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:
  sched: fix typo in sched-rt-group.txt file
  ftrace: fix typo about map of kernel priority in ftrace.txt file.
  sched: properly define the sched_group::cpumask and sched_domain::span fields
  sched, timers: cleanup avenrun users
  sched, timers: move calc_load() to scheduler
  sched: Don't export sched_mc_power_savings on multi-socket single core system
  sched: emit thread info flags with stack trace
  sched: rt: document the risk of small values in the bandwidth settings
  sched: Replace first_cpu() with cpumask_first() in ILB nomination code
  sched: remove extra call overhead for schedule()
  sched: use group_first_cpu() instead of cpumask_first(sched_group_cpus())
  wait: don't use __wake_up_common()
  sched: Nominate a power-efficient ilb in select_nohz_balancer()
  sched: Nominate idle load balancer from a semi-idle package.
  sched: remove redundant hierarchy walk in check_preempt_wakeup

Documentation/scheduler/sched-rt-group.txt

@@ -4,6 +4,7 @@
 CONTENTS
 ========
 
+0. WARNING
 1. Overview
   1.1 The problem
   1.2 The solution
@@ -14,6 +15,23 @@ CONTENTS
 3. Future plans
 
 
+0. WARNING
+==========
+
+ Fiddling with these settings can result in an unstable system, the knobs are
+ root only and assumes root knows what he is doing.
+
+Most notable:
+
+ * very small values in sched_rt_period_us can result in an unstable
+   system when the period is smaller than either the available hrtimer
+   resolution, or the time it takes to handle the budget refresh itself.
+
+ * very small values in sched_rt_runtime_us can result in an unstable
+   system when the runtime is so small the system has difficulty making
+   forward progress (NOTE: the migration thread and kstopmachine both
+   are real-time processes).
+
 1. Overview
 ===========
 
@@ -169,7 +187,7 @@ get their allocated time.
 
 Implementing SCHED_EDF might take a while to complete. Priority Inheritance is
 the biggest challenge as the current linux PI infrastructure is geared towards
-the limited static priority levels 0-139. With deadline scheduling you need to
+the limited static priority levels 0-99. With deadline scheduling you need to
 do deadline inheritance (since priority is inversely proportional to the
 deadline delta (deadline - now).
 

Documentation/trace/ftrace.txt

@@ -518,9 +518,18 @@ priority with zero (0) being the highest priority and the nice
 values starting at 100 (nice -20). Below is a quick chart to map
 the kernel priority to user land priorities.
 
-  Kernel priority: 0 to 99    ==> user RT priority 99 to 0
-  Kernel priority: 100 to 139 ==> user nice -20 to 19
-  Kernel priority: 140        ==> idle task priority
+   Kernel Space                     User Space
+ ===============================================================
+   0(high) to  98(low)     user RT priority 99(high) to 1(low)
+                           with SCHED_RR or SCHED_FIFO
+ ---------------------------------------------------------------
+  99                       sched_priority is not used in scheduling
+                           decisions(it must be specified as 0)
+ ---------------------------------------------------------------
+ 100(high) to 139(low)     user nice -20(high) to 19(low)
+ ---------------------------------------------------------------
+ 140                       idle task priority
+ ---------------------------------------------------------------
 
 The task states are:
 

arch/x86/include/asm/topology.h

@@ -203,7 +203,8 @@ struct pci_bus;
 void x86_pci_root_bus_res_quirks(struct pci_bus *b);
 
 #ifdef CONFIG_SMP
-#define mc_capable()	(cpumask_weight(cpu_core_mask(0)) != nr_cpu_ids)
+#define mc_capable()	((boot_cpu_data.x86_max_cores > 1) && \
+			(cpumask_weight(cpu_core_mask(0)) != nr_cpu_ids))
 #define smt_capable()			(smp_num_siblings > 1)
 #endif
 

fs/proc/loadavg.c

@@ -12,20 +12,14 @@
 
 static int loadavg_proc_show(struct seq_file *m, void *v)
 {
-	int a, b, c;
-	unsigned long seq;
+	unsigned long avnrun[3];
 
-	do {
-		seq = read_seqbegin(&xtime_lock);
-		a = avenrun[0] + (FIXED_1/200);
-		b = avenrun[1] + (FIXED_1/200);
-		c = avenrun[2] + (FIXED_1/200);
-	} while (read_seqretry(&xtime_lock, seq));
+	get_avenrun(avnrun, FIXED_1/200, 0);
 
-	seq_printf(m, "%d.%02d %d.%02d %d.%02d %ld/%d %d\n",
-		LOAD_INT(a), LOAD_FRAC(a),
-		LOAD_INT(b), LOAD_FRAC(b),
-		LOAD_INT(c), LOAD_FRAC(c),
+	seq_printf(m, "%lu.%02lu %lu.%02lu %lu.%02lu %ld/%d %d\n",
+		LOAD_INT(avnrun[0]), LOAD_FRAC(avnrun[0]),
+		LOAD_INT(avnrun[1]), LOAD_FRAC(avnrun[1]),
+		LOAD_INT(avnrun[2]), LOAD_FRAC(avnrun[2]),
 		nr_running(), nr_threads,
 		task_active_pid_ns(current)->last_pid);
 	return 0;

include/linux/sched.h

@@ -116,6 +116,7 @@ struct fs_struct;
  *    11 bit fractions.
  */
 extern unsigned long avenrun[];		/* Load averages */
+extern void get_avenrun(unsigned long *loads, unsigned long offset, int shift);
 
 #define FSHIFT		11		/* nr of bits of precision */
 #define FIXED_1		(1<<FSHIFT)	/* 1.0 as fixed-point */
@@ -135,8 +136,8 @@ DECLARE_PER_CPU(unsigned long, process_counts);
 extern int nr_processes(void);
 extern unsigned long nr_running(void);
 extern unsigned long nr_uninterruptible(void);
-extern unsigned long nr_active(void);
 extern unsigned long nr_iowait(void);
+extern void calc_global_load(void);
 
 extern unsigned long get_parent_ip(unsigned long addr);
 
@@ -838,7 +839,17 @@ struct sched_group {
 	 */
 	u32 reciprocal_cpu_power;
 
-	unsigned long cpumask[];
+	/*
+	 * The CPUs this group covers.
+	 *
+	 * NOTE: this field is variable length. (Allocated dynamically
+	 * by attaching extra space to the end of the structure,
+	 * depending on how many CPUs the kernel has booted up with)
+	 *
+	 * It is also be embedded into static data structures at build
+	 * time. (See 'struct static_sched_group' in kernel/sched.c)
+	 */
+	unsigned long cpumask[0];
 };
 
 static inline struct cpumask *sched_group_cpus(struct sched_group *sg)
@@ -924,8 +935,17 @@ struct sched_domain {
 	char *name;
 #endif
 
-	/* span of all CPUs in this domain */
-	unsigned long span[];
+	/*
+	 * Span of all CPUs in this domain.
+	 *
+	 * NOTE: this field is variable length. (Allocated dynamically
+	 * by attaching extra space to the end of the structure,
+	 * depending on how many CPUs the kernel has booted up with)
+	 *
+	 * It is also be embedded into static data structures at build
+	 * time. (See 'struct static_sched_domain' in kernel/sched.c)
+	 */
+	unsigned long span[0];
 };
 
 static inline struct cpumask *sched_domain_span(struct sched_domain *sd)

include/linux/wait.h

@@ -132,8 +132,6 @@ static inline void __remove_wait_queue(wait_queue_head_t *head,
 	list_del(&old->task_list);
 }
 
-void __wake_up_common(wait_queue_head_t *q, unsigned int mode,
-			int nr_exclusive, int sync, void *key);
 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,

kernel/mutex.c

@@ -249,7 +249,9 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 
 		/* didnt get the lock, go to sleep: */
 		spin_unlock_mutex(&lock->wait_lock, flags);
-		__schedule();
+		preempt_enable_no_resched();
+		schedule();
+		preempt_disable();
 		spin_lock_mutex(&lock->wait_lock, flags);
 	}
 

kernel/sched_fair.c

@@ -1487,17 +1487,10 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int sync)
 
 	find_matching_se(&se, &pse);
 
-	while (se) {
 	BUG_ON(!pse);
 
-		if (wakeup_preempt_entity(se, pse) == 1) {
+	if (wakeup_preempt_entity(se, pse) == 1)
 		resched_task(curr);
-			break;
-		}
-
-		se = parent_entity(se);
-		pse = parent_entity(pse);
-	}
 }
 
 static struct task_struct *pick_next_task_fair(struct rq *rq)

kernel/sched_idletask.c

@@ -22,7 +22,8 @@ static void check_preempt_curr_idle(struct rq *rq, struct task_struct *p, int sy
 static struct task_struct *pick_next_task_idle(struct rq *rq)
 {
 	schedstat_inc(rq, sched_goidle);
-
+	/* adjust the active tasks as we might go into a long sleep */
+	calc_load_account_active(rq);
 	return rq->idle;
 }
 

kernel/time/timekeeping.c

@@ -22,7 +22,7 @@
 
 /*
  * This read-write spinlock protects us from races in SMP while
- * playing with xtime and avenrun.
+ * playing with xtime.
  */
 __cacheline_aligned_in_smp DEFINE_SEQLOCK(xtime_lock);
 

kernel/timer.c

@@ -1122,47 +1122,6 @@ void update_process_times(int user_tick)
 	run_posix_cpu_timers(p);
 }
 
-/*
- * Nr of active tasks - counted in fixed-point numbers
- */
-static unsigned long count_active_tasks(void)
-{
-	return nr_active() * FIXED_1;
-}
-
-/*
- * Hmm.. Changed this, as the GNU make sources (load.c) seems to
- * imply that avenrun[] is the standard name for this kind of thing.
- * Nothing else seems to be standardized: the fractional size etc
- * all seem to differ on different machines.
- *
- * Requires xtime_lock to access.
- */
-unsigned long avenrun[3];
-
-EXPORT_SYMBOL(avenrun);
-
-/*
- * calc_load - given tick count, update the avenrun load estimates.
- * This is called while holding a write_lock on xtime_lock.
- */
-static inline void calc_load(unsigned long ticks)
-{
-	unsigned long active_tasks; /* fixed-point */
-	static int count = LOAD_FREQ;
-
-	count -= ticks;
-	if (unlikely(count < 0)) {
-		active_tasks = count_active_tasks();
-		do {
-			CALC_LOAD(avenrun[0], EXP_1, active_tasks);
-			CALC_LOAD(avenrun[1], EXP_5, active_tasks);
-			CALC_LOAD(avenrun[2], EXP_15, active_tasks);
-			count += LOAD_FREQ;
-		} while (count < 0);
-	}
-}
-
 /*
  * This function runs timers and the timer-tq in bottom half context.
  */
@@ -1186,16 +1145,6 @@ void run_local_timers(void)
 	softlockup_tick();
 }
 
-/*
- * Called by the timer interrupt. xtime_lock must already be taken
- * by the timer IRQ!
- */
-static inline void update_times(unsigned long ticks)
-{
-	update_wall_time();
-	calc_load(ticks);
-}
-
 /*
  * The 64-bit jiffies value is not atomic - you MUST NOT read it
  * without sampling the sequence number in xtime_lock.
@@ -1205,7 +1154,8 @@ static inline void update_times(unsigned long ticks)
 void do_timer(unsigned long ticks)
 {
 	jiffies_64 += ticks;
-	update_times(ticks);
+	update_wall_time();
+	calc_global_load();
 }
 
 #ifdef __ARCH_WANT_SYS_ALARM
@@ -1406,37 +1356,17 @@ int do_sysinfo(struct sysinfo *info)
 {
 	unsigned long mem_total, sav_total;
 	unsigned int mem_unit, bitcount;
-	unsigned long seq;
-
-	memset(info, 0, sizeof(struct sysinfo));
-
-	do {
 	struct timespec tp;
-		seq = read_seqbegin(&xtime_lock);
 
-		/*
-		 * This is annoying.  The below is the same thing
-		 * posix_get_clock_monotonic() does, but it wants to
-		 * take the lock which we want to cover the loads stuff
-		 * too.
-		 */
+	memset(info, 0, sizeof(struct sysinfo));
 
-		getnstimeofday(&tp);
-		tp.tv_sec += wall_to_monotonic.tv_sec;
-		tp.tv_nsec += wall_to_monotonic.tv_nsec;
+	ktime_get_ts(&tp);
 	monotonic_to_bootbased(&tp);
-		if (tp.tv_nsec - NSEC_PER_SEC >= 0) {
-			tp.tv_nsec = tp.tv_nsec - NSEC_PER_SEC;
-			tp.tv_sec++;
-		}
 	info->uptime = tp.tv_sec + (tp.tv_nsec ? 1 : 0);
 
-		info->loads[0] = avenrun[0] << (SI_LOAD_SHIFT - FSHIFT);
-		info->loads[1] = avenrun[1] << (SI_LOAD_SHIFT - FSHIFT);
-		info->loads[2] = avenrun[2] << (SI_LOAD_SHIFT - FSHIFT);
+	get_avenrun(info->loads, 0, SI_LOAD_SHIFT - FSHIFT);
 
 	info->procs = nr_threads;
-	} while (read_seqretry(&xtime_lock, seq));
 
 	si_meminfo(info);
 	si_swapinfo(info);

kernel/wait.c

@@ -154,7 +154,7 @@ void abort_exclusive_wait(wait_queue_head_t *q, wait_queue_t *wait,
 	if (!list_empty(&wait->task_list))
 		list_del_init(&wait->task_list);
 	else if (waitqueue_active(q))
-		__wake_up_common(q, mode, 1, 0, key);
+		__wake_up_locked_key(q, mode, key);
 	spin_unlock_irqrestore(&q->lock, flags);
 }
 EXPORT_SYMBOL(abort_exclusive_wait);