Re: [PATCH RFC] IB/iser: add task reference counter for tx commands

[Sagi Grimberg <sagi@grimberg.me>]

> Hi Kashyap Desai,
> 
> Unfortunately, there is a wider problem in iser that we do the local 
> invalidation if any, after we complete the iscsi task.
> So the right solution is to do the logic we have in NVMe/RDMA that 
> checks if remote invalidation happened and if not, it does local 
> invalidation.
> And the task is released after getting the send_completion and 
> local_invalidation/remote invalidation.
> 
> There is some infrastructure work needed to be done there.
> 
> Sagi,
> 
> Please remind me few things regarding the iSCSI bidir cmds.
> 
> In case of bidir IO cmd, if we need to use a reg_mr for it - I see a 
> potential problem there.

Not surprising.

> Is this scenario possible ?

There is no longer bidi support in scsi.
See patch: ae3d56d81507 ("scsi: remove bidirectional command support")

> I'm asking because if it is possible, so what happens in remote 
> invalidation ? what key is invalidated ? the read_key or the write_key ? 
> in ib_isert there is a priority to the read_key (is it by the spec ?).

The spec never addressed this. It wasn't well defined what to do with
remote invalidation for bidi commands.

> We don't consider this in the iser recv completion and the remote 
> invalidation checker logic.
> If it's not possible we should re-design few components in the code and 
> fix the issue that we do local_invalidation of cmd N during the send of 
> cmd N + 1.

We shouldn't bother, no consumer of this is left.