summaryrefslogtreecommitdiffstats
path: root/include/acpi
diff options
context:
space:
mode:
authorRafael J. Wysocki <rafael.j.wysocki@intel.com>2013-08-06 02:26:22 +0200
committerRafael J. Wysocki <rafael.j.wysocki@intel.com>2013-08-06 02:26:22 +0200
commit623cf33cb055b1e81fa47e4fc16789b2c129e31e (patch)
tree7f0f56d1d21be4ce727b3d2433f9379b6a363dc3 /include/acpi
parentb3b301c5fed8a0868e56c98b922cb0c881b3857d (diff)
downloadlinux-623cf33cb055b1e81fa47e4fc16789b2c129e31e.tar.gz
linux-623cf33cb055b1e81fa47e4fc16789b2c129e31e.tar.bz2
linux-623cf33cb055b1e81fa47e4fc16789b2c129e31e.zip
ACPI / PM: Walk physical_node_list under physical_node_lock
The list of physical devices corresponding to an ACPI device object is walked by acpi_system_wakeup_device_seq_show() and physical_device_enable_wakeup() without taking that object's physical_node_lock mutex. Since each of those functions may be run at any time as a result of a user space action, the lack of appropriate locking in them may lead to a kernel crash if that happens during device hot-add or hot-remove involving the device object in question. Fix the issue by modifying acpi_system_wakeup_device_seq_show() and physical_device_enable_wakeup() to use physical_node_lock as appropriate. Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Cc: All <stable@vger.kernel.org>
Diffstat (limited to 'include/acpi')
0 files changed, 0 insertions, 0 deletions