Add a new devarg 'snaplen' to configure the pcap snapshot length, which controls the maximum packet size for capture and output.
The snapshot length affects: - The pcap_set_snaplen() call when capturing from interfaces - The pcap_open_dead() snapshot parameter for output files - The reported max_rx_pktlen in device info - The reported max_mtu in device info (snaplen - ethernet header) The default value is 65535 bytes, preserving backward compatibility with previous driver behavior. Example usage: --vdev 'net_pcap0,iface=eth0,snaplen=1518' --vdev 'net_pcap0,rx_pcap=in.pcap,tx_pcap=out.pcap,snaplen=9000' Signed-off-by: Stephen Hemminger <[email protected]> --- doc/guides/nics/pcap_ring.rst | 13 ++ doc/guides/rel_notes/release_26_03.rst | 1 + drivers/net/pcap/pcap_ethdev.c | 205 +++++++++++++++---------- 3 files changed, 137 insertions(+), 82 deletions(-) diff --git a/doc/guides/nics/pcap_ring.rst b/doc/guides/nics/pcap_ring.rst index 5b9ca71b18..3a3946e4f1 100644 --- a/doc/guides/nics/pcap_ring.rst +++ b/doc/guides/nics/pcap_ring.rst @@ -132,6 +132,19 @@ Runtime Config Options In this case, one dummy rx queue is created for each tx queue argument passed +- Set the snapshot length for packet capture + + The snapshot length controls the maximum number of bytes captured per packet. + This affects both interface capture and pcap file output. + The default value is 65535 bytes, which captures complete packets up to the maximum Ethernet jumbo frame size. + Reducing this value can improve performance when only packet headers are needed. + This can be done with a ``devarg`` ``snaplen``, for example:: + + --vdev 'net_pcap0,iface=eth0,snaplen=1518' + --vdev 'net_pcap0,rx_pcap=in.pcap,tx_pcap=out.pcap,snaplen=9000' + + The snapshot length also determines the reported ``max_rx_pktlen`` and ``max_mtu`` in device info. + Examples of Usage ^^^^^^^^^^^^^^^^^ diff --git a/doc/guides/rel_notes/release_26_03.rst b/doc/guides/rel_notes/release_26_03.rst index 50ba8bf109..3ad3531800 100644 --- a/doc/guides/rel_notes/release_26_03.rst +++ b/doc/guides/rel_notes/release_26_03.rst @@ -61,6 +61,7 @@ New Features * Added support for reporting link state and speed in ``iface`` mode. * Receive timestamp offload is only done if offload flag set. * Receive timestamps support nanosecond precision. + * Added ``snaplen`` devarg to configure packet capture snapshot length. Removed Items diff --git a/drivers/net/pcap/pcap_ethdev.c b/drivers/net/pcap/pcap_ethdev.c index 415de46e22..937ed8c91b 100644 --- a/drivers/net/pcap/pcap_ethdev.c +++ b/drivers/net/pcap/pcap_ethdev.c @@ -32,8 +32,6 @@ #include "pcap_osdep.h" -#define RTE_ETH_PCAP_SNAPSHOT_LEN 65535 - #define ETH_PCAP_RX_PCAP_ARG "rx_pcap" #define ETH_PCAP_TX_PCAP_ARG "tx_pcap" #define ETH_PCAP_RX_IFACE_ARG "rx_iface" @@ -42,6 +40,9 @@ #define ETH_PCAP_IFACE_ARG "iface" #define ETH_PCAP_PHY_MAC_ARG "phy_mac" #define ETH_PCAP_INFINITE_RX_ARG "infinite_rx" +#define ETH_PCAP_SNAPSHOT_LEN_ARG "snaplen" + +#define ETH_PCAP_SNAPSHOT_LEN_DEFAULT 65535 #define ETH_PCAP_ARG_MAXLEN 64 @@ -102,6 +103,7 @@ struct pmd_internals { char devargs[ETH_PCAP_ARG_MAXLEN]; struct rte_ether_addr eth_addr; int if_index; + uint32_t snapshot_len; bool single_iface; bool phy_mac; bool infinite_rx; @@ -129,6 +131,7 @@ struct pmd_devargs { struct pmd_devargs_all { struct pmd_devargs rx_queues; struct pmd_devargs tx_queues; + uint32_t snapshot_len; bool single_iface; bool is_tx_pcap; bool is_tx_iface; @@ -146,11 +149,16 @@ static const char *valid_arguments[] = { ETH_PCAP_IFACE_ARG, ETH_PCAP_PHY_MAC_ARG, ETH_PCAP_INFINITE_RX_ARG, + ETH_PCAP_SNAPSHOT_LEN_ARG, NULL }; RTE_LOG_REGISTER_DEFAULT(eth_pcap_logtype, NOTICE); +/* Forward declaration */ +static inline int set_iface_direction(const char *iface, pcap_t *pcap, + pcap_direction_t direction); + static struct queue_missed_stat* queue_missed_stat_update(struct rte_eth_dev *dev, unsigned int qid) { @@ -402,20 +410,19 @@ calculate_timestamp(struct timeval *ts) static uint16_t eth_pcap_tx_dumper(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts) { - unsigned int i; - struct pmd_process_private *pp; struct pcap_tx_queue *dumper_q = queue; + struct rte_eth_dev *dev = &rte_eth_devices[dumper_q->port_id]; + struct pmd_internals *internals = dev->data->dev_private; + struct pmd_process_private *pp = dev->process_private; + pcap_dumper_t *dumper = pp->tx_dumper[dumper_q->queue_id]; + unsigned char *temp_data = dumper_q->bounce_buf; + uint32_t snaplen = internals->snapshot_len; uint16_t num_tx = 0; uint32_t tx_bytes = 0; struct pcap_pkthdr header; - pcap_dumper_t *dumper; - unsigned char *temp_data; - - pp = rte_eth_devices[dumper_q->port_id].process_private; - dumper = pp->tx_dumper[dumper_q->queue_id]; - temp_data = dumper_q->bounce_buf; + unsigned int i; - if (dumper == NULL || nb_pkts == 0) + if (unlikely(dumper == NULL)) return 0; /* all packets in burst have same timestamp */ @@ -433,7 +440,8 @@ eth_pcap_tx_dumper(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts) continue; } - len = caplen = rte_pktmbuf_pkt_len(mbuf); + len = rte_pktmbuf_pkt_len(mbuf); + caplen = RTE_MIN(len, snaplen); header.len = len; header.caplen = caplen; @@ -486,25 +494,22 @@ eth_tx_drop(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts) static uint16_t eth_pcap_tx(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts) { - unsigned int i; - struct pmd_process_private *pp; struct pcap_tx_queue *tx_queue = queue; + struct rte_eth_dev *dev = &rte_eth_devices[tx_queue->port_id]; + struct pmd_internals *internals = dev->data->dev_private; + struct pmd_process_private *pp = dev->process_private; + pcap_t *pcap = pp->tx_pcap[tx_queue->queue_id]; + unsigned char *temp_data = tx_queue->bounce_buf; + uint32_t snaplen = internals->snapshot_len; uint16_t num_tx = 0; uint32_t tx_bytes = 0; - pcap_t *pcap; - unsigned char *temp_data; - - pp = rte_eth_devices[tx_queue->port_id].process_private; - pcap = pp->tx_pcap[tx_queue->queue_id]; - temp_data = tx_queue->bounce_buf; + unsigned int i; - if (unlikely(nb_pkts == 0 || pcap == NULL)) + if (unlikely(pcap == NULL)) return 0; for (i = 0; i < nb_pkts; i++) { struct rte_mbuf *mbuf = bufs[i]; - uint32_t len = rte_pktmbuf_pkt_len(mbuf); - const uint8_t *data; if (mbuf->ol_flags & RTE_MBUF_F_TX_VLAN) { /* if vlan insert fails treat it as error */ @@ -512,10 +517,21 @@ eth_pcap_tx(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts) continue; } - data = rte_pktmbuf_read(mbuf, 0, len, temp_data); + uint32_t len = rte_pktmbuf_pkt_len(mbuf); + /* Is bounce buffer needed and is it big enough. */ + if (unlikely(mbuf->nb_segs > 1 && len > snaplen)) { + PMD_LOG(DEBUG, "multi-segment mbuf %u > packet size %u", + len, snaplen); + continue; + } + + const uint8_t *data = rte_pktmbuf_read(mbuf, 0, len, temp_data); if (likely(data != NULL && pcap_sendpacket(pcap, data, len) == 0)) { num_tx++; tx_bytes += len; + } else if (data != NULL) { + PMD_LOG(DEBUG, "pcap_sendpacket failed: %s", + pcap_geterr(pcap)); } } @@ -532,7 +548,7 @@ eth_pcap_tx(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts) * pcap_open_live wrapper function */ static inline int -open_iface_live(const char *iface, pcap_t **pcap) +open_iface_live(const char *iface, pcap_t **pcap, uint32_t snaplen) { char errbuf[PCAP_ERRBUF_SIZE]; pcap_t *pc; @@ -561,7 +577,7 @@ open_iface_live(const char *iface, pcap_t **pcap) PMD_LOG(WARNING, "%s: Could not set to promiscuous: %s", iface, pcap_statustostr(status)); - status = pcap_set_snaplen(pc, RTE_ETH_PCAP_SNAPSHOT_LEN); + status = pcap_set_snaplen(pc, snaplen); if (status != 0) PMD_LOG(WARNING, "%s: Could not set snapshot length: %s", iface, pcap_statustostr(status)); @@ -575,6 +591,9 @@ open_iface_live(const char *iface, pcap_t **pcap) else PMD_LOG(ERR, "%s: %s (%s)", iface, pcap_statustostr(status), cp); goto error; + } else if (status > 0) { + /* Warning condition - log but continue */ + PMD_LOG(WARNING, "%s: %s", iface, pcap_statustostr(status)); } /* @@ -603,9 +622,9 @@ open_iface_live(const char *iface, pcap_t **pcap) } static int -open_single_iface(const char *iface, pcap_t **pcap) +open_single_iface(const char *iface, pcap_t **pcap, uint32_t snaplen) { - if (open_iface_live(iface, pcap) < 0) { + if (open_iface_live(iface, pcap, snaplen) < 0) { PMD_LOG(ERR, "Couldn't open interface %s", iface); return -1; } @@ -614,7 +633,8 @@ open_single_iface(const char *iface, pcap_t **pcap) } static int -open_single_tx_pcap(const char *pcap_filename, pcap_dumper_t **dumper) +open_single_tx_pcap(const char *pcap_filename, pcap_dumper_t **dumper, + uint32_t snaplen) { pcap_t *tx_pcap; @@ -624,7 +644,7 @@ open_single_tx_pcap(const char *pcap_filename, pcap_dumper_t **dumper) * pcap holder. */ tx_pcap = pcap_open_dead_with_tstamp_precision(DLT_EN10MB, - RTE_ETH_PCAP_SNAPSHOT_LEN, PCAP_TSTAMP_PRECISION_NANO); + snaplen, PCAP_TSTAMP_PRECISION_NANO); if (tx_pcap == NULL) { PMD_LOG(ERR, "Couldn't create dead pcap"); return -1; @@ -633,9 +653,9 @@ open_single_tx_pcap(const char *pcap_filename, pcap_dumper_t **dumper) /* The dumper is created using the previous pcap_t reference */ *dumper = pcap_dump_open(tx_pcap, pcap_filename); if (*dumper == NULL) { + PMD_LOG(ERR, "Couldn't open %s for writing: %s", + pcap_filename, pcap_geterr(tx_pcap)); pcap_close(tx_pcap); - PMD_LOG(ERR, "Couldn't open %s for writing.", - pcap_filename); return -1; } @@ -685,6 +705,7 @@ eth_dev_start(struct rte_eth_dev *dev) struct pmd_process_private *pp = dev->process_private; struct pcap_tx_queue *tx; struct pcap_rx_queue *rx; + uint32_t snaplen = internals->snapshot_len; /* Special iface case. Single pcap is open and shared between tx/rx. */ if (internals->single_iface) { @@ -693,7 +714,7 @@ eth_dev_start(struct rte_eth_dev *dev) if (!pp->tx_pcap[0] && strcmp(tx->type, ETH_PCAP_IFACE_ARG) == 0) { - if (open_single_iface(tx->name, &pp->tx_pcap[0]) < 0) + if (open_single_iface(tx->name, &pp->tx_pcap[0], snaplen) < 0) return -1; pp->rx_pcap[0] = pp->tx_pcap[0]; } @@ -705,14 +726,11 @@ eth_dev_start(struct rte_eth_dev *dev) for (i = 0; i < dev->data->nb_tx_queues; i++) { tx = &internals->tx_queue[i]; - if (!pp->tx_dumper[i] && - strcmp(tx->type, ETH_PCAP_TX_PCAP_ARG) == 0) { - if (open_single_tx_pcap(tx->name, - &pp->tx_dumper[i]) < 0) + if (!pp->tx_dumper[i] && strcmp(tx->type, ETH_PCAP_TX_PCAP_ARG) == 0) { + if (open_single_tx_pcap(tx->name, &pp->tx_dumper[i], snaplen) < 0) return -1; - } else if (!pp->tx_pcap[i] && - strcmp(tx->type, ETH_PCAP_TX_IFACE_ARG) == 0) { - if (open_single_iface(tx->name, &pp->tx_pcap[i]) < 0) + } else if (!pp->tx_pcap[i] && strcmp(tx->type, ETH_PCAP_TX_IFACE_ARG) == 0) { + if (open_single_iface(tx->name, &pp->tx_pcap[i], snaplen) < 0) return -1; } } @@ -727,9 +745,14 @@ eth_dev_start(struct rte_eth_dev *dev) if (strcmp(rx->type, ETH_PCAP_RX_PCAP_ARG) == 0) { if (open_single_rx_pcap(rx->name, &pp->rx_pcap[i]) < 0) return -1; - } else if (strcmp(rx->type, ETH_PCAP_RX_IFACE_ARG) == 0) { - if (open_single_iface(rx->name, &pp->rx_pcap[i]) < 0) + } else if (strcmp(rx->type, ETH_PCAP_RX_IFACE_ARG) == 0 || + strcmp(rx->type, ETH_PCAP_RX_IFACE_IN_ARG) == 0) { + if (open_single_iface(rx->name, &pp->rx_pcap[i], snaplen) < 0) return -1; + /* Set direction for rx_iface_in */ + if (strcmp(rx->type, ETH_PCAP_RX_IFACE_IN_ARG) == 0) + set_iface_direction(rx->name, pp->rx_pcap[i], + PCAP_D_IN); } } @@ -820,11 +843,11 @@ eth_dev_info(struct rte_eth_dev *dev, dev_info->if_index = internals->if_index; dev_info->max_mac_addrs = 1; - dev_info->max_rx_pktlen = RTE_ETH_PCAP_SNAPSHOT_LEN; + dev_info->max_rx_pktlen = internals->snapshot_len; dev_info->max_rx_queues = dev->data->nb_rx_queues; dev_info->max_tx_queues = dev->data->nb_tx_queues; - dev_info->min_rx_bufsize = 0; - dev_info->max_mtu = RTE_ETH_PCAP_SNAPSHOT_LEN - RTE_ETHER_HDR_LEN; + dev_info->min_rx_bufsize = RTE_ETHER_MIN_LEN; + dev_info->max_mtu = internals->snapshot_len - RTE_ETHER_HDR_LEN; 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 | @@ -1124,7 +1147,7 @@ eth_tx_queue_setup(struct rte_eth_dev *dev, pcap_q->port_id = dev->data->port_id; pcap_q->queue_id = tx_queue_id; - pcap_q->bounce_buf = rte_malloc_socket(NULL, RTE_ETH_PCAP_SNAPSHOT_LEN, + pcap_q->bounce_buf = rte_malloc_socket(NULL, internals->snapshot_len, RTE_CACHE_LINE_SIZE, socket_id); if (pcap_q->bounce_buf == NULL) return -ENOMEM; @@ -1245,41 +1268,32 @@ open_rx_pcap(const char *key, const char *value, void *extra_args) } /* - * Opens a pcap file for writing and stores a reference to it - * for use it later on. + * Store TX pcap file configuration. + * The actual pcap dumper is opened in eth_dev_start(). */ static int open_tx_pcap(const char *key, const char *value, void *extra_args) { const char *pcap_filename = value; struct pmd_devargs *dumpers = extra_args; - pcap_dumper_t *dumper; - if (open_single_tx_pcap(pcap_filename, &dumper) < 0) + if (add_queue(dumpers, pcap_filename, key, NULL, NULL) < 0) return -1; - if (add_queue(dumpers, pcap_filename, key, NULL, dumper) < 0) { - pcap_dump_close(dumper); - return -1; - } - return 0; } /* - * Opens an interface for reading and writing + * Store interface configuration for reading and writing. + * The actual pcap handle is opened in eth_dev_start(). */ static inline int open_rx_tx_iface(const char *key, const char *value, void *extra_args) { const char *iface = value; struct pmd_devargs *tx = extra_args; - pcap_t *pcap = NULL; - - if (open_single_iface(iface, &pcap) < 0) - return -1; - tx->queue[0].pcap = pcap; + tx->queue[0].pcap = NULL; tx->queue[0].name = iface; tx->queue[0].type = key; @@ -1301,42 +1315,30 @@ set_iface_direction(const char *iface, pcap_t *pcap, return 0; } +/* + * Store interface configuration. + * The actual pcap handle is opened in eth_dev_start(). + */ static inline int open_iface(const char *key, const char *value, void *extra_args) { const char *iface = value; struct pmd_devargs *pmd = extra_args; - pcap_t *pcap = NULL; - if (open_single_iface(iface, &pcap) < 0) + if (add_queue(pmd, iface, key, NULL, NULL) < 0) return -1; - if (add_queue(pmd, iface, key, pcap, NULL) < 0) { - pcap_close(pcap); - return -1; - } return 0; } /* - * Opens a NIC for reading packets from it + * Store RX interface configuration. + * The actual pcap handle is opened and direction set in eth_dev_start(). */ static inline int open_rx_iface(const char *key, const char *value, void *extra_args) { - int ret = open_iface(key, value, extra_args); - if (ret < 0) - return ret; - if (strcmp(key, ETH_PCAP_RX_IFACE_IN_ARG) == 0) { - struct pmd_devargs *pmd = extra_args; - unsigned int qid = pmd->num_of_queue - 1; - - set_iface_direction(pmd->queue[qid].name, - pmd->queue[qid].pcap, - PCAP_D_IN); - } - - return 0; + return open_iface(key, value, extra_args); } static inline int @@ -1376,6 +1378,30 @@ process_bool_flag(const char *key, const char *value, void *extra_args) return 0; } +static int +process_snapshot_len(const char *key, const char *value, void *extra_args) +{ + uint32_t *snaplen = extra_args; + unsigned long val; + char *endptr; + + if (value == NULL || *value == '\0') { + PMD_LOG(ERR, "Argument '%s' requires a value", key); + return -1; + } + + errno = 0; + val = strtoul(value, &endptr, 10); + if (errno != 0 || *endptr != '\0' || + val < RTE_ETHER_HDR_LEN || val > UINT32_MAX) { + PMD_LOG(ERR, "Invalid '%s' value '%s'", key, value); + return -1; + } + + *snaplen = (uint32_t)val; + return 0; +} + static int pmd_init_internals(struct rte_vdev_device *vdev, const unsigned int nb_rx_queues, @@ -1540,6 +1566,8 @@ eth_from_pcaps(struct rte_vdev_device *vdev, } internals->infinite_rx = infinite_rx; + internals->snapshot_len = devargs_all->snapshot_len; + /* Assign rx ops. */ if (infinite_rx) eth_dev->rx_pkt_burst = eth_pcap_rx_infinite; @@ -1600,6 +1628,7 @@ pmd_pcap_probe(struct rte_vdev_device *dev) int ret = 0; struct pmd_devargs_all devargs_all = { + .snapshot_len = ETH_PCAP_SNAPSHOT_LEN_DEFAULT, .single_iface = 0, .is_tx_pcap = 0, .is_tx_iface = 0, @@ -1641,6 +1670,17 @@ pmd_pcap_probe(struct rte_vdev_device *dev) return -1; } + /* + * Process optional snapshot length argument. + */ + if (rte_kvargs_count(kvlist, ETH_PCAP_SNAPSHOT_LEN_ARG) == 1) { + ret = rte_kvargs_process(kvlist, ETH_PCAP_SNAPSHOT_LEN_ARG, + &process_snapshot_len, + &devargs_all.snapshot_len); + if (ret < 0) + goto free_kvlist; + } + /* * If iface argument is passed we open the NICs and use them for * reading / writing @@ -1847,4 +1887,5 @@ RTE_PMD_REGISTER_PARAM_STRING(net_pcap, ETH_PCAP_TX_IFACE_ARG "=<ifc> " ETH_PCAP_IFACE_ARG "=<ifc> " ETH_PCAP_PHY_MAC_ARG "=<0|1> " - ETH_PCAP_INFINITE_RX_ARG "=<0|1>"); + ETH_PCAP_INFINITE_RX_ARG "=<0|1> " + ETH_PCAP_SNAPSHOT_LEN_ARG "=<int>"); -- 2.51.0
