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

…ched

* git://git.kernel.org/pub/scm/linux/kernel/git/mingo/linux-2.6-sched:
  sched: proper prototype for kernel/sched.c:migration_init()
  sched: avoid large irq-latencies in smp-balancing
  sched: fix copy_namespace() <-> sched_fork() dependency in do_fork
  sched: clean up the wakeup preempt check, #2
  sched: clean up the wakeup preempt check
  sched: wakeup preemption fix
  sched: remove PREEMPT_RESTRICT
  sched: turn off PREEMPT_RESTRICT
  KVM: fix !SMP build error
  x86: make nmi_cpu_busy() always defined
  x86: make ipi_handler() always defined
  sched: cleanup, use NSEC_PER_MSEC and NSEC_PER_SEC
  sched: reintroduce SMP tunings again
  sched: restore deterministic CPU accounting on powerpc
  sched: fix delay accounting regression
  sched: reintroduce the sched_min_granularity tunable
  sched: documentation: place_entity() comments
  sched: fix vslice

arch/powerpc/kernel/process.c

@@ -350,7 +350,7 @@ struct task_struct *__switch_to(struct task_struct *prev,
 	local_irq_save(flags);
 
 	account_system_vtime(current);
-	account_process_vtime(current);
+	account_process_tick(current, 0);
 	calculate_steal_time();
 
 	last = _switch(old_thread, new_thread);

arch/powerpc/kernel/time.c

@@ -259,7 +259,7 @@ void account_system_vtime(struct task_struct *tsk)
  * user and system time records.
  * Must be called with interrupts disabled.
  */
-void account_process_vtime(struct task_struct *tsk)
+void account_process_tick(struct task_struct *tsk, int user_tick)
 {
 	cputime_t utime, utimescaled;
 
@@ -274,18 +274,6 @@ void account_process_vtime(struct task_struct *tsk)
 	account_user_time_scaled(tsk, utimescaled);
 }
 
-static void account_process_time(struct pt_regs *regs)
-{
-	int cpu = smp_processor_id();
-
-	account_process_vtime(current);
-	run_local_timers();
-	if (rcu_pending(cpu))
-		rcu_check_callbacks(cpu, user_mode(regs));
-	scheduler_tick();
- 	run_posix_cpu_timers(current);
-}
-
 /*
  * Stuff for accounting stolen time.
  */
@@ -375,7 +363,6 @@ static void snapshot_purr(void)
 
 #else /* ! CONFIG_VIRT_CPU_ACCOUNTING */
 #define calc_cputime_factors()
-#define account_process_time(regs)	update_process_times(user_mode(regs))
 #define calculate_steal_time()		do { } while (0)
 #endif
 
@@ -599,16 +586,6 @@ void timer_interrupt(struct pt_regs * regs)
 		get_lppaca()->int_dword.fields.decr_int = 0;
 #endif
 
-	/*
-	 * We cannot disable the decrementer, so in the period
-	 * between this cpu's being marked offline in cpu_online_map
-	 * and calling stop-self, it is taking timer interrupts.
-	 * Avoid calling into the scheduler rebalancing code if this
-	 * is the case.
-	 */
-	if (!cpu_is_offline(cpu))
-		account_process_time(regs);
-
 	if (evt->event_handler)
 		evt->event_handler(evt);
 

arch/s390/kernel/time.c

@@ -145,12 +145,8 @@ void account_ticks(u64 time)
 	do_timer(ticks);
 #endif
 
-#ifdef CONFIG_VIRT_CPU_ACCOUNTING
-	account_tick_vtime(current);
-#else
 	while (ticks--)
 		update_process_times(user_mode(get_irq_regs()));
-#endif
 
 	s390_do_profile();
 }

arch/s390/kernel/vtime.c

@@ -32,7 +32,7 @@ static DEFINE_PER_CPU(struct vtimer_queue, virt_cpu_timer);
  * Update process times based on virtual cpu times stored by entry.S
  * to the lowcore fields user_timer, system_timer & steal_clock.
  */
-void account_tick_vtime(struct task_struct *tsk)
+void account_process_tick(struct task_struct *tsk, int user_tick)
 {
 	cputime_t cputime;
 	__u64 timer, clock;
@@ -64,12 +64,6 @@ void account_tick_vtime(struct task_struct *tsk)
 		S390_lowcore.steal_clock -= cputime << 12;
 		account_steal_time(tsk, cputime);
 	}
-
-	run_local_timers();
-	if (rcu_pending(smp_processor_id()))
-		rcu_check_callbacks(smp_processor_id(), rcu_user_flag);
-	scheduler_tick();
- 	run_posix_cpu_timers(tsk);
 }
 
 /*

arch/x86/kernel/cpu/mtrr/main.c

@@ -139,13 +139,12 @@ struct set_mtrr_data {
 	mtrr_type	smp_type;
 };
 
-#ifdef CONFIG_SMP
-
 static void ipi_handler(void *info)
 /*  [SUMMARY] Synchronisation handler. Executed by "other" CPUs.
     [RETURNS] Nothing.
 */
 {
+#ifdef CONFIG_SMP
 	struct set_mtrr_data *data = info;
 	unsigned long flags;
 
@@ -168,9 +167,8 @@ static void ipi_handler(void *info)
 
 	atomic_dec(&data->count);
 	local_irq_restore(flags);
-}
-
 #endif
+}
 
 static inline int types_compatible(mtrr_type type1, mtrr_type type2) {
 	return type1 == MTRR_TYPE_UNCACHABLE ||

arch/x86/kernel/nmi_32.c

@@ -51,13 +51,13 @@ static int unknown_nmi_panic_callback(struct pt_regs *regs, int cpu);
 
 static int endflag __initdata = 0;
 
-#ifdef CONFIG_SMP
 /* The performance counters used by NMI_LOCAL_APIC don't trigger when
  * the CPU is idle. To make sure the NMI watchdog really ticks on all
  * CPUs during the test make them busy.
  */
 static __init void nmi_cpu_busy(void *data)
 {
+#ifdef CONFIG_SMP
 	local_irq_enable_in_hardirq();
 	/* Intentionally don't use cpu_relax here. This is
 	   to make sure that the performance counter really ticks,
@@ -67,8 +67,8 @@ static __init void nmi_cpu_busy(void *data)
 	   care if they get somewhat less cycles. */
 	while (endflag == 0)
 		mb();
-}
 #endif
+}
 
 static int __init check_nmi_watchdog(void)
 {

include/linux/sched.h

@@ -254,6 +254,7 @@ long io_schedule_timeout(long timeout);
 
 extern void cpu_init (void);
 extern void trap_init(void);
+extern void account_process_tick(struct task_struct *task, int user);
 extern void update_process_times(int user);
 extern void scheduler_tick(void);
 
@@ -862,7 +863,6 @@ struct sched_entity {
 	struct load_weight	load;		/* for load-balancing */
 	struct rb_node		run_node;
 	unsigned int		on_rq;
-	int			peer_preempt;
 
 	u64			exec_start;
 	u64			sum_exec_runtime;
@@ -1460,12 +1460,17 @@ extern void sched_idle_next(void);
 
 #ifdef CONFIG_SCHED_DEBUG
 extern unsigned int sysctl_sched_latency;
-extern unsigned int sysctl_sched_nr_latency;
+extern unsigned int sysctl_sched_min_granularity;
 extern unsigned int sysctl_sched_wakeup_granularity;
 extern unsigned int sysctl_sched_batch_wakeup_granularity;
 extern unsigned int sysctl_sched_child_runs_first;
 extern unsigned int sysctl_sched_features;
 extern unsigned int sysctl_sched_migration_cost;
+extern unsigned int sysctl_sched_nr_migrate;
+
+int sched_nr_latency_handler(struct ctl_table *table, int write,
+		struct file *file, void __user *buffer, size_t *length,
+		loff_t *ppos);
 #endif
 
 extern unsigned int sysctl_sched_compat_yield;
@@ -1983,6 +1988,14 @@ static inline void inc_syscw(struct task_struct *tsk)
 }
 #endif
 
+#ifdef CONFIG_SMP
+void migration_init(void);
+#else
+static inline void migration_init(void)
+{
+}
+#endif
+
 #endif /* __KERNEL__ */
 
 #endif

include/linux/smp.h

@@ -84,11 +84,12 @@ void smp_prepare_boot_cpu(void);
  *	These macros fold the SMP functionality into a single CPU system
  */
 #define raw_smp_processor_id()			0
-static inline int up_smp_call_function(void)
+static inline int up_smp_call_function(void (*func)(void *), void *info)
 {
 	return 0;
 }
-#define smp_call_function(func,info,retry,wait)	(up_smp_call_function())
+#define smp_call_function(func, info, retry, wait) \
+			(up_smp_call_function(func, info))
 #define on_each_cpu(func,info,retry,wait)	\
 	({					\
 		local_irq_disable();		\
@@ -107,6 +108,8 @@ static inline void smp_send_reschedule(int cpu) { }
 	local_irq_enable();	\
 	0;			\
 })
+#define smp_call_function_mask(mask, func, info, wait) \
+			(up_smp_call_function(func, info))
 
 #endif /* !SMP */
 

init/main.c

@@ -56,6 +56,7 @@
 #include <linux/pid_namespace.h>
 #include <linux/device.h>
 #include <linux/kthread.h>
+#include <linux/sched.h>
 
 #include <asm/io.h>
 #include <asm/bugs.h>
@@ -747,11 +748,8 @@ __setup("nosoftlockup", nosoftlockup_setup);
 static void __init do_pre_smp_initcalls(void)
 {
 	extern int spawn_ksoftirqd(void);
-#ifdef CONFIG_SMP
-	extern int migration_init(void);
 
 	migration_init();
-#endif
 	spawn_ksoftirqd();
 	if (!nosoftlockup)
 		spawn_softlockup_task();

kernel/fork.c

@@ -1123,6 +1123,9 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	p->blocked_on = NULL; /* not blocked yet */
 #endif
 
+	/* Perform scheduler related setup. Assign this task to a CPU. */
+	sched_fork(p, clone_flags);
+
 	if ((retval = security_task_alloc(p)))
 		goto bad_fork_cleanup_policy;
 	if ((retval = audit_alloc(p)))
@@ -1212,9 +1215,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	INIT_LIST_HEAD(&p->ptrace_children);
 	INIT_LIST_HEAD(&p->ptrace_list);
 
-	/* Perform scheduler related setup. Assign this task to a CPU. */
-	sched_fork(p, clone_flags);
-
 	/* Now that the task is set up, run cgroup callbacks if
 	 * necessary. We need to run them before the task is visible
 	 * on the tasklist. */