diff --git a/drivers/target/loopback/tcm_loop.c b/drivers/target/loopback/tcm_loop.c
index 677e4b8f0642..fb877aec6321 100644
--- a/drivers/target/loopback/tcm_loop.c
+++ b/drivers/target/loopback/tcm_loop.c
@@ -67,8 +67,12 @@ static void tcm_loop_release_cmd(struct se_cmd *se_cmd)
 {
 	struct tcm_loop_cmd *tl_cmd = container_of(se_cmd,
 				struct tcm_loop_cmd, tl_se_cmd);
+	struct scsi_cmnd *sc = tl_cmd->sc;
 
-	kmem_cache_free(tcm_loop_cmd_cache, tl_cmd);
+	if (se_cmd->se_cmd_flags & SCF_SCSI_TMR_CDB)
+		kmem_cache_free(tcm_loop_cmd_cache, tl_cmd);
+	else
+		sc->scsi_done(sc);
 }
 
 static int tcm_loop_show_info(struct seq_file *m, struct Scsi_Host *host)
@@ -164,7 +168,6 @@ static void tcm_loop_submission_work(struct work_struct *work)
 	return;
 
 out_done:
-	kmem_cache_free(tcm_loop_cmd_cache, tl_cmd);
 	sc->scsi_done(sc);
 }
 
@@ -174,20 +177,14 @@ static void tcm_loop_submission_work(struct work_struct *work)
  */
 static int tcm_loop_queuecommand(struct Scsi_Host *sh, struct scsi_cmnd *sc)
 {
-	struct tcm_loop_cmd *tl_cmd;
+	struct tcm_loop_cmd *tl_cmd = scsi_cmd_priv(sc);
 
 	pr_debug("%s() %d:%d:%d:%llu got CDB: 0x%02x scsi_buf_len: %u\n",
 		 __func__, sc->device->host->host_no, sc->device->id,
 		 sc->device->channel, sc->device->lun, sc->cmnd[0],
 		 scsi_bufflen(sc));
 
-	tl_cmd = kmem_cache_zalloc(tcm_loop_cmd_cache, GFP_ATOMIC);
-	if (!tl_cmd) {
-		set_host_byte(sc, DID_ERROR);
-		sc->scsi_done(sc);
-		return 0;
-	}
-
+	memset(tl_cmd, 0, sizeof(*tl_cmd));
 	tl_cmd->sc = sc;
 	tl_cmd->sc_cmd_tag = sc->request->tag;
 	INIT_WORK(&tl_cmd->work, tcm_loop_submission_work);
@@ -319,6 +316,7 @@ static struct scsi_host_template tcm_loop_driver_template = {
 	.dma_boundary		= PAGE_SIZE - 1,
 	.module			= THIS_MODULE,
 	.track_queue_depth	= 1,
+	.cmd_size		= sizeof(struct tcm_loop_cmd),
 };
 
 static int tcm_loop_driver_probe(struct device *dev)
@@ -579,7 +577,6 @@ static int tcm_loop_queue_data_or_status(const char *func,
 	if ((se_cmd->se_cmd_flags & SCF_OVERFLOW_BIT) ||
 	    (se_cmd->se_cmd_flags & SCF_UNDERFLOW_BIT))
 		scsi_set_resid(sc, se_cmd->residual_count);
-	sc->scsi_done(sc);
 	return 0;
 }