diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.c
index b9db6d64974384c1a91d376268d7e714ed60b465..cb239627770f4a8d64b25b1414c44129c680a55b 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.c
@@ -635,17 +635,18 @@ void hinic_sq_write_wqe(struct hinic_sq *sq, u16 prod_idx,
 }
 
 /**
- * hinic_sq_read_wqe - read wqe ptr in the current ci and update the ci
+ * hinic_sq_read_wqebb - read wqe ptr in the current ci and update the ci, the
+ * wqe only have one wqebb
  * @sq: send queue
  * @skb: return skb that was saved
- * @wqe_size: the size of the wqe
+ * @wqe_size: the wqe size ptr
  * @cons_idx: consumer index of the wqe
  *
  * Return wqe in ci position
  **/
-struct hinic_sq_wqe *hinic_sq_read_wqe(struct hinic_sq *sq,
-				       struct sk_buff **skb,
-				       unsigned int *wqe_size, u16 *cons_idx)
+struct hinic_sq_wqe *hinic_sq_read_wqebb(struct hinic_sq *sq,
+					 struct sk_buff **skb,
+					 unsigned int *wqe_size, u16 *cons_idx)
 {
 	struct hinic_hw_wqe *hw_wqe;
 	struct hinic_sq_wqe *sq_wqe;
@@ -658,6 +659,8 @@ struct hinic_sq_wqe *hinic_sq_read_wqe(struct hinic_sq *sq,
 	if (IS_ERR(hw_wqe))
 		return NULL;
 
+	*skb = sq->saved_skb[*cons_idx];
+
 	sq_wqe = &hw_wqe->sq_wqe;
 	ctrl = &sq_wqe->ctrl;
 	ctrl_info = be32_to_cpu(ctrl->ctrl_info);
@@ -665,11 +668,28 @@ struct hinic_sq_wqe *hinic_sq_read_wqe(struct hinic_sq *sq,
 
 	*wqe_size = sizeof(*ctrl) + sizeof(sq_wqe->task);
 	*wqe_size += SECT_SIZE_FROM_8BYTES(buf_sect_len);
+	*wqe_size = ALIGN(*wqe_size, sq->wq->wqebb_size);
 
-	*skb = sq->saved_skb[*cons_idx];
+	return &hw_wqe->sq_wqe;
+}
+
+/**
+ * hinic_sq_read_wqe - read wqe ptr in the current ci and update the ci
+ * @sq: send queue
+ * @skb: return skb that was saved
+ * @wqe_size: the size of the wqe
+ * @cons_idx: consumer index of the wqe
+ *
+ * Return wqe in ci position
+ **/
+struct hinic_sq_wqe *hinic_sq_read_wqe(struct hinic_sq *sq,
+				       struct sk_buff **skb,
+				       unsigned int wqe_size, u16 *cons_idx)
+{
+	struct hinic_hw_wqe *hw_wqe;
 
-	/* using the real wqe size to read wqe again */
-	hw_wqe = hinic_read_wqe(sq->wq, *wqe_size, cons_idx);
+	hw_wqe = hinic_read_wqe(sq->wq, wqe_size, cons_idx);
+	*skb = sq->saved_skb[*cons_idx];
 
 	return &hw_wqe->sq_wqe;
 }
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.h
index df729a1587e9a419921b05c7c7cea0fa7e463780..6c84f83ec283156a538706ba1c35e43d3015179d 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.h
@@ -165,7 +165,11 @@ void hinic_sq_write_wqe(struct hinic_sq *sq, u16 prod_idx,
 
 struct hinic_sq_wqe *hinic_sq_read_wqe(struct hinic_sq *sq,
 				       struct sk_buff **skb,
-				       unsigned int *wqe_size, u16 *cons_idx);
+				       unsigned int wqe_size, u16 *cons_idx);
+
+struct hinic_sq_wqe *hinic_sq_read_wqebb(struct hinic_sq *sq,
+					 struct sk_buff **skb,
+					 unsigned int *wqe_size, u16 *cons_idx);
 
 void hinic_sq_put_wqe(struct hinic_sq *sq, unsigned int wqe_size);
 
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_tx.c b/drivers/net/ethernet/huawei/hinic/hinic_tx.c
index 2353ec829c04407d88b365ba58e14ec960c4e978..c5fca0356c9c966207ca1b649dd094f4cfc7a55b 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_tx.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_tx.c
@@ -283,7 +283,11 @@ static void free_all_tx_skbs(struct hinic_txq *txq)
 	int nr_sges;
 	u16 ci;
 
-	while ((sq_wqe = hinic_sq_read_wqe(sq, &skb, &wqe_size, &ci))) {
+	while ((sq_wqe = hinic_sq_read_wqebb(sq, &skb, &wqe_size, &ci))) {
+		sq_wqe = hinic_sq_read_wqe(sq, &skb, wqe_size, &ci);
+		if (!sq_wqe)
+			break;
+
 		nr_sges = skb_shinfo(skb)->nr_frags + 1;
 
 		hinic_sq_get_sges(sq_wqe, txq->free_sges, nr_sges);
@@ -319,11 +323,21 @@ static int free_tx_poll(struct napi_struct *napi, int budget)
 	do {
 		hw_ci = HW_CONS_IDX(sq) & wq->mask;
 
-		sq_wqe = hinic_sq_read_wqe(sq, &skb, &wqe_size, &sw_ci);
+		/* Reading a WQEBB to get real WQE size and consumer index. */
+		sq_wqe = hinic_sq_read_wqebb(sq, &skb, &wqe_size, &sw_ci);
 		if ((!sq_wqe) ||
 		    (((hw_ci - sw_ci) & wq->mask) * wq->wqebb_size < wqe_size))
 			break;
 
+		/* If this WQE have multiple WQEBBs, we will read again to get
+		 * full size WQE.
+		 */
+		if (wqe_size > wq->wqebb_size) {
+			sq_wqe = hinic_sq_read_wqe(sq, &skb, wqe_size, &sw_ci);
+			if (unlikely(!sq_wqe))
+				break;
+		}
+
 		tx_bytes += skb->len;
 		pkts++;