From 6ffae8c06fab058d6c3f8ecb7f921327721034e7 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Sat, 31 Jan 2015 06:02:44 +0530 Subject: [PATCH] cpufreq: Set cpufreq_cpu_data to NULL before putting kobject In __cpufreq_remove_dev_finish(), per-cpu 'cpufreq_cpu_data' needs to be cleared before calling kobject_put(&policy->kobj) and under cpufreq_driver_lock. Otherwise, if someone else calls cpufreq_cpu_get() in parallel with it, they can obtain a non-NULL policy from that after kobject_put(&policy->kobj) was executed. Consider this case: Thread A Thread B cpufreq_cpu_get() acquire cpufreq_driver_lock read-per-cpu cpufreq_cpu_data kobject_put(&policy->kobj); kobject_get(&policy->kobj); ... per_cpu(&cpufreq_cpu_data, cpu) = NULL And this will result in a warning like this one: ------------[ cut here ]------------ WARNING: CPU: 0 PID: 4 at include/linux/kref.h:47 kobject_get+0x41/0x50() Modules linked in: acpi_cpufreq(+) nfsd auth_rpcgss nfs_acl lockd grace sunrpc xfs libcrc32c sd_mod ixgbe igb mdio ahci hwmon ... Call Trace: [] dump_stack+0x46/0x58 [] warn_slowpath_common+0x81/0xa0 [] warn_slowpath_null+0x1a/0x20 [] kobject_get+0x41/0x50 [] cpufreq_cpu_get+0x75/0xc0 [] cpufreq_update_policy+0x2e/0x1f0 [] ? up+0x32/0x50 [] ? acpi_ns_get_node+0xcb/0xf2 [] ? acpi_evaluate_object+0x22c/0x252 [] ? acpi_get_handle+0x95/0xc0 [] ? acpi_has_method+0x25/0x40 [] acpi_processor_ppc_has_changed+0x77/0x82 [] ? move_linked_works+0x66/0x90 [] acpi_processor_notify+0x58/0xe7 [] acpi_ev_notify_dispatch+0x44/0x5c [] acpi_os_execute_deferred+0x15/0x22 [] process_one_work+0x160/0x410 [] worker_thread+0x11b/0x520 [] ? rescuer_thread+0x380/0x380 [] kthread+0xe1/0x100 [] ? kthread_create_on_node+0x1b0/0x1b0 [] ret_from_fork+0x7c/0xb0 [] ? kthread_create_on_node+0x1b0/0x1b0 ---[ end trace 89e66eb9795efdf7 ]--- The actual code flow is as follows: Thread A: Workqueue: kacpi_notify acpi_processor_notify() acpi_processor_ppc_has_changed() cpufreq_update_policy() cpufreq_cpu_get() kobject_get() Thread B: xenbus_thread() xenbus_thread() msg->u.watch.handle->callback() handle_vcpu_hotplug_event() vcpu_hotplug() cpu_down() __cpu_notify(CPU_POST_DEAD..) cpufreq_cpu_callback() __cpufreq_remove_dev_finish() cpufreq_policy_put_kobj() kobject_put() cpufreq_cpu_get() gets the policy from per-cpu variable cpufreq_cpu_data under cpufreq_driver_lock, and once it gets a valid policy it expects it to not be freed until cpufreq_cpu_put() is called. But the race happens when another thread puts the kobject first and updates cpufreq_cpu_data before or later. And so the first thread gets a valid policy structure and before it does kobject_get() on it, the second one has already done kobject_put(). Fix this by setting cpufreq_cpu_data to NULL before putting the kobject and that too under locks. Reported-by: Ethan Zhao Reported-by: Santosh Shilimkar Signed-off-by: Viresh Kumar Cc: 3.12+ # 3.12+ Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/cpufreq.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index ca69f42..2b181f7 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -1392,9 +1392,10 @@ static int __cpufreq_remove_dev_finish(struct device *dev, unsigned long flags; struct cpufreq_policy *policy; - read_lock_irqsave(&cpufreq_driver_lock, flags); + write_lock_irqsave(&cpufreq_driver_lock, flags); policy = per_cpu(cpufreq_cpu_data, cpu); - read_unlock_irqrestore(&cpufreq_driver_lock, flags); + per_cpu(cpufreq_cpu_data, cpu) = NULL; + write_unlock_irqrestore(&cpufreq_driver_lock, flags); if (!policy) { pr_debug("%s: No cpu_data found\n", __func__); @@ -1449,7 +1450,6 @@ static int __cpufreq_remove_dev_finish(struct device *dev, } } - per_cpu(cpufreq_cpu_data, cpu) = NULL; return 0; } -- 2.7.4