mlx5: Rx queue setup time determine frame_sz for XDP

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 frame0_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().

V3+4: Change variable name first_frame_sz to frame0_sz

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

Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Tariq Toukan <tariqt@mellanox.com>
Cc: Saeed Mahameed <saeedm@mellanox.com>
Link: https://lore.kernel.org/bpf/158945348021.97035.12295039384250022883.stgit@firesoul
This commit is contained in:
Jesper Dangaard Brouer 2020-05-14 12:51:20 +02:00 committed by Alexei Starovoitov
parent 2a637c5b1a
commit d628ee4fef
4 changed files with 10 additions and 0 deletions

View File

@ -625,6 +625,7 @@ struct mlx5e_rq {
struct {
u16 umem_headroom;
u16 headroom;
u32 frame0_sz;
u8 map_dir; /* dma map direction */
} buff;

View File

@ -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) {

View File

@ -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",

View File

@ -1070,6 +1070,7 @@ 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;
@ -1371,6 +1372,7 @@ 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;