diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 41cbc7c89c9d21ddcf0b6bd71e05cc9fbaa2917c..a13cc62424de9e02a584f4cbb12c42e87aaad6e2 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -814,7 +814,6 @@ static int smc_connect_rdma(struct smc_sock *smc,
 			goto connect_abort;
 		}
 	}
-	smc_rmb_sync_sg_for_device(&smc->conn);
 
 	reason_code = smc_clc_send_confirm(smc, ini->first_contact_local,
 					   SMC_V1);
@@ -1598,7 +1597,6 @@ static int smc_listen_rdma_reg(struct smc_sock *new_smc, bool local_first)
 		if (smcr_lgr_reg_rmbs(conn->lnk, conn->rmb_desc))
 			return SMC_CLC_DECL_ERR_REGRMB;
 	}
-	smc_rmb_sync_sg_for_device(&new_smc->conn);
 
 	return 0;
 }
diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index bf485a2017a4e081927df8937dbc2b9126f4495e..54ad1b22cebf9690449151e3f069f5bf08d299ad 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -1453,6 +1453,9 @@ static int smcr_buf_map_link(struct smc_buf_desc *buf_desc, bool is_rmb,
 		goto free_table;
 	}
 
+	buf_desc->is_dma_need_sync |=
+		smc_ib_is_sg_need_sync(lnk, buf_desc) << lnk->link_idx;
+
 	/* create a new memory region for the RMB */
 	if (is_rmb) {
 		rc = smc_ib_get_memory_region(lnk->roce_pd,
@@ -1681,6 +1684,7 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb)
 		/* check for reusable slot in the link group */
 		buf_desc = smc_buf_get_slot(bufsize_short, lock, buf_list);
 		if (buf_desc) {
+			buf_desc->is_dma_need_sync = 0;
 			memset(buf_desc->cpu_addr, 0, bufsize);
 			break; /* found reusable slot */
 		}
@@ -1729,15 +1733,10 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb)
 	return 0;
 }
 
-void smc_sndbuf_sync_sg_for_cpu(struct smc_connection *conn)
-{
-	if (!conn->lgr || conn->lgr->is_smcd || !smc_link_active(conn->lnk))
-		return;
-	smc_ib_sync_sg_for_cpu(conn->lnk, conn->sndbuf_desc, DMA_TO_DEVICE);
-}
-
 void smc_sndbuf_sync_sg_for_device(struct smc_connection *conn)
 {
+	if (!conn->sndbuf_desc->is_dma_need_sync)
+		return;
 	if (!conn->lgr || conn->lgr->is_smcd || !smc_link_active(conn->lnk))
 		return;
 	smc_ib_sync_sg_for_device(conn->lnk, conn->sndbuf_desc, DMA_TO_DEVICE);
@@ -1747,6 +1746,8 @@ void smc_rmb_sync_sg_for_cpu(struct smc_connection *conn)
 {
 	int i;
 
+	if (!conn->rmb_desc->is_dma_need_sync)
+		return;
 	if (!conn->lgr || conn->lgr->is_smcd)
 		return;
 	for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) {
@@ -1757,20 +1758,6 @@ void smc_rmb_sync_sg_for_cpu(struct smc_connection *conn)
 	}
 }
 
-void smc_rmb_sync_sg_for_device(struct smc_connection *conn)
-{
-	int i;
-
-	if (!conn->lgr || conn->lgr->is_smcd)
-		return;
-	for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) {
-		if (!smc_link_active(&conn->lgr->lnk[i]))
-			continue;
-		smc_ib_sync_sg_for_device(&conn->lgr->lnk[i], conn->rmb_desc,
-					  DMA_FROM_DEVICE);
-	}
-}
-
 /* create the send and receive buffer for an SMC socket;
  * receive buffers are called RMBs;
  * (even though the SMC protocol allows more than one RMB-element per RMB,
diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h
index 9364d0f35ccecf7352ce59a9ae26ef2b7d7df686..07b62e62a46b6d5bcfbc01b468be9e1bd9eef25d 100644
--- a/net/smc/smc_core.h
+++ b/net/smc/smc_core.h
@@ -162,6 +162,7 @@ struct smc_buf_desc {
 					/* mem region registered */
 			u8		is_map_ib[SMC_LINKS_PER_LGR_MAX];
 					/* mem region mapped to lnk */
+			u8		is_dma_need_sync;
 			u8		is_reg_err;
 					/* buffer registration err */
 		};
@@ -392,10 +393,8 @@ void smc_rtoken_set(struct smc_link_group *lgr, int link_idx, int link_idx_new,
 		    __be32 nw_rkey_known, __be64 nw_vaddr, __be32 nw_rkey);
 void smc_rtoken_set2(struct smc_link_group *lgr, int rtok_idx, int link_id,
 		     __be64 nw_vaddr, __be32 nw_rkey);
-void smc_sndbuf_sync_sg_for_cpu(struct smc_connection *conn);
 void smc_sndbuf_sync_sg_for_device(struct smc_connection *conn);
 void smc_rmb_sync_sg_for_cpu(struct smc_connection *conn);
-void smc_rmb_sync_sg_for_device(struct smc_connection *conn);
 int smc_vlan_by_tcpsk(struct socket *clcsock, struct smc_init_info *ini);
 
 void smc_conn_free(struct smc_connection *conn);
diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c
index f1ffbd414602ee7f9dfc42f4cfdc73151031ed80..21c673b34ad5c94ce49ca698501226dd850d4f6e 100644
--- a/net/smc/smc_ib.c
+++ b/net/smc/smc_ib.c
@@ -428,6 +428,29 @@ int smc_ib_get_memory_region(struct ib_pd *pd, int access_flags,
 	return 0;
 }
 
+bool smc_ib_is_sg_need_sync(struct smc_link *lnk,
+			    struct smc_buf_desc *buf_slot)
+{
+	struct scatterlist *sg;
+	unsigned int i;
+	bool ret = false;
+
+	/* for now there is just one DMA address */
+	for_each_sg(buf_slot->sgt[lnk->link_idx].sgl, sg,
+		    buf_slot->sgt[lnk->link_idx].nents, i) {
+		if (!sg_dma_len(sg))
+			break;
+		if (dma_need_sync(lnk->smcibdev->ibdev->dma_device,
+				  sg_dma_address(sg))) {
+			ret = true;
+			goto out;
+		}
+	}
+
+out:
+	return ret;
+}
+
 /* synchronize buffer usage for cpu access */
 void smc_ib_sync_sg_for_cpu(struct smc_link *lnk,
 			    struct smc_buf_desc *buf_slot,
@@ -436,6 +459,9 @@ void smc_ib_sync_sg_for_cpu(struct smc_link *lnk,
 	struct scatterlist *sg;
 	unsigned int i;
 
+	if (!(buf_slot->is_dma_need_sync & (1U << lnk->link_idx)))
+		return;
+
 	/* for now there is just one DMA address */
 	for_each_sg(buf_slot->sgt[lnk->link_idx].sgl, sg,
 		    buf_slot->sgt[lnk->link_idx].nents, i) {
@@ -456,6 +482,9 @@ void smc_ib_sync_sg_for_device(struct smc_link *lnk,
 	struct scatterlist *sg;
 	unsigned int i;
 
+	if (!(buf_slot->is_dma_need_sync & (1U << lnk->link_idx)))
+		return;
+
 	/* for now there is just one DMA address */
 	for_each_sg(buf_slot->sgt[lnk->link_idx].sgl, sg,
 		    buf_slot->sgt[lnk->link_idx].nents, i) {
diff --git a/net/smc/smc_ib.h b/net/smc/smc_ib.h
index f90d15eae2aabc73fddf57261df86b245df5ea2b..d08c58229d4c91e0d55c959871fec5cd53b40429 100644
--- a/net/smc/smc_ib.h
+++ b/net/smc/smc_ib.h
@@ -79,6 +79,8 @@ long smc_ib_setup_per_ibdev(struct smc_ib_device *smcibdev);
 int smc_ib_get_memory_region(struct ib_pd *pd, int access_flags,
 			     struct smc_buf_desc *buf_slot, u8 link_idx);
 void smc_ib_put_memory_region(struct ib_mr *mr);
+bool smc_ib_is_sg_need_sync(struct smc_link *lnk,
+			    struct smc_buf_desc *buf_slot);
 void smc_ib_sync_sg_for_cpu(struct smc_link *lnk,
 			    struct smc_buf_desc *buf_slot,
 			    enum dma_data_direction data_direction);
diff --git a/net/smc/smc_rx.c b/net/smc/smc_rx.c
index 7f7e983e42b1f44a3d8089865c8c82b51fa52de4..4cc750916340833dec154ee51f4f07296adc956e 100644
--- a/net/smc/smc_rx.c
+++ b/net/smc/smc_rx.c
@@ -404,7 +404,6 @@ int smc_rx_recvmsg(struct smc_sock *smc, struct msghdr *msg,
 				if (rc < 0) {
 					if (!read_done)
 						read_done = -EFAULT;
-					smc_rmb_sync_sg_for_device(conn);
 					goto out;
 				}
 			}
@@ -418,7 +417,6 @@ int smc_rx_recvmsg(struct smc_sock *smc, struct msghdr *msg,
 			chunk_len_sum += chunk_len;
 			chunk_off = 0; /* modulo offset in recv ring buffer */
 		}
-		smc_rmb_sync_sg_for_device(conn);
 
 		/* update cursors */
 		if (!(flags & MSG_PEEK)) {
diff --git a/net/smc/smc_tx.c b/net/smc/smc_tx.c
index 52ef1fca0b604ce49d7d93da88c765748b14ae08..473adb26989791b6aff9c204a479330597f3fcad 100644
--- a/net/smc/smc_tx.c
+++ b/net/smc/smc_tx.c
@@ -188,7 +188,6 @@ int smc_tx_sendmsg(struct smc_sock *smc, struct msghdr *msg, size_t len)
 				  tx_cnt_prep);
 		chunk_len_sum = chunk_len;
 		chunk_off = tx_cnt_prep;
-		smc_sndbuf_sync_sg_for_cpu(conn);
 		for (chunk = 0; chunk < 2; chunk++) {
 			rc = memcpy_from_msg(sndbuf_base + chunk_off,
 					     msg, chunk_len);