[PATCH] create and destroy cpufreq sysfs entries based on cpu notifiers

cpufreq entries in sysfs should only be populated when CPU is online state.
 When we either boot with maxcpus=x and then boot the other cpus by echoing
to sysfs online file, these entries should be created and destroyed when
CPU_DEAD is notified.  Same treatement as cache entries under sysfs.

We place the processor in the lowest frequency, so hw managed P-State
transitions can still work on the other threads to save power.

Primary goal was to just make these directories appear/disapper dynamically.

There is one in this patch i had to do, which i really dont like myself but
probably best if someone handling the cpufreq infrastructure could give
this code right treatment if this is not acceptable.  I guess its probably
good for the first cut.

- Converting lock_cpu_hotplug()/unlock_cpu_hotplug() to disable/enable preempt.
  The locking was smack in the middle of the notification path, when the
  hotplug is already holding the lock. I tried another solution to avoid this
  so avoid taking locks if we know we are from notification path. The solution
  was getting very ugly and i decided this was probably good for this iteration
  until someone who understands cpufreq could do a better job than me.

(akpm: export cpucontrol to GPL modules: drivers/cpufreq/cpufreq_stats.c now
does lock_cpu_hotplug())

Signed-off-by: Ashok Raj <ashok.raj@intel.com>
Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
Cc: Dave Jones <davej@codemonkey.org.uk>
Cc: Zwane Mwaikambo <zwane@holomorphy.com>
Cc: Greg KH <greg@kroah.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

1 files changed, 38 insertions, 4 deletions

diff --git a/drivers/cpufreq/cpufreq_stats.c b/drivers/cpufreq/cpufreq_stats.c
index 741b6b191e6..3597f25d5ef 100644
--- a/drivers/cpufreq/cpufreq_stats.c
+++ b/drivers/cpufreq/cpufreq_stats.c
@@ -19,6 +19,7 @@
 #include <linux/percpu.h>
 #include <linux/kobject.h>
 #include <linux/spinlock.h>
+#include <linux/notifier.h>
 #include <asm/cputime.h>
 
 static spinlock_t cpufreq_stats_lock;
@@ -298,6 +299,27 @@ cpufreq_stat_notifier_trans (struct notifier_block *nb, unsigned long val,
 	return 0;
 }
 
+static int __cpuinit cpufreq_stat_cpu_callback(struct notifier_block *nfb,
+					unsigned long action, void *hcpu)
+{
+	unsigned int cpu = (unsigned long)hcpu;
+
+	switch (action) {
+	case CPU_ONLINE:
+		cpufreq_update_policy(cpu);
+		break;
+	case CPU_DEAD:
+		cpufreq_stats_free_table(cpu);
+		break;
+	}
+	return NOTIFY_OK;
+}
+
+static struct notifier_block cpufreq_stat_cpu_notifier =
+{
+	.notifier_call = cpufreq_stat_cpu_callback,
+};
+
 static struct notifier_block notifier_policy_block = {
 	.notifier_call = cpufreq_stat_notifier_policy
 };
@@ -311,6 +333,7 @@ __init cpufreq_stats_init(void)
 {
 	int ret;
 	unsigned int cpu;
+
 	spin_lock_init(&cpufreq_stats_lock);
 	if ((ret = cpufreq_register_notifier(&notifier_policy_block,
 				CPUFREQ_POLICY_NOTIFIER)))
@@ -323,20 +346,31 @@ __init cpufreq_stats_init(void)
 		return ret;
 	}
 
-	for_each_cpu(cpu)
-		cpufreq_update_policy(cpu);
+	register_cpu_notifier(&cpufreq_stat_cpu_notifier);
+	lock_cpu_hotplug();
+	for_each_online_cpu(cpu) {
+		cpufreq_stat_cpu_callback(&cpufreq_stat_cpu_notifier, CPU_ONLINE,
+			(void *)(long)cpu);
+	}
+	unlock_cpu_hotplug();
 	return 0;
 }
 static void
 __exit cpufreq_stats_exit(void)
 {
 	unsigned int cpu;
+
 	cpufreq_unregister_notifier(&notifier_policy_block,
 			CPUFREQ_POLICY_NOTIFIER);
 	cpufreq_unregister_notifier(&notifier_trans_block,
 			CPUFREQ_TRANSITION_NOTIFIER);
-	for_each_cpu(cpu)
-		cpufreq_stats_free_table(cpu);
+	unregister_cpu_notifier(&cpufreq_stat_cpu_notifier);
+	lock_cpu_hotplug();
+	for_each_online_cpu(cpu) {
+		cpufreq_stat_cpu_callback(&cpufreq_stat_cpu_notifier, CPU_DEAD,
+			(void *)(long)cpu);
+	}
+	unlock_cpu_hotplug();
 }
 
 MODULE_AUTHOR ("Zou Nan hai <nanhai.zou@intel.com>");