[PATCH net-next v3 28/33] mlx5: rx queue setup time determine frame_sz for XDP

[Jesper Dangaard Brouer <brouer@redhat.com>]

The mlx5 driver have multiple memory models, which are also changed
according to whether a XDP bpf_prog is attached.

The 'rx_striding_rq' setting is adjusted via ethtool priv-flags e.g.:
 # ethtool --set-priv-flags mlx5p2 rx_striding_rq off

On the general case with 4K page_size and regular MTU packet, then
the frame_sz is 2048 and 4096 when XDP is enabled, in both modes.

The info on the given frame size is stored differently depending on the
RQ-mode and encoded in a union in struct mlx5e_rq union wqe/mpwqe.
In rx striding mode rq->mpwqe.log_stride_sz is either 11 or 12, which
corresponds to 2048 or 4096 (MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ).
In non-striding mode (MLX5_WQ_TYPE_CYCLIC) the frag_stride is stored
in rq->wqe.info.arr[0].frag_stride, for the first fragment, which is
what the XDP case cares about.

To reduce effect on fast-path, this patch determine the frame_sz at
setup time, to avoid determining the memory model runtime. Variable
is named first_frame_sz to make it clear that this is only the frame
size of the first fragment.

This mlx5 driver does a DMA-sync on XDP_TX action, but grow is safe
as it have done a DMA-map on the entire PAGE_SIZE. The driver also
already does a XDP length check against sq->hw_mtu on the possible
XDP xmit paths mlx5e_xmit_xdp_frame() + mlx5e_xmit_xdp_frame_mpwqe().

V2: Fix that frag_size need to be recalc before creating SKB.

Cc: Tariq Toukan <tariqt@mellanox.com>
Cc: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h      |    1 +
 drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c  |    1 +
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c |    6 ++++++
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c   |    2 ++
 4 files changed, 10 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 0864b76ca2c0..8e75a9f9b114 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -652,6 +652,7 @@ struct mlx5e_rq {
 	struct {
 		u16            umem_headroom;
 		u16            headroom;
+		u32            frame0_sz;
 		u8             map_dir;   /* dma map direction */
 	} buff;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
index c4a7fb4ecd14..761c8979bd41 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
@@ -137,6 +137,7 @@ bool mlx5e_xdp_handle(struct mlx5e_rq *rq, struct mlx5e_dma_info *di,
 	if (xsk)
 		xdp.handle = di->xsk.handle;
 	xdp.rxq = &rq->xdp_rxq;
+	xdp.frame_sz = rq->buff.frame0_sz;
 
 	act = bpf_prog_run_xdp(prog, &xdp);
 	if (xsk) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 048a4f8601a8..c0f1912bcb65 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -462,6 +462,8 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 		rq->mpwqe.num_strides =
 			BIT(mlx5e_mpwqe_get_log_num_strides(mdev, params, xsk));
 
+		rq->buff.frame0_sz = (1 << rq->mpwqe.log_stride_sz);
+
 		err = mlx5e_create_rq_umr_mkey(mdev, rq);
 		if (err)
 			goto err_rq_wq_destroy;
@@ -485,6 +487,8 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 			num_xsk_frames = wq_sz << rq->wqe.info.log_num_frags;
 
 		rq->wqe.info = rqp->frags_info;
+		rq->buff.frame0_sz = rq->wqe.info.arr[0].frag_stride;
+
 		rq->wqe.frags =
 			kvzalloc_node(array_size(sizeof(*rq->wqe.frags),
 					(wq_sz << rq->wqe.info.log_num_frags)),
@@ -522,6 +526,8 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 	}
 
 	if (xsk) {
+		rq->buff.frame0_sz = xsk_umem_xdp_frame_sz(umem);
+
 		err = mlx5e_xsk_resize_reuseq(umem, num_xsk_frames);
 		if (unlikely(err)) {
 			mlx5_core_err(mdev, "Unable to allocate the Reuse Ring for %u frames\n",
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index d9a5a669b84d..97c2fda8f697 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -1064,6 +1064,7 @@ mlx5e_skb_from_cqe_linear(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe,
 	if (consumed)
 		return NULL; /* page/packet was consumed by XDP */
 
+	frag_size = MLX5_SKB_FRAG_SZ(rx_headroom + cqe_bcnt);
 	skb = mlx5e_build_linear_skb(rq, va, frag_size, rx_headroom, cqe_bcnt);
 	if (unlikely(!skb))
 		return NULL;
@@ -1365,6 +1366,7 @@ mlx5e_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi,
 		return NULL; /* page/packet was consumed by XDP */
 	}
 
+	frag_size = MLX5_SKB_FRAG_SZ(rx_headroom + cqe_bcnt32);
 	skb = mlx5e_build_linear_skb(rq, va, frag_size, rx_headroom, cqe_bcnt32);
 	if (unlikely(!skb))
 		return NULL;