On Fri, 2012-03-30 at 11:29 -0700, Roland Dreier wrote:
> From: Roland Dreier <roland@xxxxxxxxxxxxxxx>
>
> With the modern target core, se_cmd->t_data_sg already points to a
> sglist that covers the whole command. So task_sg chaining is needless
> overhead and obfuscation -- instead of splicing the split up task
> sglists back into one list, we can just use the original list directly.
>
> Signed-off-by: Roland Dreier <roland@xxxxxxxxxxxxxxx>
> ---
I've not hand a chance to fire up the p505 recently, so this driver is
likely have some other issues.
This patch looks fine to me. Applied to lio-core.git, and Cc'ing
Tomo-san here.
Thanks Roland!
--nab
> drivers/scsi/ibmvscsi/ibmvscsis.c | 18 ++++--------------
> 1 files changed, 4 insertions(+), 14 deletions(-)
>
> diff --git a/drivers/scsi/ibmvscsi/ibmvscsis.c b/drivers/scsi/ibmvscsi/ibmvscsis.c
> index 9ae8b83..20a0412 100644
> --- a/drivers/scsi/ibmvscsi/ibmvscsis.c
> +++ b/drivers/scsi/ibmvscsi/ibmvscsis.c
> @@ -417,7 +417,6 @@ static int ibmvscsis_queue_status(struct se_cmd *se_cmd);
> static int ibmvscsis_check_stop_free(struct se_cmd *se_cmd);
>
> static struct target_core_fabric_ops ibmvscsis_ops = {
> - .task_sg_chaining = 1,
> .get_fabric_name = ibmvscsis_get_fabric_name,
> .get_fabric_proto_ident = ibmvscsis_get_fabric_proto_ident,
> .tpg_get_wwn = ibmvscsis_get_fabric_wwn,
> @@ -1223,11 +1222,8 @@ static int ibmvscsis_write_pending(struct se_cmd *se_cmd)
> int ret;
>
> sc->sdb.length = se_cmd->data_length;
> -
> - transport_do_task_sg_chain(se_cmd);
> -
> - sc->sdb.table.nents = se_cmd->t_tasks_sg_chained_no;
> - sc->sdb.table.sgl = se_cmd->t_tasks_sg_chained;
> + sc->sdb.table.nents = se_cmd->t_data_nents;
> + sc->sdb.table.sgl = se_cmd->t_data_sg;
>
> ret = srp_transfer_data(sc, &vio_iu(iue)->srp.cmd,
> ibmvscsis_rdma, 1, 1);
> @@ -1255,14 +1251,8 @@ static int ibmvscsis_queue_data_in(struct se_cmd *se_cmd)
> scsi_set_resid(sc, se_cmd->residual_count);
>
> sc->sdb.length = se_cmd->data_length;
> -
> - /*
> - * Setup the struct se_task->task_sg[] chained SG list
> - */
> - transport_do_task_sg_chain(se_cmd);
> -
> - sc->sdb.table.nents = se_cmd->t_tasks_sg_chained_no;
> - sc->sdb.table.sgl = se_cmd->t_tasks_sg_chained;
> + sc->sdb.table.nents = se_cmd->t_data_nents;
> + sc->sdb.table.sgl = se_cmd->t_data_sg;
>
> /*
> * This will call srp_transfer_data() and post the response
--
To unsubscribe from this list: send the line "unsubscribe target-devel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
