On Sat, 2017-03-18 at 02:32 +0800, Ming Lei wrote: > On Sat, Mar 18, 2017 at 1:32 AM, Bart Van Assche wrote: > > + /* > > + * Avoid that the updates of the queue flags and q_usage_counter > > + * are reordered. > > + */ > > + smp_wmb(); > > atomic_inc_return() in blk_mq_freeze_queue_start() does imply a > barrier(smp_mb()). Hello Ming, It's probably a good idea to mention that in a comment. The implementation of blk_mq_freeze_queue_start() namely could be changed in the future such that it uses another atomic operation that doesn't implicitly perform smp_mb(). Thanks, Bart.
