[PATCH v6 1/3] ethdev: support mulitiple mbuf pools per Rx queue

[Hanumanth Pothula <hpothula@marvell.com>]

This patch adds support for multiple mempool capability.
Some of the HW has support for choosing memory pools based on the
packet's size. The capability allows PMD to choose a memory pool
based on the packet's length.

This is often useful for saving the memory where the application
can create a different pool to steer the specific size of the
packet, thus enabling effective use of memory.

For example, let's say HW has a capability of three pools,
 - pool-1 size is 2K
 - pool-2 size is > 2K and < 4K
 - pool-3 size is > 4K
Here,
        pool-1 can accommodate packets with sizes < 2K
        pool-2 can accommodate packets with sizes > 2K and < 4K
        pool-3 can accommodate packets with sizes > 4K

With multiple mempool capability enabled in SW, an application may
create three pools of different sizes and send them to PMD. Allowing
PMD to program HW based on the packet lengths. So that packets with
less than 2K are received on pool-1, packets with lengths between 2K
and 4K are received on pool-2 and finally packets greater than 4K
are received on pool-3.

Signed-off-by: Hanumanth Pothula <hpothula@marvell.com>

v6:
 - Updated release notes, release_22_11.rst.
v5:
 - Declared memory pools as struct rte_mempool **rx_mempools rather than
   as struct rte_mempool *mp.
 - Added the feature in release notes.
 - Updated conditions and strings as per review comments.
v4:
 - Renamed Offload capability name from RTE_ETH_RX_OFFLOAD_BUFFER_SORT
   to RTE_ETH_RX_OFFLOAD_MUL_MEMPOOL.
 - In struct rte_eth_rxconf, defined new pointer, which holds array of
   type struct rte_eth_rx_mempool(memory pools). This array is used
   by PMD to program multiple mempools.
v3:
 - Implemented Pool Sort capability as new Rx offload capability,
   RTE_ETH_RX_OFFLOAD_BUFFER_SORT.
v2:
 - Along with spec changes, uploading testpmd and driver changes.
---
 doc/guides/rel_notes/release_22_11.rst |  6 +++
 lib/ethdev/rte_ethdev.c                | 74 ++++++++++++++++++++++----
 lib/ethdev/rte_ethdev.h                | 22 ++++++++
 3 files changed, 92 insertions(+), 10 deletions(-)

diff --git a/doc/guides/rel_notes/release_22_11.rst b/doc/guides/rel_notes/release_22_11.rst
index 2e076ba2ad..8bb19155d9 100644
--- a/doc/guides/rel_notes/release_22_11.rst
+++ b/doc/guides/rel_notes/release_22_11.rst
@@ -55,6 +55,12 @@ New Features
      Also, make sure to start the actual text at the margin.
      =======================================================
 
+* ** Added support ethdev support for mulitiple mbuf pools per Rx queue.**
+
+  * Added new Rx offload flag ``RTE_ETH_RX_OFFLOAD_MUL_MEMPOOL`` to support
+    mulitiple mbuf pools per Rx queue. Thisi capability allows PMD to choose
+    a memory pool based on the packet's length
+
 * **Updated Wangxun ngbe driver.**
 
   * Added support to set device link down/up.
diff --git a/lib/ethdev/rte_ethdev.c b/lib/ethdev/rte_ethdev.c
index 1979dc0850..eed4834e6b 100644
--- a/lib/ethdev/rte_ethdev.c
+++ b/lib/ethdev/rte_ethdev.c
@@ -1634,6 +1634,44 @@ rte_eth_dev_is_removed(uint16_t port_id)
 	return ret;
 }
 
+static int
+rte_eth_rx_queue_check_mempool(struct rte_mempool **rx_mempool,
+			       uint16_t n_pool, uint32_t *mbp_buf_size,
+			       const struct rte_eth_dev_info *dev_info)
+{
+	uint16_t pool_idx;
+
+	if (n_pool > dev_info->max_pools) {
+		RTE_ETHDEV_LOG(ERR,
+			       "Too many Rx mempools %u vs maximum %u\n",
+			       n_pool, dev_info->max_pools);
+		return -EINVAL;
+	}
+
+	for (pool_idx = 0; pool_idx < n_pool; pool_idx++) {
+		struct rte_mempool *mpl = rx_mempool[pool_idx];
+
+		if (mpl == NULL) {
+			RTE_ETHDEV_LOG(ERR, "null Rx mempool pointer\n");
+			return -EINVAL;
+		}
+
+		*mbp_buf_size = rte_pktmbuf_data_room_size(mpl);
+		if (*mbp_buf_size < dev_info->min_rx_bufsize +
+		    RTE_PKTMBUF_HEADROOM) {
+			RTE_ETHDEV_LOG(ERR,
+				       "%s mbuf_data_room_size %u < %u (RTE_PKTMBUF_HEADROOM=%u + min_rx_bufsize(dev)=%u)\n",
+					mpl->name, *mbp_buf_size,
+					RTE_PKTMBUF_HEADROOM + dev_info->min_rx_bufsize,
+					RTE_PKTMBUF_HEADROOM,
+					dev_info->min_rx_bufsize);
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
 static int
 rte_eth_rx_queue_check_split(const struct rte_eth_rxseg_split *rx_seg,
 			     uint16_t n_seg, uint32_t *mbp_buf_size,
@@ -1733,9 +1771,12 @@ rte_eth_rx_queue_setup(uint16_t port_id, uint16_t rx_queue_id,
 
 	if (mp != NULL) {
 		/* Single pool configuration check. */
-		if (rx_conf != NULL && rx_conf->rx_nseg != 0) {
+		if (((rx_conf->offloads & RTE_ETH_RX_OFFLOAD_BUFFER_SPLIT) &&
+		    rx_conf != NULL && rx_conf->rx_nseg != 0) ||
+		   ((rx_conf->offloads & RTE_ETH_RX_OFFLOAD_MUL_MEMPOOL) &&
+		    rx_conf != NULL && rx_conf->rx_npool != 0)) {
 			RTE_ETHDEV_LOG(ERR,
-				       "Ambiguous segment configuration\n");
+				       "Ambiguous Rx mempools configuration\n");
 			return -EINVAL;
 		}
 		/*
@@ -1763,30 +1804,43 @@ rte_eth_rx_queue_setup(uint16_t port_id, uint16_t rx_queue_id,
 				       dev_info.min_rx_bufsize);
 			return -EINVAL;
 		}
-	} else {
+	} else if (rx_conf->offloads & RTE_ETH_RX_OFFLOAD_BUFFER_SPLIT) {
 		const struct rte_eth_rxseg_split *rx_seg;
 		uint16_t n_seg;
 
 		/* Extended multi-segment configuration check. */
 		if (rx_conf == NULL || rx_conf->rx_seg == NULL || rx_conf->rx_nseg == 0) {
 			RTE_ETHDEV_LOG(ERR,
-				       "Memory pool is null and no extended configuration provided\n");
+				       "Memory pool is null and no multi-segment configuration provided\n");
 			return -EINVAL;
 		}
 
 		rx_seg = (const struct rte_eth_rxseg_split *)rx_conf->rx_seg;
 		n_seg = rx_conf->rx_nseg;
 
-		if (rx_conf->offloads & RTE_ETH_RX_OFFLOAD_BUFFER_SPLIT) {
-			ret = rte_eth_rx_queue_check_split(rx_seg, n_seg,
+		ret = rte_eth_rx_queue_check_split(rx_seg, n_seg,
 							   &mbp_buf_size,
 							   &dev_info);
-			if (ret != 0)
-				return ret;
-		} else {
-			RTE_ETHDEV_LOG(ERR, "No Rx segmentation offload configured\n");
+		if (ret != 0)
+			return ret;
+	} else if (rx_conf->offloads & RTE_ETH_RX_OFFLOAD_MUL_MEMPOOL) {
+		/* Extended multi-pool configuration check. */
+		if (rx_conf == NULL || rx_conf->rx_mempools == NULL || rx_conf->rx_npool == 0) {
+			RTE_ETHDEV_LOG(ERR,
+				       "Memory pool is null and no multi-pool configuration provided\n");
 			return -EINVAL;
 		}
+
+		ret = rte_eth_rx_queue_check_mempool(rx_conf->rx_mempools,
+						     rx_conf->rx_npool,
+						     &mbp_buf_size,
+						     &dev_info);
+
+		if (ret != 0)
+			return ret;
+	} else {
+		RTE_ETHDEV_LOG(ERR, "Missing Rx mempool configuration\n");
+		return -EINVAL;
 	}
 
 	/* Use default specified by driver, if nb_rx_desc is zero */
diff --git a/lib/ethdev/rte_ethdev.h b/lib/ethdev/rte_ethdev.h
index b62ac5bb6f..306c2b3573 100644
--- a/lib/ethdev/rte_ethdev.h
+++ b/lib/ethdev/rte_ethdev.h
@@ -1067,6 +1067,25 @@ struct rte_eth_rxconf {
 	 */
 	union rte_eth_rxseg *rx_seg;
 
+	/**
+	 * Points to an array of mempools.
+	 *
+	 * Valid only when RTE_ETH_RX_OFFLOAD_MUL_MEMPOOL flag is set in
+	 * Rx offloads.
+	 *
+	 * This provides support for  multiple mbuf pools per Rx queue.
+	 *
+	 * This is often useful for saving the memory where the application can
+	 * create a different pools to steer the specific size of the packet, thus
+	 * enabling effective use of memory.
+	 *
+	 * Note that on Rx scatter enable, a packet may be delivered using a chain
+	 * of mbufs obtained from single mempool or multiple mempools based on
+	 * the NIC implementation.
+	 */
+	struct rte_mempool **rx_mempools;
+	uint16_t rx_npool; /** < number of mempools */
+
 	uint64_t reserved_64s[2]; /**< Reserved for future fields */
 	void *reserved_ptrs[2];   /**< Reserved for future fields */
 };
@@ -1395,6 +1414,7 @@ struct rte_eth_conf {
 #define RTE_ETH_RX_OFFLOAD_OUTER_UDP_CKSUM  RTE_BIT64(18)
 #define RTE_ETH_RX_OFFLOAD_RSS_HASH         RTE_BIT64(19)
 #define RTE_ETH_RX_OFFLOAD_BUFFER_SPLIT     RTE_BIT64(20)
+#define RTE_ETH_RX_OFFLOAD_MUL_MEMPOOL      RTE_BIT64(21)
 
 #define RTE_ETH_RX_OFFLOAD_CHECKSUM (RTE_ETH_RX_OFFLOAD_IPV4_CKSUM | \
 				 RTE_ETH_RX_OFFLOAD_UDP_CKSUM | \
@@ -1615,6 +1635,8 @@ struct rte_eth_dev_info {
 	/** Configured number of Rx/Tx queues */
 	uint16_t nb_rx_queues; /**< Number of Rx queues. */
 	uint16_t nb_tx_queues; /**< Number of Tx queues. */
+	/** Maximum number of pools supported per Rx queue. */
+	uint16_t max_pools;
 	/** Rx parameter recommendations */
 	struct rte_eth_dev_portconf default_rxportconf;
 	/** Tx parameter recommendations */
-- 
2.25.1