XDP hints via kfuncs for ice driver

Documentation/networking/xdp-rx-metadata.rst

@@ -18,7 +18,16 @@ Currently, the following kfuncs are supported. In the future, as more
 metadata is supported, this set will grow:
 
 .. kernel-doc:: net/core/xdp.c
-   :identifiers: bpf_xdp_metadata_rx_timestamp bpf_xdp_metadata_rx_hash
+   :identifiers: bpf_xdp_metadata_rx_timestamp
+
+.. kernel-doc:: net/core/xdp.c
+   :identifiers: bpf_xdp_metadata_rx_hash
+
+.. kernel-doc:: net/core/xdp.c
+   :identifiers: bpf_xdp_metadata_rx_vlan_tag
+
+.. kernel-doc:: net/core/xdp.c
+   :identifiers: bpf_xdp_metadata_rx_csum_lvl
 
 An XDP program can use these kfuncs to read the metadata into stack
 variables for its own consumption. Or, to pass the metadata on to other

drivers/net/ethernet/intel/ice/ice.h

@@ -943,4 +943,6 @@ static inline void ice_clear_rdma_cap(struct ice_pf *pf)
 	set_bit(ICE_FLAG_UNPLUG_AUX_DEV, pf->flags);
 	clear_bit(ICE_FLAG_RDMA_ENA, pf->flags);
 }
+
+extern const struct xdp_metadata_ops ice_xdp_md_ops;
 #endif /* _ICE_H_ */

drivers/net/ethernet/intel/ice/ice_ethtool.c

@@ -2837,7 +2837,7 @@ ice_set_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring,
 		/* clone ring and setup updated count */
 		rx_rings[i] = *vsi->rx_rings[i];
 		rx_rings[i].count = new_rx_cnt;
-		rx_rings[i].cached_phctime = pf->ptp.cached_phc_time;
+		rx_rings[i].pkt_ctx.cached_phctime = pf->ptp.cached_phc_time;
 		rx_rings[i].desc = NULL;
 		rx_rings[i].rx_buf = NULL;
 		/* this is to allow wr32 to have something to write to

drivers/net/ethernet/intel/ice/ice_lib.c

@@ -1445,7 +1445,7 @@ static int ice_vsi_alloc_rings(struct ice_vsi *vsi)
 		ring->netdev = vsi->netdev;
 		ring->dev = dev;
 		ring->count = vsi->num_rx_desc;
-		ring->cached_phctime = pf->ptp.cached_phc_time;
+		ring->pkt_ctx.cached_phctime = pf->ptp.cached_phc_time;
 		WRITE_ONCE(vsi->rx_rings[i], ring);
 	}
 

drivers/net/ethernet/intel/ice/ice_main.c

@@ -3384,6 +3384,7 @@ static void ice_set_ops(struct ice_vsi *vsi)
 
 	netdev->netdev_ops = &ice_netdev_ops;
 	netdev->udp_tunnel_nic_info = &pf->hw.udp_tunnel_nic;
+	netdev->xdp_metadata_ops = &ice_xdp_md_ops;
 	ice_set_ethtool_ops(netdev);
 
 	if (vsi->type != ICE_VSI_PF)
@@ -5929,6 +5930,23 @@ ice_fix_features(struct net_device *netdev, netdev_features_t features)
 	return features;
 }
 
+/**
+ * ice_set_rx_rings_vlan_proto - update rings with new stripped VLAN proto
+ * @vsi: PF's VSI
+ * @vlan_ethertype: VLAN ethertype (802.1Q or 802.1ad) in network byte order
+ *
+ * Store current stripped VLAN proto in ring packet context,
+ * so it can be accessed more efficiently by packet processing code.
+ */
+static void
+ice_set_rx_rings_vlan_proto(struct ice_vsi *vsi, __be16 vlan_ethertype)
+{
+	u16 i;
+
+	ice_for_each_alloc_rxq(vsi, i)
+		vsi->rx_rings[i]->pkt_ctx.vlan_proto = vlan_ethertype;
+}
+
 /**
  * ice_set_vlan_offload_features - set VLAN offload features for the PF VSI
  * @vsi: PF's VSI
@@ -5971,6 +5989,11 @@ ice_set_vlan_offload_features(struct ice_vsi *vsi, netdev_features_t features)
 	if (strip_err || insert_err)
 		return -EIO;
 
+	if (enable_stripping)
+		ice_set_rx_rings_vlan_proto(vsi, htons(vlan_ethertype));
+	else
+		ice_set_rx_rings_vlan_proto(vsi, 0);
+
 	return 0;
 }
 

drivers/net/ethernet/intel/ice/ice_ptp.c

@@ -1038,7 +1038,7 @@ static int ice_ptp_update_cached_phctime(struct ice_pf *pf)
 		ice_for_each_rxq(vsi, j) {
 			if (!vsi->rx_rings[j])
 				continue;
-			WRITE_ONCE(vsi->rx_rings[j]->cached_phctime, systime);
+			WRITE_ONCE(vsi->rx_rings[j]->pkt_ctx.cached_phctime, systime);
 		}
 	}
 	clear_bit(ICE_CFG_BUSY, pf->state);
@@ -2147,30 +2147,24 @@ int ice_ptp_set_ts_config(struct ice_pf *pf, struct ifreq *ifr)
 }
 
 /**
- * ice_ptp_rx_hwtstamp - Check for an Rx timestamp
- * @rx_ring: Ring to get the VSI info
+ * ice_ptp_get_rx_hwts - Get packet Rx timestamp
  * @rx_desc: Receive descriptor
- * @skb: Particular skb to send timestamp with
+ * @cached_time: Cached PHC time
  *
  * The driver receives a notification in the receive descriptor with timestamp.
- * The timestamp is in ns, so we must convert the result first.
  */
-void
-ice_ptp_rx_hwtstamp(struct ice_rx_ring *rx_ring,
-		    union ice_32b_rx_flex_desc *rx_desc, struct sk_buff *skb)
+u64 ice_ptp_get_rx_hwts(const union ice_32b_rx_flex_desc *rx_desc,
+			u64 cached_time)
 {
-	struct skb_shared_hwtstamps *hwtstamps;
-	u64 ts_ns, cached_time;
 	u32 ts_high;
+	u64 ts_ns;
 
 	if (!(rx_desc->wb.time_stamp_low & ICE_PTP_TS_VALID))
-		return;
-
-	cached_time = READ_ONCE(rx_ring->cached_phctime);
+		return 0;
 
 	/* Do not report a timestamp if we don't have a cached PHC time */
 	if (!cached_time)
-		return;
+		return 0;
 
 	/* Use ice_ptp_extend_32b_ts directly, using the ring-specific cached
 	 * PHC value, rather than accessing the PF. This also allows us to
@@ -2181,9 +2175,7 @@ ice_ptp_rx_hwtstamp(struct ice_rx_ring *rx_ring,
 	ts_high = le32_to_cpu(rx_desc->wb.flex_ts.ts_high);
 	ts_ns = ice_ptp_extend_32b_ts(cached_time, ts_high);
 
-	hwtstamps = skb_hwtstamps(skb);
-	memset(hwtstamps, 0, sizeof(*hwtstamps));
-	hwtstamps->hwtstamp = ns_to_ktime(ts_ns);
+	return ts_ns;
 }
 
 /**

drivers/net/ethernet/intel/ice/ice_ptp.h

@@ -268,9 +268,8 @@ void ice_ptp_extts_event(struct ice_pf *pf);
 s8 ice_ptp_request_ts(struct ice_ptp_tx *tx, struct sk_buff *skb);
 enum ice_tx_tstamp_work ice_ptp_process_ts(struct ice_pf *pf);
 
-void
-ice_ptp_rx_hwtstamp(struct ice_rx_ring *rx_ring,
-		    union ice_32b_rx_flex_desc *rx_desc, struct sk_buff *skb);
+u64 ice_ptp_get_rx_hwts(const union ice_32b_rx_flex_desc *rx_desc,
+			u64 cached_time);
 void ice_ptp_reset(struct ice_pf *pf);
 void ice_ptp_prepare_for_reset(struct ice_pf *pf);
 void ice_ptp_init(struct ice_pf *pf);
@@ -304,9 +303,13 @@ static inline bool ice_ptp_process_ts(struct ice_pf *pf)
 {
 	return true;
 }
-static inline void
-ice_ptp_rx_hwtstamp(struct ice_rx_ring *rx_ring,
-		    union ice_32b_rx_flex_desc *rx_desc, struct sk_buff *skb) { }
+
+static inline u64
+ice_ptp_get_rx_hwts(const union ice_32b_rx_flex_desc *rx_desc, u64 cached_time)
+{
+	return 0;
+}
+
 static inline void ice_ptp_reset(struct ice_pf *pf) { }
 static inline void ice_ptp_prepare_for_reset(struct ice_pf *pf) { }
 static inline void ice_ptp_init(struct ice_pf *pf) { }

drivers/net/ethernet/intel/ice/ice_txrx.c

@@ -557,20 +557,23 @@ ice_rx_frame_truesize(struct ice_rx_ring *rx_ring, const unsigned int size)
  * @xdp_prog: XDP program to run
  * @xdp_ring: ring to be used for XDP_TX action
  * @rx_buf: Rx buffer to store the XDP action
+ * @eop_desc: Last descriptor in packet to read metadata from
  *
  * Returns any of ICE_XDP_{PASS, CONSUMED, TX, REDIR}
  */
 static void
 ice_run_xdp(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp,
 	    struct bpf_prog *xdp_prog, struct ice_tx_ring *xdp_ring,
-	    struct ice_rx_buf *rx_buf)
+	    struct ice_rx_buf *rx_buf, union ice_32b_rx_flex_desc *eop_desc)
 {
 	unsigned int ret = ICE_XDP_PASS;
 	u32 act;
 
 	if (!xdp_prog)
 		goto exit;
 
+	ice_xdp_meta_set_desc(xdp, eop_desc);
+
 	act = bpf_prog_run_xdp(xdp_prog, xdp);
 	switch (act) {
 	case XDP_PASS:
@@ -1181,7 +1184,6 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget)
 		unsigned int size;
 		u16 stat_err_bits;
 		u16 vlan_tag = 0;
-		u16 rx_ptype;
 
 		/* get the Rx desc from Rx ring based on 'next_to_clean' */
 		rx_desc = ICE_RX_DESC(rx_ring, ntc);
@@ -1241,7 +1243,7 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget)
 		if (ice_is_non_eop(rx_ring, rx_desc))
 			continue;
 
-		ice_run_xdp(rx_ring, xdp, xdp_prog, xdp_ring, rx_buf);
+		ice_run_xdp(rx_ring, xdp, xdp_prog, xdp_ring, rx_buf, rx_desc);
 		if (rx_buf->act == ICE_XDP_PASS)
 			goto construct_skb;
 		total_rx_bytes += xdp_get_buff_len(xdp);
@@ -1276,7 +1278,7 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget)
 			continue;
 		}
 
-		vlan_tag = ice_get_vlan_tag_from_rx_desc(rx_desc);
+		vlan_tag = ice_get_vlan_tag(rx_desc);
 
 		/* pad the skb if needed, to make a valid ethernet frame */
 		if (eth_skb_pad(skb))
@@ -1286,10 +1288,7 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget)
 		total_rx_bytes += skb->len;
 
 		/* populate checksum, VLAN, and protocol */
-		rx_ptype = le16_to_cpu(rx_desc->wb.ptype_flex_flags0) &
-			ICE_RX_FLEX_DESC_PTYPE_M;
-
-		ice_process_skb_fields(rx_ring, rx_desc, skb, rx_ptype);
+		ice_process_skb_fields(rx_ring, rx_desc, skb);
 
 		ice_trace(clean_rx_irq_indicate, rx_ring, rx_desc, skb);
 		/* send completed skb up the stack */

drivers/net/ethernet/intel/ice/ice_txrx.h

@@ -257,6 +257,20 @@ enum ice_rx_dtype {
 	ICE_RX_DTYPE_SPLIT_ALWAYS	= 2,
 };
 
+struct ice_pkt_ctx {
+	const union ice_32b_rx_flex_desc *eop_desc;
+	u64 cached_phctime;
+	__be16 vlan_proto;
+};
+
+struct ice_xdp_buff {
+	struct xdp_buff xdp_buff;
+	struct ice_pkt_ctx pkt_ctx;
+};
+
+/* Required for compatibility with xdp_buffs from xsk_pool */
+static_assert(offsetof(struct ice_xdp_buff, xdp_buff) == 0);
+
 /* indices into GLINT_ITR registers */
 #define ICE_RX_ITR	ICE_IDX_ITR0
 #define ICE_TX_ITR	ICE_IDX_ITR1
@@ -298,7 +312,6 @@ enum ice_dynamic_itr {
 /* descriptor ring, associated with a VSI */
 struct ice_rx_ring {
 	/* CL1 - 1st cacheline starts here */
-	struct ice_rx_ring *next;	/* pointer to next ring in q_vector */
 	void *desc;			/* Descriptor ring memory */
 	struct device *dev;		/* Used for DMA mapping */
 	struct net_device *netdev;	/* netdev ring maps to */
@@ -310,12 +323,19 @@ struct ice_rx_ring {
 	u16 count;			/* Number of descriptors */
 	u16 reg_idx;			/* HW register index of the ring */
 	u16 next_to_alloc;
-	/* CL2 - 2nd cacheline starts here */
+
 	union {
 		struct ice_rx_buf *rx_buf;
 		struct xdp_buff **xdp_buf;
 	};
-	struct xdp_buff xdp;
+	/* CL2 - 2nd cacheline starts here */
+	union {
+		struct ice_xdp_buff xdp_ext;
+		struct {
+			struct xdp_buff xdp;
+			struct ice_pkt_ctx pkt_ctx;
+		};
+	};
 	/* CL3 - 3rd cacheline starts here */
 	struct bpf_prog *xdp_prog;
 	u16 rx_offset;
@@ -325,6 +345,8 @@ struct ice_rx_ring {
 	u16 next_to_clean;
 	u16 first_desc;
 
+	struct ice_rx_ring *next;	/* pointer to next ring in q_vector */
+
 	/* stats structs */
 	struct ice_ring_stats *ring_stats;
 
@@ -334,7 +356,6 @@ struct ice_rx_ring {
 	struct ice_tx_ring *xdp_ring;
 	struct xsk_buff_pool *xsk_pool;
 	dma_addr_t dma;			/* physical address of ring */
-	u64 cached_phctime;
 	u16 rx_buf_len;
 	u8 dcb_tc;			/* Traffic class of ring */
 	u8 ptp_rx;