Merge branch 'dpaa2-eth-AF_XDP-zc'

Ioana Ciornei says:

====================
net: dpaa2-eth: AF_XDP zero-copy support

This patch set adds support for AF_XDP zero-copy in the dpaa2-eth
driver. The support is available on the LX2160A SoC and its variants and
only on interfaces (DPNIs) with a maximum of 8 queues (HW limitations
are the root cause).

We are first implementing the .get_channels() callback since this a
dependency for further work.

Patches 2-3 are working on making the necessary changes for multiple
buffer pools on a single interface. By default, without an AF_XDP socket
attached, only a single buffer pool will be used and shared between all
the queues. The changes in the functions are made in this patch, but the
actual allocation and setup of a new BP is done in patch#10.

Patches 4-5 are improving the information exposed in debugfs. We are
exposing a new file to show which buffer pool is used by what channels
and how many buffers it currently has.

The 6th patch updates the dpni_set_pools() firmware API so that we are
capable of setting up a different buffer per queue in later patches.

In the 7th patch the generic dev_open/close APIs are used instead of the
dpaa2-eth internal ones.

Patches 8-9 are rearranging the existing code in dpaa2-eth.c in order to
create new functions which will be used in the XSK implementation in
dpaa2-xsk.c

Finally, the last 3 patches are adding the actual support for both the
Rx and Tx path of AF_XDP zero-copy and some associated tracepoints.
Details on the implementation can be found in the actual patch.

Changes in v2:
 - 3/12:  Export dpaa2_eth_allocate_dpbp/dpaa2_eth_free_dpbp in this
   patch to avoid a build warning. The functions will be used in next
   patches.
 - 6/12:  Use __le16 instead of u16 for the dpbp_id field.
 - 12/12: Use xdp_buff->data_hard_start when tracing the BP seeding.

Changes in v3:
 - 3/12: fix leaking of bp on error path
====================

Acked-by: Björn Töpel <bjorn@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

11 files changed, 1094 insertions, 242 deletions

diff --git a/MAINTAINERS b/MAINTAINERS
index 92708912fef8..479a15d86a91 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -6326,6 +6326,7 @@ F:	drivers/net/ethernet/freescale/dpaa2/Kconfig
 F:	drivers/net/ethernet/freescale/dpaa2/Makefile
 F:	drivers/net/ethernet/freescale/dpaa2/dpaa2-eth*
 F:	drivers/net/ethernet/freescale/dpaa2/dpaa2-mac*
+F:	drivers/net/ethernet/freescale/dpaa2/dpaa2-xsk*
 F:	drivers/net/ethernet/freescale/dpaa2/dpkg.h
 F:	drivers/net/ethernet/freescale/dpaa2/dpmac*
 F:	drivers/net/ethernet/freescale/dpaa2/dpni*
diff --git a/drivers/net/ethernet/freescale/dpaa2/Makefile b/drivers/net/ethernet/freescale/dpaa2/Makefile
index 3d9842af7f10..1b05ba8d1cbf 100644
--- a/drivers/net/ethernet/freescale/dpaa2/Makefile
+++ b/drivers/net/ethernet/freescale/dpaa2/Makefile
@@ -7,7 +7,7 @@ obj-$(CONFIG_FSL_DPAA2_ETH)		+= fsl-dpaa2-eth.o
 obj-$(CONFIG_FSL_DPAA2_PTP_CLOCK)	+= fsl-dpaa2-ptp.o
 obj-$(CONFIG_FSL_DPAA2_SWITCH)		+= fsl-dpaa2-switch.o
 
-fsl-dpaa2-eth-objs	:= dpaa2-eth.o dpaa2-ethtool.o dpni.o dpaa2-mac.o dpmac.o dpaa2-eth-devlink.o
+fsl-dpaa2-eth-objs	:= dpaa2-eth.o dpaa2-ethtool.o dpni.o dpaa2-mac.o dpmac.o dpaa2-eth-devlink.o dpaa2-xsk.o
 fsl-dpaa2-eth-${CONFIG_FSL_DPAA2_ETH_DCB} += dpaa2-eth-dcb.o
 fsl-dpaa2-eth-${CONFIG_DEBUG_FS} += dpaa2-eth-debugfs.o
 fsl-dpaa2-ptp-objs	:= dpaa2-ptp.o dprtc.o
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-debugfs.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-debugfs.c
index 8356af4631fd..1af254caeb0d 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-debugfs.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-debugfs.c
@@ -98,14 +98,14 @@ static int dpaa2_dbg_ch_show(struct seq_file *file, void *offset)
 	int i;
 
 	seq_printf(file, "Channel stats for %s:\n", priv->net_dev->name);
-	seq_printf(file, "%s%16s%16s%16s%16s%16s%16s\n",
-		   "CHID", "CPU", "Deq busy", "Frames", "CDANs",
+	seq_printf(file, "%s  %5s%16s%16s%16s%16s%16s%16s\n",
+		   "IDX", "CHID", "CPU", "Deq busy", "Frames", "CDANs",
 		   "Avg Frm/CDAN", "Buf count");
 
 	for (i = 0; i < priv->num_channels; i++) {
 		ch = priv->channel[i];
-		seq_printf(file, "%4d%16d%16llu%16llu%16llu%16llu%16d\n",
-			   ch->ch_id,
+		seq_printf(file, "%3s%d%6d%16d%16llu%16llu%16llu%16llu%16d\n",
+			   "CH#", i, ch->ch_id,
 			   ch->nctx.desired_cpu,
 			   ch->stats.dequeue_portal_busy,
 			   ch->stats.frames,
@@ -119,6 +119,51 @@ static int dpaa2_dbg_ch_show(struct seq_file *file, void *offset)
 
 DEFINE_SHOW_ATTRIBUTE(dpaa2_dbg_ch);
 
+static int dpaa2_dbg_bp_show(struct seq_file *file, void *offset)
+{
+	struct dpaa2_eth_priv *priv = (struct dpaa2_eth_priv *)file->private;
+	int i, j, num_queues, buf_cnt;
+	struct dpaa2_eth_bp *bp;
+	char ch_name[10];
+	int err;
+
+	/* Print out the header */
+	seq_printf(file, "Buffer pool info for %s:\n", priv->net_dev->name);
+	seq_printf(file, "%s  %10s%15s", "IDX", "BPID", "Buf count");
+	num_queues = dpaa2_eth_queue_count(priv);
+	for (i = 0; i < num_queues; i++) {
+		snprintf(ch_name, sizeof(ch_name), "CH#%d", i);
+		seq_printf(file, "%10s", ch_name);
+	}
+	seq_printf(file, "\n");
+
+	/* For each buffer pool, print out its BPID, the number of buffers in
+	 * that buffer pool and the channels which are using it.
+	 */
+	for (i = 0; i < priv->num_bps; i++) {
+		bp = priv->bp[i];
+
+		err = dpaa2_io_query_bp_count(NULL, bp->bpid, &buf_cnt);
+		if (err) {
+			netdev_warn(priv->net_dev, "Buffer count query error %d\n", err);
+			return err;
+		}
+
+		seq_printf(file, "%3s%d%10d%15d", "BP#", i, bp->bpid, buf_cnt);
+		for (j = 0; j < num_queues; j++) {
+			if (priv->channel[j]->bp == bp)
+				seq_printf(file, "%10s", "x");
+			else
+				seq_printf(file, "%10s", "");
+		}
+		seq_printf(file, "\n");
+	}
+
+	return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(dpaa2_dbg_bp);
+
 void dpaa2_dbg_add(struct dpaa2_eth_priv *priv)
 {
 	struct fsl_mc_device *dpni_dev;
@@ -139,6 +184,10 @@ void dpaa2_dbg_add(struct dpaa2_eth_priv *priv)
 
 	/* per-fq stats file */
 	debugfs_create_file("ch_stats", 0444, dir, priv, &dpaa2_dbg_ch_fops);
+
+	/* per buffer pool stats file */
+	debugfs_create_file("bp_stats", 0444, dir, priv, &dpaa2_dbg_bp_fops);
+
 }
 
 void dpaa2_dbg_remove(struct dpaa2_eth_priv *priv)
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-trace.h b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-trace.h
index 5fb5f14e01ec..9b43fadb9b11 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-trace.h
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-trace.h
@@ -73,6 +73,14 @@ DEFINE_EVENT(dpaa2_eth_fd, dpaa2_tx_fd,
 	     TP_ARGS(netdev, fd)
 );
 
+/* Tx (egress) XSK fd */
+DEFINE_EVENT(dpaa2_eth_fd, dpaa2_tx_xsk_fd,
+	     TP_PROTO(struct net_device *netdev,
+		      const struct dpaa2_fd *fd),
+
+	     TP_ARGS(netdev, fd)
+);
+
 /* Rx fd */
 DEFINE_EVENT(dpaa2_eth_fd, dpaa2_rx_fd,
 	     TP_PROTO(struct net_device *netdev,
@@ -81,6 +89,14 @@ DEFINE_EVENT(dpaa2_eth_fd, dpaa2_rx_fd,
 	     TP_ARGS(netdev, fd)
 );
 
+/* Rx XSK fd */
+DEFINE_EVENT(dpaa2_eth_fd, dpaa2_rx_xsk_fd,
+	     TP_PROTO(struct net_device *netdev,
+		      const struct dpaa2_fd *fd),
+
+	     TP_ARGS(netdev, fd)
+);
+
 /* Tx confirmation fd */
 DEFINE_EVENT(dpaa2_eth_fd, dpaa2_tx_conf_fd,
 	     TP_PROTO(struct net_device *netdev,
@@ -90,57 +106,81 @@ DEFINE_EVENT(dpaa2_eth_fd, dpaa2_tx_conf_fd,
 );
 
 /* Log data about raw buffers. Useful for tracing DPBP content. */
-TRACE_EVENT(dpaa2_eth_buf_seed,
-	    /* Trace function prototype */
-	    TP_PROTO(struct net_device *netdev,
-		     /* virtual address and size */
-		     void *vaddr,
-		     size_t size,
-		     /* dma map address and size */
-		     dma_addr_t dma_addr,
-		     size_t map_size,
-		     /* buffer pool id, if relevant */
-		     u16 bpid),
-
-	    /* Repeat argument list here */
-	    TP_ARGS(netdev, vaddr, size, dma_addr, map_size, bpid),
-
-	    /* A structure containing the relevant information we want
-	     * to record. Declare name and type for each normal element,
-	     * name, type and size for arrays. Use __string for variable
-	     * length strings.
-	     */
-	    TP_STRUCT__entry(
-			     __field(void *, vaddr)
-			     __field(size_t, size)
-			     __field(dma_addr_t, dma_addr)
-			     __field(size_t, map_size)
-			     __field(u16, bpid)
-			     __string(name, netdev->name)
-	    ),
-
-	    /* The function that assigns values to the above declared
-	     * fields
-	     */
-	    TP_fast_assign(
-			   __entry->vaddr = vaddr;
-			   __entry->size = size;
-			   __entry->dma_addr = dma_addr;
-			   __entry->map_size = map_size;
-			   __entry->bpid = bpid;
-			   __assign_str(name, netdev->name);
-	    ),
-
-	    /* This is what gets printed when the trace event is
-	     * triggered.
-	     */
-	    TP_printk(TR_BUF_FMT,
-		      __get_str(name),
-		      __entry->vaddr,
-		      __entry->size,
-		      &__entry->dma_addr,
-		      __entry->map_size,
-		      __entry->bpid)
+DECLARE_EVENT_CLASS(dpaa2_eth_buf,
+		    /* Trace function prototype */
+		    TP_PROTO(struct net_device *netdev,
+			     /* virtual address and size */
+			    void *vaddr,
+			    size_t size,
+			    /* dma map address and size */
+			    dma_addr_t dma_addr,
+			    size_t map_size,
+			    /* buffer pool id, if relevant */
+			    u16 bpid),
+
+		    /* Repeat argument list here */
+		    TP_ARGS(netdev, vaddr, size, dma_addr, map_size, bpid),
+
+		    /* A structure containing the relevant information we want
+		     * to record. Declare name and type for each normal element,
+		     * name, type and size for arrays. Use __string for variable
+		     * length strings.
+		     */
+		    TP_STRUCT__entry(
+				      __field(void *, vaddr)
+				      __field(size_t, size)
+				      __field(dma_addr_t, dma_addr)
+				      __field(size_t, map_size)
+				      __field(u16, bpid)
+				      __string(name, netdev->name)
+		    ),
+
+		    /* The function that assigns values to the above declared
+		     * fields
+		     */
+		    TP_fast_assign(
+				   __entry->vaddr = vaddr;
+				   __entry->size = size;
+				   __entry->dma_addr = dma_addr;
+				   __entry->map_size = map_size;
+				   __entry->bpid = bpid;
+				   __assign_str(name, netdev->name);
+		    ),
+
+		    /* This is what gets printed when the trace event is
+		     * triggered.
+		     */
+		    TP_printk(TR_BUF_FMT,
+			      __get_str(name),
+			      __entry->vaddr,
+			      __entry->size,
+			      &__entry->dma_addr,
+			      __entry->map_size,
+			      __entry->bpid)
+);
+
+/* Main memory buff seeding */
+DEFINE_EVENT(dpaa2_eth_buf, dpaa2_eth_buf_seed,
+	     TP_PROTO(struct net_device *netdev,
+		      void *vaddr,
+		      size_t size,
+		      dma_addr_t dma_addr,
+		      size_t map_size,
+		      u16 bpid),
+
+	     TP_ARGS(netdev, vaddr, size, dma_addr, map_size, bpid)
+);
+
+/* UMEM buff seeding on AF_XDP fast path */
+DEFINE_EVENT(dpaa2_eth_buf, dpaa2_xsk_buf_seed,
+	     TP_PROTO(struct net_device *netdev,
+		      void *vaddr,
+		      size_t size,
+		      dma_addr_t dma_addr,
+		      size_t map_size,
+		      u16 bpid),
+
+	     TP_ARGS(netdev, vaddr, size, dma_addr, map_size, bpid)
 );
 
 /* If only one event of a certain type needs to be declared, use TRACE_EVENT().
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
index 8d029addddad..281d7e3905c1 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause)
 /* Copyright 2014-2016 Freescale Semiconductor Inc.
- * Copyright 2016-2020 NXP
+ * Copyright 2016-2022 NXP
  */
 #include <linux/init.h>
 #include <linux/module.h>
@@ -19,6 +19,7 @@
 #include <net/pkt_cls.h>
 #include <net/sock.h>
 #include <net/tso.h>
+#include <net/xdp_sock_drv.h>
 
 #include "dpaa2-eth.h"
 
@@ -104,8 +105,8 @@ static void dpaa2_ptp_onestep_reg_update_method(struct dpaa2_eth_priv *priv)
 	priv->dpaa2_set_onestep_params_cb = dpaa2_update_ptp_onestep_direct;
 }
 
-static void *dpaa2_iova_to_virt(struct iommu_domain *domain,
-				dma_addr_t iova_addr)
+void *dpaa2_iova_to_virt(struct iommu_domain *domain,
+			 dma_addr_t iova_addr)
 {
 	phys_addr_t phys_addr;
 
@@ -279,23 +280,33 @@ static struct sk_buff *dpaa2_eth_build_frag_skb(struct dpaa2_eth_priv *priv,
  * be released in the pool
  */
 static void dpaa2_eth_free_bufs(struct dpaa2_eth_priv *priv, u64 *buf_array,
-				int count)
+				int count, bool xsk_zc)
 {
 	struct device *dev = priv->net_dev->dev.parent;
+	struct dpaa2_eth_swa *swa;
+	struct xdp_buff *xdp_buff;
 	void *vaddr;
 	int i;
 
 	for (i = 0; i < count; i++) {
 		vaddr = dpaa2_iova_to_virt(priv->iommu_domain, buf_array[i]);
-		dma_unmap_page(dev, buf_array[i], priv->rx_buf_size,
-			       DMA_BIDIRECTIONAL);
-		free_pages((unsigned long)vaddr, 0);
+
+		if (!xsk_zc) {
+			dma_unmap_page(dev, buf_array[i], priv->rx_buf_size,
+				       DMA_BIDIRECTIONAL);
+			free_pages((unsigned long)vaddr, 0);
+		} else {
+			swa = (struct dpaa2_eth_swa *)
+				(vaddr + DPAA2_ETH_RX_HWA_SIZE);
+			xdp_buff = swa->xsk.xdp_buff;
+			xsk_buff_free(xdp_buff);
+		}
 	}
 }
 
-static void dpaa2_eth_recycle_buf(struct dpaa2_eth_priv *priv,
-				  struct dpaa2_eth_channel *ch,
-				  dma_addr_t addr)
+void dpaa2_eth_recycle_buf(struct dpaa2_eth_priv *priv,
+			   struct dpaa2_eth_channel *ch,
+			   dma_addr_t addr)
 {
 	int retries = 0;
 	int err;
@@ -304,7 +315,7 @@ static void dpaa2_eth_recycle_buf(struct dpaa2_eth_priv *priv,
 	if (ch->recycled_bufs_cnt < DPAA2_ETH_BUFS_PER_CMD)
 		return;
 
-	while ((err = dpaa2_io_service_release(ch->dpio, priv->bpid,
+	while ((err = dpaa2_io_service_release(ch->dpio, ch->bp->bpid,
 					       ch->recycled_bufs,
 					       ch->recycled_bufs_cnt)) == -EBUSY) {
 		if (retries++ >= DPAA2_ETH_SWP_BUSY_RETRIES)
@@ -313,7 +324,8 @@ static void dpaa2_eth_recycle_buf(struct dpaa2_eth_priv *priv,
 	}
 
 	if (err) {
-		dpaa2_eth_free_bufs(priv, ch->recycled_bufs, ch->recycled_bufs_cnt);
+		dpaa2_eth_free_bufs(priv, ch->recycled_bufs,
+				    ch->recycled_bufs_cnt, ch->xsk_zc);
 		ch->buf_count -= ch->recycled_bufs_cnt;
 	}
 
@@ -377,10 +389,10 @@ static void dpaa2_eth_xdp_tx_flush(struct dpaa2_eth_priv *priv,
 	fq->xdp_tx_fds.num = 0;
 }
 
-static void dpaa2_eth_xdp_enqueue(struct dpaa2_eth_priv *priv,
-				  struct dpaa2_eth_channel *ch,
-				  struct dpaa2_fd *fd,
-				  void *buf_start, u16 queue_id)
+void dpaa2_eth_xdp_enqueue(struct dpaa2_eth_priv *priv,
+			   struct dpaa2_eth_channel *ch,
+			   struct dpaa2_fd *fd,
+			   void *buf_start, u16 queue_id)
 {
 	struct dpaa2_faead *faead;
 	struct dpaa2_fd *dest_fd;
@@ -485,19 +497,15 @@ out:
 	return xdp_act;
 }
 
-static struct sk_buff *dpaa2_eth_copybreak(struct dpaa2_eth_channel *ch,
-					   const struct dpaa2_fd *fd,
-					   void *fd_vaddr)
+struct sk_buff *dpaa2_eth_alloc_skb(struct dpaa2_eth_priv *priv,
+				    struct dpaa2_eth_channel *ch,
+				    const struct dpaa2_fd *fd, u32 fd_length,
+				    void *fd_vaddr)
 {
 	u16 fd_offset = dpaa2_fd_get_offset(fd);
-	struct dpaa2_eth_priv *priv = ch->priv;
-	u32 fd_length = dpaa2_fd_get_len(fd);
 	struct sk_buff *skb = NULL;
 	unsigned int skb_len;
 
-	if (fd_length > priv->rx_copybreak)
-		return NULL;
-
 	skb_len = fd_length + dpaa2_eth_needed_headroom(NULL);
 
 	skb = napi_alloc_skb(&ch->napi, skb_len);
@@ -514,11 +522,66 @@ static struct sk_buff *dpaa2_eth_copybreak(struct dpaa2_eth_channel *ch,
 	return skb;
 }
 
+static struct sk_buff *dpaa2_eth_copybreak(struct dpaa2_eth_channel *ch,
+					   const struct dpaa2_fd *fd,
+					   void *fd_vaddr)
+{
+	struct dpaa2_eth_priv *priv = ch->priv;
+	u32 fd_length = dpaa2_fd_get_len(fd);
+
+	if (fd_length > priv->rx_copybreak)
+		return NULL;
+
+	return dpaa2_eth_alloc_skb(priv, ch, fd, fd_length, fd_vaddr);
+}
+
+void dpaa2_eth_receive_skb(struct dpaa2_eth_priv *priv,
+			   struct dpaa2_eth_channel *ch,
+			   const struct dpaa2_fd *fd, void *vaddr,
+			   struct dpaa2_eth_fq *fq,
+			   struct rtnl_link_stats64 *percpu_stats,
+			   struct sk_buff *skb)
+{
+	struct dpaa2_fas *fas;
+	u32 status = 0;
+
+	fas = dpaa2_get_fas(vaddr, false);
+	prefetch(fas);
+	prefetch(skb->data);
+
+	/* Get the timestamp value */
+	if (priv->rx_tstamp) {
+		struct skb_shared_hwtstamps *shhwtstamps = skb_hwtstamps(skb);
+		__le64 *ts = dpaa2_get_ts(vaddr, false);
+		u64 ns;
+
+		memset(shhwtstamps, 0, sizeof(*shhwtstamps));
+
+		ns = DPAA2_PTP_CLK_PERIOD_NS * le64_to_cpup(ts);
+		shhwtstamps->hwtstamp = ns_to_ktime(ns);
+	}
+
+	/* Check if we need to validate the L4 csum */
+	if (likely(dpaa2_fd_get_frc(fd) & DPAA2_FD_FRC_FASV)) {
+		status = le32_to_cpu(fas->status);
+		dpaa2_eth_validate_rx_csum(priv, status, skb);
+	}
+
+	skb->protocol = eth_type_trans(skb, priv->net_dev);
+	skb_record_rx_queue(skb, fq->flowid);
+
+	percpu_stats->rx_packets++;
+	percpu_stats->rx_bytes += dpaa2_fd_get_len(fd);
+	ch->stats.bytes_per_cdan += dpaa2_fd_get_len(fd);
+
+	list_add_tail(&skb->list, ch->rx_list);
+}
+
 /* Main Rx frame processing routine */
-static void dpaa2_eth_rx(struct dpaa2_eth_priv *priv,
-			 struct dpaa2_eth_channel *ch,
-			 const struct dpaa2_fd *fd,
-			 struct dpaa2_eth_fq *fq)
+void dpaa2_eth_rx(struct dpaa2_eth_priv *priv,
+		  struct dpaa2_eth_channel *ch,
+		  const struct dpaa2_fd *fd,
+		  struct dpaa2_eth_fq *fq)
 {
 	dma_addr_t addr = dpaa2_fd_get_addr(fd);
 	u8 fd_format = dpaa2_fd_get_format(fd);
@@ -527,9 +590,7 @@ static void dpaa2_eth_rx(struct dpaa2_eth_priv *priv,
 	struct rtnl_link_stats64 *percpu_stats;
 	struct dpaa2_eth_drv_stats *percpu_extras;
 	struct device *dev = priv->net_dev->dev.parent;
-	struct dpaa2_fas *fas;
 	void *buf_data;
-	u32 status = 0;
 	u32 xdp_act;
 
 	/* Tracing point */
@@ -539,8 +600,6 @@ static void dpaa2_eth_rx(struct dpaa2_eth_priv *priv,
 	dma_sync_single_for_cpu(dev, addr, priv->rx_buf_size,
 				DMA_BIDIRECTIONAL);
 
-	fas = dpaa2_get_fas(vaddr, false);
-	prefetch(fas);
 	buf_data = vaddr + dpaa2_fd_get_offset(fd);
 	prefetch(buf_data);
 
@@ -578,35 +637,7 @@ static void dpaa2_eth_rx(struct dpaa2_eth_priv *priv,
 	if (unlikely(!skb))
 		goto err_build_skb;
 
-	prefetch(skb->data);
-
-	/* Get the timestamp value */
-	if (priv->rx_tstamp) {
-		struct skb_shared_hwtstamps *shhwtstamps = skb_hwtstamps(skb);
-		__le64 *ts = dpaa2_get_ts(vaddr, false);
-		u64 ns;
-
-		memset(shhwtstamps, 0, sizeof(*shhwtstamps));
-
-		ns = DPAA2_PTP_CLK_PERIOD_NS * le64_to_cpup(ts);
-		shhwtstamps->hwtstamp = ns_to_ktime(ns);
-	}
-
-	/* Check if we need to validate the L4 csum */
-	if (likely(dpaa2_fd_get_frc(fd) & DPAA2_FD_FRC_FASV)) {
-		status = le32_to_cpu(fas->status);
-		dpaa2_eth_validate_rx_csum(priv, status, skb);
-	}
-
-	skb->protocol = eth_type_trans(skb, priv->net_dev);
-	skb_record_rx_queue(skb, fq->flowid);
-
-	percpu_stats->rx_packets++;
-	percpu_stats->rx_bytes += dpaa2_fd_get_len(fd);
-	ch->stats.bytes_per_cdan += dpaa2_fd_get_len(fd);
-
-	list_add_tail(&skb->list, ch->rx_list);
-
+	dpaa2_eth_receive_skb(priv, ch, fd, vaddr, fq, percpu_stats, skb);
 	return;
 
 err_build_skb:
@@ -827,7 +858,7 @@ static void dpaa2_eth_enable_tx_tstamp(struct dpaa2_eth_priv *priv,
 	}
 }
 
-static void *dpaa2_eth_sgt_get(struct dpaa2_eth_priv *priv)
+void *dpaa2_eth_sgt_get(struct dpaa2_eth_priv *priv)
 {
 	struct dpaa2_eth_sgt_cache *sgt_cache;
 	void *sgt_buf = NULL;
@@ -849,7 +880,7 @@ static void *dpaa2_eth_sgt_get(struct dpaa2_eth_priv *priv)
 	return sgt_buf;
 }
 
-static void dpaa2_eth_sgt_recycle(struct dpaa2_eth_priv *priv, void *sgt_buf)
+void dpaa2_eth_sgt_recycle(struct dpaa2_eth_priv *priv, void *sgt_buf)
 {
 	struct dpaa2_eth_sgt_cache *sgt_cache;
 
@@ -1084,9 +1115,10 @@ static int dpaa2_eth_build_single_fd(struct dpaa2_eth_priv *priv,
  * This can be called either from dpaa2_eth_tx_conf() or on the error path of
  * dpaa2_eth_tx().
  */
-static void dpaa2_eth_free_tx_fd(struct dpaa2_eth_priv *priv,
-				 struct dpaa2_eth_fq *fq,
-				 const struct dpaa2_fd *fd, bool in_napi)
+void dpaa2_eth_free_tx_fd(struct dpaa2_eth_priv *priv,
+			  struct dpaa2_eth_channel *ch,
+			  struct dpaa2_eth_fq *fq,
+			  const struct dpaa2_fd *fd, bool in_napi)
 {
 	struct device *dev = priv->net_dev->dev.parent;
 	dma_addr_t fd_addr, sg_addr;
@@ -1153,6 +1185,10 @@ static void dpaa2_eth_free_tx_fd(struct dpaa2_eth_priv *priv,
 
 			if (!swa->tso.is_last_fd)
 				should_free_skb = 0;
+		} else if (swa->type == DPAA2_ETH_SWA_XSK) {
+			/* Unmap the SGT Buffer */
+			dma_unmap_single(dev, fd_addr, swa->xsk.sgt_size,
+					 DMA_BIDIRECTIONAL);
 		} else {
 			skb = swa->single.skb;
 
@@ -1170,6 +1206,12 @@ static void dpaa2_eth_free_tx_fd(struct dpaa2_eth_priv *priv,
 		return;
 	}
 
+	if (swa->type == DPAA2_ETH_SWA_XSK) {
+		ch->xsk_tx_pkts_sent++;
+		dpaa2_eth_sgt_recycle(priv, buffer_start);
+		return;
+	}
+
 	if (swa->type != DPAA2_ETH_SWA_XDP && in_napi) {
 		fq->dq_frames++;
 		fq->dq_bytes += fd_len;
@@ -1344,7 +1386,7 @@ err_alloc_tso_hdr:
 err_sgt_get:
 	/* Free all the other FDs that were already fully created */
 	for (i = 0; i < index; i++)
-		dpaa2_eth_free_tx_fd(priv, NULL, &fd_start[i], false);
+		dpaa2_eth_free_tx_fd(priv, NULL, NULL, &fd_start[i], false);
 
 	return err;
 }
@@ -1460,7 +1502,7 @@ static netdev_tx_t __dpaa2_eth_tx(struct sk_buff *skb,
 	if (unlikely(err < 0)) {
 		percpu_stats->tx_errors++;
 		/* Clean up everything, including freeing the skb */
-		dpaa2_eth_free_tx_fd(priv, fq, fd, false);
+		dpaa2_eth_free_tx_fd(priv, NULL, fq, fd, false);
 		netdev_tx_completed_queue(nq, 1, fd_len);
 	} else {
 		percpu_stats->tx_packets += total_enqueued;
@@ -1553,7 +1595,7 @@ static void dpaa2_eth_tx_conf(struct dpaa2_eth_priv *priv,
 
 	/* Check frame errors in the FD field */
 	fd_errors = dpaa2_fd_get_ctrl(fd) & DPAA2_FD_TX_ERR_MASK;
-	dpaa2_eth_free_tx_fd(priv, fq, fd, true);
+	dpaa2_eth_free_tx_fd(priv, ch, fq, fd, true);
 
 	if (likely(!fd_errors))
 		return;
@@ -1631,44 +1673,76 @@ static int dpaa2_eth_set_tx_csum(struct dpaa2_eth_priv *priv, bool enable)
  * to the specified buffer pool
  */
 static int dpaa2_eth_add_bufs(struct dpaa2_eth_priv *priv,
-			      struct dpaa2_eth_channel *ch, u16 bpid)
+			      struct dpaa2_eth_channel *ch)
 {
+	struct xdp_buff *xdp_buffs[DPAA2_ETH_BUFS_PER_CMD];
 	struct device *dev = priv->net_dev->dev.parent;
 	u64 buf_array[DPAA2_ETH_BUFS_PER_CMD];
+	struct dpaa2_eth_swa *swa;
 	struct page *page;
 	dma_addr_t addr;
 	int retries = 0;
-	int i, err;
-
-	for (i = 0; i < DPAA2_ETH_BUFS_PER_CMD; i++) {
-		/* Allocate buffer visible to WRIOP + skb shared info +
-		 * alignment padding
-		 */
-		/* allocate one page for each Rx buffer. WRIOP sees
-		 * the entire page except for a tailroom reserved for
-		 * skb shared info
+	int i = 0, err;
+	u32 batch;
+
+	/* Allocate buffers visible to WRIOP */
+	if (!ch->xsk_zc) {
+		for (i = 0; i < DPAA2_ETH_BUFS_PER_CMD; i++) {
+			/* Also allocate skb shared info and alignment padding.
+			 * There is one page for each Rx buffer. WRIOP sees
+			 * the entire page except for a tailroom reserved for
+			 * skb shared info
+			 */
+			page = dev_alloc_pages(0);
+			if (!page)
+				goto err_alloc;
+
+			addr = dma_map_page(dev, page, 0, priv->rx_buf_size,
+					    DMA_BIDIRECTIONAL);
+			if (unlikely(dma_mapping_error(dev, addr)))
+				goto err_map;
+
+			buf_array[i] = addr;
+
+			/* tracing point */
+			trace_dpaa2_eth_buf_seed(priv->net_dev,
+						 page_address(page),
+						 DPAA2_ETH_RX_BUF_RAW_SIZE,
+						 addr, priv->rx_buf_size,
+						 ch->bp->bpid);
+		}
+	} else if (xsk_buff_can_alloc(ch->xsk_pool, DPAA2_ETH_BUFS_PER_CMD)) {
+		/* Allocate XSK buffers for AF_XDP fast path in batches
+		 * of DPAA2_ETH_BUFS_PER_CMD. Bail out if the UMEM cannot
+		 * provide enough buffers at the moment
 		 */
-		page = dev_alloc_pages(0);
-		if (!page)
+		batch = xsk_buff_alloc_batch(ch->xsk_pool, xdp_buffs,
+					     DPAA2_ETH_BUFS_PER_CMD);
+		if (!batch)
 			goto err_alloc;
 
-		addr = dma_map_page(dev, page, 0, priv->rx_buf_size,
-				    DMA_BIDIRECTIONAL);
-		if (unlikely(dma_mapping_error(dev, addr)))
-			goto err_map;
+		for (i = 0; i < batch; i++) {
+			swa = (struct dpaa2_eth_swa *)(xdp_buffs[i]->data_hard_start +
+						       DPAA2_ETH_RX_HWA_SIZE);
+			swa->xsk.xdp_buff = xdp_buffs[i];
+
+			addr = xsk_buff_xdp_get_frame_dma(xdp_buffs[i]);
+			if (unlikely(dma_mapping_error(dev, addr)))
+				goto err_map;
 
-		buf_array[i] = addr;
+			buf_array[i] = addr;
 
-		/* tracing point */
-		trace_dpaa2_eth_buf_seed(priv->net_dev, page_address(page),
-					 DPAA2_ETH_RX_BUF_RAW_SIZE,
-					 addr, priv->rx_buf_size,
-					 bpid);
+			trace_dpaa2_xsk_buf_seed(priv->net_dev,
+						 xdp_buffs[i]->data_hard_start,
+						 DPAA2_ETH_RX_BUF_RAW_SIZE,
+						 addr, priv->rx_buf_size,
+						 ch->bp->bpid);
+		}
 	}
 
 release_bufs:
 	/* In case the portal is busy, retry until successful */
-	while ((err = dpaa2_io_service_release(ch->dpio, bpid,
+	while ((err = dpaa2_io_service_release(ch->dpio, ch->bp->bpid,
 					       buf_array, i)) == -EBUSY) {
 		if (retries++ >= DPAA2_ETH_SWP_BUSY_RETRIES)
 			break;
@@ -1679,14 +1753,19 @@ release_bufs:
 	 * not much else we can do about it
 	 */
 	if (err) {
-		dpaa2_eth_free_bufs(priv, buf_array, i);
+		dpaa2_eth_free_bufs(priv, buf_array, i, ch->xsk_zc);
 		return 0;
 	}
 
 	return i;
 
 err_map:
-	__free_pages(page, 0);
+	if (!ch->xsk_zc) {
+		__free_pages(page, 0);
+	} else {
+		for (; i < batch; i++)
+			xsk_buff_free(xdp_buffs[i]);
+	}
 err_alloc:
 	/* If we managed to allocate at least some buffers,
 	 * release them to hardware
@@ -1697,39 +1776,64 @@ err_alloc:
 	return 0;
 }
 
-static int dpaa2_eth_seed_pool(struct dpaa2_eth_priv *priv, u16 bpid)
+static int dpaa2_eth_seed_pool(struct dpaa2_eth_priv *priv,
+			       struct dpaa2_eth_channel *ch)
 {
-	int i, j;
+	int i;
 	int new_count;
 
-	for (j = 0; j < priv->num_channels; j++) {
-		for (i = 0; i < DPAA2_ETH_NUM_BUFS;
-		     i += DPAA2_ETH_BUFS_PER_CMD) {
-			new_count = dpaa2_eth_add_bufs(priv, priv->channel[j], bpid);
-			priv->channel[j]->buf_count += new_count;
+	for (i = 0; i < DPAA2_ETH_NUM_BUFS; i += DPAA2_ETH_BUFS_PER_CMD) {
+		new_count = dpaa2_eth_add_bufs(priv, ch);
+		ch->buf_count += new_count;
 
-			if (new_count < DPAA2_ETH_BUFS_PER_CMD) {
-				return -ENOMEM;
-			}
-		}
+		if (new_count < DPAA2_ETH_BUFS_PER_CMD)
+			return -ENOMEM;
 	}
 
 	return 0;
 }
 
+static void dpaa2_eth_seed_pools(struct dpaa2_eth_priv *priv)
+{
+	struct net_device *net_dev = priv->net_dev;
+	struct dpaa2_eth_channel *channel;
+	int i, err = 0;
+
+	for (i = 0; i < priv->num_channels; i++) {
+		channel = priv->channel[i];
+
+		err = dpaa2_eth_seed_pool(priv, channel);
+
+		/* Not much to do; the buffer pool, though not filled up,
+		 * may still contain some buffers which would enable us
+		 * to limp on.
+		 */
+		if (err)
+			netdev_err(net_dev, "Buffer seeding failed for DPBP %d (bpid=%d)\n",
+				   channel->bp->dev->obj_desc.id,
+				   channel->bp->bpid);
+	}
+}
+
 /*
- * Drain the specified number of buffers from the DPNI's private buffer pool.
+ * Drain the specified number of buffers from one of the DPNI's private buffer
+ * pools.
  * @count must not exceeed DPAA2_ETH_BUFS_PER_CMD
  */
-static void dpaa2_eth_drain_bufs(struct dpaa2_eth_priv *priv, int count)
+static void dpaa2_eth_drain_bufs(struct dpaa2_eth_priv *priv, int bpid,
+				 int count)
 {
 	u64 buf_array[DPAA2_ETH_BUFS_PER_CMD];
+	bool xsk_zc = false;
 	int retries = 0;
-	int ret;
+	int i, ret;
+
+	for (i = 0; i < priv->num_channels; i++)
+		if (priv->channel[i]->bp->bpid == bpid)
+			xsk_zc = priv->channel[i]->xsk_zc;
 
 	do {
-		ret = dpaa2_io_service_acquire(NULL, priv->bpid,
-					       buf_array, count);
+		ret = dpaa2_io_service_acquire(NULL, bpid, buf_array, count);
 		if (ret < 0) {
 			if (ret == -EBUSY &&
 			    retries++ < DPAA2_ETH_SWP_BUSY_RETRIES)
@@ -1737,28 +1841,40 @@ static void dpaa2_eth_drain_bufs(struct dpaa2_eth_priv *priv, int count)
 			netdev_err(priv->net_dev, "dpaa2_io_service_acquire() failed\n");
 			return;
 		}
-		dpaa2_eth_free_bufs(priv, buf_array, ret);
+		dpaa2_eth_free_bufs(priv, buf_array, ret, xsk_zc);
 		retries = 0;
 	} while (ret);
 }
 
-static void dpaa2_eth_drain_pool(struct dpaa2_eth_priv *priv)
+static void dpaa2_eth_drain_pool(struct dpaa2_eth_priv *priv, int bpid)
 {
 	int i;
 
-	dpaa2_eth_drain_bufs(priv, DPAA2_ETH_BUFS_PER_CMD);
-	dpaa2_eth_drain_bufs(priv, 1);
+	/* Drain the buffer pool */
+	dpaa2_eth_drain_bufs(priv, bpid, DPAA2_ETH_BUFS_PER_CMD);
+	dpaa2_eth_drain_bufs(priv, bpid, 1);
 
+	/* Setup to zero the buffer count of all channels which were
+	 * using this buffer pool.
+	 */
 	for (i = 0; i < priv->num_channels; i++)
-		priv->channel[i]->buf_count = 0;
+		if (priv->channel[i]->bp->bpid == bpid)
+			priv->channel[i]->buf_count = 0;
+}
+
+static void dpaa2_eth_drain_pools(struct dpaa2_eth_priv *priv)
+{
+	int i;
+
+	for (i = 0; i < priv->num_bps; i++)
+		dpaa2_eth_drain_pool(priv, priv->bp[i]->bpid);
 }
 
 /* Function is called from softirq context only, so we don't need to guard
  * the access to percpu count
  */
 static int dpaa2_eth_refill_pool(struct dpaa2_eth_priv *priv,
-				 struct dpaa2_eth_channel *ch,
-				 u16 bpid)
+				 struct dpaa2_eth_channel *ch)
 {
 	int new_count;
 
@@ -1766,7 +1882,7 @@ static int dpaa2_eth_refill_pool(struct dpaa2_eth_priv *priv,
 		return 0;
 
 	do {
-		new_count = dpaa2_eth_add_bufs(priv, ch, bpid);
+		new_count = dpaa2_eth_add_bufs(priv, ch);
 		if (unlikely(!new_count)) {
 			/* Out of memory; abort for now, we'll try later on */
 			break;
@@ -1830,6 +1946,7 @@ static int dpaa2_eth_poll(struct napi_struct *napi, int budget)
 	struct dpaa2_eth_fq *fq, *txc_fq = NULL;
 	struct netdev_queue *nq;
 	int store_cleaned, work_done;
+	bool work_done_zc = false;
 	struct list_head rx_list;
 	int retries = 0;
 	u16 flowid;
@@ -1842,13 +1959,22 @@ static int dpaa2_eth_poll(struct napi_struct *napi, int budget)
 	INIT_LIST_HEAD(&rx_list);
 	ch->rx_list = &rx_list;
 
+	if (ch->xsk_zc) {
+		work_done_zc = dpaa2_xsk_tx(priv, ch);
+		/* If we reached the XSK Tx per NAPI threshold, we're done */
+		if (work_done_zc) {
+			work_done = budget;
+			goto out;
+		}
+	}
+
 	do {
 		err = dpaa2_eth_pull_channel(ch);
 		if (unlikely(err))
 			break;
 
 		/* Refill pool if appropriate */
-		dpaa2_eth_refill_pool(priv, ch, priv->bpid);
+		dpaa2_eth_refill_pool(priv, ch);
 
 		store_cleaned = dpaa2_eth_consume_frames(ch, &fq);
 		if (store_cleaned <= 0)
@@ -1894,6 +2020,11 @@ static int dpaa2_eth_poll(struct napi_struct *napi, int budget)
 out:
 	netif_receive_skb_list(ch->rx_list);
 
+	if (ch->xsk_tx_pkts_sent) {
+		xsk_tx_completed(ch->xsk_pool, ch->xsk_tx_pkts_sent);
+		ch->xsk_tx_pkts_sent = 0;
+	}
+
 	if (txc_fq && txc_fq->dq_frames) {
 		nq = netdev_get_tx_queue(priv->net_dev, txc_fq->flowid);
 		netdev_tx_completed_queue(nq, txc_fq->dq_frames,
@@ -2047,15 +2178,7 @@ static int dpaa2_eth_open(struct net_device *net_dev)
 	struct dpaa2_eth_priv *priv = netdev_priv(net_dev);
 	int err;
 
-	err = dpaa2_eth_seed_pool(priv, priv->bpid);
-	if (err) {
-		/* Not much to do; the buffer pool, though not filled up,
-		 * may still contain some buffers which would enable us
-		 * to limp on.
-		 */
-		netdev_err(net_dev, "Buffer seeding failed for DPBP %d (bpid=%d)\n",
-			   priv->dpbp_dev->obj_desc.id, priv->bpid);
-	}
+	dpaa2_eth_seed_pools(priv);
 
 	if (!dpaa2_eth_is_type_phy(priv)) {
 		/* We'll only start the txqs when the link is actually ready;
@@ -2088,7 +2211,7 @@ static int dpaa2_eth_open(struct net_device *net_dev)
 
 enable_err:
 	dpaa2_eth_disable_ch_napi(priv);
-	dpaa2_eth_drain_pool(priv);
+	dpaa2_eth_drain_pools(priv);
 	return err;
 }
 
@@ -2193,7 +2316,7 @@ static int dpaa2_eth_stop(struct net_device *net_dev)
 	dpaa2_eth_disable_ch_napi(priv);
 
 	/* Empty the buffer pool */
-	dpaa2_eth_drain_pool(priv);
+	dpaa2_eth_drain_pools(priv);
 
 	/* Empty the Scatter-Gather Buffer cache */
 	dpaa2_eth_sgt_cache_drain(priv);
@@ -2602,7 +2725,7 @@ static int dpaa2_eth_setup_xdp(struct net_device *dev, struct bpf_prog *prog)
 	need_update = (!!priv->xdp_prog != !!prog);
 
 	if (up)
-		dpaa2_eth_stop(dev);
+		dev_close(dev);
 
 	/* While in xdp mode, enforce a maximum Rx frame size based on MTU.
 	 * Also, when switching between xdp/non-xdp modes we need to reconfigure
@@ -2630,7 +2753,7 @@ static int dpaa2_eth_setup_xdp(struct net_device *dev, struct bpf_prog *prog)
 	}
 
 	if (up) {
-		err = dpaa2_eth_open(dev);
+		err = dev_open(dev, NULL);
 		if (err)
 			return err;
 	}
@@ -2641,7 +2764,7 @@ out_err:
 	if (prog)
 		bpf_prog_sub(prog, priv->num_channels);
 	if (up)
-		dpaa2_eth_open(dev);
+		dev_open(dev, NULL);
 
 	return err;
 }
@@ -2651,6 +2774,8 @@ static int dpaa2_eth_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 	switch (xdp->command) {
 	case XDP_SETUP_PROG:
 		return dpaa2_eth_setup_xdp(dev, xdp->prog);
+	case XDP_SETUP_XSK_POOL:
+		return dpaa2_xsk_setup_pool(dev, xdp->xsk.pool, xdp->xsk.queue_id);
 	default:
 		return -EINVAL;
 	}
@@ -2881,6 +3006,7 @@ static const struct net_device_ops dpaa2_eth_ops = {
 	.ndo_change_mtu = dpaa2_eth_change_mtu,
 	.ndo_bpf = dpaa2_eth_xdp,
 	.ndo_xdp_xmit = dpaa2_eth_xdp_xmit,
+	.ndo_xsk_wakeup = dpaa2_xsk_wakeup,
 	.ndo_setup_tc = dpaa2_eth_setup_tc,
 	.ndo_vlan_rx_add_vid = dpaa2_eth_rx_add_vid,
 	.ndo_vlan_rx_kill_vid = dpaa2_eth_rx_kill_vid
@@ -2895,7 +3021,11 @@ static void dpaa2_eth_cdan_cb(struct dpaa2_io_notification_ctx *ctx)
 	/* Update NAPI statistics */
 	ch->stats.cdan++;
 
-	napi_schedule(&ch->napi);
+	/* NAPI can also be scheduled from the AF_XDP Tx path. Mark a missed
+	 * so that it can be rescheduled again.
+	 */
+	if (!napi_if_scheduled_mark_missed(&ch->napi))
+		napi_schedule(&ch->napi);
 }
 
 /* Allocate and configure a DPCON object */
@@ -3204,13 +3334,14 @@ static void dpaa2_eth_setup_fqs(struct dpaa2_eth_priv *priv)
 	dpaa2_eth_set_fq_affinity(priv);
 }
 
-/* Allocate and configure one buffer pool for each interface */
-static int dpaa2_eth_setup_dpbp(struct dpaa2_eth_priv *priv)
+/* Allocate and configure a buffer pool */
+struct dpaa2_eth_bp *dpaa2_eth_allocate_dpbp(struct dpaa2_eth_priv *priv)
 {
-	int err;
-	struct fsl_mc_device *dpbp_dev;
 	struct device *dev = priv->net_dev->dev.parent;
+	struct fsl_mc_device *dpbp_dev;
 	struct dpbp_attr dpbp_attrs;
+	struct dpaa2_eth_bp *bp;
+	int err;
 
 	err = fsl_mc_object_allocate(to_fsl_mc_device(dev), FSL_MC_POOL_DPBP,
 				     &dpbp_dev);
@@ -3219,12 +3350,16 @@ static int dpaa2_eth_setup_dpbp(struct dpaa2_eth_priv *priv)
 			err = -EPROBE_DEFER;
 		else
 			dev_err(dev, "DPBP device allocation failed\n");
-		return err;
+		return ERR_PTR(err);
 	}
 
-	priv->dpbp_dev = dpbp_dev;
+	bp = kzalloc(sizeof(*bp), GFP_KERNEL);
+	if (!bp) {
+		err = -ENOMEM;
+		goto err_alloc;
+	}
 
-	err = dpbp_open(priv->mc_io, 0, priv->dpbp_dev->obj_desc.id,
+	err = dpbp_open(priv->mc_io, 0, dpbp_dev->obj_desc.id,
 			&dpbp_dev->mc_handle);
 	if (err) {
 		dev_err(dev, "dpbp_open() failed\n");
@@ -3249,9 +3384,11 @@ static int dpaa2_eth_setup_dpbp(struct dpaa2_eth_priv *priv)
 		dev_err(dev, "dpbp_get_attributes() failed\n");
 		goto err_get_attr;
 	}
-	priv->bpid = dpbp_attrs.bpid;
 
-	return 0;
+	bp->dev = dpbp_dev;
+	bp->bpid = dpbp_attrs.bpid;
+
+	return bp;
 
 err_get_attr:
 	dpbp_disable(priv->mc_io, 0, dpbp_dev->mc_handle);
@@ -3259,17 +3396,58 @@ err_enable:
 err_reset:
 	dpbp_close(priv->mc_io, 0, dpbp_dev->mc_handle);
 err_open:
+	kfree(bp);
+err_alloc:
 	fsl_mc_object_free(dpbp_dev);
 
-	return err;
+	return ERR_PTR(err);
 }
 
-static void dpaa2_eth_free_dpbp(struct dpaa2_eth_priv *priv)
+static int dpaa2_eth_setup_default_dpbp(struct dpaa2_eth_priv *priv)
 {
-	dpaa2_eth_drain_pool(priv);
-	dpbp_disable(priv->mc_io, 0, priv->dpbp_dev->mc_handle);
-	dpbp_close(priv->mc_io, 0, priv->dpbp_dev->mc_handle);
-	fsl_mc_object_free(priv->dpbp_dev);
+	struct dpaa2_eth_bp *bp;
+	int i;
+
+	bp = dpaa2_eth_allocate_dpbp(priv);
+	if (IS_ERR(bp))
+		return PTR_ERR(bp);
+
+	priv->bp[DPAA2_ETH_DEFAULT_BP_IDX] = bp;
+	priv->num_bps++;
+
+	for (i = 0; i < priv->num_channels; i++)
+		priv->channel[i]->bp = bp;
+
+	return 0;
+}
+
+void dpaa2_eth_free_dpbp(struct dpaa2_eth_priv *priv, struct dpaa2_eth_bp *bp)
+{
+	int idx_bp;
+
+	/* Find the index at which this BP is stored */
+	for (idx_bp = 0; idx_bp < priv->num_bps; idx_bp++)
+		if (priv->bp[idx_bp] == bp)
+			break;
+
+	/* Drain the pool and disable the associated MC object */
+	dpaa2_eth_drain_pool(priv, bp->bpid);
+	dpbp_disable(priv->mc_io, 0, bp->dev->mc_handle);
+	dpbp_close(priv->mc_io, 0, bp->dev->mc_handle);
+	fsl_mc_object_free(bp->dev);
+	kfree(bp);
+
+	/* Move the last in use DPBP over in this position */
+	priv->bp[idx_bp] = priv->bp[priv->num_bps - 1];
+	priv->num_bps--;
+}
+
+static void dpaa2_eth_free_dpbps(struct dpaa2_eth_priv *priv)
+{
+	int i;
+
+	for (i = 0; i < priv->num_bps; i++)
+		dpaa2_eth_free_dpbp(priv, priv->bp[i]);
 }
 
 static int dpaa2_eth_set_buffer_layout(struct dpaa2_eth_priv *priv)
@@ -4154,15 +4332,16 @@ out:
  */
 static int dpaa2_eth_bind_dpni(struct dpaa2_eth_priv *priv)
 {
+	struct dpaa2_eth_bp *bp = priv->bp[DPAA2_ETH_DEFAULT_BP_IDX];
 	struct net_device *net_dev = priv->net_dev;
+	struct dpni_pools_cfg pools_params = { 0 };
 	struct device *dev = net_dev->dev.parent;
-	struct dpni_pools_cfg pools_params;
 	struct dpni_error_cfg err_cfg;
 	int err = 0;
 	int i;
 
 	pools_params.num_dpbp = 1;
-	pools_params.pools[0].dpbp_id = priv->dpbp_dev->obj_desc.id;
+	pools_params.pools[0].dpbp_id = bp->dev->obj_desc.id;
 	pools_params.pools[0].backup_pool = 0;
 	pools_params.pools[0].buffer_size = priv->rx_buf_size;
 	err = dpni_set_pools(priv->mc_io, 0, priv->mc_token, &pools_params);
@@ -4641,7 +4820,7 @@ static int dpaa2_eth_probe(struct fsl_mc_device *dpni_dev)
 
 	dpaa2_eth_setup_fqs(priv);
 
-	err = dpaa2_eth_setup_dpbp(priv);
+	err = dpaa2_eth_setup_default_dpbp(priv);
 	if (err)
 		goto err_dpbp_setup;
 
@@ -4777,7 +4956,7 @@ err_alloc_percpu_extras:
 err_alloc_percpu_stats:
 	dpaa2_eth_del_ch_napi(priv);
 err_bind:
-	dpaa2_eth_free_dpbp(priv);
+	dpaa2_eth_free_dpbps(priv);
 err_dpbp_setup:
 	dpaa2_eth_free_dpio(priv);
 err_dpio_setup:
@@ -4830,7 +5009,7 @@ static int dpaa2_eth_remove(struct fsl_mc_device *ls_dev)
 	free_percpu(priv->percpu_extras);
 
 	dpaa2_eth_del_ch_napi(priv);
-	dpaa2_eth_free_dpbp(priv);
+	dpaa2_eth_free_dpbps(priv);
 	dpaa2_eth_free_dpio(priv);
 	dpaa2_eth_free_dpni(priv);
 	if (priv->onestep_reg_base)
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
index 447718483ef4..5d0fc432e5b2 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) */
 /* Copyright 2014-2016 Freescale Semiconductor Inc.
- * Copyright 2016-2020 NXP
+ * Copyright 2016-2022 NXP
  */
 
 #ifndef __DPAA2_ETH_H
@@ -53,6 +53,12 @@
  */
 #define DPAA2_ETH_TXCONF_PER_NAPI	256
 
+/* Maximum number of Tx frames to be processed in a single NAPI
+ * call when AF_XDP is running. Bind it to DPAA2_ETH_TXCONF_PER_NAPI
+ * to maximize the throughput.
+ */
+#define DPAA2_ETH_TX_ZC_PER_NAPI	DPAA2_ETH_TXCONF_PER_NAPI
+
 /* Buffer qouta per channel. We want to keep in check number of ingress frames
  * in flight: for small sized frames, congestion group taildrop may kick in
  * first; for large sizes, Rx FQ taildrop threshold will ensure only a
@@ -109,6 +115,14 @@
 #define DPAA2_ETH_RX_BUF_ALIGN_REV1	256
 #define DPAA2_ETH_RX_BUF_ALIGN		64
 
+/* The firmware allows assigning multiple buffer pools to a single DPNI -
+ * maximum 8 DPBP objects. By default, only the first DPBP (idx 0) is used for
+ * all queues. Thus, when enabling AF_XDP we must accommodate up to 9 DPBPs
+ * object: the default and 8 other distinct buffer pools, one for each queue.
+ */
+#define DPAA2_ETH_DEFAULT_BP_IDX	0
+#define DPAA2_ETH_MAX_BPS		9
+
 /* We are accommodating a skb backpointer and some S/G info
  * in the frame's software annotation. The hardware
  * options are either 0 or 64, so we choose the latter.
@@ -122,6 +136,7 @@ enum dpaa2_eth_swa_type {
 	DPAA2_ETH_SWA_SINGLE,
 	DPAA2_ETH_SWA_SG,
 	DPAA2_ETH_SWA_XDP,
+	DPAA2_ETH_SWA_XSK,
 	DPAA2_ETH_SWA_SW_TSO,
 };
 
@@ -144,6 +159,10 @@ struct dpaa2_eth_swa {
 			struct xdp_frame *xdpf;
 		} xdp;
 		struct {
+			struct xdp_buff *xdp_buff;
+			int sgt_size;
+		} xsk;
+		struct {
 			struct sk_buff *skb;
 			int num_sg;
 			int sgt_size;
@@ -421,12 +440,19 @@ enum dpaa2_eth_fq_type {
 };
 
 struct dpaa2_eth_priv;
+struct dpaa2_eth_channel;
+struct dpaa2_eth_fq;
 
 struct dpaa2_eth_xdp_fds {
 	struct dpaa2_fd fds[DEV_MAP_BULK_SIZE];
 	ssize_t num;
 };
 
+typedef void dpaa2_eth_consume_cb_t(struct dpaa2_eth_priv *priv,
+				    struct dpaa2_eth_channel *ch,
+				    const struct dpaa2_fd *fd,
+				    struct dpaa2_eth_fq *fq);
+
 struct dpaa2_eth_fq {
 	u32 fqid;
 	u32 tx_qdbin;
@@ -439,10 +465,7 @@ struct dpaa2_eth_fq {
 	struct dpaa2_eth_channel *channel;
 	enum dpaa2_eth_fq_type type;
 
-	void (*consume)(struct dpaa2_eth_priv *priv,
-			struct dpaa2_eth_channel *ch,
-			const struct dpaa2_fd *fd,
-			struct dpaa2_eth_fq *fq);
+	dpaa2_eth_consume_cb_t *consume;
 	struct dpaa2_eth_fq_stats stats;
 
 	struct dpaa2_eth_xdp_fds xdp_redirect_fds;
@@ -454,6 +477,11 @@ struct dpaa2_eth_ch_xdp {
 	unsigned int res;
 };
 
+struct dpaa2_eth_bp {
+	struct fsl_mc_device *dev;
+	int bpid;
+};
+
 struct dpaa2_eth_channel {
 	struct dpaa2_io_notification_ctx nctx;
 	struct fsl_mc_device *dpcon;
@@ -472,6 +500,11 @@ struct dpaa2_eth_channel {
 	/* Buffers to be recycled back in the buffer pool */
 	u64 recycled_bufs[DPAA2_ETH_BUFS_PER_CMD];
 	int recycled_bufs_cnt;
+
+	bool xsk_zc;
+	int xsk_tx_pkts_sent;
+	struct xsk_buff_pool *xsk_pool;
+	struct dpaa2_eth_bp *bp;
 };
 
 struct dpaa2_eth_dist_fields {
@@ -506,7 +539,7 @@ struct dpaa2_eth_trap_data {
 
 #define DPAA2_ETH_DEFAULT_COPYBREAK	512
 
-#define DPAA2_ETH_ENQUEUE_MAX_FDS	200
+#define DPAA2_ETH_ENQUEUE_MAX_FDS	256
 struct dpaa2_eth_fds {
 	struct dpaa2_fd array[DPAA2_ETH_ENQUEUE_MAX_FDS];
 };
@@ -535,14 +568,16 @@ struct dpaa2_eth_priv {
 	u8 ptp_correction_off;
 	void (*dpaa2_set_onestep_params_cb)(struct dpaa2_eth_priv *priv,
 					    u32 offset, u8 udp);
-	struct fsl_mc_device *dpbp_dev;
 	u16 rx_buf_size;
-	u16 bpid;
 	struct iommu_domain *iommu_domain;
 
 	enum hwtstamp_tx_types tx_tstamp_type;	/* Tx timestamping type */
 	bool rx_tstamp;				/* Rx timestamping enabled */
 
+	/* Buffer pool management */
+	struct dpaa2_eth_bp *bp[DPAA2_ETH_MAX_BPS];
+	int num_bps;
+
 	u16 tx_qdid;
 	struct fsl_mc_io *mc_io;
 	/* Cores which have an affine DPIO/DPCON.
@@ -771,4 +806,54 @@ void dpaa2_eth_dl_traps_unregister(struct dpaa2_eth_priv *priv);
 
 struct dpaa2_eth_trap_item *dpaa2_eth_dl_get_trap(struct dpaa2_eth_priv *priv,
 						  struct dpaa2_fapr *fapr);
+
+struct dpaa2_eth_bp *dpaa2_eth_allocate_dpbp(struct dpaa2_eth_priv *priv);
+void dpaa2_eth_free_dpbp(struct dpaa2_eth_priv *priv, struct dpaa2_eth_bp *bp);
+
+struct sk_buff *dpaa2_eth_alloc_skb(struct dpaa2_eth_priv *priv,
+				    struct dpaa2_eth_channel *ch,
+				    const struct dpaa2_fd *fd, u32 fd_length,
+				    void *fd_vaddr);
+
+void dpaa2_eth_receive_skb(struct dpaa2_eth_priv *priv,
+			   struct dpaa2_eth_channel *ch,
+			   const struct dpaa2_fd *fd, void *vaddr,
+			   struct dpaa2_eth_fq *fq,
+			   struct rtnl_link_stats64 *percpu_stats,
+			   struct sk_buff *skb);
+
+void dpaa2_eth_rx(struct dpaa2_eth_priv *priv,
+		  struct dpaa2_eth_channel *ch,
+		  const struct dpaa2_fd *fd,
+		  struct dpaa2_eth_fq *fq);
+
+struct dpaa2_eth_bp *dpaa2_eth_allocate_dpbp(struct dpaa2_eth_priv *priv);
+void dpaa2_eth_free_dpbp(struct dpaa2_eth_priv *priv,
+			 struct dpaa2_eth_bp *bp);
+
+void *dpaa2_iova_to_virt(struct iommu_domain *domain, dma_addr_t iova_addr);
+void dpaa2_eth_recycle_buf(struct dpaa2_eth_priv *priv,
+			   struct dpaa2_eth_channel *ch,
+			   dma_addr_t addr);
+
+void dpaa2_eth_xdp_enqueue(struct dpaa2_eth_priv *priv,
+			   struct dpaa2_eth_channel *ch,
+			   struct dpaa2_fd *fd,
+			   void *buf_start, u16 queue_id);
+
+int dpaa2_xsk_wakeup(struct net_device *dev, u32 qid, u32 flags);
+int dpaa2_xsk_setup_pool(struct net_device *dev, struct xsk_buff_pool *pool, u16 qid);
+
+void dpaa2_eth_free_tx_fd(struct dpaa2_eth_priv *priv,
+			  struct dpaa2_eth_channel *ch,
+			  struct dpaa2_eth_fq *fq,
+			  const struct dpaa2_fd *fd, bool in_napi);
+bool dpaa2_xsk_tx(struct dpaa2_eth_priv *priv,
+		  struct dpaa2_eth_channel *ch);
+
+/* SGT (Scatter-Gather Table) cache management */
+void *dpaa2_eth_sgt_get(struct dpaa2_eth_priv *priv);
+
+void dpaa2_eth_sgt_recycle(struct dpaa2_eth_priv *priv, void *sgt_buf);
+
 #endif	/* __DPAA2_H */
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c
index eea7d7a07c00..32a38a03db57 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c
@@ -1,7 +1,6 @@
 // SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause)
 /* Copyright 2014-2016 Freescale Semiconductor Inc.
- * Copyright 2016 NXP
- * Copyright 2020 NXP
+ * Copyright 2016-2022 NXP
  */
 
 #include <linux/net_tstamp.h>
@@ -227,17 +226,8 @@ static void dpaa2_eth_get_ethtool_stats(struct net_device *net_dev,
 					struct ethtool_stats *stats,
 					u64 *data)
 {
-	int i = 0;
-	int j, k, err;
-	int num_cnt;
-	union dpni_statistics dpni_stats;
-	u32 fcnt, bcnt;
-	u32 fcnt_rx_total = 0, fcnt_tx_total = 0;
-	u32 bcnt_rx_total = 0, bcnt_tx_total = 0;
-	u32 buf_cnt;
 	struct dpaa2_eth_priv *priv = netdev_priv(net_dev);
-	struct dpaa2_eth_drv_stats *extras;
-	struct dpaa2_eth_ch_stats *ch_stats;
+	union dpni_statistics dpni_stats;
 	int dpni_stats_page_size[DPNI_STATISTICS_CNT] = {
 		sizeof(dpni_stats.page_0),
 		sizeof(dpni_stats.page_1),
@@ -247,6 +237,13 @@ static void dpaa2_eth_get_ethtool_stats(struct net_device *net_dev,
 		sizeof(dpni_stats.page_5),
 		sizeof(dpni_stats.page_6),
 	};
+	u32 fcnt_rx_total = 0, fcnt_tx_total = 0;
+	u32 bcnt_rx_total = 0, bcnt_tx_total = 0;
+	struct dpaa2_eth_ch_stats *ch_stats;
+	struct dpaa2_eth_drv_stats *extras;
+	u32 buf_cnt, buf_cnt_total = 0;
+	int j, k, err, num_cnt, i = 0;
+	u32 fcnt, bcnt;
 
 	memset(data, 0,
 	       sizeof(u64) * (DPAA2_ETH_NUM_STATS + DPAA2_ETH_NUM_EXTRA_STATS));
@@ -308,12 +305,15 @@ static void dpaa2_eth_get_ethtool_stats(struct net_device *net_dev,
 	*(data + i++) = fcnt_tx_total;
 	*(data + i++) = bcnt_tx_total;
 
-	err = dpaa2_io_query_bp_count(NULL, priv->bpid, &buf_cnt);
-	if (err) {
-		netdev_warn(net_dev, "Buffer count query error %d\n", err);
-		return;
+	for (j = 0; j < priv->num_bps; j++) {
+		err = dpaa2_io_query_bp_count(NULL, priv->bp[j]->bpid, &buf_cnt);
+		if (err) {
+			netdev_warn(net_dev, "Buffer count query error %d\n", err);
+			return;
+		}
+		buf_cnt_total += buf_cnt;
 	}
-	*(data + i++) = buf_cnt;
+	*(data + i++) = buf_cnt_total;
 
 	if (dpaa2_eth_has_mac(priv))
 		dpaa2_mac_get_ethtool_stats(priv->mac, data + i);
@@ -876,6 +876,29 @@ restore_rx_usecs:
 	return err;
 }
 
+static void dpaa2_eth_get_channels(struct net_device *net_dev,
+				   struct ethtool_channels *channels)
+{
+	struct dpaa2_eth_priv *priv = netdev_priv(net_dev);
+	int queue_count = dpaa2_eth_queue_count(priv);
+
+	channels->max_rx = queue_count;
+	channels->max_tx = queue_count;
+	channels->rx_count = queue_count;
+	channels->tx_count = queue_count;
+
+	/* Tx confirmation and Rx error */
+	channels->max_other = queue_count + 1;
+	channels->max_combined = channels->max_rx +
+				 channels->max_tx +
+				 channels->max_other;
+	/* Tx conf and Rx err */
+	channels->other_count = queue_count + 1;
+	channels->combined_count = channels->rx_count +
+				   channels->tx_count +
+				   channels->other_count;
+}
+
 const struct ethtool_ops dpaa2_ethtool_ops = {
 	.supported_coalesce_params = ETHTOOL_COALESCE_RX_USECS |
 				     ETHTOOL_COALESCE_USE_ADAPTIVE_RX,
@@ -896,4 +919,5 @@ const struct ethtool_ops dpaa2_ethtool_ops = {
 	.set_tunable = dpaa2_eth_set_tunable,
 	.get_coalesce = dpaa2_eth_get_coalesce,
 	.set_coalesce = dpaa2_eth_set_coalesce,
+	.get_channels = dpaa2_eth_get_channels,
 };
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-xsk.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-xsk.c
new file mode 100644
index 000000000000..567f52affe21
--- /dev/null
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-xsk.c
@@ -0,0 +1,454 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause)
+/* Copyright 2022 NXP
+ */
+#include <linux/filter.h>
+#include <linux/compiler.h>
+#include <linux/bpf_trace.h>
+#include <net/xdp.h>
+#include <net/xdp_sock_drv.h>
+
+#include "dpaa2-eth.h"
+
+static void dpaa2_eth_setup_consume_func(struct dpaa2_eth_priv *priv,
+					 struct dpaa2_eth_channel *ch,
+					 enum dpaa2_eth_fq_type type,
+					 dpaa2_eth_consume_cb_t *consume)
+{
+	struct dpaa2_eth_fq *fq;
+	int i;
+
+	for (i = 0; i < priv->num_fqs; i++) {
+		fq = &priv->fq[i];
+
+		if (fq->type != type)
+			continue;
+		if (fq->channel != ch)
+			continue;
+
+		fq->consume = consume;
+	}
+}
+
+static u32 dpaa2_xsk_run_xdp(struct dpaa2_eth_priv *priv,
+			     struct dpaa2_eth_channel *ch,
+			     struct dpaa2_eth_fq *rx_fq,
+			     struct dpaa2_fd *fd, void *vaddr)
+{
+	dma_addr_t addr = dpaa2_fd_get_addr(fd);
+	struct bpf_prog *xdp_prog;
+	struct xdp_buff *xdp_buff;
+	struct dpaa2_eth_swa *swa;
+	u32 xdp_act = XDP_PASS;
+	int err;
+
+	xdp_prog = READ_ONCE(ch->xdp.prog);
+	if (!xdp_prog)
+		goto out;
+
+	swa = (struct dpaa2_eth_swa *)(vaddr + DPAA2_ETH_RX_HWA_SIZE +
+				       ch->xsk_pool->umem->headroom);
+	xdp_buff = swa->xsk.xdp_buff;
+
+	xdp_buff->data_hard_start = vaddr;
+	xdp_buff->data = vaddr + dpaa2_fd_get_offset(fd);
+	xdp_buff->data_end = xdp_buff->data + dpaa2_fd_get_len(fd);
+	xdp_set_data_meta_invalid(xdp_buff);
+	xdp_buff->rxq = &ch->xdp_rxq;
+
+	xsk_buff_dma_sync_for_cpu(xdp_buff, ch->xsk_pool);
+	xdp_act = bpf_prog_run_xdp(xdp_prog, xdp_buff);
+
+	/* xdp.data pointer may have changed */
+	dpaa2_fd_set_offset(fd, xdp_buff->data - vaddr);
+	dpaa2_fd_set_len(fd, xdp_buff->data_end - xdp_buff->data);
+
+	if (likely(xdp_act == XDP_REDIRECT)) {
+		err = xdp_do_redirect(priv->net_dev, xdp_buff, xdp_prog);
+		if (unlikely(err)) {
+			ch->stats.xdp_drop++;
+			dpaa2_eth_recycle_buf(priv, ch, addr);
+		} else {
+			ch->buf_count--;
+			ch->stats.xdp_redirect++;
+		}
+
+		goto xdp_redir;
+	}
+
+	switch (xdp_act) {
+	case XDP_PASS:
+		break;
+	case XDP_TX:
+		dpaa2_eth_xdp_enqueue(priv, ch, fd, vaddr, rx_fq->flowid);
+		break;
+	default:
+		bpf_warn_invalid_xdp_action(priv->net_dev, xdp_prog, xdp_act);
+		fallthrough;
+	case XDP_ABORTED:
+		trace_xdp_exception(priv->net_dev, xdp_prog, xdp_act);
+		fallthrough;
+	case XDP_DROP:
+		dpaa2_eth_recycle_buf(priv, ch, addr);
+		ch->stats.xdp_drop++;
+		break;
+	}
+
+xdp_redir:
+	ch->xdp.res |= xdp_act;
+out:
+	return xdp_act;
+}
+
+/* Rx frame processing routine for the AF_XDP fast path */
+static void dpaa2_xsk_rx(struct dpaa2_eth_priv *priv,
+			 struct dpaa2_eth_channel *ch,
+			 const struct dpaa2_fd *fd,
+			 struct dpaa2_eth_fq *fq)
+{
+	dma_addr_t addr = dpaa2_fd_get_addr(fd);
+	u8 fd_format = dpaa2_fd_get_format(fd);
+	struct rtnl_link_stats64 *percpu_stats;
+	u32 fd_length = dpaa2_fd_get_len(fd);
+	struct sk_buff *skb;
+	void *vaddr;
+	u32 xdp_act;
+
+	trace_dpaa2_rx_xsk_fd(priv->net_dev, fd);
+
+	vaddr = dpaa2_iova_to_virt(priv->iommu_domain, addr);
+	percpu_stats = this_cpu_ptr(priv->percpu_stats);
+
+	if (fd_format != dpaa2_fd_single) {
+		WARN_ON(priv->xdp_prog);
+		/* AF_XDP doesn't support any other formats */
+		goto err_frame_format;
+	}
+
+	xdp_act = dpaa2_xsk_run_xdp(priv, ch, fq, (struct dpaa2_fd *)fd, vaddr);
+	if (xdp_act != XDP_PASS) {
+		percpu_stats->rx_packets++;
+		percpu_stats->rx_bytes += dpaa2_fd_get_len(fd);
+		return;
+	}
+
+	/* Build skb */
+	skb = dpaa2_eth_alloc_skb(priv, ch, fd, fd_length, vaddr);
+	if (!skb)
+		/* Nothing else we can do, recycle the buffer and
+		 * drop the frame.
+		 */
+		goto err_alloc_skb;
+
+	/* Send the skb to the Linux networking stack */
+	dpaa2_eth_receive_skb(priv, ch, fd, vaddr, fq, percpu_stats, skb);
+
+	return;
+
+err_alloc_skb:
+	dpaa2_eth_recycle_buf(priv, ch, addr);
+err_frame_format:
+	percpu_stats->rx_dropped++;
+}
+
+static void dpaa2_xsk_set_bp_per_qdbin(struct dpaa2_eth_priv *priv,
+				       struct dpni_pools_cfg *pools_params)
+{
+	int curr_bp = 0, i, j;
+
+	pools_params->pool_options = DPNI_POOL_ASSOC_QDBIN;
+	for (i = 0; i < priv->num_bps; i++) {
+		for (j = 0; j < priv->num_channels; j++)
+			if (priv->bp[i] == priv->channel[j]->bp)
+				pools_params->pools[curr_bp].priority_mask |= (1 << j);
+		if (!pools_params->pools[curr_bp].priority_mask)
+			continue;
+
+		pools_params->pools[curr_bp].dpbp_id = priv->bp[i]->bpid;
+		pools_params->pools[curr_bp].buffer_size = priv->rx_buf_size;
+		pools_params->pools[curr_bp++].backup_pool = 0;
+	}
+	pools_params->num_dpbp = curr_bp;
+}
+
+static int dpaa2_xsk_disable_pool(struct net_device *dev, u16 qid)
+{
+	struct xsk_buff_pool *pool = xsk_get_pool_from_qid(dev, qid);
+	struct dpaa2_eth_priv *priv = netdev_priv(dev);
+	struct dpni_pools_cfg pools_params = { 0 };
+	struct dpaa2_eth_channel *ch;
+	int err;
+	bool up;
+
+	ch = priv->channel[qid];
+	if (!ch->xsk_pool)
+		return -EINVAL;
+
+	up = netif_running(dev);
+	if (up)
+		dev_close(dev);
+
+	xsk_pool_dma_unmap(pool, 0);
+	err = xdp_rxq_info_reg_mem_model(&ch->xdp_rxq,
+					 MEM_TYPE_PAGE_ORDER0, NULL);
+	if (err)
+		netdev_err(dev, "xsk_rxq_info_reg_mem_model() failed (err = %d)\n",
+			   err);
+
+	dpaa2_eth_free_dpbp(priv, ch->bp);
+
+	ch->xsk_zc = false;
+	ch->xsk_pool = NULL;
+	ch->xsk_tx_pkts_sent = 0;
+	ch->bp = priv->bp[DPAA2_ETH_DEFAULT_BP_IDX];
+
+	dpaa2_eth_setup_consume_func(priv, ch, DPAA2_RX_FQ, dpaa2_eth_rx);
+
+	dpaa2_xsk_set_bp_per_qdbin(priv, &pools_params);
+	err = dpni_set_pools(priv->mc_io, 0, priv->mc_token, &pools_params);
+	if (err)
+		netdev_err(dev, "dpni_set_pools() failed\n");
+
+	if (up) {
+		err = dev_open(dev, NULL);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static int dpaa2_xsk_enable_pool(struct net_device *dev,
+				 struct xsk_buff_pool *pool,
+				 u16 qid)
+{
+	struct dpaa2_eth_priv *priv = netdev_priv(dev);
+	struct dpni_pools_cfg pools_params = { 0 };
+	struct dpaa2_eth_channel *ch;
+	int err, err2;
+	bool up;
+
+	if (priv->dpni_attrs.wriop_version < DPAA2_WRIOP_VERSION(3, 0, 0)) {
+		netdev_err(dev, "AF_XDP zero-copy not supported on devices <= WRIOP(3, 0, 0)\n");
+		return -EOPNOTSUPP;
+	}
+
+	if (priv->dpni_attrs.num_queues > 8) {
+		netdev_err(dev, "AF_XDP zero-copy not supported on DPNI with more then 8 queues\n");
+		return -EOPNOTSUPP;
+	}
+
+	up = netif_running(dev);
+	if (up)
+		dev_close(dev);
+
+	err = xsk_pool_dma_map(pool, priv->net_dev->dev.parent, 0);
+	if (err) {
+		netdev_err(dev, "xsk_pool_dma_map() failed (err = %d)\n",
+			   err);
+		goto err_dma_unmap;
+	}
+
+	ch = priv->channel[qid];
+	err = xdp_rxq_info_reg_mem_model(&ch->xdp_rxq, MEM_TYPE_XSK_BUFF_POOL, NULL);
+	if (err) {
+		netdev_err(dev, "xdp_rxq_info_reg_mem_model() failed (err = %d)\n", err);
+		goto err_mem_model;
+	}
+	xsk_pool_set_rxq_info(pool, &ch->xdp_rxq);
+
+	priv->bp[priv->num_bps] = dpaa2_eth_allocate_dpbp(priv);
+	if (IS_ERR(priv->bp[priv->num_bps])) {
+		err = PTR_ERR(priv->bp[priv->num_bps]);
+		goto err_bp_alloc;
+	}
+	ch->xsk_zc = true;
+	ch->xsk_pool = pool;
+	ch->bp = priv->bp[priv->num_bps++];
+
+	dpaa2_eth_setup_consume_func(priv, ch, DPAA2_RX_FQ, dpaa2_xsk_rx);
+
+	dpaa2_xsk_set_bp_per_qdbin(priv, &pools_params);
+	err = dpni_set_pools(priv->mc_io, 0, priv->mc_token, &pools_params);
+	if (err) {
+		netdev_err(dev, "dpni_set_pools() failed\n");
+		goto err_set_pools;
+	}
+
+	if (up) {
+		err = dev_open(dev, NULL);
+		if (err)
+			return err;
+	}
+
+	return 0;
+
+err_set_pools:
+	err2 = dpaa2_xsk_disable_pool(dev, qid);
+	if (err2)
+		netdev_err(dev, "dpaa2_xsk_disable_pool() failed %d\n", err2);
+err_bp_alloc:
+	err2 = xdp_rxq_info_reg_mem_model(&priv->channel[qid]->xdp_rxq,
+					  MEM_TYPE_PAGE_ORDER0, NULL);
+	if (err2)
+		netdev_err(dev, "xsk_rxq_info_reg_mem_model() failed with %d)\n", err2);
+err_mem_model:
+	xsk_pool_dma_unmap(pool, 0);
+err_dma_unmap:
+	if (up)
+		dev_open(dev, NULL);
+
+	return err;
+}
+
+int dpaa2_xsk_setup_pool(struct net_device *dev, struct xsk_buff_pool *pool, u16 qid)
+{
+	return pool ? dpaa2_xsk_enable_pool(dev, pool, qid) :
+		      dpaa2_xsk_disable_pool(dev, qid);
+}
+
+int dpaa2_xsk_wakeup(struct net_device *dev, u32 qid, u32 flags)
+{
+	struct dpaa2_eth_priv *priv = netdev_priv(dev);
+	struct dpaa2_eth_channel *ch = priv->channel[qid];
+
+	if (!priv->link_state.up)
+		return -ENETDOWN;
+
+	if (!priv->xdp_prog)
+		return -EINVAL;
+
+	if (!ch->xsk_zc)
+		return -EINVAL;
+
+	/* We do not have access to a per channel SW interrupt, so instead we
+	 * schedule a NAPI instance.
+	 */
+	if (!napi_if_scheduled_mark_missed(&ch->napi))
+		napi_schedule(&ch->napi);
+
+	return 0;
+}
+
+static int dpaa2_xsk_tx_build_fd(struct dpaa2_eth_priv *priv,
+				 struct dpaa2_eth_channel *ch,
+				 struct dpaa2_fd *fd,
+				 struct xdp_desc *xdp_desc)
+{
+	struct device *dev = priv->net_dev->dev.parent;
+	struct dpaa2_sg_entry *sgt;
+	struct dpaa2_eth_swa *swa;
+	void *sgt_buf = NULL;
+	dma_addr_t sgt_addr;
+	int sgt_buf_size;
+	dma_addr_t addr;
+	int err = 0;
+
+	/* Prepare the HW SGT structure */
+	sgt_buf_size = priv->tx_data_offset + sizeof(struct dpaa2_sg_entry);
+	sgt_buf = dpaa2_eth_sgt_get(priv);
+	if (unlikely(!sgt_buf))
+		return -ENOMEM;
+	sgt = (struct dpaa2_sg_entry *)(sgt_buf + priv->tx_data_offset);
+
+	/* Get the address of the XSK Tx buffer */
+	addr = xsk_buff_raw_get_dma(ch->xsk_pool, xdp_desc->addr);
+	xsk_buff_raw_dma_sync_for_device(ch->xsk_pool, addr, xdp_desc->len);
+
+	/* Fill in the HW SGT structure */
+	dpaa2_sg_set_addr(sgt, addr);
+	dpaa2_sg_set_len(sgt, xdp_desc->len);
+	dpaa2_sg_set_final(sgt, true);
+
+	/* Store the necessary info in the SGT buffer */
+	swa = (struct dpaa2_eth_swa *)sgt_buf;
+	swa->type = DPAA2_ETH_SWA_XSK;
+	swa->xsk.sgt_size = sgt_buf_size;
+
+	/* Separately map the SGT buffer */
+	sgt_addr = dma_map_single(dev, sgt_buf, sgt_buf_size, DMA_BIDIRECTIONAL);
+	if (unlikely(dma_mapping_error(dev, sgt_addr))) {
+		err = -ENOMEM;
+		goto sgt_map_failed;
+	}
+
+	/* Initialize FD fields */
+	memset(fd, 0, sizeof(struct dpaa2_fd));
+	dpaa2_fd_set_offset(fd, priv->tx_data_offset);
+	dpaa2_fd_set_format(fd, dpaa2_fd_sg);
+	dpaa2_fd_set_addr(fd, sgt_addr);
+	dpaa2_fd_set_len(fd, xdp_desc->len);
+	dpaa2_fd_set_ctrl(fd, FD_CTRL_PTA);
+
+	return 0;
+
+sgt_map_failed:
+	dpaa2_eth_sgt_recycle(priv, sgt_buf);
+
+	return err;
+}
+
+bool dpaa2_xsk_tx(struct dpaa2_eth_priv *priv,
+		  struct dpaa2_eth_channel *ch)
+{
+	struct xdp_desc *xdp_descs = ch->xsk_pool->tx_descs;
+	struct dpaa2_eth_drv_stats *percpu_extras;
+	struct rtnl_link_stats64 *percpu_stats;
+	int budget = DPAA2_ETH_TX_ZC_PER_NAPI;
+	int total_enqueued, enqueued;
+	int retries, max_retries;
+	struct dpaa2_eth_fq *fq;
+	struct dpaa2_fd *fds;
+	int batch, i, err;
+
+	percpu_stats = this_cpu_ptr(priv->percpu_stats);
+	percpu_extras = this_cpu_ptr(priv->percpu_extras);
+	fds = (this_cpu_ptr(priv->fd))->array;
+
+	/* Use the FQ with the same idx as the affine CPU */
+	fq = &priv->fq[ch->nctx.desired_cpu];
+
+	batch = xsk_tx_peek_release_desc_batch(ch->xsk_pool, budget);
+	if (!batch)
+		return false;
+
+	/* Create a FD for each XSK frame to be sent */
+	for (i = 0; i < batch; i++) {
+		err = dpaa2_xsk_tx_build_fd(priv, ch, &fds[i], &xdp_descs[i]);
+		if (err) {
+			batch = i;
+			break;
+		}
+
+		trace_dpaa2_tx_xsk_fd(priv->net_dev, &fds[i]);
+	}
+
+	/* Enqueue all the created FDs */
+	max_retries = batch * DPAA2_ETH_ENQUEUE_RETRIES;
+	total_enqueued = 0;
+	enqueued = 0;
+	retries = 0;
+	while (total_enqueued < batch && retries < max_retries) {
+		err = priv->enqueue(priv, fq, &fds[total_enqueued], 0,
+				    batch - total_enqueued, &enqueued);
+		if (err == -EBUSY) {
+			retries++;
+			continue;
+		}
+
+		total_enqueued += enqueued;
+	}
+	percpu_extras->tx_portal_busy += retries;
+
+	/* Update statistics */
+	percpu_stats->tx_packets += total_enqueued;
+	for (i = 0; i < total_enqueued; i++)
+		percpu_stats->tx_bytes += dpaa2_fd_get_len(&fds[i]);
+	for (i = total_enqueued; i < batch; i++) {
+		dpaa2_eth_free_tx_fd(priv, ch, fq, &fds[i], false);
+		percpu_stats->tx_errors++;
+	}
+
+	xsk_tx_release(ch->xsk_pool);
+
+	return total_enqueued == budget ? true : false;
+}
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpni-cmd.h b/drivers/net/ethernet/freescale/dpaa2/dpni-cmd.h
index 828f538097af..be9492b8d5dc 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpni-cmd.h
+++ b/drivers/net/ethernet/freescale/dpaa2/dpni-cmd.h
@@ -13,10 +13,12 @@
 #define DPNI_VER_MINOR				0
 #define DPNI_CMD_BASE_VERSION			1
 #define DPNI_CMD_2ND_VERSION			2
+#define DPNI_CMD_3RD_VERSION			3
 #define DPNI_CMD_ID_OFFSET			4
 
 #define DPNI_CMD(id)	(((id) << DPNI_CMD_ID_OFFSET) | DPNI_CMD_BASE_VERSION)
 #define DPNI_CMD_V2(id)	(((id) << DPNI_CMD_ID_OFFSET) | DPNI_CMD_2ND_VERSION)
+#define DPNI_CMD_V3(id)	(((id) << DPNI_CMD_ID_OFFSET) | DPNI_CMD_3RD_VERSION)
 
 #define DPNI_CMDID_OPEN					DPNI_CMD(0x801)
 #define DPNI_CMDID_CLOSE				DPNI_CMD(0x800)
@@ -39,7 +41,7 @@
 #define DPNI_CMDID_GET_IRQ_STATUS			DPNI_CMD(0x016)
 #define DPNI_CMDID_CLEAR_IRQ_STATUS			DPNI_CMD(0x017)
 
-#define DPNI_CMDID_SET_POOLS				DPNI_CMD(0x200)
+#define DPNI_CMDID_SET_POOLS				DPNI_CMD_V3(0x200)
 #define DPNI_CMDID_SET_ERRORS_BEHAVIOR			DPNI_CMD(0x20B)
 
 #define DPNI_CMDID_GET_QDID				DPNI_CMD(0x210)
@@ -115,14 +117,19 @@ struct dpni_cmd_open {
 };
 
 #define DPNI_BACKUP_POOL(val, order)	(((val) & 0x1) << (order))
+
+struct dpni_cmd_pool {
+	__le16 dpbp_id;
+	u8 priority_mask;
+	u8 pad;
+};
+
 struct dpni_cmd_set_pools {
-	/* cmd word 0 */
 	u8 num_dpbp;
 	u8 backup_pool_mask;
-	__le16 pad;
-	/* cmd word 0..4 */
-	__le32 dpbp_id[DPNI_MAX_DPBP];
-	/* cmd word 4..6 */
+	u8 pad;
+	u8 pool_options;
+	struct dpni_cmd_pool pool[DPNI_MAX_DPBP];
 	__le16 buffer_size[DPNI_MAX_DPBP];
 };
 
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpni.c b/drivers/net/ethernet/freescale/dpaa2/dpni.c
index 6c3b36f20fb8..02601a283b59 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpni.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpni.c
@@ -173,8 +173,12 @@ int dpni_set_pools(struct fsl_mc_io *mc_io,
 					  token);
 	cmd_params = (struct dpni_cmd_set_pools *)cmd.params;
 	cmd_params->num_dpbp = cfg->num_dpbp;
+	cmd_params->pool_options = cfg->pool_options;
 	for (i = 0; i < DPNI_MAX_DPBP; i++) {
-		cmd_params->dpbp_id[i] = cpu_to_le32(cfg->pools[i].dpbp_id);
+		cmd_params->pool[i].dpbp_id =
+			cpu_to_le16(cfg->pools[i].dpbp_id);
+		cmd_params->pool[i].priority_mask =
+			cfg->pools[i].priority_mask;
 		cmd_params->buffer_size[i] =
 			cpu_to_le16(cfg->pools[i].buffer_size);
 		cmd_params->backup_pool_mask |=
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpni.h b/drivers/net/ethernet/freescale/dpaa2/dpni.h
index 6fffd519aa00..5c0a1d5ac934 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpni.h
+++ b/drivers/net/ethernet/freescale/dpaa2/dpni.h
@@ -92,19 +92,28 @@ int dpni_close(struct fsl_mc_io	*mc_io,
 	       u32		cmd_flags,
 	       u16		token);
 
+#define DPNI_POOL_ASSOC_QPRI	0
+#define DPNI_POOL_ASSOC_QDBIN	1
+
 /**
  * struct dpni_pools_cfg - Structure representing buffer pools configuration
  * @num_dpbp: Number of DPBPs
+ * @pool_options: Buffer assignment options.
+ *	This field is a combination of DPNI_POOL_ASSOC_flags
  * @pools: Array of buffer pools parameters; The number of valid entries
  *	must match 'num_dpbp' value
  * @pools.dpbp_id: DPBP object ID
+ * @pools.priority: Priority mask that indicates TC's used with this buffer.
+ *	If set to 0x00 MC will assume value 0xff.
  * @pools.buffer_size: Buffer size
  * @pools.backup_pool: Backup pool
  */
 struct dpni_pools_cfg {
 	u8		num_dpbp;
+	u8		pool_options;
 	struct {
 		int	dpbp_id;
+		u8	priority_mask;
 		u16	buffer_size;
 		int	backup_pool;
 	} pools[DPNI_MAX_DPBP];