ACPICA: fix AML mutex re-entrancy
ACPI AML supports "serialized" methods which are protected
by an implicit mutex. The mutex is re-entrant for that AML thread
to allow recursion.
However, Linux implements notify() by creating a new AML thread.
So for systems where notify() re-enters a serialized method,
deadlock results.
The fix is to use the Linux thread_id as the key to allowing
re-entrancy, not the AML thread pointer.
http://bugzilla.kernel.org/show_bug.cgi?id=5534
Signed-off-by: Alexey Starikovskiy <alexey.y.starikovskiy@linux.intel.com>
Signed-off-by: Len Brown <len.brown@intel.com>
diff --git a/drivers/acpi/dispatcher/dsmethod.c b/drivers/acpi/dispatcher/dsmethod.c
index 1cbe619..1683e5c 100644
--- a/drivers/acpi/dispatcher/dsmethod.c
+++ b/drivers/acpi/dispatcher/dsmethod.c
@@ -231,10 +231,8 @@
* Obtain the method mutex if necessary. Do not acquire mutex for a
* recursive call.
*/
- if (!walk_state ||
- !obj_desc->method.mutex->mutex.owner_thread ||
- (walk_state->thread !=
- obj_desc->method.mutex->mutex.owner_thread)) {
+ if (acpi_os_get_thread_id() !=
+ obj_desc->method.mutex->mutex.owner_thread_id) {
/*
* Acquire the method mutex. This releases the interpreter if we
* block (and reacquires it before it returns)
@@ -248,14 +246,14 @@
}
/* Update the mutex and walk info and save the original sync_level */
+ obj_desc->method.mutex->mutex.owner_thread_id =
+ acpi_os_get_thread_id();
if (walk_state) {
obj_desc->method.mutex->mutex.
original_sync_level =
walk_state->thread->current_sync_level;
- obj_desc->method.mutex->mutex.owner_thread =
- walk_state->thread;
walk_state->thread->current_sync_level =
obj_desc->method.sync_level;
} else {
@@ -569,7 +567,7 @@
acpi_os_release_mutex(method_desc->method.mutex->mutex.
os_mutex);
- method_desc->method.mutex->mutex.owner_thread = NULL;
+ method_desc->method.mutex->mutex.owner_thread_id = ACPI_MUTEX_NOT_ACQUIRED;
}
}