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: (64 commits)
  sched: Fix sched::sched_stat_wait tracepoint field
  sched: Disable NEW_FAIR_SLEEPERS for now
  sched: Keep kthreads at default priority
  sched: Re-tune the scheduler latency defaults to decrease worst-case latencies
  sched: Turn off child_runs_first
  sched: Ensure that a child can't gain time over it's parent after fork()
  sched: enable SD_WAKE_IDLE
  sched: Deal with low-load in wake_affine()
  sched: Remove short cut from select_task_rq_fair()
  sched: Turn on SD_BALANCE_NEWIDLE
  sched: Clean up topology.h
  sched: Fix dynamic power-balancing crash
  sched: Remove reciprocal for cpu_power
  sched: Try to deal with low capacity, fix update_sd_power_savings_stats()
  sched: Try to deal with low capacity
  sched: Scale down cpu_power due to RT tasks
  sched: Implement dynamic cpu_power
  sched: Add smt_gain
  sched: Update the cpu_power sum during load-balance
  sched: Add SD_PREFER_SIBLING
  ...

5 files changed, 260 insertions, 108 deletions

diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h
index 330cb31bb49..6d527ee82b2 100644
--- a/include/linux/hardirq.h
+++ b/include/linux/hardirq.h
@@ -64,6 +64,12 @@
 #define HARDIRQ_OFFSET	(1UL << HARDIRQ_SHIFT)
 #define NMI_OFFSET	(1UL << NMI_SHIFT)
 
+#ifndef PREEMPT_ACTIVE
+#define PREEMPT_ACTIVE_BITS	1
+#define PREEMPT_ACTIVE_SHIFT	(NMI_SHIFT + NMI_BITS)
+#define PREEMPT_ACTIVE	(__IRQ_MASK(PREEMPT_ACTIVE_BITS) << PREEMPT_ACTIVE_SHIFT)
+#endif
+
 #if PREEMPT_ACTIVE < (1 << (NMI_SHIFT + NMI_BITS))
 #error PREEMPT_ACTIVE is too low!
 #endif
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index d6320a3e8de..2b5b1e0899a 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -125,7 +125,7 @@ extern int _cond_resched(void);
 #endif
 
 #ifdef CONFIG_DEBUG_SPINLOCK_SLEEP
-  void __might_sleep(char *file, int line);
+  void __might_sleep(char *file, int line, int preempt_offset);
 /**
  * might_sleep - annotation for functions that can sleep
  *
@@ -137,8 +137,9 @@ extern int _cond_resched(void);
  * supposed to.
  */
 # define might_sleep() \
-	do { __might_sleep(__FILE__, __LINE__); might_resched(); } while (0)
+	do { __might_sleep(__FILE__, __LINE__, 0); might_resched(); } while (0)
 #else
+  static inline void __might_sleep(char *file, int line, int preempt_offset) { }
 # define might_sleep() do { might_resched(); } while (0)
 #endif
 
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 379531c0897..f3d74bd04d1 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -38,6 +38,8 @@
 #define SCHED_BATCH		3
 /* SCHED_ISO: reserved but not implemented yet */
 #define SCHED_IDLE		5
+/* Can be ORed in to make sure the process is reverted back to SCHED_NORMAL on fork */
+#define SCHED_RESET_ON_FORK     0x40000000
 
 #ifdef __KERNEL__
 
@@ -796,18 +798,19 @@ enum cpu_idle_type {
 #define SCHED_LOAD_SCALE_FUZZ	SCHED_LOAD_SCALE
 
 #ifdef CONFIG_SMP
-#define SD_LOAD_BALANCE		1	/* Do load balancing on this domain. */
-#define SD_BALANCE_NEWIDLE	2	/* Balance when about to become idle */
-#define SD_BALANCE_EXEC		4	/* Balance on exec */
-#define SD_BALANCE_FORK		8	/* Balance on fork, clone */
-#define SD_WAKE_IDLE		16	/* Wake to idle CPU on task wakeup */
-#define SD_WAKE_AFFINE		32	/* Wake task to waking CPU */
-#define SD_WAKE_BALANCE		64	/* Perform balancing at task wakeup */
-#define SD_SHARE_CPUPOWER	128	/* Domain members share cpu power */
-#define SD_POWERSAVINGS_BALANCE	256	/* Balance for power savings */
-#define SD_SHARE_PKG_RESOURCES	512	/* Domain members share cpu pkg resources */
-#define SD_SERIALIZE		1024	/* Only a single load balancing instance */
-#define SD_WAKE_IDLE_FAR	2048	/* Gain latency sacrificing cache hit */
+#define SD_LOAD_BALANCE		0x0001	/* Do load balancing on this domain. */
+#define SD_BALANCE_NEWIDLE	0x0002	/* Balance when about to become idle */
+#define SD_BALANCE_EXEC		0x0004	/* Balance on exec */
+#define SD_BALANCE_FORK		0x0008	/* Balance on fork, clone */
+#define SD_WAKE_IDLE		0x0010	/* Wake to idle CPU on task wakeup */
+#define SD_WAKE_AFFINE		0x0020	/* Wake task to waking CPU */
+#define SD_WAKE_BALANCE		0x0040	/* Perform balancing at task wakeup */
+#define SD_SHARE_CPUPOWER	0x0080	/* Domain members share cpu power */
+#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_WAKE_IDLE_FAR	0x0800	/* Gain latency sacrificing cache hit */
+#define SD_PREFER_SIBLING	0x1000	/* Prefer to place tasks in a sibling domain */
 
 enum powersavings_balance_level {
 	POWERSAVINGS_BALANCE_NONE = 0,  /* No power saving load balance */
@@ -827,7 +830,7 @@ static inline int sd_balance_for_mc_power(void)
 	if (sched_smt_power_savings)
 		return SD_POWERSAVINGS_BALANCE;
 
-	return 0;
+	return SD_PREFER_SIBLING;
 }
 
 static inline int sd_balance_for_package_power(void)
@@ -835,7 +838,7 @@ static inline int sd_balance_for_package_power(void)
 	if (sched_mc_power_savings | sched_smt_power_savings)
 		return SD_POWERSAVINGS_BALANCE;
 
-	return 0;
+	return SD_PREFER_SIBLING;
 }
 
 /*
@@ -857,15 +860,9 @@ struct sched_group {
 
 	/*
 	 * CPU power of this group, SCHED_LOAD_SCALE being max power for a
-	 * single CPU. This is read only (except for setup, hotplug CPU).
-	 * Note : Never change cpu_power without recompute its reciprocal
-	 */
-	unsigned int __cpu_power;
-	/*
-	 * reciprocal value of cpu_power to avoid expensive divides
-	 * (see include/linux/reciprocal_div.h)
+	 * single CPU.
 	 */
-	u32 reciprocal_cpu_power;
+	unsigned int cpu_power;
 
 	/*
 	 * The CPUs this group covers.
@@ -918,6 +915,7 @@ struct sched_domain {
 	unsigned int newidle_idx;
 	unsigned int wake_idx;
 	unsigned int forkexec_idx;
+	unsigned int smt_gain;
 	int flags;			/* See SD_* */
 	enum sched_domain_level level;
 
@@ -1045,7 +1043,6 @@ struct sched_class {
 			      struct rq *busiest, struct sched_domain *sd,
 			      enum cpu_idle_type idle);
 	void (*pre_schedule) (struct rq *this_rq, struct task_struct *task);
-	int (*needs_post_schedule) (struct rq *this_rq);
 	void (*post_schedule) (struct rq *this_rq);
 	void (*task_wake_up) (struct rq *this_rq, struct task_struct *task);
 
@@ -1110,6 +1107,8 @@ struct sched_entity {
 	u64			wait_max;
 	u64			wait_count;
 	u64			wait_sum;
+	u64			iowait_count;
+	u64			iowait_sum;
 
 	u64			sleep_start;
 	u64			sleep_max;
@@ -1234,11 +1233,19 @@ struct task_struct {
 	unsigned did_exec:1;
 	unsigned in_execve:1;	/* Tell the LSMs that the process is doing an
 				 * execve */
+	unsigned in_iowait:1;
+
+
+	/* Revert to default priority/policy when forking */
+	unsigned sched_reset_on_fork:1;
+
 	pid_t pid;
 	pid_t tgid;
 
+#ifdef CONFIG_CC_STACKPROTECTOR
 	/* Canary value for the -fstack-protector gcc feature */
 	unsigned long stack_canary;
+#endif
 
 	/* 
 	 * pointers to (original) parent process, youngest child, younger sibling,
@@ -1840,11 +1847,12 @@ extern unsigned int sysctl_sched_min_granularity;
 extern unsigned int sysctl_sched_wakeup_granularity;
 extern unsigned int sysctl_sched_shares_ratelimit;
 extern unsigned int sysctl_sched_shares_thresh;
-#ifdef CONFIG_SCHED_DEBUG
 extern unsigned int sysctl_sched_child_runs_first;
+#ifdef CONFIG_SCHED_DEBUG
 extern unsigned int sysctl_sched_features;
 extern unsigned int sysctl_sched_migration_cost;
 extern unsigned int sysctl_sched_nr_migrate;
+extern unsigned int sysctl_sched_time_avg;
 extern unsigned int sysctl_timer_migration;
 
 int sched_nr_latency_handler(struct ctl_table *table, int write,
@@ -2308,23 +2316,31 @@ static inline int need_resched(void)
  * cond_resched_softirq() will enable bhs before scheduling.
  */
 extern int _cond_resched(void);
-#ifdef CONFIG_PREEMPT_BKL
-static inline int cond_resched(void)
-{
-	return 0;
-}
+
+#define cond_resched() ({			\
+	__might_sleep(__FILE__, __LINE__, 0);	\
+	_cond_resched();			\
+})
+
+extern int __cond_resched_lock(spinlock_t *lock);
+
+#ifdef CONFIG_PREEMPT
+#define PREEMPT_LOCK_OFFSET	PREEMPT_OFFSET
 #else
-static inline int cond_resched(void)
-{
-	return _cond_resched();
-}
+#define PREEMPT_LOCK_OFFSET	0
 #endif
-extern int cond_resched_lock(spinlock_t * lock);
-extern int cond_resched_softirq(void);
-static inline int cond_resched_bkl(void)
-{
-	return _cond_resched();
-}
+
+#define cond_resched_lock(lock) ({				\
+	__might_sleep(__FILE__, __LINE__, PREEMPT_LOCK_OFFSET);	\
+	__cond_resched_lock(lock);				\
+})
+
+extern int __cond_resched_softirq(void);
+
+#define cond_resched_softirq() ({				\
+	__might_sleep(__FILE__, __LINE__, SOFTIRQ_OFFSET);	\
+	__cond_resched_softirq();				\
+})
 
 /*
  * Does a critical section need to be broken due to another
diff --git a/include/linux/topology.h b/include/linux/topology.h
index 7402c1a27c4..85e8cf7d393 100644
--- a/include/linux/topology.h
+++ b/include/linux/topology.h
@@ -85,20 +85,29 @@ int arch_update_cpu_topology(void);
 #define ARCH_HAS_SCHED_WAKE_IDLE
 /* Common values for SMT siblings */
 #ifndef SD_SIBLING_INIT
-#define SD_SIBLING_INIT (struct sched_domain) {		\
-	.min_interval		= 1,			\
-	.max_interval		= 2,			\
-	.busy_factor		= 64,			\
-	.imbalance_pct		= 110,			\
-	.flags			= SD_LOAD_BALANCE	\
-				| SD_BALANCE_NEWIDLE	\
-				| SD_BALANCE_FORK	\
-				| SD_BALANCE_EXEC	\
-				| SD_WAKE_AFFINE	\
-				| SD_WAKE_BALANCE	\
-				| SD_SHARE_CPUPOWER,	\
-	.last_balance		= jiffies,		\
-	.balance_interval	= 1,			\
+#define SD_SIBLING_INIT (struct sched_domain) {				\
+	.min_interval		= 1,					\
+	.max_interval		= 2,					\
+	.busy_factor		= 64,					\
+	.imbalance_pct		= 110,					\
+									\
+	.flags			= 1*SD_LOAD_BALANCE			\
+				| 1*SD_BALANCE_NEWIDLE			\
+				| 1*SD_BALANCE_EXEC			\
+				| 1*SD_BALANCE_FORK			\
+				| 0*SD_WAKE_IDLE			\
+				| 1*SD_WAKE_AFFINE			\
+				| 1*SD_WAKE_BALANCE			\
+				| 1*SD_SHARE_CPUPOWER			\
+				| 0*SD_POWERSAVINGS_BALANCE		\
+				| 0*SD_SHARE_PKG_RESOURCES		\
+				| 0*SD_SERIALIZE			\
+				| 0*SD_WAKE_IDLE_FAR			\
+				| 0*SD_PREFER_SIBLING			\
+				,					\
+	.last_balance		= jiffies,				\
+	.balance_interval	= 1,					\
+	.smt_gain		= 1178,	/* 15% */			\
 }
 #endif
 #endif /* CONFIG_SCHED_SMT */
@@ -106,69 +115,94 @@ int arch_update_cpu_topology(void);
 #ifdef CONFIG_SCHED_MC
 /* Common values for MC siblings. for now mostly derived from SD_CPU_INIT */
 #ifndef SD_MC_INIT
-#define SD_MC_INIT (struct sched_domain) {		\
-	.min_interval		= 1,			\
-	.max_interval		= 4,			\
-	.busy_factor		= 64,			\
-	.imbalance_pct		= 125,			\
-	.cache_nice_tries	= 1,			\
-	.busy_idx		= 2,			\
-	.wake_idx		= 1,			\
-	.forkexec_idx		= 1,			\
-	.flags			= SD_LOAD_BALANCE	\
-				| SD_BALANCE_FORK	\
-				| SD_BALANCE_EXEC	\
-				| SD_WAKE_AFFINE	\
-				| SD_WAKE_BALANCE	\
-				| SD_SHARE_PKG_RESOURCES\
-				| sd_balance_for_mc_power()\
-				| sd_power_saving_flags(),\
-	.last_balance		= jiffies,		\
-	.balance_interval	= 1,			\
+#define SD_MC_INIT (struct sched_domain) {				\
+	.min_interval		= 1,					\
+	.max_interval		= 4,					\
+	.busy_factor		= 64,					\
+	.imbalance_pct		= 125,					\
+	.cache_nice_tries	= 1,					\
+	.busy_idx		= 2,					\
+	.wake_idx		= 1,					\
+	.forkexec_idx		= 1,					\
+									\
+	.flags			= 1*SD_LOAD_BALANCE			\
+				| 1*SD_BALANCE_NEWIDLE			\
+				| 1*SD_BALANCE_EXEC			\
+				| 1*SD_BALANCE_FORK			\
+				| 1*SD_WAKE_IDLE			\
+				| 1*SD_WAKE_AFFINE			\
+				| 1*SD_WAKE_BALANCE			\
+				| 0*SD_SHARE_CPUPOWER			\
+				| 1*SD_SHARE_PKG_RESOURCES		\
+				| 0*SD_SERIALIZE			\
+				| 0*SD_WAKE_IDLE_FAR			\
+				| sd_balance_for_mc_power()		\
+				| sd_power_saving_flags()		\
+				,					\
+	.last_balance		= jiffies,				\
+	.balance_interval	= 1,					\
 }
 #endif
 #endif /* CONFIG_SCHED_MC */
 
 /* Common values for CPUs */
 #ifndef SD_CPU_INIT
-#define SD_CPU_INIT (struct sched_domain) {		\
-	.min_interval		= 1,			\
-	.max_interval		= 4,			\
-	.busy_factor		= 64,			\
-	.imbalance_pct		= 125,			\
-	.cache_nice_tries	= 1,			\
-	.busy_idx		= 2,			\
-	.idle_idx		= 1,			\
-	.newidle_idx		= 2,			\
-	.wake_idx		= 1,			\
-	.forkexec_idx		= 1,			\
-	.flags			= SD_LOAD_BALANCE	\
-				| SD_BALANCE_EXEC	\
-				| SD_BALANCE_FORK	\
-				| SD_WAKE_AFFINE	\
-				| SD_WAKE_BALANCE	\
-				| sd_balance_for_package_power()\
-				| sd_power_saving_flags(),\
-	.last_balance		= jiffies,		\
-	.balance_interval	= 1,			\
+#define SD_CPU_INIT (struct sched_domain) {				\
+	.min_interval		= 1,					\
+	.max_interval		= 4,					\
+	.busy_factor		= 64,					\
+	.imbalance_pct		= 125,					\
+	.cache_nice_tries	= 1,					\
+	.busy_idx		= 2,					\
+	.idle_idx		= 1,					\
+	.newidle_idx		= 2,					\
+	.wake_idx		= 1,					\
+	.forkexec_idx		= 1,					\
+									\
+	.flags			= 1*SD_LOAD_BALANCE			\
+				| 1*SD_BALANCE_NEWIDLE			\
+				| 1*SD_BALANCE_EXEC			\
+				| 1*SD_BALANCE_FORK			\
+				| 1*SD_WAKE_IDLE			\
+				| 0*SD_WAKE_AFFINE			\
+				| 1*SD_WAKE_BALANCE			\
+				| 0*SD_SHARE_CPUPOWER			\
+				| 0*SD_SHARE_PKG_RESOURCES		\
+				| 0*SD_SERIALIZE			\
+				| 0*SD_WAKE_IDLE_FAR			\
+				| sd_balance_for_package_power()	\
+				| sd_power_saving_flags()		\
+				,					\
+	.last_balance		= jiffies,				\
+	.balance_interval	= 1,					\
 }
 #endif
 
 /* sched_domains SD_ALLNODES_INIT for NUMA machines */
-#define SD_ALLNODES_INIT (struct sched_domain) {	\
-	.min_interval		= 64,			\
-	.max_interval		= 64*num_online_cpus(),	\
-	.busy_factor		= 128,			\
-	.imbalance_pct		= 133,			\
-	.cache_nice_tries	= 1,			\
-	.busy_idx		= 3,			\
-	.idle_idx		= 3,			\
-	.flags			= SD_LOAD_BALANCE	\
-				| SD_BALANCE_NEWIDLE	\
-				| SD_WAKE_AFFINE	\
-				| SD_SERIALIZE,		\
-	.last_balance		= jiffies,		\
-	.balance_interval	= 64,			\
+#define SD_ALLNODES_INIT (struct sched_domain) {			\
+	.min_interval		= 64,					\
+	.max_interval		= 64*num_online_cpus(),			\
+	.busy_factor		= 128,					\
+	.imbalance_pct		= 133,					\
+	.cache_nice_tries	= 1,					\
+	.busy_idx		= 3,					\
+	.idle_idx		= 3,					\
+	.flags			= 1*SD_LOAD_BALANCE			\
+				| 1*SD_BALANCE_NEWIDLE			\
+				| 0*SD_BALANCE_EXEC			\
+				| 0*SD_BALANCE_FORK			\
+				| 0*SD_WAKE_IDLE			\
+				| 1*SD_WAKE_AFFINE			\
+				| 0*SD_WAKE_BALANCE			\
+				| 0*SD_SHARE_CPUPOWER			\
+				| 0*SD_POWERSAVINGS_BALANCE		\
+				| 0*SD_SHARE_PKG_RESOURCES		\
+				| 1*SD_SERIALIZE			\
+				| 1*SD_WAKE_IDLE_FAR			\
+				| 0*SD_PREFER_SIBLING			\
+				,					\
+	.last_balance		= jiffies,				\
+	.balance_interval	= 64,					\
 }
 
 #ifdef CONFIG_NUMA
diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index 8949bb7eb08..a4c369ec328 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -340,6 +340,101 @@ TRACE_EVENT(sched_signal_send,
 		  __entry->sig, __entry->comm, __entry->pid)
 );
 
+/*
+ * XXX the below sched_stat tracepoints only apply to SCHED_OTHER/BATCH/IDLE
+ *     adding sched_stat support to SCHED_FIFO/RR would be welcome.
+ */
+
+/*
+ * Tracepoint for accounting wait time (time the task is runnable
+ * but not actually running due to scheduler contention).
+ */
+TRACE_EVENT(sched_stat_wait,
+
+	TP_PROTO(struct task_struct *tsk, u64 delay),
+
+	TP_ARGS(tsk, delay),
+
+	TP_STRUCT__entry(
+		__array( char,	comm,	TASK_COMM_LEN	)
+		__field( pid_t,	pid			)
+		__field( u64,	delay			)
+	),
+
+	TP_fast_assign(
+		memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
+		__entry->pid	= tsk->pid;
+		__entry->delay	= delay;
+	)
+	TP_perf_assign(
+		__perf_count(delay);
+	),
+
+	TP_printk("task: %s:%d wait: %Lu [ns]",
+			__entry->comm, __entry->pid,
+			(unsigned long long)__entry->delay)
+);
+
+/*
+ * Tracepoint for accounting sleep time (time the task is not runnable,
+ * including iowait, see below).
+ */
+TRACE_EVENT(sched_stat_sleep,
+
+	TP_PROTO(struct task_struct *tsk, u64 delay),
+
+	TP_ARGS(tsk, delay),
+
+	TP_STRUCT__entry(
+		__array( char,	comm,	TASK_COMM_LEN	)
+		__field( pid_t,	pid			)
+		__field( u64,	delay			)
+	),
+
+	TP_fast_assign(
+		memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
+		__entry->pid	= tsk->pid;
+		__entry->delay	= delay;
+	)
+	TP_perf_assign(
+		__perf_count(delay);
+	),
+
+	TP_printk("task: %s:%d sleep: %Lu [ns]",
+			__entry->comm, __entry->pid,
+			(unsigned long long)__entry->delay)
+);
+
+/*
+ * Tracepoint for accounting iowait time (time the task is not runnable
+ * due to waiting on IO to complete).
+ */
+TRACE_EVENT(sched_stat_iowait,
+
+	TP_PROTO(struct task_struct *tsk, u64 delay),
+
+	TP_ARGS(tsk, delay),
+
+	TP_STRUCT__entry(
+		__array( char,	comm,	TASK_COMM_LEN	)
+		__field( pid_t,	pid			)
+		__field( u64,	delay			)
+	),
+
+	TP_fast_assign(
+		memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
+		__entry->pid	= tsk->pid;
+		__entry->delay	= delay;
+	)
+	TP_perf_assign(
+		__perf_count(delay);
+	),
+
+	TP_printk("task: %s:%d iowait: %Lu [ns]",
+			__entry->comm, __entry->pid,
+			(unsigned long long)__entry->delay)
+);
+
 #endif /* _TRACE_SCHED_H */
 
 /* This part must be outside protection */