[PATCH v3 37/50] net/ntnic: add basic queue operations

[Serhii Iliushyk <sil-plv@napatech.com>]

From: Danylo Vodopianov <dvo-plv@napatech.com>

Adds support for queue configure, start, stop, release.
The internal macro and functions of ntnic were also added and
initialized.

Signed-off-by: Danylo Vodopianov <dvo-plv@napatech.com>
---
v3
* Remove newline characters from logs.
---
 doc/guides/nics/features/ntnic.ini   |   1 +
 drivers/net/ntnic/include/ntos_drv.h |  34 +++++
 drivers/net/ntnic/ntnic_ethdev.c     | 208 +++++++++++++++++++++++++++
 drivers/net/ntnic/ntutil/nt_util.c   |  10 ++
 drivers/net/ntnic/ntutil/nt_util.h   |   2 +
 5 files changed, 255 insertions(+)

diff --git a/doc/guides/nics/features/ntnic.ini b/doc/guides/nics/features/ntnic.ini
index b6d92c7ee1..8b9b87bdfe 100644
--- a/doc/guides/nics/features/ntnic.ini
+++ b/doc/guides/nics/features/ntnic.ini
@@ -7,6 +7,7 @@
 FW version           = Y
 Speed capabilities   = Y
 Link status          = Y
+Queue start/stop     = Y
 Unicast MAC filter   = Y
 Multicast MAC filter = Y
 Linux                = Y
diff --git a/drivers/net/ntnic/include/ntos_drv.h b/drivers/net/ntnic/include/ntos_drv.h
index 67baf9fe0c..a77e6a0247 100644
--- a/drivers/net/ntnic/include/ntos_drv.h
+++ b/drivers/net/ntnic/include/ntos_drv.h
@@ -13,6 +13,7 @@
 
 #include <rte_ether.h>
 
+#include "stream_binary_flow_api.h"
 #include "nthw_drv.h"
 
 #define NUM_MAC_ADDRS_PER_PORT (16U)
@@ -21,6 +22,32 @@
 #define NUM_ADAPTER_MAX (8)
 #define NUM_ADAPTER_PORTS_MAX (128)
 
+
+/* Max RSS queues */
+#define MAX_QUEUES       125
+
+/* Structs: */
+struct __rte_cache_aligned ntnic_rx_queue {
+	struct flow_queue_id_s queue;    /* queue info - user id and hw queue index */
+	struct rte_mempool *mb_pool; /* mbuf memory pool */
+	uint16_t buf_size; /* Size of data area in mbuf */
+	int  enabled;  /* Enabling/disabling of this queue */
+
+	nt_meta_port_type_t type;
+	uint32_t port;     /* Rx port for this queue */
+	enum fpga_info_profile profile;  /* Inline / Capture */
+
+};
+
+struct __rte_cache_aligned ntnic_tx_queue {
+	struct flow_queue_id_s queue; /* queue info - user id and hw queue index */
+	nt_meta_port_type_t type;
+
+	uint32_t port;     /* Tx port for this queue */
+	int  enabled;  /* Enabling/disabling of this queue */
+	enum fpga_info_profile profile;  /* Inline / Capture */
+};
+
 struct pmd_internals {
 	const struct rte_pci_device *pci_dev;
 	char name[20];
@@ -30,7 +57,14 @@ struct pmd_internals {
 	unsigned int nb_tx_queues;
 	/* Offset of the VF from the PF */
 	uint8_t vf_offset;
+	uint32_t port;
 	nt_meta_port_type_t type;
+	struct flow_queue_id_s vpq[MAX_QUEUES];
+	unsigned int           vpq_nb_vq;
+	/* Array of Rx queues */
+	struct ntnic_rx_queue  rxq_scg[MAX_QUEUES];
+	/* Array of Tx queues */
+	struct ntnic_tx_queue  txq_scg[MAX_QUEUES];
 	struct drv_s *p_drv;
 	/* Ethernet (MAC) addresses. Element number zero denotes default address. */
 	struct rte_ether_addr eth_addrs[NUM_MAC_ADDRS_PER_PORT];
diff --git a/drivers/net/ntnic/ntnic_ethdev.c b/drivers/net/ntnic/ntnic_ethdev.c
index b261444e8e..b45e25844a 100644
--- a/drivers/net/ntnic/ntnic_ethdev.c
+++ b/drivers/net/ntnic/ntnic_ethdev.c
@@ -3,12 +3,17 @@
  * Copyright(c) 2023 Napatech A/S
  */
 
+#include <stdint.h>
+
 #include <rte_eal.h>
 #include <rte_dev.h>
 #include <rte_vfio.h>
 #include <rte_ethdev.h>
 #include <rte_bus_pci.h>
 #include <ethdev_pci.h>
+#include <rte_kvargs.h>
+
+#include <sys/queue.h>
 
 #include "ntlog.h"
 #include "ntdrv_4ga.h"
@@ -24,6 +29,23 @@
 
 #define EXCEPTION_PATH_HID 0
 
+#define MAX_TOTAL_QUEUES       128
+
+/* Max RSS queues */
+#define MAX_QUEUES 125
+
+#define ETH_DEV_NTNIC_HELP_ARG "help"
+#define ETH_DEV_NTHW_RXQUEUES_ARG "rxqs"
+#define ETH_DEV_NTHW_TXQUEUES_ARG "txqs"
+
+static const char *const valid_arguments[] = {
+	ETH_DEV_NTNIC_HELP_ARG,
+	ETH_DEV_NTHW_RXQUEUES_ARG,
+	ETH_DEV_NTHW_TXQUEUES_ARG,
+	NULL,
+};
+
+
 static const struct rte_pci_id nthw_pci_id_map[] = {
 	{ RTE_PCI_DEVICE(NT_HW_PCI_VENDOR_ID, NT_HW_PCI_DEVICE_ID_NT200A02) },
 	{
@@ -161,6 +183,58 @@ eth_dev_infos_get(struct rte_eth_dev *eth_dev, struct rte_eth_dev_info *dev_info
 	return 0;
 }
 
+static void eth_tx_queue_release(struct rte_eth_dev *eth_dev, uint16_t queue_id)
+{
+	(void)eth_dev;
+	(void)queue_id;
+}
+
+static void eth_rx_queue_release(struct rte_eth_dev *eth_dev, uint16_t queue_id)
+{
+	(void)eth_dev;
+	(void)queue_id;
+}
+
+static int num_queues_alloced;
+
+/* Returns num queue starting at returned queue num or -1 on fail */
+static int allocate_queue(int num)
+{
+	int next_free = num_queues_alloced;
+	NT_LOG_DBGX(DBG, NTNIC, "num_queues_alloced=%u, New queues=%u, Max queues=%u",
+		num_queues_alloced, num, MAX_TOTAL_QUEUES);
+
+	if (num_queues_alloced + num > MAX_TOTAL_QUEUES)
+		return -1;
+
+	num_queues_alloced += num;
+	return next_free;
+}
+
+static int eth_rx_queue_start(struct rte_eth_dev *eth_dev, uint16_t rx_queue_id)
+{
+	eth_dev->data->rx_queue_state[rx_queue_id] = RTE_ETH_QUEUE_STATE_STARTED;
+	return 0;
+}
+
+static int eth_rx_queue_stop(struct rte_eth_dev *eth_dev, uint16_t rx_queue_id)
+{
+	eth_dev->data->rx_queue_state[rx_queue_id] = RTE_ETH_QUEUE_STATE_STOPPED;
+	return 0;
+}
+
+static int eth_tx_queue_start(struct rte_eth_dev *eth_dev, uint16_t rx_queue_id)
+{
+	eth_dev->data->tx_queue_state[rx_queue_id] = RTE_ETH_QUEUE_STATE_STARTED;
+	return 0;
+}
+
+static int eth_tx_queue_stop(struct rte_eth_dev *eth_dev, uint16_t rx_queue_id)
+{
+	eth_dev->data->tx_queue_state[rx_queue_id] = RTE_ETH_QUEUE_STATE_STOPPED;
+	return 0;
+}
+
 static int
 eth_mac_addr_add(struct rte_eth_dev *eth_dev,
 	struct rte_ether_addr *mac_addr,
@@ -247,6 +321,15 @@ eth_dev_start(struct rte_eth_dev *eth_dev)
 
 	NT_LOG_DBGX(DBG, NTNIC, "Port %u", internals->n_intf_no);
 
+	/* Start queues */
+	uint q;
+
+	for (q = 0; q < internals->nb_rx_queues; q++)
+		eth_rx_queue_start(eth_dev, q);
+
+	for (q = 0; q < internals->nb_tx_queues; q++)
+		eth_tx_queue_start(eth_dev, q);
+
 	if (internals->type == PORT_TYPE_VIRTUAL || internals->type == PORT_TYPE_OVERRIDE) {
 		eth_dev->data->dev_link.link_status = RTE_ETH_LINK_UP;
 
@@ -296,6 +379,16 @@ eth_dev_stop(struct rte_eth_dev *eth_dev)
 
 	NT_LOG_DBGX(DBG, NTNIC, "Port %u", internals->n_intf_no);
 
+	if (internals->type != PORT_TYPE_VIRTUAL) {
+		uint q;
+
+		for (q = 0; q < internals->nb_rx_queues; q++)
+			eth_rx_queue_stop(eth_dev, q);
+
+		for (q = 0; q < internals->nb_tx_queues; q++)
+			eth_tx_queue_stop(eth_dev, q);
+	}
+
 	eth_dev->data->dev_link.link_status = RTE_ETH_LINK_DOWN;
 	return 0;
 }
@@ -438,6 +531,12 @@ static const struct eth_dev_ops nthw_eth_dev_ops = {
 	.link_update = eth_link_update,
 	.dev_infos_get = eth_dev_infos_get,
 	.fw_version_get = eth_fw_version_get,
+	.rx_queue_start = eth_rx_queue_start,
+	.rx_queue_stop = eth_rx_queue_stop,
+	.rx_queue_release = eth_rx_queue_release,
+	.tx_queue_start = eth_tx_queue_start,
+	.tx_queue_stop = eth_tx_queue_stop,
+	.tx_queue_release = eth_tx_queue_release,
 	.mac_addr_add = eth_mac_addr_add,
 	.mac_addr_set = eth_mac_addr_set,
 	.set_mc_addr_list = eth_set_mc_addr_list,
@@ -462,6 +561,7 @@ nthw_pci_dev_init(struct rte_pci_device *pci_dev)
 		return -1;
 	}
 
+	int res;
 	struct drv_s *p_drv;
 	ntdrv_4ga_t *p_nt_drv;
 	hw_info_t *p_hw_info;
@@ -469,6 +569,7 @@ nthw_pci_dev_init(struct rte_pci_device *pci_dev)
 	uint32_t n_port_mask = -1;	/* All ports enabled by default */
 	uint32_t nb_rx_queues = 1;
 	uint32_t nb_tx_queues = 1;
+	struct flow_queue_id_s queue_ids[MAX_QUEUES];
 	int n_phy_ports;
 	struct port_link_speed pls_mbps[NUM_ADAPTER_PORTS_MAX] = { 0 };
 	int num_port_speeds = 0;
@@ -476,6 +577,81 @@ nthw_pci_dev_init(struct rte_pci_device *pci_dev)
 		pci_dev->addr.function, pci_dev->addr.bus, pci_dev->addr.devid,
 		pci_dev->addr.function);
 
+	/*
+	 * Process options/arguments
+	 */
+	if (pci_dev->device.devargs && pci_dev->device.devargs->args) {
+		int kvargs_count;
+		struct rte_kvargs *kvlist =
+			rte_kvargs_parse(pci_dev->device.devargs->args, valid_arguments);
+
+		if (kvlist == NULL)
+			return -1;
+
+		/*
+		 * Argument: help
+		 * NOTE: this argument/option check should be the first as it will stop
+		 * execution after producing its output
+		 */
+		{
+			if (rte_kvargs_get(kvlist, ETH_DEV_NTNIC_HELP_ARG)) {
+				size_t i;
+
+				for (i = 0; i < RTE_DIM(valid_arguments); i++)
+					if (valid_arguments[i] == NULL)
+						break;
+
+				exit(0);
+			}
+		}
+
+		/*
+		 * rxq option/argument
+		 * The number of rxq (hostbuffers) allocated in memory.
+		 * Default is 32 RX Hostbuffers
+		 */
+		kvargs_count = rte_kvargs_count(kvlist, ETH_DEV_NTHW_RXQUEUES_ARG);
+
+		if (kvargs_count != 0) {
+			assert(kvargs_count == 1);
+			res = rte_kvargs_process(kvlist, ETH_DEV_NTHW_RXQUEUES_ARG, &string_to_u32,
+					&nb_rx_queues);
+
+			if (res < 0) {
+				NT_LOG_DBGX(ERR, NTNIC,
+					"problem with command line arguments: res=%d",
+					res);
+				return -1;
+			}
+
+			NT_LOG_DBGX(DBG, NTNIC, "devargs: %s=%u",
+				ETH_DEV_NTHW_RXQUEUES_ARG, nb_rx_queues);
+		}
+
+		/*
+		 * txq option/argument
+		 * The number of txq (hostbuffers) allocated in memory.
+		 * Default is 32 TX Hostbuffers
+		 */
+		kvargs_count = rte_kvargs_count(kvlist, ETH_DEV_NTHW_TXQUEUES_ARG);
+
+		if (kvargs_count != 0) {
+			assert(kvargs_count == 1);
+			res = rte_kvargs_process(kvlist, ETH_DEV_NTHW_TXQUEUES_ARG, &string_to_u32,
+					&nb_tx_queues);
+
+			if (res < 0) {
+				NT_LOG_DBGX(ERR, NTNIC,
+					"problem with command line arguments: res=%d",
+					res);
+				return -1;
+			}
+
+			NT_LOG_DBGX(DBG, NTNIC, "devargs: %s=%u",
+				ETH_DEV_NTHW_TXQUEUES_ARG, nb_tx_queues);
+		}
+	}
+
 
 	/* alloc */
 	p_drv = rte_zmalloc_socket(pci_dev->name, sizeof(struct drv_s), RTE_CACHE_LINE_SIZE,
@@ -581,6 +757,7 @@ nthw_pci_dev_init(struct rte_pci_device *pci_dev)
 		struct pmd_internals *internals = NULL;
 		struct rte_eth_dev *eth_dev = NULL;
 		char name[32];
+		int i;
 
 		if ((1 << n_intf_no) & ~n_port_mask) {
 			NT_LOG_DBGX(DBG, NTNIC,
@@ -608,6 +785,10 @@ nthw_pci_dev_init(struct rte_pci_device *pci_dev)
 		internals->nb_rx_queues = nb_rx_queues;
 		internals->nb_tx_queues = nb_tx_queues;
 
+		/* Not used queue index as dest port in bypass - use 0x80 + port nr */
+		for (i = 0; i < MAX_QUEUES; i++)
+			internals->vpq[i].hw_id = -1;
+
 
 		/* Setup queue_ids */
 		if (nb_rx_queues > 1) {
@@ -622,6 +803,33 @@ nthw_pci_dev_init(struct rte_pci_device *pci_dev)
 				internals->n_intf_no, nb_tx_queues);
 		}
 
+		int max_num_queues = (nb_rx_queues > nb_tx_queues) ? nb_rx_queues : nb_tx_queues;
+		int start_queue = allocate_queue(max_num_queues);
+
+		if (start_queue < 0)
+			return -1;
+
+		for (i = 0; i < (int)max_num_queues; i++) {
+			queue_ids[i].id = i;
+			queue_ids[i].hw_id = start_queue + i;
+
+			internals->rxq_scg[i].queue = queue_ids[i];
+			/* use same index in Rx and Tx rings */
+			internals->txq_scg[i].queue = queue_ids[i];
+			internals->rxq_scg[i].enabled = 0;
+			internals->txq_scg[i].type = internals->type;
+			internals->rxq_scg[i].type = internals->type;
+			internals->rxq_scg[i].port = internals->port;
+		}
+
+		/* no tx queues - tx data goes out on phy */
+		internals->vpq_nb_vq = 0;
+
+		for (i = 0; i < (int)nb_tx_queues; i++) {
+			internals->txq_scg[i].port = internals->port;
+			internals->txq_scg[i].enabled = 0;
+		}
+
 		/* Set MAC address (but only if the MAC address is permitted) */
 		if (n_intf_no < fpga_info->nthw_hw_info.vpd_info.mn_mac_addr_count) {
 			const uint64_t mac =
diff --git a/drivers/net/ntnic/ntutil/nt_util.c b/drivers/net/ntnic/ntutil/nt_util.c
index 478b1b65be..694ab7a3b3 100644
--- a/drivers/net/ntnic/ntutil/nt_util.c
+++ b/drivers/net/ntnic/ntutil/nt_util.c
@@ -234,3 +234,13 @@ int nt_link_duplex_to_eth_duplex(enum nt_link_duplex_e nt_link_duplex)
 
 	return eth_link_duplex;
 }
+
+int string_to_u32(const char *key_str __rte_unused, const char *value_str, void *extra_args)
+{
+	if (!value_str || !extra_args)
+		return -1;
+
+	const uint32_t value = strtol(value_str, NULL, 0);
+	*(uint32_t *)extra_args = value;
+	return 0;
+}
diff --git a/drivers/net/ntnic/ntutil/nt_util.h b/drivers/net/ntnic/ntutil/nt_util.h
index d82e6d3248..64947f5fbf 100644
--- a/drivers/net/ntnic/ntutil/nt_util.h
+++ b/drivers/net/ntnic/ntutil/nt_util.h
@@ -57,4 +57,6 @@ uint32_t nt_link_speed_capa_to_eth_speed_capa(int nt_link_speed_capa);
 nt_link_speed_t convert_link_speed(int link_speed_mbps);
 int nt_link_duplex_to_eth_duplex(enum nt_link_duplex_e nt_link_duplex);
 
+int string_to_u32(const char *key_str __rte_unused, const char *value_str, void *extra_args);
+
 #endif	/* NTOSS_SYSTEM_NT_UTIL_H */
-- 
2.45.0