net: dsa: felix: create a template for the DSA tags on xmit

With this patch we try to kill 2 birds with 1 stone.

First of all, some switches that use tag_ocelot.c don't have the exact
same bitfield layout for the DSA tags. The destination ports field is
different for Seville VSC9953 for example. So the choices are to either
duplicate tag_ocelot.c into a new tag_seville.c (sub-optimal) or somehow
take into account a supposed ocelot->dest_ports_offset when packing this
field into the DSA injection header (again not ideal).

Secondly, tag_ocelot.c already needs to memset a 128-bit area to zero
and call some packing() functions of dubious performance in the
fastpath. And most of the values it needs to pack are pretty much
constant (BYPASS=1, SRC_PORT=CPU, DEST=port index). So it would be good
if we could improve that.

The proposed solution is to allocate a memory area per port at probe
time, initialize that with the statically defined bits as per chip
hardware revision, and just perform a simpler memcpy in the fastpath.

Other alternatives have been analyzed, such as:
- Create a separate tag_seville.c: too much code duplication for just 1
bit field difference.
- Create a separate DSA_TAG_PROTO_SEVILLE under tag_ocelot.c, just like
tag_brcm.c, which would have a separate .xmit function. Again, too
much code duplication for just 1 bit field difference.
- Allocate the template from the init function of the tag_ocelot.c
module, instead of from the driver: couldn't figure out a method of
accessing the correct port template corresponding to the correct
tagger in the .xmit function.

Signed-off-by: Vladimir Oltean <[e-mail]>
Reviewed-by: Florian Fainelli <[e-mail]>
Signed-off-by: David S. Miller <[e-mail]>

drivers/net/dsa/ocelot/felix.c

···
 	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),
···
 			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);

drivers/net/dsa/ocelot/felix.h

···
 				 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;

drivers/net/dsa/ocelot/felix_vsc9959.c

···
 #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>
···
 	}
 }
 
+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,
···
 	.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,
 };

include/soc/mscc/ocelot.h

···
 	u8				ts_id;
 
 	phy_interface_t			phy_mode;
+
+	u8				*xmit_template;
 };
 
 struct ocelot {

net/dsa/tag_ocelot.c

···
 				   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)) {
···
 		return NULL;
 	}
 
+	ocelot_port = ocelot->ports[dp->index];
+
 	injection = skb_push(skb, OCELOT_TAG_LEN);
 
-	memset(injection, 0, 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)) {