diff --git a/drivers/scsi/iscsi_tcp.c b/drivers/scsi/iscsi_tcp.c
index 8e14cea15f980829e99afa2c43bf6872fcfd965c..54d01b9d330d46746603a556cb5f06eee58699c7 100644
--- a/drivers/scsi/iscsi_tcp.c
+++ b/drivers/scsi/iscsi_tcp.c
@@ -170,6 +170,7 @@ static void iscsi_sw_tcp_data_ready(struct sock *sk)
 	struct iscsi_sw_tcp_conn *tcp_sw_conn;
 	struct iscsi_tcp_conn *tcp_conn;
 	struct iscsi_conn *conn;
+	int current_cpu;
 
 	trace_sk_data_ready(sk);
 
@@ -180,6 +181,14 @@ static void iscsi_sw_tcp_data_ready(struct sock *sk)
 		return;
 	}
 	tcp_conn = conn->dd_data;
+
+        /* save intimate cpu when in softirq */
+        if (!sock_owned_by_user_nocheck(sk)) {
+                current_cpu = smp_processor_id();
+                if (conn->intimate_cpu != current_cpu)
+                        conn->intimate_cpu = current_cpu;
+        }
+
 	tcp_sw_conn = tcp_conn->dd_data;
 
 	if (tcp_sw_conn->queue_recv)
diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c
index 0fda8905eabd8278f578e54a8f502ab2996629ed..2d585f80e12291b0bc8db7575f5552aa513f2be6 100644
--- a/drivers/scsi/libiscsi.c
+++ b/drivers/scsi/libiscsi.c
@@ -89,9 +89,15 @@ inline void iscsi_conn_queue_xmit(struct iscsi_conn *conn)
 {
 	struct Scsi_Host *shost = conn->session->host;
 	struct iscsi_host *ihost = shost_priv(shost);
+	int intimate_cpu = conn->intimate_cpu;
 
-	if (ihost->workq)
-		queue_work(ihost->workq, &conn->xmitwork);
+	if (ihost->workq) {
+	        /* we expect it to be excuted on the same numa of the intimate cpu */
+	        if ((intimate_cpu >= 0) && cpu_possible(intimate_cpu))
+	                queue_work_on(intimate_cpu, ihost->workq, &conn->xmitwork);
+	        else
+	                queue_work(ihost->workq, &conn->xmitwork);
+	}
 }
 EXPORT_SYMBOL_GPL(iscsi_conn_queue_xmit);
 
@@ -2907,9 +2913,9 @@ struct Scsi_Host *iscsi_host_alloc(const struct scsi_host_template *sht,
 	ihost = shost_priv(shost);
 
 	if (xmit_can_sleep) {
-		ihost->workq = alloc_workqueue("iscsi_q_%d",
-			WQ_SYSFS | __WQ_LEGACY | WQ_MEM_RECLAIM | WQ_UNBOUND,
-			1, shost->host_no);
+		/* this kind of workqueue only support single work */
+		ihost->workq = alloc_ordered_workqueue("iscsi_q_%d", __WQ_LEGACY | WQ_MEM_RECLAIM |
+				                        __WQ_DYNAMIC, shost->host_no);
 		if (!ihost->workq)
 			goto free_host;
 	}
@@ -3190,6 +3196,7 @@ iscsi_conn_setup(struct iscsi_cls_session *cls_session, int dd_size,
 	conn->c_stage = ISCSI_CONN_INITIAL_STAGE;
 	conn->id = conn_idx;
 	conn->exp_statsn = 0;
+	conn->intimate_cpu = -1;
 
 	timer_setup(&conn->transport_timer, iscsi_check_transport_timeouts, 0);
 
diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h
index 9619098755fb3d24fb3bf24b4d0ca43c992035ad..485c0f5b251882d5ce3dc30e5c65f02d08043609 100644
--- a/include/linux/workqueue.h
+++ b/include/linux/workqueue.h
@@ -415,6 +415,7 @@ enum {
 	__WQ_ORDERED		= 1 << 17, /* internal: workqueue is ordered */
 	__WQ_LEGACY		= 1 << 18, /* internal: create*_workqueue() */
 	__WQ_ORDERED_EXPLICIT	= 1 << 19, /* internal: alloc_ordered_workqueue() */
+	__WQ_DYNAMIC            = 1 << 25, /* internal: only support single work order WQ */
 
 	WQ_MAX_ACTIVE		= 512,	  /* I like 512, better ideas? */
 	WQ_UNBOUND_MAX_ACTIVE	= WQ_MAX_ACTIVE,
diff --git a/include/scsi/libiscsi.h b/include/scsi/libiscsi.h
index d253b82e973e43e08721bfaab14ef2b9503d1000..ead17d2224a1f231b072265ffe8c2bca5705b44c 100644
--- a/include/scsi/libiscsi.h
+++ b/include/scsi/libiscsi.h
@@ -266,6 +266,7 @@ struct iscsi_conn {
 	/* custom statistics */
 	uint32_t		eh_abort_cnt;
 	uint32_t		fmr_unalign_cnt;
+	int			intimate_cpu;
 
 	KABI_RESERVE(1)
 	KABI_RESERVE(2)
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 1888741f5edd79e6cbf88f4a82e16e44e36f0f7f..590703eb6e3e74e38274147f1795336662d71b11 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -4375,6 +4375,9 @@ apply_wqattrs_prepare(struct workqueue_struct *wq,
 
 	/* save the user configured attrs and sanitize it. */
 	copy_workqueue_attrs(new_attrs, attrs);
+	if (wq->flags & __WQ_DYNAMIC)
+		new_attrs->ordered = false;
+
 	cpumask_and(new_attrs->cpumask, new_attrs->cpumask, cpu_possible_mask);
 	cpumask_copy(new_attrs->__pod_cpumask, new_attrs->cpumask);
 	ctx->attrs = new_attrs;
@@ -4591,10 +4594,12 @@ static int alloc_and_link_pwqs(struct workqueue_struct *wq)
 	cpus_read_lock();
 	if (wq->flags & __WQ_ORDERED) {
 		ret = apply_workqueue_attrs(wq, ordered_wq_attrs[highpri]);
-		/* there should only be single pwq for ordering guarantee */
-		WARN(!ret && (wq->pwqs.next != &wq->dfl_pwq->pwqs_node ||
-			      wq->pwqs.prev != &wq->dfl_pwq->pwqs_node),
-		     "ordering guarantee broken for workqueue %s\n", wq->name);
+		if (!(wq->flags & __WQ_DYNAMIC)) {
+                       /* there should only be single pwq for ordering guarantee */
+                       WARN(!ret && (wq->pwqs.next != &wq->dfl_pwq->pwqs_node ||
+                                       wq->pwqs.prev != &wq->dfl_pwq->pwqs_node),
+                                       "ordering guarantee broken for workqueue %s\n", wq->name);
+               }
 	} else {
 		ret = apply_workqueue_attrs(wq, unbound_std_wq_attrs[highpri]);
 	}
@@ -5798,7 +5803,7 @@ static int workqueue_apply_unbound_cpumask(const cpumask_var_t unbound_cpumask)
 			continue;
 
 		/* creating multiple pwqs breaks ordering guarantee */
-		if (!list_empty(&wq->pwqs)) {
+		if (!list_empty(&wq->pwqs) && !(wq->flags & __WQ_DYNAMIC)) {
 			if (wq->flags & __WQ_ORDERED_EXPLICIT)
 				continue;
 			wq->flags &= ~__WQ_ORDERED;