Merge branch 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (49 commits)
  stop_machine: Move local variable closer to the usage site in cpu_stop_cpu_callback()
  sched, wait: Use wrapper functions
  sched: Remove a stale comment
  ondemand: Make the iowait-is-busy time a sysfs tunable
  ondemand: Solve a big performance issue by counting IOWAIT time as busy
  sched: Intoduce get_cpu_iowait_time_us()
  sched: Eliminate the ts->idle_lastupdate field
  sched: Fold updating of the last_update_time_info into update_ts_time_stats()
  sched: Update the idle statistics in get_cpu_idle_time_us()
  sched: Introduce a function to update the idle statistics
  sched: Add a comment to get_cpu_idle_time_us()
  cpu_stop: add dummy implementation for UP
  sched: Remove rq argument to the tracepoints
  rcu: need barrier() in UP synchronize_sched_expedited()
  sched: correctly place paranioa memory barriers in synchronize_sched_expedited()
  sched: kill paranoia check in synchronize_sched_expedited()
  sched: replace migration_thread with cpu_stop
  stop_machine: reimplement using cpu_stop
  cpu_stop: implement stop_cpu[s]()
  sched: Fix select_idle_sibling() logic in select_task_rq_fair()
  ...

2 files changed, 75 insertions, 14 deletions

diff --git a/drivers/cpufreq/cpufreq_ondemand.c b/drivers/cpufreq/cpufreq_ondemand.c
index bd444dc93cf2..8e9dbdc6c700 100644
--- a/drivers/cpufreq/cpufreq_ondemand.c
+++ b/drivers/cpufreq/cpufreq_ondemand.c
@@ -73,6 +73,7 @@ enum {DBS_NORMAL_SAMPLE, DBS_SUB_SAMPLE};
 
 struct cpu_dbs_info_s {
 	cputime64_t prev_cpu_idle;
+	cputime64_t prev_cpu_iowait;
 	cputime64_t prev_cpu_wall;
 	cputime64_t prev_cpu_nice;
 	struct cpufreq_policy *cur_policy;
@@ -108,6 +109,7 @@ static struct dbs_tuners {
 	unsigned int down_differential;
 	unsigned int ignore_nice;
 	unsigned int powersave_bias;
+	unsigned int io_is_busy;
 } dbs_tuners_ins = {
 	.up_threshold = DEF_FREQUENCY_UP_THRESHOLD,
 	.down_differential = DEF_FREQUENCY_DOWN_DIFFERENTIAL,
@@ -148,6 +150,16 @@ static inline cputime64_t get_cpu_idle_time(unsigned int cpu, cputime64_t *wall)
 	return idle_time;
 }
 
+static inline cputime64_t get_cpu_iowait_time(unsigned int cpu, cputime64_t *wall)
+{
+	u64 iowait_time = get_cpu_iowait_time_us(cpu, wall);
+
+	if (iowait_time == -1ULL)
+		return 0;
+
+	return iowait_time;
+}
+
 /*
  * Find right freq to be set now with powersave_bias on.
  * Returns the freq_hi to be used right now and will set freq_hi_jiffies,
@@ -249,6 +261,7 @@ static ssize_t show_##file_name						\
 	return sprintf(buf, "%u\n", dbs_tuners_ins.object);		\
 }
 show_one(sampling_rate, sampling_rate);
+show_one(io_is_busy, io_is_busy);
 show_one(up_threshold, up_threshold);
 show_one(ignore_nice_load, ignore_nice);
 show_one(powersave_bias, powersave_bias);
@@ -299,6 +312,23 @@ static ssize_t store_sampling_rate(struct kobject *a, struct attribute *b,
 	return count;
 }
 
+static ssize_t store_io_is_busy(struct kobject *a, struct attribute *b,
+				   const char *buf, size_t count)
+{
+	unsigned int input;
+	int ret;
+
+	ret = sscanf(buf, "%u", &input);
+	if (ret != 1)
+		return -EINVAL;
+
+	mutex_lock(&dbs_mutex);
+	dbs_tuners_ins.io_is_busy = !!input;
+	mutex_unlock(&dbs_mutex);
+
+	return count;
+}
+
 static ssize_t store_up_threshold(struct kobject *a, struct attribute *b,
 				  const char *buf, size_t count)
 {
@@ -381,6 +411,7 @@ static struct global_attr _name = \
 __ATTR(_name, 0644, show_##_name, store_##_name)
 
 define_one_rw(sampling_rate);
+define_one_rw(io_is_busy);
 define_one_rw(up_threshold);
 define_one_rw(ignore_nice_load);
 define_one_rw(powersave_bias);
@@ -392,6 +423,7 @@ static struct attribute *dbs_attributes[] = {
 	&up_threshold.attr,
 	&ignore_nice_load.attr,
 	&powersave_bias.attr,
+	&io_is_busy.attr,
 	NULL
 };
 
@@ -470,14 +502,15 @@ static void dbs_check_cpu(struct cpu_dbs_info_s *this_dbs_info)
 
 	for_each_cpu(j, policy->cpus) {
 		struct cpu_dbs_info_s *j_dbs_info;
-		cputime64_t cur_wall_time, cur_idle_time;
-		unsigned int idle_time, wall_time;
+		cputime64_t cur_wall_time, cur_idle_time, cur_iowait_time;
+		unsigned int idle_time, wall_time, iowait_time;
 		unsigned int load, load_freq;
 		int freq_avg;
 
 		j_dbs_info = &per_cpu(od_cpu_dbs_info, j);
 
 		cur_idle_time = get_cpu_idle_time(j, &cur_wall_time);
+		cur_iowait_time = get_cpu_iowait_time(j, &cur_wall_time);
 
 		wall_time = (unsigned int) cputime64_sub(cur_wall_time,
 				j_dbs_info->prev_cpu_wall);
@@ -487,6 +520,10 @@ static void dbs_check_cpu(struct cpu_dbs_info_s *this_dbs_info)
 				j_dbs_info->prev_cpu_idle);
 		j_dbs_info->prev_cpu_idle = cur_idle_time;
 
+		iowait_time = (unsigned int) cputime64_sub(cur_iowait_time,
+				j_dbs_info->prev_cpu_iowait);
+		j_dbs_info->prev_cpu_iowait = cur_iowait_time;
+
 		if (dbs_tuners_ins.ignore_nice) {
 			cputime64_t cur_nice;
 			unsigned long cur_nice_jiffies;
@@ -504,6 +541,16 @@ static void dbs_check_cpu(struct cpu_dbs_info_s *this_dbs_info)
 			idle_time += jiffies_to_usecs(cur_nice_jiffies);
 		}
 
+		/*
+		 * For the purpose of ondemand, waiting for disk IO is an
+		 * indication that you're performance critical, and not that
+		 * the system is actually idle. So subtract the iowait time
+		 * from the cpu idle time.
+		 */
+
+		if (dbs_tuners_ins.io_is_busy && idle_time >= iowait_time)
+			idle_time -= iowait_time;
+
 		if (unlikely(!wall_time || wall_time < idle_time))
 			continue;
 
@@ -617,6 +664,29 @@ static inline void dbs_timer_exit(struct cpu_dbs_info_s *dbs_info)
 	cancel_delayed_work_sync(&dbs_info->work);
 }
 
+/*
+ * Not all CPUs want IO time to be accounted as busy; this dependson how
+ * efficient idling at a higher frequency/voltage is.
+ * Pavel Machek says this is not so for various generations of AMD and old
+ * Intel systems.
+ * Mike Chan (androidlcom) calis this is also not true for ARM.
+ * Because of this, whitelist specific known (series) of CPUs by default, and
+ * leave all others up to the user.
+ */
+static int should_io_be_busy(void)
+{
+#if defined(CONFIG_X86)
+	/*
+	 * For Intel, Core 2 (model 15) andl later have an efficient idle.
+	 */
+	if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL &&
+	    boot_cpu_data.x86 == 6 &&
+	    boot_cpu_data.x86_model >= 15)
+		return 1;
+#endif
+	return 0;
+}
+
 static int cpufreq_governor_dbs(struct cpufreq_policy *policy,
 				   unsigned int event)
 {
@@ -679,6 +749,7 @@ static int cpufreq_governor_dbs(struct cpufreq_policy *policy,
 			dbs_tuners_ins.sampling_rate =
 				max(min_sampling_rate,
 				    latency * LATENCY_MULTIPLIER);
+			dbs_tuners_ins.io_is_busy = should_io_be_busy();
 		}
 		mutex_unlock(&dbs_mutex);
 
diff --git a/drivers/xen/manage.c b/drivers/xen/manage.c
index 2ac4440e7b08..8943b8ccee1a 100644
--- a/drivers/xen/manage.c
+++ b/drivers/xen/manage.c
@@ -80,12 +80,6 @@ static void do_suspend(void)
 
 	shutting_down = SHUTDOWN_SUSPEND;
 
-	err = stop_machine_create();
-	if (err) {
-		printk(KERN_ERR "xen suspend: failed to setup stop_machine %d\n", err);
-		goto out;
-	}
-
 #ifdef CONFIG_PREEMPT
 	/* If the kernel is preemptible, we need to freeze all the processes
 	   to prevent them from being in the middle of a pagetable update
@@ -93,7 +87,7 @@ static void do_suspend(void)
 	err = freeze_processes();
 	if (err) {
 		printk(KERN_ERR "xen suspend: freeze failed %d\n", err);
-		goto out_destroy_sm;
+		goto out;
 	}
 #endif
 
@@ -136,12 +130,8 @@ out_resume:
 out_thaw:
 #ifdef CONFIG_PREEMPT
 	thaw_processes();
-
-out_destroy_sm:
-#endif
-	stop_machine_destroy();
-
 out:
+#endif
 	shutting_down = SHUTDOWN_INVALID;
 }
 #endif	/* CONFIG_PM_SLEEP */