[CPUFREQ] Eliminate the recent lockdep warnings in cpufreq

Commit b14893a62c73af0eca414cfed505b8c09efc613c although it was very
much needed to properly cleanup ondemand timer, opened-up a can of worms
related to locking dependencies in cpufreq.

Patch here defines the need for dbs_mutex and cleans up its usage in
ondemand governor. This also resolves the lockdep warnings reported here

http://lkml.indiana.edu/hypermail/linux/kernel/0906.1/01925.html
http://lkml.indiana.edu/hypermail/linux/kernel/0907.0/00820.html

and few others..

Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
Signed-off-by: Dave Jones <davej@redhat.com>

1 files changed, 11 insertions, 16 deletions

diff --git a/drivers/cpufreq/cpufreq_ondemand.c b/drivers/cpufreq/cpufreq_ondemand.c
index 1911d17..246ae14 100644
--- a/drivers/cpufreq/cpufreq_ondemand.c
+++ b/drivers/cpufreq/cpufreq_ondemand.c
@@ -78,15 +78,10 @@ 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
- * DEADLOCK ALERT! (2) : do_dbs_timer() must not take the dbs_mutex, because it
- * would deadlock with cancel_delayed_work_sync(), which is needed for proper
- * raceless workqueue teardown.
+ * dbs_mutex protects data in dbs_tuners_ins from concurrent changes on
+ * different CPUs. It protects dbs_enable in governor start/stop. It also
+ * serializes governor limit_change with do_dbs_timer. We do not want
+ * do_dbs_timer to run when user is changing the governor or limits.
  */
 static DEFINE_MUTEX(dbs_mutex);
 
@@ -494,11 +489,10 @@ static void do_dbs_timer(struct work_struct *work)
 
 	delay -= jiffies % delay;
 
-	if (lock_policy_rwsem_write(cpu) < 0)
-		return;
+	mutex_lock(&dbs_mutex);
 
 	if (!dbs_info->enable) {
-		unlock_policy_rwsem_write(cpu);
+		mutex_unlock(&dbs_mutex);
 		return;
 	}
 
@@ -517,7 +511,7 @@ static void do_dbs_timer(struct work_struct *work)
 			dbs_info->freq_lo, CPUFREQ_RELATION_H);
 	}
 	queue_delayed_work_on(cpu, kondemand_wq, &dbs_info->work, delay);
-	unlock_policy_rwsem_write(cpu);
+	mutex_unlock(&dbs_mutex);
 }
 
 static inline void dbs_timer_init(struct cpu_dbs_info_s *dbs_info)
@@ -598,14 +592,15 @@ static int cpufreq_governor_dbs(struct cpufreq_policy *policy,
 				max(min_sampling_rate,
 				    latency * LATENCY_MULTIPLIER);
 		}
-		dbs_timer_init(this_dbs_info);
-
 		mutex_unlock(&dbs_mutex);
+
+		dbs_timer_init(this_dbs_info);
 		break;
 
 	case CPUFREQ_GOV_STOP:
-		mutex_lock(&dbs_mutex);
 		dbs_timer_exit(this_dbs_info);
+
+		mutex_lock(&dbs_mutex);
 		sysfs_remove_group(&policy->kobj, &dbs_attr_group);
 		dbs_enable--;
 		mutex_unlock(&dbs_mutex);