iv/linux
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

net/mlx5e: XDP, Allow non-linear single-segment frames in XDP TX MPWQE

Browse Source 
Under a few restrictions, TX MPWQE feature can serve multiple TX packets
in a single TX descriptor. It requires each of the packets to have a
single scatter entry / segment.

Today we allow only linear frames to use this feature, although there's
no real problem with non-linear ones where the whole packet reside in
the first fragment.

Expand the XDP TX MPWQE feature support to include such frames. This is
in preparation for the downstream patch, in which we will generate such
non-linear frames.

Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This commit is contained in:
Tariq Toukan 2023-04-17 15:18:59 +03:00 committed by David S. Miller
parent 124d0d8daf
commit 63abf14e13
1 changed files with 26 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

35
drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
View File

@ -405,18 +405,35 @@ mlx5e_xmit_xdp_frame_mpwqe(struct mlx5e_xdpsq *sq, struct mlx5e_xmit_data *xdptx
{
struct mlx5e_tx_mpwqe *session = &sq->mpwqe;
struct mlx5e_xdpsq_stats *stats = sq->stats;
struct mlx5e_xmit_data *p = xdptxd;
struct mlx5e_xmit_data tmp;
if (xdptxd->has_frags) {
/* MPWQE is enabled, but a multi-buffer packet is queued for
* transmission. MPWQE can't send fragmented packets, so close
* the current session and fall back to a regular WQE.
*/
if (unlikely(sq->mpwqe.wqe))
mlx5e_xdp_mpwqe_complete(sq);
return mlx5e_xmit_xdp_frame(sq, xdptxd, 0);
struct mlx5e_xmit_data_frags *xdptxdf =
container_of(xdptxd, struct mlx5e_xmit_data_frags, xd);
if (!!xdptxd->len + xdptxdf->sinfo->nr_frags > 1) {
/* MPWQE is enabled, but a multi-buffer packet is queued for
* transmission. MPWQE can't send fragmented packets, so close
* the current session and fall back to a regular WQE.
*/
if (unlikely(sq->mpwqe.wqe))
mlx5e_xdp_mpwqe_complete(sq);
return mlx5e_xmit_xdp_frame(sq, xdptxd, 0);
}
if (!xdptxd->len) {
skb_frag_t *frag = &xdptxdf->sinfo->frags[0];
tmp.data = skb_frag_address(frag);
tmp.len = skb_frag_size(frag);
tmp.dma_addr = xdptxdf->dma_arr ? xdptxdf->dma_arr[0] :
page_pool_get_dma_addr(skb_frag_page(frag)) +
skb_frag_off(frag);
p = &tmp;
}
}
if (unlikely(xdptxd->len > sq->hw_mtu)) {
if (unlikely(p->len > sq->hw_mtu)) {
stats->err++;
return false;
}
@ -434,7 +451,7 @@ mlx5e_xmit_xdp_frame_mpwqe(struct mlx5e_xdpsq *sq, struct mlx5e_xmit_data *xdptx
mlx5e_xdp_mpwqe_session_start(sq);
}
mlx5e_xdp_mpwqe_add_dseg(sq, xdptxd, stats);
mlx5e_xdp_mpwqe_add_dseg(sq, p, stats);
if (unlikely(mlx5e_xdp_mpwqe_is_full(session, sq->max_sq_mpw_wqebbs)))
mlx5e_xdp_mpwqe_complete(sq);