X-Git-Url: http://git.onelab.eu/?a=blobdiff_plain;f=drivers%2Fcpufreq%2Fcpufreq_conservative.c;h=eef0270c6f3ddf98b23b3495628a60894199ec10;hb=refs%2Fheads%2Fvserver;hp=e07a35487bde7cf5b713c0c203a4819a537ae901;hpb=43bc926fffd92024b46cafaf7350d669ba9ca884;p=linux-2.6.git

diff --git a/drivers/cpufreq/cpufreq_conservative.c b/drivers/cpufreq/cpufreq_conservative.c
index e07a35487..eef0270c6 100644
--- a/drivers/cpufreq/cpufreq_conservative.c
+++ b/drivers/cpufreq/cpufreq_conservative.c
@@ -22,6 +22,7 @@
 #include <linux/types.h>
 #include <linux/fs.h>
 #include <linux/sysfs.h>
+#include <linux/cpu.h>
 #include <linux/sched.h>
 #include <linux/kmod.h>
 #include <linux/workqueue.h>
@@ -43,22 +44,24 @@
  * latency of the processor. The governor will work on any processor with 
  * transition latency <= 10mS, using appropriate sampling 
  * rate.
- * For CPUs with transition latency > 10mS (mostly drivers with CPUFREQ_ETERNAL)
- * this governor will not work.
+ * For CPUs with transition latency > 10mS (mostly drivers
+ * with CPUFREQ_ETERNAL), this governor will not work.
  * All times here are in uS.
  */
 static unsigned int 				def_sampling_rate;
 #define MIN_SAMPLING_RATE_RATIO			(2)
 /* for correct statistics, we need at least 10 ticks between each measure */
-#define MIN_STAT_SAMPLING_RATE			(MIN_SAMPLING_RATE_RATIO * jiffies_to_usecs(10))
-#define MIN_SAMPLING_RATE			(def_sampling_rate / MIN_SAMPLING_RATE_RATIO)
+#define MIN_STAT_SAMPLING_RATE			\
+			(MIN_SAMPLING_RATE_RATIO * jiffies_to_usecs(10))
+#define MIN_SAMPLING_RATE			\
+			(def_sampling_rate / MIN_SAMPLING_RATE_RATIO)
 #define MAX_SAMPLING_RATE			(500 * def_sampling_rate)
 #define DEF_SAMPLING_RATE_LATENCY_MULTIPLIER	(1000)
 #define DEF_SAMPLING_DOWN_FACTOR		(1)
 #define MAX_SAMPLING_DOWN_FACTOR		(10)
 #define TRANSITION_LATENCY_LIMIT		(10 * 1000)
 
-static void do_dbs_timer(void *data);
+static void do_dbs_timer(struct work_struct *work);
 
 struct cpu_dbs_info_s {
 	struct cpufreq_policy 	*cur_policy;
@@ -72,8 +75,16 @@ static DEFINE_PER_CPU(struct cpu_dbs_info_s, cpu_dbs_info);
 
 static unsigned int dbs_enable;	/* number of CPUs using this policy */
 
+/*
+ * DEADLOCK ALERT! There is a ordering requirement between cpu_hotplug
+ * lock and dbs_mutex. cpu_hotplug lock should always be held before
+ * dbs_mutex. If any function that can potentially take cpu_hotplug lock
+ * (like __cpufreq_driver_target()) is being called with dbs_mutex taken, then
+ * cpu_hotplug lock should be taken before that. Note that cpu_hotplug lock
+ * is recursive for the same process. -Venki
+ */
 static DEFINE_MUTEX 	(dbs_mutex);
-static DECLARE_WORK	(dbs_work, do_dbs_timer, NULL);
+static DECLARE_DELAYED_WORK(dbs_work, do_dbs_timer);
 
 struct dbs_tuners {
 	unsigned int 		sampling_rate;
@@ -94,11 +105,16 @@ static struct dbs_tuners dbs_tuners_ins = {
 
 static inline unsigned int get_cpu_idle_time(unsigned int cpu)
 {
-	return	kstat_cpu(cpu).cpustat.idle +
+	unsigned int add_nice = 0, ret;
+
+	if (dbs_tuners_ins.ignore_nice)
+		add_nice = kstat_cpu(cpu).cpustat.nice;
+
+	ret = 	kstat_cpu(cpu).cpustat.idle +
 		kstat_cpu(cpu).cpustat.iowait +
-		( dbs_tuners_ins.ignore_nice ?
-		  kstat_cpu(cpu).cpustat.nice :
-		  0);
+		add_nice;
+
+	return ret;
 }
 
 /************************** sysfs interface ************************/
@@ -411,20 +427,21 @@ static void dbs_check_cpu(int cpu)
 	}
 }
 
-static void do_dbs_timer(void *data)
+static void do_dbs_timer(struct work_struct *work)
 { 
 	int i;
+	lock_cpu_hotplug();
 	mutex_lock(&dbs_mutex);
 	for_each_online_cpu(i)
 		dbs_check_cpu(i);
 	schedule_delayed_work(&dbs_work, 
 			usecs_to_jiffies(dbs_tuners_ins.sampling_rate));
 	mutex_unlock(&dbs_mutex);
+	unlock_cpu_hotplug();
 } 
 
 static inline void dbs_timer_init(void)
 {
-	INIT_WORK(&dbs_work, do_dbs_timer, NULL);
 	schedule_delayed_work(&dbs_work,
 			usecs_to_jiffies(dbs_tuners_ins.sampling_rate));
 	return;
@@ -442,6 +459,7 @@ static int cpufreq_governor_dbs(struct cpufreq_policy *policy,
 	unsigned int cpu = policy->cpu;
 	struct cpu_dbs_info_s *this_dbs_info;
 	unsigned int j;
+	int rc;
 
 	this_dbs_info = &per_cpu(cpu_dbs_info, cpu);
 
@@ -458,6 +476,13 @@ static int cpufreq_governor_dbs(struct cpufreq_policy *policy,
 			break;
 		 
 		mutex_lock(&dbs_mutex);
+
+		rc = sysfs_create_group(&policy->kobj, &dbs_attr_group);
+		if (rc) {
+			mutex_unlock(&dbs_mutex);
+			return rc;
+		}
+
 		for_each_cpu_mask(j, policy->cpus) {
 			struct cpu_dbs_info_s *j_dbs_info;
 			j_dbs_info = &per_cpu(cpu_dbs_info, j);
@@ -470,7 +495,7 @@ static int cpufreq_governor_dbs(struct cpufreq_policy *policy,
 		this_dbs_info->enable = 1;
 		this_dbs_info->down_skip = 0;
 		this_dbs_info->requested_freq = policy->cur;
-		sysfs_create_group(&policy->kobj, &dbs_attr_group);
+
 		dbs_enable++;
 		/*
 		 * Start the timerschedule work, when this governor