[dpdk-dev] [PATCH v10 1/1] net/af_xdp: introduce AF XDP PMD driver

[Xiaolong Ye <xiaolong.ye@intel.com>]

Add a new PMD driver for AF_XDP which is a proposed faster version of
AF_PACKET interface in Linux. More info about AF_XDP, please refer to [1]
[2].

This is the vanilla version PMD which just uses a raw buffer registered as
the umem.

[1] https://fosdem.org/2018/schedule/event/af_xdp/
[2] https://lwn.net/Articles/745934/

Signed-off-by: Xiaolong Ye <xiaolong.ye@intel.com>
---
 MAINTAINERS                                   |   7 +
 config/common_base                            |   5 +
 doc/guides/nics/af_xdp.rst                    |  50 +
 doc/guides/nics/features/af_xdp.ini           |  11 +
 doc/guides/nics/index.rst                     |   1 +
 doc/guides/rel_notes/release_19_05.rst        |   7 +
 drivers/net/Makefile                          |   1 +
 drivers/net/af_xdp/Makefile                   |  28 +
 drivers/net/af_xdp/af_xdp_deps.h              |  14 +
 drivers/net/af_xdp/meson.build                |  21 +
 drivers/net/af_xdp/rte_eth_af_xdp.c           | 955 ++++++++++++++++++
 drivers/net/af_xdp/rte_pmd_af_xdp_version.map |   3 +
 drivers/net/meson.build                       |   1 +
 mk/rte.app.mk                                 |   1 +
 14 files changed, 1105 insertions(+)
 create mode 100644 doc/guides/nics/af_xdp.rst
 create mode 100644 doc/guides/nics/features/af_xdp.ini
 create mode 100644 drivers/net/af_xdp/Makefile
 create mode 100644 drivers/net/af_xdp/af_xdp_deps.h
 create mode 100644 drivers/net/af_xdp/meson.build
 create mode 100644 drivers/net/af_xdp/rte_eth_af_xdp.c
 create mode 100644 drivers/net/af_xdp/rte_pmd_af_xdp_version.map

diff --git a/MAINTAINERS b/MAINTAINERS
index 71ac8cd4b..f30572c07 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -489,6 +489,13 @@ M: John W. Linville <linville@tuxdriver.com>
 F: drivers/net/af_packet/
 F: doc/guides/nics/features/afpacket.ini
 
+Linux AF_XDP
+M: Xiaolong Ye <xiaolong.ye@intel.com>
+M: Qi Zhang <qi.z.zhang@intel.com>
+F: drivers/net/af_xdp/
+F: doc/guides/nics/af_xdp.rst
+F: doc/guides/nics/features/af_xdp.ini
+
 Amazon ENA
 M: Marcin Wojtas <mw@semihalf.com>
 M: Michal Krawczyk <mk@semihalf.com>
diff --git a/config/common_base b/config/common_base
index 6292bc4af..b95ee03d7 100644
--- a/config/common_base
+++ b/config/common_base
@@ -430,6 +430,11 @@ CONFIG_RTE_LIBRTE_VMXNET3_DEBUG_TX_FREE=n
 #
 CONFIG_RTE_LIBRTE_PMD_AF_PACKET=n
 
+#
+# Compile software PMD backed by AF_XDP sockets (Linux only)
+#
+CONFIG_RTE_LIBRTE_PMD_AF_XDP=n
+
 #
 # Compile link bonding PMD library
 #
diff --git a/doc/guides/nics/af_xdp.rst b/doc/guides/nics/af_xdp.rst
new file mode 100644
index 000000000..175038153
--- /dev/null
+++ b/doc/guides/nics/af_xdp.rst
@@ -0,0 +1,50 @@
+..  SPDX-License-Identifier: BSD-3-Clause
+    Copyright(c) 2019 Intel Corporation.
+
+AF_XDP Poll Mode Driver
+==========================
+
+AF_XDP is an address family that is optimized for high performance
+packet processing. AF_XDP sockets enable the possibility for XDP program to
+redirect packets to a memory buffer in userspace.
+
+For the full details behind AF_XDP socket, you can refer to
+`AF_XDP documentation in the Kernel
+<https://www.kernel.org/doc/Documentation/networking/af_xdp.rst>`_.
+
+This Linux-specific PMD driver creates the AF_XDP socket and binds it to a
+specific netdev queue, it allows a DPDK application to send and receive raw
+packets through the socket which would bypass the kernel network stack.
+Current implementation only supports single queue, multi-queues feature will
+be added later.
+
+Note that MTU of AF_XDP PMD is limited due to XDP lacks support for
+fragmentation.
+
+Options
+-------
+
+The following options can be provided to set up an af_xdp port in DPDK.
+
+*   ``iface`` - name of the Kernel interface to attach to (required);
+*   ``queue`` - netdev queue id (optional, default 0);
+
+Prerequisites
+-------------
+
+This is a Linux-specific PMD, thus the following prerequisites apply:
+
+*  A Linux Kernel (version > v4.18) with XDP sockets configuration enabled;
+*  libbpf (within kernel version > v5.1-rc4) with latest af_xdp support installed,
+   User can install libbpf via `make install_lib` && `make install_headers` in
+   <kernel src tree>/tools/lib/bpf;
+*  A Kernel bound interface to attach to;
+
+Set up an af_xdp interface
+-----------------------------
+
+The following example will set up an af_xdp interface in DPDK:
+
+.. code-block:: console
+
+    --vdev net_af_xdp,iface=ens786f1,queue=0
diff --git a/doc/guides/nics/features/af_xdp.ini b/doc/guides/nics/features/af_xdp.ini
new file mode 100644
index 000000000..36953c2de
--- /dev/null
+++ b/doc/guides/nics/features/af_xdp.ini
@@ -0,0 +1,11 @@
+;
+; Supported features of the 'af_xdp' network poll mode driver.
+;
+; Refer to default.ini for the full list of available PMD features.
+;
+[Features]
+Link status          = Y
+MTU update           = Y
+Promiscuous mode     = Y
+Stats per queue      = Y
+x86-64               = Y
diff --git a/doc/guides/nics/index.rst b/doc/guides/nics/index.rst
index 5c80e3baa..a4b80a3d0 100644
--- a/doc/guides/nics/index.rst
+++ b/doc/guides/nics/index.rst
@@ -12,6 +12,7 @@ Network Interface Controller Drivers
     features
     build_and_test
     af_packet
+    af_xdp
     ark
     atlantic
     avp
diff --git a/doc/guides/rel_notes/release_19_05.rst b/doc/guides/rel_notes/release_19_05.rst
index bdad1ddbe..79e36739f 100644
--- a/doc/guides/rel_notes/release_19_05.rst
+++ b/doc/guides/rel_notes/release_19_05.rst
@@ -74,6 +74,13 @@ New Features
     process.
   * Added support for Rx packet types list in a secondary process.
 
+* **Added the AF_XDP PMD.**
+
+  Added a Linux-specific PMD driver for AF_XDP, it can create the AF_XDP socket
+  and bind it to a specific netdev queue, it allows a DPDK application to send
+  and receive raw packets through the socket which would bypass the kernel
+  network stack to achieve high performance packet processing.
+
 * **Updated Mellanox drivers.**
 
    New features and improvements were done in mlx4 and mlx5 PMDs:
diff --git a/drivers/net/Makefile b/drivers/net/Makefile
index 502869a87..5d401b8c5 100644
--- a/drivers/net/Makefile
+++ b/drivers/net/Makefile
@@ -9,6 +9,7 @@ ifeq ($(CONFIG_RTE_LIBRTE_THUNDERX_NICVF_PMD),d)
 endif
 
 DIRS-$(CONFIG_RTE_LIBRTE_PMD_AF_PACKET) += af_packet
+DIRS-$(CONFIG_RTE_LIBRTE_PMD_AF_XDP) += af_xdp
 DIRS-$(CONFIG_RTE_LIBRTE_ARK_PMD) += ark
 DIRS-$(CONFIG_RTE_LIBRTE_ATLANTIC_PMD) += atlantic
 DIRS-$(CONFIG_RTE_LIBRTE_AVP_PMD) += avp
diff --git a/drivers/net/af_xdp/Makefile b/drivers/net/af_xdp/Makefile
new file mode 100644
index 000000000..eeba6b693
--- /dev/null
+++ b/drivers/net/af_xdp/Makefile
@@ -0,0 +1,28 @@
+# SPDX-License-Identifier: BSD-3-Clause
+# Copyright(c) 2019 Intel Corporation
+
+include $(RTE_SDK)/mk/rte.vars.mk
+
+#
+# library name
+#
+LIB = librte_pmd_af_xdp.a
+
+EXPORT_MAP := rte_pmd_af_xdp_version.map
+
+LIBABIVER := 1
+
+CFLAGS += -O3
+
+CFLAGS += $(WERROR_FLAGS)
+LDLIBS += -lrte_eal -lrte_mbuf -lrte_mempool -lrte_ring
+LDLIBS += -lrte_ethdev -lrte_net -lrte_kvargs
+LDLIBS += -lrte_bus_vdev
+LDLIBS += $(shell command -v pkg-config > /dev/null 2>&1 && pkg-config --libs libbpf || echo "-lbpf")
+
+#
+# all source are stored in SRCS-y
+#
+SRCS-$(CONFIG_RTE_LIBRTE_PMD_AF_XDP) += rte_eth_af_xdp.c
+
+include $(RTE_SDK)/mk/rte.lib.mk
diff --git a/drivers/net/af_xdp/af_xdp_deps.h b/drivers/net/af_xdp/af_xdp_deps.h
new file mode 100644
index 000000000..8c8f8b6ab
--- /dev/null
+++ b/drivers/net/af_xdp/af_xdp_deps.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2019 Intel Corporation.
+ */
+
+#ifndef AF_XDP_DEPS_H_
+#define AF_XDP_DEPS_H_
+
+#include <rte_atomic.h>
+#include <rte_branch_prediction.h>
+
+#define smp_rmb() rte_rmb()
+#define smp_wmb() rte_wmb()
+
+#endif /* AF_XDP_DEPS_H_ */
diff --git a/drivers/net/af_xdp/meson.build b/drivers/net/af_xdp/meson.build
new file mode 100644
index 000000000..d40aae190
--- /dev/null
+++ b/drivers/net/af_xdp/meson.build
@@ -0,0 +1,21 @@
+# SPDX-License-Identifier: BSD-3-Clause
+# Copyright(c) 2019 Intel Corporation
+
+if host_machine.system() != 'linux'
+	build = false
+endif
+
+bpf_dep = dependency('libbpf', required: false)
+if bpf_dep.found()
+	build = true
+else
+	bpf_dep = cc.find_library('libbpf', required: false)
+	if bpf_dep.found() and cc.has_header('xsk.h', dependencies: bpf_dep) and cc.has_header('linux/if_xdp.h')
+		build = true
+		pkgconfig_extra_libs += '-lbpf'
+	else
+		build = false
+	endif
+endif
+sources = files('rte_eth_af_xdp.c')
+ext_deps += bpf_dep
diff --git a/drivers/net/af_xdp/rte_eth_af_xdp.c b/drivers/net/af_xdp/rte_eth_af_xdp.c
new file mode 100644
index 000000000..007a1c6b4
--- /dev/null
+++ b/drivers/net/af_xdp/rte_eth_af_xdp.c
@@ -0,0 +1,955 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2019 Intel Corporation.
+ */
+#include <unistd.h>
+#include <errno.h>
+#include <stdlib.h>
+#include <string.h>
+#include <netinet/in.h>
+#include <net/if.h>
+#include <sys/socket.h>
+#include <sys/ioctl.h>
+#include <linux/if_ether.h>
+#include <linux/if_xdp.h>
+#include <linux/if_link.h>
+#include "af_xdp_deps.h"
+#include <bpf/xsk.h>
+
+#include <rte_ethdev.h>
+#include <rte_ethdev_driver.h>
+#include <rte_ethdev_vdev.h>
+#include <rte_kvargs.h>
+#include <rte_bus_vdev.h>
+#include <rte_string_fns.h>
+#include <rte_branch_prediction.h>
+#include <rte_common.h>
+#include <rte_config.h>
+#include <rte_dev.h>
+#include <rte_eal.h>
+#include <rte_ether.h>
+#include <rte_lcore.h>
+#include <rte_log.h>
+#include <rte_memory.h>
+#include <rte_memzone.h>
+#include <rte_mbuf.h>
+#include <rte_malloc.h>
+#include <rte_ring.h>
+
+#ifndef SOL_XDP
+#define SOL_XDP 283
+#endif
+
+#ifndef AF_XDP
+#define AF_XDP 44
+#endif
+
+#ifndef PF_XDP
+#define PF_XDP AF_XDP
+#endif
+
+static int af_xdp_logtype;
+
+#define AF_XDP_LOG(level, fmt, args...)			\
+	rte_log(RTE_LOG_ ## level, af_xdp_logtype,	\
+		"%s(): " fmt, __func__, ##args)
+
+#define ETH_AF_XDP_FRAME_SIZE		XSK_UMEM__DEFAULT_FRAME_SIZE
+#define ETH_AF_XDP_NUM_BUFFERS		4096
+#define ETH_AF_XDP_DATA_HEADROOM	0
+#define ETH_AF_XDP_DFLT_NUM_DESCS	XSK_RING_CONS__DEFAULT_NUM_DESCS
+#define ETH_AF_XDP_DFLT_QUEUE_IDX	0
+
+#define ETH_AF_XDP_RX_BATCH_SIZE	32
+#define ETH_AF_XDP_TX_BATCH_SIZE	32
+
+#define ETH_AF_XDP_MAX_QUEUE_PAIRS     16
+
+struct xsk_umem_info {
+	struct xsk_ring_prod fq;
+	struct xsk_ring_cons cq;
+	struct xsk_umem *umem;
+	struct rte_ring *buf_ring;
+	const struct rte_memzone *mz;
+};
+
+struct rx_stats {
+	uint64_t rx_pkts;
+	uint64_t rx_bytes;
+	uint64_t rx_dropped;
+};
+
+struct pkt_rx_queue {
+	struct xsk_ring_cons rx;
+	struct xsk_umem_info *umem;
+	struct xsk_socket *xsk;
+	struct rte_mempool *mb_pool;
+
+	struct rx_stats stats;
+
+	struct pkt_tx_queue *pair;
+	uint16_t queue_idx;
+};
+
+struct tx_stats {
+	uint64_t tx_pkts;
+	uint64_t err_pkts;
+	uint64_t tx_bytes;
+};
+
+struct pkt_tx_queue {
+	struct xsk_ring_prod tx;
+
+	struct tx_stats stats;
+
+	struct pkt_rx_queue *pair;
+	uint16_t queue_idx;
+};
+
+struct pmd_internals {
+	int if_index;
+	char if_name[IFNAMSIZ];
+	uint16_t queue_idx;
+	struct ether_addr eth_addr;
+	struct xsk_umem_info *umem;
+	struct rte_mempool *mb_pool_share;
+
+	struct pkt_rx_queue rx_queues[ETH_AF_XDP_MAX_QUEUE_PAIRS];
+	struct pkt_tx_queue tx_queues[ETH_AF_XDP_MAX_QUEUE_PAIRS];
+};
+
+#define ETH_AF_XDP_IFACE_ARG			"iface"
+#define ETH_AF_XDP_QUEUE_IDX_ARG		"queue"
+
+static const char * const valid_arguments[] = {
+	ETH_AF_XDP_IFACE_ARG,
+	ETH_AF_XDP_QUEUE_IDX_ARG,
+	NULL
+};
+
+static const struct rte_eth_link pmd_link = {
+	.link_speed = ETH_SPEED_NUM_10G,
+	.link_duplex = ETH_LINK_FULL_DUPLEX,
+	.link_status = ETH_LINK_DOWN,
+	.link_autoneg = ETH_LINK_AUTONEG
+};
+
+static inline int
+reserve_fill_queue(struct xsk_umem_info *umem, int reserve_size)
+{
+	struct xsk_ring_prod *fq = &umem->fq;
+	uint32_t idx;
+	int i, ret;
+
+	ret = xsk_ring_prod__reserve(fq, reserve_size, &idx);
+	if (unlikely(!ret)) {
+		AF_XDP_LOG(ERR, "Failed to reserve enough fq descs.\n");
+		return ret;
+	}
+
+	for (i = 0; i < reserve_size; i++) {
+		__u64 *fq_addr;
+		void *addr = NULL;
+		if (rte_ring_dequeue(umem->buf_ring, &addr)) {
+			i--;
+			break;
+		}
+		fq_addr = xsk_ring_prod__fill_addr(fq, idx++);
+		*fq_addr = (uint64_t)addr;
+	}
+
+	xsk_ring_prod__submit(fq, i);
+
+	return 0;
+}
+
+static uint16_t
+eth_af_xdp_rx(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts)
+{
+	struct pkt_rx_queue *rxq = queue;
+	struct xsk_ring_cons *rx = &rxq->rx;
+	struct xsk_umem_info *umem = rxq->umem;
+	struct xsk_ring_prod *fq = &umem->fq;
+	uint32_t idx_rx = 0;
+	uint32_t free_thresh = fq->size >> 1;
+	struct rte_mbuf *mbufs[ETH_AF_XDP_TX_BATCH_SIZE];
+	unsigned long dropped = 0;
+	unsigned long rx_bytes = 0;
+	uint16_t count = 0;
+	int rcvd, i;
+
+	nb_pkts = RTE_MIN(nb_pkts, ETH_AF_XDP_TX_BATCH_SIZE);
+
+	rcvd = xsk_ring_cons__peek(rx, nb_pkts, &idx_rx);
+	if (rcvd == 0)
+		return 0;
+
+	if (xsk_prod_nb_free(fq, free_thresh) >= free_thresh)
+		(void)reserve_fill_queue(umem, ETH_AF_XDP_RX_BATCH_SIZE);
+
+	if (unlikely(rte_pktmbuf_alloc_bulk(rxq->mb_pool, mbufs, rcvd) != 0))
+		return 0;
+
+	for (i = 0; i < rcvd; i++) {
+		const struct xdp_desc *desc;
+		uint64_t addr;
+		uint32_t len;
+		void *pkt;
+
+		desc = xsk_ring_cons__rx_desc(rx, idx_rx++);
+		addr = desc->addr;
+		len = desc->len;
+		pkt = xsk_umem__get_data(rxq->umem->mz->addr, addr);
+
+		rte_memcpy(rte_pktmbuf_mtod(mbufs[i], void *), pkt, len);
+		rte_pktmbuf_pkt_len(mbufs[i]) = len;
+		rte_pktmbuf_data_len(mbufs[i]) = len;
+		rx_bytes += len;
+		bufs[count++] = mbufs[i];
+
+		rte_ring_enqueue(umem->buf_ring, (void *)addr);
+	}
+
+	xsk_ring_cons__release(rx, rcvd);
+
+	/* statistics */
+	rxq->stats.rx_pkts += (rcvd - dropped);
+	rxq->stats.rx_bytes += rx_bytes;
+
+	return count;
+}
+
+static void
+pull_umem_cq(struct xsk_umem_info *umem, int size)
+{
+	struct xsk_ring_cons *cq = &umem->cq;
+	size_t i, n;
+	uint32_t idx_cq = 0;
+
+	n = xsk_ring_cons__peek(cq, size, &idx_cq);
+
+	for (i = 0; i < n; i++) {
+		uint64_t addr;
+		addr = *xsk_ring_cons__comp_addr(cq, idx_cq++);
+		rte_ring_enqueue(umem->buf_ring, (void *)addr);
+	}
+
+	xsk_ring_cons__release(cq, n);
+}
+
+static void
+kick_tx(struct pkt_tx_queue *txq)
+{
+	struct xsk_umem_info *umem = txq->pair->umem;
+
+	while (send(xsk_socket__fd(txq->pair->xsk), NULL,
+		      0, MSG_DONTWAIT) < 0) {
+		/* some thing unexpected */
+		if (errno != EBUSY && errno != EAGAIN && errno != EINTR)
+			break;
+
+		/* pull from completion queue to leave more space */
+		if (errno == EAGAIN)
+			pull_umem_cq(umem, ETH_AF_XDP_TX_BATCH_SIZE);
+	}
+	pull_umem_cq(umem, ETH_AF_XDP_TX_BATCH_SIZE);
+}
+
+static uint16_t
+eth_af_xdp_tx(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts)
+{
+	struct pkt_tx_queue *txq = queue;
+	struct xsk_umem_info *umem = txq->pair->umem;
+	struct rte_mbuf *mbuf;
+	void *addrs[ETH_AF_XDP_TX_BATCH_SIZE];
+	unsigned long tx_bytes = 0;
+	int i, valid = 0;
+	uint32_t idx_tx;
+
+	nb_pkts = RTE_MIN(nb_pkts, ETH_AF_XDP_TX_BATCH_SIZE);
+
+	pull_umem_cq(umem, nb_pkts);
+
+	nb_pkts = rte_ring_dequeue_bulk(umem->buf_ring, addrs,
+					nb_pkts, NULL);
+	if (nb_pkts == 0)
+		return 0;
+
+	if (xsk_ring_prod__reserve(&txq->tx, nb_pkts, &idx_tx) != nb_pkts) {
+		kick_tx(txq);
+		return 0;
+	}
+
+	for (i = 0; i < nb_pkts; i++) {
+		struct xdp_desc *desc;
+		void *pkt;
+		uint32_t buf_len = ETH_AF_XDP_FRAME_SIZE
+					- ETH_AF_XDP_DATA_HEADROOM;
+		desc = xsk_ring_prod__tx_desc(&txq->tx, idx_tx + i);
+		mbuf = bufs[i];
+		if (mbuf->pkt_len <= buf_len) {
+			desc->addr = (uint64_t)addrs[valid];
+			desc->len = mbuf->pkt_len;
+			pkt = xsk_umem__get_data(umem->mz->addr,
+						 desc->addr);
+			rte_memcpy(pkt, rte_pktmbuf_mtod(mbuf, void *),
+			       desc->len);
+			valid++;
+			tx_bytes += mbuf->pkt_len;
+		}
+		rte_pktmbuf_free(mbuf);
+	}
+
+	xsk_ring_prod__submit(&txq->tx, nb_pkts);
+
+	kick_tx(txq);
+
+	if (valid < nb_pkts)
+		rte_ring_enqueue_bulk(umem->buf_ring, &addrs[valid],
+				 nb_pkts - valid, NULL);
+
+	txq->stats.err_pkts += nb_pkts - valid;
+	txq->stats.tx_pkts += valid;
+	txq->stats.tx_bytes += tx_bytes;
+
+	return nb_pkts;
+}
+
+static int
+eth_dev_start(struct rte_eth_dev *dev)
+{
+	dev->data->dev_link.link_status = ETH_LINK_UP;
+
+	return 0;
+}
+
+/* This function gets called when the current port gets stopped. */
+static void
+eth_dev_stop(struct rte_eth_dev *dev)
+{
+	dev->data->dev_link.link_status = ETH_LINK_DOWN;
+}
+
+static int
+eth_dev_configure(struct rte_eth_dev *dev)
+{
+	/* rx/tx must be paired */
+	if (dev->data->nb_rx_queues != dev->data->nb_tx_queues)
+		return -EINVAL;
+
+	return 0;
+}
+
+static void
+eth_dev_info(struct rte_eth_dev *dev, struct rte_eth_dev_info *dev_info)
+{
+	struct pmd_internals *internals = dev->data->dev_private;
+
+	dev_info->if_index = internals->if_index;
+	dev_info->max_mac_addrs = 1;
+	dev_info->max_rx_pktlen = ETH_FRAME_LEN;
+	dev_info->max_rx_queues = 1;
+	dev_info->max_tx_queues = 1;
+
+	dev_info->default_rxportconf.nb_queues = 1;
+	dev_info->default_txportconf.nb_queues = 1;
+	dev_info->default_rxportconf.ring_size = ETH_AF_XDP_DFLT_NUM_DESCS;
+	dev_info->default_txportconf.ring_size = ETH_AF_XDP_DFLT_NUM_DESCS;
+}
+
+static int
+eth_stats_get(struct rte_eth_dev *dev, struct rte_eth_stats *stats)
+{
+	struct pmd_internals *internals = dev->data->dev_private;
+	struct xdp_statistics xdp_stats;
+	struct pkt_rx_queue *rxq;
+	socklen_t optlen;
+	int i, ret;
+
+	for (i = 0; i < dev->data->nb_rx_queues; i++) {
+		optlen = sizeof(struct xdp_statistics);
+		rxq = &internals->rx_queues[i];
+		stats->q_ipackets[i] = internals->rx_queues[i].stats.rx_pkts;
+		stats->q_ibytes[i] = internals->rx_queues[i].stats.rx_bytes;
+
+		stats->q_opackets[i] = internals->tx_queues[i].stats.tx_pkts;
+		stats->q_obytes[i] = internals->tx_queues[i].stats.tx_bytes;
+
+		stats->ipackets += stats->q_ipackets[i];
+		stats->ibytes += stats->q_ibytes[i];
+		stats->imissed += internals->rx_queues[i].stats.rx_dropped;
+		ret = getsockopt(xsk_socket__fd(rxq->xsk), SOL_XDP,
+				XDP_STATISTICS, &xdp_stats, &optlen);
+		if (ret != 0) {
+			AF_XDP_LOG(ERR, "getsockopt() failed for XDP_STATISTICS.\n");
+			return -1;
+		}
+		stats->imissed += xdp_stats.rx_dropped;
+
+		stats->opackets += stats->q_opackets[i];
+		stats->oerrors += internals->tx_queues[i].stats.err_pkts;
+		stats->obytes += stats->q_obytes[i];
+	}
+
+	return 0;
+}
+
+static void
+eth_stats_reset(struct rte_eth_dev *dev)
+{
+	struct pmd_internals *internals = dev->data->dev_private;
+	int i;
+
+	for (i = 0; i < ETH_AF_XDP_MAX_QUEUE_PAIRS; i++) {
+		memset(&internals->rx_queues[i].stats, 0,
+					sizeof(struct rx_stats));
+		memset(&internals->tx_queues[i].stats, 0,
+					sizeof(struct tx_stats));
+	}
+}
+
+static void
+remove_xdp_program(struct pmd_internals *internals)
+{
+	uint32_t curr_prog_id = 0;
+
+	if (bpf_get_link_xdp_id(internals->if_index, &curr_prog_id,
+				XDP_FLAGS_UPDATE_IF_NOEXIST)) {
+		AF_XDP_LOG(ERR, "bpf_get_link_xdp_id failed\n");
+		return;
+	}
+	bpf_set_link_xdp_fd(internals->if_index, -1,
+			XDP_FLAGS_UPDATE_IF_NOEXIST);
+}
+
+static void
+eth_dev_close(struct rte_eth_dev *dev)
+{
+	struct pmd_internals *internals = dev->data->dev_private;
+	struct pkt_rx_queue *rxq;
+	int i;
+
+	AF_XDP_LOG(INFO, "Closing AF_XDP ethdev on numa socket %u\n",
+		rte_socket_id());
+
+	for (i = 0; i < ETH_AF_XDP_MAX_QUEUE_PAIRS; i++) {
+		rxq = &internals->rx_queues[i];
+		if (rxq->umem == NULL)
+			break;
+		xsk_socket__delete(rxq->xsk);
+	}
+
+	(void)xsk_umem__delete(internals->umem->umem);
+	remove_xdp_program(internals);
+}
+
+static void
+eth_queue_release(void *q __rte_unused)
+{
+}
+
+static int
+eth_link_update(struct rte_eth_dev *dev __rte_unused,
+		int wait_to_complete __rte_unused)
+{
+	return 0;
+}
+
+static void
+xdp_umem_destroy(struct xsk_umem_info *umem)
+{
+	rte_memzone_free(umem->mz);
+	umem->mz = NULL;
+
+	rte_ring_free(umem->buf_ring);
+	umem->buf_ring = NULL;
+
+	rte_free(umem);
+	umem = NULL;
+}
+
+static struct
+xsk_umem_info *xdp_umem_configure(void)
+{
+	struct xsk_umem_info *umem;
+	const struct rte_memzone *mz;
+	struct xsk_umem_config usr_config = {
+		.fill_size = ETH_AF_XDP_DFLT_NUM_DESCS,
+		.comp_size = ETH_AF_XDP_DFLT_NUM_DESCS,
+		.frame_size = ETH_AF_XDP_FRAME_SIZE,
+		.frame_headroom = ETH_AF_XDP_DATA_HEADROOM };
+	int ret;
+	uint64_t i;
+
+	umem = rte_zmalloc_socket("umem", sizeof(*umem), 0, rte_socket_id());
+	if (umem == NULL) {
+		AF_XDP_LOG(ERR, "Failed to allocate umem info");
+		return NULL;
+	}
+
+	umem->buf_ring = rte_ring_create("af_xdp_ring",
+					 ETH_AF_XDP_NUM_BUFFERS,
+					 rte_socket_id(),
+					 0x0);
+	if (umem->buf_ring == NULL) {
+		AF_XDP_LOG(ERR, "Failed to create rte_ring\n");
+		goto err;
+	}
+
+	for (i = 0; i < ETH_AF_XDP_NUM_BUFFERS; i++)
+		rte_ring_enqueue(umem->buf_ring,
+				 (void *)(i * ETH_AF_XDP_FRAME_SIZE +
+					  ETH_AF_XDP_DATA_HEADROOM));
+
+	mz = rte_memzone_reserve_aligned("af_xdp uemem",
+			ETH_AF_XDP_NUM_BUFFERS * ETH_AF_XDP_FRAME_SIZE,
+			rte_socket_id(), RTE_MEMZONE_IOVA_CONTIG,
+			getpagesize());
+	if (mz == NULL) {
+		AF_XDP_LOG(ERR, "Failed to reserve memzone for af_xdp umem.\n");
+		goto err;
+	}
+
+	ret = xsk_umem__create(&umem->umem, mz->addr,
+			       ETH_AF_XDP_NUM_BUFFERS * ETH_AF_XDP_FRAME_SIZE,
+			       &umem->fq, &umem->cq,
+			       &usr_config);
+
+	if (ret) {
+		AF_XDP_LOG(ERR, "Failed to create umem");
+		goto err;
+	}
+	umem->mz = mz;
+
+	return umem;
+
+err:
+	xdp_umem_destroy(umem);
+	return NULL;
+}
+
+static int
+xsk_configure(struct pmd_internals *internals, struct pkt_rx_queue *rxq,
+	      int ring_size)
+{
+	struct xsk_socket_config cfg;
+	struct pkt_tx_queue *txq = rxq->pair;
+	int ret = 0;
+	int reserve_size;
+
+	rxq->umem = xdp_umem_configure();
+	if (rxq->umem == NULL)
+		return -ENOMEM;
+
+	cfg.rx_size = ring_size;
+	cfg.tx_size = ring_size;
+	cfg.libbpf_flags = 0;
+	cfg.xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST;
+	cfg.bind_flags = 0;
+	ret = xsk_socket__create(&rxq->xsk, internals->if_name,
+			internals->queue_idx, rxq->umem->umem, &rxq->rx,
+			&txq->tx, &cfg);
+	if (ret) {
+		AF_XDP_LOG(ERR, "Failed to create xsk socket.\n");
+		goto err;
+	}
+
+	reserve_size = ETH_AF_XDP_DFLT_NUM_DESCS / 2;
+	ret = reserve_fill_queue(rxq->umem, reserve_size);
+	if (ret) {
+		xsk_socket__delete(rxq->xsk);
+		AF_XDP_LOG(ERR, "Failed to reserve fill queue.\n");
+		goto err;
+	}
+
+	return 0;
+
+err:
+	xdp_umem_destroy(rxq->umem);
+
+	return ret;
+}
+
+static void
+queue_reset(struct pmd_internals *internals, uint16_t queue_idx)
+{
+	struct pkt_rx_queue *rxq = &internals->rx_queues[queue_idx];
+	struct pkt_tx_queue *txq = rxq->pair;
+
+	memset(rxq, 0, sizeof(*rxq));
+	memset(txq, 0, sizeof(*txq));
+	rxq->pair = txq;
+	txq->pair = rxq;
+	rxq->queue_idx = queue_idx;
+	txq->queue_idx = queue_idx;
+}
+
+static int
+eth_rx_queue_setup(struct rte_eth_dev *dev,
+		   uint16_t rx_queue_id,
+		   uint16_t nb_rx_desc,
+		   unsigned int socket_id __rte_unused,
+		   const struct rte_eth_rxconf *rx_conf __rte_unused,
+		   struct rte_mempool *mb_pool)
+{
+	struct pmd_internals *internals = dev->data->dev_private;
+	uint32_t buf_size, data_size;
+	struct pkt_rx_queue *rxq;
+	int ret;
+
+	rxq = &internals->rx_queues[rx_queue_id];
+	queue_reset(internals, rx_queue_id);
+
+	/* Now get the space available for data in the mbuf */
+	buf_size = rte_pktmbuf_data_room_size(mb_pool) -
+		RTE_PKTMBUF_HEADROOM;
+	data_size = ETH_AF_XDP_FRAME_SIZE - ETH_AF_XDP_DATA_HEADROOM;
+
+	if (data_size > buf_size) {
+		AF_XDP_LOG(ERR, "%s: %d bytes will not fit in mbuf (%d bytes)\n",
+			dev->device->name, data_size, buf_size);
+		ret = -ENOMEM;
+		goto err;
+	}
+
+	rxq->mb_pool = mb_pool;
+
+	if (xsk_configure(internals, rxq, nb_rx_desc)) {
+		AF_XDP_LOG(ERR, "Failed to configure xdp socket\n");
+		ret = -EINVAL;
+		goto err;
+	}
+
+	internals->umem = rxq->umem;
+
+	dev->data->rx_queues[rx_queue_id] = rxq;
+	return 0;
+
+err:
+	queue_reset(internals, rx_queue_id);
+	return ret;
+}
+
+static int
+eth_tx_queue_setup(struct rte_eth_dev *dev,
+		   uint16_t tx_queue_id,
+		   uint16_t nb_tx_desc __rte_unused,
+		   unsigned int socket_id __rte_unused,
+		   const struct rte_eth_txconf *tx_conf __rte_unused)
+{
+	struct pmd_internals *internals = dev->data->dev_private;
+	struct pkt_tx_queue *txq;
+
+	txq = &internals->tx_queues[tx_queue_id];
+
+	dev->data->tx_queues[tx_queue_id] = txq;
+	return 0;
+}
+
+static int
+eth_dev_mtu_set(struct rte_eth_dev *dev, uint16_t mtu)
+{
+	struct pmd_internals *internals = dev->data->dev_private;
+	struct ifreq ifr = { .ifr_mtu = mtu };
+	int ret;
+	int s;
+
+	s = socket(PF_INET, SOCK_DGRAM, 0);
+	if (s < 0)
+		return -EINVAL;
+
+	strlcpy(ifr.ifr_name, internals->if_name, IFNAMSIZ);
+	ret = ioctl(s, SIOCSIFMTU, &ifr);
+	close(s);
+
+	return (ret < 0) ? -errno : 0;
+}
+
+static void
+eth_dev_change_flags(char *if_name, uint32_t flags, uint32_t mask)
+{
+	struct ifreq ifr;
+	int s;
+
+	s = socket(PF_INET, SOCK_DGRAM, 0);
+	if (s < 0)
+		return;
+
+	strlcpy(ifr.ifr_name, if_name, IFNAMSIZ);
+	if (ioctl(s, SIOCGIFFLAGS, &ifr) < 0)
+		goto out;
+	ifr.ifr_flags &= mask;
+	ifr.ifr_flags |= flags;
+	if (ioctl(s, SIOCSIFFLAGS, &ifr) < 0)
+		goto out;
+out:
+	close(s);
+}
+
+static void
+eth_dev_promiscuous_enable(struct rte_eth_dev *dev)
+{
+	struct pmd_internals *internals = dev->data->dev_private;
+
+	eth_dev_change_flags(internals->if_name, IFF_PROMISC, ~0);
+}
+
+static void
+eth_dev_promiscuous_disable(struct rte_eth_dev *dev)
+{
+	struct pmd_internals *internals = dev->data->dev_private;
+
+	eth_dev_change_flags(internals->if_name, 0, ~IFF_PROMISC);
+}
+
+static const struct eth_dev_ops ops = {
+	.dev_start = eth_dev_start,
+	.dev_stop = eth_dev_stop,
+	.dev_close = eth_dev_close,
+	.dev_configure = eth_dev_configure,
+	.dev_infos_get = eth_dev_info,
+	.mtu_set = eth_dev_mtu_set,
+	.promiscuous_enable = eth_dev_promiscuous_enable,
+	.promiscuous_disable = eth_dev_promiscuous_disable,
+	.rx_queue_setup = eth_rx_queue_setup,
+	.tx_queue_setup = eth_tx_queue_setup,
+	.rx_queue_release = eth_queue_release,
+	.tx_queue_release = eth_queue_release,
+	.link_update = eth_link_update,
+	.stats_get = eth_stats_get,
+	.stats_reset = eth_stats_reset,
+};
+
+/** parse integer from integer argument */
+static int
+parse_integer_arg(const char *key __rte_unused,
+		  const char *value, void *extra_args)
+{
+	int *i = (int *)extra_args;
+	char *end;
+
+	*i = strtol(value, &end, 10);
+	if (*i < 0) {
+		AF_XDP_LOG(ERR, "Argument has to be positive.\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+/** parse name argument */
+static int
+parse_name_arg(const char *key __rte_unused,
+	       const char *value, void *extra_args)
+{
+	char *name = extra_args;
+
+	if (strnlen(value, IFNAMSIZ) > IFNAMSIZ - 1) {
+		AF_XDP_LOG(ERR, "Invalid name %s, should be less than %u bytes.\n",
+			   value, IFNAMSIZ);
+		return -EINVAL;
+	}
+
+	strlcpy(name, value, IFNAMSIZ);
+
+	return 0;
+}
+
+static int
+parse_parameters(struct rte_kvargs *kvlist,
+		 char *if_name,
+		 int *queue_idx)
+{
+	int ret;
+
+	ret = rte_kvargs_process(kvlist, ETH_AF_XDP_IFACE_ARG,
+				 &parse_name_arg, if_name);
+	if (ret < 0)
+		goto free_kvlist;
+
+	ret = rte_kvargs_process(kvlist, ETH_AF_XDP_QUEUE_IDX_ARG,
+				 &parse_integer_arg, queue_idx);
+	if (ret < 0)
+		goto free_kvlist;
+
+free_kvlist:
+	rte_kvargs_free(kvlist);
+	return ret;
+}
+
+static int
+get_iface_info(const char *if_name,
+	       struct ether_addr *eth_addr,
+	       int *if_index)
+{
+	struct ifreq ifr;
+	int sock = socket(AF_INET, SOCK_DGRAM, IPPROTO_IP);
+
+	if (sock < 0)
+		return -1;
+
+	strlcpy(ifr.ifr_name, if_name, IFNAMSIZ);
+	if (ioctl(sock, SIOCGIFINDEX, &ifr))
+		goto error;
+
+	*if_index = ifr.ifr_ifindex;
+
+	if (ioctl(sock, SIOCGIFHWADDR, &ifr))
+		goto error;
+
+	rte_memcpy(eth_addr, ifr.ifr_hwaddr.sa_data, ETHER_ADDR_LEN);
+
+	close(sock);
+	return 0;
+
+error:
+	close(sock);
+	return -1;
+}
+
+static struct rte_eth_dev *
+init_internals(struct rte_vdev_device *dev,
+	       const char *if_name,
+	       int queue_idx)
+{
+	const char *name = rte_vdev_device_name(dev);
+	const unsigned int numa_node = dev->device.numa_node;
+	struct pmd_internals *internals;
+	struct rte_eth_dev *eth_dev;
+	int ret;
+	int i;
+
+	internals = rte_zmalloc_socket(name, sizeof(*internals), 0, numa_node);
+	if (internals == NULL)
+		return NULL;
+
+	internals->queue_idx = queue_idx;
+	strlcpy(internals->if_name, if_name, IFNAMSIZ);
+
+	for (i = 0; i < ETH_AF_XDP_MAX_QUEUE_PAIRS; i++) {
+		internals->tx_queues[i].pair = &internals->rx_queues[i];
+		internals->rx_queues[i].pair = &internals->tx_queues[i];
+	}
+
+	ret = get_iface_info(if_name, &internals->eth_addr,
+			     &internals->if_index);
+	if (ret)
+		goto err;
+
+	eth_dev = rte_eth_vdev_allocate(dev, 0);
+	if (eth_dev == NULL)
+		goto err;
+
+	eth_dev->data->dev_private = internals;
+	eth_dev->data->dev_link = pmd_link;
+	eth_dev->data->mac_addrs = &internals->eth_addr;
+	eth_dev->dev_ops = &ops;
+	eth_dev->rx_pkt_burst = eth_af_xdp_rx;
+	eth_dev->tx_pkt_burst = eth_af_xdp_tx;
+
+	return eth_dev;
+
+err:
+	rte_free(internals);
+	return NULL;
+}
+
+static int
+rte_pmd_af_xdp_probe(struct rte_vdev_device *dev)
+{
+	struct rte_kvargs *kvlist;
+	char if_name[IFNAMSIZ] = {'\0'};
+	int xsk_queue_idx = ETH_AF_XDP_DFLT_QUEUE_IDX;
+	struct rte_eth_dev *eth_dev = NULL;
+	const char *name;
+
+	AF_XDP_LOG(INFO, "Initializing pmd_af_xdp for %s\n",
+		rte_vdev_device_name(dev));
+
+	name = rte_vdev_device_name(dev);
+	if (rte_eal_process_type() == RTE_PROC_SECONDARY &&
+		strlen(rte_vdev_device_args(dev)) == 0) {
+		eth_dev = rte_eth_dev_attach_secondary(name);
+		if (eth_dev == NULL) {
+			AF_XDP_LOG(ERR, "Failed to probe %s\n", name);
+			return -EINVAL;
+		}
+		eth_dev->dev_ops = &ops;
+		rte_eth_dev_probing_finish(eth_dev);
+		return 0;
+	}
+
+	kvlist = rte_kvargs_parse(rte_vdev_device_args(dev), valid_arguments);
+	if (kvlist == NULL) {
+		AF_XDP_LOG(ERR, "Invalid kvargs key\n");
+		return -EINVAL;
+	}
+
+	if (dev->device.numa_node == SOCKET_ID_ANY)
+		dev->device.numa_node = rte_socket_id();
+
+	if (parse_parameters(kvlist, if_name, &xsk_queue_idx) < 0) {
+		AF_XDP_LOG(ERR, "Invalid kvargs value\n");
+		return -EINVAL;
+	}
+
+	if (strlen(if_name) == 0) {
+		AF_XDP_LOG(ERR, "Network interface must be specified\n");
+		return -EINVAL;
+	}
+
+	eth_dev = init_internals(dev, if_name, xsk_queue_idx);
+	if (eth_dev == NULL) {
+		AF_XDP_LOG(ERR, "Failed to init internals\n");
+		return -1;
+	}
+
+	rte_eth_dev_probing_finish(eth_dev);
+
+	return 0;
+}
+
+static int
+rte_pmd_af_xdp_remove(struct rte_vdev_device *dev)
+{
+	struct rte_eth_dev *eth_dev = NULL;
+	struct pmd_internals *internals;
+
+	AF_XDP_LOG(INFO, "Removing AF_XDP ethdev on numa socket %u\n",
+		rte_socket_id());
+
+	if (dev == NULL)
+		return -1;
+
+	/* find the ethdev entry */
+	eth_dev = rte_eth_dev_allocated(rte_vdev_device_name(dev));
+	if (eth_dev == NULL)
+		return -1;
+
+	internals = eth_dev->data->dev_private;
+
+	rte_ring_free(internals->umem->buf_ring);
+	rte_memzone_free(internals->umem->mz);
+	rte_free(internals->umem);
+
+	rte_eth_dev_release_port(eth_dev);
+
+
+	return 0;
+}
+
+static struct rte_vdev_driver pmd_af_xdp_drv = {
+	.probe = rte_pmd_af_xdp_probe,
+	.remove = rte_pmd_af_xdp_remove,
+};
+
+RTE_PMD_REGISTER_VDEV(net_af_xdp, pmd_af_xdp_drv);
+RTE_PMD_REGISTER_PARAM_STRING(net_af_xdp,
+			      "iface=<string> "
+			      "queue=<int> ");
+
+RTE_INIT(af_xdp_init_log)
+{
+	af_xdp_logtype = rte_log_register("pmd.net.af_xdp");
+	if (af_xdp_logtype >= 0)
+		rte_log_set_level(af_xdp_logtype, RTE_LOG_NOTICE);
+}
diff --git a/drivers/net/af_xdp/rte_pmd_af_xdp_version.map b/drivers/net/af_xdp/rte_pmd_af_xdp_version.map
new file mode 100644
index 000000000..c6db030fe
--- /dev/null
+++ b/drivers/net/af_xdp/rte_pmd_af_xdp_version.map
@@ -0,0 +1,3 @@
+DPDK_19.05 {
+	local: *;
+};
diff --git a/drivers/net/meson.build b/drivers/net/meson.build
index 3ecc78cee..1105e72d8 100644
--- a/drivers/net/meson.build
+++ b/drivers/net/meson.build
@@ -2,6 +2,7 @@
 # Copyright(c) 2017 Intel Corporation
 
 drivers = ['af_packet',
+	'af_xdp',
 	'ark',
 	'atlantic',
 	'avp',
diff --git a/mk/rte.app.mk b/mk/rte.app.mk
index 262132fc6..f916bc9ef 100644
--- a/mk/rte.app.mk
+++ b/mk/rte.app.mk
@@ -143,6 +143,7 @@ _LDLIBS-$(CONFIG_RTE_LIBRTE_DPAA2_MEMPOOL)  += -lrte_mempool_dpaa2
 endif
 
 _LDLIBS-$(CONFIG_RTE_LIBRTE_PMD_AF_PACKET)  += -lrte_pmd_af_packet
+_LDLIBS-$(CONFIG_RTE_LIBRTE_PMD_AF_XDP)     += -lrte_pmd_af_xdp -lbpf
 _LDLIBS-$(CONFIG_RTE_LIBRTE_ARK_PMD)        += -lrte_pmd_ark
 _LDLIBS-$(CONFIG_RTE_LIBRTE_ATLANTIC_PMD)   += -lrte_pmd_atlantic
 _LDLIBS-$(CONFIG_RTE_LIBRTE_AVP_PMD)        += -lrte_pmd_avp
-- 
2.17.1