Merge patch series "scsi: target: Allow userspace to config cmd submission"

Mike Christie <[email protected]> says:

The following patches were made over Linus's tree but apply over
Martin's branches. They allow userspace to configure how fabric
drivers submit cmds to backend drivers.

Right now loop and vhost use a worker thread, and the other drivers
submit from the contexts they receive/process the cmd from. For
multiple LUN cases where the target can queue more cmds than the
backend can handle then deferring to a worker thread is safest because
the backend driver can block when doing things like waiting for a free
request/tag. Deferring also helps when the target has to handle
transport level requests from the recv context.

For cases where the backend devices can queue everything the target
sends, then there is no need to defer to a workqueue and you can see a
perf boost of up to 26% for small IO workloads. For a nvme device and
vhost-scsi I can see with 4K IOs:

fio jobs        1       2       4       8       10
--------------------------------------------------
workqueue
submit        94K     190K    394K    770K    890K

direct
submit       128K     252K    488K    950K    -

Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Martin K. Petersen <[email protected]>

Author: martinkpetersen

drivers/infiniband/ulp/srpt/ib_srpt.c

@@ -3867,6 +3867,9 @@ static const struct target_core_fabric_ops srpt_template = {
 	.tfc_discovery_attrs		= srpt_da_attrs,
 	.tfc_wwn_attrs			= srpt_wwn_attrs,
 	.tfc_tpg_attrib_attrs		= srpt_tpg_attrib_attrs,
+
+	.default_submit_type		= TARGET_DIRECT_SUBMIT,
+	.direct_submit_supp		= 1,
 };
 
 /**

drivers/scsi/elx/efct/efct_lio.c

@@ -1611,6 +1611,8 @@ static const struct target_core_fabric_ops efct_lio_ops = {
 	.sess_get_initiator_sid		= NULL,
 	.tfc_tpg_base_attrs		= efct_lio_tpg_attrs,
 	.tfc_tpg_attrib_attrs           = efct_lio_tpg_attrib_attrs,
+	.default_submit_type		= TARGET_DIRECT_SUBMIT,
+	.direct_submit_supp		= 1,
 };
 
 static const struct target_core_fabric_ops efct_lio_npiv_ops = {
@@ -1646,6 +1648,9 @@ static const struct target_core_fabric_ops efct_lio_npiv_ops = {
 	.sess_get_initiator_sid		= NULL,
 	.tfc_tpg_base_attrs		= efct_lio_npiv_tpg_attrs,
 	.tfc_tpg_attrib_attrs		= efct_lio_npiv_tpg_attrib_attrs,
+
+	.default_submit_type		= TARGET_DIRECT_SUBMIT,
+	.direct_submit_supp		= 1,
 };
 
 int efct_scsi_tgt_driver_init(void)

drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c

@@ -3975,6 +3975,9 @@ static const struct target_core_fabric_ops ibmvscsis_ops = {
 	.fabric_drop_tpg		= ibmvscsis_drop_tpg,
 
 	.tfc_wwn_attrs			= ibmvscsis_wwn_attrs,
+
+	.default_submit_type		= TARGET_DIRECT_SUBMIT,
+	.direct_submit_supp		= 1,
 };
 
 static void ibmvscsis_dev_release(struct device *dev) {};

drivers/scsi/qla2xxx/tcm_qla2xxx.c

@@ -1822,6 +1822,9 @@ static const struct target_core_fabric_ops tcm_qla2xxx_ops = {
 	.tfc_wwn_attrs			= tcm_qla2xxx_wwn_attrs,
 	.tfc_tpg_base_attrs		= tcm_qla2xxx_tpg_attrs,
 	.tfc_tpg_attrib_attrs		= tcm_qla2xxx_tpg_attrib_attrs,
+
+	.default_submit_type		= TARGET_DIRECT_SUBMIT,
+	.direct_submit_supp		= 1,
 };
 
 static const struct target_core_fabric_ops tcm_qla2xxx_npiv_ops = {
@@ -1859,6 +1862,9 @@ static const struct target_core_fabric_ops tcm_qla2xxx_npiv_ops = {
 	.fabric_init_nodeacl		= tcm_qla2xxx_init_nodeacl,
 
 	.tfc_wwn_attrs			= tcm_qla2xxx_wwn_attrs,
+
+	.default_submit_type		= TARGET_DIRECT_SUBMIT,
+	.direct_submit_supp		= 1,
 };
 
 static int tcm_qla2xxx_register_configfs(void)

drivers/target/iscsi/iscsi_target.c

@@ -1234,12 +1234,6 @@ int iscsit_setup_scsi_cmd(struct iscsit_conn *conn, struct iscsit_cmd *cmd,
 	spin_lock_bh(&conn->cmd_lock);
 	list_add_tail(&cmd->i_conn_node, &conn->conn_cmd_list);
 	spin_unlock_bh(&conn->cmd_lock);
-	/*
-	 * Check if we need to delay processing because of ALUA
-	 * Active/NonOptimized primary access state..
-	 */
-	core_alua_check_nonop_delay(&cmd->se_cmd);
-
 	return 0;
 }
 EXPORT_SYMBOL(iscsit_setup_scsi_cmd);

drivers/target/iscsi/iscsi_target_configfs.c

@@ -1589,5 +1589,8 @@ const struct target_core_fabric_ops iscsi_ops = {
 	.tfc_tpg_nacl_auth_attrs	= lio_target_nacl_auth_attrs,
 	.tfc_tpg_nacl_param_attrs	= lio_target_nacl_param_attrs,
 
-	.write_pending_must_be_called	= true,
+	.write_pending_must_be_called	= 1,
+
+	.default_submit_type		= TARGET_DIRECT_SUBMIT,
+	.direct_submit_supp		= 1,
 };

drivers/target/iscsi/iscsi_target_erl1.c

@@ -948,7 +948,7 @@ int iscsit_execute_cmd(struct iscsit_cmd *cmd, int ooo)
 
 			iscsit_set_unsolicited_dataout(cmd);
 		}
-		return transport_handle_cdb_direct(&cmd->se_cmd);
+		return target_submit(&cmd->se_cmd);
 
 	case ISCSI_OP_NOOP_OUT:
 	case ISCSI_OP_TEXT:

drivers/target/iscsi/iscsi_target_tmr.c

@@ -318,7 +318,7 @@ static int iscsit_task_reassign_complete_read(
 		pr_debug("READ ITT: 0x%08x: t_state: %d never sent to"
 			" transport\n", cmd->init_task_tag,
 			cmd->se_cmd.t_state);
-		transport_handle_cdb_direct(se_cmd);
+		target_submit(se_cmd);
 		return 0;
 	}
 

drivers/target/loopback/tcm_loop.c

@@ -154,7 +154,7 @@ static void tcm_loop_target_queue_cmd(struct tcm_loop_cmd *tl_cmd)
 			       GFP_ATOMIC))
 		return;
 
-	target_queue_submission(se_cmd);
+	target_submit(se_cmd);
 	return;
 
 out_done:
@@ -1102,6 +1102,8 @@ static const struct target_core_fabric_ops loop_ops = {
 	.tfc_wwn_attrs			= tcm_loop_wwn_attrs,
 	.tfc_tpg_base_attrs		= tcm_loop_tpg_attrs,
 	.tfc_tpg_attrib_attrs		= tcm_loop_tpg_attrib_attrs,
+	.default_submit_type		= TARGET_QUEUE_SUBMIT,
+	.direct_submit_supp		= 0,
 };
 
 static int __init tcm_loop_fabric_init(void)

drivers/target/sbp/sbp_target.c

@@ -2278,6 +2278,9 @@ static const struct target_core_fabric_ops sbp_ops = {
 	.tfc_wwn_attrs			= sbp_wwn_attrs,
 	.tfc_tpg_base_attrs		= sbp_tpg_base_attrs,
 	.tfc_tpg_attrib_attrs		= sbp_tpg_attrib_attrs,
+
+	.default_submit_type		= TARGET_DIRECT_SUBMIT,
+	.direct_submit_supp		= 1,
 };
 
 static int __init sbp_init(void)