X-Git-Url: http://git.droids-corp.org/?a=blobdiff_plain;f=drivers%2Fnet%2Ftap%2Frte_eth_tap.c;h=71be763d66e8b4bc4d7a831766a2d67cba7357ba;hb=6d13ea8e8e49ab957deae2bba5ecf4a4bfe747d1;hp=172a7ba4c87638c952be37938c828c864bcd33cd;hpb=1b3b7caeb1f8685e916b31f58e84345a4a57f80f;p=dpdk.git diff --git a/drivers/net/tap/rte_eth_tap.c b/drivers/net/tap/rte_eth_tap.c index 172a7ba4c8..71be763d66 100644 --- a/drivers/net/tap/rte_eth_tap.c +++ b/drivers/net/tap/rte_eth_tap.c @@ -16,7 +16,10 @@ #include #include #include +#include +#include +#include #include #include #include @@ -34,7 +37,9 @@ #include #include #include +#include +#include #include #include #include @@ -54,6 +59,18 @@ #define ETH_TAP_CMP_MAC_FMT "0123456789ABCDEFabcdef" #define ETH_TAP_MAC_ARG_FMT ETH_TAP_MAC_FIXED "|" ETH_TAP_USR_MAC_FMT +#define TAP_GSO_MBUFS_PER_CORE 128 +#define TAP_GSO_MBUF_SEG_SIZE 128 +#define TAP_GSO_MBUF_CACHE_SIZE 4 +#define TAP_GSO_MBUFS_NUM \ + (TAP_GSO_MBUFS_PER_CORE * TAP_GSO_MBUF_CACHE_SIZE) + +/* IPC key for queue fds sync */ +#define TAP_MP_KEY "tap_mp_sync_queues" + +#define TAP_IOV_DEFAULT_MAX 1024 + +static int tap_devices_count; static struct rte_vdev_driver pmd_tap_drv; static struct rte_vdev_driver pmd_tun_drv; @@ -64,12 +81,6 @@ static const char *valid_arguments[] = { NULL }; -static int tap_unit; -static int tun_unit; - -static int tap_type; -static char tuntap_name[8]; - static volatile uint32_t tap_trigger; /* Rx trigger */ static struct rte_eth_link pmd_link = { @@ -93,15 +104,33 @@ enum ioctl_mode { REMOTE_ONLY, }; +/* Message header to synchronize queues via IPC */ +struct ipc_queues { + char port_name[RTE_DEV_NAME_MAX_LEN]; + int rxq_count; + int txq_count; + /* + * The file descriptors are in the dedicated part + * of the Unix message to be translated by the kernel. + */ +}; + static int tap_intr_handle_set(struct rte_eth_dev *dev, int set); -/* Tun/Tap allocation routine +/** + * Tun/Tap allocation routine + * + * @param[in] pmd + * Pointer to private structure. * - * name is the number of the interface to use, unless NULL to take the host - * supplied name. + * @param[in] is_keepalive + * Keepalive flag + * + * @return + * -1 on failure, fd on success */ static int -tun_alloc(struct pmd_internals *pmd) +tun_alloc(struct pmd_internals *pmd, int is_keepalive) { struct ifreq ifr; #ifdef IFF_MULTI_QUEUE @@ -115,25 +144,23 @@ tun_alloc(struct pmd_internals *pmd) * Do not set IFF_NO_PI as packet information header will be needed * to check if a received packet has been truncated. */ - ifr.ifr_flags = (tap_type) ? IFF_TAP : IFF_TUN | IFF_POINTOPOINT; - snprintf(ifr.ifr_name, IFNAMSIZ, "%s", pmd->name); - - TAP_LOG(DEBUG, "ifr_name '%s'", ifr.ifr_name); + ifr.ifr_flags = (pmd->type == ETH_TUNTAP_TYPE_TAP) ? + IFF_TAP : IFF_TUN | IFF_POINTOPOINT; + strlcpy(ifr.ifr_name, pmd->name, IFNAMSIZ); fd = open(TUN_TAP_DEV_PATH, O_RDWR); if (fd < 0) { - TAP_LOG(ERR, "Unable to create %s interface", tuntap_name); + TAP_LOG(ERR, "Unable to open %s interface", TUN_TAP_DEV_PATH); goto error; } #ifdef IFF_MULTI_QUEUE /* Grab the TUN features to verify we can work multi-queue */ if (ioctl(fd, TUNGETFEATURES, &features) < 0) { - TAP_LOG(ERR, "%s unable to get TUN/TAP features", - tuntap_name); + TAP_LOG(ERR, "unable to get TUN/TAP features"); goto error; } - TAP_LOG(DEBUG, "%s Features %08x", tuntap_name, features); + TAP_LOG(DEBUG, "%s Features %08x", TUN_TAP_DEV_PATH, features); if (features & IFF_MULTI_QUEUE) { TAP_LOG(DEBUG, " Multi-queue support for %d queues", @@ -153,6 +180,27 @@ tun_alloc(struct pmd_internals *pmd) goto error; } + /* + * Name passed to kernel might be wildcard like dtun%d + * and need to find the resulting device. + */ + TAP_LOG(DEBUG, "Device name is '%s'", ifr.ifr_name); + strlcpy(pmd->name, ifr.ifr_name, RTE_ETH_NAME_MAX_LEN); + + if (is_keepalive) { + /* + * Detach the TUN/TAP keep-alive queue + * to avoid traffic through it + */ + ifr.ifr_flags = IFF_DETACH_QUEUE; + if (ioctl(fd, TUNSETQUEUE, (void *)&ifr) < 0) { + TAP_LOG(WARNING, + "Unable to detach keep-alive queue for %s: %s", + ifr.ifr_name, strerror(errno)); + goto error; + } + } + /* Always set the file descriptor to non-blocking */ if (fcntl(fd, F_SETFL, O_NONBLOCK) < 0) { TAP_LOG(WARNING, @@ -202,7 +250,7 @@ tun_alloc(struct pmd_internals *pmd) return fd; error: - if (fd > 0) + if (fd >= 0) close(fd); return -1; } @@ -213,7 +261,7 @@ tap_verify_csum(struct rte_mbuf *mbuf) uint32_t l2 = mbuf->packet_type & RTE_PTYPE_L2_MASK; uint32_t l3 = mbuf->packet_type & RTE_PTYPE_L3_MASK; uint32_t l4 = mbuf->packet_type & RTE_PTYPE_L4_MASK; - unsigned int l2_len = sizeof(struct ether_hdr); + unsigned int l2_len = sizeof(struct rte_ether_hdr); unsigned int l3_len; uint16_t cksum = 0; void *l3_hdr; @@ -235,13 +283,27 @@ tap_verify_csum(struct rte_mbuf *mbuf) l3_len = 4 * (iph->version_ihl & 0xf); if (unlikely(l2_len + l3_len > rte_pktmbuf_data_len(mbuf))) return; + /* check that the total length reported by header is not + * greater than the total received size + */ + if (l2_len + rte_be_to_cpu_16(iph->total_length) > + rte_pktmbuf_data_len(mbuf)) + return; cksum = ~rte_raw_cksum(iph, l3_len); mbuf->ol_flags |= cksum ? PKT_RX_IP_CKSUM_BAD : PKT_RX_IP_CKSUM_GOOD; } else if (l3 == RTE_PTYPE_L3_IPV6) { + struct ipv6_hdr *iph = l3_hdr; + l3_len = sizeof(struct ipv6_hdr); + /* check that the total length reported by header is not + * greater than the total received size + */ + if (l2_len + l3_len + rte_be_to_cpu_16(iph->payload_len) > + rte_pktmbuf_data_len(mbuf)) + return; } else { /* IPv6 extensions are not supported */ return; @@ -276,23 +338,7 @@ tap_rx_offload_get_queue_capa(void) return DEV_RX_OFFLOAD_SCATTER | DEV_RX_OFFLOAD_IPV4_CKSUM | DEV_RX_OFFLOAD_UDP_CKSUM | - DEV_RX_OFFLOAD_TCP_CKSUM | - DEV_RX_OFFLOAD_CRC_STRIP; -} - -static bool -tap_rxq_are_offloads_valid(struct rte_eth_dev *dev, uint64_t offloads) -{ - uint64_t port_offloads = dev->data->dev_conf.rxmode.offloads; - uint64_t queue_supp_offloads = tap_rx_offload_get_queue_capa(); - uint64_t port_supp_offloads = tap_rx_offload_get_port_capa(); - - if ((offloads & (queue_supp_offloads | port_supp_offloads)) != - offloads) - return false; - if ((port_offloads ^ offloads) & port_supp_offloads) - return false; - return true; + DEV_RX_OFFLOAD_TCP_CKSUM; } /* Callback to handle the rx burst of packets to the correct interface and @@ -302,6 +348,7 @@ static uint16_t pmd_rx_burst(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts) { struct rx_queue *rxq = queue; + struct pmd_process_private *process_private; uint16_t num_rx; unsigned long num_rx_bytes = 0; uint32_t trigger = tap_trigger; @@ -310,6 +357,7 @@ pmd_rx_burst(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts) return 0; if (trigger) rxq->trigger_seen = trigger; + process_private = rte_eth_devices[rxq->in_port].process_private; rte_compiler_barrier(); for (num_rx = 0; num_rx < nb_pkts; ) { struct rte_mbuf *mbuf = rxq->pool; @@ -318,9 +366,9 @@ pmd_rx_burst(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts) uint16_t data_off = rte_pktmbuf_headroom(mbuf); int len; - len = readv(rxq->fd, *rxq->iovecs, - 1 + - (rxq->rxmode->offloads & DEV_RX_OFFLOAD_SCATTER ? + len = readv(process_private->rxq_fds[rxq->queue_id], + *rxq->iovecs, + 1 + (rxq->rxmode->offloads & DEV_RX_OFFLOAD_SCATTER ? rxq->nb_rx_desc : 1)); if (len < (int)sizeof(struct tun_pi)) break; @@ -405,28 +453,45 @@ tap_tx_offload_get_queue_capa(void) return DEV_TX_OFFLOAD_MULTI_SEGS | DEV_TX_OFFLOAD_IPV4_CKSUM | DEV_TX_OFFLOAD_UDP_CKSUM | - DEV_TX_OFFLOAD_TCP_CKSUM; + DEV_TX_OFFLOAD_TCP_CKSUM | + DEV_TX_OFFLOAD_TCP_TSO; } -static bool -tap_txq_are_offloads_valid(struct rte_eth_dev *dev, uint64_t offloads) +/* Finalize l4 checksum calculation */ +static void +tap_tx_l4_cksum(uint16_t *l4_cksum, uint16_t l4_phdr_cksum, + uint32_t l4_raw_cksum) { - uint64_t port_offloads = dev->data->dev_conf.txmode.offloads; - uint64_t queue_supp_offloads = tap_tx_offload_get_queue_capa(); - uint64_t port_supp_offloads = tap_tx_offload_get_port_capa(); + if (l4_cksum) { + uint32_t cksum; - if ((offloads & (queue_supp_offloads | port_supp_offloads)) != - offloads) - return false; - /* Verify we have no conflict with port offloads */ - if ((port_offloads ^ offloads) & port_supp_offloads) - return false; - return true; + cksum = __rte_raw_cksum_reduce(l4_raw_cksum); + cksum += l4_phdr_cksum; + + cksum = ((cksum & 0xffff0000) >> 16) + (cksum & 0xffff); + cksum = (~cksum) & 0xffff; + if (cksum == 0) + cksum = 0xffff; + *l4_cksum = cksum; + } +} + +/* Accumaulate L4 raw checksums */ +static void +tap_tx_l4_add_rcksum(char *l4_data, unsigned int l4_len, uint16_t *l4_cksum, + uint32_t *l4_raw_cksum) +{ + if (l4_cksum == NULL) + return; + + *l4_raw_cksum = __rte_raw_cksum(l4_data, l4_len, *l4_raw_cksum); } +/* L3 and L4 pseudo headers checksum offloads */ static void -tap_tx_offload(char *packet, uint64_t ol_flags, unsigned int l2_len, - unsigned int l3_len) +tap_tx_l3_cksum(char *packet, uint64_t ol_flags, unsigned int l2_len, + unsigned int l3_len, unsigned int l4_len, uint16_t **l4_cksum, + uint16_t *l4_phdr_cksum, uint32_t *l4_raw_cksum) { void *l3_hdr = packet + l2_len; @@ -439,38 +504,140 @@ tap_tx_offload(char *packet, uint64_t ol_flags, unsigned int l2_len, iph->hdr_checksum = (cksum == 0xffff) ? cksum : ~cksum; } if (ol_flags & PKT_TX_L4_MASK) { - uint16_t l4_len; - uint32_t cksum; - uint16_t *l4_cksum; void *l4_hdr; l4_hdr = packet + l2_len + l3_len; if ((ol_flags & PKT_TX_L4_MASK) == PKT_TX_UDP_CKSUM) - l4_cksum = &((struct udp_hdr *)l4_hdr)->dgram_cksum; + *l4_cksum = &((struct udp_hdr *)l4_hdr)->dgram_cksum; else if ((ol_flags & PKT_TX_L4_MASK) == PKT_TX_TCP_CKSUM) - l4_cksum = &((struct tcp_hdr *)l4_hdr)->cksum; + *l4_cksum = &((struct tcp_hdr *)l4_hdr)->cksum; else return; - *l4_cksum = 0; - if (ol_flags & PKT_TX_IPV4) { - struct ipv4_hdr *iph = l3_hdr; + **l4_cksum = 0; + if (ol_flags & PKT_TX_IPV4) + *l4_phdr_cksum = rte_ipv4_phdr_cksum(l3_hdr, 0); + else + *l4_phdr_cksum = rte_ipv6_phdr_cksum(l3_hdr, 0); + *l4_raw_cksum = __rte_raw_cksum(l4_hdr, l4_len, 0); + } +} - l4_len = rte_be_to_cpu_16(iph->total_length) - l3_len; - cksum = rte_ipv4_phdr_cksum(l3_hdr, 0); - } else { - struct ipv6_hdr *ip6h = l3_hdr; +static inline void +tap_write_mbufs(struct tx_queue *txq, uint16_t num_mbufs, + struct rte_mbuf **pmbufs, + uint16_t *num_packets, unsigned long *num_tx_bytes) +{ + int i; + uint16_t l234_hlen; + struct pmd_process_private *process_private; + + process_private = rte_eth_devices[txq->out_port].process_private; - /* payload_len does not include ext headers */ - l4_len = rte_be_to_cpu_16(ip6h->payload_len) - - l3_len + sizeof(struct ipv6_hdr); - cksum = rte_ipv6_phdr_cksum(l3_hdr, 0); + for (i = 0; i < num_mbufs; i++) { + struct rte_mbuf *mbuf = pmbufs[i]; + struct iovec iovecs[mbuf->nb_segs + 2]; + struct tun_pi pi = { .flags = 0, .proto = 0x00 }; + struct rte_mbuf *seg = mbuf; + char m_copy[mbuf->data_len]; + int proto; + int n; + int j; + int k; /* current index in iovecs for copying segments */ + uint16_t seg_len; /* length of first segment */ + uint16_t nb_segs; + uint16_t *l4_cksum; /* l4 checksum (pseudo header + payload) */ + uint32_t l4_raw_cksum = 0; /* TCP/UDP payload raw checksum */ + uint16_t l4_phdr_cksum = 0; /* TCP/UDP pseudo header checksum */ + uint16_t is_cksum = 0; /* in case cksum should be offloaded */ + + l4_cksum = NULL; + if (txq->type == ETH_TUNTAP_TYPE_TUN) { + /* + * TUN and TAP are created with IFF_NO_PI disabled. + * For TUN PMD this mandatory as fields are used by + * Kernel tun.c to determine whether its IP or non IP + * packets. + * + * The logic fetches the first byte of data from mbuf + * then compares whether its v4 or v6. If first byte + * is 4 or 6, then protocol field is updated. + */ + char *buff_data = rte_pktmbuf_mtod(seg, void *); + proto = (*buff_data & 0xf0); + pi.proto = (proto == 0x40) ? + rte_cpu_to_be_16(ETHER_TYPE_IPv4) : + ((proto == 0x60) ? + rte_cpu_to_be_16(ETHER_TYPE_IPv6) : + 0x00); } - cksum += rte_raw_cksum(l4_hdr, l4_len); - cksum = ((cksum & 0xffff0000) >> 16) + (cksum & 0xffff); - cksum = (~cksum) & 0xffff; - if (cksum == 0) - cksum = 0xffff; - *l4_cksum = cksum; + + k = 0; + iovecs[k].iov_base = π + iovecs[k].iov_len = sizeof(pi); + k++; + + nb_segs = mbuf->nb_segs; + if (txq->csum && + ((mbuf->ol_flags & (PKT_TX_IP_CKSUM | PKT_TX_IPV4) || + (mbuf->ol_flags & PKT_TX_L4_MASK) == PKT_TX_UDP_CKSUM || + (mbuf->ol_flags & PKT_TX_L4_MASK) == PKT_TX_TCP_CKSUM))) { + is_cksum = 1; + + /* Support only packets with at least layer 4 + * header included in the first segment + */ + seg_len = rte_pktmbuf_data_len(mbuf); + l234_hlen = mbuf->l2_len + mbuf->l3_len + mbuf->l4_len; + if (seg_len < l234_hlen) + break; + + /* To change checksums, work on a * copy of l2, l3 + * headers + l4 pseudo header + */ + rte_memcpy(m_copy, rte_pktmbuf_mtod(mbuf, void *), + l234_hlen); + tap_tx_l3_cksum(m_copy, mbuf->ol_flags, + mbuf->l2_len, mbuf->l3_len, mbuf->l4_len, + &l4_cksum, &l4_phdr_cksum, + &l4_raw_cksum); + iovecs[k].iov_base = m_copy; + iovecs[k].iov_len = l234_hlen; + k++; + + /* Update next iovecs[] beyond l2, l3, l4 headers */ + if (seg_len > l234_hlen) { + iovecs[k].iov_len = seg_len - l234_hlen; + iovecs[k].iov_base = + rte_pktmbuf_mtod(seg, char *) + + l234_hlen; + tap_tx_l4_add_rcksum(iovecs[k].iov_base, + iovecs[k].iov_len, l4_cksum, + &l4_raw_cksum); + k++; + nb_segs++; + } + seg = seg->next; + } + + for (j = k; j <= nb_segs; j++) { + iovecs[j].iov_len = rte_pktmbuf_data_len(seg); + iovecs[j].iov_base = rte_pktmbuf_mtod(seg, void *); + if (is_cksum) + tap_tx_l4_add_rcksum(iovecs[j].iov_base, + iovecs[j].iov_len, l4_cksum, + &l4_raw_cksum); + seg = seg->next; + } + + if (is_cksum) + tap_tx_l4_cksum(l4_cksum, l4_phdr_cksum, l4_raw_cksum); + + /* copy the tx frame data */ + n = writev(process_private->txq_fds[txq->queue_id], iovecs, j); + if (n <= 0) + break; + (*num_packets)++; + (*num_tx_bytes) += rte_pktmbuf_pkt_len(mbuf); } } @@ -481,6 +648,7 @@ pmd_tx_burst(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts) { struct tx_queue *txq = queue; uint16_t num_tx = 0; + uint16_t num_packets = 0; unsigned long num_tx_bytes = 0; uint32_t max_size; int i; @@ -488,72 +656,74 @@ pmd_tx_burst(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts) if (unlikely(nb_pkts == 0)) return 0; + struct rte_mbuf *gso_mbufs[MAX_GSO_MBUFS]; max_size = *txq->mtu + (ETHER_HDR_LEN + ETHER_CRC_LEN + 4); for (i = 0; i < nb_pkts; i++) { - struct rte_mbuf *mbuf = bufs[num_tx]; - struct iovec iovecs[mbuf->nb_segs + 1]; - struct tun_pi pi = { .flags = 0, .proto = 0x00 }; - struct rte_mbuf *seg = mbuf; - char m_copy[mbuf->data_len]; - int n; + struct rte_mbuf *mbuf_in = bufs[num_tx]; + struct rte_mbuf **mbuf; + uint16_t num_mbufs = 0; + uint16_t tso_segsz = 0; + int ret; + uint16_t hdrs_len; int j; + uint64_t tso; - /* stats.errs will be incremented */ - if (rte_pktmbuf_pkt_len(mbuf) > max_size) - break; + tso = mbuf_in->ol_flags & PKT_TX_TCP_SEG; + if (tso) { + struct rte_gso_ctx *gso_ctx = &txq->gso_ctx; - /* - * TUN and TAP are created with IFF_NO_PI disabled. - * For TUN PMD this mandatory as fields are used by - * Kernel tun.c to determine whether its IP or non IP - * packets. - * - * The logic fetches the first byte of data from mbuf. - * compares whether its v4 or v6. If none matches default - * value 0x00 is taken for protocol field. - */ - char *buff_data = rte_pktmbuf_mtod(seg, void *); - j = (*buff_data & 0xf0); - pi.proto = (j == 0x40) ? 0x0008 : - (j == 0x60) ? 0xdd86 : 0x00; - - iovecs[0].iov_base = π - iovecs[0].iov_len = sizeof(pi); - for (j = 1; j <= mbuf->nb_segs; j++) { - iovecs[j].iov_len = rte_pktmbuf_data_len(seg); - iovecs[j].iov_base = - rte_pktmbuf_mtod(seg, void *); - seg = seg->next; - } - if (txq->csum && - ((mbuf->ol_flags & (PKT_TX_IP_CKSUM | PKT_TX_IPV4) || - (mbuf->ol_flags & PKT_TX_L4_MASK) == PKT_TX_UDP_CKSUM || - (mbuf->ol_flags & PKT_TX_L4_MASK) == PKT_TX_TCP_CKSUM))) { - /* Support only packets with all data in the same seg */ - if (mbuf->nb_segs > 1) + assert(gso_ctx != NULL); + + /* TCP segmentation implies TCP checksum offload */ + mbuf_in->ol_flags |= PKT_TX_TCP_CKSUM; + + /* gso size is calculated without ETHER_CRC_LEN */ + hdrs_len = mbuf_in->l2_len + mbuf_in->l3_len + + mbuf_in->l4_len; + tso_segsz = mbuf_in->tso_segsz + hdrs_len; + if (unlikely(tso_segsz == hdrs_len) || + tso_segsz > *txq->mtu) { + txq->stats.errs++; break; - /* To change checksums, work on a copy of data. */ - rte_memcpy(m_copy, rte_pktmbuf_mtod(mbuf, void *), - rte_pktmbuf_data_len(mbuf)); - tap_tx_offload(m_copy, mbuf->ol_flags, - mbuf->l2_len, mbuf->l3_len); - iovecs[1].iov_base = m_copy; + } + gso_ctx->gso_size = tso_segsz; + ret = rte_gso_segment(mbuf_in, /* packet to segment */ + gso_ctx, /* gso control block */ + (struct rte_mbuf **)&gso_mbufs, /* out mbufs */ + RTE_DIM(gso_mbufs)); /* max tso mbufs */ + + /* ret contains the number of new created mbufs */ + if (ret < 0) + break; + + mbuf = gso_mbufs; + num_mbufs = ret; + } else { + /* stats.errs will be incremented */ + if (rte_pktmbuf_pkt_len(mbuf_in) > max_size) + break; + + /* ret 0 indicates no new mbufs were created */ + ret = 0; + mbuf = &mbuf_in; + num_mbufs = 1; } - /* copy the tx frame data */ - n = writev(txq->fd, iovecs, mbuf->nb_segs + 1); - if (n <= 0) - break; + tap_write_mbufs(txq, num_mbufs, mbuf, + &num_packets, &num_tx_bytes); num_tx++; - num_tx_bytes += mbuf->pkt_len; - rte_pktmbuf_free(mbuf); + /* free original mbuf */ + rte_pktmbuf_free(mbuf_in); + /* free tso mbufs */ + for (j = 0; j < ret; j++) + rte_pktmbuf_free(mbuf[j]); } - txq->stats.opackets += num_tx; + txq->stats.opackets += num_packets; txq->stats.errs += nb_pkts - num_tx; txq->stats.obytes += num_tx_bytes; - return num_tx; + return num_packets; } static const char * @@ -590,9 +760,9 @@ tap_ioctl(struct pmd_internals *pmd, unsigned long request, */ apply: if (remote) - snprintf(ifr->ifr_name, IFNAMSIZ, "%s", pmd->remote_iface); + strlcpy(ifr->ifr_name, pmd->remote_iface, IFNAMSIZ); else if (mode == LOCAL_ONLY || mode == LOCAL_AND_REMOTE) - snprintf(ifr->ifr_name, IFNAMSIZ, "%s", pmd->name); + strlcpy(ifr->ifr_name, pmd->name, IFNAMSIZ); switch (request) { case SIOCSIFFLAGS: /* fetch current flags to leave other flags untouched */ @@ -648,12 +818,22 @@ tap_link_set_up(struct rte_eth_dev *dev) static int tap_dev_start(struct rte_eth_dev *dev) { - int err; + int err, i; err = tap_intr_handle_set(dev, 1); if (err) return err; - return tap_link_set_up(dev); + + err = tap_link_set_up(dev); + if (err) + return err; + + for (i = 0; i < dev->data->nb_tx_queues; i++) + dev->data->tx_queue_state[i] = RTE_ETH_QUEUE_STATE_STARTED; + for (i = 0; i < dev->data->nb_rx_queues; i++) + dev->data->rx_queue_state[i] = RTE_ETH_QUEUE_STATE_STARTED; + + return err; } /* This function gets called when the current port gets stopped. @@ -661,6 +841,13 @@ tap_dev_start(struct rte_eth_dev *dev) static void tap_dev_stop(struct rte_eth_dev *dev) { + int i; + + for (i = 0; i < dev->data->nb_tx_queues; i++) + dev->data->tx_queue_state[i] = RTE_ETH_QUEUE_STATE_STOPPED; + for (i = 0; i < dev->data->nb_rx_queues; i++) + dev->data->rx_queue_state[i] = RTE_ETH_QUEUE_STATE_STOPPED; + tap_intr_handle_set(dev, 0); tap_link_set_down(dev); } @@ -668,18 +855,8 @@ tap_dev_stop(struct rte_eth_dev *dev) static int tap_dev_configure(struct rte_eth_dev *dev) { - uint64_t supp_tx_offloads = tap_tx_offload_get_port_capa() | - tap_tx_offload_get_queue_capa(); - uint64_t tx_offloads = dev->data->dev_conf.txmode.offloads; + struct pmd_internals *pmd = dev->data->dev_private; - if ((tx_offloads & supp_tx_offloads) != tx_offloads) { - rte_errno = ENOTSUP; - TAP_LOG(ERR, - "Some Tx offloads are not supported " - "requested 0x%" PRIx64 " supported 0x%" PRIx64, - tx_offloads, supp_tx_offloads); - return -rte_errno; - } if (dev->data->nb_rx_queues > RTE_PMD_TAP_MAX_QUEUES) { TAP_LOG(ERR, "%s: number of rx queues %d exceeds max num of queues %d", @@ -697,11 +874,11 @@ tap_dev_configure(struct rte_eth_dev *dev) return -1; } - TAP_LOG(INFO, "%s: %p: TX configured queues number: %u", - dev->device->name, (void *)dev, dev->data->nb_tx_queues); + TAP_LOG(INFO, "%s: %s: TX configured queues number: %u", + dev->device->name, pmd->name, dev->data->nb_tx_queues); - TAP_LOG(INFO, "%s: %p: RX configured queues number: %u", - dev->device->name, (void *)dev, dev->data->nb_rx_queues); + TAP_LOG(INFO, "%s: %s: RX configured queues number: %u", + dev->device->name, pmd->name, dev->data->nb_rx_queues); return 0; } @@ -758,6 +935,12 @@ tap_dev_info(struct rte_eth_dev *dev, struct rte_eth_dev_info *dev_info) dev_info->tx_queue_offload_capa = tap_tx_offload_get_queue_capa(); dev_info->tx_offload_capa = tap_tx_offload_get_port_capa() | dev_info->tx_queue_offload_capa; + dev_info->hash_key_size = TAP_RSS_HASH_KEY_SIZE; + /* + * limitation: TAP supports all of IP, UDP and TCP hash + * functions together and not in partial combinations + */ + dev_info->flow_type_rss_offloads = ~TAP_RSS_HF_MASK; } static int @@ -827,19 +1010,20 @@ tap_dev_close(struct rte_eth_dev *dev) { int i; struct pmd_internals *internals = dev->data->dev_private; + struct pmd_process_private *process_private = dev->process_private; tap_link_set_down(dev); tap_flow_flush(dev, NULL); tap_flow_implicit_flush(internals, NULL); for (i = 0; i < RTE_PMD_TAP_MAX_QUEUES; i++) { - if (internals->rxq[i].fd != -1) { - close(internals->rxq[i].fd); - internals->rxq[i].fd = -1; + if (process_private->rxq_fds[i] != -1) { + close(process_private->rxq_fds[i]); + process_private->rxq_fds[i] = -1; } - if (internals->txq[i].fd != -1) { - close(internals->txq[i].fd); - internals->txq[i].fd = -1; + if (process_private->txq_fds[i] != -1) { + close(process_private->txq_fds[i]); + process_private->txq_fds[i] = -1; } } @@ -848,16 +1032,29 @@ tap_dev_close(struct rte_eth_dev *dev) ioctl(internals->ioctl_sock, SIOCSIFFLAGS, &internals->remote_initial_flags); } + + if (internals->ka_fd != -1) { + close(internals->ka_fd); + internals->ka_fd = -1; + } + /* + * Since TUN device has no more opened file descriptors + * it will be removed from kernel + */ } static void tap_rx_queue_release(void *queue) { struct rx_queue *rxq = queue; + struct pmd_process_private *process_private; - if (rxq && (rxq->fd > 0)) { - close(rxq->fd); - rxq->fd = -1; + if (!rxq) + return; + process_private = rte_eth_devices[rxq->in_port].process_private; + if (process_private->rxq_fds[rxq->queue_id] > 0) { + close(process_private->rxq_fds[rxq->queue_id]); + process_private->rxq_fds[rxq->queue_id] = -1; rte_pktmbuf_free(rxq->pool); rte_free(rxq->iovecs); rxq->pool = NULL; @@ -869,10 +1066,15 @@ static void tap_tx_queue_release(void *queue) { struct tx_queue *txq = queue; + struct pmd_process_private *process_private; + + if (!txq) + return; + process_private = rte_eth_devices[txq->out_port].process_private; - if (txq && (txq->fd > 0)) { - close(txq->fd); - txq->fd = -1; + if (process_private->txq_fds[txq->queue_id] > 0) { + close(process_private->txq_fds[txq->queue_id]); + process_private->txq_fds[txq->queue_id] = -1; } } @@ -948,13 +1150,19 @@ tap_allmulti_disable(struct rte_eth_dev *dev) } static int -tap_mac_set(struct rte_eth_dev *dev, struct ether_addr *mac_addr) +tap_mac_set(struct rte_eth_dev *dev, struct rte_ether_addr *mac_addr) { struct pmd_internals *pmd = dev->data->dev_private; enum ioctl_mode mode = LOCAL_ONLY; struct ifreq ifr; int ret; + if (pmd->type == ETH_TUNTAP_TYPE_TUN) { + TAP_LOG(ERR, "%s: can't MAC address for TUN", + dev->device->name); + return -ENOTSUP; + } + if (is_zero_ether_addr(mac_addr)) { TAP_LOG(ERR, "%s: can't set an empty MAC address", dev->device->name); @@ -964,15 +1172,16 @@ tap_mac_set(struct rte_eth_dev *dev, struct ether_addr *mac_addr) ret = tap_ioctl(pmd, SIOCGIFHWADDR, &ifr, 0, LOCAL_ONLY); if (ret < 0) return ret; - if (is_same_ether_addr((struct ether_addr *)&ifr.ifr_hwaddr.sa_data, + if (is_same_ether_addr((struct rte_ether_addr *)&ifr.ifr_hwaddr.sa_data, mac_addr)) return 0; /* Check the current MAC address on the remote */ ret = tap_ioctl(pmd, SIOCGIFHWADDR, &ifr, 0, REMOTE_ONLY); if (ret < 0) return ret; - if (!is_same_ether_addr((struct ether_addr *)&ifr.ifr_hwaddr.sa_data, - mac_addr)) + if (!is_same_ether_addr( + (struct rte_ether_addr *)&ifr.ifr_hwaddr.sa_data, + mac_addr)) mode = LOCAL_AND_REMOTE; ifr.ifr_hwaddr.sa_family = AF_LOCAL; rte_memcpy(ifr.ifr_hwaddr.sa_data, mac_addr, ETHER_ADDR_LEN); @@ -1001,32 +1210,77 @@ tap_mac_set(struct rte_eth_dev *dev, struct ether_addr *mac_addr) return 0; } +static int +tap_gso_ctx_setup(struct rte_gso_ctx *gso_ctx, struct rte_eth_dev *dev) +{ + uint32_t gso_types; + char pool_name[64]; + + /* + * Create private mbuf pool with TAP_GSO_MBUF_SEG_SIZE bytes + * size per mbuf use this pool for both direct and indirect mbufs + */ + + struct rte_mempool *mp; /* Mempool for GSO packets */ + + /* initialize GSO context */ + gso_types = DEV_TX_OFFLOAD_TCP_TSO; + snprintf(pool_name, sizeof(pool_name), "mp_%s", dev->device->name); + mp = rte_mempool_lookup((const char *)pool_name); + if (!mp) { + mp = rte_pktmbuf_pool_create(pool_name, TAP_GSO_MBUFS_NUM, + TAP_GSO_MBUF_CACHE_SIZE, 0, + RTE_PKTMBUF_HEADROOM + TAP_GSO_MBUF_SEG_SIZE, + SOCKET_ID_ANY); + if (!mp) { + struct pmd_internals *pmd = dev->data->dev_private; + RTE_LOG(DEBUG, PMD, "%s: failed to create mbuf pool for device %s\n", + pmd->name, dev->device->name); + return -1; + } + } + + gso_ctx->direct_pool = mp; + gso_ctx->indirect_pool = mp; + gso_ctx->gso_types = gso_types; + gso_ctx->gso_size = 0; /* gso_size is set in tx_burst() per packet */ + gso_ctx->flag = 0; + + return 0; +} + static int tap_setup_queue(struct rte_eth_dev *dev, struct pmd_internals *internals, uint16_t qid, int is_rx) { + int ret; int *fd; int *other_fd; const char *dir; struct pmd_internals *pmd = dev->data->dev_private; + struct pmd_process_private *process_private = dev->process_private; struct rx_queue *rx = &internals->rxq[qid]; struct tx_queue *tx = &internals->txq[qid]; + struct rte_gso_ctx *gso_ctx; if (is_rx) { - fd = &rx->fd; - other_fd = &tx->fd; + fd = &process_private->rxq_fds[qid]; + other_fd = &process_private->txq_fds[qid]; dir = "rx"; + gso_ctx = NULL; } else { - fd = &tx->fd; - other_fd = &rx->fd; + fd = &process_private->txq_fds[qid]; + other_fd = &process_private->rxq_fds[qid]; dir = "tx"; + gso_ctx = &tx->gso_ctx; } if (*fd != -1) { /* fd for this queue already exists */ TAP_LOG(DEBUG, "%s: fd %d for %s queue qid %d exists", pmd->name, *fd, dir, qid); + gso_ctx = NULL; } else if (*other_fd != -1) { /* Only other_fd exists. dup it */ *fd = dup(*other_fd); @@ -1039,7 +1293,7 @@ tap_setup_queue(struct rte_eth_dev *dev, pmd->name, *other_fd, dir, qid, *fd); } else { /* Both RX and TX fds do not exist (equal -1). Create fd */ - *fd = tun_alloc(pmd); + *fd = tun_alloc(pmd, 0); if (*fd < 0) { *fd = -1; /* restore original value */ TAP_LOG(ERR, "%s: tun_alloc() failed.", pmd->name); @@ -1051,6 +1305,13 @@ tap_setup_queue(struct rte_eth_dev *dev, tx->mtu = &dev->data->mtu; rx->rxmode = &dev->data->dev_conf.rxmode; + if (gso_ctx) { + ret = tap_gso_ctx_setup(gso_ctx, dev); + if (ret) + return -1; + } + + tx->type = pmd->type; return *fd; } @@ -1064,9 +1325,17 @@ tap_rx_queue_setup(struct rte_eth_dev *dev, struct rte_mempool *mp) { struct pmd_internals *internals = dev->data->dev_private; + struct pmd_process_private *process_private = dev->process_private; struct rx_queue *rxq = &internals->rxq[rx_queue_id]; struct rte_mbuf **tmp = &rxq->pool; long iov_max = sysconf(_SC_IOV_MAX); + + if (iov_max <= 0) { + TAP_LOG(WARNING, + "_SC_IOV_MAX is not defined. Using %d as default", + TAP_IOV_DEFAULT_MAX); + iov_max = TAP_IOV_DEFAULT_MAX; + } uint16_t nb_desc = RTE_MIN(nb_rx_desc, iov_max - 1); struct iovec (*iovecs)[nb_desc + 1]; int data_off = RTE_PKTMBUF_HEADROOM; @@ -1081,22 +1350,10 @@ tap_rx_queue_setup(struct rte_eth_dev *dev, return -1; } - /* Verify application offloads are valid for our port and queue. */ - if (!tap_rxq_are_offloads_valid(dev, rx_conf->offloads)) { - rte_errno = ENOTSUP; - TAP_LOG(ERR, - "%p: Rx queue offloads 0x%" PRIx64 - " don't match port offloads 0x%" PRIx64 - " or supported offloads 0x%" PRIx64, - (void *)dev, rx_conf->offloads, - dev->data->dev_conf.rxmode.offloads, - (tap_rx_offload_get_port_capa() | - tap_rx_offload_get_queue_capa())); - return -rte_errno; - } rxq->mp = mp; rxq->trigger_seen = 1; /* force initial burst */ rxq->in_port = dev->data->port_id; + rxq->queue_id = rx_queue_id; rxq->nb_rx_desc = nb_desc; iovecs = rte_zmalloc_socket(dev->device->name, sizeof(*iovecs), 0, socket_id); @@ -1135,7 +1392,8 @@ tap_rx_queue_setup(struct rte_eth_dev *dev, } TAP_LOG(DEBUG, " RX TUNTAP device name %s, qid %d on fd %d", - internals->name, rx_queue_id, internals->rxq[rx_queue_id].fd); + internals->name, rx_queue_id, + process_private->rxq_fds[rx_queue_id]); return 0; @@ -1155,43 +1413,31 @@ tap_tx_queue_setup(struct rte_eth_dev *dev, const struct rte_eth_txconf *tx_conf) { struct pmd_internals *internals = dev->data->dev_private; + struct pmd_process_private *process_private = dev->process_private; struct tx_queue *txq; int ret; + uint64_t offloads; if (tx_queue_id >= dev->data->nb_tx_queues) return -1; dev->data->tx_queues[tx_queue_id] = &internals->txq[tx_queue_id]; txq = dev->data->tx_queues[tx_queue_id]; - /* - * Don't verify port offloads for application which - * use the old API. - */ - if (tx_conf != NULL && - !!(tx_conf->txq_flags & ETH_TXQ_FLAGS_IGNORE)) { - if (tap_txq_are_offloads_valid(dev, tx_conf->offloads)) { - txq->csum = !!(tx_conf->offloads & - (DEV_TX_OFFLOAD_IPV4_CKSUM | - DEV_TX_OFFLOAD_UDP_CKSUM | - DEV_TX_OFFLOAD_TCP_CKSUM)); - } else { - rte_errno = ENOTSUP; - TAP_LOG(ERR, - "%p: Tx queue offloads 0x%" PRIx64 - " don't match port offloads 0x%" PRIx64 - " or supported offloads 0x%" PRIx64, - (void *)dev, tx_conf->offloads, - dev->data->dev_conf.txmode.offloads, - (tap_tx_offload_get_port_capa() | - tap_tx_offload_get_queue_capa())); - return -rte_errno; - } - } + txq->out_port = dev->data->port_id; + txq->queue_id = tx_queue_id; + + offloads = tx_conf->offloads | dev->data->dev_conf.txmode.offloads; + txq->csum = !!(offloads & + (DEV_TX_OFFLOAD_IPV4_CKSUM | + DEV_TX_OFFLOAD_UDP_CKSUM | + DEV_TX_OFFLOAD_TCP_CKSUM)); + ret = tap_setup_queue(dev, internals, tx_queue_id, 0); if (ret == -1) return -1; TAP_LOG(DEBUG, " TX TUNTAP device name %s, qid %d on fd %d csum %s", - internals->name, tx_queue_id, internals->txq[tx_queue_id].fd, + internals->name, tx_queue_id, + process_private->txq_fds[tx_queue_id], txq->csum ? "on" : "off"); return 0; @@ -1213,7 +1459,7 @@ tap_mtu_set(struct rte_eth_dev *dev, uint16_t mtu) static int tap_set_mc_addr_list(struct rte_eth_dev *dev __rte_unused, - struct ether_addr *mc_addr_set __rte_unused, + struct rte_ether_addr *mc_addr_set __rte_unused, uint32_t nb_mc_addr __rte_unused) { /* @@ -1334,6 +1580,70 @@ tap_flow_ctrl_set(struct rte_eth_dev *dev __rte_unused, return 0; } +/** + * DPDK callback to update the RSS hash configuration. + * + * @param dev + * Pointer to Ethernet device structure. + * @param[in] rss_conf + * RSS configuration data. + * + * @return + * 0 on success, a negative errno value otherwise and rte_errno is set. + */ +static int +tap_rss_hash_update(struct rte_eth_dev *dev, + struct rte_eth_rss_conf *rss_conf) +{ + if (rss_conf->rss_hf & TAP_RSS_HF_MASK) { + rte_errno = EINVAL; + return -rte_errno; + } + if (rss_conf->rss_key && rss_conf->rss_key_len) { + /* + * Currently TAP RSS key is hard coded + * and cannot be updated + */ + TAP_LOG(ERR, + "port %u RSS key cannot be updated", + dev->data->port_id); + rte_errno = EINVAL; + return -rte_errno; + } + return 0; +} + +static int +tap_rx_queue_start(struct rte_eth_dev *dev, uint16_t rx_queue_id) +{ + dev->data->rx_queue_state[rx_queue_id] = RTE_ETH_QUEUE_STATE_STARTED; + + return 0; +} + +static int +tap_tx_queue_start(struct rte_eth_dev *dev, uint16_t tx_queue_id) +{ + dev->data->tx_queue_state[tx_queue_id] = RTE_ETH_QUEUE_STATE_STARTED; + + return 0; +} + +static int +tap_rx_queue_stop(struct rte_eth_dev *dev, uint16_t rx_queue_id) +{ + dev->data->rx_queue_state[rx_queue_id] = RTE_ETH_QUEUE_STATE_STOPPED; + + return 0; +} + +static int +tap_tx_queue_stop(struct rte_eth_dev *dev, uint16_t tx_queue_id) +{ + dev->data->tx_queue_state[tx_queue_id] = RTE_ETH_QUEUE_STATE_STOPPED; + + return 0; +} static const struct eth_dev_ops ops = { .dev_start = tap_dev_start, .dev_stop = tap_dev_stop, @@ -1342,6 +1652,10 @@ static const struct eth_dev_ops ops = { .dev_infos_get = tap_dev_info, .rx_queue_setup = tap_rx_queue_setup, .tx_queue_setup = tap_tx_queue_setup, + .rx_queue_start = tap_rx_queue_start, + .tx_queue_start = tap_tx_queue_start, + .rx_queue_stop = tap_rx_queue_stop, + .tx_queue_stop = tap_tx_queue_stop, .rx_queue_release = tap_rx_queue_release, .tx_queue_release = tap_tx_queue_release, .flow_ctrl_get = tap_flow_ctrl_get, @@ -1359,22 +1673,29 @@ static const struct eth_dev_ops ops = { .stats_get = tap_stats_get, .stats_reset = tap_stats_reset, .dev_supported_ptypes_get = tap_dev_supported_ptypes_get, + .rss_hash_update = tap_rss_hash_update, .filter_ctrl = tap_dev_filter_ctrl, }; +static const char *tuntap_types[ETH_TUNTAP_TYPE_MAX] = { + "UNKNOWN", "TUN", "TAP" +}; + static int -eth_dev_tap_create(struct rte_vdev_device *vdev, char *tap_name, - char *remote_iface, struct ether_addr *mac_addr) +eth_dev_tap_create(struct rte_vdev_device *vdev, const char *tap_name, + char *remote_iface, struct rte_ether_addr *mac_addr, + enum rte_tuntap_type type) { int numa_node = rte_socket_id(); struct rte_eth_dev *dev; struct pmd_internals *pmd; + struct pmd_process_private *process_private; + const char *tuntap_name = tuntap_types[type]; struct rte_eth_dev_data *data; struct ifreq ifr; int i; - TAP_LOG(DEBUG, "%s device on numa %u", - tuntap_name, rte_socket_id()); + TAP_LOG(DEBUG, "%s device on numa %u", tuntap_name, rte_socket_id()); dev = rte_eth_vdev_allocate(vdev, sizeof(*pmd)); if (!dev) { @@ -1383,9 +1704,19 @@ eth_dev_tap_create(struct rte_vdev_device *vdev, char *tap_name, goto error_exit_nodev; } + process_private = (struct pmd_process_private *) + rte_zmalloc_socket(tap_name, sizeof(struct pmd_process_private), + RTE_CACHE_LINE_SIZE, dev->device->numa_node); + + if (process_private == NULL) { + TAP_LOG(ERR, "Failed to alloc memory for process private"); + return -1; + } pmd = dev->data->dev_private; + dev->process_private = process_private; pmd->dev = dev; - snprintf(pmd->name, sizeof(pmd->name), "%s", tap_name); + strlcpy(pmd->name, tap_name, sizeof(pmd->name)); + pmd->type = type; pmd->ioctl_sock = socket(AF_INET, SOCK_DGRAM, 0); if (pmd->ioctl_sock == -1) { @@ -1416,31 +1747,37 @@ eth_dev_tap_create(struct rte_vdev_device *vdev, char *tap_name, dev->intr_handle = &pmd->intr_handle; /* Presetup the fds to -1 as being not valid */ + pmd->ka_fd = -1; for (i = 0; i < RTE_PMD_TAP_MAX_QUEUES; i++) { - pmd->rxq[i].fd = -1; - pmd->txq[i].fd = -1; + process_private->rxq_fds[i] = -1; + process_private->txq_fds[i] = -1; } - if (tap_type) { + if (pmd->type == ETH_TUNTAP_TYPE_TAP) { if (is_zero_ether_addr(mac_addr)) eth_random_addr((uint8_t *)&pmd->eth_addr); else rte_memcpy(&pmd->eth_addr, mac_addr, sizeof(*mac_addr)); } - /* Immediately create the netdevice (this will create the 1st queue). */ - /* rx queue */ - if (tap_setup_queue(dev, pmd, 0, 1) == -1) - goto error_exit; - /* tx queue */ - if (tap_setup_queue(dev, pmd, 0, 0) == -1) + /* + * Allocate a TUN device keep-alive file descriptor that will only be + * closed when the TUN device itself is closed or removed. + * This keep-alive file descriptor will guarantee that the TUN device + * exists even when all of its queues are closed + */ + pmd->ka_fd = tun_alloc(pmd, 1); + if (pmd->ka_fd == -1) { + TAP_LOG(ERR, "Unable to create %s interface", tuntap_name); goto error_exit; + } + TAP_LOG(DEBUG, "allocated %s", pmd->name); ifr.ifr_mtu = dev->data->mtu; if (tap_ioctl(pmd, SIOCSIFMTU, &ifr, 1, LOCAL_AND_REMOTE) < 0) goto error_exit; - if (tap_type) { + if (pmd->type == ETH_TUNTAP_TYPE_TAP) { memset(&ifr, 0, sizeof(struct ifreq)); ifr.ifr_hwaddr.sa_family = AF_LOCAL; rte_memcpy(ifr.ifr_hwaddr.sa_data, &pmd->eth_addr, @@ -1487,8 +1824,7 @@ eth_dev_tap_create(struct rte_vdev_device *vdev, char *tap_name, pmd->name, remote_iface); goto error_remote; } - snprintf(pmd->remote_iface, RTE_ETH_NAME_MAX_LEN, - "%s", remote_iface); + strlcpy(pmd->remote_iface, remote_iface, RTE_ETH_NAME_MAX_LEN); /* Save state of remote device */ tap_ioctl(pmd, SIOCGIFFLAGS, &pmd->remote_initial_flags, 0, REMOTE_ONLY); @@ -1532,6 +1868,7 @@ eth_dev_tap_create(struct rte_vdev_device *vdev, char *tap_name, } } + rte_eth_dev_probing_finish(dev); return 0; disable_rte_flow: @@ -1541,6 +1878,7 @@ disable_rte_flow: TAP_LOG(ERR, "Remote feature requires flow support."); goto error_exit; } + rte_eth_dev_probing_finish(dev); return 0; error_remote: @@ -1551,6 +1889,8 @@ error_remote: error_exit: if (pmd->ioctl_sock > 0) close(pmd->ioctl_sock); + /* mac_addrs must not be freed alone because part of dev_private */ + dev->data->mac_addrs = NULL; rte_eth_dev_release_port(dev); error_exit_nodev: @@ -1560,6 +1900,24 @@ error_exit_nodev: return -EINVAL; } +/* make sure name is a possible Linux network device name */ +static bool +is_valid_iface(const char *name) +{ + if (*name == '\0') + return false; + + if (strnlen(name, IFNAMSIZ) == IFNAMSIZ) + return false; + + while (*name) { + if (*name == '/' || *name == ':' || isspace(*name)) + return false; + name++; + } + return true; +} + static int set_interface_name(const char *key __rte_unused, const char *value, @@ -1567,12 +1925,17 @@ set_interface_name(const char *key __rte_unused, { char *name = (char *)extra_args; - if (value) - strlcpy(name, value, RTE_ETH_NAME_MAX_LEN - 1); - else - snprintf(name, RTE_ETH_NAME_MAX_LEN - 1, "%s%d", - DEFAULT_TAP_NAME, (tap_unit - 1)); - + if (value) { + if (!is_valid_iface(value)) { + TAP_LOG(ERR, "TAP invalid remote interface name (%s)", + value); + return -1; + } + strlcpy(name, value, RTE_ETH_NAME_MAX_LEN); + } else { + /* use tap%d which causes kernel to choose next available */ + strlcpy(name, DEFAULT_TAP_NAME "%d", RTE_ETH_NAME_MAX_LEN); + } return 0; } @@ -1583,13 +1946,19 @@ set_remote_iface(const char *key __rte_unused, { char *name = (char *)extra_args; - if (value) + if (value) { + if (!is_valid_iface(value)) { + TAP_LOG(ERR, "TAP invalid remote interface name (%s)", + value); + return -1; + } strlcpy(name, value, RTE_ETH_NAME_MAX_LEN); + } return 0; } -static int parse_user_mac(struct ether_addr *user_mac, +static int parse_user_mac(struct rte_ether_addr *user_mac, const char *value) { unsigned int index = 0; @@ -1617,7 +1986,7 @@ set_mac_type(const char *key __rte_unused, const char *value, void *extra_args) { - struct ether_addr *user_mac = extra_args; + struct rte_ether_addr *user_mac = extra_args; if (!value) return 0; @@ -1657,14 +2026,28 @@ rte_pmd_tun_probe(struct rte_vdev_device *dev) struct rte_kvargs *kvlist = NULL; char tun_name[RTE_ETH_NAME_MAX_LEN]; char remote_iface[RTE_ETH_NAME_MAX_LEN]; - - tap_type = 0; - strcpy(tuntap_name, "TUN"); + struct rte_eth_dev *eth_dev; name = rte_vdev_device_name(dev); params = rte_vdev_device_args(dev); memset(remote_iface, 0, RTE_ETH_NAME_MAX_LEN); + if (rte_eal_process_type() == RTE_PROC_SECONDARY && + strlen(params) == 0) { + eth_dev = rte_eth_dev_attach_secondary(name); + if (!eth_dev) { + TAP_LOG(ERR, "Failed to probe %s", name); + return -1; + } + eth_dev->dev_ops = &ops; + eth_dev->device = &dev->device; + rte_eth_dev_probing_finish(eth_dev); + return 0; + } + + /* use tun%d which causes kernel to choose next available */ + strlcpy(tun_name, DEFAULT_TUN_NAME "%d", RTE_ETH_NAME_MAX_LEN); + if (params && (params[0] != '\0')) { TAP_LOG(DEBUG, "parameters (%s)", params); @@ -1683,22 +2066,128 @@ rte_pmd_tun_probe(struct rte_vdev_device *dev) } pmd_link.link_speed = ETH_SPEED_NUM_10G; - TAP_LOG(NOTICE, "Initializing pmd_tun for %s as %s", - name, tun_name); + TAP_LOG(DEBUG, "Initializing pmd_tun for %s", name); - ret = eth_dev_tap_create(dev, tun_name, remote_iface, 0); + ret = eth_dev_tap_create(dev, tun_name, remote_iface, 0, + ETH_TUNTAP_TYPE_TUN); leave: if (ret == -1) { TAP_LOG(ERR, "Failed to create pmd for %s as %s", name, tun_name); - tun_unit--; /* Restore the unit number */ } rte_kvargs_free(kvlist); return ret; } +/* Request queue file descriptors from secondary to primary. */ +static int +tap_mp_attach_queues(const char *port_name, struct rte_eth_dev *dev) +{ + int ret; + struct timespec timeout = {.tv_sec = 1, .tv_nsec = 0}; + struct rte_mp_msg request, *reply; + struct rte_mp_reply replies; + struct ipc_queues *request_param = (struct ipc_queues *)request.param; + struct ipc_queues *reply_param; + struct pmd_process_private *process_private = dev->process_private; + int queue, fd_iterator; + + /* Prepare the request */ + memset(&request, 0, sizeof(request)); + strlcpy(request.name, TAP_MP_KEY, sizeof(request.name)); + strlcpy(request_param->port_name, port_name, + sizeof(request_param->port_name)); + request.len_param = sizeof(*request_param); + /* Send request and receive reply */ + ret = rte_mp_request_sync(&request, &replies, &timeout); + if (ret < 0 || replies.nb_received != 1) { + TAP_LOG(ERR, "Failed to request queues from primary: %d", + rte_errno); + return -1; + } + reply = &replies.msgs[0]; + reply_param = (struct ipc_queues *)reply->param; + TAP_LOG(DEBUG, "Received IPC reply for %s", reply_param->port_name); + + /* Attach the queues from received file descriptors */ + if (reply_param->rxq_count + reply_param->txq_count != reply->num_fds) { + TAP_LOG(ERR, "Unexpected number of fds received"); + return -1; + } + + dev->data->nb_rx_queues = reply_param->rxq_count; + dev->data->nb_tx_queues = reply_param->txq_count; + fd_iterator = 0; + for (queue = 0; queue < reply_param->rxq_count; queue++) + process_private->rxq_fds[queue] = reply->fds[fd_iterator++]; + for (queue = 0; queue < reply_param->txq_count; queue++) + process_private->txq_fds[queue] = reply->fds[fd_iterator++]; + free(reply); + return 0; +} + +/* Send the queue file descriptors from the primary process to secondary. */ +static int +tap_mp_sync_queues(const struct rte_mp_msg *request, const void *peer) +{ + struct rte_eth_dev *dev; + struct pmd_process_private *process_private; + struct rte_mp_msg reply; + const struct ipc_queues *request_param = + (const struct ipc_queues *)request->param; + struct ipc_queues *reply_param = + (struct ipc_queues *)reply.param; + uint16_t port_id; + int queue; + int ret; + + /* Get requested port */ + TAP_LOG(DEBUG, "Received IPC request for %s", request_param->port_name); + ret = rte_eth_dev_get_port_by_name(request_param->port_name, &port_id); + if (ret) { + TAP_LOG(ERR, "Failed to get port id for %s", + request_param->port_name); + return -1; + } + dev = &rte_eth_devices[port_id]; + process_private = dev->process_private; + + /* Fill file descriptors for all queues */ + reply.num_fds = 0; + reply_param->rxq_count = 0; + if (dev->data->nb_rx_queues + dev->data->nb_tx_queues > + RTE_MP_MAX_FD_NUM){ + TAP_LOG(ERR, "Number of rx/tx queues exceeds max number of fds"); + return -1; + } + + for (queue = 0; queue < dev->data->nb_rx_queues; queue++) { + reply.fds[reply.num_fds++] = process_private->rxq_fds[queue]; + reply_param->rxq_count++; + } + RTE_ASSERT(reply_param->rxq_count == dev->data->nb_rx_queues); + + reply_param->txq_count = 0; + for (queue = 0; queue < dev->data->nb_tx_queues; queue++) { + reply.fds[reply.num_fds++] = process_private->txq_fds[queue]; + reply_param->txq_count++; + } + RTE_ASSERT(reply_param->txq_count == dev->data->nb_tx_queues); + + /* Send reply */ + strlcpy(reply.name, request->name, sizeof(reply.name)); + strlcpy(reply_param->port_name, request_param->port_name, + sizeof(reply_param->port_name)); + reply.len_param = sizeof(*reply_param); + if (rte_mp_reply(&reply, peer) < 0) { + TAP_LOG(ERR, "Failed to reply an IPC request to sync queues"); + return -1; + } + return 0; +} + /* Open a TAP interface device. */ static int @@ -1710,30 +2199,49 @@ rte_pmd_tap_probe(struct rte_vdev_device *dev) int speed; char tap_name[RTE_ETH_NAME_MAX_LEN]; char remote_iface[RTE_ETH_NAME_MAX_LEN]; - struct ether_addr user_mac = { .addr_bytes = {0} }; + struct rte_ether_addr user_mac = { .addr_bytes = {0} }; struct rte_eth_dev *eth_dev; - - tap_type = 1; - strcpy(tuntap_name, "TAP"); + int tap_devices_count_increased = 0; name = rte_vdev_device_name(dev); params = rte_vdev_device_args(dev); - if (rte_eal_process_type() == RTE_PROC_SECONDARY && - strlen(params) == 0) { + if (rte_eal_process_type() == RTE_PROC_SECONDARY) { eth_dev = rte_eth_dev_attach_secondary(name); if (!eth_dev) { TAP_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; + eth_dev->rx_pkt_burst = pmd_rx_burst; + eth_dev->tx_pkt_burst = pmd_tx_burst; + if (!rte_eal_primary_proc_alive(NULL)) { + TAP_LOG(ERR, "Primary process is missing"); + return -1; + } + eth_dev->process_private = (struct pmd_process_private *) + rte_zmalloc_socket(name, + sizeof(struct pmd_process_private), + RTE_CACHE_LINE_SIZE, + eth_dev->device->numa_node); + if (eth_dev->process_private == NULL) { + TAP_LOG(ERR, + "Failed to alloc memory for process private"); + return -1; + } + + ret = tap_mp_attach_queues(name, eth_dev); + if (ret != 0) + return -1; + rte_eth_dev_probing_finish(eth_dev); return 0; } speed = ETH_SPEED_NUM_10G; - snprintf(tap_name, sizeof(tap_name), "%s%d", - DEFAULT_TAP_NAME, tap_unit++); + + /* use tap%d which causes kernel to choose next available */ + strlcpy(tap_name, DEFAULT_TAP_NAME "%d", RTE_ETH_NAME_MAX_LEN); memset(remote_iface, 0, RTE_ETH_NAME_MAX_LEN); if (params && (params[0] != '\0')) { @@ -1771,16 +2279,31 @@ rte_pmd_tap_probe(struct rte_vdev_device *dev) } pmd_link.link_speed = speed; - TAP_LOG(NOTICE, "Initializing pmd_tap for %s as %s", - name, tap_name); + TAP_LOG(DEBUG, "Initializing pmd_tap for %s", name); - ret = eth_dev_tap_create(dev, tap_name, remote_iface, &user_mac); + /* Register IPC feed callback */ + if (!tap_devices_count) { + ret = rte_mp_action_register(TAP_MP_KEY, tap_mp_sync_queues); + if (ret < 0) { + TAP_LOG(ERR, "tap: Failed to register IPC callback: %s", + strerror(rte_errno)); + goto leave; + } + } + tap_devices_count++; + tap_devices_count_increased = 1; + ret = eth_dev_tap_create(dev, tap_name, remote_iface, &user_mac, + ETH_TUNTAP_TYPE_TAP); leave: if (ret == -1) { TAP_LOG(ERR, "Failed to create pmd for %s as %s", name, tap_name); - tap_unit--; /* Restore the unit number */ + if (tap_devices_count_increased == 1) { + if (tap_devices_count == 1) + rte_mp_action_unregister(TAP_MP_KEY); + tap_devices_count--; + } } rte_kvargs_free(kvlist); @@ -1794,38 +2317,53 @@ rte_pmd_tap_remove(struct rte_vdev_device *dev) { struct rte_eth_dev *eth_dev = NULL; struct pmd_internals *internals; + struct pmd_process_private *process_private; int i; - TAP_LOG(DEBUG, "Closing TUN/TAP Ethernet device on numa %u", - rte_socket_id()); - /* find the ethdev entry */ eth_dev = rte_eth_dev_allocated(rte_vdev_device_name(dev)); if (!eth_dev) - return 0; + return -ENODEV; + + /* 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; + process_private = eth_dev->process_private; + + TAP_LOG(DEBUG, "Closing %s Ethernet device on numa %u", + tuntap_types[internals->type], rte_socket_id()); + if (internals->nlsk_fd) { tap_flow_flush(eth_dev, NULL); tap_flow_implicit_flush(internals, NULL); tap_nl_final(internals->nlsk_fd); } for (i = 0; i < RTE_PMD_TAP_MAX_QUEUES; i++) { - if (internals->rxq[i].fd != -1) { - close(internals->rxq[i].fd); - internals->rxq[i].fd = -1; + if (process_private->rxq_fds[i] != -1) { + close(process_private->rxq_fds[i]); + process_private->rxq_fds[i] = -1; } - if (internals->txq[i].fd != -1) { - close(internals->txq[i].fd); - internals->txq[i].fd = -1; + if (process_private->txq_fds[i] != -1) { + close(process_private->txq_fds[i]); + process_private->txq_fds[i] = -1; } } close(internals->ioctl_sock); - rte_free(eth_dev->data->dev_private); - + rte_free(eth_dev->process_private); + if (tap_devices_count == 1) + rte_mp_action_unregister(TAP_MP_KEY); + tap_devices_count--; rte_eth_dev_release_port(eth_dev); + if (internals->ka_fd != -1) { + close(internals->ka_fd); + internals->ka_fd = -1; + } return 0; } @@ -1850,9 +2388,7 @@ RTE_PMD_REGISTER_PARAM_STRING(net_tap, ETH_TAP_REMOTE_ARG "="); int tap_logtype; -RTE_INIT(tap_init_log); -static void -tap_init_log(void) +RTE_INIT(tap_init_log) { tap_logtype = rte_log_register("pmd.net.tap"); if (tap_logtype >= 0)