Merge commit 'v2.6.37-rc3' into sched/core

Merge reason: Pick up latest fixes.

Signed-off-by: Ingo Molnar <mingo@elte.hu>

11 files changed, 84 insertions, 39 deletions

diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c
index 37755d6..a6e7297 100644
--- a/kernel/debug/kdb/kdb_main.c
+++ b/kernel/debug/kdb/kdb_main.c
@@ -82,7 +82,7 @@ static kdbtab_t kdb_base_commands[50];
 #define for_each_kdbcmd(cmd, num)					\
 	for ((cmd) = kdb_base_commands, (num) = 0;			\
 	     num < kdb_max_commands;					\
-	     num == KDB_BASE_CMD_MAX ? cmd = kdb_commands : cmd++, num++)
+	     num++, num == KDB_BASE_CMD_MAX ? cmd = kdb_commands : cmd++)
 
 typedef struct _kdbmsg {
 	int	km_diag;	/* kdb diagnostic */
@@ -646,7 +646,7 @@ static int kdb_defcmd2(const char *cmdstr, const char *argv0)
 	}
 	if (!s->usable)
 		return KDB_NOTIMP;
-	s->command = kmalloc((s->count + 1) * sizeof(*(s->command)), GFP_KDB);
+	s->command = kzalloc((s->count + 1) * sizeof(*(s->command)), GFP_KDB);
 	if (!s->command) {
 		kdb_printf("Could not allocate new kdb_defcmd table for %s\n",
 			   cmdstr);
@@ -2361,7 +2361,7 @@ static int kdb_pid(int argc, const char **argv)
  */
 static int kdb_ll(int argc, const char **argv)
 {
-	int diag;
+	int diag = 0;
 	unsigned long addr;
 	long offset = 0;
 	unsigned long va;
@@ -2400,20 +2400,21 @@ static int kdb_ll(int argc, const char **argv)
 		char buf[80];
 
 		if (KDB_FLAG(CMD_INTERRUPT))
-			return 0;
+			goto out;
 
 		sprintf(buf, "%s " kdb_machreg_fmt "\n", command, va);
 		diag = kdb_parse(buf);
 		if (diag)
-			return diag;
+			goto out;
 
 		addr = va + linkoffset;
 		if (kdb_getword(&va, addr, sizeof(va)))
-			return 0;
+			goto out;
 	}
-	kfree(command);
 
-	return 0;
+out:
+	kfree(command);
+	return diag;
 }
 
 static int kdb_kgdb(int argc, const char **argv)
@@ -2739,13 +2740,13 @@ int kdb_register_repeat(char *cmd,
 		}
 		if (kdb_commands) {
 			memcpy(new, kdb_commands,
-			       kdb_max_commands * sizeof(*new));
+			  (kdb_max_commands - KDB_BASE_CMD_MAX) * sizeof(*new));
 			kfree(kdb_commands);
 		}
 		memset(new + kdb_max_commands, 0,
 		       kdb_command_extend * sizeof(*new));
 		kdb_commands = new;
-		kp = kdb_commands + kdb_max_commands;
+		kp = kdb_commands + kdb_max_commands - KDB_BASE_CMD_MAX;
 		kdb_max_commands += kdb_command_extend;
 	}
 
diff --git a/kernel/futex.c b/kernel/futex.c
index 6c683b3..40a8777 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -2489,7 +2489,8 @@ void exit_robust_list(struct task_struct *curr)
 {
 	struct robust_list_head __user *head = curr->robust_list;
 	struct robust_list __user *entry, *next_entry, *pending;
-	unsigned int limit = ROBUST_LIST_LIMIT, pi, next_pi, pip;
+	unsigned int limit = ROBUST_LIST_LIMIT, pi, pip;
+	unsigned int uninitialized_var(next_pi);
 	unsigned long futex_offset;
 	int rc;
 
diff --git a/kernel/futex_compat.c b/kernel/futex_compat.c
index 06da4df..a7934ac 100644
--- a/kernel/futex_compat.c
+++ b/kernel/futex_compat.c
@@ -49,7 +49,8 @@ void compat_exit_robust_list(struct task_struct *curr)
 {
 	struct compat_robust_list_head __user *head = curr->compat_robust_list;
 	struct robust_list __user *entry, *next_entry, *pending;
-	unsigned int limit = ROBUST_LIST_LIMIT, pi, next_pi, pip;
+	unsigned int limit = ROBUST_LIST_LIMIT, pi, pip;
+	unsigned int uninitialized_var(next_pi);
 	compat_uptr_t uentry, next_uentry, upending;
 	compat_long_t futex_offset;
 	int rc;
diff --git a/kernel/pm_qos_params.c b/kernel/pm_qos_params.c
index c7a8f45..aeaa7f8 100644
--- a/kernel/pm_qos_params.c
+++ b/kernel/pm_qos_params.c
@@ -121,10 +121,10 @@ static inline int pm_qos_get_value(struct pm_qos_object *o)
 
 	switch (o->type) {
 	case PM_QOS_MIN:
-		return plist_last(&o->requests)->prio;
+		return plist_first(&o->requests)->prio;
 
 	case PM_QOS_MAX:
-		return plist_first(&o->requests)->prio;
+		return plist_last(&o->requests)->prio;
 
 	default:
 		/* runtime check for not using enum */
diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig
index 29bff61..a5aff3e 100644
--- a/kernel/power/Kconfig
+++ b/kernel/power/Kconfig
@@ -246,9 +246,13 @@ config PM_OPS
 	depends on PM_SLEEP || PM_RUNTIME
 	default y
 
+config ARCH_HAS_OPP
+	bool
+
 config PM_OPP
 	bool "Operating Performance Point (OPP) Layer library"
 	depends on PM
+	depends on ARCH_HAS_OPP
 	---help---
 	  SOCs have a standard set of tuples consisting of frequency and
 	  voltage pairs that the device will support per voltage domain. This
diff --git a/kernel/sched.c b/kernel/sched.c
index 324afce..3e8a7db 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -557,18 +557,8 @@ struct rq {
 
 static DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
 
-static inline
-void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags)
-{
-	rq->curr->sched_class->check_preempt_curr(rq, p, flags);
 
-	/*
-	 * A queue event has occurred, and we're going to schedule.  In
-	 * this case, we can save a useless back to back clock update.
-	 */
-	if (test_tsk_need_resched(p))
-		rq->skip_clock_update = 1;
-}
+static void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags);
 
 static inline int cpu_of(struct rq *rq)
 {
@@ -1980,6 +1970,31 @@ static inline void check_class_changed(struct rq *rq, struct task_struct *p,
 		p->sched_class->prio_changed(rq, p, oldprio, running);
 }
 
+static void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags)
+{
+	const struct sched_class *class;
+
+	if (p->sched_class == rq->curr->sched_class) {
+		rq->curr->sched_class->check_preempt_curr(rq, p, flags);
+	} else {
+		for_each_class(class) {
+			if (class == rq->curr->sched_class)
+				break;
+			if (class == p->sched_class) {
+				resched_task(rq->curr);
+				break;
+			}
+		}
+	}
+
+	/*
+	 * A queue event has occurred, and we're going to schedule.  In
+	 * this case, we can save a useless back to back clock update.
+	 */
+	if (test_tsk_need_resched(rq->curr))
+		rq->skip_clock_update = 1;
+}
+
 #ifdef CONFIG_SMP
 /*
  * Is this task likely cache-hot:
@@ -6737,6 +6752,8 @@ static void init_sched_groups_power(int cpu, struct sched_domain *sd)
 	if (cpu != group_first_cpu(sd->groups))
 		return;
 
+	sd->groups->group_weight = cpumask_weight(sched_group_cpus(sd->groups));
+
 	child = sd->child;
 
 	sd->groups->cpu_power = 0;
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 82fd884..fdbdb50 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -1799,12 +1799,6 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_
 	struct cfs_rq *cfs_rq = task_cfs_rq(curr);
 	int scale = cfs_rq->nr_running >= sched_nr_latency;
 
-	if (unlikely(rt_prio(p->prio)))
-		goto preempt;
-
-	if (unlikely(p->sched_class != &fair_sched_class))
-		return;
-
 	if (unlikely(se == pse))
 		return;
 
@@ -2226,13 +2220,16 @@ struct sd_lb_stats {
 	unsigned long this_load_per_task;
 	unsigned long this_nr_running;
 	unsigned long this_has_capacity;
+	unsigned int  this_idle_cpus;
 
 	/* Statistics of the busiest group */
+	unsigned int  busiest_idle_cpus;
 	unsigned long max_load;
 	unsigned long busiest_load_per_task;
 	unsigned long busiest_nr_running;
 	unsigned long busiest_group_capacity;
 	unsigned long busiest_has_capacity;
+	unsigned int  busiest_group_weight;
 
 	int group_imb; /* Is there imbalance in this sd */
 #if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
@@ -2254,6 +2251,8 @@ struct sg_lb_stats {
 	unsigned long sum_nr_running; /* Nr tasks running in the group */
 	unsigned long sum_weighted_load; /* Weighted load of group's tasks */
 	unsigned long group_capacity;
+	unsigned long idle_cpus;
+	unsigned long group_weight;
 	int group_imb; /* Is there an imbalance in the group ? */
 	int group_has_capacity; /* Is there extra capacity in the group? */
 };
@@ -2622,7 +2621,8 @@ static inline void update_sg_lb_stats(struct sched_domain *sd,
 		sgs->group_load += load;
 		sgs->sum_nr_running += rq->nr_running;
 		sgs->sum_weighted_load += weighted_cpuload(i);
-
+		if (idle_cpu(i))
+			sgs->idle_cpus++;
 	}
 
 	/*
@@ -2660,6 +2660,7 @@ static inline void update_sg_lb_stats(struct sched_domain *sd,
 	sgs->group_capacity = DIV_ROUND_CLOSEST(group->cpu_power, SCHED_LOAD_SCALE);
 	if (!sgs->group_capacity)
 		sgs->group_capacity = fix_small_capacity(sd, group);
+	sgs->group_weight = group->group_weight;
 
 	if (sgs->group_capacity > sgs->sum_nr_running)
 		sgs->group_has_capacity = 1;
@@ -2767,13 +2768,16 @@ static inline void update_sd_lb_stats(struct sched_domain *sd, int this_cpu,
 			sds->this_nr_running = sgs.sum_nr_running;
 			sds->this_load_per_task = sgs.sum_weighted_load;
 			sds->this_has_capacity = sgs.group_has_capacity;
+			sds->this_idle_cpus = sgs.idle_cpus;
 		} else if (update_sd_pick_busiest(sd, sds, sg, &sgs, this_cpu)) {
 			sds->max_load = sgs.avg_load;
 			sds->busiest = sg;
 			sds->busiest_nr_running = sgs.sum_nr_running;
+			sds->busiest_idle_cpus = sgs.idle_cpus;
 			sds->busiest_group_capacity = sgs.group_capacity;
 			sds->busiest_load_per_task = sgs.sum_weighted_load;
 			sds->busiest_has_capacity = sgs.group_has_capacity;
+			sds->busiest_group_weight = sgs.group_weight;
 			sds->group_imb = sgs.group_imb;
 		}
 
@@ -3051,8 +3055,26 @@ find_busiest_group(struct sched_domain *sd, int this_cpu,
 	if (sds.this_load >= sds.avg_load)
 		goto out_balanced;
 
-	if (100 * sds.max_load <= sd->imbalance_pct * sds.this_load)
-		goto out_balanced;
+	/*
+	 * In the CPU_NEWLY_IDLE, use imbalance_pct to be conservative.
+	 * And to check for busy balance use !idle_cpu instead of
+	 * CPU_NOT_IDLE. This is because HT siblings will use CPU_NOT_IDLE
+	 * even when they are idle.
+	 */
+	if (idle == CPU_NEWLY_IDLE || !idle_cpu(this_cpu)) {
+		if (100 * sds.max_load <= sd->imbalance_pct * sds.this_load)
+			goto out_balanced;
+	} else {
+		/*
+		 * This cpu is idle. If the busiest group load doesn't
+		 * have more tasks than the number of available cpu's and
+		 * there is no imbalance between this and busiest group
+		 * wrt to idle cpu's, it is balanced.
+		 */
+		if ((sds.this_idle_cpus  <= sds.busiest_idle_cpus + 1) &&
+		    sds.busiest_nr_running <= sds.busiest_group_weight)
+			goto out_balanced;
+	}
 
 force_balance:
 	/* Looks like there is an imbalance. Compute it */
diff --git a/kernel/sched_stoptask.c b/kernel/sched_stoptask.c
index 45bddc0..2bf6b47 100644
--- a/kernel/sched_stoptask.c
+++ b/kernel/sched_stoptask.c
@@ -19,14 +19,14 @@ select_task_rq_stop(struct rq *rq, struct task_struct *p,
 static void
 check_preempt_curr_stop(struct rq *rq, struct task_struct *p, int flags)
 {
-	resched_task(rq->curr); /* we preempt everything */
+	/* we're never preempted */
 }
 
 static struct task_struct *pick_next_task_stop(struct rq *rq)
 {
 	struct task_struct *stop = rq->stop;
 
-	if (stop && stop->state == TASK_RUNNING)
+	if (stop && stop->se.on_rq)
 		return stop;
 
 	return NULL;
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 9b520d7..a00fdef 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -690,7 +690,6 @@ static struct ctl_table kern_table[] = {
 		.extra1		= &zero,
 		.extra2		= &ten_thousand,
 	},
-#endif
 	{
 		.procname	= "dmesg_restrict",
 		.data		= &dmesg_restrict,
@@ -700,6 +699,7 @@ static struct ctl_table kern_table[] = {
 		.extra1		= &zero,
 		.extra2		= &one,
 	},
+#endif
 	{
 		.procname	= "ngroups_max",
 		.data		= &ngroups_max,
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index e04b8bc..ea37e2f 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -126,7 +126,7 @@ if FTRACE
 config FUNCTION_TRACER
 	bool "Kernel Function Tracer"
 	depends on HAVE_FUNCTION_TRACER
-	select FRAME_POINTER if (!ARM_UNWIND)
+	select FRAME_POINTER if !ARM_UNWIND && !S390
 	select KALLSYMS
 	select GENERIC_TRACER
 	select CONTEXT_SWITCH_TRACER
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 82d9b81..0420841 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -17,7 +17,6 @@
 #include <linux/writeback.h>
 #include <linux/kallsyms.h>
 #include <linux/seq_file.h>
-#include <linux/smp_lock.h>
 #include <linux/notifier.h>
 #include <linux/irqflags.h>
 #include <linux/debugfs.h>