[v2,1/6] net/af_xdp: introduce AF XDP PMD driver
Checks
Commit Message
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 | 6 +
config/common_base | 5 +
config/common_linux | 1 +
doc/guides/nics/af_xdp.rst | 45 +
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 | 33 +
drivers/net/af_xdp/meson.build | 21 +
drivers/net/af_xdp/rte_eth_af_xdp.c | 930 ++++++++++++++++++
drivers/net/af_xdp/rte_pmd_af_xdp_version.map | 3 +
drivers/net/meson.build | 1 +
mk/rte.app.mk | 1 +
14 files changed, 1066 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/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
Comments
On 2019-03-19 08:12, Xiaolong Ye wrote:
> 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 | 6 +
> config/common_base | 5 +
> config/common_linux | 1 +
> doc/guides/nics/af_xdp.rst | 45 +
> 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 | 33 +
> drivers/net/af_xdp/meson.build | 21 +
> drivers/net/af_xdp/rte_eth_af_xdp.c | 930 ++++++++++++++++++
> drivers/net/af_xdp/rte_pmd_af_xdp_version.map | 3 +
> drivers/net/meson.build | 1 +
> mk/rte.app.mk | 1 +
> 14 files changed, 1066 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/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 452b8eb82..1cc54b439 100644
> --- a/MAINTAINERS
> +++ b/MAINTAINERS
> @@ -468,6 +468,12 @@ 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/features/af_xdp.rst
> +
> 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 0b09a9348..4044de205 100644
> --- a/config/common_base
> +++ b/config/common_base
> @@ -416,6 +416,11 @@ 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/config/common_linux b/config/common_linux
> index 75334273d..0b1249da0 100644
> --- a/config/common_linux
> +++ b/config/common_linux
> @@ -19,6 +19,7 @@ CONFIG_RTE_LIBRTE_VHOST_POSTCOPY=n
> CONFIG_RTE_LIBRTE_PMD_VHOST=y
> CONFIG_RTE_LIBRTE_IFC_PMD=y
> CONFIG_RTE_LIBRTE_PMD_AF_PACKET=y
> +CONFIG_RTE_LIBRTE_PMD_AF_XDP=y
> CONFIG_RTE_LIBRTE_PMD_SOFTNIC=y
> CONFIG_RTE_LIBRTE_PMD_TAP=y
> CONFIG_RTE_LIBRTE_AVP_PMD=y
> diff --git a/doc/guides/nics/af_xdp.rst b/doc/guides/nics/af_xdp.rst
> new file mode 100644
> index 000000000..dd5654dd1
> --- /dev/null
> +++ b/doc/guides/nics/af_xdp.rst
> @@ -0,0 +1,45 @@
> +.. SPDX-License-Identifier: BSD-3-Clause
> + Copyright(c) 2018 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.
> +
> +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 > 4.18) with XDP sockets configuration enabled;
> +* libbpf (within kernel version > 5.1) with latest af_xdp support installed
> +* 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 eth_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..7b8fcce00
> --- /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
> \ No newline at end of file
> 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 61a2c7383..062facf89 100644
> --- a/doc/guides/rel_notes/release_19_05.rst
> +++ b/doc/guides/rel_notes/release_19_05.rst
> @@ -65,6 +65,13 @@ 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..6cf0ed7db
> --- /dev/null
> +++ b/drivers/net/af_xdp/Makefile
> @@ -0,0 +1,33 @@
> +# 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
> +
> +# require kernel version >= v5.1-rc1
> +LINUX_VERSION := $(shell uname -r)
> +CFLAGS += -I/lib/modules/$(LINUX_VERSION)/build/tools/include
> +CFLAGS += -I/lib/modules/$(LINUX_VERSION)/build/tools/lib/bpf
> +
> +CFLAGS += $(WERROR_FLAGS)
> +LDLIBS += -lrte_eal -lrte_mbuf -lrte_mempool -lrte_ring
> +LDLIBS += -lrte_ethdev -lrte_net -lrte_kvargs
> +LDLIBS += -lrte_bus_vdev
> +LDLIBS += -lbpf
> +
> +#
> +# all source are stored in SRCS-y
> +#
> +SRCS-$(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/meson.build b/drivers/net/af_xdp/meson.build
> new file mode 100644
> index 000000000..635e67483
> --- /dev/null
> +++ b/drivers/net/af_xdp/meson.build
> @@ -0,0 +1,21 @@
> +# SPDX-License-Identifier: BSD-3-Clause
> +# Copyright(c) 2018 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)
> + 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..96dedc0c4
> --- /dev/null
> +++ b/drivers/net/af_xdp/rte_eth_af_xdp.c
> @@ -0,0 +1,930 @@
> +/* SPDX-License-Identifier: BSD-3-Clause
> + * Copyright(c) 2019 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 <rte_string_fns.h>
> +
> +#include <linux/if_ether.h>
> +#include <linux/if_xdp.h>
> +#include <linux/if_link.h>
> +#include <asm/barrier.h>
Is this include used?
> +#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 <bpf/bpf.h>
> +#include <xsk.h>
> +
> +#define RTE_LOGTYPE_AF_XDP RTE_LOGTYPE_USER1
> +#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_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;
> + void *buffer;
> +};
> +
> +struct pkt_rx_queue {
> + struct xsk_ring_cons rx;
> + struct xsk_umem_info *umem;
> + struct xsk_socket *xsk;
> + struct rte_mempool *mb_pool;
> +
> + uint64_t rx_pkts;
> + uint64_t rx_bytes;
> + uint64_t rx_dropped;
> +
> + struct pkt_tx_queue *pair;
> + uint16_t queue_idx;
> +};
> +
> +struct pkt_tx_queue {
> + struct xsk_ring_prod tx;
> +
> + uint64_t tx_pkts;
> + uint64_t err_pkts;
> + uint64_t tx_bytes;
> +
> + 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];
> +};
> +
> +static const char * const valid_arguments[] = {
> + ETH_AF_XDP_IFACE_ARG,
> + ETH_AF_XDP_QUEUE_IDX_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 inline int
> +reserve_fill_queue(struct xsk_umem_info *umem, int reserve_size)
> +{
> + struct xsk_ring_prod *fq = &umem->fq;
> + uint32_t idx;
> + void *addr = NULL;
> + int i, ret = 0;
No need to initialize 'ret'. Is there a point to set 'addr'?
> +
> + ret = xsk_ring_prod__reserve(fq, reserve_size, &idx);
> + if (!ret) {
> + RTE_LOG(ERR, AF_XDP, "Failed to reserve enough fq descs.\n");
> + return ret;
> + }
> +
> + for (i = 0; i < reserve_size; i++) {
> + rte_ring_dequeue(umem->buf_ring, &addr);
> + *xsk_ring_prod__fill_addr(fq, idx++) = (uint64_t)addr;
Consider introducing a tmp variable to make this more readable.
> + }
> +
> + xsk_ring_prod__submit(fq, reserve_size);
> +
> + 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;
> + uint32_t free_thresh = fq->size >> 1;
> + struct rte_mbuf *mbuf;
> + unsigned long dropped = 0;
> + unsigned long rx_bytes = 0;
> + uint16_t count = 0;
> + int rcvd, i;
> +
> + nb_pkts = nb_pkts < ETH_AF_XDP_RX_BATCH_SIZE ?
> + nb_pkts : ETH_AF_XDP_RX_BATCH_SIZE;
> +
> + rcvd = xsk_ring_cons__peek(rx, nb_pkts, &idx_rx); > + if (!rcvd)
Since peek returns the number of entries, not a boolean, do:
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);
> +
> + for (i = 0; i < rcvd; i++) {
> + uint64_t addr = xsk_ring_cons__rx_desc(rx, idx_rx)->addr;
> + uint32_t len = xsk_ring_cons__rx_desc(rx, idx_rx++)->len;
Use a tmp variable, instead of two calls.
> + char *pkt = xsk_umem__get_data(rxq->umem->buffer, addr);
> +
Don't mix declaration and code. Why is this a char pointer? As opppose
to void.
> + mbuf = rte_pktmbuf_alloc(rxq->mb_pool);
> + if (mbuf) {
1.8.1
> + memcpy(rte_pktmbuf_mtod(mbuf, void*), pkt, len);
rte_memcpy()
> + rte_pktmbuf_pkt_len(mbuf) =
> + rte_pktmbuf_data_len(mbuf) = len;
Consider splitting this into two statements.
> + rx_bytes += len;
> + bufs[count++] = mbuf;
> + } else {
> + dropped++;
> + }
> + rte_ring_enqueue(umem->buf_ring, (void *)addr);
> + }
> +
> + xsk_ring_cons__release(rx, rcvd);
> +
> + /* statistics */
> + rxq->rx_pkts += (rcvd - dropped);
> + rxq->rx_bytes += rx_bytes;
> + rxq->rx_dropped += dropped;
> +
> + return count;
> +}
> +
> +static void pull_umem_cq(struct xsk_umem_info *umem, int size)
> +{
> + struct xsk_ring_cons *cq = &umem->cq;
> + int i, n;
> + uint32_t idx_cq;
> + uint64_t addr;
> +
> + n = xsk_ring_cons__peek(cq, size, &idx_cq);
Use size_t for n.
> + if (n > 0) {
> + for (i = 0; i < n; i++) {
Consider declaring 'addr' in this scope.
> + 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;
> + int ret;
> +
> + while (1) {
for (;;)
> + ret = sendto(xsk_socket__fd(txq->pair->xsk), NULL, 0,
> + MSG_DONTWAIT, NULL, 0);
> +
> + /* everything is ok */
> + if (ret >= 0)
Use likely()?
> + break;
> +
> + /* some thing unexpected */
> + if (errno != EBUSY && errno != EAGAIN)
> + break;
> +
> + /* pull from complete qeueu 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 = nb_pkts < ETH_AF_XDP_TX_BATCH_SIZE ?
> + nb_pkts : ETH_AF_XDP_TX_BATCH_SIZE;
Use RTE_MIN().
> +
> + pull_umem_cq(umem, nb_pkts);
> +
> + nb_pkts = rte_ring_dequeue_bulk(umem->buf_ring, addrs,
> + nb_pkts, NULL);
> + if (!nb_pkts)
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;
> + char *pkt;
Use void pointer?
> + unsigned int buf_len = ETH_AF_XDP_FRAME_SIZE
> + - ETH_AF_XDP_DATA_HEADROOM;
Use uint32_t, as you seem to do elsewhere.
> + 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->buffer,
> + desc->addr);
> + memcpy(pkt, rte_pktmbuf_mtod(mbuf, void *),
> + desc->len);
rte_memcpy()
> + 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->err_pkts += nb_pkts - valid;
> + txq->tx_pkts += valid;
> + txq->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 __rte_unused)
> +{
> + /* 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 = (uint32_t)ETH_FRAME_LEN;
> + dev_info->max_rx_queues = 1;
> + dev_info->max_tx_queues = 1;
> + dev_info->min_rx_bufsize = 0;
> +
> + 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;
> +
> + optlen = sizeof(struct xdp_statistics);
> + for (i = 0; i < dev->data->nb_rx_queues; i++) {
> + rxq = &internals->rx_queues[i];
> + stats->q_ipackets[i] = internals->rx_queues[i].rx_pkts;
> + stats->q_ibytes[i] = internals->rx_queues[i].rx_bytes;
> +
> + stats->q_opackets[i] = internals->tx_queues[i].tx_pkts;
> + stats->q_obytes[i] = internals->tx_queues[i].tx_bytes;
> +
> + stats->ipackets += stats->q_ipackets[i];
> + stats->ibytes += stats->q_ibytes[i];
> + stats->imissed += internals->rx_queues[i].rx_dropped;
> + getsockopt(xsk_socket__fd(rxq->xsk), SOL_XDP, XDP_STATISTICS,
> + &xdp_stats, &optlen);
> + stats->imissed += xdp_stats.rx_dropped;
> +
> + stats->opackets += stats->q_opackets[i];
> + stats->oerrors += stats->q_errors[i];
> + stats->oerrors += internals->tx_queues[i].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++) {
> + internals->rx_queues[i].rx_pkts = 0;
> + internals->rx_queues[i].rx_bytes = 0;
> + internals->rx_queues[i].rx_dropped = 0;
> +
> + internals->tx_queues[i].tx_pkts = 0;
> + internals->tx_queues[i].err_pkts = 0;
> + internals->tx_queues[i].tx_bytes = 0;
> + }
> +}
> +
> +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)) {
> + RTE_LOG(ERR, AF_XDP, "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;
> +
> + RTE_LOG(INFO, AF_XDP, "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)
> + 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)
> +{
> + free(umem->buffer);
> + umem->buffer = NULL;
> +
> + rte_ring_free(umem->buf_ring);
> + umem->buf_ring = NULL;
> +
> + free(umem);
> + umem = NULL;
> +}
> +
> +static struct xsk_umem_info *xdp_umem_configure(void)
> +{
> + struct xsk_umem_info *umem;
> + 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 };
> + void *bufs = NULL;
> + char ring_name[0x100];
> + int ret;
> + uint64_t i;
> +
> + umem = calloc(1, sizeof(*umem));
> + if (!umem) {
1.8.1
> + RTE_LOG(ERR, AF_XDP, "Failed to allocate umem info");
> + return NULL;
> + }
> +
> + snprintf(ring_name, 0x100, "af_xdp_ring");
Again the magical 0x100.
> + umem->buf_ring = rte_ring_create(ring_name,
> + ETH_AF_XDP_NUM_BUFFERS,
> + SOCKET_ID_ANY,
> + 0x0);
> + if (!umem->buf_ring) {
1.8.1
> + RTE_LOG(ERR, AF_XDP,
> + "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));
> +
> + if (posix_memalign(&bufs, getpagesize(),
> + ETH_AF_XDP_NUM_BUFFERS * ETH_AF_XDP_FRAME_SIZE)) {
> + RTE_LOG(ERR, AF_XDP, "Failed to allocate memory pool.\n");
> + goto err;
> + }
> + ret = xsk_umem__create(&umem->umem, bufs,
> + ETH_AF_XDP_NUM_BUFFERS * ETH_AF_XDP_FRAME_SIZE,
> + &umem->fq, &umem->cq,
> + &usr_config);
> +
> + if (ret) {
> + RTE_LOG(ERR, AF_XDP, "Failed to create umem");
> + goto err;
> + }
> + umem->buffer = bufs;
> +
> + 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) {
1.8.1
> + ret = -ENOMEM;
> + goto err;
> + }
> +
> + 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) {
> + RTE_LOG(ERR, AF_XDP, "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) {
> + RTE_LOG(ERR, AF_XDP, "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;
> + int xsk_fd = xsk_socket__fd(rxq->xsk);
> +
> + if (xsk_fd) {
> + close(xsk_fd);
> + if (internals->umem) {
1.8.1
> + xdp_umem_destroy(internals->umem);
> + internals->umem = NULL;
> + }
> + }
> + 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;
> + unsigned int buf_size, data_size;
uint32_t
> + struct pkt_rx_queue *rxq;
> + int ret = 0;
No need to set 'ret'. Alternatively, restructure so you always return '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) {
> + RTE_LOG(ERR, AF_XDP,
> + "%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)) {
> + RTE_LOG(ERR, AF_XDP,
> + "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);
> +
> + 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;
> +
> + 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;
> +
> + *i = atoi(value);
Use strtol().
> + if (*i < 0) {
> + RTE_LOG(ERR, AF_XDP, "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 (strlen(value) > IFNAMSIZ) {
The buffer is IFNAMSIZ bytes (which it should be), so it can't hold a
string with strlen() == IFNAMSIZ.
> + RTE_LOG(ERR, AF_XDP, "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 = 0;
Should not be initialized.
> +
> + 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;
I fail to see the point of this goto, but maybe there's more code to
follow in future patches.
> +
> +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 (ioctl(sock, SIOCGIFHWADDR, &ifr))
> + goto error;
> +
> + rte_memcpy(eth_addr, ifr.ifr_hwaddr.sa_data, ETHER_ADDR_LEN);
> +
> + close(sock);
> + *if_index = if_nametoindex(if_name);
> + return 0;
> +
> +error:
> + close(sock);
> + return -1;
> +}
> +
> +static int
> +init_internals(struct rte_vdev_device *dev,
> + const char *if_name,
> + int queue_idx,
> + struct rte_eth_dev **eth_dev)
> +{
> + const char *name = rte_vdev_device_name(dev);
> + const unsigned int numa_node = dev->device.numa_node;
> + struct pmd_internals *internals = NULL;
> + int ret;
> + int i;
> +
> + internals = rte_zmalloc_socket(name, sizeof(*internals), 0, numa_node);
> + if (!internals)
1.8.1
> + return -ENOMEM;
> +
> + 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)
1.8.1
> + 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 0;
> +
> +err:
> + rte_free(internals);
> + return -1;
> +}
> +
> +static int
> +rte_pmd_af_xdp_probe(struct rte_vdev_device *dev)
> +{
> + struct rte_kvargs *kvlist;
> + char if_name[IFNAMSIZ];
> + int xsk_queue_idx = ETH_AF_XDP_DFLT_QUEUE_IDX;
> + struct rte_eth_dev *eth_dev = NULL;
> + const char *name;
> + int ret;
> +
> + RTE_LOG(INFO, AF_XDP, "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) {
> + RTE_LOG(ERR, AF_XDP, "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) {
> + RTE_LOG(ERR, AF_XDP, "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) {
> + RTE_LOG(ERR, AF_XDP, "Invalid kvargs value\n");
> + return -EINVAL;
> + }
> +
> + ret = init_internals(dev, if_name, xsk_queue_idx, ð_dev);
> + if (ret) {
> + RTE_LOG(ERR, AF_XDP, "Failed to init internals\n");
> + return ret;
> + }
> +
> + 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;
> +
> + RTE_LOG(INFO, AF_XDP, "Removing 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->umem->buf_ring);
> + rte_free(internals->umem->buffer);
> + 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(eth_af_xdp, pmd_af_xdp_drv);
> +RTE_PMD_REGISTER_PARAM_STRING(eth_af_xdp,
> + "iface=<string> "
> + "queue=<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..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..be0af73cc 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 -lelf -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
>
Hi, Mattias
Thanks for your comments.
On 03/19, Mattias Rönnblom wrote:
>On 2019-03-19 08:12, Xiaolong Ye wrote:
>> 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 | 6 +
>> config/common_base | 5 +
>> config/common_linux | 1 +
>> doc/guides/nics/af_xdp.rst | 45 +
>> 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 | 33 +
>> drivers/net/af_xdp/meson.build | 21 +
>> drivers/net/af_xdp/rte_eth_af_xdp.c | 930 ++++++++++++++++++
>> drivers/net/af_xdp/rte_pmd_af_xdp_version.map | 3 +
>> drivers/net/meson.build | 1 +
>> mk/rte.app.mk | 1 +
>> 14 files changed, 1066 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/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 452b8eb82..1cc54b439 100644
>> --- a/MAINTAINERS
>> +++ b/MAINTAINERS
>> @@ -468,6 +468,12 @@ 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/features/af_xdp.rst
>> +
>> 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 0b09a9348..4044de205 100644
>> --- a/config/common_base
>> +++ b/config/common_base
>> @@ -416,6 +416,11 @@ 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/config/common_linux b/config/common_linux
>> index 75334273d..0b1249da0 100644
>> --- a/config/common_linux
>> +++ b/config/common_linux
>> @@ -19,6 +19,7 @@ CONFIG_RTE_LIBRTE_VHOST_POSTCOPY=n
>> CONFIG_RTE_LIBRTE_PMD_VHOST=y
>> CONFIG_RTE_LIBRTE_IFC_PMD=y
>> CONFIG_RTE_LIBRTE_PMD_AF_PACKET=y
>> +CONFIG_RTE_LIBRTE_PMD_AF_XDP=y
>> CONFIG_RTE_LIBRTE_PMD_SOFTNIC=y
>> CONFIG_RTE_LIBRTE_PMD_TAP=y
>> CONFIG_RTE_LIBRTE_AVP_PMD=y
>> diff --git a/doc/guides/nics/af_xdp.rst b/doc/guides/nics/af_xdp.rst
>> new file mode 100644
>> index 000000000..dd5654dd1
>> --- /dev/null
>> +++ b/doc/guides/nics/af_xdp.rst
>> @@ -0,0 +1,45 @@
>> +.. SPDX-License-Identifier: BSD-3-Clause
>> + Copyright(c) 2018 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.
>> +
>> +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 > 4.18) with XDP sockets configuration enabled;
>> +* libbpf (within kernel version > 5.1) with latest af_xdp support installed
>> +* 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 eth_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..7b8fcce00
>> --- /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
>> \ No newline at end of file
>> 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 61a2c7383..062facf89 100644
>> --- a/doc/guides/rel_notes/release_19_05.rst
>> +++ b/doc/guides/rel_notes/release_19_05.rst
>> @@ -65,6 +65,13 @@ 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..6cf0ed7db
>> --- /dev/null
>> +++ b/drivers/net/af_xdp/Makefile
>> @@ -0,0 +1,33 @@
>> +# 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
>> +
>> +# require kernel version >= v5.1-rc1
>> +LINUX_VERSION := $(shell uname -r)
>> +CFLAGS += -I/lib/modules/$(LINUX_VERSION)/build/tools/include
>> +CFLAGS += -I/lib/modules/$(LINUX_VERSION)/build/tools/lib/bpf
>> +
>> +CFLAGS += $(WERROR_FLAGS)
>> +LDLIBS += -lrte_eal -lrte_mbuf -lrte_mempool -lrte_ring
>> +LDLIBS += -lrte_ethdev -lrte_net -lrte_kvargs
>> +LDLIBS += -lrte_bus_vdev
>> +LDLIBS += -lbpf
>> +
>> +#
>> +# all source are stored in SRCS-y
>> +#
>> +SRCS-$(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/meson.build b/drivers/net/af_xdp/meson.build
>> new file mode 100644
>> index 000000000..635e67483
>> --- /dev/null
>> +++ b/drivers/net/af_xdp/meson.build
>> @@ -0,0 +1,21 @@
>> +# SPDX-License-Identifier: BSD-3-Clause
>> +# Copyright(c) 2018 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)
>> + 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..96dedc0c4
>> --- /dev/null
>> +++ b/drivers/net/af_xdp/rte_eth_af_xdp.c
>> @@ -0,0 +1,930 @@
>> +/* SPDX-License-Identifier: BSD-3-Clause
>> + * Copyright(c) 2019 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 <rte_string_fns.h>
>> +
>> +#include <linux/if_ether.h>
>> +#include <linux/if_xdp.h>
>> +#include <linux/if_link.h>
>> +#include <asm/barrier.h>
>
>Is this include used?
Yes, this is needed by xsk.h below which calls smp_wmb() & smp_rmb().
>
>> +#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 <bpf/bpf.h>
>> +#include <xsk.h>
>> +
>> +#define RTE_LOGTYPE_AF_XDP RTE_LOGTYPE_USER1
>> +#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_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;
>> + void *buffer;
>> +};
>> +
>> +struct pkt_rx_queue {
>> + struct xsk_ring_cons rx;
>> + struct xsk_umem_info *umem;
>> + struct xsk_socket *xsk;
>> + struct rte_mempool *mb_pool;
>> +
>> + uint64_t rx_pkts;
>> + uint64_t rx_bytes;
>> + uint64_t rx_dropped;
>> +
>> + struct pkt_tx_queue *pair;
>> + uint16_t queue_idx;
>> +};
>> +
>> +struct pkt_tx_queue {
>> + struct xsk_ring_prod tx;
>> +
>> + uint64_t tx_pkts;
>> + uint64_t err_pkts;
>> + uint64_t tx_bytes;
>> +
>> + 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];
>> +};
>> +
>> +static const char * const valid_arguments[] = {
>> + ETH_AF_XDP_IFACE_ARG,
>> + ETH_AF_XDP_QUEUE_IDX_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 inline int
>> +reserve_fill_queue(struct xsk_umem_info *umem, int reserve_size)
>> +{
>> + struct xsk_ring_prod *fq = &umem->fq;
>> + uint32_t idx;
>> + void *addr = NULL;
>> + int i, ret = 0;
>
>No need to initialize 'ret'. Is there a point to set 'addr'?
Ok, I'll keep it uninitialized.
addr needs be set otherwise there would be a build error:
drivers/net/af_xdp/rte_eth_af_xdp.c:129:40: error: ‘addr’ may be used uninitialized in this function [-Werror=maybe-uninitialized]
*xsk_ring_prod__fill_addr(fq, idx++) = (uint64_t)addr;
^
>
>> +
>> + ret = xsk_ring_prod__reserve(fq, reserve_size, &idx);
>> + if (!ret) {
>> + RTE_LOG(ERR, AF_XDP, "Failed to reserve enough fq descs.\n");
>> + return ret;
>> + }
>> +
>> + for (i = 0; i < reserve_size; i++) {
>> + rte_ring_dequeue(umem->buf_ring, &addr);
>> + *xsk_ring_prod__fill_addr(fq, idx++) = (uint64_t)addr;
>
>Consider introducing a tmp variable to make this more readable.
Got it.
>
>> + }
>> +
>> + xsk_ring_prod__submit(fq, reserve_size);
>> +
>> + 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;
>> + uint32_t free_thresh = fq->size >> 1;
>> + struct rte_mbuf *mbuf;
>> + unsigned long dropped = 0;
>> + unsigned long rx_bytes = 0;
>> + uint16_t count = 0;
>> + int rcvd, i;
>> +
>> + nb_pkts = nb_pkts < ETH_AF_XDP_RX_BATCH_SIZE ?
>> + nb_pkts : ETH_AF_XDP_RX_BATCH_SIZE;
>> +
>> + rcvd = xsk_ring_cons__peek(rx, nb_pkts, &idx_rx); > + if (!rcvd)
>
>Since peek returns the number of entries, not a boolean, do:
>rcvd == 0
Got it.
>
>> + return 0;
>> +
>> + if (xsk_prod_nb_free(fq, free_thresh) >= free_thresh)
>> + (void)reserve_fill_queue(umem, ETH_AF_XDP_RX_BATCH_SIZE);
>> +
>> + for (i = 0; i < rcvd; i++) {
>> + uint64_t addr = xsk_ring_cons__rx_desc(rx, idx_rx)->addr;
>> + uint32_t len = xsk_ring_cons__rx_desc(rx, idx_rx++)->len;
>
>Use a tmp variable, instead of two calls.
Got it.
>
>> + char *pkt = xsk_umem__get_data(rxq->umem->buffer, addr);
>> +
>
>Don't mix declaration and code. Why is this a char pointer? As opppose to
>void.
I'll split the declaration and code.
pkt should be a void *, will correct it in next version.
>
>> + mbuf = rte_pktmbuf_alloc(rxq->mb_pool);
>> + if (mbuf) {
>
>1.8.1
Got it.
>
>> + memcpy(rte_pktmbuf_mtod(mbuf, void*), pkt, len);
>
>rte_memcpy()
Got it.
>
>> + rte_pktmbuf_pkt_len(mbuf) =
>> + rte_pktmbuf_data_len(mbuf) = len;
>
>Consider splitting this into two statements.
Got it.
>
>> + rx_bytes += len;
>> + bufs[count++] = mbuf;
>> + } else {
>> + dropped++;
>> + }
>> + rte_ring_enqueue(umem->buf_ring, (void *)addr);
>> + }
>> +
>> + xsk_ring_cons__release(rx, rcvd);
>> +
>> + /* statistics */
>> + rxq->rx_pkts += (rcvd - dropped);
>> + rxq->rx_bytes += rx_bytes;
>> + rxq->rx_dropped += dropped;
>> +
>> + return count;
>> +}
>> +
>> +static void pull_umem_cq(struct xsk_umem_info *umem, int size)
>> +{
>> + struct xsk_ring_cons *cq = &umem->cq;
>> + int i, n;
>> + uint32_t idx_cq;
>> + uint64_t addr;
>> +
>> + n = xsk_ring_cons__peek(cq, size, &idx_cq);
>
>Use size_t for n.
Got it.
>
>> + if (n > 0) {
>> + for (i = 0; i < n; i++) {
>
>Consider declaring 'addr' in this scope.
Got it.
>
>> + 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;
>> + int ret;
>> +
>> + while (1) {
>
>for (;;)
Got it, is it a preference in DPDK convention for loop?
>
>> + ret = sendto(xsk_socket__fd(txq->pair->xsk), NULL, 0,
>> + MSG_DONTWAIT, NULL, 0);
>> +
>> + /* everything is ok */
>> + if (ret >= 0)
>
>Use likely()?
Got it.
>
>> + break;
>> +
>> + /* some thing unexpected */
>> + if (errno != EBUSY && errno != EAGAIN)
>> + break;
>> +
>> + /* pull from complete qeueu 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 = nb_pkts < ETH_AF_XDP_TX_BATCH_SIZE ?
>> + nb_pkts : ETH_AF_XDP_TX_BATCH_SIZE;
>
>Use RTE_MIN().
Got it.
>
>> +
>> + pull_umem_cq(umem, nb_pkts);
>> +
>> + nb_pkts = rte_ring_dequeue_bulk(umem->buf_ring, addrs,
>> + nb_pkts, NULL);
>> + if (!nb_pkts)
>
>nb_pkts == 0
Got it.
>
>> + 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;
>> + char *pkt;
>
>Use void pointer?
Got it.
>
>> + unsigned int buf_len = ETH_AF_XDP_FRAME_SIZE
>> + - ETH_AF_XDP_DATA_HEADROOM;
>
>Use uint32_t, as you seem to do elsewhere.
Got it.
>
>> + 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->buffer,
>> + desc->addr);
>> + memcpy(pkt, rte_pktmbuf_mtod(mbuf, void *),
>> + desc->len);
>
>rte_memcpy()
Got it.
>
>> + 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->err_pkts += nb_pkts - valid;
>> + txq->tx_pkts += valid;
>> + txq->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 __rte_unused)
>> +{
>> + /* 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 = (uint32_t)ETH_FRAME_LEN;
>> + dev_info->max_rx_queues = 1;
>> + dev_info->max_tx_queues = 1;
>> + dev_info->min_rx_bufsize = 0;
>> +
>> + 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;
>> +
>> + optlen = sizeof(struct xdp_statistics);
>> + for (i = 0; i < dev->data->nb_rx_queues; i++) {
>> + rxq = &internals->rx_queues[i];
>> + stats->q_ipackets[i] = internals->rx_queues[i].rx_pkts;
>> + stats->q_ibytes[i] = internals->rx_queues[i].rx_bytes;
>> +
>> + stats->q_opackets[i] = internals->tx_queues[i].tx_pkts;
>> + stats->q_obytes[i] = internals->tx_queues[i].tx_bytes;
>> +
>> + stats->ipackets += stats->q_ipackets[i];
>> + stats->ibytes += stats->q_ibytes[i];
>> + stats->imissed += internals->rx_queues[i].rx_dropped;
>> + getsockopt(xsk_socket__fd(rxq->xsk), SOL_XDP, XDP_STATISTICS,
>> + &xdp_stats, &optlen);
>> + stats->imissed += xdp_stats.rx_dropped;
>> +
>> + stats->opackets += stats->q_opackets[i];
>> + stats->oerrors += stats->q_errors[i];
>> + stats->oerrors += internals->tx_queues[i].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++) {
>> + internals->rx_queues[i].rx_pkts = 0;
>> + internals->rx_queues[i].rx_bytes = 0;
>> + internals->rx_queues[i].rx_dropped = 0;
>> +
>> + internals->tx_queues[i].tx_pkts = 0;
>> + internals->tx_queues[i].err_pkts = 0;
>> + internals->tx_queues[i].tx_bytes = 0;
>> + }
>> +}
>> +
>> +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)) {
>> + RTE_LOG(ERR, AF_XDP, "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;
>> +
>> + RTE_LOG(INFO, AF_XDP, "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)
>> + 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)
>> +{
>> + free(umem->buffer);
>> + umem->buffer = NULL;
>> +
>> + rte_ring_free(umem->buf_ring);
>> + umem->buf_ring = NULL;
>> +
>> + free(umem);
>> + umem = NULL;
>> +}
>> +
>> +static struct xsk_umem_info *xdp_umem_configure(void)
>> +{
>> + struct xsk_umem_info *umem;
>> + 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 };
>> + void *bufs = NULL;
>> + char ring_name[0x100];
>> + int ret;
>> + uint64_t i;
>> +
>> + umem = calloc(1, sizeof(*umem));
>> + if (!umem) {
>
>1.8.1
Got it.
>
>> + RTE_LOG(ERR, AF_XDP, "Failed to allocate umem info");
>> + return NULL;
>> + }
>> +
>> + snprintf(ring_name, 0x100, "af_xdp_ring");
>
>Again the magical 0x100.
Will correct it.
>
>> + umem->buf_ring = rte_ring_create(ring_name,
>> + ETH_AF_XDP_NUM_BUFFERS,
>> + SOCKET_ID_ANY,
>> + 0x0);
>> + if (!umem->buf_ring) {
>
>1.8.1
Got it.
>
>> + RTE_LOG(ERR, AF_XDP,
>> + "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));
>> +
>> + if (posix_memalign(&bufs, getpagesize(),
>> + ETH_AF_XDP_NUM_BUFFERS * ETH_AF_XDP_FRAME_SIZE)) {
>> + RTE_LOG(ERR, AF_XDP, "Failed to allocate memory pool.\n");
>> + goto err;
>> + }
>> + ret = xsk_umem__create(&umem->umem, bufs,
>> + ETH_AF_XDP_NUM_BUFFERS * ETH_AF_XDP_FRAME_SIZE,
>> + &umem->fq, &umem->cq,
>> + &usr_config);
>> +
>> + if (ret) {
>> + RTE_LOG(ERR, AF_XDP, "Failed to create umem");
>> + goto err;
>> + }
>> + umem->buffer = bufs;
>> +
>> + 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) {
>
>1.8.1
Got it.
>
>> + ret = -ENOMEM;
>> + goto err;
>> + }
>> +
>> + 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) {
>> + RTE_LOG(ERR, AF_XDP, "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) {
>> + RTE_LOG(ERR, AF_XDP, "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;
>> + int xsk_fd = xsk_socket__fd(rxq->xsk);
>> +
>> + if (xsk_fd) {
>> + close(xsk_fd);
>> + if (internals->umem) {
>
>1.8.1
Got it.
>
>> + xdp_umem_destroy(internals->umem);
>> + internals->umem = NULL;
>> + }
>> + }
>> + 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;
>> + unsigned int buf_size, data_size;
>
>uint32_t
Got it.
>
>> + struct pkt_rx_queue *rxq;
>> + int ret = 0;
>
>No need to set 'ret'. Alternatively, restructure so you always return 'ret'.
Got it.
>
>> +
>> + 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) {
>> + RTE_LOG(ERR, AF_XDP,
>> + "%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)) {
>> + RTE_LOG(ERR, AF_XDP,
>> + "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);
>> +
>> + 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;
>> +
>> + 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;
>> +
>> + *i = atoi(value);
>
>Use strtol().
Got it.
>
>> + if (*i < 0) {
>> + RTE_LOG(ERR, AF_XDP, "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 (strlen(value) > IFNAMSIZ) {
>
>The buffer is IFNAMSIZ bytes (which it should be), so it can't hold a string
>with strlen() == IFNAMSIZ.
Good catch. should be strlen(value) > IFNAMSIZ - 1
>
>> + RTE_LOG(ERR, AF_XDP, "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 = 0;
>
>Should not be initialized.
Got it.
>
>> +
>> + 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;
>
>I fail to see the point of this goto, but maybe there's more code to follow
>in future patches.
Yes, We'll add more parameters in the future.
>
>> +
>> +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 (ioctl(sock, SIOCGIFHWADDR, &ifr))
>> + goto error;
>> +
>> + rte_memcpy(eth_addr, ifr.ifr_hwaddr.sa_data, ETHER_ADDR_LEN);
>> +
>> + close(sock);
>> + *if_index = if_nametoindex(if_name);
>> + return 0;
>> +
>> +error:
>> + close(sock);
>> + return -1;
>> +}
>> +
>> +static int
>> +init_internals(struct rte_vdev_device *dev,
>> + const char *if_name,
>> + int queue_idx,
>> + struct rte_eth_dev **eth_dev)
>> +{
>> + const char *name = rte_vdev_device_name(dev);
>> + const unsigned int numa_node = dev->device.numa_node;
>> + struct pmd_internals *internals = NULL;
>> + int ret;
>> + int i;
>> +
>> + internals = rte_zmalloc_socket(name, sizeof(*internals), 0, numa_node);
>> + if (!internals)
>
>1.8.1
Got it.
>
>> + return -ENOMEM;
>> +
>> + 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)
>
>1.8.1
Got it.
>
>> + 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 0;
>> +
>> +err:
>> + rte_free(internals);
>> + return -1;
>> +}
>> +
>> +static int
>> +rte_pmd_af_xdp_probe(struct rte_vdev_device *dev)
>> +{
>> + struct rte_kvargs *kvlist;
>> + char if_name[IFNAMSIZ];
>> + int xsk_queue_idx = ETH_AF_XDP_DFLT_QUEUE_IDX;
>> + struct rte_eth_dev *eth_dev = NULL;
>> + const char *name;
>> + int ret;
>> +
>> + RTE_LOG(INFO, AF_XDP, "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) {
>> + RTE_LOG(ERR, AF_XDP, "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) {
>> + RTE_LOG(ERR, AF_XDP, "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) {
>> + RTE_LOG(ERR, AF_XDP, "Invalid kvargs value\n");
>> + return -EINVAL;
>> + }
>> +
>> + ret = init_internals(dev, if_name, xsk_queue_idx, ð_dev);
>> + if (ret) {
>> + RTE_LOG(ERR, AF_XDP, "Failed to init internals\n");
>> + return ret;
>> + }
>> +
>> + 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;
>> +
>> + RTE_LOG(INFO, AF_XDP, "Removing 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->umem->buf_ring);
>> + rte_free(internals->umem->buffer);
>> + 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(eth_af_xdp, pmd_af_xdp_drv);
>> +RTE_PMD_REGISTER_PARAM_STRING(eth_af_xdp,
>> + "iface=<string> "
>> + "queue=<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..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..be0af73cc 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 -lelf -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
>>
Lots of little review comments. This is what I saw in 30 minutes.
Expect more.
On Tue, 19 Mar 2019 15:12:51 +0800
Xiaolong Ye <xiaolong.ye@intel.com> wrote:
> + nb_pkts = nb_pkts < ETH_AF_XDP_RX_BATCH_SIZE ?
> + nb_pkts : ETH_AF_XDP_RX_BATCH_SIZE;
Maybe use RTE_MIN() ?
> + mbuf = rte_pktmbuf_alloc(rxq->mb_pool);
> + if (mbuf) {
> + memcpy(rte_pktmbuf_mtod(mbuf, void*), pkt, len);
Space necessary in "void*"
Use rte_memcpy.
> +static void pull_umem_cq(struct xsk_umem_info *umem, int size)
> +{
> + struct xsk_ring_cons *cq = &umem->cq;
> + int i, n;
> + uint32_t idx_cq;
> + uint64_t addr;
> +
> + n = xsk_ring_cons__peek(cq, size, &idx_cq);
> + if (n > 0) {
> + for (i = 0; i < n; i++) {
You don't need the if (n > 0) since if n <= 0 the for loop
would happen 0 times.
> +
> +static void kick_tx(struct pkt_tx_queue *txq)
> +{
> + struct xsk_umem_info *umem = txq->pair->umem;
> + int ret;
> +
> + while (1) {
> + ret = sendto(xsk_socket__fd(txq->pair->xsk), NULL, 0,
> + MSG_DONTWAIT, NULL, 0);
> +
> + /* everything is ok */
> + if (ret >= 0)
> + break;
I would prefer:
while ((send(xsk_socket__fd(fd, NULL, 0, MSG_DONTWAIT) < 0) {
Because:
- use while() to make looping clearer rather than while(1)
- use send() rather than sendto() because you aren't sending with addr
- you don't care about return value (ie.ret)
> +
> + /* some thing unexpected */
> + if (errno != EBUSY && errno != EAGAIN)
> + break;
What about EINTR
> +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;
Cast here is unnecessary.
> + dev_info->max_rx_queues = 1;
> + dev_info->max_tx_queues = 1;
> + dev_info->min_rx_bufsize = 0;
dev_info is already zero, don't need to fill other values.
> +
> +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;
> +
> + 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;
> +
> + optlen = sizeof(struct xdp_statistics);
In theory each call to getsockopt() could change or reduce the value of
optlen. Best to initialize in loop before each call.
> + for (i = 0; i < dev->data->nb_rx_queues; i++) {
> + rxq = &internals->rx_queues[i];
> + stats->q_ipackets[i] = internals->rx_queues[i].rx_pkts;
> + stats->q_ibytes[i] = internals->rx_queues[i].rx_bytes;
> +
> + stats->q_opackets[i] = internals->tx_queues[i].tx_pkts;
> + stats->q_obytes[i] = internals->tx_queues[i].tx_bytes;
> +
> + stats->ipackets += stats->q_ipackets[i];
> + stats->ibytes += stats->q_ibytes[i];
> + stats->imissed += internals->rx_queues[i].rx_dropped;
> + getsockopt(xsk_socket__fd(rxq->xsk), SOL_XDP, XDP_STATISTICS,
> + &xdp_stats, &optlen);
You need to check return value of getsockopt() otherwise coverity will complain.
> +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++) {
> + internals->rx_queues[i].rx_pkts = 0;
> + internals->rx_queues[i].rx_bytes = 0;
> + internals->rx_queues[i].rx_dropped = 0;
> +
> + internals->tx_queues[i].tx_pkts = 0;
> + internals->tx_queues[i].err_pkts = 0;
> + internals->tx_queues[i].tx_bytes = 0;
Put all the statistics together and use memset?
> +static struct xsk_umem_info *xdp_umem_configure(void)
> +{
> + struct xsk_umem_info *umem;
> + 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 };
> + void *bufs = NULL;
> + char ring_name[0x100];
0x100 is unconvential here. Instead use RTE_RING_NAMESIZE
but variable is unnecessary, see below
> + int ret;
> + uint64_t i;
> +
> + umem = calloc(1, sizeof(*umem));
Why not use rte_zmalloc_node to:
1. work with primary/secondary
2. guarantee memory on correct numa node?
> + if (!umem) {
> + RTE_LOG(ERR, AF_XDP, "Failed to allocate umem info");
> + return NULL;
> + }
> +
> + snprintf(ring_name, 0x100, "af_xdp_ring");
If ring is always the same, why copy it. Just use string literal
> +/** parse name argument */
> +static int
> +parse_name_arg(const char *key __rte_unused,
> + const char *value, void *extra_args)
> +{
> + char *name = extra_args;
> +
> + if (strlen(value) > IFNAMSIZ) {
Why not:
if (strnlen(value, IFNAMSIZ) >= IFNAMSIZ) {
> +
> +static int
> +init_internals(struct rte_vdev_device *dev,
> + const char *if_name,
> + int queue_idx,
> + struct rte_eth_dev **eth_dev)
If you changed the function to return the new eth_dev (and return NULL on error)
then you wouldn't have to pass eth_dev by reference.
static struct rte_eth_dev *
allocate_ethdev(struct rte_vdev_device *dev, const char *if_name, uint16_t queue_idx)
{
> +{
> + const char *name = rte_vdev_device_name(dev);
> + const unsigned int numa_node = dev->device.numa_node;
> + struct pmd_internals *internals = NULL;
Useless initialization, first thing you do is allocate this.
> + int ret;
> + int i;
> +
> + internals = rte_zmalloc_socket(name, sizeof(*internals), 0, numa_node);
On Tue, 19 Mar 2019 15:12:51 +0800
Xiaolong Ye <xiaolong.ye@intel.com> wrote:
> 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 | 6 +
> config/common_base | 5 +
> config/common_linux | 1 +
> doc/guides/nics/af_xdp.rst | 45 +
> 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 | 33 +
> drivers/net/af_xdp/meson.build | 21 +
> drivers/net/af_xdp/rte_eth_af_xdp.c | 930 ++++++++++++++++++
> drivers/net/af_xdp/rte_pmd_af_xdp_version.map | 3 +
> drivers/net/meson.build | 1 +
> mk/rte.app.mk | 1 +
> 14 files changed, 1066 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/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 452b8eb82..1cc54b439 100644
> --- a/MAINTAINERS
> +++ b/MAINTAINERS
> @@ -468,6 +468,12 @@ 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/features/af_xdp.rst
> +
> 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 0b09a9348..4044de205 100644
> --- a/config/common_base
> +++ b/config/common_base
> @@ -416,6 +416,11 @@ 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/config/common_linux b/config/common_linux
> index 75334273d..0b1249da0 100644
> --- a/config/common_linux
> +++ b/config/common_linux
> @@ -19,6 +19,7 @@ CONFIG_RTE_LIBRTE_VHOST_POSTCOPY=n
> CONFIG_RTE_LIBRTE_PMD_VHOST=y
> CONFIG_RTE_LIBRTE_IFC_PMD=y
> CONFIG_RTE_LIBRTE_PMD_AF_PACKET=y
> +CONFIG_RTE_LIBRTE_PMD_AF_XDP=y
> CONFIG_RTE_LIBRTE_PMD_SOFTNIC=y
> CONFIG_RTE_LIBRTE_PMD_TAP=y
> CONFIG_RTE_LIBRTE_AVP_PMD=y
> diff --git a/doc/guides/nics/af_xdp.rst b/doc/guides/nics/af_xdp.rst
> new file mode 100644
> index 000000000..dd5654dd1
> --- /dev/null
> +++ b/doc/guides/nics/af_xdp.rst
> @@ -0,0 +1,45 @@
> +.. SPDX-License-Identifier: BSD-3-Clause
> + Copyright(c) 2018 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.
> +
> +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 > 4.18) with XDP sockets configuration enabled;
> +* libbpf (within kernel version > 5.1) with latest af_xdp support installed
> +* 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 eth_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..7b8fcce00
> --- /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
> \ No newline at end of file
This is bad. Configure your editor to always put newline at end of file.
In .emacs
(setq require-final-newline t)
On Tue, Mar 19, 2019 at 09:16:27AM -0700, Stephen Hemminger wrote:
> On Tue, 19 Mar 2019 15:12:51 +0800
> Xiaolong Ye <xiaolong.ye@intel.com> wrote:
>
> > 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 | 6 +
> > config/common_base | 5 +
> > config/common_linux | 1 +
> > doc/guides/nics/af_xdp.rst | 45 +
> > 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 | 33 +
> > drivers/net/af_xdp/meson.build | 21 +
> > drivers/net/af_xdp/rte_eth_af_xdp.c | 930 ++++++++++++++++++
> > drivers/net/af_xdp/rte_pmd_af_xdp_version.map | 3 +
> > drivers/net/meson.build | 1 +
> > mk/rte.app.mk | 1 +
> > 14 files changed, 1066 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/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 452b8eb82..1cc54b439 100644
> > --- a/MAINTAINERS
> > +++ b/MAINTAINERS
> > @@ -468,6 +468,12 @@ 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/features/af_xdp.rst
> > +
> > 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 0b09a9348..4044de205 100644
> > --- a/config/common_base
> > +++ b/config/common_base
> > @@ -416,6 +416,11 @@ 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/config/common_linux b/config/common_linux
> > index 75334273d..0b1249da0 100644
> > --- a/config/common_linux
> > +++ b/config/common_linux
> > @@ -19,6 +19,7 @@ CONFIG_RTE_LIBRTE_VHOST_POSTCOPY=n
> > CONFIG_RTE_LIBRTE_PMD_VHOST=y
> > CONFIG_RTE_LIBRTE_IFC_PMD=y
> > CONFIG_RTE_LIBRTE_PMD_AF_PACKET=y
> > +CONFIG_RTE_LIBRTE_PMD_AF_XDP=y
> > CONFIG_RTE_LIBRTE_PMD_SOFTNIC=y
> > CONFIG_RTE_LIBRTE_PMD_TAP=y
> > CONFIG_RTE_LIBRTE_AVP_PMD=y
> > diff --git a/doc/guides/nics/af_xdp.rst b/doc/guides/nics/af_xdp.rst
> > new file mode 100644
> > index 000000000..dd5654dd1
> > --- /dev/null
> > +++ b/doc/guides/nics/af_xdp.rst
> > @@ -0,0 +1,45 @@
> > +.. SPDX-License-Identifier: BSD-3-Clause
> > + Copyright(c) 2018 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.
> > +
> > +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 > 4.18) with XDP sockets configuration enabled;
> > +* libbpf (within kernel version > 5.1) with latest af_xdp support installed
> > +* 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 eth_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..7b8fcce00
> > --- /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
> > \ No newline at end of file
>
>
> This is bad. Configure your editor to always put newline at end of file.
> In .emacs
>
> (setq require-final-newline t)
>
Or use Vim which needs no extra configuration to do this. :-)
On 03/19, Stephen Hemminger wrote:
>> \ No newline at end of file
>
>
>This is bad. Configure your editor to always put newline at end of file.
>In .emacs
>
> (setq require-final-newline t)
>
I wasn't aware of it before, thanks for the info, will configure it for my emacs.
Thanks,
Xiaolong
On 03/19, Bruce Richardson wrote:
>> This is bad. Configure your editor to always put newline at end of file.
>> In .emacs
>>
>> (setq require-final-newline t)
>>
>Or use Vim which needs no extra configuration to do this. :-)
I used to be a Vimer, just switch to emacs recently. :-)
>
Hi, Stephen
On 03/19, Stephen Hemminger wrote:
>Lots of little review comments. This is what I saw in 30 minutes.
>Expect more.
Thanks for taking time to review my patch. They are all valuable inputs.
>
>
>On Tue, 19 Mar 2019 15:12:51 +0800
>Xiaolong Ye <xiaolong.ye@intel.com> wrote:
>
>> + nb_pkts = nb_pkts < ETH_AF_XDP_RX_BATCH_SIZE ?
>> + nb_pkts : ETH_AF_XDP_RX_BATCH_SIZE;
>
>Maybe use RTE_MIN() ?
Will do.
>
>> + mbuf = rte_pktmbuf_alloc(rxq->mb_pool);
>> + if (mbuf) {
>> + memcpy(rte_pktmbuf_mtod(mbuf, void*), pkt, len);
>
>Space necessary in "void*"
>Use rte_memcpy.
Will do.
>
>> +static void pull_umem_cq(struct xsk_umem_info *umem, int size)
>> +{
>> + struct xsk_ring_cons *cq = &umem->cq;
>> + int i, n;
>> + uint32_t idx_cq;
>> + uint64_t addr;
>> +
>> + n = xsk_ring_cons__peek(cq, size, &idx_cq);
>> + if (n > 0) {
>> + for (i = 0; i < n; i++) {
>
>You don't need the if (n > 0) since if n <= 0 the for loop
>would happen 0 times.
Will remove the redundant "if (n > 0)"
>
>> +
>> +static void kick_tx(struct pkt_tx_queue *txq)
>> +{
>> + struct xsk_umem_info *umem = txq->pair->umem;
>> + int ret;
>> +
>> + while (1) {
>> + ret = sendto(xsk_socket__fd(txq->pair->xsk), NULL, 0,
>> + MSG_DONTWAIT, NULL, 0);
>> +
>> + /* everything is ok */
>> + if (ret >= 0)
>> + break;
>
>I would prefer:
> while ((send(xsk_socket__fd(fd, NULL, 0, MSG_DONTWAIT) < 0) {
>
>Because:
> - use while() to make looping clearer rather than while(1)
> - use send() rather than sendto() because you aren't sending with addr
> - you don't care about return value (ie.ret)
>
>> +
>> + /* some thing unexpected */
>> + if (errno != EBUSY && errno != EAGAIN)
>> + break;
>
>What about EINTR
>
>
>
>> +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;
>
>Cast here is unnecessary.
Got it.
>
>> + dev_info->max_rx_queues = 1;
>> + dev_info->max_tx_queues = 1;
>> + dev_info->min_rx_bufsize = 0;
>
>dev_info is already zero, don't need to fill other values.
Got it.
>
>> +
>> +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;
>> +
>> + 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;
>> +
>> + optlen = sizeof(struct xdp_statistics);
>
>In theory each call to getsockopt() could change or reduce the value of
>optlen. Best to initialize in loop before each call.
Got it.
>
>> + for (i = 0; i < dev->data->nb_rx_queues; i++) {
>> + rxq = &internals->rx_queues[i];
>> + stats->q_ipackets[i] = internals->rx_queues[i].rx_pkts;
>> + stats->q_ibytes[i] = internals->rx_queues[i].rx_bytes;
>> +
>> + stats->q_opackets[i] = internals->tx_queues[i].tx_pkts;
>> + stats->q_obytes[i] = internals->tx_queues[i].tx_bytes;
>> +
>> + stats->ipackets += stats->q_ipackets[i];
>> + stats->ibytes += stats->q_ibytes[i];
>> + stats->imissed += internals->rx_queues[i].rx_dropped;
>> + getsockopt(xsk_socket__fd(rxq->xsk), SOL_XDP, XDP_STATISTICS,
>> + &xdp_stats, &optlen);
>
>You need to check return value of getsockopt() otherwise coverity will complain.
Got it.
>
>> +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++) {
>> + internals->rx_queues[i].rx_pkts = 0;
>> + internals->rx_queues[i].rx_bytes = 0;
>> + internals->rx_queues[i].rx_dropped = 0;
>> +
>> + internals->tx_queues[i].tx_pkts = 0;
>> + internals->tx_queues[i].err_pkts = 0;
>> + internals->tx_queues[i].tx_bytes = 0;
>
>Put all the statistics together and use memset?
Sounds good, will do.
>
>> +static struct xsk_umem_info *xdp_umem_configure(void)
>> +{
>> + struct xsk_umem_info *umem;
>> + 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 };
>> + void *bufs = NULL;
>> + char ring_name[0x100];
>
>0x100 is unconvential here. Instead use RTE_RING_NAMESIZE
>but variable is unnecessary, see below
Got it.
>
>> + int ret;
>> + uint64_t i;
>> +
>> + umem = calloc(1, sizeof(*umem));
>
>Why not use rte_zmalloc_node to:
> 1. work with primary/secondary
> 2. guarantee memory on correct numa node?
Will do.
>
>> + if (!umem) {
>> + RTE_LOG(ERR, AF_XDP, "Failed to allocate umem info");
>> + return NULL;
>> + }
>> +
>> + snprintf(ring_name, 0x100, "af_xdp_ring");
>
>If ring is always the same, why copy it. Just use string literal
Got it.
>
>> +/** parse name argument */
>> +static int
>> +parse_name_arg(const char *key __rte_unused,
>> + const char *value, void *extra_args)
>> +{
>> + char *name = extra_args;
>> +
>> + if (strlen(value) > IFNAMSIZ) {
>
>Why not:
> if (strnlen(value, IFNAMSIZ) >= IFNAMSIZ) {
Will do.
>
>> +
>> +static int
>> +init_internals(struct rte_vdev_device *dev,
>> + const char *if_name,
>> + int queue_idx,
>> + struct rte_eth_dev **eth_dev)
>
>If you changed the function to return the new eth_dev (and return NULL on error)
>then you wouldn't have to pass eth_dev by reference.
>
>static struct rte_eth_dev *
>allocate_ethdev(struct rte_vdev_device *dev, const char *if_name, uint16_t queue_idx)
Sounds better, will do.
>{
>
>> +{
>> + const char *name = rte_vdev_device_name(dev);
>> + const unsigned int numa_node = dev->device.numa_node;
>> + struct pmd_internals *internals = NULL;
>
>Useless initialization, first thing you do is allocate this.
Got it.
Thanks,
Xiaolong
>
>
>> + int ret;
>> + int i;
>> +
>> + internals = rte_zmalloc_socket(name, sizeof(*internals), 0, numa_node);
>
On Tue, Mar 19, 2019 at 8:17 AM Xiaolong Ye <xiaolong.ye@intel.com> wrote:
> diff --git a/doc/guides/nics/features/af_xdp.ini
> b/doc/guides/nics/features/af_xdp.ini
> new file mode 100644
> index 000000000..7b8fcce00
> --- /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
>
Is there really a limitation on x86?
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..6cf0ed7db
> --- /dev/null
> +++ b/drivers/net/af_xdp/Makefile
> @@ -0,0 +1,33 @@
> +# SPDX-License-Identifier: BSD-3-Clause
> +# Copyright(c) 2018 Intel Corporation
>
2018? 2019?
+
> +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
> +
> +# require kernel version >= v5.1-rc1
> +LINUX_VERSION := $(shell uname -r)
> +CFLAGS += -I/lib/modules/$(LINUX_VERSION)/build/tools/include
> +CFLAGS += -I/lib/modules/$(LINUX_VERSION)/build/tools/lib/bpf
>
We can reuse RTE_KERNELDIR here (even if the docs state that this was to
build kmods so far).
> 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..96dedc0c4
> --- /dev/null
> +++ b/drivers/net/af_xdp/rte_eth_af_xdp.c
>
[snip]
> +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;
> +
> + optlen = sizeof(struct xdp_statistics);
> + for (i = 0; i < dev->data->nb_rx_queues; i++) {
> + rxq = &internals->rx_queues[i];
> + stats->q_ipackets[i] = internals->rx_queues[i].rx_pkts;
> + stats->q_ibytes[i] = internals->rx_queues[i].rx_bytes;
> +
> + stats->q_opackets[i] = internals->tx_queues[i].tx_pkts;
> + stats->q_obytes[i] = internals->tx_queues[i].tx_bytes;
> +
> + stats->ipackets += stats->q_ipackets[i];
> + stats->ibytes += stats->q_ibytes[i];
> + stats->imissed += internals->rx_queues[i].rx_dropped;
> + getsockopt(xsk_socket__fd(rxq->xsk), SOL_XDP,
> XDP_STATISTICS,
> + &xdp_stats, &optlen);
> + stats->imissed += xdp_stats.rx_dropped;
> +
> + stats->opackets += stats->q_opackets[i];
> + stats->oerrors += stats->q_errors[i];
>
You forgot to remove stats->q_errors[i];
+ stats->oerrors += internals->tx_queues[i].err_pkts;
> + stats->obytes += stats->q_obytes[i];
> + }
> +
> + return 0;
> +}
Thanks for your comments.
On 03/20, David Marchand wrote:
>On Tue, Mar 19, 2019 at 8:17 AM Xiaolong Ye <xiaolong.ye@intel.com> wrote:
>
>> diff --git a/doc/guides/nics/features/af_xdp.ini
>> b/doc/guides/nics/features/af_xdp.ini
>> new file mode 100644
>> index 000000000..7b8fcce00
>> --- /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
>>
>
>Is there really a limitation on x86?
I think no, just don't have a chance to try it on a x86-32 machine.
>
>
>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..6cf0ed7db
>> --- /dev/null
>> +++ b/drivers/net/af_xdp/Makefile
>> @@ -0,0 +1,33 @@
>> +# SPDX-License-Identifier: BSD-3-Clause
>> +# Copyright(c) 2018 Intel Corporation
>>
>
>2018? 2019?
Will correct it to 2019.
>
>+
>> +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
>> +
>> +# require kernel version >= v5.1-rc1
>> +LINUX_VERSION := $(shell uname -r)
>> +CFLAGS += -I/lib/modules/$(LINUX_VERSION)/build/tools/include
>> +CFLAGS += -I/lib/modules/$(LINUX_VERSION)/build/tools/lib/bpf
>>
>
>We can reuse RTE_KERNELDIR here (even if the docs state that this was to
>build kmods so far).
Will do.
>
>
>> 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..96dedc0c4
>> --- /dev/null
>> +++ b/drivers/net/af_xdp/rte_eth_af_xdp.c
>>
>
>[snip]
>
>
>> +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;
>> +
>> + optlen = sizeof(struct xdp_statistics);
>> + for (i = 0; i < dev->data->nb_rx_queues; i++) {
>> + rxq = &internals->rx_queues[i];
>> + stats->q_ipackets[i] = internals->rx_queues[i].rx_pkts;
>> + stats->q_ibytes[i] = internals->rx_queues[i].rx_bytes;
>> +
>> + stats->q_opackets[i] = internals->tx_queues[i].tx_pkts;
>> + stats->q_obytes[i] = internals->tx_queues[i].tx_bytes;
>> +
>> + stats->ipackets += stats->q_ipackets[i];
>> + stats->ibytes += stats->q_ibytes[i];
>> + stats->imissed += internals->rx_queues[i].rx_dropped;
>> + getsockopt(xsk_socket__fd(rxq->xsk), SOL_XDP,
>> XDP_STATISTICS,
>> + &xdp_stats, &optlen);
>> + stats->imissed += xdp_stats.rx_dropped;
>> +
>> + stats->opackets += stats->q_opackets[i];
>> + stats->oerrors += stats->q_errors[i];
>>
>
>You forgot to remove stats->q_errors[i];
>
>+ stats->oerrors += internals->tx_queues[i].err_pkts;
My bad, will remove it in next version.
Thanks,
Xiaolong
>> + stats->obytes += stats->q_obytes[i];
>> + }
>> +
>> + return 0;
>> +}
>
>
>
>--
>David Marchand
@@ -468,6 +468,12 @@ 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/features/af_xdp.rst
+
Amazon ENA
M: Marcin Wojtas <mw@semihalf.com>
M: Michal Krawczyk <mk@semihalf.com>
@@ -416,6 +416,11 @@ 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
#
@@ -19,6 +19,7 @@ CONFIG_RTE_LIBRTE_VHOST_POSTCOPY=n
CONFIG_RTE_LIBRTE_PMD_VHOST=y
CONFIG_RTE_LIBRTE_IFC_PMD=y
CONFIG_RTE_LIBRTE_PMD_AF_PACKET=y
+CONFIG_RTE_LIBRTE_PMD_AF_XDP=y
CONFIG_RTE_LIBRTE_PMD_SOFTNIC=y
CONFIG_RTE_LIBRTE_PMD_TAP=y
CONFIG_RTE_LIBRTE_AVP_PMD=y
new file mode 100644
@@ -0,0 +1,45 @@
+.. SPDX-License-Identifier: BSD-3-Clause
+ Copyright(c) 2018 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.
+
+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 > 4.18) with XDP sockets configuration enabled;
+* libbpf (within kernel version > 5.1) with latest af_xdp support installed
+* 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 eth_af_xdp,iface=ens786f1,queue=0
new file mode 100644
@@ -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
\ No newline at end of file
@@ -12,6 +12,7 @@ Network Interface Controller Drivers
features
build_and_test
af_packet
+ af_xdp
ark
atlantic
avp
@@ -65,6 +65,13 @@ 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:
@@ -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
new file mode 100644
@@ -0,0 +1,33 @@
+# 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
+
+# require kernel version >= v5.1-rc1
+LINUX_VERSION := $(shell uname -r)
+CFLAGS += -I/lib/modules/$(LINUX_VERSION)/build/tools/include
+CFLAGS += -I/lib/modules/$(LINUX_VERSION)/build/tools/lib/bpf
+
+CFLAGS += $(WERROR_FLAGS)
+LDLIBS += -lrte_eal -lrte_mbuf -lrte_mempool -lrte_ring
+LDLIBS += -lrte_ethdev -lrte_net -lrte_kvargs
+LDLIBS += -lrte_bus_vdev
+LDLIBS += -lbpf
+
+#
+# all source are stored in SRCS-y
+#
+SRCS-$(CONFIG_RTE_LIBRTE_PMD_AF_XDP) += rte_eth_af_xdp.c
+
+include $(RTE_SDK)/mk/rte.lib.mk
new file mode 100644
@@ -0,0 +1,21 @@
+# SPDX-License-Identifier: BSD-3-Clause
+# Copyright(c) 2018 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)
+ build = true
+ pkgconfig_extra_libs += '-lbpf'
+ else
+ build = false
+ endif
+endif
+sources = files('rte_eth_af_xdp.c')
+ext_deps += bpf_dep
new file mode 100644
@@ -0,0 +1,930 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2019 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 <rte_string_fns.h>
+
+#include <linux/if_ether.h>
+#include <linux/if_xdp.h>
+#include <linux/if_link.h>
+#include <asm/barrier.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 <bpf/bpf.h>
+#include <xsk.h>
+
+#define RTE_LOGTYPE_AF_XDP RTE_LOGTYPE_USER1
+#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_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;
+ void *buffer;
+};
+
+struct pkt_rx_queue {
+ struct xsk_ring_cons rx;
+ struct xsk_umem_info *umem;
+ struct xsk_socket *xsk;
+ struct rte_mempool *mb_pool;
+
+ uint64_t rx_pkts;
+ uint64_t rx_bytes;
+ uint64_t rx_dropped;
+
+ struct pkt_tx_queue *pair;
+ uint16_t queue_idx;
+};
+
+struct pkt_tx_queue {
+ struct xsk_ring_prod tx;
+
+ uint64_t tx_pkts;
+ uint64_t err_pkts;
+ uint64_t tx_bytes;
+
+ 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];
+};
+
+static const char * const valid_arguments[] = {
+ ETH_AF_XDP_IFACE_ARG,
+ ETH_AF_XDP_QUEUE_IDX_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 inline int
+reserve_fill_queue(struct xsk_umem_info *umem, int reserve_size)
+{
+ struct xsk_ring_prod *fq = &umem->fq;
+ uint32_t idx;
+ void *addr = NULL;
+ int i, ret = 0;
+
+ ret = xsk_ring_prod__reserve(fq, reserve_size, &idx);
+ if (!ret) {
+ RTE_LOG(ERR, AF_XDP, "Failed to reserve enough fq descs.\n");
+ return ret;
+ }
+
+ for (i = 0; i < reserve_size; i++) {
+ rte_ring_dequeue(umem->buf_ring, &addr);
+ *xsk_ring_prod__fill_addr(fq, idx++) = (uint64_t)addr;
+ }
+
+ xsk_ring_prod__submit(fq, reserve_size);
+
+ 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;
+ uint32_t free_thresh = fq->size >> 1;
+ struct rte_mbuf *mbuf;
+ unsigned long dropped = 0;
+ unsigned long rx_bytes = 0;
+ uint16_t count = 0;
+ int rcvd, i;
+
+ nb_pkts = nb_pkts < ETH_AF_XDP_RX_BATCH_SIZE ?
+ nb_pkts : ETH_AF_XDP_RX_BATCH_SIZE;
+
+ rcvd = xsk_ring_cons__peek(rx, nb_pkts, &idx_rx);
+ if (!rcvd)
+ return 0;
+
+ if (xsk_prod_nb_free(fq, free_thresh) >= free_thresh)
+ (void)reserve_fill_queue(umem, ETH_AF_XDP_RX_BATCH_SIZE);
+
+ for (i = 0; i < rcvd; i++) {
+ uint64_t addr = xsk_ring_cons__rx_desc(rx, idx_rx)->addr;
+ uint32_t len = xsk_ring_cons__rx_desc(rx, idx_rx++)->len;
+ char *pkt = xsk_umem__get_data(rxq->umem->buffer, addr);
+
+ mbuf = rte_pktmbuf_alloc(rxq->mb_pool);
+ if (mbuf) {
+ memcpy(rte_pktmbuf_mtod(mbuf, void*), pkt, len);
+ rte_pktmbuf_pkt_len(mbuf) =
+ rte_pktmbuf_data_len(mbuf) = len;
+ rx_bytes += len;
+ bufs[count++] = mbuf;
+ } else {
+ dropped++;
+ }
+ rte_ring_enqueue(umem->buf_ring, (void *)addr);
+ }
+
+ xsk_ring_cons__release(rx, rcvd);
+
+ /* statistics */
+ rxq->rx_pkts += (rcvd - dropped);
+ rxq->rx_bytes += rx_bytes;
+ rxq->rx_dropped += dropped;
+
+ return count;
+}
+
+static void pull_umem_cq(struct xsk_umem_info *umem, int size)
+{
+ struct xsk_ring_cons *cq = &umem->cq;
+ int i, n;
+ uint32_t idx_cq;
+ uint64_t addr;
+
+ n = xsk_ring_cons__peek(cq, size, &idx_cq);
+ if (n > 0) {
+ for (i = 0; i < n; i++) {
+ 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;
+ int ret;
+
+ while (1) {
+ ret = sendto(xsk_socket__fd(txq->pair->xsk), NULL, 0,
+ MSG_DONTWAIT, NULL, 0);
+
+ /* everything is ok */
+ if (ret >= 0)
+ break;
+
+ /* some thing unexpected */
+ if (errno != EBUSY && errno != EAGAIN)
+ break;
+
+ /* pull from complete qeueu 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 = nb_pkts < ETH_AF_XDP_TX_BATCH_SIZE ?
+ 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)
+ 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;
+ char *pkt;
+ unsigned int 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->buffer,
+ desc->addr);
+ 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->err_pkts += nb_pkts - valid;
+ txq->tx_pkts += valid;
+ txq->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 __rte_unused)
+{
+ /* 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 = (uint32_t)ETH_FRAME_LEN;
+ dev_info->max_rx_queues = 1;
+ dev_info->max_tx_queues = 1;
+ dev_info->min_rx_bufsize = 0;
+
+ 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;
+
+ optlen = sizeof(struct xdp_statistics);
+ for (i = 0; i < dev->data->nb_rx_queues; i++) {
+ rxq = &internals->rx_queues[i];
+ stats->q_ipackets[i] = internals->rx_queues[i].rx_pkts;
+ stats->q_ibytes[i] = internals->rx_queues[i].rx_bytes;
+
+ stats->q_opackets[i] = internals->tx_queues[i].tx_pkts;
+ stats->q_obytes[i] = internals->tx_queues[i].tx_bytes;
+
+ stats->ipackets += stats->q_ipackets[i];
+ stats->ibytes += stats->q_ibytes[i];
+ stats->imissed += internals->rx_queues[i].rx_dropped;
+ getsockopt(xsk_socket__fd(rxq->xsk), SOL_XDP, XDP_STATISTICS,
+ &xdp_stats, &optlen);
+ stats->imissed += xdp_stats.rx_dropped;
+
+ stats->opackets += stats->q_opackets[i];
+ stats->oerrors += stats->q_errors[i];
+ stats->oerrors += internals->tx_queues[i].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++) {
+ internals->rx_queues[i].rx_pkts = 0;
+ internals->rx_queues[i].rx_bytes = 0;
+ internals->rx_queues[i].rx_dropped = 0;
+
+ internals->tx_queues[i].tx_pkts = 0;
+ internals->tx_queues[i].err_pkts = 0;
+ internals->tx_queues[i].tx_bytes = 0;
+ }
+}
+
+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)) {
+ RTE_LOG(ERR, AF_XDP, "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;
+
+ RTE_LOG(INFO, AF_XDP, "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)
+ 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)
+{
+ free(umem->buffer);
+ umem->buffer = NULL;
+
+ rte_ring_free(umem->buf_ring);
+ umem->buf_ring = NULL;
+
+ free(umem);
+ umem = NULL;
+}
+
+static struct xsk_umem_info *xdp_umem_configure(void)
+{
+ struct xsk_umem_info *umem;
+ 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 };
+ void *bufs = NULL;
+ char ring_name[0x100];
+ int ret;
+ uint64_t i;
+
+ umem = calloc(1, sizeof(*umem));
+ if (!umem) {
+ RTE_LOG(ERR, AF_XDP, "Failed to allocate umem info");
+ return NULL;
+ }
+
+ snprintf(ring_name, 0x100, "af_xdp_ring");
+ umem->buf_ring = rte_ring_create(ring_name,
+ ETH_AF_XDP_NUM_BUFFERS,
+ SOCKET_ID_ANY,
+ 0x0);
+ if (!umem->buf_ring) {
+ RTE_LOG(ERR, AF_XDP,
+ "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));
+
+ if (posix_memalign(&bufs, getpagesize(),
+ ETH_AF_XDP_NUM_BUFFERS * ETH_AF_XDP_FRAME_SIZE)) {
+ RTE_LOG(ERR, AF_XDP, "Failed to allocate memory pool.\n");
+ goto err;
+ }
+ ret = xsk_umem__create(&umem->umem, bufs,
+ ETH_AF_XDP_NUM_BUFFERS * ETH_AF_XDP_FRAME_SIZE,
+ &umem->fq, &umem->cq,
+ &usr_config);
+
+ if (ret) {
+ RTE_LOG(ERR, AF_XDP, "Failed to create umem");
+ goto err;
+ }
+ umem->buffer = bufs;
+
+ 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) {
+ ret = -ENOMEM;
+ goto err;
+ }
+
+ 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) {
+ RTE_LOG(ERR, AF_XDP, "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) {
+ RTE_LOG(ERR, AF_XDP, "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;
+ int xsk_fd = xsk_socket__fd(rxq->xsk);
+
+ if (xsk_fd) {
+ close(xsk_fd);
+ if (internals->umem) {
+ xdp_umem_destroy(internals->umem);
+ internals->umem = NULL;
+ }
+ }
+ 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;
+ unsigned int buf_size, data_size;
+ struct pkt_rx_queue *rxq;
+ int ret = 0;
+
+ 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) {
+ RTE_LOG(ERR, AF_XDP,
+ "%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)) {
+ RTE_LOG(ERR, AF_XDP,
+ "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);
+
+ 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;
+
+ 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;
+
+ *i = atoi(value);
+ if (*i < 0) {
+ RTE_LOG(ERR, AF_XDP, "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 (strlen(value) > IFNAMSIZ) {
+ RTE_LOG(ERR, AF_XDP, "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 = 0;
+
+ 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 (ioctl(sock, SIOCGIFHWADDR, &ifr))
+ goto error;
+
+ rte_memcpy(eth_addr, ifr.ifr_hwaddr.sa_data, ETHER_ADDR_LEN);
+
+ close(sock);
+ *if_index = if_nametoindex(if_name);
+ return 0;
+
+error:
+ close(sock);
+ return -1;
+}
+
+static int
+init_internals(struct rte_vdev_device *dev,
+ const char *if_name,
+ int queue_idx,
+ struct rte_eth_dev **eth_dev)
+{
+ const char *name = rte_vdev_device_name(dev);
+ const unsigned int numa_node = dev->device.numa_node;
+ struct pmd_internals *internals = NULL;
+ int ret;
+ int i;
+
+ internals = rte_zmalloc_socket(name, sizeof(*internals), 0, numa_node);
+ if (!internals)
+ return -ENOMEM;
+
+ 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)
+ 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 0;
+
+err:
+ rte_free(internals);
+ return -1;
+}
+
+static int
+rte_pmd_af_xdp_probe(struct rte_vdev_device *dev)
+{
+ struct rte_kvargs *kvlist;
+ char if_name[IFNAMSIZ];
+ int xsk_queue_idx = ETH_AF_XDP_DFLT_QUEUE_IDX;
+ struct rte_eth_dev *eth_dev = NULL;
+ const char *name;
+ int ret;
+
+ RTE_LOG(INFO, AF_XDP, "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) {
+ RTE_LOG(ERR, AF_XDP, "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) {
+ RTE_LOG(ERR, AF_XDP, "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) {
+ RTE_LOG(ERR, AF_XDP, "Invalid kvargs value\n");
+ return -EINVAL;
+ }
+
+ ret = init_internals(dev, if_name, xsk_queue_idx, ð_dev);
+ if (ret) {
+ RTE_LOG(ERR, AF_XDP, "Failed to init internals\n");
+ return ret;
+ }
+
+ 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;
+
+ RTE_LOG(INFO, AF_XDP, "Removing 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->umem->buf_ring);
+ rte_free(internals->umem->buffer);
+ 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(eth_af_xdp, pmd_af_xdp_drv);
+RTE_PMD_REGISTER_PARAM_STRING(eth_af_xdp,
+ "iface=<string> "
+ "queue=<int> ");
new file mode 100644
@@ -0,0 +1,3 @@
+DPDK_19.05 {
+ local: *;
+};
@@ -2,6 +2,7 @@
# Copyright(c) 2017 Intel Corporation
drivers = ['af_packet',
+ 'af_xdp',
'ark',
'atlantic',
'avp',
@@ -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 -lelf -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