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

Pull scheduler changes for v3.4 from Ingo Molnar

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (27 commits)
  printk: Make it compile with !CONFIG_PRINTK
  sched/x86: Fix overflow in cyc2ns_offset
  sched: Fix nohz load accounting -- again!
  sched: Update yield() docs
  printk/sched: Introduce special printk_sched() for those awkward moments
  sched/nohz: Correctly initialize 'next_balance' in 'nohz' idle balancer
  sched: Cleanup cpu_active madness
  sched: Fix load-balance wreckage
  sched: Clean up parameter passing of proc_sched_autogroup_set_nice()
  sched: Ditch per cgroup task lists for load-balancing
  sched: Rename load-balancing fields
  sched: Move load-balancing arguments into helper struct
  sched/rt: Do not submit new work when PI-blocked
  sched/rt: Prevent idle task boosting
  sched/wait: Add __wake_up_all_locked() API
  sched/rt: Document scheduler related skip-resched-check sites
  sched/rt: Use schedule_preempt_disabled()
  sched/rt: Add schedule_preempt_disabled()
  sched/rt: Do not throttle when PI boosting
  sched/rt: Keep period timer ticking when rt throttling is active
  ...

include/linux/init_task.h

@@ -149,7 +149,7 @@ extern struct cred init_cred;
 	},								\
 	.rt		= {						\
 		.run_list	= LIST_HEAD_INIT(tsk.rt.run_list),	\
-		.time_slice	= HZ, 					\
+		.time_slice	= RR_TIMESLICE,				\
 		.nr_cpus_allowed = NR_CPUS,				\
 	},								\
 	.tasks		= LIST_HEAD_INIT(tsk.tasks),			\

include/linux/kernel.h

@@ -85,6 +85,19 @@
 }							\
 )
 
+/*
+ * Multiplies an integer by a fraction, while avoiding unnecessary
+ * overflow or loss of precision.
+ */
+#define mult_frac(x, numer, denom)(			\
+{							\
+	typeof(x) quot = (x) / (denom);			\
+	typeof(x) rem  = (x) % (denom);			\
+	(quot * (numer)) + ((rem * (numer)) / (denom));	\
+}							\
+)
+
+
 #define _RET_IP_		(unsigned long)__builtin_return_address(0)
 #define _THIS_IP_  ({ __label__ __here; __here: (unsigned long)&&__here; })
 

include/linux/preempt.h

@@ -48,12 +48,14 @@ do { \
 	barrier(); \
 } while (0)
 
-#define preempt_enable_no_resched() \
+#define sched_preempt_enable_no_resched() \
 do { \
 	barrier(); \
 	dec_preempt_count(); \
 } while (0)
 
+#define preempt_enable_no_resched()	sched_preempt_enable_no_resched()
+
 #define preempt_enable() \
 do { \
 	preempt_enable_no_resched(); \
@@ -92,6 +94,7 @@ do { \
 #else /* !CONFIG_PREEMPT_COUNT */
 
 #define preempt_disable()		do { } while (0)
+#define sched_preempt_enable_no_resched()	do { } while (0)
 #define preempt_enable_no_resched()	do { } while (0)
 #define preempt_enable()		do { } while (0)
 

include/linux/printk.h

@@ -100,6 +100,11 @@ int vprintk(const char *fmt, va_list args);
 asmlinkage __printf(1, 2) __cold
 int printk(const char *fmt, ...);
 
+/*
+ * Special printk facility for scheduler use only, _DO_NOT_USE_ !
+ */
+__printf(1, 2) __cold int printk_sched(const char *fmt, ...);
+
 /*
  * Please don't use printk_ratelimit(), because it shares ratelimiting state
  * with all other unrelated printk_ratelimit() callsites.  Instead use
@@ -127,6 +132,11 @@ int printk(const char *s, ...)
 {
 	return 0;
 }
+static inline __printf(1, 2) __cold
+int printk_sched(const char *s, ...)
+{
+	return 0;
+}
 static inline int printk_ratelimit(void)
 {
 	return 0;

include/linux/sched.h

@@ -361,6 +361,7 @@ extern signed long schedule_timeout_interruptible(signed long timeout);
 extern signed long schedule_timeout_killable(signed long timeout);
 extern signed long schedule_timeout_uninterruptible(signed long timeout);
 asmlinkage void schedule(void);
+extern void schedule_preempt_disabled(void);
 extern int mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner);
 
 struct nsproxy;
@@ -905,6 +906,7 @@ struct sched_group_power {
 	 * single CPU.
 	 */
 	unsigned int power, power_orig;
+	unsigned long next_update;
 	/*
 	 * Number of busy cpus in this group.
 	 */
@@ -1052,6 +1054,8 @@ static inline int test_sd_parent(struct sched_domain *sd, int flag)
 unsigned long default_scale_freq_power(struct sched_domain *sd, int cpu);
 unsigned long default_scale_smt_power(struct sched_domain *sd, int cpu);
 
+bool cpus_share_cache(int this_cpu, int that_cpu);
+
 #else /* CONFIG_SMP */
 
 struct sched_domain_attr;
@@ -1061,6 +1065,12 @@ partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
 			struct sched_domain_attr *dattr_new)
 {
 }
+
+static inline bool cpus_share_cache(int this_cpu, int that_cpu)
+{
+	return true;
+}
+
 #endif	/* !CONFIG_SMP */
 
 
@@ -1225,6 +1235,12 @@ struct sched_rt_entity {
 #endif
 };
 
+/*
+ * default timeslice is 100 msecs (used only for SCHED_RR tasks).
+ * Timeslices get refilled after they expire.
+ */
+#define RR_TIMESLICE		(100 * HZ / 1000)
+
 struct rcu_node;
 
 enum perf_event_task_context {
@@ -2047,7 +2063,7 @@ extern void sched_autogroup_fork(struct signal_struct *sig);
 extern void sched_autogroup_exit(struct signal_struct *sig);
 #ifdef CONFIG_PROC_FS
 extern void proc_sched_autogroup_show_task(struct task_struct *p, struct seq_file *m);
-extern int proc_sched_autogroup_set_nice(struct task_struct *p, int *nice);
+extern int proc_sched_autogroup_set_nice(struct task_struct *p, int nice);
 #endif
 #else
 static inline void sched_autogroup_create_attach(struct task_struct *p) { }
@@ -2064,12 +2080,20 @@ extern unsigned int sysctl_sched_cfs_bandwidth_slice;
 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);
+static inline bool tsk_is_pi_blocked(struct task_struct *tsk)
+{
+	return tsk->pi_blocked_on != NULL;
+}
 #else
 static inline int rt_mutex_getprio(struct task_struct *p)
 {
 	return p->normal_prio;
 }
 # define rt_mutex_adjust_pi(p)		do { } while (0)
+static inline bool tsk_is_pi_blocked(struct task_struct *tsk)
+{
+	return false;
+}
 #endif
 
 extern bool yield_to(struct task_struct *p, bool preempt);
@@ -2388,12 +2412,15 @@ static inline void task_unlock(struct task_struct *p)
 extern struct sighand_struct *__lock_task_sighand(struct task_struct *tsk,
 							unsigned long *flags);
 
-#define lock_task_sighand(tsk, flags)					\
-({	struct sighand_struct *__ss;					\
-	__cond_lock(&(tsk)->sighand->siglock,				\
-		    (__ss = __lock_task_sighand(tsk, flags)));		\
-	__ss;								\
-})									\
+static inline struct sighand_struct *lock_task_sighand(struct task_struct *tsk,
+						       unsigned long *flags)
+{
+	struct sighand_struct *ret;
+
+	ret = __lock_task_sighand(tsk, flags);
+	(void)__cond_lock(&tsk->sighand->siglock, ret);
+	return ret;
+}
 
 static inline void unlock_task_sighand(struct task_struct *tsk,
 						unsigned long *flags)

include/linux/wait.h

@@ -157,7 +157,7 @@ void __wake_up(wait_queue_head_t *q, unsigned int mode, int nr, void *key);
 void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key);
 void __wake_up_sync_key(wait_queue_head_t *q, unsigned int mode, int nr,
 			void *key);
-void __wake_up_locked(wait_queue_head_t *q, unsigned int mode);
+void __wake_up_locked(wait_queue_head_t *q, unsigned int mode, int nr);
 void __wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr);
 void __wake_up_bit(wait_queue_head_t *, void *, int);
 int __wait_on_bit(wait_queue_head_t *, struct wait_bit_queue *, int (*)(void *), unsigned);
@@ -170,7 +170,8 @@ wait_queue_head_t *bit_waitqueue(void *, int);
 #define wake_up(x)			__wake_up(x, TASK_NORMAL, 1, NULL)
 #define wake_up_nr(x, nr)		__wake_up(x, TASK_NORMAL, nr, NULL)
 #define wake_up_all(x)			__wake_up(x, TASK_NORMAL, 0, NULL)
-#define wake_up_locked(x)		__wake_up_locked((x), TASK_NORMAL)
+#define wake_up_locked(x)		__wake_up_locked((x), TASK_NORMAL, 1)
+#define wake_up_all_locked(x)		__wake_up_locked((x), TASK_NORMAL, 0)
 
 #define wake_up_interruptible(x)	__wake_up(x, TASK_INTERRUPTIBLE, 1, NULL)
 #define wake_up_interruptible_nr(x, nr)	__wake_up(x, TASK_INTERRUPTIBLE, nr, NULL)