target: Add support for TMR percpu reference counting

This patch introduces TMR percpu reference counting using
se_lun->lun_ref in transport_lookup_tmr_lun(), following
how existing non TMR per se_lun reference counting works
within transport_lookup_cmd_lun().

It also adds explicit transport_lun_remove_cmd() calls to
drop the reference in the three tmr related locations that
invoke transport_cmd_check_stop_to_fabric();

   - target_tmr_work() during normal ->queue_tm_rsp()
   - target_complete_tmr_failure() during error ->queue_tm_rsp()
   - transport_generic_handle_tmr() during early failure

Also, note the exception paths in transport_generic_free_cmd()
and transport_cmd_finish_abort() already check SCF_SE_LUN_CMD,
and will invoke transport_lun_remove_cmd() when necessary.
Reviewed-by: Himanshu Madhani <himanshu.madhani@cavium.com>
Reviewed-by: Quinn Tran <quinn.tran@cavium.com>
Cc: Mike Christie <mchristi@redhat.com>
Cc: Hannes Reinecke <hare@suse.com>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>

drivers/target/target_core_device.c

@@ -168,11 +168,20 @@ int transport_lookup_tmr_lun(struct se_cmd *se_cmd, u64 unpacked_lun)
 	rcu_read_lock();
 	deve = target_nacl_find_deve(nacl, unpacked_lun);
 	if (deve) {
-		se_cmd->se_lun = rcu_dereference(deve->se_lun);
 		se_lun = rcu_dereference(deve->se_lun);
+
+		if (!percpu_ref_tryget_live(&se_lun->lun_ref)) {
+			se_lun = NULL;
+			goto out_unlock;
+		}
+
+		se_cmd->se_lun = rcu_dereference(deve->se_lun);
 		se_cmd->pr_res_key = deve->pr_res_key;
 		se_cmd->orig_fe_lun = unpacked_lun;
+		se_cmd->se_cmd_flags |= SCF_SE_LUN_CMD;
+		se_cmd->lun_ref_active = true;
 	}
+out_unlock:
 	rcu_read_unlock();
 
 	if (!se_lun) {
@@ -182,9 +191,6 @@ int transport_lookup_tmr_lun(struct se_cmd *se_cmd, u64 unpacked_lun)
 			unpacked_lun);
 		return -ENODEV;
 	}
-	/*
-	 * XXX: Add percpu se_lun->lun_ref reference count for TMR
-	 */
 	se_cmd->se_dev = rcu_dereference_raw(se_lun->lun_se_dev);
 	se_tmr->tmr_dev = rcu_dereference_raw(se_lun->lun_se_dev);
 

drivers/target/target_core_transport.c

@@ -1590,6 +1590,7 @@ static void target_complete_tmr_failure(struct work_struct *work)
 	se_cmd->se_tmr_req->response = TMR_LUN_DOES_NOT_EXIST;
 	se_cmd->se_tfo->queue_tm_rsp(se_cmd);
 
+	transport_lun_remove_cmd(se_cmd);
 	transport_cmd_check_stop_to_fabric(se_cmd);
 }
 
@@ -3201,6 +3202,7 @@ static void target_tmr_work(struct work_struct *work)
 	cmd->se_tfo->queue_tm_rsp(cmd);
 
 check_stop:
+	transport_lun_remove_cmd(cmd);
 	transport_cmd_check_stop_to_fabric(cmd);
 }
 
@@ -3223,6 +3225,7 @@ int transport_generic_handle_tmr(
 		pr_warn_ratelimited("handle_tmr caught CMD_T_ABORTED TMR %d"
 			"ref_tag: %llu tag: %llu\n", cmd->se_tmr_req->function,
 			cmd->se_tmr_req->ref_task_tag, cmd->tag);
+		transport_lun_remove_cmd(cmd);
 		transport_cmd_check_stop_to_fabric(cmd);
 		return 0;
 	}