Merge branch 'thunderx-xdp'

Sunil Goutham says:

====================
net: thunderx: Adds XDP support

This patch series adds support for XDP to ThunderX NIC driver
which is used on CN88xx, CN81xx and CN83xx platforms.

Patches 1-4 are performance improvement and cleanup patches
which are done keeping XDP performance bottlenecks in view.
Rest of the patches adds actual XDP support.
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

drivers/net/ethernet/cavium/thunder/nic.h

@@ -252,12 +252,14 @@ struct nicvf_drv_stats {
 	u64 tx_csum_overflow;
 
 	/* driver debug stats */
-	u64 rcv_buffer_alloc_failures;
 	u64 tx_tso;
 	u64 tx_timeout;
 	u64 txq_stop;
 	u64 txq_wake;
 
+	u64 rcv_buffer_alloc_failures;
+	u64 page_alloc;
+
 	struct u64_stats_sync   syncp;
 };
 
@@ -266,9 +268,9 @@ struct nicvf {
 	struct net_device	*netdev;
 	struct pci_dev		*pdev;
 	void __iomem		*reg_base;
+	struct bpf_prog         *xdp_prog;
 #define	MAX_QUEUES_PER_QSET			8
 	struct queue_set	*qs;
-	struct nicvf_cq_poll	*napi[8];
 	void			*iommu_domain;
 	u8			vf_id;
 	u8			sqs_id;
@@ -294,6 +296,7 @@ struct nicvf {
 	/* Queue count */
 	u8			rx_queues;
 	u8			tx_queues;
+	u8			xdp_tx_queues;
 	u8			max_queues;
 
 	u8			node;
@@ -318,6 +321,9 @@ struct nicvf {
 	struct nicvf_drv_stats  __percpu *drv_stats;
 	struct bgx_stats	bgx_stats;
 
+	/* Napi */
+	struct nicvf_cq_poll	*napi[8];
+
 	/* MSI-X  */
 	u8			num_vec;
 	char			irq_name[NIC_VF_MSIX_VECTORS][IFNAMSIZ + 15];

drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c

@@ -100,11 +100,12 @@ static const struct nicvf_stat nicvf_drv_stats[] = {
 	NICVF_DRV_STAT(tx_csum_overlap),
 	NICVF_DRV_STAT(tx_csum_overflow),
 
-	NICVF_DRV_STAT(rcv_buffer_alloc_failures),
 	NICVF_DRV_STAT(tx_tso),
 	NICVF_DRV_STAT(tx_timeout),
 	NICVF_DRV_STAT(txq_stop),
 	NICVF_DRV_STAT(txq_wake),
+	NICVF_DRV_STAT(rcv_buffer_alloc_failures),
+	NICVF_DRV_STAT(page_alloc),
 };
 
 static const struct nicvf_stat nicvf_queue_stats[] = {
@@ -720,7 +721,7 @@ static int nicvf_set_channels(struct net_device *dev,
 	struct nicvf *nic = netdev_priv(dev);
 	int err = 0;
 	bool if_up = netif_running(dev);
-	int cqcount;
+	u8 cqcount, txq_count;
 
 	if (!channel->rx_count || !channel->tx_count)
 		return -EINVAL;
@@ -729,10 +730,26 @@ static int nicvf_set_channels(struct net_device *dev,
 	if (channel->tx_count > nic->max_queues)
 		return -EINVAL;
 
+	if (nic->xdp_prog &&
+	    ((channel->tx_count + channel->rx_count) > nic->max_queues)) {
+		netdev_err(nic->netdev,
+			   "XDP mode, RXQs + TXQs > Max %d\n",
+			   nic->max_queues);
+		return -EINVAL;
+	}
+
 	if (if_up)
 		nicvf_stop(dev);
 
-	cqcount = max(channel->rx_count, channel->tx_count);
+	nic->rx_queues = channel->rx_count;
+	nic->tx_queues = channel->tx_count;
+	if (!nic->xdp_prog)
+		nic->xdp_tx_queues = 0;
+	else
+		nic->xdp_tx_queues = channel->rx_count;
+
+	txq_count = nic->xdp_tx_queues + nic->tx_queues;
+	cqcount = max(nic->rx_queues, txq_count);
 
 	if (cqcount > MAX_CMP_QUEUES_PER_QS) {
 		nic->sqs_count = roundup(cqcount, MAX_CMP_QUEUES_PER_QS);
@@ -741,12 +758,10 @@ static int nicvf_set_channels(struct net_device *dev,
 		nic->sqs_count = 0;
 	}
 
-	nic->qs->rq_cnt = min_t(u32, channel->rx_count, MAX_RCV_QUEUES_PER_QS);
-	nic->qs->sq_cnt = min_t(u32, channel->tx_count, MAX_SND_QUEUES_PER_QS);
+	nic->qs->rq_cnt = min_t(u8, nic->rx_queues, MAX_RCV_QUEUES_PER_QS);
+	nic->qs->sq_cnt = min_t(u8, txq_count, MAX_SND_QUEUES_PER_QS);
 	nic->qs->cq_cnt = max(nic->qs->rq_cnt, nic->qs->sq_cnt);
 
-	nic->rx_queues = channel->rx_count;
-	nic->tx_queues = channel->tx_count;
 	err = nicvf_set_real_num_queues(dev, nic->tx_queues, nic->rx_queues);
 	if (err)
 		return err;

drivers/net/ethernet/cavium/thunder/nicvf_main.c

@@ -17,6 +17,9 @@
 #include <linux/prefetch.h>
 #include <linux/irq.h>
 #include <linux/iommu.h>
+#include <linux/bpf.h>
+#include <linux/bpf_trace.h>
+#include <linux/filter.h>
 
 #include "nic_reg.h"
 #include "nic.h"
@@ -397,8 +400,10 @@ static void nicvf_request_sqs(struct nicvf *nic)
 
 	if (nic->rx_queues > MAX_RCV_QUEUES_PER_QS)
 		rx_queues = nic->rx_queues - MAX_RCV_QUEUES_PER_QS;
-	if (nic->tx_queues > MAX_SND_QUEUES_PER_QS)
-		tx_queues = nic->tx_queues - MAX_SND_QUEUES_PER_QS;
+
+	tx_queues = nic->tx_queues + nic->xdp_tx_queues;
+	if (tx_queues > MAX_SND_QUEUES_PER_QS)
+		tx_queues = tx_queues - MAX_SND_QUEUES_PER_QS;
 
 	/* Set no of Rx/Tx queues in each of the SQsets */
 	for (sqs = 0; sqs < nic->sqs_count; sqs++) {
@@ -496,12 +501,99 @@ static int nicvf_init_resources(struct nicvf *nic)
 	return 0;
 }
 
+static inline bool nicvf_xdp_rx(struct nicvf *nic, struct bpf_prog *prog,
+				struct cqe_rx_t *cqe_rx, struct snd_queue *sq,
+				struct sk_buff **skb)
+{
+	struct xdp_buff xdp;
+	struct page *page;
+	u32 action;
+	u16 len, offset = 0;
+	u64 dma_addr, cpu_addr;
+	void *orig_data;
+
+	/* Retrieve packet buffer's DMA address and length */
+	len = *((u16 *)((void *)cqe_rx + (3 * sizeof(u64))));
+	dma_addr = *((u64 *)((void *)cqe_rx + (7 * sizeof(u64))));
+
+	cpu_addr = nicvf_iova_to_phys(nic, dma_addr);
+	if (!cpu_addr)
+		return false;
+	cpu_addr = (u64)phys_to_virt(cpu_addr);
+	page = virt_to_page((void *)cpu_addr);
+
+	xdp.data_hard_start = page_address(page);
+	xdp.data = (void *)cpu_addr;
+	xdp.data_end = xdp.data + len;
+	orig_data = xdp.data;
+
+	rcu_read_lock();
+	action = bpf_prog_run_xdp(prog, &xdp);
+	rcu_read_unlock();
+
+	/* Check if XDP program has changed headers */
+	if (orig_data != xdp.data) {
+		len = xdp.data_end - xdp.data;
+		offset = orig_data - xdp.data;
+		dma_addr -= offset;
+	}
+
+	switch (action) {
+	case XDP_PASS:
+		/* Check if it's a recycled page, if not
+		 * unmap the DMA mapping.
+		 *
+		 * Recycled page holds an extra reference.
+		 */
+		if (page_ref_count(page) == 1) {
+			dma_addr &= PAGE_MASK;
+			dma_unmap_page_attrs(&nic->pdev->dev, dma_addr,
+					     RCV_FRAG_LEN + XDP_PACKET_HEADROOM,
+					     DMA_FROM_DEVICE,
+					     DMA_ATTR_SKIP_CPU_SYNC);
+		}
+
+		/* Build SKB and pass on packet to network stack */
+		*skb = build_skb(xdp.data,
+				 RCV_FRAG_LEN - cqe_rx->align_pad + offset);
+		if (!*skb)
+			put_page(page);
+		else
+			skb_put(*skb, len);
+		return false;
+	case XDP_TX:
+		nicvf_xdp_sq_append_pkt(nic, sq, (u64)xdp.data, dma_addr, len);
+		return true;
+	default:
+		bpf_warn_invalid_xdp_action(action);
+	case XDP_ABORTED:
+		trace_xdp_exception(nic->netdev, prog, action);
+	case XDP_DROP:
+		/* Check if it's a recycled page, if not
+		 * unmap the DMA mapping.
+		 *
+		 * Recycled page holds an extra reference.
+		 */
+		if (page_ref_count(page) == 1) {
+			dma_addr &= PAGE_MASK;
+			dma_unmap_page_attrs(&nic->pdev->dev, dma_addr,
+					     RCV_FRAG_LEN + XDP_PACKET_HEADROOM,
+					     DMA_FROM_DEVICE,
+					     DMA_ATTR_SKIP_CPU_SYNC);
+		}
+		put_page(page);
+		return true;
+	}
+	return false;
+}
+
 static void nicvf_snd_pkt_handler(struct net_device *netdev,
 				  struct cqe_send_t *cqe_tx,
-				  int cqe_type, int budget,
+				  int budget, int *subdesc_cnt,
 				  unsigned int *tx_pkts, unsigned int *tx_bytes)
 {
 	struct sk_buff *skb = NULL;
+	struct page *page;
 	struct nicvf *nic = netdev_priv(netdev);
 	struct snd_queue *sq;
 	struct sq_hdr_subdesc *hdr;
@@ -513,12 +605,26 @@ static void nicvf_snd_pkt_handler(struct net_device *netdev,
 	if (hdr->subdesc_type != SQ_DESC_TYPE_HEADER)
 		return;
 
-	netdev_dbg(nic->netdev,
-		   "%s Qset #%d SQ #%d SQ ptr #%d subdesc count %d\n",
-		   __func__, cqe_tx->sq_qs, cqe_tx->sq_idx,
-		   cqe_tx->sqe_ptr, hdr->subdesc_cnt);
+	/* Check for errors */
+	if (cqe_tx->send_status)
+		nicvf_check_cqe_tx_errs(nic->pnicvf, cqe_tx);
+
+	/* Is this a XDP designated Tx queue */
+	if (sq->is_xdp) {
+		page = (struct page *)sq->xdp_page[cqe_tx->sqe_ptr];
+		/* Check if it's recycled page or else unmap DMA mapping */
+		if (page && (page_ref_count(page) == 1))
+			nicvf_unmap_sndq_buffers(nic, sq, cqe_tx->sqe_ptr,
+						 hdr->subdesc_cnt);
+
+		/* Release page reference for recycling */
+		if (page)
+			put_page(page);
+		sq->xdp_page[cqe_tx->sqe_ptr] = (u64)NULL;
+		*subdesc_cnt += hdr->subdesc_cnt + 1;
+		return;
+	}
 
-	nicvf_check_cqe_tx_errs(nic, cqe_tx);
 	skb = (struct sk_buff *)sq->skbuff[cqe_tx->sqe_ptr];
 	if (skb) {
 		/* Check for dummy descriptor used for HW TSO offload on 88xx */
@@ -528,12 +634,12 @@ static void nicvf_snd_pkt_handler(struct net_device *netdev,
 			 (struct sq_hdr_subdesc *)GET_SQ_DESC(sq, hdr->rsvd2);
 			nicvf_unmap_sndq_buffers(nic, sq, hdr->rsvd2,
 						 tso_sqe->subdesc_cnt);
-			nicvf_put_sq_desc(sq, tso_sqe->subdesc_cnt + 1);
+			*subdesc_cnt += tso_sqe->subdesc_cnt + 1;
 		} else {
 			nicvf_unmap_sndq_buffers(nic, sq, cqe_tx->sqe_ptr,
 						 hdr->subdesc_cnt);
 		}
-		nicvf_put_sq_desc(sq, hdr->subdesc_cnt + 1);
+		*subdesc_cnt += hdr->subdesc_cnt + 1;
 		prefetch(skb);
 		(*tx_pkts)++;
 		*tx_bytes += skb->len;
@@ -544,7 +650,7 @@ static void nicvf_snd_pkt_handler(struct net_device *netdev,
 		 * a SKB attached, so just free SQEs here.
 		 */
 		if (!nic->hw_tso)
-			nicvf_put_sq_desc(sq, hdr->subdesc_cnt + 1);
+			*subdesc_cnt += hdr->subdesc_cnt + 1;
 	}
 }
 
@@ -578,9 +684,9 @@ static inline void nicvf_set_rxhash(struct net_device *netdev,
 
 static void nicvf_rcv_pkt_handler(struct net_device *netdev,
 				  struct napi_struct *napi,
-				  struct cqe_rx_t *cqe_rx)
+				  struct cqe_rx_t *cqe_rx, struct snd_queue *sq)
 {
-	struct sk_buff *skb;
+	struct sk_buff *skb = NULL;
 	struct nicvf *nic = netdev_priv(netdev);
 	struct nicvf *snic = nic;
 	int err = 0;
@@ -595,16 +701,25 @@ static void nicvf_rcv_pkt_handler(struct net_device *netdev,
 	}
 
 	/* Check for errors */
-	err = nicvf_check_cqe_rx_errs(nic, cqe_rx);
-	if (err && !cqe_rx->rb_cnt)
-		return;
+	if (cqe_rx->err_level || cqe_rx->err_opcode) {
+		err = nicvf_check_cqe_rx_errs(nic, cqe_rx);
+		if (err && !cqe_rx->rb_cnt)
+			return;
+	}
 
-	skb = nicvf_get_rcv_skb(snic, cqe_rx);
-	if (!skb) {
-		netdev_dbg(nic->netdev, "Packet not received\n");
-		return;
+	/* For XDP, ignore pkts spanning multiple pages */
+	if (nic->xdp_prog && (cqe_rx->rb_cnt == 1)) {
+		/* Packet consumed by XDP */
+		if (nicvf_xdp_rx(snic, nic->xdp_prog, cqe_rx, sq, &skb))
+			return;
+	} else {
+		skb = nicvf_get_rcv_skb(snic, cqe_rx,
+					nic->xdp_prog ? true : false);
 	}
 
+	if (!skb)
+		return;
+
 	if (netif_msg_pktdata(nic)) {
 		netdev_info(nic->netdev, "%s: skb 0x%p, len=%d\n", netdev->name,
 			    skb, skb->len);
@@ -646,13 +761,14 @@ static int nicvf_cq_intr_handler(struct net_device *netdev, u8 cq_idx,
 {
 	int processed_cqe, work_done = 0, tx_done = 0;
 	int cqe_count, cqe_head;
+	int subdesc_cnt = 0;
 	struct nicvf *nic = netdev_priv(netdev);
 	struct queue_set *qs = nic->qs;
 	struct cmp_queue *cq = &qs->cq[cq_idx];
 	struct cqe_rx_t *cq_desc;
 	struct netdev_queue *txq;
-	struct snd_queue *sq;
-	unsigned int tx_pkts = 0, tx_bytes = 0;
+	struct snd_queue *sq = &qs->sq[cq_idx];
+	unsigned int tx_pkts = 0, tx_bytes = 0, txq_idx;
 
 	spin_lock_bh(&cq->lock);
 loop:
@@ -667,8 +783,6 @@ static int nicvf_cq_intr_handler(struct net_device *netdev, u8 cq_idx,
 	cqe_head = nicvf_queue_reg_read(nic, NIC_QSET_CQ_0_7_HEAD, cq_idx) >> 9;
 	cqe_head &= 0xFFFF;
 
-	netdev_dbg(nic->netdev, "%s CQ%d cqe_count %d cqe_head %d\n",
-		   __func__, cq_idx, cqe_count, cqe_head);
 	while (processed_cqe < cqe_count) {
 		/* Get the CQ descriptor */
 		cq_desc = (struct cqe_rx_t *)GET_CQ_DESC(cq, cqe_head);
@@ -682,17 +796,15 @@ static int nicvf_cq_intr_handler(struct net_device *netdev, u8 cq_idx,
 			break;
 		}
 
-		netdev_dbg(nic->netdev, "CQ%d cq_desc->cqe_type %d\n",
-			   cq_idx, cq_desc->cqe_type);
 		switch (cq_desc->cqe_type) {
 		case CQE_TYPE_RX:
-			nicvf_rcv_pkt_handler(netdev, napi, cq_desc);
+			nicvf_rcv_pkt_handler(netdev, napi, cq_desc, sq);
 			work_done++;
 		break;
 		case CQE_TYPE_SEND:
-			nicvf_snd_pkt_handler(netdev,
-					      (void *)cq_desc, CQE_TYPE_SEND,
-					      budget, &tx_pkts, &tx_bytes);
+			nicvf_snd_pkt_handler(netdev, (void *)cq_desc,
+					      budget, &subdesc_cnt,
+					      &tx_pkts, &tx_bytes);
 			tx_done++;
 		break;
 		case CQE_TYPE_INVALID:
@@ -704,9 +816,6 @@ static int nicvf_cq_intr_handler(struct net_device *netdev, u8 cq_idx,
 		}
 		processed_cqe++;
 	}
-	netdev_dbg(nic->netdev,
-		   "%s CQ%d processed_cqe %d work_done %d budget %d\n",
-		   __func__, cq_idx, processed_cqe, work_done, budget);
 
 	/* Ring doorbell to inform H/W to reuse processed CQEs */
 	nicvf_queue_reg_write(nic, NIC_QSET_CQ_0_7_DOOR,
@@ -716,13 +825,26 @@ static int nicvf_cq_intr_handler(struct net_device *netdev, u8 cq_idx,
 		goto loop;
 
 done:
+	/* Update SQ's descriptor free count */
+	if (subdesc_cnt)
+		nicvf_put_sq_desc(sq, subdesc_cnt);
+
+	txq_idx = nicvf_netdev_qidx(nic, cq_idx);
+	/* Handle XDP TX queues */
+	if (nic->pnicvf->xdp_prog) {
+		if (txq_idx < nic->pnicvf->xdp_tx_queues) {
+			nicvf_xdp_sq_doorbell(nic, sq, cq_idx);
+			goto out;
+		}
+		nic = nic->pnicvf;
+		txq_idx -= nic->pnicvf->xdp_tx_queues;
+	}
+
 	/* Wakeup TXQ if its stopped earlier due to SQ full */
-	sq = &nic->qs->sq[cq_idx];
 	if (tx_done ||
 	    (atomic_read(&sq->free_cnt) >= MIN_SQ_DESC_PER_PKT_XMIT)) {
 		netdev = nic->pnicvf->netdev;
-		txq = netdev_get_tx_queue(netdev,
-					  nicvf_netdev_qidx(nic, cq_idx));
+		txq = netdev_get_tx_queue(netdev, txq_idx);
 		if (tx_pkts)
 			netdev_tx_completed_queue(txq, tx_pkts, tx_bytes);
 
@@ -735,10 +857,11 @@ static int nicvf_cq_intr_handler(struct net_device *netdev, u8 cq_idx,
 			if (netif_msg_tx_err(nic))
 				netdev_warn(netdev,
 					    "%s: Transmit queue wakeup SQ%d\n",
-					    netdev->name, cq_idx);
+					    netdev->name, txq_idx);
 		}
 	}
 
+out:
 	spin_unlock_bh(&cq->lock);
 	return work_done;
 }
@@ -1054,6 +1177,13 @@ static netdev_tx_t nicvf_xmit(struct sk_buff *skb, struct net_device *netdev)
 		return NETDEV_TX_OK;
 	}
 
+	/* In XDP case, initial HW tx queues are used for XDP,
+	 * but stack's queue mapping starts at '0', so skip the
+	 * Tx queues attached to Rx queues for XDP.
+	 */
+	if (nic->xdp_prog)
+		qid += nic->xdp_tx_queues;
+
 	snic = nic;
 	/* Get secondary Qset's SQ structure */
 	if (qid >= MAX_SND_QUEUES_PER_QS) {
@@ -1531,6 +1661,114 @@ static int nicvf_set_features(struct net_device *netdev,
 	return 0;
 }
 
+static void nicvf_set_xdp_queues(struct nicvf *nic, bool bpf_attached)
+{
+	u8 cq_count, txq_count;
+
+	/* Set XDP Tx queue count same as Rx queue count */
+	if (!bpf_attached)
+		nic->xdp_tx_queues = 0;
+	else
+		nic->xdp_tx_queues = nic->rx_queues;
+
+	/* If queue count > MAX_CMP_QUEUES_PER_QS, then additional qsets
+	 * needs to be allocated, check how many.
+	 */
+	txq_count = nic->xdp_tx_queues + nic->tx_queues;
+	cq_count = max(nic->rx_queues, txq_count);
+	if (cq_count > MAX_CMP_QUEUES_PER_QS) {
+		nic->sqs_count = roundup(cq_count, MAX_CMP_QUEUES_PER_QS);
+		nic->sqs_count = (nic->sqs_count / MAX_CMP_QUEUES_PER_QS) - 1;
+	} else {
+		nic->sqs_count = 0;
+	}
+
+	/* Set primary Qset's resources */
+	nic->qs->rq_cnt = min_t(u8, nic->rx_queues, MAX_RCV_QUEUES_PER_QS);
+	nic->qs->sq_cnt = min_t(u8, txq_count, MAX_SND_QUEUES_PER_QS);
+	nic->qs->cq_cnt = max_t(u8, nic->qs->rq_cnt, nic->qs->sq_cnt);
+
+	/* Update stack */
+	nicvf_set_real_num_queues(nic->netdev, nic->tx_queues, nic->rx_queues);
+}
+
+static int nicvf_xdp_setup(struct nicvf *nic, struct bpf_prog *prog)
+{
+	struct net_device *dev = nic->netdev;
+	bool if_up = netif_running(nic->netdev);
+	struct bpf_prog *old_prog;
+	bool bpf_attached = false;
+
+	/* For now just support only the usual MTU sized frames */
+	if (prog && (dev->mtu > 1500)) {
+		netdev_warn(dev, "Jumbo frames not yet supported with XDP, current MTU %d.\n",
+			    dev->mtu);
+		return -EOPNOTSUPP;
+	}
+
+	/* ALL SQs attached to CQs i.e same as RQs, are treated as
+	 * XDP Tx queues and more Tx queues are allocated for
+	 * network stack to send pkts out.
+	 *
+	 * No of Tx queues are either same as Rx queues or whatever
+	 * is left in max no of queues possible.
+	 */
+	if ((nic->rx_queues + nic->tx_queues) > nic->max_queues) {
+		netdev_warn(dev,
+			    "Failed to attach BPF prog, RXQs + TXQs > Max %d\n",
+			    nic->max_queues);
+		return -ENOMEM;
+	}
+
+	if (if_up)
+		nicvf_stop(nic->netdev);
+
+	old_prog = xchg(&nic->xdp_prog, prog);
+	/* Detach old prog, if any */
+	if (old_prog)
+		bpf_prog_put(old_prog);
+
+	if (nic->xdp_prog) {
+		/* Attach BPF program */
+		nic->xdp_prog = bpf_prog_add(nic->xdp_prog, nic->rx_queues - 1);
+		if (!IS_ERR(nic->xdp_prog))
+			bpf_attached = true;
+	}
+
+	/* Calculate Tx queues needed for XDP and network stack */
+	nicvf_set_xdp_queues(nic, bpf_attached);
+
+	if (if_up) {
+		/* Reinitialize interface, clean slate */
+		nicvf_open(nic->netdev);
+		netif_trans_update(nic->netdev);
+	}
+
+	return 0;
+}
+
+static int nicvf_xdp(struct net_device *netdev, struct netdev_xdp *xdp)
+{
+	struct nicvf *nic = netdev_priv(netdev);
+
+	/* To avoid checks while retrieving buffer address from CQE_RX,
+	 * do not support XDP for T88 pass1.x silicons which are anyway
+	 * not in use widely.
+	 */
+	if (pass1_silicon(nic->pdev))
+		return -EOPNOTSUPP;
+
+	switch (xdp->command) {
+	case XDP_SETUP_PROG:
+		return nicvf_xdp_setup(nic, xdp->prog);
+	case XDP_QUERY_PROG:
+		xdp->prog_attached = !!nic->xdp_prog;
+		return 0;
+	default:
+		return -EINVAL;
+	}
+}
+
 static const struct net_device_ops nicvf_netdev_ops = {
 	.ndo_open		= nicvf_open,
 	.ndo_stop		= nicvf_stop,
@@ -1541,6 +1779,7 @@ static const struct net_device_ops nicvf_netdev_ops = {
 	.ndo_tx_timeout         = nicvf_tx_timeout,
 	.ndo_fix_features       = nicvf_fix_features,
 	.ndo_set_features       = nicvf_set_features,
+	.ndo_xdp		= nicvf_xdp,
 };
 
 static int nicvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)

drivers/net/ethernet/cavium/thunder/nicvf_queues.c

@@ -19,16 +19,8 @@
 #include "q_struct.h"
 #include "nicvf_queues.h"
 
-#define NICVF_PAGE_ORDER ((PAGE_SIZE <= 4096) ?  PAGE_ALLOC_COSTLY_ORDER : 0)
-
-static inline u64 nicvf_iova_to_phys(struct nicvf *nic, dma_addr_t dma_addr)
-{
-	/* Translation is installed only when IOMMU is present */
-	if (nic->iommu_domain)
-		return iommu_iova_to_phys(nic->iommu_domain, dma_addr);
-	return dma_addr;
-}
-
+static inline void nicvf_sq_add_gather_subdesc(struct snd_queue *sq, int qentry,
+					       int size, u64 data);
 static void nicvf_get_page(struct nicvf *nic)
 {
 	if (!nic->rb_pageref || !nic->rb_page)
@@ -90,46 +82,152 @@ static void nicvf_free_q_desc_mem(struct nicvf *nic, struct q_desc_mem *dmem)
 	dmem->base = NULL;
 }
 
-/* Allocate buffer for packet reception
- * HW returns memory address where packet is DMA'ed but not a pointer
- * into RBDR ring, so save buffer address at the start of fragment and
- * align the start address to a cache aligned address
+#define XDP_PAGE_REFCNT_REFILL 256
+
+/* Allocate a new page or recycle one if possible
+ *
+ * We cannot optimize dma mapping here, since
+ * 1. It's only one RBDR ring for 8 Rx queues.
+ * 2. CQE_RX gives address of the buffer where pkt has been DMA'ed
+ *    and not idx into RBDR ring, so can't refer to saved info.
+ * 3. There are multiple receive buffers per page
  */
-static inline int nicvf_alloc_rcv_buffer(struct nicvf *nic, gfp_t gfp,
-					 u32 buf_len, u64 **rbuf)
+static inline struct pgcache *nicvf_alloc_page(struct nicvf *nic,
+					       struct rbdr *rbdr, gfp_t gfp)
+{
+	int ref_count;
+	struct page *page = NULL;
+	struct pgcache *pgcache, *next;
+
+	/* Check if page is already allocated */
+	pgcache = &rbdr->pgcache[rbdr->pgidx];
+	page = pgcache->page;
+	/* Check if page can be recycled */
+	if (page) {
+		ref_count = page_ref_count(page);
+		/* Check if this page has been used once i.e 'put_page'
+		 * called after packet transmission i.e internal ref_count
+		 * and page's ref_count are equal i.e page can be recycled.
+		 */
+		if (rbdr->is_xdp && (ref_count == pgcache->ref_count))
+			pgcache->ref_count--;
+		else
+			page = NULL;
+
+		/* In non-XDP mode, page's ref_count needs to be '1' for it
+		 * to be recycled.
+		 */
+		if (!rbdr->is_xdp && (ref_count != 1))
+			page = NULL;
+	}
+
+	if (!page) {
+		page = alloc_pages(gfp | __GFP_COMP | __GFP_NOWARN, 0);
+		if (!page)
+			return NULL;
+
+		this_cpu_inc(nic->pnicvf->drv_stats->page_alloc);
+
+		/* Check for space */
+		if (rbdr->pgalloc >= rbdr->pgcnt) {
+			/* Page can still be used */
+			nic->rb_page = page;
+			return NULL;
+		}
+
+		/* Save the page in page cache */
+		pgcache->page = page;
+		pgcache->dma_addr = 0;
+		pgcache->ref_count = 0;
+		rbdr->pgalloc++;
+	}
+
+	/* Take additional page references for recycling */
+	if (rbdr->is_xdp) {
+		/* Since there is single RBDR (i.e single core doing
+		 * page recycling) per 8 Rx queues, in XDP mode adjusting
+		 * page references atomically is the biggest bottleneck, so
+		 * take bunch of references at a time.
+		 *
+		 * So here, below reference counts defer by '1'.
+		 */
+		if (!pgcache->ref_count) {
+			pgcache->ref_count = XDP_PAGE_REFCNT_REFILL;
+			page_ref_add(page, XDP_PAGE_REFCNT_REFILL);
+		}
+	} else {
+		/* In non-XDP case, single 64K page is divided across multiple
+		 * receive buffers, so cost of recycling is less anyway.
+		 * So we can do with just one extra reference.
+		 */
+		page_ref_add(page, 1);
+	}
+
+	rbdr->pgidx++;
+	rbdr->pgidx &= (rbdr->pgcnt - 1);
+
+	/* Prefetch refcount of next page in page cache */
+	next = &rbdr->pgcache[rbdr->pgidx];
+	page = next->page;
+	if (page)
+		prefetch(&page->_refcount);
+
+	return pgcache;
+}
+
+/* Allocate buffer for packet reception */
+static inline int nicvf_alloc_rcv_buffer(struct nicvf *nic, struct rbdr *rbdr,
+					 gfp_t gfp, u32 buf_len, u64 *rbuf)
 {
-	int order = NICVF_PAGE_ORDER;
+	struct pgcache *pgcache = NULL;
 
-	/* Check if request can be accomodated in previous allocated page */
-	if (nic->rb_page &&
-	    ((nic->rb_page_offset + buf_len) < (PAGE_SIZE << order))) {
+	/* Check if request can be accomodated in previous allocated page.
+	 * But in XDP mode only one buffer per page is permitted.
+	 */
+	if (!rbdr->is_xdp && nic->rb_page &&
+	    ((nic->rb_page_offset + buf_len) <= PAGE_SIZE)) {
 		nic->rb_pageref++;
 		goto ret;
 	}
 
 	nicvf_get_page(nic);
+	nic->rb_page = NULL;
 
-	/* Allocate a new page */
-	nic->rb_page = alloc_pages(gfp | __GFP_COMP | __GFP_NOWARN,
-				   order);
-	if (!nic->rb_page) {
+	/* Get new page, either recycled or new one */
+	pgcache = nicvf_alloc_page(nic, rbdr, gfp);
+	if (!pgcache && !nic->rb_page) {
 		this_cpu_inc(nic->pnicvf->drv_stats->rcv_buffer_alloc_failures);
 		return -ENOMEM;
 	}
+
 	nic->rb_page_offset = 0;
+
+	/* Reserve space for header modifications by BPF program */
+	if (rbdr->is_xdp)
+		buf_len += XDP_PACKET_HEADROOM;
+
+	/* Check if it's recycled */
+	if (pgcache)
+		nic->rb_page = pgcache->page;
 ret:
-	/* HW will ensure data coherency, CPU sync not required */
-	*rbuf = (u64 *)((u64)dma_map_page_attrs(&nic->pdev->dev, nic->rb_page,
+	if (rbdr->is_xdp && pgcache && pgcache->dma_addr) {
+		*rbuf = pgcache->dma_addr;
+	} else {
+		/* HW will ensure data coherency, CPU sync not required */
+		*rbuf = (u64)dma_map_page_attrs(&nic->pdev->dev, nic->rb_page,
 						nic->rb_page_offset, buf_len,
 						DMA_FROM_DEVICE,
-						DMA_ATTR_SKIP_CPU_SYNC));
-	if (dma_mapping_error(&nic->pdev->dev, (dma_addr_t)*rbuf)) {
-		if (!nic->rb_page_offset)
-			__free_pages(nic->rb_page, order);
-		nic->rb_page = NULL;
-		return -ENOMEM;
+						DMA_ATTR_SKIP_CPU_SYNC);
+		if (dma_mapping_error(&nic->pdev->dev, (dma_addr_t)*rbuf)) {
+			if (!nic->rb_page_offset)
+				__free_pages(nic->rb_page, 0);
+			nic->rb_page = NULL;
+			return -ENOMEM;
+		}
+		if (pgcache)
+			pgcache->dma_addr = *rbuf + XDP_PACKET_HEADROOM;
+		nic->rb_page_offset += buf_len;
 	}
-	nic->rb_page_offset += buf_len;
 
 	return 0;
 }
@@ -159,7 +257,7 @@ static int  nicvf_init_rbdr(struct nicvf *nic, struct rbdr *rbdr,
 			    int ring_len, int buf_size)
 {
 	int idx;
-	u64 *rbuf;
+	u64 rbuf;
 	struct rbdr_entry_t *desc;
 	int err;
 
@@ -177,10 +275,34 @@ static int  nicvf_init_rbdr(struct nicvf *nic, struct rbdr *rbdr,
 	rbdr->head = 0;
 	rbdr->tail = 0;
 
+	/* Initialize page recycling stuff.
+	 *
+	 * Can't use single buffer per page especially with 64K pages.
+	 * On embedded platforms i.e 81xx/83xx available memory itself
+	 * is low and minimum ring size of RBDR is 8K, that takes away
+	 * lots of memory.
+	 *
+	 * But for XDP it has to be a single buffer per page.
+	 */
+	if (!nic->pnicvf->xdp_prog) {
+		rbdr->pgcnt = ring_len / (PAGE_SIZE / buf_size);
+		rbdr->is_xdp = false;
+	} else {
+		rbdr->pgcnt = ring_len;
+		rbdr->is_xdp = true;
+	}
+	rbdr->pgcnt = roundup_pow_of_two(rbdr->pgcnt);
+	rbdr->pgcache = kzalloc(sizeof(*rbdr->pgcache) *
+				rbdr->pgcnt, GFP_KERNEL);
+	if (!rbdr->pgcache)
+		return -ENOMEM;
+	rbdr->pgidx = 0;
+	rbdr->pgalloc = 0;
+
 	nic->rb_page = NULL;
 	for (idx = 0; idx < ring_len; idx++) {
-		err = nicvf_alloc_rcv_buffer(nic, GFP_KERNEL, RCV_FRAG_LEN,
-					     &rbuf);
+		err = nicvf_alloc_rcv_buffer(nic, rbdr, GFP_KERNEL,
+					     RCV_FRAG_LEN, &rbuf);
 		if (err) {
 			/* To free already allocated and mapped ones */
 			rbdr->tail = idx - 1;
@@ -188,7 +310,7 @@ static int  nicvf_init_rbdr(struct nicvf *nic, struct rbdr *rbdr,
 		}
 
 		desc = GET_RBDR_DESC(rbdr, idx);
-		desc->buf_addr = (u64)rbuf >> NICVF_RCV_BUF_ALIGN;
+		desc->buf_addr = rbuf & ~(NICVF_RCV_BUF_ALIGN_BYTES - 1);
 	}
 
 	nicvf_get_page(nic);
@@ -201,6 +323,7 @@ static void nicvf_free_rbdr(struct nicvf *nic, struct rbdr *rbdr)
 {
 	int head, tail;
 	u64 buf_addr, phys_addr;
+	struct pgcache *pgcache;
 	struct rbdr_entry_t *desc;
 
 	if (!rbdr)
@@ -216,7 +339,7 @@ static void nicvf_free_rbdr(struct nicvf *nic, struct rbdr *rbdr)
 	/* Release page references */
 	while (head != tail) {
 		desc = GET_RBDR_DESC(rbdr, head);
-		buf_addr = ((u64)desc->buf_addr) << NICVF_RCV_BUF_ALIGN;
+		buf_addr = desc->buf_addr;
 		phys_addr = nicvf_iova_to_phys(nic, buf_addr);
 		dma_unmap_page_attrs(&nic->pdev->dev, buf_addr, RCV_FRAG_LEN,
 				     DMA_FROM_DEVICE, DMA_ATTR_SKIP_CPU_SYNC);
@@ -227,13 +350,31 @@ static void nicvf_free_rbdr(struct nicvf *nic, struct rbdr *rbdr)
 	}
 	/* Release buffer of tail desc */
 	desc = GET_RBDR_DESC(rbdr, tail);
-	buf_addr = ((u64)desc->buf_addr) << NICVF_RCV_BUF_ALIGN;
+	buf_addr = desc->buf_addr;
 	phys_addr = nicvf_iova_to_phys(nic, buf_addr);
 	dma_unmap_page_attrs(&nic->pdev->dev, buf_addr, RCV_FRAG_LEN,
 			     DMA_FROM_DEVICE, DMA_ATTR_SKIP_CPU_SYNC);
 	if (phys_addr)
 		put_page(virt_to_page(phys_to_virt(phys_addr)));
 
+	/* Sync page cache info */
+	smp_rmb();
+
+	/* Release additional page references held for recycling */
+	head = 0;
+	while (head < rbdr->pgcnt) {
+		pgcache = &rbdr->pgcache[head];
+		if (pgcache->page && page_ref_count(pgcache->page) != 0) {
+			if (!rbdr->is_xdp) {
+				put_page(pgcache->page);
+				continue;
+			}
+			page_ref_sub(pgcache->page, pgcache->ref_count - 1);
+			put_page(pgcache->page);
+		}
+		head++;
+	}
+
 	/* Free RBDR ring */
 	nicvf_free_q_desc_mem(nic, &rbdr->dmem);
 }
@@ -248,7 +389,7 @@ static void nicvf_refill_rbdr(struct nicvf *nic, gfp_t gfp)
 	int refill_rb_cnt;
 	struct rbdr *rbdr;
 	struct rbdr_entry_t *desc;
-	u64 *rbuf;
+	u64 rbuf;
 	int new_rb = 0;
 
 refill:
@@ -269,17 +410,20 @@ static void nicvf_refill_rbdr(struct nicvf *nic, gfp_t gfp)
 	else
 		refill_rb_cnt = qs->rbdr_len - qcount - 1;
 
+	/* Sync page cache info */
+	smp_rmb();
+
 	/* Start filling descs from tail */
 	tail = nicvf_queue_reg_read(nic, NIC_QSET_RBDR_0_1_TAIL, rbdr_idx) >> 3;
 	while (refill_rb_cnt) {
 		tail++;
 		tail &= (rbdr->dmem.q_len - 1);
 
-		if (nicvf_alloc_rcv_buffer(nic, gfp, RCV_FRAG_LEN, &rbuf))
+		if (nicvf_alloc_rcv_buffer(nic, rbdr, gfp, RCV_FRAG_LEN, &rbuf))
 			break;
 
 		desc = GET_RBDR_DESC(rbdr, tail);
-		desc->buf_addr = (u64)rbuf >> NICVF_RCV_BUF_ALIGN;
+		desc->buf_addr = rbuf & ~(NICVF_RCV_BUF_ALIGN_BYTES - 1);
 		refill_rb_cnt--;
 		new_rb++;
 	}
@@ -362,7 +506,7 @@ static void nicvf_free_cmp_queue(struct nicvf *nic, struct cmp_queue *cq)
 
 /* Initialize transmit queue */
 static int nicvf_init_snd_queue(struct nicvf *nic,
-				struct snd_queue *sq, int q_len)
+				struct snd_queue *sq, int q_len, int qidx)
 {
 	int err;
 
@@ -375,17 +519,38 @@ static int nicvf_init_snd_queue(struct nicvf *nic,
 	sq->skbuff = kcalloc(q_len, sizeof(u64), GFP_KERNEL);
 	if (!sq->skbuff)
 		return -ENOMEM;
+
 	sq->head = 0;
 	sq->tail = 0;
-	atomic_set(&sq->free_cnt, q_len - 1);
 	sq->thresh = SND_QUEUE_THRESH;
 
-	/* Preallocate memory for TSO segment's header */
-	sq->tso_hdrs = dma_alloc_coherent(&nic->pdev->dev,
-					  q_len * TSO_HEADER_SIZE,
-					  &sq->tso_hdrs_phys, GFP_KERNEL);
-	if (!sq->tso_hdrs)
-		return -ENOMEM;
+	/* Check if this SQ is a XDP TX queue */
+	if (nic->sqs_mode)
+		qidx += ((nic->sqs_id + 1) * MAX_SND_QUEUES_PER_QS);
+	if (qidx < nic->pnicvf->xdp_tx_queues) {
+		/* Alloc memory to save page pointers for XDP_TX */
+		sq->xdp_page = kcalloc(q_len, sizeof(u64), GFP_KERNEL);
+		if (!sq->xdp_page)
+			return -ENOMEM;
+		sq->xdp_desc_cnt = 0;
+		sq->xdp_free_cnt = q_len - 1;
+		sq->is_xdp = true;
+	} else {
+		sq->xdp_page = NULL;
+		sq->xdp_desc_cnt = 0;
+		sq->xdp_free_cnt = 0;
+		sq->is_xdp = false;
+
+		atomic_set(&sq->free_cnt, q_len - 1);
+
+		/* Preallocate memory for TSO segment's header */
+		sq->tso_hdrs = dma_alloc_coherent(&nic->pdev->dev,
+						  q_len * TSO_HEADER_SIZE,
+						  &sq->tso_hdrs_phys,
+						  GFP_KERNEL);
+		if (!sq->tso_hdrs)
+			return -ENOMEM;
+	}
 
 	return 0;
 }
@@ -411,6 +576,7 @@ void nicvf_unmap_sndq_buffers(struct nicvf *nic, struct snd_queue *sq,
 static void nicvf_free_snd_queue(struct nicvf *nic, struct snd_queue *sq)
 {
 	struct sk_buff *skb;
+	struct page *page;
 	struct sq_hdr_subdesc *hdr;
 	struct sq_hdr_subdesc *tso_sqe;
 
@@ -428,8 +594,15 @@ static void nicvf_free_snd_queue(struct nicvf *nic, struct snd_queue *sq)
 	smp_rmb();
 	while (sq->head != sq->tail) {
 		skb = (struct sk_buff *)sq->skbuff[sq->head];
-		if (!skb)
+		if (!skb || !sq->xdp_page)
+			goto next;
+
+		page = (struct page *)sq->xdp_page[sq->head];
+		if (!page)
 			goto next;
+		else
+			put_page(page);
+
 		hdr = (struct sq_hdr_subdesc *)GET_SQ_DESC(sq, sq->head);
 		/* Check for dummy descriptor used for HW TSO offload on 88xx */
 		if (hdr->dont_send) {
@@ -442,12 +615,14 @@ static void nicvf_free_snd_queue(struct nicvf *nic, struct snd_queue *sq)
 			nicvf_unmap_sndq_buffers(nic, sq, sq->head,
 						 hdr->subdesc_cnt);
 		}
-		dev_kfree_skb_any(skb);
+		if (skb)
+			dev_kfree_skb_any(skb);
 next:
 		sq->head++;
 		sq->head &= (sq->dmem.q_len - 1);
 	}
 	kfree(sq->skbuff);
+	kfree(sq->xdp_page);
 	nicvf_free_q_desc_mem(nic, &sq->dmem);
 }
 
@@ -838,7 +1013,7 @@ static int nicvf_alloc_resources(struct nicvf *nic)
 
 	/* Alloc send queue */
 	for (qidx = 0; qidx < qs->sq_cnt; qidx++) {
-		if (nicvf_init_snd_queue(nic, &qs->sq[qidx], qs->sq_len))
+		if (nicvf_init_snd_queue(nic, &qs->sq[qidx], qs->sq_len, qidx))
 			goto alloc_fail;
 	}
 
@@ -876,6 +1051,7 @@ int nicvf_set_qset_resources(struct nicvf *nic)
 
 	nic->rx_queues = qs->rq_cnt;
 	nic->tx_queues = qs->sq_cnt;
+	nic->xdp_tx_queues = 0;
 
 	return 0;
 }
@@ -940,7 +1116,10 @@ static inline int nicvf_get_sq_desc(struct snd_queue *sq, int desc_cnt)
 	int qentry;
 
 	qentry = sq->tail;
-	atomic_sub(desc_cnt, &sq->free_cnt);
+	if (!sq->is_xdp)
+		atomic_sub(desc_cnt, &sq->free_cnt);
+	else
+		sq->xdp_free_cnt -= desc_cnt;
 	sq->tail += desc_cnt;
 	sq->tail &= (sq->dmem.q_len - 1);
 
@@ -958,7 +1137,10 @@ static inline void nicvf_rollback_sq_desc(struct snd_queue *sq,
 /* Free descriptor back to SQ for future use */
 void nicvf_put_sq_desc(struct snd_queue *sq, int desc_cnt)
 {
-	atomic_add(desc_cnt, &sq->free_cnt);
+	if (!sq->is_xdp)
+		atomic_add(desc_cnt, &sq->free_cnt);
+	else
+		sq->xdp_free_cnt += desc_cnt;
 	sq->head += desc_cnt;
 	sq->head &= (sq->dmem.q_len - 1);
 }
@@ -1016,6 +1198,58 @@ void nicvf_sq_free_used_descs(struct net_device *netdev, struct snd_queue *sq,
 	}
 }
 
+/* XDP Transmit APIs */
+void nicvf_xdp_sq_doorbell(struct nicvf *nic,
+			   struct snd_queue *sq, int sq_num)
+{
+	if (!sq->xdp_desc_cnt)
+		return;
+
+	/* make sure all memory stores are done before ringing doorbell */
+	wmb();
+
+	/* Inform HW to xmit all TSO segments */
+	nicvf_queue_reg_write(nic, NIC_QSET_SQ_0_7_DOOR,
+			      sq_num, sq->xdp_desc_cnt);
+	sq->xdp_desc_cnt = 0;
+}
+
+static inline void
+nicvf_xdp_sq_add_hdr_subdesc(struct snd_queue *sq, int qentry,
+			     int subdesc_cnt, u64 data, int len)
+{
+	struct sq_hdr_subdesc *hdr;
+
+	hdr = (struct sq_hdr_subdesc *)GET_SQ_DESC(sq, qentry);
+	memset(hdr, 0, SND_QUEUE_DESC_SIZE);
+	hdr->subdesc_type = SQ_DESC_TYPE_HEADER;
+	hdr->subdesc_cnt = subdesc_cnt;
+	hdr->tot_len = len;
+	hdr->post_cqe = 1;
+	sq->xdp_page[qentry] = (u64)virt_to_page((void *)data);
+}
+
+int nicvf_xdp_sq_append_pkt(struct nicvf *nic, struct snd_queue *sq,
+			    u64 bufaddr, u64 dma_addr, u16 len)
+{
+	int subdesc_cnt = MIN_SQ_DESC_PER_PKT_XMIT;
+	int qentry;
+
+	if (subdesc_cnt > sq->xdp_free_cnt)
+		return 0;
+
+	qentry = nicvf_get_sq_desc(sq, subdesc_cnt);
+
+	nicvf_xdp_sq_add_hdr_subdesc(sq, qentry, subdesc_cnt - 1, bufaddr, len);
+
+	qentry = nicvf_get_nxt_sqentry(sq, qentry);
+	nicvf_sq_add_gather_subdesc(sq, qentry, len, dma_addr);
+
+	sq->xdp_desc_cnt += subdesc_cnt;
+
+	return 1;
+}
+
 /* Calculate no of SQ subdescriptors needed to transmit all
  * segments of this TSO packet.
  * Taken from 'Tilera network driver' with a minor modification.
@@ -1374,8 +1608,33 @@ static inline unsigned frag_num(unsigned i)
 #endif
 }
 
+static void nicvf_unmap_rcv_buffer(struct nicvf *nic, u64 dma_addr,
+				   u64 buf_addr, bool xdp)
+{
+	struct page *page = NULL;
+	int len = RCV_FRAG_LEN;
+
+	if (xdp) {
+		page = virt_to_page(phys_to_virt(buf_addr));
+		/* Check if it's a recycled page, if not
+		 * unmap the DMA mapping.
+		 *
+		 * Recycled page holds an extra reference.
+		 */
+		if (page_ref_count(page) != 1)
+			return;
+
+		len += XDP_PACKET_HEADROOM;
+		/* Receive buffers in XDP mode are mapped from page start */
+		dma_addr &= PAGE_MASK;
+	}
+	dma_unmap_page_attrs(&nic->pdev->dev, dma_addr, len,
+			     DMA_FROM_DEVICE, DMA_ATTR_SKIP_CPU_SYNC);
+}
+
 /* Returns SKB for a received packet */
-struct sk_buff *nicvf_get_rcv_skb(struct nicvf *nic, struct cqe_rx_t *cqe_rx)
+struct sk_buff *nicvf_get_rcv_skb(struct nicvf *nic,
+				  struct cqe_rx_t *cqe_rx, bool xdp)
 {
 	int frag;
 	int payload_len = 0;
@@ -1410,10 +1669,9 @@ struct sk_buff *nicvf_get_rcv_skb(struct nicvf *nic, struct cqe_rx_t *cqe_rx)
 
 		if (!frag) {
 			/* First fragment */
-			dma_unmap_page_attrs(&nic->pdev->dev,
-					     *rb_ptrs - cqe_rx->align_pad,
-					     RCV_FRAG_LEN, DMA_FROM_DEVICE,
-					     DMA_ATTR_SKIP_CPU_SYNC);
+			nicvf_unmap_rcv_buffer(nic,
+					       *rb_ptrs - cqe_rx->align_pad,
+					       phys_addr, xdp);
 			skb = nicvf_rb_ptr_to_skb(nic,
 						  phys_addr - cqe_rx->align_pad,
 						  payload_len);
@@ -1423,9 +1681,7 @@ struct sk_buff *nicvf_get_rcv_skb(struct nicvf *nic, struct cqe_rx_t *cqe_rx)
 			skb_put(skb, payload_len);
 		} else {
 			/* Add fragments */
-			dma_unmap_page_attrs(&nic->pdev->dev, *rb_ptrs,
-					     RCV_FRAG_LEN, DMA_FROM_DEVICE,
-					     DMA_ATTR_SKIP_CPU_SYNC);
+			nicvf_unmap_rcv_buffer(nic, *rb_ptrs, phys_addr, xdp);
 			page = virt_to_page(phys_to_virt(phys_addr));
 			offset = phys_to_virt(phys_addr) - page_address(page);
 			skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page,
@@ -1555,9 +1811,6 @@ void nicvf_update_sq_stats(struct nicvf *nic, int sq_idx)
 /* Check for errors in the receive cmp.queue entry */
 int nicvf_check_cqe_rx_errs(struct nicvf *nic, struct cqe_rx_t *cqe_rx)
 {
-	if (!cqe_rx->err_level && !cqe_rx->err_opcode)
-		return 0;
-
 	if (netif_msg_rx_err(nic))
 		netdev_err(nic->netdev,
 			   "%s: RX error CQE err_level 0x%x err_opcode 0x%x\n",
@@ -1646,8 +1899,6 @@ int nicvf_check_cqe_rx_errs(struct nicvf *nic, struct cqe_rx_t *cqe_rx)
 int nicvf_check_cqe_tx_errs(struct nicvf *nic, struct cqe_send_t *cqe_tx)
 {
 	switch (cqe_tx->send_status) {
-	case CQ_TX_ERROP_GOOD:
-		return 0;
 	case CQ_TX_ERROP_DESC_FAULT:
 		this_cpu_inc(nic->drv_stats->tx_desc_fault);
 		break;

drivers/net/ethernet/cavium/thunder/nicvf_queues.h

@@ -10,6 +10,7 @@
 #define NICVF_QUEUES_H
 
 #include <linux/netdevice.h>
+#include <linux/iommu.h>
 #include "q_struct.h"
 
 #define MAX_QUEUE_SET			128
@@ -213,6 +214,12 @@ struct q_desc_mem {
 	void		*unalign_base;
 };
 
+struct pgcache {
+	struct page	*page;
+	int		ref_count;
+	u64		dma_addr;
+};
+
 struct rbdr {
 	bool		enable;
 	u32		dma_size;
@@ -222,6 +229,13 @@ struct rbdr {
 	u32		head;
 	u32		tail;
 	struct q_desc_mem   dmem;
+	bool		is_xdp;
+
+	/* For page recycling */
+	int		pgidx;
+	int		pgcnt;
+	int		pgalloc;
+	struct pgcache	*pgcache;
 } ____cacheline_aligned_in_smp;
 
 struct rcv_queue {
@@ -258,6 +272,10 @@ struct snd_queue {
 	u32		tail;
 	u64		*skbuff;
 	void		*desc;
+	u64		*xdp_page;
+	u16		xdp_desc_cnt;
+	u16		xdp_free_cnt;
+	bool		is_xdp;
 
 #define	TSO_HEADER_SIZE	128
 	/* For TSO segment's header */
@@ -301,6 +319,14 @@ struct queue_set {
 
 #define	CQ_ERR_MASK	(CQ_WR_FULL | CQ_WR_DISABLE | CQ_WR_FAULT)
 
+static inline u64 nicvf_iova_to_phys(struct nicvf *nic, dma_addr_t dma_addr)
+{
+	/* Translation is installed only when IOMMU is present */
+	if (nic->iommu_domain)
+		return iommu_iova_to_phys(nic->iommu_domain, dma_addr);
+	return dma_addr;
+}
+
 void nicvf_unmap_sndq_buffers(struct nicvf *nic, struct snd_queue *sq,
 			      int hdr_sqe, u8 subdesc_cnt);
 void nicvf_config_vlan_stripping(struct nicvf *nic,
@@ -318,8 +344,12 @@ void nicvf_sq_free_used_descs(struct net_device *netdev,
 			      struct snd_queue *sq, int qidx);
 int nicvf_sq_append_skb(struct nicvf *nic, struct snd_queue *sq,
 			struct sk_buff *skb, u8 sq_num);
+int nicvf_xdp_sq_append_pkt(struct nicvf *nic, struct snd_queue *sq,
+			    u64 bufaddr, u64 dma_addr, u16 len);
+void nicvf_xdp_sq_doorbell(struct nicvf *nic, struct snd_queue *sq, int sq_num);
 
-struct sk_buff *nicvf_get_rcv_skb(struct nicvf *nic, struct cqe_rx_t *cqe_rx);
+struct sk_buff *nicvf_get_rcv_skb(struct nicvf *nic,
+				  struct cqe_rx_t *cqe_rx, bool xdp);
 void nicvf_rbdr_task(unsigned long data);
 void nicvf_rbdr_work(struct work_struct *work);
 

drivers/net/ethernet/cavium/thunder/q_struct.h

@@ -359,15 +359,7 @@ union cq_desc_t {
 };
 
 struct rbdr_entry_t {
-#if defined(__BIG_ENDIAN_BITFIELD)
-	u64   rsvd0:15;
-	u64   buf_addr:42;
-	u64   cache_align:7;
-#elif defined(__LITTLE_ENDIAN_BITFIELD)
-	u64   cache_align:7;
-	u64   buf_addr:42;
-	u64   rsvd0:15;
-#endif
+	u64   buf_addr;
 };
 
 /* TCP reassembly context */