#include <rte_string_fns.h>
#include <rte_mbuf.h>
-#include <rte_ethdev_driver.h>
-#include <rte_ethdev_vdev.h>
+#include <ethdev_driver.h>
+#include <ethdev_vdev.h>
#include <rte_malloc.h>
#include <rte_kvargs.h>
#include <rte_bus_vdev.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>
#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;
struct rte_mempool *mb_pool;
uint16_t in_port;
+ uint8_t vlan_strip;
volatile unsigned long rx_pkts;
volatile unsigned long rx_bytes;
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[] = {
};
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_FIXED,
+ .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,
};
-static int af_packet_logtype;
+RTE_LOG_REGISTER_DEFAULT(af_packet_logtype, NOTICE);
#define PMD_LOG(level, fmt, args...) \
rte_log(RTE_LOG_ ## level, af_packet_logtype, \
/* check for vlan info */
if (ppd->tp_status & TP_STATUS_VLAN_VALID) {
mbuf->vlan_tci = ppd->tp_vlan_tci;
- mbuf->ol_flags |= (PKT_RX_VLAN | PKT_RX_VLAN_STRIPPED);
+ 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 */
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.
*/
}
/* insert vlan info if necessary */
- if (mbuf->ol_flags & PKT_TX_VLAN_PKT) {
+ 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 ((ppd->tp_status != TP_STATUS_AVAILABLE) &&
- (poll(&pfd, 1, -1) < 0))
+ if (!tx_ring_status_available(ppd->tp_status) &&
+ poll(&pfd, 1, -1) < 0)
break;
/* copy the tx frame data */
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;
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;
}
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 = DEV_TX_OFFLOAD_MULTI_SEGS |
- DEV_TX_OFFLOAD_VLAN_INSERT;
+ 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;
}
return 0;
}
-static void
-eth_dev_close(struct rte_eth_dev *dev __rte_unused)
+static int
+eth_dev_close(struct rte_eth_dev *dev)
{
-}
+ struct pmd_internals *internals;
+ struct tpacket_req *req;
+ unsigned int q;
-static void
-eth_queue_release(void *q __rte_unused)
-{
+ 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
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_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)
{
.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,
if (*internals == NULL)
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);
PMD_LOG(ERR,
"%s: I/F name too long (%s)",
name, pair->value);
- return -1;
+ goto free_internals;
}
if (ioctl(sockfd, SIOCGIFINDEX, &ifr) == -1) {
PMD_LOG_ERRNO(ERR, "%s: ioctl failed (SIOCGIFINDEX)", name);
- return -1;
+ goto free_internals;
}
(*internals)->if_name = strdup(pair->value);
if ((*internals)->if_name == NULL)
- return -1;
+ goto free_internals;
(*internals)->if_index = ifr.ifr_ifindex;
if (ioctl(sockfd, SIOCGIFHWADDR, &ifr) == -1) {
PMD_LOG_ERRNO(ERR, "%s: ioctl failed (SIOCGIFHWADDR)", name);
- return -1;
+ goto free_internals;
}
memcpy(&(*internals)->eth_addr, ifr.ifr_hwaddr.sa_data, ETH_ALEN);
PMD_LOG_ERRNO(ERR,
"%s: could not open AF_PACKET socket",
name);
- return -1;
+ goto error;
}
tpver = TPACKET_V2;
goto error;
}
+ if (qdisc_bypass) {
#if defined(PACKET_QDISC_BYPASS)
- 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;
- }
-#else
- RTE_SET_USED(qdisc_bypass);
+ 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) {
data->nb_tx_queues = (uint16_t)nb_queues;
data->dev_link = pmd_link;
data->mac_addrs = &(*internals)->eth_addr;
+ data->dev_flags |= RTE_ETH_DEV_AUTOFILL_QUEUE_XSTATS;
(*eth_dev)->dev_ops = &ops;
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);
return -1;
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) {
+ if (qpairs < 1) {
PMD_LOG(ERR,
"%s: invalid qpairs value",
name);
static int
rte_pmd_af_packet_remove(struct rte_vdev_device *dev)
{
- struct rte_eth_dev *eth_dev = NULL;
- struct pmd_internals *internals;
- struct tpacket_req *req;
- unsigned q;
-
- PMD_LOG(INFO, "Closing AF_PACKET ethdev on numa socket %u",
- rte_socket_id());
+ struct rte_eth_dev *eth_dev;
if (dev == NULL)
return -1;
/* find the ethdev entry */
eth_dev = rte_eth_dev_allocated(rte_vdev_device_name(dev));
if (eth_dev == NULL)
- return -1;
-
- /* mac_addrs must not be freed alone because part of dev_private */
- eth_dev->data->mac_addrs = NULL;
-
- if (rte_eal_process_type() != RTE_PROC_PRIMARY)
- return rte_eth_dev_release_port(eth_dev);
-
- internals = eth_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);
+ return 0; /* port already released */
+ eth_dev_close(eth_dev);
rte_eth_dev_release_port(eth_dev);
return 0;
"framesz=<int> "
"framecnt=<int> "
"qdisc_bypass=<0|1>");
-
-RTE_INIT(af_packet_init_log)
-{
- af_packet_logtype = rte_log_register("pmd.net.packet");
- if (af_packet_logtype >= 0)
- rte_log_set_level(af_packet_logtype, RTE_LOG_NOTICE);
-}
git.droids-corp.org / dpdk.git / blobdiff