[PATCH v2 37/52] acpi-cpufreq: Fix CPU hotplug callback registration

[PATCH v2 37/52] acpi-cpufreq: Fix CPU hotplug callback registration

[Srivatsa S. Bhat]

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 acpi-cpufreq code by using this latter form of callback registration.

Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: cpufreq@vger.kernel.org
Cc: linux-pm@vger.kernel.org
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>
---

 drivers/cpufreq/acpi-cpufreq.c |    7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/cpufreq/acpi-cpufreq.c b/drivers/cpufreq/acpi-cpufreq.c
index 18448a7..245ae078e 100644
--- a/drivers/cpufreq/acpi-cpufreq.c
+++ b/drivers/cpufreq/acpi-cpufreq.c
@@ -907,15 +907,16 @@ static void __init acpi_cpufreq_boost_init(void)
 
 		acpi_cpufreq_driver.boost_supported = true;
 		acpi_cpufreq_driver.boost_enabled = boost_state(0);
-		get_online_cpus();
+
+		cpu_notifier_register_begin();
 
 		/* Force all MSRs to the same value */
 		boost_set_msrs(acpi_cpufreq_driver.boost_enabled,
 			       cpu_online_mask);
 
-		register_cpu_notifier(&boost_nb);
+		__register_cpu_notifier(&boost_nb);
 
-		put_online_cpus();
+		cpu_notifier_register_done();
 	}
 }
 

[PATCH v2 40/52] intel-idle: Fix CPU hotplug callback registration

[Srivatsa S. Bhat]

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 intel-idle code by using this latter form of callback registration.

Cc: Len Brown <lenb@kernel.org>
Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: linux-pm@vger.kernel.org
Signed-off-by: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>
---

 drivers/idle/intel_idle.c |   12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index 8e1939f..51493ed 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -681,14 +681,19 @@ static int __init intel_idle_init(void)
 	if (intel_idle_cpuidle_devices == NULL)
 		return -ENOMEM;
 
+	cpu_notifier_register_begin();
+
 	for_each_online_cpu(i) {
 		retval = intel_idle_cpu_init(i);
 		if (retval) {
+			cpu_notifier_register_done();
 			cpuidle_unregister_driver(&intel_idle_driver);
 			return retval;
 		}
 	}
-	register_cpu_notifier(&cpu_hotplug_notifier);
+	__register_cpu_notifier(&cpu_hotplug_notifier);
+
+	cpu_notifier_register_done();
 
 	return 0;
 }
@@ -698,10 +703,13 @@ static void __exit intel_idle_exit(void)
 	intel_idle_cpuidle_devices_uninit();
 	cpuidle_unregister_driver(&intel_idle_driver);
 
+	cpu_notifier_register_begin();
 
 	if (lapic_timer_reliable_states != LAPIC_TIMER_ALWAYS_RELIABLE)
 		on_each_cpu(__setup_broadcast_timer, (void *)false, 1);
-	unregister_cpu_notifier(&cpu_hotplug_notifier);
+	__unregister_cpu_notifier(&cpu_hotplug_notifier);
+
+	cpu_notifier_register_done();
 
 	return;
 }

[PATCH v2 43/52] thermal, x86-pkg-temp: Fix CPU hotplug callback registration

[Srivatsa S. Bhat]

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.zhang@intel.com>
Cc: Eduardo Valentin <eduardo.valentin@ti.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: linux-pm@vger.kernel.org
Signed-off-by: Srivatsa S. Bhat <srivatsa.bhat@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);