X-Git-Url: http://git.droids-corp.org/?a=blobdiff_plain;f=drivers%2Fnet%2Faf_packet%2Frte_eth_af_packet.c;h=57eccfd047fc879dab3748304e2aa2131194ea1e;hb=05e34de29862280553788232aa8c666c7f0ca44d;hp=6777c41b5202ff0a43490aa3cad73981989966d9;hpb=50a3345fa9ea6482f197567497b0b8d201173a59;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 6777c41b52..57eccfd047 100644 --- a/drivers/net/af_packet/rte_eth_af_packet.c +++ b/drivers/net/af_packet/rte_eth_af_packet.c @@ -1,46 +1,17 @@ -/*- - * BSD LICENSE - * - * Copyright(c) 2014 John W. Linville - * - * 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 + * Originally based upon librte_pmd_pcap code: + * Copyright(c) 2010-2015 Intel Corporation. + * Copyright(c) 2014 6WIND S.A. + * All rights reserved. */ #include -#include +#include +#include #include #include -#include +#include #include #include @@ -58,6 +29,7 @@ #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) @@ -74,7 +46,7 @@ struct pkt_rx_queue { unsigned int framenum; struct rte_mempool *mb_pool; - uint8_t in_port; + uint16_t in_port; volatile unsigned long rx_pkts; volatile unsigned long err_pkts; @@ -83,6 +55,7 @@ struct pkt_rx_queue { struct pkt_tx_queue { int sockfd; + unsigned int frame_data_size; struct iovec *rd; uint8_t *map; @@ -98,6 +71,7 @@ struct pmd_internals { unsigned nb_queues; int if_index; + char *if_name; struct ether_addr eth_addr; struct tpacket_req req; @@ -112,16 +86,15 @@ 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 const char *drivername = "AF_PACKET PMD"; - 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_autoneg = ETH_LINK_AUTONEG }; static uint16_t @@ -161,6 +134,12 @@ 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 |= (PKT_RX_VLAN | PKT_RX_VLAN_STRIPPED); + } + /* release incoming frame and advance ring buffer */ ppd->tp_status = TP_STATUS_KERNEL; if (++framenum >= framecount) @@ -206,17 +185,41 @@ eth_af_packet_tx(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts) framenum = pkt_q->framenum; ppd = (struct tpacket2_hdr *) pkt_q->rd[framenum].iov_base; for (i = 0; i < nb_pkts; i++) { + 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 & PKT_TX_VLAN_PKT) { + 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)) - continue; + 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; @@ -230,14 +233,17 @@ eth_af_packet_tx(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts) } /* 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) { + /* error sending -- no packets transmitted */ + 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 @@ -261,9 +267,16 @@ eth_dev_stop(struct rte_eth_dev *dev) 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; @@ -280,17 +293,15 @@ 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->driver_name = drivername; 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_queues = (uint16_t)internals->nb_queues; dev_info->max_tx_queues = (uint16_t)internals->nb_queues; dev_info->min_rx_bufsize = 0; - dev_info->pci_dev = NULL; } -static void +static int eth_stats_get(struct rte_eth_dev *dev, struct rte_eth_stats *igb_stats) { unsigned i, imax; @@ -323,6 +334,7 @@ eth_stats_get(struct rte_eth_dev *dev, struct rte_eth_stats *igb_stats) igb_stats->opackets = tx_total; igb_stats->oerrors = tx_err_total; igb_stats->obytes = tx_bytes_total; + return 0; } static void @@ -370,18 +382,20 @@ eth_rx_queue_setup(struct rte_eth_dev *dev, { 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); + 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 (ETH_FRAME_LEN > buf_size) { + if (data_size > 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); + dev->device->name, data_size, buf_size); return -ENOMEM; } @@ -405,12 +419,80 @@ eth_tx_queue_setup(struct rte_eth_dev *dev, 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 - + sizeof(struct sockaddr_ll); + + if (mtu > data_size) + return -EINVAL; + + s = socket(PF_INET, SOCK_DGRAM, 0); + if (s < 0) + return -EINVAL; + + snprintf(ifr.ifr_name, IFNAMSIZ, "%s", internals->if_name); + ret = ioctl(s, SIOCSIFMTU, &ifr); + close(s); + + if (ret < 0) + return -EINVAL; + + return 0; +} + +static void +eth_dev_change_flags(char *if_name, uint32_t flags, uint32_t mask) +{ + struct ifreq ifr; + int s; + + s = socket(PF_INET, SOCK_DGRAM, 0); + if (s < 0) + return; + + snprintf(ifr.ifr_name, IFNAMSIZ, "%s", if_name); + if (ioctl(s, SIOCGIFFLAGS, &ifr) < 0) + goto out; + ifr.ifr_flags &= mask; + ifr.ifr_flags |= flags; + if (ioctl(s, SIOCSIFFLAGS, &ifr) < 0) + goto out; +out: + close(s); +} + +static void +eth_dev_promiscuous_enable(struct rte_eth_dev *dev) +{ + struct pmd_internals *internals = dev->data->dev_private; + + eth_dev_change_flags(internals->if_name, IFF_PROMISC, ~0); +} + +static void +eth_dev_promiscuous_disable(struct rte_eth_dev *dev) +{ + struct pmd_internals *internals = dev->data->dev_private; + + 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, + .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, @@ -440,19 +522,23 @@ open_packet_iface(const char *key __rte_unused, return 0; } +static struct rte_vdev_driver pmd_af_packet_drv; + 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; @@ -465,7 +551,9 @@ rte_pmd_init_internals(const char *name, 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]; @@ -524,6 +612,9 @@ rte_pmd_init_internals(const char *name, name); goto error_early; } + (*internals)->if_name = strdup(pair->value); + if ((*internals)->if_name == NULL) + goto error_early; (*internals)->if_index = ifr.ifr_ifindex; if (ioctl(sockfd, SIOCGIFHWADDR, &ifr) == -1) { @@ -578,9 +669,8 @@ rte_pmd_init_internals(const char *name, } #if defined(PACKET_QDISC_BYPASS) - bypass = 1; rc = setsockopt(qsockfd, SOL_PACKET, PACKET_QDISC_BYPASS, - &bypass, sizeof(bypass)); + &qdisc_bypass, sizeof(qdisc_bypass)); if (rc == -1) { RTE_LOG(ERR, PMD, "%s: could not set PACKET_QDISC_BYPASS " @@ -588,6 +678,8 @@ rte_pmd_init_internals(const char *name, pair->value); goto error; } +#else + RTE_SET_USED(qdisc_bypass); #endif rc = setsockopt(qsockfd, SOL_PACKET, PACKET_RX_RING, req, sizeof(*req)); @@ -633,6 +725,9 @@ rte_pmd_init_internals(const char *name, 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; @@ -666,7 +761,7 @@ rte_pmd_init_internals(const char *name, } /* 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; @@ -680,22 +775,15 @@ rte_pmd_init_internals(const char *name, (*internals)->nb_queues = nb_queues; + rte_memcpy(data, (*eth_dev)->data, sizeof(*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)); (*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 = drivername; - (*eth_dev)->data->kdrv = RTE_KDRV_NONE; - (*eth_dev)->data->numa_node = numa_node; return 0; @@ -712,6 +800,7 @@ error: ((*internals)->rx_queue[q].sockfd != qsockfd)) close((*internals)->rx_queue[q].sockfd); } + free((*internals)->if_name); rte_free(*internals); error_early: rte_free(data); @@ -719,11 +808,11 @@ error_early: } 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; @@ -733,6 +822,7 @@ rte_eth_from_packet(const char *name, 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) @@ -784,6 +874,16 @@ rte_eth_from_packet(const char *name, } continue; } + if (strstr(pair->key, ETH_AF_PACKET_QDISC_BYPASS_ARG) != NULL) { + qdisc_bypass = atoi(pair->value); + if (qdisc_bypass > 1) { + RTE_LOG(ERR, PMD, + "%s: invalid bypass value\n", + name); + return -1; + } + continue; + } } if (framesize > blocksize) { @@ -806,11 +906,12 @@ rte_eth_from_packet(const char *name, 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) + 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; @@ -820,18 +921,16 @@ rte_eth_from_packet(const char *name, } 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; - RTE_LOG(INFO, PMD, "Initializing pmd_af_packet for %s\n", name); + RTE_LOG(INFO, PMD, "Initializing pmd_af_packet for %s\n", + rte_vdev_device_name(dev)); - numa_node = rte_socket_id(); - - 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; @@ -849,7 +948,10 @@ rte_pmd_af_packet_probe(const char *name, const char *params) 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: @@ -858,7 +960,7 @@ 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; @@ -867,11 +969,11 @@ rte_pmd_af_packet_remove(const char *name) RTE_LOG(INFO, PMD, "Closing AF_PACKET ethdev on numa socket %u\n", rte_socket_id()); - 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; @@ -880,6 +982,7 @@ rte_pmd_af_packet_remove(const char *name) rte_free(internals->rx_queue[q].rd); rte_free(internals->tx_queue[q].rd); } + free(internals->if_name); rte_free(eth_dev->data->dev_private); rte_free(eth_dev->data); @@ -894,10 +997,12 @@ static struct rte_vdev_driver pmd_af_packet_drv = { .remove = rte_pmd_af_packet_remove, }; -DRIVER_REGISTER_VDEV(net_af_packet, pmd_af_packet_drv); -DRIVER_REGISTER_PARAM_STRING(net_af_packet, +RTE_PMD_REGISTER_VDEV(net_af_packet, pmd_af_packet_drv); +RTE_PMD_REGISTER_ALIAS(net_af_packet, eth_af_packet); +RTE_PMD_REGISTER_PARAM_STRING(net_af_packet, "iface= " "qpairs= " "blocksz= " "framesz= " - "framecnt="); + "framecnt= " + "qdisc_bypass=<0|1>");