From 2f9d09394d138be99050ad9eabe4d3ff13f79da4 Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Fri, 13 Nov 2020 12:48:30 +0100 Subject: net: mvneta: Add xdp tx return bulking support Convert mvneta driver to xdp_return_frame_bulk APIs. XDP_REDIRECT (upstream codepath): 275Kpps XDP_REDIRECT (upstream codepath + bulking APIs): 284Kpps Co-developed-by: Jesper Dangaard Brouer Signed-off-by: Jesper Dangaard Brouer Signed-off-by: Lorenzo Bianconi Signed-off-by: Daniel Borkmann Acked-by: John Fastabend Link: https://lore.kernel.org/bpf/9af8014006d022fc0fec78cdaa71beb56999750d.1605267335.git.lorenzo@kernel.org --- drivers/net/ethernet/marvell/mvneta.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'drivers') diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index 54b0bf574c05..183530ed4d1d 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -1834,8 +1834,13 @@ static void mvneta_txq_bufs_free(struct mvneta_port *pp, struct netdev_queue *nq, bool napi) { unsigned int bytes_compl = 0, pkts_compl = 0; + struct xdp_frame_bulk bq; int i; + xdp_frame_bulk_init(&bq); + + rcu_read_lock(); /* need for xdp_return_frame_bulk */ + for (i = 0; i < num; i++) { struct mvneta_tx_buf *buf = &txq->buf[txq->txq_get_index]; struct mvneta_tx_desc *tx_desc = txq->descs + @@ -1857,9 +1862,12 @@ static void mvneta_txq_bufs_free(struct mvneta_port *pp, if (napi && buf->type == MVNETA_TYPE_XDP_TX) xdp_return_frame_rx_napi(buf->xdpf); else - xdp_return_frame(buf->xdpf); + xdp_return_frame_bulk(buf->xdpf, &bq); } } + xdp_flush_frame_bulk(&bq); + + rcu_read_unlock(); netdev_tx_completed_queue(nq, pkts_compl, bytes_compl); } -- cgit v1.2.3 From dbef19ccde5d83dd16646532f091b54a67c73cd1 Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Fri, 13 Nov 2020 12:48:31 +0100 Subject: net: mvpp2: Add xdp tx return bulking support Convert mvpp2 driver to xdp_return_frame_bulk APIs. XDP_REDIRECT (upstream codepath): 1.79Mpps XDP_REDIRECT (upstream codepath + bulking APIs): 1.93Mpps Co-developed-by: Jesper Dangaard Brouer Signed-off-by: Jesper Dangaard Brouer Signed-off-by: Lorenzo Bianconi Signed-off-by: Daniel Borkmann Tested-by: Matteo Croce Acked-by: John Fastabend Link: https://lore.kernel.org/bpf/0b38c295e58e8ce251ef6b4e2187a2f457f9f7a3.1605267335.git.lorenzo@kernel.org --- drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'drivers') diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index f6616c8933ca..3069e192d773 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -2440,8 +2440,13 @@ static void mvpp2_txq_bufs_free(struct mvpp2_port *port, struct mvpp2_tx_queue *txq, struct mvpp2_txq_pcpu *txq_pcpu, int num) { + struct xdp_frame_bulk bq; int i; + xdp_frame_bulk_init(&bq); + + rcu_read_lock(); /* need for xdp_return_frame_bulk */ + for (i = 0; i < num; i++) { struct mvpp2_txq_pcpu_buf *tx_buf = txq_pcpu->buffs + txq_pcpu->txq_get_index; @@ -2454,10 +2459,13 @@ static void mvpp2_txq_bufs_free(struct mvpp2_port *port, dev_kfree_skb_any(tx_buf->skb); else if (tx_buf->type == MVPP2_TYPE_XDP_TX || tx_buf->type == MVPP2_TYPE_XDP_NDO) - xdp_return_frame(tx_buf->xdpf); + xdp_return_frame_bulk(tx_buf->xdpf, &bq); mvpp2_txq_inc_get(txq_pcpu); } + xdp_flush_frame_bulk(&bq); + + rcu_read_unlock(); } static inline struct mvpp2_rx_queue *mvpp2_get_rx_queue(struct mvpp2_port *port, -- cgit v1.2.3 From b87c57ae12dbecd50471b437e09e3f7dc916d8bc Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Fri, 13 Nov 2020 12:48:32 +0100 Subject: net: mlx5: Add xdp tx return bulking support Convert mlx5 driver to xdp_return_frame_bulk APIs. XDP_REDIRECT (upstream codepath): 8.9Mpps XDP_REDIRECT (upstream codepath + bulking APIs): 10.2Mpps Co-developed-by: Jesper Dangaard Brouer Signed-off-by: Jesper Dangaard Brouer Signed-off-by: Lorenzo Bianconi Signed-off-by: Daniel Borkmann Tested-by: Jesper Dangaard Brouer Acked-by: John Fastabend Link: https://lore.kernel.org/bpf/250460319fd868b7b5668fc1deca74dd42813a90.1605267335.git.lorenzo@kernel.org --- drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c | 22 ++++++++++++++++++---- 1 file changed, 18 insertions(+), 4 deletions(-) (limited to 'drivers') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c index ae90d533a350..2e3e78b0f333 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c @@ -366,7 +366,8 @@ mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xmit_data *xdptxd, static void mlx5e_free_xdpsq_desc(struct mlx5e_xdpsq *sq, struct mlx5e_xdp_wqe_info *wi, u32 *xsk_frames, - bool recycle) + bool recycle, + struct xdp_frame_bulk *bq) { struct mlx5e_xdp_info_fifo *xdpi_fifo = &sq->db.xdpi_fifo; u16 i; @@ -379,7 +380,7 @@ static void mlx5e_free_xdpsq_desc(struct mlx5e_xdpsq *sq, /* XDP_TX from the XSK RQ and XDP_REDIRECT */ dma_unmap_single(sq->pdev, xdpi.frame.dma_addr, xdpi.frame.xdpf->len, DMA_TO_DEVICE); - xdp_return_frame(xdpi.frame.xdpf); + xdp_return_frame_bulk(xdpi.frame.xdpf, bq); break; case MLX5E_XDP_XMIT_MODE_PAGE: /* XDP_TX from the regular RQ */ @@ -397,12 +398,15 @@ static void mlx5e_free_xdpsq_desc(struct mlx5e_xdpsq *sq, bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq) { + struct xdp_frame_bulk bq; struct mlx5e_xdpsq *sq; struct mlx5_cqe64 *cqe; u32 xsk_frames = 0; u16 sqcc; int i; + xdp_frame_bulk_init(&bq); + sq = container_of(cq, struct mlx5e_xdpsq, cq); if (unlikely(!test_bit(MLX5E_SQ_STATE_ENABLED, &sq->state))) @@ -434,7 +438,7 @@ bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq) sqcc += wi->num_wqebbs; - mlx5e_free_xdpsq_desc(sq, wi, &xsk_frames, true); + mlx5e_free_xdpsq_desc(sq, wi, &xsk_frames, true, &bq); } while (!last_wqe); if (unlikely(get_cqe_opcode(cqe) != MLX5_CQE_REQ)) { @@ -447,6 +451,8 @@ bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq) } } while ((++i < MLX5E_TX_CQ_POLL_BUDGET) && (cqe = mlx5_cqwq_get_cqe(&cq->wq))); + xdp_flush_frame_bulk(&bq); + if (xsk_frames) xsk_tx_completed(sq->xsk_pool, xsk_frames); @@ -463,8 +469,13 @@ bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq) void mlx5e_free_xdpsq_descs(struct mlx5e_xdpsq *sq) { + struct xdp_frame_bulk bq; u32 xsk_frames = 0; + xdp_frame_bulk_init(&bq); + + rcu_read_lock(); /* need for xdp_return_frame_bulk */ + while (sq->cc != sq->pc) { struct mlx5e_xdp_wqe_info *wi; u16 ci; @@ -474,9 +485,12 @@ void mlx5e_free_xdpsq_descs(struct mlx5e_xdpsq *sq) sq->cc += wi->num_wqebbs; - mlx5e_free_xdpsq_desc(sq, wi, &xsk_frames, false); + mlx5e_free_xdpsq_desc(sq, wi, &xsk_frames, false, &bq); } + xdp_flush_frame_bulk(&bq); + rcu_read_unlock(); + if (xsk_frames) xsk_tx_completed(sq->xsk_pool, xsk_frames); } -- cgit v1.2.3