DPDK patches and discussions
 help / color / mirror / Atom feed
From: Qi Zhang <qi.z.zhang@intel.com>
To: dev@dpdk.org
Cc: magnus.karlsson@intel.com, bjorn.topel@intel.com,
	Qi Zhang <qi.z.zhang@intel.com>
Subject: [dpdk-dev] [RFC v2 1/7] net/af_xdp: new PMD driver
Date: Thu,  8 Mar 2018 21:52:43 +0800	[thread overview]
Message-ID: <20180308135249.28187-2-qi.z.zhang@intel.com> (raw)
In-Reply-To: <20180308135249.28187-1-qi.z.zhang@intel.com>

This is the vanilla version.
Packet data will copy between af_xdp memory buffer and mbuf mempool.
indexes of memory buffer is simply managed by a fifo ring.

Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
---
 config/common_base                            |   5 +
 config/common_linuxapp                        |   1 +
 drivers/net/Makefile                          |   1 +
 drivers/net/af_xdp/Makefile                   |  26 +
 drivers/net/af_xdp/meson.build                |   7 +
 drivers/net/af_xdp/rte_eth_af_xdp.c           | 760 ++++++++++++++++++++++++++
 drivers/net/af_xdp/rte_pmd_af_xdp_version.map |   4 +
 drivers/net/af_xdp/xdpsock_queue.h            |  66 +++
 mk/rte.app.mk                                 |   1 +
 9 files changed, 871 insertions(+)
 create mode 100644 drivers/net/af_xdp/Makefile
 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
 create mode 100644 drivers/net/af_xdp/xdpsock_queue.h

diff --git a/config/common_base b/config/common_base
index ad03cf433..84b7b3b7e 100644
--- a/config/common_base
+++ b/config/common_base
@@ -368,6 +368,11 @@ 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
 #
 CONFIG_RTE_LIBRTE_PMD_BOND=y
diff --git a/config/common_linuxapp b/config/common_linuxapp
index ff98f2355..3b10695b6 100644
--- a/config/common_linuxapp
+++ b/config/common_linuxapp
@@ -16,6 +16,7 @@ CONFIG_RTE_LIBRTE_VHOST=y
 CONFIG_RTE_LIBRTE_VHOST_NUMA=y
 CONFIG_RTE_LIBRTE_PMD_VHOST=y
 CONFIG_RTE_LIBRTE_PMD_AF_PACKET=y
+CONFIG_RTE_LIBRTE_PMD_AF_XDP=y
 CONFIG_RTE_LIBRTE_PMD_TAP=y
 CONFIG_RTE_LIBRTE_AVP_PMD=y
 CONFIG_RTE_LIBRTE_VDEV_NETVSC_PMD=y
diff --git a/drivers/net/Makefile b/drivers/net/Makefile
index e1127326b..409234ac3 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_AVF_PMD) += avf
 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..990073655
--- /dev/null
+++ b/drivers/net/af_xdp/Makefile
@@ -0,0 +1,26 @@
+# SPDX-License-Identifier: BSD-3-Clause
+# Copyright(c) 2018 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 -I/opt/af_xdp/linux_headers/include
+CFLAGS += $(WERROR_FLAGS)
+LDLIBS += -lrte_eal -lrte_mbuf -lrte_mempool -lrte_ring
+LDLIBS += -lrte_ethdev -lrte_net -lrte_kvargs
+LDLIBS += -lrte_bus_vdev
+
+#
+# all source are stored in SRCS-y
+#
+SRCS-$(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/meson.build b/drivers/net/af_xdp/meson.build
new file mode 100644
index 000000000..4b6652685
--- /dev/null
+++ b/drivers/net/af_xdp/meson.build
@@ -0,0 +1,7 @@
+# SPDX-License-Identifier: BSD-3-Clause
+# Copyright(c) 2018 Intel Corporation
+
+if host_machine.system() != 'linux'
+	build = false
+endif
+sources = files('rte_eth_af_xdp.c')
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..5c7c53aeb
--- /dev/null
+++ b/drivers/net/af_xdp/rte_eth_af_xdp.c
@@ -0,0 +1,760 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2018 Intel Corporation.
+ */
+
+#include <rte_mbuf.h>
+#include <rte_ethdev_driver.h>
+#include <rte_ethdev_vdev.h>
+#include <rte_malloc.h>
+#include <rte_kvargs.h>
+#include <rte_bus_vdev.h>
+
+#include <linux/if_ether.h>
+#include <linux/if_xdp.h>
+#include <arpa/inet.h>
+#include <net/if.h>
+#include <sys/types.h>
+#include <sys/socket.h>
+#include <sys/ioctl.h>
+#include <sys/mman.h>
+#include <unistd.h>
+#include <poll.h>
+#include "xdpsock_queue.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
+
+#define ETH_AF_XDP_IFACE_ARG		"iface"
+#define ETH_AF_XDP_QUEUE_IDX_ARG	"queue"
+#define ETH_AF_XDP_RING_SIZE_ARG	"ringsz"
+
+#define ETH_AF_XDP_FRAME_SIZE		2048
+#define ETH_AF_XDP_NUM_BUFFERS		131072
+#define ETH_AF_XDP_DATA_HEADROOM	0
+#define ETH_AF_XDP_DFLT_RING_SIZE	1024
+#define ETH_AF_XDP_DFLT_QUEUE_IDX	0
+
+#define ETH_AF_XDP_RX_BATCH_SIZE	32
+#define ETH_AF_XDP_TX_BATCH_SIZE	32
+
+struct xdp_umem {
+	char *buffer;
+	size_t size;
+	unsigned int frame_size;
+	unsigned int frame_size_log2;
+	unsigned int nframes;
+	int mr_fd;
+};
+
+struct pmd_internals {
+	int sfd;
+	int if_index;
+	char if_name[IFNAMSIZ];
+	struct ether_addr eth_addr;
+	struct xdp_queue rx;
+	struct xdp_queue tx;
+	struct xdp_umem *umem;
+	struct rte_mempool *mb_pool;
+
+	unsigned long rx_pkts;
+	unsigned long rx_bytes;
+	unsigned long rx_dropped;
+
+	unsigned long tx_pkts;
+	unsigned long err_pkts;
+	unsigned long tx_bytes;
+
+	uint16_t port_id;
+	uint16_t queue_idx;
+	int ring_size;
+	struct rte_ring *buf_ring;
+};
+
+static const char * const valid_arguments[] = {
+	ETH_AF_XDP_IFACE_ARG,
+	ETH_AF_XDP_QUEUE_IDX_ARG,
+	ETH_AF_XDP_RING_SIZE_ARG,
+	NULL
+};
+
+static 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 void *get_pkt_data(struct pmd_internals *internals,
+			  uint32_t index,
+			  uint32_t offset)
+{
+	return (void *)(internals->umem->buffer +
+			(index << internals->umem->frame_size_log2) + offset);
+}
+
+static uint16_t
+eth_af_xdp_rx(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts)
+{
+	struct pmd_internals *internals = queue;
+	struct xdp_queue *rxq = &internals->rx;
+	struct rte_mbuf *mbuf;
+	unsigned long dropped = 0;
+	unsigned long rx_bytes = 0;
+	uint16_t count = 0;
+
+	nb_pkts = nb_pkts < ETH_AF_XDP_RX_BATCH_SIZE ?
+		  nb_pkts : ETH_AF_XDP_RX_BATCH_SIZE;
+
+	struct xdp_desc descs[ETH_AF_XDP_RX_BATCH_SIZE];
+	void *indexes[ETH_AF_XDP_RX_BATCH_SIZE];
+	int rcvd, i;
+
+	/* fill rx ring */
+	if (rxq->num_free >= ETH_AF_XDP_RX_BATCH_SIZE) {
+		int n = rte_ring_dequeue_bulk(internals->buf_ring,
+					      indexes,
+					      ETH_AF_XDP_RX_BATCH_SIZE,
+					      NULL);
+		for (i = 0; i < n; i++)
+			descs[i].idx = (uint32_t)((long int)indexes[i]);
+		xq_enq(rxq, descs, n);
+	}
+
+	/* read data */
+	rcvd = xq_deq(rxq, descs, nb_pkts);
+	if (rcvd == 0)
+		return 0;
+
+	for (i = 0; i < rcvd; i++) {
+		char *pkt;
+		uint32_t idx = descs[i].idx;
+
+		mbuf = rte_pktmbuf_alloc(internals->mb_pool);
+		rte_pktmbuf_pkt_len(mbuf) =
+			rte_pktmbuf_data_len(mbuf) =
+			descs[i].len;
+		if (mbuf) {
+			pkt = get_pkt_data(internals, idx, descs[i].offset);
+			memcpy(rte_pktmbuf_mtod(mbuf, void *),
+			       pkt, descs[i].len);
+			rx_bytes += descs[i].len;
+			bufs[count++] = mbuf;
+		} else {
+			dropped++;
+		}
+		indexes[i] = (void *)((long int)idx);
+	}
+
+	rte_ring_enqueue_bulk(internals->buf_ring, indexes, rcvd, NULL);
+
+	internals->rx_pkts += (rcvd - dropped);
+	internals->rx_bytes += rx_bytes;
+	internals->rx_dropped += dropped;
+
+	return count;
+}
+
+static void kick_tx(int fd)
+{
+	int ret;
+
+	for (;;) {
+		ret = sendto(fd, NULL, 0, MSG_DONTWAIT, NULL, 0);
+		if (ret >= 0 || errno == ENOBUFS)
+			return;
+		if (errno == EAGAIN)
+			continue;
+	}
+}
+
+static uint16_t
+eth_af_xdp_tx(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts)
+{
+	struct pmd_internals *internals = queue;
+	struct xdp_queue *txq = &internals->tx;
+	struct rte_mbuf *mbuf;
+	struct xdp_desc descs[ETH_AF_XDP_TX_BATCH_SIZE];
+	void *indexes[ETH_AF_XDP_TX_BATCH_SIZE];
+	uint16_t i, valid;
+	unsigned long tx_bytes = 0;
+
+	nb_pkts = nb_pkts < ETH_AF_XDP_TX_BATCH_SIZE ?
+		  nb_pkts : ETH_AF_XDP_TX_BATCH_SIZE;
+
+	if (txq->num_free < ETH_AF_XDP_TX_BATCH_SIZE * 2) {
+		int n = xq_deq(txq, descs, ETH_AF_XDP_TX_BATCH_SIZE);
+
+		for (i = 0; i < n; i++)
+			indexes[i] = (void *)((long int)descs[i].idx);
+		rte_ring_enqueue_bulk(internals->buf_ring, indexes, n, NULL);
+	}
+
+	nb_pkts = nb_pkts > txq->num_free ? txq->num_free : nb_pkts;
+	nb_pkts = rte_ring_dequeue_bulk(internals->buf_ring, indexes,
+					nb_pkts, NULL);
+
+	valid = 0;
+	for (i = 0; i < nb_pkts; i++) {
+		char *pkt;
+		unsigned int buf_len =
+			internals->umem->frame_size - ETH_AF_XDP_DATA_HEADROOM;
+		mbuf = bufs[i];
+		if (mbuf->pkt_len <= buf_len) {
+			descs[valid].idx = (uint32_t)((long int)indexes[valid]);
+			descs[valid].offset = ETH_AF_XDP_DATA_HEADROOM;
+			descs[valid].flags = 0;
+			descs[valid].len = mbuf->pkt_len;
+			pkt = get_pkt_data(internals, descs[i].idx,
+					   descs[i].offset);
+			memcpy(pkt, rte_pktmbuf_mtod(mbuf, void *),
+			       descs[i].len);
+			valid++;
+			tx_bytes += mbuf->pkt_len;
+		}
+		/* packet will be consumed anyway */
+		rte_pktmbuf_free(mbuf);
+	}
+
+	xq_enq(txq, descs, valid);
+	kick_tx(internals->sfd);
+
+	if (valid < nb_pkts)
+		rte_ring_enqueue_bulk(internals->buf_ring, &indexes[valid],
+				      nb_pkts - valid, NULL);
+
+	internals->err_pkts += (nb_pkts - valid);
+	internals->tx_pkts += valid;
+	internals->tx_bytes += tx_bytes;
+
+	return nb_pkts;
+}
+
+static void
+fill_rx_desc(struct pmd_internals *internals)
+{
+	int num_free = internals->rx.num_free;
+	void *p = NULL;
+	int i;
+
+	for (i = 0; i < num_free; i++) {
+		struct xdp_desc desc = {};
+
+		rte_ring_dequeue(internals->buf_ring, &p);
+		desc.idx = (uint32_t)((long int)p);
+		xq_enq(&internals->rx, &desc, 1);
+	}
+}
+
+static int
+eth_dev_start(struct rte_eth_dev *dev)
+{
+	struct pmd_internals *internals = dev->data->dev_private;
+
+	dev->data->dev_link.link_status = ETH_LINK_UP;
+	fill_rx_desc(internals);
+
+	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 __rte_unused)
+{
+	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 = (uint32_t)ETH_FRAME_LEN;
+	dev_info->max_rx_queues = 1;
+	dev_info->max_tx_queues = 1;
+	dev_info->min_rx_bufsize = 0;
+}
+
+static int
+eth_stats_get(struct rte_eth_dev *dev, struct rte_eth_stats *stats)
+{
+	const struct pmd_internals *internals = dev->data->dev_private;
+
+	stats->ipackets = stats->q_ipackets[0] =
+		internals->rx_pkts;
+	stats->ibytes = stats->q_ibytes[0] =
+		internals->rx_bytes;
+	stats->imissed =
+		internals->rx_dropped;
+
+	stats->opackets = stats->q_opackets[0]
+		= internals->tx_pkts;
+	stats->oerrors = stats->q_errors[0] =
+		internals->err_pkts;
+	stats->obytes = stats->q_obytes[0] =
+		internals->tx_bytes;
+
+	return 0;
+}
+
+static void
+eth_stats_reset(struct rte_eth_dev *dev)
+{
+	struct pmd_internals *internals = dev->data->dev_private;
+
+	internals->rx_pkts = 0;
+	internals->rx_bytes = 0;
+	internals->rx_dropped = 0;
+
+	internals->tx_pkts = 0;
+	internals->err_pkts = 0;
+	internals->tx_bytes = 0;
+}
+
+static void
+eth_dev_close(struct rte_eth_dev *dev __rte_unused)
+{
+}
+
+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 struct xdp_umem *xsk_alloc_and_mem_reg_buffers(int sfd, size_t nbuffers)
+{
+	struct xdp_mr_req req = { .frame_size = ETH_AF_XDP_FRAME_SIZE,
+				  .data_headroom = ETH_AF_XDP_DATA_HEADROOM };
+	struct xdp_umem *umem;
+	void *bufs;
+	int ret;
+
+	ret = posix_memalign((void **)&bufs, getpagesize(),
+			     nbuffers * req.frame_size);
+	if (ret)
+		return NULL;
+
+	umem = calloc(1, sizeof(*umem));
+	if (!umem) {
+		free(bufs);
+		return NULL;
+	}
+
+	req.addr = (unsigned long)bufs;
+	req.len = nbuffers * req.frame_size;
+	ret = setsockopt(sfd, SOL_XDP, XDP_MEM_REG, &req, sizeof(req));
+	RTE_ASSERT(ret == 0);
+
+	umem->frame_size = ETH_AF_XDP_FRAME_SIZE;
+	umem->frame_size_log2 = 11;
+	umem->buffer = bufs;
+	umem->size = nbuffers * req.frame_size;
+	umem->nframes = nbuffers;
+	umem->mr_fd = sfd;
+
+	return umem;
+}
+
+static int
+xdp_configure(struct pmd_internals *internals)
+{
+	struct sockaddr_xdp sxdp;
+	struct xdp_ring_req req;
+	char ring_name[0x100];
+	int ret = 0;
+	long int i;
+
+	snprintf(ring_name, 0x100, "%s_%s_%d", "af_xdp_ring",
+		 internals->if_name, internals->queue_idx);
+	internals->buf_ring = rte_ring_create(ring_name,
+					      ETH_AF_XDP_NUM_BUFFERS,
+					      SOCKET_ID_ANY,
+					      0x0);
+	if (!internals->buf_ring)
+		return -1;
+
+	for (i = 0; i < ETH_AF_XDP_NUM_BUFFERS; i++)
+		rte_ring_enqueue(internals->buf_ring, (void *)i);
+
+	internals->umem = xsk_alloc_and_mem_reg_buffers(internals->sfd,
+							ETH_AF_XDP_NUM_BUFFERS);
+	if (!internals->umem)
+		goto error;
+
+	req.mr_fd = internals->umem->mr_fd;
+	req.desc_nr = internals->ring_size;
+
+	ret = setsockopt(internals->sfd, SOL_XDP, XDP_RX_RING,
+			 &req, sizeof(req));
+
+	RTE_ASSERT(ret == 0);
+
+	ret = setsockopt(internals->sfd, SOL_XDP, XDP_TX_RING,
+			 &req, sizeof(req));
+
+	RTE_ASSERT(ret == 0);
+
+	internals->rx.ring = mmap(0, req.desc_nr * sizeof(struct xdp_desc),
+				  PROT_READ | PROT_WRITE,
+				  MAP_SHARED | MAP_LOCKED | MAP_POPULATE,
+				  internals->sfd,
+				  XDP_PGOFF_RX_RING);
+	RTE_ASSERT(internals->rx.ring != MAP_FAILED);
+
+	internals->rx.num_free = req.desc_nr;
+	internals->rx.ring_mask = req.desc_nr - 1;
+
+	internals->tx.ring = mmap(0, req.desc_nr * sizeof(struct xdp_desc),
+				  PROT_READ | PROT_WRITE,
+				  MAP_SHARED | MAP_LOCKED | MAP_POPULATE,
+				  internals->sfd,
+				  XDP_PGOFF_TX_RING);
+	RTE_ASSERT(internals->tx.ring != MAP_FAILED);
+
+	internals->tx.num_free = req.desc_nr;
+	internals->tx.ring_mask = req.desc_nr - 1;
+
+	sxdp.sxdp_family = PF_XDP;
+	sxdp.sxdp_ifindex = internals->if_index;
+	sxdp.sxdp_queue_id = internals->queue_idx;
+
+	ret = bind(internals->sfd, (struct sockaddr *)&sxdp, sizeof(sxdp));
+	RTE_ASSERT(ret == 0);
+
+	return ret;
+error:
+	rte_ring_free(internals->buf_ring);
+	internals->buf_ring = NULL;
+	return -1;
+}
+
+static int
+eth_rx_queue_setup(struct rte_eth_dev *dev,
+		   uint16_t rx_queue_id,
+		   uint16_t nb_rx_desc __rte_unused,
+		   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;
+	unsigned int buf_size, data_size;
+
+	RTE_ASSERT(rx_queue_id == 0);
+	internals->mb_pool = mb_pool;
+	xdp_configure(internals);
+
+	/* Now get the space available for data in the mbuf */
+	buf_size = rte_pktmbuf_data_room_size(internals->mb_pool) -
+		RTE_PKTMBUF_HEADROOM;
+	data_size = internals->umem->frame_size;
+
+	if (data_size > buf_size) {
+		RTE_LOG(ERR, PMD,
+			"%s: %d bytes will not fit in mbuf (%d bytes)\n",
+			dev->device->name, data_size, buf_size);
+		return -ENOMEM;
+	}
+
+	dev->data->rx_queues[rx_queue_id] = internals;
+	return 0;
+}
+
+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;
+
+	RTE_ASSERT(tx_queue_id == 0);
+	dev->data->tx_queues[tx_queue_id] = internals;
+	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;
+
+	snprintf(ifr.ifr_name, IFNAMSIZ, "%s", internals->if_name);
+	ret = ioctl(s, SIOCSIFMTU, &ifr);
+	close(s);
+
+	if (ret < 0)
+		return -EINVAL;
+
+	return 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;
+
+	snprintf(ifr.ifr_name, IFNAMSIZ, "%s", if_name);
+	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,
+};
+
+static struct rte_vdev_driver pmd_af_xdp_drv;
+
+static void
+parse_parameters(struct rte_kvargs *kvlist,
+		 char **if_name,
+		 int *queue_idx,
+		 int *ring_size)
+{
+	struct rte_kvargs_pair *pair = NULL;
+	unsigned int k_idx;
+
+	for (k_idx = 0; k_idx < kvlist->count; k_idx++) {
+		pair = &kvlist->pairs[k_idx];
+		if (strstr(pair->key, ETH_AF_XDP_IFACE_ARG))
+			*if_name = pair->value;
+		else if (strstr(pair->key, ETH_AF_XDP_QUEUE_IDX_ARG))
+			*queue_idx = atoi(pair->value);
+		else if (strstr(pair->key, ETH_AF_XDP_RING_SIZE_ARG))
+			*ring_size = atoi(pair->value);
+	}
+}
+
+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;
+
+	strcpy(ifr.ifr_name, if_name);
+	if (ioctl(sock, SIOCGIFINDEX, &ifr))
+		goto error;
+	*if_index = ifr.ifr_ifindex;
+
+	if (ioctl(sock, SIOCGIFHWADDR, &ifr))
+		goto error;
+
+	memcpy(eth_addr, ifr.ifr_hwaddr.sa_data, 6);
+
+	close(sock);
+	return 0;
+
+error:
+	close(sock);
+	return -1;
+}
+
+static int
+init_internals(struct rte_vdev_device *dev,
+	       const char *if_name,
+	       int queue_idx,
+	       int ring_size)
+{
+	const char *name = rte_vdev_device_name(dev);
+	struct rte_eth_dev *eth_dev = NULL;
+	struct rte_eth_dev_data *data = NULL;
+	const unsigned int numa_node = dev->device.numa_node;
+	struct pmd_internals *internals = NULL;
+	int ret;
+
+	data = rte_zmalloc_socket(name, sizeof(*internals), 0, numa_node);
+	if (!data)
+		return -1;
+
+	internals = rte_zmalloc_socket(name, sizeof(*internals), 0, numa_node);
+	if (!internals)
+		goto error_1;
+
+	internals->queue_idx = queue_idx;
+	internals->ring_size = ring_size;
+	strcpy(internals->if_name, if_name);
+	internals->sfd = socket(PF_XDP, SOCK_RAW, 0);
+	if (internals->sfd < 0)
+		goto error_2;
+
+	ret = get_iface_info(if_name, &internals->eth_addr,
+			     &internals->if_index);
+	if (ret)
+		goto error_3;
+
+	eth_dev = rte_eth_vdev_allocate(dev, 0);
+	if (!eth_dev)
+		goto error_3;
+
+	rte_memcpy(data, eth_dev->data, sizeof(*data));
+	internals->port_id = eth_dev->data->port_id;
+	data->dev_private = internals;
+	data->nb_rx_queues = 1;
+	data->nb_tx_queues = 1;
+	data->dev_link = pmd_link;
+	data->mac_addrs = &internals->eth_addr;
+
+	eth_dev->data = data;
+	eth_dev->dev_ops = &ops;
+
+	eth_dev->rx_pkt_burst = eth_af_xdp_rx;
+	eth_dev->tx_pkt_burst = eth_af_xdp_tx;
+
+	return 0;
+
+error_3:
+	close(internals->sfd);
+
+error_2:
+	rte_free(internals);
+
+error_1:
+	rte_free(data);
+	return -1;
+}
+
+static int
+rte_pmd_af_xdp_probe(struct rte_vdev_device *dev)
+{
+	struct rte_kvargs *kvlist;
+	char *if_name = NULL;
+	int ring_size = ETH_AF_XDP_DFLT_RING_SIZE;
+	int queue_idx = ETH_AF_XDP_DFLT_QUEUE_IDX;
+	int ret;
+
+	RTE_LOG(INFO, PMD, "Initializing pmd_af_packet for %s\n",
+		rte_vdev_device_name(dev));
+
+	kvlist = rte_kvargs_parse(rte_vdev_device_args(dev), valid_arguments);
+	if (!kvlist) {
+		RTE_LOG(ERR, PMD,
+			"Invalid kvargs");
+		return -1;
+	}
+
+	if (dev->device.numa_node == SOCKET_ID_ANY)
+		dev->device.numa_node = rte_socket_id();
+
+	parse_parameters(kvlist, &if_name, &queue_idx, &ring_size);
+
+	ret = init_internals(dev, if_name, queue_idx, ring_size);
+	rte_kvargs_free(kvlist);
+
+	return ret;
+}
+
+static int
+rte_pmd_af_xdp_remove(struct rte_vdev_device *dev)
+{
+	struct rte_eth_dev *eth_dev = NULL;
+	struct pmd_internals *internals;
+
+	RTE_LOG(INFO, PMD, "Closing AF_XDP ethdev on numa socket %u\n",
+		rte_socket_id());
+
+	if (!dev)
+		return -1;
+
+	/* find the ethdev entry */
+	eth_dev = rte_eth_dev_allocated(rte_vdev_device_name(dev));
+	if (!eth_dev)
+		return -1;
+
+	internals = eth_dev->data->dev_private;
+	rte_ring_free(internals->buf_ring);
+	rte_free(internals->umem);
+	rte_free(eth_dev->data->dev_private);
+	rte_free(eth_dev->data);
+	close(internals->sfd);
+
+	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_ALIAS(net_af_xdp, eth_af_xdp);
+RTE_PMD_REGISTER_PARAM_STRING(net_af_xdp,
+			      "iface=<string> "
+			      "queue=<int> "
+			      "ringsz=<int> ");
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..ef3539840
--- /dev/null
+++ b/drivers/net/af_xdp/rte_pmd_af_xdp_version.map
@@ -0,0 +1,4 @@
+DPDK_2.0 {
+
+	local: *;
+};
diff --git a/drivers/net/af_xdp/xdpsock_queue.h b/drivers/net/af_xdp/xdpsock_queue.h
new file mode 100644
index 000000000..c5d0cb56a
--- /dev/null
+++ b/drivers/net/af_xdp/xdpsock_queue.h
@@ -0,0 +1,66 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2018 Intel Corporation.
+ */
+
+#ifndef __XDPSOCK_QUEUE_H
+#define __XDPSOCK_QUEUE_H
+
+static inline int xq_enq(struct xdp_queue *q,
+			 const struct xdp_desc *descs,
+			 unsigned int ndescs)
+{
+	unsigned int avail_idx = q->avail_idx;
+	unsigned int i;
+	int j;
+
+	if (q->num_free < ndescs)
+		return -ENOSPC;
+
+	q->num_free -= ndescs;
+
+	for (i = 0; i < ndescs; i++) {
+		unsigned int idx = avail_idx++ & q->ring_mask;
+
+		q->ring[idx].idx	= descs[i].idx;
+		q->ring[idx].len	= descs[i].len;
+		q->ring[idx].offset	= descs[i].offset;
+		q->ring[idx].error	= 0;
+	}
+	rte_smp_wmb();
+
+	for (j = ndescs - 1; j >= 0; j--) {
+		unsigned int idx = (q->avail_idx + j) & q->ring_mask;
+
+		q->ring[idx].flags = descs[j].flags | XDP_DESC_KERNEL;
+	}
+	q->avail_idx += ndescs;
+
+	return 0;
+}
+
+static inline int xq_deq(struct xdp_queue *q,
+			 struct xdp_desc *descs,
+			 int ndescs)
+{
+	unsigned int idx, last_used_idx = q->last_used_idx;
+	int i, entries = 0;
+
+	for (i = 0; i < ndescs; i++) {
+		idx = (last_used_idx++) & q->ring_mask;
+		if (q->ring[idx].flags & XDP_DESC_KERNEL)
+			break;
+		entries++;
+	}
+	q->num_free += entries;
+
+	rte_smp_rmb();
+
+	for (i = 0; i < entries; i++) {
+		idx = q->last_used_idx++ & q->ring_mask;
+		descs[i] = q->ring[idx];
+	}
+
+	return entries;
+}
+
+#endif /* __XDPSOCK_QUEUE_H */
diff --git a/mk/rte.app.mk b/mk/rte.app.mk
index 3eb41d176..bc26e1457 100644
--- a/mk/rte.app.mk
+++ b/mk/rte.app.mk
@@ -120,6 +120,7 @@ ifeq ($(CONFIG_RTE_BUILD_SHARED_LIB),n)
 _LDLIBS-$(CONFIG_RTE_DRIVER_MEMPOOL_STACK)  += -lrte_mempool_stack
 
 _LDLIBS-$(CONFIG_RTE_LIBRTE_PMD_AF_PACKET)  += -lrte_pmd_af_packet
+_LDLIBS-$(CONFIG_RTE_LIBRTE_PMD_AF_XDP)     += -lrte_pmd_af_xdp
 _LDLIBS-$(CONFIG_RTE_LIBRTE_ARK_PMD)        += -lrte_pmd_ark
 _LDLIBS-$(CONFIG_RTE_LIBRTE_AVF_PMD)        += -lrte_pmd_avf
 _LDLIBS-$(CONFIG_RTE_LIBRTE_AVP_PMD)        += -lrte_pmd_avp
-- 
2.13.6

  reply	other threads:[~2018-03-08 13:52 UTC|newest]

Thread overview: 11+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-03-08 13:52 [dpdk-dev] [RFC v2 0/7] PMD driver for AF_XDP Qi Zhang
2018-03-08 13:52 ` Qi Zhang [this message]
2018-03-08 13:52 ` [dpdk-dev] [RFC v2 2/7] lib/mbuf: enable parse flags when create mempool Qi Zhang
2018-03-08 13:52 ` [dpdk-dev] [RFC v2 3/7] lib/mempool: allow page size aligned mempool Qi Zhang
2018-03-08 13:52 ` [dpdk-dev] [RFC v2 4/7] net/af_xdp: use mbuf mempool for buffer management Qi Zhang
2018-03-08 13:52 ` [dpdk-dev] [RFC v2 5/7] net/af_xdp: enable share mempool Qi Zhang
2018-03-08 13:52 ` [dpdk-dev] [RFC v2 6/7] net/af_xdp: load BPF file Qi Zhang
2018-03-08 14:20   ` Zhang, Qi Z
2018-03-08 23:15   ` Stephen Hemminger
2018-05-09  7:02     ` Björn Töpel
2018-03-08 13:52 ` [dpdk-dev] [RFC v2 7/7] app/testpmd: enable parameter for mempool flags Qi Zhang

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20180308135249.28187-2-qi.z.zhang@intel.com \
    --to=qi.z.zhang@intel.com \
    --cc=bjorn.topel@intel.com \
    --cc=dev@dpdk.org \
    --cc=magnus.karlsson@intel.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).