On Tue, Jun 13 2017, Ming Lei wrote: > On Tue, Jun 06, 2017 at 10:03:12AM -0600, Jens Axboe wrote: > > On 06/06/2017 09:21 AM, Ming Lei wrote: > > > Hi, > > > > > > There is one big issue in current blk_mq_quiesce_queue(): > > > > > > - in case of direct issue or BLK_MQ_S_START_ON_RUN, dispatch won't > > > be prevented after blk_mq_quiesce_queue() is returned. > > > > > > > > > The 1st two patches fix two problems in direct issue, please consider > > > it for v4.12. > > > > > > The other 10 patches improves blk_mq_quiesce_queue(), and > > > make is easy to use, and avoid race between queue restart and > > > quiescing. These 10 patches should be for v4.13. > > > > I've added 1-2 for 4.12, I'll review the rest for 4.13 when some > > cycles free up. > > Hi Jens, > > If you are fine with 3-12, could you consider it for v4.13? > > The fixes on uses of blk_mq_tagset_busy_iter() depends on > this patchset. Yes, I think it looks fine. I've applied the rest, except the nvme patch, which no longer applies since start/stop changes have been made there. Please resend that one against for-4.13/block, thanks. -- Jens Axboe
