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

…inux/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: (27 commits)
  sched: Use correct macro to display sched_child_runs_first in /proc/sched_debug
  sched: No need for bootmem special cases
  sched: Revert nohz_ratelimit() for now
  sched: Reduce update_group_power() calls
  sched: Update rq->clock for nohz balanced cpus
  sched: Fix spelling of sibling
  sched, cpuset: Drop __cpuexit from cpu hotplug callbacks
  sched: Fix the racy usage of thread_group_cputimer() in fastpath_timer_check()
  sched: run_posix_cpu_timers: Don't check ->exit_state, use lock_task_sighand()
  sched: thread_group_cputime: Simplify, document the "alive" check
  sched: Remove the obsolete exit_state/signal hacks
  sched: task_tick_rt: Remove the obsolete ->signal != NULL check
  sched: __sched_setscheduler: Read the RLIMIT_RTPRIO value lockless
  sched: Fix comments to make them DocBook happy
  sched: Fix fix_small_capacity
  powerpc: Exclude arch_sd_sibiling_asym_packing() on UP
  powerpc: Enable asymmetric SMT scheduling on POWER7
  sched: Add asymmetric group packing option for sibling domain
  sched: Fix capacity calculations for SMT4
  sched: Change nohz idle load balancing logic to push model
  ...

arch/parisc/kernel/ftrace.c

@@ -82,7 +82,7 @@ unsigned long ftrace_return_to_handler(unsigned long retval0,
 	unsigned long ret;
 
 	pop_return_trace(&trace, &ret);
-	trace.rettime = cpu_clock(raw_smp_processor_id());
+	trace.rettime = local_clock();
 	ftrace_graph_return(&trace);
 
 	if (unlikely(!ret)) {
@@ -126,7 +126,7 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr)
 		return;
 	}
 
-	calltime = cpu_clock(raw_smp_processor_id());
+	calltime = local_clock();
 
 	if (push_return_trace(old, calltime,
 				self_addr, &trace.depth) == -EBUSY) {

arch/powerpc/include/asm/cputable.h

@@ -197,6 +197,7 @@ extern const char *powerpc_base_platform;
 #define CPU_FTR_SAO			LONG_ASM_CONST(0x0020000000000000)
 #define CPU_FTR_CP_USE_DCBTZ		LONG_ASM_CONST(0x0040000000000000)
 #define CPU_FTR_UNALIGNED_LD_STD	LONG_ASM_CONST(0x0080000000000000)
+#define CPU_FTR_ASYM_SMT		LONG_ASM_CONST(0x0100000000000000)
 
 #ifndef __ASSEMBLY__
 
@@ -412,7 +413,7 @@ extern const char *powerpc_base_platform;
 	    CPU_FTR_MMCRA | CPU_FTR_SMT | \
 	    CPU_FTR_COHERENT_ICACHE | CPU_FTR_LOCKLESS_TLBIE | \
 	    CPU_FTR_PURR | CPU_FTR_SPURR | CPU_FTR_REAL_LE | \
-	    CPU_FTR_DSCR | CPU_FTR_SAO)
+	    CPU_FTR_DSCR | CPU_FTR_SAO  | CPU_FTR_ASYM_SMT)
 #define CPU_FTRS_CELL	(CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \
 	    CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \
 	    CPU_FTR_ALTIVEC_COMP | CPU_FTR_MMCRA | CPU_FTR_SMT | \

arch/powerpc/kernel/process.c

@@ -1299,3 +1299,14 @@ unsigned long randomize_et_dyn(unsigned long base)
 
 	return ret;
 }
+
+#ifdef CONFIG_SMP
+int arch_sd_sibling_asym_packing(void)
+{
+	if (cpu_has_feature(CPU_FTR_ASYM_SMT)) {
+		printk_once(KERN_INFO "Enabling Asymmetric SMT scheduling\n");
+		return SD_ASYM_PACKING;
+	}
+	return 0;
+}
+#endif

include/linux/cpu.h

@@ -48,6 +48,31 @@ extern ssize_t arch_cpu_release(const char *, size_t);
 #endif
 struct notifier_block;
 
+/*
+ * CPU notifier priorities.
+ */
+enum {
+	/*
+	 * SCHED_ACTIVE marks a cpu which is coming up active during
+	 * CPU_ONLINE and CPU_DOWN_FAILED and must be the first
+	 * notifier.  CPUSET_ACTIVE adjusts cpuset according to
+	 * cpu_active mask right after SCHED_ACTIVE.  During
+	 * CPU_DOWN_PREPARE, SCHED_INACTIVE and CPUSET_INACTIVE are
+	 * ordered in the similar way.
+	 *
+	 * This ordering guarantees consistent cpu_active mask and
+	 * migration behavior to all cpu notifiers.
+	 */
+	CPU_PRI_SCHED_ACTIVE	= INT_MAX,
+	CPU_PRI_CPUSET_ACTIVE	= INT_MAX - 1,
+	CPU_PRI_SCHED_INACTIVE	= INT_MIN + 1,
+	CPU_PRI_CPUSET_INACTIVE	= INT_MIN,
+
+	/* migration should happen before other stuff but after perf */
+	CPU_PRI_PERF		= 20,
+	CPU_PRI_MIGRATION	= 10,
+};
+
 #ifdef CONFIG_SMP
 /* Need to know about CPUs going up/down? */
 #if defined(CONFIG_HOTPLUG_CPU) || !defined(MODULE)

include/linux/cpuset.h

@@ -20,6 +20,7 @@ extern int number_of_cpusets;	/* How many cpusets are defined in system? */
 
 extern int cpuset_init(void);
 extern void cpuset_init_smp(void);
+extern void cpuset_update_active_cpus(void);
 extern void cpuset_cpus_allowed(struct task_struct *p, struct cpumask *mask);
 extern int cpuset_cpus_allowed_fallback(struct task_struct *p);
 extern nodemask_t cpuset_mems_allowed(struct task_struct *p);
@@ -132,6 +133,11 @@ static inline void set_mems_allowed(nodemask_t nodemask)
 static inline int cpuset_init(void) { return 0; }
 static inline void cpuset_init_smp(void) {}
 
+static inline void cpuset_update_active_cpus(void)
+{
+	partition_sched_domains(1, NULL, NULL);
+}
+
 static inline void cpuset_cpus_allowed(struct task_struct *p,
 				       struct cpumask *mask)
 {

include/linux/perf_event.h

@@ -1067,7 +1067,7 @@ static inline void perf_event_disable(struct perf_event *event)		{ }
 #define perf_cpu_notifier(fn)					\
 do {								\
 	static struct notifier_block fn##_nb __cpuinitdata =	\
-		{ .notifier_call = fn, .priority = 20 };	\
+		{ .notifier_call = fn, .priority = CPU_PRI_PERF }; \
 	fn(&fn##_nb, (unsigned long)CPU_UP_PREPARE,		\
 		(void *)(unsigned long)smp_processor_id());	\
 	fn(&fn##_nb, (unsigned long)CPU_STARTING,		\

include/linux/sched.h

@@ -272,19 +272,10 @@ extern int runqueue_is_locked(int cpu);
 
 extern cpumask_var_t nohz_cpu_mask;
 #if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ)
-extern int select_nohz_load_balancer(int cpu);
-extern int get_nohz_load_balancer(void);
-extern int nohz_ratelimit(int cpu);
+extern void select_nohz_load_balancer(int stop_tick);
+extern int get_nohz_timer_target(void);
 #else
-static inline int select_nohz_load_balancer(int cpu)
-{
-	return 0;
-}
-
-static inline int nohz_ratelimit(int cpu)
-{
-	return 0;
-}
+static inline void select_nohz_load_balancer(int stop_tick) { }
 #endif
 
 /*
@@ -801,7 +792,7 @@ enum cpu_idle_type {
 #define SD_POWERSAVINGS_BALANCE	0x0100	/* Balance for power savings */
 #define SD_SHARE_PKG_RESOURCES	0x0200	/* Domain members share cpu pkg resources */
 #define SD_SERIALIZE		0x0400	/* Only a single load balancing instance */
-
+#define SD_ASYM_PACKING		0x0800  /* Place busy groups earlier in the domain */
 #define SD_PREFER_SIBLING	0x1000	/* Prefer to place tasks in a sibling domain */
 
 enum powersavings_balance_level {
@@ -836,6 +827,8 @@ static inline int sd_balance_for_package_power(void)
 	return SD_PREFER_SIBLING;
 }
 
+extern int __weak arch_sd_sibiling_asym_packing(void);
+
 /*
  * Optimise SD flags for power savings:
  * SD_BALANCE_NEWIDLE helps agressive task consolidation and power savings.
@@ -857,7 +850,7 @@ struct sched_group {
 	 * CPU power of this group, SCHED_LOAD_SCALE being max power for a
 	 * single CPU.
 	 */
-	unsigned int cpu_power;
+	unsigned int cpu_power, cpu_power_orig;
 
 	/*
 	 * The CPUs this group covers.
@@ -1693,6 +1686,7 @@ extern void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *
 #define PF_EXITING	0x00000004	/* getting shut down */
 #define PF_EXITPIDONE	0x00000008	/* pi exit done on shut down */
 #define PF_VCPU		0x00000010	/* I'm a virtual CPU */
+#define PF_WQ_WORKER	0x00000020	/* I'm a workqueue worker */
 #define PF_FORKNOEXEC	0x00000040	/* forked but didn't exec */
 #define PF_MCE_PROCESS  0x00000080      /* process policy on mce errors */
 #define PF_SUPERPRIV	0x00000100	/* used super-user privileges */
@@ -1787,20 +1781,23 @@ static inline int set_cpus_allowed(struct task_struct *p, cpumask_t new_mask)
 #endif
 
 /*
- * Architectures can set this to 1 if they have specified
- * CONFIG_HAVE_UNSTABLE_SCHED_CLOCK in their arch Kconfig,
- * but then during bootup it turns out that sched_clock()
- * is reliable after all:
+ * Do not use outside of architecture code which knows its limitations.
+ *
+ * sched_clock() has no promise of monotonicity or bounded drift between
+ * CPUs, use (which you should not) requires disabling IRQs.
+ *
+ * Please use one of the three interfaces below.
  */
-#ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
-extern int sched_clock_stable;
-#endif
-
-/* ftrace calls sched_clock() directly */
 extern unsigned long long notrace sched_clock(void);
+/*
+ * See the comment in kernel/sched_clock.c
+ */
+extern u64 cpu_clock(int cpu);
+extern u64 local_clock(void);
+extern u64 sched_clock_cpu(int cpu);
+
 
 extern void sched_clock_init(void);
-extern u64 sched_clock_cpu(int cpu);
 
 #ifndef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
 static inline void sched_clock_tick(void)
@@ -1815,17 +1812,19 @@ static inline void sched_clock_idle_wakeup_event(u64 delta_ns)
 {
 }
 #else
+/*
+ * Architectures can set this to 1 if they have specified
+ * CONFIG_HAVE_UNSTABLE_SCHED_CLOCK in their arch Kconfig,
+ * but then during bootup it turns out that sched_clock()
+ * is reliable after all:
+ */
+extern int sched_clock_stable;
+
 extern void sched_clock_tick(void);
 extern void sched_clock_idle_sleep_event(void);
 extern void sched_clock_idle_wakeup_event(u64 delta_ns);
 #endif
 
-/*
- * For kernel-internal use: high-speed (but slightly incorrect) per-cpu
- * clock constructed from sched_clock():
- */
-extern unsigned long long cpu_clock(int cpu);
-
 extern unsigned long long
 task_sched_runtime(struct task_struct *task);
 extern unsigned long long thread_group_sched_runtime(struct task_struct *task);

include/linux/topology.h

@@ -103,6 +103,7 @@ int arch_update_cpu_topology(void);
 				| 1*SD_SHARE_PKG_RESOURCES		\
 				| 0*SD_SERIALIZE			\
 				| 0*SD_PREFER_SIBLING			\
+				| arch_sd_sibling_asym_packing()	\
 				,					\
 	.last_balance		= jiffies,				\
 	.balance_interval	= 1,					\

kernel/cpu.c

@@ -235,11 +235,8 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
 		return -EINVAL;
 
 	cpu_hotplug_begin();
-	set_cpu_active(cpu, false);
 	err = __cpu_notify(CPU_DOWN_PREPARE | mod, hcpu, -1, &nr_calls);
 	if (err) {
-		set_cpu_active(cpu, true);
-
 		nr_calls--;
 		__cpu_notify(CPU_DOWN_FAILED | mod, hcpu, nr_calls, NULL);
 		printk("%s: attempt to take down CPU %u failed\n",
@@ -249,7 +246,6 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
 
 	err = __stop_machine(take_cpu_down, &tcd_param, cpumask_of(cpu));
 	if (err) {
-		set_cpu_active(cpu, true);
 		/* CPU didn't die: tell everyone.  Can't complain. */
 		cpu_notify_nofail(CPU_DOWN_FAILED | mod, hcpu);
 
@@ -321,8 +317,6 @@ static int __cpuinit _cpu_up(unsigned int cpu, int tasks_frozen)
 		goto out_notify;
 	BUG_ON(!cpu_online(cpu));
 
-	set_cpu_active(cpu, true);
-
 	/* Now call notifier in preparation. */
 	cpu_notify(CPU_ONLINE | mod, hcpu);
 

kernel/cpuset.c

@@ -2113,31 +2113,17 @@ static void scan_for_empty_cpusets(struct cpuset *root)
  * but making no active use of cpusets.
  *
  * This routine ensures that top_cpuset.cpus_allowed tracks
- * cpu_online_map on each CPU hotplug (cpuhp) event.
+ * cpu_active_mask on each CPU hotplug (cpuhp) event.
  *
  * Called within get_online_cpus().  Needs to call cgroup_lock()
  * before calling generate_sched_domains().
  */
-static int cpuset_track_online_cpus(struct notifier_block *unused_nb,
-				unsigned long phase, void *unused_cpu)
+void cpuset_update_active_cpus(void)
 {
 	struct sched_domain_attr *attr;
 	cpumask_var_t *doms;
 	int ndoms;
 
-	switch (phase) {
-	case CPU_ONLINE:
-	case CPU_ONLINE_FROZEN:
-	case CPU_DOWN_PREPARE:
-	case CPU_DOWN_PREPARE_FROZEN:
-	case CPU_DOWN_FAILED:
-	case CPU_DOWN_FAILED_FROZEN:
-		break;
-
-	default:
-		return NOTIFY_DONE;
-	}
-
 	cgroup_lock();
 	mutex_lock(&callback_mutex);
 	cpumask_copy(top_cpuset.cpus_allowed, cpu_active_mask);
@@ -2148,8 +2134,6 @@ static int cpuset_track_online_cpus(struct notifier_block *unused_nb,
 
 	/* Have scheduler rebuild the domains */
 	partition_sched_domains(ndoms, doms, attr);
-
-	return NOTIFY_OK;
 }
 
 #ifdef CONFIG_MEMORY_HOTPLUG
@@ -2203,7 +2187,6 @@ void __init cpuset_init_smp(void)
 	cpumask_copy(top_cpuset.cpus_allowed, cpu_active_mask);
 	top_cpuset.mems_allowed = node_states[N_HIGH_MEMORY];
 
-	hotcpu_notifier(cpuset_track_online_cpus, 0);
 	hotplug_memory_notifier(cpuset_track_online_nodes, 10);
 
 	cpuset_wq = create_singlethread_workqueue("cpuset");

kernel/fork.c

@@ -907,7 +907,7 @@ static void copy_flags(unsigned long clone_flags, struct task_struct *p)
 {
 	unsigned long new_flags = p->flags;
 
-	new_flags &= ~PF_SUPERPRIV;
+	new_flags &= ~(PF_SUPERPRIV | PF_WQ_WORKER);
 	new_flags |= PF_FORKNOEXEC;
 	new_flags |= PF_STARTING;
 	p->flags = new_flags;

kernel/hrtimer.c

@@ -144,12 +144,8 @@ struct hrtimer_clock_base *lock_hrtimer_base(const struct hrtimer *timer,
 static int hrtimer_get_target(int this_cpu, int pinned)
 {
 #ifdef CONFIG_NO_HZ
-	if (!pinned && get_sysctl_timer_migration() && idle_cpu(this_cpu)) {
-		int preferred_cpu = get_nohz_load_balancer();
-
-		if (preferred_cpu >= 0)
-			return preferred_cpu;
-	}
+	if (!pinned && get_sysctl_timer_migration() && idle_cpu(this_cpu))
+		return get_nohz_timer_target();
 #endif
 	return this_cpu;
 }

kernel/lockdep.c

@@ -146,7 +146,7 @@ static DEFINE_PER_CPU(struct lock_class_stats[MAX_LOCKDEP_KEYS],
 
 static inline u64 lockstat_clock(void)
 {
-	return cpu_clock(smp_processor_id());
+	return local_clock();
 }
 
 static int lock_point(unsigned long points[], unsigned long ip)

kernel/perf_event.c

@@ -214,7 +214,7 @@ static void perf_unpin_context(struct perf_event_context *ctx)
 
 static inline u64 perf_clock(void)
 {
-	return cpu_clock(raw_smp_processor_id());
+	return local_clock();
 }
 
 /*