idpf: convert header split mode to libeth + napi_build_skb()

Currently, idpf uses the following model for the header buffers:

* buffers are allocated via dma_alloc_coherent();
* when receiving, napi_alloc_skb() is called and then the header is
  copied to the newly allocated linear part.

This is far from optimal as DMA coherent zone is slow on many systems
and memcpy() neutralizes the idea and benefits of the header split. Not
speaking of that XDP can't be run on DMA coherent buffers, but at the
same time the idea of allocating an skb to run XDP program is ill.
Instead, use libeth to create page_pools for the header buffers, allocate
them dynamically and then build an skb via napi_build_skb() around them
with no memory copy. With one exception...

When you enable header split, you expect you'll always have a separate
header buffer, so that you could reserve headroom and tailroom only
there and then use full buffers for the data. For example, this is how
TCP zerocopy works -- you have to have the payload aligned to PAGE_SIZE.
The current hardware running idpf does *not* guarantee that you'll
always have headers placed separately. For example, on my setup, even
ICMP packets are written as one piece to the data buffers. You can't
build a valid skb around a data buffer in this case.
To not complicate things and not lose TCP zerocopy etc., when such thing
happens, use the empty header buffer and pull either full frame (if it's
short) or the Ethernet header there and build an skb around it. GRO
layer will pull more from the data buffer later. This W/A will hopefully
be removed one day.

Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>

1 files changed, 10 insertions, 4 deletions

diff --git a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c
index 83f3543a30e1..50dcb3ab02b1 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c
@@ -1604,32 +1604,38 @@ setup_rxqs:
 			num_rxq = rx_qgrp->singleq.num_rxq;
 
 		for (j = 0; j < num_rxq; j++, k++) {
+			const struct idpf_bufq_set *sets;
 			struct idpf_rx_queue *rxq;
 
 			if (!idpf_is_queue_model_split(vport->rxq_model)) {
 				rxq = rx_qgrp->singleq.rxqs[j];
 				goto common_qi_fields;
 			}
+
 			rxq = &rx_qgrp->splitq.rxq_sets[j]->rxq;
-			qi[k].rx_bufq1_id =
-			  cpu_to_le16(rxq->bufq_sets[0].bufq.q_id);
+			sets = rxq->bufq_sets;
+
+			qi[k].rx_bufq1_id = cpu_to_le16(sets[0].bufq.q_id);
 			if (vport->num_bufqs_per_qgrp > IDPF_SINGLE_BUFQ_PER_RXQ_GRP) {
 				qi[k].bufq2_ena = IDPF_BUFQ2_ENA;
 				qi[k].rx_bufq2_id =
-				  cpu_to_le16(rxq->bufq_sets[1].bufq.q_id);
+					cpu_to_le16(sets[1].bufq.q_id);
 			}
 			qi[k].rx_buffer_low_watermark =
 				cpu_to_le16(rxq->rx_buffer_low_watermark);
 			if (idpf_is_feature_ena(vport, NETIF_F_GRO_HW))
 				qi[k].qflags |= cpu_to_le16(VIRTCHNL2_RXQ_RSC);
 
-common_qi_fields:
+			rxq->rx_hbuf_size = sets[0].bufq.rx_hbuf_size;
+
 			if (idpf_queue_has(HSPLIT_EN, rxq)) {
 				qi[k].qflags |=
 					cpu_to_le16(VIRTCHNL2_RXQ_HDR_SPLIT);
 				qi[k].hdr_buffer_size =
 					cpu_to_le16(rxq->rx_hbuf_size);
 			}
+
+common_qi_fields:
 			qi[k].queue_id = cpu_to_le32(rxq->q_id);
 			qi[k].model = cpu_to_le16(vport->rxq_model);
 			qi[k].type = cpu_to_le32(VIRTCHNL2_QUEUE_TYPE_RX);