By default, AF_PACKET delivers both incoming and outgoing packets. This might surprise applications that expect rte_eth_rx_burst() to return only incoming traffic.
This patch adds the devarg ignore_outgoing=<0|1> to enable PACKET_IGNORE_OUTGOING. When set, the kernel drops outgoing frames. The default is 0 to keep the existing behavior. Signed-off-by: Frank Dressler <[email protected]> --- v3: - drop #ifdef PACKET_IGNORE_OUTGOING (uapi since 4.20; DPDK requires kernel >= 5.4) - fail the test if ignore_outgoing=1 cannot create a port - drop kernel >= 4.20 notes from docs and release notes v2: - use PACKET_IGNORE_OUTGOING / ignore_outgoing= instead of capture_dir --- .mailmap | 1 + app/test/test_pmd_af_packet.c | 97 +++++++++++++++++++++++ doc/guides/nics/af_packet.rst | 3 + doc/guides/rel_notes/release_26_11.rst | 6 ++ drivers/net/af_packet/rte_eth_af_packet.c | 25 +++++- 5 files changed, 131 insertions(+), 1 deletion(-) diff --git a/.mailmap b/.mailmap index 2e348c3bce..a04fc553d4 100644 --- a/.mailmap +++ b/.mailmap @@ -505,6 +505,7 @@ Francis Kelly <[email protected]> <[email protected]> Francis Racicot <[email protected]> Franck Lenormand <[email protected]> François-Frédéric Ozog <[email protected]> +Frank Dressler <[email protected]> Frank Du <[email protected]> Frank Zhao <[email protected]> Frederico Cadete <[email protected]> diff --git a/app/test/test_pmd_af_packet.c b/app/test/test_pmd_af_packet.c index b668ca5b81..1ed1de8c02 100644 --- a/app/test/test_pmd_af_packet.c +++ b/app/test/test_pmd_af_packet.c @@ -913,6 +913,102 @@ test_af_packet_qdisc_bypass(void) return TEST_SUCCESS; } +/* + * Test: Ignore outgoing packets configuration + * TX on the TAP with qdisc_bypass=0 produces PACKET_OUTGOING frames. + * A peer with ignore_outgoing=0 should see them; ignore_outgoing=1 must not. + */ +static int +test_af_packet_ignore_outgoing(void) +{ + struct rte_mbuf *bufs[BURST_SIZE]; + uint16_t tx_port, rx_port_ign_out_off, rx_port_ign_out_on, nb_tx; + unsigned int rx_off = 0, rx_on = 0, allocated; + uint64_t elapsed = 0; + const char *err = NULL; + int ret; + + if (!tap_created) { + printf("SKIPPED: TAP interface not available (need root)\n"); + return TEST_SKIPPED; + } + + ret = create_af_packet_port("net_af_packet_ign_on", + "iface=" TAP_DEV_NAME ",ignore_outgoing=1", + &rx_port_ign_out_on); + if (ret != 0) { + err = "Failed to create ignore_outgoing=1 port"; + goto fail_rx_ign_on; + } + + ret = create_af_packet_port("net_af_packet_ign_off", + "iface=" TAP_DEV_NAME ",ignore_outgoing=0", + &rx_port_ign_out_off); + if (ret != 0) { + err = "Failed to create ignore_outgoing=0 port"; + goto fail_rx_ign_off; + } + + /* qdisc_bypass=0 so the kernel TX tap sees the TX packets */ + ret = create_af_packet_port("net_af_packet_ign_tx", + "iface=" TAP_DEV_NAME ",qdisc_bypass=0", &tx_port); + if (ret != 0) { + err = "Failed to create TX af_packet port"; + goto fail_tx; + } + + if (configure_af_packet_port(rx_port_ign_out_on, 1, 1) != 0 || + configure_af_packet_port(rx_port_ign_out_off, 1, 1) != 0 || + configure_af_packet_port(tx_port, 1, 1) != 0) { + err = "Failed to configure ports"; + goto fail_setup; + } + + while (do_rx_burst(rx_port_ign_out_off, 0, bufs, BURST_SIZE) > 0) + ; + while (do_rx_burst(rx_port_ign_out_on, 0, bufs, BURST_SIZE) > 0) + ; + + allocated = alloc_tx_mbufs(bufs, 4); + nb_tx = do_tx_burst(tx_port, 0, bufs, allocated); + if (allocated == 0 || nb_tx == 0) { + err = "TX setup failed"; + goto fail_setup; + } + + while (elapsed < LOOPBACK_TIMEOUT_US) { + rx_off += do_rx_burst(rx_port_ign_out_off, 0, bufs, BURST_SIZE); + rx_on += do_rx_burst(rx_port_ign_out_on, 0, bufs, BURST_SIZE); + if (rx_off >= nb_tx) + break; + rte_delay_us_block(STATS_POLL_INTERVAL_US); + elapsed += STATS_POLL_INTERVAL_US; + } + +fail_setup: + rte_eth_dev_stop(tx_port); + rte_eth_dev_close(tx_port); + rte_vdev_uninit("net_af_packet_ign_tx"); +fail_tx: + rte_eth_dev_stop(rx_port_ign_out_off); + rte_eth_dev_close(rx_port_ign_out_off); + rte_vdev_uninit("net_af_packet_ign_off"); +fail_rx_ign_off: + rte_eth_dev_stop(rx_port_ign_out_on); + rte_eth_dev_close(rx_port_ign_out_on); + rte_vdev_uninit("net_af_packet_ign_on"); +fail_rx_ign_on: + TEST_ASSERT(err == NULL, "%s", err); + TEST_ASSERT(rx_off > 0, "Expected packets with ignore_outgoing=0"); + TEST_ASSERT(rx_on == 0, "Expected no packets with ignore_outgoing=1"); + + ret = rte_vdev_init("net_af_packet_ign_bad", + "iface=" TAP_DEV_NAME ",ignore_outgoing=2"); + TEST_ASSERT(ret != 0, "Expected failure with ignore_outgoing=2"); + + return TEST_SUCCESS; +} + /* * Test: Multiple queue pairs */ @@ -1107,6 +1203,7 @@ static struct unit_test_suite af_packet_test_suite = { TEST_CASE(test_af_packet_invalid_qpairs), TEST_CASE(test_af_packet_frame_config), TEST_CASE(test_af_packet_qdisc_bypass), + TEST_CASE(test_af_packet_ignore_outgoing), TEST_CASE(test_af_packet_multi_queue), TEST_CASES_END() /**< NULL terminate unit test array */ diff --git a/doc/guides/nics/af_packet.rst b/doc/guides/nics/af_packet.rst index 1505b98ff7..11c9def583 100644 --- a/doc/guides/nics/af_packet.rst +++ b/doc/guides/nics/af_packet.rst @@ -25,6 +25,9 @@ Some of these, in turn, will be used to configure the PACKET_MMAP settings. disabled by default); * ``fanout_mode`` - set fanout algorithm. Possible choices: hash, lb, cpu, rollover, rnd, qm (optional, default hash); +* ``ignore_outgoing`` - set PACKET_IGNORE_OUTGOING so the socket does not + receive packets transmitted by the host on the same interface (optional, + default 0); * ``blocksz`` - PACKET_MMAP block size (optional, default 4096); * ``framesz`` - PACKET_MMAP frame size (optional, default 2048B; Note: multiple of 16B); diff --git a/doc/guides/rel_notes/release_26_11.rst b/doc/guides/rel_notes/release_26_11.rst index 030bd84cea..13598e1272 100644 --- a/doc/guides/rel_notes/release_26_11.rst +++ b/doc/guides/rel_notes/release_26_11.rst @@ -64,6 +64,12 @@ New Features Added ``rte_vlan_insert_tpid()`` to the net library. +* **Updated AF_PACKET driver.** + + Added ``ignore_outgoing`` vdev argument to enable ``PACKET_IGNORE_OUTGOING``, + so the PMD does not receive packets transmitted by the host on the same + interface. + * **Updated AF_XDP driver.** * Changed the default device plugin endpoint path used when diff --git a/drivers/net/af_packet/rte_eth_af_packet.c b/drivers/net/af_packet/rte_eth_af_packet.c index a93df97023..66400073a7 100644 --- a/drivers/net/af_packet/rte_eth_af_packet.c +++ b/drivers/net/af_packet/rte_eth_af_packet.c @@ -39,6 +39,7 @@ #define ETH_AF_PACKET_FRAMECOUNT_ARG "framecnt" #define ETH_AF_PACKET_QDISC_BYPASS_ARG "qdisc_bypass" #define ETH_AF_PACKET_FANOUT_MODE_ARG "fanout_mode" +#define ETH_AF_PACKET_IGNORE_OUTGOING_ARG "ignore_outgoing" #define DFLT_FRAME_SIZE (1 << 11) #define DFLT_FRAME_COUNT (1 << 9) @@ -103,6 +104,7 @@ static const char *valid_arguments[] = { ETH_AF_PACKET_FRAMECOUNT_ARG, ETH_AF_PACKET_QDISC_BYPASS_ARG, ETH_AF_PACKET_FANOUT_MODE_ARG, + ETH_AF_PACKET_IGNORE_OUTGOING_ARG, NULL }; @@ -877,6 +879,7 @@ rte_pmd_init_internals(struct rte_vdev_device *dev, unsigned int framecnt, unsigned int qdisc_bypass, const char *fanout_mode, + unsigned int ignore_outgoing, struct pmd_internals **internals, struct rte_eth_dev **eth_dev, struct rte_kvargs *kvlist) @@ -1025,6 +1028,17 @@ rte_pmd_init_internals(struct rte_vdev_device *dev, #endif } + if (ignore_outgoing) { + rc = setsockopt(qsockfd, SOL_PACKET, PACKET_IGNORE_OUTGOING, + &ignore_outgoing, sizeof(ignore_outgoing)); + if (rc == -1) { + PMD_LOG_ERRNO(ERR, + "%s: could not set PACKET_IGNORE_OUTGOING on AF_PACKET socket for %s", + name, pair->value); + goto error; + } + } + rc = setsockopt(qsockfd, SOL_PACKET, PACKET_RX_RING, req, sizeof(*req)); if (rc == -1) { PMD_LOG_ERRNO(ERR, @@ -1206,6 +1220,7 @@ rte_eth_from_packet(struct rte_vdev_device *dev, unsigned int qpairs = 1; unsigned int qdisc_bypass = 1; const char *fanout_mode = NULL; + unsigned int ignore_outgoing = 0; /* do some parameter checking */ if (*sockfd < 0) @@ -1272,6 +1287,11 @@ rte_eth_from_packet(struct rte_vdev_device *dev, fanout_mode = pair->value; continue; } + if (strstr(pair->key, ETH_AF_PACKET_IGNORE_OUTGOING_ARG) != NULL) { + if (parse_uint(pair->key, pair->value, &ignore_outgoing, 1) < 0) + return -1; + continue; + } } if (framesize > blocksize) { @@ -1298,12 +1318,14 @@ rte_eth_from_packet(struct rte_vdev_device *dev, PMD_LOG(DEBUG, "%s:\tfanout mode %s", name, fanout_mode); else PMD_LOG(DEBUG, "%s:\tfanout mode %s", name, "default PACKET_FANOUT_HASH"); + PMD_LOG(DEBUG, "%s:\tignore outgoing %d", name, ignore_outgoing); if (rte_pmd_init_internals(dev, *sockfd, qpairs, blocksize, blockcount, framesize, framecount, qdisc_bypass, fanout_mode, + ignore_outgoing, &internals, ð_dev, kvlist) < 0) return -1; @@ -1401,4 +1423,5 @@ RTE_PMD_REGISTER_PARAM_STRING(net_af_packet, "framesz=<int> " "framecnt=<int> " "qdisc_bypass=<0|1> " - "fanout_mode=<hash|lb|cpu|rollover|rnd|qm>"); + "fanout_mode=<hash|lb|cpu|rollover|rnd|qm> " + "ignore_outgoing=<0|1>"); -- 2.56.0
