net: ethernet: mtk_eth_soc: enable hardware DSA untagging

- pass the tag to DSA via metadata dst
- disabled on 7986 for now, since it's not working yet
- disabled if a MAC is enabled that does not use DSA

This improves performance by bypassing the DSA tag driver and avoiding extra
skb data mangling

Signed-off-by: Felix Fietkau <[email protected]>
Signed-off-by: Jakub Kicinski <[email protected]>

Author: nbd168

drivers/net/ethernet/mediatek/mtk_eth_soc.c

@@ -23,6 +23,7 @@
 #include <linux/jhash.h>
 #include <linux/bitfield.h>
 #include <net/dsa.h>
+#include <net/dst_metadata.h>
 
 #include "mtk_eth_soc.h"
 #include "mtk_wed.h"
@@ -1939,13 +1940,19 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget,
 				__vlan_hwaccel_put_tag(skb, htons(RX_DMA_VPID(trxd.rxd3)),
 						       RX_DMA_VID(trxd.rxd3));
 			}
+		}
+
+		/* When using VLAN untagging in combination with DSA, the
+		 * hardware treats the MTK special tag as a VLAN and untags it.
+		 */
+		if (skb_vlan_tag_present(skb) && netdev_uses_dsa(netdev)) {
+			unsigned int port = ntohs(skb->vlan_proto) & GENMASK(2, 0);
 
-			/* If the device is attached to a dsa switch, the special
-			 * tag inserted in VLAN field by hw switch can * be offloaded
-			 * by RX HW VLAN offload. Clear vlan info.
-			 */
-			if (netdev_uses_dsa(netdev))
-				__vlan_hwaccel_clear_tag(skb);
+			if (port < ARRAY_SIZE(eth->dsa_meta) &&
+			    eth->dsa_meta[port])
+				skb_dst_set_noref(skb, &eth->dsa_meta[port]->dst);
+
+			__vlan_hwaccel_clear_tag(skb);
 		}
 
 		skb_record_rx_queue(skb, 0);
@@ -2990,11 +2997,46 @@ static void mtk_gdm_config(struct mtk_eth *eth, u32 config)
 	mtk_w32(eth, 0, MTK_RST_GL);
 }
 
+
+static bool mtk_uses_dsa(struct net_device *dev)
+{
+#if IS_ENABLED(CONFIG_NET_DSA)
+	return netdev_uses_dsa(dev) &&
+	       dev->dsa_ptr->tag_ops->proto == DSA_TAG_PROTO_MTK;
+#else
+	return false;
+#endif
+}
+
 static int mtk_open(struct net_device *dev)
 {
 	struct mtk_mac *mac = netdev_priv(dev);
 	struct mtk_eth *eth = mac->hw;
-	int err;
+	int i, err;
+
+	if (mtk_uses_dsa(dev) && !eth->prog) {
+		for (i = 0; i < ARRAY_SIZE(eth->dsa_meta); i++) {
+			struct metadata_dst *md_dst = eth->dsa_meta[i];
+
+			if (md_dst)
+				continue;
+
+			md_dst = metadata_dst_alloc(0, METADATA_HW_PORT_MUX,
+						    GFP_KERNEL);
+			if (!md_dst)
+				return -ENOMEM;
+
+			md_dst->u.port_info.port_id = i;
+			eth->dsa_meta[i] = md_dst;
+		}
+	} else {
+		/* Hardware special tag parsing needs to be disabled if at least
+		 * one MAC does not use DSA.
+		 */
+		u32 val = mtk_r32(eth, MTK_CDMP_IG_CTRL);
+		val &= ~MTK_CDMP_STAG_EN;
+		mtk_w32(eth, val, MTK_CDMP_IG_CTRL);
+	}
 
 	err = phylink_of_phy_connect(mac->phylink, mac->of_node, 0);
 	if (err) {
@@ -3321,6 +3363,10 @@ static int mtk_hw_init(struct mtk_eth *eth)
 	 */
 	val = mtk_r32(eth, MTK_CDMQ_IG_CTRL);
 	mtk_w32(eth, val | MTK_CDMQ_STAG_EN, MTK_CDMQ_IG_CTRL);
+	if (!MTK_HAS_CAPS(eth->soc->caps, MTK_NETSYS_V2)) {
+		val = mtk_r32(eth, MTK_CDMP_IG_CTRL);
+		mtk_w32(eth, val | MTK_CDMP_STAG_EN, MTK_CDMP_IG_CTRL);
+	}
 
 	/* Enable RX VLan Offloading */
 	mtk_w32(eth, 1, MTK_CDMP_EG_CTRL);
@@ -3538,6 +3584,12 @@ static int mtk_free_dev(struct mtk_eth *eth)
 		free_netdev(eth->netdev[i]);
 	}
 
+	for (i = 0; i < ARRAY_SIZE(eth->dsa_meta); i++) {
+		if (!eth->dsa_meta[i])
+			break;
+		metadata_dst_free(eth->dsa_meta[i]);
+	}
+
 	return 0;
 }
 

drivers/net/ethernet/mediatek/mtk_eth_soc.h

@@ -22,6 +22,9 @@
 #include <linux/bpf_trace.h>
 #include "mtk_ppe.h"
 
+#define MTK_MAX_DSA_PORTS	7
+#define MTK_DSA_PORT_MASK	GENMASK(2, 0)
+
 #define MTK_QDMA_PAGE_SIZE	2048
 #define MTK_MAX_RX_LENGTH	1536
 #define MTK_MAX_RX_LENGTH_2K	2048
@@ -91,6 +94,9 @@
 #define MTK_CDMQ_IG_CTRL	0x1400
 #define MTK_CDMQ_STAG_EN	BIT(0)
 
+/* CDMQ Exgress Control Register */
+#define MTK_CDMQ_EG_CTRL	0x1404
+
 /* CDMP Ingress Control Register */
 #define MTK_CDMP_IG_CTRL	0x400
 #define MTK_CDMP_STAG_EN	BIT(0)
@@ -1121,6 +1127,8 @@ struct mtk_eth {
 
 	int				ip_align;
 
+	struct metadata_dst		*dsa_meta[MTK_MAX_DSA_PORTS];
+
 	struct mtk_ppe			*ppe[2];
 	struct rhashtable		flow_table;