To support shared Rx queue, this patch introduces dedicate forwarding
engine. The engine groups received packets by mbuf->port into sub-group,
updates stream statistics and simply frees packets.
Signed-off-by: Xueming Li <xuemingl@nvidia.com>
---
app/test-pmd/meson.build | 1 +
app/test-pmd/shared_rxq_fwd.c | 115 ++++++++++++++++++++
app/test-pmd/testpmd.c | 1 +
app/test-pmd/testpmd.h | 1 +
doc/guides/testpmd_app_ug/run_app.rst | 5 +-
doc/guides/testpmd_app_ug/testpmd_funcs.rst | 5 +-
6 files changed, 126 insertions(+), 2 deletions(-)
create mode 100644 app/test-pmd/shared_rxq_fwd.c
@@ -22,6 +22,7 @@ sources = files(
'noisy_vnf.c',
'parameters.c',
'rxonly.c',
+ 'shared_rxq_fwd.c',
'testpmd.c',
'txonly.c',
'util.c',
new file mode 100644
@@ -0,0 +1,115 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright (c) 2021 NVIDIA Corporation & Affiliates
+ */
+
+#include <rte_ethdev.h>
+
+#include "testpmd.h"
+
+/*
+ * Rx only sub-burst forwarding.
+ */
+static void
+forward_rx_only(uint16_t nb_rx, struct rte_mbuf **pkts_burst)
+{
+ rte_pktmbuf_free_bulk(pkts_burst, nb_rx);
+}
+
+/**
+ * Get packet source stream by source port and queue.
+ * All streams of same shared Rx queue locates on same core.
+ */
+static struct fwd_stream *
+forward_stream_get(struct fwd_stream *fs, uint16_t port)
+{
+ streamid_t sm_id;
+ struct fwd_lcore *fc;
+ struct fwd_stream **fsm;
+ streamid_t nb_fs;
+
+ fc = fs->lcore;
+ fsm = &fwd_streams[fc->stream_idx];
+ nb_fs = fc->stream_nb;
+ for (sm_id = 0; sm_id < nb_fs; sm_id++) {
+ if (fsm[sm_id]->rx_port == port &&
+ fsm[sm_id]->rx_queue == fs->rx_queue)
+ return fsm[sm_id];
+ }
+ return NULL;
+}
+
+/**
+ * Forward packet by source port and queue.
+ */
+static void
+forward_sub_burst(struct fwd_stream *src_fs, uint16_t port, uint16_t nb_rx,
+ struct rte_mbuf **pkts)
+{
+ struct fwd_stream *fs = forward_stream_get(src_fs, port);
+
+ if (fs != NULL) {
+ fs->rx_packets += nb_rx;
+ forward_rx_only(nb_rx, pkts);
+ } else {
+ /* Source stream not found, drop all packets. */
+ src_fs->fwd_dropped += nb_rx;
+ while (nb_rx > 0)
+ rte_pktmbuf_free(pkts[--nb_rx]);
+ }
+}
+
+/**
+ * Forward packets from shared Rx queue.
+ *
+ * Source port of packets are identified by mbuf->port.
+ */
+static void
+forward_shared_rxq(struct fwd_stream *fs, uint16_t nb_rx,
+ struct rte_mbuf **pkts_burst)
+{
+ uint16_t i, nb_sub_burst, port, last_port;
+
+ nb_sub_burst = 0;
+ last_port = pkts_burst[0]->port;
+ /* Locate sub-burst according to mbuf->port. */
+ for (i = 0; i < nb_rx - 1; ++i) {
+ rte_prefetch0(pkts_burst[i + 1]);
+ port = pkts_burst[i]->port;
+ if (i > 0 && last_port != port) {
+ /* Forward packets with same source port. */
+ forward_sub_burst(fs, last_port, nb_sub_burst,
+ &pkts_burst[i - nb_sub_burst]);
+ nb_sub_burst = 0;
+ last_port = port;
+ }
+ nb_sub_burst++;
+ }
+ /* Last sub-burst. */
+ nb_sub_burst++;
+ forward_sub_burst(fs, last_port, nb_sub_burst,
+ &pkts_burst[nb_rx - nb_sub_burst]);
+}
+
+static void
+shared_rxq_fwd(struct fwd_stream *fs)
+{
+ struct rte_mbuf *pkts_burst[nb_pkt_per_burst];
+ uint16_t nb_rx;
+ uint64_t start_tsc = 0;
+
+ get_start_cycles(&start_tsc);
+ nb_rx = rte_eth_rx_burst(fs->rx_port, fs->rx_queue, pkts_burst,
+ nb_pkt_per_burst);
+ inc_rx_burst_stats(fs, nb_rx);
+ if (unlikely(nb_rx == 0))
+ return;
+ forward_shared_rxq(fs, nb_rx, pkts_burst);
+ get_end_cycles(fs, start_tsc);
+}
+
+struct fwd_engine shared_rxq_engine = {
+ .fwd_mode_name = "shared_rxq",
+ .port_fwd_begin = NULL,
+ .port_fwd_end = NULL,
+ .packet_fwd = shared_rxq_fwd,
+};
@@ -188,6 +188,7 @@ struct fwd_engine * fwd_engines[] = {
#ifdef RTE_LIBRTE_IEEE1588
&ieee1588_fwd_engine,
#endif
+ &shared_rxq_engine,
NULL,
};
@@ -339,6 +339,7 @@ extern struct fwd_engine five_tuple_swap_fwd_engine;
#ifdef RTE_LIBRTE_IEEE1588
extern struct fwd_engine ieee1588_fwd_engine;
#endif
+extern struct fwd_engine shared_rxq_engine;
extern struct fwd_engine * fwd_engines[]; /**< NULL terminated array. */
extern cmdline_parse_inst_t cmd_set_raw;
@@ -258,6 +258,7 @@ The command line options are:
tm
noisy
5tswap
+ shared-rxq
* ``--rss-ip``
@@ -399,7 +400,9 @@ The command line options are:
Create queues in shared Rx queue mode if device supports.
Shared Rx queues are grouped per X ports. X defaults to UINT32_MAX,
- implies all ports join share group 1.
+ implies all ports join share group 1. Forwarding engine "shared-rxq"
+ should be used for shared Rx queues. This engine does Rx only and
+ update stream statistics accordingly.
* ``--eth-link-speed``
@@ -314,7 +314,7 @@ set fwd
Set the packet forwarding mode::
testpmd> set fwd (io|mac|macswap|flowgen| \
- rxonly|txonly|csum|icmpecho|noisy|5tswap) (""|retry)
+ rxonly|txonly|csum|icmpecho|noisy|5tswap|shared-rxq) (""|retry)
``retry`` can be specified for forwarding engines except ``rx_only``.
@@ -357,6 +357,9 @@ The available information categories are:
L4 swaps the source port and destination port of transport layer (TCP and UDP).
+* ``shared-rxq``: Receive only for shared Rx queue.
+ Resolve packet source port from mbuf and update stream statistics accordingly.
+
Example::
testpmd> set fwd rxonly