-/*-
- * BSD LICENSE
- *
- * Copyright(c) 2014 John W. Linville <linville@tuxdriver.com>
- *
- * Originally based upon librte_pmd_pcap code:
- *
- * Copyright(c) 2010-2015 Intel Corporation. All rights reserved.
- * Copyright(c) 2014 6WIND S.A.
- * All rights reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- * * Redistributions of source code must retain the above copyright
- * notice, this list of conditions and the following disclaimer.
- * * Redistributions in binary form must reproduce the above copyright
- * notice, this list of conditions and the following disclaimer in
- * the documentation and/or other materials provided with the
- * distribution.
- * * Neither the name of Intel Corporation nor the names of its
- * contributors may be used to endorse or promote products derived
- * from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2014 John W. Linville <linville@tuxdriver.com>
+ * Originally based upon librte_pmd_pcap code:
+ * Copyright(c) 2010-2015 Intel Corporation.
+ * Copyright(c) 2014 6WIND S.A.
+ * All rights reserved.
*/
+#include <rte_string_fns.h>
#include <rte_mbuf.h>
-#include <rte_ethdev.h>
+#include <ethdev_driver.h>
+#include <ethdev_vdev.h>
#include <rte_malloc.h>
#include <rte_kvargs.h>
-#include <rte_vdev.h>
+#include <rte_bus_vdev.h>
+#include <errno.h>
#include <linux/if_ether.h>
#include <linux/if_packet.h>
#include <arpa/inet.h>
#include <net/if.h>
+#include <net/if_arp.h>
#include <sys/types.h>
#include <sys/socket.h>
#include <sys/ioctl.h>
+#include <string.h>
#include <sys/mman.h>
#include <unistd.h>
#include <poll.h>
#define ETH_AF_PACKET_BLOCKSIZE_ARG "blocksz"
#define ETH_AF_PACKET_FRAMESIZE_ARG "framesz"
#define ETH_AF_PACKET_FRAMECOUNT_ARG "framecnt"
+#define ETH_AF_PACKET_QDISC_BYPASS_ARG "qdisc_bypass"
-#define DFLT_BLOCK_SIZE (1 << 12)
#define DFLT_FRAME_SIZE (1 << 11)
#define DFLT_FRAME_COUNT (1 << 9)
-#define RTE_PMD_AF_PACKET_MAX_RINGS 16
-
struct pkt_rx_queue {
int sockfd;
unsigned int framenum;
struct rte_mempool *mb_pool;
- uint8_t in_port;
+ uint16_t in_port;
+ uint8_t vlan_strip;
volatile unsigned long rx_pkts;
- volatile unsigned long err_pkts;
volatile unsigned long rx_bytes;
};
struct pkt_tx_queue {
int sockfd;
+ unsigned int frame_data_size;
struct iovec *rd;
uint8_t *map;
unsigned nb_queues;
int if_index;
- struct ether_addr eth_addr;
+ char *if_name;
+ struct rte_ether_addr eth_addr;
struct tpacket_req req;
- struct pkt_rx_queue rx_queue[RTE_PMD_AF_PACKET_MAX_RINGS];
- struct pkt_tx_queue tx_queue[RTE_PMD_AF_PACKET_MAX_RINGS];
+ struct pkt_rx_queue *rx_queue;
+ struct pkt_tx_queue *tx_queue;
+ uint8_t vlan_strip;
};
static const char *valid_arguments[] = {
ETH_AF_PACKET_BLOCKSIZE_ARG,
ETH_AF_PACKET_FRAMESIZE_ARG,
ETH_AF_PACKET_FRAMECOUNT_ARG,
+ ETH_AF_PACKET_QDISC_BYPASS_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_SPEED_AUTONEG
+ .link_speed = RTE_ETH_SPEED_NUM_10G,
+ .link_duplex = RTE_ETH_LINK_FULL_DUPLEX,
+ .link_status = RTE_ETH_LINK_DOWN,
+ .link_autoneg = RTE_ETH_LINK_FIXED,
};
+RTE_LOG_REGISTER_DEFAULT(af_packet_logtype, NOTICE);
+
+#define PMD_LOG(level, fmt, args...) \
+ rte_log(RTE_LOG_ ## level, af_packet_logtype, \
+ "%s(): " fmt "\n", __func__, ##args)
+
+#define PMD_LOG_ERRNO(level, fmt, args...) \
+ rte_log(RTE_LOG_ ## level, af_packet_logtype, \
+ "%s(): " fmt ":%s\n", __func__, ##args, strerror(errno))
+
static uint16_t
eth_af_packet_rx(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts)
{
pbuf = (uint8_t *) ppd + ppd->tp_mac;
memcpy(rte_pktmbuf_mtod(mbuf, void *), pbuf, rte_pktmbuf_data_len(mbuf));
+ /* check for vlan info */
+ if (ppd->tp_status & TP_STATUS_VLAN_VALID) {
+ mbuf->vlan_tci = ppd->tp_vlan_tci;
+ mbuf->ol_flags |= (RTE_MBUF_F_RX_VLAN | RTE_MBUF_F_RX_VLAN_STRIPPED);
+
+ if (!pkt_q->vlan_strip && rte_vlan_insert(&mbuf))
+ PMD_LOG(ERR, "Failed to reinsert VLAN tag");
+ }
+
/* release incoming frame and advance ring buffer */
ppd->tp_status = TP_STATUS_KERNEL;
if (++framenum >= framecount)
return num_rx;
}
+/*
+ * Check if there is an available frame in the ring
+ */
+static inline bool
+tx_ring_status_available(uint32_t tp_status)
+{
+ /*
+ * We eliminate the timestamp status from the packet status.
+ * This should only matter if timestamping is enabled on the socket,
+ * but there is a bug in the kernel which is fixed in newer releases.
+ *
+ * See the following kernel commit for reference:
+ * commit 171c3b151118a2fe0fc1e2a9d1b5a1570cfe82d2
+ * net: packetmmap: fix only tx timestamp on request
+ */
+ tp_status &= ~(TP_STATUS_TS_SOFTWARE | TP_STATUS_TS_RAW_HARDWARE);
+
+ return tp_status == TP_STATUS_AVAILABLE;
+}
+
/*
* Callback to handle sending packets through a real NIC.
*/
framenum = pkt_q->framenum;
ppd = (struct tpacket2_hdr *) pkt_q->rd[framenum].iov_base;
for (i = 0; i < nb_pkts; i++) {
- /* point at the next incoming frame */
- if ((ppd->tp_status != TP_STATUS_AVAILABLE) &&
- (poll(&pfd, 1, -1) < 0))
+ mbuf = *bufs++;
+
+ /* drop oversized packets */
+ if (mbuf->pkt_len > pkt_q->frame_data_size) {
+ rte_pktmbuf_free(mbuf);
+ continue;
+ }
+
+ /* insert vlan info if necessary */
+ if (mbuf->ol_flags & RTE_MBUF_F_TX_VLAN) {
+ if (rte_vlan_insert(&mbuf)) {
+ rte_pktmbuf_free(mbuf);
continue;
+ }
+ }
+
+ /* point at the next incoming frame */
+ if (!tx_ring_status_available(ppd->tp_status)) {
+ if (poll(&pfd, 1, -1) < 0)
+ break;
+
+ /* poll() can return POLLERR if the interface is down */
+ if (pfd.revents & POLLERR)
+ break;
+ }
+
+ /*
+ * poll() will almost always return POLLOUT, even if there
+ * are no extra buffers available
+ *
+ * This happens, because packet_poll() calls datagram_poll()
+ * which checks the space left in the socket buffer and,
+ * in the case of packet_mmap, the default socket buffer length
+ * doesn't match the requested size for the tx_ring.
+ * As such, there is almost always space left in socket buffer,
+ * which doesn't seem to be correlated to the requested size
+ * for the tx_ring in packet_mmap.
+ *
+ * This results in poll() returning POLLOUT.
+ */
+ if (!tx_ring_status_available(ppd->tp_status))
+ break;
/* copy the tx frame data */
- mbuf = bufs[num_tx];
pbuf = (uint8_t *) ppd + TPACKET2_HDRLEN -
sizeof(struct sockaddr_ll);
- memcpy(pbuf, rte_pktmbuf_mtod(mbuf, void*), rte_pktmbuf_data_len(mbuf));
- ppd->tp_len = ppd->tp_snaplen = rte_pktmbuf_data_len(mbuf);
+
+ struct rte_mbuf *tmp_mbuf = mbuf;
+ while (tmp_mbuf) {
+ uint16_t data_len = rte_pktmbuf_data_len(tmp_mbuf);
+ memcpy(pbuf, rte_pktmbuf_mtod(tmp_mbuf, void*), data_len);
+ pbuf += data_len;
+ tmp_mbuf = tmp_mbuf->next;
+ }
+
+ ppd->tp_len = mbuf->pkt_len;
+ ppd->tp_snaplen = mbuf->pkt_len;
/* release incoming frame and advance ring buffer */
ppd->tp_status = TP_STATUS_SEND_REQUEST;
}
/* kick-off transmits */
- if (sendto(pkt_q->sockfd, NULL, 0, MSG_DONTWAIT, NULL, 0) == -1)
- return 0; /* error sending -- no packets transmitted */
+ if (sendto(pkt_q->sockfd, NULL, 0, MSG_DONTWAIT, NULL, 0) == -1 &&
+ errno != ENOBUFS && errno != EAGAIN) {
+ /*
+ * In case of a ENOBUFS/EAGAIN error all of the enqueued
+ * packets will be considered successful even though only some
+ * are sent.
+ */
+
+ num_tx = 0;
+ num_tx_bytes = 0;
+ }
pkt_q->framenum = framenum;
pkt_q->tx_pkts += num_tx;
- pkt_q->err_pkts += nb_pkts - num_tx;
+ pkt_q->err_pkts += i - num_tx;
pkt_q->tx_bytes += num_tx_bytes;
- return num_tx;
+ return i;
}
static int
eth_dev_start(struct rte_eth_dev *dev)
{
- dev->data->dev_link.link_status = ETH_LINK_UP;
+ dev->data->dev_link.link_status = RTE_ETH_LINK_UP;
return 0;
}
/*
* This function gets called when the current port gets stopped.
*/
-static void
+static int
eth_dev_stop(struct rte_eth_dev *dev)
{
unsigned i;
sockfd = internals->rx_queue[i].sockfd;
if (sockfd != -1)
close(sockfd);
- sockfd = internals->tx_queue[i].sockfd;
- if (sockfd != -1)
- close(sockfd);
+
+ /* Prevent use after free in case tx fd == rx fd */
+ if (sockfd != internals->tx_queue[i].sockfd) {
+ sockfd = internals->tx_queue[i].sockfd;
+ if (sockfd != -1)
+ close(sockfd);
+ }
+
+ internals->rx_queue[i].sockfd = -1;
+ internals->tx_queue[i].sockfd = -1;
}
- dev->data->dev_link.link_status = ETH_LINK_DOWN;
+ dev->data->dev_link.link_status = RTE_ETH_LINK_DOWN;
+ return 0;
}
static int
eth_dev_configure(struct rte_eth_dev *dev __rte_unused)
{
+ struct rte_eth_conf *dev_conf = &dev->data->dev_conf;
+ const struct rte_eth_rxmode *rxmode = &dev_conf->rxmode;
+ struct pmd_internals *internals = dev->data->dev_private;
+
+ internals->vlan_strip = !!(rxmode->offloads & RTE_ETH_RX_OFFLOAD_VLAN_STRIP);
return 0;
}
-static void
+static int
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_pktlen = RTE_ETHER_MAX_LEN;
dev_info->max_rx_queues = (uint16_t)internals->nb_queues;
dev_info->max_tx_queues = (uint16_t)internals->nb_queues;
dev_info->min_rx_bufsize = 0;
+ dev_info->tx_offload_capa = RTE_ETH_TX_OFFLOAD_MULTI_SEGS |
+ RTE_ETH_TX_OFFLOAD_VLAN_INSERT;
+ dev_info->rx_offload_capa = RTE_ETH_RX_OFFLOAD_VLAN_STRIP;
+
+ return 0;
}
-static void
+static int
eth_stats_get(struct rte_eth_dev *dev, struct rte_eth_stats *igb_stats)
{
unsigned i, imax;
internal->nb_queues : RTE_ETHDEV_QUEUE_STAT_CNTRS);
for (i = 0; i < imax; i++) {
igb_stats->q_opackets[i] = internal->tx_queue[i].tx_pkts;
- igb_stats->q_errors[i] = internal->tx_queue[i].err_pkts;
igb_stats->q_obytes[i] = internal->tx_queue[i].tx_bytes;
tx_total += igb_stats->q_opackets[i];
- tx_err_total += igb_stats->q_errors[i];
+ tx_err_total += internal->tx_queue[i].err_pkts;
tx_bytes_total += igb_stats->q_obytes[i];
}
igb_stats->opackets = tx_total;
igb_stats->oerrors = tx_err_total;
igb_stats->obytes = tx_bytes_total;
+ return 0;
}
-static void
+static int
eth_stats_reset(struct rte_eth_dev *dev)
{
unsigned i;
internal->tx_queue[i].err_pkts = 0;
internal->tx_queue[i].tx_bytes = 0;
}
-}
-static void
-eth_dev_close(struct rte_eth_dev *dev __rte_unused)
-{
+ return 0;
}
-static void
-eth_queue_release(void *q __rte_unused)
+static int
+eth_dev_close(struct rte_eth_dev *dev)
{
+ struct pmd_internals *internals;
+ struct tpacket_req *req;
+ unsigned int q;
+
+ if (rte_eal_process_type() != RTE_PROC_PRIMARY)
+ return 0;
+
+ PMD_LOG(INFO, "Closing AF_PACKET ethdev on NUMA socket %u",
+ rte_socket_id());
+
+ internals = dev->data->dev_private;
+ req = &internals->req;
+ for (q = 0; q < internals->nb_queues; q++) {
+ munmap(internals->rx_queue[q].map,
+ 2 * req->tp_block_size * req->tp_block_nr);
+ rte_free(internals->rx_queue[q].rd);
+ rte_free(internals->tx_queue[q].rd);
+ }
+ free(internals->if_name);
+ rte_free(internals->rx_queue);
+ rte_free(internals->tx_queue);
+
+ /* mac_addrs must not be freed alone because part of dev_private */
+ dev->data->mac_addrs = NULL;
+ return 0;
}
static int
{
struct pmd_internals *internals = dev->data->dev_private;
struct pkt_rx_queue *pkt_q = &internals->rx_queue[rx_queue_id];
- uint16_t buf_size;
+ unsigned int buf_size, data_size;
pkt_q->mb_pool = mb_pool;
/* Now get the space available for data in the mbuf */
- buf_size = (uint16_t)(rte_pktmbuf_data_room_size(pkt_q->mb_pool) -
- RTE_PKTMBUF_HEADROOM);
-
- if (ETH_FRAME_LEN > buf_size) {
- RTE_LOG(ERR, PMD,
- "%s: %d bytes will not fit in mbuf (%d bytes)\n",
- dev->data->name, ETH_FRAME_LEN, buf_size);
+ buf_size = rte_pktmbuf_data_room_size(pkt_q->mb_pool) -
+ RTE_PKTMBUF_HEADROOM;
+ data_size = internals->req.tp_frame_size;
+ data_size -= TPACKET2_HDRLEN - sizeof(struct sockaddr_ll);
+
+ if (data_size > buf_size) {
+ PMD_LOG(ERR,
+ "%s: %d bytes will not fit in mbuf (%d bytes)",
+ dev->device->name, data_size, buf_size);
return -ENOMEM;
}
dev->data->rx_queues[rx_queue_id] = pkt_q;
pkt_q->in_port = dev->data->port_id;
+ pkt_q->vlan_strip = internals->vlan_strip;
return 0;
}
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;
+ unsigned int data_size = internals->req.tp_frame_size -
+ TPACKET2_HDRLEN;
+
+ if (mtu > data_size)
+ return -EINVAL;
+
+ 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 int
+eth_dev_macaddr_set(struct rte_eth_dev *dev, struct rte_ether_addr *addr)
+{
+ struct pmd_internals *internals = dev->data->dev_private;
+ struct ifreq ifr = { };
+ int sockfd = internals->rx_queue[0].sockfd;
+ int ret;
+
+ if (sockfd == -1) {
+ PMD_LOG(ERR, "receive socket not found");
+ return -EINVAL;
+ }
+
+ strlcpy(ifr.ifr_name, internals->if_name, IFNAMSIZ);
+ ifr.ifr_hwaddr.sa_family = ARPHRD_ETHER;
+ memcpy(ifr.ifr_hwaddr.sa_data, addr, sizeof(*addr));
+ ret = ioctl(sockfd, SIOCSIFHWADDR, &ifr);
+
+ if (ret < 0) {
+ PMD_LOG_ERRNO(ERR, "ioctl(SIOCSIFHWADDR) failed");
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static int
+eth_dev_change_flags(char *if_name, uint32_t flags, uint32_t mask)
+{
+ struct ifreq ifr;
+ int ret = 0;
+ int s;
+
+ s = socket(PF_INET, SOCK_DGRAM, 0);
+ if (s < 0)
+ return -errno;
+
+ strlcpy(ifr.ifr_name, if_name, IFNAMSIZ);
+ if (ioctl(s, SIOCGIFFLAGS, &ifr) < 0) {
+ ret = -errno;
+ goto out;
+ }
+ ifr.ifr_flags &= mask;
+ ifr.ifr_flags |= flags;
+ if (ioctl(s, SIOCSIFFLAGS, &ifr) < 0) {
+ ret = -errno;
+ goto out;
+ }
+out:
+ close(s);
+ return ret;
+}
+
+static int
+eth_dev_promiscuous_enable(struct rte_eth_dev *dev)
+{
+ struct pmd_internals *internals = dev->data->dev_private;
+
+ return eth_dev_change_flags(internals->if_name, IFF_PROMISC, ~0);
+}
+
+static int
+eth_dev_promiscuous_disable(struct rte_eth_dev *dev)
+{
+ struct pmd_internals *internals = dev->data->dev_private;
+
+ return 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,
+ .mac_addr_set = eth_dev_macaddr_set,
+ .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,
/* Open an AF_PACKET socket... */
*sockfd = socket(AF_PACKET, SOCK_RAW, htons(ETH_P_ALL));
if (*sockfd == -1) {
- RTE_LOG(ERR, PMD, "Could not open AF_PACKET socket\n");
+ PMD_LOG(ERR, "Could not open AF_PACKET socket");
return -1;
}
}
static int
-rte_pmd_init_internals(const char *name,
+rte_pmd_init_internals(struct rte_vdev_device *dev,
const int sockfd,
const unsigned nb_queues,
unsigned int blocksize,
unsigned int blockcnt,
unsigned int framesize,
unsigned int framecnt,
- const unsigned numa_node,
+ unsigned int qdisc_bypass,
struct pmd_internals **internals,
struct rte_eth_dev **eth_dev,
struct rte_kvargs *kvlist)
{
+ const char *name = rte_vdev_device_name(dev);
+ const unsigned int numa_node = dev->device.numa_node;
struct rte_eth_dev_data *data = NULL;
struct rte_kvargs_pair *pair = NULL;
struct ifreq ifr;
int rc, tpver, discard;
int qsockfd = -1;
unsigned int i, q, rdsize;
- int fanout_arg __rte_unused, bypass __rte_unused;
+#if defined(PACKET_FANOUT)
+ int fanout_arg;
+#endif
for (k_idx = 0; k_idx < kvlist->count; k_idx++) {
pair = &kvlist->pairs[k_idx];
break;
}
if (pair == NULL) {
- RTE_LOG(ERR, PMD,
- "%s: no interface specified for AF_PACKET ethdev\n",
+ PMD_LOG(ERR,
+ "%s: no interface specified for AF_PACKET ethdev",
name);
- goto error_early;
+ return -1;
}
- RTE_LOG(INFO, PMD,
- "%s: creating AF_PACKET-backed ethdev on numa socket %u\n",
+ PMD_LOG(INFO,
+ "%s: creating AF_PACKET-backed ethdev on numa socket %u",
name, numa_node);
- /*
- * now do all data allocation - for eth_dev structure, dummy pci driver
- * and internal (private) data
- */
- data = rte_zmalloc_socket(name, sizeof(*data), 0, numa_node);
- if (data == NULL)
- goto error_early;
-
*internals = rte_zmalloc_socket(name, sizeof(**internals),
0, numa_node);
if (*internals == NULL)
- goto error_early;
+ return -1;
+
+
+ (*internals)->rx_queue = rte_calloc_socket("af_packet_rx",
+ nb_queues,
+ sizeof(struct pkt_rx_queue),
+ 0, numa_node);
+ (*internals)->tx_queue = rte_calloc_socket("af_packet_tx",
+ nb_queues,
+ sizeof(struct pkt_tx_queue),
+ 0, numa_node);
+ if (!(*internals)->rx_queue || !(*internals)->tx_queue) {
+ goto free_internals;
+ }
for (q = 0; q < nb_queues; q++) {
(*internals)->rx_queue[q].map = MAP_FAILED;
(*internals)->tx_queue[q].map = MAP_FAILED;
+ (*internals)->rx_queue[q].sockfd = -1;
+ (*internals)->tx_queue[q].sockfd = -1;
}
req = &((*internals)->req);
memcpy(ifr.ifr_name, pair->value, ifnamelen);
ifr.ifr_name[ifnamelen] = '\0';
} else {
- RTE_LOG(ERR, PMD,
- "%s: I/F name too long (%s)\n",
+ PMD_LOG(ERR,
+ "%s: I/F name too long (%s)",
name, pair->value);
- goto error_early;
+ goto free_internals;
}
if (ioctl(sockfd, SIOCGIFINDEX, &ifr) == -1) {
- RTE_LOG(ERR, PMD,
- "%s: ioctl failed (SIOCGIFINDEX)\n",
- name);
- goto error_early;
+ PMD_LOG_ERRNO(ERR, "%s: ioctl failed (SIOCGIFINDEX)", name);
+ goto free_internals;
}
+ (*internals)->if_name = strdup(pair->value);
+ if ((*internals)->if_name == NULL)
+ goto free_internals;
(*internals)->if_index = ifr.ifr_ifindex;
if (ioctl(sockfd, SIOCGIFHWADDR, &ifr) == -1) {
- RTE_LOG(ERR, PMD,
- "%s: ioctl failed (SIOCGIFHWADDR)\n",
- name);
- goto error_early;
+ PMD_LOG_ERRNO(ERR, "%s: ioctl failed (SIOCGIFHWADDR)", name);
+ goto free_internals;
}
memcpy(&(*internals)->eth_addr, ifr.ifr_hwaddr.sa_data, ETH_ALEN);
/* Open an AF_PACKET socket for this queue... */
qsockfd = socket(AF_PACKET, SOCK_RAW, htons(ETH_P_ALL));
if (qsockfd == -1) {
- RTE_LOG(ERR, PMD,
- "%s: could not open AF_PACKET socket\n",
- name);
- return -1;
+ PMD_LOG_ERRNO(ERR,
+ "%s: could not open AF_PACKET socket",
+ name);
+ goto error;
}
tpver = TPACKET_V2;
rc = setsockopt(qsockfd, SOL_PACKET, PACKET_VERSION,
&tpver, sizeof(tpver));
if (rc == -1) {
- RTE_LOG(ERR, PMD,
- "%s: could not set PACKET_VERSION on AF_PACKET "
- "socket for %s\n", name, pair->value);
+ PMD_LOG_ERRNO(ERR,
+ "%s: could not set PACKET_VERSION on AF_PACKET socket for %s",
+ name, pair->value);
goto error;
}
rc = setsockopt(qsockfd, SOL_PACKET, PACKET_LOSS,
&discard, sizeof(discard));
if (rc == -1) {
- RTE_LOG(ERR, PMD,
- "%s: could not set PACKET_LOSS on "
- "AF_PACKET socket for %s\n", name, pair->value);
+ PMD_LOG_ERRNO(ERR,
+ "%s: could not set PACKET_LOSS on AF_PACKET socket for %s",
+ name, pair->value);
goto error;
}
+ if (qdisc_bypass) {
#if defined(PACKET_QDISC_BYPASS)
- bypass = 1;
- rc = setsockopt(qsockfd, SOL_PACKET, PACKET_QDISC_BYPASS,
- &bypass, sizeof(bypass));
- if (rc == -1) {
- RTE_LOG(ERR, PMD,
- "%s: could not set PACKET_QDISC_BYPASS "
- "on AF_PACKET socket for %s\n", name,
- pair->value);
- goto error;
- }
+ rc = setsockopt(qsockfd, SOL_PACKET, PACKET_QDISC_BYPASS,
+ &qdisc_bypass, sizeof(qdisc_bypass));
+ if (rc == -1) {
+ PMD_LOG_ERRNO(ERR,
+ "%s: could not set PACKET_QDISC_BYPASS on AF_PACKET socket for %s",
+ name, pair->value);
+ goto error;
+ }
#endif
+ }
rc = setsockopt(qsockfd, SOL_PACKET, PACKET_RX_RING, req, sizeof(*req));
if (rc == -1) {
- RTE_LOG(ERR, PMD,
- "%s: could not set PACKET_RX_RING on AF_PACKET "
- "socket for %s\n", name, pair->value);
+ PMD_LOG_ERRNO(ERR,
+ "%s: could not set PACKET_RX_RING on AF_PACKET socket for %s",
+ name, pair->value);
goto error;
}
rc = setsockopt(qsockfd, SOL_PACKET, PACKET_TX_RING, req, sizeof(*req));
if (rc == -1) {
- RTE_LOG(ERR, PMD,
+ PMD_LOG_ERRNO(ERR,
"%s: could not set PACKET_TX_RING on AF_PACKET "
- "socket for %s\n", name, pair->value);
+ "socket for %s", name, pair->value);
goto error;
}
PROT_READ | PROT_WRITE, MAP_SHARED | MAP_LOCKED,
qsockfd, 0);
if (rx_queue->map == MAP_FAILED) {
- RTE_LOG(ERR, PMD,
- "%s: call to mmap failed on AF_PACKET socket for %s\n",
+ PMD_LOG_ERRNO(ERR,
+ "%s: call to mmap failed on AF_PACKET socket for %s",
name, pair->value);
goto error;
}
tx_queue = &((*internals)->tx_queue[q]);
tx_queue->framecount = req->tp_frame_nr;
+ tx_queue->frame_data_size = req->tp_frame_size;
+ tx_queue->frame_data_size -= TPACKET2_HDRLEN -
+ sizeof(struct sockaddr_ll);
tx_queue->map = rx_queue->map + req->tp_block_size * req->tp_block_nr;
rc = bind(qsockfd, (const struct sockaddr*)&sockaddr, sizeof(sockaddr));
if (rc == -1) {
- RTE_LOG(ERR, PMD,
- "%s: could not bind AF_PACKET socket to %s\n",
- name, pair->value);
+ PMD_LOG_ERRNO(ERR,
+ "%s: could not bind AF_PACKET socket to %s",
+ name, pair->value);
goto error;
}
rc = setsockopt(qsockfd, SOL_PACKET, PACKET_FANOUT,
&fanout_arg, sizeof(fanout_arg));
if (rc == -1) {
- RTE_LOG(ERR, PMD,
- "%s: could not set PACKET_FANOUT on AF_PACKET socket "
- "for %s\n", name, pair->value);
+ PMD_LOG_ERRNO(ERR,
+ "%s: could not set PACKET_FANOUT on AF_PACKET socket for %s",
+ name, pair->value);
goto error;
}
#endif
}
/* reserve an ethdev entry */
- *eth_dev = rte_eth_dev_allocate(name);
+ *eth_dev = rte_eth_vdev_allocate(dev, 0);
if (*eth_dev == NULL)
goto error;
(*internals)->nb_queues = nb_queues;
+ data = (*eth_dev)->data;
data->dev_private = *internals;
- data->port_id = (*eth_dev)->data->port_id;
data->nb_rx_queues = (uint16_t)nb_queues;
data->nb_tx_queues = (uint16_t)nb_queues;
data->dev_link = pmd_link;
data->mac_addrs = &(*internals)->eth_addr;
- strncpy(data->name,
- (*eth_dev)->data->name, strlen((*eth_dev)->data->name));
+ data->dev_flags |= RTE_ETH_DEV_AUTOFILL_QUEUE_XSTATS;
- (*eth_dev)->data = data;
(*eth_dev)->dev_ops = &ops;
- (*eth_dev)->driver = NULL;
- (*eth_dev)->data->dev_flags = RTE_ETH_DEV_DETACHABLE;
- (*eth_dev)->data->drv_name = "AF_PACKET PMD";
- (*eth_dev)->data->kdrv = RTE_KDRV_NONE;
- (*eth_dev)->data->numa_node = numa_node;
return 0;
if (qsockfd != -1)
close(qsockfd);
for (q = 0; q < nb_queues; q++) {
- munmap((*internals)->rx_queue[q].map,
- 2 * req->tp_block_size * req->tp_block_nr);
+ if ((*internals)->rx_queue[q].map != MAP_FAILED)
+ munmap((*internals)->rx_queue[q].map,
+ 2 * req->tp_block_size * req->tp_block_nr);
rte_free((*internals)->rx_queue[q].rd);
rte_free((*internals)->tx_queue[q].rd);
- if (((*internals)->rx_queue[q].sockfd != 0) &&
+ if (((*internals)->rx_queue[q].sockfd >= 0) &&
((*internals)->rx_queue[q].sockfd != qsockfd))
close((*internals)->rx_queue[q].sockfd);
}
+free_internals:
+ rte_free((*internals)->rx_queue);
+ rte_free((*internals)->tx_queue);
+ free((*internals)->if_name);
rte_free(*internals);
-error_early:
- rte_free(data);
return -1;
}
static int
-rte_eth_from_packet(const char *name,
+rte_eth_from_packet(struct rte_vdev_device *dev,
int const *sockfd,
- const unsigned numa_node,
struct rte_kvargs *kvlist)
{
+ const char *name = rte_vdev_device_name(dev);
struct pmd_internals *internals = NULL;
struct rte_eth_dev *eth_dev = NULL;
struct rte_kvargs_pair *pair = NULL;
unsigned k_idx;
unsigned int blockcount;
- unsigned int blocksize = DFLT_BLOCK_SIZE;
+ unsigned int blocksize;
unsigned int framesize = DFLT_FRAME_SIZE;
unsigned int framecount = DFLT_FRAME_COUNT;
unsigned int qpairs = 1;
+ unsigned int qdisc_bypass = 1;
/* do some parameter checking */
if (*sockfd < 0)
return -1;
+ blocksize = getpagesize();
+
/*
* Walk arguments for configurable settings
*/
pair = &kvlist->pairs[k_idx];
if (strstr(pair->key, ETH_AF_PACKET_NUM_Q_ARG) != NULL) {
qpairs = atoi(pair->value);
- if (qpairs < 1 ||
- qpairs > RTE_PMD_AF_PACKET_MAX_RINGS) {
- RTE_LOG(ERR, PMD,
- "%s: invalid qpairs value\n",
+ if (qpairs < 1) {
+ PMD_LOG(ERR,
+ "%s: invalid qpairs value",
name);
return -1;
}
if (strstr(pair->key, ETH_AF_PACKET_BLOCKSIZE_ARG) != NULL) {
blocksize = atoi(pair->value);
if (!blocksize) {
- RTE_LOG(ERR, PMD,
- "%s: invalid blocksize value\n",
+ PMD_LOG(ERR,
+ "%s: invalid blocksize value",
name);
return -1;
}
if (strstr(pair->key, ETH_AF_PACKET_FRAMESIZE_ARG) != NULL) {
framesize = atoi(pair->value);
if (!framesize) {
- RTE_LOG(ERR, PMD,
- "%s: invalid framesize value\n",
+ PMD_LOG(ERR,
+ "%s: invalid framesize value",
name);
return -1;
}
if (strstr(pair->key, ETH_AF_PACKET_FRAMECOUNT_ARG) != NULL) {
framecount = atoi(pair->value);
if (!framecount) {
- RTE_LOG(ERR, PMD,
- "%s: invalid framecount value\n",
+ PMD_LOG(ERR,
+ "%s: invalid framecount value",
name);
return -1;
}
continue;
}
+ if (strstr(pair->key, ETH_AF_PACKET_QDISC_BYPASS_ARG) != NULL) {
+ qdisc_bypass = atoi(pair->value);
+ if (qdisc_bypass > 1) {
+ PMD_LOG(ERR,
+ "%s: invalid bypass value",
+ name);
+ return -1;
+ }
+ continue;
+ }
}
if (framesize > blocksize) {
- RTE_LOG(ERR, PMD,
- "%s: AF_PACKET MMAP frame size exceeds block size!\n",
+ PMD_LOG(ERR,
+ "%s: AF_PACKET MMAP frame size exceeds block size!",
name);
return -1;
}
blockcount = framecount / (blocksize / framesize);
if (!blockcount) {
- RTE_LOG(ERR, PMD,
- "%s: invalid AF_PACKET MMAP parameters\n", name);
+ PMD_LOG(ERR,
+ "%s: invalid AF_PACKET MMAP parameters", name);
return -1;
}
- RTE_LOG(INFO, PMD, "%s: AF_PACKET MMAP parameters:\n", name);
- RTE_LOG(INFO, PMD, "%s:\tblock size %d\n", name, blocksize);
- RTE_LOG(INFO, PMD, "%s:\tblock count %d\n", name, blockcount);
- RTE_LOG(INFO, PMD, "%s:\tframe size %d\n", name, framesize);
- RTE_LOG(INFO, PMD, "%s:\tframe count %d\n", name, framecount);
-
- if (rte_pmd_init_internals(name, *sockfd, qpairs,
- blocksize, blockcount,
- framesize, framecount,
- numa_node, &internals, ð_dev,
- kvlist) < 0)
+ PMD_LOG(INFO, "%s: AF_PACKET MMAP parameters:", name);
+ PMD_LOG(INFO, "%s:\tblock size %d", name, blocksize);
+ PMD_LOG(INFO, "%s:\tblock count %d", name, blockcount);
+ PMD_LOG(INFO, "%s:\tframe size %d", name, framesize);
+ PMD_LOG(INFO, "%s:\tframe count %d", name, framecount);
+
+ if (rte_pmd_init_internals(dev, *sockfd, qpairs,
+ blocksize, blockcount,
+ framesize, framecount,
+ qdisc_bypass,
+ &internals, ð_dev,
+ kvlist) < 0)
return -1;
eth_dev->rx_pkt_burst = eth_af_packet_rx;
eth_dev->tx_pkt_burst = eth_af_packet_tx;
+ rte_eth_dev_probing_finish(eth_dev);
return 0;
}
static int
-rte_pmd_af_packet_probe(const char *name, const char *params)
+rte_pmd_af_packet_probe(struct rte_vdev_device *dev)
{
- unsigned numa_node;
int ret = 0;
struct rte_kvargs *kvlist;
int sockfd = -1;
+ struct rte_eth_dev *eth_dev;
+ const char *name = rte_vdev_device_name(dev);
- RTE_LOG(INFO, PMD, "Initializing pmd_af_packet for %s\n", name);
+ PMD_LOG(INFO, "Initializing pmd_af_packet for %s", name);
- numa_node = rte_socket_id();
+ if (rte_eal_process_type() == RTE_PROC_SECONDARY) {
+ eth_dev = rte_eth_dev_attach_secondary(name);
+ if (!eth_dev) {
+ PMD_LOG(ERR, "Failed to probe %s", name);
+ return -1;
+ }
+ /* TODO: request info from primary to set up Rx and Tx */
+ eth_dev->dev_ops = &ops;
+ eth_dev->device = &dev->device;
+ rte_eth_dev_probing_finish(eth_dev);
+ return 0;
+ }
- kvlist = rte_kvargs_parse(params, valid_arguments);
+ kvlist = rte_kvargs_parse(rte_vdev_device_args(dev), valid_arguments);
if (kvlist == NULL) {
ret = -1;
goto exit;
goto exit;
}
- ret = rte_eth_from_packet(name, &sockfd, numa_node, kvlist);
+ if (dev->device.numa_node == SOCKET_ID_ANY)
+ dev->device.numa_node = rte_socket_id();
+
+ ret = rte_eth_from_packet(dev, &sockfd, kvlist);
close(sockfd); /* no longer needed */
exit:
}
static int
-rte_pmd_af_packet_remove(const char *name)
+rte_pmd_af_packet_remove(struct rte_vdev_device *dev)
{
- struct rte_eth_dev *eth_dev = NULL;
- struct pmd_internals *internals;
- unsigned q;
-
- RTE_LOG(INFO, PMD, "Closing AF_PACKET ethdev on numa socket %u\n",
- rte_socket_id());
+ struct rte_eth_dev *eth_dev;
- if (name == NULL)
+ if (dev == NULL)
return -1;
/* find the ethdev entry */
- eth_dev = rte_eth_dev_allocated(name);
+ eth_dev = rte_eth_dev_allocated(rte_vdev_device_name(dev));
if (eth_dev == NULL)
- return -1;
-
- internals = eth_dev->data->dev_private;
- for (q = 0; q < internals->nb_queues; q++) {
- rte_free(internals->rx_queue[q].rd);
- rte_free(internals->tx_queue[q].rd);
- }
-
- rte_free(eth_dev->data->dev_private);
- rte_free(eth_dev->data);
+ return 0; /* port already released */
+ eth_dev_close(eth_dev);
rte_eth_dev_release_port(eth_dev);
return 0;
"qpairs=<int> "
"blocksz=<int> "
"framesz=<int> "
- "framecnt=<int>");
+ "framecnt=<int> "
+ "qdisc_bypass=<0|1>");