[PATCH] net/idpf: fix Tx of large mbuf segments

[Bruce Richardson <bruce.richardson@intel.com>]

When TSO is enabled, and we get a packet to transmit where an individual
mbuf segment is longer than 16k, we need to split that segment across
multiple Tx descriptors. This support is present in the single-queue
mode of idpf - since it shares common code with the other Intel drivers
-  but was missing from the splitq path.

This patch adds the proper data path handling. Previous work ensured
that the descriptor count calculation took over-sized segments into
account but the actual descriptor writing part was overlooked.

Fixes: 770f4dfe0f79 ("net/idpf: support basic Tx data path")
Fixes: 2904020f8313 ("net/intel: add common function to calculate needed descs")
Cc: stable@dpdk.org

Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
---
v2: rework implementation based on changes to the idpf driver
    since v1 was submitted.
---
 drivers/net/intel/idpf/idpf_common_rxtx.c | 37 ++++++++++++++++++++---
 1 file changed, 32 insertions(+), 5 deletions(-)

diff --git a/drivers/net/intel/idpf/idpf_common_rxtx.c b/drivers/net/intel/idpf/idpf_common_rxtx.c
index a123d969ee..8aa61a2af4 100644
--- a/drivers/net/intel/idpf/idpf_common_rxtx.c
+++ b/drivers/net/intel/idpf/idpf_common_rxtx.c
@@ -994,16 +994,43 @@ idpf_dp_splitq_xmit_pkts(void *tx_queue, struct rte_mbuf **tx_pkts,
 		uint16_t first_sw_id = sw_id;
 
 		do {
+			uint16_t slen = tx_pkt->data_len;
+			rte_iova_t buf_dma_addr = rte_mbuf_data_iova(tx_pkt);
+
+			/* Split segment across multiple descriptors if needed
+			 * for TSO packets where segment exceeds max buf size.
+			 */
+			while ((ol_flags & RTE_MBUF_F_TX_TCP_SEG) &&
+					unlikely(slen > CI_MAX_DATA_PER_TXD)) {
+				txd = &txr[tx_id];
+				txn = &sw_ring[txe->next_id];
+				txe->mbuf = NULL;
+
+				txd->buf_addr = rte_cpu_to_le_64(buf_dma_addr);
+				txd->qw1.cmd_dtype = cmd_dtype |
+					IDPF_TX_DESC_DTYPE_FLEX_FLOW_SCHE;
+				txd->qw1.rxr_bufsize = CI_MAX_DATA_PER_TXD;
+				txd->qw1.compl_tag = sw_id;
+
+				buf_dma_addr += CI_MAX_DATA_PER_TXD;
+				slen -= CI_MAX_DATA_PER_TXD;
+
+				tx_id++;
+				if (tx_id == txq->nb_tx_desc)
+					tx_id = 0;
+				sw_id = txe->next_id;
+				txe = txn;
+			}
+
 			txd = &txr[tx_id];
 			txn = &sw_ring[txe->next_id];
 			txe->mbuf = tx_pkt;
 
 			/* Setup TX descriptor */
-			txd->buf_addr =
-				rte_cpu_to_le_64(rte_mbuf_data_iova(tx_pkt));
-			cmd_dtype |= IDPF_TX_DESC_DTYPE_FLEX_FLOW_SCHE;
-			txd->qw1.cmd_dtype = cmd_dtype;
-			txd->qw1.rxr_bufsize = tx_pkt->data_len;
+			txd->buf_addr = rte_cpu_to_le_64(buf_dma_addr);
+			txd->qw1.cmd_dtype = cmd_dtype |
+				IDPF_TX_DESC_DTYPE_FLEX_FLOW_SCHE;
+			txd->qw1.rxr_bufsize = slen;
 			txd->qw1.compl_tag = sw_id;
 			tx_id++;
 			if (tx_id == txq->nb_tx_desc)
-- 
2.53.0