[RFC v2 3/7] ethdev: introduce Rx queue based limit watermark

[Spike Du]

LWM(limit watermark) describes the fullness of a Rx queue. If the Rx
queue fullness is above LWM, the device will trigger the event
RTE_ETH_EVENT_RX_LWM.
LWM is defined as a percentage of Rx queue size with valid value of
[0,99].
Setting LWM to 0 means disable it, which is the default.
When translate the percentage to queue descriptor number, the numbe
should be bigger than 0 and less than queue size.
Add LWM's configuration and query driver callbacks in eth_dev_ops.

Signed-off-by: Spike Du <spiked at nvidia.com>
---
 lib/ethdev/ethdev_driver.h | 22 ++++++++++++
 lib/ethdev/rte_ethdev.c    | 52 +++++++++++++++++++++++++++
 lib/ethdev/rte_ethdev.h    | 74 +++++++++++++++++++++++++++++++++++++-
 lib/ethdev/version.map     |  4 +++
 4 files changed, 151 insertions(+), 1 deletion(-)

diff --git a/lib/ethdev/ethdev_driver.h b/lib/ethdev/ethdev_driver.h
index 69d9dc21d8..12ec5e7e19 100644
--- a/lib/ethdev/ethdev_driver.h
+++ b/lib/ethdev/ethdev_driver.h
@@ -470,6 +470,23 @@ typedef int (*eth_rx_queue_setup_t)(struct rte_eth_dev *dev,
 				    const struct rte_eth_rxconf *rx_conf,
 				    struct rte_mempool *mb_pool);
 
+/**
+ * @internal Set Rx queue limit watermark.
+ * see @rte_eth_rx_lwm_set()
+ */
+typedef int (*eth_rx_queue_lwm_set_t)(struct rte_eth_dev *dev,
+				      uint16_t rx_queue_id,
+				      uint8_t lwm);
+
+/**
+ * @internal Query queue limit watermark.
+ * see @rte_eth_rx_lwm_query()
+ */
+
+typedef int (*eth_rx_queue_lwm_query_t)(struct rte_eth_dev *dev,
+					uint16_t *rx_queue_id,
+					uint8_t *lwm);
+
 /** @internal Setup a transmit queue of an Ethernet device. */
 typedef int (*eth_tx_queue_setup_t)(struct rte_eth_dev *dev,
 				    uint16_t tx_queue_id,
@@ -1168,6 +1185,11 @@ struct eth_dev_ops {
 	/** Priority flow control queue configure */
 	priority_flow_ctrl_queue_config_t priority_flow_ctrl_queue_config;
 
+	/** Set Rx queue limit watermark */
+	eth_rx_queue_lwm_set_t rx_queue_lwm_set;
+	/** Query Rx queue limit watermark */
+	eth_rx_queue_lwm_query_t rx_queue_lwm_query;
+
 	/** Set Unicast Table Array */
 	eth_uc_hash_table_set_t    uc_hash_table_set;
 	/** Set Unicast hash bitmap */
diff --git a/lib/ethdev/rte_ethdev.c b/lib/ethdev/rte_ethdev.c
index 8520aec561..0a46c71288 100644
--- a/lib/ethdev/rte_ethdev.c
+++ b/lib/ethdev/rte_ethdev.c
@@ -4429,6 +4429,58 @@ int rte_eth_set_queue_rate_limit(uint16_t port_id, uint16_t queue_idx,
 							queue_idx, tx_rate));
 }
 
+int rte_eth_rx_lwm_set(uint16_t port_id, uint16_t queue_id,
+		       uint8_t lwm)
+{
+	struct rte_eth_dev *dev;
+	struct rte_eth_dev_info dev_info;
+	int ret;
+
+	RTE_ETH_VALID_PORTID_OR_ERR_RET(port_id, -ENODEV);
+	dev = &rte_eth_devices[port_id];
+
+	ret = rte_eth_dev_info_get(port_id, &dev_info);
+	if (ret != 0)
+		return ret;
+
+	if (queue_id > dev_info.max_rx_queues) {
+		RTE_ETHDEV_LOG(ERR,
+			"Set queue LWM:port %u: invalid queue ID=%u.\n",
+			port_id, queue_id);
+		return -EINVAL;
+	}
+
+	if (lwm > 99)
+		return -EINVAL;
+	RTE_FUNC_PTR_OR_ERR_RET(*dev->dev_ops->rx_queue_lwm_set, -ENOTSUP);
+	return eth_err(port_id, (*dev->dev_ops->rx_queue_lwm_set)(dev,
+							     queue_id, lwm));
+}
+
+int rte_eth_rx_lwm_query(uint16_t port_id, uint16_t *queue_id,
+			 uint8_t *lwm)
+{
+	struct rte_eth_dev_info dev_info;
+	struct rte_eth_dev *dev;
+	int ret;
+
+	RTE_ETH_VALID_PORTID_OR_ERR_RET(port_id, -ENODEV);
+	dev = &rte_eth_devices[port_id];
+
+	ret = rte_eth_dev_info_get(port_id, &dev_info);
+	if (ret != 0)
+		return ret;
+
+	if (queue_id == NULL)
+		return -EINVAL;
+	if (*queue_id >= dev_info.max_rx_queues)
+		*queue_id = 0;
+
+	RTE_FUNC_PTR_OR_ERR_RET(*dev->dev_ops->rx_queue_lwm_query, -ENOTSUP);
+	return eth_err(port_id, (*dev->dev_ops->rx_queue_lwm_query)(dev,
+							     queue_id, lwm));
+}
+
 RTE_INIT(eth_dev_init_fp_ops)
 {
 	uint32_t i;
diff --git a/lib/ethdev/rte_ethdev.h b/lib/ethdev/rte_ethdev.h
index 04cff8ee10..687ae5ff29 100644
--- a/lib/ethdev/rte_ethdev.h
+++ b/lib/ethdev/rte_ethdev.h
@@ -1249,7 +1249,16 @@ struct rte_eth_rxconf {
 	 */
 	union rte_eth_rxseg *rx_seg;
 
-	uint64_t reserved_64s[2]; /**< Reserved for future fields */
+	/**
+	 * Per-queue Rx limit watermark defined as percentage of Rx queue
+	 * size. If Rx queue receives traffic higher than this percentage,
+	 * the event RTE_ETH_EVENT_RX_LWM is triggered.
+	 */
+	uint8_t lwm;
+
+	uint8_t reserved_bits[3];
+	uint32_t reserved_32s;
+	uint64_t reserved_64s;
 	void *reserved_ptrs[2];   /**< Reserved for future fields */
 };
 
@@ -3668,6 +3677,64 @@ int rte_eth_dev_get_vlan_offload(uint16_t port_id);
  */
 int rte_eth_dev_set_vlan_pvid(uint16_t port_id, uint16_t pvid, int on);
 
+/**
+ * @warning
+ * @b EXPERIMENTAL: this API may change without prior notice.
+ *
+ * Set Rx queue based limit watermark.
+ *
+ * @param port_id
+ *  The port identifier of the Ethernet device.
+ * @param queue_id
+ *  The index of the receive queue.
+ * @param lwm
+ *  The limit watermark percentage of Rx queue size which describes
+ *  the fullness of Rx queue. If the Rx queue fullness is above LWM,
+ *  the device will trigger the event RTE_ETH_EVENT_RX_LWM.
+ *  [1-99] to set a new LWM.
+ *  0 to disable watermark monitoring.
+ *
+ * @return
+ *   - 0 if successful.
+ *   - negative if failed.
+ */
+__rte_experimental
+int rte_eth_rx_lwm_set(uint16_t port_id, uint16_t queue_id, uint8_t lwm);
+
+/**
+ * @warning
+ * @b EXPERIMENTAL: this API may change without prior notice.
+ *
+ * Query Rx queue based limit watermark.
+ * The function queries all queues in the port circularly until one
+ * pending LWM event is found or no pending LWM event is found.
+ *
+ * @param port_id
+ *  The port identifier of the Ethernet device.
+ * @param queue_id
+ *  The API caller sets the starting Rx queue id in the pointer.
+ *  If the queue_id is bigger than maximum queue id of the port,
+ *  it's rewinded to 0 so that application can keep calling
+ *  this function to handle all pending LWM events in the queues
+ *  with a simple increment between calls.
+ *  If a Rx queue has pending lwm event, the pointer is updated
+ *  with this Rx queue id; otherwise this pointer's content is
+ *  unchanged.
+ * @param lwm
+ *  The pointer to the limit watermark percentage of Rx queue.
+ *  If Rx queue with pending lwm event is found, the queue's LWM
+ *  percentage is stored in this pointer, otherwise the pointer's
+ *  content is unchanged.
+ *
+ * @return
+ *   - 1 if a Rx queue with pending lwm event is found.
+ *   - 0 if no Rx queue with pending lwm event is found.
+ *   - -EINVAL if queue_id is NULL.
+ */
+__rte_experimental
+int rte_eth_rx_lwm_query(uint16_t port_id, uint16_t *queue_id,
+			 uint8_t *lwm);
+
 typedef void (*buffer_tx_error_fn)(struct rte_mbuf **unsent, uint16_t count,
 		void *userdata);
 
@@ -3873,6 +3940,11 @@ enum rte_eth_event_type {
 	RTE_ETH_EVENT_DESTROY,  /**< port is released */
 	RTE_ETH_EVENT_IPSEC,    /**< IPsec offload related event */
 	RTE_ETH_EVENT_FLOW_AGED,/**< New aged-out flows is detected */
+	/**
+	 *  watermark value is exceeded in a queue.
+	 *  see @rte_eth_rx_lwm_set()
+	 */
+	RTE_ETH_EVENT_RX_LWM,
 	RTE_ETH_EVENT_MAX       /**< max value of this enum */
 };
 
diff --git a/lib/ethdev/version.map b/lib/ethdev/version.map
index 20391ab29e..5cf44c5d1d 100644
--- a/lib/ethdev/version.map
+++ b/lib/ethdev/version.map
@@ -279,6 +279,10 @@ EXPERIMENTAL {
 	rte_flow_async_action_handle_create;
 	rte_flow_async_action_handle_destroy;
 	rte_flow_async_action_handle_update;
+
+	# added in 22.07
+	rte_eth_rx_lwm_set;
+	rte_eth_rx_lwm_query;
 };
 
 INTERNAL {
-- 
2.27.0