Merge branch 'mtk_eth_soc-rx-vlan-offload-improvement-dsa-hardware-untag-support'

Felix Fietkau says:

====================
mtk_eth_soc rx vlan offload improvement + dsa hardware untag support

This series improves rx vlan offloading on mtk_eth_soc and extends it to
support hardware DSA untagging where possible.
This improves performance by avoiding calls into the DSA tag driver receive
function, including mangling of skb->data.

This is split out of a previous series, which added other fixes and
multiqueue support
====================

Link: https://lore.kernel.org/r/20221114124214.58199-1-nbd@nbd.nameSigned-off-by: Jakub Kicinski <kuba@kernel.org>

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"
@@ -1936,15 +1937,21 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget,
 						htons(RX_DMA_VPID(trxd.rxd4)),
 						RX_DMA_VID(trxd.rxd4));
 			} else if (trxd.rxd2 & RX_DMA_VTAG) {
-				__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q),
+				__vlan_hwaccel_put_tag(skb, htons(RX_DMA_VPID(trxd.rxd3)),
 						       RX_DMA_VID(trxd.rxd3));
 			}
+		}
 
-			/* 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.
+		/* When using VLAN untagging in combination with DSA, the
+		 * hardware treats the MTK special tag as a VLAN and untags it.
 		 */
-			if (netdev_uses_dsa(netdev))
+		if (skb_vlan_tag_present(skb) && netdev_uses_dsa(netdev)) {
+			unsigned int port = ntohs(skb->vlan_proto) & GENMASK(2, 0);
+
+			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);
 		}
 
@@ -2724,15 +2731,30 @@ static netdev_features_t mtk_fix_features(struct net_device *dev,
 
 static int mtk_set_features(struct net_device *dev, netdev_features_t features)
 {
-	int err = 0;
+	struct mtk_mac *mac = netdev_priv(dev);
+	struct mtk_eth *eth = mac->hw;
+	netdev_features_t diff = dev->features ^ features;
+	int i;
+
+	if ((diff & NETIF_F_LRO) && !(features & NETIF_F_LRO))
+		mtk_hwlro_netdev_disable(dev);
 
-	if (!((dev->features ^ features) & NETIF_F_LRO))
+	/* Set RX VLAN offloading */
+	if (!(diff & NETIF_F_HW_VLAN_CTAG_RX))
 		return 0;
 
-	if (!(features & NETIF_F_LRO))
-		mtk_hwlro_netdev_disable(dev);
+	mtk_w32(eth, !!(features & NETIF_F_HW_VLAN_CTAG_RX),
+		MTK_CDMP_EG_CTRL);
 
-	return err;
+	/* sync features with other MAC */
+	for (i = 0; i < MTK_MAC_COUNT; i++) {
+		if (!eth->netdev[i] || eth->netdev[i] == dev)
+			continue;
+		eth->netdev[i]->features &= ~NETIF_F_HW_VLAN_CTAG_RX;
+		eth->netdev[i]->features |= features & NETIF_F_HW_VLAN_CTAG_RX;
+	}
+
+	return 0;
 }
 
 /* wait for DMA to finish whatever it is doing before we start using it again */
@@ -2975,11 +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) {
@@ -3306,6 +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);
@@ -3523,6 +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;
 

net/core/flow_dissector.c

@@ -971,12 +971,14 @@ bool __skb_flow_dissect(const struct net *net,
 #if IS_ENABLED(CONFIG_NET_DSA)
 		if (unlikely(skb->dev && netdev_uses_dsa(skb->dev) &&
 			     proto == htons(ETH_P_XDSA))) {
+			struct metadata_dst *md_dst = skb_metadata_dst(skb);
 			const struct dsa_device_ops *ops;
 			int offset = 0;
 
 			ops = skb->dev->dsa_ptr->tag_ops;
 			/* Only DSA header taggers break flow dissection */
-			if (ops->needed_headroom) {
+			if (ops->needed_headroom &&
+			    (!md_dst || md_dst->type != METADATA_HW_PORT_MUX)) {
 				if (ops->flow_dissect)
 					ops->flow_dissect(skb, &proto, &offset);
 				else

net/dsa/dsa.c

@@ -11,6 +11,7 @@
 #include <linux/netdevice.h>
 #include <linux/sysfs.h>
 #include <linux/ptp_classify.h>
+#include <net/dst_metadata.h>
 
 #include "dsa_priv.h"
 
@@ -216,6 +217,7 @@ static bool dsa_skb_defer_rx_timestamp(struct dsa_slave_priv *p,
 static int dsa_switch_rcv(struct sk_buff *skb, struct net_device *dev,
 			  struct packet_type *pt, struct net_device *unused)
 {
+	struct metadata_dst *md_dst = skb_metadata_dst(skb);
 	struct dsa_port *cpu_dp = dev->dsa_ptr;
 	struct sk_buff *nskb = NULL;
 	struct dsa_slave_priv *p;
@@ -229,7 +231,22 @@ static int dsa_switch_rcv(struct sk_buff *skb, struct net_device *dev,
 	if (!skb)
 		return 0;
 
+	if (md_dst && md_dst->type == METADATA_HW_PORT_MUX) {
+		unsigned int port = md_dst->u.port_info.port_id;
+
+		skb_dst_drop(skb);
+		if (!skb_has_extensions(skb))
+			skb->slow_gro = 0;
+
+		skb->dev = dsa_master_find_slave(dev, 0, port);
+		if (likely(skb->dev)) {
+			dsa_default_offload_fwd_mark(skb);
+			nskb = skb;
+		}
+	} else {
 		nskb = cpu_dp->rcv(skb, dev);
+	}
+
 	if (!nskb) {
 		kfree_skb(skb);
 		return 0;