X-Git-Url: http://git.droids-corp.org/?a=blobdiff_plain;ds=sidebyside;f=drivers%2Fnet%2Faf_packet%2Frte_eth_af_packet.c;h=1396f32c3dccd800d2276245829ff49ad88271e6;hb=25ed2ebff131dededf0cb3ac38ce196a41b76f43;hp=7d0ff1cbb3ee6f69988c21ef755cde736d5b0e37;hpb=b142387b07600c320683255d237b9109299883d5;p=dpdk.git diff --git a/drivers/net/af_packet/rte_eth_af_packet.c b/drivers/net/af_packet/rte_eth_af_packet.c index 7d0ff1cbb3..1396f32c3d 100644 --- a/drivers/net/af_packet/rte_eth_af_packet.c +++ b/drivers/net/af_packet/rte_eth_af_packet.c @@ -8,8 +8,8 @@ #include #include -#include -#include +#include +#include #include #include #include @@ -48,6 +48,7 @@ struct pkt_rx_queue { struct rte_mempool *mb_pool; uint16_t in_port; + uint8_t vlan_strip; volatile unsigned long rx_pkts; volatile unsigned long rx_bytes; @@ -78,6 +79,7 @@ struct pmd_internals { struct pkt_rx_queue *rx_queue; struct pkt_tx_queue *tx_queue; + uint8_t vlan_strip; }; static const char *valid_arguments[] = { @@ -91,13 +93,13 @@ 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, }; -RTE_LOG_REGISTER(af_packet_logtype, pmd.net.packet, NOTICE); +RTE_LOG_REGISTER_DEFAULT(af_packet_logtype, NOTICE); #define PMD_LOG(level, fmt, args...) \ rte_log(RTE_LOG_ ## level, af_packet_logtype, \ @@ -147,7 +149,10 @@ eth_af_packet_rx(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts) /* 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 */ @@ -167,6 +172,26 @@ eth_af_packet_rx(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts) 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. */ @@ -204,7 +229,7 @@ eth_af_packet_tx(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts) } /* 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; @@ -212,8 +237,30 @@ eth_af_packet_tx(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts) } /* 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)) { + 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 */ @@ -265,14 +312,14 @@ eth_af_packet_tx(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts) 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; @@ -295,12 +342,18 @@ eth_dev_stop(struct rte_eth_dev *dev) 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; } @@ -311,12 +364,13 @@ eth_dev_info(struct rte_eth_dev *dev, struct rte_eth_dev_info *dev_info) 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 = 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; } @@ -377,14 +431,33 @@ eth_stats_reset(struct rte_eth_dev *dev) } static int -eth_dev_close(struct rte_eth_dev *dev __rte_unused) +eth_dev_close(struct rte_eth_dev *dev) { - return 0; -} + 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 @@ -423,6 +496,7 @@ eth_rx_queue_setup(struct rte_eth_dev *dev, 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; } @@ -549,8 +623,6 @@ static const struct eth_dev_ops ops = { .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, @@ -723,18 +795,18 @@ rte_pmd_init_internals(struct rte_vdev_device *dev, 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) { @@ -835,6 +907,7 @@ rte_pmd_init_internals(struct rte_vdev_device *dev, 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; @@ -1033,13 +1106,7 @@ exit: 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; @@ -1047,26 +1114,9 @@ rte_pmd_af_packet_remove(struct rte_vdev_device *dev) /* 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); - rte_free(internals->rx_queue); - rte_free(internals->tx_queue); + return 0; /* port already released */ + eth_dev_close(eth_dev); rte_eth_dev_release_port(eth_dev); return 0;