[dpdk-dev] [PATCH 1/3] vmxnet3: support jumbo frames

[Stephen Hemminger]

Add support for linking multi-segment buffers together to
handle Jumbo packets. The vmxnet3 API supports having header
and body buffer types. What this patch does is fill the primary
ring completely with header buffers and the secondary ring
with body buffers. This allows for non-jumbo frames to only
use one mbuf (from primary ring); and jumbo frames will have
first mbuf from primary ring and following mbufs from other
ring.

This could be optimized in future if the DPDK had API
to supply different sized mbufs (two pools) into driver.

Signed-off-by: Stephen Hemminger <shemming at brocade.com>
---
 drivers/net/vmxnet3/vmxnet3_ethdev.c |  3 +-
 drivers/net/vmxnet3/vmxnet3_ring.h   |  2 +
 drivers/net/vmxnet3/vmxnet3_rxtx.c   | 80 +++++++++++++++++++-----------------
 3 files changed, 46 insertions(+), 39 deletions(-)

diff --git a/drivers/net/vmxnet3/vmxnet3_ethdev.c b/drivers/net/vmxnet3/vmxnet3_ethdev.c
index c363bf6..585ee60 100644
--- a/drivers/net/vmxnet3/vmxnet3_ethdev.c
+++ b/drivers/net/vmxnet3/vmxnet3_ethdev.c
@@ -425,6 +425,7 @@ vmxnet3_setup_driver_shared(struct rte_eth_dev *dev)
 {
 	struct rte_eth_conf port_conf = dev->data->dev_conf;
 	struct vmxnet3_hw *hw = dev->data->dev_private;
+	uint32_t mtu = dev->data->mtu;
 	Vmxnet3_DriverShared *shared = hw->shared;
 	Vmxnet3_DSDevRead *devRead = &shared->devRead;
 	uint32_t *mac_ptr;
@@ -442,7 +443,7 @@ vmxnet3_setup_driver_shared(struct rte_eth_dev *dev)
 	devRead->misc.driverInfo.vmxnet3RevSpt = 1;
 	devRead->misc.driverInfo.uptVerSpt     = 1;
 
-	devRead->misc.mtu = rte_le_to_cpu_32(dev->data->mtu);
+	devRead->misc.mtu = rte_le_to_cpu_32(mtu);
 	devRead->misc.queueDescPA  = hw->queueDescPA;
 	devRead->misc.queueDescLen = hw->queue_desc_len;
 	devRead->misc.numTxQueues  = hw->num_tx_queues;
diff --git a/drivers/net/vmxnet3/vmxnet3_ring.h b/drivers/net/vmxnet3/vmxnet3_ring.h
index da4c595..1d1879a 100644
--- a/drivers/net/vmxnet3/vmxnet3_ring.h
+++ b/drivers/net/vmxnet3/vmxnet3_ring.h
@@ -171,6 +171,8 @@ typedef struct vmxnet3_rx_queue {
 	uint32_t                    qid1;
 	uint32_t                    qid2;
 	Vmxnet3_RxQueueDesc         *shared;
+	struct rte_mbuf		    *start_seg;
+	struct rte_mbuf		    *last_seg;
 	struct vmxnet3_rxq_stats    stats;
 	bool                        stopped;
 	uint16_t                    queue_id;      /**< Device RX queue index. */
diff --git a/drivers/net/vmxnet3/vmxnet3_rxtx.c b/drivers/net/vmxnet3/vmxnet3_rxtx.c
index 8385478..4ed1646 100644
--- a/drivers/net/vmxnet3/vmxnet3_rxtx.c
+++ b/drivers/net/vmxnet3/vmxnet3_rxtx.c
@@ -570,35 +570,11 @@ vmxnet3_recv_pkts(void *rx_queue, struct rte_mbuf **rx_pkts, uint16_t nb_pkts)
 		rxd = (Vmxnet3_RxDesc *)rxq->cmd_ring[ring_idx].base + idx;
 		rbi = rxq->cmd_ring[ring_idx].buf_info + idx;
 
-		if (unlikely(rcd->sop != 1 || rcd->eop != 1)) {
-			rte_pktmbuf_free_seg(rbi->m);
-			PMD_RX_LOG(DEBUG, "Packet spread across multiple buffers\n)");
-			goto rcd_done;
-		}
-
 		PMD_RX_LOG(DEBUG, "rxd idx: %d ring idx: %d.", idx, ring_idx);
 
 		VMXNET3_ASSERT(rcd->len <= rxd->len);
 		VMXNET3_ASSERT(rbi->m);
 
-		if (unlikely(rcd->len == 0)) {
-			PMD_RX_LOG(DEBUG, "Rx buf was skipped. rxring[%d][%d]\n)",
-				   ring_idx, idx);
-			VMXNET3_ASSERT(rcd->sop && rcd->eop);
-			rte_pktmbuf_free_seg(rbi->m);
-			goto rcd_done;
-		}
-
-		/* Assuming a packet is coming in a single packet buffer */
-		if (unlikely(rxd->btype != VMXNET3_RXD_BTYPE_HEAD)) {
-			PMD_RX_LOG(DEBUG,
-				   "Alert : Misbehaving device, incorrect "
-				   " buffer type used. iPacket dropped.");
-			rte_pktmbuf_free_seg(rbi->m);
-			goto rcd_done;
-		}
-		VMXNET3_ASSERT(rxd->btype == VMXNET3_RXD_BTYPE_HEAD);
-
 		/* Get the packet buffer pointer from buf_info */
 		rxm = rbi->m;
 
@@ -610,7 +586,7 @@ vmxnet3_recv_pkts(void *rx_queue, struct rte_mbuf **rx_pkts, uint16_t nb_pkts)
 		rxq->cmd_ring[ring_idx].next2comp = idx;
 
 		/* For RCD with EOP set, check if there is frame error */
-		if (unlikely(rcd->err)) {
+		if (unlikely(rcd->eop && rcd->err)) {
 			rxq->stats.drop_total++;
 			rxq->stats.drop_err++;
 
@@ -636,9 +612,47 @@ vmxnet3_recv_pkts(void *rx_queue, struct rte_mbuf **rx_pkts, uint16_t nb_pkts)
 		rxm->ol_flags = 0;
 		rxm->vlan_tci = 0;
 
-		vmxnet3_rx_offload(rcd, rxm);
+		/*
+		 * If this is the first buffer of the received packet,
+		 * set the pointer to the first mbuf of the packet
+		 * Otherwise, update the total length and the number of segments
+		 * of the current scattered packet, and update the pointer to
+		 * the last mbuf of the current packet.
+		 */
+		if (rcd->sop) {
+			VMXNET3_ASSERT(rxq->start_seg != NULL);
+			VMXNET3_ASSERT(rxd->btype == VMXNET3_RXD_BTYPE_HEAD);
+
+			if (unlikely(rcd->len == 0)) {
+				VMXNET3_ASSERT(rcd->eop);
+				
+				PMD_RX_LOG(DEBUG,
+					   "Rx buf was skipped. rxring[%d][%d])",
+					   ring_idx, idx);
+				rte_pktmbuf_free_seg(rxm);
+				goto rcd_done;
+			}
+
+			rxq->start_seg = rxm;
+			vmxnet3_rx_offload(rcd, rxm);
+		} else {
+			struct rte_mbuf *start = rxq->start_seg;
+
+			VMXNET3_ASSERT(rxd->btype == VMXNET3_RXD_BTYPE_BODY);
+			VMXNET3_ASSERT(start != NULL);
+
+			start->pkt_len += rxm->data_len;
+			start->nb_segs++;
+
+			rxq->last_seg->next = rxm;
+		}
+		rxq->last_seg = rxm;
+
+		if (rcd->eop) {
+			rx_pkts[nb_rx++] = rxq->start_seg;
+			rxq->start_seg = NULL;
+		}
 
-		rx_pkts[nb_rx++] = rxm;
 rcd_done:
 		rxq->cmd_ring[ring_idx].next2comp = idx;
 		VMXNET3_INC_RING_IDX_ONLY(rxq->cmd_ring[ring_idx].next2comp, rxq->cmd_ring[ring_idx].size);
@@ -807,20 +821,9 @@ vmxnet3_dev_rx_queue_setup(struct rte_eth_dev *dev,
 	int size;
 	uint8_t i;
 	char mem_name[32];
-	uint16_t buf_size;
 
 	PMD_INIT_FUNC_TRACE();
 
-	buf_size = rte_pktmbuf_data_room_size(mp) -
-		RTE_PKTMBUF_HEADROOM;
-
-	if (dev->data->dev_conf.rxmode.max_rx_pkt_len > buf_size) {
-		PMD_INIT_LOG(ERR, "buf_size = %u, max_pkt_len = %u, "
-			     "VMXNET3 don't support scatter packets yet",
-			     buf_size, dev->data->dev_conf.rxmode.max_rx_pkt_len);
-		return -EINVAL;
-	}
-
 	rxq = rte_zmalloc("ethdev_rx_queue", sizeof(struct vmxnet3_rx_queue), RTE_CACHE_LINE_SIZE);
 	if (rxq == NULL) {
 		PMD_INIT_LOG(ERR, "Can not allocate rx queue structure");
@@ -939,6 +942,7 @@ vmxnet3_dev_rxtx_init(struct rte_eth_dev *dev)
 			}
 		}
 		rxq->stopped = FALSE;
+		rxq->start_seg = NULL;
 	}
 
 	for (i = 0; i < dev->data->nb_tx_queues; i++) {
-- 
2.1.4