When commands sent down the "fast path" fail, they must be re-tried down the
normal RAID path. We do this by kicking i/o's back to the scsi mid layer with
a DID_SOFT_ERROR status, which causes them to be retried. This won't work for
SG_IO's and other non REQ_TYPE_FS i/o's which could get kicked all the way back
to the application, which may have no idea that the command needs resubmitting
and likely no way to resubmit it in such a way the that driver can recognize it
as a resubmit and send it down the normal RAID path. So we just always send
non REQ_TYPE_FS i/o's down the normal RAID path, never down the "fast path".
Signed-off-by: Stephen M. Cameron <scameron@beardog.cce.hp.com>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
if ((likely(h->transMethod & CFGTBL_Trans_io_accel1)) &&
(dev->ioaccel_handle) &&
((cmd->cmnd[0] == READ_10) || (cmd->cmnd[0] == WRITE_10)) &&
- (scsi_sg_count(cmd) <= IOACCEL1_MAXSGENTRIES))
+ (scsi_sg_count(cmd) <= IOACCEL1_MAXSGENTRIES) &&
+ likely(cmd->request->cmd_type == REQ_TYPE_FS))
return hpsa_scsi_ioaccel_queue_command(h, c);
c->Header.ReplyQueue = 0; /* unused in simple mode */