[PATCH 1/2] ethdev: support selective Rx data

[Gregory Etelson <getelson@nvidia.com>]

In some cases application does not need to receive entire packet
from port hardware.
If application could receive required Rx data only and safely discard
the rest of Rx packet data, that could improve port performance by
reducing PCI bandwidth and application memory consumption.

Selective Rx data allows application to receive
only pre-configured packet segments and discard the rest.
For example:
- Deliver the first N bytes only.
- Deliver the last N bytes only.
- Deliver N1 bytes from offset Off1 and N2 bytes from offset Off2.

Selective Rx data is implemented on-top of the existing Rx
BUFFER_SPLIT functionality:
- The rte_eth_rxseg_split will use the NULL mempool for data segments
that should be discarded.
- PMD will not create MBUF segments if no data was read.

For example: Deliver Ethernet header only

Rx queue segments configuration:
struct rte_eth_rxseg_split split[2] = {
    {
        .mp = <some mempool>,
        .length = sizeof(struct rte_ether_hdr)
    },
    {
        .mp = NULL, /* discard data */
        .length = <MTU>
    }
};

Received MBUF configuration:
mbuf[0].pkt_len = sizeof(struct rte_ether_hdr);
mbuf[0].data_len = sizeof(struct rte_ether_hdr);
mbuf[0].next = NULL; /* The next segment did not deliver data */

After selective Rx, the mbuf packet length reflects only the
existing data that was actually received, and can be less than the
original wire packet length.

A PMD activates the selective Rx data capability by setting the
rte_eth_rxseg_capa.selective_read bit.

Signed-off-by: Gregory Etelson <getelson@nvidia.com>
---
 lib/ethdev/rte_ethdev.c | 10 +++++++---
 lib/ethdev/rte_ethdev.h |  8 +++++++-
 2 files changed, 14 insertions(+), 4 deletions(-)

diff --git a/lib/ethdev/rte_ethdev.c b/lib/ethdev/rte_ethdev.c
index c6fe0d5165..68a51c97c5 100644
--- a/lib/ethdev/rte_ethdev.c
+++ b/lib/ethdev/rte_ethdev.c
@@ -2161,9 +2161,11 @@ rte_eth_rx_queue_check_split(uint16_t port_id,
 		uint32_t proto_hdr = rx_seg[seg_idx].proto_hdr;
 
 		if (mpl == NULL) {
-			RTE_ETHDEV_LOG_LINE(ERR, "null mempool pointer");
-			ret = -EINVAL;
-			goto out;
+			if (dev_info->rx_seg_capa.selective_read == 0) {
+				RTE_ETHDEV_LOG_LINE(ERR, "null mempool pointer");
+				ret = -EINVAL;
+				goto out;
+			}
 		}
 		if (seg_idx != 0 && mp_first != mpl &&
 		    seg_capa->multi_pools == 0) {
@@ -2185,6 +2187,8 @@ rte_eth_rx_queue_check_split(uint16_t port_id,
 				goto out;
 			}
 		}
+		if (mpl == NULL)
+			goto out;
 
 		offset += seg_idx != 0 ? 0 : RTE_PKTMBUF_HEADROOM;
 		*mbp_buf_size = rte_pktmbuf_data_room_size(mpl);
diff --git a/lib/ethdev/rte_ethdev.h b/lib/ethdev/rte_ethdev.h
index a66c2abbdb..173c773e72 100644
--- a/lib/ethdev/rte_ethdev.h
+++ b/lib/ethdev/rte_ethdev.h
@@ -1121,7 +1121,12 @@ struct rte_eth_txmode {
  *   The rest will be put into the last valid pool.
  */
 struct rte_eth_rxseg_split {
-	struct rte_mempool *mp; /**< Memory pool to allocate segment from. */
+	/**
+	 * Memory pool to allocate segment from.
+	 * NULL means skipped segment in selective Rx data. @see selective_read.
+	 * Skipped Rx segment length is not reflected in mbuf packet length.
+	 */
+	struct rte_mempool *mp;
 	uint16_t length; /**< Segment data length, configures split point. */
 	uint16_t offset; /**< Data offset from beginning of mbuf data buffer. */
 	/**
@@ -1758,6 +1763,7 @@ struct rte_eth_rxseg_capa {
 	uint32_t multi_pools:1; /**< Supports receiving to multiple pools.*/
 	uint32_t offset_allowed:1; /**< Supports buffer offsets. */
 	uint32_t offset_align_log2:4; /**< Required offset alignment. */
+	uint32_t selective_read:1; /**< Supports selective read. */
 	uint16_t max_nseg; /**< Maximum amount of segments to split. */
 	uint16_t reserved; /**< Reserved field. */
 };
-- 
2.51.0