[SCSI] mpt2sas: WarpDrive Infinite command retries due to wrong scsi command entry in MPI message

Issue:

This issue is seen on LSI H/W WarpDrive SSS6200 When filed direct I/O
is tried as volume I/O the scmd field in internal lookup table get
cleared and because of that the retried volume I/O never gets reported
as completed to SML.

Result:

I/O timeout and Error handling thread will kicking off

Fix:

Setting back the scmd in the lookup table before retrying the failed
direct i/o

Signed-off-by: Kashyap Desai <[e-mail]>
Signed-off-by: James Bottomley <[e-mail]>

drivers/scsi/mpt2sas/mpt2sas_scsih.c

···
 	u32 log_info;
 	struct MPT2SAS_DEVICE *sas_device_priv_data;
 	u32 response_code = 0;
+	unsigned long flags;
 
 	mpi_reply = mpt2sas_base_get_reply_virt_addr(ioc, reply);
 	scmd = _scsih_scsi_lookup_get_clear(ioc, smid);
···
 	 * the failed direct I/O should be redirected to volume
 	 */
 	if (_scsih_scsi_direct_io_get(ioc, smid)) {
+		spin_lock_irqsave(&ioc->scsi_lookup_lock, flags);
+		ioc->scsi_lookup[smid - 1].scmd = scmd;
+		spin_unlock_irqrestore(&ioc->scsi_lookup_lock, flags);
 		_scsih_scsi_direct_io_set(ioc, smid, 0);
 		memcpy(mpi_request->CDB.CDB32, scmd->cmnd, scmd->cmd_len);
 		mpi_request->DevHandle =