On 10/03/2011 12:29 PM, vikas.chaudhary@xxxxxxxxxx wrote:
> From: Manish Rangankar <manish.rangankar@xxxxxxxxxx>
>
> Devices are getting blocked during continuous link up and down. Solution is,
> during relogin unblock the session before sending connection logged in event.
>
> JIRA Key: UPSISCSI-138
>
> Signed-off-by: Manish Rangankar <manish.rangankar@xxxxxxxxxx>
> Signed-off-by: Vikas Chaudhary <vikas.chaudhary@xxxxxxxxxx>
> ---
> drivers/scsi/qla4xxx/ql4_init.c | 1 +
> 1 files changed, 1 insertions(+), 0 deletions(-)
>
> diff --git a/drivers/scsi/qla4xxx/ql4_init.c b/drivers/scsi/qla4xxx/ql4_init.c
> index cc10bac..e07d99b 100644
> --- a/drivers/scsi/qla4xxx/ql4_init.c
> +++ b/drivers/scsi/qla4xxx/ql4_init.c
> @@ -900,6 +900,7 @@ int qla4xxx_process_ddb_changed(struct scsi_qla_host *ha, uint32_t fw_ddb_index,
> switch (state) {
> case DDB_DS_SESSION_ACTIVE:
> case DDB_DS_DISCOVERY:
> + iscsi_unblock_session(ddb_entry->sess);
Shouldn't this alreadu get done when start_conn callback is called?
Is the problem that start_conn is getting called when login is started
and not when we are actually logged in (when we get the logged in event
below)?
The start_conn callback use looks wrong right now for qla4xxx.
user/initiator.c:setup_offload_login_phase() will call it when we are
only in_login. It should only be called when we are logged_in, because
it will unlbock the devices, update the iscsi session state and could
start IO before the driver is ready.
> iscsi_conn_login_event(ddb_entry->conn,
> ISCSI_CONN_STATE_LOGGED_IN);
> qla4xxx_update_session_conn_param(ha, ddb_entry);
--
To unsubscribe from this list: send the line "unsubscribe linux-scsi" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
