new file mode 100644
@@ -0,0 +1,251 @@
+.. SPDX-License-Identifier: BSD-3-Clause
+ Copyright(c) 2023 Intel Corporation.
+
+Using a CNI with the AF_XDP driver
+==================================
+
+Introduction
+------------
+
+CNI, the Container Network Interface, is a technology for configuring container
+network interfaces and which can be used to setup Kubernetes networking. AF_XDP
+is a Linux socket Address Family that enables an XDP program to redirect packets
+to a memory buffer in userspace.
+
+This document explains how to enable the `AF_XDP Plugin for Kubernetes`_ within
+a DPDK application using the `AF_XDP PMD`_ to connect and use these technologies.
+
+.. _AF_XDP Plugin for Kubernetes: https://github.com/intel/afxdp-plugins-for-kubernetes
+
+Background
+----------
+
+The standard `AF_XDP PMD`_ initialization process involves loading an eBPF program
+onto the kernel netdev to be used by the PMD. This operation requires root or
+escalated Linux privileges and thus prevents the PMD from working in an
+unprivileged container. The AF_XDP CNI plugin handles this situation by
+providing a device plugin that performs the program loading.
+
+At a technical level the CNI opens a Unix Domain Socket and listens for a client
+to make requests over that socket. A DPDK application acting as a client
+connects and initiates a configuration "handshake". The client then receives a
+file descriptor which points to the XSKMAP associated with the loaded eBPF
+program. The XSKMAP is a BPF map of AF_XDP sockets (XSK). The client can then
+proceed with creating an AF_XDP socket and inserting that socket into the XSKMAP
+pointed to by the descriptor.
+
+The EAL vdev argument ``use_cni`` is used to indicate that the user wishes to
+run the PMD in unprivileged mode and to receive the XSKMAP file descriptor from
+the CNI. When this flag is set, the ``XSK_LIBBPF_FLAGS__INHIBIT_PROG_LOAD``
+libbpf flag should be used when creating the socket to instruct libbpf not to
+load the default libbpf program on the netdev. Instead the loading is handled by
+the CNI.
+
+.. _AF_XDP PMD: https://doc.dpdk.org/guides/nics/af_xdp.html
+
+.. Note::
+
+ The Unix Domain Socket file path appear in the end user is "/tmp/afxdp.sock".
+
+Prerequisites
+-------------
+
+Docker and container prerequisites:
+
+* Set up the device plugin as described in the instructions for `AF_XDP Plugin
+ for Kubernetes`_.
+
+* The Docker image should contain the libbpf and libxdp libraries, which
+ are dependencies for AF_XDP, and should include support for the ``ethtool``
+ command.
+
+* The Pod should have enabled the capabilities ``CAP_NET_RAW`` and ``CAP_BPF``
+ for AF_XDP along with support for hugepages.
+
+* Increase locked memory limit so containers have enough memory for packet
+ buffers.
+ For example:
+
+ .. code-block:: console
+
+ cat << EOF | sudo tee /etc/systemd/system/containerd.service.d/limits.conf
+ [Service]
+ LimitMEMLOCK=infinity
+ EOF
+
+* dpdk-testpmd application should have AF_XDP Feature enabled.
+
+ For further information see the docs for the: :doc:`../../nics/af_xdp`.
+
+
+Example
+-------
+
+Howto run dpdk-testpmd with CNI plugin:
+
+* Clone the CNI plugin
+
+ .. code-block:: console
+
+ # git clone https://github.com/intel/afxdp-plugins-for-kubernetes.git
+
+* Build the CNI plugin
+
+ .. code-block:: console
+
+ # cd afxdp-plugins-for-kubernetes/
+ # make build
+
+ .. Note::
+
+ CNI plugin has a dependence on the config.json.
+
+ Sample Config.json
+
+ .. code-block:: json
+
+ {
+ "logLevel":"debug",
+ "logFile":"afxdp-dp-e2e.log",
+ "pools":[
+ {
+ "name":"e2e",
+ "mode":"primary",
+ "timeout":30,
+ "ethtoolCmds" : ["-L -device- combined 1"],
+ "devices":[
+ {
+ "name":"ens785f0"
+ }
+ ]
+ }
+ ]
+ }
+
+ For further reference please use the `config.json`_
+
+ .. _config.json: https://github.com/intel/afxdp-plugins-for-kubernetes/blob/v0.0.2/test/e2e/config.json
+
+* Create the Network Attachment definition
+
+ .. code-block:: console
+
+ # kubectl create -f nad.yaml
+
+ Sample nad.yml
+
+ .. code-block:: yaml
+
+ apiVersion: "k8s.cni.cncf.io/v1"
+ kind: NetworkAttachmentDefinition
+ metadata:
+ name: afxdp-e2e-test
+ annotations:
+ k8s.v1.cni.cncf.io/resourceName: afxdp/e2e
+ spec:
+ config: '{
+ "cniVersion": "0.3.0",
+ "type": "afxdp",
+ "mode": "cdq",
+ "logFile": "afxdp-cni-e2e.log",
+ "logLevel": "debug",
+ "ipam": {
+ "type": "host-local",
+ "subnet": "192.168.1.0/24",
+ "rangeStart": "192.168.1.200",
+ "rangeEnd": "192.168.1.216",
+ "routes": [
+ { "dst": "0.0.0.0/0" }
+ ],
+ "gateway": "192.168.1.1"
+ }
+ }'
+
+ For further reference please use the `nad.yaml`_
+
+ .. _nad.yaml: https://github.com/intel/afxdp-plugins-for-kubernetes/blob/v0.0.2/test/e2e/nad.yaml
+
+* Build the Docker image
+
+ .. code-block:: console
+
+ # docker build -t afxdp-e2e-test -f Dockerfile .
+
+ Sample Dockerfile:
+
+ .. code-block:: console
+
+ FROM ubuntu:20.04
+ RUN apt-get update -y
+ RUN apt install build-essential libelf-dev -y
+ RUN apt-get install iproute2 acl -y
+ RUN apt install python3-pyelftools ethtool -y
+ RUN apt install libnuma-dev libjansson-dev libpcap-dev net-tools -y
+ RUN apt-get install clang llvm -y
+ COPY ./libbpf<version>.tar.gz /tmp
+ RUN cd /tmp && tar -xvmf libbpf<version>.tar.gz && cd libbpf/src && make install
+ COPY ./libxdp<version>.tar.gz /tmp
+ RUN cd /tmp && tar -xvmf libxdp<version>.tar.gz && cd libxdp && make install
+
+ .. Note::
+
+ All the files that need to COPY-ed should be in the same directory as the Dockerfile
+
+* Run the Pod
+
+ .. code-block:: console
+
+ # kubectl create -f pod.yaml
+
+ Sample pod.yaml:
+
+ .. code-block:: yaml
+
+ apiVersion: v1
+ kind: Pod
+ metadata:
+ name: afxdp-e2e-test
+ annotations:
+ k8s.v1.cni.cncf.io/networks: afxdp-e2e-test
+ spec:
+ containers:
+ - name: afxdp
+ image: afxdp-e2e-test:latest
+ imagePullPolicy: Never
+ env:
+ - name: LD_LIBRARY_PATH
+ value: /usr/lib64/:/usr/local/lib/
+ command: ["tail", "-f", "/dev/null"]
+ securityContext:
+ capabilities:
+ add:
+ - CAP_NET_RAW
+ - CAP_BPF
+ resources:
+ requests:
+ hugepages-2Mi: 2Gi
+ memory: 2Gi
+ afxdp/e2e: '1'
+ limits:
+ hugepages-2Mi: 2Gi
+ memory: 2Gi
+ afxdp/e2e: '1'
+
+ For further reference please use the `pod.yaml`_
+
+ .. _pod.yaml: https://github.com/intel/afxdp-plugins-for-kubernetes/blob/v0.0.2/test/e2e/pod-1c1d.yaml
+
+* Run DPDK with a command like the following:
+
+ .. code-block:: console
+
+ kubectl exec -i <Pod name> --container <containers name> -- \
+ /<Path>/dpdk-testpmd -l 0,1 --no-pci \
+ --vdev=net_af_xdp0,use_cni=1,iface=<interface name> \
+ -- --no-mlockall --in-memory
+
+
+For further reference please use the `e2e`_ test case in `AF_XDP Plugin for Kubernetes`_
+
+
+ .. _e2e: https://github.com/intel/afxdp-plugins-for-kubernetes/tree/v0.0.2/test/e2e
@@ -21,3 +21,4 @@ HowTo Guides
debug_troubleshoot
openwrt
avx512
+ af_xdp_cni
@@ -151,6 +151,17 @@ instead of zero copy mode (if available).
--vdev net_af_xdp,iface=ens786f1,force_copy=1
+use_cni
+~~~~~~~
+
+The EAL vdev argument use_cni is used to indicate that the user wishes to
+enable the `AF_XDP Plugin for Kubernetes`_ within a DPDK application.
+
+.. _AF_XDP Plugin for Kubernetes: https://github.com/intel/afxdp-plugins-for-kubernetes
+
+.. code-block:: console
+
+ --vdev=net_af_xdp0,use_cni=1
Limitations
-----------
@@ -7,6 +7,7 @@
#include <string.h>
#include <netinet/in.h>
#include <net/if.h>
+#include <sys/un.h>
#include <sys/socket.h>
#include <sys/ioctl.h>
#include <linux/if_ether.h>
@@ -81,6 +82,23 @@ RTE_LOG_REGISTER_DEFAULT(af_xdp_logtype, NOTICE);
#define ETH_AF_XDP_MP_KEY "afxdp_mp_send_fds"
+#define MAX_LONG_OPT_SZ 64
+#define UDS_MAX_FD_NUM 2
+#define UDS_MAX_CMD_LEN 64
+#define UDS_MAX_CMD_RESP 128
+#define UDS_XSK_MAP_FD_MSG "/xsk_map_fd"
+#define UDS_SOCK "/tmp/afxdp.sock"
+#define UDS_CONNECT_MSG "/connect"
+#define UDS_HOST_OK_MSG "/host_ok"
+#define UDS_HOST_NAK_MSG "/host_nak"
+#define UDS_VERSION_MSG "/version"
+#define UDS_XSK_MAP_FD_MSG "/xsk_map_fd"
+#define UDS_XSK_SOCKET_MSG "/xsk_socket"
+#define UDS_FD_ACK_MSG "/fd_ack"
+#define UDS_FD_NAK_MSG "/fd_nak"
+#define UDS_FIN_MSG "/fin"
+#define UDS_FIN_ACK_MSG "/fin_ack"
+
static int afxdp_dev_count;
/* Message header to synchronize fds via IPC */
@@ -151,6 +169,7 @@ struct pmd_internals {
char prog_path[PATH_MAX];
bool custom_prog_configured;
bool force_copy;
+ bool use_cni;
struct bpf_map *map;
struct rte_ether_addr eth_addr;
@@ -170,6 +189,7 @@ struct pmd_process_private {
#define ETH_AF_XDP_PROG_ARG "xdp_prog"
#define ETH_AF_XDP_BUDGET_ARG "busy_budget"
#define ETH_AF_XDP_FORCE_COPY_ARG "force_copy"
+#define ETH_AF_XDP_USE_CNI_ARG "use_cni"
static const char * const valid_arguments[] = {
ETH_AF_XDP_IFACE_ARG,
@@ -179,6 +199,7 @@ static const char * const valid_arguments[] = {
ETH_AF_XDP_PROG_ARG,
ETH_AF_XDP_BUDGET_ARG,
ETH_AF_XDP_FORCE_COPY_ARG,
+ ETH_AF_XDP_USE_CNI_ARG,
NULL
};
@@ -1129,7 +1150,8 @@ xsk_umem_info *xdp_umem_configure(struct pmd_internals *internals,
ret = xsk_umem__create(&umem->umem, base_addr, umem_size,
&rxq->fq, &rxq->cq, &usr_config);
if (ret) {
- AF_XDP_LOG(ERR, "Failed to create umem\n");
+ AF_XDP_LOG(ERR, "Failed to create umem [%d]: [%s]\n",
+ errno, strerror(errno));
goto err;
}
umem->buffer = base_addr;
@@ -1314,6 +1336,245 @@ configure_preferred_busy_poll(struct pkt_rx_queue *rxq)
return 0;
}
+static int
+init_uds_sock(struct sockaddr_un *server)
+{
+ int sock;
+
+ sock = socket(AF_UNIX, SOCK_SEQPACKET, 0);
+ if (sock < 0) {
+ AF_XDP_LOG(ERR, "Failed to opening stream socket\n");
+ return -1;
+ }
+
+ server->sun_family = AF_UNIX;
+ strlcpy(server->sun_path, UDS_SOCK, sizeof(server->sun_path));
+
+ if (connect(sock, (struct sockaddr *)server, sizeof(struct sockaddr_un)) < 0) {
+ close(sock);
+ AF_XDP_LOG(ERR, "Error connecting stream socket errno = [%d]: [%s]\n",
+ errno, strerror(errno));
+ return -1;
+ }
+
+ return sock;
+}
+
+struct msg_internal {
+ char response[UDS_MAX_CMD_RESP];
+ int len_param;
+ int num_fds;
+ int fds[UDS_MAX_FD_NUM];
+};
+
+static int
+send_msg(int sock, char *request, int *fd)
+{
+ int snd;
+ struct iovec iov;
+ struct msghdr msgh;
+ struct cmsghdr *cmsg;
+ struct sockaddr_un dst;
+ char control[CMSG_SPACE(sizeof(*fd))];
+
+ memset(&dst, 0, sizeof(dst));
+ dst.sun_family = AF_UNIX;
+ strlcpy(dst.sun_path, UDS_SOCK, sizeof(dst.sun_path));
+
+ /* Initialize message header structure */
+ memset(&msgh, 0, sizeof(msgh));
+ memset(control, 0, sizeof(control));
+ iov.iov_base = request;
+ iov.iov_len = strlen(request);
+
+ msgh.msg_name = &dst;
+ msgh.msg_namelen = sizeof(dst);
+ msgh.msg_iov = &iov;
+ msgh.msg_iovlen = 1;
+ msgh.msg_control = control;
+ msgh.msg_controllen = sizeof(control);
+
+ /* Translate the FD. */
+ cmsg = CMSG_FIRSTHDR(&msgh);
+ cmsg->cmsg_len = CMSG_LEN(sizeof(*fd));
+ cmsg->cmsg_level = SOL_SOCKET;
+ cmsg->cmsg_type = SCM_RIGHTS;
+ memcpy(CMSG_DATA(cmsg), fd, sizeof(*fd));
+
+ /* Send the request message. */
+ do {
+ snd = sendmsg(sock, &msgh, 0);
+ } while (snd < 0 && errno == EINTR);
+
+ return snd;
+}
+
+static int
+read_msg(int sock, char *response, struct sockaddr_un *s, int *fd)
+{
+ int msglen;
+ struct msghdr msgh;
+ struct iovec iov;
+ char control[CMSG_SPACE(sizeof(*fd))];
+ struct cmsghdr *cmsg;
+
+ /* Initialize message header structure */
+ memset(&msgh, 0, sizeof(msgh));
+ iov.iov_base = response;
+ iov.iov_len = UDS_MAX_CMD_RESP;
+
+ msgh.msg_name = s;
+ msgh.msg_namelen = sizeof(*s);
+ msgh.msg_iov = &iov;
+ msgh.msg_iovlen = 1;
+ msgh.msg_control = control;
+ msgh.msg_controllen = sizeof(control);
+
+ msglen = recvmsg(sock, &msgh, 0);
+
+ /* zero length message means socket was closed */
+ if (msglen == 0)
+ return 0;
+
+ if (msglen < 0) {
+ AF_XDP_LOG(ERR, "recvmsg failed, %s\n", strerror(errno));
+ return -1;
+ }
+
+ /* read auxiliary FDs if any */
+ for (cmsg = CMSG_FIRSTHDR(&msgh); cmsg != NULL;
+ cmsg = CMSG_NXTHDR(&msgh, cmsg)) {
+ if (cmsg->cmsg_level == SOL_SOCKET &&
+ cmsg->cmsg_type == SCM_RIGHTS) {
+ memcpy(fd, CMSG_DATA(cmsg), sizeof(*fd));
+ break;
+ }
+ }
+
+ response[msglen] = '\0';
+ return msglen;
+}
+
+static int
+make_request_cni(int sock, struct sockaddr_un *server, char *request,
+ int *req_fd, char *response, int *out_fd)
+{
+ int rval;
+
+ AF_XDP_LOG(DEBUG, "Request: [%s]\n", request);
+
+ /* if no file descriptor to send then directly write to socket.
+ * else use sendmsg() to send the file descriptor.
+ */
+ if (req_fd == NULL)
+ rval = write(sock, request, strlen(request));
+ else
+ rval = send_msg(sock, request, req_fd);
+
+ if (rval < 0) {
+ AF_XDP_LOG(ERR, "Write error %s\n", strerror(errno));
+ return -1;
+ }
+
+ rval = read_msg(sock, response, server, out_fd);
+ if (rval <= 0) {
+ AF_XDP_LOG(ERR, "Read error %d\n", rval);
+ return -1;
+ }
+ AF_XDP_LOG(DEBUG, "Response: [%s]\n", request);
+
+ return 0;
+}
+
+static int
+check_response(char *response, char *exp_resp, long size)
+{
+ return strncmp(response, exp_resp, size);
+}
+
+static int
+get_cni_fd(char *if_name)
+{
+ char request[UDS_MAX_CMD_LEN], response[UDS_MAX_CMD_RESP];
+ char hostname[MAX_LONG_OPT_SZ], exp_resp[UDS_MAX_CMD_RESP];
+ struct sockaddr_un server;
+ int xsk_map_fd = -1, out_fd = 0;
+ int sock, err;
+
+ err = gethostname(hostname, MAX_LONG_OPT_SZ - 1);
+ if (err)
+ return -1;
+
+ memset(&server, 0, sizeof(server));
+ sock = init_uds_sock(&server);
+
+ /* Initiates handshake to CNI send: /connect,hostname */
+ snprintf(request, sizeof(request), "%s,%s", UDS_CONNECT_MSG, hostname);
+ memset(response, 0, sizeof(response));
+ if (make_request_cni(sock, &server, request, NULL, response, &out_fd) < 0) {
+ AF_XDP_LOG(ERR, "Error in processing cmd [%s]\n", request);
+ goto err_close;
+ }
+
+ /* Expect /host_ok */
+ strlcpy(exp_resp, UDS_HOST_OK_MSG, UDS_MAX_CMD_LEN);
+ if (check_response(response, exp_resp, strlen(exp_resp)) < 0) {
+ AF_XDP_LOG(ERR, "Unexpected response [%s]\n", response);
+ goto err_close;
+ }
+ /* Request for "/version" */
+ strlcpy(request, UDS_VERSION_MSG, UDS_MAX_CMD_LEN);
+ memset(response, 0, sizeof(response));
+ if (make_request_cni(sock, &server, request, NULL, response, &out_fd) < 0) {
+ AF_XDP_LOG(ERR, "Error in processing cmd [%s]\n", request);
+ goto err_close;
+ }
+
+ /* Request for file descriptor for netdev name*/
+ snprintf(request, sizeof(request), "%s,%s", UDS_XSK_MAP_FD_MSG, if_name);
+ memset(response, 0, sizeof(response));
+ if (make_request_cni(sock, &server, request, NULL, response, &out_fd) < 0) {
+ AF_XDP_LOG(ERR, "Error in processing cmd [%s]\n", request);
+ goto err_close;
+ }
+
+ if (out_fd < 0) {
+ AF_XDP_LOG(ERR, "Error in processing cmd [%s]\n", request);
+ goto err_close;
+ }
+
+ xsk_map_fd = out_fd;
+
+ /* Expect fd_ack with file descriptor */
+ strlcpy(exp_resp, UDS_FD_ACK_MSG, UDS_MAX_CMD_LEN);
+ if (check_response(response, exp_resp, strlen(exp_resp)) < 0) {
+ AF_XDP_LOG(ERR, "Unexpected response [%s]\n", response);
+ goto err_close;
+ }
+
+ /* Initiate close connection */
+ strlcpy(request, UDS_FIN_MSG, UDS_MAX_CMD_LEN);
+ memset(response, 0, sizeof(response));
+ if (make_request_cni(sock, &server, request, NULL, response, &out_fd) < 0) {
+ AF_XDP_LOG(ERR, "Error in processing cmd [%s]\n", request);
+ goto err_close;
+ }
+
+ /* Connection close */
+ strlcpy(exp_resp, UDS_FIN_ACK_MSG, UDS_MAX_CMD_LEN);
+ if (check_response(response, exp_resp, strlen(exp_resp)) < 0) {
+ AF_XDP_LOG(ERR, "Unexpected response [%s]\n", response);
+ goto err_close;
+ }
+ close(sock);
+
+ return xsk_map_fd;
+
+err_close:
+ close(sock);
+ return -1;
+}
+
static int
xsk_configure(struct pmd_internals *internals, struct pkt_rx_queue *rxq,
int ring_size)
@@ -1362,6 +1623,10 @@ xsk_configure(struct pmd_internals *internals, struct pkt_rx_queue *rxq,
cfg.bind_flags |= XDP_USE_NEED_WAKEUP;
#endif
+ /* Disable libbpf from loading XDP program */
+ if (internals->use_cni)
+ cfg.libbpf_flags |= XSK_LIBBPF_FLAGS__INHIBIT_PROG_LOAD;
+
if (strnlen(internals->prog_path, PATH_MAX)) {
if (!internals->custom_prog_configured) {
ret = load_custom_xdp_prog(internals->prog_path,
@@ -1413,7 +1678,23 @@ xsk_configure(struct pmd_internals *internals, struct pkt_rx_queue *rxq,
}
}
- if (rxq->busy_budget) {
+ if (internals->use_cni) {
+ int err, fd, map_fd;
+
+ /* get socket fd from CNI plugin */
+ map_fd = get_cni_fd(internals->if_name);
+ if (map_fd < 0) {
+ AF_XDP_LOG(ERR, "Failed to receive CNI plugin fd\n");
+ goto out_xsk;
+ }
+ /* get socket fd */
+ fd = xsk_socket__fd(rxq->xsk);
+ err = bpf_map_update_elem(map_fd, &rxq->xsk_queue_idx, &fd, 0);
+ if (err) {
+ AF_XDP_LOG(ERR, "Failed to insert unprivileged xsk in map.\n");
+ goto out_xsk;
+ }
+ } else if (rxq->busy_budget) {
ret = configure_preferred_busy_poll(rxq);
if (ret) {
AF_XDP_LOG(ERR, "Failed configure busy polling.\n");
@@ -1584,6 +1865,27 @@ static const struct eth_dev_ops ops = {
.get_monitor_addr = eth_get_monitor_addr,
};
+/* CNI option works in unprivileged container environment
+ * and ethernet device functionality will be reduced. So
+ * additional customiszed eth_dev_ops struct is needed
+ * for cni. Promiscuous enable and disable functionality
+ * is removed.
+ **/
+static const struct eth_dev_ops ops_cni = {
+ .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,
+ .rx_queue_setup = eth_rx_queue_setup,
+ .tx_queue_setup = eth_tx_queue_setup,
+ .link_update = eth_link_update,
+ .stats_get = eth_stats_get,
+ .stats_reset = eth_stats_reset,
+ .get_monitor_addr = eth_get_monitor_addr,
+};
+
/** parse busy_budget argument */
static int
parse_budget_arg(const char *key __rte_unused,
@@ -1704,8 +2006,8 @@ xdp_get_channels_info(const char *if_name, int *max_queues,
static int
parse_parameters(struct rte_kvargs *kvlist, char *if_name, int *start_queue,
- int *queue_cnt, int *shared_umem, char *prog_path,
- int *busy_budget, int *force_copy)
+ int *queue_cnt, int *shared_umem, char *prog_path,
+ int *busy_budget, int *force_copy, int *use_cni)
{
int ret;
@@ -1746,6 +2048,11 @@ parse_parameters(struct rte_kvargs *kvlist, char *if_name, int *start_queue,
if (ret < 0)
goto free_kvlist;
+ ret = rte_kvargs_process(kvlist, ETH_AF_XDP_USE_CNI_ARG,
+ &parse_integer_arg, use_cni);
+ if (ret < 0)
+ goto free_kvlist;
+
free_kvlist:
rte_kvargs_free(kvlist);
return ret;
@@ -1783,8 +2090,9 @@ get_iface_info(const char *if_name,
static struct rte_eth_dev *
init_internals(struct rte_vdev_device *dev, const char *if_name,
- int start_queue_idx, int queue_cnt, int shared_umem,
- const char *prog_path, int busy_budget, int force_copy)
+ int start_queue_idx, int queue_cnt, int shared_umem,
+ const char *prog_path, int busy_budget, int force_copy,
+ int use_cni)
{
const char *name = rte_vdev_device_name(dev);
const unsigned int numa_node = dev->device.numa_node;
@@ -1813,6 +2121,7 @@ init_internals(struct rte_vdev_device *dev, const char *if_name,
#endif
internals->shared_umem = shared_umem;
internals->force_copy = force_copy;
+ internals->use_cni = use_cni;
if (xdp_get_channels_info(if_name, &internals->max_queue_cnt,
&internals->combined_queue_cnt)) {
@@ -1871,7 +2180,11 @@ init_internals(struct rte_vdev_device *dev, const char *if_name,
eth_dev->data->dev_link = pmd_link;
eth_dev->data->mac_addrs = &internals->eth_addr;
eth_dev->data->dev_flags |= RTE_ETH_DEV_AUTOFILL_QUEUE_XSTATS;
- eth_dev->dev_ops = &ops;
+ if (!internals->use_cni)
+ eth_dev->dev_ops = &ops;
+ else
+ eth_dev->dev_ops = &ops_cni;
+
eth_dev->rx_pkt_burst = eth_af_xdp_rx;
eth_dev->tx_pkt_burst = eth_af_xdp_tx;
eth_dev->process_private = process_private;
@@ -1998,6 +2311,7 @@ rte_pmd_af_xdp_probe(struct rte_vdev_device *dev)
char prog_path[PATH_MAX] = {'\0'};
int busy_budget = -1, ret;
int force_copy = 0;
+ int use_cni = 0;
struct rte_eth_dev *eth_dev = NULL;
const char *name = rte_vdev_device_name(dev);
@@ -2043,7 +2357,7 @@ rte_pmd_af_xdp_probe(struct rte_vdev_device *dev)
if (parse_parameters(kvlist, if_name, &xsk_start_queue_idx,
&xsk_queue_cnt, &shared_umem, prog_path,
- &busy_budget, &force_copy) < 0) {
+ &busy_budget, &force_copy, &use_cni) < 0) {
AF_XDP_LOG(ERR, "Invalid kvargs value\n");
return -EINVAL;
}
@@ -2057,8 +2371,8 @@ rte_pmd_af_xdp_probe(struct rte_vdev_device *dev)
busy_budget;
eth_dev = init_internals(dev, if_name, xsk_start_queue_idx,
- xsk_queue_cnt, shared_umem, prog_path,
- busy_budget, force_copy);
+ xsk_queue_cnt, shared_umem, prog_path,
+ busy_budget, force_copy, use_cni);
if (eth_dev == NULL) {
AF_XDP_LOG(ERR, "Failed to init internals\n");
return -1;
@@ -2118,4 +2432,5 @@ RTE_PMD_REGISTER_PARAM_STRING(net_af_xdp,
"shared_umem=<int> "
"xdp_prog=<string> "
"busy_budget=<int> "
- "force_copy=<int> ");
+ "force_copy=<int> "
+ "use_cni=<int> ");