[dpdk-dev] [PATCH 19.08] net/pcap: enable infinitely rxing a pcap file

[Cian Ferriter]

It can be useful to use pcap files for some rudimental performance
testing. This patch enables this functionality in the pcap driver.

At a high level, this works by creaing a ring of sufficient size to
store the packets in the pcap file passed to the application. When the
rx function for this mode is called, packets are dequeued from the ring
for use by the application and also enqueued back on to the ring to be
"received" again.

A tx_drop mode is also added since transmitting to a tx_pcap file isn't
desirable at a high traffic rate.

Jumbo frames are not supported in this mode. When filling the ring at rx
queue setup time, the presence of multi segment mbufs is checked for.
The PMD will exit on detection of these multi segment mbufs.

Signed-off-by: Cian Ferriter <cian.ferriter at intel.com>
---
 doc/guides/nics/pcap_ring.rst   |  15 +++
 drivers/net/pcap/rte_eth_pcap.c | 209 ++++++++++++++++++++++++++++++--
 2 files changed, 215 insertions(+), 9 deletions(-)

diff --git a/doc/guides/nics/pcap_ring.rst b/doc/guides/nics/pcap_ring.rst
index c1ef9196b..45f55a345 100644
--- a/doc/guides/nics/pcap_ring.rst
+++ b/doc/guides/nics/pcap_ring.rst
@@ -106,6 +106,21 @@ Runtime Config Options
 
    --vdev 'net_pcap0,iface=eth0,phy_mac=1'
 
+- Use the RX PCAP file to infinitely receive packets
+
+ In case ``rx_pcap=`` configuration is set, user may want to use the selected PCAP file for rudimental
+ performance testing. This can be done with a ``devarg`` ``infinite_rx``, for example::
+
+   --vdev 'net_pcap0,rx_pcap=file_rx.pcap,infinite_rx=1,tx_drop=1'
+
+ When this mode is used, it is recommended to use the ``tx_drop`` ``devarg``.
+
+- Drop all packets on transmit
+
+ The user may want to drop all packets on tx for a device. This can be done with the ``tx_drop`` ``devarg``, for example::
+
+   --vdev 'net_pcap0,rx_pcap=file_rx.pcap,tx_drop=1'
+
 Examples of Usage
 ^^^^^^^^^^^^^^^^^
 
diff --git a/drivers/net/pcap/rte_eth_pcap.c b/drivers/net/pcap/rte_eth_pcap.c
index 353538f16..b72db973a 100644
--- a/drivers/net/pcap/rte_eth_pcap.c
+++ b/drivers/net/pcap/rte_eth_pcap.c
@@ -39,6 +39,8 @@
 #define ETH_PCAP_TX_IFACE_ARG "tx_iface"
 #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_TX_DROP_ARG  "tx_drop"
 
 #define ETH_PCAP_ARG_MAXLEN	64
 
@@ -64,6 +66,9 @@ struct pcap_rx_queue {
 	struct queue_stat rx_stat;
 	char name[PATH_MAX];
 	char type[ETH_PCAP_ARG_MAXLEN];
+
+	/* Contains pre-generated packets, to be looped through */
+	struct rte_ring *pkts;
 };
 
 struct pcap_tx_queue {
@@ -82,6 +87,7 @@ struct pmd_internals {
 	int if_index;
 	int single_iface;
 	int phy_mac;
+	int infinite_rx;
 };
 
 struct pmd_process_private {
@@ -109,6 +115,8 @@ static const char *valid_arguments[] = {
 	ETH_PCAP_TX_IFACE_ARG,
 	ETH_PCAP_IFACE_ARG,
 	ETH_PCAP_PHY_MAC_ARG,
+	ETH_PCAP_INFINITE_RX_ARG,
+	ETH_PCAP_TX_DROP_ARG,
 	NULL
 };
 
@@ -178,6 +186,40 @@ eth_pcap_gather_data(unsigned char *data, struct rte_mbuf *mbuf)
 	}
 }
 
+static uint16_t
+eth_pcap_rx_infinite(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts)
+{
+	int i;
+	struct pcap_rx_queue *pcap_q = queue;
+
+	if (unlikely(nb_pkts == 0))
+		return 0;
+
+	if (rte_pktmbuf_alloc_bulk(pcap_q->mb_pool, bufs, nb_pkts) != 0)
+		return 0;
+
+	for (i = 0; i < nb_pkts; i++) {
+		struct rte_mbuf *pcap_buf;
+		int err = rte_ring_dequeue(pcap_q->pkts, (void **)&pcap_buf);
+		if (err)
+			rte_panic("failed to dequeue from pcap pkts ring\n");
+
+		rte_memcpy(rte_pktmbuf_mtod(bufs[i], void *),
+				rte_pktmbuf_mtod(pcap_buf, void *),
+				pcap_buf->data_len);
+		bufs[i]->data_len = pcap_buf->data_len;
+		bufs[i]->pkt_len = pcap_buf->pkt_len;
+		bufs[i]->port = pcap_q->port_id;
+
+		/* enqueue packet back on ring to allow infinite rx */
+		rte_ring_enqueue(pcap_q->pkts, pcap_buf);
+	}
+
+	pcap_q->rx_stat.pkts += i;
+
+	return i;
+}
+
 static uint16_t
 eth_pcap_rx(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts)
 {
@@ -320,6 +362,26 @@ eth_pcap_tx_dumper(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts)
 	return num_tx;
 }
 
+/*
+ * Callback to handle dropping packets in the infinite rx case.
+ */
+static uint16_t
+eth_tx_drop(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts)
+{
+	unsigned int i;
+	struct pcap_tx_queue *tx_queue = queue;
+
+	if (unlikely(nb_pkts == 0))
+		return 0;
+
+	for (i = 0; i < nb_pkts; i++)
+		rte_pktmbuf_free(bufs[i]);
+
+	tx_queue->tx_stat.pkts += nb_pkts;
+
+	return i;
+}
+
 /*
  * Callback to handle sending packets through a real NIC.
  */
@@ -447,6 +509,24 @@ open_single_rx_pcap(const char *pcap_filename, pcap_t **pcap)
 	return 0;
 }
 
+static uint64_t
+count_packets_in_pcaps(pcap_t **pcap, struct pcap_rx_queue *pcap_q)
+{
+	const u_char *packet;
+	struct pcap_pkthdr header;
+	uint64_t pcap_pkt_count;
+
+	while ((packet = pcap_next(*pcap, &header)))
+		pcap_pkt_count++;
+
+	/* the pcap is reopened so it can be used as normal later */
+	pcap_close(*pcap);
+	*pcap = NULL;
+	open_single_rx_pcap(pcap_q->name, pcap);
+
+	return pcap_pkt_count;
+}
+
 static int
 eth_dev_start(struct rte_eth_dev *dev)
 {
@@ -663,6 +743,7 @@ eth_rx_queue_setup(struct rte_eth_dev *dev,
 		const struct rte_eth_rxconf *rx_conf __rte_unused,
 		struct rte_mempool *mb_pool)
 {
+	unsigned int i;
 	struct pmd_internals *internals = dev->data->dev_private;
 	struct pcap_rx_queue *pcap_q = &internals->rx_queue[rx_queue_id];
 
@@ -671,6 +752,49 @@ eth_rx_queue_setup(struct rte_eth_dev *dev,
 	pcap_q->queue_id = rx_queue_id;
 	dev->data->rx_queues[rx_queue_id] = pcap_q;
 
+	if (internals->infinite_rx) {
+		struct pmd_process_private *pp;
+		char ring_name[NAME_MAX];
+		uint16_t num_rx = 0;
+		static uint32_t ring_number;
+		uint64_t pcap_pkt_count = 0;
+		pcap_t **pcap;
+
+		pp = rte_eth_devices[pcap_q->port_id].process_private;
+		pcap = &pp->rx_pcap[pcap_q->queue_id];
+
+		if (unlikely(*pcap == NULL))
+			rte_panic("no packets in pcap to fill ring with\n");
+
+		pcap_pkt_count = count_packets_in_pcaps(pcap, pcap_q);
+
+		snprintf(ring_name, sizeof(ring_name), "PCAP_RING%" PRIu16,
+				ring_number);
+
+		pcap_q->pkts = rte_ring_create(ring_name,
+				rte_align64pow2(pcap_pkt_count + 1), 0,
+				RING_F_SP_ENQ | RING_F_SC_DEQ);
+		ring_number++;
+		if (!pcap_q->pkts)
+			rte_panic("failed to alloc ring\n");
+
+
+		struct rte_mbuf *bufs[pcap_pkt_count];
+		if (rte_pktmbuf_alloc_bulk(mb_pool, bufs, pcap_pkt_count) != 0)
+			return 0;
+
+		num_rx = eth_pcap_rx(pcap_q, bufs, pcap_pkt_count);
+
+		/* check for multiseg mbufs */
+		for (i = 0; i < num_rx; i++) {
+			if (bufs[i]->nb_segs != 1)
+				rte_panic("jumbo frames are not supported in infinite rx mode\n");
+		}
+
+		rte_ring_enqueue_bulk(pcap_q->pkts, (void * const *)bufs,
+				num_rx, NULL);
+	}
+
 	return 0;
 }
 
@@ -908,6 +1032,34 @@ select_phy_mac(const char *key __rte_unused, const char *value,
 	return 0;
 }
 
+static int
+get_infinite_rx_arg(const char *key __rte_unused,
+		const char *value, void *extra_args)
+{
+	if (extra_args) {
+		const int infinite_rx = atoi(value);
+		int *enable_infinite_rx = extra_args;
+
+		if (infinite_rx)
+			*enable_infinite_rx = 1;
+	}
+	return 0;
+}
+
+static int
+get_tx_drop_arg(const char *key __rte_unused,
+		const char *value, void *extra_args)
+{
+	if (extra_args) {
+		const int tx_drop = atoi(value);
+		int *enable_tx_drop = extra_args;
+
+		if (tx_drop)
+			*enable_tx_drop = 1;
+	}
+	return 0;
+}
+
 static struct rte_vdev_driver pmd_pcap_drv;
 
 static int
@@ -1105,7 +1257,8 @@ static int
 eth_from_pcaps(struct rte_vdev_device *vdev,
 		struct pmd_devargs *rx_queues, const unsigned int nb_rx_queues,
 		struct pmd_devargs *tx_queues, const unsigned int nb_tx_queues,
-		int single_iface, unsigned int using_dumpers)
+		int single_iface, unsigned int using_dumpers,
+		unsigned int infinite_rx)
 {
 	struct pmd_internals *internals = NULL;
 	struct rte_eth_dev *eth_dev = NULL;
@@ -1132,9 +1285,18 @@ eth_from_pcaps(struct rte_vdev_device *vdev,
 		}
 	}
 
-	eth_dev->rx_pkt_burst = eth_pcap_rx;
+	/* assign rx ops */
+	if (infinite_rx) {
+		eth_dev->rx_pkt_burst = eth_pcap_rx_infinite;
+		internals->infinite_rx = infinite_rx;
+	} else {
+		eth_dev->rx_pkt_burst = eth_pcap_rx;
+	}
 
-	if (using_dumpers)
+	/* assign tx ops */
+	if (infinite_rx)
+		eth_dev->tx_pkt_burst = eth_tx_drop;
+	else if (using_dumpers)
 		eth_dev->tx_pkt_burst = eth_pcap_tx_dumper;
 	else
 		eth_dev->tx_pkt_burst = eth_pcap_tx;
@@ -1148,6 +1310,7 @@ pmd_pcap_probe(struct rte_vdev_device *dev)
 {
 	const char *name;
 	unsigned int is_rx_pcap = 0, is_tx_pcap = 0;
+	unsigned int infinite_rx = 0, tx_drop = 0;
 	struct rte_kvargs *kvlist;
 	struct pmd_devargs pcaps = {0};
 	struct pmd_devargs dumpers = {0};
@@ -1217,6 +1380,17 @@ pmd_pcap_probe(struct rte_vdev_device *dev)
 	pcaps.num_of_queue = 0;
 
 	if (is_rx_pcap) {
+		/*
+		 * We check whether we want to infinitely rx the pcap file
+		 */
+		if (rte_kvargs_count(kvlist, ETH_PCAP_INFINITE_RX_ARG) == 1) {
+			ret = rte_kvargs_process(kvlist,
+					ETH_PCAP_INFINITE_RX_ARG,
+					&get_infinite_rx_arg, &infinite_rx);
+			if (ret < 0)
+				goto free_kvlist;
+		}
+
 		ret = rte_kvargs_process(kvlist, ETH_PCAP_RX_PCAP_ARG,
 				&open_rx_pcap, &pcaps);
 	} else {
@@ -1228,18 +1402,30 @@ pmd_pcap_probe(struct rte_vdev_device *dev)
 		goto free_kvlist;
 
 	/*
-	 * We check whether we want to open a TX stream to a real NIC or a
-	 * pcap file
+	 * We check whether we want to open a TX stream to a real NIC,
+	 * a pcap file, or drop packets on tx
 	 */
 	is_tx_pcap = rte_kvargs_count(kvlist, ETH_PCAP_TX_PCAP_ARG) ? 1 : 0;
 	dumpers.num_of_queue = 0;
 
-	if (is_tx_pcap)
+	tx_drop = rte_kvargs_count(kvlist, ETH_PCAP_TX_DROP_ARG) ? 1 : 0;
+	if (rte_kvargs_count(kvlist, ETH_PCAP_TX_DROP_ARG) == 1) {
+		ret = rte_kvargs_process(kvlist, ETH_PCAP_TX_DROP_ARG,
+				&get_tx_drop_arg, &tx_drop);
+		if (ret < 0)
+			goto free_kvlist;
+	}
+
+	if (tx_drop) {
+		/* add dummy queue which counts dropped packets */
+		ret = add_queue(&dumpers, "dummy", "tx_drop", NULL, NULL);
+	} else if (is_tx_pcap) {
 		ret = rte_kvargs_process(kvlist, ETH_PCAP_TX_PCAP_ARG,
 				&open_tx_pcap, &dumpers);
-	else
+	} else {
 		ret = rte_kvargs_process(kvlist, ETH_PCAP_TX_IFACE_ARG,
 				&open_tx_iface, &dumpers);
+	}
 
 	if (ret < 0)
 		goto free_kvlist;
@@ -1285,8 +1471,11 @@ pmd_pcap_probe(struct rte_vdev_device *dev)
 		goto free_kvlist;
 	}
 
+	PMD_LOG(INFO, "Configure pmd_pcap: infinite_rx is %s",
+			infinite_rx ? "enabled" : "disabled");
+
 	ret = eth_from_pcaps(dev, &pcaps, pcaps.num_of_queue, &dumpers,
-		dumpers.num_of_queue, single_iface, is_tx_pcap);
+		dumpers.num_of_queue, single_iface, is_tx_pcap, infinite_rx);
 
 free_kvlist:
 	rte_kvargs_free(kvlist);
@@ -1338,7 +1527,9 @@ RTE_PMD_REGISTER_PARAM_STRING(net_pcap,
 	ETH_PCAP_RX_IFACE_IN_ARG "=<ifc> "
 	ETH_PCAP_TX_IFACE_ARG "=<ifc> "
 	ETH_PCAP_IFACE_ARG "=<ifc> "
-	ETH_PCAP_PHY_MAC_ARG "=<int>");
+	ETH_PCAP_PHY_MAC_ARG "=<int>"
+	ETH_PCAP_INFINITE_RX_ARG "=<int>"
+	ETH_PCAP_TX_DROP_ARG "=<int>");
 
 RTE_INIT(eth_pcap_init_log)
 {
-- 
2.17.1