Merge branch 'nfp-xdp_adjust_head'

Jakub Kicinski says:

====================
nfp: XDP adjust head support

This series adds support for XDP adjust head.  Bulk of the code
is actually just paying technical debt.  On reconfiguration request
nfp was allocating new resources separately leaving device running
with the existing set of rings.  We used to manage the new resources
in special ring set structures.  This set is simply separating the
datapath part of the device structure from the control information
allowing the new datapath structure to be allocated with all new
memory and rings.  The swap operation is now greatly simplified.
We also save a lot of parameter passing this way.  Hopefully the churn
is worth the negative diffstat.

Support for XDP adjust head is done in a pretty standard way.  NFP
is a bit special because it prepends metadata before packet data
so we have to do a bit of memcpying in case XDP will run.  We also
luck out a little bit because the fact that we already have prepend
space allocated means that one byte is enough to store the extra XDP
space (256 of standard prepend space is a bit inconvenient since
it would normally require 16bits or boolean with additional shifts).
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

7 files changed, 655 insertions, 683 deletions

diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net.h b/drivers/net/ethernet/netronome/nfp/nfp_net.h
index 34f8c439f42f..4d45f4573b57 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net.h
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net.h
@@ -50,14 +50,14 @@
 
 #include "nfp_net_ctrl.h"
 
-#define nn_err(nn, fmt, args...)  netdev_err((nn)->netdev, fmt, ## args)
-#define nn_warn(nn, fmt, args...) netdev_warn((nn)->netdev, fmt, ## args)
-#define nn_info(nn, fmt, args...) netdev_info((nn)->netdev, fmt, ## args)
-#define nn_dbg(nn, fmt, args...)  netdev_dbg((nn)->netdev, fmt, ## args)
-#define nn_warn_ratelimit(nn, fmt, args...)				\
+#define nn_err(nn, fmt, args...)  netdev_err((nn)->dp.netdev, fmt, ## args)
+#define nn_warn(nn, fmt, args...) netdev_warn((nn)->dp.netdev, fmt, ## args)
+#define nn_info(nn, fmt, args...) netdev_info((nn)->dp.netdev, fmt, ## args)
+#define nn_dbg(nn, fmt, args...)  netdev_dbg((nn)->dp.netdev, fmt, ## args)
+#define nn_dp_warn(dp, fmt, args...)					\
 	do {								\
 		if (unlikely(net_ratelimit()))				\
-			netdev_warn((nn)->netdev, fmt, ## args);	\
+			netdev_warn((dp)->netdev, fmt, ## args);	\
 	} while (0)
 
 /* Max time to wait for NFP to respond on updates (in seconds) */
@@ -316,8 +316,6 @@ struct nfp_net_rx_buf {
  * @rxds:       Virtual address of FL/RX ring in host memory
  * @dma:        DMA address of the FL/RX ring
  * @size:       Size, in bytes, of the FL/RX ring (needed to free)
- * @bufsz:	Buffer allocation size for convenience of management routines
- *		(NOTE: this is in second cache line, do not use on fast path!)
  */
 struct nfp_net_rx_ring {
 	struct nfp_net_r_vector *r_vec;
@@ -339,7 +337,6 @@ struct nfp_net_rx_ring {
 
 	dma_addr_t dma;
 	unsigned int size;
-	unsigned int bufsz;
 } ____cacheline_aligned;
 
 /**
@@ -434,18 +431,73 @@ struct nfp_stat_pair {
 };
 
 /**
- * struct nfp_net - NFP network device structure
+ * struct nfp_net_dp - NFP network device datapath data structure
  * @dev:		Backpointer to struct device
- * @netdev:             Backpointer to net_device structure
- * @is_vf:              Is the driver attached to a VF?
+ * @netdev:		Backpointer to net_device structure
+ * @is_vf:		Is the driver attached to a VF?
  * @bpf_offload_skip_sw:  Offloaded BPF program will not be rerun by cls_bpf
  * @bpf_offload_xdp:	Offloaded BPF program is XDP
  * @chained_metadata_format:  Firemware will use new metadata format
- * @ctrl:               Local copy of the control register/word.
- * @fl_bufsz:           Currently configured size of the freelist buffers
+ * @rx_dma_dir:		Mapping direction for RX buffers
+ * @rx_dma_off:		Offset at which DMA packets (for XDP headroom)
  * @rx_offset:		Offset in the RX buffers where packet data starts
+ * @ctrl:		Local copy of the control register/word.
+ * @fl_bufsz:		Currently configured size of the freelist buffers
  * @xdp_prog:		Installed XDP program
- * @fw_ver:             Firmware version
+ * @tx_rings:		Array of pre-allocated TX ring structures
+ * @rx_rings:		Array of pre-allocated RX ring structures
+ * @ctrl_bar:		Pointer to mapped control BAR
+ *
+ * @txd_cnt:		Size of the TX ring in number of descriptors
+ * @rxd_cnt:		Size of the RX ring in number of descriptors
+ * @num_r_vecs:		Number of used ring vectors
+ * @num_tx_rings:	Currently configured number of TX rings
+ * @num_stack_tx_rings:	Number of TX rings used by the stack (not XDP)
+ * @num_rx_rings:	Currently configured number of RX rings
+ * @mtu:		Device MTU
+ */
+struct nfp_net_dp {
+	struct device *dev;
+	struct net_device *netdev;
+
+	u8 is_vf:1;
+	u8 bpf_offload_skip_sw:1;
+	u8 bpf_offload_xdp:1;
+	u8 chained_metadata_format:1;
+
+	u8 rx_dma_dir;
+	u8 rx_dma_off;
+
+	u8 rx_offset;
+
+	u32 ctrl;
+	u32 fl_bufsz;
+
+	struct bpf_prog *xdp_prog;
+
+	struct nfp_net_tx_ring *tx_rings;
+	struct nfp_net_rx_ring *rx_rings;
+
+	u8 __iomem *ctrl_bar;
+
+	/* Cold data follows */
+
+	unsigned int txd_cnt;
+	unsigned int rxd_cnt;
+
+	unsigned int num_r_vecs;
+
+	unsigned int num_tx_rings;
+	unsigned int num_stack_tx_rings;
+	unsigned int num_rx_rings;
+
+	unsigned int mtu;
+};
+
+/**
+ * struct nfp_net - NFP network device structure
+ * @dp:			Datapath structure
+ * @fw_ver:		Firmware version
  * @cap:                Capabilities advertised by the Firmware
  * @max_mtu:            Maximum support MTU advertised by the Firmware
  * @rss_hfunc:		RSS selected hash function
@@ -457,17 +509,9 @@ struct nfp_stat_pair {
  * @rx_filter_change:	Jiffies when statistics last changed
  * @rx_filter_stats_timer:  Timer for polling filter offload statistics
  * @rx_filter_lock:	Lock protecting timer state changes (teardown)
+ * @max_r_vecs:		Number of allocated interrupt vectors for RX/TX
  * @max_tx_rings:       Maximum number of TX rings supported by the Firmware
  * @max_rx_rings:       Maximum number of RX rings supported by the Firmware
- * @num_tx_rings:       Currently configured number of TX rings
- * @num_stack_tx_rings:	Number of TX rings used by the stack (not XDP)
- * @num_rx_rings:       Currently configured number of RX rings
- * @txd_cnt:            Size of the TX ring in number of descriptors
- * @rxd_cnt:            Size of the RX ring in number of descriptors
- * @tx_rings:           Array of pre-allocated TX ring structures
- * @rx_rings:           Array of pre-allocated RX ring structures
- * @max_r_vecs:	        Number of allocated interrupt vectors for RX/TX
- * @num_r_vecs:         Number of used ring vectors
  * @r_vecs:             Pre-allocated array of ring vectors
  * @irq_entries:        Pre-allocated array of MSI-X entries
  * @lsc_handler:        Handler for Link State Change interrupt
@@ -491,7 +535,6 @@ struct nfp_stat_pair {
  * @vxlan_ports:	VXLAN ports for RX inner csum offload communicated to HW
  * @vxlan_usecnt:	IPv4/IPv6 VXLAN port use counts
  * @qcp_cfg:            Pointer to QCP queue used for configuration notification
- * @ctrl_bar:           Pointer to mapped control BAR
  * @tx_bar:             Pointer to mapped TX queues
  * @rx_bar:             Pointer to mapped FL/RX queues
  * @debugfs_dir:	Device directory in debugfs
@@ -502,25 +545,10 @@ struct nfp_stat_pair {
  * @eth_port:		Translated ETH Table port entry
  */
 struct nfp_net {
-	struct device *dev;
-	struct net_device *netdev;
-
-	unsigned is_vf:1;
-	unsigned bpf_offload_skip_sw:1;
-	unsigned bpf_offload_xdp:1;
-	unsigned chained_metadata_format:1;
-
-	u32 ctrl;
-	u32 fl_bufsz;
-
-	u32 rx_offset;
-
-	struct bpf_prog *xdp_prog;
-
-	struct nfp_net_tx_ring *tx_rings;
-	struct nfp_net_rx_ring *rx_rings;
+	struct nfp_net_dp dp;
 
 	struct nfp_net_fw_version fw_ver;
+
 	u32 cap;
 	u32 max_mtu;
 
@@ -537,18 +565,10 @@ struct nfp_net {
 	unsigned int max_tx_rings;
 	unsigned int max_rx_rings;
 
-	unsigned int num_tx_rings;
-	unsigned int num_stack_tx_rings;
-	unsigned int num_rx_rings;
-
 	int stride_tx;
 	int stride_rx;
 
-	int txd_cnt;
-	int rxd_cnt;
-
 	unsigned int max_r_vecs;
-	unsigned int num_r_vecs;
 	struct nfp_net_r_vector r_vecs[NFP_NET_MAX_R_VECS];
 	struct msix_entry irq_entries[NFP_NET_MAX_IRQS];
 
@@ -582,7 +602,6 @@ struct nfp_net {
 
 	u8 __iomem *qcp_cfg;
 
-	u8 __iomem *ctrl_bar;
 	u8 __iomem *tx_bar;
 	u8 __iomem *rx_bar;
 
@@ -597,54 +616,47 @@ struct nfp_net {
 	struct nfp_eth_table_port *eth_port;
 };
 
-struct nfp_net_ring_set {
-	unsigned int n_rings;
-	unsigned int mtu;
-	unsigned int dcnt;
-	void *rings;
-};
-
 /* Functions to read/write from/to a BAR
  * Performs any endian conversion necessary.
  */
 static inline u16 nn_readb(struct nfp_net *nn, int off)
 {
-	return readb(nn->ctrl_bar + off);
+	return readb(nn->dp.ctrl_bar + off);
 }
 
 static inline void nn_writeb(struct nfp_net *nn, int off, u8 val)
 {
-	writeb(val, nn->ctrl_bar + off);
+	writeb(val, nn->dp.ctrl_bar + off);
 }
 
 static inline u16 nn_readw(struct nfp_net *nn, int off)
 {
-	return readw(nn->ctrl_bar + off);
+	return readw(nn->dp.ctrl_bar + off);
 }
 
 static inline void nn_writew(struct nfp_net *nn, int off, u16 val)
 {
-	writew(val, nn->ctrl_bar + off);
+	writew(val, nn->dp.ctrl_bar + off);
 }
 
 static inline u32 nn_readl(struct nfp_net *nn, int off)
 {
-	return readl(nn->ctrl_bar + off);
+	return readl(nn->dp.ctrl_bar + off);
 }
 
 static inline void nn_writel(struct nfp_net *nn, int off, u32 val)
 {
-	writel(val, nn->ctrl_bar + off);
+	writel(val, nn->dp.ctrl_bar + off);
 }
 
 static inline u64 nn_readq(struct nfp_net *nn, int off)
 {
-	return readq(nn->ctrl_bar + off);
+	return readq(nn->dp.ctrl_bar + off);
 }
 
 static inline void nn_writeq(struct nfp_net *nn, int off, u64 val)
 {
-	writeq(val, nn->ctrl_bar + off);
+	writeq(val, nn->dp.ctrl_bar + off);
 }
 
 /* Flush posted PCI writes by reading something without side effects */
@@ -798,9 +810,9 @@ void nfp_net_irqs_disable(struct pci_dev *pdev);
 void
 nfp_net_irqs_assign(struct nfp_net *nn, struct msix_entry *irq_entries,
 		    unsigned int n);
-int
-nfp_net_ring_reconfig(struct nfp_net *nn, struct bpf_prog **xdp_prog,
-		      struct nfp_net_ring_set *rx, struct nfp_net_ring_set *tx);
+
+struct nfp_net_dp *nfp_net_clone_dp(struct nfp_net *nn);
+int nfp_net_ring_reconfig(struct nfp_net *nn, struct nfp_net_dp *new);
 
 #ifdef CONFIG_NFP_DEBUG
 void nfp_net_debugfs_create(void);
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index 2d964d030dbe..f134f1808b9a 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -85,20 +85,18 @@ void nfp_net_get_fw_version(struct nfp_net_fw_version *fw_ver,
 	put_unaligned_le32(reg, fw_ver);
 }
 
-static dma_addr_t
-nfp_net_dma_map_rx(struct nfp_net *nn, void *frag, unsigned int bufsz,
-		   int direction)
+static dma_addr_t nfp_net_dma_map_rx(struct nfp_net_dp *dp, void *frag)
 {
-	return dma_map_single(nn->dev, frag + NFP_NET_RX_BUF_HEADROOM,
-			      bufsz - NFP_NET_RX_BUF_NON_DATA, direction);
+	return dma_map_single(dp->dev, frag + NFP_NET_RX_BUF_HEADROOM,
+			      dp->fl_bufsz - NFP_NET_RX_BUF_NON_DATA,
+			      dp->rx_dma_dir);
 }
 
-static void
-nfp_net_dma_unmap_rx(struct nfp_net *nn, dma_addr_t dma_addr,
-		     unsigned int bufsz, int direction)
+static void nfp_net_dma_unmap_rx(struct nfp_net_dp *dp, dma_addr_t dma_addr)
 {
-	dma_unmap_single(nn->dev, dma_addr,
-			 bufsz - NFP_NET_RX_BUF_NON_DATA, direction);
+	dma_unmap_single(dp->dev, dma_addr,
+			 dp->fl_bufsz - NFP_NET_RX_BUF_NON_DATA,
+			 dp->rx_dma_dir);
 }
 
 /* Firmware reconfig
@@ -329,19 +327,22 @@ void
 nfp_net_irqs_assign(struct nfp_net *nn, struct msix_entry *irq_entries,
 		    unsigned int n)
 {
+	struct nfp_net_dp *dp = &nn->dp;
+
 	nn->max_r_vecs = n - NFP_NET_NON_Q_VECTORS;
-	nn->num_r_vecs = nn->max_r_vecs;
+	dp->num_r_vecs = nn->max_r_vecs;
 
 	memcpy(nn->irq_entries, irq_entries, sizeof(*irq_entries) * n);
 
-	if (nn->num_rx_rings > nn->num_r_vecs ||
-	    nn->num_tx_rings > nn->num_r_vecs)
+	if (dp->num_rx_rings > dp->num_r_vecs ||
+	    dp->num_tx_rings > dp->num_r_vecs)
 		nn_warn(nn, "More rings (%d,%d) than vectors (%d).\n",
-			nn->num_rx_rings, nn->num_tx_rings, nn->num_r_vecs);
+			dp->num_rx_rings, dp->num_tx_rings,
+			dp->num_r_vecs);
 
-	nn->num_rx_rings = min(nn->num_r_vecs, nn->num_rx_rings);
-	nn->num_tx_rings = min(nn->num_r_vecs, nn->num_tx_rings);
-	nn->num_stack_tx_rings = nn->num_tx_rings;
+	dp->num_rx_rings = min(dp->num_r_vecs, dp->num_rx_rings);
+	dp->num_tx_rings = min(dp->num_r_vecs, dp->num_tx_rings);
+	dp->num_stack_tx_rings = dp->num_tx_rings;
 }
 
 /**
@@ -396,11 +397,11 @@ static void nfp_net_read_link_status(struct nfp_net *nn)
 	nn->link_up = link_up;
 
 	if (nn->link_up) {
-		netif_carrier_on(nn->netdev);
-		netdev_info(nn->netdev, "NIC Link is Up\n");
+		netif_carrier_on(nn->dp.netdev);
+		netdev_info(nn->dp.netdev, "NIC Link is Up\n");
 	} else {
-		netif_carrier_off(nn->netdev);
-		netdev_info(nn->netdev, "NIC Link is Down\n");
+		netif_carrier_off(nn->dp.netdev);
+		netdev_info(nn->dp.netdev, "NIC Link is Down\n");
 	}
 out:
 	spin_unlock_irqrestore(&nn->link_status_lock, flags);
@@ -532,7 +533,7 @@ nfp_net_aux_irq_request(struct nfp_net *nn, u32 ctrl_offset,
 
 	entry = &nn->irq_entries[vector_idx];
 
-	snprintf(name, name_sz, format, netdev_name(nn->netdev));
+	snprintf(name, name_sz, format, netdev_name(nn->dp.netdev));
 	err = request_irq(entry->vector, handler, 0, name, nn);
 	if (err) {
 		nn_err(nn, "Failed to request IRQ %d (err=%d).\n",
@@ -619,7 +620,6 @@ static void nfp_net_tx_ring_stop(struct netdev_queue *nd_q,
 
 /**
  * nfp_net_tx_tso() - Set up Tx descriptor for LSO
- * @nn:  NFP Net device
  * @r_vec: per-ring structure
  * @txbuf: Pointer to driver soft TX descriptor
  * @txd: Pointer to HW TX descriptor
@@ -628,7 +628,7 @@ static void nfp_net_tx_ring_stop(struct netdev_queue *nd_q,
  * Set up Tx descriptor for LSO, do nothing for non-LSO skbs.
  * Return error on packet header greater than maximum supported LSO header size.
  */
-static void nfp_net_tx_tso(struct nfp_net *nn, struct nfp_net_r_vector *r_vec,
+static void nfp_net_tx_tso(struct nfp_net_r_vector *r_vec,
 			   struct nfp_net_tx_buf *txbuf,
 			   struct nfp_net_tx_desc *txd, struct sk_buff *skb)
 {
@@ -659,7 +659,7 @@ static void nfp_net_tx_tso(struct nfp_net *nn, struct nfp_net_r_vector *r_vec,
 
 /**
  * nfp_net_tx_csum() - Set TX CSUM offload flags in TX descriptor
- * @nn:  NFP Net device
+ * @dp:  NFP Net data path struct
  * @r_vec: per-ring structure
  * @txbuf: Pointer to driver soft TX descriptor
  * @txd: Pointer to TX descriptor
@@ -668,7 +668,8 @@ static void nfp_net_tx_tso(struct nfp_net *nn, struct nfp_net_r_vector *r_vec,
  * This function sets the TX checksum flags in the TX descriptor based
  * on the configuration and the protocol of the packet to be transmitted.
  */
-static void nfp_net_tx_csum(struct nfp_net *nn, struct nfp_net_r_vector *r_vec,
+static void nfp_net_tx_csum(struct nfp_net_dp *dp,
+			    struct nfp_net_r_vector *r_vec,
 			    struct nfp_net_tx_buf *txbuf,
 			    struct nfp_net_tx_desc *txd, struct sk_buff *skb)
 {
@@ -676,7 +677,7 @@ static void nfp_net_tx_csum(struct nfp_net *nn, struct nfp_net_r_vector *r_vec,
 	struct iphdr *iph;
 	u8 l4_hdr;
 
-	if (!(nn->ctrl & NFP_NET_CFG_CTRL_TXCSUM))
+	if (!(dp->ctrl & NFP_NET_CFG_CTRL_TXCSUM))
 		return;
 
 	if (skb->ip_summed != CHECKSUM_PARTIAL)
@@ -695,8 +696,7 @@ static void nfp_net_tx_csum(struct nfp_net *nn, struct nfp_net_r_vector *r_vec,
 	} else if (ipv6h->version == 6) {
 		l4_hdr = ipv6h->nexthdr;
 	} else {
-		nn_warn_ratelimit(nn, "partial checksum but ipv=%x!\n",
-				  iph->version);
+		nn_dp_warn(dp, "partial checksum but ipv=%x!\n", iph->version);
 		return;
 	}
 
@@ -708,8 +708,7 @@ static void nfp_net_tx_csum(struct nfp_net *nn, struct nfp_net_r_vector *r_vec,
 		txd->flags |= PCIE_DESC_TX_UDP_CSUM;
 		break;
 	default:
-		nn_warn_ratelimit(nn, "partial checksum but l4 proto=%x!\n",
-				  l4_hdr);
+		nn_dp_warn(dp, "partial checksum but l4 proto=%x!\n", l4_hdr);
 		return;
 	}
 
@@ -744,22 +743,24 @@ static int nfp_net_tx(struct sk_buff *skb, struct net_device *netdev)
 	struct nfp_net_r_vector *r_vec;
 	struct nfp_net_tx_buf *txbuf;
 	struct netdev_queue *nd_q;
+	struct nfp_net_dp *dp;
 	dma_addr_t dma_addr;
 	unsigned int fsize;
 	int f, nr_frags;
 	int wr_idx;
 	u16 qidx;
 
+	dp = &nn->dp;
 	qidx = skb_get_queue_mapping(skb);
-	tx_ring = &nn->tx_rings[qidx];
+	tx_ring = &dp->tx_rings[qidx];
 	r_vec = tx_ring->r_vec;
-	nd_q = netdev_get_tx_queue(nn->netdev, qidx);
+	nd_q = netdev_get_tx_queue(dp->netdev, qidx);
 
 	nr_frags = skb_shinfo(skb)->nr_frags;
 
 	if (unlikely(nfp_net_tx_full(tx_ring, nr_frags + 1))) {
-		nn_warn_ratelimit(nn, "TX ring %d busy. wrp=%u rdp=%u\n",
-				  qidx, tx_ring->wr_p, tx_ring->rd_p);
+		nn_dp_warn(dp, "TX ring %d busy. wrp=%u rdp=%u\n",
+			   qidx, tx_ring->wr_p, tx_ring->rd_p);
 		netif_tx_stop_queue(nd_q);
 		u64_stats_update_begin(&r_vec->tx_sync);
 		r_vec->tx_busy++;
@@ -768,9 +769,9 @@ static int nfp_net_tx(struct sk_buff *skb, struct net_device *netdev)
 	}
 
 	/* Start with the head skbuf */
-	dma_addr = dma_map_single(nn->dev, skb->data, skb_headlen(skb),
+	dma_addr = dma_map_single(dp->dev, skb->data, skb_headlen(skb),
 				  DMA_TO_DEVICE);
-	if (dma_mapping_error(nn->dev, dma_addr))
+	if (dma_mapping_error(dp->dev, dma_addr))
 		goto err_free;
 
 	wr_idx = tx_ring->wr_p & (tx_ring->cnt - 1);
@@ -794,11 +795,11 @@ static int nfp_net_tx(struct sk_buff *skb, struct net_device *netdev)
 	txd->mss = 0;
 	txd->l4_offset = 0;
 
-	nfp_net_tx_tso(nn, r_vec, txbuf, txd, skb);
+	nfp_net_tx_tso(r_vec, txbuf, txd, skb);
 
-	nfp_net_tx_csum(nn, r_vec, txbuf, txd, skb);
+	nfp_net_tx_csum(dp, r_vec, txbuf, txd, skb);
 
-	if (skb_vlan_tag_present(skb) && nn->ctrl & NFP_NET_CFG_CTRL_TXVLAN) {
+	if (skb_vlan_tag_present(skb) && dp->ctrl & NFP_NET_CFG_CTRL_TXVLAN) {
 		txd->flags |= PCIE_DESC_TX_VLAN;
 		txd->vlan = cpu_to_le16(skb_vlan_tag_get(skb));
 	}
@@ -812,9 +813,9 @@ static int nfp_net_tx(struct sk_buff *skb, struct net_device *netdev)
 			frag = &skb_shinfo(skb)->frags[f];
 			fsize = skb_frag_size(frag);
 
-			dma_addr = skb_frag_dma_map(nn->dev, frag, 0,
+			dma_addr = skb_frag_dma_map(dp->dev, frag, 0,
 						    fsize, DMA_TO_DEVICE);
-			if (dma_mapping_error(nn->dev, dma_addr))
+			if (dma_mapping_error(dp->dev, dma_addr))
 				goto err_unmap;
 
 			wr_idx = (wr_idx + 1) & (tx_ring->cnt - 1);
@@ -853,7 +854,7 @@ err_unmap:
 	--f;
 	while (f >= 0) {
 		frag = &skb_shinfo(skb)->frags[f];
-		dma_unmap_page(nn->dev, tx_ring->txbufs[wr_idx].dma_addr,
+		dma_unmap_page(dp->dev, tx_ring->txbufs[wr_idx].dma_addr,
 			       skb_frag_size(frag), DMA_TO_DEVICE);
 		tx_ring->txbufs[wr_idx].skb = NULL;
 		tx_ring->txbufs[wr_idx].dma_addr = 0;
@@ -862,13 +863,13 @@ err_unmap:
 		if (wr_idx < 0)
 			wr_idx += tx_ring->cnt;
 	}
-	dma_unmap_single(nn->dev, tx_ring->txbufs[wr_idx].dma_addr,
+	dma_unmap_single(dp->dev, tx_ring->txbufs[wr_idx].dma_addr,
 			 skb_headlen(skb), DMA_TO_DEVICE);
 	tx_ring->txbufs[wr_idx].skb = NULL;
 	tx_ring->txbufs[wr_idx].dma_addr = 0;
 	tx_ring->txbufs[wr_idx].fidx = -2;
 err_free:
-	nn_warn_ratelimit(nn, "Failed to map DMA TX buffer\n");
+	nn_dp_warn(dp, "Failed to map DMA TX buffer\n");
 	u64_stats_update_begin(&r_vec->tx_sync);
 	r_vec->tx_errors++;
 	u64_stats_update_end(&r_vec->tx_sync);
@@ -885,7 +886,7 @@ err_free:
 static void nfp_net_tx_complete(struct nfp_net_tx_ring *tx_ring)
 {
 	struct nfp_net_r_vector *r_vec = tx_ring->r_vec;
-	struct nfp_net *nn = r_vec->nfp_net;
+	struct nfp_net_dp *dp = &r_vec->nfp_net->dp;
 	const struct skb_frag_struct *frag;
 	struct netdev_queue *nd_q;
 	u32 done_pkts = 0, done_bytes = 0;
@@ -919,7 +920,7 @@ static void nfp_net_tx_complete(struct nfp_net_tx_ring *tx_ring)
 
 		if (fidx == -1) {
 			/* unmap head */
-			dma_unmap_single(nn->dev, tx_ring->txbufs[idx].dma_addr,
+			dma_unmap_single(dp->dev, tx_ring->txbufs[idx].dma_addr,
 					 skb_headlen(skb), DMA_TO_DEVICE);
 
 			done_pkts += tx_ring->txbufs[idx].pkt_cnt;
@@ -927,7 +928,7 @@ static void nfp_net_tx_complete(struct nfp_net_tx_ring *tx_ring)
 		} else {
 			/* unmap fragment */
 			frag = &skb_shinfo(skb)->frags[fidx];
-			dma_unmap_page(nn->dev, tx_ring->txbufs[idx].dma_addr,
+			dma_unmap_page(dp->dev, tx_ring->txbufs[idx].dma_addr,
 				       skb_frag_size(frag), DMA_TO_DEVICE);
 		}
 
@@ -947,7 +948,7 @@ static void nfp_net_tx_complete(struct nfp_net_tx_ring *tx_ring)
 	r_vec->tx_pkts += done_pkts;
 	u64_stats_update_end(&r_vec->tx_sync);
 
-	nd_q = netdev_get_tx_queue(nn->netdev, tx_ring->idx);
+	nd_q = netdev_get_tx_queue(dp->netdev, tx_ring->idx);
 	netdev_tx_completed_queue(nd_q, done_pkts, done_bytes);
 	if (nfp_net_tx_ring_should_wake(tx_ring)) {
 		/* Make sure TX thread will see updated tx_ring->rd_p */
@@ -965,7 +966,7 @@ static void nfp_net_tx_complete(struct nfp_net_tx_ring *tx_ring)
 static void nfp_net_xdp_complete(struct nfp_net_tx_ring *tx_ring)
 {
 	struct nfp_net_r_vector *r_vec = tx_ring->r_vec;
-	struct nfp_net *nn = r_vec->nfp_net;
+	struct nfp_net_dp *dp = &r_vec->nfp_net->dp;
 	u32 done_pkts = 0, done_bytes = 0;
 	int idx, todo;
 	u32 qcp_rd_p;
@@ -988,8 +989,7 @@ static void nfp_net_xdp_complete(struct nfp_net_tx_ring *tx_ring)
 		if (!tx_ring->txbufs[idx].frag)
 			continue;
 
-		nfp_net_dma_unmap_rx(nn, tx_ring->txbufs[idx].dma_addr,
-				     nn->fl_bufsz, DMA_BIDIRECTIONAL);
+		nfp_net_dma_unmap_rx(dp, tx_ring->txbufs[idx].dma_addr);
 		__free_page(virt_to_page(tx_ring->txbufs[idx].frag));
 
 		done_pkts++;
@@ -1014,13 +1014,13 @@ static void nfp_net_xdp_complete(struct nfp_net_tx_ring *tx_ring)
 
 /**
  * nfp_net_tx_ring_reset() - Free any untransmitted buffers and reset pointers
- * @nn:		NFP Net device
+ * @dp:		NFP Net data path struct
  * @tx_ring:	TX ring structure
  *
  * Assumes that the device is stopped
  */
 static void
-nfp_net_tx_ring_reset(struct nfp_net *nn, struct nfp_net_tx_ring *tx_ring)
+nfp_net_tx_ring_reset(struct nfp_net_dp *dp, struct nfp_net_tx_ring *tx_ring)
 {
 	struct nfp_net_r_vector *r_vec = tx_ring->r_vec;
 	const struct skb_frag_struct *frag;
@@ -1034,8 +1034,7 @@ nfp_net_tx_ring_reset(struct nfp_net *nn, struct nfp_net_tx_ring *tx_ring)
 		tx_buf = &tx_ring->txbufs[idx];
 
 		if (tx_ring == r_vec->xdp_ring) {
-			nfp_net_dma_unmap_rx(nn, tx_buf->dma_addr,
-					     nn->fl_bufsz, DMA_BIDIRECTIONAL);
+			nfp_net_dma_unmap_rx(dp, tx_buf->dma_addr);
 			__free_page(virt_to_page(tx_ring->txbufs[idx].frag));
 		} else {
 			struct sk_buff *skb = tx_ring->txbufs[idx].skb;
@@ -1043,13 +1042,13 @@ nfp_net_tx_ring_reset(struct nfp_net *nn, struct nfp_net_tx_ring *tx_ring)
 
 			if (tx_buf->fidx == -1) {
 				/* unmap head */
-				dma_unmap_single(nn->dev, tx_buf->dma_addr,
+				dma_unmap_single(dp->dev, tx_buf->dma_addr,
 						 skb_headlen(skb),
 						 DMA_TO_DEVICE);
 			} else {
 				/* unmap fragment */
 				frag = &skb_shinfo(skb)->frags[tx_buf->fidx];
-				dma_unmap_page(nn->dev, tx_buf->dma_addr,
+				dma_unmap_page(dp->dev, tx_buf->dma_addr,
 					       skb_frag_size(frag),
 					       DMA_TO_DEVICE);
 			}
@@ -1076,7 +1075,7 @@ nfp_net_tx_ring_reset(struct nfp_net *nn, struct nfp_net_tx_ring *tx_ring)
 	if (tx_ring == r_vec->xdp_ring)
 		return;
 
-	nd_q = netdev_get_tx_queue(nn->netdev, tx_ring->idx);
+	nd_q = netdev_get_tx_queue(dp->netdev, tx_ring->idx);
 	netdev_tx_reset_queue(nd_q);
 }
 
@@ -1085,7 +1084,7 @@ static void nfp_net_tx_timeout(struct net_device *netdev)
 	struct nfp_net *nn = netdev_priv(netdev);
 	int i;
 
-	for (i = 0; i < nn->netdev->real_num_tx_queues; i++) {
+	for (i = 0; i < nn->dp.netdev->real_num_tx_queues; i++) {
 		if (!netif_tx_queue_stopped(netdev_get_tx_queue(netdev, i)))
 			continue;
 		nn_warn(nn, "TX timeout on ring: %d\n", i);
@@ -1096,16 +1095,17 @@ static void nfp_net_tx_timeout(struct net_device *netdev)
 /* Receive processing
  */
 static unsigned int
-nfp_net_calc_fl_bufsz(struct nfp_net *nn, unsigned int mtu)
+nfp_net_calc_fl_bufsz(struct nfp_net_dp *dp)
 {
 	unsigned int fl_bufsz;
 
 	fl_bufsz = NFP_NET_RX_BUF_HEADROOM;
-	if (nn->rx_offset == NFP_NET_CFG_RX_OFFSET_DYNAMIC)
+	fl_bufsz += dp->rx_dma_off;
+	if (dp->rx_offset == NFP_NET_CFG_RX_OFFSET_DYNAMIC)
 		fl_bufsz += NFP_NET_MAX_PREPEND;
 	else
-		fl_bufsz += nn->rx_offset;
-	fl_bufsz += ETH_HLEN + VLAN_HLEN * 2 + mtu;
+		fl_bufsz += dp->rx_offset;
+	fl_bufsz += ETH_HLEN + VLAN_HLEN * 2 + dp->mtu;
 
 	fl_bufsz = SKB_DATA_ALIGN(fl_bufsz);
 	fl_bufsz += SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
@@ -1124,62 +1124,56 @@ nfp_net_free_frag(void *frag, bool xdp)
 
 /**
  * nfp_net_rx_alloc_one() - Allocate and map page frag for RX
+ * @dp:		NFP Net data path struct
  * @rx_ring:	RX ring structure of the skb
  * @dma_addr:	Pointer to storage for DMA address (output param)
- * @fl_bufsz:	size of freelist buffers
- * @xdp:	Whether XDP is enabled
  *
  * This function will allcate a new page frag, map it for DMA.
  *
  * Return: allocated page frag or NULL on failure.
  */
 static void *
-nfp_net_rx_alloc_one(struct nfp_net_rx_ring *rx_ring, dma_addr_t *dma_addr,
-		     unsigned int fl_bufsz, bool xdp)
+nfp_net_rx_alloc_one(struct nfp_net_dp *dp, struct nfp_net_rx_ring *rx_ring,
+		     dma_addr_t *dma_addr)
 {
-	struct nfp_net *nn = rx_ring->r_vec->nfp_net;
-	int direction;
 	void *frag;
 
-	if (!xdp)
-		frag = netdev_alloc_frag(fl_bufsz);
+	if (!dp->xdp_prog)
+		frag = netdev_alloc_frag(dp->fl_bufsz);
 	else
 		frag = page_address(alloc_page(GFP_KERNEL | __GFP_COLD));
 	if (!frag) {
-		nn_warn_ratelimit(nn, "Failed to alloc receive page frag\n");
+		nn_dp_warn(dp, "Failed to alloc receive page frag\n");
 		return NULL;
 	}
 
-	direction = xdp ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE;
-
-	*dma_addr = nfp_net_dma_map_rx(nn, frag, fl_bufsz, direction);
-	if (dma_mapping_error(nn->dev, *dma_addr)) {
-		nfp_net_free_frag(frag, xdp);
-		nn_warn_ratelimit(nn, "Failed to map DMA RX buffer\n");
+	*dma_addr = nfp_net_dma_map_rx(dp, frag);
+	if (dma_mapping_error(dp->dev, *dma_addr)) {
+		nfp_net_free_frag(frag, dp->xdp_prog);
+		nn_dp_warn(dp, "Failed to map DMA RX buffer\n");
 		return NULL;
 	}
 
 	return frag;
 }
 
-static void *
-nfp_net_napi_alloc_one(struct nfp_net *nn, int direction, dma_addr_t *dma_addr)
+static void *nfp_net_napi_alloc_one(struct nfp_net_dp *dp, dma_addr_t *dma_addr)
 {
 	void *frag;
 
-	if (!nn->xdp_prog)
-		frag = napi_alloc_frag(nn->fl_bufsz);
+	if (!dp->xdp_prog)
+		frag = napi_alloc_frag(dp->fl_bufsz);
 	else
 		frag = page_address(alloc_page(GFP_ATOMIC | __GFP_COLD));
 	if (!frag) {
-		nn_warn_ratelimit(nn, "Failed to alloc receive page frag\n");
+		nn_dp_warn(dp, "Failed to alloc receive page frag\n");
 		return NULL;
 	}
 
-	*dma_addr = nfp_net_dma_map_rx(nn, frag, nn->fl_bufsz, direction);
-	if (dma_mapping_error(nn->dev, *dma_addr)) {
-		nfp_net_free_frag(frag, nn->xdp_prog);
-		nn_warn_ratelimit(nn, "Failed to map DMA RX buffer\n");
+	*dma_addr = nfp_net_dma_map_rx(dp, frag);
+	if (dma_mapping_error(dp->dev, *dma_addr)) {
+		nfp_net_free_frag(frag, dp->xdp_prog);
+		nn_dp_warn(dp, "Failed to map DMA RX buffer\n");
 		return NULL;
 	}
 
@@ -1188,11 +1182,13 @@ nfp_net_napi_alloc_one(struct nfp_net *nn, int direction, dma_addr_t *dma_addr)
 
 /**
  * nfp_net_rx_give_one() - Put mapped skb on the software and hardware rings
+ * @dp:		NFP Net data path struct
  * @rx_ring:	RX ring structure
  * @frag:	page fragment buffer
  * @dma_addr:	DMA address of skb mapping
  */
-static void nfp_net_rx_give_one(struct nfp_net_rx_ring *rx_ring,
+static void nfp_net_rx_give_one(const struct nfp_net_dp *dp,
+				struct nfp_net_rx_ring *rx_ring,
 				void *frag, dma_addr_t dma_addr)
 {
 	unsigned int wr_idx;
@@ -1206,7 +1202,8 @@ static void nfp_net_rx_give_one(struct nfp_net_rx_ring *rx_ring,
 	/* Fill freelist descriptor */
 	rx_ring->rxds[wr_idx].fld.reserved = 0;
 	rx_ring->rxds[wr_idx].fld.meta_len_dd = 0;
-	nfp_desc_set_dma_addr(&rx_ring->rxds[wr_idx].fld, dma_addr);
+	nfp_desc_set_dma_addr(&rx_ring->rxds[wr_idx].fld,
+			      dma_addr + dp->rx_dma_off);
 
 	rx_ring->wr_p++;
 	rx_ring->wr_ptr_add++;
@@ -1247,19 +1244,17 @@ static void nfp_net_rx_ring_reset(struct nfp_net_rx_ring *rx_ring)
 
 /**
  * nfp_net_rx_ring_bufs_free() - Free any buffers currently on the RX ring
- * @nn:		NFP Net device
+ * @dp:		NFP Net data path struct
  * @rx_ring:	RX ring to remove buffers from
- * @xdp:	Whether XDP is enabled
  *
  * Assumes that the device is stopped and buffers are in [0, ring->cnt - 1)
  * entries.  After device is disabled nfp_net_rx_ring_reset() must be called
  * to restore required ring geometry.
  */
 static void
-nfp_net_rx_ring_bufs_free(struct nfp_net *nn, struct nfp_net_rx_ring *rx_ring,
-			  bool xdp)
+nfp_net_rx_ring_bufs_free(struct nfp_net_dp *dp,
+			  struct nfp_net_rx_ring *rx_ring)
 {
-	int direction = xdp ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE;
 	unsigned int i;
 
 	for (i = 0; i < rx_ring->cnt - 1; i++) {
@@ -1270,9 +1265,8 @@ nfp_net_rx_ring_bufs_free(struct nfp_net *nn, struct nfp_net_rx_ring *rx_ring,
 		if (!rx_ring->rxbufs[i].frag)
 			continue;
 
-		nfp_net_dma_unmap_rx(nn, rx_ring->rxbufs[i].dma_addr,
-				     rx_ring->bufsz, direction);
-		nfp_net_free_frag(rx_ring->rxbufs[i].frag, xdp);
+		nfp_net_dma_unmap_rx(dp, rx_ring->rxbufs[i].dma_addr);
+		nfp_net_free_frag(rx_ring->rxbufs[i].frag, dp->xdp_prog);
 		rx_ring->rxbufs[i].dma_addr = 0;
 		rx_ring->rxbufs[i].frag = NULL;
 	}
@@ -1280,13 +1274,12 @@ nfp_net_rx_ring_bufs_free(struct nfp_net *nn, struct nfp_net_rx_ring *rx_ring,
 
 /**
  * nfp_net_rx_ring_bufs_alloc() - Fill RX ring with buffers (don't give to FW)
- * @nn:		NFP Net device
+ * @dp:		NFP Net data path struct
  * @rx_ring:	RX ring to remove buffers from
- * @xdp:	Whether XDP is enabled
  */
 static int
-nfp_net_rx_ring_bufs_alloc(struct nfp_net *nn, struct nfp_net_rx_ring *rx_ring,
-			   bool xdp)
+nfp_net_rx_ring_bufs_alloc(struct nfp_net_dp *dp,
+			   struct nfp_net_rx_ring *rx_ring)
 {
 	struct nfp_net_rx_buf *rxbufs;
 	unsigned int i;
@@ -1295,10 +1288,9 @@ nfp_net_rx_ring_bufs_alloc(struct nfp_net *nn, struct nfp_net_rx_ring *rx_ring,
 
 	for (i = 0; i < rx_ring->cnt - 1; i++) {
 		rxbufs[i].frag =
-			nfp_net_rx_alloc_one(rx_ring, &rxbufs[i].dma_addr,
-					     rx_ring->bufsz, xdp);
+			nfp_net_rx_alloc_one(dp, rx_ring, &rxbufs[i].dma_addr);
 		if (!rxbufs[i].frag) {
-			nfp_net_rx_ring_bufs_free(nn, rx_ring, xdp);
+			nfp_net_rx_ring_bufs_free(dp, rx_ring);
 			return -ENOMEM;
 		}
 	}
@@ -1308,14 +1300,17 @@ nfp_net_rx_ring_bufs_alloc(struct nfp_net *nn, struct nfp_net_rx_ring *rx_ring,
 
 /**
  * nfp_net_rx_ring_fill_freelist() - Give buffers from the ring to FW
+ * @dp:	     NFP Net data path struct
  * @rx_ring: RX ring to fill
  */
-static void nfp_net_rx_ring_fill_freelist(struct nfp_net_rx_ring *rx_ring)
+static void
+nfp_net_rx_ring_fill_freelist(struct nfp_net_dp *dp,
+			      struct nfp_net_rx_ring *rx_ring)
 {
 	unsigned int i;
 
 	for (i = 0; i < rx_ring->cnt - 1; i++)
-		nfp_net_rx_give_one(rx_ring, rx_ring->rxbufs[i].frag,
+		nfp_net_rx_give_one(dp, rx_ring, rx_ring->rxbufs[i].frag,
 				    rx_ring->rxbufs[i].dma_addr);
 }
 
@@ -1335,17 +1330,18 @@ static int nfp_net_rx_csum_has_errors(u16 flags)
 
 /**
  * nfp_net_rx_csum() - set SKB checksum field based on RX descriptor flags
- * @nn:  NFP Net device
+ * @dp:  NFP Net data path struct
  * @r_vec: per-ring structure
  * @rxd: Pointer to RX descriptor
  * @skb: Pointer to SKB
  */
-static void nfp_net_rx_csum(struct nfp_net *nn, struct nfp_net_r_vector *r_vec,
+static void nfp_net_rx_csum(struct nfp_net_dp *dp,
+			    struct nfp_net_r_vector *r_vec,
 			    struct nfp_net_rx_desc *rxd, struct sk_buff *skb)
 {
 	skb_checksum_none_assert(skb);
 
-	if (!(nn->netdev->features & NETIF_F_RXCSUM))
+	if (!(dp->netdev->features & NETIF_F_RXCSUM))
 		return;
 
 	if (nfp_net_rx_csum_has_errors(le16_to_cpu(rxd->rxd.flags))) {
@@ -1396,24 +1392,21 @@ static void nfp_net_set_hash(struct net_device *netdev, struct sk_buff *skb,
 
 static void
 nfp_net_set_hash_desc(struct net_device *netdev, struct sk_buff *skb,
-		      struct nfp_net_rx_desc *rxd)
+		      void *data, struct nfp_net_rx_desc *rxd)
 {
-	struct nfp_net_rx_hash *rx_hash;
+	struct nfp_net_rx_hash *rx_hash = data;
 
 	if (!(rxd->rxd.flags & PCIE_DESC_RX_RSS))
 		return;
 
-	rx_hash = (struct nfp_net_rx_hash *)(skb->data - sizeof(*rx_hash));
-
 	nfp_net_set_hash(netdev, skb, get_unaligned_be32(&rx_hash->hash_type),
 			 &rx_hash->hash);
 }
 
 static void *
 nfp_net_parse_meta(struct net_device *netdev, struct sk_buff *skb,
-		   int meta_len)
+		   void *data, int meta_len)
 {
-	u8 *data = skb->data - meta_len;
 	u32 meta_info;
 
 	meta_info = get_unaligned_be32(data);
@@ -1443,8 +1436,9 @@ nfp_net_parse_meta(struct net_device *netdev, struct sk_buff *skb,
 }
 
 static void
-nfp_net_rx_drop(struct nfp_net_r_vector *r_vec, struct nfp_net_rx_ring *rx_ring,
-		struct nfp_net_rx_buf *rxbuf, struct sk_buff *skb)
+nfp_net_rx_drop(const struct nfp_net_dp *dp, struct nfp_net_r_vector *r_vec,
+		struct nfp_net_rx_ring *rx_ring, struct nfp_net_rx_buf *rxbuf,
+		struct sk_buff *skb)
 {
 	u64_stats_update_begin(&r_vec->rx_sync);
 	r_vec->rx_drops++;
@@ -1456,15 +1450,15 @@ nfp_net_rx_drop(struct nfp_net_r_vector *r_vec, st