diff options
Diffstat (limited to 'drivers/net')
4 files changed, 55 insertions, 0 deletions
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c index a850141789a0..812a370f6aea 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c @@ -8,6 +8,46 @@ /* RX data path */ +int mlx5e_xsk_alloc_rx_wqes_batched(struct mlx5e_rq *rq, u16 ix, int wqe_bulk) +{ + struct mlx5_wq_cyc *wq = &rq->wqe.wq; + struct xdp_buff **buffs; + u32 contig, alloc; + int i; + + /* mlx5e_init_frags_partition creates a 1:1 mapping between + * rq->wqe.frags and rq->wqe.alloc_units, which allows us to + * allocate XDP buffers straight into alloc_units. + */ + BUILD_BUG_ON(sizeof(rq->wqe.alloc_units[0]) != + sizeof(rq->wqe.alloc_units[0].xsk)); + buffs = (struct xdp_buff **)rq->wqe.alloc_units; + contig = mlx5_wq_cyc_get_size(wq) - ix; + if (wqe_bulk <= contig) { + alloc = xsk_buff_alloc_batch(rq->xsk_pool, buffs + ix, wqe_bulk); + } else { + alloc = xsk_buff_alloc_batch(rq->xsk_pool, buffs + ix, contig); + if (likely(alloc == contig)) + alloc += xsk_buff_alloc_batch(rq->xsk_pool, buffs, wqe_bulk - contig); + } + + for (i = 0; i < alloc; i++) { + int j = mlx5_wq_cyc_ctr2ix(wq, ix + i); + struct mlx5e_wqe_frag_info *frag; + struct mlx5e_rx_wqe_cyc *wqe; + dma_addr_t addr; + + wqe = mlx5_wq_cyc_get_wqe(wq, j); + /* Assumes log_num_frags == 0. */ + frag = &rq->wqe.frags[j]; + + addr = xsk_buff_xdp_get_frame_dma(frag->au->xsk); + wqe->data[0].addr = cpu_to_be64(addr + rq->buff.headroom); + } + + return alloc; +} + int mlx5e_xsk_alloc_rx_wqes(struct mlx5e_rq *rq, u16 ix, int wqe_bulk) { struct mlx5_wq_cyc *wq = &rq->wqe.wq; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.h index acabcee623f9..7898a78237b8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.h @@ -9,6 +9,7 @@ /* RX data path */ +int mlx5e_xsk_alloc_rx_wqes_batched(struct mlx5e_rq *rq, u16 ix, int wqe_bulk); int mlx5e_xsk_alloc_rx_wqes(struct mlx5e_rq *rq, u16 ix, int wqe_bulk); struct sk_buff *mlx5e_xsk_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 2719247b18db..6a0adda03463 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -433,6 +433,13 @@ static void mlx5e_init_frags_partition(struct mlx5e_rq *rq) struct mlx5e_wqe_frag_info *prev = NULL; int i; + if (rq->xsk_pool) { + /* Assumptions used by XSK batched allocator. */ + WARN_ON(rq->wqe.info.num_frags != 1); + WARN_ON(rq->wqe.info.log_num_frags != 0); + WARN_ON(rq->wqe.info.arr[0].frag_stride != PAGE_SIZE); + } + next_frag.au = &rq->wqe.alloc_units[0]; for (i = 0; i < mlx5_wq_cyc_get_size(&rq->wqe.wq); i++) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index 6321eb3fff31..5f411c29157f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -827,7 +827,14 @@ INDIRECT_CALLABLE_SCOPE bool mlx5e_post_rx_wqes(struct mlx5e_rq *rq) if (!rq->xsk_pool) count = mlx5e_alloc_rx_wqes(rq, head, wqe_bulk); + else if (likely(!rq->xsk_pool->dma_need_sync)) + count = mlx5e_xsk_alloc_rx_wqes_batched(rq, head, wqe_bulk); else + /* If dma_need_sync is true, it's more efficient to call + * xsk_buff_alloc in a loop, rather than xsk_buff_alloc_batch, + * because the latter does the same check and returns only one + * frame. + */ count = mlx5e_xsk_alloc_rx_wqes(rq, head, wqe_bulk); mlx5_wq_cyc_push_n(wq, count); |