[RFC][PATCH 0/8] load-balancing and cpu_power -v2

[RFC][PATCH 0/8] load-balancing and cpu_power -v2

[Peter Zijlstra]

A more complete version, one that compiles and mostly works on the
simple tests to which it was subjected.

It still lacks integration with APERF/MPERF because that stuff was
hidding in some acpi driver instead of placed in arch code for general
consumption.. will fix.

Also, SD_SHARE_CPUPOWER seems redundant in the face of sd->level ==
SD_LV_SIBLING, should we remove the SD_flag or depricate the level?

Anyway, have at it, poke holes and report issues.

[RFC][PATCH 1/8] sched: restore __cpu_power to a straight sum of power

[Peter Zijlstra]

[-- Attachment #1: sched-lb-1.patch --]
[-- Type: text/plain, Size: 2319 bytes --]

cpu_power is supposed to be a representation of the process capacity
of the cpu, not a value to randomly tweak in order to affect
placement.

Remove the placement hacks.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
---
 include/linux/sched.h    |    1 +
 include/linux/topology.h |    1 +
 kernel/sched.c           |   34 ++++++++++++++++++----------------
 3 files changed, 20 insertions(+), 16 deletions(-)

Index: linux-2.6/kernel/sched.c
===================================================================
--- linux-2.6.orig/kernel/sched.c
+++ linux-2.6/kernel/sched.c
@@ -8468,15 +8468,13 @@ static void free_sched_groups(const stru
  * there are asymmetries in the topology. If there are asymmetries, group
  * having more cpu_power will pickup more load compared to the group having
  * less cpu_power.
- *
- * cpu_power will be a multiple of SCHED_LOAD_SCALE. This multiple represents
- * the maximum number of tasks a group can handle in the presence of other idle
- * or lightly loaded groups in the same sched domain.
  */
 static void init_sched_groups_power(int cpu, struct sched_domain *sd)
 {
 	struct sched_domain *child;
 	struct sched_group *group;
+	long power;
+	int weight;
 
 	WARN_ON(!sd || !sd->groups);
 
@@ -8487,22 +8485,20 @@ static void init_sched_groups_power(int 
 
 	sd->groups->__cpu_power = 0;
 
-	/*
-	 * For perf policy, if the groups in child domain share resources
-	 * (for example cores sharing some portions of the cache hierarchy
-	 * or SMT), then set this domain groups cpu_power such that each group
-	 * can handle only one task, when there are other idle groups in the
-	 * same sched domain.
-	 */
-	if (!child || (!(sd->flags & SD_POWERSAVINGS_BALANCE) &&
-		       (child->flags &
-			(SD_SHARE_CPUPOWER | SD_SHARE_PKG_RESOURCES)))) {
-		sg_inc_cpu_power(sd->groups, SCHED_LOAD_SCALE);
+	if (!child) {
+		power = SCHED_LOAD_SCALE;
+		weight = cpumask_weight(sched_domain_span(sd));
+		/*
+		 * SMT siblings share the power of a single core.
+		 */
+		if ((sd->flags & SD_SHARE_CPUPOWER) && weight > 1)
+			power /= weight;
+		sg_inc_cpu_power(sd->groups, power);
 		return;
 	}
 
 	/*
-	 * add cpu_power of each child group to this groups cpu_power
+	 * Add cpu_power of each child group to this groups cpu_power.
 	 */
 	group = child->groups;
 	do {

-- 

[RFC][PATCH 2/8] sched: SD_PREFER_SIBLING

[Peter Zijlstra]

[-- Attachment #1: sched-lb-2.patch --]
[-- Type: text/plain, Size: 3901 bytes --]

Do the placement thing using SD flags

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
---
 include/linux/sched.h |   29 +++++++++++++++--------------
 kernel/sched.c        |   14 +++++++++++++-
 2 files changed, 28 insertions(+), 15 deletions(-)

Index: linux-2.6/include/linux/sched.h
===================================================================
--- linux-2.6.orig/include/linux/sched.h
+++ linux-2.6/include/linux/sched.h
@@ -808,18 +808,19 @@ 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 */
@@ -839,7 +840,7 @@ static inline int sd_balance_for_mc_powe
 	if (sched_smt_power_savings)
 		return SD_POWERSAVINGS_BALANCE;
 
-	return 0;
+	return SD_PREFER_SIBLING;
 }
 
 static inline int sd_balance_for_package_power(void)
@@ -847,7 +848,7 @@ static inline int sd_balance_for_package
 	if (sched_mc_power_savings | sched_smt_power_savings)
 		return SD_POWERSAVINGS_BALANCE;
 
-	return 0;
+	return SD_PREFER_SIBLING;
 }
 
 /*
Index: linux-2.6/kernel/sched.c
===================================================================
--- linux-2.6.orig/kernel/sched.c
+++ linux-2.6/kernel/sched.c
@@ -3803,9 +3803,13 @@ static inline void update_sd_lb_stats(st
 			const struct cpumask *cpus, int *balance,
 			struct sd_lb_stats *sds)
 {
+	struct sched_domain *child = sd->child;
 	struct sched_group *group = sd->groups;
 	struct sg_lb_stats sgs;
-	int load_idx;
+	int load_idx, prefer_sibling = 0;
+
+	if (child && child->flags & SD_PREFER_SIBLING)
+		prefer_sibling = 1;
 
 	init_sd_power_savings_stats(sd, sds, idle);
 	load_idx = get_sd_load_idx(sd, idle);
@@ -3825,6 +3829,14 @@ static inline void update_sd_lb_stats(st
 		sds->total_load += sgs.group_load;
 		sds->total_pwr += group->__cpu_power;
 
+		/*
+		 * In case the child domain prefers tasks go to siblings
+		 * first, lower the group capacity to one so that we'll try
+		 * and move all the excess tasks away.
+		 */
+		if (prefer_sibling)
+			sgs.group_capacity = 1;
+
 		if (local_group) {
 			sds->this_load = sgs.avg_load;
 			sds->this = group;

-- 

[RFC][PATCH 3/8] sched: update the cpu_power sum during load-balance

[Peter Zijlstra]

[-- Attachment #1: sched-lb-3.patch --]
[-- Type: text/plain, Size: 2677 bytes --]

In order to prepare for a more dynamic cpu_power, update the group sum
while walking the sched domains during load-balance.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
---
 kernel/sched.c |   33 +++++++++++++++++++++++++++++----
 1 file changed, 29 insertions(+), 4 deletions(-)

Index: linux-2.6/kernel/sched.c
===================================================================
--- linux-2.6.orig/kernel/sched.c
+++ linux-2.6/kernel/sched.c
@@ -3699,6 +3699,28 @@ static inline int check_power_save_busie
 }
 #endif /* CONFIG_SCHED_MC || CONFIG_SCHED_SMT */
 
+static void update_sched_power(struct sched_domain *sd)
+{
+	struct sched_domain *child = sd->child;
+	struct sched_group *group, *sdg = sd->groups;
+	unsigned long power = sdg->__cpu_power;
+
+	if (!child) {
+		/* compute cpu power for this cpu */
+		return;
+	}
+
+	sdg->__cpu_power = 0;
+
+	group = child->groups;
+	do {
+		sdg->__cpu_power += group->__cpu_power;
+		group = group->next;
+	} while (group != child->groups);
+
+	if (power != sdg->__cpu_power)
+		sdg->reciprocal_cpu_power = reciprocal_value(sdg->__cpu_power);
+}
 
 /**
  * update_sg_lb_stats - Update sched_group's statistics for load balancing.
@@ -3712,7 +3734,8 @@ static inline int check_power_save_busie
  * @balance: Should we balance.
  * @sgs: variable to hold the statistics for this group.
  */
-static inline void update_sg_lb_stats(struct sched_group *group, int this_cpu,
+static inline void update_sg_lb_stats(struct sched_domain *sd,
+			struct sched_group *group, int this_cpu,
 			enum cpu_idle_type idle, int load_idx, int *sd_idle,
 			int local_group, const struct cpumask *cpus,
 			int *balance, struct sg_lb_stats *sgs)
@@ -3723,8 +3746,11 @@ static inline void update_sg_lb_stats(st
 	unsigned long sum_avg_load_per_task;
 	unsigned long avg_load_per_task;
 
-	if (local_group)
+	if (local_group) {
 		balance_cpu = group_first_cpu(group);
+		if (balance_cpu == this_cpu)
+			update_sched_power(sd);
+	}
 
 	/* Tally up the load of all CPUs in the group */
 	sum_avg_load_per_task = avg_load_per_task = 0;
@@ -3828,7 +3854,7 @@ static inline void update_sd_lb_stats(st
 		local_group = cpumask_test_cpu(this_cpu,
 					       sched_group_cpus(group));
 		memset(&sgs, 0, sizeof(sgs));
-		update_sg_lb_stats(group, this_cpu, idle, load_idx, sd_idle,
+		update_sg_lb_stats(sd, group, this_cpu, idle, load_idx, sd_idle,
 				local_group, cpus, balance, &sgs);
 
 		if (local_group && balance && !(*balance))
@@ -3863,7 +3889,6 @@ static inline void update_sd_lb_stats(st
 		update_sd_power_savings_stats(group, sds, local_group, &sgs);
 		group = group->next;
 	} while (group != sd->groups);
-
 }
 
 /**

-- 

[RFC][PATCH 4/8] sched: add smt_gain

[Peter Zijlstra]

[-- Attachment #1: sched-lb-1b.patch --]
[-- Type: text/plain, Size: 1916 bytes --]

The idea is that multi-threading a core yields more work capacity than
a single thread, provide a way to express a static gain for threads.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
---
 include/linux/sched.h    |    1 +
 include/linux/topology.h |    1 +
 kernel/sched.c           |    8 +++++++-
 3 files changed, 9 insertions(+), 1 deletion(-)

Index: linux-2.6/include/linux/sched.h
===================================================================
--- linux-2.6.orig/include/linux/sched.h
+++ linux-2.6/include/linux/sched.h
@@ -930,6 +930,7 @@ 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;
 
Index: linux-2.6/include/linux/topology.h
===================================================================
--- linux-2.6.orig/include/linux/topology.h
+++ linux-2.6/include/linux/topology.h
@@ -99,6 +99,7 @@ int arch_update_cpu_topology(void);
 				| SD_SHARE_CPUPOWER,	\
 	.last_balance		= jiffies,		\
 	.balance_interval	= 1,			\
+	.smt_gain		= 1178,	/* 15% */	\
 }
 #endif
 #endif /* CONFIG_SCHED_SMT */
Index: linux-2.6/kernel/sched.c
===================================================================
--- linux-2.6.orig/kernel/sched.c
+++ linux-2.6/kernel/sched.c
@@ -8490,9 +8490,15 @@ static void init_sched_groups_power(int 
 		weight = cpumask_weight(sched_domain_span(sd));
 		/*
 		 * SMT siblings share the power of a single core.
+		 * Usually multiple threads get a better yield out of
+		 * that one core than a single thread would have,
+		 * reflect that in sd->smt_gain.
 		 */
-		if ((sd->flags & SD_SHARE_CPUPOWER) && weight > 1)
+		if ((sd->flags & SD_SHARE_CPUPOWER) && weight > 1) {
+			power *= sd->smt_gain;
 			power /= weight;
+			power >>= SCHED_LOAD_SHIFT;
+		}
 		sg_inc_cpu_power(sd->groups, power);
 		return;
 	}

-- 

[RFC][PATCH 5/8] sched: dynamic cpu_power

[Peter Zijlstra]

[-- Attachment #1: sched-lb-4.patch --]
[-- Type: text/plain, Size: 1983 bytes --]

Recompute the cpu_power for each cpu during load-balance

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
---
 kernel/sched.c |   38 +++++++++++++++++++++++++++++++++++---
 1 file changed, 35 insertions(+), 3 deletions(-)

Index: linux-2.6/kernel/sched.c
===================================================================
--- linux-2.6.orig/kernel/sched.c
+++ linux-2.6/kernel/sched.c
@@ -3691,14 +3691,46 @@ static inline int check_power_save_busie
 }
 #endif /* CONFIG_SCHED_MC || CONFIG_SCHED_SMT */
 
-static void update_sched_power(struct sched_domain *sd)
+unsigned long __weak arch_smt_gain(struct sched_domain *sd, int cpu)
+{
+	unsigned long weight = cpumask_weight(sched_domain_span(sd));
+	unsigned long smt_gain = sd->smt_gain;
+
+	smt_gain /= weight;
+
+	return smt_gain;
+}
+
+static void update_cpu_power(struct sched_domain *sd, int cpu)
+{
+	unsigned long weight = cpumask_weight(sched_domain_span(sd));
+	unsigned long power = SCHED_LOAD_SCALE;
+	struct sched_group *sdg = sd->groups;
+	unsigned long old = sdg->__cpu_power;
+
+	/* here we could scale based on cpufreq */
+
+	if ((sd->flags & SD_SHARE_CPUPOWER) && weight > 1) {
+		power *= arch_smt_gain(sd, cpu);
+		power >>= SCHED_LOAD_SHIFT;
+	}
+
+	/* here we could scale based on RT time */
+
+	if (power != old) {
+		sdg->__cpu_power = power;
+		sdg->reciprocal_cpu_power = reciprocal_value(power);
+	}
+}
+
+static void update_group_power(struct sched_domain *sd, int cpu)
 {
 	struct sched_domain *child = sd->child;
 	struct sched_group *group, *sdg = sd->groups;
 	unsigned long power = sdg->__cpu_power;
 
 	if (!child) {
-		/* compute cpu power for this cpu */
+		update_cpu_power(sd, cpu);
 		return;
 	}
 
@@ -3743,7 +3775,7 @@ static inline void update_sg_lb_stats(st
 	if (local_group) {
 		balance_cpu = group_first_cpu(group);
 		if (balance_cpu == this_cpu)
-			update_sched_power(sd);
+			update_group_power(sd, this_cpu);
 	}
 
 	/* Tally up the load of all CPUs in the group */

-- 

[RFC][PATCH 6/8] sched: scale down cpu_power due to RT tasks

[Peter Zijlstra]

[-- Attachment #1: sched-lb-5.patch --]
[-- Type: text/plain, Size: 5311 bytes --]

Keep an average on the amount of time spend on RT tasks and use that
fraction to scale down the cpu_power for regular tasks.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
---
 include/linux/sched.h |    1 
 kernel/sched.c        |   64 +++++++++++++++++++++++++++++++++++++++++++++++---
 kernel/sched_rt.c     |    6 +---
 kernel/sysctl.c       |    8 ++++++
 4 files changed, 72 insertions(+), 7 deletions(-)

Index: linux-2.6/include/linux/sched.h
===================================================================
--- linux-2.6.orig/include/linux/sched.h
+++ linux-2.6/include/linux/sched.h
@@ -1863,6 +1863,7 @@ extern unsigned int sysctl_sched_child_r
 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,
Index: linux-2.6/kernel/sched.c
===================================================================
--- linux-2.6.orig/kernel/sched.c
+++ linux-2.6/kernel/sched.c
@@ -627,6 +627,9 @@ struct rq {
 
 	struct task_struct *migration_thread;
 	struct list_head migration_queue;
+
+	u64 rt_avg;
+	u64 age_stamp;
 #endif
 
 	/* calc_load related fields */
@@ -863,6 +866,14 @@ unsigned int sysctl_sched_shares_ratelim
 unsigned int sysctl_sched_shares_thresh = 4;
 
 /*
+ * period over which we average the RT time consumption, measured
+ * in ms.
+ *
+ * default: 1s
+ */
+const_debug unsigned int sysctl_sched_time_avg = MSEC_PER_SEC;
+
+/*
  * period over which we measure -rt task cpu usage in us.
  * default: 1s
  */
@@ -1280,12 +1291,37 @@ void wake_up_idle_cpu(int cpu)
 }
 #endif /* CONFIG_NO_HZ */
 
+static u64 sched_avg_period(void)
+{
+	return (u64)sysctl_sched_time_avg * NSEC_PER_MSEC / 2;
+}
+
+static void sched_avg_update(struct rq *rq)
+{
+	s64 period = sched_avg_period();
+
+	while ((s64)(rq->clock - rq->age_stamp) > period) {
+		rq->age_stamp += period;
+		rq->rt_avg /= 2;
+	}
+}
+
+static void sched_rt_avg_update(struct rq *rq, u64 rt_delta)
+{
+	rq->rt_avg += rt_delta;
+	sched_avg_update(rq);
+}
+
 #else /* !CONFIG_SMP */
 static void resched_task(struct task_struct *p)
 {
 	assert_spin_locked(&task_rq(p)->lock);
 	set_tsk_need_resched(p);
 }
+
+static void sched_rt_avg_update(struct rq *rq, u64 rt_delta)
+{
+}
 #endif /* CONFIG_SMP */
 
 #if BITS_PER_LONG == 32
@@ -3699,7 +3735,7 @@ static inline int check_power_save_busie
 }
 #endif /* CONFIG_SCHED_MC || CONFIG_SCHED_SMT */
 
-unsigned long __weak arch_smt_gain(struct sched_domain *sd, int cpu)
+unsigned long __weak arch_scale_smt_power(struct sched_domain *sd, int cpu)
 {
 	unsigned long weight = cpumask_weight(sched_domain_span(sd));
 	unsigned long smt_gain = sd->smt_gain;
@@ -3709,6 +3745,24 @@ unsigned long __weak arch_smt_gain(struc
 	return smt_gain;
 }
 
+unsigned long scale_rt_power(int cpu)
+{
+	struct rq *rq = cpu_rq(cpu);
+	u64 total, available;
+
+	sched_avg_update(rq);
+
+	total = sched_avg_period() + (rq->clock - rq->age_stamp);
+	available = total - rq->rt_avg;
+
+	if (unlikely((s64)total < SCHED_LOAD_SCALE))
+		total = SCHED_LOAD_SCALE;
+
+	total >>= SCHED_LOAD_SHIFT;
+
+	return div_u64(available, total);
+}
+
 static void update_cpu_power(struct sched_domain *sd, int cpu)
 {
 	unsigned long weight = cpumask_weight(sched_domain_span(sd));
@@ -3719,11 +3773,15 @@ static void update_cpu_power(struct sche
 	/* here we could scale based on cpufreq */
 
 	if ((sd->flags & SD_SHARE_CPUPOWER) && weight > 1) {
-		power *= arch_smt_gain(sd, cpu);
+		power *= arch_scale_smt_power(sd, cpu);
 		power >>= SCHED_LOAD_SHIFT;
 	}
 
-	/* here we could scale based on RT time */
+	power *= scale_rt_power(cpu);
+	power >>= SCHED_LOAD_SHIFT;
+
+	if (!power)
+		power = 1;
 
 	if (power != old) {
 		sdg->__cpu_power = power;
Index: linux-2.6/kernel/sched_rt.c
===================================================================
--- linux-2.6.orig/kernel/sched_rt.c
+++ linux-2.6/kernel/sched_rt.c
@@ -615,6 +615,8 @@ static void update_curr_rt(struct rq *rq
 	curr->se.exec_start = rq->clock;
 	cpuacct_charge(curr, delta_exec);
 
+	sched_rt_avg_update(rq, delta_exec);
+
 	if (!rt_bandwidth_enabled())
 		return;
 
@@ -887,8 +889,6 @@ static void enqueue_task_rt(struct rq *r
 
 	if (!task_current(rq, p) && p->rt.nr_cpus_allowed > 1)
 		enqueue_pushable_task(rq, p);
-
-	inc_cpu_load(rq, p->se.load.weight);
 }
 
 static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int sleep)
@@ -899,8 +899,6 @@ static void dequeue_task_rt(struct rq *r
 	dequeue_rt_entity(rt_se);
 
 	dequeue_pushable_task(rq, p);
-
-	dec_cpu_load(rq, p->se.load.weight);
 }
 
 /*
Index: linux-2.6/kernel/sysctl.c
===================================================================
--- linux-2.6.orig/kernel/sysctl.c
+++ linux-2.6/kernel/sysctl.c
@@ -332,6 +332,14 @@ static struct ctl_table kern_table[] = {
 	},
 	{
 		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "sched_time_avg",
+		.data		= &sysctl_sched_time_avg,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
+	{
+		.ctl_name	= CTL_UNNUMBERED,
 		.procname	= "timer_migration",
 		.data		= &sysctl_timer_migration,
 		.maxlen		= sizeof(unsigned int),

-- 

[RFC][PATCH 7/8] sched: try to deal with low capacity

[Peter Zijlstra]

[-- Attachment #1: sched-lb-6.patch --]
[-- Type: text/plain, Size: 2080 bytes --]

When the capacity drops low, we want to migrate load away. Allow the
load-balancer to remove all tasks when we hit rock bottom.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
---
 kernel/sched.c |   33 ++++++++++++++++++++++++++++-----
 1 file changed, 28 insertions(+), 5 deletions(-)

Index: linux-2.6/kernel/sched.c
===================================================================
--- linux-2.6.orig/kernel/sched.c
+++ linux-2.6/kernel/sched.c
@@ -3908,8 +3908,8 @@ static inline void update_sg_lb_stats(st
 	if ((max_cpu_load - min_cpu_load) > 2*avg_load_per_task)
 		sgs->group_imb = 1;
 
-	sgs->group_capacity = group->__cpu_power / SCHED_LOAD_SCALE;
-
+	sgs->group_capacity =
+		DIV_ROUND_CLOSEST(group->__cpu_power, SCHED_LOAD_SCALE);
 }
 
 /**
@@ -3959,7 +3959,7 @@ static inline void update_sd_lb_stats(st
 		 * and move all the excess tasks away.
 		 */
 		if (prefer_sibling)
-			sgs.group_capacity = 1;
+			sgs.group_capacity = min(sgs.group_capacity, 1UL);
 
 		if (local_group) {
 			sds->this_load = sgs.avg_load;
@@ -4191,6 +4191,26 @@ ret:
 	return NULL;
 }
 
+static struct sched_group *group_of(int cpu)
+{
+	struct sched_domain *sd = rcu_dereference(cpu_rq(cpu)->sd);
+
+	if (!sd)
+		return NULL;
+
+	return sd->groups;
+}
+
+static unsigned long power_of(int cpu)
+{
+	struct sched_group *group = group_of(cpu);
+
+	if (!group)
+		return SCHED_LOAD_SCALE;
+
+	return group->__cpu_power;
+}
+
 /*
  * find_busiest_queue - find the busiest runqueue among the cpus in group.
  */
@@ -4203,15 +4223,18 @@ find_busiest_queue(struct sched_group *g
 	int i;
 
 	for_each_cpu(i, sched_group_cpus(group)) {
+		unsigned long power = power_of(i);
+		unsigned long capacity = DIV_ROUND_CLOSEST(power, SCHED_LOAD_SCALE);
 		unsigned long wl;
 
 		if (!cpumask_test_cpu(i, cpus))
 			continue;
 
 		rq = cpu_rq(i);
-		wl = weighted_cpuload(i);
+		wl = weighted_cpuload(i) * SCHED_LOAD_SCALE;
+		wl /= power;
 
-		if (rq->nr_running == 1 && wl > imbalance)
+		if (capacity && rq->nr_running == 1 && wl > imbalance)
 			continue;
 
 		if (wl > max_load) {

-- 

[RFC][PATCH 8/8] sched: remove reciprocal for cpu_power

[Peter Zijlstra]

[-- Attachment #1: sched-lb-7.patch --]
[-- Type: text/plain, Size: 9229 bytes --]

Its a source of fail, also, now that cpu_power is dynamical, its a
waste of time.

before:
<idle>-0   [000]   132.877936: find_busiest_group: avg_load: 0 group_load: 8241 power: 1 

after:
bash-1689  [001]   137.862151: find_busiest_group: avg_load: 10636288 group_load: 10387 power: 1

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
---
 include/linux/sched.h |   10 +----
 kernel/sched.c        |  100 +++++++++++++++++---------------------------------
 2 files changed, 36 insertions(+), 74 deletions(-)

Index: linux-2.6/kernel/sched.c
===================================================================
--- linux-2.6.orig/kernel/sched.c
+++ linux-2.6/kernel/sched.c
@@ -120,30 +120,8 @@
  */
 #define RUNTIME_INF	((u64)~0ULL)
 
-#ifdef CONFIG_SMP
-
 static void double_rq_lock(struct rq *rq1, struct rq *rq2);
 
-/*
- * Divide a load by a sched group cpu_power : (load / sg->__cpu_power)
- * Since cpu_power is a 'constant', we can use a reciprocal divide.
- */
-static inline u32 sg_div_cpu_power(const struct sched_group *sg, u32 load)
-{
-	return reciprocal_divide(load, sg->reciprocal_cpu_power);
-}
-
-/*
- * Each time a sched group cpu_power is changed,
- * we must compute its reciprocal value
- */
-static inline void sg_inc_cpu_power(struct sched_group *sg, u32 val)
-{
-	sg->__cpu_power += val;
-	sg->reciprocal_cpu_power = reciprocal_value(sg->__cpu_power);
-}
-#endif
-
 static inline int rt_policy(int policy)
 {
 	if (unlikely(policy == SCHED_FIFO || policy == SCHED_RR))
@@ -2335,8 +2313,7 @@ find_idlest_group(struct sched_domain *s
 		}
 
 		/* Adjust by relative CPU power of the group */
-		avg_load = sg_div_cpu_power(group,
-				avg_load * SCHED_LOAD_SCALE);
+		avg_load = (avg_load * SCHED_LOAD_SCALE) / group->cpu_power;
 
 		if (local_group) {
 			this_load = avg_load;
@@ -3768,7 +3745,6 @@ static void update_cpu_power(struct sche
 	unsigned long weight = cpumask_weight(sched_domain_span(sd));
 	unsigned long power = SCHED_LOAD_SCALE;
 	struct sched_group *sdg = sd->groups;
-	unsigned long old = sdg->__cpu_power;
 
 	/* here we could scale based on cpufreq */
 
@@ -3783,33 +3759,26 @@ static void update_cpu_power(struct sche
 	if (!power)
 		power = 1;
 
-	if (power != old) {
-		sdg->__cpu_power = power;
-		sdg->reciprocal_cpu_power = reciprocal_value(power);
-	}
+	sdg->cpu_power = power;
 }
 
 static void update_group_power(struct sched_domain *sd, int cpu)
 {
 	struct sched_domain *child = sd->child;
 	struct sched_group *group, *sdg = sd->groups;
-	unsigned long power = sdg->__cpu_power;
 
 	if (!child) {
 		update_cpu_power(sd, cpu);
 		return;
 	}
 
-	sdg->__cpu_power = 0;
+	sdg->cpu_power = 0;
 
 	group = child->groups;
 	do {
-		sdg->__cpu_power += group->__cpu_power;
+		sdg->cpu_power += group->cpu_power;
 		group = group->next;
 	} while (group != child->groups);
-
-	if (power != sdg->__cpu_power)
-		sdg->reciprocal_cpu_power = reciprocal_value(sdg->__cpu_power);
 }
 
 /**
@@ -3889,8 +3858,7 @@ static inline void update_sg_lb_stats(st
 	}
 
 	/* Adjust by relative CPU power of the group */
-	sgs->avg_load = sg_div_cpu_power(group,
-			sgs->group_load * SCHED_LOAD_SCALE);
+	sgs->avg_load = (sgs->group_load * SCHED_LOAD_SCALE) / group->cpu_power;
 
 
 	/*
@@ -3902,14 +3870,14 @@ static inline void update_sg_lb_stats(st
 	 *      normalized nr_running number somewhere that negates
 	 *      the hierarchy?
 	 */
-	avg_load_per_task = sg_div_cpu_power(group,
-			sum_avg_load_per_task * SCHED_LOAD_SCALE);
+	avg_load_per_task = (sum_avg_load_per_task * SCHED_LOAD_SCALE) /
+		group->cpu_power;
 
 	if ((max_cpu_load - min_cpu_load) > 2*avg_load_per_task)
 		sgs->group_imb = 1;
 
 	sgs->group_capacity =
-		DIV_ROUND_CLOSEST(group->__cpu_power, SCHED_LOAD_SCALE);
+		DIV_ROUND_CLOSEST(group->cpu_power, SCHED_LOAD_SCALE);
 }
 
 /**
@@ -3951,7 +3919,7 @@ static inline void update_sd_lb_stats(st
 			return;
 
 		sds->total_load += sgs.group_load;
-		sds->total_pwr += group->__cpu_power;
+		sds->total_pwr += group->cpu_power;
 
 		/*
 		 * In case the child domain prefers tasks go to siblings
@@ -4016,28 +3984,28 @@ static inline void fix_small_imbalance(s
 	 * moving them.
 	 */
 
-	pwr_now += sds->busiest->__cpu_power *
+	pwr_now += sds->busiest->cpu_power *
 			min(sds->busiest_load_per_task, sds->max_load);
-	pwr_now += sds->this->__cpu_power *
+	pwr_now += sds->this->cpu_power *
 			min(sds->this_load_per_task, sds->this_load);
 	pwr_now /= SCHED_LOAD_SCALE;
 
 	/* Amount of load we'd subtract */
-	tmp = sg_div_cpu_power(sds->busiest,
-			sds->busiest_load_per_task * SCHED_LOAD_SCALE);
+	tmp = (sds->busiest_load_per_task * SCHED_LOAD_SCALE) /
+		sds->busiest->cpu_power;
 	if (sds->max_load > tmp)
-		pwr_move += sds->busiest->__cpu_power *
+		pwr_move += sds->busiest->cpu_power *
 			min(sds->busiest_load_per_task, sds->max_load - tmp);
 
 	/* Amount of load we'd add */
-	if (sds->max_load * sds->busiest->__cpu_power <
+	if (sds->max_load * sds->busiest->cpu_power <
 		sds->busiest_load_per_task * SCHED_LOAD_SCALE)
-		tmp = sg_div_cpu_power(sds->this,
-			sds->max_load * sds->busiest->__cpu_power);
+		tmp = (sds->max_load * sds->busiest->cpu_power) /
+			sds->this->cpu_power;
 	else
-		tmp = sg_div_cpu_power(sds->this,
-			sds->busiest_load_per_task * SCHED_LOAD_SCALE);
-	pwr_move += sds->this->__cpu_power *
+		tmp = (sds->busiest_load_per_task * SCHED_LOAD_SCALE) /
+			sds->this->cpu_power;
+	pwr_move += sds->this->cpu_power *
 			min(sds->this_load_per_task, sds->this_load + tmp);
 	pwr_move /= SCHED_LOAD_SCALE;
 
@@ -4072,8 +4040,8 @@ static inline void calculate_imbalance(s
 			sds->max_load - sds->busiest_load_per_task);
 
 	/* How much load to actually move to equalise the imbalance */
-	*imbalance = min(max_pull * sds->busiest->__cpu_power,
-		(sds->avg_load - sds->this_load) * sds->this->__cpu_power)
+	*imbalance = min(max_pull * sds->busiest->cpu_power,
+		(sds->avg_load - sds->this_load) * sds->this->cpu_power)
 			/ SCHED_LOAD_SCALE;
 
 	/*
@@ -4208,7 +4176,7 @@ static unsigned long power_of(int cpu)
 	if (!group)
 		return SCHED_LOAD_SCALE;
 
-	return group->__cpu_power;
+	return group->cpu_power;
 }
 
 /*
@@ -7934,7 +7902,7 @@ static int sched_domain_debug_one(struct
 			break;
 		}
 
-		if (!group->__cpu_power) {
+		if (!group->cpu_power) {
 			printk(KERN_CONT "\n");
 			printk(KERN_ERR "ERROR: domain->cpu_power not "
 					"set\n");
@@ -7958,9 +7926,9 @@ static int sched_domain_debug_one(struct
 		cpulist_scnprintf(str, sizeof(str), sched_group_cpus(group));
 
 		printk(KERN_CONT " %s", str);
-		if (group->__cpu_power != SCHED_LOAD_SCALE) {
-			printk(KERN_CONT " (__cpu_power = %d)",
-				group->__cpu_power);
+		if (group->cpu_power != SCHED_LOAD_SCALE) {
+			printk(KERN_CONT " (cpu_power = %d)",
+				group->cpu_power);
 		}
 
 		group = group->next;
@@ -8245,7 +8213,7 @@ init_sched_build_groups(const struct cpu
 			continue;
 
 		cpumask_clear(sched_group_cpus(sg));
-		sg->__cpu_power = 0;
+		sg->cpu_power = 0;
 
 		for_each_cpu(j, span) {
 			if (group_fn(j, cpu_map, NULL, tmpmask) != group)
@@ -8503,7 +8471,7 @@ static void init_numa_sched_groups_power
 				continue;
 			}
 
-			sg_inc_cpu_power(sg, sd->groups->__cpu_power);
+			sg->cpu_power += sd->groups->cpu_power;
 		}
 		sg = sg->next;
 	} while (sg != group_head);
@@ -8540,7 +8508,7 @@ static int build_numa_sched_groups(struc
 		sd->groups = sg;
 	}
 
-	sg->__cpu_power = 0;
+	sg->cpu_power = 0;
 	cpumask_copy(sched_group_cpus(sg), d->nodemask);
 	sg->next = sg;
 	cpumask_or(d->covered, d->covered, d->nodemask);
@@ -8563,7 +8531,7 @@ static int build_numa_sched_groups(struc
 			       "Can not alloc domain group for node %d\n", j);
 			return -ENOMEM;
 		}
-		sg->__cpu_power = 0;
+		sg->cpu_power = 0;
 		cpumask_copy(sched_group_cpus(sg), d->tmpmask);
 		sg->next = prev->next;
 		cpumask_or(d->covered, d->covered, d->tmpmask);
@@ -8641,7 +8609,7 @@ static void init_sched_groups_power(int 
 
 	child = sd->child;
 
-	sd->groups->__cpu_power = 0;
+	sd->groups->cpu_power = 0;
 
 	if (!child) {
 		power = SCHED_LOAD_SCALE;
@@ -8657,7 +8625,7 @@ static void init_sched_groups_power(int 
 			power /= weight;
 			power >>= SCHED_LOAD_SHIFT;
 		}
-		sg_inc_cpu_power(sd->groups, power);
+		sd->groups->cpu_power += power;
 		return;
 	}
 
@@ -8666,7 +8634,7 @@ static void init_sched_groups_power(int 
 	 */
 	group = child->groups;
 	do {
-		sg_inc_cpu_power(sd->groups, group->__cpu_power);
+		sd->groups->cpu_power += group->cpu_power;
 		group = group->next;
 	} while (group != child->groups);
 }
Index: linux-2.6/include/linux/sched.h
===================================================================
--- linux-2.6.orig/include/linux/sched.h
+++ linux-2.6/include/linux/sched.h
@@ -870,15 +870,9 @@ 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
+	 * single CPU.
 	 */
-	unsigned int __cpu_power;
-	/*
-	 * reciprocal value of cpu_power to avoid expensive divides
-	 * (see include/linux/reciprocal_div.h)
-	 */
-	u32 reciprocal_cpu_power;
+	unsigned int cpu_power;
 
 	/*
 	 * The CPUs this group covers.

-- 

Re: [RFC][PATCH 0/8] load-balancing and cpu_power -v2

[Gautham R Shenoy]

On Tue, Sep 01, 2009 at 10:34:31AM +0200, Peter Zijlstra wrote:
> A more complete version, one that compiles and mostly works on the
> simple tests to which it was subjected.

Very nice series.

Will queue it up for testing to see if anything
obvious breaks.

> 
> It still lacks integration with APERF/MPERF because that stuff was
> hidding in some acpi driver instead of placed in arch code for general
> consumption.. will fix.
> 
> Also, SD_SHARE_CPUPOWER seems redundant in the face of sd->level ==
> SD_LV_SIBLING, should we remove the SD_flag or depricate the level?

IIRC, the only place where we used SD_SHARE_CPUPOWER was while assigning
the cpu_power. With the arch_smt_gain() coming into picture, I feel we
can remove the SD_flag.

Not sure what you meant by deprecating the level.
> 
> Anyway, have at it, poke holes and report issues.


-- 
Thanks and Regards
gautham

Re: [RFC][PATCH 3/8] sched: update the cpu_power sum during load-balance

[Gautham R Shenoy]

On Tue, Sep 01, 2009 at 10:34:34AM +0200, Peter Zijlstra wrote:
> In order to prepare for a more dynamic cpu_power, update the group sum
> while walking the sched domains during load-balance.
> 
> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
> ---
>  kernel/sched.c |   33 +++++++++++++++++++++++++++++----
>  1 file changed, 29 insertions(+), 4 deletions(-)
> 
> Index: linux-2.6/kernel/sched.c
> ===================================================================
> --- linux-2.6.orig/kernel/sched.c
> +++ linux-2.6/kernel/sched.c
> @@ -3699,6 +3699,28 @@ static inline int check_power_save_busie
>  }
>  #endif /* CONFIG_SCHED_MC || CONFIG_SCHED_SMT */
> 
> +static void update_sched_power(struct sched_domain *sd)
> +{
> +	struct sched_domain *child = sd->child;
> +	struct sched_group *group, *sdg = sd->groups;
> +	unsigned long power = sdg->__cpu_power;
> +
> +	if (!child) {
> +		/* compute cpu power for this cpu */
> +		return;
> +	}
> +
> +	sdg->__cpu_power = 0;
> +
> +	group = child->groups;
> +	do {
> +		sdg->__cpu_power += group->__cpu_power;
> +		group = group->next;
> +	} while (group != child->groups);
> +
> +	if (power != sdg->__cpu_power)
> +		sdg->reciprocal_cpu_power = reciprocal_value(sdg->__cpu_power);
> +}
> 
>  /**
>   * update_sg_lb_stats - Update sched_group's statistics for load balancing.
> @@ -3712,7 +3734,8 @@ static inline int check_power_save_busie
>   * @balance: Should we balance.
>   * @sgs: variable to hold the statistics for this group.
>   */
> -static inline void update_sg_lb_stats(struct sched_group *group, int this_cpu,
> +static inline void update_sg_lb_stats(struct sched_domain *sd,
> +			struct sched_group *group, int this_cpu,
>  			enum cpu_idle_type idle, int load_idx, int *sd_idle,
>  			int local_group, const struct cpumask *cpus,
>  			int *balance, struct sg_lb_stats *sgs)
> @@ -3723,8 +3746,11 @@ static inline void update_sg_lb_stats(st
>  	unsigned long sum_avg_load_per_task;
>  	unsigned long avg_load_per_task;
> 
> -	if (local_group)
> +	if (local_group) {
>  		balance_cpu = group_first_cpu(group);
> +		if (balance_cpu == this_cpu)
> +			update_sched_power(sd);
> +	}

I guess the intention of this check is to ensure that the cpu_power for
the group of sd is updated only by a specific member of the group and
that would ideally be the first member of the group.

Thus, this check has more to do with this_cpu being the
group_first_cpu() than this_cpu being the balance_cpu. Correct ?

> 
>  	/* Tally up the load of all CPUs in the group */
>  	sum_avg_load_per_task = avg_load_per_task = 0;
> @@ -3828,7 +3854,7 @@ static inline void update_sd_lb_stats(st
>  		local_group = cpumask_test_cpu(this_cpu,
>  					       sched_group_cpus(group));
>  		memset(&sgs, 0, sizeof(sgs));
> -		update_sg_lb_stats(group, this_cpu, idle, load_idx, sd_idle,
> +		update_sg_lb_stats(sd, group, this_cpu, idle, load_idx, sd_idle,
>  				local_group, cpus, balance, &sgs);
> 
>  		if (local_group && balance && !(*balance))
> @@ -3863,7 +3889,6 @@ static inline void update_sd_lb_stats(st
>  		update_sd_power_savings_stats(group, sds, local_group, &sgs);
>  		group = group->next;
>  	} while (group != sd->groups);
> -
>  }
> 
>  /**
> 
> -- 

-- 
Thanks and Regards
gautham

Re: [RFC][PATCH 4/8] sched: add smt_gain

[Gautham R Shenoy]

On Tue, Sep 01, 2009 at 10:34:35AM +0200, Peter Zijlstra wrote:
> The idea is that multi-threading a core yields more work capacity than
> a single thread, provide a way to express a static gain for threads.
> 
> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
> ---
>  include/linux/sched.h    |    1 +
>  include/linux/topology.h |    1 +
>  kernel/sched.c           |    8 +++++++-
>  3 files changed, 9 insertions(+), 1 deletion(-)
> 
> Index: linux-2.6/include/linux/sched.h
> ===================================================================
> --- linux-2.6.orig/include/linux/sched.h
> +++ linux-2.6/include/linux/sched.h
> @@ -930,6 +930,7 @@ 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;
> 
> Index: linux-2.6/include/linux/topology.h
> ===================================================================
> --- linux-2.6.orig/include/linux/topology.h
> +++ linux-2.6/include/linux/topology.h
> @@ -99,6 +99,7 @@ int arch_update_cpu_topology(void);
>  				| SD_SHARE_CPUPOWER,	\
>  	.last_balance		= jiffies,		\
>  	.balance_interval	= 1,			\
> +	.smt_gain		= 1178,	/* 15% */	\

/* 15% of SCHED_LOAD_SCALE */ , I suppose.

>  }
>  #endif
>  #endif /* CONFIG_SCHED_SMT */
> Index: linux-2.6/kernel/sched.c
> ===================================================================
> --- linux-2.6.orig/kernel/sched.c
> +++ linux-2.6/kernel/sched.c
> @@ -8490,9 +8490,15 @@ static void init_sched_groups_power(int 
>  		weight = cpumask_weight(sched_domain_span(sd));
>  		/*
>  		 * SMT siblings share the power of a single core.
> +		 * Usually multiple threads get a better yield out of
> +		 * that one core than a single thread would have,
> +		 * reflect that in sd->smt_gain.
>  		 */
> -		if ((sd->flags & SD_SHARE_CPUPOWER) && weight > 1)
> +		if ((sd->flags & SD_SHARE_CPUPOWER) && weight > 1) {
> +			power *= sd->smt_gain;
>  			power /= weight;
> +			power >>= SCHED_LOAD_SHIFT;
> +		}
>  		sg_inc_cpu_power(sd->groups, power);
>  		return;
>  	}
> 
> -- 

-- 
Thanks and Regards
gautham

Re: [RFC][PATCH 5/8] sched: dynamic cpu_power

[Gautham R Shenoy]

On Tue, Sep 01, 2009 at 10:34:36AM +0200, Peter Zijlstra wrote:
> Recompute the cpu_power for each cpu during load-balance

This patch rocks! Atleast in theory, it does :-)

> 
> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
> ---
>  kernel/sched.c |   38 +++++++++++++++++++++++++++++++++++---
>  1 file changed, 35 insertions(+), 3 deletions(-)
> 
> Index: linux-2.6/kernel/sched.c
> ===================================================================
> --- linux-2.6.orig/kernel/sched.c
> +++ linux-2.6/kernel/sched.c
> @@ -3691,14 +3691,46 @@ static inline int check_power_save_busie
>  }
>  #endif /* CONFIG_SCHED_MC || CONFIG_SCHED_SMT */
> 
> -static void update_sched_power(struct sched_domain *sd)
> +unsigned long __weak arch_smt_gain(struct sched_domain *sd, int cpu)
> +{
> +	unsigned long weight = cpumask_weight(sched_domain_span(sd));
> +	unsigned long smt_gain = sd->smt_gain;
> +
> +	smt_gain /= weight;
> +
> +	return smt_gain;
> +}
> +
> +static void update_cpu_power(struct sched_domain *sd, int cpu)
> +{
> +	unsigned long weight = cpumask_weight(sched_domain_span(sd));
> +	unsigned long power = SCHED_LOAD_SCALE;
> +	struct sched_group *sdg = sd->groups;
> +	unsigned long old = sdg->__cpu_power;
> +
> +	/* here we could scale based on cpufreq */
> +
> +	if ((sd->flags & SD_SHARE_CPUPOWER) && weight > 1) {
> +		power *= arch_smt_gain(sd, cpu);
> +		power >>= SCHED_LOAD_SHIFT;
> +	}
> +
> +	/* here we could scale based on RT time */
> +
> +	if (power != old) {
> +		sdg->__cpu_power = power;
> +		sdg->reciprocal_cpu_power = reciprocal_value(power);
> +	}
> +}
> +
> +static void update_group_power(struct sched_domain *sd, int cpu)
>  {
>  	struct sched_domain *child = sd->child;
>  	struct sched_group *group, *sdg = sd->groups;
>  	unsigned long power = sdg->__cpu_power;
> 
>  	if (!child) {
> -		/* compute cpu power for this cpu */
> +		update_cpu_power(sd, cpu);
>  		return;
>  	}
> 
> @@ -3743,7 +3775,7 @@ static inline void update_sg_lb_stats(st
>  	if (local_group) {
>  		balance_cpu = group_first_cpu(group);
>  		if (balance_cpu == this_cpu)
> -			update_sched_power(sd);
> +			update_group_power(sd, this_cpu);
>  	}
> 
>  	/* Tally up the load of all CPUs in the group */
> 
> -- 

-- 
Thanks and Regards
gautham

Re: [RFC][PATCH 3/8] sched: update the cpu_power sum during load-balance

[Peter Zijlstra]

On Wed, 2009-09-02 at 16:47 +0530, Gautham R Shenoy wrote:
> > +     if (local_group) {
> >               balance_cpu = group_first_cpu(group);
> > +             if (balance_cpu == this_cpu)
> > +                     update_sched_power(sd);
> > +     }
> 
> I guess the intention of this check is to ensure that the cpu_power for
> the group of sd is updated only by a specific member of the group and
> that would ideally be the first member of the group.
> 
> Thus, this check has more to do with this_cpu being the
> group_first_cpu() than this_cpu being the balance_cpu. Correct ?

Right, so the load-balancer walks the sd tree in the fashion that only
the first cpu of the domain goes up a level. So I made that cpu also
aggregate the new cpu-power.

Re: [RFC][PATCH 4/8] sched: add smt_gain

[Peter Zijlstra]

On Wed, 2009-09-02 at 16:52 +0530, Gautham R Shenoy wrote:
> > +     .smt_gain               = 1178, /* 15% */       \
> 
> /* 15% of SCHED_LOAD_SCALE */ , I suppose.

Yeah, but that didn't fit on the line.

Also, its +15%, or 115% when pedantic ;-)

Re: [RFC][PATCH 7/8] sched: try to deal with low capacity

[Gautham R Shenoy]

On Tue, Sep 01, 2009 at 10:34:38AM +0200, Peter Zijlstra wrote:
> When the capacity drops low, we want to migrate load away. Allow the
> load-balancer to remove all tasks when we hit rock bottom.
> 
> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
> ---
>  kernel/sched.c |   33 ++++++++++++++++++++++++++++-----
>  1 file changed, 28 insertions(+), 5 deletions(-)
> 
> Index: linux-2.6/kernel/sched.c
> ===================================================================
> --- linux-2.6.orig/kernel/sched.c
> +++ linux-2.6/kernel/sched.c
> @@ -3908,8 +3908,8 @@ static inline void update_sg_lb_stats(st
>  	if ((max_cpu_load - min_cpu_load) > 2*avg_load_per_task)
>  		sgs->group_imb = 1;
> 
> -	sgs->group_capacity = group->__cpu_power / SCHED_LOAD_SCALE;
> -
> +	sgs->group_capacity =
> +		DIV_ROUND_CLOSEST(group->__cpu_power, SCHED_LOAD_SCALE);
>  }
> 
>  /**
> @@ -3959,7 +3959,7 @@ static inline void update_sd_lb_stats(st
>  		 * and move all the excess tasks away.
>  		 */
>  		if (prefer_sibling)
> -			sgs.group_capacity = 1;
> +			sgs.group_capacity = min(sgs.group_capacity, 1UL);

Ok, this means that sgs.group_capacity can now be 0, if for some reason
group->__cpu_power happens to be less than SCHED_LOAD_SCALE/2.

In that case, we need the following hunk to make it work for
update_sd_power_savings_stats(). That's because both sum_nr_running and
group_capacity are unsigned longs.

---->
diff --git a/kernel/sched.c b/kernel/sched.c
index 12fdbb8..9952292 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -3580,7 +3580,7 @@ static inline void update_sd_power_savings_stats(struct sched_group *group,
 	 * capacity but still has some space to pick up some load
 	 * from other group and save more power
 	 */
-	if (sgs->sum_nr_running > sgs->group_capacity - 1)
+	if (sgs->sum_nr_running + 1 > sgs->group_capacity)
 		return;
 
 	if (sgs->sum_nr_running > sds->leader_nr_running ||

---->


> 
>  		if (local_group) {
>  			sds->this_load = sgs.avg_load;
> @@ -4191,6 +4191,26 @@ ret:
>  	return NULL;
>  }
> 

-- 
Thanks and Regards
gautham

Re: [RFC][PATCH 0/8] load-balancing and cpu_power -v2

[Andreas Herrmann]

On Tue, Sep 01, 2009 at 10:34:31AM +0200, Peter Zijlstra wrote:
> A more complete version, one that compiles and mostly works on the
> simple tests to which it was subjected.
> 
> It still lacks integration with APERF/MPERF because that stuff was
> hidding in some acpi driver instead of placed in arch code for general
> consumption.. will fix.
> 
> Also, SD_SHARE_CPUPOWER seems redundant in the face of sd->level ==
> SD_LV_SIBLING, should we remove the SD_flag or depricate the level?
> 
> Anyway, have at it, poke holes and report issues.

Tested it (to a certain extend).
Found no performance degradation (on 1P, 2P, 4P systems). (One could
think performance might slightly degrade due to more frequent
__cpu_power updates).

Issue that I see is that switching between scheduling policies has no
effect on already running tasks:

- tasks that are already distributed among sockets are _not_
  concentrated on one socket when switching from performance to
  power_savings scheduling

- tasks utilizing a socket are _not_ distributed among sockets when
  switching from power_savings to performance policy

This applies to modification of sched_mc_power_savings. And I think
one of above scenarios is already broken in tip/master w/o your
patches.

Otherwise especially wrt to integration of APERF/MPERF this seems to
be a good approach.


Regards,
Andreas

-- 
Operating | Advanced Micro Devices GmbH
  System  | Karl-Hammerschmidt-Str. 34, 85609 Dornach b. München, Germany
 Research | Geschäftsführer: Andrew Bowd, Thomas M. McCoy, Giuliano Meroni
  Center  | Sitz: Dornach, Gemeinde Aschheim, Landkreis München
  (OSRC)  | Registergericht München, HRB Nr. 43632

Re: [RFC][PATCH 8/8] sched: remove reciprocal for cpu_power

[Andreas Herrmann]

On Tue, Sep 01, 2009 at 10:34:39AM +0200, Peter Zijlstra wrote:
> Its a source of fail, also, now that cpu_power is dynamical, its a
> waste of time.
> 
> before:
> <idle>-0   [000]   132.877936: find_busiest_group: avg_load: 0 group_load: 8241 power: 1 
> 
> after:
> bash-1689  [001]   137.862151: find_busiest_group: avg_load: 10636288 group_load: 10387 power: 1
> 
> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
> ---
>  include/linux/sched.h |   10 +----
>  kernel/sched.c        |  100 +++++++++++++++++---------------------------------
>  2 files changed, 36 insertions(+), 74 deletions(-)
> 
> Index: linux-2.6/kernel/sched.c
> ===================================================================
> --- linux-2.6.orig/kernel/sched.c
> +++ linux-2.6/kernel/sched.c
> @@ -120,30 +120,8 @@
>   */
>  #define RUNTIME_INF	((u64)~0ULL)
>  
> -#ifdef CONFIG_SMP
> -
>  static void double_rq_lock(struct rq *rq1, struct rq *rq2);
>  
> -/*
> - * Divide a load by a sched group cpu_power : (load / sg->__cpu_power)
> - * Since cpu_power is a 'constant', we can use a reciprocal divide.
> - */
> -static inline u32 sg_div_cpu_power(const struct sched_group *sg, u32 load)
> -{
> -	return reciprocal_divide(load, sg->reciprocal_cpu_power);
> -}
> -
> -/*
> - * Each time a sched group cpu_power is changed,
> - * we must compute its reciprocal value
> - */
> -static inline void sg_inc_cpu_power(struct sched_group *sg, u32 val)
> -{
> -	sg->__cpu_power += val;
> -	sg->reciprocal_cpu_power = reciprocal_value(sg->__cpu_power);
> -}
> -#endif
> -
>  static inline int rt_policy(int policy)
>  {
>  	if (unlikely(policy == SCHED_FIFO || policy == SCHED_RR))
> @@ -2335,8 +2313,7 @@ find_idlest_group(struct sched_domain *s
>  		}
>  
>  		/* Adjust by relative CPU power of the group */
> -		avg_load = sg_div_cpu_power(group,
> -				avg_load * SCHED_LOAD_SCALE);
> +		avg_load = (avg_load * SCHED_LOAD_SCALE) / group->cpu_power;
>  
>  		if (local_group) {
>  			this_load = avg_load;
> @@ -3768,7 +3745,6 @@ static void update_cpu_power(struct sche
>  	unsigned long weight = cpumask_weight(sched_domain_span(sd));
>  	unsigned long power = SCHED_LOAD_SCALE;
>  	struct sched_group *sdg = sd->groups;
> -	unsigned long old = sdg->__cpu_power;
>  
>  	/* here we could scale based on cpufreq */
>  
> @@ -3783,33 +3759,26 @@ static void update_cpu_power(struct sche
>  	if (!power)
>  		power = 1;
>  
> -	if (power != old) {
> -		sdg->__cpu_power = power;
> -		sdg->reciprocal_cpu_power = reciprocal_value(power);
> -	}
> +	sdg->cpu_power = power;
>  }
>  
>  static void update_group_power(struct sched_domain *sd, int cpu)
>  {
>  	struct sched_domain *child = sd->child;
>  	struct sched_group *group, *sdg = sd->groups;
> -	unsigned long power = sdg->__cpu_power;
>  
>  	if (!child) {
>  		update_cpu_power(sd, cpu);
>  		return;
>  	}
>  
> -	sdg->__cpu_power = 0;
> +	sdg->cpu_power = 0;
>  
>  	group = child->groups;
>  	do {
> -		sdg->__cpu_power += group->__cpu_power;
> +		sdg->cpu_power += group->cpu_power;
>  		group = group->next;
>  	} while (group != child->groups);
> -
> -	if (power != sdg->__cpu_power)
> -		sdg->reciprocal_cpu_power = reciprocal_value(sdg->__cpu_power);
>  }
>  
>  /**
> @@ -3889,8 +3858,7 @@ static inline void update_sg_lb_stats(st
>  	}
>  
>  	/* Adjust by relative CPU power of the group */
> -	sgs->avg_load = sg_div_cpu_power(group,
> -			sgs->group_load * SCHED_LOAD_SCALE);
> +	sgs->avg_load = (sgs->group_load * SCHED_LOAD_SCALE) / group->cpu_power;
>  
>  
>  	/*
> @@ -3902,14 +3870,14 @@ static inline void update_sg_lb_stats(st
>  	 *      normalized nr_running number somewhere that negates
>  	 *      the hierarchy?
>  	 */
> -	avg_load_per_task = sg_div_cpu_power(group,
> -			sum_avg_load_per_task * SCHED_LOAD_SCALE);
> +	avg_load_per_task = (sum_avg_load_per_task * SCHED_LOAD_SCALE) /
> +		group->cpu_power;
>  
>  	if ((max_cpu_load - min_cpu_load) > 2*avg_load_per_task)
>  		sgs->group_imb = 1;
>  
>  	sgs->group_capacity =
> -		DIV_ROUND_CLOSEST(group->__cpu_power, SCHED_LOAD_SCALE);
> +		DIV_ROUND_CLOSEST(group->cpu_power, SCHED_LOAD_SCALE);
>  }
>  
>  /**
> @@ -3951,7 +3919,7 @@ static inline void update_sd_lb_stats(st
>  			return;
>  
>  		sds->total_load += sgs.group_load;
> -		sds->total_pwr += group->__cpu_power;
> +		sds->total_pwr += group->cpu_power;
>  
>  		/*
>  		 * In case the child domain prefers tasks go to siblings
> @@ -4016,28 +3984,28 @@ static inline void fix_small_imbalance(s
>  	 * moving them.
>  	 */
>  
> -	pwr_now += sds->busiest->__cpu_power *
> +	pwr_now += sds->busiest->cpu_power *
>  			min(sds->busiest_load_per_task, sds->max_load);
> -	pwr_now += sds->this->__cpu_power *
> +	pwr_now += sds->this->cpu_power *
>  			min(sds->this_load_per_task, sds->this_load);
>  	pwr_now /= SCHED_LOAD_SCALE;
>  
>  	/* Amount of load we'd subtract */
> -	tmp = sg_div_cpu_power(sds->busiest,
> -			sds->busiest_load_per_task * SCHED_LOAD_SCALE);
> +	tmp = (sds->busiest_load_per_task * SCHED_LOAD_SCALE) /
> +		sds->busiest->cpu_power;
>  	if (sds->max_load > tmp)
> -		pwr_move += sds->busiest->__cpu_power *
> +		pwr_move += sds->busiest->cpu_power *
>  			min(sds->busiest_load_per_task, sds->max_load - tmp);
>  
>  	/* Amount of load we'd add */
> -	if (sds->max_load * sds->busiest->__cpu_power <
> +	if (sds->max_load * sds->busiest->cpu_power <
>  		sds->busiest_load_per_task * SCHED_LOAD_SCALE)
> -		tmp = sg_div_cpu_power(sds->this,
> -			sds->max_load * sds->busiest->__cpu_power);
> +		tmp = (sds->max_load * sds->busiest->cpu_power) /
> +			sds->this->cpu_power;
>  	else
> -		tmp = sg_div_cpu_power(sds->this,
> -			sds->busiest_load_per_task * SCHED_LOAD_SCALE);
> -	pwr_move += sds->this->__cpu_power *
> +		tmp = (sds->busiest_load_per_task * SCHED_LOAD_SCALE) /
> +			sds->this->cpu_power;
> +	pwr_move += sds->this->cpu_power *
>  			min(sds->this_load_per_task, sds->this_load + tmp);
>  	pwr_move /= SCHED_LOAD_SCALE;
>  
> @@ -4072,8 +4040,8 @@ static inline void calculate_imbalance(s
>  			sds->max_load - sds->busiest_load_per_task);
>  
>  	/* How much load to actually move to equalise the imbalance */
> -	*imbalance = min(max_pull * sds->busiest->__cpu_power,
> -		(sds->avg_load - sds->this_load) * sds->this->__cpu_power)
> +	*imbalance = min(max_pull * sds->busiest->cpu_power,
> +		(sds->avg_load - sds->this_load) * sds->this->cpu_power)
>  			/ SCHED_LOAD_SCALE;
>  
>  	/*
> @@ -4208,7 +4176,7 @@ static unsigned long power_of(int cpu)
>  	if (!group)
>  		return SCHED_LOAD_SCALE;
>  
> -	return group->__cpu_power;
> +	return group->cpu_power;
>  }
>  
>  /*
> @@ -7934,7 +7902,7 @@ static int sched_domain_debug_one(struct
>  			break;
>  		}
>  
> -		if (!group->__cpu_power) {
> +		if (!group->cpu_power) {
>  			printk(KERN_CONT "\n");
>  			printk(KERN_ERR "ERROR: domain->cpu_power not "
>  					"set\n");
> @@ -7958,9 +7926,9 @@ static int sched_domain_debug_one(struct
>  		cpulist_scnprintf(str, sizeof(str), sched_group_cpus(group));
>  
>  		printk(KERN_CONT " %s", str);
> -		if (group->__cpu_power != SCHED_LOAD_SCALE) {
> -			printk(KERN_CONT " (__cpu_power = %d)",
> -				group->__cpu_power);
> +		if (group->cpu_power != SCHED_LOAD_SCALE) {
> +			printk(KERN_CONT " (cpu_power = %d)",
> +				group->cpu_power);
>  		}
>  
>  		group = group->next;
> @@ -8245,7 +8213,7 @@ init_sched_build_groups(const struct cpu
>  			continue;
>  
>  		cpumask_clear(sched_group_cpus(sg));
> -		sg->__cpu_power = 0;
> +		sg->cpu_power = 0;
>  
>  		for_each_cpu(j, span) {
>  			if (group_fn(j, cpu_map, NULL, tmpmask) != group)
> @@ -8503,7 +8471,7 @@ static void init_numa_sched_groups_power
>  				continue;
>  			}
>  
> -			sg_inc_cpu_power(sg, sd->groups->__cpu_power);
> +			sg->cpu_power += sd->groups->cpu_power;
>  		}
>  		sg = sg->next;
>  	} while (sg != group_head);
> @@ -8540,7 +8508,7 @@ static int build_numa_sched_groups(struc
>  		sd->groups = sg;
>  	}
>  
> -	sg->__cpu_power = 0;
> +	sg->cpu_power = 0;
>  	cpumask_copy(sched_group_cpus(sg), d->nodemask);
>  	sg->next = sg;
>  	cpumask_or(d->covered, d->covered, d->nodemask);
> @@ -8563,7 +8531,7 @@ static int build_numa_sched_groups(struc
>  			       "Can not alloc domain group for node %d\n", j);
>  			return -ENOMEM;
>  		}
> -		sg->__cpu_power = 0;
> +		sg->cpu_power = 0;
>  		cpumask_copy(sched_group_cpus(sg), d->tmpmask);
>  		sg->next = prev->next;
>  		cpumask_or(d->covered, d->covered, d->tmpmask);
> @@ -8641,7 +8609,7 @@ static void init_sched_groups_power(int 
>  
>  	child = sd->child;
>  
> -	sd->groups->__cpu_power = 0;
> +	sd->groups->cpu_power = 0;
>  
>  	if (!child) {
>  		power = SCHED_LOAD_SCALE;
> @@ -8657,7 +8625,7 @@ static void init_sched_groups_power(int 
>  			power /= weight;
>  			power >>= SCHED_LOAD_SHIFT;
>  		}
> -		sg_inc_cpu_power(sd->groups, power);
> +		sd->groups->cpu_power += power;
>  		return;
>  	}
>  
> @@ -8666,7 +8634,7 @@ static void init_sched_groups_power(int 
>  	 */
>  	group = child->groups;
>  	do {
> -		sg_inc_cpu_power(sd->groups, group->__cpu_power);
> +		sd->groups->cpu_power += group->cpu_power;
>  		group = group->next;
>  	} while (group != child->groups);
>  }
> Index: linux-2.6/include/linux/sched.h
> ===================================================================
> --- linux-2.6.orig/include/linux/sched.h
> +++ linux-2.6/include/linux/sched.h
> @@ -870,15 +870,9 @@ 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
> +	 * single CPU.
>  	 */
> -	unsigned int __cpu_power;
> -	/*
> -	 * reciprocal value of cpu_power to avoid expensive divides
> -	 * (see include/linux/reciprocal_div.h)
> -	 */
> -	u32 reciprocal_cpu_power;
> +	unsigned int cpu_power;
>  
>  	/*
>  	 * The CPUs this group covers.
> 
> -- 
> 

Nice.
You might also want to remove the respective header file:

--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -64,7 +64,6 @@
 #include <linux/tsacct_kern.h>
 #include <linux/kprobes.h>
 #include <linux/delayacct.h>
-#include <linux/reciprocal_div.h>
 #include <linux/unistd.h>
 #include <linux/pagemap.h>
 #include <linux/hrtimer.h>


Regards,
Andreas

-- 
Operating | Advanced Micro Devices GmbH
  System  | Karl-Hammerschmidt-Str. 34, 85609 Dornach b. München, Germany
 Research | Geschäftsführer: Andrew Bowd, Thomas M. McCoy, Giuliano Meroni
  Center  | Sitz: Dornach, Gemeinde Aschheim, Landkreis München
  (OSRC)  | Registergericht München, HRB Nr. 43632

Re: [RFC][PATCH 0/8] load-balancing and cpu_power -v2

[Peter Zijlstra]

On Thu, 2009-09-03 at 14:10 +0200, Andreas Herrmann wrote:
> On Tue, Sep 01, 2009 at 10:34:31AM +0200, Peter Zijlstra wrote:

> > Anyway, have at it, poke holes and report issues.
> 
> Tested it (to a certain extend).
> Found no performance degradation (on 1P, 2P, 4P systems). (One could
> think performance might slightly degrade due to more frequent
> __cpu_power updates).

Grand.

> This applies to modification of sched_mc_power_savings. And I think
> one of above scenarios is already broken in tip/master w/o your
> patches.

I suspect so, but confirmation would be good, I don't have a single
machine large enough to actually test any of that power saving muck.

> Otherwise especially wrt to integration of APERF/MPERF this seems to
> be a good approach.

On that, are there AMD systems supporting APERF/MPERF? I only know of
Intel machines doing so.

Re: [RFC][PATCH 0/8] load-balancing and cpu_power -v2

[Ingo Molnar]

* Andreas Herrmann <andreas.herrmann3@amd.com> wrote:

> On Tue, Sep 01, 2009 at 10:34:31AM +0200, Peter Zijlstra wrote:
> > A more complete version, one that compiles and mostly works on the
> > simple tests to which it was subjected.
> > 
> > It still lacks integration with APERF/MPERF because that stuff was
> > hidding in some acpi driver instead of placed in arch code for general
> > consumption.. will fix.
> > 
> > Also, SD_SHARE_CPUPOWER seems redundant in the face of sd->level ==
> > SD_LV_SIBLING, should we remove the SD_flag or depricate the level?
> > 
> > Anyway, have at it, poke holes and report issues.
> 
> Tested it (to a certain extend).
> Found no performance degradation (on 1P, 2P, 4P systems). (One could
> think performance might slightly degrade due to more frequent
> __cpu_power updates).

Ok, thanks for doing that, it's really useful - this saved me a day 
of testing and allows me to accelerate these patches and try to 
queue them up in tip:sched today.

Note, we have regressed the load-balancer in recently but its 
inherent complexity makes it pretty hard to fix. We dont max out 
kbuild performance for example - i see this in my distcc builds. 
Would be nice to sort that out too for .32, on top of Peter's 
power-balancing series.

We've got the sched-domains setup simplification suggestions from 
Peter as well, those could be done separately (but are important as 
well, to express more complex hierarchies like Magny-Cours).

	Ingo

[tip:sched/balancing] sched: Restore __cpu_power to a straight sum of power

[tip-bot for Peter Zijlstra]

Commit-ID:  f93e65c186ab3c05ce2068733ca10e34fd00125e
Gitweb:     http://git.kernel.org/tip/f93e65c186ab3c05ce2068733ca10e34fd00125e
Author:     Peter Zijlstra <a.p.zijlstra@chello.nl>
AuthorDate: Tue, 1 Sep 2009 10:34:32 +0200
Committer:  Ingo Molnar <mingo@elte.hu>
CommitDate: Fri, 4 Sep 2009 10:09:53 +0200

sched: Restore __cpu_power to a straight sum of power

cpu_power is supposed to be a representation of the process
capacity of the cpu, not a value to randomly tweak in order to
affect placement.

Remove the placement hacks.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Tested-by: Andreas Herrmann <andreas.herrmann3@amd.com>
Acked-by: Andreas Herrmann <andreas.herrmann3@amd.com>
Acked-by: Gautham R Shenoy <ego@in.ibm.com>
Cc: Balbir Singh <balbir@in.ibm.com>
LKML-Reference: <20090901083825.810860576@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>


---
 kernel/sched.c |   28 ++++++++++++----------------
 1 files changed, 12 insertions(+), 16 deletions(-)

diff --git a/kernel/sched.c b/kernel/sched.c
index da1edc8..584a122 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -8464,15 +8464,13 @@ static void free_sched_groups(const struct cpumask *cpu_map,
  * there are asymmetries in the topology. If there are asymmetries, group
  * having more cpu_power will pickup more load compared to the group having
  * less cpu_power.
- *
- * cpu_power will be a multiple of SCHED_LOAD_SCALE. This multiple represents
- * the maximum number of tasks a group can handle in the presence of other idle
- * or lightly loaded groups in the same sched domain.
  */
 static void init_sched_groups_power(int cpu, struct sched_domain *sd)
 {
 	struct sched_domain *child;
 	struct sched_group *group;
+	long power;
+	int weight;
 
 	WARN_ON(!sd || !sd->groups);
 
@@ -8483,22 +8481,20 @@ static void init_sched_groups_power(int cpu, struct sched_domain *sd)
 
 	sd->groups->__cpu_power = 0;
 
-	/*
-	 * For perf policy, if the groups in child domain share resources
-	 * (for example cores sharing some portions of the cache hierarchy
-	 * or SMT), then set this domain groups cpu_power such that each group
-	 * can handle only one task, when there are other idle groups in the
-	 * same sched domain.
-	 */
-	if (!child || (!(sd->flags & SD_POWERSAVINGS_BALANCE) &&
-		       (child->flags &
-			(SD_SHARE_CPUPOWER | SD_SHARE_PKG_RESOURCES)))) {
-		sg_inc_cpu_power(sd->groups, SCHED_LOAD_SCALE);
+	if (!child) {
+		power = SCHED_LOAD_SCALE;
+		weight = cpumask_weight(sched_domain_span(sd));
+		/*
+		 * SMT siblings share the power of a single core.
+		 */
+		if ((sd->flags & SD_SHARE_CPUPOWER) && weight > 1)
+			power /= weight;
+		sg_inc_cpu_power(sd->groups, power);
 		return;
 	}
 
 	/*
-	 * add cpu_power of each child group to this groups cpu_power
+	 * Add cpu_power of each child group to this groups cpu_power.
 	 */
 	group = child->groups;
 	do {

[tip:sched/balancing] sched: Add SD_PREFER_SIBLING

[tip-bot for Peter Zijlstra]

Commit-ID:  b5d978e0c7e79a7ff842e895c85a86b38c71f1cd
Gitweb:     http://git.kernel.org/tip/b5d978e0c7e79a7ff842e895c85a86b38c71f1cd
Author:     Peter Zijlstra <a.p.zijlstra@chello.nl>
AuthorDate: Tue, 1 Sep 2009 10:34:33 +0200
Committer:  Ingo Molnar <mingo@elte.hu>
CommitDate: Fri, 4 Sep 2009 10:09:53 +0200

sched: Add SD_PREFER_SIBLING

Do the placement thing using SD flags.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Tested-by: Andreas Herrmann <andreas.herrmann3@amd.com>
Acked-by: Andreas Herrmann <andreas.herrmann3@amd.com>
Acked-by: Gautham R Shenoy <ego@in.ibm.com>
Cc: Balbir Singh <balbir@in.ibm.com>
LKML-Reference: <20090901083825.897028974@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>


---
 include/linux/sched.h |   29 +++++++++++++++--------------
 kernel/sched.c        |   14 +++++++++++++-
 2 files changed, 28 insertions(+), 15 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 9c96ef2..651dded 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -798,18 +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 */
@@ -829,7 +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)
@@ -837,7 +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;
 }
 
 /*
diff --git a/kernel/sched.c b/kernel/sched.c
index 584a122..9d64cec 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -3811,9 +3811,13 @@ static inline void update_sd_lb_stats(struct sched_domain *sd, int this_cpu,
 			const struct cpumask *cpus, int *balance,
 			struct sd_lb_stats *sds)
 {
+	struct sched_domain *child = sd->child;
 	struct sched_group *group = sd->groups;
 	struct sg_lb_stats sgs;
-	int load_idx;
+	int load_idx, prefer_sibling = 0;
+
+	if (child && child->flags & SD_PREFER_SIBLING)
+		prefer_sibling = 1;
 
 	init_sd_power_savings_stats(sd, sds, idle);
 	load_idx = get_sd_load_idx(sd, idle);
@@ -3833,6 +3837,14 @@ static inline void update_sd_lb_stats(struct sched_domain *sd, int this_cpu,
 		sds->total_load += sgs.group_load;
 		sds->total_pwr += group->__cpu_power;
 
+		/*
+		 * In case the child domain prefers tasks go to siblings
+		 * first, lower the group capacity to one so that we'll try
+		 * and move all the excess tasks away.
+		 */
+		if (prefer_sibling)
+			sgs.group_capacity = 1;
+
 		if (local_group) {
 			sds->this_load = sgs.avg_load;
 			sds->this = group;

[tip:sched/balancing] sched: Update the cpu_power sum during load-balance

[tip-bot for Peter Zijlstra]

Commit-ID:  cc9fba7d7672fa3ed58d9d9ecb6c45b1351c29a6
Gitweb:     http://git.kernel.org/tip/cc9fba7d7672fa3ed58d9d9ecb6c45b1351c29a6
Author:     Peter Zijlstra <a.p.zijlstra@chello.nl>
AuthorDate: Tue, 1 Sep 2009 10:34:34 +0200
Committer:  Ingo Molnar <mingo@elte.hu>
CommitDate: Fri, 4 Sep 2009 10:09:53 +0200

sched: Update the cpu_power sum during load-balance

In order to prepare for a more dynamic cpu_power, update the
group sum while walking the sched domains during load-balance.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Tested-by: Andreas Herrmann <andreas.herrmann3@amd.com>
Acked-by: Andreas Herrmann <andreas.herrmann3@amd.com>
Acked-by: Gautham R Shenoy <ego@in.ibm.com>
Cc: Balbir Singh <balbir@in.ibm.com>
LKML-Reference: <20090901083825.985050292@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>


---
 kernel/sched.c |   33 +++++++++++++++++++++++++++++----
 1 files changed, 29 insertions(+), 4 deletions(-)

diff --git a/kernel/sched.c b/kernel/sched.c
index 9d64cec..ecb4a47 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -3699,6 +3699,28 @@ static inline int check_power_save_busiest_group(struct sd_lb_stats *sds,
 }
 #endif /* CONFIG_SCHED_MC || CONFIG_SCHED_SMT */
 
+static void update_sched_power(struct sched_domain *sd)
+{
+	struct sched_domain *child = sd->child;
+	struct sched_group *group, *sdg = sd->groups;
+	unsigned long power = sdg->__cpu_power;
+
+	if (!child) {
+		/* compute cpu power for this cpu */
+		return;
+	}
+
+	sdg->__cpu_power = 0;
+
+	group = child->groups;
+	do {
+		sdg->__cpu_power += group->__cpu_power;
+		group = group->next;
+	} while (group != child->groups);
+
+	if (power != sdg->__cpu_power)
+		sdg->reciprocal_cpu_power = reciprocal_value(sdg->__cpu_power);
+}
 
 /**
  * update_sg_lb_stats - Update sched_group's statistics for load balancing.
@@ -3712,7 +3734,8 @@ static inline int check_power_save_busiest_group(struct sd_lb_stats *sds,
  * @balance: Should we balance.
  * @sgs: variable to hold the statistics for this group.
  */
-static inline void update_sg_lb_stats(struct sched_group *group, int this_cpu,
+static inline void update_sg_lb_stats(struct sched_domain *sd,
+			struct sched_group *group, int this_cpu,
 			enum cpu_idle_type idle, int load_idx, int *sd_idle,
 			int local_group, const struct cpumask *cpus,
 			int *balance, struct sg_lb_stats *sgs)
@@ -3723,8 +3746,11 @@ static inline void update_sg_lb_stats(struct sched_group *group, int this_cpu,
 	unsigned long sum_avg_load_per_task;
 	unsigned long avg_load_per_task;
 
-	if (local_group)
+	if (local_group) {
 		balance_cpu = group_first_cpu(group);
+		if (balance_cpu == this_cpu)
+			update_sched_power(sd);
+	}
 
 	/* Tally up the load of all CPUs in the group */
 	sum_avg_load_per_task = avg_load_per_task = 0;
@@ -3828,7 +3854,7 @@ static inline void update_sd_lb_stats(struct sched_domain *sd, int this_cpu,
 		local_group = cpumask_test_cpu(this_cpu,
 					       sched_group_cpus(group));
 		memset(&sgs, 0, sizeof(sgs));
-		update_sg_lb_stats(group, this_cpu, idle, load_idx, sd_idle,
+		update_sg_lb_stats(sd, group, this_cpu, idle, load_idx, sd_idle,
 				local_group, cpus, balance, &sgs);
 
 		if (local_group && balance && !(*balance))
@@ -3863,7 +3889,6 @@ static inline void update_sd_lb_stats(struct sched_domain *sd, int this_cpu,
 		update_sd_power_savings_stats(group, sds, local_group, &sgs);
 		group = group->next;
 	} while (group != sd->groups);
-
 }
 
 /**

[tip:sched/balancing] sched: Add smt_gain

[tip-bot for Peter Zijlstra]

Commit-ID:  a52bfd73589eaf88d9c95ad2c1de0b38a6b27972
Gitweb:     http://git.kernel.org/tip/a52bfd73589eaf88d9c95ad2c1de0b38a6b27972
Author:     Peter Zijlstra <a.p.zijlstra@chello.nl>
AuthorDate: Tue, 1 Sep 2009 10:34:35 +0200
Committer:  Ingo Molnar <mingo@elte.hu>
CommitDate: Fri, 4 Sep 2009 10:09:54 +0200

sched: Add smt_gain

The idea is that multi-threading a core yields more work
capacity than a single thread, provide a way to express a
static gain for threads.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Tested-by: Andreas Herrmann <andreas.herrmann3@amd.com>
Acked-by: Andreas Herrmann <andreas.herrmann3@amd.com>
Acked-by: Gautham R Shenoy <ego@in.ibm.com>
Cc: Balbir Singh <balbir@in.ibm.com>
LKML-Reference: <20090901083826.073345955@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>


---
 include/linux/sched.h    |    1 +
 include/linux/topology.h |    1 +
 kernel/sched.c           |    8 +++++++-
 3 files changed, 9 insertions(+), 1 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 651dded..9c81c92 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -921,6 +921,7 @@ 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;
 
diff --git a/include/linux/topology.h b/include/linux/topology.h
index 7402c1a..6203ae5 100644
--- a/include/linux/topology.h
+++ b/include/linux/topology.h
@@ -99,6 +99,7 @@ int arch_update_cpu_topology(void);
 				| SD_SHARE_CPUPOWER,	\
 	.last_balance		= jiffies,		\
 	.balance_interval	= 1,			\
+	.smt_gain		= 1178,	/* 15% */	\
 }
 #endif
 #endif /* CONFIG_SCHED_SMT */
diff --git a/kernel/sched.c b/kernel/sched.c
index ecb4a47..5511226 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -8523,9 +8523,15 @@ static void init_sched_groups_power(int cpu, struct sched_domain *sd)
 		weight = cpumask_weight(sched_domain_span(sd));
 		/*
 		 * SMT siblings share the power of a single core.
+		 * Usually multiple threads get a better yield out of
+		 * that one core than a single thread would have,
+		 * reflect that in sd->smt_gain.
 		 */
-		if ((sd->flags & SD_SHARE_CPUPOWER) && weight > 1)
+		if ((sd->flags & SD_SHARE_CPUPOWER) && weight > 1) {
+			power *= sd->smt_gain;
 			power /= weight;
+			power >>= SCHED_LOAD_SHIFT;
+		}
 		sg_inc_cpu_power(sd->groups, power);
 		return;
 	}

[tip:sched/balancing] sched: Implement dynamic cpu_power

[tip-bot for Peter Zijlstra]

Commit-ID:  ab29230e673c646292c90c8b9d378b9562145af0
Gitweb:     http://git.kernel.org/tip/ab29230e673c646292c90c8b9d378b9562145af0
Author:     Peter Zijlstra <a.p.zijlstra@chello.nl>
AuthorDate: Tue, 1 Sep 2009 10:34:36 +0200
Committer:  Ingo Molnar <mingo@elte.hu>
CommitDate: Fri, 4 Sep 2009 10:09:54 +0200

sched: Implement dynamic cpu_power

Recompute the cpu_power for each cpu during load-balance.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Tested-by: Andreas Herrmann <andreas.herrmann3@amd.com>
Acked-by: Andreas Herrmann <andreas.herrmann3@amd.com>
Acked-by: Gautham R Shenoy <ego@in.ibm.com>
Cc: Balbir Singh <balbir@in.ibm.com>
LKML-Reference: <20090901083826.162033479@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>


---
 kernel/sched.c |   38 +++++++++++++++++++++++++++++++++++---
 1 files changed, 35 insertions(+), 3 deletions(-)

diff --git a/kernel/sched.c b/kernel/sched.c
index 5511226..036600f 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -3699,14 +3699,46 @@ static inline int check_power_save_busiest_group(struct sd_lb_stats *sds,
 }
 #endif /* CONFIG_SCHED_MC || CONFIG_SCHED_SMT */
 
-static void update_sched_power(struct sched_domain *sd)
+unsigned long __weak arch_smt_gain(struct sched_domain *sd, int cpu)
+{
+	unsigned long weight = cpumask_weight(sched_domain_span(sd));
+	unsigned long smt_gain = sd->smt_gain;
+
+	smt_gain /= weight;
+
+	return smt_gain;
+}
+
+static void update_cpu_power(struct sched_domain *sd, int cpu)
+{
+	unsigned long weight = cpumask_weight(sched_domain_span(sd));
+	unsigned long power = SCHED_LOAD_SCALE;
+	struct sched_group *sdg = sd->groups;
+	unsigned long old = sdg->__cpu_power;
+
+	/* here we could scale based on cpufreq */
+
+	if ((sd->flags & SD_SHARE_CPUPOWER) && weight > 1) {
+		power *= arch_smt_gain(sd, cpu);
+		power >>= SCHED_LOAD_SHIFT;
+	}
+
+	/* here we could scale based on RT time */
+
+	if (power != old) {
+		sdg->__cpu_power = power;
+		sdg->reciprocal_cpu_power = reciprocal_value(power);
+	}
+}
+
+static void update_group_power(struct sched_domain *sd, int cpu)
 {
 	struct sched_domain *child = sd->child;
 	struct sched_group *group, *sdg = sd->groups;
 	unsigned long power = sdg->__cpu_power;
 
 	if (!child) {
-		/* compute cpu power for this cpu */
+		update_cpu_power(sd, cpu);
 		return;
 	}
 
@@ -3749,7 +3781,7 @@ static inline void update_sg_lb_stats(struct sched_domain *sd,
 	if (local_group) {
 		balance_cpu = group_first_cpu(group);
 		if (balance_cpu == this_cpu)
-			update_sched_power(sd);
+			update_group_power(sd, this_cpu);
 	}
 
 	/* Tally up the load of all CPUs in the group */

[tip:sched/balancing] sched: Scale down cpu_power due to RT tasks

[tip-bot for Peter Zijlstra]

Commit-ID:  e9e9250bc78e7f6342517214c0178a529807964b
Gitweb:     http://git.kernel.org/tip/e9e9250bc78e7f6342517214c0178a529807964b
Author:     Peter Zijlstra <a.p.zijlstra@chello.nl>
AuthorDate: Tue, 1 Sep 2009 10:34:37 +0200
Committer:  Ingo Molnar <mingo@elte.hu>
CommitDate: Fri, 4 Sep 2009 10:09:55 +0200

sched: Scale down cpu_power due to RT tasks

Keep an average on the amount of time spend on RT tasks and use
that fraction to scale down the cpu_power for regular tasks.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Tested-by: Andreas Herrmann <andreas.herrmann3@amd.com>
Acked-by: Andreas Herrmann <andreas.herrmann3@amd.com>
Acked-by: Gautham R Shenoy <ego@in.ibm.com>
Cc: Balbir Singh <balbir@in.ibm.com>
LKML-Reference: <20090901083826.287778431@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>


---
 include/linux/sched.h |    1 +
 kernel/sched.c        |   64 ++++++++++++++++++++++++++++++++++++++++++++++--
 kernel/sched_rt.c     |    6 +---
 kernel/sysctl.c       |    8 ++++++
 4 files changed, 72 insertions(+), 7 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 9c81c92..c67ddf3 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1831,6 +1831,7 @@ 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;
+extern unsigned int sysctl_sched_time_avg;
 extern unsigned int sysctl_timer_migration;
 
 int sched_nr_latency_handler(struct ctl_table *table, int write,
diff --git a/kernel/sched.c b/kernel/sched.c
index 036600f..ab532b5 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -627,6 +627,9 @@ struct rq {
 
 	struct task_struct *migration_thread;
 	struct list_head migration_queue;
+
+	u64 rt_avg;
+	u64 age_stamp;
 #endif
 
 	/* calc_load related fields */
@@ -863,6 +866,14 @@ unsigned int sysctl_sched_shares_ratelimit = 250000;
 unsigned int sysctl_sched_shares_thresh = 4;
 
 /*
+ * period over which we average the RT time consumption, measured
+ * in ms.
+ *
+ * default: 1s
+ */
+const_debug unsigned int sysctl_sched_time_avg = MSEC_PER_SEC;
+
+/*
  * period over which we measure -rt task cpu usage in us.
  * default: 1s
  */
@@ -1280,12 +1291,37 @@ void wake_up_idle_cpu(int cpu)
 }
 #endif /* CONFIG_NO_HZ */
 
+static u64 sched_avg_period(void)
+{
+	return (u64)sysctl_sched_time_avg * NSEC_PER_MSEC / 2;
+}
+
+static void sched_avg_update(struct rq *rq)
+{
+	s64 period = sched_avg_period();
+
+	while ((s64)(rq->clock - rq->age_stamp) > period) {
+		rq->age_stamp += period;
+		rq->rt_avg /= 2;
+	}
+}
+
+static void sched_rt_avg_update(struct rq *rq, u64 rt_delta)
+{
+	rq->rt_avg += rt_delta;
+	sched_avg_update(rq);
+}
+
 #else /* !CONFIG_SMP */
 static void resched_task(struct task_struct *p)
 {
 	assert_spin_locked(&task_rq(p)->lock);
 	set_tsk_need_resched(p);
 }
+
+static void sched_rt_avg_update(struct rq *rq, u64 rt_delta)
+{
+}
 #endif /* CONFIG_SMP */
 
 #if BITS_PER_LONG == 32
@@ -3699,7 +3735,7 @@ static inline int check_power_save_busiest_group(struct sd_lb_stats *sds,
 }
 #endif /* CONFIG_SCHED_MC || CONFIG_SCHED_SMT */
 
-unsigned long __weak arch_smt_gain(struct sched_domain *sd, int cpu)
+unsigned long __weak arch_scale_smt_power(struct sched_domain *sd, int cpu)
 {
 	unsigned long weight = cpumask_weight(sched_domain_span(sd));
 	unsigned long smt_gain = sd->smt_gain;
@@ -3709,6 +3745,24 @@ unsigned long __weak arch_smt_gain(struct sched_domain *sd, int cpu)
 	return smt_gain;
 }
 
+unsigned long scale_rt_power(int cpu)
+{
+	struct rq *rq = cpu_rq(cpu);
+	u64 total, available;
+
+	sched_avg_update(rq);
+
+	total = sched_avg_period() + (rq->clock - rq->age_stamp);
+	available = total - rq->rt_avg;
+
+	if (unlikely((s64)total < SCHED_LOAD_SCALE))
+		total = SCHED_LOAD_SCALE;
+
+	total >>= SCHED_LOAD_SHIFT;
+
+	return div_u64(available, total);
+}
+
 static void update_cpu_power(struct sched_domain *sd, int cpu)
 {
 	unsigned long weight = cpumask_weight(sched_domain_span(sd));
@@ -3719,11 +3773,15 @@ static void update_cpu_power(struct sched_domain *sd, int cpu)
 	/* here we could scale based on cpufreq */
 
 	if ((sd->flags & SD_SHARE_CPUPOWER) && weight > 1) {
-		power *= arch_smt_gain(sd, cpu);
+		power *= arch_scale_smt_power(sd, cpu);
 		power >>= SCHED_LOAD_SHIFT;
 	}
 
-	/* here we could scale based on RT time */
+	power *= scale_rt_power(cpu);
+	power >>= SCHED_LOAD_SHIFT;
+
+	if (!power)
+		power = 1;
 
 	if (power != old) {
 		sdg->__cpu_power = power;
diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index 3d4020a..2eb4bd6 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -615,6 +615,8 @@ static void update_curr_rt(struct rq *rq)
 	curr->se.exec_start = rq->clock;
 	cpuacct_charge(curr, delta_exec);
 
+	sched_rt_avg_update(rq, delta_exec);
+
 	if (!rt_bandwidth_enabled())
 		return;
 
@@ -887,8 +889,6 @@ static void enqueue_task_rt(struct rq *rq, struct task_struct *p, int wakeup)
 
 	if (!task_current(rq, p) && p->rt.nr_cpus_allowed > 1)
 		enqueue_pushable_task(rq, p);
-
-	inc_cpu_load(rq, p->se.load.weight);
 }
 
 static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int sleep)
@@ -899,8 +899,6 @@ static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int sleep)
 	dequeue_rt_entity(rt_se);
 
 	dequeue_pushable_task(rq, p);
-
-	dec_cpu_load(rq, p->se.load.weight);
 }
 
 /*
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 58be760..6c9836e 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -332,6 +332,14 @@ static struct ctl_table kern_table[] = {
 	},
 	{
 		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "sched_time_avg",
+		.data		= &sysctl_sched_time_avg,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
+	{
+		.ctl_name	= CTL_UNNUMBERED,
 		.procname	= "timer_migration",
 		.data		= &sysctl_timer_migration,
 		.maxlen		= sizeof(unsigned int),

[tip:sched/balancing] sched: Try to deal with low capacity

[tip-bot for Peter Zijlstra]

Commit-ID:  bdb94aa5dbd8b55e75f5a50b61312fe589e2c2d1
Gitweb:     http://git.kernel.org/tip/bdb94aa5dbd8b55e75f5a50b61312fe589e2c2d1
Author:     Peter Zijlstra <a.p.zijlstra@chello.nl>
AuthorDate: Tue, 1 Sep 2009 10:34:38 +0200
Committer:  Ingo Molnar <mingo@elte.hu>
CommitDate: Fri, 4 Sep 2009 10:09:55 +0200

sched: Try to deal with low capacity

When the capacity drops low, we want to migrate load away.
Allow the load-balancer to remove all tasks when we hit rock
bottom.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Tested-by: Andreas Herrmann <andreas.herrmann3@amd.com>
Acked-by: Andreas Herrmann <andreas.herrmann3@amd.com>
Acked-by: Gautham R Shenoy <ego@in.ibm.com>
Cc: Balbir Singh <balbir@in.ibm.com>
LKML-Reference: <20090901083826.342231003@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>


---
 kernel/sched.c |   33 ++++++++++++++++++++++++++++-----
 1 files changed, 28 insertions(+), 5 deletions(-)

diff --git a/kernel/sched.c b/kernel/sched.c
index ab532b5..5f5b359 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -3908,8 +3908,8 @@ static inline void update_sg_lb_stats(struct sched_domain *sd,
 	if ((max_cpu_load - min_cpu_load) > 2*avg_load_per_task)
 		sgs->group_imb = 1;
 
-	sgs->group_capacity = group->__cpu_power / SCHED_LOAD_SCALE;
-
+	sgs->group_capacity =
+		DIV_ROUND_CLOSEST(group->__cpu_power, SCHED_LOAD_SCALE);
 }
 
 /**
@@ -3959,7 +3959,7 @@ static inline void update_sd_lb_stats(struct sched_domain *sd, int this_cpu,
 		 * and move all the excess tasks away.
 		 */
 		if (prefer_sibling)
-			sgs.group_capacity = 1;
+			sgs.group_capacity = min(sgs.group_capacity, 1UL);
 
 		if (local_group) {
 			sds->this_load = sgs.avg_load;
@@ -4191,6 +4191,26 @@ ret:
 	return NULL;
 }
 
+static struct sched_group *group_of(int cpu)
+{
+	struct sched_domain *sd = rcu_dereference(cpu_rq(cpu)->sd);
+
+	if (!sd)
+		return NULL;
+
+	return sd->groups;
+}
+
+static unsigned long power_of(int cpu)
+{
+	struct sched_group *group = group_of(cpu);
+
+	if (!group)
+		return SCHED_LOAD_SCALE;
+
+	return group->__cpu_power;
+}
+
 /*
  * find_busiest_queue - find the busiest runqueue among the cpus in group.
  */
@@ -4203,15 +4223,18 @@ find_busiest_queue(struct sched_group *group, enum cpu_idle_type idle,
 	int i;
 
 	for_each_cpu(i, sched_group_cpus(group)) {
+		unsigned long power = power_of(i);
+		unsigned long capacity = DIV_ROUND_CLOSEST(power, SCHED_LOAD_SCALE);
 		unsigned long wl;
 
 		if (!cpumask_test_cpu(i, cpus))
 			continue;
 
 		rq = cpu_rq(i);
-		wl = weighted_cpuload(i);
+		wl = weighted_cpuload(i) * SCHED_LOAD_SCALE;
+		wl /= power;
 
-		if (rq->nr_running == 1 && wl > imbalance)
+		if (capacity && rq->nr_running == 1 && wl > imbalance)
 			continue;
 
 		if (wl > max_load) {

[tip:sched/balancing] sched: Remove reciprocal for cpu_power

[tip-bot for Peter Zijlstra]

Commit-ID:  18a3885fc1ffa92c2212ff0afdf033403d5b0fa0
Gitweb:     http://git.kernel.org/tip/18a3885fc1ffa92c2212ff0afdf033403d5b0fa0
Author:     Peter Zijlstra <a.p.zijlstra@chello.nl>
AuthorDate: Tue, 1 Sep 2009 10:34:39 +0200
Committer:  Ingo Molnar <mingo@elte.hu>
CommitDate: Fri, 4 Sep 2009 10:09:56 +0200

sched: Remove reciprocal for cpu_power

Its a source of fail, also, now that cpu_power is dynamical,
its a waste of time.

before:
<idle>-0   [000]   132.877936: find_busiest_group: avg_load: 0 group_load: 8241 power: 1

after:
bash-1689  [001]   137.862151: find_busiest_group: avg_load: 10636288 group_load: 10387 power: 1

[ v2: build fix from From: Andreas Herrmann ]

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Tested-by: Andreas Herrmann <andreas.herrmann3@amd.com>
Acked-by: Andreas Herrmann <andreas.herrmann3@amd.com>
Acked-by: Gautham R Shenoy <ego@in.ibm.com>
Cc: Balbir Singh <balbir@in.ibm.com>
LKML-Reference: <20090901083826.425896304@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>


---
 include/linux/sched.h |   10 +----
 kernel/sched.c        |  101 ++++++++++++++++--------------------------------
 2 files changed, 36 insertions(+), 75 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index c67ddf3..3b7f43e 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -860,15 +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
+	 * single CPU.
 	 */
-	unsigned int __cpu_power;
-	/*
-	 * reciprocal value of cpu_power to avoid expensive divides
-	 * (see include/linux/reciprocal_div.h)
-	 */
-	u32 reciprocal_cpu_power;
+	unsigned int cpu_power;
 
 	/*
 	 * The CPUs this group covers.
diff --git a/kernel/sched.c b/kernel/sched.c
index e1ebf9b..b537853 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -64,7 +64,6 @@
 #include <linux/tsacct_kern.h>
 #include <linux/kprobes.h>
 #include <linux/delayacct.h>
-#include <linux/reciprocal_div.h>
 #include <linux/unistd.h>
 #include <linux/pagemap.h>
 #include <linux/hrtimer.h>
@@ -120,30 +119,8 @@
  */
 #define RUNTIME_INF	((u64)~0ULL)
 
-#ifdef CONFIG_SMP
-
 static void double_rq_lock(struct rq *rq1, struct rq *rq2);
 
-/*
- * Divide a load by a sched group cpu_power : (load / sg->__cpu_power)
- * Since cpu_power is a 'constant', we can use a reciprocal divide.
- */
-static inline u32 sg_div_cpu_power(const struct sched_group *sg, u32 load)
-{
-	return reciprocal_divide(load, sg->reciprocal_cpu_power);
-}
-
-/*
- * Each time a sched group cpu_power is changed,
- * we must compute its reciprocal value
- */
-static inline void sg_inc_cpu_power(struct sched_group *sg, u32 val)
-{
-	sg->__cpu_power += val;
-	sg->reciprocal_cpu_power = reciprocal_value(sg->__cpu_power);
-}
-#endif
-
 static inline int rt_policy(int policy)
 {
 	if (unlikely(policy == SCHED_FIFO || policy == SCHED_RR))
@@ -2335,8 +2312,7 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p, int this_cpu)
 		}
 
 		/* Adjust by relative CPU power of the group */
-		avg_load = sg_div_cpu_power(group,
-				avg_load * SCHED_LOAD_SCALE);
+		avg_load = (avg_load * SCHED_LOAD_SCALE) / group->cpu_power;
 
 		if (local_group) {
 			this_load = avg_load;
@@ -3768,7 +3744,6 @@ static void update_cpu_power(struct sched_domain *sd, int cpu)
 	unsigned long weight = cpumask_weight(sched_domain_span(sd));
 	unsigned long power = SCHED_LOAD_SCALE;
 	struct sched_group *sdg = sd->groups;
-	unsigned long old = sdg->__cpu_power;
 
 	/* here we could scale based on cpufreq */
 
@@ -3783,33 +3758,26 @@ static void update_cpu_power(struct sched_domain *sd, int cpu)
 	if (!power)
 		power = 1;
 
-	if (power != old) {
-		sdg->__cpu_power = power;
-		sdg->reciprocal_cpu_power = reciprocal_value(power);
-	}
+	sdg->cpu_power = power;
 }
 
 static void update_group_power(struct sched_domain *sd, int cpu)
 {
 	struct sched_domain *child = sd->child;
 	struct sched_group *group, *sdg = sd->groups;
-	unsigned long power = sdg->__cpu_power;
 
 	if (!child) {
 		update_cpu_power(sd, cpu);
 		return;
 	}
 
-	sdg->__cpu_power = 0;
+	sdg->cpu_power = 0;
 
 	group = child->groups;
 	do {
-		sdg->__cpu_power += group->__cpu_power;
+		sdg->cpu_power += group->cpu_power;
 		group = group->next;
 	} while (group != child->groups);
-
-	if (power != sdg->__cpu_power)
-		sdg->reciprocal_cpu_power = reciprocal_value(sdg->__cpu_power);
 }
 
 /**
@@ -3889,8 +3857,7 @@ static inline void update_sg_lb_stats(struct sched_domain *sd,
 	}
 
 	/* Adjust by relative CPU power of the group */
-	sgs->avg_load = sg_div_cpu_power(group,
-			sgs->group_load * SCHED_LOAD_SCALE);
+	sgs->avg_load = (sgs->group_load * SCHED_LOAD_SCALE) / group->cpu_power;
 
 
 	/*
@@ -3902,14 +3869,14 @@ static inline void update_sg_lb_stats(struct sched_domain *sd,
 	 *      normalized nr_running number somewhere that negates
 	 *      the hierarchy?
 	 */
-	avg_load_per_task = sg_div_cpu_power(group,
-			sum_avg_load_per_task * SCHED_LOAD_SCALE);
+	avg_load_per_task = (sum_avg_load_per_task * SCHED_LOAD_SCALE) /
+		group->cpu_power;
 
 	if ((max_cpu_load - min_cpu_load) > 2*avg_load_per_task)
 		sgs->group_imb = 1;
 
 	sgs->group_capacity =
-		DIV_ROUND_CLOSEST(group->__cpu_power, SCHED_LOAD_SCALE);
+		DIV_ROUND_CLOSEST(group->cpu_power, SCHED_LOAD_SCALE);
 }
 
 /**
@@ -3951,7 +3918,7 @@ static inline void update_sd_lb_stats(struct sched_domain *sd, int this_cpu,
 			return;
 
 		sds->total_load += sgs.group_load;
-		sds->total_pwr += group->__cpu_power;
+		sds->total_pwr += group->cpu_power;
 
 		/*
 		 * In case the child domain prefers tasks go to siblings
@@ -4016,28 +3983,28 @@ static inline void fix_small_imbalance(struct sd_lb_stats *sds,
 	 * moving them.
 	 */
 
-	pwr_now += sds->busiest->__cpu_power *
+	pwr_now += sds->busiest->cpu_power *
 			min(sds->busiest_load_per_task, sds->max_load);
-	pwr_now += sds->this->__cpu_power *
+	pwr_now += sds->this->cpu_power *
 			min(sds->this_load_per_task, sds->this_load);
 	pwr_now /= SCHED_LOAD_SCALE;
 
 	/* Amount of load we'd subtract */
-	tmp = sg_div_cpu_power(sds->busiest,
-			sds->busiest_load_per_task * SCHED_LOAD_SCALE);
+	tmp = (sds->busiest_load_per_task * SCHED_LOAD_SCALE) /
+		sds->busiest->cpu_power;
 	if (sds->max_load > tmp)
-		pwr_move += sds->busiest->__cpu_power *
+		pwr_move += sds->busiest->cpu_power *
 			min(sds->busiest_load_per_task, sds->max_load - tmp);
 
 	/* Amount of load we'd add */
-	if (sds->max_load * sds->busiest->__cpu_power <
+	if (sds->max_load * sds->busiest->cpu_power <
 		sds->busiest_load_per_task * SCHED_LOAD_SCALE)
-		tmp = sg_div_cpu_power(sds->this,
-			sds->max_load * sds->busiest->__cpu_power);
+		tmp = (sds->max_load * sds->busiest->cpu_power) /
+			sds->this->cpu_power;
 	else
-		tmp = sg_div_cpu_power(sds->this,
-			sds->busiest_load_per_task * SCHED_LOAD_SCALE);
-	pwr_move += sds->this->__cpu_power *
+		tmp = (sds->busiest_load_per_task * SCHED_LOAD_SCALE) /
+			sds->this->cpu_power;
+	pwr_move += sds->this->cpu_power *
 			min(sds->this_load_per_task, sds->this_load + tmp);
 	pwr_move /= SCHED_LOAD_SCALE;
 
@@ -4072,8 +4039,8 @@ static inline void calculate_imbalance(struct sd_lb_stats *sds, int this_cpu,
 			sds->max_load - sds->busiest_load_per_task);
 
 	/* How much load to actually move to equalise the imbalance */
-	*imbalance = min(max_pull * sds->busiest->__cpu_power,
-		(sds->avg_load - sds->this_load) * sds->this->__cpu_power)
+	*imbalance = min(max_pull * sds->busiest->cpu_power,
+		(sds->avg_load - sds->this_load) * sds->this->cpu_power)
 			/ SCHED_LOAD_SCALE;
 
 	/*
@@ -4208,7 +4175,7 @@ static unsigned long power_of(int cpu)
 	if (!group)
 		return SCHED_LOAD_SCALE;
 
-	return group->__cpu_power;
+	return group->cpu_power;
 }
 
 /*
@@ -7922,7 +7889,7 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
 			break;
 		}
 
-		if (!group->__cpu_power) {
+		if (!group->cpu_power) {
 			printk(KERN_CONT "\n");
 			printk(KERN_ERR "ERROR: domain->cpu_power not "
 					"set\n");
@@ -7946,9 +7913,9 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
 		cpulist_scnprintf(str, sizeof(str), sched_group_cpus(group));
 
 		printk(KERN_CONT " %s", str);
-		if (group->__cpu_power != SCHED_LOAD_SCALE) {
-			printk(KERN_CONT " (__cpu_power = %d)",
-				group->__cpu_power);
+		if (group->cpu_power != SCHED_LOAD_SCALE) {
+			printk(KERN_CONT " (cpu_power = %d)",
+				group->cpu_power);
 		}
 
 		group = group->next;
@@ -8233,7 +8200,7 @@ init_sched_build_groups(const struct cpumask *span,
 			continue;
 
 		cpumask_clear(sched_group_cpus(sg));
-		sg->__cpu_power = 0;
+		sg->cpu_power = 0;
 
 		for_each_cpu(j, span) {
 			if (group_fn(j, cpu_map, NULL, tmpmask) != group)
@@ -8491,7 +8458,7 @@ static void init_numa_sched_groups_power(struct sched_group *group_head)
 				continue;
 			}
 
-			sg_inc_cpu_power(sg, sd->groups->__cpu_power);
+			sg->cpu_power += sd->groups->cpu_power;
 		}
 		sg = sg->next;
 	} while (sg != group_head);
@@ -8528,7 +8495,7 @@ static int build_numa_sched_groups(struct s_data *d,
 		sd->groups = sg;
 	}
 
-	sg->__cpu_power = 0;
+	sg->cpu_power = 0;
 	cpumask_copy(sched_group_cpus(sg), d->nodemask);
 	sg->next = sg;
 	cpumask_or(d->covered, d->covered, d->nodemask);
@@ -8551,7 +8518,7 @@ static int build_numa_sched_groups(struct s_data *d,
 			       "Can not alloc domain group for node %d\n", j);
 			return -ENOMEM;
 		}
-		sg->__cpu_power = 0;
+		sg->cpu_power = 0;
 		cpumask_copy(sched_group_cpus(sg), d->tmpmask);
 		sg->next = prev->next;
 		cpumask_or(d->covered, d->covered, d->tmpmask);
@@ -8629,7 +8596,7 @@ static void init_sched_groups_power(int cpu, struct sched_domain *sd)
 
 	child = sd->child;
 
-	sd->groups->__cpu_power = 0;
+	sd->groups->cpu_power = 0;
 
 	if (!child) {
 		power = SCHED_LOAD_SCALE;
@@ -8645,7 +8612,7 @@ static void init_sched_groups_power(int cpu, struct sched_domain *sd)
 			power /= weight;
 			power >>= SCHED_LOAD_SHIFT;
 		}
-		sg_inc_cpu_power(sd->groups, power);
+		sd->groups->cpu_power += power;
 		return;
 	}
 
@@ -8654,7 +8621,7 @@ static void init_sched_groups_power(int cpu, struct sched_domain *sd)
 	 */
 	group = child->groups;
 	do {
-		sg_inc_cpu_power(sd->groups, group->__cpu_power);
+		sd->groups->cpu_power += group->cpu_power;
 		group = group->next;
 	} while (group != child->groups);
 }

[crash] Re: [RFC][PATCH 0/8] load-balancing and cpu_power -v2

[Ingo Molnar]

[-- Attachment #1: Type: text/plain, Size: 5243 bytes --]


i've queued up Peter's patches, with your and Gautham's fixes 
embedded. It works mostly fine - except on two larger boxes, where 
-tip stress-testing triggered this crash:

aldebaran login: [ 1774.088275] divide error: 0000 [#1] SMP 
[ 1774.092293] last sysfs file: /sys/devices/system/cpu/cpu15/cache/index2/shared_cpu_map
[ 1774.100355] CPU 13 
[ 1774.102498] Modules linked in:
[ 1774.105631] Pid: 30881, comm: hackbench Not tainted 2.6.31-rc8-tip-01308-g484d664-dirty #1629 X8DTN
[ 1774.114807] RIP: 0010:[<ffffffff81041c38>]  [<ffffffff81041c38>] sched_balance_self+0x19b/0x2d4
[ 1774.123676] RSP: 0018:ffff880306c1fd58  EFLAGS: 00010246
[ 1774.129037] RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000000
[ 1774.136287] RDX: 0000000000000000 RSI: 0000000000000040 RDI: 0000000000000040
[ 1774.143554] RBP: ffff880306c1fde8 R08: 0000000000000000 R09: ffffc9000140f4c8
[ 1774.150748] R10: ffff88031288c650 R11: ffff880306c1fe08 R12: ffffc90001a0f3a0
[ 1774.158007] R13: ffffc9000140f4b0 R14: 0000000000000000 R15: 0000000000014f00
[ 1774.165248] FS:  0000000000000000(0000) GS:ffffc90001a00000(0063) knlGS:00000000f7f156c0
[ 1774.173473] CS:  0010 DS: 002b ES: 002b CR0: 000000008005003b
[ 1774.179320] CR2: 000000004822c0ac CR3: 000000031357b000 CR4: 00000000000006e0
[ 1774.186586] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[ 1774.193826] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400
[ 1774.201101] Process hackbench (pid: 30881, threadinfo ffff880306c1e000, task ffff88030b4aa710)
[ 1774.209836] Stack:
[ 1774.211861]  0000000000014f00 0000000000014f00 0000000000014f00 0000000000014f10
[ 1774.219300] <0> 0000000000014f10 0000000d00000008 ffff88030b4aa710 ffffc9000140f4c0
[ 1774.227129] <0> 0000000006c1fdd8 0000007d00000001 ffff88030b4aa900 ffffc9000100f4b0
[ 1774.235225] Call Trace:
[ 1774.237704]  [<ffffffff810444c4>] sched_fork+0x2c/0x15f
[ 1774.243032]  [<ffffffff8104942d>] copy_process+0x407/0xda7
[ 1774.248608]  [<ffffffff81049f16>] do_fork+0x149/0x309
[ 1774.253809]  [<ffffffff8120ff12>] ? __up_read+0x9e/0xa8
[ 1774.259101]  [<ffffffff8106df32>] ? up_read+0xe/0x10
[ 1774.264129]  [<ffffffff81565d66>] ? do_page_fault+0x291/0x2c3
[ 1774.269968]  [<ffffffff81035028>] sys32_clone+0x2c/0x2e
[ 1774.275267]  [<ffffffff81034d05>] ia32_ptregs_common+0x25/0x4c
[ 1774.281200] Code: cb 48 8b 7d a8 ff c2 be 40 00 00 00 48 63 d2 e8 73 9b 1c 00 3b 05 19 2e 8c 00 89 c2 7c 8d 41 8b 4d 08 48 c1 e3 0a 31 d2 48 89 d8 <48> f7 f1 83 7d b4 00 48 89 c1 75 16 4c 39 f0 73 0d 49 89 c6 48 
[ 1774.301423] RIP  [<ffffffff81041c38>] sched_balance_self+0x19b/0x2d4
[ 1774.307903]  RSP <ffff880306c1fd58>
[ 1774.311474] ---[ end trace a56b661c1598b0fc ]---
[ 1774.316202] Kernel panic - not syncing: Fatal exception
[ 1774.321497] Pid: 30881, comm: hackbench Tainted: G      D    2.6.31-rc8-tip-01308-g484d664-dirty #1629
[ 1774.330925] Call Trace:
[ 1774.333402]  [<ffffffff81561aaa>] panic+0x7a/0x125
[ 1774.338269]  [<ffffffff815645d2>] oops_end+0xaa/0xba
[ 1774.343321]  [<ffffffff8100f4f1>] die+0x5a/0x63
[ 1774.347887]  [<ffffffff81563ff6>] do_trap+0x110/0x11f
[ 1774.353052]  [<ffffffff8100d8ab>] do_divide_error+0x90/0x99
[ 1774.358691]  [<ffffffff81041c38>] ? sched_balance_self+0x19b/0x2d4
[ 1774.364966]  [<ffffffff810d8021>] ? zone_statistics+0x65/0x6a
[ 1774.370831]  [<ffffffff810cb2ef>] ? get_page_from_freelist+0x4a2/0x675
[ 1774.377487]  [<ffffffff8100cad5>] divide_error+0x15/0x20
[ 1774.382894]  [<ffffffff81041c38>] ? sched_balance_self+0x19b/0x2d4
[ 1774.389173]  [<ffffffff81041c21>] ? sched_balance_self+0x184/0x2d4
[ 1774.395479]  [<ffffffff810444c4>] sched_fork+0x2c/0x15f
[ 1774.400792]  [<ffffffff8104942d>] copy_process+0x407/0xda7
[ 1774.406397]  [<ffffffff81049f16>] do_fork+0x149/0x309
[ 1774.411562]  [<ffffffff8120ff12>] ? __up_read+0x9e/0xa8
[ 1774.416897]  [<ffffffff8106df32>] ? up_read+0xe/0x10
[ 1774.421957]  [<ffffffff81565d66>] ? do_page_fault+0x291/0x2c3
[ 1774.427815]  [<ffffffff81035028>] sys32_clone+0x2c/0x2e
[ 1774.433124]  [<ffffffff81034d05>] ia32_ptregs_common+0x25/0x4c

config attached as well.

the domain setup is this:

 SD flag: 4717
 +   1: SD_LOAD_BALANCE:          Do load balancing on this domain
 -   2: SD_BALANCE_NEWIDLE:       Balance when about to become idle
 +   4: SD_BALANCE_EXEC:          Balance on exec
 +   8: SD_BALANCE_FORK:          Balance on fork, clone
 -  16: SD_WAKE_IDLE:             Wake to idle CPU on task wakeup
 +  32: SD_WAKE_AFFINE:           Wake task to waking CPU
 +  64: SD_WAKE_BALANCE:          Perform balancing at task wakeup
 + 512: SD_SHARE_PKG_RESOURCES:   Domain members share cpu pkg resources
 current val on cpu0/domain1:
 SD flag: 1133
 +   1: SD_LOAD_BALANCE:          Do load balancing on this domain
 -   2: SD_BALANCE_NEWIDLE:       Balance when about to become idle
 +   4: SD_BALANCE_EXEC:          Balance on exec
 +   8: SD_BALANCE_FORK:          Balance on fork, clone
 -  16: SD_WAKE_IDLE:             Wake to idle CPU on task wakeup
 +  32: SD_WAKE_AFFINE:           Wake task to waking CPU
 +  64: SD_WAKE_BALANCE:          Perform balancing at task wakeup
 +1024: SD_SERIALIZE:             Only a single load balancing instance

it's a 4x4 Opteron testbox.

	Ingo

[-- Attachment #2: config --]
[-- Type: text/plain, Size: 65208 bytes --]

#
# Automatically generated make config: don't edit
# Linux kernel version: 2.6.31-rc8
# Fri Sep  4 09:46:25 2009
#
CONFIG_64BIT=y
# CONFIG_X86_32 is not set
CONFIG_X86_64=y
CONFIG_X86=y
CONFIG_OUTPUT_FORMAT="elf64-x86-64"
CONFIG_ARCH_DEFCONFIG="arch/x86/configs/x86_64_defconfig"
CONFIG_GENERIC_TIME=y
CONFIG_GENERIC_CMOS_UPDATE=y
CONFIG_CLOCKSOURCE_WATCHDOG=y
CONFIG_GENERIC_CLOCKEVENTS=y
CONFIG_GENERIC_CLOCKEVENTS_BROADCAST=y
CONFIG_LOCKDEP_SUPPORT=y
CONFIG_STACKTRACE_SUPPORT=y
CONFIG_HAVE_LATENCYTOP_SUPPORT=y
CONFIG_FAST_CMPXCHG_LOCAL=y
CONFIG_MMU=y
CONFIG_ZONE_DMA=y
CONFIG_GENERIC_ISA_DMA=y
CONFIG_GENERIC_IOMAP=y
CONFIG_GENERIC_BUG=y
CONFIG_GENERIC_BUG_RELATIVE_POINTERS=y
CONFIG_GENERIC_HWEIGHT=y
CONFIG_ARCH_MAY_HAVE_PC_FDC=y
CONFIG_RWSEM_GENERIC_SPINLOCK=y
# CONFIG_RWSEM_XCHGADD_ALGORITHM is not set
CONFIG_ARCH_HAS_CPU_IDLE_WAIT=y
CONFIG_GENERIC_CALIBRATE_DELAY=y
CONFIG_GENERIC_TIME_VSYSCALL=y
CONFIG_ARCH_HAS_CPU_RELAX=y
CONFIG_ARCH_HAS_DEFAULT_IDLE=y
CONFIG_ARCH_HAS_CACHE_LINE_SIZE=y
CONFIG_HAVE_SETUP_PER_CPU_AREA=y
CONFIG_HAVE_DYNAMIC_PER_CPU_AREA=y
CONFIG_HAVE_CPUMASK_OF_CPU_MAP=y
CONFIG_ARCH_HIBERNATION_POSSIBLE=y
CONFIG_ARCH_SUSPEND_POSSIBLE=y
CONFIG_ZONE_DMA32=y
CONFIG_ARCH_POPULATES_NODE_MAP=y
CONFIG_AUDIT_ARCH=y
CONFIG_ARCH_SUPPORTS_OPTIMIZED_INLINING=y
CONFIG_ARCH_SUPPORTS_DEBUG_PAGEALLOC=y
CONFIG_HAVE_INTEL_TXT=y
CONFIG_GENERIC_HARDIRQS=y
CONFIG_GENERIC_HARDIRQS_NO__DO_IRQ=y
CONFIG_GENERIC_IRQ_PROBE=y
CONFIG_GENERIC_PENDING_IRQ=y
CONFIG_USE_GENERIC_SMP_HELPERS=y
CONFIG_X86_64_SMP=y
CONFIG_X86_HT=y
CONFIG_X86_TRAMPOLINE=y
# CONFIG_KTIME_SCALAR is not set
CONFIG_BOOTPARAM_SUPPORT_NOT_WANTED=y
CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config"
CONFIG_CONSTRUCTORS=y

#
# General setup
#
CONFIG_EXPERIMENTAL=y
# CONFIG_BROKEN_BOOT_ALLOWED4 is not set
# CONFIG_BROKEN_BOOT_EUROPE is not set
# CONFIG_BROKEN_BOOT_TITAN is not set
CONFIG_LOCK_KERNEL=y
CONFIG_INIT_ENV_ARG_LIMIT=32
CONFIG_LOCALVERSION=""
CONFIG_LOCALVERSION_AUTO=y
CONFIG_HAVE_KERNEL_GZIP=y
CONFIG_HAVE_KERNEL_BZIP2=y
CONFIG_HAVE_KERNEL_LZMA=y
CONFIG_KERNEL_GZIP=y
# CONFIG_KERNEL_BZIP2 is not set
# CONFIG_KERNEL_LZMA is not set
CONFIG_SWAP=y
CONFIG_SYSVIPC=y
CONFIG_SYSVIPC_SYSCTL=y
CONFIG_POSIX_MQUEUE=y
CONFIG_POSIX_MQUEUE_SYSCTL=y
CONFIG_BSD_PROCESS_ACCT=y
# CONFIG_BSD_PROCESS_ACCT_V3 is not set
CONFIG_TASKSTATS=y
CONFIG_TASK_DELAY_ACCT=y
CONFIG_TASK_XACCT=y
CONFIG_TASK_IO_ACCOUNTING=y
CONFIG_AUDIT=y
CONFIG_AUDITSYSCALL=y
CONFIG_AUDIT_TREE=y

#
# RCU Subsystem
#
CONFIG_TREE_RCU=y
# CONFIG_TREE_PREEMPT_RCU is not set
# CONFIG_RCU_TRACE is not set
CONFIG_RCU_FANOUT=64
# CONFIG_RCU_FANOUT_EXACT is not set
# CONFIG_TREE_RCU_TRACE is not set
# CONFIG_IKCONFIG is not set
CONFIG_LOG_BUF_SHIFT=18
CONFIG_HAVE_UNSTABLE_SCHED_CLOCK=y
CONFIG_GROUP_SCHED=y
CONFIG_FAIR_GROUP_SCHED=y
# CONFIG_RT_GROUP_SCHED is not set
# CONFIG_USER_SCHED is not set
CONFIG_CGROUP_SCHED=y
CONFIG_CGROUPS=y
# CONFIG_CGROUP_DEBUG is not set
CONFIG_CGROUP_NS=y
CONFIG_CGROUP_FREEZER=y
# CONFIG_CGROUP_DEVICE is not set
CONFIG_CPUSETS=y
CONFIG_PROC_PID_CPUSET=y
CONFIG_CGROUP_CPUACCT=y
CONFIG_RESOURCE_COUNTERS=y
# CONFIG_CGROUP_MEM_RES_CTLR is not set
CONFIG_SYSFS_DEPRECATED=y
# CONFIG_SYSFS_DEPRECATED_V2 is not set
CONFIG_RELAY=y
CONFIG_NAMESPACES=y
CONFIG_UTS_NS=y
CONFIG_IPC_NS=y
CONFIG_USER_NS=y
CONFIG_PID_NS=y
CONFIG_NET_NS=y
CONFIG_BLK_DEV_INITRD=y
CONFIG_INITRAMFS_SOURCE=""
CONFIG_RD_GZIP=y
CONFIG_RD_BZIP2=y
CONFIG_RD_LZMA=y
CONFIG_CC_OPTIMIZE_FOR_SIZE=y
CONFIG_SYSCTL=y
CONFIG_ANON_INODES=y
# CONFIG_EMBEDDED is not set
CONFIG_UID16=y
CONFIG_SYSCTL_SYSCALL=y
CONFIG_KALLSYMS=y
CONFIG_KALLSYMS_ALL=y
CONFIG_KALLSYMS_EXTRA_PASS=y
CONFIG_HOTPLUG=y
CONFIG_PRINTK=y
CONFIG_BUG=y
CONFIG_ELF_CORE=y
CONFIG_PCSPKR_PLATFORM=y
CONFIG_BASE_FULL=y
CONFIG_FUTEX=y
CONFIG_EPOLL=y
CONFIG_SIGNALFD=y
CONFIG_TIMERFD=y
CONFIG_EVENTFD=y
CONFIG_SHMEM=y
CONFIG_AIO=y
CONFIG_HAVE_PERF_COUNTERS=y

#
# Performance Counters
#
CONFIG_PERF_COUNTERS=y
CONFIG_EVENT_PROFILE=y
CONFIG_VM_EVENT_COUNTERS=y
CONFIG_PCI_QUIRKS=y
CONFIG_SLUB_DEBUG=y
# CONFIG_STRIP_ASM_SYMS is not set
# CONFIG_COMPAT_BRK is not set
# CONFIG_SLAB is not set
CONFIG_SLUB=y
# CONFIG_SLOB is not set
CONFIG_PROFILING=y
CONFIG_TRACEPOINTS=y
CONFIG_MARKERS=y
# CONFIG_OPROFILE is not set
CONFIG_HAVE_OPROFILE=y
CONFIG_KPROBES=y
CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS=y
CONFIG_KRETPROBES=y
CONFIG_HAVE_IOREMAP_PROT=y
CONFIG_HAVE_KPROBES=y
CONFIG_HAVE_KRETPROBES=y
CONFIG_HAVE_ARCH_TRACEHOOK=y
CONFIG_HAVE_DMA_ATTRS=y
CONFIG_HAVE_DMA_API_DEBUG=y
CONFIG_HAVE_HW_BREAKPOINT=y

#
# GCOV-based kernel profiling
#
# CONFIG_SLOW_WORK is not set
# CONFIG_HAVE_GENERIC_DMA_COHERENT is not set
CONFIG_SLABINFO=y
CONFIG_RT_MUTEXES=y
CONFIG_BASE_SMALL=0
CONFIG_MODULES=y
# CONFIG_MODULE_FORCE_LOAD is not set
CONFIG_MODULE_UNLOAD=y
CONFIG_MODULE_FORCE_UNLOAD=y
# CONFIG_MODVERSIONS is not set
# CONFIG_MODULE_SRCVERSION_ALL is not set
CONFIG_STOP_MACHINE=y
CONFIG_BLOCK=y
CONFIG_BLK_DEV_BSG=y
# CONFIG_BLK_DEV_INTEGRITY is not set
CONFIG_BLOCK_COMPAT=y

#
# IO Schedulers
#
CONFIG_IOSCHED_NOOP=y
CONFIG_IOSCHED_AS=y
CONFIG_IOSCHED_DEADLINE=y
CONFIG_IOSCHED_CFQ=y
# CONFIG_DEFAULT_AS is not set
# CONFIG_DEFAULT_DEADLINE is not set
CONFIG_DEFAULT_CFQ=y
# CONFIG_DEFAULT_NOOP is not set
CONFIG_DEFAULT_IOSCHED="cfq"
CONFIG_FREEZER=y

#
# Processor type and features
#
CONFIG_TICK_ONESHOT=y
CONFIG_NO_HZ=y
CONFIG_HIGH_RES_TIMERS=y
CONFIG_GENERIC_CLOCKEVENTS_BUILD=y
# CONFIG_SMP_SUPPORT is not set
CONFIG_SPARSE_IRQ=y
CONFIG_NUMA_IRQ_DESC=y
CONFIG_X86_MPPARSE=y
CONFIG_X86_EXTENDED_PLATFORM=y
# CONFIG_X86_VSMP is not set
CONFIG_SCHED_OMIT_FRAME_POINTER=y
# CONFIG_PARAVIRT_GUEST is not set
# CONFIG_MEMTEST is not set
# CONFIG_M386 is not set
# CONFIG_M486 is not set
# CONFIG_M586 is not set
# CONFIG_M586TSC is not set
# CONFIG_M586MMX is not set
# CONFIG_M686 is not set
# CONFIG_MPENTIUMII is not set
# CONFIG_MPENTIUMIII is not set
# CONFIG_MPENTIUMM is not set
# CONFIG_MPENTIUM4 is not set
# CONFIG_MK6 is not set
# CONFIG_MK7 is not set
# CONFIG_MK8 is not set
# CONFIG_MCRUSOE is not set
# CONFIG_MEFFICEON is not set
# CONFIG_MWINCHIPC6 is not set
# CONFIG_MWINCHIP3D is not set
# CONFIG_MGEODEGX1 is not set
# CONFIG_MGEODE_LX is not set
# CONFIG_MCYRIXIII is not set
# CONFIG_MVIAC3_2 is not set
# CONFIG_MVIAC7 is not set
# CONFIG_MPSC is not set
# CONFIG_MCORE2 is not set
# CONFIG_MATOM is not set
CONFIG_GENERIC_CPU=y
CONFIG_X86_CPU=y
CONFIG_X86_L1_CACHE_BYTES=64
CONFIG_X86_INTERNODE_CACHE_BYTES=64
CONFIG_X86_CMPXCHG=y
CONFIG_X86_L1_CACHE_SHIFT=6
CONFIG_X86_WP_WORKS_OK=y
CONFIG_X86_TSC=y
CONFIG_X86_CMPXCHG64=y
CONFIG_X86_CMOV=y
CONFIG_X86_MINIMUM_CPU_FAMILY=64
CONFIG_X86_DEBUGCTLMSR=y
CONFIG_CPU_SUP_INTEL=y
CONFIG_CPU_SUP_AMD=y
CONFIG_CPU_SUP_CENTAUR=y
# CONFIG_X86_DS is not set
CONFIG_HPET_TIMER=y
CONFIG_HPET_EMULATE_RTC=y
CONFIG_DMI=y
CONFIG_GART_IOMMU=y
CONFIG_CALGARY_IOMMU=y
CONFIG_CALGARY_IOMMU_ENABLED_BY_DEFAULT=y
CONFIG_AMD_IOMMU=y
CONFIG_AMD_IOMMU_STATS=y
CONFIG_SWIOTLB=y
CONFIG_IOMMU_HELPER=y
CONFIG_IOMMU_API=y
# CONFIG_MAXSMP is not set
CONFIG_NR_CPUS=64
CONFIG_SCHED_SMT=y
CONFIG_SCHED_MC=y
# CONFIG_PREEMPT_NONE is not set
CONFIG_PREEMPT_VOLUNTARY=y
# CONFIG_PREEMPT is not set
CONFIG_X86_LOCAL_APIC=y
CONFIG_X86_IO_APIC=y
CONFIG_X86_REROUTE_FOR_BROKEN_BOOT_IRQS=y
CONFIG_X86_MCE=y
CONFIG_X86_MCE_INTEL=y
CONFIG_X86_MCE_AMD=y
CONFIG_X86_MCE_THRESHOLD=y
# CONFIG_X86_MCE_INJECT is not set
CONFIG_X86_THERMAL_VECTOR=y
# CONFIG_I8K is not set
CONFIG_MICROCODE=y
CONFIG_MICROCODE_INTEL=y
CONFIG_MICROCODE_AMD=y
CONFIG_MICROCODE_OLD_INTERFACE=y
CONFIG_X86_MSR=y
CONFIG_X86_CPUID=y
CONFIG_X86_CPU_DEBUG=y
# CONFIG_UP_WANTED_1 is not set
CONFIG_SMP=y
CONFIG_ARCH_PHYS_ADDR_T_64BIT=y
CONFIG_DIRECT_GBPAGES=y
CONFIG_NUMA=y
CONFIG_K8_NUMA=y
CONFIG_X86_64_ACPI_NUMA=y
CONFIG_NODES_SPAN_OTHER_NODES=y
# CONFIG_NUMA_EMU is not set
CONFIG_NODES_SHIFT=6
CONFIG_ARCH_SPARSEMEM_DEFAULT=y
CONFIG_ARCH_SPARSEMEM_ENABLE=y
CONFIG_ARCH_SELECT_MEMORY_MODEL=y
CONFIG_ILLEGAL_POINTER_VALUE=0xdead000000000000
CONFIG_SELECT_MEMORY_MODEL=y
# CONFIG_FLATMEM_MANUAL is not set
# CONFIG_DISCONTIGMEM_MANUAL is not set
CONFIG_SPARSEMEM_MANUAL=y
CONFIG_SPARSEMEM=y
CONFIG_NEED_MULTIPLE_NODES=y
CONFIG_HAVE_MEMORY_PRESENT=y
CONFIG_SPARSEMEM_EXTREME=y
CONFIG_SPARSEMEM_VMEMMAP_ENABLE=y
CONFIG_SPARSEMEM_VMEMMAP=y

#
# Memory hotplug is currently incompatible with Software Suspend
#
CONFIG_PAGEFLAGS_EXTENDED=y
CONFIG_SPLIT_PTLOCK_CPUS=4
CONFIG_MIGRATION=y
CONFIG_PHYS_ADDR_T_64BIT=y
CONFIG_ZONE_DMA_FLAG=1
CONFIG_BOUNCE=y
CONFIG_VIRT_TO_BUS=y
CONFIG_HAVE_MLOCK=y
CONFIG_HAVE_MLOCKED_PAGE_BIT=y
CONFIG_DEFAULT_MMAP_MIN_ADDR=4096
CONFIG_X86_CHECK_BIOS_CORRUPTION=y
CONFIG_X86_BOOTPARAM_MEMORY_CORRUPTION_CHECK=y
CONFIG_X86_RESERVE_LOW_64K=y
CONFIG_MTRR=y
# CONFIG_MTRR_SANITIZER is not set
CONFIG_X86_PAT=y
CONFIG_ARCH_USES_PG_UNCACHED=y
CONFIG_EFI=y
CONFIG_SECCOMP=y
# CONFIG_CC_STACKPROTECTOR is not set
# CONFIG_HZ_100 is not set
# CONFIG_HZ_250 is not set
# CONFIG_HZ_300 is not set
CONFIG_HZ_1000=y
CONFIG_HZ=1000
CONFIG_SCHED_HRTICK=y
CONFIG_KEXEC=y
CONFIG_CRASH_DUMP=y
# CONFIG_KEXEC_JUMP is not set
CONFIG_PHYSICAL_START=0x1000000
# CONFIG_RELOCATABLE is not set
CONFIG_PHYSICAL_ALIGN=0x1000000
CONFIG_HOTPLUG_CPU=y
# CONFIG_COMPAT_VDSO is not set
# CONFIG_CMDLINE_BOOL is not set
CONFIG_ARCH_ENABLE_MEMORY_HOTPLUG=y
CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID=y

#
# Power management and ACPI options
#
CONFIG_ARCH_HIBERNATION_HEADER=y
CONFIG_PM=y
CONFIG_PM_DEBUG=y
# CONFIG_PM_VERBOSE is not set
CONFIG_CAN_PM_TRACE=y
CONFIG_PM_TRACE=y
CONFIG_PM_TRACE_RTC=y
CONFIG_PM_SLEEP_SMP=y
CONFIG_PM_SLEEP=y
CONFIG_SUSPEND=y
CONFIG_SUSPEND_FREEZER=y
CONFIG_HIBERNATION_NVS=y
CONFIG_HIBERNATION=y
CONFIG_PM_STD_PARTITION=""
CONFIG_ACPI=y
CONFIG_ACPI_SLEEP=y
CONFIG_ACPI_PROCFS=y
CONFIG_ACPI_PROCFS_POWER=y
CONFIG_ACPI_SYSFS_POWER=y
CONFIG_ACPI_PROC_EVENT=y
CONFIG_ACPI_AC=y
CONFIG_ACPI_BATTERY=y
CONFIG_ACPI_BUTTON=y
CONFIG_ACPI_VIDEO=y
CONFIG_ACPI_FAN=y
CONFIG_ACPI_DOCK=y
CONFIG_ACPI_PROCESSOR=y
CONFIG_ACPI_HOTPLUG_CPU=y
CONFIG_ACPI_THERMAL=y
CONFIG_ACPI_NUMA=y
# CONFIG_ACPI_CUSTOM_DSDT is not set
CONFIG_ACPI_BLACKLIST_YEAR=0
# CONFIG_ACPI_DEBUG is not set
# CONFIG_ACPI_PCI_SLOT is not set
CONFIG_X86_PM_TIMER=y
CONFIG_ACPI_CONTAINER=y
# CONFIG_ACPI_SBS is not set

#
# CPU Frequency scaling
#
CONFIG_CPU_FREQ=y
CONFIG_CPU_FREQ_TABLE=y
CONFIG_CPU_FREQ_DEBUG=y
# CONFIG_CPU_FREQ_STAT is not set
# CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE is not set
# CONFIG_CPU_FREQ_DEFAULT_GOV_POWERSAVE is not set
CONFIG_CPU_FREQ_DEFAULT_GOV_USERSPACE=y
# CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND is not set
# CONFIG_CPU_FREQ_DEFAULT_GOV_CONSERVATIVE is not set
CONFIG_CPU_FREQ_GOV_PERFORMANCE=y
# CONFIG_CPU_FREQ_GOV_POWERSAVE is not set
CONFIG_CPU_FREQ_GOV_USERSPACE=y
CONFIG_CPU_FREQ_GOV_ONDEMAND=y
# CONFIG_CPU_FREQ_GOV_CONSERVATIVE is not set

#
# CPUFreq processor drivers
#
CONFIG_X86_ACPI_CPUFREQ=y
# CONFIG_X86_POWERNOW_K8 is not set
# CONFIG_X86_SPEEDSTEP_CENTRINO is not set
# CONFIG_X86_P4_CLOCKMOD is not set

#
# shared options
#
# CONFIG_X86_SPEEDSTEP_LIB is not set
CONFIG_CPU_IDLE=y
CONFIG_CPU_IDLE_GOV_LADDER=y
CONFIG_CPU_IDLE_GOV_MENU=y

#
# Memory power savings
#
# CONFIG_I7300_IDLE is not set

#
# Bus options (PCI etc.)
#
CONFIG_PCI=y
CONFIG_PCI_DIRECT=y
CONFIG_PCI_MMCONFIG=y
CONFIG_PCI_DOMAINS=y
CONFIG_DMAR=y
# CONFIG_DMAR_DEFAULT_ON is not set
# CONFIG_DMAR_BROKEN_GFX_WA is not set
CONFIG_DMAR_FLOPPY_WA=y
# CONFIG_INTR_REMAP is not set
CONFIG_PCIEPORTBUS=y
# CONFIG_HOTPLUG_PCI_PCIE is not set
CONFIG_PCIEAER=y
# CONFIG_PCIE_ECRC is not set
# CONFIG_PCIEAER_INJECT is not set
# CONFIG_PCIEASPM is not set
CONFIG_ARCH_SUPPORTS_MSI=y
CONFIG_PCI_MSI=y
# CONFIG_PCI_LEGACY is not set
# CONFIG_PCI_DEBUG is not set
# CONFIG_PCI_STUB is not set
CONFIG_HT_IRQ=y
# CONFIG_PCI_IOV is not set
CONFIG_ISA_DMA_API=y
CONFIG_K8_NB=y
CONFIG_PCCARD=y
# CONFIG_PCMCIA_DEBUG is not set
CONFIG_PCMCIA=y
CONFIG_PCMCIA_LOAD_CIS=y
CONFIG_PCMCIA_IOCTL=y
CONFIG_CARDBUS=y

#
# PC-card bridges
#
CONFIG_YENTA=y
CONFIG_YENTA_O2=y
CONFIG_YENTA_RICOH=y
CONFIG_YENTA_TI=y
CONFIG_YENTA_ENE_TUNE=y
CONFIG_YENTA_TOSHIBA=y
# CONFIG_PD6729 is not set
# CONFIG_I82092 is not set
CONFIG_PCCARD_NONSTATIC=y
CONFIG_HOTPLUG_PCI=y
# CONFIG_HOTPLUG_PCI_FAKE is not set
# CONFIG_HOTPLUG_PCI_ACPI is not set
# CONFIG_HOTPLUG_PCI_CPCI is not set
# CONFIG_HOTPLUG_PCI_SHPC is not set

#
# Executable file formats / Emulations
#
CONFIG_BINFMT_ELF=y
CONFIG_COMPAT_BINFMT_ELF=y
CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS=y
# CONFIG_HAVE_AOUT is not set
CONFIG_BINFMT_MISC=y
CONFIG_IA32_EMULATION=y
# CONFIG_IA32_AOUT is not set
CONFIG_COMPAT=y
CONFIG_COMPAT_FOR_U64_ALIGNMENT=y
CONFIG_SYSVIPC_COMPAT=y
CONFIG_NET=y

#
# Networking options
#
CONFIG_PACKET=y
CONFIG_PACKET_MMAP=y
CONFIG_UNIX=y
CONFIG_XFRM=y
CONFIG_XFRM_USER=y
# CONFIG_XFRM_SUB_POLICY is not set
# CONFIG_XFRM_MIGRATE is not set
# CONFIG_XFRM_STATISTICS is not set
# CONFIG_NET_KEY is not set
CONFIG_INET=y
CONFIG_IP_MULTICAST=y
CONFIG_IP_ADVANCED_ROUTER=y
CONFIG_ASK_IP_FIB_HASH=y
# CONFIG_IP_FIB_TRIE is not set
CONFIG_IP_FIB_HASH=y
CONFIG_IP_MULTIPLE_TABLES=y
CONFIG_IP_ROUTE_MULTIPATH=y
CONFIG_IP_ROUTE_VERBOSE=y
CONFIG_IP_PNP=y
CONFIG_IP_PNP_DHCP=y
CONFIG_IP_PNP_BOOTP=y
CONFIG_IP_PNP_RARP=y
# CONFIG_NET_IPIP is not set
# CONFIG_NET_IPGRE is not set
CONFIG_IP_MROUTE=y
CONFIG_IP_PIMSM_V1=y
CONFIG_IP_PIMSM_V2=y
# CONFIG_ARPD is not set
CONFIG_SYN_COOKIES=y
# CONFIG_INET_AH is not set
# CONFIG_INET_ESP is not set
# CONFIG_INET_IPCOMP is not set
# CONFIG_INET_XFRM_TUNNEL is not set
CONFIG_INET_TUNNEL=y
# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
# CONFIG_INET_XFRM_MODE_TUNNEL is not set
# CONFIG_INET_XFRM_MODE_BEET is not set
CONFIG_INET_LRO=y
# CONFIG_INET_DIAG is not set
CONFIG_TCP_CONG_ADVANCED=y
# CONFIG_TCP_CONG_BIC is not set
CONFIG_TCP_CONG_CUBIC=y
# CONFIG_TCP_CONG_WESTWOOD is not set
# CONFIG_TCP_CONG_HTCP is not set
# CONFIG_TCP_CONG_HSTCP is not set
# CONFIG_TCP_CONG_HYBLA is not set
# CONFIG_TCP_CONG_VEGAS is not set
# CONFIG_TCP_CONG_SCALABLE is not set
# CONFIG_TCP_CONG_LP is not set
# CONFIG_TCP_CONG_VENO is not set
# CONFIG_TCP_CONG_YEAH is not set
# CONFIG_TCP_CONG_ILLINOIS is not set
# CONFIG_DEFAULT_BIC is not set
CONFIG_DEFAULT_CUBIC=y
# CONFIG_DEFAULT_HTCP is not set
# CONFIG_DEFAULT_VEGAS is not set
# CONFIG_DEFAULT_WESTWOOD is not set
# CONFIG_DEFAULT_RENO is not set
CONFIG_DEFAULT_TCP_CONG="cubic"
CONFIG_TCP_MD5SIG=y
CONFIG_IPV6=y
# CONFIG_IPV6_PRIVACY is not set
# CONFIG_IPV6_ROUTER_PREF is not set
# CONFIG_IPV6_OPTIMISTIC_DAD is not set
CONFIG_INET6_AH=y
CONFIG_INET6_ESP=y
# CONFIG_INET6_IPCOMP is not set
# CONFIG_IPV6_MIP6 is not set
# CONFIG_INET6_XFRM_TUNNEL is not set
# CONFIG_INET6_TUNNEL is not set
CONFIG_INET6_XFRM_MODE_TRANSPORT=y
CONFIG_INET6_XFRM_MODE_TUNNEL=y
CONFIG_INET6_XFRM_MODE_BEET=y
# CONFIG_INET6_XFRM_MODE_ROUTEOPTIMIZATION is not set
CONFIG_IPV6_SIT=y
CONFIG_IPV6_NDISC_NODETYPE=y
# CONFIG_IPV6_TUNNEL is not set
# CONFIG_IPV6_MULTIPLE_TABLES is not set
# CONFIG_IPV6_MROUTE is not set
CONFIG_NETLABEL=y
CONFIG_NETWORK_SECMARK=y
CONFIG_NETFILTER=y
# CONFIG_NETFILTER_DEBUG is not set
# CONFIG_NETFILTER_ADVANCED is not set

#
# Core Netfilter Configuration
#
CONFIG_NETFILTER_NETLINK=y
CONFIG_NETFILTER_NETLINK_LOG=y
CONFIG_NF_CONNTRACK=y
CONFIG_NF_CONNTRACK_SECMARK=y
CONFIG_NF_CONNTRACK_FTP=y
CONFIG_NF_CONNTRACK_IRC=y
CONFIG_NF_CONNTRACK_SIP=y
CONFIG_NF_CT_NETLINK=y
CONFIG_NETFILTER_XTABLES=y
CONFIG_NETFILTER_XT_TARGET_CONNSECMARK=y
CONFIG_NETFILTER_XT_TARGET_MARK=y
CONFIG_NETFILTER_XT_TARGET_NFLOG=y
CONFIG_NETFILTER_XT_TARGET_SECMARK=y
CONFIG_NETFILTER_XT_TARGET_TCPMSS=y
CONFIG_NETFILTER_XT_MATCH_CONNTRACK=y
CONFIG_NETFILTER_XT_MATCH_MARK=y
CONFIG_NETFILTER_XT_MATCH_POLICY=y
CONFIG_NETFILTER_XT_MATCH_STATE=y
# CONFIG_IP_VS is not set

#
# IP: Netfilter Configuration
#
CONFIG_NF_DEFRAG_IPV4=y
CONFIG_NF_CONNTRACK_IPV4=y
CONFIG_NF_CONNTRACK_PROC_COMPAT=y
CONFIG_IP_NF_IPTABLES=y
CONFIG_IP_NF_FILTER=y
CONFIG_IP_NF_TARGET_REJECT=y
CONFIG_IP_NF_TARGET_LOG=y
CONFIG_IP_NF_TARGET_ULOG=y
CONFIG_NF_NAT=y
CONFIG_NF_NAT_NEEDED=y
CONFIG_IP_NF_TARGET_MASQUERADE=y
CONFIG_NF_NAT_FTP=y
CONFIG_NF_NAT_IRC=y
# CONFIG_NF_NAT_TFTP is not set
# CONFIG_NF_NAT_AMANDA is not set
# CONFIG_NF_NAT_PPTP is not set
# CONFIG_NF_NAT_H323 is not set
CONFIG_NF_NAT_SIP=y
CONFIG_IP_NF_MANGLE=y

#
# IPv6: Netfilter Configuration
#
CONFIG_NF_CONNTRACK_IPV6=y
CONFIG_IP6_NF_IPTABLES=y
CONFIG_IP6_NF_MATCH_IPV6HEADER=y
CONFIG_IP6_NF_TARGET_LOG=y
CONFIG_IP6_NF_FILTER=y
CONFIG_IP6_NF_TARGET_REJECT=y
CONFIG_IP6_NF_MANGLE=y
# CONFIG_IP_DCCP is not set
# CONFIG_IP_SCTP is not set
# CONFIG_TIPC is not set
# CONFIG_ATM is not set
# CONFIG_BRIDGE is not set
# CONFIG_NET_DSA is not set
# CONFIG_VLAN_8021Q is not set
# CONFIG_DECNET is not set
CONFIG_LLC=y
# CONFIG_LLC2 is not set
# CONFIG_IPX is not set
# CONFIG_ATALK is not set
# CONFIG_X25 is not set
# CONFIG_LAPB is not set
# CONFIG_ECONET is not set
# CONFIG_WAN_ROUTER is not set
# CONFIG_PHONET is not set
# CONFIG_IEEE802154 is not set
CONFIG_NET_SCHED=y

#
# Queueing/Scheduling
#
# CONFIG_NET_SCH_CBQ is not set
# CONFIG_NET_SCH_HTB is not set
# CONFIG_NET_SCH_HFSC is not set
# CONFIG_NET_SCH_PRIO is not set
# CONFIG_NET_SCH_MULTIQ is not set
# CONFIG_NET_SCH_RED is not set
# CONFIG_NET_SCH_SFQ is not set
# CONFIG_NET_SCH_TEQL is not set
# CONFIG_NET_SCH_TBF is not set
# CONFIG_NET_SCH_GRED is not set
# CONFIG_NET_SCH_DSMARK is not set
# CONFIG_NET_SCH_NETEM is not set
# CONFIG_NET_SCH_DRR is not set
# CONFIG_NET_SCH_INGRESS is not set

#
# Classification
#
CONFIG_NET_CLS=y
# CONFIG_NET_CLS_BASIC is not set
# CONFIG_NET_CLS_TCINDEX is not set
# CONFIG_NET_CLS_ROUTE4 is not set
# CONFIG_NET_CLS_FW is not set
# CONFIG_NET_CLS_U32 is not set
# CONFIG_NET_CLS_RSVP is not set
# CONFIG_NET_CLS_RSVP6 is not set
# CONFIG_NET_CLS_FLOW is not set
# CONFIG_NET_CLS_CGROUP is not set
CONFIG_NET_EMATCH=y
CONFIG_NET_EMATCH_STACK=32
# CONFIG_NET_EMATCH_CMP is not set
# CONFIG_NET_EMATCH_NBYTE is not set
# CONFIG_NET_EMATCH_U32 is not set
# CONFIG_NET_EMATCH_META is not set
# CONFIG_NET_EMATCH_TEXT is not set
CONFIG_NET_CLS_ACT=y
# CONFIG_NET_ACT_POLICE is not set
# CONFIG_NET_ACT_GACT is not set
# CONFIG_NET_ACT_MIRRED is not set
# CONFIG_NET_ACT_IPT is not set
# CONFIG_NET_ACT_NAT is not set
# CONFIG_NET_ACT_PEDIT is not set
# CONFIG_NET_ACT_SIMP is not set
# CONFIG_NET_ACT_SKBEDIT is not set
CONFIG_NET_SCH_FIFO=y
# CONFIG_DCB is not set

#
# Network testing
#
# CONFIG_NET_PKTGEN is not set
# CONFIG_NET_TCPPROBE is not set
# CONFIG_NET_DROP_MONITOR is not set
CONFIG_HAMRADIO=y

#
# Packet Radio protocols
#
# CONFIG_AX25 is not set
# CONFIG_CAN is not set
# CONFIG_IRDA is not set
# CONFIG_BT is not set
# CONFIG_AF_RXRPC is not set
CONFIG_FIB_RULES=y
# CONFIG_WIRELESS is not set
# CONFIG_WIMAX is not set
CONFIG_RFKILL=y
CONFIG_RFKILL_LEDS=y
CONFIG_RFKILL_INPUT=y

#
# Device Drivers
#

#
# Generic Driver Options
#
CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
CONFIG_STANDALONE=y
CONFIG_PREVENT_FIRMWARE_BUILD=y
CONFIG_FW_LOADER=y
CONFIG_FIRMWARE_IN_KERNEL=y
CONFIG_EXTRA_FIRMWARE=""
# CONFIG_DEBUG_DRIVER is not set
CONFIG_DEBUG_DEVRES=y
# CONFIG_SYS_HYPERVISOR is not set
CONFIG_CONNECTOR=y
CONFIG_PROC_EVENTS=y
# CONFIG_PARPORT is not set
CONFIG_PNP=y
CONFIG_PNP_DEBUG_MESSAGES=y

#
# Protocols
#
CONFIG_PNPACPI=y
CONFIG_BLK_DEV=y
# CONFIG_BLK_DEV_FD is not set
CONFIG_BLK_CPQ_DA=y
# CONFIG_BLK_CPQ_CISS_DA is not set
# CONFIG_BLK_DEV_DAC960 is not set
# CONFIG_BLK_DEV_UMEM is not set
# CONFIG_BLK_DEV_COW_COMMON is not set
CONFIG_BLK_DEV_LOOP=y
# CONFIG_BLK_DEV_CRYPTOLOOP is not set
# CONFIG_BLK_DEV_NBD is not set
# CONFIG_BLK_DEV_SX8 is not set
# CONFIG_BLK_DEV_UB is not set
CONFIG_BLK_DEV_RAM=y
CONFIG_BLK_DEV_RAM_COUNT=16
CONFIG_BLK_DEV_RAM_SIZE=16384
# CONFIG_BLK_DEV_XIP is not set
# CONFIG_CDROM_PKTCDVD is not set
# CONFIG_ATA_OVER_ETH is not set
# CONFIG_BLK_DEV_HD is not set
CONFIG_MISC_DEVICES=y
# CONFIG_IBM_ASM is not set
# CONFIG_PHANTOM is not set
# CONFIG_SGI_IOC4 is not set
# CONFIG_TIFM_CORE is not set
# CONFIG_ICS932S401 is not set
# CONFIG_ENCLOSURE_SERVICES is not set
# CONFIG_HP_ILO is not set
# CONFIG_ISL29003 is not set
# CONFIG_C2PORT is not set

#
# EEPROM support
#
# CONFIG_EEPROM_AT24 is not set
# CONFIG_EEPROM_LEGACY is not set
# CONFIG_EEPROM_MAX6875 is not set
# CONFIG_EEPROM_93CX6 is not set
# CONFIG_CB710_CORE is not set
CONFIG_HAVE_IDE=y

#
# SCSI device support
#
# CONFIG_RAID_ATTRS is not set
CONFIG_SCSI=y
CONFIG_SCSI_DMA=y
# CONFIG_SCSI_TGT is not set
# CONFIG_SCSI_NETLINK is not set
CONFIG_SCSI_PROC_FS=y

#
# SCSI support type (disk, tape, CD-ROM)
#
CONFIG_BLK_DEV_SD=y
# CONFIG_CHR_DEV_ST is not set
# CONFIG_CHR_DEV_OSST is not set
CONFIG_BLK_DEV_SR=y
CONFIG_BLK_DEV_SR_VENDOR=y
CONFIG_CHR_DEV_SG=y
# CONFIG_CHR_DEV_SCH is not set
# CONFIG_SCSI_MULTI_LUN is not set
CONFIG_SCSI_CONSTANTS=y
# CONFIG_SCSI_LOGGING is not set
# CONFIG_SCSI_SCAN_ASYNC is not set
CONFIG_SCSI_WAIT_SCAN=m

#
# SCSI Transports
#
CONFIG_SCSI_SPI_ATTRS=y
# CONFIG_SCSI_FC_ATTRS is not set
# CONFIG_SCSI_ISCSI_ATTRS is not set
# CONFIG_SCSI_SAS_ATTRS is not set
# CONFIG_SCSI_SAS_LIBSAS is not set
# CONFIG_SCSI_LOWLEVEL is not set
CONFIG_SCSI_AIC7XXX=y
# CONFIG_SCSI_LOWLEVEL_PCMCIA is not set
# CONFIG_SCSI_DH is not set
# CONFIG_SCSI_OSD_INITIATOR is not set
CONFIG_ATA=y
# CONFIG_ATA_NONSTANDARD is not set
CONFIG_ATA_ACPI=y
CONFIG_SATA_PMP=y
CONFIG_SATA_AHCI=y
# CONFIG_SATA_SIL24 is not set
CONFIG_ATA_SFF=y
# CONFIG_SATA_SVW is not set
CONFIG_ATA_PIIX=y
# CONFIG_SATA_MV is not set
CONFIG_SATA_NV=y
# CONFIG_PDC_ADMA is not set
# CONFIG_SATA_QSTOR is not set
# CONFIG_SATA_PROMISE is not set
# CONFIG_SATA_SX4 is not set
# CONFIG_SATA_SIL is not set
# CONFIG_SATA_SIS is not set
# CONFIG_SATA_ULI is not set
# CONFIG_SATA_VIA is not set
# CONFIG_SATA_VITESSE is not set
# CONFIG_SATA_INIC162X is not set
# CONFIG_PATA_ACPI is not set
# CONFIG_PATA_ALI is not set
CONFIG_PATA_AMD=y
# CONFIG_PATA_ARTOP is not set
# CONFIG_PATA_ATIIXP is not set
# CONFIG_PATA_CMD640_PCI is not set
# CONFIG_PATA_CMD64X is not set
# CONFIG_PATA_CS5520 is not set
# CONFIG_PATA_CS5530 is not set
# CONFIG_PATA_CYPRESS is not set
# CONFIG_PATA_EFAR is not set
# CONFIG_ATA_GENERIC is not set
# CONFIG_PATA_HPT366 is not set
# CONFIG_PATA_HPT37X is not set
# CONFIG_PATA_HPT3X2N is not set
# CONFIG_PATA_HPT3X3 is not set
# CONFIG_PATA_IT821X is not set
# CONFIG_PATA_IT8213 is not set
# CONFIG_PATA_JMICRON is not set
# CONFIG_PATA_TRIFLEX is not set
# CONFIG_PATA_MARVELL is not set
# CONFIG_PATA_MPIIX is not set
CONFIG_PATA_OLDPIIX=y
# CONFIG_PATA_NETCELL is not set
# CONFIG_PATA_NINJA32 is not set
# CONFIG_PATA_NS87410 is not set
# CONFIG_PATA_NS87415 is not set
# CONFIG_PATA_OPTI is not set
# CONFIG_PATA_OPTIDMA is not set
# CONFIG_PATA_PCMCIA is not set
# CONFIG_PATA_PDC_OLD is not set
# CONFIG_PATA_RADISYS is not set
# CONFIG_PATA_RZ1000 is not set
# CONFIG_PATA_SC1200 is not set
# CONFIG_PATA_SERVERWORKS is not set
# CONFIG_PATA_PDC2027X is not set
# CONFIG_PATA_SIL680 is not set
# CONFIG_PATA_SIS is not set
# CONFIG_PATA_VIA is not set
# CONFIG_PATA_WINBOND is not set
CONFIG_PATA_SCH=y
CONFIG_MD=y
CONFIG_BLK_DEV_MD=y
CONFIG_MD_AUTODETECT=y
# CONFIG_MD_LINEAR is not set
# CONFIG_MD_RAID0 is not set
# CONFIG_MD_RAID1 is not set
# CONFIG_MD_RAID10 is not set
# CONFIG_MD_RAID456 is not set
# CONFIG_MD_MULTIPATH is not set
# CONFIG_MD_FAULTY is not set
CONFIG_BLK_DEV_DM=y
# CONFIG_DM_DEBUG is not set
# CONFIG_DM_CRYPT is not set
# CONFIG_DM_SNAPSHOT is not set
CONFIG_DM_MIRROR=y
# CONFIG_DM_LOG_USERSPACE is not set
CONFIG_DM_ZERO=y
# CONFIG_DM_MULTIPATH is not set
# CONFIG_DM_DELAY is not set
# CONFIG_DM_UEVENT is not set
# CONFIG_FUSION is not set

#
# IEEE 1394 (FireWire) support
#

#
# You can enable one or both FireWire driver stacks.
#

#
# See the help texts for more information.
#
# CONFIG_FIREWIRE is not set
# CONFIG_IEEE1394 is not set
# CONFIG_I2O is not set
CONFIG_MACINTOSH_DRIVERS=y
CONFIG_MAC_EMUMOUSEBTN=y
CONFIG_NETDEVICES=y
# CONFIG_IFB is not set
# CONFIG_DUMMY is not set
# CONFIG_BONDING is not set
# CONFIG_MACVLAN is not set
# CONFIG_EQUALIZER is not set
# CONFIG_TUN is not set
# CONFIG_VETH is not set
# CONFIG_NET_SB1000 is not set
# CONFIG_ARCNET is not set
CONFIG_PHYLIB=y

#
# MII PHY device drivers
#
# CONFIG_MARVELL_PHY is not set
# CONFIG_DAVICOM_PHY is not set
# CONFIG_QSEMI_PHY is not set
# CONFIG_LXT_PHY is not set
# CONFIG_CICADA_PHY is not set
# CONFIG_VITESSE_PHY is not set
# CONFIG_SMSC_PHY is not set
# CONFIG_BROADCOM_PHY is not set
# CONFIG_ICPLUS_PHY is not set
# CONFIG_REALTEK_PHY is not set
# CONFIG_NATIONAL_PHY is not set
# CONFIG_STE10XP is not set
# CONFIG_LSI_ET1011C_PHY is not set
# CONFIG_FIXED_PHY is not set
# CONFIG_MDIO_BITBANG is not set
CONFIG_NET_ETHERNET=y
CONFIG_MII=y
# CONFIG_HAPPYMEAL is not set
# CONFIG_SUNGEM is not set
# CONFIG_CASSINI is not set
CONFIG_NET_VENDOR_3COM=y
CONFIG_VORTEX=y
# CONFIG_TYPHOON is not set
# CONFIG_ETHOC is not set
# CONFIG_DNET is not set
CONFIG_NET_TULIP=y
# CONFIG_DE2104X is not set
# CONFIG_TULIP is not set
# CONFIG_DE4X5 is not set
# CONFIG_WINBOND_840 is not set
# CONFIG_DM9102 is not set
# CONFIG_ULI526X is not set
# CONFIG_PCMCIA_XIRCOM is not set
# CONFIG_HP100 is not set
# CONFIG_IBM_NEW_EMAC_ZMII is not set
# CONFIG_IBM_NEW_EMAC_RGMII is not set
# CONFIG_IBM_NEW_EMAC_TAH is not set
# CONFIG_IBM_NEW_EMAC_EMAC4 is not set
# CONFIG_IBM_NEW_EMAC_NO_FLOW_CTRL is not set
# CONFIG_IBM_NEW_EMAC_MAL_CLR_ICINTSTAT is not set
# CONFIG_IBM_NEW_EMAC_MAL_COMMON_ERR is not set
CONFIG_NET_PCI=y
# CONFIG_PCNET32 is not set
# CONFIG_AMD8111_ETH is not set
# CONFIG_ADAPTEC_STARFIRE is not set
# CONFIG_B44 is not set
CONFIG_FORCEDETH=y
# CONFIG_FORCEDETH_NAPI is not set
CONFIG_E100=y
# CONFIG_FEALNX is not set
# CONFIG_NATSEMI is not set
# CONFIG_NE2K_PCI is not set
# CONFIG_8139CP is not set
CONFIG_8139TOO=y
CONFIG_8139TOO_PIO=y
# CONFIG_8139TOO_TUNE_TWISTER is not set
# CONFIG_8139TOO_8129 is not set
# CONFIG_8139_OLD_RX_RESET is not set
# CONFIG_R6040 is not set
# CONFIG_SIS900 is not set
# CONFIG_EPIC100 is not set
# CONFIG_SMSC9420 is not set
# CONFIG_SUNDANCE is not set
# CONFIG_TLAN is not set
# CONFIG_KS8842 is not set
# CONFIG_VIA_RHINE is not set
# CONFIG_SC92031 is not set
# CONFIG_ATL2 is not set
CONFIG_NETDEV_1000=y
# CONFIG_ACENIC is not set
# CONFIG_DL2K is not set
CONFIG_E1000=y
CONFIG_E1000E=y
# CONFIG_IP1000 is not set
CONFIG_IGB=y
CONFIG_IGBVF=y
# CONFIG_NS83820 is not set
# CONFIG_HAMACHI is not set
# CONFIG_YELLOWFIN is not set
# CONFIG_R8169 is not set
# CONFIG_SIS190 is not set
# CONFIG_SKGE is not set
CONFIG_SKY2=y
# CONFIG_SKY2_DEBUG is not set
# CONFIG_VIA_VELOCITY is not set
CONFIG_TIGON3=y
# CONFIG_BNX2 is not set
# CONFIG_QLA3XXX is not set
# CONFIG_ATL1 is not set
# CONFIG_ATL1E is not set
# CONFIG_ATL1C is not set
# CONFIG_JME is not set
CONFIG_NETDEV_10000=y
# CONFIG_CHELSIO_T1 is not set
CONFIG_CHELSIO_T3_DEPENDS=y
# CONFIG_CHELSIO_T3 is not set
# CONFIG_ENIC is not set
# CONFIG_IXGBE is not set
# CONFIG_IXGB is not set
# CONFIG_S2IO is not set
# CONFIG_MYRI10GE is not set
# CONFIG_NIU is not set
# CONFIG_MLX4_EN is not set
# CONFIG_MLX4_CORE is not set
# CONFIG_TEHUTI is not set
# CONFIG_BNX2X is not set
# CONFIG_QLGE is not set
# CONFIG_SFC is not set
# CONFIG_BE2NET is not set
CONFIG_TR=y
# CONFIG_IBMOL is not set
# CONFIG_3C359 is not set
# CONFIG_TMS380TR is not set

#
# Wireless LAN
#
# CONFIG_WLAN_PRE80211 is not set
CONFIG_WLAN_80211=y
# CONFIG_PCMCIA_RAYCS is not set
# CONFIG_LIBERTAS is not set
# CONFIG_AIRO is not set
# CONFIG_ATMEL is not set
# CONFIG_AIRO_CS is not set
# CONFIG_PCMCIA_WL3501 is not set
# CONFIG_PRISM54 is not set
# CONFIG_USB_ZD1201 is not set
# CONFIG_IPW2100 is not set
# CONFIG_IPW2200 is not set
# CONFIG_HOSTAP is not set
# CONFIG_HERMES is not set

#
# Enable WiMAX (Networking options) to see the WiMAX drivers
#

#
# USB Network Adapters
#
# CONFIG_USB_CATC is not set
# CONFIG_USB_KAWETH is not set
# CONFIG_USB_PEGASUS is not set
# CONFIG_USB_RTL8150 is not set
# CONFIG_USB_USBNET is not set
# CONFIG_USB_HSO is not set
CONFIG_NET_PCMCIA=y
# CONFIG_PCMCIA_3C589 is not set
# CONFIG_PCMCIA_3C574 is not set
# CONFIG_PCMCIA_FMVJ18X is not set
# CONFIG_PCMCIA_PCNET is not set
# CONFIG_PCMCIA_NMCLAN is not set
# CONFIG_PCMCIA_SMC91C92 is not set
# CONFIG_PCMCIA_XIRC2PS is not set
# CONFIG_PCMCIA_AXNET is not set
# CONFIG_PCMCIA_IBMTR is not set
# CONFIG_WAN is not set
CONFIG_FDDI=y
# CONFIG_DEFXX is not set
# CONFIG_SKFP is not set
# CONFIG_HIPPI is not set
# CONFIG_PPP is not set
# CONFIG_SLIP is not set
# CONFIG_NET_FC is not set
CONFIG_NETCONSOLE=y
# CONFIG_NETCONSOLE_DYNAMIC is not set
CONFIG_NETPOLL=y
# CONFIG_NETPOLL_TRAP is not set
CONFIG_NET_POLL_CONTROLLER=y
# CONFIG_ISDN is not set
# CONFIG_PHONE is not set

#
# Input device support
#
CONFIG_INPUT=y
CONFIG_INPUT_FF_MEMLESS=y
CONFIG_INPUT_POLLDEV=y

#
# Userland interfaces
#
CONFIG_INPUT_MOUSEDEV=y
# CONFIG_INPUT_MOUSEDEV_PSAUX is not set
CONFIG_INPUT_MOUSEDEV_SCREEN_X=1024
CONFIG_INPUT_MOUSEDEV_SCREEN_Y=768
# CONFIG_INPUT_JOYDEV is not set
CONFIG_INPUT_EVDEV=y
# CONFIG_INPUT_EVBUG is not set

#
# Input Device Drivers
#
CONFIG_INPUT_KEYBOARD=y
CONFIG_KEYBOARD_ATKBD=y
# CONFIG_KEYBOARD_LKKBD is not set
# CONFIG_KEYBOARD_LM8323 is not set
# CONFIG_KEYBOARD_NEWTON is not set
# CONFIG_KEYBOARD_STOWAWAY is not set
# CONFIG_KEYBOARD_SUNKBD is not set
# CONFIG_KEYBOARD_XTKBD is not set
CONFIG_INPUT_MOUSE=y
CONFIG_MOUSE_PS2=y
CONFIG_MOUSE_PS2_ALPS=y
CONFIG_MOUSE_PS2_LOGIPS2PP=y
CONFIG_MOUSE_PS2_SYNAPTICS=y
CONFIG_MOUSE_PS2_LIFEBOOK=y
CONFIG_MOUSE_PS2_TRACKPOINT=y
# CONFIG_MOUSE_PS2_ELANTECH is not set
# CONFIG_MOUSE_PS2_TOUCHKIT is not set
# CONFIG_MOUSE_SERIAL is not set
# CONFIG_MOUSE_APPLETOUCH is not set
# CONFIG_MOUSE_BCM5974 is not set
# CONFIG_MOUSE_VSXXXAA is not set
# CONFIG_MOUSE_SYNAPTICS_I2C is not set
CONFIG_INPUT_JOYSTICK=y
# CONFIG_JOYSTICK_ANALOG is not set
# CONFIG_JOYSTICK_A3D is not set
# CONFIG_JOYSTICK_ADI is not set
# CONFIG_JOYSTICK_COBRA is not set
# CONFIG_JOYSTICK_GF2K is not set
# CONFIG_JOYSTICK_GRIP is not set
# CONFIG_JOYSTICK_GRIP_MP is not set
# CONFIG_JOYSTICK_GUILLEMOT is not set
# CONFIG_JOYSTICK_INTERACT is not set
# CONFIG_JOYSTICK_SIDEWINDER is not set
# CONFIG_JOYSTICK_TMDC is not set
# CONFIG_JOYSTICK_IFORCE is not set
# CONFIG_JOYSTICK_WARRIOR is not set
# CONFIG_JOYSTICK_MAGELLAN is not set
# CONFIG_JOYSTICK_SPACEORB is not set
# CONFIG_JOYSTICK_SPACEBALL is not set
# CONFIG_JOYSTICK_STINGER is not set
# CONFIG_JOYSTICK_TWIDJOY is not set
# CONFIG_JOYSTICK_ZHENHUA is not set
# CONFIG_JOYSTICK_JOYDUMP is not set
# CONFIG_JOYSTICK_XPAD is not set
CONFIG_INPUT_TABLET=y
# CONFIG_TABLET_USB_ACECAD is not set
# CONFIG_TABLET_USB_AIPTEK is not set
# CONFIG_TABLET_USB_GTCO is not set
# CONFIG_TABLET_USB_KBTAB is not set
# CONFIG_TABLET_USB_WACOM is not set
CONFIG_INPUT_TOUCHSCREEN=y
# CONFIG_TOUCHSCREEN_AD7879_I2C is not set
# CONFIG_TOUCHSCREEN_AD7879 is not set
# CONFIG_TOUCHSCREEN_EETI is not set
# CONFIG_TOUCHSCREEN_FUJITSU is not set
# CONFIG_TOUCHSCREEN_GUNZE is not set
# CONFIG_TOUCHSCREEN_ELO is not set
# CONFIG_TOUCHSCREEN_WACOM_W8001 is not set
# CONFIG_TOUCHSCREEN_MTOUCH is not set
# CONFIG_TOUCHSCREEN_INEXIO is not set
# CONFIG_TOUCHSCREEN_MK712 is not set
# CONFIG_TOUCHSCREEN_PENMOUNT is not set
# CONFIG_TOUCHSCREEN_TOUCHRIGHT is not set
# CONFIG_TOUCHSCREEN_TOUCHWIN is not set
# CONFIG_TOUCHSCREEN_USB_COMPOSITE is not set
# CONFIG_TOUCHSCREEN_TOUCHIT213 is not set
# CONFIG_TOUCHSCREEN_TSC2007 is not set
# CONFIG_TOUCHSCREEN_W90X900 is not set
CONFIG_INPUT_MISC=y
# CONFIG_INPUT_PCSPKR is not set
# CONFIG_INPUT_APANEL is not set
# CONFIG_INPUT_ATLAS_BTNS is not set
# CONFIG_INPUT_ATI_REMOTE is not set
# CONFIG_INPUT_ATI_REMOTE2 is not set
# CONFIG_INPUT_KEYSPAN_REMOTE is not set
# CONFIG_INPUT_POWERMATE is not set
# CONFIG_INPUT_YEALINK is not set
# CONFIG_INPUT_CM109 is not set
# CONFIG_INPUT_UINPUT is not set

#
# Hardware I/O ports
#
CONFIG_SERIO=y
CONFIG_SERIO_I8042=y
CONFIG_SERIO_SERPORT=y
# CONFIG_SERIO_CT82C710 is not set
# CONFIG_SERIO_PCIPS2 is not set
CONFIG_SERIO_LIBPS2=y
# CONFIG_SERIO_RAW is not set
# CONFIG_GAMEPORT is not set

#
# Character devices
#
CONFIG_VT=y
CONFIG_CONSOLE_TRANSLATIONS=y
CONFIG_VT_CONSOLE=y
CONFIG_HW_CONSOLE=y
CONFIG_VT_HW_CONSOLE_BINDING=y
CONFIG_DEVKMEM=y
CONFIG_SERIAL_NONSTANDARD=y
# CONFIG_COMPUTONE is not set
# CONFIG_ROCKETPORT is not set
# CONFIG_CYCLADES is not set
# CONFIG_DIGIEPCA is not set
# CONFIG_MOXA_INTELLIO is not set
# CONFIG_MOXA_SMARTIO is not set
# CONFIG_ISI is not set
# CONFIG_SYNCLINK is not set
# CONFIG_SYNCLINKMP is not set
# CONFIG_SYNCLINK_GT is not set
# CONFIG_N_HDLC is not set
# CONFIG_RISCOM8 is not set
# CONFIG_SPECIALIX is not set
# CONFIG_SX is not set
# CONFIG_RIO is not set
# CONFIG_STALDRV is not set
# CONFIG_NOZOMI is not set

#
# Serial drivers
#
CONFIG_SERIAL_8250=y
CONFIG_SERIAL_8250_CONSOLE=y
CONFIG_FIX_EARLYCON_MEM=y
CONFIG_SERIAL_8250_PCI=y
CONFIG_SERIAL_8250_PNP=y
# CONFIG_SERIAL_8250_CS is not set
CONFIG_SERIAL_8250_NR_UARTS=32
CONFIG_SERIAL_8250_RUNTIME_UARTS=4
CONFIG_SERIAL_8250_EXTENDED=y
CONFIG_SERIAL_8250_MANY_PORTS=y
CONFIG_SERIAL_8250_SHARE_IRQ=y
CONFIG_SERIAL_8250_DETECT_IRQ=y
CONFIG_SERIAL_8250_RSA=y

#
# Non-8250 serial port support
#
CONFIG_SERIAL_CORE=y
CONFIG_SERIAL_CORE_CONSOLE=y
# CONFIG_SERIAL_JSM is not set
CONFIG_UNIX98_PTYS=y
# CONFIG_DEVPTS_MULTIPLE_INSTANCES is not set
# CONFIG_LEGACY_PTYS is not set
# CONFIG_IPMI_HANDLER is not set
CONFIG_HW_RANDOM=y
# CONFIG_HW_RANDOM_TIMERIOMEM is not set
# CONFIG_HW_RANDOM_INTEL is not set
# CONFIG_HW_RANDOM_AMD is not set
CONFIG_HW_RANDOM_VIA=y
CONFIG_NVRAM=y
# CONFIG_R3964 is not set
# CONFIG_APPLICOM is not set

#
# PCMCIA character devices
#
# CONFIG_SYNCLINK_CS is not set
# CONFIG_CARDMAN_4000 is not set
# CONFIG_CARDMAN_4040 is not set
# CONFIG_IPWIRELESS is not set
# CONFIG_MWAVE is not set
# CONFIG_PC8736x_GPIO is not set
# CONFIG_RAW_DRIVER is not set
CONFIG_HPET=y
# CONFIG_HPET_MMAP is not set
# CONFIG_HANGCHECK_TIMER is not set
# CONFIG_TCG_TPM is not set
# CONFIG_TELCLOCK is not set
CONFIG_DEVPORT=y
CONFIG_I2C=y
CONFIG_I2C_BOARDINFO=y
# CONFIG_I2C_CHARDEV is not set
CONFIG_I2C_HELPER_AUTO=y
CONFIG_I2C_ALGOBIT=y

#
# I2C Hardware Bus support
#

#
# PC SMBus host controller drivers
#
# CONFIG_I2C_ALI1535 is not set
# CONFIG_I2C_ALI1563 is not set
# CONFIG_I2C_ALI15X3 is not set
# CONFIG_I2C_AMD756 is not set
# CONFIG_I2C_AMD8111 is not set
CONFIG_I2C_I801=y
# CONFIG_I2C_ISCH is not set
# CONFIG_I2C_PIIX4 is not set
# CONFIG_I2C_NFORCE2 is not set
# CONFIG_I2C_SIS5595 is not set
# CONFIG_I2C_SIS630 is not set
# CONFIG_I2C_SIS96X is not set
# CONFIG_I2C_VIA is not set
# CONFIG_I2C_VIAPRO is not set

#
# I2C system bus drivers (mostly embedded / system-on-chip)
#
# CONFIG_I2C_OCORES is not set
# CONFIG_I2C_SIMTEC is not set

#
# External I2C/SMBus adapter drivers
#
# CONFIG_I2C_PARPORT_LIGHT is not set
# CONFIG_I2C_TAOS_EVM is not set
# CONFIG_I2C_TINY_USB is not set

#
# Graphics adapter I2C/DDC channel drivers
#
# CONFIG_I2C_VOODOO3 is not set

#
# Other I2C/SMBus bus drivers
#
# CONFIG_I2C_PCA_PLATFORM is not set
# CONFIG_I2C_STUB is not set

#
# Miscellaneous I2C Chip support
#
# CONFIG_DS1682 is not set
# CONFIG_SENSORS_PCF8574 is not set
# CONFIG_PCF8575 is not set
# CONFIG_SENSORS_PCA9539 is not set
# CONFIG_SENSORS_TSL2550 is not set
# CONFIG_I2C_DEBUG_CORE is not set
# CONFIG_I2C_DEBUG_ALGO is not set
# CONFIG_I2C_DEBUG_BUS is not set
# CONFIG_I2C_DEBUG_CHIP is not set
# CONFIG_SPI is not set

#
# PPS support
#
# CONFIG_PPS is not set
CONFIG_ARCH_WANT_OPTIONAL_GPIOLIB=y
# CONFIG_GPIOLIB is not set
# CONFIG_W1 is not set
CONFIG_POWER_SUPPLY=y
# CONFIG_POWER_SUPPLY_DEBUG is not set
# CONFIG_PDA_POWER is not set
# CONFIG_BATTERY_DS2760 is not set
# CONFIG_BATTERY_DS2782 is not set
# CONFIG_BATTERY_BQ27x00 is not set
# CONFIG_BATTERY_MAX17040 is not set
CONFIG_HWMON=y
# CONFIG_HWMON_VID is not set
# CONFIG_SENSORS_ABITUGURU is not set
# CONFIG_SENSORS_ABITUGURU3 is not set
# CONFIG_SENSORS_AD7414 is not set
# CONFIG_SENSORS_AD7418 is not set
# CONFIG_SENSORS_ADM1021 is not set
# CONFIG_SENSORS_ADM1025 is not set
# CONFIG_SENSORS_ADM1026 is not set
# CONFIG_SENSORS_ADM1029 is not set
# CONFIG_SENSORS_ADM1031 is not set
# CONFIG_SENSORS_ADM9240 is not set
# CONFIG_SENSORS_ADT7462 is not set
# CONFIG_SENSORS_ADT7470 is not set
# CONFIG_SENSORS_ADT7473 is not set
# CONFIG_SENSORS_ADT7475 is not set
# CONFIG_SENSORS_K8TEMP is not set
# CONFIG_SENSORS_ASB100 is not set
# CONFIG_SENSORS_ATK0110 is not set
# CONFIG_SENSORS_ATXP1 is not set
# CONFIG_SENSORS_DS1621 is not set
# CONFIG_SENSORS_I5K_AMB is not set
# CONFIG_SENSORS_F71805F is not set
# CONFIG_SENSORS_F71882FG is not set
# CONFIG_SENSORS_F75375S is not set
# CONFIG_SENSORS_FSCHER is not set
# CONFIG_SENSORS_FSCPOS is not set
# CONFIG_SENSORS_FSCHMD is not set
# CONFIG_SENSORS_G760A is not set
# CONFIG_SENSORS_GL518SM is not set
# CONFIG_SENSORS_GL520SM is not set
# CONFIG_SENSORS_CORETEMP is not set
# CONFIG_SENSORS_IT87 is not set
# CONFIG_SENSORS_LM63 is not set
# CONFIG_SENSORS_LM75 is not set
# CONFIG_SENSORS_LM77 is not set
# CONFIG_SENSORS_LM78 is not set
# CONFIG_SENSORS_LM80 is not set
# CONFIG_SENSORS_LM83 is not set
# CONFIG_SENSORS_LM85 is not set
# CONFIG_SENSORS_LM87 is not set
# CONFIG_SENSORS_LM90 is not set
# CONFIG_SENSORS_LM92 is not set
# CONFIG_SENSORS_LM93 is not set
# CONFIG_SENSORS_LTC4215 is not set
# CONFIG_SENSORS_LTC4245 is not set
# CONFIG_SENSORS_LM95241 is not set
# CONFIG_SENSORS_MAX1619 is not set
# CONFIG_SENSORS_MAX6650 is not set
# CONFIG_SENSORS_PC87360 is not set
# CONFIG_SENSORS_PC87427 is not set
# CONFIG_SENSORS_PCF8591 is not set
# CONFIG_SENSORS_SIS5595 is not set
# CONFIG_SENSORS_DME1737 is not set
# CONFIG_SENSORS_SMSC47M1 is not set
# CONFIG_SENSORS_SMSC47M192 is not set
# CONFIG_SENSORS_SMSC47B397 is not set
# CONFIG_SENSORS_ADS7828 is not set
# CONFIG_SENSORS_THMC50 is not set
# CONFIG_SENSORS_TMP401 is not set
# CONFIG_SENSORS_VIA686A is not set
# CONFIG_SENSORS_VT1211 is not set
# CONFIG_SENSORS_VT8231 is not set
# CONFIG_SENSORS_W83781D is not set
# CONFIG_SENSORS_W83791D is not set
# CONFIG_SENSORS_W83792D is not set
# CONFIG_SENSORS_W83793 is not set
# CONFIG_SENSORS_W83L785TS is not set
# CONFIG_SENSORS_W83L786NG is not set
# CONFIG_SENSORS_W83627HF is not set
# CONFIG_SENSORS_W83627EHF is not set
# CONFIG_SENSORS_HDAPS is not set
# CONFIG_SENSORS_LIS3LV02D is not set
# CONFIG_SENSORS_APPLESMC is not set
# CONFIG_HWMON_DEBUG_CHIP is not set
CONFIG_THERMAL=y
# CONFIG_THERMAL_HWMON is not set
CONFIG_WATCHDOG=y
# CONFIG_WATCHDOG_NOWAYOUT is not set

#
# Watchdog Device Drivers
#
# CONFIG_SOFT_WATCHDOG is not set
# CONFIG_ACQUIRE_WDT is not set
# CONFIG_ADVANTECH_WDT is not set
# CONFIG_ALIM1535_WDT is not set
# CONFIG_ALIM7101_WDT is not set
# CONFIG_SC520_WDT is not set
# CONFIG_IB700_WDT is not set
# CONFIG_IBMASR is not set
# CONFIG_WAFER_WDT is not set
# CONFIG_I6300ESB_WDT is not set
# CONFIG_ITCO_WDT is not set
# CONFIG_IT8712F_WDT is not set
# CONFIG_IT87_WDT is not set
# CONFIG_HP_WATCHDOG is not set
# CONFIG_SC1200_WDT is not set
# CONFIG_PC87413_WDT is not set
# CONFIG_60XX_WDT is not set
# CONFIG_SBC8360_WDT is not set
# CONFIG_CPU5_WDT is not set
# CONFIG_SMSC_SCH311X_WDT is not set
# CONFIG_SMSC37B787_WDT is not set
# CONFIG_W83627HF_WDT is not set
# CONFIG_W83697HF_WDT is not set
# CONFIG_W83697UG_WDT is not set
# CONFIG_W83877F_WDT is not set
# CONFIG_W83977F_WDT is not set
# CONFIG_MACHZ_WDT is not set
# CONFIG_SBC_EPX_C3_WATCHDOG is not set

#
# PCI-based Watchdog Cards
#
# CONFIG_PCIPCWATCHDOG is not set
# CONFIG_WDTPCI is not set

#
# USB-based Watchdog Cards
#
# CONFIG_USBPCWATCHDOG is not set
CONFIG_SSB_POSSIBLE=y

#
# Sonics Silicon Backplane
#
# CONFIG_SSB is not set

#
# Multifunction device drivers
#
# CONFIG_MFD_CORE is not set
# CONFIG_MFD_SM501 is not set
# CONFIG_HTC_PASIC3 is not set
# CONFIG_TWL4030_CORE is not set
# CONFIG_MFD_TMIO is not set
# CONFIG_PMIC_DA903X is not set
# CONFIG_MFD_WM8400 is not set
# CONFIG_MFD_PCF50633 is not set
# CONFIG_AB3100_CORE is not set
# CONFIG_REGULATOR is not set
# CONFIG_MEDIA_SUPPORT is not set

#
# Graphics support
#
CONFIG_AGP=y
CONFIG_AGP_AMD64=y
CONFIG_AGP_INTEL=y
# CONFIG_AGP_SIS is not set
# CONFIG_AGP_VIA is not set
CONFIG_DRM=y
# CONFIG_DRM_TDFX is not set
# CONFIG_DRM_R128 is not set
# CONFIG_DRM_RADEON is not set
# CONFIG_DRM_I810 is not set
# CONFIG_DRM_I830 is not set
CONFIG_DRM_I915=y
CONFIG_DRM_I915_KMS=y
# CONFIG_DRM_MGA is not set
# CONFIG_DRM_SIS is not set
# CONFIG_DRM_VIA is not set
# CONFIG_DRM_SAVAGE is not set
# CONFIG_VGASTATE is not set
CONFIG_VIDEO_OUTPUT_CONTROL=y
CONFIG_FB=y
# CONFIG_FIRMWARE_EDID is not set
# CONFIG_FB_DDC is not set
# CONFIG_FB_BOOT_VESA_SUPPORT is not set
CONFIG_FB_CFB_FILLRECT=y
CONFIG_FB_CFB_COPYAREA=y
CONFIG_FB_CFB_IMAGEBLIT=y
# CONFIG_FB_CFB_REV_PIXELS_IN_BYTE is not set
# CONFIG_FB_SYS_FILLRECT is not set
# CONFIG_FB_SYS_COPYAREA is not set
# CONFIG_FB_SYS_IMAGEBLIT is not set
# CONFIG_FB_FOREIGN_ENDIAN is not set
# CONFIG_FB_SYS_FOPS is not set
# CONFIG_FB_SVGALIB is not set
# CONFIG_FB_MACMODES is not set
# CONFIG_FB_BACKLIGHT is not set
CONFIG_FB_MODE_HELPERS=y
CONFIG_FB_TILEBLITTING=y

#
# Frame buffer hardware drivers
#
# CONFIG_FB_PM2 is not set
# CONFIG_FB_CYBER2000 is not set
# CONFIG_FB_ARC is not set
# CONFIG_FB_IMSTT is not set
# CONFIG_FB_UVESA is not set
CONFIG_FB_EFI=y
# CONFIG_FB_N411 is not set
# CONFIG_FB_HGA is not set
# CONFIG_FB_S1D13XXX is not set
# CONFIG_FB_NVIDIA is not set
# CONFIG_FB_RIVA is not set
# CONFIG_FB_LE80578 is not set
# CONFIG_FB_MATROX is not set
# CONFIG_FB_ATY128 is not set
# CONFIG_FB_ATY is not set
# CONFIG_FB_S3 is not set
# CONFIG_FB_SAVAGE is not set
# CONFIG_FB_SIS is not set
# CONFIG_FB_VIA is not set
# CONFIG_FB_NEOMAGIC is not set
# CONFIG_FB_KYRO is not set
# CONFIG_FB_3DFX is not set
# CONFIG_FB_VOODOO1 is not set
# CONFIG_FB_VT8623 is not set
# CONFIG_FB_TRIDENT is not set
# CONFIG_FB_ARK is not set
# CONFIG_FB_PM3 is not set
# CONFIG_FB_CARMINE is not set
# CONFIG_FB_GEODE is not set
# CONFIG_FB_METRONOME is not set
# CONFIG_FB_MB862XX is not set
# CONFIG_FB_BROADSHEET is not set
CONFIG_BACKLIGHT_LCD_SUPPORT=y
# CONFIG_LCD_CLASS_DEVICE is not set
CONFIG_BACKLIGHT_CLASS_DEVICE=y
CONFIG_BACKLIGHT_GENERIC=y
# CONFIG_BACKLIGHT_PROGEAR is not set
# CONFIG_BACKLIGHT_MBP_NVIDIA is not set
# CONFIG_BACKLIGHT_SAHARA is not set

#
# Display device support
#
# CONFIG_DISPLAY_SUPPORT is not set

#
# Console display driver support
#
CONFIG_VGA_CONSOLE=y
CONFIG_VGACON_SOFT_SCROLLBACK=y
CONFIG_VGACON_SOFT_SCROLLBACK_SIZE=64
CONFIG_DUMMY_CONSOLE=y
CONFIG_FRAMEBUFFER_CONSOLE=y
# CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY is not set
# CONFIG_FRAMEBUFFER_CONSOLE_ROTATION is not set
# CONFIG_FONTS is not set
CONFIG_FONT_8x8=y
CONFIG_FONT_8x16=y
CONFIG_LOGO=y
# CONFIG_LOGO_LINUX_MONO is not set
# CONFIG_LOGO_LINUX_VGA16 is not set
CONFIG_LOGO_LINUX_CLUT224=y
CONFIG_SOUND=y
CONFIG_SOUND_OSS_CORE=y
CONFIG_SND=y
CONFIG_SND_TIMER=y
CONFIG_SND_PCM=y
CONFIG_SND_HWDEP=y
CONFIG_SND_SEQUENCER=y
CONFIG_SND_SEQ_DUMMY=y
CONFIG_SND_OSSEMUL=y
CONFIG_SND_MIXER_OSS=y
CONFIG_SND_PCM_OSS=y
CONFIG_SND_PCM_OSS_PLUGINS=y
CONFIG_SND_SEQUENCER_OSS=y
CONFIG_SND_HRTIMER=y
CONFIG_SND_SEQ_HRTIMER_DEFAULT=y
CONFIG_SND_DYNAMIC_MINORS=y
CONFIG_SND_SUPPORT_OLD_API=y
CONFIG_SND_VERBOSE_PROCFS=y
# CONFIG_SND_VERBOSE_PRINTK is not set
# CONFIG_SND_DEBUG is not set
CONFIG_SND_VMASTER=y
# CONFIG_SND_RAWMIDI_SEQ is not set
# CONFIG_SND_OPL3_LIB_SEQ is not set
# CONFIG_SND_OPL4_LIB_SEQ is not set
# CONFIG_SND_SBAWE_SEQ is not set
# CONFIG_SND_EMU10K1_SEQ is not set
CONFIG_SND_DRIVERS=y
# CONFIG_SND_PCSP is not set
# CONFIG_SND_DUMMY is not set
# CONFIG_SND_VIRMIDI is not set
# CONFIG_SND_SERIAL_U16550 is not set
# CONFIG_SND_MPU401 is not set
CONFIG_SND_PCI=y
# CONFIG_SND_AD1889 is not set
# CONFIG_SND_ALS300 is not set
# CONFIG_SND_ALS4000 is not set
# CONFIG_SND_ALI5451 is not set
# CONFIG_SND_ATIIXP is not set
# CONFIG_SND_ATIIXP_MODEM is not set
# CONFIG_SND_AU8810 is not set
# CONFIG_SND_AU8820 is not set
# CONFIG_SND_AU8830 is not set
# CONFIG_SND_AW2 is not set
# CONFIG_SND_AZT3328 is not set
# CONFIG_SND_BT87X is not set
# CONFIG_SND_CA0106 is not set
# CONFIG_SND_CMIPCI is not set
# CONFIG_SND_OXYGEN is not set
# CONFIG_SND_CS4281 is not set
# CONFIG_SND_CS46XX is not set
# CONFIG_SND_CS5530 is not set
# CONFIG_SND_CTXFI is not set
# CONFIG_SND_DARLA20 is not set
# CONFIG_SND_GINA20 is not set
# CONFIG_SND_LAYLA20 is not set
# CONFIG_SND_DARLA24 is not set
# CONFIG_SND_GINA24 is not set
# CONFIG_SND_LAYLA24 is not set
# CONFIG_SND_MONA is not set
# CONFIG_SND_MIA is not set
# CONFIG_SND_ECHO3G is not set
# CONFIG_SND_INDIGO is not set
# CONFIG_SND_INDIGOIO is not set
# CONFIG_SND_INDIGODJ is not set
# CONFIG_SND_INDIGOIOX is not set
# CONFIG_SND_INDIGODJX is not set
# CONFIG_SND_EMU10K1 is not set
# CONFIG_SND_EMU10K1X is not set
# CONFIG_SND_ENS1370 is not set
# CONFIG_SND_ENS1371 is not set
# CONFIG_SND_ES1938 is not set
# CONFIG_SND_ES1968 is not set
# CONFIG_SND_FM801 is not set
CONFIG_SND_HDA_INTEL=y
CONFIG_SND_HDA_HWDEP=y
# CONFIG_SND_HDA_RECONFIG is not set
# CONFIG_SND_HDA_INPUT_BEEP is not set
# CONFIG_SND_HDA_INPUT_JACK is not set
CONFIG_SND_HDA_CODEC_REALTEK=y
CONFIG_SND_HDA_CODEC_ANALOG=y
CONFIG_SND_HDA_CODEC_SIGMATEL=y
CONFIG_SND_HDA_CODEC_VIA=y
CONFIG_SND_HDA_CODEC_ATIHDMI=y
CONFIG_SND_HDA_CODEC_NVHDMI=y
CONFIG_SND_HDA_CODEC_INTELHDMI=y
CONFIG_SND_HDA_ELD=y
CONFIG_SND_HDA_CODEC_CONEXANT=y
CONFIG_SND_HDA_CODEC_CA0110=y
CONFIG_SND_HDA_CODEC_CMEDIA=y
CONFIG_SND_HDA_CODEC_SI3054=y
CONFIG_SND_HDA_GENERIC=y
# CONFIG_SND_HDA_POWER_SAVE is not set
# CONFIG_SND_HDSP is not set
# CONFIG_SND_HDSPM is not set
# CONFIG_SND_HIFIER is not set
# CONFIG_SND_ICE1712 is not set
# CONFIG_SND_ICE1724 is not set
# CONFIG_SND_INTEL8X0 is not set
# CONFIG_SND_INTEL8X0M is not set
# CONFIG_SND_KORG1212 is not set
# CONFIG_SND_LX6464ES is not set
# CONFIG_SND_MAESTRO3 is not set
# CONFIG_SND_MIXART is not set
# CONFIG_SND_NM256 is not set
# CONFIG_SND_PCXHR is not set
# CONFIG_SND_RIPTIDE is not set
# CONFIG_SND_RME32 is not set
# CONFIG_SND_RME96 is not set
# CONFIG_SND_RME9652 is not set
# CONFIG_SND_SONICVIBES is not set
# CONFIG_SND_TRIDENT is not set
# CONFIG_SND_VIA82XX is not set
# CONFIG_SND_VIA82XX_MODEM is not set
# CONFIG_SND_VIRTUOSO is not set
# CONFIG_SND_VX222 is not set
# CONFIG_SND_YMFPCI is not set
CONFIG_SND_USB=y
# CONFIG_SND_USB_AUDIO is not set
# CONFIG_SND_USB_USX2Y is not set
# CONFIG_SND_USB_CAIAQ is not set
# CONFIG_SND_USB_US122L is not set
CONFIG_SND_PCMCIA=y
# CONFIG_SND_VXPOCKET is not set
# CONFIG_SND_PDAUDIOCF is not set
# CONFIG_SND_SOC is not set
# CONFIG_SOUND_PRIME is not set
CONFIG_HID_SUPPORT=y
CONFIG_HID=y
CONFIG_HID_DEBUG=y
CONFIG_HIDRAW=y

#
# USB Input Devices
#
CONFIG_USB_HID=y
CONFIG_HID_PID=y
CONFIG_USB_HIDDEV=y
CONFIG_USB_MOUSE=y

#
# Special HID drivers
#
CONFIG_HID_A4TECH=y
CONFIG_HID_APPLE=y
CONFIG_HID_BELKIN=y
CONFIG_HID_CHERRY=y
CONFIG_HID_CHICONY=y
CONFIG_HID_CYPRESS=y
CONFIG_HID_DRAGONRISE=y
# CONFIG_DRAGONRISE_FF is not set
CONFIG_HID_EZKEY=y
CONFIG_HID_KYE=y
CONFIG_HID_GYRATION=y
CONFIG_HID_KENSINGTON=y
CONFIG_HID_LOGITECH=y
CONFIG_LOGITECH_FF=y
# CONFIG_LOGIRUMBLEPAD2_FF is not set
CONFIG_HID_MICROSOFT=y
CONFIG_HID_MONTEREY=y
CONFIG_HID_NTRIG=y
CONFIG_HID_PANTHERLORD=y
CONFIG_PANTHERLORD_FF=y
CONFIG_HID_PETALYNX=y
CONFIG_HID_SAMSUNG=y
CONFIG_HID_SONY=y
CONFIG_HID_SUNPLUS=y
CONFIG_HID_GREENASIA=y
# CONFIG_GREENASIA_FF is not set
CONFIG_HID_SMARTJOYPLUS=y
# CONFIG_SMARTJOYPLUS_FF is not set
CONFIG_HID_TOPSEED=y
CONFIG_HID_THRUSTMASTER=y
CONFIG_THRUSTMASTER_FF=y
CONFIG_HID_ZEROPLUS=y
CONFIG_ZEROPLUS_FF=y
CONFIG_USB_SUPPORT=y
CONFIG_USB_ARCH_HAS_HCD=y
CONFIG_USB_ARCH_HAS_OHCI=y
CONFIG_USB_ARCH_HAS_EHCI=y
CONFIG_USB=y
CONFIG_USB_DEBUG=y
CONFIG_USB_ANNOUNCE_NEW_DEVICES=y

#
# Miscellaneous USB options
#
CONFIG_USB_DEVICEFS=y
# CONFIG_USB_DEVICE_CLASS is not set
# CONFIG_USB_DYNAMIC_MINORS is not set
CONFIG_USB_SUSPEND=y
# CONFIG_USB_OTG is not set
CONFIG_USB_MON=y
# CONFIG_USB_WUSB is not set
# CONFIG_USB_WUSB_CBAF is not set

#
# USB Host Controller Drivers
#
# CONFIG_USB_C67X00_HCD is not set
# CONFIG_USB_XHCI_HCD is not set
CONFIG_USB_EHCI_HCD=y
# CONFIG_USB_EHCI_ROOT_HUB_TT is not set
# CONFIG_USB_EHCI_TT_NEWSCHED is not set
# CONFIG_USB_OXU210HP_HCD is not set
# CONFIG_USB_ISP116X_HCD is not set
# CONFIG_USB_ISP1760_HCD is not set
CONFIG_USB_OHCI_HCD=y
# CONFIG_USB_OHCI_BIG_ENDIAN_DESC is not set
# CONFIG_USB_OHCI_BIG_ENDIAN_MMIO is not set
CONFIG_USB_OHCI_LITTLE_ENDIAN=y
CONFIG_USB_UHCI_HCD=y
# CONFIG_USB_SL811_HCD is not set
# CONFIG_USB_R8A66597_HCD is not set
# CONFIG_USB_HWA_HCD is not set

#
# USB Device Class drivers
#
# CONFIG_USB_ACM is not set
CONFIG_USB_PRINTER=y
# CONFIG_USB_WDM is not set
# CONFIG_USB_TMC is not set

#
# NOTE: USB_STORAGE depends on SCSI but BLK_DEV_SD may
#

#
# also be needed; see USB_STORAGE Help for more info
#
CONFIG_USB_STORAGE=y
# CONFIG_USB_STORAGE_DEBUG is not set
# CONFIG_USB_STORAGE_DATAFAB is not set
# CONFIG_USB_STORAGE_FREECOM is not set
# CONFIG_USB_STORAGE_ISD200 is not set
# CONFIG_USB_STORAGE_USBAT is not set
# CONFIG_USB_STORAGE_SDDR09 is not set
# CONFIG_USB_STORAGE_SDDR55 is not set
# CONFIG_USB_STORAGE_JUMPSHOT is not set
# CONFIG_USB_STORAGE_ALAUDA is not set
# CONFIG_USB_STORAGE_ONETOUCH is not set
# CONFIG_USB_STORAGE_KARMA is not set
# CONFIG_USB_STORAGE_CYPRESS_ATACB is not set
CONFIG_USB_LIBUSUAL=y

#
# USB Imaging devices
#
# CONFIG_USB_MDC800 is not set
# CONFIG_USB_MICROTEK is not set

#
# USB port drivers
#
# CONFIG_USB_SERIAL is not set

#
# USB Miscellaneous drivers
#
# CONFIG_USB_EMI62 is not set
# CONFIG_USB_EMI26 is not set
# CONFIG_USB_ADUTUX is not set
# CONFIG_USB_SEVSEG is not set
# CONFIG_USB_RIO500 is not set
# CONFIG_USB_LEGOTOWER is not set
# CONFIG_USB_LCD is not set
# CONFIG_USB_BERRY_CHARGE is not set
# CONFIG_USB_LED is not set
# CONFIG_USB_CYPRESS_CY7C63 is not set
# CONFIG_USB_CYTHERM is not set
# CONFIG_USB_IDMOUSE is not set
# CONFIG_USB_FTDI_ELAN is not set
# CONFIG_USB_APPLEDISPLAY is not set
# CONFIG_USB_SISUSBVGA is not set
# CONFIG_USB_LD is not set
# CONFIG_USB_TRANCEVIBRATOR is not set
# CONFIG_USB_IOWARRIOR is not set
# CONFIG_USB_TEST is not set
# CONFIG_USB_ISIGHTFW is not set
# CONFIG_USB_VST is not set

#
# OTG and related infrastructure
#
# CONFIG_NOP_USB_XCEIV is not set
# CONFIG_UWB is not set
# CONFIG_MMC is not set
# CONFIG_MEMSTICK is not set
CONFIG_NEW_LEDS=y
CONFIG_LEDS_CLASS=y

#
# LED drivers
#
# CONFIG_LEDS_ALIX2 is not set
# CONFIG_LEDS_PCA9532 is not set
# CONFIG_LEDS_LP3944 is not set
# CONFIG_LEDS_CLEVO_MAIL is not set
# CONFIG_LEDS_PCA955X is not set
# CONFIG_LEDS_BD2802 is not set

#
# LED Triggers
#
CONFIG_LEDS_TRIGGERS=y
# CONFIG_LEDS_TRIGGER_TIMER is not set
# CONFIG_LEDS_TRIGGER_HEARTBEAT is not set
# CONFIG_LEDS_TRIGGER_BACKLIGHT is not set
# CONFIG_LEDS_TRIGGER_DEFAULT_ON is not set

#
# iptables trigger is under Netfilter config (LED target)
#
# CONFIG_ACCESSIBILITY is not set
# CONFIG_INFINIBAND is not set
CONFIG_EDAC=y

#
# Reporting subsystems
#
# CONFIG_EDAC_DEBUG is not set
# CONFIG_EDAC_MM_EDAC is not set
CONFIG_RTC_LIB=y
CONFIG_RTC_CLASS=y
# CONFIG_RTC_HCTOSYS is not set
# CONFIG_RTC_DEBUG is not set

#
# RTC interfaces
#
CONFIG_RTC_INTF_SYSFS=y
CONFIG_RTC_INTF_PROC=y
CONFIG_RTC_INTF_DEV=y
# CONFIG_RTC_INTF_DEV_UIE_EMUL is not set
# CONFIG_RTC_DRV_TEST is not set

#
# I2C RTC drivers
#
# CONFIG_RTC_DRV_DS1307 is not set
# CONFIG_RTC_DRV_DS1374 is not set
# CONFIG_RTC_DRV_DS1672 is not set
# CONFIG_RTC_DRV_MAX6900 is not set
# CONFIG_RTC_DRV_RS5C372 is not set
# CONFIG_RTC_DRV_ISL1208 is not set
# CONFIG_RTC_DRV_X1205 is not set
# CONFIG_RTC_DRV_PCF8563 is not set
# CONFIG_RTC_DRV_PCF8583 is not set
# CONFIG_RTC_DRV_M41T80 is not set
# CONFIG_RTC_DRV_S35390A is not set
# CONFIG_RTC_DRV_FM3130 is not set
# CONFIG_RTC_DRV_RX8581 is not set
# CONFIG_RTC_DRV_RX8025 is not set

#
# SPI RTC drivers
#

#
# Platform RTC drivers
#
CONFIG_RTC_DRV_CMOS=y
# CONFIG_RTC_DRV_DS1286 is not set
# CONFIG_RTC_DRV_DS1511 is not set
# CONFIG_RTC_DRV_DS1553 is not set
# CONFIG_RTC_DRV_DS1742 is not set
# CONFIG_RTC_DRV_STK17TA8 is not set
# CONFIG_RTC_DRV_M48T86 is not set
# CONFIG_RTC_DRV_M48T35 is not set
# CONFIG_RTC_DRV_M48T59 is not set
# CONFIG_RTC_DRV_BQ4802 is not set
# CONFIG_RTC_DRV_V3020 is not set

#
# on-CPU RTC drivers
#
CONFIG_DMADEVICES=y

#
# DMA Devices
#
# CONFIG_INTEL_IOATDMA is not set
# CONFIG_AUXDISPLAY is not set
# CONFIG_UIO is not set

#
# TI VLYNQ
#
CONFIG_X86_PLATFORM_DEVICES=y
# CONFIG_ACER_WMI is not set
# CONFIG_ASUS_LAPTOP is not set
# CONFIG_FUJITSU_LAPTOP is not set
# CONFIG_MSI_LAPTOP is not set
# CONFIG_PANASONIC_LAPTOP is not set
# CONFIG_COMPAL_LAPTOP is not set
# CONFIG_SONY_LAPTOP is not set
# CONFIG_THINKPAD_ACPI is not set
# CONFIG_INTEL_MENLOW is not set
CONFIG_EEEPC_LAPTOP=y
# CONFIG_ACPI_WMI is not set
# CONFIG_ACPI_ASUS is not set
# CONFIG_ACPI_TOSHIBA is not set

#
# Firmware Drivers
#
# CONFIG_EDD is not set
CONFIG_FIRMWARE_MEMMAP=y
CONFIG_EFI_VARS=y
# CONFIG_DELL_RBU is not set
# CONFIG_DCDBAS is not set
CONFIG_DMIID=y
# CONFIG_ISCSI_IBFT_FIND is not set

#
# File systems
#
# CONFIG_EXT2_FS is not set
CONFIG_EXT3_FS=y
# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
CONFIG_EXT3_FS_XATTR=y
CONFIG_EXT3_FS_POSIX_ACL=y
CONFIG_EXT3_FS_SECURITY=y
# CONFIG_EXT4_FS is not set
CONFIG_JBD=y
# CONFIG_JBD_DEBUG is not set
CONFIG_FS_MBCACHE=y
# CONFIG_REISERFS_FS is not set
# CONFIG_JFS_FS is not set
CONFIG_FS_POSIX_ACL=y
# CONFIG_XFS_FS is not set
# CONFIG_GFS2_FS is not set
# CONFIG_OCFS2_FS is not set
# CONFIG_BTRFS_FS is not set
CONFIG_FILE_LOCKING=y
CONFIG_FSNOTIFY=y
CONFIG_DNOTIFY=y
CONFIG_INOTIFY=y
CONFIG_INOTIFY_USER=y
CONFIG_QUOTA=y
CONFIG_QUOTA_NETLINK_INTERFACE=y
# CONFIG_PRINT_QUOTA_WARNING is not set
CONFIG_QUOTA_TREE=y
# CONFIG_QFMT_V1 is not set
CONFIG_QFMT_V2=y
CONFIG_QUOTACTL=y
# CONFIG_AUTOFS_FS is not set
CONFIG_AUTOFS4_FS=y
# CONFIG_FUSE_FS is not set
CONFIG_GENERIC_ACL=y

#
# Caches
#
# CONFIG_FSCACHE is not set

#
# CD-ROM/DVD Filesystems
#
CONFIG_ISO9660_FS=y
CONFIG_JOLIET=y
CONFIG_ZISOFS=y
# CONFIG_UDF_FS is not set

#
# DOS/FAT/NT Filesystems
#
CONFIG_FAT_FS=y
CONFIG_MSDOS_FS=y
CONFIG_VFAT_FS=y
CONFIG_FAT_DEFAULT_CODEPAGE=437
CONFIG_FAT_DEFAULT_IOCHARSET="iso8859-1"
# CONFIG_NTFS_FS is not set

#
# Pseudo filesystems
#
CONFIG_PROC_FS=y
CONFIG_PROC_KCORE=y
CONFIG_PROC_VMCORE=y
CONFIG_PROC_SYSCTL=y
CONFIG_PROC_PAGE_MONITOR=y
CONFIG_SYSFS=y
CONFIG_TMPFS=y
CONFIG_TMPFS_POSIX_ACL=y
CONFIG_HUGETLBFS=y
CONFIG_HUGETLB_PAGE=y
# CONFIG_CONFIGFS_FS is not set
CONFIG_MISC_FILESYSTEMS=y
# CONFIG_ADFS_FS is not set
# CONFIG_AFFS_FS is not set
# CONFIG_ECRYPT_FS is not set
# CONFIG_HFS_FS is not set
# CONFIG_HFSPLUS_FS is not set
# CONFIG_BEFS_FS is not set
# CONFIG_BFS_FS is not set
# CONFIG_EFS_FS is not set
# CONFIG_CRAMFS is not set
# CONFIG_SQUASHFS is not set
# CONFIG_VXFS_FS is not set
# CONFIG_MINIX_FS is not set
# CONFIG_OMFS_FS is not set
# CONFIG_HPFS_FS is not set
# CONFIG_QNX4FS_FS is not set
# CONFIG_ROMFS_FS is not set
# CONFIG_SYSV_FS is not set
# CONFIG_UFS_FS is not set
# CONFIG_NILFS2_FS is not set
CONFIG_NETWORK_FILESYSTEMS=y
CONFIG_NFS_FS=y
CONFIG_NFS_V3=y
CONFIG_NFS_V3_ACL=y
CONFIG_NFS_V4=y
# CONFIG_NFS_V4_1 is not set
# CONFIG_NFSD is not set
CONFIG_LOCKD=y
CONFIG_LOCKD_V4=y
CONFIG_NFS_ACL_SUPPORT=y
CONFIG_NFS_COMMON=y
CONFIG_SUNRPC=y
CONFIG_SUNRPC_GSS=y
CONFIG_RPCSEC_GSS_KRB5=y
# CONFIG_RPCSEC_GSS_SPKM3 is not set
# CONFIG_SMB_FS is not set
# CONFIG_CIFS is not set
# CONFIG_NCP_FS is not set
# CONFIG_CODA_FS is not set
# CONFIG_AFS_FS is not set

#
# Partition Types
#
CONFIG_PARTITION_ADVANCED=y
# CONFIG_ACORN_PARTITION is not set
CONFIG_OSF_PARTITION=y
CONFIG_AMIGA_PARTITION=y
# CONFIG_ATARI_PARTITION is not set
CONFIG_MAC_PARTITION=y
CONFIG_MSDOS_PARTITION=y
CONFIG_BSD_DISKLABEL=y
CONFIG_MINIX_SUBPARTITION=y
CONFIG_SOLARIS_X86_PARTITION=y
CONFIG_UNIXWARE_DISKLABEL=y
# CONFIG_LDM_PARTITION is not set
CONFIG_SGI_PARTITION=y
# CONFIG_ULTRIX_PARTITION is not set
CONFIG_SUN_PARTITION=y
CONFIG_KARMA_PARTITION=y
CONFIG_EFI_PARTITION=y
# CONFIG_SYSV68_PARTITION is not set
CONFIG_NLS=y
CONFIG_NLS_DEFAULT="utf8"
CONFIG_NLS_CODEPAGE_437=y
# CONFIG_NLS_CODEPAGE_737 is not set
# CONFIG_NLS_CODEPAGE_775 is not set
# CONFIG_NLS_CODEPAGE_850 is not set
# CONFIG_NLS_CODEPAGE_852 is not set
# CONFIG_NLS_CODEPAGE_855 is not set
# CONFIG_NLS_CODEPAGE_857 is not set
# CONFIG_NLS_CODEPAGE_860 is not set
# CONFIG_NLS_CODEPAGE_861 is not set
# CONFIG_NLS_CODEPAGE_862 is not set
# CONFIG_NLS_CODEPAGE_863 is not set
# CONFIG_NLS_CODEPAGE_864 is not set
# CONFIG_NLS_CODEPAGE_865 is not set
# CONFIG_NLS_CODEPAGE_866 is not set
# CONFIG_NLS_CODEPAGE_869 is not set
# CONFIG_NLS_CODEPAGE_936 is not set
# CONFIG_NLS_CODEPAGE_950 is not set
# CONFIG_NLS_CODEPAGE_932 is not set
# CONFIG_NLS_CODEPAGE_949 is not set
# CONFIG_NLS_CODEPAGE_874 is not set
# CONFIG_NLS_ISO8859_8 is not set
# CONFIG_NLS_CODEPAGE_1250 is not set
# CONFIG_NLS_CODEPAGE_1251 is not set
CONFIG_NLS_ASCII=y
CONFIG_NLS_ISO8859_1=y
# CONFIG_NLS_ISO8859_2 is not set
# CONFIG_NLS_ISO8859_3 is not set
# CONFIG_NLS_ISO8859_4 is not set
# CONFIG_NLS_ISO8859_5 is not set
# CONFIG_NLS_ISO8859_6 is not set
# CONFIG_NLS_ISO8859_7 is not set
# CONFIG_NLS_ISO8859_9 is not set
# CONFIG_NLS_ISO8859_13 is not set
# CONFIG_NLS_ISO8859_14 is not set
# CONFIG_NLS_ISO8859_15 is not set
# CONFIG_NLS_KOI8_R is not set
# CONFIG_NLS_KOI8_U is not set
CONFIG_NLS_UTF8=y
# CONFIG_DLM is not set

#
# Kernel hacking
#
CONFIG_TRACE_IRQFLAGS_SUPPORT=y
CONFIG_PRINTK_TIME=y
CONFIG_ALLOW_WARNINGS=y
# CONFIG_ENABLE_WARN_DEPRECATED is not set
CONFIG_ENABLE_MUST_CHECK=y
CONFIG_FRAME_WARN=2048
CONFIG_MAGIC_SYSRQ=y
# CONFIG_UNUSED_SYMBOLS is not set
CONFIG_DEBUG_FS=y
# CONFIG_HEADERS_CHECK is not set
# CONFIG_DEBUG_SECTION_MISMATCH is not set
CONFIG_DEBUG_KERNEL=y
# CONFIG_DEBUG_SHIRQ is not set
# CONFIG_DETECT_SOFTLOCKUP is not set
# CONFIG_DETECT_HUNG_TASK is not set
# CONFIG_SCHED_DEBUG is not set
CONFIG_SCHEDSTATS=y
CONFIG_TIMER_STATS=y
# CONFIG_DEBUG_OBJECTS is not set
# CONFIG_SLUB_DEBUG_ON is not set
# CONFIG_SLUB_STATS is not set
# CONFIG_DEBUG_KMEMLEAK is not set
# CONFIG_DEBUG_RT_MUTEXES is not set
# CONFIG_RT_MUTEX_TESTER is not set
# CONFIG_DEBUG_SPINLOCK is not set
# CONFIG_DEBUG_MUTEXES is not set
# CONFIG_DEBUG_LOCK_ALLOC is not set
# CONFIG_PROVE_LOCKING is not set
# CONFIG_LOCK_STAT is not set
# CONFIG_DEBUG_SPINLOCK_SLEEP is not set
# CONFIG_DEBUG_LOCKING_API_SELFTESTS is not set
CONFIG_STACKTRACE=y
CONFIG_DEBUG_BUGVERBOSE=y
# CONFIG_DEBUG_VM is not set
# CONFIG_DEBUG_VIRTUAL is not set
# CONFIG_DEBUG_WRITECOUNT is not set
CONFIG_DEBUG_MEMORY_INIT=y
# CONFIG_DEBUG_LIST is not set
# CONFIG_DEBUG_SG is not set
# CONFIG_DEBUG_NOTIFIERS is not set
CONFIG_ARCH_WANT_FRAME_POINTERS=y
CONFIG_FRAME_POINTER=y
# CONFIG_BOOT_PRINTK_DELAY is not set
# CONFIG_RCU_TORTURE_TEST is not set
# CONFIG_RCU_CPU_STALL_DETECTOR is not set
# CONFIG_KPROBES_SANITY_TEST is not set
# CONFIG_BACKTRACE_SELF_TEST is not set
# CONFIG_LKDTM is not set
# CONFIG_FAULT_INJECTION is not set
# CONFIG_LATENCYTOP is not set
CONFIG_SYSCTL_SYSCALL_CHECK=y
# CONFIG_DEBUG_PAGEALLOC is not set
CONFIG_USER_STACKTRACE_SUPPORT=y
CONFIG_NOP_TRACER=y
CONFIG_HAVE_FTRACE_NMI_ENTER=y
CONFIG_HAVE_FUNCTION_TRACER=y
CONFIG_HAVE_FUNCTION_GRAPH_TRACER=y
CONFIG_HAVE_FUNCTION_GRAPH_FP_TEST=y
CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST=y
CONFIG_HAVE_DYNAMIC_FTRACE=y
CONFIG_HAVE_FTRACE_MCOUNT_RECORD=y
CONFIG_HAVE_SYSCALL_TRACEPOINTS=y
CONFIG_TRACER_MAX_TRACE=y
CONFIG_RING_BUFFER=y
CONFIG_FTRACE_NMI_ENTER=y
CONFIG_EVENT_TRACING=y
CONFIG_CONTEXT_SWITCH_TRACER=y
CONFIG_TRACING=y
CONFIG_GENERIC_TRACER=y
CONFIG_TRACING_SUPPORT=y
CONFIG_FTRACE=y
CONFIG_FUNCTION_TRACER=y
CONFIG_FUNCTION_GRAPH_TRACER=y
# CONFIG_IRQSOFF_TRACER is not set
CONFIG_SYSPROF_TRACER=y
CONFIG_SCHED_TRACER=y
CONFIG_FTRACE_SYSCALLS=y
# CONFIG_BOOT_TRACER is not set
CONFIG_BRANCH_PROFILE_NONE=y
# CONFIG_PROFILE_ANNOTATED_BRANCHES is not set
# CONFIG_PROFILE_ALL_BRANCHES is not set
CONFIG_POWER_TRACER=y
CONFIG_KSYM_TRACER=y
CONFIG_PROFILE_KSYM_TRACER=y
# CONFIG_STACK_TRACER is not set
CONFIG_KMEMTRACE=y
CONFIG_WORKQUEUE_TRACER=y
CONFIG_BLK_DEV_IO_TRACE=y
CONFIG_DYNAMIC_FTRACE=y
# CONFIG_FUNCTION_PROFILER is not set
CONFIG_FTRACE_MCOUNT_RECORD=y
# CONFIG_FTRACE_STARTUP_TEST is not set
# CONFIG_MMIOTRACE is not set
# CONFIG_RING_BUFFER_BENCHMARK is not set
CONFIG_PROVIDE_OHCI1394_DMA_INIT=y
# CONFIG_DYNAMIC_DEBUG is not set
# CONFIG_DMA_API_DEBUG is not set
# CONFIG_SAMPLES is not set
CONFIG_HAVE_ARCH_KGDB=y
# CONFIG_KGDB is not set
CONFIG_HAVE_ARCH_KMEMCHECK=y
# CONFIG_STRICT_DEVMEM is not set
CONFIG_X86_VERBOSE_BOOTUP=y
CONFIG_EARLY_PRINTK=y
CONFIG_EARLY_PRINTK_DBGP=y
CONFIG_DEBUG_STACKOVERFLOW=y
CONFIG_DEBUG_STACK_USAGE=y
# CONFIG_DEBUG_PER_CPU_MAPS is not set
# CONFIG_X86_PTDUMP is not set
CONFIG_DEBUG_RODATA=y
# CONFIG_DEBUG_RODATA_TEST is not set
CONFIG_DEBUG_NX_TEST=m
# CONFIG_IOMMU_DEBUG is not set
# CONFIG_IOMMU_STRESS is not set
CONFIG_HAVE_MMIOTRACE_SUPPORT=y
CONFIG_IO_DELAY_TYPE_0X80=0
CONFIG_IO_DELAY_TYPE_0XED=1
CONFIG_IO_DELAY_TYPE_UDELAY=2
CONFIG_IO_DELAY_TYPE_NONE=3
CONFIG_IO_DELAY_0X80=y
# CONFIG_IO_DELAY_0XED is not set
# CONFIG_IO_DELAY_UDELAY is not set
# CONFIG_IO_DELAY_NONE is not set
CONFIG_DEFAULT_IO_DELAY_TYPE=0
CONFIG_DEBUG_BOOT_PARAMS=y
# CONFIG_CPA_DEBUG is not set
CONFIG_OPTIMIZE_INLINING=y

#
# Security options
#
CONFIG_KEYS=y
CONFIG_KEYS_DEBUG_PROC_KEYS=y
CONFIG_SECURITY=y
# CONFIG_SECURITYFS is not set
CONFIG_SECURITY_NETWORK=y
# CONFIG_SECURITY_NETWORK_XFRM is not set
# CONFIG_SECURITY_PATH is not set
CONFIG_SECURITY_FILE_CAPABILITIES=y
# CONFIG_INTEL_TXT is not set
CONFIG_LSM_MMAP_MIN_ADDR=65536
CONFIG_SECURITY_SELINUX=y
CONFIG_SECURITY_SELINUX_BOOTPARAM=y
CONFIG_SECURITY_SELINUX_BOOTPARAM_VALUE=1
CONFIG_SECURITY_SELINUX_DISABLE=y
CONFIG_SECURITY_SELINUX_DEVELOP=y
CONFIG_SECURITY_SELINUX_AVC_STATS=y
CONFIG_SECURITY_SELINUX_CHECKREQPROT_VALUE=1
# CONFIG_SECURITY_TOMOYO is not set
# CONFIG_IMA is not set
CONFIG_CRYPTO=y

#
# Crypto core or helper
#
# CONFIG_CRYPTO_FIPS is not set
CONFIG_CRYPTO_ALGAPI=y
CONFIG_CRYPTO_ALGAPI2=y
CONFIG_CRYPTO_AEAD=y
CONFIG_CRYPTO_AEAD2=y
CONFIG_CRYPTO_BLKCIPHER=y
CONFIG_CRYPTO_BLKCIPHER2=y
CONFIG_CRYPTO_HASH=y
CONFIG_CRYPTO_HASH2=y
CONFIG_CRYPTO_RNG2=y
CONFIG_CRYPTO_PCOMP=y
CONFIG_CRYPTO_MANAGER=y
CONFIG_CRYPTO_MANAGER2=y
# CONFIG_CRYPTO_GF128MUL is not set
# CONFIG_CRYPTO_NULL is not set
CONFIG_CRYPTO_WORKQUEUE=y
# CONFIG_CRYPTO_CRYPTD is not set
CONFIG_CRYPTO_AUTHENC=y
# CONFIG_CRYPTO_TEST is not set

#
# Authenticated Encryption with Associated Data
#
# CONFIG_CRYPTO_CCM is not set
# CONFIG_CRYPTO_GCM is not set
# CONFIG_CRYPTO_SEQIV is not set

#
# Block modes
#
CONFIG_CRYPTO_CBC=y
# CONFIG_CRYPTO_CTR is not set
# CONFIG_CRYPTO_CTS is not set
CONFIG_CRYPTO_ECB=y
# CONFIG_CRYPTO_LRW is not set
# CONFIG_CRYPTO_PCBC is not set
# CONFIG_CRYPTO_XTS is not set

#
# Hash modes
#
CONFIG_CRYPTO_HMAC=y
# CONFIG_CRYPTO_XCBC is not set

#
# Digest
#
# CONFIG_CRYPTO_CRC32C is not set
# CONFIG_CRYPTO_CRC32C_INTEL is not set
# CONFIG_CRYPTO_MD4 is not set
CONFIG_CRYPTO_MD5=y
# CONFIG_CRYPTO_MICHAEL_MIC is not set
# CONFIG_CRYPTO_RMD128 is not set
# CONFIG_CRYPTO_RMD160 is not set
# CONFIG_CRYPTO_RMD256 is not set
# CONFIG_CRYPTO_RMD320 is not set
CONFIG_CRYPTO_SHA1=y
# CONFIG_CRYPTO_SHA256 is not set
# CONFIG_CRYPTO_SHA512 is not set
# CONFIG_CRYPTO_TGR192 is not set
# CONFIG_CRYPTO_WP512 is not set

#
# Ciphers
#
CONFIG_CRYPTO_AES=y
# CONFIG_CRYPTO_AES_X86_64 is not set
# CONFIG_CRYPTO_AES_NI_INTEL is not set
# CONFIG_CRYPTO_ANUBIS is not set
CONFIG_CRYPTO_ARC4=y
# CONFIG_CRYPTO_BLOWFISH is not set
# CONFIG_CRYPTO_CAMELLIA is not set
# CONFIG_CRYPTO_CAST5 is not set
# CONFIG_CRYPTO_CAST6 is not set
CONFIG_CRYPTO_DES=y
# CONFIG_CRYPTO_FCRYPT is not set
# CONFIG_CRYPTO_KHAZAD is not set
# CONFIG_CRYPTO_SALSA20 is not set
# CONFIG_CRYPTO_SALSA20_X86_64 is not set
# CONFIG_CRYPTO_SEED is not set
# CONFIG_CRYPTO_SERPENT is not set
# CONFIG_CRYPTO_TEA is not set
# CONFIG_CRYPTO_TWOFISH is not set
# CONFIG_CRYPTO_TWOFISH_X86_64 is not set

#
# Compression
#
# CONFIG_CRYPTO_DEFLATE is not set
# CONFIG_CRYPTO_ZLIB is not set
# CONFIG_CRYPTO_LZO is not set

#
# Random Number Generation
#
# CONFIG_CRYPTO_ANSI_CPRNG is not set
CONFIG_CRYPTO_HW=y
# CONFIG_CRYPTO_DEV_PADLOCK is not set
# CONFIG_CRYPTO_DEV_HIFN_795X is not set
CONFIG_HAVE_KVM=y
CONFIG_HAVE_KVM_IRQCHIP=y
CONFIG_VIRTUALIZATION=y
# CONFIG_KVM is not set
# CONFIG_VIRTIO_PCI is not set
# CONFIG_VIRTIO_BALLOON is not set
CONFIG_BINARY_PRINTF=y

#
# Library routines
#
CONFIG_BITREVERSE=y
CONFIG_GENERIC_FIND_FIRST_BIT=y
CONFIG_GENERIC_FIND_NEXT_BIT=y
CONFIG_GENERIC_FIND_LAST_BIT=y
# CONFIG_CRC_CCITT is not set
# CONFIG_CRC16 is not set
CONFIG_CRC_T10DIF=y
# CONFIG_CRC_ITU_T is not set
CONFIG_CRC32=y
# CONFIG_CRC7 is not set
# CONFIG_LIBCRC32C is not set
CONFIG_ZLIB_INFLATE=y
CONFIG_DECOMPRESS_GZIP=y
CONFIG_DECOMPRESS_BZIP2=y
CONFIG_DECOMPRESS_LZMA=y
CONFIG_HAS_IOMEM=y
CONFIG_HAS_IOPORT=y
CONFIG_HAS_DMA=y
CONFIG_NLATTR=y
CONFIG_FORCE_SUCCESSFUL_BUILD=y
CONFIG_FORCE_MINIMAL_CONFIG=y
CONFIG_FORCE_MINIMAL_CONFIG_64=y
CONFIG_FORCE_MINIMAL_CONFIG_PHYS=y

[tip:sched/balancing] sched: Fix dynamic power-balancing crash

[tip-bot for Ingo Molnar]

Commit-ID:  d7ea17a76916e456fcc78e45142c66f7fb875e3d
Gitweb:     http://git.kernel.org/tip/d7ea17a76916e456fcc78e45142c66f7fb875e3d
Author:     Ingo Molnar <mingo@elte.hu>
AuthorDate: Fri, 4 Sep 2009 11:49:25 +0200
Committer:  Ingo Molnar <mingo@elte.hu>
CommitDate: Fri, 4 Sep 2009 11:52:52 +0200

sched: Fix dynamic power-balancing crash

This crash:

[ 1774.088275] divide error: 0000 [#1] SMP
[ 1774.100355] CPU 13
[ 1774.102498] Modules linked in:
[ 1774.105631] Pid: 30881, comm: hackbench Not tainted 2.6.31-rc8-tip-01308-g484d664-dirty #1629 X8DTN
[ 1774.114807] RIP: 0010:[<ffffffff81041c38>]  [<ffffffff81041c38>]
sched_balance_self+0x19b/0x2d4

Triggers because update_group_power() modifies the sd tree and does
temporary calculations there - not considering that other CPUs
could observe intermediate values, such as the zero initial value.

Calculate it in a temporary variable instead. (we need no memory
barrier as these are all statistical values anyway)

Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
LKML-Reference: <20090904092742.GA11014@elte.hu>
Signed-off-by: Ingo Molnar <mingo@elte.hu>


---
 kernel/sched.c |    7 +++++--
 1 files changed, 5 insertions(+), 2 deletions(-)

diff --git a/kernel/sched.c b/kernel/sched.c
index b537853..796baf7 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -3765,19 +3765,22 @@ static void update_group_power(struct sched_domain *sd, int cpu)
 {
 	struct sched_domain *child = sd->child;
 	struct sched_group *group, *sdg = sd->groups;
+	unsigned long power;
 
 	if (!child) {
 		update_cpu_power(sd, cpu);
 		return;
 	}
 
-	sdg->cpu_power = 0;
+	power = 0;
 
 	group = child->groups;
 	do {
-		sdg->cpu_power += group->cpu_power;
+		power += group->cpu_power;
 		group = group->next;
 	} while (group != child->groups);
+
+	sdg->cpu_power = power;
 }
 
 /**