[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>

3 files changed, 103 insertions, 9 deletions

diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 346906a96e8b..6c6121b85a54 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -4,6 +4,9 @@
  *  Copyright (C) 2001 Russell King
  *            (C) 2002 - 2003 Dominik Brodowski <linux@brodo.de>
  *
+ *  Oct 2005 - Ashok Raj <ashok.raj@intel.com>
+ *                      Added handling for CPU hotplug
+ *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
@@ -567,6 +570,9 @@ static int cpufreq_add_dev (struct sys_device * sys_dev)
         unsigned long flags;
         unsigned int j;
 
+        if (cpu_is_offline(cpu))
+                return 0;
+
         cpufreq_debug_disable_ratelimit();
         dprintk("adding CPU %u\n", cpu);
 
@@ -673,7 +679,7 @@ err_out:
 
 nomem_out:
         module_put(cpufreq_driver->owner);
- module_out:
+module_out:
         cpufreq_debug_enable_ratelimit();
         return ret;
 }
@@ -762,7 +768,6 @@ static int cpufreq_remove_dev (struct sys_device * sys_dev)
         down(&data->lock);
         if (cpufreq_driver->target)
                 __cpufreq_governor(data, CPUFREQ_GOV_STOP);
-        cpufreq_driver->target = NULL;
         up(&data->lock);
 
         kobject_unregister(&data->kobj);
@@ -1109,17 +1114,30 @@ int __cpufreq_driver_target(struct cpufreq_policy *policy,
                             unsigned int relation)
 {
         int retval = -EINVAL;
-        lock_cpu_hotplug();
+
+        /*
+         * Converted the lock_cpu_hotplug to preempt_disable()
+         * and preempt_enable(). This is a bit kludgy and relies on how cpu
+         * hotplug works. All we need is a guarantee that cpu hotplug won't make
+         * progress on any cpu. Once we do preempt_disable(), this would ensure
+         * that hotplug threads don't get onto this cpu, thereby delaying
+         * the cpu remove process.
+         *
+         * We removed the lock_cpu_hotplug since we need to call this function
+         * via cpu hotplug callbacks, which result in locking the cpu hotplug
+         * thread itself. Agree this is not very clean, cpufreq community
+         * could improve this if required. - Ashok Raj <ashok.raj@intel.com>
+         */
+        preempt_disable();
         dprintk("target for CPU %u: %u kHz, relation %u\n", policy->cpu,
                 target_freq, relation);
         if (cpu_online(policy->cpu) && cpufreq_driver->target)
                 retval = cpufreq_driver->target(policy, target_freq, relation);
-        unlock_cpu_hotplug();
+        preempt_enable();
         return retval;
 }
 EXPORT_SYMBOL_GPL(__cpufreq_driver_target);
 
-
 int cpufreq_driver_target(struct cpufreq_policy *policy,
                           unsigned int target_freq,
                           unsigned int relation)
@@ -1406,6 +1424,45 @@ int cpufreq_update_policy(unsigned int cpu)
 }
 EXPORT_SYMBOL(cpufreq_update_policy);
 
+static int __cpuinit cpufreq_cpu_callback(struct notifier_block *nfb,
+                                        unsigned long action, void *hcpu)
+{
+        unsigned int cpu = (unsigned long)hcpu;
+        struct cpufreq_policy *policy;
+        struct sys_device *sys_dev;
+
+        sys_dev = get_cpu_sysdev(cpu);
+
+        if (sys_dev) {
+                switch (action) {
+                case CPU_ONLINE:
+                        cpufreq_add_dev(sys_dev);
+                        break;
+                case CPU_DOWN_PREPARE:
+                        /*
+                         * We attempt to put this cpu in lowest frequency
+                         * possible before going down. This will permit
+                         * hardware-managed P-State to switch other related
+                         * threads to min or higher speeds if possible.
+                         */
+                        policy = cpufreq_cpu_data[cpu];
+                        if (policy) {
+                                cpufreq_driver_target(policy, policy->min,
+                                                CPUFREQ_RELATION_H);
+                        }
+                        break;
+                case CPU_DEAD:
+                        cpufreq_remove_dev(sys_dev);
+                        break;
+                }
+        }
+        return NOTIFY_OK;
+}
+
+static struct notifier_block cpufreq_cpu_notifier =
+{
+    .notifier_call = cpufreq_cpu_callback,
+};
 
 /*********************************************************************
  *               REGISTER / UNREGISTER CPUFREQ DRIVER                *
@@ -1466,6 +1523,7 @@ int cpufreq_register_driver(struct cpufreq_driver *driver_data)
         }
 
         if (!ret) {
+                register_cpu_notifier(&cpufreq_cpu_notifier);
                 dprintk("driver %s up and running\n", driver_data->name);
                 cpufreq_debug_enable_ratelimit();
         }
@@ -1497,6 +1555,7 @@ int cpufreq_unregister_driver(struct cpufreq_driver *driver)
         dprintk("unregistering driver %s\n", driver->name);
 
         sysdev_driver_unregister(&cpu_sysdev_class, &cpufreq_sysdev_driver);
+        unregister_cpu_notifier(&cpufreq_cpu_notifier);
 
         spin_lock_irqsave(&cpufreq_driver_lock, flags);
         cpufreq_driver = NULL;
diff --git a/drivers/cpufreq/cpufreq_stats.c b/drivers/cpufreq/cpufreq_stats.c
index 741b6b191e6a..3597f25d5efa 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>");
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 53d8263ae12e..3619e939182e 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -17,6 +17,7 @@
 
 /* This protects CPUs going up and down... */
 DECLARE_MUTEX(cpucontrol);
+EXPORT_SYMBOL_GPL(cpucontrol);
 
 static struct notifier_block *cpu_chain;