On Tue, 2017-08-01 at 18:44 +0800, Ming Lei wrote:

On Mon, Jul 31, 2017 at 11:42:21PM +0000, Bart Van Assche wrote:

quoted

Since setting, clearing and testing of BLK_MQ_S_BUSY can happen concurr=

ently

quoted

and since clearing and testing happens without any locks held I'm afrai=

d this

quoted

patch introduces the following race conditions:
[ ... ]
* Checking BLK_MQ_S_BUSY after requests have been removed from the disp=

atch list

quoted

  but before that bit is cleared, resulting in test_bit(BLK_MQ_S_BUSY, =

&hctx->state)

quoted

  reporting that the BLK_MQ_S_BUSY
has been set although there are no requests
  on the dispatch list.

=20
That won't be a problem, because dispatch will be started in the
context in which dispatch list is flushed, since the BUSY bit
is cleared after blk_mq_dispatch_rq_list() returns. So no I/O
hang.

Hello Ming,

Please consider changing the name of the BLK_MQ_S_BUSY constant. That bit
is used to serialize dispatching requests from the hctx dispatch list but
that's not clear from the name of that constant.

Thanks,

Bart.=