On 06/01/2016 16:34, Bart Van Assche wrote:
On 01/06/2016 03:21 PM, Sagi Grimberg wrote:
Avoid that srpt_close_session() waits if it doesn't have to wait.
Can you explain when it doesn't have to wait? is it possible that
srpt_release_channel_work() was already triggered? isn't that a problem?
Hello Sagi,
The target core can decide to shut down an RDMA channel or a channel
shutdown can be the result of the reception of a DREQ message. It is in
the latter case that srpt_release_channel_work() can have finished
before srpt_close_session() is called.
I understood that, and the reason I asked was because of the fact that
you dereference the ch while the channel release is ongoing...
Further reading tells me this is handled in patch 15 "IB/srpt: Fix a
rare crash in srpt_close_session()" correct?
If so, should it come before this patch?
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
