Subsystems that want to register CPU hotplug callbacks, as well as perform
initialization for the CPUs that are already online, often do it as shown
below:

        get_online_cpus();

        for_each_online_cpu(cpu)
                init_cpu(cpu);

        register_cpu_notifier(&foobar_cpu_notifier);

        put_online_cpus();

This is wrong, since it is prone to ABBA deadlocks involving the
cpu_add_remove_lock and the cpu_hotplug.lock (when running concurrently
with CPU hotplug operations).

Instead, the correct and race-free way of performing the callback
registration is:

        cpu_notifier_register_begin();

        for_each_online_cpu(cpu)
                init_cpu(cpu);

        /* Note the use of the double underscored version of the API */
        __register_cpu_notifier(&foobar_cpu_notifier);

        cpu_notifier_register_done();


Fix the thermal x86-pkg-temp code by using this latter form of callback
registration.

Cc: Zhang Rui <rui.zh...@intel.com>
Cc: Eduardo Valentin <eduardo.valen...@ti.com>
Cc: Ingo Molnar <mi...@kernel.org>
Cc: linux...@vger.kernel.org
Signed-off-by: Srivatsa S. Bhat <srivatsa.b...@linux.vnet.ibm.com>
---

 drivers/thermal/x86_pkg_temp_thermal.c |   14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/thermal/x86_pkg_temp_thermal.c 
b/drivers/thermal/x86_pkg_temp_thermal.c
index 972e1c7..7592048 100644
--- a/drivers/thermal/x86_pkg_temp_thermal.c
+++ b/drivers/thermal/x86_pkg_temp_thermal.c
@@ -589,12 +589,12 @@ static int __init pkg_temp_thermal_init(void)
        platform_thermal_package_rate_control =
                        pkg_temp_thermal_platform_thermal_rate_control;
 
-       get_online_cpus();
+       cpu_notifier_register_begin();
        for_each_online_cpu(i)
                if (get_core_online(i))
                        goto err_ret;
-       register_hotcpu_notifier(&pkg_temp_thermal_notifier);
-       put_online_cpus();
+       __register_hotcpu_notifier(&pkg_temp_thermal_notifier);
+       cpu_notifier_register_done();
 
        pkg_temp_debugfs_init(); /* Don't care if fails */
 
@@ -603,7 +603,7 @@ static int __init pkg_temp_thermal_init(void)
 err_ret:
        for_each_online_cpu(i)
                put_core_offline(i);
-       put_online_cpus();
+       cpu_notifier_register_done();
        kfree(pkg_work_scheduled);
        platform_thermal_package_notify = NULL;
        platform_thermal_package_rate_control = NULL;
@@ -616,8 +616,8 @@ static void __exit pkg_temp_thermal_exit(void)
        struct phy_dev_entry *phdev, *n;
        int i;
 
-       get_online_cpus();
-       unregister_hotcpu_notifier(&pkg_temp_thermal_notifier);
+       cpu_notifier_register_begin();
+       __unregister_hotcpu_notifier(&pkg_temp_thermal_notifier);
        mutex_lock(&phy_dev_list_mutex);
        list_for_each_entry_safe(phdev, n, &phy_dev_list, list) {
                /* Retore old MSR value for package thermal interrupt */
@@ -635,7 +635,7 @@ static void __exit pkg_temp_thermal_exit(void)
        for_each_online_cpu(i)
                cancel_delayed_work_sync(
                        &per_cpu(pkg_temp_thermal_threshold_work, i));
-       put_online_cpus();
+       cpu_notifier_register_done();
 
        kfree(pkg_work_scheduled);
 

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

Reply via email to