-	  to users or control groups (depending on the "Basis for grouping tasks"
-	  setting below. If enabled, it will also make it impossible to
-	  schedule realtime tasks for non-root users until you allocate
-	  realtime bandwidth for them.
-	  See Documentation/scheduler/sched-rt-group.txt for more information.
-
-choice
-	depends on GROUP_SCHED
-	prompt "Basis for grouping tasks"
-	default USER_SCHED
-
-config USER_SCHED
-	bool "user id"
-	help
-	  This option will choose userid as the basis for grouping
-	  tasks, thus providing equal CPU bandwidth to each user.
-
-config CGROUP_SCHED
-	bool "Control groups"
- 	depends on CGROUPS
- 	help
-	  This option allows you to create arbitrary task groups
-	  using the "cgroup" pseudo filesystem and control
-	  the cpu bandwidth allocated to each such task group.
-	  Refer to Documentation/cgroups/cgroups.txt for more
-	  information on "cgroup" pseudo filesystem.
-
-endchoice
-
 menuconfig CGROUPS
 	boolean "Control Group support"
 	help
@@ -632,6 +581,36 @@ config CGROUP_MEM_RES_CTLR_SWAP
 	  Now, memory usage of swap_cgroup is 2 bytes per entry. If swap page
 	  size is 4096bytes, 512k per 1Gbytes of swap.
 
+menuconfig CGROUP_SCHED
+	bool "Group CPU scheduler"
+	depends on EXPERIMENTAL && CGROUPS
+	default n
+	help
+	  This feature lets CPU scheduler recognize task groups and control CPU
+	  bandwidth allocation to such task groups. It uses cgroups to group
+	  tasks.
+
+if CGROUP_SCHED
+config FAIR_GROUP_SCHED
+	bool "Group scheduling for SCHED_OTHER"
+	depends on CGROUP_SCHED
+	default CGROUP_SCHED
+
+config RT_GROUP_SCHED
+	bool "Group scheduling for SCHED_RR/FIFO"
+	depends on EXPERIMENTAL
+	depends on CGROUP_SCHED
+	default n
+	help
+	  This feature lets you explicitly allocate real CPU bandwidth
+	  to users or control groups (depending on the "Basis for grouping tasks"
+	  setting below. If enabled, it will also make it impossible to
+	  schedule realtime tasks for non-root users until you allocate
+	  realtime bandwidth for them.
+	  See Documentation/scheduler/sched-rt-group.txt for more information.
+
+endif #CGROUP_SCHED
+
 endif # CGROUPS
 
 config MM_OWNER

kernel/ksysfs.c

@@ -197,16 +197,8 @@ static int __init ksysfs_init(void)
 			goto group_exit;
 	}
 
-	/* create the /sys/kernel/uids/ directory */
-	error = uids_sysfs_init();
-	if (error)
-		goto notes_exit;
-
 	return 0;
 
-notes_exit:
-	if (notes_size > 0)
-		sysfs_remove_bin_file(kernel_kobj, &notes_attr);
 group_exit:
 	sysfs_remove_group(kernel_kobj, &kernel_attr_group);
 kset_exit:

kernel/kthread.c

@@ -101,7 +101,7 @@ static void create_kthread(struct kthread_create_info *create)
  *
  * Description: This helper function creates and names a kernel
  * thread.  The thread will be stopped: use wake_up_process() to start
- * it.  See also kthread_run(), kthread_create_on_cpu().
+ * it.  See also kthread_run().
  *
  * When woken, the thread will run @threadfn() with @data as its
  * argument. @threadfn() can either call do_exit() directly if it is a

kernel/sched_cpupri.c

@@ -47,9 +47,7 @@ static int convert_prio(int prio)
 }
 
 #define for_each_cpupri_active(array, idx)                    \
-  for (idx = find_first_bit(array, CPUPRI_NR_PRIORITIES);     \
-       idx < CPUPRI_NR_PRIORITIES;                            \
-       idx = find_next_bit(array, CPUPRI_NR_PRIORITIES, idx+1))
+	for_each_bit(idx, array, CPUPRI_NR_PRIORITIES)
 
 /**
  * cpupri_find - find the best (lowest-pri) CPU in the system

kernel/sched_idletask.c

@@ -44,24 +44,6 @@ 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_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, int queued)
 {
 }
@@ -97,7 +79,7 @@ static void prio_changed_idle(struct rq *rq, struct task_struct *p,
 		check_preempt_curr(rq, p, 0);
 }
 
-unsigned int get_rr_interval_idle(struct rq *rq, struct task_struct *task)
+static unsigned int get_rr_interval_idle(struct rq *rq, struct task_struct *task)
 {
 	return 0;
 }
@@ -119,9 +101,6 @@ static const struct sched_class idle_sched_class = {
 
 #ifdef CONFIG_SMP
 	.select_task_rq		= select_task_rq_idle,
-
-	.load_balance		= load_balance_idle,
-	.move_one_task		= move_one_task_idle,
 #endif
 
 	.set_curr_task          = set_curr_task_idle,

kernel/sched_rt.c

@@ -194,17 +194,20 @@ static inline struct rt_rq *group_rt_rq(struct sched_rt_entity *rt_se)
 	return rt_se->my_q;
 }
 
-static void enqueue_rt_entity(struct sched_rt_entity *rt_se);
+static void enqueue_rt_entity(struct sched_rt_entity *rt_se, bool head);
 static void dequeue_rt_entity(struct sched_rt_entity *rt_se);
 
 static void sched_rt_rq_enqueue(struct rt_rq *rt_rq)
 {
+	int this_cpu = smp_processor_id();
 	struct task_struct *curr = rq_of_rt_rq(rt_rq)->curr;
-	struct sched_rt_entity *rt_se = rt_rq->rt_se;
+	struct sched_rt_entity *rt_se;
+
+	rt_se = rt_rq->tg->rt_se[this_cpu];
 
 	if (rt_rq->rt_nr_running) {
 		if (rt_se && !on_rt_rq(rt_se))
-			enqueue_rt_entity(rt_se);
+			enqueue_rt_entity(rt_se, false);
 		if (rt_rq->highest_prio.curr < curr->prio)
 			resched_task(curr);
 	}
@@ -212,7 +215,10 @@ static void sched_rt_rq_enqueue(struct rt_rq *rt_rq)
 
 static void sched_rt_rq_dequeue(struct rt_rq *rt_rq)
 {
-	struct sched_rt_entity *rt_se = rt_rq->rt_se;
+	int this_cpu = smp_processor_id();
+	struct sched_rt_entity *rt_se;
+
+	rt_se = rt_rq->tg->rt_se[this_cpu];
 
 	if (rt_se && on_rt_rq(rt_se))
 		dequeue_rt_entity(rt_se);
@@ -803,7 +809,7 @@ void dec_rt_tasks(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
 	dec_rt_group(rt_se, rt_rq);
 }
 
-static void __enqueue_rt_entity(struct sched_rt_entity *rt_se)
+static void __enqueue_rt_entity(struct sched_rt_entity *rt_se, bool head)
 {
 	struct rt_rq *rt_rq = rt_rq_of_se(rt_se);
 	struct rt_prio_array *array = &rt_rq->active;
@@ -819,7 +825,10 @@ static void __enqueue_rt_entity(struct sched_rt_entity *rt_se)
 	if (group_rq && (rt_rq_throttled(group_rq) || !group_rq->rt_nr_running))
 		return;
 
-	list_add_tail(&rt_se->run_list, queue);
+	if (head)
+		list_add(&rt_se->run_list, queue);
+	else
+		list_add_tail(&rt_se->run_list, queue);
 	__set_bit(rt_se_prio(rt_se), array->bitmap);
 
 	inc_rt_tasks(rt_se, rt_rq);
@@ -856,11 +865,11 @@ static void dequeue_rt_stack(struct sched_rt_entity *rt_se)
 	}
 }
 
-static void enqueue_rt_entity(struct sched_rt_entity *rt_se)
+static void enqueue_rt_entity(struct sched_rt_entity *rt_se, bool head)
 {
 	dequeue_rt_stack(rt_se);
 	for_each_sched_rt_entity(rt_se)
-		__enqueue_rt_entity(rt_se);
+		__enqueue_rt_entity(rt_se, head);
 }
 
 static void dequeue_rt_entity(struct sched_rt_entity *rt_se)
@@ -871,21 +880,22 @@ static void dequeue_rt_entity(struct sched_rt_entity *rt_se)
 		struct rt_rq *rt_rq = group_rt_rq(rt_se);
 
 		if (rt_rq && rt_rq->rt_nr_running)
-			__enqueue_rt_entity(rt_se);
+			__enqueue_rt_entity(rt_se, false);
 	}
 }
 
 /*
  * Adding/removing a task to/from a priority array:
  */
-static void enqueue_task_rt(struct rq *rq, struct task_struct *p, int wakeup)
+static void
+enqueue_task_rt(struct rq *rq, struct task_struct *p, int wakeup, bool head)
 {
 	struct sched_rt_entity *rt_se = &p->rt;
 
 	if (wakeup)
 		rt_se->timeout = 0;
 
-	enqueue_rt_entity(rt_se);
+	enqueue_rt_entity(rt_se, head);
 
 	if (!task_current(rq, p) && p->rt.nr_cpus_allowed > 1)
 		enqueue_pushable_task(rq, p);
@@ -1481,24 +1491,6 @@ static void task_woken_rt(struct rq *rq, struct task_struct *p)
 		push_rt_tasks(rq);
 }
 
-static unsigned long
-load_balance_rt(struct rq *this_rq, int this_cpu, struct rq *busiest,
-		unsigned long max_load_move,
-		struct sched_domain *sd, enum cpu_idle_type idle,
-		int *all_pinned, int *this_best_prio)
-{
-	/* don't touch RT tasks */
-	return 0;
-}
-
-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)
-{
-	/* don't touch RT tasks */
-	return 0;
-}
-
 static void set_cpus_allowed_rt(struct task_struct *p,
 				const struct cpumask *new_mask)
 {
@@ -1721,7 +1713,7 @@ static void set_curr_task_rt(struct rq *rq)
 	dequeue_pushable_task(rq, p);
 }
 
-unsigned int get_rr_interval_rt(struct rq *rq, struct task_struct *task)
+static unsigned int get_rr_interval_rt(struct rq *rq, struct task_struct *task)
 {
 	/*
 	 * Time slice is 0 for SCHED_FIFO tasks
@@ -1746,8 +1738,6 @@ static const struct sched_class rt_sched_class = {
 #ifdef CONFIG_SMP
 	.select_task_rq		= select_task_rq_rt,
 
-	.load_balance		= load_balance_rt,
-	.move_one_task		= move_one_task_rt,
 	.set_cpus_allowed       = set_cpus_allowed_rt,
 	.rq_online              = rq_online_rt,
 	.rq_offline             = rq_offline_rt,

kernel/sys.c

@@ -571,11 +571,6 @@ static int set_user(struct cred *new)
 	if (!new_user)
 		return -EAGAIN;
 
-	if (!task_can_switch_user(new_user, current)) {
-		free_uid(new_user);
-		return -EINVAL;
-	}
-
 	if (atomic_read(&new_user->processes) >=
 				current->signal->rlim[RLIMIT_NPROC].rlim_cur &&
 			new_user != INIT_USER) {