diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c
index 4b255ed614e47491ef2f5f8e1684867bd6dd3835..b9981d8c4c98b93902addb47b41a9e19d092d0b6 100644
--- a/drivers/net/dsa/ocelot/felix.c
+++ b/drivers/net/dsa/ocelot/felix.c
@@ -522,6 +522,7 @@ static int felix_init_structs(struct felix *felix, int num_phys_ports)
 	for (port = 0; port < num_phys_ports; port++) {
 		struct ocelot_port *ocelot_port;
 		struct regmap *target;
+		u8 *template;
 
 		ocelot_port = devm_kzalloc(ocelot->dev,
 					   sizeof(struct ocelot_port),
@@ -547,10 +548,22 @@ static int felix_init_structs(struct felix *felix, int num_phys_ports)
 			return PTR_ERR(target);
 		}
 
+		template = devm_kzalloc(ocelot->dev, OCELOT_TAG_LEN,
+					GFP_KERNEL);
+		if (!template) {
+			dev_err(ocelot->dev,
+				"Failed to allocate memory for DSA tag\n");
+			kfree(port_phy_modes);
+			return -ENOMEM;
+		}
+
 		ocelot_port->phy_mode = port_phy_modes[port];
 		ocelot_port->ocelot = ocelot;
 		ocelot_port->target = target;
+		ocelot_port->xmit_template = template;
 		ocelot->ports[port] = ocelot_port;
+
+		felix->info->xmit_template_populate(ocelot, port);
 	}
 
 	kfree(port_phy_modes);
diff --git a/drivers/net/dsa/ocelot/felix.h b/drivers/net/dsa/ocelot/felix.h
index 00137b64132b2e3024eb8b7c3208d533eea4c0e9..a85631d716b94c2a58bb526e1d5b885fc91438c2 100644
--- a/drivers/net/dsa/ocelot/felix.h
+++ b/drivers/net/dsa/ocelot/felix.h
@@ -43,6 +43,7 @@ struct felix_info {
 				 enum tc_setup_type type, void *type_data);
 	void	(*port_sched_speed_set)(struct ocelot *ocelot, int port,
 					u32 speed);
+	void	(*xmit_template_populate)(struct ocelot *ocelot, int port);
 };
 
 extern struct felix_info		felix_info_vsc9959;
diff --git a/drivers/net/dsa/ocelot/felix_vsc9959.c b/drivers/net/dsa/ocelot/felix_vsc9959.c
index efbfbdccb2b6972af8bc2d1a6491701ed82017a2..d640146acc3dda7550efd6cb0c9a3a15b8d43b8e 100644
--- a/drivers/net/dsa/ocelot/felix_vsc9959.c
+++ b/drivers/net/dsa/ocelot/felix_vsc9959.c
@@ -8,6 +8,7 @@
 #include <soc/mscc/ocelot_ptp.h>
 #include <soc/mscc/ocelot_sys.h>
 #include <soc/mscc/ocelot.h>
+#include <linux/packing.h>
 #include <net/pkt_sched.h>
 #include <linux/iopoll.h>
 #include <linux/pci.h>
@@ -1432,6 +1433,24 @@ static int vsc9959_port_setup_tc(struct dsa_switch *ds, int port,
 	}
 }
 
+static void vsc9959_xmit_template_populate(struct ocelot *ocelot, int port)
+{
+	struct ocelot_port *ocelot_port = ocelot->ports[port];
+	u8 *template = ocelot_port->xmit_template;
+	u64 bypass, dest, src;
+
+	/* Set the source port as the CPU port module and not the
+	 * NPI port
+	 */
+	src = ocelot->num_phys_ports;
+	dest = BIT(port);
+	bypass = true;
+
+	packing(template, &bypass, 127, 127, OCELOT_TAG_LEN, PACK, 0);
+	packing(template, &dest,    68,  56, OCELOT_TAG_LEN, PACK, 0);
+	packing(template, &src,     46,  43, OCELOT_TAG_LEN, PACK, 0);
+}
+
 struct felix_info felix_info_vsc9959 = {
 	.target_io_res		= vsc9959_target_io_res,
 	.port_io_res		= vsc9959_port_io_res,
@@ -1458,4 +1477,5 @@ struct felix_info felix_info_vsc9959 = {
 	.prevalidate_phy_mode	= vsc9959_prevalidate_phy_mode,
 	.port_setup_tc          = vsc9959_port_setup_tc,
 	.port_sched_speed_set   = vsc9959_sched_speed_set,
+	.xmit_template_populate	= vsc9959_xmit_template_populate,
 };
diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h
index 19d97585345a459563522e9391ff1c7422e9e8c6..6cfbace5777027e9487290b30905a0d715f95d41 100644
--- a/include/soc/mscc/ocelot.h
+++ b/include/soc/mscc/ocelot.h
@@ -564,6 +564,8 @@ struct ocelot_port {
 	u8				ts_id;
 
 	phy_interface_t			phy_mode;
+
+	u8				*xmit_template;
 };
 
 struct ocelot {
diff --git a/net/dsa/tag_ocelot.c b/net/dsa/tag_ocelot.c
index b0c98ee4e13b39e2d7e5af5a559bbdf44726cec4..42f327c06dcacea54458d8a3d6e8cd154da2687a 100644
--- a/net/dsa/tag_ocelot.c
+++ b/net/dsa/tag_ocelot.c
@@ -137,11 +137,10 @@ static struct sk_buff *ocelot_xmit(struct sk_buff *skb,
 				   struct net_device *netdev)
 {
 	struct dsa_port *dp = dsa_slave_to_port(netdev);
-	u64 bypass, dest, src, qos_class, rew_op;
 	struct dsa_switch *ds = dp->ds;
-	int port = dp->index;
 	struct ocelot *ocelot = ds->priv;
-	struct ocelot_port *ocelot_port = ocelot->ports[port];
+	struct ocelot_port *ocelot_port;
+	u64 qos_class, rew_op;
 	u8 *injection;
 
 	if (unlikely(skb_cow_head(skb, OCELOT_TAG_LEN) < 0)) {
@@ -149,19 +148,15 @@ static struct sk_buff *ocelot_xmit(struct sk_buff *skb,
 		return NULL;
 	}
 
-	injection = skb_push(skb, OCELOT_TAG_LEN);
+	ocelot_port = ocelot->ports[dp->index];
 
-	memset(injection, 0, OCELOT_TAG_LEN);
+	injection = skb_push(skb, OCELOT_TAG_LEN);
 
-	/* Set the source port as the CPU port module and not the NPI port */
-	src = ocelot->num_phys_ports;
-	dest = BIT(port);
-	bypass = true;
+	memcpy(injection, ocelot_port->xmit_template, OCELOT_TAG_LEN);
+	/* Fix up the fields which are not statically determined
+	 * in the template
+	 */
 	qos_class = skb->priority;
-
-	packing(injection, &bypass,   127, 127, OCELOT_TAG_LEN, PACK, 0);
-	packing(injection, &dest,      68,  56, OCELOT_TAG_LEN, PACK, 0);
-	packing(injection, &src,       46,  43, OCELOT_TAG_LEN, PACK, 0);
 	packing(injection, &qos_class, 19,  17, OCELOT_TAG_LEN, PACK, 0);
 
 	if (ocelot->ptp && (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)) {